From bac6eb7235ab2efb4c0391c9572f9fc796aef22b Mon Sep 17 00:00:00 2001
From: Andreas Helbech Kleist <andreaskleist@gmail.com>
Date: Wed, 5 Jul 2023 11:59:22 -0700
Subject: [PATCH 0001/1189] Input: exc3000 - add ACPI support for EXC80H60

EXC80H60 is used in Ambu aBox2 with ACPI _HID "EGA00001".

Snippet of from "apcidump -b; iasl ssdt2.dat" on target:

        Device (TPL2)
        {
            Name (HID2, Zero)
            Name (_HID, "EGA00001")  // _HID: Hardware ID
            Name (_CID, "PNP0C50" /* HID Protocol Device (I2C bus) */)
		// _CID: Compatible ID
            Name (_S0W, 0x04)  // _S0W: S0 Device Wake State
            Name (SBFB, ResourceTemplate ()

Signed-off-by: Andreas Helbech Kleist <andreaskleist@gmail.com>
Link: https://lore.kernel.org/r/20230705091817.1300928-1-andreaskleist@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/exc3000.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/input/touchscreen/exc3000.c b/drivers/input/touchscreen/exc3000.c
index 4af4c1e5d0da..66ed2eaa6dcb 100644
--- a/drivers/input/touchscreen/exc3000.c
+++ b/drivers/input/touchscreen/exc3000.c
@@ -7,6 +7,7 @@
  * minimal implementation based on egalax_ts.c and egalax_i2c.c
  */
 
+#include <linux/acpi.h>
 #include <linux/bitops.h>
 #include <linux/delay.h>
 #include <linux/device.h>
@@ -454,10 +455,19 @@ static const struct of_device_id exc3000_of_match[] = {
 MODULE_DEVICE_TABLE(of, exc3000_of_match);
 #endif
 
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id exc3000_acpi_match[] = {
+	{ "EGA00001", .driver_data = (kernel_ulong_t)&exc3000_info[EETI_EXC80H60] },
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, exc3000_acpi_match);
+#endif
+
 static struct i2c_driver exc3000_driver = {
 	.driver = {
 		.name	= "exc3000",
 		.of_match_table = of_match_ptr(exc3000_of_match),
+		.acpi_match_table = ACPI_PTR(exc3000_acpi_match),
 	},
 	.id_table	= exc3000_id,
 	.probe		= exc3000_probe,

From afbc67a90c7ccef304796af15477b43de5555b07 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 5 Jul 2023 12:26:19 -0700
Subject: [PATCH 0002/1189] Input: cpcap-pwrbutton - remove initial kernel-doc
 notation

Change the beginning "/**" in the file to "/*" since it is not a
kernel-doc comment. This prevents a kernel-doc warning:

drivers/input/misc/cpcap-pwrbutton.c:2: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst
 * CPCAP Power Button Input Driver

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Link: https://lore.kernel.org/r/20230703230005.14877-1-rdunlap@infradead.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/cpcap-pwrbutton.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/input/misc/cpcap-pwrbutton.c b/drivers/input/misc/cpcap-pwrbutton.c
index 879790bbf9fe..5aff5a7d6a35 100644
--- a/drivers/input/misc/cpcap-pwrbutton.c
+++ b/drivers/input/misc/cpcap-pwrbutton.c
@@ -1,4 +1,4 @@
-/**
+/*
  * CPCAP Power Button Input Driver
  *
  * Copyright (C) 2017 Sebastian Reichel <sre@kernel.org>

From 2479191c30fe90c368fd6c8842e9846959466ccd Mon Sep 17 00:00:00 2001
From: Sebastian Reichel <sre@kernel.org>
Date: Wed, 5 Jul 2023 14:49:36 -0700
Subject: [PATCH 0003/1189] Input: cpcap-pwrbutton - replace GPLv2 boilerplate
 with SPDX

Replace the GPLv2 boilerplate text with a nice and short
SPDX header.

Signed-off-by: Sebastian Reichel <sre@kernel.org>
Link: https://lore.kernel.org/r/20230705212231.631525-1-sre@kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/cpcap-pwrbutton.c | 10 +---------
 1 file changed, 1 insertion(+), 9 deletions(-)

diff --git a/drivers/input/misc/cpcap-pwrbutton.c b/drivers/input/misc/cpcap-pwrbutton.c
index 5aff5a7d6a35..85cddb84717a 100644
--- a/drivers/input/misc/cpcap-pwrbutton.c
+++ b/drivers/input/misc/cpcap-pwrbutton.c
@@ -1,16 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * CPCAP Power Button Input Driver
  *
  * Copyright (C) 2017 Sebastian Reichel <sre@kernel.org>
- *
- * This file is subject to the terms and conditions of the GNU General
- * Public License. See the file "COPYING" in the main directory of this
- * archive for more details.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/module.h>

From 650cda2ce25f08e8fae391b3ba6be27e7296c6a5 Mon Sep 17 00:00:00 2001
From: Niklas Schnelle <schnelle@linux.ibm.com>
Date: Wed, 5 Jul 2023 14:56:28 -0700
Subject: [PATCH 0004/1189] Input: gameport - add ISA and HAS_IOPORT
 dependencies

In a future patch HAS_IOPORT=n will result in inb()/outb() and friends
not being declared. As ISA already implies HAS_IOPORT we can simply add
this dependency and guard sections of code using inb()/outb() as
alternative access methods.

Co-developed-by: Arnd Bergmann <arnd@kernel.org>
Signed-off-by: Arnd Bergmann <arnd@kernel.org>
Signed-off-by: Niklas Schnelle <schnelle@linux.ibm.com>
Link: https://lore.kernel.org/r/20230703152355.3897456-2-schnelle@linux.ibm.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/gameport/Kconfig    |  4 +++-
 drivers/input/gameport/gameport.c | 26 +++++++++++++++++++++-----
 2 files changed, 24 insertions(+), 6 deletions(-)

diff --git a/drivers/input/gameport/Kconfig b/drivers/input/gameport/Kconfig
index 5a2c2fb3217d..fe73b26e647a 100644
--- a/drivers/input/gameport/Kconfig
+++ b/drivers/input/gameport/Kconfig
@@ -25,6 +25,7 @@ if GAMEPORT
 
 config GAMEPORT_NS558
 	tristate "Classic ISA and PnP gameport support"
+	depends on ISA
 	help
 	  Say Y here if you have an ISA or PnP gameport.
 
@@ -35,6 +36,7 @@ config GAMEPORT_NS558
 
 config GAMEPORT_L4
 	tristate "PDPI Lightning 4 gamecard support"
+	depends on ISA
 	help
 	  Say Y here if you have a PDPI Lightning 4 gamecard.
 
@@ -53,7 +55,7 @@ config GAMEPORT_EMU10K1
 
 config GAMEPORT_FM801
 	tristate "ForteMedia FM801 gameport support"
-	depends on PCI
+	depends on PCI && HAS_IOPORT
 	help
 	  Say Y here if you have ForteMedia FM801 PCI audio controller
 	  (Abit AU10, Genius Sound Maker, HP Workstation zx2000,
diff --git a/drivers/input/gameport/gameport.c b/drivers/input/gameport/gameport.c
index a1443320b419..34f416a3ebcb 100644
--- a/drivers/input/gameport/gameport.c
+++ b/drivers/input/gameport/gameport.c
@@ -519,12 +519,32 @@ EXPORT_SYMBOL(gameport_set_phys);
 
 static void gameport_default_trigger(struct gameport *gameport)
 {
+#ifdef CONFIG_HAS_IOPORT
 	outb(0xff, gameport->io);
+#endif
 }
 
 static unsigned char gameport_default_read(struct gameport *gameport)
 {
+#ifdef CONFIG_HAS_IOPORT
 	return inb(gameport->io);
+#else
+	return 0xff;
+#endif
+}
+
+static void gameport_setup_default_handlers(struct gameport *gameport)
+{
+	if ((!gameport->trigger || !gameport->read) &&
+	    !IS_ENABLED(CONFIG_HAS_IOPORT))
+		dev_err(&gameport->dev,
+			"I/O port access is required for %s (%s) but is not available\n",
+			gameport->phys, gameport->name);
+
+	if (!gameport->trigger)
+		gameport->trigger = gameport_default_trigger;
+	if (!gameport->read)
+		gameport->read = gameport_default_read;
 }
 
 /*
@@ -545,11 +565,7 @@ static void gameport_init_port(struct gameport *gameport)
 	if (gameport->parent)
 		gameport->dev.parent = &gameport->parent->dev;
 
-	if (!gameport->trigger)
-		gameport->trigger = gameport_default_trigger;
-	if (!gameport->read)
-		gameport->read = gameport_default_read;
-
+	gameport_setup_default_handlers(gameport);
 	INIT_LIST_HEAD(&gameport->node);
 	spin_lock_init(&gameport->timer_lock);
 	timer_setup(&gameport->poll_timer, gameport_run_poll_handler, 0);

From 1680ac7a5ad578d7acf819912557ceea4b4a5a88 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Fri, 7 Jul 2023 16:18:29 -0700
Subject: [PATCH 0005/1189] Input: gameport - use IS_REACHABLE() instead of
 open-coding it

Replace an open-coded preprocessor conditional with an equivalent helper.

Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://lore.kernel.org/r/ZKYLLmsdCH0Gp7TO@google.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 include/linux/gameport.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/gameport.h b/include/linux/gameport.h
index 0a221e768ea4..07e370113b2b 100644
--- a/include/linux/gameport.h
+++ b/include/linux/gameport.h
@@ -63,7 +63,7 @@ struct gameport_driver {
 int gameport_open(struct gameport *gameport, struct gameport_driver *drv, int mode);
 void gameport_close(struct gameport *gameport);
 
-#if defined(CONFIG_GAMEPORT) || (defined(MODULE) && defined(CONFIG_GAMEPORT_MODULE))
+#if IS_REACHABLE(CONFIG_GAMEPORT)
 
 void __gameport_register_port(struct gameport *gameport, struct module *owner);
 /* use a define to avoid include chaining to get THIS_MODULE */

From 05e6329443734a2a0aefb845d74375081d6626b6 Mon Sep 17 00:00:00 2001
From: Vicki Pfau <vi@endrift.com>
Date: Fri, 7 Jul 2023 10:34:41 -0700
Subject: [PATCH 0006/1189] Input: xpad - fix support for some third-party
 controllers

Some third-party controllers, such as the HORPIAD FPS for Nintendo Switch
and Gamesir-G3w, require a specific packet that the first-party XInput
driver sends before it will start sending reports. It's not currently known
what this packet does, but since the first-party driver always sends it's
unlikely that this could cause issues with existing controllers.

Co-authored-by: Andrey Smirnov <andrew.smirnov@gmail.com>
Signed-off-by: Vicki Pfau <vi@endrift.com>
Link: https://lore.kernel.org/r/20230607012812.379640-2-vi@endrift.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/joystick/xpad.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 5d6a25b42bf9..745047215e42 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -264,6 +264,7 @@ static const struct xpad_device {
 	{ 0x0f0d, 0x0067, "HORIPAD ONE", 0, XTYPE_XBOXONE },
 	{ 0x0f0d, 0x0078, "Hori Real Arcade Pro V Kai Xbox One", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOXONE },
 	{ 0x0f0d, 0x00c5, "Hori Fighting Commander ONE", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOXONE },
+	{ 0x0f0d, 0x00dc, "HORIPAD FPS for Nintendo Switch", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 },
 	{ 0x0f30, 0x010b, "Philips Recoil", 0, XTYPE_XBOX },
 	{ 0x0f30, 0x0202, "Joytech Advanced Controller", 0, XTYPE_XBOX },
 	{ 0x0f30, 0x8888, "BigBen XBMiniPad Controller", 0, XTYPE_XBOX },
@@ -1720,6 +1721,27 @@ static int xpad_start_input(struct usb_xpad *xpad)
 			return error;
 		}
 	}
+	if (xpad->xtype == XTYPE_XBOX360) {
+		/*
+		 * Some third-party controllers Xbox 360-style controllers
+		 * require this message to finish initialization.
+		 */
+		u8 dummy[20];
+
+		error = usb_control_msg_recv(xpad->udev, 0,
+					     /* bRequest */ 0x01,
+					     /* bmRequestType */
+					     USB_TYPE_VENDOR | USB_DIR_IN |
+						USB_RECIP_INTERFACE,
+					     /* wValue */ 0x100,
+					     /* wIndex */ 0x00,
+					     dummy, sizeof(dummy),
+					     25, GFP_KERNEL);
+		if (error)
+			dev_warn(&xpad->dev->dev,
+				 "unable to receive magic message: %d\n",
+				 error);
+	}
 
 	return 0;
 }

From 1dfd41115f186bf0c7a9b3f0dd39a0985d828d65 Mon Sep 17 00:00:00 2001
From: Sam Lantinga <slouken@libsdl.org>
Date: Fri, 7 Jul 2023 15:10:59 -0700
Subject: [PATCH 0007/1189] Input: xpad - add GameSir VID for Xbox One
 controllers

Signed-off-by: Sam Lantinga <slouken@libsdl.org>
Signed-off-by: Vicki Pfau <vi@endrift.com>
Link: https://lore.kernel.org/r/20230607012812.379640-3-vi@endrift.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/joystick/xpad.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 745047215e42..e0b6edb35b59 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -501,6 +501,7 @@ static const struct usb_device_id xpad_table[] = {
 	XPAD_XBOX360_VENDOR(0x2f24),		/* GameSir controllers */
 	XPAD_XBOX360_VENDOR(0x31e3),		/* Wooting Keyboards */
 	XPAD_XBOX360_VENDOR(0x3285),		/* Nacon GC-100 */
+	XPAD_XBOXONE_VENDOR(0x3537),		/* GameSir Controllers */
 	{ }
 };
 

From 854d2233de0ac8ad37b71ec3698946054b22104c Mon Sep 17 00:00:00 2001
From: Jonathan Frederick <doublej472@gmail.com>
Date: Fri, 7 Jul 2023 15:11:33 -0700
Subject: [PATCH 0008/1189] Input: xpad - add GameSir T4 Kaleid Controller
 support

Add VID and PID to the xpad_device table to allow driver
to use the GameSir T4 Kaleid Controller, which is
XTYPE_XBOX360 compatible in xinput mode.

Signed-off-by: Jonathan Frederick <doublej472@gmail.com>
Link: https://lore.kernel.org/r/ZKeKSbP3faIPv5jB@dbj-hp-flip
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/joystick/xpad.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index e0b6edb35b59..c4bc0958471d 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -367,6 +367,7 @@ static const struct xpad_device {
 	{ 0x31e3, 0x1300, "Wooting 60HE (AVR)", 0, XTYPE_XBOX360 },
 	{ 0x31e3, 0x1310, "Wooting 60HE (ARM)", 0, XTYPE_XBOX360 },
 	{ 0x3285, 0x0607, "Nacon GC-100", 0, XTYPE_XBOX360 },
+	{ 0x3537, 0x1004, "GameSir T4 Kaleid", 0, XTYPE_XBOX360 },
 	{ 0x3767, 0x0101, "Fanatec Speedster 3 Forceshock Wheel", 0, XTYPE_XBOX },
 	{ 0xffff, 0xffff, "Chinese-made Xbox Controller", 0, XTYPE_XBOX },
 	{ 0x0000, 0x0000, "Generic X-Box pad", 0, XTYPE_UNKNOWN }
@@ -501,6 +502,7 @@ static const struct usb_device_id xpad_table[] = {
 	XPAD_XBOX360_VENDOR(0x2f24),		/* GameSir controllers */
 	XPAD_XBOX360_VENDOR(0x31e3),		/* Wooting Keyboards */
 	XPAD_XBOX360_VENDOR(0x3285),		/* Nacon GC-100 */
+	XPAD_XBOX360_VENDOR(0x3537),		/* GameSir Controllers */
 	XPAD_XBOXONE_VENDOR(0x3537),		/* GameSir Controllers */
 	{ }
 };

From ff785255699c78c1b2ca0b21f2ae4a3ea4163bb0 Mon Sep 17 00:00:00 2001
From: Mike Looijmans <mike.looijmans@topic.nl>
Date: Fri, 7 Jul 2023 16:28:07 -0700
Subject: [PATCH 0009/1189] dt-bindings: input: exc3000: support power supply
 regulators

Add power supply regulator support to the exc3000 devices.

Signed-off-by: Mike Looijmans <mike.looijmans@topic.nl>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20230707131042.10795-1-mike.looijmans@topic.nl
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 .../devicetree/bindings/input/touchscreen/eeti,exc3000.yaml     | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/input/touchscreen/eeti,exc3000.yaml b/Documentation/devicetree/bindings/input/touchscreen/eeti,exc3000.yaml
index 007adbc89c14..9dc25d30a0a8 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/eeti,exc3000.yaml
+++ b/Documentation/devicetree/bindings/input/touchscreen/eeti,exc3000.yaml
@@ -24,6 +24,8 @@ properties:
     maxItems: 1
   reset-gpios:
     maxItems: 1
+  vdd-supply:
+    description: Power supply regulator for the chip
   touchscreen-size-x: true
   touchscreen-size-y: true
   touchscreen-inverted-x: true

From 0d384e5959dde12717419a3fd77ee62cc10f069f Mon Sep 17 00:00:00 2001
From: Mike Looijmans <mike.looijmans@topic.nl>
Date: Fri, 7 Jul 2023 16:29:15 -0700
Subject: [PATCH 0010/1189] Input: exc3000 - support power supply regulators

Add power supply regulator support to the exc3000 devices.

Signed-off-by: Mike Looijmans <mike.looijmans@topic.nl>
Link: https://lore.kernel.org/r/20230707131042.10795-2-mike.looijmans@topic.nl
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/exc3000.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/input/touchscreen/exc3000.c b/drivers/input/touchscreen/exc3000.c
index 4af4c1e5d0da..e3f6d21b3c1b 100644
--- a/drivers/input/touchscreen/exc3000.c
+++ b/drivers/input/touchscreen/exc3000.c
@@ -18,6 +18,7 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/regulator/consumer.h>
 #include <linux/sizes.h>
 #include <linux/timer.h>
 #include <asm/unaligned.h>
@@ -360,6 +361,12 @@ static int exc3000_probe(struct i2c_client *client)
 	if (IS_ERR(data->reset))
 		return PTR_ERR(data->reset);
 
+	/* For proper reset sequence, enable power while reset asserted */
+	error = devm_regulator_get_enable(&client->dev, "vdd");
+	if (error && error != -ENODEV)
+		return dev_err_probe(&client->dev, error,
+				     "failed to request vdd regulator\n");
+
 	if (data->reset) {
 		msleep(EXC3000_RESET_MS);
 		gpiod_set_value_cansleep(data->reset, 0);

From caec3d4416a2fbd7399556ba366da4d8fc05d9f5 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 25 Jun 2023 18:27:54 +0200
Subject: [PATCH 0011/1189] Input: gpio_keys_polled - simplify with
 dev_err_probe()

Common pattern of handling deferred probe can be simplified with
dev_err_probe().  Less code and also it prints the error value.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20230625162817.100397-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/gpio_keys_polled.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/input/keyboard/gpio_keys_polled.c b/drivers/input/keyboard/gpio_keys_polled.c
index c3937d2fc744..ba00ecfbd343 100644
--- a/drivers/input/keyboard/gpio_keys_polled.c
+++ b/drivers/input/keyboard/gpio_keys_polled.c
@@ -299,13 +299,9 @@ static int gpio_keys_polled_probe(struct platform_device *pdev)
 							     NULL, GPIOD_IN,
 							     button->desc);
 			if (IS_ERR(bdata->gpiod)) {
-				error = PTR_ERR(bdata->gpiod);
-				if (error != -EPROBE_DEFER)
-					dev_err(dev,
-						"failed to get gpio: %d\n",
-						error);
 				fwnode_handle_put(child);
-				return error;
+				return dev_err_probe(dev, PTR_ERR(bdata->gpiod),
+						     "failed to get gpio\n");
 			}
 		} else if (gpio_is_valid(button->gpio)) {
 			/*

From c4834f4ad7fdc9002e7d3424bd7aed7a63f070be Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 25 Jun 2023 18:27:55 +0200
Subject: [PATCH 0012/1189] Input: gpio-vibra - simplify with dev_err_probe()

Common pattern of handling deferred probe can be simplified with
dev_err_probe().  Less code and also it prints the error value.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20230625162817.100397-3-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/gpio-vibra.c | 20 ++++++--------------
 drivers/input/misc/pwm-beeper.c | 19 +++++--------------
 2 files changed, 11 insertions(+), 28 deletions(-)

diff --git a/drivers/input/misc/gpio-vibra.c b/drivers/input/misc/gpio-vibra.c
index 134a1309ba92..c1c3ba5960dd 100644
--- a/drivers/input/misc/gpio-vibra.c
+++ b/drivers/input/misc/gpio-vibra.c
@@ -113,22 +113,14 @@ static int gpio_vibrator_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	vibrator->vcc = devm_regulator_get(&pdev->dev, "vcc");
-	err = PTR_ERR_OR_ZERO(vibrator->vcc);
-	if (err) {
-		if (err != -EPROBE_DEFER)
-			dev_err(&pdev->dev, "Failed to request regulator: %d\n",
-				err);
-		return err;
-	}
+	if (IS_ERR(vibrator->vcc))
+		return dev_err_probe(&pdev->dev, PTR_ERR(vibrator->vcc),
+				     "Failed to request regulator\n");
 
 	vibrator->gpio = devm_gpiod_get(&pdev->dev, "enable", GPIOD_OUT_LOW);
-	err = PTR_ERR_OR_ZERO(vibrator->gpio);
-	if (err) {
-		if (err != -EPROBE_DEFER)
-			dev_err(&pdev->dev, "Failed to request main gpio: %d\n",
-				err);
-		return err;
-	}
+	if (IS_ERR(vibrator->gpio))
+		return dev_err_probe(&pdev->dev, PTR_ERR(vibrator->gpio),
+				     "Failed to request main gpio\n");
 
 	INIT_WORK(&vibrator->play_work, gpio_vibrator_play_work);
 
diff --git a/drivers/input/misc/pwm-beeper.c b/drivers/input/misc/pwm-beeper.c
index 3cf1812384e6..1e731d8397c6 100644
--- a/drivers/input/misc/pwm-beeper.c
+++ b/drivers/input/misc/pwm-beeper.c
@@ -132,13 +132,8 @@ static int pwm_beeper_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	beeper->pwm = devm_pwm_get(dev, NULL);
-	if (IS_ERR(beeper->pwm)) {
-		error = PTR_ERR(beeper->pwm);
-		if (error != -EPROBE_DEFER)
-			dev_err(dev, "Failed to request PWM device: %d\n",
-				error);
-		return error;
-	}
+	if (IS_ERR(beeper->pwm))
+		return dev_err_probe(dev, PTR_ERR(beeper->pwm), "Failed to request PWM device\n");
 
 	/* Sync up PWM state and ensure it is off. */
 	pwm_init_state(beeper->pwm, &state);
@@ -151,13 +146,9 @@ static int pwm_beeper_probe(struct platform_device *pdev)
 	}
 
 	beeper->amplifier = devm_regulator_get(dev, "amp");
-	if (IS_ERR(beeper->amplifier)) {
-		error = PTR_ERR(beeper->amplifier);
-		if (error != -EPROBE_DEFER)
-			dev_err(dev, "Failed to get 'amp' regulator: %d\n",
-				error);
-		return error;
-	}
+	if (IS_ERR(beeper->amplifier))
+		return dev_err_probe(dev, PTR_ERR(beeper->amplifier),
+				     "Failed to get 'amp' regulator\n");
 
 	INIT_WORK(&beeper->work, pwm_beeper_work);
 

From a07e68dff58bd536f9e909b007875726eade5c0e Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 25 Jun 2023 18:27:56 +0200
Subject: [PATCH 0013/1189] Input: pwm-vibra - simplify with dev_err_probe()

Common pattern of handling deferred probe can be simplified with
dev_err_probe().  Less code and also it prints the error value.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20230625162817.100397-4-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/pwm-vibra.c | 30 +++++++++---------------------
 1 file changed, 9 insertions(+), 21 deletions(-)

diff --git a/drivers/input/misc/pwm-vibra.c b/drivers/input/misc/pwm-vibra.c
index 2ba035299db8..a3cde30ee8d2 100644
--- a/drivers/input/misc/pwm-vibra.c
+++ b/drivers/input/misc/pwm-vibra.c
@@ -140,32 +140,20 @@ static int pwm_vibrator_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	vibrator->vcc = devm_regulator_get(&pdev->dev, "vcc");
-	err = PTR_ERR_OR_ZERO(vibrator->vcc);
-	if (err) {
-		if (err != -EPROBE_DEFER)
-			dev_err(&pdev->dev, "Failed to request regulator: %d\n",
-				err);
-		return err;
-	}
+	if (IS_ERR(vibrator->vcc))
+		return dev_err_probe(&pdev->dev, PTR_ERR(vibrator->vcc),
+				     "Failed to request regulator\n");
 
 	vibrator->enable_gpio = devm_gpiod_get_optional(&pdev->dev, "enable",
 							GPIOD_OUT_LOW);
-	err = PTR_ERR_OR_ZERO(vibrator->enable_gpio);
-	if (err) {
-		if (err != -EPROBE_DEFER)
-			dev_err(&pdev->dev, "Failed to request enable gpio: %d\n",
-				err);
-		return err;
-	}
+	if (IS_ERR(vibrator->enable_gpio))
+		return dev_err_probe(&pdev->dev, PTR_ERR(vibrator->enable_gpio),
+				     "Failed to request enable gpio\n");
 
 	vibrator->pwm = devm_pwm_get(&pdev->dev, "enable");
-	err = PTR_ERR_OR_ZERO(vibrator->pwm);
-	if (err) {
-		if (err != -EPROBE_DEFER)
-			dev_err(&pdev->dev, "Failed to request main pwm: %d\n",
-				err);
-		return err;
-	}
+	if (IS_ERR(vibrator->pwm))
+		return dev_err_probe(&pdev->dev, PTR_ERR(vibrator->pwm),
+				     "Failed to request main pwm\n");
 
 	INIT_WORK(&vibrator->play_work, pwm_vibrator_play_work);
 

From 1e402a15bc00201c1068596445ebfe98d60d1c58 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 25 Jun 2023 18:27:57 +0200
Subject: [PATCH 0014/1189] Input: rotary_encoder - simplify with
 dev_err_probe()

Common pattern of handling deferred probe can be simplified with
dev_err_probe().  Less code and also it prints the error value.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20230625162817.100397-5-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/rotary_encoder.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/input/misc/rotary_encoder.c b/drivers/input/misc/rotary_encoder.c
index 22ec62083065..fb3a34f8eccd 100644
--- a/drivers/input/misc/rotary_encoder.c
+++ b/drivers/input/misc/rotary_encoder.c
@@ -236,12 +236,8 @@ static int rotary_encoder_probe(struct platform_device *pdev)
 		device_property_read_bool(dev, "rotary-encoder,relative-axis");
 
 	encoder->gpios = devm_gpiod_get_array(dev, NULL, GPIOD_IN);
-	if (IS_ERR(encoder->gpios)) {
-		err = PTR_ERR(encoder->gpios);
-		if (err != -EPROBE_DEFER)
-			dev_err(dev, "unable to get gpios: %d\n", err);
-		return err;
-	}
+	if (IS_ERR(encoder->gpios))
+		return dev_err_probe(dev, PTR_ERR(encoder->gpios), "unable to get gpios\n");
 	if (encoder->gpios->ndescs < 2) {
 		dev_err(dev, "not enough gpios found\n");
 		return -EINVAL;

From 50653e8fada2f92c07559e129199daaa3f760d00 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 25 Jun 2023 18:27:58 +0200
Subject: [PATCH 0015/1189] Input: elan_i2c - simplify with dev_err_probe()

Common pattern of handling deferred probe can be simplified with
dev_err_probe().  Less code and also it prints the error value.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20230625162817.100397-6-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/mouse/elan_i2c_core.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c
index 0cff742302a9..148a601396f9 100644
--- a/drivers/input/mouse/elan_i2c_core.c
+++ b/drivers/input/mouse/elan_i2c_core.c
@@ -1221,13 +1221,8 @@ static int elan_probe(struct i2c_client *client)
 	mutex_init(&data->sysfs_mutex);
 
 	data->vcc = devm_regulator_get(dev, "vcc");
-	if (IS_ERR(data->vcc)) {
-		error = PTR_ERR(data->vcc);
-		if (error != -EPROBE_DEFER)
-			dev_err(dev, "Failed to get 'vcc' regulator: %d\n",
-				error);
-		return error;
-	}
+	if (IS_ERR(data->vcc))
+		return dev_err_probe(dev, PTR_ERR(data->vcc), "Failed to get 'vcc' regulator\n");
 
 	error = regulator_enable(data->vcc);
 	if (error) {

From 2886c5b97c8f753eb4aff618ae78832718835151 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 25 Jun 2023 18:27:59 +0200
Subject: [PATCH 0016/1189] Input: bu21013_ts - simplify with dev_err_probe()

Common pattern of handling deferred probe can be simplified with
dev_err_probe().  Less code and also it prints the error value.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20230625162817.100397-7-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/bu21013_ts.c | 17 ++++++-----------
 1 file changed, 6 insertions(+), 11 deletions(-)

diff --git a/drivers/input/touchscreen/bu21013_ts.c b/drivers/input/touchscreen/bu21013_ts.c
index 85332cfaa29d..f811677a59f7 100644
--- a/drivers/input/touchscreen/bu21013_ts.c
+++ b/drivers/input/touchscreen/bu21013_ts.c
@@ -495,12 +495,10 @@ static int bu21013_probe(struct i2c_client *client)
 
 	/* Named "CS" on the chip, DT binding is "reset" */
 	ts->cs_gpiod = devm_gpiod_get(&client->dev, "reset", GPIOD_OUT_HIGH);
-	error = PTR_ERR_OR_ZERO(ts->cs_gpiod);
-	if (error) {
-		if (error != -EPROBE_DEFER)
-			dev_err(&client->dev, "failed to get CS GPIO\n");
-		return error;
-	}
+	if (IS_ERR(ts->cs_gpiod))
+		return dev_err_probe(&client->dev, PTR_ERR(ts->cs_gpiod),
+				     "failed to get CS GPIO\n");
+
 	gpiod_set_consumer_name(ts->cs_gpiod, "BU21013 CS");
 
 	error = devm_add_action_or_reset(&client->dev,
@@ -515,11 +513,8 @@ static int bu21013_probe(struct i2c_client *client)
 	ts->int_gpiod = devm_gpiod_get_optional(&client->dev,
 						"touch", GPIOD_IN);
 	error = PTR_ERR_OR_ZERO(ts->int_gpiod);
-	if (error) {
-		if (error != -EPROBE_DEFER)
-			dev_err(&client->dev, "failed to get INT GPIO\n");
-		return error;
-	}
+	if (error)
+		return dev_err_probe(&client->dev, error, "failed to get INT GPIO\n");
 
 	if (ts->int_gpiod)
 		gpiod_set_consumer_name(ts->int_gpiod, "BU21013 INT");

From 64eb0f741ea2f4b73bcf30d66cf7d1c16593f581 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 25 Jun 2023 18:28:00 +0200
Subject: [PATCH 0017/1189] Input: bu21029_ts - simplify with dev_err_probe()

Common pattern of handling deferred probe can be simplified with
dev_err_probe().  Less code and also it prints the error value.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20230625162817.100397-8-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/bu21029_ts.c | 20 ++++++--------------
 1 file changed, 6 insertions(+), 14 deletions(-)

diff --git a/drivers/input/touchscreen/bu21029_ts.c b/drivers/input/touchscreen/bu21029_ts.c
index c8126d2efe95..3d81ebe66b66 100644
--- a/drivers/input/touchscreen/bu21029_ts.c
+++ b/drivers/input/touchscreen/bu21029_ts.c
@@ -359,23 +359,15 @@ static int bu21029_probe(struct i2c_client *client)
 	}
 
 	bu21029->vdd = devm_regulator_get(&client->dev, "vdd");
-	if (IS_ERR(bu21029->vdd)) {
-		error = PTR_ERR(bu21029->vdd);
-		if (error != -EPROBE_DEFER)
-			dev_err(&client->dev,
-				"failed to acquire 'vdd' supply: %d\n", error);
-		return error;
-	}
+	if (IS_ERR(bu21029->vdd))
+		return dev_err_probe(&client->dev, PTR_ERR(bu21029->vdd),
+				     "failed to acquire 'vdd' supply\n");
 
 	bu21029->reset_gpios = devm_gpiod_get_optional(&client->dev,
 						       "reset", GPIOD_OUT_HIGH);
-	if (IS_ERR(bu21029->reset_gpios)) {
-		error = PTR_ERR(bu21029->reset_gpios);
-		if (error != -EPROBE_DEFER)
-			dev_err(&client->dev,
-				"failed to acquire 'reset' gpio: %d\n", error);
-		return error;
-	}
+	if (IS_ERR(bu21029->reset_gpios))
+		return dev_err_probe(&client->dev, PTR_ERR(bu21029->reset_gpios),
+				     "failed to acquire 'reset' gpio\n");
 
 	in_dev = devm_input_allocate_device(&client->dev);
 	if (!in_dev) {

From 0d9025a46b2f218c52f2216afabc24537b1e5187 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 25 Jun 2023 18:28:01 +0200
Subject: [PATCH 0018/1189] Input: chipone_icn8318 - simplify with
 dev_err_probe()

Common pattern of handling deferred probe can be simplified with
dev_err_probe().  Less code and also it prints the error value.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20230625162817.100397-9-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/chipone_icn8318.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/input/touchscreen/chipone_icn8318.c b/drivers/input/touchscreen/chipone_icn8318.c
index 9fbeaf17f00b..d6876d10b252 100644
--- a/drivers/input/touchscreen/chipone_icn8318.c
+++ b/drivers/input/touchscreen/chipone_icn8318.c
@@ -191,12 +191,8 @@ static int icn8318_probe(struct i2c_client *client)
 		return -ENOMEM;
 
 	data->wake_gpio = devm_gpiod_get(dev, "wake", GPIOD_OUT_LOW);
-	if (IS_ERR(data->wake_gpio)) {
-		error = PTR_ERR(data->wake_gpio);
-		if (error != -EPROBE_DEFER)
-			dev_err(dev, "Error getting wake gpio: %d\n", error);
-		return error;
-	}
+	if (IS_ERR(data->wake_gpio))
+		return dev_err_probe(dev, PTR_ERR(data->wake_gpio), "Error getting wake gpio\n");
 
 	input = devm_input_allocate_device(dev);
 	if (!input)

From 8d3b0460e8ef68f893d9f1f6f5da37d67be33b89 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 25 Jun 2023 18:28:02 +0200
Subject: [PATCH 0019/1189] Input: cy8ctma140 - simplify with dev_err_probe()

Common pattern of handling deferred probe can be simplified with
dev_err_probe().  Less code and also it prints the error value.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20230625162817.100397-10-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/cy8ctma140.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/input/touchscreen/cy8ctma140.c b/drivers/input/touchscreen/cy8ctma140.c
index 967ecde23e83..ea3895167b82 100644
--- a/drivers/input/touchscreen/cy8ctma140.c
+++ b/drivers/input/touchscreen/cy8ctma140.c
@@ -258,12 +258,8 @@ static int cy8ctma140_probe(struct i2c_client *client)
 	ts->regulators[1].supply = "vdd";
 	error = devm_regulator_bulk_get(dev, ARRAY_SIZE(ts->regulators),
 				      ts->regulators);
-	if (error) {
-		if (error != -EPROBE_DEFER)
-			dev_err(dev, "Failed to get regulators %d\n",
-				error);
-		return error;
-	}
+	if (error)
+		return dev_err_probe(dev, error, "Failed to get regulators\n");
 
 	error = cy8ctma140_power_up(ts);
 	if (error)

From 14e5f4db20096e0be30b8a567e92b726f4d86ac0 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 25 Jun 2023 18:28:03 +0200
Subject: [PATCH 0020/1189] Input: edf-ft5x06 - simplify with dev_err_probe()

Common pattern of handling deferred probe can be simplified with
dev_err_probe().  Less code and also it prints the error value.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20230625162817.100397-11-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/edt-ft5x06.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c
index 795c7dad22bf..457d53337fbb 100644
--- a/drivers/input/touchscreen/edt-ft5x06.c
+++ b/drivers/input/touchscreen/edt-ft5x06.c
@@ -1168,13 +1168,9 @@ static int edt_ft5x06_ts_probe(struct i2c_client *client)
 	tsdata->max_support_points = chip_data->max_support_points;
 
 	tsdata->vcc = devm_regulator_get(&client->dev, "vcc");
-	if (IS_ERR(tsdata->vcc)) {
-		error = PTR_ERR(tsdata->vcc);
-		if (error != -EPROBE_DEFER)
-			dev_err(&client->dev,
-				"failed to request regulator: %d\n", error);
-		return error;
-	}
+	if (IS_ERR(tsdata->vcc))
+		return dev_err_probe(&client->dev, PTR_ERR(tsdata->vcc),
+				     "failed to request regulator\n");
 
 	tsdata->iovcc = devm_regulator_get(&client->dev, "iovcc");
 	if (IS_ERR(tsdata->iovcc)) {

From d9efc285f75e7f6028ff3b87f0169a0decfdc36b Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 25 Jun 2023 18:28:04 +0200
Subject: [PATCH 0021/1189] Input: ektf2127 - simplify with dev_err_probe()

Common pattern of handling deferred probe can be simplified with
dev_err_probe().  Less code and also it prints the error value.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20230625162817.100397-12-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/ektf2127.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/input/touchscreen/ektf2127.c b/drivers/input/touchscreen/ektf2127.c
index fd8724a3c19f..cc3103b9cbfb 100644
--- a/drivers/input/touchscreen/ektf2127.c
+++ b/drivers/input/touchscreen/ektf2127.c
@@ -264,12 +264,8 @@ static int ektf2127_probe(struct i2c_client *client)
 
 	/* This requests the gpio *and* turns on the touchscreen controller */
 	ts->power_gpios = devm_gpiod_get(dev, "power", GPIOD_OUT_HIGH);
-	if (IS_ERR(ts->power_gpios)) {
-		error = PTR_ERR(ts->power_gpios);
-		if (error != -EPROBE_DEFER)
-			dev_err(dev, "Error getting power gpio: %d\n", error);
-		return error;
-	}
+	if (IS_ERR(ts->power_gpios))
+		return dev_err_probe(dev, PTR_ERR(ts->power_gpios), "Error getting power gpio\n");
 
 	input = devm_input_allocate_device(dev);
 	if (!input)

From e89f0de5da36ff28182cba576649d893e2776916 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 25 Jun 2023 18:28:05 +0200
Subject: [PATCH 0022/1189] Input: elants_i2c - simplify with dev_err_probe()

Common pattern of handling deferred probe can be simplified with
dev_err_probe().  Less code and also it prints the error value.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20230625162817.100397-13-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/elants_i2c.c | 22 ++++++----------------
 1 file changed, 6 insertions(+), 16 deletions(-)

diff --git a/drivers/input/touchscreen/elants_i2c.c b/drivers/input/touchscreen/elants_i2c.c
index 2da1db64126d..a1af3de9f310 100644
--- a/drivers/input/touchscreen/elants_i2c.c
+++ b/drivers/input/touchscreen/elants_i2c.c
@@ -1438,24 +1438,14 @@ static int elants_i2c_probe(struct i2c_client *client)
 	i2c_set_clientdata(client, ts);
 
 	ts->vcc33 = devm_regulator_get(&client->dev, "vcc33");
-	if (IS_ERR(ts->vcc33)) {
-		error = PTR_ERR(ts->vcc33);
-		if (error != -EPROBE_DEFER)
-			dev_err(&client->dev,
-				"Failed to get 'vcc33' regulator: %d\n",
-				error);
-		return error;
-	}
+	if (IS_ERR(ts->vcc33))
+		return dev_err_probe(&client->dev, PTR_ERR(ts->vcc33),
+				     "Failed to get 'vcc33' regulator\n");
 
 	ts->vccio = devm_regulator_get(&client->dev, "vccio");
-	if (IS_ERR(ts->vccio)) {
-		error = PTR_ERR(ts->vccio);
-		if (error != -EPROBE_DEFER)
-			dev_err(&client->dev,
-				"Failed to get 'vccio' regulator: %d\n",
-				error);
-		return error;
-	}
+	if (IS_ERR(ts->vccio))
+		return dev_err_probe(&client->dev, PTR_ERR(ts->vccio),
+				     "Failed to get 'vccio' regulator\n");
 
 	ts->reset_gpio = devm_gpiod_get(&client->dev, "reset", GPIOD_OUT_HIGH);
 	if (IS_ERR(ts->reset_gpio)) {

From bf2ae3897f7165e6ff0f5cfded7211cf08d5d855 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 25 Jun 2023 18:28:06 +0200
Subject: [PATCH 0023/1189] Input: goodix - simplify with dev_err_probe()

Common pattern of handling deferred probe can be simplified with
dev_err_probe().  Less code and also it prints the error value.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20230625162817.100397-14-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/goodix.c | 40 ++++++++----------------------
 1 file changed, 11 insertions(+), 29 deletions(-)

diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c
index f6beef523140..d88e1222dd93 100644
--- a/drivers/input/touchscreen/goodix.c
+++ b/drivers/input/touchscreen/goodix.c
@@ -927,7 +927,6 @@ static int goodix_add_acpi_gpio_mappings(struct goodix_ts_data *ts)
  */
 static int goodix_get_gpio_config(struct goodix_ts_data *ts)
 {
-	int error;
 	struct device *dev;
 	struct gpio_desc *gpiod;
 	bool added_acpi_mappings = false;
@@ -943,33 +942,20 @@ static int goodix_get_gpio_config(struct goodix_ts_data *ts)
 	ts->gpiod_rst_flags = GPIOD_IN;
 
 	ts->avdd28 = devm_regulator_get(dev, "AVDD28");
-	if (IS_ERR(ts->avdd28)) {
-		error = PTR_ERR(ts->avdd28);
-		if (error != -EPROBE_DEFER)
-			dev_err(dev,
-				"Failed to get AVDD28 regulator: %d\n", error);
-		return error;
-	}
+	if (IS_ERR(ts->avdd28))
+		return dev_err_probe(dev, PTR_ERR(ts->avdd28), "Failed to get AVDD28 regulator\n");
 
 	ts->vddio = devm_regulator_get(dev, "VDDIO");
-	if (IS_ERR(ts->vddio)) {
-		error = PTR_ERR(ts->vddio);
-		if (error != -EPROBE_DEFER)
-			dev_err(dev,
-				"Failed to get VDDIO regulator: %d\n", error);
-		return error;
-	}
+	if (IS_ERR(ts->vddio))
+		return dev_err_probe(dev, PTR_ERR(ts->vddio), "Failed to get VDDIO regulator\n");
 
 retry_get_irq_gpio:
 	/* Get the interrupt GPIO pin number */
 	gpiod = devm_gpiod_get_optional(dev, GOODIX_GPIO_INT_NAME, GPIOD_IN);
-	if (IS_ERR(gpiod)) {
-		error = PTR_ERR(gpiod);
-		if (error != -EPROBE_DEFER)
-			dev_err(dev, "Failed to get %s GPIO: %d\n",
-				GOODIX_GPIO_INT_NAME, error);
-		return error;
-	}
+	if (IS_ERR(gpiod))
+		return dev_err_probe(dev, PTR_ERR(gpiod), "Failed to get %s GPIO\n",
+				     GOODIX_GPIO_INT_NAME);
+
 	if (!gpiod && has_acpi_companion(dev) && !added_acpi_mappings) {
 		added_acpi_mappings = true;
 		if (goodix_add_acpi_gpio_mappings(ts) == 0)
@@ -980,13 +966,9 @@ retry_get_irq_gpio:
 
 	/* Get the reset line GPIO pin number */
 	gpiod = devm_gpiod_get_optional(dev, GOODIX_GPIO_RST_NAME, ts->gpiod_rst_flags);
-	if (IS_ERR(gpiod)) {
-		error = PTR_ERR(gpiod);
-		if (error != -EPROBE_DEFER)
-			dev_err(dev, "Failed to get %s GPIO: %d\n",
-				GOODIX_GPIO_RST_NAME, error);
-		return error;
-	}
+	if (IS_ERR(gpiod))
+		return dev_err_probe(dev, PTR_ERR(gpiod), "Failed to get %s GPIO\n",
+				     GOODIX_GPIO_RST_NAME);
 
 	ts->gpiod_rst = gpiod;
 

From 10ba628ee0af65796acce5f888598e42f5bca309 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 25 Jun 2023 18:28:07 +0200
Subject: [PATCH 0024/1189] Input: melfas_mip4 - simplify with dev_err_probe()

Common pattern of handling deferred probe can be simplified with
dev_err_probe().  Less code and also it prints the error value.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20230625162817.100397-15-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/melfas_mip4.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/drivers/input/touchscreen/melfas_mip4.c b/drivers/input/touchscreen/melfas_mip4.c
index 32896e5085bd..2ac4483fbc25 100644
--- a/drivers/input/touchscreen/melfas_mip4.c
+++ b/drivers/input/touchscreen/melfas_mip4.c
@@ -1451,13 +1451,8 @@ static int mip4_probe(struct i2c_client *client)
 
 	ts->gpio_ce = devm_gpiod_get_optional(&client->dev,
 					      "ce", GPIOD_OUT_LOW);
-	if (IS_ERR(ts->gpio_ce)) {
-		error = PTR_ERR(ts->gpio_ce);
-		if (error != -EPROBE_DEFER)
-			dev_err(&client->dev,
-				"Failed to get gpio: %d\n", error);
-		return error;
-	}
+	if (IS_ERR(ts->gpio_ce))
+		return dev_err_probe(&client->dev, PTR_ERR(ts->gpio_ce), "Failed to get gpio\n");
 
 	error = mip4_power_on(ts);
 	if (error)

From e32825c47042d4e727b867bb98d679bb5cc74f87 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 25 Jun 2023 18:28:08 +0200
Subject: [PATCH 0025/1189] Input: pixcir_i2c_ts - simplify with
 dev_err_probe()

Common pattern of handling deferred probe can be simplified with
dev_err_probe().  Less code and also it prints the error value.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20230625162817.100397-16-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/pixcir_i2c_ts.c | 38 +++++++----------------
 1 file changed, 12 insertions(+), 26 deletions(-)

diff --git a/drivers/input/touchscreen/pixcir_i2c_ts.c b/drivers/input/touchscreen/pixcir_i2c_ts.c
index 554e179c2e48..0b4576091dac 100644
--- a/drivers/input/touchscreen/pixcir_i2c_ts.c
+++ b/drivers/input/touchscreen/pixcir_i2c_ts.c
@@ -515,41 +515,27 @@ static int pixcir_i2c_ts_probe(struct i2c_client *client)
 	input_set_drvdata(input, tsdata);
 
 	tsdata->gpio_attb = devm_gpiod_get(dev, "attb", GPIOD_IN);
-	if (IS_ERR(tsdata->gpio_attb)) {
-		error = PTR_ERR(tsdata->gpio_attb);
-		if (error != -EPROBE_DEFER)
-			dev_err(dev, "Failed to request ATTB gpio: %d\n",
-				error);
-		return error;
-	}
+	if (IS_ERR(tsdata->gpio_attb))
+		return dev_err_probe(dev, PTR_ERR(tsdata->gpio_attb),
+				     "Failed to request ATTB gpio\n");
 
 	tsdata->gpio_reset = devm_gpiod_get_optional(dev, "reset",
 						     GPIOD_OUT_LOW);
-	if (IS_ERR(tsdata->gpio_reset)) {
-		error = PTR_ERR(tsdata->gpio_reset);
-		if (error != -EPROBE_DEFER)
-			dev_err(dev, "Failed to request RESET gpio: %d\n",
-				error);
-		return error;
-	}
+	if (IS_ERR(tsdata->gpio_reset))
+		return dev_err_probe(dev, PTR_ERR(tsdata->gpio_reset),
+				     "Failed to request RESET gpio\n");
 
 	tsdata->gpio_wake = devm_gpiod_get_optional(dev, "wake",
 						    GPIOD_OUT_HIGH);
-	if (IS_ERR(tsdata->gpio_wake)) {
-		error = PTR_ERR(tsdata->gpio_wake);
-		if (error != -EPROBE_DEFER)
-			dev_err(dev, "Failed to get wake gpio: %d\n", error);
-		return error;
-	}
+	if (IS_ERR(tsdata->gpio_wake))
+		return dev_err_probe(dev, PTR_ERR(tsdata->gpio_wake),
+				     "Failed to get wake gpio\n");
 
 	tsdata->gpio_enable = devm_gpiod_get_optional(dev, "enable",
 						      GPIOD_OUT_HIGH);
-	if (IS_ERR(tsdata->gpio_enable)) {
-		error = PTR_ERR(tsdata->gpio_enable);
-		if (error != -EPROBE_DEFER)
-			dev_err(dev, "Failed to get enable gpio: %d\n", error);
-		return error;
-	}
+	if (IS_ERR(tsdata->gpio_enable))
+		return dev_err_probe(dev, PTR_ERR(tsdata->gpio_enable),
+				     "Failed to get enable gpio\n");
 
 	if (tsdata->gpio_enable)
 		msleep(100);

From ca0d9997f5437ddb754b8743ff15d853d474371e Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 25 Jun 2023 18:28:09 +0200
Subject: [PATCH 0026/1189] Input: raydium_i2c_ts - simplify with
 dev_err_probe()

Common pattern of handling deferred probe can be simplified with
dev_err_probe().  Less code and also it prints the error value.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20230625162817.100397-17-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/raydium_i2c_ts.c | 30 +++++++---------------
 1 file changed, 9 insertions(+), 21 deletions(-)

diff --git a/drivers/input/touchscreen/raydium_i2c_ts.c b/drivers/input/touchscreen/raydium_i2c_ts.c
index 76e7d62d5870..78dd3059d585 100644
--- a/drivers/input/touchscreen/raydium_i2c_ts.c
+++ b/drivers/input/touchscreen/raydium_i2c_ts.c
@@ -1087,32 +1087,20 @@ static int raydium_i2c_probe(struct i2c_client *client)
 	i2c_set_clientdata(client, ts);
 
 	ts->avdd = devm_regulator_get(&client->dev, "avdd");
-	if (IS_ERR(ts->avdd)) {
-		error = PTR_ERR(ts->avdd);
-		if (error != -EPROBE_DEFER)
-			dev_err(&client->dev,
-				"Failed to get 'avdd' regulator: %d\n", error);
-		return error;
-	}
+	if (IS_ERR(ts->avdd))
+		return dev_err_probe(&client->dev, PTR_ERR(ts->avdd),
+				     "Failed to get 'avdd' regulator\n");
 
 	ts->vccio = devm_regulator_get(&client->dev, "vccio");
-	if (IS_ERR(ts->vccio)) {
-		error = PTR_ERR(ts->vccio);
-		if (error != -EPROBE_DEFER)
-			dev_err(&client->dev,
-				"Failed to get 'vccio' regulator: %d\n", error);
-		return error;
-	}
+	if (IS_ERR(ts->vccio))
+		return dev_err_probe(&client->dev, PTR_ERR(ts->vccio),
+				     "Failed to get 'vccio' regulator\n");
 
 	ts->reset_gpio = devm_gpiod_get_optional(&client->dev, "reset",
 						 GPIOD_OUT_LOW);
-	if (IS_ERR(ts->reset_gpio)) {
-		error = PTR_ERR(ts->reset_gpio);
-		if (error != -EPROBE_DEFER)
-			dev_err(&client->dev,
-				"failed to get reset gpio: %d\n", error);
-		return error;
-	}
+	if (IS_ERR(ts->reset_gpio))
+		return dev_err_probe(&client->dev, PTR_ERR(ts->reset_gpio),
+				     "Failed to get reset gpio\n");
 
 	error = raydium_i2c_power_on(ts);
 	if (error)

From 17d981fa707ef6f212dda17d1ec64a4a360c91a7 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 25 Jun 2023 18:28:10 +0200
Subject: [PATCH 0027/1189] Input: resistive-adc-touch - simplify with
 dev_err_probe()

Common pattern of handling deferred probe can be simplified with
dev_err_probe().  Less code and also it prints the error value.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20230625162817.100397-18-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/resistive-adc-touch.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/input/touchscreen/resistive-adc-touch.c b/drivers/input/touchscreen/resistive-adc-touch.c
index 6f754a8d30b1..7e761ec73273 100644
--- a/drivers/input/touchscreen/resistive-adc-touch.c
+++ b/drivers/input/touchscreen/resistive-adc-touch.c
@@ -210,12 +210,8 @@ static int grts_probe(struct platform_device *pdev)
 
 	/* get the channels from IIO device */
 	st->iio_chans = devm_iio_channel_get_all(dev);
-	if (IS_ERR(st->iio_chans)) {
-		error = PTR_ERR(st->iio_chans);
-		if (error != -EPROBE_DEFER)
-			dev_err(dev, "can't get iio channels.\n");
-		return error;
-	}
+	if (IS_ERR(st->iio_chans))
+		return dev_err_probe(dev, PTR_ERR(st->iio_chans), "can't get iio channels\n");
 
 	if (!device_property_present(dev, "io-channel-names"))
 		return -ENODEV;

From 21142c1cb29048f536700b833be1b2806fff3ef7 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 25 Jun 2023 18:28:11 +0200
Subject: [PATCH 0028/1189] Input: silead - simplify with dev_err_probe()

Common pattern of handling deferred probe can be simplified with
dev_err_probe().  Less code and also it prints the error value.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20230625162817.100397-19-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/silead.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/input/touchscreen/silead.c b/drivers/input/touchscreen/silead.c
index 9e28f962e059..62f562ad5026 100644
--- a/drivers/input/touchscreen/silead.c
+++ b/drivers/input/touchscreen/silead.c
@@ -706,11 +706,9 @@ static int silead_ts_probe(struct i2c_client *client)
 
 	/* Power GPIO pin */
 	data->gpio_power = devm_gpiod_get_optional(dev, "power", GPIOD_OUT_LOW);
-	if (IS_ERR(data->gpio_power)) {
-		if (PTR_ERR(data->gpio_power) != -EPROBE_DEFER)
-			dev_err(dev, "Shutdown GPIO request failed\n");
-		return PTR_ERR(data->gpio_power);
-	}
+	if (IS_ERR(data->gpio_power))
+		return dev_err_probe(dev, PTR_ERR(data->gpio_power),
+				     "Shutdown GPIO request failed\n");
 
 	error = silead_ts_setup(client);
 	if (error)

From d3aeb44cc6b21944c31b07728516924e9cb10825 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 25 Jun 2023 18:28:12 +0200
Subject: [PATCH 0029/1189] Input: sis_i2c - simplify with dev_err_probe()

Common pattern of handling deferred probe can be simplified with
dev_err_probe().  Less code and also it prints the error value.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20230625162817.100397-20-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/sis_i2c.c | 20 ++++++--------------
 1 file changed, 6 insertions(+), 14 deletions(-)

diff --git a/drivers/input/touchscreen/sis_i2c.c b/drivers/input/touchscreen/sis_i2c.c
index 426564d0fc39..ed56cb546f39 100644
--- a/drivers/input/touchscreen/sis_i2c.c
+++ b/drivers/input/touchscreen/sis_i2c.c
@@ -310,23 +310,15 @@ static int sis_ts_probe(struct i2c_client *client)
 
 	ts->attn_gpio = devm_gpiod_get_optional(&client->dev,
 						"attn", GPIOD_IN);
-	if (IS_ERR(ts->attn_gpio)) {
-		error = PTR_ERR(ts->attn_gpio);
-		if (error != -EPROBE_DEFER)
-			dev_err(&client->dev,
-				"Failed to get attention GPIO: %d\n", error);
-		return error;
-	}
+	if (IS_ERR(ts->attn_gpio))
+		return dev_err_probe(&client->dev, PTR_ERR(ts->attn_gpio),
+				     "Failed to get attention GPIO\n");
 
 	ts->reset_gpio = devm_gpiod_get_optional(&client->dev,
 						 "reset", GPIOD_OUT_LOW);
-	if (IS_ERR(ts->reset_gpio)) {
-		error = PTR_ERR(ts->reset_gpio);
-		if (error != -EPROBE_DEFER)
-			dev_err(&client->dev,
-				"Failed to get reset GPIO: %d\n", error);
-		return error;
-	}
+	if (IS_ERR(ts->reset_gpio))
+		return dev_err_probe(&client->dev, PTR_ERR(ts->reset_gpio),
+				     "Failed to get reset GPIO\n");
 
 	sis_ts_reset(ts);
 

From d08149c13aa27bd2c0884915dea0eb1a171e1c2e Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 25 Jun 2023 18:28:13 +0200
Subject: [PATCH 0030/1189] Input: surface3_spi - simplify with dev_err_probe()

Common pattern of handling deferred probe can be simplified with
dev_err_probe().  Less code and also it prints the error value.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20230625162817.100397-21-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/surface3_spi.c | 13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)

diff --git a/drivers/input/touchscreen/surface3_spi.c b/drivers/input/touchscreen/surface3_spi.c
index 31d140248f2e..7efbcd0fde4f 100644
--- a/drivers/input/touchscreen/surface3_spi.c
+++ b/drivers/input/touchscreen/surface3_spi.c
@@ -221,7 +221,6 @@ static void surface3_spi_power(struct surface3_ts_data *data, bool on)
  */
 static int surface3_spi_get_gpio_config(struct surface3_ts_data *data)
 {
-	int error;
 	struct device *dev;
 	struct gpio_desc *gpiod;
 	int i;
@@ -231,15 +230,9 @@ static int surface3_spi_get_gpio_config(struct surface3_ts_data *data)
 	/* Get the reset lines GPIO pin number */
 	for (i = 0; i < 2; i++) {
 		gpiod = devm_gpiod_get_index(dev, NULL, i, GPIOD_OUT_LOW);
-		if (IS_ERR(gpiod)) {
-			error = PTR_ERR(gpiod);
-			if (error != -EPROBE_DEFER)
-				dev_err(dev,
-					"Failed to get power GPIO %d: %d\n",
-					i,
-					error);
-			return error;
-		}
+		if (IS_ERR(gpiod))
+			return dev_err_probe(dev, PTR_ERR(gpiod),
+					     "Failed to get power GPIO %d\n", i);
 
 		data->gpiod_rst[i] = gpiod;
 	}

From 337ac36c3bc0be71e73322cbbc0d6a8b8a2c05f6 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 25 Jun 2023 18:28:14 +0200
Subject: [PATCH 0031/1189] Input: sx8643 - simplify with dev_err_probe()

Common pattern of handling deferred probe can be simplified with
dev_err_probe().  Less code and also it prints the error value.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20230625162817.100397-22-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/sx8654.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/drivers/input/touchscreen/sx8654.c b/drivers/input/touchscreen/sx8654.c
index 0293c493bc79..f5c5881cef6b 100644
--- a/drivers/input/touchscreen/sx8654.c
+++ b/drivers/input/touchscreen/sx8654.c
@@ -323,13 +323,9 @@ static int sx8654_probe(struct i2c_client *client)
 
 	sx8654->gpio_reset = devm_gpiod_get_optional(&client->dev, "reset",
 						     GPIOD_OUT_HIGH);
-	if (IS_ERR(sx8654->gpio_reset)) {
-		error = PTR_ERR(sx8654->gpio_reset);
-		if (error != -EPROBE_DEFER)
-			dev_err(&client->dev, "unable to get reset-gpio: %d\n",
-				error);
-		return error;
-	}
+	if (IS_ERR(sx8654->gpio_reset))
+		return dev_err_probe(&client->dev, PTR_ERR(sx8654->gpio_reset),
+				     "unable to get reset-gpio\n");
 	dev_dbg(&client->dev, "got GPIO reset pin\n");
 
 	sx8654->data = device_get_match_data(&client->dev);

From a2c795b696b20ebc56462a2fbbc0d612ef265389 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 25 Jun 2023 18:28:15 +0200
Subject: [PATCH 0032/1189] Input: bcm-keypad - simplify with dev_err_probe()

Common pattern of handling deferred probe can be simplified with
dev_err_probe() and devm_clk_get_optional().  Less code and the error
value gets printed.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20230625162817.100397-23-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/bcm-keypad.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/drivers/input/keyboard/bcm-keypad.c b/drivers/input/keyboard/bcm-keypad.c
index 56a919ec23b5..05b09066df84 100644
--- a/drivers/input/keyboard/bcm-keypad.c
+++ b/drivers/input/keyboard/bcm-keypad.c
@@ -365,17 +365,11 @@ static int bcm_kp_probe(struct platform_device *pdev)
 		return PTR_ERR(kp->base);
 
 	/* Enable clock */
-	kp->clk = devm_clk_get(&pdev->dev, "peri_clk");
+	kp->clk = devm_clk_get_optional(&pdev->dev, "peri_clk");
 	if (IS_ERR(kp->clk)) {
-		error = PTR_ERR(kp->clk);
-		if (error != -ENOENT) {
-			if (error != -EPROBE_DEFER)
-				dev_err(&pdev->dev, "Failed to get clock\n");
-			return error;
-		}
-		dev_dbg(&pdev->dev,
-			"No clock specified. Assuming it's enabled\n");
-		kp->clk = NULL;
+		return dev_err_probe(&pdev->dev, error, "Failed to get clock\n");
+	} else if (!kp->clk) {
+		dev_dbg(&pdev->dev, "No clock specified. Assuming it's enabled\n");
 	} else {
 		unsigned int desired_rate;
 		long actual_rate;

From 2bdb1a9a8a1775cdf15bd1299da8fd7e9b5f10a3 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 25 Jun 2023 18:28:16 +0200
Subject: [PATCH 0033/1189] Input: bu21013_ts - use local 'client->dev'
 variable in probe()

'dev' is shorter and simpler than '&client->dev' and in few cases it
allows to skip line wrapping. Probe function uses '&client->dev' a lot,
so this improves readability slightly.

Suggested-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20230625162817.100397-24-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/bu21013_ts.c | 61 ++++++++++++--------------
 1 file changed, 28 insertions(+), 33 deletions(-)

diff --git a/drivers/input/touchscreen/bu21013_ts.c b/drivers/input/touchscreen/bu21013_ts.c
index f811677a59f7..652439a79e21 100644
--- a/drivers/input/touchscreen/bu21013_ts.c
+++ b/drivers/input/touchscreen/bu21013_ts.c
@@ -410,31 +410,32 @@ static int bu21013_probe(struct i2c_client *client)
 	struct input_dev *in_dev;
 	struct input_absinfo *info;
 	u32 max_x = 0, max_y = 0;
+	struct device *dev = &client->dev;
 	int error;
 
 	if (!i2c_check_functionality(client->adapter,
 				     I2C_FUNC_SMBUS_BYTE_DATA)) {
-		dev_err(&client->dev, "i2c smbus byte data not supported\n");
+		dev_err(dev, "i2c smbus byte data not supported\n");
 		return -EIO;
 	}
 
 	if (!client->irq) {
-		dev_err(&client->dev, "No IRQ set up\n");
+		dev_err(dev, "No IRQ set up\n");
 		return -EINVAL;
 	}
 
-	ts = devm_kzalloc(&client->dev, sizeof(*ts), GFP_KERNEL);
+	ts = devm_kzalloc(dev, sizeof(*ts), GFP_KERNEL);
 	if (!ts)
 		return -ENOMEM;
 
 	ts->client = client;
 
-	ts->x_flip = device_property_read_bool(&client->dev, "rohm,flip-x");
-	ts->y_flip = device_property_read_bool(&client->dev, "rohm,flip-y");
+	ts->x_flip = device_property_read_bool(dev, "rohm,flip-x");
+	ts->y_flip = device_property_read_bool(dev, "rohm,flip-y");
 
-	in_dev = devm_input_allocate_device(&client->dev);
+	in_dev = devm_input_allocate_device(dev);
 	if (!in_dev) {
-		dev_err(&client->dev, "device memory alloc failed\n");
+		dev_err(dev, "device memory alloc failed\n");
 		return -ENOMEM;
 	}
 	ts->in_dev = in_dev;
@@ -444,8 +445,8 @@ static int bu21013_probe(struct i2c_client *client)
 	in_dev->name = DRIVER_TP;
 	in_dev->id.bustype = BUS_I2C;
 
-	device_property_read_u32(&client->dev, "rohm,touch-max-x", &max_x);
-	device_property_read_u32(&client->dev, "rohm,touch-max-y", &max_y);
+	device_property_read_u32(dev, "rohm,touch-max-x", &max_x);
+	device_property_read_u32(dev, "rohm,touch-max-y", &max_y);
 
 	input_set_abs_params(in_dev, ABS_MT_POSITION_X, 0, max_x, 0, 0);
 	input_set_abs_params(in_dev, ABS_MT_POSITION_Y, 0, max_y, 0, 0);
@@ -454,14 +455,14 @@ static int bu21013_probe(struct i2c_client *client)
 
 	/* Adjust for the legacy "flip" properties, if present */
 	if (!ts->props.invert_x &&
-	    device_property_read_bool(&client->dev, "rohm,flip-x")) {
+	    device_property_read_bool(dev, "rohm,flip-x")) {
 		info = &in_dev->absinfo[ABS_MT_POSITION_X];
 		info->maximum -= info->minimum;
 		info->minimum = 0;
 	}
 
 	if (!ts->props.invert_y &&
-	    device_property_read_bool(&client->dev, "rohm,flip-y")) {
+	    device_property_read_bool(dev, "rohm,flip-y")) {
 		info = &in_dev->absinfo[ABS_MT_POSITION_Y];
 		info->maximum -= info->minimum;
 		info->minimum = 0;
@@ -471,50 +472,46 @@ static int bu21013_probe(struct i2c_client *client)
 				    INPUT_MT_DIRECT | INPUT_MT_TRACK |
 					INPUT_MT_DROP_UNUSED);
 	if (error) {
-		dev_err(&client->dev, "failed to initialize MT slots");
+		dev_err(dev, "failed to initialize MT slots");
 		return error;
 	}
 
-	ts->regulator = devm_regulator_get(&client->dev, "avdd");
+	ts->regulator = devm_regulator_get(dev, "avdd");
 	if (IS_ERR(ts->regulator)) {
-		dev_err(&client->dev, "regulator_get failed\n");
+		dev_err(dev, "regulator_get failed\n");
 		return PTR_ERR(ts->regulator);
 	}
 
 	error = regulator_enable(ts->regulator);
 	if (error) {
-		dev_err(&client->dev, "regulator enable failed\n");
+		dev_err(dev, "regulator enable failed\n");
 		return error;
 	}
 
-	error = devm_add_action_or_reset(&client->dev, bu21013_power_off, ts);
+	error = devm_add_action_or_reset(dev, bu21013_power_off, ts);
 	if (error) {
-		dev_err(&client->dev, "failed to install power off handler\n");
+		dev_err(dev, "failed to install power off handler\n");
 		return error;
 	}
 
 	/* Named "CS" on the chip, DT binding is "reset" */
-	ts->cs_gpiod = devm_gpiod_get(&client->dev, "reset", GPIOD_OUT_HIGH);
+	ts->cs_gpiod = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH);
 	if (IS_ERR(ts->cs_gpiod))
-		return dev_err_probe(&client->dev, PTR_ERR(ts->cs_gpiod),
-				     "failed to get CS GPIO\n");
+		return dev_err_probe(dev, PTR_ERR(ts->cs_gpiod), "failed to get CS GPIO\n");
 
 	gpiod_set_consumer_name(ts->cs_gpiod, "BU21013 CS");
 
-	error = devm_add_action_or_reset(&client->dev,
-					 bu21013_disable_chip, ts);
+	error = devm_add_action_or_reset(dev, bu21013_disable_chip, ts);
 	if (error) {
-		dev_err(&client->dev,
-			"failed to install chip disable handler\n");
+		dev_err(dev, "failed to install chip disable handler\n");
 		return error;
 	}
 
 	/* Named "INT" on the chip, DT binding is "touch" */
-	ts->int_gpiod = devm_gpiod_get_optional(&client->dev,
-						"touch", GPIOD_IN);
+	ts->int_gpiod = devm_gpiod_get_optional(dev, "touch", GPIOD_IN);
 	error = PTR_ERR_OR_ZERO(ts->int_gpiod);
 	if (error)
-		return dev_err_probe(&client->dev, error, "failed to get INT GPIO\n");
+		return dev_err_probe(dev, error, "failed to get INT GPIO\n");
 
 	if (ts->int_gpiod)
 		gpiod_set_consumer_name(ts->int_gpiod, "BU21013 INT");
@@ -522,22 +519,20 @@ static int bu21013_probe(struct i2c_client *client)
 	/* configure the touch panel controller */
 	error = bu21013_init_chip(ts);
 	if (error) {
-		dev_err(&client->dev, "error in bu21013 config\n");
+		dev_err(dev, "error in bu21013 config\n");
 		return error;
 	}
 
-	error = devm_request_threaded_irq(&client->dev, client->irq,
-					  NULL, bu21013_gpio_irq,
+	error = devm_request_threaded_irq(dev, client->irq, NULL, bu21013_gpio_irq,
 					  IRQF_ONESHOT, DRIVER_TP, ts);
 	if (error) {
-		dev_err(&client->dev, "request irq %d failed\n",
-			client->irq);
+		dev_err(dev, "request irq %d failed\n", client->irq);
 		return error;
 	}
 
 	error = input_register_device(in_dev);
 	if (error) {
-		dev_err(&client->dev, "failed to register input device\n");
+		dev_err(dev, "failed to register input device\n");
 		return error;
 	}
 

From 59a51ba6e946a2a02865285eb3e10bb607033dd3 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 25 Jun 2023 18:28:17 +0200
Subject: [PATCH 0034/1189] Input: bu21029_ts - use local 'client->dev'
 variable in probe()

'dev' is shorter and simpler than '&client->dev' and in few cases it
allows to skip line wrapping. Probe function uses '&client->dev' a lot,
so this improves readability slightly.

Suggested-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20230625162817.100397-25-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/bu21029_ts.c | 35 +++++++++++---------------
 1 file changed, 15 insertions(+), 20 deletions(-)

diff --git a/drivers/input/touchscreen/bu21029_ts.c b/drivers/input/touchscreen/bu21029_ts.c
index 3d81ebe66b66..e1dfbd92ab64 100644
--- a/drivers/input/touchscreen/bu21029_ts.c
+++ b/drivers/input/touchscreen/bu21029_ts.c
@@ -333,6 +333,7 @@ static void bu21029_stop_chip(struct input_dev *dev)
 
 static int bu21029_probe(struct i2c_client *client)
 {
+	struct device *dev = &client->dev;
 	struct bu21029_ts_data *bu21029;
 	struct input_dev *in_dev;
 	int error;
@@ -341,37 +342,33 @@ static int bu21029_probe(struct i2c_client *client)
 				     I2C_FUNC_SMBUS_WRITE_BYTE |
 				     I2C_FUNC_SMBUS_WRITE_BYTE_DATA |
 				     I2C_FUNC_SMBUS_READ_I2C_BLOCK)) {
-		dev_err(&client->dev,
-			"i2c functionality support is not sufficient\n");
+		dev_err(dev, "i2c functionality support is not sufficient\n");
 		return -EIO;
 	}
 
-	bu21029 = devm_kzalloc(&client->dev, sizeof(*bu21029), GFP_KERNEL);
+	bu21029 = devm_kzalloc(dev, sizeof(*bu21029), GFP_KERNEL);
 	if (!bu21029)
 		return -ENOMEM;
 
-	error = device_property_read_u32(&client->dev, "rohm,x-plate-ohms",
-					 &bu21029->x_plate_ohms);
+	error = device_property_read_u32(dev, "rohm,x-plate-ohms", &bu21029->x_plate_ohms);
 	if (error) {
-		dev_err(&client->dev,
-			"invalid 'x-plate-ohms' supplied: %d\n", error);
+		dev_err(dev, "invalid 'x-plate-ohms' supplied: %d\n", error);
 		return error;
 	}
 
-	bu21029->vdd = devm_regulator_get(&client->dev, "vdd");
+	bu21029->vdd = devm_regulator_get(dev, "vdd");
 	if (IS_ERR(bu21029->vdd))
-		return dev_err_probe(&client->dev, PTR_ERR(bu21029->vdd),
+		return dev_err_probe(dev, PTR_ERR(bu21029->vdd),
 				     "failed to acquire 'vdd' supply\n");
 
-	bu21029->reset_gpios = devm_gpiod_get_optional(&client->dev,
-						       "reset", GPIOD_OUT_HIGH);
+	bu21029->reset_gpios = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
 	if (IS_ERR(bu21029->reset_gpios))
-		return dev_err_probe(&client->dev, PTR_ERR(bu21029->reset_gpios),
+		return dev_err_probe(dev, PTR_ERR(bu21029->reset_gpios),
 				     "failed to acquire 'reset' gpio\n");
 
-	in_dev = devm_input_allocate_device(&client->dev);
+	in_dev = devm_input_allocate_device(dev);
 	if (!in_dev) {
-		dev_err(&client->dev, "unable to allocate input device\n");
+		dev_err(dev, "unable to allocate input device\n");
 		return -ENOMEM;
 	}
 
@@ -392,20 +389,18 @@ static int bu21029_probe(struct i2c_client *client)
 
 	input_set_drvdata(in_dev, bu21029);
 
-	error = devm_request_threaded_irq(&client->dev, client->irq,
-					  NULL, bu21029_touch_soft_irq,
+	error = devm_request_threaded_irq(dev, client->irq, NULL,
+					  bu21029_touch_soft_irq,
 					  IRQF_ONESHOT | IRQF_NO_AUTOEN,
 					  DRIVER_NAME, bu21029);
 	if (error) {
-		dev_err(&client->dev,
-			"unable to request touch irq: %d\n", error);
+		dev_err(dev, "unable to request touch irq: %d\n", error);
 		return error;
 	}
 
 	error = input_register_device(in_dev);
 	if (error) {
-		dev_err(&client->dev,
-			"unable to register input device: %d\n", error);
+		dev_err(dev, "unable to register input device: %d\n", error);
 		return error;
 	}
 

From 3ce6e06202b49802e8e0c4c8858717f534a308d0 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sat, 17 Jun 2023 09:05:42 +0200
Subject: [PATCH 0035/1189] Input: pinephone-keyboard - use
 devm_regulator_get_enable()

Use devm_regulator_get_enable() instead of hand writing it. It saves some
line of code.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/78d7a4719ed7c372a7aa62afb66d4f1561799b5f.1686985515.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/pinephone-keyboard.c | 20 +-------------------
 1 file changed, 1 insertion(+), 19 deletions(-)

diff --git a/drivers/input/keyboard/pinephone-keyboard.c b/drivers/input/keyboard/pinephone-keyboard.c
index 038ff3549a7a..147b1f288a33 100644
--- a/drivers/input/keyboard/pinephone-keyboard.c
+++ b/drivers/input/keyboard/pinephone-keyboard.c
@@ -318,40 +318,22 @@ static void ppkb_close(struct input_dev *input)
 	ppkb_set_scan(client, false);
 }
 
-static void ppkb_regulator_disable(void *regulator)
-{
-	regulator_disable(regulator);
-}
-
 static int ppkb_probe(struct i2c_client *client)
 {
 	struct device *dev = &client->dev;
 	unsigned int phys_rows, phys_cols;
 	struct pinephone_keyboard *ppkb;
-	struct regulator *vbat_supply;
 	u8 info[PPKB_MATRIX_SIZE + 1];
 	struct device_node *i2c_bus;
 	int ret;
 	int error;
 
-	vbat_supply = devm_regulator_get(dev, "vbat");
-	error = PTR_ERR_OR_ZERO(vbat_supply);
+	error = devm_regulator_get_enable(dev, "vbat");
 	if (error) {
 		dev_err(dev, "Failed to get VBAT supply: %d\n", error);
 		return error;
 	}
 
-	error = regulator_enable(vbat_supply);
-	if (error) {
-		dev_err(dev, "Failed to enable VBAT: %d\n", error);
-		return error;
-	}
-
-	error = devm_add_action_or_reset(dev, ppkb_regulator_disable,
-					 vbat_supply);
-	if (error)
-		return error;
-
 	ret = i2c_smbus_read_i2c_block_data(client, 0, sizeof(info), info);
 	if (ret != sizeof(info)) {
 		error = ret < 0 ? ret : -EIO;

From 26ab82616eb51bd236f12d6427d05d18c573f6e2 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sat, 17 Jun 2023 09:12:03 +0200
Subject: [PATCH 0036/1189] Input: adp5588-keys - use
 devm_regulator_get_enable()

Use devm_regulator_get_enable() instead of hand writing it. It saves some
line of code.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Acked-by: Michael Hennerich <michael.hennerich@analog.com>
Link: https://lore.kernel.org/r/af343b5b0d740cc9f8863264c30e3da4215721d7.1686985911.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/adp5588-keys.c | 17 +----------------
 1 file changed, 1 insertion(+), 16 deletions(-)

diff --git a/drivers/input/keyboard/adp5588-keys.c b/drivers/input/keyboard/adp5588-keys.c
index 896a5a989ddc..61e8e43e9c2b 100644
--- a/drivers/input/keyboard/adp5588-keys.c
+++ b/drivers/input/keyboard/adp5588-keys.c
@@ -713,17 +713,11 @@ static int adp5588_fw_parse(struct adp5588_kpad *kpad)
 	return 0;
 }
 
-static void adp5588_disable_regulator(void *reg)
-{
-	regulator_disable(reg);
-}
-
 static int adp5588_probe(struct i2c_client *client)
 {
 	struct adp5588_kpad *kpad;
 	struct input_dev *input;
 	struct gpio_desc *gpio;
-	struct regulator *vcc;
 	unsigned int revid;
 	int ret;
 	int error;
@@ -749,16 +743,7 @@ static int adp5588_probe(struct i2c_client *client)
 	if (error)
 		return error;
 
-	vcc = devm_regulator_get(&client->dev, "vcc");
-	if (IS_ERR(vcc))
-		return PTR_ERR(vcc);
-
-	error = regulator_enable(vcc);
-	if (error)
-		return error;
-
-	error = devm_add_action_or_reset(&client->dev,
-					 adp5588_disable_regulator, vcc);
+	error = devm_regulator_get_enable(&client->dev, "vcc");
 	if (error)
 		return error;
 

From 685b37704ce68924fa823d1cc37e512555526e06 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Wed, 21 Jun 2023 11:32:45 +0200
Subject: [PATCH 0037/1189] dt-bindings: input: touchscreen: edt-ft5x06: Add
 'threshold' property

Add a new property 'threshold' to the edt-ft5x06 touchscreen binding.
This property allows setting the "click"-threshold in the range from 0
to 255. This change addresses the following dtbs_check warning:
imx6dl-lanmcu.dtb: touchscreen@38: 'threshold' does not match any of the regexes: 'pinctrl-[0-9]+'

Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230621093245.78130-6-o.rempel@pengutronix.de
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 .../devicetree/bindings/input/touchscreen/edt-ft5x06.yaml   | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml b/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml
index ef4c841387bd..f2808cb4d99d 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml
+++ b/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml
@@ -93,6 +93,12 @@ properties:
     minimum: 1
     maximum: 255
 
+  threshold:
+    description: Allows setting the  "click"-threshold in the range from 0 to 255.
+    $ref: /schemas/types.yaml#/definitions/uint32
+    minimum: 0
+    maximum: 255
+
   touchscreen-size-x: true
   touchscreen-size-y: true
   touchscreen-fuzz-x: true

From 85429376884f239f854e9b5c6d9defaa1de4619e Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Mon, 10 Jul 2023 14:36:32 +0200
Subject: [PATCH 0038/1189] Input: novatek-nvt-ts - fix input_register_device()
 failure error message

Fix input_register_device() failure logging "failed to request irq"
as error message.

Reviewed-by: Peter Hutterer <peter.hutterer@who-t.net>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20230710123633.323937-1-hdegoede@redhat.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/novatek-nvt-ts.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/input/touchscreen/novatek-nvt-ts.c b/drivers/input/touchscreen/novatek-nvt-ts.c
index 7f7d879aac6d..047e371448ce 100644
--- a/drivers/input/touchscreen/novatek-nvt-ts.c
+++ b/drivers/input/touchscreen/novatek-nvt-ts.c
@@ -272,7 +272,7 @@ static int nvt_ts_probe(struct i2c_client *client)
 
 	error = input_register_device(input);
 	if (error) {
-		dev_err(dev, "failed to request irq: %d\n", error);
+		dev_err(dev, "failed to register input device: %d\n", error);
 		return error;
 	}
 

From 7249bdbd5eae873557abcee25f30a8b0d2fc4b3f Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Mon, 10 Jul 2023 14:36:33 +0200
Subject: [PATCH 0039/1189] Input: novatek-nvt-ts - add touchscreen model
 number to description

A phoronix forum member actual found documentation on what the model
number for the touchscreen controller on the Acer Iconia One 7 B1-750 is.

Update the driver's description to include this.

Link: https://www.phoronix.com/forums/forum/hardware/general-hardware/1382535-10-years-later-linux-getting-a-touchscreen-driver-for-a-once-popular-tablet?p=1384707#post1384707
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20230710123633.323937-2-hdegoede@redhat.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/Kconfig          | 4 ++--
 drivers/input/touchscreen/novatek-nvt-ts.c | 8 +++-----
 2 files changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig
index c2cbd332af1d..fb4c23917b69 100644
--- a/drivers/input/touchscreen/Kconfig
+++ b/drivers/input/touchscreen/Kconfig
@@ -655,10 +655,10 @@ config TOUCHSCREEN_MTOUCH
 	  module will be called mtouch.
 
 config TOUCHSCREEN_NOVATEK_NVT_TS
-	tristate "Novatek NVT-ts touchscreen support"
+	tristate "Novatek NT11205 touchscreen support"
 	depends on I2C
 	help
-	  Say Y here if you have a Novatek NVT-ts touchscreen.
+	  Say Y here if you have a Novatek NT11205 touchscreen.
 	  If unsure, say N.
 
 	  To compile this driver as a module, choose M here: the
diff --git a/drivers/input/touchscreen/novatek-nvt-ts.c b/drivers/input/touchscreen/novatek-nvt-ts.c
index 047e371448ce..1a797e410a3f 100644
--- a/drivers/input/touchscreen/novatek-nvt-ts.c
+++ b/drivers/input/touchscreen/novatek-nvt-ts.c
@@ -1,9 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Driver for Novatek i2c touchscreen controller as found on
- * the Acer Iconia One 7 B1-750 tablet. The Touchscreen controller
- * model-number is unknown. Android calls this a "NVT-ts" touchscreen,
- * but that may apply to other Novatek controller models too.
+ * Driver for Novatek NT11205 i2c touchscreen controller as found
+ * on the Acer Iconia One 7 B1-750 tablet.
  *
  * Copyright (c) 2023 Hans de Goede <hdegoede@redhat.com>
  */
@@ -296,6 +294,6 @@ static struct i2c_driver nvt_ts_driver = {
 
 module_i2c_driver(nvt_ts_driver);
 
-MODULE_DESCRIPTION("Novatek NVT-ts touchscreen driver");
+MODULE_DESCRIPTION("Novatek NT11205 touchscreen driver");
 MODULE_AUTHOR("Hans de Goede <hdegoede@redhat.com>");
 MODULE_LICENSE("GPL");

From 80c268c3394e9a7118c4ce0fee0eaffab85b762a Mon Sep 17 00:00:00 2001
From: Martin Kaiser <martin@kaiser.cx>
Date: Sun, 9 Jul 2023 15:41:08 +0200
Subject: [PATCH 0040/1189] Input: tegra-kbc - use
 devm_platform_ioremap_resource

devm_platform_get_and_ioremap_resource maps a resource and returns its
physical address. If we don't need the physical address, we should call
devm_platform_ioremap_resource instead.

Signed-off-by: Martin Kaiser <martin@kaiser.cx>
Acked-by: Thierry Reding <treding@nvidia.com>
Link: https://lore.kernel.org/r/20230709134109.182418-1-martin@kaiser.cx
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/tegra-kbc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/input/keyboard/tegra-kbc.c b/drivers/input/keyboard/tegra-kbc.c
index d5a6c7d8eb25..c9a823ea45d0 100644
--- a/drivers/input/keyboard/tegra-kbc.c
+++ b/drivers/input/keyboard/tegra-kbc.c
@@ -640,7 +640,7 @@ static int tegra_kbc_probe(struct platform_device *pdev)
 
 	timer_setup(&kbc->timer, tegra_kbc_keypress_timer, 0);
 
-	kbc->mmio = devm_platform_get_and_ioremap_resource(pdev, 0, NULL);
+	kbc->mmio = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(kbc->mmio))
 		return PTR_ERR(kbc->mmio);
 

From 2e00b8bf5624767f6be7427b6eb532524793463e Mon Sep 17 00:00:00 2001
From: Jeff LaBundy <jeff@labundy.com>
Date: Sun, 9 Jul 2023 12:06:37 -0500
Subject: [PATCH 0041/1189] Input: iqs7222 - configure power mode before
 triggering ATI

If the device drops into ultra-low-power mode before being placed
into normal-power mode as part of ATI being triggered, the device
does not assert any interrupts until the ATI routine is restarted
two seconds later.

Solve this problem by adopting the vendor's recommendation, which
calls for the device to be placed into normal-power mode prior to
being configured and ATI being triggered.

The original implementation followed this sequence, but the order
was inadvertently changed as part of the resolution of a separate
erratum.

Fixes: 1e4189d8af27 ("Input: iqs7222 - protect volatile registers")
Signed-off-by: Jeff LaBundy <jeff@labundy.com>
Link: https://lore.kernel.org/r/ZKrpHc2Ji9qR25r2@nixie71
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/iqs7222.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/input/misc/iqs7222.c b/drivers/input/misc/iqs7222.c
index 096b0925f41b..acb95048e823 100644
--- a/drivers/input/misc/iqs7222.c
+++ b/drivers/input/misc/iqs7222.c
@@ -1381,9 +1381,6 @@ static int iqs7222_ati_trigger(struct iqs7222_private *iqs7222)
 	if (error)
 		return error;
 
-	sys_setup &= ~IQS7222_SYS_SETUP_INTF_MODE_MASK;
-	sys_setup &= ~IQS7222_SYS_SETUP_PWR_MODE_MASK;
-
 	for (i = 0; i < IQS7222_NUM_RETRIES; i++) {
 		/*
 		 * Trigger ATI from streaming and normal-power modes so that
@@ -1561,8 +1558,11 @@ static int iqs7222_dev_init(struct iqs7222_private *iqs7222, int dir)
 			return error;
 	}
 
-	if (dir == READ)
+	if (dir == READ) {
+		iqs7222->sys_setup[0] &= ~IQS7222_SYS_SETUP_INTF_MODE_MASK;
+		iqs7222->sys_setup[0] &= ~IQS7222_SYS_SETUP_PWR_MODE_MASK;
 		return 0;
+	}
 
 	return iqs7222_ati_trigger(iqs7222);
 }

From 92b46a7bd1c4966e8178da008930cdc0af43dad8 Mon Sep 17 00:00:00 2001
From: Jeff LaBundy <jeff@labundy.com>
Date: Sun, 9 Jul 2023 12:06:57 -0500
Subject: [PATCH 0042/1189] dt-bindings: input: iqs7222: Define units for
 slider properties

The units assumed by the 'azoteq,top-speed', 'azoteq,bottom-speed'
and 'azoteq,gesture-dist' properties are unspecified; define them
according to the device's datasheet.

Signed-off-by: Jeff LaBundy <jeff@labundy.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/ZKrpMekZBt95Gmnr@nixie71
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 .../bindings/input/azoteq,iqs7222.yaml           | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/Documentation/devicetree/bindings/input/azoteq,iqs7222.yaml b/Documentation/devicetree/bindings/input/azoteq,iqs7222.yaml
index 9ddba7f2e7aa..4c8690b62ce0 100644
--- a/Documentation/devicetree/bindings/input/azoteq,iqs7222.yaml
+++ b/Documentation/devicetree/bindings/input/azoteq,iqs7222.yaml
@@ -521,16 +521,16 @@ patternProperties:
         minimum: 0
         maximum: 65535
         description:
-          Specifies the speed of movement after which coordinate filtering is
-          no longer applied.
+          Specifies the speed (in coordinates traveled per conversion) after
+          which coordinate filtering is no longer applied.
 
       azoteq,bottom-speed:
         $ref: /schemas/types.yaml#/definitions/uint32
         minimum: 0
         maximum: 255
         description:
-          Specifies the speed of movement after which coordinate filtering is
-          linearly reduced.
+          Specifies the speed (in coordinates traveled per conversion) after
+          which coordinate filtering is linearly reduced.
 
       azoteq,bottom-beta:
         $ref: /schemas/types.yaml#/definitions/uint32
@@ -595,10 +595,10 @@ patternProperties:
             minimum: 0
             maximum: 4080
             description:
-              Specifies the distance across which a swipe or flick gesture must
-              travel in order to be acknowledged by the device. The number spec-
-              ified for any one swipe or flick gesture applies to all remaining
-              swipe or flick gestures.
+              Specifies the distance (in coordinates) across which a swipe or
+              flick gesture must travel in order to be acknowledged by the
+              device. The number specified for any one swipe or flick gesture
+              applies to all remaining swipe or flick gestures.
 
           azoteq,gpio-select:
             $ref: /schemas/types.yaml#/definitions/uint32-array

From 823b28c5e590cccbfc94e69f06a884278dde7943 Mon Sep 17 00:00:00 2001
From: Jeff LaBundy <jeff@labundy.com>
Date: Sun, 9 Jul 2023 12:07:05 -0500
Subject: [PATCH 0043/1189] dt-bindings: input: iqs7222: Add properties for
 Azoteq IQS7222D

Extend the common binding to include a new variant of the silicon,
which effectively replaces a pair of slider nodes with a trackpad
node comprising the same or similar properties.

As part of this change, the if/then/else schema have been updated
to identify properties that are not supported by the new device.

Signed-off-by: Jeff LaBundy <jeff@labundy.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/ZKrpOdp+rM8gDekw@nixie71
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 .../bindings/input/azoteq,iqs7222.yaml        | 232 ++++++++++++++++--
 1 file changed, 215 insertions(+), 17 deletions(-)

diff --git a/Documentation/devicetree/bindings/input/azoteq,iqs7222.yaml b/Documentation/devicetree/bindings/input/azoteq,iqs7222.yaml
index 4c8690b62ce0..5b1769c19b17 100644
--- a/Documentation/devicetree/bindings/input/azoteq,iqs7222.yaml
+++ b/Documentation/devicetree/bindings/input/azoteq,iqs7222.yaml
@@ -4,14 +4,14 @@
 $id: http://devicetree.org/schemas/input/azoteq,iqs7222.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
-title: Azoteq IQS7222A/B/C Capacitive Touch Controller
+title: Azoteq IQS7222A/B/C/D Capacitive Touch Controller
 
 maintainers:
   - Jeff LaBundy <jeff@labundy.com>
 
 description: |
-  The Azoteq IQS7222A, IQS7222B and IQS7222C are multichannel capacitive touch
-  controllers that feature additional sensing capabilities.
+  The Azoteq IQS7222A, IQS7222B, IQS7222C and IQS7222D are multichannel
+  capacitive touch controllers that feature additional sensing capabilities.
 
   Link to datasheets: https://www.azoteq.com/
 
@@ -21,6 +21,7 @@ properties:
       - azoteq,iqs7222a
       - azoteq,iqs7222b
       - azoteq,iqs7222c
+      - azoteq,iqs7222d
 
   reg:
     maxItems: 1
@@ -173,6 +174,152 @@ properties:
     maximum: 3000
     description: Specifies the report rate (in ms) during ultra-low-power mode.
 
+  touchscreen-size-x: true
+  touchscreen-size-y: true
+  touchscreen-inverted-x: true
+  touchscreen-inverted-y: true
+  touchscreen-swapped-x-y: true
+
+  trackpad:
+    type: object
+    description: Represents all channels associated with the trackpad.
+
+    properties:
+      azoteq,channel-select:
+        $ref: /schemas/types.yaml#/definitions/uint32-array
+        minItems: 1
+        maxItems: 12
+        items:
+          minimum: 0
+          maximum: 13
+        description:
+          Specifies the order of the channels that participate in the trackpad.
+          Specify 255 to omit a given channel for the purpose of mapping a non-
+          rectangular trackpad.
+
+      azoteq,num-rows:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 1
+        maximum: 12
+        description: Specifies the number of rows that comprise the trackpad.
+
+      azoteq,num-cols:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 1
+        maximum: 12
+        description: Specifies the number of columns that comprise the trackpad.
+
+      azoteq,top-speed:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        multipleOf: 4
+        minimum: 0
+        maximum: 1020
+        description:
+          Specifies the speed (in coordinates traveled per conversion) after
+          which coordinate filtering is no longer applied.
+
+      azoteq,bottom-speed:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 255
+        description:
+          Specifies the speed (in coordinates traveled per conversion) after
+          which coordinate filtering is linearly reduced.
+
+      azoteq,use-prox:
+        type: boolean
+        description:
+          Directs the trackpad to respond to the proximity states of the
+          selected channels instead of their corresponding touch states.
+          Note the trackpad cannot report granular coordinates during a
+          state of proximity.
+
+    patternProperties:
+      "^azoteq,lower-cal-(x|y)$":
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 255
+        description: Specifies the trackpad's lower starting points.
+
+      "^azoteq,upper-cal-(x|y)$":
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 255
+        description: Specifies the trackpad's upper starting points.
+
+      "^event-(press|tap|(swipe|flick)-(x|y)-(pos|neg))$":
+        type: object
+        $ref: input.yaml#
+        description:
+          Represents a press or gesture event reported by the trackpad. Specify
+          'linux,code' under the press event to report absolute coordinates.
+
+        properties:
+          linux,code: true
+
+          azoteq,gesture-angle-tighten:
+            type: boolean
+            description:
+              Limits the tangent of the gesture angle to 0.5 (axial gestures
+              only). If specified in one direction, the effect is applied in
+              either direction.
+
+          azoteq,gesture-max-ms:
+            multipleOf: 16
+            minimum: 0
+            maximum: 4080
+            description:
+              Specifies the length of time (in ms) within which a tap, swipe
+              or flick gesture must be completed in order to be acknowledged
+              by the device. The number specified for any one swipe or flick
+              gesture applies to all other swipe or flick gestures.
+
+          azoteq,gesture-min-ms:
+            multipleOf: 16
+            minimum: 0
+            maximum: 4080
+            description:
+              Specifies the length of time (in ms) for which a tap gesture must
+              be held in order to be acknowledged by the device.
+
+          azoteq,gesture-dist:
+            $ref: /schemas/types.yaml#/definitions/uint32
+            minimum: 0
+            maximum: 65535
+            description:
+              Specifies the distance (in coordinates) across which a swipe or
+              flick gesture must travel in order to be acknowledged by the
+              device. The number specified for any one swipe or flick gesture
+              applies to all remaining swipe or flick gestures.
+
+              For tap gestures, this property specifies the distance from the
+              original point of contact across which the contact is permitted
+              to travel before the gesture is rejected by the device.
+
+          azoteq,gpio-select:
+            $ref: /schemas/types.yaml#/definitions/uint32-array
+            minItems: 1
+            maxItems: 3
+            items:
+              minimum: 0
+              maximum: 2
+            description: |
+              Specifies one or more GPIO mapped to the event as follows:
+              0: GPIO0
+              1: GPIO3
+              2: GPIO4
+
+              Note that although multiple events can be mapped to a single
+              GPIO, they must all be of the same type (proximity, touch or
+              trackpad gesture).
+
+        additionalProperties: false
+
+    required:
+      - azoteq,channel-select
+
+    additionalProperties: false
+
 patternProperties:
   "^cycle-[0-9]$":
     type: object
@@ -288,6 +435,10 @@ patternProperties:
           Activates the reference channel in response to proximity events
           instead of touch events.
 
+      azoteq,counts-filt-enable:
+        type: boolean
+        description: Applies counts filtering to the channel.
+
       azoteq,ati-band:
         $ref: /schemas/types.yaml#/definitions/uint32
         enum: [0, 1, 2, 3]
@@ -432,12 +583,12 @@ patternProperties:
             description: |
               Specifies one or more GPIO mapped to the event as follows:
               0: GPIO0
-              1: GPIO3 (IQS7222C only)
-              2: GPIO4 (IQS7222C only)
+              1: GPIO3
+              2: GPIO4
 
               Note that although multiple events can be mapped to a single
               GPIO, they must all be of the same type (proximity, touch or
-              slider gesture).
+              slider/trackpad gesture).
 
           azoteq,thresh:
             $ref: /schemas/types.yaml#/definitions/uint32
@@ -610,8 +761,8 @@ patternProperties:
             description: |
               Specifies one or more GPIO mapped to the event as follows:
               0: GPIO0
-              1: GPIO3 (IQS7222C only)
-              2: GPIO4 (IQS7222C only)
+              1: GPIO3
+              2: GPIO4
 
               Note that although multiple events can be mapped to a single
               GPIO, they must all be of the same type (proximity, touch or
@@ -629,8 +780,8 @@ patternProperties:
     description: |
       Represents a GPIO mapped to one or more events as follows:
       gpio-0: GPIO0
-      gpio-1: GPIO3 (IQS7222C only)
-      gpio-2: GPIO4 (IQS7222C only)
+      gpio-1: GPIO3
+      gpio-2: GPIO4
 
     allOf:
       - $ref: ../pinctrl/pincfg-node.yaml#
@@ -641,11 +792,53 @@ patternProperties:
     additionalProperties: false
 
 allOf:
+  - $ref: touchscreen/touchscreen.yaml#
+
   - if:
       properties:
         compatible:
           contains:
-            const: azoteq,iqs7222b
+            enum:
+              - azoteq,iqs7222a
+              - azoteq,iqs7222b
+              - azoteq,iqs7222c
+
+    then:
+      properties:
+        touchscreen-size-x: false
+        touchscreen-size-y: false
+        touchscreen-inverted-x: false
+        touchscreen-inverted-y: false
+        touchscreen-swapped-x-y: false
+
+        trackpad: false
+
+      patternProperties:
+        "^channel-([0-9]|1[0-9])$":
+          properties:
+            azoteq,counts-filt-enable: false
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - azoteq,iqs7222b
+              - azoteq,iqs7222c
+
+    then:
+      patternProperties:
+        "^channel-([0-9]|1[0-9])$":
+          properties:
+            azoteq,ulp-allow: false
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - azoteq,iqs7222b
+              - azoteq,iqs7222d
 
     then:
       patternProperties:
@@ -657,13 +850,22 @@ allOf:
           properties:
             azoteq,ref-select: false
 
+        "^slider-[0-1]$": false
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: azoteq,iqs7222b
+
+    then:
+      patternProperties:
+        "^channel-([0-9]|1[0-9])$":
           patternProperties:
             "^event-(prox|touch)$":
               properties:
                 azoteq,gpio-select: false
 
-        "^slider-[0-1]$": false
-
         "^gpio-[0-2]$": false
 
   - if:
@@ -704,10 +906,6 @@ allOf:
 
     else:
       patternProperties:
-        "^channel-([0-9]|1[0-9])$":
-          properties:
-            azoteq,ulp-allow: false
-
         "^slider-[0-1]$":
           patternProperties:
             "^event-(press|tap|(swipe|flick)-(pos|neg))$":

From dd24e202ac722b3fea1fadb7f6c0b2db61086e78 Mon Sep 17 00:00:00 2001
From: Jeff LaBundy <jeff@labundy.com>
Date: Sun, 9 Jul 2023 12:07:18 -0500
Subject: [PATCH 0044/1189] Input: iqs7222 - add support for Azoteq IQS7222D

The vendor has introduced a new variant of silicon which is highly
similar to the existing IQS7222A, but with its independent sliders
essentially replaced with a single-contact trackpad.

Update the common driver to support this new device's register map
and report trackpad events. As with the IQS7222A, the new IQS7222D
can report both raw coordinates as well as gestures.

Signed-off-by: Jeff LaBundy <jeff@labundy.com>
Link: https://lore.kernel.org/r/ZKrpRh6RT6+6KrMQ@nixie71
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/Kconfig   |   4 +-
 drivers/input/misc/iqs7222.c | 468 ++++++++++++++++++++++++++++++++++-
 2 files changed, 461 insertions(+), 11 deletions(-)

diff --git a/drivers/input/misc/Kconfig b/drivers/input/misc/Kconfig
index 81a54a59e13c..c47eecc6f83b 100644
--- a/drivers/input/misc/Kconfig
+++ b/drivers/input/misc/Kconfig
@@ -791,10 +791,10 @@ config INPUT_IQS626A
 	  module will be called iqs626a.
 
 config INPUT_IQS7222
-	tristate "Azoteq IQS7222A/B/C capacitive touch controller"
+	tristate "Azoteq IQS7222A/B/C/D capacitive touch controller"
 	depends on I2C
 	help
-	  Say Y to enable support for the Azoteq IQS7222A/B/C family
+	  Say Y to enable support for the Azoteq IQS7222A/B/C/D family
 	  of capacitive touch controllers.
 
 	  To compile this driver as a module, choose M here: the
diff --git a/drivers/input/misc/iqs7222.c b/drivers/input/misc/iqs7222.c
index acb95048e823..a9c1dba1e8c1 100644
--- a/drivers/input/misc/iqs7222.c
+++ b/drivers/input/misc/iqs7222.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Azoteq IQS7222A/B/C Capacitive Touch Controller
+ * Azoteq IQS7222A/B/C/D Capacitive Touch Controller
  *
  * Copyright (C) 2022 Jeff LaBundy <jeff@labundy.com>
  */
@@ -12,6 +12,7 @@
 #include <linux/gpio/consumer.h>
 #include <linux/i2c.h>
 #include <linux/input.h>
+#include <linux/input/touchscreen.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/ktime.h>
@@ -25,6 +26,7 @@
 #define IQS7222_PROD_NUM_A			840
 #define IQS7222_PROD_NUM_B			698
 #define IQS7222_PROD_NUM_C			863
+#define IQS7222_PROD_NUM_D			1046
 
 #define IQS7222_SYS_STATUS			0x10
 #define IQS7222_SYS_STATUS_RESET		BIT(3)
@@ -54,6 +56,7 @@
 
 #define IQS7222_EVENT_MASK_ATI			BIT(12)
 #define IQS7222_EVENT_MASK_SLDR			BIT(10)
+#define IQS7222_EVENT_MASK_TPAD			IQS7222_EVENT_MASK_SLDR
 #define IQS7222_EVENT_MASK_TOUCH		BIT(1)
 #define IQS7222_EVENT_MASK_PROX			BIT(0)
 
@@ -71,6 +74,7 @@
 #define IQS7222_MAX_COLS_CHAN			6
 #define IQS7222_MAX_COLS_FILT			2
 #define IQS7222_MAX_COLS_SLDR			11
+#define IQS7222_MAX_COLS_TPAD			24
 #define IQS7222_MAX_COLS_GPIO			3
 #define IQS7222_MAX_COLS_SYS			13
 
@@ -102,16 +106,18 @@ enum iqs7222_reg_grp_id {
 	IQS7222_REG_GRP_BTN,
 	IQS7222_REG_GRP_CHAN,
 	IQS7222_REG_GRP_SLDR,
+	IQS7222_REG_GRP_TPAD,
 	IQS7222_REG_GRP_GPIO,
 	IQS7222_REG_GRP_SYS,
 	IQS7222_NUM_REG_GRPS
 };
 
 static const char * const iqs7222_reg_grp_names[IQS7222_NUM_REG_GRPS] = {
-	[IQS7222_REG_GRP_CYCLE] = "cycle",
-	[IQS7222_REG_GRP_CHAN] = "channel",
-	[IQS7222_REG_GRP_SLDR] = "slider",
-	[IQS7222_REG_GRP_GPIO] = "gpio",
+	[IQS7222_REG_GRP_CYCLE] = "cycle-%d",
+	[IQS7222_REG_GRP_CHAN] = "channel-%d",
+	[IQS7222_REG_GRP_SLDR] = "slider-%d",
+	[IQS7222_REG_GRP_TPAD] = "trackpad",
+	[IQS7222_REG_GRP_GPIO] = "gpio-%d",
 };
 
 static const unsigned int iqs7222_max_cols[IQS7222_NUM_REG_GRPS] = {
@@ -122,6 +128,7 @@ static const unsigned int iqs7222_max_cols[IQS7222_NUM_REG_GRPS] = {
 	[IQS7222_REG_GRP_CHAN] = IQS7222_MAX_COLS_CHAN,
 	[IQS7222_REG_GRP_FILT] = IQS7222_MAX_COLS_FILT,
 	[IQS7222_REG_GRP_SLDR] = IQS7222_MAX_COLS_SLDR,
+	[IQS7222_REG_GRP_TPAD] = IQS7222_MAX_COLS_TPAD,
 	[IQS7222_REG_GRP_GPIO] = IQS7222_MAX_COLS_GPIO,
 	[IQS7222_REG_GRP_SYS] = IQS7222_MAX_COLS_SYS,
 };
@@ -130,8 +137,10 @@ static const unsigned int iqs7222_gpio_links[] = { 2, 5, 6, };
 
 struct iqs7222_event_desc {
 	const char *name;
+	u16 link;
 	u16 mask;
 	u16 val;
+	u16 strict;
 	u16 enable;
 	enum iqs7222_reg_key_id reg_key;
 };
@@ -188,6 +197,93 @@ static const struct iqs7222_event_desc iqs7222_sl_events[] = {
 	},
 };
 
+static const struct iqs7222_event_desc iqs7222_tp_events[] = {
+	{
+		.name = "event-press",
+		.link = BIT(7),
+	},
+	{
+		.name = "event-tap",
+		.link = BIT(0),
+		.mask = BIT(0),
+		.val = BIT(0),
+		.enable = BIT(0),
+		.reg_key = IQS7222_REG_KEY_TAP,
+	},
+	{
+		.name = "event-swipe-x-pos",
+		.link = BIT(2),
+		.mask = BIT(2) | BIT(1),
+		.val = BIT(2),
+		.strict = BIT(4),
+		.enable = BIT(1),
+		.reg_key = IQS7222_REG_KEY_AXIAL,
+	},
+	{
+		.name = "event-swipe-y-pos",
+		.link = BIT(3),
+		.mask = BIT(3) | BIT(1),
+		.val = BIT(3),
+		.strict = BIT(3),
+		.enable = BIT(1),
+		.reg_key = IQS7222_REG_KEY_AXIAL,
+	},
+	{
+		.name = "event-swipe-x-neg",
+		.link = BIT(4),
+		.mask = BIT(4) | BIT(1),
+		.val = BIT(4),
+		.strict = BIT(4),
+		.enable = BIT(1),
+		.reg_key = IQS7222_REG_KEY_AXIAL,
+	},
+	{
+		.name = "event-swipe-y-neg",
+		.link = BIT(5),
+		.mask = BIT(5) | BIT(1),
+		.val = BIT(5),
+		.strict = BIT(3),
+		.enable = BIT(1),
+		.reg_key = IQS7222_REG_KEY_AXIAL,
+	},
+	{
+		.name = "event-flick-x-pos",
+		.link = BIT(2),
+		.mask = BIT(2) | BIT(1),
+		.val = BIT(2) | BIT(1),
+		.strict = BIT(4),
+		.enable = BIT(2),
+		.reg_key = IQS7222_REG_KEY_AXIAL,
+	},
+	{
+		.name = "event-flick-y-pos",
+		.link = BIT(3),
+		.mask = BIT(3) | BIT(1),
+		.val = BIT(3) | BIT(1),
+		.strict = BIT(3),
+		.enable = BIT(2),
+		.reg_key = IQS7222_REG_KEY_AXIAL,
+	},
+	{
+		.name = "event-flick-x-neg",
+		.link = BIT(4),
+		.mask = BIT(4) | BIT(1),
+		.val = BIT(4) | BIT(1),
+		.strict = BIT(4),
+		.enable = BIT(2),
+		.reg_key = IQS7222_REG_KEY_AXIAL,
+	},
+	{
+		.name = "event-flick-y-neg",
+		.link = BIT(5),
+		.mask = BIT(5) | BIT(1),
+		.val = BIT(5) | BIT(1),
+		.strict = BIT(3),
+		.enable = BIT(2),
+		.reg_key = IQS7222_REG_KEY_AXIAL,
+	},
+};
+
 struct iqs7222_reg_grp_desc {
 	u16 base;
 	int num_row;
@@ -524,6 +620,62 @@ static const struct iqs7222_dev_desc iqs7222_devs[] = {
 			},
 		},
 	},
+	{
+		.prod_num = IQS7222_PROD_NUM_D,
+		.fw_major = 0,
+		.fw_minor = 37,
+		.touch_link = 1770,
+		.allow_offset = 9,
+		.event_offset = 10,
+		.comms_offset = 11,
+		.reg_grps = {
+			[IQS7222_REG_GRP_STAT] = {
+				.base = IQS7222_SYS_STATUS,
+				.num_row = 1,
+				.num_col = 7,
+			},
+			[IQS7222_REG_GRP_CYCLE] = {
+				.base = 0x8000,
+				.num_row = 7,
+				.num_col = 2,
+			},
+			[IQS7222_REG_GRP_GLBL] = {
+				.base = 0x8700,
+				.num_row = 1,
+				.num_col = 3,
+			},
+			[IQS7222_REG_GRP_BTN] = {
+				.base = 0x9000,
+				.num_row = 14,
+				.num_col = 3,
+			},
+			[IQS7222_REG_GRP_CHAN] = {
+				.base = 0xA000,
+				.num_row = 14,
+				.num_col = 4,
+			},
+			[IQS7222_REG_GRP_FILT] = {
+				.base = 0xAE00,
+				.num_row = 1,
+				.num_col = 2,
+			},
+			[IQS7222_REG_GRP_TPAD] = {
+				.base = 0xB000,
+				.num_row = 1,
+				.num_col = 24,
+			},
+			[IQS7222_REG_GRP_GPIO] = {
+				.base = 0xC000,
+				.num_row = 3,
+				.num_col = 3,
+			},
+			[IQS7222_REG_GRP_SYS] = {
+				.base = IQS7222_SYS_SETUP,
+				.num_row = 1,
+				.num_col = 12,
+			},
+		},
+	},
 };
 
 struct iqs7222_prop_desc {
@@ -1008,6 +1160,123 @@ static const struct iqs7222_prop_desc iqs7222_props[] = {
 		.val_pitch = 4,
 		.label = "maximum gesture time",
 	},
+	{
+		.name = "azoteq,num-rows",
+		.reg_grp = IQS7222_REG_GRP_TPAD,
+		.reg_offset = 0,
+		.reg_shift = 4,
+		.reg_width = 4,
+		.val_min = 1,
+		.val_max = 12,
+		.label = "number of rows",
+	},
+	{
+		.name = "azoteq,num-cols",
+		.reg_grp = IQS7222_REG_GRP_TPAD,
+		.reg_offset = 0,
+		.reg_shift = 0,
+		.reg_width = 4,
+		.val_min = 1,
+		.val_max = 12,
+		.label = "number of columns",
+	},
+	{
+		.name = "azoteq,lower-cal-y",
+		.reg_grp = IQS7222_REG_GRP_TPAD,
+		.reg_offset = 1,
+		.reg_shift = 8,
+		.reg_width = 8,
+		.label = "lower vertical calibration",
+	},
+	{
+		.name = "azoteq,lower-cal-x",
+		.reg_grp = IQS7222_REG_GRP_TPAD,
+		.reg_offset = 1,
+		.reg_shift = 0,
+		.reg_width = 8,
+		.label = "lower horizontal calibration",
+	},
+	{
+		.name = "azoteq,upper-cal-y",
+		.reg_grp = IQS7222_REG_GRP_TPAD,
+		.reg_offset = 2,
+		.reg_shift = 8,
+		.reg_width = 8,
+		.label = "upper vertical calibration",
+	},
+	{
+		.name = "azoteq,upper-cal-x",
+		.reg_grp = IQS7222_REG_GRP_TPAD,
+		.reg_offset = 2,
+		.reg_shift = 0,
+		.reg_width = 8,
+		.label = "upper horizontal calibration",
+	},
+	{
+		.name = "azoteq,top-speed",
+		.reg_grp = IQS7222_REG_GRP_TPAD,
+		.reg_offset = 3,
+		.reg_shift = 8,
+		.reg_width = 8,
+		.val_pitch = 4,
+		.label = "top speed",
+	},
+	{
+		.name = "azoteq,bottom-speed",
+		.reg_grp = IQS7222_REG_GRP_TPAD,
+		.reg_offset = 3,
+		.reg_shift = 0,
+		.reg_width = 8,
+		.label = "bottom speed",
+	},
+	{
+		.name = "azoteq,gesture-min-ms",
+		.reg_grp = IQS7222_REG_GRP_TPAD,
+		.reg_key = IQS7222_REG_KEY_TAP,
+		.reg_offset = 20,
+		.reg_shift = 8,
+		.reg_width = 8,
+		.val_pitch = 16,
+		.label = "minimum gesture time",
+	},
+	{
+		.name = "azoteq,gesture-max-ms",
+		.reg_grp = IQS7222_REG_GRP_TPAD,
+		.reg_key = IQS7222_REG_KEY_AXIAL,
+		.reg_offset = 21,
+		.reg_shift = 8,
+		.reg_width = 8,
+		.val_pitch = 16,
+		.label = "maximum gesture time",
+	},
+	{
+		.name = "azoteq,gesture-max-ms",
+		.reg_grp = IQS7222_REG_GRP_TPAD,
+		.reg_key = IQS7222_REG_KEY_TAP,
+		.reg_offset = 21,
+		.reg_shift = 0,
+		.reg_width = 8,
+		.val_pitch = 16,
+		.label = "maximum gesture time",
+	},
+	{
+		.name = "azoteq,gesture-dist",
+		.reg_grp = IQS7222_REG_GRP_TPAD,
+		.reg_key = IQS7222_REG_KEY_TAP,
+		.reg_offset = 22,
+		.reg_shift = 0,
+		.reg_width = 16,
+		.label = "gesture distance",
+	},
+	{
+		.name = "azoteq,gesture-dist",
+		.reg_grp = IQS7222_REG_GRP_TPAD,
+		.reg_key = IQS7222_REG_KEY_AXIAL,
+		.reg_offset = 23,
+		.reg_shift = 0,
+		.reg_width = 16,
+		.label = "gesture distance",
+	},
 	{
 		.name = "drive-open-drain",
 		.reg_grp = IQS7222_REG_GRP_GPIO,
@@ -1091,16 +1360,19 @@ struct iqs7222_private {
 	struct gpio_desc *irq_gpio;
 	struct i2c_client *client;
 	struct input_dev *keypad;
+	struct touchscreen_properties prop;
 	unsigned int kp_type[IQS7222_MAX_CHAN][ARRAY_SIZE(iqs7222_kp_events)];
 	unsigned int kp_code[IQS7222_MAX_CHAN][ARRAY_SIZE(iqs7222_kp_events)];
 	unsigned int sl_code[IQS7222_MAX_SLDR][ARRAY_SIZE(iqs7222_sl_events)];
 	unsigned int sl_axis[IQS7222_MAX_SLDR];
+	unsigned int tp_code[ARRAY_SIZE(iqs7222_tp_events)];
 	u16 cycle_setup[IQS7222_MAX_CHAN / 2][IQS7222_MAX_COLS_CYCLE];
 	u16 glbl_setup[IQS7222_MAX_COLS_GLBL];
 	u16 btn_setup[IQS7222_MAX_CHAN][IQS7222_MAX_COLS_BTN];
 	u16 chan_setup[IQS7222_MAX_CHAN][IQS7222_MAX_COLS_CHAN];
 	u16 filt_setup[IQS7222_MAX_COLS_FILT];
 	u16 sldr_setup[IQS7222_MAX_SLDR][IQS7222_MAX_COLS_SLDR];
+	u16 tpad_setup[IQS7222_MAX_COLS_TPAD];
 	u16 gpio_setup[ARRAY_SIZE(iqs7222_gpio_links)][IQS7222_MAX_COLS_GPIO];
 	u16 sys_setup[IQS7222_MAX_COLS_SYS];
 };
@@ -1127,6 +1399,9 @@ static u16 *iqs7222_setup(struct iqs7222_private *iqs7222,
 	case IQS7222_REG_GRP_SLDR:
 		return iqs7222->sldr_setup[row];
 
+	case IQS7222_REG_GRP_TPAD:
+		return iqs7222->tpad_setup;
+
 	case IQS7222_REG_GRP_GPIO:
 		return iqs7222->gpio_setup[row];
 
@@ -1936,6 +2211,14 @@ static int iqs7222_parse_chan(struct iqs7222_private *iqs7222,
 		ref_setup[4] = dev_desc->touch_link;
 		if (fwnode_property_present(chan_node, "azoteq,use-prox"))
 			ref_setup[4] -= 2;
+	} else if (dev_desc->reg_grps[IQS7222_REG_GRP_TPAD].num_row &&
+		   fwnode_property_present(chan_node,
+					   "azoteq,counts-filt-enable")) {
+		/*
+		 * In the case of IQS7222D, however, the reference mode field
+		 * is partially repurposed as a counts filter enable control.
+		 */
+		chan_setup[0] |= IQS7222_CHAN_SETUP_0_REF_MODE_REF;
 	}
 
 	if (fwnode_property_present(chan_node, "azoteq,rx-enable")) {
@@ -2278,6 +2561,136 @@ static int iqs7222_parse_sldr(struct iqs7222_private *iqs7222,
 				   IQS7222_REG_KEY_NO_WHEEL);
 }
 
+static int iqs7222_parse_tpad(struct iqs7222_private *iqs7222,
+			      struct fwnode_handle *tpad_node, int tpad_index)
+{
+	const struct iqs7222_dev_desc *dev_desc = iqs7222->dev_desc;
+	struct touchscreen_properties *prop = &iqs7222->prop;
+	struct i2c_client *client = iqs7222->client;
+	int num_chan = dev_desc->reg_grps[IQS7222_REG_GRP_CHAN].num_row;
+	int count, error, i;
+	u16 *event_mask = &iqs7222->sys_setup[dev_desc->event_offset];
+	u16 *tpad_setup = iqs7222->tpad_setup;
+	unsigned int chan_sel[12];
+
+	error = iqs7222_parse_props(iqs7222, tpad_node, tpad_index,
+				    IQS7222_REG_GRP_TPAD,
+				    IQS7222_REG_KEY_NONE);
+	if (error)
+		return error;
+
+	count = fwnode_property_count_u32(tpad_node, "azoteq,channel-select");
+	if (count < 0) {
+		dev_err(&client->dev, "Failed to count %s channels: %d\n",
+			fwnode_get_name(tpad_node), count);
+		return count;
+	} else if (!count || count > ARRAY_SIZE(chan_sel)) {
+		dev_err(&client->dev, "Invalid number of %s channels\n",
+			fwnode_get_name(tpad_node));
+		return -EINVAL;
+	}
+
+	error = fwnode_property_read_u32_array(tpad_node,
+					       "azoteq,channel-select",
+					       chan_sel, count);
+	if (error) {
+		dev_err(&client->dev, "Failed to read %s channels: %d\n",
+			fwnode_get_name(tpad_node), error);
+		return error;
+	}
+
+	tpad_setup[6] &= ~GENMASK(num_chan - 1, 0);
+
+	for (i = 0; i < ARRAY_SIZE(chan_sel); i++) {
+		tpad_setup[8 + i] = 0;
+		if (i >= count || chan_sel[i] == U8_MAX)
+			continue;
+
+		if (chan_sel[i] >= num_chan) {
+			dev_err(&client->dev, "Invalid %s channel: %u\n",
+				fwnode_get_name(tpad_node), chan_sel[i]);
+			return -EINVAL;
+		}
+
+		/*
+		 * The following fields indicate which channels participate in
+		 * the trackpad, as well as each channel's relative placement.
+		 */
+		tpad_setup[6] |= BIT(chan_sel[i]);
+		tpad_setup[8 + i] = chan_sel[i] * 34 + 1072;
+	}
+
+	tpad_setup[7] = dev_desc->touch_link;
+	if (fwnode_property_present(tpad_node, "azoteq,use-prox"))
+		tpad_setup[7] -= 2;
+
+	for (i = 0; i < ARRAY_SIZE(iqs7222_tp_events); i++)
+		tpad_setup[20] &= ~(iqs7222_tp_events[i].strict |
+				    iqs7222_tp_events[i].enable);
+
+	for (i = 0; i < ARRAY_SIZE(iqs7222_tp_events); i++) {
+		const char *event_name = iqs7222_tp_events[i].name;
+		struct fwnode_handle *event_node;
+
+		event_node = fwnode_get_named_child_node(tpad_node, event_name);
+		if (!event_node)
+			continue;
+
+		if (fwnode_property_present(event_node,
+					    "azoteq,gesture-angle-tighten"))
+			tpad_setup[20] |= iqs7222_tp_events[i].strict;
+
+		tpad_setup[20] |= iqs7222_tp_events[i].enable;
+
+		error = iqs7222_parse_event(iqs7222, event_node, tpad_index,
+					    IQS7222_REG_GRP_TPAD,
+					    iqs7222_tp_events[i].reg_key,
+					    iqs7222_tp_events[i].link, 1566,
+					    NULL,
+					    &iqs7222->tp_code[i]);
+		fwnode_handle_put(event_node);
+		if (error)
+			return error;
+
+		if (!dev_desc->event_offset)
+			continue;
+
+		/*
+		 * The press/release event is determined based on whether the
+		 * coordinate fields report 0xFFFF and solely relies on touch
+		 * or proximity interrupts to be unmasked.
+		 */
+		if (i)
+			*event_mask |= IQS7222_EVENT_MASK_TPAD;
+		else if (tpad_setup[7] == dev_desc->touch_link)
+			*event_mask |= IQS7222_EVENT_MASK_TOUCH;
+		else
+			*event_mask |= IQS7222_EVENT_MASK_PROX;
+	}
+
+	if (!iqs7222->tp_code[0])
+		return 0;
+
+	input_set_abs_params(iqs7222->keypad, ABS_X,
+			     0, (tpad_setup[4] ? : 1) - 1, 0, 0);
+
+	input_set_abs_params(iqs7222->keypad, ABS_Y,
+			     0, (tpad_setup[5] ? : 1) - 1, 0, 0);
+
+	touchscreen_parse_properties(iqs7222->keypad, false, prop);
+
+	if (prop->max_x >= U16_MAX || prop->max_y >= U16_MAX) {
+		dev_err(&client->dev, "Invalid trackpad size: %u*%u\n",
+			prop->max_x, prop->max_y);
+		return -EINVAL;
+	}
+
+	tpad_setup[4] = prop->max_x + 1;
+	tpad_setup[5] = prop->max_y + 1;
+
+	return 0;
+}
+
 static int (*iqs7222_parse_extra[IQS7222_NUM_REG_GRPS])
 				(struct iqs7222_private *iqs7222,
 				 struct fwnode_handle *reg_grp_node,
@@ -2285,6 +2698,7 @@ static int (*iqs7222_parse_extra[IQS7222_NUM_REG_GRPS])
 	[IQS7222_REG_GRP_CYCLE] = iqs7222_parse_cycle,
 	[IQS7222_REG_GRP_CHAN] = iqs7222_parse_chan,
 	[IQS7222_REG_GRP_SLDR] = iqs7222_parse_sldr,
+	[IQS7222_REG_GRP_TPAD] = iqs7222_parse_tpad,
 };
 
 static int iqs7222_parse_reg_grp(struct iqs7222_private *iqs7222,
@@ -2298,7 +2712,7 @@ static int iqs7222_parse_reg_grp(struct iqs7222_private *iqs7222,
 	if (iqs7222_reg_grp_names[reg_grp]) {
 		char reg_grp_name[16];
 
-		snprintf(reg_grp_name, sizeof(reg_grp_name), "%s-%d",
+		snprintf(reg_grp_name, sizeof(reg_grp_name),
 			 iqs7222_reg_grp_names[reg_grp], reg_grp_index);
 
 		reg_grp_node = device_get_named_child_node(&client->dev,
@@ -2346,8 +2760,8 @@ static int iqs7222_parse_all(struct iqs7222_private *iqs7222)
 			continue;
 
 		/*
-		 * The IQS7222C exposes multiple GPIO and must be informed
-		 * as to which GPIO this group represents.
+		 * The IQS7222C and IQS7222D expose multiple GPIO and must be
+		 * informed as to which GPIO this group represents.
 		 */
 		for (j = 0; j < ARRAY_SIZE(iqs7222_gpio_links); j++)
 			gpio_setup[0] &= ~BIT(iqs7222_gpio_links[j]);
@@ -2480,6 +2894,41 @@ static int iqs7222_report(struct iqs7222_private *iqs7222)
 					 iqs7222->sl_code[i][j], 0);
 	}
 
+	for (i = 0; i < dev_desc->reg_grps[IQS7222_REG_GRP_TPAD].num_row; i++) {
+		u16 tpad_pos_x = le16_to_cpu(status[4]);
+		u16 tpad_pos_y = le16_to_cpu(status[5]);
+		u16 state = le16_to_cpu(status[6]);
+
+		input_report_key(iqs7222->keypad, iqs7222->tp_code[0],
+				 tpad_pos_x < U16_MAX);
+
+		if (tpad_pos_x < U16_MAX)
+			touchscreen_report_pos(iqs7222->keypad, &iqs7222->prop,
+					       tpad_pos_x, tpad_pos_y, false);
+
+		if (!(le16_to_cpu(status[1]) & IQS7222_EVENT_MASK_TPAD))
+			continue;
+
+		/*
+		 * Skip the press/release event, as it does not have separate
+		 * status fields and is handled separately.
+		 */
+		for (j = 1; j < ARRAY_SIZE(iqs7222_tp_events); j++) {
+			u16 mask = iqs7222_tp_events[j].mask;
+			u16 val = iqs7222_tp_events[j].val;
+
+			input_report_key(iqs7222->keypad,
+					 iqs7222->tp_code[j],
+					 (state & mask) == val);
+		}
+
+		input_sync(iqs7222->keypad);
+
+		for (j = 1; j < ARRAY_SIZE(iqs7222_tp_events); j++)
+			input_report_key(iqs7222->keypad,
+					 iqs7222->tp_code[j], 0);
+	}
+
 	input_sync(iqs7222->keypad);
 
 	return 0;
@@ -2584,6 +3033,7 @@ static const struct of_device_id iqs7222_of_match[] = {
 	{ .compatible = "azoteq,iqs7222a" },
 	{ .compatible = "azoteq,iqs7222b" },
 	{ .compatible = "azoteq,iqs7222c" },
+	{ .compatible = "azoteq,iqs7222d" },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, iqs7222_of_match);
@@ -2598,5 +3048,5 @@ static struct i2c_driver iqs7222_i2c_driver = {
 module_i2c_driver(iqs7222_i2c_driver);
 
 MODULE_AUTHOR("Jeff LaBundy <jeff@labundy.com>");
-MODULE_DESCRIPTION("Azoteq IQS7222A/B/C Capacitive Touch Controller");
+MODULE_DESCRIPTION("Azoteq IQS7222A/B/C/D Capacitive Touch Controller");
 MODULE_LICENSE("GPL");

From 5abb32411f221a000ff3d05bea31b4ce61cc6236 Mon Sep 17 00:00:00 2001
From: Yangtao Li <frank.li@vivo.com>
Date: Mon, 10 Jul 2023 13:35:30 -0700
Subject: [PATCH 0045/1189] Input: bcm-keypad - convert to
 devm_platform_ioremap_resource()

Use devm_platform_ioremap_resource() to simplify code.

Signed-off-by: Yangtao Li <frank.li@vivo.com>
Link: https://lore.kernel.org/r/20230705052346.39337-1-frank.li@vivo.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/bcm-keypad.c | 10 +---------
 1 file changed, 1 insertion(+), 9 deletions(-)

diff --git a/drivers/input/keyboard/bcm-keypad.c b/drivers/input/keyboard/bcm-keypad.c
index 05b09066df84..0aa6ef0da0ee 100644
--- a/drivers/input/keyboard/bcm-keypad.c
+++ b/drivers/input/keyboard/bcm-keypad.c
@@ -307,7 +307,6 @@ static int bcm_kp_probe(struct platform_device *pdev)
 {
 	struct bcm_kp *kp;
 	struct input_dev *input_dev;
-	struct resource *res;
 	int error;
 
 	kp = devm_kzalloc(&pdev->dev, sizeof(*kp), GFP_KERNEL);
@@ -353,14 +352,7 @@ static int bcm_kp_probe(struct platform_device *pdev)
 		return error;
 	}
 
-	/* Get the KEYPAD base address */
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(&pdev->dev, "Missing keypad base address resource\n");
-		return -ENODEV;
-	}
-
-	kp->base = devm_ioremap_resource(&pdev->dev, res);
+	kp->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(kp->base))
 		return PTR_ERR(kp->base);
 

From 3799836f606fdd85acd6807ed52032ab2ea3bce2 Mon Sep 17 00:00:00 2001
From: Yangtao Li <frank.li@vivo.com>
Date: Mon, 10 Jul 2023 15:26:06 -0700
Subject: [PATCH 0046/1189] Input: lpc32xx-keys - convert to
 devm_platform_ioremap_resource()

Use devm_platform_ioremap_resource() to simplify code.

Signed-off-by: Yangtao Li <frank.li@vivo.com>
Link: https://lore.kernel.org/r/20230705052346.39337-2-frank.li@vivo.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/lpc32xx-keys.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/drivers/input/keyboard/lpc32xx-keys.c b/drivers/input/keyboard/lpc32xx-keys.c
index 911e1181cd6f..322a87807159 100644
--- a/drivers/input/keyboard/lpc32xx-keys.c
+++ b/drivers/input/keyboard/lpc32xx-keys.c
@@ -160,17 +160,10 @@ static int lpc32xx_kscan_probe(struct platform_device *pdev)
 {
 	struct lpc32xx_kscan_drv *kscandat;
 	struct input_dev *input;
-	struct resource *res;
 	size_t keymap_size;
 	int error;
 	int irq;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(&pdev->dev, "failed to get platform I/O memory\n");
-		return -EINVAL;
-	}
-
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0)
 		return -EINVAL;
@@ -221,7 +214,7 @@ static int lpc32xx_kscan_probe(struct platform_device *pdev)
 
 	input_set_drvdata(kscandat->input, kscandat);
 
-	kscandat->kscan_base = devm_ioremap_resource(&pdev->dev, res);
+	kscandat->kscan_base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(kscandat->kscan_base))
 		return PTR_ERR(kscandat->kscan_base);
 

From b1066df414d7ef6d9674c259b8871f428e12fd63 Mon Sep 17 00:00:00 2001
From: Yangtao Li <frank.li@vivo.com>
Date: Mon, 10 Jul 2023 15:26:25 -0700
Subject: [PATCH 0047/1189] Input: nspire-keypad - use
 devm_platform_get_and_ioremap_resource()

Convert platform_get_resource(), devm_ioremap_resource() to a single
call to devm_platform_get_and_ioremap_resource(), as this is exactly
what this function does.

Signed-off-by: Yangtao Li <frank.li@vivo.com>
Link: https://lore.kernel.org/r/20230705052346.39337-3-frank.li@vivo.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/nspire-keypad.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/input/keyboard/nspire-keypad.c b/drivers/input/keyboard/nspire-keypad.c
index e9fa1423f136..096c18d7bca1 100644
--- a/drivers/input/keyboard/nspire-keypad.c
+++ b/drivers/input/keyboard/nspire-keypad.c
@@ -186,8 +186,7 @@ static int nspire_keypad_probe(struct platform_device *pdev)
 		return PTR_ERR(keypad->clk);
 	}
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	keypad->reg_base = devm_ioremap_resource(&pdev->dev, res);
+	keypad->reg_base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
 	if (IS_ERR(keypad->reg_base))
 		return PTR_ERR(keypad->reg_base);
 

From e79637731c6a386baa567f7210791b88216ec8bf Mon Sep 17 00:00:00 2001
From: Yangtao Li <frank.li@vivo.com>
Date: Mon, 10 Jul 2023 16:39:23 -0700
Subject: [PATCH 0048/1189] Input: omap4-keyad - convert to
 devm_platform_ioremap_resource()

Use devm_platform_ioremap_resource() to simplify code.

Signed-off-by: Yangtao Li <frank.li@vivo.com>
Link: https://lore.kernel.org/r/20230705052346.39337-4-frank.li@vivo.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/omap4-keypad.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/drivers/input/keyboard/omap4-keypad.c b/drivers/input/keyboard/omap4-keypad.c
index 9f085d5679db..773e55eed88b 100644
--- a/drivers/input/keyboard/omap4-keypad.c
+++ b/drivers/input/keyboard/omap4-keypad.c
@@ -341,17 +341,10 @@ static int omap4_keypad_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct omap4_keypad *keypad_data;
 	struct input_dev *input_dev;
-	struct resource *res;
 	unsigned int max_keys;
 	int irq;
 	int error;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(&pdev->dev, "no base address specified\n");
-		return -EINVAL;
-	}
-
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0)
 		return irq;
@@ -370,7 +363,7 @@ static int omap4_keypad_probe(struct platform_device *pdev)
 	if (error)
 		return error;
 
-	keypad_data->base = devm_ioremap_resource(dev, res);
+	keypad_data->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(keypad_data->base))
 		return PTR_ERR(keypad_data->base);
 

From db9842298ad525265d48aa6b9da20f37a4a36481 Mon Sep 17 00:00:00 2001
From: Yangtao Li <frank.li@vivo.com>
Date: Mon, 10 Jul 2023 16:40:10 -0700
Subject: [PATCH 0049/1189] Input: opencores-kbd - convert to
 devm_platform_ioremap_resource()

Use devm_platform_ioremap_resource() to simplify code.

Signed-off-by: Yangtao Li <frank.li@vivo.com>
Link: https://lore.kernel.org/r/20230705052346.39337-5-frank.li@vivo.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/opencores-kbd.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/drivers/input/keyboard/opencores-kbd.c b/drivers/input/keyboard/opencores-kbd.c
index b0ea387414c1..7ffe1a70c856 100644
--- a/drivers/input/keyboard/opencores-kbd.c
+++ b/drivers/input/keyboard/opencores-kbd.c
@@ -39,15 +39,8 @@ static int opencores_kbd_probe(struct platform_device *pdev)
 {
 	struct input_dev *input;
 	struct opencores_kbd *opencores_kbd;
-	struct resource *res;
 	int irq, i, error;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(&pdev->dev, "missing board memory resource\n");
-		return -EINVAL;
-	}
-
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0)
 		return -EINVAL;
@@ -65,7 +58,7 @@ static int opencores_kbd_probe(struct platform_device *pdev)
 
 	opencores_kbd->input = input;
 
-	opencores_kbd->addr = devm_ioremap_resource(&pdev->dev, res);
+	opencores_kbd->addr = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(opencores_kbd->addr))
 		return PTR_ERR(opencores_kbd->addr);
 

From 198a2ccaaab8fca64f7b367969038badae96f3bd Mon Sep 17 00:00:00 2001
From: Yangtao Li <frank.li@vivo.com>
Date: Mon, 10 Jul 2023 16:40:32 -0700
Subject: [PATCH 0050/1189] Input: pxa27x_keypad - convert to
 devm_platform_ioremap_resource()

Use devm_platform_ioremap_resource() to simplify code.

Signed-off-by: Yangtao Li <frank.li@vivo.com>
Link: https://lore.kernel.org/r/20230705052346.39337-6-frank.li@vivo.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/pxa27x_keypad.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/drivers/input/keyboard/pxa27x_keypad.c b/drivers/input/keyboard/pxa27x_keypad.c
index 871f858d0ba7..3724363d140e 100644
--- a/drivers/input/keyboard/pxa27x_keypad.c
+++ b/drivers/input/keyboard/pxa27x_keypad.c
@@ -717,7 +717,6 @@ static int pxa27x_keypad_probe(struct platform_device *pdev)
 	struct device_node *np = pdev->dev.of_node;
 	struct pxa27x_keypad *keypad;
 	struct input_dev *input_dev;
-	struct resource *res;
 	int irq, error;
 
 	/* Driver need build keycode from device tree or pdata */
@@ -728,12 +727,6 @@ static int pxa27x_keypad_probe(struct platform_device *pdev)
 	if (irq < 0)
 		return -ENXIO;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (res == NULL) {
-		dev_err(&pdev->dev, "failed to get I/O memory\n");
-		return -ENXIO;
-	}
-
 	keypad = devm_kzalloc(&pdev->dev, sizeof(*keypad),
 			      GFP_KERNEL);
 	if (!keypad)
@@ -747,7 +740,7 @@ static int pxa27x_keypad_probe(struct platform_device *pdev)
 	keypad->input_dev = input_dev;
 	keypad->irq = irq;
 
-	keypad->mmio_base = devm_ioremap_resource(&pdev->dev, res);
+	keypad->mmio_base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(keypad->mmio_base))
 		return PTR_ERR(keypad->mmio_base);
 

From b1c5590045a08751f3d523b2343e848365e6b046 Mon Sep 17 00:00:00 2001
From: Yangtao Li <frank.li@vivo.com>
Date: Mon, 10 Jul 2023 16:40:46 -0700
Subject: [PATCH 0051/1189] Input: sun4i-lradc-keys - convert to
 devm_platform_ioremap_resource()

Use devm_platform_ioremap_resource() to simplify code.

Signed-off-by: Yangtao Li <frank.li@vivo.com>
Link: https://lore.kernel.org/r/20230705052346.39337-7-frank.li@vivo.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/sun4i-lradc-keys.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/input/keyboard/sun4i-lradc-keys.c b/drivers/input/keyboard/sun4i-lradc-keys.c
index 15c15c0958b0..95d927cc8b7e 100644
--- a/drivers/input/keyboard/sun4i-lradc-keys.c
+++ b/drivers/input/keyboard/sun4i-lradc-keys.c
@@ -307,8 +307,7 @@ static int sun4i_lradc_probe(struct platform_device *pdev)
 
 	input_set_drvdata(lradc->input, lradc);
 
-	lradc->base = devm_ioremap_resource(dev,
-			      platform_get_resource(pdev, IORESOURCE_MEM, 0));
+	lradc->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(lradc->base))
 		return PTR_ERR(lradc->base);
 

From c0551abb0557bb25440d57b60fc11f8ed13d62e9 Mon Sep 17 00:00:00 2001
From: Yangtao Li <frank.li@vivo.com>
Date: Mon, 10 Jul 2023 17:29:41 -0700
Subject: [PATCH 0052/1189] Input: nomadik-ske-keypad - convert to use devm_*
 api

Use devm_* api to simplify code, this makes it unnecessary to explicitly
release resources.

Signed-off-by: Yangtao Li <frank.li@vivo.com>
Link: https://lore.kernel.org/r/20230705052346.39337-8-frank.li@vivo.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/nomadik-ske-keypad.c | 127 ++++++--------------
 1 file changed, 35 insertions(+), 92 deletions(-)

diff --git a/drivers/input/keyboard/nomadik-ske-keypad.c b/drivers/input/keyboard/nomadik-ske-keypad.c
index 970f2a671c2e..b3ccc97f61e1 100644
--- a/drivers/input/keyboard/nomadik-ske-keypad.c
+++ b/drivers/input/keyboard/nomadik-ske-keypad.c
@@ -221,13 +221,20 @@ static irqreturn_t ske_keypad_irq(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static void ske_keypad_board_exit(void *data)
+{
+	struct ske_keypad *keypad = data;
+
+	keypad->board->exit();
+}
+
 static int __init ske_keypad_probe(struct platform_device *pdev)
 {
 	const struct ske_keypad_platform_data *plat =
 			dev_get_platdata(&pdev->dev);
+	struct device *dev = &pdev->dev;
 	struct ske_keypad *keypad;
 	struct input_dev *input;
-	struct resource *res;
 	int irq;
 	int error;
 
@@ -238,20 +245,14 @@ static int __init ske_keypad_probe(struct platform_device *pdev)
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0)
-		return -EINVAL;
+		return irq;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(&pdev->dev, "missing platform resources\n");
-		return -EINVAL;
-	}
-
-	keypad = kzalloc(sizeof(struct ske_keypad), GFP_KERNEL);
-	input = input_allocate_device();
+	keypad = devm_kzalloc(dev, sizeof(struct ske_keypad),
+			      GFP_KERNEL);
+	input = devm_input_allocate_device(dev);
 	if (!keypad || !input) {
 		dev_err(&pdev->dev, "failed to allocate keypad memory\n");
-		error = -ENOMEM;
-		goto err_free_mem;
+		return -ENOMEM;
 	}
 
 	keypad->irq = irq;
@@ -259,31 +260,20 @@ static int __init ske_keypad_probe(struct platform_device *pdev)
 	keypad->input = input;
 	spin_lock_init(&keypad->ske_keypad_lock);
 
-	if (!request_mem_region(res->start, resource_size(res), pdev->name)) {
-		dev_err(&pdev->dev, "failed to request I/O memory\n");
-		error = -EBUSY;
-		goto err_free_mem;
-	}
+	keypad->reg_base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(keypad->reg_base))
+		return PTR_ERR(keypad->reg_base);
 
-	keypad->reg_base = ioremap(res->start, resource_size(res));
-	if (!keypad->reg_base) {
-		dev_err(&pdev->dev, "failed to remap I/O memory\n");
-		error = -ENXIO;
-		goto err_free_mem_region;
-	}
-
-	keypad->pclk = clk_get(&pdev->dev, "apb_pclk");
+	keypad->pclk = devm_clk_get_enabled(dev, "apb_pclk");
 	if (IS_ERR(keypad->pclk)) {
 		dev_err(&pdev->dev, "failed to get pclk\n");
-		error = PTR_ERR(keypad->pclk);
-		goto err_iounmap;
+		return PTR_ERR(keypad->pclk);
 	}
 
-	keypad->clk = clk_get(&pdev->dev, NULL);
+	keypad->clk = devm_clk_get_enabled(dev, NULL);
 	if (IS_ERR(keypad->clk)) {
 		dev_err(&pdev->dev, "failed to get clk\n");
-		error = PTR_ERR(keypad->clk);
-		goto err_pclk;
+		return PTR_ERR(keypad->clk);
 	}
 
 	input->id.bustype = BUS_HOST;
@@ -295,48 +285,43 @@ static int __init ske_keypad_probe(struct platform_device *pdev)
 					   keypad->keymap, input);
 	if (error) {
 		dev_err(&pdev->dev, "Failed to build keymap\n");
-		goto err_clk;
+		return error;
 	}
 
 	input_set_capability(input, EV_MSC, MSC_SCAN);
 	if (!plat->no_autorepeat)
 		__set_bit(EV_REP, input->evbit);
 
-	error = clk_prepare_enable(keypad->pclk);
-	if (error) {
-		dev_err(&pdev->dev, "Failed to prepare/enable pclk\n");
-		goto err_clk;
-	}
-
-	error = clk_prepare_enable(keypad->clk);
-	if (error) {
-		dev_err(&pdev->dev, "Failed to prepare/enable clk\n");
-		goto err_pclk_disable;
-	}
-
-
 	/* go through board initialization helpers */
 	if (keypad->board->init)
 		keypad->board->init();
 
+	if (keypad->board->exit) {
+		error = devm_add_action_or_reset(dev, ske_keypad_board_exit,
+						 keypad);
+		if (error)
+			return error;
+	}
+
 	error = ske_keypad_chip_init(keypad);
 	if (error) {
 		dev_err(&pdev->dev, "unable to init keypad hardware\n");
-		goto err_clk_disable;
+		return error;
 	}
 
-	error = request_threaded_irq(keypad->irq, NULL, ske_keypad_irq,
-				     IRQF_ONESHOT, "ske-keypad", keypad);
+	error = devm_request_threaded_irq(dev, keypad->irq,
+					  NULL, ske_keypad_irq,
+					  IRQF_ONESHOT, "ske-keypad", keypad);
 	if (error) {
 		dev_err(&pdev->dev, "allocate irq %d failed\n", keypad->irq);
-		goto err_clk_disable;
+		return error;
 	}
 
 	error = input_register_device(input);
 	if (error) {
 		dev_err(&pdev->dev,
-				"unable to register input device: %d\n", error);
-		goto err_free_irq;
+			"unable to register input device: %d\n", error);
+		return error;
 	}
 
 	if (plat->wakeup_enable)
@@ -344,47 +329,6 @@ static int __init ske_keypad_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, keypad);
 
-	return 0;
-
-err_free_irq:
-	free_irq(keypad->irq, keypad);
-err_clk_disable:
-	clk_disable_unprepare(keypad->clk);
-err_pclk_disable:
-	clk_disable_unprepare(keypad->pclk);
-err_clk:
-	clk_put(keypad->clk);
-err_pclk:
-	clk_put(keypad->pclk);
-err_iounmap:
-	iounmap(keypad->reg_base);
-err_free_mem_region:
-	release_mem_region(res->start, resource_size(res));
-err_free_mem:
-	input_free_device(input);
-	kfree(keypad);
-	return error;
-}
-
-static int ske_keypad_remove(struct platform_device *pdev)
-{
-	struct ske_keypad *keypad = platform_get_drvdata(pdev);
-	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-
-	free_irq(keypad->irq, keypad);
-
-	input_unregister_device(keypad->input);
-
-	clk_disable_unprepare(keypad->clk);
-	clk_put(keypad->clk);
-
-	if (keypad->board->exit)
-		keypad->board->exit();
-
-	iounmap(keypad->reg_base);
-	release_mem_region(res->start, resource_size(res));
-	kfree(keypad);
-
 	return 0;
 }
 
@@ -424,7 +368,6 @@ static struct platform_driver ske_keypad_driver = {
 		.name = "nmk-ske-keypad",
 		.pm = pm_sleep_ptr(&ske_keypad_dev_pm_ops),
 	},
-	.remove = ske_keypad_remove,
 };
 
 module_platform_driver_probe(ske_keypad_driver, ske_keypad_probe);

From f1efdf7fcef91fdeb2664b5856fdc51a049b8892 Mon Sep 17 00:00:00 2001
From: Yangtao Li <frank.li@vivo.com>
Date: Mon, 10 Jul 2023 17:22:04 -0700
Subject: [PATCH 0053/1189] Input: lpc32xx_ts - convert to use devm_* api

Use devm_* api to simplify code, this makes it unnecessary to explicitly
release resources.

Signed-off-by: Yangtao Li <frank.li@vivo.com>
Link: https://lore.kernel.org/r/20230705052346.39337-10-frank.li@vivo.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/lpc32xx_ts.c | 98 ++++++--------------------
 1 file changed, 22 insertions(+), 76 deletions(-)

diff --git a/drivers/input/touchscreen/lpc32xx_ts.c b/drivers/input/touchscreen/lpc32xx_ts.c
index 15b5cb763526..9bad8b93c039 100644
--- a/drivers/input/touchscreen/lpc32xx_ts.c
+++ b/drivers/input/touchscreen/lpc32xx_ts.c
@@ -198,54 +198,36 @@ static void lpc32xx_ts_close(struct input_dev *dev)
 
 static int lpc32xx_ts_probe(struct platform_device *pdev)
 {
+	struct device *dev = &pdev->dev;
 	struct lpc32xx_tsc *tsc;
 	struct input_dev *input;
-	struct resource *res;
-	resource_size_t size;
 	int irq;
 	int error;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(&pdev->dev, "Can't get memory resource\n");
-		return -ENOENT;
-	}
-
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0)
 		return irq;
 
-	tsc = kzalloc(sizeof(*tsc), GFP_KERNEL);
-	input = input_allocate_device();
-	if (!tsc || !input) {
-		dev_err(&pdev->dev, "failed allocating memory\n");
-		error = -ENOMEM;
-		goto err_free_mem;
-	}
+	tsc = devm_kzalloc(dev, sizeof(*tsc), GFP_KERNEL);
+	if (!tsc)
+		return -ENOMEM;
 
-	tsc->dev = input;
 	tsc->irq = irq;
 
-	size = resource_size(res);
+	tsc->tsc_base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(tsc->tsc_base))
+		return PTR_ERR(tsc->tsc_base);
 
-	if (!request_mem_region(res->start, size, pdev->name)) {
-		dev_err(&pdev->dev, "TSC registers are not free\n");
-		error = -EBUSY;
-		goto err_free_mem;
-	}
-
-	tsc->tsc_base = ioremap(res->start, size);
-	if (!tsc->tsc_base) {
-		dev_err(&pdev->dev, "Can't map memory\n");
-		error = -ENOMEM;
-		goto err_release_mem;
-	}
-
-	tsc->clk = clk_get(&pdev->dev, NULL);
+	tsc->clk = devm_clk_get(dev, NULL);
 	if (IS_ERR(tsc->clk)) {
 		dev_err(&pdev->dev, "failed getting clock\n");
-		error = PTR_ERR(tsc->clk);
-		goto err_unmap;
+		return PTR_ERR(tsc->clk);
+	}
+
+	input = devm_input_allocate_device(dev);
+	if (!input) {
+		dev_err(&pdev->dev, "failed allocating input device\n");
+		return -ENOMEM;
 	}
 
 	input->name = MOD_NAME;
@@ -254,68 +236,33 @@ static int lpc32xx_ts_probe(struct platform_device *pdev)
 	input->id.vendor = 0x0001;
 	input->id.product = 0x0002;
 	input->id.version = 0x0100;
-	input->dev.parent = &pdev->dev;
 	input->open = lpc32xx_ts_open;
 	input->close = lpc32xx_ts_close;
 
-	input->evbit[0] = BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS);
-	input->keybit[BIT_WORD(BTN_TOUCH)] = BIT_MASK(BTN_TOUCH);
+	input_set_capability(input, EV_KEY, BTN_TOUCH);
 	input_set_abs_params(input, ABS_X, LPC32XX_TSC_MIN_XY_VAL,
 			     LPC32XX_TSC_MAX_XY_VAL, 0, 0);
 	input_set_abs_params(input, ABS_Y, LPC32XX_TSC_MIN_XY_VAL,
 			     LPC32XX_TSC_MAX_XY_VAL, 0, 0);
 
 	input_set_drvdata(input, tsc);
+	tsc->dev = input;
 
-	error = request_irq(tsc->irq, lpc32xx_ts_interrupt,
-			    0, pdev->name, tsc);
+	error = devm_request_irq(dev, tsc->irq, lpc32xx_ts_interrupt,
+				 0, pdev->name, tsc);
 	if (error) {
 		dev_err(&pdev->dev, "failed requesting interrupt\n");
-		goto err_put_clock;
+		return error;
 	}
 
 	error = input_register_device(input);
 	if (error) {
 		dev_err(&pdev->dev, "failed registering input device\n");
-		goto err_free_irq;
+		return error;
 	}
 
 	platform_set_drvdata(pdev, tsc);
-	device_init_wakeup(&pdev->dev, 1);
-
-	return 0;
-
-err_free_irq:
-	free_irq(tsc->irq, tsc);
-err_put_clock:
-	clk_put(tsc->clk);
-err_unmap:
-	iounmap(tsc->tsc_base);
-err_release_mem:
-	release_mem_region(res->start, size);
-err_free_mem:
-	input_free_device(input);
-	kfree(tsc);
-
-	return error;
-}
-
-static int lpc32xx_ts_remove(struct platform_device *pdev)
-{
-	struct lpc32xx_tsc *tsc = platform_get_drvdata(pdev);
-	struct resource *res;
-
-	free_irq(tsc->irq, tsc);
-
-	input_unregister_device(tsc->dev);
-
-	clk_put(tsc->clk);
-
-	iounmap(tsc->tsc_base);
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	release_mem_region(res->start, resource_size(res));
-
-	kfree(tsc);
+	device_init_wakeup(&pdev->dev, true);
 
 	return 0;
 }
@@ -384,7 +331,6 @@ MODULE_DEVICE_TABLE(of, lpc32xx_tsc_of_match);
 
 static struct platform_driver lpc32xx_ts_driver = {
 	.probe		= lpc32xx_ts_probe,
-	.remove		= lpc32xx_ts_remove,
 	.driver		= {
 		.name	= MOD_NAME,
 		.pm	= LPC32XX_TS_PM_OPS,

From ea55d5a2cf7c507a9ac03b41716bf1877edad153 Mon Sep 17 00:00:00 2001
From: Oliver Upton <oliver.upton@linux.dev>
Date: Mon, 10 Jul 2023 19:31:37 +0000
Subject: [PATCH 0054/1189] KVM: arm64: Delete pointless switch statement in
 kvm_reset_vcpu()

The vCPU target hasn't mattered for quite a long time now. Delete the
useless switch statement in kvm_reset_vcpu(), which hilariously only had
a default case in it.

Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230710193140.1706399-2-oliver.upton@linux.dev
---
 arch/arm64/kvm/reset.c | 23 +++++++++--------------
 1 file changed, 9 insertions(+), 14 deletions(-)

diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index bc8556b6f459..7a65a35ee4ac 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -248,21 +248,16 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 		}
 	}
 
-	switch (vcpu->arch.target) {
-	default:
-		if (vcpu_el1_is_32bit(vcpu)) {
-			pstate = VCPU_RESET_PSTATE_SVC;
-		} else if (vcpu_has_nv(vcpu)) {
-			pstate = VCPU_RESET_PSTATE_EL2;
-		} else {
-			pstate = VCPU_RESET_PSTATE_EL1;
-		}
+	if (vcpu_el1_is_32bit(vcpu))
+		pstate = VCPU_RESET_PSTATE_SVC;
+	else if (vcpu_has_nv(vcpu))
+		pstate = VCPU_RESET_PSTATE_EL2;
+	else
+		pstate = VCPU_RESET_PSTATE_EL1;
 
-		if (kvm_vcpu_has_pmu(vcpu) && !kvm_arm_support_pmu_v3()) {
-			ret = -EINVAL;
-			goto out;
-		}
-		break;
+	if (kvm_vcpu_has_pmu(vcpu) && !kvm_arm_support_pmu_v3()) {
+		ret = -EINVAL;
+		goto out;
 	}
 
 	/* Reset core registers */

From c8a67729b8a36a5f4857de645ee9808fc99d8618 Mon Sep 17 00:00:00 2001
From: Oliver Upton <oliver.upton@linux.dev>
Date: Mon, 10 Jul 2023 19:31:38 +0000
Subject: [PATCH 0055/1189] KVM: arm64: Remove pointless check for changed init
 target

At any time there is only a single valid value for KVM_ARM_VCPU_INIT,
depending on the current CPU implementation. In all likelihood, this
will be the generic ARMv8 target.

Drop the pointless check for a changed target value between calls to
KVM_ARM_VCPU_INIT and instead rely on the check against
kvm_target_cpu().

Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230710193140.1706399-3-oliver.upton@linux.dev
---
 arch/arm64/kvm/arm.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index c2c14059f6a8..3f844934b9f3 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -1212,8 +1212,7 @@ static bool kvm_vcpu_init_changed(struct kvm_vcpu *vcpu,
 {
 	unsigned long features = init->features[0];
 
-	return !bitmap_equal(vcpu->arch.features, &features, KVM_VCPU_MAX_FEATURES) ||
-			vcpu->arch.target != init->target;
+	return !bitmap_equal(vcpu->arch.features, &features, KVM_VCPU_MAX_FEATURES);
 }
 
 static int __kvm_vcpu_set_target(struct kvm_vcpu *vcpu,

From ef98406036769107d5c49a519b31c940910b98d3 Mon Sep 17 00:00:00 2001
From: Oliver Upton <oliver.upton@linux.dev>
Date: Mon, 10 Jul 2023 19:31:39 +0000
Subject: [PATCH 0056/1189] KVM: arm64: Replace vCPU target with a
 configuration flag

The value of kvm_vcpu_arch::target has been used to determine if a vCPU
has actually been initialized. Storing this as an integer is needless at
this point, as KVM doesn't do any microarch-specific emulation in the
first place. Instead, all we care about is whether or not the vCPU has
been initialized.

Delete the field in favor of a vCPU configuration flag indicating if
KVM_ARM_VCPU_INIT has completed for the vCPU.

Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230710193140.1706399-4-oliver.upton@linux.dev
---
 arch/arm64/include/asm/kvm_host.h |  5 +++--
 arch/arm64/kvm/arm.c              | 12 +++++-------
 arch/arm64/kvm/hyp/nvhe/switch.c  |  2 +-
 3 files changed, 9 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 8b6096753740..b53105bccff9 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -567,8 +567,7 @@ struct kvm_vcpu_arch {
 	/* Cache some mmu pages needed inside spinlock regions */
 	struct kvm_mmu_memory_cache mmu_page_cache;
 
-	/* Target CPU and feature flags */
-	int target;
+	/* feature flags */
 	DECLARE_BITMAP(features, KVM_VCPU_MAX_FEATURES);
 
 	/* Virtual SError ESR to restore when HCR_EL2.VSE is set */
@@ -669,6 +668,8 @@ struct kvm_vcpu_arch {
 #define VCPU_SVE_FINALIZED	__vcpu_single_flag(cflags, BIT(1))
 /* PTRAUTH exposed to guest */
 #define GUEST_HAS_PTRAUTH	__vcpu_single_flag(cflags, BIT(2))
+/* KVM_ARM_VCPU_INIT completed */
+#define VCPU_INITIALIZED	__vcpu_single_flag(cflags, BIT(3))
 
 /* Exception pending */
 #define PENDING_EXCEPTION	__vcpu_single_flag(iflags, BIT(0))
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 3f844934b9f3..13f1bde0bc2d 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -360,7 +360,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 #endif
 
 	/* Force users to call KVM_ARM_VCPU_INIT */
-	vcpu->arch.target = -1;
+	vcpu_clear_flag(vcpu, VCPU_INITIALIZED);
 	bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES);
 
 	vcpu->arch.mmu_page_cache.gfp_zero = __GFP_ZERO;
@@ -569,7 +569,7 @@ unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu)
 
 static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.target >= 0;
+	return vcpu_get_flag(vcpu, VCPU_INITIALIZED);
 }
 
 /*
@@ -1051,7 +1051,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 			 * invalid. The VMM can try and fix it by issuing  a
 			 * KVM_ARM_VCPU_INIT if it really wants to.
 			 */
-			vcpu->arch.target = -1;
+			vcpu_clear_flag(vcpu, VCPU_INITIALIZED);
 			ret = ARM_EXCEPTION_IL;
 		}
 
@@ -1228,20 +1228,18 @@ static int __kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
 	    !bitmap_equal(kvm->arch.vcpu_features, &features, KVM_VCPU_MAX_FEATURES))
 		goto out_unlock;
 
-	vcpu->arch.target = init->target;
 	bitmap_copy(vcpu->arch.features, &features, KVM_VCPU_MAX_FEATURES);
 
 	/* Now we know what it is, we can reset it. */
 	ret = kvm_reset_vcpu(vcpu);
 	if (ret) {
-		vcpu->arch.target = -1;
 		bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES);
 		goto out_unlock;
 	}
 
 	bitmap_copy(kvm->arch.vcpu_features, &features, KVM_VCPU_MAX_FEATURES);
 	set_bit(KVM_ARCH_FLAG_VCPU_FEATURES_CONFIGURED, &kvm->arch.flags);
-
+	vcpu_set_flag(vcpu, VCPU_INITIALIZED);
 out_unlock:
 	mutex_unlock(&kvm->arch.config_lock);
 	return ret;
@@ -1259,7 +1257,7 @@ static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
 	if (ret)
 		return ret;
 
-	if (vcpu->arch.target == -1)
+	if (!kvm_vcpu_initialized(vcpu))
 		return __kvm_vcpu_set_target(vcpu, init);
 
 	if (kvm_vcpu_init_changed(vcpu, init))
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index 0a6271052def..b9caac3e7b1d 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -236,7 +236,7 @@ static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code)
 		 * KVM_ARM_VCPU_INIT, however, this is likely not possible for
 		 * protected VMs.
 		 */
-		vcpu->arch.target = -1;
+		vcpu_clear_flag(vcpu, VCPU_INITIALIZED);
 		*exit_code &= BIT(ARM_EXIT_WITH_SERROR_BIT);
 		*exit_code |= ARM_EXCEPTION_IL;
 	}

From 5346f7e13e5eb134920a14504b6900c6168dd16e Mon Sep 17 00:00:00 2001
From: Oliver Upton <oliver.upton@linux.dev>
Date: Mon, 10 Jul 2023 19:31:40 +0000
Subject: [PATCH 0057/1189] KVM: arm64: Always return generic v8 as the
 preferred target

Userspace selecting an implementation-specific vCPU target has been
completely useless for a very long time. Let's go whole hog and start
returning the generic v8 target across all implementations as the
preferred target.

Uphold the pre-existing behavior by tolerating either the generic target
or an implementation-specific target if the vCPU happens to be running
on one of the lucky few parts.

Acked-by: Zenghui Yu <yuzenghui@huawei.com>
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230710193140.1706399-5-oliver.upton@linux.dev
---
 arch/arm64/include/asm/kvm_host.h |  1 -
 arch/arm64/kvm/arm.c              |  9 +++++----
 arch/arm64/kvm/guest.c            | 15 ---------------
 3 files changed, 5 insertions(+), 20 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index b53105bccff9..ed60277e834a 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -898,7 +898,6 @@ struct kvm_vcpu_stat {
 	u64 exits;
 };
 
-void kvm_vcpu_preferred_target(struct kvm_vcpu_init *init);
 unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu);
 int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices);
 int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 13f1bde0bc2d..9ab17ecd76bb 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -1250,7 +1250,8 @@ static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
 {
 	int ret;
 
-	if (init->target != kvm_target_cpu())
+	if (init->target != KVM_ARM_TARGET_GENERIC_V8 &&
+	    init->target != kvm_target_cpu())
 		return -EINVAL;
 
 	ret = kvm_vcpu_init_check_features(vcpu, init);
@@ -1585,9 +1586,9 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 		return kvm_vm_ioctl_set_device_addr(kvm, &dev_addr);
 	}
 	case KVM_ARM_PREFERRED_TARGET: {
-		struct kvm_vcpu_init init;
-
-		kvm_vcpu_preferred_target(&init);
+		struct kvm_vcpu_init init = {
+			.target = KVM_ARM_TARGET_GENERIC_V8,
+		};
 
 		if (copy_to_user(argp, &init, sizeof(init)))
 			return -EFAULT;
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 20280a5233f6..95f6945c4432 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -884,21 +884,6 @@ u32 __attribute_const__ kvm_target_cpu(void)
 	return KVM_ARM_TARGET_GENERIC_V8;
 }
 
-void kvm_vcpu_preferred_target(struct kvm_vcpu_init *init)
-{
-	u32 target = kvm_target_cpu();
-
-	memset(init, 0, sizeof(*init));
-
-	/*
-	 * For now, we don't return any features.
-	 * In future, we might use features to return target
-	 * specific features available for the preferred
-	 * target type.
-	 */
-	init->target = (__u32)target;
-}
-
 int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
 	return -EINVAL;

From 0b64150c34290df5bf962b3b7e45389b0acb03ae Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Wed, 12 Jul 2023 11:53:23 -0700
Subject: [PATCH 0058/1189] Input: bcm-keypad - correct dev_err_probe() error

Pass proper PTR_ERR as dev_err_probe() argument.

Fixes: a2c795b696b2 ("Input: bcm-keypad - simplify with dev_err_probe()")
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/r/202306261505.wTjCXRIO-lkp@intel.com/
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20230711072449.43569-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/bcm-keypad.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/input/keyboard/bcm-keypad.c b/drivers/input/keyboard/bcm-keypad.c
index 0aa6ef0da0ee..f3c3746acd4c 100644
--- a/drivers/input/keyboard/bcm-keypad.c
+++ b/drivers/input/keyboard/bcm-keypad.c
@@ -359,7 +359,7 @@ static int bcm_kp_probe(struct platform_device *pdev)
 	/* Enable clock */
 	kp->clk = devm_clk_get_optional(&pdev->dev, "peri_clk");
 	if (IS_ERR(kp->clk)) {
-		return dev_err_probe(&pdev->dev, error, "Failed to get clock\n");
+		return dev_err_probe(&pdev->dev, PTR_ERR(kp->clk), "Failed to get clock\n");
 	} else if (!kp->clk) {
 		dev_dbg(&pdev->dev, "No clock specified. Assuming it's enabled\n");
 	} else {

From eb09074bdb05ffd6bfe77f8b4a41b76ef78c997b Mon Sep 17 00:00:00 2001
From: Werner Sembach <wse@tuxedocomputers.com>
Date: Wed, 12 Jul 2023 11:56:51 -0700
Subject: [PATCH 0059/1189] Input: i8042 - add quirk for TUXEDO Gemini 17
 Gen1/Clevo PD70PN

The touchpad of this device is both connected via PS/2 and i2c. This causes
strange behavior when both driver fight for control. The easy fix is to
prevent the PS/2 driver from accessing the mouse port as the full feature
set of the touchpad is only supported in the i2c interface anyway.

The strange behavior in this case is, that when an external screen is
connected and the notebook is closed, the pointer on the external screen is
moving to the lower right corner. When the notebook is opened again, this
movement stops, but the touchpad clicks are unresponsive afterwards until
reboot.

Signed-off-by: Werner Sembach <wse@tuxedocomputers.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230607173331.851192-1-wse@tuxedocomputers.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/i8042-acpipnpio.h | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h
index 028e45bd050b..1724d6cb8649 100644
--- a/drivers/input/serio/i8042-acpipnpio.h
+++ b/drivers/input/serio/i8042-acpipnpio.h
@@ -1281,6 +1281,13 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
 					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
 	},
+	/* See comment on TUXEDO InfinityBook S17 Gen6 / Clevo NS70MU above */
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "PD5x_7xPNP_PNR_PNN_PNT"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_NOAUX)
+	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "X170SM"),

From 0859c1764c77dd61adf46e3d0c440145118d9e0e Mon Sep 17 00:00:00 2001
From: Roi L <roeilev321_@outlook.com>
Date: Wed, 12 Jul 2023 14:09:06 -0700
Subject: [PATCH 0060/1189] Input: rotary_encoder - don't double assign
 input->dev.parent

devm_input_allocate_device() already assigns the @dev.parent field of the
input device/structure, so there's no need to reassign input->dev.parent
to dev.

Signed-off-by: Roi L <roeilev321_@outlook.com>
Link: https://lore.kernel.org/r/PH0P220MB0460B69CA018F5515F5FACDDDD53A@PH0P220MB0460.NAMP220.PROD.OUTLOOK.COM
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/rotary_encoder.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/input/misc/rotary_encoder.c b/drivers/input/misc/rotary_encoder.c
index fb3a34f8eccd..e94cab8133be 100644
--- a/drivers/input/misc/rotary_encoder.c
+++ b/drivers/input/misc/rotary_encoder.c
@@ -251,7 +251,6 @@ static int rotary_encoder_probe(struct platform_device *pdev)
 
 	input->name = pdev->name;
 	input->id.bustype = BUS_HOST;
-	input->dev.parent = dev;
 
 	if (encoder->relative_axis)
 		input_set_capability(input, EV_REL, encoder->axis);

From d6239463206525f2b64bbf9bfeb83a81f0235914 Mon Sep 17 00:00:00 2001
From: Jeff LaBundy <jeff@labundy.com>
Date: Mon, 29 May 2023 19:33:47 -0500
Subject: [PATCH 0061/1189] dt-bindings: input: Add bindings for Azoteq
 IQS7210A/7211A/E

Add bindings for the Azoteq IQS7210A/7211A/E family of trackpad/
touchscreen controllers.

Signed-off-by: Jeff LaBundy <jeff@labundy.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/ZHVEa0yM1LLUJEfO@nixie71
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 .../input/touchscreen/azoteq,iqs7211.yaml     | 769 ++++++++++++++++++
 1 file changed, 769 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/input/touchscreen/azoteq,iqs7211.yaml

diff --git a/Documentation/devicetree/bindings/input/touchscreen/azoteq,iqs7211.yaml b/Documentation/devicetree/bindings/input/touchscreen/azoteq,iqs7211.yaml
new file mode 100644
index 000000000000..8cf371b99f19
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/touchscreen/azoteq,iqs7211.yaml
@@ -0,0 +1,769 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/input/touchscreen/azoteq,iqs7211.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Azoteq IQS7210A/7211A/E Trackpad/Touchscreen Controller
+
+maintainers:
+  - Jeff LaBundy <jeff@labundy.com>
+
+description: |
+  The Azoteq IQS7210A, IQS7211A and IQS7211E trackpad and touchscreen control-
+  lers employ projected-capacitance sensing and can track two contacts.
+
+  Link to datasheets: https://www.azoteq.com/
+
+properties:
+  compatible:
+    enum:
+      - azoteq,iqs7210a
+      - azoteq,iqs7211a
+      - azoteq,iqs7211e
+
+  reg:
+    maxItems: 1
+
+  irq-gpios:
+    maxItems: 1
+    description:
+      Specifies the GPIO connected to the device's active-low RDY output. The
+      pin doubles as the IQS7211E's active-low MCLR input, in which case this
+      GPIO must be configured as open-drain.
+
+  reset-gpios:
+    maxItems: 1
+    description:
+      Specifies the GPIO connected to the device's active-low MCLR input. The
+      device is temporarily held in hardware reset prior to initialization if
+      this property is present.
+
+  azoteq,forced-comms:
+    type: boolean
+    description:
+      Enables forced communication; to be used with host adapters that cannot
+      tolerate clock stretching.
+
+  azoteq,forced-comms-default:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    enum: [0, 1]
+    description:
+      Indicates if the device's OTP memory enables (1) or disables (0) forced
+      communication by default. Specifying this property can expedite startup
+      time if the default value is known.
+
+      If this property is not specified, communication is not initiated until
+      the device asserts its RDY pin shortly after exiting hardware reset. At
+      that point, forced communication is either enabled or disabled based on
+      the presence or absence of the 'azoteq,forced-comms' property.
+
+  azoteq,rate-active-ms:
+    minimum: 0
+    maximum: 65535
+    description: Specifies the report rate (in ms) during active mode.
+
+  azoteq,rate-touch-ms:
+    minimum: 0
+    maximum: 65535
+    description: Specifies the report rate (in ms) during idle-touch mode.
+
+  azoteq,rate-idle-ms:
+    minimum: 0
+    maximum: 65535
+    description: Specifies the report rate (in ms) during idle mode.
+
+  azoteq,rate-lp1-ms:
+    minimum: 0
+    maximum: 65535
+    description: Specifies the report rate (in ms) during low-power mode 1.
+
+  azoteq,rate-lp2-ms:
+    minimum: 0
+    maximum: 65535
+    description: Specifies the report rate (in ms) during low-power mode 2.
+
+  azoteq,timeout-active-ms:
+    multipleOf: 1000
+    minimum: 0
+    maximum: 65535000
+    description:
+      Specifies the length of time (in ms) to wait for an event before moving
+      from active mode to idle or idle-touch modes.
+
+  azoteq,timeout-touch-ms:
+    multipleOf: 1000
+    minimum: 0
+    maximum: 65535000
+    description:
+      Specifies the length of time (in ms) to wait for an event before moving
+      from idle-touch mode to idle mode.
+
+  azoteq,timeout-idle-ms:
+    multipleOf: 1000
+    minimum: 0
+    maximum: 65535000
+    description:
+      Specifies the length of time (in ms) to wait for an event before moving
+      from idle mode to low-power mode 1.
+
+  azoteq,timeout-lp1-ms:
+    multipleOf: 1000
+    minimum: 0
+    maximum: 65535000
+    description:
+      Specifies the length of time (in ms) to wait for an event before moving
+      from low-power mode 1 to low-power mode 2.
+
+  azoteq,timeout-lp2-ms:
+    multipleOf: 1000
+    minimum: 0
+    maximum: 60000
+    description:
+      Specifies the rate (in ms) at which the trackpad reference values
+      are updated during low-power modes 1 and 2.
+
+  azoteq,timeout-ati-ms:
+    multipleOf: 1000
+    minimum: 0
+    maximum: 60000
+    description:
+      Specifies the delay (in ms) before the automatic tuning implementation
+      (ATI) is retried in the event it fails to complete.
+
+  azoteq,timeout-comms-ms:
+    minimum: 0
+    maximum: 65535
+    description:
+      Specifies the delay (in ms) before a communication window is closed.
+
+  azoteq,timeout-press-ms:
+    multipleOf: 1000
+    minimum: 0
+    maximum: 60000
+    description:
+      Specifies the length of time (in ms) to wait before automatically
+      releasing a press event. Specify zero to allow the press state to
+      persist indefinitely.
+
+  azoteq,fosc-freq:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    enum: [0, 1]
+    description: |
+      Specifies the device's core clock frequency as follows:
+      0: 14 MHz
+      1: 18 MHz
+
+  azoteq,fosc-trim:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    minimum: 0
+    maximum: 15
+    description: Specifies the device's core clock frequency trim.
+
+  azoteq,num-contacts:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    minimum: 0
+    maximum: 2
+    default: 0
+    description: Specifies the number of contacts reported by the device.
+
+  azoteq,contact-split:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    minimum: 0
+    maximum: 255
+    description: Specifies the contact (finger) split factor.
+
+  azoteq,trim-x:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    minimum: 0
+    maximum: 255
+    description: Specifies the horizontal trim width.
+
+  azoteq,trim-y:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    minimum: 0
+    maximum: 255
+    description: Specifies the vertical trim height.
+
+  trackpad:
+    type: object
+    description: Represents all channels associated with the trackpad.
+
+    properties:
+      azoteq,rx-enable:
+        $ref: /schemas/types.yaml#/definitions/uint32-array
+        minItems: 1
+        maxItems: 8
+        items:
+          minimum: 0
+          maximum: 7
+        description:
+          Specifies the order of the CRx pin(s) associated with the trackpad.
+
+      azoteq,tx-enable:
+        $ref: /schemas/types.yaml#/definitions/uint32-array
+        minItems: 1
+        maxItems: 12
+        items:
+          minimum: 0
+          maximum: 11
+        description:
+          Specifies the order of the CTx pin(s) associated with the trackpad.
+
+      azoteq,channel-select:
+        $ref: /schemas/types.yaml#/definitions/uint32-array
+        minItems: 1
+        maxItems: 36
+        items:
+          minimum: 0
+          maximum: 255
+        description: |
+          Specifies the channels mapped to each cycle in the following order:
+          Cycle 0, slot 0
+          Cycle 0, slot 1
+          Cycle 1, slot 0
+          Cycle 1, slot 1
+          ...and so on. Specify 255 to disable a given slot.
+
+      azoteq,ati-frac-div-fine:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 31
+        description: Specifies the trackpad's ATI fine fractional divider.
+
+      azoteq,ati-frac-mult-coarse:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 15
+        description: Specifies the trackpad's ATI coarse fractional multiplier.
+
+      azoteq,ati-frac-div-coarse:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 31
+        description: Specifies the trackpad's ATI coarse fractional divider.
+
+      azoteq,ati-comp-div:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 31
+        description: Specifies the trackpad's ATI compensation divider.
+
+      azoteq,ati-target:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 65535
+        description: Specifies the trackpad's ATI target.
+
+      azoteq,touch-enter:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 255
+        description: Specifies the trackpad's touch entrance factor.
+
+      azoteq,touch-exit:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 255
+        description: Specifies the trackpad's touch exit factor.
+
+      azoteq,thresh:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 255
+        description: Specifies the trackpad's stationary touch threshold.
+
+      azoteq,conv-period:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 255
+        description: Specifies the trackpad's conversion period.
+
+      azoteq,conv-frac:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 255
+        description: Specifies the trackpad's conversion frequency fraction.
+
+    patternProperties:
+      "^event-(tap(-double|-triple)?|hold|palm|swipe-(x|y)-(pos|neg)(-hold)?)$":
+        type: object
+        $ref: ../input.yaml#
+        description:
+          Represents a gesture event reported by the trackpad. In the case of
+          axial gestures, the duration or distance specified in one direction
+          applies to both directions along the same axis.
+
+        properties:
+          linux,code: true
+
+          azoteq,gesture-max-ms:
+            minimum: 0
+            maximum: 65535
+            description: Specifies the maximum duration of tap/swipe gestures.
+
+          azoteq,gesture-mid-ms:
+            minimum: 0
+            maximum: 65535
+            description:
+              Specifies the maximum duration between subsequent tap gestures
+              (IQS7211E only).
+
+          azoteq,gesture-min-ms:
+            minimum: 0
+            maximum: 65535
+            description: Specifies the minimum duration of hold gestures.
+
+          azoteq,gesture-dist:
+            $ref: /schemas/types.yaml#/definitions/uint32
+            minimum: 0
+            maximum: 65535
+            description:
+              Specifies the minimum (swipe) or maximum (tap and hold) distance
+              a finger may travel to be considered a gesture.
+
+          azoteq,gesture-dist-rep:
+            $ref: /schemas/types.yaml#/definitions/uint32
+            minimum: 0
+            maximum: 65535
+            description:
+              Specifies the minimum distance a finger must travel to elicit a
+              repeated swipe gesture (IQS7211E only).
+
+          azoteq,gesture-angle:
+            $ref: /schemas/types.yaml#/definitions/uint32
+            minimum: 0
+            maximum: 75
+            description:
+              Specifies the maximum angle (in degrees) a finger may travel to
+              be considered a swipe gesture.
+
+          azoteq,thresh:
+            $ref: /schemas/types.yaml#/definitions/uint32
+            minimum: 0
+            maximum: 42
+            description: Specifies the palm gesture threshold (IQS7211E only).
+
+        additionalProperties: false
+
+    dependencies:
+      azoteq,rx-enable: ["azoteq,tx-enable"]
+      azoteq,tx-enable: ["azoteq,rx-enable"]
+      azoteq,channel-select: ["azoteq,rx-enable"]
+
+    additionalProperties: false
+
+  alp:
+    type: object
+    $ref: ../input.yaml#
+    description: Represents the alternate low-power channel (ALP).
+
+    properties:
+      azoteq,rx-enable:
+        $ref: /schemas/types.yaml#/definitions/uint32-array
+        minItems: 1
+        maxItems: 8
+        items:
+          minimum: 0
+          maximum: 7
+        description:
+          Specifies the CRx pin(s) associated with the ALP in no particular
+          order.
+
+      azoteq,tx-enable:
+        $ref: /schemas/types.yaml#/definitions/uint32-array
+        minItems: 1
+        maxItems: 12
+        items:
+          minimum: 0
+          maximum: 11
+        description:
+          Specifies the CTx pin(s) associated with the ALP in no particular
+          order.
+
+      azoteq,ati-frac-div-fine:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 31
+        description: Specifies the ALP's ATI fine fractional divider.
+
+      azoteq,ati-frac-mult-coarse:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 15
+        description: Specifies the ALP's ATI coarse fractional multiplier.
+
+      azoteq,ati-frac-div-coarse:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 31
+        description: Specifies the ALP's ATI coarse fractional divider.
+
+      azoteq,ati-comp-div:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 31
+        description: Specifies the ALP's ATI compensation divider.
+
+      azoteq,ati-target:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 65535
+        description: Specifies the ALP's ATI target.
+
+      azoteq,ati-base:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        multipleOf: 8
+        minimum: 0
+        maximum: 255
+        description: Specifies the ALP's ATI base.
+
+      azoteq,ati-mode:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        enum: [0, 1]
+        description: |
+          Specifies the ALP's ATI mode as follows:
+          0: Partial
+          1: Full
+
+      azoteq,sense-mode:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        enum: [0, 1]
+        description: |
+          Specifies the ALP's sensing mode as follows:
+          0: Self capacitive
+          1: Mutual capacitive
+
+      azoteq,debounce-enter:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 255
+        description: Specifies the ALP's debounce entrance factor.
+
+      azoteq,debounce-exit:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 255
+        description: Specifies the ALP's debounce exit factor.
+
+      azoteq,thresh:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 65535
+        description: Specifies the ALP's proximity or touch threshold.
+
+      azoteq,conv-period:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 255
+        description: Specifies the ALP's conversion period.
+
+      azoteq,conv-frac:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 255
+        description: Specifies the ALP's conversion frequency fraction.
+
+      linux,code: true
+
+    additionalProperties: false
+
+  button:
+    type: object
+    description: Represents the inductive or capacitive button.
+
+    properties:
+      azoteq,ati-frac-div-fine:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 31
+        description: Specifies the button's ATI fine fractional divider.
+
+      azoteq,ati-frac-mult-coarse:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 15
+        description: Specifies the button's ATI coarse fractional multiplier.
+
+      azoteq,ati-frac-div-coarse:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 31
+        description: Specifies the button's ATI coarse fractional divider.
+
+      azoteq,ati-comp-div:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 31
+        description: Specifies the button's ATI compensation divider.
+
+      azoteq,ati-target:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 65535
+        description: Specifies the button's ATI target.
+
+      azoteq,ati-base:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        multipleOf: 8
+        minimum: 0
+        maximum: 255
+        description: Specifies the button's ATI base.
+
+      azoteq,ati-mode:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        enum: [0, 1]
+        description: |
+          Specifies the button's ATI mode as follows:
+          0: Partial
+          1: Full
+
+      azoteq,sense-mode:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        enum: [0, 1, 2]
+        description: |
+          Specifies the button's sensing mode as follows:
+          0: Self capacitive
+          1: Mutual capacitive
+          2: Inductive
+
+      azoteq,touch-enter:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 255
+        description: Specifies the button's touch entrance factor.
+
+      azoteq,touch-exit:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 255
+        description: Specifies the button's touch exit factor.
+
+      azoteq,debounce-enter:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 255
+        description: Specifies the button's debounce entrance factor.
+
+      azoteq,debounce-exit:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 255
+        description: Specifies the button's debounce exit factor.
+
+      azoteq,thresh:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 65535
+        description: Specifies the button's proximity threshold.
+
+      azoteq,conv-period:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 255
+        description: Specifies the button's conversion period.
+
+      azoteq,conv-frac:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 255
+        description: Specifies the button's conversion frequency fraction.
+
+    patternProperties:
+      "^event-(prox|touch)$":
+        type: object
+        $ref: ../input.yaml#
+        description:
+          Represents a proximity or touch event reported by the button.
+
+        properties:
+          linux,code: true
+
+        additionalProperties: false
+
+    additionalProperties: false
+
+  wakeup-source: true
+
+  touchscreen-size-x: true
+  touchscreen-size-y: true
+  touchscreen-inverted-x: true
+  touchscreen-inverted-y: true
+  touchscreen-swapped-x-y: true
+
+dependencies:
+  touchscreen-size-x: ["azoteq,num-contacts"]
+  touchscreen-size-y: ["azoteq,num-contacts"]
+  touchscreen-inverted-x: ["azoteq,num-contacts"]
+  touchscreen-inverted-y: ["azoteq,num-contacts"]
+  touchscreen-swapped-x-y: ["azoteq,num-contacts"]
+
+required:
+  - compatible
+  - reg
+  - irq-gpios
+
+additionalProperties: false
+
+allOf:
+  - $ref: touchscreen.yaml#
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: azoteq,iqs7210a
+
+    then:
+      properties:
+        alp:
+          properties:
+            azoteq,rx-enable:
+              maxItems: 4
+              items:
+                minimum: 4
+
+    else:
+      properties:
+        azoteq,timeout-press-ms: false
+
+        alp:
+          properties:
+            azoteq,ati-mode: false
+
+        button: false
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: azoteq,iqs7211e
+
+    then:
+      properties:
+        reset-gpios: false
+
+        trackpad:
+          properties:
+            azoteq,tx-enable:
+              maxItems: 13
+              items:
+                maximum: 12
+
+        alp:
+          properties:
+            azoteq,tx-enable:
+              maxItems: 13
+              items:
+                maximum: 12
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/input/input.h>
+
+    i2c {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            touch@56 {
+                    compatible = "azoteq,iqs7210a";
+                    reg = <0x56>;
+                    irq-gpios = <&gpio 4 GPIO_ACTIVE_LOW>;
+                    reset-gpios = <&gpio 17 (GPIO_ACTIVE_LOW |
+                                             GPIO_PUSH_PULL)>;
+                    azoteq,num-contacts = <2>;
+
+                    trackpad {
+                            azoteq,rx-enable = <6>, <5>, <4>, <3>, <2>;
+                            azoteq,tx-enable = <1>, <7>, <8>, <9>, <10>;
+                    };
+
+                    button {
+                            azoteq,sense-mode = <2>;
+                            azoteq,touch-enter = <40>;
+                            azoteq,touch-exit = <36>;
+
+                            event-touch {
+                                    linux,code = <KEY_HOME>;
+                            };
+                    };
+
+                    alp {
+                            azoteq,sense-mode = <1>;
+                            linux,code = <KEY_POWER>;
+                    };
+            };
+    };
+
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/input/input.h>
+
+    i2c {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            touch@56 {
+                    compatible = "azoteq,iqs7211e";
+                    reg = <0x56>;
+                    irq-gpios = <&gpio 4 (GPIO_ACTIVE_LOW |
+                                          GPIO_OPEN_DRAIN)>;
+
+                    trackpad {
+                            event-tap {
+                                    linux,code = <KEY_PLAYPAUSE>;
+                            };
+
+                            event-tap-double {
+                                    linux,code = <KEY_SHUFFLE>;
+                            };
+
+                            event-tap-triple {
+                                    linux,code = <KEY_AGAIN>;
+                            };
+
+                            event-hold {
+                                    linux,code = <KEY_STOP>;
+                            };
+
+                            event-palm {
+                                    linux,code = <KEY_EXIT>;
+                            };
+
+                            event-swipe-x-pos {
+                                    linux,code = <KEY_REWIND>;
+                            };
+
+                            event-swipe-x-pos-hold {
+                                    linux,code = <KEY_PREVIOUS>;
+                            };
+
+                            event-swipe-x-neg {
+                                    linux,code = <KEY_FASTFORWARD>;
+                            };
+
+                            event-swipe-x-neg-hold {
+                                    linux,code = <KEY_NEXT>;
+                            };
+
+                            event-swipe-y-pos {
+                                    linux,code = <KEY_VOLUMEUP>;
+                            };
+
+                            event-swipe-y-pos-hold {
+                                    linux,code = <KEY_MUTE>;
+                            };
+
+                            event-swipe-y-neg {
+                                    linux,code = <KEY_VOLUMEDOWN>;
+                            };
+
+                            event-swipe-y-neg-hold {
+                                    linux,code = <KEY_MUTE>;
+                            };
+                    };
+            };
+    };
+
+...

From f2ba47e65f3b5642488802a60cb7dd068f425edc Mon Sep 17 00:00:00 2001
From: Jeff LaBundy <jeff@labundy.com>
Date: Mon, 29 May 2023 19:34:00 -0500
Subject: [PATCH 0062/1189] Input: add support for Azoteq IQS7210A/7211A/E

Add support for the Azoteq IQS7210A/7211A/E family of trackpad/
touchscreen controllers.

Signed-off-by: Jeff LaBundy <jeff@labundy.com>
Link: https://lore.kernel.org/r/ZHVEeDlYyr69A59K@nixie71
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/Kconfig   |   10 +
 drivers/input/touchscreen/Makefile  |    1 +
 drivers/input/touchscreen/iqs7211.c | 2569 +++++++++++++++++++++++++++
 3 files changed, 2580 insertions(+)
 create mode 100644 drivers/input/touchscreen/iqs7211.c

diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig
index fb4c23917b69..e3e2324547b9 100644
--- a/drivers/input/touchscreen/Kconfig
+++ b/drivers/input/touchscreen/Kconfig
@@ -1365,6 +1365,16 @@ config TOUCHSCREEN_IQS5XX
 	  To compile this driver as a module, choose M here: the
 	  module will be called iqs5xx.
 
+config TOUCHSCREEN_IQS7211
+	tristate "Azoteq IQS7210A/7211A/E trackpad/touchscreen controller"
+	depends on I2C
+	help
+	  Say Y to enable support for the Azoteq IQS7210A/7211A/E
+	  family of trackpad/touchscreen controllers.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called iqs7211.
+
 config TOUCHSCREEN_ZINITIX
 	tristate "Zinitix touchscreen support"
 	depends on I2C
diff --git a/drivers/input/touchscreen/Makefile b/drivers/input/touchscreen/Makefile
index 159cd5136fdb..62bd24f3ac8e 100644
--- a/drivers/input/touchscreen/Makefile
+++ b/drivers/input/touchscreen/Makefile
@@ -115,5 +115,6 @@ obj-$(CONFIG_TOUCHSCREEN_COLIBRI_VF50)	+= colibri-vf50-ts.o
 obj-$(CONFIG_TOUCHSCREEN_ROHM_BU21023)	+= rohm_bu21023.o
 obj-$(CONFIG_TOUCHSCREEN_RASPBERRYPI_FW)	+= raspberrypi-ts.o
 obj-$(CONFIG_TOUCHSCREEN_IQS5XX)	+= iqs5xx.o
+obj-$(CONFIG_TOUCHSCREEN_IQS7211)	+= iqs7211.o
 obj-$(CONFIG_TOUCHSCREEN_ZINITIX)	+= zinitix.o
 obj-$(CONFIG_TOUCHSCREEN_HIMAX_HX83112B)	+= himax_hx83112b.o
diff --git a/drivers/input/touchscreen/iqs7211.c b/drivers/input/touchscreen/iqs7211.c
new file mode 100644
index 000000000000..f60316d37f45
--- /dev/null
+++ b/drivers/input/touchscreen/iqs7211.c
@@ -0,0 +1,2569 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Azoteq IQS7210A/7211A/E Trackpad/Touchscreen Controller
+ *
+ * Copyright (C) 2023 Jeff LaBundy <jeff@labundy.com>
+ */
+
+#include <linux/bits.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/gpio/consumer.h>
+#include <linux/i2c.h>
+#include <linux/input.h>
+#include <linux/input/mt.h>
+#include <linux/input/touchscreen.h>
+#include <linux/interrupt.h>
+#include <linux/iopoll.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/property.h>
+#include <linux/slab.h>
+#include <asm/unaligned.h>
+
+#define IQS7211_PROD_NUM			0x00
+
+#define IQS7211_EVENT_MASK_ALL			GENMASK(14, 8)
+#define IQS7211_EVENT_MASK_ALP			BIT(13)
+#define IQS7211_EVENT_MASK_BTN			BIT(12)
+#define IQS7211_EVENT_MASK_ATI			BIT(11)
+#define IQS7211_EVENT_MASK_MOVE			BIT(10)
+#define IQS7211_EVENT_MASK_GSTR			BIT(9)
+#define IQS7211_EVENT_MODE			BIT(8)
+
+#define IQS7211_COMMS_ERROR			0xEEEE
+#define IQS7211_COMMS_RETRY_MS			50
+#define IQS7211_COMMS_SLEEP_US			100
+#define IQS7211_COMMS_TIMEOUT_US		(100 * USEC_PER_MSEC)
+#define IQS7211_RESET_TIMEOUT_MS		150
+#define IQS7211_START_TIMEOUT_US		(1 * USEC_PER_SEC)
+
+#define IQS7211_NUM_RETRIES			5
+#define IQS7211_NUM_CRX				8
+#define IQS7211_MAX_CTX				13
+
+#define IQS7211_MAX_CONTACTS			2
+#define IQS7211_MAX_CYCLES			21
+
+/*
+ * The following delay is used during instances that must wait for the open-
+ * drain RDY pin to settle. Its value is calculated as 5*R*C, where R and C
+ * represent typical datasheet values of 4.7k and 100 nF, respectively.
+ */
+#define iqs7211_irq_wait()			usleep_range(2500, 2600)
+
+enum iqs7211_dev_id {
+	IQS7210A,
+	IQS7211A,
+	IQS7211E,
+};
+
+enum iqs7211_comms_mode {
+	IQS7211_COMMS_MODE_WAIT,
+	IQS7211_COMMS_MODE_FREE,
+	IQS7211_COMMS_MODE_FORCE,
+};
+
+struct iqs7211_reg_field_desc {
+	struct list_head list;
+	u8 addr;
+	u16 mask;
+	u16 val;
+};
+
+enum iqs7211_reg_key_id {
+	IQS7211_REG_KEY_NONE,
+	IQS7211_REG_KEY_PROX,
+	IQS7211_REG_KEY_TOUCH,
+	IQS7211_REG_KEY_TAP,
+	IQS7211_REG_KEY_HOLD,
+	IQS7211_REG_KEY_PALM,
+	IQS7211_REG_KEY_AXIAL_X,
+	IQS7211_REG_KEY_AXIAL_Y,
+	IQS7211_REG_KEY_RESERVED
+};
+
+enum iqs7211_reg_grp_id {
+	IQS7211_REG_GRP_TP,
+	IQS7211_REG_GRP_BTN,
+	IQS7211_REG_GRP_ALP,
+	IQS7211_REG_GRP_SYS,
+	IQS7211_NUM_REG_GRPS
+};
+
+static const char * const iqs7211_reg_grp_names[IQS7211_NUM_REG_GRPS] = {
+	[IQS7211_REG_GRP_TP] = "trackpad",
+	[IQS7211_REG_GRP_BTN] = "button",
+	[IQS7211_REG_GRP_ALP] = "alp",
+};
+
+static const u16 iqs7211_reg_grp_masks[IQS7211_NUM_REG_GRPS] = {
+	[IQS7211_REG_GRP_TP] = IQS7211_EVENT_MASK_GSTR,
+	[IQS7211_REG_GRP_BTN] = IQS7211_EVENT_MASK_BTN,
+	[IQS7211_REG_GRP_ALP] = IQS7211_EVENT_MASK_ALP,
+};
+
+struct iqs7211_event_desc {
+	const char *name;
+	u16 mask;
+	u16 enable;
+	enum iqs7211_reg_grp_id reg_grp;
+	enum iqs7211_reg_key_id reg_key;
+};
+
+static const struct iqs7211_event_desc iqs7210a_kp_events[] = {
+	{
+		.mask = BIT(10),
+		.enable = BIT(13) | BIT(12),
+		.reg_grp = IQS7211_REG_GRP_ALP,
+	},
+	{
+		.name = "event-prox",
+		.mask = BIT(2),
+		.enable = BIT(5) | BIT(4),
+		.reg_grp = IQS7211_REG_GRP_BTN,
+		.reg_key = IQS7211_REG_KEY_PROX,
+	},
+	{
+		.name = "event-touch",
+		.mask = BIT(3),
+		.enable = BIT(5) | BIT(4),
+		.reg_grp = IQS7211_REG_GRP_BTN,
+		.reg_key = IQS7211_REG_KEY_TOUCH,
+	},
+	{
+		.name = "event-tap",
+		.mask = BIT(0),
+		.enable = BIT(0),
+		.reg_grp = IQS7211_REG_GRP_TP,
+		.reg_key = IQS7211_REG_KEY_TAP,
+	},
+	{
+		.name = "event-hold",
+		.mask = BIT(1),
+		.enable = BIT(1),
+		.reg_grp = IQS7211_REG_GRP_TP,
+		.reg_key = IQS7211_REG_KEY_HOLD,
+	},
+	{
+		.name = "event-swipe-x-neg",
+		.mask = BIT(2),
+		.enable = BIT(2),
+		.reg_grp = IQS7211_REG_GRP_TP,
+		.reg_key = IQS7211_REG_KEY_AXIAL_X,
+	},
+	{
+		.name = "event-swipe-x-pos",
+		.mask = BIT(3),
+		.enable = BIT(3),
+		.reg_grp = IQS7211_REG_GRP_TP,
+		.reg_key = IQS7211_REG_KEY_AXIAL_X,
+	},
+	{
+		.name = "event-swipe-y-pos",
+		.mask = BIT(4),
+		.enable = BIT(4),
+		.reg_grp = IQS7211_REG_GRP_TP,
+		.reg_key = IQS7211_REG_KEY_AXIAL_Y,
+	},
+	{
+		.name = "event-swipe-y-neg",
+		.mask = BIT(5),
+		.enable = BIT(5),
+		.reg_grp = IQS7211_REG_GRP_TP,
+		.reg_key = IQS7211_REG_KEY_AXIAL_Y,
+	},
+};
+
+static const struct iqs7211_event_desc iqs7211a_kp_events[] = {
+	{
+		.mask = BIT(14),
+		.reg_grp = IQS7211_REG_GRP_ALP,
+	},
+	{
+		.name = "event-tap",
+		.mask = BIT(0),
+		.enable = BIT(0),
+		.reg_grp = IQS7211_REG_GRP_TP,
+		.reg_key = IQS7211_REG_KEY_TAP,
+	},
+	{
+		.name = "event-hold",
+		.mask = BIT(1),
+		.enable = BIT(1),
+		.reg_grp = IQS7211_REG_GRP_TP,
+		.reg_key = IQS7211_REG_KEY_HOLD,
+	},
+	{
+		.name = "event-swipe-x-neg",
+		.mask = BIT(2),
+		.enable = BIT(2),
+		.reg_grp = IQS7211_REG_GRP_TP,
+		.reg_key = IQS7211_REG_KEY_AXIAL_X,
+	},
+	{
+		.name = "event-swipe-x-pos",
+		.mask = BIT(3),
+		.enable = BIT(3),
+		.reg_grp = IQS7211_REG_GRP_TP,
+		.reg_key = IQS7211_REG_KEY_AXIAL_X,
+	},
+	{
+		.name = "event-swipe-y-pos",
+		.mask = BIT(4),
+		.enable = BIT(4),
+		.reg_grp = IQS7211_REG_GRP_TP,
+		.reg_key = IQS7211_REG_KEY_AXIAL_Y,
+	},
+	{
+		.name = "event-swipe-y-neg",
+		.mask = BIT(5),
+		.enable = BIT(5),
+		.reg_grp = IQS7211_REG_GRP_TP,
+		.reg_key = IQS7211_REG_KEY_AXIAL_Y,
+	},
+};
+
+static const struct iqs7211_event_desc iqs7211e_kp_events[] = {
+	{
+		.mask = BIT(14),
+		.reg_grp = IQS7211_REG_GRP_ALP,
+	},
+	{
+		.name = "event-tap",
+		.mask = BIT(0),
+		.enable = BIT(0),
+		.reg_grp = IQS7211_REG_GRP_TP,
+		.reg_key = IQS7211_REG_KEY_TAP,
+	},
+	{
+		.name = "event-tap-double",
+		.mask = BIT(1),
+		.enable = BIT(1),
+		.reg_grp = IQS7211_REG_GRP_TP,
+		.reg_key = IQS7211_REG_KEY_TAP,
+	},
+	{
+		.name = "event-tap-triple",
+		.mask = BIT(2),
+		.enable = BIT(2),
+		.reg_grp = IQS7211_REG_GRP_TP,
+		.reg_key = IQS7211_REG_KEY_TAP,
+	},
+	{
+		.name = "event-hold",
+		.mask = BIT(3),
+		.enable = BIT(3),
+		.reg_grp = IQS7211_REG_GRP_TP,
+		.reg_key = IQS7211_REG_KEY_HOLD,
+	},
+	{
+		.name = "event-palm",
+		.mask = BIT(4),
+		.enable = BIT(4),
+		.reg_grp = IQS7211_REG_GRP_TP,
+		.reg_key = IQS7211_REG_KEY_PALM,
+	},
+	{
+		.name = "event-swipe-x-pos",
+		.mask = BIT(8),
+		.enable = BIT(8),
+		.reg_grp = IQS7211_REG_GRP_TP,
+		.reg_key = IQS7211_REG_KEY_AXIAL_X,
+	},
+	{
+		.name = "event-swipe-x-neg",
+		.mask = BIT(9),
+		.enable = BIT(9),
+		.reg_grp = IQS7211_REG_GRP_TP,
+		.reg_key = IQS7211_REG_KEY_AXIAL_X,
+	},
+	{
+		.name = "event-swipe-y-pos",
+		.mask = BIT(10),
+		.enable = BIT(10),
+		.reg_grp = IQS7211_REG_GRP_TP,
+		.reg_key = IQS7211_REG_KEY_AXIAL_Y,
+	},
+	{
+		.name = "event-swipe-y-neg",
+		.mask = BIT(11),
+		.enable = BIT(11),
+		.reg_grp = IQS7211_REG_GRP_TP,
+		.reg_key = IQS7211_REG_KEY_AXIAL_Y,
+	},
+	{
+		.name = "event-swipe-x-pos-hold",
+		.mask = BIT(12),
+		.enable = BIT(12),
+		.reg_grp = IQS7211_REG_GRP_TP,
+		.reg_key = IQS7211_REG_KEY_HOLD,
+	},
+	{
+		.name = "event-swipe-x-neg-hold",
+		.mask = BIT(13),
+		.enable = BIT(13),
+		.reg_grp = IQS7211_REG_GRP_TP,
+		.reg_key = IQS7211_REG_KEY_HOLD,
+	},
+	{
+		.name = "event-swipe-y-pos-hold",
+		.mask = BIT(14),
+		.enable = BIT(14),
+		.reg_grp = IQS7211_REG_GRP_TP,
+		.reg_key = IQS7211_REG_KEY_HOLD,
+	},
+	{
+		.name = "event-swipe-y-neg-hold",
+		.mask = BIT(15),
+		.enable = BIT(15),
+		.reg_grp = IQS7211_REG_GRP_TP,
+		.reg_key = IQS7211_REG_KEY_HOLD,
+	},
+};
+
+struct iqs7211_dev_desc {
+	const char *tp_name;
+	const char *kp_name;
+	u16 prod_num;
+	u16 show_reset;
+	u16 ati_error[IQS7211_NUM_REG_GRPS];
+	u16 ati_start[IQS7211_NUM_REG_GRPS];
+	u16 suspend;
+	u16 ack_reset;
+	u16 comms_end;
+	u16 comms_req;
+	int charge_shift;
+	int info_offs;
+	int gesture_offs;
+	int contact_offs;
+	u8 sys_stat;
+	u8 sys_ctrl;
+	u8 alp_config;
+	u8 tp_config;
+	u8 exp_file;
+	u8 kp_enable[IQS7211_NUM_REG_GRPS];
+	u8 gesture_angle;
+	u8 rx_tx_map;
+	u8 cycle_alloc[2];
+	u8 cycle_limit[2];
+	const struct iqs7211_event_desc *kp_events;
+	int num_kp_events;
+	int min_crx_alp;
+	int num_ctx;
+};
+
+static const struct iqs7211_dev_desc iqs7211_devs[] = {
+	[IQS7210A] = {
+		.tp_name = "iqs7210a_trackpad",
+		.kp_name = "iqs7210a_keys",
+		.prod_num = 944,
+		.show_reset = BIT(15),
+		.ati_error = {
+			[IQS7211_REG_GRP_TP] = BIT(12),
+			[IQS7211_REG_GRP_BTN] = BIT(0),
+			[IQS7211_REG_GRP_ALP] = BIT(8),
+		},
+		.ati_start = {
+			[IQS7211_REG_GRP_TP] = BIT(13),
+			[IQS7211_REG_GRP_BTN] = BIT(1),
+			[IQS7211_REG_GRP_ALP] = BIT(9),
+		},
+		.suspend = BIT(11),
+		.ack_reset = BIT(7),
+		.comms_end = BIT(2),
+		.comms_req = BIT(1),
+		.charge_shift = 4,
+		.info_offs = 0,
+		.gesture_offs = 1,
+		.contact_offs = 4,
+		.sys_stat = 0x0A,
+		.sys_ctrl = 0x35,
+		.alp_config = 0x39,
+		.tp_config = 0x4E,
+		.exp_file = 0x57,
+		.kp_enable = {
+			[IQS7211_REG_GRP_TP] = 0x58,
+			[IQS7211_REG_GRP_BTN] = 0x37,
+			[IQS7211_REG_GRP_ALP] = 0x37,
+		},
+		.gesture_angle = 0x5F,
+		.rx_tx_map = 0x60,
+		.cycle_alloc = { 0x66, 0x75, },
+		.cycle_limit = { 10, 6, },
+		.kp_events = iqs7210a_kp_events,
+		.num_kp_events = ARRAY_SIZE(iqs7210a_kp_events),
+		.min_crx_alp = 4,
+		.num_ctx = IQS7211_MAX_CTX - 1,
+	},
+	[IQS7211A] = {
+		.tp_name = "iqs7211a_trackpad",
+		.kp_name = "iqs7211a_keys",
+		.prod_num = 763,
+		.show_reset = BIT(7),
+		.ati_error = {
+			[IQS7211_REG_GRP_TP] = BIT(3),
+			[IQS7211_REG_GRP_ALP] = BIT(5),
+		},
+		.ati_start = {
+			[IQS7211_REG_GRP_TP] = BIT(5),
+			[IQS7211_REG_GRP_ALP] = BIT(6),
+		},
+		.ack_reset = BIT(7),
+		.comms_req = BIT(4),
+		.charge_shift = 0,
+		.info_offs = 0,
+		.gesture_offs = 1,
+		.contact_offs = 4,
+		.sys_stat = 0x10,
+		.sys_ctrl = 0x50,
+		.tp_config = 0x60,
+		.alp_config = 0x72,
+		.exp_file = 0x74,
+		.kp_enable = {
+			[IQS7211_REG_GRP_TP] = 0x80,
+		},
+		.gesture_angle = 0x87,
+		.rx_tx_map = 0x90,
+		.cycle_alloc = { 0xA0, 0xB0, },
+		.cycle_limit = { 10, 8, },
+		.kp_events = iqs7211a_kp_events,
+		.num_kp_events = ARRAY_SIZE(iqs7211a_kp_events),
+		.num_ctx = IQS7211_MAX_CTX - 1,
+	},
+	[IQS7211E] = {
+		.tp_name = "iqs7211e_trackpad",
+		.kp_name = "iqs7211e_keys",
+		.prod_num = 1112,
+		.show_reset = BIT(7),
+		.ati_error = {
+			[IQS7211_REG_GRP_TP] = BIT(3),
+			[IQS7211_REG_GRP_ALP] = BIT(5),
+		},
+		.ati_start = {
+			[IQS7211_REG_GRP_TP] = BIT(5),
+			[IQS7211_REG_GRP_ALP] = BIT(6),
+		},
+		.suspend = BIT(11),
+		.ack_reset = BIT(7),
+		.comms_end = BIT(6),
+		.comms_req = BIT(4),
+		.charge_shift = 0,
+		.info_offs = 1,
+		.gesture_offs = 0,
+		.contact_offs = 2,
+		.sys_stat = 0x0E,
+		.sys_ctrl = 0x33,
+		.tp_config = 0x41,
+		.alp_config = 0x36,
+		.exp_file = 0x4A,
+		.kp_enable = {
+			[IQS7211_REG_GRP_TP] = 0x4B,
+		},
+		.gesture_angle = 0x55,
+		.rx_tx_map = 0x56,
+		.cycle_alloc = { 0x5D, 0x6C, },
+		.cycle_limit = { 10, 11, },
+		.kp_events = iqs7211e_kp_events,
+		.num_kp_events = ARRAY_SIZE(iqs7211e_kp_events),
+		.num_ctx = IQS7211_MAX_CTX,
+	},
+};
+
+struct iqs7211_prop_desc {
+	const char *name;
+	enum iqs7211_reg_key_id reg_key;
+	u8 reg_addr[IQS7211_NUM_REG_GRPS][ARRAY_SIZE(iqs7211_devs)];
+	int reg_shift;
+	int reg_width;
+	int val_pitch;
+	int val_min;
+	int val_max;
+	const char *label;
+};
+
+static const struct iqs7211_prop_desc iqs7211_props[] = {
+	{
+		.name = "azoteq,ati-frac-div-fine",
+		.reg_addr = {
+			[IQS7211_REG_GRP_TP] = {
+				[IQS7210A] = 0x1E,
+				[IQS7211A] = 0x30,
+				[IQS7211E] = 0x21,
+			},
+			[IQS7211_REG_GRP_BTN] = {
+				[IQS7210A] = 0x22,
+			},
+			[IQS7211_REG_GRP_ALP] = {
+				[IQS7210A] = 0x23,
+				[IQS7211A] = 0x36,
+				[IQS7211E] = 0x25,
+			},
+		},
+		.reg_shift = 9,
+		.reg_width = 5,
+		.label = "ATI fine fractional divider",
+	},
+	{
+		.name = "azoteq,ati-frac-mult-coarse",
+		.reg_addr = {
+			[IQS7211_REG_GRP_TP] = {
+				[IQS7210A] = 0x1E,
+				[IQS7211A] = 0x30,
+				[IQS7211E] = 0x21,
+			},
+			[IQS7211_REG_GRP_BTN] = {
+				[IQS7210A] = 0x22,
+			},
+			[IQS7211_REG_GRP_ALP] = {
+				[IQS7210A] = 0x23,
+				[IQS7211A] = 0x36,
+				[IQS7211E] = 0x25,
+			},
+		},
+		.reg_shift = 5,
+		.reg_width = 4,
+		.label = "ATI coarse fractional multiplier",
+	},
+	{
+		.name = "azoteq,ati-frac-div-coarse",
+		.reg_addr = {
+			[IQS7211_REG_GRP_TP] = {
+				[IQS7210A] = 0x1E,
+				[IQS7211A] = 0x30,
+				[IQS7211E] = 0x21,
+			},
+			[IQS7211_REG_GRP_BTN] = {
+				[IQS7210A] = 0x22,
+			},
+			[IQS7211_REG_GRP_ALP] = {
+				[IQS7210A] = 0x23,
+				[IQS7211A] = 0x36,
+				[IQS7211E] = 0x25,
+			},
+		},
+		.reg_shift = 0,
+		.reg_width = 5,
+		.label = "ATI coarse fractional divider",
+	},
+	{
+		.name = "azoteq,ati-comp-div",
+		.reg_addr = {
+			[IQS7211_REG_GRP_TP] = {
+				[IQS7210A] = 0x1F,
+				[IQS7211E] = 0x22,
+			},
+			[IQS7211_REG_GRP_BTN] = {
+				[IQS7210A] = 0x24,
+			},
+			[IQS7211_REG_GRP_ALP] = {
+				[IQS7211E] = 0x26,
+			},
+		},
+		.reg_shift = 0,
+		.reg_width = 8,
+		.val_max = 31,
+		.label = "ATI compensation divider",
+	},
+	{
+		.name = "azoteq,ati-comp-div",
+		.reg_addr = {
+			[IQS7211_REG_GRP_ALP] = {
+				[IQS7210A] = 0x24,
+			},
+		},
+		.reg_shift = 8,
+		.reg_width = 8,
+		.val_max = 31,
+		.label = "ATI compensation divider",
+	},
+	{
+		.name = "azoteq,ati-comp-div",
+		.reg_addr = {
+			[IQS7211_REG_GRP_TP] = {
+				[IQS7211A] = 0x31,
+			},
+			[IQS7211_REG_GRP_ALP] = {
+				[IQS7211A] = 0x37,
+			},
+		},
+		.val_max = 31,
+		.label = "ATI compensation divider",
+	},
+	{
+		.name = "azoteq,ati-target",
+		.reg_addr = {
+			[IQS7211_REG_GRP_TP] = {
+				[IQS7210A] = 0x20,
+				[IQS7211A] = 0x32,
+				[IQS7211E] = 0x23,
+			},
+			[IQS7211_REG_GRP_BTN] = {
+				[IQS7210A] = 0x27,
+			},
+			[IQS7211_REG_GRP_ALP] = {
+				[IQS7210A] = 0x28,
+				[IQS7211A] = 0x38,
+				[IQS7211E] = 0x27,
+			},
+		},
+		.label = "ATI target",
+	},
+	{
+		.name = "azoteq,ati-base",
+		.reg_addr[IQS7211_REG_GRP_ALP] = {
+			[IQS7210A] = 0x26,
+		},
+		.reg_shift = 8,
+		.reg_width = 8,
+		.val_pitch = 8,
+		.label = "ATI base",
+	},
+	{
+		.name = "azoteq,ati-base",
+		.reg_addr[IQS7211_REG_GRP_BTN] = {
+			[IQS7210A] = 0x26,
+		},
+		.reg_shift = 0,
+		.reg_width = 8,
+		.val_pitch = 8,
+		.label = "ATI base",
+	},
+	{
+		.name = "azoteq,rate-active-ms",
+		.reg_addr[IQS7211_REG_GRP_SYS] = {
+			[IQS7210A] = 0x29,
+			[IQS7211A] = 0x40,
+			[IQS7211E] = 0x28,
+		},
+		.label = "active mode report rate",
+	},
+	{
+		.name = "azoteq,rate-touch-ms",
+		.reg_addr[IQS7211_REG_GRP_SYS] = {
+			[IQS7210A] = 0x2A,
+			[IQS7211A] = 0x41,
+			[IQS7211E] = 0x29,
+		},
+		.label = "idle-touch mode report rate",
+	},
+	{
+		.name = "azoteq,rate-idle-ms",
+		.reg_addr[IQS7211_REG_GRP_SYS] = {
+			[IQS7210A] = 0x2B,
+			[IQS7211A] = 0x42,
+			[IQS7211E] = 0x2A,
+		},
+		.label = "idle mode report rate",
+	},
+	{
+		.name = "azoteq,rate-lp1-ms",
+		.reg_addr[IQS7211_REG_GRP_SYS] = {
+			[IQS7210A] = 0x2C,
+			[IQS7211A] = 0x43,
+			[IQS7211E] = 0x2B,
+		},
+		.label = "low-power mode 1 report rate",
+	},
+	{
+		.name = "azoteq,rate-lp2-ms",
+		.reg_addr[IQS7211_REG_GRP_SYS] = {
+			[IQS7210A] = 0x2D,
+			[IQS7211A] = 0x44,
+			[IQS7211E] = 0x2C,
+		},
+		.label = "low-power mode 2 report rate",
+	},
+	{
+		.name = "azoteq,timeout-active-ms",
+		.reg_addr[IQS7211_REG_GRP_SYS] = {
+			[IQS7210A] = 0x2E,
+			[IQS7211A] = 0x45,
+			[IQS7211E] = 0x2D,
+		},
+		.val_pitch = 1000,
+		.label = "active mode timeout",
+	},
+	{
+		.name = "azoteq,timeout-touch-ms",
+		.reg_addr[IQS7211_REG_GRP_SYS] = {
+			[IQS7210A] = 0x2F,
+			[IQS7211A] = 0x46,
+			[IQS7211E] = 0x2E,
+		},
+		.val_pitch = 1000,
+		.label = "idle-touch mode timeout",
+	},
+	{
+		.name = "azoteq,timeout-idle-ms",
+		.reg_addr[IQS7211_REG_GRP_SYS] = {
+			[IQS7210A] = 0x30,
+			[IQS7211A] = 0x47,
+			[IQS7211E] = 0x2F,
+		},
+		.val_pitch = 1000,
+		.label = "idle mode timeout",
+	},
+	{
+		.name = "azoteq,timeout-lp1-ms",
+		.reg_addr[IQS7211_REG_GRP_SYS] = {
+			[IQS7210A] = 0x31,
+			[IQS7211A] = 0x48,
+			[IQS7211E] = 0x30,
+		},
+		.val_pitch = 1000,
+		.label = "low-power mode 1 timeout",
+	},
+	{
+		.name = "azoteq,timeout-lp2-ms",
+		.reg_addr[IQS7211_REG_GRP_SYS] = {
+			[IQS7210A] = 0x32,
+			[IQS7211E] = 0x31,
+		},
+		.reg_shift = 8,
+		.reg_width = 8,
+		.val_pitch = 1000,
+		.val_max = 60000,
+		.label = "trackpad reference value update rate",
+	},
+	{
+		.name = "azoteq,timeout-lp2-ms",
+		.reg_addr[IQS7211_REG_GRP_SYS] = {
+			[IQS7211A] = 0x49,
+		},
+		.val_pitch = 1000,
+		.val_max = 60000,
+		.label = "trackpad reference value update rate",
+	},
+	{
+		.name = "azoteq,timeout-ati-ms",
+		.reg_addr[IQS7211_REG_GRP_SYS] = {
+			[IQS7210A] = 0x32,
+			[IQS7211E] = 0x31,
+		},
+		.reg_width = 8,
+		.val_pitch = 1000,
+		.val_max = 60000,
+		.label = "ATI error timeout",
+	},
+	{
+		.name = "azoteq,timeout-ati-ms",
+		.reg_addr[IQS7211_REG_GRP_SYS] = {
+			[IQS7211A] = 0x35,
+		},
+		.val_pitch = 1000,
+		.val_max = 60000,
+		.label = "ATI error timeout",
+	},
+	{
+		.name = "azoteq,timeout-comms-ms",
+		.reg_addr[IQS7211_REG_GRP_SYS] = {
+			[IQS7210A] = 0x33,
+			[IQS7211A] = 0x4A,
+			[IQS7211E] = 0x32,
+		},
+		.label = "communication timeout",
+	},
+	{
+		.name = "azoteq,timeout-press-ms",
+		.reg_addr[IQS7211_REG_GRP_SYS] = {
+			[IQS7210A] = 0x34,
+		},
+		.reg_width = 8,
+		.val_pitch = 1000,
+		.val_max = 60000,
+		.label = "press timeout",
+	},
+	{
+		.name = "azoteq,ati-mode",
+		.reg_addr[IQS7211_REG_GRP_ALP] = {
+			[IQS7210A] = 0x37,
+		},
+		.reg_shift = 15,
+		.reg_width = 1,
+		.label = "ATI mode",
+	},
+	{
+		.name = "azoteq,ati-mode",
+		.reg_addr[IQS7211_REG_GRP_BTN] = {
+			[IQS7210A] = 0x37,
+		},
+		.reg_shift = 7,
+		.reg_width = 1,
+		.label = "ATI mode",
+	},
+	{
+		.name = "azoteq,sense-mode",
+		.reg_addr[IQS7211_REG_GRP_ALP] = {
+			[IQS7210A] = 0x37,
+			[IQS7211A] = 0x72,
+			[IQS7211E] = 0x36,
+		},
+		.reg_shift = 8,
+		.reg_width = 1,
+		.label = "sensing mode",
+	},
+	{
+		.name = "azoteq,sense-mode",
+		.reg_addr[IQS7211_REG_GRP_BTN] = {
+			[IQS7210A] = 0x37,
+		},
+		.reg_shift = 0,
+		.reg_width = 2,
+		.val_max = 2,
+		.label = "sensing mode",
+	},
+	{
+		.name = "azoteq,fosc-freq",
+		.reg_addr[IQS7211_REG_GRP_SYS] = {
+			[IQS7210A] = 0x38,
+			[IQS7211A] = 0x52,
+			[IQS7211E] = 0x35,
+		},
+		.reg_shift = 4,
+		.reg_width = 1,
+		.label = "core clock frequency selection",
+	},
+	{
+		.name = "azoteq,fosc-trim",
+		.reg_addr[IQS7211_REG_GRP_SYS] = {
+			[IQS7210A] = 0x38,
+			[IQS7211A] = 0x52,
+			[IQS7211E] = 0x35,
+		},
+		.reg_shift = 0,
+		.reg_width = 4,
+		.label = "core clock frequency trim",
+	},
+	{
+		.name = "azoteq,touch-exit",
+		.reg_addr = {
+			[IQS7211_REG_GRP_TP] = {
+				[IQS7210A] = 0x3B,
+				[IQS7211A] = 0x53,
+				[IQS7211E] = 0x38,
+			},
+			[IQS7211_REG_GRP_BTN] = {
+				[IQS7210A] = 0x3E,
+			},
+		},
+		.reg_shift = 8,
+		.reg_width = 8,
+		.label = "touch exit factor",
+	},
+	{
+		.name = "azoteq,touch-enter",
+		.reg_addr = {
+			[IQS7211_REG_GRP_TP] = {
+				[IQS7210A] = 0x3B,
+				[IQS7211A] = 0x53,
+				[IQS7211E] = 0x38,
+			},
+			[IQS7211_REG_GRP_BTN] = {
+				[IQS7210A] = 0x3E,
+			},
+		},
+		.reg_shift = 0,
+		.reg_width = 8,
+		.label = "touch entrance factor",
+	},
+	{
+		.name = "azoteq,thresh",
+		.reg_addr = {
+			[IQS7211_REG_GRP_BTN] = {
+				[IQS7210A] = 0x3C,
+			},
+			[IQS7211_REG_GRP_ALP] = {
+				[IQS7210A] = 0x3D,
+				[IQS7211A] = 0x54,
+				[IQS7211E] = 0x39,
+			},
+		},
+		.label = "threshold",
+	},
+	{
+		.name = "azoteq,debounce-exit",
+		.reg_addr = {
+			[IQS7211_REG_GRP_BTN] = {
+				[IQS7210A] = 0x3F,
+			},
+			[IQS7211_REG_GRP_ALP] = {
+				[IQS7210A] = 0x40,
+				[IQS7211A] = 0x56,
+				[IQS7211E] = 0x3A,
+			},
+		},
+		.reg_shift = 8,
+		.reg_width = 8,
+		.label = "debounce exit factor",
+	},
+	{
+		.name = "azoteq,debounce-enter",
+		.reg_addr = {
+			[IQS7211_REG_GRP_BTN] = {
+				[IQS7210A] = 0x3F,
+			},
+			[IQS7211_REG_GRP_ALP] = {
+				[IQS7210A] = 0x40,
+				[IQS7211A] = 0x56,
+				[IQS7211E] = 0x3A,
+			},
+		},
+		.reg_shift = 0,
+		.reg_width = 8,
+		.label = "debounce entrance factor",
+	},
+	{
+		.name = "azoteq,conv-frac",
+		.reg_addr = {
+			[IQS7211_REG_GRP_TP] = {
+				[IQS7210A] = 0x48,
+				[IQS7211A] = 0x58,
+				[IQS7211E] = 0x3D,
+			},
+			[IQS7211_REG_GRP_BTN] = {
+				[IQS7210A] = 0x49,
+			},
+			[IQS7211_REG_GRP_ALP] = {
+				[IQS7210A] = 0x4A,
+				[IQS7211A] = 0x59,
+				[IQS7211E] = 0x3E,
+			},
+		},
+		.reg_shift = 8,
+		.reg_width = 8,
+		.label = "conversion frequency fractional divider",
+	},
+	{
+		.name = "azoteq,conv-period",
+		.reg_addr = {
+			[IQS7211_REG_GRP_TP] = {
+				[IQS7210A] = 0x48,
+				[IQS7211A] = 0x58,
+				[IQS7211E] = 0x3D,
+			},
+			[IQS7211_REG_GRP_BTN] = {
+				[IQS7210A] = 0x49,
+			},
+			[IQS7211_REG_GRP_ALP] = {
+				[IQS7210A] = 0x4A,
+				[IQS7211A] = 0x59,
+				[IQS7211E] = 0x3E,
+			},
+		},
+		.reg_shift = 0,
+		.reg_width = 8,
+		.label = "conversion period",
+	},
+	{
+		.name = "azoteq,thresh",
+		.reg_addr[IQS7211_REG_GRP_TP] = {
+			[IQS7210A] = 0x55,
+			[IQS7211A] = 0x67,
+			[IQS7211E] = 0x48,
+		},
+		.reg_shift = 0,
+		.reg_width = 8,
+		.label = "threshold",
+	},
+	{
+		.name = "azoteq,contact-split",
+		.reg_addr[IQS7211_REG_GRP_SYS] = {
+			[IQS7210A] = 0x55,
+			[IQS7211A] = 0x67,
+			[IQS7211E] = 0x48,
+		},
+		.reg_shift = 8,
+		.reg_width = 8,
+		.label = "contact split factor",
+	},
+	{
+		.name = "azoteq,trim-x",
+		.reg_addr[IQS7211_REG_GRP_SYS] = {
+			[IQS7210A] = 0x56,
+			[IQS7211E] = 0x49,
+		},
+		.reg_shift = 0,
+		.reg_width = 8,
+		.label = "horizontal trim width",
+	},
+	{
+		.name = "azoteq,trim-x",
+		.reg_addr[IQS7211_REG_GRP_SYS] = {
+			[IQS7211A] = 0x68,
+		},
+		.label = "horizontal trim width",
+	},
+	{
+		.name = "azoteq,trim-y",
+		.reg_addr[IQS7211_REG_GRP_SYS] = {
+			[IQS7210A] = 0x56,
+			[IQS7211E] = 0x49,
+		},
+		.reg_shift = 8,
+		.reg_width = 8,
+		.label = "vertical trim height",
+	},
+	{
+		.name = "azoteq,trim-y",
+		.reg_addr[IQS7211_REG_GRP_SYS] = {
+			[IQS7211A] = 0x69,
+		},
+		.label = "vertical trim height",
+	},
+	{
+		.name = "azoteq,gesture-max-ms",
+		.reg_key = IQS7211_REG_KEY_TAP,
+		.reg_addr[IQS7211_REG_GRP_TP] = {
+			[IQS7210A] = 0x59,
+			[IQS7211A] = 0x81,
+			[IQS7211E] = 0x4C,
+		},
+		.label = "maximum gesture time",
+	},
+	{
+		.name = "azoteq,gesture-mid-ms",
+		.reg_key = IQS7211_REG_KEY_TAP,
+		.reg_addr[IQS7211_REG_GRP_TP] = {
+			[IQS7211E] = 0x4D,
+		},
+		.label = "repeated gesture time",
+	},
+	{
+		.name = "azoteq,gesture-dist",
+		.reg_key = IQS7211_REG_KEY_TAP,
+		.reg_addr[IQS7211_REG_GRP_TP] = {
+			[IQS7210A] = 0x5A,
+			[IQS7211A] = 0x82,
+			[IQS7211E] = 0x4E,
+		},
+		.label = "gesture distance",
+	},
+	{
+		.name = "azoteq,gesture-dist",
+		.reg_key = IQS7211_REG_KEY_HOLD,
+		.reg_addr[IQS7211_REG_GRP_TP] = {
+			[IQS7210A] = 0x5A,
+			[IQS7211A] = 0x82,
+			[IQS7211E] = 0x4E,
+		},
+		.label = "gesture distance",
+	},
+	{
+		.name = "azoteq,gesture-min-ms",
+		.reg_key = IQS7211_REG_KEY_HOLD,
+		.reg_addr[IQS7211_REG_GRP_TP] = {
+			[IQS7210A] = 0x5B,
+			[IQS7211A] = 0x83,
+			[IQS7211E] = 0x4F,
+		},
+		.label = "minimum gesture time",
+	},
+	{
+		.name = "azoteq,gesture-max-ms",
+		.reg_key = IQS7211_REG_KEY_AXIAL_X,
+		.reg_addr[IQS7211_REG_GRP_TP] = {
+			[IQS7210A] = 0x5C,
+			[IQS7211A] = 0x84,
+			[IQS7211E] = 0x50,
+		},
+		.label = "maximum gesture time",
+	},
+	{
+		.name = "azoteq,gesture-max-ms",
+		.reg_key = IQS7211_REG_KEY_AXIAL_Y,
+		.reg_addr[IQS7211_REG_GRP_TP] = {
+			[IQS7210A] = 0x5C,
+			[IQS7211A] = 0x84,
+			[IQS7211E] = 0x50,
+		},
+		.label = "maximum gesture time",
+	},
+	{
+		.name = "azoteq,gesture-dist",
+		.reg_key = IQS7211_REG_KEY_AXIAL_X,
+		.reg_addr[IQS7211_REG_GRP_TP] = {
+			[IQS7210A] = 0x5D,
+			[IQS7211A] = 0x85,
+			[IQS7211E] = 0x51,
+		},
+		.label = "gesture distance",
+	},
+	{
+		.name = "azoteq,gesture-dist",
+		.reg_key = IQS7211_REG_KEY_AXIAL_Y,
+		.reg_addr[IQS7211_REG_GRP_TP] = {
+			[IQS7210A] = 0x5E,
+			[IQS7211A] = 0x86,
+			[IQS7211E] = 0x52,
+		},
+		.label = "gesture distance",
+	},
+	{
+		.name = "azoteq,gesture-dist-rep",
+		.reg_key = IQS7211_REG_KEY_AXIAL_X,
+		.reg_addr[IQS7211_REG_GRP_TP] = {
+			[IQS7211E] = 0x53,
+		},
+		.label = "repeated gesture distance",
+	},
+	{
+		.name = "azoteq,gesture-dist-rep",
+		.reg_key = IQS7211_REG_KEY_AXIAL_Y,
+		.reg_addr[IQS7211_REG_GRP_TP] = {
+			[IQS7211E] = 0x54,
+		},
+		.label = "repeated gesture distance",
+	},
+	{
+		.name = "azoteq,thresh",
+		.reg_key = IQS7211_REG_KEY_PALM,
+		.reg_addr[IQS7211_REG_GRP_TP] = {
+			[IQS7211E] = 0x55,
+		},
+		.reg_shift = 8,
+		.reg_width = 8,
+		.val_max = 42,
+		.label = "threshold",
+	},
+};
+
+static const u8 iqs7211_gesture_angle[] = {
+	0x00, 0x01, 0x02, 0x03,
+	0x04, 0x06, 0x07, 0x08,
+	0x09, 0x0A, 0x0B, 0x0C,
+	0x0E, 0x0F, 0x10, 0x11,
+	0x12, 0x14, 0x15, 0x16,
+	0x17, 0x19, 0x1A, 0x1B,
+	0x1C, 0x1E, 0x1F, 0x21,
+	0x22, 0x23, 0x25, 0x26,
+	0x28, 0x2A, 0x2B, 0x2D,
+	0x2E, 0x30, 0x32, 0x34,
+	0x36, 0x38, 0x3A, 0x3C,
+	0x3E, 0x40, 0x42, 0x45,
+	0x47, 0x4A, 0x4C, 0x4F,
+	0x52, 0x55, 0x58, 0x5B,
+	0x5F, 0x63, 0x66, 0x6B,
+	0x6F, 0x73, 0x78, 0x7E,
+	0x83, 0x89, 0x90, 0x97,
+	0x9E, 0xA7, 0xB0, 0xBA,
+	0xC5, 0xD1, 0xDF, 0xEF,
+};
+
+struct iqs7211_ver_info {
+	__le16 prod_num;
+	__le16 major;
+	__le16 minor;
+	__le32 patch;
+} __packed;
+
+struct iqs7211_touch_data {
+	__le16 abs_x;
+	__le16 abs_y;
+	__le16 pressure;
+	__le16 area;
+} __packed;
+
+struct iqs7211_tp_config {
+	u8 tp_settings;
+	u8 total_rx;
+	u8 total_tx;
+	u8 num_contacts;
+	__le16 max_x;
+	__le16 max_y;
+} __packed;
+
+struct iqs7211_private {
+	const struct iqs7211_dev_desc *dev_desc;
+	struct gpio_desc *reset_gpio;
+	struct gpio_desc *irq_gpio;
+	struct i2c_client *client;
+	struct input_dev *tp_idev;
+	struct input_dev *kp_idev;
+	struct iqs7211_ver_info ver_info;
+	struct iqs7211_tp_config tp_config;
+	struct touchscreen_properties prop;
+	struct list_head reg_field_head;
+	enum iqs7211_comms_mode comms_init;
+	enum iqs7211_comms_mode comms_mode;
+	unsigned int num_contacts;
+	unsigned int kp_code[ARRAY_SIZE(iqs7211e_kp_events)];
+	u8 rx_tx_map[IQS7211_MAX_CTX + 1];
+	u8 cycle_alloc[2][33];
+	u8 exp_file[2];
+	u16 event_mask;
+	u16 ati_start;
+	u16 gesture_cache;
+};
+
+static int iqs7211_irq_poll(struct iqs7211_private *iqs7211, u64 timeout_us)
+{
+	int error, val;
+
+	error = readx_poll_timeout(gpiod_get_value_cansleep, iqs7211->irq_gpio,
+				   val, val, IQS7211_COMMS_SLEEP_US, timeout_us);
+
+	return val < 0 ? val : error;
+}
+
+static int iqs7211_hard_reset(struct iqs7211_private *iqs7211)
+{
+	if (!iqs7211->reset_gpio)
+		return 0;
+
+	gpiod_set_value_cansleep(iqs7211->reset_gpio, 1);
+
+	/*
+	 * The following delay ensures the shared RDY/MCLR pin is sampled in
+	 * between periodic assertions by the device and assumes the default
+	 * communication timeout has not been overwritten in OTP memory.
+	 */
+	if (iqs7211->reset_gpio == iqs7211->irq_gpio)
+		msleep(IQS7211_RESET_TIMEOUT_MS);
+	else
+		usleep_range(1000, 1100);
+
+	gpiod_set_value_cansleep(iqs7211->reset_gpio, 0);
+	if (iqs7211->reset_gpio == iqs7211->irq_gpio)
+		iqs7211_irq_wait();
+
+	return iqs7211_irq_poll(iqs7211, IQS7211_START_TIMEOUT_US);
+}
+
+static int iqs7211_force_comms(struct iqs7211_private *iqs7211)
+{
+	u8 msg_buf[] = { 0xFF, };
+	int ret;
+
+	switch (iqs7211->comms_mode) {
+	case IQS7211_COMMS_MODE_WAIT:
+		return iqs7211_irq_poll(iqs7211, IQS7211_START_TIMEOUT_US);
+
+	case IQS7211_COMMS_MODE_FREE:
+		return 0;
+
+	case IQS7211_COMMS_MODE_FORCE:
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	/*
+	 * The device cannot communicate until it asserts its interrupt (RDY)
+	 * pin. Attempts to do so while RDY is deasserted return an ACK; how-
+	 * ever all write data is ignored, and all read data returns 0xEE.
+	 *
+	 * Unsolicited communication must be preceded by a special force com-
+	 * munication command, after which the device eventually asserts its
+	 * RDY pin and agrees to communicate.
+	 *
+	 * Regardless of whether communication is forced or the result of an
+	 * interrupt, the device automatically deasserts its RDY pin once it
+	 * detects an I2C stop condition, or a timeout expires.
+	 */
+	ret = gpiod_get_value_cansleep(iqs7211->irq_gpio);
+	if (ret < 0)
+		return ret;
+	else if (ret > 0)
+		return 0;
+
+	ret = i2c_master_send(iqs7211->client, msg_buf, sizeof(msg_buf));
+	if (ret < (int)sizeof(msg_buf)) {
+		if (ret >= 0)
+			ret = -EIO;
+
+		msleep(IQS7211_COMMS_RETRY_MS);
+		return ret;
+	}
+
+	iqs7211_irq_wait();
+
+	return iqs7211_irq_poll(iqs7211, IQS7211_COMMS_TIMEOUT_US);
+}
+
+static int iqs7211_read_burst(struct iqs7211_private *iqs7211,
+			      u8 reg, void *val, u16 val_len)
+{
+	int ret, i;
+	struct i2c_client *client = iqs7211->client;
+	struct i2c_msg msg[] = {
+		{
+			.addr = client->addr,
+			.flags = 0,
+			.len = sizeof(reg),
+			.buf = &reg,
+		},
+		{
+			.addr = client->addr,
+			.flags = I2C_M_RD,
+			.len = val_len,
+			.buf = (u8 *)val,
+		},
+	};
+
+	/*
+	 * The following loop protects against an edge case in which the RDY
+	 * pin is automatically deasserted just as the read is initiated. In
+	 * that case, the read must be retried using forced communication.
+	 */
+	for (i = 0; i < IQS7211_NUM_RETRIES; i++) {
+		ret = iqs7211_force_comms(iqs7211);
+		if (ret < 0)
+			continue;
+
+		ret = i2c_transfer(client->adapter, msg, ARRAY_SIZE(msg));
+		if (ret < (int)ARRAY_SIZE(msg)) {
+			if (ret >= 0)
+				ret = -EIO;
+
+			msleep(IQS7211_COMMS_RETRY_MS);
+			continue;
+		}
+
+		if (get_unaligned_le16(msg[1].buf) == IQS7211_COMMS_ERROR) {
+			ret = -ENODATA;
+			continue;
+		}
+
+		ret = 0;
+		break;
+	}
+
+	iqs7211_irq_wait();
+
+	if (ret < 0)
+		dev_err(&client->dev,
+			"Failed to read from address 0x%02X: %d\n", reg, ret);
+
+	return ret;
+}
+
+static int iqs7211_read_word(struct iqs7211_private *iqs7211, u8 reg, u16 *val)
+{
+	__le16 val_buf;
+	int error;
+
+	error = iqs7211_read_burst(iqs7211, reg, &val_buf, sizeof(val_buf));
+	if (error)
+		return error;
+
+	*val = le16_to_cpu(val_buf);
+
+	return 0;
+}
+
+static int iqs7211_write_burst(struct iqs7211_private *iqs7211,
+			       u8 reg, const void *val, u16 val_len)
+{
+	int msg_len = sizeof(reg) + val_len;
+	int ret, i;
+	struct i2c_client *client = iqs7211->client;
+	u8 *msg_buf;
+
+	msg_buf = kzalloc(msg_len, GFP_KERNEL);
+	if (!msg_buf)
+		return -ENOMEM;
+
+	*msg_buf = reg;
+	memcpy(msg_buf + sizeof(reg), val, val_len);
+
+	/*
+	 * The following loop protects against an edge case in which the RDY
+	 * pin is automatically asserted just before the force communication
+	 * command is sent.
+	 *
+	 * In that case, the subsequent I2C stop condition tricks the device
+	 * into preemptively deasserting the RDY pin and the command must be
+	 * sent again.
+	 */
+	for (i = 0; i < IQS7211_NUM_RETRIES; i++) {
+		ret = iqs7211_force_comms(iqs7211);
+		if (ret < 0)
+			continue;
+
+		ret = i2c_master_send(client, msg_buf, msg_len);
+		if (ret < msg_len) {
+			if (ret >= 0)
+				ret = -EIO;
+
+			msleep(IQS7211_COMMS_RETRY_MS);
+			continue;
+		}
+
+		ret = 0;
+		break;
+	}
+
+	kfree(msg_buf);
+
+	iqs7211_irq_wait();
+
+	if (ret < 0)
+		dev_err(&client->dev,
+			"Failed to write to address 0x%02X: %d\n", reg, ret);
+
+	return ret;
+}
+
+static int iqs7211_write_word(struct iqs7211_private *iqs7211, u8 reg, u16 val)
+{
+	__le16 val_buf = cpu_to_le16(val);
+
+	return iqs7211_write_burst(iqs7211, reg, &val_buf, sizeof(val_buf));
+}
+
+static int iqs7211_start_comms(struct iqs7211_private *iqs7211)
+{
+	const struct iqs7211_dev_desc *dev_desc = iqs7211->dev_desc;
+	struct i2c_client *client = iqs7211->client;
+	bool forced_comms;
+	unsigned int val;
+	u16 comms_setup;
+	int error;
+
+	/*
+	 * Until forced communication can be enabled, the host must wait for a
+	 * communication window each time it intends to elicit a response from
+	 * the device.
+	 *
+	 * Forced communication is not necessary, however, if the host adapter
+	 * can support clock stretching. In that case, the device freely clock
+	 * stretches until all pending conversions are complete.
+	 */
+	forced_comms = device_property_present(&client->dev,
+					       "azoteq,forced-comms");
+
+	error = device_property_read_u32(&client->dev,
+					 "azoteq,forced-comms-default", &val);
+	if (error == -EINVAL) {
+		iqs7211->comms_init = IQS7211_COMMS_MODE_WAIT;
+	} else if (error) {
+		dev_err(&client->dev,
+			"Failed to read default communication mode: %d\n",
+			error);
+		return error;
+	} else if (val) {
+		iqs7211->comms_init = forced_comms ? IQS7211_COMMS_MODE_FORCE
+						   : IQS7211_COMMS_MODE_WAIT;
+	} else {
+		iqs7211->comms_init = forced_comms ? IQS7211_COMMS_MODE_WAIT
+						   : IQS7211_COMMS_MODE_FREE;
+	}
+
+	iqs7211->comms_mode = iqs7211->comms_init;
+
+	error = iqs7211_hard_reset(iqs7211);
+	if (error) {
+		dev_err(&client->dev, "Failed to reset device: %d\n", error);
+		return error;
+	}
+
+	error = iqs7211_read_burst(iqs7211, IQS7211_PROD_NUM,
+				   &iqs7211->ver_info,
+				   sizeof(iqs7211->ver_info));
+	if (error)
+		return error;
+
+	if (le16_to_cpu(iqs7211->ver_info.prod_num) != dev_desc->prod_num) {
+		dev_err(&client->dev, "Invalid product number: %u\n",
+			le16_to_cpu(iqs7211->ver_info.prod_num));
+		return -EINVAL;
+	}
+
+	error = iqs7211_read_word(iqs7211, dev_desc->sys_ctrl + 1,
+				  &comms_setup);
+	if (error)
+		return error;
+
+	if (forced_comms)
+		comms_setup |= dev_desc->comms_req;
+	else
+		comms_setup &= ~dev_desc->comms_req;
+
+	error = iqs7211_write_word(iqs7211, dev_desc->sys_ctrl + 1,
+				   comms_setup | dev_desc->comms_end);
+	if (error)
+		return error;
+
+	if (forced_comms)
+		iqs7211->comms_mode = IQS7211_COMMS_MODE_FORCE;
+	else
+		iqs7211->comms_mode = IQS7211_COMMS_MODE_FREE;
+
+	error = iqs7211_read_burst(iqs7211, dev_desc->exp_file,
+				   iqs7211->exp_file,
+				   sizeof(iqs7211->exp_file));
+	if (error)
+		return error;
+
+	error = iqs7211_read_burst(iqs7211, dev_desc->tp_config,
+				   &iqs7211->tp_config,
+				   sizeof(iqs7211->tp_config));
+	if (error)
+		return error;
+
+	error = iqs7211_write_word(iqs7211, dev_desc->sys_ctrl + 1,
+				   comms_setup);
+	if (error)
+		return error;
+
+	iqs7211->event_mask = comms_setup & ~IQS7211_EVENT_MASK_ALL;
+	iqs7211->event_mask |= (IQS7211_EVENT_MASK_ATI | IQS7211_EVENT_MODE);
+
+	return 0;
+}
+
+static int iqs7211_init_device(struct iqs7211_private *iqs7211)
+{
+	const struct iqs7211_dev_desc *dev_desc = iqs7211->dev_desc;
+	struct iqs7211_reg_field_desc *reg_field;
+	__le16 sys_ctrl[] = {
+		cpu_to_le16(dev_desc->ack_reset),
+		cpu_to_le16(iqs7211->event_mask),
+	};
+	int error, i;
+
+	/*
+	 * Acknowledge reset before writing any registers in case the device
+	 * suffers a spurious reset during initialization. The communication
+	 * mode is configured at this time as well.
+	 */
+	error = iqs7211_write_burst(iqs7211, dev_desc->sys_ctrl, sys_ctrl,
+				    sizeof(sys_ctrl));
+	if (error)
+		return error;
+
+	if (iqs7211->event_mask & dev_desc->comms_req)
+		iqs7211->comms_mode = IQS7211_COMMS_MODE_FORCE;
+	else
+		iqs7211->comms_mode = IQS7211_COMMS_MODE_FREE;
+
+	/*
+	 * Take advantage of the stop-bit disable function, if available, to
+	 * save the trouble of having to reopen a communication window after
+	 * each read or write.
+	 */
+	error = iqs7211_write_word(iqs7211, dev_desc->sys_ctrl + 1,
+				   iqs7211->event_mask | dev_desc->comms_end);
+	if (error)
+		return error;
+
+	list_for_each_entry(reg_field, &iqs7211->reg_field_head, list) {
+		u16 new_val = reg_field->val;
+
+		if (reg_field->mask < U16_MAX) {
+			u16 old_val;
+
+			error = iqs7211_read_word(iqs7211, reg_field->addr,
+						  &old_val);
+			if (error)
+				return error;
+
+			new_val = old_val & ~reg_field->mask;
+			new_val |= reg_field->val;
+
+			if (new_val == old_val)
+				continue;
+		}
+
+		error = iqs7211_write_word(iqs7211, reg_field->addr, new_val);
+		if (error)
+			return error;
+	}
+
+	error = iqs7211_write_burst(iqs7211, dev_desc->tp_config,
+				    &iqs7211->tp_config,
+				    sizeof(iqs7211->tp_config));
+	if (error)
+		return error;
+
+	if (**iqs7211->cycle_alloc) {
+		error = iqs7211_write_burst(iqs7211, dev_desc->rx_tx_map,
+					    &iqs7211->rx_tx_map,
+					    dev_desc->num_ctx);
+		if (error)
+			return error;
+
+		for (i = 0; i < sizeof(dev_desc->cycle_limit); i++) {
+			error = iqs7211_write_burst(iqs7211,
+						    dev_desc->cycle_alloc[i],
+						    iqs7211->cycle_alloc[i],
+						    dev_desc->cycle_limit[i] * 3);
+			if (error)
+				return error;
+		}
+	}
+
+	*sys_ctrl = cpu_to_le16(iqs7211->ati_start);
+
+	return iqs7211_write_burst(iqs7211, dev_desc->sys_ctrl, sys_ctrl,
+				   sizeof(sys_ctrl));
+}
+
+static int iqs7211_add_field(struct iqs7211_private *iqs7211,
+			     struct iqs7211_reg_field_desc new_field)
+{
+	struct i2c_client *client = iqs7211->client;
+	struct iqs7211_reg_field_desc *reg_field;
+
+	if (!new_field.addr)
+		return 0;
+
+	list_for_each_entry(reg_field, &iqs7211->reg_field_head, list) {
+		if (reg_field->addr != new_field.addr)
+			continue;
+
+		reg_field->mask |= new_field.mask;
+		reg_field->val |= new_field.val;
+		return 0;
+	}
+
+	reg_field = devm_kzalloc(&client->dev, sizeof(*reg_field), GFP_KERNEL);
+	if (!reg_field)
+		return -ENOMEM;
+
+	reg_field->addr = new_field.addr;
+	reg_field->mask = new_field.mask;
+	reg_field->val = new_field.val;
+
+	list_add(&reg_field->list, &iqs7211->reg_field_head);
+
+	return 0;
+}
+
+static int iqs7211_parse_props(struct iqs7211_private *iqs7211,
+			       struct fwnode_handle *reg_grp_node,
+			       enum iqs7211_reg_grp_id reg_grp,
+			       enum iqs7211_reg_key_id reg_key)
+{
+	struct i2c_client *client = iqs7211->client;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(iqs7211_props); i++) {
+		const char *name = iqs7211_props[i].name;
+		u8 reg_addr = iqs7211_props[i].reg_addr[reg_grp]
+						       [iqs7211->dev_desc -
+							iqs7211_devs];
+		int reg_shift = iqs7211_props[i].reg_shift;
+		int reg_width = iqs7211_props[i].reg_width ? : 16;
+		int val_pitch = iqs7211_props[i].val_pitch ? : 1;
+		int val_min = iqs7211_props[i].val_min;
+		int val_max = iqs7211_props[i].val_max;
+		const char *label = iqs7211_props[i].label ? : name;
+		struct iqs7211_reg_field_desc reg_field;
+		unsigned int val;
+		int error;
+
+		if (iqs7211_props[i].reg_key != reg_key)
+			continue;
+
+		if (!reg_addr)
+			continue;
+
+		error = fwnode_property_read_u32(reg_grp_node, name, &val);
+		if (error == -EINVAL) {
+			continue;
+		} else if (error) {
+			dev_err(&client->dev, "Failed to read %s %s: %d\n",
+				fwnode_get_name(reg_grp_node), label, error);
+			return error;
+		}
+
+		if (!val_max)
+			val_max = GENMASK(reg_width - 1, 0) * val_pitch;
+
+		if (val < val_min || val > val_max) {
+			dev_err(&client->dev, "Invalid %s: %u\n", label, val);
+			return -EINVAL;
+		}
+
+		reg_field.addr = reg_addr;
+		reg_field.mask = GENMASK(reg_shift + reg_width - 1, reg_shift);
+		reg_field.val = val / val_pitch << reg_shift;
+
+		error = iqs7211_add_field(iqs7211, reg_field);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
+static int iqs7211_parse_event(struct iqs7211_private *iqs7211,
+			       struct fwnode_handle *event_node,
+			       enum iqs7211_reg_grp_id reg_grp,
+			       enum iqs7211_reg_key_id reg_key,
+			       unsigned int *event_code)
+{
+	const struct iqs7211_dev_desc *dev_desc = iqs7211->dev_desc;
+	struct i2c_client *client = iqs7211->client;
+	struct iqs7211_reg_field_desc reg_field;
+	unsigned int val;
+	int error;
+
+	error = iqs7211_parse_props(iqs7211, event_node, reg_grp, reg_key);
+	if (error)
+		return error;
+
+	if (reg_key == IQS7211_REG_KEY_AXIAL_X ||
+	    reg_key == IQS7211_REG_KEY_AXIAL_Y) {
+		error = fwnode_property_read_u32(event_node,
+						 "azoteq,gesture-angle", &val);
+		if (!error) {
+			if (val >= ARRAY_SIZE(iqs7211_gesture_angle)) {
+				dev_err(&client->dev,
+					"Invalid %s gesture angle: %u\n",
+					fwnode_get_name(event_node), val);
+				return -EINVAL;
+			}
+
+			reg_field.addr = dev_desc->gesture_angle;
+			reg_field.mask = U8_MAX;
+			reg_field.val = iqs7211_gesture_angle[val];
+
+			error = iqs7211_add_field(iqs7211, reg_field);
+			if (error)
+				return error;
+		} else if (error != -EINVAL) {
+			dev_err(&client->dev,
+				"Failed to read %s gesture angle: %d\n",
+				fwnode_get_name(event_node), error);
+			return error;
+		}
+	}
+
+	error = fwnode_property_read_u32(event_node, "linux,code", event_code);
+	if (error == -EINVAL)
+		error = 0;
+	else if (error)
+		dev_err(&client->dev, "Failed to read %s code: %d\n",
+			fwnode_get_name(event_node), error);
+
+	return error;
+}
+
+static int iqs7211_parse_cycles(struct iqs7211_private *iqs7211,
+				struct fwnode_handle *tp_node)
+{
+	const struct iqs7211_dev_desc *dev_desc = iqs7211->dev_desc;
+	struct i2c_client *client = iqs7211->client;
+	int num_cycles = dev_desc->cycle_limit[0] + dev_desc->cycle_limit[1];
+	int error, count, i, j, k, cycle_start;
+	unsigned int cycle_alloc[IQS7211_MAX_CYCLES][2];
+	u8 total_rx = iqs7211->tp_config.total_rx;
+	u8 total_tx = iqs7211->tp_config.total_tx;
+
+	for (i = 0; i < IQS7211_MAX_CYCLES * 2; i++)
+		*(cycle_alloc[0] + i) = U8_MAX;
+
+	count = fwnode_property_count_u32(tp_node, "azoteq,channel-select");
+	if (count == -EINVAL) {
+		/*
+		 * Assign each sensing cycle's slots (0 and 1) to a channel,
+		 * defined as the intersection between two CRx and CTx pins.
+		 * A channel assignment of 255 means the slot is unused.
+		 */
+		for (i = 0, cycle_start = 0; i < total_tx; i++) {
+			int cycle_stop = 0;
+
+			for (j = 0; j < total_rx; j++) {
+				/*
+				 * Channels formed by CRx0-3 and CRx4-7 are
+				 * bound to slots 0 and 1, respectively.
+				 */
+				int slot = iqs7211->rx_tx_map[j] < 4 ? 0 : 1;
+				int chan = i * total_rx + j;
+
+				for (k = cycle_start; k < num_cycles; k++) {
+					if (cycle_alloc[k][slot] < U8_MAX)
+						continue;
+
+					cycle_alloc[k][slot] = chan;
+					break;
+				}
+
+				if (k < num_cycles) {
+					cycle_stop = max(k, cycle_stop);
+					continue;
+				}
+
+				dev_err(&client->dev,
+					"Insufficient number of cycles\n");
+				return -EINVAL;
+			}
+
+			/*
+			 * Sensing cycles cannot straddle more than one CTx
+			 * pin. As such, the next row's starting cycle must
+			 * be greater than the previous row's highest cycle.
+			 */
+			cycle_start = cycle_stop + 1;
+		}
+	} else if (count < 0) {
+		dev_err(&client->dev, "Failed to count channels: %d\n", count);
+		return count;
+	} else if (count > num_cycles * 2) {
+		dev_err(&client->dev, "Insufficient number of cycles\n");
+		return -EINVAL;
+	} else if (count > 0) {
+		error = fwnode_property_read_u32_array(tp_node,
+						       "azoteq,channel-select",
+						       cycle_alloc[0], count);
+		if (error) {
+			dev_err(&client->dev, "Failed to read channels: %d\n",
+				error);
+			return error;
+		}
+
+		for (i = 0; i < count; i++) {
+			int chan = *(cycle_alloc[0] + i);
+
+			if (chan == U8_MAX)
+				continue;
+
+			if (chan >= total_rx * total_tx) {
+				dev_err(&client->dev, "Invalid channel: %d\n",
+					chan);
+				return -EINVAL;
+			}
+
+			for (j = 0; j < count; j++) {
+				if (j == i || *(cycle_alloc[0] + j) != chan)
+					continue;
+
+				dev_err(&client->dev, "Duplicate channel: %d\n",
+					chan);
+				return -EINVAL;
+			}
+		}
+	}
+
+	/*
+	 * Once the raw channel assignments have been derived, they must be
+	 * packed according to the device's register map.
+	 */
+	for (i = 0, cycle_start = 0; i < sizeof(dev_desc->cycle_limit); i++) {
+		int offs = 0;
+
+		for (j = cycle_start;
+		     j < cycle_start + dev_desc->cycle_limit[i]; j++) {
+			iqs7211->cycle_alloc[i][offs++] = 0x05;
+			iqs7211->cycle_alloc[i][offs++] = cycle_alloc[j][0];
+			iqs7211->cycle_alloc[i][offs++] = cycle_alloc[j][1];
+		}
+
+		cycle_start += dev_desc->cycle_limit[i];
+	}
+
+	return 0;
+}
+
+static int iqs7211_parse_tp(struct iqs7211_private *iqs7211,
+			    struct fwnode_handle *tp_node)
+{
+	const struct iqs7211_dev_desc *dev_desc = iqs7211->dev_desc;
+	struct i2c_client *client = iqs7211->client;
+	unsigned int pins[IQS7211_MAX_CTX];
+	int error, count, i, j;
+
+	count = fwnode_property_count_u32(tp_node, "azoteq,rx-enable");
+	if (count == -EINVAL) {
+		return 0;
+	} else if (count < 0) {
+		dev_err(&client->dev, "Failed to count CRx pins: %d\n", count);
+		return count;
+	} else if (count > IQS7211_NUM_CRX) {
+		dev_err(&client->dev, "Invalid number of CRx pins\n");
+		return -EINVAL;
+	}
+
+	error = fwnode_property_read_u32_array(tp_node, "azoteq,rx-enable",
+					       pins, count);
+	if (error) {
+		dev_err(&client->dev, "Failed to read CRx pins: %d\n", error);
+		return error;
+	}
+
+	for (i = 0; i < count; i++) {
+		if (pins[i] >= IQS7211_NUM_CRX) {
+			dev_err(&client->dev, "Invalid CRx pin: %u\n", pins[i]);
+			return -EINVAL;
+		}
+
+		iqs7211->rx_tx_map[i] = pins[i];
+	}
+
+	iqs7211->tp_config.total_rx = count;
+
+	count = fwnode_property_count_u32(tp_node, "azoteq,tx-enable");
+	if (count < 0) {
+		dev_err(&client->dev, "Failed to count CTx pins: %d\n", count);
+		return count;
+	} else if (count > dev_desc->num_ctx) {
+		dev_err(&client->dev, "Invalid number of CTx pins\n");
+		return -EINVAL;
+	}
+
+	error = fwnode_property_read_u32_array(tp_node, "azoteq,tx-enable",
+					       pins, count);
+	if (error) {
+		dev_err(&client->dev, "Failed to read CTx pins: %d\n", error);
+		return error;
+	}
+
+	for (i = 0; i < count; i++) {
+		if (pins[i] >= dev_desc->num_ctx) {
+			dev_err(&client->dev, "Invalid CTx pin: %u\n", pins[i]);
+			return -EINVAL;
+		}
+
+		for (j = 0; j < iqs7211->tp_config.total_rx; j++) {
+			if (iqs7211->rx_tx_map[j] != pins[i])
+				continue;
+
+			dev_err(&client->dev, "Conflicting CTx pin: %u\n",
+				pins[i]);
+			return -EINVAL;
+		}
+
+		iqs7211->rx_tx_map[iqs7211->tp_config.total_rx + i] = pins[i];
+	}
+
+	iqs7211->tp_config.total_tx = count;
+
+	return iqs7211_parse_cycles(iqs7211, tp_node);
+}
+
+static int iqs7211_parse_alp(struct iqs7211_private *iqs7211,
+			     struct fwnode_handle *alp_node)
+{
+	const struct iqs7211_dev_desc *dev_desc = iqs7211->dev_desc;
+	struct i2c_client *client = iqs7211->client;
+	struct iqs7211_reg_field_desc reg_field;
+	int error, count, i;
+
+	count = fwnode_property_count_u32(alp_node, "azoteq,rx-enable");
+	if (count < 0 && count != -EINVAL) {
+		dev_err(&client->dev, "Failed to count CRx pins: %d\n", count);
+		return count;
+	} else if (count > IQS7211_NUM_CRX) {
+		dev_err(&client->dev, "Invalid number of CRx pins\n");
+		return -EINVAL;
+	} else if (count >= 0) {
+		unsigned int pins[IQS7211_NUM_CRX];
+
+		error = fwnode_property_read_u32_array(alp_node,
+						       "azoteq,rx-enable",
+						       pins, count);
+		if (error) {
+			dev_err(&client->dev, "Failed to read CRx pins: %d\n",
+				error);
+			return error;
+		}
+
+		reg_field.addr = dev_desc->alp_config;
+		reg_field.mask = GENMASK(IQS7211_NUM_CRX - 1, 0);
+		reg_field.val = 0;
+
+		for (i = 0; i < count; i++) {
+			if (pins[i] < dev_desc->min_crx_alp ||
+			    pins[i] >= IQS7211_NUM_CRX) {
+				dev_err(&client->dev, "Invalid CRx pin: %u\n",
+					pins[i]);
+				return -EINVAL;
+			}
+
+			reg_field.val |= BIT(pins[i]);
+		}
+
+		error = iqs7211_add_field(iqs7211, reg_field);
+		if (error)
+			return error;
+	}
+
+	count = fwnode_property_count_u32(alp_node, "azoteq,tx-enable");
+	if (count < 0 && count != -EINVAL) {
+		dev_err(&client->dev, "Failed to count CTx pins: %d\n", count);
+		return count;
+	} else if (count > dev_desc->num_ctx) {
+		dev_err(&client->dev, "Invalid number of CTx pins\n");
+		return -EINVAL;
+	} else if (count >= 0) {
+		unsigned int pins[IQS7211_MAX_CTX];
+
+		error = fwnode_property_read_u32_array(alp_node,
+						       "azoteq,tx-enable",
+						       pins, count);
+		if (error) {
+			dev_err(&client->dev, "Failed to read CTx pins: %d\n",
+				error);
+			return error;
+		}
+
+		reg_field.addr = dev_desc->alp_config + 1;
+		reg_field.mask = GENMASK(dev_desc->num_ctx - 1, 0);
+		reg_field.val = 0;
+
+		for (i = 0; i < count; i++) {
+			if (pins[i] >= dev_desc->num_ctx) {
+				dev_err(&client->dev, "Invalid CTx pin: %u\n",
+					pins[i]);
+				return -EINVAL;
+			}
+
+			reg_field.val |= BIT(pins[i]);
+		}
+
+		error = iqs7211_add_field(iqs7211, reg_field);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
+static int (*iqs7211_parse_extra[IQS7211_NUM_REG_GRPS])
+				(struct iqs7211_private *iqs7211,
+				 struct fwnode_handle *reg_grp_node) = {
+	[IQS7211_REG_GRP_TP] = iqs7211_parse_tp,
+	[IQS7211_REG_GRP_ALP] = iqs7211_parse_alp,
+};
+
+static int iqs7211_parse_reg_grp(struct iqs7211_private *iqs7211,
+				 struct fwnode_handle *reg_grp_node,
+				 enum iqs7211_reg_grp_id reg_grp)
+{
+	const struct iqs7211_dev_desc *dev_desc = iqs7211->dev_desc;
+	struct iqs7211_reg_field_desc reg_field;
+	int error, i;
+
+	error = iqs7211_parse_props(iqs7211, reg_grp_node, reg_grp,
+				    IQS7211_REG_KEY_NONE);
+	if (error)
+		return error;
+
+	if (iqs7211_parse_extra[reg_grp]) {
+		error = iqs7211_parse_extra[reg_grp](iqs7211, reg_grp_node);
+		if (error)
+			return error;
+	}
+
+	iqs7211->ati_start |= dev_desc->ati_start[reg_grp];
+
+	reg_field.addr = dev_desc->kp_enable[reg_grp];
+	reg_field.mask = 0;
+	reg_field.val = 0;
+
+	for (i = 0; i < dev_desc->num_kp_events; i++) {
+		const char *event_name = dev_desc->kp_events[i].name;
+		struct fwnode_handle *event_node;
+
+		if (dev_desc->kp_events[i].reg_grp != reg_grp)
+			continue;
+
+		reg_field.mask |= dev_desc->kp_events[i].enable;
+
+		if (event_name)
+			event_node = fwnode_get_named_child_node(reg_grp_node,
+								 event_name);
+		else
+			event_node = fwnode_handle_get(reg_grp_node);
+
+		if (!event_node)
+			continue;
+
+		error = iqs7211_parse_event(iqs7211, event_node,
+					    dev_desc->kp_events[i].reg_grp,
+					    dev_desc->kp_events[i].reg_key,
+					    &iqs7211->kp_code[i]);
+		fwnode_handle_put(event_node);
+		if (error)
+			return error;
+
+		reg_field.val |= dev_desc->kp_events[i].enable;
+
+		iqs7211->event_mask |= iqs7211_reg_grp_masks[reg_grp];
+	}
+
+	return iqs7211_add_field(iqs7211, reg_field);
+}
+
+static int iqs7211_register_kp(struct iqs7211_private *iqs7211)
+{
+	const struct iqs7211_dev_desc *dev_desc = iqs7211->dev_desc;
+	struct input_dev *kp_idev = iqs7211->kp_idev;
+	struct i2c_client *client = iqs7211->client;
+	int error, i;
+
+	for (i = 0; i < dev_desc->num_kp_events; i++)
+		if (iqs7211->kp_code[i])
+			break;
+
+	if (i == dev_desc->num_kp_events)
+		return 0;
+
+	kp_idev = devm_input_allocate_device(&client->dev);
+	if (!kp_idev)
+		return -ENOMEM;
+
+	iqs7211->kp_idev = kp_idev;
+
+	kp_idev->name = dev_desc->kp_name;
+	kp_idev->id.bustype = BUS_I2C;
+
+	for (i = 0; i < dev_desc->num_kp_events; i++)
+		if (iqs7211->kp_code[i])
+			input_set_capability(iqs7211->kp_idev, EV_KEY,
+					     iqs7211->kp_code[i]);
+
+	error = input_register_device(kp_idev);
+	if (error)
+		dev_err(&client->dev, "Failed to register %s: %d\n",
+			kp_idev->name, error);
+
+	return error;
+}
+
+static int iqs7211_register_tp(struct iqs7211_private *iqs7211)
+{
+	const struct iqs7211_dev_desc *dev_desc = iqs7211->dev_desc;
+	struct touchscreen_properties *prop = &iqs7211->prop;
+	struct input_dev *tp_idev = iqs7211->tp_idev;
+	struct i2c_client *client = iqs7211->client;
+	int error;
+
+	error = device_property_read_u32(&client->dev, "azoteq,num-contacts",
+					 &iqs7211->num_contacts);
+	if (error == -EINVAL) {
+		return 0;
+	} else if (error) {
+		dev_err(&client->dev, "Failed to read number of contacts: %d\n",
+			error);
+		return error;
+	} else if (iqs7211->num_contacts > IQS7211_MAX_CONTACTS) {
+		dev_err(&client->dev, "Invalid number of contacts: %u\n",
+			iqs7211->num_contacts);
+		return -EINVAL;
+	}
+
+	iqs7211->tp_config.num_contacts = iqs7211->num_contacts ? : 1;
+
+	if (!iqs7211->num_contacts)
+		return 0;
+
+	iqs7211->event_mask |= IQS7211_EVENT_MASK_MOVE;
+
+	tp_idev = devm_input_allocate_device(&client->dev);
+	if (!tp_idev)
+		return -ENOMEM;
+
+	iqs7211->tp_idev = tp_idev;
+
+	tp_idev->name = dev_desc->tp_name;
+	tp_idev->id.bustype = BUS_I2C;
+
+	input_set_abs_params(tp_idev, ABS_MT_POSITION_X,
+			     0, le16_to_cpu(iqs7211->tp_config.max_x), 0, 0);
+
+	input_set_abs_params(tp_idev, ABS_MT_POSITION_Y,
+			     0, le16_to_cpu(iqs7211->tp_config.max_y), 0, 0);
+
+	input_set_abs_params(tp_idev, ABS_MT_PRESSURE, 0, U16_MAX, 0, 0);
+
+	touchscreen_parse_properties(tp_idev, true, prop);
+
+	/*
+	 * The device reserves 0xFFFF for coordinates that correspond to slots
+	 * which are not in a state of touch.
+	 */
+	if (prop->max_x >= U16_MAX || prop->max_y >= U16_MAX) {
+		dev_err(&client->dev, "Invalid trackpad size: %u*%u\n",
+			prop->max_x, prop->max_y);
+		return -EINVAL;
+	}
+
+	iqs7211->tp_config.max_x = cpu_to_le16(prop->max_x);
+	iqs7211->tp_config.max_y = cpu_to_le16(prop->max_y);
+
+	error = input_mt_init_slots(tp_idev, iqs7211->num_contacts,
+				    INPUT_MT_DIRECT);
+	if (error) {
+		dev_err(&client->dev, "Failed to initialize slots: %d\n",
+			error);
+		return error;
+	}
+
+	error = input_register_device(tp_idev);
+	if (error)
+		dev_err(&client->dev, "Failed to register %s: %d\n",
+			tp_idev->name, error);
+
+	return error;
+}
+
+static int iqs7211_report(struct iqs7211_private *iqs7211)
+{
+	const struct iqs7211_dev_desc *dev_desc = iqs7211->dev_desc;
+	struct i2c_client *client = iqs7211->client;
+	struct iqs7211_touch_data *touch_data;
+	u16 info_flags, charge_mode, gesture_flags;
+	__le16 status[12];
+	int error, i;
+
+	error = iqs7211_read_burst(iqs7211, dev_desc->sys_stat, status,
+				   dev_desc->contact_offs * sizeof(__le16) +
+				   iqs7211->num_contacts * sizeof(*touch_data));
+	if (error)
+		return error;
+
+	info_flags = le16_to_cpu(status[dev_desc->info_offs]);
+
+	if (info_flags & dev_desc->show_reset) {
+		dev_err(&client->dev, "Unexpected device reset\n");
+
+		/*
+		 * The device may or may not expect forced communication after
+		 * it exits hardware reset, so the corresponding state machine
+		 * must be reset as well.
+		 */
+		iqs7211->comms_mode = iqs7211->comms_init;
+
+		return iqs7211_init_device(iqs7211);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(dev_desc->ati_error); i++) {
+		if (!(info_flags & dev_desc->ati_error[i]))
+			continue;
+
+		dev_err(&client->dev, "Unexpected %s ATI error\n",
+			iqs7211_reg_grp_names[i]);
+		return 0;
+	}
+
+	for (i = 0; i < iqs7211->num_contacts; i++) {
+		u16 pressure;
+
+		touch_data = (struct iqs7211_touch_data *)
+			     &status[dev_desc->contact_offs] + i;
+		pressure = le16_to_cpu(touch_data->pressure);
+
+		input_mt_slot(iqs7211->tp_idev, i);
+		if (input_mt_report_slot_state(iqs7211->tp_idev, MT_TOOL_FINGER,
+					       pressure != 0)) {
+			touchscreen_report_pos(iqs7211->tp_idev, &iqs7211->prop,
+					       le16_to_cpu(touch_data->abs_x),
+					       le16_to_cpu(touch_data->abs_y),
+					       true);
+			input_report_abs(iqs7211->tp_idev, ABS_MT_PRESSURE,
+					 pressure);
+		}
+	}
+
+	if (iqs7211->num_contacts) {
+		input_mt_sync_frame(iqs7211->tp_idev);
+		input_sync(iqs7211->tp_idev);
+	}
+
+	if (!iqs7211->kp_idev)
+		return 0;
+
+	charge_mode = info_flags & GENMASK(dev_desc->charge_shift + 2,
+					   dev_desc->charge_shift);
+	charge_mode >>= dev_desc->charge_shift;
+
+	/*
+	 * A charging mode higher than 2 (idle mode) indicates the device last
+	 * operated in low-power mode and intends to express an ALP event.
+	 */
+	if (info_flags & dev_desc->kp_events->mask && charge_mode > 2) {
+		input_report_key(iqs7211->kp_idev, *iqs7211->kp_code, 1);
+		input_sync(iqs7211->kp_idev);
+
+		input_report_key(iqs7211->kp_idev, *iqs7211->kp_code, 0);
+	}
+
+	for (i = 0; i < dev_desc->num_kp_events; i++) {
+		if (dev_desc->kp_events[i].reg_grp != IQS7211_REG_GRP_BTN)
+			continue;
+
+		input_report_key(iqs7211->kp_idev, iqs7211->kp_code[i],
+				 info_flags & dev_desc->kp_events[i].mask);
+	}
+
+	gesture_flags = le16_to_cpu(status[dev_desc->gesture_offs]);
+
+	for (i = 0; i < dev_desc->num_kp_events; i++) {
+		enum iqs7211_reg_key_id reg_key = dev_desc->kp_events[i].reg_key;
+		u16 mask = dev_desc->kp_events[i].mask;
+
+		if (dev_desc->kp_events[i].reg_grp != IQS7211_REG_GRP_TP)
+			continue;
+
+		if ((gesture_flags ^ iqs7211->gesture_cache) & mask)
+			input_report_key(iqs7211->kp_idev, iqs7211->kp_code[i],
+					 gesture_flags & mask);
+
+		iqs7211->gesture_cache &= ~mask;
+
+		/*
+		 * Hold and palm gestures persist while the contact remains in
+		 * place; all others are momentary and hence are followed by a
+		 * complementary release event.
+		 */
+		if (reg_key == IQS7211_REG_KEY_HOLD ||
+		    reg_key == IQS7211_REG_KEY_PALM) {
+			iqs7211->gesture_cache |= gesture_flags & mask;
+			gesture_flags &= ~mask;
+		}
+	}
+
+	if (gesture_flags) {
+		input_sync(iqs7211->kp_idev);
+
+		for (i = 0; i < dev_desc->num_kp_events; i++)
+			if (dev_desc->kp_events[i].reg_grp == IQS7211_REG_GRP_TP &&
+			    gesture_flags & dev_desc->kp_events[i].mask)
+				input_report_key(iqs7211->kp_idev,
+						 iqs7211->kp_code[i], 0);
+	}
+
+	input_sync(iqs7211->kp_idev);
+
+	return 0;
+}
+
+static irqreturn_t iqs7211_irq(int irq, void *context)
+{
+	struct iqs7211_private *iqs7211 = context;
+
+	return iqs7211_report(iqs7211) ? IRQ_NONE : IRQ_HANDLED;
+}
+
+static int iqs7211_suspend(struct device *dev)
+{
+	struct iqs7211_private *iqs7211 = dev_get_drvdata(dev);
+	const struct iqs7211_dev_desc *dev_desc = iqs7211->dev_desc;
+	int error;
+
+	if (!dev_desc->suspend || device_may_wakeup(dev))
+		return 0;
+
+	/*
+	 * I2C communication prompts the device to assert its RDY pin if it is
+	 * not already asserted. As such, the interrupt must be disabled so as
+	 * to prevent reentrant interrupts.
+	 */
+	disable_irq(gpiod_to_irq(iqs7211->irq_gpio));
+
+	error = iqs7211_write_word(iqs7211, dev_desc->sys_ctrl,
+				   dev_desc->suspend);
+
+	enable_irq(gpiod_to_irq(iqs7211->irq_gpio));
+
+	return error;
+}
+
+static int iqs7211_resume(struct device *dev)
+{
+	struct iqs7211_private *iqs7211 = dev_get_drvdata(dev);
+	const struct iqs7211_dev_desc *dev_desc = iqs7211->dev_desc;
+	__le16 sys_ctrl[] = {
+		0,
+		cpu_to_le16(iqs7211->event_mask),
+	};
+	int error;
+
+	if (!dev_desc->suspend || device_may_wakeup(dev))
+		return 0;
+
+	disable_irq(gpiod_to_irq(iqs7211->irq_gpio));
+
+	/*
+	 * Forced communication, if in use, must be explicitly enabled as part
+	 * of the wake-up command.
+	 */
+	error = iqs7211_write_burst(iqs7211, dev_desc->sys_ctrl, sys_ctrl,
+				    sizeof(sys_ctrl));
+
+	enable_irq(gpiod_to_irq(iqs7211->irq_gpio));
+
+	return error;
+}
+
+static DEFINE_SIMPLE_DEV_PM_OPS(iqs7211_pm, iqs7211_suspend, iqs7211_resume);
+
+static ssize_t fw_info_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	struct iqs7211_private *iqs7211 = dev_get_drvdata(dev);
+
+	return scnprintf(buf, PAGE_SIZE, "%u.%u.%u.%u:%u.%u\n",
+			 le16_to_cpu(iqs7211->ver_info.prod_num),
+			 le32_to_cpu(iqs7211->ver_info.patch),
+			 le16_to_cpu(iqs7211->ver_info.major),
+			 le16_to_cpu(iqs7211->ver_info.minor),
+			 iqs7211->exp_file[1], iqs7211->exp_file[0]);
+}
+
+static DEVICE_ATTR_RO(fw_info);
+
+static struct attribute *iqs7211_attrs[] = {
+	&dev_attr_fw_info.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(iqs7211);
+
+static const struct of_device_id iqs7211_of_match[] = {
+	{
+		.compatible = "azoteq,iqs7210a",
+		.data = (void *)IQS7210A,
+	},
+	{
+		.compatible = "azoteq,iqs7211a",
+		.data = (void *)IQS7211A,
+	},
+	{
+		.compatible = "azoteq,iqs7211e",
+		.data = (void *)IQS7211E,
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, iqs7211_of_match);
+
+static const struct i2c_device_id iqs7211_id[] = {
+	{ "iqs7210a", IQS7210A },
+	{ "iqs7211a", IQS7211A },
+	{ "iqs7211e", IQS7211E },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, iqs7211_id);
+
+static int iqs7211_probe(struct i2c_client *client)
+{
+	struct iqs7211_private *iqs7211;
+	enum iqs7211_reg_grp_id reg_grp;
+	enum iqs7211_dev_id dev_id;
+	unsigned long irq_flags;
+	bool shared_irq;
+	int error, irq;
+
+	iqs7211 = devm_kzalloc(&client->dev, sizeof(*iqs7211), GFP_KERNEL);
+	if (!iqs7211)
+		return -ENOMEM;
+
+	i2c_set_clientdata(client, iqs7211);
+	iqs7211->client = client;
+
+	INIT_LIST_HEAD(&iqs7211->reg_field_head);
+
+	if (client->dev.of_node)
+		dev_id = (enum iqs7211_dev_id)of_device_get_match_data(&client->dev);
+	else
+		dev_id = i2c_match_id(iqs7211_id, client)->driver_data;
+
+	shared_irq = iqs7211_devs[dev_id].num_ctx == IQS7211_MAX_CTX;
+	iqs7211->dev_desc = &iqs7211_devs[dev_id];
+
+	/*
+	 * The RDY pin behaves as an interrupt, but must also be polled ahead
+	 * of unsolicited I2C communication. As such, it is first opened as a
+	 * GPIO and then passed to gpiod_to_irq() to register the interrupt.
+	 *
+	 * If an extra CTx pin is present, the RDY and MCLR pins are combined
+	 * into a single bidirectional pin. In that case, the platform's GPIO
+	 * must be configured as an open-drain output.
+	 */
+	iqs7211->irq_gpio = devm_gpiod_get(&client->dev, "irq",
+					   shared_irq ? GPIOD_OUT_LOW
+						      : GPIOD_IN);
+	if (IS_ERR(iqs7211->irq_gpio)) {
+		error = PTR_ERR(iqs7211->irq_gpio);
+		dev_err(&client->dev, "Failed to request IRQ GPIO: %d\n",
+			error);
+		return error;
+	}
+
+	if (shared_irq) {
+		iqs7211->reset_gpio = iqs7211->irq_gpio;
+	} else {
+		iqs7211->reset_gpio = devm_gpiod_get_optional(&client->dev,
+							      "reset",
+							      GPIOD_OUT_HIGH);
+		if (IS_ERR(iqs7211->reset_gpio)) {
+			error = PTR_ERR(iqs7211->reset_gpio);
+			dev_err(&client->dev,
+				"Failed to request reset GPIO: %d\n", error);
+			return error;
+		}
+	}
+
+	error = iqs7211_start_comms(iqs7211);
+	if (error)
+		return error;
+
+	for (reg_grp = 0; reg_grp < IQS7211_NUM_REG_GRPS; reg_grp++) {
+		const char *reg_grp_name = iqs7211_reg_grp_names[reg_grp];
+		struct fwnode_handle *reg_grp_node;
+
+		if (reg_grp_name)
+			reg_grp_node = device_get_named_child_node(&client->dev,
+								   reg_grp_name);
+		else
+			reg_grp_node = fwnode_handle_get(dev_fwnode(&client->dev));
+
+		if (!reg_grp_node)
+			continue;
+
+		error = iqs7211_parse_reg_grp(iqs7211, reg_grp_node, reg_grp);
+		fwnode_handle_put(reg_grp_node);
+		if (error)
+			return error;
+	}
+
+	error = iqs7211_register_kp(iqs7211);
+	if (error)
+		return error;
+
+	error = iqs7211_register_tp(iqs7211);
+	if (error)
+		return error;
+
+	error = iqs7211_init_device(iqs7211);
+	if (error)
+		return error;
+
+	irq = gpiod_to_irq(iqs7211->irq_gpio);
+	if (irq < 0)
+		return irq;
+
+	irq_flags = gpiod_is_active_low(iqs7211->irq_gpio) ? IRQF_TRIGGER_LOW
+							   : IRQF_TRIGGER_HIGH;
+	irq_flags |= IRQF_ONESHOT;
+
+	error = devm_request_threaded_irq(&client->dev, irq, NULL, iqs7211_irq,
+					  irq_flags, client->name, iqs7211);
+	if (error)
+		dev_err(&client->dev, "Failed to request IRQ: %d\n", error);
+
+	return error;
+}
+
+static struct i2c_driver iqs7211_i2c_driver = {
+	.probe = iqs7211_probe,
+	.id_table = iqs7211_id,
+	.driver = {
+		.name = "iqs7211",
+		.of_match_table = iqs7211_of_match,
+		.dev_groups = iqs7211_groups,
+		.pm = pm_sleep_ptr(&iqs7211_pm),
+	},
+};
+module_i2c_driver(iqs7211_i2c_driver);
+
+MODULE_AUTHOR("Jeff LaBundy <jeff@labundy.com>");
+MODULE_DESCRIPTION("Azoteq IQS7210A/7211A/E Trackpad/Touchscreen Controller");
+MODULE_LICENSE("GPL");

From 677232f879f2464007c511a73048ff5996b479fc Mon Sep 17 00:00:00 2001
From: Jeff LaBundy <jeff@labundy.com>
Date: Thu, 13 Jul 2023 13:12:02 -0500
Subject: [PATCH 0063/1189] Input: iqs7211 - point to match data directly

Point the OF match table directly to the struct that describes the
device as opposed to an intermediate enum; doing so simplifies the
code and avoids a clang warning.

As part of this change, the I2C device ID table is removed, as the
device cannot probe without an OF node due to the unique nature of
the hardware's interrupt pin.

Fixes: f2ba47e65f3b ("Input: add support for Azoteq IQS7210A/7211A/E")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202307131717.LtwApG0z-lkp@intel.com/
Signed-off-by: Jeff LaBundy <jeff@labundy.com>
Link: https://lore.kernel.org/r/ZLA+cuciIeVcCvm6@nixie71
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/iqs7211.c | 26 +++++++-------------------
 1 file changed, 7 insertions(+), 19 deletions(-)

diff --git a/drivers/input/touchscreen/iqs7211.c b/drivers/input/touchscreen/iqs7211.c
index f60316d37f45..dc084f873762 100644
--- a/drivers/input/touchscreen/iqs7211.c
+++ b/drivers/input/touchscreen/iqs7211.c
@@ -2420,33 +2420,24 @@ ATTRIBUTE_GROUPS(iqs7211);
 static const struct of_device_id iqs7211_of_match[] = {
 	{
 		.compatible = "azoteq,iqs7210a",
-		.data = (void *)IQS7210A,
+		.data = &iqs7211_devs[IQS7210A],
 	},
 	{
 		.compatible = "azoteq,iqs7211a",
-		.data = (void *)IQS7211A,
+		.data = &iqs7211_devs[IQS7211A],
 	},
 	{
 		.compatible = "azoteq,iqs7211e",
-		.data = (void *)IQS7211E,
+		.data = &iqs7211_devs[IQS7211E],
 	},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, iqs7211_of_match);
 
-static const struct i2c_device_id iqs7211_id[] = {
-	{ "iqs7210a", IQS7210A },
-	{ "iqs7211a", IQS7211A },
-	{ "iqs7211e", IQS7211E },
-	{ }
-};
-MODULE_DEVICE_TABLE(i2c, iqs7211_id);
-
 static int iqs7211_probe(struct i2c_client *client)
 {
 	struct iqs7211_private *iqs7211;
 	enum iqs7211_reg_grp_id reg_grp;
-	enum iqs7211_dev_id dev_id;
 	unsigned long irq_flags;
 	bool shared_irq;
 	int error, irq;
@@ -2460,13 +2451,11 @@ static int iqs7211_probe(struct i2c_client *client)
 
 	INIT_LIST_HEAD(&iqs7211->reg_field_head);
 
-	if (client->dev.of_node)
-		dev_id = (enum iqs7211_dev_id)of_device_get_match_data(&client->dev);
-	else
-		dev_id = i2c_match_id(iqs7211_id, client)->driver_data;
+	iqs7211->dev_desc = device_get_match_data(&client->dev);
+	if (!iqs7211->dev_desc)
+		return -ENODEV;
 
-	shared_irq = iqs7211_devs[dev_id].num_ctx == IQS7211_MAX_CTX;
-	iqs7211->dev_desc = &iqs7211_devs[dev_id];
+	shared_irq = iqs7211->dev_desc->num_ctx == IQS7211_MAX_CTX;
 
 	/*
 	 * The RDY pin behaves as an interrupt, but must also be polled ahead
@@ -2554,7 +2543,6 @@ static int iqs7211_probe(struct i2c_client *client)
 
 static struct i2c_driver iqs7211_i2c_driver = {
 	.probe = iqs7211_probe,
-	.id_table = iqs7211_id,
 	.driver = {
 		.name = "iqs7211",
 		.of_match_table = iqs7211_of_match,

From dbce1a7d5dce7318d8465b1e0d052ef1d2202237 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Mon, 17 Jul 2023 09:03:47 -0700
Subject: [PATCH 0064/1189] Input: Explicitly include correct DT includes

The DT of_device.h and of_platform.h date back to the separate
of_platform_bus_type before it as merged into the regular platform bus.
As part of that merge prepping Arm DT support 13 years ago, they
"temporarily" include each other. They also include platform_device.h
and of.h. As a result, there's a pretty much random mix of those include
files used throughout the tree. In order to detangle these headers and
replace the implicit includes with struct declarations, users need to
explicitly include the correct includes.

Signed-off-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230714174633.4058096-1-robh@kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/sun4i-lradc-keys.c | 3 ++-
 drivers/input/keyboard/tm2-touchkey.c     | 1 -
 drivers/input/misc/gpio-vibra.c           | 2 +-
 drivers/input/misc/iqs269a.c              | 2 +-
 drivers/input/misc/iqs626a.c              | 2 +-
 drivers/input/misc/iqs7222.c              | 2 +-
 drivers/input/misc/mma8450.c              | 2 +-
 drivers/input/misc/pm8941-pwrkey.c        | 1 -
 drivers/input/misc/pm8xxx-vibrator.c      | 1 -
 drivers/input/misc/pmic8xxx-pwrkey.c      | 1 -
 drivers/input/misc/pwm-vibra.c            | 2 +-
 drivers/input/misc/sparcspkr.c            | 3 ++-
 drivers/input/serio/apbps2.c              | 2 +-
 drivers/input/serio/i8042-sparcio.h       | 4 +++-
 drivers/input/serio/xilinx_ps2.c          | 4 ++--
 drivers/input/touchscreen/cyttsp5.c       | 2 +-
 drivers/input/touchscreen/ili210x.c       | 2 +-
 drivers/input/touchscreen/iqs5xx.c        | 2 +-
 drivers/input/touchscreen/mms114.c        | 1 -
 drivers/input/touchscreen/pixcir_i2c_ts.c | 2 +-
 drivers/input/touchscreen/ti_am335x_tsc.c | 1 -
 21 files changed, 20 insertions(+), 22 deletions(-)

diff --git a/drivers/input/keyboard/sun4i-lradc-keys.c b/drivers/input/keyboard/sun4i-lradc-keys.c
index 95d927cc8b7e..f304cab0ebdb 100644
--- a/drivers/input/keyboard/sun4i-lradc-keys.c
+++ b/drivers/input/keyboard/sun4i-lradc-keys.c
@@ -21,10 +21,11 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/module.h>
-#include <linux/of_platform.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/pm_wakeirq.h>
 #include <linux/pm_wakeup.h>
+#include <linux/property.h>
 #include <linux/regulator/consumer.h>
 #include <linux/reset.h>
 #include <linux/slab.h>
diff --git a/drivers/input/keyboard/tm2-touchkey.c b/drivers/input/keyboard/tm2-touchkey.c
index 75bd3ea51194..0fd761ae052f 100644
--- a/drivers/input/keyboard/tm2-touchkey.c
+++ b/drivers/input/keyboard/tm2-touchkey.c
@@ -19,7 +19,6 @@
 #include <linux/leds.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/pm.h>
 #include <linux/regulator/consumer.h>
 
diff --git a/drivers/input/misc/gpio-vibra.c b/drivers/input/misc/gpio-vibra.c
index c1c3ba5960dd..ad44b4d18a2a 100644
--- a/drivers/input/misc/gpio-vibra.c
+++ b/drivers/input/misc/gpio-vibra.c
@@ -18,7 +18,7 @@
 #include <linux/input.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/property.h>
 #include <linux/regulator/consumer.h>
diff --git a/drivers/input/misc/iqs269a.c b/drivers/input/misc/iqs269a.c
index 1272ef7b5794..c0a085639870 100644
--- a/drivers/input/misc/iqs269a.c
+++ b/drivers/input/misc/iqs269a.c
@@ -17,9 +17,9 @@
 #include <linux/input.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
-#include <linux/of_device.h>
 #include <linux/property.h>
 #include <linux/regmap.h>
 #include <linux/slab.h>
diff --git a/drivers/input/misc/iqs626a.c b/drivers/input/misc/iqs626a.c
index 50035c25c3f7..0dab54d3a060 100644
--- a/drivers/input/misc/iqs626a.c
+++ b/drivers/input/misc/iqs626a.c
@@ -19,8 +19,8 @@
 #include <linux/input/touchscreen.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
 #include <linux/property.h>
 #include <linux/regmap.h>
 #include <linux/slab.h>
diff --git a/drivers/input/misc/iqs7222.c b/drivers/input/misc/iqs7222.c
index a9c1dba1e8c1..36aeeae77611 100644
--- a/drivers/input/misc/iqs7222.c
+++ b/drivers/input/misc/iqs7222.c
@@ -16,8 +16,8 @@
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/ktime.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
 #include <linux/property.h>
 #include <linux/slab.h>
 #include <asm/unaligned.h>
diff --git a/drivers/input/misc/mma8450.c b/drivers/input/misc/mma8450.c
index 76a190b2220b..662b436d765b 100644
--- a/drivers/input/misc/mma8450.c
+++ b/drivers/input/misc/mma8450.c
@@ -11,7 +11,7 @@
 #include <linux/delay.h>
 #include <linux/i2c.h>
 #include <linux/input.h>
-#include <linux/of_device.h>
+#include <linux/mod_devicetable.h>
 
 #define MMA8450_DRV_NAME	"mma8450"
 
diff --git a/drivers/input/misc/pm8941-pwrkey.c b/drivers/input/misc/pm8941-pwrkey.c
index 74d77d8aaeff..ba747c5b2b5f 100644
--- a/drivers/input/misc/pm8941-pwrkey.c
+++ b/drivers/input/misc/pm8941-pwrkey.c
@@ -14,7 +14,6 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/reboot.h>
 #include <linux/regmap.h>
diff --git a/drivers/input/misc/pm8xxx-vibrator.c b/drivers/input/misc/pm8xxx-vibrator.c
index 04cb87efd799..5c288fe7accf 100644
--- a/drivers/input/misc/pm8xxx-vibrator.c
+++ b/drivers/input/misc/pm8xxx-vibrator.c
@@ -7,7 +7,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
 #include <linux/slab.h>
diff --git a/drivers/input/misc/pmic8xxx-pwrkey.c b/drivers/input/misc/pmic8xxx-pwrkey.c
index 89fb137e3715..c406a1cca5c4 100644
--- a/drivers/input/misc/pmic8xxx-pwrkey.c
+++ b/drivers/input/misc/pmic8xxx-pwrkey.c
@@ -12,7 +12,6 @@
 #include <linux/regmap.h>
 #include <linux/log2.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 
 #define PON_CNTL_1 0x1C
 #define PON_CNTL_PULL_UP BIT(7)
diff --git a/drivers/input/misc/pwm-vibra.c b/drivers/input/misc/pwm-vibra.c
index a3cde30ee8d2..acac79c488aa 100644
--- a/drivers/input/misc/pwm-vibra.c
+++ b/drivers/input/misc/pwm-vibra.c
@@ -15,7 +15,7 @@
 #include <linux/input.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/property.h>
 #include <linux/pwm.h>
diff --git a/drivers/input/misc/sparcspkr.c b/drivers/input/misc/sparcspkr.c
index cdcb7737c46a..e5dd84725c6e 100644
--- a/drivers/input/misc/sparcspkr.c
+++ b/drivers/input/misc/sparcspkr.c
@@ -9,7 +9,8 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/input.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
 #include <linux/slab.h>
 
 #include <asm/io.h>
diff --git a/drivers/input/serio/apbps2.c b/drivers/input/serio/apbps2.c
index 513d96e40e0e..3f6866d39b86 100644
--- a/drivers/input/serio/apbps2.c
+++ b/drivers/input/serio/apbps2.c
@@ -14,11 +14,11 @@
  * Contributors: Daniel Hellstrom <daniel@gaisler.com>
  */
 #include <linux/platform_device.h>
-#include <linux/of_device.h>
 #include <linux/module.h>
 #include <linux/serio.h>
 #include <linux/errno.h>
 #include <linux/interrupt.h>
+#include <linux/of.h>
 #include <linux/of_irq.h>
 #include <linux/device.h>
 #include <linux/delay.h>
diff --git a/drivers/input/serio/i8042-sparcio.h b/drivers/input/serio/i8042-sparcio.h
index c712c1fe0605..b68793bf05c8 100644
--- a/drivers/input/serio/i8042-sparcio.h
+++ b/drivers/input/serio/i8042-sparcio.h
@@ -2,7 +2,9 @@
 #ifndef _I8042_SPARCIO_H
 #define _I8042_SPARCIO_H
 
-#include <linux/of_device.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/types.h>
 
 #include <asm/io.h>
diff --git a/drivers/input/serio/xilinx_ps2.c b/drivers/input/serio/xilinx_ps2.c
index 960d7601fbc8..f3d28da70b75 100644
--- a/drivers/input/serio/xilinx_ps2.c
+++ b/drivers/input/serio/xilinx_ps2.c
@@ -14,10 +14,10 @@
 #include <linux/slab.h>
 #include <linux/list.h>
 #include <linux/io.h>
+#include <linux/mod_devicetable.h>
 #include <linux/of_address.h>
-#include <linux/of_device.h>
 #include <linux/of_irq.h>
-#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 
 #define DRIVER_NAME		"xilinx_ps2"
 
diff --git a/drivers/input/touchscreen/cyttsp5.c b/drivers/input/touchscreen/cyttsp5.c
index b461ded946fc..db5a885ecd72 100644
--- a/drivers/input/touchscreen/cyttsp5.c
+++ b/drivers/input/touchscreen/cyttsp5.c
@@ -18,8 +18,8 @@
 #include <linux/input/touchscreen.h>
 #include <linux/interrupt.h>
 #include <linux/i2c.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
 #include <linux/regmap.h>
 #include <asm/unaligned.h>
 
diff --git a/drivers/input/touchscreen/ili210x.c b/drivers/input/touchscreen/ili210x.c
index f7cd773f7292..ad6828e4f2e2 100644
--- a/drivers/input/touchscreen/ili210x.c
+++ b/drivers/input/touchscreen/ili210x.c
@@ -8,8 +8,8 @@
 #include <linux/input/mt.h>
 #include <linux/input/touchscreen.h>
 #include <linux/interrupt.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
 #include <linux/sizes.h>
 #include <linux/slab.h>
 #include <asm/unaligned.h>
diff --git a/drivers/input/touchscreen/iqs5xx.c b/drivers/input/touchscreen/iqs5xx.c
index 0aa9d6492df8..b4768b66eb10 100644
--- a/drivers/input/touchscreen/iqs5xx.c
+++ b/drivers/input/touchscreen/iqs5xx.c
@@ -23,8 +23,8 @@
 #include <linux/input/touchscreen.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
 #include <linux/slab.h>
 #include <asm/unaligned.h>
 
diff --git a/drivers/input/touchscreen/mms114.c b/drivers/input/touchscreen/mms114.c
index ac12494c7930..6109cf7e779a 100644
--- a/drivers/input/touchscreen/mms114.c
+++ b/drivers/input/touchscreen/mms114.c
@@ -7,7 +7,6 @@
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/i2c.h>
 #include <linux/input/mt.h>
 #include <linux/input/touchscreen.h>
diff --git a/drivers/input/touchscreen/pixcir_i2c_ts.c b/drivers/input/touchscreen/pixcir_i2c_ts.c
index 0b4576091dac..4ede0687beb0 100644
--- a/drivers/input/touchscreen/pixcir_i2c_ts.c
+++ b/drivers/input/touchscreen/pixcir_i2c_ts.c
@@ -13,8 +13,8 @@
 #include <linux/input/mt.h>
 #include <linux/input/touchscreen.h>
 #include <linux/interrupt.h>
-#include <linux/of_device.h>
 #include <linux/module.h>
+#include <linux/of.h>
 #include <linux/slab.h>
 
 #define PIXCIR_MAX_SLOTS       5 /* Max fingers supported by driver */
diff --git a/drivers/input/touchscreen/ti_am335x_tsc.c b/drivers/input/touchscreen/ti_am335x_tsc.c
index decf2d24a115..9aa4e35fb4f5 100644
--- a/drivers/input/touchscreen/ti_am335x_tsc.c
+++ b/drivers/input/touchscreen/ti_am335x_tsc.c
@@ -25,7 +25,6 @@
 #include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/sort.h>
 #include <linux/pm_wakeirq.h>
 

From 904ef2c47d8f3d0f0c7d5c0dd68ecc95908d7360 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Mon, 17 Jul 2023 08:50:36 -0700
Subject: [PATCH 0065/1189] Input: gpio-keys - convert to dev_err_probe()

Use the dev_err_probe() helper, instead of open-coding the same
operation.

While at it, invert the error checking logic to simplify code flow.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/d225a837c50e2b19a41555a8f7ce0f94b1689aa4.1689600353.git.geert+renesas@glider.be
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/gpio_keys.c | 21 +++++++++------------
 1 file changed, 9 insertions(+), 12 deletions(-)

diff --git a/drivers/input/keyboard/gpio_keys.c b/drivers/input/keyboard/gpio_keys.c
index c928829a8b0c..2e7c2c046e67 100644
--- a/drivers/input/keyboard/gpio_keys.c
+++ b/drivers/input/keyboard/gpio_keys.c
@@ -523,18 +523,15 @@ static int gpio_keys_setup_key(struct platform_device *pdev,
 						     NULL, GPIOD_IN, desc);
 		if (IS_ERR(bdata->gpiod)) {
 			error = PTR_ERR(bdata->gpiod);
-			if (error == -ENOENT) {
-				/*
-				 * GPIO is optional, we may be dealing with
-				 * purely interrupt-driven setup.
-				 */
-				bdata->gpiod = NULL;
-			} else {
-				if (error != -EPROBE_DEFER)
-					dev_err(dev, "failed to get gpio: %d\n",
-						error);
-				return error;
-			}
+			if (error != -ENOENT)
+				return dev_err_probe(dev, error,
+						     "failed to get gpio\n");
+
+			/*
+			 * GPIO is optional, we may be dealing with
+			 * purely interrupt-driven setup.
+			 */
+			bdata->gpiod = NULL;
 		}
 	} else if (gpio_is_valid(button->gpio)) {
 		/*

From d7781232b5b2d049e654d5ead9921dc49090d214 Mon Sep 17 00:00:00 2001
From: Samuel Holland <samuel.holland@sifive.com>
Date: Mon, 17 Jul 2023 12:20:03 -0700
Subject: [PATCH 0066/1189] Input: da9063 - add wakeup support

Mark the IRQ as a wake IRQ so it will be enabled during system suspend.

Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
Link: https://lore.kernel.org/r/20230717192004.1304287-1-samuel.holland@sifive.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/da9063_onkey.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/input/misc/da9063_onkey.c b/drivers/input/misc/da9063_onkey.c
index b14a389600c9..74808bae326a 100644
--- a/drivers/input/misc/da9063_onkey.c
+++ b/drivers/input/misc/da9063_onkey.c
@@ -10,6 +10,7 @@
 #include <linux/input.h>
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
+#include <linux/pm_wakeirq.h>
 #include <linux/workqueue.h>
 #include <linux/regmap.h>
 #include <linux/of.h>
@@ -251,6 +252,14 @@ static int da9063_onkey_probe(struct platform_device *pdev)
 		return error;
 	}
 
+	error = dev_pm_set_wake_irq(&pdev->dev, irq);
+	if (error)
+		dev_warn(&pdev->dev,
+			 "Failed to set IRQ %d as a wake IRQ: %d\n",
+			 irq, error);
+	else
+		device_init_wakeup(&pdev->dev, true);
+
 	error = input_register_device(onkey->input);
 	if (error) {
 		dev_err(&pdev->dev,

From 21c133be0266b4e7aaf184175d61f5b1824a8769 Mon Sep 17 00:00:00 2001
From: Artur Weber <aweber.kernel@gmail.com>
Date: Tue, 18 Jul 2023 23:15:32 -0700
Subject: [PATCH 0067/1189] dt-bindings: mms114: Add linux,keycodes property
 for touch keys

MELFAS MMS114 and similar touchscreens have support for touch keys.
Add the linux,keycodes property which can be used to set up the
keycodes for the touch keys.

Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Artur Weber <aweber.kernel@gmail.com>
Link: https://lore.kernel.org/r/20230714100424.29798-2-aweber.kernel@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 .../devicetree/bindings/input/touchscreen/melfas,mms114.yaml | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/Documentation/devicetree/bindings/input/touchscreen/melfas,mms114.yaml b/Documentation/devicetree/bindings/input/touchscreen/melfas,mms114.yaml
index fdd02898e249..07f9dd6b1c9c 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/melfas,mms114.yaml
+++ b/Documentation/devicetree/bindings/input/touchscreen/melfas,mms114.yaml
@@ -52,6 +52,11 @@ properties:
   touchscreen-swapped-x-y: true
   touchscreen-max-pressure: true
 
+  linux,keycodes:
+    description: Keycodes for the touch keys
+    minItems: 1
+    maxItems: 15
+
 additionalProperties: false
 
 required:

From bf93349b11ab6f4a5861fbabe01236bf3d58075a Mon Sep 17 00:00:00 2001
From: Artur Weber <aweber.kernel@gmail.com>
Date: Tue, 18 Jul 2023 23:15:43 -0700
Subject: [PATCH 0068/1189] Input: mms114 - add support for touch keys

MELFAS MMS114 and similar touchscreens have support for touch keys.
Enable support of them in the driver. The keycodes to emit can be
controlled by the linux,keycodes DT property.

Sidenote - the MAX_TOUCHKEYS value is set to 15, as that's the
maximum value that the ID field can contain. I don't have access
to any datasheets that could confirm or deny whether this is accurate.

Most downstream drivers I've been able to find only use up to 2 keys
(though I did find a driver that mentioned up to 4, but only 2 were
used). They don't have any checks for a maximum keycode value, it is
just extracted from the ID bits (0xf mask).

The drivers I've been able to find also don't use touch ID 0; I assume
that it is never used, so the keycodes provided in the DT start from
touch ID 1. I suppose this is in-line with the regular behavior
for touch IDs in touchscreen events, as there the provided touch ID
is always lowered by 1, which would cause an overflow if it was 0...
Just in case, we quietly return if the touch ID is set to 0 here.

The implementation of the linux,keycodes property handling code was
adapted from the msg2638 driver.

Signed-off-by: Artur Weber <aweber.kernel@gmail.com>
Link: https://lore.kernel.org/r/20230714100424.29798-3-aweber.kernel@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/mms114.c | 88 +++++++++++++++++++++++++++---
 1 file changed, 81 insertions(+), 7 deletions(-)

diff --git a/drivers/input/touchscreen/mms114.c b/drivers/input/touchscreen/mms114.c
index 6109cf7e779a..af233b6a16d9 100644
--- a/drivers/input/touchscreen/mms114.c
+++ b/drivers/input/touchscreen/mms114.c
@@ -42,6 +42,7 @@
 /* Touchscreen absolute values */
 #define MMS114_MAX_AREA			0xff
 
+#define MMS114_MAX_TOUCHKEYS		15
 #define MMS114_MAX_TOUCH		10
 #define MMS114_EVENT_SIZE		8
 #define MMS136_EVENT_SIZE		6
@@ -69,6 +70,9 @@ struct mms114_data {
 	unsigned int		contact_threshold;
 	unsigned int		moving_threshold;
 
+	u32 keycodes[MMS114_MAX_TOUCHKEYS];
+	int num_keycodes;
+
 	/* Use cache data for mode control register(write only) */
 	u8			cache_mode_control;
 };
@@ -166,11 +170,6 @@ static void mms114_process_mt(struct mms114_data *data, struct mms114_touch *tou
 		return;
 	}
 
-	if (touch->type != MMS114_TYPE_TOUCHSCREEN) {
-		dev_err(&client->dev, "Wrong touch type (%d)\n", touch->type);
-		return;
-	}
-
 	id = touch->id - 1;
 	x = touch->x_lo | touch->x_hi << 8;
 	y = touch->y_lo | touch->y_hi << 8;
@@ -190,9 +189,33 @@ static void mms114_process_mt(struct mms114_data *data, struct mms114_touch *tou
 	}
 }
 
+static void mms114_process_touchkey(struct mms114_data *data,
+				    struct mms114_touch *touch)
+{
+	struct i2c_client *client = data->client;
+	struct input_dev *input_dev = data->input_dev;
+	unsigned int keycode_id;
+
+	if (touch->id == 0)
+		return;
+
+	if (touch->id > data->num_keycodes) {
+		dev_err(&client->dev, "Wrong touch id for touchkey (%d)\n",
+			touch->id);
+		return;
+	}
+
+	keycode_id = touch->id - 1;
+	dev_dbg(&client->dev, "keycode id: %d, pressed: %d\n", keycode_id,
+		touch->pressed);
+
+	input_report_key(input_dev, data->keycodes[keycode_id], touch->pressed);
+}
+
 static irqreturn_t mms114_interrupt(int irq, void *dev_id)
 {
 	struct mms114_data *data = dev_id;
+	struct i2c_client *client = data->client;
 	struct input_dev *input_dev = data->input_dev;
 	struct mms114_touch touch[MMS114_MAX_TOUCH];
 	int packet_size;
@@ -222,8 +245,22 @@ static irqreturn_t mms114_interrupt(int irq, void *dev_id)
 	if (error < 0)
 		goto out;
 
-	for (index = 0; index < touch_size; index++)
-		mms114_process_mt(data, touch + index);
+	for (index = 0; index < touch_size; index++) {
+		switch (touch[index].type) {
+		case MMS114_TYPE_TOUCHSCREEN:
+			mms114_process_mt(data, touch + index);
+			break;
+
+		case MMS114_TYPE_TOUCHKEY:
+			mms114_process_touchkey(data, touch + index);
+			break;
+
+		default:
+			dev_err(&client->dev, "Wrong touch type (%d)\n",
+				touch[index].type);
+			break;
+		}
+	}
 
 	input_mt_report_pointer_emulation(data->input_dev, true);
 	input_sync(data->input_dev);
@@ -445,6 +482,7 @@ static int mms114_probe(struct i2c_client *client)
 	struct input_dev *input_dev;
 	const void *match_data;
 	int error;
+	int i;
 
 	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
 		dev_err(&client->dev, "Not supported I2C adapter\n");
@@ -468,6 +506,42 @@ static int mms114_probe(struct i2c_client *client)
 
 	data->type = (enum mms_type)match_data;
 
+	data->num_keycodes = device_property_count_u32(&client->dev,
+						       "linux,keycodes");
+	if (data->num_keycodes == -EINVAL) {
+		data->num_keycodes = 0;
+	} else if (data->num_keycodes < 0) {
+		dev_err(&client->dev,
+			"Unable to parse linux,keycodes property: %d\n",
+			data->num_keycodes);
+		return data->num_keycodes;
+	} else if (data->num_keycodes > MMS114_MAX_TOUCHKEYS) {
+		dev_warn(&client->dev,
+			"Found %d linux,keycodes but max is %d, ignoring the rest\n",
+			 data->num_keycodes, MMS114_MAX_TOUCHKEYS);
+		data->num_keycodes = MMS114_MAX_TOUCHKEYS;
+	}
+
+	if (data->num_keycodes > 0) {
+		error = device_property_read_u32_array(&client->dev,
+						       "linux,keycodes",
+						       data->keycodes,
+						       data->num_keycodes);
+		if (error) {
+			dev_err(&client->dev,
+				"Unable to read linux,keycodes values: %d\n",
+				error);
+			return error;
+		}
+
+		input_dev->keycode = data->keycodes;
+		input_dev->keycodemax = data->num_keycodes;
+		input_dev->keycodesize = sizeof(data->keycodes[0]);
+		for (i = 0; i < data->num_keycodes; i++)
+			input_set_capability(input_dev,
+					     EV_KEY, data->keycodes[i]);
+	}
+
 	input_set_capability(input_dev, EV_ABS, ABS_MT_POSITION_X);
 	input_set_capability(input_dev, EV_ABS, ABS_MT_POSITION_Y);
 	input_set_abs_params(input_dev, ABS_MT_PRESSURE, 0, 255, 0, 0);

From b4f78ff746ec5274fffa92fa2a4dc531360b5016 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 14 Jul 2023 22:56:14 +0200
Subject: [PATCH 0069/1189] pwm: Use a consistent name for pwm_chip pointers in
 the core
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Most variables of type struct pwm_chip * are named "chip", there are
only three outliers called "pc". Change these three to "chip", too, for
consistency.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/core.c  | 28 ++++++++++++++--------------
 include/linux/pwm.h |  6 +++---
 2 files changed, 17 insertions(+), 17 deletions(-)

diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index 3dacceaef4a9..8c798753c016 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -127,28 +127,28 @@ static int pwm_device_request(struct pwm_device *pwm, const char *label)
 }
 
 struct pwm_device *
-of_pwm_xlate_with_flags(struct pwm_chip *pc, const struct of_phandle_args *args)
+of_pwm_xlate_with_flags(struct pwm_chip *chip, const struct of_phandle_args *args)
 {
 	struct pwm_device *pwm;
 
-	if (pc->of_pwm_n_cells < 2)
+	if (chip->of_pwm_n_cells < 2)
 		return ERR_PTR(-EINVAL);
 
 	/* flags in the third cell are optional */
 	if (args->args_count < 2)
 		return ERR_PTR(-EINVAL);
 
-	if (args->args[0] >= pc->npwm)
+	if (args->args[0] >= chip->npwm)
 		return ERR_PTR(-EINVAL);
 
-	pwm = pwm_request_from_chip(pc, args->args[0], NULL);
+	pwm = pwm_request_from_chip(chip, args->args[0], NULL);
 	if (IS_ERR(pwm))
 		return pwm;
 
 	pwm->args.period = args->args[1];
 	pwm->args.polarity = PWM_POLARITY_NORMAL;
 
-	if (pc->of_pwm_n_cells >= 3) {
+	if (chip->of_pwm_n_cells >= 3) {
 		if (args->args_count > 2 && args->args[2] & PWM_POLARITY_INVERTED)
 			pwm->args.polarity = PWM_POLARITY_INVERSED;
 	}
@@ -158,18 +158,18 @@ of_pwm_xlate_with_flags(struct pwm_chip *pc, const struct of_phandle_args *args)
 EXPORT_SYMBOL_GPL(of_pwm_xlate_with_flags);
 
 struct pwm_device *
-of_pwm_single_xlate(struct pwm_chip *pc, const struct of_phandle_args *args)
+of_pwm_single_xlate(struct pwm_chip *chip, const struct of_phandle_args *args)
 {
 	struct pwm_device *pwm;
 
-	if (pc->of_pwm_n_cells < 1)
+	if (chip->of_pwm_n_cells < 1)
 		return ERR_PTR(-EINVAL);
 
 	/* validate that one cell is specified, optionally with flags */
 	if (args->args_count != 1 && args->args_count != 2)
 		return ERR_PTR(-EINVAL);
 
-	pwm = pwm_request_from_chip(pc, 0, NULL);
+	pwm = pwm_request_from_chip(chip, 0, NULL);
 	if (IS_ERR(pwm))
 		return pwm;
 
@@ -692,7 +692,7 @@ static struct pwm_device *of_pwm_get(struct device *dev, struct device_node *np,
 	struct pwm_device *pwm = NULL;
 	struct of_phandle_args args;
 	struct device_link *dl;
-	struct pwm_chip *pc;
+	struct pwm_chip *chip;
 	int index = 0;
 	int err;
 
@@ -709,16 +709,16 @@ static struct pwm_device *of_pwm_get(struct device *dev, struct device_node *np,
 		return ERR_PTR(err);
 	}
 
-	pc = fwnode_to_pwmchip(of_fwnode_handle(args.np));
-	if (IS_ERR(pc)) {
-		if (PTR_ERR(pc) != -EPROBE_DEFER)
+	chip = fwnode_to_pwmchip(of_fwnode_handle(args.np));
+	if (IS_ERR(chip)) {
+		if (PTR_ERR(chip) != -EPROBE_DEFER)
 			pr_err("%s(): PWM chip not found\n", __func__);
 
-		pwm = ERR_CAST(pc);
+		pwm = ERR_CAST(chip);
 		goto put;
 	}
 
-	pwm = pc->of_xlate(pc, &args);
+	pwm = chip->of_xlate(chip, &args);
 	if (IS_ERR(pwm))
 		goto put;
 
diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index 04ae1d9073a7..d2f9f690a9c1 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -298,7 +298,7 @@ struct pwm_chip {
 	int base;
 	unsigned int npwm;
 
-	struct pwm_device * (*of_xlate)(struct pwm_chip *pc,
+	struct pwm_device * (*of_xlate)(struct pwm_chip *chip,
 					const struct of_phandle_args *args);
 	unsigned int of_pwm_n_cells;
 
@@ -395,9 +395,9 @@ struct pwm_device *pwm_request_from_chip(struct pwm_chip *chip,
 					 unsigned int index,
 					 const char *label);
 
-struct pwm_device *of_pwm_xlate_with_flags(struct pwm_chip *pc,
+struct pwm_device *of_pwm_xlate_with_flags(struct pwm_chip *chip,
 		const struct of_phandle_args *args);
-struct pwm_device *of_pwm_single_xlate(struct pwm_chip *pc,
+struct pwm_device *of_pwm_single_xlate(struct pwm_chip *chip,
 				       const struct of_phandle_args *args);
 
 struct pwm_device *pwm_get(struct device *dev, const char *con_id);

From 3f6a74bd628278e6eab4220449702a388aea7595 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 19 Jul 2023 12:20:11 -0300
Subject: [PATCH 0070/1189] perf evsel: Free evsel->filter on the destructor

Noticed with:

  make EXTRA_CFLAGS="-fsanitize=address" BUILD_BPF_SKEL=1 CORESIGHT=1 O=/tmp/build/perf-tools-next -C tools/perf install-bin

Direct leak of 45 byte(s) in 1 object(s) allocated from:
    #0 0x7f213f87243b in strdup (/lib64/libasan.so.8+0x7243b)
    #1 0x63d15f in evsel__set_filter util/evsel.c:1371
    #2 0x63d15f in evsel__append_filter util/evsel.c:1387
    #3 0x63d15f in evsel__append_tp_filter util/evsel.c:1400
    #4 0x62cd52 in evlist__append_tp_filter util/evlist.c:1145
    #5 0x62cd52 in evlist__append_tp_filter_pids util/evlist.c:1196
    #6 0x541e49 in trace__set_filter_loop_pids /home/acme/git/perf-tools/tools/perf/builtin-trace.c:3646
    #7 0x541e49 in trace__set_filter_pids /home/acme/git/perf-tools/tools/perf/builtin-trace.c:3670
    #8 0x541e49 in trace__run /home/acme/git/perf-tools/tools/perf/builtin-trace.c:3970
    #9 0x541e49 in cmd_trace /home/acme/git/perf-tools/tools/perf/builtin-trace.c:5141
    #10 0x5ef1a2 in run_builtin /home/acme/git/perf-tools/tools/perf/perf.c:323
    #11 0x4196da in handle_internal_command /home/acme/git/perf-tools/tools/perf/perf.c:377
    #12 0x4196da in run_argv /home/acme/git/perf-tools/tools/perf/perf.c:421
    #13 0x4196da in main /home/acme/git/perf-tools/tools/perf/perf.c:537
    #14 0x7f213e84a50f in __libc_start_call_main (/lib64/libc.so.6+0x2750f)

Free it on evsel__exit().

Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/20230719202951.534582-2-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evsel.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 762e2b2634a5..e41bc4d9925f 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1474,6 +1474,7 @@ void evsel__exit(struct evsel *evsel)
 	perf_thread_map__put(evsel->core.threads);
 	zfree(&evsel->group_name);
 	zfree(&evsel->name);
+	zfree(&evsel->filter);
 	zfree(&evsel->pmu_name);
 	zfree(&evsel->group_pmu_name);
 	zfree(&evsel->unit);

From 04cb4fc4d40a5bf1f9d116bc77e69791451f9fcc Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 19 Jul 2023 15:23:52 -0300
Subject: [PATCH 0071/1189] perf thread: Allow tools to register a thread->priv
 destructor

So that when thread__delete() runs it can be called and free stuff tools
stashed into thread->priv, like 'perf trace' does and will use this
new facility to plug some leaks.

Added an assert(thread__priv_destructor == NULL) as suggested in Ian's
review.

Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/CAP-5=fV3Er=Ek8=iE=bSGbEBmM56_PJffMWot1g_5Bh8B5hO7A@mail.gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/thread.c | 13 +++++++++++++
 tools/perf/util/thread.h |  2 ++
 2 files changed, 15 insertions(+)

diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 0b166404c5c3..fe5e6991ae4b 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -80,6 +80,15 @@ err_thread:
 	return NULL;
 }
 
+static void (*thread__priv_destructor)(void *priv);
+
+void thread__set_priv_destructor(void (*destructor)(void *priv))
+{
+	assert(thread__priv_destructor == NULL);
+
+	thread__priv_destructor = destructor;
+}
+
 void thread__delete(struct thread *thread)
 {
 	struct namespaces *namespaces, *tmp_namespaces;
@@ -112,6 +121,10 @@ void thread__delete(struct thread *thread)
 	exit_rwsem(thread__namespaces_lock(thread));
 	exit_rwsem(thread__comm_lock(thread));
 	thread__free_stitch_list(thread);
+
+	if (thread__priv_destructor)
+		thread__priv_destructor(thread__priv(thread));
+
 	RC_CHK_FREE(thread);
 }
 
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 9068a21ce0fa..e79225a0ea46 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -71,6 +71,8 @@ struct thread *thread__new(pid_t pid, pid_t tid);
 int thread__init_maps(struct thread *thread, struct machine *machine);
 void thread__delete(struct thread *thread);
 
+void thread__set_priv_destructor(void (*destructor)(void *priv));
+
 struct thread *thread__get(struct thread *thread);
 void thread__put(struct thread *thread);
 

From 9de251cb501f834aeb13e87598d1f78588964101 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 19 Jul 2023 15:26:23 -0300
Subject: [PATCH 0072/1189] perf trace: Register a thread priv destructor

To plug these leaks detected with:

  $ make EXTRA_CFLAGS="-fsanitize=address" BUILD_BPF_SKEL=1 CORESIGHT=1 O=/tmp/build/perf-tools-next -C tools/perf install-bin

  =================================================================
  ==473890==ERROR: LeakSanitizer: detected memory leaks

  Direct leak of 112 byte(s) in 1 object(s) allocated from:
    #0 0x7fdf19aba097 in calloc (/lib64/libasan.so.8+0xba097)
    #1 0x987836 in zalloc (/home/acme/bin/perf+0x987836)
    #2 0x5367ae in thread_trace__new /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:1289
    #3 0x5367ae in thread__trace /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:1307
    #4 0x5367ae in trace__sys_exit /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:2468
    #5 0x52bf34 in trace__handle_event /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:3177
    #6 0x52bf34 in __trace__deliver_event /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:3685
    #7 0x542927 in trace__deliver_event /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:3712
    #8 0x542927 in trace__run /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:4055
    #9 0x542927 in cmd_trace /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:5141
    #10 0x5ef1a2 in run_builtin /home/acme/git/perf-tools-next/tools/perf/perf.c:323
    #11 0x4196da in handle_internal_command /home/acme/git/perf-tools-next/tools/perf/perf.c:377
    #12 0x4196da in run_argv /home/acme/git/perf-tools-next/tools/perf/perf.c:421
    #13 0x4196da in main /home/acme/git/perf-tools-next/tools/perf/perf.c:537
    #14 0x7fdf18a4a50f in __libc_start_call_main (/lib64/libc.so.6+0x2750f)

  Direct leak of 2048 byte(s) in 1 object(s) allocated from:
    #0 0x7f788fcba6af in __interceptor_malloc (/lib64/libasan.so.8+0xba6af)
    #1 0x5337c0 in trace__sys_enter /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:2342
    #2 0x52bfb4 in trace__handle_event /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:3191
    #3 0x52bfb4 in __trace__deliver_event /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:3699
    #4 0x542883 in trace__deliver_event /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:3726
    #5 0x542883 in trace__run /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:4069
    #6 0x542883 in cmd_trace /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:5155
    #7 0x5ef232 in run_builtin /home/acme/git/perf-tools-next/tools/perf/perf.c:323
    #8 0x4196da in handle_internal_command /home/acme/git/perf-tools-next/tools/perf/perf.c:377
    #9 0x4196da in run_argv /home/acme/git/perf-tools-next/tools/perf/perf.c:421
    #10 0x4196da in main /home/acme/git/perf-tools-next/tools/perf/perf.c:537
    #11 0x7f788ec4a50f in __libc_start_call_main (/lib64/libc.so.6+0x2750f)

  Indirect leak of 48 byte(s) in 1 object(s) allocated from:
    #0 0x7fdf19aba6af in __interceptor_malloc (/lib64/libasan.so.8+0xba6af)
    #1 0x77b335 in intlist__new util/intlist.c:116
    #2 0x5367fd in thread_trace__new /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:1293
    #3 0x5367fd in thread__trace /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:1307
    #4 0x5367fd in trace__sys_exit /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:2468
    #5 0x52bf34 in trace__handle_event /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:3177
    #6 0x52bf34 in __trace__deliver_event /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:3685
    #7 0x542927 in trace__deliver_event /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:3712
    #8 0x542927 in trace__run /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:4055
    #9 0x542927 in cmd_trace /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:5141
    #10 0x5ef1a2 in run_builtin /home/acme/git/perf-tools-next/tools/perf/perf.c:323
    #11 0x4196da in handle_internal_command /home/acme/git/perf-tools-next/tools/perf/perf.c:377
    #12 0x4196da in run_argv /home/acme/git/perf-tools-next/tools/perf/perf.c:421
    #13 0x4196da in main /home/acme/git/perf-tools-next/tools/perf/perf.c:537
    #14 0x7fdf18a4a50f in __libc_start_call_main (/lib64/libc.so.6+0x2750f)

Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/20230719202951.534582-4-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 6e73d0e95715..b7cbe4bcd136 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1296,6 +1296,19 @@ static struct thread_trace *thread_trace__new(void)
 	return ttrace;
 }
 
+static void thread_trace__delete(void *pttrace)
+{
+	struct thread_trace *ttrace = pttrace;
+
+	if (!ttrace)
+		return;
+
+	intlist__delete(ttrace->syscall_stats);
+	ttrace->syscall_stats = NULL;
+	zfree(&ttrace->entry_str);
+	free(ttrace);
+}
+
 static struct thread_trace *thread__trace(struct thread *thread, FILE *fp)
 {
 	struct thread_trace *ttrace;
@@ -1635,6 +1648,8 @@ static int trace__symbols_init(struct trace *trace, struct evlist *evlist)
 	if (trace->host == NULL)
 		return -ENOMEM;
 
+	thread__set_priv_destructor(thread_trace__delete);
+
 	err = trace_event__register_resolver(trace->host, trace__machine__resolve_kernel_addr);
 	if (err < 0)
 		goto out;

From 7962ef13651a9163f07b530607392ea123482e8a Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 19 Jul 2023 15:37:14 -0300
Subject: [PATCH 0073/1189] perf trace: Really free the evsel->priv area

In 3cb4d5e00e037c70 ("perf trace: Free syscall tp fields in
evsel->priv") it only was freeing if strcmp(evsel->tp_format->system,
"syscalls") returned zero, while the corresponding initialization of
evsel->priv was being performed if it was _not_ zero, i.e. if the tp
system wasn't 'syscalls'.

Just stop looking for that and free it if evsel->priv was set, which
should be equivalent.

Also use the pre-existing evsel_trace__delete() function.

This resolves these leaks, detected with:

  $ make EXTRA_CFLAGS="-fsanitize=address" BUILD_BPF_SKEL=1 CORESIGHT=1 O=/tmp/build/perf-tools-next -C tools/perf install-bin

  =================================================================
  ==481565==ERROR: LeakSanitizer: detected memory leaks

  Direct leak of 40 byte(s) in 1 object(s) allocated from:
      #0 0x7f7343cba097 in calloc (/lib64/libasan.so.8+0xba097)
      #1 0x987966 in zalloc (/home/acme/bin/perf+0x987966)
      #2 0x52f9b9 in evsel_trace__new /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:307
      #3 0x52f9b9 in evsel__syscall_tp /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:333
      #4 0x52f9b9 in evsel__init_raw_syscall_tp /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:458
      #5 0x52f9b9 in perf_evsel__raw_syscall_newtp /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:480
      #6 0x540e8b in trace__add_syscall_newtp /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:3212
      #7 0x540e8b in trace__run /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:3891
      #8 0x540e8b in cmd_trace /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:5156
      #9 0x5ef262 in run_builtin /home/acme/git/perf-tools-next/tools/perf/perf.c:323
      #10 0x4196da in handle_internal_command /home/acme/git/perf-tools-next/tools/perf/perf.c:377
      #11 0x4196da in run_argv /home/acme/git/perf-tools-next/tools/perf/perf.c:421
      #12 0x4196da in main /home/acme/git/perf-tools-next/tools/perf/perf.c:537
      #13 0x7f7342c4a50f in __libc_start_call_main (/lib64/libc.so.6+0x2750f)

  Direct leak of 40 byte(s) in 1 object(s) allocated from:
      #0 0x7f7343cba097 in calloc (/lib64/libasan.so.8+0xba097)
      #1 0x987966 in zalloc (/home/acme/bin/perf+0x987966)
      #2 0x52f9b9 in evsel_trace__new /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:307
      #3 0x52f9b9 in evsel__syscall_tp /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:333
      #4 0x52f9b9 in evsel__init_raw_syscall_tp /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:458
      #5 0x52f9b9 in perf_evsel__raw_syscall_newtp /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:480
      #6 0x540dd1 in trace__add_syscall_newtp /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:3205
      #7 0x540dd1 in trace__run /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:3891
      #8 0x540dd1 in cmd_trace /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:5156
      #9 0x5ef262 in run_builtin /home/acme/git/perf-tools-next/tools/perf/perf.c:323
      #10 0x4196da in handle_internal_command /home/acme/git/perf-tools-next/tools/perf/perf.c:377
      #11 0x4196da in run_argv /home/acme/git/perf-tools-next/tools/perf/perf.c:421
      #12 0x4196da in main /home/acme/git/perf-tools-next/tools/perf/perf.c:537
      #13 0x7f7342c4a50f in __libc_start_call_main (/lib64/libc.so.6+0x2750f)

  SUMMARY: AddressSanitizer: 80 byte(s) leaked in 2 allocation(s).
  [root@quaco ~]#

With this we plug all leaks with "perf trace sleep 1".

Fixes: 3cb4d5e00e037c70 ("perf trace: Free syscall tp fields in evsel->priv")
Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Riccardo Mancini <rickyman7@gmail.com>
Link: https://lore.kernel.org/lkml/20230719202951.534582-5-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index b7cbe4bcd136..56651d666480 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -3151,13 +3151,8 @@ static void evlist__free_syscall_tp_fields(struct evlist *evlist)
 	struct evsel *evsel;
 
 	evlist__for_each_entry(evlist, evsel) {
-		struct evsel_trace *et = evsel->priv;
-
-		if (!et || !evsel->tp_format || strcmp(evsel->tp_format->system, "syscalls"))
-			continue;
-
-		zfree(&et->fmt);
-		free(et);
+		evsel_trace__delete(evsel->priv);
+		evsel->priv = NULL;
 	}
 }
 

From fcca1faf11b47011770c361a1dfc36ed83905148 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 19 Jul 2023 16:49:02 -0300
Subject: [PATCH 0074/1189] perf trace: Free thread_trace->files table

The fd->pathname table that is kept in 'struct thread_trace' and thus in
thread->priv must be freed when a thread is deleted.

This was also detected using -fsanitize=address.

Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/20230719202951.534582-6-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 56651d666480..7ece2521efb6 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1296,6 +1296,8 @@ static struct thread_trace *thread_trace__new(void)
 	return ttrace;
 }
 
+static void thread_trace__free_files(struct thread_trace *ttrace);
+
 static void thread_trace__delete(void *pttrace)
 {
 	struct thread_trace *ttrace = pttrace;
@@ -1305,6 +1307,7 @@ static void thread_trace__delete(void *pttrace)
 
 	intlist__delete(ttrace->syscall_stats);
 	ttrace->syscall_stats = NULL;
+	thread_trace__free_files(ttrace);
 	zfree(&ttrace->entry_str);
 	free(ttrace);
 }
@@ -1346,6 +1349,17 @@ void syscall_arg__set_ret_scnprintf(struct syscall_arg *arg,
 
 static const size_t trace__entry_str_size = 2048;
 
+static void thread_trace__free_files(struct thread_trace *ttrace)
+{
+	for (int i = 0; i < ttrace->files.max; ++i) {
+		struct file *file = ttrace->files.table + i;
+		zfree(&file->pathname);
+	}
+
+	zfree(&ttrace->files.table);
+	ttrace->files.max  = -1;
+}
+
 static struct file *thread_trace__files_entry(struct thread_trace *ttrace, int fd)
 {
 	if (fd < 0)

From faa4e0da1cbab97aa18bb6562ab32d9f0fc32e82 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 19 Jul 2023 16:53:01 -0300
Subject: [PATCH 0075/1189] MAINTAINERS: Add git information for perf-tools and
 perf-tools-next trees/branches

Now the perf tools development is done on these trees/branches:

  git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools.git perf-tools
  git git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next.git perf-tools-next

For a while I'll continue mirroring what is these to the same branches
in my git tree.

Suggested-by: John Garry <john.g.garry@oracle.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/lkml/CAP-5=fVGOP6-k=BTRd_bn=N0HVy+1ShpdW5rk5ND0ZGhm_fQkg@mail.gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 MAINTAINERS | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index aee340630eca..e351cfc7cd41 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16629,6 +16629,8 @@ L:	linux-kernel@vger.kernel.org
 S:	Supported
 W:	https://perf.wiki.kernel.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf/core
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools.git perf-tools
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next.git perf-tools-next
 F:	arch/*/events/*
 F:	arch/*/events/*/*
 F:	arch/*/include/asm/perf_event.h

From 2df270716447a1024a6c955eed8fa579333dca85 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 2 Jun 2023 15:18:27 -0300
Subject: [PATCH 0076/1189] perf bench uprobe: Add benchmark to test uprobe
 overhead

This just adds the initial "workload", a call to libc's usleep(1000us)
function:

  $ perf stat --null perf bench uprobe all
  # Running uprobe/baseline benchmark...
  # Executed 1000 usleep(1000) calls
       Total time: 1053533 usecs

   1053.533 usecs/op

   Performance counter stats for 'perf bench uprobe all':

         1.061042896 seconds time elapsed

         0.001079000 seconds user
         0.006499000 seconds sys

  $

More entries will be added using a BPF skel to add various uprobes to
the usleep() function.

Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andre Fredette <anfredet@redhat.com>
Cc: Clark Williams <williams@redhat.com>
Cc: Dave Tucker <datucker@redhat.com>
Cc: Derek Barbosa <debarbos@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/20230719204910.539044-2-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-bench.txt |  3 +
 tools/perf/bench/Build                  |  1 +
 tools/perf/bench/bench.h                |  1 +
 tools/perf/bench/uprobe.c               | 80 +++++++++++++++++++++++++
 tools/perf/builtin-bench.c              |  6 ++
 5 files changed, 91 insertions(+)
 create mode 100644 tools/perf/bench/uprobe.c

diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt
index f04f0eaded98..ca5789625cd2 100644
--- a/tools/perf/Documentation/perf-bench.txt
+++ b/tools/perf/Documentation/perf-bench.txt
@@ -67,6 +67,9 @@ SUBSYSTEM
 'internals'::
 	Benchmark internal perf functionality.
 
+'uprobe'::
+	Benchmark overhead of uprobe + BPF.
+
 'all'::
 	All benchmark subsystems.
 
diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build
index 0f158dc8139b..47412d47dccf 100644
--- a/tools/perf/bench/Build
+++ b/tools/perf/bench/Build
@@ -16,6 +16,7 @@ perf-y += inject-buildid.o
 perf-y += evlist-open-close.o
 perf-y += breakpoint.o
 perf-y += pmu-scan.o
+perf-y += uprobe.o
 
 perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o
 perf-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index 0d2b65976212..201311f75c96 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -42,6 +42,7 @@ int bench_inject_build_id(int argc, const char **argv);
 int bench_evlist_open_close(int argc, const char **argv);
 int bench_breakpoint_thread(int argc, const char **argv);
 int bench_breakpoint_enable(int argc, const char **argv);
+int bench_uprobe_baseline(int argc, const char **argv);
 int bench_pmu_scan(int argc, const char **argv);
 
 #define BENCH_FORMAT_DEFAULT_STR	"default"
diff --git a/tools/perf/bench/uprobe.c b/tools/perf/bench/uprobe.c
new file mode 100644
index 000000000000..707174220a76
--- /dev/null
+++ b/tools/perf/bench/uprobe.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/*
+ * uprobe.c
+ *
+ * uprobe benchmarks
+ *
+ *  Copyright (C) 2023, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ */
+#include "../perf.h"
+#include "../util/util.h"
+#include <subcmd/parse-options.h>
+#include "../builtin.h"
+#include "bench.h"
+#include <linux/time64.h>
+
+#include <inttypes.h>
+#include <stdio.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <time.h>
+#include <unistd.h>
+#include <stdlib.h>
+
+#define LOOPS_DEFAULT 1000
+static int loops = LOOPS_DEFAULT;
+
+static const struct option options[] = {
+	OPT_INTEGER('l', "loop",	&loops,		"Specify number of loops"),
+	OPT_END()
+};
+
+static const char * const bench_uprobe_usage[] = {
+	"perf bench uprobe <options>",
+	NULL
+};
+
+static int bench_uprobe(int argc, const char **argv)
+{
+	const char *name = "usleep(1000)", *unit = "usec";
+	struct timespec start, end;
+	u64 diff;
+	int i;
+
+	argc = parse_options(argc, argv, options, bench_uprobe_usage, 0);
+
+	clock_gettime(CLOCK_REALTIME, &start);
+
+	for (i = 0; i < loops; i++) {
+		usleep(USEC_PER_MSEC);
+	}
+
+	clock_gettime(CLOCK_REALTIME, &end);
+
+	diff = end.tv_sec * NSEC_PER_SEC + end.tv_nsec - (start.tv_sec * NSEC_PER_SEC + start.tv_nsec);
+	diff /= NSEC_PER_USEC;
+
+	switch (bench_format) {
+	case BENCH_FORMAT_DEFAULT:
+		printf("# Executed %'d %s calls\n", loops, name);
+		printf(" %14s: %'" PRIu64 " %ss\n\n", "Total time", diff, unit);
+		printf(" %'.3f %ss/op\n", (double)diff / (double)loops, unit);
+		break;
+
+	case BENCH_FORMAT_SIMPLE:
+		printf("%" PRIu64 "\n", diff);
+		break;
+
+	default:
+		/* reaching here is something of a disaster */
+		fprintf(stderr, "Unknown format:%d\n", bench_format);
+		exit(1);
+	}
+
+	return 0;
+}
+
+int bench_uprobe_baseline(int argc, const char **argv)
+{
+	return bench_uprobe(argc, argv);
+}
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index db435b791a09..09637aee8341 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -104,6 +104,11 @@ static struct bench breakpoint_benchmarks[] = {
 	{ NULL,	NULL, NULL },
 };
 
+static struct bench uprobe_benchmarks[] = {
+	{ "baseline",	"Baseline libc usleep(1000) call",	bench_uprobe_baseline,	},
+	{ NULL,	NULL, NULL },
+};
+
 struct collection {
 	const char	*name;
 	const char	*summary;
@@ -123,6 +128,7 @@ static struct collection collections[] = {
 #endif
 	{ "internals",	"Perf-internals benchmarks",			internals_benchmarks	},
 	{ "breakpoint",	"Breakpoint benchmarks",			breakpoint_benchmarks	},
+	{ "uprobe",	"uprobe benchmarks",				uprobe_benchmarks	},
 	{ "all",	"All benchmarks",				NULL			},
 	{ NULL,		NULL,						NULL			}
 };

From dded6f615b854740461be63672fa05158875ffaa Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 5 Jul 2023 08:45:12 -0300
Subject: [PATCH 0077/1189] perf bench uprobe: Print diff to baseline

This is just prep work to show the diff to the unmodified workload.

Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andre Fredette <anfredet@redhat.com>
Cc: Clark Williams <williams@redhat.com>
Cc: Dave Tucker <datucker@redhat.com>
Cc: Derek Barbosa <debarbos@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/20230719204910.539044-3-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/bench/uprobe.c | 27 ++++++++++++++++++++++++---
 1 file changed, 24 insertions(+), 3 deletions(-)

diff --git a/tools/perf/bench/uprobe.c b/tools/perf/bench/uprobe.c
index 707174220a76..60e7c43298d8 100644
--- a/tools/perf/bench/uprobe.c
+++ b/tools/perf/bench/uprobe.c
@@ -34,6 +34,29 @@ static const char * const bench_uprobe_usage[] = {
 	NULL
 };
 
+static int bench_uprobe_format__default_fprintf(const char *name, const char *unit, u64 diff, FILE *fp)
+{
+	static u64 baseline;
+	s64 diff_to_baseline = diff - baseline;
+	int printed = fprintf(fp, "# Executed %'d %s calls\n", loops, name);
+
+	printed += fprintf(fp, " %14s: %'" PRIu64 " %ss", "Total time", diff, unit);
+
+	if (baseline)
+		printed += fprintf(fp, " %s%'" PRId64 " to baseline", diff_to_baseline > 0 ? "+" : "", diff_to_baseline);
+
+	printed += fprintf(fp, "\n\n %'.3f %ss/op", (double)diff / (double)loops, unit);
+
+	if (baseline)
+		printed += fprintf(fp, " %'.3f %ss/op to baseline", (double)diff_to_baseline / (double)loops, unit);
+	else
+		baseline = diff;
+
+	fputc('\n', fp);
+
+	return printed + 1;
+}
+
 static int bench_uprobe(int argc, const char **argv)
 {
 	const char *name = "usleep(1000)", *unit = "usec";
@@ -56,9 +79,7 @@ static int bench_uprobe(int argc, const char **argv)
 
 	switch (bench_format) {
 	case BENCH_FORMAT_DEFAULT:
-		printf("# Executed %'d %s calls\n", loops, name);
-		printf(" %14s: %'" PRIu64 " %ss\n\n", "Total time", diff, unit);
-		printf(" %'.3f %ss/op\n", (double)diff / (double)loops, unit);
+		bench_uprobe_format__default_fprintf(name, unit, diff, stdout);
 		break;
 
 	case BENCH_FORMAT_SIMPLE:

From 54d811023b5f99e658511b577b16a6d7014d162c Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 5 Jul 2023 08:49:40 -0300
Subject: [PATCH 0078/1189] perf bench uprobe: Show diff to previous

Will be useful to show the incremental overhead as we do more stuff in
the BPF program attached to the uprobes.

Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andre Fredette <anfredet@redhat.com>
Cc: Clark Williams <williams@redhat.com>
Cc: Dave Tucker <datucker@redhat.com>
Cc: Derek Barbosa <debarbos@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/20230719204910.539044-4-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/bench/uprobe.c | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

diff --git a/tools/perf/bench/uprobe.c b/tools/perf/bench/uprobe.c
index 60e7c43298d8..a90e09f791c5 100644
--- a/tools/perf/bench/uprobe.c
+++ b/tools/perf/bench/uprobe.c
@@ -36,24 +36,35 @@ static const char * const bench_uprobe_usage[] = {
 
 static int bench_uprobe_format__default_fprintf(const char *name, const char *unit, u64 diff, FILE *fp)
 {
-	static u64 baseline;
-	s64 diff_to_baseline = diff - baseline;
+	static u64 baseline, previous;
+	s64 diff_to_baseline = diff - baseline,
+	    diff_to_previous = diff - previous;
 	int printed = fprintf(fp, "# Executed %'d %s calls\n", loops, name);
 
 	printed += fprintf(fp, " %14s: %'" PRIu64 " %ss", "Total time", diff, unit);
 
-	if (baseline)
+	if (baseline) {
 		printed += fprintf(fp, " %s%'" PRId64 " to baseline", diff_to_baseline > 0 ? "+" : "", diff_to_baseline);
 
+		if (previous != baseline)
+			fprintf(stdout, " %s%'" PRId64 " to previous", diff_to_previous > 0 ? "+" : "", diff_to_previous);
+	}
+
 	printed += fprintf(fp, "\n\n %'.3f %ss/op", (double)diff / (double)loops, unit);
 
-	if (baseline)
+	if (baseline) {
 		printed += fprintf(fp, " %'.3f %ss/op to baseline", (double)diff_to_baseline / (double)loops, unit);
-	else
+
+		if (previous != baseline)
+			printed += fprintf(fp, " %'.3f %ss/op to previous", (double)diff_to_previous / (double)loops, unit);
+	} else {
 		baseline = diff;
+	}
 
 	fputc('\n', fp);
 
+	previous = diff;
+
 	return printed + 1;
 }
 

From 6af5e4cf3a6521d23ca53df5001319babefdffbf Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 2 Jun 2023 17:42:47 -0300
Subject: [PATCH 0079/1189] perf bench uprobe empty: Add entry attaching an
 empty BPF program

Using libbpf and a BPF skel:

  # perf bench uprobe all
  # Running uprobe/baseline benchmark...
  # Executed 1,000 usleep(1000) calls
       Total time: 1,055,618 usecs

   1,055.618 usecs/op
  # Running uprobe/empty benchmark...
  # Executed 1,000 usleep(1000) calls
       Total time: 1,057,146 usecs +1,528 to baseline

   1,057.146 usecs/op
  #

Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andre Fredette <anfredet@redhat.com>
Cc: Clark Williams <williams@redhat.com>
Cc: Dave Tucker <datucker@redhat.com>
Cc: Derek Barbosa <debarbos@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/20230719204910.539044-5-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Makefile.perf                    |  1 +
 tools/perf/bench/bench.h                    |  1 +
 tools/perf/bench/uprobe.c                   | 75 ++++++++++++++++++++-
 tools/perf/builtin-bench.c                  |  3 +-
 tools/perf/util/bpf_skel/bench_uprobe.bpf.c | 12 ++++
 5 files changed, 88 insertions(+), 4 deletions(-)
 create mode 100644 tools/perf/util/bpf_skel/bench_uprobe.bpf.c

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 097316ef38e6..a44d16ec11ee 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -1057,6 +1057,7 @@ SKELETONS += $(SKEL_OUT)/bperf_leader.skel.h $(SKEL_OUT)/bperf_follower.skel.h
 SKELETONS += $(SKEL_OUT)/bperf_cgroup.skel.h $(SKEL_OUT)/func_latency.skel.h
 SKELETONS += $(SKEL_OUT)/off_cpu.skel.h $(SKEL_OUT)/lock_contention.skel.h
 SKELETONS += $(SKEL_OUT)/kwork_trace.skel.h $(SKEL_OUT)/sample_filter.skel.h
+SKELETONS += $(SKEL_OUT)/bench_uprobe.skel.h
 
 $(SKEL_TMP_OUT) $(LIBAPI_OUTPUT) $(LIBBPF_OUTPUT) $(LIBPERF_OUTPUT) $(LIBSUBCMD_OUTPUT) $(LIBSYMBOL_OUTPUT):
 	$(Q)$(MKDIR) -p $@
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index 201311f75c96..daf4850b441c 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -43,6 +43,7 @@ int bench_evlist_open_close(int argc, const char **argv);
 int bench_breakpoint_thread(int argc, const char **argv);
 int bench_breakpoint_enable(int argc, const char **argv);
 int bench_uprobe_baseline(int argc, const char **argv);
+int bench_uprobe_empty(int argc, const char **argv);
 int bench_pmu_scan(int argc, const char **argv);
 
 #define BENCH_FORMAT_DEFAULT_STR	"default"
diff --git a/tools/perf/bench/uprobe.c b/tools/perf/bench/uprobe.c
index a90e09f791c5..dfb90038a4f7 100644
--- a/tools/perf/bench/uprobe.c
+++ b/tools/perf/bench/uprobe.c
@@ -24,6 +24,11 @@
 #define LOOPS_DEFAULT 1000
 static int loops = LOOPS_DEFAULT;
 
+enum bench_uprobe {
+        BENCH_UPROBE__BASELINE,
+        BENCH_UPROBE__EMPTY,
+};
+
 static const struct option options[] = {
 	OPT_INTEGER('l', "loop",	&loops,		"Specify number of loops"),
 	OPT_END()
@@ -34,6 +39,59 @@ static const char * const bench_uprobe_usage[] = {
 	NULL
 };
 
+#ifdef HAVE_BPF_SKEL
+#include "bpf_skel/bench_uprobe.skel.h"
+
+struct bench_uprobe_bpf *skel;
+
+static int bench_uprobe__setup_bpf_skel(void)
+{
+	DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
+	int err;
+
+	/* Load and verify BPF application */
+	skel = bench_uprobe_bpf__open();
+	if (!skel) {
+		fprintf(stderr, "Failed to open and load uprobes bench BPF skeleton\n");
+		return -1;
+	}
+
+	err = bench_uprobe_bpf__load(skel);
+	if (err) {
+		fprintf(stderr, "Failed to load and verify BPF skeleton\n");
+		goto cleanup;
+	}
+
+	uprobe_opts.func_name = "usleep";
+	skel->links.empty = bpf_program__attach_uprobe_opts(/*prog=*/skel->progs.empty,
+							    /*pid=*/-1,
+							    /*binary_path=*/"/lib64/libc.so.6",
+							    /*func_offset=*/0,
+							    /*opts=*/&uprobe_opts);
+	if (!skel->links.empty) {
+		err = -errno;
+		fprintf(stderr, "Failed to attach bench uprobe: %s\n", strerror(errno));
+		goto cleanup;
+	}
+
+	return err;
+cleanup:
+	bench_uprobe_bpf__destroy(skel);
+	return err;
+}
+
+static void bench_uprobe__teardown_bpf_skel(void)
+{
+	if (skel) {
+		bench_uprobe_bpf__destroy(skel);
+		skel = NULL;
+	}
+}
+#else
+static int bench_uprobe__setup_bpf_skel(void) { return 0; }
+static void bench_uprobe__teardown_bpf_skel(void) {};
+#endif
+
 static int bench_uprobe_format__default_fprintf(const char *name, const char *unit, u64 diff, FILE *fp)
 {
 	static u64 baseline, previous;
@@ -68,7 +126,7 @@ static int bench_uprobe_format__default_fprintf(const char *name, const char *un
 	return printed + 1;
 }
 
-static int bench_uprobe(int argc, const char **argv)
+static int bench_uprobe(int argc, const char **argv, enum bench_uprobe bench)
 {
 	const char *name = "usleep(1000)", *unit = "usec";
 	struct timespec start, end;
@@ -77,7 +135,10 @@ static int bench_uprobe(int argc, const char **argv)
 
 	argc = parse_options(argc, argv, options, bench_uprobe_usage, 0);
 
-	clock_gettime(CLOCK_REALTIME, &start);
+	if (bench != BENCH_UPROBE__BASELINE && bench_uprobe__setup_bpf_skel() < 0)
+		return 0;
+
+        clock_gettime(CLOCK_REALTIME, &start);
 
 	for (i = 0; i < loops; i++) {
 		usleep(USEC_PER_MSEC);
@@ -103,10 +164,18 @@ static int bench_uprobe(int argc, const char **argv)
 		exit(1);
 	}
 
+	if (bench != BENCH_UPROBE__BASELINE)
+		bench_uprobe__teardown_bpf_skel();
+
 	return 0;
 }
 
 int bench_uprobe_baseline(int argc, const char **argv)
 {
-	return bench_uprobe(argc, argv);
+	return bench_uprobe(argc, argv, BENCH_UPROBE__BASELINE);
+}
+
+int bench_uprobe_empty(int argc, const char **argv)
+{
+	return bench_uprobe(argc, argv, BENCH_UPROBE__EMPTY);
 }
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index 09637aee8341..1021680bbc6d 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -105,7 +105,8 @@ static struct bench breakpoint_benchmarks[] = {
 };
 
 static struct bench uprobe_benchmarks[] = {
-	{ "baseline",	"Baseline libc usleep(1000) call",	bench_uprobe_baseline,	},
+	{ "baseline",	"Baseline libc usleep(1000) call",				bench_uprobe_baseline,	},
+	{ "empty",	"Attach empty BPF prog to uprobe on usleep, system wide",	bench_uprobe_empty,	},
 	{ NULL,	NULL, NULL },
 };
 
diff --git a/tools/perf/util/bpf_skel/bench_uprobe.bpf.c b/tools/perf/util/bpf_skel/bench_uprobe.bpf.c
new file mode 100644
index 000000000000..1365dcc5dddf
--- /dev/null
+++ b/tools/perf/util/bpf_skel/bench_uprobe.bpf.c
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+// Copyright (c) 2023 Red Hat
+#include "vmlinux.h"
+#include <bpf/bpf_tracing.h>
+
+SEC("uprobe")
+int BPF_UPROBE(empty)
+{
+       return 0;
+}
+
+char LICENSE[] SEC("license") = "Dual BSD/GPL";

From 7b47623b8cae8149688c11396bb690bed6936f70 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 2 Jun 2023 17:42:47 -0300
Subject: [PATCH 0080/1189] perf bench uprobe trace_printk: Add entry attaching
 an BPF program that does a trace_printk

  [root@five ~]# perf bench uprobe all
  # Running uprobe/baseline benchmark...
  # Executed 1,000 usleep(1000) calls
       Total time: 1,053,963 usecs

   1,053.963 usecs/op

  # Running uprobe/empty benchmark...
  # Executed 1,000 usleep(1000) calls
       Total time: 1,056,293 usecs +2,330 to baseline

   1,056.293 usecs/op 2.330 usecs/op to baseline

  # Running uprobe/trace_printk benchmark...
  # Executed 1,000 usleep(1000) calls
       Total time: 1,056,977 usecs +3,014 to baseline +684 to previous

   1,056.977 usecs/op 3.014 usecs/op to baseline 0.684 usecs/op to previous

  [root@five ~]#

Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andre Fredette <anfredet@redhat.com>
Cc: Clark Williams <williams@redhat.com>
Cc: Dave Tucker <datucker@redhat.com>
Cc: Derek Barbosa <debarbos@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/20230719204910.539044-6-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/bench/bench.h                    |  1 +
 tools/perf/bench/uprobe.c                   | 39 +++++++++++++++------
 tools/perf/builtin-bench.c                  |  1 +
 tools/perf/util/bpf_skel/bench_uprobe.bpf.c | 11 ++++++
 4 files changed, 41 insertions(+), 11 deletions(-)

diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index daf4850b441c..50de4773651f 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -44,6 +44,7 @@ int bench_breakpoint_thread(int argc, const char **argv);
 int bench_breakpoint_enable(int argc, const char **argv);
 int bench_uprobe_baseline(int argc, const char **argv);
 int bench_uprobe_empty(int argc, const char **argv);
+int bench_uprobe_trace_printk(int argc, const char **argv);
 int bench_pmu_scan(int argc, const char **argv);
 
 #define BENCH_FORMAT_DEFAULT_STR	"default"
diff --git a/tools/perf/bench/uprobe.c b/tools/perf/bench/uprobe.c
index dfb90038a4f7..914c0817fe8a 100644
--- a/tools/perf/bench/uprobe.c
+++ b/tools/perf/bench/uprobe.c
@@ -11,6 +11,7 @@
 #include <subcmd/parse-options.h>
 #include "../builtin.h"
 #include "bench.h"
+#include <linux/compiler.h>
 #include <linux/time64.h>
 
 #include <inttypes.h>
@@ -27,6 +28,7 @@ static int loops = LOOPS_DEFAULT;
 enum bench_uprobe {
         BENCH_UPROBE__BASELINE,
         BENCH_UPROBE__EMPTY,
+        BENCH_UPROBE__TRACE_PRINTK,
 };
 
 static const struct option options[] = {
@@ -42,9 +44,21 @@ static const char * const bench_uprobe_usage[] = {
 #ifdef HAVE_BPF_SKEL
 #include "bpf_skel/bench_uprobe.skel.h"
 
+#define bench_uprobe__attach_uprobe(prog) \
+	skel->links.prog = bpf_program__attach_uprobe_opts(/*prog=*/skel->progs.prog, \
+							   /*pid=*/-1, \
+							   /*binary_path=*/"/lib64/libc.so.6", \
+							   /*func_offset=*/0, \
+							   /*opts=*/&uprobe_opts); \
+	if (!skel->links.prog) { \
+		err = -errno; \
+		fprintf(stderr, "Failed to attach bench uprobe \"%s\": %s\n", #prog, strerror(errno)); \
+		goto cleanup; \
+	}
+
 struct bench_uprobe_bpf *skel;
 
-static int bench_uprobe__setup_bpf_skel(void)
+static int bench_uprobe__setup_bpf_skel(enum bench_uprobe bench)
 {
 	DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
 	int err;
@@ -63,14 +77,12 @@ static int bench_uprobe__setup_bpf_skel(void)
 	}
 
 	uprobe_opts.func_name = "usleep";
-	skel->links.empty = bpf_program__attach_uprobe_opts(/*prog=*/skel->progs.empty,
-							    /*pid=*/-1,
-							    /*binary_path=*/"/lib64/libc.so.6",
-							    /*func_offset=*/0,
-							    /*opts=*/&uprobe_opts);
-	if (!skel->links.empty) {
-		err = -errno;
-		fprintf(stderr, "Failed to attach bench uprobe: %s\n", strerror(errno));
+	switch (bench) {
+	case BENCH_UPROBE__BASELINE:							break;
+	case BENCH_UPROBE__EMPTY:	 bench_uprobe__attach_uprobe(empty);		break;
+	case BENCH_UPROBE__TRACE_PRINTK: bench_uprobe__attach_uprobe(trace_printk);	break;
+	default:
+		fprintf(stderr, "Invalid bench: %d\n", bench);
 		goto cleanup;
 	}
 
@@ -88,7 +100,7 @@ static void bench_uprobe__teardown_bpf_skel(void)
 	}
 }
 #else
-static int bench_uprobe__setup_bpf_skel(void) { return 0; }
+static int bench_uprobe__setup_bpf_skel(enum bench_uprobe bench __maybe_unused) { return 0; }
 static void bench_uprobe__teardown_bpf_skel(void) {};
 #endif
 
@@ -135,7 +147,7 @@ static int bench_uprobe(int argc, const char **argv, enum bench_uprobe bench)
 
 	argc = parse_options(argc, argv, options, bench_uprobe_usage, 0);
 
-	if (bench != BENCH_UPROBE__BASELINE && bench_uprobe__setup_bpf_skel() < 0)
+	if (bench != BENCH_UPROBE__BASELINE && bench_uprobe__setup_bpf_skel(bench) < 0)
 		return 0;
 
         clock_gettime(CLOCK_REALTIME, &start);
@@ -179,3 +191,8 @@ int bench_uprobe_empty(int argc, const char **argv)
 {
 	return bench_uprobe(argc, argv, BENCH_UPROBE__EMPTY);
 }
+
+int bench_uprobe_trace_printk(int argc, const char **argv)
+{
+	return bench_uprobe(argc, argv, BENCH_UPROBE__TRACE_PRINTK);
+}
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index 1021680bbc6d..f60ccafccac2 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -107,6 +107,7 @@ static struct bench breakpoint_benchmarks[] = {
 static struct bench uprobe_benchmarks[] = {
 	{ "baseline",	"Baseline libc usleep(1000) call",				bench_uprobe_baseline,	},
 	{ "empty",	"Attach empty BPF prog to uprobe on usleep, system wide",	bench_uprobe_empty,	},
+	{ "trace_printk", "Attach trace_printk BPF prog to uprobe on usleep syswide",	bench_uprobe_trace_printk,	},
 	{ NULL,	NULL, NULL },
 };
 
diff --git a/tools/perf/util/bpf_skel/bench_uprobe.bpf.c b/tools/perf/util/bpf_skel/bench_uprobe.bpf.c
index 1365dcc5dddf..2c55896bb33c 100644
--- a/tools/perf/util/bpf_skel/bench_uprobe.bpf.c
+++ b/tools/perf/util/bpf_skel/bench_uprobe.bpf.c
@@ -3,10 +3,21 @@
 #include "vmlinux.h"
 #include <bpf/bpf_tracing.h>
 
+unsigned int nr_uprobes;
+
 SEC("uprobe")
 int BPF_UPROBE(empty)
 {
        return 0;
 }
 
+SEC("uprobe")
+int BPF_UPROBE(trace_printk)
+{
+	char fmt[] = "perf bench uprobe %u";
+
+	bpf_trace_printk(fmt, sizeof(fmt), ++nr_uprobes);
+	return 0;
+}
+
 char LICENSE[] SEC("license") = "Dual BSD/GPL";

From 681f34d52b9647db68cebc5f957ddfff01fb6ba0 Mon Sep 17 00:00:00 2001
From: Lu Hongfei <luhongfei@vivo.com>
Date: Thu, 6 Jul 2023 17:46:34 +0800
Subject: [PATCH 0081/1189] perf diff: Replaces some ',' as separator with the
 more usual ';'

When wrapping code, use ';' better than using ',' which is more in line
with the coding habits of most engineers.

Signed-off-by: Lu Hongfei <luhongfei@vivo.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: opensource.kernel@vivo.com
Link: https://lore.kernel.org/r/20230706094635.1553-1-luhongfei@vivo.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-diff.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index e8a1b16aa5f8..57d300d8e570 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -1915,8 +1915,8 @@ static int data_init(int argc, const char **argv)
 		struct perf_data *data = &d->data;
 
 		data->path  = use_default ? defaults[i] : argv[i];
-		data->mode  = PERF_DATA_MODE_READ,
-		data->force = force,
+		data->mode  = PERF_DATA_MODE_READ;
+		data->force = force;
 
 		d->idx  = i;
 	}

From 2b6aa9e7927b8e8fe3fd1e0a189d082b0801eacd Mon Sep 17 00:00:00 2001
From: Yangtao Li <frank.li@vivo.com>
Date: Thu, 20 Jul 2023 14:30:36 -0700
Subject: [PATCH 0082/1189] Input: lm8333 - convert to use devm_* api

Use devm_* api to simplify code, this makes it unnecessary to explicitly
release resources.

Signed-off-by: Yangtao Li <frank.li@vivo.com>
Link: https://lore.kernel.org/r/20230714080611.81302-1-frank.li@vivo.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/lm8333.c | 44 +++++++++++----------------------
 1 file changed, 14 insertions(+), 30 deletions(-)

diff --git a/drivers/input/keyboard/lm8333.c b/drivers/input/keyboard/lm8333.c
index c9f05764e36d..1c070c499c85 100644
--- a/drivers/input/keyboard/lm8333.c
+++ b/drivers/input/keyboard/lm8333.c
@@ -142,18 +142,18 @@ static int lm8333_probe(struct i2c_client *client)
 		return -EINVAL;
 	}
 
-	lm8333 = kzalloc(sizeof(*lm8333), GFP_KERNEL);
-	input = input_allocate_device();
-	if (!lm8333 || !input) {
-		err = -ENOMEM;
-		goto free_mem;
-	}
+	lm8333 = devm_kzalloc(&client->dev, sizeof(*lm8333), GFP_KERNEL);
+	if (!lm8333)
+		return -ENOMEM;
+
+	input = devm_input_allocate_device(&client->dev);
+	if (!input)
+		return -ENOMEM;
 
 	lm8333->client = client;
 	lm8333->input = input;
 
 	input->name = client->name;
-	input->dev.parent = &client->dev;
 	input->id.bustype = BUS_I2C;
 
 	input_set_capability(input, EV_MSC, MSC_SCAN);
@@ -162,7 +162,7 @@ static int lm8333_probe(struct i2c_client *client)
 					 LM8333_NUM_ROWS, LM8333_NUM_COLS,
 					 lm8333->keycodes, input);
 	if (err)
-		goto free_mem;
+		return err;
 
 	if (pdata->debounce_time) {
 		err = lm8333_write8(lm8333, LM8333_DEBOUNCE,
@@ -178,34 +178,19 @@ static int lm8333_probe(struct i2c_client *client)
 			dev_warn(&client->dev, "Unable to set active time\n");
 	}
 
-	err = request_threaded_irq(client->irq, NULL, lm8333_irq_thread,
-				   IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
-				   "lm8333", lm8333);
+	err = devm_request_threaded_irq(&client->dev, client->irq,
+					NULL, lm8333_irq_thread,
+					IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
+					"lm8333", lm8333);
 	if (err)
-		goto free_mem;
+		return err;
 
 	err = input_register_device(input);
 	if (err)
-		goto free_irq;
+		return err;
 
 	i2c_set_clientdata(client, lm8333);
 	return 0;
-
- free_irq:
-	free_irq(client->irq, lm8333);
- free_mem:
-	input_free_device(input);
-	kfree(lm8333);
-	return err;
-}
-
-static void lm8333_remove(struct i2c_client *client)
-{
-	struct lm8333 *lm8333 = i2c_get_clientdata(client);
-
-	free_irq(client->irq, lm8333);
-	input_unregister_device(lm8333->input);
-	kfree(lm8333);
 }
 
 static const struct i2c_device_id lm8333_id[] = {
@@ -219,7 +204,6 @@ static struct i2c_driver lm8333_driver = {
 		.name		= "lm8333",
 	},
 	.probe		= lm8333_probe,
-	.remove		= lm8333_remove,
 	.id_table	= lm8333_id,
 };
 module_i2c_driver(lm8333_driver);

From caddca33a0177f452312f1644822bc98384ba58a Mon Sep 17 00:00:00 2001
From: Yangtao Li <frank.li@vivo.com>
Date: Thu, 20 Jul 2023 15:38:03 -0700
Subject: [PATCH 0083/1189] Input: amikbd - convert to use devm_* api

Use devm_* api to simplify code, this makes it unnecessary to explicitly
release resources.

Signed-off-by: Yangtao Li <frank.li@vivo.com>
Link: https://lore.kernel.org/r/20230714080611.81302-2-frank.li@vivo.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/amikbd.c | 25 +++++--------------------
 1 file changed, 5 insertions(+), 20 deletions(-)

diff --git a/drivers/input/keyboard/amikbd.c b/drivers/input/keyboard/amikbd.c
index a20a4e186639..e305c44cd0aa 100644
--- a/drivers/input/keyboard/amikbd.c
+++ b/drivers/input/keyboard/amikbd.c
@@ -196,7 +196,7 @@ static int __init amikbd_probe(struct platform_device *pdev)
 	struct input_dev *dev;
 	int i, err;
 
-	dev = input_allocate_device();
+	dev = devm_input_allocate_device(&pdev->dev);
 	if (!dev) {
 		dev_err(&pdev->dev, "Not enough memory for input device\n");
 		return -ENOMEM;
@@ -208,7 +208,6 @@ static int __init amikbd_probe(struct platform_device *pdev)
 	dev->id.vendor = 0x0001;
 	dev->id.product = 0x0001;
 	dev->id.version = 0x0100;
-	dev->dev.parent = &pdev->dev;
 
 	dev->evbit[0] = BIT_MASK(EV_KEY) | BIT_MASK(EV_REP);
 
@@ -218,35 +217,21 @@ static int __init amikbd_probe(struct platform_device *pdev)
 	amikbd_init_console_keymaps();
 
 	ciaa.cra &= ~0x41;	 /* serial data in, turn off TA */
-	err = request_irq(IRQ_AMIGA_CIAA_SP, amikbd_interrupt, 0, "amikbd",
-			  dev);
+	err = devm_request_irq(&pdev->dev, IRQ_AMIGA_CIAA_SP, amikbd_interrupt,
+			       0, "amikbd", dev);
 	if (err)
-		goto fail2;
+		return err;
 
 	err = input_register_device(dev);
 	if (err)
-		goto fail3;
+		return err;
 
 	platform_set_drvdata(pdev, dev);
 
 	return 0;
-
- fail3:	free_irq(IRQ_AMIGA_CIAA_SP, dev);
- fail2:	input_free_device(dev);
-	return err;
-}
-
-static int __exit amikbd_remove(struct platform_device *pdev)
-{
-	struct input_dev *dev = platform_get_drvdata(pdev);
-
-	free_irq(IRQ_AMIGA_CIAA_SP, dev);
-	input_unregister_device(dev);
-	return 0;
 }
 
 static struct platform_driver amikbd_driver = {
-	.remove = __exit_p(amikbd_remove),
 	.driver   = {
 		.name	= "amiga-keyboard",
 	},

From e175eae16c1bf92062f1f431a95f476a61a77c48 Mon Sep 17 00:00:00 2001
From: Yangtao Li <frank.li@vivo.com>
Date: Thu, 20 Jul 2023 15:41:20 -0700
Subject: [PATCH 0084/1189] Input: mcs-touchkey - convert to use devm_* api

Use devm_* api to simplify code, this makes it unnecessary to explicitly
release resources.

Signed-off-by: Yangtao Li <frank.li@vivo.com>
Link: https://lore.kernel.org/r/20230714080611.81302-3-frank.li@vivo.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/mcs_touchkey.c | 63 ++++++++++++---------------
 1 file changed, 29 insertions(+), 34 deletions(-)

diff --git a/drivers/input/keyboard/mcs_touchkey.c b/drivers/input/keyboard/mcs_touchkey.c
index de312d8eb974..f25e2b20e271 100644
--- a/drivers/input/keyboard/mcs_touchkey.c
+++ b/drivers/input/keyboard/mcs_touchkey.c
@@ -92,6 +92,13 @@ static irqreturn_t mcs_touchkey_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static void mcs_touchkey_poweroff(void *data)
+{
+	struct mcs_touchkey_data *touchkey = data;
+
+	touchkey->poweron(false);
+}
+
 static int mcs_touchkey_probe(struct i2c_client *client)
 {
 	const struct i2c_device_id *id = i2c_client_get_device_id(client);
@@ -109,13 +116,16 @@ static int mcs_touchkey_probe(struct i2c_client *client)
 		return -EINVAL;
 	}
 
-	data = kzalloc(struct_size(data, keycodes, pdata->key_maxval + 1),
-		       GFP_KERNEL);
-	input_dev = input_allocate_device();
-	if (!data || !input_dev) {
-		dev_err(&client->dev, "Failed to allocate memory\n");
-		error = -ENOMEM;
-		goto err_free_mem;
+	data = devm_kzalloc(&client->dev,
+			    struct_size(data, keycodes, pdata->key_maxval + 1),
+			    GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	input_dev = devm_input_allocate_device(&client->dev);
+	if (!input_dev) {
+		dev_err(&client->dev, "Failed to allocate input device\n");
+		return -ENOMEM;
 	}
 
 	data->client = client;
@@ -136,15 +146,13 @@ static int mcs_touchkey_probe(struct i2c_client *client)
 
 	fw_ver = i2c_smbus_read_byte_data(client, fw_reg);
 	if (fw_ver < 0) {
-		error = fw_ver;
 		dev_err(&client->dev, "i2c read error[%d]\n", error);
-		goto err_free_mem;
+		return fw_ver;
 	}
 	dev_info(&client->dev, "Firmware version: %d\n", fw_ver);
 
 	input_dev->name = "MELFAS MCS Touchkey";
 	input_dev->id.bustype = BUS_I2C;
-	input_dev->dev.parent = &client->dev;
 	input_dev->evbit[0] = BIT_MASK(EV_KEY);
 	if (!pdata->no_autorepeat)
 		input_dev->evbit[0] |= BIT_MASK(EV_REP);
@@ -169,40 +177,28 @@ static int mcs_touchkey_probe(struct i2c_client *client)
 	if (pdata->poweron) {
 		data->poweron = pdata->poweron;
 		data->poweron(true);
+
+		error = devm_add_action_or_reset(&client->dev,
+						 mcs_touchkey_poweroff, data);
+		if (error)
+			return error;
 	}
 
-	error = request_threaded_irq(client->irq, NULL, mcs_touchkey_interrupt,
-				     IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
-				     client->dev.driver->name, data);
+	error = devm_request_threaded_irq(&client->dev, client->irq,
+					  NULL, mcs_touchkey_interrupt,
+					  IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
+					  client->dev.driver->name, data);
 	if (error) {
 		dev_err(&client->dev, "Failed to register interrupt\n");
-		goto err_free_mem;
+		return error;
 	}
 
 	error = input_register_device(input_dev);
 	if (error)
-		goto err_free_irq;
+		return error;
 
 	i2c_set_clientdata(client, data);
 	return 0;
-
-err_free_irq:
-	free_irq(client->irq, data);
-err_free_mem:
-	input_free_device(input_dev);
-	kfree(data);
-	return error;
-}
-
-static void mcs_touchkey_remove(struct i2c_client *client)
-{
-	struct mcs_touchkey_data *data = i2c_get_clientdata(client);
-
-	free_irq(client->irq, data);
-	if (data->poweron)
-		data->poweron(false);
-	input_unregister_device(data->input_dev);
-	kfree(data);
 }
 
 static void mcs_touchkey_shutdown(struct i2c_client *client)
@@ -259,7 +255,6 @@ static struct i2c_driver mcs_touchkey_driver = {
 		.pm	= pm_sleep_ptr(&mcs_touchkey_pm_ops),
 	},
 	.probe		= mcs_touchkey_probe,
-	.remove		= mcs_touchkey_remove,
 	.shutdown       = mcs_touchkey_shutdown,
 	.id_table	= mcs_touchkey_id,
 };

From 447c09544275663e1082f796b26c7959915c922a Mon Sep 17 00:00:00 2001
From: Yangtao Li <frank.li@vivo.com>
Date: Thu, 20 Jul 2023 15:51:01 -0700
Subject: [PATCH 0085/1189] Input: qt1070 - convert to use devm_* api

Use devm_* api to simplify code, this makes it unnecessary to explicitly
release resources.

Signed-off-by: Yangtao Li <frank.li@vivo.com>
Link: https://lore.kernel.org/r/20230714080611.81302-5-frank.li@vivo.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/qt1070.c | 46 ++++++++++-----------------------
 1 file changed, 14 insertions(+), 32 deletions(-)

diff --git a/drivers/input/keyboard/qt1070.c b/drivers/input/keyboard/qt1070.c
index 91aaa9fc43a4..9b093b042bf1 100644
--- a/drivers/input/keyboard/qt1070.c
+++ b/drivers/input/keyboard/qt1070.c
@@ -149,20 +149,20 @@ static int qt1070_probe(struct i2c_client *client)
 	if (!qt1070_identify(client))
 		return -ENODEV;
 
-	data = kzalloc(sizeof(struct qt1070_data), GFP_KERNEL);
-	input = input_allocate_device();
-	if (!data || !input) {
-		dev_err(&client->dev, "insufficient memory\n");
-		err = -ENOMEM;
-		goto err_free_mem;
-	}
+	data = devm_kzalloc(&client->dev, sizeof(struct qt1070_data),
+			    GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	input = devm_input_allocate_device(&client->dev);
+	if (!input)
+		return -ENOMEM;
 
 	data->client = client;
 	data->input = input;
 	data->irq = client->irq;
 
 	input->name = "AT42QT1070 QTouch Sensor";
-	input->dev.parent = &client->dev;
 	input->id.bustype = BUS_I2C;
 
 	/* Add the keycode */
@@ -185,19 +185,20 @@ static int qt1070_probe(struct i2c_client *client)
 	qt1070_write(client, RESET, 1);
 	msleep(QT1070_RESET_TIME);
 
-	err = request_threaded_irq(client->irq, NULL, qt1070_interrupt,
-				   IRQF_TRIGGER_NONE | IRQF_ONESHOT,
-				   client->dev.driver->name, data);
+	err = devm_request_threaded_irq(&client->dev, client->irq,
+					NULL, qt1070_interrupt,
+					IRQF_TRIGGER_NONE | IRQF_ONESHOT,
+					client->dev.driver->name, data);
 	if (err) {
 		dev_err(&client->dev, "fail to request irq\n");
-		goto err_free_mem;
+		return err;
 	}
 
 	/* Register the input device */
 	err = input_register_device(data->input);
 	if (err) {
 		dev_err(&client->dev, "Failed to register input device\n");
-		goto err_free_irq;
+		return err;
 	}
 
 	i2c_set_clientdata(client, data);
@@ -206,24 +207,6 @@ static int qt1070_probe(struct i2c_client *client)
 	qt1070_read(client, DET_STATUS);
 
 	return 0;
-
-err_free_irq:
-	free_irq(client->irq, data);
-err_free_mem:
-	input_free_device(input);
-	kfree(data);
-	return err;
-}
-
-static void qt1070_remove(struct i2c_client *client)
-{
-	struct qt1070_data *data = i2c_get_clientdata(client);
-
-	/* Release IRQ */
-	free_irq(client->irq, data);
-
-	input_unregister_device(data->input);
-	kfree(data);
 }
 
 static int qt1070_suspend(struct device *dev)
@@ -272,7 +255,6 @@ static struct i2c_driver qt1070_driver = {
 	},
 	.id_table	= qt1070_id,
 	.probe		= qt1070_probe,
-	.remove		= qt1070_remove,
 };
 
 module_i2c_driver(qt1070_driver);

From aecab554b6ffa9a94ba796031eb39ea20eb60fb3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 14 Jul 2023 22:56:15 +0200
Subject: [PATCH 0086/1189] pwm: atmel-hlcdc: Use consistent variable naming
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In PWM drivers the variable name "chip" is usually only used for struct
pwm_chip pointers. This driver however used "chip" for its driver data
and pwm_chip pointers are named "chip", too, when there is no driver
data around and "c" otherwise. Instead use "atmel" for driver data and
always "chip" for pwm_chips.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Claudiu Beznea <claudiu.beznea@tuxon.dev>
[thierry.reding@gmail.com: replace ddata by atmel]
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-atmel-hlcdc.c | 65 ++++++++++++++++++-----------------
 1 file changed, 33 insertions(+), 32 deletions(-)

diff --git a/drivers/pwm/pwm-atmel-hlcdc.c b/drivers/pwm/pwm-atmel-hlcdc.c
index 96a709a9d49a..4d0b859d0ac1 100644
--- a/drivers/pwm/pwm-atmel-hlcdc.c
+++ b/drivers/pwm/pwm-atmel-hlcdc.c
@@ -38,11 +38,11 @@ static inline struct atmel_hlcdc_pwm *to_atmel_hlcdc_pwm(struct pwm_chip *chip)
 	return container_of(chip, struct atmel_hlcdc_pwm, chip);
 }
 
-static int atmel_hlcdc_pwm_apply(struct pwm_chip *c, struct pwm_device *pwm,
+static int atmel_hlcdc_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 				 const struct pwm_state *state)
 {
-	struct atmel_hlcdc_pwm *chip = to_atmel_hlcdc_pwm(c);
-	struct atmel_hlcdc *hlcdc = chip->hlcdc;
+	struct atmel_hlcdc_pwm *atmel = to_atmel_hlcdc_pwm(chip);
+	struct atmel_hlcdc *hlcdc = atmel->hlcdc;
 	unsigned int status;
 	int ret;
 
@@ -54,7 +54,7 @@ static int atmel_hlcdc_pwm_apply(struct pwm_chip *c, struct pwm_device *pwm,
 		u32 pwmcfg;
 		int pres;
 
-		if (!chip->errata || !chip->errata->slow_clk_erratum) {
+		if (!atmel->errata || !atmel->errata->slow_clk_erratum) {
 			clk_freq = clk_get_rate(new_clk);
 			if (!clk_freq)
 				return -EINVAL;
@@ -64,7 +64,7 @@ static int atmel_hlcdc_pwm_apply(struct pwm_chip *c, struct pwm_device *pwm,
 		}
 
 		/* Errata: cannot use slow clk on some IP revisions */
-		if ((chip->errata && chip->errata->slow_clk_erratum) ||
+		if ((atmel->errata && atmel->errata->slow_clk_erratum) ||
 		    clk_period_ns > state->period) {
 			new_clk = hlcdc->sys_clk;
 			clk_freq = clk_get_rate(new_clk);
@@ -77,8 +77,8 @@ static int atmel_hlcdc_pwm_apply(struct pwm_chip *c, struct pwm_device *pwm,
 
 		for (pres = 0; pres <= ATMEL_HLCDC_PWMPS_MAX; pres++) {
 		/* Errata: cannot divide by 1 on some IP revisions */
-			if (!pres && chip->errata &&
-			    chip->errata->div1_clk_erratum)
+			if (!pres && atmel->errata &&
+			    atmel->errata->div1_clk_erratum)
 				continue;
 
 			if ((clk_period_ns << pres) >= state->period)
@@ -90,7 +90,7 @@ static int atmel_hlcdc_pwm_apply(struct pwm_chip *c, struct pwm_device *pwm,
 
 		pwmcfg = ATMEL_HLCDC_PWMPS(pres);
 
-		if (new_clk != chip->cur_clk) {
+		if (new_clk != atmel->cur_clk) {
 			u32 gencfg = 0;
 			int ret;
 
@@ -98,8 +98,8 @@ static int atmel_hlcdc_pwm_apply(struct pwm_chip *c, struct pwm_device *pwm,
 			if (ret)
 				return ret;
 
-			clk_disable_unprepare(chip->cur_clk);
-			chip->cur_clk = new_clk;
+			clk_disable_unprepare(atmel->cur_clk);
+			atmel->cur_clk = new_clk;
 
 			if (new_clk == hlcdc->sys_clk)
 				gencfg = ATMEL_HLCDC_CLKPWMSEL;
@@ -160,8 +160,8 @@ static int atmel_hlcdc_pwm_apply(struct pwm_chip *c, struct pwm_device *pwm,
 		if (ret)
 			return ret;
 
-		clk_disable_unprepare(chip->cur_clk);
-		chip->cur_clk = NULL;
+		clk_disable_unprepare(atmel->cur_clk);
+		atmel->cur_clk = NULL;
 	}
 
 	return 0;
@@ -183,31 +183,32 @@ static const struct atmel_hlcdc_pwm_errata atmel_hlcdc_pwm_sama5d3_errata = {
 #ifdef CONFIG_PM_SLEEP
 static int atmel_hlcdc_pwm_suspend(struct device *dev)
 {
-	struct atmel_hlcdc_pwm *chip = dev_get_drvdata(dev);
+	struct atmel_hlcdc_pwm *atmel = dev_get_drvdata(dev);
 
 	/* Keep the periph clock enabled if the PWM is still running. */
-	if (pwm_is_enabled(&chip->chip.pwms[0]))
-		clk_disable_unprepare(chip->hlcdc->periph_clk);
+	if (pwm_is_enabled(&atmel->chip.pwms[0]))
+		clk_disable_unprepare(atmel->hlcdc->periph_clk);
 
 	return 0;
 }
 
 static int atmel_hlcdc_pwm_resume(struct device *dev)
 {
-	struct atmel_hlcdc_pwm *chip = dev_get_drvdata(dev);
+	struct atmel_hlcdc_pwm *atmel = dev_get_drvdata(dev);
 	struct pwm_state state;
 	int ret;
 
-	pwm_get_state(&chip->chip.pwms[0], &state);
+	pwm_get_state(&atmel->chip.pwms[0], &state);
 
 	/* Re-enable the periph clock it was stopped during suspend. */
 	if (!state.enabled) {
-		ret = clk_prepare_enable(chip->hlcdc->periph_clk);
+		ret = clk_prepare_enable(atmel->hlcdc->periph_clk);
 		if (ret)
 			return ret;
 	}
 
-	return atmel_hlcdc_pwm_apply(&chip->chip, &chip->chip.pwms[0], &state);
+	return atmel_hlcdc_pwm_apply(&atmel->chip, &atmel->chip.pwms[0],
+				     &state);
 }
 #endif
 
@@ -244,14 +245,14 @@ static int atmel_hlcdc_pwm_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *match;
 	struct device *dev = &pdev->dev;
-	struct atmel_hlcdc_pwm *chip;
+	struct atmel_hlcdc_pwm *atmel;
 	struct atmel_hlcdc *hlcdc;
 	int ret;
 
 	hlcdc = dev_get_drvdata(dev->parent);
 
-	chip = devm_kzalloc(dev, sizeof(*chip), GFP_KERNEL);
-	if (!chip)
+	atmel = devm_kzalloc(dev, sizeof(*atmel), GFP_KERNEL);
+	if (!atmel)
 		return -ENOMEM;
 
 	ret = clk_prepare_enable(hlcdc->periph_clk);
@@ -260,31 +261,31 @@ static int atmel_hlcdc_pwm_probe(struct platform_device *pdev)
 
 	match = of_match_node(atmel_hlcdc_dt_ids, dev->parent->of_node);
 	if (match)
-		chip->errata = match->data;
+		atmel->errata = match->data;
 
-	chip->hlcdc = hlcdc;
-	chip->chip.ops = &atmel_hlcdc_pwm_ops;
-	chip->chip.dev = dev;
-	chip->chip.npwm = 1;
+	atmel->hlcdc = hlcdc;
+	atmel->chip.ops = &atmel_hlcdc_pwm_ops;
+	atmel->chip.dev = dev;
+	atmel->chip.npwm = 1;
 
-	ret = pwmchip_add(&chip->chip);
+	ret = pwmchip_add(&atmel->chip);
 	if (ret) {
 		clk_disable_unprepare(hlcdc->periph_clk);
 		return ret;
 	}
 
-	platform_set_drvdata(pdev, chip);
+	platform_set_drvdata(pdev, atmel);
 
 	return 0;
 }
 
 static void atmel_hlcdc_pwm_remove(struct platform_device *pdev)
 {
-	struct atmel_hlcdc_pwm *chip = platform_get_drvdata(pdev);
+	struct atmel_hlcdc_pwm *atmel = platform_get_drvdata(pdev);
 
-	pwmchip_remove(&chip->chip);
+	pwmchip_remove(&atmel->chip);
 
-	clk_disable_unprepare(chip->hlcdc->periph_clk);
+	clk_disable_unprepare(atmel->hlcdc->periph_clk);
 }
 
 static const struct of_device_id atmel_hlcdc_pwm_dt_ids[] = {

From 51352c09eafdc53a8d5022ff00a69d1bf262a097 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 14 Jul 2023 22:56:16 +0200
Subject: [PATCH 0087/1189] pwm: bcm-kona: Consistently name pwm_chip variables
 "chip"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Most variables holding a pointer to a pwm_chip are called "chip" which
is also the usual name in most other PWM drivers. Rename the single
variable that have a different name to be called "chip", too, for
consistency.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-bcm-kona.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pwm/pwm-bcm-kona.c b/drivers/pwm/pwm-bcm-kona.c
index 4fa6e249e4cf..e5b00cc9f7a7 100644
--- a/drivers/pwm/pwm-bcm-kona.c
+++ b/drivers/pwm/pwm-bcm-kona.c
@@ -61,9 +61,9 @@ struct kona_pwmc {
 	struct clk *clk;
 };
 
-static inline struct kona_pwmc *to_kona_pwmc(struct pwm_chip *_chip)
+static inline struct kona_pwmc *to_kona_pwmc(struct pwm_chip *chip)
 {
-	return container_of(_chip, struct kona_pwmc, chip);
+	return container_of(chip, struct kona_pwmc, chip);
 }
 
 /*

From 92f2de28288bacc1455e64c957b16d7e2f721d3e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 14 Jul 2023 22:56:17 +0200
Subject: [PATCH 0088/1189] pwm: crc: Consistently name pwm_chip variables
 "chip"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Most variables holding a pointer to a pwm_chip are called "chip" which
is also the usual name in most other PWM drivers. Rename the single
variable that have a different name to be called "chip", too, for
consistency.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-crc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pwm/pwm-crc.c b/drivers/pwm/pwm-crc.c
index 4703b4a0b6e4..b9f063dc6b5f 100644
--- a/drivers/pwm/pwm-crc.c
+++ b/drivers/pwm/pwm-crc.c
@@ -34,9 +34,9 @@ struct crystalcove_pwm {
 	struct regmap *regmap;
 };
 
-static inline struct crystalcove_pwm *to_crc_pwm(struct pwm_chip *pc)
+static inline struct crystalcove_pwm *to_crc_pwm(struct pwm_chip *chip)
 {
-	return container_of(pc, struct crystalcove_pwm, chip);
+	return container_of(chip, struct crystalcove_pwm, chip);
 }
 
 static int crc_pwm_calc_clk_div(int period_ns)

From 5996cdf132dad91db596d0bdacf137cbde68dc3c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 14 Jul 2023 22:56:18 +0200
Subject: [PATCH 0089/1189] pwm: cros-ec: Consistently name pwm_chip variables
 "chip"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Most variables holding a pointer to a pwm_chip are called "chip" which
is also the usual name in most other PWM drivers. Rename the two
variables that have a different name to be called "chip", too, for
consistency.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Tzung-Bi Shih <tzungbi@kernel.org>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-cros-ec.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/pwm/pwm-cros-ec.c b/drivers/pwm/pwm-cros-ec.c
index 74e863aa1d8d..154ca0f90847 100644
--- a/drivers/pwm/pwm-cros-ec.c
+++ b/drivers/pwm/pwm-cros-ec.c
@@ -37,9 +37,9 @@ struct cros_ec_pwm {
 	u16 duty_cycle;
 };
 
-static inline struct cros_ec_pwm_device *pwm_to_cros_ec_pwm(struct pwm_chip *c)
+static inline struct cros_ec_pwm_device *pwm_to_cros_ec_pwm(struct pwm_chip *chip)
 {
-	return container_of(c, struct cros_ec_pwm_device, chip);
+	return container_of(chip, struct cros_ec_pwm_device, chip);
 }
 
 static int cros_ec_pwm_request(struct pwm_chip *chip, struct pwm_device *pwm)
@@ -218,14 +218,14 @@ static int cros_ec_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm,
 }
 
 static struct pwm_device *
-cros_ec_pwm_xlate(struct pwm_chip *pc, const struct of_phandle_args *args)
+cros_ec_pwm_xlate(struct pwm_chip *chip, const struct of_phandle_args *args)
 {
 	struct pwm_device *pwm;
 
-	if (args->args[0] >= pc->npwm)
+	if (args->args[0] >= chip->npwm)
 		return ERR_PTR(-EINVAL);
 
-	pwm = pwm_request_from_chip(pc, args->args[0], NULL);
+	pwm = pwm_request_from_chip(chip, args->args[0], NULL);
 	if (IS_ERR(pwm))
 		return pwm;
 

From 1425c40189ebbcfbf59df7fcbe0e6f4716bc1dcc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 14 Jul 2023 22:56:19 +0200
Subject: [PATCH 0090/1189] pwm: lp3943: Consistently name pwm_chip variables
 "chip"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Most variables holding a pointer to a pwm_chip are called "chip" which
is also the usual name in most other PWM drivers. Rename the single
variable that have a different name to be called "chip", too, for
consistency.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-lp3943.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pwm/pwm-lp3943.c b/drivers/pwm/pwm-lp3943.c
index 35675e4058c6..a39411b87e19 100644
--- a/drivers/pwm/pwm-lp3943.c
+++ b/drivers/pwm/pwm-lp3943.c
@@ -24,9 +24,9 @@ struct lp3943_pwm {
 	struct lp3943_platform_data *pdata;
 };
 
-static inline struct lp3943_pwm *to_lp3943_pwm(struct pwm_chip *_chip)
+static inline struct lp3943_pwm *to_lp3943_pwm(struct pwm_chip *chip)
 {
-	return container_of(_chip, struct lp3943_pwm, chip);
+	return container_of(chip, struct lp3943_pwm, chip);
 }
 
 static struct lp3943_pwm_map *

From 454a8f5967df2f41046011bbb1912d2febc66d12 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 14 Jul 2023 22:56:20 +0200
Subject: [PATCH 0091/1189] pwm: rockchip: Consistently name pwm_chip variables
 "chip"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Most variables holding a pointer to a pwm_chip are called "chip" which
is also the usual name in most other PWM drivers. Rename the single
variable that have a different name to be called "chip", too, for
consistency.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-rockchip.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pwm/pwm-rockchip.c b/drivers/pwm/pwm-rockchip.c
index c1a1f2d864b5..03ee18fb82d5 100644
--- a/drivers/pwm/pwm-rockchip.c
+++ b/drivers/pwm/pwm-rockchip.c
@@ -52,9 +52,9 @@ struct rockchip_pwm_data {
 	u32 enable_conf;
 };
 
-static inline struct rockchip_pwm_chip *to_rockchip_pwm_chip(struct pwm_chip *c)
+static inline struct rockchip_pwm_chip *to_rockchip_pwm_chip(struct pwm_chip *chip)
 {
-	return container_of(c, struct rockchip_pwm_chip, chip);
+	return container_of(chip, struct rockchip_pwm_chip, chip);
 }
 
 static int rockchip_pwm_get_state(struct pwm_chip *chip,

From daf3facb9373fe4d6a06f65e834becb16d40de7e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 14 Jul 2023 22:56:21 +0200
Subject: [PATCH 0092/1189] pwm: sifive: Consistently name pwm_chip variables
 "chip"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Most variables holding a pointer to a pwm_chip are called "chip" which
is also the usual name in most other PWM drivers. Rename the single
variable that have a different name to be called "chip", too, for
consistency.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-sifive.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pwm/pwm-sifive.c b/drivers/pwm/pwm-sifive.c
index ae49d67ab2b1..25b9b7d9476a 100644
--- a/drivers/pwm/pwm-sifive.c
+++ b/drivers/pwm/pwm-sifive.c
@@ -51,9 +51,9 @@ struct pwm_sifive_ddata {
 };
 
 static inline
-struct pwm_sifive_ddata *pwm_sifive_chip_to_ddata(struct pwm_chip *c)
+struct pwm_sifive_ddata *pwm_sifive_chip_to_ddata(struct pwm_chip *chip)
 {
-	return container_of(c, struct pwm_sifive_ddata, chip);
+	return container_of(chip, struct pwm_sifive_ddata, chip);
 }
 
 static int pwm_sifive_request(struct pwm_chip *chip, struct pwm_device *pwm)

From bc83fe5cecf55f299e1c44061bfcabd1fc2a337b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 14 Jul 2023 22:56:22 +0200
Subject: [PATCH 0093/1189] pwm: sl28cpld: Consistently name pwm_chip variables
 "chip"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Nearly all PWM drivers use the name "chip" for the member in the driver
struct pointing to the pwm_chip. Also all local variables and function
parameters with this type use this name. Rename the struct pwm_chip
member accordingly for consistency.

Also rename the parameter of the macro sl28cpld_pwm_from_chip to "chip".

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-sl28cpld.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/pwm/pwm-sl28cpld.c b/drivers/pwm/pwm-sl28cpld.c
index e64900ad4ba1..c789e934671e 100644
--- a/drivers/pwm/pwm-sl28cpld.c
+++ b/drivers/pwm/pwm-sl28cpld.c
@@ -80,12 +80,15 @@
 	regmap_write((priv)->regmap, (priv)->offset + (reg), (val))
 
 struct sl28cpld_pwm {
-	struct pwm_chip pwm_chip;
+	struct pwm_chip chip;
 	struct regmap *regmap;
 	u32 offset;
 };
-#define sl28cpld_pwm_from_chip(_chip) \
-	container_of(_chip, struct sl28cpld_pwm, pwm_chip)
+
+static inline struct sl28cpld_pwm *sl28cpld_pwm_from_chip(struct pwm_chip *chip)
+{
+	return container_of(chip, struct sl28cpld_pwm, chip);
+}
 
 static int sl28cpld_pwm_get_state(struct pwm_chip *chip,
 				  struct pwm_device *pwm,
@@ -228,12 +231,12 @@ static int sl28cpld_pwm_probe(struct platform_device *pdev)
 	}
 
 	/* Initialize the pwm_chip structure */
-	chip = &priv->pwm_chip;
+	chip = &priv->chip;
 	chip->dev = &pdev->dev;
 	chip->ops = &sl28cpld_pwm_ops;
 	chip->npwm = 1;
 
-	ret = devm_pwmchip_add(&pdev->dev, &priv->pwm_chip);
+	ret = devm_pwmchip_add(&pdev->dev, chip);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to add PWM chip (%pe)",
 			ERR_PTR(ret));

From 16636297f5440117e8aa16cdd1f54b5874f6a3a9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 14 Jul 2023 22:56:23 +0200
Subject: [PATCH 0094/1189] staging: greybus: pwm: Consistently name pwm_chip
 variables "chip"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

All function parameters of type pointer to struct pwm_chip in this
driver are called chip which is also the usual name of function
parameters and local variables in most other PWM drivers. For
consistency use the same name for the local variable of that type.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Alex Elder <elder@linaro.org>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/staging/greybus/pwm.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/staging/greybus/pwm.c b/drivers/staging/greybus/pwm.c
index 88da1d796f13..c483e1f0738e 100644
--- a/drivers/staging/greybus/pwm.c
+++ b/drivers/staging/greybus/pwm.c
@@ -267,7 +267,7 @@ static int gb_pwm_probe(struct gbphy_device *gbphy_dev,
 {
 	struct gb_connection *connection;
 	struct gb_pwm_chip *pwmc;
-	struct pwm_chip *pwm;
+	struct pwm_chip *chip;
 	int ret;
 
 	pwmc = kzalloc(sizeof(*pwmc), GFP_KERNEL);
@@ -295,13 +295,13 @@ static int gb_pwm_probe(struct gbphy_device *gbphy_dev,
 	if (ret)
 		goto exit_connection_disable;
 
-	pwm = &pwmc->chip;
+	chip = &pwmc->chip;
 
-	pwm->dev = &gbphy_dev->dev;
-	pwm->ops = &gb_pwm_ops;
-	pwm->npwm = pwmc->pwm_max + 1;
+	chip->dev = &gbphy_dev->dev;
+	chip->ops = &gb_pwm_ops;
+	chip->npwm = pwmc->pwm_max + 1;
 
-	ret = pwmchip_add(pwm);
+	ret = pwmchip_add(chip);
 	if (ret) {
 		dev_err(&gbphy_dev->dev,
 			"failed to register PWM: %d\n", ret);

From 0a41b0c5d97a3758ad102cec469aaa79c7d406b7 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Fri, 14 Jul 2023 11:48:50 -0600
Subject: [PATCH 0095/1189] pwm: Explicitly include correct DT includes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The DT of_device.h and of_platform.h date back to the separate
of_platform_bus_type before it as merged into the regular platform bus.
As part of that merge prepping Arm DT support 13 years ago, they
"temporarily" include each other. They also include platform_device.h
and of.h. As a result, there's a pretty much random mix of those include
files used throughout the tree. In order to detangle these headers and
replace the implicit includes with struct declarations, users need to
explicitly include the correct includes.

Signed-off-by: Rob Herring <robh@kernel.org>
Reviewed-by: Nobuhiro Iwamatsu <nobuhiro1.iwamatsu@toshiba.co.jp>
Acked-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Tzung-Bi Shih <tzungbi@kernel.org>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/core.c               | 1 +
 drivers/pwm/pwm-apple.c          | 1 +
 drivers/pwm/pwm-atmel-hlcdc.c    | 1 +
 drivers/pwm/pwm-atmel-tcb.c      | 3 +--
 drivers/pwm/pwm-atmel.c          | 1 -
 drivers/pwm/pwm-berlin.c         | 1 +
 drivers/pwm/pwm-cros-ec.c        | 1 +
 drivers/pwm/pwm-fsl-ftm.c        | 3 +--
 drivers/pwm/pwm-hibvt.c          | 2 +-
 drivers/pwm/pwm-imx1.c           | 1 -
 drivers/pwm/pwm-jz4740.c         | 2 +-
 drivers/pwm/pwm-lp3943.c         | 1 +
 drivers/pwm/pwm-lpc18xx-sct.c    | 1 +
 drivers/pwm/pwm-mediatek.c       | 1 -
 drivers/pwm/pwm-meson.c          | 1 -
 drivers/pwm/pwm-microchip-core.c | 2 +-
 drivers/pwm/pwm-mtk-disp.c       | 1 -
 drivers/pwm/pwm-pxa.c            | 1 +
 drivers/pwm/pwm-sifive.c         | 1 +
 drivers/pwm/pwm-sl28cpld.c       | 1 +
 drivers/pwm/pwm-sprd.c           | 1 +
 drivers/pwm/pwm-sun4i.c          | 1 -
 drivers/pwm/pwm-sunplus.c        | 1 +
 drivers/pwm/pwm-tegra.c          | 1 -
 drivers/pwm/pwm-tiecap.c         | 2 +-
 drivers/pwm/pwm-tiehrpwm.c       | 2 +-
 drivers/pwm/pwm-visconti.c       | 2 +-
 drivers/pwm/pwm-vt8500.c         | 5 +----
 28 files changed, 21 insertions(+), 21 deletions(-)

diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index 8c798753c016..11f2f1fd0846 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -8,6 +8,7 @@
 
 #include <linux/acpi.h>
 #include <linux/module.h>
+#include <linux/of.h>
 #include <linux/pwm.h>
 #include <linux/radix-tree.h>
 #include <linux/list.h>
diff --git a/drivers/pwm/pwm-apple.c b/drivers/pwm/pwm-apple.c
index a38a62edd713..8e7d67fb5fbe 100644
--- a/drivers/pwm/pwm-apple.c
+++ b/drivers/pwm/pwm-apple.c
@@ -12,6 +12,7 @@
  * - When APPLE_PWM_CTRL is set to 0, the output is constant low
  */
 
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/pwm.h>
diff --git a/drivers/pwm/pwm-atmel-hlcdc.c b/drivers/pwm/pwm-atmel-hlcdc.c
index 4d0b859d0ac1..e271d920151e 100644
--- a/drivers/pwm/pwm-atmel-hlcdc.c
+++ b/drivers/pwm/pwm-atmel-hlcdc.c
@@ -10,6 +10,7 @@
 #include <linux/delay.h>
 #include <linux/mfd/atmel-hlcdc.h>
 #include <linux/module.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/pwm.h>
 #include <linux/regmap.h>
diff --git a/drivers/pwm/pwm-atmel-tcb.c b/drivers/pwm/pwm-atmel-tcb.c
index 4a116dc44f6e..563162d660d8 100644
--- a/drivers/pwm/pwm-atmel-tcb.c
+++ b/drivers/pwm/pwm-atmel-tcb.c
@@ -19,8 +19,7 @@
 #include <linux/mfd/syscon.h>
 #include <linux/platform_device.h>
 #include <linux/pwm.h>
-#include <linux/of_device.h>
-#include <linux/of_irq.h>
+#include <linux/of.h>
 #include <linux/regmap.h>
 #include <linux/slab.h>
 #include <soc/at91/atmel_tcb.h>
diff --git a/drivers/pwm/pwm-atmel.c b/drivers/pwm/pwm-atmel.c
index 5f7d286871cf..4b243c0e8490 100644
--- a/drivers/pwm/pwm-atmel.c
+++ b/drivers/pwm/pwm-atmel.c
@@ -25,7 +25,6 @@
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/pwm.h>
 #include <linux/slab.h>
diff --git a/drivers/pwm/pwm-berlin.c b/drivers/pwm/pwm-berlin.c
index 0c5992a046b2..0971c666afd1 100644
--- a/drivers/pwm/pwm-berlin.c
+++ b/drivers/pwm/pwm-berlin.c
@@ -13,6 +13,7 @@
 #include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/pwm.h>
diff --git a/drivers/pwm/pwm-cros-ec.c b/drivers/pwm/pwm-cros-ec.c
index 154ca0f90847..baaac0c33aa0 100644
--- a/drivers/pwm/pwm-cros-ec.c
+++ b/drivers/pwm/pwm-cros-ec.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/of.h>
 #include <linux/platform_data/cros_ec_commands.h>
 #include <linux/platform_data/cros_ec_proto.h>
 #include <linux/platform_device.h>
diff --git a/drivers/pwm/pwm-fsl-ftm.c b/drivers/pwm/pwm-fsl-ftm.c
index 5caadbd6194e..b7c6045c5d08 100644
--- a/drivers/pwm/pwm-fsl-ftm.c
+++ b/drivers/pwm/pwm-fsl-ftm.c
@@ -11,8 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
-#include <linux/of_address.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/pm.h>
 #include <linux/pwm.h>
diff --git a/drivers/pwm/pwm-hibvt.c b/drivers/pwm/pwm-hibvt.c
index b95df1a96127..f7ba6fe9a349 100644
--- a/drivers/pwm/pwm-hibvt.c
+++ b/drivers/pwm/pwm-hibvt.c
@@ -10,7 +10,7 @@
 #include <linux/delay.h>
 #include <linux/io.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/pwm.h>
 #include <linux/reset.h>
diff --git a/drivers/pwm/pwm-imx1.c b/drivers/pwm/pwm-imx1.c
index 1f2eb1c8ff6c..0651983bed19 100644
--- a/drivers/pwm/pwm-imx1.c
+++ b/drivers/pwm/pwm-imx1.c
@@ -14,7 +14,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/pwm.h>
 #include <linux/slab.h>
diff --git a/drivers/pwm/pwm-jz4740.c b/drivers/pwm/pwm-jz4740.c
index 3b7067f6cd0d..ef1293f2a897 100644
--- a/drivers/pwm/pwm-jz4740.c
+++ b/drivers/pwm/pwm-jz4740.c
@@ -15,7 +15,7 @@
 #include <linux/mfd/ingenic-tcu.h>
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/pwm.h>
 #include <linux/regmap.h>
diff --git a/drivers/pwm/pwm-lp3943.c b/drivers/pwm/pwm-lp3943.c
index a39411b87e19..4b133a17f4be 100644
--- a/drivers/pwm/pwm-lp3943.c
+++ b/drivers/pwm/pwm-lp3943.c
@@ -10,6 +10,7 @@
 #include <linux/err.h>
 #include <linux/mfd/lp3943.h>
 #include <linux/module.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/pwm.h>
 #include <linux/slab.h>
diff --git a/drivers/pwm/pwm-lpc18xx-sct.c b/drivers/pwm/pwm-lpc18xx-sct.c
index b9bf5b366f4b..9ff6311bd472 100644
--- a/drivers/pwm/pwm-lpc18xx-sct.c
+++ b/drivers/pwm/pwm-lpc18xx-sct.c
@@ -22,6 +22,7 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/io.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/pwm.h>
diff --git a/drivers/pwm/pwm-mediatek.c b/drivers/pwm/pwm-mediatek.c
index 7a51d210a877..6adb0ed01906 100644
--- a/drivers/pwm/pwm-mediatek.c
+++ b/drivers/pwm/pwm-mediatek.c
@@ -14,7 +14,6 @@
 #include <linux/module.h>
 #include <linux/clk.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/pwm.h>
 #include <linux/slab.h>
diff --git a/drivers/pwm/pwm-meson.c b/drivers/pwm/pwm-meson.c
index 22f54db3ae8e..25519cddc2a9 100644
--- a/drivers/pwm/pwm-meson.c
+++ b/drivers/pwm/pwm-meson.c
@@ -37,7 +37,6 @@
 #include <linux/math64.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/pwm.h>
 #include <linux/slab.h>
diff --git a/drivers/pwm/pwm-microchip-core.c b/drivers/pwm/pwm-microchip-core.c
index 8750b57684a9..e7525c98105e 100644
--- a/drivers/pwm/pwm-microchip-core.c
+++ b/drivers/pwm/pwm-microchip-core.c
@@ -37,7 +37,7 @@
 #include <linux/math.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/pwm.h>
 
diff --git a/drivers/pwm/pwm-mtk-disp.c b/drivers/pwm/pwm-mtk-disp.c
index 2401b6733241..a83bd6e18b07 100644
--- a/drivers/pwm/pwm-mtk-disp.c
+++ b/drivers/pwm/pwm-mtk-disp.c
@@ -11,7 +11,6 @@
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/pwm.h>
 #include <linux/slab.h>
diff --git a/drivers/pwm/pwm-pxa.c b/drivers/pwm/pwm-pxa.c
index 762429d5647f..c8314053bcb0 100644
--- a/drivers/pwm/pwm-pxa.c
+++ b/drivers/pwm/pwm-pxa.c
@@ -15,6 +15,7 @@
  *   input clock (PWMCR_SD is set) and the output is driven to inactive.
  */
 
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
diff --git a/drivers/pwm/pwm-sifive.c b/drivers/pwm/pwm-sifive.c
index 25b9b7d9476a..eabddb7c7820 100644
--- a/drivers/pwm/pwm-sifive.c
+++ b/drivers/pwm/pwm-sifive.c
@@ -13,6 +13,7 @@
  */
 #include <linux/clk.h>
 #include <linux/io.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/pwm.h>
diff --git a/drivers/pwm/pwm-sl28cpld.c b/drivers/pwm/pwm-sl28cpld.c
index c789e934671e..9e42e3a74ad6 100644
--- a/drivers/pwm/pwm-sl28cpld.c
+++ b/drivers/pwm/pwm-sl28cpld.c
@@ -38,6 +38,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/pwm.h>
 #include <linux/regmap.h>
 
diff --git a/drivers/pwm/pwm-sprd.c b/drivers/pwm/pwm-sprd.c
index d43a6fa3f4e0..1499c8c1fe37 100644
--- a/drivers/pwm/pwm-sprd.c
+++ b/drivers/pwm/pwm-sprd.c
@@ -7,6 +7,7 @@
 #include <linux/err.h>
 #include <linux/io.h>
 #include <linux/math64.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/pwm.h>
diff --git a/drivers/pwm/pwm-sun4i.c b/drivers/pwm/pwm-sun4i.c
index a8790a8fc53e..c84fcf1a13dc 100644
--- a/drivers/pwm/pwm-sun4i.c
+++ b/drivers/pwm/pwm-sun4i.c
@@ -17,7 +17,6 @@
 #include <linux/jiffies.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/pwm.h>
 #include <linux/reset.h>
diff --git a/drivers/pwm/pwm-sunplus.c b/drivers/pwm/pwm-sunplus.c
index d6ebe9f03b35..7705c7b86c3a 100644
--- a/drivers/pwm/pwm-sunplus.c
+++ b/drivers/pwm/pwm-sunplus.c
@@ -23,6 +23,7 @@
 #include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/pwm.h>
diff --git a/drivers/pwm/pwm-tegra.c b/drivers/pwm/pwm-tegra.c
index 5810abf66e2a..a169a34e0778 100644
--- a/drivers/pwm/pwm-tegra.c
+++ b/drivers/pwm/pwm-tegra.c
@@ -41,7 +41,6 @@
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/pm_opp.h>
 #include <linux/pwm.h>
 #include <linux/platform_device.h>
diff --git a/drivers/pwm/pwm-tiecap.c b/drivers/pwm/pwm-tiecap.c
index 109449956307..8c94b266c1b2 100644
--- a/drivers/pwm/pwm-tiecap.c
+++ b/drivers/pwm/pwm-tiecap.c
@@ -12,7 +12,7 @@
 #include <linux/clk.h>
 #include <linux/pm_runtime.h>
 #include <linux/pwm.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 
 /* ECAP registers and bits definitions */
 #define CAP1			0x08
diff --git a/drivers/pwm/pwm-tiehrpwm.c b/drivers/pwm/pwm-tiehrpwm.c
index bb3959ace6b4..ecbfd7e954ec 100644
--- a/drivers/pwm/pwm-tiehrpwm.c
+++ b/drivers/pwm/pwm-tiehrpwm.c
@@ -12,7 +12,7 @@
 #include <linux/err.h>
 #include <linux/clk.h>
 #include <linux/pm_runtime.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 
 /* EHRPWM registers and bits definitions */
 
diff --git a/drivers/pwm/pwm-visconti.c b/drivers/pwm/pwm-visconti.c
index e3fb79b3e2a7..7f7591a2384c 100644
--- a/drivers/pwm/pwm-visconti.c
+++ b/drivers/pwm/pwm-visconti.c
@@ -21,7 +21,7 @@
 #include <linux/err.h>
 #include <linux/io.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/pwm.h>
 
diff --git a/drivers/pwm/pwm-vt8500.c b/drivers/pwm/pwm-vt8500.c
index d2c48fd98706..6d46db51daac 100644
--- a/drivers/pwm/pwm-vt8500.c
+++ b/drivers/pwm/pwm-vt8500.c
@@ -6,6 +6,7 @@
  * Copyright (C) 2010 Alexey Charkov <alchark@gmail.com>
  */
 
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
@@ -18,10 +19,6 @@
 
 #include <asm/div64.h>
 
-#include <linux/of.h>
-#include <linux/of_device.h>
-#include <linux/of_address.h>
-
 /*
  * SoC architecture allocates register space for 4 PWMs but only
  * 2 are currently implemented.

From a2f68c7e312f94c8f78740449a88e8d7308ab18d Mon Sep 17 00:00:00 2001
From: Guiting Shen <aarongt.shen@gmail.com>
Date: Sun, 16 Jul 2023 10:06:52 +0800
Subject: [PATCH 0096/1189] pwm: atmel: Enable clk when pwm already enabled in
 bootloader

The driver would never call clk_enable() if the PWM channel was already
enabled in bootloader which lead to dump the warning message "the PWM
clock already disabled" when turning off the PWM channel.

Add atmel_pwm_enable_clk_if_on() in probe function to enable clock if
the PWM channel was already enabled in bootloader.

Signed-off-by: Guiting Shen <aarongt.shen@gmail.com>
Reviewed-by: Claudiu Beznea <claudiu.beznea@tuxon.dev>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-atmel.c | 47 +++++++++++++++++++++++++++++++++++++++--
 1 file changed, 45 insertions(+), 2 deletions(-)

diff --git a/drivers/pwm/pwm-atmel.c b/drivers/pwm/pwm-atmel.c
index 4b243c0e8490..03c7810416b8 100644
--- a/drivers/pwm/pwm-atmel.c
+++ b/drivers/pwm/pwm-atmel.c
@@ -35,7 +35,7 @@
 #define PWM_SR			0x0C
 #define PWM_ISR			0x1C
 /* Bit field in SR */
-#define PWM_SR_ALL_CH_ON	0x0F
+#define PWM_SR_ALL_CH_MASK	0x0F
 
 /* The following register is PWM channel related registers */
 #define PWM_CH_REG_OFFSET	0x200
@@ -463,6 +463,42 @@ static const struct of_device_id atmel_pwm_dt_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, atmel_pwm_dt_ids);
 
+static int atmel_pwm_enable_clk_if_on(struct atmel_pwm_chip *atmel_pwm, bool on)
+{
+	unsigned int i, cnt = 0;
+	unsigned long sr;
+	int ret = 0;
+
+	sr = atmel_pwm_readl(atmel_pwm, PWM_SR) & PWM_SR_ALL_CH_MASK;
+	if (!sr)
+		return 0;
+
+	cnt = bitmap_weight(&sr, atmel_pwm->chip.npwm);
+
+	if (!on)
+		goto disable_clk;
+
+	for (i = 0; i < cnt; i++) {
+		ret = clk_enable(atmel_pwm->clk);
+		if (ret) {
+			dev_err(atmel_pwm->chip.dev,
+				"failed to enable clock for pwm %pe\n",
+				ERR_PTR(ret));
+
+			cnt = i;
+			goto disable_clk;
+		}
+	}
+
+	return 0;
+
+disable_clk:
+	while (cnt--)
+		clk_disable(atmel_pwm->clk);
+
+	return ret;
+}
+
 static int atmel_pwm_probe(struct platform_device *pdev)
 {
 	struct atmel_pwm_chip *atmel_pwm;
@@ -495,16 +531,23 @@ static int atmel_pwm_probe(struct platform_device *pdev)
 	atmel_pwm->chip.ops = &atmel_pwm_ops;
 	atmel_pwm->chip.npwm = 4;
 
+	ret = atmel_pwm_enable_clk_if_on(atmel_pwm, true);
+	if (ret < 0)
+		goto unprepare_clk;
+
 	ret = pwmchip_add(&atmel_pwm->chip);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to add PWM chip %d\n", ret);
-		goto unprepare_clk;
+		goto disable_clk;
 	}
 
 	platform_set_drvdata(pdev, atmel_pwm);
 
 	return ret;
 
+disable_clk:
+	atmel_pwm_enable_clk_if_on(atmel_pwm, false);
+
 unprepare_clk:
 	clk_unprepare(atmel_pwm->clk);
 	return ret;

From 91f88a0ac8bce5f385ef8c1a6766fce04f7f0043 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 24 Jul 2023 13:12:44 -0700
Subject: [PATCH 0097/1189] perf stat: Avoid uninitialized use of
 perf_stat_config

perf_event__read_stat_config will assign values based on number of
tags and tag values. Initialize the structs to zero before they are
assigned so that no uninitialized values can be seen.

This potential error was reported by GCC with LTO enabled.

Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Carsten Haitzler <carsten.haitzler@arm.com>
Cc: Fangrui Song <maskray@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Tom Rix <trix@redhat.com>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: bpf@vger.kernel.org
Cc: llvm@lists.linux.dev
Link: https://lore.kernel.org/r/20230724201247.748146-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/stat.c | 2 +-
 tools/perf/util/stat.c  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/tests/stat.c b/tools/perf/tests/stat.c
index 500974040fe3..706780fb5695 100644
--- a/tools/perf/tests/stat.c
+++ b/tools/perf/tests/stat.c
@@ -27,7 +27,7 @@ static int process_stat_config_event(struct perf_tool *tool __maybe_unused,
 				     struct machine *machine __maybe_unused)
 {
 	struct perf_record_stat_config *config = &event->stat_config;
-	struct perf_stat_config stat_config;
+	struct perf_stat_config stat_config = {};
 
 #define HAS(term, val) \
 	has_term(config, PERF_STAT_CONFIG_TERM__##term, val)
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 967e583392c7..ec3506042217 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -729,7 +729,7 @@ size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp)
 
 size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp)
 {
-	struct perf_stat_config sc;
+	struct perf_stat_config sc = {};
 	size_t ret;
 
 	perf_event__read_stat_config(&sc, &event->stat_config);

From 0f97a3a0deccece93797cd35ba1c18704e94b7e7 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 24 Jul 2023 13:12:45 -0700
Subject: [PATCH 0098/1189] perf parse-events: Avoid use uninitialized warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

With GCC LTO a potential use uninitialized is spotted:
```
In function ‘parse_events_config_bpf’,
    inlined from ‘parse_events_load_bpf’ at util/parse-events.c:874:8:
util/parse-events.c:792:37: error: ‘error_pos’ may be used uninitialized [-Werror=maybe-uninitialized]
  792 |                                 idx = term->err_term + error_pos;
      |                                     ^
util/parse-events.c: In function ‘parse_events_load_bpf’:
util/parse-events.c:765:13: note: ‘error_pos’ was declared here
  765 |         int error_pos;
      |             ^
```
So initialize at declaration.

Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Carsten Haitzler <carsten.haitzler@arm.com>
Cc: Fangrui Song <maskray@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Tom Rix <trix@redhat.com>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: bpf@vger.kernel.org
Cc: llvm@lists.linux.dev
Link: https://lore.kernel.org/r/20230724201247.748146-3-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index acde097e327c..da29061ecf49 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -762,7 +762,7 @@ parse_events_config_bpf(struct parse_events_state *parse_state,
 			struct list_head *head_config)
 {
 	struct parse_events_term *term;
-	int error_pos;
+	int error_pos = 0;
 
 	if (!head_config || list_empty(head_config))
 		return 0;

From 5cfb0cc0d95af8bf33a8fb1cedc3e76ca3b6fb81 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 24 Jul 2023 13:12:46 -0700
Subject: [PATCH 0099/1189] perf test: Avoid weak symbol for arch_tests

GCC LTO will complain that the array length varies for the arch_tests
weak symbol. Use extern/static and architecture determining #if to
workaround this problem.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Carsten Haitzler <carsten.haitzler@arm.com>
Cc: Fangrui Song <maskray@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Tom Rix <trix@redhat.com>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: bpf@vger.kernel.org
Cc: llvm@lists.linux.dev
Link: https://lore.kernel.org/r/20230724201247.748146-4-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/builtin-test.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 1f6557ce3b0a..6accb5442a73 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -33,9 +33,18 @@
 static bool dont_fork;
 const char *dso_to_test;
 
-struct test_suite *__weak arch_tests[] = {
+/*
+ * List of architecture specific tests. Not a weak symbol as the array length is
+ * dependent on the initialization, as such GCC with LTO complains of
+ * conflicting definitions with a weak symbol.
+ */
+#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) || defined(__powerpc64__)
+extern struct test_suite *arch_tests[];
+#else
+static struct test_suite *arch_tests[] = {
 	NULL,
 };
+#endif
 
 static struct test_suite *generic_tests[] = {
 	&suite__vmlinux_matches_kallsyms,

From c126ac4a2003fff398311739514f173944a5ceab Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 24 Jul 2023 13:12:47 -0700
Subject: [PATCH 0100/1189] perf build: Add LTO build option

Add an LTO build option, that sets the appropriate CFLAGS and CXXFLAGS
values.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Carsten Haitzler <carsten.haitzler@arm.com>
Cc: Fangrui Song <maskray@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Tom Rix <trix@redhat.com>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: bpf@vger.kernel.org
Cc: llvm@lists.linux.dev
Link: https://lore.kernel.org/r/20230724201247.748146-5-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Makefile.config | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index c5db0de49868..a9cfe83638a9 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -256,6 +256,11 @@ ifdef PARSER_DEBUG
   $(call detected_var,PARSER_DEBUG_FLEX)
 endif
 
+ifdef LTO
+  CORE_CFLAGS += -flto
+  CXXFLAGS += -flto
+endif
+
 # Try different combinations to accommodate systems that only have
 # python[2][3]-config in weird combinations in the following order of
 # priority from lowest to highest:

From 657c45b303f87d77eb4ef49e9452f1c5d1fc363c Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Fri, 14 Jul 2023 11:40:27 -0600
Subject: [PATCH 0101/1189] MIPS: Explicitly include correct DT includes

The DT of_device.h and of_platform.h date back to the separate
of_platform_bus_type before it was merged into the regular platform bus.
As part of that merge prepping Arm DT support 13 years ago, they
"temporarily" include each other. They also include platform_device.h
and of.h. As a result, there's a pretty much random mix of those include
files used throughout the tree. In order to detangle these headers and
replace the implicit includes with struct declarations, users need to
explicitly include the correct includes.

Signed-off-by: Rob Herring <robh@kernel.org>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/bmips/setup.c               | 1 -
 arch/mips/cavium-octeon/flash_setup.c | 3 ++-
 arch/mips/lantiq/irq.c                | 2 +-
 arch/mips/lantiq/xway/dcdc.c          | 3 ++-
 arch/mips/lantiq/xway/gptu.c          | 4 ++--
 arch/mips/lantiq/xway/sysctrl.c       | 1 -
 arch/mips/lantiq/xway/vmmc.c          | 3 ++-
 arch/mips/pci/pci-lantiq.c            | 4 ++--
 arch/mips/pci/pci-rt2880.c            | 5 ++---
 arch/mips/pic32/pic32mzda/config.c    | 1 -
 arch/mips/ralink/irq.c                | 2 +-
 arch/mips/ralink/of.c                 | 2 +-
 arch/mips/ralink/prom.c               | 2 --
 13 files changed, 15 insertions(+), 18 deletions(-)

diff --git a/arch/mips/bmips/setup.c b/arch/mips/bmips/setup.c
index 053805cb741c..ec180ab92eaa 100644
--- a/arch/mips/bmips/setup.c
+++ b/arch/mips/bmips/setup.c
@@ -16,7 +16,6 @@
 #include <linux/of.h>
 #include <linux/of_clk.h>
 #include <linux/of_fdt.h>
-#include <linux/of_platform.h>
 #include <linux/libfdt.h>
 #include <linux/smp.h>
 #include <asm/addrspace.h>
diff --git a/arch/mips/cavium-octeon/flash_setup.c b/arch/mips/cavium-octeon/flash_setup.c
index c8a8c6d359b9..3395acde4d60 100644
--- a/arch/mips/cavium-octeon/flash_setup.c
+++ b/arch/mips/cavium-octeon/flash_setup.c
@@ -12,7 +12,8 @@
 #include <linux/semaphore.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/map.h>
-#include <linux/of_platform.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
 #include <linux/mtd/partitions.h>
 
 #include <asm/octeon/octeon.h>
diff --git a/arch/mips/lantiq/irq.c b/arch/mips/lantiq/irq.c
index 20622bf0a9b3..8f208007b8e8 100644
--- a/arch/mips/lantiq/irq.c
+++ b/arch/mips/lantiq/irq.c
@@ -10,7 +10,7 @@
 #include <linux/sched.h>
 #include <linux/irqchip.h>
 #include <linux/irqdomain.h>
-#include <linux/of_platform.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 
diff --git a/arch/mips/lantiq/xway/dcdc.c b/arch/mips/lantiq/xway/dcdc.c
index 96199966a350..4a808f8c5beb 100644
--- a/arch/mips/lantiq/xway/dcdc.c
+++ b/arch/mips/lantiq/xway/dcdc.c
@@ -6,7 +6,8 @@
  */
 
 #include <linux/ioport.h>
-#include <linux/of_platform.h>
+#include <linux/mod_devicetable.h>
+#include <linux/platform_device.h>
 
 #include <lantiq_soc.h>
 
diff --git a/arch/mips/lantiq/xway/gptu.c b/arch/mips/lantiq/xway/gptu.c
index a492b1eb1925..e254b108fb9b 100644
--- a/arch/mips/lantiq/xway/gptu.c
+++ b/arch/mips/lantiq/xway/gptu.c
@@ -8,8 +8,8 @@
 #include <linux/interrupt.h>
 #include <linux/ioport.h>
 #include <linux/init.h>
-#include <linux/of_platform.h>
-#include <linux/of_irq.h>
+#include <linux/mod_devicetable.h>
+#include <linux/platform_device.h>
 
 #include <lantiq_soc.h>
 #include "../clk.h"
diff --git a/arch/mips/lantiq/xway/sysctrl.c b/arch/mips/lantiq/xway/sysctrl.c
index d444a1b98a72..3ed078225222 100644
--- a/arch/mips/lantiq/xway/sysctrl.c
+++ b/arch/mips/lantiq/xway/sysctrl.c
@@ -10,7 +10,6 @@
 #include <linux/clkdev.h>
 #include <linux/spinlock.h>
 #include <linux/of.h>
-#include <linux/of_platform.h>
 #include <linux/of_address.h>
 
 #include <lantiq_soc.h>
diff --git a/arch/mips/lantiq/xway/vmmc.c b/arch/mips/lantiq/xway/vmmc.c
index 2796e87dfcae..37c133052ef7 100644
--- a/arch/mips/lantiq/xway/vmmc.c
+++ b/arch/mips/lantiq/xway/vmmc.c
@@ -7,7 +7,8 @@
 #include <linux/err.h>
 #include <linux/export.h>
 #include <linux/gpio/consumer.h>
-#include <linux/of_platform.h>
+#include <linux/mod_devicetable.h>
+#include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 
 #include <lantiq_soc.h>
diff --git a/arch/mips/pci/pci-lantiq.c b/arch/mips/pci/pci-lantiq.c
index 79e29bf42a24..80f7293166bb 100644
--- a/arch/mips/pci/pci-lantiq.c
+++ b/arch/mips/pci/pci-lantiq.c
@@ -13,9 +13,9 @@
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
 #include <linux/clk.h>
-#include <linux/of_platform.h>
-#include <linux/of_irq.h>
+#include <linux/of.h>
 #include <linux/of_pci.h>
+#include <linux/platform_device.h>
 
 #include <asm/addrspace.h>
 
diff --git a/arch/mips/pci/pci-rt2880.c b/arch/mips/pci/pci-rt2880.c
index e9dd01431f21..1cada09fa5db 100644
--- a/arch/mips/pci/pci-rt2880.c
+++ b/arch/mips/pci/pci-rt2880.c
@@ -13,9 +13,8 @@
 #include <linux/pci.h>
 #include <linux/io.h>
 #include <linux/init.h>
-#include <linux/of_platform.h>
-#include <linux/of_irq.h>
-#include <linux/of_pci.h>
+#include <linux/mod_devicetable.h>
+#include <linux/platform_device.h>
 
 #include <asm/mach-ralink/rt288x.h>
 
diff --git a/arch/mips/pic32/pic32mzda/config.c b/arch/mips/pic32/pic32mzda/config.c
index f69532007717..6e94ae66eba8 100644
--- a/arch/mips/pic32/pic32mzda/config.c
+++ b/arch/mips/pic32/pic32mzda/config.c
@@ -5,7 +5,6 @@
  */
 #include <linux/init.h>
 #include <linux/io.h>
-#include <linux/of_platform.h>
 
 #include <asm/mach-pic32/pic32.h>
 
diff --git a/arch/mips/ralink/irq.c b/arch/mips/ralink/irq.c
index fa353bc13947..46aef0a1b22a 100644
--- a/arch/mips/ralink/irq.c
+++ b/arch/mips/ralink/irq.c
@@ -7,7 +7,7 @@
 
 #include <linux/io.h>
 #include <linux/bitops.h>
-#include <linux/of_platform.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/irqdomain.h>
diff --git a/arch/mips/ralink/of.c b/arch/mips/ralink/of.c
index 45d60c094496..7f90068c68f2 100644
--- a/arch/mips/ralink/of.c
+++ b/arch/mips/ralink/of.c
@@ -14,7 +14,7 @@
 #include <linux/of_fdt.h>
 #include <linux/kernel.h>
 #include <linux/memblock.h>
-#include <linux/of_platform.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
 
 #include <asm/reboot.h>
diff --git a/arch/mips/ralink/prom.c b/arch/mips/ralink/prom.c
index aaac1e6ec7d9..c3b96861844c 100644
--- a/arch/mips/ralink/prom.c
+++ b/arch/mips/ralink/prom.c
@@ -7,8 +7,6 @@
  */
 
 #include <linux/string.h>
-#include <linux/of_fdt.h>
-#include <linux/of_platform.h>
 
 #include <asm/bootinfo.h>
 #include <asm/addrspace.h>

From a79a404e6c2241ebc528b9ebf4c0832457b498c3 Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@orcam.me.uk>
Date: Tue, 18 Jul 2023 15:37:18 +0100
Subject: [PATCH 0102/1189] MIPS: Fix CONFIG_CPU_DADDI_WORKAROUNDS
 `modules_install' regression
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove a build-time check for the presence of the GCC `-msym32' option.
This option has been there since GCC 4.1.0, which is below the minimum
required as at commit 805b2e1d427a ("kbuild: include Makefile.compiler
only when compiler is needed"), when an error message:

arch/mips/Makefile:306: *** CONFIG_CPU_DADDI_WORKAROUNDS unsupported without -msym32.  Stop.

started to trigger for the `modules_install' target with configurations
such as `decstation_64_defconfig' that set CONFIG_CPU_DADDI_WORKAROUNDS,
because said commit has made `cc-option-yn' an undefined function for
non-build targets.

Reported-by: Jan-Benedict Glaw <jbglaw@lug-owl.de>
Signed-off-by: Maciej W. Rozycki <macro@orcam.me.uk>
Fixes: 805b2e1d427a ("kbuild: include Makefile.compiler only when compiler is needed")
Cc: stable@vger.kernel.org # v5.13+
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/Makefile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index a47593d72f6f..69c18074d817 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -299,8 +299,8 @@ ifdef CONFIG_64BIT
     endif
   endif
 
-  ifeq ($(KBUILD_SYM32)$(call cc-option-yn,-msym32), yy)
-    cflags-y += -msym32 -DKBUILD_64BIT_SYM32
+  ifeq ($(KBUILD_SYM32), y)
+    cflags-$(KBUILD_SYM32) += -msym32 -DKBUILD_64BIT_SYM32
   else
     ifeq ($(CONFIG_CPU_DADDI_WORKAROUNDS), y)
       $(error CONFIG_CPU_DADDI_WORKAROUNDS unsupported without -msym32)

From 4fe4a6374c4db9ae2b849b61e84b58685dca565a Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@orcam.me.uk>
Date: Tue, 18 Jul 2023 15:37:23 +0100
Subject: [PATCH 0103/1189] MIPS: Only fiddle with CHECKFLAGS if
 `need-compiler'

We have originally guarded fiddling with CHECKFLAGS in our arch Makefile
by checking for the CONFIG_MIPS variable, not set for targets such as
`distclean', etc. that neither include `.config' nor use the compiler.

Starting from commit 805b2e1d427a ("kbuild: include Makefile.compiler
only when compiler is needed") we have had a generic `need-compiler'
variable explicitly telling us if the compiler will be used and thus its
capabilities need to be checked and expressed in the form of compilation
flags.  If this variable is not set, then `make' functions such as
`cc-option' are undefined, causing all kinds of weirdness to happen if
we expect specific results to be returned, most recently:

cc1: error: '-mloongson-mmi' must be used with '-mhard-float'

messages with configurations such as `fuloong2e_defconfig' and the
`modules_install' target, which does include `.config' and yet does not
use the compiler.

Replace the check for CONFIG_MIPS with one for `need-compiler' instead,
so as to prevent the compiler from being ever called for CHECKFLAGS when
not needed.

Reported-by: Guillaume Tucker <guillaume.tucker@collabora.com>
Closes: https://lore.kernel.org/r/85031c0c-d981-031e-8a50-bc4fad2ddcd8@collabora.com/
Signed-off-by: Maciej W. Rozycki <macro@orcam.me.uk>
Fixes: 805b2e1d427a ("kbuild: include Makefile.compiler only when compiler is needed")
Cc: stable@vger.kernel.org # v5.13+
Reported-by: "kernelci.org bot" <bot@kernelci.org>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index 69c18074d817..d624b87c150d 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -341,7 +341,7 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
 
 KBUILD_LDFLAGS		+= -m $(ld-emul)
 
-ifdef CONFIG_MIPS
+ifdef need-compiler
 CHECKFLAGS += $(shell $(CC) $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) -dM -E -x c /dev/null | \
 	grep -E -vw '__GNUC_(MINOR_|PATCHLEVEL_)?_' | \
 	sed -e "s/^\#define /-D'/" -e "s/ /'='/" -e "s/$$/'/" -e 's/\$$/&&/g')

From 0859bdf1ace659e8981a82956920573c1f8203da Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@orcam.me.uk>
Date: Tue, 18 Jul 2023 15:37:27 +0100
Subject: [PATCH 0104/1189] Revert MIPS: Loongson: Fix build error when make
 modules_install

Revert commit 531b3d1195d0 ("MIPS: Loongson: Fix build error when make
modules_install"), which made `-march=loongson2e', `-march=loongson2f',
and `-march=loongson3a' compilation options probed for even though GCC
has supported them since 4.4.0, 4.4.0, and 4.6.0 respectively, which is
below our current minimum requirement of 5.1, in an attempt to work
around for the `cc-option' `make' function being undefined with `make'
targets that do not use the compiler.  The workaround has now been made
obsolete, by querying the `need-compiler' variable instead so as to make
sure the compiler isn't called for non-build targets.

Verified with `fuloong2e_defconfig' and the `modules_install' target.

Signed-off-by: Maciej W. Rozycki <macro@orcam.me.uk>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/Makefile | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index d624b87c150d..f49807e1f19b 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -181,12 +181,16 @@ endif
 cflags-$(CONFIG_CAVIUM_CN63XXP1) += -Wa,-mfix-cn63xxp1
 cflags-$(CONFIG_CPU_BMIPS)	+= -march=mips32 -Wa,-mips32 -Wa,--trap
 
-cflags-$(CONFIG_CPU_LOONGSON2E) += $(call cc-option,-march=loongson2e) -Wa,--trap
-cflags-$(CONFIG_CPU_LOONGSON2F) += $(call cc-option,-march=loongson2f) -Wa,--trap
-cflags-$(CONFIG_CPU_LOONGSON64) += $(call cc-option,-march=loongson3a,-march=mips64r2) -Wa,--trap
+cflags-$(CONFIG_CPU_LOONGSON2E) += -march=loongson2e -Wa,--trap
+cflags-$(CONFIG_CPU_LOONGSON2F) += -march=loongson2f -Wa,--trap
 # Some -march= flags enable MMI instructions, and GCC complains about that
 # support being enabled alongside -msoft-float. Thus explicitly disable MMI.
 cflags-$(CONFIG_CPU_LOONGSON2EF) += $(call cc-option,-mno-loongson-mmi)
+ifdef CONFIG_CPU_LOONGSON64
+cflags-$(CONFIG_CPU_LOONGSON64)	+= -Wa,--trap
+cflags-$(CONFIG_CC_IS_GCC) += -march=loongson3a
+cflags-$(CONFIG_CC_IS_CLANG) += -march=mips64r2
+endif
 cflags-$(CONFIG_CPU_LOONGSON64) += $(call cc-option,-mno-loongson-mmi)
 
 cflags-$(CONFIG_CPU_R4000_WORKAROUNDS)	+= $(call cc-option,-mfix-r4000,)

From 8362bf82fb5441613aac7c6c9dbb6b83def6ad3b Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Tue, 25 Jul 2023 08:37:56 -0700
Subject: [PATCH 0105/1189] Input: mcs-touchkey - fix uninitialized use of
 error in mcs_touchkey_probe()

Clang warns (or errors with CONFIG_WERROR=y):

  drivers/input/keyboard/mcs_touchkey.c:149:49: error: variable 'error' is uninitialized when used here [-Werror,-Wuninitialized]
    149 |                 dev_err(&client->dev, "i2c read error[%d]\n", error);
        |                                                               ^~~~~
  include/linux/dev_printk.h:144:65: note: expanded from macro 'dev_err'
    144 |         dev_printk_index_wrap(_dev_err, KERN_ERR, dev, dev_fmt(fmt), ##__VA_ARGS__)
        |                                                                        ^~~~~~~~~~~
  include/linux/dev_printk.h:110:23: note: expanded from macro 'dev_printk_index_wrap'
    110 |                 _p_func(dev, fmt, ##__VA_ARGS__);                       \
        |                                     ^~~~~~~~~~~
  drivers/input/keyboard/mcs_touchkey.c:110:11: note: initialize the variable 'error' to silence this warning
    110 |         int error;
        |                  ^
        |                   = 0
  1 error generated.

A refactoring updated the error handling in this block but did not
update the dev_err() call to use fw_ver instead of error. Do so now to
fix the warning and avoid printing uninitialized memory.

Closes: https://github.com/ClangBuiltLinux/linux/issues/1893
Fixes: e175eae16c1b ("Input: mcs-touchkey - convert to use devm_* api")
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Link: https://lore.kernel.org/r/20230725-mcs_touchkey-fix-wuninitialized-v1-1-615db39af51c@kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/mcs_touchkey.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/input/keyboard/mcs_touchkey.c b/drivers/input/keyboard/mcs_touchkey.c
index f25e2b20e271..2410f676c7f9 100644
--- a/drivers/input/keyboard/mcs_touchkey.c
+++ b/drivers/input/keyboard/mcs_touchkey.c
@@ -146,7 +146,7 @@ static int mcs_touchkey_probe(struct i2c_client *client)
 
 	fw_ver = i2c_smbus_read_byte_data(client, fw_reg);
 	if (fw_ver < 0) {
-		dev_err(&client->dev, "i2c read error[%d]\n", error);
+		dev_err(&client->dev, "i2c read error[%d]\n", fw_ver);
 		return fw_ver;
 	}
 	dev_info(&client->dev, "Firmware version: %d\n", fw_ver);

From 92e24e0e57f72e06c2df87116557331fd2d4dda2 Mon Sep 17 00:00:00 2001
From: Jeffery Miller <jefferymiller@google.com>
Date: Wed, 26 Jul 2023 02:52:48 +0000
Subject: [PATCH 0106/1189] Input: psmouse - add delay when deactivating for
 SMBus mode

There is a period of time between the psmouse deactivate and the
ability to communicate with the SMBus companion. Insert a
sleep after the deactivate to account for the delay and ensure
the SMBus companion is responsive.

Attempting to read from the SMBus companion too quickly was causing
the touchpad on machines with an i801_smbus companion to stop working
after a sleep/resume cycle.

On resume the rmi4_smbus would fail with errors reading the SMBus version
number:
```
[5454] i2c_i801:i801_check_post:414: i801_smbus 0000:00:1f.3: No response
smbus_result: i2c-0 a=02c f=0000 c=fd BYTE_DATA rd res=-6
rmi4_smbus 0-002c: failed to get SMBus version number!
...
rmi4_f01 rmi4-00.fn01: Failed to restore normal operation: -6.
rmi4_f01 rmi4-00.fn01: Resume failed with code -6.
rmi4_physical rmi4-00: Failed to suspend functions: -6
rmi4_smbus 0-002c: Failed to resume device: -6
```
In this case the rmi_smb_get_version fails with -ENXIO if it happens too
soon after the preceding serio_resume -> psmouse_deactivate call.

On boot this issue could cause the touchpad to stay in the limited PS/2
mode. This only reproduced in 1 in 10 boots on the Lenovo T440p.
Failures in the log on boot would show up as:
```
psmouse serio1: synaptics: Trying to set up SMBus access
[122] i2c_i801:i801_check_post:437: i801_smbus 0000:00:1f.3: No response
psmouse serio1: synaptics: SMbus companion is not ready yet
```

Experimentation on the Lenovo T440p showed that a delay of 7-12ms on
resume allowed the companion to respond.

The 30ms delay in this patch was chosen based on the linux-input message:
Link: https://lore.kernel.org/all/BYAPR03MB47572F2C65E52ED673238D41B2439@BYAPR03MB4757.namprd03.prod.outlook.com/

Signed-off-by: Jeffery Miller <jefferymiller@google.com>
Link: https://lore.kernel.org/r/20230726025256.81174-1-jefferymiller@google.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/mouse/psmouse-smbus.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/input/mouse/psmouse-smbus.c b/drivers/input/mouse/psmouse-smbus.c
index 2a2459b1b4f2..7b13de979908 100644
--- a/drivers/input/mouse/psmouse-smbus.c
+++ b/drivers/input/mouse/psmouse-smbus.c
@@ -5,6 +5,7 @@
 
 #define pr_fmt(fmt)		KBUILD_MODNAME ": " fmt
 
+#include <linux/delay.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/libps2.h>
@@ -118,13 +119,18 @@ static psmouse_ret_t psmouse_smbus_process_byte(struct psmouse *psmouse)
 	return PSMOUSE_FULL_PACKET;
 }
 
+static void psmouse_activate_smbus_mode(struct psmouse_smbus_dev *smbdev)
+{
+	if (smbdev->need_deactivate) {
+		psmouse_deactivate(smbdev->psmouse);
+		/* Give the device time to switch into SMBus mode */
+		msleep(30);
+	}
+}
+
 static int psmouse_smbus_reconnect(struct psmouse *psmouse)
 {
-	struct psmouse_smbus_dev *smbdev = psmouse->private;
-
-	if (smbdev->need_deactivate)
-		psmouse_deactivate(psmouse);
-
+	psmouse_activate_smbus_mode(psmouse->private);
 	return 0;
 }
 
@@ -257,8 +263,7 @@ int psmouse_smbus_init(struct psmouse *psmouse,
 		}
 	}
 
-	if (need_deactivate)
-		psmouse_deactivate(psmouse);
+	psmouse_activate_smbus_mode(smbdev);
 
 	psmouse->private = smbdev;
 	psmouse->protocol_handler = psmouse_smbus_process_byte;

From 84efbdb7fb8e0844a3f9c67a6bdcc89db1012e1c Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 27 Jun 2023 11:10:18 -0700
Subject: [PATCH 0107/1189] perf parse-events: Remove unused PE_PMU_EVENT_FAKE
 token

Removed by commit 70c90e4a6b2f ("perf parse-events: Avoid scanning
PMUs before parsing").

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20230627181030.95608-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.y | 42 ++--------------------------------
 1 file changed, 2 insertions(+), 40 deletions(-)

diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 9f28d4b5502f..64755f9cd600 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -63,7 +63,7 @@ static void free_list_evsel(struct list_head* list_evsel)
 %token PE_LEGACY_CACHE
 %token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP
 %token PE_ERROR
-%token PE_KERNEL_PMU_EVENT PE_PMU_EVENT_FAKE
+%token PE_KERNEL_PMU_EVENT
 %token PE_ARRAY_ALL PE_ARRAY_RANGE
 %token PE_DRV_CFG_TERM
 %token PE_TERM_HW
@@ -81,7 +81,7 @@ static void free_list_evsel(struct list_head* list_evsel)
 %type <str> PE_MODIFIER_EVENT
 %type <str> PE_MODIFIER_BP
 %type <str> PE_EVENT_NAME
-%type <str> PE_KERNEL_PMU_EVENT PE_PMU_EVENT_FAKE
+%type <str> PE_KERNEL_PMU_EVENT
 %type <str> PE_DRV_CFG_TERM
 %type <str> name_or_raw name_or_legacy
 %destructor { free ($$); } <str>
@@ -394,44 +394,6 @@ PE_KERNEL_PMU_EVENT opt_pmu_config
 		YYABORT;
 	$$ = list;
 }
-|
-PE_PMU_EVENT_FAKE sep_dc
-{
-	struct list_head *list;
-	int err;
-
-	list = alloc_list();
-	if (!list)
-		YYABORT;
-
-	err = parse_events_add_pmu(_parse_state, list, $1, /*head_config=*/NULL,
-				   /*auto_merge_stats=*/false);
-	free($1);
-	if (err < 0) {
-		free(list);
-		YYABORT;
-	}
-	$$ = list;
-}
-|
-PE_PMU_EVENT_FAKE opt_pmu_config
-{
-	struct list_head *list;
-	int err;
-
-	list = alloc_list();
-	if (!list)
-		YYABORT;
-
-	err = parse_events_add_pmu(_parse_state, list, $1, $2, /*auto_merge_stats=*/false);
-	free($1);
-	parse_events_terms__delete($2);
-	if (err < 0) {
-		free(list);
-		YYABORT;
-	}
-	$$ = list;
-}
 
 value_sym:
 PE_VALUE_SYM_HW

From bf7d46b3a088ccb8f8045c5902d5848bc23286f9 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 27 Jun 2023 11:10:19 -0700
Subject: [PATCH 0108/1189] perf parse-events: Remove unused
 PE_KERNEL_PMU_EVENT token

Removed by commit 70c90e4a6b2f ("perf parse-events: Avoid scanning
PMUs before parsing").

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20230627181030.95608-3-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.y | 27 ---------------------------
 1 file changed, 27 deletions(-)

diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 64755f9cd600..4ee6c6865655 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -63,7 +63,6 @@ static void free_list_evsel(struct list_head* list_evsel)
 %token PE_LEGACY_CACHE
 %token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP
 %token PE_ERROR
-%token PE_KERNEL_PMU_EVENT
 %token PE_ARRAY_ALL PE_ARRAY_RANGE
 %token PE_DRV_CFG_TERM
 %token PE_TERM_HW
@@ -81,7 +80,6 @@ static void free_list_evsel(struct list_head* list_evsel)
 %type <str> PE_MODIFIER_EVENT
 %type <str> PE_MODIFIER_BP
 %type <str> PE_EVENT_NAME
-%type <str> PE_KERNEL_PMU_EVENT
 %type <str> PE_DRV_CFG_TERM
 %type <str> name_or_raw name_or_legacy
 %destructor { free ($$); } <str>
@@ -358,18 +356,6 @@ PE_NAME opt_pmu_config
 #undef CLEANUP_YYABORT
 }
 |
-PE_KERNEL_PMU_EVENT sep_dc
-{
-	struct list_head *list;
-	int err;
-
-	err = parse_events_multi_pmu_add(_parse_state, $1, NULL, &list);
-	free($1);
-	if (err < 0)
-		YYABORT;
-	$$ = list;
-}
-|
 PE_NAME sep_dc
 {
 	struct list_head *list;
@@ -381,19 +367,6 @@ PE_NAME sep_dc
 		YYABORT;
 	$$ = list;
 }
-|
-PE_KERNEL_PMU_EVENT opt_pmu_config
-{
-	struct list_head *list;
-	int err;
-
-	/* frees $2 */
-	err = parse_events_multi_pmu_add(_parse_state, $1, $2, &list);
-	free($1);
-	if (err < 0)
-		YYABORT;
-	$$ = list;
-}
 
 value_sym:
 PE_VALUE_SYM_HW

From 7e34daa55051f537036a70bd29b43a4cd4c55564 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 27 Jun 2023 11:10:20 -0700
Subject: [PATCH 0109/1189] perf parse-events: Remove two unused tokens

The tokens PE_PREFIX_RAW and PE_PREFIX_GROUP are unused so remove them.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20230627181030.95608-4-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.y | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 4ee6c6865655..b09a5fa92144 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -61,7 +61,7 @@ static void free_list_evsel(struct list_head* list_evsel)
 %token PE_BPF_OBJECT PE_BPF_SOURCE
 %token PE_MODIFIER_EVENT PE_MODIFIER_BP PE_BP_COLON PE_BP_SLASH
 %token PE_LEGACY_CACHE
-%token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP
+%token PE_PREFIX_MEM
 %token PE_ERROR
 %token PE_ARRAY_ALL PE_ARRAY_RANGE
 %token PE_DRV_CFG_TERM

From 22881e2b458dc75e809fc7798f91f4814f3be65f Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 27 Jun 2023 11:10:21 -0700
Subject: [PATCH 0110/1189] perf parse-events: Add more comments to 'struct
 parse_events_state'

Improve documentation of 'struct parse_events_state'.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20230627181030.95608-5-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.h | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index b0eb95f93e9c..b37e5ee193a8 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -121,17 +121,25 @@ struct parse_events_error {
 };
 
 struct parse_events_state {
+	/* The list parsed events are placed on. */
 	struct list_head	   list;
+	/* The updated index used by entries as they are added. */
 	int			   idx;
+	/* Error information. */
 	struct parse_events_error *error;
+	/* Used by BPF event creation. */
 	struct evlist		  *evlist;
+	/* Holds returned terms for term parsing. */
 	struct list_head	  *terms;
+	/* Start token. */
 	int			   stoken;
+	/* Special fake PMU marker for testing. */
 	struct perf_pmu		  *fake_pmu;
 	/* If non-null, when wildcard matching only match the given PMU. */
 	const char		  *pmu_filter;
 	/* Should PE_LEGACY_NAME tokens be generated for config terms? */
 	bool			   match_legacy_cache_terms;
+	/* Were multiple PMUs scanned to find events? */
 	bool			   wild_card_pmus;
 };
 

From 93d7e9c8fbb4624b7dfe8b3605b9f10f192ede98 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 27 Jun 2023 11:10:22 -0700
Subject: [PATCH 0111/1189] perf parse-events: Avoid regrouped warning for wild
 card events

There is logic to avoid printing the regrouping warning for wild card
PMUs, this logic also needs to apply for wild card events.

Before:
```
$ perf stat -e '{data_read,data_write}' -a sleep 1
WARNING: events were regrouped to match PMUs

 Performance counter stats for 'system wide':

          2,979.16 MiB  data_read
            410.26 MiB  data_write

       1.001541923 seconds time elapsed
```
After:
```
$ perf stat -e '{data_read,data_write}' -a sleep 1

 Performance counter stats for 'system wide':

          2,975.94 MiB  data_read
            432.05 MiB  data_write

       1.001119499 seconds time elapsed
```

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20230627181030.95608-6-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index da29061ecf49..75778d5be5b6 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1730,6 +1730,7 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 							  auto_merge_stats)) {
 					pr_debug("%s -> %s/%s/\n", str,
 						 pmu->name, alias->str);
+					parse_state->wild_card_pmus = true;
 					ok++;
 				}
 				parse_events_terms__delete(orig_head);

From 31f077c374a8e7cf1960560c0c5e4065048557c0 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 22 Jun 2023 10:57:44 -0400
Subject: [PATCH 0112/1189] rtc: pcf2127: improve rtc_read_time() performance

Improve performance and readability of rtc_read_time() by reading only
the 7 time registers, instead of reading 8 registers (additional CTRL3
register).

We drop reading of CTRL3 to monitor the low battery flag, as this
check is already available in the ioctl. Anyway, this check only
display an info message and has no other impacts.

The code readability also improves as we do not have to fiddle with
buffer pointer and size arithmetic.

Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20230622145800.2442116-2-hugo@hugovil.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-pcf2127.c | 40 +++++++++++++--------------------------
 1 file changed, 13 insertions(+), 27 deletions(-)

diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index ee03b04b74ba..8d40a413a8fe 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -45,12 +45,6 @@
 /* Time and date registers */
 #define PCF2127_REG_SC			0x03
 #define PCF2127_BIT_SC_OSF			BIT(7)
-#define PCF2127_REG_MN			0x04
-#define PCF2127_REG_HR			0x05
-#define PCF2127_REG_DM			0x06
-#define PCF2127_REG_DW			0x07
-#define PCF2127_REG_MO			0x08
-#define PCF2127_REG_YR			0x09
 /* Alarm registers */
 #define PCF2127_REG_ALARM_SC		0x0A
 #define PCF2127_REG_ALARM_MN		0x0B
@@ -117,27 +111,22 @@ struct pcf2127 {
 static int pcf2127_rtc_read_time(struct device *dev, struct rtc_time *tm)
 {
 	struct pcf2127 *pcf2127 = dev_get_drvdata(dev);
-	unsigned char buf[10];
+	unsigned char buf[7];
 	int ret;
 
 	/*
 	 * Avoid reading CTRL2 register as it causes WD_VAL register
 	 * value to reset to 0 which means watchdog is stopped.
 	 */
-	ret = regmap_bulk_read(pcf2127->regmap, PCF2127_REG_CTRL3,
-			       (buf + PCF2127_REG_CTRL3),
-			       ARRAY_SIZE(buf) - PCF2127_REG_CTRL3);
+	ret = regmap_bulk_read(pcf2127->regmap, PCF2127_REG_SC, buf,
+			       sizeof(buf));
 	if (ret) {
 		dev_err(dev, "%s: read error\n", __func__);
 		return ret;
 	}
 
-	if (buf[PCF2127_REG_CTRL3] & PCF2127_BIT_CTRL3_BLF)
-		dev_info(dev,
-			"low voltage detected, check/replace RTC battery.\n");
-
 	/* Clock integrity is not guaranteed when OSF flag is set. */
-	if (buf[PCF2127_REG_SC] & PCF2127_BIT_SC_OSF) {
+	if (buf[0] & PCF2127_BIT_SC_OSF) {
 		/*
 		 * no need clear the flag here,
 		 * it will be cleared once the new date is saved
@@ -148,20 +137,17 @@ static int pcf2127_rtc_read_time(struct device *dev, struct rtc_time *tm)
 	}
 
 	dev_dbg(dev,
-		"%s: raw data is cr3=%02x, sec=%02x, min=%02x, hr=%02x, "
+		"%s: raw data is sec=%02x, min=%02x, hr=%02x, "
 		"mday=%02x, wday=%02x, mon=%02x, year=%02x\n",
-		__func__, buf[PCF2127_REG_CTRL3], buf[PCF2127_REG_SC],
-		buf[PCF2127_REG_MN], buf[PCF2127_REG_HR],
-		buf[PCF2127_REG_DM], buf[PCF2127_REG_DW],
-		buf[PCF2127_REG_MO], buf[PCF2127_REG_YR]);
+		__func__, buf[0], buf[1], buf[2], buf[3], buf[4], buf[5], buf[6]);
 
-	tm->tm_sec = bcd2bin(buf[PCF2127_REG_SC] & 0x7F);
-	tm->tm_min = bcd2bin(buf[PCF2127_REG_MN] & 0x7F);
-	tm->tm_hour = bcd2bin(buf[PCF2127_REG_HR] & 0x3F); /* rtc hr 0-23 */
-	tm->tm_mday = bcd2bin(buf[PCF2127_REG_DM] & 0x3F);
-	tm->tm_wday = buf[PCF2127_REG_DW] & 0x07;
-	tm->tm_mon = bcd2bin(buf[PCF2127_REG_MO] & 0x1F) - 1; /* rtc mn 1-12 */
-	tm->tm_year = bcd2bin(buf[PCF2127_REG_YR]);
+	tm->tm_sec = bcd2bin(buf[0] & 0x7F);
+	tm->tm_min = bcd2bin(buf[1] & 0x7F);
+	tm->tm_hour = bcd2bin(buf[2] & 0x3F); /* rtc hr 0-23 */
+	tm->tm_mday = bcd2bin(buf[3] & 0x3F);
+	tm->tm_wday = buf[4] & 0x07;
+	tm->tm_mon = bcd2bin(buf[5] & 0x1F) - 1; /* rtc mn 1-12 */
+	tm->tm_year = bcd2bin(buf[6]);
 	tm->tm_year += 100;
 
 	dev_dbg(dev, "%s: tm is secs=%d, mins=%d, hours=%d, "

From 720fb4b83b565c7ae31059620e960ecbf5dc73a3 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 22 Jun 2023 10:57:45 -0400
Subject: [PATCH 0113/1189] rtc: pcf2127: improve timestamp reading performance

Reading the 7 timetamp registers currently involves reading 25 registers
solely to be able to print the content of the three control registers,
in addition to the 7 timestamp registers. This print never occurs,
unless the user enables dynamic debug in this driver or set
CONFIG_RTC_DEBUG.

Reading the timestamp registers should consist of reading 7
consecutive timestamp registers.

This patch optimize the performance of reading the timestamp registers
by reading 7 consecutive registers instead of 25, and dropping the
print of the control registers.

Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20230622145800.2442116-3-hugo@hugovil.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-pcf2127.c | 30 ++++++++++--------------------
 1 file changed, 10 insertions(+), 20 deletions(-)

diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index 8d40a413a8fe..3332d26aee11 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -66,12 +66,6 @@
 #define PCF2127_REG_TS_CTRL		0x12
 #define PCF2127_BIT_TS_CTRL_TSOFF		BIT(6)
 #define PCF2127_BIT_TS_CTRL_TSM			BIT(7)
-#define PCF2127_REG_TS_SC		0x13
-#define PCF2127_REG_TS_MN		0x14
-#define PCF2127_REG_TS_HR		0x15
-#define PCF2127_REG_TS_DM		0x16
-#define PCF2127_REG_TS_MO		0x17
-#define PCF2127_REG_TS_YR		0x18
 /*
  * RAM registers
  * PCF2127 has 512 bytes general-purpose static RAM (SRAM) that is
@@ -440,9 +434,9 @@ static int pcf2127_rtc_ts_read(struct device *dev, time64_t *ts)
 	struct pcf2127 *pcf2127 = dev_get_drvdata(dev);
 	struct rtc_time tm;
 	int ret;
-	unsigned char data[25];
+	unsigned char data[7];
 
-	ret = regmap_bulk_read(pcf2127->regmap, PCF2127_REG_CTRL1, data,
+	ret = regmap_bulk_read(pcf2127->regmap, PCF2127_REG_TS_CTRL, data,
 			       sizeof(data));
 	if (ret) {
 		dev_err(dev, "%s: read error ret=%d\n", __func__, ret);
@@ -450,20 +444,16 @@ static int pcf2127_rtc_ts_read(struct device *dev, time64_t *ts)
 	}
 
 	dev_dbg(dev,
-		"%s: raw data is cr1=%02x, cr2=%02x, cr3=%02x, ts_sc=%02x, ts_mn=%02x, ts_hr=%02x, ts_dm=%02x, ts_mo=%02x, ts_yr=%02x\n",
-		__func__, data[PCF2127_REG_CTRL1], data[PCF2127_REG_CTRL2],
-		data[PCF2127_REG_CTRL3], data[PCF2127_REG_TS_SC],
-		data[PCF2127_REG_TS_MN], data[PCF2127_REG_TS_HR],
-		data[PCF2127_REG_TS_DM], data[PCF2127_REG_TS_MO],
-		data[PCF2127_REG_TS_YR]);
+		"%s: raw data is ts_sc=%02x, ts_mn=%02x, ts_hr=%02x, ts_dm=%02x, ts_mo=%02x, ts_yr=%02x\n",
+		__func__, data[1], data[2], data[3], data[4], data[5], data[6]);
 
-	tm.tm_sec = bcd2bin(data[PCF2127_REG_TS_SC] & 0x7F);
-	tm.tm_min = bcd2bin(data[PCF2127_REG_TS_MN] & 0x7F);
-	tm.tm_hour = bcd2bin(data[PCF2127_REG_TS_HR] & 0x3F);
-	tm.tm_mday = bcd2bin(data[PCF2127_REG_TS_DM] & 0x3F);
+	tm.tm_sec = bcd2bin(data[1] & 0x7F);
+	tm.tm_min = bcd2bin(data[2] & 0x7F);
+	tm.tm_hour = bcd2bin(data[3] & 0x3F);
+	tm.tm_mday = bcd2bin(data[4] & 0x3F);
 	/* TS_MO register (month) value range: 1-12 */
-	tm.tm_mon = bcd2bin(data[PCF2127_REG_TS_MO] & 0x1F) - 1;
-	tm.tm_year = bcd2bin(data[PCF2127_REG_TS_YR]);
+	tm.tm_mon = bcd2bin(data[5] & 0x1F) - 1;
+	tm.tm_year = bcd2bin(data[6]);
 	if (tm.tm_year < 70)
 		tm.tm_year += 100; /* assume we are in 1970...2069 */
 

From 3d740c647ff8b77b2a560ebd95ac746c46f49ed4 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 22 Jun 2023 10:57:46 -0400
Subject: [PATCH 0114/1189] rtc: pcf2127: lower message severity if setting
 time fails

Noted while reviewing new PCF2131 driver.

Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20230622145800.2442116-4-hugo@hugovil.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-pcf2127.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index 3332d26aee11..2a4d980bb7d5 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -181,8 +181,7 @@ static int pcf2127_rtc_set_time(struct device *dev, struct rtc_time *tm)
 	/* write register's data */
 	err = regmap_bulk_write(pcf2127->regmap, PCF2127_REG_SC, buf, i);
 	if (err) {
-		dev_err(dev,
-			"%s: err=%d", __func__, err);
+		dev_dbg(dev, "%s: err=%d", __func__, err);
 		return err;
 	}
 

From 0476b6c8e8b1a6dfa3a259bc7e3c135145532c71 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 22 Jun 2023 10:57:47 -0400
Subject: [PATCH 0115/1189] rtc: pcf2127: remove superfluous comments

Noted while reviewing new PCF2131 driver.

Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20230622145800.2442116-5-hugo@hugovil.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-pcf2127.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index 2a4d980bb7d5..309d1710a1c8 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -137,10 +137,10 @@ static int pcf2127_rtc_read_time(struct device *dev, struct rtc_time *tm)
 
 	tm->tm_sec = bcd2bin(buf[0] & 0x7F);
 	tm->tm_min = bcd2bin(buf[1] & 0x7F);
-	tm->tm_hour = bcd2bin(buf[2] & 0x3F); /* rtc hr 0-23 */
+	tm->tm_hour = bcd2bin(buf[2] & 0x3F);
 	tm->tm_mday = bcd2bin(buf[3] & 0x3F);
 	tm->tm_wday = buf[4] & 0x07;
-	tm->tm_mon = bcd2bin(buf[5] & 0x1F) - 1; /* rtc mn 1-12 */
+	tm->tm_mon = bcd2bin(buf[5] & 0x1F) - 1;
 	tm->tm_year = bcd2bin(buf[6]);
 	tm->tm_year += 100;
 

From fd28ceb4603f9541dcb4ed12b1365cff5af38203 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 22 Jun 2023 10:57:48 -0400
Subject: [PATCH 0116/1189] rtc: pcf2127: add variant-specific configuration
 structure

Create variant-specific configuration structures to simplify the
implementation of new variants into this driver. It will also avoid
to have too many tests for a specific variant, or a list of variants
for new devices, inside the code itself.

Add configuration options for the support of the NVMEM, bit CD0 in
register WD_CTL as well as the maximum number of registers for each
variant, instead of hardcoding the variant (PCF2127) inside the
i2c_device_id and spi_device_id structures.

Also specify a different maximum number of registers (max_register)
for the PCF2129.

Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20230622145800.2442116-6-hugo@hugovil.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-pcf2127.c | 98 +++++++++++++++++++++++++++++++--------
 1 file changed, 79 insertions(+), 19 deletions(-)

diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index 309d1710a1c8..23ab872c36cb 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -21,6 +21,7 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_irq.h>
+#include <linux/of_device.h>
 #include <linux/regmap.h>
 #include <linux/watchdog.h>
 
@@ -89,10 +90,24 @@
 		PCF2127_BIT_CTRL2_WDTF | \
 		PCF2127_BIT_CTRL2_TSF2)
 
+enum pcf21xx_type {
+	PCF2127,
+	PCF2129,
+	PCF21XX_LAST_ID
+};
+
+struct pcf21xx_config {
+	int type; /* IC variant */
+	int max_register;
+	unsigned int has_nvmem:1;
+	unsigned int has_bit_wd_ctl_cd0:1;
+};
+
 struct pcf2127 {
 	struct rtc_device *rtc;
 	struct watchdog_device wdd;
 	struct regmap *regmap;
+	const struct pcf21xx_config *cfg;
 	time64_t ts;
 	bool ts_valid;
 	bool irq_enabled;
@@ -606,8 +621,23 @@ static const struct attribute_group pcf2127_attr_group = {
 	.attrs	= pcf2127_attrs,
 };
 
+static struct pcf21xx_config pcf21xx_cfg[] = {
+	[PCF2127] = {
+		.type = PCF2127,
+		.max_register = 0x1d,
+		.has_nvmem = 1,
+		.has_bit_wd_ctl_cd0 = 1,
+	},
+	[PCF2129] = {
+		.type = PCF2129,
+		.max_register = 0x19,
+		.has_nvmem = 0,
+		.has_bit_wd_ctl_cd0 = 0,
+	},
+};
+
 static int pcf2127_probe(struct device *dev, struct regmap *regmap,
-			 int alarm_irq, const char *name, bool is_pcf2127)
+			 int alarm_irq, const char *name, const struct pcf21xx_config *config)
 {
 	struct pcf2127 *pcf2127;
 	int ret = 0;
@@ -620,6 +650,7 @@ static int pcf2127_probe(struct device *dev, struct regmap *regmap,
 		return -ENOMEM;
 
 	pcf2127->regmap = regmap;
+	pcf2127->cfg = config;
 
 	dev_set_drvdata(dev, pcf2127);
 
@@ -663,7 +694,7 @@ static int pcf2127_probe(struct device *dev, struct regmap *regmap,
 		set_bit(RTC_FEATURE_ALARM, pcf2127->rtc->features);
 	}
 
-	if (is_pcf2127) {
+	if (pcf2127->cfg->has_nvmem) {
 		struct nvmem_config nvmem_cfg = {
 			.priv = pcf2127,
 			.reg_read = pcf2127_nvmem_read,
@@ -709,7 +740,7 @@ static int pcf2127_probe(struct device *dev, struct regmap *regmap,
 				 PCF2127_BIT_WD_CTL_TF1 |
 				 PCF2127_BIT_WD_CTL_TF0,
 				 PCF2127_BIT_WD_CTL_CD1 |
-				 (is_pcf2127 ? PCF2127_BIT_WD_CTL_CD0 : 0) |
+				 (pcf2127->cfg->has_bit_wd_ctl_cd0 ? PCF2127_BIT_WD_CTL_CD0 : 0) |
 				 PCF2127_BIT_WD_CTL_TF1);
 	if (ret) {
 		dev_err(dev, "%s: watchdog config (wd_ctl) failed\n", __func__);
@@ -774,9 +805,9 @@ static int pcf2127_probe(struct device *dev, struct regmap *regmap,
 
 #ifdef CONFIG_OF
 static const struct of_device_id pcf2127_of_match[] = {
-	{ .compatible = "nxp,pcf2127" },
-	{ .compatible = "nxp,pcf2129" },
-	{ .compatible = "nxp,pca2129" },
+	{ .compatible = "nxp,pcf2127", .data = &pcf21xx_cfg[PCF2127] },
+	{ .compatible = "nxp,pcf2129", .data = &pcf21xx_cfg[PCF2129] },
+	{ .compatible = "nxp,pca2129", .data = &pcf21xx_cfg[PCF2129] },
 	{}
 };
 MODULE_DEVICE_TABLE(of, pcf2127_of_match);
@@ -861,26 +892,40 @@ static const struct regmap_bus pcf2127_i2c_regmap = {
 static struct i2c_driver pcf2127_i2c_driver;
 
 static const struct i2c_device_id pcf2127_i2c_id[] = {
-	{ "pcf2127", 1 },
-	{ "pcf2129", 0 },
-	{ "pca2129", 0 },
+	{ "pcf2127", PCF2127 },
+	{ "pcf2129", PCF2129 },
+	{ "pca2129", PCF2129 },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, pcf2127_i2c_id);
 
 static int pcf2127_i2c_probe(struct i2c_client *client)
 {
-	const struct i2c_device_id *id = i2c_match_id(pcf2127_i2c_id, client);
 	struct regmap *regmap;
-	static const struct regmap_config config = {
+	static struct regmap_config config = {
 		.reg_bits = 8,
 		.val_bits = 8,
-		.max_register = 0x1d,
 	};
+	const struct pcf21xx_config *variant;
 
 	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C))
 		return -ENODEV;
 
+	if (client->dev.of_node) {
+		variant = of_device_get_match_data(&client->dev);
+		if (!variant)
+			return -ENODEV;
+	} else {
+		enum pcf21xx_type type =
+			i2c_match_id(pcf2127_i2c_id, client)->driver_data;
+
+		if (type >= PCF21XX_LAST_ID)
+			return -ENODEV;
+		variant = &pcf21xx_cfg[type];
+	}
+
+	config.max_register = variant->max_register,
+
 	regmap = devm_regmap_init(&client->dev, &pcf2127_i2c_regmap,
 					&client->dev, &config);
 	if (IS_ERR(regmap)) {
@@ -890,7 +935,7 @@ static int pcf2127_i2c_probe(struct i2c_client *client)
 	}
 
 	return pcf2127_probe(&client->dev, regmap, client->irq,
-			     pcf2127_i2c_driver.driver.name, id->driver_data);
+			     pcf2127_i2c_driver.driver.name, variant);
 }
 
 static struct i2c_driver pcf2127_i2c_driver = {
@@ -928,17 +973,32 @@ static void pcf2127_i2c_unregister_driver(void)
 #if IS_ENABLED(CONFIG_SPI_MASTER)
 
 static struct spi_driver pcf2127_spi_driver;
+static const struct spi_device_id pcf2127_spi_id[];
 
 static int pcf2127_spi_probe(struct spi_device *spi)
 {
-	static const struct regmap_config config = {
+	static struct regmap_config config = {
 		.reg_bits = 8,
 		.val_bits = 8,
 		.read_flag_mask = 0xa0,
 		.write_flag_mask = 0x20,
-		.max_register = 0x1d,
 	};
 	struct regmap *regmap;
+	const struct pcf21xx_config *variant;
+
+	if (spi->dev.of_node) {
+		variant = of_device_get_match_data(&spi->dev);
+		if (!variant)
+			return -ENODEV;
+	} else {
+		enum pcf21xx_type type = spi_get_device_id(spi)->driver_data;
+
+		if (type >= PCF21XX_LAST_ID)
+			return -ENODEV;
+		variant = &pcf21xx_cfg[type];
+	}
+
+	config.max_register = variant->max_register,
 
 	regmap = devm_regmap_init_spi(spi, &config);
 	if (IS_ERR(regmap)) {
@@ -949,13 +1009,13 @@ static int pcf2127_spi_probe(struct spi_device *spi)
 
 	return pcf2127_probe(&spi->dev, regmap, spi->irq,
 			     pcf2127_spi_driver.driver.name,
-			     spi_get_device_id(spi)->driver_data);
+			     variant);
 }
 
 static const struct spi_device_id pcf2127_spi_id[] = {
-	{ "pcf2127", 1 },
-	{ "pcf2129", 0 },
-	{ "pca2129", 0 },
+	{ "pcf2127", PCF2127 },
+	{ "pcf2129", PCF2129 },
+	{ "pca2129", PCF2129 },
 	{ }
 };
 MODULE_DEVICE_TABLE(spi, pcf2127_spi_id);

From 6211acee8edf4af61f7745a92c4b4cb05a4340f9 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 22 Jun 2023 10:57:49 -0400
Subject: [PATCH 0117/1189] rtc: pcf2127: adapt for time/date registers at any
 offset

This will simplify the implementation of new variants into this driver.

Some variants (PCF2131) have a 100th seconds register. This register is
currently not supported in this driver.

Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20230622145800.2442116-7-hugo@hugovil.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-pcf2127.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index 23ab872c36cb..e65e86e08acc 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -44,7 +44,7 @@
 #define PCF2127_BIT_CTRL3_BF			BIT(3)
 #define PCF2127_BIT_CTRL3_BTSE			BIT(4)
 /* Time and date registers */
-#define PCF2127_REG_SC			0x03
+#define PCF2127_REG_TIME_BASE		0x03
 #define PCF2127_BIT_SC_OSF			BIT(7)
 /* Alarm registers */
 #define PCF2127_REG_ALARM_SC		0x0A
@@ -101,6 +101,7 @@ struct pcf21xx_config {
 	int max_register;
 	unsigned int has_nvmem:1;
 	unsigned int has_bit_wd_ctl_cd0:1;
+	u8 reg_time_base; /* Time/date base register. */
 };
 
 struct pcf2127 {
@@ -127,8 +128,8 @@ static int pcf2127_rtc_read_time(struct device *dev, struct rtc_time *tm)
 	 * Avoid reading CTRL2 register as it causes WD_VAL register
 	 * value to reset to 0 which means watchdog is stopped.
 	 */
-	ret = regmap_bulk_read(pcf2127->regmap, PCF2127_REG_SC, buf,
-			       sizeof(buf));
+	ret = regmap_bulk_read(pcf2127->regmap, pcf2127->cfg->reg_time_base,
+			       buf, sizeof(buf));
 	if (ret) {
 		dev_err(dev, "%s: read error\n", __func__);
 		return ret;
@@ -194,7 +195,7 @@ static int pcf2127_rtc_set_time(struct device *dev, struct rtc_time *tm)
 	buf[i++] = bin2bcd(tm->tm_year - 100);
 
 	/* write register's data */
-	err = regmap_bulk_write(pcf2127->regmap, PCF2127_REG_SC, buf, i);
+	err = regmap_bulk_write(pcf2127->regmap, pcf2127->cfg->reg_time_base, buf, i);
 	if (err) {
 		dev_dbg(dev, "%s: err=%d", __func__, err);
 		return err;
@@ -627,12 +628,14 @@ static struct pcf21xx_config pcf21xx_cfg[] = {
 		.max_register = 0x1d,
 		.has_nvmem = 1,
 		.has_bit_wd_ctl_cd0 = 1,
+		.reg_time_base = PCF2127_REG_TIME_BASE,
 	},
 	[PCF2129] = {
 		.type = PCF2129,
 		.max_register = 0x19,
 		.has_nvmem = 0,
 		.has_bit_wd_ctl_cd0 = 0,
+		.reg_time_base = PCF2127_REG_TIME_BASE,
 	},
 };
 

From 7c6f0db41ab5fbd7ee3a2f9880ac23509a5d55d1 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 22 Jun 2023 10:57:50 -0400
Subject: [PATCH 0118/1189] rtc: pcf2127: adapt for alarm registers at any
 offset

This will simplify the implementation of new variants into this driver.

Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20230622145800.2442116-8-hugo@hugovil.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-pcf2127.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index e65e86e08acc..8849d57c0384 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -47,11 +47,7 @@
 #define PCF2127_REG_TIME_BASE		0x03
 #define PCF2127_BIT_SC_OSF			BIT(7)
 /* Alarm registers */
-#define PCF2127_REG_ALARM_SC		0x0A
-#define PCF2127_REG_ALARM_MN		0x0B
-#define PCF2127_REG_ALARM_HR		0x0C
-#define PCF2127_REG_ALARM_DM		0x0D
-#define PCF2127_REG_ALARM_DW		0x0E
+#define PCF2127_REG_ALARM_BASE		0x0A
 #define PCF2127_BIT_ALARM_AE			BIT(7)
 /* CLKOUT control register */
 #define PCF2127_REG_CLKOUT		0x0f
@@ -102,6 +98,7 @@ struct pcf21xx_config {
 	unsigned int has_nvmem:1;
 	unsigned int has_bit_wd_ctl_cd0:1;
 	u8 reg_time_base; /* Time/date base register. */
+	u8 regs_alarm_base; /* Alarm function base registers. */
 };
 
 struct pcf2127 {
@@ -381,8 +378,8 @@ static int pcf2127_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 	if (ret)
 		return ret;
 
-	ret = regmap_bulk_read(pcf2127->regmap, PCF2127_REG_ALARM_SC, buf,
-			       sizeof(buf));
+	ret = regmap_bulk_read(pcf2127->regmap, pcf2127->cfg->regs_alarm_base,
+			       buf, sizeof(buf));
 	if (ret)
 		return ret;
 
@@ -432,8 +429,8 @@ static int pcf2127_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 	buf[3] = bin2bcd(alrm->time.tm_mday);
 	buf[4] = PCF2127_BIT_ALARM_AE; /* Do not match on week day */
 
-	ret = regmap_bulk_write(pcf2127->regmap, PCF2127_REG_ALARM_SC, buf,
-				sizeof(buf));
+	ret = regmap_bulk_write(pcf2127->regmap, pcf2127->cfg->regs_alarm_base,
+				buf, sizeof(buf));
 	if (ret)
 		return ret;
 
@@ -629,6 +626,7 @@ static struct pcf21xx_config pcf21xx_cfg[] = {
 		.has_nvmem = 1,
 		.has_bit_wd_ctl_cd0 = 1,
 		.reg_time_base = PCF2127_REG_TIME_BASE,
+		.regs_alarm_base = PCF2127_REG_ALARM_BASE,
 	},
 	[PCF2129] = {
 		.type = PCF2129,
@@ -636,6 +634,7 @@ static struct pcf21xx_config pcf21xx_cfg[] = {
 		.has_nvmem = 0,
 		.has_bit_wd_ctl_cd0 = 0,
 		.reg_time_base = PCF2127_REG_TIME_BASE,
+		.regs_alarm_base = PCF2127_REG_ALARM_BASE,
 	},
 };
 

From 6b57ec29e3fc31d43e672f6fede5d4a76140308b Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 22 Jun 2023 10:57:51 -0400
Subject: [PATCH 0119/1189] rtc: pcf2127: adapt for WD registers at any offset

This will simplify the implementation of new variants into this driver.

Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Reviewed-by: Bruno Thomsen <bruno.thomsen@gmail.com>
Tested-by: Bruno Thomsen <bruno.thomsen@gmail.com>
Link: https://lore.kernel.org/r/20230622145800.2442116-9-hugo@hugovil.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-pcf2127.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index 8849d57c0384..fb1b2b89e909 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -99,6 +99,8 @@ struct pcf21xx_config {
 	unsigned int has_bit_wd_ctl_cd0:1;
 	u8 reg_time_base; /* Time/date base register. */
 	u8 regs_alarm_base; /* Alarm function base registers. */
+	u8 reg_wd_ctl; /* Watchdog control register. */
+	u8 reg_wd_val; /* Watchdog value register. */
 };
 
 struct pcf2127 {
@@ -269,7 +271,7 @@ static int pcf2127_wdt_ping(struct watchdog_device *wdd)
 {
 	struct pcf2127 *pcf2127 = watchdog_get_drvdata(wdd);
 
-	return regmap_write(pcf2127->regmap, PCF2127_REG_WD_VAL, wdd->timeout);
+	return regmap_write(pcf2127->regmap, pcf2127->cfg->reg_wd_val, wdd->timeout);
 }
 
 /*
@@ -303,7 +305,7 @@ static int pcf2127_wdt_stop(struct watchdog_device *wdd)
 {
 	struct pcf2127 *pcf2127 = watchdog_get_drvdata(wdd);
 
-	return regmap_write(pcf2127->regmap, PCF2127_REG_WD_VAL,
+	return regmap_write(pcf2127->regmap, pcf2127->cfg->reg_wd_val,
 			    PCF2127_WD_VAL_STOP);
 }
 
@@ -352,7 +354,7 @@ static int pcf2127_watchdog_init(struct device *dev, struct pcf2127 *pcf2127)
 	watchdog_set_drvdata(&pcf2127->wdd, pcf2127);
 
 	/* Test if watchdog timer is started by bootloader */
-	ret = regmap_read(pcf2127->regmap, PCF2127_REG_WD_VAL, &wdd_timeout);
+	ret = regmap_read(pcf2127->regmap, pcf2127->cfg->reg_wd_val, &wdd_timeout);
 	if (ret)
 		return ret;
 
@@ -627,6 +629,8 @@ static struct pcf21xx_config pcf21xx_cfg[] = {
 		.has_bit_wd_ctl_cd0 = 1,
 		.reg_time_base = PCF2127_REG_TIME_BASE,
 		.regs_alarm_base = PCF2127_REG_ALARM_BASE,
+		.reg_wd_ctl = PCF2127_REG_WD_CTL,
+		.reg_wd_val = PCF2127_REG_WD_VAL,
 	},
 	[PCF2129] = {
 		.type = PCF2129,
@@ -635,6 +639,8 @@ static struct pcf21xx_config pcf21xx_cfg[] = {
 		.has_bit_wd_ctl_cd0 = 0,
 		.reg_time_base = PCF2127_REG_TIME_BASE,
 		.regs_alarm_base = PCF2127_REG_ALARM_BASE,
+		.reg_wd_ctl = PCF2127_REG_WD_CTL,
+		.reg_wd_val = PCF2127_REG_WD_VAL,
 	},
 };
 
@@ -736,7 +742,7 @@ static int pcf2127_probe(struct device *dev, struct regmap *regmap,
 	 * as T. Bits labeled as T must always be written with
 	 * logic 0.
 	 */
-	ret = regmap_update_bits(pcf2127->regmap, PCF2127_REG_WD_CTL,
+	ret = regmap_update_bits(pcf2127->regmap, pcf2127->cfg->reg_wd_ctl,
 				 PCF2127_BIT_WD_CTL_CD1 |
 				 PCF2127_BIT_WD_CTL_CD0 |
 				 PCF2127_BIT_WD_CTL_TF1 |

From fc16599e0153e91ba12d856e40f6fc56906077f1 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 22 Jun 2023 10:57:52 -0400
Subject: [PATCH 0120/1189] rtc: pcf2127: adapt for CLKOUT register at any
 offset

This will simplify the implementation of new variants into this driver.

Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Reviewed-by: Bruno Thomsen <bruno.thomsen@gmail.com>
Link: https://lore.kernel.org/r/20230622145800.2442116-10-hugo@hugovil.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-pcf2127.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index fb1b2b89e909..c4c0bf574e6b 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -101,6 +101,7 @@ struct pcf21xx_config {
 	u8 regs_alarm_base; /* Alarm function base registers. */
 	u8 reg_wd_ctl; /* Watchdog control register. */
 	u8 reg_wd_val; /* Watchdog value register. */
+	u8 reg_clkout; /* Clkout register. */
 };
 
 struct pcf2127 {
@@ -631,6 +632,7 @@ static struct pcf21xx_config pcf21xx_cfg[] = {
 		.regs_alarm_base = PCF2127_REG_ALARM_BASE,
 		.reg_wd_ctl = PCF2127_REG_WD_CTL,
 		.reg_wd_val = PCF2127_REG_WD_VAL,
+		.reg_clkout = PCF2127_REG_CLKOUT,
 	},
 	[PCF2129] = {
 		.type = PCF2129,
@@ -641,6 +643,7 @@ static struct pcf21xx_config pcf21xx_cfg[] = {
 		.regs_alarm_base = PCF2127_REG_ALARM_BASE,
 		.reg_wd_ctl = PCF2127_REG_WD_CTL,
 		.reg_wd_val = PCF2127_REG_WD_VAL,
+		.reg_clkout = PCF2127_REG_CLKOUT,
 	},
 };
 
@@ -720,12 +723,12 @@ static int pcf2127_probe(struct device *dev, struct regmap *regmap,
 	regmap_clear_bits(pcf2127->regmap, PCF2127_REG_CTRL1,
 				PCF2127_BIT_CTRL1_POR_OVRD);
 
-	ret = regmap_read(pcf2127->regmap, PCF2127_REG_CLKOUT, &val);
+	ret = regmap_read(pcf2127->regmap, pcf2127->cfg->reg_clkout, &val);
 	if (ret < 0)
 		return ret;
 
 	if (!(val & PCF2127_BIT_CLKOUT_OTPR)) {
-		ret = regmap_set_bits(pcf2127->regmap, PCF2127_REG_CLKOUT,
+		ret = regmap_set_bits(pcf2127->regmap, pcf2127->cfg->reg_clkout,
 				      PCF2127_BIT_CLKOUT_OTPR);
 		if (ret < 0)
 			return ret;

From 420cc9e850dbc8e6ea7dd1e53d62d64cd8766354 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 22 Jun 2023 10:57:53 -0400
Subject: [PATCH 0121/1189] rtc: pcf2127: add support for multiple TS functions

This will simplify the implementation of new variants into this driver.

Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20230622145800.2442116-11-hugo@hugovil.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-pcf2127.c | 272 ++++++++++++++++++++++++++++----------
 1 file changed, 203 insertions(+), 69 deletions(-)

diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index c4c0bf574e6b..9d91cff173cf 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -59,8 +59,8 @@
 #define PCF2127_BIT_WD_CTL_CD0			BIT(6)
 #define PCF2127_BIT_WD_CTL_CD1			BIT(7)
 #define PCF2127_REG_WD_VAL		0x11
-/* Tamper timestamp registers */
-#define PCF2127_REG_TS_CTRL		0x12
+/* Tamper timestamp1 registers */
+#define PCF2127_REG_TS1_BASE		0x12
 #define PCF2127_BIT_TS_CTRL_TSOFF		BIT(6)
 #define PCF2127_BIT_TS_CTRL_TSM			BIT(7)
 /*
@@ -86,12 +86,36 @@
 		PCF2127_BIT_CTRL2_WDTF | \
 		PCF2127_BIT_CTRL2_TSF2)
 
+#define PCF2127_MAX_TS_SUPPORTED	1
+
 enum pcf21xx_type {
 	PCF2127,
 	PCF2129,
 	PCF21XX_LAST_ID
 };
 
+struct pcf21xx_ts_config {
+	u8 reg_base; /* Base register to read timestamp values. */
+
+	/*
+	 * If the TS input pin is driven to GND, an interrupt can be generated
+	 * (supported by all variants).
+	 */
+	u8 gnd_detect_reg; /* Interrupt control register address. */
+	u8 gnd_detect_bit; /* Interrupt bit. */
+
+	/*
+	 * If the TS input pin is driven to an intermediate level between GND
+	 * and supply, an interrupt can be generated (optional feature depending
+	 * on variant).
+	 */
+	u8 inter_detect_reg; /* Interrupt control register address. */
+	u8 inter_detect_bit; /* Interrupt bit. */
+
+	u8 ie_reg; /* Interrupt enable control register. */
+	u8 ie_bit; /* Interrupt enable bit. */
+};
+
 struct pcf21xx_config {
 	int type; /* IC variant */
 	int max_register;
@@ -102,6 +126,9 @@ struct pcf21xx_config {
 	u8 reg_wd_ctl; /* Watchdog control register. */
 	u8 reg_wd_val; /* Watchdog value register. */
 	u8 reg_clkout; /* Clkout register. */
+	unsigned int ts_count;
+	struct pcf21xx_ts_config ts[PCF2127_MAX_TS_SUPPORTED];
+	struct attribute_group attribute_group;
 };
 
 struct pcf2127 {
@@ -109,9 +136,9 @@ struct pcf2127 {
 	struct watchdog_device wdd;
 	struct regmap *regmap;
 	const struct pcf21xx_config *cfg;
-	time64_t ts;
-	bool ts_valid;
 	bool irq_enabled;
+	time64_t ts[PCF2127_MAX_TS_SUPPORTED]; /* Timestamp values. */
+	bool ts_valid[PCF2127_MAX_TS_SUPPORTED];  /* Timestamp valid indication. */
 };
 
 /*
@@ -441,18 +468,19 @@ static int pcf2127_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 }
 
 /*
- * This function reads ctrl2 register, caller is responsible for calling
- * pcf2127_wdt_active_ping()
+ * This function reads one timestamp function data, caller is responsible for
+ * calling pcf2127_wdt_active_ping()
  */
-static int pcf2127_rtc_ts_read(struct device *dev, time64_t *ts)
+static int pcf2127_rtc_ts_read(struct device *dev, time64_t *ts,
+			       int ts_id)
 {
 	struct pcf2127 *pcf2127 = dev_get_drvdata(dev);
 	struct rtc_time tm;
 	int ret;
 	unsigned char data[7];
 
-	ret = regmap_bulk_read(pcf2127->regmap, PCF2127_REG_TS_CTRL, data,
-			       sizeof(data));
+	ret = regmap_bulk_read(pcf2127->regmap, pcf2127->cfg->ts[ts_id].reg_base,
+			       data, sizeof(data));
 	if (ret) {
 		dev_err(dev, "%s: read error ret=%d\n", __func__, ret);
 		return ret;
@@ -482,18 +510,21 @@ static int pcf2127_rtc_ts_read(struct device *dev, time64_t *ts)
 	return 0;
 };
 
-static void pcf2127_rtc_ts_snapshot(struct device *dev)
+static void pcf2127_rtc_ts_snapshot(struct device *dev, int ts_id)
 {
 	struct pcf2127 *pcf2127 = dev_get_drvdata(dev);
 	int ret;
 
-	/* Let userspace read the first timestamp */
-	if (pcf2127->ts_valid)
+	if (ts_id >= pcf2127->cfg->ts_count)
 		return;
 
-	ret = pcf2127_rtc_ts_read(dev, &pcf2127->ts);
+	/* Let userspace read the first timestamp */
+	if (pcf2127->ts_valid[ts_id])
+		return;
+
+	ret = pcf2127_rtc_ts_read(dev, &pcf2127->ts[ts_id], ts_id);
 	if (!ret)
-		pcf2127->ts_valid = true;
+		pcf2127->ts_valid[ts_id] = true;
 }
 
 static irqreturn_t pcf2127_rtc_irq(int irq, void *dev)
@@ -514,7 +545,7 @@ static irqreturn_t pcf2127_rtc_irq(int irq, void *dev)
 		return IRQ_NONE;
 
 	if (ctrl1 & PCF2127_BIT_CTRL1_TSF1 || ctrl2 & PCF2127_BIT_CTRL2_TSF2)
-		pcf2127_rtc_ts_snapshot(dev);
+		pcf2127_rtc_ts_snapshot(dev, 0);
 
 	if (ctrl1 & PCF2127_CTRL1_IRQ_MASK)
 		regmap_write(pcf2127->regmap, PCF2127_REG_CTRL1,
@@ -543,28 +574,41 @@ static const struct rtc_class_ops pcf2127_rtc_ops = {
 
 /* sysfs interface */
 
-static ssize_t timestamp0_store(struct device *dev,
-				struct device_attribute *attr,
-				const char *buf, size_t count)
+static ssize_t timestamp_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf, size_t count, int ts_id)
 {
 	struct pcf2127 *pcf2127 = dev_get_drvdata(dev->parent);
 	int ret;
 
+	if (ts_id >= pcf2127->cfg->ts_count)
+		return 0;
+
 	if (pcf2127->irq_enabled) {
-		pcf2127->ts_valid = false;
+		pcf2127->ts_valid[ts_id] = false;
 	} else {
-		ret = regmap_update_bits(pcf2127->regmap, PCF2127_REG_CTRL1,
-			PCF2127_BIT_CTRL1_TSF1, 0);
+		/* Always clear GND interrupt bit. */
+		ret = regmap_update_bits(pcf2127->regmap,
+					 pcf2127->cfg->ts[ts_id].gnd_detect_reg,
+					 pcf2127->cfg->ts[ts_id].gnd_detect_bit,
+					 0);
+
 		if (ret) {
-			dev_err(dev, "%s: update ctrl1 ret=%d\n", __func__, ret);
+			dev_err(dev, "%s: update TS gnd detect ret=%d\n", __func__, ret);
 			return ret;
 		}
 
-		ret = regmap_update_bits(pcf2127->regmap, PCF2127_REG_CTRL2,
-			PCF2127_BIT_CTRL2_TSF2, 0);
-		if (ret) {
-			dev_err(dev, "%s: update ctrl2 ret=%d\n", __func__, ret);
-			return ret;
+		if (pcf2127->cfg->ts[ts_id].inter_detect_bit) {
+			/* Clear intermediate level interrupt bit if supported. */
+			ret = regmap_update_bits(pcf2127->regmap,
+						 pcf2127->cfg->ts[ts_id].inter_detect_reg,
+						 pcf2127->cfg->ts[ts_id].inter_detect_bit,
+						 0);
+			if (ret) {
+				dev_err(dev, "%s: update TS intermediate level detect ret=%d\n",
+					__func__, ret);
+				return ret;
+			}
 		}
 
 		ret = pcf2127_wdt_active_ping(&pcf2127->wdd);
@@ -573,34 +617,63 @@ static ssize_t timestamp0_store(struct device *dev,
 	}
 
 	return count;
+}
+
+static ssize_t timestamp0_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t count)
+{
+	return timestamp_store(dev, attr, buf, count, 0);
 };
 
-static ssize_t timestamp0_show(struct device *dev,
-			       struct device_attribute *attr, char *buf)
+static ssize_t timestamp_show(struct device *dev,
+			      struct device_attribute *attr, char *buf,
+			      int ts_id)
 {
 	struct pcf2127 *pcf2127 = dev_get_drvdata(dev->parent);
-	unsigned int ctrl1, ctrl2;
 	int ret;
 	time64_t ts;
 
+	if (ts_id >= pcf2127->cfg->ts_count)
+		return 0;
+
 	if (pcf2127->irq_enabled) {
-		if (!pcf2127->ts_valid)
+		if (!pcf2127->ts_valid[ts_id])
 			return 0;
-		ts = pcf2127->ts;
+		ts = pcf2127->ts[ts_id];
 	} else {
-		ret = regmap_read(pcf2127->regmap, PCF2127_REG_CTRL1, &ctrl1);
+		u8 valid_low = 0;
+		u8 valid_inter = 0;
+		unsigned int ctrl;
+
+		/* Check if TS input pin is driven to GND, supported by all
+		 * variants.
+		 */
+		ret = regmap_read(pcf2127->regmap,
+				  pcf2127->cfg->ts[ts_id].gnd_detect_reg,
+				  &ctrl);
 		if (ret)
 			return 0;
 
-		ret = regmap_read(pcf2127->regmap, PCF2127_REG_CTRL2, &ctrl2);
-		if (ret)
+		valid_low = ctrl & pcf2127->cfg->ts[ts_id].gnd_detect_bit;
+
+		if (pcf2127->cfg->ts[ts_id].inter_detect_bit) {
+			/* Check if TS input pin is driven to intermediate level
+			 * between GND and supply, if supported by variant.
+			 */
+			ret = regmap_read(pcf2127->regmap,
+					  pcf2127->cfg->ts[ts_id].inter_detect_reg,
+					  &ctrl);
+			if (ret)
+				return 0;
+
+			valid_inter = ctrl & pcf2127->cfg->ts[ts_id].inter_detect_bit;
+		}
+
+		if (!valid_low && !valid_inter)
 			return 0;
 
-		if (!(ctrl1 & PCF2127_BIT_CTRL1_TSF1) &&
-		    !(ctrl2 & PCF2127_BIT_CTRL2_TSF2))
-			return 0;
-
-		ret = pcf2127_rtc_ts_read(dev->parent, &ts);
+		ret = pcf2127_rtc_ts_read(dev->parent, &ts, ts_id);
 		if (ret)
 			return 0;
 
@@ -609,6 +682,12 @@ static ssize_t timestamp0_show(struct device *dev,
 			return ret;
 	}
 	return sprintf(buf, "%llu\n", (unsigned long long)ts);
+}
+
+static ssize_t timestamp0_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	return timestamp_show(dev, attr, buf, 0);
 };
 
 static DEVICE_ATTR_RW(timestamp0);
@@ -618,10 +697,6 @@ static struct attribute *pcf2127_attrs[] = {
 	NULL
 };
 
-static const struct attribute_group pcf2127_attr_group = {
-	.attrs	= pcf2127_attrs,
-};
-
 static struct pcf21xx_config pcf21xx_cfg[] = {
 	[PCF2127] = {
 		.type = PCF2127,
@@ -633,6 +708,19 @@ static struct pcf21xx_config pcf21xx_cfg[] = {
 		.reg_wd_ctl = PCF2127_REG_WD_CTL,
 		.reg_wd_val = PCF2127_REG_WD_VAL,
 		.reg_clkout = PCF2127_REG_CLKOUT,
+		.ts_count = 1,
+		.ts[0] = {
+			.reg_base  = PCF2127_REG_TS1_BASE,
+			.gnd_detect_reg = PCF2127_REG_CTRL1,
+			.gnd_detect_bit = PCF2127_BIT_CTRL1_TSF1,
+			.inter_detect_reg = PCF2127_REG_CTRL2,
+			.inter_detect_bit = PCF2127_BIT_CTRL2_TSF2,
+			.ie_reg    = PCF2127_REG_CTRL2,
+			.ie_bit    = PCF2127_BIT_CTRL2_TSIE,
+		},
+		.attribute_group = {
+			.attrs	= pcf2127_attrs,
+		},
 	},
 	[PCF2129] = {
 		.type = PCF2129,
@@ -644,9 +732,74 @@ static struct pcf21xx_config pcf21xx_cfg[] = {
 		.reg_wd_ctl = PCF2127_REG_WD_CTL,
 		.reg_wd_val = PCF2127_REG_WD_VAL,
 		.reg_clkout = PCF2127_REG_CLKOUT,
+		.ts_count = 1,
+		.ts[0] = {
+			.reg_base  = PCF2127_REG_TS1_BASE,
+			.gnd_detect_reg = PCF2127_REG_CTRL1,
+			.gnd_detect_bit = PCF2127_BIT_CTRL1_TSF1,
+			.inter_detect_reg = PCF2127_REG_CTRL2,
+			.inter_detect_bit = PCF2127_BIT_CTRL2_TSF2,
+			.ie_reg    = PCF2127_REG_CTRL2,
+			.ie_bit    = PCF2127_BIT_CTRL2_TSIE,
+		},
+		.attribute_group = {
+			.attrs	= pcf2127_attrs,
+		},
 	},
 };
 
+/*
+ * Enable timestamp function and corresponding interrupt(s).
+ */
+static int pcf2127_enable_ts(struct device *dev, int ts_id)
+{
+	struct pcf2127 *pcf2127 = dev_get_drvdata(dev);
+	int ret;
+
+	if (ts_id >= pcf2127->cfg->ts_count) {
+		dev_err(dev, "%s: invalid tamper detection ID (%d)\n",
+			__func__, ts_id);
+		return -EINVAL;
+	}
+
+	/* Enable timestamp function. */
+	ret = regmap_update_bits(pcf2127->regmap,
+				 pcf2127->cfg->ts[ts_id].reg_base,
+				 PCF2127_BIT_TS_CTRL_TSOFF |
+				 PCF2127_BIT_TS_CTRL_TSM,
+				 PCF2127_BIT_TS_CTRL_TSM);
+	if (ret) {
+		dev_err(dev, "%s: tamper detection config (ts%d_ctrl) failed\n",
+			__func__, ts_id);
+		return ret;
+	}
+
+	/* TS input pin driven to GND detection is supported by all variants.
+	 * Make sure that interrupt bit is defined.
+	 */
+	if (pcf2127->cfg->ts[ts_id].gnd_detect_bit == 0) {
+		dev_err(dev, "%s: tamper detection to GND configuration invalid\n",
+			__func__);
+		return ret;
+	}
+
+	/*
+	 * Enable interrupt generation when TSF timestamp flag is set.
+	 * Interrupt signals are open-drain outputs and can be left floating if
+	 * unused.
+	 */
+	ret = regmap_update_bits(pcf2127->regmap, pcf2127->cfg->ts[ts_id].ie_reg,
+				 pcf2127->cfg->ts[ts_id].ie_bit,
+				 pcf2127->cfg->ts[ts_id].ie_bit);
+	if (ret) {
+		dev_err(dev, "%s: tamper detection TSIE%d config failed\n",
+			__func__, ts_id);
+		return ret;
+	}
+
+	return ret;
+}
+
 static int pcf2127_probe(struct device *dev, struct regmap *regmap,
 			 int alarm_irq, const char *name, const struct pcf21xx_config *config)
 {
@@ -777,34 +930,15 @@ static int pcf2127_probe(struct device *dev, struct regmap *regmap,
 	}
 
 	/*
-	 * Enable timestamp function and store timestamp of first trigger
-	 * event until TSF1 and TSF2 interrupt flags are cleared.
+	 * Enable timestamp functions 1 to 4.
 	 */
-	ret = regmap_update_bits(pcf2127->regmap, PCF2127_REG_TS_CTRL,
-				 PCF2127_BIT_TS_CTRL_TSOFF |
-				 PCF2127_BIT_TS_CTRL_TSM,
-				 PCF2127_BIT_TS_CTRL_TSM);
-	if (ret) {
-		dev_err(dev, "%s: tamper detection config (ts_ctrl) failed\n",
-			__func__);
-		return ret;
+	for (int i = 0; i < pcf2127->cfg->ts_count; i++) {
+		ret = pcf2127_enable_ts(dev, i);
+		if (ret)
+			return ret;
 	}
 
-	/*
-	 * Enable interrupt generation when TSF1 or TSF2 timestamp flags
-	 * are set. Interrupt signal is an open-drain output and can be
-	 * left floating if unused.
-	 */
-	ret = regmap_update_bits(pcf2127->regmap, PCF2127_REG_CTRL2,
-				 PCF2127_BIT_CTRL2_TSIE,
-				 PCF2127_BIT_CTRL2_TSIE);
-	if (ret) {
-		dev_err(dev, "%s: tamper detection config (ctrl2) failed\n",
-			__func__);
-		return ret;
-	}
-
-	ret = rtc_add_group(pcf2127->rtc, &pcf2127_attr_group);
+	ret = rtc_add_group(pcf2127->rtc, &pcf2127->cfg->attribute_group);
 	if (ret) {
 		dev_err(dev, "%s: tamper sysfs registering failed\n",
 			__func__);

From afc505bf9039caf5a377d8b9705ef42f6d4ac7d4 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 22 Jun 2023 10:57:54 -0400
Subject: [PATCH 0122/1189] rtc: pcf2127: add support for PCF2131 RTC

This RTC is very similar in functionality to the PCF2127/29.

Basically it:
  -supports two new control registers at offsets 4 and 5
  -supports a new reset register (not implemented in this driver)
  -supports 4 tamper detection functions instead of 1
  -has no nvmem (like the PCF2129)
  -has two output interrupt pins

Because of that, most of the register addresses are very different,
although they still follow the same layout. For example, the tamper
registers have a different base address, but the offsets are all the same.

Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20230622145800.2442116-12-hugo@hugovil.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/Kconfig       |   4 +-
 drivers/rtc/rtc-pcf2127.c | 234 ++++++++++++++++++++++++++++++++++----
 2 files changed, 215 insertions(+), 23 deletions(-)

diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 05f4b2d66290..e8bad8c93ba9 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -904,9 +904,9 @@ config RTC_DRV_PCF2127
 	select REGMAP_SPI if SPI_MASTER
 	select WATCHDOG_CORE if WATCHDOG
 	help
-	  If you say yes here you get support for the NXP PCF2127/29 RTC
+	  If you say yes here you get support for the NXP PCF2127/29/31 RTC
 	  chips with integrated quartz crystal for industrial applications.
-	  Both chips also have watchdog timer and tamper switch detection
+	  These chips also have watchdog timer and tamper switch detection
 	  features.
 
 	  PCF2127 has an additional feature of 512 bytes battery backed
diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index 9d91cff173cf..8c2ad9eac861 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * An I2C and SPI driver for the NXP PCF2127/29 RTC
+ * An I2C and SPI driver for the NXP PCF2127/29/31 RTC
  * Copyright 2013 Til-Technologies
  *
  * Author: Renaud Cerrato <r.cerrato@til-technologies.fr>
@@ -8,9 +8,13 @@
  * Watchdog and tamper functions
  * Author: Bruno Thomsen <bruno.thomsen@gmail.com>
  *
+ * PCF2131 support
+ * Author: Hugo Villeneuve <hvilleneuve@dimonoff.com>
+ *
  * based on the other drivers in this same directory.
  *
- * Datasheet: https://www.nxp.com/docs/en/data-sheet/PCF2127.pdf
+ * Datasheets: https://www.nxp.com/docs/en/data-sheet/PCF2127.pdf
+ *             https://www.nxp.com/docs/en/data-sheet/PCF2131DS.pdf
  */
 
 #include <linux/i2c.h>
@@ -67,7 +71,7 @@
  * RAM registers
  * PCF2127 has 512 bytes general-purpose static RAM (SRAM) that is
  * battery backed and can survive a power outage.
- * PCF2129 doesn't have this feature.
+ * PCF2129/31 doesn't have this feature.
  */
 #define PCF2127_REG_RAM_ADDR_MSB	0x1A
 #define PCF2127_REG_RAM_WRT_CMD		0x1C
@@ -86,11 +90,65 @@
 		PCF2127_BIT_CTRL2_WDTF | \
 		PCF2127_BIT_CTRL2_TSF2)
 
-#define PCF2127_MAX_TS_SUPPORTED	1
+#define PCF2127_MAX_TS_SUPPORTED	4
+
+/* Control register 4 */
+#define PCF2131_REG_CTRL4		0x03
+#define PCF2131_BIT_CTRL4_TSF4			BIT(4)
+#define PCF2131_BIT_CTRL4_TSF3			BIT(5)
+#define PCF2131_BIT_CTRL4_TSF2			BIT(6)
+#define PCF2131_BIT_CTRL4_TSF1			BIT(7)
+/* Control register 5 */
+#define PCF2131_REG_CTRL5		0x04
+#define PCF2131_BIT_CTRL5_TSIE4			BIT(4)
+#define PCF2131_BIT_CTRL5_TSIE3			BIT(5)
+#define PCF2131_BIT_CTRL5_TSIE2			BIT(6)
+#define PCF2131_BIT_CTRL5_TSIE1			BIT(7)
+/* Software reset register */
+#define PCF2131_REG_SR_RESET		0x05
+#define PCF2131_SR_RESET_READ_PATTERN	(BIT(2) | BIT(5))
+#define PCF2131_SR_RESET_CPR_CMD	(PCF2131_SR_RESET_READ_PATTERN | BIT(7))
+/* Time and date registers */
+#define PCF2131_REG_TIME_BASE		0x07
+/* Alarm registers */
+#define PCF2131_REG_ALARM_BASE		0x0E
+/* CLKOUT control register */
+#define PCF2131_REG_CLKOUT		0x13
+/* Watchdog registers */
+#define PCF2131_REG_WD_CTL		0x35
+#define PCF2131_REG_WD_VAL		0x36
+/* Tamper timestamp1 registers */
+#define PCF2131_REG_TS1_BASE		0x14
+/* Tamper timestamp2 registers */
+#define PCF2131_REG_TS2_BASE		0x1B
+/* Tamper timestamp3 registers */
+#define PCF2131_REG_TS3_BASE		0x22
+/* Tamper timestamp4 registers */
+#define PCF2131_REG_TS4_BASE		0x29
+/* Interrupt mask registers */
+#define PCF2131_REG_INT_A_MASK1		0x31
+#define PCF2131_REG_INT_A_MASK2		0x32
+#define PCF2131_REG_INT_B_MASK1		0x33
+#define PCF2131_REG_INT_B_MASK2		0x34
+#define PCF2131_BIT_INT_BLIE		BIT(0)
+#define PCF2131_BIT_INT_BIE		BIT(1)
+#define PCF2131_BIT_INT_AIE		BIT(2)
+#define PCF2131_BIT_INT_WD_CD		BIT(3)
+#define PCF2131_BIT_INT_SI		BIT(4)
+#define PCF2131_BIT_INT_MI		BIT(5)
+#define PCF2131_CTRL2_IRQ_MASK ( \
+		PCF2127_BIT_CTRL2_AF | \
+		PCF2127_BIT_CTRL2_WDTF)
+#define PCF2131_CTRL4_IRQ_MASK ( \
+		PCF2131_BIT_CTRL4_TSF4 | \
+		PCF2131_BIT_CTRL4_TSF3 | \
+		PCF2131_BIT_CTRL4_TSF2 | \
+		PCF2131_BIT_CTRL4_TSF1)
 
 enum pcf21xx_type {
 	PCF2127,
 	PCF2129,
+	PCF2131,
 	PCF21XX_LAST_ID
 };
 
@@ -530,30 +588,64 @@ static void pcf2127_rtc_ts_snapshot(struct device *dev, int ts_id)
 static irqreturn_t pcf2127_rtc_irq(int irq, void *dev)
 {
 	struct pcf2127 *pcf2127 = dev_get_drvdata(dev);
-	unsigned int ctrl1, ctrl2;
+	unsigned int ctrl2;
 	int ret = 0;
 
-	ret = regmap_read(pcf2127->regmap, PCF2127_REG_CTRL1, &ctrl1);
-	if (ret)
-		return IRQ_NONE;
-
 	ret = regmap_read(pcf2127->regmap, PCF2127_REG_CTRL2, &ctrl2);
 	if (ret)
 		return IRQ_NONE;
 
-	if (!(ctrl1 & PCF2127_CTRL1_IRQ_MASK || ctrl2 & PCF2127_CTRL2_IRQ_MASK))
-		return IRQ_NONE;
+	if (pcf2127->cfg->ts_count == 1) {
+		/* PCF2127/29 */
+		unsigned int ctrl1;
 
-	if (ctrl1 & PCF2127_BIT_CTRL1_TSF1 || ctrl2 & PCF2127_BIT_CTRL2_TSF2)
-		pcf2127_rtc_ts_snapshot(dev, 0);
+		ret = regmap_read(pcf2127->regmap, PCF2127_REG_CTRL1, &ctrl1);
+		if (ret)
+			return IRQ_NONE;
 
-	if (ctrl1 & PCF2127_CTRL1_IRQ_MASK)
-		regmap_write(pcf2127->regmap, PCF2127_REG_CTRL1,
-			ctrl1 & ~PCF2127_CTRL1_IRQ_MASK);
+		if (!(ctrl1 & PCF2127_CTRL1_IRQ_MASK || ctrl2 & PCF2127_CTRL2_IRQ_MASK))
+			return IRQ_NONE;
 
-	if (ctrl2 & PCF2127_CTRL2_IRQ_MASK)
-		regmap_write(pcf2127->regmap, PCF2127_REG_CTRL2,
-			ctrl2 & ~PCF2127_CTRL2_IRQ_MASK);
+		if (ctrl1 & PCF2127_BIT_CTRL1_TSF1 || ctrl2 & PCF2127_BIT_CTRL2_TSF2)
+			pcf2127_rtc_ts_snapshot(dev, 0);
+
+		if (ctrl1 & PCF2127_CTRL1_IRQ_MASK)
+			regmap_write(pcf2127->regmap, PCF2127_REG_CTRL1,
+				     ctrl1 & ~PCF2127_CTRL1_IRQ_MASK);
+
+		if (ctrl2 & PCF2127_CTRL2_IRQ_MASK)
+			regmap_write(pcf2127->regmap, PCF2127_REG_CTRL2,
+				     ctrl2 & ~PCF2127_CTRL2_IRQ_MASK);
+	} else {
+		/* PCF2131. */
+		unsigned int ctrl4;
+
+		ret = regmap_read(pcf2127->regmap, PCF2131_REG_CTRL4, &ctrl4);
+		if (ret)
+			return IRQ_NONE;
+
+		if (!(ctrl4 & PCF2131_CTRL4_IRQ_MASK || ctrl2 & PCF2131_CTRL2_IRQ_MASK))
+			return IRQ_NONE;
+
+		if (ctrl4 & PCF2131_CTRL4_IRQ_MASK) {
+			int i;
+			int tsf_bit = PCF2131_BIT_CTRL4_TSF1; /* Start at bit 7. */
+
+			for (i = 0; i < pcf2127->cfg->ts_count; i++) {
+				if (ctrl4 & tsf_bit)
+					pcf2127_rtc_ts_snapshot(dev, i);
+
+				tsf_bit = tsf_bit >> 1;
+			}
+
+			regmap_write(pcf2127->regmap, PCF2131_REG_CTRL4,
+				     ctrl4 & ~PCF2131_CTRL4_IRQ_MASK);
+		}
+
+		if (ctrl2 & PCF2131_CTRL2_IRQ_MASK)
+			regmap_write(pcf2127->regmap, PCF2127_REG_CTRL2,
+				     ctrl2 & ~PCF2131_CTRL2_IRQ_MASK);
+	}
 
 	if (ctrl2 & PCF2127_BIT_CTRL2_AF)
 		rtc_update_irq(pcf2127->rtc, 1, RTC_IRQF | RTC_AF);
@@ -626,6 +718,27 @@ static ssize_t timestamp0_store(struct device *dev,
 	return timestamp_store(dev, attr, buf, count, 0);
 };
 
+static ssize_t timestamp1_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t count)
+{
+	return timestamp_store(dev, attr, buf, count, 1);
+};
+
+static ssize_t timestamp2_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t count)
+{
+	return timestamp_store(dev, attr, buf, count, 2);
+};
+
+static ssize_t timestamp3_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t count)
+{
+	return timestamp_store(dev, attr, buf, count, 3);
+};
+
 static ssize_t timestamp_show(struct device *dev,
 			      struct device_attribute *attr, char *buf,
 			      int ts_id)
@@ -690,13 +803,42 @@ static ssize_t timestamp0_show(struct device *dev,
 	return timestamp_show(dev, attr, buf, 0);
 };
 
+static ssize_t timestamp1_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	return timestamp_show(dev, attr, buf, 1);
+};
+
+static ssize_t timestamp2_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	return timestamp_show(dev, attr, buf, 2);
+};
+
+static ssize_t timestamp3_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	return timestamp_show(dev, attr, buf, 3);
+};
+
 static DEVICE_ATTR_RW(timestamp0);
+static DEVICE_ATTR_RW(timestamp1);
+static DEVICE_ATTR_RW(timestamp2);
+static DEVICE_ATTR_RW(timestamp3);
 
 static struct attribute *pcf2127_attrs[] = {
 	&dev_attr_timestamp0.attr,
 	NULL
 };
 
+static struct attribute *pcf2131_attrs[] = {
+	&dev_attr_timestamp0.attr,
+	&dev_attr_timestamp1.attr,
+	&dev_attr_timestamp2.attr,
+	&dev_attr_timestamp3.attr,
+	NULL
+};
+
 static struct pcf21xx_config pcf21xx_cfg[] = {
 	[PCF2127] = {
 		.type = PCF2127,
@@ -746,6 +888,53 @@ static struct pcf21xx_config pcf21xx_cfg[] = {
 			.attrs	= pcf2127_attrs,
 		},
 	},
+	[PCF2131] = {
+		.type = PCF2131,
+		.max_register = 0x36,
+		.has_nvmem = 0,
+		.has_bit_wd_ctl_cd0 = 0,
+		.reg_time_base = PCF2131_REG_TIME_BASE,
+		.regs_alarm_base = PCF2131_REG_ALARM_BASE,
+		.reg_wd_ctl = PCF2131_REG_WD_CTL,
+		.reg_wd_val = PCF2131_REG_WD_VAL,
+		.reg_clkout = PCF2131_REG_CLKOUT,
+		.ts_count = 4,
+		.ts[0] = {
+			.reg_base  = PCF2131_REG_TS1_BASE,
+			.gnd_detect_reg = PCF2131_REG_CTRL4,
+			.gnd_detect_bit = PCF2131_BIT_CTRL4_TSF1,
+			.inter_detect_bit = 0,
+			.ie_reg    = PCF2131_REG_CTRL5,
+			.ie_bit    = PCF2131_BIT_CTRL5_TSIE1,
+		},
+		.ts[1] = {
+			.reg_base  = PCF2131_REG_TS2_BASE,
+			.gnd_detect_reg = PCF2131_REG_CTRL4,
+			.gnd_detect_bit = PCF2131_BIT_CTRL4_TSF2,
+			.inter_detect_bit = 0,
+			.ie_reg    = PCF2131_REG_CTRL5,
+			.ie_bit    = PCF2131_BIT_CTRL5_TSIE2,
+		},
+		.ts[2] = {
+			.reg_base  = PCF2131_REG_TS3_BASE,
+			.gnd_detect_reg = PCF2131_REG_CTRL4,
+			.gnd_detect_bit = PCF2131_BIT_CTRL4_TSF3,
+			.inter_detect_bit = 0,
+			.ie_reg    = PCF2131_REG_CTRL5,
+			.ie_bit    = PCF2131_BIT_CTRL5_TSIE3,
+		},
+		.ts[3] = {
+			.reg_base  = PCF2131_REG_TS4_BASE,
+			.gnd_detect_reg = PCF2131_REG_CTRL4,
+			.gnd_detect_bit = PCF2131_BIT_CTRL4_TSF4,
+			.inter_detect_bit = 0,
+			.ie_reg    = PCF2131_REG_CTRL5,
+			.ie_bit    = PCF2131_BIT_CTRL5_TSIE4,
+		},
+		.attribute_group = {
+			.attrs	= pcf2131_attrs,
+		},
+	},
 };
 
 /*
@@ -893,7 +1082,7 @@ static int pcf2127_probe(struct device *dev, struct regmap *regmap,
 	 * Watchdog timer enabled and reset pin /RST activated when timed out.
 	 * Select 1Hz clock source for watchdog timer.
 	 * Note: Countdown timer disabled and not available.
-	 * For pca2129, pcf2129, only bit[7] is for Symbol WD_CD
+	 * For pca2129, pcf2129 and pcf2131, only bit[7] is for Symbol WD_CD
 	 * of register watchdg_tim_ctl. The bit[6] is labeled
 	 * as T. Bits labeled as T must always be written with
 	 * logic 0.
@@ -953,6 +1142,7 @@ static const struct of_device_id pcf2127_of_match[] = {
 	{ .compatible = "nxp,pcf2127", .data = &pcf21xx_cfg[PCF2127] },
 	{ .compatible = "nxp,pcf2129", .data = &pcf21xx_cfg[PCF2129] },
 	{ .compatible = "nxp,pca2129", .data = &pcf21xx_cfg[PCF2129] },
+	{ .compatible = "nxp,pcf2131", .data = &pcf21xx_cfg[PCF2131] },
 	{}
 };
 MODULE_DEVICE_TABLE(of, pcf2127_of_match);
@@ -1040,6 +1230,7 @@ static const struct i2c_device_id pcf2127_i2c_id[] = {
 	{ "pcf2127", PCF2127 },
 	{ "pcf2129", PCF2129 },
 	{ "pca2129", PCF2129 },
+	{ "pcf2131", PCF2131 },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, pcf2127_i2c_id);
@@ -1161,6 +1352,7 @@ static const struct spi_device_id pcf2127_spi_id[] = {
 	{ "pcf2127", PCF2127 },
 	{ "pcf2129", PCF2129 },
 	{ "pca2129", PCF2129 },
+	{ "pcf2131", PCF2131 },
 	{ }
 };
 MODULE_DEVICE_TABLE(spi, pcf2127_spi_id);
@@ -1225,5 +1417,5 @@ static void __exit pcf2127_exit(void)
 module_exit(pcf2127_exit)
 
 MODULE_AUTHOR("Renaud Cerrato <r.cerrato@til-technologies.fr>");
-MODULE_DESCRIPTION("NXP PCF2127/29 RTC driver");
+MODULE_DESCRIPTION("NXP PCF2127/29/31 RTC driver");
 MODULE_LICENSE("GPL v2");

From e1849b8fcdfaa71f2e8f9376c9568877ff2bf52b Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 22 Jun 2023 10:57:55 -0400
Subject: [PATCH 0123/1189] rtc: pcf2127: add support for PCF2131 interrupts on
 output INT_A

The PCF2127 and PCF2129 have one output interrupt pin. The PCF2131 has
two, named INT_A and INT_B. The hardware support that any interrupt
source can be routed to either one or both of them.

Force all interrupt sources to go to the INT A pin.

Support to route any interrupt source to INT A/B pins is not supported
by this driver at the moment.

Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Reviewed-by: Bruno Thomsen <bruno.thomsen@gmail.com>
Link: https://lore.kernel.org/r/20230622145800.2442116-13-hugo@hugovil.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-pcf2127.c | 35 +++++++++++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)

diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index 8c2ad9eac861..83dcb1e43abb 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -179,6 +179,7 @@ struct pcf21xx_config {
 	int max_register;
 	unsigned int has_nvmem:1;
 	unsigned int has_bit_wd_ctl_cd0:1;
+	unsigned int has_int_a_b:1; /* PCF2131 supports two interrupt outputs. */
 	u8 reg_time_base; /* Time/date base register. */
 	u8 regs_alarm_base; /* Alarm function base registers. */
 	u8 reg_wd_ctl; /* Watchdog control register. */
@@ -845,6 +846,7 @@ static struct pcf21xx_config pcf21xx_cfg[] = {
 		.max_register = 0x1d,
 		.has_nvmem = 1,
 		.has_bit_wd_ctl_cd0 = 1,
+		.has_int_a_b = 0,
 		.reg_time_base = PCF2127_REG_TIME_BASE,
 		.regs_alarm_base = PCF2127_REG_ALARM_BASE,
 		.reg_wd_ctl = PCF2127_REG_WD_CTL,
@@ -869,6 +871,7 @@ static struct pcf21xx_config pcf21xx_cfg[] = {
 		.max_register = 0x19,
 		.has_nvmem = 0,
 		.has_bit_wd_ctl_cd0 = 0,
+		.has_int_a_b = 0,
 		.reg_time_base = PCF2127_REG_TIME_BASE,
 		.regs_alarm_base = PCF2127_REG_ALARM_BASE,
 		.reg_wd_ctl = PCF2127_REG_WD_CTL,
@@ -893,6 +896,7 @@ static struct pcf21xx_config pcf21xx_cfg[] = {
 		.max_register = 0x36,
 		.has_nvmem = 0,
 		.has_bit_wd_ctl_cd0 = 0,
+		.has_int_a_b = 1,
 		.reg_time_base = PCF2131_REG_TIME_BASE,
 		.regs_alarm_base = PCF2131_REG_ALARM_BASE,
 		.reg_wd_ctl = PCF2131_REG_WD_CTL,
@@ -989,6 +993,28 @@ static int pcf2127_enable_ts(struct device *dev, int ts_id)
 	return ret;
 }
 
+/* Route all interrupt sources to INT A pin. */
+static int pcf2127_configure_interrupt_pins(struct device *dev)
+{
+	struct pcf2127 *pcf2127 = dev_get_drvdata(dev);
+	int ret;
+
+	/* Mask bits need to be cleared to enable corresponding
+	 * interrupt source.
+	 */
+	ret = regmap_write(pcf2127->regmap,
+			   PCF2131_REG_INT_A_MASK1, 0);
+	if (ret)
+		return ret;
+
+	ret = regmap_write(pcf2127->regmap,
+			   PCF2131_REG_INT_A_MASK2, 0);
+	if (ret)
+		return ret;
+
+	return ret;
+}
+
 static int pcf2127_probe(struct device *dev, struct regmap *regmap,
 			 int alarm_irq, const char *name, const struct pcf21xx_config *config)
 {
@@ -1047,6 +1073,15 @@ static int pcf2127_probe(struct device *dev, struct regmap *regmap,
 		set_bit(RTC_FEATURE_ALARM, pcf2127->rtc->features);
 	}
 
+	if (pcf2127->cfg->has_int_a_b) {
+		/* Configure int A/B pins, independently of alarm_irq. */
+		ret = pcf2127_configure_interrupt_pins(dev);
+		if (ret) {
+			dev_err(dev, "failed to configure interrupt pins\n");
+			return ret;
+		}
+	}
+
 	if (pcf2127->cfg->has_nvmem) {
 		struct nvmem_config nvmem_cfg = {
 			.priv = pcf2127,

From 3d715ebaf006bd5a495e9a717cf0fc5c260ee738 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 22 Jun 2023 10:57:56 -0400
Subject: [PATCH 0124/1189] rtc: pcf2127: adapt time/date registers write
 sequence for PCF2131

The sequence for updating the time/date registers is slightly
different between PCF2127/29 and PCF2131.

For PCF2127/29, during write operations, the time counting
circuits (memory locations 03h through 09h) are automatically blocked.

For PCF2131, time/date registers write access requires setting the
STOP bit and sending the clear prescaler instruction (CPR). STOP then
needs to be released once write operation is completed.

Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20230622145800.2442116-14-hugo@hugovil.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-pcf2127.c | 35 ++++++++++++++++++++++++++++++++++-
 1 file changed, 34 insertions(+), 1 deletion(-)

diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index 83dcb1e43abb..f6a549b1f743 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -33,6 +33,7 @@
 #define PCF2127_REG_CTRL1		0x00
 #define PCF2127_BIT_CTRL1_POR_OVRD		BIT(3)
 #define PCF2127_BIT_CTRL1_TSF1			BIT(4)
+#define PCF2127_BIT_CTRL1_STOP			BIT(5)
 /* Control register 2 */
 #define PCF2127_REG_CTRL2		0x01
 #define PCF2127_BIT_CTRL2_AIE			BIT(1)
@@ -280,13 +281,45 @@ static int pcf2127_rtc_set_time(struct device *dev, struct rtc_time *tm)
 	/* year */
 	buf[i++] = bin2bcd(tm->tm_year - 100);
 
-	/* write register's data */
+	/* Write access to time registers:
+	 * PCF2127/29: no special action required.
+	 * PCF2131:    requires setting the STOP and CPR bits. STOP bit needs to
+	 *             be cleared after time registers are updated.
+	 */
+	if (pcf2127->cfg->type == PCF2131) {
+		err = regmap_update_bits(pcf2127->regmap, PCF2127_REG_CTRL1,
+					 PCF2127_BIT_CTRL1_STOP,
+					 PCF2127_BIT_CTRL1_STOP);
+		if (err) {
+			dev_dbg(dev, "setting STOP bit failed\n");
+			return err;
+		}
+
+		err = regmap_write(pcf2127->regmap, PCF2131_REG_SR_RESET,
+				   PCF2131_SR_RESET_CPR_CMD);
+		if (err) {
+			dev_dbg(dev, "sending CPR cmd failed\n");
+			return err;
+		}
+	}
+
+	/* write time register's data */
 	err = regmap_bulk_write(pcf2127->regmap, pcf2127->cfg->reg_time_base, buf, i);
 	if (err) {
 		dev_dbg(dev, "%s: err=%d", __func__, err);
 		return err;
 	}
 
+	if (pcf2127->cfg->type == PCF2131) {
+		/* Clear STOP bit (PCF2131 only) after write is completed. */
+		err = regmap_update_bits(pcf2127->regmap, PCF2127_REG_CTRL1,
+					 PCF2127_BIT_CTRL1_STOP, 0);
+		if (err) {
+			dev_dbg(dev, "clearing STOP bit failed\n");
+			return err;
+		}
+	}
+
 	return 0;
 }
 

From adb9675d74e403537150f025ed2b7a2e1ed0a7b4 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 22 Jun 2023 10:57:57 -0400
Subject: [PATCH 0125/1189] rtc: pcf2127: support generic watchdog timing
 configuration

Introduce in the configuration structure two new values to hold the
watchdog clock source and the min_hw_heartbeat_ms value.

The minimum and maximum timeout values are automatically computed from
the watchdog clock source value for each variant.

The PCF2131 has no 1Hz watchdog clock source, as is the case for
PCF2127/29.

The next best choice is using a 1/4Hz clock, giving a watchdog timeout
range between 4 and 1016s. By using the same register configuration as
for the PCF2127/29, the 1/4Hz clock source is selected.

Note: the PCF2127 datasheet gives a min/max range between 1 and 255s,
but it should be between 2 and 254s, because the watchdog is triggered
when the timer value reaches 1, not 0.

Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20230622145800.2442116-15-hugo@hugovil.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-pcf2127.c | 64 +++++++++++++++++++++++++++++++++------
 1 file changed, 55 insertions(+), 9 deletions(-)

diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index f6a549b1f743..59c0dcfed5c8 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -80,9 +80,14 @@
 
 /* Watchdog timer value constants */
 #define PCF2127_WD_VAL_STOP		0
-#define PCF2127_WD_VAL_MIN		2
-#define PCF2127_WD_VAL_MAX		255
-#define PCF2127_WD_VAL_DEFAULT		60
+/* PCF2127/29 watchdog timer value constants */
+#define PCF2127_WD_CLOCK_HZ_X1000	1000 /* 1Hz */
+#define PCF2127_WD_MIN_HW_HEARTBEAT_MS	500
+/* PCF2131 watchdog timer value constants */
+#define PCF2131_WD_CLOCK_HZ_X1000	250  /* 1/4Hz */
+#define PCF2131_WD_MIN_HW_HEARTBEAT_MS	4000
+
+#define PCF2127_WD_DEFAULT_TIMEOUT_S	60
 
 /* Mask for currently enabled interrupts */
 #define PCF2127_CTRL1_IRQ_MASK (PCF2127_BIT_CTRL1_TSF1)
@@ -186,6 +191,8 @@ struct pcf21xx_config {
 	u8 reg_wd_ctl; /* Watchdog control register. */
 	u8 reg_wd_val; /* Watchdog value register. */
 	u8 reg_clkout; /* Clkout register. */
+	int wdd_clock_hz_x1000; /* Watchdog clock in Hz multiplicated by 1000 */
+	int wdd_min_hw_heartbeat_ms;
 	unsigned int ts_count;
 	struct pcf21xx_ts_config ts[PCF2127_MAX_TS_SUPPORTED];
 	struct attribute_group attribute_group;
@@ -389,9 +396,16 @@ static int pcf2127_nvmem_write(void *priv, unsigned int offset,
 
 static int pcf2127_wdt_ping(struct watchdog_device *wdd)
 {
+	int wd_val;
 	struct pcf2127 *pcf2127 = watchdog_get_drvdata(wdd);
 
-	return regmap_write(pcf2127->regmap, pcf2127->cfg->reg_wd_val, wdd->timeout);
+	/*
+	 * Compute counter value of WATCHDG_TIM_VAL to obtain desired period
+	 * in seconds, depending on the source clock frequency.
+	 */
+	wd_val = ((wdd->timeout * pcf2127->cfg->wdd_clock_hz_x1000) / 1000) + 1;
+
+	return regmap_write(pcf2127->regmap, pcf2127->cfg->reg_wd_val, wd_val);
 }
 
 /*
@@ -453,6 +467,23 @@ static const struct watchdog_ops pcf2127_watchdog_ops = {
 	.set_timeout = pcf2127_wdt_set_timeout,
 };
 
+/*
+ * Compute watchdog period, t, in seconds, from the WATCHDG_TIM_VAL register
+ * value, n, and the clock frequency, f1000, in Hz x 1000.
+ *
+ * The PCF2127/29 datasheet gives t as:
+ *   t = n / f
+ * The PCF2131 datasheet gives t as:
+ *   t = (n - 1) / f
+ * For both variants, the watchdog is triggered when the WATCHDG_TIM_VAL reaches
+ * the value 1, and not zero. Consequently, the equation from the PCF2131
+ * datasheet seems to be the correct one for both variants.
+ */
+static int pcf2127_watchdog_get_period(int n, int f1000)
+{
+	return (1000 * (n - 1)) / f1000;
+}
+
 static int pcf2127_watchdog_init(struct device *dev, struct pcf2127 *pcf2127)
 {
 	u32 wdd_timeout;
@@ -465,10 +496,19 @@ static int pcf2127_watchdog_init(struct device *dev, struct pcf2127 *pcf2127)
 	pcf2127->wdd.parent = dev;
 	pcf2127->wdd.info = &pcf2127_wdt_info;
 	pcf2127->wdd.ops = &pcf2127_watchdog_ops;
-	pcf2127->wdd.min_timeout = PCF2127_WD_VAL_MIN;
-	pcf2127->wdd.max_timeout = PCF2127_WD_VAL_MAX;
-	pcf2127->wdd.timeout = PCF2127_WD_VAL_DEFAULT;
-	pcf2127->wdd.min_hw_heartbeat_ms = 500;
+
+	pcf2127->wdd.min_timeout =
+		pcf2127_watchdog_get_period(
+			2, pcf2127->cfg->wdd_clock_hz_x1000);
+	pcf2127->wdd.max_timeout =
+		pcf2127_watchdog_get_period(
+			255, pcf2127->cfg->wdd_clock_hz_x1000);
+	pcf2127->wdd.timeout = PCF2127_WD_DEFAULT_TIMEOUT_S;
+
+	dev_dbg(dev, "%s clock = %d Hz / 1000\n", __func__,
+		pcf2127->cfg->wdd_clock_hz_x1000);
+
+	pcf2127->wdd.min_hw_heartbeat_ms = pcf2127->cfg->wdd_min_hw_heartbeat_ms;
 	pcf2127->wdd.status = WATCHDOG_NOWAYOUT_INIT_STATUS;
 
 	watchdog_set_drvdata(&pcf2127->wdd, pcf2127);
@@ -885,6 +925,8 @@ static struct pcf21xx_config pcf21xx_cfg[] = {
 		.reg_wd_ctl = PCF2127_REG_WD_CTL,
 		.reg_wd_val = PCF2127_REG_WD_VAL,
 		.reg_clkout = PCF2127_REG_CLKOUT,
+		.wdd_clock_hz_x1000 = PCF2127_WD_CLOCK_HZ_X1000,
+		.wdd_min_hw_heartbeat_ms = PCF2127_WD_MIN_HW_HEARTBEAT_MS,
 		.ts_count = 1,
 		.ts[0] = {
 			.reg_base  = PCF2127_REG_TS1_BASE,
@@ -910,6 +952,8 @@ static struct pcf21xx_config pcf21xx_cfg[] = {
 		.reg_wd_ctl = PCF2127_REG_WD_CTL,
 		.reg_wd_val = PCF2127_REG_WD_VAL,
 		.reg_clkout = PCF2127_REG_CLKOUT,
+		.wdd_clock_hz_x1000 = PCF2127_WD_CLOCK_HZ_X1000,
+		.wdd_min_hw_heartbeat_ms = PCF2127_WD_MIN_HW_HEARTBEAT_MS,
 		.ts_count = 1,
 		.ts[0] = {
 			.reg_base  = PCF2127_REG_TS1_BASE,
@@ -935,6 +979,8 @@ static struct pcf21xx_config pcf21xx_cfg[] = {
 		.reg_wd_ctl = PCF2131_REG_WD_CTL,
 		.reg_wd_val = PCF2131_REG_WD_VAL,
 		.reg_clkout = PCF2131_REG_CLKOUT,
+		.wdd_clock_hz_x1000 = PCF2131_WD_CLOCK_HZ_X1000,
+		.wdd_min_hw_heartbeat_ms = PCF2131_WD_MIN_HW_HEARTBEAT_MS,
 		.ts_count = 4,
 		.ts[0] = {
 			.reg_base  = PCF2131_REG_TS1_BASE,
@@ -1148,7 +1194,7 @@ static int pcf2127_probe(struct device *dev, struct regmap *regmap,
 
 	/*
 	 * Watchdog timer enabled and reset pin /RST activated when timed out.
-	 * Select 1Hz clock source for watchdog timer.
+	 * Select 1Hz clock source for watchdog timer (1/4Hz for PCF2131).
 	 * Note: Countdown timer disabled and not available.
 	 * For pca2129, pcf2129 and pcf2131, only bit[7] is for Symbol WD_CD
 	 * of register watchdg_tim_ctl. The bit[6] is labeled

From 081602a1d85b1fd7ad9ea298cffb4e5ad5296952 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 22 Jun 2023 10:57:58 -0400
Subject: [PATCH 0126/1189] rtc: pcf2127: add flag for watchdog register value
 read support

The watchdog value register cannot be read on the PCF2131 after being
set.

Add a new flag to identify which variant has read access to this
register, and use this flag to selectively test if watchdog timer was
started by bootloader.

Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Reviewed-by: Bruno Thomsen <bruno.thomsen@gmail.com>
Link: https://lore.kernel.org/r/20230622145800.2442116-16-hugo@hugovil.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-pcf2127.c | 20 ++++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)

diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index 59c0dcfed5c8..3acab5a19aba 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -185,6 +185,7 @@ struct pcf21xx_config {
 	int max_register;
 	unsigned int has_nvmem:1;
 	unsigned int has_bit_wd_ctl_cd0:1;
+	unsigned int wd_val_reg_readable:1; /* If watchdog value register can be read. */
 	unsigned int has_int_a_b:1; /* PCF2131 supports two interrupt outputs. */
 	u8 reg_time_base; /* Time/date base register. */
 	u8 regs_alarm_base; /* Alarm function base registers. */
@@ -486,7 +487,6 @@ static int pcf2127_watchdog_get_period(int n, int f1000)
 
 static int pcf2127_watchdog_init(struct device *dev, struct pcf2127 *pcf2127)
 {
-	u32 wdd_timeout;
 	int ret;
 
 	if (!IS_ENABLED(CONFIG_WATCHDOG) ||
@@ -514,12 +514,17 @@ static int pcf2127_watchdog_init(struct device *dev, struct pcf2127 *pcf2127)
 	watchdog_set_drvdata(&pcf2127->wdd, pcf2127);
 
 	/* Test if watchdog timer is started by bootloader */
-	ret = regmap_read(pcf2127->regmap, pcf2127->cfg->reg_wd_val, &wdd_timeout);
-	if (ret)
-		return ret;
+	if (pcf2127->cfg->wd_val_reg_readable) {
+		u32 wdd_timeout;
 
-	if (wdd_timeout)
-		set_bit(WDOG_HW_RUNNING, &pcf2127->wdd.status);
+		ret = regmap_read(pcf2127->regmap, pcf2127->cfg->reg_wd_val,
+				  &wdd_timeout);
+		if (ret)
+			return ret;
+
+		if (wdd_timeout)
+			set_bit(WDOG_HW_RUNNING, &pcf2127->wdd.status);
+	}
 
 	return devm_watchdog_register_device(dev, &pcf2127->wdd);
 }
@@ -919,6 +924,7 @@ static struct pcf21xx_config pcf21xx_cfg[] = {
 		.max_register = 0x1d,
 		.has_nvmem = 1,
 		.has_bit_wd_ctl_cd0 = 1,
+		.wd_val_reg_readable = 1,
 		.has_int_a_b = 0,
 		.reg_time_base = PCF2127_REG_TIME_BASE,
 		.regs_alarm_base = PCF2127_REG_ALARM_BASE,
@@ -946,6 +952,7 @@ static struct pcf21xx_config pcf21xx_cfg[] = {
 		.max_register = 0x19,
 		.has_nvmem = 0,
 		.has_bit_wd_ctl_cd0 = 0,
+		.wd_val_reg_readable = 1,
 		.has_int_a_b = 0,
 		.reg_time_base = PCF2127_REG_TIME_BASE,
 		.regs_alarm_base = PCF2127_REG_ALARM_BASE,
@@ -973,6 +980,7 @@ static struct pcf21xx_config pcf21xx_cfg[] = {
 		.max_register = 0x36,
 		.has_nvmem = 0,
 		.has_bit_wd_ctl_cd0 = 0,
+		.wd_val_reg_readable = 0,
 		.has_int_a_b = 1,
 		.reg_time_base = PCF2131_REG_TIME_BASE,
 		.regs_alarm_base = PCF2131_REG_ALARM_BASE,

From e9a5a1b418dd9a82d1de71e82ec64ad195b5300a Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 22 Jun 2023 10:57:59 -0400
Subject: [PATCH 0127/1189] rtc: pcf2127: add UIE support for PCF2131

The PCF2127/29 do NOT support alarms with a 1 second resolution, but
the PCF2131 does.

Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20230622145800.2442116-17-hugo@hugovil.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-pcf2127.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index 3acab5a19aba..78141bb06ab0 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -1128,8 +1128,16 @@ static int pcf2127_probe(struct device *dev, struct regmap *regmap,
 	pcf2127->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	pcf2127->rtc->range_max = RTC_TIMESTAMP_END_2099;
 	pcf2127->rtc->set_start_time = true; /* Sets actual start to 1970 */
-	set_bit(RTC_FEATURE_ALARM_RES_2S, pcf2127->rtc->features);
-	clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, pcf2127->rtc->features);
+
+	/*
+	 * PCF2127/29 do not work correctly when setting alarms at 1s intervals.
+	 * PCF2131 is ok.
+	 */
+	if (pcf2127->cfg->type == PCF2127 || pcf2127->cfg->type == PCF2129) {
+		set_bit(RTC_FEATURE_ALARM_RES_2S, pcf2127->rtc->features);
+		clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, pcf2127->rtc->features);
+	}
+
 	clear_bit(RTC_FEATURE_ALARM, pcf2127->rtc->features);
 
 	if (alarm_irq > 0) {

From 2080e08460c41c6d432575132868fdf076768c92 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 22 Jun 2023 10:58:00 -0400
Subject: [PATCH 0128/1189] dt-bindings: rtc: pcf2127: add PCF2131

Add support for new NXP RTC PCF2131.

Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20230622145800.2442116-18-hugo@hugovil.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 Documentation/devicetree/bindings/rtc/nxp,pcf2127.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/rtc/nxp,pcf2127.yaml b/Documentation/devicetree/bindings/rtc/nxp,pcf2127.yaml
index bcb230027622..2d9fe5a75b06 100644
--- a/Documentation/devicetree/bindings/rtc/nxp,pcf2127.yaml
+++ b/Documentation/devicetree/bindings/rtc/nxp,pcf2127.yaml
@@ -18,6 +18,7 @@ properties:
       - nxp,pca2129
       - nxp,pcf2127
       - nxp,pcf2129
+      - nxp,pcf2131
 
   reg:
     maxItems: 1

From f69cb2d6034ddf8dae6848d29b9d4efba8cd4df9 Mon Sep 17 00:00:00 2001
From: Antonio Borneo <antonio.borneo@foss.st.com>
Date: Wed, 5 Jul 2023 19:43:51 +0200
Subject: [PATCH 0129/1189] rtc: stm32: use the proper register sequence to
 read date/time

Date and time are read from two separate RTC registers.
To ensure consistency between the two registers, reading the time
register locks the values in the shadow date register until the
date register is read.
Thus, the whole date/time read requires reading the time register
first, followed by reading the date register.
If the reads are done in reversed order, the shadow date register
will remain locked until a future read operation. The future read
will read the former date value that could be already invalid.

Fix the read order of date/time registers in stm32_rtc_valid_alrm()

Signed-off-by: Antonio Borneo <antonio.borneo@foss.st.com>
Signed-off-by: Valentin Caron <valentin.caron@foss.st.com>
Link: https://lore.kernel.org/r/20230705174357.353616-2-valentin.caron@foss.st.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-stm32.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/rtc/rtc-stm32.c b/drivers/rtc/rtc-stm32.c
index 3d36e11cff80..abb77ad774a1 100644
--- a/drivers/rtc/rtc-stm32.c
+++ b/drivers/rtc/rtc-stm32.c
@@ -429,8 +429,8 @@ static int stm32_rtc_valid_alrm(struct stm32_rtc *rtc, struct rtc_time *tm)
 {
 	const struct stm32_rtc_registers *regs = &rtc->data->regs;
 	int cur_day, cur_mon, cur_year, cur_hour, cur_min, cur_sec;
-	unsigned int dr = readl_relaxed(rtc->base + regs->dr);
 	unsigned int tr = readl_relaxed(rtc->base + regs->tr);
+	unsigned int dr = readl_relaxed(rtc->base + regs->dr);
 
 	cur_day = (dr & STM32_RTC_DR_DATE) >> STM32_RTC_DR_DATE_SHIFT;
 	cur_mon = (dr & STM32_RTC_DR_MONTH) >> STM32_RTC_DR_MONTH_SHIFT;

From 1c18b8ec52396af6a6e20cd3450dc9bff0781ab8 Mon Sep 17 00:00:00 2001
From: Antonio Borneo <antonio.borneo@foss.st.com>
Date: Wed, 5 Jul 2023 19:43:52 +0200
Subject: [PATCH 0130/1189] rtc: stm32: don't stop time counter if not needed

RTC counters are stopped when INIT bit in ISR register is set and
start counting from the (eventual) new value when INIT is reset.

In stm32_rtc_init(), called during probe, the INIT bit is set to
program the prescaler and the 24h mode. This halts the RTC counter
at each probe tentative causing the RTC time to loose from 0.3s to
0.8s at each kernel boot.
If the RTC is battery powered, both prescaler value and 24h mode
are kept during power cycle and there is no need to program them
again.

Check if the desired prescaler value and the 24h mode are already
programmed, then skip reprogramming them to avoid halting the time
counter.

Signed-off-by: Antonio Borneo <antonio.borneo@foss.st.com>
Signed-off-by: Valentin Caron <valentin.caron@foss.st.com>
Link: https://lore.kernel.org/r/20230705174357.353616-3-valentin.caron@foss.st.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-stm32.c | 23 +++++++++++++++++------
 1 file changed, 17 insertions(+), 6 deletions(-)

diff --git a/drivers/rtc/rtc-stm32.c b/drivers/rtc/rtc-stm32.c
index abb77ad774a1..bd7a59a07537 100644
--- a/drivers/rtc/rtc-stm32.c
+++ b/drivers/rtc/rtc-stm32.c
@@ -628,7 +628,7 @@ static int stm32_rtc_init(struct platform_device *pdev,
 	const struct stm32_rtc_registers *regs = &rtc->data->regs;
 	unsigned int prer, pred_a, pred_s, pred_a_max, pred_s_max, cr;
 	unsigned int rate;
-	int ret = 0;
+	int ret;
 
 	rate = clk_get_rate(rtc->rtc_ck);
 
@@ -656,6 +656,20 @@ static int stm32_rtc_init(struct platform_device *pdev,
 			 "fast" : "slow");
 	}
 
+	cr = readl_relaxed(rtc->base + regs->cr);
+
+	prer = readl_relaxed(rtc->base + regs->prer);
+	prer &= STM32_RTC_PRER_PRED_S | STM32_RTC_PRER_PRED_A;
+
+	pred_s = (pred_s << STM32_RTC_PRER_PRED_S_SHIFT) &
+		 STM32_RTC_PRER_PRED_S;
+	pred_a = (pred_a << STM32_RTC_PRER_PRED_A_SHIFT) &
+		 STM32_RTC_PRER_PRED_A;
+
+	/* quit if there is nothing to initialize */
+	if ((cr & STM32_RTC_CR_FMT) == 0 && prer == (pred_s | pred_a))
+		return 0;
+
 	stm32_rtc_wpr_unlock(rtc);
 
 	ret = stm32_rtc_enter_init_mode(rtc);
@@ -665,13 +679,10 @@ static int stm32_rtc_init(struct platform_device *pdev,
 		goto end;
 	}
 
-	prer = (pred_s << STM32_RTC_PRER_PRED_S_SHIFT) & STM32_RTC_PRER_PRED_S;
-	writel_relaxed(prer, rtc->base + regs->prer);
-	prer |= (pred_a << STM32_RTC_PRER_PRED_A_SHIFT) & STM32_RTC_PRER_PRED_A;
-	writel_relaxed(prer, rtc->base + regs->prer);
+	writel_relaxed(pred_s, rtc->base + regs->prer);
+	writel_relaxed(pred_a | pred_s, rtc->base + regs->prer);
 
 	/* Force 24h time format */
-	cr = readl_relaxed(rtc->base + regs->cr);
 	cr &= ~STM32_RTC_CR_FMT;
 	writel_relaxed(cr, rtc->base + regs->cr);
 

From 2487925731b75961cf4b7d1d0d28d204b63787b9 Mon Sep 17 00:00:00 2001
From: Christophe Guibout <christophe.guibout@foss.st.com>
Date: Wed, 5 Jul 2023 19:43:53 +0200
Subject: [PATCH 0131/1189] rtc: stm32: improve rtc precision

The rtc is used to update the stgen counter on wake up from
low power modes, so it needs to be as much accurate as possible.

The maximization of asynchronous divider leads to a 4ms rtc
precision clock.
By decreasing pred_a to 0, it will have pred_s=32767 (when
need_accuracy is true), so stgen clock becomes more accurate
with 30us precision.
Nevertheless this will leads to an increase of power consumption.

Signed-off-by: Christophe Guibout <christophe.guibout@foss.st.com>
Signed-off-by: Valentin Caron <valentin.caron@foss.st.com>
Link: https://lore.kernel.org/r/20230705174357.353616-4-valentin.caron@foss.st.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-stm32.c | 26 ++++++++++++++++++++++----
 1 file changed, 22 insertions(+), 4 deletions(-)

diff --git a/drivers/rtc/rtc-stm32.c b/drivers/rtc/rtc-stm32.c
index bd7a59a07537..cad88668bcfb 100644
--- a/drivers/rtc/rtc-stm32.c
+++ b/drivers/rtc/rtc-stm32.c
@@ -114,6 +114,7 @@ struct stm32_rtc_data {
 	void (*clear_events)(struct stm32_rtc *rtc, unsigned int flags);
 	bool has_pclk;
 	bool need_dbp;
+	bool need_accuracy;
 };
 
 struct stm32_rtc {
@@ -545,6 +546,7 @@ static void stm32_rtc_clear_events(struct stm32_rtc *rtc,
 static const struct stm32_rtc_data stm32_rtc_data = {
 	.has_pclk = false,
 	.need_dbp = true,
+	.need_accuracy = false,
 	.regs = {
 		.tr = 0x00,
 		.dr = 0x04,
@@ -566,6 +568,7 @@ static const struct stm32_rtc_data stm32_rtc_data = {
 static const struct stm32_rtc_data stm32h7_rtc_data = {
 	.has_pclk = true,
 	.need_dbp = true,
+	.need_accuracy = false,
 	.regs = {
 		.tr = 0x00,
 		.dr = 0x04,
@@ -596,6 +599,7 @@ static void stm32mp1_rtc_clear_events(struct stm32_rtc *rtc,
 static const struct stm32_rtc_data stm32mp1_data = {
 	.has_pclk = true,
 	.need_dbp = false,
+	.need_accuracy = true,
 	.regs = {
 		.tr = 0x00,
 		.dr = 0x04,
@@ -636,11 +640,25 @@ static int stm32_rtc_init(struct platform_device *pdev,
 	pred_a_max = STM32_RTC_PRER_PRED_A >> STM32_RTC_PRER_PRED_A_SHIFT;
 	pred_s_max = STM32_RTC_PRER_PRED_S >> STM32_RTC_PRER_PRED_S_SHIFT;
 
-	for (pred_a = pred_a_max; pred_a + 1 > 0; pred_a--) {
-		pred_s = (rate / (pred_a + 1)) - 1;
+	if (rate > (pred_a_max + 1) * (pred_s_max + 1)) {
+		dev_err(&pdev->dev, "rtc_ck rate is too high: %dHz\n", rate);
+		return -EINVAL;
+	}
 
-		if (((pred_s + 1) * (pred_a + 1)) == rate)
-			break;
+	if (rtc->data->need_accuracy) {
+		for (pred_a = 0; pred_a <= pred_a_max; pred_a++) {
+			pred_s = (rate / (pred_a + 1)) - 1;
+
+			if (pred_s <= pred_s_max && ((pred_s + 1) * (pred_a + 1)) == rate)
+				break;
+		}
+	} else {
+		for (pred_a = pred_a_max; pred_a + 1 > 0; pred_a--) {
+			pred_s = (rate / (pred_a + 1)) - 1;
+
+			if (((pred_s + 1) * (pred_a + 1)) == rate)
+				break;
+		}
 	}
 
 	/*

From 95f7679c3ab2d032d935692426b6d9f7e681fd60 Mon Sep 17 00:00:00 2001
From: Valentin Caron <valentin.caron@foss.st.com>
Date: Wed, 5 Jul 2023 19:43:54 +0200
Subject: [PATCH 0132/1189] rtc: stm32: don't print an error on probe deferral

Change stm32-rtc driver to not generate an error message when
device probe operation is deferred for a clock.

Signed-off-by: Etienne Carriere <etienne.carriere@foss.st.com>
Signed-off-by: Valentin Caron <valentin.caron@foss.st.com>
Link: https://lore.kernel.org/r/20230705174357.353616-5-valentin.caron@foss.st.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-stm32.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/rtc/rtc-stm32.c b/drivers/rtc/rtc-stm32.c
index cad88668bcfb..5ebf0b8e75f9 100644
--- a/drivers/rtc/rtc-stm32.c
+++ b/drivers/rtc/rtc-stm32.c
@@ -6,6 +6,7 @@
 
 #include <linux/bcd.h>
 #include <linux/clk.h>
+#include <linux/errno.h>
 #include <linux/iopoll.h>
 #include <linux/ioport.h>
 #include <linux/mfd/syscon.h>
@@ -759,16 +760,13 @@ static int stm32_rtc_probe(struct platform_device *pdev)
 		rtc->rtc_ck = devm_clk_get(&pdev->dev, NULL);
 	} else {
 		rtc->pclk = devm_clk_get(&pdev->dev, "pclk");
-		if (IS_ERR(rtc->pclk)) {
-			dev_err(&pdev->dev, "no pclk clock");
-			return PTR_ERR(rtc->pclk);
-		}
+		if (IS_ERR(rtc->pclk))
+			return dev_err_probe(&pdev->dev, PTR_ERR(rtc->pclk), "no pclk clock");
+
 		rtc->rtc_ck = devm_clk_get(&pdev->dev, "rtc_ck");
 	}
-	if (IS_ERR(rtc->rtc_ck)) {
-		dev_err(&pdev->dev, "no rtc_ck clock");
-		return PTR_ERR(rtc->rtc_ck);
-	}
+	if (IS_ERR(rtc->rtc_ck))
+		return dev_err_probe(&pdev->dev, PTR_ERR(rtc->rtc_ck), "no rtc_ck clock");
 
 	if (rtc->data->has_pclk) {
 		ret = clk_prepare_enable(rtc->pclk);

From fb9a7e5360dc8089097337a9685f6fed350a310f Mon Sep 17 00:00:00 2001
From: Gabriel Fernandez <gabriel.fernandez@foss.st.com>
Date: Wed, 5 Jul 2023 19:43:55 +0200
Subject: [PATCH 0133/1189] rtc: stm32: change PM callbacks to "_noirq()"

The RTC driver stops the RTCAPB clock during suspend, but the
irq handler from RTC is called before starting clock. Then we are
blocked while accessing RTC registers.

We changes PM callbacks to '_no_irq()' to disable irq during
resume callback and so irq handler will be called after the enable
of RTCAPB clock.

Signed-off-by: Gabriel Fernandez <gabriel.fernandez@foss.st.com>
Signed-off-by: Valentin Caron <valentin.caron@foss.st.com>
Link: https://lore.kernel.org/r/20230705174357.353616-6-valentin.caron@foss.st.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-stm32.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/rtc/rtc-stm32.c b/drivers/rtc/rtc-stm32.c
index 5ebf0b8e75f9..17e549806784 100644
--- a/drivers/rtc/rtc-stm32.c
+++ b/drivers/rtc/rtc-stm32.c
@@ -919,8 +919,9 @@ static int stm32_rtc_resume(struct device *dev)
 }
 #endif
 
-static SIMPLE_DEV_PM_OPS(stm32_rtc_pm_ops,
-			 stm32_rtc_suspend, stm32_rtc_resume);
+static const struct dev_pm_ops stm32_rtc_pm_ops = {
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(stm32_rtc_suspend, stm32_rtc_resume)
+};
 
 static struct platform_driver stm32_rtc_driver = {
 	.probe		= stm32_rtc_probe,

From 46828a5f89044b8e057f6bbb50ae2bac926a0fa2 Mon Sep 17 00:00:00 2001
From: Valentin Caron <valentin.caron@foss.st.com>
Date: Wed, 5 Jul 2023 19:43:56 +0200
Subject: [PATCH 0134/1189] rtc: stm32: fix issues of stm32_rtc_valid_alrm
 function

stm32_rtc_valid_alrm function has some issues :
- arithmetical operations are impossible on BCD values
- "cur_mon + 1" can overflow
- the use case with the next month, the same day/hour/minutes went wrong

To solve that, we prefer to use timestamp comparison.
e.g. : On 5 Dec. 2021, the alarm limit is 5 Jan. 2022 (+31 days)
       On 31 Jan 2021, the alarm limit is 28 Feb. 2022 (+28 days)

Signed-off-by: Valentin Caron <valentin.caron@foss.st.com>
Link: https://lore.kernel.org/r/20230705174357.353616-7-valentin.caron@foss.st.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-stm32.c | 61 ++++++++++++++++++++++-------------------
 1 file changed, 33 insertions(+), 28 deletions(-)

diff --git a/drivers/rtc/rtc-stm32.c b/drivers/rtc/rtc-stm32.c
index 17e549806784..836d39a124dd 100644
--- a/drivers/rtc/rtc-stm32.c
+++ b/drivers/rtc/rtc-stm32.c
@@ -90,6 +90,9 @@
 /* Max STM32 RTC register offset is 0x3FC */
 #define UNDEF_REG			0xFFFF
 
+/* STM32 RTC driver time helpers */
+#define SEC_PER_DAY		(24 * 60 * 60)
+
 struct stm32_rtc;
 
 struct stm32_rtc_registers {
@@ -427,40 +430,42 @@ static int stm32_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
 	return 0;
 }
 
-static int stm32_rtc_valid_alrm(struct stm32_rtc *rtc, struct rtc_time *tm)
+static int stm32_rtc_valid_alrm(struct device *dev, struct rtc_time *tm)
 {
-	const struct stm32_rtc_registers *regs = &rtc->data->regs;
-	int cur_day, cur_mon, cur_year, cur_hour, cur_min, cur_sec;
-	unsigned int tr = readl_relaxed(rtc->base + regs->tr);
-	unsigned int dr = readl_relaxed(rtc->base + regs->dr);
-
-	cur_day = (dr & STM32_RTC_DR_DATE) >> STM32_RTC_DR_DATE_SHIFT;
-	cur_mon = (dr & STM32_RTC_DR_MONTH) >> STM32_RTC_DR_MONTH_SHIFT;
-	cur_year = (dr & STM32_RTC_DR_YEAR) >> STM32_RTC_DR_YEAR_SHIFT;
-	cur_sec = (tr & STM32_RTC_TR_SEC) >> STM32_RTC_TR_SEC_SHIFT;
-	cur_min = (tr & STM32_RTC_TR_MIN) >> STM32_RTC_TR_MIN_SHIFT;
-	cur_hour = (tr & STM32_RTC_TR_HOUR) >> STM32_RTC_TR_HOUR_SHIFT;
+	static struct rtc_time now;
+	time64_t max_alarm_time64;
+	int max_day_forward;
+	int next_month;
+	int next_year;
 
 	/*
 	 * Assuming current date is M-D-Y H:M:S.
 	 * RTC alarm can't be set on a specific month and year.
 	 * So the valid alarm range is:
 	 *	M-D-Y H:M:S < alarm <= (M+1)-D-Y H:M:S
-	 * with a specific case for December...
 	 */
-	if ((((tm->tm_year > cur_year) &&
-	      (tm->tm_mon == 0x1) && (cur_mon == 0x12)) ||
-	     ((tm->tm_year == cur_year) &&
-	      (tm->tm_mon <= cur_mon + 1))) &&
-	    ((tm->tm_mday > cur_day) ||
-	     ((tm->tm_mday == cur_day) &&
-	     ((tm->tm_hour > cur_hour) ||
-	      ((tm->tm_hour == cur_hour) && (tm->tm_min > cur_min)) ||
-	      ((tm->tm_hour == cur_hour) && (tm->tm_min == cur_min) &&
-	       (tm->tm_sec >= cur_sec))))))
-		return 0;
+	stm32_rtc_read_time(dev, &now);
 
-	return -EINVAL;
+	/*
+	 * Find the next month and the year of the next month.
+	 * Note: tm_mon and next_month are from 0 to 11
+	 */
+	next_month = now.tm_mon + 1;
+	if (next_month == 12) {
+		next_month = 0;
+		next_year = now.tm_year + 1;
+	} else {
+		next_year = now.tm_year;
+	}
+
+	/* Find the maximum limit of alarm in days. */
+	max_day_forward = rtc_month_days(now.tm_mon, now.tm_year)
+			 - now.tm_mday
+			 + min(rtc_month_days(next_month, next_year), now.tm_mday);
+
+	/* Convert to timestamp and compare the alarm time and its upper limit */
+	max_alarm_time64 = rtc_tm_to_time64(&now) + max_day_forward * SEC_PER_DAY;
+	return rtc_tm_to_time64(tm) <= max_alarm_time64 ? 0 : -EINVAL;
 }
 
 static int stm32_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
@@ -471,17 +476,17 @@ static int stm32_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 	unsigned int cr, isr, alrmar;
 	int ret = 0;
 
-	tm2bcd(tm);
-
 	/*
 	 * RTC alarm can't be set on a specific date, unless this date is
 	 * up to the same day of month next month.
 	 */
-	if (stm32_rtc_valid_alrm(rtc, tm) < 0) {
+	if (stm32_rtc_valid_alrm(dev, tm) < 0) {
 		dev_err(dev, "Alarm can be set only on upcoming month.\n");
 		return -EINVAL;
 	}
 
+	tm2bcd(tm);
+
 	alrmar = 0;
 	/* tm_year and tm_mon are not used because not supported by RTC */
 	alrmar |= (tm->tm_mday << STM32_RTC_ALRMXR_DATE_SHIFT) &

From 650915ecd8f8cbb58e1ef55430f9e15ae03fd7d8 Mon Sep 17 00:00:00 2001
From: Valentin Caron <valentin.caron@foss.st.com>
Date: Wed, 5 Jul 2023 19:43:57 +0200
Subject: [PATCH 0135/1189] rtc: stm32: fix unnecessary parentheses

Fix a few style issues reported by checkpatch.pl:
- Unnecessary parentheses
- Lines should not end with a '('

Signed-off-by: Valentin Caron <valentin.caron@foss.st.com>
Link: https://lore.kernel.org/r/20230705174357.353616-8-valentin.caron@foss.st.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-stm32.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/rtc/rtc-stm32.c b/drivers/rtc/rtc-stm32.c
index 836d39a124dd..85689192fa7a 100644
--- a/drivers/rtc/rtc-stm32.c
+++ b/drivers/rtc/rtc-stm32.c
@@ -163,10 +163,9 @@ static int stm32_rtc_enter_init_mode(struct stm32_rtc *rtc)
 		 * slowest rtc_ck frequency may be 32kHz and highest should be
 		 * 1MHz, we poll every 10 us with a timeout of 100ms.
 		 */
-		return readl_relaxed_poll_timeout_atomic(
-					rtc->base + regs->isr,
-					isr, (isr & STM32_RTC_ISR_INITF),
-					10, 100000);
+		return readl_relaxed_poll_timeout_atomic(rtc->base + regs->isr, isr,
+							 (isr & STM32_RTC_ISR_INITF),
+							 10, 100000);
 	}
 
 	return 0;
@@ -671,7 +670,7 @@ static int stm32_rtc_init(struct platform_device *pdev,
 	 * Can't find a 1Hz, so give priority to RTC power consumption
 	 * by choosing the higher possible value for prediv_a
 	 */
-	if ((pred_s > pred_s_max) || (pred_a > pred_a_max)) {
+	if (pred_s > pred_s_max || pred_a > pred_a_max) {
 		pred_a = pred_a_max;
 		pred_s = (rate / (pred_a + 1)) - 1;
 

From b7f73b6e921b457a222e86cf53fe3950c6b5aed5 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Mon, 10 Jul 2023 12:47:47 +0100
Subject: [PATCH 0136/1189] rtc: isl1208: Simplify probe()

Simplify the probe() by replacing of_device_get_match_data() and
i2c_match_id() by i2c_get_match_data() as we have similar I2C
and DT-based matching table.

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20230710114747.106496-1-biju.das.jz@bp.renesas.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-isl1208.c | 14 +++-----------
 1 file changed, 3 insertions(+), 11 deletions(-)

diff --git a/drivers/rtc/rtc-isl1208.c b/drivers/rtc/rtc-isl1208.c
index b0712b4e3648..57e77b55e484 100644
--- a/drivers/rtc/rtc-isl1208.c
+++ b/drivers/rtc/rtc-isl1208.c
@@ -862,17 +862,9 @@ isl1208_probe(struct i2c_client *client)
 	i2c_set_clientdata(client, isl1208);
 
 	/* Determine which chip we have */
-	if (client->dev.of_node) {
-		isl1208->config = of_device_get_match_data(&client->dev);
-		if (!isl1208->config)
-			return -ENODEV;
-	} else {
-		const struct i2c_device_id *id = i2c_match_id(isl1208_id, client);
-
-		if (!id)
-			return -ENODEV;
-		isl1208->config = (struct isl1208_config *)id->driver_data;
-	}
+	isl1208->config = i2c_get_match_data(client);
+	if (!isl1208->config)
+		return -ENODEV;
 
 	rc = isl1208_clk_present(client, "xin");
 	if (rc < 0)

From 68c624f860b30408afde81a91b4c9df3e915ed85 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Mon, 17 Jul 2023 13:40:58 +0100
Subject: [PATCH 0137/1189] rtc: pcf85063: Simplify probe()

The pcf85063_ids[].driver_data could store a pointer to the config,
like for DT-based matching, making I2C and DT-based matching
more similar.

After that, we can simplify the probe() by replacing of_device_get_
match_data() and i2c_match_id() by i2c_get_match_data() as we have
similar I2C and DT-based matching table.

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20230717124059.196244-2-biju.das.jz@bp.renesas.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-pcf85063.c | 26 ++++++++------------------
 1 file changed, 8 insertions(+), 18 deletions(-)

diff --git a/drivers/rtc/rtc-pcf85063.c b/drivers/rtc/rtc-pcf85063.c
index e517abfaee2a..a3b75c96ff9a 100644
--- a/drivers/rtc/rtc-pcf85063.c
+++ b/drivers/rtc/rtc-pcf85063.c
@@ -556,8 +556,6 @@ static struct pcf85063_config pcf85063_cfg[] = {
 	},
 };
 
-static const struct i2c_device_id pcf85063_ids[];
-
 static int pcf85063_probe(struct i2c_client *client)
 {
 	struct pcf85063 *pcf85063;
@@ -579,17 +577,9 @@ static int pcf85063_probe(struct i2c_client *client)
 	if (!pcf85063)
 		return -ENOMEM;
 
-	if (client->dev.of_node) {
-		config = of_device_get_match_data(&client->dev);
-		if (!config)
-			return -ENODEV;
-	} else {
-		enum pcf85063_type type =
-			i2c_match_id(pcf85063_ids, client)->driver_data;
-		if (type >= PCF85063_LAST_ID)
-			return -ENODEV;
-		config = &pcf85063_cfg[type];
-	}
+	config = i2c_get_match_data(client);
+	if (!config)
+		return -ENODEV;
 
 	pcf85063->regmap = devm_regmap_init_i2c(client, &config->regmap);
 	if (IS_ERR(pcf85063->regmap))
@@ -655,11 +645,11 @@ static int pcf85063_probe(struct i2c_client *client)
 }
 
 static const struct i2c_device_id pcf85063_ids[] = {
-	{ "pca85073a", PCF85063A },
-	{ "pcf85063", PCF85063 },
-	{ "pcf85063tp", PCF85063TP },
-	{ "pcf85063a", PCF85063A },
-	{ "rv8263", RV8263 },
+	{ "pca85073a", .driver_data = (kernel_ulong_t)&pcf85063_cfg[PCF85063A] },
+	{ "pcf85063", .driver_data = (kernel_ulong_t)&pcf85063_cfg[PCF85063] },
+	{ "pcf85063tp", .driver_data = (kernel_ulong_t)&pcf85063_cfg[PCF85063TP] },
+	{ "pcf85063a", .driver_data = (kernel_ulong_t)&pcf85063_cfg[PCF85063A] },
+	{ "rv8263", .driver_data = (kernel_ulong_t)&pcf85063_cfg[RV8263] },
 	{}
 };
 MODULE_DEVICE_TABLE(i2c, pcf85063_ids);

From 5789837c782771eadc9be47487067399609832e7 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Mon, 17 Jul 2023 13:40:59 +0100
Subject: [PATCH 0138/1189] rtc: pcf85063: Drop enum pcf85063_type and split
 pcf85063_cfg[]

Drop enum pcf85063_type and split the array pcf85063_cfg[] as individual
variables, and make lines shorter by referring to e.g. &pcf85063_cfg
instead of &pcf85063_cfg[PCF85063].

Suggested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Link: https://lore.kernel.org/r/20230717124059.196244-3-biju.das.jz@bp.renesas.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-pcf85063.c | 83 +++++++++++++++++---------------------
 1 file changed, 38 insertions(+), 45 deletions(-)

diff --git a/drivers/rtc/rtc-pcf85063.c b/drivers/rtc/rtc-pcf85063.c
index a3b75c96ff9a..f501b6f9ed01 100644
--- a/drivers/rtc/rtc-pcf85063.c
+++ b/drivers/rtc/rtc-pcf85063.c
@@ -514,46 +514,39 @@ static struct clk *pcf85063_clkout_register_clk(struct pcf85063 *pcf85063)
 }
 #endif
 
-enum pcf85063_type {
-	PCF85063,
-	PCF85063TP,
-	PCF85063A,
-	RV8263,
-	PCF85063_LAST_ID
+static const struct pcf85063_config config_pcf85063 = {
+	.regmap = {
+		.reg_bits = 8,
+		.val_bits = 8,
+		.max_register = 0x0a,
+	},
 };
 
-static struct pcf85063_config pcf85063_cfg[] = {
-	[PCF85063] = {
-		.regmap = {
-			.reg_bits = 8,
-			.val_bits = 8,
-			.max_register = 0x0a,
-		},
+static const struct pcf85063_config config_pcf85063tp = {
+	.regmap = {
+		.reg_bits = 8,
+		.val_bits = 8,
+		.max_register = 0x0a,
 	},
-	[PCF85063TP] = {
-		.regmap = {
-			.reg_bits = 8,
-			.val_bits = 8,
-			.max_register = 0x0a,
-		},
+};
+
+static const struct pcf85063_config config_pcf85063a = {
+	.regmap = {
+		.reg_bits = 8,
+		.val_bits = 8,
+		.max_register = 0x11,
 	},
-	[PCF85063A] = {
-		.regmap = {
-			.reg_bits = 8,
-			.val_bits = 8,
-			.max_register = 0x11,
-		},
-		.has_alarms = 1,
-	},
-	[RV8263] = {
-		.regmap = {
-			.reg_bits = 8,
-			.val_bits = 8,
-			.max_register = 0x11,
-		},
-		.has_alarms = 1,
-		.force_cap_7000 = 1,
+	.has_alarms = 1,
+};
+
+static const struct pcf85063_config config_rv8263 = {
+	.regmap = {
+		.reg_bits = 8,
+		.val_bits = 8,
+		.max_register = 0x11,
 	},
+	.has_alarms = 1,
+	.force_cap_7000 = 1,
 };
 
 static int pcf85063_probe(struct i2c_client *client)
@@ -645,22 +638,22 @@ static int pcf85063_probe(struct i2c_client *client)
 }
 
 static const struct i2c_device_id pcf85063_ids[] = {
-	{ "pca85073a", .driver_data = (kernel_ulong_t)&pcf85063_cfg[PCF85063A] },
-	{ "pcf85063", .driver_data = (kernel_ulong_t)&pcf85063_cfg[PCF85063] },
-	{ "pcf85063tp", .driver_data = (kernel_ulong_t)&pcf85063_cfg[PCF85063TP] },
-	{ "pcf85063a", .driver_data = (kernel_ulong_t)&pcf85063_cfg[PCF85063A] },
-	{ "rv8263", .driver_data = (kernel_ulong_t)&pcf85063_cfg[RV8263] },
+	{ "pca85073a", .driver_data = (kernel_ulong_t)&config_pcf85063a },
+	{ "pcf85063", .driver_data = (kernel_ulong_t)&config_pcf85063 },
+	{ "pcf85063tp", .driver_data = (kernel_ulong_t)&config_pcf85063tp },
+	{ "pcf85063a", .driver_data = (kernel_ulong_t)&config_pcf85063a },
+	{ "rv8263", .driver_data = (kernel_ulong_t)&config_rv8263 },
 	{}
 };
 MODULE_DEVICE_TABLE(i2c, pcf85063_ids);
 
 #ifdef CONFIG_OF
 static const struct of_device_id pcf85063_of_match[] = {
-	{ .compatible = "nxp,pca85073a", .data = &pcf85063_cfg[PCF85063A] },
-	{ .compatible = "nxp,pcf85063", .data = &pcf85063_cfg[PCF85063] },
-	{ .compatible = "nxp,pcf85063tp", .data = &pcf85063_cfg[PCF85063TP] },
-	{ .compatible = "nxp,pcf85063a", .data = &pcf85063_cfg[PCF85063A] },
-	{ .compatible = "microcrystal,rv8263", .data = &pcf85063_cfg[RV8263] },
+	{ .compatible = "nxp,pca85073a", .data = &config_pcf85063a },
+	{ .compatible = "nxp,pcf85063", .data = &config_pcf85063 },
+	{ .compatible = "nxp,pcf85063tp", .data = &config_pcf85063tp },
+	{ .compatible = "nxp,pcf85063a", .data = &config_pcf85063a },
+	{ .compatible = "microcrystal,rv8263", .data = &config_rv8263 },
 	{}
 };
 MODULE_DEVICE_TABLE(of, pcf85063_of_match);

From 766c3f8a092b4d42abd68ee0338349838430a5ee Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 19 Jul 2023 21:28:18 +0200
Subject: [PATCH 0139/1189] rtc: bq4802: add sparc dependency

The added HAS_IOPORT dependency might not actually be necessary as Geert
points out, but the driver is also only used on one architecture. Sparc
is also a special case here since it converts port numbers into virtual
addresses rather than having them mapped into a particular part of the
__iomem address space, so the difference is actually not important here.

Add a dependency on sparc, but allow compile-testing otherwise, to
make this clearer without anyone having to spend much time modernizing
the driver beyond that.

Reported-by: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: David S. Miller <davem@davemloft.net>
Link: https://lore.kernel.org/all/CAMuHMdWEx0F=fNei4Bz_JPkuvoaN-+zk08h0i8KnSi_VjO615g@mail.gmail.com/
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20230719192835.1025406-1-arnd@kernel.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index e8bad8c93ba9..d7502433c78a 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -1196,6 +1196,7 @@ config RTC_DRV_MSM6242
 config RTC_DRV_BQ4802
 	tristate "TI BQ4802"
 	depends on HAS_IOMEM && HAS_IOPORT
+	depends on SPARC || COMPILE_TEST
 	help
 	  If you say Y here you will get support for the TI
 	  BQ4802 RTC chip.

From 3c87b351809f220294aec3c0df7b078ff5c5b15b Mon Sep 17 00:00:00 2001
From: Andrej Picej <andrej.picej@norik.com>
Date: Fri, 23 Jun 2023 10:15:33 +0200
Subject: [PATCH 0140/1189] rtc: rv3028: Add support for
 "aux-voltage-chargeable" property

Property "trickle-resistor-ohms" allows us to set trickle charger
resistor. However there is no possibility to disable it afterwards.

Add support for "aux-voltage-chargeable" property which can be used to
enable/disable the trickle charger circuit explicitly. The default
behavior of the code is kept as it is!

Additionally, lets make sure we only update internal EEPROM in case of a
change. This prevents wear due to excessive EEPROM writes on each probe.

Signed-off-by: Andrej Picej <andrej.picej@norik.com>
Link: https://lore.kernel.org/r/20230623081533.76334-1-andrej.picej@norik.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-rv3028.c | 80 ++++++++++++++++++++++++++++++----------
 1 file changed, 61 insertions(+), 19 deletions(-)

diff --git a/drivers/rtc/rtc-rv3028.c b/drivers/rtc/rtc-rv3028.c
index 076e56f4e01a..e039b472eaa6 100644
--- a/drivers/rtc/rtc-rv3028.c
+++ b/drivers/rtc/rtc-rv3028.c
@@ -855,11 +855,68 @@ static const struct regmap_config regmap_config = {
         .max_register = 0x37,
 };
 
+static u8 rv3028_set_trickle_charger(struct rv3028_data *rv3028,
+				     struct i2c_client *client)
+{
+	int ret, val_old, val;
+	u32 ohms, chargeable;
+
+	ret = regmap_read(rv3028->regmap, RV3028_BACKUP, &val_old);
+	if (ret < 0)
+		return ret;
+
+	/* mask out only trickle charger bits */
+	val_old = val_old & (RV3028_BACKUP_TCE | RV3028_BACKUP_TCR_MASK);
+	val = val_old;
+
+	/* setup trickle charger */
+	if (!device_property_read_u32(&client->dev, "trickle-resistor-ohms",
+				      &ohms)) {
+		int i;
+
+		for (i = 0; i < ARRAY_SIZE(rv3028_trickle_resistors); i++)
+			if (ohms == rv3028_trickle_resistors[i])
+				break;
+
+		if (i < ARRAY_SIZE(rv3028_trickle_resistors)) {
+			/* enable trickle charger and its resistor */
+			val = RV3028_BACKUP_TCE | i;
+		} else {
+			dev_warn(&client->dev, "invalid trickle resistor value\n");
+		}
+	}
+
+	if (!device_property_read_u32(&client->dev, "aux-voltage-chargeable",
+				      &chargeable)) {
+		switch (chargeable) {
+		case 0:
+			val &= ~RV3028_BACKUP_TCE;
+			break;
+		case 1:
+			val |= RV3028_BACKUP_TCE;
+			break;
+		default:
+			dev_warn(&client->dev,
+				 "unsupported aux-voltage-chargeable value\n");
+			break;
+		}
+	}
+
+	/* only update EEPROM if changes are necessary */
+	if (val_old != val) {
+		ret = rv3028_update_cfg(rv3028, RV3028_BACKUP, RV3028_BACKUP_TCE |
+						RV3028_BACKUP_TCR_MASK, val);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+
 static int rv3028_probe(struct i2c_client *client)
 {
 	struct rv3028_data *rv3028;
 	int ret, status;
-	u32 ohms;
 	struct nvmem_config nvmem_cfg = {
 		.name = "rv3028_nvram",
 		.word_size = 1,
@@ -937,24 +994,9 @@ static int rv3028_probe(struct i2c_client *client)
 	if (ret)
 		return ret;
 
-	/* setup trickle charger */
-	if (!device_property_read_u32(&client->dev, "trickle-resistor-ohms",
-				      &ohms)) {
-		int i;
-
-		for (i = 0; i < ARRAY_SIZE(rv3028_trickle_resistors); i++)
-			if (ohms == rv3028_trickle_resistors[i])
-				break;
-
-		if (i < ARRAY_SIZE(rv3028_trickle_resistors)) {
-			ret = rv3028_update_cfg(rv3028, RV3028_BACKUP, RV3028_BACKUP_TCE |
-						 RV3028_BACKUP_TCR_MASK, RV3028_BACKUP_TCE | i);
-			if (ret)
-				return ret;
-		} else {
-			dev_warn(&client->dev, "invalid trickle resistor value\n");
-		}
-	}
+	ret = rv3028_set_trickle_charger(rv3028, client);
+	if (ret)
+		return ret;
 
 	ret = rtc_add_group(rv3028->rtc, &rv3028_attr_group);
 	if (ret)

From 574ca75f8d2935053872aa1b15d8ba24bfb5e51c Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Fri, 14 Jul 2023 11:46:23 -0600
Subject: [PATCH 0141/1189] i3c: Explicitly include correct DT includes

The DT of_device.h and of_platform.h date back to the separate
of_platform_bus_type before it as merged into the regular platform bus.
As part of that merge prepping Arm DT support 13 years ago, they
"temporarily" include each other. They also include platform_device.h
and of.h. As a result, there's a pretty much random mix of those include
files used throughout the tree. In order to detangle these headers and
replace the implicit includes with struct declarations, users need to
explicitly include the correct includes.

Signed-off-by: Rob Herring <robh@kernel.org>
Reviewed-by: Jeremy Kerr <jk@codeconstruct.com.au>
Link: https://lore.kernel.org/r/20230714174623.4057784-1-robh@kernel.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/ast2600-i3c-master.c | 1 -
 drivers/i3c/master/i3c-master-cdns.c    | 1 -
 2 files changed, 2 deletions(-)

diff --git a/drivers/i3c/master/ast2600-i3c-master.c b/drivers/i3c/master/ast2600-i3c-master.c
index 09ed19d489e9..01a47d3dd499 100644
--- a/drivers/i3c/master/ast2600-i3c-master.c
+++ b/drivers/i3c/master/ast2600-i3c-master.c
@@ -8,7 +8,6 @@
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
 
diff --git a/drivers/i3c/master/i3c-master-cdns.c b/drivers/i3c/master/i3c-master-cdns.c
index 01610fa5b0cc..49551db71bc9 100644
--- a/drivers/i3c/master/i3c-master-cdns.c
+++ b/drivers/i3c/master/i3c-master-cdns.c
@@ -22,7 +22,6 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/workqueue.h>
-#include <linux/of_device.h>
 
 #define DEV_ID				0x0
 #define DEV_ID_I3C_MASTER		0x5034

From 48144c2890503b919bc8ee128b63e37008d69250 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Mon, 24 Jul 2023 14:54:54 -0600
Subject: [PATCH 0142/1189] rtc: Explicitly include correct DT includes

The DT of_device.h and of_platform.h date back to the separate
of_platform_bus_type before it as merged into the regular platform bus.
As part of that merge prepping Arm DT support 13 years ago, they
"temporarily" include each other. They also include platform_device.h
and of.h. As a result, there's a pretty much random mix of those include
files used throughout the tree. In order to detangle these headers and
replace the implicit includes with struct declarations, users need to
explicitly include the correct includes.

Signed-off-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230724205456.767430-1-robh@kernel.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-abx80x.c        | 2 +-
 drivers/rtc/rtc-armada38x.c     | 1 -
 drivers/rtc/rtc-at91rm9200.c    | 1 -
 drivers/rtc/rtc-ds1742.c        | 1 -
 drivers/rtc/rtc-fsl-ftm-alarm.c | 5 +----
 drivers/rtc/rtc-isl12026.c      | 1 -
 drivers/rtc/rtc-isl1208.c       | 2 +-
 drivers/rtc/rtc-jz4740.c        | 2 +-
 drivers/rtc/rtc-lpc24xx.c       | 3 +--
 drivers/rtc/rtc-m41t80.c        | 2 +-
 drivers/rtc/rtc-mpc5121.c       | 4 +---
 drivers/rtc/rtc-mt6397.c        | 2 +-
 drivers/rtc/rtc-mt7622.c        | 4 ++--
 drivers/rtc/rtc-mxc.c           | 1 -
 drivers/rtc/rtc-pcf85063.c      | 2 +-
 drivers/rtc/rtc-pcf85363.c      | 1 -
 drivers/rtc/rtc-pxa.c           | 1 -
 drivers/rtc/rtc-rs5c372.c       | 2 +-
 drivers/rtc/rtc-rv3028.c        | 2 +-
 drivers/rtc/rtc-rv3032.c        | 2 +-
 drivers/rtc/rtc-rv8803.c        | 2 +-
 drivers/rtc/rtc-rx6110.c        | 1 -
 drivers/rtc/rtc-rx8581.c        | 1 -
 drivers/rtc/rtc-rzn1.c          | 2 +-
 drivers/rtc/rtc-s3c.c           | 1 -
 drivers/rtc/rtc-stm32.c         | 3 ++-
 drivers/rtc/rtc-stmp3xxx.c      | 1 -
 drivers/rtc/rtc-sun6i.c         | 1 -
 drivers/rtc/rtc-sunxi.c         | 2 --
 drivers/rtc/rtc-ti-k3.c         | 2 +-
 30 files changed, 19 insertions(+), 38 deletions(-)

diff --git a/drivers/rtc/rtc-abx80x.c b/drivers/rtc/rtc-abx80x.c
index e08d3181bd2a..fde2b8054c2e 100644
--- a/drivers/rtc/rtc-abx80x.c
+++ b/drivers/rtc/rtc-abx80x.c
@@ -15,7 +15,7 @@
 #include <linux/i2c.h>
 #include <linux/kstrtox.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/rtc.h>
 #include <linux/watchdog.h>
 
diff --git a/drivers/rtc/rtc-armada38x.c b/drivers/rtc/rtc-armada38x.c
index b4139c200676..8abcad38b10c 100644
--- a/drivers/rtc/rtc-armada38x.c
+++ b/drivers/rtc/rtc-armada38x.c
@@ -11,7 +11,6 @@
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/rtc.h>
 
diff --git a/drivers/rtc/rtc-at91rm9200.c b/drivers/rtc/rtc-at91rm9200.c
index e9d17232d0a8..245588a7b417 100644
--- a/drivers/rtc/rtc-at91rm9200.c
+++ b/drivers/rtc/rtc-at91rm9200.c
@@ -22,7 +22,6 @@
 #include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/rtc.h>
diff --git a/drivers/rtc/rtc-ds1742.c b/drivers/rtc/rtc-ds1742.c
index a5026b0514e7..6ae8b9a294fe 100644
--- a/drivers/rtc/rtc-ds1742.c
+++ b/drivers/rtc/rtc-ds1742.c
@@ -16,7 +16,6 @@
 #include <linux/jiffies.h>
 #include <linux/rtc.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/io.h>
 #include <linux/module.h>
diff --git a/drivers/rtc/rtc-fsl-ftm-alarm.c b/drivers/rtc/rtc-fsl-ftm-alarm.c
index 3d7c4077fe1c..a72c4ad0cec6 100644
--- a/drivers/rtc/rtc-fsl-ftm-alarm.c
+++ b/drivers/rtc/rtc-fsl-ftm-alarm.c
@@ -11,11 +11,8 @@
 #include <linux/err.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
 #include <linux/platform_device.h>
-#include <linux/of.h>
-#include <linux/of_device.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/fsl/ftm.h>
 #include <linux/rtc.h>
diff --git a/drivers/rtc/rtc-isl12026.c b/drivers/rtc/rtc-isl12026.c
index 5abff5d348ac..8b00659fc955 100644
--- a/drivers/rtc/rtc-isl12026.c
+++ b/drivers/rtc/rtc-isl12026.c
@@ -11,7 +11,6 @@
 #include <linux/mutex.h>
 #include <linux/nvmem-provider.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/rtc.h>
 #include <linux/slab.h>
 
diff --git a/drivers/rtc/rtc-isl1208.c b/drivers/rtc/rtc-isl1208.c
index 57e77b55e484..712ca652d6d3 100644
--- a/drivers/rtc/rtc-isl1208.c
+++ b/drivers/rtc/rtc-isl1208.c
@@ -9,7 +9,7 @@
 #include <linux/clk.h>
 #include <linux/i2c.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/of_irq.h>
 #include <linux/rtc.h>
 
diff --git a/drivers/rtc/rtc-jz4740.c b/drivers/rtc/rtc-jz4740.c
index 36453b008139..6ba889d7d4c4 100644
--- a/drivers/rtc/rtc-jz4740.c
+++ b/drivers/rtc/rtc-jz4740.c
@@ -11,7 +11,7 @@
 #include <linux/iopoll.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/pm_wakeirq.h>
 #include <linux/property.h>
diff --git a/drivers/rtc/rtc-lpc24xx.c b/drivers/rtc/rtc-lpc24xx.c
index a4612e543f35..df17c48ff086 100644
--- a/drivers/rtc/rtc-lpc24xx.c
+++ b/drivers/rtc/rtc-lpc24xx.c
@@ -9,9 +9,8 @@
 #include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/rtc.h>
 
diff --git a/drivers/rtc/rtc-m41t80.c b/drivers/rtc/rtc-m41t80.c
index 3cc5151e0986..866489ad56d6 100644
--- a/drivers/rtc/rtc-m41t80.c
+++ b/drivers/rtc/rtc-m41t80.c
@@ -17,7 +17,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/rtc.h>
 #include <linux/slab.h>
 #include <linux/mutex.h>
diff --git a/drivers/rtc/rtc-mpc5121.c b/drivers/rtc/rtc-mpc5121.c
index 07df43e4c4d0..28858fcaea8f 100644
--- a/drivers/rtc/rtc-mpc5121.c
+++ b/drivers/rtc/rtc-mpc5121.c
@@ -11,10 +11,8 @@
 #include <linux/module.h>
 #include <linux/rtc.h>
 #include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_device.h>
 #include <linux/of_irq.h>
-#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/io.h>
 #include <linux/slab.h>
 
diff --git a/drivers/rtc/rtc-mt6397.c b/drivers/rtc/rtc-mt6397.c
index 1d297af80f87..1617063669cc 100644
--- a/drivers/rtc/rtc-mt6397.c
+++ b/drivers/rtc/rtc-mt6397.c
@@ -9,7 +9,7 @@
 #include <linux/mfd/mt6397/core.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
 #include <linux/rtc.h>
diff --git a/drivers/rtc/rtc-mt7622.c b/drivers/rtc/rtc-mt7622.c
index 81857a457c32..094c649fc137 100644
--- a/drivers/rtc/rtc-mt7622.c
+++ b/drivers/rtc/rtc-mt7622.c
@@ -7,9 +7,9 @@
 
 #include <linux/clk.h>
 #include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of_address.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/rtc.h>
 
diff --git a/drivers/rtc/rtc-mxc.c b/drivers/rtc/rtc-mxc.c
index 762cf03345f1..dbb935dbbd8a 100644
--- a/drivers/rtc/rtc-mxc.c
+++ b/drivers/rtc/rtc-mxc.c
@@ -11,7 +11,6 @@
 #include <linux/pm_wakeirq.h>
 #include <linux/clk.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 
 #define RTC_INPUT_CLK_32768HZ	(0x00 << 5)
 #define RTC_INPUT_CLK_32000HZ	(0x01 << 5)
diff --git a/drivers/rtc/rtc-pcf85063.c b/drivers/rtc/rtc-pcf85063.c
index f501b6f9ed01..fdbc07f14036 100644
--- a/drivers/rtc/rtc-pcf85063.c
+++ b/drivers/rtc/rtc-pcf85063.c
@@ -14,7 +14,7 @@
 #include <linux/bcd.h>
 #include <linux/rtc.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/pm_wakeirq.h>
 #include <linux/regmap.h>
 
diff --git a/drivers/rtc/rtc-pcf85363.c b/drivers/rtc/rtc-pcf85363.c
index 65b8b1338dbb..569c79bac0ee 100644
--- a/drivers/rtc/rtc-pcf85363.c
+++ b/drivers/rtc/rtc-pcf85363.c
@@ -15,7 +15,6 @@
 #include <linux/errno.h>
 #include <linux/bcd.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/regmap.h>
 
 /*
diff --git a/drivers/rtc/rtc-pxa.c b/drivers/rtc/rtc-pxa.c
index eeacf480cf36..e400c78252e8 100644
--- a/drivers/rtc/rtc-pxa.c
+++ b/drivers/rtc/rtc-pxa.c
@@ -14,7 +14,6 @@
 #include <linux/io.h>
 #include <linux/slab.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 
 #include "rtc-sa1100.h"
 
diff --git a/drivers/rtc/rtc-rs5c372.c b/drivers/rtc/rtc-rs5c372.c
index a5a6c8772ecd..ecabeef09196 100644
--- a/drivers/rtc/rtc-rs5c372.c
+++ b/drivers/rtc/rtc-rs5c372.c
@@ -12,7 +12,7 @@
 #include <linux/bcd.h>
 #include <linux/slab.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 
 /*
  * Ricoh has a family of I2C based RTCs, which differ only slightly from
diff --git a/drivers/rtc/rtc-rv3028.c b/drivers/rtc/rtc-rv3028.c
index e039b472eaa6..2f001c59c61d 100644
--- a/drivers/rtc/rtc-rv3028.c
+++ b/drivers/rtc/rtc-rv3028.c
@@ -17,7 +17,7 @@
 #include <linux/kernel.h>
 #include <linux/log2.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/regmap.h>
 #include <linux/rtc.h>
 
diff --git a/drivers/rtc/rtc-rv3032.c b/drivers/rtc/rtc-rv3032.c
index 6b8eb2039a33..35b2e36b426a 100644
--- a/drivers/rtc/rtc-rv3032.c
+++ b/drivers/rtc/rtc-rv3032.c
@@ -19,7 +19,7 @@
 #include <linux/kernel.h>
 #include <linux/log2.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/regmap.h>
 #include <linux/rtc.h>
 
diff --git a/drivers/rtc/rtc-rv8803.c b/drivers/rtc/rtc-rv8803.c
index 98679cae13e8..fd8ab0b2f731 100644
--- a/drivers/rtc/rtc-rv8803.c
+++ b/drivers/rtc/rtc-rv8803.c
@@ -15,7 +15,7 @@
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/rtc.h>
 
 #define RV8803_I2C_TRY_COUNT		4
diff --git a/drivers/rtc/rtc-rx6110.c b/drivers/rtc/rtc-rx6110.c
index 8702db6096ba..834274db8c3f 100644
--- a/drivers/rtc/rtc-rx6110.c
+++ b/drivers/rtc/rtc-rx6110.c
@@ -13,7 +13,6 @@
 #include <linux/regmap.h>
 #include <linux/rtc.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/spi/spi.h>
 #include <linux/i2c.h>
 
diff --git a/drivers/rtc/rtc-rx8581.c b/drivers/rtc/rtc-rx8581.c
index 82881fd2e14a..48efd61a114d 100644
--- a/drivers/rtc/rtc-rx8581.c
+++ b/drivers/rtc/rtc-rx8581.c
@@ -13,7 +13,6 @@
 #include <linux/i2c.h>
 #include <linux/bcd.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/regmap.h>
 #include <linux/rtc.h>
 #include <linux/log2.h>
diff --git a/drivers/rtc/rtc-rzn1.c b/drivers/rtc/rtc-rzn1.c
index dca736caba85..6f98969eedca 100644
--- a/drivers/rtc/rtc-rzn1.c
+++ b/drivers/rtc/rtc-rzn1.c
@@ -15,7 +15,7 @@
 #include <linux/init.h>
 #include <linux/iopoll.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/mod_devicetable.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/rtc.h>
diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c
index 70e1a18e5efd..282238818f63 100644
--- a/drivers/rtc/rtc-s3c.c
+++ b/drivers/rtc/rtc-s3c.c
@@ -23,7 +23,6 @@
 #include <linux/log2.h>
 #include <linux/slab.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/uaccess.h>
 #include <linux/io.h>
 
diff --git a/drivers/rtc/rtc-stm32.c b/drivers/rtc/rtc-stm32.c
index 85689192fa7a..3ae875b19af8 100644
--- a/drivers/rtc/rtc-stm32.c
+++ b/drivers/rtc/rtc-stm32.c
@@ -11,7 +11,8 @@
 #include <linux/ioport.h>
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
 #include <linux/pm_wakeirq.h>
 #include <linux/regmap.h>
 #include <linux/rtc.h>
diff --git a/drivers/rtc/rtc-stmp3xxx.c b/drivers/rtc/rtc-stmp3xxx.c
index 6f11b745f34d..7566d0a44af8 100644
--- a/drivers/rtc/rtc-stmp3xxx.c
+++ b/drivers/rtc/rtc-stmp3xxx.c
@@ -18,7 +18,6 @@
 #include <linux/delay.h>
 #include <linux/rtc.h>
 #include <linux/slab.h>
-#include <linux/of_device.h>
 #include <linux/of.h>
 #include <linux/stmp_device.h>
 #include <linux/stmp3xxx_rtc_wdt.h>
diff --git a/drivers/rtc/rtc-sun6i.c b/drivers/rtc/rtc-sun6i.c
index 71548dd59a3a..753a2d9c8a17 100644
--- a/drivers/rtc/rtc-sun6i.c
+++ b/drivers/rtc/rtc-sun6i.c
@@ -24,7 +24,6 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/rtc.h>
 #include <linux/slab.h>
diff --git a/drivers/rtc/rtc-sunxi.c b/drivers/rtc/rtc-sunxi.c
index 5d019e3a835a..5cab9953c44f 100644
--- a/drivers/rtc/rtc-sunxi.c
+++ b/drivers/rtc/rtc-sunxi.c
@@ -14,8 +14,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/rtc.h>
 #include <linux/types.h>
diff --git a/drivers/rtc/rtc-ti-k3.c b/drivers/rtc/rtc-ti-k3.c
index 0d90fe923355..ec759d8f7023 100644
--- a/drivers/rtc/rtc-ti-k3.c
+++ b/drivers/rtc/rtc-ti-k3.c
@@ -9,7 +9,7 @@
 #include <linux/delay.h>
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/sys_soc.h>
 #include <linux/property.h>

From 58f3e83260a78cfd5648efa5448b237b9c230fc0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 25 Jul 2023 09:04:29 +0200
Subject: [PATCH 0143/1189] rtc: isl12026: Drop "_new" from probe callback name
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The driver was introduced when .probe_new was the right probe callback
to use for i2c drivers. Today .probe is the right one (again) and the
driver was already switched in commit 31b0cecb4042 ("rtc: Switch i2c
drivers back to use .probe()") but the name continued to include "_new"
in its name.

To prevent code readers wondering about what might be new here, drop
that irritating part of the name.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230725070429.383070-1-u.kleine-koenig@pengutronix.de
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-isl12026.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/rtc/rtc-isl12026.c b/drivers/rtc/rtc-isl12026.c
index 8b00659fc955..2aabb9151d4c 100644
--- a/drivers/rtc/rtc-isl12026.c
+++ b/drivers/rtc/rtc-isl12026.c
@@ -428,7 +428,7 @@ static void isl12026_force_power_modes(struct i2c_client *client)
 	}
 }
 
-static int isl12026_probe_new(struct i2c_client *client)
+static int isl12026_probe(struct i2c_client *client)
 {
 	struct isl12026 *priv;
 	int ret;
@@ -489,7 +489,7 @@ static struct i2c_driver isl12026_driver = {
 		.name	= "rtc-isl12026",
 		.of_match_table = isl12026_dt_match,
 	},
-	.probe		= isl12026_probe_new,
+	.probe		= isl12026_probe,
 	.remove		= isl12026_remove,
 };
 

From 018121e655c8ac2b369f70758dbddf7a37ef534f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 25 Jul 2023 10:19:45 +0200
Subject: [PATCH 0144/1189] pwm: Remove outdated documentation for
 pwmchip_remove()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

pwmchip_remove() returns void since some time but the documentation still
mentions the situations where it used to return an error code. Just remove
this old and now wrong text.

Fixes: 8083f58d08fd ("pwm: Make pwmchip_remove() return void")
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/core.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index 11f2f1fd0846..00e85acd92c4 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -313,10 +313,7 @@ EXPORT_SYMBOL_GPL(pwmchip_add);
  * pwmchip_remove() - remove a PWM chip
  * @chip: the PWM chip to remove
  *
- * Removes a PWM chip. This function may return busy if the PWM chip provides
- * a PWM device that is still requested.
- *
- * Returns: 0 on success or a negative error code on failure.
+ * Removes a PWM chip.
  */
 void pwmchip_remove(struct pwm_chip *chip)
 {

From bdebe27e3dc22c11c72b0d1ef4ed30355f154e58 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Tue, 25 Jul 2023 14:59:21 +0100
Subject: [PATCH 0145/1189] pwm: rz-mtu3: Fix build warning 'num_channel_ios'
 not described

Fix the below build warning:
warning: Function parameter or member 'num_channel_ios' not described
in 'rz_mtu3_channel_io_map'

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-rz-mtu3.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pwm/pwm-rz-mtu3.c b/drivers/pwm/pwm-rz-mtu3.c
index bed8bd671e37..a56cecb0e46e 100644
--- a/drivers/pwm/pwm-rz-mtu3.c
+++ b/drivers/pwm/pwm-rz-mtu3.c
@@ -40,7 +40,7 @@
  * struct rz_mtu3_channel_io_map - MTU3 pwm channel map
  *
  * @base_pwm_number: First PWM of a channel
- * @num: number of IOs on the HW channel.
+ * @num_channel_ios: number of IOs on the HW channel.
  */
 struct rz_mtu3_channel_io_map {
 	u8 base_pwm_number;

From 84c33f4278249aecb49375fb884b0b14a3664a63 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 28 Jul 2023 09:12:59 +0200
Subject: [PATCH 0146/1189] pwm: Drop unused #include <linux/radix-tree.h>
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

core.c doens't use any of the symbols provided by linux/radix-tree.h
and compiles just fine without this include. So drop the #include.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/core.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index 00e85acd92c4..b4703dfc9e4d 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -10,7 +10,6 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/pwm.h>
-#include <linux/radix-tree.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
 #include <linux/err.h>

From 0323e8fedd1ef25342cf7abf3a2024f5670362b8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 19 Jul 2023 21:20:09 +0200
Subject: [PATCH 0147/1189] pwm: atmel-tcb: Harmonize resource allocation order
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Allocate driver data as first resource in the probe function. This way it
can be used during allocation of the other resources (instead of assigning
these to local variables first and update driver data only when it's
allocated). Also as driver data is allocated using a devm function this
should happen first to have the order of freeing resources in the error
path and the remove function in reverse.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-atmel-tcb.c | 49 +++++++++++++++----------------------
 1 file changed, 20 insertions(+), 29 deletions(-)

diff --git a/drivers/pwm/pwm-atmel-tcb.c b/drivers/pwm/pwm-atmel-tcb.c
index 563162d660d8..c20054a68368 100644
--- a/drivers/pwm/pwm-atmel-tcb.c
+++ b/drivers/pwm/pwm-atmel-tcb.c
@@ -421,13 +421,14 @@ static int atmel_tcb_pwm_probe(struct platform_device *pdev)
 	struct atmel_tcb_pwm_chip *tcbpwm;
 	const struct atmel_tcb_config *config;
 	struct device_node *np = pdev->dev.of_node;
-	struct regmap *regmap;
-	struct clk *clk, *gclk = NULL;
-	struct clk *slow_clk;
 	char clk_name[] = "t0_clk";
 	int err;
 	int channel;
 
+	tcbpwm = devm_kzalloc(&pdev->dev, sizeof(*tcbpwm), GFP_KERNEL);
+	if (tcbpwm == NULL)
+		return -ENOMEM;
+
 	err = of_property_read_u32(np, "reg", &channel);
 	if (err < 0) {
 		dev_err(&pdev->dev,
@@ -436,47 +437,37 @@ static int atmel_tcb_pwm_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	regmap = syscon_node_to_regmap(np->parent);
-	if (IS_ERR(regmap))
-		return PTR_ERR(regmap);
+	tcbpwm->regmap = syscon_node_to_regmap(np->parent);
+	if (IS_ERR(tcbpwm->regmap))
+		return PTR_ERR(tcbpwm->regmap);
 
-	slow_clk = of_clk_get_by_name(np->parent, "slow_clk");
-	if (IS_ERR(slow_clk))
-		return PTR_ERR(slow_clk);
+	tcbpwm->slow_clk = of_clk_get_by_name(np->parent, "slow_clk");
+	if (IS_ERR(tcbpwm->slow_clk))
+		return PTR_ERR(tcbpwm->slow_clk);
 
 	clk_name[1] += channel;
-	clk = of_clk_get_by_name(np->parent, clk_name);
-	if (IS_ERR(clk))
-		clk = of_clk_get_by_name(np->parent, "t0_clk");
-	if (IS_ERR(clk))
-		return PTR_ERR(clk);
+	tcbpwm->clk = of_clk_get_by_name(np->parent, clk_name);
+	if (IS_ERR(tcbpwm->clk))
+		tcbpwm->clk = of_clk_get_by_name(np->parent, "t0_clk");
+	if (IS_ERR(tcbpwm->clk))
+		return PTR_ERR(tcbpwm->clk);
 
 	match = of_match_node(atmel_tcb_of_match, np->parent);
 	config = match->data;
 
 	if (config->has_gclk) {
-		gclk = of_clk_get_by_name(np->parent, "gclk");
-		if (IS_ERR(gclk))
-			return PTR_ERR(gclk);
-	}
-
-	tcbpwm = devm_kzalloc(&pdev->dev, sizeof(*tcbpwm), GFP_KERNEL);
-	if (tcbpwm == NULL) {
-		err = -ENOMEM;
-		goto err_slow_clk;
+		tcbpwm->gclk = of_clk_get_by_name(np->parent, "gclk");
+		if (IS_ERR(tcbpwm->gclk))
+			return PTR_ERR(tcbpwm->gclk);
 	}
 
 	tcbpwm->chip.dev = &pdev->dev;
 	tcbpwm->chip.ops = &atmel_tcb_pwm_ops;
 	tcbpwm->chip.npwm = NPWM;
 	tcbpwm->channel = channel;
-	tcbpwm->regmap = regmap;
-	tcbpwm->clk = clk;
-	tcbpwm->gclk = gclk;
-	tcbpwm->slow_clk = slow_clk;
 	tcbpwm->width = config->counter_width;
 
-	err = clk_prepare_enable(slow_clk);
+	err = clk_prepare_enable(tcbpwm->slow_clk);
 	if (err)
 		goto err_slow_clk;
 
@@ -494,7 +485,7 @@ err_disable_clk:
 	clk_disable_unprepare(tcbpwm->slow_clk);
 
 err_slow_clk:
-	clk_put(slow_clk);
+	clk_put(tcbpwm->slow_clk);
 
 	return err;
 }

From c11622324c023415fb69196c5fc3782d2b8cced0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 19 Jul 2023 21:20:10 +0200
Subject: [PATCH 0148/1189] pwm: atmel-tcb: Fix resource freeing in error path
 and remove
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Several resources were not freed in the error path and the remove
function. Add the forgotten items.

Fixes: 34cbcd72588f ("pwm: atmel-tcb: Add sama5d2 support")
Fixes: 061f8572a31c ("pwm: atmel-tcb: Switch to new binding")
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Claudiu Beznea <claudiu.beznea@tuxon.dev>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-atmel-tcb.c | 23 +++++++++++++++++------
 1 file changed, 17 insertions(+), 6 deletions(-)

diff --git a/drivers/pwm/pwm-atmel-tcb.c b/drivers/pwm/pwm-atmel-tcb.c
index c20054a68368..825dd04b86a7 100644
--- a/drivers/pwm/pwm-atmel-tcb.c
+++ b/drivers/pwm/pwm-atmel-tcb.c
@@ -449,16 +449,20 @@ static int atmel_tcb_pwm_probe(struct platform_device *pdev)
 	tcbpwm->clk = of_clk_get_by_name(np->parent, clk_name);
 	if (IS_ERR(tcbpwm->clk))
 		tcbpwm->clk = of_clk_get_by_name(np->parent, "t0_clk");
-	if (IS_ERR(tcbpwm->clk))
-		return PTR_ERR(tcbpwm->clk);
+	if (IS_ERR(tcbpwm->clk)) {
+		err = PTR_ERR(tcbpwm->clk);
+		goto err_slow_clk;
+	}
 
 	match = of_match_node(atmel_tcb_of_match, np->parent);
 	config = match->data;
 
 	if (config->has_gclk) {
 		tcbpwm->gclk = of_clk_get_by_name(np->parent, "gclk");
-		if (IS_ERR(tcbpwm->gclk))
-			return PTR_ERR(tcbpwm->gclk);
+		if (IS_ERR(tcbpwm->gclk)) {
+			err = PTR_ERR(tcbpwm->gclk);
+			goto err_clk;
+		}
 	}
 
 	tcbpwm->chip.dev = &pdev->dev;
@@ -469,7 +473,7 @@ static int atmel_tcb_pwm_probe(struct platform_device *pdev)
 
 	err = clk_prepare_enable(tcbpwm->slow_clk);
 	if (err)
-		goto err_slow_clk;
+		goto err_gclk;
 
 	spin_lock_init(&tcbpwm->lock);
 
@@ -484,6 +488,12 @@ static int atmel_tcb_pwm_probe(struct platform_device *pdev)
 err_disable_clk:
 	clk_disable_unprepare(tcbpwm->slow_clk);
 
+err_gclk:
+	clk_put(tcbpwm->gclk);
+
+err_clk:
+	clk_put(tcbpwm->clk);
+
 err_slow_clk:
 	clk_put(tcbpwm->slow_clk);
 
@@ -497,8 +507,9 @@ static void atmel_tcb_pwm_remove(struct platform_device *pdev)
 	pwmchip_remove(&tcbpwm->chip);
 
 	clk_disable_unprepare(tcbpwm->slow_clk);
-	clk_put(tcbpwm->slow_clk);
+	clk_put(tcbpwm->gclk);
 	clk_put(tcbpwm->clk);
+	clk_put(tcbpwm->slow_clk);
 }
 
 static const struct of_device_id atmel_tcb_pwm_dt_ids[] = {

From 78dca23bd6706dd6a3cdb5c0052f48794b4d2bed Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 19 Jul 2023 21:20:11 +0200
Subject: [PATCH 0149/1189] pwm: atmel-tcb: Put per-channel data into driver
 data
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This simplifies the code, reduces the number of memory allocations and
pointer dereferences.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Claudiu Beznea <claudiu.beznea@tuxon.dev>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-atmel-tcb.c | 29 +++++++++--------------------
 1 file changed, 9 insertions(+), 20 deletions(-)

diff --git a/drivers/pwm/pwm-atmel-tcb.c b/drivers/pwm/pwm-atmel-tcb.c
index 825dd04b86a7..8d0b74b0307c 100644
--- a/drivers/pwm/pwm-atmel-tcb.c
+++ b/drivers/pwm/pwm-atmel-tcb.c
@@ -56,7 +56,7 @@ struct atmel_tcb_pwm_chip {
 	struct clk *clk;
 	struct clk *gclk;
 	struct clk *slow_clk;
-	struct atmel_tcb_pwm_device *pwms[NPWM];
+	struct atmel_tcb_pwm_device pwms[NPWM];
 	struct atmel_tcb_channel bkup;
 };
 
@@ -72,7 +72,7 @@ static int atmel_tcb_pwm_set_polarity(struct pwm_chip *chip,
 				      enum pwm_polarity polarity)
 {
 	struct atmel_tcb_pwm_chip *tcbpwmc = to_tcb_chip(chip);
-	struct atmel_tcb_pwm_device *tcbpwm = tcbpwmc->pwms[pwm->hwpwm];
+	struct atmel_tcb_pwm_device *tcbpwm = &tcbpwmc->pwms[pwm->hwpwm];
 
 	tcbpwm->polarity = polarity;
 
@@ -83,19 +83,13 @@ static int atmel_tcb_pwm_request(struct pwm_chip *chip,
 				 struct pwm_device *pwm)
 {
 	struct atmel_tcb_pwm_chip *tcbpwmc = to_tcb_chip(chip);
-	struct atmel_tcb_pwm_device *tcbpwm;
+	struct atmel_tcb_pwm_device *tcbpwm = &tcbpwmc->pwms[pwm->hwpwm];
 	unsigned cmr;
 	int ret;
 
-	tcbpwm = devm_kzalloc(chip->dev, sizeof(*tcbpwm), GFP_KERNEL);
-	if (!tcbpwm)
-		return -ENOMEM;
-
 	ret = clk_prepare_enable(tcbpwmc->clk);
-	if (ret) {
-		devm_kfree(chip->dev, tcbpwm);
+	if (ret)
 		return ret;
-	}
 
 	tcbpwm->polarity = PWM_POLARITY_NORMAL;
 	tcbpwm->duty = 0;
@@ -130,25 +124,20 @@ static int atmel_tcb_pwm_request(struct pwm_chip *chip,
 	regmap_write(tcbpwmc->regmap, ATMEL_TC_REG(tcbpwmc->channel, CMR), cmr);
 	spin_unlock(&tcbpwmc->lock);
 
-	tcbpwmc->pwms[pwm->hwpwm] = tcbpwm;
-
 	return 0;
 }
 
 static void atmel_tcb_pwm_free(struct pwm_chip *chip, struct pwm_device *pwm)
 {
 	struct atmel_tcb_pwm_chip *tcbpwmc = to_tcb_chip(chip);
-	struct atmel_tcb_pwm_device *tcbpwm = tcbpwmc->pwms[pwm->hwpwm];
 
 	clk_disable_unprepare(tcbpwmc->clk);
-	tcbpwmc->pwms[pwm->hwpwm] = NULL;
-	devm_kfree(chip->dev, tcbpwm);
 }
 
 static void atmel_tcb_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
 {
 	struct atmel_tcb_pwm_chip *tcbpwmc = to_tcb_chip(chip);
-	struct atmel_tcb_pwm_device *tcbpwm = tcbpwmc->pwms[pwm->hwpwm];
+	struct atmel_tcb_pwm_device *tcbpwm = &tcbpwmc->pwms[pwm->hwpwm];
 	unsigned cmr;
 	enum pwm_polarity polarity = tcbpwm->polarity;
 
@@ -205,7 +194,7 @@ static void atmel_tcb_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
 static int atmel_tcb_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm)
 {
 	struct atmel_tcb_pwm_chip *tcbpwmc = to_tcb_chip(chip);
-	struct atmel_tcb_pwm_device *tcbpwm = tcbpwmc->pwms[pwm->hwpwm];
+	struct atmel_tcb_pwm_device *tcbpwm = &tcbpwmc->pwms[pwm->hwpwm];
 	u32 cmr;
 	enum pwm_polarity polarity = tcbpwm->polarity;
 
@@ -290,7 +279,7 @@ static int atmel_tcb_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
 				int duty_ns, int period_ns)
 {
 	struct atmel_tcb_pwm_chip *tcbpwmc = to_tcb_chip(chip);
-	struct atmel_tcb_pwm_device *tcbpwm = tcbpwmc->pwms[pwm->hwpwm];
+	struct atmel_tcb_pwm_device *tcbpwm = &tcbpwmc->pwms[pwm->hwpwm];
 	struct atmel_tcb_pwm_device *atcbpwm = NULL;
 	int i = 0;
 	int slowclk = 0;
@@ -337,9 +326,9 @@ static int atmel_tcb_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
 	period = div_u64(period_ns, min);
 
 	if (pwm->hwpwm == 0)
-		atcbpwm = tcbpwmc->pwms[1];
+		atcbpwm = &tcbpwmc->pwms[1];
 	else
-		atcbpwm = tcbpwmc->pwms[0];
+		atcbpwm = &tcbpwmc->pwms[0];
 
 	/*
 	 * PWM devices provided by the TCB driver are grouped by 2.

From 9a6ac822a2153d583b0da95b8693e954b5f4203a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 19 Jul 2023 21:20:12 +0200
Subject: [PATCH 0150/1189] pwm: atmel-tcb: Unroll atmel_tcb_pwm_set_polarity()
 into only caller
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

atmel_tcb_pwm_set_polarity() is only called once and effectively wraps
an assignment only. Replace the function call by the respective
assignment.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Claudiu Beznea <claudiu.beznea@tuxon.dev>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-atmel-tcb.c | 17 +++--------------
 1 file changed, 3 insertions(+), 14 deletions(-)

diff --git a/drivers/pwm/pwm-atmel-tcb.c b/drivers/pwm/pwm-atmel-tcb.c
index 8d0b74b0307c..0c220c0a463c 100644
--- a/drivers/pwm/pwm-atmel-tcb.c
+++ b/drivers/pwm/pwm-atmel-tcb.c
@@ -67,18 +67,6 @@ static inline struct atmel_tcb_pwm_chip *to_tcb_chip(struct pwm_chip *chip)
 	return container_of(chip, struct atmel_tcb_pwm_chip, chip);
 }
 
-static int atmel_tcb_pwm_set_polarity(struct pwm_chip *chip,
-				      struct pwm_device *pwm,
-				      enum pwm_polarity polarity)
-{
-	struct atmel_tcb_pwm_chip *tcbpwmc = to_tcb_chip(chip);
-	struct atmel_tcb_pwm_device *tcbpwm = &tcbpwmc->pwms[pwm->hwpwm];
-
-	tcbpwm->polarity = polarity;
-
-	return 0;
-}
-
 static int atmel_tcb_pwm_request(struct pwm_chip *chip,
 				 struct pwm_device *pwm)
 {
@@ -356,11 +344,12 @@ static int atmel_tcb_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
 static int atmel_tcb_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 			       const struct pwm_state *state)
 {
+	struct atmel_tcb_pwm_chip *tcbpwmc = to_tcb_chip(chip);
+	struct atmel_tcb_pwm_device *tcbpwm = &tcbpwmc->pwms[pwm->hwpwm];
 	int duty_cycle, period;
 	int ret;
 
-	/* This function only sets a flag in driver data */
-	atmel_tcb_pwm_set_polarity(chip, pwm, state->polarity);
+	tcbpwm->polarity = state->polarity;
 
 	if (!state->enabled) {
 		atmel_tcb_pwm_disable(chip, pwm);

From 28a1dadc49e2902d0a7a2e8c699a15f93b1b6f40 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 19 Jul 2023 21:20:13 +0200
Subject: [PATCH 0151/1189] pwm: atmel-tcb: Don't track polarity in driver data
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

struct atmel_tcb_pwm_device::polarity is only used in atmel_tcb_pwm_enable
and atmel_tcb_pwm_disable(). These functions are only called by
atmel_tcb_pwm_apply() after the member variable was assigned to
state->polarity. So the value assigned in atmel_tcb_pwm_request() is
never used and the member can be dropped from struct atmel_tcb_pwm_device.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Claudiu Beznea <claudiu.beznea@tuxon.dev>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-atmel-tcb.c | 18 ++++++------------
 1 file changed, 6 insertions(+), 12 deletions(-)

diff --git a/drivers/pwm/pwm-atmel-tcb.c b/drivers/pwm/pwm-atmel-tcb.c
index 0c220c0a463c..c00dd37c5fbd 100644
--- a/drivers/pwm/pwm-atmel-tcb.c
+++ b/drivers/pwm/pwm-atmel-tcb.c
@@ -33,7 +33,6 @@
 				 ATMEL_TC_BEEVT | ATMEL_TC_BSWTRG)
 
 struct atmel_tcb_pwm_device {
-	enum pwm_polarity polarity;	/* PWM polarity */
 	unsigned div;			/* PWM clock divider */
 	unsigned duty;			/* PWM duty expressed in clk cycles */
 	unsigned period;		/* PWM period expressed in clk cycles */
@@ -79,7 +78,6 @@ static int atmel_tcb_pwm_request(struct pwm_chip *chip,
 	if (ret)
 		return ret;
 
-	tcbpwm->polarity = PWM_POLARITY_NORMAL;
 	tcbpwm->duty = 0;
 	tcbpwm->period = 0;
 	tcbpwm->div = 0;
@@ -122,12 +120,12 @@ static void atmel_tcb_pwm_free(struct pwm_chip *chip, struct pwm_device *pwm)
 	clk_disable_unprepare(tcbpwmc->clk);
 }
 
-static void atmel_tcb_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
+static void atmel_tcb_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm,
+				  enum pwm_polarity polarity)
 {
 	struct atmel_tcb_pwm_chip *tcbpwmc = to_tcb_chip(chip);
 	struct atmel_tcb_pwm_device *tcbpwm = &tcbpwmc->pwms[pwm->hwpwm];
 	unsigned cmr;
-	enum pwm_polarity polarity = tcbpwm->polarity;
 
 	/*
 	 * If duty is 0 the timer will be stopped and we have to
@@ -179,12 +177,12 @@ static void atmel_tcb_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
 	spin_unlock(&tcbpwmc->lock);
 }
 
-static int atmel_tcb_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm)
+static int atmel_tcb_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm,
+				enum pwm_polarity polarity)
 {
 	struct atmel_tcb_pwm_chip *tcbpwmc = to_tcb_chip(chip);
 	struct atmel_tcb_pwm_device *tcbpwm = &tcbpwmc->pwms[pwm->hwpwm];
 	u32 cmr;
-	enum pwm_polarity polarity = tcbpwm->polarity;
 
 	/*
 	 * If duty is 0 the timer will be stopped and we have to
@@ -344,15 +342,11 @@ static int atmel_tcb_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
 static int atmel_tcb_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 			       const struct pwm_state *state)
 {
-	struct atmel_tcb_pwm_chip *tcbpwmc = to_tcb_chip(chip);
-	struct atmel_tcb_pwm_device *tcbpwm = &tcbpwmc->pwms[pwm->hwpwm];
 	int duty_cycle, period;
 	int ret;
 
-	tcbpwm->polarity = state->polarity;
-
 	if (!state->enabled) {
-		atmel_tcb_pwm_disable(chip, pwm);
+		atmel_tcb_pwm_disable(chip, pwm, state->polarity);
 		return 0;
 	}
 
@@ -363,7 +357,7 @@ static int atmel_tcb_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 	if (ret)
 		return ret;
 
-	return atmel_tcb_pwm_enable(chip, pwm);
+	return atmel_tcb_pwm_enable(chip, pwm, state->polarity);
 }
 
 static const struct pwm_ops atmel_tcb_pwm_ops = {

From 4aed0ccd6868e6ec71f0cf26fc755dbd67447072 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 18 Jul 2023 16:41:28 +0200
Subject: [PATCH 0152/1189] pwm: lpc18xx-sct: Simplify using
 devm_clk_get_enabled()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

With devm_clk_get_enabled() the call to clk_disable_unprepare() can be
dropped from the error path and the remove callback.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-lpc18xx-sct.c | 33 ++++++++-------------------------
 1 file changed, 8 insertions(+), 25 deletions(-)

diff --git a/drivers/pwm/pwm-lpc18xx-sct.c b/drivers/pwm/pwm-lpc18xx-sct.c
index 9ff6311bd472..7a19a840bca5 100644
--- a/drivers/pwm/pwm-lpc18xx-sct.c
+++ b/drivers/pwm/pwm-lpc18xx-sct.c
@@ -367,30 +367,21 @@ static int lpc18xx_pwm_probe(struct platform_device *pdev)
 	if (IS_ERR(lpc18xx_pwm->base))
 		return PTR_ERR(lpc18xx_pwm->base);
 
-	lpc18xx_pwm->pwm_clk = devm_clk_get(&pdev->dev, "pwm");
+	lpc18xx_pwm->pwm_clk = devm_clk_get_enabled(&pdev->dev, "pwm");
 	if (IS_ERR(lpc18xx_pwm->pwm_clk))
 		return dev_err_probe(&pdev->dev, PTR_ERR(lpc18xx_pwm->pwm_clk),
 				     "failed to get pwm clock\n");
 
-	ret = clk_prepare_enable(lpc18xx_pwm->pwm_clk);
-	if (ret < 0)
-		return dev_err_probe(&pdev->dev, ret,
-				     "could not prepare or enable pwm clock\n");
-
 	lpc18xx_pwm->clk_rate = clk_get_rate(lpc18xx_pwm->pwm_clk);
-	if (!lpc18xx_pwm->clk_rate) {
-		ret = dev_err_probe(&pdev->dev,
-				    -EINVAL, "pwm clock has no frequency\n");
-		goto disable_pwmclk;
-	}
+	if (!lpc18xx_pwm->clk_rate)
+		return dev_err_probe(&pdev->dev,
+				     -EINVAL, "pwm clock has no frequency\n");
 
 	/*
 	 * If clkrate is too fast, the calculations in .apply() might overflow.
 	 */
-	if (lpc18xx_pwm->clk_rate > NSEC_PER_SEC) {
-		ret = dev_err_probe(&pdev->dev, -EINVAL, "pwm clock to fast\n");
-		goto disable_pwmclk;
-	}
+	if (lpc18xx_pwm->clk_rate > NSEC_PER_SEC)
+		return dev_err_probe(&pdev->dev, -EINVAL, "pwm clock to fast\n");
 
 	mutex_init(&lpc18xx_pwm->res_lock);
 	mutex_init(&lpc18xx_pwm->period_lock);
@@ -436,18 +427,12 @@ static int lpc18xx_pwm_probe(struct platform_device *pdev)
 	lpc18xx_pwm_writel(lpc18xx_pwm, LPC18XX_PWM_CTRL, val);
 
 	ret = pwmchip_add(&lpc18xx_pwm->chip);
-	if (ret < 0) {
-		dev_err_probe(&pdev->dev, ret, "pwmchip_add failed\n");
-		goto disable_pwmclk;
-	}
+	if (ret < 0)
+		return dev_err_probe(&pdev->dev, ret, "pwmchip_add failed\n");
 
 	platform_set_drvdata(pdev, lpc18xx_pwm);
 
 	return 0;
-
-disable_pwmclk:
-	clk_disable_unprepare(lpc18xx_pwm->pwm_clk);
-	return ret;
 }
 
 static void lpc18xx_pwm_remove(struct platform_device *pdev)
@@ -460,8 +445,6 @@ static void lpc18xx_pwm_remove(struct platform_device *pdev)
 	val = lpc18xx_pwm_readl(lpc18xx_pwm, LPC18XX_PWM_CTRL);
 	lpc18xx_pwm_writel(lpc18xx_pwm, LPC18XX_PWM_CTRL,
 			   val | LPC18XX_PWM_CTRL_HALT);
-
-	clk_disable_unprepare(lpc18xx_pwm->pwm_clk);
 }
 
 static struct platform_driver lpc18xx_pwm_driver = {

From 63808bbb3e226b0160f61723614e612fbf51541c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 18 Jul 2023 17:06:57 +0200
Subject: [PATCH 0153/1189] pwm: pxa: Don't reimplement
 of_device_get_match_data()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Apart from the return type pxa_pwm_get_id_dt() reimplements
of_device_get_match_data(). Drop the former and replace the call to it
by the latter.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-pxa.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/drivers/pwm/pwm-pxa.c b/drivers/pwm/pwm-pxa.c
index c8314053bcb0..1e475ed10180 100644
--- a/drivers/pwm/pwm-pxa.c
+++ b/drivers/pwm/pwm-pxa.c
@@ -157,13 +157,6 @@ MODULE_DEVICE_TABLE(of, pwm_of_match);
 #define pwm_of_match NULL
 #endif
 
-static const struct platform_device_id *pxa_pwm_get_id_dt(struct device *dev)
-{
-	const struct of_device_id *id = of_match_device(pwm_of_match, dev);
-
-	return id ? id->data : NULL;
-}
-
 static int pwm_probe(struct platform_device *pdev)
 {
 	const struct platform_device_id *id = platform_get_device_id(pdev);
@@ -171,7 +164,7 @@ static int pwm_probe(struct platform_device *pdev)
 	int ret = 0;
 
 	if (IS_ENABLED(CONFIG_OF) && id == NULL)
-		id = pxa_pwm_get_id_dt(&pdev->dev);
+		id = of_device_get_match_data(&pdev->dev);
 
 	if (id == NULL)
 		return -EINVAL;

From 250b4ca0c9d611c61e12a8eb2d24e69f9058de2b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 18 Jul 2023 17:23:27 +0200
Subject: [PATCH 0154/1189] pwm: ntxec: Drop a write-only variable from driver
 data
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

.dev is assigned in .probe() and never read. So it serves no purpose and
can be removed.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-ntxec.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/pwm/pwm-ntxec.c b/drivers/pwm/pwm-ntxec.c
index ab63b081df53..baf912c5bf0f 100644
--- a/drivers/pwm/pwm-ntxec.c
+++ b/drivers/pwm/pwm-ntxec.c
@@ -24,7 +24,6 @@
 #include <linux/types.h>
 
 struct ntxec_pwm {
-	struct device *dev;
 	struct ntxec *ec;
 	struct pwm_chip chip;
 };
@@ -148,7 +147,6 @@ static int ntxec_pwm_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	priv->ec = ec;
-	priv->dev = &pdev->dev;
 
 	chip = &priv->chip;
 	chip->dev = &pdev->dev;

From 387c74e5f91d8e6f0c6e49fddd8b0e53118e5def Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 18 Jul 2023 19:53:10 +0200
Subject: [PATCH 0155/1189] pwm: ntxec: Use device_set_of_node_from_dev()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Compared to overwriting pdev->dev.of_node directly, this takes care of
reference counting. It also prevents that the parent device matches this
driver. See commit 9b22c17a3cc5 ("of: Check 'of_node_reused' flag on
of_match_device()") for further details.

Suggested-by: Rob Herring <robh@kernel.org>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-ntxec.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pwm/pwm-ntxec.c b/drivers/pwm/pwm-ntxec.c
index baf912c5bf0f..7514ea384ec5 100644
--- a/drivers/pwm/pwm-ntxec.c
+++ b/drivers/pwm/pwm-ntxec.c
@@ -140,7 +140,7 @@ static int ntxec_pwm_probe(struct platform_device *pdev)
 	struct ntxec_pwm *priv;
 	struct pwm_chip *chip;
 
-	pdev->dev.of_node = pdev->dev.parent->of_node;
+	device_set_of_node_from_dev(&pdev->dev, pdev->dev.parent);
 
 	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)

From 86eed2a10304a9efe56c2b192b914b377cad260d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 25 Jul 2023 10:10:04 +0200
Subject: [PATCH 0156/1189] pwm: Fix order of freeing resources in
 pwmchip_remove()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

pwmchip_add() calls of_pwmchip_add() only after adding the chip to
pwm_chips and releasing pwm_lock. So the proper order in
pwmchip_remove() is to call of_pwmchip_remove() before taking the mutex
and removing the chip from pwm_chips. This way pwmchip_remove() releases
the resources in reverse order compared to pwmchip_add() requesting
them.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/core.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index b4703dfc9e4d..dc66e3405bf5 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -318,13 +318,13 @@ void pwmchip_remove(struct pwm_chip *chip)
 {
 	pwmchip_sysfs_unexport(chip);
 
+	if (IS_ENABLED(CONFIG_OF))
+		of_pwmchip_remove(chip);
+
 	mutex_lock(&pwm_lock);
 
 	list_del_init(&chip->list);
 
-	if (IS_ENABLED(CONFIG_OF))
-		of_pwmchip_remove(chip);
-
 	free_pwms(chip);
 
 	mutex_unlock(&pwm_lock);

From e9c2f69aac05919a4f2bf72a7b53c43ac3f4c410 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 13 Jul 2023 17:51:41 +0200
Subject: [PATCH 0157/1189] pwm: stm32: Don't modify HW state in .remove()
 callback
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

A consumer is expected to disable a PWM before calling pwm_put(). And if
they didn't there is hopefully a good reason (or the consumer needs
fixing). Also if disabling an enabled PWM was the right thing to do,
this should better be done in the framework instead of in each low level
driver.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-stm32.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/pwm/pwm-stm32.c b/drivers/pwm/pwm-stm32.c
index 62e397aeb9aa..687967d3265f 100644
--- a/drivers/pwm/pwm-stm32.c
+++ b/drivers/pwm/pwm-stm32.c
@@ -649,10 +649,6 @@ static int stm32_pwm_probe(struct platform_device *pdev)
 static void stm32_pwm_remove(struct platform_device *pdev)
 {
 	struct stm32_pwm *priv = platform_get_drvdata(pdev);
-	unsigned int i;
-
-	for (i = 0; i < priv->chip.npwm; i++)
-		pwm_disable(&priv->chip.pwms[i]);
 
 	pwmchip_remove(&priv->chip);
 }

From 8c89fd866ad221af037ef0ec3d60b83d0b859c65 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 13 Jul 2023 17:51:42 +0200
Subject: [PATCH 0158/1189] pwm: stm32: Simplify using devm_pwmchip_add()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This allows to drop the platform_driver's remove function.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-stm32.c | 10 +---------
 1 file changed, 1 insertion(+), 9 deletions(-)

diff --git a/drivers/pwm/pwm-stm32.c b/drivers/pwm/pwm-stm32.c
index 687967d3265f..3d6be7749e23 100644
--- a/drivers/pwm/pwm-stm32.c
+++ b/drivers/pwm/pwm-stm32.c
@@ -637,7 +637,7 @@ static int stm32_pwm_probe(struct platform_device *pdev)
 	priv->chip.ops = &stm32pwm_ops;
 	priv->chip.npwm = stm32_pwm_detect_channels(priv);
 
-	ret = pwmchip_add(&priv->chip);
+	ret = devm_pwmchip_add(dev, &priv->chip);
 	if (ret < 0)
 		return ret;
 
@@ -646,13 +646,6 @@ static int stm32_pwm_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static void stm32_pwm_remove(struct platform_device *pdev)
-{
-	struct stm32_pwm *priv = platform_get_drvdata(pdev);
-
-	pwmchip_remove(&priv->chip);
-}
-
 static int __maybe_unused stm32_pwm_suspend(struct device *dev)
 {
 	struct stm32_pwm *priv = dev_get_drvdata(dev);
@@ -697,7 +690,6 @@ MODULE_DEVICE_TABLE(of, stm32_pwm_of_match);
 
 static struct platform_driver stm32_pwm_driver = {
 	.probe	= stm32_pwm_probe,
-	.remove_new = stm32_pwm_remove,
 	.driver	= {
 		.name = "stm32-pwm",
 		.of_match_table = stm32_pwm_of_match,

From b2c71e9f8dd0d023a847f6c38f9a83c0949ec01a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 14 Jul 2023 23:45:18 +0200
Subject: [PATCH 0159/1189] pwm: stmpe: Handle errors when disabling the signal
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Before the pwm framework implementedatomic updates (with the .apply()
callback) the .disable() callback returned void. This is still visible
in the stmpe driver which drops errors in the disable path.

Improve the driver to forward failures in stmpe_24xx_pwm_disable() to
the caller of pwm_apply_state().

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-stmpe.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/pwm/pwm-stmpe.c b/drivers/pwm/pwm-stmpe.c
index 5d4a4762ce0c..e205405c4828 100644
--- a/drivers/pwm/pwm-stmpe.c
+++ b/drivers/pwm/pwm-stmpe.c
@@ -61,8 +61,8 @@ static int stmpe_24xx_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm)
 	return 0;
 }
 
-static void stmpe_24xx_pwm_disable(struct pwm_chip *chip,
-				   struct pwm_device *pwm)
+static int stmpe_24xx_pwm_disable(struct pwm_chip *chip,
+				  struct pwm_device *pwm)
 {
 	struct stmpe_pwm *stmpe_pwm = to_stmpe_pwm(chip);
 	u8 value;
@@ -72,17 +72,16 @@ static void stmpe_24xx_pwm_disable(struct pwm_chip *chip,
 	if (ret < 0) {
 		dev_err(chip->dev, "error reading PWM#%u control\n",
 			pwm->hwpwm);
-		return;
+		return ret;
 	}
 
 	value = ret & ~BIT(pwm->hwpwm);
 
 	ret = stmpe_reg_write(stmpe_pwm->stmpe, STMPE24XX_PWMCS, value);
-	if (ret) {
+	if (ret)
 		dev_err(chip->dev, "error writing PWM#%u control\n",
 			pwm->hwpwm);
-		return;
-	}
+	return ret;
 }
 
 /* STMPE 24xx PWM instructions */
@@ -111,7 +110,9 @@ static int stmpe_24xx_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
 
 	/* Make sure we are disabled */
 	if (pwm_is_enabled(pwm)) {
-		stmpe_24xx_pwm_disable(chip, pwm);
+		ret = stmpe_24xx_pwm_disable(chip, pwm);
+		if (ret)
+			return ret;
 	} else {
 		/* Connect the PWM to the pin */
 		pin = pwm->hwpwm;
@@ -269,7 +270,7 @@ static int stmpe_24xx_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 
 	if (!state->enabled) {
 		if (pwm->state.enabled)
-			stmpe_24xx_pwm_disable(chip, pwm);
+			return stmpe_24xx_pwm_disable(chip, pwm);
 
 		return 0;
 	}

From 8b9d91d23c18423d4e4bda735f20b669fb28115f Mon Sep 17 00:00:00 2001
From: Stanislav Jakubek <stano.jakubek@gmail.com>
Date: Sun, 18 Jun 2023 16:23:27 +0200
Subject: [PATCH 0160/1189] dt-bindings: pwm: brcm,kona-pwm: convert to YAML
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Convert Broadcom Kona family PWM controller bindings to DT schema.

Change during conversion:
  - add used, but previously undocumented brcm,bcm11351-pwm compatible

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Stanislav Jakubek <stano.jakubek@gmail.com>
Acked-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 .../devicetree/bindings/pwm/brcm,kona-pwm.txt | 21 --------
 .../bindings/pwm/brcm,kona-pwm.yaml           | 51 +++++++++++++++++++
 2 files changed, 51 insertions(+), 21 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/pwm/brcm,kona-pwm.txt
 create mode 100644 Documentation/devicetree/bindings/pwm/brcm,kona-pwm.yaml

diff --git a/Documentation/devicetree/bindings/pwm/brcm,kona-pwm.txt b/Documentation/devicetree/bindings/pwm/brcm,kona-pwm.txt
deleted file mode 100644
index c42eecfc81ed..000000000000
--- a/Documentation/devicetree/bindings/pwm/brcm,kona-pwm.txt
+++ /dev/null
@@ -1,21 +0,0 @@
-Broadcom Kona PWM controller device tree bindings
-
-This controller has 6 channels.
-
-Required Properties :
-- compatible: should contain "brcm,kona-pwm"
-- reg: physical base address and length of the controller's registers
-- clocks: phandle + clock specifier pair for the external clock
-- #pwm-cells: Should be 3. See pwm.yaml in this directory for a
-  description of the cells format.
-
-Refer to clocks/clock-bindings.txt for generic clock consumer properties.
-
-Example:
-
-pwm: pwm@3e01a000 {
-	compatible = "brcm,bcm11351-pwm", "brcm,kona-pwm";
-	reg = <0x3e01a000 0xc4>;
-	clocks = <&pwm_clk>;
-	#pwm-cells = <3>;
-};
diff --git a/Documentation/devicetree/bindings/pwm/brcm,kona-pwm.yaml b/Documentation/devicetree/bindings/pwm/brcm,kona-pwm.yaml
new file mode 100644
index 000000000000..e86c8053b366
--- /dev/null
+++ b/Documentation/devicetree/bindings/pwm/brcm,kona-pwm.yaml
@@ -0,0 +1,51 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pwm/brcm,kona-pwm.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Broadcom Kona family PWM controller
+
+description:
+  This controller has 6 channels.
+
+maintainers:
+  - Florian Fainelli <f.fainelli@gmail.com>
+
+allOf:
+  - $ref: pwm.yaml#
+
+properties:
+  compatible:
+    items:
+      - enum:
+          - brcm,bcm11351-pwm
+      - const: brcm,kona-pwm
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  '#pwm-cells':
+    const: 3
+
+required:
+  - compatible
+  - reg
+  - clocks
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/bcm281xx.h>
+
+    pwm@3e01a000 {
+       compatible = "brcm,bcm11351-pwm", "brcm,kona-pwm";
+       reg = <0x3e01a000 0xcc>;
+       clocks = <&slave_ccu BCM281XX_SLAVE_CCU_PWM>;
+       #pwm-cells = <3>;
+    };
+...

From b22bb0d6a828b4eab579056647d2f362ac116cf2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 28 Jul 2023 10:11:05 +0200
Subject: [PATCH 0161/1189] pwm: atmel: Simplify using devm functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For all resources used by the driver there is a devm variant to allocate
these. This simplifies the error path in the probe callback and allows
to drop the remove callback.

While at it also use dev_err_probe() to compact returning an error.

With the remove callback gone, there is no user of driver data left, so
the call to platform_set_drvdata() can also be dropped.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-atmel.c | 33 +++++++--------------------------
 1 file changed, 7 insertions(+), 26 deletions(-)

diff --git a/drivers/pwm/pwm-atmel.c b/drivers/pwm/pwm-atmel.c
index 03c7810416b8..1f73325d1bea 100644
--- a/drivers/pwm/pwm-atmel.c
+++ b/drivers/pwm/pwm-atmel.c
@@ -517,15 +517,10 @@ static int atmel_pwm_probe(struct platform_device *pdev)
 	if (IS_ERR(atmel_pwm->base))
 		return PTR_ERR(atmel_pwm->base);
 
-	atmel_pwm->clk = devm_clk_get(&pdev->dev, NULL);
+	atmel_pwm->clk = devm_clk_get_prepared(&pdev->dev, NULL);
 	if (IS_ERR(atmel_pwm->clk))
-		return PTR_ERR(atmel_pwm->clk);
-
-	ret = clk_prepare(atmel_pwm->clk);
-	if (ret) {
-		dev_err(&pdev->dev, "failed to prepare PWM clock\n");
-		return ret;
-	}
+		return dev_err_probe(&pdev->dev, PTR_ERR(atmel_pwm->clk),
+				     "failed to get prepared PWM clock\n");
 
 	atmel_pwm->chip.dev = &pdev->dev;
 	atmel_pwm->chip.ops = &atmel_pwm_ops;
@@ -533,42 +528,28 @@ static int atmel_pwm_probe(struct platform_device *pdev)
 
 	ret = atmel_pwm_enable_clk_if_on(atmel_pwm, true);
 	if (ret < 0)
-		goto unprepare_clk;
+		return ret;
 
-	ret = pwmchip_add(&atmel_pwm->chip);
+	ret = devm_pwmchip_add(&pdev->dev, &atmel_pwm->chip);
 	if (ret < 0) {
-		dev_err(&pdev->dev, "failed to add PWM chip %d\n", ret);
+		dev_err_probe(&pdev->dev, ret, "failed to add PWM chip\n");
 		goto disable_clk;
 	}
 
-	platform_set_drvdata(pdev, atmel_pwm);
-
-	return ret;
+	return 0;
 
 disable_clk:
 	atmel_pwm_enable_clk_if_on(atmel_pwm, false);
 
-unprepare_clk:
-	clk_unprepare(atmel_pwm->clk);
 	return ret;
 }
 
-static void atmel_pwm_remove(struct platform_device *pdev)
-{
-	struct atmel_pwm_chip *atmel_pwm = platform_get_drvdata(pdev);
-
-	pwmchip_remove(&atmel_pwm->chip);
-
-	clk_unprepare(atmel_pwm->clk);
-}
-
 static struct platform_driver atmel_pwm_driver = {
 	.driver = {
 		.name = "atmel-pwm",
 		.of_match_table = of_match_ptr(atmel_pwm_dt_ids),
 	},
 	.probe = atmel_pwm_probe,
-	.remove_new = atmel_pwm_remove,
 };
 module_platform_driver(atmel_pwm_driver);
 

From 1ba11daef0a9b062e40b5393d285c82ab6483730 Mon Sep 17 00:00:00 2001
From: Shaoqin Huang <shahuang@redhat.com>
Date: Thu, 27 Jul 2023 05:07:54 -0400
Subject: [PATCH 0162/1189] KVM: arm64: Use the known cpu id instead of
 smp_processor_id()

In kvm_arch_vcpu_load(), it has the parameter cpu which is the value of
smp_processor_id(), so no need to get it again. Simply replace it.

Signed-off-by: Shaoqin Huang <shahuang@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230727090754.1900310-1-shahuang@redhat.com
---
 arch/arm64/kvm/arm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 72dc53a75d1c..3c015bdd35ee 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -462,7 +462,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		vcpu_ptrauth_disable(vcpu);
 	kvm_arch_vcpu_load_debug_state_flags(vcpu);
 
-	if (!cpumask_test_cpu(smp_processor_id(), vcpu->kvm->arch.supported_cpus))
+	if (!cpumask_test_cpu(cpu, vcpu->kvm->arch.supported_cpus))
 		vcpu_set_on_unsupported_cpu(vcpu);
 }
 

From e21f3905f98ff1f72b06614440c2be93fda58b44 Mon Sep 17 00:00:00 2001
From: Zenghui Yu <yuzenghui@huawei.com>
Date: Mon, 24 Jul 2023 22:22:57 +0800
Subject: [PATCH 0163/1189] KVM: arm64: Drop HCR_VIRT_EXCP_MASK

This was introduced in commit 0369f6a34b9f ("arm64: KVM: EL2 register
definitions") and for more than 10 years nobody used. Remove it.

Signed-off-by: Zenghui Yu <yuzenghui@huawei.com>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230724142257.1551-1-yuzenghui@huawei.com
---
 arch/arm64/include/asm/kvm_arm.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 58e5eb27da68..d04ef89ca6a0 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -89,7 +89,6 @@
 			 HCR_BSU_IS | HCR_FB | HCR_TACR | \
 			 HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \
 			 HCR_FMO | HCR_IMO | HCR_PTW | HCR_TID3)
-#define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF)
 #define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK | HCR_ATA)
 #define HCR_HOST_NVHE_PROTECTED_FLAGS (HCR_HOST_NVHE_FLAGS | HCR_TSC)
 #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)

From 1bb5187b673208f7191f227249ffe7401e969b97 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Fri, 14 Jul 2023 11:50:29 -0600
Subject: [PATCH 0164/1189] backlight: qcom-wled: Explicitly include correct DT
 includes

The DT of_device.h and of_platform.h date back to the separate
of_platform_bus_type before it as merged into the regular platform bus.
As part of that merge prepping Arm DT support 13 years ago, they
"temporarily" include each other. They also include platform_device.h
and of.h. As a result, there's a pretty much random mix of those include
files used throughout the tree. In order to detangle these headers and
replace the implicit includes with struct declarations, users need to
explicitly include the correct includes.

Signed-off-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230714175029.4065326-1-robh@kernel.org
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/video/backlight/qcom-wled.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/video/backlight/qcom-wled.c b/drivers/video/backlight/qcom-wled.c
index c6996aa288e6..10129095a4c1 100644
--- a/drivers/video/backlight/qcom-wled.c
+++ b/drivers/video/backlight/qcom-wled.c
@@ -9,8 +9,8 @@
 #include <linux/backlight.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/of_address.h>
+#include <linux/platform_device.h>
 #include <linux/regmap.h>
 
 /* From DT binding */

From 4c09e20b3c85f60353ace21092e34f35f5e3ab00 Mon Sep 17 00:00:00 2001
From: Artur Weber <aweber.kernel@gmail.com>
Date: Fri, 14 Jul 2023 14:14:39 +0200
Subject: [PATCH 0165/1189] backlight: lp855x: Initialize PWM state on first
 brightness change
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As pointed out by Uwe Kleine-König[1], the changes introduced in
commit c1ff7da03e16 ("video: backlight: lp855x: Get PWM for PWM mode
during probe") caused the PWM state set up by the bootloader to be
re-set when the driver is probed. This differs from the behavior from
before that patch, where the PWM state would be initialized on the
first brightness change.

Fix this by moving the PWM state initialization into the PWM control
function. Add a new variable, needs_pwm_init, to the device info struct
to allow us to check whether we need the initialization, or whether it
has already been done.

[1] https://lore.kernel.org/lkml/20230614083953.e4kkweddjz7wztby@pengutronix.de/

Fixes: c1ff7da03e16 ("video: backlight: lp855x: Get PWM for PWM mode during probe")
Signed-off-by: Artur Weber <aweber.kernel@gmail.com>
Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org>
Link: https://lore.kernel.org/r/20230714121440.7717-2-aweber.kernel@gmail.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/video/backlight/lp855x_bl.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/video/backlight/lp855x_bl.c b/drivers/video/backlight/lp855x_bl.c
index 1c9e921bca14..349ec324bc1e 100644
--- a/drivers/video/backlight/lp855x_bl.c
+++ b/drivers/video/backlight/lp855x_bl.c
@@ -71,6 +71,7 @@ struct lp855x {
 	struct device *dev;
 	struct lp855x_platform_data *pdata;
 	struct pwm_device *pwm;
+	bool needs_pwm_init;
 	struct regulator *supply;	/* regulator for VDD input */
 	struct regulator *enable;	/* regulator for EN/VDDIO input */
 };
@@ -220,7 +221,15 @@ static void lp855x_pwm_ctrl(struct lp855x *lp, int br, int max_br)
 {
 	struct pwm_state state;
 
-	pwm_get_state(lp->pwm, &state);
+	if (lp->needs_pwm_init) {
+		pwm_init_state(lp->pwm, &state);
+		/* Legacy platform data compatibility */
+		if (lp->pdata->period_ns > 0)
+			state.period = lp->pdata->period_ns;
+		lp->needs_pwm_init = false;
+	} else {
+		pwm_get_state(lp->pwm, &state);
+	}
 
 	state.duty_cycle = div_u64(br * state.period, max_br);
 	state.enabled = state.duty_cycle;
@@ -387,7 +396,6 @@ static int lp855x_probe(struct i2c_client *cl)
 	const struct i2c_device_id *id = i2c_client_get_device_id(cl);
 	const struct acpi_device_id *acpi_id = NULL;
 	struct device *dev = &cl->dev;
-	struct pwm_state pwmstate;
 	struct lp855x *lp;
 	int ret;
 
@@ -470,15 +478,11 @@ static int lp855x_probe(struct i2c_client *cl)
 		else
 			return dev_err_probe(dev, ret, "getting PWM\n");
 
+		lp->needs_pwm_init = false;
 		lp->mode = REGISTER_BASED;
 		dev_dbg(dev, "mode: register based\n");
 	} else {
-		pwm_init_state(lp->pwm, &pwmstate);
-		/* Legacy platform data compatibility */
-		if (lp->pdata->period_ns > 0)
-			pwmstate.period = lp->pdata->period_ns;
-		pwm_apply_state(lp->pwm, &pwmstate);
-
+		lp->needs_pwm_init = true;
 		lp->mode = PWM_BASED;
 		dev_dbg(dev, "mode: PWM based\n");
 	}

From 5145531be5fbad0e914d1dc1cbd392d7b756abaa Mon Sep 17 00:00:00 2001
From: Artur Weber <aweber.kernel@gmail.com>
Date: Fri, 14 Jul 2023 14:14:40 +0200
Subject: [PATCH 0166/1189] backlight: lp855x: Catch errors when changing
 brightness

The lp855x_bl_update_status function's return type is int, but
it always returns 0, without checking for the results of the
write_byte/pwm_ctrl functions called within.

Make this function return the return values of the functions it
calls, and modify the lp855x_pwm_ctrl function to return errors.

Signed-off-by: Artur Weber <aweber.kernel@gmail.com>
Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org>
Link: https://lore.kernel.org/r/20230714121440.7717-3-aweber.kernel@gmail.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/video/backlight/lp855x_bl.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/video/backlight/lp855x_bl.c b/drivers/video/backlight/lp855x_bl.c
index 349ec324bc1e..61a7f45bfad8 100644
--- a/drivers/video/backlight/lp855x_bl.c
+++ b/drivers/video/backlight/lp855x_bl.c
@@ -217,7 +217,7 @@ err:
 	return ret;
 }
 
-static void lp855x_pwm_ctrl(struct lp855x *lp, int br, int max_br)
+static int lp855x_pwm_ctrl(struct lp855x *lp, int br, int max_br)
 {
 	struct pwm_state state;
 
@@ -234,23 +234,26 @@ static void lp855x_pwm_ctrl(struct lp855x *lp, int br, int max_br)
 	state.duty_cycle = div_u64(br * state.period, max_br);
 	state.enabled = state.duty_cycle;
 
-	pwm_apply_state(lp->pwm, &state);
+	return pwm_apply_state(lp->pwm, &state);
 }
 
 static int lp855x_bl_update_status(struct backlight_device *bl)
 {
 	struct lp855x *lp = bl_get_data(bl);
 	int brightness = bl->props.brightness;
+	int ret;
 
 	if (bl->props.state & (BL_CORE_SUSPENDED | BL_CORE_FBBLANK))
 		brightness = 0;
 
 	if (lp->mode == PWM_BASED)
-		lp855x_pwm_ctrl(lp, brightness, bl->props.max_brightness);
+		ret = lp855x_pwm_ctrl(lp, brightness,
+				      bl->props.max_brightness);
 	else if (lp->mode == REGISTER_BASED)
-		lp855x_write_byte(lp, lp->cfg->reg_brightness, (u8)brightness);
+		ret = lp855x_write_byte(lp, lp->cfg->reg_brightness,
+					(u8)brightness);
 
-	return 0;
+	return ret;
 }
 
 static const struct backlight_ops lp855x_bl_ops = {

From 0723807978b14837262671d30b5cc8b1b5268281 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Wed, 26 Jul 2023 19:20:28 -0600
Subject: [PATCH 0167/1189] MIPS: Fixup explicit DT include clean-up

Commit 657c45b303f87d77 ("MIPS: Explicitly include correct DT includes")
removed a necessary include by mistake and missed adding an explicit
include of spinlock.h (from of.h -> kobject.h -> spinlock.h).

Fixes: 657c45b303f87d77 ("MIPS: Explicitly include correct DT includes")
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Rob Herring <robh@kernel.org>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/lantiq/xway/gptu.c       | 1 +
 arch/mips/pic32/pic32mzda/config.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/arch/mips/lantiq/xway/gptu.c b/arch/mips/lantiq/xway/gptu.c
index e254b108fb9b..8d52001301de 100644
--- a/arch/mips/lantiq/xway/gptu.c
+++ b/arch/mips/lantiq/xway/gptu.c
@@ -9,6 +9,7 @@
 #include <linux/ioport.h>
 #include <linux/init.h>
 #include <linux/mod_devicetable.h>
+#include <linux/of_irq.h>
 #include <linux/platform_device.h>
 
 #include <lantiq_soc.h>
diff --git a/arch/mips/pic32/pic32mzda/config.c b/arch/mips/pic32/pic32mzda/config.c
index 6e94ae66eba8..73be5689e0df 100644
--- a/arch/mips/pic32/pic32mzda/config.c
+++ b/arch/mips/pic32/pic32mzda/config.c
@@ -5,6 +5,7 @@
  */
 #include <linux/init.h>
 #include <linux/io.h>
+#include <linux/spinlock.h>
 
 #include <asm/mach-pic32/pic32.h>
 

From e1a7566d0955cc5357903c04030aac05ced95939 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Wed, 26 Jul 2023 19:20:39 -0600
Subject: [PATCH 0168/1189] MIPS: More explicit DT include clean-ups

A couple more clean-ups in the MIPS code.

The DT of_device.h and of_platform.h date back to the separate
of_platform_bus_type before it was merged into the regular platform bus.
As part of that merge prepping Arm DT support 13 years ago, they
"temporarily" include each other. They also include platform_device.h
and of.h. As a result, there's a pretty much random mix of those include
files used throughout the tree. In order to detangle these headers and
replace the implicit includes with struct declarations, users need to
explicitly include the correct includes.

Signed-off-by: Rob Herring <robh@kernel.org>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/cavium-octeon/octeon-platform.c | 2 ++
 arch/mips/cavium-octeon/octeon-usb.c      | 2 ++
 arch/mips/ralink/ill_acc.c                | 2 ++
 3 files changed, 6 insertions(+)

diff --git a/arch/mips/cavium-octeon/octeon-platform.c b/arch/mips/cavium-octeon/octeon-platform.c
index ce05c0dd3acd..60da1b2091f5 100644
--- a/arch/mips/cavium-octeon/octeon-platform.c
+++ b/arch/mips/cavium-octeon/octeon-platform.c
@@ -8,8 +8,10 @@
  */
 
 #include <linux/etherdevice.h>
+#include <linux/of.h>
 #include <linux/of_platform.h>
 #include <linux/of_fdt.h>
+#include <linux/platform_device.h>
 #include <linux/libfdt.h>
 
 #include <asm/octeon/octeon.h>
diff --git a/arch/mips/cavium-octeon/octeon-usb.c b/arch/mips/cavium-octeon/octeon-usb.c
index 2add435ad038..add0f23592b3 100644
--- a/arch/mips/cavium-octeon/octeon-usb.c
+++ b/arch/mips/cavium-octeon/octeon-usb.c
@@ -15,7 +15,9 @@
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/of.h>
 #include <linux/of_platform.h>
+#include <linux/platform_device.h>
 
 /*
  * USB Control Register
diff --git a/arch/mips/ralink/ill_acc.c b/arch/mips/ralink/ill_acc.c
index f395ae218470..25341b2319d0 100644
--- a/arch/mips/ralink/ill_acc.c
+++ b/arch/mips/ralink/ill_acc.c
@@ -5,8 +5,10 @@
  */
 
 #include <linux/interrupt.h>
+#include <linux/of.h>
 #include <linux/of_platform.h>
 #include <linux/of_irq.h>
+#include <linux/platform_device.h>
 
 #include <asm/mach-ralink/ralink_regs.h>
 

From ef8365dfaa53c11722904dd590154f981d735754 Mon Sep 17 00:00:00 2001
From: Keguang Zhang <keguang.zhang@gmail.com>
Date: Wed, 26 Jul 2023 20:51:30 +0800
Subject: [PATCH 0169/1189] MIPS: loongson32: Remove regs-clk.h

Since commit c46496119ed0 ("clk: loongson1: Remove
the outdated driver"), no one is using regs-clk.h.
Therefore, remove this obsolete header file.

Signed-off-by: Keguang Zhang <keguang.zhang@gmail.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 .../include/asm/mach-loongson32/loongson1.h   |  1 -
 .../include/asm/mach-loongson32/regs-clk.h    | 81 -------------------
 2 files changed, 82 deletions(-)
 delete mode 100644 arch/mips/include/asm/mach-loongson32/regs-clk.h

diff --git a/arch/mips/include/asm/mach-loongson32/loongson1.h b/arch/mips/include/asm/mach-loongson32/loongson1.h
index 7971272345d3..bc27fcee3176 100644
--- a/arch/mips/include/asm/mach-loongson32/loongson1.h
+++ b/arch/mips/include/asm/mach-loongson32/loongson1.h
@@ -45,7 +45,6 @@
 #define LS1X_NAND_BASE			0x1fe78000
 #define LS1X_CLK_BASE			0x1fe78030
 
-#include <regs-clk.h>
 #include <regs-mux.h>
 #include <regs-rtc.h>
 
diff --git a/arch/mips/include/asm/mach-loongson32/regs-clk.h b/arch/mips/include/asm/mach-loongson32/regs-clk.h
deleted file mode 100644
index 98136fa8bee1..000000000000
--- a/arch/mips/include/asm/mach-loongson32/regs-clk.h
+++ /dev/null
@@ -1,81 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Copyright (c) 2011 Zhang, Keguang <keguang.zhang@gmail.com>
- *
- * Loongson 1 Clock Register Definitions.
- */
-
-#ifndef __ASM_MACH_LOONGSON32_REGS_CLK_H
-#define __ASM_MACH_LOONGSON32_REGS_CLK_H
-
-#define LS1X_CLK_REG(x) \
-		((void __iomem *)KSEG1ADDR(LS1X_CLK_BASE + (x)))
-
-#define LS1X_CLK_PLL_FREQ		LS1X_CLK_REG(0x0)
-#define LS1X_CLK_PLL_DIV		LS1X_CLK_REG(0x4)
-
-#if defined(CONFIG_LOONGSON1_LS1B)
-/* Clock PLL Divisor Register Bits */
-#define DIV_DC_EN			BIT(31)
-#define DIV_DC_RST			BIT(30)
-#define DIV_CPU_EN			BIT(25)
-#define DIV_CPU_RST			BIT(24)
-#define DIV_DDR_EN			BIT(19)
-#define DIV_DDR_RST			BIT(18)
-#define RST_DC_EN			BIT(5)
-#define RST_DC				BIT(4)
-#define RST_DDR_EN			BIT(3)
-#define RST_DDR				BIT(2)
-#define RST_CPU_EN			BIT(1)
-#define RST_CPU				BIT(0)
-
-#define DIV_DC_SHIFT			26
-#define DIV_CPU_SHIFT			20
-#define DIV_DDR_SHIFT			14
-
-#define DIV_DC_WIDTH			4
-#define DIV_CPU_WIDTH			4
-#define DIV_DDR_WIDTH			4
-
-#define BYPASS_DC_SHIFT			12
-#define BYPASS_DDR_SHIFT		10
-#define BYPASS_CPU_SHIFT		8
-
-#define BYPASS_DC_WIDTH			1
-#define BYPASS_DDR_WIDTH		1
-#define BYPASS_CPU_WIDTH		1
-
-#elif defined(CONFIG_LOONGSON1_LS1C)
-/* PLL/SDRAM Frequency configuration register Bits */
-#define PLL_VALID			BIT(31)
-#define FRAC_N				GENMASK(23, 16)
-#define RST_TIME			GENMASK(3, 2)
-#define SDRAM_DIV			GENMASK(1, 0)
-
-/* CPU/CAMERA/DC Frequency configuration register Bits */
-#define DIV_DC_EN			BIT(31)
-#define DIV_DC				GENMASK(30, 24)
-#define DIV_CAM_EN			BIT(23)
-#define DIV_CAM				GENMASK(22, 16)
-#define DIV_CPU_EN			BIT(15)
-#define DIV_CPU				GENMASK(14, 8)
-#define DIV_DC_SEL_EN			BIT(5)
-#define DIV_DC_SEL			BIT(4)
-#define DIV_CAM_SEL_EN			BIT(3)
-#define DIV_CAM_SEL			BIT(2)
-#define DIV_CPU_SEL_EN			BIT(1)
-#define DIV_CPU_SEL			BIT(0)
-
-#define DIV_DC_SHIFT			24
-#define DIV_CAM_SHIFT			16
-#define DIV_CPU_SHIFT			8
-#define DIV_DDR_SHIFT			0
-
-#define DIV_DC_WIDTH			7
-#define DIV_CAM_WIDTH			7
-#define DIV_CPU_WIDTH			7
-#define DIV_DDR_WIDTH			2
-
-#endif
-
-#endif /* __ASM_MACH_LOONGSON32_REGS_CLK_H */

From 20463908951be777b3300c1a3a845877266f8fee Mon Sep 17 00:00:00 2001
From: Keguang Zhang <keguang.zhang@gmail.com>
Date: Wed, 26 Jul 2023 20:51:31 +0800
Subject: [PATCH 0170/1189] MIPS: loongson32: Remove regs-rtc.h

Since commit 35508d242409 ("MIPS: loongson32: ls1c: Fix hang
during startup"), no one is calling ls1x_rtc_set_extclk().
Therefore, remove this obsolete function.

Since commit 9fb23090658a ("rtc: Remove the Loongson-1
RTC driver"), no one is using regs-rtc.h.
Therefore, remove this obsolete header file.

Signed-off-by: Keguang Zhang <keguang.zhang@gmail.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 .../include/asm/mach-loongson32/loongson1.h   |  1 -
 .../include/asm/mach-loongson32/regs-rtc.h    | 19 -------------------
 arch/mips/loongson32/common/platform.c        |  8 --------
 3 files changed, 28 deletions(-)
 delete mode 100644 arch/mips/include/asm/mach-loongson32/regs-rtc.h

diff --git a/arch/mips/include/asm/mach-loongson32/loongson1.h b/arch/mips/include/asm/mach-loongson32/loongson1.h
index bc27fcee3176..84f45461c832 100644
--- a/arch/mips/include/asm/mach-loongson32/loongson1.h
+++ b/arch/mips/include/asm/mach-loongson32/loongson1.h
@@ -46,6 +46,5 @@
 #define LS1X_CLK_BASE			0x1fe78030
 
 #include <regs-mux.h>
-#include <regs-rtc.h>
 
 #endif /* __ASM_MACH_LOONGSON32_LOONGSON1_H */
diff --git a/arch/mips/include/asm/mach-loongson32/regs-rtc.h b/arch/mips/include/asm/mach-loongson32/regs-rtc.h
deleted file mode 100644
index a3d096be1607..000000000000
--- a/arch/mips/include/asm/mach-loongson32/regs-rtc.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Copyright (c) 2016 Yang Ling <gnaygnil@gmail.com>
- *
- * Loongson 1 RTC timer Register Definitions.
- */
-
-#ifndef __ASM_MACH_LOONGSON32_REGS_RTC_H
-#define __ASM_MACH_LOONGSON32_REGS_RTC_H
-
-#define LS1X_RTC_REG(x) \
-		((void __iomem *)KSEG1ADDR(LS1X_RTC_BASE + (x)))
-
-#define LS1X_RTC_CTRL	LS1X_RTC_REG(0x40)
-
-#define RTC_EXTCLK_OK	(BIT(5) | BIT(8))
-#define RTC_EXTCLK_EN	BIT(8)
-
-#endif /* __ASM_MACH_LOONGSON32_REGS_RTC_H */
diff --git a/arch/mips/loongson32/common/platform.c b/arch/mips/loongson32/common/platform.c
index 64d7979394e6..8075590a9f83 100644
--- a/arch/mips/loongson32/common/platform.c
+++ b/arch/mips/loongson32/common/platform.c
@@ -265,14 +265,6 @@ struct platform_device ls1x_ehci_pdev = {
 };
 
 /* Real Time Clock */
-void __init ls1x_rtc_set_extclk(struct platform_device *pdev)
-{
-	u32 val = __raw_readl(LS1X_RTC_CTRL);
-
-	if (!(val & RTC_EXTCLK_OK))
-		__raw_writel(val | RTC_EXTCLK_EN, LS1X_RTC_CTRL);
-}
-
 struct platform_device ls1x_rtc_pdev = {
 	.name		= "ls1x-rtc",
 	.id		= -1,

From f11a9967413281b49690d864795e7c5f8f8e4fda Mon Sep 17 00:00:00 2001
From: Jiaxun Yang <jiaxun.yang@flygoat.com>
Date: Tue, 25 Jul 2023 14:01:44 +0800
Subject: [PATCH 0171/1189] MIPS: Loongson64: Fix more __iomem attributes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There are some __iomem type casting being missed in previous patch.
Fix them here.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202307020639.QCZOKp8B-lkp@intel.com/
Signed-off-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/loongson64/smp.c | 160 ++++++++++++++++++-------------------
 1 file changed, 80 insertions(+), 80 deletions(-)

diff --git a/arch/mips/loongson64/smp.c b/arch/mips/loongson64/smp.c
index cdecd7af11a6..e015a26a40f7 100644
--- a/arch/mips/loongson64/smp.c
+++ b/arch/mips/loongson64/smp.c
@@ -187,181 +187,181 @@ static void csr_ipi_probe(void)
 
 static void ipi_set0_regs_init(void)
 {
-	ipi_set0_regs[0] = (void *)
+	ipi_set0_regs[0] = (void __iomem *)
 		(SMP_CORE_GROUP0_BASE + SMP_CORE0_OFFSET + SET0);
-	ipi_set0_regs[1] = (void *)
+	ipi_set0_regs[1] = (void __iomem *)
 		(SMP_CORE_GROUP0_BASE + SMP_CORE1_OFFSET + SET0);
-	ipi_set0_regs[2] = (void *)
+	ipi_set0_regs[2] = (void __iomem *)
 		(SMP_CORE_GROUP0_BASE + SMP_CORE2_OFFSET + SET0);
-	ipi_set0_regs[3] = (void *)
+	ipi_set0_regs[3] = (void __iomem *)
 		(SMP_CORE_GROUP0_BASE + SMP_CORE3_OFFSET + SET0);
-	ipi_set0_regs[4] = (void *)
+	ipi_set0_regs[4] = (void __iomem *)
 		(SMP_CORE_GROUP1_BASE + SMP_CORE0_OFFSET + SET0);
-	ipi_set0_regs[5] = (void *)
+	ipi_set0_regs[5] = (void __iomem *)
 		(SMP_CORE_GROUP1_BASE + SMP_CORE1_OFFSET + SET0);
-	ipi_set0_regs[6] = (void *)
+	ipi_set0_regs[6] = (void __iomem *)
 		(SMP_CORE_GROUP1_BASE + SMP_CORE2_OFFSET + SET0);
-	ipi_set0_regs[7] = (void *)
+	ipi_set0_regs[7] = (void __iomem *)
 		(SMP_CORE_GROUP1_BASE + SMP_CORE3_OFFSET + SET0);
-	ipi_set0_regs[8] = (void *)
+	ipi_set0_regs[8] = (void __iomem *)
 		(SMP_CORE_GROUP2_BASE + SMP_CORE0_OFFSET + SET0);
-	ipi_set0_regs[9] = (void *)
+	ipi_set0_regs[9] = (void __iomem *)
 		(SMP_CORE_GROUP2_BASE + SMP_CORE1_OFFSET + SET0);
-	ipi_set0_regs[10] = (void *)
+	ipi_set0_regs[10] = (void __iomem *)
 		(SMP_CORE_GROUP2_BASE + SMP_CORE2_OFFSET + SET0);
-	ipi_set0_regs[11] = (void *)
+	ipi_set0_regs[11] = (void __iomem *)
 		(SMP_CORE_GROUP2_BASE + SMP_CORE3_OFFSET + SET0);
-	ipi_set0_regs[12] = (void *)
+	ipi_set0_regs[12] = (void __iomem *)
 		(SMP_CORE_GROUP3_BASE + SMP_CORE0_OFFSET + SET0);
-	ipi_set0_regs[13] = (void *)
+	ipi_set0_regs[13] = (void __iomem *)
 		(SMP_CORE_GROUP3_BASE + SMP_CORE1_OFFSET + SET0);
-	ipi_set0_regs[14] = (void *)
+	ipi_set0_regs[14] = (void __iomem *)
 		(SMP_CORE_GROUP3_BASE + SMP_CORE2_OFFSET + SET0);
-	ipi_set0_regs[15] = (void *)
+	ipi_set0_regs[15] = (void __iomem *)
 		(SMP_CORE_GROUP3_BASE + SMP_CORE3_OFFSET + SET0);
 }
 
 static void ipi_clear0_regs_init(void)
 {
-	ipi_clear0_regs[0] = (void *)
+	ipi_clear0_regs[0] = (void __iomem *)
 		(SMP_CORE_GROUP0_BASE + SMP_CORE0_OFFSET + CLEAR0);
-	ipi_clear0_regs[1] = (void *)
+	ipi_clear0_regs[1] = (void __iomem *)
 		(SMP_CORE_GROUP0_BASE + SMP_CORE1_OFFSET + CLEAR0);
-	ipi_clear0_regs[2] = (void *)
+	ipi_clear0_regs[2] = (void __iomem *)
 		(SMP_CORE_GROUP0_BASE + SMP_CORE2_OFFSET + CLEAR0);
-	ipi_clear0_regs[3] = (void *)
+	ipi_clear0_regs[3] = (void __iomem *)
 		(SMP_CORE_GROUP0_BASE + SMP_CORE3_OFFSET + CLEAR0);
-	ipi_clear0_regs[4] = (void *)
+	ipi_clear0_regs[4] = (void __iomem *)
 		(SMP_CORE_GROUP1_BASE + SMP_CORE0_OFFSET + CLEAR0);
-	ipi_clear0_regs[5] = (void *)
+	ipi_clear0_regs[5] = (void __iomem *)
 		(SMP_CORE_GROUP1_BASE + SMP_CORE1_OFFSET + CLEAR0);
-	ipi_clear0_regs[6] = (void *)
+	ipi_clear0_regs[6] = (void __iomem *)
 		(SMP_CORE_GROUP1_BASE + SMP_CORE2_OFFSET + CLEAR0);
-	ipi_clear0_regs[7] = (void *)
+	ipi_clear0_regs[7] = (void __iomem *)
 		(SMP_CORE_GROUP1_BASE + SMP_CORE3_OFFSET + CLEAR0);
-	ipi_clear0_regs[8] = (void *)
+	ipi_clear0_regs[8] = (void __iomem *)
 		(SMP_CORE_GROUP2_BASE + SMP_CORE0_OFFSET + CLEAR0);
-	ipi_clear0_regs[9] = (void *)
+	ipi_clear0_regs[9] = (void __iomem *)
 		(SMP_CORE_GROUP2_BASE + SMP_CORE1_OFFSET + CLEAR0);
-	ipi_clear0_regs[10] = (void *)
+	ipi_clear0_regs[10] = (void __iomem *)
 		(SMP_CORE_GROUP2_BASE + SMP_CORE2_OFFSET + CLEAR0);
-	ipi_clear0_regs[11] = (void *)
+	ipi_clear0_regs[11] = (void __iomem *)
 		(SMP_CORE_GROUP2_BASE + SMP_CORE3_OFFSET + CLEAR0);
-	ipi_clear0_regs[12] = (void *)
+	ipi_clear0_regs[12] = (void __iomem *)
 		(SMP_CORE_GROUP3_BASE + SMP_CORE0_OFFSET + CLEAR0);
-	ipi_clear0_regs[13] = (void *)
+	ipi_clear0_regs[13] = (void __iomem *)
 		(SMP_CORE_GROUP3_BASE + SMP_CORE1_OFFSET + CLEAR0);
-	ipi_clear0_regs[14] = (void *)
+	ipi_clear0_regs[14] = (void __iomem *)
 		(SMP_CORE_GROUP3_BASE + SMP_CORE2_OFFSET + CLEAR0);
-	ipi_clear0_regs[15] = (void *)
+	ipi_clear0_regs[15] = (void __iomem *)
 		(SMP_CORE_GROUP3_BASE + SMP_CORE3_OFFSET + CLEAR0);
 }
 
 static void ipi_status0_regs_init(void)
 {
-	ipi_status0_regs[0] = (void *)
+	ipi_status0_regs[0] = (void __iomem *)
 		(SMP_CORE_GROUP0_BASE + SMP_CORE0_OFFSET + STATUS0);
-	ipi_status0_regs[1] = (void *)
+	ipi_status0_regs[1] = (void __iomem *)
 		(SMP_CORE_GROUP0_BASE + SMP_CORE1_OFFSET + STATUS0);
-	ipi_status0_regs[2] = (void *)
+	ipi_status0_regs[2] = (void __iomem *)
 		(SMP_CORE_GROUP0_BASE + SMP_CORE2_OFFSET + STATUS0);
-	ipi_status0_regs[3] = (void *)
+	ipi_status0_regs[3] = (void __iomem *)
 		(SMP_CORE_GROUP0_BASE + SMP_CORE3_OFFSET + STATUS0);
-	ipi_status0_regs[4] = (void *)
+	ipi_status0_regs[4] = (void __iomem *)
 		(SMP_CORE_GROUP1_BASE + SMP_CORE0_OFFSET + STATUS0);
-	ipi_status0_regs[5] = (void *)
+	ipi_status0_regs[5] = (void __iomem *)
 		(SMP_CORE_GROUP1_BASE + SMP_CORE1_OFFSET + STATUS0);
-	ipi_status0_regs[6] = (void *)
+	ipi_status0_regs[6] = (void __iomem *)
 		(SMP_CORE_GROUP1_BASE + SMP_CORE2_OFFSET + STATUS0);
-	ipi_status0_regs[7] = (void *)
+	ipi_status0_regs[7] = (void __iomem *)
 		(SMP_CORE_GROUP1_BASE + SMP_CORE3_OFFSET + STATUS0);
-	ipi_status0_regs[8] = (void *)
+	ipi_status0_regs[8] = (void __iomem *)
 		(SMP_CORE_GROUP2_BASE + SMP_CORE0_OFFSET + STATUS0);
-	ipi_status0_regs[9] = (void *)
+	ipi_status0_regs[9] = (void __iomem *)
 		(SMP_CORE_GROUP2_BASE + SMP_CORE1_OFFSET + STATUS0);
-	ipi_status0_regs[10] = (void *)
+	ipi_status0_regs[10] = (void __iomem *)
 		(SMP_CORE_GROUP2_BASE + SMP_CORE2_OFFSET + STATUS0);
-	ipi_status0_regs[11] = (void *)
+	ipi_status0_regs[11] = (void __iomem *)
 		(SMP_CORE_GROUP2_BASE + SMP_CORE3_OFFSET + STATUS0);
-	ipi_status0_regs[12] = (void *)
+	ipi_status0_regs[12] = (void __iomem *)
 		(SMP_CORE_GROUP3_BASE + SMP_CORE0_OFFSET + STATUS0);
-	ipi_status0_regs[13] = (void *)
+	ipi_status0_regs[13] = (void __iomem *)
 		(SMP_CORE_GROUP3_BASE + SMP_CORE1_OFFSET + STATUS0);
-	ipi_status0_regs[14] = (void *)
+	ipi_status0_regs[14] = (void __iomem *)
 		(SMP_CORE_GROUP3_BASE + SMP_CORE2_OFFSET + STATUS0);
-	ipi_status0_regs[15] = (void *)
+	ipi_status0_regs[15] = (void __iomem *)
 		(SMP_CORE_GROUP3_BASE + SMP_CORE3_OFFSET + STATUS0);
 }
 
 static void ipi_en0_regs_init(void)
 {
-	ipi_en0_regs[0] = (void *)
+	ipi_en0_regs[0] = (void __iomem *)
 		(SMP_CORE_GROUP0_BASE + SMP_CORE0_OFFSET + EN0);
-	ipi_en0_regs[1] = (void *)
+	ipi_en0_regs[1] = (void __iomem *)
 		(SMP_CORE_GROUP0_BASE + SMP_CORE1_OFFSET + EN0);
-	ipi_en0_regs[2] = (void *)
+	ipi_en0_regs[2] = (void __iomem *)
 		(SMP_CORE_GROUP0_BASE + SMP_CORE2_OFFSET + EN0);
-	ipi_en0_regs[3] = (void *)
+	ipi_en0_regs[3] = (void __iomem *)
 		(SMP_CORE_GROUP0_BASE + SMP_CORE3_OFFSET + EN0);
-	ipi_en0_regs[4] = (void *)
+	ipi_en0_regs[4] = (void __iomem *)
 		(SMP_CORE_GROUP1_BASE + SMP_CORE0_OFFSET + EN0);
-	ipi_en0_regs[5] = (void *)
+	ipi_en0_regs[5] = (void __iomem *)
 		(SMP_CORE_GROUP1_BASE + SMP_CORE1_OFFSET + EN0);
-	ipi_en0_regs[6] = (void *)
+	ipi_en0_regs[6] = (void __iomem *)
 		(SMP_CORE_GROUP1_BASE + SMP_CORE2_OFFSET + EN0);
-	ipi_en0_regs[7] = (void *)
+	ipi_en0_regs[7] = (void __iomem *)
 		(SMP_CORE_GROUP1_BASE + SMP_CORE3_OFFSET + EN0);
-	ipi_en0_regs[8] = (void *)
+	ipi_en0_regs[8] = (void __iomem *)
 		(SMP_CORE_GROUP2_BASE + SMP_CORE0_OFFSET + EN0);
-	ipi_en0_regs[9] = (void *)
+	ipi_en0_regs[9] = (void __iomem *)
 		(SMP_CORE_GROUP2_BASE + SMP_CORE1_OFFSET + EN0);
-	ipi_en0_regs[10] = (void *)
+	ipi_en0_regs[10] = (void __iomem *)
 		(SMP_CORE_GROUP2_BASE + SMP_CORE2_OFFSET + EN0);
-	ipi_en0_regs[11] = (void *)
+	ipi_en0_regs[11] = (void __iomem *)
 		(SMP_CORE_GROUP2_BASE + SMP_CORE3_OFFSET + EN0);
-	ipi_en0_regs[12] = (void *)
+	ipi_en0_regs[12] = (void __iomem *)
 		(SMP_CORE_GROUP3_BASE + SMP_CORE0_OFFSET + EN0);
-	ipi_en0_regs[13] = (void *)
+	ipi_en0_regs[13] = (void __iomem *)
 		(SMP_CORE_GROUP3_BASE + SMP_CORE1_OFFSET + EN0);
-	ipi_en0_regs[14] = (void *)
+	ipi_en0_regs[14] = (void __iomem *)
 		(SMP_CORE_GROUP3_BASE + SMP_CORE2_OFFSET + EN0);
-	ipi_en0_regs[15] = (void *)
+	ipi_en0_regs[15] = (void __iomem *)
 		(SMP_CORE_GROUP3_BASE + SMP_CORE3_OFFSET + EN0);
 }
 
 static void ipi_mailbox_buf_init(void)
 {
-	ipi_mailbox_buf[0] = (void *)
+	ipi_mailbox_buf[0] = (void __iomem *)
 		(SMP_CORE_GROUP0_BASE + SMP_CORE0_OFFSET + BUF);
-	ipi_mailbox_buf[1] = (void *)
+	ipi_mailbox_buf[1] = (void __iomem *)
 		(SMP_CORE_GROUP0_BASE + SMP_CORE1_OFFSET + BUF);
-	ipi_mailbox_buf[2] = (void *)
+	ipi_mailbox_buf[2] = (void __iomem *)
 		(SMP_CORE_GROUP0_BASE + SMP_CORE2_OFFSET + BUF);
-	ipi_mailbox_buf[3] = (void *)
+	ipi_mailbox_buf[3] = (void __iomem *)
 		(SMP_CORE_GROUP0_BASE + SMP_CORE3_OFFSET + BUF);
-	ipi_mailbox_buf[4] = (void *)
+	ipi_mailbox_buf[4] = (void __iomem *)
 		(SMP_CORE_GROUP1_BASE + SMP_CORE0_OFFSET + BUF);
-	ipi_mailbox_buf[5] = (void *)
+	ipi_mailbox_buf[5] = (void __iomem *)
 		(SMP_CORE_GROUP1_BASE + SMP_CORE1_OFFSET + BUF);
-	ipi_mailbox_buf[6] = (void *)
+	ipi_mailbox_buf[6] = (void __iomem *)
 		(SMP_CORE_GROUP1_BASE + SMP_CORE2_OFFSET + BUF);
-	ipi_mailbox_buf[7] = (void *)
+	ipi_mailbox_buf[7] = (void __iomem *)
 		(SMP_CORE_GROUP1_BASE + SMP_CORE3_OFFSET + BUF);
-	ipi_mailbox_buf[8] = (void *)
+	ipi_mailbox_buf[8] = (void __iomem *)
 		(SMP_CORE_GROUP2_BASE + SMP_CORE0_OFFSET + BUF);
-	ipi_mailbox_buf[9] = (void *)
+	ipi_mailbox_buf[9] = (void __iomem *)
 		(SMP_CORE_GROUP2_BASE + SMP_CORE1_OFFSET + BUF);
-	ipi_mailbox_buf[10] = (void *)
+	ipi_mailbox_buf[10] = (void __iomem *)
 		(SMP_CORE_GROUP2_BASE + SMP_CORE2_OFFSET + BUF);
-	ipi_mailbox_buf[11] = (void *)
+	ipi_mailbox_buf[11] = (void __iomem *)
 		(SMP_CORE_GROUP2_BASE + SMP_CORE3_OFFSET + BUF);
-	ipi_mailbox_buf[12] = (void *)
+	ipi_mailbox_buf[12] = (void __iomem *)
 		(SMP_CORE_GROUP3_BASE + SMP_CORE0_OFFSET + BUF);
-	ipi_mailbox_buf[13] = (void *)
+	ipi_mailbox_buf[13] = (void __iomem *)
 		(SMP_CORE_GROUP3_BASE + SMP_CORE1_OFFSET + BUF);
-	ipi_mailbox_buf[14] = (void *)
+	ipi_mailbox_buf[14] = (void __iomem *)
 		(SMP_CORE_GROUP3_BASE + SMP_CORE2_OFFSET + BUF);
-	ipi_mailbox_buf[15] = (void *)
+	ipi_mailbox_buf[15] = (void __iomem *)
 		(SMP_CORE_GROUP3_BASE + SMP_CORE3_OFFSET + BUF);
 }
 

From fe1328b5b2a087221e31da77e617f4c2b70f3b7f Mon Sep 17 00:00:00 2001
From: Ying Liu <victor.liu@nxp.com>
Date: Fri, 21 Jul 2023 09:29:03 +0000
Subject: [PATCH 0172/1189] backlight: gpio_backlight: Drop output GPIO
 direction check for initial power state

So, let's drop output GPIO direction check and only check GPIO value to set
the initial power state.

Fixes: 706dc68102bc ("backlight: gpio: Explicitly set the direction of the GPIO")
Signed-off-by: Liu Ying <victor.liu@nxp.com>
Reviewed-by: Andy Shevchenko <andy@kernel.org>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Link: https://lore.kernel.org/r/20230721093342.1532531-1-victor.liu@nxp.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/video/backlight/gpio_backlight.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/video/backlight/gpio_backlight.c b/drivers/video/backlight/gpio_backlight.c
index 6f78d928f054..38c46936fdcd 100644
--- a/drivers/video/backlight/gpio_backlight.c
+++ b/drivers/video/backlight/gpio_backlight.c
@@ -87,8 +87,7 @@ static int gpio_backlight_probe(struct platform_device *pdev)
 		/* Not booted with device tree or no phandle link to the node */
 		bl->props.power = def_value ? FB_BLANK_UNBLANK
 					    : FB_BLANK_POWERDOWN;
-	else if (gpiod_get_direction(gbl->gpiod) == 0 &&
-		 gpiod_get_value_cansleep(gbl->gpiod) == 0)
+	else if (gpiod_get_value_cansleep(gbl->gpiod) == 0)
 		bl->props.power = FB_BLANK_POWERDOWN;
 	else
 		bl->props.power = FB_BLANK_UNBLANK;

From cbc02854331edc6dc22d8b77b6e22e38ebc7dd51 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Wed, 26 Jul 2023 22:58:17 -0400
Subject: [PATCH 0173/1189] XArray: Do not return sibling entries from
 xa_load()

It is possible for xa_load() to observe a sibling entry pointing to
another sibling entry.  An example:

Thread A:		Thread B:
			xa_store_range(xa, entry, 188, 191, gfp);
xa_load(xa, 191);
entry = xa_entry(xa, node, 63);
[entry is a sibling of 188]
			xa_store_range(xa, entry, 184, 191, gfp);
if (xa_is_sibling(entry))
offset = xa_to_sibling(entry);
entry = xa_entry(xas->xa, node, offset);
[entry is now a sibling of 184]

It is sufficient to go around this loop until we hit a non-sibling entry.
Sibling entries always point earlier in the node, so we are guaranteed
to terminate this search.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Fixes: 6b24ca4a1a8d ("mm: Use multi-index entries in the page cache")
Cc: stable@vger.kernel.org
---
 lib/xarray.c                          |  2 +-
 tools/testing/radix-tree/multiorder.c | 68 ++++++++++++++++++++++++++-
 2 files changed, 67 insertions(+), 3 deletions(-)

diff --git a/lib/xarray.c b/lib/xarray.c
index 2071a3718f4e..142e36f9dfda 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -206,7 +206,7 @@ static void *xas_descend(struct xa_state *xas, struct xa_node *node)
 	void *entry = xa_entry(xas->xa, node, offset);
 
 	xas->xa_node = node;
-	if (xa_is_sibling(entry)) {
+	while (xa_is_sibling(entry)) {
 		offset = xa_to_sibling(entry);
 		entry = xa_entry(xas->xa, node, offset);
 		if (node->shift && xa_is_node(entry))
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index e00520cc6349..cffaf2245d4f 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -159,7 +159,7 @@ void multiorder_tagged_iteration(struct xarray *xa)
 	item_kill_tree(xa);
 }
 
-bool stop_iteration = false;
+bool stop_iteration;
 
 static void *creator_func(void *ptr)
 {
@@ -201,6 +201,7 @@ static void multiorder_iteration_race(struct xarray *xa)
 	pthread_t worker_thread[num_threads];
 	int i;
 
+	stop_iteration = false;
 	pthread_create(&worker_thread[0], NULL, &creator_func, xa);
 	for (i = 1; i < num_threads; i++)
 		pthread_create(&worker_thread[i], NULL, &iterator_func, xa);
@@ -211,6 +212,61 @@ static void multiorder_iteration_race(struct xarray *xa)
 	item_kill_tree(xa);
 }
 
+static void *load_creator(void *ptr)
+{
+	/* 'order' is set up to ensure we have sibling entries */
+	unsigned int order;
+	struct radix_tree_root *tree = ptr;
+	int i;
+
+	rcu_register_thread();
+	item_insert_order(tree, 3 << RADIX_TREE_MAP_SHIFT, 0);
+	item_insert_order(tree, 2 << RADIX_TREE_MAP_SHIFT, 0);
+	for (i = 0; i < 10000; i++) {
+		for (order = 1; order < RADIX_TREE_MAP_SHIFT; order++) {
+			unsigned long index = (3 << RADIX_TREE_MAP_SHIFT) -
+						(1 << order);
+			item_insert_order(tree, index, order);
+			item_delete_rcu(tree, index);
+		}
+	}
+	rcu_unregister_thread();
+
+	stop_iteration = true;
+	return NULL;
+}
+
+static void *load_worker(void *ptr)
+{
+	unsigned long index = (3 << RADIX_TREE_MAP_SHIFT) - 1;
+
+	rcu_register_thread();
+	while (!stop_iteration) {
+		struct item *item = xa_load(ptr, index);
+		assert(!xa_is_internal(item));
+	}
+	rcu_unregister_thread();
+
+	return NULL;
+}
+
+static void load_race(struct xarray *xa)
+{
+	const int num_threads = sysconf(_SC_NPROCESSORS_ONLN) * 4;
+	pthread_t worker_thread[num_threads];
+	int i;
+
+	stop_iteration = false;
+	pthread_create(&worker_thread[0], NULL, &load_creator, xa);
+	for (i = 1; i < num_threads; i++)
+		pthread_create(&worker_thread[i], NULL, &load_worker, xa);
+
+	for (i = 0; i < num_threads; i++)
+		pthread_join(worker_thread[i], NULL);
+
+	item_kill_tree(xa);
+}
+
 static DEFINE_XARRAY(array);
 
 void multiorder_checks(void)
@@ -218,12 +274,20 @@ void multiorder_checks(void)
 	multiorder_iteration(&array);
 	multiorder_tagged_iteration(&array);
 	multiorder_iteration_race(&array);
+	load_race(&array);
 
 	radix_tree_cpu_dead(0);
 }
 
-int __weak main(void)
+int __weak main(int argc, char **argv)
 {
+	int opt;
+
+	while ((opt = getopt(argc, argv, "ls:v")) != -1) {
+		if (opt == 'v')
+			test_verbose++;
+	}
+
 	rcu_register_thread();
 	radix_tree_init();
 	multiorder_checks();

From 88cc47e24597971b05b6e94c28a2fc81d2a8d61a Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 28 Jul 2023 17:26:54 -0300
Subject: [PATCH 0174/1189] perf build: Define YYNOMEM as YYNOABORT for bison <
 3.81

YYNOMEM was introduced in bison 3.81, so define it as YYABORT for older
versions, which should provide the previous perf behaviour.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/Build | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 96f4ea1d45c5..9c6c4475524b 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -301,6 +301,12 @@ ifeq ($(BISON_GE_35),1)
 else
   bison_flags += -w
 endif
+
+BISON_LT_381 := $(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\).\([0-9]\+\)/\1\2\3/g') \< 381)
+ifeq ($(BISON_LT_381),1)
+  bison_flags += -DYYNOMEM=YYABORT
+endif
+
 CFLAGS_parse-events-bison.o += $(bison_flags)
 CFLAGS_pmu-bison.o          += -DYYLTYPE_IS_TRIVIAL=0 $(bison_flags)
 CFLAGS_expr-bison.o         += -DYYLTYPE_IS_TRIVIAL=0 $(bison_flags)

From 9462e4de62755c85867991a4beccff15377d0e95 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 27 Jun 2023 11:10:23 -0700
Subject: [PATCH 0175/1189] perf parse-event: Add memory allocation test for
 name terms

If the name memory allocation fails then propagate to the parser.

Committer notes:

Use $(BISON_FALLBACK_FLAGS) on the bison call so that we continue
building with older bison versions, before 3.81, where YYNOMEM isn't
present.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20230627181030.95608-7-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/Build          | 2 +-
 tools/perf/util/parse-events.c | 5 ++++-
 tools/perf/util/parse-events.y | 2 +-
 3 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 9c6c4475524b..bb08149179e4 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -246,7 +246,7 @@ $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-flex.h: util/parse-
 
 $(OUTPUT)util/parse-events-bison.c $(OUTPUT)util/parse-events-bison.h: util/parse-events.y
 	$(call rule_mkdir)
-	$(Q)$(call echo-cmd,bison)$(BISON) -v $< -d $(PARSER_DEBUG_BISON) $(BISON_FILE_PREFIX_MAP) \
+	$(Q)$(call echo-cmd,bison)$(BISON) -v $< -d $(PARSER_DEBUG_BISON) $(BISON_FILE_PREFIX_MAP) $(BISON_FALLBACK_FLAGS) \
 		-o $(OUTPUT)util/parse-events-bison.c -p parse_events_
 
 $(OUTPUT)util/expr-flex.c $(OUTPUT)util/expr-flex.h: util/expr.l $(OUTPUT)util/expr-bison.c
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 75778d5be5b6..83adb0c2a6bc 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1973,8 +1973,11 @@ int parse_events_name(struct list_head *list, const char *name)
 	struct evsel *evsel;
 
 	__evlist__for_each_entry(list, evsel) {
-		if (!evsel->name)
+		if (!evsel->name) {
 			evsel->name = strdup(name);
+			if (!evsel->name)
+				return -ENOMEM;
+		}
 	}
 
 	return 0;
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index b09a5fa92144..3ee351768433 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -263,7 +263,7 @@ PE_EVENT_NAME event_def
 	free($1);
 	if (err) {
 		free_list_evsel($2);
-		YYABORT;
+		YYNOMEM;
 	}
 	$$ = $2;
 }

From a7a3252dad354a9e5c173156dab959e4019b9467 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 27 Jun 2023 11:10:24 -0700
Subject: [PATCH 0176/1189] perf parse-events: Separate YYABORT and YYNOMEM
 cases

Split cases in event_pmu for greater accuracy.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20230627181030.95608-8-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.y | 45 ++++++++++++++++++++--------------
 1 file changed, 26 insertions(+), 19 deletions(-)

diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 3ee351768433..d22866b97b76 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -283,37 +283,42 @@ event_pmu:
 PE_NAME opt_pmu_config
 {
 	struct parse_events_state *parse_state = _parse_state;
-	struct parse_events_error *error = parse_state->error;
 	struct list_head *list = NULL, *orig_terms = NULL, *terms= NULL;
+	struct parse_events_error *error = parse_state->error;
 	char *pattern = NULL;
 
-#define CLEANUP_YYABORT					\
+#define CLEANUP						\
 	do {						\
 		parse_events_terms__delete($2);		\
 		parse_events_terms__delete(orig_terms);	\
 		free(list);				\
 		free($1);				\
 		free(pattern);				\
-		YYABORT;				\
 	} while(0)
 
-	if (parse_events_copy_term_list($2, &orig_terms))
-		CLEANUP_YYABORT;
-
 	if (error)
 		error->idx = @1.first_column;
 
+	if (parse_events_copy_term_list($2, &orig_terms)) {
+		CLEANUP;
+		YYNOMEM;
+	}
+
 	list = alloc_list();
-	if (!list)
-		CLEANUP_YYABORT;
+	if (!list) {
+		CLEANUP;
+		YYNOMEM;
+	}
 	/* Attempt to add to list assuming $1 is a PMU name. */
 	if (parse_events_add_pmu(parse_state, list, $1, $2, /*auto_merge_stats=*/false)) {
 		struct perf_pmu *pmu = NULL;
 		int ok = 0;
 
 		/* Failure to add, try wildcard expansion of $1 as a PMU name. */
-		if (asprintf(&pattern, "%s*", $1) < 0)
-			CLEANUP_YYABORT;
+		if (asprintf(&pattern, "%s*", $1) < 0) {
+			CLEANUP;
+			YYNOMEM;
+		}
 
 		while ((pmu = perf_pmus__scan(pmu)) != NULL) {
 			char *name = pmu->name;
@@ -328,8 +333,10 @@ PE_NAME opt_pmu_config
 			    !perf_pmu__match(pattern, pmu->alias_name, $1)) {
 				bool auto_merge_stats = perf_pmu__auto_merge_stats(pmu);
 
-				if (parse_events_copy_term_list(orig_terms, &terms))
-					CLEANUP_YYABORT;
+				if (parse_events_copy_term_list(orig_terms, &terms)) {
+					CLEANUP;
+					YYNOMEM;
+				}
 				if (!parse_events_add_pmu(parse_state, list, pmu->name, terms,
 							  auto_merge_stats)) {
 					ok++;
@@ -345,15 +352,15 @@ PE_NAME opt_pmu_config
 			ok = !parse_events_multi_pmu_add(parse_state, $1, $2, &list);
 			$2 = NULL;
 		}
-		if (!ok)
-			CLEANUP_YYABORT;
+		if (!ok) {
+			CLEANUP;
+			YYABORT;
+		}
 	}
-	parse_events_terms__delete($2);
-	parse_events_terms__delete(orig_terms);
-	free(pattern);
-	free($1);
 	$$ = list;
-#undef CLEANUP_YYABORT
+	list = NULL;
+	CLEANUP;
+#undef CLEANUP
 }
 |
 PE_NAME sep_dc

From 77cdd787fc45e3426b8e0b5038b85c276540dfb4 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 27 Jun 2023 11:10:25 -0700
Subject: [PATCH 0177/1189] perf parse-events: Move instances of YYABORT to
 YYNOMEM

Migration to improve error reporting as YYABORT cases should carry
event parsing errors.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20230627181030.95608-9-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.y | 58 +++++++++++++++++++++++-----------
 1 file changed, 40 insertions(+), 18 deletions(-)

diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index d22866b97b76..eaf43bd8fe3f 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -390,7 +390,8 @@ value_sym '/' event_config '/'
 	bool wildcard = (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE);
 
 	list = alloc_list();
-	ABORT_ON(!list);
+	if (!list)
+		YYNOMEM;
 	err = parse_events_add_numeric(_parse_state, list, type, config, $3, wildcard);
 	parse_events_terms__delete($3);
 	if (err) {
@@ -408,7 +409,8 @@ value_sym sep_slash_slash_dc
 	bool wildcard = (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE);
 
 	list = alloc_list();
-	ABORT_ON(!list);
+	if (!list)
+		YYNOMEM;
 	ABORT_ON(parse_events_add_numeric(_parse_state, list, type, config,
 					  /*head_config=*/NULL, wildcard));
 	$$ = list;
@@ -419,7 +421,8 @@ PE_VALUE_SYM_TOOL sep_slash_slash_dc
 	struct list_head *list;
 
 	list = alloc_list();
-	ABORT_ON(!list);
+	if (!list)
+		YYNOMEM;
 	ABORT_ON(parse_events_add_tool(_parse_state, list, $1));
 	$$ = list;
 }
@@ -432,7 +435,9 @@ PE_LEGACY_CACHE opt_event_config
 	int err;
 
 	list = alloc_list();
-	ABORT_ON(!list);
+	if (!list)
+		YYNOMEM;
+
 	err = parse_events_add_cache(list, &parse_state->idx, $1, parse_state, $2);
 
 	parse_events_terms__delete($2);
@@ -451,7 +456,9 @@ PE_PREFIX_MEM PE_VALUE PE_BP_SLASH PE_VALUE PE_BP_COLON PE_MODIFIER_BP opt_event
 	int err;
 
 	list = alloc_list();
-	ABORT_ON(!list);
+	if (!list)
+		YYNOMEM;
+
 	err = parse_events_add_breakpoint(_parse_state, list,
 					  $2, $6, $4, $7);
 	parse_events_terms__delete($7);
@@ -469,7 +476,9 @@ PE_PREFIX_MEM PE_VALUE PE_BP_SLASH PE_VALUE opt_event_config
 	int err;
 
 	list = alloc_list();
-	ABORT_ON(!list);
+	if (!list)
+		YYNOMEM;
+
 	err = parse_events_add_breakpoint(_parse_state, list,
 					  $2, NULL, $4, $5);
 	parse_events_terms__delete($5);
@@ -486,7 +495,9 @@ PE_PREFIX_MEM PE_VALUE PE_BP_COLON PE_MODIFIER_BP opt_event_config
 	int err;
 
 	list = alloc_list();
-	ABORT_ON(!list);
+	if (!list)
+		YYNOMEM;
+
 	err = parse_events_add_breakpoint(_parse_state, list,
 					  $2, $4, 0, $5);
 	parse_events_terms__delete($5);
@@ -504,7 +515,8 @@ PE_PREFIX_MEM PE_VALUE opt_event_config
 	int err;
 
 	list = alloc_list();
-	ABORT_ON(!list);
+	if (!list)
+		YYNOMEM;
 	err = parse_events_add_breakpoint(_parse_state, list,
 					  $2, NULL, 0, $3);
 	parse_events_terms__delete($3);
@@ -524,7 +536,8 @@ tracepoint_name opt_event_config
 	int err;
 
 	list = alloc_list();
-	ABORT_ON(!list);
+	if (!list)
+		YYNOMEM;
 	if (error)
 		error->idx = @1.first_column;
 
@@ -556,7 +569,8 @@ PE_VALUE ':' PE_VALUE opt_event_config
 	int err;
 
 	list = alloc_list();
-	ABORT_ON(!list);
+	if (!list)
+		YYNOMEM;
 	err = parse_events_add_numeric(_parse_state, list, (u32)$1, $3, $4,
 				       /*wildcard=*/false);
 	parse_events_terms__delete($4);
@@ -575,7 +589,8 @@ PE_RAW opt_event_config
 	u64 num;
 
 	list = alloc_list();
-	ABORT_ON(!list);
+	if (!list)
+		YYNOMEM;
 	errno = 0;
 	num = strtoull($1 + 1, NULL, 16);
 	ABORT_ON(errno);
@@ -598,7 +613,8 @@ PE_BPF_OBJECT opt_event_config
 	int err;
 
 	list = alloc_list();
-	ABORT_ON(!list);
+	if (!list)
+		YYNOMEM;
 	err = parse_events_load_bpf(parse_state, list, $1, false, $2);
 	parse_events_terms__delete($2);
 	free($1);
@@ -615,7 +631,8 @@ PE_BPF_SOURCE opt_event_config
 	int err;
 
 	list = alloc_list();
-	ABORT_ON(!list);
+	if (!list)
+		YYNOMEM;
 	err = parse_events_load_bpf(_parse_state, list, $1, true, $2);
 	parse_events_terms__delete($2);
 	if (err) {
@@ -680,7 +697,8 @@ event_term
 	struct list_head *head = malloc(sizeof(*head));
 	struct parse_events_term *term = $1;
 
-	ABORT_ON(!head);
+	if (!head)
+		YYNOMEM;
 	INIT_LIST_HEAD(head);
 	list_add_tail(&term->list, head);
 	$$ = head;
@@ -857,7 +875,8 @@ PE_DRV_CFG_TERM
 	struct parse_events_term *term;
 	char *config = strdup($1);
 
-	ABORT_ON(!config);
+	if (!config)
+		YYNOMEM;
 	if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_DRV_CFG,
 					config, $1, &@1, NULL)) {
 		free($1);
@@ -888,7 +907,8 @@ array_terms ',' array_term
 	new_array.ranges = realloc($1.ranges,
 				sizeof(new_array.ranges[0]) *
 				new_array.nr_ranges);
-	ABORT_ON(!new_array.ranges);
+	if (!new_array.ranges)
+		YYNOMEM;
 	memcpy(&new_array.ranges[$1.nr_ranges], $3.ranges,
 	       $3.nr_ranges * sizeof(new_array.ranges[0]));
 	free($3.ranges);
@@ -904,7 +924,8 @@ PE_VALUE
 
 	array.nr_ranges = 1;
 	array.ranges = malloc(sizeof(array.ranges[0]));
-	ABORT_ON(!array.ranges);
+	if (!array.ranges)
+		YYNOMEM;
 	array.ranges[0].start = $1;
 	array.ranges[0].length = 1;
 	$$ = array;
@@ -917,7 +938,8 @@ PE_VALUE PE_ARRAY_RANGE PE_VALUE
 	ABORT_ON($3 < $1);
 	array.nr_ranges = 1;
 	array.ranges = malloc(sizeof(array.ranges[0]));
-	ABORT_ON(!array.ranges);
+	if (!array.ranges)
+		YYNOMEM;
 	array.ranges[0].start = $1;
 	array.ranges[0].length = $3 - $1 + 1;
 	$$ = array;

From b52cb995f1a559bc6e1a7cdc0ed0375503528541 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 27 Jun 2023 11:10:26 -0700
Subject: [PATCH 0178/1189] perf parse-events: Separate ENOMEM memory handling

Add PE_ABORT that will YYNOMEM or YYABORT accordingly.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20230627181030.95608-10-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.y | 134 ++++++++++++++++++++-------------
 1 file changed, 82 insertions(+), 52 deletions(-)

diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index eaf43bd8fe3f..f090a85c4518 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -28,6 +28,13 @@ do { \
 		YYABORT; \
 } while (0)
 
+#define PE_ABORT(val) \
+do { \
+	if (val == -ENOMEM) \
+		YYNOMEM; \
+	YYABORT; \
+} while (0)
+
 static struct list_head* alloc_list(void)
 {
 	struct list_head *list;
@@ -371,7 +378,7 @@ PE_NAME sep_dc
 	err = parse_events_multi_pmu_add(_parse_state, $1, NULL, &list);
 	free($1);
 	if (err < 0)
-		YYABORT;
+		PE_ABORT(err);
 	$$ = list;
 }
 
@@ -396,7 +403,7 @@ value_sym '/' event_config '/'
 	parse_events_terms__delete($3);
 	if (err) {
 		free_list_evsel(list);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = list;
 }
@@ -407,23 +414,28 @@ value_sym sep_slash_slash_dc
 	int type = $1 >> 16;
 	int config = $1 & 255;
 	bool wildcard = (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE);
+	int err;
 
 	list = alloc_list();
 	if (!list)
 		YYNOMEM;
-	ABORT_ON(parse_events_add_numeric(_parse_state, list, type, config,
-					  /*head_config=*/NULL, wildcard));
+	err = parse_events_add_numeric(_parse_state, list, type, config, /*head_config=*/NULL, wildcard);
+	if (err)
+		PE_ABORT(err);
 	$$ = list;
 }
 |
 PE_VALUE_SYM_TOOL sep_slash_slash_dc
 {
 	struct list_head *list;
+	int err;
 
 	list = alloc_list();
 	if (!list)
 		YYNOMEM;
-	ABORT_ON(parse_events_add_tool(_parse_state, list, $1));
+	err = parse_events_add_tool(_parse_state, list, $1);
+	if (err)
+		YYNOMEM;
 	$$ = list;
 }
 
@@ -444,7 +456,7 @@ PE_LEGACY_CACHE opt_event_config
 	free($1);
 	if (err) {
 		free_list_evsel(list);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = list;
 }
@@ -465,7 +477,7 @@ PE_PREFIX_MEM PE_VALUE PE_BP_SLASH PE_VALUE PE_BP_COLON PE_MODIFIER_BP opt_event
 	free($6);
 	if (err) {
 		free(list);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = list;
 }
@@ -484,7 +496,7 @@ PE_PREFIX_MEM PE_VALUE PE_BP_SLASH PE_VALUE opt_event_config
 	parse_events_terms__delete($5);
 	if (err) {
 		free(list);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = list;
 }
@@ -504,7 +516,7 @@ PE_PREFIX_MEM PE_VALUE PE_BP_COLON PE_MODIFIER_BP opt_event_config
 	free($4);
 	if (err) {
 		free(list);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = list;
 }
@@ -522,7 +534,7 @@ PE_PREFIX_MEM PE_VALUE opt_event_config
 	parse_events_terms__delete($3);
 	if (err) {
 		free(list);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = list;
 }
@@ -549,7 +561,7 @@ tracepoint_name opt_event_config
 	free($1.event);
 	if (err) {
 		free(list);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = list;
 }
@@ -576,7 +588,7 @@ PE_VALUE ':' PE_VALUE opt_event_config
 	parse_events_terms__delete($4);
 	if (err) {
 		free(list);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = list;
 }
@@ -600,7 +612,7 @@ PE_RAW opt_event_config
 	parse_events_terms__delete($2);
 	if (err) {
 		free(list);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = list;
 }
@@ -620,7 +632,7 @@ PE_BPF_OBJECT opt_event_config
 	free($1);
 	if (err) {
 		free(list);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = list;
 }
@@ -637,7 +649,7 @@ PE_BPF_SOURCE opt_event_config
 	parse_events_terms__delete($2);
 	if (err) {
 		free(list);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = list;
 }
@@ -712,11 +724,12 @@ event_term:
 PE_RAW
 {
 	struct parse_events_term *term;
+	int err = parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_RAW,
+					 strdup("raw"), $1, &@1, &@1);
 
-	if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_RAW,
-					strdup("raw"), $1, &@1, &@1)) {
+	if (err) {
 		free($1);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = term;
 }
@@ -724,12 +737,12 @@ PE_RAW
 name_or_raw '=' name_or_legacy
 {
 	struct parse_events_term *term;
+	int err = parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER, $1, $3, &@1, &@3);
 
-	if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, $3, &@1, &@3)) {
+	if (err) {
 		free($1);
 		free($3);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = term;
 }
@@ -737,11 +750,12 @@ name_or_raw '=' name_or_legacy
 name_or_raw '=' PE_VALUE
 {
 	struct parse_events_term *term;
+	int err = parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+					 $1, $3, false, &@1, &@3);
 
-	if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, $3, false, &@1, &@3)) {
+	if (err) {
 		free($1);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = term;
 }
@@ -749,12 +763,13 @@ name_or_raw '=' PE_VALUE
 name_or_raw '=' PE_TERM_HW
 {
 	struct parse_events_term *term;
+	int err = parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
+					 $1, $3.str, &@1, &@3);
 
-	if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, $3.str, &@1, &@3)) {
+	if (err) {
 		free($1);
 		free($3.str);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = term;
 }
@@ -762,11 +777,12 @@ name_or_raw '=' PE_TERM_HW
 PE_LEGACY_CACHE
 {
 	struct parse_events_term *term;
+	int err = parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE,
+					 $1, 1, true, &@1, NULL);
 
-	if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE,
-					$1, 1, true, &@1, NULL)) {
+	if (err) {
 		free($1);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = term;
 }
@@ -774,11 +790,12 @@ PE_LEGACY_CACHE
 PE_NAME
 {
 	struct parse_events_term *term;
+	int err = parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+					 $1, 1, true, &@1, NULL);
 
-	if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, 1, true, &@1, NULL)) {
+	if (err) {
 		free($1);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = term;
 }
@@ -786,11 +803,12 @@ PE_NAME
 PE_TERM_HW
 {
 	struct parse_events_term *term;
+	int err = parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_HARDWARE,
+					 $1.str, $1.num & 255, false, &@1, NULL);
 
-	if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_HARDWARE,
-				   $1.str, $1.num & 255, false, &@1, NULL)) {
+	if (err) {
 		free($1.str);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = term;
 }
@@ -798,10 +816,11 @@ PE_TERM_HW
 PE_TERM '=' name_or_legacy
 {
 	struct parse_events_term *term;
+	int err = parse_events_term__str(&term, (int)$1, NULL, $3, &@1, &@3);
 
-	if (parse_events_term__str(&term, (int)$1, NULL, $3, &@1, &@3)) {
+	if (err) {
 		free($3);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = term;
 }
@@ -809,10 +828,11 @@ PE_TERM '=' name_or_legacy
 PE_TERM '=' PE_TERM_HW
 {
 	struct parse_events_term *term;
+	int err = parse_events_term__str(&term, (int)$1, NULL, $3.str, &@1, &@3);
 
-	if (parse_events_term__str(&term, (int)$1, NULL, $3.str, &@1, &@3)) {
+	if (err) {
 		free($3.str);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = term;
 }
@@ -820,37 +840,46 @@ PE_TERM '=' PE_TERM_HW
 PE_TERM '=' PE_TERM
 {
 	struct parse_events_term *term;
+	int err = parse_events_term__term(&term, (int)$1, (int)$3, &@1, &@3);
+
+	if (err)
+		PE_ABORT(err);
 
-	ABORT_ON(parse_events_term__term(&term, (int)$1, (int)$3, &@1, &@3));
 	$$ = term;
 }
 |
 PE_TERM '=' PE_VALUE
 {
 	struct parse_events_term *term;
+	int err = parse_events_term__num(&term, (int)$1, NULL, $3, false, &@1, &@3);
+
+	if (err)
+		PE_ABORT(err);
 
-	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3, false, &@1, &@3));
 	$$ = term;
 }
 |
 PE_TERM
 {
 	struct parse_events_term *term;
+	int err = parse_events_term__num(&term, (int)$1, NULL, 1, true, &@1, NULL);
+
+	if (err)
+		PE_ABORT(err);
 
-	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1, true, &@1, NULL));
 	$$ = term;
 }
 |
 name_or_raw array '=' name_or_legacy
 {
 	struct parse_events_term *term;
+	int err = parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER, $1, $4, &@1, &@4);
 
-	if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, $4, &@1, &@4)) {
+	if (err) {
 		free($1);
 		free($4);
 		free($2.ranges);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	term->array = $2;
 	$$ = term;
@@ -859,12 +888,12 @@ name_or_raw array '=' name_or_legacy
 name_or_raw array '=' PE_VALUE
 {
 	struct parse_events_term *term;
+	int err = parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, $1, $4, false, &@1, &@4);
 
-	if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, $4, false, &@1, &@4)) {
+	if (err) {
 		free($1);
 		free($2.ranges);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	term->array = $2;
 	$$ = term;
@@ -874,14 +903,15 @@ PE_DRV_CFG_TERM
 {
 	struct parse_events_term *term;
 	char *config = strdup($1);
+	int err;
 
 	if (!config)
 		YYNOMEM;
-	if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_DRV_CFG,
-					config, $1, &@1, NULL)) {
+	err = parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_DRV_CFG, config, $1, &@1, NULL);
+	if (err) {
 		free($1);
 		free(config);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = term;
 }

From b30d4f0b695428f513c561eeaea52e042ef48550 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 27 Jun 2023 11:10:27 -0700
Subject: [PATCH 0179/1189] perf parse-events: Additional error reporting

When no events or PMUs match report an error for event_pmu:

Before:
```
$ perf stat -e 'asdfasdf' -a sleep 1
Run 'perf list' for a list of valid events

 Usage: perf stat [<options>] [<command>]

    -e, --event <event>   event selector. use 'perf list' to list available events
```

After:
```
$ perf stat -e 'asdfasdf' -a sleep 1
event syntax error: 'asdfasdf'
                     \___ Bad event name

Unabled to find PMU or event on a PMU of 'asdfasdf'
Run 'perf list' for a list of valid events

 Usage: perf stat [<options>] [<command>]

    -e, --event <event>   event selector. use 'perf list' to list available events
```

Fixes the inadvertent removal when hybrid parsing was modified.

Fixes: 70c90e4a6b2fbe77 ("perf parse-events: Avoid scanning PMUs before parsing")
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20230627181030.95608-11-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.y | 25 +++++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index f090a85c4518..a636a7db6e6f 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -291,7 +291,6 @@ PE_NAME opt_pmu_config
 {
 	struct parse_events_state *parse_state = _parse_state;
 	struct list_head *list = NULL, *orig_terms = NULL, *terms= NULL;
-	struct parse_events_error *error = parse_state->error;
 	char *pattern = NULL;
 
 #define CLEANUP						\
@@ -303,9 +302,6 @@ PE_NAME opt_pmu_config
 		free(pattern);				\
 	} while(0)
 
-	if (error)
-		error->idx = @1.first_column;
-
 	if (parse_events_copy_term_list($2, &orig_terms)) {
 		CLEANUP;
 		YYNOMEM;
@@ -360,6 +356,14 @@ PE_NAME opt_pmu_config
 			$2 = NULL;
 		}
 		if (!ok) {
+			struct parse_events_error *error = parse_state->error;
+			char *help;
+
+			if (asprintf(&help, "Unabled to find PMU or event on a PMU of '%s'", $1) < 0)
+				help = NULL;
+			parse_events_error__handle(error, @1.first_column,
+						   strdup("Bad event or PMU"),
+						   help);
 			CLEANUP;
 			YYABORT;
 		}
@@ -376,9 +380,18 @@ PE_NAME sep_dc
 	int err;
 
 	err = parse_events_multi_pmu_add(_parse_state, $1, NULL, &list);
-	free($1);
-	if (err < 0)
+	if (err < 0) {
+		struct parse_events_state *parse_state = _parse_state;
+		struct parse_events_error *error = parse_state->error;
+		char *help;
+
+		if (asprintf(&help, "Unabled to find PMU or event on a PMU of '%s'", $1) < 0)
+			help = NULL;
+		parse_events_error__handle(error, @1.first_column, strdup("Bad event name"), help);
+		free($1);
 		PE_ABORT(err);
+	}
+	free($1);
 	$$ = list;
 }
 

From d81fa63b09fbd8b6ae5761164ed75f9ccf005893 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 27 Jun 2023 11:10:28 -0700
Subject: [PATCH 0180/1189] perf parse-events: Populate error column for
 BPF/tracepoint events

Follow convention from parse_events_terms__num/str and pass the
YYLTYPE for the location.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20230627181030.95608-12-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/bpf.c         |  2 +-
 tools/perf/util/parse-events.c | 80 ++++++++++++++++++++--------------
 tools/perf/util/parse-events.h |  8 ++--
 tools/perf/util/parse-events.y |  6 +--
 4 files changed, 57 insertions(+), 39 deletions(-)

diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 8beb46066034..31796f2a80f4 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -124,7 +124,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
 	parse_state.error = &parse_error;
 	INIT_LIST_HEAD(&parse_state.list);
 
-	err = parse_events_load_bpf_obj(&parse_state, &parse_state.list, obj, NULL);
+	err = parse_events_load_bpf_obj(&parse_state, &parse_state.list, obj, NULL, NULL);
 	parse_events_error__exit(&parse_error);
 	if (err == -ENODATA) {
 		pr_debug("Failed to add events selected by BPF, debuginfo package not installed\n");
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 83adb0c2a6bc..7c13b70e743c 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -499,7 +499,7 @@ int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
 
 #ifdef HAVE_LIBTRACEEVENT
 static void tracepoint_error(struct parse_events_error *e, int err,
-			     const char *sys, const char *name)
+			     const char *sys, const char *name, int column)
 {
 	const char *str;
 	char help[BUFSIZ];
@@ -526,18 +526,19 @@ static void tracepoint_error(struct parse_events_error *e, int err,
 	}
 
 	tracing_path__strerror_open_tp(err, help, sizeof(help), sys, name);
-	parse_events_error__handle(e, 0, strdup(str), strdup(help));
+	parse_events_error__handle(e, column, strdup(str), strdup(help));
 }
 
 static int add_tracepoint(struct list_head *list, int *idx,
 			  const char *sys_name, const char *evt_name,
 			  struct parse_events_error *err,
-			  struct list_head *head_config)
+			  struct list_head *head_config, void *loc_)
 {
+	YYLTYPE *loc = loc_;
 	struct evsel *evsel = evsel__newtp_idx(sys_name, evt_name, (*idx)++);
 
 	if (IS_ERR(evsel)) {
-		tracepoint_error(err, PTR_ERR(evsel), sys_name, evt_name);
+		tracepoint_error(err, PTR_ERR(evsel), sys_name, evt_name, loc->first_column);
 		return PTR_ERR(evsel);
 	}
 
@@ -556,7 +557,7 @@ static int add_tracepoint(struct list_head *list, int *idx,
 static int add_tracepoint_multi_event(struct list_head *list, int *idx,
 				      const char *sys_name, const char *evt_name,
 				      struct parse_events_error *err,
-				      struct list_head *head_config)
+				      struct list_head *head_config, YYLTYPE *loc)
 {
 	char *evt_path;
 	struct dirent *evt_ent;
@@ -565,13 +566,13 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx,
 
 	evt_path = get_events_file(sys_name);
 	if (!evt_path) {
-		tracepoint_error(err, errno, sys_name, evt_name);
+		tracepoint_error(err, errno, sys_name, evt_name, loc->first_column);
 		return -1;
 	}
 	evt_dir = opendir(evt_path);
 	if (!evt_dir) {
 		put_events_file(evt_path);
-		tracepoint_error(err, errno, sys_name, evt_name);
+		tracepoint_error(err, errno, sys_name, evt_name, loc->first_column);
 		return -1;
 	}
 
@@ -588,11 +589,11 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx,
 		found++;
 
 		ret = add_tracepoint(list, idx, sys_name, evt_ent->d_name,
-				     err, head_config);
+				     err, head_config, loc);
 	}
 
 	if (!found) {
-		tracepoint_error(err, ENOENT, sys_name, evt_name);
+		tracepoint_error(err, ENOENT, sys_name, evt_name, loc->first_column);
 		ret = -1;
 	}
 
@@ -604,19 +605,19 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx,
 static int add_tracepoint_event(struct list_head *list, int *idx,
 				const char *sys_name, const char *evt_name,
 				struct parse_events_error *err,
-				struct list_head *head_config)
+				struct list_head *head_config, YYLTYPE *loc)
 {
 	return strpbrk(evt_name, "*?") ?
-	       add_tracepoint_multi_event(list, idx, sys_name, evt_name,
-					  err, head_config) :
-	       add_tracepoint(list, idx, sys_name, evt_name,
-			      err, head_config);
+		add_tracepoint_multi_event(list, idx, sys_name, evt_name,
+					   err, head_config, loc) :
+		add_tracepoint(list, idx, sys_name, evt_name,
+			       err, head_config, loc);
 }
 
 static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
 				    const char *sys_name, const char *evt_name,
 				    struct parse_events_error *err,
-				    struct list_head *head_config)
+				    struct list_head *head_config, YYLTYPE *loc)
 {
 	struct dirent *events_ent;
 	DIR *events_dir;
@@ -624,7 +625,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
 
 	events_dir = tracing_events__opendir();
 	if (!events_dir) {
-		tracepoint_error(err, errno, sys_name, evt_name);
+		tracepoint_error(err, errno, sys_name, evt_name, loc->first_column);
 		return -1;
 	}
 
@@ -640,7 +641,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
 			continue;
 
 		ret = add_tracepoint_event(list, idx, events_ent->d_name,
-					   evt_name, err, head_config);
+					   evt_name, err, head_config, loc);
 	}
 
 	closedir(events_dir);
@@ -653,6 +654,7 @@ struct __add_bpf_event_param {
 	struct parse_events_state *parse_state;
 	struct list_head *list;
 	struct list_head *head_config;
+	YYLTYPE *loc;
 };
 
 static int add_bpf_event(const char *group, const char *event, int fd, struct bpf_object *obj,
@@ -679,7 +681,7 @@ static int add_bpf_event(const char *group, const char *event, int fd, struct bp
 
 	err = parse_events_add_tracepoint(&new_evsels, &parse_state->idx, group,
 					  event, parse_state->error,
-					  param->head_config);
+					  param->head_config, param->loc);
 	if (err) {
 		struct evsel *evsel, *tmp;
 
@@ -706,12 +708,14 @@ static int add_bpf_event(const char *group, const char *event, int fd, struct bp
 int parse_events_load_bpf_obj(struct parse_events_state *parse_state,
 			      struct list_head *list,
 			      struct bpf_object *obj,
-			      struct list_head *head_config)
+			      struct list_head *head_config,
+			      void *loc)
 {
 	int err;
 	char errbuf[BUFSIZ];
-	struct __add_bpf_event_param param = {parse_state, list, head_config};
+	struct __add_bpf_event_param param = {parse_state, list, head_config, loc};
 	static bool registered_unprobe_atexit = false;
+	YYLTYPE test_loc = {.first_column = -1};
 
 	if (IS_ERR(obj) || !obj) {
 		snprintf(errbuf, sizeof(errbuf),
@@ -742,6 +746,9 @@ int parse_events_load_bpf_obj(struct parse_events_state *parse_state,
 		goto errout;
 	}
 
+	if (!param.loc)
+		param.loc = &test_loc;
+
 	err = bpf__foreach_event(obj, add_bpf_event, &param);
 	if (err) {
 		snprintf(errbuf, sizeof(errbuf),
@@ -751,7 +758,7 @@ int parse_events_load_bpf_obj(struct parse_events_state *parse_state,
 
 	return 0;
 errout:
-	parse_events_error__handle(parse_state->error, 0,
+	parse_events_error__handle(parse_state->error, param.loc->first_column,
 				strdup(errbuf), strdup("(add -v to see detail)"));
 	return err;
 }
@@ -839,11 +846,13 @@ int parse_events_load_bpf(struct parse_events_state *parse_state,
 			  struct list_head *list,
 			  char *bpf_file_name,
 			  bool source,
-			  struct list_head *head_config)
+			  struct list_head *head_config,
+			  void *loc_)
 {
 	int err;
 	struct bpf_object *obj;
 	LIST_HEAD(obj_head_config);
+	YYLTYPE *loc = loc_;
 
 	if (head_config)
 		split_bpf_config_terms(head_config, &obj_head_config);
@@ -863,12 +872,12 @@ int parse_events_load_bpf(struct parse_events_state *parse_state,
 						   -err, errbuf,
 						   sizeof(errbuf));
 
-		parse_events_error__handle(parse_state->error, 0,
+		parse_events_error__handle(parse_state->error, loc->first_column,
 					strdup(errbuf), strdup("(add -v to see detail)"));
 		return err;
 	}
 
-	err = parse_events_load_bpf_obj(parse_state, list, obj, head_config);
+	err = parse_events_load_bpf_obj(parse_state, list, obj, head_config, loc);
 	if (err)
 		return err;
 	err = parse_events_config_bpf(parse_state, obj, &obj_head_config);
@@ -885,9 +894,12 @@ int parse_events_load_bpf(struct parse_events_state *parse_state,
 int parse_events_load_bpf_obj(struct parse_events_state *parse_state,
 			      struct list_head *list __maybe_unused,
 			      struct bpf_object *obj __maybe_unused,
-			      struct list_head *head_config __maybe_unused)
+			      struct list_head *head_config __maybe_unused,
+			      void *loc_)
 {
-	parse_events_error__handle(parse_state->error, 0,
+	YYLTYPE *loc = loc_;
+
+	parse_events_error__handle(parse_state->error, loc->first_column,
 				   strdup("BPF support is not compiled"),
 				   strdup("Make sure libbpf-devel is available at build time."));
 	return -ENOTSUP;
@@ -897,9 +909,12 @@ int parse_events_load_bpf(struct parse_events_state *parse_state,
 			  struct list_head *list __maybe_unused,
 			  char *bpf_file_name __maybe_unused,
 			  bool source __maybe_unused,
-			  struct list_head *head_config __maybe_unused)
+			  struct list_head *head_config __maybe_unused,
+			  void *loc_)
 {
-	parse_events_error__handle(parse_state->error, 0,
+	YYLTYPE *loc = loc_;
+
+	parse_events_error__handle(parse_state->error, loc->first_column,
 				   strdup("BPF support is not compiled"),
 				   strdup("Make sure libbpf-devel is available at build time."));
 	return -ENOTSUP;
@@ -1441,8 +1456,9 @@ static int get_config_chgs(struct perf_pmu *pmu, struct list_head *head_config,
 int parse_events_add_tracepoint(struct list_head *list, int *idx,
 				const char *sys, const char *event,
 				struct parse_events_error *err,
-				struct list_head *head_config)
+				struct list_head *head_config, void *loc_)
 {
+	YYLTYPE *loc = loc_;
 #ifdef HAVE_LIBTRACEEVENT
 	if (head_config) {
 		struct perf_event_attr attr;
@@ -1454,17 +1470,17 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx,
 
 	if (strpbrk(sys, "*?"))
 		return add_tracepoint_multi_sys(list, idx, sys, event,
-						err, head_config);
+						err, head_config, loc);
 	else
 		return add_tracepoint_event(list, idx, sys, event,
-					    err, head_config);
+					    err, head_config, loc);
 #else
 	(void)list;
 	(void)idx;
 	(void)sys;
 	(void)event;
 	(void)head_config;
-	parse_events_error__handle(err, 0, strdup("unsupported tracepoint"),
+	parse_events_error__handle(err, loc->first_column, strdup("unsupported tracepoint"),
 				strdup("libtraceevent is necessary for tracepoint support"));
 	return -1;
 #endif
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index b37e5ee193a8..cabbe70adb82 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -169,18 +169,20 @@ int parse_events_name(struct list_head *list, const char *name);
 int parse_events_add_tracepoint(struct list_head *list, int *idx,
 				const char *sys, const char *event,
 				struct parse_events_error *error,
-				struct list_head *head_config);
+				struct list_head *head_config, void *loc);
 int parse_events_load_bpf(struct parse_events_state *parse_state,
 			  struct list_head *list,
 			  char *bpf_file_name,
 			  bool source,
-			  struct list_head *head_config);
+			  struct list_head *head_config,
+			  void *loc);
 /* Provide this function for perf test */
 struct bpf_object;
 int parse_events_load_bpf_obj(struct parse_events_state *parse_state,
 			      struct list_head *list,
 			      struct bpf_object *obj,
-			      struct list_head *head_config);
+			      struct list_head *head_config,
+			      void *loc);
 int parse_events_add_numeric(struct parse_events_state *parse_state,
 			     struct list_head *list,
 			     u32 type, u64 config,
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index a636a7db6e6f..50f5b819de37 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -567,7 +567,7 @@ tracepoint_name opt_event_config
 		error->idx = @1.first_column;
 
 	err = parse_events_add_tracepoint(list, &parse_state->idx, $1.sys, $1.event,
-					error, $2);
+					error, $2, &@1);
 
 	parse_events_terms__delete($2);
 	free($1.sys);
@@ -640,7 +640,7 @@ PE_BPF_OBJECT opt_event_config
 	list = alloc_list();
 	if (!list)
 		YYNOMEM;
-	err = parse_events_load_bpf(parse_state, list, $1, false, $2);
+	err = parse_events_load_bpf(parse_state, list, $1, false, $2, &@1);
 	parse_events_terms__delete($2);
 	free($1);
 	if (err) {
@@ -658,7 +658,7 @@ PE_BPF_SOURCE opt_event_config
 	list = alloc_list();
 	if (!list)
 		YYNOMEM;
-	err = parse_events_load_bpf(_parse_state, list, $1, true, $2);
+	err = parse_events_load_bpf(_parse_state, list, $1, true, $2, &@1);
 	parse_events_terms__delete($2);
 	if (err) {
 		free(list);

From 81a4e31f8c4a50bc5c5f49a1e2e4a295edd57719 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 27 Jun 2023 11:10:29 -0700
Subject: [PATCH 0181/1189] perf parse-events: Improve location for add pmu

Improve the location for add PMU for cases when PMUs aren't found.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20230627181030.95608-13-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.c | 12 +++++++-----
 tools/perf/util/parse-events.h |  4 ++--
 tools/perf/util/parse-events.y |  8 ++++----
 3 files changed, 13 insertions(+), 11 deletions(-)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 7c13b70e743c..926d3ac97324 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1575,13 +1575,14 @@ static bool config_term_percore(struct list_head *config_terms)
 int parse_events_add_pmu(struct parse_events_state *parse_state,
 			 struct list_head *list, char *name,
 			 struct list_head *head_config,
-			 bool auto_merge_stats)
+			 bool auto_merge_stats, void *loc_)
 {
 	struct perf_event_attr attr;
 	struct perf_pmu_info info;
 	struct perf_pmu *pmu;
 	struct evsel *evsel;
 	struct parse_events_error *err = parse_state->error;
+	YYLTYPE *loc = loc_;
 	LIST_HEAD(config_terms);
 
 	pmu = parse_state->fake_pmu ?: perf_pmus__find(name);
@@ -1605,7 +1606,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 		if (asprintf(&err_str,
 				"Cannot find PMU `%s'. Missing kernel support?",
 				name) >= 0)
-			parse_events_error__handle(err, 0, err_str, NULL);
+			parse_events_error__handle(err, loc->first_column, err_str, NULL);
 		return -EINVAL;
 	}
 	if (head_config)
@@ -1691,12 +1692,13 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 
 int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 			       char *str, struct list_head *head,
-			       struct list_head **listp)
+			       struct list_head **listp, void *loc_)
 {
 	struct parse_events_term *term;
 	struct list_head *list = NULL;
 	struct list_head *orig_head = NULL;
 	struct perf_pmu *pmu = NULL;
+	YYLTYPE *loc = loc_;
 	int ok = 0;
 	char *config;
 
@@ -1743,7 +1745,7 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 				parse_events_copy_term_list(head, &orig_head);
 				if (!parse_events_add_pmu(parse_state, list,
 							  pmu->name, orig_head,
-							  auto_merge_stats)) {
+							  auto_merge_stats, loc)) {
 					pr_debug("%s -> %s/%s/\n", str,
 						 pmu->name, alias->str);
 					parse_state->wild_card_pmus = true;
@@ -1756,7 +1758,7 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 
 	if (parse_state->fake_pmu) {
 		if (!parse_events_add_pmu(parse_state, list, str, head,
-					  /*auto_merge_stats=*/true)) {
+					  /*auto_merge_stats=*/true, loc)) {
 			pr_debug("%s -> %s/%s/\n", str, "fake_pmu", str);
 			ok++;
 		}
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index cabbe70adb82..e59b33805886 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -202,7 +202,7 @@ int parse_events_add_breakpoint(struct parse_events_state *parse_state,
 int parse_events_add_pmu(struct parse_events_state *parse_state,
 			 struct list_head *list, char *name,
 			 struct list_head *head_config,
-			 bool auto_merge_stats);
+			bool auto_merge_stats, void *loc);
 
 struct evsel *parse_events__add_event(int idx, struct perf_event_attr *attr,
 				      const char *name, const char *metric_id,
@@ -211,7 +211,7 @@ struct evsel *parse_events__add_event(int idx, struct perf_event_attr *attr,
 int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 			       char *str,
 			       struct list_head *head_config,
-			       struct list_head **listp);
+			       struct list_head **listp, void *loc);
 
 int parse_events_copy_term_list(struct list_head *old,
 				 struct list_head **new);
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 50f5b819de37..844646752462 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -313,7 +313,7 @@ PE_NAME opt_pmu_config
 		YYNOMEM;
 	}
 	/* Attempt to add to list assuming $1 is a PMU name. */
-	if (parse_events_add_pmu(parse_state, list, $1, $2, /*auto_merge_stats=*/false)) {
+	if (parse_events_add_pmu(parse_state, list, $1, $2, /*auto_merge_stats=*/false, &@1)) {
 		struct perf_pmu *pmu = NULL;
 		int ok = 0;
 
@@ -341,7 +341,7 @@ PE_NAME opt_pmu_config
 					YYNOMEM;
 				}
 				if (!parse_events_add_pmu(parse_state, list, pmu->name, terms,
-							  auto_merge_stats)) {
+							  auto_merge_stats, &@1)) {
 					ok++;
 					parse_state->wild_card_pmus = true;
 				}
@@ -352,7 +352,7 @@ PE_NAME opt_pmu_config
 		if (!ok) {
 			/* Failure to add, assume $1 is an event name. */
 			zfree(&list);
-			ok = !parse_events_multi_pmu_add(parse_state, $1, $2, &list);
+			ok = !parse_events_multi_pmu_add(parse_state, $1, $2, &list, &@1);
 			$2 = NULL;
 		}
 		if (!ok) {
@@ -379,7 +379,7 @@ PE_NAME sep_dc
 	struct list_head *list;
 	int err;
 
-	err = parse_events_multi_pmu_add(_parse_state, $1, NULL, &list);
+	err = parse_events_multi_pmu_add(_parse_state, $1, NULL, &list, &@1);
 	if (err < 0) {
 		struct parse_events_state *parse_state = _parse_state;
 		struct parse_events_error *error = parse_state->error;

From 4c11adff675652759a0f0ad2194f4646b5463a42 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 27 Jun 2023 11:10:30 -0700
Subject: [PATCH 0182/1189] perf parse-events: Remove ABORT_ON

Prefer informative messages rather than none with ABORT_ON. Document
one failure mode and add an error message for another.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20230627181030.95608-14-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.y | 22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 844646752462..454577f7aff6 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -22,12 +22,6 @@
 
 void parse_events_error(YYLTYPE *loc, void *parse_state, void *scanner, char const *msg);
 
-#define ABORT_ON(val) \
-do { \
-	if (val) \
-		YYABORT; \
-} while (0)
-
 #define PE_ABORT(val) \
 do { \
 	if (val == -ENOMEM) \
@@ -618,7 +612,9 @@ PE_RAW opt_event_config
 		YYNOMEM;
 	errno = 0;
 	num = strtoull($1 + 1, NULL, 16);
-	ABORT_ON(errno);
+	/* Given the lexer will only give [a-fA-F0-9]+ a failure here should be impossible. */
+	if (errno)
+		YYABORT;
 	free($1);
 	err = parse_events_add_numeric(_parse_state, list, PERF_TYPE_RAW, num, $2,
 				       /*wildcard=*/false);
@@ -978,7 +974,17 @@ PE_VALUE PE_ARRAY_RANGE PE_VALUE
 {
 	struct parse_events_array array;
 
-	ABORT_ON($3 < $1);
+	if ($3 < $1) {
+		struct parse_events_state *parse_state = _parse_state;
+		struct parse_events_error *error = parse_state->error;
+		char *err_str;
+
+		if (asprintf(&err_str, "Expected '%ld' to be less-than '%ld'", $3, $1) < 0)
+			err_str = NULL;
+
+		parse_events_error__handle(error, @1.first_column, err_str, NULL);
+		YYABORT;
+	}
 	array.nr_ranges = 1;
 	array.ranges = malloc(sizeof(array.ranges[0]));
 	if (!array.ranges)

From f9dd531c5b82037f0f8f9ffc04ce0c09840fba2e Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 24 Jul 2023 17:19:28 -0700
Subject: [PATCH 0183/1189] perf symbols: Add kallsyms__get_symbol_start()

The kallsyms__get_symbol_start() to get any symbol address from
kallsyms.  The existing kallsyms__get_function_start() only allows text
symbols so create this to allow data symbols too.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230725001929.368041-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/event.c | 30 +++++++++++++++++++++++++++---
 tools/perf/util/event.h |  2 ++
 2 files changed, 29 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 4cbb092e0684..923c0fb15122 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -93,8 +93,8 @@ struct process_symbol_args {
 	u64	   start;
 };
 
-static int find_symbol_cb(void *arg, const char *name, char type,
-			  u64 start)
+static int find_func_symbol_cb(void *arg, const char *name, char type,
+			       u64 start)
 {
 	struct process_symbol_args *args = arg;
 
@@ -110,12 +110,36 @@ static int find_symbol_cb(void *arg, const char *name, char type,
 	return 1;
 }
 
+static int find_any_symbol_cb(void *arg, const char *name,
+			      char type __maybe_unused, u64 start)
+{
+	struct process_symbol_args *args = arg;
+
+	if (strcmp(name, args->name))
+		return 0;
+
+	args->start = start;
+	return 1;
+}
+
 int kallsyms__get_function_start(const char *kallsyms_filename,
 				 const char *symbol_name, u64 *addr)
 {
 	struct process_symbol_args args = { .name = symbol_name, };
 
-	if (kallsyms__parse(kallsyms_filename, &args, find_symbol_cb) <= 0)
+	if (kallsyms__parse(kallsyms_filename, &args, find_func_symbol_cb) <= 0)
+		return -1;
+
+	*addr = args.start;
+	return 0;
+}
+
+int kallsyms__get_symbol_start(const char *kallsyms_filename,
+			       const char *symbol_name, u64 *addr)
+{
+	struct process_symbol_args args = { .name = symbol_name, };
+
+	if (kallsyms__parse(kallsyms_filename, &args, find_any_symbol_cb) <= 0)
 		return -1;
 
 	*addr = args.start;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index de20e01c9d72..d8bcee2e9b93 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -360,6 +360,8 @@ size_t perf_event__fprintf(union perf_event *event, struct machine *machine, FIL
 
 int kallsyms__get_function_start(const char *kallsyms_filename,
 				 const char *symbol_name, u64 *addr);
+int kallsyms__get_symbol_start(const char *kallsyms_filename,
+			       const char *symbol_name, u64 *addr);
 
 void event_attr_init(struct perf_event_attr *attr);
 

From 69a87a32f5cd8b262cb2195b045f96c63aede734 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 24 Jul 2023 17:19:29 -0700
Subject: [PATCH 0184/1189] perf machine: Include data symbols in the kernel
 map

When 'perf record -d' is used, it needs data mmaps to symbolize global
data.  But it missed to collect kernel data maps so it cannot symbolize
them.  Instead of having a separate map, just increase the kernel map
size to include the data section.

Probably we can have a separate kernel map for data, but the current
code assumes a single kernel map.  So it'd require more changes in other
places and looks error-prone.  I decided not to go that way for now.

Also it seems the kernel module size already includes the data section.

For example, my system has the following.

  $ grep -e _stext -e _etext -e _edata /proc/kallsyms
  ffffffff99800000 T _stext
  ffffffff9a601ac8 T _etext
  ffffffff9b446a00 D _edata

Size of the text section is (0x9a601ac8 - 0x99800000 = 0xe01ac8) and
size including data section is (0x9b446a00 - 0x99800000 = 0x1c46a00).

Before:
  $ perf record -d true

  $ perf report -D | grep MMAP | head -1
  0 0 0x460 [0x60]: PERF_RECORD_MMAP -1/0: [0xffffffff99800000(0xe01ac8) @ 0xffffffff99800000]: x [kernel.kallsyms]_text
                                                               ^^^^^^^^
                                                                 here
After:
  $ perf report -D | grep MMAP | head -1
  0 0 0x460 [0x60]: PERF_RECORD_MMAP -1/0: [0xffffffff99800000(0x1c46a00) @ 0xffffffff99800000]: x [kernel.kallsyms]_text
                                                               ^^^^^^^^^

Instead of just replacing it to _edata, try _edata first and then fall
back to _etext just in case.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230725001929.368041-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/machine.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 4e62843d51b7..11de3ca8d4fa 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1216,7 +1216,9 @@ static int machine__get_running_kernel_start(struct machine *machine,
 
 	*start = addr;
 
-	err = kallsyms__get_function_start(filename, "_etext", &addr);
+	err = kallsyms__get_symbol_start(filename, "_edata", &addr);
+	if (err)
+		err = kallsyms__get_function_start(filename, "_etext", &addr);
 	if (!err)
 		*end = addr;
 

From 1e37201405590eac6491f9e677bd4064a92900e8 Mon Sep 17 00:00:00 2001
From: Xiu Jianfeng <xiujianfeng@huawei.com>
Date: Thu, 27 Jul 2023 10:50:01 +0000
Subject: [PATCH 0185/1189] perf doc: Fix typo in perf.data-file-format.txt

The 'it' should be 'is' here, fix it.

Signed-off-by: Xiu Jianfeng <xiujianfeng@huawei.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230727105001.261420-1-xiujianfeng@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf.data-file-format.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt
index 635ba043fd7d..010a4edcd384 100644
--- a/tools/perf/Documentation/perf.data-file-format.txt
+++ b/tools/perf/Documentation/perf.data-file-format.txt
@@ -43,7 +43,7 @@ struct perf_file_section {
 
 Flags section:
 
-For each of the optional features a perf_file_section it placed after the data
+For each of the optional features a perf_file_section is placed after the data
 section if the feature bit is set in the perf_header flags bitset. The
 respective perf_file_section points to the data of the additional header and
 defines its size.

From 1699d3efe111e33e275ca7d4163c8b1470ba79b3 Mon Sep 17 00:00:00 2001
From: Anup Sharma <anupnewsmail@gmail.com>
Date: Fri, 21 Jul 2023 23:22:28 +0530
Subject: [PATCH 0186/1189] perf scripts python: Add initial script file with
 usage information

Added necessary modules, including the Perf-Trace-Util
library, and defines the required functions and variables
for using perf script python. The perf_trace_context and
Core modules for tracing and processing events has been
also imported. Added usage information.

Signed-off-by: Anup Sharma <anupnewsmail@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/f2f1a62f1cc69f44a5414da46a26a4cf124d2744.1689961706.git.anupnewsmail@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/gecko.py | 31 ++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)
 create mode 100644 tools/perf/scripts/python/gecko.py

diff --git a/tools/perf/scripts/python/gecko.py b/tools/perf/scripts/python/gecko.py
new file mode 100644
index 000000000000..7a62c1b411d9
--- /dev/null
+++ b/tools/perf/scripts/python/gecko.py
@@ -0,0 +1,31 @@
+# firefox-gecko-converter.py - Convert perf record output to Firefox's gecko profile format
+# SPDX-License-Identifier: GPL-2.0
+#
+# The script converts perf.data to Gecko Profile Format,
+# which can be read by https://profiler.firefox.com/.
+#
+# Usage:
+#
+#     perf record -a -g -F 99 sleep 60
+#     perf script report gecko > output.json
+
+import os
+import sys
+from typing import Dict
+
+# Add the Perf-Trace-Util library to the Python path
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+
+# Uses perf script python interface to parse each
+# event and store the data in the thread builder.
+def process_event(param_dict: Dict) -> None:
+	pass
+
+# Trace_end runs at the end and will be used to aggregate
+# the data into the final json object and print it out to stdout.
+def trace_end() -> None:
+	pass

From 0a02e44cc2fe1657af1f2740cb9a1dcd8a9338cc Mon Sep 17 00:00:00 2001
From: Anup Sharma <anupnewsmail@gmail.com>
Date: Fri, 21 Jul 2023 23:22:56 +0530
Subject: [PATCH 0187/1189] perf scripts python: Extact necessary information
 from process event

The script takes in a sample event dictionary(param_dict) and retrieves
relevant data such as time stamp, PID, TID, and comm for each event.
Also start time is defined as a global variable as it need to be passed
to trace_end for gecko meta information field creation.

Signed-off-by: Anup Sharma <anupnewsmail@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/19910fefcfe4be03cd5c2aa3fec11d3f86c0381b.1689961706.git.anupnewsmail@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/gecko.py | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/tools/perf/scripts/python/gecko.py b/tools/perf/scripts/python/gecko.py
index 7a62c1b411d9..a02b1e04ff52 100644
--- a/tools/perf/scripts/python/gecko.py
+++ b/tools/perf/scripts/python/gecko.py
@@ -20,10 +20,22 @@ sys.path.append(os.environ['PERF_EXEC_PATH'] + \
 from perf_trace_context import *
 from Core import *
 
+# start_time is intialiazed only once for the all event traces.
+start_time = None
+
 # Uses perf script python interface to parse each
 # event and store the data in the thread builder.
 def process_event(param_dict: Dict) -> None:
-	pass
+	global start_time
+	global tid_to_thread
+	time_stamp = (param_dict['sample']['time'] // 1000) / 1000
+	pid = param_dict['sample']['pid']
+	tid = param_dict['sample']['tid']
+	comm = param_dict['comm']
+
+	# Start time is the time of the first sample
+	if not start_time:
+		start_time = time_stamp
 
 # Trace_end runs at the end and will be used to aggregate
 # the data into the final json object and print it out to stdout.

From 5aacd7f08a3276f4fad729a600d51a1cc5d5191a Mon Sep 17 00:00:00 2001
From: Anup Sharma <anupnewsmail@gmail.com>
Date: Fri, 21 Jul 2023 23:23:19 +0530
Subject: [PATCH 0188/1189] perf scripts python: Add classes and conversion
 functions

This commit introduces new classes and conversion functions to
facilitate the representation of Gecko profile information. The new
classes Frame, Stack, Sample, and Thread are added to handle specific
components of the profile data, also link to the origin docs has been
commented out.

Additionally, Inside the Thread class _to_json_dict() method has been
created that converts the current thread data into the corresponding
format expected by the GeckoThread JSON schema, as per the Gecko
profile format specification.

Signed-off-by: Anup Sharma <anupnewsmail@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/ab7b40bd32df7101a6f8b4a3aa41570b63b831ac.1689961706.git.anupnewsmail@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/gecko.py | 133 ++++++++++++++++++++++++++++-
 1 file changed, 132 insertions(+), 1 deletion(-)

diff --git a/tools/perf/scripts/python/gecko.py b/tools/perf/scripts/python/gecko.py
index a02b1e04ff52..2cd5cd6e31e3 100644
--- a/tools/perf/scripts/python/gecko.py
+++ b/tools/perf/scripts/python/gecko.py
@@ -11,7 +11,8 @@
 
 import os
 import sys
-from typing import Dict
+from dataclasses import dataclass, field
+from typing import List, Dict, Optional, NamedTuple, Set, Tuple, Any
 
 # Add the Perf-Trace-Util library to the Python path
 sys.path.append(os.environ['PERF_EXEC_PATH'] + \
@@ -20,9 +21,139 @@ sys.path.append(os.environ['PERF_EXEC_PATH'] + \
 from perf_trace_context import *
 from Core import *
 
+StringID = int
+StackID = int
+FrameID = int
+CategoryID = int
+Milliseconds = float
+
 # start_time is intialiazed only once for the all event traces.
 start_time = None
 
+# https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L156
+class Frame(NamedTuple):
+	string_id: StringID
+	relevantForJS: bool
+	innerWindowID: int
+	implementation: None
+	optimizations: None
+	line: None
+	column: None
+	category: CategoryID
+	subcategory: int
+
+# https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L216
+class Stack(NamedTuple):
+	prefix_id: Optional[StackID]
+	frame_id: FrameID
+
+# https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L90
+class Sample(NamedTuple):
+	stack_id: Optional[StackID]
+	time_ms: Milliseconds
+	responsiveness: int
+
+@dataclass
+class Thread:
+	"""A builder for a profile of the thread.
+
+	Attributes:
+		comm: Thread command-line (name).
+		pid: process ID of containing process.
+		tid: thread ID.
+		samples: Timeline of profile samples.
+		frameTable: interned stack frame ID -> stack frame.
+		stringTable: interned string ID -> string.
+		stringMap: interned string -> string ID.
+		stackTable: interned stack ID -> stack.
+		stackMap: (stack prefix ID, leaf stack frame ID) -> interned Stack ID.
+		frameMap: Stack Frame string -> interned Frame ID.
+		comm: str
+		pid: int
+		tid: int
+		samples: List[Sample] = field(default_factory=list)
+		frameTable: List[Frame] = field(default_factory=list)
+		stringTable: List[str] = field(default_factory=list)
+		stringMap: Dict[str, int] = field(default_factory=dict)
+		stackTable: List[Stack] = field(default_factory=list)
+		stackMap: Dict[Tuple[Optional[int], int], int] = field(default_factory=dict)
+		frameMap: Dict[str, int] = field(default_factory=dict)
+	"""
+	comm: str
+	pid: int
+	tid: int
+	samples: List[Sample] = field(default_factory=list)
+	frameTable: List[Frame] = field(default_factory=list)
+	stringTable: List[str] = field(default_factory=list)
+	stringMap: Dict[str, int] = field(default_factory=dict)
+	stackTable: List[Stack] = field(default_factory=list)
+	stackMap: Dict[Tuple[Optional[int], int], int] = field(default_factory=dict)
+	frameMap: Dict[str, int] = field(default_factory=dict)
+
+	def _to_json_dict(self) -> Dict:
+		"""Converts current Thread to GeckoThread JSON format."""
+		# Gecko profile format is row-oriented data as List[List],
+		# And a schema for interpreting each index.
+		# Schema:
+		# https://github.com/firefox-devtools/profiler/blob/main/docs-developer/gecko-profile-format.md
+		# https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L230
+		return {
+			"tid": self.tid,
+			"pid": self.pid,
+			"name": self.comm,
+			# https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L51
+			"markers": {
+				"schema": {
+					"name": 0,
+					"startTime": 1,
+					"endTime": 2,
+					"phase": 3,
+					"category": 4,
+					"data": 5,
+				},
+				"data": [],
+			},
+
+			# https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L90
+			"samples": {
+				"schema": {
+					"stack": 0,
+					"time": 1,
+					"responsiveness": 2,
+				},
+				"data": self.samples
+			},
+
+			# https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L156
+			"frameTable": {
+				"schema": {
+					"location": 0,
+					"relevantForJS": 1,
+					"innerWindowID": 2,
+					"implementation": 3,
+					"optimizations": 4,
+					"line": 5,
+					"column": 6,
+					"category": 7,
+					"subcategory": 8,
+				},
+				"data": self.frameTable,
+			},
+
+			# https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L216
+			"stackTable": {
+				"schema": {
+					"prefix": 0,
+					"frame": 1,
+				},
+				"data": self.stackTable,
+			},
+			"stringTable": self.stringTable,
+			"registerTime": 0,
+			"unregisterTime": None,
+			"processType": "default",
+		}
+
 # Uses perf script python interface to parse each
 # event and store the data in the thread builder.
 def process_event(param_dict: Dict) -> None:

From 833daec7e6cfda0d6c30a94c21b6706ff094cd45 Mon Sep 17 00:00:00 2001
From: Anup Sharma <anupnewsmail@gmail.com>
Date: Fri, 21 Jul 2023 23:24:42 +0530
Subject: [PATCH 0189/1189] perf scripts python: Add trace end processing and
 PRODUCT and CATEGORIES information

The final output will now be presented in JSON format following the Gecko
profile structure. Additionally, the inclusion of PRODUCT allows easy retrieval
of header information for UI.

Furthermore, CATEGORIES have been introduced to enable customization of
kernel and user colors using input arguments. To facilitate this functionality,
an argparse-based parser has been implemented.

Note: The implementation of threads will be addressed in subsequent commits
for now I have commented it out.

Signed-off-by: Anup Sharma <anupnewsmail@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/fa6d027e4134c48e8a2ea45dd8f6b21e6a3418e4.1689961706.git.anupnewsmail@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/gecko.py | 65 +++++++++++++++++++++++++++++-
 1 file changed, 64 insertions(+), 1 deletion(-)

diff --git a/tools/perf/scripts/python/gecko.py b/tools/perf/scripts/python/gecko.py
index 2cd5cd6e31e3..794a91bec464 100644
--- a/tools/perf/scripts/python/gecko.py
+++ b/tools/perf/scripts/python/gecko.py
@@ -11,6 +11,8 @@
 
 import os
 import sys
+import json
+import argparse
 from dataclasses import dataclass, field
 from typing import List, Dict, Optional, NamedTuple, Set, Tuple, Any
 
@@ -30,6 +32,13 @@ Milliseconds = float
 # start_time is intialiazed only once for the all event traces.
 start_time = None
 
+# https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/profile.js#L425
+# Follow Brendan Gregg's Flamegraph convention: orange for kernel and yellow for user space by default.
+CATEGORIES = None
+
+# The product name is used by the profiler UI to show the Operating system and Processor.
+PRODUCT = os.popen('uname -op').read().strip()
+
 # https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L156
 class Frame(NamedTuple):
 	string_id: StringID
@@ -171,4 +180,58 @@ def process_event(param_dict: Dict) -> None:
 # Trace_end runs at the end and will be used to aggregate
 # the data into the final json object and print it out to stdout.
 def trace_end() -> None:
-	pass
+	# Schema: https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L305
+	gecko_profile_with_meta = {
+		"meta": {
+			"interval": 1,
+			"processType": 0,
+			"product": PRODUCT,
+			"stackwalk": 1,
+			"debug": 0,
+			"gcpoison": 0,
+			"asyncstack": 1,
+			"startTime": start_time,
+			"shutdownTime": None,
+			"version": 24,
+			"presymbolicated": True,
+			"categories": CATEGORIES,
+			"markerSchema": [],
+			},
+		"libs": [],
+		# threads will be implemented in later commits.
+		# "threads": threads,
+		"processes": [],
+		"pausedRanges": [],
+	}
+	json.dump(gecko_profile_with_meta, sys.stdout, indent=2)
+
+def main() -> None:
+	global CATEGORIES
+	parser = argparse.ArgumentParser(description="Convert perf.data to Firefox\'s Gecko Profile format")
+
+	# Add the command-line options
+	# Colors must be defined according to this:
+	# https://github.com/firefox-devtools/profiler/blob/50124adbfa488adba6e2674a8f2618cf34b59cd2/res/css/categories.css
+	parser.add_argument('--user-color', default='yellow', help='Color for the User category')
+	parser.add_argument('--kernel-color', default='orange', help='Color for the Kernel category')
+	# Parse the command-line arguments
+	args = parser.parse_args()
+	# Access the values provided by the user
+	user_color = args.user_color
+	kernel_color = args.kernel_color
+
+	CATEGORIES = [
+		{
+			"name": 'User',
+			"color": user_color,
+			"subcategories": ['Other']
+		},
+		{
+			"name": 'Kernel',
+			"color": kernel_color,
+			"subcategories": ['Other']
+		},
+	]
+
+if __name__ == '__main__':
+    main()

From 258dfd41c1df2030772ceab378f7bd6f0f78b938 Mon Sep 17 00:00:00 2001
From: Anup Sharma <anupnewsmail@gmail.com>
Date: Fri, 21 Jul 2023 23:25:38 +0530
Subject: [PATCH 0190/1189] perf scripts python: Implement add sample function
 and thread processing

The intern_stack function is responsible for retrieving
or creating a stack_id based on the provided frame_id and prefix_id.
It first generates a key using the frame_id and prefix_id values.
If the stack corresponding to the key is found in the stackMap,
it is returned. Otherwise, a new stack is created by appending
the prefix_id and frame_id to the stackTable. The key
and the index of the newly created stack are added to the
stackMap for future reference.

The _intern_frame function is responsible for retrieving or
creating a frame_id based on the provided frame string. If the frame_id
corresponding to the frameString is found in the frameMap, it is
returned. Otherwise, a new frame is created by appending relevant
information to the frameTable and adding the frameString to the string_id
through _intern_string.

The _intern_string function will gets a matching string, or saves the new
string and returns a String ID.

Signed-off-by: Anup Sharma <anupnewsmail@gmail.com>
Link: https://lore.kernel.org/r/4442f4b1ab4c7317cf940560a3a285fcdfbeeb08.1689961706.git.anupnewsmail@gmail.com
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: linux-kernel@vger.kernel.org
Cc: linux-perf-users@vger.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/gecko.py | 54 ++++++++++++++++++++++++++++++
 1 file changed, 54 insertions(+)

diff --git a/tools/perf/scripts/python/gecko.py b/tools/perf/scripts/python/gecko.py
index 794a91bec464..97949249a3c0 100644
--- a/tools/perf/scripts/python/gecko.py
+++ b/tools/perf/scripts/python/gecko.py
@@ -13,6 +13,7 @@ import os
 import sys
 import json
 import argparse
+from functools import reduce
 from dataclasses import dataclass, field
 from typing import List, Dict, Optional, NamedTuple, Set, Tuple, Any
 
@@ -39,6 +40,10 @@ CATEGORIES = None
 # The product name is used by the profiler UI to show the Operating system and Processor.
 PRODUCT = os.popen('uname -op').read().strip()
 
+# The category index is used by the profiler UI to show the color of the flame graph.
+USER_CATEGORY_INDEX = 0
+KERNEL_CATEGORY_INDEX = 1
+
 # https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L156
 class Frame(NamedTuple):
 	string_id: StringID
@@ -99,6 +104,55 @@ class Thread:
 	stackMap: Dict[Tuple[Optional[int], int], int] = field(default_factory=dict)
 	frameMap: Dict[str, int] = field(default_factory=dict)
 
+	def _intern_stack(self, frame_id: int, prefix_id: Optional[int]) -> int:
+		"""Gets a matching stack, or saves the new stack. Returns a Stack ID."""
+		key = f"{frame_id}" if prefix_id is None else f"{frame_id},{prefix_id}"
+		# key = (prefix_id, frame_id)
+		stack_id = self.stackMap.get(key)
+		if stack_id is None:
+			# return stack_id
+			stack_id = len(self.stackTable)
+			self.stackTable.append(Stack(prefix_id=prefix_id, frame_id=frame_id))
+			self.stackMap[key] = stack_id
+		return stack_id
+
+	def _intern_string(self, string: str) -> int:
+		"""Gets a matching string, or saves the new string. Returns a String ID."""
+		string_id = self.stringMap.get(string)
+		if string_id is not None:
+			return string_id
+		string_id = len(self.stringTable)
+		self.stringTable.append(string)
+		self.stringMap[string] = string_id
+		return string_id
+
+	def _intern_frame(self, frame_str: str) -> int:
+		"""Gets a matching stack frame, or saves the new frame. Returns a Frame ID."""
+		frame_id = self.frameMap.get(frame_str)
+		if frame_id is not None:
+			return frame_id
+		frame_id = len(self.frameTable)
+		self.frameMap[frame_str] = frame_id
+		string_id = self._intern_string(frame_str)
+
+		symbol_name_to_category = KERNEL_CATEGORY_INDEX if frame_str.find('kallsyms') != -1 \
+		or frame_str.find('/vmlinux') != -1 \
+		or frame_str.endswith('.ko)') \
+		else USER_CATEGORY_INDEX
+
+		self.frameTable.append(Frame(
+			string_id=string_id,
+			relevantForJS=False,
+			innerWindowID=0,
+			implementation=None,
+			optimizations=None,
+			line=None,
+			column=None,
+			category=symbol_name_to_category,
+			subcategory=None,
+		))
+		return frame_id
+
 	def _to_json_dict(self) -> Dict:
 		"""Converts current Thread to GeckoThread JSON format."""
 		# Gecko profile format is row-oriented data as List[List],

From 2d889c6af1cc125380b03b6efdaed0a4b4611aed Mon Sep 17 00:00:00 2001
From: Anup Sharma <anupnewsmail@gmail.com>
Date: Fri, 21 Jul 2023 23:26:24 +0530
Subject: [PATCH 0191/1189] perf scripts python: Implement add sample function
 and thread processing

The stack has been created for storing func and dso from the callchain.
The sample has been added to a specific thread. It first checks if the
thread exists in the Thread class. Then it call _add_sample function
which is responsible for appending a new entry to the samples list.

Also callchain parsing and storing part is implemented. Moreover removed
the comment from thread.

Signed-off-by: Anup Sharma <anupnewsmail@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/5a112be85ccdcdcd611e343f6a7a7482d01f6299.1689961706.git.anupnewsmail@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/gecko.py | 52 ++++++++++++++++++++++++++++--
 1 file changed, 50 insertions(+), 2 deletions(-)

diff --git a/tools/perf/scripts/python/gecko.py b/tools/perf/scripts/python/gecko.py
index 97949249a3c0..278c3aed282a 100644
--- a/tools/perf/scripts/python/gecko.py
+++ b/tools/perf/scripts/python/gecko.py
@@ -40,6 +40,9 @@ CATEGORIES = None
 # The product name is used by the profiler UI to show the Operating system and Processor.
 PRODUCT = os.popen('uname -op').read().strip()
 
+# Here key = tid, value = Thread
+tid_to_thread = dict()
+
 # The category index is used by the profiler UI to show the color of the flame graph.
 USER_CATEGORY_INDEX = 0
 KERNEL_CATEGORY_INDEX = 1
@@ -153,6 +156,25 @@ class Thread:
 		))
 		return frame_id
 
+	def _add_sample(self, comm: str, stack: List[str], time_ms: Milliseconds) -> None:
+		"""Add a timestamped stack trace sample to the thread builder.
+		Args:
+			comm: command-line (name) of the thread at this sample
+			stack: sampled stack frames. Root first, leaf last.
+			time_ms: timestamp of sample in milliseconds.
+		"""
+		# Ihreads may not set their names right after they are created.
+		# Instead, they might do it later. In such situations, to use the latest name they have set.
+		if self.comm != comm:
+			self.comm = comm
+
+		prefix_stack_id = reduce(lambda prefix_id, frame: self._intern_stack
+						(self._intern_frame(frame), prefix_id), stack, None)
+		if prefix_stack_id is not None:
+			self.samples.append(Sample(stack_id=prefix_stack_id,
+									time_ms=time_ms,
+									responsiveness=0))
+
 	def _to_json_dict(self) -> Dict:
 		"""Converts current Thread to GeckoThread JSON format."""
 		# Gecko profile format is row-oriented data as List[List],
@@ -231,9 +253,36 @@ def process_event(param_dict: Dict) -> None:
 	if not start_time:
 		start_time = time_stamp
 
+	# Parse and append the callchain of the current sample into a stack.
+	stack = []
+	if param_dict['callchain']:
+		for call in param_dict['callchain']:
+			if 'sym' not in call:
+				continue
+			stack.append(f'{call["sym"]["name"]} (in {call["dso"]})')
+		if len(stack) != 0:
+			# Reverse the stack, as root come first and the leaf at the end.
+			stack = stack[::-1]
+
+	# During perf record if -g is not used, the callchain is not available.
+	# In that case, the symbol and dso are available in the event parameters.
+	else:
+		func = param_dict['symbol'] if 'symbol' in param_dict else '[unknown]'
+		dso = param_dict['dso'] if 'dso' in param_dict else '[unknown]'
+		stack.append(f'{func} (in {dso})')
+
+	# Add sample to the specific thread.
+	thread = tid_to_thread.get(tid)
+	if thread is None:
+		thread = Thread(comm=comm, pid=pid, tid=tid)
+		tid_to_thread[tid] = thread
+	thread._add_sample(comm=comm, stack=stack, time_ms=time_stamp)
+
 # Trace_end runs at the end and will be used to aggregate
 # the data into the final json object and print it out to stdout.
 def trace_end() -> None:
+	threads = [thread._to_json_dict() for thread in tid_to_thread.values()]
+
 	# Schema: https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L305
 	gecko_profile_with_meta = {
 		"meta": {
@@ -252,8 +301,7 @@ def trace_end() -> None:
 			"markerSchema": [],
 			},
 		"libs": [],
-		# threads will be implemented in later commits.
-		# "threads": threads,
+		"threads": threads,
 		"processes": [],
 		"pausedRanges": [],
 	}

From f9f72b2ab77e986ac30de09a735a002b37d81503 Mon Sep 17 00:00:00 2001
From: Anup Sharma <anupnewsmail@gmail.com>
Date: Fri, 21 Jul 2023 23:27:46 +0530
Subject: [PATCH 0192/1189] perf scripts python: Add command execution for
 gecko script

This will enable the execution of gecko.py script using record and
report commands in 'perf script'.  And this will be also reflected at
"perf script -l" command.

For Example:
    perf script record gecko
    perf script report gecko

Committer notes:

As discussed on the perf tools office hours, I made -F 99 the default
for the record script and removed the double -- on the report script so
that the existing 'perf script' protocol for the combined operation:

    # perf script gecko

Works, i.e. the record script pipes its stdout into the stdin of the
report script, basically:

  /bin/sh /usr/libexec/perf-core/scripts/python/bin/gecko-record -F 99 -g -a -q -o - | \
  /bin/sh /usr/libexec/perf-core/scripts/python/bin/gecko-report -i -

Testing it:

The resulting JSON file needs to be uploaded to
https://profiler.firefox.com, Anup already has code to start a local
http server on the trace_begin handler of the gecko python script, start
firefox and feed it the JSON.

The example below only collects sample for the specified workload, so
that we don't produce thousands of lines, to collect system wide
samples, use instead:

  # perf script gecko -a sleep 0.5

  # nohup perf script gecko sleep 0.5
  {
    "meta": {
      "interval": 1,
      "processType": 0,
      "product": "x86_64 GNU/Linux",
      "stackwalk": 1,
      "debug": 0,
      "gcpoison": 0,
      "asyncstack": 1,
      "startTime": 274601692.636,
      "shutdownTime": null,
      "version": 24,
      "presymbolicated": true,
      "categories": [
        {
          "name": "User",
          "color": "yellow",
          "subcategories": [
            "Other"
          ]
        },
        {
          "name": "Kernel",
          "color": "orange",
          "subcategories": [
            "Other"
          ]
        }
      ],
      "markerSchema": []
    },
    "libs": [],
    "threads": [
      {
        "tid": 3344498,
        "pid": 3344498,
        "name": "sleep",
        "markers": {
          "schema": {
            "name": 0,
            "startTime": 1,
            "endTime": 2,
            "phase": 3,
            "category": 4,
            "data": 5
          },
          "data": []
        },
        "samples": {
          "schema": {
            "stack": 0,
            "time": 1,
            "responsiveness": 2
          },
          "data": [
            [
              21,
              274601692.636,
              0
            ],
            [
              23,
              274601692.641,
              0
            ],
            [
              29,
              274601692.643,
              0
            ],
            [
              42,
              274601692.648,
              0
            ]
          ]
        },
        "frameTable": {
          "schema": {
            "location": 0,
            "relevantForJS": 1,
            "innerWindowID": 2,
            "implementation": 3,
            "optimizations": 4,
            "line": 5,
            "column": 6,
            "category": 7,
            "subcategory": 8
          },
          "data": [
            [
              0,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              1,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              2,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              3,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              4,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              5,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              6,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              7,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              8,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              9,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              10,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              11,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              12,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              13,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              14,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              15,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              16,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              17,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              18,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              19,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              20,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              21,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              22,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              23,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              24,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              25,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              26,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              27,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              28,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              29,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              30,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              31,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              32,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              33,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              34,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              35,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              36,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              37,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ],
            [
              38,
              false,
              0,
              null,
              null,
              null,
              null,
              1,
              null
            ]
          ]
        },
        "stackTable": {
          "schema": {
            "prefix": 0,
            "frame": 1
          },
          "data": [
            [
              null,
              0
            ],
            [
              0,
              1
            ],
            [
              1,
              2
            ],
            [
              2,
              3
            ],
            [
              3,
              4
            ],
            [
              4,
              5
            ],
            [
              5,
              6
            ],
            [
              6,
              7
            ],
            [
              7,
              8
            ],
            [
              8,
              9
            ],
            [
              9,
              10
            ],
            [
              10,
              11
            ],
            [
              11,
              12
            ],
            [
              12,
              13
            ],
            [
              13,
              14
            ],
            [
              14,
              15
            ],
            [
              15,
              16
            ],
            [
              16,
              17
            ],
            [
              17,
              18
            ],
            [
              18,
              19
            ],
            [
              19,
              20
            ],
            [
              20,
              21
            ],
            [
              20,
              22
            ],
            [
              22,
              23
            ],
            [
              11,
              24
            ],
            [
              24,
              25
            ],
            [
              25,
              26
            ],
            [
              26,
              27
            ],
            [
              27,
              28
            ],
            [
              28,
              29
            ],
            [
              9,
              11
            ],
            [
              30,
              24
            ],
            [
              31,
              25
            ],
            [
              32,
              30
            ],
            [
              33,
              31
            ],
            [
              34,
              32
            ],
            [
              35,
              29
            ],
            [
              36,
              33
            ],
            [
              37,
              34
            ],
            [
              38,
              35
            ],
            [
              39,
              36
            ],
            [
              40,
              37
            ],
            [
              41,
              38
            ]
          ]
        },
        "stringTable": [
          "__func__.0 (in [kernel.kallsyms].rodata)",
          "perf_trace_ext4_fc_track_inode (in [kernel.kallsyms])",
          "perf_trace_ext4_es_insert_delayed_block (in [kernel.kallsyms])",
          "ext4_es_show_pblock (in [kernel.kallsyms])",
          "perf_trace_ext4_ext_rm_leaf (in [kernel.kallsyms])",
          "devcgroup_access_write (in [kernel.kallsyms])",
          "devcgroup_update_access (in [kernel.kallsyms])",
          "propagate_exception (in [kernel.kallsyms])",
          "revalidate_active_exceptions (in [kernel.kallsyms])",
          "perf_trace_ext4_fc_commit_stop (in [kernel.kallsyms])",
          "perf_fetch_caller_regs (in [kernel.kallsyms])",
          "khugepaged (in [kernel.kallsyms])",
          "khugepaged_wait_work (in [kernel.kallsyms])",
          "freezable_schedule_timeout (in [kernel.kallsyms])",
          "freezer_count (in [kernel.kallsyms])",
          "try_to_freeze (in [kernel.kallsyms])",
          "try_to_freeze_unsafe (in [kernel.kallsyms])",
          "split_huge_pages_write (in [kernel.kallsyms])",
          "migrate_pages (in [kernel.kallsyms])",
          "unmap_and_move (in [kernel.kallsyms])",
          "__unmap_and_move (in [kernel.kallsyms])",
          "collect_events (in [kernel.kallsyms])",
          "uncore_down_prepare (in [kernel.kallsyms])",
          "perf_iommu_read (in [kernel.kallsyms])",
          "khugepaged_do_scan (in [kernel.kallsyms])",
          "khugepaged_scan_mm_slot (in [kernel.kallsyms])",
          "khugepaged_scan_file (in [kernel.kallsyms])",
          "need_resched (in [kernel.kallsyms])",
          "get_current (in [kernel.kallsyms])",
          "move_to_new_page (in [kernel.kallsyms])",
          "khugepaged_scan_pmd (in [kernel.kallsyms])",
          "trace_mm_khugepaged_scan_pmd (in [kernel.kallsyms])",
          "migrate_huge_page_move_mapping (in [kernel.kallsyms])",
          "do_huge_pmd_numa_page (in [kernel.kallsyms])",
          "pmd_pfn (in [kernel.kallsyms])",
          "protnone_mask (in [kernel.kallsyms])",
          "__pte_needs_invert (in [kernel.kallsyms])",
          "reclaim_high (in [kernel.kallsyms])",
          "memcg_memory_event (in [kernel.kallsyms])"
        ],
        "registerTime": 0,
        "unregisterTime": null,
        "processType": "default"
      }
    ],
    "processes": [],
    "pausedRanges": []
  }
  #

Signed-off-by: Anup Sharma <anupnewsmail@gmail.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/cbf03cda175ea3dd2c6cd87bd3f12d803446cb95.1689961706.git.anupnewsmail@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/bin/gecko-record | 2 ++
 tools/perf/scripts/python/bin/gecko-report | 3 +++
 2 files changed, 5 insertions(+)
 create mode 100644 tools/perf/scripts/python/bin/gecko-record
 create mode 100644 tools/perf/scripts/python/bin/gecko-report

diff --git a/tools/perf/scripts/python/bin/gecko-record b/tools/perf/scripts/python/bin/gecko-record
new file mode 100644
index 000000000000..f0d1aa55f171
--- /dev/null
+++ b/tools/perf/scripts/python/bin/gecko-record
@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -F 99 -g "$@"
diff --git a/tools/perf/scripts/python/bin/gecko-report b/tools/perf/scripts/python/bin/gecko-report
new file mode 100644
index 000000000000..0c12cc08f3ab
--- /dev/null
+++ b/tools/perf/scripts/python/bin/gecko-report
@@ -0,0 +1,3 @@
+#!/bin/bash
+# description: create firefox gecko profile json format from perf.data
+perf script "$@" -s "$PERF_EXEC_PATH"/scripts/python/gecko.py

From 404e077a16bb7796908b604b2df02cd650c965aa Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@arm.com>
Date: Wed, 28 Jun 2023 11:53:02 +0100
Subject: [PATCH 0193/1189] perf tools: Add a place to put kernel config
 fragments for test runs

Defconfig doesn't give full coverage for a perf test run, so these can
be merged with defconfig to do so. It's not complete yet, but is a
starting point as a place to add to when a specific test needs something
extra to run.

Signed-off-by: James Clark <james.clark@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Aishwarya.TCV@arm.com
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Brown <broonie@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230628105303.4053478-2-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/config-fragments/README |  7 +++++++
 tools/perf/tests/config-fragments/arm64  |  1 +
 tools/perf/tests/config-fragments/config | 11 +++++++++++
 3 files changed, 19 insertions(+)
 create mode 100644 tools/perf/tests/config-fragments/README
 create mode 100644 tools/perf/tests/config-fragments/arm64
 create mode 100644 tools/perf/tests/config-fragments/config

diff --git a/tools/perf/tests/config-fragments/README b/tools/perf/tests/config-fragments/README
new file mode 100644
index 000000000000..fe7de5d93674
--- /dev/null
+++ b/tools/perf/tests/config-fragments/README
@@ -0,0 +1,7 @@
+This folder is for kernel config fragments that can be merged with
+defconfig to give full test coverage of a perf test run. This is only
+an optimistic set as some features require hardware support in order to
+pass and not skip.
+
+'config' is shared across all platforms, and for arch specific files,
+the file name should match that used in the ARCH=... make option.
diff --git a/tools/perf/tests/config-fragments/arm64 b/tools/perf/tests/config-fragments/arm64
new file mode 100644
index 000000000000..64c4ab17cd58
--- /dev/null
+++ b/tools/perf/tests/config-fragments/arm64
@@ -0,0 +1 @@
+CONFIG_CORESIGHT_SOURCE_ETM4X=y
diff --git a/tools/perf/tests/config-fragments/config b/tools/perf/tests/config-fragments/config
new file mode 100644
index 000000000000..c340b3195fca
--- /dev/null
+++ b/tools/perf/tests/config-fragments/config
@@ -0,0 +1,11 @@
+CONFIG_TRACEPOINTS=y
+CONFIG_STACKTRACE=y
+CONFIG_NOP_TRACER=y
+CONFIG_RING_BUFFER=y
+CONFIG_EVENT_TRACING=y
+CONFIG_CONTEXT_SWITCH_TRACER=y
+CONFIG_TRACING=y
+CONFIG_GENERIC_TRACER=y
+CONFIG_FTRACE=y
+CONFIG_FTRACE_SYSCALLS=y
+CONFIG_BRANCH_PROFILE_NONE=y

From 24069d8112c94e76758da83a5bddc9aa98601d22 Mon Sep 17 00:00:00 2001
From: Jing Zhang <renyu.zj@linux.alibaba.com>
Date: Fri, 28 Jul 2023 15:09:33 +0800
Subject: [PATCH 0194/1189] perf jevents: Add support for Yitian 710 DDR PMU
 (arm64) aliasing

Add alias support for T-HEAD Yitian 710 SoC DDR PMU events.

Reviewed-by: John Garry <john.g.garry@oracle.com>
Reviewed-by: Shuai Xue <xueshuai@linux.alibaba.com>
Signed-off-by: Jing Zhang <renyu.zj@linux.alibaba.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: Zhuo Song <zhuo.song@linux.alibaba.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-doc@vger.kernel.org
Link: https://lore.kernel.org/r/1690528175-2499-2-git-send-email-renyu.zj@linux.alibaba.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../freescale/yitian710/sys/ali_drw.json      | 373 ++++++++++++++++++
 tools/perf/pmu-events/jevents.py              |   1 +
 2 files changed, 374 insertions(+)
 create mode 100644 tools/perf/pmu-events/arch/arm64/freescale/yitian710/sys/ali_drw.json

diff --git a/tools/perf/pmu-events/arch/arm64/freescale/yitian710/sys/ali_drw.json b/tools/perf/pmu-events/arch/arm64/freescale/yitian710/sys/ali_drw.json
new file mode 100644
index 000000000000..e21c469a8ef0
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/freescale/yitian710/sys/ali_drw.json
@@ -0,0 +1,373 @@
+[
+	{
+		"BriefDescription": "A Write or Read Op at HIF interface. The unit is 64B.",
+		"ConfigCode": "0x0",
+		"EventName": "hif_rd_or_wr",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A Write Op at HIF interface. The unit is 64B.",
+		"ConfigCode": "0x1",
+		"EventName": "hif_wr",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A Read Op at HIF interface. The unit is 64B.",
+		"ConfigCode": "0x2",
+		"EventName": "hif_rd",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A Read-Modify-Write Op at HIF interface. The unit is 64B.",
+		"ConfigCode": "0x3",
+		"EventName": "hif_rmw",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A high priority Read at HIF interface. The unit is 64B.",
+		"ConfigCode": "0x4",
+		"EventName": "hif_hi_pri_rd",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A write data cycle at DFI interface (to DRAM).",
+		"ConfigCode": "0x7",
+		"EventName": "dfi_wr_data_cycles",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A read data cycle at DFI interface (to DRAM).",
+		"ConfigCode": "0x8",
+		"EventName": "dfi_rd_data_cycles",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A high priority read becomes critical.",
+		"ConfigCode": "0x9",
+		"EventName": "hpr_xact_when_critical",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A low priority read becomes critical.",
+		"ConfigCode": "0xA",
+		"EventName": "lpr_xact_when_critical",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A write becomes critical.",
+		"ConfigCode": "0xB",
+		"EventName": "wr_xact_when_critical",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "An Activate(ACT) command to DRAM.",
+		"ConfigCode": "0xC",
+		"EventName": "op_is_activate",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A Read or Write CAS command to DRAM.",
+		"ConfigCode": "0xD",
+		"EventName": "op_is_rd_or_wr",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "An Activate(ACT) command for read to DRAM.",
+		"ConfigCode": "0xE",
+		"EventName": "op_is_rd_activate",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A Read CAS command to DRAM.",
+		"ConfigCode": "0xF",
+		"EventName": "op_is_rd",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A Write CAS command to DRAM.",
+		"ConfigCode": "0x10",
+		"EventName": "op_is_wr",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A Masked Write command to DRAM.",
+		"ConfigCode": "0x11",
+		"EventName": "op_is_mwr",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A Precharge(PRE) command to DRAM.",
+		"ConfigCode": "0x12",
+		"EventName": "op_is_precharge",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A Precharge(PRE) required by read or write.",
+		"ConfigCode": "0x13",
+		"EventName": "precharge_for_rdwr",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A Precharge(PRE) required by other conditions.",
+		"ConfigCode": "0x14",
+		"EventName": "precharge_for_other",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A read-write turnaround.",
+		"ConfigCode": "0x15",
+		"EventName": "rdwr_transitions",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A write combine(merge) in write data buffer.",
+		"ConfigCode": "0x16",
+		"EventName": "write_combine",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A Write-After-Read hazard.",
+		"ConfigCode": "0x17",
+		"EventName": "war_hazard",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A Read-After-Write hazard.",
+		"ConfigCode": "0x18",
+		"EventName": "raw_hazard",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A Write-After-Write hazard.",
+		"ConfigCode": "0x19",
+		"EventName": "waw_hazard",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "Rank0 enters self-refresh(SRE).",
+		"ConfigCode": "0x1A",
+		"EventName": "op_is_enter_selfref_rk0",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "Rank1 enters self-refresh(SRE).",
+		"ConfigCode": "0x1B",
+		"EventName": "op_is_enter_selfref_rk1",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "Rank2 enters self-refresh(SRE).",
+		"ConfigCode": "0x1C",
+		"EventName": "op_is_enter_selfref_rk2",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "Rank3 enters self-refresh(SRE).",
+		"ConfigCode": "0x1D",
+		"EventName": "op_is_enter_selfref_rk3",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "Rank0 enters power-down(PDE).",
+		"ConfigCode": "0x1E",
+		"EventName": "op_is_enter_powerdown_rk0",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "Rank1 enters power-down(PDE).",
+		"ConfigCode": "0x1F",
+		"EventName": "op_is_enter_powerdown_rk1",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "Rank2 enters power-down(PDE).",
+		"ConfigCode": "0x20",
+		"EventName": "op_is_enter_powerdown_rk2",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "Rank3 enters power-down(PDE).",
+		"ConfigCode": "0x21",
+		"EventName": "op_is_enter_powerdown_rk3",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A cycle that Rank0 stays in self-refresh mode.",
+		"ConfigCode": "0x26",
+		"EventName": "selfref_mode_rk0",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A cycle that Rank1 stays in self-refresh mode.",
+		"ConfigCode": "0x27",
+		"EventName": "selfref_mode_rk1",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A cycle that Rank2 stays in self-refresh mode.",
+		"ConfigCode": "0x28",
+		"EventName": "selfref_mode_rk2",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A cycle that Rank3 stays in self-refresh mode.",
+		"ConfigCode": "0x29",
+		"EventName": "selfref_mode_rk3",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "An auto-refresh(REF) command to DRAM.",
+		"ConfigCode": "0x2A",
+		"EventName": "op_is_refresh",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A critical auto-refresh(REF) command to DRAM.",
+		"ConfigCode": "0x2B",
+		"EventName": "op_is_crit_ref",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "An MRR or MRW command to DRAM.",
+		"ConfigCode": "0x2D",
+		"EventName": "op_is_load_mode",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A ZQCal command to DRAM.",
+		"ConfigCode": "0x2E",
+		"EventName": "op_is_zqcl",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "At least one entry in read queue reaches the visible window limit.",
+		"ConfigCode": "0x30",
+		"EventName": "visible_window_limit_reached_rd",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "At least one entry in write queue reaches the visible window limit.",
+		"ConfigCode": "0x31",
+		"EventName": "visible_window_limit_reached_wr",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A DQS Oscillator MPC command to DRAM.",
+		"ConfigCode": "0x34",
+		"EventName": "op_is_dqsosc_mpc",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A DQS Oscillator MRR command to DRAM.",
+		"ConfigCode": "0x35",
+		"EventName": "op_is_dqsosc_mrr",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A Temperature Compensated Refresh(TCR) MRR command to DRAM.",
+		"ConfigCode": "0x36",
+		"EventName": "op_is_tcr_mrr",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A ZQCal Start command to DRAM.",
+		"ConfigCode": "0x37",
+		"EventName": "op_is_zqstart",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A ZQCal Latch command to DRAM.",
+		"ConfigCode": "0x38",
+		"EventName": "op_is_zqlatch",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A packet at CHI TXREQ interface (request).",
+		"ConfigCode": "0x39",
+		"EventName": "chi_txreq",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A packet at CHI TXDAT interface (read data).",
+		"ConfigCode": "0x3A",
+		"EventName": "chi_txdat",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A packet at CHI RXDAT interface (write data).",
+		"ConfigCode": "0x3B",
+		"EventName": "chi_rxdat",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A packet at CHI RXRSP interface.",
+		"ConfigCode": "0x3C",
+		"EventName": "chi_rxrsp",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "A violation detected in TZC.",
+		"ConfigCode": "0x3D",
+		"EventName": "tsz_vio",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"BriefDescription": "The ddr cycles.",
+		"ConfigCode": "0x80",
+		"EventName": "ddr_cycles",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	}
+]
diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index 12e80bb7939b..08ec9aa583e7 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -274,6 +274,7 @@ class JsonEvent:
           'DFPMC': 'amd_df',
           'cpu_core': 'cpu_core',
           'cpu_atom': 'cpu_atom',
+          'ali_drw': 'ali_drw',
       }
       return table[unit] if unit in table else f'uncore_{unit.lower()}'
 

From 3e65bd13746af54bbe9a9c415a437bcc0b78282c Mon Sep 17 00:00:00 2001
From: Jing Zhang <renyu.zj@linux.alibaba.com>
Date: Fri, 28 Jul 2023 15:09:34 +0800
Subject: [PATCH 0195/1189] perf vendor events arm64: Add JSON metrics for
 Yitian 710 DDR

Add JSON metrics for T-HEAD Yitian 710 SoC DDR.

Reviewed-by: John Garry <john.g.garry@oracle.com>
Signed-off-by: Jing Zhang <renyu.zj@linux.alibaba.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Shuai Xue <xueshuai@linux.alibaba.com>
Cc: Will Deacon <will@kernel.org>
Cc: Zhuo Song <zhuo.song@linux.alibaba.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-doc@vger.kernel.org
Link: https://lore.kernel.org/r/1690528175-2499-3-git-send-email-renyu.zj@linux.alibaba.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../freescale/yitian710/sys/metrics.json      | 20 +++++++++++++++++++
 1 file changed, 20 insertions(+)
 create mode 100644 tools/perf/pmu-events/arch/arm64/freescale/yitian710/sys/metrics.json

diff --git a/tools/perf/pmu-events/arch/arm64/freescale/yitian710/sys/metrics.json b/tools/perf/pmu-events/arch/arm64/freescale/yitian710/sys/metrics.json
new file mode 100644
index 000000000000..bc865b374b6a
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/freescale/yitian710/sys/metrics.json
@@ -0,0 +1,20 @@
+[
+	{
+		"MetricName": "ddr_read_bandwidth.all",
+		"BriefDescription": "The ddr read bandwidth(MB/s).",
+		"MetricGroup": "ali_drw",
+		"MetricExpr": "hif_rd * 64 / 1e6 / duration_time",
+		"ScaleUnit": "1MB/s",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	},
+	{
+		"MetricName": "ddr_write_bandwidth.all",
+		"BriefDescription": "The ddr write bandwidth(MB/s).",
+		"MetricGroup": "ali_drw",
+		"MetricExpr": "(hif_wr + hif_rmw) * 64 / 1e6 / duration_time",
+		"ScaleUnit": "1MB/s",
+		"Unit": "ali_drw",
+		"Compat": "ali_drw_pmu"
+	}
+]

From f849ce6baf467ea7fb9e68ae05d5d045f3aa89e8 Mon Sep 17 00:00:00 2001
From: Jing Zhang <renyu.zj@linux.alibaba.com>
Date: Fri, 28 Jul 2023 15:09:35 +0800
Subject: [PATCH 0196/1189] perf docs: Update metric usage for Alibaba's T-Head
 PMU driver (arm64)

Alibaba's T-Head ali_drw PMU supports DDR bandwidth metrics. Update
its usage in the documentation.

Reviewed-by: John Garry <john.g.garry@oracle.com>
Signed-off-by: Jing Zhang <renyu.zj@linux.alibaba.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Shuai Xue <xueshuai@linux.alibaba.com>
Cc: Will Deacon <will@kernel.org>
Cc: Zhuo Song <zhuo.song@linux.alibaba.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-doc@vger.kernel.org
Link: https://lore.kernel.org/r/1690528175-2499-4-git-send-email-renyu.zj@linux.alibaba.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 Documentation/admin-guide/perf/alibaba_pmu.rst | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/Documentation/admin-guide/perf/alibaba_pmu.rst b/Documentation/admin-guide/perf/alibaba_pmu.rst
index 11de998bb480..7d840023903f 100644
--- a/Documentation/admin-guide/perf/alibaba_pmu.rst
+++ b/Documentation/admin-guide/perf/alibaba_pmu.rst
@@ -88,6 +88,11 @@ data bandwidth::
     -e ali_drw_27080/hif_rmw/ \
     -e ali_drw_27080/cycle/ -- sleep 10
 
+Example usage of counting all memory read/write bandwidth by metric::
+
+  perf stat -M ddr_read_bandwidth.all -- sleep 10
+  perf stat -M ddr_write_bandwidth.all -- sleep 10
+
 The average DRAM bandwidth can be calculated as follows:
 
 - Read Bandwidth =  perf_hif_rd * DDRC_WIDTH * DDRC_Freq / DDRC_Cycle

From 1134f290d07c251969d731781863dc513d81d049 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 27 Jul 2023 23:49:12 -0700
Subject: [PATCH 0197/1189] perf bpf-loader: Remove unneeded diagnostic pragma

Added during the progress to libbpf 1.0 the deprecated functions are
no longer used and so the pragma can be removed.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: James Clark <james.clark@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rob Herring <robh@kernel.org>
Cc: Tom Rix <trix@redhat.com>
Cc: bpf@vger.kernel.org
Cc: llvm@lists.linux.dev
Link: https://lore.kernel.org/r/20230728064917.767761-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/bpf-loader.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 44cde27d6389..8f4c76f2265a 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -32,9 +32,6 @@
 
 #include <internal/xyarray.h>
 
-/* temporarily disable libbpf deprecation warnings */
-#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
-
 static int libbpf_perf_print(enum libbpf_print_level level __attribute__((unused)),
 			      const char *fmt, va_list args)
 {

From 435bea0a45cb309772b22c56b2d570f743f655e0 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 27 Jul 2023 23:49:13 -0700
Subject: [PATCH 0198/1189] perf build: Don't always set -funwind-tables and
 -ggdb3

Commit 6a40cd90f5deb6de ("perf tools: Add libunwind dependency for DWARF
CFI unwinding") added libunwind support but also -funwind-tables and
-ggdb3 to the standard build. These build flags aren't necessary so
remove, set -g when DEBUG is enabled for the build.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: James Clark <james.clark@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rob Herring <robh@kernel.org>
Cc: Tom Rix <trix@redhat.com>
Cc: bpf@vger.kernel.org
Cc: llvm@lists.linux.dev
Link: https://lore.kernel.org/r/20230728064917.767761-3-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Makefile.config | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index a9cfe83638a9..14709a6bd622 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -246,6 +246,9 @@ ifeq ($(CC_NO_CLANG), 0)
 else
   CORE_CFLAGS += -O6
 endif
+else
+  CORE_CFLAGS += -g
+  CXXFLAGS += -g
 endif
 
 ifdef PARSER_DEBUG
@@ -324,8 +327,6 @@ FEATURE_CHECK_LDFLAGS-disassembler-four-args = -lbfd -lopcodes -ldl
 FEATURE_CHECK_LDFLAGS-disassembler-init-styled = -lbfd -lopcodes -ldl
 
 CORE_CFLAGS += -fno-omit-frame-pointer
-CORE_CFLAGS += -ggdb3
-CORE_CFLAGS += -funwind-tables
 CORE_CFLAGS += -Wall
 CORE_CFLAGS += -Wextra
 CORE_CFLAGS += -std=gnu11
@@ -333,8 +334,6 @@ CORE_CFLAGS += -std=gnu11
 CXXFLAGS += -std=gnu++14 -fno-exceptions -fno-rtti
 CXXFLAGS += -Wall
 CXXFLAGS += -fno-omit-frame-pointer
-CXXFLAGS += -ggdb3
-CXXFLAGS += -funwind-tables
 CXXFLAGS += -Wno-strict-aliasing
 
 HOSTCFLAGS += -Wall

From e5764ae4c9714e58fa3c38a7e4900d4379dc2263 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 27 Jul 2023 23:49:14 -0700
Subject: [PATCH 0199/1189] perf build: Add Wextra for C++ compilation

Commit d58ac0bf8d1e ("perf build: Add clang and llvm compile and
linking support") added -Wall and -Wno-strict-aliasing for CXXFLAGS,
but not -Wextra. -Wno-strict-aliasing is no longer necessary, adding
-Wextra for CXXFLAGS requires adding -Wno-unused-parameter clang.cpp
and clang-test.cpp for LIBCLANGLLVM=1 to build.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: James Clark <james.clark@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rob Herring <robh@kernel.org>
Cc: Tom Rix <trix@redhat.com>
Cc: bpf@vger.kernel.org
Cc: llvm@lists.linux.dev
Link: https://lore.kernel.org/r/20230728064917.767761-4-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Makefile.config | 2 +-
 tools/perf/util/c++/Build  | 3 +++
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 14709a6bd622..fe7afe6d8529 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -333,8 +333,8 @@ CORE_CFLAGS += -std=gnu11
 
 CXXFLAGS += -std=gnu++14 -fno-exceptions -fno-rtti
 CXXFLAGS += -Wall
+CXXFLAGS += -Wextra
 CXXFLAGS += -fno-omit-frame-pointer
-CXXFLAGS += -Wno-strict-aliasing
 
 HOSTCFLAGS += -Wall
 HOSTCFLAGS += -Wextra
diff --git a/tools/perf/util/c++/Build b/tools/perf/util/c++/Build
index 613ecfd76527..8610d032ac19 100644
--- a/tools/perf/util/c++/Build
+++ b/tools/perf/util/c++/Build
@@ -1,2 +1,5 @@
 perf-$(CONFIG_CLANGLLVM) += clang.o
 perf-$(CONFIG_CLANGLLVM) += clang-test.o
+
+CXXFLAGS_clang.o += -Wno-unused-parameter
+CXXFLAGS_clang-test.o += -Wno-unused-parameter

From b265ee7bae1192ecc55ecaf7e63c8ed84cc2f509 Mon Sep 17 00:00:00 2001
From: Alexey Kardashevskiy <aik@amd.com>
Date: Thu, 15 Jun 2023 16:37:49 +1000
Subject: [PATCH 0200/1189] KVM: SEV: move set_dr_intercepts/clr_dr_intercepts
 from the header

Static functions set_dr_intercepts() and clr_dr_intercepts() are only
called from SVM so move them to .c.

No functional change intended.

Signed-off-by: Alexey Kardashevskiy <aik@amd.com>
Reviewed-by: Carlos Bilbao <carlos.bilbao@amd.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Reviewed-by: Santosh Shukla <santosh.shukla@amd.com>
Link: https://lore.kernel.org/r/20230615063757.3039121-2-aik@amd.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.c | 42 ++++++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/svm/svm.h | 42 ------------------------------------------
 2 files changed, 42 insertions(+), 42 deletions(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index d381ad424554..42f17ae99c9e 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -677,6 +677,48 @@ free_save_area:
 
 }
 
+static void set_dr_intercepts(struct vcpu_svm *svm)
+{
+	struct vmcb *vmcb = svm->vmcb01.ptr;
+
+	if (!sev_es_guest(svm->vcpu.kvm)) {
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_READ);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_READ);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_READ);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_READ);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_READ);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_READ);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_READ);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_WRITE);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_WRITE);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_WRITE);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_WRITE);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_WRITE);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_WRITE);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_WRITE);
+	}
+
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE);
+
+	recalc_intercepts(svm);
+}
+
+static void clr_dr_intercepts(struct vcpu_svm *svm)
+{
+	struct vmcb *vmcb = svm->vmcb01.ptr;
+
+	vmcb->control.intercepts[INTERCEPT_DR] = 0;
+
+	/* DR7 access must remain intercepted for an SEV-ES guest */
+	if (sev_es_guest(svm->vcpu.kvm)) {
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE);
+	}
+
+	recalc_intercepts(svm);
+}
+
 static int direct_access_msr_slot(u32 msr)
 {
 	u32 i;
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 18af7e712a5a..800ca1776b59 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -404,48 +404,6 @@ static inline bool vmcb12_is_intercept(struct vmcb_ctrl_area_cached *control, u3
 	return test_bit(bit, (unsigned long *)&control->intercepts);
 }
 
-static inline void set_dr_intercepts(struct vcpu_svm *svm)
-{
-	struct vmcb *vmcb = svm->vmcb01.ptr;
-
-	if (!sev_es_guest(svm->vcpu.kvm)) {
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_READ);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_READ);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_READ);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_READ);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_READ);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_READ);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_READ);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_WRITE);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_WRITE);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_WRITE);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_WRITE);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_WRITE);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_WRITE);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_WRITE);
-	}
-
-	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ);
-	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE);
-
-	recalc_intercepts(svm);
-}
-
-static inline void clr_dr_intercepts(struct vcpu_svm *svm)
-{
-	struct vmcb *vmcb = svm->vmcb01.ptr;
-
-	vmcb->control.intercepts[INTERCEPT_DR] = 0;
-
-	/* DR7 access must remain intercepted for an SEV-ES guest */
-	if (sev_es_guest(svm->vcpu.kvm)) {
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE);
-	}
-
-	recalc_intercepts(svm);
-}
-
 static inline void set_exception_intercept(struct vcpu_svm *svm, u32 bit)
 {
 	struct vmcb *vmcb = svm->vmcb01.ptr;

From 29de732cc95cb5219d8c2bd145cb7293cb572fc3 Mon Sep 17 00:00:00 2001
From: Alexey Kardashevskiy <aik@amd.com>
Date: Thu, 15 Jun 2023 16:37:50 +1000
Subject: [PATCH 0201/1189] KVM: SEV: Move SEV's GP_VECTOR intercept setup to
 SEV

Currently SVM setup is done sequentially in
init_vmcb() -> sev_init_vmcb() -> sev_es_init_vmcb() and tries
keeping SVM/SEV/SEV-ES bits separated. One of the exceptions
is #GP intercept which init_vmcb() skips setting for SEV guests and
then sev_es_init_vmcb() needlessly clears it.

Remove the SEV check from init_vmcb(). Clear the #GP intercept in
sev_init_vmcb(). SEV-ES will use the SEV setting.

No functional change intended.

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Alexey Kardashevskiy <aik@amd.com>
Reviewed-by: Carlos Bilbao <carlos.bilbao@amd.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Reviewed-by: Santosh Shukla <santosh.shukla@amd.com>
Link: https://lore.kernel.org/r/20230615063757.3039121-3-aik@amd.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/sev.c | 9 ++++++---
 arch/x86/kvm/svm/svm.c | 5 ++---
 2 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 07756b7348ae..fd6e316c1a23 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2974,9 +2974,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
 	svm_set_intercept(svm, TRAP_CR4_WRITE);
 	svm_set_intercept(svm, TRAP_CR8_WRITE);
 
-	/* No support for enable_vmware_backdoor */
-	clr_exception_intercept(svm, GP_VECTOR);
-
 	/* Can't intercept XSETBV, HV can't modify XCR0 directly */
 	svm_clr_intercept(svm, INTERCEPT_XSETBV);
 
@@ -3002,6 +2999,12 @@ void sev_init_vmcb(struct vcpu_svm *svm)
 	svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ENABLE;
 	clr_exception_intercept(svm, UD_VECTOR);
 
+	/*
+	 * Don't intercept #GP for SEV guests, e.g. for the VMware backdoor, as
+	 * KVM can't decrypt guest memory to decode the faulting instruction.
+	 */
+	clr_exception_intercept(svm, GP_VECTOR);
+
 	if (sev_es_guest(svm->vcpu.kvm))
 		sev_es_init_vmcb(svm);
 }
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 42f17ae99c9e..a0e803f2a574 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1243,10 +1243,9 @@ static void init_vmcb(struct kvm_vcpu *vcpu)
 	 * Guest access to VMware backdoor ports could legitimately
 	 * trigger #GP because of TSS I/O permission bitmap.
 	 * We intercept those #GP and allow access to them anyway
-	 * as VMware does.  Don't intercept #GP for SEV guests as KVM can't
-	 * decrypt guest memory to decode the faulting instruction.
+	 * as VMware does.
 	 */
-	if (enable_vmware_backdoor && !sev_guest(vcpu->kvm))
+	if (enable_vmware_backdoor)
 		set_exception_intercept(svm, GP_VECTOR);
 
 	svm_set_intercept(svm, INTERCEPT_INTR);

From f8d808ed1ba0019997f18ff2be0cf85e33a31022 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 15 Jun 2023 16:37:51 +1000
Subject: [PATCH 0202/1189] KVM: SVM: Rewrite
 sev_es_prepare_switch_to_guest()'s comment about swap types

Rewrite the comment(s) in sev_es_prepare_switch_to_guest() to explain the
swap types employed by the CPU for SEV-ES guests, i.e. to explain why KVM
needs to save a seemingly random subset of host state, and to provide a
decoder for the APM's Type-A/B/C terminology.

Signed-off-by: Alexey Kardashevskiy <aik@amd.com>
Link: https://lore.kernel.org/r/20230615063757.3039121-4-aik@amd.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/sev.c | 25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index fd6e316c1a23..d58a25a92aa3 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -3023,19 +3023,24 @@ void sev_es_vcpu_reset(struct vcpu_svm *svm)
 void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa)
 {
 	/*
-	 * As an SEV-ES guest, hardware will restore the host state on VMEXIT,
-	 * of which one step is to perform a VMLOAD.  KVM performs the
-	 * corresponding VMSAVE in svm_prepare_guest_switch for both
-	 * traditional and SEV-ES guests.
+	 * All host state for SEV-ES guests is categorized into three swap types
+	 * based on how it is handled by hardware during a world switch:
+	 *
+	 * A: VMRUN:   Host state saved in host save area
+	 *    VMEXIT:  Host state loaded from host save area
+	 *
+	 * B: VMRUN:   Host state _NOT_ saved in host save area
+	 *    VMEXIT:  Host state loaded from host save area
+	 *
+	 * C: VMRUN:   Host state _NOT_ saved in host save area
+	 *    VMEXIT:  Host state initialized to default(reset) values
+	 *
+	 * Manually save type-B state, i.e. state that is loaded by VMEXIT but
+	 * isn't saved by VMRUN, that isn't already saved by VMSAVE (performed
+	 * by common SVM code).
 	 */
-
-	/* XCR0 is restored on VMEXIT, save the current host value */
 	hostsa->xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-
-	/* PKRU is restored on VMEXIT, save the current host value */
 	hostsa->pkru = read_pkru();
-
-	/* MSR_IA32_XSS is restored on VMEXIT, save the currnet host value */
 	hostsa->xss = host_xss;
 }
 

From 2837dd00f8fc69111cd6b1dc8481d2fb490d11c9 Mon Sep 17 00:00:00 2001
From: Alexey Kardashevskiy <aik@amd.com>
Date: Thu, 15 Jun 2023 16:37:52 +1000
Subject: [PATCH 0203/1189] KVM: SEV-ES: explicitly disable debug

SVM/SEV enable debug registers intercepts to skip swapping DRs
on entering/exiting the guest. When the guest is in control of
debug registers (vcpu->guest_debug == 0), there is an optimisation to
reduce the number of context switches: intercepts are cleared and
the KVM_DEBUGREG_WONT_EXIT flag is set to tell KVM to do swapping
on guest enter/exit.

The same code also executes for SEV-ES, however it has no effect as
- it always takes (vcpu->guest_debug == 0) branch;
- KVM_DEBUGREG_WONT_EXIT is set but DR7 intercept is not cleared;
- vcpu_enter_guest() writes DRs but VMRUN for SEV-ES swaps them
with the values from _encrypted_ VMSA.

Be explicit about SEV-ES not supporting debug:
- return right away from dr_interception() and skip unnecessary processing;
- return an error right away from the KVM_SEV_LAUNCH_UPDATE_VMSA handler
if debugging was already enabled.
KVM_SET_GUEST_DEBUG are failing already after KVM_SEV_LAUNCH_UPDATE_VMSA
is finished due to vcpu->arch.guest_state_protected set to true.

Add WARN_ON to kvm_x86::sync_dirty_debug_regs() (saves guest DRs on
guest exit) to signify that SEV-ES won't hit that path.

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Alexey Kardashevskiy <aik@amd.com>
Link: https://lore.kernel.org/r/20230615063757.3039121-5-aik@amd.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/sev.c | 5 +++++
 arch/x86/kvm/svm/svm.c | 9 ++++++++-
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index d58a25a92aa3..0299bbe188f1 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -619,6 +619,11 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu,
 	struct vcpu_svm *svm = to_svm(vcpu);
 	int ret;
 
+	if (vcpu->guest_debug) {
+		pr_warn_once("KVM_SET_GUEST_DEBUG for SEV-ES guest is not supported");
+		return -EINVAL;
+	}
+
 	/* Perform some pre-encryption checks against the VMSA */
 	ret = sev_es_sync_vmsa(svm);
 	if (ret)
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index a0e803f2a574..e838cfecc0fa 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1983,7 +1983,7 @@ static void svm_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	if (vcpu->arch.guest_state_protected)
+	if (WARN_ON_ONCE(sev_es_guest(vcpu->kvm)))
 		return;
 
 	get_debugreg(vcpu->arch.db[0], 0);
@@ -2714,6 +2714,13 @@ static int dr_interception(struct kvm_vcpu *vcpu)
 	unsigned long val;
 	int err = 0;
 
+	/*
+	 * SEV-ES intercepts DR7 only to disable guest debugging and the guest issues a VMGEXIT
+	 * for DR7 write only. KVM cannot change DR7 (always swapped as type 'A') so return early.
+	 */
+	if (sev_es_guest(vcpu->kvm))
+		return 1;
+
 	if (vcpu->guest_debug == 0) {
 		/*
 		 * No more DR vmexits; force a reload of the debug registers

From c2690b5f01948dfec19d50086312848c0b5b02b0 Mon Sep 17 00:00:00 2001
From: Alexey Kardashevskiy <aik@amd.com>
Date: Thu, 15 Jun 2023 16:37:53 +1000
Subject: [PATCH 0204/1189] KVM: SVM/SEV/SEV-ES: Rework intercepts

Currently SVM setup is done sequentially in
init_vmcb() -> sev_init_vmcb() -> sev_es_init_vmcb()
and tries keeping SVM/SEV/SEV-ES bits separated. One of the exceptions
is DR intercepts which is for SEV-ES before sev_es_init_vmcb() runs.

Move the SEV-ES intercept setup to sev_es_init_vmcb(). From now on
set_dr_intercepts()/clr_dr_intercepts() handle SVM/SEV only.

No functional change intended.

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Alexey Kardashevskiy <aik@amd.com>
Reviewed-by: Santosh Shukla <santosh.shukla@amd.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Link: https://lore.kernel.org/r/20230615063757.3039121-6-aik@amd.com
[sean: drop comment about intercepting DR7]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/sev.c |  6 ++++++
 arch/x86/kvm/svm/svm.c | 37 ++++++++++++++-----------------------
 2 files changed, 20 insertions(+), 23 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 0299bbe188f1..b3ef509f6fda 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2951,6 +2951,7 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in)
 
 static void sev_es_init_vmcb(struct vcpu_svm *svm)
 {
+	struct vmcb *vmcb = svm->vmcb01.ptr;
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 
 	svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ES_ENABLE;
@@ -2979,6 +2980,11 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
 	svm_set_intercept(svm, TRAP_CR4_WRITE);
 	svm_set_intercept(svm, TRAP_CR8_WRITE);
 
+	vmcb->control.intercepts[INTERCEPT_DR] = 0;
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE);
+	recalc_intercepts(svm);
+
 	/* Can't intercept XSETBV, HV can't modify XCR0 directly */
 	svm_clr_intercept(svm, INTERCEPT_XSETBV);
 
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index e838cfecc0fa..8fad9ebb5126 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -681,23 +681,20 @@ static void set_dr_intercepts(struct vcpu_svm *svm)
 {
 	struct vmcb *vmcb = svm->vmcb01.ptr;
 
-	if (!sev_es_guest(svm->vcpu.kvm)) {
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_READ);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_READ);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_READ);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_READ);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_READ);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_READ);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_READ);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_WRITE);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_WRITE);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_WRITE);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_WRITE);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_WRITE);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_WRITE);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_WRITE);
-	}
-
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_WRITE);
 	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ);
 	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE);
 
@@ -710,12 +707,6 @@ static void clr_dr_intercepts(struct vcpu_svm *svm)
 
 	vmcb->control.intercepts[INTERCEPT_DR] = 0;
 
-	/* DR7 access must remain intercepted for an SEV-ES guest */
-	if (sev_es_guest(svm->vcpu.kvm)) {
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ);
-		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE);
-	}
-
 	recalc_intercepts(svm);
 }
 

From d1f85fbe836e61ed330a242f927a98abd98929cc Mon Sep 17 00:00:00 2001
From: Alexey Kardashevskiy <aik@amd.com>
Date: Thu, 15 Jun 2023 16:37:54 +1000
Subject: [PATCH 0205/1189] KVM: SEV: Enable data breakpoints in SEV-ES

Add support for "DebugSwap for SEV-ES guests", which provides support
for swapping DR[0-3] and DR[0-3]_ADDR_MASK on VMRUN and VMEXIT, i.e.
allows KVM to expose debug capabilities to SEV-ES guests. Without
DebugSwap support, the CPU doesn't save/load most _guest_ debug
registers (except DR6/7), and KVM cannot manually context switch guest
DRs due the VMSA being encrypted.

Enable DebugSwap if and only if the CPU also supports NoNestedDataBp,
which causes the CPU to ignore nested #DBs, i.e. #DBs that occur when
vectoring a #DB.  Without NoNestedDataBp, a malicious guest can DoS
the host by putting the CPU into an infinite loop of vectoring #DBs
(see https://bugzilla.redhat.com/show_bug.cgi?id=1278496)

Set the features bit in sev_es_sync_vmsa() which is the last point
when VMSA is not encrypted yet as sev_(es_)init_vmcb() (where the most
init happens) is called not only when VCPU is initialised but also on
intrahost migration when VMSA is encrypted.

Eliminate DR7 intercepts as KVM can't modify guest DR7, and intercepting
DR7 would completely defeat the purpose of enabling DebugSwap.

Make X86_FEATURE_DEBUG_SWAP appear in /proc/cpuinfo (by not adding "") to
let the operator know if the VM can debug.

Signed-off-by: Alexey Kardashevskiy <aik@amd.com>
Link: https://lore.kernel.org/r/20230615063757.3039121-7-aik@amd.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/cpufeatures.h       |  1 +
 arch/x86/include/asm/svm.h               |  1 +
 arch/x86/kvm/svm/sev.c                   | 36 ++++++++++++++++++++++--
 tools/arch/x86/include/asm/cpufeatures.h |  1 +
 4 files changed, 36 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index cb8ca46213be..31c862d79fae 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -434,6 +434,7 @@
 #define X86_FEATURE_SEV_ES		(19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */
 #define X86_FEATURE_V_TSC_AUX		(19*32+ 9) /* "" Virtual TSC_AUX */
 #define X86_FEATURE_SME_COHERENT	(19*32+10) /* "" AMD hardware-enforced cache coherency */
+#define X86_FEATURE_DEBUG_SWAP		(19*32+14) /* AMD SEV-ES full debug state swap support */
 
 /* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */
 #define X86_FEATURE_NO_NESTED_DATA_BP	(20*32+ 0) /* "" No Nested Data Breakpoints */
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index e7c7379d6ac7..72ebd5e4e975 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -288,6 +288,7 @@ static_assert((X2AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == X2AVIC_
 
 #define AVIC_HPA_MASK	~((0xFFFULL << 52) | 0xFFF)
 
+#define SVM_SEV_FEAT_DEBUG_SWAP                        BIT(5)
 
 struct vmcb_seg {
 	u16 selector;
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index b3ef509f6fda..b7cd0cc4a19c 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -23,6 +23,7 @@
 #include <asm/pkru.h>
 #include <asm/trapnr.h>
 #include <asm/fpu/xcr.h>
+#include <asm/debugreg.h>
 
 #include "mmu.h"
 #include "x86.h"
@@ -54,9 +55,14 @@ module_param_named(sev, sev_enabled, bool, 0444);
 /* enable/disable SEV-ES support */
 static bool sev_es_enabled = true;
 module_param_named(sev_es, sev_es_enabled, bool, 0444);
+
+/* enable/disable SEV-ES DebugSwap support */
+static bool sev_es_debug_swap_enabled = true;
+module_param_named(debug_swap, sev_es_debug_swap_enabled, bool, 0444);
 #else
 #define sev_enabled false
 #define sev_es_enabled false
+#define sev_es_debug_swap_enabled false
 #endif /* CONFIG_KVM_AMD_SEV */
 
 static u8 sev_enc_bit;
@@ -606,6 +612,9 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm)
 	save->xss  = svm->vcpu.arch.ia32_xss;
 	save->dr6  = svm->vcpu.arch.dr6;
 
+	if (sev_es_debug_swap_enabled)
+		save->sev_features |= SVM_SEV_FEAT_DEBUG_SWAP;
+
 	pr_debug("Virtual Machine Save Area (VMSA):\n");
 	print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1, save, sizeof(*save), false);
 
@@ -2261,6 +2270,9 @@ out:
 
 	sev_enabled = sev_supported;
 	sev_es_enabled = sev_es_supported;
+	if (!sev_es_enabled || !cpu_feature_enabled(X86_FEATURE_DEBUG_SWAP) ||
+	    !cpu_feature_enabled(X86_FEATURE_NO_NESTED_DATA_BP))
+		sev_es_debug_swap_enabled = false;
 #endif
 }
 
@@ -2981,9 +2993,11 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
 	svm_set_intercept(svm, TRAP_CR8_WRITE);
 
 	vmcb->control.intercepts[INTERCEPT_DR] = 0;
-	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ);
-	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE);
-	recalc_intercepts(svm);
+	if (!sev_es_debug_swap_enabled) {
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE);
+		recalc_intercepts(svm);
+	}
 
 	/* Can't intercept XSETBV, HV can't modify XCR0 directly */
 	svm_clr_intercept(svm, INTERCEPT_XSETBV);
@@ -3053,6 +3067,22 @@ void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa)
 	hostsa->xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
 	hostsa->pkru = read_pkru();
 	hostsa->xss = host_xss;
+
+	/*
+	 * If DebugSwap is enabled, debug registers are loaded but NOT saved by
+	 * the CPU (Type-B). If DebugSwap is disabled/unsupported, the CPU both
+	 * saves and loads debug registers (Type-A).
+	 */
+	if (sev_es_debug_swap_enabled) {
+		hostsa->dr0 = native_get_debugreg(0);
+		hostsa->dr1 = native_get_debugreg(1);
+		hostsa->dr2 = native_get_debugreg(2);
+		hostsa->dr3 = native_get_debugreg(3);
+		hostsa->dr0_addr_mask = amd_get_dr_addr_mask(0);
+		hostsa->dr1_addr_mask = amd_get_dr_addr_mask(1);
+		hostsa->dr2_addr_mask = amd_get_dr_addr_mask(2);
+		hostsa->dr3_addr_mask = amd_get_dr_addr_mask(3);
+	}
 }
 
 void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index cb8ca46213be..31c862d79fae 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -434,6 +434,7 @@
 #define X86_FEATURE_SEV_ES		(19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */
 #define X86_FEATURE_V_TSC_AUX		(19*32+ 9) /* "" Virtual TSC_AUX */
 #define X86_FEATURE_SME_COHERENT	(19*32+10) /* "" AMD hardware-enforced cache coherency */
+#define X86_FEATURE_DEBUG_SWAP		(19*32+14) /* AMD SEV-ES full debug state swap support */
 
 /* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */
 #define X86_FEATURE_NO_NESTED_DATA_BP	(20*32+ 0) /* "" No Nested Data Breakpoints */

From 90cbf6d914ad7856ca1145dee02babb9eab7bec1 Mon Sep 17 00:00:00 2001
From: Alexey Kardashevskiy <aik@amd.com>
Date: Thu, 15 Jun 2023 16:37:55 +1000
Subject: [PATCH 0206/1189] KVM: SEV-ES: Eliminate #DB intercept when DebugSwap
 enabled

Disable #DB for SEV-ES guests when DebugSwap is enabled. There is no point
in such intercept as KVM does not allow guest debug for SEV-ES guests.

Signed-off-by: Alexey Kardashevskiy <aik@amd.com>
Link: https://lore.kernel.org/r/20230615063757.3039121-8-aik@amd.com
[sean: add comment as to why KVM disables #DB intercept iff DebugSwap=1]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/sev.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index b7cd0cc4a19c..b35cd670ce66 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2997,6 +2997,17 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
 		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ);
 		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE);
 		recalc_intercepts(svm);
+	} else {
+		/*
+		 * Disable #DB intercept iff DebugSwap is enabled.  KVM doesn't
+		 * allow debugging SEV-ES guests, and enables DebugSwap iff
+		 * NO_NESTED_DATA_BP is supported, so there's no reason to
+		 * intercept #DB when DebugSwap is enabled.  For simplicity
+		 * with respect to guest debug, intercept #DB for other VMs
+		 * even if NO_NESTED_DATA_BP is supported, i.e. even if the
+		 * guest can't DoS the CPU with infinite #DB vectoring.
+		 */
+		clr_exception_intercept(svm, DB_VECTOR);
 	}
 
 	/* Can't intercept XSETBV, HV can't modify XCR0 directly */

From 389fbbec261b2842fd0e34b26a2b288b122cc406 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 15 Jun 2023 16:37:56 +1000
Subject: [PATCH 0207/1189] KVM: SVM: Don't defer NMI unblocking until next
 exit for SEV-ES guests

Immediately mark NMIs as unmasked in response to #VMGEXIT(NMI complete)
instead of setting awaiting_iret_completion and waiting until the *next*
VM-Exit to unmask NMIs.  The whole point of "NMI complete" is that the
guest is responsible for telling the hypervisor when it's safe to inject
an NMI, i.e. there's no need to wait.  And because there's no IRET to
single-step, the next VM-Exit could be a long time coming, i.e. KVM could
incorrectly hold an NMI pending for far longer than what is required and
expected.

Opportunistically fix a stale reference to HF_IRET_MASK.

Fixes: 916b54a7688b ("KVM: x86: Move HF_NMI_MASK and HF_IRET_MASK into "struct vcpu_svm"")
Fixes: 4444dfe4050b ("KVM: SVM: Add NMI support for an SEV-ES guest")
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Link: https://lore.kernel.org/r/20230615063757.3039121-9-aik@amd.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/sev.c |  5 ++++-
 arch/x86/kvm/svm/svm.c | 10 +++++-----
 2 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index b35cd670ce66..2cd15783dfb9 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2900,7 +2900,10 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 					    svm->sev_es.ghcb_sa);
 		break;
 	case SVM_VMGEXIT_NMI_COMPLETE:
-		ret = svm_invoke_exit_handler(vcpu, SVM_EXIT_IRET);
+		++vcpu->stat.nmi_window_exits;
+		svm->nmi_masked = false;
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
+		ret = 1;
 		break;
 	case SVM_VMGEXIT_AP_HLT_LOOP:
 		ret = kvm_emulate_ap_reset_hold(vcpu);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 8fad9ebb5126..b15bc158ecc6 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -2535,12 +2535,13 @@ static int iret_interception(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	WARN_ON_ONCE(sev_es_guest(vcpu->kvm));
+
 	++vcpu->stat.nmi_window_exits;
 	svm->awaiting_iret_completion = true;
 
 	svm_clr_iret_intercept(svm);
-	if (!sev_es_guest(vcpu->kvm))
-		svm->nmi_iret_rip = kvm_rip_read(vcpu);
+	svm->nmi_iret_rip = kvm_rip_read(vcpu);
 
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 	return 1;
@@ -3950,12 +3951,11 @@ static void svm_complete_interrupts(struct kvm_vcpu *vcpu)
 	svm->soft_int_injected = false;
 
 	/*
-	 * If we've made progress since setting HF_IRET_MASK, we've
+	 * If we've made progress since setting awaiting_iret_completion, we've
 	 * executed an IRET and can allow NMI injection.
 	 */
 	if (svm->awaiting_iret_completion &&
-	    (sev_es_guest(vcpu->kvm) ||
-	     kvm_rip_read(vcpu) != svm->nmi_iret_rip)) {
+	    kvm_rip_read(vcpu) != svm->nmi_iret_rip) {
 		svm->awaiting_iret_completion = false;
 		svm->nmi_masked = false;
 		kvm_make_request(KVM_REQ_EVENT, vcpu);

From a6bb5709029756a6151afed0eec26ba2bfabed51 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 15 Jun 2023 16:37:57 +1000
Subject: [PATCH 0208/1189] KVM: SVM: Don't try to pointlessly single-step
 SEV-ES guests for NMI window

Bail early from svm_enable_nmi_window() for SEV-ES guests without trying
to enable single-step of the guest, as single-stepping an SEV-ES guest is
impossible and the guest is responsible for *telling* KVM when it is ready
for an new NMI to be injected.

Functionally, setting TF and RF in svm->vmcb->save.rflags is benign as the
field is ignored by hardware, but it's all kinds of confusing.

Signed-off-by: Alexey Kardashevskiy <aik@amd.com>
Link: https://lore.kernel.org/r/20230615063757.3039121-10-aik@amd.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index b15bc158ecc6..1bc0936bbd51 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3802,6 +3802,19 @@ static void svm_enable_nmi_window(struct kvm_vcpu *vcpu)
 	if (svm_get_nmi_mask(vcpu) && !svm->awaiting_iret_completion)
 		return; /* IRET will cause a vm exit */
 
+	/*
+	 * SEV-ES guests are responsible for signaling when a vCPU is ready to
+	 * receive a new NMI, as SEV-ES guests can't be single-stepped, i.e.
+	 * KVM can't intercept and single-step IRET to detect when NMIs are
+	 * unblocked (architecturally speaking).  See SVM_VMGEXIT_NMI_COMPLETE.
+	 *
+	 * Note, GIF is guaranteed to be '1' for SEV-ES guests as hardware
+	 * ignores SEV-ES guest writes to EFER.SVME *and* CLGI/STGI are not
+	 * supported NAEs in the GHCB protocol.
+	 */
+	if (sev_es_guest(vcpu->kvm))
+		return;
+
 	if (!gif_set(svm)) {
 		if (vgif)
 			svm_set_intercept(svm, INTERCEPT_STGI);

From f94c3bce7491228733b765e60189aa325b866ff0 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sun, 23 Jul 2023 22:13:39 -0700
Subject: [PATCH 0209/1189] Input: qt2160 - tweak check for i2c adapter
 functionality

i2c_check_functionality() returns essentially a boolean and not an error
code, so treat it as such.

Link: https://lore.kernel.org/r/20230724051345.335219-1-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/qt2160.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/input/keyboard/qt2160.c b/drivers/input/keyboard/qt2160.c
index 599ea85cfd30..b0b9d7a2691e 100644
--- a/drivers/input/keyboard/qt2160.c
+++ b/drivers/input/keyboard/qt2160.c
@@ -345,12 +345,9 @@ static int qt2160_probe(struct i2c_client *client)
 	int i;
 	int error;
 
-	/* Check functionality */
-	error = i2c_check_functionality(client->adapter,
-			I2C_FUNC_SMBUS_BYTE);
-	if (!error) {
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_BYTE)) {
 		dev_err(&client->dev, "%s adapter not supported\n",
-				dev_driver_string(&client->adapter->dev));
+			dev_driver_string(&client->adapter->dev));
 		return -ENODEV;
 	}
 

From f1fbff609a1439df4afedde7663148bffa9d67ea Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sun, 23 Jul 2023 22:13:40 -0700
Subject: [PATCH 0210/1189] Input: qt2160 - switch to using threaded interrupt
 handler

Instead of using combination of normal IRQ and work item which required
careful handling on device teardown, use standard threaded interrupt that
allows communication wityh the chip over slow (I2C) bus directly in the
interrupt handler.

To support polling mode switch to standard polling support implemented by
the input core.

Link: https://lore.kernel.org/r/20230724051345.335219-2-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/qt2160.c | 53 ++++++++++++---------------------
 1 file changed, 19 insertions(+), 34 deletions(-)

diff --git a/drivers/input/keyboard/qt2160.c b/drivers/input/keyboard/qt2160.c
index b0b9d7a2691e..b8c0f0ebf604 100644
--- a/drivers/input/keyboard/qt2160.c
+++ b/drivers/input/keyboard/qt2160.c
@@ -32,7 +32,7 @@
 
 #define QT2160_NUM_LEDS_X	8
 
-#define QT2160_CYCLE_INTERVAL	(2*HZ)
+#define QT2160_CYCLE_INTERVAL	2000 /* msec - 2 sec */
 
 static unsigned char qt2160_key2code[] = {
 	KEY_0, KEY_1, KEY_2, KEY_3,
@@ -54,7 +54,6 @@ struct qt2160_led {
 struct qt2160_data {
 	struct i2c_client *client;
 	struct input_dev *input;
-	struct delayed_work dwork;
 	unsigned short keycodes[ARRAY_SIZE(qt2160_key2code)];
 	u16 key_matrix;
 #ifdef CONFIG_LEDS_CLASS
@@ -155,10 +154,10 @@ static int qt2160_read_block(struct i2c_client *client,
 	return 0;
 }
 
-static int qt2160_get_key_matrix(struct qt2160_data *qt2160)
+static void qt2160_get_key_matrix(struct input_dev *input)
 {
+	struct qt2160_data *qt2160 = input_get_drvdata(input);
 	struct i2c_client *client = qt2160->client;
-	struct input_dev *input = qt2160->input;
 	u8 regs[6];
 	u16 old_matrix, new_matrix;
 	int ret, i, mask;
@@ -173,7 +172,7 @@ static int qt2160_get_key_matrix(struct qt2160_data *qt2160)
 	if (ret) {
 		dev_err(&client->dev,
 			"could not perform chip read.\n");
-		return ret;
+		return;
 	}
 
 	old_matrix = qt2160->key_matrix;
@@ -191,37 +190,17 @@ static int qt2160_get_key_matrix(struct qt2160_data *qt2160)
 	}
 
 	input_sync(input);
-
-	return 0;
 }
 
-static irqreturn_t qt2160_irq(int irq, void *_qt2160)
+static irqreturn_t qt2160_irq(int irq, void *data)
 {
-	struct qt2160_data *qt2160 = _qt2160;
+	struct input_dev *input = data;
 
-	mod_delayed_work(system_wq, &qt2160->dwork, 0);
+	qt2160_get_key_matrix(input);
 
 	return IRQ_HANDLED;
 }
 
-static void qt2160_schedule_read(struct qt2160_data *qt2160)
-{
-	schedule_delayed_work(&qt2160->dwork, QT2160_CYCLE_INTERVAL);
-}
-
-static void qt2160_worker(struct work_struct *work)
-{
-	struct qt2160_data *qt2160 =
-		container_of(work, struct qt2160_data, dwork.work);
-
-	dev_dbg(&qt2160->client->dev, "worker\n");
-
-	qt2160_get_key_matrix(qt2160);
-
-	/* Avoid device lock up by checking every so often */
-	qt2160_schedule_read(qt2160);
-}
-
 static int qt2160_read(struct i2c_client *client, u8 reg)
 {
 	int ret;
@@ -365,7 +344,6 @@ static int qt2160_probe(struct i2c_client *client)
 
 	qt2160->client = client;
 	qt2160->input = input;
-	INIT_DELAYED_WORK(&qt2160->dwork, qt2160_worker);
 
 	input->name = "AT42QT2160 Touch Sense Keyboard";
 	input->id.bustype = BUS_I2C;
@@ -382,6 +360,8 @@ static int qt2160_probe(struct i2c_client *client)
 	}
 	__clear_bit(KEY_RESERVED, input->keybit);
 
+	input_set_drvdata(input, qt2160);
+
 	/* Calibrate device */
 	error = qt2160_write(client, QT2160_CMD_CALIBRATE, 1);
 	if (error) {
@@ -390,13 +370,21 @@ static int qt2160_probe(struct i2c_client *client)
 	}
 
 	if (client->irq) {
-		error = request_irq(client->irq, qt2160_irq,
-				    IRQF_TRIGGER_FALLING, "qt2160", qt2160);
+		error = request_threaded_irq(client->irq, NULL, qt2160_irq,
+					     IRQF_TRIGGER_LOW | IRQF_ONESHOT,
+					     "qt2160", input);
 		if (error) {
 			dev_err(&client->dev,
 				"failed to allocate irq %d\n", client->irq);
 			goto err_free_mem;
 		}
+	} else {
+		error = input_setup_polling(input, qt2160_get_key_matrix);
+		if (error) {
+			dev_err(&client->dev, "Failed to setup polling\n");
+			goto err_free_mem;
+		}
+		input_set_poll_interval(input, QT2160_CYCLE_INTERVAL);
 	}
 
 	error = qt2160_register_leds(qt2160);
@@ -413,7 +401,6 @@ static int qt2160_probe(struct i2c_client *client)
 	}
 
 	i2c_set_clientdata(client, qt2160);
-	qt2160_schedule_read(qt2160);
 
 	return 0;
 
@@ -438,8 +425,6 @@ static void qt2160_remove(struct i2c_client *client)
 	if (client->irq)
 		free_irq(client->irq, qt2160);
 
-	cancel_delayed_work_sync(&qt2160->dwork);
-
 	input_unregister_device(qt2160->input);
 	kfree(qt2160);
 }

From d675c9b573dd23714c5d3fee64c834bc459d626a Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sun, 23 Jul 2023 22:13:41 -0700
Subject: [PATCH 0211/1189] Input: qt2160 - do not hard code interrupt trigger

Rely on the platform and ACPI/DT to set up the interrupt trigger.

Link: https://lore.kernel.org/r/20230724051345.335219-3-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/qt2160.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/input/keyboard/qt2160.c b/drivers/input/keyboard/qt2160.c
index b8c0f0ebf604..6cfaabd10482 100644
--- a/drivers/input/keyboard/qt2160.c
+++ b/drivers/input/keyboard/qt2160.c
@@ -371,8 +371,7 @@ static int qt2160_probe(struct i2c_client *client)
 
 	if (client->irq) {
 		error = request_threaded_irq(client->irq, NULL, qt2160_irq,
-					     IRQF_TRIGGER_LOW | IRQF_ONESHOT,
-					     "qt2160", input);
+					     IRQF_ONESHOT, "qt2160", input);
 		if (error) {
 			dev_err(&client->dev,
 				"failed to allocate irq %d\n", client->irq);

From 3e4bb047b23375a34dbf5885709ac3729d9cfb22 Mon Sep 17 00:00:00 2001
From: Yangtao Li <frank.li@vivo.com>
Date: Sun, 23 Jul 2023 22:13:42 -0700
Subject: [PATCH 0212/1189] Input: qt2160 - convert to use devm_* api

Use devm_* api to simplify code, this makes it unnecessary to explicitly
release resources.

Signed-off-by: Yangtao Li <frank.li@vivo.com>
Link: https://lore.kernel.org/r/20230714080611.81302-7-frank.li@vivo.com
Link: https://lore.kernel.org/r/20230724051345.335219-4-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/qt2160.c | 77 +++++++++------------------------
 1 file changed, 20 insertions(+), 57 deletions(-)

diff --git a/drivers/input/keyboard/qt2160.c b/drivers/input/keyboard/qt2160.c
index 6cfaabd10482..7e3b09642ab7 100644
--- a/drivers/input/keyboard/qt2160.c
+++ b/drivers/input/keyboard/qt2160.c
@@ -239,7 +239,7 @@ static int qt2160_write(struct i2c_client *client, u8 reg, u8 data)
 static int qt2160_register_leds(struct qt2160_data *qt2160)
 {
 	struct i2c_client *client = qt2160->client;
-	int ret;
+	int error;
 	int i;
 
 	for (i = 0; i < QT2160_NUM_LEDS_X; i++) {
@@ -252,9 +252,9 @@ static int qt2160_register_leds(struct qt2160_data *qt2160)
 		led->id = i;
 		led->qt2160 = qt2160;
 
-		ret = led_classdev_register(&client->dev, &led->cdev);
-		if (ret < 0)
-			return ret;
+		error = devm_led_classdev_register(&client->dev, &led->cdev);
+		if (error)
+			return error;
 	}
 
 	/* Tur off LEDs */
@@ -265,14 +265,6 @@ static int qt2160_register_leds(struct qt2160_data *qt2160)
 	return 0;
 }
 
-static void qt2160_unregister_leds(struct qt2160_data *qt2160)
-{
-	int i;
-
-	for (i = 0; i < QT2160_NUM_LEDS_X; i++)
-		led_classdev_unregister(&qt2160->leds[i].cdev);
-}
-
 #else
 
 static inline int qt2160_register_leds(struct qt2160_data *qt2160)
@@ -280,10 +272,6 @@ static inline int qt2160_register_leds(struct qt2160_data *qt2160)
 	return 0;
 }
 
-static inline void qt2160_unregister_leds(struct qt2160_data *qt2160)
-{
-}
-
 #endif
 
 static bool qt2160_identify(struct i2c_client *client)
@@ -334,13 +322,13 @@ static int qt2160_probe(struct i2c_client *client)
 		return -ENODEV;
 
 	/* Chip is valid and active. Allocate structure */
-	qt2160 = kzalloc(sizeof(struct qt2160_data), GFP_KERNEL);
-	input = input_allocate_device();
-	if (!qt2160 || !input) {
-		dev_err(&client->dev, "insufficient memory\n");
-		error = -ENOMEM;
-		goto err_free_mem;
-	}
+	qt2160 = devm_kzalloc(&client->dev, sizeof(*qt2160), GFP_KERNEL);
+	if (!qt2160)
+		return -ENOMEM;
+
+	input = devm_input_allocate_device(&client->dev);
+	if (!input)
+		return -ENOMEM;
 
 	qt2160->client = client;
 	qt2160->input = input;
@@ -366,22 +354,24 @@ static int qt2160_probe(struct i2c_client *client)
 	error = qt2160_write(client, QT2160_CMD_CALIBRATE, 1);
 	if (error) {
 		dev_err(&client->dev, "failed to calibrate device\n");
-		goto err_free_mem;
+		return error;
 	}
 
 	if (client->irq) {
-		error = request_threaded_irq(client->irq, NULL, qt2160_irq,
-					     IRQF_ONESHOT, "qt2160", input);
+		error = devm_request_threaded_irq(&client->dev, client->irq,
+						  NULL, qt2160_irq,
+						  IRQF_ONESHOT,
+						  "qt2160", input);
 		if (error) {
 			dev_err(&client->dev,
 				"failed to allocate irq %d\n", client->irq);
-			goto err_free_mem;
+			return error;
 		}
 	} else {
 		error = input_setup_polling(input, qt2160_get_key_matrix);
 		if (error) {
 			dev_err(&client->dev, "Failed to setup polling\n");
-			goto err_free_mem;
+			return error;
 		}
 		input_set_poll_interval(input, QT2160_CYCLE_INTERVAL);
 	}
@@ -389,43 +379,17 @@ static int qt2160_probe(struct i2c_client *client)
 	error = qt2160_register_leds(qt2160);
 	if (error) {
 		dev_err(&client->dev, "Failed to register leds\n");
-		goto err_free_irq;
+		return error;
 	}
 
 	error = input_register_device(qt2160->input);
 	if (error) {
 		dev_err(&client->dev,
 			"Failed to register input device\n");
-		goto err_unregister_leds;
+		return error;
 	}
 
-	i2c_set_clientdata(client, qt2160);
-
 	return 0;
-
-err_unregister_leds:
-	qt2160_unregister_leds(qt2160);
-err_free_irq:
-	if (client->irq)
-		free_irq(client->irq, qt2160);
-err_free_mem:
-	input_free_device(input);
-	kfree(qt2160);
-	return error;
-}
-
-static void qt2160_remove(struct i2c_client *client)
-{
-	struct qt2160_data *qt2160 = i2c_get_clientdata(client);
-
-	qt2160_unregister_leds(qt2160);
-
-	/* Release IRQ so no queue will be scheduled */
-	if (client->irq)
-		free_irq(client->irq, qt2160);
-
-	input_unregister_device(qt2160->input);
-	kfree(qt2160);
 }
 
 static const struct i2c_device_id qt2160_idtable[] = {
@@ -442,7 +406,6 @@ static struct i2c_driver qt2160_driver = {
 
 	.id_table	= qt2160_idtable,
 	.probe		= qt2160_probe,
-	.remove		= qt2160_remove,
 };
 
 module_i2c_driver(qt2160_driver);

From 0410595e23f8eb801301ee3e44597d3a780b6285 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sun, 23 Jul 2023 22:28:59 -0700
Subject: [PATCH 0213/1189] Input: lm8323 - rely on device core to create
 kp_disable attribute

Device core now has facilities to create driver-specific device attributes
as part of driver probing, use them.

Link: https://lore.kernel.org/r/20230724052901.350240-1-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/lm8323.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/input/keyboard/lm8323.c b/drivers/input/keyboard/lm8323.c
index 3964f6e0f6af..d5195415533a 100644
--- a/drivers/input/keyboard/lm8323.c
+++ b/drivers/input/keyboard/lm8323.c
@@ -615,6 +615,12 @@ static ssize_t lm8323_set_disable(struct device *dev,
 }
 static DEVICE_ATTR(disable_kp, 0644, lm8323_show_disable, lm8323_set_disable);
 
+static struct attribute *lm8323_attrs[] = {
+	&dev_attr_disable_kp.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(lm8323);
+
 static int lm8323_probe(struct i2c_client *client)
 {
 	struct lm8323_platform_data *pdata = dev_get_platdata(&client->dev);
@@ -696,9 +702,6 @@ static int lm8323_probe(struct i2c_client *client)
 	}
 
 	lm->kp_enabled = true;
-	err = device_create_file(&client->dev, &dev_attr_disable_kp);
-	if (err < 0)
-		goto fail2;
 
 	idev->name = pdata->name ? : "LM8323 keypad";
 	snprintf(lm->phys, sizeof(lm->phys),
@@ -719,14 +722,14 @@ static int lm8323_probe(struct i2c_client *client)
 	err = input_register_device(idev);
 	if (err) {
 		dev_dbg(&client->dev, "error registering input device\n");
-		goto fail3;
+		goto fail2;
 	}
 
 	err = request_threaded_irq(client->irq, NULL, lm8323_irq,
 			  IRQF_TRIGGER_LOW|IRQF_ONESHOT, "lm8323", lm);
 	if (err) {
 		dev_err(&client->dev, "could not get IRQ %d\n", client->irq);
-		goto fail4;
+		goto fail3;
 	}
 
 	i2c_set_clientdata(client, lm);
@@ -736,11 +739,9 @@ static int lm8323_probe(struct i2c_client *client)
 
 	return 0;
 
-fail4:
+fail3:
 	input_unregister_device(idev);
 	idev = NULL;
-fail3:
-	device_remove_file(&client->dev, &dev_attr_disable_kp);
 fail2:
 	while (--pwm >= 0)
 		if (lm->pwm[pwm].enabled)
@@ -761,8 +762,6 @@ static void lm8323_remove(struct i2c_client *client)
 
 	input_unregister_device(lm->idev);
 
-	device_remove_file(&lm->client->dev, &dev_attr_disable_kp);
-
 	for (i = 0; i < 3; i++)
 		if (lm->pwm[i].enabled)
 			led_classdev_unregister(&lm->pwm[i].cdev);
@@ -823,8 +822,9 @@ static const struct i2c_device_id lm8323_id[] = {
 
 static struct i2c_driver lm8323_i2c_driver = {
 	.driver = {
-		.name	= "lm8323",
-		.pm	= pm_sleep_ptr(&lm8323_pm_ops),
+		.name		= "lm8323",
+		.pm		= pm_sleep_ptr(&lm8323_pm_ops),
+		.dev_groups	= lm8323_groups,
 	},
 	.probe		= lm8323_probe,
 	.remove		= lm8323_remove,

From fe45d12745d61fd333e56c1c25c060350a520a39 Mon Sep 17 00:00:00 2001
From: Yangtao Li <frank.li@vivo.com>
Date: Sun, 23 Jul 2023 22:29:00 -0700
Subject: [PATCH 0214/1189] Input: lm8323 - convert to use devm_* api

Use devm_* api to simplify code, this makes it unnecessary to explicitly
release resources.

Signed-off-by: Yangtao Li <frank.li@vivo.com>
Link: https://lore.kernel.org/r/20230724052901.350240-2-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/lm8323.c | 77 +++++++++++----------------------
 1 file changed, 26 insertions(+), 51 deletions(-)

diff --git a/drivers/input/keyboard/lm8323.c b/drivers/input/keyboard/lm8323.c
index d5195415533a..7bee93e9b0f5 100644
--- a/drivers/input/keyboard/lm8323.c
+++ b/drivers/input/keyboard/lm8323.c
@@ -556,6 +556,7 @@ static int init_pwm(struct lm8323_chip *lm, int id, struct device *dev,
 		    const char *name)
 {
 	struct lm8323_pwm *pwm;
+	int err;
 
 	BUG_ON(id > 3);
 
@@ -575,9 +576,11 @@ static int init_pwm(struct lm8323_chip *lm, int id, struct device *dev,
 		pwm->cdev.name = name;
 		pwm->cdev.brightness_set = lm8323_pwm_set_brightness;
 		pwm->cdev.groups = lm8323_pwm_groups;
-		if (led_classdev_register(dev, &pwm->cdev) < 0) {
-			dev_err(dev, "couldn't register PWM %d\n", id);
-			return -1;
+
+		err = devm_led_classdev_register(dev, &pwm->cdev);
+		if (err) {
+			dev_err(dev, "couldn't register PWM %d: %d\n", id, err);
+			return err;
 		}
 		pwm->enabled = true;
 	}
@@ -585,8 +588,6 @@ static int init_pwm(struct lm8323_chip *lm, int id, struct device *dev,
 	return 0;
 }
 
-static struct i2c_driver lm8323_i2c_driver;
-
 static ssize_t lm8323_show_disable(struct device *dev,
 				   struct device_attribute *attr, char *buf)
 {
@@ -648,12 +649,13 @@ static int lm8323_probe(struct i2c_client *client)
 		return -EINVAL;
 	}
 
-	lm = kzalloc(sizeof *lm, GFP_KERNEL);
-	idev = input_allocate_device();
-	if (!lm || !idev) {
-		err = -ENOMEM;
-		goto fail1;
-	}
+	lm = devm_kzalloc(&client->dev, sizeof(*lm), GFP_KERNEL);
+	if (!lm)
+		return -ENOMEM;
+
+	idev = devm_input_allocate_device(&client->dev);
+	if (!idev)
+		return -ENOMEM;
 
 	lm->client = client;
 	lm->idev = idev;
@@ -669,8 +671,10 @@ static int lm8323_probe(struct i2c_client *client)
 
 	lm8323_reset(lm);
 
-	/* Nothing's set up to service the IRQ yet, so just spin for max.
-	 * 100ms until we can configure. */
+	/*
+	 * Nothing's set up to service the IRQ yet, so just spin for max.
+	 * 100ms until we can configure.
+	 */
 	tmo = jiffies + msecs_to_jiffies(100);
 	while (lm8323_read(lm, LM8323_CMD_READ_INT, data, 1) == 1) {
 		if (data[0] & INT_NOINIT)
@@ -690,15 +694,14 @@ static int lm8323_probe(struct i2c_client *client)
 	/* If a true probe check the device */
 	if (lm8323_read_id(lm, data) != 0) {
 		dev_err(&client->dev, "device not found\n");
-		err = -ENODEV;
-		goto fail1;
+		return -ENODEV;
 	}
 
 	for (pwm = 0; pwm < LM8323_NUM_PWMS; pwm++) {
 		err = init_pwm(lm, pwm + 1, &client->dev,
 			       pdata->pwm_names[pwm]);
-		if (err < 0)
-			goto fail2;
+		if (err)
+			return err;
 	}
 
 	lm->kp_enabled = true;
@@ -722,14 +725,16 @@ static int lm8323_probe(struct i2c_client *client)
 	err = input_register_device(idev);
 	if (err) {
 		dev_dbg(&client->dev, "error registering input device\n");
-		goto fail2;
+		return err;
 	}
 
-	err = request_threaded_irq(client->irq, NULL, lm8323_irq,
-			  IRQF_TRIGGER_LOW|IRQF_ONESHOT, "lm8323", lm);
+	err = devm_request_threaded_irq(&client->dev, client->irq,
+					NULL, lm8323_irq,
+					IRQF_TRIGGER_LOW | IRQF_ONESHOT,
+					"lm8323", lm);
 	if (err) {
 		dev_err(&client->dev, "could not get IRQ %d\n", client->irq);
-		goto fail3;
+		return err;
 	}
 
 	i2c_set_clientdata(client, lm);
@@ -738,35 +743,6 @@ static int lm8323_probe(struct i2c_client *client)
 	enable_irq_wake(client->irq);
 
 	return 0;
-
-fail3:
-	input_unregister_device(idev);
-	idev = NULL;
-fail2:
-	while (--pwm >= 0)
-		if (lm->pwm[pwm].enabled)
-			led_classdev_unregister(&lm->pwm[pwm].cdev);
-fail1:
-	input_free_device(idev);
-	kfree(lm);
-	return err;
-}
-
-static void lm8323_remove(struct i2c_client *client)
-{
-	struct lm8323_chip *lm = i2c_get_clientdata(client);
-	int i;
-
-	disable_irq_wake(client->irq);
-	free_irq(client->irq, lm);
-
-	input_unregister_device(lm->idev);
-
-	for (i = 0; i < 3; i++)
-		if (lm->pwm[i].enabled)
-			led_classdev_unregister(&lm->pwm[i].cdev);
-
-	kfree(lm);
 }
 
 /*
@@ -827,7 +803,6 @@ static struct i2c_driver lm8323_i2c_driver = {
 		.dev_groups	= lm8323_groups,
 	},
 	.probe		= lm8323_probe,
-	.remove		= lm8323_remove,
 	.id_table	= lm8323_id,
 };
 MODULE_DEVICE_TABLE(i2c, lm8323_id);

From 687fe7dfb736b03ab820d172ea5dbfc1ec447135 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sun, 23 Jul 2023 22:30:18 -0700
Subject: [PATCH 0215/1189] Input: tca6416-keypad - always expect proper IRQ
 number in i2c client

Remove option having i2c client contain raw gpio number instead of proper
IRQ number. There are no users of this facility in mainline and it will
allow cleaning up the driver code with regard to wakeup handling, etc.

Link: https://lore.kernel.org/r/20230724053024.352054-1-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/tca6416-keypad.c | 27 +++++++++----------------
 include/linux/tca6416_keypad.h          |  1 -
 2 files changed, 10 insertions(+), 18 deletions(-)

diff --git a/drivers/input/keyboard/tca6416-keypad.c b/drivers/input/keyboard/tca6416-keypad.c
index 2f745cabf4f2..01bc0b881188 100644
--- a/drivers/input/keyboard/tca6416-keypad.c
+++ b/drivers/input/keyboard/tca6416-keypad.c
@@ -148,7 +148,7 @@ static int tca6416_keys_open(struct input_dev *dev)
 	if (chip->use_polling)
 		schedule_delayed_work(&chip->dwork, msecs_to_jiffies(100));
 	else
-		enable_irq(chip->irqnum);
+		enable_irq(chip->client->irq);
 
 	return 0;
 }
@@ -160,7 +160,7 @@ static void tca6416_keys_close(struct input_dev *dev)
 	if (chip->use_polling)
 		cancel_delayed_work_sync(&chip->dwork);
 	else
-		disable_irq(chip->irqnum);
+		disable_irq(chip->client->irq);
 }
 
 static int tca6416_setup_registers(struct tca6416_keypad_chip *chip)
@@ -266,12 +266,7 @@ static int tca6416_keypad_probe(struct i2c_client *client)
 		goto fail1;
 
 	if (!chip->use_polling) {
-		if (pdata->irq_is_gpio)
-			chip->irqnum = gpio_to_irq(client->irq);
-		else
-			chip->irqnum = client->irq;
-
-		error = request_threaded_irq(chip->irqnum, NULL,
+		error = request_threaded_irq(client->irq, NULL,
 					     tca6416_keys_isr,
 					     IRQF_TRIGGER_FALLING |
 					     IRQF_ONESHOT | IRQF_NO_AUTOEN,
@@ -279,7 +274,7 @@ static int tca6416_keypad_probe(struct i2c_client *client)
 		if (error) {
 			dev_dbg(&client->dev,
 				"Unable to claim irq %d; error %d\n",
-				chip->irqnum, error);
+				client->irq, error);
 			goto fail1;
 		}
 	}
@@ -298,8 +293,8 @@ static int tca6416_keypad_probe(struct i2c_client *client)
 
 fail2:
 	if (!chip->use_polling) {
-		free_irq(chip->irqnum, chip);
-		enable_irq(chip->irqnum);
+		free_irq(client->irq, chip);
+		enable_irq(client->irq);
 	}
 fail1:
 	input_free_device(input);
@@ -312,8 +307,8 @@ static void tca6416_keypad_remove(struct i2c_client *client)
 	struct tca6416_keypad_chip *chip = i2c_get_clientdata(client);
 
 	if (!chip->use_polling) {
-		free_irq(chip->irqnum, chip);
-		enable_irq(chip->irqnum);
+		free_irq(client->irq, chip);
+		enable_irq(client->irq);
 	}
 
 	input_unregister_device(chip->input);
@@ -323,10 +318,9 @@ static void tca6416_keypad_remove(struct i2c_client *client)
 static int tca6416_keypad_suspend(struct device *dev)
 {
 	struct i2c_client *client = to_i2c_client(dev);
-	struct tca6416_keypad_chip *chip = i2c_get_clientdata(client);
 
 	if (device_may_wakeup(dev))
-		enable_irq_wake(chip->irqnum);
+		enable_irq_wake(client->irq);
 
 	return 0;
 }
@@ -334,10 +328,9 @@ static int tca6416_keypad_suspend(struct device *dev)
 static int tca6416_keypad_resume(struct device *dev)
 {
 	struct i2c_client *client = to_i2c_client(dev);
-	struct tca6416_keypad_chip *chip = i2c_get_clientdata(client);
 
 	if (device_may_wakeup(dev))
-		disable_irq_wake(chip->irqnum);
+		disable_irq_wake(client->irq);
 
 	return 0;
 }
diff --git a/include/linux/tca6416_keypad.h b/include/linux/tca6416_keypad.h
index b0d36a9934cc..5cf6f6f82aa7 100644
--- a/include/linux/tca6416_keypad.h
+++ b/include/linux/tca6416_keypad.h
@@ -25,7 +25,6 @@ struct tca6416_keys_platform_data {
 	unsigned int rep:1;	/* enable input subsystem auto repeat */
 	uint16_t pinmask;
 	uint16_t invert;
-	int irq_is_gpio;
 	int use_polling;	/* use polling if Interrupt is not connected*/
 };
 #endif

From d3176b29263aa8211830c77d87a806066c2c178c Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sun, 23 Jul 2023 22:30:19 -0700
Subject: [PATCH 0216/1189] Input: tca6416-keypad - rely on I2C core to set up
 suspend/resume

tca6416_keypad_suspend() and tca6416_keypad_resume() only configure device
IRQ for wakeup. I2C core already does this by registering interrupt as a
wakeup IRQ in case when device is marked as wakeup-enabled, so we can
simply remove this code from the driver.

Link: https://lore.kernel.org/r/20230724053024.352054-2-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/tca6416-keypad.c | 25 -------------------------
 1 file changed, 25 deletions(-)

diff --git a/drivers/input/keyboard/tca6416-keypad.c b/drivers/input/keyboard/tca6416-keypad.c
index 01bc0b881188..906dffbf171c 100644
--- a/drivers/input/keyboard/tca6416-keypad.c
+++ b/drivers/input/keyboard/tca6416-keypad.c
@@ -287,7 +287,6 @@ static int tca6416_keypad_probe(struct i2c_client *client)
 	}
 
 	i2c_set_clientdata(client, chip);
-	device_init_wakeup(&client->dev, 1);
 
 	return 0;
 
@@ -315,33 +314,9 @@ static void tca6416_keypad_remove(struct i2c_client *client)
 	kfree(chip);
 }
 
-static int tca6416_keypad_suspend(struct device *dev)
-{
-	struct i2c_client *client = to_i2c_client(dev);
-
-	if (device_may_wakeup(dev))
-		enable_irq_wake(client->irq);
-
-	return 0;
-}
-
-static int tca6416_keypad_resume(struct device *dev)
-{
-	struct i2c_client *client = to_i2c_client(dev);
-
-	if (device_may_wakeup(dev))
-		disable_irq_wake(client->irq);
-
-	return 0;
-}
-
-static DEFINE_SIMPLE_DEV_PM_OPS(tca6416_keypad_dev_pm_ops,
-				tca6416_keypad_suspend, tca6416_keypad_resume);
-
 static struct i2c_driver tca6416_keypad_driver = {
 	.driver = {
 		.name	= "tca6416-keypad",
-		.pm	= pm_sleep_ptr(&tca6416_keypad_dev_pm_ops),
 	},
 	.probe		= tca6416_keypad_probe,
 	.remove		= tca6416_keypad_remove,

From cc141c35af873c6796e043adcb820833bd8ef8c5 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sun, 23 Jul 2023 22:30:20 -0700
Subject: [PATCH 0217/1189] Input: tca6416-keypad - fix interrupt enable
 disbalance

The driver has been switched to use IRQF_NO_AUTOEN, but in the error
unwinding and remove paths calls to enable_irq() were left in place, which
will lead to an incorrect enable counter value.

Fixes: bcd9730a04a1 ("Input: move to use request_irq by IRQF_NO_AUTOEN flag")
Link: https://lore.kernel.org/r/20230724053024.352054-3-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/tca6416-keypad.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/input/keyboard/tca6416-keypad.c b/drivers/input/keyboard/tca6416-keypad.c
index 906dffbf171c..21a2f2de4345 100644
--- a/drivers/input/keyboard/tca6416-keypad.c
+++ b/drivers/input/keyboard/tca6416-keypad.c
@@ -291,10 +291,8 @@ static int tca6416_keypad_probe(struct i2c_client *client)
 	return 0;
 
 fail2:
-	if (!chip->use_polling) {
+	if (!chip->use_polling)
 		free_irq(client->irq, chip);
-		enable_irq(client->irq);
-	}
 fail1:
 	input_free_device(input);
 	kfree(chip);
@@ -305,10 +303,8 @@ static void tca6416_keypad_remove(struct i2c_client *client)
 {
 	struct tca6416_keypad_chip *chip = i2c_get_clientdata(client);
 
-	if (!chip->use_polling) {
+	if (!chip->use_polling)
 		free_irq(client->irq, chip);
-		enable_irq(client->irq);
-	}
 
 	input_unregister_device(chip->input);
 	kfree(chip);

From 91a4c69052bb660bc818878309d8a777e635a144 Mon Sep 17 00:00:00 2001
From: Yangtao Li <frank.li@vivo.com>
Date: Sun, 23 Jul 2023 22:30:21 -0700
Subject: [PATCH 0218/1189] Input: tca6416-keypad - convert to use devm_* api

Use devm_* api to simplify code, this makes it unnecessary to explicitly
release resources.

Signed-off-by: Yangtao Li <frank.li@vivo.com>
Link: https://lore.kernel.org/r/20230724053024.352054-4-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/tca6416-keypad.c | 53 +++++++++----------------
 1 file changed, 18 insertions(+), 35 deletions(-)

diff --git a/drivers/input/keyboard/tca6416-keypad.c b/drivers/input/keyboard/tca6416-keypad.c
index 21a2f2de4345..ff665319791e 100644
--- a/drivers/input/keyboard/tca6416-keypad.c
+++ b/drivers/input/keyboard/tca6416-keypad.c
@@ -216,12 +216,15 @@ static int tca6416_keypad_probe(struct i2c_client *client)
 		return -EINVAL;
 	}
 
-	chip = kzalloc(struct_size(chip, buttons, pdata->nbuttons), GFP_KERNEL);
-	input = input_allocate_device();
-	if (!chip || !input) {
-		error = -ENOMEM;
-		goto fail1;
-	}
+	chip = devm_kzalloc(&client->dev,
+			    struct_size(chip, buttons, pdata->nbuttons),
+			    GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	input = devm_input_allocate_device(&client->dev);
+	if (!input)
+		return -ENOMEM;
 
 	chip->client = client;
 	chip->input = input;
@@ -233,7 +236,6 @@ static int tca6416_keypad_probe(struct i2c_client *client)
 
 	input->phys = "tca6416-keys/input0";
 	input->name = client->name;
-	input->dev.parent = &client->dev;
 
 	input->open = tca6416_keys_open;
 	input->close = tca6416_keys_close;
@@ -263,19 +265,20 @@ static int tca6416_keypad_probe(struct i2c_client *client)
 	 */
 	error = tca6416_setup_registers(chip);
 	if (error)
-		goto fail1;
+		return error;
 
 	if (!chip->use_polling) {
-		error = request_threaded_irq(client->irq, NULL,
-					     tca6416_keys_isr,
-					     IRQF_TRIGGER_FALLING |
-					     IRQF_ONESHOT | IRQF_NO_AUTOEN,
-					     "tca6416-keypad", chip);
+		error = devm_request_threaded_irq(&client->dev, client->irq,
+						  NULL, tca6416_keys_isr,
+						  IRQF_TRIGGER_FALLING |
+							IRQF_ONESHOT |
+							IRQF_NO_AUTOEN,
+						  "tca6416-keypad", chip);
 		if (error) {
 			dev_dbg(&client->dev,
 				"Unable to claim irq %d; error %d\n",
 				client->irq, error);
-			goto fail1;
+			return error;
 		}
 	}
 
@@ -283,31 +286,12 @@ static int tca6416_keypad_probe(struct i2c_client *client)
 	if (error) {
 		dev_dbg(&client->dev,
 			"Unable to register input device, error: %d\n", error);
-		goto fail2;
+		return error;
 	}
 
 	i2c_set_clientdata(client, chip);
 
 	return 0;
-
-fail2:
-	if (!chip->use_polling)
-		free_irq(client->irq, chip);
-fail1:
-	input_free_device(input);
-	kfree(chip);
-	return error;
-}
-
-static void tca6416_keypad_remove(struct i2c_client *client)
-{
-	struct tca6416_keypad_chip *chip = i2c_get_clientdata(client);
-
-	if (!chip->use_polling)
-		free_irq(client->irq, chip);
-
-	input_unregister_device(chip->input);
-	kfree(chip);
 }
 
 static struct i2c_driver tca6416_keypad_driver = {
@@ -315,7 +299,6 @@ static struct i2c_driver tca6416_keypad_driver = {
 		.name	= "tca6416-keypad",
 	},
 	.probe		= tca6416_keypad_probe,
-	.remove		= tca6416_keypad_remove,
 	.id_table	= tca6416_id,
 };
 

From 57b0c96f1e34f550ec7c6699e81a6cfce7857159 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sun, 23 Jul 2023 22:30:22 -0700
Subject: [PATCH 0219/1189] Input: tca6416-keypad - switch to using input
 core's polling features

Instead of rolling custom polling implementation use input core
facilities.

Link: https://lore.kernel.org/r/20230724053024.352054-5-dmitry.torokhov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/tca6416-keypad.c | 48 +++++++++++--------------
 1 file changed, 20 insertions(+), 28 deletions(-)

diff --git a/drivers/input/keyboard/tca6416-keypad.c b/drivers/input/keyboard/tca6416-keypad.c
index ff665319791e..8af59ced1ec2 100644
--- a/drivers/input/keyboard/tca6416-keypad.c
+++ b/drivers/input/keyboard/tca6416-keypad.c
@@ -24,6 +24,8 @@
 #define TCA6416_INVERT         2
 #define TCA6416_DIRECTION      3
 
+#define TCA6416_POLL_INTERVAL	100 /* msec */
+
 static const struct i2c_device_id tca6416_id[] = {
 	{ "tca6416-keys", 16, },
 	{ "tca6408-keys", 8, },
@@ -43,7 +45,6 @@ struct tca6416_keypad_chip {
 
 	struct i2c_client *client;
 	struct input_dev *input;
-	struct delayed_work dwork;
 	int io_size;
 	int irqnum;
 	u16 pinmask;
@@ -85,9 +86,9 @@ static int tca6416_read_reg(struct tca6416_keypad_chip *chip, int reg, u16 *val)
 	return 0;
 }
 
-static void tca6416_keys_scan(struct tca6416_keypad_chip *chip)
+static void tca6416_keys_scan(struct input_dev *input)
 {
-	struct input_dev *input = chip->input;
+	struct tca6416_keypad_chip *chip = input_get_drvdata(input);
 	u16 reg_val, val;
 	int error, i, pin_index;
 
@@ -122,33 +123,20 @@ static void tca6416_keys_scan(struct tca6416_keypad_chip *chip)
  */
 static irqreturn_t tca6416_keys_isr(int irq, void *dev_id)
 {
-	struct tca6416_keypad_chip *chip = dev_id;
-
-	tca6416_keys_scan(chip);
+	tca6416_keys_scan(dev_id);
 
 	return IRQ_HANDLED;
 }
 
-static void tca6416_keys_work_func(struct work_struct *work)
-{
-	struct tca6416_keypad_chip *chip =
-		container_of(work, struct tca6416_keypad_chip, dwork.work);
-
-	tca6416_keys_scan(chip);
-	schedule_delayed_work(&chip->dwork, msecs_to_jiffies(100));
-}
-
 static int tca6416_keys_open(struct input_dev *dev)
 {
 	struct tca6416_keypad_chip *chip = input_get_drvdata(dev);
 
-	/* Get initial device state in case it has switches */
-	tca6416_keys_scan(chip);
-
-	if (chip->use_polling)
-		schedule_delayed_work(&chip->dwork, msecs_to_jiffies(100));
-	else
+	if (!chip->use_polling) {
+		/* Get initial device state in case it has switches */
+		tca6416_keys_scan(dev);
 		enable_irq(chip->client->irq);
+	}
 
 	return 0;
 }
@@ -157,9 +145,7 @@ static void tca6416_keys_close(struct input_dev *dev)
 {
 	struct tca6416_keypad_chip *chip = input_get_drvdata(dev);
 
-	if (chip->use_polling)
-		cancel_delayed_work_sync(&chip->dwork);
-	else
+	if (!chip->use_polling)
 		disable_irq(chip->client->irq);
 }
 
@@ -232,8 +218,6 @@ static int tca6416_keypad_probe(struct i2c_client *client)
 	chip->pinmask = pdata->pinmask;
 	chip->use_polling = pdata->use_polling;
 
-	INIT_DELAYED_WORK(&chip->dwork, tca6416_keys_work_func);
-
 	input->phys = "tca6416-keys/input0";
 	input->name = client->name;
 
@@ -267,13 +251,21 @@ static int tca6416_keypad_probe(struct i2c_client *client)
 	if (error)
 		return error;
 
-	if (!chip->use_polling) {
+	if (chip->use_polling) {
+		error = input_setup_polling(input, tca6416_keys_scan);
+		if (error) {
+			dev_err(&client->dev, "Failed to setup polling\n");
+			return error;
+		}
+
+		input_set_poll_interval(input, TCA6416_POLL_INTERVAL);
+	} else {
 		error = devm_request_threaded_irq(&client->dev, client->irq,
 						  NULL, tca6416_keys_isr,
 						  IRQF_TRIGGER_FALLING |
 							IRQF_ONESHOT |
 							IRQF_NO_AUTOEN,
-						  "tca6416-keypad", chip);
+						  "tca6416-keypad", input);
 		if (error) {
 			dev_dbg(&client->dev,
 				"Unable to claim irq %d; error %d\n",

From 1d6664fadda3e028b8220ba1ba487a928e801825 Mon Sep 17 00:00:00 2001
From: Like Xu <likexu@tencent.com>
Date: Sun, 25 Jun 2023 15:34:38 +0800
Subject: [PATCH 0220/1189] KVM: x86: Use sysfs_emit() instead of sprintf()

Use sysfs_emit() instead of the sprintf() for sysfs entries. sysfs_emit()
knows the maximum of the temporary buffer used for outputting sysfs
content and avoids overrunning the buffer length.

Signed-off-by: Like Xu <likexu@tencent.com>
Link: https://lore.kernel.org/r/20230625073438.57427-1-likexu@tencent.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/mmu/mmu.c | 2 +-
 arch/x86/kvm/vmx/vmx.c | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index ec169f5c7dce..31d9cbe817a2 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -6862,7 +6862,7 @@ static void mmu_destroy_caches(void)
 static int get_nx_huge_pages(char *buffer, const struct kernel_param *kp)
 {
 	if (nx_hugepage_mitigation_hard_disabled)
-		return sprintf(buffer, "never\n");
+		return sysfs_emit(buffer, "never\n");
 
 	return param_get_bool(buffer, kp);
 }
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 0ecf4be2c6af..254f2296e549 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -366,9 +366,9 @@ static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp)
 static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp)
 {
 	if (WARN_ON_ONCE(l1tf_vmx_mitigation >= ARRAY_SIZE(vmentry_l1d_param)))
-		return sprintf(s, "???\n");
+		return sysfs_emit(s, "???\n");
 
-	return sprintf(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option);
+	return sysfs_emit(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option);
 }
 
 static void vmx_setup_fb_clear_ctrl(void)

From 54116d442e001e1b6bd482122043b1870998a1f3 Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Tue, 1 Aug 2023 16:44:52 -0700
Subject: [PATCH 0221/1189] Input: rpckbd - fix the return value handle for
 platform_get_irq()

There is no possible for platform_get_irq() to return 0,
and the return value of platform_get_irq() is more sensible
to show the error reason.

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Link: https://lore.kernel.org/r/20230731122246.2028651-1-ruanjinjie@huawei.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/rpckbd.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/input/serio/rpckbd.c b/drivers/input/serio/rpckbd.c
index ce420eb1f51b..e8a9709f32eb 100644
--- a/drivers/input/serio/rpckbd.c
+++ b/drivers/input/serio/rpckbd.c
@@ -101,12 +101,12 @@ static int rpckbd_probe(struct platform_device *dev)
 	int tx_irq, rx_irq;
 
 	rx_irq = platform_get_irq(dev, 0);
-	if (rx_irq <= 0)
-		return rx_irq < 0 ? rx_irq : -ENXIO;
+	if (rx_irq < 0)
+		return rx_irq;
 
 	tx_irq = platform_get_irq(dev, 1);
-	if (tx_irq <= 0)
-		return tx_irq < 0 ? tx_irq : -ENXIO;
+	if (tx_irq < 0)
+		return tx_irq;
 
 	serio = kzalloc(sizeof(struct serio), GFP_KERNEL);
 	rpckbd = kzalloc(sizeof(*rpckbd), GFP_KERNEL);

From 0d033770d43a7aa36025bcef9a60da7fb750f735 Mon Sep 17 00:00:00 2001
From: Michal Luczaj <mhal@rbox.co>
Date: Fri, 28 Jul 2023 02:12:57 +0200
Subject: [PATCH 0222/1189] KVM: x86: Fix KVM_CAP_SYNC_REGS's sync_regs()
 TOCTOU issues

In a spirit of using a sledgehammer to crack a nut, make sync_regs() feed
__set_sregs() and kvm_vcpu_ioctl_x86_set_vcpu_events() with kernel's own
copy of data.

Both __set_sregs() and kvm_vcpu_ioctl_x86_set_vcpu_events() assume they
have exclusive rights to structs they operate on. While this is true when
coming from an ioctl handler (caller makes a local copy of user's data),
sync_regs() breaks this contract; a pointer to a user-modifiable memory
(vcpu->run->s.regs) is provided. This can lead to a situation when incoming
data is checked and/or sanitized only to be re-set by a user thread running
in parallel.

Signed-off-by: Michal Luczaj <mhal@rbox.co>
Fixes: 01643c51bfcf ("KVM: x86: KVM_CAP_SYNC_REGS")
Link: https://lore.kernel.org/r/20230728001606.2275586-2-mhal@rbox.co
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/x86.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a6b9bea62fb8..0145d844283b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -11777,15 +11777,22 @@ static int sync_regs(struct kvm_vcpu *vcpu)
 		__set_regs(vcpu, &vcpu->run->s.regs.regs);
 		vcpu->run->kvm_dirty_regs &= ~KVM_SYNC_X86_REGS;
 	}
+
 	if (vcpu->run->kvm_dirty_regs & KVM_SYNC_X86_SREGS) {
-		if (__set_sregs(vcpu, &vcpu->run->s.regs.sregs))
+		struct kvm_sregs sregs = vcpu->run->s.regs.sregs;
+
+		if (__set_sregs(vcpu, &sregs))
 			return -EINVAL;
+
 		vcpu->run->kvm_dirty_regs &= ~KVM_SYNC_X86_SREGS;
 	}
+
 	if (vcpu->run->kvm_dirty_regs & KVM_SYNC_X86_EVENTS) {
-		if (kvm_vcpu_ioctl_x86_set_vcpu_events(
-				vcpu, &vcpu->run->s.regs.events))
+		struct kvm_vcpu_events events = vcpu->run->s.regs.events;
+
+		if (kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events))
 			return -EINVAL;
+
 		vcpu->run->kvm_dirty_regs &= ~KVM_SYNC_X86_EVENTS;
 	}
 

From ae895cbe613a5b193f3953c90c075306bfa4d30b Mon Sep 17 00:00:00 2001
From: Michal Luczaj <mhal@rbox.co>
Date: Fri, 28 Jul 2023 02:12:58 +0200
Subject: [PATCH 0223/1189] KVM: selftests: Extend x86's sync_regs_test to
 check for CR4 races

Attempt to modify vcpu->run->s.regs _after_ the sanity checks performed by
KVM_CAP_SYNC_REGS's arch/x86/kvm/x86.c:sync_regs().  This can lead to some
nonsensical vCPU states accompanied by kernel splats, e.g. disabling PAE
while long mode is enabled makes KVM all kinds of confused:

 WARNING: CPU: 0 PID: 1142 at arch/x86/kvm/mmu/paging_tmpl.h:358 paging32_walk_addr_generic+0x431/0x8f0 [kvm]

 arch/x86/kvm/mmu/paging_tmpl.h:
 KVM_BUG_ON(is_long_mode(vcpu) && !is_pae(vcpu), vcpu->kvm)

Signed-off-by: Michal Luczaj <mhal@rbox.co>
Link: https://lore.kernel.org/r/20230728001606.2275586-3-mhal@rbox.co
[sean: see link]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../selftests/kvm/x86_64/sync_regs_test.c     | 72 +++++++++++++++++++
 1 file changed, 72 insertions(+)

diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
index 2da89fdc2471..13ac3ae8e704 100644
--- a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
@@ -15,6 +15,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <sys/ioctl.h>
+#include <pthread.h>
 
 #include "test_util.h"
 #include "kvm_util.h"
@@ -80,6 +81,75 @@ static void compare_vcpu_events(struct kvm_vcpu_events *left,
 #define TEST_SYNC_FIELDS   (KVM_SYNC_X86_REGS|KVM_SYNC_X86_SREGS|KVM_SYNC_X86_EVENTS)
 #define INVALID_SYNC_FIELD 0x80000000
 
+/*
+ * Toggle CR4.PAE while KVM is processing SREGS, EFER.LME=1 with CR4.PAE=0 is
+ * illegal, and KVM's MMU heavily relies on vCPU state being valid.
+ */
+static noinline void *race_sregs_cr4(void *arg)
+{
+	struct kvm_run *run = (struct kvm_run *)arg;
+	__u64 *cr4 = &run->s.regs.sregs.cr4;
+	__u64 pae_enabled = *cr4;
+	__u64 pae_disabled = *cr4 & ~X86_CR4_PAE;
+
+	for (;;) {
+		WRITE_ONCE(run->kvm_dirty_regs, KVM_SYNC_X86_SREGS);
+		WRITE_ONCE(*cr4, pae_enabled);
+		asm volatile(".rept 512\n\t"
+			     "nop\n\t"
+			     ".endr");
+		WRITE_ONCE(*cr4, pae_disabled);
+
+		pthread_testcancel();
+	}
+
+	return NULL;
+}
+
+static void race_sync_regs(void *racer)
+{
+	const time_t TIMEOUT = 2; /* seconds, roughly */
+	struct kvm_translation tr;
+	struct kvm_vcpu *vcpu;
+	struct kvm_run *run;
+	struct kvm_vm *vm;
+	pthread_t thread;
+	time_t t;
+
+	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
+	run = vcpu->run;
+
+	run->kvm_valid_regs = KVM_SYNC_X86_SREGS;
+	vcpu_run(vcpu);
+	run->kvm_valid_regs = 0;
+
+	/*
+	 * Selftests run 64-bit guests by default, both EFER.LME and CR4.PAE
+	 * should already be set in guest state.
+	 */
+	TEST_ASSERT((run->s.regs.sregs.cr4 & X86_CR4_PAE) &&
+		    (run->s.regs.sregs.efer & EFER_LME),
+		    "vCPU should be in long mode, CR4.PAE=%d, EFER.LME=%d",
+		    !!(run->s.regs.sregs.cr4 & X86_CR4_PAE),
+		    !!(run->s.regs.sregs.efer & EFER_LME));
+
+	ASSERT_EQ(pthread_create(&thread, NULL, racer, (void *)run), 0);
+
+	for (t = time(NULL) + TIMEOUT; time(NULL) < t;) {
+		__vcpu_run(vcpu);
+
+		if (racer == race_sregs_cr4) {
+			tr = (struct kvm_translation) { .linear_address = 0 };
+			__vcpu_ioctl(vcpu, KVM_TRANSLATE, &tr);
+		}
+	}
+
+	ASSERT_EQ(pthread_cancel(thread), 0);
+	ASSERT_EQ(pthread_join(thread, NULL), 0);
+
+	kvm_vm_free(vm);
+}
+
 int main(int argc, char *argv[])
 {
 	struct kvm_vcpu *vcpu;
@@ -218,5 +288,7 @@ int main(int argc, char *argv[])
 
 	kvm_vm_free(vm);
 
+	race_sync_regs(race_sregs_cr4);
+
 	return 0;
 }

From 60c4063b475215321fc63ab253c9a840bb664f35 Mon Sep 17 00:00:00 2001
From: Michal Luczaj <mhal@rbox.co>
Date: Fri, 28 Jul 2023 02:12:58 +0200
Subject: [PATCH 0224/1189] KVM: selftests: Extend x86's sync_regs_test to
 check for event vector races

Attempt to modify the to-be-injected exception vector to an illegal value
_after_ the sanity checks performed by KVM_CAP_SYNC_REGS's
arch/x86/kvm/x86.c:kvm_vcpu_ioctl_x86_set_vcpu_events().  Buggy KVM
versions will eventually yells loudly about attempting to inject a bogus
vector, e.g.

  WARNING: CPU: 0 PID: 1107 at arch/x86/kvm/x86.c:547 kvm_check_and_inject_events+0x4a0/0x500 [kvm]

  arch/x86/kvm/x86.c:exception_type():
  WARN_ON(vector > 31 || vector == NMI_VECTOR)

Signed-off-by: Michal Luczaj <mhal@rbox.co>
Link: https://lore.kernel.org/r/20230728001606.2275586-3-mhal@rbox.co
[sean: split to separate patch]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../selftests/kvm/x86_64/sync_regs_test.c     | 22 +++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
index 13ac3ae8e704..e4ff2eaad7cd 100644
--- a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
@@ -81,6 +81,27 @@ static void compare_vcpu_events(struct kvm_vcpu_events *left,
 #define TEST_SYNC_FIELDS   (KVM_SYNC_X86_REGS|KVM_SYNC_X86_SREGS|KVM_SYNC_X86_EVENTS)
 #define INVALID_SYNC_FIELD 0x80000000
 
+/*
+ * Set an invalid exception vector while KVM is processing events.  KVM is
+ * supposed to reject any vector >= 32, as well as NMIs (vector 2).
+ */
+static void *race_events_exc(void *arg)
+{
+	struct kvm_run *run = (struct kvm_run *)arg;
+	struct kvm_vcpu_events *events = &run->s.regs.events;
+
+	for (;;) {
+		WRITE_ONCE(run->kvm_dirty_regs, KVM_SYNC_X86_EVENTS);
+		WRITE_ONCE(events->flags, 0);
+		WRITE_ONCE(events->exception.pending, 1);
+		WRITE_ONCE(events->exception.nr, 255);
+
+		pthread_testcancel();
+	}
+
+	return NULL;
+}
+
 /*
  * Toggle CR4.PAE while KVM is processing SREGS, EFER.LME=1 with CR4.PAE=0 is
  * illegal, and KVM's MMU heavily relies on vCPU state being valid.
@@ -289,6 +310,7 @@ int main(int argc, char *argv[])
 	kvm_vm_free(vm);
 
 	race_sync_regs(race_sregs_cr4);
+	race_sync_regs(race_events_exc);
 
 	return 0;
 }

From 0de704d2d6c82c7498fa1b8df66903f8139e3de2 Mon Sep 17 00:00:00 2001
From: Michal Luczaj <mhal@rbox.co>
Date: Fri, 28 Jul 2023 02:12:58 +0200
Subject: [PATCH 0225/1189] KVM: selftests: Extend x86's sync_regs_test to
 check for exception races

Attempt to set the to-be-queued exception to be both pending and injected
_after_ KVM_CAP_SYNC_REGS's kvm_vcpu_ioctl_x86_set_vcpu_events() squashes
the pending exception (if there's also an injected exception).  Buggy KVM
versions will eventually yell loudly about having impossible state when
processing queued excpetions, e.g.

  WARNING: CPU: 0 PID: 1115 at arch/x86/kvm/x86.c:10095 kvm_check_and_inject_events+0x220/0x500 [kvm]

  arch/x86/kvm/x86.c:kvm_check_and_inject_events():
  WARN_ON_ONCE(vcpu->arch.exception.injected &&
	       vcpu->arch.exception.pending);

Signed-off-by: Michal Luczaj <mhal@rbox.co>
Link: https://lore.kernel.org/r/20230728001606.2275586-3-mhal@rbox.co
[sean: split to separate patch, massage changelog and comment]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../selftests/kvm/x86_64/sync_regs_test.c     | 23 +++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
index e4ff2eaad7cd..7e5b13869e2e 100644
--- a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
@@ -81,6 +81,28 @@ static void compare_vcpu_events(struct kvm_vcpu_events *left,
 #define TEST_SYNC_FIELDS   (KVM_SYNC_X86_REGS|KVM_SYNC_X86_SREGS|KVM_SYNC_X86_EVENTS)
 #define INVALID_SYNC_FIELD 0x80000000
 
+/*
+ * Set an exception as pending *and* injected while KVM is processing events.
+ * KVM is supposed to ignore/drop pending exceptions if userspace is also
+ * requesting that an exception be injected.
+ */
+static void *race_events_inj_pen(void *arg)
+{
+	struct kvm_run *run = (struct kvm_run *)arg;
+	struct kvm_vcpu_events *events = &run->s.regs.events;
+
+	for (;;) {
+		WRITE_ONCE(run->kvm_dirty_regs, KVM_SYNC_X86_EVENTS);
+		WRITE_ONCE(events->flags, 0);
+		WRITE_ONCE(events->exception.injected, 1);
+		WRITE_ONCE(events->exception.pending, 1);
+
+		pthread_testcancel();
+	}
+
+	return NULL;
+}
+
 /*
  * Set an invalid exception vector while KVM is processing events.  KVM is
  * supposed to reject any vector >= 32, as well as NMIs (vector 2).
@@ -311,6 +333,7 @@ int main(int argc, char *argv[])
 
 	race_sync_regs(race_sregs_cr4);
 	race_sync_regs(race_events_exc);
+	race_sync_regs(race_events_inj_pen);
 
 	return 0;
 }

From b859b018aadfd05f0526533fd1bcf04024d01917 Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Mon, 31 Jul 2023 10:24:05 +0800
Subject: [PATCH 0226/1189] KVM: selftests: use unified time type for
 comparison

With test case kvm_page_table_test, start time is acquired with
time type CLOCK_MONOTONIC_RAW, however end time in timespec_elapsed()
is acquired with time type CLOCK_MONOTONIC. This can cause inaccurate
elapsed time calculation due to mixing timebases, e.g. LoongArch in
particular will see weirdness.

Modify kvm_page_table_test to use unified time type CLOCK_MONOTONIC for
start time.

Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Link: https://lore.kernel.org/r/20230731022405.854884-1-maobibo@loongson.cn
[sean: massage changelog]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/kvm_page_table_test.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c
index b3b00be1ef82..69f26d80c821 100644
--- a/tools/testing/selftests/kvm/kvm_page_table_test.c
+++ b/tools/testing/selftests/kvm/kvm_page_table_test.c
@@ -200,7 +200,7 @@ static void *vcpu_worker(void *data)
 		if (READ_ONCE(host_quit))
 			return NULL;
 
-		clock_gettime(CLOCK_MONOTONIC_RAW, &start);
+		clock_gettime(CLOCK_MONOTONIC, &start);
 		ret = _vcpu_run(vcpu);
 		ts_diff = timespec_elapsed(start);
 
@@ -367,7 +367,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	/* Test the stage of KVM creating mappings */
 	*current_stage = KVM_CREATE_MAPPINGS;
 
-	clock_gettime(CLOCK_MONOTONIC_RAW, &start);
+	clock_gettime(CLOCK_MONOTONIC, &start);
 	vcpus_complete_new_stage(*current_stage);
 	ts_diff = timespec_elapsed(start);
 
@@ -380,7 +380,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	*current_stage = KVM_UPDATE_MAPPINGS;
 
-	clock_gettime(CLOCK_MONOTONIC_RAW, &start);
+	clock_gettime(CLOCK_MONOTONIC, &start);
 	vcpus_complete_new_stage(*current_stage);
 	ts_diff = timespec_elapsed(start);
 
@@ -392,7 +392,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	*current_stage = KVM_ADJUST_MAPPINGS;
 
-	clock_gettime(CLOCK_MONOTONIC_RAW, &start);
+	clock_gettime(CLOCK_MONOTONIC, &start);
 	vcpus_complete_new_stage(*current_stage);
 	ts_diff = timespec_elapsed(start);
 

From 7e4966e6e13d0dad5eae934aff8b875a2aa8f469 Mon Sep 17 00:00:00 2001
From: Minjie Du <duminjie@vivo.com>
Date: Tue, 4 Jul 2023 20:21:47 +0800
Subject: [PATCH 0227/1189] KVM: selftests: Remove superfluous variable
 assignment

Don't nullify "nodep" to NULL one line before it's set to "tmp".

Signed-off-by: Minjie Du <duminjie@vivo.com>
Link: https://lore.kernel.org/r/20230704122148.11573-1-duminjie@vivo.com
[sean: massage shortlog+changelog]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/lib/sparsebit.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/testing/selftests/kvm/lib/sparsebit.c b/tools/testing/selftests/kvm/lib/sparsebit.c
index 50e0cf41a7dd..88cb6b84e6f3 100644
--- a/tools/testing/selftests/kvm/lib/sparsebit.c
+++ b/tools/testing/selftests/kvm/lib/sparsebit.c
@@ -634,7 +634,6 @@ static void node_reduce(struct sparsebit *s, struct node *nodep)
 				tmp = node_prev(s, nodep);
 
 			node_rm(s, nodep);
-			nodep = NULL;
 
 			nodep = tmp;
 			reduction_performed = true;

From 6d85f51a1f08411617d0bfe12c537ed6eba7f0f4 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Wed, 12 Jul 2023 09:59:07 +0200
Subject: [PATCH 0228/1189] KVM: selftests: Rename the ASSERT_EQ macro
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is already an ASSERT_EQ macro in the file
tools/testing/selftests/kselftest_harness.h, so currently KVM selftests
can't include test_util.h from the KVM selftests together with that file.
Rename the macro in the KVM selftests to TEST_ASSERT_EQ to avoid the
problem - it is also more similar to the other macros in test_util.h that
way.

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Link: https://lore.kernel.org/r/20230712075910.22480-2-thuth@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../selftests/kvm/aarch64/aarch32_id_regs.c   |  8 +--
 .../selftests/kvm/aarch64/page_fault_test.c   | 10 +--
 .../testing/selftests/kvm/include/test_util.h |  4 +-
 tools/testing/selftests/kvm/lib/kvm_util.c    |  2 +-
 .../selftests/kvm/max_guest_memory_test.c     |  2 +-
 tools/testing/selftests/kvm/s390x/cmma_test.c | 62 +++++++++----------
 tools/testing/selftests/kvm/s390x/memop.c     |  6 +-
 tools/testing/selftests/kvm/s390x/tprot.c     |  4 +-
 .../x86_64/dirty_log_page_splitting_test.c    | 18 +++---
 .../x86_64/exit_on_emulation_failure_test.c   |  2 +-
 .../kvm/x86_64/nested_exceptions_test.c       | 12 ++--
 .../kvm/x86_64/recalc_apic_map_test.c         |  6 +-
 .../selftests/kvm/x86_64/sync_regs_test.c     |  6 +-
 .../selftests/kvm/x86_64/tsc_msrs_test.c      | 32 +++++-----
 .../vmx_exception_with_invalid_guest_state.c  |  2 +-
 .../selftests/kvm/x86_64/vmx_pmu_caps_test.c  |  3 +-
 .../selftests/kvm/x86_64/xapic_state_test.c   |  8 +--
 .../selftests/kvm/x86_64/xen_vmcall_test.c    | 20 +++---
 18 files changed, 104 insertions(+), 103 deletions(-)

diff --git a/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c b/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c
index 4951ac53d1f8..b90580840b22 100644
--- a/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c
+++ b/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c
@@ -98,7 +98,7 @@ static void test_user_raz_wi(struct kvm_vcpu *vcpu)
 		uint64_t val;
 
 		vcpu_get_reg(vcpu, reg_id, &val);
-		ASSERT_EQ(val, 0);
+		TEST_ASSERT_EQ(val, 0);
 
 		/*
 		 * Expect the ioctl to succeed with no effect on the register
@@ -107,7 +107,7 @@ static void test_user_raz_wi(struct kvm_vcpu *vcpu)
 		vcpu_set_reg(vcpu, reg_id, BAD_ID_REG_VAL);
 
 		vcpu_get_reg(vcpu, reg_id, &val);
-		ASSERT_EQ(val, 0);
+		TEST_ASSERT_EQ(val, 0);
 	}
 }
 
@@ -127,14 +127,14 @@ static void test_user_raz_invariant(struct kvm_vcpu *vcpu)
 		uint64_t val;
 
 		vcpu_get_reg(vcpu, reg_id, &val);
-		ASSERT_EQ(val, 0);
+		TEST_ASSERT_EQ(val, 0);
 
 		r = __vcpu_set_reg(vcpu, reg_id, BAD_ID_REG_VAL);
 		TEST_ASSERT(r < 0 && errno == EINVAL,
 			    "unexpected KVM_SET_ONE_REG error: r=%d, errno=%d", r, errno);
 
 		vcpu_get_reg(vcpu, reg_id, &val);
-		ASSERT_EQ(val, 0);
+		TEST_ASSERT_EQ(val, 0);
 	}
 }
 
diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
index df10f1ffa20d..e5bb8767d2cb 100644
--- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c
+++ b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
@@ -318,7 +318,7 @@ static int uffd_generic_handler(int uffd_mode, int uffd, struct uffd_msg *msg,
 
 	TEST_ASSERT(uffd_mode == UFFDIO_REGISTER_MODE_MISSING,
 		    "The only expected UFFD mode is MISSING");
-	ASSERT_EQ(addr, (uint64_t)args->hva);
+	TEST_ASSERT_EQ(addr, (uint64_t)args->hva);
 
 	pr_debug("uffd fault: addr=%p write=%d\n",
 		 (void *)addr, !!(flags & UFFD_PAGEFAULT_FLAG_WRITE));
@@ -432,7 +432,7 @@ static void mmio_on_test_gpa_handler(struct kvm_vm *vm, struct kvm_run *run)
 	region = vm_get_mem_region(vm, MEM_REGION_TEST_DATA);
 	hva = (void *)region->region.userspace_addr;
 
-	ASSERT_EQ(run->mmio.phys_addr, region->region.guest_phys_addr);
+	TEST_ASSERT_EQ(run->mmio.phys_addr, region->region.guest_phys_addr);
 
 	memcpy(hva, run->mmio.data, run->mmio.len);
 	events.mmio_exits += 1;
@@ -631,9 +631,9 @@ static void setup_default_handlers(struct test_desc *test)
 
 static void check_event_counts(struct test_desc *test)
 {
-	ASSERT_EQ(test->expected_events.uffd_faults, events.uffd_faults);
-	ASSERT_EQ(test->expected_events.mmio_exits, events.mmio_exits);
-	ASSERT_EQ(test->expected_events.fail_vcpu_runs, events.fail_vcpu_runs);
+	TEST_ASSERT_EQ(test->expected_events.uffd_faults, events.uffd_faults);
+	TEST_ASSERT_EQ(test->expected_events.mmio_exits, events.mmio_exits);
+	TEST_ASSERT_EQ(test->expected_events.fail_vcpu_runs, events.fail_vcpu_runs);
 }
 
 static void print_test_banner(enum vm_guest_mode mode, struct test_params *p)
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index a6e9f215ce70..e734e52d8a3a 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -53,11 +53,11 @@ void test_assert(bool exp, const char *exp_str,
 #define TEST_ASSERT(e, fmt, ...) \
 	test_assert((e), #e, __FILE__, __LINE__, fmt, ##__VA_ARGS__)
 
-#define ASSERT_EQ(a, b) do { \
+#define TEST_ASSERT_EQ(a, b) do { \
 	typeof(a) __a = (a); \
 	typeof(b) __b = (b); \
 	TEST_ASSERT(__a == __b, \
-		    "ASSERT_EQ(%s, %s) failed.\n" \
+		    "TEST_ASSERT_EQ(%s, %s) failed.\n" \
 		    "\t%s is %#lx\n" \
 		    "\t%s is %#lx", \
 		    #a, #b, #a, (unsigned long) __a, #b, (unsigned long) __b); \
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 9741a7ff6380..3170d7a4520b 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -994,7 +994,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	if (src_type == VM_MEM_SRC_ANONYMOUS_THP)
 		alignment = max(backing_src_pagesz, alignment);
 
-	ASSERT_EQ(guest_paddr, align_up(guest_paddr, backing_src_pagesz));
+	TEST_ASSERT_EQ(guest_paddr, align_up(guest_paddr, backing_src_pagesz));
 
 	/* Add enough memory to align up if necessary */
 	if (alignment > 1)
diff --git a/tools/testing/selftests/kvm/max_guest_memory_test.c b/tools/testing/selftests/kvm/max_guest_memory_test.c
index feaf2be20ff2..6628dc4dda89 100644
--- a/tools/testing/selftests/kvm/max_guest_memory_test.c
+++ b/tools/testing/selftests/kvm/max_guest_memory_test.c
@@ -55,7 +55,7 @@ static void rendezvous_with_boss(void)
 static void run_vcpu(struct kvm_vcpu *vcpu)
 {
 	vcpu_run(vcpu);
-	ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE);
+	TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE);
 }
 
 static void *vcpu_worker(void *data)
diff --git a/tools/testing/selftests/kvm/s390x/cmma_test.c b/tools/testing/selftests/kvm/s390x/cmma_test.c
index 1d73e78e8fa7..c8e0a6495a63 100644
--- a/tools/testing/selftests/kvm/s390x/cmma_test.c
+++ b/tools/testing/selftests/kvm/s390x/cmma_test.c
@@ -237,8 +237,8 @@ static void test_get_cmma_basic(void)
 
 	/* GET_CMMA_BITS without CMMA enabled should fail */
 	rc = vm_get_cmma_bits(vm, 0, &errno_out);
-	ASSERT_EQ(rc, -1);
-	ASSERT_EQ(errno_out, ENXIO);
+	TEST_ASSERT_EQ(rc, -1);
+	TEST_ASSERT_EQ(errno_out, ENXIO);
 
 	enable_cmma(vm);
 	vcpu = vm_vcpu_add(vm, 1, guest_do_one_essa);
@@ -247,31 +247,31 @@ static void test_get_cmma_basic(void)
 
 	/* GET_CMMA_BITS without migration mode and without peeking should fail */
 	rc = vm_get_cmma_bits(vm, 0, &errno_out);
-	ASSERT_EQ(rc, -1);
-	ASSERT_EQ(errno_out, EINVAL);
+	TEST_ASSERT_EQ(rc, -1);
+	TEST_ASSERT_EQ(errno_out, EINVAL);
 
 	/* GET_CMMA_BITS without migration mode and with peeking should work */
 	rc = vm_get_cmma_bits(vm, KVM_S390_CMMA_PEEK, &errno_out);
-	ASSERT_EQ(rc, 0);
-	ASSERT_EQ(errno_out, 0);
+	TEST_ASSERT_EQ(rc, 0);
+	TEST_ASSERT_EQ(errno_out, 0);
 
 	enable_dirty_tracking(vm);
 	enable_migration_mode(vm);
 
 	/* GET_CMMA_BITS with invalid flags */
 	rc = vm_get_cmma_bits(vm, 0xfeedc0fe, &errno_out);
-	ASSERT_EQ(rc, -1);
-	ASSERT_EQ(errno_out, EINVAL);
+	TEST_ASSERT_EQ(rc, -1);
+	TEST_ASSERT_EQ(errno_out, EINVAL);
 
 	kvm_vm_free(vm);
 }
 
 static void assert_exit_was_hypercall(struct kvm_vcpu *vcpu)
 {
-	ASSERT_EQ(vcpu->run->exit_reason, 13);
-	ASSERT_EQ(vcpu->run->s390_sieic.icptcode, 4);
-	ASSERT_EQ(vcpu->run->s390_sieic.ipa, 0x8300);
-	ASSERT_EQ(vcpu->run->s390_sieic.ipb, 0x5010000);
+	TEST_ASSERT_EQ(vcpu->run->exit_reason, 13);
+	TEST_ASSERT_EQ(vcpu->run->s390_sieic.icptcode, 4);
+	TEST_ASSERT_EQ(vcpu->run->s390_sieic.ipa, 0x8300);
+	TEST_ASSERT_EQ(vcpu->run->s390_sieic.ipb, 0x5010000);
 }
 
 static void test_migration_mode(void)
@@ -283,8 +283,8 @@ static void test_migration_mode(void)
 
 	/* enabling migration mode on a VM without memory should fail */
 	rc = __enable_migration_mode(vm);
-	ASSERT_EQ(rc, -1);
-	ASSERT_EQ(errno, EINVAL);
+	TEST_ASSERT_EQ(rc, -1);
+	TEST_ASSERT_EQ(errno, EINVAL);
 	TEST_ASSERT(!is_migration_mode_on(vm), "migration mode should still be off");
 	errno = 0;
 
@@ -304,8 +304,8 @@ static void test_migration_mode(void)
 
 	/* migration mode when memslots have dirty tracking off should fail */
 	rc = __enable_migration_mode(vm);
-	ASSERT_EQ(rc, -1);
-	ASSERT_EQ(errno, EINVAL);
+	TEST_ASSERT_EQ(rc, -1);
+	TEST_ASSERT_EQ(errno, EINVAL);
 	TEST_ASSERT(!is_migration_mode_on(vm), "migration mode should still be off");
 	errno = 0;
 
@@ -314,7 +314,7 @@ static void test_migration_mode(void)
 
 	/* enabling migration mode should work now */
 	rc = __enable_migration_mode(vm);
-	ASSERT_EQ(rc, 0);
+	TEST_ASSERT_EQ(rc, 0);
 	TEST_ASSERT(is_migration_mode_on(vm), "migration mode should be on");
 	errno = 0;
 
@@ -350,7 +350,7 @@ static void test_migration_mode(void)
 	 */
 	vm_mem_region_set_flags(vm, TEST_DATA_TWO_MEMSLOT, KVM_MEM_LOG_DIRTY_PAGES);
 	rc = __enable_migration_mode(vm);
-	ASSERT_EQ(rc, 0);
+	TEST_ASSERT_EQ(rc, 0);
 	TEST_ASSERT(is_migration_mode_on(vm), "migration mode should be on");
 	errno = 0;
 
@@ -394,9 +394,9 @@ static void assert_all_slots_cmma_dirty(struct kvm_vm *vm)
 	};
 	memset(cmma_value_buf, 0xff, sizeof(cmma_value_buf));
 	vm_ioctl(vm, KVM_S390_GET_CMMA_BITS, &args);
-	ASSERT_EQ(args.count, MAIN_PAGE_COUNT);
-	ASSERT_EQ(args.remaining, TEST_DATA_PAGE_COUNT);
-	ASSERT_EQ(args.start_gfn, 0);
+	TEST_ASSERT_EQ(args.count, MAIN_PAGE_COUNT);
+	TEST_ASSERT_EQ(args.remaining, TEST_DATA_PAGE_COUNT);
+	TEST_ASSERT_EQ(args.start_gfn, 0);
 
 	/* ...and then - after a hole - the TEST_DATA memslot should follow */
 	args = (struct kvm_s390_cmma_log){
@@ -407,9 +407,9 @@ static void assert_all_slots_cmma_dirty(struct kvm_vm *vm)
 	};
 	memset(cmma_value_buf, 0xff, sizeof(cmma_value_buf));
 	vm_ioctl(vm, KVM_S390_GET_CMMA_BITS, &args);
-	ASSERT_EQ(args.count, TEST_DATA_PAGE_COUNT);
-	ASSERT_EQ(args.start_gfn, TEST_DATA_START_GFN);
-	ASSERT_EQ(args.remaining, 0);
+	TEST_ASSERT_EQ(args.count, TEST_DATA_PAGE_COUNT);
+	TEST_ASSERT_EQ(args.start_gfn, TEST_DATA_START_GFN);
+	TEST_ASSERT_EQ(args.remaining, 0);
 
 	/* ...and nothing else should be there */
 	args = (struct kvm_s390_cmma_log){
@@ -420,9 +420,9 @@ static void assert_all_slots_cmma_dirty(struct kvm_vm *vm)
 	};
 	memset(cmma_value_buf, 0xff, sizeof(cmma_value_buf));
 	vm_ioctl(vm, KVM_S390_GET_CMMA_BITS, &args);
-	ASSERT_EQ(args.count, 0);
-	ASSERT_EQ(args.start_gfn, 0);
-	ASSERT_EQ(args.remaining, 0);
+	TEST_ASSERT_EQ(args.count, 0);
+	TEST_ASSERT_EQ(args.start_gfn, 0);
+	TEST_ASSERT_EQ(args.remaining, 0);
 }
 
 /**
@@ -498,11 +498,11 @@ static void assert_cmma_dirty(u64 first_dirty_gfn,
 			      u64 dirty_gfn_count,
 			      const struct kvm_s390_cmma_log *res)
 {
-	ASSERT_EQ(res->start_gfn, first_dirty_gfn);
-	ASSERT_EQ(res->count, dirty_gfn_count);
+	TEST_ASSERT_EQ(res->start_gfn, first_dirty_gfn);
+	TEST_ASSERT_EQ(res->count, dirty_gfn_count);
 	for (size_t i = 0; i < dirty_gfn_count; i++)
-		ASSERT_EQ(cmma_value_buf[0], 0x0); /* stable state */
-	ASSERT_EQ(cmma_value_buf[dirty_gfn_count], 0xff); /* not touched */
+		TEST_ASSERT_EQ(cmma_value_buf[0], 0x0); /* stable state */
+	TEST_ASSERT_EQ(cmma_value_buf[dirty_gfn_count], 0xff); /* not touched */
 }
 
 static void test_get_skip_holes(void)
diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390x/memop.c
index 8e4b94d7b8dd..de73dc030905 100644
--- a/tools/testing/selftests/kvm/s390x/memop.c
+++ b/tools/testing/selftests/kvm/s390x/memop.c
@@ -281,8 +281,8 @@ enum stage {
 	if (uc.cmd == UCALL_ABORT) {					\
 		REPORT_GUEST_ASSERT_2(uc, "hints: %lu, %lu");		\
 	}								\
-	ASSERT_EQ(uc.cmd, UCALL_SYNC);					\
-	ASSERT_EQ(uc.args[1], __stage);					\
+	TEST_ASSERT_EQ(uc.cmd, UCALL_SYNC);				\
+	TEST_ASSERT_EQ(uc.args[1], __stage);				\
 })									\
 
 static void prepare_mem12(void)
@@ -808,7 +808,7 @@ static void test_termination(void)
 	HOST_SYNC(t.vcpu, STAGE_IDLED);
 	MOP(t.vm, ABSOLUTE, READ, &teid, sizeof(teid), GADDR(prefix + 168));
 	/* Bits 56, 60, 61 form a code, 0 being the only one allowing for termination */
-	ASSERT_EQ(teid & teid_mask, 0);
+	TEST_ASSERT_EQ(teid & teid_mask, 0);
 
 	kvm_vm_free(t.kvm_vm);
 }
diff --git a/tools/testing/selftests/kvm/s390x/tprot.c b/tools/testing/selftests/kvm/s390x/tprot.c
index a9a0b76e5fa4..40d3ea16c052 100644
--- a/tools/testing/selftests/kvm/s390x/tprot.c
+++ b/tools/testing/selftests/kvm/s390x/tprot.c
@@ -191,8 +191,8 @@ static void guest_code(void)
 	get_ucall(__vcpu, &uc);					\
 	if (uc.cmd == UCALL_ABORT)				\
 		REPORT_GUEST_ASSERT_2(uc, "hints: %lu, %lu");	\
-	ASSERT_EQ(uc.cmd, UCALL_SYNC);				\
-	ASSERT_EQ(uc.args[1], __stage);				\
+	TEST_ASSERT_EQ(uc.cmd, UCALL_SYNC);			\
+	TEST_ASSERT_EQ(uc.args[1], __stage);			\
 })
 
 #define HOST_SYNC(vcpu, stage)			\
diff --git a/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c b/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c
index beb7e2c10211..634c6bfcd572 100644
--- a/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c
+++ b/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c
@@ -72,7 +72,7 @@ static void vcpu_worker(struct memstress_vcpu_args *vcpu_args)
 
 		vcpu_run(vcpu);
 
-		ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_SYNC);
+		TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_SYNC);
 
 		vcpu_last_completed_iteration[vcpu_idx] = current_iteration;
 
@@ -179,12 +179,12 @@ static void run_test(enum vm_guest_mode mode, void *unused)
 	 * with that capability.
 	 */
 	if (dirty_log_manual_caps) {
-		ASSERT_EQ(stats_clear_pass[0].hugepages, 0);
-		ASSERT_EQ(stats_clear_pass[0].pages_4k, total_4k_pages);
-		ASSERT_EQ(stats_dirty_logging_enabled.hugepages, stats_populated.hugepages);
+		TEST_ASSERT_EQ(stats_clear_pass[0].hugepages, 0);
+		TEST_ASSERT_EQ(stats_clear_pass[0].pages_4k, total_4k_pages);
+		TEST_ASSERT_EQ(stats_dirty_logging_enabled.hugepages, stats_populated.hugepages);
 	} else {
-		ASSERT_EQ(stats_dirty_logging_enabled.hugepages, 0);
-		ASSERT_EQ(stats_dirty_logging_enabled.pages_4k, total_4k_pages);
+		TEST_ASSERT_EQ(stats_dirty_logging_enabled.hugepages, 0);
+		TEST_ASSERT_EQ(stats_dirty_logging_enabled.pages_4k, total_4k_pages);
 	}
 
 	/*
@@ -192,9 +192,9 @@ static void run_test(enum vm_guest_mode mode, void *unused)
 	 * memory again, the page counts should be the same as they were
 	 * right after initial population of memory.
 	 */
-	ASSERT_EQ(stats_populated.pages_4k, stats_repopulated.pages_4k);
-	ASSERT_EQ(stats_populated.pages_2m, stats_repopulated.pages_2m);
-	ASSERT_EQ(stats_populated.pages_1g, stats_repopulated.pages_1g);
+	TEST_ASSERT_EQ(stats_populated.pages_4k, stats_repopulated.pages_4k);
+	TEST_ASSERT_EQ(stats_populated.pages_2m, stats_repopulated.pages_2m);
+	TEST_ASSERT_EQ(stats_populated.pages_1g, stats_repopulated.pages_1g);
 }
 
 static void help(char *name)
diff --git a/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c b/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c
index e334844d6e1d..6c2e5e0ceb1f 100644
--- a/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c
+++ b/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c
@@ -35,7 +35,7 @@ int main(int argc, char *argv[])
 	vcpu_run(vcpu);
 	handle_flds_emulation_failure_exit(vcpu);
 	vcpu_run(vcpu);
-	ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE);
+	TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE);
 
 	kvm_vm_free(vm);
 	return 0;
diff --git a/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c b/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c
index 6502aa23c2f8..5f074a6da90c 100644
--- a/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c
+++ b/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c
@@ -247,12 +247,12 @@ int main(int argc, char *argv[])
 
 	/* Verify the pending events comes back out the same as it went in. */
 	vcpu_events_get(vcpu, &events);
-	ASSERT_EQ(events.flags & KVM_VCPUEVENT_VALID_PAYLOAD,
-		  KVM_VCPUEVENT_VALID_PAYLOAD);
-	ASSERT_EQ(events.exception.pending, true);
-	ASSERT_EQ(events.exception.nr, SS_VECTOR);
-	ASSERT_EQ(events.exception.has_error_code, true);
-	ASSERT_EQ(events.exception.error_code, SS_ERROR_CODE);
+	TEST_ASSERT_EQ(events.flags & KVM_VCPUEVENT_VALID_PAYLOAD,
+			KVM_VCPUEVENT_VALID_PAYLOAD);
+	TEST_ASSERT_EQ(events.exception.pending, true);
+	TEST_ASSERT_EQ(events.exception.nr, SS_VECTOR);
+	TEST_ASSERT_EQ(events.exception.has_error_code, true);
+	TEST_ASSERT_EQ(events.exception.error_code, SS_ERROR_CODE);
 
 	/*
 	 * Run for real with the pending #SS, L1 should get a VM-Exit due to
diff --git a/tools/testing/selftests/kvm/x86_64/recalc_apic_map_test.c b/tools/testing/selftests/kvm/x86_64/recalc_apic_map_test.c
index 4c416ebe7d66..cbc92a862ea9 100644
--- a/tools/testing/selftests/kvm/x86_64/recalc_apic_map_test.c
+++ b/tools/testing/selftests/kvm/x86_64/recalc_apic_map_test.c
@@ -57,7 +57,7 @@ int main(void)
 	for (i = 0; i < KVM_MAX_VCPUS; i++)
 		vcpu_set_msr(vcpus[i], MSR_IA32_APICBASE, LAPIC_X2APIC);
 
-	ASSERT_EQ(pthread_create(&thread, NULL, race, vcpus[0]), 0);
+	TEST_ASSERT_EQ(pthread_create(&thread, NULL, race, vcpus[0]), 0);
 
 	vcpuN = vcpus[KVM_MAX_VCPUS - 1];
 	for (t = time(NULL) + TIMEOUT; time(NULL) < t;) {
@@ -65,8 +65,8 @@ int main(void)
 		vcpu_set_msr(vcpuN, MSR_IA32_APICBASE, LAPIC_DISABLED);
 	}
 
-	ASSERT_EQ(pthread_cancel(thread), 0);
-	ASSERT_EQ(pthread_join(thread, NULL), 0);
+	TEST_ASSERT_EQ(pthread_cancel(thread), 0);
+	TEST_ASSERT_EQ(pthread_join(thread, NULL), 0);
 
 	kvm_vm_free(vm);
 
diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
index 7e5b13869e2e..93fac74ca0a7 100644
--- a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
@@ -176,7 +176,7 @@ static void race_sync_regs(void *racer)
 		    !!(run->s.regs.sregs.cr4 & X86_CR4_PAE),
 		    !!(run->s.regs.sregs.efer & EFER_LME));
 
-	ASSERT_EQ(pthread_create(&thread, NULL, racer, (void *)run), 0);
+	TEST_ASSERT_EQ(pthread_create(&thread, NULL, racer, (void *)run), 0);
 
 	for (t = time(NULL) + TIMEOUT; time(NULL) < t;) {
 		__vcpu_run(vcpu);
@@ -187,8 +187,8 @@ static void race_sync_regs(void *racer)
 		}
 	}
 
-	ASSERT_EQ(pthread_cancel(thread), 0);
-	ASSERT_EQ(pthread_join(thread, NULL), 0);
+	TEST_ASSERT_EQ(pthread_cancel(thread), 0);
+	TEST_ASSERT_EQ(pthread_join(thread, NULL), 0);
 
 	kvm_vm_free(vm);
 }
diff --git a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c
index c9f67702f657..9265965bd2cd 100644
--- a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c
@@ -103,39 +103,39 @@ int main(void)
 	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
 
 	val = 0;
-	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val);
-	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val);
+	TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val);
+	TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val);
 
 	/* Guest: writes to MSR_IA32_TSC affect both MSRs.  */
 	run_vcpu(vcpu, 1);
 	val = 1ull * GUEST_STEP;
-	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val);
-	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val);
+	TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val);
+	TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val);
 
 	/* Guest: writes to MSR_IA32_TSC_ADJUST affect both MSRs.  */
 	run_vcpu(vcpu, 2);
 	val = 2ull * GUEST_STEP;
-	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val);
-	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val);
+	TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val);
+	TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val);
 
 	/*
 	 * Host: writes to MSR_IA32_TSC set the host-side offset
 	 * and therefore do not change MSR_IA32_TSC_ADJUST.
 	 */
 	vcpu_set_msr(vcpu, MSR_IA32_TSC, HOST_ADJUST + val);
-	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val);
-	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val);
+	TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val);
+	TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val);
 	run_vcpu(vcpu, 3);
 
 	/* Host: writes to MSR_IA32_TSC_ADJUST do not modify the TSC.  */
 	vcpu_set_msr(vcpu, MSR_IA32_TSC_ADJUST, UNITY * 123456);
-	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val);
-	ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_TSC_ADJUST), UNITY * 123456);
+	TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val);
+	TEST_ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_TSC_ADJUST), UNITY * 123456);
 
 	/* Restore previous value.  */
 	vcpu_set_msr(vcpu, MSR_IA32_TSC_ADJUST, val);
-	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val);
-	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val);
+	TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val);
+	TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val);
 
 	/*
 	 * Guest: writes to MSR_IA32_TSC_ADJUST do not destroy the
@@ -143,8 +143,8 @@ int main(void)
 	 */
 	run_vcpu(vcpu, 4);
 	val = 3ull * GUEST_STEP;
-	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val);
-	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val);
+	TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val);
+	TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val);
 
 	/*
 	 * Guest: writes to MSR_IA32_TSC affect both MSRs, so the host-side
@@ -152,8 +152,8 @@ int main(void)
 	 */
 	run_vcpu(vcpu, 5);
 	val = 4ull * GUEST_STEP;
-	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val);
-	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val - HOST_ADJUST);
+	TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val);
+	TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val - HOST_ADJUST);
 
 	kvm_vm_free(vm);
 
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c
index be0bdb8c6f78..a9b827c69f32 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c
@@ -50,7 +50,7 @@ static void set_timer(void)
 	timer.it_value.tv_sec  = 0;
 	timer.it_value.tv_usec = 200;
 	timer.it_interval = timer.it_value;
-	ASSERT_EQ(setitimer(ITIMER_REAL, &timer, NULL), 0);
+	TEST_ASSERT_EQ(setitimer(ITIMER_REAL, &timer, NULL), 0);
 }
 
 static void set_or_clear_invalid_guest_state(struct kvm_vcpu *vcpu, bool set)
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c
index 4c90f76930f9..34efd57c2b32 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c
@@ -103,7 +103,8 @@ static void test_guest_wrmsr_perf_capabilities(union perf_capabilities host_cap)
 		TEST_FAIL("Unexpected ucall: %lu", uc.cmd);
 	}
 
-	ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), host_cap.capabilities);
+	TEST_ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES),
+			host_cap.capabilities);
 
 	vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities);
 
diff --git a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c
index 396c13f42457..ab75b873a4ad 100644
--- a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c
@@ -65,17 +65,17 @@ static void ____test_icr(struct xapic_vcpu *x, uint64_t val)
 	vcpu_ioctl(vcpu, KVM_SET_LAPIC, &xapic);
 
 	vcpu_run(vcpu);
-	ASSERT_EQ(get_ucall(vcpu, &uc), UCALL_SYNC);
-	ASSERT_EQ(uc.args[1], val);
+	TEST_ASSERT_EQ(get_ucall(vcpu, &uc), UCALL_SYNC);
+	TEST_ASSERT_EQ(uc.args[1], val);
 
 	vcpu_ioctl(vcpu, KVM_GET_LAPIC, &xapic);
 	icr = (u64)(*((u32 *)&xapic.regs[APIC_ICR])) |
 	      (u64)(*((u32 *)&xapic.regs[APIC_ICR2])) << 32;
 	if (!x->is_x2apic) {
 		val &= (-1u | (0xffull << (32 + 24)));
-		ASSERT_EQ(icr, val & ~APIC_ICR_BUSY);
+		TEST_ASSERT_EQ(icr, val & ~APIC_ICR_BUSY);
 	} else {
-		ASSERT_EQ(icr & ~APIC_ICR_BUSY, val & ~APIC_ICR_BUSY);
+		TEST_ASSERT_EQ(icr & ~APIC_ICR_BUSY, val & ~APIC_ICR_BUSY);
 	}
 }
 
diff --git a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c
index c94cde3b523f..e149d0574961 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c
@@ -108,16 +108,16 @@ int main(int argc, char *argv[])
 		vcpu_run(vcpu);
 
 		if (run->exit_reason == KVM_EXIT_XEN) {
-			ASSERT_EQ(run->xen.type, KVM_EXIT_XEN_HCALL);
-			ASSERT_EQ(run->xen.u.hcall.cpl, 0);
-			ASSERT_EQ(run->xen.u.hcall.longmode, 1);
-			ASSERT_EQ(run->xen.u.hcall.input, INPUTVALUE);
-			ASSERT_EQ(run->xen.u.hcall.params[0], ARGVALUE(1));
-			ASSERT_EQ(run->xen.u.hcall.params[1], ARGVALUE(2));
-			ASSERT_EQ(run->xen.u.hcall.params[2], ARGVALUE(3));
-			ASSERT_EQ(run->xen.u.hcall.params[3], ARGVALUE(4));
-			ASSERT_EQ(run->xen.u.hcall.params[4], ARGVALUE(5));
-			ASSERT_EQ(run->xen.u.hcall.params[5], ARGVALUE(6));
+			TEST_ASSERT_EQ(run->xen.type, KVM_EXIT_XEN_HCALL);
+			TEST_ASSERT_EQ(run->xen.u.hcall.cpl, 0);
+			TEST_ASSERT_EQ(run->xen.u.hcall.longmode, 1);
+			TEST_ASSERT_EQ(run->xen.u.hcall.input, INPUTVALUE);
+			TEST_ASSERT_EQ(run->xen.u.hcall.params[0], ARGVALUE(1));
+			TEST_ASSERT_EQ(run->xen.u.hcall.params[1], ARGVALUE(2));
+			TEST_ASSERT_EQ(run->xen.u.hcall.params[2], ARGVALUE(3));
+			TEST_ASSERT_EQ(run->xen.u.hcall.params[3], ARGVALUE(4));
+			TEST_ASSERT_EQ(run->xen.u.hcall.params[4], ARGVALUE(5));
+			TEST_ASSERT_EQ(run->xen.u.hcall.params[5], ARGVALUE(6));
 			run->xen.u.hcall.result = RETVALUE;
 			continue;
 		}

From b145c58d95fff280c2726d0024005ae0a4ec378d Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:11 -0700
Subject: [PATCH 0229/1189] KVM: selftests: Make TEST_ASSERT_EQ() output look
 like normal TEST_ASSERT()

Clean up TEST_ASSERT_EQ() so that the (mostly) raw code is captured in the
main assert message, not the helper macro's code.  E.g. make this:

  x86_64/tsc_msrs_test.c:106: __a == __b
  pid=40470 tid=40470 errno=0 - Success
     1	0x000000000040170e: main at tsc_msrs_test.c:106
     2	0x0000000000416f23: __libc_start_call_main at libc-start.o:?
     3	0x000000000041856f: __libc_start_main_impl at ??:?
     4	0x0000000000401ef0: _start at ??:?
  TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val + 1) failed.
	rounded_host_rdmsr(MSR_IA32_TSC) is 0
	val + 1 is 0x1

look like this:

  x86_64/tsc_msrs_test.c:106: rounded_host_rdmsr(MSR_IA32_TSC) == val + 1
  pid=5737 tid=5737 errno=0 - Success
     1	0x0000000000401714: main at tsc_msrs_test.c:106
     2	0x0000000000415c23: __libc_start_call_main at libc-start.o:?
     3	0x000000000041726f: __libc_start_main_impl at ??:?
     4	0x0000000000401e60: _start at ??:?
  0 != 0x1 (rounded_host_rdmsr(MSR_IA32_TSC) != val + 1)

Opportunstically clean up the formatting of the entire macro.

Link: https://lore.kernel.org/r/20230729003643.1053367-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/include/test_util.h | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index e734e52d8a3a..a4bea44f990c 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -53,14 +53,13 @@ void test_assert(bool exp, const char *exp_str,
 #define TEST_ASSERT(e, fmt, ...) \
 	test_assert((e), #e, __FILE__, __LINE__, fmt, ##__VA_ARGS__)
 
-#define TEST_ASSERT_EQ(a, b) do { \
-	typeof(a) __a = (a); \
-	typeof(b) __b = (b); \
-	TEST_ASSERT(__a == __b, \
-		    "TEST_ASSERT_EQ(%s, %s) failed.\n" \
-		    "\t%s is %#lx\n" \
-		    "\t%s is %#lx", \
-		    #a, #b, #a, (unsigned long) __a, #b, (unsigned long) __b); \
+#define TEST_ASSERT_EQ(a, b)						\
+do {									\
+	typeof(a) __a = (a);						\
+	typeof(b) __b = (b);						\
+	test_assert(__a == __b, #a " == " #b, __FILE__, __LINE__,	\
+		    "%#lx != %#lx (%s != %s)",				\
+		    (unsigned long)(__a), (unsigned long)(__b), #a, #b);\
 } while (0)
 
 #define TEST_ASSERT_KVM_EXIT_REASON(vcpu, expected) do {		\

From 6783ca4105a75d1ba4f89b13cef1bc1f677c41e5 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:12 -0700
Subject: [PATCH 0230/1189] KVM: selftests: Add a shameful hack to
 preserve/clobber GPRs across ucall

Preserve or clobber all GPRs (except RIP and RSP, as they're saved and
restored via the VMCS) when performing a ucall on x86 to fudge around a
horrific long-standing bug in selftests' nested VMX support where L2's
GPRs are not preserved across a nested VM-Exit.  I.e. if a test triggers a
nested VM-Exit to L1 in response to a ucall, e.g. GUEST_SYNC(), then L2's
GPR state can be corrupted.

The issues manifests as an unexpected #GP in clear_bit() when running the
hyperv_evmcs test due to RBX being used to track the ucall object, and RBX
being clobbered by the nested VM-Exit.  The problematic hyperv_evmcs
testcase is where L0 (test's host userspace) injects an NMI in response to
GUEST_SYNC(8) from L2, but the bug could "randomly" manifest in any test
that induces a nested VM-Exit from L0.  The bug hasn't caused failures in
the past due to sheer dumb luck.

The obvious fix is to rework the nVMX helpers to save/restore L2 GPRs
across VM-Exit and VM-Enter, but that is a much bigger task and carries
its own risks, e.g. nSVM does save/restore GPRs, but not in a thread-safe
manner, and there is a _lot_ of cleanup that can be done to unify code
for doing VM-Enter on nVMX, nSVM, and eVMCS.

Link: https://lore.kernel.org/r/20230729003643.1053367-4-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../testing/selftests/kvm/lib/x86_64/ucall.c  | 32 +++++++++++++++++--
 1 file changed, 30 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/kvm/lib/x86_64/ucall.c b/tools/testing/selftests/kvm/lib/x86_64/ucall.c
index 4d41dc63cc9e..a53df3ece2f8 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/ucall.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/ucall.c
@@ -14,8 +14,36 @@ void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
 
 void ucall_arch_do_ucall(vm_vaddr_t uc)
 {
-	asm volatile("in %[port], %%al"
-		: : [port] "d" (UCALL_PIO_PORT), "D" (uc) : "rax", "memory");
+	/*
+	 * FIXME: Revert this hack (the entire commit that added it) once nVMX
+	 * preserves L2 GPRs across a nested VM-Exit.  If a ucall from L2, e.g.
+	 * to do a GUEST_SYNC(), lands the vCPU in L1, any and all GPRs can be
+	 * clobbered by L1.  Save and restore non-volatile GPRs (clobbering RBP
+	 * in particular is problematic) along with RDX and RDI (which are
+	 * inputs), and clobber volatile GPRs. *sigh*
+	 */
+#define HORRIFIC_L2_UCALL_CLOBBER_HACK	\
+	"rcx", "rsi", "r8", "r9", "r10", "r11"
+
+	asm volatile("push %%rbp\n\t"
+		     "push %%r15\n\t"
+		     "push %%r14\n\t"
+		     "push %%r13\n\t"
+		     "push %%r12\n\t"
+		     "push %%rbx\n\t"
+		     "push %%rdx\n\t"
+		     "push %%rdi\n\t"
+		     "in %[port], %%al\n\t"
+		     "pop %%rdi\n\t"
+		     "pop %%rdx\n\t"
+		     "pop %%rbx\n\t"
+		     "pop %%r12\n\t"
+		     "pop %%r13\n\t"
+		     "pop %%r14\n\t"
+		     "pop %%r15\n\t"
+		     "pop %%rbp\n\t"
+		: : [port] "d" (UCALL_PIO_PORT), "D" (uc) : "rax", "memory",
+		     HORRIFIC_L2_UCALL_CLOBBER_HACK);
 }
 
 void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu)

From a1c1b55e116c14de4f8a78286b502101f2a1620c Mon Sep 17 00:00:00 2001
From: Aaron Lewis <aaronlewis@google.com>
Date: Fri, 28 Jul 2023 17:36:13 -0700
Subject: [PATCH 0231/1189] KVM: selftests: Add strnlen() to the string
 overrides

Add strnlen() to the string overrides to allow it to be called in the
guest.

The implementation for strnlen() was taken from the kernel's generic
version, lib/string.c.

This will be needed when printf() is introduced.

Signed-off-by: Aaron Lewis <aaronlewis@google.com>
Link: https://lore.kernel.org/r/20230729003643.1053367-5-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/Makefile              | 1 +
 tools/testing/selftests/kvm/lib/string_override.c | 9 +++++++++
 2 files changed, 10 insertions(+)

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index c692cc86e7da..f6c14ab476ac 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -204,6 +204,7 @@ endif
 CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \
 	-Wno-gnu-variable-sized-type-not-at-end -MD\
 	-fno-builtin-memcmp -fno-builtin-memcpy -fno-builtin-memset \
+	-fno-builtin-strnlen \
 	-fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \
 	-I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \
 	-I$(<D) -Iinclude/$(ARCH_DIR) -I ../rseq -I.. $(EXTRA_CFLAGS) \
diff --git a/tools/testing/selftests/kvm/lib/string_override.c b/tools/testing/selftests/kvm/lib/string_override.c
index 632398adc229..5d1c87277c49 100644
--- a/tools/testing/selftests/kvm/lib/string_override.c
+++ b/tools/testing/selftests/kvm/lib/string_override.c
@@ -37,3 +37,12 @@ void *memset(void *s, int c, size_t count)
 		*xs++ = c;
 	return s;
 }
+
+size_t strnlen(const char *s, size_t count)
+{
+	const char *sc;
+
+	for (sc = s; count-- && *sc != '\0'; ++sc)
+		/* nothing */;
+	return sc - s;
+}

From e5119382499cefc839097dcc78f27ab00131e7ad Mon Sep 17 00:00:00 2001
From: Aaron Lewis <aaronlewis@google.com>
Date: Fri, 28 Jul 2023 17:36:14 -0700
Subject: [PATCH 0232/1189] KVM: selftests: Add guest_snprintf() to KVM
 selftests

Add a local version of guest_snprintf() for use in the guest.

Having a local copy allows the guest access to string formatting
options without dependencies on LIBC.  LIBC is problematic because
it heavily relies on both AVX-512 instructions and a TLS, neither of
which are guaranteed to be set up in the guest.

The file guest_sprintf.c was lifted from arch/x86/boot/printf.c and
adapted to work in the guest, including the addition of buffer length.
I.e. s/sprintf/snprintf/

The functions where prefixed with "guest_" to allow guests to
explicitly call them.

A string formatted by this function is expected to succeed or die.  If
something goes wrong during the formatting process a GUEST_ASSERT()
will be thrown.

Signed-off-by: Aaron Lewis <aaronlewis@google.com>
Link: https://lore.kernel.org/all/mtdi6smhur5rqffvpu7qux7mptonw223y2653x2nwzvgm72nlo@zyc4w3kwl3rg
[sean: add a link to the discussion of other options]
Link: https://lore.kernel.org/r/20230729003643.1053367-6-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/Makefile          |   1 +
 .../testing/selftests/kvm/include/test_util.h |   3 +
 .../testing/selftests/kvm/lib/guest_sprintf.c | 307 ++++++++++++++++++
 3 files changed, 311 insertions(+)
 create mode 100644 tools/testing/selftests/kvm/lib/guest_sprintf.c

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index f6c14ab476ac..f65889f5a083 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -23,6 +23,7 @@ LIBKVM += lib/guest_modes.c
 LIBKVM += lib/io.c
 LIBKVM += lib/kvm_util.c
 LIBKVM += lib/memstress.c
+LIBKVM += lib/guest_sprintf.c
 LIBKVM += lib/rbtree.c
 LIBKVM += lib/sparsebit.c
 LIBKVM += lib/test_util.c
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index a4bea44f990c..7a5907da1719 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -185,4 +185,7 @@ static inline uint32_t atoi_non_negative(const char *name, const char *num_str)
 	return num;
 }
 
+int guest_vsnprintf(char *buf, int n, const char *fmt, va_list args);
+int guest_snprintf(char *buf, int n, const char *fmt, ...);
+
 #endif /* SELFTEST_KVM_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/lib/guest_sprintf.c b/tools/testing/selftests/kvm/lib/guest_sprintf.c
new file mode 100644
index 000000000000..c4a69d8aeb68
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/guest_sprintf.c
@@ -0,0 +1,307 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include "test_util.h"
+#include "kvm_util.h"
+#include "ucall_common.h"
+
+#define APPEND_BUFFER_SAFE(str, end, v) \
+do {					\
+	GUEST_ASSERT(str < end);	\
+	*str++ = (v);			\
+} while (0)
+
+static int isdigit(int ch)
+{
+	return (ch >= '0') && (ch <= '9');
+}
+
+static int skip_atoi(const char **s)
+{
+	int i = 0;
+
+	while (isdigit(**s))
+		i = i * 10 + *((*s)++) - '0';
+	return i;
+}
+
+#define ZEROPAD	1		/* pad with zero */
+#define SIGN	2		/* unsigned/signed long */
+#define PLUS	4		/* show plus */
+#define SPACE	8		/* space if plus */
+#define LEFT	16		/* left justified */
+#define SMALL	32		/* Must be 32 == 0x20 */
+#define SPECIAL	64		/* 0x */
+
+#define __do_div(n, base)				\
+({							\
+	int __res;					\
+							\
+	__res = ((uint64_t) n) % (uint32_t) base;	\
+	n = ((uint64_t) n) / (uint32_t) base;		\
+	__res;						\
+})
+
+static char *number(char *str, const char *end, long num, int base, int size,
+		    int precision, int type)
+{
+	/* we are called with base 8, 10 or 16, only, thus don't need "G..."  */
+	static const char digits[16] = "0123456789ABCDEF"; /* "GHIJKLMNOPQRSTUVWXYZ"; */
+
+	char tmp[66];
+	char c, sign, locase;
+	int i;
+
+	/*
+	 * locase = 0 or 0x20. ORing digits or letters with 'locase'
+	 * produces same digits or (maybe lowercased) letters
+	 */
+	locase = (type & SMALL);
+	if (type & LEFT)
+		type &= ~ZEROPAD;
+	if (base < 2 || base > 16)
+		return NULL;
+	c = (type & ZEROPAD) ? '0' : ' ';
+	sign = 0;
+	if (type & SIGN) {
+		if (num < 0) {
+			sign = '-';
+			num = -num;
+			size--;
+		} else if (type & PLUS) {
+			sign = '+';
+			size--;
+		} else if (type & SPACE) {
+			sign = ' ';
+			size--;
+		}
+	}
+	if (type & SPECIAL) {
+		if (base == 16)
+			size -= 2;
+		else if (base == 8)
+			size--;
+	}
+	i = 0;
+	if (num == 0)
+		tmp[i++] = '0';
+	else
+		while (num != 0)
+			tmp[i++] = (digits[__do_div(num, base)] | locase);
+	if (i > precision)
+		precision = i;
+	size -= precision;
+	if (!(type & (ZEROPAD + LEFT)))
+		while (size-- > 0)
+			APPEND_BUFFER_SAFE(str, end, ' ');
+	if (sign)
+		APPEND_BUFFER_SAFE(str, end, sign);
+	if (type & SPECIAL) {
+		if (base == 8)
+			APPEND_BUFFER_SAFE(str, end, '0');
+		else if (base == 16) {
+			APPEND_BUFFER_SAFE(str, end, '0');
+			APPEND_BUFFER_SAFE(str, end, 'x');
+		}
+	}
+	if (!(type & LEFT))
+		while (size-- > 0)
+			APPEND_BUFFER_SAFE(str, end, c);
+	while (i < precision--)
+		APPEND_BUFFER_SAFE(str, end, '0');
+	while (i-- > 0)
+		APPEND_BUFFER_SAFE(str, end, tmp[i]);
+	while (size-- > 0)
+		APPEND_BUFFER_SAFE(str, end, ' ');
+
+	return str;
+}
+
+int guest_vsnprintf(char *buf, int n, const char *fmt, va_list args)
+{
+	char *str, *end;
+	const char *s;
+	uint64_t num;
+	int i, base;
+	int len;
+
+	int flags;		/* flags to number() */
+
+	int field_width;	/* width of output field */
+	int precision;		/*
+				 * min. # of digits for integers; max
+				 * number of chars for from string
+				 */
+	int qualifier;		/* 'h', 'l', or 'L' for integer fields */
+
+	end = buf + n;
+	GUEST_ASSERT(buf < end);
+	GUEST_ASSERT(n > 0);
+
+	for (str = buf; *fmt; ++fmt) {
+		if (*fmt != '%') {
+			APPEND_BUFFER_SAFE(str, end, *fmt);
+			continue;
+		}
+
+		/* process flags */
+		flags = 0;
+repeat:
+		++fmt;		/* this also skips first '%' */
+		switch (*fmt) {
+		case '-':
+			flags |= LEFT;
+			goto repeat;
+		case '+':
+			flags |= PLUS;
+			goto repeat;
+		case ' ':
+			flags |= SPACE;
+			goto repeat;
+		case '#':
+			flags |= SPECIAL;
+			goto repeat;
+		case '0':
+			flags |= ZEROPAD;
+			goto repeat;
+		}
+
+		/* get field width */
+		field_width = -1;
+		if (isdigit(*fmt))
+			field_width = skip_atoi(&fmt);
+		else if (*fmt == '*') {
+			++fmt;
+			/* it's the next argument */
+			field_width = va_arg(args, int);
+			if (field_width < 0) {
+				field_width = -field_width;
+				flags |= LEFT;
+			}
+		}
+
+		/* get the precision */
+		precision = -1;
+		if (*fmt == '.') {
+			++fmt;
+			if (isdigit(*fmt))
+				precision = skip_atoi(&fmt);
+			else if (*fmt == '*') {
+				++fmt;
+				/* it's the next argument */
+				precision = va_arg(args, int);
+			}
+			if (precision < 0)
+				precision = 0;
+		}
+
+		/* get the conversion qualifier */
+		qualifier = -1;
+		if (*fmt == 'h' || *fmt == 'l' || *fmt == 'L') {
+			qualifier = *fmt;
+			++fmt;
+		}
+
+		/* default base */
+		base = 10;
+
+		switch (*fmt) {
+		case 'c':
+			if (!(flags & LEFT))
+				while (--field_width > 0)
+					APPEND_BUFFER_SAFE(str, end, ' ');
+			APPEND_BUFFER_SAFE(str, end,
+					    (uint8_t)va_arg(args, int));
+			while (--field_width > 0)
+				APPEND_BUFFER_SAFE(str, end, ' ');
+			continue;
+
+		case 's':
+			s = va_arg(args, char *);
+			len = strnlen(s, precision);
+
+			if (!(flags & LEFT))
+				while (len < field_width--)
+					APPEND_BUFFER_SAFE(str, end, ' ');
+			for (i = 0; i < len; ++i)
+				APPEND_BUFFER_SAFE(str, end, *s++);
+			while (len < field_width--)
+				APPEND_BUFFER_SAFE(str, end, ' ');
+			continue;
+
+		case 'p':
+			if (field_width == -1) {
+				field_width = 2 * sizeof(void *);
+				flags |= SPECIAL | SMALL | ZEROPAD;
+			}
+			str = number(str, end,
+				     (uint64_t)va_arg(args, void *), 16,
+				     field_width, precision, flags);
+			continue;
+
+		case 'n':
+			if (qualifier == 'l') {
+				long *ip = va_arg(args, long *);
+				*ip = (str - buf);
+			} else {
+				int *ip = va_arg(args, int *);
+				*ip = (str - buf);
+			}
+			continue;
+
+		case '%':
+			APPEND_BUFFER_SAFE(str, end, '%');
+			continue;
+
+		/* integer number formats - set up the flags and "break" */
+		case 'o':
+			base = 8;
+			break;
+
+		case 'x':
+			flags |= SMALL;
+		case 'X':
+			base = 16;
+			break;
+
+		case 'd':
+		case 'i':
+			flags |= SIGN;
+		case 'u':
+			break;
+
+		default:
+			APPEND_BUFFER_SAFE(str, end, '%');
+			if (*fmt)
+				APPEND_BUFFER_SAFE(str, end, *fmt);
+			else
+				--fmt;
+			continue;
+		}
+		if (qualifier == 'l')
+			num = va_arg(args, uint64_t);
+		else if (qualifier == 'h') {
+			num = (uint16_t)va_arg(args, int);
+			if (flags & SIGN)
+				num = (int16_t)num;
+		} else if (flags & SIGN)
+			num = va_arg(args, int);
+		else
+			num = va_arg(args, uint32_t);
+		str = number(str, end, num, base, field_width, precision, flags);
+	}
+
+	GUEST_ASSERT(str < end);
+	*str = '\0';
+	return str - buf;
+}
+
+int guest_snprintf(char *buf, int n, const char *fmt, ...)
+{
+	va_list va;
+	int len;
+
+	va_start(va, fmt);
+	len = guest_vsnprintf(buf, n, fmt, va);
+	va_end(va);
+
+	return len;
+}

From 215a681710a554b224d743e4a9cd68965889713c Mon Sep 17 00:00:00 2001
From: Aaron Lewis <aaronlewis@google.com>
Date: Fri, 28 Jul 2023 17:36:15 -0700
Subject: [PATCH 0233/1189] KVM: selftests: Add additional pages to the guest
 to accommodate ucall

Add additional pages to the guest to account for the number of pages
the ucall headers need.  The only reason things worked before is the
ucall headers are fairly small.  If they were ever to increase in
size the guest could run out of memory.

This is done in preparation for adding string formatting options to
the guest through the ucall framework which increases the size of
the ucall headers.

Fixes: 426729b2cf2e ("KVM: selftests: Add ucall pool based implementation")
Signed-off-by: Aaron Lewis <aaronlewis@google.com>
Link: https://lore.kernel.org/r/20230729003643.1053367-7-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/include/ucall_common.h | 1 +
 tools/testing/selftests/kvm/lib/kvm_util.c         | 4 ++++
 tools/testing/selftests/kvm/lib/ucall_common.c     | 5 +++++
 3 files changed, 10 insertions(+)

diff --git a/tools/testing/selftests/kvm/include/ucall_common.h b/tools/testing/selftests/kvm/include/ucall_common.h
index 1a6aaef5ccae..bcbb362aa77f 100644
--- a/tools/testing/selftests/kvm/include/ucall_common.h
+++ b/tools/testing/selftests/kvm/include/ucall_common.h
@@ -34,6 +34,7 @@ void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu);
 void ucall(uint64_t cmd, int nargs, ...);
 uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc);
 void ucall_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa);
+int ucall_nr_pages_required(uint64_t page_size);
 
 /*
  * Perform userspace call without any associated data.  This bare call avoids
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 3170d7a4520b..7a8af1821f5d 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -312,6 +312,7 @@ static uint64_t vm_nr_pages_required(enum vm_guest_mode mode,
 				     uint32_t nr_runnable_vcpus,
 				     uint64_t extra_mem_pages)
 {
+	uint64_t page_size = vm_guest_mode_params[mode].page_size;
 	uint64_t nr_pages;
 
 	TEST_ASSERT(nr_runnable_vcpus,
@@ -340,6 +341,9 @@ static uint64_t vm_nr_pages_required(enum vm_guest_mode mode,
 	 */
 	nr_pages += (nr_pages + extra_mem_pages) / PTES_PER_MIN_PAGE * 2;
 
+	/* Account for the number of pages needed by ucall. */
+	nr_pages += ucall_nr_pages_required(page_size);
+
 	return vm_adjust_num_guest_pages(mode, nr_pages);
 }
 
diff --git a/tools/testing/selftests/kvm/lib/ucall_common.c b/tools/testing/selftests/kvm/lib/ucall_common.c
index 2f0e2ea941cc..77ada362273d 100644
--- a/tools/testing/selftests/kvm/lib/ucall_common.c
+++ b/tools/testing/selftests/kvm/lib/ucall_common.c
@@ -11,6 +11,11 @@ struct ucall_header {
 	struct ucall ucalls[KVM_MAX_VCPUS];
 };
 
+int ucall_nr_pages_required(uint64_t page_size)
+{
+	return align_up(sizeof(struct ucall_header), page_size) / page_size;
+}
+
 /*
  * ucall_pool holds per-VM values (global data is duplicated by each VM), it
  * must not be accessed from host code.

From 57e5c1fef5ecc7c346ff971817ba6985643e0a24 Mon Sep 17 00:00:00 2001
From: Aaron Lewis <aaronlewis@google.com>
Date: Fri, 28 Jul 2023 17:36:16 -0700
Subject: [PATCH 0234/1189] KVM: selftests: Add string formatting options to
 ucall

Add more flexibility to guest debugging and testing by adding
GUEST_PRINTF() and GUEST_ASSERT_FMT() to the ucall framework.

Add a sized buffer to the ucall structure to hold the formatted string,
i.e. to allow the guest to easily resolve the string, and thus avoid the
ugly pattern of the host side having to make assumptions about the desired
format, as well as having to pass around a large number of parameters.

The buffer size was chosen to accommodate most use cases, and based on
similar usage.  E.g. printf() uses the same size buffer in
arch/x86/boot/printf.c.  And 1KiB ought to be enough for anybody.

Signed-off-by: Aaron Lewis <aaronlewis@google.com>
[sean: massage changelog, wrap macro param in ()]
Link: https://lore.kernel.org/r/20230729003643.1053367-8-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../selftests/kvm/include/ucall_common.h        |  7 +++++++
 tools/testing/selftests/kvm/lib/ucall_common.c  | 17 +++++++++++++++++
 2 files changed, 24 insertions(+)

diff --git a/tools/testing/selftests/kvm/include/ucall_common.h b/tools/testing/selftests/kvm/include/ucall_common.h
index bcbb362aa77f..b5548aeba9f0 100644
--- a/tools/testing/selftests/kvm/include/ucall_common.h
+++ b/tools/testing/selftests/kvm/include/ucall_common.h
@@ -13,15 +13,18 @@ enum {
 	UCALL_NONE,
 	UCALL_SYNC,
 	UCALL_ABORT,
+	UCALL_PRINTF,
 	UCALL_DONE,
 	UCALL_UNHANDLED,
 };
 
 #define UCALL_MAX_ARGS 7
+#define UCALL_BUFFER_LEN 1024
 
 struct ucall {
 	uint64_t cmd;
 	uint64_t args[UCALL_MAX_ARGS];
+	char buffer[UCALL_BUFFER_LEN];
 
 	/* Host virtual address of this struct. */
 	struct ucall *hva;
@@ -32,6 +35,7 @@ void ucall_arch_do_ucall(vm_vaddr_t uc);
 void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu);
 
 void ucall(uint64_t cmd, int nargs, ...);
+void ucall_fmt(uint64_t cmd, const char *fmt, ...);
 uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc);
 void ucall_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa);
 int ucall_nr_pages_required(uint64_t page_size);
@@ -47,8 +51,11 @@ int ucall_nr_pages_required(uint64_t page_size);
 #define GUEST_SYNC_ARGS(stage, arg1, arg2, arg3, arg4)	\
 				ucall(UCALL_SYNC, 6, "hello", stage, arg1, arg2, arg3, arg4)
 #define GUEST_SYNC(stage)	ucall(UCALL_SYNC, 2, "hello", stage)
+#define GUEST_PRINTF(_fmt, _args...) ucall_fmt(UCALL_PRINTF, _fmt, ##_args)
 #define GUEST_DONE()		ucall(UCALL_DONE, 0)
 
+#define REPORT_GUEST_PRINTF(ucall) pr_info("%s", (ucall).buffer)
+
 enum guest_assert_builtin_args {
 	GUEST_ERROR_STRING,
 	GUEST_FILE,
diff --git a/tools/testing/selftests/kvm/lib/ucall_common.c b/tools/testing/selftests/kvm/lib/ucall_common.c
index 77ada362273d..b507db91139b 100644
--- a/tools/testing/selftests/kvm/lib/ucall_common.c
+++ b/tools/testing/selftests/kvm/lib/ucall_common.c
@@ -75,6 +75,23 @@ static void ucall_free(struct ucall *uc)
 	clear_bit(uc - ucall_pool->ucalls, ucall_pool->in_use);
 }
 
+void ucall_fmt(uint64_t cmd, const char *fmt, ...)
+{
+	struct ucall *uc;
+	va_list va;
+
+	uc = ucall_alloc();
+	uc->cmd = cmd;
+
+	va_start(va, fmt);
+	guest_vsnprintf(uc->buffer, UCALL_BUFFER_LEN, fmt, va);
+	va_end(va);
+
+	ucall_arch_do_ucall((vm_vaddr_t)uc->hva);
+
+	ucall_free(uc);
+}
+
 void ucall(uint64_t cmd, int nargs, ...)
 {
 	struct ucall *uc;

From 289c2b4db8f336b96d918eb0c548382aee71ed79 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:17 -0700
Subject: [PATCH 0235/1189] KVM: selftests: Add formatted guest assert support
 in ucall framework

Add printf-based GUEST_ASSERT macros and accompanying host-side support to
provide an assert-specific versions of GUEST_PRINTF().  To make it easier
to parse assert messages, for humans and bots alike, preserve/use the same
layout as host asserts, e.g. in the example below, the reported expression,
file, line number, and message are from the guest assertion, not the host
reporting of the assertion.

The call stack still captures the host reporting, but capturing the guest
stack is a less pressing concern, i.e. can be done in the future, and an
optimal solution would capture *both* the host and guest stacks, i.e.
capturing the host stack isn't an outright bug.

  Running soft int test
  ==== Test Assertion Failure ====
    x86_64/svm_nested_soft_inject_test.c:39: regs->rip != (unsigned long)l2_guest_code_int
    pid=214104 tid=214104 errno=4 - Interrupted system call
       1	0x0000000000401b35: run_test at svm_nested_soft_inject_test.c:191
       2	0x00000000004017d2: main at svm_nested_soft_inject_test.c:212
       3	0x0000000000415b03: __libc_start_call_main at libc-start.o:?
       4	0x000000000041714f: __libc_start_main_impl at ??:?
       5	0x0000000000401660: _start at ??:?
    Expected IRQ at RIP 0x401e50, received IRQ at 0x401e50

Don't bother sharing code between ucall_assert() and ucall_fmt(), as
forwarding the variable arguments would either require using macros or
building a va_list, i.e. would make the code less readable and/or require
just as much copy+paste code anyways.

Gate the new macros with a flag so that tests can more or less be switched
over one-by-one.  The slow conversion won't be perfect, e.g. library code
won't pick up the flag, but the only asserts in library code are of the
vanilla GUEST_ASSERT() variety, i.e. don't print out variables.

Add a temporary alias to GUEST_ASSERT_1() to fudge around ARM's
arch_timer.h header using GUEST_ASSERT_1(), thus thwarting any attempt to
convert tests one-by-one.

Link: https://lore.kernel.org/r/20230729003643.1053367-9-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../selftests/kvm/include/ucall_common.h      | 48 +++++++++++++++++++
 .../testing/selftests/kvm/lib/ucall_common.c  | 22 +++++++++
 2 files changed, 70 insertions(+)

diff --git a/tools/testing/selftests/kvm/include/ucall_common.h b/tools/testing/selftests/kvm/include/ucall_common.h
index b5548aeba9f0..4ce11c15285a 100644
--- a/tools/testing/selftests/kvm/include/ucall_common.h
+++ b/tools/testing/selftests/kvm/include/ucall_common.h
@@ -36,6 +36,8 @@ void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu);
 
 void ucall(uint64_t cmd, int nargs, ...);
 void ucall_fmt(uint64_t cmd, const char *fmt, ...);
+void ucall_assert(uint64_t cmd, const char *exp, const char *file,
+		  unsigned int line, const char *fmt, ...);
 uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc);
 void ucall_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa);
 int ucall_nr_pages_required(uint64_t page_size);
@@ -63,6 +65,50 @@ enum guest_assert_builtin_args {
 	GUEST_ASSERT_BUILTIN_NARGS
 };
 
+#ifdef USE_GUEST_ASSERT_PRINTF
+#define ____GUEST_ASSERT(_condition, _exp, _fmt, _args...)				\
+do {											\
+	if (!(_condition))								\
+		ucall_assert(UCALL_ABORT, _exp, __FILE__, __LINE__, _fmt, ##_args);	\
+} while (0)
+
+#define __GUEST_ASSERT(_condition, _fmt, _args...)				\
+	____GUEST_ASSERT(_condition, #_condition, _fmt, ##_args)
+
+#define GUEST_ASSERT(_condition)						\
+	__GUEST_ASSERT(_condition, #_condition)
+
+#define GUEST_FAIL(_fmt, _args...)						\
+	ucall_assert(UCALL_ABORT, "Unconditional guest failure",		\
+		     __FILE__, __LINE__, _fmt, ##_args)
+
+#define GUEST_ASSERT_EQ(a, b)							\
+do {										\
+	typeof(a) __a = (a);							\
+	typeof(b) __b = (b);							\
+	____GUEST_ASSERT(__a == __b, #a " == " #b, "%#lx != %#lx (%s != %s)",	\
+			 (unsigned long)(__a), (unsigned long)(__b), #a, #b);	\
+} while (0)
+
+#define GUEST_ASSERT_NE(a, b)							\
+do {										\
+	typeof(a) __a = (a);							\
+	typeof(b) __b = (b);							\
+	____GUEST_ASSERT(__a != __b, #a " != " #b, "%#lx == %#lx (%s == %s)",	\
+			 (unsigned long)(__a), (unsigned long)(__b), #a, #b);	\
+} while (0)
+
+#define REPORT_GUEST_ASSERT(ucall)						\
+	test_assert(false, (const char *)(ucall).args[GUEST_ERROR_STRING],	\
+		    (const char *)(ucall).args[GUEST_FILE],			\
+		    (ucall).args[GUEST_LINE], "%s", (ucall).buffer)
+
+/* FIXME: Drop this alias once the param-based guest asserts are gone. */
+#define GUEST_ASSERT_1(_condition, arg1) \
+	__GUEST_ASSERT(_condition, "arg1 = 0x%lx", arg1)
+
+#else
+
 #define __GUEST_ASSERT(_condition, _condstr, _nargs, _args...)		\
 do {									\
 	if (!(_condition))						\
@@ -129,4 +175,6 @@ do {									\
 #define REPORT_GUEST_ASSERT_N(ucall, fmt, args...)	\
 	__REPORT_GUEST_ASSERT((ucall), fmt, ##args)
 
+#endif /* USE_GUEST_ASSERT_PRINTF */
+
 #endif /* SELFTEST_KVM_UCALL_COMMON_H */
diff --git a/tools/testing/selftests/kvm/lib/ucall_common.c b/tools/testing/selftests/kvm/lib/ucall_common.c
index b507db91139b..816a3fa109bf 100644
--- a/tools/testing/selftests/kvm/lib/ucall_common.c
+++ b/tools/testing/selftests/kvm/lib/ucall_common.c
@@ -75,6 +75,28 @@ static void ucall_free(struct ucall *uc)
 	clear_bit(uc - ucall_pool->ucalls, ucall_pool->in_use);
 }
 
+void ucall_assert(uint64_t cmd, const char *exp, const char *file,
+		  unsigned int line, const char *fmt, ...)
+{
+	struct ucall *uc;
+	va_list va;
+
+	uc = ucall_alloc();
+	uc->cmd = cmd;
+
+	WRITE_ONCE(uc->args[GUEST_ERROR_STRING], (uint64_t)(exp));
+	WRITE_ONCE(uc->args[GUEST_FILE], (uint64_t)(file));
+	WRITE_ONCE(uc->args[GUEST_LINE], line);
+
+	va_start(va, fmt);
+	guest_vsnprintf(uc->buffer, UCALL_BUFFER_LEN, fmt, va);
+	va_end(va);
+
+	ucall_arch_do_ucall((vm_vaddr_t)uc->hva);
+
+	ucall_free(uc);
+}
+
 void ucall_fmt(uint64_t cmd, const char *fmt, ...)
 {
 	struct ucall *uc;

From b35f4c73d389d3b04e5edf3d1fd041ed3070228b Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Mon, 31 Jul 2023 13:30:24 -0700
Subject: [PATCH 0236/1189] KVM: selftests: Add arch ucall.h and inline simple
 arch hooks

Add an architecture specific ucall.h and inline the simple arch hooks,
e.g. the init hook for everything except ARM, and the actual "do ucall"
hook for everything except x86 (which should be simple, but temporarily
isn't due to carrying a workaround).

Having a per-arch ucall header will allow adding a #define for the
expected KVM exit reason for a ucall that is colocated (for everything
except x86) with the ucall itself.

Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20230731203026.1192091-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../selftests/kvm/include/aarch64/ucall.h      | 18 ++++++++++++++++++
 .../selftests/kvm/include/riscv/ucall.h        | 18 ++++++++++++++++++
 .../selftests/kvm/include/s390x/ucall.h        | 17 +++++++++++++++++
 .../selftests/kvm/include/ucall_common.h       |  1 +
 .../selftests/kvm/include/x86_64/ucall.h       | 11 +++++++++++
 .../testing/selftests/kvm/lib/aarch64/ucall.c  | 11 +----------
 tools/testing/selftests/kvm/lib/riscv/ucall.c  | 11 -----------
 tools/testing/selftests/kvm/lib/s390x/ucall.c  | 10 ----------
 tools/testing/selftests/kvm/lib/x86_64/ucall.c |  4 ----
 9 files changed, 66 insertions(+), 35 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/include/aarch64/ucall.h
 create mode 100644 tools/testing/selftests/kvm/include/riscv/ucall.h
 create mode 100644 tools/testing/selftests/kvm/include/s390x/ucall.h
 create mode 100644 tools/testing/selftests/kvm/include/x86_64/ucall.h

diff --git a/tools/testing/selftests/kvm/include/aarch64/ucall.h b/tools/testing/selftests/kvm/include/aarch64/ucall.h
new file mode 100644
index 000000000000..fe65fdf4f0d3
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/aarch64/ucall.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef SELFTEST_KVM_UCALL_H
+#define SELFTEST_KVM_UCALL_H
+
+#include "kvm_util_base.h"
+
+/*
+ * ucall_exit_mmio_addr holds per-VM values (global data is duplicated by each
+ * VM), it must not be accessed from host code.
+ */
+extern vm_vaddr_t *ucall_exit_mmio_addr;
+
+static inline void ucall_arch_do_ucall(vm_vaddr_t uc)
+{
+	WRITE_ONCE(*ucall_exit_mmio_addr, uc);
+}
+
+#endif
diff --git a/tools/testing/selftests/kvm/include/riscv/ucall.h b/tools/testing/selftests/kvm/include/riscv/ucall.h
new file mode 100644
index 000000000000..86ed0500972b
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/riscv/ucall.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef SELFTEST_KVM_UCALL_H
+#define SELFTEST_KVM_UCALL_H
+
+#include "processor.h"
+
+static inline void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
+{
+}
+
+static inline void ucall_arch_do_ucall(vm_vaddr_t uc)
+{
+	sbi_ecall(KVM_RISCV_SELFTESTS_SBI_EXT,
+		  KVM_RISCV_SELFTESTS_SBI_UCALL,
+		  uc, 0, 0, 0, 0, 0);
+}
+
+#endif
diff --git a/tools/testing/selftests/kvm/include/s390x/ucall.h b/tools/testing/selftests/kvm/include/s390x/ucall.h
new file mode 100644
index 000000000000..47ad4b1fbccb
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/s390x/ucall.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef SELFTEST_KVM_UCALL_H
+#define SELFTEST_KVM_UCALL_H
+
+#include "kvm_util_base.h"
+
+static inline void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
+{
+}
+
+static inline void ucall_arch_do_ucall(vm_vaddr_t uc)
+{
+	/* Exit via DIAGNOSE 0x501 (normally used for breakpoints) */
+	asm volatile ("diag 0,%0,0x501" : : "a"(uc) : "memory");
+}
+
+#endif
diff --git a/tools/testing/selftests/kvm/include/ucall_common.h b/tools/testing/selftests/kvm/include/ucall_common.h
index 4ce11c15285a..9e5948dab030 100644
--- a/tools/testing/selftests/kvm/include/ucall_common.h
+++ b/tools/testing/selftests/kvm/include/ucall_common.h
@@ -7,6 +7,7 @@
 #ifndef SELFTEST_KVM_UCALL_COMMON_H
 #define SELFTEST_KVM_UCALL_COMMON_H
 #include "test_util.h"
+#include "ucall.h"
 
 /* Common ucalls */
 enum {
diff --git a/tools/testing/selftests/kvm/include/x86_64/ucall.h b/tools/testing/selftests/kvm/include/x86_64/ucall.h
new file mode 100644
index 000000000000..05cc69b0d550
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/x86_64/ucall.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef SELFTEST_KVM_UCALL_H
+#define SELFTEST_KVM_UCALL_H
+
+#include "kvm_util_base.h"
+
+static inline void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
+{
+}
+
+#endif
diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
index f212bd8ab93d..ddab0ce89d4d 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
@@ -6,11 +6,7 @@
  */
 #include "kvm_util.h"
 
-/*
- * ucall_exit_mmio_addr holds per-VM values (global data is duplicated by each
- * VM), it must not be accessed from host code.
- */
-static vm_vaddr_t *ucall_exit_mmio_addr;
+vm_vaddr_t *ucall_exit_mmio_addr;
 
 void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
 {
@@ -23,11 +19,6 @@ void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
 	write_guest_global(vm, ucall_exit_mmio_addr, (vm_vaddr_t *)mmio_gva);
 }
 
-void ucall_arch_do_ucall(vm_vaddr_t uc)
-{
-	WRITE_ONCE(*ucall_exit_mmio_addr, uc);
-}
-
 void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
diff --git a/tools/testing/selftests/kvm/lib/riscv/ucall.c b/tools/testing/selftests/kvm/lib/riscv/ucall.c
index 9a3476a2dfca..fe6d1004f018 100644
--- a/tools/testing/selftests/kvm/lib/riscv/ucall.c
+++ b/tools/testing/selftests/kvm/lib/riscv/ucall.c
@@ -10,10 +10,6 @@
 #include "kvm_util.h"
 #include "processor.h"
 
-void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
-{
-}
-
 struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
 			unsigned long arg1, unsigned long arg2,
 			unsigned long arg3, unsigned long arg4,
@@ -40,13 +36,6 @@ struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
 	return ret;
 }
 
-void ucall_arch_do_ucall(vm_vaddr_t uc)
-{
-	sbi_ecall(KVM_RISCV_SELFTESTS_SBI_EXT,
-		  KVM_RISCV_SELFTESTS_SBI_UCALL,
-		  uc, 0, 0, 0, 0, 0);
-}
-
 void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
diff --git a/tools/testing/selftests/kvm/lib/s390x/ucall.c b/tools/testing/selftests/kvm/lib/s390x/ucall.c
index a7f02dc372cf..cca98734653d 100644
--- a/tools/testing/selftests/kvm/lib/s390x/ucall.c
+++ b/tools/testing/selftests/kvm/lib/s390x/ucall.c
@@ -6,16 +6,6 @@
  */
 #include "kvm_util.h"
 
-void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
-{
-}
-
-void ucall_arch_do_ucall(vm_vaddr_t uc)
-{
-	/* Exit via DIAGNOSE 0x501 (normally used for breakpoints) */
-	asm volatile ("diag 0,%0,0x501" : : "a"(uc) : "memory");
-}
-
 void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
diff --git a/tools/testing/selftests/kvm/lib/x86_64/ucall.c b/tools/testing/selftests/kvm/lib/x86_64/ucall.c
index a53df3ece2f8..1265cecc7dd1 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/ucall.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/ucall.c
@@ -8,10 +8,6 @@
 
 #define UCALL_PIO_PORT ((uint16_t)0x1000)
 
-void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
-{
-}
-
 void ucall_arch_do_ucall(vm_vaddr_t uc)
 {
 	/*

From edb5b700f9f8a21e57aef14cf795fb958cc38628 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Mon, 31 Jul 2023 13:30:25 -0700
Subject: [PATCH 0237/1189] KVM: selftests: Add #define of expected KVM exit
 reason for ucall

Define the expected architecture specific exit reason for a successful
ucall so that common tests can assert that a ucall occurred without the
test needing to implement arch specific code.

Suggested-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20230731203026.1192091-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/include/aarch64/ucall.h | 2 ++
 tools/testing/selftests/kvm/include/riscv/ucall.h   | 2 ++
 tools/testing/selftests/kvm/include/s390x/ucall.h   | 2 ++
 tools/testing/selftests/kvm/include/x86_64/ucall.h  | 2 ++
 4 files changed, 8 insertions(+)

diff --git a/tools/testing/selftests/kvm/include/aarch64/ucall.h b/tools/testing/selftests/kvm/include/aarch64/ucall.h
index fe65fdf4f0d3..4b68f37efd36 100644
--- a/tools/testing/selftests/kvm/include/aarch64/ucall.h
+++ b/tools/testing/selftests/kvm/include/aarch64/ucall.h
@@ -4,6 +4,8 @@
 
 #include "kvm_util_base.h"
 
+#define UCALL_EXIT_REASON       KVM_EXIT_MMIO
+
 /*
  * ucall_exit_mmio_addr holds per-VM values (global data is duplicated by each
  * VM), it must not be accessed from host code.
diff --git a/tools/testing/selftests/kvm/include/riscv/ucall.h b/tools/testing/selftests/kvm/include/riscv/ucall.h
index 86ed0500972b..be46eb32ec27 100644
--- a/tools/testing/selftests/kvm/include/riscv/ucall.h
+++ b/tools/testing/selftests/kvm/include/riscv/ucall.h
@@ -4,6 +4,8 @@
 
 #include "processor.h"
 
+#define UCALL_EXIT_REASON       KVM_EXIT_RISCV_SBI
+
 static inline void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
 {
 }
diff --git a/tools/testing/selftests/kvm/include/s390x/ucall.h b/tools/testing/selftests/kvm/include/s390x/ucall.h
index 47ad4b1fbccb..b231bf2e49d6 100644
--- a/tools/testing/selftests/kvm/include/s390x/ucall.h
+++ b/tools/testing/selftests/kvm/include/s390x/ucall.h
@@ -4,6 +4,8 @@
 
 #include "kvm_util_base.h"
 
+#define UCALL_EXIT_REASON       KVM_EXIT_S390_SIEIC
+
 static inline void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
 {
 }
diff --git a/tools/testing/selftests/kvm/include/x86_64/ucall.h b/tools/testing/selftests/kvm/include/x86_64/ucall.h
index 05cc69b0d550..06b244bd06ee 100644
--- a/tools/testing/selftests/kvm/include/x86_64/ucall.h
+++ b/tools/testing/selftests/kvm/include/x86_64/ucall.h
@@ -4,6 +4,8 @@
 
 #include "kvm_util_base.h"
 
+#define UCALL_EXIT_REASON       KVM_EXIT_IO
+
 static inline void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
 {
 }

From 5d1d46f9d56fb567718175cb0cb7a084d444a9d4 Mon Sep 17 00:00:00 2001
From: Aaron Lewis <aaronlewis@google.com>
Date: Mon, 31 Jul 2023 13:30:26 -0700
Subject: [PATCH 0238/1189] KVM: selftests: Add a selftest for guest prints and
 formatted asserts

Add a test to exercise the various features in KVM selftest's local
snprintf() and compare them to LIBC's snprintf() to ensure they behave
the same.

This is not an exhaustive test.  KVM's local snprintf() does not
implement all the features LIBC does, e.g. KVM's local snprintf() does
not support floats or doubles, so testing for those features were
excluded.

Testing was added for the features that are expected to work to
support a minimal version of printf() in the guest.

Signed-off-by: Aaron Lewis <aaronlewis@google.com>
[sean: use UCALL_EXIT_REASON, enable for all architectures]
Link: https://lore.kernel.org/r/20230731203026.1192091-4-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/Makefile          |   4 +
 .../testing/selftests/kvm/guest_print_test.c  | 221 ++++++++++++++++++
 2 files changed, 225 insertions(+)
 create mode 100644 tools/testing/selftests/kvm/guest_print_test.c

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index f65889f5a083..77026907968f 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -123,6 +123,7 @@ TEST_GEN_PROGS_x86_64 += access_tracking_perf_test
 TEST_GEN_PROGS_x86_64 += demand_paging_test
 TEST_GEN_PROGS_x86_64 += dirty_log_test
 TEST_GEN_PROGS_x86_64 += dirty_log_perf_test
+TEST_GEN_PROGS_x86_64 += guest_print_test
 TEST_GEN_PROGS_x86_64 += hardware_disable_test
 TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus
 TEST_GEN_PROGS_x86_64 += kvm_page_table_test
@@ -153,6 +154,7 @@ TEST_GEN_PROGS_aarch64 += access_tracking_perf_test
 TEST_GEN_PROGS_aarch64 += demand_paging_test
 TEST_GEN_PROGS_aarch64 += dirty_log_test
 TEST_GEN_PROGS_aarch64 += dirty_log_perf_test
+TEST_GEN_PROGS_aarch64 += guest_print_test
 TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus
 TEST_GEN_PROGS_aarch64 += kvm_page_table_test
 TEST_GEN_PROGS_aarch64 += memslot_modification_stress_test
@@ -169,6 +171,7 @@ TEST_GEN_PROGS_s390x += s390x/tprot
 TEST_GEN_PROGS_s390x += s390x/cmma_test
 TEST_GEN_PROGS_s390x += demand_paging_test
 TEST_GEN_PROGS_s390x += dirty_log_test
+TEST_GEN_PROGS_s390x += guest_print_test
 TEST_GEN_PROGS_s390x += kvm_create_max_vcpus
 TEST_GEN_PROGS_s390x += kvm_page_table_test
 TEST_GEN_PROGS_s390x += rseq_test
@@ -177,6 +180,7 @@ TEST_GEN_PROGS_s390x += kvm_binary_stats_test
 
 TEST_GEN_PROGS_riscv += demand_paging_test
 TEST_GEN_PROGS_riscv += dirty_log_test
+TEST_GEN_PROGS_riscv += guest_print_test
 TEST_GEN_PROGS_riscv += kvm_create_max_vcpus
 TEST_GEN_PROGS_riscv += kvm_page_table_test
 TEST_GEN_PROGS_riscv += set_memory_region_test
diff --git a/tools/testing/selftests/kvm/guest_print_test.c b/tools/testing/selftests/kvm/guest_print_test.c
new file mode 100644
index 000000000000..267e01d057fb
--- /dev/null
+++ b/tools/testing/selftests/kvm/guest_print_test.c
@@ -0,0 +1,221 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * A test for GUEST_PRINTF
+ *
+ * Copyright 2022, Google, Inc. and/or its affiliates.
+ */
+#define USE_GUEST_ASSERT_PRINTF 1
+
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+struct guest_vals {
+	uint64_t a;
+	uint64_t b;
+	uint64_t type;
+};
+
+static struct guest_vals vals;
+
+/* GUEST_PRINTF()/GUEST_ASSERT_FMT() does not support float or double. */
+#define TYPE_LIST					\
+TYPE(test_type_i64,  I64,  "%ld",   int64_t)		\
+TYPE(test_type_u64,  U64u, "%lu",   uint64_t)		\
+TYPE(test_type_x64,  U64x, "0x%lx", uint64_t)		\
+TYPE(test_type_X64,  U64X, "0x%lX", uint64_t)		\
+TYPE(test_type_u32,  U32u, "%u",    uint32_t)		\
+TYPE(test_type_x32,  U32x, "0x%x",  uint32_t)		\
+TYPE(test_type_X32,  U32X, "0x%X",  uint32_t)		\
+TYPE(test_type_int,  INT,  "%d",    int)		\
+TYPE(test_type_char, CHAR, "%c",    char)		\
+TYPE(test_type_str,  STR,  "'%s'",  const char *)	\
+TYPE(test_type_ptr,  PTR,  "%p",    uintptr_t)
+
+enum args_type {
+#define TYPE(fn, ext, fmt_t, T) TYPE_##ext,
+	TYPE_LIST
+#undef TYPE
+};
+
+static void run_test(struct kvm_vcpu *vcpu, const char *expected_printf,
+		     const char *expected_assert);
+
+#define BUILD_TYPE_STRINGS_AND_HELPER(fn, ext, fmt_t, T)		     \
+const char *PRINTF_FMT_##ext = "Got params a = " fmt_t " and b = " fmt_t;    \
+const char *ASSERT_FMT_##ext = "Expected " fmt_t ", got " fmt_t " instead";  \
+static void fn(struct kvm_vcpu *vcpu, T a, T b)				     \
+{									     \
+	char expected_printf[UCALL_BUFFER_LEN];				     \
+	char expected_assert[UCALL_BUFFER_LEN];				     \
+									     \
+	snprintf(expected_printf, UCALL_BUFFER_LEN, PRINTF_FMT_##ext, a, b); \
+	snprintf(expected_assert, UCALL_BUFFER_LEN, ASSERT_FMT_##ext, a, b); \
+	vals = (struct guest_vals){ (uint64_t)a, (uint64_t)b, TYPE_##ext };  \
+	sync_global_to_guest(vcpu->vm, vals);				     \
+	run_test(vcpu, expected_printf, expected_assert);		     \
+}
+
+#define TYPE(fn, ext, fmt_t, T) \
+		BUILD_TYPE_STRINGS_AND_HELPER(fn, ext, fmt_t, T)
+	TYPE_LIST
+#undef TYPE
+
+static void guest_code(void)
+{
+	while (1) {
+		switch (vals.type) {
+#define TYPE(fn, ext, fmt_t, T)							\
+		case TYPE_##ext:						\
+			GUEST_PRINTF(PRINTF_FMT_##ext, vals.a, vals.b);		\
+			__GUEST_ASSERT(vals.a == vals.b,			\
+				       ASSERT_FMT_##ext, vals.a, vals.b);	\
+			break;
+		TYPE_LIST
+#undef TYPE
+		default:
+			GUEST_SYNC(vals.type);
+		}
+
+		GUEST_DONE();
+	}
+}
+
+/*
+ * Unfortunately this gets a little messy because 'assert_msg' doesn't
+ * just contains the matching string, it also contains additional assert
+ * info.  Fortunately the part that matches should be at the very end of
+ * 'assert_msg'.
+ */
+static void ucall_abort(const char *assert_msg, const char *expected_assert_msg)
+{
+	int len_str = strlen(assert_msg);
+	int len_substr = strlen(expected_assert_msg);
+	int offset = len_str - len_substr;
+
+	TEST_ASSERT(len_substr <= len_str,
+		    "Expected '%s' to be a substring of '%s'\n",
+		    assert_msg, expected_assert_msg);
+
+	TEST_ASSERT(strcmp(&assert_msg[offset], expected_assert_msg) == 0,
+		    "Unexpected mismatch. Expected: '%s', got: '%s'",
+		    expected_assert_msg, &assert_msg[offset]);
+}
+
+static void run_test(struct kvm_vcpu *vcpu, const char *expected_printf,
+		     const char *expected_assert)
+{
+	struct kvm_run *run = vcpu->run;
+	struct ucall uc;
+
+	while (1) {
+		vcpu_run(vcpu);
+
+		TEST_ASSERT(run->exit_reason == UCALL_EXIT_REASON,
+			    "Unexpected exit reason: %u (%s),\n",
+			    run->exit_reason, exit_reason_str(run->exit_reason));
+
+		switch (get_ucall(vcpu, &uc)) {
+		case UCALL_SYNC:
+			TEST_FAIL("Unknown 'args_type' = %lu", uc.args[1]);
+			break;
+		case UCALL_PRINTF:
+			TEST_ASSERT(strcmp(uc.buffer, expected_printf) == 0,
+				    "Unexpected mismatch. Expected: '%s', got: '%s'",
+				    expected_printf, uc.buffer);
+			break;
+		case UCALL_ABORT:
+			ucall_abort(uc.buffer, expected_assert);
+			break;
+		case UCALL_DONE:
+			return;
+		default:
+			TEST_FAIL("Unknown ucall %lu", uc.cmd);
+		}
+	}
+}
+
+static void guest_code_limits(void)
+{
+	char test_str[UCALL_BUFFER_LEN + 10];
+
+	memset(test_str, 'a', sizeof(test_str));
+	test_str[sizeof(test_str) - 1] = 0;
+
+	GUEST_PRINTF("%s", test_str);
+}
+
+static void test_limits(void)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_run *run;
+	struct kvm_vm *vm;
+	struct ucall uc;
+
+	vm = vm_create_with_one_vcpu(&vcpu, guest_code_limits);
+	run = vcpu->run;
+	vcpu_run(vcpu);
+
+	TEST_ASSERT(run->exit_reason == UCALL_EXIT_REASON,
+		    "Unexpected exit reason: %u (%s),\n",
+		    run->exit_reason, exit_reason_str(run->exit_reason));
+
+	TEST_ASSERT(get_ucall(vcpu, &uc) == UCALL_ABORT,
+		    "Unexpected ucall command: %lu,  Expected: %u (UCALL_ABORT)\n",
+		    uc.cmd, UCALL_ABORT);
+
+	kvm_vm_free(vm);
+}
+
+int main(int argc, char *argv[])
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+
+	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
+
+	test_type_i64(vcpu, -1, -1);
+	test_type_i64(vcpu, -1,  1);
+	test_type_i64(vcpu, 0x1234567890abcdef, 0x1234567890abcdef);
+	test_type_i64(vcpu, 0x1234567890abcdef, 0x1234567890abcdee);
+
+	test_type_u64(vcpu, 0x1234567890abcdef, 0x1234567890abcdef);
+	test_type_u64(vcpu, 0x1234567890abcdef, 0x1234567890abcdee);
+	test_type_x64(vcpu, 0x1234567890abcdef, 0x1234567890abcdef);
+	test_type_x64(vcpu, 0x1234567890abcdef, 0x1234567890abcdee);
+	test_type_X64(vcpu, 0x1234567890abcdef, 0x1234567890abcdef);
+	test_type_X64(vcpu, 0x1234567890abcdef, 0x1234567890abcdee);
+
+	test_type_u32(vcpu, 0x90abcdef, 0x90abcdef);
+	test_type_u32(vcpu, 0x90abcdef, 0x90abcdee);
+	test_type_x32(vcpu, 0x90abcdef, 0x90abcdef);
+	test_type_x32(vcpu, 0x90abcdef, 0x90abcdee);
+	test_type_X32(vcpu, 0x90abcdef, 0x90abcdef);
+	test_type_X32(vcpu, 0x90abcdef, 0x90abcdee);
+
+	test_type_int(vcpu, -1, -1);
+	test_type_int(vcpu, -1,  1);
+	test_type_int(vcpu,  1,  1);
+
+	test_type_char(vcpu, 'a', 'a');
+	test_type_char(vcpu, 'a', 'A');
+	test_type_char(vcpu, 'a', 'b');
+
+	test_type_str(vcpu, "foo", "foo");
+	test_type_str(vcpu, "foo", "bar");
+
+	test_type_ptr(vcpu, 0x1234567890abcdef, 0x1234567890abcdef);
+	test_type_ptr(vcpu, 0x1234567890abcdef, 0x1234567890abcdee);
+
+	kvm_vm_free(vm);
+
+	test_limits();
+
+	return 0;
+}

From db44e1c871bcf6228b9447aada421088e036692a Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:19 -0700
Subject: [PATCH 0239/1189] KVM: selftests: Convert aarch_timer to printf style
 GUEST_ASSERT

Convert ARM's aarch_timer test to use printf-based GUEST_ASSERT().
To maintain existing functionality, manually print the host information,
e.g. stage and iteration, to stderr prior to reporting the guest assert.

Link: https://lore.kernel.org/r/20230729003643.1053367-11-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../selftests/kvm/aarch64/arch_timer.c        | 22 +++++++++----------
 1 file changed, 10 insertions(+), 12 deletions(-)

diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c
index 8ef370924a02..b53bcf126e6a 100644
--- a/tools/testing/selftests/kvm/aarch64/arch_timer.c
+++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c
@@ -19,6 +19,7 @@
  *
  * Copyright (c) 2021, Google LLC.
  */
+#define USE_GUEST_ASSERT_PRINTF 1
 
 #define _GNU_SOURCE
 
@@ -155,11 +156,13 @@ static void guest_validate_irq(unsigned int intid,
 	xcnt_diff_us = cycles_to_usec(xcnt - shared_data->xcnt);
 
 	/* Make sure we are dealing with the correct timer IRQ */
-	GUEST_ASSERT_2(intid == timer_irq, intid, timer_irq);
+	GUEST_ASSERT_EQ(intid, timer_irq);
 
 	/* Basic 'timer condition met' check */
-	GUEST_ASSERT_3(xcnt >= cval, xcnt, cval, xcnt_diff_us);
-	GUEST_ASSERT_1(xctl & CTL_ISTATUS, xctl);
+	__GUEST_ASSERT(xcnt >= cval,
+		       "xcnt = 0x%llx, cval = 0x%llx, xcnt_diff_us = 0x%llx",
+		       xcnt, cval, xcnt_diff_us);
+	__GUEST_ASSERT(xctl & CTL_ISTATUS, "xcnt = 0x%llx", xcnt);
 
 	WRITE_ONCE(shared_data->nr_iter, shared_data->nr_iter + 1);
 }
@@ -192,8 +195,7 @@ static void guest_run_stage(struct test_vcpu_shared_data *shared_data,
 			TIMER_TEST_ERR_MARGIN_US);
 
 		irq_iter = READ_ONCE(shared_data->nr_iter);
-		GUEST_ASSERT_2(config_iter + 1 == irq_iter,
-				config_iter + 1, irq_iter);
+		GUEST_ASSERT_EQ(config_iter + 1, irq_iter);
 	}
 }
 
@@ -243,13 +245,9 @@ static void *test_vcpu_run(void *arg)
 		break;
 	case UCALL_ABORT:
 		sync_global_from_guest(vm, *shared_data);
-		REPORT_GUEST_ASSERT_N(uc, "values: %lu, %lu; %lu, vcpu %u; stage; %u; iter: %u",
-				      GUEST_ASSERT_ARG(uc, 0),
-				      GUEST_ASSERT_ARG(uc, 1),
-				      GUEST_ASSERT_ARG(uc, 2),
-				      vcpu_idx,
-				      shared_data->guest_stage,
-				      shared_data->nr_iter);
+		fprintf(stderr, "Guest assert failed,  vcpu %u; stage; %u; iter: %u\n",
+			vcpu_idx, shared_data->guest_stage, shared_data->nr_iter);
+		REPORT_GUEST_ASSERT(uc);
 		break;
 	default:
 		TEST_FAIL("Unexpected guest exit\n");

From bac9aeecc387a1436567b6e74f8257f7e8c4d194 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:20 -0700
Subject: [PATCH 0240/1189] KVM: selftests: Convert debug-exceptions to printf
 style GUEST_ASSERT

Convert ARM's debug exceptions  test to use printf-based GUEST_ASSERT().
Opportunistically Use GUEST_ASSERT_EQ() in guest_code_ss() so that the
expected vs. actual values get printed out.

Link: https://lore.kernel.org/r/20230729003643.1053367-12-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/aarch64/debug-exceptions.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
index 637be796086f..fdd5b05e1b0e 100644
--- a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
+++ b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
@@ -1,4 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
+#define USE_GUEST_ASSERT_PRINTF 1
+
 #include <test_util.h>
 #include <kvm_util.h>
 #include <processor.h>
@@ -365,7 +367,7 @@ static void guest_wp_handler(struct ex_regs *regs)
 
 static void guest_ss_handler(struct ex_regs *regs)
 {
-	GUEST_ASSERT_1(ss_idx < 4, ss_idx);
+	__GUEST_ASSERT(ss_idx < 4, "Expected index < 4, got '%u'", ss_idx);
 	ss_addr[ss_idx++] = regs->pc;
 	regs->pstate |= SPSR_SS;
 }
@@ -410,8 +412,8 @@ static void guest_code_ss(int test_cnt)
 		/* Userspace disables Single Step when the end is nigh. */
 		asm volatile("iter_ss_end:\n");
 
-		GUEST_ASSERT(bvr == w_bvr);
-		GUEST_ASSERT(wvr == w_wvr);
+		GUEST_ASSERT_EQ(bvr, w_bvr);
+		GUEST_ASSERT_EQ(wvr, w_wvr);
 	}
 	GUEST_DONE();
 }
@@ -450,7 +452,7 @@ static void test_guest_debug_exceptions(uint8_t bpn, uint8_t wpn, uint8_t ctx_bp
 	vcpu_run(vcpu);
 	switch (get_ucall(vcpu, &uc)) {
 	case UCALL_ABORT:
-		REPORT_GUEST_ASSERT_2(uc, "values: %#lx, %#lx");
+		REPORT_GUEST_ASSERT(uc);
 		break;
 	case UCALL_DONE:
 		goto done;

From af5b41b97f1cc9d766f700197955965872aba4a3 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:21 -0700
Subject: [PATCH 0241/1189] KVM: selftests: Convert ARM's hypercalls test to
 printf style GUEST_ASSERT

Convert ARM's hypercalls test to use printf-based GUEST_ASSERT().
Opportunistically use GUEST_FAIL() to complain about an unexpected stage.

Link: https://lore.kernel.org/r/20230729003643.1053367-13-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../selftests/kvm/aarch64/hypercalls.c        | 20 +++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/kvm/aarch64/hypercalls.c b/tools/testing/selftests/kvm/aarch64/hypercalls.c
index bef1499fb465..94555a7d3c7e 100644
--- a/tools/testing/selftests/kvm/aarch64/hypercalls.c
+++ b/tools/testing/selftests/kvm/aarch64/hypercalls.c
@@ -8,6 +8,7 @@
  * hypercalls are properly masked or unmasked to the guest when disabled or
  * enabled from the KVM userspace, respectively.
  */
+#define USE_GUEST_ASSERT_PRINTF 1
 
 #include <errno.h>
 #include <linux/arm-smccc.h>
@@ -105,15 +106,17 @@ static void guest_test_hvc(const struct test_hvc_info *hc_info)
 		switch (stage) {
 		case TEST_STAGE_HVC_IFACE_FEAT_DISABLED:
 		case TEST_STAGE_HVC_IFACE_FALSE_INFO:
-			GUEST_ASSERT_3(res.a0 == SMCCC_RET_NOT_SUPPORTED,
-					res.a0, hc_info->func_id, hc_info->arg1);
+			__GUEST_ASSERT(res.a0 == SMCCC_RET_NOT_SUPPORTED,
+				       "a0 = 0x%lx, func_id = 0x%x, arg1 = 0x%llx, stage = %u",
+					res.a0, hc_info->func_id, hc_info->arg1, stage);
 			break;
 		case TEST_STAGE_HVC_IFACE_FEAT_ENABLED:
-			GUEST_ASSERT_3(res.a0 != SMCCC_RET_NOT_SUPPORTED,
-					res.a0, hc_info->func_id, hc_info->arg1);
+			__GUEST_ASSERT(res.a0 != SMCCC_RET_NOT_SUPPORTED,
+				       "a0 = 0x%lx, func_id = 0x%x, arg1 = 0x%llx, stage = %u",
+					res.a0, hc_info->func_id, hc_info->arg1, stage);
 			break;
 		default:
-			GUEST_ASSERT_1(0, stage);
+			GUEST_FAIL("Unexpected stage = %u", stage);
 		}
 	}
 }
@@ -132,7 +135,7 @@ static void guest_code(void)
 			guest_test_hvc(false_hvc_info);
 			break;
 		default:
-			GUEST_ASSERT_1(0, stage);
+			GUEST_FAIL("Unexpected stage = %u", stage);
 		}
 
 		GUEST_SYNC(stage);
@@ -290,10 +293,7 @@ static void test_run(void)
 			guest_done = true;
 			break;
 		case UCALL_ABORT:
-			REPORT_GUEST_ASSERT_N(uc, "values: 0x%lx, 0x%lx; 0x%lx, stage: %u",
-					      GUEST_ASSERT_ARG(uc, 0),
-					      GUEST_ASSERT_ARG(uc, 1),
-					      GUEST_ASSERT_ARG(uc, 2), stage);
+			REPORT_GUEST_ASSERT(uc);
 			break;
 		default:
 			TEST_FAIL("Unexpected guest exit\n");

From df27f6b45454c02919b84dfe3ffad3f665108d23 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:22 -0700
Subject: [PATCH 0242/1189] KVM: selftests: Convert ARM's page fault test to
 printf style GUEST_ASSERT

Use GUEST_FAIL() in ARM's page fault test to report unexpected faults.

Link: https://lore.kernel.org/r/20230729003643.1053367-14-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/aarch64/page_fault_test.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
index e5bb8767d2cb..0b0dd90feae5 100644
--- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c
+++ b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
@@ -7,6 +7,7 @@
  * hugetlbfs with a hole). It checks that the expected handling method is
  * called (e.g., uffd faults with the right address and write/read flag).
  */
+#define USE_GUEST_ASSERT_PRINTF 1
 
 #define _GNU_SOURCE
 #include <linux/bitmap.h>
@@ -293,12 +294,12 @@ static void guest_code(struct test_desc *test)
 
 static void no_dabt_handler(struct ex_regs *regs)
 {
-	GUEST_ASSERT_1(false, read_sysreg(far_el1));
+	GUEST_FAIL("Unexpected dabt, far_el1 = 0x%llx", read_sysreg(far_el1));
 }
 
 static void no_iabt_handler(struct ex_regs *regs)
 {
-	GUEST_ASSERT_1(false, regs->pc);
+	GUEST_FAIL("Unexpected iabt, pc = 0x%lx", regs->pc);
 }
 
 static struct uffd_args {
@@ -679,7 +680,7 @@ static void vcpu_run_loop(struct kvm_vm *vm, struct kvm_vcpu *vcpu,
 			}
 			break;
 		case UCALL_ABORT:
-			REPORT_GUEST_ASSERT_2(uc, "values: %#lx, %#lx");
+			REPORT_GUEST_ASSERT(uc);
 			break;
 		case UCALL_DONE:
 			goto done;

From d0ad3bacc523cd780d573c890ebf3b14cec5df22 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:23 -0700
Subject: [PATCH 0243/1189] KVM: selftests: Convert ARM's vGIC IRQ test to
 printf style GUEST_ASSERT

Use printf-based guest assert reporting in ARM's vGIC IRQ test.  Note,
this is not as innocuous as it looks!  The printf-based version of
GUEST_ASSERT_EQ() ensures the expressions are evaluated only once, whereas
the old version did not!

Link: https://lore.kernel.org/r/20230729003643.1053367-15-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/aarch64/vgic_irq.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kvm/aarch64/vgic_irq.c b/tools/testing/selftests/kvm/aarch64/vgic_irq.c
index 90d854e0fcff..67da33aa6d17 100644
--- a/tools/testing/selftests/kvm/aarch64/vgic_irq.c
+++ b/tools/testing/selftests/kvm/aarch64/vgic_irq.c
@@ -7,6 +7,7 @@
  * host to inject a specific intid via a GUEST_SYNC call, and then checks that
  * it received it.
  */
+#define USE_GUEST_ASSERT_PRINTF 1
 
 #include <asm/kvm.h>
 #include <asm/kvm_para.h>
@@ -781,7 +782,7 @@ static void test_vgic(uint32_t nr_irqs, bool level_sensitive, bool eoi_split)
 			run_guest_cmd(vcpu, gic_fd, &inject_args, &args);
 			break;
 		case UCALL_ABORT:
-			REPORT_GUEST_ASSERT_2(uc, "values: %#lx, %#lx");
+			REPORT_GUEST_ASSERT(uc);
 			break;
 		case UCALL_DONE:
 			goto done;

From c55a475d5fc42931992b667aa16bed2db6058d06 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:24 -0700
Subject: [PATCH 0244/1189] KVM: selftests: Convert the memslot performance
 test to printf guest asserts

Use the printf-based GUEST_ASSERT_EQ() in the memslot perf test instead of
an half-baked open code version.

Link: https://lore.kernel.org/r/20230729003643.1053367-16-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/memslot_perf_test.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c
index 4210cd21d159..55f1bc70e571 100644
--- a/tools/testing/selftests/kvm/memslot_perf_test.c
+++ b/tools/testing/selftests/kvm/memslot_perf_test.c
@@ -6,6 +6,8 @@
  *
  * Basic guest setup / host vCPU thread code lifted from set_memory_region_test.
  */
+#define USE_GUEST_ASSERT_PRINTF 1
+
 #include <pthread.h>
 #include <sched.h>
 #include <semaphore.h>
@@ -157,7 +159,7 @@ static void *vcpu_worker(void *__data)
 				goto done;
 			break;
 		case UCALL_ABORT:
-			REPORT_GUEST_ASSERT_1(uc, "val = %lu");
+			REPORT_GUEST_ASSERT(uc);
 			break;
 		case UCALL_DONE:
 			goto done;
@@ -560,7 +562,7 @@ static void guest_code_test_memslot_rw(void)
 		     ptr < MEM_TEST_GPA + MEM_TEST_SIZE; ptr += page_size) {
 			uint64_t val = *(uint64_t *)ptr;
 
-			GUEST_ASSERT_1(val == MEM_TEST_VAL_2, val);
+			GUEST_ASSERT_EQ(val, MEM_TEST_VAL_2);
 			*(uint64_t *)ptr = 0;
 		}
 

From 428c76c769fa652e2186de464c74e34daede489f Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:25 -0700
Subject: [PATCH 0245/1189] KVM: selftests: Convert s390's memop test to printf
 style GUEST_ASSERT

Convert s390's memop test to printf-based GUEST_ASSERT, and
opportunistically use GUEST_FAIL() to report invalid sizes.

Link: https://lore.kernel.org/r/20230729003643.1053367-17-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/s390x/memop.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390x/memop.c
index de73dc030905..a49173907cec 100644
--- a/tools/testing/selftests/kvm/s390x/memop.c
+++ b/tools/testing/selftests/kvm/s390x/memop.c
@@ -4,6 +4,7 @@
  *
  * Copyright (C) 2019, Red Hat, Inc.
  */
+#define USE_GUEST_ASSERT_PRINTF 1
 
 #include <stdio.h>
 #include <stdlib.h>
@@ -279,7 +280,7 @@ enum stage {
 	vcpu_run(__vcpu);						\
 	get_ucall(__vcpu, &uc);						\
 	if (uc.cmd == UCALL_ABORT) {					\
-		REPORT_GUEST_ASSERT_2(uc, "hints: %lu, %lu");		\
+		REPORT_GUEST_ASSERT(uc);				\
 	}								\
 	TEST_ASSERT_EQ(uc.cmd, UCALL_SYNC);				\
 	TEST_ASSERT_EQ(uc.args[1], __stage);				\
@@ -469,7 +470,7 @@ static __uint128_t cut_to_size(int size, __uint128_t val)
 	case 16:
 		return val;
 	}
-	GUEST_ASSERT_1(false, "Invalid size");
+	GUEST_FAIL("Invalid size = %u", size);
 	return 0;
 }
 
@@ -598,7 +599,7 @@ static bool _cmpxchg(int size, void *target, __uint128_t *old_addr, __uint128_t
 			return ret;
 		}
 	}
-	GUEST_ASSERT_1(false, "Invalid size");
+	GUEST_FAIL("Invalid size = %u", size);
 	return 0;
 }
 

From 5f82bbab84adcb8990f17503393628a210086b2c Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:26 -0700
Subject: [PATCH 0246/1189] KVM: selftests: Convert s390's tprot test to printf
 style GUEST_ASSERT

Convert s390's tprot test to printf-based GUEST_ASSERT.

Link: https://lore.kernel.org/r/20230729003643.1053367-18-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/s390x/tprot.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/kvm/s390x/tprot.c b/tools/testing/selftests/kvm/s390x/tprot.c
index 40d3ea16c052..c12c6824d963 100644
--- a/tools/testing/selftests/kvm/s390x/tprot.c
+++ b/tools/testing/selftests/kvm/s390x/tprot.c
@@ -4,6 +4,7 @@
  *
  * Copyright IBM Corp. 2021
  */
+#define USE_GUEST_ASSERT_PRINTF 1
 
 #include <sys/mman.h>
 #include "test_util.h"
@@ -156,7 +157,9 @@ static enum stage perform_next_stage(int *i, bool mapped_0)
 		       !mapped_0;
 		if (!skip) {
 			result = test_protection(tests[*i].addr, tests[*i].key);
-			GUEST_ASSERT_2(result == tests[*i].expected, *i, result);
+			__GUEST_ASSERT(result == tests[*i].expected,
+				       "Wanted %u, got %u, for i = %u",
+				       tests[*i].expected, result, *i);
 		}
 	}
 	return stage;
@@ -190,7 +193,7 @@ static void guest_code(void)
 	vcpu_run(__vcpu);					\
 	get_ucall(__vcpu, &uc);					\
 	if (uc.cmd == UCALL_ABORT)				\
-		REPORT_GUEST_ASSERT_2(uc, "hints: %lu, %lu");	\
+		REPORT_GUEST_ASSERT(uc);			\
 	TEST_ASSERT_EQ(uc.cmd, UCALL_SYNC);			\
 	TEST_ASSERT_EQ(uc.args[1], __stage);			\
 })

From 9291c9cef5b52b64a20f92ea63341d903f0ae328 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:27 -0700
Subject: [PATCH 0247/1189] KVM: selftests: Convert set_memory_region_test to
 printf-based GUEST_ASSERT

Convert set_memory_region_test to print-based GUEST_ASSERT, using a combo
of newfangled macros to report (hopefully) useful information.

Link: https://lore.kernel.org/r/20230729003643.1053367-19-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../selftests/kvm/set_memory_region_test.c    | 23 +++++++++++--------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
index a849ce23ca97..dd8f4bac9df8 100644
--- a/tools/testing/selftests/kvm/set_memory_region_test.c
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -1,4 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
+#define USE_GUEST_ASSERT_PRINTF 1
+
 #define _GNU_SOURCE /* for program_invocation_short_name */
 #include <fcntl.h>
 #include <pthread.h>
@@ -88,7 +90,7 @@ static void *vcpu_worker(void *data)
 	}
 
 	if (run->exit_reason == KVM_EXIT_IO && cmd == UCALL_ABORT)
-		REPORT_GUEST_ASSERT_1(uc, "val = %lu");
+		REPORT_GUEST_ASSERT(uc);
 
 	return NULL;
 }
@@ -156,19 +158,22 @@ static void guest_code_move_memory_region(void)
 	 * window where the memslot is invalid is usually quite small.
 	 */
 	val = guest_spin_on_val(0);
-	GUEST_ASSERT_1(val == 1 || val == MMIO_VAL, val);
+	__GUEST_ASSERT(val == 1 || val == MMIO_VAL,
+		       "Expected '1' or MMIO ('%llx'), got '%llx'", MMIO_VAL, val);
 
 	/* Spin until the misaligning memory region move completes. */
 	val = guest_spin_on_val(MMIO_VAL);
-	GUEST_ASSERT_1(val == 1 || val == 0, val);
+	__GUEST_ASSERT(val == 1 || val == 0,
+		       "Expected '0' or '1' (no MMIO), got '%llx'", val);
 
 	/* Spin until the memory region starts to get re-aligned. */
 	val = guest_spin_on_val(0);
-	GUEST_ASSERT_1(val == 1 || val == MMIO_VAL, val);
+	__GUEST_ASSERT(val == 1 || val == MMIO_VAL,
+		       "Expected '1' or MMIO ('%llx'), got '%llx'", MMIO_VAL, val);
 
 	/* Spin until the re-aligning memory region move completes. */
 	val = guest_spin_on_val(MMIO_VAL);
-	GUEST_ASSERT_1(val == 1, val);
+	GUEST_ASSERT_EQ(val, 1);
 
 	GUEST_DONE();
 }
@@ -224,15 +229,15 @@ static void guest_code_delete_memory_region(void)
 
 	/* Spin until the memory region is deleted. */
 	val = guest_spin_on_val(0);
-	GUEST_ASSERT_1(val == MMIO_VAL, val);
+	GUEST_ASSERT_EQ(val, MMIO_VAL);
 
 	/* Spin until the memory region is recreated. */
 	val = guest_spin_on_val(MMIO_VAL);
-	GUEST_ASSERT_1(val == 0, val);
+	GUEST_ASSERT_EQ(val, 0);
 
 	/* Spin until the memory region is deleted. */
 	val = guest_spin_on_val(0);
-	GUEST_ASSERT_1(val == MMIO_VAL, val);
+	GUEST_ASSERT_EQ(val, MMIO_VAL);
 
 	asm("1:\n\t"
 	    ".pushsection .rodata\n\t"
@@ -249,7 +254,7 @@ static void guest_code_delete_memory_region(void)
 	    "final_rip_end: .quad 1b\n\t"
 	    ".popsection");
 
-	GUEST_ASSERT_1(0, 0);
+	GUEST_ASSERT(0);
 }
 
 static void test_delete_memory_region(void)

From 3d9bd831175e898284eb92dadac7049cd055bad6 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:28 -0700
Subject: [PATCH 0248/1189] KVM: selftests: Convert steal_time test to printf
 style GUEST_ASSERT

Convert the steal_time test to use printf-based GUEST_ASERT.
Opportunistically use GUEST_ASSERT_EQ() and GUEST_ASSERT_NE() so that the
test spits out debug information on failure.

Link: https://lore.kernel.org/r/20230729003643.1053367-20-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/steal_time.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c
index c87f38712073..8649c8545882 100644
--- a/tools/testing/selftests/kvm/steal_time.c
+++ b/tools/testing/selftests/kvm/steal_time.c
@@ -4,6 +4,8 @@
  *
  * Copyright (C) 2020, Red Hat, Inc.
  */
+#define USE_GUEST_ASSERT_PRINTF 1
+
 #define _GNU_SOURCE
 #include <stdio.h>
 #include <time.h>
@@ -31,8 +33,8 @@ static uint64_t guest_stolen_time[NR_VCPUS];
 static void check_status(struct kvm_steal_time *st)
 {
 	GUEST_ASSERT(!(READ_ONCE(st->version) & 1));
-	GUEST_ASSERT(READ_ONCE(st->flags) == 0);
-	GUEST_ASSERT(READ_ONCE(st->preempted) == 0);
+	GUEST_ASSERT_EQ(READ_ONCE(st->flags), 0);
+	GUEST_ASSERT_EQ(READ_ONCE(st->preempted), 0);
 }
 
 static void guest_code(int cpu)
@@ -40,7 +42,7 @@ static void guest_code(int cpu)
 	struct kvm_steal_time *st = st_gva[cpu];
 	uint32_t version;
 
-	GUEST_ASSERT(rdmsr(MSR_KVM_STEAL_TIME) == ((uint64_t)st_gva[cpu] | KVM_MSR_ENABLED));
+	GUEST_ASSERT_EQ(rdmsr(MSR_KVM_STEAL_TIME), ((uint64_t)st_gva[cpu] | KVM_MSR_ENABLED));
 
 	memset(st, 0, sizeof(*st));
 	GUEST_SYNC(0);
@@ -122,8 +124,8 @@ static int64_t smccc(uint32_t func, uint64_t arg)
 
 static void check_status(struct st_time *st)
 {
-	GUEST_ASSERT(READ_ONCE(st->rev) == 0);
-	GUEST_ASSERT(READ_ONCE(st->attr) == 0);
+	GUEST_ASSERT_EQ(READ_ONCE(st->rev), 0);
+	GUEST_ASSERT_EQ(READ_ONCE(st->attr), 0);
 }
 
 static void guest_code(int cpu)
@@ -132,15 +134,15 @@ static void guest_code(int cpu)
 	int64_t status;
 
 	status = smccc(SMCCC_ARCH_FEATURES, PV_TIME_FEATURES);
-	GUEST_ASSERT(status == 0);
+	GUEST_ASSERT_EQ(status, 0);
 	status = smccc(PV_TIME_FEATURES, PV_TIME_FEATURES);
-	GUEST_ASSERT(status == 0);
+	GUEST_ASSERT_EQ(status, 0);
 	status = smccc(PV_TIME_FEATURES, PV_TIME_ST);
-	GUEST_ASSERT(status == 0);
+	GUEST_ASSERT_EQ(status, 0);
 
 	status = smccc(PV_TIME_ST, 0);
-	GUEST_ASSERT(status != -1);
-	GUEST_ASSERT(status == (ulong)st_gva[cpu]);
+	GUEST_ASSERT_NE(status, -1);
+	GUEST_ASSERT_EQ(status, (ulong)st_gva[cpu]);
 
 	st = (struct st_time *)status;
 	GUEST_SYNC(0);

From 06b651d250e5eea0a1c1fd31fbbc0e0b27f66592 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:29 -0700
Subject: [PATCH 0249/1189] KVM: selftests: Convert x86's CPUID test to printf
 style GUEST_ASSERT

Convert x86's CPUID test to use printf-based GUEST_ASSERT_EQ() so that
the test prints out debug information.  Note, the test previously used
REPORT_GUEST_ASSERT_2(), but that was pointless because none of the
guest-side code passed any parameters to the assert.

Link: https://lore.kernel.org/r/20230729003643.1053367-21-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/x86_64/cpuid_test.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/kvm/x86_64/cpuid_test.c b/tools/testing/selftests/kvm/x86_64/cpuid_test.c
index d3c3aa93f090..eb1b65ffc0d5 100644
--- a/tools/testing/selftests/kvm/x86_64/cpuid_test.c
+++ b/tools/testing/selftests/kvm/x86_64/cpuid_test.c
@@ -4,6 +4,8 @@
  *
  * Generic tests for KVM CPUID set/get ioctls
  */
+#define USE_GUEST_ASSERT_PRINTF 1
+
 #include <asm/kvm_para.h>
 #include <linux/kvm_para.h>
 #include <stdint.h>
@@ -35,10 +37,10 @@ static void test_guest_cpuids(struct kvm_cpuid2 *guest_cpuid)
 			guest_cpuid->entries[i].index,
 			&eax, &ebx, &ecx, &edx);
 
-		GUEST_ASSERT(eax == guest_cpuid->entries[i].eax &&
-			     ebx == guest_cpuid->entries[i].ebx &&
-			     ecx == guest_cpuid->entries[i].ecx &&
-			     edx == guest_cpuid->entries[i].edx);
+		GUEST_ASSERT_EQ(eax, guest_cpuid->entries[i].eax);
+		GUEST_ASSERT_EQ(ebx, guest_cpuid->entries[i].ebx);
+		GUEST_ASSERT_EQ(ecx, guest_cpuid->entries[i].ecx);
+		GUEST_ASSERT_EQ(edx, guest_cpuid->entries[i].edx);
 	}
 
 }
@@ -51,7 +53,7 @@ static void guest_main(struct kvm_cpuid2 *guest_cpuid)
 
 	GUEST_SYNC(2);
 
-	GUEST_ASSERT(this_cpu_property(X86_PROPERTY_MAX_KVM_LEAF) == 0x40000001);
+	GUEST_ASSERT_EQ(this_cpu_property(X86_PROPERTY_MAX_KVM_LEAF), 0x40000001);
 
 	GUEST_DONE();
 }
@@ -116,7 +118,7 @@ static void run_vcpu(struct kvm_vcpu *vcpu, int stage)
 	case UCALL_DONE:
 		return;
 	case UCALL_ABORT:
-		REPORT_GUEST_ASSERT_2(uc, "values: %#lx, %#lx");
+		REPORT_GUEST_ASSERT(uc);
 	default:
 		TEST_ASSERT(false, "Unexpected exit: %s",
 			    exit_reason_str(vcpu->run->exit_reason));

From 82cb0ed66d4e5207c53b31a29d9f71af83190ee6 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:30 -0700
Subject: [PATCH 0250/1189] KVM: selftests: Convert the Hyper-V extended
 hypercalls test to printf asserts

Convert x86's Hyper-V extended hypercalls test to use printf-based
GUEST_ASSERT_EQ().

Link: https://lore.kernel.org/r/20230729003643.1053367-22-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c  | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c b/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c
index 73af44d2167f..0107d54a1a08 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c
@@ -8,6 +8,7 @@
  * Copyright 2022 Google LLC
  * Author: Vipin Sharma <vipinsh@google.com>
  */
+#define USE_GUEST_ASSERT_PRINTF 1
 
 #include "kvm_util.h"
 #include "processor.h"
@@ -84,7 +85,7 @@ int main(void)
 
 	switch (get_ucall(vcpu, &uc)) {
 	case UCALL_ABORT:
-		REPORT_GUEST_ASSERT_2(uc, "arg1 = %ld, arg2 = %ld");
+		REPORT_GUEST_ASSERT(uc);
 		break;
 	case UCALL_DONE:
 		break;

From 8d1d3ce604e54c43228439291db53543da156110 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:31 -0700
Subject: [PATCH 0251/1189] KVM: selftests: Convert the Hyper-V feature test to
 printf style GUEST_ASSERT

Convert x86's Hyper-V feature test to use print-based guest asserts.
Opportunistically use the EQ and NE variants in a few places to capture
additional information.

Link: https://lore.kernel.org/r/20230729003643.1053367-23-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../selftests/kvm/x86_64/hyperv_features.c    | 31 +++++++++++++------
 1 file changed, 21 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
index 78606de9385d..41a6beff78c4 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
@@ -4,6 +4,8 @@
  *
  * Tests for Hyper-V features enablement
  */
+#define USE_GUEST_ASSERT_PRINTF 1
+
 #include <asm/kvm_para.h>
 #include <linux/kvm_para.h>
 #include <stdint.h>
@@ -53,16 +55,21 @@ static void guest_msr(struct msr_data *msr)
 		vector = rdmsr_safe(msr->idx, &msr_val);
 
 	if (msr->fault_expected)
-		GUEST_ASSERT_3(vector == GP_VECTOR, msr->idx, vector, GP_VECTOR);
+		__GUEST_ASSERT(vector == GP_VECTOR,
+			       "Expected #GP on %sMSR(0x%x), got vector '0x%x'",
+			       msr->idx, msr->write ? "WR" : "RD", vector);
 	else
-		GUEST_ASSERT_3(!vector, msr->idx, vector, 0);
+		__GUEST_ASSERT(!vector,
+			       "Expected success on %sMSR(0x%x), got vector '0x%x'",
+			       msr->idx, msr->write ? "WR" : "RD", vector);
 
 	if (vector || is_write_only_msr(msr->idx))
 		goto done;
 
 	if (msr->write)
-		GUEST_ASSERT_3(msr_val == msr->write_val, msr->idx,
-			       msr_val, msr->write_val);
+		__GUEST_ASSERT(!vector,
+			       "WRMSR(0x%x) to '0x%llx', RDMSR read '0x%llx'",
+			       msr->idx, msr->write_val, msr_val);
 
 	/* Invariant TSC bit appears when TSC invariant control MSR is written to */
 	if (msr->idx == HV_X64_MSR_TSC_INVARIANT_CONTROL) {
@@ -82,7 +89,7 @@ static void guest_hcall(vm_vaddr_t pgs_gpa, struct hcall_data *hcall)
 	u64 res, input, output;
 	uint8_t vector;
 
-	GUEST_ASSERT(hcall->control);
+	GUEST_ASSERT_NE(hcall->control, 0);
 
 	wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID);
 	wrmsr(HV_X64_MSR_HYPERCALL, pgs_gpa);
@@ -96,10 +103,14 @@ static void guest_hcall(vm_vaddr_t pgs_gpa, struct hcall_data *hcall)
 
 	vector = __hyperv_hypercall(hcall->control, input, output, &res);
 	if (hcall->ud_expected) {
-		GUEST_ASSERT_2(vector == UD_VECTOR, hcall->control, vector);
+		__GUEST_ASSERT(vector == UD_VECTOR,
+			       "Expected #UD for control '%u', got vector '0x%x'",
+			       hcall->control, vector);
 	} else {
-		GUEST_ASSERT_2(!vector, hcall->control, vector);
-		GUEST_ASSERT_2(res == hcall->expect, hcall->expect, res);
+		__GUEST_ASSERT(!vector,
+			       "Expected no exception for control '%u', got vector '0x%x'",
+			       hcall->control, vector);
+		GUEST_ASSERT_EQ(res, hcall->expect);
 	}
 
 	GUEST_DONE();
@@ -495,7 +506,7 @@ static void guest_test_msrs_access(void)
 
 		switch (get_ucall(vcpu, &uc)) {
 		case UCALL_ABORT:
-			REPORT_GUEST_ASSERT_3(uc, "MSR = %lx, arg1 = %lx, arg2 = %lx");
+			REPORT_GUEST_ASSERT(uc);
 			return;
 		case UCALL_DONE:
 			break;
@@ -665,7 +676,7 @@ static void guest_test_hcalls_access(void)
 
 		switch (get_ucall(vcpu, &uc)) {
 		case UCALL_ABORT:
-			REPORT_GUEST_ASSERT_2(uc, "arg1 = %lx, arg2 = %lx");
+			REPORT_GUEST_ASSERT(uc);
 			return;
 		case UCALL_DONE:
 			break;

From bf6c760b9df39ebc83245b37ef09ee390ba05e9f Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:32 -0700
Subject: [PATCH 0252/1189] KVM: selftests: Convert x86's KVM paravirt test to
 printf style GUEST_ASSERT

Convert x86's KVM paravirtualization test to use the printf-based
GUEST_ASSERT_EQ().

Link: https://lore.kernel.org/r/20230729003643.1053367-24-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/x86_64/kvm_pv_test.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c
index f774a9e62858..1c28b77ff3cd 100644
--- a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c
+++ b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c
@@ -4,6 +4,8 @@
  *
  * Tests for KVM paravirtual feature disablement
  */
+#define USE_GUEST_ASSERT_PRINTF 1
+
 #include <asm/kvm_para.h>
 #include <linux/kvm_para.h>
 #include <stdint.h>
@@ -46,10 +48,10 @@ static void test_msr(struct msr_data *msr)
 	PR_MSR(msr);
 
 	vector = rdmsr_safe(msr->idx, &ignored);
-	GUEST_ASSERT_1(vector == GP_VECTOR, vector);
+	GUEST_ASSERT_EQ(vector, GP_VECTOR);
 
 	vector = wrmsr_safe(msr->idx, 0);
-	GUEST_ASSERT_1(vector == GP_VECTOR, vector);
+	GUEST_ASSERT_EQ(vector, GP_VECTOR);
 }
 
 struct hcall_data {
@@ -77,7 +79,7 @@ static void test_hcall(struct hcall_data *hc)
 
 	PR_HCALL(hc);
 	r = kvm_hypercall(hc->nr, 0, 0, 0, 0);
-	GUEST_ASSERT(r == -KVM_ENOSYS);
+	GUEST_ASSERT_EQ(r, -KVM_ENOSYS);
 }
 
 static void guest_main(void)
@@ -125,7 +127,7 @@ static void enter_guest(struct kvm_vcpu *vcpu)
 			pr_hcall(&uc);
 			break;
 		case UCALL_ABORT:
-			REPORT_GUEST_ASSERT_1(uc, "vector = %lu");
+			REPORT_GUEST_ASSERT(uc);
 			return;
 		case UCALL_DONE:
 			return;

From 0f52e4aaa61400ce68e122b678811777734421ff Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:33 -0700
Subject: [PATCH 0253/1189] KVM: selftests: Convert the MONITOR/MWAIT test to
 use printf guest asserts

Convert x86's MONITOR/MWAIT test to use printf-based guest asserts.  Add a
macro to handle reporting failures to reduce the amount of copy+paste
needed for MONITOR vs. MWAIT.

Link: https://lore.kernel.org/r/20230729003643.1053367-25-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../selftests/kvm/x86_64/monitor_mwait_test.c | 37 +++++++++++--------
 1 file changed, 22 insertions(+), 15 deletions(-)

diff --git a/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c b/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c
index 72812644d7f5..960fecab3742 100644
--- a/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c
+++ b/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c
@@ -1,4 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
+#define USE_GUEST_ASSERT_PRINTF 1
+
 #include <fcntl.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -16,14 +18,25 @@ enum monitor_mwait_testcases {
 	MWAIT_DISABLED = BIT(2),
 };
 
+/*
+ * If both MWAIT and its quirk are disabled, MONITOR/MWAIT should #UD, in all
+ * other scenarios KVM should emulate them as nops.
+ */
+#define GUEST_ASSERT_MONITOR_MWAIT(insn, testcase, vector)		\
+do {									\
+	bool fault_wanted = ((testcase) & MWAIT_QUIRK_DISABLED) &&	\
+			    ((testcase) & MWAIT_DISABLED);		\
+									\
+	if (fault_wanted)						\
+		__GUEST_ASSERT((vector) == UD_VECTOR,			\
+			       "Expected #UD on " insn " for testcase '0x%x', got '0x%x'", vector); \
+	else								\
+		__GUEST_ASSERT(!(vector),				\
+			       "Expected success on " insn " for testcase '0x%x', got '0x%x'", vector); \
+} while (0)
+
 static void guest_monitor_wait(int testcase)
 {
-	/*
-	 * If both MWAIT and its quirk are disabled, MONITOR/MWAIT should #UD,
-	 * in all other scenarios KVM should emulate them as nops.
-	 */
-	bool fault_wanted = (testcase & MWAIT_QUIRK_DISABLED) &&
-			    (testcase & MWAIT_DISABLED);
 	u8 vector;
 
 	GUEST_SYNC(testcase);
@@ -33,16 +46,10 @@ static void guest_monitor_wait(int testcase)
 	 * intercept checks, so the inputs for MONITOR and MWAIT must be valid.
 	 */
 	vector = kvm_asm_safe("monitor", "a"(guest_monitor_wait), "c"(0), "d"(0));
-	if (fault_wanted)
-		GUEST_ASSERT_2(vector == UD_VECTOR, testcase, vector);
-	else
-		GUEST_ASSERT_2(!vector, testcase, vector);
+	GUEST_ASSERT_MONITOR_MWAIT("MONITOR", testcase, vector);
 
 	vector = kvm_asm_safe("mwait", "a"(guest_monitor_wait), "c"(0), "d"(0));
-	if (fault_wanted)
-		GUEST_ASSERT_2(vector == UD_VECTOR, testcase, vector);
-	else
-		GUEST_ASSERT_2(!vector, testcase, vector);
+	GUEST_ASSERT_MONITOR_MWAIT("MWAIT", testcase, vector);
 }
 
 static void guest_code(void)
@@ -85,7 +92,7 @@ int main(int argc, char *argv[])
 			testcase = uc.args[1];
 			break;
 		case UCALL_ABORT:
-			REPORT_GUEST_ASSERT_2(uc, "testcase = %lx, vector = %ld");
+			REPORT_GUEST_ASSERT(uc);
 			goto done;
 		case UCALL_DONE:
 			goto done;

From b13a307ce3c6435c288017d7edf1c6e2827470dc Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:34 -0700
Subject: [PATCH 0254/1189] KVM: selftests: Convert x86's nested exceptions
 test to printf guest asserts

Convert x86's nested exceptions test to printf-based guest asserts, and
use REPORT_GUEST_ASSERT() instead of TEST_FAIL() so that output is
formatted correctly.

Link: https://lore.kernel.org/r/20230729003643.1053367-26-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c b/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c
index 5f074a6da90c..4a29f59a76be 100644
--- a/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c
+++ b/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c
@@ -1,4 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
+#define USE_GUEST_ASSERT_PRINTF 1
+
 #define _GNU_SOURCE /* for program_invocation_short_name */
 
 #include "test_util.h"
@@ -180,9 +182,7 @@ static void assert_ucall_vector(struct kvm_vcpu *vcpu, int vector)
 			    "Expected L2 to ask for %d, L2 says it's done", vector);
 		break;
 	case UCALL_ABORT:
-		TEST_FAIL("%s at %s:%ld (0x%lx != 0x%lx)",
-			  (const char *)uc.args[0], __FILE__, uc.args[1],
-			  uc.args[2], uc.args[3]);
+		REPORT_GUEST_ASSERT(uc);
 		break;
 	default:
 		TEST_FAIL("Expected L2 to ask for %d, got unexpected ucall %lu", vector, uc.cmd);

From 40b319d6b4e109d5e94ac1054d5147624e79088f Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:35 -0700
Subject: [PATCH 0255/1189] KVM: selftests: Convert x86's set BSP ID test to
 printf style guest asserts

Convert the set_boot_cpu_id test to use printf-based guest asserts,
specifically the EQ and NE variants.

Link: https://lore.kernel.org/r/20230729003643.1053367-27-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c b/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c
index b25d7556b638..abb3f26d3ce0 100644
--- a/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c
+++ b/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c
@@ -4,6 +4,8 @@
  *
  * Copyright (C) 2020, Red Hat, Inc.
  */
+#define USE_GUEST_ASSERT_PRINTF 1
+
 #define _GNU_SOURCE /* for program_invocation_name */
 #include <fcntl.h>
 #include <stdio.h>
@@ -20,7 +22,7 @@ static void guest_bsp_vcpu(void *arg)
 {
 	GUEST_SYNC(1);
 
-	GUEST_ASSERT(get_bsp_flag() != 0);
+	GUEST_ASSERT_NE(get_bsp_flag(), 0);
 
 	GUEST_DONE();
 }
@@ -29,7 +31,7 @@ static void guest_not_bsp_vcpu(void *arg)
 {
 	GUEST_SYNC(1);
 
-	GUEST_ASSERT(get_bsp_flag() == 0);
+	GUEST_ASSERT_EQ(get_bsp_flag(), 0);
 
 	GUEST_DONE();
 }
@@ -65,7 +67,7 @@ static void run_vcpu(struct kvm_vcpu *vcpu)
 					stage);
 			break;
 		case UCALL_ABORT:
-			REPORT_GUEST_ASSERT_2(uc, "values: %#lx, %#lx");
+			REPORT_GUEST_ASSERT(uc);
 		default:
 			TEST_ASSERT(false, "Unexpected exit: %s",
 				    exit_reason_str(vcpu->run->exit_reason));

From a925f799428168e1a849509c0f425673b62e53ad Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:36 -0700
Subject: [PATCH 0256/1189] KVM: selftests: Convert the nSVM software interrupt
 test to printf guest asserts

Convert x86's nested SVM software interrupt injection test to use printf-
based guest asserts.  Opportunistically use GUEST_ASSERT() and
GUEST_FAIL() in a few locations to spit out more debug information.

Link: https://lore.kernel.org/r/20230729003643.1053367-28-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../kvm/x86_64/svm_nested_soft_inject_test.c  | 22 ++++++++++---------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c
index 4e2479716da6..c908412c5754 100644
--- a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c
+++ b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c
@@ -8,6 +8,7 @@
  *   Copyright (C) 2021, Red Hat, Inc.
  *
  */
+#define USE_GUEST_ASSERT_PRINTF 1
 
 #include <stdatomic.h>
 #include <stdio.h>
@@ -34,13 +35,12 @@ static void l2_guest_code_int(void);
 static void guest_int_handler(struct ex_regs *regs)
 {
 	int_fired++;
-	GUEST_ASSERT_2(regs->rip == (unsigned long)l2_guest_code_int,
-		       regs->rip, (unsigned long)l2_guest_code_int);
+	GUEST_ASSERT_EQ(regs->rip, (unsigned long)l2_guest_code_int);
 }
 
 static void l2_guest_code_int(void)
 {
-	GUEST_ASSERT_1(int_fired == 1, int_fired);
+	GUEST_ASSERT_EQ(int_fired, 1);
 
 	/*
          * Same as the vmmcall() function, but with a ud2 sneaked after the
@@ -53,7 +53,7 @@ static void l2_guest_code_int(void)
                              : "rbx", "rdx", "rsi", "rdi", "r8", "r9",
                                "r10", "r11", "r12", "r13", "r14", "r15");
 
-	GUEST_ASSERT_1(bp_fired == 1, bp_fired);
+	GUEST_ASSERT_EQ(bp_fired, 1);
 	hlt();
 }
 
@@ -66,9 +66,9 @@ static void guest_nmi_handler(struct ex_regs *regs)
 
 	if (nmi_stage_get() == 1) {
 		vmmcall();
-		GUEST_ASSERT(false);
+		GUEST_FAIL("Unexpected resume after VMMCALL");
 	} else {
-		GUEST_ASSERT_1(nmi_stage_get() == 3, nmi_stage_get());
+		GUEST_ASSERT_EQ(nmi_stage_get(), 3);
 		GUEST_DONE();
 	}
 }
@@ -104,7 +104,8 @@ static void l1_guest_code(struct svm_test_data *svm, uint64_t is_nmi, uint64_t i
 	}
 
 	run_guest(vmcb, svm->vmcb_gpa);
-	GUEST_ASSERT_3(vmcb->control.exit_code == SVM_EXIT_VMMCALL,
+	__GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL,
+		       "Expected VMMCAL #VMEXIT, got '0x%x', info1 = '0x%llx, info2 = '0x%llx'",
 		       vmcb->control.exit_code,
 		       vmcb->control.exit_info_1, vmcb->control.exit_info_2);
 
@@ -112,7 +113,7 @@ static void l1_guest_code(struct svm_test_data *svm, uint64_t is_nmi, uint64_t i
 		clgi();
 		x2apic_write_reg(APIC_ICR, APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_NMI);
 
-		GUEST_ASSERT_1(nmi_stage_get() == 1, nmi_stage_get());
+		GUEST_ASSERT_EQ(nmi_stage_get(), 1);
 		nmi_stage_inc();
 
 		stgi();
@@ -133,7 +134,8 @@ static void l1_guest_code(struct svm_test_data *svm, uint64_t is_nmi, uint64_t i
 	vmcb->control.next_rip = vmcb->save.rip + 2;
 
 	run_guest(vmcb, svm->vmcb_gpa);
-	GUEST_ASSERT_3(vmcb->control.exit_code == SVM_EXIT_HLT,
+	__GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_HLT,
+		       "Expected HLT #VMEXIT, got '0x%x', info1 = '0x%llx, info2 = '0x%llx'",
 		       vmcb->control.exit_code,
 		       vmcb->control.exit_info_1, vmcb->control.exit_info_2);
 
@@ -185,7 +187,7 @@ static void run_test(bool is_nmi)
 
 	switch (get_ucall(vcpu, &uc)) {
 	case UCALL_ABORT:
-		REPORT_GUEST_ASSERT_3(uc, "vals = 0x%lx 0x%lx 0x%lx");
+		REPORT_GUEST_ASSERT(uc);
 		break;
 		/* NOT REACHED */
 	case UCALL_DONE:

From 847ae0795514a15f2845584870750aac4fc5aaee Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:37 -0700
Subject: [PATCH 0257/1189] KVM: selftests: Convert x86's TSC MSRs test to use
 printf guest asserts

Convert x86's TSC MSRs test, and it's liberal use of GUEST_ASSERT_EQ(), to
use printf-based guest assert reporting.

Link: https://lore.kernel.org/r/20230729003643.1053367-29-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c
index 9265965bd2cd..cf9114f70e1c 100644
--- a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c
@@ -4,6 +4,8 @@
  *
  * Copyright (C) 2020, Red Hat, Inc.
  */
+#define USE_GUEST_ASSERT_PRINTF 1
+
 #include <stdio.h>
 #include <string.h>
 #include "kvm_util.h"
@@ -84,7 +86,7 @@ static void run_vcpu(struct kvm_vcpu *vcpu, int stage)
 		ksft_test_result_pass("stage %d passed\n", stage + 1);
 		return;
 	case UCALL_ABORT:
-		REPORT_GUEST_ASSERT_2(uc, "values: %#lx, %#lx");
+		REPORT_GUEST_ASSERT(uc);
 	default:
 		TEST_ASSERT(false, "Unexpected exit: %s",
 			    exit_reason_str(vcpu->run->exit_reason));

From 417bfd0c820f17f40572aca37e5134ed329b791f Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:38 -0700
Subject: [PATCH 0258/1189] KVM: selftests: Convert the x86 userspace I/O test
 to printf guest assert

Convert x86's userspace I/O test to use printf-based guest asserts.

Link: https://lore.kernel.org/r/20230729003643.1053367-30-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../testing/selftests/kvm/x86_64/userspace_io_test.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c
index 0cb51fa42773..2c5d2a18d184 100644
--- a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c
+++ b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c
@@ -1,4 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
+#define USE_GUEST_ASSERT_PRINTF 1
+
 #include <fcntl.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -20,8 +22,8 @@ static void guest_ins_port80(uint8_t *buffer, unsigned int count)
 		end = (unsigned long)buffer + 8192;
 
 	asm volatile("cld; rep; insb" : "+D"(buffer), "+c"(count) : "d"(0x80) : "memory");
-	GUEST_ASSERT_1(count == 0, count);
-	GUEST_ASSERT_2((unsigned long)buffer == end, buffer, end);
+	GUEST_ASSERT_EQ(count, 0);
+	GUEST_ASSERT_EQ((unsigned long)buffer, end);
 }
 
 static void guest_code(void)
@@ -43,7 +45,9 @@ static void guest_code(void)
 	memset(buffer, 0, sizeof(buffer));
 	guest_ins_port80(buffer, 8192);
 	for (i = 0; i < 8192; i++)
-		GUEST_ASSERT_2(buffer[i] == 0xaa, i, buffer[i]);
+		__GUEST_ASSERT(buffer[i] == 0xaa,
+			       "Expected '0xaa', got '0x%x' at buffer[%u]",
+			       buffer[i], i);
 
 	GUEST_DONE();
 }
@@ -91,7 +95,7 @@ int main(int argc, char *argv[])
 	case UCALL_DONE:
 		break;
 	case UCALL_ABORT:
-		REPORT_GUEST_ASSERT_2(uc, "argN+1 = 0x%lx, argN+2 = 0x%lx");
+		REPORT_GUEST_ASSERT(uc);
 	default:
 		TEST_FAIL("Unknown ucall %lu", uc.cmd);
 	}

From 30a6e0b4553dbf2d935d26945788d37ddb234fa7 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:39 -0700
Subject: [PATCH 0259/1189] KVM: selftests: Convert VMX's PMU capabilities test
 to printf guest asserts

Convert x86's VMX PMU capabilities test to use printf-based guest asserts.
Opportunstically add a helper to do the WRMSR+assert so as to reduce the
amount of copy+paste needed to spit out debug information.

Link: https://lore.kernel.org/r/20230729003643.1053367-31-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../selftests/kvm/x86_64/vmx_pmu_caps_test.c  | 28 ++++++++++---------
 1 file changed, 15 insertions(+), 13 deletions(-)

diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c
index 34efd57c2b32..ba09d5a01c39 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c
@@ -10,6 +10,7 @@
  * and check it can be retrieved with KVM_GET_MSR, also test
  * the invalid LBR formats are rejected.
  */
+#define USE_GUEST_ASSERT_PRINTF 1
 
 #define _GNU_SOURCE /* for program_invocation_short_name */
 #include <sys/ioctl.h>
@@ -52,23 +53,24 @@ static const union perf_capabilities format_caps = {
 	.pebs_format = -1,
 };
 
+static void guest_test_perf_capabilities_gp(uint64_t val)
+{
+	uint8_t vector = wrmsr_safe(MSR_IA32_PERF_CAPABILITIES, val);
+
+	__GUEST_ASSERT(vector == GP_VECTOR,
+		       "Expected #GP for value '0x%llx', got vector '0x%x'",
+		       val, vector);
+}
+
 static void guest_code(uint64_t current_val)
 {
-	uint8_t vector;
 	int i;
 
-	vector = wrmsr_safe(MSR_IA32_PERF_CAPABILITIES, current_val);
-	GUEST_ASSERT_2(vector == GP_VECTOR, current_val, vector);
+	guest_test_perf_capabilities_gp(current_val);
+	guest_test_perf_capabilities_gp(0);
 
-	vector = wrmsr_safe(MSR_IA32_PERF_CAPABILITIES, 0);
-	GUEST_ASSERT_2(vector == GP_VECTOR, 0, vector);
-
-	for (i = 0; i < 64; i++) {
-		vector = wrmsr_safe(MSR_IA32_PERF_CAPABILITIES,
-				    current_val ^ BIT_ULL(i));
-		GUEST_ASSERT_2(vector == GP_VECTOR,
-			       current_val ^ BIT_ULL(i), vector);
-	}
+	for (i = 0; i < 64; i++)
+		guest_test_perf_capabilities_gp(current_val ^ BIT_ULL(i));
 
 	GUEST_DONE();
 }
@@ -95,7 +97,7 @@ static void test_guest_wrmsr_perf_capabilities(union perf_capabilities host_cap)
 
 	switch (get_ucall(vcpu, &uc)) {
 	case UCALL_ABORT:
-		REPORT_GUEST_ASSERT_2(uc, "val = 0x%lx, vector = %lu");
+		REPORT_GUEST_ASSERT(uc);
 		break;
 	case UCALL_DONE:
 		break;

From 4e15c38a1aca477d7f99b66b745e811bc95f9420 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:40 -0700
Subject: [PATCH 0260/1189] KVM: selftests: Convert x86's XCR0 test to use
 printf-based guest asserts

Convert x86's XCR0 vs. CPUID test to use printf-based guest asserts.

Link: https://lore.kernel.org/r/20230729003643.1053367-32-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../selftests/kvm/x86_64/xcr0_cpuid_test.c    | 29 ++++++++++++-------
 1 file changed, 18 insertions(+), 11 deletions(-)

diff --git a/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c b/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c
index 905bd5ae4431..5e8290797720 100644
--- a/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c
@@ -4,6 +4,7 @@
  *
  * Copyright (C) 2022, Google LLC.
  */
+#define USE_GUEST_ASSERT_PRINTF 1
 
 #include <fcntl.h>
 #include <stdio.h>
@@ -20,13 +21,14 @@
  * Assert that architectural dependency rules are satisfied, e.g. that AVX is
  * supported if and only if SSE is supported.
  */
-#define ASSERT_XFEATURE_DEPENDENCIES(supported_xcr0, xfeatures, dependencies)	  \
-do {										  \
-	uint64_t __supported = (supported_xcr0) & ((xfeatures) | (dependencies)); \
-										  \
-	GUEST_ASSERT_3((__supported & (xfeatures)) != (xfeatures) ||		  \
-		       __supported == ((xfeatures) | (dependencies)),		  \
-		       __supported, (xfeatures), (dependencies));		  \
+#define ASSERT_XFEATURE_DEPENDENCIES(supported_xcr0, xfeatures, dependencies)		\
+do {											\
+	uint64_t __supported = (supported_xcr0) & ((xfeatures) | (dependencies));	\
+											\
+	__GUEST_ASSERT((__supported & (xfeatures)) != (xfeatures) ||			\
+		       __supported == ((xfeatures) | (dependencies)),			\
+		       "supported = 0x%llx, xfeatures = 0x%llx, dependencies = 0x%llx",	\
+		       __supported, (xfeatures), (dependencies));			\
 } while (0)
 
 /*
@@ -41,7 +43,8 @@ do {										  \
 do {									\
 	uint64_t __supported = (supported_xcr0) & (xfeatures);		\
 									\
-	GUEST_ASSERT_2(!__supported || __supported == (xfeatures),	\
+	__GUEST_ASSERT(!__supported || __supported == (xfeatures),	\
+		       "supported = 0x%llx, xfeatures = 0x%llx",	\
 		       __supported, (xfeatures));			\
 } while (0)
 
@@ -79,14 +82,18 @@ static void guest_code(void)
 				    XFEATURE_MASK_XTILE);
 
 	vector = xsetbv_safe(0, supported_xcr0);
-	GUEST_ASSERT_2(!vector, supported_xcr0, vector);
+	__GUEST_ASSERT(!vector,
+		       "Expected success on XSETBV(0x%llx), got vector '0x%x'",
+		       supported_xcr0, vector);
 
 	for (i = 0; i < 64; i++) {
 		if (supported_xcr0 & BIT_ULL(i))
 			continue;
 
 		vector = xsetbv_safe(0, supported_xcr0 | BIT_ULL(i));
-		GUEST_ASSERT_3(vector == GP_VECTOR, supported_xcr0, vector, BIT_ULL(i));
+		__GUEST_ASSERT(vector == GP_VECTOR,
+			       "Expected #GP on XSETBV(0x%llx), supported XCR0 = %llx, got vector '0x%x'",
+			       BIT_ULL(i), supported_xcr0, vector);
 	}
 
 	GUEST_DONE();
@@ -117,7 +124,7 @@ int main(int argc, char *argv[])
 
 		switch (get_ucall(vcpu, &uc)) {
 		case UCALL_ABORT:
-			REPORT_GUEST_ASSERT_3(uc, "0x%lx 0x%lx 0x%lx");
+			REPORT_GUEST_ASSERT(uc);
 			break;
 		case UCALL_DONE:
 			goto done;

From 7ce7f8e754186f71ba7daffbc99543961a613bba Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:41 -0700
Subject: [PATCH 0261/1189] KVM: selftests: Rip out old, param-based guest
 assert macros

Drop the param-based guest assert macros and enable the printf versions
for all selftests.  Note!  This change can affect tests even if they
don't use directly use guest asserts!  E.g. via library code, or due to
the compiler making different optimization decisions.

Link: https://lore.kernel.org/r/20230729003643.1053367-33-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../selftests/kvm/aarch64/arch_timer.c        |  2 -
 .../selftests/kvm/aarch64/debug-exceptions.c  |  2 -
 .../selftests/kvm/aarch64/hypercalls.c        |  2 -
 .../selftests/kvm/aarch64/page_fault_test.c   |  2 -
 .../testing/selftests/kvm/aarch64/vgic_irq.c  |  2 -
 .../testing/selftests/kvm/guest_print_test.c  |  2 -
 .../selftests/kvm/include/ucall_common.h      | 71 -------------------
 .../testing/selftests/kvm/memslot_perf_test.c |  2 -
 tools/testing/selftests/kvm/s390x/memop.c     |  2 -
 tools/testing/selftests/kvm/s390x/tprot.c     |  2 -
 .../selftests/kvm/set_memory_region_test.c    |  2 -
 tools/testing/selftests/kvm/steal_time.c      |  2 -
 .../testing/selftests/kvm/x86_64/cpuid_test.c |  2 -
 .../kvm/x86_64/hyperv_extended_hypercalls.c   |  2 -
 .../selftests/kvm/x86_64/hyperv_features.c    |  2 -
 .../selftests/kvm/x86_64/kvm_pv_test.c        |  2 -
 .../selftests/kvm/x86_64/monitor_mwait_test.c |  2 -
 .../kvm/x86_64/nested_exceptions_test.c       |  2 -
 .../selftests/kvm/x86_64/set_boot_cpu_id.c    |  2 -
 .../kvm/x86_64/svm_nested_soft_inject_test.c  |  2 -
 .../selftests/kvm/x86_64/tsc_msrs_test.c      |  2 -
 .../selftests/kvm/x86_64/userspace_io_test.c  |  2 -
 .../selftests/kvm/x86_64/vmx_pmu_caps_test.c  |  2 -
 .../selftests/kvm/x86_64/xcr0_cpuid_test.c    |  2 -
 24 files changed, 117 deletions(-)

diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c
index b53bcf126e6a..274b8465b42a 100644
--- a/tools/testing/selftests/kvm/aarch64/arch_timer.c
+++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c
@@ -19,8 +19,6 @@
  *
  * Copyright (c) 2021, Google LLC.
  */
-#define USE_GUEST_ASSERT_PRINTF 1
-
 #define _GNU_SOURCE
 
 #include <stdlib.h>
diff --git a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
index fdd5b05e1b0e..f5b6cb3a0019 100644
--- a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
+++ b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
@@ -1,6 +1,4 @@
 // SPDX-License-Identifier: GPL-2.0
-#define USE_GUEST_ASSERT_PRINTF 1
-
 #include <test_util.h>
 #include <kvm_util.h>
 #include <processor.h>
diff --git a/tools/testing/selftests/kvm/aarch64/hypercalls.c b/tools/testing/selftests/kvm/aarch64/hypercalls.c
index 94555a7d3c7e..31f66ba97228 100644
--- a/tools/testing/selftests/kvm/aarch64/hypercalls.c
+++ b/tools/testing/selftests/kvm/aarch64/hypercalls.c
@@ -8,8 +8,6 @@
  * hypercalls are properly masked or unmasked to the guest when disabled or
  * enabled from the KVM userspace, respectively.
  */
-#define USE_GUEST_ASSERT_PRINTF 1
-
 #include <errno.h>
 #include <linux/arm-smccc.h>
 #include <asm/kvm.h>
diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
index 0b0dd90feae5..47bb914ab2fa 100644
--- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c
+++ b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
@@ -7,8 +7,6 @@
  * hugetlbfs with a hole). It checks that the expected handling method is
  * called (e.g., uffd faults with the right address and write/read flag).
  */
-#define USE_GUEST_ASSERT_PRINTF 1
-
 #define _GNU_SOURCE
 #include <linux/bitmap.h>
 #include <fcntl.h>
diff --git a/tools/testing/selftests/kvm/aarch64/vgic_irq.c b/tools/testing/selftests/kvm/aarch64/vgic_irq.c
index 67da33aa6d17..2e64b4856e38 100644
--- a/tools/testing/selftests/kvm/aarch64/vgic_irq.c
+++ b/tools/testing/selftests/kvm/aarch64/vgic_irq.c
@@ -7,8 +7,6 @@
  * host to inject a specific intid via a GUEST_SYNC call, and then checks that
  * it received it.
  */
-#define USE_GUEST_ASSERT_PRINTF 1
-
 #include <asm/kvm.h>
 #include <asm/kvm_para.h>
 #include <sys/eventfd.h>
diff --git a/tools/testing/selftests/kvm/guest_print_test.c b/tools/testing/selftests/kvm/guest_print_test.c
index 267e01d057fb..41230b746190 100644
--- a/tools/testing/selftests/kvm/guest_print_test.c
+++ b/tools/testing/selftests/kvm/guest_print_test.c
@@ -4,8 +4,6 @@
  *
  * Copyright 2022, Google, Inc. and/or its affiliates.
  */
-#define USE_GUEST_ASSERT_PRINTF 1
-
 #include <fcntl.h>
 #include <stdio.h>
 #include <stdlib.h>
diff --git a/tools/testing/selftests/kvm/include/ucall_common.h b/tools/testing/selftests/kvm/include/ucall_common.h
index 9e5948dab030..99bbb56cd1a5 100644
--- a/tools/testing/selftests/kvm/include/ucall_common.h
+++ b/tools/testing/selftests/kvm/include/ucall_common.h
@@ -66,7 +66,6 @@ enum guest_assert_builtin_args {
 	GUEST_ASSERT_BUILTIN_NARGS
 };
 
-#ifdef USE_GUEST_ASSERT_PRINTF
 #define ____GUEST_ASSERT(_condition, _exp, _fmt, _args...)				\
 do {											\
 	if (!(_condition))								\
@@ -108,74 +107,4 @@ do {										\
 #define GUEST_ASSERT_1(_condition, arg1) \
 	__GUEST_ASSERT(_condition, "arg1 = 0x%lx", arg1)
 
-#else
-
-#define __GUEST_ASSERT(_condition, _condstr, _nargs, _args...)		\
-do {									\
-	if (!(_condition))						\
-		ucall(UCALL_ABORT, GUEST_ASSERT_BUILTIN_NARGS + _nargs,	\
-		      "Failed guest assert: " _condstr,			\
-		      __FILE__, __LINE__, ##_args);			\
-} while (0)
-
-#define GUEST_ASSERT(_condition) \
-	__GUEST_ASSERT(_condition, #_condition, 0, 0)
-
-#define GUEST_ASSERT_1(_condition, arg1) \
-	__GUEST_ASSERT(_condition, #_condition, 1, (arg1))
-
-#define GUEST_ASSERT_2(_condition, arg1, arg2) \
-	__GUEST_ASSERT(_condition, #_condition, 2, (arg1), (arg2))
-
-#define GUEST_ASSERT_3(_condition, arg1, arg2, arg3) \
-	__GUEST_ASSERT(_condition, #_condition, 3, (arg1), (arg2), (arg3))
-
-#define GUEST_ASSERT_4(_condition, arg1, arg2, arg3, arg4) \
-	__GUEST_ASSERT(_condition, #_condition, 4, (arg1), (arg2), (arg3), (arg4))
-
-#define GUEST_ASSERT_EQ(a, b) __GUEST_ASSERT((a) == (b), #a " == " #b, 2, a, b)
-
-#define __REPORT_GUEST_ASSERT(_ucall, fmt, _args...)			\
-	TEST_FAIL("%s at %s:%ld\n" fmt,					\
-		  (const char *)(_ucall).args[GUEST_ERROR_STRING],	\
-		  (const char *)(_ucall).args[GUEST_FILE],		\
-		  (_ucall).args[GUEST_LINE],				\
-		  ##_args)
-
-#define GUEST_ASSERT_ARG(ucall, i) ((ucall).args[GUEST_ASSERT_BUILTIN_NARGS + i])
-
-#define REPORT_GUEST_ASSERT(ucall)		\
-	__REPORT_GUEST_ASSERT((ucall), "")
-
-#define REPORT_GUEST_ASSERT_1(ucall, fmt)			\
-	__REPORT_GUEST_ASSERT((ucall),				\
-			      fmt,				\
-			      GUEST_ASSERT_ARG((ucall), 0))
-
-#define REPORT_GUEST_ASSERT_2(ucall, fmt)			\
-	__REPORT_GUEST_ASSERT((ucall),				\
-			      fmt,				\
-			      GUEST_ASSERT_ARG((ucall), 0),	\
-			      GUEST_ASSERT_ARG((ucall), 1))
-
-#define REPORT_GUEST_ASSERT_3(ucall, fmt)			\
-	__REPORT_GUEST_ASSERT((ucall),				\
-			      fmt,				\
-			      GUEST_ASSERT_ARG((ucall), 0),	\
-			      GUEST_ASSERT_ARG((ucall), 1),	\
-			      GUEST_ASSERT_ARG((ucall), 2))
-
-#define REPORT_GUEST_ASSERT_4(ucall, fmt)			\
-	__REPORT_GUEST_ASSERT((ucall),				\
-			      fmt,				\
-			      GUEST_ASSERT_ARG((ucall), 0),	\
-			      GUEST_ASSERT_ARG((ucall), 1),	\
-			      GUEST_ASSERT_ARG((ucall), 2),	\
-			      GUEST_ASSERT_ARG((ucall), 3))
-
-#define REPORT_GUEST_ASSERT_N(ucall, fmt, args...)	\
-	__REPORT_GUEST_ASSERT((ucall), fmt, ##args)
-
-#endif /* USE_GUEST_ASSERT_PRINTF */
-
 #endif /* SELFTEST_KVM_UCALL_COMMON_H */
diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c
index 55f1bc70e571..20eb2e730800 100644
--- a/tools/testing/selftests/kvm/memslot_perf_test.c
+++ b/tools/testing/selftests/kvm/memslot_perf_test.c
@@ -6,8 +6,6 @@
  *
  * Basic guest setup / host vCPU thread code lifted from set_memory_region_test.
  */
-#define USE_GUEST_ASSERT_PRINTF 1
-
 #include <pthread.h>
 #include <sched.h>
 #include <semaphore.h>
diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390x/memop.c
index a49173907cec..bb3ca9a5d731 100644
--- a/tools/testing/selftests/kvm/s390x/memop.c
+++ b/tools/testing/selftests/kvm/s390x/memop.c
@@ -4,8 +4,6 @@
  *
  * Copyright (C) 2019, Red Hat, Inc.
  */
-#define USE_GUEST_ASSERT_PRINTF 1
-
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
diff --git a/tools/testing/selftests/kvm/s390x/tprot.c b/tools/testing/selftests/kvm/s390x/tprot.c
index c12c6824d963..c73f948c9b63 100644
--- a/tools/testing/selftests/kvm/s390x/tprot.c
+++ b/tools/testing/selftests/kvm/s390x/tprot.c
@@ -4,8 +4,6 @@
  *
  * Copyright IBM Corp. 2021
  */
-#define USE_GUEST_ASSERT_PRINTF 1
-
 #include <sys/mman.h>
 #include "test_util.h"
 #include "kvm_util.h"
diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
index dd8f4bac9df8..b32960189f5f 100644
--- a/tools/testing/selftests/kvm/set_memory_region_test.c
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -1,6 +1,4 @@
 // SPDX-License-Identifier: GPL-2.0
-#define USE_GUEST_ASSERT_PRINTF 1
-
 #define _GNU_SOURCE /* for program_invocation_short_name */
 #include <fcntl.h>
 #include <pthread.h>
diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c
index 8649c8545882..171adfb2a6cb 100644
--- a/tools/testing/selftests/kvm/steal_time.c
+++ b/tools/testing/selftests/kvm/steal_time.c
@@ -4,8 +4,6 @@
  *
  * Copyright (C) 2020, Red Hat, Inc.
  */
-#define USE_GUEST_ASSERT_PRINTF 1
-
 #define _GNU_SOURCE
 #include <stdio.h>
 #include <time.h>
diff --git a/tools/testing/selftests/kvm/x86_64/cpuid_test.c b/tools/testing/selftests/kvm/x86_64/cpuid_test.c
index eb1b65ffc0d5..3b34d8156d1c 100644
--- a/tools/testing/selftests/kvm/x86_64/cpuid_test.c
+++ b/tools/testing/selftests/kvm/x86_64/cpuid_test.c
@@ -4,8 +4,6 @@
  *
  * Generic tests for KVM CPUID set/get ioctls
  */
-#define USE_GUEST_ASSERT_PRINTF 1
-
 #include <asm/kvm_para.h>
 #include <linux/kvm_para.h>
 #include <stdint.h>
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c b/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c
index 0107d54a1a08..e036db1f32b9 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c
@@ -8,8 +8,6 @@
  * Copyright 2022 Google LLC
  * Author: Vipin Sharma <vipinsh@google.com>
  */
-#define USE_GUEST_ASSERT_PRINTF 1
-
 #include "kvm_util.h"
 #include "processor.h"
 #include "hyperv.h"
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
index 41a6beff78c4..9f28aa276c4e 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
@@ -4,8 +4,6 @@
  *
  * Tests for Hyper-V features enablement
  */
-#define USE_GUEST_ASSERT_PRINTF 1
-
 #include <asm/kvm_para.h>
 #include <linux/kvm_para.h>
 #include <stdint.h>
diff --git a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c
index 1c28b77ff3cd..9e2879af7c20 100644
--- a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c
+++ b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c
@@ -4,8 +4,6 @@
  *
  * Tests for KVM paravirtual feature disablement
  */
-#define USE_GUEST_ASSERT_PRINTF 1
-
 #include <asm/kvm_para.h>
 #include <linux/kvm_para.h>
 #include <stdint.h>
diff --git a/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c b/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c
index 960fecab3742..80aa3d8b18f8 100644
--- a/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c
+++ b/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c
@@ -1,6 +1,4 @@
 // SPDX-License-Identifier: GPL-2.0
-#define USE_GUEST_ASSERT_PRINTF 1
-
 #include <fcntl.h>
 #include <stdio.h>
 #include <stdlib.h>
diff --git a/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c b/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c
index 4a29f59a76be..3670331adf21 100644
--- a/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c
+++ b/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c
@@ -1,6 +1,4 @@
 // SPDX-License-Identifier: GPL-2.0-only
-#define USE_GUEST_ASSERT_PRINTF 1
-
 #define _GNU_SOURCE /* for program_invocation_short_name */
 
 #include "test_util.h"
diff --git a/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c b/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c
index abb3f26d3ce0..366cf18600bc 100644
--- a/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c
+++ b/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c
@@ -4,8 +4,6 @@
  *
  * Copyright (C) 2020, Red Hat, Inc.
  */
-#define USE_GUEST_ASSERT_PRINTF 1
-
 #define _GNU_SOURCE /* for program_invocation_name */
 #include <fcntl.h>
 #include <stdio.h>
diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c
index c908412c5754..7ee44496cf97 100644
--- a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c
+++ b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c
@@ -8,8 +8,6 @@
  *   Copyright (C) 2021, Red Hat, Inc.
  *
  */
-#define USE_GUEST_ASSERT_PRINTF 1
-
 #include <stdatomic.h>
 #include <stdio.h>
 #include <unistd.h>
diff --git a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c
index cf9114f70e1c..12b0964f4f13 100644
--- a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c
@@ -4,8 +4,6 @@
  *
  * Copyright (C) 2020, Red Hat, Inc.
  */
-#define USE_GUEST_ASSERT_PRINTF 1
-
 #include <stdio.h>
 #include <string.h>
 #include "kvm_util.h"
diff --git a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c
index 2c5d2a18d184..255c50b0dc32 100644
--- a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c
+++ b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c
@@ -1,6 +1,4 @@
 // SPDX-License-Identifier: GPL-2.0
-#define USE_GUEST_ASSERT_PRINTF 1
-
 #include <fcntl.h>
 #include <stdio.h>
 #include <stdlib.h>
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c
index ba09d5a01c39..ebbcb0a3f743 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c
@@ -10,8 +10,6 @@
  * and check it can be retrieved with KVM_GET_MSR, also test
  * the invalid LBR formats are rejected.
  */
-#define USE_GUEST_ASSERT_PRINTF 1
-
 #define _GNU_SOURCE /* for program_invocation_short_name */
 #include <sys/ioctl.h>
 
diff --git a/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c b/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c
index 5e8290797720..77d04a7bdadd 100644
--- a/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c
@@ -4,8 +4,6 @@
  *
  * Copyright (C) 2022, Google LLC.
  */
-#define USE_GUEST_ASSERT_PRINTF 1
-
 #include <fcntl.h>
 #include <stdio.h>
 #include <stdlib.h>

From 6f321017c84b33a69f6ac131f6c91d1e8a5ff585 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:42 -0700
Subject: [PATCH 0262/1189] KVM: selftests: Print out guest RIP on unhandled
 exception

Use the newfanged printf-based guest assert framework to spit out the
guest RIP when an unhandled exception is detected, which makes debugging
such failures *much* easier.

Link: https://lore.kernel.org/r/20230729003643.1053367-34-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../selftests/kvm/lib/x86_64/processor.c       | 18 ++++++------------
 1 file changed, 6 insertions(+), 12 deletions(-)

diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index d4a0b504b1e0..d8288374078e 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -1074,11 +1074,6 @@ static bool kvm_fixup_exception(struct ex_regs *regs)
 	return true;
 }
 
-void kvm_exit_unexpected_vector(uint32_t value)
-{
-	ucall(UCALL_UNHANDLED, 1, value);
-}
-
 void route_exception(struct ex_regs *regs)
 {
 	typedef void(*handler)(struct ex_regs *);
@@ -1092,7 +1087,10 @@ void route_exception(struct ex_regs *regs)
 	if (kvm_fixup_exception(regs))
 		return;
 
-	kvm_exit_unexpected_vector(regs->vector);
+	ucall_assert(UCALL_UNHANDLED,
+		     "Unhandled exception in guest", __FILE__, __LINE__,
+		     "Unhandled exception '0x%lx' at guest RIP '0x%lx'",
+		     regs->vector, regs->rip);
 }
 
 void vm_init_descriptor_tables(struct kvm_vm *vm)
@@ -1135,12 +1133,8 @@ void assert_on_unhandled_exception(struct kvm_vcpu *vcpu)
 {
 	struct ucall uc;
 
-	if (get_ucall(vcpu, &uc) == UCALL_UNHANDLED) {
-		uint64_t vector = uc.args[0];
-
-		TEST_FAIL("Unexpected vectored event in guest (vector:0x%lx)",
-			  vector);
-	}
+	if (get_ucall(vcpu, &uc) == UCALL_UNHANDLED)
+		REPORT_GUEST_ASSERT(uc);
 }
 
 const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid,

From a05c4c2bd8b59e291cc9d68b79d6b45a34bcb54e Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:36:43 -0700
Subject: [PATCH 0263/1189] KVM: selftests: Use GUEST_FAIL() in ARM's arch
 timer helpers

Use GUEST_FAIL() in ARM's arch timer helpers now that printf-based
guest asserts are the default (and only) style of guest asserts, and
say goodbye to the GUEST_ASSERT_1() alias.

Link: https://lore.kernel.org/r/20230729003643.1053367-35-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../selftests/kvm/include/aarch64/arch_timer.h       | 12 ++++++------
 tools/testing/selftests/kvm/include/ucall_common.h   |  4 ----
 2 files changed, 6 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/kvm/include/aarch64/arch_timer.h b/tools/testing/selftests/kvm/include/aarch64/arch_timer.h
index cb7c03de3a21..b3e97525cb55 100644
--- a/tools/testing/selftests/kvm/include/aarch64/arch_timer.h
+++ b/tools/testing/selftests/kvm/include/aarch64/arch_timer.h
@@ -41,7 +41,7 @@ static inline uint64_t timer_get_cntct(enum arch_timer timer)
 	case PHYSICAL:
 		return read_sysreg(cntpct_el0);
 	default:
-		GUEST_ASSERT_1(0, timer);
+		GUEST_FAIL("Unexpected timer type = %u", timer);
 	}
 
 	/* We should not reach here */
@@ -58,7 +58,7 @@ static inline void timer_set_cval(enum arch_timer timer, uint64_t cval)
 		write_sysreg(cval, cntp_cval_el0);
 		break;
 	default:
-		GUEST_ASSERT_1(0, timer);
+		GUEST_FAIL("Unexpected timer type = %u", timer);
 	}
 
 	isb();
@@ -72,7 +72,7 @@ static inline uint64_t timer_get_cval(enum arch_timer timer)
 	case PHYSICAL:
 		return read_sysreg(cntp_cval_el0);
 	default:
-		GUEST_ASSERT_1(0, timer);
+		GUEST_FAIL("Unexpected timer type = %u", timer);
 	}
 
 	/* We should not reach here */
@@ -89,7 +89,7 @@ static inline void timer_set_tval(enum arch_timer timer, uint32_t tval)
 		write_sysreg(tval, cntp_tval_el0);
 		break;
 	default:
-		GUEST_ASSERT_1(0, timer);
+		GUEST_FAIL("Unexpected timer type = %u", timer);
 	}
 
 	isb();
@@ -105,7 +105,7 @@ static inline void timer_set_ctl(enum arch_timer timer, uint32_t ctl)
 		write_sysreg(ctl, cntp_ctl_el0);
 		break;
 	default:
-		GUEST_ASSERT_1(0, timer);
+		GUEST_FAIL("Unexpected timer type = %u", timer);
 	}
 
 	isb();
@@ -119,7 +119,7 @@ static inline uint32_t timer_get_ctl(enum arch_timer timer)
 	case PHYSICAL:
 		return read_sysreg(cntp_ctl_el0);
 	default:
-		GUEST_ASSERT_1(0, timer);
+		GUEST_FAIL("Unexpected timer type = %u", timer);
 	}
 
 	/* We should not reach here */
diff --git a/tools/testing/selftests/kvm/include/ucall_common.h b/tools/testing/selftests/kvm/include/ucall_common.h
index 99bbb56cd1a5..112bc1da732a 100644
--- a/tools/testing/selftests/kvm/include/ucall_common.h
+++ b/tools/testing/selftests/kvm/include/ucall_common.h
@@ -103,8 +103,4 @@ do {										\
 		    (const char *)(ucall).args[GUEST_FILE],			\
 		    (ucall).args[GUEST_LINE], "%s", (ucall).buffer)
 
-/* FIXME: Drop this alias once the param-based guest asserts are gone. */
-#define GUEST_ASSERT_1(_condition, arg1) \
-	__GUEST_ASSERT(_condition, "arg1 = 0x%lx", arg1)
-
 #endif /* SELFTEST_KVM_UCALL_COMMON_H */

From 7f717f54845c518a64fe5464d855ddeca272483a Mon Sep 17 00:00:00 2001
From: Michal Luczaj <mhal@rbox.co>
Date: Tue, 18 Jul 2023 12:15:44 +0200
Subject: [PATCH 0264/1189] KVM: x86: Remove
 x86_emulate_ops::guest_has_long_mode

Remove x86_emulate_ops::guest_has_long_mode along with its implementation,
emulator_guest_has_long_mode(). It has been unused since commit
1d0da94cdafe ("KVM: x86: do not go through ctxt->ops when emulating rsm").

No functional change intended.

Signed-off-by: Michal Luczaj <mhal@rbox.co>
Link: https://lore.kernel.org/r/20230718101809.1249769-1-mhal@rbox.co
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/kvm_emulate.h | 1 -
 arch/x86/kvm/x86.c         | 6 ------
 2 files changed, 7 deletions(-)

diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
index ab65f3a47dfd..be7aeb9b8ea3 100644
--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
@@ -213,7 +213,6 @@ struct x86_emulate_ops {
 
 	bool (*get_cpuid)(struct x86_emulate_ctxt *ctxt, u32 *eax, u32 *ebx,
 			  u32 *ecx, u32 *edx, bool exact_only);
-	bool (*guest_has_long_mode)(struct x86_emulate_ctxt *ctxt);
 	bool (*guest_has_movbe)(struct x86_emulate_ctxt *ctxt);
 	bool (*guest_has_fxsr)(struct x86_emulate_ctxt *ctxt);
 	bool (*guest_has_rdpid)(struct x86_emulate_ctxt *ctxt);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a6b9bea62fb8..0fca1546e029 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8229,11 +8229,6 @@ static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt,
 	return kvm_cpuid(emul_to_vcpu(ctxt), eax, ebx, ecx, edx, exact_only);
 }
 
-static bool emulator_guest_has_long_mode(struct x86_emulate_ctxt *ctxt)
-{
-	return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_LM);
-}
-
 static bool emulator_guest_has_movbe(struct x86_emulate_ctxt *ctxt)
 {
 	return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_MOVBE);
@@ -8335,7 +8330,6 @@ static const struct x86_emulate_ops emulate_ops = {
 	.fix_hypercall       = emulator_fix_hypercall,
 	.intercept           = emulator_intercept,
 	.get_cpuid           = emulator_get_cpuid,
-	.guest_has_long_mode = emulator_guest_has_long_mode,
 	.guest_has_movbe     = emulator_guest_has_movbe,
 	.guest_has_fxsr      = emulator_guest_has_fxsr,
 	.guest_has_rdpid     = emulator_guest_has_rdpid,

From af8e2ccfa6f101f505add076c1a4d56c718e0d50 Mon Sep 17 00:00:00 2001
From: Takahiro Itazuri <itazur@amazon.com>
Date: Wed, 12 Jul 2023 19:31:36 +0100
Subject: [PATCH 0265/1189] KVM: x86: Advertise host CPUID 0x80000005 in
 KVM_GET_SUPPORTED_CPUID

Advertise CPUID 0x80000005 (L1 cache and TLB info) to userspace so that
VMMs that reflect KVM_GET_SUPPORTED_CPUID into KVM_SET_CPUID2 will
enumerate sane cache/TLB information to the guest.

CPUID 0x80000006 (L2 cache and TLB and L3 cache info) has been returned
since commit 43d05de2bee7 ("KVM: pass through CPUID(0x80000006)").
Enumerating both 0x80000005 and 0x80000006 with KVM_GET_SUPPORTED_CPUID
is better than reporting one or the other, and 0x80000005 could be helpful
for VMM to pass it to KVM_SET_CPUID{,2} for the same reason with
0x80000006.

Signed-off-by: Takahiro Itazuri <itazur@amazon.com>
Link: https://lore.kernel.org/all/ZK7NmfKI9xur%2FMop@google.com
Link: https://lore.kernel.org/r/20230712183136.85561-1-itazur@amazon.com
[sean: add link, massage changelog]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/cpuid.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 7f4d13383cf2..ad6566636c22 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -1151,6 +1151,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		cpuid_entry_override(entry, CPUID_8000_0001_EDX);
 		cpuid_entry_override(entry, CPUID_8000_0001_ECX);
 		break;
+	case 0x80000005:
+		/*  Pass host L1 cache and TLB info. */
+		break;
 	case 0x80000006:
 		/* Drop reserved bits, pass host L2 cache and TLB info. */
 		entry->edx &= ~GENMASK(17, 16);

From a2fd5d02bad6d63daaaf4a8bb19c2400387aca61 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 6 Jun 2023 17:43:09 -0700
Subject: [PATCH 0266/1189] KVM: x86: Snapshot host's
 MSR_IA32_ARCH_CAPABILITIES

Snapshot the host's MSR_IA32_ARCH_CAPABILITIES, if it's supported, instead
of reading the MSR every time KVM wants to query the host state, e.g. when
initializing the default value during vCPU creation.  The paths that query
ARCH_CAPABILITIES aren't particularly performance sensitive, but creating
vCPUs is a frequent enough operation that burning 8 bytes is a good
trade-off.

Alternatively, KVM could add a field in kvm_caps and thus skip the
on-demand calculations entirely, but a pure snapshot isn't possible due to
the way KVM handles the l1tf_vmx_mitigation module param.  And unlike the
other "supported" fields in kvm_caps, KVM doesn't enforce the "supported"
value, i.e. KVM treats ARCH_CAPABILITIES like a CPUID leaf and lets
userspace advertise whatever it wants.  Those problems are solvable, but
it's not clear there is real benefit versus snapshotting the host value,
and grabbing the host value will allow additional cleanup of KVM's
FB_CLEAR_CTRL code.

Link: https://lore.kernel.org/all/20230524061634.54141-2-chao.gao@intel.com
Cc: Chao Gao <chao.gao@intel.com>
Cc: Xiaoyao Li <xiaoyao.li@intel.com>
Reviewed-by: Chao Gao <chao.gao@intel.com>
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Link: https://lore.kernel.org/r/20230607004311.1420507-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/vmx/vmx.c | 22 ++++++----------------
 arch/x86/kvm/x86.c     | 13 +++++++------
 arch/x86/kvm/x86.h     |  1 +
 3 files changed, 14 insertions(+), 22 deletions(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 254f2296e549..f0ec9acae86c 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -255,14 +255,9 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
 		return 0;
 	}
 
-	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) {
-		u64 msr;
-
-		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr);
-		if (msr & ARCH_CAP_SKIP_VMENTRY_L1DFLUSH) {
-			l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED;
-			return 0;
-		}
+	if (host_arch_capabilities & ARCH_CAP_SKIP_VMENTRY_L1DFLUSH) {
+		l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED;
+		return 0;
 	}
 
 	/* If set to auto use the default l1tf mitigation method */
@@ -373,15 +368,10 @@ static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp)
 
 static void vmx_setup_fb_clear_ctrl(void)
 {
-	u64 msr;
-
-	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES) &&
+	if ((host_arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) &&
 	    !boot_cpu_has_bug(X86_BUG_MDS) &&
-	    !boot_cpu_has_bug(X86_BUG_TAA)) {
-		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr);
-		if (msr & ARCH_CAP_FB_CLEAR_CTRL)
-			vmx_fb_clear_ctrl_available = true;
-	}
+	    !boot_cpu_has_bug(X86_BUG_TAA))
+		vmx_fb_clear_ctrl_available = true;
 }
 
 static __always_inline void vmx_disable_fb_clear(struct vcpu_vmx *vmx)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0fca1546e029..a1b13d2d1d71 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -237,6 +237,9 @@ EXPORT_SYMBOL_GPL(enable_apicv);
 u64 __read_mostly host_xss;
 EXPORT_SYMBOL_GPL(host_xss);
 
+u64 __read_mostly host_arch_capabilities;
+EXPORT_SYMBOL_GPL(host_arch_capabilities);
+
 const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
 	KVM_GENERIC_VM_STATS(),
 	STATS_DESC_COUNTER(VM, mmu_shadow_zapped),
@@ -1611,12 +1614,7 @@ static bool kvm_is_immutable_feature_msr(u32 msr)
 
 static u64 kvm_get_arch_capabilities(void)
 {
-	u64 data = 0;
-
-	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) {
-		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, data);
-		data &= KVM_SUPPORTED_ARCH_CAP;
-	}
+	u64 data = host_arch_capabilities & KVM_SUPPORTED_ARCH_CAP;
 
 	/*
 	 * If nx_huge_pages is enabled, KVM's shadow paging will ensure that
@@ -9490,6 +9488,9 @@ static int __kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
 
 	kvm_init_pmu_capability(ops->pmu_ops);
 
+	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
+		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, host_arch_capabilities);
+
 	r = ops->hardware_setup();
 	if (r != 0)
 		goto out_mmu_exit;
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 82e3dafc5453..1e7be1f6ab29 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -323,6 +323,7 @@ fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu);
 
 extern u64 host_xcr0;
 extern u64 host_xss;
+extern u64 host_arch_capabilities;
 
 extern struct kvm_caps kvm_caps;
 

From 550ba57faa04042956079b8d09ec0f83bef8817f Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 6 Jun 2023 17:43:10 -0700
Subject: [PATCH 0267/1189] KVM: VMX: Drop unnecessary
 vmx_fb_clear_ctrl_available "cache"

Now that KVM snapshots the host's MSR_IA32_ARCH_CAPABILITIES, drop the
similar snapshot/cache of whether or not KVM is allowed to manipulate
MSR_IA32_MCU_OPT_CTRL.FB_CLEAR_DIS.  The motivation for the cache was
presumably to avoid the RDMSR, e.g. boot_cpu_has_bug() is quite cheap, and
modifying the vCPU's MSR_IA32_ARCH_CAPABILITIES is an infrequent option
and a relatively slow path.

Cc: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Reviewed-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Link: https://lore.kernel.org/r/20230607004311.1420507-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/vmx/vmx.c | 17 +++--------------
 1 file changed, 3 insertions(+), 14 deletions(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index f0ec9acae86c..e6d1ce2d230c 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -237,9 +237,6 @@ static const struct {
 #define L1D_CACHE_ORDER 4
 static void *vmx_l1d_flush_pages;
 
-/* Control for disabling CPU Fill buffer clear */
-static bool __read_mostly vmx_fb_clear_ctrl_available;
-
 static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
 {
 	struct page *page;
@@ -366,14 +363,6 @@ static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp)
 	return sysfs_emit(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option);
 }
 
-static void vmx_setup_fb_clear_ctrl(void)
-{
-	if ((host_arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) &&
-	    !boot_cpu_has_bug(X86_BUG_MDS) &&
-	    !boot_cpu_has_bug(X86_BUG_TAA))
-		vmx_fb_clear_ctrl_available = true;
-}
-
 static __always_inline void vmx_disable_fb_clear(struct vcpu_vmx *vmx)
 {
 	u64 msr;
@@ -399,7 +388,9 @@ static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx)
 
 static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx)
 {
-	vmx->disable_fb_clear = vmx_fb_clear_ctrl_available;
+	vmx->disable_fb_clear = (host_arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) &&
+				!boot_cpu_has_bug(X86_BUG_MDS) &&
+				!boot_cpu_has_bug(X86_BUG_TAA);
 
 	/*
 	 * If guest will not execute VERW, there is no need to set FB_CLEAR_DIS
@@ -8626,8 +8617,6 @@ static int __init vmx_init(void)
 	if (r)
 		goto err_l1d_flush;
 
-	vmx_setup_fb_clear_ctrl();
-
 	for_each_possible_cpu(cpu) {
 		INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));
 

From 775bc098657b4996c8537d0eaf9c20138428b699 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 21 Jul 2023 16:38:58 -0700
Subject: [PATCH 0268/1189] KVM: VMX: Drop manual TLB flush when migrating
 vmcs.APIC_ACCESS_ADDR
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove the superfluous flush of the current TLB in VMX's handling of
migration of the APIC-access page, as a full TLB flush on all vCPUs will
have already been performed in response to kvm_unmap_gfn_range() *if*
there were SPTEs pointing at the APIC-access page.  And if there were no
valid SPTEs, then there can't possibly be TLB entries to flush.

The extra flush was added by commit fb6c81984313 ("kvm: vmx: Flush TLB
when the APIC-access address changes"), with the justification of "because
the SDM says so".  The SDM said, and still says:

 As detailed in Section xx.x.x, an access to the APIC-access page might
 not cause an APIC-access VM exit if software does not properly invalidate
 information that may be cached from the EPT paging structures. If EPT was
 in use on a logical processor at one time with EPTP X, it is recommended
 that software use the INVEPT instruction with the “single-context” INVEPT
 type and with EPTP X in the INVEPT descriptor before a VM entry on the
 same logical processor that enables EPT with EPTP X and either (a) the
 "virtualize APIC accesses" VM- execution control was changed from 0 to 1;
 or (b) the value of the APIC-access address was changed.

But the "recommendation" for (b) is predicated on there actually being
a valid EPT translation *and* possible TLB entries for the GPA (or guest
VA when using shadow paging).  It's possible that a different vCPU has
established a mapping for the new page, but the current vCPU can't have
entered the guest, i.e. can't have created a TLB entry, between flushing
the old mappings and changing its vmcs.APIC_ACCESS_ADDR.

kvm_unmap_gfn_range() waits for all vCPUs to ack KVM_REQ_APIC_PAGE_RELOAD,
and then flushes remote TLBs (which may or may not also pend a request).
Thus the vCPU is guaranteed to update vmcs.APIC_ACCESS_ADDR before
re-entering the guest and before it can possibly create new TLB entries.

In other words, KVM does flush in this case, it just does so earlier
on while handling the page migration.

Note, VMX also flushes if the vCPU is migrated to a new pCPU, i.e. if
the vCPU is migrated to a pCPU that entered the guest for a different
vCPU.

Suggested-by: Yu Zhang <yu.c.zhang@linux.intel.com>
Cc: Jim Mattson <jmattson@google.com>
Reviewed-by: Yu Zhang <yu.c.zhang@linux.intel.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Link: https://lore.kernel.org/r/20230721233858.2343941-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/vmx/vmx.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 0ecf4be2c6af..3f868826db7d 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6767,8 +6767,10 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu)
 	vmcs_write64(APIC_ACCESS_ADDR, pfn_to_hpa(pfn));
 	read_unlock(&vcpu->kvm->mmu_lock);
 
-	vmx_flush_tlb_current(vcpu);
-
+	/*
+	 * No need for a manual TLB flush at this point, KVM has already done a
+	 * flush if there were SPTEs pointing at the previous page.
+	 */
 out:
 	/*
 	 * Do not pin apic access page in memory, the MMU notifier

From d518f8cc10af7a1265595fccf553a3a5f7121e4f Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 7 Jun 2023 13:35:17 -0700
Subject: [PATCH 0269/1189] KVM: SVM: Fix dead KVM_BUG() code in LBR MSR
 virtualization

Refactor KVM's handling of LBR MSRs on SVM to avoid a second layer of
case statements, and thus eliminate a dead KVM_BUG() call, which (a) will
never be hit in the current code base and (b) if a future commit breaks
things, will never fire as KVM passes "false" instead "true" or '1' for
the KVM_BUG() condition.

Reported-by: Michal Luczaj <mhal@rbox.co>
Cc: Yuan Yao <yuan.yao@intel.com>
Link: https://lore.kernel.org/r/20230607203519.1570167-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.c | 45 +++++++++++++++---------------------------
 1 file changed, 16 insertions(+), 29 deletions(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 1bc0936bbd51..623916221ff7 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -980,43 +980,22 @@ static void svm_disable_lbrv(struct kvm_vcpu *vcpu)
 		svm_copy_lbrs(svm->vmcb01.ptr, svm->vmcb);
 }
 
-static int svm_get_lbr_msr(struct vcpu_svm *svm, u32 index)
+static struct vmcb *svm_get_lbr_vmcb(struct vcpu_svm *svm)
 {
 	/*
-	 * If the LBR virtualization is disabled, the LBR msrs are always
-	 * kept in the vmcb01 to avoid copying them on nested guest entries.
-	 *
-	 * If nested, and the LBR virtualization is enabled/disabled, the msrs
-	 * are moved between the vmcb01 and vmcb02 as needed.
+	 * If LBR virtualization is disabled, the LBR MSRs are always kept in
+	 * vmcb01.  If LBR virtualization is enabled and L1 is running VMs of
+	 * its own, the MSRs are moved between vmcb01 and vmcb02 as needed.
 	 */
-	struct vmcb *vmcb =
-		(svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK) ?
-			svm->vmcb : svm->vmcb01.ptr;
-
-	switch (index) {
-	case MSR_IA32_DEBUGCTLMSR:
-		return vmcb->save.dbgctl;
-	case MSR_IA32_LASTBRANCHFROMIP:
-		return vmcb->save.br_from;
-	case MSR_IA32_LASTBRANCHTOIP:
-		return vmcb->save.br_to;
-	case MSR_IA32_LASTINTFROMIP:
-		return vmcb->save.last_excp_from;
-	case MSR_IA32_LASTINTTOIP:
-		return vmcb->save.last_excp_to;
-	default:
-		KVM_BUG(false, svm->vcpu.kvm,
-			"%s: Unknown MSR 0x%x", __func__, index);
-		return 0;
-	}
+	return svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK ? svm->vmcb :
+								   svm->vmcb01.ptr;
 }
 
 void svm_update_lbrv(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	bool enable_lbrv = svm_get_lbr_msr(svm, MSR_IA32_DEBUGCTLMSR) &
-					   DEBUGCTLMSR_LBR;
+	bool enable_lbrv = svm_get_lbr_vmcb(svm)->save.dbgctl & DEBUGCTLMSR_LBR;
 
 	bool current_enable_lbrv = !!(svm->vmcb->control.virt_ext &
 				      LBR_CTL_ENABLE_MASK);
@@ -2835,11 +2814,19 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		msr_info->data = svm->tsc_aux;
 		break;
 	case MSR_IA32_DEBUGCTLMSR:
+		msr_info->data = svm_get_lbr_vmcb(svm)->save.dbgctl;
+		break;
 	case MSR_IA32_LASTBRANCHFROMIP:
+		msr_info->data = svm_get_lbr_vmcb(svm)->save.br_from;
+		break;
 	case MSR_IA32_LASTBRANCHTOIP:
+		msr_info->data = svm_get_lbr_vmcb(svm)->save.br_to;
+		break;
 	case MSR_IA32_LASTINTFROMIP:
+		msr_info->data = svm_get_lbr_vmcb(svm)->save.last_excp_from;
+		break;
 	case MSR_IA32_LASTINTTOIP:
-		msr_info->data = svm_get_lbr_msr(svm, msr_info->index);
+		msr_info->data = svm_get_lbr_vmcb(svm)->save.last_excp_to;
 		break;
 	case MSR_VM_HSAVE_PA:
 		msr_info->data = svm->nested.hsave_msr;

From 41dfb5f13ed9101b217e7085e5b5fb07d705e27f Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 7 Jun 2023 13:35:18 -0700
Subject: [PATCH 0270/1189] KVM: SVM: Clean up handling of LBR virtualization
 enabled

Clean up the enable_lbrv computation in svm_update_lbrv() to consolidate
the logic for computing enable_lbrv into a single statement, and to remove
the coding style violations (lack of curly braces on nested if).

No functional change intended.

Link: https://lore.kernel.org/r/20230607203519.1570167-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.c | 13 ++++---------
 1 file changed, 4 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 623916221ff7..6fa918b588d2 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -994,15 +994,10 @@ static struct vmcb *svm_get_lbr_vmcb(struct vcpu_svm *svm)
 void svm_update_lbrv(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-
-	bool enable_lbrv = svm_get_lbr_vmcb(svm)->save.dbgctl & DEBUGCTLMSR_LBR;
-
-	bool current_enable_lbrv = !!(svm->vmcb->control.virt_ext &
-				      LBR_CTL_ENABLE_MASK);
-
-	if (unlikely(is_guest_mode(vcpu) && svm->lbrv_enabled))
-		if (unlikely(svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))
-			enable_lbrv = true;
+	bool current_enable_lbrv = svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK;
+	bool enable_lbrv = (svm_get_lbr_vmcb(svm)->save.dbgctl & DEBUGCTLMSR_LBR) ||
+			   (is_guest_mode(vcpu) && svm->lbrv_enabled &&
+			    (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK));
 
 	if (enable_lbrv == current_enable_lbrv)
 		return;

From a85cd52d720588b0060a0ebac5c7f497ad6bcd86 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 7 Jun 2023 13:35:19 -0700
Subject: [PATCH 0271/1189] KVM: SVM: Use svm_get_lbr_vmcb() helper to handle
 writes to DEBUGCTL

Use the recently introduced svm_get_lbr_vmcb() instead an open coded
equivalent to retrieve the target VMCB when emulating writes to
MSR_IA32_DEBUGCTLMSR.

No functional change intended.

Link: https://lore.kernel.org/r/20230607203519.1570167-4-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 6fa918b588d2..d76c8a0764f1 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3052,13 +3052,8 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		if (data & DEBUGCTL_RESERVED_BITS)
 			return 1;
 
-		if (svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK)
-			svm->vmcb->save.dbgctl = data;
-		else
-			svm->vmcb01.ptr->save.dbgctl = data;
-
+		svm_get_lbr_vmcb(svm)->save.dbgctl = data;
 		svm_update_lbrv(vcpu);
-
 		break;
 	case MSR_VM_HSAVE_PA:
 		/*

From 0033fa35491680bce65ff78fb41445f472aa5baa Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 6 Jun 2023 18:02:03 -0700
Subject: [PATCH 0272/1189] KVM: x86/pmu: Use enums instead of hardcoded magic
 for arch event indices

Add "enum intel_pmu_architectural_events" to replace the magic numbers for
the (pseudo-)architectural events, and to give a meaningful name to each
event so that new readers don't need psychic powers to understand what the
code is doing.

Cc: Aaron Lewis <aaronlewis@google.com>
Cc: Like Xu <like.xu.linux@gmail.com>
Reviewed-by: Like Xu <likexu@tencent.com>
Link: https://lore.kernel.org/r/20230607010206.1425277-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/vmx/pmu_intel.c | 55 ++++++++++++++++++++++++++++--------
 1 file changed, 43 insertions(+), 12 deletions(-)

diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 80c769c58a87..1109cbdedcae 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -22,23 +22,51 @@
 
 #define MSR_PMC_FULL_WIDTH_BIT      (MSR_IA32_PMC0 - MSR_IA32_PERFCTR0)
 
+enum intel_pmu_architectural_events {
+	/*
+	 * The order of the architectural events matters as support for each
+	 * event is enumerated via CPUID using the index of the event.
+	 */
+	INTEL_ARCH_CPU_CYCLES,
+	INTEL_ARCH_INSTRUCTIONS_RETIRED,
+	INTEL_ARCH_REFERENCE_CYCLES,
+	INTEL_ARCH_LLC_REFERENCES,
+	INTEL_ARCH_LLC_MISSES,
+	INTEL_ARCH_BRANCHES_RETIRED,
+	INTEL_ARCH_BRANCHES_MISPREDICTED,
+
+	NR_REAL_INTEL_ARCH_EVENTS,
+
+	/*
+	 * Pseudo-architectural event used to implement IA32_FIXED_CTR2, a.k.a.
+	 * TSC reference cycles.  The architectural reference cycles event may
+	 * or may not actually use the TSC as the reference, e.g. might use the
+	 * core crystal clock or the bus clock (yeah, "architectural").
+	 */
+	PSEUDO_ARCH_REFERENCE_CYCLES = NR_REAL_INTEL_ARCH_EVENTS,
+	NR_INTEL_ARCH_EVENTS,
+};
+
 static struct {
 	u8 eventsel;
 	u8 unit_mask;
 } const intel_arch_events[] = {
-	[0] = { 0x3c, 0x00 },
-	[1] = { 0xc0, 0x00 },
-	[2] = { 0x3c, 0x01 },
-	[3] = { 0x2e, 0x4f },
-	[4] = { 0x2e, 0x41 },
-	[5] = { 0xc4, 0x00 },
-	[6] = { 0xc5, 0x00 },
-	/* The above index must match CPUID 0x0A.EBX bit vector */
-	[7] = { 0x00, 0x03 },
+	[INTEL_ARCH_CPU_CYCLES]			= { 0x3c, 0x00 },
+	[INTEL_ARCH_INSTRUCTIONS_RETIRED]	= { 0xc0, 0x00 },
+	[INTEL_ARCH_REFERENCE_CYCLES]		= { 0x3c, 0x01 },
+	[INTEL_ARCH_LLC_REFERENCES]		= { 0x2e, 0x4f },
+	[INTEL_ARCH_LLC_MISSES]			= { 0x2e, 0x41 },
+	[INTEL_ARCH_BRANCHES_RETIRED]		= { 0xc4, 0x00 },
+	[INTEL_ARCH_BRANCHES_MISPREDICTED]	= { 0xc5, 0x00 },
+	[PSEUDO_ARCH_REFERENCE_CYCLES]		= { 0x00, 0x03 },
 };
 
 /* mapping between fixed pmc index and intel_arch_events array */
-static int fixed_pmc_events[] = {1, 0, 7};
+static int fixed_pmc_events[] = {
+	[0] = INTEL_ARCH_INSTRUCTIONS_RETIRED,
+	[1] = INTEL_ARCH_CPU_CYCLES,
+	[2] = PSEUDO_ARCH_REFERENCE_CYCLES,
+};
 
 static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data)
 {
@@ -80,13 +108,16 @@ static bool intel_hw_event_available(struct kvm_pmc *pmc)
 	u8 unit_mask = (pmc->eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8;
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(intel_arch_events); i++) {
+	BUILD_BUG_ON(ARRAY_SIZE(intel_arch_events) != NR_INTEL_ARCH_EVENTS);
+
+	for (i = 0; i < NR_INTEL_ARCH_EVENTS; i++) {
 		if (intel_arch_events[i].eventsel != event_select ||
 		    intel_arch_events[i].unit_mask != unit_mask)
 			continue;
 
 		/* disable event that reported as not present by cpuid */
-		if ((i < 7) && !(pmu->available_event_types & (1 << i)))
+		if ((i < PSEUDO_ARCH_REFERENCE_CYCLES) &&
+		    !(pmu->available_event_types & (1 << i)))
 			return false;
 
 		break;

From bc9658999b3e44cbad964fe9fbab5a25bd4f5ed3 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 6 Jun 2023 18:02:04 -0700
Subject: [PATCH 0273/1189] KVM: x86/pmu: Simplify intel_hw_event_available()

Walk only the "real", i.e. non-pseudo, architectural events when checking
if a hardware event is available, i.e. isn't disabled by guest CPUID.
Skipping pseudo-arch events in the loop body is unnecessarily convoluted,
especially now that KVM has enums that delineate between real and pseudo
events.

Link: https://lore.kernel.org/r/20230607010206.1425277-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/vmx/pmu_intel.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 1109cbdedcae..db23697f3141 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -110,17 +110,16 @@ static bool intel_hw_event_available(struct kvm_pmc *pmc)
 
 	BUILD_BUG_ON(ARRAY_SIZE(intel_arch_events) != NR_INTEL_ARCH_EVENTS);
 
-	for (i = 0; i < NR_INTEL_ARCH_EVENTS; i++) {
+	/*
+	 * Disallow events reported as unavailable in guest CPUID.  Note, this
+	 * doesn't apply to pseudo-architectural events.
+	 */
+	for (i = 0; i < NR_REAL_INTEL_ARCH_EVENTS; i++) {
 		if (intel_arch_events[i].eventsel != event_select ||
 		    intel_arch_events[i].unit_mask != unit_mask)
 			continue;
 
-		/* disable event that reported as not present by cpuid */
-		if ((i < PSEUDO_ARCH_REFERENCE_CYCLES) &&
-		    !(pmu->available_event_types & (1 << i)))
-			return false;
-
-		break;
+		return pmu->available_event_types & BIT(i);
 	}
 
 	return true;

From 6d88d0ee5de142921598e5c0041792bbd860913d Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 6 Jun 2023 18:02:05 -0700
Subject: [PATCH 0274/1189] KVM: x86/pmu: Require nr fixed_pmc_events to match
 nr max fixed counters

Assert that the number of known fixed_pmc_events matches the max number of
fixed counters supported by KVM, and clean up related code.

Opportunistically extend setup_fixed_pmc_eventsel()'s use of
array_index_nospec() to cover fixed_counters, as nr_arch_fixed_counters is
set based on userspace input (but capped using KVM-controlled values).

Link: https://lore.kernel.org/r/20230607010206.1425277-4-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/vmx/pmu_intel.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index db23697f3141..f2efa0bf7ae8 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -468,16 +468,17 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 
 static void setup_fixed_pmc_eventsel(struct kvm_pmu *pmu)
 {
-	size_t size = ARRAY_SIZE(fixed_pmc_events);
-	struct kvm_pmc *pmc;
-	u32 event;
 	int i;
 
+	BUILD_BUG_ON(ARRAY_SIZE(fixed_pmc_events) != KVM_PMC_MAX_FIXED);
+
 	for (i = 0; i < pmu->nr_arch_fixed_counters; i++) {
-		pmc = &pmu->fixed_counters[i];
-		event = fixed_pmc_events[array_index_nospec(i, size)];
+		int index = array_index_nospec(i, KVM_PMC_MAX_FIXED);
+		struct kvm_pmc *pmc = &pmu->fixed_counters[index];
+		u32 event = fixed_pmc_events[index];
+
 		pmc->eventsel = (intel_arch_events[event].unit_mask << 8) |
-			intel_arch_events[event].eventsel;
+				 intel_arch_events[event].eventsel;
 	}
 }
 
@@ -538,10 +539,8 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 	if (pmu->version == 1) {
 		pmu->nr_arch_fixed_counters = 0;
 	} else {
-		pmu->nr_arch_fixed_counters =
-			min3(ARRAY_SIZE(fixed_pmc_events),
-			     (size_t) edx.split.num_counters_fixed,
-			     (size_t)kvm_pmu_cap.num_counters_fixed);
+		pmu->nr_arch_fixed_counters = min_t(int, edx.split.num_counters_fixed,
+						    kvm_pmu_cap.num_counters_fixed);
 		edx.split.bit_width_fixed = min_t(int, edx.split.bit_width_fixed,
 						  kvm_pmu_cap.bit_width_fixed);
 		pmu->counter_bitmask[KVM_PMC_FIXED] =

From 6de2ccc169683bf81feba163834dae7cdebdd826 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 6 Jun 2023 18:02:06 -0700
Subject: [PATCH 0275/1189] KVM: x86/pmu: Move .hw_event_available() check out
 of PMC filter helper

Move the call to kvm_x86_pmu.hw_event_available(), which has nothing to
with the userspace PMU filter, out of check_pmu_event_filter() and into
its sole caller pmc_event_is_allowed().  pmc_event_is_allowed() didn't
exist when commit 7aadaa988c5e ("KVM: x86/pmu: Drop amd_event_mapping[]
in the KVM context"), so presumably the motivation for invoking
.hw_event_available() from check_pmu_event_filter() was to avoid having
to add multiple call sites.

Link: https://lore.kernel.org/r/20230607010206.1425277-5-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/pmu.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index bf653df86112..edb89b51b383 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -382,9 +382,6 @@ static bool check_pmu_event_filter(struct kvm_pmc *pmc)
 	struct kvm_x86_pmu_event_filter *filter;
 	struct kvm *kvm = pmc->vcpu->kvm;
 
-	if (!static_call(kvm_x86_pmu_hw_event_available)(pmc))
-		return false;
-
 	filter = srcu_dereference(kvm->arch.pmu_event_filter, &kvm->srcu);
 	if (!filter)
 		return true;
@@ -398,6 +395,7 @@ static bool check_pmu_event_filter(struct kvm_pmc *pmc)
 static bool pmc_event_is_allowed(struct kvm_pmc *pmc)
 {
 	return pmc_is_globally_enabled(pmc) && pmc_speculative_in_use(pmc) &&
+	       static_call(kvm_x86_pmu_hw_event_available)(pmc) &&
 	       check_pmu_event_filter(pmc);
 }
 

From 41e90a69a49be2e3467e811ae8fdc17456af1b02 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 2 Jun 2023 16:32:49 -0700
Subject: [PATCH 0276/1189] KVM: x86: Retry APIC optimized map recalc if vCPU
 is added/enabled

Retry the optimized APIC map recalculation if an APIC-enabled vCPU shows
up between allocating the map and filling in the map data.  Conditionally
reschedule before retrying even though the number of vCPUs that can be
created is bounded by KVM.  Retrying a few thousand times isn't so slow
as to be hugely problematic, but it's not blazing fast either.

Reset xapic_id_mistach on each retry as a vCPU could change its xAPIC ID
between loops, but do NOT reset max_id.  The map size also factors in
whether or not a vCPU's local APIC is hardware-enabled, i.e. userspace
and/or the guest can theoretically keep KVM retrying indefinitely.  The
only downside is that KVM will allocate more memory than is strictly
necessary if the vCPU with the highest x2APIC ID disabled its APIC while
the recalculation was in-progress.

Refresh kvm->arch.apic_map_dirty to opportunistically change it from
DIRTY => UPDATE_IN_PROGRESS to avoid an unnecessary recalc from a
different task, i.e. if another task is waiting to attempt an update
(which is likely since a retry happens if and only if an update is
required).

Link: https://lore.kernel.org/r/20230602233250.1014316-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/lapic.c | 29 +++++++++++++++++++++++++----
 1 file changed, 25 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 113ca9661ab2..673880bc0762 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -376,7 +376,8 @@ void kvm_recalculate_apic_map(struct kvm *kvm)
 	struct kvm_vcpu *vcpu;
 	unsigned long i;
 	u32 max_id = 255; /* enough space for any xAPIC ID */
-	bool xapic_id_mismatch = false;
+	bool xapic_id_mismatch;
+	int r;
 
 	/* Read kvm->arch.apic_map_dirty before kvm->arch.apic_map.  */
 	if (atomic_read_acquire(&kvm->arch.apic_map_dirty) == CLEAN)
@@ -386,9 +387,14 @@ void kvm_recalculate_apic_map(struct kvm *kvm)
 		  "Dirty APIC map without an in-kernel local APIC");
 
 	mutex_lock(&kvm->arch.apic_map_lock);
+
+retry:
 	/*
-	 * Read kvm->arch.apic_map_dirty before kvm->arch.apic_map
-	 * (if clean) or the APIC registers (if dirty).
+	 * Read kvm->arch.apic_map_dirty before kvm->arch.apic_map (if clean)
+	 * or the APIC registers (if dirty).  Note, on retry the map may have
+	 * not yet been marked dirty by whatever task changed a vCPU's x2APIC
+	 * ID, i.e. the map may still show up as in-progress.  In that case
+	 * this task still needs to retry and complete its calculation.
 	 */
 	if (atomic_cmpxchg_acquire(&kvm->arch.apic_map_dirty,
 				   DIRTY, UPDATE_IN_PROGRESS) == CLEAN) {
@@ -397,6 +403,15 @@ void kvm_recalculate_apic_map(struct kvm *kvm)
 		return;
 	}
 
+	/*
+	 * Reset the mismatch flag between attempts so that KVM does the right
+	 * thing if a vCPU changes its xAPIC ID, but do NOT reset max_id, i.e.
+	 * keep max_id strictly increasing.  Disallowing max_id from shrinking
+	 * ensures KVM won't get stuck in an infinite loop, e.g. if the vCPU
+	 * with the highest x2APIC ID is toggling its APIC on and off.
+	 */
+	xapic_id_mismatch = false;
+
 	kvm_for_each_vcpu(i, vcpu, kvm)
 		if (kvm_apic_present(vcpu))
 			max_id = max(max_id, kvm_x2apic_id(vcpu->arch.apic));
@@ -415,9 +430,15 @@ void kvm_recalculate_apic_map(struct kvm *kvm)
 		if (!kvm_apic_present(vcpu))
 			continue;
 
-		if (kvm_recalculate_phys_map(new, vcpu, &xapic_id_mismatch)) {
+		r = kvm_recalculate_phys_map(new, vcpu, &xapic_id_mismatch);
+		if (r) {
 			kvfree(new);
 			new = NULL;
+			if (r == -E2BIG) {
+				cond_resched();
+				goto retry;
+			}
+
 			goto out;
 		}
 

From a9b451509565d40a5ca3b41c39a2b758cdbc5355 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 31 Jul 2023 16:19:21 -0300
Subject: [PATCH 0277/1189] tools build: Add 3-component logical version
 comparators

The next cset needs to compare if a flex version is greater or
equal/less than another, but since there is no canonical, generally
available way to compare versions in the command line (sort -V, yeah,
but...), just use awk to canonicalize the versions like is also done in
scripts/rust_is_available.sh.

There was a problem spotted in linux-next where a bashism, here
documents, aka the '<<<' stdin redirector, for strings to be used as the
stdin for awk. Use $(shell echo | awk ...) instead.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/scripts/utilities.mak | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/tools/scripts/utilities.mak b/tools/scripts/utilities.mak
index 172e47273b5d..d69d0345cc23 100644
--- a/tools/scripts/utilities.mak
+++ b/tools/scripts/utilities.mak
@@ -177,3 +177,23 @@ $(if $($(1)),$(call _ge_attempt,$($(1)),$(1)),$(call _ge_attempt,$(2)))
 endef
 _ge_attempt = $(or $(get-executable),$(call _gea_err,$(2)))
 _gea_err  = $(if $(1),$(error Please set '$(1)' appropriately))
+
+# version-ge3
+#
+# Usage $(call version-ge3,2.6.4,$(FLEX_VERSION))
+#
+# To compare if a 3 component version is greater or equal to another, first use
+# was to check the flex version to see if we can use compiler warnings as
+# errors for one of the cases flex generates code C compilers complains about.
+
+version-ge3 = $(shell echo "$(1).$(2)" | awk -F'.' '{ printf("%d\n", (10000000 * $$1 + 10000 * $$2 + $$3) >= (10000000 * $$4 + 10000 * $$5 + $$6)) }')
+
+# version-lt3
+#
+# Usage $(call version-lt3,2.6.2,$(FLEX_VERSION))
+#
+# To compare if a 3 component version is less thjan another, first use was to
+# check the flex version to see if we can use compiler warnings as errors for
+# one of the cases flex generates code C compilers complains about.
+
+version-lt3 = $(shell echo "$(1).$(2)" | awk -F'.' '{ printf("%d\n", (10000000 * $$1 + 10000 * $$2 + $$3) < (10000000 * $$4 + 10000 * $$5 + $$6)) }')

From 10c775afa5992d55be76fa40a6373a93751ba6b4 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 27 Jul 2023 23:49:15 -0700
Subject: [PATCH 0278/1189] perf build: Disable fewer flex warnings

If flex is version 2.6.4, reduce the number of flex C warnings
disabled. Earlier flex versions have all C warnings disabled.

Committer notes:

Added this to the list of ignored warnings to get it building on
a Fedora 36 machine with flex 2.6.4:

  -Wno-misleading-indentation

Noticed when building with:

  $ make LLVM=1 -C tools/perf NO_BPF_SKEL=1 DEBUG=1

Take two:

We can't just try to canonicalize flex versions by just removing the
dots, as we end up with:

	2.6.4 >= 2.5.37

becoming:

	264 >= 2537

Failing the build on flex 2.5.37, so instead use the back to the past
added $(call version_ge3,$(FLEX_VERSION),2.6.4) variant to check for
that.

Making sure $(FLEX_VERSION) keeps the dots as we may want to use 'sort
-V' or something nicer when available everywhere.

Some other tweaks for other flex versions and combinations with gcc and
clang versions were added, notes on the patch.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rob Herring <robh@kernel.org>
Cc: Tom Rix <trix@redhat.com>
Cc: bpf@vger.kernel.org
Cc: llvm@lists.linux.dev
Link: https://lore.kernel.org/r/20230728064917.767761-5-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/Build | 24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index bb08149179e4..15c69decb76b 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -1,3 +1,5 @@
+include $(srctree)/tools/scripts/utilities.mak
+
 perf-y += arm64-frame-pointer-unwind-support.o
 perf-y += addr_location.o
 perf-y += annotate.o
@@ -279,16 +281,26 @@ $(OUTPUT)util/bpf-filter-bison.c $(OUTPUT)util/bpf-filter-bison.h: util/bpf-filt
 	$(Q)$(call echo-cmd,bison)$(BISON) -v $< -d $(PARSER_DEBUG_BISON) $(BISON_FILE_PREFIX_MAP) \
 		-o $(OUTPUT)util/bpf-filter-bison.c -p perf_bpf_filter_
 
-FLEX_GE_26 := $(shell expr $(shell $(FLEX) --version | sed -e  's/flex \([0-9]\+\).\([0-9]\+\)/\1\2/g') \>\= 26)
-ifeq ($(FLEX_GE_26),1)
-  flex_flags := -Wno-switch-enum -Wno-switch-default -Wno-unused-function -Wno-redundant-decls -Wno-sign-compare -Wno-unused-parameter -Wno-missing-prototypes -Wno-missing-declarations
-  CC_HASNT_MISLEADING_INDENTATION := $(shell echo "int main(void) { return 0 }" | $(CC) -Werror -Wno-misleading-indentation -o /dev/null -xc - 2>&1 | grep -q -- -Wno-misleading-indentation ; echo $$?)
-  ifeq ($(CC_HASNT_MISLEADING_INDENTATION), 1)
-    flex_flags += -Wno-misleading-indentation
+FLEX_VERSION := $(shell $(FLEX) --version | cut -d' ' -f2)
+
+FLEX_GE_260 := $(call version-ge3,$(FLEX_VERSION),2.6.0)
+ifeq ($(FLEX_GE_260),1)
+  flex_flags := -Wno-redundant-decls -Wno-switch-default -Wno-unused-function -Wno-misleading-indentation
+
+  # Some newer clang and gcc version complain about this
+  # util/parse-events-bison.c:1317:9: error: variable 'parse_events_nerrs' set but not used [-Werror,-Wunused-but-set-variable]
+  #  int yynerrs = 0;
+
+  flex_flags += -Wno-unused-but-set-variable
+
+  FLEX_LT_262 := $(call version-lt3,$(FLEX_VERSION),2.6.2)
+  ifeq ($(FLEX_LT_262),1)
+    flex_flags += -Wno-sign-compare
   endif
 else
   flex_flags := -w
 endif
+
 CFLAGS_parse-events-flex.o  += $(flex_flags)
 CFLAGS_pmu-flex.o           += $(flex_flags)
 CFLAGS_expr-flex.o          += $(flex_flags)

From ddc8e4c966923ad1137790817157c8a5f0301aec Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 27 Jul 2023 23:49:16 -0700
Subject: [PATCH 0279/1189] perf build: Disable fewer bison warnings

If bison is version 3.8.2, reduce the number of bison C warnings
disabled. Earlier bison versions have all C warnings disabled. Avoid
implicit declarations of yylex by adding the declaration in the C
file. A header can't be included as a circular dependency would occur
due to the lexer using the bison defined tokens.

Committer notes:

Some recent versions of gcc and clang (noticed on Alpine Linux 3.17,
edge, clearlinux, fedora 37, etc.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rob Herring <robh@kernel.org>
Cc: Tom Rix <trix@redhat.com>
Cc: bpf@vger.kernel.org
Cc: llvm@lists.linux.dev
Link: https://lore.kernel.org/r/20230728064917.767761-6-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/Build          | 12 ++++++++----
 tools/perf/util/bpf-filter.y   |  2 ++
 tools/perf/util/expr.y         |  4 +++-
 tools/perf/util/parse-events.y |  1 +
 tools/perf/util/pmu.y          |  3 +++
 5 files changed, 17 insertions(+), 5 deletions(-)

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 15c69decb76b..1acfbbd1f39a 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -306,10 +306,14 @@ CFLAGS_pmu-flex.o           += $(flex_flags)
 CFLAGS_expr-flex.o          += $(flex_flags)
 CFLAGS_bpf-filter-flex.o    += $(flex_flags)
 
-bison_flags := -DYYENABLE_NLS=0
-BISON_GE_35 := $(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\)/\1\2/g') \>\= 35)
-ifeq ($(BISON_GE_35),1)
-  bison_flags += -Wno-unused-parameter -Wno-nested-externs -Wno-implicit-function-declaration -Wno-switch-enum -Wno-unused-but-set-variable -Wno-unknown-warning-option
+# Some newer clang and gcc version complain about this
+# util/parse-events-bison.c:1317:9: error: variable 'parse_events_nerrs' set but not used [-Werror,-Wunused-but-set-variable]
+#  int yynerrs = 0;
+
+bison_flags := -DYYENABLE_NLS=0 -Wno-unused-but-set-variable
+BISON_GE_382 := $(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\).\([0-9]\+\)/\1\2\3/g') \>\= 382)
+ifeq ($(BISON_GE_382),1)
+  bison_flags += -Wno-switch-enum
 else
   bison_flags += -w
 endif
diff --git a/tools/perf/util/bpf-filter.y b/tools/perf/util/bpf-filter.y
index 07d6c7926c13..5dfa948fc986 100644
--- a/tools/perf/util/bpf-filter.y
+++ b/tools/perf/util/bpf-filter.y
@@ -9,6 +9,8 @@
 #include <linux/list.h>
 #include "bpf-filter.h"
 
+int perf_bpf_filter_lex(void);
+
 static void perf_bpf_filter_error(struct list_head *expr __maybe_unused,
 				  char const *msg)
 {
diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y
index dd504afd8f36..65d54a6f29ad 100644
--- a/tools/perf/util/expr.y
+++ b/tools/perf/util/expr.y
@@ -7,6 +7,8 @@
 #include "util/debug.h"
 #define IN_EXPR_Y 1
 #include "expr.h"
+#include "expr-bison.h"
+int expr_lex(YYSTYPE * yylval_param , void *yyscanner);
 %}
 
 %define api.pure full
@@ -56,7 +58,7 @@
 static void expr_error(double *final_val __maybe_unused,
 		       struct expr_parse_ctx *ctx __maybe_unused,
 		       bool compute_ids __maybe_unused,
-		       void *scanner,
+		       void *scanner __maybe_unused,
 		       const char *s)
 {
 	pr_debug("%s\n", s);
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 454577f7aff6..251b7d2fde32 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -20,6 +20,7 @@
 #include "parse-events.h"
 #include "parse-events-bison.h"
 
+int parse_events_lex(YYSTYPE * yylval_param, YYLTYPE * yylloc_param , void *yyscanner);
 void parse_events_error(YYLTYPE *loc, void *parse_state, void *scanner, char const *msg);
 
 #define PE_ABORT(val) \
diff --git a/tools/perf/util/pmu.y b/tools/perf/util/pmu.y
index dff4e892ac4d..3d46cca3bb94 100644
--- a/tools/perf/util/pmu.y
+++ b/tools/perf/util/pmu.y
@@ -11,6 +11,9 @@
 #include <linux/bitmap.h>
 #include <string.h>
 #include "pmu.h"
+#include "pmu-bison.h"
+
+int perf_pmu_lex(YYSTYPE * yylval_param , void *yyscanner);
 
 #define ABORT_ON(val) \
 do { \

From f776b0435e8cf6e73359d4203c2bc7bf2cf4b2af Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 27 Jul 2023 23:49:17 -0700
Subject: [PATCH 0280/1189] perf build: Remove -Wno-redundant-decls in 2 cases

Properly fix a warning and remove the -Wno-redundant-decls C flag.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rob Herring <robh@kernel.org>
Cc: Tom Rix <trix@redhat.com>
Cc: bpf@vger.kernel.org
Cc: llvm@lists.linux.dev
Link: https://lore.kernel.org/r/20230728064917.767761-7-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/Build          | 2 --
 tools/perf/util/parse-events.c | 1 -
 2 files changed, 3 deletions(-)

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 1acfbbd1f39a..d487aec0b458 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -338,8 +338,6 @@ CFLAGS_find_bit.o      += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ET
 CFLAGS_rbtree.o        += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_libstring.o     += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_hweight.o       += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
-CFLAGS_parse-events.o  += -Wno-redundant-decls
-CFLAGS_expr.o          += -Wno-redundant-decls
 CFLAGS_header.o        += -include $(OUTPUT)PERF-VERSION-FILE
 CFLAGS_arm-spe.o       += -I$(srctree)/tools/arch/arm64/include/
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 926d3ac97324..ac315e1be2bc 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -35,7 +35,6 @@
 #ifdef PARSER_DEBUG
 extern int parse_events_debug;
 #endif
-int parse_events_parse(void *parse_state, void *scanner);
 static int get_config_terms(struct list_head *head_config,
 			    struct list_head *head_terms __maybe_unused);
 

From 7822a8913f4c51c7d1aff793b525d60c3384fb5b Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 27 Jul 2023 19:24:46 -0700
Subject: [PATCH 0281/1189] perf build: Update build rule for generated files

The bison and flex generate C files from the source (.y and .l)
files.  When O= option is used, they are saved in a separate directory
but the default build rule assumes the .C files are in the source
directory.  So it might read invalid file if there are generated files
from an old version.  The same is true for the pmu-events files.

For example, the following command would cause a build failure:

  $ git checkout v6.3
  $ make -C tools/perf  # build in the same directory

  $ git checkout v6.5-rc2
  $ mkdir build  # create a build directory
  $ make -C tools/perf O=build  # build in a different directory but it
                                # refers files in the source directory

Let's update the build rule to specify those cases explicitly to depend
on the files in the output directory.

Note that it's not a complete fix and it needs the next patch for the
include path too.

Fixes: 80eeb67fe577aa76 ("perf jevents: Program to convert JSON file")
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Anup Sharma <anupnewsmail@gmail.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230728022447.1323563-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/build/Makefile.build  | 10 ++++++++++
 tools/perf/pmu-events/Build |  6 ++++++
 2 files changed, 16 insertions(+)

diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build
index 89430338a3d9..fac42486a8cf 100644
--- a/tools/build/Makefile.build
+++ b/tools/build/Makefile.build
@@ -117,6 +117,16 @@ $(OUTPUT)%.s: %.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_s_c)
 
+# bison and flex files are generated in the OUTPUT directory
+# so it needs a separate rule to depend on them properly
+$(OUTPUT)%-bison.o: $(OUTPUT)%-bison.c FORCE
+	$(call rule_mkdir)
+	$(call if_changed_dep,$(host)cc_o_c)
+
+$(OUTPUT)%-flex.o: $(OUTPUT)%-flex.c FORCE
+	$(call rule_mkdir)
+	$(call if_changed_dep,$(host)cc_o_c)
+
 # Gather build data:
 #   obj-y        - list of build objects
 #   subdir-y     - list of directories to nest
diff --git a/tools/perf/pmu-events/Build b/tools/perf/pmu-events/Build
index 150765f2baee..1d18bb89402e 100644
--- a/tools/perf/pmu-events/Build
+++ b/tools/perf/pmu-events/Build
@@ -35,3 +35,9 @@ $(PMU_EVENTS_C): $(JSON) $(JSON_TEST) $(JEVENTS_PY) $(METRIC_PY) $(METRIC_TEST_L
 	$(call rule_mkdir)
 	$(Q)$(call echo-cmd,gen)$(PYTHON) $(JEVENTS_PY) $(JEVENTS_ARCH) $(JEVENTS_MODEL) pmu-events/arch $@
 endif
+
+# pmu-events.c file is generated in the OUTPUT directory so it needs a
+# separate rule to depend on it properly
+$(OUTPUT)pmu-events/pmu-events.o: $(PMU_EVENTS_C)
+	$(call rule_mkdir)
+	$(call if_changed_dep,cc_o_c)

From c7e97f215a4ad634b746804679f5937d25f77e29 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 27 Jul 2023 19:24:47 -0700
Subject: [PATCH 0282/1189] perf build: Include generated header files properly

The flex and bison generate header files from the source.  When user
specified a build directory with O= option, it'd generate files under
the directory.  The build command has -I option to specify the header
include directory.

But the -I option only affects the files included like <...>.  Let's
change the flex and bison headers to use it instead of "...".

Fixes: 80eeb67fe577aa76 ("perf jevents: Program to convert JSON file")
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Anup Sharma <anupnewsmail@gmail.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230728022447.1323563-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/jevents.py | 2 +-
 tools/perf/util/bpf-filter.c     | 4 ++--
 tools/perf/util/expr.c           | 4 ++--
 tools/perf/util/parse-events.c   | 4 ++--
 tools/perf/util/pmu.c            | 4 ++--
 5 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index 08ec9aa583e7..8cd561aa606a 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -1000,7 +1000,7 @@ such as "arm/cortex-a34".''',
   _args = ap.parse_args()
 
   _args.output_file.write("""
-#include "pmu-events/pmu-events.h"
+#include <pmu-events/pmu-events.h>
 #include "util/header.h"
 #include "util/pmu.h"
 #include <string.h>
diff --git a/tools/perf/util/bpf-filter.c b/tools/perf/util/bpf-filter.c
index 0b30688d78a7..47f01df658d9 100644
--- a/tools/perf/util/bpf-filter.c
+++ b/tools/perf/util/bpf-filter.c
@@ -9,8 +9,8 @@
 #include "util/evsel.h"
 
 #include "util/bpf-filter.h"
-#include "util/bpf-filter-flex.h"
-#include "util/bpf-filter-bison.h"
+#include <util/bpf-filter-flex.h>
+#include <util/bpf-filter-bison.h>
 
 #include "bpf_skel/sample-filter.h"
 #include "bpf_skel/sample_filter.skel.h"
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index 4814262e3805..7410a165f68b 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -10,8 +10,8 @@
 #include "debug.h"
 #include "evlist.h"
 #include "expr.h"
-#include "expr-bison.h"
-#include "expr-flex.h"
+#include <util/expr-bison.h>
+#include <util/expr-flex.h>
 #include "util/hashmap.h"
 #include "smt.h"
 #include "tsc.h"
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index ac315e1be2bc..acddb2542b1a 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -18,8 +18,8 @@
 #include "debug.h"
 #include <api/fs/tracing_path.h>
 #include <perf/cpumap.h>
-#include "parse-events-bison.h"
-#include "parse-events-flex.h"
+#include <util/parse-events-bison.h>
+#include <util/parse-events-flex.h>
 #include "pmu.h"
 #include "pmus.h"
 #include "asm/bug.h"
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 7f984a7f16ca..b6654b9f55d2 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -19,8 +19,8 @@
 #include "evsel.h"
 #include "pmu.h"
 #include "pmus.h"
-#include "pmu-bison.h"
-#include "pmu-flex.h"
+#include <util/pmu-bison.h>
+#include <util/pmu-flex.h>
 #include "parse-events.h"
 #include "print-events.h"
 #include "header.h"

From c76a1444c00ea6900a5e7d10065d6e93b0e104f9 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 27 Jul 2023 17:12:10 -0700
Subject: [PATCH 0283/1189] perf parse-event: Avoid BPF test SEGV

loc is passed as NULL in tools/perf/tests/bpf.c do_test, meaning
errors trigger a SEGV when trying to access. Add the missing NULL
check.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rob Herring <robh@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Wang ShaoBo <bobo.shaobowang@huawei.com>
Cc: YueHaibing <yuehaibing@huawei.com>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20230728001212.457900-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index acddb2542b1a..e17e96b4f798 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -757,7 +757,7 @@ int parse_events_load_bpf_obj(struct parse_events_state *parse_state,
 
 	return 0;
 errout:
-	parse_events_error__handle(parse_state->error, param.loc->first_column,
+	parse_events_error__handle(parse_state->error, param.loc ? param.loc->first_column : 0,
 				strdup(errbuf), strdup("(add -v to see detail)"));
 	return err;
 }

From 30f4ade33d649aa0e8603386721f184ad9d3cb55 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 27 Jul 2023 17:12:11 -0700
Subject: [PATCH 0284/1189] perf tools: Revert enable indices setting syntax
 for BPF map

This reverts commit e571e029bdbf ("perf tools: Enable indices setting
syntax for BPF map").

The reverted commit added a notion of arrays that could be set as
event terms for BPF events. The parsing hasn't worked over multiple
Linux releases. Given the broken nature of the parsing it appears the
code isn't in use, nor could I find a way for it to be used to add a
test.

The original commit contains a test in the commit message,
however, running it yields:
```
$ perf record -e './test_bpf_map_3.c/map:channel.value[0,1,2,3...5]=101/' usleep 2
event syntax error: '..pf_map_3.c/map:channel.value[0,1,2,3...5]=101/'
                                  \___ parser error
Run 'perf list' for a list of valid events

 Usage: perf record [<options>] [<command>]
    or: perf record [<options>] -- <command> [<options>]

    -e, --event <event>   event selector. use 'perf list' to list available events
```

Given the code can't be used this commit reverts and removes it.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rob Herring <robh@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Wang ShaoBo <bobo.shaobowang@huawei.com>
Cc: YueHaibing <yuehaibing@huawei.com>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20230728001212.457900-3-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.c |   8 +--
 tools/perf/util/parse-events.l |  11 ---
 tools/perf/util/parse-events.y | 122 ---------------------------------
 3 files changed, 1 insertion(+), 140 deletions(-)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index e17e96b4f798..37614dc1d698 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -799,13 +799,7 @@ parse_events_config_bpf(struct parse_events_state *parse_state,
 
 			parse_events_error__handle(parse_state->error, idx,
 						strdup(errbuf),
-						strdup(
-"Hint:\tValid config terms:\n"
-"     \tmap:[<arraymap>].value<indices>=[value]\n"
-"     \tmap:[<eventmap>].event<indices>=[event]\n"
-"\n"
-"     \twhere <indices> is something like [0,3...5] or [all]\n"
-"     \t(add -v to see detail)"));
+						NULL);
 			return err;
 		}
 	}
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 99335ec586ae..d7d084cc4140 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -175,7 +175,6 @@ do {							\
 %x mem
 %s config
 %x event
-%x array
 
 group		[^,{}/]*[{][^}]*[}][^,{}/]*
 event_pmu	[^,{}/]+[/][^/]*[/][^,{}/]*
@@ -251,14 +250,6 @@ non_digit	[^0-9]
 		}
 }
 
-<array>{
-"]"			{ BEGIN(config); return ']'; }
-{num_dec}		{ return value(yyscanner, 10); }
-{num_hex}		{ return value(yyscanner, 16); }
-,			{ return ','; }
-"\.\.\."		{ return PE_ARRAY_RANGE; }
-}
-
 <config>{
 	/*
 	 * Please update config_term_names when new static term is added.
@@ -302,8 +293,6 @@ r0x{num_raw_hex}	{ return str(yyscanner, PE_RAW); }
 {lc_type}-{lc_op_result}	{ return lc_str(yyscanner, _parse_state); }
 {lc_type}-{lc_op_result}-{lc_op_result}	{ return lc_str(yyscanner, _parse_state); }
 {name_minus}		{ return str(yyscanner, PE_NAME); }
-\[all\]			{ return PE_ARRAY_ALL; }
-"["			{ BEGIN(array); return '['; }
 @{drv_cfg_term}		{ return drv_str(yyscanner, PE_DRV_CFG_TERM); }
 }
 
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 251b7d2fde32..c3517e3498d7 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -65,7 +65,6 @@ static void free_list_evsel(struct list_head* list_evsel)
 %token PE_LEGACY_CACHE
 %token PE_PREFIX_MEM
 %token PE_ERROR
-%token PE_ARRAY_ALL PE_ARRAY_RANGE
 %token PE_DRV_CFG_TERM
 %token PE_TERM_HW
 %type <num> PE_VALUE
@@ -109,11 +108,6 @@ static void free_list_evsel(struct list_head* list_evsel)
 %type <list_evsel> groups
 %destructor { free_list_evsel ($$); } <list_evsel>
 %type <tracepoint_name> tracepoint_name
-%destructor { free ($$.sys); free ($$.event); } <tracepoint_name>
-%type <array> array
-%type <array> array_term
-%type <array> array_terms
-%destructor { free ($$.ranges); } <array>
 %type <hardware_term> PE_TERM_HW
 %destructor { free ($$.str); } <hardware_term>
 
@@ -128,7 +122,6 @@ static void free_list_evsel(struct list_head* list_evsel)
 		char *sys;
 		char *event;
 	} tracepoint_name;
-	struct parse_events_array array;
 	struct hardware_term {
 		char *str;
 		u64 num;
@@ -879,121 +872,6 @@ PE_TERM
 
 	$$ = term;
 }
-|
-name_or_raw array '=' name_or_legacy
-{
-	struct parse_events_term *term;
-	int err = parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER, $1, $4, &@1, &@4);
-
-	if (err) {
-		free($1);
-		free($4);
-		free($2.ranges);
-		PE_ABORT(err);
-	}
-	term->array = $2;
-	$$ = term;
-}
-|
-name_or_raw array '=' PE_VALUE
-{
-	struct parse_events_term *term;
-	int err = parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, $1, $4, false, &@1, &@4);
-
-	if (err) {
-		free($1);
-		free($2.ranges);
-		PE_ABORT(err);
-	}
-	term->array = $2;
-	$$ = term;
-}
-|
-PE_DRV_CFG_TERM
-{
-	struct parse_events_term *term;
-	char *config = strdup($1);
-	int err;
-
-	if (!config)
-		YYNOMEM;
-	err = parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_DRV_CFG, config, $1, &@1, NULL);
-	if (err) {
-		free($1);
-		free(config);
-		PE_ABORT(err);
-	}
-	$$ = term;
-}
-
-array:
-'[' array_terms ']'
-{
-	$$ = $2;
-}
-|
-PE_ARRAY_ALL
-{
-	$$.nr_ranges = 0;
-	$$.ranges = NULL;
-}
-
-array_terms:
-array_terms ',' array_term
-{
-	struct parse_events_array new_array;
-
-	new_array.nr_ranges = $1.nr_ranges + $3.nr_ranges;
-	new_array.ranges = realloc($1.ranges,
-				sizeof(new_array.ranges[0]) *
-				new_array.nr_ranges);
-	if (!new_array.ranges)
-		YYNOMEM;
-	memcpy(&new_array.ranges[$1.nr_ranges], $3.ranges,
-	       $3.nr_ranges * sizeof(new_array.ranges[0]));
-	free($3.ranges);
-	$$ = new_array;
-}
-|
-array_term
-
-array_term:
-PE_VALUE
-{
-	struct parse_events_array array;
-
-	array.nr_ranges = 1;
-	array.ranges = malloc(sizeof(array.ranges[0]));
-	if (!array.ranges)
-		YYNOMEM;
-	array.ranges[0].start = $1;
-	array.ranges[0].length = 1;
-	$$ = array;
-}
-|
-PE_VALUE PE_ARRAY_RANGE PE_VALUE
-{
-	struct parse_events_array array;
-
-	if ($3 < $1) {
-		struct parse_events_state *parse_state = _parse_state;
-		struct parse_events_error *error = parse_state->error;
-		char *err_str;
-
-		if (asprintf(&err_str, "Expected '%ld' to be less-than '%ld'", $3, $1) < 0)
-			err_str = NULL;
-
-		parse_events_error__handle(error, @1.first_column, err_str, NULL);
-		YYABORT;
-	}
-	array.nr_ranges = 1;
-	array.ranges = malloc(sizeof(array.ranges[0]));
-	if (!array.ranges)
-		YYNOMEM;
-	array.ranges[0].start = $1;
-	array.ranges[0].length = $3 - $1 + 1;
-	$$ = array;
-}
 
 sep_dc: ':' |
 

From c9b57eb8dcb097e32f9a73f88f6d13c57ce65b4d Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 27 Jul 2023 17:12:12 -0700
Subject: [PATCH 0285/1189] perf parse-events: Remove array remnants

parse_events_array was set up by event term parsing, which no longer
exists. Remove this struct and references to it.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rob Herring <robh@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Wang ShaoBo <bobo.shaobowang@huawei.com>
Cc: YueHaibing <yuehaibing@huawei.com>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20230728001212.457900-4-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/bpf-loader.c   | 101 ---------------------------------
 tools/perf/util/parse-events.c |   8 ---
 tools/perf/util/parse-events.h |  10 ----
 3 files changed, 119 deletions(-)

diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 8f4c76f2265a..50e42698cbb7 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -1088,16 +1088,12 @@ enum bpf_map_op_type {
 
 enum bpf_map_key_type {
 	BPF_MAP_KEY_ALL,
-	BPF_MAP_KEY_RANGES,
 };
 
 struct bpf_map_op {
 	struct list_head list;
 	enum bpf_map_op_type op_type;
 	enum bpf_map_key_type key_type;
-	union {
-		struct parse_events_array array;
-	} k;
 	union {
 		u64 value;
 		struct evsel *evsel;
@@ -1113,8 +1109,6 @@ bpf_map_op__delete(struct bpf_map_op *op)
 {
 	if (!list_empty(&op->list))
 		list_del_init(&op->list);
-	if (op->key_type == BPF_MAP_KEY_RANGES)
-		parse_events__clear_array(&op->k.array);
 	free(op);
 }
 
@@ -1193,18 +1187,6 @@ bpf_map_op_setkey(struct bpf_map_op *op, struct parse_events_term *term)
 	if (!term)
 		return 0;
 
-	if (term->array.nr_ranges) {
-		size_t memsz = term->array.nr_ranges *
-				sizeof(op->k.array.ranges[0]);
-
-		op->k.array.ranges = memdup(term->array.ranges, memsz);
-		if (!op->k.array.ranges) {
-			pr_debug("Not enough memory to alloc indices for map\n");
-			return -ENOMEM;
-		}
-		op->key_type = BPF_MAP_KEY_RANGES;
-		op->k.array.nr_ranges = term->array.nr_ranges;
-	}
 	return 0;
 }
 
@@ -1241,18 +1223,6 @@ bpf_map_op__clone(struct bpf_map_op *op)
 	}
 
 	INIT_LIST_HEAD(&newop->list);
-	if (op->key_type == BPF_MAP_KEY_RANGES) {
-		size_t memsz = op->k.array.nr_ranges *
-			       sizeof(op->k.array.ranges[0]);
-
-		newop->k.array.ranges = memdup(op->k.array.ranges, memsz);
-		if (!newop->k.array.ranges) {
-			pr_debug("Failed to alloc indices for map\n");
-			free(newop);
-			return NULL;
-		}
-	}
-
 	return newop;
 }
 
@@ -1453,40 +1423,6 @@ struct bpf_obj_config__map_func bpf_obj_config__map_funcs[] = {
 	{"event", bpf_map__config_event},
 };
 
-static int
-config_map_indices_range_check(struct parse_events_term *term,
-			       struct bpf_map *map,
-			       const char *map_name)
-{
-	struct parse_events_array *array = &term->array;
-	unsigned int i;
-
-	if (!array->nr_ranges)
-		return 0;
-	if (!array->ranges) {
-		pr_debug("ERROR: map %s: array->nr_ranges is %d but range array is NULL\n",
-			 map_name, (int)array->nr_ranges);
-		return -BPF_LOADER_ERRNO__INTERNAL;
-	}
-
-	if (!map) {
-		pr_debug("Map '%s' is invalid\n", map_name);
-		return -BPF_LOADER_ERRNO__INTERNAL;
-	}
-
-	for (i = 0; i < array->nr_ranges; i++) {
-		unsigned int start = array->ranges[i].start;
-		size_t length = array->ranges[i].length;
-		unsigned int idx = start + length - 1;
-
-		if (idx >= bpf_map__max_entries(map)) {
-			pr_debug("ERROR: index %d too large\n", idx);
-			return -BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG;
-		}
-	}
-	return 0;
-}
-
 static int
 bpf__obj_config_map(struct bpf_object *obj,
 		    struct parse_events_term *term,
@@ -1522,12 +1458,6 @@ bpf__obj_config_map(struct bpf_object *obj,
 		goto out;
 	}
 
-	*key_scan_pos += strlen(map_opt);
-	err = config_map_indices_range_check(term, map, map_name);
-	if (err)
-		goto out;
-	*key_scan_pos -= strlen(map_opt);
-
 	for (i = 0; i < ARRAY_SIZE(bpf_obj_config__map_funcs); i++) {
 		struct bpf_obj_config__map_func *func =
 				&bpf_obj_config__map_funcs[i];
@@ -1576,7 +1506,6 @@ typedef int (*map_config_func_t)(const char *name, int map_fd,
 				 const struct bpf_map *map,
 				 struct bpf_map_op *op,
 				 void *pkey, void *arg);
-
 static int
 foreach_key_array_all(map_config_func_t func,
 		      void *arg, const char *name,
@@ -1597,32 +1526,6 @@ foreach_key_array_all(map_config_func_t func,
 	return 0;
 }
 
-static int
-foreach_key_array_ranges(map_config_func_t func, void *arg,
-			 const char *name, int map_fd,
-			 const struct bpf_map *map,
-			 struct bpf_map_op *op)
-{
-	unsigned int i, j;
-	int err;
-
-	for (i = 0; i < op->k.array.nr_ranges; i++) {
-		unsigned int start = op->k.array.ranges[i].start;
-		size_t length = op->k.array.ranges[i].length;
-
-		for (j = 0; j < length; j++) {
-			unsigned int idx = start + j;
-
-			err = func(name, map_fd, map, op, &idx, arg);
-			if (err) {
-				pr_debug("ERROR: failed to insert value to %s[%u]\n",
-					 name, idx);
-				return err;
-			}
-		}
-	}
-	return 0;
-}
 
 static int
 bpf_map_config_foreach_key(struct bpf_map *map,
@@ -1663,10 +1566,6 @@ bpf_map_config_foreach_key(struct bpf_map *map,
 				err = foreach_key_array_all(func, arg, name,
 							    map_fd, map, op);
 				break;
-			case BPF_MAP_KEY_RANGES:
-				err = foreach_key_array_ranges(func, arg, name,
-							       map_fd, map, op);
-				break;
 			default:
 				pr_debug("ERROR: keytype for map '%s' invalid\n",
 					 name);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 37614dc1d698..52e9f062b26b 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -2716,9 +2716,6 @@ int parse_events_term__clone(struct parse_events_term **new,
 
 void parse_events_term__delete(struct parse_events_term *term)
 {
-	if (term->array.nr_ranges)
-		zfree(&term->array.ranges);
-
 	if (term->type_val != PARSE_EVENTS__TERM_TYPE_NUM)
 		zfree(&term->val.str);
 
@@ -2769,11 +2766,6 @@ void parse_events_terms__delete(struct list_head *terms)
 	free(terms);
 }
 
-void parse_events__clear_array(struct parse_events_array *a)
-{
-	zfree(&a->ranges);
-}
-
 void parse_events_evlist_error(struct parse_events_state *parse_state,
 			       int idx, const char *str)
 {
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index e59b33805886..b77ff619a623 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -81,17 +81,8 @@ enum {
 	__PARSE_EVENTS__TERM_TYPE_NR,
 };
 
-struct parse_events_array {
-	size_t nr_ranges;
-	struct {
-		unsigned int start;
-		size_t length;
-	} *ranges;
-};
-
 struct parse_events_term {
 	char *config;
-	struct parse_events_array array;
 	union {
 		char *str;
 		u64  num;
@@ -162,7 +153,6 @@ int parse_events_term__clone(struct parse_events_term **new,
 void parse_events_term__delete(struct parse_events_term *term);
 void parse_events_terms__delete(struct list_head *terms);
 void parse_events_terms__purge(struct list_head *terms);
-void parse_events__clear_array(struct parse_events_array *a);
 int parse_events__modifier_event(struct list_head *list, char *str, bool add);
 int parse_events__modifier_group(struct list_head *list, char *event_mod);
 int parse_events_name(struct list_head *list, const char *name);

From 11cb1ed477692320af116c543b47084cbb898026 Mon Sep 17 00:00:00 2001
From: Aditya Gupta <adityag@linux.ibm.com>
Date: Tue, 25 Jul 2023 11:46:49 +0530
Subject: [PATCH 0286/1189] perf tests task_analyzer: Check perf build options
 for libtraceevent support

Currently we depend on output of 'perf record -e "sched:sched_switch"', to
check whether perf was built with libtraceevent support.

Instead, a more straightforward approach can be to check the build options,
using 'perf version --build-options', to check for libtraceevent support.

When perf is compiled WITHOUT libtraceevent ('make NO_LIBTRACEEVENT=1'),
'perf version --build-options' outputs (output trimmed):

	 ...
         libtraceevent: [ OFF ]  # HAVE_LIBTRACEEVENT
	 ...

While, when perf is compiled WITH libtraceevent,

'perf version --build-options' outputs:

...
         libtraceevent: [ on ]  # HAVE_LIBTRACEEVENT
	 ...

Committer notes:

Removed one grep in the pipleline by combining the two into just one
expression that covers the OFF + HAVE_LIBTRACEEVENT.

Suggested-by: Ian Rogers <irogers@google.com>
Signed-off-by: Aditya Gupta <adityag@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230725061649.34937-1-adityag@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/test_task_analyzer.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/shell/test_task_analyzer.sh b/tools/perf/tests/shell/test_task_analyzer.sh
index 0095abbe20ca..92d15154ba79 100755
--- a/tools/perf/tests/shell/test_task_analyzer.sh
+++ b/tools/perf/tests/shell/test_task_analyzer.sh
@@ -52,7 +52,7 @@ find_str_or_fail() {
 
 # check if perf is compiled with libtraceevent support
 skip_no_probe_record_support() {
-	perf record -e "sched:sched_switch" -a -- sleep 1 2>&1 | grep "libtraceevent is necessary for tracepoint support" && return 2
+	perf version --build-options | grep -q " OFF .* HAVE_LIBTRACEEVENT" && return 2
 	return 0
 }
 

From 38beba673b43b168906fff54f59cf004d2eb8120 Mon Sep 17 00:00:00 2001
From: Akanksha J N <akanksha@linux.ibm.com>
Date: Sun, 9 Jul 2023 23:57:35 +0530
Subject: [PATCH 0287/1189] perf tests trace+probe_vfs_getname: Fix shellcheck
 warnings about word splitting/quoting

Running shellcheck -S on probe_vfs_getname.sh, throws below warnings:

Before fix:

$ shellcheck -S warning trace+probe_vfs_getname.sh

	In trace+probe_vfs_getname.sh line 13:
	. $(dirname $0)/lib/probe.sh
	  ^-----------^ SC2046 (warning): Quote this to prevent word splitting.

	In trace+probe_vfs_getname.sh line 18:
	. $(dirname $0)/lib/probe_vfs_getname.sh
	  ^-----------^ SC2046 (warning): Quote this to prevent word splitting.

	In trace+probe_vfs_getname.sh line 21:
		evts=$(echo $(perf list syscalls:sys_enter_open* 2>/dev/null | grep -E 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/')
		            ^-- SC2046 (warning): Quote this to prevent word splitting.

Fix the shellcheck warnings by adding quotes to prevent word splitting.

Signed-off-by: Akanksha J N <akanksha@linux.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230709182800.53002-2-atrajeev@linux.vnet.ibm.com
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/trace+probe_vfs_getname.sh | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
index 0a4bac3dd77e..db2ff141f703 100755
--- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
@@ -10,15 +10,15 @@
 # SPDX-License-Identifier: GPL-2.0
 # Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
 
-. $(dirname $0)/lib/probe.sh
+. "$(dirname $0)"/lib/probe.sh
 
 skip_if_no_perf_probe || exit 2
 skip_if_no_perf_trace || exit 2
 
-. $(dirname $0)/lib/probe_vfs_getname.sh
+. "$(dirname $0)"/lib/probe_vfs_getname.sh
 
 trace_open_vfs_getname() {
-	evts=$(echo $(perf list syscalls:sys_enter_open* 2>/dev/null | grep -E 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/')
+	evts="$(echo "$(perf list syscalls:sys_enter_open* 2>/dev/null | grep -E 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/')" | sed ':a;N;s:\n:,:g')"
 	perf trace -e $evts touch $file 2>&1 | \
 	grep -E " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open(at)?\((dfd: +CWD, +)?filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
 }

From 7b485d9468903dea570542dc814f778d268162f6 Mon Sep 17 00:00:00 2001
From: Kajol Jain <kjain@linux.ibm.com>
Date: Sun, 9 Jul 2023 23:57:36 +0530
Subject: [PATCH 0288/1189] perf tests probe_vfs_getname: Fix shellcheck
 warnings about word splitting/quoting

Running shellcheck on probe_vfs_getname.sh throws below warning:

In tests/shell/probe_vfs_getname.sh line 7:
. $(dirname $0)/lib/probe.sh
  ^-----------^ SC2046 (warning): Quote this to prevent word splitting.

In tests/shell/probe_vfs_getname.sh line 11:
. $(dirname $0)/lib/probe_vfs_getname.sh
  ^-----------^ SC2046 (warning): Quote this to prevent word splitting.

Fixed the warning by adding quotes to avoid word splitting.

ShellCheck result with patch:
    # shellcheck -S warning probe_vfs_getname.sh
    #

Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230709182800.53002-3-atrajeev@linux.vnet.ibm.com
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/probe_vfs_getname.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/tests/shell/probe_vfs_getname.sh b/tools/perf/tests/shell/probe_vfs_getname.sh
index 5d1b63d3f3e1..871243d6d03a 100755
--- a/tools/perf/tests/shell/probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/probe_vfs_getname.sh
@@ -4,11 +4,11 @@
 # SPDX-License-Identifier: GPL-2.0
 # Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
 
-. $(dirname $0)/lib/probe.sh
+. "$(dirname $0)"/lib/probe.sh
 
 skip_if_no_perf_probe || exit 2
 
-. $(dirname $0)/lib/probe_vfs_getname.sh
+. "$(dirname $0)"/lib/probe_vfs_getname.sh
 
 add_probe_vfs_getname || skip_if_no_debuginfo
 err=$?

From a225c3049791b1591debf07fa9f4377b2c331ecc Mon Sep 17 00:00:00 2001
From: Kajol Jain <kjain@linux.ibm.com>
Date: Sun, 9 Jul 2023 23:57:37 +0530
Subject: [PATCH 0289/1189] perf tests record_offcpu: Fix shellcheck warnings
 about word splitting/quoting and signal names case

Running shellcheck on record_offcpu.sh throws below warning:

In tests/shell/record_offcpu.sh line 13:
  trap - exit term int
         ^--^ SC3049 (warning): In POSIX sh, using lower/mixed case for signal names is undefined.
              ^--^ SC3049 (warning): In POSIX sh, using lower/mixed case for signal names is undefined.
                   ^-^ SC3049 (warning): In POSIX sh, using lower/mixed case for signal names is undefined.

In tests/shell/record_offcpu.sh line 20:
trap trap_cleanup exit term int
                  ^--^ SC3049 (warning): In POSIX sh, using lower/mixed case for signal names is undefined.
                       ^--^ SC3049 (warning): In POSIX sh, using lower/mixed case for signal names is undefined.
                            ^-^ SC3049 (warning): In POSIX sh, using lower/mixed case for signal names is undefined.

In tests/shell/record_offcpu.sh line 25:
  if [ `id -u` != 0 ]
       ^-----^ SC2046 (warning): Quote this to prevent word splitting.

Fixed the warnings by:
- Capitalize signals(INT, TERM, EXIT) to avoid mixed/lower case naming of
signals.
- Adding quotes to avoid word splitting.

Result from shellcheck after patch changes:
     $ shellcheck -S warning record_offcpu.sh
     $

Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230709182800.53002-4-atrajeev@linux.vnet.ibm.com
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/record_offcpu.sh | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/perf/tests/shell/record_offcpu.sh b/tools/perf/tests/shell/record_offcpu.sh
index f062ae9a95e1..a0d14cd0aa79 100755
--- a/tools/perf/tests/shell/record_offcpu.sh
+++ b/tools/perf/tests/shell/record_offcpu.sh
@@ -10,19 +10,19 @@ perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
 cleanup() {
   rm -f ${perfdata}
   rm -f ${perfdata}.old
-  trap - exit term int
+  trap - EXIT TERM INT
 }
 
 trap_cleanup() {
   cleanup
   exit 1
 }
-trap trap_cleanup exit term int
+trap trap_cleanup EXIT TERM INT
 
 test_offcpu_priv() {
   echo "Checking off-cpu privilege"
 
-  if [ `id -u` != 0 ]
+  if [ "$(id -u)" != 0 ]
   then
     echo "off-cpu test [Skipped permission]"
     err=2

From edf197cb9da529ef854ba21311ddbaddc7098eba Mon Sep 17 00:00:00 2001
From: Kajol Jain <kjain@linux.ibm.com>
Date: Sun, 9 Jul 2023 23:57:38 +0530
Subject: [PATCH 0290/1189] perf tests lock_contention: Fix shellcheck issue
 about quoting to avoid word splitting

Running shellcheck on lock_contention.sh generates below warning:

In tests/shell/lock_contention.sh line 24:
	if [ `id -u` != 0 ]; then
             ^-----^ SC2046 (warning): Quote this to prevent word splitting.

In tests/shell/lock_contention.sh line 160:
	local type=$(head -1 "${result}" | awk '{ print $8 }' | sed -e 's/:.*//')
        ^--------^ SC3043 (warning): In POSIX sh, 'local' is undefined.
              ^--^ SC2155 (warning): Declare and assign separately to avoid masking return values.
                   ^-- SC2046 (warning): Quote this to prevent word splitting.

Fixed above warnings by:

- Adding quotes to avoid word splitting.
- Fixing shellcheck warnings for local usage, by prefixing
  function name to the variable.

Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230709182800.53002-5-atrajeev@linux.vnet.ibm.com
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/lock_contention.sh | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/perf/tests/shell/lock_contention.sh b/tools/perf/tests/shell/lock_contention.sh
index 4a194420416e..d120e83db7d9 100755
--- a/tools/perf/tests/shell/lock_contention.sh
+++ b/tools/perf/tests/shell/lock_contention.sh
@@ -21,7 +21,7 @@ trap_cleanup() {
 trap trap_cleanup EXIT TERM INT
 
 check() {
-	if [ `id -u` != 0 ]; then
+	if [ "$(id -u)" != 0 ]; then
 		echo "[Skip] No root permission"
 		err=2
 		exit
@@ -157,10 +157,10 @@ test_lock_filter()
 	perf lock contention -i ${perfdata} -L tasklist_lock -q 2> ${result}
 
 	# find out the type of tasklist_lock
-	local type=$(head -1 "${result}" | awk '{ print $8 }' | sed -e 's/:.*//')
+	test_lock_filter_type=$(head -1 "${result}" | awk '{ print $8 }' | sed -e 's/:.*//')
 
-	if [ "$(grep -c -v "${type}" "${result}")" != "0" ]; then
-		echo "[Fail] Recorded result should not have non-${type} locks:" "$(cat "${result}")"
+	if [ "$(grep -c -v "${test_lock_filter_type}" "${result}")" != "0" ]; then
+		echo "[Fail] Recorded result should not have non-${test_lock_filter_type} locks:" "$(cat "${result}")"
 		err=1
 		exit
 	fi
@@ -170,8 +170,8 @@ test_lock_filter()
 	fi
 
 	perf lock con -a -b -L tasklist_lock -q -- perf bench sched messaging > /dev/null 2> ${result}
-	if [ "$(grep -c -v "${type}" "${result}")" != "0" ]; then
-		echo "[Fail] BPF result should not have non-${type} locks:" "$(cat "${result}")"
+	if [ "$(grep -c -v "${test_lock_filter_type}" "${result}")" != "0" ]; then
+		echo "[Fail] BPF result should not have non-${test_lock_filter_type} locks:" "$(cat "${result}")"
 		err=1
 		exit
 	fi

From 0dd1f815545d7210150642741c364521cc5cf116 Mon Sep 17 00:00:00 2001
From: Kajol Jain <kjain@linux.ibm.com>
Date: Sun, 9 Jul 2023 23:57:39 +0530
Subject: [PATCH 0291/1189] perf test stat_bpf_counters_cgrp: Fix shellcheck
 issue about logical operators

Running shellcheck on lock_contention.sh generates below warning:

In stat_bpf_counters_cgrp.sh line 28:
	if [ -d /sys/fs/cgroup/system.slice -a -d /sys/fs/cgroup/user.slice ]; then
                                            ^-- SC2166 (warning): Prefer [ p ] && [ q ] as [ p -a q ] is not well defined.

In stat_bpf_counters_cgrp.sh line 34:
	local self_cgrp=$(grep perf_event /proc/self/cgroup | cut -d: -f3)
        ^-------------^ SC3043 (warning): In POSIX sh, 'local' is undefined.
              ^-------^ SC2155 (warning): Declare and assign separately to avoid masking return values.
                        ^-- SC2046 (warning): Quote this to prevent word splitting.

In stat_bpf_counters_cgrp.sh line 51:
	local output
        ^----------^ SC3043 (warning): In POSIX sh, 'local' is undefined.

In stat_bpf_counters_cgrp.sh line 65:
	local output
        ^----------^ SC3043 (warning): In POSIX sh, 'local' is undefined.

Fixed above warnings by:
- Changing the expression [p -a q] to [p] && [q].
- Fixing shellcheck warnings for local usage, by prefixing
  function name to the variable.

Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230709182800.53002-6-atrajeev@linux.vnet.ibm.com
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../tests/shell/stat_bpf_counters_cgrp.sh     | 28 ++++++++-----------
 1 file changed, 12 insertions(+), 16 deletions(-)

diff --git a/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh
index d724855d097c..a74440a00b6b 100755
--- a/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh
+++ b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh
@@ -25,22 +25,22 @@ check_bpf_counter()
 find_cgroups()
 {
 	# try usual systemd slices first
-	if [ -d /sys/fs/cgroup/system.slice -a -d /sys/fs/cgroup/user.slice ]; then
+	if [ -d /sys/fs/cgroup/system.slice ] && [ -d /sys/fs/cgroup/user.slice ]; then
 		test_cgroups="system.slice,user.slice"
 		return
 	fi
 
 	# try root and self cgroups
-	local self_cgrp=$(grep perf_event /proc/self/cgroup | cut -d: -f3)
-	if [ -z ${self_cgrp} ]; then
+	find_cgroups_self_cgrp=$(grep perf_event /proc/self/cgroup | cut -d: -f3)
+	if [ -z ${find_cgroups_self_cgrp} ]; then
 		# cgroup v2 doesn't specify perf_event
-		self_cgrp=$(grep ^0: /proc/self/cgroup | cut -d: -f3)
+		find_cgroups_self_cgrp=$(grep ^0: /proc/self/cgroup | cut -d: -f3)
 	fi
 
-	if [ -z ${self_cgrp} ]; then
+	if [ -z ${find_cgroups_self_cgrp} ]; then
 		test_cgroups="/"
 	else
-		test_cgroups="/,${self_cgrp}"
+		test_cgroups="/,${find_cgroups_self_cgrp}"
 	fi
 }
 
@@ -48,13 +48,11 @@ find_cgroups()
 # Just check if it runs without failure and has non-zero results.
 check_system_wide_counted()
 {
-	local output
-
-	output=$(perf stat -a --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, sleep 1  2>&1)
-	if echo ${output} | grep -q -F "<not "; then
+	check_system_wide_counted_output=$(perf stat -a --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, sleep 1  2>&1)
+	if echo ${check_system_wide_counted_output} | grep -q -F "<not "; then
 		echo "Some system-wide events are not counted"
 		if [ "${verbose}" = "1" ]; then
-			echo ${output}
+			echo ${check_system_wide_counted_output}
 		fi
 		exit 1
 	fi
@@ -62,13 +60,11 @@ check_system_wide_counted()
 
 check_cpu_list_counted()
 {
-	local output
-
-	output=$(perf stat -C 1 --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, taskset -c 1 sleep 1  2>&1)
-	if echo ${output} | grep -q -F "<not "; then
+	check_cpu_list_counted_output=$(perf stat -C 1 --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, taskset -c 1 sleep 1  2>&1)
+	if echo ${check_cpu_list_counted_output} | grep -q -F "<not "; then
 		echo "Some CPU events are not counted"
 		if [ "${verbose}" = "1" ]; then
-			echo ${output}
+			echo ${check_cpu_list_counted_output}
 		fi
 		exit 1
 	fi

From e9c7c3a1092aca9a3247bd342ccf1861a540e403 Mon Sep 17 00:00:00 2001
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Date: Sun, 9 Jul 2023 23:57:40 +0530
Subject: [PATCH 0292/1189] perf tests: Address signal case issues detected via
 shellcheck

Running shellcheck -S on test_arm_spe_fork.sh throws below warnings:

   In tests/shell/test_arm_spe_fork.sh line 25:
   trap cleanup_files exit term int
                      ^--^ SC3049 (warning): In POSIX sh, using lower/mixed case for signal names is undefined.
                           ^--^ SC3049 (warning): In POSIX sh, using lower/mixed case for signal names is undefined.
                                ^-^ SC3049 (warning): In POSIX sh, using lower/mixed case for signal names is undefined.

Fixed this issue by using uppercase for "EXIT", "TERM" and
"INIT" signals to avoid using lower/mixed case for signal
names as input.

Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230709182800.53002-7-atrajeev@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/test_arm_spe_fork.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/shell/test_arm_spe_fork.sh b/tools/perf/tests/shell/test_arm_spe_fork.sh
index fad361675a1d..1a7e6a82d0e3 100755
--- a/tools/perf/tests/shell/test_arm_spe_fork.sh
+++ b/tools/perf/tests/shell/test_arm_spe_fork.sh
@@ -22,7 +22,7 @@ cleanup_files()
 	rm -f ${PERF_DATA}
 }
 
-trap cleanup_files exit term int
+trap cleanup_files EXIT TERM INT
 
 echo "Recording workload..."
 perf record -o ${PERF_DATA} -e arm_spe/period=65536/ -vvv -- $TEST_PROGRAM > ${PERF_RECORD_LOG} 2>&1 &

From faae152aa6d237001e55bfcb9026cadf9531fc3c Mon Sep 17 00:00:00 2001
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Date: Sun, 9 Jul 2023 23:57:41 +0530
Subject: [PATCH 0293/1189] perf tests stat+csv_summary: Fix unused variable
 references detected via shellcheck

Running shellcheck on stat+csv_summary.sh throws below warnings:

   In tests/shell/stat+csv_summary.sh line 26:
   while read num event run pct
              ^-^ SC2034 (warning): num appears unused. Verify use (or export if used externally).
                  ^---^ SC2034 (warning): event appears unused. Verify use (or export if used externally).
                        ^-^ SC2034 (warning): run appears unused. Verify use (or export if used externally).
                            ^-^ SC2034 (warning): pct appears unused. Verify use (or export if used externally).

These variables are intentionally unused since they are needed to parse
through the output. Use "_" as a prefix for these throw away variables.

Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230709182800.53002-8-atrajeev@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/stat+csv_summary.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/tests/shell/stat+csv_summary.sh b/tools/perf/tests/shell/stat+csv_summary.sh
index 5571ff75eb42..8bae9c8a835e 100755
--- a/tools/perf/tests/shell/stat+csv_summary.sh
+++ b/tools/perf/tests/shell/stat+csv_summary.sh
@@ -10,7 +10,7 @@ set -e
 #
 perf stat -e cycles  -x' ' -I1000 --interval-count 1 --summary 2>&1 | \
 grep -e summary | \
-while read summary num event run pct
+while read summary _num _event _run _pct
 do
 	if [ $summary != "summary" ]; then
 		exit 1
@@ -23,7 +23,7 @@ done
 #
 perf stat -e cycles  -x' ' -I1000 --interval-count 1 --summary --no-csv-summary 2>&1 | \
 grep -e summary | \
-while read num event run pct
+while read _num _event _run _pct
 do
 	exit 1
 done

From 38b3fa07f19e0c6b22ea1167d82b184bb0e0a830 Mon Sep 17 00:00:00 2001
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Date: Sun, 9 Jul 2023 23:57:42 +0530
Subject: [PATCH 0294/1189] perf tests perf_dat _converter_json: Use quoting to
 avoid word splitting

Running shellcheck on test_perf_data_converter_json.sh throws
below warning:

   In tests/shell/test_perf_data_converter_json.sh line 42:
   	if [ $(cat "${result}" | wc -l) -gt "0" ] ; then
                ^------------------------^ SC2046 (warning): Quote this to prevent word splitting.

Fixed the warning by adding quotes to avoid word splitting.

ShellCheck result with patch:
    # shellcheck -S warning test_perf_data_converter_json.sh
    #

Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230709182800.53002-9-atrajeev@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/test_perf_data_converter_json.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/shell/test_perf_data_converter_json.sh b/tools/perf/tests/shell/test_perf_data_converter_json.sh
index 72ac6c83231c..6ded58f98f55 100755
--- a/tools/perf/tests/shell/test_perf_data_converter_json.sh
+++ b/tools/perf/tests/shell/test_perf_data_converter_json.sh
@@ -39,7 +39,7 @@ test_json_converter_command()
 	echo "Testing Perf Data Convertion Command to JSON"
 	perf record -o "$perfdata" -F 99 -g -- perf test -w noploop > /dev/null 2>&1
 	perf data convert --to-json "$result" --force -i "$perfdata" >/dev/null 2>&1
-	if [ $(cat "${result}" | wc -l) -gt "0" ] ; then
+	if [ "$(cat ${result} | wc -l)" -gt "0" ] ; then
 		echo "Perf Data Converter Command to JSON [SUCCESS]"
 	else
 		echo "Perf Data Converter Command to JSON [FAILED]"

From d10eedd87bb3e7678c3a0f77a5cfe7150a318ee2 Mon Sep 17 00:00:00 2001
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Date: Sun, 9 Jul 2023 23:57:43 +0530
Subject: [PATCH 0295/1189] perf tests stat_bpf_counters: Fix usage of '==' to
 address shellcheck warning

Running shellcheck on stat_bpf_counter.sh generates below
warning:

   In tests/shell/stat_bpf_counters.sh line 34:
   if [ "$base_cycles" == "<not" ]; then
                       ^-- SC3014 (warning): In POSIX sh, == in place of = is undefined.

   In tests/shell/stat_bpf_counters.sh line 39:
   if [ "$bpf_cycles" == "<not" ]; then
                      ^-- SC3014 (warning): In POSIX sh, == in place of = is undefined.

Fix this by using "=" instead of "==" to work for
all shells.

Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230709182800.53002-10-atrajeev@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/stat_bpf_counters.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/tests/shell/stat_bpf_counters.sh b/tools/perf/tests/shell/stat_bpf_counters.sh
index 13473aeba489..513cd1e58e0e 100755
--- a/tools/perf/tests/shell/stat_bpf_counters.sh
+++ b/tools/perf/tests/shell/stat_bpf_counters.sh
@@ -31,12 +31,12 @@ if ! perf stat --bpf-counters true > /dev/null 2>&1; then
 fi
 
 base_cycles=$(perf stat --no-big-num -e cycles -- perf bench sched messaging -g 1 -l 100 -t 2>&1 | awk '/cycles/ {print $1}')
-if [ "$base_cycles" == "<not" ]; then
+if [ "$base_cycles" = "<not" ]; then
 	echo "Skipping: cycles event not counted"
 	exit 2
 fi
 bpf_cycles=$(perf stat --no-big-num --bpf-counters -e cycles -- perf bench sched messaging -g 1 -l 100 -t 2>&1 | awk '/cycles/ {print $1}')
-if [ "$bpf_cycles" == "<not" ]; then
+if [ "$bpf_cycles" = "<not" ]; then
 	echo "Failed: cycles not counted with --bpf-counters"
 	exit 1
 fi

From d13841e7898bf3a1a5fcd19fcb70331f74215061 Mon Sep 17 00:00:00 2001
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Date: Sun, 9 Jul 2023 23:57:44 +0530
Subject: [PATCH 0296/1189] perf tests stat+shadow_stat: Fix shellcheck warning
 about unused variable

Running shellcheck on stat+shadow_stat.sh generates below warning:

In tests/shell/stat+shadow_stat.sh line 48:
        while read cpu num evt hash ipc rest
                               ^--^ SC2034 (warning): hash appears unused. Verify use (or export if used externally).

This variable is intentionally unused since it is needed to parse
through the output. Use "_" as a prefix for this throw away variable.

Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230709182800.53002-11-atrajeev@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/stat+shadow_stat.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/tests/shell/stat+shadow_stat.sh b/tools/perf/tests/shell/stat+shadow_stat.sh
index 0e9cba84e757..a1918a15e36a 100755
--- a/tools/perf/tests/shell/stat+shadow_stat.sh
+++ b/tools/perf/tests/shell/stat+shadow_stat.sh
@@ -14,7 +14,7 @@ test_global_aggr()
 {
 	perf stat -a --no-big-num -e cycles,instructions sleep 1  2>&1 | \
 	grep -e cycles -e instructions | \
-	while read num evt hash ipc rest
+	while read num evt _hash ipc rest
 	do
 		# skip not counted events
 		if [ "$num" = "<not" ]; then
@@ -45,7 +45,7 @@ test_no_aggr()
 {
 	perf stat -a -A --no-big-num -e cycles,instructions sleep 1  2>&1 | \
 	grep ^CPU | \
-	while read cpu num evt hash ipc rest
+	while read cpu num evt _hash ipc rest
 	do
 		# skip not counted events
 		if [ "$num" = "<not" ]; then

From 60f253ea7f1ba5122dff18812610b59477690dab Mon Sep 17 00:00:00 2001
From: Kajol Jain <kjain@linux.ibm.com>
Date: Sun, 9 Jul 2023 23:57:45 +0530
Subject: [PATCH 0297/1189] perf tests asm_pure_loop: Fix shellcheck warning
 about word splitting/quote

Running shellcheck on asm_pure_loop.sh throws below warning:

In coresight/asm_pure_loop.sh line 8:
. $(dirname $0)/../lib/coresight.sh
  ^-----------^ SC2046 (warning): Quote this to prevent word splitting.

Fixed the warning by adding quotes to avoid word splitting.

ShellCheck result with patch:
    # shellcheck -S warning coresight/asm_pure_loop.sh
    #

Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230709182800.53002-12-atrajeev@linux.vnet.ibm.com
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/coresight/asm_pure_loop.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/shell/coresight/asm_pure_loop.sh b/tools/perf/tests/shell/coresight/asm_pure_loop.sh
index 569e9d46162b..779bc8608e1e 100755
--- a/tools/perf/tests/shell/coresight/asm_pure_loop.sh
+++ b/tools/perf/tests/shell/coresight/asm_pure_loop.sh
@@ -5,7 +5,7 @@
 # Carsten Haitzler <carsten.haitzler@arm.com>, 2021
 
 TEST="asm_pure_loop"
-. $(dirname $0)/../lib/coresight.sh
+. "$(dirname $0)"/../lib/coresight.sh
 ARGS=""
 DATV="out"
 DATA="$DATD/perf-$TEST-$DATV.data"

From 5f83f1d58821660ced1c7330a6dd3ff013240f66 Mon Sep 17 00:00:00 2001
From: Kajol Jain <kjain@linux.ibm.com>
Date: Sun, 9 Jul 2023 23:57:46 +0530
Subject: [PATCH 0298/1189] perf tests memcpy_thread_16k_10: Fix shellcheck
 warning about word splitting/quote

Running shellcheck on memcpy_thread_16k_10.sh throws below warning:

In memcpy_thread_16k_10.sh line 8:
. $(dirname $0)/../lib/coresight.sh
  ^-----------^ SC2046 (warning): Quote this to prevent word splitting.

Fixed the warning by adding quotes to avoid word splitting.

ShellCheck result with patch:
    # shellcheck -S warning coresight/memcpy_thread_16k_10.sh
    #

Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230709182800.53002-13-atrajeev@linux.vnet.ibm.com
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/coresight/memcpy_thread_16k_10.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/shell/coresight/memcpy_thread_16k_10.sh b/tools/perf/tests/shell/coresight/memcpy_thread_16k_10.sh
index d21ba8545938..08a44e52ce9b 100755
--- a/tools/perf/tests/shell/coresight/memcpy_thread_16k_10.sh
+++ b/tools/perf/tests/shell/coresight/memcpy_thread_16k_10.sh
@@ -5,7 +5,7 @@
 # Carsten Haitzler <carsten.haitzler@arm.com>, 2021
 
 TEST="memcpy_thread"
-. $(dirname $0)/../lib/coresight.sh
+. "$(dirname $0)"/../lib/coresight.sh
 ARGS="16 10 1"
 DATV="16k_10"
 DATA="$DATD/perf-$TEST-$DATV.data"

From 05ef238cd05db7b3b2e596027c403964de1d3919 Mon Sep 17 00:00:00 2001
From: Kajol Jain <kjain@linux.ibm.com>
Date: Sun, 9 Jul 2023 23:57:47 +0530
Subject: [PATCH 0299/1189] perf tests lib probe: Fix shellcheck warning about
 about missing shebang

Running shellcheck on probe.sh throws below warning:

In lib/probe.sh line 1:
^-- SC2148 (error): Tips depend on target shell and yours is unknown. Add a shebang or a 'shell' directive.

Fixed the warnings by adding shell directive.

Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230709182800.53002-14-atrajeev@linux.vnet.ibm.com
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/lib/probe.sh | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/tests/shell/lib/probe.sh b/tools/perf/tests/shell/lib/probe.sh
index 51e3f60baba0..5aa6e2ec5734 100644
--- a/tools/perf/tests/shell/lib/probe.sh
+++ b/tools/perf/tests/shell/lib/probe.sh
@@ -1,3 +1,4 @@
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 # Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
 

From f188b2ce65730178f8dc0d105beb759719a12e6c Mon Sep 17 00:00:00 2001
From: Kajol Jain <kjain@linux.ibm.com>
Date: Sun, 9 Jul 2023 23:57:48 +0530
Subject: [PATCH 0300/1189] perf beauty arch_errno_names: Fix shellcheck issue
 about local variables

Running shellcheck on arch_errno_names.sh generates below warning:

In arch_errno_names.sh line 20:
	local arch="$1"
        ^--------^ SC3043 (warning): In POSIX sh, 'local' is undefined.

......

In arch_errno_names.sh line 61:
	local arch
        ^--------^ SC3043 (warning): In POSIX sh, 'local' is undefined.

In arch_errno_names.sh line 67:
		printf '\t\treturn errno_to_name__%s(err);\n' $(arch_string "$arch")
                                                              ^--------------------^ SC2046 (warning): Quote this to prevent word splitting.

In arch_errno_names.sh line 69:
	printf '\treturn errno_to_name__%s(err);\n' $(arch_string "$default")
                                                    ^-----------------------^ SC2046 (warning): Quote this to prevent word splitting.

Fixed the warnings by:
- Fixing shellcheck warnings for local usage, by removing
  local from the variable names
- Adding quotes to avoid word splitting

Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230709182800.53002-15-atrajeev@linux.vnet.ibm.com
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/arch_errno_names.sh | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/tools/perf/trace/beauty/arch_errno_names.sh b/tools/perf/trace/beauty/arch_errno_names.sh
index 37c53bac5f56..cc09dcaa891e 100755
--- a/tools/perf/trace/beauty/arch_errno_names.sh
+++ b/tools/perf/trace/beauty/arch_errno_names.sh
@@ -17,8 +17,7 @@ arch_string()
 
 asm_errno_file()
 {
-	local arch="$1"
-	local header
+	arch="$1"
 
 	header="$toolsdir/arch/$arch/include/uapi/asm/errno.h"
 	if test -r "$header"; then
@@ -30,8 +29,7 @@ asm_errno_file()
 
 create_errno_lookup_func()
 {
-	local arch=$(arch_string "$1")
-	local nr name
+	arch=$(arch_string "$1")
 
 	printf "static const char *errno_to_name__%s(int err)\n{\n\tswitch (err) {\n" $arch
 
@@ -44,8 +42,8 @@ create_errno_lookup_func()
 
 process_arch()
 {
-	local arch="$1"
-	local asm_errno=$(asm_errno_file "$arch")
+	arch="$1"
+	asm_errno=$(asm_errno_file "$arch")
 
 	$gcc $CFLAGS $include_path -E -dM -x c $asm_errno \
 		|grep -hE '^#define[[:blank:]]+(E[^[:blank:]]+)[[:blank:]]+([[:digit:]]+).*' \
@@ -56,9 +54,8 @@ process_arch()
 
 create_arch_errno_table_func()
 {
-	local archlist="$1"
-	local default="$2"
-	local arch
+	archlist="$1"
+	default="$2"
 
 	printf 'const char *arch_syscalls__strerrno(const char *arch, int err)\n'
 	printf '{\n'

From e936584214b93929eb41ec598959469e3a1f6079 Mon Sep 17 00:00:00 2001
From: Kajol Jain <kjain@linux.ibm.com>
Date: Sun, 9 Jul 2023 23:57:49 +0530
Subject: [PATCH 0301/1189] perf build: Fix shellcheck issue about quotes for
 check-headers.sh

Running shellcheck on check-headers.sh generates below warning:

In check-headers.sh line 126:
  check_2 "tools/$file" "$file" $*
                                ^-- SC2048 (warning): Use "$@" (with quotes) to prevent whitespace problems.

In check-headers.sh line 134:
  check_2 "tools/perf/trace/beauty/$file" "$file" $*
                                                  ^-- SC2048 (warning): Use "$@" (with quotes) to prevent whitespace problems.

In check-headers.sh line 186:
cd tools/perf
^-----------^ SC2164 (warning): Use 'cd ... || exit' or 'cd ... || return' in case cd fails.

Fixed the warnings by:
- Using "$@" instead of $*
- Adding exit condition with cd command

Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230709182800.53002-16-atrajeev@linux.vnet.ibm.com
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/check-headers.sh | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index a0f1d8adce60..4314c9197850 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -123,7 +123,7 @@ check () {
 
   shift
 
-  check_2 "tools/$file" "$file" $*
+  check_2 "tools/$file" "$file" "$@"
 }
 
 beauty_check () {
@@ -131,7 +131,7 @@ beauty_check () {
 
   shift
 
-  check_2 "tools/perf/trace/beauty/$file" "$file" $*
+  check_2 "tools/perf/trace/beauty/$file" "$file" "$@"
 }
 
 # Check if we have the kernel headers (tools/perf/../../include), else
@@ -183,7 +183,7 @@ done
 check_2 tools/perf/util/hashmap.h tools/lib/bpf/hashmap.h
 check_2 tools/perf/util/hashmap.c tools/lib/bpf/hashmap.c
 
-cd tools/perf
+cd tools/perf || exit
 
 if [ ${#FAILURES[@]} -gt 0 ]
 then

From 5fe0531205688fe9bda0ce94628b133b0f94b229 Mon Sep 17 00:00:00 2001
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Date: Sun, 9 Jul 2023 23:57:50 +0530
Subject: [PATCH 0302/1189] perf tests thread_loop_check_tid_10: Fix shellcheck
 warnings bout word splitting/quoting

Fix the shellcheck warnings for thread_loop_check_tid_10.sh

   In ./tools/perf/tests/shell/coresight/thread_loop_check_tid_10.sh line 8:
   . $(dirname $0)/../lib/coresight.sh
     ^-----------^ SC2046 (warning): Quote this to prevent word splitting.

Add quotes to prevent word splitting which are caused by
unquoted command expansions.

Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230709182800.53002-17-atrajeev@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/coresight/thread_loop_check_tid_10.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/shell/coresight/thread_loop_check_tid_10.sh b/tools/perf/tests/shell/coresight/thread_loop_check_tid_10.sh
index 7c13636fc778..c83a200dede4 100755
--- a/tools/perf/tests/shell/coresight/thread_loop_check_tid_10.sh
+++ b/tools/perf/tests/shell/coresight/thread_loop_check_tid_10.sh
@@ -5,7 +5,7 @@
 # Carsten Haitzler <carsten.haitzler@arm.com>, 2021
 
 TEST="thread_loop"
-. $(dirname $0)/../lib/coresight.sh
+. "$(dirname $0)"/../lib/coresight.sh
 ARGS="10 1"
 DATV="check-tid-10th"
 DATA="$DATD/perf-$TEST-$DATV.data"

From b19de09bbee61aa9ef9fba392a9c8743019b858f Mon Sep 17 00:00:00 2001
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Date: Sun, 9 Jul 2023 23:57:51 +0530
Subject: [PATCH 0303/1189] perf tests unroll_loop_thread_10: Fix shellcheck
 warnings about word splitting/quoting

Fix the shellcheck warnings for unroll_loop_thread_10.sh
Add quotes to prevent word splitting which are caused by
unquoted command expansions.

Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230709182800.53002-18-atrajeev@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/coresight/unroll_loop_thread_10.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/shell/coresight/unroll_loop_thread_10.sh b/tools/perf/tests/shell/coresight/unroll_loop_thread_10.sh
index f48c85230b15..7304e3d3a6ff 100755
--- a/tools/perf/tests/shell/coresight/unroll_loop_thread_10.sh
+++ b/tools/perf/tests/shell/coresight/unroll_loop_thread_10.sh
@@ -5,7 +5,7 @@
 # Carsten Haitzler <carsten.haitzler@arm.com>, 2021
 
 TEST="unroll_loop_thread"
-. $(dirname $0)/../lib/coresight.sh
+. "$(dirname $0)"/../lib/coresight.sh
 ARGS="10"
 DATV="10"
 DATA="$DATD/perf-$TEST-$DATV.data"

From a5f3171b13525d106e15286d96a9b53dcf7d4fd5 Mon Sep 17 00:00:00 2001
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Date: Sun, 9 Jul 2023 23:57:52 +0530
Subject: [PATCH 0304/1189] perf tests lib probe_vfs_getname: Fix shellcheck
 warnings about missing shebang/local variables

Running shellcheck on probe_vfs_getname fails with below
warning:

   In ./tools/perf/tests/shell/lib/probe_vfs_getname.sh line 1:
   # Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
   ^-- SC2148 (error): Tips depend on target shell and yours is unknown. Add a shebang or a 'shell' directive.

   In ./tools/perf/tests/shell/lib/probe_vfs_getname.sh line 14:
   	   local verbose=$1
           ^-----------^ SC3043 (warning): In POSIX sh, 'local' is undefined.

Fix this:
  - by adding shebang in the beginning of the file and
  - rename variable verbose to "add_probe_verbose" after removing
    local

Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230709182800.53002-19-atrajeev@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/lib/probe_vfs_getname.sh | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/tools/perf/tests/shell/lib/probe_vfs_getname.sh b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
index 60c5e34f90c4..bf4c1fb71c4b 100644
--- a/tools/perf/tests/shell/lib/probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
@@ -1,3 +1,4 @@
+#!/bin/sh
 # Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
 
 perf probe -l 2>&1 | grep -q probe:vfs_getname
@@ -10,11 +11,11 @@ cleanup_probe_vfs_getname() {
 }
 
 add_probe_vfs_getname() {
-	local verbose=$1
+	add_probe_verbose=$1
 	if [ $had_vfs_getname -eq 1 ] ; then
 		line=$(perf probe -L getname_flags 2>&1 | grep -E 'result.*=.*filename;' | sed -r 's/[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*/\1/')
 		perf probe -q       "vfs_getname=getname_flags:${line} pathname=result->name:string" || \
-		perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:ustring"
+		perf probe $add_probe_verbose "vfs_getname=getname_flags:${line} pathname=filename:ustring"
 	fi
 }
 

From 1e094f925e1ec2825586b6a7c15f90afed9c1468 Mon Sep 17 00:00:00 2001
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Date: Sun, 9 Jul 2023 23:57:53 +0530
Subject: [PATCH 0305/1189] perf tests lib waiting: Fix the shellcheck warnings
 about missing shebang

Running shellcheck in "lib/waiting.sh" generates below
warning:

   In ./tools/perf/tests/shell/lib/waiting.sh line 1:
   # SPDX-License-Identifier: GPL-2.0
   ^-- SC2148 (error): Tips depend on target shell and yours is unknown. Add a shebang or a 'shell' directive.

Fix this by adding shebang in the beginning of the script.

Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230709182800.53002-20-atrajeev@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/lib/waiting.sh | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/tests/shell/lib/waiting.sh b/tools/perf/tests/shell/lib/waiting.sh
index e7a39134a68e..bdd5a7c71591 100644
--- a/tools/perf/tests/shell/lib/waiting.sh
+++ b/tools/perf/tests/shell/lib/waiting.sh
@@ -1,3 +1,4 @@
+#!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 
 tenths=date\ +%s%1N

From 5e9310ae235bc304a522f14a7fce6293e3cb9d14 Mon Sep 17 00:00:00 2001
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Date: Sun, 9 Jul 2023 23:57:54 +0530
Subject: [PATCH 0306/1189] perf trace x86_arch_prctl: Address shellcheck
 warnings about local variables

Running shellcheck on x86_arch_prctl.sh generates below warning:

  In ./tools/perf/trace/beauty/x86_arch_prctl.sh line 10:
      	local idx=$1
        ^-------^ SC3043 (warning): In POSIX sh, 'local' is undefined.

  In ./tools/perf/trace/beauty/x86_arch_prctl.sh line 11:
	local prefix=$2
        ^----------^ SC3043 (warning): In POSIX sh, 'local' is undefined.

   In ./tools/perf/trace/beauty/x86_arch_prctl.sh line 12:
	local first_entry=$3
        ^---------------^ SC3043 (warning): In POSIX sh, 'local' is undefined.

Fix this by removing local since these are variables used only in
specific function

Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230709182800.53002-21-atrajeev@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/x86_arch_prctl.sh | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/perf/trace/beauty/x86_arch_prctl.sh b/tools/perf/trace/beauty/x86_arch_prctl.sh
index fd5c740512c5..b1596df251f0 100755
--- a/tools/perf/trace/beauty/x86_arch_prctl.sh
+++ b/tools/perf/trace/beauty/x86_arch_prctl.sh
@@ -7,9 +7,9 @@
 prctl_arch_header=${x86_header_dir}/prctl.h
 
 print_range () {
-	local idx=$1
-	local prefix=$2
-	local first_entry=$3
+	idx=$1
+	prefix=$2
+	first_entry=$3
 
 	printf "#define x86_arch_prctl_codes_%d_offset %s\n" $idx $first_entry
 	printf "static const char *x86_arch_prctl_codes_%d[] = {\n" $idx

From 84caba70d09c20638ee1ecdd24e0932520ad63fe Mon Sep 17 00:00:00 2001
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Date: Sun, 9 Jul 2023 23:57:55 +0530
Subject: [PATCH 0307/1189] perf arch x86: Address shellcheck warnings about
 unused variables in syscalltbl.sh

Running shellcheck on syscalltbl.sh generates below warning:

   In ./tools/perf/arch/x86/entry/syscalls/syscalltbl.sh line 27:
   while read nr abi name entry compat; do
                 ^-^ SC2034 (warning): abi appears unused. Verify use (or export if used externally).
                                ^----^ SC2034 (warning): compat appears unused. Verify use (or export if used externally).

These variables are intentionally unused since they are needed to parse
through the output. Use "_" as a prefix for these throw away variables.

Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230709182800.53002-22-atrajeev@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/x86/entry/syscalls/syscalltbl.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh b/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh
index fa526a993845..59d7914ed6bb 100755
--- a/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh
+++ b/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh
@@ -24,7 +24,7 @@ sorted_table=$(mktemp /tmp/syscalltbl.XXXXXX)
 grep '^[0-9]' "$in" | sort -n > $sorted_table
 
 max_nr=0
-while read nr abi name entry compat; do
+while read nr _abi name entry _compat; do
     if [ $nr -ge 512 ] ; then # discard compat sycalls
         break
     fi

From 3a4367c11884a0be3a74963b37d2b2fe243ee1d4 Mon Sep 17 00:00:00 2001
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Date: Sun, 9 Jul 2023 23:57:56 +0530
Subject: [PATCH 0308/1189] perf tests record+zstd_comp_decomp: Fix the
 shellcheck warnings about word splitting/quoting

Running shellcheck on record+zstd_comp_decomp.sh testcases
throws below warning:

   In tests/shell/record+zstd_comp_decomp.sh line 16:
       	   $perf_tool record -o $trace_file $gflag -z -F 5000 -- \
                                ^---------^ SC2086 (info): Double quote to prevent globbing and word splitting.

   Did you mean:
     	   $perf_tool record -o "$trace_file" $gflag -z -F 5000 -- \

   In tests/shell/record+zstd_comp_decomp.sh line 22:
	   $perf_tool report -i $trace_file --header --stats | \
                                ^---------^ SC2086 (info): Double quote to prevent globbing and word splitting.

Added double quote around file names to fix these
shellcheck reported issues.

Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230709182800.53002-23-atrajeev@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/record+zstd_comp_decomp.sh | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/tools/perf/tests/shell/record+zstd_comp_decomp.sh b/tools/perf/tests/shell/record+zstd_comp_decomp.sh
index 49bd875d5122..8929046e9057 100755
--- a/tools/perf/tests/shell/record+zstd_comp_decomp.sh
+++ b/tools/perf/tests/shell/record+zstd_comp_decomp.sh
@@ -13,25 +13,25 @@ skip_if_no_z_record() {
 collect_z_record() {
 	echo "Collecting compressed record file:"
 	[ "$(uname -m)" != s390x ] && gflag='-g'
-	$perf_tool record -o $trace_file $gflag -z -F 5000 -- \
+	$perf_tool record -o "$trace_file" $gflag -z -F 5000 -- \
 		dd count=500 if=/dev/urandom of=/dev/null
 }
 
 check_compressed_stats() {
 	echo "Checking compressed events stats:"
-	$perf_tool report -i $trace_file --header --stats | \
+	$perf_tool report -i "$trace_file" --header --stats | \
 		grep -E "(# compressed : Zstd,)|(COMPRESSED events:)"
 }
 
 check_compressed_output() {
-	$perf_tool inject -i $trace_file -o $trace_file.decomp &&
-	$perf_tool report -i $trace_file --stdio -F comm,dso,sym | head -n -3 > $trace_file.comp.output &&
-	$perf_tool report -i $trace_file.decomp --stdio -F comm,dso,sym | head -n -3 > $trace_file.decomp.output &&
-	diff $trace_file.comp.output $trace_file.decomp.output
+	$perf_tool inject -i "$trace_file" -o "$trace_file.decomp" &&
+	$perf_tool report -i "$trace_file" --stdio -F comm,dso,sym | head -n -3 > "$trace_file.comp.output" &&
+	$perf_tool report -i "$trace_file.decomp" --stdio -F comm,dso,sym | head -n -3 > "$trace_file.decomp.output" &&
+	diff "$trace_file.comp.output" "$trace_file.decomp.output"
 }
 
 skip_if_no_z_record || exit 2
 collect_z_record && check_compressed_stats && check_compressed_output
 err=$?
-rm -f $trace_file*
+rm -f "$trace_file*"
 exit $err

From 1f14b8af2c9c5ec43a834c960f436721253ff592 Mon Sep 17 00:00:00 2001
From: Kajol Jain <kjain@linux.ibm.com>
Date: Sun, 9 Jul 2023 23:57:57 +0530
Subject: [PATCH 0309/1189] perf tests coresight thread_loop_check_tid_2: Fix
 shellcheck warnings about word splitting/quoting

Running shellcheck on thread_loop_check_tid_2.sh throws below warning:

In tests/shell/coresight/thread_loop_check_tid_2.sh line 8:
. $(dirname $0)/../lib/coresight.sh
  ^-----------^ SC2046 (warning): Quote this to prevent word splitting.

Fixed the warning by adding quotes to avoid word splitting.

Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230709182800.53002-24-atrajeev@linux.vnet.ibm.com
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/coresight/thread_loop_check_tid_2.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/shell/coresight/thread_loop_check_tid_2.sh b/tools/perf/tests/shell/coresight/thread_loop_check_tid_2.sh
index a067145af43c..6346fd5e87c8 100755
--- a/tools/perf/tests/shell/coresight/thread_loop_check_tid_2.sh
+++ b/tools/perf/tests/shell/coresight/thread_loop_check_tid_2.sh
@@ -5,7 +5,7 @@
 # Carsten Haitzler <carsten.haitzler@arm.com>, 2021
 
 TEST="thread_loop"
-. $(dirname $0)/../lib/coresight.sh
+. "$(dirname $0)"/../lib/coresight.sh
 ARGS="2 20"
 DATV="check-tid-2th"
 DATA="$DATD/perf-$TEST-$DATV.data"

From eef1fb50caba2a4c508ffede6e98695c013ca1df Mon Sep 17 00:00:00 2001
From: Kajol Jain <kjain@linux.ibm.com>
Date: Sun, 9 Jul 2023 23:57:58 +0530
Subject: [PATCH 0310/1189] perf tests lib stat_output: Fix shellcheck warning
 about missing shebang

Running shellcheck on stat_output.sh throws below warning:

In tests/shell/lib/stat_output.sh line 1:
^-- SC2148 (error): Tips depend on target shell and yours is unknown. Add a shebang or a 'shell' directive.

Fixed the warning by adding shell directive.

Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230709182800.53002-25-atrajeev@linux.vnet.ibm.com
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/lib/stat_output.sh | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/tests/shell/lib/stat_output.sh b/tools/perf/tests/shell/lib/stat_output.sh
index 698343f0ecf9..3cc158a64326 100644
--- a/tools/perf/tests/shell/lib/stat_output.sh
+++ b/tools/perf/tests/shell/lib/stat_output.sh
@@ -1,3 +1,4 @@
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
 # Return true if perf_event_paranoid is > $1 and not running as root.

From 8439b44abb0c2e6522823e0e20ae21feb882b408 Mon Sep 17 00:00:00 2001
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Date: Sun, 9 Jul 2023 23:57:59 +0530
Subject: [PATCH 0311/1189] perf tests stat+std_output: Fix shellcheck warnings
 about word splitting/quoting

Running shellcheck on stat+csv_output.sh throws below
warning:

   In tests/shell/stat+csv_output.sh line 9:
   . $(dirname $0)/lib/stat_output.sh
     ^-----------^ SC2046 (warning): Quote this to prevent word splitting.

Fixed the warning by adding quotes to avoid word splitting.

Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230709182800.53002-26-atrajeev@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/stat+csv_output.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/shell/stat+csv_output.sh b/tools/perf/tests/shell/stat+csv_output.sh
index 34a0701fee05..d890eb26e914 100755
--- a/tools/perf/tests/shell/stat+csv_output.sh
+++ b/tools/perf/tests/shell/stat+csv_output.sh
@@ -6,7 +6,7 @@
 
 set -e
 
-. $(dirname $0)/lib/stat_output.sh
+. "$(dirname $0)"/lib/stat_output.sh
 
 csv_sep=@
 

From 35578a551b757cd00afe9b81406363f85cab16b2 Mon Sep 17 00:00:00 2001
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Date: Sun, 9 Jul 2023 23:58:00 +0530
Subject: [PATCH 0312/1189] perf tests stat+std_output: Fix shellcheck warnings
 about word splitting/quoting and local variables

Running shellcheck on stat_std_output testcase throws
below warning:

   In tests/shell/stat+std_output.sh line 9:
   . $(dirname $0)/lib/stat_output.sh
     ^-----------^ SC2046 (warning): Quote this to prevent word splitting.

   In tests/shell/stat+std_output.sh line 32:
   	   local -i cnt=0
                    ^-^ SC2034 (warning): cnt appears unused. Verify use (or export if used externally).

Fixed the warning by adding quotes to avoid word splitting
and removed unused variable "cnt" at line 32.

Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230709182800.53002-27-atrajeev@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/stat+std_output.sh | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/tools/perf/tests/shell/stat+std_output.sh b/tools/perf/tests/shell/stat+std_output.sh
index f972b31fa0c2..fb2b10547a11 100755
--- a/tools/perf/tests/shell/stat+std_output.sh
+++ b/tools/perf/tests/shell/stat+std_output.sh
@@ -6,7 +6,7 @@
 
 set -e
 
-. $(dirname $0)/lib/stat_output.sh
+. "$(dirname $0)"/lib/stat_output.sh
 
 stat_output=$(mktemp /tmp/__perf_test.stat_output.std.XXXXX)
 
@@ -28,7 +28,6 @@ trap trap_cleanup EXIT TERM INT
 
 function commachecker()
 {
-	local -i cnt=0
 	local prefix=1
 
 	case "$1"

From ed847e30f001b207013b6136c264454d7560557f Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 1 Aug 2023 09:36:08 -0300
Subject: [PATCH 0313/1189] perf test bpf: Address error about non-null
 argument for epoll_pwait 2nd arg
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

First noticed on Fedora Rawhide:

  tests/bpf.c: In function ‘epoll_pwait_loop’:
  tests/bpf.c:36:17: error: argument 2 null where non-null expected [-Werror=nonnull]
     36 |                 epoll_pwait(-(i + 1), NULL, 0, 0, NULL);
        |                 ^~~~~~~~~~~
  In file included from tests/bpf.c:5:
  /usr/include/sys/epoll.h:134:12: note: in a call to function ‘epoll_pwait’ declared ‘nonnull’
    134 | extern int epoll_pwait (int __epfd, struct epoll_event *__events,
        |            ^~~~~~~~~~~

  [perfbuilder@27cfe44d67ed perf-6.5.0-rc2]$ gcc -v
  Using built-in specs.
  COLLECT_GCC=gcc
  COLLECT_LTO_WRAPPER=/usr/libexec/gcc/x86_64-redhat-linux/13/lto-wrapper
  OFFLOAD_TARGET_NAMES=nvptx-none
  OFFLOAD_TARGET_DEFAULT=1
  Target: x86_64-redhat-linux
  Configured with: ../configure --enable-bootstrap --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,m2,lto --prefix=/usr --mandir=/usr/share/man --infodir=/usr/share/info --with-bugurl=http://bugzilla.redhat.com/bugzilla --enable-shared --enable-threads=posix --enable-checking=release --enable-multilib --with-system-zlib --enable-__cxa_atexit --disable-libunwind-exceptions --enable-gnu-unique-object --enable-linker-build-id --with-gcc-major-version-only --enable-libstdcxx-backtrace --with-libstdcxx-zoneinfo=/usr/share/zoneinfo --with-linker-hash-style=gnu --enable-plugin --enable-initfini-array --with-isl=/builddir/build/BUILD/gcc-13.2.1-20230728/obj-x86_64-redhat-linux/isl-install --enable-offload-targets=nvptx-none --without-cuda-driver --enable-offload-defaulted --enable-gnu-indirect-function --enable-cet --with-tune=generic --with-arch_32=i686 --build=x86_64-redhat-linux --with-build-config=bootstrap-lto --enable-link-serialization=1
  Thread model: posix
  Supported LTO compression algorithms: zlib zstd
  gcc version 13.2.1 20230728 (Red Hat 13.2.1-1) (GCC)
  [perfbuilder@27cfe44d67ed perf-6.5.0-rc2]$

Just add that argument to address this compiler warning.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/ZMj8+bvN86D0ZKiB@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/bpf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 31796f2a80f4..9ccecd873ecd 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -29,11 +29,12 @@
 
 static int epoll_pwait_loop(void)
 {
+	struct epoll_event events;
 	int i;
 
 	/* Should fail NR_ITERS times */
 	for (i = 0; i < NR_ITERS; i++)
-		epoll_pwait(-(i + 1), NULL, 0, 0, NULL);
+		epoll_pwait(-(i + 1), &events, 0, 0, NULL);
 	return 0;
 }
 

From e8ca4f0f8c03330bf912daee6aa258f4d33ee724 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Fri, 28 Jul 2023 23:19:30 +0900
Subject: [PATCH 0314/1189] perf probe: Show correct error message about
 @symbol usage for uprobe

Since @symbol variable access is not supported by uprobe event, it must be
correctly warn user instead of kernel version update.

Committer testing:

With/without the patch:

  [root@quaco ~]# perf probe -x ~/bin/perf -L sigtrap_handler
  <sigtrap_handler@/home/acme/git/perf-tools-next/tools/perf/tests/sigtrap.c:0>
        0  sigtrap_handler(int signum __maybe_unused, siginfo_t *info, void *ucontext __maybe_unused)
        1  {
        2         if (!__atomic_fetch_add(&ctx.signal_count, 1, __ATOMIC_RELAXED))
        3                 ctx.first_siginfo = *info;
        4         __atomic_fetch_sub(&ctx.tids_want_signal, syscall(SYS_gettid), __ATOMIC_RELAXED);
        5  }

           static void *test_thread(void *arg)
           {

  [root@quaco ~]# perf probe -x ~/bin/perf sigtrap_handler:4 "ctx.signal_count"

Without the patch:

  [root@quaco ~]# perf probe -x ~/bin/perf sigtrap_handler:4 "ctx.signal_count"
  Failed to write event: Invalid argument
  Please upgrade your kernel to at least 3.14 to have access to feature @ctx
    Error: Failed to add events.
  [root@quaco ~]#

With the patch:

  [root@quaco ~]#
  Failed to write event: Invalid argument
  @ctx accesses a variable by symbol name, but that is not supported for user application probe.
    Error: Failed to add events.
  [root@quaco ~]#

Reported-by: Arnaldo Carvalho de Melo <acme@kernel.org>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Closes: https://lore.kernel.org/all/ZLWDEjvFjrrEJODp@kernel.org/
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: https://lore.kernel.org/r/169055397023.67089.12693645664676964310.stgit@devnote2
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/probe-event.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 16822a8a540f..2d056f02ae40 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -2800,13 +2800,18 @@ static void warn_uprobe_event_compat(struct probe_trace_event *tev)
 	if (!tev->uprobes || tev->nargs == 0 || !buf)
 		goto out;
 
-	for (i = 0; i < tev->nargs; i++)
-		if (strglobmatch(tev->args[i].value, "[$@+-]*")) {
-			pr_warning("Please upgrade your kernel to at least "
-				   "3.14 to have access to feature %s\n",
+	for (i = 0; i < tev->nargs; i++) {
+		if (strchr(tev->args[i].value, '@')) {
+			pr_warning("%s accesses a variable by symbol name, but that is not supported for user application probe.\n",
 				   tev->args[i].value);
 			break;
 		}
+		if (strglobmatch(tev->args[i].value, "[$+-]*")) {
+			pr_warning("Please upgrade your kernel to at least 3.14 to have access to feature %s\n",
+				   tev->args[i].value);
+			break;
+		}
+	}
 out:
 	free(buf);
 }

From 714b4511114254c9cf143dd31c4d4251129fb0a5 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 31 Jul 2023 22:36:31 -0700
Subject: [PATCH 0315/1189] perf parse-events x86: Avoid sorting
 uops_retired.slots

As topdown.slots may appear as slots it may get confused with
uops_retired.slots which is an invalid perf metric event group leader.

Special case uops_retired.slots to avoid this confusion.

Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Link: https://lore.kernel.org/r/20230801053634.1142634-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/x86/util/evlist.c | 7 ++++---
 tools/perf/arch/x86/util/evsel.c  | 7 +++----
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c
index cbd582182932..b1ce0c52d88d 100644
--- a/tools/perf/arch/x86/util/evlist.c
+++ b/tools/perf/arch/x86/util/evlist.c
@@ -75,11 +75,12 @@ int arch_evlist__add_default_attrs(struct evlist *evlist,
 
 int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs)
 {
-	if (topdown_sys_has_perf_metrics() && evsel__sys_has_perf_metrics(lhs)) {
+	if (topdown_sys_has_perf_metrics() &&
+	    (arch_evsel__must_be_in_group(lhs) || arch_evsel__must_be_in_group(rhs))) {
 		/* Ensure the topdown slots comes first. */
-		if (strcasestr(lhs->name, "slots"))
+		if (strcasestr(lhs->name, "slots") && !strcasestr(lhs->name, "uops_retired.slots"))
 			return -1;
-		if (strcasestr(rhs->name, "slots"))
+		if (strcasestr(rhs->name, "slots") && !strcasestr(rhs->name, "uops_retired.slots"))
 			return 1;
 		/* Followed by topdown events. */
 		if (strcasestr(lhs->name, "topdown") && !strcasestr(rhs->name, "topdown"))
diff --git a/tools/perf/arch/x86/util/evsel.c b/tools/perf/arch/x86/util/evsel.c
index 81d22657922a..090d0f371891 100644
--- a/tools/perf/arch/x86/util/evsel.c
+++ b/tools/perf/arch/x86/util/evsel.c
@@ -40,12 +40,11 @@ bool evsel__sys_has_perf_metrics(const struct evsel *evsel)
 
 bool arch_evsel__must_be_in_group(const struct evsel *evsel)
 {
-	if (!evsel__sys_has_perf_metrics(evsel))
+	if (!evsel__sys_has_perf_metrics(evsel) || !evsel->name ||
+	    strcasestr(evsel->name, "uops_retired.slots"))
 		return false;
 
-	return evsel->name &&
-		(strcasestr(evsel->name, "slots") ||
-		 strcasestr(evsel->name, "topdown"));
+	return strcasestr(evsel->name, "topdown") || strcasestr(evsel->name, "slots");
 }
 
 int arch_evsel__hw_name(struct evsel *evsel, char *bf, size_t size)

From ab0cfb796e03b24584bdb110111f1a290eb0df05 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 31 Jul 2023 22:36:32 -0700
Subject: [PATCH 0316/1189] perf vendor events intel: Update meteorlake to 1.04

1.04 events were released in:

  https://github.com/intel/perfmon/commit/44fe3681501f43fc515577aced8e944b187c8e51

Addition of 51 core events.

Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Link: https://lore.kernel.org/r/20230801053634.1142634-3-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/arch/x86/mapfile.csv    |   2 +-
 .../pmu-events/arch/x86/meteorlake/cache.json | 165 ++++++++++++++++++
 .../arch/x86/meteorlake/floating-point.json   |   8 +
 .../arch/x86/meteorlake/frontend.json         |  56 ++++++
 .../arch/x86/meteorlake/memory.json           |  80 +++++++++
 .../pmu-events/arch/x86/meteorlake/other.json |  16 ++
 .../arch/x86/meteorlake/pipeline.json         | 159 +++++++++++++++++
 7 files changed, 485 insertions(+), 1 deletion(-)

diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index 6650100830c4..9020d7a23c91 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -19,7 +19,7 @@ GenuineIntel-6-3A,v24,ivybridge,core
 GenuineIntel-6-3E,v23,ivytown,core
 GenuineIntel-6-2D,v23,jaketown,core
 GenuineIntel-6-(57|85),v10,knightslanding,core
-GenuineIntel-6-A[AC],v1.03,meteorlake,core
+GenuineIntel-6-A[AC],v1.04,meteorlake,core
 GenuineIntel-6-1[AEF],v3,nehalemep,core
 GenuineIntel-6-2E,v3,nehalemex,core
 GenuineIntel-6-A7,v1.01,rocketlake,core
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/cache.json b/tools/perf/pmu-events/arch/x86/meteorlake/cache.json
index e1ae7c92f38e..1de0200b32f6 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/cache.json
@@ -36,6 +36,15 @@
         "UMask": "0x2",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Number of cycles a demand request has waited due to L1D due to lack of L2 resources.",
+        "EventCode": "0x48",
+        "EventName": "L1D_PEND_MISS.L2_STALLS",
+        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x4",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Number of L1D misses that are outstanding",
         "EventCode": "0x48",
@@ -260,6 +269,15 @@
         "UMask": "0x40",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Cycles when L1D is locked",
+        "EventCode": "0x42",
+        "EventName": "LOCK_CYCLES.CACHE_LOCK_DURATION",
+        "PublicDescription": "This event counts the number of cycles when the L1D is locked. It is a superset of the 0x1 mask (BUS_LOCK_CLOCKS.BUS_LOCK_DURATION).",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Counts the number of cacheable memory requests that miss in the LLC. Counts on a per core basis.",
         "EventCode": "0x2e",
@@ -514,6 +532,17 @@
         "UMask": "0x4",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
+        "Data_LA": "1",
+        "EventCode": "0xd2",
+        "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
+        "PEBS": "1",
+        "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
+        "SampleAfterValue": "20011",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Retired load instructions whose data sources were hits in L3 without snoops required",
         "Data_LA": "1",
@@ -730,6 +759,14 @@
         "UMask": "0x1",
         "Unit": "cpu_atom"
     },
+    {
+        "BriefDescription": "MEM_STORE_RETIRED.L2_HIT",
+        "EventCode": "0x44",
+        "EventName": "MEM_STORE_RETIRED.L2_HIT",
+        "SampleAfterValue": "200003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Counts the number of load ops retired.",
         "Data_LA": "1",
@@ -977,6 +1014,15 @@
         "UMask": "0x8",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Cacheable and Non-Cacheable code read requests",
+        "EventCode": "0x21",
+        "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD",
+        "PublicDescription": "Counts both cacheable and Non-Cacheable code read requests.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x2",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Demand Data Read requests sent to uncore",
         "EventCode": "0x21",
@@ -995,6 +1041,89 @@
         "UMask": "0x4",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
+        "CounterMask": "1",
+        "EventCode": "0x20",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
+        "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x8",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Cycles with offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore.",
+        "CounterMask": "1",
+        "EventCode": "0x20",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD",
+        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Cycles where at least 1 outstanding demand data read request is pending.",
+        "CounterMask": "1",
+        "EventCode": "0x20",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Cycles with offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore.",
+        "CounterMask": "1",
+        "EventCode": "0x20",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
+        "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x4",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD",
+        "EventCode": "0x20",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x8",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore, every cycle.",
+        "EventCode": "0x20",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD",
+        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.",
+        "EventCode": "0x20",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD",
+        "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.   Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.",
+        "CounterMask": "6",
+        "EventCode": "0x20",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Store Read transactions pending for off-core. Highly correlated.",
+        "EventCode": "0x20",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO",
+        "PublicDescription": "Counts the number of off-core outstanding read-for-ownership (RFO) store transactions every cycle. An RFO transaction is considered to be in the Off-core outstanding state between L2 cache miss and transaction completion.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x4",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Counts bus locks, accounts for cache line split locks and UC locks.",
         "EventCode": "0x2c",
@@ -1004,6 +1133,42 @@
         "UMask": "0x10",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Number of PREFETCHNTA instructions executed.",
+        "EventCode": "0x40",
+        "EventName": "SW_PREFETCH_ACCESS.NTA",
+        "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Number of PREFETCHW instructions executed.",
+        "EventCode": "0x40",
+        "EventName": "SW_PREFETCH_ACCESS.PREFETCHW",
+        "PublicDescription": "Counts the number of PREFETCHW instructions executed.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x8",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Number of PREFETCHT0 instructions executed.",
+        "EventCode": "0x40",
+        "EventName": "SW_PREFETCH_ACCESS.T0",
+        "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x2",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.",
+        "EventCode": "0x40",
+        "EventName": "SW_PREFETCH_ACCESS.T1_T2",
+        "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x4",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to an icache miss",
         "EventCode": "0x71",
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/floating-point.json b/tools/perf/pmu-events/arch/x86/meteorlake/floating-point.json
index 616489f0974a..f66506ee37ef 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/floating-point.json
@@ -41,6 +41,14 @@
         "UMask": "0x2",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "FP_ARITH_DISPATCHED.PORT_5",
+        "EventCode": "0xb3",
+        "EventName": "FP_ARITH_DISPATCHED.PORT_5",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x4",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Counts number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
         "EventCode": "0xc7",
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json b/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json
index 0f064518d1c0..8264419500a5 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json
@@ -43,6 +43,14 @@
         "UMask": "0x2",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "DSB_FILL.FB_STALL_OT",
+        "EventCode": "0x62",
+        "EventName": "DSB_FILL.FB_STALL_OT",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x10",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Retired ANT branches",
         "EventCode": "0xc6",
@@ -55,6 +63,30 @@
         "UMask": "0x3",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Retired Instructions who experienced DSB miss.",
+        "EventCode": "0xc6",
+        "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS",
+        "MSRIndex": "0x3F7",
+        "MSRValue": "0x1",
+        "PEBS": "1",
+        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
+        "SampleAfterValue": "100007",
+        "UMask": "0x3",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Retired Instructions who experienced a critical DSB miss.",
+        "EventCode": "0xc6",
+        "EventName": "FRONTEND_RETIRED.DSB_MISS",
+        "MSRIndex": "0x3F7",
+        "MSRValue": "0x11",
+        "PEBS": "1",
+        "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.",
+        "SampleAfterValue": "100007",
+        "UMask": "0x3",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to ITLB miss",
         "EventCode": "0xc6",
@@ -88,6 +120,18 @@
         "UMask": "0x3",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.",
+        "EventCode": "0xc6",
+        "EventName": "FRONTEND_RETIRED.L2_MISS",
+        "MSRIndex": "0x3F7",
+        "MSRValue": "0x13",
+        "PEBS": "1",
+        "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.",
+        "SampleAfterValue": "100007",
+        "UMask": "0x3",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Retired instructions after front-end starvation of at least 1 cycle",
         "EventCode": "0xc6",
@@ -243,6 +287,18 @@
         "UMask": "0x3",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.",
+        "EventCode": "0xc6",
+        "EventName": "FRONTEND_RETIRED.STLB_MISS",
+        "MSRIndex": "0x3F7",
+        "MSRValue": "0x15",
+        "PEBS": "1",
+        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
+        "SampleAfterValue": "100007",
+        "UMask": "0x3",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "FRONTEND_RETIRED.UNKNOWN_BRANCH",
         "EventCode": "0xc6",
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/memory.json b/tools/perf/pmu-events/arch/x86/meteorlake/memory.json
index 67e949b4c789..2605e1d0ba9f 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/memory.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/memory.json
@@ -66,6 +66,15 @@
         "UMask": "0x84",
         "Unit": "cpu_atom"
     },
+    {
+        "BriefDescription": "Number of machine clears due to memory ordering conflicts.",
+        "EventCode": "0xc3",
+        "EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
+        "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture",
+        "SampleAfterValue": "100003",
+        "UMask": "0x2",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.",
         "CounterMask": "3",
@@ -95,6 +104,35 @@
         "UMask": "0x9",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "MEMORY_ORDERING.MD_NUKE",
+        "EventCode": "0x09",
+        "EventName": "MEMORY_ORDERING.MD_NUKE",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts the number of memory ordering machine clears due to memory renaming.",
+        "EventCode": "0x09",
+        "EventName": "MEMORY_ORDERING.MRN_NUKE",
+        "SampleAfterValue": "100003",
+        "UMask": "0x2",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.",
+        "Data_LA": "1",
+        "EventCode": "0xcd",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x400",
+        "PEBS": "2",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.  Reported latency may be longer than just the memory latency.",
+        "SampleAfterValue": "53",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.",
         "Data_LA": "1",
@@ -121,6 +159,19 @@
         "UMask": "0x1",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles.",
+        "Data_LA": "1",
+        "EventCode": "0xcd",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2048",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x800",
+        "PEBS": "2",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles.  Reported latency may be longer than just the memory latency.",
+        "SampleAfterValue": "23",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.",
         "Data_LA": "1",
@@ -235,5 +286,34 @@
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Cycles where data return is pending for a Demand Data Read request who miss L3 cache.",
+        "CounterMask": "1",
+        "EventCode": "0x20",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD",
+        "PublicDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x10",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache.",
+        "EventCode": "0x20",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD",
+        "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache.  Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x10",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Cycles where the core is waiting on at least 6 outstanding demand data read requests known to have missed the L3 cache.",
+        "CounterMask": "6",
+        "EventCode": "0x20",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6",
+        "PublicDescription": "Cycles where the core is waiting on at least 6 outstanding demand data read requests known to have missed the L3 cache.  Note that this event does not capture all elapsed cycles while the requests are outstanding - only cycles from when the requests were known to have missed the L3 cache.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x10",
+        "Unit": "cpu_core"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/other.json b/tools/perf/pmu-events/arch/x86/meteorlake/other.json
index 2ec57f487525..f4c603599df4 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/other.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/other.json
@@ -1,4 +1,12 @@
 [
+    {
+        "BriefDescription": "ASSISTS.PAGE_FAULT",
+        "EventCode": "0xc1",
+        "EventName": "ASSISTS.PAGE_FAULT",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x8",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Counts streaming stores that have any type of response.",
         "EventCode": "0x2A,0x2B",
@@ -30,6 +38,14 @@
         "UMask": "0x7",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "RS.EMPTY_RESOURCE",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY_RESOURCE",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state. For Tremont, UMWAIT and TPAUSE will only put the CPU into C0.1 activity state (not C0.2 activity state)",
         "EventCode": "0x75",
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json b/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json
index eeaa7a97f71c..352c5efafc06 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json
@@ -311,6 +311,16 @@
         "UMask": "0x60",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "This event counts the number of mispredicted ret instructions retired. Non PEBS",
+        "EventCode": "0xc5",
+        "EventName": "BR_MISP_RETIRED.RET",
+        "PEBS": "1",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.",
+        "SampleAfterValue": "100007",
+        "UMask": "0x8",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Counts the number of mispredicted near RET branch instructions retired.",
         "EventCode": "0xc5",
@@ -329,6 +339,33 @@
         "UMask": "0x48",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state.",
+        "EventCode": "0xec",
+        "EventName": "CPU_CLK_UNHALTED.C01",
+        "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x10",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state.",
+        "EventCode": "0xec",
+        "EventName": "CPU_CLK_UNHALTED.C02",
+        "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x20",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Core clocks when the thread is in the C0.1 or C0.2 or running a PAUSE in C0 ACPI state.",
+        "EventCode": "0xec",
+        "EventName": "CPU_CLK_UNHALTED.C0_WAIT",
+        "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x70",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles",
         "EventName": "CPU_CLK_UNHALTED.CORE",
@@ -361,6 +398,24 @@
         "UMask": "0x2",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "CPU_CLK_UNHALTED.PAUSE",
+        "EventCode": "0xec",
+        "EventName": "CPU_CLK_UNHALTED.PAUSE",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x40",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "CPU_CLK_UNHALTED.PAUSE_INST",
+        "CounterMask": "1",
+        "EdgeDetect": "1",
+        "EventCode": "0xec",
+        "EventName": "CPU_CLK_UNHALTED.PAUSE_INST",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x40",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Core crystal clock cycles. Cycle counts are evenly distributed between active threads in the Core.",
         "EventCode": "0x3c",
@@ -602,6 +657,15 @@
         "UMask": "0x10",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Retired NOP instructions.",
+        "EventCode": "0xc0",
+        "EventName": "INST_RETIRED.NOP",
+        "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Precise instruction retired with PEBS precise-distribution",
         "EventName": "INST_RETIRED.PREC_DIST",
@@ -611,6 +675,15 @@
         "UMask": "0x1",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Iterations of Repeat string retired instructions.",
+        "EventCode": "0xc0",
+        "EventName": "INST_RETIRED.REP_ITERATION",
+        "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x8",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Cycles the Backend cluster is recovering after a miss-speculation or a Store Buffer or Load Buffer drain stall.",
         "CounterMask": "1",
@@ -621,6 +694,17 @@
         "UMask": "0x3",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Clears speculative count",
+        "CounterMask": "1",
+        "EdgeDetect": "1",
+        "EventCode": "0xad",
+        "EventName": "INT_MISC.CLEARS_COUNT",
+        "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears",
+        "SampleAfterValue": "500009",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Counts cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.",
         "EventCode": "0xad",
@@ -630,6 +714,15 @@
         "UMask": "0x80",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Cycles when Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the thread",
+        "EventCode": "0xad",
+        "EventName": "INT_MISC.RAT_STALLS",
+        "PublicDescription": "This event counts the number of cycles during which Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the current thread. This also includes the cycles during which the Allocator is serving another thread.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x8",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread",
         "EventCode": "0xad",
@@ -733,6 +826,15 @@
         "UMask": "0x4",
         "Unit": "cpu_atom"
     },
+    {
+        "BriefDescription": "False dependencies in MOB due to partial compare on address.",
+        "EventCode": "0x03",
+        "EventName": "LD_BLOCKS.ADDRESS_ALIAS",
+        "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x4",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Counts the number of retired loads that are blocked because its address exactly matches an older store whose data is not ready.",
         "EventCode": "0x03",
@@ -742,6 +844,15 @@
         "UMask": "0x1",
         "Unit": "cpu_atom"
     },
+    {
+        "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
+        "EventCode": "0x03",
+        "EventName": "LD_BLOCKS.NO_SR",
+        "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x88",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Counts the number of retired loads that are blocked because its address partially overlapped with an older store.",
         "EventCode": "0x03",
@@ -751,6 +862,15 @@
         "UMask": "0x2",
         "Unit": "cpu_atom"
     },
+    {
+        "BriefDescription": "Loads blocked due to overlapping with a preceding store that cannot be forwarded.",
+        "EventCode": "0x03",
+        "EventName": "LD_BLOCKS.STORE_FORWARD",
+        "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x82",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
         "CounterMask": "1",
@@ -823,6 +943,24 @@
         "UMask": "0x1",
         "Unit": "cpu_atom"
     },
+    {
+        "BriefDescription": "Self-modifying code (SMC) detected.",
+        "EventCode": "0xc3",
+        "EventName": "MACHINE_CLEARS.SMC",
+        "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x4",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "LFENCE instructions retired",
+        "EventCode": "0xe0",
+        "EventName": "MISC2_RETIRED.LFENCE",
+        "PublicDescription": "number of LFENCE retired instructions",
+        "SampleAfterValue": "400009",
+        "UMask": "0x20",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Counts cycles where the pipeline is stalled due to serializing operations.",
         "EventCode": "0xa2",
@@ -1260,6 +1398,16 @@
         "UMask": "0x1",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Cycles with retired uop(s).",
+        "CounterMask": "1",
+        "EventCode": "0xc2",
+        "EventName": "UOPS_RETIRED.CYCLES",
+        "PublicDescription": "Counts cycles where at least one uop has retired.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Retired uops except the last uop of each instruction.",
         "EventCode": "0xc2",
@@ -1306,6 +1454,17 @@
         "UMask": "0x2",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Cycles without actually retired uops.",
+        "CounterMask": "1",
+        "EventCode": "0xc2",
+        "EventName": "UOPS_RETIRED.STALLS",
+        "Invert": "1",
+        "PublicDescription": "This event counts cycles without actually retired uops.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Cycles with less than 10 actually retired uops.",
         "CounterMask": "10",

From b691f30700b56fe4fba690e17b1e1b2eb327a589 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 31 Jul 2023 22:36:33 -0700
Subject: [PATCH 0317/1189] perf vendor events intel: Update sapphirerapids to
 1.15

1.15 events were released in:

  https://github.com/intel/perfmon/commit/76dfb81a1148ec049fd9caae9c62529404da63df

Adds the events OCR.DEMAND_DATA_RD.LOCAL_SOCKET_PMM and
OCR.DEMAND_DATA_RD.PMM.

Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Link: https://lore.kernel.org/r/20230801053634.1142634-4-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/arch/x86/mapfile.csv     |  2 +-
 .../arch/x86/sapphirerapids/other.json         | 18 ++++++++++++++++++
 2 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index 9020d7a23c91..3a8770e29fe8 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -24,7 +24,7 @@ GenuineIntel-6-1[AEF],v3,nehalemep,core
 GenuineIntel-6-2E,v3,nehalemex,core
 GenuineIntel-6-A7,v1.01,rocketlake,core
 GenuineIntel-6-2A,v19,sandybridge,core
-GenuineIntel-6-(8F|CF),v1.14,sapphirerapids,core
+GenuineIntel-6-(8F|CF),v1.15,sapphirerapids,core
 GenuineIntel-6-AF,v1.00,sierraforest,core
 GenuineIntel-6-(37|4A|4C|4D|5A),v15,silvermont,core
 GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v57,skylake,core
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/other.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/other.json
index 31b6be9fb8c7..442ef3807a9d 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/other.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/other.json
@@ -76,6 +76,24 @@
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by PMM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts PMM accesses that are controlled by the close or distant SNC Cluster.",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.LOCAL_SOCKET_PMM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x700C00001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by PMM.",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.PMM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x703C00001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
     {
         "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.",
         "EventCode": "0x2A,0x2B",

From 9a7d82c188baea8049e62cc1c92eb5b1846ed4ad Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 31 Jul 2023 22:36:34 -0700
Subject: [PATCH 0318/1189] perf vendor events intel: Update Icelake+ metric
 constraints

Avoid grouping events especially in cases where the kernel's PMU
driver fails to not open the events, causing the events to report back
as "<not counted>".

This update comes from:

  https://github.com/intel/perfmon/pull/94

Fixes issues reported with patch:

  https://lore.kernel.org/lkml/20230719001836.198363-3-irogers@google.com/

Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Link: https://lore.kernel.org/r/20230801053634.1142634-5-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../pmu-events/arch/x86/alderlake/adl-metrics.json    | 11 +++++++----
 .../pmu-events/arch/x86/alderlaken/adln-metrics.json  |  2 ++
 .../perf/pmu-events/arch/x86/icelake/icl-metrics.json | 10 ++++++----
 .../pmu-events/arch/x86/icelakex/icx-metrics.json     | 10 ++++++----
 .../pmu-events/arch/x86/rocketlake/rkl-metrics.json   | 10 ++++++----
 .../arch/x86/sapphirerapids/spr-metrics.json          |  9 +++++----
 .../pmu-events/arch/x86/tigerlake/tgl-metrics.json    | 10 ++++++----
 7 files changed, 38 insertions(+), 24 deletions(-)

diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
index daf9458f0b77..c6780d5c456b 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
@@ -558,6 +558,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the Last Level Cache (LLC) or other core with HITE/F/M.",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ / tma_info_core_clks - max((cpu_atom@MEM_BOUND_STALLS.LOAD@ - cpu_atom@LD_HEAD.L1_MISS_AT_RET@) / tma_info_core_clks, 0) * cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ / cpu_atom@MEM_BOUND_STALLS.LOAD@",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -800,6 +801,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a store forward block.",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
@@ -1058,7 +1060,6 @@
     },
     {
         "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector",
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
@@ -1230,6 +1231,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
@@ -1267,6 +1269,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))",
         "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_info_bottleneck_memory_bandwidth",
@@ -1355,7 +1358,6 @@
     },
     {
         "BriefDescription": "Floating Point Operations Per Cycle",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.SCALAR_DOUBLE@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@) + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / tma_info_core_core_clks",
         "MetricGroup": "Flops;Ret",
         "MetricName": "tma_info_core_flopc",
@@ -1363,7 +1365,6 @@
     },
     {
         "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(cpu_core@FP_ARITH_DISPATCHED.PORT_0@ + cpu_core@FP_ARITH_DISPATCHED.PORT_1@ + cpu_core@FP_ARITH_DISPATCHED.PORT_5@) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
@@ -1769,7 +1770,6 @@
     },
     {
         "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire",
@@ -2002,6 +2002,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -2375,6 +2376,7 @@
     },
     {
         "BriefDescription": "This metric represents rate of split store accesses",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
@@ -2405,6 +2407,7 @@
     },
     {
         "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
index 0f1628d698da..06e67e34e1bf 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
@@ -466,6 +466,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the Last Level Cache (LLC) or other core with HITE/F/M.",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / tma_info_core_clks - max((MEM_BOUND_STALLS.LOAD - LD_HEAD.L1_MISS_AT_RET) / tma_info_core_clks, 0) * MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_BOUND_STALLS.LOAD",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -682,6 +683,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a store forward block.",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
diff --git a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json
index 8fcc05c4e0a1..a6eed0d9a26d 100644
--- a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json
@@ -85,6 +85,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
@@ -319,7 +320,6 @@
     },
     {
         "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector",
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
@@ -464,6 +464,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
@@ -497,6 +498,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))",
         "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_info_bottleneck_memory_bandwidth",
@@ -574,14 +576,12 @@
     },
     {
         "BriefDescription": "Floating Point Operations Per Cycle",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_core_clks",
         "MetricGroup": "Flops;Ret",
         "MetricName": "tma_info_core_flopc"
     },
     {
         "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
@@ -927,7 +927,6 @@
     },
     {
         "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
@@ -1100,6 +1099,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -1419,6 +1419,7 @@
     },
     {
         "BriefDescription": "This metric represents rate of split store accesses",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
@@ -1446,6 +1447,7 @@
     },
     {
         "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
diff --git a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json
index 9bb7e3f20f7f..7082ad5ba961 100644
--- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json
@@ -289,6 +289,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
@@ -523,7 +524,6 @@
     },
     {
         "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector",
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
@@ -668,6 +668,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
@@ -701,6 +702,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))",
         "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_info_bottleneck_memory_bandwidth",
@@ -778,14 +780,12 @@
     },
     {
         "BriefDescription": "Floating Point Operations Per Cycle",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_core_clks",
         "MetricGroup": "Flops;Ret",
         "MetricName": "tma_info_core_flopc"
     },
     {
         "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
@@ -1144,7 +1144,6 @@
     },
     {
         "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
@@ -1369,6 +1368,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -1715,6 +1715,7 @@
     },
     {
         "BriefDescription": "This metric represents rate of split store accesses",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
@@ -1742,6 +1743,7 @@
     },
     {
         "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
diff --git a/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json b/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json
index 1bb9cededa56..a0191c8b708d 100644
--- a/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json
@@ -85,6 +85,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
@@ -319,7 +320,6 @@
     },
     {
         "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector",
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
@@ -464,6 +464,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
@@ -497,6 +498,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))",
         "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_info_bottleneck_memory_bandwidth",
@@ -574,14 +576,12 @@
     },
     {
         "BriefDescription": "Floating Point Operations Per Cycle",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_core_clks",
         "MetricGroup": "Flops;Ret",
         "MetricName": "tma_info_core_flopc"
     },
     {
         "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
@@ -933,7 +933,6 @@
     },
     {
         "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
@@ -1126,6 +1125,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -1445,6 +1445,7 @@
     },
     {
         "BriefDescription": "This metric represents rate of split store accesses",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
@@ -1472,6 +1473,7 @@
     },
     {
         "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
index c207c851a9f9..222212abd811 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
@@ -553,7 +553,6 @@
     },
     {
         "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector + tma_fp_amx",
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
@@ -717,6 +716,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
@@ -750,6 +750,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))",
         "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_info_bottleneck_memory_bandwidth",
@@ -827,14 +828,12 @@
     },
     {
         "BriefDescription": "Floating Point Operations Per Cycle",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + FP_ARITH_INST_RETIRED2.SCALAR_HALF + 2 * (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF) + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * (FP_ARITH_INST_RETIRED2.128B_PACKED_HALF + cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@) + 16 * (FP_ARITH_INST_RETIRED2.256B_PACKED_HALF + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) + 32 * FP_ARITH_INST_RETIRED2.512B_PACKED_HALF + 4 * AMX_OPS_RETIRED.BF16",
         "MetricGroup": "Flops;Ret",
         "MetricName": "tma_info_core_flopc"
     },
     {
         "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(FP_ARITH_DISPATCHED.PORT_0 + FP_ARITH_DISPATCHED.PORT_1 + FP_ARITH_DISPATCHED.PORT_5) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
@@ -1216,7 +1215,6 @@
     },
     {
         "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
@@ -1467,6 +1465,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -1841,6 +1840,7 @@
     },
     {
         "BriefDescription": "This metric represents rate of split store accesses",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
@@ -1868,6 +1868,7 @@
     },
     {
         "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json
index c7c2d6ab1a93..fab084e1bc69 100644
--- a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json
@@ -79,6 +79,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
@@ -313,7 +314,6 @@
     },
     {
         "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector",
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
@@ -458,6 +458,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
@@ -491,6 +492,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))",
         "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_info_bottleneck_memory_bandwidth",
@@ -568,14 +570,12 @@
     },
     {
         "BriefDescription": "Floating Point Operations Per Cycle",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_core_clks",
         "MetricGroup": "Flops;Ret",
         "MetricName": "tma_info_core_flopc"
     },
     {
         "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
@@ -927,7 +927,6 @@
     },
     {
         "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
@@ -1114,6 +1113,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -1433,6 +1433,7 @@
     },
     {
         "BriefDescription": "This metric represents rate of split store accesses",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
@@ -1460,6 +1461,7 @@
     },
     {
         "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",

From a7789d3f2e96ac1056f127d529f9c35e3ce88479 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 2 Aug 2023 10:33:42 -0300
Subject: [PATCH 0319/1189] perf python: Cope with declarations after
 statements found in Python.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

With -Werror the build was failing on fedora rawhide:

  [perfbuilder@27cfe44d67ed perf-6.5.0-rc2]$ gcc -v
  Using built-in specs.
  COLLECT_GCC=gcc
  COLLECT_LTO_WRAPPER=/usr/libexec/gcc/x86_64-redhat-linux/13/lto-wrapper
  OFFLOAD_TARGET_NAMES=nvptx-none
  OFFLOAD_TARGET_DEFAULT=1
  Target: x86_64-redhat-linux
  Configured with: ../configure --enable-bootstrap --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,m2,lto --prefix=/usr --mandir=/usr/share/man --infodir=/usr/share/info --with-bugurl=http://bugzilla.redhat.com/bugzilla --enable-shared --enable-threads=posix --enable-checking=release --enable-multilib --with-system-zlib --enable-__cxa_atexit --disable-libunwind-exceptions --enable-gnu-unique-object --enable-linker-build-id --with-gcc-major-version-only --enable-libstdcxx-backtrace --with-libstdcxx-zoneinfo=/usr/share/zoneinfo --with-linker-hash-style=gnu --enable-plugin --enable-initfini-array --with-isl=/builddir/build/BUILD/gcc-13.2.1-20230728/obj-x86_64-redhat-linux/isl-install --enable-offload-targets=nvptx-none --without-cuda-driver --enable-offload-defaulted --enable-gnu-indirect-function --enable-cet --with-tune=generic --with-arch_32=i686 --build=x86_64-redhat-linux --with-build-config=bootstrap-lto --enable-link-serialization=1
  Thread model: posix
  Supported LTO compression algorithms: zlib zstd
  gcc version 13.2.1 20230728 (Red Hat 13.2.1-1) (GCC)
  [perfbuilder@27cfe44d67ed perf-6.5.0-rc2]$

  In file included from /usr/include/python3.12/Python.h:44,
                   from /git/perf-6.5.0-rc2/tools/perf/util/python.c:2:
  /usr/include/python3.12/object.h: In function ‘Py_SIZE’:
  /usr/include/python3.12/object.h:217:5: error: ISO C90 forbids mixed declarations and code [-Werror=declaration-after-statement]
    217 |     PyVarObject *var_ob = _PyVarObject_CAST(ob);
        |     ^~~~~~~~~~~
    LD      /tmp/build/perf/arch/perf-in.o
  In file included from /usr/include/python3.12/Python.h:53:
  /usr/include/python3.12/cpython/longintrepr.h: In function ‘_PyLong_CompactValue’:
  /usr/include/python3.12/cpython/longintrepr.h:121:5: error: ISO C90 forbids mixed declarations and code [-Werror=declaration-after-statement]
    121 |     Py_ssize_t sign = 1 - (op->long_value.lv_tag & _PyLong_SIGN_MASK);
        |     ^~~~~~~~~~

So add -Wno-declaration-after-statement to the python binding CFLAGS.

Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/ZMpcTMvnQns81YWA@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/setup.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 869738fc06c3..79d5e2955f85 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -66,6 +66,9 @@ if cc_is_clang:
 else:
     cflags += ['-Wno-cast-function-type' ]
 
+# The python headers have mixed code with declarations (decls after asserts, for instance)
+cflags += [ "-Wno-declaration-after-statement" ]
+
 src_perf  = getenv('srctree') + '/tools/perf'
 build_lib = getenv('PYTHON_EXTBUILD_LIB')
 build_tmp = getenv('PYTHON_EXTBUILD_TMP')

From c43888e739bbf184eb95018188215a5487cc0b15 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 2 Aug 2023 10:33:42 -0300
Subject: [PATCH 0320/1189] perf script python: Cope with declarations after
 statements found in Python.h

With -Werror the build was failing on fedora rawhide:

  [perfbuilder@27cfe44d67ed perf-6.5.0-rc2]$ gcc -v
  Using built-in specs.
  COLLECT_GCC=gcc
  COLLECT_LTO_WRAPPER=/usr/libexec/gcc/x86_64-redhat-linux/13/lto-wrapper
  OFFLOAD_TARGET_NAMES=nvptx-none
  OFFLOAD_TARGET_DEFAULT=1
  Target: x86_64-redhat-linux
  Configured with: ../configure --enable-bootstrap --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,m2,lto --prefix=/usr --mandir=/usr/share/man --infodir=/usr/share/info --with-bugurl=http://bugzilla.redhat.com/bugzilla --enable-shared --enable-threads=posix --enable-checking=release --enable-multilib --with-system-zlib --enable-__cxa_atexit --disable-libunwind-exceptions --enable-gnu-unique-object --enable-linker-build-id --with-gcc-major-version-only --enable-libstdcxx-backtrace --with-libstdcxx-zoneinfo=/usr/share/zoneinfo --with-linker-hash-style=gnu --enable-plugin --enable-initfini-array --with-isl=/builddir/build/BUILD/gcc-13.2.1-20230728/obj-x86_64-redhat-linux/isl-install --enable-offload-targets=nvptx-none --without-cuda-driver --enable-offload-defaulted --enable-gnu-indirect-function --enable-cet --with-tune=generic --with-arch_32=i686 --build=x86_64-redhat-linux --with-build-config=bootstrap-lto --enable-link-serialization=1
  Thread model: posix
  Supported LTO compression algorithms: zlib zstd
  gcc version 13.2.1 20230728 (Red Hat 13.2.1-1) (GCC)
  [perfbuilder@27cfe44d67ed perf-6.5.0-rc2]$

  In file included from /usr/include/python3.12/Python.h:44,
                   from scripts/python/Perf-Trace-Util/Context.c:14:
  /usr/include/python3.12/object.h: In function 'Py_SIZE':
  /usr/include/python3.12/object.h:217:5: error: ISO C90 forbids mixed declarations and code [-Werror=declaration-after-statement]
    217 |     PyVarObject *var_ob = _PyVarObject_CAST(ob);
        |     ^~~~~~~~~~~
  In file included from /usr/include/python3.12/Python.h:53:
  /usr/include/python3.12/cpython/longintrepr.h: In function '_PyLong_CompactValue':
  /usr/include/python3.12/cpython/longintrepr.h:121:5: error: ISO C90 forbids mixed declarations and code [-Werror=declaration-after-statement]
    121 |     Py_ssize_t sign = 1 - (op->long_value.lv_tag & _PyLong_SIGN_MASK);
        |     ^~~~~~~~~~
  <SNIP>
  In file included from /usr/include/python3.12/Python.h:44,
                   from util/scripting-engines/trace-event-python.c:22:
  /usr/include/python3.12/object.h: In function 'Py_SIZE':
  /usr/include/python3.12/object.h:217:5: error: ISO C90 forbids mixed declarations and code [-Werror=declaration-after-statement]
    217 |     PyVarObject *var_ob = _PyVarObject_CAST(ob);
        |     ^~~~~~~~~~~
    CC      /tmp/build/perf/util/units.o
    CC      /tmp/build/perf/util/time-utils.o
  In file included from /usr/include/python3.12/Python.h:53:
  /usr/include/python3.12/cpython/longintrepr.h: In function '_PyLong_CompactValue':
  /usr/include/python3.12/cpython/longintrepr.h:121:5: error: ISO C90 forbids mixed declarations and code [-Werror=declaration-after-statement]
    121 |     Py_ssize_t sign = 1 - (op->long_value.lv_tag & _PyLong_SIGN_MASK);
        |     ^~~~~~~~~~

So add -Wno-declaration-after-statement to the python scripting CFLAGS.

Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/ZMpdKeO8gU%2FcWDqH@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/Perf-Trace-Util/Build | 3 ++-
 tools/perf/util/scripting-engines/Build         | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/tools/perf/scripts/python/Perf-Trace-Util/Build b/tools/perf/scripts/python/Perf-Trace-Util/Build
index 7d0e33ce6aba..5b0b5ff7e14a 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/Build
+++ b/tools/perf/scripts/python/Perf-Trace-Util/Build
@@ -1,3 +1,4 @@
 perf-y += Context.o
 
-CFLAGS_Context.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs
+# -Wno-declaration-after-statement: The python headers have mixed code with declarations (decls after asserts, for instance)
+CFLAGS_Context.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs -Wno-declaration-after-statement
diff --git a/tools/perf/util/scripting-engines/Build b/tools/perf/util/scripting-engines/Build
index c220fec97032..586b94e90f4e 100644
--- a/tools/perf/util/scripting-engines/Build
+++ b/tools/perf/util/scripting-engines/Build
@@ -5,4 +5,5 @@ perf-$(CONFIG_LIBPYTHON) += trace-event-python.o
 
 CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-nested-externs -Wno-undef -Wno-switch-default -Wno-bad-function-cast -Wno-declaration-after-statement -Wno-switch-enum
 
-CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-deprecated-declarations -Wno-switch-enum
+# -Wno-declaration-after-statement: The python headers have mixed code with declarations (decls after asserts, for instance)
+CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-deprecated-declarations -Wno-switch-enum -Wno-declaration-after-statement

From 4e95ed4f4d5bc6838a10e6952999b41b1d07e56f Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Tue, 25 Jul 2023 17:03:46 +0200
Subject: [PATCH 0321/1189] perf build: Update feature check for clang and llvm

Perf build auto-detects features and packages already installed for its
build. This is done in directory tools/build/feature. This directory
contains small sample programs. When they successfully compile the
necessary prereqs in form of libraries and header files are present.

Such a check is also done for llvm and clang. And the checks fail.

Fix this and update to the latest C++ standard and use the new library
provided by clang (which contains new packaging) s/ee this link for
reference:

 https://fedoraproject.org/wiki/Changes/Stop-Shipping-Individual-Component-Libraries-In-clang-lib-Package

Output before:
 # rm -f ./test-clang.bin; make test-clang.bin; ./test-clang.bin; \
	ll test-clang.make.output
 g++  -MD -Wall -Werror -o test-clang.bin test-clang.cpp \
	 	> test-clang.make.output 2>&1 -std=gnu++14 \
	-I/usr/include 		\
	-L/usr/lib64		\
	-Wl,--start-group -lclangBasic -lclangDriver	\
	  -lclangFrontend -lclangEdit -lclangLex	\
	  -lclangAST -Wl,--end-group 			\
	-lLLVM-16	\
			\
	> test-clang.make.output 2>&1
 make: *** [Makefile:356: test-clang.bin] Error 1
 -bash: ./test-clang.bin: No such file or directory
 -rw-r--r--. 1 root root 252041 Jul 12 09:56 test-clang.make.output
 #

File test-clang.make.output contains many lines of unreferenced
symbols.

Output after:
 # rm -f ./test-clang.bin; make test-clang.bin; ./test-clang.bin; \
	cat test-clang.make.output
 g++  -MD -Wall -Werror -o test-clang.bin test-clang.cpp \
	 > test-clang.make.output 2>&1 -std=gnu++17	\
	-I/usr/include 		\
	-L/usr/lib64		\
	-Wl,--start-group -lclang-cpp -Wl,--end-group	\
	-lLLVM-16	\
			\
	> test-clang.make.output 2>&1
 #

Committer notes:

Test it in the tools/build/feature directory, and have clang-devel and
llvm-devel installed.

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lore.kernel.org/r/20230725150347.3479291-1-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/build/feature/Makefile | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 2cd6dbbee088..3184f387990a 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -340,7 +340,7 @@ $(OUTPUT)test-jvmti-cmlr.bin:
 	$(BUILD)
 
 $(OUTPUT)test-llvm.bin:
-	$(BUILDXX) -std=gnu++14 				\
+	$(BUILDXX) -std=gnu++17 				\
 		-I$(shell $(LLVM_CONFIG) --includedir) 		\
 		-L$(shell $(LLVM_CONFIG) --libdir)		\
 		$(shell $(LLVM_CONFIG) --libs Core BPF)		\
@@ -348,17 +348,15 @@ $(OUTPUT)test-llvm.bin:
 		> $(@:.bin=.make.output) 2>&1
 
 $(OUTPUT)test-llvm-version.bin:
-	$(BUILDXX) -std=gnu++14					\
+	$(BUILDXX) -std=gnu++17					\
 		-I$(shell $(LLVM_CONFIG) --includedir)		\
 		> $(@:.bin=.make.output) 2>&1
 
 $(OUTPUT)test-clang.bin:
-	$(BUILDXX) -std=gnu++14					\
+	$(BUILDXX) -std=gnu++17					\
 		-I$(shell $(LLVM_CONFIG) --includedir) 		\
 		-L$(shell $(LLVM_CONFIG) --libdir)		\
-		-Wl,--start-group -lclangBasic -lclangDriver	\
-		  -lclangFrontend -lclangEdit -lclangLex	\
-		  -lclangAST -Wl,--end-group 			\
+		-Wl,--start-group -lclang-cpp -Wl,--end-group	\
 		$(shell $(LLVM_CONFIG) --libs Core option)	\
 		$(shell $(LLVM_CONFIG) --system-libs)		\
 		> $(@:.bin=.make.output) 2>&1

From 8fcaea9fd0dabc33f1a18f62aa3cf3d12286cd9f Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Tue, 25 Jul 2023 17:03:47 +0200
Subject: [PATCH 0322/1189] perf build: Support llvm and clang support compiled
 in

Perf build suports llvm and clang support compiled in.
Test case 56 builtin clang support provides a test case
which is always skipped.

Link perf with the latest llvm and clang libraries and
enable this test case.

Use 'make LIBCLANGLLVM=1' to include this support.

V2: Add Library patch before -lclang-cpp

Output before:

  # ./perf test 56
  56: builtin clang support                  :
  56.1: builtin clang compile C source to IR : Skip (not compiled in)
  56.2: builtin clang compile C source to ELF object: Skip (not compiled in)

Output after:

  # ./perf test 56
  56: builtin clang support                          :
  56.1: builtin clang compile C source to IR         : Ok
  56.2: builtin clang compile C source to ELF object : Ok
  #

From Ian Rogers:

  Build tested with LLVM 14 and 15 using:
  BUILD_BPF_SKEL=1 LIBCLANGLLVM=1 LLVM_CONFIG=llvm-config-14
  BUILD_BPF_SKEL=1 LIBCLANGLLVM=1 LLVM_CONFIG=llvm-config-15

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Ian Rogers <irogers@google.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lore.kernel.org/r/20230725150347.3479291-2-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Makefile.config | 2 +-
 tools/perf/Makefile.perf   | 5 +----
 2 files changed, 2 insertions(+), 5 deletions(-)

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index fe7afe6d8529..1bf8dc53641f 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -331,7 +331,7 @@ CORE_CFLAGS += -Wall
 CORE_CFLAGS += -Wextra
 CORE_CFLAGS += -std=gnu11
 
-CXXFLAGS += -std=gnu++14 -fno-exceptions -fno-rtti
+CXXFLAGS += -std=gnu++17 -fno-exceptions -fno-rtti
 CXXFLAGS += -Wall
 CXXFLAGS += -Wextra
 CXXFLAGS += -fno-omit-frame-pointer
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index a44d16ec11ee..0ed7ee0c1665 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -426,10 +426,7 @@ EXTLIBS := $(call filter-out,$(EXCLUDE_EXTLIBS),$(EXTLIBS))
 LIBS = -Wl,--whole-archive $(PERFLIBS) $(EXTRA_PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group
 
 ifeq ($(USE_CLANG), 1)
-  CLANGLIBS_LIST = AST Basic CodeGen Driver Frontend Lex Tooling Edit Sema Analysis Parse Serialization
-  CLANGLIBS_NOEXT_LIST = $(foreach l,$(CLANGLIBS_LIST),$(shell $(LLVM_CONFIG) --libdir)/libclang$(l))
-  LIBCLANG = $(foreach l,$(CLANGLIBS_NOEXT_LIST),$(wildcard $(l).a $(l).so))
-  LIBS += -Wl,--start-group $(LIBCLANG) -Wl,--end-group
+  LIBS += -L$(shell $(LLVM_CONFIG) --libdir) -lclang-cpp
 endif
 
 ifeq ($(USE_LLVM), 1)

From 979e9c9fc9c2a761303585e07fe2699bdd88182f Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 2 Aug 2023 18:22:14 -0300
Subject: [PATCH 0323/1189] perf annotate bpf: Don't enclose non-debug code
 with an assert()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In 616b14b47a86d880 ("perf build: Conditionally define NDEBUG") we
started using NDEBUG=1 when DEBUG=1 isn't present, so code that is
enclosed with assert() is not called.

In dd317df072071903 ("perf build: Make binutil libraries opt in") we
stopped linking against binutils-devel, for licensing reasons.

Recently people asked me why annotation of BPF programs wasn't working,
i.e. this:

  $ perf annotate bpf_prog_5280546344e3f45c_kfree_skb

was returning:

  case SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF:
     scnprintf(buf, buflen, "Please link with binutils's libopcode to enable BPF annotation");

This was on a fedora rpm, so its new enough that I had to try to test by
rebuilding using BUILD_NONDISTRO=1, only to get it segfaulting on me.

This combination made this libopcode function not to be called:

        assert(bfd_check_format(bfdf, bfd_object));

Changing it to:

	if (!bfd_check_format(bfdf, bfd_object))
		abort();

Made it work, looking at this "check" function made me realize it
changes the 'bfdf' internal state, i.e. we better call it.

So stop using assert() on it, just call it and abort if it fails.

Probably it is better to propagate the error, etc, but it seems it is
unlikely to fail from the usage done so far and we really need to stop
using libopcodes, so do the quick fix above and move on.

With it we have BPF annotation back working when built with
BUILD_NONDISTRO=1:

  ⬢[acme@toolbox perf-tools-next]$ perf annotate --stdio2 bpf_prog_5280546344e3f45c_kfree_skb   | head
  No kallsyms or vmlinux with build-id 939bc71a1a51cdc434e60af93c7e734f7d5c0e7e was found
  Samples: 12  of event 'cpu-clock:ppp', 4000 Hz, Event count (approx.): 3000000, [percent: local period]
  bpf_prog_5280546344e3f45c_kfree_skb() bpf_prog_5280546344e3f45c_kfree_skb
  Percent      int kfree_skb(struct trace_event_raw_kfree_skb *args) {
                 nop
   33.33         xchg   %ax,%ax
                 push   %rbp
                 mov    %rsp,%rbp
                 sub    $0x180,%rsp
                 push   %rbx
                 push   %r13
  ⬢[acme@toolbox perf-tools-next]$

Fixes: 6987561c9e86eace ("perf annotate: Enable annotation of BPF programs")
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mohamed Mahmoud <mmahmoud@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Dave Tucker <datucker@redhat.com>
Cc: Derek Barbosa <debarbos@redhat.com>
Cc: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/lkml/ZMrMzoQBe0yqMek1@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/annotate.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index ba988a13dacb..82956adf9963 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1846,8 +1846,11 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 	perf_exe(tpath, sizeof(tpath));
 
 	bfdf = bfd_openr(tpath, NULL);
-	assert(bfdf);
-	assert(bfd_check_format(bfdf, bfd_object));
+	if (bfdf == NULL)
+		abort();
+
+	if (!bfd_check_format(bfdf, bfd_object))
+		abort();
 
 	s = open_memstream(&buf, &buf_size);
 	if (!s) {
@@ -1895,7 +1898,8 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 #else
 	disassemble = disassembler(bfdf);
 #endif
-	assert(disassemble);
+	if (disassemble == NULL)
+		abort();
 
 	fflush(s);
 	do {

From e2cabf2a44791f01c21f8d5189b946926e34142e Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 31 Jul 2023 02:49:32 -0700
Subject: [PATCH 0324/1189] perf hists browser: Fix hierarchy mode header

The commit ef9ff6017e3c4593 ("perf ui browser: Move the extra title
lines from the hists browser") introduced ui_browser__gotorc_title() to
help moving non-title lines easily.  But it missed to update the title
for the hierarchy mode so it won't print the header line on TUI at all.

  $ perf report --hierarchy

Fixes: ef9ff6017e3c4593 ("perf ui browser: Move the extra title lines from the hists browser")
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230731094934.1616495-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/ui/browsers/hists.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index c7ad9e003080..d8b88f10a48d 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1779,7 +1779,7 @@ static void hists_browser__hierarchy_headers(struct hist_browser *browser)
 	hists_browser__scnprintf_hierarchy_headers(browser, headers,
 						   sizeof(headers));
 
-	ui_browser__gotorc(&browser->b, 0, 0);
+	ui_browser__gotorc_title(&browser->b, 0, 0);
 	ui_browser__set_color(&browser->b, HE_COLORSET_ROOT);
 	ui_browser__write_nstring(&browser->b, headers, browser->b.width + 1);
 }

From f6b8436bede3e80226e8b2100279c4450c73806a Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 31 Jul 2023 02:49:33 -0700
Subject: [PATCH 0325/1189] perf hists browser: Fix the number of entries for
 'e' key

The 'e' key is to toggle expand/collapse the selected entry only.  But
the current code has a bug that it only increases the number of entries
by 1 in the hierarchy mode so users cannot move under the current entry
after the key stroke.  This is due to a wrong assumption in the
hist_entry__set_folding().

The commit b33f922651011eff ("perf hists browser: Put hist_entry folding
logic into single function") factored out the code, but actually it
should be handled separately.  The hist_browser__set_folding() is to
update fold state for each entry so it needs to traverse all (child)
entries regardless of the current fold state.  So it increases the
number of entries by 1.

But the hist_entry__set_folding() only cares the currently selected
entry and its all children.  So it should count all unfolded child
entries.  This code is implemented in hist_browser__toggle_fold()
already so we can just call it.

Fixes: b33f922651011eff ("perf hists browser: Put hist_entry folding logic into single function")
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230731094934.1616495-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/ui/browsers/hists.c | 58 ++++++++++++++--------------------
 1 file changed, 24 insertions(+), 34 deletions(-)

diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index d8b88f10a48d..70db5a717905 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -407,11 +407,6 @@ static bool hist_browser__selection_has_children(struct hist_browser *browser)
 	return container_of(ms, struct callchain_list, ms)->has_children;
 }
 
-static bool hist_browser__he_selection_unfolded(struct hist_browser *browser)
-{
-	return browser->he_selection ? browser->he_selection->unfolded : false;
-}
-
 static bool hist_browser__selection_unfolded(struct hist_browser *browser)
 {
 	struct hist_entry *he = browser->he_selection;
@@ -584,8 +579,8 @@ static int hierarchy_set_folding(struct hist_browser *hb, struct hist_entry *he,
 	return n;
 }
 
-static void __hist_entry__set_folding(struct hist_entry *he,
-				      struct hist_browser *hb, bool unfold)
+static void hist_entry__set_folding(struct hist_entry *he,
+				    struct hist_browser *hb, bool unfold)
 {
 	hist_entry__init_have_children(he);
 	he->unfolded = unfold ? he->has_children : false;
@@ -603,34 +598,12 @@ static void __hist_entry__set_folding(struct hist_entry *he,
 		he->nr_rows = 0;
 }
 
-static void hist_entry__set_folding(struct hist_entry *he,
-				    struct hist_browser *browser, bool unfold)
-{
-	double percent;
-
-	percent = hist_entry__get_percent_limit(he);
-	if (he->filtered || percent < browser->min_pcnt)
-		return;
-
-	__hist_entry__set_folding(he, browser, unfold);
-
-	if (!he->depth || unfold)
-		browser->nr_hierarchy_entries++;
-	if (he->leaf)
-		browser->nr_callchain_rows += he->nr_rows;
-	else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) {
-		browser->nr_hierarchy_entries++;
-		he->has_no_entry = true;
-		he->nr_rows = 1;
-	} else
-		he->has_no_entry = false;
-}
-
 static void
 __hist_browser__set_folding(struct hist_browser *browser, bool unfold)
 {
 	struct rb_node *nd;
 	struct hist_entry *he;
+	double percent;
 
 	nd = rb_first_cached(&browser->hists->entries);
 	while (nd) {
@@ -640,6 +613,21 @@ __hist_browser__set_folding(struct hist_browser *browser, bool unfold)
 		nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD);
 
 		hist_entry__set_folding(he, browser, unfold);
+
+		percent = hist_entry__get_percent_limit(he);
+		if (he->filtered || percent < browser->min_pcnt)
+			continue;
+
+		if (!he->depth || unfold)
+			browser->nr_hierarchy_entries++;
+		if (he->leaf)
+			browser->nr_callchain_rows += he->nr_rows;
+		else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) {
+			browser->nr_hierarchy_entries++;
+			he->has_no_entry = true;
+			he->nr_rows = 1;
+		} else
+			he->has_no_entry = false;
 	}
 }
 
@@ -659,8 +647,10 @@ static void hist_browser__set_folding_selected(struct hist_browser *browser, boo
 	if (!browser->he_selection)
 		return;
 
-	hist_entry__set_folding(browser->he_selection, browser, unfold);
-	browser->b.nr_entries = hist_browser__nr_entries(browser);
+	if (unfold == browser->he_selection->unfolded)
+		return;
+
+	hist_browser__toggle_fold(browser);
 }
 
 static void ui_browser__warn_lost_events(struct ui_browser *browser)
@@ -732,8 +722,8 @@ static int hist_browser__handle_hotkey(struct hist_browser *browser, bool warn_l
 		hist_browser__set_folding(browser, true);
 		break;
 	case 'e':
-		/* Expand the selected entry. */
-		hist_browser__set_folding_selected(browser, !hist_browser__he_selection_unfolded(browser));
+		/* Toggle expand/collapse the selected entry. */
+		hist_browser__toggle_fold(browser);
 		break;
 	case 'H':
 		browser->show_headers = !browser->show_headers;

From b23c83ad2c638420ec0608a9de354507c41bec29 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 21 Jul 2023 13:18:41 -0700
Subject: [PATCH 0326/1189] x86/reboot: VMCLEAR active VMCSes before emergency
 reboot

VMCLEAR active VMCSes before any emergency reboot, not just if the kernel
may kexec into a new kernel after a crash.  Per Intel's SDM, the VMX
architecture doesn't require the CPU to flush the VMCS cache on INIT.  If
an emergency reboot doesn't RESET CPUs, cached VMCSes could theoretically
be kept and only be written back to memory after the new kernel is booted,
i.e. could effectively corrupt memory after reboot.

Opportunistically remove the setting of the global pointer to NULL to make
checkpatch happy.

Cc: Andrew Cooper <Andrew.Cooper3@citrix.com>
Link: https://lore.kernel.org/r/20230721201859.2307736-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/kexec.h  |  2 --
 arch/x86/include/asm/reboot.h |  2 ++
 arch/x86/kernel/crash.c       | 31 -------------------------------
 arch/x86/kernel/reboot.c      | 22 ++++++++++++++++++++++
 arch/x86/kvm/vmx/vmx.c        | 10 +++-------
 5 files changed, 27 insertions(+), 40 deletions(-)

diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index 5b77bbc28f96..819046974b99 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -205,8 +205,6 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image);
 #endif
 #endif
 
-typedef void crash_vmclear_fn(void);
-extern crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss;
 extern void kdump_nmi_shootdown_cpus(void);
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h
index 9177b4354c3f..dc201724a643 100644
--- a/arch/x86/include/asm/reboot.h
+++ b/arch/x86/include/asm/reboot.h
@@ -25,6 +25,8 @@ void __noreturn machine_real_restart(unsigned int type);
 #define MRR_BIOS	0
 #define MRR_APM		1
 
+typedef void crash_vmclear_fn(void);
+extern crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss;
 void cpu_emergency_disable_virtualization(void);
 
 typedef void (*nmi_shootdown_cb)(int, struct pt_regs*);
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index cdd92ab43cda..54cd959cb316 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -48,38 +48,12 @@ struct crash_memmap_data {
 	unsigned int type;
 };
 
-/*
- * This is used to VMCLEAR all VMCSs loaded on the
- * processor. And when loading kvm_intel module, the
- * callback function pointer will be assigned.
- *
- * protected by rcu.
- */
-crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss = NULL;
-EXPORT_SYMBOL_GPL(crash_vmclear_loaded_vmcss);
-
-static inline void cpu_crash_vmclear_loaded_vmcss(void)
-{
-	crash_vmclear_fn *do_vmclear_operation = NULL;
-
-	rcu_read_lock();
-	do_vmclear_operation = rcu_dereference(crash_vmclear_loaded_vmcss);
-	if (do_vmclear_operation)
-		do_vmclear_operation();
-	rcu_read_unlock();
-}
-
 #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)
 
 static void kdump_nmi_callback(int cpu, struct pt_regs *regs)
 {
 	crash_save_cpu(regs, cpu);
 
-	/*
-	 * VMCLEAR VMCSs loaded on all cpus if needed.
-	 */
-	cpu_crash_vmclear_loaded_vmcss();
-
 	/*
 	 * Disable Intel PT to stop its logging
 	 */
@@ -133,11 +107,6 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
 
 	crash_smp_send_stop();
 
-	/*
-	 * VMCLEAR VMCSs loaded on this cpu if needed.
-	 */
-	cpu_crash_vmclear_loaded_vmcss();
-
 	cpu_emergency_disable_virtualization();
 
 	/*
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 3adbe97015c1..3fa4c6717a1d 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -787,6 +787,26 @@ void machine_crash_shutdown(struct pt_regs *regs)
 }
 #endif
 
+/*
+ * This is used to VMCLEAR all VMCSs loaded on the
+ * processor. And when loading kvm_intel module, the
+ * callback function pointer will be assigned.
+ *
+ * protected by rcu.
+ */
+crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss;
+EXPORT_SYMBOL_GPL(crash_vmclear_loaded_vmcss);
+
+static inline void cpu_crash_vmclear_loaded_vmcss(void)
+{
+	crash_vmclear_fn *do_vmclear_operation = NULL;
+
+	rcu_read_lock();
+	do_vmclear_operation = rcu_dereference(crash_vmclear_loaded_vmcss);
+	if (do_vmclear_operation)
+		do_vmclear_operation();
+	rcu_read_unlock();
+}
 
 /* This is the CPU performing the emergency shutdown work. */
 int crashing_cpu = -1;
@@ -798,6 +818,8 @@ int crashing_cpu = -1;
  */
 void cpu_emergency_disable_virtualization(void)
 {
+	cpu_crash_vmclear_loaded_vmcss();
+
 	cpu_emergency_vmxoff();
 	cpu_emergency_svm_disable();
 }
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index e6d1ce2d230c..75351477f090 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -41,7 +41,7 @@
 #include <asm/idtentry.h>
 #include <asm/io.h>
 #include <asm/irq_remapping.h>
-#include <asm/kexec.h>
+#include <asm/reboot.h>
 #include <asm/perf_event.h>
 #include <asm/mmu_context.h>
 #include <asm/mshyperv.h>
@@ -725,7 +725,6 @@ static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx,
 	return ret;
 }
 
-#ifdef CONFIG_KEXEC_CORE
 static void crash_vmclear_local_loaded_vmcss(void)
 {
 	int cpu = raw_smp_processor_id();
@@ -735,7 +734,6 @@ static void crash_vmclear_local_loaded_vmcss(void)
 			    loaded_vmcss_on_cpu_link)
 		vmcs_clear(v->vmcs);
 }
-#endif /* CONFIG_KEXEC_CORE */
 
 static void __loaded_vmcs_clear(void *arg)
 {
@@ -8573,10 +8571,9 @@ static void __vmx_exit(void)
 {
 	allow_smaller_maxphyaddr = false;
 
-#ifdef CONFIG_KEXEC_CORE
 	RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL);
 	synchronize_rcu();
-#endif
+
 	vmx_cleanup_l1d_flush();
 }
 
@@ -8623,10 +8620,9 @@ static int __init vmx_init(void)
 		pi_init_cpu(cpu);
 	}
 
-#ifdef CONFIG_KEXEC_CORE
 	rcu_assign_pointer(crash_vmclear_loaded_vmcss,
 			   crash_vmclear_local_loaded_vmcss);
-#endif
+
 	vmx_check_vmcs12_offsets();
 
 	/*

From 5e408396c60cd0f0b53a43713016b6d6af8d69e0 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 21 Jul 2023 13:18:42 -0700
Subject: [PATCH 0327/1189] x86/reboot: Harden virtualization hooks for
 emergency reboot

Provide dedicated helpers to (un)register virt hooks used during an
emergency crash/reboot, and WARN if there is an attempt to overwrite
the registered callback, or an attempt to do an unpaired unregister.

Opportunsitically use rcu_assign_pointer() instead of RCU_INIT_POINTER(),
mainly so that the set/unset paths are more symmetrical, but also because
any performance gains from using RCU_INIT_POINTER() are meaningless for
this code.

Reviewed-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/r/20230721201859.2307736-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/reboot.h |  5 +++--
 arch/x86/kernel/reboot.c      | 30 ++++++++++++++++++++++++------
 arch/x86/kvm/vmx/vmx.c        |  6 ++----
 3 files changed, 29 insertions(+), 12 deletions(-)

diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h
index dc201724a643..74c6a624d166 100644
--- a/arch/x86/include/asm/reboot.h
+++ b/arch/x86/include/asm/reboot.h
@@ -25,8 +25,9 @@ void __noreturn machine_real_restart(unsigned int type);
 #define MRR_BIOS	0
 #define MRR_APM		1
 
-typedef void crash_vmclear_fn(void);
-extern crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss;
+typedef void (cpu_emergency_virt_cb)(void);
+void cpu_emergency_register_virt_callback(cpu_emergency_virt_cb *callback);
+void cpu_emergency_unregister_virt_callback(cpu_emergency_virt_cb *callback);
 void cpu_emergency_disable_virtualization(void);
 
 typedef void (*nmi_shootdown_cb)(int, struct pt_regs*);
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 3fa4c6717a1d..62ccedeb5e2b 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -794,17 +794,35 @@ void machine_crash_shutdown(struct pt_regs *regs)
  *
  * protected by rcu.
  */
-crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss;
-EXPORT_SYMBOL_GPL(crash_vmclear_loaded_vmcss);
+static cpu_emergency_virt_cb __rcu *cpu_emergency_virt_callback;
+
+void cpu_emergency_register_virt_callback(cpu_emergency_virt_cb *callback)
+{
+	if (WARN_ON_ONCE(rcu_access_pointer(cpu_emergency_virt_callback)))
+		return;
+
+	rcu_assign_pointer(cpu_emergency_virt_callback, callback);
+}
+EXPORT_SYMBOL_GPL(cpu_emergency_register_virt_callback);
+
+void cpu_emergency_unregister_virt_callback(cpu_emergency_virt_cb *callback)
+{
+	if (WARN_ON_ONCE(rcu_access_pointer(cpu_emergency_virt_callback) != callback))
+		return;
+
+	rcu_assign_pointer(cpu_emergency_virt_callback, NULL);
+	synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(cpu_emergency_unregister_virt_callback);
 
 static inline void cpu_crash_vmclear_loaded_vmcss(void)
 {
-	crash_vmclear_fn *do_vmclear_operation = NULL;
+	cpu_emergency_virt_cb *callback;
 
 	rcu_read_lock();
-	do_vmclear_operation = rcu_dereference(crash_vmclear_loaded_vmcss);
-	if (do_vmclear_operation)
-		do_vmclear_operation();
+	callback = rcu_dereference(cpu_emergency_virt_callback);
+	if (callback)
+		callback();
 	rcu_read_unlock();
 }
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 75351477f090..661ba09685b8 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -8571,8 +8571,7 @@ static void __vmx_exit(void)
 {
 	allow_smaller_maxphyaddr = false;
 
-	RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL);
-	synchronize_rcu();
+	cpu_emergency_unregister_virt_callback(crash_vmclear_local_loaded_vmcss);
 
 	vmx_cleanup_l1d_flush();
 }
@@ -8620,8 +8619,7 @@ static int __init vmx_init(void)
 		pi_init_cpu(cpu);
 	}
 
-	rcu_assign_pointer(crash_vmclear_loaded_vmcss,
-			   crash_vmclear_local_loaded_vmcss);
+	cpu_emergency_register_virt_callback(crash_vmclear_local_loaded_vmcss);
 
 	vmx_check_vmcs12_offsets();
 

From 119b5cb4ffd0166f3e98e9ee042f5046f7744f28 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 21 Jul 2023 13:18:43 -0700
Subject: [PATCH 0328/1189] x86/reboot: KVM: Handle VMXOFF in KVM's reboot
 callback

Use KVM VMX's reboot/crash callback to do VMXOFF in an emergency instead
of manually and blindly doing VMXOFF.  There's no need to attempt VMXOFF
if a hypervisor, i.e. KVM, isn't loaded/active, i.e. if the CPU can't
possibly be post-VMXON.

Reviewed-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/r/20230721201859.2307736-4-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/virtext.h | 10 ----------
 arch/x86/kernel/reboot.c       | 29 +++++++++--------------------
 arch/x86/kvm/vmx/vmx.c         |  8 +++++---
 3 files changed, 14 insertions(+), 33 deletions(-)

diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index 3b12e6b99412..5bc29fab15da 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -70,16 +70,6 @@ static inline void __cpu_emergency_vmxoff(void)
 		cpu_vmxoff();
 }
 
-/** Disable VMX if it is supported and enabled on the current CPU
- */
-static inline void cpu_emergency_vmxoff(void)
-{
-	if (cpu_has_vmx())
-		__cpu_emergency_vmxoff();
-}
-
-
-
 
 /*
  * SVM functions:
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 62ccedeb5e2b..d2d0f2672a64 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -787,13 +787,7 @@ void machine_crash_shutdown(struct pt_regs *regs)
 }
 #endif
 
-/*
- * This is used to VMCLEAR all VMCSs loaded on the
- * processor. And when loading kvm_intel module, the
- * callback function pointer will be assigned.
- *
- * protected by rcu.
- */
+/* RCU-protected callback to disable virtualization prior to reboot. */
 static cpu_emergency_virt_cb __rcu *cpu_emergency_virt_callback;
 
 void cpu_emergency_register_virt_callback(cpu_emergency_virt_cb *callback)
@@ -815,17 +809,6 @@ void cpu_emergency_unregister_virt_callback(cpu_emergency_virt_cb *callback)
 }
 EXPORT_SYMBOL_GPL(cpu_emergency_unregister_virt_callback);
 
-static inline void cpu_crash_vmclear_loaded_vmcss(void)
-{
-	cpu_emergency_virt_cb *callback;
-
-	rcu_read_lock();
-	callback = rcu_dereference(cpu_emergency_virt_callback);
-	if (callback)
-		callback();
-	rcu_read_unlock();
-}
-
 /* This is the CPU performing the emergency shutdown work. */
 int crashing_cpu = -1;
 
@@ -836,9 +819,15 @@ int crashing_cpu = -1;
  */
 void cpu_emergency_disable_virtualization(void)
 {
-	cpu_crash_vmclear_loaded_vmcss();
+	cpu_emergency_virt_cb *callback;
 
-	cpu_emergency_vmxoff();
+	rcu_read_lock();
+	callback = rcu_dereference(cpu_emergency_virt_callback);
+	if (callback)
+		callback();
+	rcu_read_unlock();
+
+	/* KVM_AMD doesn't yet utilize the common callback. */
 	cpu_emergency_svm_disable();
 }
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 661ba09685b8..df991f15baf4 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -725,7 +725,7 @@ static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx,
 	return ret;
 }
 
-static void crash_vmclear_local_loaded_vmcss(void)
+static void vmx_emergency_disable(void)
 {
 	int cpu = raw_smp_processor_id();
 	struct loaded_vmcs *v;
@@ -733,6 +733,8 @@ static void crash_vmclear_local_loaded_vmcss(void)
 	list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu),
 			    loaded_vmcss_on_cpu_link)
 		vmcs_clear(v->vmcs);
+
+	__cpu_emergency_vmxoff();
 }
 
 static void __loaded_vmcs_clear(void *arg)
@@ -8571,7 +8573,7 @@ static void __vmx_exit(void)
 {
 	allow_smaller_maxphyaddr = false;
 
-	cpu_emergency_unregister_virt_callback(crash_vmclear_local_loaded_vmcss);
+	cpu_emergency_unregister_virt_callback(vmx_emergency_disable);
 
 	vmx_cleanup_l1d_flush();
 }
@@ -8619,7 +8621,7 @@ static int __init vmx_init(void)
 		pi_init_cpu(cpu);
 	}
 
-	cpu_emergency_register_virt_callback(crash_vmclear_local_loaded_vmcss);
+	cpu_emergency_register_virt_callback(vmx_emergency_disable);
 
 	vmx_check_vmcs12_offsets();
 

From baeb4de7ad12b700a91f2a7be8e1c0389a5c8fd4 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 21 Jul 2023 13:18:44 -0700
Subject: [PATCH 0329/1189] x86/reboot: KVM: Disable SVM during reboot via
 virt/KVM reboot callback

Use the virt callback to disable SVM (and set GIF=1) during an emergency
instead of blindly attempting to disable SVM.  Like the VMX case, if a
hypervisor, i.e. KVM, isn't loaded/active, SVM can't be in use.

Acked-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/r/20230721201859.2307736-5-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/virtext.h |  8 --------
 arch/x86/kernel/reboot.c       |  3 ---
 arch/x86/kvm/svm/svm.c         | 19 +++++++++++++++++--
 3 files changed, 17 insertions(+), 13 deletions(-)

diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index 5bc29fab15da..aaed66249ccf 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -133,12 +133,4 @@ fault:
 	}
 }
 
-/** Makes sure SVM is disabled, if it is supported on the CPU
- */
-static inline void cpu_emergency_svm_disable(void)
-{
-	if (cpu_has_svm(NULL))
-		cpu_svm_disable();
-}
-
 #endif /* _ASM_X86_VIRTEX_H */
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index d2d0f2672a64..48ad2d1ff83d 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -826,9 +826,6 @@ void cpu_emergency_disable_virtualization(void)
 	if (callback)
 		callback();
 	rcu_read_unlock();
-
-	/* KVM_AMD doesn't yet utilize the common callback. */
-	cpu_emergency_svm_disable();
 }
 
 #if defined(CONFIG_SMP)
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index d381ad424554..1ae9c2c7eacb 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -39,6 +39,7 @@
 #include <asm/spec-ctrl.h>
 #include <asm/cpu_device_id.h>
 #include <asm/traps.h>
+#include <asm/reboot.h>
 #include <asm/fpu/api.h>
 
 #include <asm/virtext.h>
@@ -563,6 +564,11 @@ out:
 	preempt_enable();
 }
 
+static void svm_emergency_disable(void)
+{
+	cpu_svm_disable();
+}
+
 static void svm_hardware_disable(void)
 {
 	/* Make sure we clean up behind us */
@@ -5209,6 +5215,13 @@ static struct kvm_x86_init_ops svm_init_ops __initdata = {
 	.pmu_ops = &amd_pmu_ops,
 };
 
+static void __svm_exit(void)
+{
+	kvm_x86_vendor_exit();
+
+	cpu_emergency_unregister_virt_callback(svm_emergency_disable);
+}
+
 static int __init svm_init(void)
 {
 	int r;
@@ -5222,6 +5235,8 @@ static int __init svm_init(void)
 	if (r)
 		return r;
 
+	cpu_emergency_register_virt_callback(svm_emergency_disable);
+
 	/*
 	 * Common KVM initialization _must_ come last, after this, /dev/kvm is
 	 * exposed to userspace!
@@ -5234,14 +5249,14 @@ static int __init svm_init(void)
 	return 0;
 
 err_kvm_init:
-	kvm_x86_vendor_exit();
+	__svm_exit();
 	return r;
 }
 
 static void __exit svm_exit(void)
 {
 	kvm_exit();
-	kvm_x86_vendor_exit();
+	__svm_exit();
 }
 
 module_init(svm_init)

From ad93c1a7c0102c93e92bf0c06412a1f588e015ab Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 21 Jul 2023 13:18:45 -0700
Subject: [PATCH 0330/1189] x86/reboot: Assert that IRQs are disabled when
 turning off virtualization

Assert that IRQs are disabled when turning off virtualization in an
emergency.  KVM enables hardware via on_each_cpu(), i.e. could re-enable
hardware if a pending IPI were delivered after disabling virtualization.

Remove a misleading comment from emergency_reboot_disable_virtualization()
about "just" needing to guarantee the CPU is stable (see above).

Reviewed-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/r/20230721201859.2307736-6-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kernel/reboot.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 48ad2d1ff83d..4cad7183b89e 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -532,7 +532,6 @@ static inline void nmi_shootdown_cpus_on_restart(void);
 
 static void emergency_reboot_disable_virtualization(void)
 {
-	/* Just make sure we won't change CPUs while doing this */
 	local_irq_disable();
 
 	/*
@@ -821,6 +820,13 @@ void cpu_emergency_disable_virtualization(void)
 {
 	cpu_emergency_virt_cb *callback;
 
+	/*
+	 * IRQs must be disabled as KVM enables virtualization in hardware via
+	 * function call IPIs, i.e. IRQs need to be disabled to guarantee
+	 * virtualization stays disabled.
+	 */
+	lockdep_assert_irqs_disabled();
+
 	rcu_read_lock();
 	callback = rcu_dereference(cpu_emergency_virt_callback);
 	if (callback)

From edc8deb087d884bac2f7013f0c23af73042b23a7 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 21 Jul 2023 13:18:46 -0700
Subject: [PATCH 0331/1189] x86/reboot: Hoist "disable virt" helpers above
 "emergency reboot" path

Move the various "disable virtualization" helpers above the emergency
reboot path so that emergency_reboot_disable_virtualization() can be
stubbed out in a future patch if neither KVM_INTEL nor KVM_AMD is enabled,
i.e. if there is no in-tree user of CPU virtualization.

No functional change intended.

Reviewed-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/r/20230721201859.2307736-7-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kernel/reboot.c | 90 ++++++++++++++++++++--------------------
 1 file changed, 45 insertions(+), 45 deletions(-)

diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 4cad7183b89e..85cb2dfcb67b 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -530,6 +530,51 @@ static inline void kb_wait(void)
 
 static inline void nmi_shootdown_cpus_on_restart(void);
 
+/* RCU-protected callback to disable virtualization prior to reboot. */
+static cpu_emergency_virt_cb __rcu *cpu_emergency_virt_callback;
+
+void cpu_emergency_register_virt_callback(cpu_emergency_virt_cb *callback)
+{
+	if (WARN_ON_ONCE(rcu_access_pointer(cpu_emergency_virt_callback)))
+		return;
+
+	rcu_assign_pointer(cpu_emergency_virt_callback, callback);
+}
+EXPORT_SYMBOL_GPL(cpu_emergency_register_virt_callback);
+
+void cpu_emergency_unregister_virt_callback(cpu_emergency_virt_cb *callback)
+{
+	if (WARN_ON_ONCE(rcu_access_pointer(cpu_emergency_virt_callback) != callback))
+		return;
+
+	rcu_assign_pointer(cpu_emergency_virt_callback, NULL);
+	synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(cpu_emergency_unregister_virt_callback);
+
+/*
+ * Disable virtualization, i.e. VMX or SVM, to ensure INIT is recognized during
+ * reboot.  VMX blocks INIT if the CPU is post-VMXON, and SVM blocks INIT if
+ * GIF=0, i.e. if the crash occurred between CLGI and STGI.
+ */
+void cpu_emergency_disable_virtualization(void)
+{
+	cpu_emergency_virt_cb *callback;
+
+	/*
+	 * IRQs must be disabled as KVM enables virtualization in hardware via
+	 * function call IPIs, i.e. IRQs need to be disabled to guarantee
+	 * virtualization stays disabled.
+	 */
+	lockdep_assert_irqs_disabled();
+
+	rcu_read_lock();
+	callback = rcu_dereference(cpu_emergency_virt_callback);
+	if (callback)
+		callback();
+	rcu_read_unlock();
+}
+
 static void emergency_reboot_disable_virtualization(void)
 {
 	local_irq_disable();
@@ -786,54 +831,9 @@ void machine_crash_shutdown(struct pt_regs *regs)
 }
 #endif
 
-/* RCU-protected callback to disable virtualization prior to reboot. */
-static cpu_emergency_virt_cb __rcu *cpu_emergency_virt_callback;
-
-void cpu_emergency_register_virt_callback(cpu_emergency_virt_cb *callback)
-{
-	if (WARN_ON_ONCE(rcu_access_pointer(cpu_emergency_virt_callback)))
-		return;
-
-	rcu_assign_pointer(cpu_emergency_virt_callback, callback);
-}
-EXPORT_SYMBOL_GPL(cpu_emergency_register_virt_callback);
-
-void cpu_emergency_unregister_virt_callback(cpu_emergency_virt_cb *callback)
-{
-	if (WARN_ON_ONCE(rcu_access_pointer(cpu_emergency_virt_callback) != callback))
-		return;
-
-	rcu_assign_pointer(cpu_emergency_virt_callback, NULL);
-	synchronize_rcu();
-}
-EXPORT_SYMBOL_GPL(cpu_emergency_unregister_virt_callback);
-
 /* This is the CPU performing the emergency shutdown work. */
 int crashing_cpu = -1;
 
-/*
- * Disable virtualization, i.e. VMX or SVM, to ensure INIT is recognized during
- * reboot.  VMX blocks INIT if the CPU is post-VMXON, and SVM blocks INIT if
- * GIF=0, i.e. if the crash occurred between CLGI and STGI.
- */
-void cpu_emergency_disable_virtualization(void)
-{
-	cpu_emergency_virt_cb *callback;
-
-	/*
-	 * IRQs must be disabled as KVM enables virtualization in hardware via
-	 * function call IPIs, i.e. IRQs need to be disabled to guarantee
-	 * virtualization stays disabled.
-	 */
-	lockdep_assert_irqs_disabled();
-
-	rcu_read_lock();
-	callback = rcu_dereference(cpu_emergency_virt_callback);
-	if (callback)
-		callback();
-	rcu_read_unlock();
-}
-
 #if defined(CONFIG_SMP)
 
 static nmi_shootdown_cb shootdown_callback;

From 59765db5fc82726b32876b794667e2c6936a98ab Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 21 Jul 2023 13:18:47 -0700
Subject: [PATCH 0332/1189] x86/reboot: Disable virtualization during reboot
 iff callback is registered

Attempt to disable virtualization during an emergency reboot if and only
if there is a registered virt callback, i.e. iff a hypervisor (KVM) is
active.  If there's no active hypervisor, then the CPU can't be operating
with VMX or SVM enabled (barring an egregious bug).

Checking for a valid callback instead of simply for SVM or VMX support
can also eliminates spurious NMIs by avoiding the unecessary call to
nmi_shootdown_cpus_on_restart().

Note, IRQs are disabled, which prevents KVM from coming along and
enabling virtualization after the fact.

Reviewed-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/r/20230721201859.2307736-8-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kernel/reboot.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 85cb2dfcb67b..98e5db3fd7f4 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -22,7 +22,6 @@
 #include <asm/reboot_fixups.h>
 #include <asm/reboot.h>
 #include <asm/pci_x86.h>
-#include <asm/virtext.h>
 #include <asm/cpu.h>
 #include <asm/nmi.h>
 #include <asm/smp.h>
@@ -589,7 +588,7 @@ static void emergency_reboot_disable_virtualization(void)
 	 * Do the NMI shootdown even if virtualization is off on _this_ CPU, as
 	 * other CPUs may have virtualization enabled.
 	 */
-	if (cpu_has_vmx() || cpu_has_svm(NULL)) {
+	if (rcu_access_pointer(cpu_emergency_virt_callback)) {
 		/* Safely force _this_ CPU out of VMX/SVM operation. */
 		cpu_emergency_disable_virtualization();
 

From 261cd5ed934e6923187cf1c9eaa6cb63f2b81212 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 21 Jul 2023 13:18:48 -0700
Subject: [PATCH 0333/1189] x86/reboot: Expose VMCS crash hooks if and only if
 KVM_{INTEL,AMD} is enabled

Expose the crash/reboot hooks used by KVM to disable virtualization in
hardware and unblock INIT only if there's a potential in-tree user,
i.e. either KVM_INTEL or KVM_AMD is enabled.

Reviewed-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/r/20230721201859.2307736-9-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/reboot.h | 4 ++++
 arch/x86/kernel/reboot.c      | 5 ++++-
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h
index 74c6a624d166..6536873f8fc0 100644
--- a/arch/x86/include/asm/reboot.h
+++ b/arch/x86/include/asm/reboot.h
@@ -25,10 +25,14 @@ void __noreturn machine_real_restart(unsigned int type);
 #define MRR_BIOS	0
 #define MRR_APM		1
 
+#if IS_ENABLED(CONFIG_KVM_INTEL) || IS_ENABLED(CONFIG_KVM_AMD)
 typedef void (cpu_emergency_virt_cb)(void);
 void cpu_emergency_register_virt_callback(cpu_emergency_virt_cb *callback);
 void cpu_emergency_unregister_virt_callback(cpu_emergency_virt_cb *callback);
 void cpu_emergency_disable_virtualization(void);
+#else
+static inline void cpu_emergency_disable_virtualization(void) {}
+#endif /* CONFIG_KVM_INTEL || CONFIG_KVM_AMD */
 
 typedef void (*nmi_shootdown_cb)(int, struct pt_regs*);
 void nmi_shootdown_cpus(nmi_shootdown_cb callback);
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 98e5db3fd7f4..830425e6d38e 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -529,6 +529,7 @@ static inline void kb_wait(void)
 
 static inline void nmi_shootdown_cpus_on_restart(void);
 
+#if IS_ENABLED(CONFIG_KVM_INTEL) || IS_ENABLED(CONFIG_KVM_AMD)
 /* RCU-protected callback to disable virtualization prior to reboot. */
 static cpu_emergency_virt_cb __rcu *cpu_emergency_virt_callback;
 
@@ -596,7 +597,9 @@ static void emergency_reboot_disable_virtualization(void)
 		nmi_shootdown_cpus_on_restart();
 	}
 }
-
+#else
+static void emergency_reboot_disable_virtualization(void) { }
+#endif /* CONFIG_KVM_INTEL || CONFIG_KVM_AMD */
 
 void __attribute__((weak)) mach_reboot_fixups(void)
 {

From b6a6af0d19cea17a3c1e34f81f0d521775f94ab5 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 21 Jul 2023 13:18:49 -0700
Subject: [PATCH 0334/1189] x86/virt: KVM: Open code cpu_has_vmx() in KVM VMX

Fold the raw CPUID check for VMX into kvm_is_vmx_supported(), its sole
user.  Keep the check even though KVM also checks X86_FEATURE_VMX, as the
intent is to provide a unique error message if VMX is unsupported by
hardware, whereas X86_FEATURE_VMX may be clear due to firmware and/or
kernel actions.

No functional change intended.

Reviewed-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/r/20230721201859.2307736-10-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/virtext.h | 10 ----------
 arch/x86/kvm/vmx/vmx.c         |  2 +-
 2 files changed, 1 insertion(+), 11 deletions(-)

diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index aaed66249ccf..b1171a5ad452 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -22,14 +22,6 @@
 /*
  * VMX functions:
  */
-
-static inline int cpu_has_vmx(void)
-{
-	unsigned long ecx = cpuid_ecx(1);
-	return test_bit(5, &ecx); /* CPUID.1:ECX.VMX[bit 5] -> VT */
-}
-
-
 /**
  * cpu_vmxoff() - Disable VMX on the current CPU
  *
@@ -61,8 +53,6 @@ static inline int cpu_vmx_enabled(void)
 }
 
 /** Disable VMX if it is enabled on the current CPU
- *
- * You shouldn't call this if cpu_has_vmx() returns 0.
  */
 static inline void __cpu_emergency_vmxoff(void)
 {
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index df991f15baf4..4b9d68826172 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2699,7 +2699,7 @@ static bool kvm_is_vmx_supported(void)
 {
 	int cpu = raw_smp_processor_id();
 
-	if (!cpu_has_vmx()) {
+	if (!(cpuid_ecx(1) & feature_bit(VMX))) {
 		pr_err("VMX not supported by CPU %d\n", cpu);
 		return false;
 	}

From 22e420e127399f2e75c8efddff763e92247f3da7 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 21 Jul 2023 13:18:50 -0700
Subject: [PATCH 0335/1189] x86/virt: KVM: Move VMXOFF helpers into KVM VMX

Now that VMX is disabled in emergencies via the virt callbacks, move the
VMXOFF helpers into KVM, the only remaining user.

No functional change intended.

Reviewed-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/r/20230721201859.2307736-11-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/virtext.h | 42 ----------------------------------
 arch/x86/kvm/vmx/vmx.c         | 29 ++++++++++++++++++++---
 2 files changed, 26 insertions(+), 45 deletions(-)

diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index b1171a5ad452..a27801f2bc71 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -19,48 +19,6 @@
 #include <asm/svm.h>
 #include <asm/tlbflush.h>
 
-/*
- * VMX functions:
- */
-/**
- * cpu_vmxoff() - Disable VMX on the current CPU
- *
- * Disable VMX and clear CR4.VMXE (even if VMXOFF faults)
- *
- * Note, VMXOFF causes a #UD if the CPU is !post-VMXON, but it's impossible to
- * atomically track post-VMXON state, e.g. this may be called in NMI context.
- * Eat all faults as all other faults on VMXOFF faults are mode related, i.e.
- * faults are guaranteed to be due to the !post-VMXON check unless the CPU is
- * magically in RM, VM86, compat mode, or at CPL>0.
- */
-static inline int cpu_vmxoff(void)
-{
-	asm_volatile_goto("1: vmxoff\n\t"
-			  _ASM_EXTABLE(1b, %l[fault])
-			  ::: "cc", "memory" : fault);
-
-	cr4_clear_bits(X86_CR4_VMXE);
-	return 0;
-
-fault:
-	cr4_clear_bits(X86_CR4_VMXE);
-	return -EIO;
-}
-
-static inline int cpu_vmx_enabled(void)
-{
-	return __read_cr4() & X86_CR4_VMXE;
-}
-
-/** Disable VMX if it is enabled on the current CPU
- */
-static inline void __cpu_emergency_vmxoff(void)
-{
-	if (cpu_vmx_enabled())
-		cpu_vmxoff();
-}
-
-
 /*
  * SVM functions:
  */
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 4b9d68826172..64377fe3a990 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -47,7 +47,6 @@
 #include <asm/mshyperv.h>
 #include <asm/mwait.h>
 #include <asm/spec-ctrl.h>
-#include <asm/virtext.h>
 #include <asm/vmx.h>
 
 #include "capabilities.h"
@@ -725,6 +724,29 @@ static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx,
 	return ret;
 }
 
+/*
+ * Disable VMX and clear CR4.VMXE (even if VMXOFF faults)
+ *
+ * Note, VMXOFF causes a #UD if the CPU is !post-VMXON, but it's impossible to
+ * atomically track post-VMXON state, e.g. this may be called in NMI context.
+ * Eat all faults as all other faults on VMXOFF faults are mode related, i.e.
+ * faults are guaranteed to be due to the !post-VMXON check unless the CPU is
+ * magically in RM, VM86, compat mode, or at CPL>0.
+ */
+static int kvm_cpu_vmxoff(void)
+{
+	asm_volatile_goto("1: vmxoff\n\t"
+			  _ASM_EXTABLE(1b, %l[fault])
+			  ::: "cc", "memory" : fault);
+
+	cr4_clear_bits(X86_CR4_VMXE);
+	return 0;
+
+fault:
+	cr4_clear_bits(X86_CR4_VMXE);
+	return -EIO;
+}
+
 static void vmx_emergency_disable(void)
 {
 	int cpu = raw_smp_processor_id();
@@ -734,7 +756,8 @@ static void vmx_emergency_disable(void)
 			    loaded_vmcss_on_cpu_link)
 		vmcs_clear(v->vmcs);
 
-	__cpu_emergency_vmxoff();
+	if (__read_cr4() & X86_CR4_VMXE)
+		kvm_cpu_vmxoff();
 }
 
 static void __loaded_vmcs_clear(void *arg)
@@ -2799,7 +2822,7 @@ static void vmx_hardware_disable(void)
 {
 	vmclear_local_loaded_vmcss();
 
-	if (cpu_vmxoff())
+	if (kvm_cpu_vmxoff())
 		kvm_spurious_fault();
 
 	hv_reset_evmcs();

From 554856b69e3d1faae6f056f75ed6262b5eb01546 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 21 Jul 2023 13:18:51 -0700
Subject: [PATCH 0336/1189] KVM: SVM: Make KVM_AMD depend on CPU_SUP_AMD or
 CPU_SUP_HYGON

Make building KVM SVM support depend on support for AMD or Hygon.  KVM
already effectively restricts SVM support to AMD and Hygon by virtue of
the vendor string checks in cpu_has_svm(), and KVM VMX supports depends
on one of its three known vendors (Intel, Centaur, or Zhaoxin).

Add the CPU_SUP_HYGON clause even though CPU_SUP_HYGON selects CPU_SUP_AMD
to document that KVM SVM support isn't just for AMD CPUs, and to prevent
breakage should Hygon support ever become a standalone thing.

Link: https://lore.kernel.org/r/20230721201859.2307736-12-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 89ca7f4c1464..66dbd1f4d57d 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -101,7 +101,7 @@ config X86_SGX_KVM
 
 config KVM_AMD
 	tristate "KVM for AMD processors support"
-	depends on KVM
+	depends on KVM && (CPU_SUP_AMD || CPU_SUP_HYGON)
 	help
 	  Provides support for KVM on AMD processors equipped with the AMD-V
 	  (SVM) extensions.

From 5df8ecfe3632d5879d1f154f7aa8de441b5d1c89 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 21 Jul 2023 13:18:52 -0700
Subject: [PATCH 0337/1189] x86/virt: Drop unnecessary check on extended CPUID
 level in cpu_has_svm()

Drop the explicit check on the extended CPUID level in cpu_has_svm(), the
kernel's cached CPUID info will leave the entire SVM leaf unset if said
leaf is not supported by hardware.  Prior to using cached information,
the check was needed to avoid false positives due to Intel's rather crazy
CPUID behavior of returning the values of the maximum supported leaf if
the specified leaf is unsupported.

Fixes: 682a8108872f ("x86/kvm/svm: Simplify cpu_has_svm()")
Link: https://lore.kernel.org/r/20230721201859.2307736-13-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/virtext.h | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index a27801f2bc71..be50c414efe4 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -39,12 +39,6 @@ static inline int cpu_has_svm(const char **msg)
 		return 0;
 	}
 
-	if (boot_cpu_data.extended_cpuid_level < SVM_CPUID_FUNC) {
-		if (msg)
-			*msg = "can't execute cpuid_8000000a";
-		return 0;
-	}
-
 	if (!boot_cpu_has(X86_FEATURE_SVM)) {
 		if (msg)
 			*msg = "svm not available";

From 85fd29dd5fe459b732e46c7a9782fc403c5604ed Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 21 Jul 2023 13:18:53 -0700
Subject: [PATCH 0338/1189] x86/virt: KVM: Open code cpu_has_svm() into
 kvm_is_svm_supported()

Fold the guts of cpu_has_svm() into kvm_is_svm_supported(), its sole
remaining user.

No functional change intended.

Reviewed-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/r/20230721201859.2307736-14-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/virtext.h | 28 ----------------------------
 arch/x86/kvm/svm/svm.c         | 11 ++++++++---
 2 files changed, 8 insertions(+), 31 deletions(-)

diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index be50c414efe4..632575e257d8 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -22,35 +22,7 @@
 /*
  * SVM functions:
  */
-
-/** Check if the CPU has SVM support
- *
- * You can use the 'msg' arg to get a message describing the problem,
- * if the function returns zero. Simply pass NULL if you are not interested
- * on the messages; gcc should take care of not generating code for
- * the messages on this case.
- */
-static inline int cpu_has_svm(const char **msg)
-{
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
-	    boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) {
-		if (msg)
-			*msg = "not amd or hygon";
-		return 0;
-	}
-
-	if (!boot_cpu_has(X86_FEATURE_SVM)) {
-		if (msg)
-			*msg = "svm not available";
-		return 0;
-	}
-	return 1;
-}
-
-
 /** Disable SVM on the current CPU
- *
- * You should call this only if cpu_has_svm() returned true.
  */
 static inline void cpu_svm_disable(void)
 {
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 1ae9c2c7eacb..ff6c769aafb2 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -521,11 +521,16 @@ static void svm_init_osvw(struct kvm_vcpu *vcpu)
 static bool kvm_is_svm_supported(void)
 {
 	int cpu = raw_smp_processor_id();
-	const char *msg;
 	u64 vm_cr;
 
-	if (!cpu_has_svm(&msg)) {
-		pr_err("SVM not supported by CPU %d, %s\n", cpu, msg);
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
+	    boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) {
+		pr_err("CPU %d isn't AMD or Hygon\n", cpu);
+		return false;
+	}
+
+	if (!boot_cpu_has(X86_FEATURE_SVM)) {
+		pr_err("SVM not supported by CPU %d\n", cpu);
 		return false;
 	}
 

From c4db4f20f3bf619bacd3d705bf427016453eedb1 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 21 Jul 2023 13:18:54 -0700
Subject: [PATCH 0339/1189] KVM: SVM: Check that the current CPU supports SVM
 in kvm_is_svm_supported()

Check "this" CPU instead of the boot CPU when querying SVM support so that
the per-CPU checks done during hardware enabling actually function as
intended, i.e. will detect issues where SVM isn't support on all CPUs.

Disable migration for the use from svm_init() mostly so that the standard
accessors for the per-CPU data can be used without getting yelled at by
CONFIG_DEBUG_PREEMPT=y sanity checks.  Preventing the "disabled by BIOS"
error message from reporting the wrong CPU is largely a bonus, as ensuring
a stable CPU during module load is a non-goal for KVM.

Link: https://lore.kernel.org/all/ZAdxNgv0M6P63odE@google.com
Cc: Kai Huang <kai.huang@intel.com>
Cc: Chao Gao <chao.gao@intel.com>
Reviewed-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/r/20230721201859.2307736-15-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.c | 25 +++++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index ff6c769aafb2..9e449167e71b 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -518,18 +518,20 @@ static void svm_init_osvw(struct kvm_vcpu *vcpu)
 		vcpu->arch.osvw.status |= 1;
 }
 
-static bool kvm_is_svm_supported(void)
+static bool __kvm_is_svm_supported(void)
 {
-	int cpu = raw_smp_processor_id();
+	int cpu = smp_processor_id();
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+
 	u64 vm_cr;
 
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
-	    boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) {
+	if (c->x86_vendor != X86_VENDOR_AMD &&
+	    c->x86_vendor != X86_VENDOR_HYGON) {
 		pr_err("CPU %d isn't AMD or Hygon\n", cpu);
 		return false;
 	}
 
-	if (!boot_cpu_has(X86_FEATURE_SVM)) {
+	if (!cpu_has(c, X86_FEATURE_SVM)) {
 		pr_err("SVM not supported by CPU %d\n", cpu);
 		return false;
 	}
@@ -548,9 +550,20 @@ static bool kvm_is_svm_supported(void)
 	return true;
 }
 
+static bool kvm_is_svm_supported(void)
+{
+	bool supported;
+
+	migrate_disable();
+	supported = __kvm_is_svm_supported();
+	migrate_enable();
+
+	return supported;
+}
+
 static int svm_check_processor_compat(void)
 {
-	if (!kvm_is_svm_supported())
+	if (!__kvm_is_svm_supported())
 		return -EIO;
 
 	return 0;

From f9a8866040fcf8672f20c67e07e67ba5a00caba4 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 21 Jul 2023 13:18:55 -0700
Subject: [PATCH 0340/1189] KVM: VMX: Ensure CPU is stable when probing basic
 VMX support

Disable migration when probing VMX support during module load to ensure
the CPU is stable, mostly to match similar SVM logic, where allowing
migration effective requires deliberately writing buggy code.  As a bonus,
KVM won't report the wrong CPU to userspace if VMX is unsupported, but in
practice that is a very, very minor bonus as the only way that reporting
the wrong CPU would actually matter is if hardware is broken or if the
system is misconfigured, i.e. if KVM gets migrated from a CPU that _does_
support VMX to a CPU that does _not_ support VMX.

Reviewed-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/r/20230721201859.2307736-16-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/vmx/vmx.c | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 64377fe3a990..ff0eced7d2ab 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2718,9 +2718,9 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf,
 	return 0;
 }
 
-static bool kvm_is_vmx_supported(void)
+static bool __kvm_is_vmx_supported(void)
 {
-	int cpu = raw_smp_processor_id();
+	int cpu = smp_processor_id();
 
 	if (!(cpuid_ecx(1) & feature_bit(VMX))) {
 		pr_err("VMX not supported by CPU %d\n", cpu);
@@ -2736,13 +2736,24 @@ static bool kvm_is_vmx_supported(void)
 	return true;
 }
 
+static bool kvm_is_vmx_supported(void)
+{
+	bool supported;
+
+	migrate_disable();
+	supported = __kvm_is_vmx_supported();
+	migrate_enable();
+
+	return supported;
+}
+
 static int vmx_check_processor_compat(void)
 {
 	int cpu = raw_smp_processor_id();
 	struct vmcs_config vmcs_conf;
 	struct vmx_capability vmx_cap;
 
-	if (!kvm_is_vmx_supported())
+	if (!__kvm_is_vmx_supported())
 		return -EIO;
 
 	if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0) {

From 76ab8161083bfd0ae4de9b93e68d639da6e1c726 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 21 Jul 2023 13:18:56 -0700
Subject: [PATCH 0341/1189] x86/virt: KVM: Move "disable SVM" helper into KVM
 SVM

Move cpu_svm_disable() into KVM proper now that all hardware
virtualization management is routed through KVM.  Remove the now-empty
virtext.h.

No functional change intended.

Reviewed-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/r/20230721201859.2307736-17-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/virtext.h | 50 ----------------------------------
 arch/x86/kvm/svm/svm.c         | 29 +++++++++++++++++---
 2 files changed, 25 insertions(+), 54 deletions(-)
 delete mode 100644 arch/x86/include/asm/virtext.h

diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
deleted file mode 100644
index 632575e257d8..000000000000
--- a/arch/x86/include/asm/virtext.h
+++ /dev/null
@@ -1,50 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/* CPU virtualization extensions handling
- *
- * This should carry the code for handling CPU virtualization extensions
- * that needs to live in the kernel core.
- *
- * Author: Eduardo Habkost <ehabkost@redhat.com>
- *
- * Copyright (C) 2008, Red Hat Inc.
- *
- * Contains code from KVM, Copyright (C) 2006 Qumranet, Inc.
- */
-#ifndef _ASM_X86_VIRTEX_H
-#define _ASM_X86_VIRTEX_H
-
-#include <asm/processor.h>
-
-#include <asm/vmx.h>
-#include <asm/svm.h>
-#include <asm/tlbflush.h>
-
-/*
- * SVM functions:
- */
-/** Disable SVM on the current CPU
- */
-static inline void cpu_svm_disable(void)
-{
-	uint64_t efer;
-
-	wrmsrl(MSR_VM_HSAVE_PA, 0);
-	rdmsrl(MSR_EFER, efer);
-	if (efer & EFER_SVME) {
-		/*
-		 * Force GIF=1 prior to disabling SVM to ensure INIT and NMI
-		 * aren't blocked, e.g. if a fatal error occurred between CLGI
-		 * and STGI.  Note, STGI may #UD if SVM is disabled from NMI
-		 * context between reading EFER and executing STGI.  In that
-		 * case, GIF must already be set, otherwise the NMI would have
-		 * been blocked, so just eat the fault.
-		 */
-		asm_volatile_goto("1: stgi\n\t"
-				  _ASM_EXTABLE(1b, %l[fault])
-				  ::: "memory" : fault);
-fault:
-		wrmsrl(MSR_EFER, efer & ~EFER_SVME);
-	}
-}
-
-#endif /* _ASM_X86_VIRTEX_H */
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 9e449167e71b..47f9c7156609 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -42,8 +42,6 @@
 #include <asm/reboot.h>
 #include <asm/fpu/api.h>
 
-#include <asm/virtext.h>
-
 #include <trace/events/ipi.h>
 
 #include "trace.h"
@@ -582,9 +580,32 @@ out:
 	preempt_enable();
 }
 
+static inline void kvm_cpu_svm_disable(void)
+{
+	uint64_t efer;
+
+	wrmsrl(MSR_VM_HSAVE_PA, 0);
+	rdmsrl(MSR_EFER, efer);
+	if (efer & EFER_SVME) {
+		/*
+		 * Force GIF=1 prior to disabling SVM to ensure INIT and NMI
+		 * aren't blocked, e.g. if a fatal error occurred between CLGI
+		 * and STGI.  Note, STGI may #UD if SVM is disabled from NMI
+		 * context between reading EFER and executing STGI.  In that
+		 * case, GIF must already be set, otherwise the NMI would have
+		 * been blocked, so just eat the fault.
+		 */
+		asm_volatile_goto("1: stgi\n\t"
+				  _ASM_EXTABLE(1b, %l[fault])
+				  ::: "memory" : fault);
+fault:
+		wrmsrl(MSR_EFER, efer & ~EFER_SVME);
+	}
+}
+
 static void svm_emergency_disable(void)
 {
-	cpu_svm_disable();
+	kvm_cpu_svm_disable();
 }
 
 static void svm_hardware_disable(void)
@@ -593,7 +614,7 @@ static void svm_hardware_disable(void)
 	if (tsc_scaling)
 		__svm_write_tsc_multiplier(SVM_TSC_RATIO_DEFAULT);
 
-	cpu_svm_disable();
+	kvm_cpu_svm_disable();
 
 	amd_pmu_disable_virt();
 }

From 6ae44e012f4c35fb67bc61bd0bf1b3c5f504d931 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 21 Jul 2023 13:18:57 -0700
Subject: [PATCH 0342/1189] KVM: x86: Force kvm_rebooting=true during emergency
 reboot/crash

Set kvm_rebooting when virtualization is disabled in an emergency so that
KVM eats faults on virtualization instructions even if kvm_reboot() isn't
reached.

Reviewed-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/r/20230721201859.2307736-18-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.c | 2 ++
 arch/x86/kvm/vmx/vmx.c | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 47f9c7156609..8d1b3c801629 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -605,6 +605,8 @@ fault:
 
 static void svm_emergency_disable(void)
 {
+	kvm_rebooting = true;
+
 	kvm_cpu_svm_disable();
 }
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index ff0eced7d2ab..415665c40a39 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -752,6 +752,8 @@ static void vmx_emergency_disable(void)
 	int cpu = raw_smp_processor_id();
 	struct loaded_vmcs *v;
 
+	kvm_rebooting = true;
+
 	list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu),
 			    loaded_vmcss_on_cpu_link)
 		vmcs_clear(v->vmcs);

From 2e6b9bd49b702c4a52278e35202354b709021116 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 21 Jul 2023 13:18:58 -0700
Subject: [PATCH 0343/1189] KVM: SVM: Use "standard" stgi() helper when
 disabling SVM

Now that kvm_rebooting is guaranteed to be true prior to disabling SVM
in an emergency, use the existing stgi() helper instead of open coding
STGI.  In effect, eat faults on STGI if and only if kvm_rebooting==true.

Link: https://lore.kernel.org/r/20230721201859.2307736-19-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.c | 13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 8d1b3c801629..4785d780cce3 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -588,17 +588,10 @@ static inline void kvm_cpu_svm_disable(void)
 	rdmsrl(MSR_EFER, efer);
 	if (efer & EFER_SVME) {
 		/*
-		 * Force GIF=1 prior to disabling SVM to ensure INIT and NMI
-		 * aren't blocked, e.g. if a fatal error occurred between CLGI
-		 * and STGI.  Note, STGI may #UD if SVM is disabled from NMI
-		 * context between reading EFER and executing STGI.  In that
-		 * case, GIF must already be set, otherwise the NMI would have
-		 * been blocked, so just eat the fault.
+		 * Force GIF=1 prior to disabling SVM, e.g. to ensure INIT and
+		 * NMI aren't blocked.
 		 */
-		asm_volatile_goto("1: stgi\n\t"
-				  _ASM_EXTABLE(1b, %l[fault])
-				  ::: "memory" : fault);
-fault:
+		stgi();
 		wrmsrl(MSR_EFER, efer & ~EFER_SVME);
 	}
 }

From a788fbb763b5001f67f2ecdf207a357f9b12838f Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 21 Jul 2023 13:18:59 -0700
Subject: [PATCH 0344/1189] KVM: VMX: Skip VMCLEAR logic during emergency
 reboots if CR4.VMXE=0

Bail from vmx_emergency_disable() without processing the list of loaded
VMCSes if CR4.VMXE=0, i.e. if the CPU can't be post-VMXON.  It should be
impossible for the list to have entries if VMX is already disabled, and
even if that invariant doesn't hold, VMCLEAR will #UD anyways, i.e.
processing the list is pointless even if it somehow isn't empty.

Assuming no existing KVM bugs, this should be a glorified nop.  The
primary motivation for the change is to avoid having code that looks like
it does VMCLEAR, but then skips VMXON, which is nonsensical.

Suggested-by: Kai Huang <kai.huang@intel.com>
Reviewed-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/r/20230721201859.2307736-20-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/vmx/vmx.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 415665c40a39..83338872a39f 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -754,12 +754,20 @@ static void vmx_emergency_disable(void)
 
 	kvm_rebooting = true;
 
+	/*
+	 * Note, CR4.VMXE can be _cleared_ in NMI context, but it can only be
+	 * set in task context.  If this races with VMX is disabled by an NMI,
+	 * VMCLEAR and VMXOFF may #UD, but KVM will eat those faults due to
+	 * kvm_rebooting set.
+	 */
+	if (!(__read_cr4() & X86_CR4_VMXE))
+		return;
+
 	list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu),
 			    loaded_vmcss_on_cpu_link)
 		vmcs_clear(v->vmcs);
 
-	if (__read_cr4() & X86_CR4_VMXE)
-		kvm_cpu_vmxoff();
+	kvm_cpu_vmxoff();
 }
 
 static void __loaded_vmcs_clear(void *arg)

From 99b668545356115e11a6cca519361c8cfd02569e Mon Sep 17 00:00:00 2001
From: Tao Su <tao1.su@linux.intel.com>
Date: Wed, 2 Aug 2023 10:29:54 +0800
Subject: [PATCH 0345/1189] KVM: x86: Advertise AMX-COMPLEX CPUID to userspace

Latest Intel platform GraniteRapids-D introduces AMX-COMPLEX, which adds
two instructions to perform matrix multiplication of two tiles containing
complex elements and accumulate the results into a packed single precision
tile.

AMX-COMPLEX is enumerated via CPUID.(EAX=7,ECX=1):EDX[bit 8]

Advertise AMX_COMPLEX if it's supported in hardware.  There are no VMX
controls for the feature, i.e. the instructions can't be interecepted, and
KVM advertises base AMX in CPUID if AMX is supported in hardware, even if
KVM doesn't advertise AMX as being supported in XCR0, e.g. because the
process didn't opt-in to allocating tile data.

Signed-off-by: Tao Su <tao1.su@linux.intel.com>
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Link: https://lore.kernel.org/r/20230802022954.193843-1-tao1.su@linux.intel.com
[sean: tweak last paragraph of changelog]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/cpuid.c         | 3 ++-
 arch/x86/kvm/reverse_cpuid.h | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index ad6566636c22..5a88affb2e1a 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -647,7 +647,8 @@ void kvm_set_cpu_caps(void)
 	);
 
 	kvm_cpu_cap_init_kvm_defined(CPUID_7_1_EDX,
-		F(AVX_VNNI_INT8) | F(AVX_NE_CONVERT) | F(PREFETCHITI)
+		F(AVX_VNNI_INT8) | F(AVX_NE_CONVERT) | F(PREFETCHITI) |
+		F(AMX_COMPLEX)
 	);
 
 	kvm_cpu_cap_mask(CPUID_D_1_EAX,
diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h
index 56cbdb24400a..b81650678375 100644
--- a/arch/x86/kvm/reverse_cpuid.h
+++ b/arch/x86/kvm/reverse_cpuid.h
@@ -43,6 +43,7 @@ enum kvm_only_cpuid_leafs {
 /* Intel-defined sub-features, CPUID level 0x00000007:1 (EDX) */
 #define X86_FEATURE_AVX_VNNI_INT8       KVM_X86_FEATURE(CPUID_7_1_EDX, 4)
 #define X86_FEATURE_AVX_NE_CONVERT      KVM_X86_FEATURE(CPUID_7_1_EDX, 5)
+#define X86_FEATURE_AMX_COMPLEX         KVM_X86_FEATURE(CPUID_7_1_EDX, 8)
 #define X86_FEATURE_PREFETCHITI         KVM_X86_FEATURE(CPUID_7_1_EDX, 14)
 
 /* CPUID level 0x80000007 (EDX). */

From 7cafe9b8e22bb3d77f130c461aedf6868c4aaf58 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:15:48 -0700
Subject: [PATCH 0346/1189] KVM: nSVM: Check instead of asserting on nested TSC
 scaling support

Check for nested TSC scaling support on nested SVM VMRUN instead of
asserting that TSC scaling is exposed to L1 if L1's MSR_AMD64_TSC_RATIO
has diverged from KVM's default.  Userspace can trigger the WARN at will
by writing the MSR and then updating guest CPUID to hide the feature
(modifying guest CPUID is allowed anytime before KVM_RUN).  E.g. hacking
KVM's state_test selftest to do

		vcpu_set_msr(vcpu, MSR_AMD64_TSC_RATIO, 0);
		vcpu_clear_cpuid_feature(vcpu, X86_FEATURE_TSCRATEMSR);

after restoring state in a new VM+vCPU yields an endless supply of:

  ------------[ cut here ]------------
  WARNING: CPU: 164 PID: 62565 at arch/x86/kvm/svm/nested.c:699
           nested_vmcb02_prepare_control+0x3d6/0x3f0 [kvm_amd]
  Call Trace:
   <TASK>
   enter_svm_guest_mode+0x114/0x560 [kvm_amd]
   nested_svm_vmrun+0x260/0x330 [kvm_amd]
   vmrun_interception+0x29/0x30 [kvm_amd]
   svm_invoke_exit_handler+0x35/0x100 [kvm_amd]
   svm_handle_exit+0xe7/0x180 [kvm_amd]
   kvm_arch_vcpu_ioctl_run+0x1eab/0x2570 [kvm]
   kvm_vcpu_ioctl+0x4c9/0x5b0 [kvm]
   __se_sys_ioctl+0x7a/0xc0
   __x64_sys_ioctl+0x21/0x30
   do_syscall_64+0x41/0x90
   entry_SYSCALL_64_after_hwframe+0x63/0xcd
  RIP: 0033:0x45ca1b

Note, the nested #VMEXIT path has the same flaw, but needs a different
fix and will be handled separately.

Fixes: 5228eb96a487 ("KVM: x86: nSVM: implement nested TSC scaling")
Cc: Maxim Levitsky <mlevitsk@redhat.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230729011608.1065019-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/nested.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 96936ddf1b3c..0b90f5cf9df3 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -695,10 +695,9 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,
 
 	vmcb02->control.tsc_offset = vcpu->arch.tsc_offset;
 
-	if (svm->tsc_ratio_msr != kvm_caps.default_tsc_scaling_ratio) {
-		WARN_ON(!svm->tsc_scaling_enabled);
+	if (svm->tsc_scaling_enabled &&
+	    svm->tsc_ratio_msr != kvm_caps.default_tsc_scaling_ratio)
 		nested_svm_update_tsc_ratio_msr(vcpu);
-	}
 
 	vmcb02->control.int_ctl             =
 		(svm->nested.ctl.int_ctl & int_ctl_vmcb12_bits) |

From 0c94e2468491cbf0754f49a5136ab51294a96b69 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:15:49 -0700
Subject: [PATCH 0347/1189] KVM: nSVM: Load L1's TSC multiplier based on L1
 state, not L2 state

When emulating nested VM-Exit, load L1's TSC multiplier if L1's desired
ratio doesn't match the current ratio, not if the ratio L1 is using for
L2 diverges from the default.  Functionally, the end result is the same
as KVM will run L2 with L1's multiplier if L2's multiplier is the default,
i.e. checking that L1's multiplier is loaded is equivalent to checking if
L2 has a non-default multiplier.

However, the assertion that TSC scaling is exposed to L1 is flawed, as
userspace can trigger the WARN at will by writing the MSR and then
updating guest CPUID to hide the feature (modifying guest CPUID is
allowed anytime before KVM_RUN).  E.g. hacking KVM's state_test
selftest to do

                vcpu_set_msr(vcpu, MSR_AMD64_TSC_RATIO, 0);
                vcpu_clear_cpuid_feature(vcpu, X86_FEATURE_TSCRATEMSR);

after restoring state in a new VM+vCPU yields an endless supply of:

  ------------[ cut here ]------------
  WARNING: CPU: 10 PID: 206939 at arch/x86/kvm/svm/nested.c:1105
           nested_svm_vmexit+0x6af/0x720 [kvm_amd]
  Call Trace:
   nested_svm_exit_handled+0x102/0x1f0 [kvm_amd]
   svm_handle_exit+0xb9/0x180 [kvm_amd]
   kvm_arch_vcpu_ioctl_run+0x1eab/0x2570 [kvm]
   kvm_vcpu_ioctl+0x4c9/0x5b0 [kvm]
   ? trace_hardirqs_off+0x4d/0xa0
   __se_sys_ioctl+0x7a/0xc0
   __x64_sys_ioctl+0x21/0x30
   do_syscall_64+0x41/0x90
   entry_SYSCALL_64_after_hwframe+0x63/0xcd

Unlike the nested VMRUN path, hoisting the svm->tsc_scaling_enabled check
into the if-statement is wrong as KVM needs to ensure L1's multiplier is
loaded in the above scenario.   Alternatively, the WARN_ON() could simply
be deleted, but that would make KVM's behavior even more subtle, e.g. it's
not immediately obvious why it's safe to write MSR_AMD64_TSC_RATIO when
checking only tsc_ratio_msr.

Fixes: 5228eb96a487 ("KVM: x86: nSVM: implement nested TSC scaling")
Cc: Maxim Levitsky <mlevitsk@redhat.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230729011608.1065019-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/nested.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 0b90f5cf9df3..c66c823ae222 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -1100,8 +1100,8 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 		vmcb_mark_dirty(vmcb01, VMCB_INTERCEPTS);
 	}
 
-	if (svm->tsc_ratio_msr != kvm_caps.default_tsc_scaling_ratio) {
-		WARN_ON(!svm->tsc_scaling_enabled);
+	if (kvm_caps.has_tsc_control &&
+	    vcpu->arch.tsc_scaling_ratio != vcpu->arch.l1_tsc_scaling_ratio) {
 		vcpu->arch.tsc_scaling_ratio = vcpu->arch.l1_tsc_scaling_ratio;
 		__svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio);
 	}

From c0dc39bd2c584879748dfd1321f8541d1cbeb9b8 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:15:50 -0700
Subject: [PATCH 0348/1189] KVM: nSVM: Use the "outer" helper for writing
 multiplier to MSR_AMD64_TSC_RATIO

When emulating nested SVM transitions, use the outer helper for writing
the TSC multiplier for L2.  Using the inner helper only for one-off cases,
i.e. for paths where KVM is NOT emulating or modifying vCPU state, will
allow for multiple cleanups:

 - Explicitly disabling preemption only in the outer helper
 - Getting the multiplier from the vCPU field in the outer helper
 - Skipping the WRMSR in the outer helper if guest state isn't loaded

Opportunistically delete an extra newline.

No functional change intended.

Link: https://lore.kernel.org/r/20230729011608.1065019-4-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/nested.c | 4 ++--
 arch/x86/kvm/svm/svm.c    | 5 ++---
 arch/x86/kvm/svm/svm.h    | 2 +-
 3 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index c66c823ae222..5d5a1d7832fb 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -1103,7 +1103,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	if (kvm_caps.has_tsc_control &&
 	    vcpu->arch.tsc_scaling_ratio != vcpu->arch.l1_tsc_scaling_ratio) {
 		vcpu->arch.tsc_scaling_ratio = vcpu->arch.l1_tsc_scaling_ratio;
-		__svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio);
+		svm_write_tsc_multiplier(vcpu, vcpu->arch.tsc_scaling_ratio);
 	}
 
 	svm->nested.ctl.nested_cr3 = 0;
@@ -1536,7 +1536,7 @@ void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu)
 	vcpu->arch.tsc_scaling_ratio =
 		kvm_calc_nested_tsc_multiplier(vcpu->arch.l1_tsc_scaling_ratio,
 					       svm->tsc_ratio_msr);
-	__svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio);
+	svm_write_tsc_multiplier(vcpu, vcpu->arch.tsc_scaling_ratio);
 }
 
 /* Inverse operation of nested_copy_vmcb_control_to_cache(). asid is copied too. */
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 4785d780cce3..7217f7532df9 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -567,7 +567,7 @@ static int svm_check_processor_compat(void)
 	return 0;
 }
 
-void __svm_write_tsc_multiplier(u64 multiplier)
+static void __svm_write_tsc_multiplier(u64 multiplier)
 {
 	preempt_disable();
 
@@ -1150,12 +1150,11 @@ static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 	vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
 }
 
-static void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier)
+void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier)
 {
 	__svm_write_tsc_multiplier(multiplier);
 }
 
-
 /* Evaluate instruction intercepts that depend on guest CPUID features. */
 static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu,
 					      struct vcpu_svm *svm)
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 18af7e712a5a..7132c0a04817 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -658,7 +658,7 @@ int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
 			       bool has_error_code, u32 error_code);
 int nested_svm_exit_special(struct vcpu_svm *svm);
 void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu);
-void __svm_write_tsc_multiplier(u64 multiplier);
+void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier);
 void nested_copy_vmcb_control_to_cache(struct vcpu_svm *svm,
 				       struct vmcb_control_area *control);
 void nested_copy_vmcb_save_to_cache(struct vcpu_svm *svm,

From 229725acfaea0dd81f245aec40986dc766de40fa Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:15:51 -0700
Subject: [PATCH 0349/1189] KVM: SVM: Clean up preemption toggling related to
 MSR_AMD64_TSC_RATIO

Explicitly disable preemption when writing MSR_AMD64_TSC_RATIO only in the
"outer" helper, as all direct callers of the "inner" helper now run with
preemption already disabled.  And that isn't a coincidence, as the outer
helper requires a vCPU and is intended to be used when modifying guest
state and/or emulating guest instructions, which are typically done with
preemption enabled.

Direct use of the inner helper should be extremely limited, as the only
time KVM should modify MSR_AMD64_TSC_RATIO without a vCPU is when
sanitizing the MSR for a specific pCPU (currently done when {en,dis}abling
disabling SVM). The other direct caller is svm_prepare_switch_to_guest(),
which does have a vCPU, but is a one-off special case: KVM is about to
enter the guest on a specific pCPU and thus must have preemption disabled.

Link: https://lore.kernel.org/r/20230729011608.1065019-5-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 7217f7532df9..b66af2966ec7 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -569,15 +569,11 @@ static int svm_check_processor_compat(void)
 
 static void __svm_write_tsc_multiplier(u64 multiplier)
 {
-	preempt_disable();
-
 	if (multiplier == __this_cpu_read(current_tsc_ratio))
-		goto out;
+		return;
 
 	wrmsrl(MSR_AMD64_TSC_RATIO, multiplier);
 	__this_cpu_write(current_tsc_ratio, multiplier);
-out:
-	preempt_enable();
 }
 
 static inline void kvm_cpu_svm_disable(void)
@@ -1152,7 +1148,9 @@ static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 
 void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier)
 {
+	preempt_disable();
 	__svm_write_tsc_multiplier(multiplier);
+	preempt_enable();
 }
 
 /* Evaluate instruction intercepts that depend on guest CPUID features. */

From 2d63699099ac1fad13a0dbf8538faf4127c062e8 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:15:52 -0700
Subject: [PATCH 0350/1189] KVM: x86: Always write vCPU's current TSC
 offset/ratio in vendor hooks

Drop the @offset and @multiplier params from the kvm_x86_ops hooks for
propagating TSC offsets/multipliers into hardware, and instead have the
vendor implementations pull the information directly from the vCPU
structure.  The respective vCPU fields _must_ be written at the same
time in order to maintain consistent state, i.e. it's not random luck
that the value passed in by all callers is grabbed from the vCPU.

Explicitly grabbing the value from the vCPU field in SVM's implementation
in particular will allow for additional cleanup without introducing even
more subtle dependencies.  Specifically, SVM can skip the WRMSR if guest
state isn't loaded, i.e. svm_prepare_switch_to_guest() will load the
correct value for the vCPU prior to entering the guest.

This also reconciles KVM's handling of related values that are stored in
the vCPU, as svm_write_tsc_offset() already assumes/requires the caller
to have updated l1_tsc_offset.

Link: https://lore.kernel.org/r/20230729011608.1065019-6-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/kvm_host.h | 4 ++--
 arch/x86/kvm/svm/nested.c       | 4 ++--
 arch/x86/kvm/svm/svm.c          | 8 ++++----
 arch/x86/kvm/svm/svm.h          | 2 +-
 arch/x86/kvm/vmx/vmx.c          | 8 ++++----
 arch/x86/kvm/x86.c              | 5 ++---
 6 files changed, 15 insertions(+), 16 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 28bd38303d70..dad9331c5270 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1654,8 +1654,8 @@ struct kvm_x86_ops {
 
 	u64 (*get_l2_tsc_offset)(struct kvm_vcpu *vcpu);
 	u64 (*get_l2_tsc_multiplier)(struct kvm_vcpu *vcpu);
-	void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
-	void (*write_tsc_multiplier)(struct kvm_vcpu *vcpu, u64 multiplier);
+	void (*write_tsc_offset)(struct kvm_vcpu *vcpu);
+	void (*write_tsc_multiplier)(struct kvm_vcpu *vcpu);
 
 	/*
 	 * Retrieve somewhat arbitrary exit information.  Intended to
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 5d5a1d7832fb..3342cc4a5189 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -1103,7 +1103,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	if (kvm_caps.has_tsc_control &&
 	    vcpu->arch.tsc_scaling_ratio != vcpu->arch.l1_tsc_scaling_ratio) {
 		vcpu->arch.tsc_scaling_ratio = vcpu->arch.l1_tsc_scaling_ratio;
-		svm_write_tsc_multiplier(vcpu, vcpu->arch.tsc_scaling_ratio);
+		svm_write_tsc_multiplier(vcpu);
 	}
 
 	svm->nested.ctl.nested_cr3 = 0;
@@ -1536,7 +1536,7 @@ void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu)
 	vcpu->arch.tsc_scaling_ratio =
 		kvm_calc_nested_tsc_multiplier(vcpu->arch.l1_tsc_scaling_ratio,
 					       svm->tsc_ratio_msr);
-	svm_write_tsc_multiplier(vcpu, vcpu->arch.tsc_scaling_ratio);
+	svm_write_tsc_multiplier(vcpu);
 }
 
 /* Inverse operation of nested_copy_vmcb_control_to_cache(). asid is copied too. */
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index b66af2966ec7..2542066652a3 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1137,19 +1137,19 @@ static u64 svm_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu)
 	return svm->tsc_ratio_msr;
 }
 
-static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
+static void svm_write_tsc_offset(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	svm->vmcb01.ptr->control.tsc_offset = vcpu->arch.l1_tsc_offset;
-	svm->vmcb->control.tsc_offset = offset;
+	svm->vmcb->control.tsc_offset = vcpu->arch.tsc_offset;
 	vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
 }
 
-void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier)
+void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu)
 {
 	preempt_disable();
-	__svm_write_tsc_multiplier(multiplier);
+	__svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio);
 	preempt_enable();
 }
 
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 7132c0a04817..5829a1801862 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -658,7 +658,7 @@ int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
 			       bool has_error_code, u32 error_code);
 int nested_svm_exit_special(struct vcpu_svm *svm);
 void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu);
-void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier);
+void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu);
 void nested_copy_vmcb_control_to_cache(struct vcpu_svm *svm,
 				       struct vmcb_control_area *control);
 void nested_copy_vmcb_save_to_cache(struct vcpu_svm *svm,
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 83338872a39f..3235998ca261 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1898,14 +1898,14 @@ u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu)
 	return kvm_caps.default_tsc_scaling_ratio;
 }
 
-static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
+static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu)
 {
-	vmcs_write64(TSC_OFFSET, offset);
+	vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
 }
 
-static void vmx_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier)
+static void vmx_write_tsc_multiplier(struct kvm_vcpu *vcpu)
 {
-	vmcs_write64(TSC_MULTIPLIER, multiplier);
+	vmcs_write64(TSC_MULTIPLIER, vcpu->arch.tsc_scaling_ratio);
 }
 
 /*
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a1b13d2d1d71..80ec33fc823b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2613,7 +2613,7 @@ static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 l1_offset)
 	else
 		vcpu->arch.tsc_offset = l1_offset;
 
-	static_call(kvm_x86_write_tsc_offset)(vcpu, vcpu->arch.tsc_offset);
+	static_call(kvm_x86_write_tsc_offset)(vcpu);
 }
 
 static void kvm_vcpu_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 l1_multiplier)
@@ -2629,8 +2629,7 @@ static void kvm_vcpu_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 l1_multipli
 		vcpu->arch.tsc_scaling_ratio = l1_multiplier;
 
 	if (kvm_caps.has_tsc_control)
-		static_call(kvm_x86_write_tsc_multiplier)(
-			vcpu, vcpu->arch.tsc_scaling_ratio);
+		static_call(kvm_x86_write_tsc_multiplier)(vcpu);
 }
 
 static inline bool kvm_check_tsc_unstable(void)

From 223f93d4d88aedc02bdcc92b3734e76f707812f3 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:15:53 -0700
Subject: [PATCH 0351/1189] KVM: nSVM: Skip writes to MSR_AMD64_TSC_RATIO if
 guest state isn't loaded

Skip writes to MSR_AMD64_TSC_RATIO that are done in the context of a vCPU
if guest state isn't loaded, i.e. if KVM will update MSR_AMD64_TSC_RATIO
during svm_prepare_switch_to_guest() before entering the guest.  Checking
guest_state_loaded may or may not be a net positive for performance as
the current_tsc_ratio cache will optimize away duplicate WRMSRs in the
vast majority of scenarios.  However, the cost of the check is negligible,
and the real motivation is to document that KVM needs to load the vCPU's
value only when running the vCPU.

Link: https://lore.kernel.org/r/20230729011608.1065019-7-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 2542066652a3..6d8932e05753 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1149,7 +1149,8 @@ static void svm_write_tsc_offset(struct kvm_vcpu *vcpu)
 void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu)
 {
 	preempt_disable();
-	__svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio);
+	if (to_svm(vcpu)->guest_state_loaded)
+		__svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio);
 	preempt_enable();
 }
 

From 7bc0153c53bc1ef96e5d1ffb039d9070a944966b Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 4 Aug 2023 13:18:38 -0300
Subject: [PATCH 0352/1189] perf probe: Free string returned by
 synthesize_perf_probe_point() on failure to add a probe

Building perf with EXTRA_CFLAGS="-fsanitize=address" a leak is detect
when trying to add a probe to a non-existent function:

  # perf probe -x ~/bin/perf dso__neW
  Probe point 'dso__neW' not found.
    Error: Failed to add events.

  =================================================================
  ==296634==ERROR: LeakSanitizer: detected memory leaks

  Direct leak of 128 byte(s) in 1 object(s) allocated from:
      #0 0x7f67642ba097 in calloc (/lib64/libasan.so.8+0xba097)
      #1 0x7f67641a76f1 in allocate_cfi (/lib64/libdw.so.1+0x3f6f1)

  Direct leak of 65 byte(s) in 1 object(s) allocated from:
      #0 0x7f67642b95b5 in __interceptor_realloc.part.0 (/lib64/libasan.so.8+0xb95b5)
      #1 0x6cac75 in strbuf_grow util/strbuf.c:64
      #2 0x6ca934 in strbuf_init util/strbuf.c:25
      #3 0x9337d2 in synthesize_perf_probe_point util/probe-event.c:2018
      #4 0x92be51 in try_to_find_probe_trace_events util/probe-event.c:964
      #5 0x93d5c6 in convert_to_probe_trace_events util/probe-event.c:3512
      #6 0x93d6d5 in convert_perf_probe_events util/probe-event.c:3529
      #7 0x56f37f in perf_add_probe_events /var/home/acme/git/perf-tools-next/tools/perf/builtin-probe.c:354
      #8 0x572fbc in __cmd_probe /var/home/acme/git/perf-tools-next/tools/perf/builtin-probe.c:738
      #9 0x5730f2 in cmd_probe /var/home/acme/git/perf-tools-next/tools/perf/builtin-probe.c:766
      #10 0x635d81 in run_builtin /var/home/acme/git/perf-tools-next/tools/perf/perf.c:323
      #11 0x6362c1 in handle_internal_command /var/home/acme/git/perf-tools-next/tools/perf/perf.c:377
      #12 0x63667a in run_argv /var/home/acme/git/perf-tools-next/tools/perf/perf.c:421
      #13 0x636b8d in main /var/home/acme/git/perf-tools-next/tools/perf/perf.c:537
      #14 0x7f676302950f in __libc_start_call_main (/lib64/libc.so.6+0x2950f)

  SUMMARY: AddressSanitizer: 193 byte(s) leaked in 2 allocation(s).
  #

synthesize_perf_probe_point() returns a "detachec" strbuf, i.e. a
malloc'ed string that needs to be free'd.

An audit will be performed to find other such cases.

Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/ZM0l1Oxamr4SVjfY@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/probe-event.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 2d056f02ae40..c7bfeab610a3 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -961,8 +961,9 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 	debuginfo__delete(dinfo);
 
 	if (ntevs == 0)	{	/* No error but failed to find probe point. */
-		pr_warning("Probe point '%s' not found.\n",
-			   synthesize_perf_probe_point(&pev->point));
+		char *probe_point = synthesize_perf_probe_point(&pev->point);
+		pr_warning("Probe point '%s' not found.\n", probe_point);
+		free(probe_point);
 		return -ENODEV;
 	} else if (ntevs < 0) {
 		/* Error path : ntevs < 0 */

From a612bbf8b8fdd29136a1ac8b2afca3780278d344 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 4 Aug 2023 13:18:38 -0300
Subject: [PATCH 0353/1189] perf probe: Free string returned by
 synthesize_perf_probe_point() on failure in synthesize_perf_probe_command()

Building perf with EXTRA_CFLAGS="-fsanitize=address" a leak was detected
elsewhere and lead to an audit, where we found that
synthesize_perf_probe_command() may leak synthesize_perf_probe_point()
return on failure, fix it.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/ZM0mzpQktHnhXJXr@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/probe-event.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index c7bfeab610a3..2835d87cb977 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -2063,14 +2063,18 @@ char *synthesize_perf_probe_command(struct perf_probe_event *pev)
 			goto out;
 
 	tmp = synthesize_perf_probe_point(&pev->point);
-	if (!tmp || strbuf_addstr(&buf, tmp) < 0)
+	if (!tmp || strbuf_addstr(&buf, tmp) < 0) {
+		free(tmp);
 		goto out;
+	}
 	free(tmp);
 
 	for (i = 0; i < pev->nargs; i++) {
 		tmp = synthesize_perf_probe_arg(pev->args + i);
-		if (!tmp || strbuf_addf(&buf, " %s", tmp) < 0)
+		if (!tmp || strbuf_addf(&buf, " %s", tmp) < 0) {
+			free(tmp);
 			goto out;
+		}
 		free(tmp);
 	}
 

From aeb50d3f2cd6255b7d065a91ed6a01784b208e6f Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 4 Aug 2023 13:30:06 -0300
Subject: [PATCH 0354/1189] perf probe: Make synthesize_perf_probe_point()
 private to probe-event.c

Not used in any other place, so just make it static.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/ZM0pjfOe6R4X%2Fcql@kernel.org/
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/probe-event.c | 4 +++-
 tools/perf/util/probe-event.h | 1 -
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 2835d87cb977..1a5b7fa459b2 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -53,6 +53,8 @@
 bool probe_event_dry_run;	/* Dry run flag */
 struct probe_conf probe_conf = { .magic_num = DEFAULT_PROBE_MAGIC_NUM };
 
+static char *synthesize_perf_probe_point(struct perf_probe_point *pp);
+
 #define semantic_error(msg ...) pr_err("Semantic error :" msg)
 
 int e_snprintf(char *str, size_t size, const char *format, ...)
@@ -2010,7 +2012,7 @@ out:
 }
 
 /* Compose only probe point (not argument) */
-char *synthesize_perf_probe_point(struct perf_probe_point *pp)
+static char *synthesize_perf_probe_point(struct perf_probe_point *pp)
 {
 	struct strbuf buf;
 	char *tmp, *ret = NULL;
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 8ad5b1579f1d..7e3b6c3d1f74 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -137,7 +137,6 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev);
 char *synthesize_perf_probe_command(struct perf_probe_event *pev);
 char *synthesize_probe_trace_command(struct probe_trace_event *tev);
 char *synthesize_perf_probe_arg(struct perf_probe_arg *pa);
-char *synthesize_perf_probe_point(struct perf_probe_point *pp);
 
 int perf_probe_event__copy(struct perf_probe_event *dst,
 			   struct perf_probe_event *src);

From e98b1085be795354073debd371e2889bea4902b9 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Tue, 11 Jul 2023 17:40:47 +0530
Subject: [PATCH 0355/1189] RISC-V: KVM: Factor-out ONE_REG related code to its
 own source file

The VCPU ONE_REG interface has grown over time and it will continue
to grow with new ISA extensions and other features. Let us move all
ONE_REG related code to its own source file so that vcpu.c only
focuses only on high-level VCPU functions.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/include/asm/kvm_host.h |   6 +
 arch/riscv/kvm/Makefile           |   1 +
 arch/riscv/kvm/vcpu.c             | 529 +---------------------------
 arch/riscv/kvm/vcpu_onereg.c      | 548 ++++++++++++++++++++++++++++++
 4 files changed, 556 insertions(+), 528 deletions(-)
 create mode 100644 arch/riscv/kvm/vcpu_onereg.c

diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index 2d8ee53b66c7..55bc7bdbff48 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -337,6 +337,12 @@ int kvm_riscv_vcpu_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 
 void __kvm_riscv_switch_to(struct kvm_vcpu_arch *vcpu_arch);
 
+void kvm_riscv_vcpu_setup_isa(struct kvm_vcpu *vcpu);
+int kvm_riscv_vcpu_get_reg(struct kvm_vcpu *vcpu,
+			   const struct kvm_one_reg *reg);
+int kvm_riscv_vcpu_set_reg(struct kvm_vcpu *vcpu,
+			   const struct kvm_one_reg *reg);
+
 int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq);
 int kvm_riscv_vcpu_unset_interrupt(struct kvm_vcpu *vcpu, unsigned int irq);
 void kvm_riscv_vcpu_flush_interrupts(struct kvm_vcpu *vcpu);
diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile
index fee0671e2dc1..4c2067fc59fc 100644
--- a/arch/riscv/kvm/Makefile
+++ b/arch/riscv/kvm/Makefile
@@ -19,6 +19,7 @@ kvm-y += vcpu_exit.o
 kvm-y += vcpu_fp.o
 kvm-y += vcpu_vector.o
 kvm-y += vcpu_insn.o
+kvm-y += vcpu_onereg.o
 kvm-y += vcpu_switch.o
 kvm-y += vcpu_sbi.o
 kvm-$(CONFIG_RISCV_SBI_V01) += vcpu_sbi_v01.o
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index d12ef99901fc..452d6548e951 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -13,16 +13,12 @@
 #include <linux/kdebug.h>
 #include <linux/module.h>
 #include <linux/percpu.h>
-#include <linux/uaccess.h>
 #include <linux/vmalloc.h>
 #include <linux/sched/signal.h>
 #include <linux/fs.h>
 #include <linux/kvm_host.h>
 #include <asm/csr.h>
 #include <asm/cacheflush.h>
-#include <asm/hwcap.h>
-#include <asm/sbi.h>
-#include <asm/vector.h>
 #include <asm/kvm_vcpu_vector.h>
 
 const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
@@ -46,79 +42,6 @@ const struct kvm_stats_header kvm_vcpu_stats_header = {
 		       sizeof(kvm_vcpu_stats_desc),
 };
 
-#define KVM_RISCV_BASE_ISA_MASK		GENMASK(25, 0)
-
-#define KVM_ISA_EXT_ARR(ext)		[KVM_RISCV_ISA_EXT_##ext] = RISCV_ISA_EXT_##ext
-
-/* Mapping between KVM ISA Extension ID & Host ISA extension ID */
-static const unsigned long kvm_isa_ext_arr[] = {
-	[KVM_RISCV_ISA_EXT_A] = RISCV_ISA_EXT_a,
-	[KVM_RISCV_ISA_EXT_C] = RISCV_ISA_EXT_c,
-	[KVM_RISCV_ISA_EXT_D] = RISCV_ISA_EXT_d,
-	[KVM_RISCV_ISA_EXT_F] = RISCV_ISA_EXT_f,
-	[KVM_RISCV_ISA_EXT_H] = RISCV_ISA_EXT_h,
-	[KVM_RISCV_ISA_EXT_I] = RISCV_ISA_EXT_i,
-	[KVM_RISCV_ISA_EXT_M] = RISCV_ISA_EXT_m,
-	[KVM_RISCV_ISA_EXT_V] = RISCV_ISA_EXT_v,
-
-	KVM_ISA_EXT_ARR(SSAIA),
-	KVM_ISA_EXT_ARR(SSTC),
-	KVM_ISA_EXT_ARR(SVINVAL),
-	KVM_ISA_EXT_ARR(SVNAPOT),
-	KVM_ISA_EXT_ARR(SVPBMT),
-	KVM_ISA_EXT_ARR(ZBB),
-	KVM_ISA_EXT_ARR(ZIHINTPAUSE),
-	KVM_ISA_EXT_ARR(ZICBOM),
-	KVM_ISA_EXT_ARR(ZICBOZ),
-};
-
-static unsigned long kvm_riscv_vcpu_base2isa_ext(unsigned long base_ext)
-{
-	unsigned long i;
-
-	for (i = 0; i < KVM_RISCV_ISA_EXT_MAX; i++) {
-		if (kvm_isa_ext_arr[i] == base_ext)
-			return i;
-	}
-
-	return KVM_RISCV_ISA_EXT_MAX;
-}
-
-static bool kvm_riscv_vcpu_isa_enable_allowed(unsigned long ext)
-{
-	switch (ext) {
-	case KVM_RISCV_ISA_EXT_H:
-		return false;
-	case KVM_RISCV_ISA_EXT_V:
-		return riscv_v_vstate_ctrl_user_allowed();
-	default:
-		break;
-	}
-
-	return true;
-}
-
-static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
-{
-	switch (ext) {
-	case KVM_RISCV_ISA_EXT_A:
-	case KVM_RISCV_ISA_EXT_C:
-	case KVM_RISCV_ISA_EXT_I:
-	case KVM_RISCV_ISA_EXT_M:
-	case KVM_RISCV_ISA_EXT_SSAIA:
-	case KVM_RISCV_ISA_EXT_SSTC:
-	case KVM_RISCV_ISA_EXT_SVINVAL:
-	case KVM_RISCV_ISA_EXT_SVNAPOT:
-	case KVM_RISCV_ISA_EXT_ZIHINTPAUSE:
-	case KVM_RISCV_ISA_EXT_ZBB:
-		return false;
-	default:
-		break;
-	}
-
-	return true;
-}
-
 static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
@@ -176,7 +99,6 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	int rc;
 	struct kvm_cpu_context *cntx;
 	struct kvm_vcpu_csr *reset_csr = &vcpu->arch.guest_reset_csr;
-	unsigned long host_isa, i;
 
 	/* Mark this VCPU never ran */
 	vcpu->arch.ran_atleast_once = false;
@@ -184,12 +106,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	bitmap_zero(vcpu->arch.isa, RISCV_ISA_EXT_MAX);
 
 	/* Setup ISA features available to VCPU */
-	for (i = 0; i < ARRAY_SIZE(kvm_isa_ext_arr); i++) {
-		host_isa = kvm_isa_ext_arr[i];
-		if (__riscv_isa_extension_available(NULL, host_isa) &&
-		    kvm_riscv_vcpu_isa_enable_allowed(i))
-			set_bit(host_isa, vcpu->arch.isa);
-	}
+	kvm_riscv_vcpu_setup_isa(vcpu);
 
 	/* Setup vendor, arch, and implementation details */
 	vcpu->arch.mvendorid = sbi_get_mvendorid();
@@ -294,450 +211,6 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
 	return VM_FAULT_SIGBUS;
 }
 
-static int kvm_riscv_vcpu_get_reg_config(struct kvm_vcpu *vcpu,
-					 const struct kvm_one_reg *reg)
-{
-	unsigned long __user *uaddr =
-			(unsigned long __user *)(unsigned long)reg->addr;
-	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
-					    KVM_REG_SIZE_MASK |
-					    KVM_REG_RISCV_CONFIG);
-	unsigned long reg_val;
-
-	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
-		return -EINVAL;
-
-	switch (reg_num) {
-	case KVM_REG_RISCV_CONFIG_REG(isa):
-		reg_val = vcpu->arch.isa[0] & KVM_RISCV_BASE_ISA_MASK;
-		break;
-	case KVM_REG_RISCV_CONFIG_REG(zicbom_block_size):
-		if (!riscv_isa_extension_available(vcpu->arch.isa, ZICBOM))
-			return -EINVAL;
-		reg_val = riscv_cbom_block_size;
-		break;
-	case KVM_REG_RISCV_CONFIG_REG(zicboz_block_size):
-		if (!riscv_isa_extension_available(vcpu->arch.isa, ZICBOZ))
-			return -EINVAL;
-		reg_val = riscv_cboz_block_size;
-		break;
-	case KVM_REG_RISCV_CONFIG_REG(mvendorid):
-		reg_val = vcpu->arch.mvendorid;
-		break;
-	case KVM_REG_RISCV_CONFIG_REG(marchid):
-		reg_val = vcpu->arch.marchid;
-		break;
-	case KVM_REG_RISCV_CONFIG_REG(mimpid):
-		reg_val = vcpu->arch.mimpid;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
-		return -EFAULT;
-
-	return 0;
-}
-
-static int kvm_riscv_vcpu_set_reg_config(struct kvm_vcpu *vcpu,
-					 const struct kvm_one_reg *reg)
-{
-	unsigned long __user *uaddr =
-			(unsigned long __user *)(unsigned long)reg->addr;
-	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
-					    KVM_REG_SIZE_MASK |
-					    KVM_REG_RISCV_CONFIG);
-	unsigned long i, isa_ext, reg_val;
-
-	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
-		return -EINVAL;
-
-	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
-		return -EFAULT;
-
-	switch (reg_num) {
-	case KVM_REG_RISCV_CONFIG_REG(isa):
-		/*
-		 * This ONE REG interface is only defined for
-		 * single letter extensions.
-		 */
-		if (fls(reg_val) >= RISCV_ISA_EXT_BASE)
-			return -EINVAL;
-
-		if (!vcpu->arch.ran_atleast_once) {
-			/* Ignore the enable/disable request for certain extensions */
-			for (i = 0; i < RISCV_ISA_EXT_BASE; i++) {
-				isa_ext = kvm_riscv_vcpu_base2isa_ext(i);
-				if (isa_ext >= KVM_RISCV_ISA_EXT_MAX) {
-					reg_val &= ~BIT(i);
-					continue;
-				}
-				if (!kvm_riscv_vcpu_isa_enable_allowed(isa_ext))
-					if (reg_val & BIT(i))
-						reg_val &= ~BIT(i);
-				if (!kvm_riscv_vcpu_isa_disable_allowed(isa_ext))
-					if (!(reg_val & BIT(i)))
-						reg_val |= BIT(i);
-			}
-			reg_val &= riscv_isa_extension_base(NULL);
-			/* Do not modify anything beyond single letter extensions */
-			reg_val = (vcpu->arch.isa[0] & ~KVM_RISCV_BASE_ISA_MASK) |
-				  (reg_val & KVM_RISCV_BASE_ISA_MASK);
-			vcpu->arch.isa[0] = reg_val;
-			kvm_riscv_vcpu_fp_reset(vcpu);
-		} else {
-			return -EOPNOTSUPP;
-		}
-		break;
-	case KVM_REG_RISCV_CONFIG_REG(zicbom_block_size):
-		return -EOPNOTSUPP;
-	case KVM_REG_RISCV_CONFIG_REG(zicboz_block_size):
-		return -EOPNOTSUPP;
-	case KVM_REG_RISCV_CONFIG_REG(mvendorid):
-		if (!vcpu->arch.ran_atleast_once)
-			vcpu->arch.mvendorid = reg_val;
-		else
-			return -EBUSY;
-		break;
-	case KVM_REG_RISCV_CONFIG_REG(marchid):
-		if (!vcpu->arch.ran_atleast_once)
-			vcpu->arch.marchid = reg_val;
-		else
-			return -EBUSY;
-		break;
-	case KVM_REG_RISCV_CONFIG_REG(mimpid):
-		if (!vcpu->arch.ran_atleast_once)
-			vcpu->arch.mimpid = reg_val;
-		else
-			return -EBUSY;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int kvm_riscv_vcpu_get_reg_core(struct kvm_vcpu *vcpu,
-				       const struct kvm_one_reg *reg)
-{
-	struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
-	unsigned long __user *uaddr =
-			(unsigned long __user *)(unsigned long)reg->addr;
-	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
-					    KVM_REG_SIZE_MASK |
-					    KVM_REG_RISCV_CORE);
-	unsigned long reg_val;
-
-	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
-		return -EINVAL;
-	if (reg_num >= sizeof(struct kvm_riscv_core) / sizeof(unsigned long))
-		return -EINVAL;
-
-	if (reg_num == KVM_REG_RISCV_CORE_REG(regs.pc))
-		reg_val = cntx->sepc;
-	else if (KVM_REG_RISCV_CORE_REG(regs.pc) < reg_num &&
-		 reg_num <= KVM_REG_RISCV_CORE_REG(regs.t6))
-		reg_val = ((unsigned long *)cntx)[reg_num];
-	else if (reg_num == KVM_REG_RISCV_CORE_REG(mode))
-		reg_val = (cntx->sstatus & SR_SPP) ?
-				KVM_RISCV_MODE_S : KVM_RISCV_MODE_U;
-	else
-		return -EINVAL;
-
-	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
-		return -EFAULT;
-
-	return 0;
-}
-
-static int kvm_riscv_vcpu_set_reg_core(struct kvm_vcpu *vcpu,
-				       const struct kvm_one_reg *reg)
-{
-	struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
-	unsigned long __user *uaddr =
-			(unsigned long __user *)(unsigned long)reg->addr;
-	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
-					    KVM_REG_SIZE_MASK |
-					    KVM_REG_RISCV_CORE);
-	unsigned long reg_val;
-
-	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
-		return -EINVAL;
-	if (reg_num >= sizeof(struct kvm_riscv_core) / sizeof(unsigned long))
-		return -EINVAL;
-
-	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
-		return -EFAULT;
-
-	if (reg_num == KVM_REG_RISCV_CORE_REG(regs.pc))
-		cntx->sepc = reg_val;
-	else if (KVM_REG_RISCV_CORE_REG(regs.pc) < reg_num &&
-		 reg_num <= KVM_REG_RISCV_CORE_REG(regs.t6))
-		((unsigned long *)cntx)[reg_num] = reg_val;
-	else if (reg_num == KVM_REG_RISCV_CORE_REG(mode)) {
-		if (reg_val == KVM_RISCV_MODE_S)
-			cntx->sstatus |= SR_SPP;
-		else
-			cntx->sstatus &= ~SR_SPP;
-	} else
-		return -EINVAL;
-
-	return 0;
-}
-
-static int kvm_riscv_vcpu_general_get_csr(struct kvm_vcpu *vcpu,
-					  unsigned long reg_num,
-					  unsigned long *out_val)
-{
-	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
-
-	if (reg_num >= sizeof(struct kvm_riscv_csr) / sizeof(unsigned long))
-		return -EINVAL;
-
-	if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) {
-		kvm_riscv_vcpu_flush_interrupts(vcpu);
-		*out_val = (csr->hvip >> VSIP_TO_HVIP_SHIFT) & VSIP_VALID_MASK;
-		*out_val |= csr->hvip & ~IRQ_LOCAL_MASK;
-	} else
-		*out_val = ((unsigned long *)csr)[reg_num];
-
-	return 0;
-}
-
-static inline int kvm_riscv_vcpu_general_set_csr(struct kvm_vcpu *vcpu,
-						 unsigned long reg_num,
-						 unsigned long reg_val)
-{
-	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
-
-	if (reg_num >= sizeof(struct kvm_riscv_csr) / sizeof(unsigned long))
-		return -EINVAL;
-
-	if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) {
-		reg_val &= VSIP_VALID_MASK;
-		reg_val <<= VSIP_TO_HVIP_SHIFT;
-	}
-
-	((unsigned long *)csr)[reg_num] = reg_val;
-
-	if (reg_num == KVM_REG_RISCV_CSR_REG(sip))
-		WRITE_ONCE(vcpu->arch.irqs_pending_mask[0], 0);
-
-	return 0;
-}
-
-static int kvm_riscv_vcpu_get_reg_csr(struct kvm_vcpu *vcpu,
-				      const struct kvm_one_reg *reg)
-{
-	int rc;
-	unsigned long __user *uaddr =
-			(unsigned long __user *)(unsigned long)reg->addr;
-	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
-					    KVM_REG_SIZE_MASK |
-					    KVM_REG_RISCV_CSR);
-	unsigned long reg_val, reg_subtype;
-
-	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
-		return -EINVAL;
-
-	reg_subtype = reg_num & KVM_REG_RISCV_SUBTYPE_MASK;
-	reg_num &= ~KVM_REG_RISCV_SUBTYPE_MASK;
-	switch (reg_subtype) {
-	case KVM_REG_RISCV_CSR_GENERAL:
-		rc = kvm_riscv_vcpu_general_get_csr(vcpu, reg_num, &reg_val);
-		break;
-	case KVM_REG_RISCV_CSR_AIA:
-		rc = kvm_riscv_vcpu_aia_get_csr(vcpu, reg_num, &reg_val);
-		break;
-	default:
-		rc = -EINVAL;
-		break;
-	}
-	if (rc)
-		return rc;
-
-	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
-		return -EFAULT;
-
-	return 0;
-}
-
-static int kvm_riscv_vcpu_set_reg_csr(struct kvm_vcpu *vcpu,
-				      const struct kvm_one_reg *reg)
-{
-	int rc;
-	unsigned long __user *uaddr =
-			(unsigned long __user *)(unsigned long)reg->addr;
-	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
-					    KVM_REG_SIZE_MASK |
-					    KVM_REG_RISCV_CSR);
-	unsigned long reg_val, reg_subtype;
-
-	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
-		return -EINVAL;
-
-	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
-		return -EFAULT;
-
-	reg_subtype = reg_num & KVM_REG_RISCV_SUBTYPE_MASK;
-	reg_num &= ~KVM_REG_RISCV_SUBTYPE_MASK;
-	switch (reg_subtype) {
-	case KVM_REG_RISCV_CSR_GENERAL:
-		rc = kvm_riscv_vcpu_general_set_csr(vcpu, reg_num, reg_val);
-		break;
-	case KVM_REG_RISCV_CSR_AIA:
-		rc = kvm_riscv_vcpu_aia_set_csr(vcpu, reg_num, reg_val);
-		break;
-	default:
-		rc = -EINVAL;
-		break;
-	}
-	if (rc)
-		return rc;
-
-	return 0;
-}
-
-static int kvm_riscv_vcpu_get_reg_isa_ext(struct kvm_vcpu *vcpu,
-					  const struct kvm_one_reg *reg)
-{
-	unsigned long __user *uaddr =
-			(unsigned long __user *)(unsigned long)reg->addr;
-	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
-					    KVM_REG_SIZE_MASK |
-					    KVM_REG_RISCV_ISA_EXT);
-	unsigned long reg_val = 0;
-	unsigned long host_isa_ext;
-
-	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
-		return -EINVAL;
-
-	if (reg_num >= KVM_RISCV_ISA_EXT_MAX ||
-	    reg_num >= ARRAY_SIZE(kvm_isa_ext_arr))
-		return -EINVAL;
-
-	host_isa_ext = kvm_isa_ext_arr[reg_num];
-	if (__riscv_isa_extension_available(vcpu->arch.isa, host_isa_ext))
-		reg_val = 1; /* Mark the given extension as available */
-
-	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
-		return -EFAULT;
-
-	return 0;
-}
-
-static int kvm_riscv_vcpu_set_reg_isa_ext(struct kvm_vcpu *vcpu,
-					  const struct kvm_one_reg *reg)
-{
-	unsigned long __user *uaddr =
-			(unsigned long __user *)(unsigned long)reg->addr;
-	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
-					    KVM_REG_SIZE_MASK |
-					    KVM_REG_RISCV_ISA_EXT);
-	unsigned long reg_val;
-	unsigned long host_isa_ext;
-
-	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
-		return -EINVAL;
-
-	if (reg_num >= KVM_RISCV_ISA_EXT_MAX ||
-	    reg_num >= ARRAY_SIZE(kvm_isa_ext_arr))
-		return -EINVAL;
-
-	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
-		return -EFAULT;
-
-	host_isa_ext = kvm_isa_ext_arr[reg_num];
-	if (!__riscv_isa_extension_available(NULL, host_isa_ext))
-		return	-EOPNOTSUPP;
-
-	if (!vcpu->arch.ran_atleast_once) {
-		/*
-		 * All multi-letter extension and a few single letter
-		 * extension can be disabled
-		 */
-		if (reg_val == 1 &&
-		    kvm_riscv_vcpu_isa_enable_allowed(reg_num))
-			set_bit(host_isa_ext, vcpu->arch.isa);
-		else if (!reg_val &&
-			 kvm_riscv_vcpu_isa_disable_allowed(reg_num))
-			clear_bit(host_isa_ext, vcpu->arch.isa);
-		else
-			return -EINVAL;
-		kvm_riscv_vcpu_fp_reset(vcpu);
-	} else {
-		return -EOPNOTSUPP;
-	}
-
-	return 0;
-}
-
-static int kvm_riscv_vcpu_set_reg(struct kvm_vcpu *vcpu,
-				  const struct kvm_one_reg *reg)
-{
-	switch (reg->id & KVM_REG_RISCV_TYPE_MASK) {
-	case KVM_REG_RISCV_CONFIG:
-		return kvm_riscv_vcpu_set_reg_config(vcpu, reg);
-	case KVM_REG_RISCV_CORE:
-		return kvm_riscv_vcpu_set_reg_core(vcpu, reg);
-	case KVM_REG_RISCV_CSR:
-		return kvm_riscv_vcpu_set_reg_csr(vcpu, reg);
-	case KVM_REG_RISCV_TIMER:
-		return kvm_riscv_vcpu_set_reg_timer(vcpu, reg);
-	case KVM_REG_RISCV_FP_F:
-		return kvm_riscv_vcpu_set_reg_fp(vcpu, reg,
-						 KVM_REG_RISCV_FP_F);
-	case KVM_REG_RISCV_FP_D:
-		return kvm_riscv_vcpu_set_reg_fp(vcpu, reg,
-						 KVM_REG_RISCV_FP_D);
-	case KVM_REG_RISCV_ISA_EXT:
-		return kvm_riscv_vcpu_set_reg_isa_ext(vcpu, reg);
-	case KVM_REG_RISCV_SBI_EXT:
-		return kvm_riscv_vcpu_set_reg_sbi_ext(vcpu, reg);
-	case KVM_REG_RISCV_VECTOR:
-		return kvm_riscv_vcpu_set_reg_vector(vcpu, reg,
-						 KVM_REG_RISCV_VECTOR);
-	default:
-		break;
-	}
-
-	return -EINVAL;
-}
-
-static int kvm_riscv_vcpu_get_reg(struct kvm_vcpu *vcpu,
-				  const struct kvm_one_reg *reg)
-{
-	switch (reg->id & KVM_REG_RISCV_TYPE_MASK) {
-	case KVM_REG_RISCV_CONFIG:
-		return kvm_riscv_vcpu_get_reg_config(vcpu, reg);
-	case KVM_REG_RISCV_CORE:
-		return kvm_riscv_vcpu_get_reg_core(vcpu, reg);
-	case KVM_REG_RISCV_CSR:
-		return kvm_riscv_vcpu_get_reg_csr(vcpu, reg);
-	case KVM_REG_RISCV_TIMER:
-		return kvm_riscv_vcpu_get_reg_timer(vcpu, reg);
-	case KVM_REG_RISCV_FP_F:
-		return kvm_riscv_vcpu_get_reg_fp(vcpu, reg,
-						 KVM_REG_RISCV_FP_F);
-	case KVM_REG_RISCV_FP_D:
-		return kvm_riscv_vcpu_get_reg_fp(vcpu, reg,
-						 KVM_REG_RISCV_FP_D);
-	case KVM_REG_RISCV_ISA_EXT:
-		return kvm_riscv_vcpu_get_reg_isa_ext(vcpu, reg);
-	case KVM_REG_RISCV_SBI_EXT:
-		return kvm_riscv_vcpu_get_reg_sbi_ext(vcpu, reg);
-	case KVM_REG_RISCV_VECTOR:
-		return kvm_riscv_vcpu_get_reg_vector(vcpu, reg,
-						 KVM_REG_RISCV_VECTOR);
-	default:
-		break;
-	}
-
-	return -EINVAL;
-}
-
 long kvm_arch_vcpu_async_ioctl(struct file *filp,
 			       unsigned int ioctl, unsigned long arg)
 {
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
new file mode 100644
index 000000000000..3efa2a77d2d9
--- /dev/null
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -0,0 +1,548 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 Western Digital Corporation or its affiliates.
+ * Copyright (C) 2023 Ventana Micro Systems Inc.
+ *
+ * Authors:
+ *	Anup Patel <apatel@ventanamicro.com>
+ */
+
+#include <linux/bitops.h>
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/uaccess.h>
+#include <linux/kvm_host.h>
+#include <asm/cacheflush.h>
+#include <asm/hwcap.h>
+#include <asm/kvm_vcpu_vector.h>
+#include <asm/vector.h>
+
+#define KVM_RISCV_BASE_ISA_MASK		GENMASK(25, 0)
+
+#define KVM_ISA_EXT_ARR(ext)		\
+[KVM_RISCV_ISA_EXT_##ext] = RISCV_ISA_EXT_##ext
+
+/* Mapping between KVM ISA Extension ID & Host ISA extension ID */
+static const unsigned long kvm_isa_ext_arr[] = {
+	[KVM_RISCV_ISA_EXT_A] = RISCV_ISA_EXT_a,
+	[KVM_RISCV_ISA_EXT_C] = RISCV_ISA_EXT_c,
+	[KVM_RISCV_ISA_EXT_D] = RISCV_ISA_EXT_d,
+	[KVM_RISCV_ISA_EXT_F] = RISCV_ISA_EXT_f,
+	[KVM_RISCV_ISA_EXT_H] = RISCV_ISA_EXT_h,
+	[KVM_RISCV_ISA_EXT_I] = RISCV_ISA_EXT_i,
+	[KVM_RISCV_ISA_EXT_M] = RISCV_ISA_EXT_m,
+	[KVM_RISCV_ISA_EXT_V] = RISCV_ISA_EXT_v,
+
+	KVM_ISA_EXT_ARR(SSAIA),
+	KVM_ISA_EXT_ARR(SSTC),
+	KVM_ISA_EXT_ARR(SVINVAL),
+	KVM_ISA_EXT_ARR(SVNAPOT),
+	KVM_ISA_EXT_ARR(SVPBMT),
+	KVM_ISA_EXT_ARR(ZBB),
+	KVM_ISA_EXT_ARR(ZIHINTPAUSE),
+	KVM_ISA_EXT_ARR(ZICBOM),
+	KVM_ISA_EXT_ARR(ZICBOZ),
+};
+
+static unsigned long kvm_riscv_vcpu_base2isa_ext(unsigned long base_ext)
+{
+	unsigned long i;
+
+	for (i = 0; i < KVM_RISCV_ISA_EXT_MAX; i++) {
+		if (kvm_isa_ext_arr[i] == base_ext)
+			return i;
+	}
+
+	return KVM_RISCV_ISA_EXT_MAX;
+}
+
+static bool kvm_riscv_vcpu_isa_enable_allowed(unsigned long ext)
+{
+	switch (ext) {
+	case KVM_RISCV_ISA_EXT_H:
+		return false;
+	case KVM_RISCV_ISA_EXT_V:
+		return riscv_v_vstate_ctrl_user_allowed();
+	default:
+		break;
+	}
+
+	return true;
+}
+
+static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
+{
+	switch (ext) {
+	case KVM_RISCV_ISA_EXT_A:
+	case KVM_RISCV_ISA_EXT_C:
+	case KVM_RISCV_ISA_EXT_I:
+	case KVM_RISCV_ISA_EXT_M:
+	case KVM_RISCV_ISA_EXT_SSAIA:
+	case KVM_RISCV_ISA_EXT_SSTC:
+	case KVM_RISCV_ISA_EXT_SVINVAL:
+	case KVM_RISCV_ISA_EXT_SVNAPOT:
+	case KVM_RISCV_ISA_EXT_ZIHINTPAUSE:
+	case KVM_RISCV_ISA_EXT_ZBB:
+		return false;
+	default:
+		break;
+	}
+
+	return true;
+}
+
+void kvm_riscv_vcpu_setup_isa(struct kvm_vcpu *vcpu)
+{
+	unsigned long host_isa, i;
+
+	for (i = 0; i < ARRAY_SIZE(kvm_isa_ext_arr); i++) {
+		host_isa = kvm_isa_ext_arr[i];
+		if (__riscv_isa_extension_available(NULL, host_isa) &&
+		    kvm_riscv_vcpu_isa_enable_allowed(i))
+			set_bit(host_isa, vcpu->arch.isa);
+	}
+}
+
+static int kvm_riscv_vcpu_get_reg_config(struct kvm_vcpu *vcpu,
+					 const struct kvm_one_reg *reg)
+{
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_CONFIG);
+	unsigned long reg_val;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+
+	switch (reg_num) {
+	case KVM_REG_RISCV_CONFIG_REG(isa):
+		reg_val = vcpu->arch.isa[0] & KVM_RISCV_BASE_ISA_MASK;
+		break;
+	case KVM_REG_RISCV_CONFIG_REG(zicbom_block_size):
+		if (!riscv_isa_extension_available(vcpu->arch.isa, ZICBOM))
+			return -EINVAL;
+		reg_val = riscv_cbom_block_size;
+		break;
+	case KVM_REG_RISCV_CONFIG_REG(zicboz_block_size):
+		if (!riscv_isa_extension_available(vcpu->arch.isa, ZICBOZ))
+			return -EINVAL;
+		reg_val = riscv_cboz_block_size;
+		break;
+	case KVM_REG_RISCV_CONFIG_REG(mvendorid):
+		reg_val = vcpu->arch.mvendorid;
+		break;
+	case KVM_REG_RISCV_CONFIG_REG(marchid):
+		reg_val = vcpu->arch.marchid;
+		break;
+	case KVM_REG_RISCV_CONFIG_REG(mimpid):
+		reg_val = vcpu->arch.mimpid;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int kvm_riscv_vcpu_set_reg_config(struct kvm_vcpu *vcpu,
+					 const struct kvm_one_reg *reg)
+{
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_CONFIG);
+	unsigned long i, isa_ext, reg_val;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+
+	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	switch (reg_num) {
+	case KVM_REG_RISCV_CONFIG_REG(isa):
+		/*
+		 * This ONE REG interface is only defined for
+		 * single letter extensions.
+		 */
+		if (fls(reg_val) >= RISCV_ISA_EXT_BASE)
+			return -EINVAL;
+
+		if (!vcpu->arch.ran_atleast_once) {
+			/* Ignore the enable/disable request for certain extensions */
+			for (i = 0; i < RISCV_ISA_EXT_BASE; i++) {
+				isa_ext = kvm_riscv_vcpu_base2isa_ext(i);
+				if (isa_ext >= KVM_RISCV_ISA_EXT_MAX) {
+					reg_val &= ~BIT(i);
+					continue;
+				}
+				if (!kvm_riscv_vcpu_isa_enable_allowed(isa_ext))
+					if (reg_val & BIT(i))
+						reg_val &= ~BIT(i);
+				if (!kvm_riscv_vcpu_isa_disable_allowed(isa_ext))
+					if (!(reg_val & BIT(i)))
+						reg_val |= BIT(i);
+			}
+			reg_val &= riscv_isa_extension_base(NULL);
+			/* Do not modify anything beyond single letter extensions */
+			reg_val = (vcpu->arch.isa[0] & ~KVM_RISCV_BASE_ISA_MASK) |
+				  (reg_val & KVM_RISCV_BASE_ISA_MASK);
+			vcpu->arch.isa[0] = reg_val;
+			kvm_riscv_vcpu_fp_reset(vcpu);
+		} else {
+			return -EOPNOTSUPP;
+		}
+		break;
+	case KVM_REG_RISCV_CONFIG_REG(zicbom_block_size):
+		return -EOPNOTSUPP;
+	case KVM_REG_RISCV_CONFIG_REG(zicboz_block_size):
+		return -EOPNOTSUPP;
+	case KVM_REG_RISCV_CONFIG_REG(mvendorid):
+		if (!vcpu->arch.ran_atleast_once)
+			vcpu->arch.mvendorid = reg_val;
+		else
+			return -EBUSY;
+		break;
+	case KVM_REG_RISCV_CONFIG_REG(marchid):
+		if (!vcpu->arch.ran_atleast_once)
+			vcpu->arch.marchid = reg_val;
+		else
+			return -EBUSY;
+		break;
+	case KVM_REG_RISCV_CONFIG_REG(mimpid):
+		if (!vcpu->arch.ran_atleast_once)
+			vcpu->arch.mimpid = reg_val;
+		else
+			return -EBUSY;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int kvm_riscv_vcpu_get_reg_core(struct kvm_vcpu *vcpu,
+				       const struct kvm_one_reg *reg)
+{
+	struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_CORE);
+	unsigned long reg_val;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+	if (reg_num >= sizeof(struct kvm_riscv_core) / sizeof(unsigned long))
+		return -EINVAL;
+
+	if (reg_num == KVM_REG_RISCV_CORE_REG(regs.pc))
+		reg_val = cntx->sepc;
+	else if (KVM_REG_RISCV_CORE_REG(regs.pc) < reg_num &&
+		 reg_num <= KVM_REG_RISCV_CORE_REG(regs.t6))
+		reg_val = ((unsigned long *)cntx)[reg_num];
+	else if (reg_num == KVM_REG_RISCV_CORE_REG(mode))
+		reg_val = (cntx->sstatus & SR_SPP) ?
+				KVM_RISCV_MODE_S : KVM_RISCV_MODE_U;
+	else
+		return -EINVAL;
+
+	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int kvm_riscv_vcpu_set_reg_core(struct kvm_vcpu *vcpu,
+				       const struct kvm_one_reg *reg)
+{
+	struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_CORE);
+	unsigned long reg_val;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+	if (reg_num >= sizeof(struct kvm_riscv_core) / sizeof(unsigned long))
+		return -EINVAL;
+
+	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	if (reg_num == KVM_REG_RISCV_CORE_REG(regs.pc))
+		cntx->sepc = reg_val;
+	else if (KVM_REG_RISCV_CORE_REG(regs.pc) < reg_num &&
+		 reg_num <= KVM_REG_RISCV_CORE_REG(regs.t6))
+		((unsigned long *)cntx)[reg_num] = reg_val;
+	else if (reg_num == KVM_REG_RISCV_CORE_REG(mode)) {
+		if (reg_val == KVM_RISCV_MODE_S)
+			cntx->sstatus |= SR_SPP;
+		else
+			cntx->sstatus &= ~SR_SPP;
+	} else
+		return -EINVAL;
+
+	return 0;
+}
+
+static int kvm_riscv_vcpu_general_get_csr(struct kvm_vcpu *vcpu,
+					  unsigned long reg_num,
+					  unsigned long *out_val)
+{
+	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
+
+	if (reg_num >= sizeof(struct kvm_riscv_csr) / sizeof(unsigned long))
+		return -EINVAL;
+
+	if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) {
+		kvm_riscv_vcpu_flush_interrupts(vcpu);
+		*out_val = (csr->hvip >> VSIP_TO_HVIP_SHIFT) & VSIP_VALID_MASK;
+		*out_val |= csr->hvip & ~IRQ_LOCAL_MASK;
+	} else
+		*out_val = ((unsigned long *)csr)[reg_num];
+
+	return 0;
+}
+
+static int kvm_riscv_vcpu_general_set_csr(struct kvm_vcpu *vcpu,
+					  unsigned long reg_num,
+					  unsigned long reg_val)
+{
+	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
+
+	if (reg_num >= sizeof(struct kvm_riscv_csr) / sizeof(unsigned long))
+		return -EINVAL;
+
+	if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) {
+		reg_val &= VSIP_VALID_MASK;
+		reg_val <<= VSIP_TO_HVIP_SHIFT;
+	}
+
+	((unsigned long *)csr)[reg_num] = reg_val;
+
+	if (reg_num == KVM_REG_RISCV_CSR_REG(sip))
+		WRITE_ONCE(vcpu->arch.irqs_pending_mask[0], 0);
+
+	return 0;
+}
+
+static int kvm_riscv_vcpu_get_reg_csr(struct kvm_vcpu *vcpu,
+				      const struct kvm_one_reg *reg)
+{
+	int rc;
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_CSR);
+	unsigned long reg_val, reg_subtype;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+
+	reg_subtype = reg_num & KVM_REG_RISCV_SUBTYPE_MASK;
+	reg_num &= ~KVM_REG_RISCV_SUBTYPE_MASK;
+	switch (reg_subtype) {
+	case KVM_REG_RISCV_CSR_GENERAL:
+		rc = kvm_riscv_vcpu_general_get_csr(vcpu, reg_num, &reg_val);
+		break;
+	case KVM_REG_RISCV_CSR_AIA:
+		rc = kvm_riscv_vcpu_aia_get_csr(vcpu, reg_num, &reg_val);
+		break;
+	default:
+		rc = -EINVAL;
+		break;
+	}
+	if (rc)
+		return rc;
+
+	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int kvm_riscv_vcpu_set_reg_csr(struct kvm_vcpu *vcpu,
+				      const struct kvm_one_reg *reg)
+{
+	int rc;
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_CSR);
+	unsigned long reg_val, reg_subtype;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+
+	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	reg_subtype = reg_num & KVM_REG_RISCV_SUBTYPE_MASK;
+	reg_num &= ~KVM_REG_RISCV_SUBTYPE_MASK;
+	switch (reg_subtype) {
+	case KVM_REG_RISCV_CSR_GENERAL:
+		rc = kvm_riscv_vcpu_general_set_csr(vcpu, reg_num, reg_val);
+		break;
+	case KVM_REG_RISCV_CSR_AIA:
+		rc = kvm_riscv_vcpu_aia_set_csr(vcpu, reg_num, reg_val);
+		break;
+	default:
+		rc = -EINVAL;
+		break;
+	}
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+static int kvm_riscv_vcpu_get_reg_isa_ext(struct kvm_vcpu *vcpu,
+					  const struct kvm_one_reg *reg)
+{
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_ISA_EXT);
+	unsigned long reg_val = 0;
+	unsigned long host_isa_ext;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+
+	if (reg_num >= KVM_RISCV_ISA_EXT_MAX ||
+	    reg_num >= ARRAY_SIZE(kvm_isa_ext_arr))
+		return -EINVAL;
+
+	host_isa_ext = kvm_isa_ext_arr[reg_num];
+	if (__riscv_isa_extension_available(vcpu->arch.isa, host_isa_ext))
+		reg_val = 1; /* Mark the given extension as available */
+
+	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int kvm_riscv_vcpu_set_reg_isa_ext(struct kvm_vcpu *vcpu,
+					  const struct kvm_one_reg *reg)
+{
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_ISA_EXT);
+	unsigned long reg_val;
+	unsigned long host_isa_ext;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+
+	if (reg_num >= KVM_RISCV_ISA_EXT_MAX ||
+	    reg_num >= ARRAY_SIZE(kvm_isa_ext_arr))
+		return -EINVAL;
+
+	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	host_isa_ext = kvm_isa_ext_arr[reg_num];
+	if (!__riscv_isa_extension_available(NULL, host_isa_ext))
+		return	-EOPNOTSUPP;
+
+	if (!vcpu->arch.ran_atleast_once) {
+		/*
+		 * All multi-letter extension and a few single letter
+		 * extension can be disabled
+		 */
+		if (reg_val == 1 &&
+		    kvm_riscv_vcpu_isa_enable_allowed(reg_num))
+			set_bit(host_isa_ext, vcpu->arch.isa);
+		else if (!reg_val &&
+			 kvm_riscv_vcpu_isa_disable_allowed(reg_num))
+			clear_bit(host_isa_ext, vcpu->arch.isa);
+		else
+			return -EINVAL;
+		kvm_riscv_vcpu_fp_reset(vcpu);
+	} else {
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+int kvm_riscv_vcpu_set_reg(struct kvm_vcpu *vcpu,
+			   const struct kvm_one_reg *reg)
+{
+	switch (reg->id & KVM_REG_RISCV_TYPE_MASK) {
+	case KVM_REG_RISCV_CONFIG:
+		return kvm_riscv_vcpu_set_reg_config(vcpu, reg);
+	case KVM_REG_RISCV_CORE:
+		return kvm_riscv_vcpu_set_reg_core(vcpu, reg);
+	case KVM_REG_RISCV_CSR:
+		return kvm_riscv_vcpu_set_reg_csr(vcpu, reg);
+	case KVM_REG_RISCV_TIMER:
+		return kvm_riscv_vcpu_set_reg_timer(vcpu, reg);
+	case KVM_REG_RISCV_FP_F:
+		return kvm_riscv_vcpu_set_reg_fp(vcpu, reg,
+						 KVM_REG_RISCV_FP_F);
+	case KVM_REG_RISCV_FP_D:
+		return kvm_riscv_vcpu_set_reg_fp(vcpu, reg,
+						 KVM_REG_RISCV_FP_D);
+	case KVM_REG_RISCV_ISA_EXT:
+		return kvm_riscv_vcpu_set_reg_isa_ext(vcpu, reg);
+	case KVM_REG_RISCV_SBI_EXT:
+		return kvm_riscv_vcpu_set_reg_sbi_ext(vcpu, reg);
+	case KVM_REG_RISCV_VECTOR:
+		return kvm_riscv_vcpu_set_reg_vector(vcpu, reg,
+						 KVM_REG_RISCV_VECTOR);
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+
+int kvm_riscv_vcpu_get_reg(struct kvm_vcpu *vcpu,
+			   const struct kvm_one_reg *reg)
+{
+	switch (reg->id & KVM_REG_RISCV_TYPE_MASK) {
+	case KVM_REG_RISCV_CONFIG:
+		return kvm_riscv_vcpu_get_reg_config(vcpu, reg);
+	case KVM_REG_RISCV_CORE:
+		return kvm_riscv_vcpu_get_reg_core(vcpu, reg);
+	case KVM_REG_RISCV_CSR:
+		return kvm_riscv_vcpu_get_reg_csr(vcpu, reg);
+	case KVM_REG_RISCV_TIMER:
+		return kvm_riscv_vcpu_get_reg_timer(vcpu, reg);
+	case KVM_REG_RISCV_FP_F:
+		return kvm_riscv_vcpu_get_reg_fp(vcpu, reg,
+						 KVM_REG_RISCV_FP_F);
+	case KVM_REG_RISCV_FP_D:
+		return kvm_riscv_vcpu_get_reg_fp(vcpu, reg,
+						 KVM_REG_RISCV_FP_D);
+	case KVM_REG_RISCV_ISA_EXT:
+		return kvm_riscv_vcpu_get_reg_isa_ext(vcpu, reg);
+	case KVM_REG_RISCV_SBI_EXT:
+		return kvm_riscv_vcpu_get_reg_sbi_ext(vcpu, reg);
+	case KVM_REG_RISCV_VECTOR:
+		return kvm_riscv_vcpu_get_reg_vector(vcpu, reg,
+						 KVM_REG_RISCV_VECTOR);
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}

From 613029442a4b837d3f8ce8ab08064f095ecdbdb6 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Tue, 11 Jul 2023 22:11:16 +0530
Subject: [PATCH 0356/1189] RISC-V: KVM: Extend ONE_REG to enable/disable
 multiple ISA extensions

Currently, the ISA extension ONE_REG interface only allows enabling or
disabling one extension at a time. To improve this, we extend the ISA
extension ONE_REG interface (similar to SBI extension ONE_REG interface)
so that KVM user space can enable/disable multiple extensions in one
ioctl.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/include/uapi/asm/kvm.h |   9 ++
 arch/riscv/kvm/vcpu_onereg.c      | 153 ++++++++++++++++++++++++------
 2 files changed, 133 insertions(+), 29 deletions(-)

diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index 930fdc4101cd..6c2285f86545 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -193,6 +193,15 @@ enum KVM_RISCV_SBI_EXT_ID {
 
 /* ISA Extension registers are mapped as type 7 */
 #define KVM_REG_RISCV_ISA_EXT		(0x07 << KVM_REG_RISCV_TYPE_SHIFT)
+#define KVM_REG_RISCV_ISA_SINGLE	(0x0 << KVM_REG_RISCV_SUBTYPE_SHIFT)
+#define KVM_REG_RISCV_ISA_MULTI_EN	(0x1 << KVM_REG_RISCV_SUBTYPE_SHIFT)
+#define KVM_REG_RISCV_ISA_MULTI_DIS	(0x2 << KVM_REG_RISCV_SUBTYPE_SHIFT)
+#define KVM_REG_RISCV_ISA_MULTI_REG(__ext_id)	\
+		((__ext_id) / __BITS_PER_LONG)
+#define KVM_REG_RISCV_ISA_MULTI_MASK(__ext_id)	\
+		(1UL << ((__ext_id) % __BITS_PER_LONG))
+#define KVM_REG_RISCV_ISA_MULTI_REG_LAST	\
+		KVM_REG_RISCV_ISA_MULTI_REG(KVM_RISCV_ISA_EXT_MAX - 1)
 
 /* SBI extension registers are mapped as type 8 */
 #define KVM_REG_RISCV_SBI_EXT		(0x08 << KVM_REG_RISCV_TYPE_SHIFT)
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index 3efa2a77d2d9..c57c7fa260c2 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -409,55 +409,34 @@ static int kvm_riscv_vcpu_set_reg_csr(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-static int kvm_riscv_vcpu_get_reg_isa_ext(struct kvm_vcpu *vcpu,
-					  const struct kvm_one_reg *reg)
+static int riscv_vcpu_get_isa_ext_single(struct kvm_vcpu *vcpu,
+					 unsigned long reg_num,
+					 unsigned long *reg_val)
 {
-	unsigned long __user *uaddr =
-			(unsigned long __user *)(unsigned long)reg->addr;
-	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
-					    KVM_REG_SIZE_MASK |
-					    KVM_REG_RISCV_ISA_EXT);
-	unsigned long reg_val = 0;
 	unsigned long host_isa_ext;
 
-	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
-		return -EINVAL;
-
 	if (reg_num >= KVM_RISCV_ISA_EXT_MAX ||
 	    reg_num >= ARRAY_SIZE(kvm_isa_ext_arr))
 		return -EINVAL;
 
+	*reg_val = 0;
 	host_isa_ext = kvm_isa_ext_arr[reg_num];
 	if (__riscv_isa_extension_available(vcpu->arch.isa, host_isa_ext))
-		reg_val = 1; /* Mark the given extension as available */
-
-	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
-		return -EFAULT;
+		*reg_val = 1; /* Mark the given extension as available */
 
 	return 0;
 }
 
-static int kvm_riscv_vcpu_set_reg_isa_ext(struct kvm_vcpu *vcpu,
-					  const struct kvm_one_reg *reg)
+static int riscv_vcpu_set_isa_ext_single(struct kvm_vcpu *vcpu,
+					 unsigned long reg_num,
+					 unsigned long reg_val)
 {
-	unsigned long __user *uaddr =
-			(unsigned long __user *)(unsigned long)reg->addr;
-	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
-					    KVM_REG_SIZE_MASK |
-					    KVM_REG_RISCV_ISA_EXT);
-	unsigned long reg_val;
 	unsigned long host_isa_ext;
 
-	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
-		return -EINVAL;
-
 	if (reg_num >= KVM_RISCV_ISA_EXT_MAX ||
 	    reg_num >= ARRAY_SIZE(kvm_isa_ext_arr))
 		return -EINVAL;
 
-	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
-		return -EFAULT;
-
 	host_isa_ext = kvm_isa_ext_arr[reg_num];
 	if (!__riscv_isa_extension_available(NULL, host_isa_ext))
 		return	-EOPNOTSUPP;
@@ -483,6 +462,122 @@ static int kvm_riscv_vcpu_set_reg_isa_ext(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static int riscv_vcpu_get_isa_ext_multi(struct kvm_vcpu *vcpu,
+					unsigned long reg_num,
+					unsigned long *reg_val)
+{
+	unsigned long i, ext_id, ext_val;
+
+	if (reg_num > KVM_REG_RISCV_ISA_MULTI_REG_LAST)
+		return -EINVAL;
+
+	for (i = 0; i < BITS_PER_LONG; i++) {
+		ext_id = i + reg_num * BITS_PER_LONG;
+		if (ext_id >= KVM_RISCV_ISA_EXT_MAX)
+			break;
+
+		ext_val = 0;
+		riscv_vcpu_get_isa_ext_single(vcpu, ext_id, &ext_val);
+		if (ext_val)
+			*reg_val |= KVM_REG_RISCV_ISA_MULTI_MASK(ext_id);
+	}
+
+	return 0;
+}
+
+static int riscv_vcpu_set_isa_ext_multi(struct kvm_vcpu *vcpu,
+					unsigned long reg_num,
+					unsigned long reg_val, bool enable)
+{
+	unsigned long i, ext_id;
+
+	if (reg_num > KVM_REG_RISCV_ISA_MULTI_REG_LAST)
+		return -EINVAL;
+
+	for_each_set_bit(i, &reg_val, BITS_PER_LONG) {
+		ext_id = i + reg_num * BITS_PER_LONG;
+		if (ext_id >= KVM_RISCV_ISA_EXT_MAX)
+			break;
+
+		riscv_vcpu_set_isa_ext_single(vcpu, ext_id, enable);
+	}
+
+	return 0;
+}
+
+static int kvm_riscv_vcpu_get_reg_isa_ext(struct kvm_vcpu *vcpu,
+					  const struct kvm_one_reg *reg)
+{
+	int rc;
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_ISA_EXT);
+	unsigned long reg_val, reg_subtype;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+
+	reg_subtype = reg_num & KVM_REG_RISCV_SUBTYPE_MASK;
+	reg_num &= ~KVM_REG_RISCV_SUBTYPE_MASK;
+
+	reg_val = 0;
+	switch (reg_subtype) {
+	case KVM_REG_RISCV_ISA_SINGLE:
+		rc = riscv_vcpu_get_isa_ext_single(vcpu, reg_num, &reg_val);
+		break;
+	case KVM_REG_RISCV_ISA_MULTI_EN:
+	case KVM_REG_RISCV_ISA_MULTI_DIS:
+		rc = riscv_vcpu_get_isa_ext_multi(vcpu, reg_num, &reg_val);
+		if (!rc && reg_subtype == KVM_REG_RISCV_ISA_MULTI_DIS)
+			reg_val = ~reg_val;
+		break;
+	default:
+		rc = -EINVAL;
+	}
+	if (rc)
+		return rc;
+
+	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int kvm_riscv_vcpu_set_reg_isa_ext(struct kvm_vcpu *vcpu,
+					  const struct kvm_one_reg *reg)
+{
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_ISA_EXT);
+	unsigned long reg_val, reg_subtype;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+
+	reg_subtype = reg_num & KVM_REG_RISCV_SUBTYPE_MASK;
+	reg_num &= ~KVM_REG_RISCV_SUBTYPE_MASK;
+
+	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	switch (reg_subtype) {
+	case KVM_REG_RISCV_ISA_SINGLE:
+		return riscv_vcpu_set_isa_ext_single(vcpu, reg_num, reg_val);
+	case KVM_REG_RISCV_SBI_MULTI_EN:
+		return riscv_vcpu_set_isa_ext_multi(vcpu, reg_num, reg_val, true);
+	case KVM_REG_RISCV_SBI_MULTI_DIS:
+		return riscv_vcpu_set_isa_ext_multi(vcpu, reg_num, reg_val, false);
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 int kvm_riscv_vcpu_set_reg(struct kvm_vcpu *vcpu,
 			   const struct kvm_one_reg *reg)
 {

From 41716861e4251b202809fc57deaed3881934e062 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Wed, 12 Jul 2023 12:38:11 +0530
Subject: [PATCH 0357/1189] RISC-V: KVM: Allow Zba and Zbs extensions for
 Guest/VM

We extend the KVM ISA extension ONE_REG interface to allow KVM
user space to detect and enable Zba and Zbs extensions for Guest/VM.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/include/uapi/asm/kvm.h | 2 ++
 arch/riscv/kvm/vcpu_onereg.c      | 4 ++++
 2 files changed, 6 insertions(+)

diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index 6c2285f86545..68f929d88f43 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -124,6 +124,8 @@ enum KVM_RISCV_ISA_EXT_ID {
 	KVM_RISCV_ISA_EXT_SSAIA,
 	KVM_RISCV_ISA_EXT_V,
 	KVM_RISCV_ISA_EXT_SVNAPOT,
+	KVM_RISCV_ISA_EXT_ZBA,
+	KVM_RISCV_ISA_EXT_ZBS,
 	KVM_RISCV_ISA_EXT_MAX,
 };
 
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index c57c7fa260c2..4389ae050d33 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -38,7 +38,9 @@ static const unsigned long kvm_isa_ext_arr[] = {
 	KVM_ISA_EXT_ARR(SVINVAL),
 	KVM_ISA_EXT_ARR(SVNAPOT),
 	KVM_ISA_EXT_ARR(SVPBMT),
+	KVM_ISA_EXT_ARR(ZBA),
 	KVM_ISA_EXT_ARR(ZBB),
+	KVM_ISA_EXT_ARR(ZBS),
 	KVM_ISA_EXT_ARR(ZIHINTPAUSE),
 	KVM_ISA_EXT_ARR(ZICBOM),
 	KVM_ISA_EXT_ARR(ZICBOZ),
@@ -82,7 +84,9 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
 	case KVM_RISCV_ISA_EXT_SVINVAL:
 	case KVM_RISCV_ISA_EXT_SVNAPOT:
 	case KVM_RISCV_ISA_EXT_ZIHINTPAUSE:
+	case KVM_RISCV_ISA_EXT_ZBA:
 	case KVM_RISCV_ISA_EXT_ZBB:
+	case KVM_RISCV_ISA_EXT_ZBS:
 		return false;
 	default:
 		break;

From 043cba064ecd2c3ccaf575c15caf6dd829c64e7b Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Wed, 12 Jul 2023 12:53:50 +0530
Subject: [PATCH 0358/1189] RISC-V: KVM: Allow Zicntr, Zicsr, Zifencei, and
 Zihpm for Guest/VM

We extend the KVM ISA extension ONE_REG interface to allow KVM
user space to detect and enable Zicntr, Zicsr, Zifencei, and Zihpm
extensions for Guest/VM.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/include/uapi/asm/kvm.h | 4 ++++
 arch/riscv/kvm/vcpu_onereg.c      | 8 ++++++++
 2 files changed, 12 insertions(+)

diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index 68f929d88f43..9c35e1427f73 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -126,6 +126,10 @@ enum KVM_RISCV_ISA_EXT_ID {
 	KVM_RISCV_ISA_EXT_SVNAPOT,
 	KVM_RISCV_ISA_EXT_ZBA,
 	KVM_RISCV_ISA_EXT_ZBS,
+	KVM_RISCV_ISA_EXT_ZICNTR,
+	KVM_RISCV_ISA_EXT_ZICSR,
+	KVM_RISCV_ISA_EXT_ZIFENCEI,
+	KVM_RISCV_ISA_EXT_ZIHPM,
 	KVM_RISCV_ISA_EXT_MAX,
 };
 
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index 4389ae050d33..0f75b6b3ced1 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -41,7 +41,11 @@ static const unsigned long kvm_isa_ext_arr[] = {
 	KVM_ISA_EXT_ARR(ZBA),
 	KVM_ISA_EXT_ARR(ZBB),
 	KVM_ISA_EXT_ARR(ZBS),
+	KVM_ISA_EXT_ARR(ZICNTR),
+	KVM_ISA_EXT_ARR(ZICSR),
+	KVM_ISA_EXT_ARR(ZIFENCEI),
 	KVM_ISA_EXT_ARR(ZIHINTPAUSE),
+	KVM_ISA_EXT_ARR(ZIHPM),
 	KVM_ISA_EXT_ARR(ZICBOM),
 	KVM_ISA_EXT_ARR(ZICBOZ),
 };
@@ -83,7 +87,11 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
 	case KVM_RISCV_ISA_EXT_SSTC:
 	case KVM_RISCV_ISA_EXT_SVINVAL:
 	case KVM_RISCV_ISA_EXT_SVNAPOT:
+	case KVM_RISCV_ISA_EXT_ZICNTR:
+	case KVM_RISCV_ISA_EXT_ZICSR:
+	case KVM_RISCV_ISA_EXT_ZIFENCEI:
 	case KVM_RISCV_ISA_EXT_ZIHINTPAUSE:
+	case KVM_RISCV_ISA_EXT_ZIHPM:
 	case KVM_RISCV_ISA_EXT_ZBA:
 	case KVM_RISCV_ISA_EXT_ZBB:
 	case KVM_RISCV_ISA_EXT_ZBS:

From d2064d4a6e3a565879da196947fb35cc7b1f3256 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Wed, 12 Jul 2023 15:33:12 +0530
Subject: [PATCH 0359/1189] RISC-V: KVM: Sort ISA extensions alphabetically in
 ONE_REG interface

Let us sort isa extensions alphabetically in kvm_isa_ext_arr[] and
kvm_riscv_vcpu_isa_disable_allowed() so that future insertions are
more predictable.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_onereg.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index 0f75b6b3ced1..0dc2c2cecb45 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -24,6 +24,7 @@
 
 /* Mapping between KVM ISA Extension ID & Host ISA extension ID */
 static const unsigned long kvm_isa_ext_arr[] = {
+	/* Single letter extensions (alphabetically sorted) */
 	[KVM_RISCV_ISA_EXT_A] = RISCV_ISA_EXT_a,
 	[KVM_RISCV_ISA_EXT_C] = RISCV_ISA_EXT_c,
 	[KVM_RISCV_ISA_EXT_D] = RISCV_ISA_EXT_d,
@@ -32,7 +33,7 @@ static const unsigned long kvm_isa_ext_arr[] = {
 	[KVM_RISCV_ISA_EXT_I] = RISCV_ISA_EXT_i,
 	[KVM_RISCV_ISA_EXT_M] = RISCV_ISA_EXT_m,
 	[KVM_RISCV_ISA_EXT_V] = RISCV_ISA_EXT_v,
-
+	/* Multi letter extensions (alphabetically sorted) */
 	KVM_ISA_EXT_ARR(SSAIA),
 	KVM_ISA_EXT_ARR(SSTC),
 	KVM_ISA_EXT_ARR(SVINVAL),
@@ -41,13 +42,13 @@ static const unsigned long kvm_isa_ext_arr[] = {
 	KVM_ISA_EXT_ARR(ZBA),
 	KVM_ISA_EXT_ARR(ZBB),
 	KVM_ISA_EXT_ARR(ZBS),
+	KVM_ISA_EXT_ARR(ZICBOM),
+	KVM_ISA_EXT_ARR(ZICBOZ),
 	KVM_ISA_EXT_ARR(ZICNTR),
 	KVM_ISA_EXT_ARR(ZICSR),
 	KVM_ISA_EXT_ARR(ZIFENCEI),
 	KVM_ISA_EXT_ARR(ZIHINTPAUSE),
 	KVM_ISA_EXT_ARR(ZIHPM),
-	KVM_ISA_EXT_ARR(ZICBOM),
-	KVM_ISA_EXT_ARR(ZICBOZ),
 };
 
 static unsigned long kvm_riscv_vcpu_base2isa_ext(unsigned long base_ext)
@@ -87,14 +88,14 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
 	case KVM_RISCV_ISA_EXT_SSTC:
 	case KVM_RISCV_ISA_EXT_SVINVAL:
 	case KVM_RISCV_ISA_EXT_SVNAPOT:
+	case KVM_RISCV_ISA_EXT_ZBA:
+	case KVM_RISCV_ISA_EXT_ZBB:
+	case KVM_RISCV_ISA_EXT_ZBS:
 	case KVM_RISCV_ISA_EXT_ZICNTR:
 	case KVM_RISCV_ISA_EXT_ZICSR:
 	case KVM_RISCV_ISA_EXT_ZIFENCEI:
 	case KVM_RISCV_ISA_EXT_ZIHINTPAUSE:
 	case KVM_RISCV_ISA_EXT_ZIHPM:
-	case KVM_RISCV_ISA_EXT_ZBA:
-	case KVM_RISCV_ISA_EXT_ZBB:
-	case KVM_RISCV_ISA_EXT_ZBS:
 		return false;
 	default:
 		break;

From 2776421e6839b67c34261861b169b7ee737b4c00 Mon Sep 17 00:00:00 2001
From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Date: Fri, 28 Jul 2023 18:01:22 -0300
Subject: [PATCH 0360/1189] RISC-V: KVM: provide UAPI for host SATP mode

KVM userspaces need to be aware of the host SATP to allow them to
advertise it back to the guest OS.

Since this information is used to build the guest FDT we can't wait for
the SATP reg to be readable. We just need to read the SATP mode, thus
we can use the existing 'satp_mode' global that represents the SATP reg
with MODE set and both ASID and PPN cleared. E.g. for a 32 bit host
running with sv32 satp_mode is 0x80000000, for a 64 bit host running
sv57 satp_mode is 0xa000000000000000, and so on.

Add a new userspace virtual config register 'satp_mode' to allow
userspace to read the current SATP mode the host is using with
GET_ONE_REG API before spinning the vcpu.

'satp_mode' can't be changed via KVM, so SET_ONE_REG is allowed as long
as userspace writes the existing 'satp_mode'.

Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/include/asm/csr.h      | 2 ++
 arch/riscv/include/uapi/asm/kvm.h | 1 +
 arch/riscv/kvm/vcpu_onereg.c      | 7 +++++++
 3 files changed, 10 insertions(+)

diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h
index 7bac43a3176e..777cb8299551 100644
--- a/arch/riscv/include/asm/csr.h
+++ b/arch/riscv/include/asm/csr.h
@@ -54,6 +54,7 @@
 #ifndef CONFIG_64BIT
 #define SATP_PPN	_AC(0x003FFFFF, UL)
 #define SATP_MODE_32	_AC(0x80000000, UL)
+#define SATP_MODE_SHIFT	31
 #define SATP_ASID_BITS	9
 #define SATP_ASID_SHIFT	22
 #define SATP_ASID_MASK	_AC(0x1FF, UL)
@@ -62,6 +63,7 @@
 #define SATP_MODE_39	_AC(0x8000000000000000, UL)
 #define SATP_MODE_48	_AC(0x9000000000000000, UL)
 #define SATP_MODE_57	_AC(0xa000000000000000, UL)
+#define SATP_MODE_SHIFT	60
 #define SATP_ASID_BITS	16
 #define SATP_ASID_SHIFT	44
 #define SATP_ASID_MASK	_AC(0xFFFF, UL)
diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index 9c35e1427f73..992c5e407104 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -55,6 +55,7 @@ struct kvm_riscv_config {
 	unsigned long marchid;
 	unsigned long mimpid;
 	unsigned long zicboz_block_size;
+	unsigned long satp_mode;
 };
 
 /* CORE registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index 0dc2c2cecb45..85773e858120 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -152,6 +152,9 @@ static int kvm_riscv_vcpu_get_reg_config(struct kvm_vcpu *vcpu,
 	case KVM_REG_RISCV_CONFIG_REG(mimpid):
 		reg_val = vcpu->arch.mimpid;
 		break;
+	case KVM_REG_RISCV_CONFIG_REG(satp_mode):
+		reg_val = satp_mode >> SATP_MODE_SHIFT;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -234,6 +237,10 @@ static int kvm_riscv_vcpu_set_reg_config(struct kvm_vcpu *vcpu,
 		else
 			return -EBUSY;
 		break;
+	case KVM_REG_RISCV_CONFIG_REG(satp_mode):
+		if (reg_val != (satp_mode >> SATP_MODE_SHIFT))
+			return -EINVAL;
+		break;
 	default:
 		return -EINVAL;
 	}

From 2a88f38cd58d026c0e13f4aaa495965d4e9626b9 Mon Sep 17 00:00:00 2001
From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Date: Thu, 3 Aug 2023 13:32:53 -0300
Subject: [PATCH 0361/1189] RISC-V: KVM: return ENOENT in *_one_reg() when reg
 is unknown

get_one_reg() and set_one_reg() are returning EINVAL errors for almost
everything: if a reg doesn't exist, if a reg ID is malformatted, if the
associated CPU extension that implements the reg isn't present in the
host, and for set_one_reg() if the value being written is invalid.

This isn't wrong according to the existing KVM API docs (EINVAL can be
used when there's no such register) but adding more ENOENT instances
will make easier for userspace to understand what went wrong.

Existing userspaces can be affected by this error code change. We
checked a few. As of current upstream code, crosvm doesn't check for any
particular errno code when using kvm_(get|set)_one_reg(). Neither does
QEMU. rust-vmm doesn't have kvm-riscv support yet. Thus we have a good
chance of changing these error codes now while the KVM RISC-V ecosystem
is still new, minimizing user impact.

Change all get_one_reg() and set_one_reg() implementations to return
-ENOENT at all "no such register" cases.

Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/aia.c         |  4 ++--
 arch/riscv/kvm/vcpu_fp.c     | 12 ++++++------
 arch/riscv/kvm/vcpu_onereg.c | 36 ++++++++++++++++++------------------
 arch/riscv/kvm/vcpu_sbi.c    | 16 +++++++++-------
 arch/riscv/kvm/vcpu_timer.c  |  8 ++++----
 5 files changed, 39 insertions(+), 37 deletions(-)

diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c
index 585a3b42c52c..74bb27440527 100644
--- a/arch/riscv/kvm/aia.c
+++ b/arch/riscv/kvm/aia.c
@@ -176,7 +176,7 @@ int kvm_riscv_vcpu_aia_get_csr(struct kvm_vcpu *vcpu,
 	struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr;
 
 	if (reg_num >= sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long))
-		return -EINVAL;
+		return -ENOENT;
 
 	*out_val = 0;
 	if (kvm_riscv_aia_available())
@@ -192,7 +192,7 @@ int kvm_riscv_vcpu_aia_set_csr(struct kvm_vcpu *vcpu,
 	struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr;
 
 	if (reg_num >= sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long))
-		return -EINVAL;
+		return -ENOENT;
 
 	if (kvm_riscv_aia_available()) {
 		((unsigned long *)csr)[reg_num] = val;
diff --git a/arch/riscv/kvm/vcpu_fp.c b/arch/riscv/kvm/vcpu_fp.c
index 9d8cbc42057a..08ba48a395aa 100644
--- a/arch/riscv/kvm/vcpu_fp.c
+++ b/arch/riscv/kvm/vcpu_fp.c
@@ -96,7 +96,7 @@ int kvm_riscv_vcpu_get_reg_fp(struct kvm_vcpu *vcpu,
 			  reg_num <= KVM_REG_RISCV_FP_F_REG(f[31]))
 			reg_val = &cntx->fp.f.f[reg_num];
 		else
-			return -EINVAL;
+			return -ENOENT;
 	} else if ((rtype == KVM_REG_RISCV_FP_D) &&
 		   riscv_isa_extension_available(vcpu->arch.isa, d)) {
 		if (reg_num == KVM_REG_RISCV_FP_D_REG(fcsr)) {
@@ -109,9 +109,9 @@ int kvm_riscv_vcpu_get_reg_fp(struct kvm_vcpu *vcpu,
 				return -EINVAL;
 			reg_val = &cntx->fp.d.f[reg_num];
 		} else
-			return -EINVAL;
+			return -ENOENT;
 	} else
-		return -EINVAL;
+		return -ENOENT;
 
 	if (copy_to_user(uaddr, reg_val, KVM_REG_SIZE(reg->id)))
 		return -EFAULT;
@@ -141,7 +141,7 @@ int kvm_riscv_vcpu_set_reg_fp(struct kvm_vcpu *vcpu,
 			  reg_num <= KVM_REG_RISCV_FP_F_REG(f[31]))
 			reg_val = &cntx->fp.f.f[reg_num];
 		else
-			return -EINVAL;
+			return -ENOENT;
 	} else if ((rtype == KVM_REG_RISCV_FP_D) &&
 		   riscv_isa_extension_available(vcpu->arch.isa, d)) {
 		if (reg_num == KVM_REG_RISCV_FP_D_REG(fcsr)) {
@@ -154,9 +154,9 @@ int kvm_riscv_vcpu_set_reg_fp(struct kvm_vcpu *vcpu,
 				return -EINVAL;
 			reg_val = &cntx->fp.d.f[reg_num];
 		} else
-			return -EINVAL;
+			return -ENOENT;
 	} else
-		return -EINVAL;
+		return -ENOENT;
 
 	if (copy_from_user(reg_val, uaddr, KVM_REG_SIZE(reg->id)))
 		return -EFAULT;
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index 85773e858120..456e9f31441a 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -156,7 +156,7 @@ static int kvm_riscv_vcpu_get_reg_config(struct kvm_vcpu *vcpu,
 		reg_val = satp_mode >> SATP_MODE_SHIFT;
 		break;
 	default:
-		return -EINVAL;
+		return -ENOENT;
 	}
 
 	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
@@ -242,7 +242,7 @@ static int kvm_riscv_vcpu_set_reg_config(struct kvm_vcpu *vcpu,
 			return -EINVAL;
 		break;
 	default:
-		return -EINVAL;
+		return -ENOENT;
 	}
 
 	return 0;
@@ -262,7 +262,7 @@ static int kvm_riscv_vcpu_get_reg_core(struct kvm_vcpu *vcpu,
 	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
 		return -EINVAL;
 	if (reg_num >= sizeof(struct kvm_riscv_core) / sizeof(unsigned long))
-		return -EINVAL;
+		return -ENOENT;
 
 	if (reg_num == KVM_REG_RISCV_CORE_REG(regs.pc))
 		reg_val = cntx->sepc;
@@ -273,7 +273,7 @@ static int kvm_riscv_vcpu_get_reg_core(struct kvm_vcpu *vcpu,
 		reg_val = (cntx->sstatus & SR_SPP) ?
 				KVM_RISCV_MODE_S : KVM_RISCV_MODE_U;
 	else
-		return -EINVAL;
+		return -ENOENT;
 
 	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
 		return -EFAULT;
@@ -295,7 +295,7 @@ static int kvm_riscv_vcpu_set_reg_core(struct kvm_vcpu *vcpu,
 	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
 		return -EINVAL;
 	if (reg_num >= sizeof(struct kvm_riscv_core) / sizeof(unsigned long))
-		return -EINVAL;
+		return -ENOENT;
 
 	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
 		return -EFAULT;
@@ -311,7 +311,7 @@ static int kvm_riscv_vcpu_set_reg_core(struct kvm_vcpu *vcpu,
 		else
 			cntx->sstatus &= ~SR_SPP;
 	} else
-		return -EINVAL;
+		return -ENOENT;
 
 	return 0;
 }
@@ -323,7 +323,7 @@ static int kvm_riscv_vcpu_general_get_csr(struct kvm_vcpu *vcpu,
 	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
 
 	if (reg_num >= sizeof(struct kvm_riscv_csr) / sizeof(unsigned long))
-		return -EINVAL;
+		return -ENOENT;
 
 	if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) {
 		kvm_riscv_vcpu_flush_interrupts(vcpu);
@@ -342,7 +342,7 @@ static int kvm_riscv_vcpu_general_set_csr(struct kvm_vcpu *vcpu,
 	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
 
 	if (reg_num >= sizeof(struct kvm_riscv_csr) / sizeof(unsigned long))
-		return -EINVAL;
+		return -ENOENT;
 
 	if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) {
 		reg_val &= VSIP_VALID_MASK;
@@ -381,7 +381,7 @@ static int kvm_riscv_vcpu_get_reg_csr(struct kvm_vcpu *vcpu,
 		rc = kvm_riscv_vcpu_aia_get_csr(vcpu, reg_num, &reg_val);
 		break;
 	default:
-		rc = -EINVAL;
+		rc = -ENOENT;
 		break;
 	}
 	if (rc)
@@ -420,7 +420,7 @@ static int kvm_riscv_vcpu_set_reg_csr(struct kvm_vcpu *vcpu,
 		rc = kvm_riscv_vcpu_aia_set_csr(vcpu, reg_num, reg_val);
 		break;
 	default:
-		rc = -EINVAL;
+		rc = -ENOENT;
 		break;
 	}
 	if (rc)
@@ -437,7 +437,7 @@ static int riscv_vcpu_get_isa_ext_single(struct kvm_vcpu *vcpu,
 
 	if (reg_num >= KVM_RISCV_ISA_EXT_MAX ||
 	    reg_num >= ARRAY_SIZE(kvm_isa_ext_arr))
-		return -EINVAL;
+		return -ENOENT;
 
 	*reg_val = 0;
 	host_isa_ext = kvm_isa_ext_arr[reg_num];
@@ -455,7 +455,7 @@ static int riscv_vcpu_set_isa_ext_single(struct kvm_vcpu *vcpu,
 
 	if (reg_num >= KVM_RISCV_ISA_EXT_MAX ||
 	    reg_num >= ARRAY_SIZE(kvm_isa_ext_arr))
-		return -EINVAL;
+		return -ENOENT;
 
 	host_isa_ext = kvm_isa_ext_arr[reg_num];
 	if (!__riscv_isa_extension_available(NULL, host_isa_ext))
@@ -489,7 +489,7 @@ static int riscv_vcpu_get_isa_ext_multi(struct kvm_vcpu *vcpu,
 	unsigned long i, ext_id, ext_val;
 
 	if (reg_num > KVM_REG_RISCV_ISA_MULTI_REG_LAST)
-		return -EINVAL;
+		return -ENOENT;
 
 	for (i = 0; i < BITS_PER_LONG; i++) {
 		ext_id = i + reg_num * BITS_PER_LONG;
@@ -512,7 +512,7 @@ static int riscv_vcpu_set_isa_ext_multi(struct kvm_vcpu *vcpu,
 	unsigned long i, ext_id;
 
 	if (reg_num > KVM_REG_RISCV_ISA_MULTI_REG_LAST)
-		return -EINVAL;
+		return -ENOENT;
 
 	for_each_set_bit(i, &reg_val, BITS_PER_LONG) {
 		ext_id = i + reg_num * BITS_PER_LONG;
@@ -554,7 +554,7 @@ static int kvm_riscv_vcpu_get_reg_isa_ext(struct kvm_vcpu *vcpu,
 			reg_val = ~reg_val;
 		break;
 	default:
-		rc = -EINVAL;
+		rc = -ENOENT;
 	}
 	if (rc)
 		return rc;
@@ -592,7 +592,7 @@ static int kvm_riscv_vcpu_set_reg_isa_ext(struct kvm_vcpu *vcpu,
 	case KVM_REG_RISCV_SBI_MULTI_DIS:
 		return riscv_vcpu_set_isa_ext_multi(vcpu, reg_num, reg_val, false);
 	default:
-		return -EINVAL;
+		return -ENOENT;
 	}
 
 	return 0;
@@ -627,7 +627,7 @@ int kvm_riscv_vcpu_set_reg(struct kvm_vcpu *vcpu,
 		break;
 	}
 
-	return -EINVAL;
+	return -ENOENT;
 }
 
 int kvm_riscv_vcpu_get_reg(struct kvm_vcpu *vcpu,
@@ -659,5 +659,5 @@ int kvm_riscv_vcpu_get_reg(struct kvm_vcpu *vcpu,
 		break;
 	}
 
-	return -EINVAL;
+	return -ENOENT;
 }
diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c
index 7b46e04fb667..9cd97091c723 100644
--- a/arch/riscv/kvm/vcpu_sbi.c
+++ b/arch/riscv/kvm/vcpu_sbi.c
@@ -140,8 +140,10 @@ static int riscv_vcpu_set_sbi_ext_single(struct kvm_vcpu *vcpu,
 	const struct kvm_riscv_sbi_extension_entry *sext = NULL;
 	struct kvm_vcpu_sbi_context *scontext = &vcpu->arch.sbi_context;
 
-	if (reg_num >= KVM_RISCV_SBI_EXT_MAX ||
-	    (reg_val != 1 && reg_val != 0))
+	if (reg_num >= KVM_RISCV_SBI_EXT_MAX)
+		return -ENOENT;
+
+	if (reg_val != 1 && reg_val != 0)
 		return -EINVAL;
 
 	for (i = 0; i < ARRAY_SIZE(sbi_ext); i++) {
@@ -175,7 +177,7 @@ static int riscv_vcpu_get_sbi_ext_single(struct kvm_vcpu *vcpu,
 	struct kvm_vcpu_sbi_context *scontext = &vcpu->arch.sbi_context;
 
 	if (reg_num >= KVM_RISCV_SBI_EXT_MAX)
-		return -EINVAL;
+		return -ENOENT;
 
 	for (i = 0; i < ARRAY_SIZE(sbi_ext); i++) {
 		if (sbi_ext[i].ext_idx == reg_num) {
@@ -206,7 +208,7 @@ static int riscv_vcpu_set_sbi_ext_multi(struct kvm_vcpu *vcpu,
 	unsigned long i, ext_id;
 
 	if (reg_num > KVM_REG_RISCV_SBI_MULTI_REG_LAST)
-		return -EINVAL;
+		return -ENOENT;
 
 	for_each_set_bit(i, &reg_val, BITS_PER_LONG) {
 		ext_id = i + reg_num * BITS_PER_LONG;
@@ -226,7 +228,7 @@ static int riscv_vcpu_get_sbi_ext_multi(struct kvm_vcpu *vcpu,
 	unsigned long i, ext_id, ext_val;
 
 	if (reg_num > KVM_REG_RISCV_SBI_MULTI_REG_LAST)
-		return -EINVAL;
+		return -ENOENT;
 
 	for (i = 0; i < BITS_PER_LONG; i++) {
 		ext_id = i + reg_num * BITS_PER_LONG;
@@ -272,7 +274,7 @@ int kvm_riscv_vcpu_set_reg_sbi_ext(struct kvm_vcpu *vcpu,
 	case KVM_REG_RISCV_SBI_MULTI_DIS:
 		return riscv_vcpu_set_sbi_ext_multi(vcpu, reg_num, reg_val, false);
 	default:
-		return -EINVAL;
+		return -ENOENT;
 	}
 
 	return 0;
@@ -307,7 +309,7 @@ int kvm_riscv_vcpu_get_reg_sbi_ext(struct kvm_vcpu *vcpu,
 			reg_val = ~reg_val;
 		break;
 	default:
-		rc = -EINVAL;
+		rc = -ENOENT;
 	}
 	if (rc)
 		return rc;
diff --git a/arch/riscv/kvm/vcpu_timer.c b/arch/riscv/kvm/vcpu_timer.c
index 3ac2ff6a65da..527d269cafff 100644
--- a/arch/riscv/kvm/vcpu_timer.c
+++ b/arch/riscv/kvm/vcpu_timer.c
@@ -170,7 +170,7 @@ int kvm_riscv_vcpu_get_reg_timer(struct kvm_vcpu *vcpu,
 	if (KVM_REG_SIZE(reg->id) != sizeof(u64))
 		return -EINVAL;
 	if (reg_num >= sizeof(struct kvm_riscv_timer) / sizeof(u64))
-		return -EINVAL;
+		return -ENOENT;
 
 	switch (reg_num) {
 	case KVM_REG_RISCV_TIMER_REG(frequency):
@@ -187,7 +187,7 @@ int kvm_riscv_vcpu_get_reg_timer(struct kvm_vcpu *vcpu,
 					  KVM_RISCV_TIMER_STATE_OFF;
 		break;
 	default:
-		return -EINVAL;
+		return -ENOENT;
 	}
 
 	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
@@ -211,7 +211,7 @@ int kvm_riscv_vcpu_set_reg_timer(struct kvm_vcpu *vcpu,
 	if (KVM_REG_SIZE(reg->id) != sizeof(u64))
 		return -EINVAL;
 	if (reg_num >= sizeof(struct kvm_riscv_timer) / sizeof(u64))
-		return -EINVAL;
+		return -ENOENT;
 
 	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
 		return -EFAULT;
@@ -233,7 +233,7 @@ int kvm_riscv_vcpu_set_reg_timer(struct kvm_vcpu *vcpu,
 			ret = kvm_riscv_vcpu_timer_cancel(t);
 		break;
 	default:
-		ret = -EINVAL;
+		ret = -ENOENT;
 		break;
 	}
 

From a044ef71043ebc23903f657fd51b10783d34918b Mon Sep 17 00:00:00 2001
From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Date: Thu, 3 Aug 2023 13:32:54 -0300
Subject: [PATCH 0362/1189] RISC-V: KVM: use ENOENT in *_one_reg() when
 extension is unavailable

Following a similar logic as the previous patch let's minimize the EINVAL
usage in *_one_reg() APIs by using ENOENT when an extension that
implements the reg is not available.

For consistency we're also replacing an EOPNOTSUPP instance that should
be an ENOENT since it's an "extension is not available" error.

Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_onereg.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index 456e9f31441a..1ffd8ac3800a 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -135,12 +135,12 @@ static int kvm_riscv_vcpu_get_reg_config(struct kvm_vcpu *vcpu,
 		break;
 	case KVM_REG_RISCV_CONFIG_REG(zicbom_block_size):
 		if (!riscv_isa_extension_available(vcpu->arch.isa, ZICBOM))
-			return -EINVAL;
+			return -ENOENT;
 		reg_val = riscv_cbom_block_size;
 		break;
 	case KVM_REG_RISCV_CONFIG_REG(zicboz_block_size):
 		if (!riscv_isa_extension_available(vcpu->arch.isa, ZICBOZ))
-			return -EINVAL;
+			return -ENOENT;
 		reg_val = riscv_cboz_block_size;
 		break;
 	case KVM_REG_RISCV_CONFIG_REG(mvendorid):
@@ -459,7 +459,7 @@ static int riscv_vcpu_set_isa_ext_single(struct kvm_vcpu *vcpu,
 
 	host_isa_ext = kvm_isa_ext_arr[reg_num];
 	if (!__riscv_isa_extension_available(NULL, host_isa_ext))
-		return	-EOPNOTSUPP;
+		return -ENOENT;
 
 	if (!vcpu->arch.ran_atleast_once) {
 		/*

From e29f57911d61bcbbe442c72933c606225d3d4d68 Mon Sep 17 00:00:00 2001
From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Date: Thu, 3 Aug 2023 13:32:55 -0300
Subject: [PATCH 0363/1189] RISC-V: KVM: do not EOPNOTSUPP in set_one_reg()
 zicbo(m|z)

zicbom_block_size and zicboz_block_size have a peculiar API: they can be
read via get_one_reg() but any write will return a EOPNOTSUPP.

It makes sense to return a 'not supported' error since both values can't
be changed, but as far as userspace goes they're regs that are throwing
the same EOPNOTSUPP error even if they were read beforehand via
get_one_reg(), even if the same  read value is being written back.
EOPNOTSUPP is also returned even if ZICBOM/ZICBOZ aren't enabled in the
host.

Change both to work more like their counterparts in get_one_reg() and
return -ENOENT if their respective extensions aren't available. After
that, check if the userspace is written a valid value (i.e. the host
value). Throw an -EINVAL if that's not case, let it slide otherwise.

This allows both regs to be read/written by userspace in a 'lazy'
manner, as long as the userspace doesn't change the reg vals.

Suggested-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_onereg.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index 1ffd8ac3800a..e06256dd8d24 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -216,9 +216,17 @@ static int kvm_riscv_vcpu_set_reg_config(struct kvm_vcpu *vcpu,
 		}
 		break;
 	case KVM_REG_RISCV_CONFIG_REG(zicbom_block_size):
-		return -EOPNOTSUPP;
+		if (!riscv_isa_extension_available(vcpu->arch.isa, ZICBOM))
+			return -ENOENT;
+		if (reg_val != riscv_cbom_block_size)
+			return -EINVAL;
+		break;
 	case KVM_REG_RISCV_CONFIG_REG(zicboz_block_size):
-		return -EOPNOTSUPP;
+		if (!riscv_isa_extension_available(vcpu->arch.isa, ZICBOZ))
+			return -ENOENT;
+		if (reg_val != riscv_cboz_block_size)
+			return -EINVAL;
+		break;
 	case KVM_REG_RISCV_CONFIG_REG(mvendorid):
 		if (!vcpu->arch.ran_atleast_once)
 			vcpu->arch.mvendorid = reg_val;

From 432a8b35cc23d3af9c60e9c0d191d7ff737afbdc Mon Sep 17 00:00:00 2001
From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Date: Thu, 3 Aug 2023 13:32:56 -0300
Subject: [PATCH 0364/1189] RISC-V: KVM: do not EOPNOTSUPP in set
 KVM_REG_RISCV_TIMER_REG

The KVM_REG_RISCV_TIMER_REG can be read via get_one_reg(). But trying to
write anything in this reg via set_one_reg() results in an EOPNOTSUPP.

Change the API to behave like cbom_block_size: instead of always
erroring out with EOPNOTSUPP, allow userspace to write the same value
(riscv_timebase) back, throwing an EINVAL if a different value is
attempted.

Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_timer.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/kvm/vcpu_timer.c b/arch/riscv/kvm/vcpu_timer.c
index 527d269cafff..75486b25ac45 100644
--- a/arch/riscv/kvm/vcpu_timer.c
+++ b/arch/riscv/kvm/vcpu_timer.c
@@ -218,7 +218,8 @@ int kvm_riscv_vcpu_set_reg_timer(struct kvm_vcpu *vcpu,
 
 	switch (reg_num) {
 	case KVM_REG_RISCV_TIMER_REG(frequency):
-		ret = -EOPNOTSUPP;
+		if (reg_val != riscv_timebase)
+			return -EINVAL;
 		break;
 	case KVM_REG_RISCV_TIMER_REG(time):
 		gt->time_delta = reg_val - get_cycles64();

From d57304bbfb742bf744d2cd4dc3a08ce3fbfba787 Mon Sep 17 00:00:00 2001
From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Date: Thu, 3 Aug 2023 13:32:57 -0300
Subject: [PATCH 0365/1189] RISC-V: KVM: use EBUSY when
 !vcpu->arch.ran_atleast_once

vcpu_set_reg_config() and vcpu_set_reg_isa_ext() is throwing an
EOPNOTSUPP error when !vcpu->arch.ran_atleast_once. In similar cases
we're throwing an EBUSY error, like in mvendorid/marchid/mimpid
set_reg().

EOPNOTSUPP has a conotation of finality. EBUSY is more adequate in this
case since its a condition/error related to the vcpu lifecycle.

Change these EOPNOTSUPP instances to EBUSY.

Suggested-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_onereg.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index e06256dd8d24..971a2eb83180 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -212,7 +212,7 @@ static int kvm_riscv_vcpu_set_reg_config(struct kvm_vcpu *vcpu,
 			vcpu->arch.isa[0] = reg_val;
 			kvm_riscv_vcpu_fp_reset(vcpu);
 		} else {
-			return -EOPNOTSUPP;
+			return -EBUSY;
 		}
 		break;
 	case KVM_REG_RISCV_CONFIG_REG(zicbom_block_size):
@@ -484,7 +484,7 @@ static int riscv_vcpu_set_isa_ext_single(struct kvm_vcpu *vcpu,
 			return -EINVAL;
 		kvm_riscv_vcpu_fp_reset(vcpu);
 	} else {
-		return -EOPNOTSUPP;
+		return -EBUSY;
 	}
 
 	return 0;

From bea8d23713a2b2dc07ae9d7325b1269dff8c8a1f Mon Sep 17 00:00:00 2001
From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Date: Thu, 3 Aug 2023 13:32:58 -0300
Subject: [PATCH 0366/1189] RISC-V: KVM: avoid EBUSY when writing same ISA val

kvm_riscv_vcpu_set_reg_config() will return -EBUSY if the ISA config reg
is being written after the VCPU ran at least once.

The same restriction isn't placed in kvm_riscv_vcpu_get_reg_config(), so
there's a chance that we'll -EBUSY out on an ISA config reg write even
if the userspace intended no changes to it.

We'll allow the same form of 'lazy writing' that registers such as
zicbom/zicboz_block_size supports: avoid erroring out if userspace made
no changes to the ISA config reg.

Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_onereg.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index 971a2eb83180..a0b0364b038f 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -190,6 +190,13 @@ static int kvm_riscv_vcpu_set_reg_config(struct kvm_vcpu *vcpu,
 		if (fls(reg_val) >= RISCV_ISA_EXT_BASE)
 			return -EINVAL;
 
+		/*
+		 * Return early (i.e. do nothing) if reg_val is the same
+		 * value retrievable via kvm_riscv_vcpu_get_reg_config().
+		 */
+		if (reg_val == (vcpu->arch.isa[0] & KVM_RISCV_BASE_ISA_MASK))
+			break;
+
 		if (!vcpu->arch.ran_atleast_once) {
 			/* Ignore the enable/disable request for certain extensions */
 			for (i = 0; i < RISCV_ISA_EXT_BASE; i++) {

From 63bd660657efade03270c8cc7e3d9b6993350e56 Mon Sep 17 00:00:00 2001
From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Date: Thu, 3 Aug 2023 13:32:59 -0300
Subject: [PATCH 0367/1189] RISC-V: KVM: avoid EBUSY when writing the same
 machine ID val

Right now we do not allow any write in mvendorid/marchid/mimpid if the
vcpu already started, preventing these regs to be changed.

However, if userspace doesn't change them, an alternative is to consider
the reg write a no-op and avoid erroring out altogether. Userpace can
then be oblivious about KVM internals if no changes were intended in the
first place.

Allow the same form of 'lazy writing' that registers such as
zicbom/zicboz_block_size supports: avoid erroring out if userspace makes
no changes in mvendorid/marchid/mimpid during reg write.

Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_onereg.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index a0b0364b038f..81cb6b2784db 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -235,18 +235,24 @@ static int kvm_riscv_vcpu_set_reg_config(struct kvm_vcpu *vcpu,
 			return -EINVAL;
 		break;
 	case KVM_REG_RISCV_CONFIG_REG(mvendorid):
+		if (reg_val == vcpu->arch.mvendorid)
+			break;
 		if (!vcpu->arch.ran_atleast_once)
 			vcpu->arch.mvendorid = reg_val;
 		else
 			return -EBUSY;
 		break;
 	case KVM_REG_RISCV_CONFIG_REG(marchid):
+		if (reg_val == vcpu->arch.marchid)
+			break;
 		if (!vcpu->arch.ran_atleast_once)
 			vcpu->arch.marchid = reg_val;
 		else
 			return -EBUSY;
 		break;
 	case KVM_REG_RISCV_CONFIG_REG(mimpid):
+		if (reg_val == vcpu->arch.mimpid)
+			break;
 		if (!vcpu->arch.ran_atleast_once)
 			vcpu->arch.mimpid = reg_val;
 		else

From 1099c80906d358db542c64aba370291ae4b932b7 Mon Sep 17 00:00:00 2001
From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Date: Thu, 3 Aug 2023 13:33:00 -0300
Subject: [PATCH 0368/1189] RISC-V: KVM: avoid EBUSY when writing the same
 isa_ext val

riscv_vcpu_set_isa_ext_single() will prevent any write of isa_ext regs
if the vcpu already started spinning.

But if there's no extension state (enabled/disabled) made by the
userspace, there's no need to -EBUSY out - we can treat the operation as
a no-op.

zicbom/zicboz_block_size, ISA config reg and mvendorid/march/mimpid
already works in a more permissive manner w.r.t userspace writes being a
no-op, so let's do the same with isa_ext writes.

Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_onereg.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index 81cb6b2784db..989ea32dbcbe 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -482,6 +482,9 @@ static int riscv_vcpu_set_isa_ext_single(struct kvm_vcpu *vcpu,
 	if (!__riscv_isa_extension_available(NULL, host_isa_ext))
 		return -ENOENT;
 
+	if (reg_val == test_bit(host_isa_ext, vcpu->arch.isa))
+		return 0;
+
 	if (!vcpu->arch.ran_atleast_once) {
 		/*
 		 * All multi-letter extension and a few single letter

From 1deaf754f5310e348e6386e75b7f16a0089fa3b7 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Thu, 3 Aug 2023 13:33:01 -0300
Subject: [PATCH 0369/1189] RISC-V: KVM: Improve vector save/restore errors

kvm_riscv_vcpu_(get/set)_reg_vector() now returns ENOENT if V is not
available, EINVAL if reg type is not of VECTOR type, and any error that
might be thrown by kvm_riscv_vcpu_vreg_addr().

Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_vector.c | 60 ++++++++++++++++++++----------------
 1 file changed, 33 insertions(+), 27 deletions(-)

diff --git a/arch/riscv/kvm/vcpu_vector.c b/arch/riscv/kvm/vcpu_vector.c
index edd2eecbddc2..39c5bceb4d1b 100644
--- a/arch/riscv/kvm/vcpu_vector.c
+++ b/arch/riscv/kvm/vcpu_vector.c
@@ -91,44 +91,44 @@ void kvm_riscv_vcpu_free_vector_context(struct kvm_vcpu *vcpu)
 }
 #endif
 
-static void *kvm_riscv_vcpu_vreg_addr(struct kvm_vcpu *vcpu,
+static int kvm_riscv_vcpu_vreg_addr(struct kvm_vcpu *vcpu,
 				      unsigned long reg_num,
-				      size_t reg_size)
+				      size_t reg_size,
+				      void **reg_val)
 {
 	struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
-	void *reg_val;
 	size_t vlenb = riscv_v_vsize / 32;
 
 	if (reg_num < KVM_REG_RISCV_VECTOR_REG(0)) {
 		if (reg_size != sizeof(unsigned long))
-			return NULL;
+			return -EINVAL;
 		switch (reg_num) {
 		case KVM_REG_RISCV_VECTOR_CSR_REG(vstart):
-			reg_val = &cntx->vector.vstart;
+			*reg_val = &cntx->vector.vstart;
 			break;
 		case KVM_REG_RISCV_VECTOR_CSR_REG(vl):
-			reg_val = &cntx->vector.vl;
+			*reg_val = &cntx->vector.vl;
 			break;
 		case KVM_REG_RISCV_VECTOR_CSR_REG(vtype):
-			reg_val = &cntx->vector.vtype;
+			*reg_val = &cntx->vector.vtype;
 			break;
 		case KVM_REG_RISCV_VECTOR_CSR_REG(vcsr):
-			reg_val = &cntx->vector.vcsr;
+			*reg_val = &cntx->vector.vcsr;
 			break;
 		case KVM_REG_RISCV_VECTOR_CSR_REG(datap):
 		default:
-			return NULL;
+			return -ENOENT;
 		}
 	} else if (reg_num <= KVM_REG_RISCV_VECTOR_REG(31)) {
 		if (reg_size != vlenb)
-			return NULL;
-		reg_val = cntx->vector.datap
+			return -EINVAL;
+		*reg_val = cntx->vector.datap
 			  + (reg_num - KVM_REG_RISCV_VECTOR_REG(0)) * vlenb;
 	} else {
-		return NULL;
+		return -ENOENT;
 	}
 
-	return reg_val;
+	return 0;
 }
 
 int kvm_riscv_vcpu_get_reg_vector(struct kvm_vcpu *vcpu,
@@ -141,17 +141,20 @@ int kvm_riscv_vcpu_get_reg_vector(struct kvm_vcpu *vcpu,
 	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
 					    KVM_REG_SIZE_MASK |
 					    rtype);
-	void *reg_val = NULL;
 	size_t reg_size = KVM_REG_SIZE(reg->id);
+	void *reg_val;
+	int rc;
 
-	if (rtype == KVM_REG_RISCV_VECTOR &&
-	    riscv_isa_extension_available(isa, v)) {
-		reg_val = kvm_riscv_vcpu_vreg_addr(vcpu, reg_num, reg_size);
-	}
-
-	if (!reg_val)
+	if (rtype != KVM_REG_RISCV_VECTOR)
 		return -EINVAL;
 
+	if (!riscv_isa_extension_available(isa, v))
+		return -ENOENT;
+
+	rc = kvm_riscv_vcpu_vreg_addr(vcpu, reg_num, reg_size, &reg_val);
+	if (rc)
+		return rc;
+
 	if (copy_to_user(uaddr, reg_val, reg_size))
 		return -EFAULT;
 
@@ -168,17 +171,20 @@ int kvm_riscv_vcpu_set_reg_vector(struct kvm_vcpu *vcpu,
 	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
 					    KVM_REG_SIZE_MASK |
 					    rtype);
-	void *reg_val = NULL;
 	size_t reg_size = KVM_REG_SIZE(reg->id);
+	void *reg_val;
+	int rc;
 
-	if (rtype == KVM_REG_RISCV_VECTOR &&
-	    riscv_isa_extension_available(isa, v)) {
-		reg_val = kvm_riscv_vcpu_vreg_addr(vcpu, reg_num, reg_size);
-	}
-
-	if (!reg_val)
+	if (rtype != KVM_REG_RISCV_VECTOR)
 		return -EINVAL;
 
+	if (!riscv_isa_extension_available(isa, v))
+		return -ENOENT;
+
+	rc = kvm_riscv_vcpu_vreg_addr(vcpu, reg_num, reg_size, &reg_val);
+	if (rc)
+		return rc;
+
 	if (copy_from_user(reg_val, uaddr, reg_size))
 		return -EFAULT;
 

From e47f3c2843c2c23467f9447ed977dfccbe13a6f7 Mon Sep 17 00:00:00 2001
From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Date: Thu, 3 Aug 2023 13:33:02 -0300
Subject: [PATCH 0370/1189] docs: kvm: riscv: document EBUSY in KVM_SET_ONE_REG

The EBUSY errno is being used for KVM_SET_ONE_REG as a way to tell
userspace that a given reg can't be changed after the vcpu started.

Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 Documentation/virt/kvm/api.rst | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index c0ddd3035462..3249fb56cc69 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -2259,6 +2259,8 @@ Errors:
   EINVAL   invalid register ID, or no such register or used with VMs in
            protected virtualization mode on s390
   EPERM    (arm64) register access not allowed before vcpu finalization
+  EBUSY    (riscv) changing register value not allowed after the vcpu
+           has run at least once
   ======   ============================================================
 
 (These error codes are indicative only: do not rely on a specific error

From 630b4cee9c378e2dbb56ed84f71fc2fac50b716e Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Fri, 4 Aug 2023 16:56:18 +0300
Subject: [PATCH 0371/1189] RISC-V: KVM: Improve vector save/restore functions

Make two nonfunctional changes to the vector get/set vector reg
functions and their supporting function for simplification and
readability. The first is to not pass KVM_REG_RISCV_VECTOR, but
rather integrate it directly into the masking. The second is to
rename reg_val to reg_addr where and address is used instead of
a value.

Also opportunistically touch up some of the code formatting for
a third nonfunctional change.

Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/include/asm/kvm_vcpu_vector.h |  6 ++--
 arch/riscv/kvm/vcpu_onereg.c             |  6 ++--
 arch/riscv/kvm/vcpu_vector.c             | 46 ++++++++++--------------
 3 files changed, 23 insertions(+), 35 deletions(-)

diff --git a/arch/riscv/include/asm/kvm_vcpu_vector.h b/arch/riscv/include/asm/kvm_vcpu_vector.h
index ff994fdd6d0d..27f5bccdd8b0 100644
--- a/arch/riscv/include/asm/kvm_vcpu_vector.h
+++ b/arch/riscv/include/asm/kvm_vcpu_vector.h
@@ -74,9 +74,7 @@ static inline void kvm_riscv_vcpu_free_vector_context(struct kvm_vcpu *vcpu)
 #endif
 
 int kvm_riscv_vcpu_get_reg_vector(struct kvm_vcpu *vcpu,
-				  const struct kvm_one_reg *reg,
-				  unsigned long rtype);
+				  const struct kvm_one_reg *reg);
 int kvm_riscv_vcpu_set_reg_vector(struct kvm_vcpu *vcpu,
-				  const struct kvm_one_reg *reg,
-				  unsigned long rtype);
+				  const struct kvm_one_reg *reg);
 #endif
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index 989ea32dbcbe..9fee1c176fbb 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -645,8 +645,7 @@ int kvm_riscv_vcpu_set_reg(struct kvm_vcpu *vcpu,
 	case KVM_REG_RISCV_SBI_EXT:
 		return kvm_riscv_vcpu_set_reg_sbi_ext(vcpu, reg);
 	case KVM_REG_RISCV_VECTOR:
-		return kvm_riscv_vcpu_set_reg_vector(vcpu, reg,
-						 KVM_REG_RISCV_VECTOR);
+		return kvm_riscv_vcpu_set_reg_vector(vcpu, reg);
 	default:
 		break;
 	}
@@ -677,8 +676,7 @@ int kvm_riscv_vcpu_get_reg(struct kvm_vcpu *vcpu,
 	case KVM_REG_RISCV_SBI_EXT:
 		return kvm_riscv_vcpu_get_reg_sbi_ext(vcpu, reg);
 	case KVM_REG_RISCV_VECTOR:
-		return kvm_riscv_vcpu_get_reg_vector(vcpu, reg,
-						 KVM_REG_RISCV_VECTOR);
+		return kvm_riscv_vcpu_get_reg_vector(vcpu, reg);
 	default:
 		break;
 	}
diff --git a/arch/riscv/kvm/vcpu_vector.c b/arch/riscv/kvm/vcpu_vector.c
index 39c5bceb4d1b..b430cbb69521 100644
--- a/arch/riscv/kvm/vcpu_vector.c
+++ b/arch/riscv/kvm/vcpu_vector.c
@@ -92,9 +92,9 @@ void kvm_riscv_vcpu_free_vector_context(struct kvm_vcpu *vcpu)
 #endif
 
 static int kvm_riscv_vcpu_vreg_addr(struct kvm_vcpu *vcpu,
-				      unsigned long reg_num,
-				      size_t reg_size,
-				      void **reg_val)
+				    unsigned long reg_num,
+				    size_t reg_size,
+				    void **reg_addr)
 {
 	struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
 	size_t vlenb = riscv_v_vsize / 32;
@@ -104,16 +104,16 @@ static int kvm_riscv_vcpu_vreg_addr(struct kvm_vcpu *vcpu,
 			return -EINVAL;
 		switch (reg_num) {
 		case KVM_REG_RISCV_VECTOR_CSR_REG(vstart):
-			*reg_val = &cntx->vector.vstart;
+			*reg_addr = &cntx->vector.vstart;
 			break;
 		case KVM_REG_RISCV_VECTOR_CSR_REG(vl):
-			*reg_val = &cntx->vector.vl;
+			*reg_addr = &cntx->vector.vl;
 			break;
 		case KVM_REG_RISCV_VECTOR_CSR_REG(vtype):
-			*reg_val = &cntx->vector.vtype;
+			*reg_addr = &cntx->vector.vtype;
 			break;
 		case KVM_REG_RISCV_VECTOR_CSR_REG(vcsr):
-			*reg_val = &cntx->vector.vcsr;
+			*reg_addr = &cntx->vector.vcsr;
 			break;
 		case KVM_REG_RISCV_VECTOR_CSR_REG(datap):
 		default:
@@ -122,8 +122,8 @@ static int kvm_riscv_vcpu_vreg_addr(struct kvm_vcpu *vcpu,
 	} else if (reg_num <= KVM_REG_RISCV_VECTOR_REG(31)) {
 		if (reg_size != vlenb)
 			return -EINVAL;
-		*reg_val = cntx->vector.datap
-			  + (reg_num - KVM_REG_RISCV_VECTOR_REG(0)) * vlenb;
+		*reg_addr = cntx->vector.datap +
+			    (reg_num - KVM_REG_RISCV_VECTOR_REG(0)) * vlenb;
 	} else {
 		return -ENOENT;
 	}
@@ -132,60 +132,52 @@ static int kvm_riscv_vcpu_vreg_addr(struct kvm_vcpu *vcpu,
 }
 
 int kvm_riscv_vcpu_get_reg_vector(struct kvm_vcpu *vcpu,
-				  const struct kvm_one_reg *reg,
-				  unsigned long rtype)
+				  const struct kvm_one_reg *reg)
 {
 	unsigned long *isa = vcpu->arch.isa;
 	unsigned long __user *uaddr =
 			(unsigned long __user *)(unsigned long)reg->addr;
 	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
 					    KVM_REG_SIZE_MASK |
-					    rtype);
+					    KVM_REG_RISCV_VECTOR);
 	size_t reg_size = KVM_REG_SIZE(reg->id);
-	void *reg_val;
+	void *reg_addr;
 	int rc;
 
-	if (rtype != KVM_REG_RISCV_VECTOR)
-		return -EINVAL;
-
 	if (!riscv_isa_extension_available(isa, v))
 		return -ENOENT;
 
-	rc = kvm_riscv_vcpu_vreg_addr(vcpu, reg_num, reg_size, &reg_val);
+	rc = kvm_riscv_vcpu_vreg_addr(vcpu, reg_num, reg_size, &reg_addr);
 	if (rc)
 		return rc;
 
-	if (copy_to_user(uaddr, reg_val, reg_size))
+	if (copy_to_user(uaddr, reg_addr, reg_size))
 		return -EFAULT;
 
 	return 0;
 }
 
 int kvm_riscv_vcpu_set_reg_vector(struct kvm_vcpu *vcpu,
-				  const struct kvm_one_reg *reg,
-				  unsigned long rtype)
+				  const struct kvm_one_reg *reg)
 {
 	unsigned long *isa = vcpu->arch.isa;
 	unsigned long __user *uaddr =
 			(unsigned long __user *)(unsigned long)reg->addr;
 	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
 					    KVM_REG_SIZE_MASK |
-					    rtype);
+					    KVM_REG_RISCV_VECTOR);
 	size_t reg_size = KVM_REG_SIZE(reg->id);
-	void *reg_val;
+	void *reg_addr;
 	int rc;
 
-	if (rtype != KVM_REG_RISCV_VECTOR)
-		return -EINVAL;
-
 	if (!riscv_isa_extension_available(isa, v))
 		return -ENOENT;
 
-	rc = kvm_riscv_vcpu_vreg_addr(vcpu, reg_num, reg_size, &reg_val);
+	rc = kvm_riscv_vcpu_vreg_addr(vcpu, reg_num, reg_size, &reg_addr);
 	if (rc)
 		return rc;
 
-	if (copy_from_user(reg_val, uaddr, reg_size))
+	if (copy_from_user(reg_addr, uaddr, reg_size))
 		return -EFAULT;
 
 	return 0;

From 8c49c6e1a7b790c4cb9f464c5485117451d91c60 Mon Sep 17 00:00:00 2001
From: Ivan Babrou <ivan@cloudflare.com>
Date: Mon, 17 Jul 2023 17:07:37 -0700
Subject: [PATCH 0372/1189] perf script: Print "cgroup" field on the same line
 as "comm"

Commit 3fd7a168bf51 ("perf script: Add 'cgroup' field for output")
added support for printing cgroup path in perf script output.

It was okay if you didn't want any stacks:

    $ sudo perf script --comms jpegtran:23f4bf -F comm,tid,cpu,time,cgroup
    jpegtran:23f4bf 3321915 [013] 404718.587488:  /idle.slice/polish.service
    jpegtran:23f4bf 3321915 [031] 404718.592073:  /idle.slice/polish.service

With stacks it gets messier as cgroup is printed after the stack:

    $ perf script --comms jpegtran:23f4bf -F comm,tid,cpu,time,cgroup,ip,sym
    jpegtran:23f4bf 3321915 [013] 404718.587488:
                    5c554 compress_output
                    570d9 jpeg_finish_compress
                    3476e jpegtran_main
                    330ee jpegtran::main
                    326e2 core::ops::function::FnOnce::call_once (inlined)
                    326e2 std::sys_common::backtrace::__rust_begin_short_backtrace
    /idle.slice/polish.service
    jpegtran:23f4bf 3321915 [031] 404718.592073:
                    8474d jsimd_encode_mcu_AC_first_prepare_sse2.PADDING
                55af68e62fff [unknown]
    /idle.slice/polish.service

Let's instead print cgroup on the same line as comm:

    $ perf script --comms jpegtran:23f4bf -F comm,tid,cpu,time,cgroup,ip,sym
    jpegtran:23f4bf 3321915 [013] 404718.587488:  /idle.slice/polish.service
                    5c554 compress_output
                    570d9 jpeg_finish_compress
                    3476e jpegtran_main
                    330ee jpegtran::main
                    326e2 core::ops::function::FnOnce::call_once (inlined)
                    326e2 std::sys_common::backtrace::__rust_begin_short_backtrace

    jpegtran:23f4bf 3321915 [031] 404718.592073:  /idle.slice/polish.service
                    8474d jsimd_encode_mcu_AC_first_prepare_sse2.PADDING
                55af68e62fff [unknown]

Fixes: 3fd7a168bf514979 ("perf script: Add 'cgroup' field for output")
Signed-off-by: Ivan Babrou <ivan@cloudflare.com>
Acked-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: kernel-team@cloudflare.com
Link: https://lore.kernel.org/r/20230718000737.49077-1-ivan@cloudflare.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-script.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 200b3e7ea8da..517bf25750c8 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2199,6 +2199,17 @@ static void process_event(struct perf_script *script,
 	if (PRINT_FIELD(RETIRE_LAT))
 		fprintf(fp, "%16" PRIu16, sample->retire_lat);
 
+	if (PRINT_FIELD(CGROUP)) {
+		const char *cgrp_name;
+		struct cgroup *cgrp = cgroup__find(machine->env,
+						   sample->cgroup);
+		if (cgrp != NULL)
+			cgrp_name = cgrp->name;
+		else
+			cgrp_name = "unknown";
+		fprintf(fp, " %s", cgrp_name);
+	}
+
 	if (PRINT_FIELD(IP)) {
 		struct callchain_cursor *cursor = NULL;
 
@@ -2243,17 +2254,6 @@ static void process_event(struct perf_script *script,
 	if (PRINT_FIELD(CODE_PAGE_SIZE))
 		fprintf(fp, " %s", get_page_size_name(sample->code_page_size, str));
 
-	if (PRINT_FIELD(CGROUP)) {
-		const char *cgrp_name;
-		struct cgroup *cgrp = cgroup__find(machine->env,
-						   sample->cgroup);
-		if (cgrp != NULL)
-			cgrp_name = cgrp->name;
-		else
-			cgrp_name = "unknown";
-		fprintf(fp, " %s", cgrp_name);
-	}
-
 	perf_sample__fprintf_ipc(sample, attr, fp);
 
 	fprintf(fp, "\n");

From dfaf20af7649c82b0c53103e3bd9f3e6c3751c9d Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Tue, 25 Jul 2023 16:41:27 +0800
Subject: [PATCH 0373/1189] KVM: arm64: selftests: Replace str_with_index with
 strdup_printf

The original author of aarch64/get-reg-list.c (me) was wearing
tunnel vision goggles when implementing str_with_index(). There's
no reason to have such a special case string function. Instead,
take inspiration from glib and implement strdup_printf. The
implementation builds on vasprintf() which requires _GNU_SOURCE,
but we require _GNU_SOURCE in most files already.

Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Haibo Xu <haibo1.xu@intel.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 .../selftests/kvm/aarch64/get-reg-list.c      | 23 ++++---------------
 .../testing/selftests/kvm/include/test_util.h |  2 ++
 tools/testing/selftests/kvm/lib/test_util.c   | 15 ++++++++++++
 3 files changed, 22 insertions(+), 18 deletions(-)

diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
index 4f10055af2aa..52244de20dce 100644
--- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -180,19 +180,6 @@ static bool check_supported_feat_reg(struct kvm_vcpu *vcpu, __u64 reg)
 	return true;
 }
 
-static const char *str_with_index(const char *template, __u64 index)
-{
-	char *str, *p;
-	int n;
-
-	str = strdup(template);
-	p = strstr(str, "##");
-	n = sprintf(p, "%lld", index);
-	strcat(p + n, strstr(template, "##") + 2);
-
-	return (const char *)str;
-}
-
 #define REG_MASK (KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_COPROC_MASK)
 
 #define CORE_REGS_XX_NR_WORDS	2
@@ -211,7 +198,7 @@ static const char *core_id_to_str(struct vcpu_config *c, __u64 id)
 	     KVM_REG_ARM_CORE_REG(regs.regs[30]):
 		idx = (core_off - KVM_REG_ARM_CORE_REG(regs.regs[0])) / CORE_REGS_XX_NR_WORDS;
 		TEST_ASSERT(idx < 31, "%s: Unexpected regs.regs index: %lld", config_name(c), idx);
-		return str_with_index("KVM_REG_ARM_CORE_REG(regs.regs[##])", idx);
+		return strdup_printf("KVM_REG_ARM_CORE_REG(regs.regs[%lld])", idx);
 	case KVM_REG_ARM_CORE_REG(regs.sp):
 		return "KVM_REG_ARM_CORE_REG(regs.sp)";
 	case KVM_REG_ARM_CORE_REG(regs.pc):
@@ -226,12 +213,12 @@ static const char *core_id_to_str(struct vcpu_config *c, __u64 id)
 	     KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]):
 		idx = (core_off - KVM_REG_ARM_CORE_REG(spsr[0])) / CORE_SPSR_XX_NR_WORDS;
 		TEST_ASSERT(idx < KVM_NR_SPSR, "%s: Unexpected spsr index: %lld", config_name(c), idx);
-		return str_with_index("KVM_REG_ARM_CORE_REG(spsr[##])", idx);
+		return strdup_printf("KVM_REG_ARM_CORE_REG(spsr[%lld])", idx);
 	case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ...
 	     KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]):
 		idx = (core_off - KVM_REG_ARM_CORE_REG(fp_regs.vregs[0])) / CORE_FPREGS_XX_NR_WORDS;
 		TEST_ASSERT(idx < 32, "%s: Unexpected fp_regs.vregs index: %lld", config_name(c), idx);
-		return str_with_index("KVM_REG_ARM_CORE_REG(fp_regs.vregs[##])", idx);
+		return strdup_printf("KVM_REG_ARM_CORE_REG(fp_regs.vregs[%lld])", idx);
 	case KVM_REG_ARM_CORE_REG(fp_regs.fpsr):
 		return "KVM_REG_ARM_CORE_REG(fp_regs.fpsr)";
 	case KVM_REG_ARM_CORE_REG(fp_regs.fpcr):
@@ -260,13 +247,13 @@ static const char *sve_id_to_str(struct vcpu_config *c, __u64 id)
 		n = (id >> 5) & (KVM_ARM64_SVE_NUM_ZREGS - 1);
 		TEST_ASSERT(id == KVM_REG_ARM64_SVE_ZREG(n, 0),
 			    "%s: Unexpected bits set in SVE ZREG id: 0x%llx", config_name(c), id);
-		return str_with_index("KVM_REG_ARM64_SVE_ZREG(##, 0)", n);
+		return strdup_printf("KVM_REG_ARM64_SVE_ZREG(%lld, 0)", n);
 	case KVM_REG_ARM64_SVE_PREG_BASE ...
 	     KVM_REG_ARM64_SVE_PREG_BASE + (1ULL << 5) * KVM_ARM64_SVE_NUM_PREGS - 1:
 		n = (id >> 5) & (KVM_ARM64_SVE_NUM_PREGS - 1);
 		TEST_ASSERT(id == KVM_REG_ARM64_SVE_PREG(n, 0),
 			    "%s: Unexpected bits set in SVE PREG id: 0x%llx", config_name(c), id);
-		return str_with_index("KVM_REG_ARM64_SVE_PREG(##, 0)", n);
+		return strdup_printf("KVM_REG_ARM64_SVE_PREG(%lld, 0)", n);
 	case KVM_REG_ARM64_SVE_FFR_BASE:
 		TEST_ASSERT(id == KVM_REG_ARM64_SVE_FFR(0),
 			    "%s: Unexpected bits set in SVE FFR id: 0x%llx", config_name(c), id);
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index a6e9f215ce70..7e0182f837b5 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -186,4 +186,6 @@ static inline uint32_t atoi_non_negative(const char *name, const char *num_str)
 	return num;
 }
 
+char *strdup_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2), nonnull(1)));
+
 #endif /* SELFTEST_KVM_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c
index b772193f6c18..3e36019eeb4a 100644
--- a/tools/testing/selftests/kvm/lib/test_util.c
+++ b/tools/testing/selftests/kvm/lib/test_util.c
@@ -5,6 +5,9 @@
  * Copyright (C) 2020, Google LLC.
  */
 
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdarg.h>
 #include <assert.h>
 #include <ctype.h>
 #include <limits.h>
@@ -377,3 +380,15 @@ int atoi_paranoid(const char *num_str)
 
 	return num;
 }
+
+char *strdup_printf(const char *fmt, ...)
+{
+	va_list ap;
+	char *str;
+
+	va_start(ap, fmt);
+	vasprintf(&str, fmt, ap);
+	va_end(ap);
+
+	return str;
+}

From 2653860812949d485e18414b72fa542c84763f71 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Tue, 25 Jul 2023 16:41:28 +0800
Subject: [PATCH 0374/1189] KVM: arm64: selftests: Drop SVE cap check in
 print_reg

The check doesn't prove much anyway, as the reg lists could be
messed up too. Just drop the check to simplify making print_reg
more independent.

Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Haibo Xu <haibo1.xu@intel.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 .../testing/selftests/kvm/aarch64/get-reg-list.c  | 15 +--------------
 1 file changed, 1 insertion(+), 14 deletions(-)

diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
index 52244de20dce..335bd5eb250a 100644
--- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -129,16 +129,6 @@ static const char *config_name(struct vcpu_config *c)
 	return c->name;
 }
 
-static bool has_cap(struct vcpu_config *c, long capability)
-{
-	struct reg_sublist *s;
-
-	for_each_sublist(c, s)
-		if (s->capability == capability)
-			return true;
-	return false;
-}
-
 static bool filter_reg(__u64 reg)
 {
 	/*
@@ -335,10 +325,7 @@ static void print_reg(struct vcpu_config *c, __u64 id)
 		printf("\tKVM_REG_ARM_FW_FEAT_BMAP_REG(%lld),\n", id & 0xffff);
 		break;
 	case KVM_REG_ARM64_SVE:
-		if (has_cap(c, KVM_CAP_ARM_SVE))
-			printf("\t%s,\n", sve_id_to_str(c, id));
-		else
-			TEST_FAIL("%s: KVM_REG_ARM64_SVE is an unexpected coproc type in reg id: 0x%llx", config_name(c), id);
+		printf("\t%s,\n", sve_id_to_str(c, id));
 		break;
 	default:
 		TEST_FAIL("%s: Unexpected coproc type: 0x%llx in reg id: 0x%llx",

From c2b5aa7aebbae018edd988e9815087abf72e526b Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Tue, 25 Jul 2023 16:41:29 +0800
Subject: [PATCH 0375/1189] KVM: arm64: selftests: Remove print_reg's
 dependency on vcpu_config

print_reg() and its helpers only use the vcpu_config pointer for
config_name(). So just pass the config name in instead, which is used
as a prefix in asserts. print_reg() can now be compiled independently
of config_name().

Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Haibo Xu <haibo1.xu@intel.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 .../selftests/kvm/aarch64/get-reg-list.c      | 52 +++++++++----------
 1 file changed, 26 insertions(+), 26 deletions(-)

diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
index 335bd5eb250a..c9412be3a04c 100644
--- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -176,7 +176,7 @@ static bool check_supported_feat_reg(struct kvm_vcpu *vcpu, __u64 reg)
 #define CORE_SPSR_XX_NR_WORDS	2
 #define CORE_FPREGS_XX_NR_WORDS	4
 
-static const char *core_id_to_str(struct vcpu_config *c, __u64 id)
+static const char *core_id_to_str(const char *prefix, __u64 id)
 {
 	__u64 core_off = id & ~REG_MASK, idx;
 
@@ -187,7 +187,7 @@ static const char *core_id_to_str(struct vcpu_config *c, __u64 id)
 	case KVM_REG_ARM_CORE_REG(regs.regs[0]) ...
 	     KVM_REG_ARM_CORE_REG(regs.regs[30]):
 		idx = (core_off - KVM_REG_ARM_CORE_REG(regs.regs[0])) / CORE_REGS_XX_NR_WORDS;
-		TEST_ASSERT(idx < 31, "%s: Unexpected regs.regs index: %lld", config_name(c), idx);
+		TEST_ASSERT(idx < 31, "%s: Unexpected regs.regs index: %lld", prefix, idx);
 		return strdup_printf("KVM_REG_ARM_CORE_REG(regs.regs[%lld])", idx);
 	case KVM_REG_ARM_CORE_REG(regs.sp):
 		return "KVM_REG_ARM_CORE_REG(regs.sp)";
@@ -202,12 +202,12 @@ static const char *core_id_to_str(struct vcpu_config *c, __u64 id)
 	case KVM_REG_ARM_CORE_REG(spsr[0]) ...
 	     KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]):
 		idx = (core_off - KVM_REG_ARM_CORE_REG(spsr[0])) / CORE_SPSR_XX_NR_WORDS;
-		TEST_ASSERT(idx < KVM_NR_SPSR, "%s: Unexpected spsr index: %lld", config_name(c), idx);
+		TEST_ASSERT(idx < KVM_NR_SPSR, "%s: Unexpected spsr index: %lld", prefix, idx);
 		return strdup_printf("KVM_REG_ARM_CORE_REG(spsr[%lld])", idx);
 	case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ...
 	     KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]):
 		idx = (core_off - KVM_REG_ARM_CORE_REG(fp_regs.vregs[0])) / CORE_FPREGS_XX_NR_WORDS;
-		TEST_ASSERT(idx < 32, "%s: Unexpected fp_regs.vregs index: %lld", config_name(c), idx);
+		TEST_ASSERT(idx < 32, "%s: Unexpected fp_regs.vregs index: %lld", prefix, idx);
 		return strdup_printf("KVM_REG_ARM_CORE_REG(fp_regs.vregs[%lld])", idx);
 	case KVM_REG_ARM_CORE_REG(fp_regs.fpsr):
 		return "KVM_REG_ARM_CORE_REG(fp_regs.fpsr)";
@@ -215,11 +215,11 @@ static const char *core_id_to_str(struct vcpu_config *c, __u64 id)
 		return "KVM_REG_ARM_CORE_REG(fp_regs.fpcr)";
 	}
 
-	TEST_FAIL("%s: Unknown core reg id: 0x%llx", config_name(c), id);
+	TEST_FAIL("%s: Unknown core reg id: 0x%llx", prefix, id);
 	return NULL;
 }
 
-static const char *sve_id_to_str(struct vcpu_config *c, __u64 id)
+static const char *sve_id_to_str(const char *prefix, __u64 id)
 {
 	__u64 sve_off, n, i;
 
@@ -229,37 +229,37 @@ static const char *sve_id_to_str(struct vcpu_config *c, __u64 id)
 	sve_off = id & ~(REG_MASK | ((1ULL << 5) - 1));
 	i = id & (KVM_ARM64_SVE_MAX_SLICES - 1);
 
-	TEST_ASSERT(i == 0, "%s: Currently we don't expect slice > 0, reg id 0x%llx", config_name(c), id);
+	TEST_ASSERT(i == 0, "%s: Currently we don't expect slice > 0, reg id 0x%llx", prefix, id);
 
 	switch (sve_off) {
 	case KVM_REG_ARM64_SVE_ZREG_BASE ...
 	     KVM_REG_ARM64_SVE_ZREG_BASE + (1ULL << 5) * KVM_ARM64_SVE_NUM_ZREGS - 1:
 		n = (id >> 5) & (KVM_ARM64_SVE_NUM_ZREGS - 1);
 		TEST_ASSERT(id == KVM_REG_ARM64_SVE_ZREG(n, 0),
-			    "%s: Unexpected bits set in SVE ZREG id: 0x%llx", config_name(c), id);
+			    "%s: Unexpected bits set in SVE ZREG id: 0x%llx", prefix, id);
 		return strdup_printf("KVM_REG_ARM64_SVE_ZREG(%lld, 0)", n);
 	case KVM_REG_ARM64_SVE_PREG_BASE ...
 	     KVM_REG_ARM64_SVE_PREG_BASE + (1ULL << 5) * KVM_ARM64_SVE_NUM_PREGS - 1:
 		n = (id >> 5) & (KVM_ARM64_SVE_NUM_PREGS - 1);
 		TEST_ASSERT(id == KVM_REG_ARM64_SVE_PREG(n, 0),
-			    "%s: Unexpected bits set in SVE PREG id: 0x%llx", config_name(c), id);
+			    "%s: Unexpected bits set in SVE PREG id: 0x%llx", prefix, id);
 		return strdup_printf("KVM_REG_ARM64_SVE_PREG(%lld, 0)", n);
 	case KVM_REG_ARM64_SVE_FFR_BASE:
 		TEST_ASSERT(id == KVM_REG_ARM64_SVE_FFR(0),
-			    "%s: Unexpected bits set in SVE FFR id: 0x%llx", config_name(c), id);
+			    "%s: Unexpected bits set in SVE FFR id: 0x%llx", prefix, id);
 		return "KVM_REG_ARM64_SVE_FFR(0)";
 	}
 
 	return NULL;
 }
 
-static void print_reg(struct vcpu_config *c, __u64 id)
+static void print_reg(const char *prefix, __u64 id)
 {
 	unsigned op0, op1, crn, crm, op2;
 	const char *reg_size = NULL;
 
 	TEST_ASSERT((id & KVM_REG_ARCH_MASK) == KVM_REG_ARM64,
-		    "%s: KVM_REG_ARM64 missing in reg id: 0x%llx", config_name(c), id);
+		    "%s: KVM_REG_ARM64 missing in reg id: 0x%llx", prefix, id);
 
 	switch (id & KVM_REG_SIZE_MASK) {
 	case KVM_REG_SIZE_U8:
@@ -291,16 +291,16 @@ static void print_reg(struct vcpu_config *c, __u64 id)
 		break;
 	default:
 		TEST_FAIL("%s: Unexpected reg size: 0x%llx in reg id: 0x%llx",
-			  config_name(c), (id & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT, id);
+			  prefix, (id & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT, id);
 	}
 
 	switch (id & KVM_REG_ARM_COPROC_MASK) {
 	case KVM_REG_ARM_CORE:
-		printf("\tKVM_REG_ARM64 | %s | KVM_REG_ARM_CORE | %s,\n", reg_size, core_id_to_str(c, id));
+		printf("\tKVM_REG_ARM64 | %s | KVM_REG_ARM_CORE | %s,\n", reg_size, core_id_to_str(prefix, id));
 		break;
 	case KVM_REG_ARM_DEMUX:
 		TEST_ASSERT(!(id & ~(REG_MASK | KVM_REG_ARM_DEMUX_ID_MASK | KVM_REG_ARM_DEMUX_VAL_MASK)),
-			    "%s: Unexpected bits set in DEMUX reg id: 0x%llx", config_name(c), id);
+			    "%s: Unexpected bits set in DEMUX reg id: 0x%llx", prefix, id);
 		printf("\tKVM_REG_ARM64 | %s | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | %lld,\n",
 		       reg_size, id & KVM_REG_ARM_DEMUX_VAL_MASK);
 		break;
@@ -311,25 +311,25 @@ static void print_reg(struct vcpu_config *c, __u64 id)
 		crm = (id & KVM_REG_ARM64_SYSREG_CRM_MASK) >> KVM_REG_ARM64_SYSREG_CRM_SHIFT;
 		op2 = (id & KVM_REG_ARM64_SYSREG_OP2_MASK) >> KVM_REG_ARM64_SYSREG_OP2_SHIFT;
 		TEST_ASSERT(id == ARM64_SYS_REG(op0, op1, crn, crm, op2),
-			    "%s: Unexpected bits set in SYSREG reg id: 0x%llx", config_name(c), id);
+			    "%s: Unexpected bits set in SYSREG reg id: 0x%llx", prefix, id);
 		printf("\tARM64_SYS_REG(%d, %d, %d, %d, %d),\n", op0, op1, crn, crm, op2);
 		break;
 	case KVM_REG_ARM_FW:
 		TEST_ASSERT(id == KVM_REG_ARM_FW_REG(id & 0xffff),
-			    "%s: Unexpected bits set in FW reg id: 0x%llx", config_name(c), id);
+			    "%s: Unexpected bits set in FW reg id: 0x%llx", prefix, id);
 		printf("\tKVM_REG_ARM_FW_REG(%lld),\n", id & 0xffff);
 		break;
 	case KVM_REG_ARM_FW_FEAT_BMAP:
 		TEST_ASSERT(id == KVM_REG_ARM_FW_FEAT_BMAP_REG(id & 0xffff),
-			    "%s: Unexpected bits set in the bitmap feature FW reg id: 0x%llx", config_name(c), id);
+			    "%s: Unexpected bits set in the bitmap feature FW reg id: 0x%llx", prefix, id);
 		printf("\tKVM_REG_ARM_FW_FEAT_BMAP_REG(%lld),\n", id & 0xffff);
 		break;
 	case KVM_REG_ARM64_SVE:
-		printf("\t%s,\n", sve_id_to_str(c, id));
+		printf("\t%s,\n", sve_id_to_str(prefix, id));
 		break;
 	default:
 		TEST_FAIL("%s: Unexpected coproc type: 0x%llx in reg id: 0x%llx",
-			  config_name(c), (id & KVM_REG_ARM_COPROC_MASK) >> KVM_REG_ARM_COPROC_SHIFT, id);
+			  prefix, (id & KVM_REG_ARM_COPROC_MASK) >> KVM_REG_ARM_COPROC_SHIFT, id);
 	}
 }
 
@@ -458,7 +458,7 @@ static void run_test(struct vcpu_config *c)
 			__u64 id = reg_list->reg[i];
 			if ((print_list && !filter_reg(id)) ||
 			    (print_filtered && filter_reg(id)))
-				print_reg(c, id);
+				print_reg(config_name(c), id);
 		}
 		putchar('\n');
 		return;
@@ -486,7 +486,7 @@ static void run_test(struct vcpu_config *c)
 		ret = __vcpu_get_reg(vcpu, reg_list->reg[i], &addr);
 		if (ret) {
 			printf("%s: Failed to get ", config_name(c));
-			print_reg(c, reg.id);
+			print_reg(config_name(c), reg.id);
 			putchar('\n');
 			++failed_get;
 		}
@@ -498,7 +498,7 @@ static void run_test(struct vcpu_config *c)
 				ret = __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, &reg);
 				if (ret != -1 || errno != EPERM) {
 					printf("%s: Failed to reject (ret=%d, errno=%d) ", config_name(c), ret, errno);
-					print_reg(c, reg.id);
+					print_reg(config_name(c), reg.id);
 					putchar('\n');
 					++failed_reject;
 				}
@@ -510,7 +510,7 @@ static void run_test(struct vcpu_config *c)
 			ret = __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, &reg);
 			if (ret) {
 				printf("%s: Failed to set ", config_name(c));
-				print_reg(c, reg.id);
+				print_reg(config_name(c), reg.id);
 				putchar('\n');
 				++failed_set;
 			}
@@ -548,7 +548,7 @@ static void run_test(struct vcpu_config *c)
 		       "Consider adding them to the blessed reg "
 		       "list with the following lines:\n\n", config_name(c), new_regs);
 		for_each_new_reg(i)
-			print_reg(c, reg_list->reg[i]);
+			print_reg(config_name(c), reg_list->reg[i]);
 		putchar('\n');
 	}
 
@@ -556,7 +556,7 @@ static void run_test(struct vcpu_config *c)
 		printf("\n%s: There are %d missing registers.\n"
 		       "The following lines are missing registers:\n\n", config_name(c), missing_regs);
 		for_each_missing_reg(i)
-			print_reg(c, blessed_reg[i]);
+			print_reg(config_name(c), blessed_reg[i]);
 		putchar('\n');
 	}
 

From 9177b715cdccdfd6711511440cf43b8be6e28c6c Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Tue, 25 Jul 2023 16:41:30 +0800
Subject: [PATCH 0376/1189] KVM: arm64: selftests: Rename vcpu_config and add
 to kvm_util.h

Rename vcpu_config to vcpu_reg_list to be more specific and add
it to kvm_util.h. While it may not get used outside get-reg-list
tests, exporting it doesn't hurt, as long as it has a unique enough
name. This is a step in the direction of sharing most of the get-
reg-list test code between architectures.

Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Haibo Xu <haibo1.xu@intel.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 .../selftests/kvm/aarch64/get-reg-list.c      | 60 +++++++------------
 .../selftests/kvm/include/kvm_util_base.h     | 16 +++++
 2 files changed, 38 insertions(+), 38 deletions(-)

diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
index c9412be3a04c..cb6b40e167d0 100644
--- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -37,17 +37,6 @@
 static struct kvm_reg_list *reg_list;
 static __u64 *blessed_reg, blessed_n;
 
-struct reg_sublist {
-	const char *name;
-	long capability;
-	int feature;
-	bool finalize;
-	__u64 *regs;
-	__u64 regs_n;
-	__u64 *rejects_set;
-	__u64 rejects_set_n;
-};
-
 struct feature_id_reg {
 	__u64 reg;
 	__u64 id_reg;
@@ -76,12 +65,7 @@ static struct feature_id_reg feat_id_regs[] = {
 	}
 };
 
-struct vcpu_config {
-	char *name;
-	struct reg_sublist sublists[];
-};
-
-static struct vcpu_config *vcpu_configs[];
+static struct vcpu_reg_list *vcpu_configs[];
 static int vcpu_configs_n;
 
 #define for_each_sublist(c, s)							\
@@ -103,9 +87,9 @@ static int vcpu_configs_n;
 	for_each_reg_filtered(i)						\
 		if (!find_reg(blessed_reg, blessed_n, reg_list->reg[i]))
 
-static const char *config_name(struct vcpu_config *c)
+static const char *config_name(struct vcpu_reg_list *c)
 {
-	struct reg_sublist *s;
+	struct vcpu_reg_sublist *s;
 	int len = 0;
 
 	if (c->name)
@@ -390,18 +374,18 @@ static void core_reg_fixup(void)
 	reg_list = tmp;
 }
 
-static void prepare_vcpu_init(struct vcpu_config *c, struct kvm_vcpu_init *init)
+static void prepare_vcpu_init(struct vcpu_reg_list *c, struct kvm_vcpu_init *init)
 {
-	struct reg_sublist *s;
+	struct vcpu_reg_sublist *s;
 
 	for_each_sublist(c, s)
 		if (s->capability)
 			init->features[s->feature / 32] |= 1 << (s->feature % 32);
 }
 
-static void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_config *c)
+static void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c)
 {
-	struct reg_sublist *s;
+	struct vcpu_reg_sublist *s;
 	int feature;
 
 	for_each_sublist(c, s) {
@@ -412,9 +396,9 @@ static void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_config *c)
 	}
 }
 
-static void check_supported(struct vcpu_config *c)
+static void check_supported(struct vcpu_reg_list *c)
 {
-	struct reg_sublist *s;
+	struct vcpu_reg_sublist *s;
 
 	for_each_sublist(c, s) {
 		if (!s->capability)
@@ -430,14 +414,14 @@ static bool print_list;
 static bool print_filtered;
 static bool fixup_core_regs;
 
-static void run_test(struct vcpu_config *c)
+static void run_test(struct vcpu_reg_list *c)
 {
 	struct kvm_vcpu_init init = { .target = -1, };
 	int new_regs = 0, missing_regs = 0, i, n;
 	int failed_get = 0, failed_set = 0, failed_reject = 0;
 	struct kvm_vcpu *vcpu;
 	struct kvm_vm *vm;
-	struct reg_sublist *s;
+	struct vcpu_reg_sublist *s;
 
 	check_supported(c);
 
@@ -574,7 +558,7 @@ static void run_test(struct vcpu_config *c)
 
 static void help(void)
 {
-	struct vcpu_config *c;
+	struct vcpu_reg_list *c;
 	int i;
 
 	printf(
@@ -598,9 +582,9 @@ static void help(void)
 	);
 }
 
-static struct vcpu_config *parse_config(const char *config)
+static struct vcpu_reg_list *parse_config(const char *config)
 {
-	struct vcpu_config *c;
+	struct vcpu_reg_list *c;
 	int i;
 
 	if (config[8] != '=')
@@ -620,7 +604,7 @@ static struct vcpu_config *parse_config(const char *config)
 
 int main(int ac, char **av)
 {
-	struct vcpu_config *c, *sel = NULL;
+	struct vcpu_reg_list *c, *sel = NULL;
 	int i, ret = 0;
 	pid_t pid;
 
@@ -1104,14 +1088,14 @@ static __u64 pauth_generic_regs[] = {
 		.regs_n		= ARRAY_SIZE(pauth_generic_regs),	\
 	}
 
-static struct vcpu_config vregs_config = {
+static struct vcpu_reg_list vregs_config = {
 	.sublists = {
 	BASE_SUBLIST,
 	VREGS_SUBLIST,
 	{0},
 	},
 };
-static struct vcpu_config vregs_pmu_config = {
+static struct vcpu_reg_list vregs_pmu_config = {
 	.sublists = {
 	BASE_SUBLIST,
 	VREGS_SUBLIST,
@@ -1119,14 +1103,14 @@ static struct vcpu_config vregs_pmu_config = {
 	{0},
 	},
 };
-static struct vcpu_config sve_config = {
+static struct vcpu_reg_list sve_config = {
 	.sublists = {
 	BASE_SUBLIST,
 	SVE_SUBLIST,
 	{0},
 	},
 };
-static struct vcpu_config sve_pmu_config = {
+static struct vcpu_reg_list sve_pmu_config = {
 	.sublists = {
 	BASE_SUBLIST,
 	SVE_SUBLIST,
@@ -1134,7 +1118,7 @@ static struct vcpu_config sve_pmu_config = {
 	{0},
 	},
 };
-static struct vcpu_config pauth_config = {
+static struct vcpu_reg_list pauth_config = {
 	.sublists = {
 	BASE_SUBLIST,
 	VREGS_SUBLIST,
@@ -1142,7 +1126,7 @@ static struct vcpu_config pauth_config = {
 	{0},
 	},
 };
-static struct vcpu_config pauth_pmu_config = {
+static struct vcpu_reg_list pauth_pmu_config = {
 	.sublists = {
 	BASE_SUBLIST,
 	VREGS_SUBLIST,
@@ -1152,7 +1136,7 @@ static struct vcpu_config pauth_pmu_config = {
 	},
 };
 
-static struct vcpu_config *vcpu_configs[] = {
+static struct vcpu_reg_list *vcpu_configs[] = {
 	&vregs_config,
 	&vregs_pmu_config,
 	&sve_config,
diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
index eb1ff597bcca..b5189c7df482 100644
--- a/tools/testing/selftests/kvm/include/kvm_util_base.h
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -15,6 +15,7 @@
 #include <linux/kernel.h>
 #include <linux/kvm.h>
 #include "linux/rbtree.h"
+#include <linux/types.h>
 
 #include <asm/atomic.h>
 
@@ -124,6 +125,21 @@ struct kvm_vm {
 	uint32_t memslots[NR_MEM_REGIONS];
 };
 
+struct vcpu_reg_sublist {
+	const char *name;
+	long capability;
+	int feature;
+	bool finalize;
+	__u64 *regs;
+	__u64 regs_n;
+	__u64 *rejects_set;
+	__u64 rejects_set_n;
+};
+
+struct vcpu_reg_list {
+	char *name;
+	struct vcpu_reg_sublist sublists[];
+};
 
 #define kvm_for_each_vcpu(vm, i, vcpu)			\
 	for ((i) = 0; (i) <= (vm)->last_vcpu_id; (i)++)	\

From 0ace6bda5701a38211ac21d45d4683721758e844 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Tue, 25 Jul 2023 16:41:31 +0800
Subject: [PATCH 0377/1189] KVM: arm64: selftests: Delete core_reg_fixup

core_reg_fixup() complicates sharing the get-reg-list test with
other architectures. Rather than work at keeping it, with plenty
of #ifdeffery, just delete it, as it's unlikely to test a kernel
based on anything older than v5.2 with the get-reg-list test,
which is a test meant to check for regressions in new kernels.
(And, an older version of the test can still be used for older
kernels if necessary.)

Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Haibo Xu <haibo1.xu@intel.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 .../selftests/kvm/aarch64/get-reg-list.c      | 83 +++----------------
 1 file changed, 10 insertions(+), 73 deletions(-)

diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
index cb6b40e167d0..11630bbfb86b 100644
--- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -17,12 +17,10 @@
  * by running the test with the --list command line argument.
  *
  * Note, the blessed list should be created from the oldest possible
- * kernel. We can't go older than v4.15, though, because that's the first
- * release to expose the ID system registers in KVM_GET_REG_LIST, see
- * commit 93390c0a1b20 ("arm64: KVM: Hide unsupported AArch64 CPU features
- * from guests"). Also, one must use the --core-reg-fixup command line
- * option when running on an older kernel that doesn't include df205b5c6328
- * ("KVM: arm64: Filter out invalid core register IDs in KVM_GET_REG_LIST")
+ * kernel. We can't go older than v5.2, though, because that's the first
+ * release which includes df205b5c6328 ("KVM: arm64: Filter out invalid
+ * core register IDs in KVM_GET_REG_LIST"). Without that commit the core
+ * registers won't match expectations.
  */
 #include <stdio.h>
 #include <stdlib.h>
@@ -317,63 +315,6 @@ static void print_reg(const char *prefix, __u64 id)
 	}
 }
 
-/*
- * Older kernels listed each 32-bit word of CORE registers separately.
- * For 64 and 128-bit registers we need to ignore the extra words. We
- * also need to fixup the sizes, because the older kernels stated all
- * registers were 64-bit, even when they weren't.
- */
-static void core_reg_fixup(void)
-{
-	struct kvm_reg_list *tmp;
-	__u64 id, core_off;
-	int i;
-
-	tmp = calloc(1, sizeof(*tmp) + reg_list->n * sizeof(__u64));
-
-	for (i = 0; i < reg_list->n; ++i) {
-		id = reg_list->reg[i];
-
-		if ((id & KVM_REG_ARM_COPROC_MASK) != KVM_REG_ARM_CORE) {
-			tmp->reg[tmp->n++] = id;
-			continue;
-		}
-
-		core_off = id & ~REG_MASK;
-
-		switch (core_off) {
-		case 0x52: case 0xd2: case 0xd6:
-			/*
-			 * These offsets are pointing at padding.
-			 * We need to ignore them too.
-			 */
-			continue;
-		case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ...
-		     KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]):
-			if (core_off & 3)
-				continue;
-			id &= ~KVM_REG_SIZE_MASK;
-			id |= KVM_REG_SIZE_U128;
-			tmp->reg[tmp->n++] = id;
-			continue;
-		case KVM_REG_ARM_CORE_REG(fp_regs.fpsr):
-		case KVM_REG_ARM_CORE_REG(fp_regs.fpcr):
-			id &= ~KVM_REG_SIZE_MASK;
-			id |= KVM_REG_SIZE_U32;
-			tmp->reg[tmp->n++] = id;
-			continue;
-		default:
-			if (core_off & 1)
-				continue;
-			tmp->reg[tmp->n++] = id;
-			break;
-		}
-	}
-
-	free(reg_list);
-	reg_list = tmp;
-}
-
 static void prepare_vcpu_init(struct vcpu_reg_list *c, struct kvm_vcpu_init *init)
 {
 	struct vcpu_reg_sublist *s;
@@ -412,7 +353,6 @@ static void check_supported(struct vcpu_reg_list *c)
 
 static bool print_list;
 static bool print_filtered;
-static bool fixup_core_regs;
 
 static void run_test(struct vcpu_reg_list *c)
 {
@@ -433,9 +373,6 @@ static void run_test(struct vcpu_reg_list *c)
 
 	reg_list = vcpu_get_reg_list(vcpu);
 
-	if (fixup_core_regs)
-		core_reg_fixup();
-
 	if (print_list || print_filtered) {
 		putchar('\n');
 		for_each_reg(i) {
@@ -563,7 +500,7 @@ static void help(void)
 
 	printf(
 	"\n"
-	"usage: get-reg-list [--config=<selection>] [--list] [--list-filtered] [--core-reg-fixup]\n\n"
+	"usage: get-reg-list [--config=<selection>] [--list] [--list-filtered]\n\n"
 	" --config=<selection>        Used to select a specific vcpu configuration for the test/listing\n"
 	"                             '<selection>' may be\n");
 
@@ -577,7 +514,6 @@ static void help(void)
 	"\n"
 	" --list                      Print the register list rather than test it (requires --config)\n"
 	" --list-filtered             Print registers that would normally be filtered out (requires --config)\n"
-	" --core-reg-fixup            Needed when running on old kernels with broken core reg listings\n"
 	"\n"
 	);
 }
@@ -609,9 +545,7 @@ int main(int ac, char **av)
 	pid_t pid;
 
 	for (i = 1; i < ac; ++i) {
-		if (strcmp(av[i], "--core-reg-fixup") == 0)
-			fixup_core_regs = true;
-		else if (strncmp(av[i], "--config", 8) == 0)
+		if (strncmp(av[i], "--config", 8) == 0)
 			sel = parse_config(av[i]);
 		else if (strcmp(av[i], "--list") == 0)
 			print_list = true;
@@ -654,8 +588,11 @@ int main(int ac, char **av)
 }
 
 /*
- * The current blessed list was primed with the output of kernel version
+ * The original blessed list was primed with the output of kernel version
  * v4.15 with --core-reg-fixup and then later updated with new registers.
+ * (The --core-reg-fixup option and it's fixup function have been removed
+ * from the test, as it's unlikely to use this type of test on a kernel
+ * older than v5.2.)
  *
  * The blessed list is up to date with kernel version v6.4 (or so we hope)
  */

From 4460a7dc77d00340c59f7e4252c65efd5fbe877b Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Mon, 31 Jul 2023 12:40:31 +0100
Subject: [PATCH 0378/1189] KVM: arm64: Remove redundant kvm_set_pfn_accessed()
 from user_mem_abort()

The function user_mem_abort() calls kvm_release_pfn_clean(),
which eventually calls kvm_set_page_accessed(). Therefore, remove
the redundant call to kvm_set_pfn_accessed().

Signed-off-by: Fuad Tabba <tabba@google.com>
Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230731114110.2673451-1-tabba@google.com
---
 arch/arm64/kvm/mmu.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index d3b4feed460c..137b775d238b 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1541,7 +1541,6 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 
 out_unlock:
 	read_unlock(&kvm->mmu_lock);
-	kvm_set_pfn_accessed(pfn);
 	kvm_release_pfn_clean(pfn);
 	return ret != -EAGAIN ? ret : 0;
 }

From 17da79e009c376523ab977a351a2a69bad8e847b Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Tue, 25 Jul 2023 16:41:32 +0800
Subject: [PATCH 0379/1189] KVM: arm64: selftests: Split get-reg-list test code

Split the arch-neutral test code out of aarch64/get-reg-list.c into
get-reg-list.c. To do this we invent a new make variable
$(SPLIT_TESTS) which expects common parts to be in the KVM selftests
root and the counterparts to have the same name, but be in
$(ARCH_DIR).

There's still some work to be done to de-aarch64 the common
get-reg-list.c, but we leave that to the next patch to avoid
modifying too much code while moving it.

Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Haibo Xu <haibo1.xu@intel.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 tools/testing/selftests/kvm/Makefile          |  12 +-
 .../selftests/kvm/aarch64/get-reg-list.c      | 367 +----------------
 tools/testing/selftests/kvm/get-reg-list.c    | 377 ++++++++++++++++++
 3 files changed, 398 insertions(+), 358 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/get-reg-list.c

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index c692cc86e7da..95f180e711d5 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -140,7 +140,6 @@ TEST_GEN_PROGS_EXTENDED_x86_64 += x86_64/nx_huge_pages_test
 TEST_GEN_PROGS_aarch64 += aarch64/aarch32_id_regs
 TEST_GEN_PROGS_aarch64 += aarch64/arch_timer
 TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions
-TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list
 TEST_GEN_PROGS_aarch64 += aarch64/hypercalls
 TEST_GEN_PROGS_aarch64 += aarch64/page_fault_test
 TEST_GEN_PROGS_aarch64 += aarch64/psci_test
@@ -152,6 +151,7 @@ TEST_GEN_PROGS_aarch64 += access_tracking_perf_test
 TEST_GEN_PROGS_aarch64 += demand_paging_test
 TEST_GEN_PROGS_aarch64 += dirty_log_test
 TEST_GEN_PROGS_aarch64 += dirty_log_perf_test
+TEST_GEN_PROGS_aarch64 += get-reg-list
 TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus
 TEST_GEN_PROGS_aarch64 += kvm_page_table_test
 TEST_GEN_PROGS_aarch64 += memslot_modification_stress_test
@@ -181,6 +181,8 @@ TEST_GEN_PROGS_riscv += kvm_page_table_test
 TEST_GEN_PROGS_riscv += set_memory_region_test
 TEST_GEN_PROGS_riscv += kvm_binary_stats_test
 
+SPLIT_TESTS += get-reg-list
+
 TEST_PROGS += $(TEST_PROGS_$(ARCH_DIR))
 TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(ARCH_DIR))
 TEST_GEN_PROGS_EXTENDED += $(TEST_GEN_PROGS_EXTENDED_$(ARCH_DIR))
@@ -228,11 +230,14 @@ LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C))
 LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S))
 LIBKVM_STRING_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_STRING))
 LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(LIBKVM_STRING_OBJ)
+SPLIT_TESTS_TARGETS := $(patsubst %, $(OUTPUT)/%, $(SPLIT_TESTS))
+SPLIT_TESTS_OBJS := $(patsubst %, $(ARCH_DIR)/%.o, $(SPLIT_TESTS))
 
 TEST_GEN_OBJ = $(patsubst %, %.o, $(TEST_GEN_PROGS))
 TEST_GEN_OBJ += $(patsubst %, %.o, $(TEST_GEN_PROGS_EXTENDED))
 TEST_DEP_FILES = $(patsubst %.o, %.d, $(TEST_GEN_OBJ))
 TEST_DEP_FILES += $(patsubst %.o, %.d, $(LIBKVM_OBJS))
+TEST_DEP_FILES += $(patsubst %.o, %.d, $(SPLIT_TESTS_OBJS))
 -include $(TEST_DEP_FILES)
 
 $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): %: %.o
@@ -240,7 +245,10 @@ $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): %: %.o
 $(TEST_GEN_OBJ): $(OUTPUT)/%.o: %.c
 	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
 
-EXTRA_CLEAN += $(LIBKVM_OBJS) $(TEST_DEP_FILES) $(TEST_GEN_OBJ) cscope.*
+$(SPLIT_TESTS_TARGETS): %: %.o $(SPLIT_TESTS_OBJS)
+	$(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) $^ $(LDLIBS) -o $@
+
+EXTRA_CLEAN += $(LIBKVM_OBJS) $(TEST_DEP_FILES) $(TEST_GEN_OBJ) $(SPLIT_TESTS_OBJS) cscope.*
 
 x := $(shell mkdir -p $(sort $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ))))
 $(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c
diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
index 11630bbfb86b..f72f1a522ff4 100644
--- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -4,37 +4,17 @@
  *
  * Copyright (C) 2020, Red Hat, Inc.
  *
- * When attempting to migrate from a host with an older kernel to a host
- * with a newer kernel we allow the newer kernel on the destination to
- * list new registers with get-reg-list. We assume they'll be unused, at
- * least until the guest reboots, and so they're relatively harmless.
- * However, if the destination host with the newer kernel is missing
- * registers which the source host with the older kernel has, then that's
- * a regression in get-reg-list. This test checks for that regression by
- * checking the current list against a blessed list. We should never have
- * missing registers, but if new ones appear then they can probably be
- * added to the blessed list. A completely new blessed list can be created
- * by running the test with the --list command line argument.
- *
- * Note, the blessed list should be created from the oldest possible
- * kernel. We can't go older than v5.2, though, because that's the first
+ * While the blessed list should be created from the oldest possible
+ * kernel, we can't go older than v5.2, though, because that's the first
  * release which includes df205b5c6328 ("KVM: arm64: Filter out invalid
  * core register IDs in KVM_GET_REG_LIST"). Without that commit the core
  * registers won't match expectations.
  */
 #include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <unistd.h>
-#include <sys/types.h>
-#include <sys/wait.h>
 #include "kvm_util.h"
 #include "test_util.h"
 #include "processor.h"
 
-static struct kvm_reg_list *reg_list;
-static __u64 *blessed_reg, blessed_n;
-
 struct feature_id_reg {
 	__u64 reg;
 	__u64 id_reg;
@@ -63,55 +43,7 @@ static struct feature_id_reg feat_id_regs[] = {
 	}
 };
 
-static struct vcpu_reg_list *vcpu_configs[];
-static int vcpu_configs_n;
-
-#define for_each_sublist(c, s)							\
-	for ((s) = &(c)->sublists[0]; (s)->regs; ++(s))
-
-#define for_each_reg(i)								\
-	for ((i) = 0; (i) < reg_list->n; ++(i))
-
-#define for_each_reg_filtered(i)						\
-	for_each_reg(i)								\
-		if (!filter_reg(reg_list->reg[i]))
-
-#define for_each_missing_reg(i)							\
-	for ((i) = 0; (i) < blessed_n; ++(i))					\
-		if (!find_reg(reg_list->reg, reg_list->n, blessed_reg[i]))	\
-			if (check_supported_feat_reg(vcpu, blessed_reg[i]))
-
-#define for_each_new_reg(i)							\
-	for_each_reg_filtered(i)						\
-		if (!find_reg(blessed_reg, blessed_n, reg_list->reg[i]))
-
-static const char *config_name(struct vcpu_reg_list *c)
-{
-	struct vcpu_reg_sublist *s;
-	int len = 0;
-
-	if (c->name)
-		return c->name;
-
-	for_each_sublist(c, s)
-		len += strlen(s->name) + 1;
-
-	c->name = malloc(len);
-
-	len = 0;
-	for_each_sublist(c, s) {
-		if (!strcmp(s->name, "base"))
-			continue;
-		strcat(c->name + len, s->name);
-		len += strlen(s->name) + 1;
-		c->name[len - 1] = '+';
-	}
-	c->name[len - 1] = '\0';
-
-	return c->name;
-}
-
-static bool filter_reg(__u64 reg)
+bool filter_reg(__u64 reg)
 {
 	/*
 	 * DEMUX register presence depends on the host's CLIDR_EL1.
@@ -123,16 +55,6 @@ static bool filter_reg(__u64 reg)
 	return false;
 }
 
-static bool find_reg(__u64 regs[], __u64 nr_regs, __u64 reg)
-{
-	int i;
-
-	for (i = 0; i < nr_regs; ++i)
-		if (reg == regs[i])
-			return true;
-	return false;
-}
-
 static bool check_supported_feat_reg(struct kvm_vcpu *vcpu, __u64 reg)
 {
 	int i, ret;
@@ -152,6 +74,11 @@ static bool check_supported_feat_reg(struct kvm_vcpu *vcpu, __u64 reg)
 	return true;
 }
 
+bool check_supported_reg(struct kvm_vcpu *vcpu, __u64 reg)
+{
+	return check_supported_feat_reg(vcpu, reg);
+}
+
 #define REG_MASK (KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_COPROC_MASK)
 
 #define CORE_REGS_XX_NR_WORDS	2
@@ -235,7 +162,7 @@ static const char *sve_id_to_str(const char *prefix, __u64 id)
 	return NULL;
 }
 
-static void print_reg(const char *prefix, __u64 id)
+void print_reg(const char *prefix, __u64 id)
 {
 	unsigned op0, op1, crn, crm, op2;
 	const char *reg_size = NULL;
@@ -315,278 +242,6 @@ static void print_reg(const char *prefix, __u64 id)
 	}
 }
 
-static void prepare_vcpu_init(struct vcpu_reg_list *c, struct kvm_vcpu_init *init)
-{
-	struct vcpu_reg_sublist *s;
-
-	for_each_sublist(c, s)
-		if (s->capability)
-			init->features[s->feature / 32] |= 1 << (s->feature % 32);
-}
-
-static void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c)
-{
-	struct vcpu_reg_sublist *s;
-	int feature;
-
-	for_each_sublist(c, s) {
-		if (s->finalize) {
-			feature = s->feature;
-			vcpu_ioctl(vcpu, KVM_ARM_VCPU_FINALIZE, &feature);
-		}
-	}
-}
-
-static void check_supported(struct vcpu_reg_list *c)
-{
-	struct vcpu_reg_sublist *s;
-
-	for_each_sublist(c, s) {
-		if (!s->capability)
-			continue;
-
-		__TEST_REQUIRE(kvm_has_cap(s->capability),
-			       "%s: %s not available, skipping tests\n",
-			       config_name(c), s->name);
-	}
-}
-
-static bool print_list;
-static bool print_filtered;
-
-static void run_test(struct vcpu_reg_list *c)
-{
-	struct kvm_vcpu_init init = { .target = -1, };
-	int new_regs = 0, missing_regs = 0, i, n;
-	int failed_get = 0, failed_set = 0, failed_reject = 0;
-	struct kvm_vcpu *vcpu;
-	struct kvm_vm *vm;
-	struct vcpu_reg_sublist *s;
-
-	check_supported(c);
-
-	vm = vm_create_barebones();
-	prepare_vcpu_init(c, &init);
-	vcpu = __vm_vcpu_add(vm, 0);
-	aarch64_vcpu_setup(vcpu, &init);
-	finalize_vcpu(vcpu, c);
-
-	reg_list = vcpu_get_reg_list(vcpu);
-
-	if (print_list || print_filtered) {
-		putchar('\n');
-		for_each_reg(i) {
-			__u64 id = reg_list->reg[i];
-			if ((print_list && !filter_reg(id)) ||
-			    (print_filtered && filter_reg(id)))
-				print_reg(config_name(c), id);
-		}
-		putchar('\n');
-		return;
-	}
-
-	/*
-	 * We only test that we can get the register and then write back the
-	 * same value. Some registers may allow other values to be written
-	 * back, but others only allow some bits to be changed, and at least
-	 * for ID registers set will fail if the value does not exactly match
-	 * what was returned by get. If registers that allow other values to
-	 * be written need to have the other values tested, then we should
-	 * create a new set of tests for those in a new independent test
-	 * executable.
-	 */
-	for_each_reg(i) {
-		uint8_t addr[2048 / 8];
-		struct kvm_one_reg reg = {
-			.id = reg_list->reg[i],
-			.addr = (__u64)&addr,
-		};
-		bool reject_reg = false;
-		int ret;
-
-		ret = __vcpu_get_reg(vcpu, reg_list->reg[i], &addr);
-		if (ret) {
-			printf("%s: Failed to get ", config_name(c));
-			print_reg(config_name(c), reg.id);
-			putchar('\n');
-			++failed_get;
-		}
-
-		/* rejects_set registers are rejected after KVM_ARM_VCPU_FINALIZE */
-		for_each_sublist(c, s) {
-			if (s->rejects_set && find_reg(s->rejects_set, s->rejects_set_n, reg.id)) {
-				reject_reg = true;
-				ret = __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, &reg);
-				if (ret != -1 || errno != EPERM) {
-					printf("%s: Failed to reject (ret=%d, errno=%d) ", config_name(c), ret, errno);
-					print_reg(config_name(c), reg.id);
-					putchar('\n');
-					++failed_reject;
-				}
-				break;
-			}
-		}
-
-		if (!reject_reg) {
-			ret = __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, &reg);
-			if (ret) {
-				printf("%s: Failed to set ", config_name(c));
-				print_reg(config_name(c), reg.id);
-				putchar('\n');
-				++failed_set;
-			}
-		}
-	}
-
-	for_each_sublist(c, s)
-		blessed_n += s->regs_n;
-	blessed_reg = calloc(blessed_n, sizeof(__u64));
-
-	n = 0;
-	for_each_sublist(c, s) {
-		for (i = 0; i < s->regs_n; ++i)
-			blessed_reg[n++] = s->regs[i];
-	}
-
-	for_each_new_reg(i)
-		++new_regs;
-
-	for_each_missing_reg(i)
-		++missing_regs;
-
-	if (new_regs || missing_regs) {
-		n = 0;
-		for_each_reg_filtered(i)
-			++n;
-
-		printf("%s: Number blessed registers: %5lld\n", config_name(c), blessed_n);
-		printf("%s: Number registers:         %5lld (includes %lld filtered registers)\n",
-		       config_name(c), reg_list->n, reg_list->n - n);
-	}
-
-	if (new_regs) {
-		printf("\n%s: There are %d new registers.\n"
-		       "Consider adding them to the blessed reg "
-		       "list with the following lines:\n\n", config_name(c), new_regs);
-		for_each_new_reg(i)
-			print_reg(config_name(c), reg_list->reg[i]);
-		putchar('\n');
-	}
-
-	if (missing_regs) {
-		printf("\n%s: There are %d missing registers.\n"
-		       "The following lines are missing registers:\n\n", config_name(c), missing_regs);
-		for_each_missing_reg(i)
-			print_reg(config_name(c), blessed_reg[i]);
-		putchar('\n');
-	}
-
-	TEST_ASSERT(!missing_regs && !failed_get && !failed_set && !failed_reject,
-		    "%s: There are %d missing registers; "
-		    "%d registers failed get; %d registers failed set; %d registers failed reject",
-		    config_name(c), missing_regs, failed_get, failed_set, failed_reject);
-
-	pr_info("%s: PASS\n", config_name(c));
-	blessed_n = 0;
-	free(blessed_reg);
-	free(reg_list);
-	kvm_vm_free(vm);
-}
-
-static void help(void)
-{
-	struct vcpu_reg_list *c;
-	int i;
-
-	printf(
-	"\n"
-	"usage: get-reg-list [--config=<selection>] [--list] [--list-filtered]\n\n"
-	" --config=<selection>        Used to select a specific vcpu configuration for the test/listing\n"
-	"                             '<selection>' may be\n");
-
-	for (i = 0; i < vcpu_configs_n; ++i) {
-		c = vcpu_configs[i];
-		printf(
-	"                               '%s'\n", config_name(c));
-	}
-
-	printf(
-	"\n"
-	" --list                      Print the register list rather than test it (requires --config)\n"
-	" --list-filtered             Print registers that would normally be filtered out (requires --config)\n"
-	"\n"
-	);
-}
-
-static struct vcpu_reg_list *parse_config(const char *config)
-{
-	struct vcpu_reg_list *c;
-	int i;
-
-	if (config[8] != '=')
-		help(), exit(1);
-
-	for (i = 0; i < vcpu_configs_n; ++i) {
-		c = vcpu_configs[i];
-		if (strcmp(config_name(c), &config[9]) == 0)
-			break;
-	}
-
-	if (i == vcpu_configs_n)
-		help(), exit(1);
-
-	return c;
-}
-
-int main(int ac, char **av)
-{
-	struct vcpu_reg_list *c, *sel = NULL;
-	int i, ret = 0;
-	pid_t pid;
-
-	for (i = 1; i < ac; ++i) {
-		if (strncmp(av[i], "--config", 8) == 0)
-			sel = parse_config(av[i]);
-		else if (strcmp(av[i], "--list") == 0)
-			print_list = true;
-		else if (strcmp(av[i], "--list-filtered") == 0)
-			print_filtered = true;
-		else if (strcmp(av[i], "--help") == 0 || strcmp(av[1], "-h") == 0)
-			help(), exit(0);
-		else
-			help(), exit(1);
-	}
-
-	if (print_list || print_filtered) {
-		/*
-		 * We only want to print the register list of a single config.
-		 */
-		if (!sel)
-			help(), exit(1);
-	}
-
-	for (i = 0; i < vcpu_configs_n; ++i) {
-		c = vcpu_configs[i];
-		if (sel && c != sel)
-			continue;
-
-		pid = fork();
-
-		if (!pid) {
-			run_test(c);
-			exit(0);
-		} else {
-			int wstatus;
-			pid_t wpid = wait(&wstatus);
-			TEST_ASSERT(wpid == pid && WIFEXITED(wstatus), "wait: Unexpected return");
-			if (WEXITSTATUS(wstatus) && WEXITSTATUS(wstatus) != KSFT_SKIP)
-				ret = KSFT_FAIL;
-		}
-	}
-
-	return ret;
-}
-
 /*
  * The original blessed list was primed with the output of kernel version
  * v4.15 with --core-reg-fixup and then later updated with new registers.
@@ -1073,7 +728,7 @@ static struct vcpu_reg_list pauth_pmu_config = {
 	},
 };
 
-static struct vcpu_reg_list *vcpu_configs[] = {
+struct vcpu_reg_list *vcpu_configs[] = {
 	&vregs_config,
 	&vregs_pmu_config,
 	&sve_config,
@@ -1081,4 +736,4 @@ static struct vcpu_reg_list *vcpu_configs[] = {
 	&pauth_config,
 	&pauth_pmu_config,
 };
-static int vcpu_configs_n = ARRAY_SIZE(vcpu_configs);
+int vcpu_configs_n = ARRAY_SIZE(vcpu_configs);
diff --git a/tools/testing/selftests/kvm/get-reg-list.c b/tools/testing/selftests/kvm/get-reg-list.c
new file mode 100644
index 000000000000..a29e548643d1
--- /dev/null
+++ b/tools/testing/selftests/kvm/get-reg-list.c
@@ -0,0 +1,377 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Check for KVM_GET_REG_LIST regressions.
+ *
+ * Copyright (C) 2020, Red Hat, Inc.
+ *
+ * When attempting to migrate from a host with an older kernel to a host
+ * with a newer kernel we allow the newer kernel on the destination to
+ * list new registers with get-reg-list. We assume they'll be unused, at
+ * least until the guest reboots, and so they're relatively harmless.
+ * However, if the destination host with the newer kernel is missing
+ * registers which the source host with the older kernel has, then that's
+ * a regression in get-reg-list. This test checks for that regression by
+ * checking the current list against a blessed list. We should never have
+ * missing registers, but if new ones appear then they can probably be
+ * added to the blessed list. A completely new blessed list can be created
+ * by running the test with the --list command line argument.
+ *
+ * The blessed list should be created from the oldest possible kernel.
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include "kvm_util.h"
+#include "test_util.h"
+#include "processor.h"
+
+static struct kvm_reg_list *reg_list;
+static __u64 *blessed_reg, blessed_n;
+
+extern struct vcpu_reg_list *vcpu_configs[];
+extern int vcpu_configs_n;
+
+#define for_each_sublist(c, s)							\
+	for ((s) = &(c)->sublists[0]; (s)->regs; ++(s))
+
+#define for_each_reg(i)								\
+	for ((i) = 0; (i) < reg_list->n; ++(i))
+
+#define for_each_reg_filtered(i)						\
+	for_each_reg(i)								\
+		if (!filter_reg(reg_list->reg[i]))
+
+#define for_each_missing_reg(i)							\
+	for ((i) = 0; (i) < blessed_n; ++(i))					\
+		if (!find_reg(reg_list->reg, reg_list->n, blessed_reg[i]))	\
+			if (check_supported_reg(vcpu, blessed_reg[i]))
+
+#define for_each_new_reg(i)							\
+	for_each_reg_filtered(i)						\
+		if (!find_reg(blessed_reg, blessed_n, reg_list->reg[i]))
+
+static const char *config_name(struct vcpu_reg_list *c)
+{
+	struct vcpu_reg_sublist *s;
+	int len = 0;
+
+	if (c->name)
+		return c->name;
+
+	for_each_sublist(c, s)
+		len += strlen(s->name) + 1;
+
+	c->name = malloc(len);
+
+	len = 0;
+	for_each_sublist(c, s) {
+		if (!strcmp(s->name, "base"))
+			continue;
+		strcat(c->name + len, s->name);
+		len += strlen(s->name) + 1;
+		c->name[len - 1] = '+';
+	}
+	c->name[len - 1] = '\0';
+
+	return c->name;
+}
+
+bool __weak check_supported_reg(struct kvm_vcpu *vcpu, __u64 reg)
+{
+	return true;
+}
+
+bool __weak filter_reg(__u64 reg)
+{
+	return false;
+}
+
+static bool find_reg(__u64 regs[], __u64 nr_regs, __u64 reg)
+{
+	int i;
+
+	for (i = 0; i < nr_regs; ++i)
+		if (reg == regs[i])
+			return true;
+	return false;
+}
+
+void __weak print_reg(const char *prefix, __u64 id)
+{
+	printf("\t0x%llx,\n", id);
+}
+
+static void prepare_vcpu_init(struct vcpu_reg_list *c, struct kvm_vcpu_init *init)
+{
+	struct vcpu_reg_sublist *s;
+
+	for_each_sublist(c, s)
+		if (s->capability)
+			init->features[s->feature / 32] |= 1 << (s->feature % 32);
+}
+
+static void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c)
+{
+	struct vcpu_reg_sublist *s;
+	int feature;
+
+	for_each_sublist(c, s) {
+		if (s->finalize) {
+			feature = s->feature;
+			vcpu_ioctl(vcpu, KVM_ARM_VCPU_FINALIZE, &feature);
+		}
+	}
+}
+
+static void check_supported(struct vcpu_reg_list *c)
+{
+	struct vcpu_reg_sublist *s;
+
+	for_each_sublist(c, s) {
+		if (!s->capability)
+			continue;
+
+		__TEST_REQUIRE(kvm_has_cap(s->capability),
+			       "%s: %s not available, skipping tests\n",
+			       config_name(c), s->name);
+	}
+}
+
+static bool print_list;
+static bool print_filtered;
+
+static void run_test(struct vcpu_reg_list *c)
+{
+	struct kvm_vcpu_init init = { .target = -1, };
+	int new_regs = 0, missing_regs = 0, i, n;
+	int failed_get = 0, failed_set = 0, failed_reject = 0;
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+	struct vcpu_reg_sublist *s;
+
+	check_supported(c);
+
+	vm = vm_create_barebones();
+	prepare_vcpu_init(c, &init);
+	vcpu = __vm_vcpu_add(vm, 0);
+	aarch64_vcpu_setup(vcpu, &init);
+	finalize_vcpu(vcpu, c);
+
+	reg_list = vcpu_get_reg_list(vcpu);
+
+	if (print_list || print_filtered) {
+		putchar('\n');
+		for_each_reg(i) {
+			__u64 id = reg_list->reg[i];
+			if ((print_list && !filter_reg(id)) ||
+			    (print_filtered && filter_reg(id)))
+				print_reg(config_name(c), id);
+		}
+		putchar('\n');
+		return;
+	}
+
+	/*
+	 * We only test that we can get the register and then write back the
+	 * same value. Some registers may allow other values to be written
+	 * back, but others only allow some bits to be changed, and at least
+	 * for ID registers set will fail if the value does not exactly match
+	 * what was returned by get. If registers that allow other values to
+	 * be written need to have the other values tested, then we should
+	 * create a new set of tests for those in a new independent test
+	 * executable.
+	 */
+	for_each_reg(i) {
+		uint8_t addr[2048 / 8];
+		struct kvm_one_reg reg = {
+			.id = reg_list->reg[i],
+			.addr = (__u64)&addr,
+		};
+		bool reject_reg = false;
+		int ret;
+
+		ret = __vcpu_get_reg(vcpu, reg_list->reg[i], &addr);
+		if (ret) {
+			printf("%s: Failed to get ", config_name(c));
+			print_reg(config_name(c), reg.id);
+			putchar('\n');
+			++failed_get;
+		}
+
+		/* rejects_set registers are rejected after KVM_ARM_VCPU_FINALIZE */
+		for_each_sublist(c, s) {
+			if (s->rejects_set && find_reg(s->rejects_set, s->rejects_set_n, reg.id)) {
+				reject_reg = true;
+				ret = __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, &reg);
+				if (ret != -1 || errno != EPERM) {
+					printf("%s: Failed to reject (ret=%d, errno=%d) ", config_name(c), ret, errno);
+					print_reg(config_name(c), reg.id);
+					putchar('\n');
+					++failed_reject;
+				}
+				break;
+			}
+		}
+
+		if (!reject_reg) {
+			ret = __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, &reg);
+			if (ret) {
+				printf("%s: Failed to set ", config_name(c));
+				print_reg(config_name(c), reg.id);
+				putchar('\n');
+				++failed_set;
+			}
+		}
+	}
+
+	for_each_sublist(c, s)
+		blessed_n += s->regs_n;
+	blessed_reg = calloc(blessed_n, sizeof(__u64));
+
+	n = 0;
+	for_each_sublist(c, s) {
+		for (i = 0; i < s->regs_n; ++i)
+			blessed_reg[n++] = s->regs[i];
+	}
+
+	for_each_new_reg(i)
+		++new_regs;
+
+	for_each_missing_reg(i)
+		++missing_regs;
+
+	if (new_regs || missing_regs) {
+		n = 0;
+		for_each_reg_filtered(i)
+			++n;
+
+		printf("%s: Number blessed registers: %5lld\n", config_name(c), blessed_n);
+		printf("%s: Number registers:         %5lld (includes %lld filtered registers)\n",
+		       config_name(c), reg_list->n, reg_list->n - n);
+	}
+
+	if (new_regs) {
+		printf("\n%s: There are %d new registers.\n"
+		       "Consider adding them to the blessed reg "
+		       "list with the following lines:\n\n", config_name(c), new_regs);
+		for_each_new_reg(i)
+			print_reg(config_name(c), reg_list->reg[i]);
+		putchar('\n');
+	}
+
+	if (missing_regs) {
+		printf("\n%s: There are %d missing registers.\n"
+		       "The following lines are missing registers:\n\n", config_name(c), missing_regs);
+		for_each_missing_reg(i)
+			print_reg(config_name(c), blessed_reg[i]);
+		putchar('\n');
+	}
+
+	TEST_ASSERT(!missing_regs && !failed_get && !failed_set && !failed_reject,
+		    "%s: There are %d missing registers; "
+		    "%d registers failed get; %d registers failed set; %d registers failed reject",
+		    config_name(c), missing_regs, failed_get, failed_set, failed_reject);
+
+	pr_info("%s: PASS\n", config_name(c));
+	blessed_n = 0;
+	free(blessed_reg);
+	free(reg_list);
+	kvm_vm_free(vm);
+}
+
+static void help(void)
+{
+	struct vcpu_reg_list *c;
+	int i;
+
+	printf(
+	"\n"
+	"usage: get-reg-list [--config=<selection>] [--list] [--list-filtered]\n\n"
+	" --config=<selection>        Used to select a specific vcpu configuration for the test/listing\n"
+	"                             '<selection>' may be\n");
+
+	for (i = 0; i < vcpu_configs_n; ++i) {
+		c = vcpu_configs[i];
+		printf(
+	"                               '%s'\n", config_name(c));
+	}
+
+	printf(
+	"\n"
+	" --list                      Print the register list rather than test it (requires --config)\n"
+	" --list-filtered             Print registers that would normally be filtered out (requires --config)\n"
+	"\n"
+	);
+}
+
+static struct vcpu_reg_list *parse_config(const char *config)
+{
+	struct vcpu_reg_list *c = NULL;
+	int i;
+
+	if (config[8] != '=')
+		help(), exit(1);
+
+	for (i = 0; i < vcpu_configs_n; ++i) {
+		c = vcpu_configs[i];
+		if (strcmp(config_name(c), &config[9]) == 0)
+			break;
+	}
+
+	if (i == vcpu_configs_n)
+		help(), exit(1);
+
+	return c;
+}
+
+int main(int ac, char **av)
+{
+	struct vcpu_reg_list *c, *sel = NULL;
+	int i, ret = 0;
+	pid_t pid;
+
+	for (i = 1; i < ac; ++i) {
+		if (strncmp(av[i], "--config", 8) == 0)
+			sel = parse_config(av[i]);
+		else if (strcmp(av[i], "--list") == 0)
+			print_list = true;
+		else if (strcmp(av[i], "--list-filtered") == 0)
+			print_filtered = true;
+		else if (strcmp(av[i], "--help") == 0 || strcmp(av[1], "-h") == 0)
+			help(), exit(0);
+		else
+			help(), exit(1);
+	}
+
+	if (print_list || print_filtered) {
+		/*
+		 * We only want to print the register list of a single config.
+		 */
+		if (!sel)
+			help(), exit(1);
+	}
+
+	for (i = 0; i < vcpu_configs_n; ++i) {
+		c = vcpu_configs[i];
+		if (sel && c != sel)
+			continue;
+
+		pid = fork();
+
+		if (!pid) {
+			run_test(c);
+			exit(0);
+		} else {
+			int wstatus;
+			pid_t wpid = wait(&wstatus);
+			TEST_ASSERT(wpid == pid && WIFEXITED(wstatus), "wait: Unexpected return");
+			if (WEXITSTATUS(wstatus) && WEXITSTATUS(wstatus) != KSFT_SKIP)
+				ret = KSFT_FAIL;
+		}
+	}
+
+	return ret;
+}

From be4c58060c3efd1f8dff59e59ff8e69d08f00560 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Tue, 25 Jul 2023 16:41:33 +0800
Subject: [PATCH 0380/1189] KVM: arm64: selftests: Finish generalizing
 get-reg-list

Add some unfortunate #ifdeffery to ensure the common get-reg-list.c
can be compiled and run with other architectures. The next
architecture to support get-reg-list should now only need to provide
$(ARCH_DIR)/get-reg-list.c where arch-specific print_reg() and
vcpu_configs[] get defined.

Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Haibo Xu <haibo1.xu@intel.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 tools/testing/selftests/kvm/get-reg-list.c | 26 +++++++++++++++++-----
 1 file changed, 21 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/kvm/get-reg-list.c b/tools/testing/selftests/kvm/get-reg-list.c
index a29e548643d1..853cbf470da2 100644
--- a/tools/testing/selftests/kvm/get-reg-list.c
+++ b/tools/testing/selftests/kvm/get-reg-list.c
@@ -104,6 +104,7 @@ void __weak print_reg(const char *prefix, __u64 id)
 	printf("\t0x%llx,\n", id);
 }
 
+#ifdef __aarch64__
 static void prepare_vcpu_init(struct vcpu_reg_list *c, struct kvm_vcpu_init *init)
 {
 	struct vcpu_reg_sublist *s;
@@ -126,6 +127,25 @@ static void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c)
 	}
 }
 
+static struct kvm_vcpu *vcpu_config_get_vcpu(struct vcpu_reg_list *c, struct kvm_vm *vm)
+{
+	struct kvm_vcpu_init init = { .target = -1, };
+	struct kvm_vcpu *vcpu;
+
+	prepare_vcpu_init(c, &init);
+	vcpu = __vm_vcpu_add(vm, 0);
+	aarch64_vcpu_setup(vcpu, &init);
+	finalize_vcpu(vcpu, c);
+
+	return vcpu;
+}
+#else
+static struct kvm_vcpu *vcpu_config_get_vcpu(struct vcpu_reg_list *c, struct kvm_vm *vm)
+{
+	return __vm_vcpu_add(vm, 0);
+}
+#endif
+
 static void check_supported(struct vcpu_reg_list *c)
 {
 	struct vcpu_reg_sublist *s;
@@ -145,7 +165,6 @@ static bool print_filtered;
 
 static void run_test(struct vcpu_reg_list *c)
 {
-	struct kvm_vcpu_init init = { .target = -1, };
 	int new_regs = 0, missing_regs = 0, i, n;
 	int failed_get = 0, failed_set = 0, failed_reject = 0;
 	struct kvm_vcpu *vcpu;
@@ -155,10 +174,7 @@ static void run_test(struct vcpu_reg_list *c)
 	check_supported(c);
 
 	vm = vm_create_barebones();
-	prepare_vcpu_init(c, &init);
-	vcpu = __vm_vcpu_add(vm, 0);
-	aarch64_vcpu_setup(vcpu, &init);
-	finalize_vcpu(vcpu, c);
+	vcpu = vcpu_config_get_vcpu(c, vm);
 
 	reg_list = vcpu_get_reg_list(vcpu);
 

From 90a6bcbc542d0d61f50eeb85952e4fc49dbf3841 Mon Sep 17 00:00:00 2001
From: Haibo Xu <haibo1.xu@intel.com>
Date: Tue, 25 Jul 2023 16:41:34 +0800
Subject: [PATCH 0381/1189] KVM: arm64: selftests: Move reject_set check logic
 to a function

No functional changes. Just move the reject_set check logic to a
function so we can check for a specific errno. This is a preparation
for support reject_set in riscv.

Suggested-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Haibo Xu <haibo1.xu@intel.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 tools/testing/selftests/kvm/aarch64/get-reg-list.c | 5 +++++
 tools/testing/selftests/kvm/get-reg-list.c         | 7 ++++++-
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
index f72f1a522ff4..f8ebc058b191 100644
--- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -79,6 +79,11 @@ bool check_supported_reg(struct kvm_vcpu *vcpu, __u64 reg)
 	return check_supported_feat_reg(vcpu, reg);
 }
 
+bool check_reject_set(int err)
+{
+	return err == EPERM;
+}
+
 #define REG_MASK (KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_COPROC_MASK)
 
 #define CORE_REGS_XX_NR_WORDS	2
diff --git a/tools/testing/selftests/kvm/get-reg-list.c b/tools/testing/selftests/kvm/get-reg-list.c
index 853cbf470da2..1df94e8e9ed5 100644
--- a/tools/testing/selftests/kvm/get-reg-list.c
+++ b/tools/testing/selftests/kvm/get-reg-list.c
@@ -104,6 +104,11 @@ void __weak print_reg(const char *prefix, __u64 id)
 	printf("\t0x%llx,\n", id);
 }
 
+bool __weak check_reject_set(int err)
+{
+	return true;
+}
+
 #ifdef __aarch64__
 static void prepare_vcpu_init(struct vcpu_reg_list *c, struct kvm_vcpu_init *init)
 {
@@ -222,7 +227,7 @@ static void run_test(struct vcpu_reg_list *c)
 			if (s->rejects_set && find_reg(s->rejects_set, s->rejects_set_n, reg.id)) {
 				reject_reg = true;
 				ret = __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, &reg);
-				if (ret != -1 || errno != EPERM) {
+				if (ret != -1 || !check_reject_set(errno)) {
 					printf("%s: Failed to reject (ret=%d, errno=%d) ", config_name(c), ret, errno);
 					print_reg(config_name(c), reg.id);
 					putchar('\n');

From e85660338f2b1f20981f2a343a33db75255942a7 Mon Sep 17 00:00:00 2001
From: Haibo Xu <haibo1.xu@intel.com>
Date: Tue, 25 Jul 2023 16:41:35 +0800
Subject: [PATCH 0382/1189] KVM: arm64: selftests: Move finalize_vcpu back to
 run_test

No functional changes. Just move the finalize_vcpu call back to
run_test and do weak function trick to prepare for the opration
in riscv.

Suggested-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Haibo Xu <haibo1.xu@intel.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 .../selftests/kvm/aarch64/get-reg-list.c      | 13 +++++++++++
 tools/testing/selftests/kvm/get-reg-list.c    | 22 +++++--------------
 .../selftests/kvm/include/kvm_util_base.h     |  3 +++
 3 files changed, 21 insertions(+), 17 deletions(-)

diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
index f8ebc058b191..709d7d721760 100644
--- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -84,6 +84,19 @@ bool check_reject_set(int err)
 	return err == EPERM;
 }
 
+void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c)
+{
+	struct vcpu_reg_sublist *s;
+	int feature;
+
+	for_each_sublist(c, s) {
+		if (s->finalize) {
+			feature = s->feature;
+			vcpu_ioctl(vcpu, KVM_ARM_VCPU_FINALIZE, &feature);
+		}
+	}
+}
+
 #define REG_MASK (KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_COPROC_MASK)
 
 #define CORE_REGS_XX_NR_WORDS	2
diff --git a/tools/testing/selftests/kvm/get-reg-list.c b/tools/testing/selftests/kvm/get-reg-list.c
index 1df94e8e9ed5..43a919f2208f 100644
--- a/tools/testing/selftests/kvm/get-reg-list.c
+++ b/tools/testing/selftests/kvm/get-reg-list.c
@@ -34,9 +34,6 @@ static __u64 *blessed_reg, blessed_n;
 extern struct vcpu_reg_list *vcpu_configs[];
 extern int vcpu_configs_n;
 
-#define for_each_sublist(c, s)							\
-	for ((s) = &(c)->sublists[0]; (s)->regs; ++(s))
-
 #define for_each_reg(i)								\
 	for ((i) = 0; (i) < reg_list->n; ++(i))
 
@@ -109,6 +106,10 @@ bool __weak check_reject_set(int err)
 	return true;
 }
 
+void __weak finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c)
+{
+}
+
 #ifdef __aarch64__
 static void prepare_vcpu_init(struct vcpu_reg_list *c, struct kvm_vcpu_init *init)
 {
@@ -119,19 +120,6 @@ static void prepare_vcpu_init(struct vcpu_reg_list *c, struct kvm_vcpu_init *ini
 			init->features[s->feature / 32] |= 1 << (s->feature % 32);
 }
 
-static void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c)
-{
-	struct vcpu_reg_sublist *s;
-	int feature;
-
-	for_each_sublist(c, s) {
-		if (s->finalize) {
-			feature = s->feature;
-			vcpu_ioctl(vcpu, KVM_ARM_VCPU_FINALIZE, &feature);
-		}
-	}
-}
-
 static struct kvm_vcpu *vcpu_config_get_vcpu(struct vcpu_reg_list *c, struct kvm_vm *vm)
 {
 	struct kvm_vcpu_init init = { .target = -1, };
@@ -140,7 +128,6 @@ static struct kvm_vcpu *vcpu_config_get_vcpu(struct vcpu_reg_list *c, struct kvm
 	prepare_vcpu_init(c, &init);
 	vcpu = __vm_vcpu_add(vm, 0);
 	aarch64_vcpu_setup(vcpu, &init);
-	finalize_vcpu(vcpu, c);
 
 	return vcpu;
 }
@@ -180,6 +167,7 @@ static void run_test(struct vcpu_reg_list *c)
 
 	vm = vm_create_barebones();
 	vcpu = vcpu_config_get_vcpu(c, vm);
+	finalize_vcpu(vcpu, c);
 
 	reg_list = vcpu_get_reg_list(vcpu);
 
diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
index b5189c7df482..bc7c08a09d30 100644
--- a/tools/testing/selftests/kvm/include/kvm_util_base.h
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -141,6 +141,9 @@ struct vcpu_reg_list {
 	struct vcpu_reg_sublist sublists[];
 };
 
+#define for_each_sublist(c, s)		\
+	for ((s) = &(c)->sublists[0]; (s)->regs; ++(s))
+
 #define kvm_for_each_vcpu(vm, i, vcpu)			\
 	for ((i) = 0; (i) <= (vm)->last_vcpu_id; (i)++)	\
 		if (!((vcpu) = vm->vcpus[i]))		\

From c47467712e8be10805aed4db5626a39aedc784bb Mon Sep 17 00:00:00 2001
From: Haibo Xu <haibo1.xu@intel.com>
Date: Tue, 25 Jul 2023 16:41:36 +0800
Subject: [PATCH 0383/1189] KVM: selftests: Only do get/set tests on present
 blessed list

Only do the get/set tests on present and blessed registers
since we don't know the capabilities of any new ones.

Suggested-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Haibo Xu <haibo1.xu@intel.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 tools/testing/selftests/kvm/get-reg-list.c | 29 ++++++++++++++--------
 1 file changed, 18 insertions(+), 11 deletions(-)

diff --git a/tools/testing/selftests/kvm/get-reg-list.c b/tools/testing/selftests/kvm/get-reg-list.c
index 43a919f2208f..2232620fb797 100644
--- a/tools/testing/selftests/kvm/get-reg-list.c
+++ b/tools/testing/selftests/kvm/get-reg-list.c
@@ -50,6 +50,10 @@ extern int vcpu_configs_n;
 	for_each_reg_filtered(i)						\
 		if (!find_reg(blessed_reg, blessed_n, reg_list->reg[i]))
 
+#define for_each_present_blessed_reg(i)						\
+	for_each_reg(i)								\
+		if (find_reg(blessed_reg, blessed_n, reg_list->reg[i]))
+
 static const char *config_name(struct vcpu_reg_list *c)
 {
 	struct vcpu_reg_sublist *s;
@@ -183,6 +187,16 @@ static void run_test(struct vcpu_reg_list *c)
 		return;
 	}
 
+	for_each_sublist(c, s)
+		blessed_n += s->regs_n;
+	blessed_reg = calloc(blessed_n, sizeof(__u64));
+
+	n = 0;
+	for_each_sublist(c, s) {
+		for (i = 0; i < s->regs_n; ++i)
+			blessed_reg[n++] = s->regs[i];
+	}
+
 	/*
 	 * We only test that we can get the register and then write back the
 	 * same value. Some registers may allow other values to be written
@@ -192,8 +206,11 @@ static void run_test(struct vcpu_reg_list *c)
 	 * be written need to have the other values tested, then we should
 	 * create a new set of tests for those in a new independent test
 	 * executable.
+	 *
+	 * Only do the get/set tests on present, blessed list registers,
+	 * since we don't know the capabilities of any new registers.
 	 */
-	for_each_reg(i) {
+	for_each_present_blessed_reg(i) {
 		uint8_t addr[2048 / 8];
 		struct kvm_one_reg reg = {
 			.id = reg_list->reg[i],
@@ -236,16 +253,6 @@ static void run_test(struct vcpu_reg_list *c)
 		}
 	}
 
-	for_each_sublist(c, s)
-		blessed_n += s->regs_n;
-	blessed_reg = calloc(blessed_n, sizeof(__u64));
-
-	n = 0;
-	for_each_sublist(c, s) {
-		for (i = 0; i < s->regs_n; ++i)
-			blessed_reg[n++] = s->regs[i];
-	}
-
 	for_each_new_reg(i)
 		++new_regs;
 

From cbc0daa67c62bcfeb45cccfc821216549566fb40 Mon Sep 17 00:00:00 2001
From: Haibo Xu <haibo1.xu@intel.com>
Date: Tue, 25 Jul 2023 16:41:37 +0800
Subject: [PATCH 0384/1189] KVM: selftests: Add skip_set facility to
 get_reg_list test

Add new skips_set members to vcpu_reg_sublist so as to skip
set operation on some registers.

Suggested-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Haibo Xu <haibo1.xu@intel.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 tools/testing/selftests/kvm/get-reg-list.c    | 20 +++++++++++++------
 .../selftests/kvm/include/kvm_util_base.h     |  2 ++
 2 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/kvm/get-reg-list.c b/tools/testing/selftests/kvm/get-reg-list.c
index 2232620fb797..be7bf5224434 100644
--- a/tools/testing/selftests/kvm/get-reg-list.c
+++ b/tools/testing/selftests/kvm/get-reg-list.c
@@ -163,6 +163,7 @@ static void run_test(struct vcpu_reg_list *c)
 {
 	int new_regs = 0, missing_regs = 0, i, n;
 	int failed_get = 0, failed_set = 0, failed_reject = 0;
+	int skipped_set = 0;
 	struct kvm_vcpu *vcpu;
 	struct kvm_vm *vm;
 	struct vcpu_reg_sublist *s;
@@ -216,7 +217,7 @@ static void run_test(struct vcpu_reg_list *c)
 			.id = reg_list->reg[i],
 			.addr = (__u64)&addr,
 		};
-		bool reject_reg = false;
+		bool reject_reg = false, skip_reg = false;
 		int ret;
 
 		ret = __vcpu_get_reg(vcpu, reg_list->reg[i], &addr);
@@ -227,8 +228,8 @@ static void run_test(struct vcpu_reg_list *c)
 			++failed_get;
 		}
 
-		/* rejects_set registers are rejected after KVM_ARM_VCPU_FINALIZE */
 		for_each_sublist(c, s) {
+			/* rejects_set registers are rejected for set operation */
 			if (s->rejects_set && find_reg(s->rejects_set, s->rejects_set_n, reg.id)) {
 				reject_reg = true;
 				ret = __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, &reg);
@@ -240,9 +241,16 @@ static void run_test(struct vcpu_reg_list *c)
 				}
 				break;
 			}
+
+			/* skips_set registers are skipped for set operation */
+			if (s->skips_set && find_reg(s->skips_set, s->skips_set_n, reg.id)) {
+				skip_reg = true;
+				++skipped_set;
+				break;
+			}
 		}
 
-		if (!reject_reg) {
+		if (!reject_reg && !skip_reg) {
 			ret = __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, &reg);
 			if (ret) {
 				printf("%s: Failed to set ", config_name(c));
@@ -287,9 +295,9 @@ static void run_test(struct vcpu_reg_list *c)
 	}
 
 	TEST_ASSERT(!missing_regs && !failed_get && !failed_set && !failed_reject,
-		    "%s: There are %d missing registers; "
-		    "%d registers failed get; %d registers failed set; %d registers failed reject",
-		    config_name(c), missing_regs, failed_get, failed_set, failed_reject);
+		    "%s: There are %d missing registers; %d registers failed get; "
+		    "%d registers failed set; %d registers failed reject; %d registers skipped set",
+		    config_name(c), missing_regs, failed_get, failed_set, failed_reject, skipped_set);
 
 	pr_info("%s: PASS\n", config_name(c));
 	blessed_n = 0;
diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
index bc7c08a09d30..a18db6a7b3cf 100644
--- a/tools/testing/selftests/kvm/include/kvm_util_base.h
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -134,6 +134,8 @@ struct vcpu_reg_sublist {
 	__u64 regs_n;
 	__u64 *rejects_set;
 	__u64 rejects_set_n;
+	__u64 *skips_set;
+	__u64 skips_set_n;
 };
 
 struct vcpu_reg_list {

From 031f9efafc08d68b1b672e83ee73f6ea5c69c2ef Mon Sep 17 00:00:00 2001
From: Haibo Xu <haibo1.xu@intel.com>
Date: Tue, 25 Jul 2023 16:41:38 +0800
Subject: [PATCH 0385/1189] KVM: riscv: Add KVM_GET_REG_LIST API support

KVM_GET_REG_LIST API will return all registers that are available to
KVM_GET/SET_ONE_REG APIs. It's very useful to identify some platform
regression issue during VM migration.

Since this API was already supported on arm64, it is straightforward
to enable it on riscv with similar code structure.

Signed-off-by: Haibo Xu <haibo1.xu@intel.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 Documentation/virt/kvm/api.rst    |   2 +-
 arch/riscv/include/asm/kvm_host.h |   3 +
 arch/riscv/kvm/vcpu.c             |  18 ++
 arch/riscv/kvm/vcpu_onereg.c      | 366 ++++++++++++++++++++++++++++++
 4 files changed, 388 insertions(+), 1 deletion(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 3249fb56cc69..660d9ca7a251 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -3501,7 +3501,7 @@ VCPU matching underlying host.
 ---------------------
 
 :Capability: basic
-:Architectures: arm64, mips
+:Architectures: arm64, mips, riscv
 :Type: vcpu ioctl
 :Parameters: struct kvm_reg_list (in/out)
 :Returns: 0 on success; -1 on error
diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index 55bc7bdbff48..1ebf20dfbaa6 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -338,6 +338,9 @@ int kvm_riscv_vcpu_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 void __kvm_riscv_switch_to(struct kvm_vcpu_arch *vcpu_arch);
 
 void kvm_riscv_vcpu_setup_isa(struct kvm_vcpu *vcpu);
+unsigned long kvm_riscv_vcpu_num_regs(struct kvm_vcpu *vcpu);
+int kvm_riscv_vcpu_copy_reg_indices(struct kvm_vcpu *vcpu,
+				    u64 __user *uindices);
 int kvm_riscv_vcpu_get_reg(struct kvm_vcpu *vcpu,
 			   const struct kvm_one_reg *reg);
 int kvm_riscv_vcpu_set_reg(struct kvm_vcpu *vcpu,
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index 452d6548e951..82229db1ce73 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -254,6 +254,24 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 			r = kvm_riscv_vcpu_get_reg(vcpu, &reg);
 		break;
 	}
+	case KVM_GET_REG_LIST: {
+		struct kvm_reg_list __user *user_list = argp;
+		struct kvm_reg_list reg_list;
+		unsigned int n;
+
+		r = -EFAULT;
+		if (copy_from_user(&reg_list, user_list, sizeof(reg_list)))
+			break;
+		n = reg_list.n;
+		reg_list.n = kvm_riscv_vcpu_num_regs(vcpu);
+		if (copy_to_user(user_list, &reg_list, sizeof(reg_list)))
+			break;
+		r = -E2BIG;
+		if (n < reg_list.n)
+			break;
+		r = kvm_riscv_vcpu_copy_reg_indices(vcpu, user_list->reg);
+		break;
+	}
 	default:
 		break;
 	}
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index 9fee1c176fbb..1b7e9fa265cb 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -622,6 +622,372 @@ static int kvm_riscv_vcpu_set_reg_isa_ext(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static int copy_config_reg_indices(const struct kvm_vcpu *vcpu,
+				u64 __user *uindices)
+{
+	int n = 0;
+
+	for (int i = 0; i < sizeof(struct kvm_riscv_config)/sizeof(unsigned long);
+		 i++) {
+		u64 size;
+		u64 reg;
+
+		/*
+		 * Avoid reporting config reg if the corresponding extension
+		 * was not available.
+		 */
+		if (i == KVM_REG_RISCV_CONFIG_REG(zicbom_block_size) &&
+			!riscv_isa_extension_available(vcpu->arch.isa, ZICBOM))
+			continue;
+		else if (i == KVM_REG_RISCV_CONFIG_REG(zicboz_block_size) &&
+			!riscv_isa_extension_available(vcpu->arch.isa, ZICBOZ))
+			continue;
+
+		size = IS_ENABLED(CONFIG_32BIT) ? KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64;
+		reg = KVM_REG_RISCV | size | KVM_REG_RISCV_CONFIG | i;
+
+		if (uindices) {
+			if (put_user(reg, uindices))
+				return -EFAULT;
+			uindices++;
+		}
+
+		n++;
+	}
+
+	return n;
+}
+
+static unsigned long num_config_regs(const struct kvm_vcpu *vcpu)
+{
+	return copy_config_reg_indices(vcpu, NULL);
+}
+
+static inline unsigned long num_core_regs(void)
+{
+	return sizeof(struct kvm_riscv_core) / sizeof(unsigned long);
+}
+
+static int copy_core_reg_indices(u64 __user *uindices)
+{
+	int n = num_core_regs();
+
+	for (int i = 0; i < n; i++) {
+		u64 size = IS_ENABLED(CONFIG_32BIT) ?
+			   KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64;
+		u64 reg = KVM_REG_RISCV | size | KVM_REG_RISCV_CORE | i;
+
+		if (uindices) {
+			if (put_user(reg, uindices))
+				return -EFAULT;
+			uindices++;
+		}
+	}
+
+	return n;
+}
+
+static inline unsigned long num_csr_regs(const struct kvm_vcpu *vcpu)
+{
+	unsigned long n = sizeof(struct kvm_riscv_csr) / sizeof(unsigned long);
+
+	if (riscv_isa_extension_available(vcpu->arch.isa, SSAIA))
+		n += sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long);
+
+	return n;
+}
+
+static int copy_csr_reg_indices(const struct kvm_vcpu *vcpu,
+				u64 __user *uindices)
+{
+	int n1 = sizeof(struct kvm_riscv_csr) / sizeof(unsigned long);
+	int n2 = 0;
+
+	/* copy general csr regs */
+	for (int i = 0; i < n1; i++) {
+		u64 size = IS_ENABLED(CONFIG_32BIT) ?
+			   KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64;
+		u64 reg = KVM_REG_RISCV | size | KVM_REG_RISCV_CSR |
+				  KVM_REG_RISCV_CSR_GENERAL | i;
+
+		if (uindices) {
+			if (put_user(reg, uindices))
+				return -EFAULT;
+			uindices++;
+		}
+	}
+
+	/* copy AIA csr regs */
+	if (riscv_isa_extension_available(vcpu->arch.isa, SSAIA)) {
+		n2 = sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long);
+
+		for (int i = 0; i < n2; i++) {
+			u64 size = IS_ENABLED(CONFIG_32BIT) ?
+				   KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64;
+			u64 reg = KVM_REG_RISCV | size | KVM_REG_RISCV_CSR |
+					  KVM_REG_RISCV_CSR_AIA | i;
+
+			if (uindices) {
+				if (put_user(reg, uindices))
+					return -EFAULT;
+				uindices++;
+			}
+		}
+	}
+
+	return n1 + n2;
+}
+
+static inline unsigned long num_timer_regs(void)
+{
+	return sizeof(struct kvm_riscv_timer) / sizeof(u64);
+}
+
+static int copy_timer_reg_indices(u64 __user *uindices)
+{
+	int n = num_timer_regs();
+
+	for (int i = 0; i < n; i++) {
+		u64 reg = KVM_REG_RISCV | KVM_REG_SIZE_U64 |
+			  KVM_REG_RISCV_TIMER | i;
+
+		if (uindices) {
+			if (put_user(reg, uindices))
+				return -EFAULT;
+			uindices++;
+		}
+	}
+
+	return n;
+}
+
+static inline unsigned long num_fp_f_regs(const struct kvm_vcpu *vcpu)
+{
+	const struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
+
+	if (riscv_isa_extension_available(vcpu->arch.isa, f))
+		return sizeof(cntx->fp.f) / sizeof(u32);
+	else
+		return 0;
+}
+
+static int copy_fp_f_reg_indices(const struct kvm_vcpu *vcpu,
+				u64 __user *uindices)
+{
+	int n = num_fp_f_regs(vcpu);
+
+	for (int i = 0; i < n; i++) {
+		u64 reg = KVM_REG_RISCV | KVM_REG_SIZE_U32 |
+			  KVM_REG_RISCV_FP_F | i;
+
+		if (uindices) {
+			if (put_user(reg, uindices))
+				return -EFAULT;
+			uindices++;
+		}
+	}
+
+	return n;
+}
+
+static inline unsigned long num_fp_d_regs(const struct kvm_vcpu *vcpu)
+{
+	const struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
+
+	if (riscv_isa_extension_available(vcpu->arch.isa, d))
+		return sizeof(cntx->fp.d.f) / sizeof(u64) + 1;
+	else
+		return 0;
+}
+
+static int copy_fp_d_reg_indices(const struct kvm_vcpu *vcpu,
+				u64 __user *uindices)
+{
+	int i;
+	int n = num_fp_d_regs(vcpu);
+	u64 reg;
+
+	/* copy fp.d.f indices */
+	for (i = 0; i < n-1; i++) {
+		reg = KVM_REG_RISCV | KVM_REG_SIZE_U64 |
+		      KVM_REG_RISCV_FP_D | i;
+
+		if (uindices) {
+			if (put_user(reg, uindices))
+				return -EFAULT;
+			uindices++;
+		}
+	}
+
+	/* copy fp.d.fcsr indices */
+	reg = KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_D | i;
+	if (uindices) {
+		if (put_user(reg, uindices))
+			return -EFAULT;
+		uindices++;
+	}
+
+	return n;
+}
+
+static int copy_isa_ext_reg_indices(const struct kvm_vcpu *vcpu,
+				u64 __user *uindices)
+{
+	unsigned int n = 0;
+	unsigned long isa_ext;
+
+	for (int i = 0; i < KVM_RISCV_ISA_EXT_MAX; i++) {
+		u64 size = IS_ENABLED(CONFIG_32BIT) ?
+			   KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64;
+		u64 reg = KVM_REG_RISCV | size | KVM_REG_RISCV_ISA_EXT | i;
+
+		isa_ext = kvm_isa_ext_arr[i];
+		if (!__riscv_isa_extension_available(vcpu->arch.isa, isa_ext))
+			continue;
+
+		if (uindices) {
+			if (put_user(reg, uindices))
+				return -EFAULT;
+			uindices++;
+		}
+
+		n++;
+	}
+
+	return n;
+}
+
+static inline unsigned long num_isa_ext_regs(const struct kvm_vcpu *vcpu)
+{
+	return copy_isa_ext_reg_indices(vcpu, NULL);;
+}
+
+static inline unsigned long num_sbi_ext_regs(void)
+{
+	/*
+	 * number of KVM_REG_RISCV_SBI_SINGLE +
+	 * 2 x (number of KVM_REG_RISCV_SBI_MULTI)
+	 */
+	return KVM_RISCV_SBI_EXT_MAX + 2*(KVM_REG_RISCV_SBI_MULTI_REG_LAST+1);
+}
+
+static int copy_sbi_ext_reg_indices(u64 __user *uindices)
+{
+	int n;
+
+	/* copy KVM_REG_RISCV_SBI_SINGLE */
+	n = KVM_RISCV_SBI_EXT_MAX;
+	for (int i = 0; i < n; i++) {
+		u64 size = IS_ENABLED(CONFIG_32BIT) ?
+			   KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64;
+		u64 reg = KVM_REG_RISCV | size | KVM_REG_RISCV_SBI_EXT |
+			  KVM_REG_RISCV_SBI_SINGLE | i;
+
+		if (uindices) {
+			if (put_user(reg, uindices))
+				return -EFAULT;
+			uindices++;
+		}
+	}
+
+	/* copy KVM_REG_RISCV_SBI_MULTI */
+	n = KVM_REG_RISCV_SBI_MULTI_REG_LAST + 1;
+	for (int i = 0; i < n; i++) {
+		u64 size = IS_ENABLED(CONFIG_32BIT) ?
+			   KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64;
+		u64 reg = KVM_REG_RISCV | size | KVM_REG_RISCV_SBI_EXT |
+			  KVM_REG_RISCV_SBI_MULTI_EN | i;
+
+		if (uindices) {
+			if (put_user(reg, uindices))
+				return -EFAULT;
+			uindices++;
+		}
+
+		reg = KVM_REG_RISCV | size | KVM_REG_RISCV_SBI_EXT |
+			  KVM_REG_RISCV_SBI_MULTI_DIS | i;
+
+		if (uindices) {
+			if (put_user(reg, uindices))
+				return -EFAULT;
+			uindices++;
+		}
+	}
+
+	return num_sbi_ext_regs();
+}
+
+/*
+ * kvm_riscv_vcpu_num_regs - how many registers do we present via KVM_GET/SET_ONE_REG
+ *
+ * This is for all registers.
+ */
+unsigned long kvm_riscv_vcpu_num_regs(struct kvm_vcpu *vcpu)
+{
+	unsigned long res = 0;
+
+	res += num_config_regs(vcpu);
+	res += num_core_regs();
+	res += num_csr_regs(vcpu);
+	res += num_timer_regs();
+	res += num_fp_f_regs(vcpu);
+	res += num_fp_d_regs(vcpu);
+	res += num_isa_ext_regs(vcpu);
+	res += num_sbi_ext_regs();
+
+	return res;
+}
+
+/*
+ * kvm_riscv_vcpu_copy_reg_indices - get indices of all registers.
+ */
+int kvm_riscv_vcpu_copy_reg_indices(struct kvm_vcpu *vcpu,
+				    u64 __user *uindices)
+{
+	int ret;
+
+	ret = copy_config_reg_indices(vcpu, uindices);
+	if (ret < 0)
+		return ret;
+	uindices += ret;
+
+	ret = copy_core_reg_indices(uindices);
+	if (ret < 0)
+		return ret;
+	uindices += ret;
+
+	ret = copy_csr_reg_indices(vcpu, uindices);
+	if (ret < 0)
+		return ret;
+	uindices += ret;
+
+	ret = copy_timer_reg_indices(uindices);
+	if (ret < 0)
+		return ret;
+	uindices += ret;
+
+	ret = copy_fp_f_reg_indices(vcpu, uindices);
+	if (ret < 0)
+		return ret;
+	uindices += ret;
+
+	ret = copy_fp_d_reg_indices(vcpu, uindices);
+	if (ret < 0)
+		return ret;
+	uindices += ret;
+
+	ret = copy_isa_ext_reg_indices(vcpu, uindices);
+	if (ret < 0)
+		return ret;
+	uindices += ret;
+
+	ret = copy_sbi_ext_reg_indices(uindices);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
 int kvm_riscv_vcpu_set_reg(struct kvm_vcpu *vcpu,
 			   const struct kvm_one_reg *reg)
 {

From 477069398ed6e0498ee243e799cb6c68baf6ccb8 Mon Sep 17 00:00:00 2001
From: Haibo Xu <haibo1.xu@intel.com>
Date: Tue, 25 Jul 2023 16:41:39 +0800
Subject: [PATCH 0386/1189] KVM: riscv: selftests: Add get-reg-list test

get-reg-list test is used to check for KVM registers regressions
during VM migration which happens when destination host kernel
missing registers that the source host kernel has. The blessed
list registers was created by running on v6.5-rc3

Signed-off-by: Haibo Xu <haibo1.xu@intel.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 tools/testing/selftests/kvm/Makefile          |   1 +
 .../selftests/kvm/include/riscv/processor.h   |   3 +
 .../selftests/kvm/riscv/get-reg-list.c        | 872 ++++++++++++++++++
 3 files changed, 876 insertions(+)
 create mode 100644 tools/testing/selftests/kvm/riscv/get-reg-list.c

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 95f180e711d5..72ba48fcdc66 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -176,6 +176,7 @@ TEST_GEN_PROGS_s390x += kvm_binary_stats_test
 
 TEST_GEN_PROGS_riscv += demand_paging_test
 TEST_GEN_PROGS_riscv += dirty_log_test
+TEST_GEN_PROGS_riscv += get-reg-list
 TEST_GEN_PROGS_riscv += kvm_create_max_vcpus
 TEST_GEN_PROGS_riscv += kvm_page_table_test
 TEST_GEN_PROGS_riscv += set_memory_region_test
diff --git a/tools/testing/selftests/kvm/include/riscv/processor.h b/tools/testing/selftests/kvm/include/riscv/processor.h
index d00d213c3805..5b62a3d2aa9b 100644
--- a/tools/testing/selftests/kvm/include/riscv/processor.h
+++ b/tools/testing/selftests/kvm/include/riscv/processor.h
@@ -38,6 +38,9 @@ static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t idx,
 					     KVM_REG_RISCV_TIMER_REG(name), \
 					     KVM_REG_SIZE_U64)
 
+#define RISCV_ISA_EXT_REG(idx)	__kvm_reg_id(KVM_REG_RISCV_ISA_EXT, \
+					     idx, KVM_REG_SIZE_ULONG)
+
 /* L3 index Bit[47:39] */
 #define PGTBL_L3_INDEX_MASK			0x0000FF8000000000ULL
 #define PGTBL_L3_INDEX_SHIFT			39
diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
new file mode 100644
index 000000000000..d8ecacd03ecf
--- /dev/null
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -0,0 +1,872 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Check for KVM_GET_REG_LIST regressions.
+ *
+ * Copyright (c) 2023 Intel Corporation
+ *
+ */
+#include <stdio.h>
+#include "kvm_util.h"
+#include "test_util.h"
+#include "processor.h"
+
+#define REG_MASK (KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK)
+
+bool filter_reg(__u64 reg)
+{
+	/*
+	 * Some ISA extensions are optional and not present on all host,
+	 * but they can't be disabled through ISA_EXT registers when present.
+	 * So, to make life easy, just filtering out these kind of registers.
+	 */
+	switch (reg & ~REG_MASK) {
+	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SSTC:
+	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SVINVAL:
+	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIHINTPAUSE:
+	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBB:
+	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SSAIA:
+	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBA:
+	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBS:
+	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICNTR:
+	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICSR:
+	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIFENCEI:
+	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIHPM:
+		return true;
+	default:
+		break;
+	}
+
+	return false;
+}
+
+bool check_reject_set(int err)
+{
+	return err == EINVAL;
+}
+
+static inline bool vcpu_has_ext(struct kvm_vcpu *vcpu, int ext)
+{
+	int ret;
+	unsigned long value;
+
+	ret = __vcpu_get_reg(vcpu, RISCV_ISA_EXT_REG(ext), &value);
+	if (ret) {
+		printf("Failed to get ext %d", ext);
+		return false;
+	}
+
+	return !!value;
+}
+
+void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c)
+{
+	struct vcpu_reg_sublist *s;
+
+	/*
+	 * Disable all extensions which were enabled by default
+	 * if they were available in the risc-v host.
+	 */
+	for (int i = 0; i < KVM_RISCV_ISA_EXT_MAX; i++)
+		__vcpu_set_reg(vcpu, RISCV_ISA_EXT_REG(i), 0);
+
+	for_each_sublist(c, s) {
+		if (!s->feature)
+			continue;
+
+		/* Try to enable the desired extension */
+		__vcpu_set_reg(vcpu, RISCV_ISA_EXT_REG(s->feature), 1);
+
+		/* Double check whether the desired extension was enabled */
+		__TEST_REQUIRE(vcpu_has_ext(vcpu, s->feature),
+			       "%s not available, skipping tests\n", s->name);
+	}
+}
+
+static const char *config_id_to_str(__u64 id)
+{
+	/* reg_off is the offset into struct kvm_riscv_config */
+	__u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_CONFIG);
+
+	switch (reg_off) {
+	case KVM_REG_RISCV_CONFIG_REG(isa):
+		return "KVM_REG_RISCV_CONFIG_REG(isa)";
+	case KVM_REG_RISCV_CONFIG_REG(zicbom_block_size):
+		return "KVM_REG_RISCV_CONFIG_REG(zicbom_block_size)";
+	case KVM_REG_RISCV_CONFIG_REG(zicboz_block_size):
+		return "KVM_REG_RISCV_CONFIG_REG(zicboz_block_size)";
+	case KVM_REG_RISCV_CONFIG_REG(mvendorid):
+		return "KVM_REG_RISCV_CONFIG_REG(mvendorid)";
+	case KVM_REG_RISCV_CONFIG_REG(marchid):
+		return "KVM_REG_RISCV_CONFIG_REG(marchid)";
+	case KVM_REG_RISCV_CONFIG_REG(mimpid):
+		return "KVM_REG_RISCV_CONFIG_REG(mimpid)";
+	case KVM_REG_RISCV_CONFIG_REG(satp_mode):
+		return "KVM_REG_RISCV_CONFIG_REG(satp_mode)";
+	}
+
+	/*
+	 * Config regs would grow regularly with new pseudo reg added, so
+	 * just show raw id to indicate a new pseudo config reg.
+	 */
+	return strdup_printf("KVM_REG_RISCV_CONFIG_REG(%lld) /* UNKNOWN */", reg_off);
+}
+
+static const char *core_id_to_str(const char *prefix, __u64 id)
+{
+	/* reg_off is the offset into struct kvm_riscv_core */
+	__u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_CORE);
+
+	switch (reg_off) {
+	case KVM_REG_RISCV_CORE_REG(regs.pc):
+		return "KVM_REG_RISCV_CORE_REG(regs.pc)";
+	case KVM_REG_RISCV_CORE_REG(regs.ra):
+		return "KVM_REG_RISCV_CORE_REG(regs.ra)";
+	case KVM_REG_RISCV_CORE_REG(regs.sp):
+		return "KVM_REG_RISCV_CORE_REG(regs.sp)";
+	case KVM_REG_RISCV_CORE_REG(regs.gp):
+		return "KVM_REG_RISCV_CORE_REG(regs.gp)";
+	case KVM_REG_RISCV_CORE_REG(regs.tp):
+		return "KVM_REG_RISCV_CORE_REG(regs.tp)";
+	case KVM_REG_RISCV_CORE_REG(regs.t0) ... KVM_REG_RISCV_CORE_REG(regs.t2):
+		return strdup_printf("KVM_REG_RISCV_CORE_REG(regs.t%lld)",
+			   reg_off - KVM_REG_RISCV_CORE_REG(regs.t0));
+	case KVM_REG_RISCV_CORE_REG(regs.s0) ... KVM_REG_RISCV_CORE_REG(regs.s1):
+		return strdup_printf("KVM_REG_RISCV_CORE_REG(regs.s%lld)",
+			   reg_off - KVM_REG_RISCV_CORE_REG(regs.s0));
+	case KVM_REG_RISCV_CORE_REG(regs.a0) ... KVM_REG_RISCV_CORE_REG(regs.a7):
+		return strdup_printf("KVM_REG_RISCV_CORE_REG(regs.a%lld)",
+			   reg_off - KVM_REG_RISCV_CORE_REG(regs.a0));
+	case KVM_REG_RISCV_CORE_REG(regs.s2) ... KVM_REG_RISCV_CORE_REG(regs.s11):
+		return strdup_printf("KVM_REG_RISCV_CORE_REG(regs.s%lld)",
+			   reg_off - KVM_REG_RISCV_CORE_REG(regs.s2) + 2);
+	case KVM_REG_RISCV_CORE_REG(regs.t3) ... KVM_REG_RISCV_CORE_REG(regs.t6):
+		return strdup_printf("KVM_REG_RISCV_CORE_REG(regs.t%lld)",
+			   reg_off - KVM_REG_RISCV_CORE_REG(regs.t3) + 3);
+	case KVM_REG_RISCV_CORE_REG(mode):
+		return "KVM_REG_RISCV_CORE_REG(mode)";
+	}
+
+	TEST_FAIL("%s: Unknown core reg id: 0x%llx", prefix, id);
+	return NULL;
+}
+
+#define RISCV_CSR_GENERAL(csr) \
+	"KVM_REG_RISCV_CSR_GENERAL | KVM_REG_RISCV_CSR_REG(" #csr ")"
+#define RISCV_CSR_AIA(csr) \
+	"KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_REG(" #csr ")"
+
+static const char *general_csr_id_to_str(__u64 reg_off)
+{
+	/* reg_off is the offset into struct kvm_riscv_csr */
+	switch (reg_off) {
+	case KVM_REG_RISCV_CSR_REG(sstatus):
+		return RISCV_CSR_GENERAL(sstatus);
+	case KVM_REG_RISCV_CSR_REG(sie):
+		return RISCV_CSR_GENERAL(sie);
+	case KVM_REG_RISCV_CSR_REG(stvec):
+		return RISCV_CSR_GENERAL(stvec);
+	case KVM_REG_RISCV_CSR_REG(sscratch):
+		return RISCV_CSR_GENERAL(sscratch);
+	case KVM_REG_RISCV_CSR_REG(sepc):
+		return RISCV_CSR_GENERAL(sepc);
+	case KVM_REG_RISCV_CSR_REG(scause):
+		return RISCV_CSR_GENERAL(scause);
+	case KVM_REG_RISCV_CSR_REG(stval):
+		return RISCV_CSR_GENERAL(stval);
+	case KVM_REG_RISCV_CSR_REG(sip):
+		return RISCV_CSR_GENERAL(sip);
+	case KVM_REG_RISCV_CSR_REG(satp):
+		return RISCV_CSR_GENERAL(satp);
+	case KVM_REG_RISCV_CSR_REG(scounteren):
+		return RISCV_CSR_GENERAL(scounteren);
+	}
+
+	TEST_FAIL("Unknown general csr reg: 0x%llx", reg_off);
+	return NULL;
+}
+
+static const char *aia_csr_id_to_str(__u64 reg_off)
+{
+	/* reg_off is the offset into struct kvm_riscv_aia_csr */
+	switch (reg_off) {
+	case KVM_REG_RISCV_CSR_AIA_REG(siselect):
+		return RISCV_CSR_AIA(siselect);
+	case KVM_REG_RISCV_CSR_AIA_REG(iprio1):
+		return RISCV_CSR_AIA(iprio1);
+	case KVM_REG_RISCV_CSR_AIA_REG(iprio2):
+		return RISCV_CSR_AIA(iprio2);
+	case KVM_REG_RISCV_CSR_AIA_REG(sieh):
+		return RISCV_CSR_AIA(sieh);
+	case KVM_REG_RISCV_CSR_AIA_REG(siph):
+		return RISCV_CSR_AIA(siph);
+	case KVM_REG_RISCV_CSR_AIA_REG(iprio1h):
+		return RISCV_CSR_AIA(iprio1h);
+	case KVM_REG_RISCV_CSR_AIA_REG(iprio2h):
+		return RISCV_CSR_AIA(iprio2h);
+	}
+
+	TEST_FAIL("Unknown aia csr reg: 0x%llx", reg_off);
+	return NULL;
+}
+
+static const char *csr_id_to_str(const char *prefix, __u64 id)
+{
+	__u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_CSR);
+	__u64 reg_subtype = reg_off & KVM_REG_RISCV_SUBTYPE_MASK;
+
+	reg_off &= ~KVM_REG_RISCV_SUBTYPE_MASK;
+
+	switch (reg_subtype) {
+	case KVM_REG_RISCV_CSR_GENERAL:
+		return general_csr_id_to_str(reg_off);
+	case KVM_REG_RISCV_CSR_AIA:
+		return aia_csr_id_to_str(reg_off);
+	}
+
+	TEST_FAIL("%s: Unknown csr subtype: 0x%llx", prefix, reg_subtype);
+	return NULL;
+}
+
+static const char *timer_id_to_str(const char *prefix, __u64 id)
+{
+	/* reg_off is the offset into struct kvm_riscv_timer */
+	__u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_TIMER);
+
+	switch (reg_off) {
+	case KVM_REG_RISCV_TIMER_REG(frequency):
+		return "KVM_REG_RISCV_TIMER_REG(frequency)";
+	case KVM_REG_RISCV_TIMER_REG(time):
+		return "KVM_REG_RISCV_TIMER_REG(time)";
+	case KVM_REG_RISCV_TIMER_REG(compare):
+		return "KVM_REG_RISCV_TIMER_REG(compare)";
+	case KVM_REG_RISCV_TIMER_REG(state):
+		return "KVM_REG_RISCV_TIMER_REG(state)";
+	}
+
+	TEST_FAIL("%s: Unknown timer reg id: 0x%llx", prefix, id);
+	return NULL;
+}
+
+static const char *fp_f_id_to_str(const char *prefix, __u64 id)
+{
+	/* reg_off is the offset into struct __riscv_f_ext_state */
+	__u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_FP_F);
+
+	switch (reg_off) {
+	case KVM_REG_RISCV_FP_F_REG(f[0]) ...
+	     KVM_REG_RISCV_FP_F_REG(f[31]):
+		return strdup_printf("KVM_REG_RISCV_FP_F_REG(f[%lld])", reg_off);
+	case KVM_REG_RISCV_FP_F_REG(fcsr):
+		return "KVM_REG_RISCV_FP_F_REG(fcsr)";
+	}
+
+	TEST_FAIL("%s: Unknown fp_f reg id: 0x%llx", prefix, id);
+	return NULL;
+}
+
+static const char *fp_d_id_to_str(const char *prefix, __u64 id)
+{
+	/* reg_off is the offset into struct __riscv_d_ext_state */
+	__u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_FP_D);
+
+	switch (reg_off) {
+	case KVM_REG_RISCV_FP_D_REG(f[0]) ...
+	     KVM_REG_RISCV_FP_D_REG(f[31]):
+		return strdup_printf("KVM_REG_RISCV_FP_D_REG(f[%lld])", reg_off);
+	case KVM_REG_RISCV_FP_D_REG(fcsr):
+		return "KVM_REG_RISCV_FP_D_REG(fcsr)";
+	}
+
+	TEST_FAIL("%s: Unknown fp_d reg id: 0x%llx", prefix, id);
+	return NULL;
+}
+
+static const char *isa_ext_id_to_str(__u64 id)
+{
+	/* reg_off is the offset into unsigned long kvm_isa_ext_arr[] */
+	__u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_ISA_EXT);
+
+	static const char * const kvm_isa_ext_reg_name[] = {
+		"KVM_RISCV_ISA_EXT_A",
+		"KVM_RISCV_ISA_EXT_C",
+		"KVM_RISCV_ISA_EXT_D",
+		"KVM_RISCV_ISA_EXT_F",
+		"KVM_RISCV_ISA_EXT_H",
+		"KVM_RISCV_ISA_EXT_I",
+		"KVM_RISCV_ISA_EXT_M",
+		"KVM_RISCV_ISA_EXT_SVPBMT",
+		"KVM_RISCV_ISA_EXT_SSTC",
+		"KVM_RISCV_ISA_EXT_SVINVAL",
+		"KVM_RISCV_ISA_EXT_ZIHINTPAUSE",
+		"KVM_RISCV_ISA_EXT_ZICBOM",
+		"KVM_RISCV_ISA_EXT_ZICBOZ",
+		"KVM_RISCV_ISA_EXT_ZBB",
+		"KVM_RISCV_ISA_EXT_SSAIA",
+		"KVM_RISCV_ISA_EXT_V",
+		"KVM_RISCV_ISA_EXT_SVNAPOT",
+		"KVM_RISCV_ISA_EXT_ZBA",
+		"KVM_RISCV_ISA_EXT_ZBS",
+		"KVM_RISCV_ISA_EXT_ZICNTR",
+		"KVM_RISCV_ISA_EXT_ZICSR",
+		"KVM_RISCV_ISA_EXT_ZIFENCEI",
+		"KVM_RISCV_ISA_EXT_ZIHPM",
+	};
+
+	if (reg_off >= ARRAY_SIZE(kvm_isa_ext_reg_name)) {
+		/*
+		 * isa_ext regs would grow regularly with new isa extension added, so
+		 * just show "reg" to indicate a new extension.
+		 */
+		return strdup_printf("%lld /* UNKNOWN */", reg_off);
+	}
+
+	return kvm_isa_ext_reg_name[reg_off];
+}
+
+static const char *sbi_ext_single_id_to_str(__u64 reg_off)
+{
+	/* reg_off is KVM_RISCV_SBI_EXT_ID */
+	static const char * const kvm_sbi_ext_reg_name[] = {
+		"KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_V01",
+		"KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_TIME",
+		"KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_IPI",
+		"KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_RFENCE",
+		"KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_SRST",
+		"KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_HSM",
+		"KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_PMU",
+		"KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_EXPERIMENTAL",
+		"KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_VENDOR",
+	};
+
+	if (reg_off >= ARRAY_SIZE(kvm_sbi_ext_reg_name)) {
+		/*
+		 * sbi_ext regs would grow regularly with new sbi extension added, so
+		 * just show "reg" to indicate a new extension.
+		 */
+		return strdup_printf("KVM_REG_RISCV_SBI_SINGLE | %lld /* UNKNOWN */", reg_off);
+	}
+
+	return kvm_sbi_ext_reg_name[reg_off];
+}
+
+static const char *sbi_ext_multi_id_to_str(__u64 reg_subtype, __u64 reg_off)
+{
+	if (reg_off > KVM_REG_RISCV_SBI_MULTI_REG_LAST) {
+		/*
+		 * sbi_ext regs would grow regularly with new sbi extension added, so
+		 * just show "reg" to indicate a new extension.
+		 */
+		return strdup_printf("%lld /* UNKNOWN */", reg_off);
+	}
+
+	switch (reg_subtype) {
+	case KVM_REG_RISCV_SBI_MULTI_EN:
+		return strdup_printf("KVM_REG_RISCV_SBI_MULTI_EN | %lld", reg_off);
+	case KVM_REG_RISCV_SBI_MULTI_DIS:
+		return strdup_printf("KVM_REG_RISCV_SBI_MULTI_DIS | %lld", reg_off);
+	}
+
+	return NULL;
+}
+
+static const char *sbi_ext_id_to_str(const char *prefix, __u64 id)
+{
+	__u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_SBI_EXT);
+	__u64 reg_subtype = reg_off & KVM_REG_RISCV_SUBTYPE_MASK;
+
+	reg_off &= ~KVM_REG_RISCV_SUBTYPE_MASK;
+
+	switch (reg_subtype) {
+	case KVM_REG_RISCV_SBI_SINGLE:
+		return sbi_ext_single_id_to_str(reg_off);
+	case KVM_REG_RISCV_SBI_MULTI_EN:
+	case KVM_REG_RISCV_SBI_MULTI_DIS:
+		return sbi_ext_multi_id_to_str(reg_subtype, reg_off);
+	}
+
+	TEST_FAIL("%s: Unknown sbi ext subtype: 0x%llx", prefix, reg_subtype);
+	return NULL;
+}
+
+void print_reg(const char *prefix, __u64 id)
+{
+	const char *reg_size = NULL;
+
+	TEST_ASSERT((id & KVM_REG_ARCH_MASK) == KVM_REG_RISCV,
+		    "%s: KVM_REG_RISCV missing in reg id: 0x%llx", prefix, id);
+
+	switch (id & KVM_REG_SIZE_MASK) {
+	case KVM_REG_SIZE_U32:
+		reg_size = "KVM_REG_SIZE_U32";
+		break;
+	case KVM_REG_SIZE_U64:
+		reg_size = "KVM_REG_SIZE_U64";
+		break;
+	case KVM_REG_SIZE_U128:
+		reg_size = "KVM_REG_SIZE_U128";
+		break;
+	default:
+		TEST_FAIL("%s: Unexpected reg size: 0x%llx in reg id: 0x%llx",
+			  prefix, (id & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT, id);
+	}
+
+	switch (id & KVM_REG_RISCV_TYPE_MASK) {
+	case KVM_REG_RISCV_CONFIG:
+		printf("\tKVM_REG_RISCV | %s | KVM_REG_RISCV_CONFIG | %s,\n",
+				reg_size, config_id_to_str(id));
+		break;
+	case KVM_REG_RISCV_CORE:
+		printf("\tKVM_REG_RISCV | %s | KVM_REG_RISCV_CORE | %s,\n",
+				reg_size, core_id_to_str(prefix, id));
+		break;
+	case KVM_REG_RISCV_CSR:
+		printf("\tKVM_REG_RISCV | %s | KVM_REG_RISCV_CSR | %s,\n",
+				reg_size, csr_id_to_str(prefix, id));
+		break;
+	case KVM_REG_RISCV_TIMER:
+		printf("\tKVM_REG_RISCV | %s | KVM_REG_RISCV_TIMER | %s,\n",
+				reg_size, timer_id_to_str(prefix, id));
+		break;
+	case KVM_REG_RISCV_FP_F:
+		printf("\tKVM_REG_RISCV | %s | KVM_REG_RISCV_FP_F | %s,\n",
+				reg_size, fp_f_id_to_str(prefix, id));
+		break;
+	case KVM_REG_RISCV_FP_D:
+		printf("\tKVM_REG_RISCV | %s | KVM_REG_RISCV_FP_D | %s,\n",
+				reg_size, fp_d_id_to_str(prefix, id));
+		break;
+	case KVM_REG_RISCV_ISA_EXT:
+		printf("\tKVM_REG_RISCV | %s | KVM_REG_RISCV_ISA_EXT | %s,\n",
+				reg_size, isa_ext_id_to_str(id));
+		break;
+	case KVM_REG_RISCV_SBI_EXT:
+		printf("\tKVM_REG_RISCV | %s | KVM_REG_RISCV_SBI_EXT | %s,\n",
+				reg_size, sbi_ext_id_to_str(prefix, id));
+		break;
+	default:
+		TEST_FAIL("%s: Unexpected reg type: 0x%llx in reg id: 0x%llx", prefix,
+				(id & KVM_REG_RISCV_TYPE_MASK) >> KVM_REG_RISCV_TYPE_SHIFT, id);
+	}
+}
+
+/*
+ * The current blessed list was primed with the output of kernel version
+ * v6.5-rc3 and then later updated with new registers.
+ */
+static __u64 base_regs[] = {
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(isa),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(mvendorid),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(marchid),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(mimpid),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(satp_mode),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.pc),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.ra),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.sp),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.gp),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.tp),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.t0),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.t1),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.t2),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.s0),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.s1),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.a0),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.a1),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.a2),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.a3),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.a4),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.a5),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.a6),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.a7),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.s2),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.s3),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.s4),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.s5),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.s6),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.s7),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.s8),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.s9),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.s10),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.s11),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.t3),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.t4),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.t5),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.t6),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(mode),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_GENERAL | KVM_REG_RISCV_CSR_REG(sstatus),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_GENERAL | KVM_REG_RISCV_CSR_REG(sie),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_GENERAL | KVM_REG_RISCV_CSR_REG(stvec),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_GENERAL | KVM_REG_RISCV_CSR_REG(sscratch),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_GENERAL | KVM_REG_RISCV_CSR_REG(sepc),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_GENERAL | KVM_REG_RISCV_CSR_REG(scause),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_GENERAL | KVM_REG_RISCV_CSR_REG(stval),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_GENERAL | KVM_REG_RISCV_CSR_REG(sip),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_GENERAL | KVM_REG_RISCV_CSR_REG(satp),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_GENERAL | KVM_REG_RISCV_CSR_REG(scounteren),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(frequency),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(time),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(compare),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(state),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_A,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_C,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_I,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_M,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_V01,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_TIME,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_IPI,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_RFENCE,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_SRST,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_HSM,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_PMU,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_EXPERIMENTAL,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_VENDOR,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_MULTI_EN | 0,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_MULTI_DIS | 0,
+};
+
+/*
+ * The skips_set list registers that should skip set test.
+ *  - KVM_REG_RISCV_TIMER_REG(state): set would fail if it was not initialized properly.
+ */
+static __u64 base_skips_set[] = {
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(state),
+};
+
+static __u64 h_regs[] = {
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_H,
+};
+
+static __u64 zicbom_regs[] = {
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(zicbom_block_size),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICBOM,
+};
+
+static __u64 zicboz_regs[] = {
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(zicboz_block_size),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICBOZ,
+};
+
+static __u64 svpbmt_regs[] = {
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SVPBMT,
+};
+
+static __u64 sstc_regs[] = {
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SSTC,
+};
+
+static __u64 svinval_regs[] = {
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SVINVAL,
+};
+
+static __u64 zihintpause_regs[] = {
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIHINTPAUSE,
+};
+
+static __u64 zba_regs[] = {
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBA,
+};
+
+static __u64 zbb_regs[] = {
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBB,
+};
+
+static __u64 zbs_regs[] = {
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBS,
+};
+
+static __u64 zicntr_regs[] = {
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICNTR,
+};
+
+static __u64 zicsr_regs[] = {
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICSR,
+};
+
+static __u64 zifencei_regs[] = {
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIFENCEI,
+};
+
+static __u64 zihpm_regs[] = {
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIHPM,
+};
+
+static __u64 aia_regs[] = {
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(siselect),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(iprio1),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(iprio2),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(sieh),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(siph),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(iprio1h),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(iprio2h),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SSAIA,
+};
+
+static __u64 fp_f_regs[] = {
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[0]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[1]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[2]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[3]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[4]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[5]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[6]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[7]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[8]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[9]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[10]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[11]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[12]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[13]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[14]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[15]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[16]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[17]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[18]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[19]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[20]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[21]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[22]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[23]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[24]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[25]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[26]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[27]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[28]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[29]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[30]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[31]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(fcsr),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_F,
+};
+
+static __u64 fp_d_regs[] = {
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[0]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[1]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[2]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[3]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[4]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[5]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[6]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[7]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[8]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[9]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[10]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[11]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[12]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[13]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[14]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[15]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[16]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[17]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[18]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[19]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[20]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[21]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[22]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[23]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[24]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[25]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[26]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[27]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[28]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[29]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[30]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[31]),
+	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(fcsr),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_D,
+};
+
+#define BASE_SUBLIST \
+	{"base", .regs = base_regs, .regs_n = ARRAY_SIZE(base_regs), \
+	 .skips_set = base_skips_set, .skips_set_n = ARRAY_SIZE(base_skips_set),}
+#define H_REGS_SUBLIST \
+	{"h", .feature = KVM_RISCV_ISA_EXT_H, .regs = h_regs, .regs_n = ARRAY_SIZE(h_regs),}
+#define ZICBOM_REGS_SUBLIST \
+	{"zicbom", .feature = KVM_RISCV_ISA_EXT_ZICBOM, .regs = zicbom_regs, .regs_n = ARRAY_SIZE(zicbom_regs),}
+#define ZICBOZ_REGS_SUBLIST \
+	{"zicboz", .feature = KVM_RISCV_ISA_EXT_ZICBOZ, .regs = zicboz_regs, .regs_n = ARRAY_SIZE(zicboz_regs),}
+#define SVPBMT_REGS_SUBLIST \
+	{"svpbmt", .feature = KVM_RISCV_ISA_EXT_SVPBMT, .regs = svpbmt_regs, .regs_n = ARRAY_SIZE(svpbmt_regs),}
+#define SSTC_REGS_SUBLIST \
+	{"sstc", .feature = KVM_RISCV_ISA_EXT_SSTC, .regs = sstc_regs, .regs_n = ARRAY_SIZE(sstc_regs),}
+#define SVINVAL_REGS_SUBLIST \
+	{"svinval", .feature = KVM_RISCV_ISA_EXT_SVINVAL, .regs = svinval_regs, .regs_n = ARRAY_SIZE(svinval_regs),}
+#define ZIHINTPAUSE_REGS_SUBLIST \
+	{"zihintpause", .feature = KVM_RISCV_ISA_EXT_ZIHINTPAUSE, .regs = zihintpause_regs, .regs_n = ARRAY_SIZE(zihintpause_regs),}
+#define ZBA_REGS_SUBLIST \
+	{"zba", .feature = KVM_RISCV_ISA_EXT_ZBA, .regs = zba_regs, .regs_n = ARRAY_SIZE(zba_regs),}
+#define ZBB_REGS_SUBLIST \
+	{"zbb", .feature = KVM_RISCV_ISA_EXT_ZBB, .regs = zbb_regs, .regs_n = ARRAY_SIZE(zbb_regs),}
+#define ZBS_REGS_SUBLIST \
+	{"zbs", .feature = KVM_RISCV_ISA_EXT_ZBS, .regs = zbs_regs, .regs_n = ARRAY_SIZE(zbs_regs),}
+#define ZICNTR_REGS_SUBLIST \
+	{"zicntr", .feature = KVM_RISCV_ISA_EXT_ZICNTR, .regs = zicntr_regs, .regs_n = ARRAY_SIZE(zicntr_regs),}
+#define ZICSR_REGS_SUBLIST \
+	{"zicsr", .feature = KVM_RISCV_ISA_EXT_ZICSR, .regs = zicsr_regs, .regs_n = ARRAY_SIZE(zicsr_regs),}
+#define ZIFENCEI_REGS_SUBLIST \
+	{"zifencei", .feature = KVM_RISCV_ISA_EXT_ZIFENCEI, .regs = zifencei_regs, .regs_n = ARRAY_SIZE(zifencei_regs),}
+#define ZIHPM_REGS_SUBLIST \
+	{"zihpm", .feature = KVM_RISCV_ISA_EXT_ZIHPM, .regs = zihpm_regs, .regs_n = ARRAY_SIZE(zihpm_regs),}
+#define AIA_REGS_SUBLIST \
+	{"aia", .feature = KVM_RISCV_ISA_EXT_SSAIA, .regs = aia_regs, .regs_n = ARRAY_SIZE(aia_regs),}
+#define FP_F_REGS_SUBLIST \
+	{"fp_f", .feature = KVM_RISCV_ISA_EXT_F, .regs = fp_f_regs, \
+		.regs_n = ARRAY_SIZE(fp_f_regs),}
+#define FP_D_REGS_SUBLIST \
+	{"fp_d", .feature = KVM_RISCV_ISA_EXT_D, .regs = fp_d_regs, \
+		.regs_n = ARRAY_SIZE(fp_d_regs),}
+
+static struct vcpu_reg_list h_config = {
+	.sublists = {
+	BASE_SUBLIST,
+	H_REGS_SUBLIST,
+	{0},
+	},
+};
+
+static struct vcpu_reg_list zicbom_config = {
+	.sublists = {
+	BASE_SUBLIST,
+	ZICBOM_REGS_SUBLIST,
+	{0},
+	},
+};
+
+static struct vcpu_reg_list zicboz_config = {
+	.sublists = {
+	BASE_SUBLIST,
+	ZICBOZ_REGS_SUBLIST,
+	{0},
+	},
+};
+
+static struct vcpu_reg_list svpbmt_config = {
+	.sublists = {
+	BASE_SUBLIST,
+	SVPBMT_REGS_SUBLIST,
+	{0},
+	},
+};
+
+static struct vcpu_reg_list sstc_config = {
+	.sublists = {
+	BASE_SUBLIST,
+	SSTC_REGS_SUBLIST,
+	{0},
+	},
+};
+
+static struct vcpu_reg_list svinval_config = {
+	.sublists = {
+	BASE_SUBLIST,
+	SVINVAL_REGS_SUBLIST,
+	{0},
+	},
+};
+
+static struct vcpu_reg_list zihintpause_config = {
+	.sublists = {
+	BASE_SUBLIST,
+	ZIHINTPAUSE_REGS_SUBLIST,
+	{0},
+	},
+};
+
+static struct vcpu_reg_list zba_config = {
+	.sublists = {
+	BASE_SUBLIST,
+	ZBA_REGS_SUBLIST,
+	{0},
+	},
+};
+
+static struct vcpu_reg_list zbb_config = {
+	.sublists = {
+	BASE_SUBLIST,
+	ZBB_REGS_SUBLIST,
+	{0},
+	},
+};
+
+static struct vcpu_reg_list zbs_config = {
+	.sublists = {
+	BASE_SUBLIST,
+	ZBS_REGS_SUBLIST,
+	{0},
+	},
+};
+
+static struct vcpu_reg_list zicntr_config = {
+	.sublists = {
+	BASE_SUBLIST,
+	ZICNTR_REGS_SUBLIST,
+	{0},
+	},
+};
+
+static struct vcpu_reg_list zicsr_config = {
+	.sublists = {
+	BASE_SUBLIST,
+	ZICSR_REGS_SUBLIST,
+	{0},
+	},
+};
+
+static struct vcpu_reg_list zifencei_config = {
+	.sublists = {
+	BASE_SUBLIST,
+	ZIFENCEI_REGS_SUBLIST,
+	{0},
+	},
+};
+
+static struct vcpu_reg_list zihpm_config = {
+	.sublists = {
+	BASE_SUBLIST,
+	ZIHPM_REGS_SUBLIST,
+	{0},
+	},
+};
+
+static struct vcpu_reg_list aia_config = {
+	.sublists = {
+	BASE_SUBLIST,
+	AIA_REGS_SUBLIST,
+	{0},
+	},
+};
+
+static struct vcpu_reg_list fp_f_config = {
+	.sublists = {
+	BASE_SUBLIST,
+	FP_F_REGS_SUBLIST,
+	{0},
+	},
+};
+
+static struct vcpu_reg_list fp_d_config = {
+	.sublists = {
+	BASE_SUBLIST,
+	FP_D_REGS_SUBLIST,
+	{0},
+	},
+};
+
+struct vcpu_reg_list *vcpu_configs[] = {
+	&h_config,
+	&zicbom_config,
+	&zicboz_config,
+	&svpbmt_config,
+	&sstc_config,
+	&svinval_config,
+	&zihintpause_config,
+	&zba_config,
+	&zbb_config,
+	&zbs_config,
+	&zicntr_config,
+	&zicsr_config,
+	&zifencei_config,
+	&zihpm_config,
+	&aia_config,
+	&fp_f_config,
+	&fp_d_config,
+};
+int vcpu_configs_n = ARRAY_SIZE(vcpu_configs);

From a69c610e13e2b2de8a1ed2683f13e21b3200bd7a Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 1 Aug 2023 12:59:15 +0200
Subject: [PATCH 0387/1189] rtc: stm32: remove incorrect #ifdef check

After a previous commit changed the driver over to
SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(), the suspend/resume
functions must no longer be hidden behind an #ifdef:

In file included from include/linux/clk.h:13,
                 from drivers/rtc/rtc-stm32.c:8:
drivers/rtc/rtc-stm32.c:927:39: error: 'stm32_rtc_suspend' undeclared here (not in a function); did you mean 'stm32_rtc_probe'?
  927 |         SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(stm32_rtc_suspend, stm32_rtc_resume)
      |                                       ^~~~~~~~~~~~~~~~~
include/linux/kernel.h:58:44: note: in definition of macro 'PTR_IF'
   58 | #define PTR_IF(cond, ptr)       ((cond) ? (ptr) : NULL)
      |                                            ^~~
include/linux/pm.h:329:26: note: in expansion of macro 'pm_sleep_ptr'
  329 |         .suspend_noirq = pm_sleep_ptr(suspend_fn), \
      |                          ^~~~~~~~~~~~

Fixes: fb9a7e5360dc8 ("rtc: stm32: change PM callbacks to "_noirq()"")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Valentin Caron <valentin.caron@foss.st.com>
Link: https://lore.kernel.org/r/20230801105932.3738430-1-arnd@kernel.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-stm32.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/rtc/rtc-stm32.c b/drivers/rtc/rtc-stm32.c
index 3ae875b19af8..3ce4b3d08155 100644
--- a/drivers/rtc/rtc-stm32.c
+++ b/drivers/rtc/rtc-stm32.c
@@ -891,7 +891,6 @@ static void stm32_rtc_remove(struct platform_device *pdev)
 	device_init_wakeup(&pdev->dev, false);
 }
 
-#ifdef CONFIG_PM_SLEEP
 static int stm32_rtc_suspend(struct device *dev)
 {
 	struct stm32_rtc *rtc = dev_get_drvdata(dev);
@@ -922,7 +921,6 @@ static int stm32_rtc_resume(struct device *dev)
 
 	return ret;
 }
-#endif
 
 static const struct dev_pm_ops stm32_rtc_pm_ops = {
 	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(stm32_rtc_suspend, stm32_rtc_resume)

From df9c16b5ccc8e4aab5e492b5f110167c75c74b0a Mon Sep 17 00:00:00 2001
From: Chen Jiahao <chenjiahao16@huawei.com>
Date: Wed, 2 Aug 2023 17:36:50 +0800
Subject: [PATCH 0388/1189] rtc: sunplus: Clean up redundant dev_err_probe()

Referring to platform_get_irq()'s definition, the return value has
already been checked if ret < 0, and printed via dev_err_probe().
Calling dev_err_probe() one more time outside platform_get_irq()
is obviously redundant.

Removing dev_err_probe() outside platform_get_irq() to clean up
above problem.

Signed-off-by: Chen Jiahao <chenjiahao16@huawei.com>
Link: https://lore.kernel.org/r/20230802093650.976352-1-chenjiahao16@huawei.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-sunplus.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/rtc/rtc-sunplus.c b/drivers/rtc/rtc-sunplus.c
index f33dc301f301..20c7e97c2fc8 100644
--- a/drivers/rtc/rtc-sunplus.c
+++ b/drivers/rtc/rtc-sunplus.c
@@ -244,7 +244,7 @@ static int sp_rtc_probe(struct platform_device *plat_dev)
 
 	sp_rtc->irq = platform_get_irq(plat_dev, 0);
 	if (sp_rtc->irq < 0)
-		return dev_err_probe(&plat_dev->dev, sp_rtc->irq, "platform_get_irq failed\n");
+		return sp_rtc->irq;
 
 	ret = devm_request_irq(&plat_dev->dev, sp_rtc->irq, sp_rtc_irq_handler,
 			       IRQF_TRIGGER_RISING, "rtc irq", plat_dev);

From cbf871e6d8ce23dd4d458d8b7ab9d4a267e7bc03 Mon Sep 17 00:00:00 2001
From: Billy Tsai <billy_tsai@aspeedtech.com>
Date: Wed, 2 Aug 2023 18:09:09 +0800
Subject: [PATCH 0389/1189] i3c/master: cmd_v1: Fix the exit criteria for the
 daa procedure

The exit criteria for the DAA should check if the data length is equal to
1, instead of checking if the response status is equal to 1.

Signed-off-by: Billy Tsai <billy_tsai@aspeedtech.com>
Link: https://lore.kernel.org/r/20230802100909.2568215-1-billy_tsai@aspeedtech.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/cmd_v1.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c b/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c
index d97c3175e0e2..6a781f89b0e4 100644
--- a/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c
+++ b/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c
@@ -339,7 +339,7 @@ static int hci_cmd_v1_daa(struct i3c_hci *hci)
 			break;
 		}
 		if (RESP_STATUS(xfer[0].response) == RESP_ERR_NACK &&
-		    RESP_STATUS(xfer[0].response) == 1) {
+		    RESP_DATA_LENGTH(xfer->response) == 1) {
 			ret = 0;  /* no more devices to be assigned */
 			break;
 		}

From 4f3688dca15053555ade31a785a9c75837a64fb8 Mon Sep 17 00:00:00 2001
From: Zhu Wang <wangzhu9@huawei.com>
Date: Tue, 8 Aug 2023 19:52:09 +0800
Subject: [PATCH 0390/1189] rtc: remove redundant of_match_ptr()

Signed-off-by: Zhu Wang <wangzhu9@huawei.com>
Link: https://lore.kernel.org/r/20230808115213.154377-2-wangzhu9@huawei.com
Link: https://lore.kernel.org/r/20230808115213.154377-3-wangzhu9@huawei.com
Link: https://lore.kernel.org/r/20230808115213.154377-4-wangzhu9@huawei.com
Link: https://lore.kernel.org/r/20230808115213.154377-5-wangzhu9@huawei.com
Link: https://lore.kernel.org/r/20230808115213.154377-6-wangzhu9@huawei.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-armada38x.c  | 4 +---
 drivers/rtc/rtc-aspeed.c     | 2 +-
 drivers/rtc/rtc-at91rm9200.c | 2 +-
 drivers/rtc/rtc-at91sam9.c   | 2 +-
 drivers/rtc/rtc-nct3018y.c   | 2 +-
 5 files changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/rtc/rtc-armada38x.c b/drivers/rtc/rtc-armada38x.c
index 8abcad38b10c..569c1054d6b0 100644
--- a/drivers/rtc/rtc-armada38x.c
+++ b/drivers/rtc/rtc-armada38x.c
@@ -473,7 +473,6 @@ static const struct armada38x_rtc_data armada8k_data = {
 	.alarm = ALARM2,
 };
 
-#ifdef CONFIG_OF
 static const struct of_device_id armada38x_rtc_of_match_table[] = {
 	{
 		.compatible = "marvell,armada-380-rtc",
@@ -486,7 +485,6 @@ static const struct of_device_id armada38x_rtc_of_match_table[] = {
 	{}
 };
 MODULE_DEVICE_TABLE(of, armada38x_rtc_of_match_table);
-#endif
 
 static __init int armada38x_rtc_probe(struct platform_device *pdev)
 {
@@ -576,7 +574,7 @@ static struct platform_driver armada38x_rtc_driver = {
 	.driver		= {
 		.name	= "armada38x-rtc",
 		.pm	= &armada38x_rtc_pm_ops,
-		.of_match_table = of_match_ptr(armada38x_rtc_of_match_table),
+		.of_match_table = armada38x_rtc_of_match_table,
 	},
 };
 
diff --git a/drivers/rtc/rtc-aspeed.c b/drivers/rtc/rtc-aspeed.c
index a93352ed3aec..880b015eebaf 100644
--- a/drivers/rtc/rtc-aspeed.c
+++ b/drivers/rtc/rtc-aspeed.c
@@ -118,7 +118,7 @@ MODULE_DEVICE_TABLE(of, aspeed_rtc_match);
 static struct platform_driver aspeed_rtc_driver = {
 	.driver = {
 		.name = "aspeed-rtc",
-		.of_match_table = of_match_ptr(aspeed_rtc_match),
+		.of_match_table = aspeed_rtc_match,
 	},
 };
 
diff --git a/drivers/rtc/rtc-at91rm9200.c b/drivers/rtc/rtc-at91rm9200.c
index 245588a7b417..add4f71d7b3b 100644
--- a/drivers/rtc/rtc-at91rm9200.c
+++ b/drivers/rtc/rtc-at91rm9200.c
@@ -641,7 +641,7 @@ static struct platform_driver at91_rtc_driver = {
 	.driver		= {
 		.name	= "at91_rtc",
 		.pm	= &at91_rtc_pm_ops,
-		.of_match_table = of_match_ptr(at91_rtc_dt_ids),
+		.of_match_table = at91_rtc_dt_ids,
 	},
 };
 
diff --git a/drivers/rtc/rtc-at91sam9.c b/drivers/rtc/rtc-at91sam9.c
index 610f27dfc462..f93bee96e362 100644
--- a/drivers/rtc/rtc-at91sam9.c
+++ b/drivers/rtc/rtc-at91sam9.c
@@ -534,7 +534,7 @@ static struct platform_driver at91_rtc_driver = {
 	.driver		= {
 		.name	= "rtc-at91sam9",
 		.pm	= &at91_rtc_pm_ops,
-		.of_match_table = of_match_ptr(at91_rtc_dt_ids),
+		.of_match_table = at91_rtc_dt_ids,
 	},
 };
 
diff --git a/drivers/rtc/rtc-nct3018y.c b/drivers/rtc/rtc-nct3018y.c
index a4e3f924837e..ed4e606be8e5 100644
--- a/drivers/rtc/rtc-nct3018y.c
+++ b/drivers/rtc/rtc-nct3018y.c
@@ -538,7 +538,7 @@ MODULE_DEVICE_TABLE(of, nct3018y_of_match);
 static struct i2c_driver nct3018y_driver = {
 	.driver		= {
 		.name	= "rtc-nct3018y",
-		.of_match_table = of_match_ptr(nct3018y_of_match),
+		.of_match_table = nct3018y_of_match,
 	},
 	.probe		= nct3018y_probe,
 	.id_table	= nct3018y_id,

From 300098637900f7ff99cafed2be7221407b82df83 Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Thu, 3 Aug 2023 16:51:49 +0800
Subject: [PATCH 0391/1189] i3c: master: svc: Do not check for 0 return after
 calling platform_get_irq()

It is not possible for platform_get_irq() to return 0. Use the
return value from platform_get_irq().

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/r/20230803085149.149248-1-ruanjinjie@huawei.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/svc-i3c-master.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c
index 0d63b732ef0c..770b40e28015 100644
--- a/drivers/i3c/master/svc-i3c-master.c
+++ b/drivers/i3c/master/svc-i3c-master.c
@@ -1518,8 +1518,8 @@ static int svc_i3c_master_probe(struct platform_device *pdev)
 		return PTR_ERR(master->sclk);
 
 	master->irq = platform_get_irq(pdev, 0);
-	if (master->irq <= 0)
-		return -ENOENT;
+	if (master->irq < 0)
+		return master->irq;
 
 	master->dev = dev;
 

From 878460e8d0ff84a0edbaff9d06f9d9dbe8353800 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 10 Aug 2023 11:46:20 -0300
Subject: [PATCH 0392/1189] perf build: Remove -Wno-unused-but-set-variable
 from the flex flags when building with clang < 13.0.0

clang < 13.0.0 doesn't grok -Wno-unused-but-set-variable, so just remove
it to avoid:

  error: unknown warning option '-Wno-unused-but-set-variable'; did you mean '-Wno-unused-const-variable'? [-Werror,-Wunknown-warning-option]
  make[4]: *** [/git/perf-6.5.0-rc4/tools/build/Makefile.build:128: /tmp/build/perf/util/pmu-flex.o] Error 1
  make[4]: *** Waiting for unfinished jobs....

Fixes: ddc8e4c966923ad1 ("perf build: Disable fewer bison warnings")
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/ZNUSWr52jUnVaaa%2F@kernel.org/
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/Build | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index d487aec0b458..9699e31ff4c0 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -1,3 +1,4 @@
+include $(srctree)/tools/scripts/Makefile.include
 include $(srctree)/tools/scripts/utilities.mak
 
 perf-y += arm64-frame-pointer-unwind-support.o
@@ -301,16 +302,21 @@ else
   flex_flags := -w
 endif
 
-CFLAGS_parse-events-flex.o  += $(flex_flags)
-CFLAGS_pmu-flex.o           += $(flex_flags)
-CFLAGS_expr-flex.o          += $(flex_flags)
-CFLAGS_bpf-filter-flex.o    += $(flex_flags)
-
 # Some newer clang and gcc version complain about this
 # util/parse-events-bison.c:1317:9: error: variable 'parse_events_nerrs' set but not used [-Werror,-Wunused-but-set-variable]
 #  int yynerrs = 0;
 
 bison_flags := -DYYENABLE_NLS=0 -Wno-unused-but-set-variable
+
+# Old clangs don't grok -Wno-unused-but-set-variable, remove it
+ifeq ($(CC_NO_CLANG), 0)
+  CLANG_VERSION := $(shell $(CLANG) --version | head -1 | sed 's/.*clang version \([[:digit:]]\+.[[:digit:]]\+.[[:digit:]]\+\).*/\1/g')
+  ifeq ($(call version-lt3,$(CLANG_VERSION),13.0.0),1)
+    bison_flags := $(subst -Wno-unused-but-set-variable,,$(bison_flags))
+    flex_flags := $(subst -Wno-unused-but-set-variable,,$(flex_flags))
+  endif
+endif
+
 BISON_GE_382 := $(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\).\([0-9]\+\)/\1\2\3/g') \>\= 382)
 ifeq ($(BISON_GE_382),1)
   bison_flags += -Wno-switch-enum
@@ -323,6 +329,11 @@ ifeq ($(BISON_LT_381),1)
   bison_flags += -DYYNOMEM=YYABORT
 endif
 
+CFLAGS_parse-events-flex.o  += $(flex_flags)
+CFLAGS_pmu-flex.o           += $(flex_flags)
+CFLAGS_expr-flex.o          += $(flex_flags)
+CFLAGS_bpf-filter-flex.o    += $(flex_flags)
+
 CFLAGS_parse-events-bison.o += $(bison_flags)
 CFLAGS_pmu-bison.o          += -DYYLTYPE_IS_TRIVIAL=0 $(bison_flags)
 CFLAGS_expr-bison.o         += -DYYLTYPE_IS_TRIVIAL=0 $(bison_flags)

From e59fea47f83e8a9ac5b772d140a0d67d50ba0ed8 Mon Sep 17 00:00:00 2001
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Date: Fri, 11 Aug 2023 10:45:46 +0530
Subject: [PATCH 0393/1189] perf symbols: Fix DSO kernel load and symbol
 process to correctly map DSO to its long_name, type and adjust_symbols

Test "object code reading" fails sometimes for kernel address as below:

    Reading object code for memory address: 0xc000000000004c3c
    File is: [kernel.kallsyms]
    On file address is: 0x14c3c
    dso__data_read_offset failed
    test child finished with -1
    ---- end ----
    Object code reading: FAILED!

Here dso__data_read_offset() fails for symbol address
0xc000000000004c3c. This is because the DSO long_name here is
"[kernel.kallsyms]" and hence open_dso() fails to open this file. There
is an incorrect DSO to map handling here. The key points here are:

- The DSO long_name is set to "[kernel.kallsyms]". This file is
  not present and hence returns error
- The DSO binary type is set to DSO_BINARY_TYPE__NOT_FOUND
- The DSO adjust_symbols member is set to zero

In the end dso__data_read_offset() returns -1 and the address 0x14c3c
can not be resolved. Hence the test fails. But the address actually maps
to the kernel DSO

    # objdump -z -d --start-address=0xc000000000004c3c --stop-address=0xc000000000004cbc /home/athira/linux/vmlinux

    /home/athira/linux/vmlinux:     file format elf64-powerpcle

    Disassembly of section .head.text:

    c000000000004c3c <exc_virt_0x4c00_system_call+0x3c>:
    c000000000004c3c:	a6 02 9b 7d 	mfsrr1  r12
    c000000000004c40:	78 13 42 7c 	mr      r2,r2
    c000000000004c44:	18 00 4d e9 	ld      r10,24(r13)
    c000000000004c48:	60 c6 4a 61 	ori     r10,r10,50784
    c000000000004c4c:	a6 03 49 7d 	mtctr   r10

Fix dso__process_kernel_symbol() to set the binary_type and
adjust_symbols members. dso->adjust_symbols is used by
map__rip_2objdump() which converts the symbol start address to the
objdump address. Also set dso->long_name in dso__load_vmlinux().

Suggested-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230811051546.70039-1-atrajeev@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/symbol-elf.c |  2 ++
 tools/perf/util/symbol.c     | 15 ++++++++++-----
 2 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 8bd466d1c2bd..95e99c332d7e 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -1440,6 +1440,8 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
 		curr_dso->kernel = dso->kernel;
 		curr_dso->long_name = dso->long_name;
 		curr_dso->long_name_len = dso->long_name_len;
+		curr_dso->binary_type = dso->binary_type;
+		curr_dso->adjust_symbols = dso->adjust_symbols;
 		curr_map = map__new2(start, curr_dso);
 		dso__put(curr_dso);
 		if (curr_map == NULL)
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index f849f9ef68e6..3f36675b7c8f 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -2204,15 +2204,20 @@ int dso__load_vmlinux(struct dso *dso, struct map *map,
 	if (symsrc__init(&ss, dso, symfs_vmlinux, symtab_type))
 		return -1;
 
+	/*
+	 * dso__load_sym() may copy 'dso' which will result in the copies having
+	 * an incorrect long name unless we set it here first.
+	 */
+	dso__set_long_name(dso, vmlinux, vmlinux_allocated);
+	if (dso->kernel == DSO_SPACE__KERNEL_GUEST)
+		dso->binary_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
+	else
+		dso->binary_type = DSO_BINARY_TYPE__VMLINUX;
+
 	err = dso__load_sym(dso, map, &ss, &ss, 0);
 	symsrc__destroy(&ss);
 
 	if (err > 0) {
-		if (dso->kernel == DSO_SPACE__KERNEL_GUEST)
-			dso->binary_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
-		else
-			dso->binary_type = DSO_BINARY_TYPE__VMLINUX;
-		dso__set_long_name(dso, vmlinux, vmlinux_allocated);
 		dso__set_loaded(dso);
 		pr_debug("Using %s for symbols\n", symfs_vmlinux);
 	}

From 33d9c5062113a4bd9c5f7414fdeccea3c58e6809 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 10 Aug 2023 11:09:44 -0700
Subject: [PATCH 0394/1189] perf script python: Add stub for PMU symbol to the
 python binding

Fix missing symbol seen in:

  ```
   19: 'import perf' in python                                         :
  --- start ---
  test child forked, pid 2640936
  python usage test: "echo "import sys ; sys.path.insert(0, 'python'); import perf" | '/usr/bin/python3' "
  Traceback (most recent call last):
    File "<stdin>", line 1, in <module>
  ImportError: tools/perf/python/perf.cpython-311-x86_64-linux-gnu.so: undefined symbol: perf_pmus__supports_extended_type
  test child finished with -1
  ---- end ----
  'import perf' in python: FAILED!
  ```

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20230810180944.2794188-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/python.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 4eed8ec23994..c29f5f0bb552 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -113,6 +113,11 @@ bool evsel__is_aux_event(const struct evsel *evsel __maybe_unused)
 	return false;
 }
 
+bool perf_pmus__supports_extended_type(void)
+{
+	return false;
+}
+
 /*
  * Add this one here not to drag util/metricgroup.c
  */

From 130c3f7e4640a0c5b18c1c8461a1d0e1053119c1 Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Fri, 4 Aug 2023 18:06:17 +0800
Subject: [PATCH 0395/1189] watchdog: menz069_wdt: Remove redundant
 initialization owner in men_z069_driver

The module_mcb_driver() will set "THIS_MODULE" to driver.owner when
register a mcb_driver driver, so it is redundant initialization to set
driver.owner in men_z069_driver statement. Remove it for clean code.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20230804100617.100251-1-lizetao1@huawei.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/menz69_wdt.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/watchdog/menz69_wdt.c b/drivers/watchdog/menz69_wdt.c
index 3c98030b9fcd..c7de30270043 100644
--- a/drivers/watchdog/menz69_wdt.c
+++ b/drivers/watchdog/menz69_wdt.c
@@ -153,7 +153,6 @@ MODULE_DEVICE_TABLE(mcb, men_z069_ids);
 static struct mcb_driver men_z069_driver = {
 	.driver = {
 		.name = "z069-wdt",
-		.owner = THIS_MODULE,
 	},
 	.probe = men_z069_probe,
 	.remove = men_z069_remove,

From e81e57fe89a20c1ee5e0f0b927ce8fe614118458 Mon Sep 17 00:00:00 2001
From: Bharat Bhushan <bbhushan2@marvell.com>
Date: Thu, 3 Aug 2023 08:55:22 +0530
Subject: [PATCH 0396/1189] dt-bindings: watchdog: marvell GTI system watchdog
 driver

Add binding documentation for the Marvell GTI system
watchdog driver.

Signed-off-by: Bharat Bhushan <bbhushan2@marvell.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20230803032523.6242-1-bbhushan2@marvell.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 .../watchdog/marvell,cn10624-wdt.yaml         | 83 +++++++++++++++++++
 1 file changed, 83 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/watchdog/marvell,cn10624-wdt.yaml

diff --git a/Documentation/devicetree/bindings/watchdog/marvell,cn10624-wdt.yaml b/Documentation/devicetree/bindings/watchdog/marvell,cn10624-wdt.yaml
new file mode 100644
index 000000000000..1b583f232e53
--- /dev/null
+++ b/Documentation/devicetree/bindings/watchdog/marvell,cn10624-wdt.yaml
@@ -0,0 +1,83 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/watchdog/marvell,cn10624-wdt.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Marvell Global Timer (GTI) system watchdog
+
+maintainers:
+  - Bharat Bhushan <bbhushan2@marvell.com>
+
+allOf:
+  - $ref: watchdog.yaml#
+
+properties:
+  compatible:
+    oneOf:
+      - enum:
+          - marvell,cn9670-wdt
+          - marvell,cn10624-wdt
+
+      - items:
+          - enum:
+              - marvell,cn9880-wdt
+              - marvell,cnf9535-wdt
+          - const: marvell,cn9670-wdt
+
+      - items:
+          - enum:
+              - marvell,cn10308-wdt
+              - marvell,cnf10518-wdt
+          - const: marvell,cn10624-wdt
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  clock-names:
+    items:
+      - const: refclk
+
+  marvell,wdt-timer-index:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    minimum: 0
+    maximum: 63
+    description:
+      An SoC have many timers (up to 64), firmware can reserve one or more timer
+      for some other use case and configures one of the global timer as watchdog
+      timer. Firmware will update this field with the timer number configured
+      as watchdog timer.
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    soc {
+        #address-cells = <2>;
+        #size-cells = <2>;
+
+        watchdog@802000040000 {
+            compatible = "marvell,cn9670-wdt";
+            reg = <0x00008020 0x00040000 0x00000000 0x00020000>;
+            interrupts = <GIC_SPI 38 IRQ_TYPE_EDGE_RISING>;
+            clocks = <&sclk>;
+            clock-names = "refclk";
+            marvell,wdt-timer-index = <63>;
+        };
+    };
+
+...

From ef9e7fe2c890f7609b5a667eba282f900434e58d Mon Sep 17 00:00:00 2001
From: Bharat Bhushan <bbhushan2@marvell.com>
Date: Thu, 3 Aug 2023 08:55:23 +0530
Subject: [PATCH 0397/1189] Watchdog: Add marvell GTI watchdog driver

This patch add support for Marvell GTI watchdog.  Global timer
unit (GTI) support hardware watchdog timer. Software programs
watchdog timer to generate interrupt on first timeout, second
timeout is configured to be ignored and system reboots on
third timeout.

Signed-off-by: Bharat Bhushan <bbhushan2@marvell.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20230803032523.6242-2-bbhushan2@marvell.com
[groeck: MODULE_LICENSE GPL v2 -> GPL since that is sufficient]
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/Kconfig           |  13 ++
 drivers/watchdog/Makefile          |   1 +
 drivers/watchdog/marvell_gti_wdt.c | 340 +++++++++++++++++++++++++++++
 3 files changed, 354 insertions(+)
 create mode 100644 drivers/watchdog/marvell_gti_wdt.c

diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index ee97d89dfc11..a23f7a0168e0 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -1797,6 +1797,19 @@ config OCTEON_WDT
 	  from the first interrupt, it is then only poked when the
 	  device is written.
 
+config MARVELL_GTI_WDT
+	tristate "Marvell GTI Watchdog driver"
+	depends on ARCH_THUNDER || (COMPILE_TEST && 64BIT)
+	default y
+	select WATCHDOG_CORE
+	help
+	  Marvell GTI hardware supports watchdog timer. First timeout
+	  works as watchdog pretimeout and installed interrupt handler
+	  will be called on first timeout. Hardware can generate interrupt
+	  to SCP on second timeout but it is not enabled, so second
+	  timeout is ignored. If device poke does not happen then system
+	  will reboot on third timeout.
+
 config BCM2835_WDT
 	tristate "Broadcom BCM2835 hardware watchdog"
 	depends on ARCH_BCM2835 || (OF && COMPILE_TEST)
diff --git a/drivers/watchdog/Makefile b/drivers/watchdog/Makefile
index 3633f5b98236..7eab9de311cb 100644
--- a/drivers/watchdog/Makefile
+++ b/drivers/watchdog/Makefile
@@ -98,6 +98,7 @@ obj-$(CONFIG_VISCONTI_WATCHDOG) += visconti_wdt.o
 obj-$(CONFIG_MSC313E_WATCHDOG) += msc313e_wdt.o
 obj-$(CONFIG_APPLE_WATCHDOG) += apple_wdt.o
 obj-$(CONFIG_SUNPLUS_WATCHDOG) += sunplus_wdt.o
+obj-$(CONFIG_MARVELL_GTI_WDT) += marvell_gti_wdt.o
 
 # X86 (i386 + ia64 + x86_64) Architecture
 obj-$(CONFIG_ACQUIRE_WDT) += acquirewdt.o
diff --git a/drivers/watchdog/marvell_gti_wdt.c b/drivers/watchdog/marvell_gti_wdt.c
new file mode 100644
index 000000000000..d7eb8286e11e
--- /dev/null
+++ b/drivers/watchdog/marvell_gti_wdt.c
@@ -0,0 +1,340 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Marvell GTI Watchdog driver
+ *
+ * Copyright (C) 2023 Marvell.
+ */
+
+#include <linux/clk.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/watchdog.h>
+
+/*
+ * Hardware supports following mode of operation:
+ * 1) Interrupt Only:
+ *    This will generate the interrupt to arm core whenever timeout happens.
+ *
+ * 2) Interrupt + del3t (Interrupt to firmware (SCP processor)).
+ *    This will generate interrupt to arm core on 1st timeout happens
+ *    This will generate interrupt to SCP processor on 2nd timeout happens
+ *
+ * 3) Interrupt + Interrupt to SCP processor (called delt3t) + reboot.
+ *    This will generate interrupt to arm core on 1st timeout happens
+ *    Will generate interrupt to SCP processor on 2nd timeout happens,
+ *    if interrupt is configured.
+ *    Reboot on 3rd timeout.
+ *
+ * Driver will use hardware in mode-3 above so that system can reboot in case
+ * a hardware hang. Also h/w is configured not to generate SCP interrupt, so
+ * effectively 2nd timeout is ignored within hardware.
+ *
+ * First timeout is effectively watchdog pretimeout.
+ */
+
+/* GTI CWD Watchdog (GTI_CWD_WDOG) Register */
+#define GTI_CWD_WDOG(reg_offset)	(0x8 * (reg_offset))
+#define GTI_CWD_WDOG_MODE_INT_DEL3T_RST	0x3
+#define GTI_CWD_WDOG_MODE_MASK		GENMASK_ULL(1, 0)
+#define GTI_CWD_WDOG_LEN_SHIFT		4
+#define GTI_CWD_WDOG_LEN_MASK		GENMASK_ULL(19, 4)
+#define GTI_CWD_WDOG_CNT_SHIFT		20
+#define GTI_CWD_WDOG_CNT_MASK		GENMASK_ULL(43, 20)
+
+/* GTI CWD Watchdog Interrupt (GTI_CWD_INT) Register */
+#define GTI_CWD_INT			0x200
+#define GTI_CWD_INT_PENDING_STATUS(bit)	BIT_ULL(bit)
+
+/* GTI CWD Watchdog Interrupt Enable Clear (GTI_CWD_INT_ENA_CLR) Register */
+#define GTI_CWD_INT_ENA_CLR		0x210
+#define GTI_CWD_INT_ENA_CLR_VAL(bit)	BIT_ULL(bit)
+
+/* GTI CWD Watchdog Interrupt Enable Set (GTI_CWD_INT_ENA_SET) Register */
+#define GTI_CWD_INT_ENA_SET		0x218
+#define GTI_CWD_INT_ENA_SET_VAL(bit)	BIT_ULL(bit)
+
+/* GTI CWD Watchdog Poke (GTI_CWD_POKE) Registers */
+#define GTI_CWD_POKE(reg_offset)	(0x10000 + 0x8 * (reg_offset))
+#define GTI_CWD_POKE_VAL		1
+
+struct gti_match_data {
+	u32 gti_num_timers;
+};
+
+static const struct gti_match_data match_data_octeontx2 = {
+	.gti_num_timers = 54,
+};
+
+static const struct gti_match_data match_data_cn10k = {
+	.gti_num_timers = 64,
+};
+
+struct gti_wdt_priv {
+	struct watchdog_device wdev;
+	void __iomem *base;
+	u32 clock_freq;
+	struct clk *sclk;
+	/* wdt_timer_idx used for timer to be used for system watchdog */
+	u32 wdt_timer_idx;
+	const struct gti_match_data *data;
+};
+
+static irqreturn_t gti_wdt_interrupt(int irq, void *data)
+{
+	struct watchdog_device *wdev = data;
+	struct gti_wdt_priv *priv = watchdog_get_drvdata(wdev);
+
+	/* Clear Interrupt Pending Status */
+	writeq(GTI_CWD_INT_PENDING_STATUS(priv->wdt_timer_idx),
+	       priv->base + GTI_CWD_INT);
+
+	watchdog_notify_pretimeout(wdev);
+
+	return IRQ_HANDLED;
+}
+
+static int gti_wdt_ping(struct watchdog_device *wdev)
+{
+	struct gti_wdt_priv *priv = watchdog_get_drvdata(wdev);
+
+	writeq(GTI_CWD_POKE_VAL,
+	       priv->base + GTI_CWD_POKE(priv->wdt_timer_idx));
+
+	return 0;
+}
+
+static int gti_wdt_start(struct watchdog_device *wdev)
+{
+	struct gti_wdt_priv *priv = watchdog_get_drvdata(wdev);
+	u64 regval;
+
+	if (!wdev->pretimeout)
+		return -EINVAL;
+
+	set_bit(WDOG_HW_RUNNING, &wdev->status);
+
+	/* Clear any pending interrupt */
+	writeq(GTI_CWD_INT_PENDING_STATUS(priv->wdt_timer_idx),
+	       priv->base + GTI_CWD_INT);
+
+	/* Enable Interrupt */
+	writeq(GTI_CWD_INT_ENA_SET_VAL(priv->wdt_timer_idx),
+	       priv->base + GTI_CWD_INT_ENA_SET);
+
+	/* Set (Interrupt + SCP interrupt (DEL3T) + core domain reset) Mode */
+	regval = readq(priv->base + GTI_CWD_WDOG(priv->wdt_timer_idx));
+	regval |= GTI_CWD_WDOG_MODE_INT_DEL3T_RST;
+	writeq(regval, priv->base + GTI_CWD_WDOG(priv->wdt_timer_idx));
+
+	return 0;
+}
+
+static int gti_wdt_stop(struct watchdog_device *wdev)
+{
+	struct gti_wdt_priv *priv = watchdog_get_drvdata(wdev);
+	u64 regval;
+
+	/* Disable Interrupt */
+	writeq(GTI_CWD_INT_ENA_CLR_VAL(priv->wdt_timer_idx),
+	       priv->base + GTI_CWD_INT_ENA_CLR);
+
+	/* Set GTI_CWD_WDOG.Mode = 0 to stop the timer */
+	regval = readq(priv->base + GTI_CWD_WDOG(priv->wdt_timer_idx));
+	regval &= ~GTI_CWD_WDOG_MODE_MASK;
+	writeq(regval, priv->base + GTI_CWD_WDOG(priv->wdt_timer_idx));
+
+	return 0;
+}
+
+static int gti_wdt_settimeout(struct watchdog_device *wdev,
+					unsigned int timeout)
+{
+	struct gti_wdt_priv *priv = watchdog_get_drvdata(wdev);
+	u64 timeout_wdog, regval;
+
+	/* Update new timeout */
+	wdev->timeout = timeout;
+
+	/* Pretimeout is 1/3 of timeout */
+	wdev->pretimeout = timeout / 3;
+
+	/* Get clock cycles from pretimeout */
+	timeout_wdog = (u64)priv->clock_freq * wdev->pretimeout;
+
+	/* Watchdog counts in 1024 cycle steps */
+	timeout_wdog = timeout_wdog >> 10;
+
+	/* GTI_CWD_WDOG.CNT: reload counter is 16-bit */
+	timeout_wdog = (timeout_wdog + 0xff) >> 8;
+	if (timeout_wdog >= 0x10000)
+		timeout_wdog = 0xffff;
+
+	/*
+	 * GTI_CWD_WDOG.LEN is 24bit, lower 8-bits should be zero and
+	 * upper 16-bits are same as GTI_CWD_WDOG.CNT
+	 */
+	regval = readq(priv->base + GTI_CWD_WDOG(priv->wdt_timer_idx));
+	regval &= GTI_CWD_WDOG_MODE_MASK;
+	regval |= (timeout_wdog << (GTI_CWD_WDOG_CNT_SHIFT + 8)) |
+		   (timeout_wdog << GTI_CWD_WDOG_LEN_SHIFT);
+	writeq(regval, priv->base + GTI_CWD_WDOG(priv->wdt_timer_idx));
+
+	return 0;
+}
+
+static int gti_wdt_set_pretimeout(struct watchdog_device *wdev,
+					unsigned int timeout)
+{
+	struct gti_wdt_priv *priv = watchdog_get_drvdata(wdev);
+	struct watchdog_device *wdog_dev = &priv->wdev;
+
+	/* pretimeout should 1/3 of max_timeout */
+	if (timeout * 3 <= wdog_dev->max_timeout)
+		return gti_wdt_settimeout(wdev, timeout * 3);
+
+	return -EINVAL;
+}
+
+static void gti_clk_disable_unprepare(void *data)
+{
+	clk_disable_unprepare(data);
+}
+
+static int gti_wdt_get_cntfrq(struct platform_device *pdev,
+			      struct gti_wdt_priv *priv)
+{
+	int err;
+
+	priv->sclk = devm_clk_get_enabled(&pdev->dev, NULL);
+	if (IS_ERR(priv->sclk))
+		return PTR_ERR(priv->sclk);
+
+	err = devm_add_action_or_reset(&pdev->dev,
+				       gti_clk_disable_unprepare, priv->sclk);
+	if (err)
+		return err;
+
+	priv->clock_freq = clk_get_rate(priv->sclk);
+	if (!priv->clock_freq)
+		return -EINVAL;
+
+	return 0;
+}
+
+static const struct watchdog_info gti_wdt_ident = {
+	.identity = "Marvell GTI watchdog",
+	.options = WDIOF_SETTIMEOUT | WDIOF_PRETIMEOUT | WDIOF_KEEPALIVEPING |
+		   WDIOF_MAGICCLOSE | WDIOF_CARDRESET,
+};
+
+static const struct watchdog_ops gti_wdt_ops = {
+	.owner = THIS_MODULE,
+	.start = gti_wdt_start,
+	.stop = gti_wdt_stop,
+	.ping = gti_wdt_ping,
+	.set_timeout = gti_wdt_settimeout,
+	.set_pretimeout = gti_wdt_set_pretimeout,
+};
+
+static int gti_wdt_probe(struct platform_device *pdev)
+{
+	struct gti_wdt_priv *priv;
+	struct device *dev = &pdev->dev;
+	struct watchdog_device *wdog_dev;
+	u64 max_pretimeout;
+	u32 wdt_idx;
+	int irq;
+	int err;
+
+	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(priv->base))
+		return dev_err_probe(&pdev->dev, PTR_ERR(priv->base),
+			      "reg property not valid/found\n");
+
+	err = gti_wdt_get_cntfrq(pdev, priv);
+	if (err)
+		return dev_err_probe(&pdev->dev, err,
+				     "GTI clock frequency not valid/found");
+
+	priv->data = of_device_get_match_data(dev);
+
+	/* default use last timer for watchdog */
+	priv->wdt_timer_idx = priv->data->gti_num_timers - 1;
+
+	err = of_property_read_u32(dev->of_node, "marvell,wdt-timer-index",
+				   &wdt_idx);
+	if (!err) {
+		if (wdt_idx >= priv->data->gti_num_timers)
+			return dev_err_probe(&pdev->dev, err,
+				"GTI wdog timer index not valid");
+
+		priv->wdt_timer_idx = wdt_idx;
+	}
+
+	wdog_dev = &priv->wdev;
+	wdog_dev->info = &gti_wdt_ident,
+	wdog_dev->ops = &gti_wdt_ops,
+	wdog_dev->parent = dev;
+	/*
+	 * Watchdog counter is 24 bit where lower 8 bits are zeros
+	 * This counter decrements every 1024 clock cycles.
+	 */
+	max_pretimeout = (GTI_CWD_WDOG_CNT_MASK >> GTI_CWD_WDOG_CNT_SHIFT);
+	max_pretimeout &= ~0xFFUL;
+	max_pretimeout = (max_pretimeout * 1024) / priv->clock_freq;
+	wdog_dev->pretimeout = max_pretimeout;
+
+	/* Maximum timeout is 3 times the pretimeout */
+	wdog_dev->max_timeout = max_pretimeout * 3;
+	/* Minimum first timeout (pretimeout) is 1, so min_timeout as 3 */
+	wdog_dev->min_timeout = 3;
+	wdog_dev->timeout = wdog_dev->pretimeout;
+
+	watchdog_set_drvdata(wdog_dev, priv);
+	platform_set_drvdata(pdev, priv);
+	gti_wdt_settimeout(wdog_dev, wdog_dev->timeout);
+	watchdog_stop_on_reboot(wdog_dev);
+	watchdog_stop_on_unregister(wdog_dev);
+
+	err = devm_watchdog_register_device(dev, wdog_dev);
+	if (err)
+		return err;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return dev_err_probe(&pdev->dev, irq, "IRQ resource not found\n");
+
+	err = devm_request_irq(dev, irq, gti_wdt_interrupt, 0,
+			       pdev->name, &priv->wdev);
+	if (err)
+		return dev_err_probe(dev, err, "Failed to register interrupt handler\n");
+
+	dev_info(dev, "Watchdog enabled (timeout=%d sec)\n", wdog_dev->timeout);
+	return 0;
+}
+
+static const struct of_device_id gti_wdt_of_match[] = {
+	{ .compatible = "marvell,cn9670-wdt", .data = &match_data_octeontx2},
+	{ .compatible = "marvell,cn10624-wdt", .data = &match_data_cn10k},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, gti_wdt_of_match);
+
+static struct platform_driver gti_wdt_driver = {
+	.driver = {
+		.name = "gti-wdt",
+		.of_match_table = gti_wdt_of_match,
+	},
+	.probe = gti_wdt_probe,
+};
+module_platform_driver(gti_wdt_driver);
+
+MODULE_AUTHOR("Bharat Bhushan <bbhushan2@marvell.com>");
+MODULE_DESCRIPTION("Marvell GTI watchdog driver");
+MODULE_LICENSE("GPL");

From cc85f87a77b8d6124c85c9d71d6956c0248fdf19 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Wed, 26 Jul 2023 17:33:00 -0600
Subject: [PATCH 0398/1189] watchdog: Explicitly include correct DT includes

The DT of_device.h and of_platform.h date back to the separate
of_platform_bus_type before it was merged into the regular platform bus.
As part of that merge prepping Arm DT support 13 years ago, they
"temporarily" include each other. They also include platform_device.h
and of.h. As a result, there's a pretty much random mix of those include
files used throughout the tree. In order to detangle these headers and
replace the implicit includes with struct declarations, users need to
explicitly include the correct includes.

Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Alim Akhtar <alim.akhtar@samsung.com>
Signed-off-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230726233302.3812749-1-robh@kernel.org
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/armada_37xx_wdt.c | 1 -
 drivers/watchdog/at91rm9200_wdt.c  | 3 +--
 drivers/watchdog/cpwd.c            | 2 +-
 drivers/watchdog/ftwdt010_wdt.c    | 6 ++----
 drivers/watchdog/gef_wdt.c         | 2 +-
 drivers/watchdog/imx2_wdt.c        | 3 +--
 drivers/watchdog/imx7ulp_wdt.c     | 1 -
 drivers/watchdog/lantiq_wdt.c      | 3 ++-
 drivers/watchdog/meson_wdt.c       | 4 ++--
 drivers/watchdog/mpc8xxx_wdt.c     | 4 ++--
 drivers/watchdog/mtk_wdt.c         | 1 -
 drivers/watchdog/of_xilinx_wdt.c   | 3 +--
 drivers/watchdog/pic32-dmt.c       | 1 -
 drivers/watchdog/pic32-wdt.c       | 1 -
 drivers/watchdog/pika_wdt.c        | 2 +-
 drivers/watchdog/qcom-wdt.c        | 1 -
 drivers/watchdog/rave-sp-wdt.c     | 2 +-
 drivers/watchdog/riowd.c           | 2 +-
 drivers/watchdog/rza_wdt.c         | 4 ++--
 drivers/watchdog/rzg2l_wdt.c       | 2 +-
 drivers/watchdog/s3c2410_wdt.c     | 1 -
 drivers/watchdog/sama5d4_wdt.c     | 1 -
 drivers/watchdog/sbsa_gwdt.c       | 3 +--
 drivers/watchdog/starfive-wdt.c    | 3 ++-
 drivers/watchdog/stm32_iwdg.c      | 1 -
 drivers/watchdog/sunxi_wdt.c       | 1 -
 drivers/watchdog/xilinx_wwdt.c     | 4 ++--
 27 files changed, 24 insertions(+), 38 deletions(-)

diff --git a/drivers/watchdog/armada_37xx_wdt.c b/drivers/watchdog/armada_37xx_wdt.c
index e58652939f8a..8133a5d05647 100644
--- a/drivers/watchdog/armada_37xx_wdt.c
+++ b/drivers/watchdog/armada_37xx_wdt.c
@@ -14,7 +14,6 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
 #include <linux/types.h>
diff --git a/drivers/watchdog/at91rm9200_wdt.c b/drivers/watchdog/at91rm9200_wdt.c
index d20ec27ba354..558015f08c7a 100644
--- a/drivers/watchdog/at91rm9200_wdt.c
+++ b/drivers/watchdog/at91rm9200_wdt.c
@@ -18,6 +18,7 @@
 #include <linux/mfd/syscon.h>
 #include <linux/mfd/syscon/atmel-st.h>
 #include <linux/miscdevice.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/platform_device.h>
@@ -26,8 +27,6 @@
 #include <linux/types.h>
 #include <linux/watchdog.h>
 #include <linux/uaccess.h>
-#include <linux/of.h>
-#include <linux/of_device.h>
 
 #define WDT_DEFAULT_TIME	5	/* seconds */
 #define WDT_MAX_TIME		256	/* seconds */
diff --git a/drivers/watchdog/cpwd.c b/drivers/watchdog/cpwd.c
index 47250f9b68c7..901b94d456db 100644
--- a/drivers/watchdog/cpwd.c
+++ b/drivers/watchdog/cpwd.c
@@ -31,7 +31,7 @@
 #include <linux/mutex.h>
 #include <linux/io.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
+#include <linux/platform_device.h>
 #include <linux/uaccess.h>
 
 #include <asm/irq.h>
diff --git a/drivers/watchdog/ftwdt010_wdt.c b/drivers/watchdog/ftwdt010_wdt.c
index 442c5bf63ff4..28f5af752c10 100644
--- a/drivers/watchdog/ftwdt010_wdt.c
+++ b/drivers/watchdog/ftwdt010_wdt.c
@@ -14,7 +14,7 @@
 #include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/mod_devicetable.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/watchdog.h>
@@ -221,20 +221,18 @@ static const struct dev_pm_ops ftwdt010_wdt_dev_pm_ops = {
 				ftwdt010_wdt_resume)
 };
 
-#ifdef CONFIG_OF
 static const struct of_device_id ftwdt010_wdt_match[] = {
 	{ .compatible = "faraday,ftwdt010" },
 	{ .compatible = "cortina,gemini-watchdog" },
 	{},
 };
 MODULE_DEVICE_TABLE(of, ftwdt010_wdt_match);
-#endif
 
 static struct platform_driver ftwdt010_wdt_driver = {
 	.probe		= ftwdt010_wdt_probe,
 	.driver		= {
 		.name	= "ftwdt010-wdt",
-		.of_match_table = of_match_ptr(ftwdt010_wdt_match),
+		.of_match_table = ftwdt010_wdt_match,
 		.pm = &ftwdt010_wdt_dev_pm_ops,
 	},
 };
diff --git a/drivers/watchdog/gef_wdt.c b/drivers/watchdog/gef_wdt.c
index 97afc907f659..6a1db1c783fa 100644
--- a/drivers/watchdog/gef_wdt.c
+++ b/drivers/watchdog/gef_wdt.c
@@ -31,7 +31,7 @@
 #include <linux/fs.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
-#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/io.h>
 #include <linux/uaccess.h>
 
diff --git a/drivers/watchdog/imx2_wdt.c b/drivers/watchdog/imx2_wdt.c
index 6fcc3596103c..1a27665a2f53 100644
--- a/drivers/watchdog/imx2_wdt.c
+++ b/drivers/watchdog/imx2_wdt.c
@@ -26,8 +26,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
-#include <linux/of_address.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
 #include <linux/watchdog.h>
diff --git a/drivers/watchdog/imx7ulp_wdt.c b/drivers/watchdog/imx7ulp_wdt.c
index 7ca486794ba7..c703586c6e5f 100644
--- a/drivers/watchdog/imx7ulp_wdt.c
+++ b/drivers/watchdog/imx7ulp_wdt.c
@@ -9,7 +9,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/reboot.h>
 #include <linux/watchdog.h>
diff --git a/drivers/watchdog/lantiq_wdt.c b/drivers/watchdog/lantiq_wdt.c
index 6fab504af88b..a273b97ebcb4 100644
--- a/drivers/watchdog/lantiq_wdt.c
+++ b/drivers/watchdog/lantiq_wdt.c
@@ -9,7 +9,8 @@
 #include <linux/module.h>
 #include <linux/bitops.h>
 #include <linux/watchdog.h>
-#include <linux/of_platform.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
 #include <linux/uaccess.h>
 #include <linux/clk.h>
 #include <linux/io.h>
diff --git a/drivers/watchdog/meson_wdt.c b/drivers/watchdog/meson_wdt.c
index 539feaa1f904..497496f64f55 100644
--- a/drivers/watchdog/meson_wdt.c
+++ b/drivers/watchdog/meson_wdt.c
@@ -11,11 +11,11 @@
 #include <linux/init.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
-#include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/types.h>
 #include <linux/watchdog.h>
 
diff --git a/drivers/watchdog/mpc8xxx_wdt.c b/drivers/watchdog/mpc8xxx_wdt.c
index 1c569be72ea2..867f9f311379 100644
--- a/drivers/watchdog/mpc8xxx_wdt.c
+++ b/drivers/watchdog/mpc8xxx_wdt.c
@@ -16,8 +16,8 @@
 #include <linux/fs.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
-#include <linux/of_address.h>
-#include <linux/of_platform.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
 #include <linux/module.h>
 #include <linux/watchdog.h>
 #include <linux/io.h>
diff --git a/drivers/watchdog/mtk_wdt.c b/drivers/watchdog/mtk_wdt.c
index a9c437598e7e..b2330b16b497 100644
--- a/drivers/watchdog/mtk_wdt.c
+++ b/drivers/watchdog/mtk_wdt.c
@@ -25,7 +25,6 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/reset-controller.h>
 #include <linux/types.h>
diff --git a/drivers/watchdog/of_xilinx_wdt.c b/drivers/watchdog/of_xilinx_wdt.c
index 2a079ca04aa3..05657dc1d36a 100644
--- a/drivers/watchdog/of_xilinx_wdt.c
+++ b/drivers/watchdog/of_xilinx_wdt.c
@@ -10,14 +10,13 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/module.h>
+#include <linux/platform_device.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/ioport.h>
 #include <linux/watchdog.h>
 #include <linux/io.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
-#include <linux/of_address.h>
 
 /* Register offsets for the Wdt device */
 #define XWT_TWCSR0_OFFSET   0x0 /* Control/Status Register0 */
diff --git a/drivers/watchdog/pic32-dmt.c b/drivers/watchdog/pic32-dmt.c
index bc4ccddc75a3..ab0682492c85 100644
--- a/drivers/watchdog/pic32-dmt.c
+++ b/drivers/watchdog/pic32-dmt.c
@@ -12,7 +12,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/pm.h>
 #include <linux/watchdog.h>
diff --git a/drivers/watchdog/pic32-wdt.c b/drivers/watchdog/pic32-wdt.c
index 6d1a00222991..1d282de312ef 100644
--- a/drivers/watchdog/pic32-wdt.c
+++ b/drivers/watchdog/pic32-wdt.c
@@ -12,7 +12,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/pm.h>
 #include <linux/watchdog.h>
diff --git a/drivers/watchdog/pika_wdt.c b/drivers/watchdog/pika_wdt.c
index a98abd0d3146..782b8c23d99c 100644
--- a/drivers/watchdog/pika_wdt.c
+++ b/drivers/watchdog/pika_wdt.c
@@ -23,8 +23,8 @@
 #include <linux/bitops.h>
 #include <linux/uaccess.h>
 #include <linux/io.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
-#include <linux/of_platform.h>
 
 #define DRV_NAME "PIKA-WDT"
 
diff --git a/drivers/watchdog/qcom-wdt.c b/drivers/watchdog/qcom-wdt.c
index d776474dcdf3..9e790f0c2096 100644
--- a/drivers/watchdog/qcom-wdt.c
+++ b/drivers/watchdog/qcom-wdt.c
@@ -11,7 +11,6 @@
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/watchdog.h>
-#include <linux/of_device.h>
 
 enum wdt_reg {
 	WDT_RST,
diff --git a/drivers/watchdog/rave-sp-wdt.c b/drivers/watchdog/rave-sp-wdt.c
index 2c95615b6354..5d1c2176d445 100644
--- a/drivers/watchdog/rave-sp-wdt.c
+++ b/drivers/watchdog/rave-sp-wdt.c
@@ -13,7 +13,7 @@
 #include <linux/mfd/rave-sp.h>
 #include <linux/module.h>
 #include <linux/nvmem-consumer.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/reboot.h>
 #include <linux/slab.h>
diff --git a/drivers/watchdog/riowd.c b/drivers/watchdog/riowd.c
index c04b383e1712..b293792a292a 100644
--- a/drivers/watchdog/riowd.c
+++ b/drivers/watchdog/riowd.c
@@ -14,7 +14,7 @@
 #include <linux/miscdevice.h>
 #include <linux/watchdog.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
+#include <linux/platform_device.h>
 #include <linux/io.h>
 #include <linux/uaccess.h>
 #include <linux/slab.h>
diff --git a/drivers/watchdog/rza_wdt.c b/drivers/watchdog/rza_wdt.c
index fe6c2ed35e04..cb4901b3f777 100644
--- a/drivers/watchdog/rza_wdt.c
+++ b/drivers/watchdog/rza_wdt.c
@@ -9,9 +9,9 @@
 #include <linux/bitops.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
+#include <linux/io.h>
 #include <linux/module.h>
-#include <linux/of_address.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/watchdog.h>
 
diff --git a/drivers/watchdog/rzg2l_wdt.c b/drivers/watchdog/rzg2l_wdt.c
index d404953d0e0f..1741f98ca67c 100644
--- a/drivers/watchdog/rzg2l_wdt.c
+++ b/drivers/watchdog/rzg2l_wdt.c
@@ -11,7 +11,7 @@
 #include <linux/iopoll.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/reset.h>
diff --git a/drivers/watchdog/s3c2410_wdt.c b/drivers/watchdog/s3c2410_wdt.c
index 95416a9bdd4b..2bcc8faa7fa5 100644
--- a/drivers/watchdog/s3c2410_wdt.c
+++ b/drivers/watchdog/s3c2410_wdt.c
@@ -23,7 +23,6 @@
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/mfd/syscon.h>
 #include <linux/regmap.h>
 #include <linux/delay.h>
diff --git a/drivers/watchdog/sama5d4_wdt.c b/drivers/watchdog/sama5d4_wdt.c
index aeee934ca51b..71e8b5fbf51f 100644
--- a/drivers/watchdog/sama5d4_wdt.c
+++ b/drivers/watchdog/sama5d4_wdt.c
@@ -11,7 +11,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/of_irq.h>
 #include <linux/platform_device.h>
 #include <linux/reboot.h>
diff --git a/drivers/watchdog/sbsa_gwdt.c b/drivers/watchdog/sbsa_gwdt.c
index fd3cfdda4949..421ebcda62e6 100644
--- a/drivers/watchdog/sbsa_gwdt.c
+++ b/drivers/watchdog/sbsa_gwdt.c
@@ -43,10 +43,9 @@
 #include <linux/io.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/interrupt.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
-#include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/uaccess.h>
 #include <linux/watchdog.h>
diff --git a/drivers/watchdog/starfive-wdt.c b/drivers/watchdog/starfive-wdt.c
index 8058fca4d05d..9e6db8e0164f 100644
--- a/drivers/watchdog/starfive-wdt.c
+++ b/drivers/watchdog/starfive-wdt.c
@@ -8,7 +8,8 @@
 #include <linux/clk.h>
 #include <linux/iopoll.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/reset.h>
 #include <linux/watchdog.h>
diff --git a/drivers/watchdog/stm32_iwdg.c b/drivers/watchdog/stm32_iwdg.c
index 570a71509d2a..fa5e70c4b93a 100644
--- a/drivers/watchdog/stm32_iwdg.c
+++ b/drivers/watchdog/stm32_iwdg.c
@@ -17,7 +17,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/watchdog.h>
 
diff --git a/drivers/watchdog/sunxi_wdt.c b/drivers/watchdog/sunxi_wdt.c
index 6cf82922d3fb..b85354a99582 100644
--- a/drivers/watchdog/sunxi_wdt.c
+++ b/drivers/watchdog/sunxi_wdt.c
@@ -18,7 +18,6 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/types.h>
 #include <linux/watchdog.h>
diff --git a/drivers/watchdog/xilinx_wwdt.c b/drivers/watchdog/xilinx_wwdt.c
index 2585038d5575..1d998db41533 100644
--- a/drivers/watchdog/xilinx_wwdt.c
+++ b/drivers/watchdog/xilinx_wwdt.c
@@ -9,9 +9,9 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/ioport.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
-#include <linux/of_address.h>
+#include <linux/platform_device.h>
 #include <linux/watchdog.h>
 
 /* Max timeout is calculated at 100MHz source clock */

From 6eb28a38f6478a650c7e76b2d6910669615d8a62 Mon Sep 17 00:00:00 2001
From: Florent CARLI <fcarli@gmail.com>
Date: Fri, 21 Jul 2023 10:13:47 +0200
Subject: [PATCH 0399/1189] watchdog: advantech_ec_wdt: fix Kconfig
 dependencies

This driver uses the WATCHDOG_CORE framework and ISA_BUS_API.
This commit has these dependencies correctly selected.

Signed-off-by: Florent CARLI <fcarli@gmail.com>
Co-authored-by: Yoann Congal <yoann.congal@smile.fr>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20230721081347.52069-1-fcarli@gmail.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/Kconfig | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index a23f7a0168e0..5a1d0380c66b 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -1075,6 +1075,8 @@ config ADVANTECH_WDT
 config ADVANTECH_EC_WDT
 	tristate "Advantech Embedded Controller Watchdog Timer"
 	depends on X86
+	select ISA_BUS_API
+	select WATCHDOG_CORE
 	help
 		This driver supports Advantech products with ITE based Embedded Controller.
 		It does not support Advantech products with other ECs or without EC.

From f1a43aadb5a690e141a3b6700e2a40c1d4dbe088 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Fri, 28 Jul 2023 13:50:21 -0600
Subject: [PATCH 0400/1189] watchdog: Enable COMPILE_TEST for more drivers

There's quite a few watchdog drivers which are easily enabled for
COMPILE_TEST, so let's enable them.

Signed-off-by: Rob Herring <robh@kernel.org>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20230728195022.1198555-1-robh@kernel.org
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/Kconfig         | 80 ++++++++++++++++----------------
 drivers/watchdog/loongson1_wdt.c |  1 +
 2 files changed, 41 insertions(+), 40 deletions(-)

diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 5a1d0380c66b..f5057b35fcfd 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -307,7 +307,7 @@ config XILINX_WATCHDOG
 config XILINX_WINDOW_WATCHDOG
 	tristate "Xilinx window watchdog timer"
 	depends on HAS_IOMEM
-	depends on ARM64
+	depends on ARM64 || COMPILE_TEST
 	select WATCHDOG_CORE
 	help
 	  Window watchdog driver for the versal_wwdt IP core.
@@ -343,7 +343,7 @@ config RAVE_SP_WATCHDOG
 
 config MLX_WDT
 	tristate "Mellanox Watchdog"
-	depends on MELLANOX_PLATFORM
+	depends on MELLANOX_PLATFORM || COMPILE_TEST
 	select WATCHDOG_CORE
 	select REGMAP
 	help
@@ -493,7 +493,7 @@ config FTWDT010_WATCHDOG
 
 config IXP4XX_WATCHDOG
 	tristate "IXP4xx Watchdog"
-	depends on ARCH_IXP4XX
+	depends on ARCH_IXP4XX || (ARM && COMPILE_TEST)
 	select WATCHDOG_CORE
 	help
 	  Say Y here if to include support for the watchdog timer
@@ -529,7 +529,7 @@ config S3C2410_WATCHDOG
 
 config SA1100_WATCHDOG
 	tristate "SA1100/PXA2xx watchdog"
-	depends on ARCH_SA1100 || ARCH_PXA
+	depends on ARCH_SA1100 || ARCH_PXA || COMPILE_TEST
 	help
 	  Watchdog timer embedded into SA11x0 and PXA2xx chips. This will
 	  reboot your system when timeout is reached.
@@ -720,7 +720,7 @@ config IMX2_WDT
 config IMX_SC_WDT
 	tristate "IMX SC Watchdog"
 	depends on HAVE_ARM_SMCCC
-	depends on IMX_SCU
+	depends on IMX_SCU || COMPILE_TEST
 	select WATCHDOG_CORE
 	help
 	  This is the driver for the system controller watchdog
@@ -931,7 +931,7 @@ config ASPEED_WATCHDOG
 
 config STM32_WATCHDOG
 	tristate "STM32 Independent WatchDoG (IWDG) support"
-	depends on ARCH_STM32
+	depends on ARCH_STM32 || COMPILE_TEST
 	select WATCHDOG_CORE
 	default y
 	help
@@ -1065,7 +1065,7 @@ config ACQUIRE_WDT
 
 config ADVANTECH_WDT
 	tristate "Advantech SBC Watchdog Timer"
-	depends on X86
+	depends on X86 || COMPILE_TEST
 	help
 	  If you are configuring a Linux kernel for the Advantech single-board
 	  computer, say `Y' here to support its built-in watchdog timer
@@ -1074,7 +1074,7 @@ config ADVANTECH_WDT
 
 config ADVANTECH_EC_WDT
 	tristate "Advantech Embedded Controller Watchdog Timer"
-	depends on X86
+	depends on X86 || COMPILE_TEST
 	select ISA_BUS_API
 	select WATCHDOG_CORE
 	help
@@ -1083,7 +1083,7 @@ config ADVANTECH_EC_WDT
 
 config ALIM1535_WDT
 	tristate "ALi M1535 PMU Watchdog Timer"
-	depends on X86 && PCI
+	depends on (X86 || COMPILE_TEST) && PCI
 	help
 	  This is the driver for the hardware watchdog on the ALi M1535 PMU.
 
@@ -1107,7 +1107,7 @@ config ALIM7101_WDT
 
 config EBC_C384_WDT
 	tristate "WinSystems EBC-C384 Watchdog Timer"
-	depends on X86
+	depends on X86 || COMPILE_TEST
 	select ISA_BUS_API
 	select WATCHDOG_CORE
 	help
@@ -1117,7 +1117,7 @@ config EBC_C384_WDT
 
 config EXAR_WDT
 	tristate "Exar Watchdog Timer"
-	depends on X86
+	depends on X86 || COMPILE_TEST
 	select WATCHDOG_CORE
 	help
 	  Enables watchdog timer support for the watchdog timer present
@@ -1128,7 +1128,7 @@ config EXAR_WDT
 
 config F71808E_WDT
 	tristate "Fintek F718xx, F818xx Super I/O Watchdog"
-	depends on X86
+	depends on X86 || COMPILE_TEST
 	select WATCHDOG_CORE
 	help
 	  This is the driver for the hardware watchdog on the Fintek F71808E,
@@ -1140,7 +1140,7 @@ config F71808E_WDT
 
 config SP5100_TCO
 	tristate "AMD/ATI SP5100 TCO Timer/Watchdog"
-	depends on X86 && PCI
+	depends on (X86 || COMPILE_TEST) && PCI
 	select WATCHDOG_CORE
 	help
 	  Hardware watchdog driver for the AMD/ATI SP5100 chipset. The TCO
@@ -1179,7 +1179,7 @@ config SC520_WDT
 
 config SBC_FITPC2_WATCHDOG
 	tristate "Compulab SBC-FITPC2 watchdog"
-	depends on X86
+	depends on X86 || COMPILE_TEST
 	help
 	  This is the driver for the built-in watchdog timer on the fit-PC2,
 	  fit-PC2i, CM-iAM single-board computers made by Compulab.
@@ -1204,7 +1204,7 @@ config SBC_FITPC2_WATCHDOG
 
 config EUROTECH_WDT
 	tristate "Eurotech CPU-1220/1410 Watchdog Timer"
-	depends on X86
+	depends on X86 || COMPILE_TEST
 	help
 	  Enable support for the watchdog timer on the Eurotech CPU-1220 and
 	  CPU-1410 cards.  These are PC/104 SBCs. Spec sheets and product
@@ -1212,7 +1212,7 @@ config EUROTECH_WDT
 
 config IB700_WDT
 	tristate "IB700 SBC Watchdog Timer"
-	depends on X86
+	depends on X86 || COMPILE_TEST
 	help
 	  This is the driver for the hardware watchdog on the IB700 Single
 	  Board Computer produced by TMC Technology (www.tmc-uk.com). This
@@ -1229,7 +1229,7 @@ config IB700_WDT
 
 config IBMASR
 	tristate "IBM Automatic Server Restart"
-	depends on X86
+	depends on X86 || COMPILE_TEST
 	help
 	  This is the driver for the IBM Automatic Server Restart watchdog
 	  timer built-in into some eServer xSeries machines.
@@ -1239,7 +1239,7 @@ config IBMASR
 
 config WAFER_WDT
 	tristate "ICP Single Board Computer Watchdog Timer"
-	depends on X86
+	depends on X86 || COMPILE_TEST
 	help
 	  This is a driver for the hardware watchdog on the ICP Single
 	  Board Computer. This driver is working on (at least) the following
@@ -1261,7 +1261,7 @@ config I6300ESB_WDT
 
 config IE6XX_WDT
 	tristate "Intel Atom E6xx Watchdog"
-	depends on X86 && PCI
+	depends on (X86 || COMPILE_TEST) && PCI
 	select WATCHDOG_CORE
 	select MFD_CORE
 	select LPC_SCH
@@ -1321,7 +1321,7 @@ config ITCO_VENDOR_SUPPORT
 
 config IT8712F_WDT
 	tristate "IT8712F (Smart Guardian) Watchdog Timer"
-	depends on X86
+	depends on X86 || COMPILE_TEST
 	help
 	  This is the driver for the built-in watchdog timer on the IT8712F
 	  Super I/0 chipset used on many motherboards.
@@ -1334,7 +1334,7 @@ config IT8712F_WDT
 
 config IT87_WDT
 	tristate "IT87 Watchdog Timer"
-	depends on X86
+	depends on X86 || COMPILE_TEST
 	select WATCHDOG_CORE
 	help
 	  This is the driver for the hardware watchdog on the ITE IT8607,
@@ -1352,7 +1352,7 @@ config IT87_WDT
 config HP_WATCHDOG
 	tristate "HP ProLiant iLO2+ Hardware Watchdog Timer"
 	select WATCHDOG_CORE
-	depends on (ARM64 || X86) && PCI
+	depends on (ARM64 || X86 || COMPILE_TEST) && PCI
 	help
 	  A software monitoring watchdog and NMI handling driver. This driver
 	  will detect lockups and provide a stack trace. This is a driver that
@@ -1382,7 +1382,7 @@ config KEMPLD_WDT
 
 config SC1200_WDT
 	tristate "National Semiconductor PC87307/PC97307 (ala SC1200) Watchdog"
-	depends on X86
+	depends on X86 || COMPILE_TEST
 	help
 	  This is a driver for National Semiconductor PC87307/PC97307 hardware
 	  watchdog cards as found on the SC1200. This watchdog is mainly used
@@ -1405,7 +1405,7 @@ config SCx200_WDT
 
 config PC87413_WDT
 	tristate "NS PC87413 watchdog"
-	depends on X86
+	depends on X86 || COMPILE_TEST
 	help
 	  This is the driver for the hardware watchdog on the PC87413 chipset
 	  This watchdog simply watches your kernel to make sure it doesn't
@@ -1419,7 +1419,7 @@ config PC87413_WDT
 
 config NV_TCO
 	tristate "nVidia TCO Timer/Watchdog"
-	depends on X86 && PCI
+	depends on (X86 || COMPILE_TEST) && PCI
 	help
 	  Hardware driver for the TCO timer built into the nVidia Hub family
 	  (such as the MCP51).  The TCO (Total Cost of Ownership) timer is a
@@ -1448,7 +1448,7 @@ config RDC321X_WDT
 
 config 60XX_WDT
 	tristate "SBC-60XX Watchdog Timer"
-	depends on X86
+	depends on X86 || COMPILE_TEST
 	help
 	  This driver can be used with the watchdog timer found on some
 	  single board computers, namely the 6010 PII based computer.
@@ -1488,7 +1488,7 @@ config SBC7240_WDT
 
 config CPU5_WDT
 	tristate "SMA CPU5 Watchdog"
-	depends on X86
+	depends on X86 || COMPILE_TEST
 	help
 	  TBD.
 	  To compile this driver as a module, choose M here: the
@@ -1496,7 +1496,7 @@ config CPU5_WDT
 
 config SMSC_SCH311X_WDT
 	tristate "SMSC SCH311X Watchdog Timer"
-	depends on X86
+	depends on X86 || COMPILE_TEST
 	help
 	  This is the driver for the hardware watchdog timer on the
 	  SMSC SCH3112, SCH3114 and SCH3116 Super IO chipset
@@ -1508,7 +1508,7 @@ config SMSC_SCH311X_WDT
 
 config SMSC37B787_WDT
 	tristate "Winbond SMsC37B787 Watchdog Timer"
-	depends on X86
+	depends on X86 || COMPILE_TEST
 	help
 	  This is the driver for the hardware watchdog component on the
 	  Winbond SMsC37B787 chipset as used on the NetRunner Mainboard
@@ -1528,7 +1528,7 @@ config SMSC37B787_WDT
 
 config TQMX86_WDT
 	tristate "TQ-Systems TQMX86 Watchdog Timer"
-	depends on X86
+	depends on X86 || COMPILE_TEST
 	select WATCHDOG_CORE
 	help
 	  This is the driver for the hardware watchdog timer in the TQMX86 IO
@@ -1541,7 +1541,7 @@ config TQMX86_WDT
 
 config VIA_WDT
 	tristate "VIA Watchdog Timer"
-	depends on X86 && PCI
+	depends on (X86 || COMPILE_TEST) && PCI
 	select WATCHDOG_CORE
 	help
 	  This is the driver for the hardware watchdog timer on VIA
@@ -1554,7 +1554,7 @@ config VIA_WDT
 
 config W83627HF_WDT
 	tristate "Watchdog timer for W83627HF/W83627DHG and compatibles"
-	depends on X86
+	depends on X86 || COMPILE_TEST
 	select WATCHDOG_CORE
 	help
 	  This is the driver for the hardware watchdog on the following
@@ -1584,7 +1584,7 @@ config W83627HF_WDT
 
 config W83877F_WDT
 	tristate "W83877F (EMACS) Watchdog Timer"
-	depends on X86
+	depends on X86 || COMPILE_TEST
 	help
 	  This is the driver for the hardware watchdog on the W83877F chipset
 	  as used in EMACS PC-104 motherboards (and likely others).  This
@@ -1599,7 +1599,7 @@ config W83877F_WDT
 
 config W83977F_WDT
 	tristate "W83977F (PCM-5335) Watchdog Timer"
-	depends on X86
+	depends on X86 || COMPILE_TEST
 	help
 	  This is the driver for the hardware watchdog on the W83977F I/O chip
 	  as used in AAEON's PCM-5335 SBC (and likely others).  This
@@ -1612,7 +1612,7 @@ config W83977F_WDT
 
 config MACHZ_WDT
 	tristate "ZF MachZ Watchdog"
-	depends on X86
+	depends on X86 || COMPILE_TEST
 	help
 	  If you are using a ZF Micro MachZ processor, say Y here, otherwise
 	  N.  This is the driver for the watchdog timer built-in on that
@@ -1625,7 +1625,7 @@ config MACHZ_WDT
 
 config SBC_EPX_C3_WATCHDOG
 	tristate "Winsystems SBC EPX-C3 watchdog"
-	depends on X86
+	depends on X86 || COMPILE_TEST
 	help
 	  This is the driver for the built-in watchdog timer on the EPX-C3
 	  Single-board computer made by Winsystems, Inc.
@@ -1740,7 +1740,7 @@ config INDYDOG
 
 config JZ4740_WDT
 	tristate "Ingenic jz4740 SoC hardware watchdog"
-	depends on MIPS
+	depends on MIPS || COMPILE_TEST
 	depends on COMMON_CLK
 	select WATCHDOG_CORE
 	select MFD_SYSCON
@@ -1837,7 +1837,7 @@ config BCM_KONA_WDT
 
 config BCM_KONA_WDT_DEBUG
 	bool "DEBUGFS support for BCM Kona Watchdog"
-	depends on BCM_KONA_WDT
+	depends on BCM_KONA_WDT || COMPILE_TEST
 	help
 	  If enabled, adds /sys/kernel/debug/bcm_kona_wdt/info which provides
 	  access to the driver's internal data structures as well as watchdog
@@ -1878,7 +1878,7 @@ config LANTIQ_WDT
 
 config LOONGSON1_WDT
 	tristate "Loongson1 SoC hardware watchdog"
-	depends on MACH_LOONGSON32
+	depends on MACH_LOONGSON32 || COMPILE_TEST
 	select WATCHDOG_CORE
 	help
 	  Hardware driver for the Loongson1 SoC Watchdog Timer.
@@ -1892,7 +1892,7 @@ config RALINK_WDT
 
 config GXP_WATCHDOG
 	tristate "HPE GXP watchdog support"
-	depends on ARCH_HPE_GXP
+	depends on ARCH_HPE_GXP || COMPILE_TEST
 	select WATCHDOG_CORE
 	help
 	  Say Y here to include support for the watchdog timer
diff --git a/drivers/watchdog/loongson1_wdt.c b/drivers/watchdog/loongson1_wdt.c
index 4ac7810a314d..0587ff44d3a1 100644
--- a/drivers/watchdog/loongson1_wdt.c
+++ b/drivers/watchdog/loongson1_wdt.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/clk.h>
+#include <linux/io.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>

From 122b159d9f1374a7252c927df2b2a575f77de85b Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Tue, 8 Aug 2023 00:32:41 +0900
Subject: [PATCH 0401/1189] mips: remove unneeded #include <asm/export.h>
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is no EXPORT_SYMBOL line there, hence #include <asm/export.h>
is unneeded.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/kernel/octeon_switch.S | 1 -
 arch/mips/kernel/r2300_switch.S  | 1 -
 2 files changed, 2 deletions(-)

diff --git a/arch/mips/kernel/octeon_switch.S b/arch/mips/kernel/octeon_switch.S
index 9b7c8ab6f08c..447a3ea14aa1 100644
--- a/arch/mips/kernel/octeon_switch.S
+++ b/arch/mips/kernel/octeon_switch.S
@@ -11,7 +11,6 @@
  *    written by Carsten Langgaard, carstenl@mips.com
  */
 #include <asm/asm.h>
-#include <asm/export.h>
 #include <asm/asm-offsets.h>
 #include <asm/mipsregs.h>
 #include <asm/regdef.h>
diff --git a/arch/mips/kernel/r2300_switch.S b/arch/mips/kernel/r2300_switch.S
index 71b1aafae1bb..48e63943e6f7 100644
--- a/arch/mips/kernel/r2300_switch.S
+++ b/arch/mips/kernel/r2300_switch.S
@@ -13,7 +13,6 @@
  */
 #include <asm/asm.h>
 #include <asm/cachectl.h>
-#include <asm/export.h>
 #include <asm/fpregdef.h>
 #include <asm/mipsregs.h>
 #include <asm/asm-offsets.h>

From 9259e15b3f27fa5cc5999db554bce713f32769c3 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Tue, 8 Aug 2023 00:32:42 +0900
Subject: [PATCH 0402/1189] mips: replace #include <asm/export.h> with #include
 <linux/export.h>
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit ddb5cdbafaaa ("kbuild: generate KSYMTAB entries by modpost")
deprecated <asm/export.h>, which is now a wrapper of <linux/export.h>.

Replace #include <asm/export.h> with #include <linux/export.h>.

After all the <asm/export.h> lines are converted, <asm/export.h> and
<asm-generic/export.h> will be removed.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/cavium-octeon/octeon-memcpy.S | 2 +-
 arch/mips/kernel/mcount.S               | 2 +-
 arch/mips/kernel/r2300_fpu.S            | 2 +-
 arch/mips/kernel/r4k_fpu.S              | 2 +-
 arch/mips/lib/csum_partial.S            | 2 +-
 arch/mips/lib/memcpy.S                  | 2 +-
 arch/mips/lib/memset.S                  | 2 +-
 arch/mips/lib/strncpy_user.S            | 2 +-
 arch/mips/lib/strnlen_user.S            | 2 +-
 arch/mips/mm/page-funcs.S               | 2 +-
 arch/mips/mm/tlb-funcs.S                | 2 +-
 11 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/arch/mips/cavium-octeon/octeon-memcpy.S b/arch/mips/cavium-octeon/octeon-memcpy.S
index 25860fba6218..fef0c6de3fa1 100644
--- a/arch/mips/cavium-octeon/octeon-memcpy.S
+++ b/arch/mips/cavium-octeon/octeon-memcpy.S
@@ -13,9 +13,9 @@
  * Mnemonic names for arguments to memcpy/__copy_user
  */
 
+#include <linux/export.h>
 #include <asm/asm.h>
 #include <asm/asm-offsets.h>
-#include <asm/export.h>
 #include <asm/regdef.h>
 
 #define dst a0
diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S
index cff52b283e03..fcec579f64e9 100644
--- a/arch/mips/kernel/mcount.S
+++ b/arch/mips/kernel/mcount.S
@@ -10,7 +10,7 @@
  * Author: Wu Zhangjin <wuzhangjin@gmail.com>
  */
 
-#include <asm/export.h>
+#include <linux/export.h>
 #include <asm/regdef.h>
 #include <asm/stackframe.h>
 #include <asm/ftrace.h>
diff --git a/arch/mips/kernel/r2300_fpu.S b/arch/mips/kernel/r2300_fpu.S
index 6c745aa9e825..c000b22e3fcd 100644
--- a/arch/mips/kernel/r2300_fpu.S
+++ b/arch/mips/kernel/r2300_fpu.S
@@ -11,10 +11,10 @@
  * Further modifications to make this work:
  * Copyright (c) 1998 Harald Koerfgen
  */
+#include <linux/export.h>
 #include <asm/asm.h>
 #include <asm/asmmacro.h>
 #include <asm/errno.h>
-#include <asm/export.h>
 #include <asm/fpregdef.h>
 #include <asm/mipsregs.h>
 #include <asm/asm-offsets.h>
diff --git a/arch/mips/kernel/r4k_fpu.S b/arch/mips/kernel/r4k_fpu.S
index 4e8c98517d9d..4bb97ee89904 100644
--- a/arch/mips/kernel/r4k_fpu.S
+++ b/arch/mips/kernel/r4k_fpu.S
@@ -12,10 +12,10 @@
  * Copyright (C) 2000 MIPS Technologies, Inc.
  * Copyright (C) 1999, 2001 Silicon Graphics, Inc.
  */
+#include <linux/export.h>
 #include <asm/asm.h>
 #include <asm/asmmacro.h>
 #include <asm/errno.h>
-#include <asm/export.h>
 #include <asm/fpregdef.h>
 #include <asm/mipsregs.h>
 #include <asm/asm-offsets.h>
diff --git a/arch/mips/lib/csum_partial.S b/arch/mips/lib/csum_partial.S
index 7767137c3e49..3d2ff4118d79 100644
--- a/arch/mips/lib/csum_partial.S
+++ b/arch/mips/lib/csum_partial.S
@@ -11,9 +11,9 @@
  * Copyright (C) 2014 Imagination Technologies Ltd.
  */
 #include <linux/errno.h>
+#include <linux/export.h>
 #include <asm/asm.h>
 #include <asm/asm-offsets.h>
-#include <asm/export.h>
 #include <asm/regdef.h>
 
 #ifdef CONFIG_64BIT
diff --git a/arch/mips/lib/memcpy.S b/arch/mips/lib/memcpy.S
index 18a43f2e29c8..a4b4e805ff13 100644
--- a/arch/mips/lib/memcpy.S
+++ b/arch/mips/lib/memcpy.S
@@ -32,9 +32,9 @@
 #undef CONFIG_CPU_HAS_PREFETCH
 #endif
 
+#include <linux/export.h>
 #include <asm/asm.h>
 #include <asm/asm-offsets.h>
-#include <asm/export.h>
 #include <asm/regdef.h>
 
 #define dst a0
diff --git a/arch/mips/lib/memset.S b/arch/mips/lib/memset.S
index 0b342bae9a98..79405c32cc85 100644
--- a/arch/mips/lib/memset.S
+++ b/arch/mips/lib/memset.S
@@ -8,9 +8,9 @@
  * Copyright (C) 2007 by Maciej W. Rozycki
  * Copyright (C) 2011, 2012 MIPS Technologies, Inc.
  */
+#include <linux/export.h>
 #include <asm/asm.h>
 #include <asm/asm-offsets.h>
-#include <asm/export.h>
 #include <asm/regdef.h>
 
 #if LONGSIZE == 4
diff --git a/arch/mips/lib/strncpy_user.S b/arch/mips/lib/strncpy_user.S
index 13aaa9927ad1..94f4203563c1 100644
--- a/arch/mips/lib/strncpy_user.S
+++ b/arch/mips/lib/strncpy_user.S
@@ -7,9 +7,9 @@
  * Copyright (C) 2011 MIPS Technologies, Inc.
  */
 #include <linux/errno.h>
+#include <linux/export.h>
 #include <asm/asm.h>
 #include <asm/asm-offsets.h>
-#include <asm/export.h>
 #include <asm/regdef.h>
 
 #define EX(insn,reg,addr,handler)			\
diff --git a/arch/mips/lib/strnlen_user.S b/arch/mips/lib/strnlen_user.S
index 6de31b616f9c..c192a6f6cd84 100644
--- a/arch/mips/lib/strnlen_user.S
+++ b/arch/mips/lib/strnlen_user.S
@@ -6,9 +6,9 @@
  * Copyright (c) 1996, 1998, 1999, 2004 by Ralf Baechle
  * Copyright (c) 1999 Silicon Graphics, Inc.
  */
+#include <linux/export.h>
 #include <asm/asm.h>
 #include <asm/asm-offsets.h>
-#include <asm/export.h>
 #include <asm/regdef.h>
 
 #define EX(insn,reg,addr,handler)			\
diff --git a/arch/mips/mm/page-funcs.S b/arch/mips/mm/page-funcs.S
index 43181ac0a1af..42d0516ca18a 100644
--- a/arch/mips/mm/page-funcs.S
+++ b/arch/mips/mm/page-funcs.S
@@ -8,8 +8,8 @@
  * Copyright (C) 2012  MIPS Technologies, Inc.
  * Copyright (C) 2012  Ralf Baechle <ralf@linux-mips.org>
  */
+#include <linux/export.h>
 #include <asm/asm.h>
-#include <asm/export.h>
 #include <asm/regdef.h>
 
 #ifdef CONFIG_SIBYTE_DMA_PAGEOPS
diff --git a/arch/mips/mm/tlb-funcs.S b/arch/mips/mm/tlb-funcs.S
index 00fef578c8cd..2705d7dcb33e 100644
--- a/arch/mips/mm/tlb-funcs.S
+++ b/arch/mips/mm/tlb-funcs.S
@@ -11,8 +11,8 @@
  * Copyright (C) 2012  MIPS Technologies, Inc.
  * Copyright (C) 2012  Ralf Baechle <ralf@linux-mips.org>
  */
+#include <linux/export.h>
 #include <asm/asm.h>
-#include <asm/export.h>
 #include <asm/regdef.h>
 
 #define FASTPATH_SIZE	128

From 0eefa56435299fb867fe6975cdf9c908b9c2ff8f Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Tue, 8 Aug 2023 00:32:43 +0900
Subject: [PATCH 0403/1189] mips: remove <asm/export.h>
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

All *.S files under arch/mips/ have been converted to include
<linux/export.h> instead of <asm/export.h>.

Remove <asm/export.h>.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/include/asm/Kbuild | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index dee172716581..7ba67a0d6c97 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -7,7 +7,6 @@ generated-y += unistd_nr_n32.h
 generated-y += unistd_nr_n64.h
 generated-y += unistd_nr_o32.h
 
-generic-y += export.h
 generic-y += kvm_para.h
 generic-y += mcs_spinlock.h
 generic-y += parport.h

From ed07f6c26f9c18e5122ecba0526923ba32a7a6f7 Mon Sep 17 00:00:00 2001
From: Sui Jingfeng <suijingfeng@loongson.cn>
Date: Thu, 3 Aug 2023 17:16:37 +0800
Subject: [PATCH 0404/1189] Mips: loongson3_defconfig: Enable ast drm driver by
 default

ASpeed GPU is typically found on the Loongson server platform, as a
peripheral device driver, it generally should be compiled as a module.

Tested on loongson 3B4000 server[1].

[1] https://github.com/loongson-gfx/loongson_boards/tree/main/ls3b4000x2_server

Signed-off-by: Sui Jingfeng <suijingfeng@loongson.cn>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/configs/loongson3_defconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/mips/configs/loongson3_defconfig b/arch/mips/configs/loongson3_defconfig
index 3087e64e6ebe..a9fadea72da5 100644
--- a/arch/mips/configs/loongson3_defconfig
+++ b/arch/mips/configs/loongson3_defconfig
@@ -283,6 +283,7 @@ CONFIG_DRM_AMDGPU_USERPTR=y
 CONFIG_DRM_AMD_ACP=y
 CONFIG_DRM_AMD_DC=y
 CONFIG_DRM_AMD_DC_SI=y
+CONFIG_DRM_AST=m
 CONFIG_DRM_RADEON=m
 CONFIG_DRM_QXL=y
 CONFIG_DRM_VIRTIO_GPU=y

From 07b4c950f27bef0362dc6ad7ee713aab61d58149 Mon Sep 17 00:00:00 2001
From: Felix Engelhardt <felix.engelhardt@eidu.com>
Date: Tue, 15 Aug 2023 11:37:48 -0700
Subject: [PATCH 0405/1189] Input: goodix - add support for ACPI ID GDX9110

The Goodix touchscreen controller with ACPI ID GDX9110 was not recognized
by the goodix driver. This patch adds this ID to the list of supported IDs,
allowing the driver to be used with this device. The change will allow
Linux to be used on ~1 million tablet devices used in Kenyan primary
schools.

Signed-off-by: Felix Engelhardt <felix.engelhardt@eidu.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20230807124723.382899-1-felix.engelhardt@eidu.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/goodix.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c
index f5aa240739f9..7f5cfc5e136e 100644
--- a/drivers/input/touchscreen/goodix.c
+++ b/drivers/input/touchscreen/goodix.c
@@ -1517,6 +1517,7 @@ MODULE_DEVICE_TABLE(i2c, goodix_ts_id);
 static const struct acpi_device_id goodix_acpi_match[] = {
 	{ "GDIX1001", 0 },
 	{ "GDIX1002", 0 },
+	{ "GDX9110", 0 },
 	{ }
 };
 MODULE_DEVICE_TABLE(acpi, goodix_acpi_match);

From a6b33d009fc1fe80c935f18b714b36c81e1f1400 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Mon, 14 Aug 2023 22:06:36 +0800
Subject: [PATCH 0406/1189] KVM: arm64: Remove unused declarations

Commit 53692908b0f5 ("KVM: arm/arm64: vgic: Fix source vcpu issues for GICv2 SGI")
removed vgic_v2_set_npie()/vgic_v3_set_npie() but not the declarations.
Commit 29eb5a3c57f7 ("KVM: arm64: Handle PtrAuth traps early") left behind
kvm_arm_vcpu_ptrauth_trap(), remove it.
Commit 2a0c343386ae ("KVM: arm64: Initialize trap registers for protected VMs")
declared but never implemented kvm_init_protected_traps() and
commit cf5d318865e2 ("arm/arm64: KVM: Turn off vcpus on PSCI shutdown/reboot")
declared but never implemented force_vm_exit().

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Zenghui Yu <zenghui.yu@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230814140636.45988-1-yuehaibing@huawei.com
---
 arch/arm64/include/asm/kvm_host.h | 6 ------
 arch/arm64/kvm/vgic/vgic.h        | 2 --
 2 files changed, 8 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index d3dd05bbfe23..d1a40fa26369 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -967,8 +967,6 @@ void kvm_arm_resume_guest(struct kvm *kvm);
 #define kvm_call_hyp_nvhe(f, ...) f(__VA_ARGS__)
 #endif /* __KVM_NVHE_HYPERVISOR__ */
 
-void force_vm_exit(const cpumask_t *mask);
-
 int handle_exit(struct kvm_vcpu *vcpu, int exception_index);
 void handle_exit_early(struct kvm_vcpu *vcpu, int exception_index);
 
@@ -1049,8 +1047,6 @@ static inline bool kvm_system_needs_idmapped_vectors(void)
 	return cpus_have_const_cap(ARM64_SPECTRE_V3A);
 }
 
-void kvm_arm_vcpu_ptrauth_trap(struct kvm_vcpu *vcpu);
-
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 
@@ -1118,8 +1114,6 @@ static inline bool kvm_vm_is_protected(struct kvm *kvm)
 	return false;
 }
 
-void kvm_init_protected_traps(struct kvm_vcpu *vcpu);
-
 int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature);
 bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu);
 
diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h
index f9923beedd27..0ab09b0d4440 100644
--- a/arch/arm64/kvm/vgic/vgic.h
+++ b/arch/arm64/kvm/vgic/vgic.h
@@ -199,7 +199,6 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu);
 void vgic_v2_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr);
 void vgic_v2_clear_lr(struct kvm_vcpu *vcpu, int lr);
 void vgic_v2_set_underflow(struct kvm_vcpu *vcpu);
-void vgic_v2_set_npie(struct kvm_vcpu *vcpu);
 int vgic_v2_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr);
 int vgic_v2_dist_uaccess(struct kvm_vcpu *vcpu, bool is_write,
 			 int offset, u32 *val);
@@ -233,7 +232,6 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu);
 void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr);
 void vgic_v3_clear_lr(struct kvm_vcpu *vcpu, int lr);
 void vgic_v3_set_underflow(struct kvm_vcpu *vcpu);
-void vgic_v3_set_npie(struct kvm_vcpu *vcpu);
 void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
 void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
 void vgic_v3_enable(struct kvm_vcpu *vcpu);

From 7777ac3dfe29f55dd0323d05a4cc81164fcfeb0e Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 15 Aug 2023 16:30:56 -0300
Subject: [PATCH 0407/1189] perf test trace+probe_vfs_getname.sh: Remove stray
 \ before /

Running on fedora:38 in verbose mode I noticed:

  # perf test -v 117
  grep: warning: stray \ before /
  117: Check open filename arg using perf trace + vfs_getname          :

Remove that \ before /.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/ZNvTDsSMO3nw9Tnp@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/trace+probe_vfs_getname.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
index db2ff141f703..3697f054ce19 100755
--- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
@@ -20,7 +20,7 @@ skip_if_no_perf_trace || exit 2
 trace_open_vfs_getname() {
 	evts="$(echo "$(perf list syscalls:sys_enter_open* 2>/dev/null | grep -E 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/')" | sed ':a;N;s:\n:,:g')"
 	perf trace -e $evts touch $file 2>&1 | \
-	grep -E " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open(at)?\((dfd: +CWD, +)?filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
+	grep -E " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch/[0-9]+ open(at)?\((dfd: +CWD, +)?filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
 }
 
 

From 6f769c3458b6cf2ddb3537c2a0b17463ead2af87 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 15 Aug 2023 16:35:19 -0300
Subject: [PATCH 0408/1189] perf tests trace+probe_vfs_getname.sh: Accept
 quotes surrounding the filename

With augmented_raw_syscalls transformed into a BPF skel made the output have a "
around the filenames, which is not what the old perf probe vfs_getname
method of obtaining filenames did, so accept the augmented way, with the
quotes.

At this point probably removing all the logic for the vfs_getname method
is in order, will do it at some point.

For now lets accept with/without quotes and make that test pass.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/trace+probe_vfs_getname.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
index 3697f054ce19..4014487cf4d9 100755
--- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
@@ -20,7 +20,7 @@ skip_if_no_perf_trace || exit 2
 trace_open_vfs_getname() {
 	evts="$(echo "$(perf list syscalls:sys_enter_open* 2>/dev/null | grep -E 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/')" | sed ':a;N;s:\n:,:g')"
 	perf trace -e $evts touch $file 2>&1 | \
-	grep -E " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch/[0-9]+ open(at)?\((dfd: +CWD, +)?filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
+	grep -E " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch/[0-9]+ open(at)?\((dfd: +CWD, +)?filename: +\"?${file}\"?, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
 }
 
 

From 56b11a2126bf2f422831ecf6112b87a4485b221b Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 11 Aug 2023 12:19:48 -0300
Subject: [PATCH 0409/1189] perf bpf: Remove support for embedding clang for
 compiling BPF events (-e foo.c)

This never was in the default build for perf, is difficult to maintain
as it uses clang/llvm internals so ditch it, keeping, for now, the
external compilation of .c BPF into .o bytecode and its subsequent
loading, that is also going to be removed, do it separately to help
bisection and to properly document what is being removed and why.

Committer notes:

Extracted from a larger patch and removed some leftovers, namely
deleting these now unused feature tests:

    tools/build/feature/test-clang.cpp
    tools/build/feature/test-cxx.cpp
    tools/build/feature/test-llvm-version.cpp
    tools/build/feature/test-llvm.cpp

Testing the use of BPF events after applying this patch:

To use the external clang/llvm toolchain to compile a .c event and then
use libbpf to load it, to get the syscalls:sys_enter_open* tracepoints
and read the filename pointer, putting it into the ring buffer right
after the usual tracepoint payload for 'perf trace' to then print it:

  [root@quaco ~]# perf trace -e /home/acme/git/perf-tools-next/tools/perf/examples/bpf/augmented_raw_syscalls.c,open* --max-events=10
     0.000 systemd-oomd/959 openat(dfd: CWD, filename: "/proc/meminfo", flags: RDONLY|CLOEXEC) = 12
     0.083 abrt-dump-jour/1453 openat(dfd: CWD, filename: "/var/log/journal/d6a97235307247e09f13f326fb607e3c/system.journal", flags: RDONLY|CLOEXEC|NONBLOCK) = 4
     0.063 abrt-dump-jour/1454 openat(dfd: CWD, filename: "/var/log/journal/d6a97235307247e09f13f326fb607e3c/system.journal", flags: RDONLY|CLOEXEC|NONBLOCK) = 4
     0.082 abrt-dump-jour/1455 openat(dfd: CWD, filename: "/var/log/journal/d6a97235307247e09f13f326fb607e3c/system.journal", flags: RDONLY|CLOEXEC|NONBLOCK) = 4
   250.124 systemd-oomd/959 openat(dfd: CWD, filename: "/proc/meminfo", flags: RDONLY|CLOEXEC) = 12
   250.521 systemd-oomd/959 openat(dfd: CWD, filename: "/sys/fs/cgroup/user.slice/user-1000.slice/user@1000.service/app.slice/memory.pressure", flags: RDONLY|CLOEXEC) = 12
   251.047 systemd-oomd/959 openat(dfd: CWD, filename: "/sys/fs/cgroup/user.slice/user-1000.slice/user@1000.service/app.slice/memory.current", flags: RDONLY|CLOEXEC) = 12
   251.162 systemd-oomd/959 openat(dfd: CWD, filename: "/sys/fs/cgroup/user.slice/user-1000.slice/user@1000.service/app.slice/memory.min", flags: RDONLY|CLOEXEC) = 12
   251.242 systemd-oomd/959 openat(dfd: CWD, filename: "/sys/fs/cgroup/user.slice/user-1000.slice/user@1000.service/app.slice/memory.low", flags: RDONLY|CLOEXEC) = 12
   251.353 systemd-oomd/959 openat(dfd: CWD, filename: "/sys/fs/cgroup/user.slice/user-1000.slice/user@1000.service/app.slice/memory.swap.current", flags: RDONLY|CLOEXEC) = 12
  [root@quaco ~]#

Same thing, but with a prebuilt .o BPF bytecode:

  [root@quaco ~]# perf trace -e /home/acme/git/perf-tools-next/tools/perf/examples/bpf/augmented_raw_syscalls.o,open* --max-events=10
     0.000 systemd-oomd/959 openat(dfd: CWD, filename: "/proc/meminfo", flags: RDONLY|CLOEXEC) = 12
     0.083 abrt-dump-jour/1453 openat(dfd: CWD, filename: "/var/log/journal/d6a97235307247e09f13f326fb607e3c/system.journal", flags: RDONLY|CLOEXEC|NONBLOCK) = 4
     0.083 abrt-dump-jour/1455 openat(dfd: CWD, filename: "/var/log/journal/d6a97235307247e09f13f326fb607e3c/system.journal", flags: RDONLY|CLOEXEC|NONBLOCK) = 4
     0.062 abrt-dump-jour/1454 openat(dfd: CWD, filename: "/var/log/journal/d6a97235307247e09f13f326fb607e3c/system.journal", flags: RDONLY|CLOEXEC|NONBLOCK) = 4
   249.985 systemd-oomd/959 openat(dfd: CWD, filename: "/proc/meminfo", flags: RDONLY|CLOEXEC) = 12
   466.763 thermald/1234 openat(dfd: CWD, filename: "/sys/class/powercap/intel-rapl/intel-rapl:0/intel-rapl:0:2/energy_uj") = 13
   467.145 thermald/1234 openat(dfd: CWD, filename: "/sys/class/powercap/intel-rapl/intel-rapl:0/energy_uj") = 13
   467.311 thermald/1234 openat(dfd: CWD, filename: "/sys/class/thermal/thermal_zone2/temp") = 13
   500.040 cgroupify/24006 openat(dfd: 4, filename: ".", flags: RDONLY|CLOEXEC|DIRECTORY|NONBLOCK) = 5
   500.295 cgroupify/24006 openat(dfd: 4, filename: "24616/cgroup.procs") = 5
  [root@quaco ~]#

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Carsten Haitzler <carsten.haitzler@arm.com>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Fangrui Song <maskray@google.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: "Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Cc: Tiezhu Yang <yangtiezhu@loongson.cn>
Cc: Tom Rix <trix@redhat.com>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Wang ShaoBo <bobo.shaobowang@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: Yonghong Song <yhs@fb.com>
Cc: YueHaibing <yuehaibing@huawei.com>
Link: https://lore.kernel.org/lkml/ZNZWsAXg2px1sm2h@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/build/feature/test-clang.cpp        |  28 ---
 tools/build/feature/test-cxx.cpp          |  16 --
 tools/build/feature/test-llvm-version.cpp |  12 --
 tools/build/feature/test-llvm.cpp         |  14 --
 tools/perf/Makefile.config                |  31 ---
 tools/perf/Makefile.perf                  |  17 --
 tools/perf/tests/Build                    |   1 -
 tools/perf/tests/builtin-test.c           |   1 -
 tools/perf/tests/clang.c                  |  32 ---
 tools/perf/tests/make                     |   1 -
 tools/perf/util/Build                     |   2 -
 tools/perf/util/bpf-loader.c              |  15 +-
 tools/perf/util/c++/Build                 |   5 -
 tools/perf/util/c++/clang-c.h             |  43 -----
 tools/perf/util/c++/clang-test.cpp        |  67 -------
 tools/perf/util/c++/clang.cpp             | 225 ----------------------
 tools/perf/util/c++/clang.h               |  27 ---
 17 files changed, 4 insertions(+), 533 deletions(-)
 delete mode 100644 tools/build/feature/test-clang.cpp
 delete mode 100644 tools/build/feature/test-cxx.cpp
 delete mode 100644 tools/build/feature/test-llvm-version.cpp
 delete mode 100644 tools/build/feature/test-llvm.cpp
 delete mode 100644 tools/perf/tests/clang.c
 delete mode 100644 tools/perf/util/c++/Build
 delete mode 100644 tools/perf/util/c++/clang-c.h
 delete mode 100644 tools/perf/util/c++/clang-test.cpp
 delete mode 100644 tools/perf/util/c++/clang.cpp
 delete mode 100644 tools/perf/util/c++/clang.h

diff --git a/tools/build/feature/test-clang.cpp b/tools/build/feature/test-clang.cpp
deleted file mode 100644
index 7d87075cd1c5..000000000000
--- a/tools/build/feature/test-clang.cpp
+++ /dev/null
@@ -1,28 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include "clang/Basic/Version.h"
-#if CLANG_VERSION_MAJOR < 8
-#include "clang/Basic/VirtualFileSystem.h"
-#endif
-#include "clang/Driver/Driver.h"
-#include "clang/Frontend/TextDiagnosticPrinter.h"
-#include "llvm/ADT/IntrusiveRefCntPtr.h"
-#include "llvm/Support/ManagedStatic.h"
-#if CLANG_VERSION_MAJOR >= 8
-#include "llvm/Support/VirtualFileSystem.h"
-#endif
-#include "llvm/Support/raw_ostream.h"
-
-using namespace clang;
-using namespace clang::driver;
-
-int main()
-{
-	IntrusiveRefCntPtr<DiagnosticIDs> DiagID(new DiagnosticIDs());
-	IntrusiveRefCntPtr<DiagnosticOptions> DiagOpts = new DiagnosticOptions();
-
-	DiagnosticsEngine Diags(DiagID, &*DiagOpts);
-	Driver TheDriver("test", "bpf-pc-linux", Diags);
-
-	llvm::llvm_shutdown();
-	return 0;
-}
diff --git a/tools/build/feature/test-cxx.cpp b/tools/build/feature/test-cxx.cpp
deleted file mode 100644
index 396aaedd2418..000000000000
--- a/tools/build/feature/test-cxx.cpp
+++ /dev/null
@@ -1,16 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <iostream>
-#include <memory>
-
-static void print_str(std::string s)
-{
-	std::cout << s << std::endl;
-}
-
-int main()
-{
-	std::string s("Hello World!");
-	print_str(std::move(s));
-	std::cout << "|" << s << "|" << std::endl;
-	return 0;
-}
diff --git a/tools/build/feature/test-llvm-version.cpp b/tools/build/feature/test-llvm-version.cpp
deleted file mode 100644
index 8a091625446a..000000000000
--- a/tools/build/feature/test-llvm-version.cpp
+++ /dev/null
@@ -1,12 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <cstdio>
-#include "llvm/Config/llvm-config.h"
-
-#define NUM_VERSION (((LLVM_VERSION_MAJOR) << 16) + (LLVM_VERSION_MINOR << 8) + LLVM_VERSION_PATCH)
-#define pass int main() {printf("%x\n", NUM_VERSION); return 0;}
-
-#if NUM_VERSION >= 0x030900
-pass
-#else
-# error This LLVM is not tested yet.
-#endif
diff --git a/tools/build/feature/test-llvm.cpp b/tools/build/feature/test-llvm.cpp
deleted file mode 100644
index 88a3d1bdd9f6..000000000000
--- a/tools/build/feature/test-llvm.cpp
+++ /dev/null
@@ -1,14 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include "llvm/Support/ManagedStatic.h"
-#include "llvm/Support/raw_ostream.h"
-#define NUM_VERSION (((LLVM_VERSION_MAJOR) << 16) + (LLVM_VERSION_MINOR << 8) + LLVM_VERSION_PATCH)
-
-#if NUM_VERSION < 0x030900
-# error "LLVM version too low"
-#endif
-int main()
-{
-	llvm::errs() << "Hello World!\n";
-	llvm::llvm_shutdown();
-	return 0;
-}
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 1bf8dc53641f..e0592ed4c10f 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -1127,37 +1127,6 @@ ifndef NO_JVMTI
   endif
 endif
 
-USE_CXX = 0
-USE_CLANGLLVM = 0
-ifdef LIBCLANGLLVM
-  $(call feature_check,cxx)
-  ifneq ($(feature-cxx), 1)
-    msg := $(warning No g++ found, disable clang and llvm support. Please install g++)
-  else
-    $(call feature_check,llvm)
-    $(call feature_check,llvm-version)
-    ifneq ($(feature-llvm), 1)
-      msg := $(warning No suitable libLLVM found, disabling builtin clang and LLVM support. Please install llvm-dev(el) (>= 3.9.0))
-    else
-      $(call feature_check,clang)
-      ifneq ($(feature-clang), 1)
-        msg := $(warning No suitable libclang found, disabling builtin clang and LLVM support. Please install libclang-dev(el) (>= 3.9.0))
-      else
-        CFLAGS += -DHAVE_LIBCLANGLLVM_SUPPORT
-        CXXFLAGS += -DHAVE_LIBCLANGLLVM_SUPPORT -I$(shell $(LLVM_CONFIG) --includedir)
-        $(call detected,CONFIG_CXX)
-        $(call detected,CONFIG_CLANGLLVM)
-	USE_CXX = 1
-	USE_LLVM = 1
-	USE_CLANG = 1
-        ifneq ($(feature-llvm-version),1)
-          msg := $(warning This version of LLVM is not tested. May cause build errors)
-        endif
-      endif
-    endif
-  endif
-endif
-
 ifndef NO_LIBPFM4
   $(call feature_check,libpfm4)
   ifeq ($(feature-libpfm4), 1)
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 0ed7ee0c1665..5370d7bf123e 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -99,10 +99,6 @@ include ../scripts/utilities.mak
 # Define NO_JVMTI_CMLR (debug only) if you do not want to process CMLR
 # data for java source lines.
 #
-# Define LIBCLANGLLVM if you DO want builtin clang and llvm support.
-# When selected, pass LLVM_CONFIG=/path/to/llvm-config to `make' if
-# llvm-config is not in $PATH.
-#
 # Define CORESIGHT if you DO WANT support for CoreSight trace decoding.
 #
 # Define NO_AIO if you do not want support of Posix AIO based trace
@@ -425,19 +421,6 @@ endif
 EXTLIBS := $(call filter-out,$(EXCLUDE_EXTLIBS),$(EXTLIBS))
 LIBS = -Wl,--whole-archive $(PERFLIBS) $(EXTRA_PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group
 
-ifeq ($(USE_CLANG), 1)
-  LIBS += -L$(shell $(LLVM_CONFIG) --libdir) -lclang-cpp
-endif
-
-ifeq ($(USE_LLVM), 1)
-  LIBLLVM = $(shell $(LLVM_CONFIG) --libs all) $(shell $(LLVM_CONFIG) --system-libs)
-  LIBS += -L$(shell $(LLVM_CONFIG) --libdir) $(LIBLLVM)
-endif
-
-ifeq ($(USE_CXX), 1)
-  LIBS += -lstdc++
-endif
-
 export INSTALL SHELL_PATH
 
 ### Build rules
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index fb9ac5dc4079..52df5923a8b9 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -51,7 +51,6 @@ perf-y += sdt.o
 perf-y += is_printable_array.o
 perf-y += bitmap.o
 perf-y += perf-hooks.o
-perf-y += clang.o
 perf-y += unit_number__scnprintf.o
 perf-y += mem2node.o
 perf-y += maps.o
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 6accb5442a73..0f3691fd31c2 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -108,7 +108,6 @@ static struct test_suite *generic_tests[] = {
 	&suite__is_printable_array,
 	&suite__bitmap_print,
 	&suite__perf_hooks,
-	&suite__clang,
 	&suite__unit_number__scnprint,
 	&suite__mem2node,
 	&suite__time_utils,
diff --git a/tools/perf/tests/clang.c b/tools/perf/tests/clang.c
deleted file mode 100644
index a7111005d5b9..000000000000
--- a/tools/perf/tests/clang.c
+++ /dev/null
@@ -1,32 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include "tests.h"
-#include "c++/clang-c.h"
-#include <linux/kernel.h>
-
-#ifndef HAVE_LIBCLANGLLVM_SUPPORT
-static int test__clang_to_IR(struct test_suite *test __maybe_unused,
-			     int subtest __maybe_unused)
-{
-	return TEST_SKIP;
-}
-
-static int test__clang_to_obj(struct test_suite *test __maybe_unused,
-			      int subtest __maybe_unused)
-{
-	return TEST_SKIP;
-}
-#endif
-
-static struct test_case clang_tests[] = {
-	TEST_CASE_REASON("builtin clang compile C source to IR", clang_to_IR,
-			 "not compiled in"),
-	TEST_CASE_REASON("builtin clang compile C source to ELF object",
-			 clang_to_obj,
-			 "not compiled in"),
-	{ .name = NULL, }
-};
-
-struct test_suite suite__clang = {
-	.desc = "builtin clang support",
-	.test_cases = clang_tests,
-};
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index 58cf96d762d0..ea4c341f5af1 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -95,7 +95,6 @@ make_with_babeltrace:= LIBBABELTRACE=1
 make_with_coresight := CORESIGHT=1
 make_no_sdt	    := NO_SDT=1
 make_no_syscall_tbl := NO_SYSCALL_TABLE=1
-make_with_clangllvm := LIBCLANGLLVM=1
 make_no_libpfm4     := NO_LIBPFM4=1
 make_with_gtk2      := GTK2=1
 make_refcnt_check   := EXTRA_CFLAGS="-DREFCNT_CHECKING=1"
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 9699e31ff4c0..ff3b55c7ed43 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -232,8 +232,6 @@ perf-y += perf-hooks.o
 perf-$(CONFIG_LIBBPF) += bpf-event.o
 perf-$(CONFIG_LIBBPF) += bpf-utils.o
 
-perf-$(CONFIG_CXX) += c++/
-
 perf-$(CONFIG_LIBPFM4) += pfm.o
 
 CFLAGS_config.o   += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 50e42698cbb7..b54e42f17926 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -26,7 +26,6 @@
 #include "strfilter.h"
 #include "util.h"
 #include "llvm-utils.h"
-#include "c++/clang-c.h"
 #include "util/hashmap.h"
 #include "asm/bug.h"
 
@@ -220,16 +219,10 @@ struct bpf_object *bpf__prepare_load(const char *filename, bool source)
 		void *obj_buf;
 		size_t obj_buf_sz;
 
-		perf_clang__init();
-		err = perf_clang__compile_bpf(filename, &obj_buf, &obj_buf_sz);
-		perf_clang__cleanup();
-		if (err) {
-			pr_debug("bpf: builtin compilation failed: %d, try external compiler\n", err);
-			err = llvm__compile_bpf(filename, &obj_buf, &obj_buf_sz);
-			if (err)
-				return ERR_PTR(-BPF_LOADER_ERRNO__COMPILE);
-		} else
-			pr_debug("bpf: successful builtin compilation\n");
+		err = llvm__compile_bpf(filename, &obj_buf, &obj_buf_sz);
+		if (err)
+			return ERR_PTR(-BPF_LOADER_ERRNO__COMPILE);
+
 		obj = bpf_object__open_mem(obj_buf, obj_buf_sz, &opts);
 
 		if (!IS_ERR_OR_NULL(obj) && llvm_param.dump_obj)
diff --git a/tools/perf/util/c++/Build b/tools/perf/util/c++/Build
deleted file mode 100644
index 8610d032ac19..000000000000
--- a/tools/perf/util/c++/Build
+++ /dev/null
@@ -1,5 +0,0 @@
-perf-$(CONFIG_CLANGLLVM) += clang.o
-perf-$(CONFIG_CLANGLLVM) += clang-test.o
-
-CXXFLAGS_clang.o += -Wno-unused-parameter
-CXXFLAGS_clang-test.o += -Wno-unused-parameter
diff --git a/tools/perf/util/c++/clang-c.h b/tools/perf/util/c++/clang-c.h
deleted file mode 100644
index d3731a876b6c..000000000000
--- a/tools/perf/util/c++/clang-c.h
+++ /dev/null
@@ -1,43 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef PERF_UTIL_CLANG_C_H
-#define PERF_UTIL_CLANG_C_H
-
-#include <stddef.h>	/* for size_t */
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-#ifdef HAVE_LIBCLANGLLVM_SUPPORT
-extern void perf_clang__init(void);
-extern void perf_clang__cleanup(void);
-
-struct test_suite;
-extern int test__clang_to_IR(struct test_suite *test, int subtest);
-extern int test__clang_to_obj(struct test_suite *test, int subtest);
-
-extern int perf_clang__compile_bpf(const char *filename,
-				   void **p_obj_buf,
-				   size_t *p_obj_buf_sz);
-#else
-
-#include <errno.h>
-#include <linux/compiler.h>	/* for __maybe_unused */
-
-static inline void perf_clang__init(void) { }
-static inline void perf_clang__cleanup(void) { }
-
-static inline int
-perf_clang__compile_bpf(const char *filename __maybe_unused,
-			void **p_obj_buf __maybe_unused,
-			size_t *p_obj_buf_sz __maybe_unused)
-{
-	return -ENOTSUP;
-}
-
-#endif
-
-#ifdef __cplusplus
-}
-#endif
-#endif
diff --git a/tools/perf/util/c++/clang-test.cpp b/tools/perf/util/c++/clang-test.cpp
deleted file mode 100644
index a4683ca53697..000000000000
--- a/tools/perf/util/c++/clang-test.cpp
+++ /dev/null
@@ -1,67 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include "clang.h"
-#include "clang-c.h"
-extern "C" {
-#include "../util.h"
-}
-#include "llvm/IR/Function.h"
-#include "llvm/IR/LLVMContext.h"
-
-#include <tests/llvm.h>
-#include <string>
-
-class perf_clang_scope {
-public:
-	explicit perf_clang_scope() {perf_clang__init();}
-	~perf_clang_scope() {perf_clang__cleanup();}
-};
-
-static std::unique_ptr<llvm::Module>
-__test__clang_to_IR(void)
-{
-	unsigned int kernel_version;
-
-	if (fetch_kernel_version(&kernel_version, NULL, 0))
-		return std::unique_ptr<llvm::Module>(nullptr);
-
-	std::string cflag_kver("-DLINUX_VERSION_CODE=" +
-				std::to_string(kernel_version));
-
-	std::unique_ptr<llvm::Module> M =
-		perf::getModuleFromSource({cflag_kver.c_str()},
-					  "perf-test.c",
-					  test_llvm__bpf_base_prog);
-	return M;
-}
-
-extern "C" {
-int test__clang_to_IR(struct test_suite *test __maybe_unused,
-                      int subtest __maybe_unused)
-{
-	perf_clang_scope _scope;
-
-	auto M = __test__clang_to_IR();
-	if (!M)
-		return -1;
-	for (llvm::Function& F : *M)
-		if (F.getName() == "bpf_func__SyS_epoll_pwait")
-			return 0;
-	return -1;
-}
-
-int test__clang_to_obj(struct test_suite *test __maybe_unused,
-                       int subtest __maybe_unused)
-{
-	perf_clang_scope _scope;
-
-	auto M = __test__clang_to_IR();
-	if (!M)
-		return -1;
-
-	auto Buffer = perf::getBPFObjectFromModule(&*M);
-	if (!Buffer)
-		return -1;
-	return 0;
-}
-
-}
diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp
deleted file mode 100644
index 1aad7d6d34aa..000000000000
--- a/tools/perf/util/c++/clang.cpp
+++ /dev/null
@@ -1,225 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * llvm C frontend for perf. Support dynamically compile C file
- *
- * Inspired by clang example code:
- * http://llvm.org/svn/llvm-project/cfe/trunk/examples/clang-interpreter/main.cpp
- *
- * Copyright (C) 2016 Wang Nan <wangnan0@huawei.com>
- * Copyright (C) 2016 Huawei Inc.
- */
-
-#include "clang/Basic/Version.h"
-#include "clang/CodeGen/CodeGenAction.h"
-#include "clang/Frontend/CompilerInvocation.h"
-#include "clang/Frontend/CompilerInstance.h"
-#include "clang/Frontend/TextDiagnosticPrinter.h"
-#include "clang/Tooling/Tooling.h"
-#include "llvm/IR/LegacyPassManager.h"
-#include "llvm/IR/Module.h"
-#include "llvm/Option/Option.h"
-#include "llvm/Support/FileSystem.h"
-#include "llvm/Support/ManagedStatic.h"
-#if CLANG_VERSION_MAJOR >= 14
-#include "llvm/MC/TargetRegistry.h"
-#else
-#include "llvm/Support/TargetRegistry.h"
-#endif
-#include "llvm/Support/TargetSelect.h"
-#include "llvm/Target/TargetMachine.h"
-#include "llvm/Target/TargetOptions.h"
-#include <memory>
-
-#include "clang.h"
-#include "clang-c.h"
-
-namespace perf {
-
-static std::unique_ptr<llvm::LLVMContext> LLVMCtx;
-
-using namespace clang;
-
-static CompilerInvocation *
-createCompilerInvocation(llvm::opt::ArgStringList CFlags, StringRef& Path,
-			 DiagnosticsEngine& Diags)
-{
-	llvm::opt::ArgStringList CCArgs {
-		"-cc1",
-		"-triple", "bpf-pc-linux",
-		"-fsyntax-only",
-		"-O2",
-		"-nostdsysteminc",
-		"-nobuiltininc",
-		"-vectorize-loops",
-		"-vectorize-slp",
-		"-Wno-unused-value",
-		"-Wno-pointer-sign",
-		"-x", "c"};
-
-	CCArgs.append(CFlags.begin(), CFlags.end());
-	CompilerInvocation *CI = tooling::newInvocation(&Diags, CCArgs
-#if CLANG_VERSION_MAJOR >= 11
-                                                        ,/*BinaryName=*/nullptr
-#endif
-                                                        );
-
-	FrontendOptions& Opts = CI->getFrontendOpts();
-	Opts.Inputs.clear();
-	Opts.Inputs.emplace_back(Path,
-			FrontendOptions::getInputKindForExtension("c"));
-	return CI;
-}
-
-static std::unique_ptr<llvm::Module>
-getModuleFromSource(llvm::opt::ArgStringList CFlags,
-		    StringRef Path, IntrusiveRefCntPtr<vfs::FileSystem> VFS)
-{
-	CompilerInstance Clang;
-	Clang.createDiagnostics();
-
-#if CLANG_VERSION_MAJOR < 9
-	Clang.setVirtualFileSystem(&*VFS);
-#else
-	Clang.createFileManager(&*VFS);
-#endif
-
-#if CLANG_VERSION_MAJOR < 4
-	IntrusiveRefCntPtr<CompilerInvocation> CI =
-		createCompilerInvocation(std::move(CFlags), Path,
-					 Clang.getDiagnostics());
-	Clang.setInvocation(&*CI);
-#else
-	std::shared_ptr<CompilerInvocation> CI(
-		createCompilerInvocation(std::move(CFlags), Path,
-					 Clang.getDiagnostics()));
-	Clang.setInvocation(CI);
-#endif
-
-	std::unique_ptr<CodeGenAction> Act(new EmitLLVMOnlyAction(&*LLVMCtx));
-	if (!Clang.ExecuteAction(*Act))
-		return std::unique_ptr<llvm::Module>(nullptr);
-
-	return Act->takeModule();
-}
-
-std::unique_ptr<llvm::Module>
-getModuleFromSource(llvm::opt::ArgStringList CFlags,
-		    StringRef Name, StringRef Content)
-{
-	using namespace vfs;
-
-	llvm::IntrusiveRefCntPtr<OverlayFileSystem> OverlayFS(
-			new OverlayFileSystem(getRealFileSystem()));
-	llvm::IntrusiveRefCntPtr<InMemoryFileSystem> MemFS(
-			new InMemoryFileSystem(true));
-
-	/*
-	 * pushOverlay helps setting working dir for MemFS. Must call
-	 * before addFile.
-	 */
-	OverlayFS->pushOverlay(MemFS);
-	MemFS->addFile(Twine(Name), 0, llvm::MemoryBuffer::getMemBuffer(Content));
-
-	return getModuleFromSource(std::move(CFlags), Name, OverlayFS);
-}
-
-std::unique_ptr<llvm::Module>
-getModuleFromSource(llvm::opt::ArgStringList CFlags, StringRef Path)
-{
-	IntrusiveRefCntPtr<vfs::FileSystem> VFS(vfs::getRealFileSystem());
-	return getModuleFromSource(std::move(CFlags), Path, VFS);
-}
-
-std::unique_ptr<llvm::SmallVectorImpl<char>>
-getBPFObjectFromModule(llvm::Module *Module)
-{
-	using namespace llvm;
-
-	std::string TargetTriple("bpf-pc-linux");
-	std::string Error;
-	const Target* Target = TargetRegistry::lookupTarget(TargetTriple, Error);
-	if (!Target) {
-		llvm::errs() << Error;
-		return std::unique_ptr<llvm::SmallVectorImpl<char>>(nullptr);
-	}
-
-	llvm::TargetOptions Opt;
-	TargetMachine *TargetMachine =
-		Target->createTargetMachine(TargetTriple,
-					    "generic", "",
-					    Opt, Reloc::Static);
-
-	Module->setDataLayout(TargetMachine->createDataLayout());
-	Module->setTargetTriple(TargetTriple);
-
-	std::unique_ptr<SmallVectorImpl<char>> Buffer(new SmallVector<char, 0>());
-	raw_svector_ostream ostream(*Buffer);
-
-	legacy::PassManager PM;
-	bool NotAdded;
-	NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream
-#if CLANG_VERSION_MAJOR >= 7
-                                                      , /*DwoOut=*/nullptr
-#endif
-#if CLANG_VERSION_MAJOR < 10
-                                                      , TargetMachine::CGFT_ObjectFile
-#else
-                                                      , llvm::CGFT_ObjectFile
-#endif
-                                                      );
-	if (NotAdded) {
-		llvm::errs() << "TargetMachine can't emit a file of this type\n";
-		return std::unique_ptr<llvm::SmallVectorImpl<char>>(nullptr);
-	}
-	PM.run(*Module);
-
-	return Buffer;
-}
-
-}
-
-extern "C" {
-void perf_clang__init(void)
-{
-	perf::LLVMCtx.reset(new llvm::LLVMContext());
-	LLVMInitializeBPFTargetInfo();
-	LLVMInitializeBPFTarget();
-	LLVMInitializeBPFTargetMC();
-	LLVMInitializeBPFAsmPrinter();
-}
-
-void perf_clang__cleanup(void)
-{
-	perf::LLVMCtx.reset(nullptr);
-	llvm::llvm_shutdown();
-}
-
-int perf_clang__compile_bpf(const char *filename,
-			    void **p_obj_buf,
-			    size_t *p_obj_buf_sz)
-{
-	using namespace perf;
-
-	if (!p_obj_buf || !p_obj_buf_sz)
-		return -EINVAL;
-
-	llvm::opt::ArgStringList CFlags;
-	auto M = getModuleFromSource(std::move(CFlags), filename);
-	if (!M)
-		return  -EINVAL;
-	auto O = getBPFObjectFromModule(&*M);
-	if (!O)
-		return -EINVAL;
-
-	size_t size = O->size_in_bytes();
-	void *buffer;
-
-	buffer = malloc(size);
-	if (!buffer)
-		return -ENOMEM;
-	memcpy(buffer, O->data(), size);
-	*p_obj_buf = buffer;
-	*p_obj_buf_sz = size;
-	return 0;
-}
-}
diff --git a/tools/perf/util/c++/clang.h b/tools/perf/util/c++/clang.h
deleted file mode 100644
index 6ce33e22f23c..000000000000
--- a/tools/perf/util/c++/clang.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef PERF_UTIL_CLANG_H
-#define PERF_UTIL_CLANG_H
-
-#include "llvm/ADT/StringRef.h"
-#include "llvm/IR/LLVMContext.h"
-#include "llvm/IR/Module.h"
-#include "llvm/Option/Option.h"
-#include <memory>
-
-namespace perf {
-
-using namespace llvm;
-
-std::unique_ptr<Module>
-getModuleFromSource(opt::ArgStringList CFlags,
-		    StringRef Name, StringRef Content);
-
-std::unique_ptr<Module>
-getModuleFromSource(opt::ArgStringList CFlags,
-		    StringRef Path);
-
-std::unique_ptr<llvm::SmallVectorImpl<char>>
-getBPFObjectFromModule(llvm::Module *Module);
-
-}
-#endif

From 3d6dfae889174340af94c7357c8bae018966c524 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 11 Aug 2023 15:26:11 -0300
Subject: [PATCH 0410/1189] perf parse-events: Remove BPF event support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

New features like the BPF --filter support in perf record have made the
BPF event functionality somewhat redundant. As shown by commit
fcb027c1a4f6 ("perf tools: Revert enable indices setting syntax for BPF
map") and commit 14e4b9f4289a ("perf trace: Raw augmented syscalls fix
libbpf 1.0+ compatibility") the BPF event support hasn't been well
maintained and it adds considerable complexity in areas like event
parsing, not least as '/' is a separator for event modifiers as well as
in paths.

This patch removes support in the event parser for BPF events and then
the associated functions are removed. This leads to the removal of whole
source files like bpf-loader.c.  Removing support means that augmented
syscalls in perf trace is broken, this will be fixed in a later commit
adding support using BPF skeletons.

The removal of BPF events causes an unused label warning from flex
generated code, so update build to ignore it:

  ```
  util/parse-events-flex.c:2704:1: error: label ‘find_rule’ defined but not used [-Werror=unused-label]
  2704 | find_rule: /* we branch to this label when backing up */
  ```

Committer notes:

Extracted from a larger patch that was also removing the support for
linking with libllvm and libclang, that were an alternative to using an
external clang execution to compile the .c event source code into BPF
bytecode.

Testing it:

  # perf trace -e /home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.c
  event syntax error: '/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.c'
                        \___ Bad event or PMU

  Unabled to find PMU or event on a PMU of 'home'

  Initial error:
  event syntax error: '/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.c'
                        \___ Cannot find PMU `home'. Missing kernel support?
  Run 'perf list' for a list of valid events

   Usage: perf trace [<options>] [<command>]
      or: perf trace [<options>] -- <command> [<options>]
      or: perf trace record [<options>] [<command>]
      or: perf trace record [<options>] -- <command> [<options>]

      -e, --event <event>   event/syscall selector. use 'perf list' to list available events
  #

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Carsten Haitzler <carsten.haitzler@arm.com>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Fangrui Song <maskray@google.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Cc: Tiezhu Yang <yangtiezhu@loongson.cn>
Cc: Tom Rix <trix@redhat.com>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Wang ShaoBo <bobo.shaobowang@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: Yonghong Song <yhs@fb.com>
Cc: YueHaibing <yuehaibing@huawei.com>
Cc: bpf@vger.kernel.org
Cc: llvm@lists.linux.dev
Link: https://lore.kernel.org/r/20230810184853.2860737-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-config.txt      |   33 -
 tools/perf/Documentation/perf-record.txt      |   22 -
 tools/perf/Makefile.config                    |   12 -
 tools/perf/builtin-record.c                   |   45 -
 tools/perf/builtin-trace.c                    |  146 +-
 tools/perf/perf.c                             |    2 -
 tools/perf/tests/.gitignore                   |    5 -
 tools/perf/tests/Build                        |   30 -
 tools/perf/tests/bpf-script-example.c         |   60 -
 tools/perf/tests/bpf-script-test-kbuild.c     |   21 -
 tools/perf/tests/bpf-script-test-prologue.c   |   49 -
 tools/perf/tests/bpf-script-test-relocation.c |   51 -
 tools/perf/tests/bpf.c                        |  390 ----
 tools/perf/tests/builtin-test.c               |    2 -
 tools/perf/tests/llvm.c                       |  219 --
 tools/perf/tests/llvm.h                       |   31 -
 tools/perf/tests/tests.h                      |    2 -
 tools/perf/util/Build                         |    6 +-
 tools/perf/util/bpf-loader.c                  | 1999 -----------------
 tools/perf/util/bpf-loader.h                  |  216 --
 tools/perf/util/config.c                      |    4 -
 tools/perf/util/llvm-utils.c                  |  612 -----
 tools/perf/util/llvm-utils.h                  |   69 -
 tools/perf/util/parse-events.c                |  268 ---
 tools/perf/util/parse-events.h                |   15 -
 tools/perf/util/parse-events.l                |   31 -
 tools/perf/util/parse-events.y                |   44 +-
 27 files changed, 3 insertions(+), 4381 deletions(-)
 delete mode 100644 tools/perf/tests/.gitignore
 delete mode 100644 tools/perf/tests/bpf-script-example.c
 delete mode 100644 tools/perf/tests/bpf-script-test-kbuild.c
 delete mode 100644 tools/perf/tests/bpf-script-test-prologue.c
 delete mode 100644 tools/perf/tests/bpf-script-test-relocation.c
 delete mode 100644 tools/perf/tests/bpf.c
 delete mode 100644 tools/perf/tests/llvm.c
 delete mode 100644 tools/perf/tests/llvm.h
 delete mode 100644 tools/perf/util/bpf-loader.c
 delete mode 100644 tools/perf/util/bpf-loader.h
 delete mode 100644 tools/perf/util/llvm-utils.c
 delete mode 100644 tools/perf/util/llvm-utils.h

diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 1478068ad5dd..0b4e79dbd3f6 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -125,9 +125,6 @@ Given a $HOME/.perfconfig like this:
 		group = true
 		skip-empty = true
 
-	[llvm]
-		dump-obj = true
-		clang-opt = -g
 
 You can hide source code of annotate feature setting the config to false with
 
@@ -657,36 +654,6 @@ ftrace.*::
 		-F option is not specified. Possible values are 'function' and
 		'function_graph'.
 
-llvm.*::
-	llvm.clang-path::
-		Path to clang. If omit, search it from $PATH.
-
-	llvm.clang-bpf-cmd-template::
-		Cmdline template. Below lines show its default value. Environment
-		variable is used to pass options.
-		"$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
-		"-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE "	\
-		"$CLANG_OPTIONS $PERF_BPF_INC_OPTIONS $KERNEL_INC_OPTIONS " \
-		"-Wno-unused-value -Wno-pointer-sign "		\
-		"-working-directory $WORKING_DIR "		\
-		"-c \"$CLANG_SOURCE\" --target=bpf $CLANG_EMIT_LLVM -O2 -o - $LLVM_OPTIONS_PIPE"
-
-	llvm.clang-opt::
-		Options passed to clang.
-
-	llvm.kbuild-dir::
-		kbuild directory. If not set, use /lib/modules/`uname -r`/build.
-		If set to "" deliberately, skip kernel header auto-detector.
-
-	llvm.kbuild-opts::
-		Options passed to 'make' when detecting kernel header options.
-
-	llvm.dump-obj::
-		Enable perf dump BPF object files compiled by LLVM.
-
-	llvm.opts::
-		Options passed to llc.
-
 samples.*::
 
 	samples.context::
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 680396c56bd1..7d362407fb39 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -99,20 +99,6 @@ OPTIONS
           If you want to profile write accesses in [0x1000~1008), just set
           'mem:0x1000/8:w'.
 
-        - a BPF source file (ending in .c) or a precompiled object file (ending
-          in .o) selects one or more BPF events.
-          The BPF program can attach to various perf events based on the ELF section
-          names.
-
-          When processing a '.c' file, perf searches an installed LLVM to compile it
-          into an object file first. Optional clang options can be passed via the
-          '--clang-opt' command line option, e.g.:
-
-            perf record --clang-opt "-DLINUX_VERSION_CODE=0x50000" \
-                        -e tests/bpf-script-example.c
-
-          Note: '--clang-opt' must be placed before '--event/-e'.
-
 	- a group of events surrounded by a pair of brace ("{event1,event2,...}").
 	  Each event is separated by commas and the group should be quoted to
 	  prevent the shell interpretation.  You also need to use --group on
@@ -547,14 +533,6 @@ PERF_RECORD_SWITCH_CPU_WIDE. In some cases (e.g. Intel PT, CoreSight or Arm SPE)
 switch events will be enabled automatically, which can be suppressed by
 by the option --no-switch-events.
 
---clang-path=PATH::
-Path to clang binary to use for compiling BPF scriptlets.
-(enabled when BPF support is on)
-
---clang-opt=OPTIONS::
-Options passed to clang when compiling BPF scriptlets.
-(enabled when BPF support is on)
-
 --vmlinux=PATH::
 Specify vmlinux path which has debuginfo.
 (enabled when BPF prologue is on)
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index e0592ed4c10f..d66b52407e19 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -589,18 +589,6 @@ ifndef NO_LIBELF
 	LIBBPF_STATIC := 1
       endif
     endif
-
-    ifndef NO_DWARF
-      ifdef PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET
-        CFLAGS += -DHAVE_BPF_PROLOGUE
-        $(call detected,CONFIG_BPF_PROLOGUE)
-      else
-        msg := $(warning BPF prologue is not supported by architecture $(SRCARCH), missing regs_query_register_offset());
-      endif
-    else
-      msg := $(warning DWARF support is off, BPF prologue is disabled);
-    endif
-
   endif # NO_LIBBPF
 endif # NO_LIBELF
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index aec18db7ff23..34bb31f08bb5 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -37,8 +37,6 @@
 #include "util/parse-branch-options.h"
 #include "util/parse-regs-options.h"
 #include "util/perf_api_probe.h"
-#include "util/llvm-utils.h"
-#include "util/bpf-loader.h"
 #include "util/trigger.h"
 #include "util/perf-hooks.h"
 #include "util/cpu-set-sched.h"
@@ -2465,16 +2463,6 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		}
 	}
 
-	err = bpf__apply_obj_config();
-	if (err) {
-		char errbuf[BUFSIZ];
-
-		bpf__strerror_apply_obj_config(err, errbuf, sizeof(errbuf));
-		pr_err("ERROR: Apply config to BPF failed: %s\n",
-			 errbuf);
-		goto out_free_threads;
-	}
-
 	/*
 	 * Normally perf_session__new would do this, but it doesn't have the
 	 * evlist.
@@ -3486,10 +3474,6 @@ static struct option __record_options[] = {
 		    "collect kernel callchains"),
 	OPT_BOOLEAN(0, "user-callchains", &record.opts.user_callchains,
 		    "collect user callchains"),
-	OPT_STRING(0, "clang-path", &llvm_param.clang_path, "clang path",
-		   "clang binary to use for compiling BPF scriptlets"),
-	OPT_STRING(0, "clang-opt", &llvm_param.clang_opt, "clang options",
-		   "options passed to clang when compiling BPF scriptlets"),
 	OPT_STRING(0, "vmlinux", &symbol_conf.vmlinux_name,
 		   "file", "vmlinux pathname"),
 	OPT_BOOLEAN(0, "buildid-all", &record.buildid_all,
@@ -3967,27 +3951,6 @@ int cmd_record(int argc, const char **argv)
 
 	setlocale(LC_ALL, "");
 
-#ifndef HAVE_LIBBPF_SUPPORT
-# define set_nobuild(s, l, c) set_option_nobuild(record_options, s, l, "NO_LIBBPF=1", c)
-	set_nobuild('\0', "clang-path", true);
-	set_nobuild('\0', "clang-opt", true);
-# undef set_nobuild
-#endif
-
-#ifndef HAVE_BPF_PROLOGUE
-# if !defined (HAVE_DWARF_SUPPORT)
-#  define REASON  "NO_DWARF=1"
-# elif !defined (HAVE_LIBBPF_SUPPORT)
-#  define REASON  "NO_LIBBPF=1"
-# else
-#  define REASON  "this architecture doesn't support BPF prologue"
-# endif
-# define set_nobuild(s, l, c) set_option_nobuild(record_options, s, l, REASON, c)
-	set_nobuild('\0', "vmlinux", true);
-# undef set_nobuild
-# undef REASON
-#endif
-
 #ifndef HAVE_BPF_SKEL
 # define set_nobuild(s, l, m, c) set_option_nobuild(record_options, s, l, m, c)
 	set_nobuild('\0', "off-cpu", "no BUILD_BPF_SKEL=1", true);
@@ -4116,14 +4079,6 @@ int cmd_record(int argc, const char **argv)
 	if (dry_run)
 		goto out;
 
-	err = bpf__setup_stdout(rec->evlist);
-	if (err) {
-		bpf__strerror_setup_stdout(rec->evlist, err, errbuf, sizeof(errbuf));
-		pr_err("ERROR: Setup BPF stdout failed: %s\n",
-			 errbuf);
-		goto out;
-	}
-
 	err = -ENOMEM;
 
 	if (rec->no_buildid_cache || rec->no_buildid) {
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 7ece2521efb6..59862467e781 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -18,6 +18,7 @@
 #include <api/fs/tracing_path.h>
 #ifdef HAVE_LIBBPF_SUPPORT
 #include <bpf/bpf.h>
+#include <bpf/libbpf.h>
 #endif
 #include "util/bpf_map.h"
 #include "util/rlimit.h"
@@ -53,7 +54,6 @@
 #include "trace/beauty/beauty.h"
 #include "trace-event.h"
 #include "util/parse-events.h"
-#include "util/bpf-loader.h"
 #include "util/tracepoint.h"
 #include "callchain.h"
 #include "print_binary.h"
@@ -3287,17 +3287,6 @@ static struct bpf_map *trace__find_bpf_map_by_name(struct trace *trace, const ch
 	return bpf_object__find_map_by_name(trace->bpf_obj, name);
 }
 
-static void trace__set_bpf_map_filtered_pids(struct trace *trace)
-{
-	trace->filter_pids.map = trace__find_bpf_map_by_name(trace, "pids_filtered");
-}
-
-static void trace__set_bpf_map_syscalls(struct trace *trace)
-{
-	trace->syscalls.prog_array.sys_enter = trace__find_bpf_map_by_name(trace, "syscalls_sys_enter");
-	trace->syscalls.prog_array.sys_exit  = trace__find_bpf_map_by_name(trace, "syscalls_sys_exit");
-}
-
 static struct bpf_program *trace__find_bpf_program_by_title(struct trace *trace, const char *name)
 {
 	struct bpf_program *pos, *prog = NULL;
@@ -3553,25 +3542,6 @@ static int trace__init_syscalls_bpf_prog_array_maps(struct trace *trace)
 	return err;
 }
 
-static void trace__delete_augmented_syscalls(struct trace *trace)
-{
-	struct evsel *evsel, *tmp;
-
-	evlist__remove(trace->evlist, trace->syscalls.events.augmented);
-	evsel__delete(trace->syscalls.events.augmented);
-	trace->syscalls.events.augmented = NULL;
-
-	evlist__for_each_entry_safe(trace->evlist, tmp, evsel) {
-		if (evsel->bpf_obj == trace->bpf_obj) {
-			evlist__remove(trace->evlist, evsel);
-			evsel__delete(evsel);
-		}
-
-	}
-
-	bpf_object__close(trace->bpf_obj);
-	trace->bpf_obj = NULL;
-}
 #else // HAVE_LIBBPF_SUPPORT
 static struct bpf_map *trace__find_bpf_map_by_name(struct trace *trace __maybe_unused,
 						   const char *name __maybe_unused)
@@ -3579,45 +3549,12 @@ static struct bpf_map *trace__find_bpf_map_by_name(struct trace *trace __maybe_u
 	return NULL;
 }
 
-static void trace__set_bpf_map_filtered_pids(struct trace *trace __maybe_unused)
-{
-}
-
-static void trace__set_bpf_map_syscalls(struct trace *trace __maybe_unused)
-{
-}
-
-static struct bpf_program *trace__find_bpf_program_by_title(struct trace *trace __maybe_unused,
-							    const char *name __maybe_unused)
-{
-	return NULL;
-}
-
 static int trace__init_syscalls_bpf_prog_array_maps(struct trace *trace __maybe_unused)
 {
 	return 0;
 }
-
-static void trace__delete_augmented_syscalls(struct trace *trace __maybe_unused)
-{
-}
 #endif // HAVE_LIBBPF_SUPPORT
 
-static bool trace__only_augmented_syscalls_evsels(struct trace *trace)
-{
-	struct evsel *evsel;
-
-	evlist__for_each_entry(trace->evlist, evsel) {
-		if (evsel == trace->syscalls.events.augmented ||
-		    evsel->bpf_obj == trace->bpf_obj)
-			continue;
-
-		return false;
-	}
-
-	return true;
-}
-
 static int trace__set_ev_qualifier_filter(struct trace *trace)
 {
 	if (trace->syscalls.events.sys_enter)
@@ -3981,16 +3918,6 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	if (err < 0)
 		goto out_error_open;
 
-	err = bpf__apply_obj_config();
-	if (err) {
-		char errbuf[BUFSIZ];
-
-		bpf__strerror_apply_obj_config(err, errbuf, sizeof(errbuf));
-		pr_err("ERROR: Apply config to BPF failed: %s\n",
-			 errbuf);
-		goto out_error_open;
-	}
-
 	err = trace__set_filter_pids(trace);
 	if (err < 0)
 		goto out_error_mem;
@@ -4922,77 +4849,6 @@ int cmd_trace(int argc, const char **argv)
 				       "cgroup monitoring only available in system-wide mode");
 	}
 
-	evsel = bpf__setup_output_event(trace.evlist, "__augmented_syscalls__");
-	if (IS_ERR(evsel)) {
-		bpf__strerror_setup_output_event(trace.evlist, PTR_ERR(evsel), bf, sizeof(bf));
-		pr_err("ERROR: Setup trace syscalls enter failed: %s\n", bf);
-		goto out;
-	}
-
-	if (evsel) {
-		trace.syscalls.events.augmented = evsel;
-
-		evsel = evlist__find_tracepoint_by_name(trace.evlist, "raw_syscalls:sys_enter");
-		if (evsel == NULL) {
-			pr_err("ERROR: raw_syscalls:sys_enter not found in the augmented BPF object\n");
-			goto out;
-		}
-
-		if (evsel->bpf_obj == NULL) {
-			pr_err("ERROR: raw_syscalls:sys_enter not associated to a BPF object\n");
-			goto out;
-		}
-
-		trace.bpf_obj = evsel->bpf_obj;
-
-		/*
-		 * If we have _just_ the augmenter event but don't have a
-		 * explicit --syscalls, then assume we want all strace-like
-		 * syscalls:
-		 */
-		if (!trace.trace_syscalls && trace__only_augmented_syscalls_evsels(&trace))
-			trace.trace_syscalls = true;
-		/*
-		 * So, if we have a syscall augmenter, but trace_syscalls, aka
-		 * strace-like syscall tracing is not set, then we need to trow
-		 * away the augmenter, i.e. all the events that were created
-		 * from that BPF object file.
-		 *
-		 * This is more to fix the current .perfconfig trace.add_events
-		 * style of setting up the strace-like eBPF based syscall point
-		 * payload augmenter.
-		 *
-		 * All this complexity will be avoided by adding an alternative
-		 * to trace.add_events in the form of
-		 * trace.bpf_augmented_syscalls, that will be only parsed if we
-		 * need it.
-		 *
-		 * .perfconfig trace.add_events is still useful if we want, for
-		 * instance, have msr_write.msr in some .perfconfig profile based
-		 * 'perf trace --config determinism.profile' mode, where for some
-		 * particular goal/workload type we want a set of events and
-		 * output mode (with timings, etc) instead of having to add
-		 * all via the command line.
-		 *
-		 * Also --config to specify an alternate .perfconfig file needs
-		 * to be implemented.
-		 */
-		if (!trace.trace_syscalls) {
-			trace__delete_augmented_syscalls(&trace);
-		} else {
-			trace__set_bpf_map_filtered_pids(&trace);
-			trace__set_bpf_map_syscalls(&trace);
-			trace.syscalls.unaugmented_prog = trace__find_bpf_program_by_title(&trace, "!raw_syscalls:unaugmented");
-		}
-	}
-
-	err = bpf__setup_stdout(trace.evlist);
-	if (err) {
-		bpf__strerror_setup_stdout(trace.evlist, err, bf, sizeof(bf));
-		pr_err("ERROR: Setup BPF stdout failed: %s\n", bf);
-		goto out;
-	}
-
 	err = -1;
 
 	if (map_dump_str) {
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 38cae4721583..d3fc8090413c 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -18,7 +18,6 @@
 #include <subcmd/run-command.h>
 #include "util/parse-events.h"
 #include <subcmd/parse-options.h>
-#include "util/bpf-loader.h"
 #include "util/debug.h"
 #include "util/event.h"
 #include "util/util.h" // usage()
@@ -324,7 +323,6 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 	perf_config__exit();
 	exit_browser(status);
 	perf_env__exit(&perf_env);
-	bpf__clear();
 
 	if (status)
 		return status & 0xff;
diff --git a/tools/perf/tests/.gitignore b/tools/perf/tests/.gitignore
deleted file mode 100644
index d053b325f728..000000000000
--- a/tools/perf/tests/.gitignore
+++ /dev/null
@@ -1,5 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-llvm-src-base.c
-llvm-src-kbuild.c
-llvm-src-prologue.c
-llvm-src-relocation.c
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 52df5923a8b9..63d5e6d5f165 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -37,8 +37,6 @@ perf-y += sample-parsing.o
 perf-y += parse-no-sample-id-all.o
 perf-y += kmod-path.o
 perf-y += thread-map.o
-perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o llvm-src-prologue.o llvm-src-relocation.o
-perf-y += bpf.o
 perf-y += topology.o
 perf-y += mem.o
 perf-y += cpumap.o
@@ -69,34 +67,6 @@ perf-y += sigtrap.o
 perf-y += event_groups.o
 perf-y += symbols.o
 
-$(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build
-	$(call rule_mkdir)
-	$(Q)echo '#include <tests/llvm.h>' > $@
-	$(Q)echo 'const char test_llvm__bpf_base_prog[] =' >> $@
-	$(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@
-	$(Q)echo ';' >> $@
-
-$(OUTPUT)tests/llvm-src-kbuild.c: tests/bpf-script-test-kbuild.c tests/Build
-	$(call rule_mkdir)
-	$(Q)echo '#include <tests/llvm.h>' > $@
-	$(Q)echo 'const char test_llvm__bpf_test_kbuild_prog[] =' >> $@
-	$(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@
-	$(Q)echo ';' >> $@
-
-$(OUTPUT)tests/llvm-src-prologue.c: tests/bpf-script-test-prologue.c tests/Build
-	$(call rule_mkdir)
-	$(Q)echo '#include <tests/llvm.h>' > $@
-	$(Q)echo 'const char test_llvm__bpf_test_prologue_prog[] =' >> $@
-	$(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@
-	$(Q)echo ';' >> $@
-
-$(OUTPUT)tests/llvm-src-relocation.c: tests/bpf-script-test-relocation.c tests/Build
-	$(call rule_mkdir)
-	$(Q)echo '#include <tests/llvm.h>' > $@
-	$(Q)echo 'const char test_llvm__bpf_test_relocation[] =' >> $@
-	$(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@
-	$(Q)echo ';' >> $@
-
 ifeq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc))
 perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
 endif
diff --git a/tools/perf/tests/bpf-script-example.c b/tools/perf/tests/bpf-script-example.c
deleted file mode 100644
index b638cc99d5ae..000000000000
--- a/tools/perf/tests/bpf-script-example.c
+++ /dev/null
@@ -1,60 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * bpf-script-example.c
- * Test basic LLVM building
- */
-#ifndef LINUX_VERSION_CODE
-# error Need LINUX_VERSION_CODE
-# error Example: for 4.2 kernel, put 'clang-opt="-DLINUX_VERSION_CODE=0x40200" into llvm section of ~/.perfconfig'
-#endif
-#define BPF_ANY 0
-#define BPF_MAP_TYPE_ARRAY 2
-#define BPF_FUNC_map_lookup_elem 1
-#define BPF_FUNC_map_update_elem 2
-
-static void *(*bpf_map_lookup_elem)(void *map, void *key) =
-	(void *) BPF_FUNC_map_lookup_elem;
-static void *(*bpf_map_update_elem)(void *map, void *key, void *value, int flags) =
-	(void *) BPF_FUNC_map_update_elem;
-
-/*
- * Following macros are taken from tools/lib/bpf/bpf_helpers.h,
- * and are used to create BTF defined maps. It is easier to take
- * 2 simple macros, than being able to include above header in
- * runtime.
- *
- * __uint - defines integer attribute of BTF map definition,
- * Such attributes are represented using a pointer to an array,
- * in which dimensionality of array encodes specified integer
- * value.
- *
- * __type - defines pointer variable with typeof(val) type for
- * attributes like key or value, which will be defined by the
- * size of the type.
- */
-#define __uint(name, val) int (*name)[val]
-#define __type(name, val) typeof(val) *name
-
-#define SEC(NAME) __attribute__((section(NAME), used))
-struct {
-	__uint(type, BPF_MAP_TYPE_ARRAY);
-	__uint(max_entries, 1);
-	__type(key, int);
-	__type(value, int);
-} flip_table SEC(".maps");
-
-SEC("syscalls:sys_enter_epoll_pwait")
-int bpf_func__SyS_epoll_pwait(void *ctx)
-{
-	int ind =0;
-	int *flag = bpf_map_lookup_elem(&flip_table, &ind);
-	int new_flag;
-	if (!flag)
-		return 0;
-	/* flip flag and store back */
-	new_flag = !*flag;
-	bpf_map_update_elem(&flip_table, &ind, &new_flag, BPF_ANY);
-	return new_flag;
-}
-char _license[] SEC("license") = "GPL";
-int _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/tools/perf/tests/bpf-script-test-kbuild.c b/tools/perf/tests/bpf-script-test-kbuild.c
deleted file mode 100644
index 219673aa278f..000000000000
--- a/tools/perf/tests/bpf-script-test-kbuild.c
+++ /dev/null
@@ -1,21 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * bpf-script-test-kbuild.c
- * Test include from kernel header
- */
-#ifndef LINUX_VERSION_CODE
-# error Need LINUX_VERSION_CODE
-# error Example: for 4.2 kernel, put 'clang-opt="-DLINUX_VERSION_CODE=0x40200" into llvm section of ~/.perfconfig'
-#endif
-#define SEC(NAME) __attribute__((section(NAME), used))
-
-#include <uapi/linux/fs.h>
-
-SEC("func=vfs_llseek")
-int bpf_func__vfs_llseek(void *ctx)
-{
-	return 0;
-}
-
-char _license[] SEC("license") = "GPL";
-int _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/tools/perf/tests/bpf-script-test-prologue.c b/tools/perf/tests/bpf-script-test-prologue.c
deleted file mode 100644
index 91778b5c6125..000000000000
--- a/tools/perf/tests/bpf-script-test-prologue.c
+++ /dev/null
@@ -1,49 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * bpf-script-test-prologue.c
- * Test BPF prologue
- */
-#ifndef LINUX_VERSION_CODE
-# error Need LINUX_VERSION_CODE
-# error Example: for 4.2 kernel, put 'clang-opt="-DLINUX_VERSION_CODE=0x40200" into llvm section of ~/.perfconfig'
-#endif
-#define SEC(NAME) __attribute__((section(NAME), used))
-
-#include <uapi/linux/fs.h>
-
-/*
- * If CONFIG_PROFILE_ALL_BRANCHES is selected,
- * 'if' is redefined after include kernel header.
- * Recover 'if' for BPF object code.
- */
-#ifdef if
-# undef if
-#endif
-
-typedef unsigned int __bitwise fmode_t;
-
-#define FMODE_READ		0x1
-#define FMODE_WRITE		0x2
-
-static void (*bpf_trace_printk)(const char *fmt, int fmt_size, ...) =
-	(void *) 6;
-
-SEC("func=null_lseek file->f_mode offset orig")
-int bpf_func__null_lseek(void *ctx, int err, unsigned long _f_mode,
-			 unsigned long offset, unsigned long orig)
-{
-	fmode_t f_mode = (fmode_t)_f_mode;
-
-	if (err)
-		return 0;
-	if (f_mode & FMODE_WRITE)
-		return 0;
-	if (offset & 1)
-		return 0;
-	if (orig == SEEK_CUR)
-		return 0;
-	return 1;
-}
-
-char _license[] SEC("license") = "GPL";
-int _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/tools/perf/tests/bpf-script-test-relocation.c b/tools/perf/tests/bpf-script-test-relocation.c
deleted file mode 100644
index 74006e4b2d24..000000000000
--- a/tools/perf/tests/bpf-script-test-relocation.c
+++ /dev/null
@@ -1,51 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * bpf-script-test-relocation.c
- * Test BPF loader checking relocation
- */
-#ifndef LINUX_VERSION_CODE
-# error Need LINUX_VERSION_CODE
-# error Example: for 4.2 kernel, put 'clang-opt="-DLINUX_VERSION_CODE=0x40200" into llvm section of ~/.perfconfig'
-#endif
-#define BPF_ANY 0
-#define BPF_MAP_TYPE_ARRAY 2
-#define BPF_FUNC_map_lookup_elem 1
-#define BPF_FUNC_map_update_elem 2
-
-static void *(*bpf_map_lookup_elem)(void *map, void *key) =
-	(void *) BPF_FUNC_map_lookup_elem;
-static void *(*bpf_map_update_elem)(void *map, void *key, void *value, int flags) =
-	(void *) BPF_FUNC_map_update_elem;
-
-struct bpf_map_def {
-	unsigned int type;
-	unsigned int key_size;
-	unsigned int value_size;
-	unsigned int max_entries;
-};
-
-#define SEC(NAME) __attribute__((section(NAME), used))
-struct bpf_map_def SEC("maps") my_table = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 1,
-};
-
-int this_is_a_global_val;
-
-SEC("func=sys_write")
-int bpf_func__sys_write(void *ctx)
-{
-	int key = 0;
-	int value = 0;
-
-	/*
-	 * Incorrect relocation. Should not allow this program be
-	 * loaded into kernel.
-	 */
-	bpf_map_update_elem(&this_is_a_global_val, &key, &value, 0);
-	return 0;
-}
-char _license[] SEC("license") = "GPL";
-int _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
deleted file mode 100644
index 9ccecd873ecd..000000000000
--- a/tools/perf/tests/bpf.c
+++ /dev/null
@@ -1,390 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <errno.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <sys/epoll.h>
-#include <sys/types.h>
-#include <sys/stat.h>
-#include <fcntl.h>
-#include <util/record.h>
-#include <util/util.h>
-#include <util/bpf-loader.h>
-#include <util/evlist.h>
-#include <linux/filter.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <api/fs/fs.h>
-#include <perf/mmap.h>
-#include "tests.h"
-#include "llvm.h"
-#include "debug.h"
-#include "parse-events.h"
-#include "util/mmap.h"
-#define NR_ITERS       111
-#define PERF_TEST_BPF_PATH "/sys/fs/bpf/perf_test"
-
-#if defined(HAVE_LIBBPF_SUPPORT) && defined(HAVE_LIBTRACEEVENT)
-#include <linux/bpf.h>
-#include <bpf/bpf.h>
-
-static int epoll_pwait_loop(void)
-{
-	struct epoll_event events;
-	int i;
-
-	/* Should fail NR_ITERS times */
-	for (i = 0; i < NR_ITERS; i++)
-		epoll_pwait(-(i + 1), &events, 0, 0, NULL);
-	return 0;
-}
-
-#ifdef HAVE_BPF_PROLOGUE
-
-static int llseek_loop(void)
-{
-	int fds[2], i;
-
-	fds[0] = open("/dev/null", O_RDONLY);
-	fds[1] = open("/dev/null", O_RDWR);
-
-	if (fds[0] < 0 || fds[1] < 0)
-		return -1;
-
-	for (i = 0; i < NR_ITERS; i++) {
-		lseek(fds[i % 2], i, (i / 2) % 2 ? SEEK_CUR : SEEK_SET);
-		lseek(fds[(i + 1) % 2], i, (i / 2) % 2 ? SEEK_CUR : SEEK_SET);
-	}
-	close(fds[0]);
-	close(fds[1]);
-	return 0;
-}
-
-#endif
-
-static struct {
-	enum test_llvm__testcase prog_id;
-	const char *name;
-	const char *msg_compile_fail;
-	const char *msg_load_fail;
-	int (*target_func)(void);
-	int expect_result;
-	bool	pin;
-} bpf_testcase_table[] = {
-	{
-		.prog_id	  = LLVM_TESTCASE_BASE,
-		.name		  = "[basic_bpf_test]",
-		.msg_compile_fail = "fix 'perf test LLVM' first",
-		.msg_load_fail	  = "load bpf object failed",
-		.target_func	  = &epoll_pwait_loop,
-		.expect_result	  = (NR_ITERS + 1) / 2,
-	},
-	{
-		.prog_id	  = LLVM_TESTCASE_BASE,
-		.name		  = "[bpf_pinning]",
-		.msg_compile_fail = "fix kbuild first",
-		.msg_load_fail	  = "check your vmlinux setting?",
-		.target_func	  = &epoll_pwait_loop,
-		.expect_result	  = (NR_ITERS + 1) / 2,
-		.pin		  = true,
-	},
-#ifdef HAVE_BPF_PROLOGUE
-	{
-		.prog_id	  = LLVM_TESTCASE_BPF_PROLOGUE,
-		.name		  = "[bpf_prologue_test]",
-		.msg_compile_fail = "fix kbuild first",
-		.msg_load_fail	  = "check your vmlinux setting?",
-		.target_func	  = &llseek_loop,
-		.expect_result	  = (NR_ITERS + 1) / 4,
-	},
-#endif
-};
-
-static int do_test(struct bpf_object *obj, int (*func)(void),
-		   int expect)
-{
-	struct record_opts opts = {
-		.target = {
-			.uid = UINT_MAX,
-			.uses_mmap = true,
-		},
-		.freq	      = 0,
-		.mmap_pages   = 256,
-		.default_interval = 1,
-	};
-
-	char pid[16];
-	char sbuf[STRERR_BUFSIZE];
-	struct evlist *evlist;
-	int i, ret = TEST_FAIL, err = 0, count = 0;
-
-	struct parse_events_state parse_state;
-	struct parse_events_error parse_error;
-
-	parse_events_error__init(&parse_error);
-	bzero(&parse_state, sizeof(parse_state));
-	parse_state.error = &parse_error;
-	INIT_LIST_HEAD(&parse_state.list);
-
-	err = parse_events_load_bpf_obj(&parse_state, &parse_state.list, obj, NULL, NULL);
-	parse_events_error__exit(&parse_error);
-	if (err == -ENODATA) {
-		pr_debug("Failed to add events selected by BPF, debuginfo package not installed\n");
-		return TEST_SKIP;
-	}
-	if (err || list_empty(&parse_state.list)) {
-		pr_debug("Failed to add events selected by BPF\n");
-		return TEST_FAIL;
-	}
-
-	snprintf(pid, sizeof(pid), "%d", getpid());
-	pid[sizeof(pid) - 1] = '\0';
-	opts.target.tid = opts.target.pid = pid;
-
-	/* Instead of evlist__new_default, don't add default events */
-	evlist = evlist__new();
-	if (!evlist) {
-		pr_debug("Not enough memory to create evlist\n");
-		return TEST_FAIL;
-	}
-
-	err = evlist__create_maps(evlist, &opts.target);
-	if (err < 0) {
-		pr_debug("Not enough memory to create thread/cpu maps\n");
-		goto out_delete_evlist;
-	}
-
-	evlist__splice_list_tail(evlist, &parse_state.list);
-
-	evlist__config(evlist, &opts, NULL);
-
-	err = evlist__open(evlist);
-	if (err < 0) {
-		pr_debug("perf_evlist__open: %s\n",
-			 str_error_r(errno, sbuf, sizeof(sbuf)));
-		goto out_delete_evlist;
-	}
-
-	err = evlist__mmap(evlist, opts.mmap_pages);
-	if (err < 0) {
-		pr_debug("evlist__mmap: %s\n",
-			 str_error_r(errno, sbuf, sizeof(sbuf)));
-		goto out_delete_evlist;
-	}
-
-	evlist__enable(evlist);
-	(*func)();
-	evlist__disable(evlist);
-
-	for (i = 0; i < evlist->core.nr_mmaps; i++) {
-		union perf_event *event;
-		struct mmap *md;
-
-		md = &evlist->mmap[i];
-		if (perf_mmap__read_init(&md->core) < 0)
-			continue;
-
-		while ((event = perf_mmap__read_event(&md->core)) != NULL) {
-			const u32 type = event->header.type;
-
-			if (type == PERF_RECORD_SAMPLE)
-				count ++;
-		}
-		perf_mmap__read_done(&md->core);
-	}
-
-	if (count != expect * evlist->core.nr_entries) {
-		pr_debug("BPF filter result incorrect, expected %d, got %d samples\n", expect * evlist->core.nr_entries, count);
-		goto out_delete_evlist;
-	}
-
-	ret = TEST_OK;
-
-out_delete_evlist:
-	evlist__delete(evlist);
-	return ret;
-}
-
-static struct bpf_object *
-prepare_bpf(void *obj_buf, size_t obj_buf_sz, const char *name)
-{
-	struct bpf_object *obj;
-
-	obj = bpf__prepare_load_buffer(obj_buf, obj_buf_sz, name);
-	if (IS_ERR(obj)) {
-		pr_debug("Compile BPF program failed.\n");
-		return NULL;
-	}
-	return obj;
-}
-
-static int __test__bpf(int idx)
-{
-	int ret;
-	void *obj_buf;
-	size_t obj_buf_sz;
-	struct bpf_object *obj;
-
-	ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
-				       bpf_testcase_table[idx].prog_id,
-				       false, NULL);
-	if (ret != TEST_OK || !obj_buf || !obj_buf_sz) {
-		pr_debug("Unable to get BPF object, %s\n",
-			 bpf_testcase_table[idx].msg_compile_fail);
-		if ((idx == 0) || (ret == TEST_SKIP))
-			return TEST_SKIP;
-		else
-			return TEST_FAIL;
-	}
-
-	obj = prepare_bpf(obj_buf, obj_buf_sz,
-			  bpf_testcase_table[idx].name);
-	if ((!!bpf_testcase_table[idx].target_func) != (!!obj)) {
-		if (!obj)
-			pr_debug("Fail to load BPF object: %s\n",
-				 bpf_testcase_table[idx].msg_load_fail);
-		else
-			pr_debug("Success unexpectedly: %s\n",
-				 bpf_testcase_table[idx].msg_load_fail);
-		ret = TEST_FAIL;
-		goto out;
-	}
-
-	if (obj) {
-		ret = do_test(obj,
-			      bpf_testcase_table[idx].target_func,
-			      bpf_testcase_table[idx].expect_result);
-		if (ret != TEST_OK)
-			goto out;
-		if (bpf_testcase_table[idx].pin) {
-			int err;
-
-			if (!bpf_fs__mount()) {
-				pr_debug("BPF filesystem not mounted\n");
-				ret = TEST_FAIL;
-				goto out;
-			}
-			err = mkdir(PERF_TEST_BPF_PATH, 0777);
-			if (err && errno != EEXIST) {
-				pr_debug("Failed to make perf_test dir: %s\n",
-					 strerror(errno));
-				ret = TEST_FAIL;
-				goto out;
-			}
-			if (bpf_object__pin(obj, PERF_TEST_BPF_PATH))
-				ret = TEST_FAIL;
-			if (rm_rf(PERF_TEST_BPF_PATH))
-				ret = TEST_FAIL;
-		}
-	}
-
-out:
-	free(obj_buf);
-	bpf__clear();
-	return ret;
-}
-
-static int check_env(void)
-{
-	LIBBPF_OPTS(bpf_prog_load_opts, opts);
-	int err;
-	char license[] = "GPL";
-
-	struct bpf_insn insns[] = {
-		BPF_MOV64_IMM(BPF_REG_0, 1),
-		BPF_EXIT_INSN(),
-	};
-
-	err = fetch_kernel_version(&opts.kern_version, NULL, 0);
-	if (err) {
-		pr_debug("Unable to get kernel version\n");
-		return err;
-	}
-	err = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, license, insns,
-			    ARRAY_SIZE(insns), &opts);
-	if (err < 0) {
-		pr_err("Missing basic BPF support, skip this test: %s\n",
-		       strerror(errno));
-		return err;
-	}
-	close(err);
-
-	return 0;
-}
-
-static int test__bpf(int i)
-{
-	int err;
-
-	if (i < 0 || i >= (int)ARRAY_SIZE(bpf_testcase_table))
-		return TEST_FAIL;
-
-	if (geteuid() != 0) {
-		pr_debug("Only root can run BPF test\n");
-		return TEST_SKIP;
-	}
-
-	if (check_env())
-		return TEST_SKIP;
-
-	err = __test__bpf(i);
-	return err;
-}
-#endif
-
-static int test__basic_bpf_test(struct test_suite *test __maybe_unused,
-				int subtest __maybe_unused)
-{
-#if defined(HAVE_LIBBPF_SUPPORT) && defined(HAVE_LIBTRACEEVENT)
-	return test__bpf(0);
-#else
-	pr_debug("Skip BPF test because BPF or libtraceevent support is not compiled\n");
-	return TEST_SKIP;
-#endif
-}
-
-static int test__bpf_pinning(struct test_suite *test __maybe_unused,
-			     int subtest __maybe_unused)
-{
-#if defined(HAVE_LIBBPF_SUPPORT) && defined(HAVE_LIBTRACEEVENT)
-	return test__bpf(1);
-#else
-	pr_debug("Skip BPF test because BPF or libtraceevent support is not compiled\n");
-	return TEST_SKIP;
-#endif
-}
-
-static int test__bpf_prologue_test(struct test_suite *test __maybe_unused,
-				   int subtest __maybe_unused)
-{
-#if defined(HAVE_LIBBPF_SUPPORT) && defined(HAVE_BPF_PROLOGUE) && defined(HAVE_LIBTRACEEVENT)
-	return test__bpf(2);
-#else
-	pr_debug("Skip BPF test because BPF or libtraceevent support is not compiled\n");
-	return TEST_SKIP;
-#endif
-}
-
-
-static struct test_case bpf_tests[] = {
-#if defined(HAVE_LIBBPF_SUPPORT) && defined(HAVE_LIBTRACEEVENT)
-	TEST_CASE("Basic BPF filtering", basic_bpf_test),
-	TEST_CASE_REASON("BPF pinning", bpf_pinning,
-			"clang isn't installed or environment missing BPF support"),
-#ifdef HAVE_BPF_PROLOGUE
-	TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test,
-			"clang/debuginfo isn't installed or environment missing BPF support"),
-#else
-	TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test, "not compiled in"),
-#endif
-#else
-	TEST_CASE_REASON("Basic BPF filtering", basic_bpf_test, "not compiled in or missing libtraceevent support"),
-	TEST_CASE_REASON("BPF pinning", bpf_pinning, "not compiled in or missing libtraceevent support"),
-	TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test, "not compiled in or missing libtraceevent support"),
-#endif
-	{ .name = NULL, }
-};
-
-struct test_suite suite__bpf = {
-	.desc = "BPF filter",
-	.test_cases = bpf_tests,
-};
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 0f3691fd31c2..0ad18cf6dd22 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -92,9 +92,7 @@ static struct test_suite *generic_tests[] = {
 	&suite__fdarray__add,
 	&suite__kmod_path__parse,
 	&suite__thread_map,
-	&suite__llvm,
 	&suite__session_topology,
-	&suite__bpf,
 	&suite__thread_map_synthesize,
 	&suite__thread_map_remove,
 	&suite__cpu_map,
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
deleted file mode 100644
index 0bc25a56cfef..000000000000
--- a/tools/perf/tests/llvm.c
+++ /dev/null
@@ -1,219 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include "tests.h"
-#include "debug.h"
-
-#ifdef HAVE_LIBBPF_SUPPORT
-#include <bpf/libbpf.h>
-#include <util/llvm-utils.h>
-#include "llvm.h"
-static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz)
-{
-	struct bpf_object *obj;
-
-	obj = bpf_object__open_mem(obj_buf, obj_buf_sz, NULL);
-	if (libbpf_get_error(obj))
-		return TEST_FAIL;
-	bpf_object__close(obj);
-	return TEST_OK;
-}
-
-static struct {
-	const char *source;
-	const char *desc;
-	bool should_load_fail;
-} bpf_source_table[__LLVM_TESTCASE_MAX] = {
-	[LLVM_TESTCASE_BASE] = {
-		.source = test_llvm__bpf_base_prog,
-		.desc = "Basic BPF llvm compile",
-	},
-	[LLVM_TESTCASE_KBUILD] = {
-		.source = test_llvm__bpf_test_kbuild_prog,
-		.desc = "kbuild searching",
-	},
-	[LLVM_TESTCASE_BPF_PROLOGUE] = {
-		.source = test_llvm__bpf_test_prologue_prog,
-		.desc = "Compile source for BPF prologue generation",
-	},
-	[LLVM_TESTCASE_BPF_RELOCATION] = {
-		.source = test_llvm__bpf_test_relocation,
-		.desc = "Compile source for BPF relocation",
-		.should_load_fail = true,
-	},
-};
-
-int
-test_llvm__fetch_bpf_obj(void **p_obj_buf,
-			 size_t *p_obj_buf_sz,
-			 enum test_llvm__testcase idx,
-			 bool force,
-			 bool *should_load_fail)
-{
-	const char *source;
-	const char *desc;
-	const char *tmpl_old, *clang_opt_old;
-	char *tmpl_new = NULL, *clang_opt_new = NULL;
-	int err, old_verbose, ret = TEST_FAIL;
-
-	if (idx >= __LLVM_TESTCASE_MAX)
-		return TEST_FAIL;
-
-	source = bpf_source_table[idx].source;
-	desc = bpf_source_table[idx].desc;
-	if (should_load_fail)
-		*should_load_fail = bpf_source_table[idx].should_load_fail;
-
-	/*
-	 * Skip this test if user's .perfconfig doesn't set [llvm] section
-	 * and clang is not found in $PATH
-	 */
-	if (!force && (!llvm_param.user_set_param &&
-		       llvm__search_clang())) {
-		pr_debug("No clang, skip this test\n");
-		return TEST_SKIP;
-	}
-
-	/*
-	 * llvm is verbosity when error. Suppress all error output if
-	 * not 'perf test -v'.
-	 */
-	old_verbose = verbose;
-	if (verbose == 0)
-		verbose = -1;
-
-	*p_obj_buf = NULL;
-	*p_obj_buf_sz = 0;
-
-	if (!llvm_param.clang_bpf_cmd_template)
-		goto out;
-
-	if (!llvm_param.clang_opt)
-		llvm_param.clang_opt = strdup("");
-
-	err = asprintf(&tmpl_new, "echo '%s' | %s%s", source,
-		       llvm_param.clang_bpf_cmd_template,
-		       old_verbose ? "" : " 2>/dev/null");
-	if (err < 0)
-		goto out;
-	err = asprintf(&clang_opt_new, "-xc %s", llvm_param.clang_opt);
-	if (err < 0)
-		goto out;
-
-	tmpl_old = llvm_param.clang_bpf_cmd_template;
-	llvm_param.clang_bpf_cmd_template = tmpl_new;
-	clang_opt_old = llvm_param.clang_opt;
-	llvm_param.clang_opt = clang_opt_new;
-
-	err = llvm__compile_bpf("-", p_obj_buf, p_obj_buf_sz);
-
-	llvm_param.clang_bpf_cmd_template = tmpl_old;
-	llvm_param.clang_opt = clang_opt_old;
-
-	verbose = old_verbose;
-	if (err)
-		goto out;
-
-	ret = TEST_OK;
-out:
-	free(tmpl_new);
-	free(clang_opt_new);
-	if (ret != TEST_OK)
-		pr_debug("Failed to compile test case: '%s'\n", desc);
-	return ret;
-}
-
-static int test__llvm(int subtest)
-{
-	int ret;
-	void *obj_buf = NULL;
-	size_t obj_buf_sz = 0;
-	bool should_load_fail = false;
-
-	if ((subtest < 0) || (subtest >= __LLVM_TESTCASE_MAX))
-		return TEST_FAIL;
-
-	ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
-				       subtest, false, &should_load_fail);
-
-	if (ret == TEST_OK && !should_load_fail) {
-		ret = test__bpf_parsing(obj_buf, obj_buf_sz);
-		if (ret != TEST_OK) {
-			pr_debug("Failed to parse test case '%s'\n",
-				 bpf_source_table[subtest].desc);
-		}
-	}
-	free(obj_buf);
-
-	return ret;
-}
-#endif //HAVE_LIBBPF_SUPPORT
-
-static int test__llvm__bpf_base_prog(struct test_suite *test __maybe_unused,
-				     int subtest __maybe_unused)
-{
-#ifdef HAVE_LIBBPF_SUPPORT
-	return test__llvm(LLVM_TESTCASE_BASE);
-#else
-	pr_debug("Skip LLVM test because BPF support is not compiled\n");
-	return TEST_SKIP;
-#endif
-}
-
-static int test__llvm__bpf_test_kbuild_prog(struct test_suite *test __maybe_unused,
-					    int subtest __maybe_unused)
-{
-#ifdef HAVE_LIBBPF_SUPPORT
-	return test__llvm(LLVM_TESTCASE_KBUILD);
-#else
-	pr_debug("Skip LLVM test because BPF support is not compiled\n");
-	return TEST_SKIP;
-#endif
-}
-
-static int test__llvm__bpf_test_prologue_prog(struct test_suite *test __maybe_unused,
-					      int subtest __maybe_unused)
-{
-#ifdef HAVE_LIBBPF_SUPPORT
-	return test__llvm(LLVM_TESTCASE_BPF_PROLOGUE);
-#else
-	pr_debug("Skip LLVM test because BPF support is not compiled\n");
-	return TEST_SKIP;
-#endif
-}
-
-static int test__llvm__bpf_test_relocation(struct test_suite *test __maybe_unused,
-					   int subtest __maybe_unused)
-{
-#ifdef HAVE_LIBBPF_SUPPORT
-	return test__llvm(LLVM_TESTCASE_BPF_RELOCATION);
-#else
-	pr_debug("Skip LLVM test because BPF support is not compiled\n");
-	return TEST_SKIP;
-#endif
-}
-
-
-static struct test_case llvm_tests[] = {
-#ifdef HAVE_LIBBPF_SUPPORT
-	TEST_CASE("Basic BPF llvm compile", llvm__bpf_base_prog),
-	TEST_CASE("kbuild searching", llvm__bpf_test_kbuild_prog),
-	TEST_CASE("Compile source for BPF prologue generation",
-		  llvm__bpf_test_prologue_prog),
-	TEST_CASE("Compile source for BPF relocation", llvm__bpf_test_relocation),
-#else
-	TEST_CASE_REASON("Basic BPF llvm compile", llvm__bpf_base_prog, "not compiled in"),
-	TEST_CASE_REASON("kbuild searching", llvm__bpf_test_kbuild_prog, "not compiled in"),
-	TEST_CASE_REASON("Compile source for BPF prologue generation",
-			llvm__bpf_test_prologue_prog, "not compiled in"),
-	TEST_CASE_REASON("Compile source for BPF relocation",
-			llvm__bpf_test_relocation, "not compiled in"),
-#endif
-	{ .name = NULL, }
-};
-
-struct test_suite suite__llvm = {
-	.desc = "LLVM search and compile",
-	.test_cases = llvm_tests,
-};
diff --git a/tools/perf/tests/llvm.h b/tools/perf/tests/llvm.h
deleted file mode 100644
index f68b0d9b8ae2..000000000000
--- a/tools/perf/tests/llvm.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef PERF_TEST_LLVM_H
-#define PERF_TEST_LLVM_H
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-#include <stddef.h> /* for size_t */
-#include <stdbool.h> /* for bool */
-
-extern const char test_llvm__bpf_base_prog[];
-extern const char test_llvm__bpf_test_kbuild_prog[];
-extern const char test_llvm__bpf_test_prologue_prog[];
-extern const char test_llvm__bpf_test_relocation[];
-
-enum test_llvm__testcase {
-	LLVM_TESTCASE_BASE,
-	LLVM_TESTCASE_KBUILD,
-	LLVM_TESTCASE_BPF_PROLOGUE,
-	LLVM_TESTCASE_BPF_RELOCATION,
-	__LLVM_TESTCASE_MAX,
-};
-
-int test_llvm__fetch_bpf_obj(void **p_obj_buf, size_t *p_obj_buf_sz,
-			     enum test_llvm__testcase index, bool force,
-			     bool *should_load_fail);
-#ifdef __cplusplus
-}
-#endif
-#endif
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index f424c0b7f43f..f33cfc3c19a4 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -113,7 +113,6 @@ DECLARE_SUITE(fdarray__filter);
 DECLARE_SUITE(fdarray__add);
 DECLARE_SUITE(kmod_path__parse);
 DECLARE_SUITE(thread_map);
-DECLARE_SUITE(llvm);
 DECLARE_SUITE(bpf);
 DECLARE_SUITE(session_topology);
 DECLARE_SUITE(thread_map_synthesize);
@@ -129,7 +128,6 @@ DECLARE_SUITE(sdt_event);
 DECLARE_SUITE(is_printable_array);
 DECLARE_SUITE(bitmap_print);
 DECLARE_SUITE(perf_hooks);
-DECLARE_SUITE(clang);
 DECLARE_SUITE(unit_number__scnprint);
 DECLARE_SUITE(mem2node);
 DECLARE_SUITE(maps__merge_in);
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index ff3b55c7ed43..c6650d3fb066 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -23,7 +23,6 @@ perf-y += evswitch.o
 perf-y += find_bit.o
 perf-y += get_current_dir_name.o
 perf-y += levenshtein.o
-perf-y += llvm-utils.o
 perf-y += mmap.o
 perf-y += memswap.o
 perf-y += parse-events.o
@@ -150,7 +149,6 @@ perf-y += list_sort.o
 perf-y += mutex.o
 perf-y += sharded_mutex.o
 
-perf-$(CONFIG_LIBBPF) += bpf-loader.o
 perf-$(CONFIG_LIBBPF) += bpf_map.o
 perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter.o
 perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter_cgroup.o
@@ -168,7 +166,6 @@ ifeq ($(CONFIG_LIBTRACEEVENT),y)
   perf-$(CONFIG_PERF_BPF_SKEL) += bpf_kwork.o
 endif
 
-perf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
 perf-$(CONFIG_LIBELF) += symbol-elf.o
 perf-$(CONFIG_LIBELF) += probe-file.o
 perf-$(CONFIG_LIBELF) += probe-event.o
@@ -235,7 +232,6 @@ perf-$(CONFIG_LIBBPF) += bpf-utils.o
 perf-$(CONFIG_LIBPFM4) += pfm.o
 
 CFLAGS_config.o   += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
-CFLAGS_llvm-utils.o += -DLIBBPF_INCLUDE_DIR="BUILD_STR($(libbpf_include_dir_SQ))"
 
 # avoid compiler warnings in 32-bit mode
 CFLAGS_genelf_debug.o  += -Wno-packed
@@ -327,7 +323,7 @@ ifeq ($(BISON_LT_381),1)
   bison_flags += -DYYNOMEM=YYABORT
 endif
 
-CFLAGS_parse-events-flex.o  += $(flex_flags)
+CFLAGS_parse-events-flex.o  += $(flex_flags) -Wno-unused-label
 CFLAGS_pmu-flex.o           += $(flex_flags)
 CFLAGS_expr-flex.o          += $(flex_flags)
 CFLAGS_bpf-filter-flex.o    += $(flex_flags)
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
deleted file mode 100644
index b54e42f17926..000000000000
--- a/tools/perf/util/bpf-loader.c
+++ /dev/null
@@ -1,1999 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * bpf-loader.c
- *
- * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
- * Copyright (C) 2015 Huawei Inc.
- */
-
-#include <linux/bpf.h>
-#include <bpf/libbpf.h>
-#include <bpf/bpf.h>
-#include <linux/filter.h>
-#include <linux/err.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/zalloc.h>
-#include <errno.h>
-#include <stdlib.h>
-#include "debug.h"
-#include "evlist.h"
-#include "bpf-loader.h"
-#include "bpf-prologue.h"
-#include "probe-event.h"
-#include "probe-finder.h" // for MAX_PROBES
-#include "parse-events.h"
-#include "strfilter.h"
-#include "util.h"
-#include "llvm-utils.h"
-#include "util/hashmap.h"
-#include "asm/bug.h"
-
-#include <internal/xyarray.h>
-
-static int libbpf_perf_print(enum libbpf_print_level level __attribute__((unused)),
-			      const char *fmt, va_list args)
-{
-	return veprintf(1, verbose, pr_fmt(fmt), args);
-}
-
-struct bpf_prog_priv {
-	bool is_tp;
-	char *sys_name;
-	char *evt_name;
-	struct perf_probe_event pev;
-	bool need_prologue;
-	struct bpf_insn *insns_buf;
-	int nr_types;
-	int *type_mapping;
-	int *prologue_fds;
-};
-
-struct bpf_perf_object {
-	struct list_head list;
-	struct bpf_object *obj;
-};
-
-struct bpf_preproc_result {
-	struct bpf_insn *new_insn_ptr;
-	int new_insn_cnt;
-};
-
-static LIST_HEAD(bpf_objects_list);
-static struct hashmap *bpf_program_hash;
-static struct hashmap *bpf_map_hash;
-
-static struct bpf_perf_object *
-bpf_perf_object__next(struct bpf_perf_object *prev)
-{
-	if (!prev) {
-		if (list_empty(&bpf_objects_list))
-			return NULL;
-
-		return list_first_entry(&bpf_objects_list, struct bpf_perf_object, list);
-	}
-	if (list_is_last(&prev->list, &bpf_objects_list))
-		return NULL;
-
-	return list_next_entry(prev, list);
-}
-
-#define bpf_perf_object__for_each(perf_obj, tmp)	\
-	for ((perf_obj) = bpf_perf_object__next(NULL),	\
-	     (tmp) = bpf_perf_object__next(perf_obj);	\
-	     (perf_obj) != NULL;			\
-	     (perf_obj) = (tmp), (tmp) = bpf_perf_object__next(tmp))
-
-static bool libbpf_initialized;
-static int libbpf_sec_handler;
-
-static int bpf_perf_object__add(struct bpf_object *obj)
-{
-	struct bpf_perf_object *perf_obj = zalloc(sizeof(*perf_obj));
-
-	if (perf_obj) {
-		INIT_LIST_HEAD(&perf_obj->list);
-		perf_obj->obj = obj;
-		list_add_tail(&perf_obj->list, &bpf_objects_list);
-	}
-	return perf_obj ? 0 : -ENOMEM;
-}
-
-static void *program_priv(const struct bpf_program *prog)
-{
-	void *priv;
-
-	if (IS_ERR_OR_NULL(bpf_program_hash))
-		return NULL;
-	if (!hashmap__find(bpf_program_hash, prog, &priv))
-		return NULL;
-	return priv;
-}
-
-static struct bpf_insn prologue_init_insn[] = {
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_MOV64_IMM(BPF_REG_5, 0),
-};
-
-static int libbpf_prog_prepare_load_fn(struct bpf_program *prog,
-				       struct bpf_prog_load_opts *opts __maybe_unused,
-				       long cookie __maybe_unused)
-{
-	size_t init_size_cnt = ARRAY_SIZE(prologue_init_insn);
-	size_t orig_insn_cnt, insn_cnt, init_size, orig_size;
-	struct bpf_prog_priv *priv = program_priv(prog);
-	const struct bpf_insn *orig_insn;
-	struct bpf_insn *insn;
-
-	if (IS_ERR_OR_NULL(priv)) {
-		pr_debug("bpf: failed to get private field\n");
-		return -BPF_LOADER_ERRNO__INTERNAL;
-	}
-
-	if (!priv->need_prologue)
-		return 0;
-
-	/* prepend initialization code to program instructions */
-	orig_insn = bpf_program__insns(prog);
-	orig_insn_cnt = bpf_program__insn_cnt(prog);
-	init_size = init_size_cnt * sizeof(*insn);
-	orig_size = orig_insn_cnt * sizeof(*insn);
-
-	insn_cnt = orig_insn_cnt + init_size_cnt;
-	insn = malloc(insn_cnt * sizeof(*insn));
-	if (!insn)
-		return -ENOMEM;
-
-	memcpy(insn, prologue_init_insn, init_size);
-	memcpy((char *) insn + init_size, orig_insn, orig_size);
-	bpf_program__set_insns(prog, insn, insn_cnt);
-	return 0;
-}
-
-static int libbpf_init(void)
-{
-	LIBBPF_OPTS(libbpf_prog_handler_opts, handler_opts,
-		.prog_prepare_load_fn = libbpf_prog_prepare_load_fn,
-	);
-
-	if (libbpf_initialized)
-		return 0;
-
-	libbpf_set_print(libbpf_perf_print);
-	libbpf_sec_handler = libbpf_register_prog_handler(NULL, BPF_PROG_TYPE_KPROBE,
-							  0, &handler_opts);
-	if (libbpf_sec_handler < 0) {
-		pr_debug("bpf: failed to register libbpf section handler: %d\n",
-			 libbpf_sec_handler);
-		return -BPF_LOADER_ERRNO__INTERNAL;
-	}
-	libbpf_initialized = true;
-	return 0;
-}
-
-struct bpf_object *
-bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, const char *name)
-{
-	LIBBPF_OPTS(bpf_object_open_opts, opts, .object_name = name);
-	struct bpf_object *obj;
-	int err;
-
-	err = libbpf_init();
-	if (err)
-		return ERR_PTR(err);
-
-	obj = bpf_object__open_mem(obj_buf, obj_buf_sz, &opts);
-	if (IS_ERR_OR_NULL(obj)) {
-		pr_debug("bpf: failed to load buffer\n");
-		return ERR_PTR(-EINVAL);
-	}
-
-	if (bpf_perf_object__add(obj)) {
-		bpf_object__close(obj);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	return obj;
-}
-
-static void bpf_perf_object__close(struct bpf_perf_object *perf_obj)
-{
-	list_del(&perf_obj->list);
-	bpf_object__close(perf_obj->obj);
-	free(perf_obj);
-}
-
-struct bpf_object *bpf__prepare_load(const char *filename, bool source)
-{
-	LIBBPF_OPTS(bpf_object_open_opts, opts, .object_name = filename);
-	struct bpf_object *obj;
-	int err;
-
-	err = libbpf_init();
-	if (err)
-		return ERR_PTR(err);
-
-	if (source) {
-		void *obj_buf;
-		size_t obj_buf_sz;
-
-		err = llvm__compile_bpf(filename, &obj_buf, &obj_buf_sz);
-		if (err)
-			return ERR_PTR(-BPF_LOADER_ERRNO__COMPILE);
-
-		obj = bpf_object__open_mem(obj_buf, obj_buf_sz, &opts);
-
-		if (!IS_ERR_OR_NULL(obj) && llvm_param.dump_obj)
-			llvm__dump_obj(filename, obj_buf, obj_buf_sz);
-
-		free(obj_buf);
-	} else {
-		obj = bpf_object__open(filename);
-	}
-
-	if (IS_ERR_OR_NULL(obj)) {
-		pr_debug("bpf: failed to load %s\n", filename);
-		return obj;
-	}
-
-	if (bpf_perf_object__add(obj)) {
-		bpf_object__close(obj);
-		return ERR_PTR(-BPF_LOADER_ERRNO__COMPILE);
-	}
-
-	return obj;
-}
-
-static void close_prologue_programs(struct bpf_prog_priv *priv)
-{
-	struct perf_probe_event *pev;
-	int i, fd;
-
-	if (!priv->need_prologue)
-		return;
-	pev = &priv->pev;
-	for (i = 0; i < pev->ntevs; i++) {
-		fd = priv->prologue_fds[i];
-		if (fd != -1)
-			close(fd);
-	}
-}
-
-static void
-clear_prog_priv(const struct bpf_program *prog __maybe_unused,
-		void *_priv)
-{
-	struct bpf_prog_priv *priv = _priv;
-
-	close_prologue_programs(priv);
-	cleanup_perf_probe_events(&priv->pev, 1);
-	zfree(&priv->insns_buf);
-	zfree(&priv->prologue_fds);
-	zfree(&priv->type_mapping);
-	zfree(&priv->sys_name);
-	zfree(&priv->evt_name);
-	free(priv);
-}
-
-static void bpf_program_hash_free(void)
-{
-	struct hashmap_entry *cur;
-	size_t bkt;
-
-	if (IS_ERR_OR_NULL(bpf_program_hash))
-		return;
-
-	hashmap__for_each_entry(bpf_program_hash, cur, bkt)
-		clear_prog_priv(cur->pkey, cur->pvalue);
-
-	hashmap__free(bpf_program_hash);
-	bpf_program_hash = NULL;
-}
-
-static void bpf_map_hash_free(void);
-
-void bpf__clear(void)
-{
-	struct bpf_perf_object *perf_obj, *tmp;
-
-	bpf_perf_object__for_each(perf_obj, tmp) {
-		bpf__unprobe(perf_obj->obj);
-		bpf_perf_object__close(perf_obj);
-	}
-
-	bpf_program_hash_free();
-	bpf_map_hash_free();
-}
-
-static size_t ptr_hash(const long __key, void *ctx __maybe_unused)
-{
-	return __key;
-}
-
-static bool ptr_equal(long key1, long key2, void *ctx __maybe_unused)
-{
-	return key1 == key2;
-}
-
-static int program_set_priv(struct bpf_program *prog, void *priv)
-{
-	void *old_priv;
-
-	/*
-	 * Should not happen, we warn about it in the
-	 * caller function - config_bpf_program
-	 */
-	if (IS_ERR(bpf_program_hash))
-		return PTR_ERR(bpf_program_hash);
-
-	if (!bpf_program_hash) {
-		bpf_program_hash = hashmap__new(ptr_hash, ptr_equal, NULL);
-		if (IS_ERR(bpf_program_hash))
-			return PTR_ERR(bpf_program_hash);
-	}
-
-	old_priv = program_priv(prog);
-	if (old_priv) {
-		clear_prog_priv(prog, old_priv);
-		return hashmap__set(bpf_program_hash, prog, priv, NULL, NULL);
-	}
-	return hashmap__add(bpf_program_hash, prog, priv);
-}
-
-static int
-prog_config__exec(const char *value, struct perf_probe_event *pev)
-{
-	pev->uprobes = true;
-	pev->target = strdup(value);
-	if (!pev->target)
-		return -ENOMEM;
-	return 0;
-}
-
-static int
-prog_config__module(const char *value, struct perf_probe_event *pev)
-{
-	pev->uprobes = false;
-	pev->target = strdup(value);
-	if (!pev->target)
-		return -ENOMEM;
-	return 0;
-}
-
-static int
-prog_config__bool(const char *value, bool *pbool, bool invert)
-{
-	int err;
-	bool bool_value;
-
-	if (!pbool)
-		return -EINVAL;
-
-	err = strtobool(value, &bool_value);
-	if (err)
-		return err;
-
-	*pbool = invert ? !bool_value : bool_value;
-	return 0;
-}
-
-static int
-prog_config__inlines(const char *value,
-		     struct perf_probe_event *pev __maybe_unused)
-{
-	return prog_config__bool(value, &probe_conf.no_inlines, true);
-}
-
-static int
-prog_config__force(const char *value,
-		   struct perf_probe_event *pev __maybe_unused)
-{
-	return prog_config__bool(value, &probe_conf.force_add, false);
-}
-
-static struct {
-	const char *key;
-	const char *usage;
-	const char *desc;
-	int (*func)(const char *, struct perf_probe_event *);
-} bpf_prog_config_terms[] = {
-	{
-		.key	= "exec",
-		.usage	= "exec=<full path of file>",
-		.desc	= "Set uprobe target",
-		.func	= prog_config__exec,
-	},
-	{
-		.key	= "module",
-		.usage	= "module=<module name>    ",
-		.desc	= "Set kprobe module",
-		.func	= prog_config__module,
-	},
-	{
-		.key	= "inlines",
-		.usage	= "inlines=[yes|no]        ",
-		.desc	= "Probe at inline symbol",
-		.func	= prog_config__inlines,
-	},
-	{
-		.key	= "force",
-		.usage	= "force=[yes|no]          ",
-		.desc	= "Forcibly add events with existing name",
-		.func	= prog_config__force,
-	},
-};
-
-static int
-do_prog_config(const char *key, const char *value,
-	       struct perf_probe_event *pev)
-{
-	unsigned int i;
-
-	pr_debug("config bpf program: %s=%s\n", key, value);
-	for (i = 0; i < ARRAY_SIZE(bpf_prog_config_terms); i++)
-		if (strcmp(key, bpf_prog_config_terms[i].key) == 0)
-			return bpf_prog_config_terms[i].func(value, pev);
-
-	pr_debug("BPF: ERROR: invalid program config option: %s=%s\n",
-		 key, value);
-
-	pr_debug("\nHint: Valid options are:\n");
-	for (i = 0; i < ARRAY_SIZE(bpf_prog_config_terms); i++)
-		pr_debug("\t%s:\t%s\n", bpf_prog_config_terms[i].usage,
-			 bpf_prog_config_terms[i].desc);
-	pr_debug("\n");
-
-	return -BPF_LOADER_ERRNO__PROGCONF_TERM;
-}
-
-static const char *
-parse_prog_config_kvpair(const char *config_str, struct perf_probe_event *pev)
-{
-	char *text = strdup(config_str);
-	char *sep, *line;
-	const char *main_str = NULL;
-	int err = 0;
-
-	if (!text) {
-		pr_debug("Not enough memory: dup config_str failed\n");
-		return ERR_PTR(-ENOMEM);
-	}
-
-	line = text;
-	while ((sep = strchr(line, ';'))) {
-		char *equ;
-
-		*sep = '\0';
-		equ = strchr(line, '=');
-		if (!equ) {
-			pr_warning("WARNING: invalid config in BPF object: %s\n",
-				   line);
-			pr_warning("\tShould be 'key=value'.\n");
-			goto nextline;
-		}
-		*equ = '\0';
-
-		err = do_prog_config(line, equ + 1, pev);
-		if (err)
-			break;
-nextline:
-		line = sep + 1;
-	}
-
-	if (!err)
-		main_str = config_str + (line - text);
-	free(text);
-
-	return err ? ERR_PTR(err) : main_str;
-}
-
-static int
-parse_prog_config(const char *config_str, const char **p_main_str,
-		  bool *is_tp, struct perf_probe_event *pev)
-{
-	int err;
-	const char *main_str = parse_prog_config_kvpair(config_str, pev);
-
-	if (IS_ERR(main_str))
-		return PTR_ERR(main_str);
-
-	*p_main_str = main_str;
-	if (!strchr(main_str, '=')) {
-		/* Is a tracepoint event? */
-		const char *s = strchr(main_str, ':');
-
-		if (!s) {
-			pr_debug("bpf: '%s' is not a valid tracepoint\n",
-				 config_str);
-			return -BPF_LOADER_ERRNO__CONFIG;
-		}
-
-		*is_tp = true;
-		return 0;
-	}
-
-	*is_tp = false;
-	err = parse_perf_probe_command(main_str, pev);
-	if (err < 0) {
-		pr_debug("bpf: '%s' is not a valid config string\n",
-			 config_str);
-		/* parse failed, don't need clear pev. */
-		return -BPF_LOADER_ERRNO__CONFIG;
-	}
-	return 0;
-}
-
-static int
-config_bpf_program(struct bpf_program *prog)
-{
-	struct perf_probe_event *pev = NULL;
-	struct bpf_prog_priv *priv = NULL;
-	const char *config_str, *main_str;
-	bool is_tp = false;
-	int err;
-
-	/* Initialize per-program probing setting */
-	probe_conf.no_inlines = false;
-	probe_conf.force_add = false;
-
-	priv = calloc(sizeof(*priv), 1);
-	if (!priv) {
-		pr_debug("bpf: failed to alloc priv\n");
-		return -ENOMEM;
-	}
-	pev = &priv->pev;
-
-	config_str = bpf_program__section_name(prog);
-	pr_debug("bpf: config program '%s'\n", config_str);
-	err = parse_prog_config(config_str, &main_str, &is_tp, pev);
-	if (err)
-		goto errout;
-
-	if (is_tp) {
-		char *s = strchr(main_str, ':');
-
-		priv->is_tp = true;
-		priv->sys_name = strndup(main_str, s - main_str);
-		priv->evt_name = strdup(s + 1);
-		goto set_priv;
-	}
-
-	if (pev->group && strcmp(pev->group, PERF_BPF_PROBE_GROUP)) {
-		pr_debug("bpf: '%s': group for event is set and not '%s'.\n",
-			 config_str, PERF_BPF_PROBE_GROUP);
-		err = -BPF_LOADER_ERRNO__GROUP;
-		goto errout;
-	} else if (!pev->group)
-		pev->group = strdup(PERF_BPF_PROBE_GROUP);
-
-	if (!pev->group) {
-		pr_debug("bpf: strdup failed\n");
-		err = -ENOMEM;
-		goto errout;
-	}
-
-	if (!pev->event) {
-		pr_debug("bpf: '%s': event name is missing. Section name should be 'key=value'\n",
-			 config_str);
-		err = -BPF_LOADER_ERRNO__EVENTNAME;
-		goto errout;
-	}
-	pr_debug("bpf: config '%s' is ok\n", config_str);
-
-set_priv:
-	err = program_set_priv(prog, priv);
-	if (err) {
-		pr_debug("Failed to set priv for program '%s'\n", config_str);
-		goto errout;
-	}
-
-	return 0;
-
-errout:
-	if (pev)
-		clear_perf_probe_event(pev);
-	free(priv);
-	return err;
-}
-
-static int bpf__prepare_probe(void)
-{
-	static int err = 0;
-	static bool initialized = false;
-
-	/*
-	 * Make err static, so if init failed the first, bpf__prepare_probe()
-	 * fails each time without calling init_probe_symbol_maps multiple
-	 * times.
-	 */
-	if (initialized)
-		return err;
-
-	initialized = true;
-	err = init_probe_symbol_maps(false);
-	if (err < 0)
-		pr_debug("Failed to init_probe_symbol_maps\n");
-	probe_conf.max_probes = MAX_PROBES;
-	return err;
-}
-
-static int
-preproc_gen_prologue(struct bpf_program *prog, int n,
-		     const struct bpf_insn *orig_insns, int orig_insns_cnt,
-		     struct bpf_preproc_result *res)
-{
-	struct bpf_prog_priv *priv = program_priv(prog);
-	struct probe_trace_event *tev;
-	struct perf_probe_event *pev;
-	struct bpf_insn *buf;
-	size_t prologue_cnt = 0;
-	int i, err;
-
-	if (IS_ERR_OR_NULL(priv) || priv->is_tp)
-		goto errout;
-
-	pev = &priv->pev;
-
-	if (n < 0 || n >= priv->nr_types)
-		goto errout;
-
-	/* Find a tev belongs to that type */
-	for (i = 0; i < pev->ntevs; i++) {
-		if (priv->type_mapping[i] == n)
-			break;
-	}
-
-	if (i >= pev->ntevs) {
-		pr_debug("Internal error: prologue type %d not found\n", n);
-		return -BPF_LOADER_ERRNO__PROLOGUE;
-	}
-
-	tev = &pev->tevs[i];
-
-	buf = priv->insns_buf;
-	err = bpf__gen_prologue(tev->args, tev->nargs,
-				buf, &prologue_cnt,
-				BPF_MAXINSNS - orig_insns_cnt);
-	if (err) {
-		const char *title;
-
-		title = bpf_program__section_name(prog);
-		pr_debug("Failed to generate prologue for program %s\n",
-			 title);
-		return err;
-	}
-
-	memcpy(&buf[prologue_cnt], orig_insns,
-	       sizeof(struct bpf_insn) * orig_insns_cnt);
-
-	res->new_insn_ptr = buf;
-	res->new_insn_cnt = prologue_cnt + orig_insns_cnt;
-	return 0;
-
-errout:
-	pr_debug("Internal error in preproc_gen_prologue\n");
-	return -BPF_LOADER_ERRNO__PROLOGUE;
-}
-
-/*
- * compare_tev_args is reflexive, transitive and antisymmetric.
- * I can proof it but this margin is too narrow to contain.
- */
-static int compare_tev_args(const void *ptev1, const void *ptev2)
-{
-	int i, ret;
-	const struct probe_trace_event *tev1 =
-		*(const struct probe_trace_event **)ptev1;
-	const struct probe_trace_event *tev2 =
-		*(const struct probe_trace_event **)ptev2;
-
-	ret = tev2->nargs - tev1->nargs;
-	if (ret)
-		return ret;
-
-	for (i = 0; i < tev1->nargs; i++) {
-		struct probe_trace_arg *arg1, *arg2;
-		struct probe_trace_arg_ref *ref1, *ref2;
-
-		arg1 = &tev1->args[i];
-		arg2 = &tev2->args[i];
-
-		ret = strcmp(arg1->value, arg2->value);
-		if (ret)
-			return ret;
-
-		ref1 = arg1->ref;
-		ref2 = arg2->ref;
-
-		while (ref1 && ref2) {
-			ret = ref2->offset - ref1->offset;
-			if (ret)
-				return ret;
-
-			ref1 = ref1->next;
-			ref2 = ref2->next;
-		}
-
-		if (ref1 || ref2)
-			return ref2 ? 1 : -1;
-	}
-
-	return 0;
-}
-
-/*
- * Assign a type number to each tevs in a pev.
- * mapping is an array with same slots as tevs in that pev.
- * nr_types will be set to number of types.
- */
-static int map_prologue(struct perf_probe_event *pev, int *mapping,
-			int *nr_types)
-{
-	int i, type = 0;
-	struct probe_trace_event **ptevs;
-
-	size_t array_sz = sizeof(*ptevs) * pev->ntevs;
-
-	ptevs = malloc(array_sz);
-	if (!ptevs) {
-		pr_debug("Not enough memory: alloc ptevs failed\n");
-		return -ENOMEM;
-	}
-
-	pr_debug("In map_prologue, ntevs=%d\n", pev->ntevs);
-	for (i = 0; i < pev->ntevs; i++)
-		ptevs[i] = &pev->tevs[i];
-
-	qsort(ptevs, pev->ntevs, sizeof(*ptevs),
-	      compare_tev_args);
-
-	for (i = 0; i < pev->ntevs; i++) {
-		int n;
-
-		n = ptevs[i] - pev->tevs;
-		if (i == 0) {
-			mapping[n] = type;
-			pr_debug("mapping[%d]=%d\n", n, type);
-			continue;
-		}
-
-		if (compare_tev_args(ptevs + i, ptevs + i - 1) == 0)
-			mapping[n] = type;
-		else
-			mapping[n] = ++type;
-
-		pr_debug("mapping[%d]=%d\n", n, mapping[n]);
-	}
-	free(ptevs);
-	*nr_types = type + 1;
-
-	return 0;
-}
-
-static int hook_load_preprocessor(struct bpf_program *prog)
-{
-	struct bpf_prog_priv *priv = program_priv(prog);
-	struct perf_probe_event *pev;
-	bool need_prologue = false;
-	int i;
-
-	if (IS_ERR_OR_NULL(priv)) {
-		pr_debug("Internal error when hook preprocessor\n");
-		return -BPF_LOADER_ERRNO__INTERNAL;
-	}
-
-	if (priv->is_tp) {
-		priv->need_prologue = false;
-		return 0;
-	}
-
-	pev = &priv->pev;
-	for (i = 0; i < pev->ntevs; i++) {
-		struct probe_trace_event *tev = &pev->tevs[i];
-
-		if (tev->nargs > 0) {
-			need_prologue = true;
-			break;
-		}
-	}
-
-	/*
-	 * Since all tevs don't have argument, we don't need generate
-	 * prologue.
-	 */
-	if (!need_prologue) {
-		priv->need_prologue = false;
-		return 0;
-	}
-
-	priv->need_prologue = true;
-	priv->insns_buf = malloc(sizeof(struct bpf_insn) * BPF_MAXINSNS);
-	if (!priv->insns_buf) {
-		pr_debug("Not enough memory: alloc insns_buf failed\n");
-		return -ENOMEM;
-	}
-
-	priv->prologue_fds = malloc(sizeof(int) * pev->ntevs);
-	if (!priv->prologue_fds) {
-		pr_debug("Not enough memory: alloc prologue fds failed\n");
-		return -ENOMEM;
-	}
-	memset(priv->prologue_fds, -1, sizeof(int) * pev->ntevs);
-
-	priv->type_mapping = malloc(sizeof(int) * pev->ntevs);
-	if (!priv->type_mapping) {
-		pr_debug("Not enough memory: alloc type_mapping failed\n");
-		return -ENOMEM;
-	}
-	memset(priv->type_mapping, -1,
-	       sizeof(int) * pev->ntevs);
-
-	return map_prologue(pev, priv->type_mapping, &priv->nr_types);
-}
-
-int bpf__probe(struct bpf_object *obj)
-{
-	int err = 0;
-	struct bpf_program *prog;
-	struct bpf_prog_priv *priv;
-	struct perf_probe_event *pev;
-
-	err = bpf__prepare_probe();
-	if (err) {
-		pr_debug("bpf__prepare_probe failed\n");
-		return err;
-	}
-
-	bpf_object__for_each_program(prog, obj) {
-		err = config_bpf_program(prog);
-		if (err)
-			goto out;
-
-		priv = program_priv(prog);
-		if (IS_ERR_OR_NULL(priv)) {
-			if (!priv)
-				err = -BPF_LOADER_ERRNO__INTERNAL;
-			else
-				err = PTR_ERR(priv);
-			goto out;
-		}
-
-		if (priv->is_tp) {
-			bpf_program__set_type(prog, BPF_PROG_TYPE_TRACEPOINT);
-			continue;
-		}
-
-		bpf_program__set_type(prog, BPF_PROG_TYPE_KPROBE);
-		pev = &priv->pev;
-
-		err = convert_perf_probe_events(pev, 1);
-		if (err < 0) {
-			pr_debug("bpf_probe: failed to convert perf probe events\n");
-			goto out;
-		}
-
-		err = apply_perf_probe_events(pev, 1);
-		if (err < 0) {
-			pr_debug("bpf_probe: failed to apply perf probe events\n");
-			goto out;
-		}
-
-		/*
-		 * After probing, let's consider prologue, which
-		 * adds program fetcher to BPF programs.
-		 *
-		 * hook_load_preprocessor() hooks pre-processor
-		 * to bpf_program, let it generate prologue
-		 * dynamically during loading.
-		 */
-		err = hook_load_preprocessor(prog);
-		if (err)
-			goto out;
-	}
-out:
-	return err < 0 ? err : 0;
-}
-
-#define EVENTS_WRITE_BUFSIZE  4096
-int bpf__unprobe(struct bpf_object *obj)
-{
-	int err, ret = 0;
-	struct bpf_program *prog;
-
-	bpf_object__for_each_program(prog, obj) {
-		struct bpf_prog_priv *priv = program_priv(prog);
-		int i;
-
-		if (IS_ERR_OR_NULL(priv) || priv->is_tp)
-			continue;
-
-		for (i = 0; i < priv->pev.ntevs; i++) {
-			struct probe_trace_event *tev = &priv->pev.tevs[i];
-			char name_buf[EVENTS_WRITE_BUFSIZE];
-			struct strfilter *delfilter;
-
-			snprintf(name_buf, EVENTS_WRITE_BUFSIZE,
-				 "%s:%s", tev->group, tev->event);
-			name_buf[EVENTS_WRITE_BUFSIZE - 1] = '\0';
-
-			delfilter = strfilter__new(name_buf, NULL);
-			if (!delfilter) {
-				pr_debug("Failed to create filter for unprobing\n");
-				ret = -ENOMEM;
-				continue;
-			}
-
-			err = del_perf_probe_events(delfilter);
-			strfilter__delete(delfilter);
-			if (err) {
-				pr_debug("Failed to delete %s\n", name_buf);
-				ret = err;
-				continue;
-			}
-		}
-	}
-	return ret;
-}
-
-static int bpf_object__load_prologue(struct bpf_object *obj)
-{
-	int init_cnt = ARRAY_SIZE(prologue_init_insn);
-	const struct bpf_insn *orig_insns;
-	struct bpf_preproc_result res;
-	struct perf_probe_event *pev;
-	struct bpf_program *prog;
-	int orig_insns_cnt;
-
-	bpf_object__for_each_program(prog, obj) {
-		struct bpf_prog_priv *priv = program_priv(prog);
-		int err, i, fd;
-
-		if (IS_ERR_OR_NULL(priv)) {
-			pr_debug("bpf: failed to get private field\n");
-			return -BPF_LOADER_ERRNO__INTERNAL;
-		}
-
-		if (!priv->need_prologue)
-			continue;
-
-		/*
-		 * For each program that needs prologue we do following:
-		 *
-		 * - take its current instructions and use them
-		 *   to generate the new code with prologue
-		 * - load new instructions with bpf_prog_load
-		 *   and keep the fd in prologue_fds
-		 * - new fd will be used in bpf__foreach_event
-		 *   to connect this program with perf evsel
-		 */
-		orig_insns = bpf_program__insns(prog);
-		orig_insns_cnt = bpf_program__insn_cnt(prog);
-
-		pev = &priv->pev;
-		for (i = 0; i < pev->ntevs; i++) {
-			/*
-			 * Skipping artificall prologue_init_insn instructions
-			 * (init_cnt), so the prologue can be generated instead
-			 * of them.
-			 */
-			err = preproc_gen_prologue(prog, i,
-						   orig_insns + init_cnt,
-						   orig_insns_cnt - init_cnt,
-						   &res);
-			if (err)
-				return err;
-
-			fd = bpf_prog_load(bpf_program__get_type(prog),
-					   bpf_program__name(prog), "GPL",
-					   res.new_insn_ptr,
-					   res.new_insn_cnt, NULL);
-			if (fd < 0) {
-				char bf[128];
-
-				libbpf_strerror(-errno, bf, sizeof(bf));
-				pr_debug("bpf: load objects with prologue failed: err=%d: (%s)\n",
-					 -errno, bf);
-				return -errno;
-			}
-			priv->prologue_fds[i] = fd;
-		}
-		/*
-		 * We no longer need the original program,
-		 * we can unload it.
-		 */
-		bpf_program__unload(prog);
-	}
-	return 0;
-}
-
-int bpf__load(struct bpf_object *obj)
-{
-	int err;
-
-	err = bpf_object__load(obj);
-	if (err) {
-		char bf[128];
-		libbpf_strerror(err, bf, sizeof(bf));
-		pr_debug("bpf: load objects failed: err=%d: (%s)\n", err, bf);
-		return err;
-	}
-	return bpf_object__load_prologue(obj);
-}
-
-int bpf__foreach_event(struct bpf_object *obj,
-		       bpf_prog_iter_callback_t func,
-		       void *arg)
-{
-	struct bpf_program *prog;
-	int err;
-
-	bpf_object__for_each_program(prog, obj) {
-		struct bpf_prog_priv *priv = program_priv(prog);
-		struct probe_trace_event *tev;
-		struct perf_probe_event *pev;
-		int i, fd;
-
-		if (IS_ERR_OR_NULL(priv)) {
-			pr_debug("bpf: failed to get private field\n");
-			return -BPF_LOADER_ERRNO__INTERNAL;
-		}
-
-		if (priv->is_tp) {
-			fd = bpf_program__fd(prog);
-			err = (*func)(priv->sys_name, priv->evt_name, fd, obj, arg);
-			if (err) {
-				pr_debug("bpf: tracepoint call back failed, stop iterate\n");
-				return err;
-			}
-			continue;
-		}
-
-		pev = &priv->pev;
-		for (i = 0; i < pev->ntevs; i++) {
-			tev = &pev->tevs[i];
-
-			if (priv->need_prologue)
-				fd = priv->prologue_fds[i];
-			else
-				fd = bpf_program__fd(prog);
-
-			if (fd < 0) {
-				pr_debug("bpf: failed to get file descriptor\n");
-				return fd;
-			}
-
-			err = (*func)(tev->group, tev->event, fd, obj, arg);
-			if (err) {
-				pr_debug("bpf: call back failed, stop iterate\n");
-				return err;
-			}
-		}
-	}
-	return 0;
-}
-
-enum bpf_map_op_type {
-	BPF_MAP_OP_SET_VALUE,
-	BPF_MAP_OP_SET_EVSEL,
-};
-
-enum bpf_map_key_type {
-	BPF_MAP_KEY_ALL,
-};
-
-struct bpf_map_op {
-	struct list_head list;
-	enum bpf_map_op_type op_type;
-	enum bpf_map_key_type key_type;
-	union {
-		u64 value;
-		struct evsel *evsel;
-	} v;
-};
-
-struct bpf_map_priv {
-	struct list_head ops_list;
-};
-
-static void
-bpf_map_op__delete(struct bpf_map_op *op)
-{
-	if (!list_empty(&op->list))
-		list_del_init(&op->list);
-	free(op);
-}
-
-static void
-bpf_map_priv__purge(struct bpf_map_priv *priv)
-{
-	struct bpf_map_op *pos, *n;
-
-	list_for_each_entry_safe(pos, n, &priv->ops_list, list) {
-		list_del_init(&pos->list);
-		bpf_map_op__delete(pos);
-	}
-}
-
-static void
-bpf_map_priv__clear(const struct bpf_map *map __maybe_unused,
-		    void *_priv)
-{
-	struct bpf_map_priv *priv = _priv;
-
-	bpf_map_priv__purge(priv);
-	free(priv);
-}
-
-static void *map_priv(const struct bpf_map *map)
-{
-	void *priv;
-
-	if (IS_ERR_OR_NULL(bpf_map_hash))
-		return NULL;
-	if (!hashmap__find(bpf_map_hash, map, &priv))
-		return NULL;
-	return priv;
-}
-
-static void bpf_map_hash_free(void)
-{
-	struct hashmap_entry *cur;
-	size_t bkt;
-
-	if (IS_ERR_OR_NULL(bpf_map_hash))
-		return;
-
-	hashmap__for_each_entry(bpf_map_hash, cur, bkt)
-		bpf_map_priv__clear(cur->pkey, cur->pvalue);
-
-	hashmap__free(bpf_map_hash);
-	bpf_map_hash = NULL;
-}
-
-static int map_set_priv(struct bpf_map *map, void *priv)
-{
-	void *old_priv;
-
-	if (WARN_ON_ONCE(IS_ERR(bpf_map_hash)))
-		return PTR_ERR(bpf_program_hash);
-
-	if (!bpf_map_hash) {
-		bpf_map_hash = hashmap__new(ptr_hash, ptr_equal, NULL);
-		if (IS_ERR(bpf_map_hash))
-			return PTR_ERR(bpf_map_hash);
-	}
-
-	old_priv = map_priv(map);
-	if (old_priv) {
-		bpf_map_priv__clear(map, old_priv);
-		return hashmap__set(bpf_map_hash, map, priv, NULL, NULL);
-	}
-	return hashmap__add(bpf_map_hash, map, priv);
-}
-
-static int
-bpf_map_op_setkey(struct bpf_map_op *op, struct parse_events_term *term)
-{
-	op->key_type = BPF_MAP_KEY_ALL;
-	if (!term)
-		return 0;
-
-	return 0;
-}
-
-static struct bpf_map_op *
-bpf_map_op__new(struct parse_events_term *term)
-{
-	struct bpf_map_op *op;
-	int err;
-
-	op = zalloc(sizeof(*op));
-	if (!op) {
-		pr_debug("Failed to alloc bpf_map_op\n");
-		return ERR_PTR(-ENOMEM);
-	}
-	INIT_LIST_HEAD(&op->list);
-
-	err = bpf_map_op_setkey(op, term);
-	if (err) {
-		free(op);
-		return ERR_PTR(err);
-	}
-	return op;
-}
-
-static struct bpf_map_op *
-bpf_map_op__clone(struct bpf_map_op *op)
-{
-	struct bpf_map_op *newop;
-
-	newop = memdup(op, sizeof(*op));
-	if (!newop) {
-		pr_debug("Failed to alloc bpf_map_op\n");
-		return NULL;
-	}
-
-	INIT_LIST_HEAD(&newop->list);
-	return newop;
-}
-
-static struct bpf_map_priv *
-bpf_map_priv__clone(struct bpf_map_priv *priv)
-{
-	struct bpf_map_priv *newpriv;
-	struct bpf_map_op *pos, *newop;
-
-	newpriv = zalloc(sizeof(*newpriv));
-	if (!newpriv) {
-		pr_debug("Not enough memory to alloc map private\n");
-		return NULL;
-	}
-	INIT_LIST_HEAD(&newpriv->ops_list);
-
-	list_for_each_entry(pos, &priv->ops_list, list) {
-		newop = bpf_map_op__clone(pos);
-		if (!newop) {
-			bpf_map_priv__purge(newpriv);
-			return NULL;
-		}
-		list_add_tail(&newop->list, &newpriv->ops_list);
-	}
-
-	return newpriv;
-}
-
-static int
-bpf_map__add_op(struct bpf_map *map, struct bpf_map_op *op)
-{
-	const char *map_name = bpf_map__name(map);
-	struct bpf_map_priv *priv = map_priv(map);
-
-	if (IS_ERR(priv)) {
-		pr_debug("Failed to get private from map %s\n", map_name);
-		return PTR_ERR(priv);
-	}
-
-	if (!priv) {
-		priv = zalloc(sizeof(*priv));
-		if (!priv) {
-			pr_debug("Not enough memory to alloc map private\n");
-			return -ENOMEM;
-		}
-		INIT_LIST_HEAD(&priv->ops_list);
-
-		if (map_set_priv(map, priv)) {
-			free(priv);
-			return -BPF_LOADER_ERRNO__INTERNAL;
-		}
-	}
-
-	list_add_tail(&op->list, &priv->ops_list);
-	return 0;
-}
-
-static struct bpf_map_op *
-bpf_map__add_newop(struct bpf_map *map, struct parse_events_term *term)
-{
-	struct bpf_map_op *op;
-	int err;
-
-	op = bpf_map_op__new(term);
-	if (IS_ERR(op))
-		return op;
-
-	err = bpf_map__add_op(map, op);
-	if (err) {
-		bpf_map_op__delete(op);
-		return ERR_PTR(err);
-	}
-	return op;
-}
-
-static int
-__bpf_map__config_value(struct bpf_map *map,
-			struct parse_events_term *term)
-{
-	struct bpf_map_op *op;
-	const char *map_name = bpf_map__name(map);
-
-	if (!map) {
-		pr_debug("Map '%s' is invalid\n", map_name);
-		return -BPF_LOADER_ERRNO__INTERNAL;
-	}
-
-	if (bpf_map__type(map) != BPF_MAP_TYPE_ARRAY) {
-		pr_debug("Map %s type is not BPF_MAP_TYPE_ARRAY\n",
-			 map_name);
-		return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
-	}
-	if (bpf_map__key_size(map) < sizeof(unsigned int)) {
-		pr_debug("Map %s has incorrect key size\n", map_name);
-		return -BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE;
-	}
-	switch (bpf_map__value_size(map)) {
-	case 1:
-	case 2:
-	case 4:
-	case 8:
-		break;
-	default:
-		pr_debug("Map %s has incorrect value size\n", map_name);
-		return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE;
-	}
-
-	op = bpf_map__add_newop(map, term);
-	if (IS_ERR(op))
-		return PTR_ERR(op);
-	op->op_type = BPF_MAP_OP_SET_VALUE;
-	op->v.value = term->val.num;
-	return 0;
-}
-
-static int
-bpf_map__config_value(struct bpf_map *map,
-		      struct parse_events_term *term,
-		      struct evlist *evlist __maybe_unused)
-{
-	if (!term->err_val) {
-		pr_debug("Config value not set\n");
-		return -BPF_LOADER_ERRNO__OBJCONF_CONF;
-	}
-
-	if (term->type_val != PARSE_EVENTS__TERM_TYPE_NUM) {
-		pr_debug("ERROR: wrong value type for 'value'\n");
-		return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE;
-	}
-
-	return __bpf_map__config_value(map, term);
-}
-
-static int
-__bpf_map__config_event(struct bpf_map *map,
-			struct parse_events_term *term,
-			struct evlist *evlist)
-{
-	struct bpf_map_op *op;
-	const char *map_name = bpf_map__name(map);
-	struct evsel *evsel = evlist__find_evsel_by_str(evlist, term->val.str);
-
-	if (!evsel) {
-		pr_debug("Event (for '%s') '%s' doesn't exist\n",
-			 map_name, term->val.str);
-		return -BPF_LOADER_ERRNO__OBJCONF_MAP_NOEVT;
-	}
-
-	if (!map) {
-		pr_debug("Map '%s' is invalid\n", map_name);
-		return PTR_ERR(map);
-	}
-
-	/*
-	 * No need to check key_size and value_size:
-	 * kernel has already checked them.
-	 */
-	if (bpf_map__type(map) != BPF_MAP_TYPE_PERF_EVENT_ARRAY) {
-		pr_debug("Map %s type is not BPF_MAP_TYPE_PERF_EVENT_ARRAY\n",
-			 map_name);
-		return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
-	}
-
-	op = bpf_map__add_newop(map, term);
-	if (IS_ERR(op))
-		return PTR_ERR(op);
-	op->op_type = BPF_MAP_OP_SET_EVSEL;
-	op->v.evsel = evsel;
-	return 0;
-}
-
-static int
-bpf_map__config_event(struct bpf_map *map,
-		      struct parse_events_term *term,
-		      struct evlist *evlist)
-{
-	if (!term->err_val) {
-		pr_debug("Config value not set\n");
-		return -BPF_LOADER_ERRNO__OBJCONF_CONF;
-	}
-
-	if (term->type_val != PARSE_EVENTS__TERM_TYPE_STR) {
-		pr_debug("ERROR: wrong value type for 'event'\n");
-		return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE;
-	}
-
-	return __bpf_map__config_event(map, term, evlist);
-}
-
-struct bpf_obj_config__map_func {
-	const char *config_opt;
-	int (*config_func)(struct bpf_map *, struct parse_events_term *,
-			   struct evlist *);
-};
-
-struct bpf_obj_config__map_func bpf_obj_config__map_funcs[] = {
-	{"value", bpf_map__config_value},
-	{"event", bpf_map__config_event},
-};
-
-static int
-bpf__obj_config_map(struct bpf_object *obj,
-		    struct parse_events_term *term,
-		    struct evlist *evlist,
-		    int *key_scan_pos)
-{
-	/* key is "map:<mapname>.<config opt>" */
-	char *map_name = strdup(term->config + sizeof("map:") - 1);
-	struct bpf_map *map;
-	int err = -BPF_LOADER_ERRNO__OBJCONF_OPT;
-	char *map_opt;
-	size_t i;
-
-	if (!map_name)
-		return -ENOMEM;
-
-	map_opt = strchr(map_name, '.');
-	if (!map_opt) {
-		pr_debug("ERROR: Invalid map config: %s\n", map_name);
-		goto out;
-	}
-
-	*map_opt++ = '\0';
-	if (*map_opt == '\0') {
-		pr_debug("ERROR: Invalid map option: %s\n", term->config);
-		goto out;
-	}
-
-	map = bpf_object__find_map_by_name(obj, map_name);
-	if (!map) {
-		pr_debug("ERROR: Map %s doesn't exist\n", map_name);
-		err = -BPF_LOADER_ERRNO__OBJCONF_MAP_NOTEXIST;
-		goto out;
-	}
-
-	for (i = 0; i < ARRAY_SIZE(bpf_obj_config__map_funcs); i++) {
-		struct bpf_obj_config__map_func *func =
-				&bpf_obj_config__map_funcs[i];
-
-		if (strcmp(map_opt, func->config_opt) == 0) {
-			err = func->config_func(map, term, evlist);
-			goto out;
-		}
-	}
-
-	pr_debug("ERROR: Invalid map config option '%s'\n", map_opt);
-	err = -BPF_LOADER_ERRNO__OBJCONF_MAP_OPT;
-out:
-	if (!err)
-		*key_scan_pos += strlen(map_opt);
-
-	free(map_name);
-	return err;
-}
-
-int bpf__config_obj(struct bpf_object *obj,
-		    struct parse_events_term *term,
-		    struct evlist *evlist,
-		    int *error_pos)
-{
-	int key_scan_pos = 0;
-	int err;
-
-	if (!obj || !term || !term->config)
-		return -EINVAL;
-
-	if (strstarts(term->config, "map:")) {
-		key_scan_pos = sizeof("map:") - 1;
-		err = bpf__obj_config_map(obj, term, evlist, &key_scan_pos);
-		goto out;
-	}
-	err = -BPF_LOADER_ERRNO__OBJCONF_OPT;
-out:
-	if (error_pos)
-		*error_pos = key_scan_pos;
-	return err;
-
-}
-
-typedef int (*map_config_func_t)(const char *name, int map_fd,
-				 const struct bpf_map *map,
-				 struct bpf_map_op *op,
-				 void *pkey, void *arg);
-static int
-foreach_key_array_all(map_config_func_t func,
-		      void *arg, const char *name,
-		      int map_fd, const struct bpf_map *map,
-		      struct bpf_map_op *op)
-{
-	unsigned int i;
-	int err;
-
-	for (i = 0; i < bpf_map__max_entries(map); i++) {
-		err = func(name, map_fd, map, op, &i, arg);
-		if (err) {
-			pr_debug("ERROR: failed to insert value to %s[%u]\n",
-				 name, i);
-			return err;
-		}
-	}
-	return 0;
-}
-
-
-static int
-bpf_map_config_foreach_key(struct bpf_map *map,
-			   map_config_func_t func,
-			   void *arg)
-{
-	int err, map_fd, type;
-	struct bpf_map_op *op;
-	const char *name = bpf_map__name(map);
-	struct bpf_map_priv *priv = map_priv(map);
-
-	if (IS_ERR(priv)) {
-		pr_debug("ERROR: failed to get private from map %s\n", name);
-		return -BPF_LOADER_ERRNO__INTERNAL;
-	}
-	if (!priv || list_empty(&priv->ops_list)) {
-		pr_debug("INFO: nothing to config for map %s\n", name);
-		return 0;
-	}
-
-	if (!map) {
-		pr_debug("Map '%s' is invalid\n", name);
-		return -BPF_LOADER_ERRNO__INTERNAL;
-	}
-	map_fd = bpf_map__fd(map);
-	if (map_fd < 0) {
-		pr_debug("ERROR: failed to get fd from map %s\n", name);
-		return map_fd;
-	}
-
-	type = bpf_map__type(map);
-	list_for_each_entry(op, &priv->ops_list, list) {
-		switch (type) {
-		case BPF_MAP_TYPE_ARRAY:
-		case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
-			switch (op->key_type) {
-			case BPF_MAP_KEY_ALL:
-				err = foreach_key_array_all(func, arg, name,
-							    map_fd, map, op);
-				break;
-			default:
-				pr_debug("ERROR: keytype for map '%s' invalid\n",
-					 name);
-				return -BPF_LOADER_ERRNO__INTERNAL;
-			}
-			if (err)
-				return err;
-			break;
-		default:
-			pr_debug("ERROR: type of '%s' incorrect\n", name);
-			return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
-		}
-	}
-
-	return 0;
-}
-
-static int
-apply_config_value_for_key(int map_fd, void *pkey,
-			   size_t val_size, u64 val)
-{
-	int err = 0;
-
-	switch (val_size) {
-	case 1: {
-		u8 _val = (u8)(val);
-		err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY);
-		break;
-	}
-	case 2: {
-		u16 _val = (u16)(val);
-		err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY);
-		break;
-	}
-	case 4: {
-		u32 _val = (u32)(val);
-		err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY);
-		break;
-	}
-	case 8: {
-		err = bpf_map_update_elem(map_fd, pkey, &val, BPF_ANY);
-		break;
-	}
-	default:
-		pr_debug("ERROR: invalid value size\n");
-		return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE;
-	}
-	if (err && errno)
-		err = -errno;
-	return err;
-}
-
-static int
-apply_config_evsel_for_key(const char *name, int map_fd, void *pkey,
-			   struct evsel *evsel)
-{
-	struct xyarray *xy = evsel->core.fd;
-	struct perf_event_attr *attr;
-	unsigned int key, events;
-	bool check_pass = false;
-	int *evt_fd;
-	int err;
-
-	if (!xy) {
-		pr_debug("ERROR: evsel not ready for map %s\n", name);
-		return -BPF_LOADER_ERRNO__INTERNAL;
-	}
-
-	if (xy->row_size / xy->entry_size != 1) {
-		pr_debug("ERROR: Dimension of target event is incorrect for map %s\n",
-			 name);
-		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM;
-	}
-
-	attr = &evsel->core.attr;
-	if (attr->inherit) {
-		pr_debug("ERROR: Can't put inherit event into map %s\n", name);
-		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH;
-	}
-
-	if (evsel__is_bpf_output(evsel))
-		check_pass = true;
-	if (attr->type == PERF_TYPE_RAW)
-		check_pass = true;
-	if (attr->type == PERF_TYPE_HARDWARE)
-		check_pass = true;
-	if (!check_pass) {
-		pr_debug("ERROR: Event type is wrong for map %s\n", name);
-		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE;
-	}
-
-	events = xy->entries / (xy->row_size / xy->entry_size);
-	key = *((unsigned int *)pkey);
-	if (key >= events) {
-		pr_debug("ERROR: there is no event %d for map %s\n",
-			 key, name);
-		return -BPF_LOADER_ERRNO__OBJCONF_MAP_MAPSIZE;
-	}
-	evt_fd = xyarray__entry(xy, key, 0);
-	err = bpf_map_update_elem(map_fd, pkey, evt_fd, BPF_ANY);
-	if (err && errno)
-		err = -errno;
-	return err;
-}
-
-static int
-apply_obj_config_map_for_key(const char *name, int map_fd,
-			     const struct bpf_map *map,
-			     struct bpf_map_op *op,
-			     void *pkey, void *arg __maybe_unused)
-{
-	int err;
-
-	switch (op->op_type) {
-	case BPF_MAP_OP_SET_VALUE:
-		err = apply_config_value_for_key(map_fd, pkey,
-						 bpf_map__value_size(map),
-						 op->v.value);
-		break;
-	case BPF_MAP_OP_SET_EVSEL:
-		err = apply_config_evsel_for_key(name, map_fd, pkey,
-						 op->v.evsel);
-		break;
-	default:
-		pr_debug("ERROR: unknown value type for '%s'\n", name);
-		err = -BPF_LOADER_ERRNO__INTERNAL;
-	}
-	return err;
-}
-
-static int
-apply_obj_config_map(struct bpf_map *map)
-{
-	return bpf_map_config_foreach_key(map,
-					  apply_obj_config_map_for_key,
-					  NULL);
-}
-
-static int
-apply_obj_config_object(struct bpf_object *obj)
-{
-	struct bpf_map *map;
-	int err;
-
-	bpf_object__for_each_map(map, obj) {
-		err = apply_obj_config_map(map);
-		if (err)
-			return err;
-	}
-	return 0;
-}
-
-int bpf__apply_obj_config(void)
-{
-	struct bpf_perf_object *perf_obj, *tmp;
-	int err;
-
-	bpf_perf_object__for_each(perf_obj, tmp) {
-		err = apply_obj_config_object(perf_obj->obj);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
-#define bpf__perf_for_each_map(map, pobj, tmp)			\
-	bpf_perf_object__for_each(pobj, tmp)			\
-		bpf_object__for_each_map(map, pobj->obj)
-
-#define bpf__perf_for_each_map_named(map, pobj, pobjtmp, name)	\
-	bpf__perf_for_each_map(map, pobj, pobjtmp)		\
-		if (bpf_map__name(map) && (strcmp(name, bpf_map__name(map)) == 0))
-
-struct evsel *bpf__setup_output_event(struct evlist *evlist, const char *name)
-{
-	struct bpf_map_priv *tmpl_priv = NULL;
-	struct bpf_perf_object *perf_obj, *tmp;
-	struct evsel *evsel = NULL;
-	struct bpf_map *map;
-	int err;
-	bool need_init = false;
-
-	bpf__perf_for_each_map_named(map, perf_obj, tmp, name) {
-		struct bpf_map_priv *priv = map_priv(map);
-
-		if (IS_ERR(priv))
-			return ERR_PTR(-BPF_LOADER_ERRNO__INTERNAL);
-
-		/*
-		 * No need to check map type: type should have been
-		 * verified by kernel.
-		 */
-		if (!need_init && !priv)
-			need_init = !priv;
-		if (!tmpl_priv && priv)
-			tmpl_priv = priv;
-	}
-
-	if (!need_init)
-		return NULL;
-
-	if (!tmpl_priv) {
-		char *event_definition = NULL;
-
-		if (asprintf(&event_definition, "bpf-output/no-inherit=1,name=%s/", name) < 0)
-			return ERR_PTR(-ENOMEM);
-
-		err = parse_event(evlist, event_definition);
-		free(event_definition);
-
-		if (err) {
-			pr_debug("ERROR: failed to create the \"%s\" bpf-output event\n", name);
-			return ERR_PTR(-err);
-		}
-
-		evsel = evlist__last(evlist);
-	}
-
-	bpf__perf_for_each_map_named(map, perf_obj, tmp, name) {
-		struct bpf_map_priv *priv = map_priv(map);
-
-		if (IS_ERR(priv))
-			return ERR_PTR(-BPF_LOADER_ERRNO__INTERNAL);
-		if (priv)
-			continue;
-
-		if (tmpl_priv) {
-			priv = bpf_map_priv__clone(tmpl_priv);
-			if (!priv)
-				return ERR_PTR(-ENOMEM);
-
-			err = map_set_priv(map, priv);
-			if (err) {
-				bpf_map_priv__clear(map, priv);
-				return ERR_PTR(err);
-			}
-		} else if (evsel) {
-			struct bpf_map_op *op;
-
-			op = bpf_map__add_newop(map, NULL);
-			if (IS_ERR(op))
-				return ERR_CAST(op);
-			op->op_type = BPF_MAP_OP_SET_EVSEL;
-			op->v.evsel = evsel;
-		}
-	}
-
-	return evsel;
-}
-
-int bpf__setup_stdout(struct evlist *evlist)
-{
-	struct evsel *evsel = bpf__setup_output_event(evlist, "__bpf_stdout__");
-	return PTR_ERR_OR_ZERO(evsel);
-}
-
-#define ERRNO_OFFSET(e)		((e) - __BPF_LOADER_ERRNO__START)
-#define ERRCODE_OFFSET(c)	ERRNO_OFFSET(BPF_LOADER_ERRNO__##c)
-#define NR_ERRNO	(__BPF_LOADER_ERRNO__END - __BPF_LOADER_ERRNO__START)
-
-static const char *bpf_loader_strerror_table[NR_ERRNO] = {
-	[ERRCODE_OFFSET(CONFIG)]	= "Invalid config string",
-	[ERRCODE_OFFSET(GROUP)]		= "Invalid group name",
-	[ERRCODE_OFFSET(EVENTNAME)]	= "No event name found in config string",
-	[ERRCODE_OFFSET(INTERNAL)]	= "BPF loader internal error",
-	[ERRCODE_OFFSET(COMPILE)]	= "Error when compiling BPF scriptlet",
-	[ERRCODE_OFFSET(PROGCONF_TERM)]	= "Invalid program config term in config string",
-	[ERRCODE_OFFSET(PROLOGUE)]	= "Failed to generate prologue",
-	[ERRCODE_OFFSET(PROLOGUE2BIG)]	= "Prologue too big for program",
-	[ERRCODE_OFFSET(PROLOGUEOOB)]	= "Offset out of bound for prologue",
-	[ERRCODE_OFFSET(OBJCONF_OPT)]	= "Invalid object config option",
-	[ERRCODE_OFFSET(OBJCONF_CONF)]	= "Config value not set (missing '=')",
-	[ERRCODE_OFFSET(OBJCONF_MAP_OPT)]	= "Invalid object map config option",
-	[ERRCODE_OFFSET(OBJCONF_MAP_NOTEXIST)]	= "Target map doesn't exist",
-	[ERRCODE_OFFSET(OBJCONF_MAP_VALUE)]	= "Incorrect value type for map",
-	[ERRCODE_OFFSET(OBJCONF_MAP_TYPE)]	= "Incorrect map type",
-	[ERRCODE_OFFSET(OBJCONF_MAP_KEYSIZE)]	= "Incorrect map key size",
-	[ERRCODE_OFFSET(OBJCONF_MAP_VALUESIZE)]	= "Incorrect map value size",
-	[ERRCODE_OFFSET(OBJCONF_MAP_NOEVT)]	= "Event not found for map setting",
-	[ERRCODE_OFFSET(OBJCONF_MAP_MAPSIZE)]	= "Invalid map size for event setting",
-	[ERRCODE_OFFSET(OBJCONF_MAP_EVTDIM)]	= "Event dimension too large",
-	[ERRCODE_OFFSET(OBJCONF_MAP_EVTINH)]	= "Doesn't support inherit event",
-	[ERRCODE_OFFSET(OBJCONF_MAP_EVTTYPE)]	= "Wrong event type for map",
-	[ERRCODE_OFFSET(OBJCONF_MAP_IDX2BIG)]	= "Index too large",
-};
-
-static int
-bpf_loader_strerror(int err, char *buf, size_t size)
-{
-	char sbuf[STRERR_BUFSIZE];
-	const char *msg;
-
-	if (!buf || !size)
-		return -1;
-
-	err = err > 0 ? err : -err;
-
-	if (err >= __LIBBPF_ERRNO__START)
-		return libbpf_strerror(err, buf, size);
-
-	if (err >= __BPF_LOADER_ERRNO__START && err < __BPF_LOADER_ERRNO__END) {
-		msg = bpf_loader_strerror_table[ERRNO_OFFSET(err)];
-		snprintf(buf, size, "%s", msg);
-		buf[size - 1] = '\0';
-		return 0;
-	}
-
-	if (err >= __BPF_LOADER_ERRNO__END)
-		snprintf(buf, size, "Unknown bpf loader error %d", err);
-	else
-		snprintf(buf, size, "%s",
-			 str_error_r(err, sbuf, sizeof(sbuf)));
-
-	buf[size - 1] = '\0';
-	return -1;
-}
-
-#define bpf__strerror_head(err, buf, size) \
-	char sbuf[STRERR_BUFSIZE], *emsg;\
-	if (!size)\
-		return 0;\
-	if (err < 0)\
-		err = -err;\
-	bpf_loader_strerror(err, sbuf, sizeof(sbuf));\
-	emsg = sbuf;\
-	switch (err) {\
-	default:\
-		scnprintf(buf, size, "%s", emsg);\
-		break;
-
-#define bpf__strerror_entry(val, fmt...)\
-	case val: {\
-		scnprintf(buf, size, fmt);\
-		break;\
-	}
-
-#define bpf__strerror_end(buf, size)\
-	}\
-	buf[size - 1] = '\0';
-
-int bpf__strerror_prepare_load(const char *filename, bool source,
-			       int err, char *buf, size_t size)
-{
-	size_t n;
-	int ret;
-
-	n = snprintf(buf, size, "Failed to load %s%s: ",
-			 filename, source ? " from source" : "");
-	if (n >= size) {
-		buf[size - 1] = '\0';
-		return 0;
-	}
-	buf += n;
-	size -= n;
-
-	ret = bpf_loader_strerror(err, buf, size);
-	buf[size - 1] = '\0';
-	return ret;
-}
-
-int bpf__strerror_probe(struct bpf_object *obj __maybe_unused,
-			int err, char *buf, size_t size)
-{
-	bpf__strerror_head(err, buf, size);
-	case BPF_LOADER_ERRNO__PROGCONF_TERM: {
-		scnprintf(buf, size, "%s (add -v to see detail)", emsg);
-		break;
-	}
-	bpf__strerror_entry(EEXIST, "Probe point exist. Try 'perf probe -d \"*\"' and set 'force=yes'");
-	bpf__strerror_entry(EACCES, "You need to be root");
-	bpf__strerror_entry(EPERM, "You need to be root, and /proc/sys/kernel/kptr_restrict should be 0");
-	bpf__strerror_entry(ENOENT, "You need to check probing points in BPF file");
-	bpf__strerror_end(buf, size);
-	return 0;
-}
-
-int bpf__strerror_load(struct bpf_object *obj,
-		       int err, char *buf, size_t size)
-{
-	bpf__strerror_head(err, buf, size);
-	case LIBBPF_ERRNO__KVER: {
-		unsigned int obj_kver = bpf_object__kversion(obj);
-		unsigned int real_kver;
-
-		if (fetch_kernel_version(&real_kver, NULL, 0)) {
-			scnprintf(buf, size, "Unable to fetch kernel version");
-			break;
-		}
-
-		if (obj_kver != real_kver) {
-			scnprintf(buf, size,
-				  "'version' ("KVER_FMT") doesn't match running kernel ("KVER_FMT")",
-				  KVER_PARAM(obj_kver),
-				  KVER_PARAM(real_kver));
-			break;
-		}
-
-		scnprintf(buf, size, "Failed to load program for unknown reason");
-		break;
-	}
-	bpf__strerror_end(buf, size);
-	return 0;
-}
-
-int bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused,
-			     struct parse_events_term *term __maybe_unused,
-			     struct evlist *evlist __maybe_unused,
-			     int *error_pos __maybe_unused, int err,
-			     char *buf, size_t size)
-{
-	bpf__strerror_head(err, buf, size);
-	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE,
-			    "Can't use this config term with this map type");
-	bpf__strerror_end(buf, size);
-	return 0;
-}
-
-int bpf__strerror_apply_obj_config(int err, char *buf, size_t size)
-{
-	bpf__strerror_head(err, buf, size);
-	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM,
-			    "Cannot set event to BPF map in multi-thread tracing");
-	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH,
-			    "%s (Hint: use -i to turn off inherit)", emsg);
-	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE,
-			    "Can only put raw, hardware and BPF output event into a BPF map");
-	bpf__strerror_end(buf, size);
-	return 0;
-}
-
-int bpf__strerror_setup_output_event(struct evlist *evlist __maybe_unused,
-				     int err, char *buf, size_t size)
-{
-	bpf__strerror_head(err, buf, size);
-	bpf__strerror_end(buf, size);
-	return 0;
-}
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
deleted file mode 100644
index 5d1c725cea29..000000000000
--- a/tools/perf/util/bpf-loader.h
+++ /dev/null
@@ -1,216 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 2015, Wang Nan <wangnan0@huawei.com>
- * Copyright (C) 2015, Huawei Inc.
- */
-#ifndef __BPF_LOADER_H
-#define __BPF_LOADER_H
-
-#include <linux/compiler.h>
-#include <linux/err.h>
-
-#ifdef HAVE_LIBBPF_SUPPORT
-#include <bpf/libbpf.h>
-
-enum bpf_loader_errno {
-	__BPF_LOADER_ERRNO__START = __LIBBPF_ERRNO__START - 100,
-	/* Invalid config string */
-	BPF_LOADER_ERRNO__CONFIG = __BPF_LOADER_ERRNO__START,
-	BPF_LOADER_ERRNO__GROUP,	/* Invalid group name */
-	BPF_LOADER_ERRNO__EVENTNAME,	/* Event name is missing */
-	BPF_LOADER_ERRNO__INTERNAL,	/* BPF loader internal error */
-	BPF_LOADER_ERRNO__COMPILE,	/* Error when compiling BPF scriptlet */
-	BPF_LOADER_ERRNO__PROGCONF_TERM,/* Invalid program config term in config string */
-	BPF_LOADER_ERRNO__PROLOGUE,	/* Failed to generate prologue */
-	BPF_LOADER_ERRNO__PROLOGUE2BIG,	/* Prologue too big for program */
-	BPF_LOADER_ERRNO__PROLOGUEOOB,	/* Offset out of bound for prologue */
-	BPF_LOADER_ERRNO__OBJCONF_OPT,	/* Invalid object config option */
-	BPF_LOADER_ERRNO__OBJCONF_CONF,	/* Config value not set (lost '=')) */
-	BPF_LOADER_ERRNO__OBJCONF_MAP_OPT,	/* Invalid object map config option */
-	BPF_LOADER_ERRNO__OBJCONF_MAP_NOTEXIST,	/* Target map not exist */
-	BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE,	/* Incorrect value type for map */
-	BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE,	/* Incorrect map type */
-	BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE,	/* Incorrect map key size */
-	BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE,/* Incorrect map value size */
-	BPF_LOADER_ERRNO__OBJCONF_MAP_NOEVT,	/* Event not found for map setting */
-	BPF_LOADER_ERRNO__OBJCONF_MAP_MAPSIZE,	/* Invalid map size for event setting */
-	BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM,	/* Event dimension too large */
-	BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH,	/* Doesn't support inherit event */
-	BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE,	/* Wrong event type for map */
-	BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG,	/* Index too large */
-	__BPF_LOADER_ERRNO__END,
-};
-#endif // HAVE_LIBBPF_SUPPORT
-
-struct evsel;
-struct evlist;
-struct bpf_object;
-struct parse_events_term;
-#define PERF_BPF_PROBE_GROUP "perf_bpf_probe"
-
-typedef int (*bpf_prog_iter_callback_t)(const char *group, const char *event,
-					int fd, struct bpf_object *obj, void *arg);
-
-#ifdef HAVE_LIBBPF_SUPPORT
-struct bpf_object *bpf__prepare_load(const char *filename, bool source);
-int bpf__strerror_prepare_load(const char *filename, bool source,
-			       int err, char *buf, size_t size);
-
-struct bpf_object *bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz,
-					    const char *name);
-
-void bpf__clear(void);
-
-int bpf__probe(struct bpf_object *obj);
-int bpf__unprobe(struct bpf_object *obj);
-int bpf__strerror_probe(struct bpf_object *obj, int err,
-			char *buf, size_t size);
-
-int bpf__load(struct bpf_object *obj);
-int bpf__strerror_load(struct bpf_object *obj, int err,
-		       char *buf, size_t size);
-int bpf__foreach_event(struct bpf_object *obj,
-		       bpf_prog_iter_callback_t func, void *arg);
-
-int bpf__config_obj(struct bpf_object *obj, struct parse_events_term *term,
-		    struct evlist *evlist, int *error_pos);
-int bpf__strerror_config_obj(struct bpf_object *obj,
-			     struct parse_events_term *term,
-			     struct evlist *evlist,
-			     int *error_pos, int err, char *buf,
-			     size_t size);
-int bpf__apply_obj_config(void);
-int bpf__strerror_apply_obj_config(int err, char *buf, size_t size);
-
-int bpf__setup_stdout(struct evlist *evlist);
-struct evsel *bpf__setup_output_event(struct evlist *evlist, const char *name);
-int bpf__strerror_setup_output_event(struct evlist *evlist, int err, char *buf, size_t size);
-#else
-#include <errno.h>
-#include <string.h>
-#include "debug.h"
-
-static inline struct bpf_object *
-bpf__prepare_load(const char *filename __maybe_unused,
-		  bool source __maybe_unused)
-{
-	pr_debug("ERROR: eBPF object loading is disabled during compiling.\n");
-	return ERR_PTR(-ENOTSUP);
-}
-
-static inline struct bpf_object *
-bpf__prepare_load_buffer(void *obj_buf __maybe_unused,
-					   size_t obj_buf_sz __maybe_unused)
-{
-	return ERR_PTR(-ENOTSUP);
-}
-
-static inline void bpf__clear(void) { }
-
-static inline int bpf__probe(struct bpf_object *obj __maybe_unused) { return 0;}
-static inline int bpf__unprobe(struct bpf_object *obj __maybe_unused) { return 0;}
-static inline int bpf__load(struct bpf_object *obj __maybe_unused) { return 0; }
-
-static inline int
-bpf__foreach_event(struct bpf_object *obj __maybe_unused,
-		   bpf_prog_iter_callback_t func __maybe_unused,
-		   void *arg __maybe_unused)
-{
-	return 0;
-}
-
-static inline int
-bpf__config_obj(struct bpf_object *obj __maybe_unused,
-		struct parse_events_term *term __maybe_unused,
-		struct evlist *evlist __maybe_unused,
-		int *error_pos __maybe_unused)
-{
-	return 0;
-}
-
-static inline int
-bpf__apply_obj_config(void)
-{
-	return 0;
-}
-
-static inline int
-bpf__setup_stdout(struct evlist *evlist __maybe_unused)
-{
-	return 0;
-}
-
-static inline struct evsel *
-bpf__setup_output_event(struct evlist *evlist __maybe_unused, const char *name __maybe_unused)
-{
-	return NULL;
-}
-
-static inline int
-__bpf_strerror(char *buf, size_t size)
-{
-	if (!size)
-		return 0;
-	strncpy(buf,
-		"ERROR: eBPF object loading is disabled during compiling.\n",
-		size);
-	buf[size - 1] = '\0';
-	return 0;
-}
-
-static inline
-int bpf__strerror_prepare_load(const char *filename __maybe_unused,
-			       bool source __maybe_unused,
-			       int err __maybe_unused,
-			       char *buf, size_t size)
-{
-	return __bpf_strerror(buf, size);
-}
-
-static inline int
-bpf__strerror_probe(struct bpf_object *obj __maybe_unused,
-		    int err __maybe_unused,
-		    char *buf, size_t size)
-{
-	return __bpf_strerror(buf, size);
-}
-
-static inline int bpf__strerror_load(struct bpf_object *obj __maybe_unused,
-				     int err __maybe_unused,
-				     char *buf, size_t size)
-{
-	return __bpf_strerror(buf, size);
-}
-
-static inline int
-bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused,
-			 struct parse_events_term *term __maybe_unused,
-			 struct evlist *evlist __maybe_unused,
-			 int *error_pos __maybe_unused,
-			 int err __maybe_unused,
-			 char *buf, size_t size)
-{
-	return __bpf_strerror(buf, size);
-}
-
-static inline int
-bpf__strerror_apply_obj_config(int err __maybe_unused,
-			       char *buf, size_t size)
-{
-	return __bpf_strerror(buf, size);
-}
-
-static inline int
-bpf__strerror_setup_output_event(struct evlist *evlist __maybe_unused,
-				 int err __maybe_unused, char *buf, size_t size)
-{
-	return __bpf_strerror(buf, size);
-}
-
-#endif
-
-static inline int bpf__strerror_setup_stdout(struct evlist *evlist, int err, char *buf, size_t size)
-{
-	return bpf__strerror_setup_output_event(evlist, err, buf, size);
-}
-#endif
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 46f144c46827..7a650de0db83 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -16,7 +16,6 @@
 #include <subcmd/exec-cmd.h>
 #include "util/event.h"  /* proc_map_timeout */
 #include "util/hist.h"  /* perf_hist_config */
-#include "util/llvm-utils.h"   /* perf_llvm_config */
 #include "util/stat.h"  /* perf_stat__set_big_num */
 #include "util/evsel.h"  /* evsel__hw_names, evsel__use_bpf_counters */
 #include "util/srcline.h"  /* addr2line_timeout_ms */
@@ -486,9 +485,6 @@ int perf_default_config(const char *var, const char *value,
 	if (strstarts(var, "call-graph."))
 		return perf_callchain_config(var, value);
 
-	if (strstarts(var, "llvm."))
-		return perf_llvm_config(var, value);
-
 	if (strstarts(var, "buildid."))
 		return perf_buildid_config(var, value);
 
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
deleted file mode 100644
index c6c9c2228578..000000000000
--- a/tools/perf/util/llvm-utils.c
+++ /dev/null
@@ -1,612 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2015, Wang Nan <wangnan0@huawei.com>
- * Copyright (C) 2015, Huawei Inc.
- */
-
-#include <errno.h>
-#include <limits.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <unistd.h>
-#include <linux/err.h>
-#include <linux/string.h>
-#include <linux/zalloc.h>
-#include "debug.h"
-#include "llvm-utils.h"
-#include "config.h"
-#include "util.h"
-#include <sys/wait.h>
-#include <subcmd/exec-cmd.h>
-
-#define CLANG_BPF_CMD_DEFAULT_TEMPLATE				\
-		"$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
-		"-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE "	\
-		"$CLANG_OPTIONS $PERF_BPF_INC_OPTIONS $KERNEL_INC_OPTIONS " \
-		"-Wno-unused-value -Wno-pointer-sign "		\
-		"-working-directory $WORKING_DIR "		\
-		"-c \"$CLANG_SOURCE\" --target=bpf $CLANG_EMIT_LLVM -g -O2 -o - $LLVM_OPTIONS_PIPE"
-
-struct llvm_param llvm_param = {
-	.clang_path = "clang",
-	.llc_path = "llc",
-	.clang_bpf_cmd_template = CLANG_BPF_CMD_DEFAULT_TEMPLATE,
-	.clang_opt = NULL,
-	.opts = NULL,
-	.kbuild_dir = NULL,
-	.kbuild_opts = NULL,
-	.user_set_param = false,
-};
-
-static void version_notice(void);
-
-int perf_llvm_config(const char *var, const char *value)
-{
-	if (!strstarts(var, "llvm."))
-		return 0;
-	var += sizeof("llvm.") - 1;
-
-	if (!strcmp(var, "clang-path"))
-		llvm_param.clang_path = strdup(value);
-	else if (!strcmp(var, "clang-bpf-cmd-template"))
-		llvm_param.clang_bpf_cmd_template = strdup(value);
-	else if (!strcmp(var, "clang-opt"))
-		llvm_param.clang_opt = strdup(value);
-	else if (!strcmp(var, "kbuild-dir"))
-		llvm_param.kbuild_dir = strdup(value);
-	else if (!strcmp(var, "kbuild-opts"))
-		llvm_param.kbuild_opts = strdup(value);
-	else if (!strcmp(var, "dump-obj"))
-		llvm_param.dump_obj = !!perf_config_bool(var, value);
-	else if (!strcmp(var, "opts"))
-		llvm_param.opts = strdup(value);
-	else {
-		pr_debug("Invalid LLVM config option: %s\n", value);
-		return -1;
-	}
-	llvm_param.user_set_param = true;
-	return 0;
-}
-
-static int
-search_program(const char *def, const char *name,
-	       char *output)
-{
-	char *env, *path, *tmp = NULL;
-	char buf[PATH_MAX];
-	int ret;
-
-	output[0] = '\0';
-	if (def && def[0] != '\0') {
-		if (def[0] == '/') {
-			if (access(def, F_OK) == 0) {
-				strlcpy(output, def, PATH_MAX);
-				return 0;
-			}
-		} else if (def[0] != '\0')
-			name = def;
-	}
-
-	env = getenv("PATH");
-	if (!env)
-		return -1;
-	env = strdup(env);
-	if (!env)
-		return -1;
-
-	ret = -ENOENT;
-	path = strtok_r(env, ":",  &tmp);
-	while (path) {
-		scnprintf(buf, sizeof(buf), "%s/%s", path, name);
-		if (access(buf, F_OK) == 0) {
-			strlcpy(output, buf, PATH_MAX);
-			ret = 0;
-			break;
-		}
-		path = strtok_r(NULL, ":", &tmp);
-	}
-
-	free(env);
-	return ret;
-}
-
-static int search_program_and_warn(const char *def, const char *name,
-				   char *output)
-{
-	int ret = search_program(def, name, output);
-
-	if (ret) {
-		pr_err("ERROR:\tunable to find %s.\n"
-		       "Hint:\tTry to install latest clang/llvm to support BPF. Check your $PATH\n"
-		       "     \tand '%s-path' option in [llvm] section of ~/.perfconfig.\n",
-		       name, name);
-		version_notice();
-	}
-	return ret;
-}
-
-#define READ_SIZE	4096
-static int
-read_from_pipe(const char *cmd, void **p_buf, size_t *p_read_sz)
-{
-	int err = 0;
-	void *buf = NULL;
-	FILE *file = NULL;
-	size_t read_sz = 0, buf_sz = 0;
-	char serr[STRERR_BUFSIZE];
-
-	file = popen(cmd, "r");
-	if (!file) {
-		pr_err("ERROR: unable to popen cmd: %s\n",
-		       str_error_r(errno, serr, sizeof(serr)));
-		return -EINVAL;
-	}
-
-	while (!feof(file) && !ferror(file)) {
-		/*
-		 * Make buf_sz always have obe byte extra space so we
-		 * can put '\0' there.
-		 */
-		if (buf_sz - read_sz < READ_SIZE + 1) {
-			void *new_buf;
-
-			buf_sz = read_sz + READ_SIZE + 1;
-			new_buf = realloc(buf, buf_sz);
-
-			if (!new_buf) {
-				pr_err("ERROR: failed to realloc memory\n");
-				err = -ENOMEM;
-				goto errout;
-			}
-
-			buf = new_buf;
-		}
-		read_sz += fread(buf + read_sz, 1, READ_SIZE, file);
-	}
-
-	if (buf_sz - read_sz < 1) {
-		pr_err("ERROR: internal error\n");
-		err = -EINVAL;
-		goto errout;
-	}
-
-	if (ferror(file)) {
-		pr_err("ERROR: error occurred when reading from pipe: %s\n",
-		       str_error_r(errno, serr, sizeof(serr)));
-		err = -EIO;
-		goto errout;
-	}
-
-	err = WEXITSTATUS(pclose(file));
-	file = NULL;
-	if (err) {
-		err = -EINVAL;
-		goto errout;
-	}
-
-	/*
-	 * If buf is string, give it terminal '\0' to make our life
-	 * easier. If buf is not string, that '\0' is out of space
-	 * indicated by read_sz so caller won't even notice it.
-	 */
-	((char *)buf)[read_sz] = '\0';
-
-	if (!p_buf)
-		free(buf);
-	else
-		*p_buf = buf;
-
-	if (p_read_sz)
-		*p_read_sz = read_sz;
-	return 0;
-
-errout:
-	if (file)
-		pclose(file);
-	free(buf);
-	if (p_buf)
-		*p_buf = NULL;
-	if (p_read_sz)
-		*p_read_sz = 0;
-	return err;
-}
-
-static inline void
-force_set_env(const char *var, const char *value)
-{
-	if (value) {
-		setenv(var, value, 1);
-		pr_debug("set env: %s=%s\n", var, value);
-	} else {
-		unsetenv(var);
-		pr_debug("unset env: %s\n", var);
-	}
-}
-
-static void
-version_notice(void)
-{
-	pr_err(
-"     \tLLVM 3.7 or newer is required. Which can be found from http://llvm.org\n"
-"     \tYou may want to try git trunk:\n"
-"     \t\tgit clone http://llvm.org/git/llvm.git\n"
-"     \t\t     and\n"
-"     \t\tgit clone http://llvm.org/git/clang.git\n\n"
-"     \tOr fetch the latest clang/llvm 3.7 from pre-built llvm packages for\n"
-"     \tdebian/ubuntu:\n"
-"     \t\thttps://apt.llvm.org/\n\n"
-"     \tIf you are using old version of clang, change 'clang-bpf-cmd-template'\n"
-"     \toption in [llvm] section of ~/.perfconfig to:\n\n"
-"     \t  \"$CLANG_EXEC $CLANG_OPTIONS $KERNEL_INC_OPTIONS $PERF_BPF_INC_OPTIONS \\\n"
-"     \t     -working-directory $WORKING_DIR -c $CLANG_SOURCE \\\n"
-"     \t     -emit-llvm -o - | /path/to/llc -march=bpf -filetype=obj -o -\"\n"
-"     \t(Replace /path/to/llc with path to your llc)\n\n"
-);
-}
-
-static int detect_kbuild_dir(char **kbuild_dir)
-{
-	const char *test_dir = llvm_param.kbuild_dir;
-	const char *prefix_dir = "";
-	const char *suffix_dir = "";
-
-	/* _UTSNAME_LENGTH is 65 */
-	char release[128];
-
-	char *autoconf_path;
-
-	int err;
-
-	if (!test_dir) {
-		err = fetch_kernel_version(NULL, release,
-					   sizeof(release));
-		if (err)
-			return -EINVAL;
-
-		test_dir = release;
-		prefix_dir = "/lib/modules/";
-		suffix_dir = "/build";
-	}
-
-	err = asprintf(&autoconf_path, "%s%s%s/include/generated/autoconf.h",
-		       prefix_dir, test_dir, suffix_dir);
-	if (err < 0)
-		return -ENOMEM;
-
-	if (access(autoconf_path, R_OK) == 0) {
-		free(autoconf_path);
-
-		err = asprintf(kbuild_dir, "%s%s%s", prefix_dir, test_dir,
-			       suffix_dir);
-		if (err < 0)
-			return -ENOMEM;
-		return 0;
-	}
-	pr_debug("%s: Couldn't find \"%s\", missing kernel-devel package?.\n",
-		 __func__, autoconf_path);
-	free(autoconf_path);
-	return -ENOENT;
-}
-
-static const char *kinc_fetch_script =
-"#!/usr/bin/env sh\n"
-"if ! test -d \"$KBUILD_DIR\"\n"
-"then\n"
-"	exit 1\n"
-"fi\n"
-"if ! test -f \"$KBUILD_DIR/include/generated/autoconf.h\"\n"
-"then\n"
-"	exit 1\n"
-"fi\n"
-"TMPDIR=`mktemp -d`\n"
-"if test -z \"$TMPDIR\"\n"
-"then\n"
-"    exit 1\n"
-"fi\n"
-"cat << EOF > $TMPDIR/Makefile\n"
-"obj-y := dummy.o\n"
-"\\$(obj)/%.o: \\$(src)/%.c\n"
-"\t@echo -n \"\\$(NOSTDINC_FLAGS) \\$(LINUXINCLUDE) \\$(EXTRA_CFLAGS)\"\n"
-"\t\\$(CC) -c -o \\$@ \\$<\n"
-"EOF\n"
-"touch $TMPDIR/dummy.c\n"
-"make -s -C $KBUILD_DIR M=$TMPDIR $KBUILD_OPTS dummy.o 2>/dev/null\n"
-"RET=$?\n"
-"rm -rf $TMPDIR\n"
-"exit $RET\n";
-
-void llvm__get_kbuild_opts(char **kbuild_dir, char **kbuild_include_opts)
-{
-	static char *saved_kbuild_dir;
-	static char *saved_kbuild_include_opts;
-	int err;
-
-	if (!kbuild_dir || !kbuild_include_opts)
-		return;
-
-	*kbuild_dir = NULL;
-	*kbuild_include_opts = NULL;
-
-	if (saved_kbuild_dir && saved_kbuild_include_opts &&
-	    !IS_ERR(saved_kbuild_dir) && !IS_ERR(saved_kbuild_include_opts)) {
-		*kbuild_dir = strdup(saved_kbuild_dir);
-		*kbuild_include_opts = strdup(saved_kbuild_include_opts);
-
-		if (*kbuild_dir && *kbuild_include_opts)
-			return;
-
-		zfree(kbuild_dir);
-		zfree(kbuild_include_opts);
-		/*
-		 * Don't fall through: it may breaks saved_kbuild_dir and
-		 * saved_kbuild_include_opts if detect them again when
-		 * memory is low.
-		 */
-		return;
-	}
-
-	if (llvm_param.kbuild_dir && !llvm_param.kbuild_dir[0]) {
-		pr_debug("[llvm.kbuild-dir] is set to \"\" deliberately.\n");
-		pr_debug("Skip kbuild options detection.\n");
-		goto errout;
-	}
-
-	err = detect_kbuild_dir(kbuild_dir);
-	if (err) {
-		pr_warning(
-"WARNING:\tunable to get correct kernel building directory.\n"
-"Hint:\tSet correct kbuild directory using 'kbuild-dir' option in [llvm]\n"
-"     \tsection of ~/.perfconfig or set it to \"\" to suppress kbuild\n"
-"     \tdetection.\n\n");
-		goto errout;
-	}
-
-	pr_debug("Kernel build dir is set to %s\n", *kbuild_dir);
-	force_set_env("KBUILD_DIR", *kbuild_dir);
-	force_set_env("KBUILD_OPTS", llvm_param.kbuild_opts);
-	err = read_from_pipe(kinc_fetch_script,
-			     (void **)kbuild_include_opts,
-			     NULL);
-	if (err) {
-		pr_warning(
-"WARNING:\tunable to get kernel include directories from '%s'\n"
-"Hint:\tTry set clang include options using 'clang-bpf-cmd-template'\n"
-"     \toption in [llvm] section of ~/.perfconfig and set 'kbuild-dir'\n"
-"     \toption in [llvm] to \"\" to suppress this detection.\n\n",
-			*kbuild_dir);
-
-		zfree(kbuild_dir);
-		goto errout;
-	}
-
-	pr_debug("include option is set to %s\n", *kbuild_include_opts);
-
-	saved_kbuild_dir = strdup(*kbuild_dir);
-	saved_kbuild_include_opts = strdup(*kbuild_include_opts);
-
-	if (!saved_kbuild_dir || !saved_kbuild_include_opts) {
-		zfree(&saved_kbuild_dir);
-		zfree(&saved_kbuild_include_opts);
-	}
-	return;
-errout:
-	saved_kbuild_dir = ERR_PTR(-EINVAL);
-	saved_kbuild_include_opts = ERR_PTR(-EINVAL);
-}
-
-int llvm__get_nr_cpus(void)
-{
-	static int nr_cpus_avail = 0;
-	char serr[STRERR_BUFSIZE];
-
-	if (nr_cpus_avail > 0)
-		return nr_cpus_avail;
-
-	nr_cpus_avail = sysconf(_SC_NPROCESSORS_CONF);
-	if (nr_cpus_avail <= 0) {
-		pr_err(
-"WARNING:\tunable to get available CPUs in this system: %s\n"
-"        \tUse 128 instead.\n", str_error_r(errno, serr, sizeof(serr)));
-		nr_cpus_avail = 128;
-	}
-	return nr_cpus_avail;
-}
-
-void llvm__dump_obj(const char *path, void *obj_buf, size_t size)
-{
-	char *obj_path = strdup(path);
-	FILE *fp;
-	char *p;
-
-	if (!obj_path) {
-		pr_warning("WARNING: Not enough memory, skip object dumping\n");
-		return;
-	}
-
-	p = strrchr(obj_path, '.');
-	if (!p || (strcmp(p, ".c") != 0)) {
-		pr_warning("WARNING: invalid llvm source path: '%s', skip object dumping\n",
-			   obj_path);
-		goto out;
-	}
-
-	p[1] = 'o';
-	fp = fopen(obj_path, "wb");
-	if (!fp) {
-		pr_warning("WARNING: failed to open '%s': %s, skip object dumping\n",
-			   obj_path, strerror(errno));
-		goto out;
-	}
-
-	pr_debug("LLVM: dumping %s\n", obj_path);
-	if (fwrite(obj_buf, size, 1, fp) != 1)
-		pr_debug("WARNING: failed to write to file '%s': %s, skip object dumping\n", obj_path, strerror(errno));
-	fclose(fp);
-out:
-	free(obj_path);
-}
-
-int llvm__compile_bpf(const char *path, void **p_obj_buf,
-		      size_t *p_obj_buf_sz)
-{
-	size_t obj_buf_sz;
-	void *obj_buf = NULL;
-	int err, nr_cpus_avail;
-	unsigned int kernel_version;
-	char linux_version_code_str[64];
-	const char *clang_opt = llvm_param.clang_opt;
-	char clang_path[PATH_MAX], llc_path[PATH_MAX], abspath[PATH_MAX], nr_cpus_avail_str[64];
-	char serr[STRERR_BUFSIZE];
-	char *kbuild_dir = NULL, *kbuild_include_opts = NULL,
-	     *perf_bpf_include_opts = NULL;
-	const char *template = llvm_param.clang_bpf_cmd_template;
-	char *pipe_template = NULL;
-	const char *opts = llvm_param.opts;
-	char *command_echo = NULL, *command_out;
-	char *libbpf_include_dir = system_path(LIBBPF_INCLUDE_DIR);
-
-	if (path[0] != '-' && realpath(path, abspath) == NULL) {
-		err = errno;
-		pr_err("ERROR: problems with path %s: %s\n",
-		       path, str_error_r(err, serr, sizeof(serr)));
-		return -err;
-	}
-
-	if (!template)
-		template = CLANG_BPF_CMD_DEFAULT_TEMPLATE;
-
-	err = search_program_and_warn(llvm_param.clang_path,
-			     "clang", clang_path);
-	if (err)
-		return -ENOENT;
-
-	/*
-	 * This is an optional work. Even it fail we can continue our
-	 * work. Needn't check error return.
-	 */
-	llvm__get_kbuild_opts(&kbuild_dir, &kbuild_include_opts);
-
-	nr_cpus_avail = llvm__get_nr_cpus();
-	snprintf(nr_cpus_avail_str, sizeof(nr_cpus_avail_str), "%d",
-		 nr_cpus_avail);
-
-	if (fetch_kernel_version(&kernel_version, NULL, 0))
-		kernel_version = 0;
-
-	snprintf(linux_version_code_str, sizeof(linux_version_code_str),
-		 "0x%x", kernel_version);
-	if (asprintf(&perf_bpf_include_opts, "-I%s/", libbpf_include_dir) < 0)
-		goto errout;
-	force_set_env("NR_CPUS", nr_cpus_avail_str);
-	force_set_env("LINUX_VERSION_CODE", linux_version_code_str);
-	force_set_env("CLANG_EXEC", clang_path);
-	force_set_env("CLANG_OPTIONS", clang_opt);
-	force_set_env("KERNEL_INC_OPTIONS", kbuild_include_opts);
-	force_set_env("PERF_BPF_INC_OPTIONS", perf_bpf_include_opts);
-	force_set_env("WORKING_DIR", kbuild_dir ? : ".");
-
-	if (opts) {
-		err = search_program_and_warn(llvm_param.llc_path, "llc", llc_path);
-		if (err)
-			goto errout;
-
-		err = -ENOMEM;
-		if (asprintf(&pipe_template, "%s -emit-llvm | %s -march=bpf %s -filetype=obj -o -",
-			      template, llc_path, opts) < 0) {
-			pr_err("ERROR:\tnot enough memory to setup command line\n");
-			goto errout;
-		}
-
-		template = pipe_template;
-
-	}
-
-	/*
-	 * Since we may reset clang's working dir, path of source file
-	 * should be transferred into absolute path, except we want
-	 * stdin to be source file (testing).
-	 */
-	force_set_env("CLANG_SOURCE",
-		      (path[0] == '-') ? path : abspath);
-
-	pr_debug("llvm compiling command template: %s\n", template);
-
-	/*
-	 * Below, substitute control characters for values that can cause the
-	 * echo to misbehave, then substitute the values back.
-	 */
-	err = -ENOMEM;
-	if (asprintf(&command_echo, "echo -n \a%s\a", template) < 0)
-		goto errout;
-
-#define SWAP_CHAR(a, b) do { if (*p == a) *p = b; } while (0)
-	for (char *p = command_echo; *p; p++) {
-		SWAP_CHAR('<', '\001');
-		SWAP_CHAR('>', '\002');
-		SWAP_CHAR('"', '\003');
-		SWAP_CHAR('\'', '\004');
-		SWAP_CHAR('|', '\005');
-		SWAP_CHAR('&', '\006');
-		SWAP_CHAR('\a', '"');
-	}
-	err = read_from_pipe(command_echo, (void **) &command_out, NULL);
-	if (err)
-		goto errout;
-
-	for (char *p = command_out; *p; p++) {
-		SWAP_CHAR('\001', '<');
-		SWAP_CHAR('\002', '>');
-		SWAP_CHAR('\003', '"');
-		SWAP_CHAR('\004', '\'');
-		SWAP_CHAR('\005', '|');
-		SWAP_CHAR('\006', '&');
-	}
-#undef SWAP_CHAR
-	pr_debug("llvm compiling command : %s\n", command_out);
-
-	err = read_from_pipe(template, &obj_buf, &obj_buf_sz);
-	if (err) {
-		pr_err("ERROR:\tunable to compile %s\n", path);
-		pr_err("Hint:\tCheck error message shown above.\n");
-		pr_err("Hint:\tYou can also pre-compile it into .o using:\n");
-		pr_err("     \t\tclang --target=bpf -O2 -c %s\n", path);
-		pr_err("     \twith proper -I and -D options.\n");
-		goto errout;
-	}
-
-	free(command_echo);
-	free(command_out);
-	free(kbuild_dir);
-	free(kbuild_include_opts);
-	free(perf_bpf_include_opts);
-	free(libbpf_include_dir);
-
-	if (!p_obj_buf)
-		free(obj_buf);
-	else
-		*p_obj_buf = obj_buf;
-
-	if (p_obj_buf_sz)
-		*p_obj_buf_sz = obj_buf_sz;
-	return 0;
-errout:
-	free(command_echo);
-	free(kbuild_dir);
-	free(kbuild_include_opts);
-	free(obj_buf);
-	free(perf_bpf_include_opts);
-	free(libbpf_include_dir);
-	free(pipe_template);
-	if (p_obj_buf)
-		*p_obj_buf = NULL;
-	if (p_obj_buf_sz)
-		*p_obj_buf_sz = 0;
-	return err;
-}
-
-int llvm__search_clang(void)
-{
-	char clang_path[PATH_MAX];
-
-	return search_program_and_warn(llvm_param.clang_path, "clang", clang_path);
-}
diff --git a/tools/perf/util/llvm-utils.h b/tools/perf/util/llvm-utils.h
deleted file mode 100644
index 7878a0e3fa98..000000000000
--- a/tools/perf/util/llvm-utils.h
+++ /dev/null
@@ -1,69 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 2015, Wang Nan <wangnan0@huawei.com>
- * Copyright (C) 2015, Huawei Inc.
- */
-#ifndef __LLVM_UTILS_H
-#define __LLVM_UTILS_H
-
-#include <stdbool.h>
-
-struct llvm_param {
-	/* Path of clang executable */
-	const char *clang_path;
-	/* Path of llc executable */
-	const char *llc_path;
-	/*
-	 * Template of clang bpf compiling. 5 env variables
-	 * can be used:
-	 *   $CLANG_EXEC:		Path to clang.
-	 *   $CLANG_OPTIONS:		Extra options to clang.
-	 *   $KERNEL_INC_OPTIONS:	Kernel include directories.
-	 *   $WORKING_DIR:		Kernel source directory.
-	 *   $CLANG_SOURCE:		Source file to be compiled.
-	 */
-	const char *clang_bpf_cmd_template;
-	/* Will be filled in $CLANG_OPTIONS */
-	const char *clang_opt;
-	/*
-	 * If present it'll add -emit-llvm to $CLANG_OPTIONS to pipe
-	 * the clang output to llc, useful for new llvm options not
-	 * yet selectable via 'clang -mllvm option', such as -mattr=dwarfris
-	 * in clang 6.0/llvm 7
-	 */
-	const char *opts;
-	/* Where to find kbuild system */
-	const char *kbuild_dir;
-	/*
-	 * Arguments passed to make, like 'ARCH=arm' if doing cross
-	 * compiling. Should not be used for dynamic compiling.
-	 */
-	const char *kbuild_opts;
-	/*
-	 * Default is false. If set to true, write compiling result
-	 * to object file.
-	 */
-	bool dump_obj;
-	/*
-	 * Default is false. If one of the above fields is set by user
-	 * explicitly then user_set_llvm is set to true. This is used
-	 * for perf test. If user doesn't set anything in .perfconfig
-	 * and clang is not found, don't trigger llvm test.
-	 */
-	bool user_set_param;
-};
-
-extern struct llvm_param llvm_param;
-int perf_llvm_config(const char *var, const char *value);
-
-int llvm__compile_bpf(const char *path, void **p_obj_buf, size_t *p_obj_buf_sz);
-
-/* This function is for test__llvm() use only */
-int llvm__search_clang(void);
-
-/* Following functions are reused by builtin clang support */
-void llvm__get_kbuild_opts(char **kbuild_dir, char **kbuild_include_opts);
-int llvm__get_nr_cpus(void);
-
-void llvm__dump_obj(const char *path, void *obj_buf, size_t size);
-#endif
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 0b5075ef00c8..00a8ec94f5b2 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -14,7 +14,6 @@
 #include "parse-events.h"
 #include "string2.h"
 #include "strlist.h"
-#include "bpf-loader.h"
 #include "debug.h"
 #include <api/fs/tracing_path.h>
 #include <perf/cpumap.h>
@@ -648,272 +647,6 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
 }
 #endif /* HAVE_LIBTRACEEVENT */
 
-#ifdef HAVE_LIBBPF_SUPPORT
-struct __add_bpf_event_param {
-	struct parse_events_state *parse_state;
-	struct list_head *list;
-	struct list_head *head_config;
-	YYLTYPE *loc;
-};
-
-static int add_bpf_event(const char *group, const char *event, int fd, struct bpf_object *obj,
-			 void *_param)
-{
-	LIST_HEAD(new_evsels);
-	struct __add_bpf_event_param *param = _param;
-	struct parse_events_state *parse_state = param->parse_state;
-	struct list_head *list = param->list;
-	struct evsel *pos;
-	int err;
-	/*
-	 * Check if we should add the event, i.e. if it is a TP but starts with a '!',
-	 * then don't add the tracepoint, this will be used for something else, like
-	 * adding to a BPF_MAP_TYPE_PROG_ARRAY.
-	 *
-	 * See tools/perf/examples/bpf/augmented_raw_syscalls.c
-	 */
-	if (group[0] == '!')
-		return 0;
-
-	pr_debug("add bpf event %s:%s and attach bpf program %d\n",
-		 group, event, fd);
-
-	err = parse_events_add_tracepoint(&new_evsels, &parse_state->idx, group,
-					  event, parse_state->error,
-					  param->head_config, param->loc);
-	if (err) {
-		struct evsel *evsel, *tmp;
-
-		pr_debug("Failed to add BPF event %s:%s\n",
-			 group, event);
-		list_for_each_entry_safe(evsel, tmp, &new_evsels, core.node) {
-			list_del_init(&evsel->core.node);
-			evsel__delete(evsel);
-		}
-		return err;
-	}
-	pr_debug("adding %s:%s\n", group, event);
-
-	list_for_each_entry(pos, &new_evsels, core.node) {
-		pr_debug("adding %s:%s to %p\n",
-			 group, event, pos);
-		pos->bpf_fd = fd;
-		pos->bpf_obj = obj;
-	}
-	list_splice(&new_evsels, list);
-	return 0;
-}
-
-int parse_events_load_bpf_obj(struct parse_events_state *parse_state,
-			      struct list_head *list,
-			      struct bpf_object *obj,
-			      struct list_head *head_config,
-			      void *loc)
-{
-	int err;
-	char errbuf[BUFSIZ];
-	struct __add_bpf_event_param param = {parse_state, list, head_config, loc};
-	static bool registered_unprobe_atexit = false;
-	YYLTYPE test_loc = {.first_column = -1};
-
-	if (IS_ERR(obj) || !obj) {
-		snprintf(errbuf, sizeof(errbuf),
-			 "Internal error: load bpf obj with NULL");
-		err = -EINVAL;
-		goto errout;
-	}
-
-	/*
-	 * Register atexit handler before calling bpf__probe() so
-	 * bpf__probe() don't need to unprobe probe points its already
-	 * created when failure.
-	 */
-	if (!registered_unprobe_atexit) {
-		atexit(bpf__clear);
-		registered_unprobe_atexit = true;
-	}
-
-	err = bpf__probe(obj);
-	if (err) {
-		bpf__strerror_probe(obj, err, errbuf, sizeof(errbuf));
-		goto errout;
-	}
-
-	err = bpf__load(obj);
-	if (err) {
-		bpf__strerror_load(obj, err, errbuf, sizeof(errbuf));
-		goto errout;
-	}
-
-	if (!param.loc)
-		param.loc = &test_loc;
-
-	err = bpf__foreach_event(obj, add_bpf_event, &param);
-	if (err) {
-		snprintf(errbuf, sizeof(errbuf),
-			 "Attach events in BPF object failed");
-		goto errout;
-	}
-
-	return 0;
-errout:
-	parse_events_error__handle(parse_state->error, param.loc ? param.loc->first_column : 0,
-				strdup(errbuf), strdup("(add -v to see detail)"));
-	return err;
-}
-
-static int
-parse_events_config_bpf(struct parse_events_state *parse_state,
-			struct bpf_object *obj,
-			struct list_head *head_config)
-{
-	struct parse_events_term *term;
-	int error_pos = 0;
-
-	if (!head_config || list_empty(head_config))
-		return 0;
-
-	list_for_each_entry(term, head_config, list) {
-		int err;
-
-		if (term->type_term != PARSE_EVENTS__TERM_TYPE_USER) {
-			parse_events_error__handle(parse_state->error, term->err_term,
-						strdup("Invalid config term for BPF object"),
-						NULL);
-			return -EINVAL;
-		}
-
-		err = bpf__config_obj(obj, term, parse_state->evlist, &error_pos);
-		if (err) {
-			char errbuf[BUFSIZ];
-			int idx;
-
-			bpf__strerror_config_obj(obj, term, parse_state->evlist,
-						 &error_pos, err, errbuf,
-						 sizeof(errbuf));
-
-			if (err == -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE)
-				idx = term->err_val;
-			else
-				idx = term->err_term + error_pos;
-
-			parse_events_error__handle(parse_state->error, idx,
-						strdup(errbuf),
-						NULL);
-			return err;
-		}
-	}
-	return 0;
-}
-
-/*
- * Split config terms:
- * perf record -e bpf.c/call-graph=fp,map:array.value[0]=1/ ...
- *  'call-graph=fp' is 'evt config', should be applied to each
- *  events in bpf.c.
- * 'map:array.value[0]=1' is 'obj config', should be processed
- * with parse_events_config_bpf.
- *
- * Move object config terms from the first list to obj_head_config.
- */
-static void
-split_bpf_config_terms(struct list_head *evt_head_config,
-		       struct list_head *obj_head_config)
-{
-	struct parse_events_term *term, *temp;
-
-	/*
-	 * Currently, all possible user config term
-	 * belong to bpf object. parse_events__is_hardcoded_term()
-	 * happens to be a good flag.
-	 *
-	 * See parse_events_config_bpf() and
-	 * config_term_tracepoint().
-	 */
-	list_for_each_entry_safe(term, temp, evt_head_config, list)
-		if (!parse_events__is_hardcoded_term(term))
-			list_move_tail(&term->list, obj_head_config);
-}
-
-int parse_events_load_bpf(struct parse_events_state *parse_state,
-			  struct list_head *list,
-			  char *bpf_file_name,
-			  bool source,
-			  struct list_head *head_config,
-			  void *loc_)
-{
-	int err;
-	struct bpf_object *obj;
-	LIST_HEAD(obj_head_config);
-	YYLTYPE *loc = loc_;
-
-	if (head_config)
-		split_bpf_config_terms(head_config, &obj_head_config);
-
-	obj = bpf__prepare_load(bpf_file_name, source);
-	if (IS_ERR(obj)) {
-		char errbuf[BUFSIZ];
-
-		err = PTR_ERR(obj);
-
-		if (err == -ENOTSUP)
-			snprintf(errbuf, sizeof(errbuf),
-				 "BPF support is not compiled");
-		else
-			bpf__strerror_prepare_load(bpf_file_name,
-						   source,
-						   -err, errbuf,
-						   sizeof(errbuf));
-
-		parse_events_error__handle(parse_state->error, loc->first_column,
-					strdup(errbuf), strdup("(add -v to see detail)"));
-		return err;
-	}
-
-	err = parse_events_load_bpf_obj(parse_state, list, obj, head_config, loc);
-	if (err)
-		return err;
-	err = parse_events_config_bpf(parse_state, obj, &obj_head_config);
-
-	/*
-	 * Caller doesn't know anything about obj_head_config,
-	 * so combine them together again before returning.
-	 */
-	if (head_config)
-		list_splice_tail(&obj_head_config, head_config);
-	return err;
-}
-#else // HAVE_LIBBPF_SUPPORT
-int parse_events_load_bpf_obj(struct parse_events_state *parse_state,
-			      struct list_head *list __maybe_unused,
-			      struct bpf_object *obj __maybe_unused,
-			      struct list_head *head_config __maybe_unused,
-			      void *loc_)
-{
-	YYLTYPE *loc = loc_;
-
-	parse_events_error__handle(parse_state->error, loc->first_column,
-				   strdup("BPF support is not compiled"),
-				   strdup("Make sure libbpf-devel is available at build time."));
-	return -ENOTSUP;
-}
-
-int parse_events_load_bpf(struct parse_events_state *parse_state,
-			  struct list_head *list __maybe_unused,
-			  char *bpf_file_name __maybe_unused,
-			  bool source __maybe_unused,
-			  struct list_head *head_config __maybe_unused,
-			  void *loc_)
-{
-	YYLTYPE *loc = loc_;
-
-	parse_events_error__handle(parse_state->error, loc->first_column,
-				   strdup("BPF support is not compiled"),
-				   strdup("Make sure libbpf-devel is available at build time."));
-	return -ENOTSUP;
-}
-#endif // HAVE_LIBBPF_SUPPORT
-
 static int
 parse_breakpoint_type(const char *type, struct perf_event_attr *attr)
 {
@@ -2274,7 +2007,6 @@ int __parse_events(struct evlist *evlist, const char *str, const char *pmu_filte
 		.list	  = LIST_HEAD_INIT(parse_state.list),
 		.idx	  = evlist->core.nr_entries,
 		.error	  = err,
-		.evlist	  = evlist,
 		.stoken	  = PE_START_EVENTS,
 		.fake_pmu = fake_pmu,
 		.pmu_filter = pmu_filter,
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index b77ff619a623..411f69b2ac3a 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -118,8 +118,6 @@ struct parse_events_state {
 	int			   idx;
 	/* Error information. */
 	struct parse_events_error *error;
-	/* Used by BPF event creation. */
-	struct evlist		  *evlist;
 	/* Holds returned terms for term parsing. */
 	struct list_head	  *terms;
 	/* Start token. */
@@ -160,19 +158,6 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx,
 				const char *sys, const char *event,
 				struct parse_events_error *error,
 				struct list_head *head_config, void *loc);
-int parse_events_load_bpf(struct parse_events_state *parse_state,
-			  struct list_head *list,
-			  char *bpf_file_name,
-			  bool source,
-			  struct list_head *head_config,
-			  void *loc);
-/* Provide this function for perf test */
-struct bpf_object;
-int parse_events_load_bpf_obj(struct parse_events_state *parse_state,
-			      struct list_head *list,
-			      struct bpf_object *obj,
-			      struct list_head *head_config,
-			      void *loc);
 int parse_events_add_numeric(struct parse_events_state *parse_state,
 			     struct list_head *list,
 			     u32 type, u64 config,
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index d7d084cc4140..1147084b2c76 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -68,31 +68,6 @@ static int lc_str(yyscan_t scanner, const struct parse_events_state *state)
 	return str(scanner, state->match_legacy_cache_terms ? PE_LEGACY_CACHE : PE_NAME);
 }
 
-static bool isbpf_suffix(char *text)
-{
-	int len = strlen(text);
-
-	if (len < 2)
-		return false;
-	if ((text[len - 1] == 'c' || text[len - 1] == 'o') &&
-	    text[len - 2] == '.')
-		return true;
-	if (len > 4 && !strcmp(text + len - 4, ".obj"))
-		return true;
-	return false;
-}
-
-static bool isbpf(yyscan_t scanner)
-{
-	char *text = parse_events_get_text(scanner);
-	struct stat st;
-
-	if (!isbpf_suffix(text))
-		return false;
-
-	return stat(text, &st) == 0;
-}
-
 /*
  * This function is called when the parser gets two kind of input:
  *
@@ -179,8 +154,6 @@ do {							\
 group		[^,{}/]*[{][^}]*[}][^,{}/]*
 event_pmu	[^,{}/]+[/][^/]*[/][^,{}/]*
 event		[^,{}/]+
-bpf_object	[^,{}]+\.(o|bpf)[a-zA-Z0-9._]*
-bpf_source	[^,{}]+\.c[a-zA-Z0-9._]*
 
 num_dec		[0-9]+
 num_hex		0x[a-fA-F0-9]+
@@ -233,8 +206,6 @@ non_digit	[^0-9]
 		}
 
 {event_pmu}	|
-{bpf_object}	|
-{bpf_source}	|
 {event}		{
 			BEGIN(INITIAL);
 			REWIND(1);
@@ -363,8 +334,6 @@ r{num_raw_hex}		{ return str(yyscanner, PE_RAW); }
 {num_hex}		{ return value(yyscanner, 16); }
 
 {modifier_event}	{ return str(yyscanner, PE_MODIFIER_EVENT); }
-{bpf_object}		{ if (!isbpf(yyscanner)) { USER_REJECT }; return str(yyscanner, PE_BPF_OBJECT); }
-{bpf_source}		{ if (!isbpf(yyscanner)) { USER_REJECT }; return str(yyscanner, PE_BPF_SOURCE); }
 {name}			{ return str(yyscanner, PE_NAME); }
 {name_tag}		{ return str(yyscanner, PE_NAME); }
 "/"			{ BEGIN(config); return '/'; }
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index c3517e3498d7..00da1f8c0baf 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -60,7 +60,6 @@ static void free_list_evsel(struct list_head* list_evsel)
 %token PE_VALUE_SYM_TOOL
 %token PE_EVENT_NAME
 %token PE_RAW PE_NAME
-%token PE_BPF_OBJECT PE_BPF_SOURCE
 %token PE_MODIFIER_EVENT PE_MODIFIER_BP PE_BP_COLON PE_BP_SLASH
 %token PE_LEGACY_CACHE
 %token PE_PREFIX_MEM
@@ -75,8 +74,6 @@ static void free_list_evsel(struct list_head* list_evsel)
 %type <num> value_sym
 %type <str> PE_RAW
 %type <str> PE_NAME
-%type <str> PE_BPF_OBJECT
-%type <str> PE_BPF_SOURCE
 %type <str> PE_LEGACY_CACHE
 %type <str> PE_MODIFIER_EVENT
 %type <str> PE_MODIFIER_BP
@@ -97,7 +94,6 @@ static void free_list_evsel(struct list_head* list_evsel)
 %type <list_evsel> event_legacy_tracepoint
 %type <list_evsel> event_legacy_numeric
 %type <list_evsel> event_legacy_raw
-%type <list_evsel> event_bpf_file
 %type <list_evsel> event_def
 %type <list_evsel> event_mod
 %type <list_evsel> event_name
@@ -271,8 +267,7 @@ event_def: event_pmu |
 	   event_legacy_mem sep_dc |
 	   event_legacy_tracepoint sep_dc |
 	   event_legacy_numeric sep_dc |
-	   event_legacy_raw sep_dc |
-	   event_bpf_file
+	   event_legacy_raw sep_dc
 
 event_pmu:
 PE_NAME opt_pmu_config
@@ -620,43 +615,6 @@ PE_RAW opt_event_config
 	$$ = list;
 }
 
-event_bpf_file:
-PE_BPF_OBJECT opt_event_config
-{
-	struct parse_events_state *parse_state = _parse_state;
-	struct list_head *list;
-	int err;
-
-	list = alloc_list();
-	if (!list)
-		YYNOMEM;
-	err = parse_events_load_bpf(parse_state, list, $1, false, $2, &@1);
-	parse_events_terms__delete($2);
-	free($1);
-	if (err) {
-		free(list);
-		PE_ABORT(err);
-	}
-	$$ = list;
-}
-|
-PE_BPF_SOURCE opt_event_config
-{
-	struct list_head *list;
-	int err;
-
-	list = alloc_list();
-	if (!list)
-		YYNOMEM;
-	err = parse_events_load_bpf(_parse_state, list, $1, true, $2, &@1);
-	parse_events_terms__delete($2);
-	if (err) {
-		free(list);
-		PE_ABORT(err);
-	}
-	$$ = list;
-}
-
 opt_event_config:
 '/' event_config '/'
 {

From 5e6da6be3082f77be06894a1a94d52a90b4007dc Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 10 Aug 2023 11:48:51 -0700
Subject: [PATCH 0411/1189] perf trace: Migrate BPF augmentation to use a
 skeleton

Previously a BPF event of augmented_raw_syscalls.c could be used to
enable augmentation of syscalls by perf trace. As BPF events are no
longer supported, switch to using a BPF skeleton which when attached
explicitly opens the sysenter and sysexit tracepoints.

The dump map is removed as debugging wasn't supported by the
augmentation and bpf_printk can be used when necessary.

Remove tools/perf/examples/bpf/augmented_raw_syscalls.c so that the
rename/migration to a BPF skeleton captures that this was the source.

Committer notes:

Some minor stylistic changes to help visualizing the diff.

Use libbpf_strerror when failing to load the augmented raw syscalls BPF.

Use  bpf_object__for_each_program(prog, trace.skel->obj) to disable auto
attachment for all but the sys_enter, sys_exit tracepoints, to avoid
having to add extra lines as we go adding support for more pointer
receiving syscalls.

Committer testing:

  # perf trace -e open*  --max-events=10
     0.000 ( 0.022 ms): systemd-oomd/1151 openat(dfd: CWD, filename: "/proc/meminfo", flags: RDONLY|CLOEXEC)    = 11
   208.833 (         ): gnome-terminal/3223 openat(dfd: CWD, filename: "/proc/51250/cmdline")                  ...
   249.993 ( 0.024 ms): systemd-oomd/1151 openat(dfd: CWD, filename: "/proc/meminfo", flags: RDONLY|CLOEXEC)    = 11
   250.118 ( 0.030 ms): systemd-oomd/1151 openat(dfd: CWD, filename: "/sys/fs/cgroup/user.slice/user-1000.slice/user@1000.service/memory.pressure", flags: RDONLY|CLOEXEC) = 11
   250.205 ( 0.016 ms): systemd-oomd/1151 openat(dfd: CWD, filename: "/sys/fs/cgroup/user.slice/user-1000.slice/user@1000.service/memory.current", flags: RDONLY|CLOEXEC) = 11
   250.244 ( 0.014 ms): systemd-oomd/1151 openat(dfd: CWD, filename: "/sys/fs/cgroup/user.slice/user-1000.slice/user@1000.service/memory.min", flags: RDONLY|CLOEXEC) = 11
   250.282 ( 0.014 ms): systemd-oomd/1151 openat(dfd: CWD, filename: "/sys/fs/cgroup/user.slice/user-1000.slice/user@1000.service/memory.low", flags: RDONLY|CLOEXEC) = 11
   250.320 ( 0.014 ms): systemd-oomd/1151 openat(dfd: CWD, filename: "/sys/fs/cgroup/user.slice/user-1000.slice/user@1000.service/memory.swap.current", flags: RDONLY|CLOEXEC) = 11
   250.355 ( 0.014 ms): systemd-oomd/1151 openat(dfd: CWD, filename: "/sys/fs/cgroup/user.slice/user-1000.slice/user@1000.service/memory.stat", flags: RDONLY|CLOEXEC) = 11
   250.717 ( 0.016 ms): systemd-oomd/1151 openat(dfd: CWD, filename: "/sys/fs/cgroup/user.slice/user-1001.slice/user@1001.service/memory.pressure", flags: RDONLY|CLOEXEC) = 11
  #
  # perf trace -e *nanosleep*  --max-events=10
         ? (         ): SCTP timer/28304  ... [continued]: clock_nanosleep())                                  = 0
     0.007 (10.058 ms): SCTP timer/28304 clock_nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }, rmtp: 0x7f0466b78de0) = 0
    10.069 (         ): SCTP timer/28304 clock_nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }, rmtp: 0x7f0466b78de0) ...
    10.069 (10.056 ms): SCTP timer/28304  ... [continued]: clock_nanosleep())                                  = 0
    17.059 (         ): podman/3572 nanosleep(rqtp: 0x7fc4f4d75be0)                                    ...
    17.059 (10.061 ms): podman/3572  ... [continued]: nanosleep())                                        = 0
    20.131 (10.059 ms): SCTP timer/28304 clock_nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }, rmtp: 0x7f0466b78de0) = 0
    30.195 (10.038 ms): SCTP timer/28304 clock_nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }, rmtp: 0x7f0466b78de0) = 0
    40.238 (10.057 ms): SCTP timer/28304 clock_nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }, rmtp: 0x7f0466b78de0) = 0
    50.301 (         ): SCTP timer/28304 clock_nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }, rmtp: 0x7f0466b78de0) ...
  #

  # perf trace -e perf_event*  -- perf stat -e instructions,cycles,cache-misses sleep 0.1
     0.000 ( 0.011 ms): perf/51331 perf_event_open(attr_uptr: { type: 0 (PERF_TYPE_HARDWARE), size: 136, config: 0x1 (PERF_COUNT_HW_INSTRUCTIONS), sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 51332 (perf), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 3
     0.013 ( 0.003 ms): perf/51331 perf_event_open(attr_uptr: { type: 0 (PERF_TYPE_HARDWARE), size: 136, config: 0 (PERF_COUNT_HW_CPU_CYCLES), sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 51332 (perf), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 4
     0.017 ( 0.002 ms): perf/51331 perf_event_open(attr_uptr: { type: 0 (PERF_TYPE_HARDWARE), size: 136, config: 0x3 (PERF_COUNT_HW_CACHE_MISSES), sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 51332 (perf), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 5

 Performance counter stats for 'sleep 0.1':

         1,495,051      instructions                     #    1.11  insn per cycle
         1,347,641      cycles
            35,424      cache-misses

       0.100935279 seconds time elapsed

       0.000924000 seconds user
       0.000000000 seconds sys

  #

  # perf trace -e connect*  ssh localhost
       0.000 ( 0.012 ms): ssh/51346 connect(fd: 4, uservaddr: { .family: LOCAL, path: /var/lib/sss/pipes/nss }, addrlen: 110) = -1 ECONNREFUSED (Connection refused)
       0.118 ( 0.004 ms): ssh/51346 connect(fd: 6, uservaddr: { .family: LOCAL, path: /var/lib/sss/pipes/nss }, addrlen: 110) = -1 ECONNREFUSED (Connection refused)
       0.399 ( 0.007 ms): ssh/51346 connect(fd: 4, uservaddr: { .family: LOCAL, path: /var/lib/sss/pipes/nss }, addrlen: 110) = -1 ECONNREFUSED (Connection refused)
       0.426 ( 0.003 ms): ssh/51346 connect(fd: 4, uservaddr: { .family: LOCAL, path: /var/lib/sss/pipes/nss }, addrlen: 110) = -1 ECONNREFUSED (Connection refused)
       0.754 ( 0.009 ms): ssh/51346 connect(fd: 4, uservaddr: { .family: INET, port: 22, addr: 127.0.0.1 }, addrlen: 16) = 0
       0.771 ( 0.010 ms): ssh/51346 connect(fd: 4, uservaddr: { .family: INET6, port: 22, addr: ::1 }, addrlen: 28) = 0
       0.798 ( 0.053 ms): ssh/51346 connect(fd: 4, uservaddr: { .family: INET6, port: 22, addr: ::1 }, addrlen: 28) = 0
       0.870 ( 0.004 ms): ssh/51346 connect(fd: 5, uservaddr: { .family: LOCAL, path: /var/lib/sss/pipes/nss }, addrlen: 110) = -1 ECONNREFUSED (Connection refused)
       0.904 ( 0.003 ms): ssh/51346 connect(fd: 5, uservaddr: { .family: LOCAL, path: /var/lib/sss/pipes/nss }, addrlen: 110) = -1 ECONNREFUSED (Connection refused)
       0.930 ( 0.003 ms): ssh/51346 connect(fd: 5, uservaddr: { .family: LOCAL, path: /var/lib/sss/pipes/nss }, addrlen: 110) = -1 ECONNREFUSED (Connection refused)
       0.957 ( 0.003 ms): ssh/51346 connect(fd: 5, uservaddr: { .family: LOCAL, path: /var/lib/sss/pipes/nss }, addrlen: 110) = -1 ECONNREFUSED (Connection refused)
       0.981 ( 0.003 ms): ssh/51346 connect(fd: 5, uservaddr: { .family: LOCAL, path: /var/lib/sss/pipes/nss }, addrlen: 110) = -1 ECONNREFUSED (Connection refused)
       1.006 ( 0.004 ms): ssh/51346 connect(fd: 5, uservaddr: { .family: LOCAL, path: /var/lib/sss/pipes/nss }, addrlen: 110) = -1 ECONNREFUSED (Connection refused)
       1.036 ( 0.005 ms): ssh/51346 connect(fd: 5, uservaddr: { .family: LOCAL, path: /var/lib/sss/pipes/nss }, addrlen: 110) = -1 ECONNREFUSED (Connection refused)
      65.077 ( 0.022 ms): ssh/51346 connect(fd: 5, uservaddr: { .family: LOCAL, path: /var/run/.heim_org.h5l.kcm-socket }, addrlen: 110) = 0
      66.608 ( 0.014 ms): ssh/51346 connect(fd: 5, uservaddr: { .family: LOCAL, path: /var/run/.heim_org.h5l.kcm-socket }, addrlen: 110) = 0
  root@localhost's password:
  #

  # perf trace -e sendto*  ping -c 2 localhost
  PING localhost(localhost (::1)) 56 data bytes
  64 bytes from localhost (::1): icmp_seq=1 ttl=64 time=0.024 ms
       0.000 ( 0.011 ms): ping/51357 sendto(fd: 5, buff: 0x7ffcca35e620, len: 20, addr: { .family: NETLINK }, addr_len: 0xc) = 20
       0.135 ( 0.026 ms): ping/51357 sendto(fd: 4, buff: 0x5601398f7b20, len: 64, addr: { .family: INET6, port: 58, addr: ::1 }, addr_len: 0x1c) = 64
    1014.929 ( 0.050 ms): ping/51357 sendto(fd: 4, buff: 0x5601398f7b20, len: 64, flags: CONFIRM, addr: { .family: INET6, port: 58, addr: ::1 }, addr_len: 0x1c) = 64
  64 bytes from localhost (::1): icmp_seq=2 ttl=64 time=0.046 ms

  --- localhost ping statistics ---
  2 packets transmitted, 2 received, 0% packet loss, time 1015ms
  rtt min/avg/max/mdev = 0.024/0.035/0.046/0.011 ms
  #

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Carsten Haitzler <carsten.haitzler@arm.com>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Fangrui Song <maskray@google.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Cc: Tiezhu Yang <yangtiezhu@loongson.cn>
Cc: Tom Rix <trix@redhat.com>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Wang ShaoBo <bobo.shaobowang@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: Yonghong Song <yhs@fb.com>
Cc: YueHaibing <yuehaibing@huawei.com>
Cc: bpf@vger.kernel.org
Cc: llvm@lists.linux.dev
Link: https://lore.kernel.org/r/20230810184853.2860737-3-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Makefile.perf                      |   1 +
 tools/perf/builtin-trace.c                    | 159 +++++++++++-------
 .../bpf_skel/augmented_raw_syscalls.bpf.c}    |  27 +--
 3 files changed, 110 insertions(+), 77 deletions(-)
 rename tools/perf/{examples/bpf/augmented_raw_syscalls.c => util/bpf_skel/augmented_raw_syscalls.bpf.c} (96%)

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 5370d7bf123e..40663c69b25c 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -1038,6 +1038,7 @@ SKELETONS += $(SKEL_OUT)/bperf_cgroup.skel.h $(SKEL_OUT)/func_latency.skel.h
 SKELETONS += $(SKEL_OUT)/off_cpu.skel.h $(SKEL_OUT)/lock_contention.skel.h
 SKELETONS += $(SKEL_OUT)/kwork_trace.skel.h $(SKEL_OUT)/sample_filter.skel.h
 SKELETONS += $(SKEL_OUT)/bench_uprobe.skel.h
+SKELETONS += $(SKEL_OUT)/augmented_raw_syscalls.skel.h
 
 $(SKEL_TMP_OUT) $(LIBAPI_OUTPUT) $(LIBBPF_OUTPUT) $(LIBPERF_OUTPUT) $(LIBSUBCMD_OUTPUT) $(LIBSYMBOL_OUTPUT):
 	$(Q)$(MKDIR) -p $@
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 59862467e781..0ebfa95895e0 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -19,6 +19,9 @@
 #ifdef HAVE_LIBBPF_SUPPORT
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
+#ifdef HAVE_BPF_SKEL
+#include "bpf_skel/augmented_raw_syscalls.skel.h"
+#endif
 #endif
 #include "util/bpf_map.h"
 #include "util/rlimit.h"
@@ -127,25 +130,19 @@ struct trace {
 	struct syscalltbl	*sctbl;
 	struct {
 		struct syscall  *table;
-		struct { // per syscall BPF_MAP_TYPE_PROG_ARRAY
-			struct bpf_map  *sys_enter,
-					*sys_exit;
-		}		prog_array;
 		struct {
 			struct evsel *sys_enter,
-					  *sys_exit,
-					  *augmented;
+				*sys_exit,
+				*bpf_output;
 		}		events;
-		struct bpf_program *unaugmented_prog;
 	} syscalls;
-	struct {
-		struct bpf_map *map;
-	} dump;
+#ifdef HAVE_BPF_SKEL
+	struct augmented_raw_syscalls_bpf *skel;
+#endif
 	struct record_opts	opts;
 	struct evlist	*evlist;
 	struct machine		*host;
 	struct thread		*current;
-	struct bpf_object	*bpf_obj;
 	struct cgroup		*cgroup;
 	u64			base_time;
 	FILE			*output;
@@ -415,6 +412,7 @@ static int evsel__init_syscall_tp(struct evsel *evsel)
 		if (evsel__init_tp_uint_field(evsel, &sc->id, "__syscall_nr") &&
 		    evsel__init_tp_uint_field(evsel, &sc->id, "nr"))
 			return -ENOENT;
+
 		return 0;
 	}
 
@@ -2845,7 +2843,7 @@ static int trace__event_handler(struct trace *trace, struct evsel *evsel,
 	if (thread)
 		trace__fprintf_comm_tid(trace, thread, trace->output);
 
-	if (evsel == trace->syscalls.events.augmented) {
+	if (evsel == trace->syscalls.events.bpf_output) {
 		int id = perf_evsel__sc_tp_uint(evsel, id, sample);
 		struct syscall *sc = trace__syscall_info(trace, evsel, id);
 
@@ -3278,24 +3276,16 @@ out_enomem:
 	goto out;
 }
 
-#ifdef HAVE_LIBBPF_SUPPORT
-static struct bpf_map *trace__find_bpf_map_by_name(struct trace *trace, const char *name)
-{
-	if (trace->bpf_obj == NULL)
-		return NULL;
-
-	return bpf_object__find_map_by_name(trace->bpf_obj, name);
-}
-
+#ifdef HAVE_BPF_SKEL
 static struct bpf_program *trace__find_bpf_program_by_title(struct trace *trace, const char *name)
 {
 	struct bpf_program *pos, *prog = NULL;
 	const char *sec_name;
 
-	if (trace->bpf_obj == NULL)
+	if (trace->skel->obj == NULL)
 		return NULL;
 
-	bpf_object__for_each_program(pos, trace->bpf_obj) {
+	bpf_object__for_each_program(pos, trace->skel->obj) {
 		sec_name = bpf_program__section_name(pos);
 		if (sec_name && !strcmp(sec_name, name)) {
 			prog = pos;
@@ -3313,12 +3303,12 @@ static struct bpf_program *trace__find_syscall_bpf_prog(struct trace *trace, str
 
 	if (prog_name == NULL) {
 		char default_prog_name[256];
-		scnprintf(default_prog_name, sizeof(default_prog_name), "!syscalls:sys_%s_%s", type, sc->name);
+		scnprintf(default_prog_name, sizeof(default_prog_name), "tp/syscalls/sys_%s_%s", type, sc->name);
 		prog = trace__find_bpf_program_by_title(trace, default_prog_name);
 		if (prog != NULL)
 			goto out_found;
 		if (sc->fmt && sc->fmt->alias) {
-			scnprintf(default_prog_name, sizeof(default_prog_name), "!syscalls:sys_%s_%s", type, sc->fmt->alias);
+			scnprintf(default_prog_name, sizeof(default_prog_name), "tp/syscalls/sys_%s_%s", type, sc->fmt->alias);
 			prog = trace__find_bpf_program_by_title(trace, default_prog_name);
 			if (prog != NULL)
 				goto out_found;
@@ -3336,7 +3326,7 @@ out_found:
 	pr_debug("Couldn't find BPF prog \"%s\" to associate with syscalls:sys_%s_%s, not augmenting it\n",
 		 prog_name, type, sc->name);
 out_unaugmented:
-	return trace->syscalls.unaugmented_prog;
+	return trace->skel->progs.syscall_unaugmented;
 }
 
 static void trace__init_syscall_bpf_progs(struct trace *trace, int id)
@@ -3353,13 +3343,13 @@ static void trace__init_syscall_bpf_progs(struct trace *trace, int id)
 static int trace__bpf_prog_sys_enter_fd(struct trace *trace, int id)
 {
 	struct syscall *sc = trace__syscall_info(trace, NULL, id);
-	return sc ? bpf_program__fd(sc->bpf_prog.sys_enter) : bpf_program__fd(trace->syscalls.unaugmented_prog);
+	return sc ? bpf_program__fd(sc->bpf_prog.sys_enter) : bpf_program__fd(trace->skel->progs.syscall_unaugmented);
 }
 
 static int trace__bpf_prog_sys_exit_fd(struct trace *trace, int id)
 {
 	struct syscall *sc = trace__syscall_info(trace, NULL, id);
-	return sc ? bpf_program__fd(sc->bpf_prog.sys_exit) : bpf_program__fd(trace->syscalls.unaugmented_prog);
+	return sc ? bpf_program__fd(sc->bpf_prog.sys_exit) : bpf_program__fd(trace->skel->progs.syscall_unaugmented);
 }
 
 static struct bpf_program *trace__find_usable_bpf_prog_entry(struct trace *trace, struct syscall *sc)
@@ -3384,7 +3374,7 @@ try_to_find_pair:
 		bool is_candidate = false;
 
 		if (pair == NULL || pair == sc ||
-		    pair->bpf_prog.sys_enter == trace->syscalls.unaugmented_prog)
+		    pair->bpf_prog.sys_enter == trace->skel->progs.syscall_unaugmented)
 			continue;
 
 		for (field = sc->args, candidate_field = pair->args;
@@ -3437,7 +3427,7 @@ try_to_find_pair:
 		 */
 		if (pair_prog == NULL) {
 			pair_prog = trace__find_syscall_bpf_prog(trace, pair, pair->fmt ? pair->fmt->bpf_prog_name.sys_enter : NULL, "enter");
-			if (pair_prog == trace->syscalls.unaugmented_prog)
+			if (pair_prog == trace->skel->progs.syscall_unaugmented)
 				goto next_candidate;
 		}
 
@@ -3452,8 +3442,8 @@ try_to_find_pair:
 
 static int trace__init_syscalls_bpf_prog_array_maps(struct trace *trace)
 {
-	int map_enter_fd = bpf_map__fd(trace->syscalls.prog_array.sys_enter),
-	    map_exit_fd  = bpf_map__fd(trace->syscalls.prog_array.sys_exit);
+	int map_enter_fd = bpf_map__fd(trace->skel->maps.syscalls_sys_enter);
+	int map_exit_fd  = bpf_map__fd(trace->skel->maps.syscalls_sys_exit);
 	int err = 0, key;
 
 	for (key = 0; key < trace->sctbl->syscalls.nr_entries; ++key) {
@@ -3515,7 +3505,7 @@ static int trace__init_syscalls_bpf_prog_array_maps(struct trace *trace)
 		 * For now we're just reusing the sys_enter prog, and if it
 		 * already has an augmenter, we don't need to find one.
 		 */
-		if (sc->bpf_prog.sys_enter != trace->syscalls.unaugmented_prog)
+		if (sc->bpf_prog.sys_enter != trace->skel->progs.syscall_unaugmented)
 			continue;
 
 		/*
@@ -3538,22 +3528,9 @@ static int trace__init_syscalls_bpf_prog_array_maps(struct trace *trace)
 			break;
 	}
 
-
 	return err;
 }
-
-#else // HAVE_LIBBPF_SUPPORT
-static struct bpf_map *trace__find_bpf_map_by_name(struct trace *trace __maybe_unused,
-						   const char *name __maybe_unused)
-{
-	return NULL;
-}
-
-static int trace__init_syscalls_bpf_prog_array_maps(struct trace *trace __maybe_unused)
-{
-	return 0;
-}
-#endif // HAVE_LIBBPF_SUPPORT
+#endif // HAVE_BPF_SKEL
 
 static int trace__set_ev_qualifier_filter(struct trace *trace)
 {
@@ -3917,13 +3894,31 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	err = evlist__open(evlist);
 	if (err < 0)
 		goto out_error_open;
+#ifdef HAVE_BPF_SKEL
+	{
+		struct perf_cpu cpu;
 
+		/*
+		 * Set up the __augmented_syscalls__ BPF map to hold for each
+		 * CPU the bpf-output event's file descriptor.
+		 */
+		perf_cpu_map__for_each_cpu(cpu, i, trace->syscalls.events.bpf_output->core.cpus) {
+			bpf_map__update_elem(trace->skel->maps.__augmented_syscalls__,
+					&cpu.cpu, sizeof(int),
+					xyarray__entry(trace->syscalls.events.bpf_output->core.fd,
+						       cpu.cpu, 0),
+					sizeof(__u32), BPF_ANY);
+		}
+	}
+#endif
 	err = trace__set_filter_pids(trace);
 	if (err < 0)
 		goto out_error_mem;
 
-	if (trace->syscalls.prog_array.sys_enter)
+#ifdef HAVE_BPF_SKEL
+	if (trace->skel->progs.sys_enter)
 		trace__init_syscalls_bpf_prog_array_maps(trace);
+#endif
 
 	if (trace->ev_qualifier_ids.nr > 0) {
 		err = trace__set_ev_qualifier_filter(trace);
@@ -3956,9 +3951,6 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	if (err < 0)
 		goto out_error_apply_filters;
 
-	if (trace->dump.map)
-		bpf_map__fprintf(trace->dump.map, trace->output);
-
 	err = evlist__mmap(evlist, trace->opts.mmap_pages);
 	if (err < 0)
 		goto out_error_mmap;
@@ -4655,6 +4647,18 @@ static void trace__exit(struct trace *trace)
 	zfree(&trace->perfconfig_events);
 }
 
+#ifdef HAVE_BPF_SKEL
+static int bpf__setup_bpf_output(struct evlist *evlist)
+{
+	int err = parse_event(evlist, "bpf-output/no-inherit=1,name=__augmented_syscalls__/");
+
+	if (err)
+		pr_debug("ERROR: failed to create the \"__augmented_syscalls__\" bpf-output event\n");
+
+	return err;
+}
+#endif
+
 int cmd_trace(int argc, const char **argv)
 {
 	const char *trace_usage[] = {
@@ -4686,7 +4690,6 @@ int cmd_trace(int argc, const char **argv)
 		.max_stack = UINT_MAX,
 		.max_events = ULONG_MAX,
 	};
-	const char *map_dump_str = NULL;
 	const char *output_name = NULL;
 	const struct option trace_options[] = {
 	OPT_CALLBACK('e', "event", &trace, "event",
@@ -4720,9 +4723,6 @@ int cmd_trace(int argc, const char **argv)
 	OPT_CALLBACK(0, "duration", &trace, "float",
 		     "show only events with duration > N.M ms",
 		     trace__set_duration),
-#ifdef HAVE_LIBBPF_SUPPORT
-	OPT_STRING(0, "map-dump", &map_dump_str, "BPF map", "BPF map to periodically dump"),
-#endif
 	OPT_BOOLEAN(0, "sched", &trace.sched, "show blocking scheduler events"),
 	OPT_INCR('v', "verbose", &verbose, "be more verbose"),
 	OPT_BOOLEAN('T', "time", &trace.full_time,
@@ -4849,16 +4849,44 @@ int cmd_trace(int argc, const char **argv)
 				       "cgroup monitoring only available in system-wide mode");
 	}
 
-	err = -1;
+#ifdef HAVE_BPF_SKEL
+	trace.skel = augmented_raw_syscalls_bpf__open();
+	if (!trace.skel) {
+		pr_debug("Failed to open augmented syscalls BPF skeleton");
+	} else {
+		/*
+		 * Disable attaching the BPF programs except for sys_enter and
+		 * sys_exit that tail call into this as necessary.
+		 */
+		struct bpf_program *prog;
 
-	if (map_dump_str) {
-		trace.dump.map = trace__find_bpf_map_by_name(&trace, map_dump_str);
-		if (trace.dump.map == NULL) {
-			pr_err("ERROR: BPF map \"%s\" not found\n", map_dump_str);
-			goto out;
+		bpf_object__for_each_program(prog, trace.skel->obj) {
+			if (prog != trace.skel->progs.sys_enter && prog != trace.skel->progs.sys_exit)
+				bpf_program__set_autoattach(prog, /*autoattach=*/false);
+		}
+
+		err = augmented_raw_syscalls_bpf__load(trace.skel);
+
+		if (err < 0) {
+			libbpf_strerror(err, bf, sizeof(bf));
+			pr_debug("Failed to load augmented syscalls BPF skeleton: %s\n", bf);
+		} else {
+			augmented_raw_syscalls_bpf__attach(trace.skel);
+			trace__add_syscall_newtp(&trace);
 		}
 	}
 
+	err = bpf__setup_bpf_output(trace.evlist);
+	if (err) {
+		libbpf_strerror(err, bf, sizeof(bf));
+		pr_err("ERROR: Setup BPF output event failed: %s\n", bf);
+		goto out;
+	}
+	trace.syscalls.events.bpf_output = evlist__last(trace.evlist);
+	assert(!strcmp(evsel__name(trace.syscalls.events.bpf_output), "__augmented_syscalls__"));
+#endif
+	err = -1;
+
 	if (trace.trace_pgfaults) {
 		trace.opts.sample_address = true;
 		trace.opts.sample_time = true;
@@ -4909,7 +4937,7 @@ int cmd_trace(int argc, const char **argv)
 	 * buffers that are being copied from kernel to userspace, think 'read'
 	 * syscall.
 	 */
-	if (trace.syscalls.events.augmented) {
+	if (trace.syscalls.events.bpf_output) {
 		evlist__for_each_entry(trace.evlist, evsel) {
 			bool raw_syscalls_sys_exit = strcmp(evsel__name(evsel), "raw_syscalls:sys_exit") == 0;
 
@@ -4918,9 +4946,9 @@ int cmd_trace(int argc, const char **argv)
 				goto init_augmented_syscall_tp;
 			}
 
-			if (trace.syscalls.events.augmented->priv == NULL &&
+			if (trace.syscalls.events.bpf_output->priv == NULL &&
 			    strstr(evsel__name(evsel), "syscalls:sys_enter")) {
-				struct evsel *augmented = trace.syscalls.events.augmented;
+				struct evsel *augmented = trace.syscalls.events.bpf_output;
 				if (evsel__init_augmented_syscall_tp(augmented, evsel) ||
 				    evsel__init_augmented_syscall_tp_args(augmented))
 					goto out;
@@ -5025,5 +5053,8 @@ out_close:
 		fclose(trace.output);
 out:
 	trace__exit(&trace);
+#ifdef HAVE_BPF_SKEL
+	augmented_raw_syscalls_bpf__destroy(trace.skel);
+#endif
 	return err;
 }
diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
similarity index 96%
rename from tools/perf/examples/bpf/augmented_raw_syscalls.c
rename to tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
index 9a03189d33d3..70478b9460ee 100644
--- a/tools/perf/examples/bpf/augmented_raw_syscalls.c
+++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
@@ -18,6 +18,8 @@
 #include <bpf/bpf_helpers.h>
 #include <linux/limits.h>
 
+#define MAX_CPUS  4096
+
 // FIXME: These should come from system headers
 typedef char bool;
 typedef int pid_t;
@@ -34,7 +36,7 @@ struct __augmented_syscalls__ {
 	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
 	__type(key, int);
 	__type(value, __u32);
-	__uint(max_entries, __NR_CPUS__);
+	__uint(max_entries, MAX_CPUS);
 } __augmented_syscalls__ SEC(".maps");
 
 /*
@@ -170,7 +172,7 @@ unsigned int augmented_arg__read_str(struct augmented_arg *augmented_arg, const
 	return augmented_len;
 }
 
-SEC("!raw_syscalls:unaugmented")
+SEC("tp/raw_syscalls/sys_enter")
 int syscall_unaugmented(struct syscall_enter_args *args)
 {
 	return 1;
@@ -182,7 +184,7 @@ int syscall_unaugmented(struct syscall_enter_args *args)
  * on from there, reading the first syscall arg as a string, i.e. open's
  * filename.
  */
-SEC("!syscalls:sys_enter_connect")
+SEC("tp/syscalls/sys_enter_connect")
 int sys_enter_connect(struct syscall_enter_args *args)
 {
 	struct augmented_args_payload *augmented_args = augmented_args_payload();
@@ -201,7 +203,7 @@ int sys_enter_connect(struct syscall_enter_args *args)
 	return augmented__output(args, augmented_args, len + socklen);
 }
 
-SEC("!syscalls:sys_enter_sendto")
+SEC("tp/syscalls/sys_enter_sendto")
 int sys_enter_sendto(struct syscall_enter_args *args)
 {
 	struct augmented_args_payload *augmented_args = augmented_args_payload();
@@ -220,7 +222,7 @@ int sys_enter_sendto(struct syscall_enter_args *args)
 	return augmented__output(args, augmented_args, len + socklen);
 }
 
-SEC("!syscalls:sys_enter_open")
+SEC("tp/syscalls/sys_enter_open")
 int sys_enter_open(struct syscall_enter_args *args)
 {
 	struct augmented_args_payload *augmented_args = augmented_args_payload();
@@ -235,7 +237,7 @@ int sys_enter_open(struct syscall_enter_args *args)
 	return augmented__output(args, augmented_args, len);
 }
 
-SEC("!syscalls:sys_enter_openat")
+SEC("tp/syscalls/sys_enter_openat")
 int sys_enter_openat(struct syscall_enter_args *args)
 {
 	struct augmented_args_payload *augmented_args = augmented_args_payload();
@@ -250,7 +252,7 @@ int sys_enter_openat(struct syscall_enter_args *args)
 	return augmented__output(args, augmented_args, len);
 }
 
-SEC("!syscalls:sys_enter_rename")
+SEC("tp/syscalls/sys_enter_rename")
 int sys_enter_rename(struct syscall_enter_args *args)
 {
 	struct augmented_args_payload *augmented_args = augmented_args_payload();
@@ -267,7 +269,7 @@ int sys_enter_rename(struct syscall_enter_args *args)
 	return augmented__output(args, augmented_args, len);
 }
 
-SEC("!syscalls:sys_enter_renameat")
+SEC("tp/syscalls/sys_enter_renameat")
 int sys_enter_renameat(struct syscall_enter_args *args)
 {
 	struct augmented_args_payload *augmented_args = augmented_args_payload();
@@ -295,7 +297,7 @@ struct perf_event_attr_size {
         __u32                   size;
 };
 
-SEC("!syscalls:sys_enter_perf_event_open")
+SEC("tp/syscalls/sys_enter_perf_event_open")
 int sys_enter_perf_event_open(struct syscall_enter_args *args)
 {
 	struct augmented_args_payload *augmented_args = augmented_args_payload();
@@ -327,7 +329,7 @@ failure:
 	return 1; /* Failure: don't filter */
 }
 
-SEC("!syscalls:sys_enter_clock_nanosleep")
+SEC("tp/syscalls/sys_enter_clock_nanosleep")
 int sys_enter_clock_nanosleep(struct syscall_enter_args *args)
 {
 	struct augmented_args_payload *augmented_args = augmented_args_payload();
@@ -358,7 +360,7 @@ static bool pid_filter__has(struct pids_filtered *pids, pid_t pid)
 	return bpf_map_lookup_elem(pids, &pid) != NULL;
 }
 
-SEC("raw_syscalls:sys_enter")
+SEC("tp/raw_syscalls/sys_enter")
 int sys_enter(struct syscall_enter_args *args)
 {
 	struct augmented_args_payload *augmented_args;
@@ -371,7 +373,6 @@ int sys_enter(struct syscall_enter_args *args)
 	 * We'll add to this as we add augmented syscalls right after that
 	 * initial, non-augmented raw_syscalls:sys_enter payload.
 	 */
-	unsigned int len = sizeof(augmented_args->args);
 
 	if (pid_filter__has(&pids_filtered, getpid()))
 		return 0;
@@ -393,7 +394,7 @@ int sys_enter(struct syscall_enter_args *args)
 	return 0;
 }
 
-SEC("raw_syscalls:sys_exit")
+SEC("tp/raw_syscalls/sys_exit")
 int sys_exit(struct syscall_exit_args *args)
 {
 	struct syscall_exit_args exit_args;

From 5056c99e8d97e1129ff29826971eefbe345b6837 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 10 Aug 2023 11:48:52 -0700
Subject: [PATCH 0412/1189] perf bpf examples: With no BPF events remove
 examples

The examples were used to give demonstrations of BPF events but such
functionality is now subsumed by using --filter with 'perf record' or
the direct use of BPF skeletons.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Carsten Haitzler <carsten.haitzler@arm.com>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Fangrui Song <maskray@google.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Cc: Tiezhu Yang <yangtiezhu@loongson.cn>
Cc: Tom Rix <trix@redhat.com>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Wang ShaoBo <bobo.shaobowang@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: Yonghong Song <yhs@fb.com>
Cc: YueHaibing <yuehaibing@huawei.com>
Cc: bpf@vger.kernel.org
Cc: llvm@lists.linux.dev
Link: https://lore.kernel.org/r/20230810184853.2860737-4-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Makefile.perf                   |  5 --
 tools/perf/examples/bpf/5sec.c             | 53 ----------------------
 tools/perf/examples/bpf/empty.c            | 12 -----
 tools/perf/examples/bpf/hello.c            | 27 -----------
 tools/perf/examples/bpf/sys_enter_openat.c | 33 --------------
 5 files changed, 130 deletions(-)
 delete mode 100644 tools/perf/examples/bpf/5sec.c
 delete mode 100644 tools/perf/examples/bpf/empty.c
 delete mode 100644 tools/perf/examples/bpf/hello.c
 delete mode 100644 tools/perf/examples/bpf/sys_enter_openat.c

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 40663c69b25c..c90d55786a02 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -958,11 +958,6 @@ ifndef NO_JVMTI
 endif
 	$(call QUIET_INSTALL, libexec) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
-ifndef NO_LIBBPF
-	$(call QUIET_INSTALL, bpf-examples) \
-		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'; \
-		$(INSTALL) examples/bpf/*.c -m 644 -t '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
-endif
 	$(call QUIET_INSTALL, perf-archive) \
 		$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 	$(call QUIET_INSTALL, perf-iostat) \
diff --git a/tools/perf/examples/bpf/5sec.c b/tools/perf/examples/bpf/5sec.c
deleted file mode 100644
index 3bd7fc17631f..000000000000
--- a/tools/perf/examples/bpf/5sec.c
+++ /dev/null
@@ -1,53 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
-    Description:
-
-    . Disable strace like syscall tracing (--no-syscalls), or try tracing
-      just some (-e *sleep).
-
-    . Attach a filter function to a kernel function, returning when it should
-      be considered, i.e. appear on the output.
-
-    . Run it system wide, so that any sleep of >= 5 seconds and < than 6
-      seconds gets caught.
-
-    . Ask for callgraphs using DWARF info, so that userspace can be unwound
-
-    . While this is running, run something like "sleep 5s".
-
-    . If we decide to add tv_nsec as well, then it becomes:
-
-      int probe(hrtimer_nanosleep, rqtp->tv_sec rqtp->tv_nsec)(void *ctx, int err, long sec, long nsec)
-
-      I.e. add where it comes from (rqtp->tv_nsec) and where it will be
-      accessible in the function body (nsec)
-
-    # perf trace --no-syscalls -e tools/perf/examples/bpf/5sec.c/call-graph=dwarf/
-         0.000 perf_bpf_probe:func:(ffffffff9811b5f0) tv_sec=5
-                                           hrtimer_nanosleep ([kernel.kallsyms])
-                                           __x64_sys_nanosleep ([kernel.kallsyms])
-                                           do_syscall_64 ([kernel.kallsyms])
-                                           entry_SYSCALL_64 ([kernel.kallsyms])
-                                           __GI___nanosleep (/usr/lib64/libc-2.26.so)
-                                           rpl_nanosleep (/usr/bin/sleep)
-                                           xnanosleep (/usr/bin/sleep)
-                                           main (/usr/bin/sleep)
-                                           __libc_start_main (/usr/lib64/libc-2.26.so)
-                                           _start (/usr/bin/sleep)
-    ^C#
-
-   Copyright (C) 2018 Red Hat, Inc., Arnaldo Carvalho de Melo <acme@redhat.com>
-*/
-
-#include <linux/bpf.h>
-#include <bpf/bpf_helpers.h>
-
-#define NSEC_PER_SEC	1000000000L
-
-SEC("hrtimer_nanosleep=hrtimer_nanosleep rqtp")
-int hrtimer_nanosleep(void *ctx, int err, long long sec)
-{
-	return sec / NSEC_PER_SEC == 5ULL;
-}
-
-char _license[] SEC("license") = "GPL";
diff --git a/tools/perf/examples/bpf/empty.c b/tools/perf/examples/bpf/empty.c
deleted file mode 100644
index 3e296c0c53d7..000000000000
--- a/tools/perf/examples/bpf/empty.c
+++ /dev/null
@@ -1,12 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/bpf.h>
-#include <bpf/bpf_helpers.h>
-
-struct syscall_enter_args;
-
-SEC("raw_syscalls:sys_enter")
-int sys_enter(struct syscall_enter_args *args)
-{
-	return 0;
-}
-char _license[] SEC("license") = "GPL";
diff --git a/tools/perf/examples/bpf/hello.c b/tools/perf/examples/bpf/hello.c
deleted file mode 100644
index e9080b0df158..000000000000
--- a/tools/perf/examples/bpf/hello.c
+++ /dev/null
@@ -1,27 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/bpf.h>
-#include <bpf/bpf_helpers.h>
-
-struct __bpf_stdout__ {
-	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
-	__type(key, int);
-	__type(value, __u32);
-	__uint(max_entries, __NR_CPUS__);
-} __bpf_stdout__ SEC(".maps");
-
-#define puts(from) \
-	({ const int __len = sizeof(from); \
-	   char __from[sizeof(from)] = from;			\
-	   bpf_perf_event_output(args, &__bpf_stdout__, BPF_F_CURRENT_CPU, \
-			  &__from, __len & (sizeof(from) - 1)); })
-
-struct syscall_enter_args;
-
-SEC("raw_syscalls:sys_enter")
-int sys_enter(struct syscall_enter_args *args)
-{
-	puts("Hello, world\n");
-	return 0;
-}
-
-char _license[] SEC("license") = "GPL";
diff --git a/tools/perf/examples/bpf/sys_enter_openat.c b/tools/perf/examples/bpf/sys_enter_openat.c
deleted file mode 100644
index c4481c390d23..000000000000
--- a/tools/perf/examples/bpf/sys_enter_openat.c
+++ /dev/null
@@ -1,33 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Hook into 'openat' syscall entry tracepoint
- *
- * Test it with:
- *
- * perf trace -e tools/perf/examples/bpf/sys_enter_openat.c cat /etc/passwd > /dev/null
- *
- * It'll catch some openat syscalls related to the dynamic linked and
- * the last one should be the one for '/etc/passwd'.
- *
- * The syscall_enter_openat_args can be used to get the syscall fields
- * and use them for filtering calls, i.e. use in expressions for
- * the return value.
- */
-
-#include <bpf/bpf.h>
-
-struct syscall_enter_openat_args {
-	unsigned long long unused;
-	long		   syscall_nr;
-	long		   dfd;
-	char		   *filename_ptr;
-	long		   flags;
-	long		   mode;
-};
-
-int syscall_enter(openat)(struct syscall_enter_openat_args *args)
-{
-	return 1;
-}
-
-license(GPL);

From cd2cece61ac5f900c43df366c9a64ddb62173707 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 10 Aug 2023 11:48:53 -0700
Subject: [PATCH 0413/1189] perf trace: Tidy comments related to BPF + syscall
 augmentation

Now tools/perf/examples/bpf/augmented_syscalls.c is
tools/perf/util/bpf_skel/augmented_syscalls.bpf.c and not enabled as a
BPF event, tidy the comments to reflect this.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Carsten Haitzler <carsten.haitzler@arm.com>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Fangrui Song <maskray@google.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Cc: Tiezhu Yang <yangtiezhu@loongson.cn>
Cc: Tom Rix <trix@redhat.com>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Wang ShaoBo <bobo.shaobowang@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: Yonghong Song <yhs@fb.com>
Cc: YueHaibing <yuehaibing@huawei.com>
Cc: bpf@vger.kernel.org
Cc: llvm@lists.linux.dev
Link: https://lore.kernel.org/r/20230810184853.2860737-5-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/beauty.h                  | 15 +++++++--------
 .../util/bpf_skel/augmented_raw_syscalls.bpf.c    |  8 --------
 2 files changed, 7 insertions(+), 16 deletions(-)

diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index 3d12bf0f6d07..788e8f6bd90e 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -67,15 +67,14 @@ extern struct strarray strarray__socket_level;
 /**
  * augmented_arg: extra payload for syscall pointer arguments
  
- * If perf_sample->raw_size is more than what a syscall sys_enter_FOO puts,
- * then its the arguments contents, so that we can show more than just a
+ * If perf_sample->raw_size is more than what a syscall sys_enter_FOO puts, then
+ * its the arguments contents, so that we can show more than just a
  * pointer. This will be done initially with eBPF, the start of that is at the
- * tools/perf/examples/bpf/augmented_syscalls.c example for the openat, but
- * will eventually be done automagically caching the running kernel tracefs
- * events data into an eBPF C script, that then gets compiled and its .o file
- * cached for subsequent use. For char pointers like the ones for 'open' like
- * syscalls its easy, for the rest we should use DWARF or better, BTF, much
- * more compact.
+ * tools/perf/util/bpf_skel/augmented_syscalls.bpf.c that will eventually be
+ * done automagically caching the running kernel tracefs events data into an
+ * eBPF C script, that then gets compiled and its .o file cached for subsequent
+ * use. For char pointers like the ones for 'open' like syscalls its easy, for
+ * the rest we should use DWARF or better, BTF, much more compact.
  *
  * @size: 8 if all we need is an integer, otherwise all of the augmented arg.
  * @int_arg: will be used for integer like pointer contents, like 'accept's 'upeer_addrlen'
diff --git a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
index 70478b9460ee..0586c4118656 100644
--- a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
+++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
@@ -2,16 +2,8 @@
 /*
  * Augment the raw_syscalls tracepoints with the contents of the pointer arguments.
  *
- * Test it with:
- *
- * perf trace -e tools/perf/examples/bpf/augmented_raw_syscalls.c cat /etc/passwd > /dev/null
- *
  * This exactly matches what is marshalled into the raw_syscall:sys_enter
  * payload expected by the 'perf trace' beautifiers.
- *
- * For now it just uses the existing tracepoint augmentation code in 'perf
- * trace', in the next csets we'll hook up these with the sys_enter/sys_exit
- * code that will combine entry/exit in a strace like way.
  */
 
 #include <linux/bpf.h>

From dc7f01f1bceca38839992b3371e0be8a3c9d5acf Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 10 Aug 2023 19:58:21 -0700
Subject: [PATCH 0414/1189] perf bpf-filter: Fix sample flag check with ||

For logical OR operator, the actual sample_flags are in the 'groups'
list so it needs to check entries in the list instead.  Otherwise it
would show the following error message.

  $ sudo perf record -a -e cycles:p --filter 'period > 100 || weight > 0' sleep 1
  Error: cycles:p event does not have sample flags 0
  failed to set filter "BPF" on event cycles:p with 2 (No such file or directory)

Actually it should warn on 'weight' is used without WEIGHT flag.

  Error: cycles:p event does not have PERF_SAMPLE_WEIGHT
   Hint: please add -W option to perf record
  failed to set filter "BPF" on event cycles:p with 2 (No such file or directory)

Fixes: 4310551b76e0d676 ("perf bpf filter: Show warning for missing sample flags")
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230811025822.3859771-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/bpf-filter.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/tools/perf/util/bpf-filter.c b/tools/perf/util/bpf-filter.c
index 47f01df658d9..b51544996046 100644
--- a/tools/perf/util/bpf-filter.c
+++ b/tools/perf/util/bpf-filter.c
@@ -62,6 +62,16 @@ static int check_sample_flags(struct evsel *evsel, struct perf_bpf_filter_expr *
 	if (evsel->core.attr.sample_type & expr->sample_flags)
 		return 0;
 
+	if (expr->op == PBF_OP_GROUP_BEGIN) {
+		struct perf_bpf_filter_expr *group;
+
+		list_for_each_entry(group, &expr->groups, list) {
+			if (check_sample_flags(evsel, group) < 0)
+				return -1;
+		}
+		return 0;
+	}
+
 	info = get_sample_info(expr->sample_flags);
 	if (info == NULL) {
 		pr_err("Error: %s event does not have sample flags %lx\n",

From 9575ecdd198a50e95ed2319471f7518465b1cd94 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 10 Aug 2023 19:58:22 -0700
Subject: [PATCH 0415/1189] perf test: Add perf record sample filtering test

  $ sudo ./perf test 'sample filter' -v
   94: perf record sample filtering (by BPF) tests                     :
  --- start ---
  test child forked, pid 3817527
  Checking BPF-filter privilege
  Basic bpf-filter test
  Basic bpf-filter test [Success]
  Failing bpf-filter test
  Error: task-clock event does not have PERF_SAMPLE_CPU
  Failing bpf-filter test [Success]
  Group bpf-filter test
  Error: task-clock event does not have PERF_SAMPLE_CPU
  Error: task-clock event does not have PERF_SAMPLE_CODE_PAGE_SIZE
  Group bpf-filter test [Success]
  test child finished with 0
  ---- end ----
  perf record sample filtering (by BPF) tests: Ok

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230811025822.3859771-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/record_bpf_filter.sh | 128 ++++++++++++++++++++
 1 file changed, 128 insertions(+)
 create mode 100755 tools/perf/tests/shell/record_bpf_filter.sh

diff --git a/tools/perf/tests/shell/record_bpf_filter.sh b/tools/perf/tests/shell/record_bpf_filter.sh
new file mode 100755
index 000000000000..e76ea861b92c
--- /dev/null
+++ b/tools/perf/tests/shell/record_bpf_filter.sh
@@ -0,0 +1,128 @@
+#!/bin/sh
+# perf record sample filtering (by BPF) tests
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+err=0
+perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+
+cleanup() {
+  rm -f "${perfdata}"
+  rm -f "${perfdata}".old
+  trap - EXIT TERM INT
+}
+
+trap_cleanup() {
+  cleanup
+  exit 1
+}
+trap trap_cleanup EXIT TERM INT
+
+test_bpf_filter_priv() {
+  echo "Checking BPF-filter privilege"
+
+  if [ "$(id -u)" != 0 ]
+  then
+    echo "bpf-filter test [Skipped permission]"
+    err=2
+    return
+  fi
+  if ! perf record -e task-clock --filter 'period > 1' \
+	  -o /dev/null --quiet true 2>&1
+  then
+    echo "bpf-filter test [Skipped missing BPF support]"
+    err=2
+    return
+  fi
+}
+
+test_bpf_filter_basic() {
+  echo "Basic bpf-filter test"
+
+  if ! perf record -e task-clock -c 10000 --filter 'ip < 0xffffffff00000000' \
+	  -o "${perfdata}" true 2> /dev/null
+  then
+    echo "Basic bpf-filter test [Failed record]"
+    err=1
+    return
+  fi
+  if perf script -i "${perfdata}" -F ip | grep 'ffffffff[0-9a-f]*'
+  then
+    echo "Basic bpf-filter test [Failed invalid output]"
+    err=1
+    return
+  fi
+  echo "Basic bpf-filter test [Success]"
+}
+
+test_bpf_filter_fail() {
+  echo "Failing bpf-filter test"
+
+  # 'cpu' requires PERF_SAMPLE_CPU flag
+  if ! perf record -e task-clock --filter 'cpu > 0' \
+	  -o /dev/null true 2>&1 | grep PERF_SAMPLE_CPU
+  then
+    echo "Failing bpf-filter test [Failed forbidden CPU]"
+    err=1
+    return
+  fi
+
+  if ! perf record --sample-cpu -e task-clock --filter 'cpu > 0' \
+	  -o /dev/null true 2>/dev/null
+  then
+    echo "Failing bpf-filter test [Failed should succeed]"
+    err=1
+    return
+  fi
+
+  echo "Failing bpf-filter test [Success]"
+}
+
+test_bpf_filter_group() {
+  echo "Group bpf-filter test"
+
+  if ! perf record -e task-clock --filter 'period > 1000 || ip > 0' \
+	  -o /dev/null true 2>/dev/null
+  then
+    echo "Group bpf-filter test [Failed should succeed]"
+    err=1
+    return
+  fi
+
+  if ! perf record -e task-clock --filter 'cpu > 0 || ip > 0' \
+	  -o /dev/null true 2>&1 | grep PERF_SAMPLE_CPU
+  then
+    echo "Group bpf-filter test [Failed forbidden CPU]"
+    err=1
+    return
+  fi
+
+  if ! perf record -e task-clock --filter 'period > 0 || code_pgsz > 4096' \
+	  -o /dev/null true 2>&1 | grep PERF_SAMPLE_CODE_PAGE_SIZE
+  then
+    echo "Group bpf-filter test [Failed forbidden CODE_PAGE_SIZE]"
+    err=1
+    return
+  fi
+
+  echo "Group bpf-filter test [Success]"
+}
+
+
+test_bpf_filter_priv
+
+if [ $err = 0 ]; then
+  test_bpf_filter_basic
+fi
+
+if [ $err = 0 ]; then
+  test_bpf_filter_fail
+fi
+
+if [ $err = 0 ]; then
+  test_bpf_filter_group
+fi
+
+cleanup
+exit $err

From d095ad45e2d808a5c8c047b5c8d5e0fad7fec4e4 Mon Sep 17 00:00:00 2001
From: Yang Jihong <yangjihong1@huawei.com>
Date: Tue, 15 Aug 2023 22:10:09 +0000
Subject: [PATCH 0416/1189] perf evsel: Remove duplicate check for `field` in
 evsel__intval()

The `file` parameter in evsel__intval() is checked repeatedly, fix it.

No functional change.

Signed-off-by: Yang Jihong <yangjihong1@huawei.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Link: https://lore.kernel.org/r/20230815221009.3641751-1-yangjihong1@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evsel.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index e41bc4d9925f..0c50c443d456 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2827,9 +2827,6 @@ u64 evsel__intval(struct evsel *evsel, struct perf_sample *sample, const char *n
 {
 	struct tep_format_field *field = evsel__field(evsel, name);
 
-	if (!field)
-		return 0;
-
 	return field ? format_field__intval(field, sample, evsel->needs_swap) : 0;
 }
 #endif

From 708a3e8b80a5364fc3dd4991f1e589a6d7a4a8e0 Mon Sep 17 00:00:00 2001
From: Wei Li <liwei391@huawei.com>
Date: Tue, 15 Aug 2023 21:17:35 +0800
Subject: [PATCH 0417/1189] perf scripts python: Support syscall name parsing
 on arm64

In the result of "perf script syscall-counts" on arm64, the syscall
events are not resolved currently. Add "aarch64" to audit uname list to
support name parsing.

* After the patch:

  [root@localhost ~]# perf script syscall-counts sleep 1
  Press control+C to stop and show the summary

  syscall events:

  event                                          count
  ----------------------------------------  -----------
  mmap                                               6
  close                                              5
  mprotect                                           4
  brk                                                3
  newfstatat                                         3
  openat                                             3
  getrandom                                          1
  prlimit64                                          1
  munmap                                             1
  clock_nanosleep                                    1
  set_robust_list                                    1
  set_tid_address                                    1
  exit_group                                         1
  read                                               1
  faccessat                                          1

Signed-off-by: Wei Li <liwei391@huawei.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Li Bin <huawei.libin@huawei.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230815131735.1237221-1-liwei391@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
index 7384dcb628c4..c37a03fb7ec5 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
@@ -54,6 +54,7 @@ try:
 	import audit
 	machine_to_id = {
 		'x86_64': audit.MACH_86_64,
+		'aarch64': audit.MACH_AARCH64,
 		'alpha'	: audit.MACH_ALPHA,
 		'ia64'	: audit.MACH_IA64,
 		'ppc'	: audit.MACH_PPC,

From 41a37430f66560c4b9a9d68a977c8dab65b97ff8 Mon Sep 17 00:00:00 2001
From: Wei Li <liwei391@huawei.com>
Date: Tue, 15 Aug 2023 21:18:05 +0800
Subject: [PATCH 0418/1189] perf scripts python: Update audit-libs package name
 for python3

'audit-libs-python' is the package for python2, update it for python3.
On Ubuntu and Fedora, the new package is 'python3-audit'.

Signed-off-by: Wei Li <liwei391@huawei.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Li Bin <huawei.libin@huawei.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230815131805.1237491-1-liwei391@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py   | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
index c37a03fb7ec5..b75d31858e54 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
@@ -74,9 +74,9 @@ try:
 except:
 	if not audit_package_warned:
 		audit_package_warned = True
-		print("Install the audit-libs-python package to get syscall names.\n"
-                    "For example:\n  # apt-get install python-audit (Ubuntu)"
-                    "\n  # yum install audit-libs-python (Fedora)"
+		print("Install the python-audit package to get syscall names.\n"
+                    "For example:\n  # apt-get install python3-audit (Ubuntu)"
+                    "\n  # yum install python3-audit (Fedora)"
                     "\n  etc.\n")
 
 def syscall_name(id):

From f178a76b054fd046d212c3c67745146ff191a443 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 31 Jul 2023 12:18:55 +0300
Subject: [PATCH 0419/1189] perf dlfilter: Add a test for resolve_address()

Extend the "dlfilter C API" test to test
perf_dlfilter_fns.resolve_address(). The test currently fails, but passes
after a subsequent patch.

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20230731091857.10681-1-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/dlfilters/dlfilter-test-api-v0.c | 26 ++++++++++++++++++++-
 1 file changed, 25 insertions(+), 1 deletion(-)

diff --git a/tools/perf/dlfilters/dlfilter-test-api-v0.c b/tools/perf/dlfilters/dlfilter-test-api-v0.c
index b1f51efd67d6..72f263d49121 100644
--- a/tools/perf/dlfilters/dlfilter-test-api-v0.c
+++ b/tools/perf/dlfilters/dlfilter-test-api-v0.c
@@ -254,6 +254,30 @@ static int check_addr_al(void *ctx)
 	return 0;
 }
 
+static int check_address_al(void *ctx, const struct perf_dlfilter_sample *sample)
+{
+	struct perf_dlfilter_al address_al;
+	const struct perf_dlfilter_al *al;
+
+	al = perf_dlfilter_fns.resolve_ip(ctx);
+	if (!al)
+		return test_fail("resolve_ip() failed");
+
+	address_al.size = sizeof(address_al);
+	if (perf_dlfilter_fns.resolve_address(ctx, sample->ip, &address_al))
+		return test_fail("resolve_address() failed");
+
+	CHECK(address_al.sym && al->sym);
+	CHECK(!strcmp(address_al.sym, al->sym));
+	CHECK(address_al.addr == al->addr);
+	CHECK(address_al.sym_start == al->sym_start);
+	CHECK(address_al.sym_end == al->sym_end);
+	CHECK(address_al.dso && al->dso);
+	CHECK(!strcmp(address_al.dso, al->dso));
+
+	return 0;
+}
+
 static int check_attr(void *ctx)
 {
 	struct perf_event_attr *attr = perf_dlfilter_fns.attr(ctx);
@@ -290,7 +314,7 @@ static int do_checks(void *data, const struct perf_dlfilter_sample *sample, void
 	if (early && !d->do_early)
 		return 0;
 
-	if (check_al(ctx) || check_addr_al(ctx))
+	if (check_al(ctx) || check_addr_al(ctx) || check_address_al(ctx, sample))
 		return -1;
 
 	if (early)

From 42c6dd9d23019ff339d0aca80a444eb71087050e Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@kernel.org>
Date: Mon, 31 Jul 2023 12:18:56 +0300
Subject: [PATCH 0420/1189] perf dlfilter: Initialize addr_location before
 passing it to thread__find_symbol_fb()

As thread__find_symbol_fb() will end up calling thread__find_map() and
it in turn will call these on uninitialized memory:

        maps__zput(al->maps);
        map__zput(al->map);
        thread__zput(al->thread);

Fixes: 0dd5041c9a0eaf8c ("perf addr_location: Add init/exit/copy functions")
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20230731091857.10681-2-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/dlfilter.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/util/dlfilter.c b/tools/perf/util/dlfilter.c
index 46f74b2344db..798a53d7e6c9 100644
--- a/tools/perf/util/dlfilter.c
+++ b/tools/perf/util/dlfilter.c
@@ -166,6 +166,7 @@ static __s32 dlfilter__resolve_address(void *ctx, __u64 address, struct perf_dlf
 	if (!thread)
 		return -1;
 
+	addr_location__init(&al);
 	thread__find_symbol_fb(thread, d->sample->cpumode, address, &al);
 
 	al_to_d_al(&al, &d_al);

From 82b0a10390e5f198a4e23c9cc6a7307d2cf099f3 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 31 Jul 2023 12:18:57 +0300
Subject: [PATCH 0421/1189] perf dlfilter: Add al_cleanup()

Add perf_dlfilter_fns.al_cleanup() to do addr_location__exit() on data
passed via perf_dlfilter_fns.resolve_address().

Add dlfilter-test-api-v2 to the "dlfilter C API" test to test it.

Update documentation, clarifying that data returned by APIs should not
be dereferenced after filter_event() and filter_event_early() return.

Fixes: 0dd5041c9a0eaf8c ("perf addr_location: Add init/exit/copy functions")
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20230731091857.10681-3-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-dlfilter.txt  |  22 +-
 tools/perf/Makefile.perf                    |   2 +-
 tools/perf/dlfilters/dlfilter-test-api-v2.c | 377 ++++++++++++++++++++
 tools/perf/include/perf/perf_dlfilter.h     |  11 +-
 tools/perf/tests/dlfilter-test.c            |  38 +-
 tools/perf/util/dlfilter.c                  |  29 ++
 6 files changed, 464 insertions(+), 15 deletions(-)
 create mode 100644 tools/perf/dlfilters/dlfilter-test-api-v2.c

diff --git a/tools/perf/Documentation/perf-dlfilter.txt b/tools/perf/Documentation/perf-dlfilter.txt
index fb22e3b31dc5..8887cc20a809 100644
--- a/tools/perf/Documentation/perf-dlfilter.txt
+++ b/tools/perf/Documentation/perf-dlfilter.txt
@@ -64,6 +64,12 @@ internal filtering.
 If implemented, 'filter_description' should return a one-line description
 of the filter, and optionally a longer description.
 
+Do not assume the 'sample' argument is valid (dereferenceable)
+after 'filter_event' and 'filter_event_early' return.
+
+Do not assume data referenced by pointers in struct perf_dlfilter_sample
+is valid (dereferenceable) after 'filter_event' and 'filter_event_early' return.
+
 The perf_dlfilter_sample structure
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
@@ -150,7 +156,8 @@ struct perf_dlfilter_fns {
 	const char *(*srcline)(void *ctx, __u32 *line_number);
 	struct perf_event_attr *(*attr)(void *ctx);
 	__s32 (*object_code)(void *ctx, __u64 ip, void *buf, __u32 len);
-	void *(*reserved[120])(void *);
+	void (*al_cleanup)(void *ctx, struct perf_dlfilter_al *al);
+	void *(*reserved[119])(void *);
 };
 ----
 
@@ -161,7 +168,8 @@ struct perf_dlfilter_fns {
 'args' returns arguments from --dlarg options.
 
 'resolve_address' provides information about 'address'. al->size must be set
-before calling. Returns 0 on success, -1 otherwise.
+before calling. Returns 0 on success, -1 otherwise. Call al_cleanup() (if present,
+see below) when 'al' data is no longer needed.
 
 'insn' returns instruction bytes and length.
 
@@ -171,6 +179,12 @@ before calling. Returns 0 on success, -1 otherwise.
 
 'object_code' reads object code and returns the number of bytes read.
 
+'al_cleanup' must be called (if present, so check perf_dlfilter_fns.al_cleanup != NULL)
+after resolve_address() to free any associated resources.
+
+Do not assume pointers obtained via perf_dlfilter_fns are valid (dereferenceable)
+after 'filter_event' and 'filter_event_early' return.
+
 The perf_dlfilter_al structure
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
@@ -197,9 +211,13 @@ struct perf_dlfilter_al {
 	/* Below members are only populated by resolve_ip() */
 	__u8 filtered; /* true if this sample event will be filtered out */
 	const char *comm;
+	void *priv; /* Private data. Do not change */
 };
 ----
 
+Do not assume data referenced by pointers in struct perf_dlfilter_al
+is valid (dereferenceable) after 'filter_event' and 'filter_event_early' return.
+
 perf_dlfilter_sample flags
 ~~~~~~~~~~~~~~~~~~~~~~~~~~
 
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index c90d55786a02..a5dd1ba0fb5f 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -377,7 +377,7 @@ ifndef NO_JVMTI
 PROGRAMS += $(OUTPUT)$(LIBJVMTI)
 endif
 
-DLFILTERS := dlfilter-test-api-v0.so dlfilter-show-cycles.so
+DLFILTERS := dlfilter-test-api-v0.so dlfilter-test-api-v2.so dlfilter-show-cycles.so
 DLFILTERS := $(patsubst %,$(OUTPUT)dlfilters/%,$(DLFILTERS))
 
 # what 'all' will build and 'install' will install, in perfexecdir
diff --git a/tools/perf/dlfilters/dlfilter-test-api-v2.c b/tools/perf/dlfilters/dlfilter-test-api-v2.c
new file mode 100644
index 000000000000..38e593d92920
--- /dev/null
+++ b/tools/perf/dlfilters/dlfilter-test-api-v2.c
@@ -0,0 +1,377 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test v2 API for perf --dlfilter shared object
+ * Copyright (c) 2023, Intel Corporation.
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdbool.h>
+
+/*
+ * Copy v2 API instead of including current API
+ */
+#include <linux/perf_event.h>
+#include <linux/types.h>
+
+/*
+ * The following macro can be used to determine if this header defines
+ * perf_dlfilter_sample machine_pid and vcpu.
+ */
+#define PERF_DLFILTER_HAS_MACHINE_PID
+
+/* Definitions for perf_dlfilter_sample flags */
+enum {
+	PERF_DLFILTER_FLAG_BRANCH	= 1ULL << 0,
+	PERF_DLFILTER_FLAG_CALL		= 1ULL << 1,
+	PERF_DLFILTER_FLAG_RETURN	= 1ULL << 2,
+	PERF_DLFILTER_FLAG_CONDITIONAL	= 1ULL << 3,
+	PERF_DLFILTER_FLAG_SYSCALLRET	= 1ULL << 4,
+	PERF_DLFILTER_FLAG_ASYNC	= 1ULL << 5,
+	PERF_DLFILTER_FLAG_INTERRUPT	= 1ULL << 6,
+	PERF_DLFILTER_FLAG_TX_ABORT	= 1ULL << 7,
+	PERF_DLFILTER_FLAG_TRACE_BEGIN	= 1ULL << 8,
+	PERF_DLFILTER_FLAG_TRACE_END	= 1ULL << 9,
+	PERF_DLFILTER_FLAG_IN_TX	= 1ULL << 10,
+	PERF_DLFILTER_FLAG_VMENTRY	= 1ULL << 11,
+	PERF_DLFILTER_FLAG_VMEXIT	= 1ULL << 12,
+};
+
+/*
+ * perf sample event information (as per perf script and <linux/perf_event.h>)
+ */
+struct perf_dlfilter_sample {
+	__u32 size; /* Size of this structure (for compatibility checking) */
+	__u16 ins_lat;		/* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */
+	__u16 p_stage_cyc;	/* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */
+	__u64 ip;
+	__s32 pid;
+	__s32 tid;
+	__u64 time;
+	__u64 addr;
+	__u64 id;
+	__u64 stream_id;
+	__u64 period;
+	__u64 weight;		/* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */
+	__u64 transaction;	/* Refer PERF_SAMPLE_TRANSACTION in <linux/perf_event.h> */
+	__u64 insn_cnt;	/* For instructions-per-cycle (IPC) */
+	__u64 cyc_cnt;		/* For instructions-per-cycle (IPC) */
+	__s32 cpu;
+	__u32 flags;		/* Refer PERF_DLFILTER_FLAG_* above */
+	__u64 data_src;		/* Refer PERF_SAMPLE_DATA_SRC in <linux/perf_event.h> */
+	__u64 phys_addr;	/* Refer PERF_SAMPLE_PHYS_ADDR in <linux/perf_event.h> */
+	__u64 data_page_size;	/* Refer PERF_SAMPLE_DATA_PAGE_SIZE in <linux/perf_event.h> */
+	__u64 code_page_size;	/* Refer PERF_SAMPLE_CODE_PAGE_SIZE in <linux/perf_event.h> */
+	__u64 cgroup;		/* Refer PERF_SAMPLE_CGROUP in <linux/perf_event.h> */
+	__u8  cpumode;		/* Refer CPUMODE_MASK etc in <linux/perf_event.h> */
+	__u8  addr_correlates_sym; /* True => resolve_addr() can be called */
+	__u16 misc;		/* Refer perf_event_header in <linux/perf_event.h> */
+	__u32 raw_size;		/* Refer PERF_SAMPLE_RAW in <linux/perf_event.h> */
+	const void *raw_data;	/* Refer PERF_SAMPLE_RAW in <linux/perf_event.h> */
+	__u64 brstack_nr;	/* Number of brstack entries */
+	const struct perf_branch_entry *brstack; /* Refer <linux/perf_event.h> */
+	__u64 raw_callchain_nr;	/* Number of raw_callchain entries */
+	const __u64 *raw_callchain; /* Refer <linux/perf_event.h> */
+	const char *event;
+	__s32 machine_pid;
+	__s32 vcpu;
+};
+
+/*
+ * Address location (as per perf script)
+ */
+struct perf_dlfilter_al {
+	__u32 size; /* Size of this structure (for compatibility checking) */
+	__u32 symoff;
+	const char *sym;
+	__u64 addr; /* Mapped address (from dso) */
+	__u64 sym_start;
+	__u64 sym_end;
+	const char *dso;
+	__u8  sym_binding; /* STB_LOCAL, STB_GLOBAL or STB_WEAK, refer <elf.h> */
+	__u8  is_64_bit; /* Only valid if dso is not NULL */
+	__u8  is_kernel_ip; /* True if in kernel space */
+	__u32 buildid_size;
+	__u8 *buildid;
+	/* Below members are only populated by resolve_ip() */
+	__u8 filtered; /* True if this sample event will be filtered out */
+	const char *comm;
+	void *priv; /* Private data (v2 API) */
+};
+
+struct perf_dlfilter_fns {
+	/* Return information about ip */
+	const struct perf_dlfilter_al *(*resolve_ip)(void *ctx);
+	/* Return information about addr (if addr_correlates_sym) */
+	const struct perf_dlfilter_al *(*resolve_addr)(void *ctx);
+	/* Return arguments from --dlarg option */
+	char **(*args)(void *ctx, int *dlargc);
+	/*
+	 * Return information about address (al->size must be set before
+	 * calling). Returns 0 on success, -1 otherwise. Call al_cleanup()
+	 * when 'al' data is no longer needed.
+	 */
+	__s32 (*resolve_address)(void *ctx, __u64 address, struct perf_dlfilter_al *al);
+	/* Return instruction bytes and length */
+	const __u8 *(*insn)(void *ctx, __u32 *length);
+	/* Return source file name and line number */
+	const char *(*srcline)(void *ctx, __u32 *line_number);
+	/* Return perf_event_attr, refer <linux/perf_event.h> */
+	struct perf_event_attr *(*attr)(void *ctx);
+	/* Read object code, return numbers of bytes read */
+	__s32 (*object_code)(void *ctx, __u64 ip, void *buf, __u32 len);
+	/*
+	 * If present (i.e. must check al_cleanup != NULL), call after
+	 * resolve_address() to free any associated resources. (v2 API)
+	 */
+	void (*al_cleanup)(void *ctx, struct perf_dlfilter_al *al);
+	/* Reserved */
+	void *(*reserved[119])(void *);
+};
+
+struct perf_dlfilter_fns perf_dlfilter_fns;
+
+static int verbose;
+
+#define pr_debug(fmt, ...) do { \
+		if (verbose > 0) \
+			fprintf(stderr, fmt, ##__VA_ARGS__); \
+	} while (0)
+
+static int test_fail(const char *msg)
+{
+	pr_debug("%s\n", msg);
+	return -1;
+}
+
+#define CHECK(x) do { \
+		if (!(x)) \
+			return test_fail("Check '" #x "' failed\n"); \
+	} while (0)
+
+struct filter_data {
+	__u64 ip;
+	__u64 addr;
+	int do_early;
+	int early_filter_cnt;
+	int filter_cnt;
+};
+
+static struct filter_data *filt_dat;
+
+int start(void **data, void *ctx)
+{
+	int dlargc;
+	char **dlargv;
+	struct filter_data *d;
+	static bool called;
+
+	verbose = 1;
+
+	CHECK(!filt_dat && !called);
+	called = true;
+
+	d = calloc(1, sizeof(*d));
+	if (!d)
+		test_fail("Failed to allocate memory");
+	filt_dat = d;
+	*data = d;
+
+	dlargv = perf_dlfilter_fns.args(ctx, &dlargc);
+
+	CHECK(dlargc == 6);
+	CHECK(!strcmp(dlargv[0], "first"));
+	verbose = strtol(dlargv[1], NULL, 0);
+	d->ip = strtoull(dlargv[2], NULL, 0);
+	d->addr = strtoull(dlargv[3], NULL, 0);
+	d->do_early = strtol(dlargv[4], NULL, 0);
+	CHECK(!strcmp(dlargv[5], "last"));
+
+	pr_debug("%s API\n", __func__);
+
+	return 0;
+}
+
+#define CHECK_SAMPLE(x) do { \
+		if (sample->x != expected.x) \
+			return test_fail("'" #x "' not expected value\n"); \
+	} while (0)
+
+static int check_sample(struct filter_data *d, const struct perf_dlfilter_sample *sample)
+{
+	struct perf_dlfilter_sample expected = {
+		.ip		= d->ip,
+		.pid		= 12345,
+		.tid		= 12346,
+		.time		= 1234567890,
+		.addr		= d->addr,
+		.id		= 99,
+		.stream_id	= 101,
+		.period		= 543212345,
+		.cpu		= 31,
+		.cpumode	= PERF_RECORD_MISC_USER,
+		.addr_correlates_sym = 1,
+		.misc		= PERF_RECORD_MISC_USER,
+	};
+
+	CHECK(sample->size >= sizeof(struct perf_dlfilter_sample));
+
+	CHECK_SAMPLE(ip);
+	CHECK_SAMPLE(pid);
+	CHECK_SAMPLE(tid);
+	CHECK_SAMPLE(time);
+	CHECK_SAMPLE(addr);
+	CHECK_SAMPLE(id);
+	CHECK_SAMPLE(stream_id);
+	CHECK_SAMPLE(period);
+	CHECK_SAMPLE(cpu);
+	CHECK_SAMPLE(cpumode);
+	CHECK_SAMPLE(addr_correlates_sym);
+	CHECK_SAMPLE(misc);
+
+	CHECK(!sample->raw_data);
+	CHECK_SAMPLE(brstack_nr);
+	CHECK(!sample->brstack);
+	CHECK_SAMPLE(raw_callchain_nr);
+	CHECK(!sample->raw_callchain);
+
+#define EVENT_NAME "branches:"
+	CHECK(!strncmp(sample->event, EVENT_NAME, strlen(EVENT_NAME)));
+
+	return 0;
+}
+
+static int check_al(void *ctx)
+{
+	const struct perf_dlfilter_al *al;
+
+	al = perf_dlfilter_fns.resolve_ip(ctx);
+	if (!al)
+		return test_fail("resolve_ip() failed");
+
+	CHECK(al->sym && !strcmp("foo", al->sym));
+	CHECK(!al->symoff);
+
+	return 0;
+}
+
+static int check_addr_al(void *ctx)
+{
+	const struct perf_dlfilter_al *addr_al;
+
+	addr_al = perf_dlfilter_fns.resolve_addr(ctx);
+	if (!addr_al)
+		return test_fail("resolve_addr() failed");
+
+	CHECK(addr_al->sym && !strcmp("bar", addr_al->sym));
+	CHECK(!addr_al->symoff);
+
+	return 0;
+}
+
+static int check_address_al(void *ctx, const struct perf_dlfilter_sample *sample)
+{
+	struct perf_dlfilter_al address_al;
+	const struct perf_dlfilter_al *al;
+
+	al = perf_dlfilter_fns.resolve_ip(ctx);
+	if (!al)
+		return test_fail("resolve_ip() failed");
+
+	address_al.size = sizeof(address_al);
+	if (perf_dlfilter_fns.resolve_address(ctx, sample->ip, &address_al))
+		return test_fail("resolve_address() failed");
+
+	CHECK(address_al.sym && al->sym);
+	CHECK(!strcmp(address_al.sym, al->sym));
+	CHECK(address_al.addr == al->addr);
+	CHECK(address_al.sym_start == al->sym_start);
+	CHECK(address_al.sym_end == al->sym_end);
+	CHECK(address_al.dso && al->dso);
+	CHECK(!strcmp(address_al.dso, al->dso));
+
+	/* al_cleanup() is v2 API so may not be present */
+	if (perf_dlfilter_fns.al_cleanup)
+		perf_dlfilter_fns.al_cleanup(ctx, &address_al);
+
+	return 0;
+}
+
+static int check_attr(void *ctx)
+{
+	struct perf_event_attr *attr = perf_dlfilter_fns.attr(ctx);
+
+	CHECK(attr);
+	CHECK(attr->type == PERF_TYPE_HARDWARE);
+	CHECK(attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
+
+	return 0;
+}
+
+static int do_checks(void *data, const struct perf_dlfilter_sample *sample, void *ctx, bool early)
+{
+	struct filter_data *d = data;
+
+	CHECK(data && filt_dat == data);
+
+	if (early) {
+		CHECK(!d->early_filter_cnt);
+		d->early_filter_cnt += 1;
+	} else {
+		CHECK(!d->filter_cnt);
+		CHECK(d->early_filter_cnt);
+		CHECK(d->do_early != 2);
+		d->filter_cnt += 1;
+	}
+
+	if (check_sample(data, sample))
+		return -1;
+
+	if (check_attr(ctx))
+		return -1;
+
+	if (early && !d->do_early)
+		return 0;
+
+	if (check_al(ctx) || check_addr_al(ctx) || check_address_al(ctx, sample))
+		return -1;
+
+	if (early)
+		return d->do_early == 2;
+
+	return 1;
+}
+
+int filter_event_early(void *data, const struct perf_dlfilter_sample *sample, void *ctx)
+{
+	pr_debug("%s API\n", __func__);
+
+	return do_checks(data, sample, ctx, true);
+}
+
+int filter_event(void *data, const struct perf_dlfilter_sample *sample, void *ctx)
+{
+	pr_debug("%s API\n", __func__);
+
+	return do_checks(data, sample, ctx, false);
+}
+
+int stop(void *data, void *ctx)
+{
+	static bool called;
+
+	pr_debug("%s API\n", __func__);
+
+	CHECK(data && filt_dat == data && !called);
+	called = true;
+
+	free(data);
+	filt_dat = NULL;
+	return 0;
+}
+
+const char *filter_description(const char **long_description)
+{
+	*long_description = "Filter used by the 'dlfilter C API' perf test";
+	return "dlfilter to test v2 C API";
+}
diff --git a/tools/perf/include/perf/perf_dlfilter.h b/tools/perf/include/perf/perf_dlfilter.h
index a26e2f129f83..16fc4568ac53 100644
--- a/tools/perf/include/perf/perf_dlfilter.h
+++ b/tools/perf/include/perf/perf_dlfilter.h
@@ -91,6 +91,7 @@ struct perf_dlfilter_al {
 	/* Below members are only populated by resolve_ip() */
 	__u8 filtered; /* True if this sample event will be filtered out */
 	const char *comm;
+	void *priv; /* Private data. Do not change */
 };
 
 struct perf_dlfilter_fns {
@@ -102,7 +103,8 @@ struct perf_dlfilter_fns {
 	char **(*args)(void *ctx, int *dlargc);
 	/*
 	 * Return information about address (al->size must be set before
-	 * calling). Returns 0 on success, -1 otherwise.
+	 * calling). Returns 0 on success, -1 otherwise. Call al_cleanup()
+	 * when 'al' data is no longer needed.
 	 */
 	__s32 (*resolve_address)(void *ctx, __u64 address, struct perf_dlfilter_al *al);
 	/* Return instruction bytes and length */
@@ -113,8 +115,13 @@ struct perf_dlfilter_fns {
 	struct perf_event_attr *(*attr)(void *ctx);
 	/* Read object code, return numbers of bytes read */
 	__s32 (*object_code)(void *ctx, __u64 ip, void *buf, __u32 len);
+	/*
+	 * If present (i.e. must check al_cleanup != NULL), call after
+	 * resolve_address() to free any associated resources.
+	 */
+	void (*al_cleanup)(void *ctx, struct perf_dlfilter_al *al);
 	/* Reserved */
-	void *(*reserved[120])(void *);
+	void *(*reserved[119])(void *);
 };
 
 /*
diff --git a/tools/perf/tests/dlfilter-test.c b/tools/perf/tests/dlfilter-test.c
index 086fd2179e41..da3a9b50b1b1 100644
--- a/tools/perf/tests/dlfilter-test.c
+++ b/tools/perf/tests/dlfilter-test.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
  * Test dlfilter C API. A perf.data file is synthesized and then processed
- * by perf script with a dlfilter named dlfilter-test-api-v0.so. Also a C file
+ * by perf script with dlfilters named dlfilter-test-api-v*.so. Also a C file
  * is compiled to provide a dso to match the synthesized perf.data file.
  */
 
@@ -37,6 +37,8 @@
 
 #define MAP_START 0x400000
 
+#define DLFILTER_TEST_NAME_MAX 128
+
 struct test_data {
 	struct perf_tool tool;
 	struct machine *machine;
@@ -45,6 +47,8 @@ struct test_data {
 	u64 bar;
 	u64 ip;
 	u64 addr;
+	char name[DLFILTER_TEST_NAME_MAX];
+	char desc[DLFILTER_TEST_NAME_MAX];
 	char perf[PATH_MAX];
 	char perf_data_file_name[PATH_MAX];
 	char c_file_name[PATH_MAX];
@@ -215,7 +219,7 @@ static int write_prog(char *file_name)
 	return err ? -1 : 0;
 }
 
-static int get_dlfilters_path(char *buf, size_t sz)
+static int get_dlfilters_path(const char *name, char *buf, size_t sz)
 {
 	char perf[PATH_MAX];
 	char path[PATH_MAX];
@@ -224,12 +228,12 @@ static int get_dlfilters_path(char *buf, size_t sz)
 
 	perf_exe(perf, sizeof(perf));
 	perf_path = dirname(perf);
-	snprintf(path, sizeof(path), "%s/dlfilters/dlfilter-test-api-v0.so", perf_path);
+	snprintf(path, sizeof(path), "%s/dlfilters/%s", perf_path, name);
 	if (access(path, R_OK)) {
 		exec_path = get_argv_exec_path();
 		if (!exec_path)
 			return -1;
-		snprintf(path, sizeof(path), "%s/dlfilters/dlfilter-test-api-v0.so", exec_path);
+		snprintf(path, sizeof(path), "%s/dlfilters/%s", exec_path, name);
 		free(exec_path);
 		if (access(path, R_OK))
 			return -1;
@@ -244,9 +248,9 @@ static int check_filter_desc(struct test_data *td)
 	char *desc = NULL;
 	int ret;
 
-	if (get_filter_desc(td->dlfilters, "dlfilter-test-api-v0.so", &desc, &long_desc) &&
+	if (get_filter_desc(td->dlfilters, td->name, &desc, &long_desc) &&
 	    long_desc && !strcmp(long_desc, "Filter used by the 'dlfilter C API' perf test") &&
-	    desc && !strcmp(desc, "dlfilter to test v0 C API"))
+	    desc && !strcmp(desc, td->desc))
 		ret = 0;
 	else
 		ret = -1;
@@ -284,7 +288,7 @@ static int get_ip_addr(struct test_data *td)
 static int do_run_perf_script(struct test_data *td, int do_early)
 {
 	return system_cmd("%s script -i %s "
-			  "--dlfilter %s/dlfilter-test-api-v0.so "
+			  "--dlfilter %s/%s "
 			  "--dlarg first "
 			  "--dlarg %d "
 			  "--dlarg %" PRIu64 " "
@@ -292,7 +296,7 @@ static int do_run_perf_script(struct test_data *td, int do_early)
 			  "--dlarg %d "
 			  "--dlarg last",
 			  td->perf, td->perf_data_file_name, td->dlfilters,
-			  verbose, td->ip, td->addr, do_early);
+			  td->name, verbose, td->ip, td->addr, do_early);
 }
 
 static int run_perf_script(struct test_data *td)
@@ -321,7 +325,7 @@ static int test__dlfilter_test(struct test_data *td)
 	u64 id = 99;
 	int err;
 
-	if (get_dlfilters_path(td->dlfilters, PATH_MAX))
+	if (get_dlfilters_path(td->name, td->dlfilters, PATH_MAX))
 		return test_result("dlfilters not found", TEST_SKIP);
 
 	if (check_filter_desc(td))
@@ -399,14 +403,18 @@ static void test_data__free(struct test_data *td)
 	}
 }
 
-static int test__dlfilter(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
+static int test__dlfilter_ver(int ver)
 {
 	struct test_data td = {.fd = -1};
 	int pid = getpid();
 	int err;
 
+	pr_debug("\n-- Testing version %d API --\n", ver);
+
 	perf_exe(td.perf, sizeof(td.perf));
 
+	snprintf(td.name, sizeof(td.name), "dlfilter-test-api-v%d.so", ver);
+	snprintf(td.desc, sizeof(td.desc), "dlfilter to test v%d C API", ver);
 	snprintf(td.perf_data_file_name, PATH_MAX, "/tmp/dlfilter-test-%u-perf-data", pid);
 	snprintf(td.c_file_name, PATH_MAX, "/tmp/dlfilter-test-%u-prog.c", pid);
 	snprintf(td.prog_file_name, PATH_MAX, "/tmp/dlfilter-test-%u-prog", pid);
@@ -416,4 +424,14 @@ static int test__dlfilter(struct test_suite *test __maybe_unused, int subtest __
 	return err;
 }
 
+static int test__dlfilter(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
+{
+	int err = test__dlfilter_ver(0);
+
+	if (err)
+		return err;
+	/* No test for version 1 */
+	return test__dlfilter_ver(2);
+}
+
 DEFINE_SUITE("dlfilter C API", dlfilter);
diff --git a/tools/perf/util/dlfilter.c b/tools/perf/util/dlfilter.c
index 798a53d7e6c9..e0f822ebb9b9 100644
--- a/tools/perf/util/dlfilter.c
+++ b/tools/perf/util/dlfilter.c
@@ -10,6 +10,8 @@
 #include <subcmd/exec-cmd.h>
 #include <linux/zalloc.h>
 #include <linux/build_bug.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
 
 #include "debug.h"
 #include "event.h"
@@ -63,6 +65,7 @@ static void al_to_d_al(struct addr_location *al, struct perf_dlfilter_al *d_al)
 	d_al->addr = al->addr;
 	d_al->comm = NULL;
 	d_al->filtered = 0;
+	d_al->priv = NULL;
 }
 
 static struct addr_location *get_al(struct dlfilter *d)
@@ -151,6 +154,11 @@ static char **dlfilter__args(void *ctx, int *dlargc)
 	return d->dlargv;
 }
 
+static bool has_priv(struct perf_dlfilter_al *d_al_p)
+{
+	return d_al_p->size >= offsetof(struct perf_dlfilter_al, priv) + sizeof(d_al_p->priv);
+}
+
 static __s32 dlfilter__resolve_address(void *ctx, __u64 address, struct perf_dlfilter_al *d_al_p)
 {
 	struct dlfilter *d = (struct dlfilter *)ctx;
@@ -177,9 +185,29 @@ static __s32 dlfilter__resolve_address(void *ctx, __u64 address, struct perf_dlf
 	memcpy(d_al_p, &d_al, min((size_t)sz, sizeof(d_al)));
 	d_al_p->size = sz;
 
+	if (has_priv(d_al_p))
+		d_al_p->priv = memdup(&al, sizeof(al));
+
 	return 0;
 }
 
+static void dlfilter__al_cleanup(void *ctx __maybe_unused, struct perf_dlfilter_al *d_al_p)
+{
+	struct addr_location *al;
+
+	/* Ensure backward compatibility */
+	if (!has_priv(d_al_p) || !d_al_p->priv)
+		return;
+
+	al = d_al_p->priv;
+
+	d_al_p->priv = NULL;
+
+	addr_location__exit(al);
+
+	free(al);
+}
+
 static const __u8 *dlfilter__insn(void *ctx, __u32 *len)
 {
 	struct dlfilter *d = (struct dlfilter *)ctx;
@@ -297,6 +325,7 @@ static const struct perf_dlfilter_fns perf_dlfilter_fns = {
 	.resolve_addr    = dlfilter__resolve_addr,
 	.args            = dlfilter__args,
 	.resolve_address = dlfilter__resolve_address,
+	.al_cleanup      = dlfilter__al_cleanup,
 	.insn            = dlfilter__insn,
 	.srcline         = dlfilter__srcline,
 	.attr            = dlfilter__attr,

From a4b6452af7f481d9a36037dd7c76c2d394992ad5 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@arm.com>
Date: Fri, 11 Aug 2023 15:39:18 +0100
Subject: [PATCH 0422/1189] perf cs-etm: Don't duplicate FIELD_GET()

linux/bitfield.h can be included as long as linux/kernel.h is included
first, so change the order of the includes and drop the duplicate macro.

Reviewed-by: John Garry <john.g.garry@oracle.com>
Signed-off-by: James Clark <james.clark@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Forrington <nick.forrington@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rob Herring <robh@kernel.org>
Cc: Sohom Datta <sohomdatta1@gmail.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20230811144017.491628-2-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/cs-etm.c | 14 ++------------
 1 file changed, 2 insertions(+), 12 deletions(-)

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 1419b40dfbe8..9729d006550d 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -6,10 +6,11 @@
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
  */
 
+#include <linux/kernel.h>
+#include <linux/bitfield.h>
 #include <linux/bitops.h>
 #include <linux/coresight-pmu.h>
 #include <linux/err.h>
-#include <linux/kernel.h>
 #include <linux/log2.h>
 #include <linux/types.h>
 #include <linux/zalloc.h>
@@ -281,17 +282,6 @@ static int cs_etm__metadata_set_trace_id(u8 trace_chan_id, u64 *cpu_metadata)
 	return 0;
 }
 
-/*
- * FIELD_GET (linux/bitfield.h) not available outside kernel code,
- * and the header contains too many dependencies to just copy over,
- * so roll our own based on the original
- */
-#define __bf_shf(x) (__builtin_ffsll(x) - 1)
-#define FIELD_GET(_mask, _reg)						\
-	({								\
-		(typeof(_mask))(((_reg) & (_mask)) >> __bf_shf(_mask)); \
-	})
-
 /*
  * Get a metadata for a specific cpu from an array.
  *

From ab3744007d51420dd63d5323acbe7abbb843ba63 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@arm.com>
Date: Fri, 11 Aug 2023 15:39:21 +0100
Subject: [PATCH 0423/1189] perf vendor events arm64: Update scale units and
 descriptions of common topdown metrics

Metrics will be published here [1] going forwards, but they have
slightly different scale units. To allow autogenerated metrics to be
added more easily, update the scale units to match.

The more detailed descriptions have also been taken and added to the
common file.

[1]: https://gitlab.arm.com/telemetry-solution/telemetry-solution/-/tree/main/data/pmu/cpu/

Reviewed-by: John Garry <john.g.garry@oracle.com>
Signed-off-by: James Clark <james.clark@arm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Forrington <nick.forrington@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rob Herring <robh@kernel.org>
Cc: Sohom Datta <sohomdatta1@gmail.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20230811144017.491628-5-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/arch/arm64/sbsa.json | 24 +++++++++++-----------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/tools/perf/pmu-events/arch/arm64/sbsa.json b/tools/perf/pmu-events/arch/arm64/sbsa.json
index f90b338261ac..4eed79a28f6e 100644
--- a/tools/perf/pmu-events/arch/arm64/sbsa.json
+++ b/tools/perf/pmu-events/arch/arm64/sbsa.json
@@ -1,34 +1,34 @@
 [
     {
-        "MetricExpr": "stall_slot_frontend / (#slots * cpu_cycles)",
-        "BriefDescription": "Frontend bound L1 topdown metric",
+        "MetricExpr": "100 * (stall_slot_frontend / (#slots * cpu_cycles))",
+        "BriefDescription": "This metric is the percentage of total slots that were stalled due to resource constraints in the frontend of the processor.",
         "DefaultMetricgroupName": "TopdownL1",
         "MetricGroup": "Default;TopdownL1",
         "MetricName": "frontend_bound",
-        "ScaleUnit": "100%"
+        "ScaleUnit": "1percent of slots"
     },
     {
-        "MetricExpr": "(1 - op_retired / op_spec) * (1 - stall_slot / (#slots * cpu_cycles))",
-        "BriefDescription": "Bad speculation L1 topdown metric",
+        "MetricExpr": "100 * ((1 - op_retired / op_spec) * (1 - stall_slot / (#slots * cpu_cycles)))",
+        "BriefDescription": "This metric is the percentage of total slots that executed operations and didn't retire due to a pipeline flush.\nThis indicates cycles that were utilized but inefficiently.",
         "DefaultMetricgroupName": "TopdownL1",
         "MetricGroup": "Default;TopdownL1",
         "MetricName": "bad_speculation",
-        "ScaleUnit": "100%"
+        "ScaleUnit": "1percent of slots"
     },
     {
-        "MetricExpr": "(op_retired / op_spec) * (1 - stall_slot / (#slots * cpu_cycles))",
-        "BriefDescription": "Retiring L1 topdown metric",
+        "MetricExpr": "100 * ((op_retired / op_spec) * (1 - stall_slot / (#slots * cpu_cycles)))",
+        "BriefDescription": "This metric is the percentage of total slots that retired operations, which indicates cycles that were utilized efficiently.",
         "DefaultMetricgroupName": "TopdownL1",
         "MetricGroup": "Default;TopdownL1",
         "MetricName": "retiring",
-        "ScaleUnit": "100%"
+        "ScaleUnit": "1percent of slots"
     },
     {
-        "MetricExpr": "stall_slot_backend / (#slots * cpu_cycles)",
-        "BriefDescription": "Backend Bound L1 topdown metric",
+        "MetricExpr": "100 * (stall_slot_backend / (#slots * cpu_cycles))",
+        "BriefDescription": "This metric is the percentage of total slots that were stalled due to resource constraints in the backend of the processor.",
         "DefaultMetricgroupName": "TopdownL1",
         "MetricGroup": "Default;TopdownL1",
         "MetricName": "backend_bound",
-        "ScaleUnit": "100%"
+        "ScaleUnit": "1percent of slots"
     }
 ]

From 4d6af37cafad69ff93f62db80d5a3daa9ac3223f Mon Sep 17 00:00:00 2001
From: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Date: Thu, 15 Jun 2023 12:58:19 +0200
Subject: [PATCH 0424/1189] rtc: isl12022: remove wrong warning for low battery
 level

There are multiple problems with this warning.

First of all, it triggers way too often, in fact nearly on every boot,
because the SR_LBAT85/SR_LBAT75 bits have another meaning when in
battery backup mode. Quoting from the data sheet:

  LOW BATTERY INDICATOR 85% BIT (LBAT85)

  In Normal Mode (VDD), this bit indicates when the battery level has
  dropped below the pre-selected trip levels. [...] The LBAT85
  detection happens automatically once every minute when seconds
  register reaches 59.

  In Battery Mode (VBAT), this bit indicates the device has entered
  into battery mode by polling once every 10 minutes. The LBAT85
  detection happens automatically once when the minute register
  reaches x9h or x0h minutes.

Similar wording applies to the LBAT75 bit.

This means that if the device is powered off for more than 10 minutes,
the LBAT85 bit is guaranteed to be set. Upon power-on, unless we're
close enough to the end of a minute and/or the boot is slow enough
that the second register passes 59, the LBAT85 bit is still set when
the kernel (or early userspace) reads the RTC to set the system's
wallclock time.

Another minor problem is with the bit logic. If the 75% level is
reached, logically we're also below 85%, so both bits would most
likely be set. So even if the battery is below 75%, the warning would
still say "voltage dropped below 85%".

A third problem is that the driver and current DT binding offer no way
to indicate the nominal battery level and/or settings of the Battery
Level Monitor Trip Bits. Since the default value of the VB85TP[2:0] and
VB75TP[2:0] bits are 000, this means the actual setting of the
LBAT85/LBAT75 bits in VDD mode doesn't happen until the battery is below
2.125V/1.875V, which for a standard 3V battery is way too late.

A fourth problem is emitting this warning from ->read_time:
util-linux' hwclock will, in the absence of support for getting an
interrupt when the seconds counter is updated, issue
ioctl(RTC_RD_TIME) in a busy-loop until it sees a change in the
seconds field. In that case, if the battery low bits are set (either
genuinely, more than a minute after boot, due to the battery actually
being low, or as above, bogusly shortly after boot), the kernel log is
swamped with hundreds of identical warnings.

Subsequent patches will add such bindings and driver support, and also
proper support for RTC_VL_READ. For now, remove the broken warning.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Link: https://lore.kernel.org/r/20230615105826.411953-2-linux@rasmusvillemoes.dk
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-isl12022.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/rtc/rtc-isl12022.c b/drivers/rtc/rtc-isl12022.c
index a613257d1574..a39aea90230f 100644
--- a/drivers/rtc/rtc-isl12022.c
+++ b/drivers/rtc/rtc-isl12022.c
@@ -141,12 +141,6 @@ static int isl12022_rtc_read_time(struct device *dev, struct rtc_time *tm)
 	if (ret)
 		return ret;
 
-	if (buf[ISL12022_REG_SR] & (ISL12022_SR_LBAT85 | ISL12022_SR_LBAT75)) {
-		dev_warn(dev,
-			 "voltage dropped below %u%%, date and time is not reliable.\n",
-			 buf[ISL12022_REG_SR] & ISL12022_SR_LBAT85 ? 85 : 75);
-	}
-
 	dev_dbg(dev,
 		"raw data is sec=%02x, min=%02x, hr=%02x, mday=%02x, mon=%02x, year=%02x, wday=%02x, sr=%02x, int=%02x",
 		buf[ISL12022_REG_SC],

From ffc005280a47030d16cbbf3105c75d3562dba5a8 Mon Sep 17 00:00:00 2001
From: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Date: Thu, 15 Jun 2023 12:58:20 +0200
Subject: [PATCH 0425/1189] dt-bindings: rtc: Move isil,isl12022 from
 trivial-rtc.yaml into own schema file

Move the isil,isl12022 RTC bindings from trivial-rtc.yaml into its own
intersil,isl12022.yaml file, in preparation for adding more bindings.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Link: https://lore.kernel.org/r/20230615105826.411953-3-linux@rasmusvillemoes.dk
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 .../bindings/rtc/intersil,isl12022.yaml       | 45 +++++++++++++++++++
 .../devicetree/bindings/rtc/trivial-rtc.yaml  |  2 -
 2 files changed, 45 insertions(+), 2 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/rtc/intersil,isl12022.yaml

diff --git a/Documentation/devicetree/bindings/rtc/intersil,isl12022.yaml b/Documentation/devicetree/bindings/rtc/intersil,isl12022.yaml
new file mode 100644
index 000000000000..054d3fc649ba
--- /dev/null
+++ b/Documentation/devicetree/bindings/rtc/intersil,isl12022.yaml
@@ -0,0 +1,45 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/rtc/intersil,isl12022.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Intersil ISL12022 Real-time Clock
+
+maintainers:
+  - Alexandre Belloni <alexandre.belloni@bootlin.com>
+
+properties:
+  compatible:
+    const: isil,isl12022
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+
+allOf:
+  - $ref: rtc.yaml#
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        rtc@6f {
+            compatible = "isil,isl12022";
+            reg = <0x6f>;
+            interrupts-extended = <&gpio1 5 IRQ_TYPE_LEVEL_LOW>;
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml b/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml
index 9af77f21bb7f..2a65f31ac5a0 100644
--- a/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml
+++ b/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml
@@ -45,8 +45,6 @@ properties:
       - isil,isl1208
       # Intersil ISL1218 Low Power RTC with Battery Backed SRAM
       - isil,isl1218
-      # Intersil ISL12022 Real-time Clock
-      - isil,isl12022
       # Real Time Clock Module with I2C-Bus
       - microcrystal,rv3029
       # Real Time Clock

From 69b569c124ffa698de25d039018fe86313c46c84 Mon Sep 17 00:00:00 2001
From: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Date: Thu, 15 Jun 2023 12:58:21 +0200
Subject: [PATCH 0426/1189] dt-bindings: rtc: isl12022: add bindings for
 battery alarm trip levels

The isl12022 has a built-in support for monitoring the voltage of the
backup battery, and setting bits in the status register when that
voltage drops below two predetermined levels (usually 85% and 75% of
the nominal voltage). However, since it can operate at wide range of
battery voltages (2.5V - 5.5V), one must configure those trip levels
according to which battery is used on a given board.

Add bindings for defining these two trip levels. While the register
and bit names suggest that they should correspond to 85% and 75% of
the nominal battery voltage, the data sheet also says

  There are total of 7 levels that could be selected for the first
  alarm. Any of the of levels could be selected as the first alarm
  with no reference as to nominal Battery voltage level.

Hence this provides the hardware designer the ability to choose values
based on the discharge characteristics of the battery chosen for the
given product, rather than just having one battery-microvolt property
and having the driver choose levels close to 0.85/0.75 times that.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20230615105826.411953-4-linux@rasmusvillemoes.dk
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 .../devicetree/bindings/rtc/intersil,isl12022.yaml       | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/Documentation/devicetree/bindings/rtc/intersil,isl12022.yaml b/Documentation/devicetree/bindings/rtc/intersil,isl12022.yaml
index 054d3fc649ba..3c6c07aaa78f 100644
--- a/Documentation/devicetree/bindings/rtc/intersil,isl12022.yaml
+++ b/Documentation/devicetree/bindings/rtc/intersil,isl12022.yaml
@@ -19,6 +19,14 @@ properties:
   interrupts:
     maxItems: 1
 
+  isil,battery-trip-levels-microvolt:
+    description:
+      The battery voltages at which the first alarm and second alarm
+      should trigger (normally ~85% and ~75% of nominal V_BAT).
+    items:
+      - enum: [2125000, 2295000, 2550000, 2805000, 3060000, 4250000, 4675000]
+      - enum: [1875000, 2025000, 2250000, 2475000, 2700000, 3750000, 4125000]
+
 required:
   - compatible
   - reg
@@ -39,6 +47,7 @@ examples:
             compatible = "isil,isl12022";
             reg = <0x6f>;
             interrupts-extended = <&gpio1 5 IRQ_TYPE_LEVEL_LOW>;
+            isil,battery-trip-levels-microvolt = <2550000>, <2250000>;
         };
     };
 

From 2caeb566baabb65add7d99ca6d8bfd566fe91582 Mon Sep 17 00:00:00 2001
From: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Date: Thu, 15 Jun 2023 12:58:22 +0200
Subject: [PATCH 0427/1189] rtc: isl12022: add support for trip level DT
 binding

Implement support for using the values given in the
isil,battery-trip-levels-microvolt property to set appropriate values
in the VB85TP/VB75TP bits in the PWR_VBAT register.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Link: https://lore.kernel.org/r/20230615105826.411953-5-linux@rasmusvillemoes.dk
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-isl12022.c | 39 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/drivers/rtc/rtc-isl12022.c b/drivers/rtc/rtc-isl12022.c
index a39aea90230f..a50eed4e4028 100644
--- a/drivers/rtc/rtc-isl12022.c
+++ b/drivers/rtc/rtc-isl12022.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/bcd.h>
+#include <linux/bitfield.h>
 #include <linux/err.h>
 #include <linux/hwmon.h>
 #include <linux/i2c.h>
@@ -31,6 +32,8 @@
 #define ISL12022_REG_SR		0x07
 #define ISL12022_REG_INT	0x08
 
+#define ISL12022_REG_PWR_VBAT	0x0a
+
 #define ISL12022_REG_BETA	0x0d
 #define ISL12022_REG_TEMP_L	0x28
 
@@ -42,6 +45,9 @@
 
 #define ISL12022_INT_WRTC	(1 << 6)
 
+#define ISL12022_REG_VB85_MASK	GENMASK(5, 3)
+#define ISL12022_REG_VB75_MASK	GENMASK(2, 0)
+
 #define ISL12022_BETA_TSE	(1 << 7)
 
 static umode_t isl12022_hwmon_is_visible(const void *data,
@@ -209,6 +215,38 @@ static const struct regmap_config regmap_config = {
 	.use_single_write = true,
 };
 
+static const u32 trip_levels[2][7] = {
+	{ 2125000, 2295000, 2550000, 2805000, 3060000, 4250000, 4675000 },
+	{ 1875000, 2025000, 2250000, 2475000, 2700000, 3750000, 4125000 },
+};
+
+static void isl12022_set_trip_levels(struct device *dev)
+{
+	struct regmap *regmap = dev_get_drvdata(dev);
+	u32 levels[2] = {0, 0};
+	int ret, i, j, x[2];
+	u8 val, mask;
+
+	device_property_read_u32_array(dev, "isil,battery-trip-levels-microvolt",
+				       levels, 2);
+
+	for (i = 0; i < 2; i++) {
+		for (j = 0; j < ARRAY_SIZE(trip_levels[i]) - 1; j++) {
+			if (levels[i] <= trip_levels[i][j])
+				break;
+		}
+		x[i] = j;
+	}
+
+	val = FIELD_PREP(ISL12022_REG_VB85_MASK, x[0]) |
+		FIELD_PREP(ISL12022_REG_VB75_MASK, x[1]);
+	mask = ISL12022_REG_VB85_MASK | ISL12022_REG_VB75_MASK;
+
+	ret = regmap_update_bits(regmap, ISL12022_REG_PWR_VBAT, mask, val);
+	if (ret)
+		dev_warn(dev, "unable to set battery alarm levels: %d\n", ret);
+}
+
 static int isl12022_probe(struct i2c_client *client)
 {
 	struct rtc_device *rtc;
@@ -225,6 +263,7 @@ static int isl12022_probe(struct i2c_client *client)
 
 	dev_set_drvdata(&client->dev, regmap);
 
+	isl12022_set_trip_levels(&client->dev);
 	isl12022_hwmon_register(&client->dev);
 
 	rtc = devm_rtc_allocate_device(&client->dev);

From eccebd813874b748ac4e79a9fe4c7290117ad3be Mon Sep 17 00:00:00 2001
From: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Date: Thu, 15 Jun 2023 12:58:23 +0200
Subject: [PATCH 0428/1189] rtc: isl12022: implement RTC_VL_READ ioctl

Hook up support for reading the values of the SR_LBAT85 and SR_LBAT75
bits. Translate the former to "battery low", and the latter to
"battery empty or not-present".

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Link: https://lore.kernel.org/r/20230615105826.411953-6-linux@rasmusvillemoes.dk
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-isl12022.c | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/drivers/rtc/rtc-isl12022.c b/drivers/rtc/rtc-isl12022.c
index a50eed4e4028..0ed28b57bcd8 100644
--- a/drivers/rtc/rtc-isl12022.c
+++ b/drivers/rtc/rtc-isl12022.c
@@ -204,7 +204,34 @@ static int isl12022_rtc_set_time(struct device *dev, struct rtc_time *tm)
 	return regmap_bulk_write(regmap, ISL12022_REG_SC, buf, sizeof(buf));
 }
 
+static int isl12022_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
+{
+	struct regmap *regmap = dev_get_drvdata(dev);
+	u32 user, val;
+	int ret;
+
+	switch (cmd) {
+	case RTC_VL_READ:
+		ret = regmap_read(regmap, ISL12022_REG_SR, &val);
+		if (ret)
+			return ret;
+
+		user = 0;
+		if (val & ISL12022_SR_LBAT85)
+			user |= RTC_VL_BACKUP_LOW;
+
+		if (val & ISL12022_SR_LBAT75)
+			user |= RTC_VL_BACKUP_EMPTY;
+
+		return put_user(user, (u32 __user *)arg);
+
+	default:
+		return -ENOIOCTLCMD;
+	}
+}
+
 static const struct rtc_class_ops isl12022_rtc_ops = {
+	.ioctl		= isl12022_rtc_ioctl,
 	.read_time	= isl12022_rtc_read_time,
 	.set_time	= isl12022_rtc_set_time,
 };

From a11b6c460620f7fb5fae4c3aee5a5ba2e1e1129b Mon Sep 17 00:00:00 2001
From: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Date: Thu, 15 Jun 2023 12:58:24 +0200
Subject: [PATCH 0429/1189] rtc: isl12022: trigger battery level detection
 during probe

Since the meaning of the SR_LBAT85 and SR_LBAT75 bits are different in
battery backup mode, they may very well be set after power on, and
stay set for up to a minute (i.e. until the battery detection in VDD
mode happens when the seconds counter hits 59). This would mean that
userspace doing a ioctl(RTC_VL_READ) early on could get a false
positive.

The battery level detection can also be triggered by explicitly
writing a 1 to the TSE bit in the BETA register. Do that once during
boot. Empirically, this does not immediately update the bits in
the status register (i.e., an immediate read of SR after this write
can still show stale values), but the update is done after a few
milliseconds, so certainly before the RTC device gets registered and
userspace has a chance of doing the ioctl() on this device.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Link: https://lore.kernel.org/r/20230615105826.411953-7-linux@rasmusvillemoes.dk
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-isl12022.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/rtc/rtc-isl12022.c b/drivers/rtc/rtc-isl12022.c
index 0ed28b57bcd8..a816c5447295 100644
--- a/drivers/rtc/rtc-isl12022.c
+++ b/drivers/rtc/rtc-isl12022.c
@@ -272,6 +272,16 @@ static void isl12022_set_trip_levels(struct device *dev)
 	ret = regmap_update_bits(regmap, ISL12022_REG_PWR_VBAT, mask, val);
 	if (ret)
 		dev_warn(dev, "unable to set battery alarm levels: %d\n", ret);
+
+	/*
+	 * Force a write of the TSE bit in the BETA register, in order
+	 * to trigger an update of the LBAT75 and LBAT85 bits in the
+	 * status register. In battery backup mode, those bits have
+	 * another meaning, so without this, they may contain stale
+	 * values for up to a minute after power-on.
+	 */
+	regmap_write_bits(regmap, ISL12022_REG_BETA,
+			  ISL12022_BETA_TSE, ISL12022_BETA_TSE);
 }
 
 static int isl12022_probe(struct i2c_client *client)

From ab246c897be0bdf981f776399ca62b5ec4b8138f Mon Sep 17 00:00:00 2001
From: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Date: Thu, 15 Jun 2023 12:58:25 +0200
Subject: [PATCH 0430/1189] dt-bindings: rtc: isl12022: add #clock-cells
 property

The isl12022 has a dual-purpose irq/f_out pin, which can either be
used as an interrupt or clock output.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20230615105826.411953-8-linux@rasmusvillemoes.dk
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 .../devicetree/bindings/rtc/intersil,isl12022.yaml     | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/Documentation/devicetree/bindings/rtc/intersil,isl12022.yaml b/Documentation/devicetree/bindings/rtc/intersil,isl12022.yaml
index 3c6c07aaa78f..c2d1441ef273 100644
--- a/Documentation/devicetree/bindings/rtc/intersil,isl12022.yaml
+++ b/Documentation/devicetree/bindings/rtc/intersil,isl12022.yaml
@@ -19,6 +19,9 @@ properties:
   interrupts:
     maxItems: 1
 
+  '#clock-cells':
+    const: 0
+
   isil,battery-trip-levels-microvolt:
     description:
       The battery voltages at which the first alarm and second alarm
@@ -33,6 +36,13 @@ required:
 
 allOf:
   - $ref: rtc.yaml#
+  # If #clock-cells is present, interrupts must not be present
+  - if:
+      required:
+        - '#clock-cells'
+    then:
+      properties:
+        interrupts: false
 
 unevaluatedProperties: false
 

From d57d12db774820819d0e591548a56b5cfc95f82a Mon Sep 17 00:00:00 2001
From: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Date: Thu, 15 Jun 2023 12:58:26 +0200
Subject: [PATCH 0431/1189] rtc: isl12022: implement support for the
 #clock-cells DT property

If device tree implies that the chip's IRQ/F_OUT pin is used as a
clock, expose that in the driver. For now, pretend it is a
fixed-rate (32kHz) clock; if other use cases appear the driver can be
updated to provide its own clk_ops etc.

When the clock output is not used on a given board, one can prolong
the battery life by ensuring that the FOx bits are 0. For the hardware
I'm currently working on, the RTC draws 1.2uA with the FOx bits at
their default 0001 value, dropping to 0.88uA when those bits are
cleared.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Link: https://lore.kernel.org/r/20230615105826.411953-9-linux@rasmusvillemoes.dk
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-isl12022.c | 44 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/drivers/rtc/rtc-isl12022.c b/drivers/rtc/rtc-isl12022.c
index a816c5447295..4eef7afcc8bc 100644
--- a/drivers/rtc/rtc-isl12022.c
+++ b/drivers/rtc/rtc-isl12022.c
@@ -10,6 +10,7 @@
 
 #include <linux/bcd.h>
 #include <linux/bitfield.h>
+#include <linux/clk-provider.h>
 #include <linux/err.h>
 #include <linux/hwmon.h>
 #include <linux/i2c.h>
@@ -44,6 +45,9 @@
 #define ISL12022_SR_LBAT75	(1 << 1)
 
 #define ISL12022_INT_WRTC	(1 << 6)
+#define ISL12022_INT_FO_MASK	GENMASK(3, 0)
+#define ISL12022_INT_FO_OFF	0x0
+#define ISL12022_INT_FO_32K	0x1
 
 #define ISL12022_REG_VB85_MASK	GENMASK(5, 3)
 #define ISL12022_REG_VB75_MASK	GENMASK(2, 0)
@@ -242,6 +246,41 @@ static const struct regmap_config regmap_config = {
 	.use_single_write = true,
 };
 
+static int isl12022_register_clock(struct device *dev)
+{
+	struct regmap *regmap = dev_get_drvdata(dev);
+	struct clk_hw *hw;
+	int ret;
+
+	if (!device_property_present(dev, "#clock-cells")) {
+		/*
+		 * Disabling the F_OUT pin reduces the power
+		 * consumption in battery mode by ~25%.
+		 */
+		regmap_update_bits(regmap, ISL12022_REG_INT, ISL12022_INT_FO_MASK,
+				   ISL12022_INT_FO_OFF);
+
+		return 0;
+	}
+
+	if (!IS_ENABLED(CONFIG_COMMON_CLK))
+		return 0;
+
+	/*
+	 * For now, only support a fixed clock of 32768Hz (the reset default).
+	 */
+	ret = regmap_update_bits(regmap, ISL12022_REG_INT,
+				 ISL12022_INT_FO_MASK, ISL12022_INT_FO_32K);
+	if (ret)
+		return ret;
+
+	hw = devm_clk_hw_register_fixed_rate(dev, "isl12022", NULL, 0, 32768);
+	if (IS_ERR(hw))
+		return PTR_ERR(hw);
+
+	return devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, hw);
+}
+
 static const u32 trip_levels[2][7] = {
 	{ 2125000, 2295000, 2550000, 2805000, 3060000, 4250000, 4675000 },
 	{ 1875000, 2025000, 2250000, 2475000, 2700000, 3750000, 4125000 },
@@ -288,6 +327,7 @@ static int isl12022_probe(struct i2c_client *client)
 {
 	struct rtc_device *rtc;
 	struct regmap *regmap;
+	int ret;
 
 	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C))
 		return -ENODEV;
@@ -300,6 +340,10 @@ static int isl12022_probe(struct i2c_client *client)
 
 	dev_set_drvdata(&client->dev, regmap);
 
+	ret = isl12022_register_clock(&client->dev);
+	if (ret)
+		return ret;
+
 	isl12022_set_trip_levels(&client->dev);
 	isl12022_hwmon_register(&client->dev);
 

From 737055e11729836fc3d7b26220affad30b4736ec Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Thu, 10 Aug 2023 12:38:59 +0200
Subject: [PATCH 0432/1189] rtc: ds1307: fix Wvoid-pointer-to-enum-cast warning

'type' is an enum, thus cast of pointer on 64-bit compile test with W=1
causes:

  rtc-ds1307.c:1747:18: error: cast to smaller integer type 'enum ds_type' from 'const void *' [-Werror,-Wvoid-pointer-to-enum-cast]

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20230810103902.151145-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-ds1307.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c
index cb5acecc11aa..506b7d1c2397 100644
--- a/drivers/rtc/rtc-ds1307.c
+++ b/drivers/rtc/rtc-ds1307.c
@@ -1744,7 +1744,7 @@ static int ds1307_probe(struct i2c_client *client)
 
 	match = device_get_match_data(&client->dev);
 	if (match) {
-		ds1307->type = (enum ds_type)match;
+		ds1307->type = (uintptr_t)match;
 		chip = &chips[ds1307->type];
 	} else if (id) {
 		chip = &chips[id->driver_data];

From fbbeae0af551b8e5fba6ba128d2190c2a29dce90 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Thu, 10 Aug 2023 12:39:00 +0200
Subject: [PATCH 0433/1189] rtc: rv8803: fix Wvoid-pointer-to-enum-cast warning

'type' is an enum, thus cast of pointer on 64-bit compile test with W=1
causes:

  rtc-rv8803.c:648:18: error: cast to smaller integer type 'enum rv8803_type' from 'const void *' [-Werror,-Wvoid-pointer-to-enum-cast]

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20230810103902.151145-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-rv8803.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/rtc/rtc-rv8803.c b/drivers/rtc/rtc-rv8803.c
index fd8ab0b2f731..1a3ec1bb5b81 100644
--- a/drivers/rtc/rtc-rv8803.c
+++ b/drivers/rtc/rtc-rv8803.c
@@ -645,8 +645,7 @@ static int rv8803_probe(struct i2c_client *client)
 	mutex_init(&rv8803->flags_lock);
 	rv8803->client = client;
 	if (client->dev.of_node) {
-		rv8803->type = (enum rv8803_type)
-			of_device_get_match_data(&client->dev);
+		rv8803->type = (uintptr_t)of_device_get_match_data(&client->dev);
 	} else {
 		const struct i2c_device_id *id = i2c_match_id(rv8803_id, client);
 

From 4ebbd463050d14989b4dd2de52deb0779969af41 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Thu, 10 Aug 2023 12:39:01 +0200
Subject: [PATCH 0434/1189] rtc: jz4740: fix Wvoid-pointer-to-enum-cast warning

'type' is an enum, thus cast of pointer on 64-bit compile test with W=1
causes:

  rtc-jz4740.c:352:14: error: cast to smaller integer type 'enum jz4740_rtc_type' from 'const void *' [-Werror,-Wvoid-pointer-to-enum-cast]

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20230810103902.151145-3-krzysztof.kozlowski@linaro.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-jz4740.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/rtc/rtc-jz4740.c b/drivers/rtc/rtc-jz4740.c
index 6ba889d7d4c4..bafa7d1b9b88 100644
--- a/drivers/rtc/rtc-jz4740.c
+++ b/drivers/rtc/rtc-jz4740.c
@@ -349,7 +349,7 @@ static int jz4740_rtc_probe(struct platform_device *pdev)
 	if (!rtc)
 		return -ENOMEM;
 
-	rtc->type = (enum jz4740_rtc_type)device_get_match_data(dev);
+	rtc->type = (uintptr_t)device_get_match_data(dev);
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0)

From e5aabfbc09ca2037e299e0c2c41235922c39b840 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Thu, 10 Aug 2023 12:39:02 +0200
Subject: [PATCH 0435/1189] rtc: rs5c372: fix Wvoid-pointer-to-enum-cast
 warning

'type' is an enum, thus cast of pointer on 64-bit compile test with W=1
causes:

  rtc-rs5c372.c:829:19: error: cast to smaller integer type 'enum rtc_type' from 'const void *' [-Werror,-Wvoid-pointer-to-enum-cast]

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20230810103902.151145-4-krzysztof.kozlowski@linaro.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-rs5c372.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/rtc/rtc-rs5c372.c b/drivers/rtc/rtc-rs5c372.c
index ecabeef09196..f8fab0205f8c 100644
--- a/drivers/rtc/rtc-rs5c372.c
+++ b/drivers/rtc/rtc-rs5c372.c
@@ -826,8 +826,7 @@ static int rs5c372_probe(struct i2c_client *client)
 	rs5c372->client = client;
 	i2c_set_clientdata(client, rs5c372);
 	if (client->dev.of_node) {
-		rs5c372->type = (enum rtc_type)
-			of_device_get_match_data(&client->dev);
+		rs5c372->type = (uintptr_t)of_device_get_match_data(&client->dev);
 	} else {
 		const struct i2c_device_id *id = i2c_match_id(rs5c372_id, client);
 		rs5c372->type = id->driver_data;

From a1ef3aaf6ada374818ebcf978c175e65a4cd60ab Mon Sep 17 00:00:00 2001
From: Changbin Du <changbin.du@huawei.com>
Date: Tue, 18 Jul 2023 16:52:42 +0800
Subject: [PATCH 0436/1189] perf docs: Fix format of unordered lists

Fix the format of unordered lists so the can wrap properly.

Signed-off-by: Changbin Du <changbin.du@huawei.com>
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230718085242.3090797-1-changbin.du@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-ftrace.txt | 16 +++---
 tools/perf/Documentation/perf-record.txt | 71 +++++++++++++-----------
 2 files changed, 47 insertions(+), 40 deletions(-)

diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt
index df4595563801..d780b93fcf87 100644
--- a/tools/perf/Documentation/perf-ftrace.txt
+++ b/tools/perf/Documentation/perf-ftrace.txt
@@ -96,8 +96,9 @@ OPTIONS for 'perf ftrace trace'
 
 --func-opts::
 	List of options allowed to set:
-	  call-graph - Display kernel stack trace for function tracer.
-	  irq-info   - Display irq context info for function tracer.
+
+	  - call-graph - Display kernel stack trace for function tracer.
+	  - irq-info   - Display irq context info for function tracer.
 
 -G::
 --graph-funcs=::
@@ -118,11 +119,12 @@ OPTIONS for 'perf ftrace trace'
 
 --graph-opts::
 	List of options allowed to set:
-	  nosleep-time - Measure on-CPU time only for function_graph tracer.
-	  noirqs       - Ignore functions that happen inside interrupt.
-	  verbose      - Show process names, PIDs, timestamps, etc.
-	  thresh=<n>   - Setup trace duration threshold in microseconds.
-	  depth=<n>    - Set max depth for function graph tracer to follow.
+
+	  - nosleep-time - Measure on-CPU time only for function_graph tracer.
+	  - noirqs       - Ignore functions that happen inside interrupt.
+	  - verbose      - Show process names, PIDs, timestamps, etc.
+	  - thresh=<n>   - Setup trace duration threshold in microseconds.
+	  - depth=<n>    - Set max depth for function graph tracer to follow.
 
 
 OPTIONS for 'perf ftrace latency'
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 7d362407fb39..d5217be012d7 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -509,9 +509,10 @@ CLOCK_BOOTTIME, CLOCK_REALTIME and CLOCK_TAI.
 Select AUX area tracing Snapshot Mode. This option is valid only with an
 AUX area tracing event. Optionally, certain snapshot capturing parameters
 can be specified in a string that follows this option:
-  'e': take one last snapshot on exit; guarantees that there is at least one
+
+  - 'e': take one last snapshot on exit; guarantees that there is at least one
        snapshot in the output file;
-  <size>: if the PMU supports this, specify the desired snapshot size.
+  - <size>: if the PMU supports this, specify the desired snapshot size.
 
 In Snapshot Mode trace data is captured only when signal SIGUSR2 is received
 and on exit if the above 'e' option is given.
@@ -550,8 +551,9 @@ providing implementation for Posix AIO API.
 
 --affinity=mode::
 Set affinity mask of trace reading thread according to the policy defined by 'mode' value:
-  node - thread affinity mask is set to NUMA node cpu mask of the processed mmap buffer
-  cpu  - thread affinity mask is set to cpu of the processed mmap buffer
+
+  - node - thread affinity mask is set to NUMA node cpu mask of the processed mmap buffer
+  - cpu  - thread affinity mask is set to cpu of the processed mmap buffer
 
 --mmap-flush=number::
 
@@ -603,16 +605,17 @@ Record timestamp boundary (time of first/last samples).
 --switch-output[=mode]::
 Generate multiple perf.data files, timestamp prefixed, switching to a new one
 based on 'mode' value:
-  "signal" - when receiving a SIGUSR2 (default value) or
-  <size>   - when reaching the size threshold, size is expected to
-             be a number with appended unit character - B/K/M/G
-  <time>   - when reaching the time threshold, size is expected to
-             be a number with appended unit character - s/m/h/d
 
-             Note: the precision of  the size  threshold  hugely depends
-             on your configuration  - the number and size of  your  ring
-             buffers (-m). It is generally more precise for higher sizes
-             (like >5M), for lower values expect different sizes.
+  - "signal" - when receiving a SIGUSR2 (default value) or
+  - <size>   - when reaching the size threshold, size is expected to
+               be a number with appended unit character - B/K/M/G
+  - <time>   - when reaching the time threshold, size is expected to
+               be a number with appended unit character - s/m/h/d
+
+               Note: the precision of  the size  threshold  hugely depends
+               on your configuration  - the number and size of  your  ring
+               buffers (-m). It is generally more precise for higher sizes
+               (like >5M), for lower values expect different sizes.
 
 A possible use case is to, given an external event, slice the perf.data file
 that gets then processed, possibly via a perf script, to decide if that
@@ -658,11 +661,12 @@ choice in this option.  For example, --synth=no would have MMAP events for
 kernel and modules.
 
 Available types are:
-  'task'    - synthesize FORK and COMM events for each task
-  'mmap'    - synthesize MMAP events for each process (implies 'task')
-  'cgroup'  - synthesize CGROUP events for each cgroup
-  'all'     - synthesize all events (default)
-  'no'      - do not synthesize any of the above events
+
+  - 'task'    - synthesize FORK and COMM events for each task
+  - 'mmap'    - synthesize MMAP events for each process (implies 'task')
+  - 'cgroup'  - synthesize CGROUP events for each cgroup
+  - 'all'     - synthesize all events (default)
+  - 'no'      - do not synthesize any of the above events
 
 --tail-synthesize::
 Instead of collecting non-sample events (for example, fork, comm, mmap) at
@@ -714,18 +718,19 @@ ctl-fifo / ack-fifo are opened and used as ctl-fd / ack-fd as follows.
 Listen on ctl-fd descriptor for command to control measurement.
 
 Available commands:
-  'enable'           : enable events
-  'disable'          : disable events
-  'enable name'      : enable event 'name'
-  'disable name'     : disable event 'name'
-  'snapshot'         : AUX area tracing snapshot).
-  'stop'             : stop perf record
-  'ping'             : ping
 
-  'evlist [-v|-g|-F] : display all events
-                       -F  Show just the sample frequency used for each event.
-                       -v  Show all fields.
-                       -g  Show event group information.
+  - 'enable'           : enable events
+  - 'disable'          : disable events
+  - 'enable name'      : enable event 'name'
+  - 'disable name'     : disable event 'name'
+  - 'snapshot'         : AUX area tracing snapshot).
+  - 'stop'             : stop perf record
+  - 'ping'             : ping
+  - 'evlist [-v|-g|-F] : display all events
+
+                         -F  Show just the sample frequency used for each event.
+                         -v  Show all fields.
+                         -g  Show event group information.
 
 Measurements can be started with events disabled using --delay=-1 option. Optionally
 send control command completion ('ack\n') to ack-fd descriptor to synchronize with the
@@ -786,10 +791,10 @@ the second monitors CPUs 1 and 5-7 with the affinity mask 5-7.
 <spec> value can also be a string meaning predefined parallel threads
 layout:
 
-    cpu    - create new data streaming thread for every monitored cpu
-    core   - create new thread to monitor CPUs grouped by a core
-    package - create new thread to monitor CPUs grouped by a package
-    numa   - create new threed to monitor CPUs grouped by a NUMA domain
+    - cpu    - create new data streaming thread for every monitored cpu
+    - core   - create new thread to monitor CPUs grouped by a core
+    - package - create new thread to monitor CPUs grouped by a package
+    - numa   - create new threed to monitor CPUs grouped by a NUMA domain
 
 Predefined layouts can be used on systems with large number of CPUs in
 order not to spawn multiple per-cpu streaming threads but still avoid LOST

From 5000e7f61a1eb82fed98d5d0c8f19477033f0914 Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@linaro.org>
Date: Tue, 6 Jun 2023 09:45:54 +0800
Subject: [PATCH 0437/1189] perf parse-regs: Refactor arch register parsing
 functions

Every architecture has a specific register parsing function for
returning register name based on register index, to support cross
analysis (e.g. we use perf x86 binary to parse Arm64's perf data), we
build all these register parsing functions into the tool, this is why
we place all related functions into util/perf_regs.c.

Unfortunately, since util/perf_regs.c needs to include every arch's
perf_regs.h, this easily introduces duplicated definitions coming from
multiple headers, finally it's fragile for building and difficult for
maintenance.

We cannot simply move these register parsing functions into the
corresponding 'arch' folder, the folder is only conditionally built
based on the target architecture.

Therefore, this commit creates a new folder util/perf-regs-arch/ and
uses a dedicated source file to keep every architecture's register
parsing function to avoid definition conflicts.

This is only a refactoring, no functionality change is expected.

Committer notes:

Had to add util/perf-regs-arch/*.c to tools/perf/util/python-ext-sources
to keep 'perf test python' passing.

Signed-off-by: Leo Yan <leo.yan@linaro.org>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Eric Lin <eric.lin@sifive.com>
Cc: Fangrui Song <maskray@google.com>
Cc: Guo Ren <guoren@kernel.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ivan Babrou <ivan@cloudflare.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-csky@vger.kernel.org
Cc: linux-riscv@lists.infradead.org
Link: https://lore.kernel.org/r/20230606014559.21783-2-leo.yan@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/Build                         |   1 +
 tools/perf/util/perf-regs-arch/Build          |   9 +
 .../util/perf-regs-arch/perf_regs_aarch64.c   |  86 +++
 .../perf/util/perf-regs-arch/perf_regs_arm.c  |  50 ++
 .../perf/util/perf-regs-arch/perf_regs_csky.c |  90 +++
 .../util/perf-regs-arch/perf_regs_loongarch.c |  81 ++
 .../perf/util/perf-regs-arch/perf_regs_mips.c |  77 ++
 .../util/perf-regs-arch/perf_regs_powerpc.c   | 135 ++++
 .../util/perf-regs-arch/perf_regs_riscv.c     |  82 ++
 .../perf/util/perf-regs-arch/perf_regs_s390.c |  86 +++
 .../perf/util/perf-regs-arch/perf_regs_x86.c  |  88 +++
 tools/perf/util/perf_regs.c                   | 716 ------------------
 tools/perf/util/perf_regs.h                   |   9 +
 tools/perf/util/python-ext-sources            |   9 +
 14 files changed, 803 insertions(+), 716 deletions(-)
 create mode 100644 tools/perf/util/perf-regs-arch/Build
 create mode 100644 tools/perf/util/perf-regs-arch/perf_regs_aarch64.c
 create mode 100644 tools/perf/util/perf-regs-arch/perf_regs_arm.c
 create mode 100644 tools/perf/util/perf-regs-arch/perf_regs_csky.c
 create mode 100644 tools/perf/util/perf-regs-arch/perf_regs_loongarch.c
 create mode 100644 tools/perf/util/perf-regs-arch/perf_regs_mips.c
 create mode 100644 tools/perf/util/perf-regs-arch/perf_regs_powerpc.c
 create mode 100644 tools/perf/util/perf-regs-arch/perf_regs_riscv.c
 create mode 100644 tools/perf/util/perf-regs-arch/perf_regs_s390.c
 create mode 100644 tools/perf/util/perf-regs-arch/perf_regs_x86.c

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index c6650d3fb066..6d657c9927f7 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -29,6 +29,7 @@ perf-y += parse-events.o
 perf-y += print-events.o
 perf-y += tracepoint.o
 perf-y += perf_regs.o
+perf-y += perf-regs-arch/
 perf-y += path.o
 perf-y += print_binary.o
 perf-y += rlimit.o
diff --git a/tools/perf/util/perf-regs-arch/Build b/tools/perf/util/perf-regs-arch/Build
new file mode 100644
index 000000000000..d9d596d330a7
--- /dev/null
+++ b/tools/perf/util/perf-regs-arch/Build
@@ -0,0 +1,9 @@
+perf-y += perf_regs_aarch64.o
+perf-y += perf_regs_arm.o
+perf-y += perf_regs_csky.o
+perf-y += perf_regs_loongarch.o
+perf-y += perf_regs_mips.o
+perf-y += perf_regs_powerpc.o
+perf-y += perf_regs_riscv.o
+perf-y += perf_regs_s390.o
+perf-y += perf_regs_x86.o
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_aarch64.c b/tools/perf/util/perf-regs-arch/perf_regs_aarch64.c
new file mode 100644
index 000000000000..c02c045af46e
--- /dev/null
+++ b/tools/perf/util/perf-regs-arch/perf_regs_aarch64.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifdef HAVE_PERF_REGS_SUPPORT
+
+#include "../perf_regs.h"
+#include "../../../arch/arm64/include/uapi/asm/perf_regs.h"
+
+const char *__perf_reg_name_arm64(int id)
+{
+	switch (id) {
+	case PERF_REG_ARM64_X0:
+		return "x0";
+	case PERF_REG_ARM64_X1:
+		return "x1";
+	case PERF_REG_ARM64_X2:
+		return "x2";
+	case PERF_REG_ARM64_X3:
+		return "x3";
+	case PERF_REG_ARM64_X4:
+		return "x4";
+	case PERF_REG_ARM64_X5:
+		return "x5";
+	case PERF_REG_ARM64_X6:
+		return "x6";
+	case PERF_REG_ARM64_X7:
+		return "x7";
+	case PERF_REG_ARM64_X8:
+		return "x8";
+	case PERF_REG_ARM64_X9:
+		return "x9";
+	case PERF_REG_ARM64_X10:
+		return "x10";
+	case PERF_REG_ARM64_X11:
+		return "x11";
+	case PERF_REG_ARM64_X12:
+		return "x12";
+	case PERF_REG_ARM64_X13:
+		return "x13";
+	case PERF_REG_ARM64_X14:
+		return "x14";
+	case PERF_REG_ARM64_X15:
+		return "x15";
+	case PERF_REG_ARM64_X16:
+		return "x16";
+	case PERF_REG_ARM64_X17:
+		return "x17";
+	case PERF_REG_ARM64_X18:
+		return "x18";
+	case PERF_REG_ARM64_X19:
+		return "x19";
+	case PERF_REG_ARM64_X20:
+		return "x20";
+	case PERF_REG_ARM64_X21:
+		return "x21";
+	case PERF_REG_ARM64_X22:
+		return "x22";
+	case PERF_REG_ARM64_X23:
+		return "x23";
+	case PERF_REG_ARM64_X24:
+		return "x24";
+	case PERF_REG_ARM64_X25:
+		return "x25";
+	case PERF_REG_ARM64_X26:
+		return "x26";
+	case PERF_REG_ARM64_X27:
+		return "x27";
+	case PERF_REG_ARM64_X28:
+		return "x28";
+	case PERF_REG_ARM64_X29:
+		return "x29";
+	case PERF_REG_ARM64_SP:
+		return "sp";
+	case PERF_REG_ARM64_LR:
+		return "lr";
+	case PERF_REG_ARM64_PC:
+		return "pc";
+	case PERF_REG_ARM64_VG:
+		return "vg";
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+#endif
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_arm.c b/tools/perf/util/perf-regs-arch/perf_regs_arm.c
new file mode 100644
index 000000000000..e8b0fcd72f34
--- /dev/null
+++ b/tools/perf/util/perf-regs-arch/perf_regs_arm.c
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifdef HAVE_PERF_REGS_SUPPORT
+
+#include "../perf_regs.h"
+#include "../../../arch/arm/include/uapi/asm/perf_regs.h"
+
+const char *__perf_reg_name_arm(int id)
+{
+	switch (id) {
+	case PERF_REG_ARM_R0:
+		return "r0";
+	case PERF_REG_ARM_R1:
+		return "r1";
+	case PERF_REG_ARM_R2:
+		return "r2";
+	case PERF_REG_ARM_R3:
+		return "r3";
+	case PERF_REG_ARM_R4:
+		return "r4";
+	case PERF_REG_ARM_R5:
+		return "r5";
+	case PERF_REG_ARM_R6:
+		return "r6";
+	case PERF_REG_ARM_R7:
+		return "r7";
+	case PERF_REG_ARM_R8:
+		return "r8";
+	case PERF_REG_ARM_R9:
+		return "r9";
+	case PERF_REG_ARM_R10:
+		return "r10";
+	case PERF_REG_ARM_FP:
+		return "fp";
+	case PERF_REG_ARM_IP:
+		return "ip";
+	case PERF_REG_ARM_SP:
+		return "sp";
+	case PERF_REG_ARM_LR:
+		return "lr";
+	case PERF_REG_ARM_PC:
+		return "pc";
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+#endif
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_csky.c b/tools/perf/util/perf-regs-arch/perf_regs_csky.c
new file mode 100644
index 000000000000..e343b1cef7ba
--- /dev/null
+++ b/tools/perf/util/perf-regs-arch/perf_regs_csky.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifdef HAVE_PERF_REGS_SUPPORT
+
+#include "../perf_regs.h"
+#include "../../arch/csky/include/uapi/asm/perf_regs.h"
+
+const char *__perf_reg_name_csky(int id)
+{
+	switch (id) {
+	case PERF_REG_CSKY_A0:
+		return "a0";
+	case PERF_REG_CSKY_A1:
+		return "a1";
+	case PERF_REG_CSKY_A2:
+		return "a2";
+	case PERF_REG_CSKY_A3:
+		return "a3";
+	case PERF_REG_CSKY_REGS0:
+		return "regs0";
+	case PERF_REG_CSKY_REGS1:
+		return "regs1";
+	case PERF_REG_CSKY_REGS2:
+		return "regs2";
+	case PERF_REG_CSKY_REGS3:
+		return "regs3";
+	case PERF_REG_CSKY_REGS4:
+		return "regs4";
+	case PERF_REG_CSKY_REGS5:
+		return "regs5";
+	case PERF_REG_CSKY_REGS6:
+		return "regs6";
+	case PERF_REG_CSKY_REGS7:
+		return "regs7";
+	case PERF_REG_CSKY_REGS8:
+		return "regs8";
+	case PERF_REG_CSKY_REGS9:
+		return "regs9";
+	case PERF_REG_CSKY_SP:
+		return "sp";
+	case PERF_REG_CSKY_LR:
+		return "lr";
+	case PERF_REG_CSKY_PC:
+		return "pc";
+#if defined(__CSKYABIV2__)
+	case PERF_REG_CSKY_EXREGS0:
+		return "exregs0";
+	case PERF_REG_CSKY_EXREGS1:
+		return "exregs1";
+	case PERF_REG_CSKY_EXREGS2:
+		return "exregs2";
+	case PERF_REG_CSKY_EXREGS3:
+		return "exregs3";
+	case PERF_REG_CSKY_EXREGS4:
+		return "exregs4";
+	case PERF_REG_CSKY_EXREGS5:
+		return "exregs5";
+	case PERF_REG_CSKY_EXREGS6:
+		return "exregs6";
+	case PERF_REG_CSKY_EXREGS7:
+		return "exregs7";
+	case PERF_REG_CSKY_EXREGS8:
+		return "exregs8";
+	case PERF_REG_CSKY_EXREGS9:
+		return "exregs9";
+	case PERF_REG_CSKY_EXREGS10:
+		return "exregs10";
+	case PERF_REG_CSKY_EXREGS11:
+		return "exregs11";
+	case PERF_REG_CSKY_EXREGS12:
+		return "exregs12";
+	case PERF_REG_CSKY_EXREGS13:
+		return "exregs13";
+	case PERF_REG_CSKY_EXREGS14:
+		return "exregs14";
+	case PERF_REG_CSKY_TLS:
+		return "tls";
+	case PERF_REG_CSKY_HI:
+		return "hi";
+	case PERF_REG_CSKY_LO:
+		return "lo";
+#endif
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+#endif
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_loongarch.c b/tools/perf/util/perf-regs-arch/perf_regs_loongarch.c
new file mode 100644
index 000000000000..6f937464067b
--- /dev/null
+++ b/tools/perf/util/perf-regs-arch/perf_regs_loongarch.c
@@ -0,0 +1,81 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifdef HAVE_PERF_REGS_SUPPORT
+
+#include "../perf_regs.h"
+#include "../../../arch/loongarch/include/uapi/asm/perf_regs.h"
+
+const char *__perf_reg_name_loongarch(int id)
+{
+	switch (id) {
+	case PERF_REG_LOONGARCH_PC:
+		return "PC";
+	case PERF_REG_LOONGARCH_R1:
+		return "%r1";
+	case PERF_REG_LOONGARCH_R2:
+		return "%r2";
+	case PERF_REG_LOONGARCH_R3:
+		return "%r3";
+	case PERF_REG_LOONGARCH_R4:
+		return "%r4";
+	case PERF_REG_LOONGARCH_R5:
+		return "%r5";
+	case PERF_REG_LOONGARCH_R6:
+		return "%r6";
+	case PERF_REG_LOONGARCH_R7:
+		return "%r7";
+	case PERF_REG_LOONGARCH_R8:
+		return "%r8";
+	case PERF_REG_LOONGARCH_R9:
+		return "%r9";
+	case PERF_REG_LOONGARCH_R10:
+		return "%r10";
+	case PERF_REG_LOONGARCH_R11:
+		return "%r11";
+	case PERF_REG_LOONGARCH_R12:
+		return "%r12";
+	case PERF_REG_LOONGARCH_R13:
+		return "%r13";
+	case PERF_REG_LOONGARCH_R14:
+		return "%r14";
+	case PERF_REG_LOONGARCH_R15:
+		return "%r15";
+	case PERF_REG_LOONGARCH_R16:
+		return "%r16";
+	case PERF_REG_LOONGARCH_R17:
+		return "%r17";
+	case PERF_REG_LOONGARCH_R18:
+		return "%r18";
+	case PERF_REG_LOONGARCH_R19:
+		return "%r19";
+	case PERF_REG_LOONGARCH_R20:
+		return "%r20";
+	case PERF_REG_LOONGARCH_R21:
+		return "%r21";
+	case PERF_REG_LOONGARCH_R22:
+		return "%r22";
+	case PERF_REG_LOONGARCH_R23:
+		return "%r23";
+	case PERF_REG_LOONGARCH_R24:
+		return "%r24";
+	case PERF_REG_LOONGARCH_R25:
+		return "%r25";
+	case PERF_REG_LOONGARCH_R26:
+		return "%r26";
+	case PERF_REG_LOONGARCH_R27:
+		return "%r27";
+	case PERF_REG_LOONGARCH_R28:
+		return "%r28";
+	case PERF_REG_LOONGARCH_R29:
+		return "%r29";
+	case PERF_REG_LOONGARCH_R30:
+		return "%r30";
+	case PERF_REG_LOONGARCH_R31:
+		return "%r31";
+	default:
+		break;
+	}
+	return NULL;
+}
+
+#endif
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_mips.c b/tools/perf/util/perf-regs-arch/perf_regs_mips.c
new file mode 100644
index 000000000000..f48fbca2f947
--- /dev/null
+++ b/tools/perf/util/perf-regs-arch/perf_regs_mips.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifdef HAVE_PERF_REGS_SUPPORT
+
+#include "../perf_regs.h"
+#include "../../../arch/mips/include/uapi/asm/perf_regs.h"
+
+const char *__perf_reg_name_mips(int id)
+{
+	switch (id) {
+	case PERF_REG_MIPS_PC:
+		return "PC";
+	case PERF_REG_MIPS_R1:
+		return "$1";
+	case PERF_REG_MIPS_R2:
+		return "$2";
+	case PERF_REG_MIPS_R3:
+		return "$3";
+	case PERF_REG_MIPS_R4:
+		return "$4";
+	case PERF_REG_MIPS_R5:
+		return "$5";
+	case PERF_REG_MIPS_R6:
+		return "$6";
+	case PERF_REG_MIPS_R7:
+		return "$7";
+	case PERF_REG_MIPS_R8:
+		return "$8";
+	case PERF_REG_MIPS_R9:
+		return "$9";
+	case PERF_REG_MIPS_R10:
+		return "$10";
+	case PERF_REG_MIPS_R11:
+		return "$11";
+	case PERF_REG_MIPS_R12:
+		return "$12";
+	case PERF_REG_MIPS_R13:
+		return "$13";
+	case PERF_REG_MIPS_R14:
+		return "$14";
+	case PERF_REG_MIPS_R15:
+		return "$15";
+	case PERF_REG_MIPS_R16:
+		return "$16";
+	case PERF_REG_MIPS_R17:
+		return "$17";
+	case PERF_REG_MIPS_R18:
+		return "$18";
+	case PERF_REG_MIPS_R19:
+		return "$19";
+	case PERF_REG_MIPS_R20:
+		return "$20";
+	case PERF_REG_MIPS_R21:
+		return "$21";
+	case PERF_REG_MIPS_R22:
+		return "$22";
+	case PERF_REG_MIPS_R23:
+		return "$23";
+	case PERF_REG_MIPS_R24:
+		return "$24";
+	case PERF_REG_MIPS_R25:
+		return "$25";
+	case PERF_REG_MIPS_R28:
+		return "$28";
+	case PERF_REG_MIPS_R29:
+		return "$29";
+	case PERF_REG_MIPS_R30:
+		return "$30";
+	case PERF_REG_MIPS_R31:
+		return "$31";
+	default:
+		break;
+	}
+	return NULL;
+}
+
+#endif
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_powerpc.c b/tools/perf/util/perf-regs-arch/perf_regs_powerpc.c
new file mode 100644
index 000000000000..dda1b4b169fc
--- /dev/null
+++ b/tools/perf/util/perf-regs-arch/perf_regs_powerpc.c
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifdef HAVE_PERF_REGS_SUPPORT
+
+#include "../perf_regs.h"
+#include "../../../arch/powerpc/include/uapi/asm/perf_regs.h"
+
+const char *__perf_reg_name_powerpc(int id)
+{
+	switch (id) {
+	case PERF_REG_POWERPC_R0:
+		return "r0";
+	case PERF_REG_POWERPC_R1:
+		return "r1";
+	case PERF_REG_POWERPC_R2:
+		return "r2";
+	case PERF_REG_POWERPC_R3:
+		return "r3";
+	case PERF_REG_POWERPC_R4:
+		return "r4";
+	case PERF_REG_POWERPC_R5:
+		return "r5";
+	case PERF_REG_POWERPC_R6:
+		return "r6";
+	case PERF_REG_POWERPC_R7:
+		return "r7";
+	case PERF_REG_POWERPC_R8:
+		return "r8";
+	case PERF_REG_POWERPC_R9:
+		return "r9";
+	case PERF_REG_POWERPC_R10:
+		return "r10";
+	case PERF_REG_POWERPC_R11:
+		return "r11";
+	case PERF_REG_POWERPC_R12:
+		return "r12";
+	case PERF_REG_POWERPC_R13:
+		return "r13";
+	case PERF_REG_POWERPC_R14:
+		return "r14";
+	case PERF_REG_POWERPC_R15:
+		return "r15";
+	case PERF_REG_POWERPC_R16:
+		return "r16";
+	case PERF_REG_POWERPC_R17:
+		return "r17";
+	case PERF_REG_POWERPC_R18:
+		return "r18";
+	case PERF_REG_POWERPC_R19:
+		return "r19";
+	case PERF_REG_POWERPC_R20:
+		return "r20";
+	case PERF_REG_POWERPC_R21:
+		return "r21";
+	case PERF_REG_POWERPC_R22:
+		return "r22";
+	case PERF_REG_POWERPC_R23:
+		return "r23";
+	case PERF_REG_POWERPC_R24:
+		return "r24";
+	case PERF_REG_POWERPC_R25:
+		return "r25";
+	case PERF_REG_POWERPC_R26:
+		return "r26";
+	case PERF_REG_POWERPC_R27:
+		return "r27";
+	case PERF_REG_POWERPC_R28:
+		return "r28";
+	case PERF_REG_POWERPC_R29:
+		return "r29";
+	case PERF_REG_POWERPC_R30:
+		return "r30";
+	case PERF_REG_POWERPC_R31:
+		return "r31";
+	case PERF_REG_POWERPC_NIP:
+		return "nip";
+	case PERF_REG_POWERPC_MSR:
+		return "msr";
+	case PERF_REG_POWERPC_ORIG_R3:
+		return "orig_r3";
+	case PERF_REG_POWERPC_CTR:
+		return "ctr";
+	case PERF_REG_POWERPC_LINK:
+		return "link";
+	case PERF_REG_POWERPC_XER:
+		return "xer";
+	case PERF_REG_POWERPC_CCR:
+		return "ccr";
+	case PERF_REG_POWERPC_SOFTE:
+		return "softe";
+	case PERF_REG_POWERPC_TRAP:
+		return "trap";
+	case PERF_REG_POWERPC_DAR:
+		return "dar";
+	case PERF_REG_POWERPC_DSISR:
+		return "dsisr";
+	case PERF_REG_POWERPC_SIER:
+		return "sier";
+	case PERF_REG_POWERPC_MMCRA:
+		return "mmcra";
+	case PERF_REG_POWERPC_MMCR0:
+		return "mmcr0";
+	case PERF_REG_POWERPC_MMCR1:
+		return "mmcr1";
+	case PERF_REG_POWERPC_MMCR2:
+		return "mmcr2";
+	case PERF_REG_POWERPC_MMCR3:
+		return "mmcr3";
+	case PERF_REG_POWERPC_SIER2:
+		return "sier2";
+	case PERF_REG_POWERPC_SIER3:
+		return "sier3";
+	case PERF_REG_POWERPC_PMC1:
+		return "pmc1";
+	case PERF_REG_POWERPC_PMC2:
+		return "pmc2";
+	case PERF_REG_POWERPC_PMC3:
+		return "pmc3";
+	case PERF_REG_POWERPC_PMC4:
+		return "pmc4";
+	case PERF_REG_POWERPC_PMC5:
+		return "pmc5";
+	case PERF_REG_POWERPC_PMC6:
+		return "pmc6";
+	case PERF_REG_POWERPC_SDAR:
+		return "sdar";
+	case PERF_REG_POWERPC_SIAR:
+		return "siar";
+	default:
+		break;
+	}
+	return NULL;
+}
+
+#endif
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_riscv.c b/tools/perf/util/perf-regs-arch/perf_regs_riscv.c
new file mode 100644
index 000000000000..c504b047cac2
--- /dev/null
+++ b/tools/perf/util/perf-regs-arch/perf_regs_riscv.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifdef HAVE_PERF_REGS_SUPPORT
+
+#include "../perf_regs.h"
+#include "../../../arch/riscv/include/uapi/asm/perf_regs.h"
+
+const char *__perf_reg_name_riscv(int id)
+{
+	switch (id) {
+	case PERF_REG_RISCV_PC:
+		return "pc";
+	case PERF_REG_RISCV_RA:
+		return "ra";
+	case PERF_REG_RISCV_SP:
+		return "sp";
+	case PERF_REG_RISCV_GP:
+		return "gp";
+	case PERF_REG_RISCV_TP:
+		return "tp";
+	case PERF_REG_RISCV_T0:
+		return "t0";
+	case PERF_REG_RISCV_T1:
+		return "t1";
+	case PERF_REG_RISCV_T2:
+		return "t2";
+	case PERF_REG_RISCV_S0:
+		return "s0";
+	case PERF_REG_RISCV_S1:
+		return "s1";
+	case PERF_REG_RISCV_A0:
+		return "a0";
+	case PERF_REG_RISCV_A1:
+		return "a1";
+	case PERF_REG_RISCV_A2:
+		return "a2";
+	case PERF_REG_RISCV_A3:
+		return "a3";
+	case PERF_REG_RISCV_A4:
+		return "a4";
+	case PERF_REG_RISCV_A5:
+		return "a5";
+	case PERF_REG_RISCV_A6:
+		return "a6";
+	case PERF_REG_RISCV_A7:
+		return "a7";
+	case PERF_REG_RISCV_S2:
+		return "s2";
+	case PERF_REG_RISCV_S3:
+		return "s3";
+	case PERF_REG_RISCV_S4:
+		return "s4";
+	case PERF_REG_RISCV_S5:
+		return "s5";
+	case PERF_REG_RISCV_S6:
+		return "s6";
+	case PERF_REG_RISCV_S7:
+		return "s7";
+	case PERF_REG_RISCV_S8:
+		return "s8";
+	case PERF_REG_RISCV_S9:
+		return "s9";
+	case PERF_REG_RISCV_S10:
+		return "s10";
+	case PERF_REG_RISCV_S11:
+		return "s11";
+	case PERF_REG_RISCV_T3:
+		return "t3";
+	case PERF_REG_RISCV_T4:
+		return "t4";
+	case PERF_REG_RISCV_T5:
+		return "t5";
+	case PERF_REG_RISCV_T6:
+		return "t6";
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+#endif
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_s390.c b/tools/perf/util/perf-regs-arch/perf_regs_s390.c
new file mode 100644
index 000000000000..e71e2302394c
--- /dev/null
+++ b/tools/perf/util/perf-regs-arch/perf_regs_s390.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifdef HAVE_PERF_REGS_SUPPORT
+
+#include "../perf_regs.h"
+#include "../../../arch/s390/include/uapi/asm/perf_regs.h"
+
+const char *__perf_reg_name_s390(int id)
+{
+	switch (id) {
+	case PERF_REG_S390_R0:
+		return "R0";
+	case PERF_REG_S390_R1:
+		return "R1";
+	case PERF_REG_S390_R2:
+		return "R2";
+	case PERF_REG_S390_R3:
+		return "R3";
+	case PERF_REG_S390_R4:
+		return "R4";
+	case PERF_REG_S390_R5:
+		return "R5";
+	case PERF_REG_S390_R6:
+		return "R6";
+	case PERF_REG_S390_R7:
+		return "R7";
+	case PERF_REG_S390_R8:
+		return "R8";
+	case PERF_REG_S390_R9:
+		return "R9";
+	case PERF_REG_S390_R10:
+		return "R10";
+	case PERF_REG_S390_R11:
+		return "R11";
+	case PERF_REG_S390_R12:
+		return "R12";
+	case PERF_REG_S390_R13:
+		return "R13";
+	case PERF_REG_S390_R14:
+		return "R14";
+	case PERF_REG_S390_R15:
+		return "R15";
+	case PERF_REG_S390_FP0:
+		return "FP0";
+	case PERF_REG_S390_FP1:
+		return "FP1";
+	case PERF_REG_S390_FP2:
+		return "FP2";
+	case PERF_REG_S390_FP3:
+		return "FP3";
+	case PERF_REG_S390_FP4:
+		return "FP4";
+	case PERF_REG_S390_FP5:
+		return "FP5";
+	case PERF_REG_S390_FP6:
+		return "FP6";
+	case PERF_REG_S390_FP7:
+		return "FP7";
+	case PERF_REG_S390_FP8:
+		return "FP8";
+	case PERF_REG_S390_FP9:
+		return "FP9";
+	case PERF_REG_S390_FP10:
+		return "FP10";
+	case PERF_REG_S390_FP11:
+		return "FP11";
+	case PERF_REG_S390_FP12:
+		return "FP12";
+	case PERF_REG_S390_FP13:
+		return "FP13";
+	case PERF_REG_S390_FP14:
+		return "FP14";
+	case PERF_REG_S390_FP15:
+		return "FP15";
+	case PERF_REG_S390_MASK:
+		return "MASK";
+	case PERF_REG_S390_PC:
+		return "PC";
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+#endif
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_x86.c b/tools/perf/util/perf-regs-arch/perf_regs_x86.c
new file mode 100644
index 000000000000..eb5d249afa70
--- /dev/null
+++ b/tools/perf/util/perf-regs-arch/perf_regs_x86.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifdef HAVE_PERF_REGS_SUPPORT
+
+#include "../perf_regs.h"
+#include "../../../arch/x86/include/uapi/asm/perf_regs.h"
+
+const char *__perf_reg_name_x86(int id)
+{
+	switch (id) {
+	case PERF_REG_X86_AX:
+		return "AX";
+	case PERF_REG_X86_BX:
+		return "BX";
+	case PERF_REG_X86_CX:
+		return "CX";
+	case PERF_REG_X86_DX:
+		return "DX";
+	case PERF_REG_X86_SI:
+		return "SI";
+	case PERF_REG_X86_DI:
+		return "DI";
+	case PERF_REG_X86_BP:
+		return "BP";
+	case PERF_REG_X86_SP:
+		return "SP";
+	case PERF_REG_X86_IP:
+		return "IP";
+	case PERF_REG_X86_FLAGS:
+		return "FLAGS";
+	case PERF_REG_X86_CS:
+		return "CS";
+	case PERF_REG_X86_SS:
+		return "SS";
+	case PERF_REG_X86_DS:
+		return "DS";
+	case PERF_REG_X86_ES:
+		return "ES";
+	case PERF_REG_X86_FS:
+		return "FS";
+	case PERF_REG_X86_GS:
+		return "GS";
+	case PERF_REG_X86_R8:
+		return "R8";
+	case PERF_REG_X86_R9:
+		return "R9";
+	case PERF_REG_X86_R10:
+		return "R10";
+	case PERF_REG_X86_R11:
+		return "R11";
+	case PERF_REG_X86_R12:
+		return "R12";
+	case PERF_REG_X86_R13:
+		return "R13";
+	case PERF_REG_X86_R14:
+		return "R14";
+	case PERF_REG_X86_R15:
+		return "R15";
+
+#define XMM(x) \
+	case PERF_REG_X86_XMM ## x:	\
+	case PERF_REG_X86_XMM ## x + 1:	\
+		return "XMM" #x;
+	XMM(0)
+	XMM(1)
+	XMM(2)
+	XMM(3)
+	XMM(4)
+	XMM(5)
+	XMM(6)
+	XMM(7)
+	XMM(8)
+	XMM(9)
+	XMM(10)
+	XMM(11)
+	XMM(12)
+	XMM(13)
+	XMM(14)
+	XMM(15)
+#undef XMM
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+#endif
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
index 9bdbaa37f813..5af1b95c3d01 100644
--- a/tools/perf/util/perf_regs.c
+++ b/tools/perf/util/perf_regs.c
@@ -22,722 +22,6 @@ uint64_t __weak arch__user_reg_mask(void)
 
 #ifdef HAVE_PERF_REGS_SUPPORT
 
-#define perf_event_arm_regs perf_event_arm64_regs
-#include "../../arch/arm64/include/uapi/asm/perf_regs.h"
-#undef perf_event_arm_regs
-
-#include "../../arch/arm/include/uapi/asm/perf_regs.h"
-#include "../../arch/csky/include/uapi/asm/perf_regs.h"
-#include "../../arch/loongarch/include/uapi/asm/perf_regs.h"
-#include "../../arch/mips/include/uapi/asm/perf_regs.h"
-#include "../../arch/powerpc/include/uapi/asm/perf_regs.h"
-#include "../../arch/riscv/include/uapi/asm/perf_regs.h"
-#include "../../arch/s390/include/uapi/asm/perf_regs.h"
-#include "../../arch/x86/include/uapi/asm/perf_regs.h"
-
-static const char *__perf_reg_name_arm64(int id)
-{
-	switch (id) {
-	case PERF_REG_ARM64_X0:
-		return "x0";
-	case PERF_REG_ARM64_X1:
-		return "x1";
-	case PERF_REG_ARM64_X2:
-		return "x2";
-	case PERF_REG_ARM64_X3:
-		return "x3";
-	case PERF_REG_ARM64_X4:
-		return "x4";
-	case PERF_REG_ARM64_X5:
-		return "x5";
-	case PERF_REG_ARM64_X6:
-		return "x6";
-	case PERF_REG_ARM64_X7:
-		return "x7";
-	case PERF_REG_ARM64_X8:
-		return "x8";
-	case PERF_REG_ARM64_X9:
-		return "x9";
-	case PERF_REG_ARM64_X10:
-		return "x10";
-	case PERF_REG_ARM64_X11:
-		return "x11";
-	case PERF_REG_ARM64_X12:
-		return "x12";
-	case PERF_REG_ARM64_X13:
-		return "x13";
-	case PERF_REG_ARM64_X14:
-		return "x14";
-	case PERF_REG_ARM64_X15:
-		return "x15";
-	case PERF_REG_ARM64_X16:
-		return "x16";
-	case PERF_REG_ARM64_X17:
-		return "x17";
-	case PERF_REG_ARM64_X18:
-		return "x18";
-	case PERF_REG_ARM64_X19:
-		return "x19";
-	case PERF_REG_ARM64_X20:
-		return "x20";
-	case PERF_REG_ARM64_X21:
-		return "x21";
-	case PERF_REG_ARM64_X22:
-		return "x22";
-	case PERF_REG_ARM64_X23:
-		return "x23";
-	case PERF_REG_ARM64_X24:
-		return "x24";
-	case PERF_REG_ARM64_X25:
-		return "x25";
-	case PERF_REG_ARM64_X26:
-		return "x26";
-	case PERF_REG_ARM64_X27:
-		return "x27";
-	case PERF_REG_ARM64_X28:
-		return "x28";
-	case PERF_REG_ARM64_X29:
-		return "x29";
-	case PERF_REG_ARM64_SP:
-		return "sp";
-	case PERF_REG_ARM64_LR:
-		return "lr";
-	case PERF_REG_ARM64_PC:
-		return "pc";
-	case PERF_REG_ARM64_VG:
-		return "vg";
-	default:
-		return NULL;
-	}
-
-	return NULL;
-}
-
-static const char *__perf_reg_name_arm(int id)
-{
-	switch (id) {
-	case PERF_REG_ARM_R0:
-		return "r0";
-	case PERF_REG_ARM_R1:
-		return "r1";
-	case PERF_REG_ARM_R2:
-		return "r2";
-	case PERF_REG_ARM_R3:
-		return "r3";
-	case PERF_REG_ARM_R4:
-		return "r4";
-	case PERF_REG_ARM_R5:
-		return "r5";
-	case PERF_REG_ARM_R6:
-		return "r6";
-	case PERF_REG_ARM_R7:
-		return "r7";
-	case PERF_REG_ARM_R8:
-		return "r8";
-	case PERF_REG_ARM_R9:
-		return "r9";
-	case PERF_REG_ARM_R10:
-		return "r10";
-	case PERF_REG_ARM_FP:
-		return "fp";
-	case PERF_REG_ARM_IP:
-		return "ip";
-	case PERF_REG_ARM_SP:
-		return "sp";
-	case PERF_REG_ARM_LR:
-		return "lr";
-	case PERF_REG_ARM_PC:
-		return "pc";
-	default:
-		return NULL;
-	}
-
-	return NULL;
-}
-
-static const char *__perf_reg_name_csky(int id)
-{
-	switch (id) {
-	case PERF_REG_CSKY_A0:
-		return "a0";
-	case PERF_REG_CSKY_A1:
-		return "a1";
-	case PERF_REG_CSKY_A2:
-		return "a2";
-	case PERF_REG_CSKY_A3:
-		return "a3";
-	case PERF_REG_CSKY_REGS0:
-		return "regs0";
-	case PERF_REG_CSKY_REGS1:
-		return "regs1";
-	case PERF_REG_CSKY_REGS2:
-		return "regs2";
-	case PERF_REG_CSKY_REGS3:
-		return "regs3";
-	case PERF_REG_CSKY_REGS4:
-		return "regs4";
-	case PERF_REG_CSKY_REGS5:
-		return "regs5";
-	case PERF_REG_CSKY_REGS6:
-		return "regs6";
-	case PERF_REG_CSKY_REGS7:
-		return "regs7";
-	case PERF_REG_CSKY_REGS8:
-		return "regs8";
-	case PERF_REG_CSKY_REGS9:
-		return "regs9";
-	case PERF_REG_CSKY_SP:
-		return "sp";
-	case PERF_REG_CSKY_LR:
-		return "lr";
-	case PERF_REG_CSKY_PC:
-		return "pc";
-#if defined(__CSKYABIV2__)
-	case PERF_REG_CSKY_EXREGS0:
-		return "exregs0";
-	case PERF_REG_CSKY_EXREGS1:
-		return "exregs1";
-	case PERF_REG_CSKY_EXREGS2:
-		return "exregs2";
-	case PERF_REG_CSKY_EXREGS3:
-		return "exregs3";
-	case PERF_REG_CSKY_EXREGS4:
-		return "exregs4";
-	case PERF_REG_CSKY_EXREGS5:
-		return "exregs5";
-	case PERF_REG_CSKY_EXREGS6:
-		return "exregs6";
-	case PERF_REG_CSKY_EXREGS7:
-		return "exregs7";
-	case PERF_REG_CSKY_EXREGS8:
-		return "exregs8";
-	case PERF_REG_CSKY_EXREGS9:
-		return "exregs9";
-	case PERF_REG_CSKY_EXREGS10:
-		return "exregs10";
-	case PERF_REG_CSKY_EXREGS11:
-		return "exregs11";
-	case PERF_REG_CSKY_EXREGS12:
-		return "exregs12";
-	case PERF_REG_CSKY_EXREGS13:
-		return "exregs13";
-	case PERF_REG_CSKY_EXREGS14:
-		return "exregs14";
-	case PERF_REG_CSKY_TLS:
-		return "tls";
-	case PERF_REG_CSKY_HI:
-		return "hi";
-	case PERF_REG_CSKY_LO:
-		return "lo";
-#endif
-	default:
-		return NULL;
-	}
-
-	return NULL;
-}
-
-static inline const char *__perf_reg_name_loongarch(int id)
-{
-	switch (id) {
-	case PERF_REG_LOONGARCH_PC:
-		return "PC";
-	case PERF_REG_LOONGARCH_R1:
-		return "%r1";
-	case PERF_REG_LOONGARCH_R2:
-		return "%r2";
-	case PERF_REG_LOONGARCH_R3:
-		return "%r3";
-	case PERF_REG_LOONGARCH_R4:
-		return "%r4";
-	case PERF_REG_LOONGARCH_R5:
-		return "%r5";
-	case PERF_REG_LOONGARCH_R6:
-		return "%r6";
-	case PERF_REG_LOONGARCH_R7:
-		return "%r7";
-	case PERF_REG_LOONGARCH_R8:
-		return "%r8";
-	case PERF_REG_LOONGARCH_R9:
-		return "%r9";
-	case PERF_REG_LOONGARCH_R10:
-		return "%r10";
-	case PERF_REG_LOONGARCH_R11:
-		return "%r11";
-	case PERF_REG_LOONGARCH_R12:
-		return "%r12";
-	case PERF_REG_LOONGARCH_R13:
-		return "%r13";
-	case PERF_REG_LOONGARCH_R14:
-		return "%r14";
-	case PERF_REG_LOONGARCH_R15:
-		return "%r15";
-	case PERF_REG_LOONGARCH_R16:
-		return "%r16";
-	case PERF_REG_LOONGARCH_R17:
-		return "%r17";
-	case PERF_REG_LOONGARCH_R18:
-		return "%r18";
-	case PERF_REG_LOONGARCH_R19:
-		return "%r19";
-	case PERF_REG_LOONGARCH_R20:
-		return "%r20";
-	case PERF_REG_LOONGARCH_R21:
-		return "%r21";
-	case PERF_REG_LOONGARCH_R22:
-		return "%r22";
-	case PERF_REG_LOONGARCH_R23:
-		return "%r23";
-	case PERF_REG_LOONGARCH_R24:
-		return "%r24";
-	case PERF_REG_LOONGARCH_R25:
-		return "%r25";
-	case PERF_REG_LOONGARCH_R26:
-		return "%r26";
-	case PERF_REG_LOONGARCH_R27:
-		return "%r27";
-	case PERF_REG_LOONGARCH_R28:
-		return "%r28";
-	case PERF_REG_LOONGARCH_R29:
-		return "%r29";
-	case PERF_REG_LOONGARCH_R30:
-		return "%r30";
-	case PERF_REG_LOONGARCH_R31:
-		return "%r31";
-	default:
-		break;
-	}
-	return NULL;
-}
-
-static const char *__perf_reg_name_mips(int id)
-{
-	switch (id) {
-	case PERF_REG_MIPS_PC:
-		return "PC";
-	case PERF_REG_MIPS_R1:
-		return "$1";
-	case PERF_REG_MIPS_R2:
-		return "$2";
-	case PERF_REG_MIPS_R3:
-		return "$3";
-	case PERF_REG_MIPS_R4:
-		return "$4";
-	case PERF_REG_MIPS_R5:
-		return "$5";
-	case PERF_REG_MIPS_R6:
-		return "$6";
-	case PERF_REG_MIPS_R7:
-		return "$7";
-	case PERF_REG_MIPS_R8:
-		return "$8";
-	case PERF_REG_MIPS_R9:
-		return "$9";
-	case PERF_REG_MIPS_R10:
-		return "$10";
-	case PERF_REG_MIPS_R11:
-		return "$11";
-	case PERF_REG_MIPS_R12:
-		return "$12";
-	case PERF_REG_MIPS_R13:
-		return "$13";
-	case PERF_REG_MIPS_R14:
-		return "$14";
-	case PERF_REG_MIPS_R15:
-		return "$15";
-	case PERF_REG_MIPS_R16:
-		return "$16";
-	case PERF_REG_MIPS_R17:
-		return "$17";
-	case PERF_REG_MIPS_R18:
-		return "$18";
-	case PERF_REG_MIPS_R19:
-		return "$19";
-	case PERF_REG_MIPS_R20:
-		return "$20";
-	case PERF_REG_MIPS_R21:
-		return "$21";
-	case PERF_REG_MIPS_R22:
-		return "$22";
-	case PERF_REG_MIPS_R23:
-		return "$23";
-	case PERF_REG_MIPS_R24:
-		return "$24";
-	case PERF_REG_MIPS_R25:
-		return "$25";
-	case PERF_REG_MIPS_R28:
-		return "$28";
-	case PERF_REG_MIPS_R29:
-		return "$29";
-	case PERF_REG_MIPS_R30:
-		return "$30";
-	case PERF_REG_MIPS_R31:
-		return "$31";
-	default:
-		break;
-	}
-	return NULL;
-}
-
-static const char *__perf_reg_name_powerpc(int id)
-{
-	switch (id) {
-	case PERF_REG_POWERPC_R0:
-		return "r0";
-	case PERF_REG_POWERPC_R1:
-		return "r1";
-	case PERF_REG_POWERPC_R2:
-		return "r2";
-	case PERF_REG_POWERPC_R3:
-		return "r3";
-	case PERF_REG_POWERPC_R4:
-		return "r4";
-	case PERF_REG_POWERPC_R5:
-		return "r5";
-	case PERF_REG_POWERPC_R6:
-		return "r6";
-	case PERF_REG_POWERPC_R7:
-		return "r7";
-	case PERF_REG_POWERPC_R8:
-		return "r8";
-	case PERF_REG_POWERPC_R9:
-		return "r9";
-	case PERF_REG_POWERPC_R10:
-		return "r10";
-	case PERF_REG_POWERPC_R11:
-		return "r11";
-	case PERF_REG_POWERPC_R12:
-		return "r12";
-	case PERF_REG_POWERPC_R13:
-		return "r13";
-	case PERF_REG_POWERPC_R14:
-		return "r14";
-	case PERF_REG_POWERPC_R15:
-		return "r15";
-	case PERF_REG_POWERPC_R16:
-		return "r16";
-	case PERF_REG_POWERPC_R17:
-		return "r17";
-	case PERF_REG_POWERPC_R18:
-		return "r18";
-	case PERF_REG_POWERPC_R19:
-		return "r19";
-	case PERF_REG_POWERPC_R20:
-		return "r20";
-	case PERF_REG_POWERPC_R21:
-		return "r21";
-	case PERF_REG_POWERPC_R22:
-		return "r22";
-	case PERF_REG_POWERPC_R23:
-		return "r23";
-	case PERF_REG_POWERPC_R24:
-		return "r24";
-	case PERF_REG_POWERPC_R25:
-		return "r25";
-	case PERF_REG_POWERPC_R26:
-		return "r26";
-	case PERF_REG_POWERPC_R27:
-		return "r27";
-	case PERF_REG_POWERPC_R28:
-		return "r28";
-	case PERF_REG_POWERPC_R29:
-		return "r29";
-	case PERF_REG_POWERPC_R30:
-		return "r30";
-	case PERF_REG_POWERPC_R31:
-		return "r31";
-	case PERF_REG_POWERPC_NIP:
-		return "nip";
-	case PERF_REG_POWERPC_MSR:
-		return "msr";
-	case PERF_REG_POWERPC_ORIG_R3:
-		return "orig_r3";
-	case PERF_REG_POWERPC_CTR:
-		return "ctr";
-	case PERF_REG_POWERPC_LINK:
-		return "link";
-	case PERF_REG_POWERPC_XER:
-		return "xer";
-	case PERF_REG_POWERPC_CCR:
-		return "ccr";
-	case PERF_REG_POWERPC_SOFTE:
-		return "softe";
-	case PERF_REG_POWERPC_TRAP:
-		return "trap";
-	case PERF_REG_POWERPC_DAR:
-		return "dar";
-	case PERF_REG_POWERPC_DSISR:
-		return "dsisr";
-	case PERF_REG_POWERPC_SIER:
-		return "sier";
-	case PERF_REG_POWERPC_MMCRA:
-		return "mmcra";
-	case PERF_REG_POWERPC_MMCR0:
-		return "mmcr0";
-	case PERF_REG_POWERPC_MMCR1:
-		return "mmcr1";
-	case PERF_REG_POWERPC_MMCR2:
-		return "mmcr2";
-	case PERF_REG_POWERPC_MMCR3:
-		return "mmcr3";
-	case PERF_REG_POWERPC_SIER2:
-		return "sier2";
-	case PERF_REG_POWERPC_SIER3:
-		return "sier3";
-	case PERF_REG_POWERPC_PMC1:
-		return "pmc1";
-	case PERF_REG_POWERPC_PMC2:
-		return "pmc2";
-	case PERF_REG_POWERPC_PMC3:
-		return "pmc3";
-	case PERF_REG_POWERPC_PMC4:
-		return "pmc4";
-	case PERF_REG_POWERPC_PMC5:
-		return "pmc5";
-	case PERF_REG_POWERPC_PMC6:
-		return "pmc6";
-	case PERF_REG_POWERPC_SDAR:
-		return "sdar";
-	case PERF_REG_POWERPC_SIAR:
-		return "siar";
-	default:
-		break;
-	}
-	return NULL;
-}
-
-static const char *__perf_reg_name_riscv(int id)
-{
-	switch (id) {
-	case PERF_REG_RISCV_PC:
-		return "pc";
-	case PERF_REG_RISCV_RA:
-		return "ra";
-	case PERF_REG_RISCV_SP:
-		return "sp";
-	case PERF_REG_RISCV_GP:
-		return "gp";
-	case PERF_REG_RISCV_TP:
-		return "tp";
-	case PERF_REG_RISCV_T0:
-		return "t0";
-	case PERF_REG_RISCV_T1:
-		return "t1";
-	case PERF_REG_RISCV_T2:
-		return "t2";
-	case PERF_REG_RISCV_S0:
-		return "s0";
-	case PERF_REG_RISCV_S1:
-		return "s1";
-	case PERF_REG_RISCV_A0:
-		return "a0";
-	case PERF_REG_RISCV_A1:
-		return "a1";
-	case PERF_REG_RISCV_A2:
-		return "a2";
-	case PERF_REG_RISCV_A3:
-		return "a3";
-	case PERF_REG_RISCV_A4:
-		return "a4";
-	case PERF_REG_RISCV_A5:
-		return "a5";
-	case PERF_REG_RISCV_A6:
-		return "a6";
-	case PERF_REG_RISCV_A7:
-		return "a7";
-	case PERF_REG_RISCV_S2:
-		return "s2";
-	case PERF_REG_RISCV_S3:
-		return "s3";
-	case PERF_REG_RISCV_S4:
-		return "s4";
-	case PERF_REG_RISCV_S5:
-		return "s5";
-	case PERF_REG_RISCV_S6:
-		return "s6";
-	case PERF_REG_RISCV_S7:
-		return "s7";
-	case PERF_REG_RISCV_S8:
-		return "s8";
-	case PERF_REG_RISCV_S9:
-		return "s9";
-	case PERF_REG_RISCV_S10:
-		return "s10";
-	case PERF_REG_RISCV_S11:
-		return "s11";
-	case PERF_REG_RISCV_T3:
-		return "t3";
-	case PERF_REG_RISCV_T4:
-		return "t4";
-	case PERF_REG_RISCV_T5:
-		return "t5";
-	case PERF_REG_RISCV_T6:
-		return "t6";
-	default:
-		return NULL;
-	}
-
-	return NULL;
-}
-
-static const char *__perf_reg_name_s390(int id)
-{
-	switch (id) {
-	case PERF_REG_S390_R0:
-		return "R0";
-	case PERF_REG_S390_R1:
-		return "R1";
-	case PERF_REG_S390_R2:
-		return "R2";
-	case PERF_REG_S390_R3:
-		return "R3";
-	case PERF_REG_S390_R4:
-		return "R4";
-	case PERF_REG_S390_R5:
-		return "R5";
-	case PERF_REG_S390_R6:
-		return "R6";
-	case PERF_REG_S390_R7:
-		return "R7";
-	case PERF_REG_S390_R8:
-		return "R8";
-	case PERF_REG_S390_R9:
-		return "R9";
-	case PERF_REG_S390_R10:
-		return "R10";
-	case PERF_REG_S390_R11:
-		return "R11";
-	case PERF_REG_S390_R12:
-		return "R12";
-	case PERF_REG_S390_R13:
-		return "R13";
-	case PERF_REG_S390_R14:
-		return "R14";
-	case PERF_REG_S390_R15:
-		return "R15";
-	case PERF_REG_S390_FP0:
-		return "FP0";
-	case PERF_REG_S390_FP1:
-		return "FP1";
-	case PERF_REG_S390_FP2:
-		return "FP2";
-	case PERF_REG_S390_FP3:
-		return "FP3";
-	case PERF_REG_S390_FP4:
-		return "FP4";
-	case PERF_REG_S390_FP5:
-		return "FP5";
-	case PERF_REG_S390_FP6:
-		return "FP6";
-	case PERF_REG_S390_FP7:
-		return "FP7";
-	case PERF_REG_S390_FP8:
-		return "FP8";
-	case PERF_REG_S390_FP9:
-		return "FP9";
-	case PERF_REG_S390_FP10:
-		return "FP10";
-	case PERF_REG_S390_FP11:
-		return "FP11";
-	case PERF_REG_S390_FP12:
-		return "FP12";
-	case PERF_REG_S390_FP13:
-		return "FP13";
-	case PERF_REG_S390_FP14:
-		return "FP14";
-	case PERF_REG_S390_FP15:
-		return "FP15";
-	case PERF_REG_S390_MASK:
-		return "MASK";
-	case PERF_REG_S390_PC:
-		return "PC";
-	default:
-		return NULL;
-	}
-
-	return NULL;
-}
-
-static const char *__perf_reg_name_x86(int id)
-{
-	switch (id) {
-	case PERF_REG_X86_AX:
-		return "AX";
-	case PERF_REG_X86_BX:
-		return "BX";
-	case PERF_REG_X86_CX:
-		return "CX";
-	case PERF_REG_X86_DX:
-		return "DX";
-	case PERF_REG_X86_SI:
-		return "SI";
-	case PERF_REG_X86_DI:
-		return "DI";
-	case PERF_REG_X86_BP:
-		return "BP";
-	case PERF_REG_X86_SP:
-		return "SP";
-	case PERF_REG_X86_IP:
-		return "IP";
-	case PERF_REG_X86_FLAGS:
-		return "FLAGS";
-	case PERF_REG_X86_CS:
-		return "CS";
-	case PERF_REG_X86_SS:
-		return "SS";
-	case PERF_REG_X86_DS:
-		return "DS";
-	case PERF_REG_X86_ES:
-		return "ES";
-	case PERF_REG_X86_FS:
-		return "FS";
-	case PERF_REG_X86_GS:
-		return "GS";
-	case PERF_REG_X86_R8:
-		return "R8";
-	case PERF_REG_X86_R9:
-		return "R9";
-	case PERF_REG_X86_R10:
-		return "R10";
-	case PERF_REG_X86_R11:
-		return "R11";
-	case PERF_REG_X86_R12:
-		return "R12";
-	case PERF_REG_X86_R13:
-		return "R13";
-	case PERF_REG_X86_R14:
-		return "R14";
-	case PERF_REG_X86_R15:
-		return "R15";
-
-#define XMM(x) \
-	case PERF_REG_X86_XMM ## x:	\
-	case PERF_REG_X86_XMM ## x + 1:	\
-		return "XMM" #x;
-	XMM(0)
-	XMM(1)
-	XMM(2)
-	XMM(3)
-	XMM(4)
-	XMM(5)
-	XMM(6)
-	XMM(7)
-	XMM(8)
-	XMM(9)
-	XMM(10)
-	XMM(11)
-	XMM(12)
-	XMM(13)
-	XMM(14)
-	XMM(15)
-#undef XMM
-	default:
-		return NULL;
-	}
-
-	return NULL;
-}
-
 const char *perf_reg_name(int id, const char *arch)
 {
 	const char *reg_name = NULL;
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index ce1127af05e4..6b19a2867171 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -36,6 +36,15 @@ extern const struct sample_reg sample_reg_masks[];
 
 const char *perf_reg_name(int id, const char *arch);
 int perf_reg_value(u64 *valp, struct regs_dump *regs, int id);
+const char *__perf_reg_name_arm64(int id);
+const char *__perf_reg_name_arm(int id);
+const char *__perf_reg_name_csky(int id);
+const char *__perf_reg_name_loongarch(int id);
+const char *__perf_reg_name_mips(int id);
+const char *__perf_reg_name_powerpc(int id);
+const char *__perf_reg_name_riscv(int id);
+const char *__perf_reg_name_s390(int id);
+const char *__perf_reg_name_x86(int id);
 
 #else
 #define PERF_REGS_MASK	0
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index d4c9b4cd35ef..26e1c8d973ea 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -40,3 +40,12 @@ util/rwsem.c
 util/hashmap.c
 util/perf_regs.c
 util/fncache.c
+util/perf-regs-arch/perf_regs_aarch64.c
+util/perf-regs-arch/perf_regs_arm.c
+util/perf-regs-arch/perf_regs_csky.c
+util/perf-regs-arch/perf_regs_loongarch.c
+util/perf-regs-arch/perf_regs_mips.c
+util/perf-regs-arch/perf_regs_powerpc.c
+util/perf-regs-arch/perf_regs_riscv.c
+util/perf-regs-arch/perf_regs_s390.c
+util/perf-regs-arch/perf_regs_x86.c

From 34af56afacd82ed585ad9cfc51a3a783ad371b26 Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@linaro.org>
Date: Tue, 6 Jun 2023 09:45:55 +0800
Subject: [PATCH 0438/1189] perf parse-regs: Introduce functions
 perf_arch_reg_{ip|sp}()

The current code uses macros PERF_REG_IP and PERF_REG_SP for parsing
registers and we build perf with these macros statically, which means it
only can correctly analyze CPU registers for the native architecture and
fails to support cross analysis (e.g. we build perf on x86 and cannot
analyze Arm64's registers).

We need to generalize util/perf_regs.c for support multi architectures,
as a first step, this commit introduces new functions perf_arch_reg_ip()
and perf_arch_reg_sp(), these two functions dynamically return IP and SP
register index respectively according to the parameter "arch".

Every architecture has its own functions (like __perf_reg_ip_arm64 and
__perf_reg_sp_arm64), these architecture specific functions are defined
in each arch source file under folder util/perf-regs-arch; at the end
all of them are built into the tool for cross analysis.

Committer notes:

Make DWARF_MINIMAL_REGS() an inline function, so that we can use the
__maybe_unused attribute for the 'arch' parameter, as this will avoid a
build failure when that variable is unused in the callers. That happens
when building on unsupported architectures, the ones without
HAVE_PERF_REGS_SUPPORT defined.

Signed-off-by: Leo Yan <leo.yan@linaro.org>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Eric Lin <eric.lin@sifive.com>
Cc: Fangrui Song <maskray@google.com>
Cc: Guo Ren <guoren@kernel.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ivan Babrou <ivan@cloudflare.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-csky@vger.kernel.org
Cc: linux-riscv@lists.infradead.org
Link: https://lore.kernel.org/r/20230606014559.21783-3-leo.yan@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evsel.c                       |  6 ++-
 .../util/perf-regs-arch/perf_regs_aarch64.c   | 10 ++++
 .../perf/util/perf-regs-arch/perf_regs_arm.c  | 10 ++++
 .../perf/util/perf-regs-arch/perf_regs_csky.c | 10 ++++
 .../util/perf-regs-arch/perf_regs_loongarch.c | 10 ++++
 .../perf/util/perf-regs-arch/perf_regs_mips.c | 10 ++++
 .../util/perf-regs-arch/perf_regs_powerpc.c   | 10 ++++
 .../util/perf-regs-arch/perf_regs_riscv.c     | 10 ++++
 .../perf/util/perf-regs-arch/perf_regs_s390.c | 10 ++++
 .../perf/util/perf-regs-arch/perf_regs_x86.c  | 10 ++++
 tools/perf/util/perf_regs.c                   | 52 +++++++++++++++++++
 tools/perf/util/perf_regs.h                   | 43 +++++++++++++--
 12 files changed, 186 insertions(+), 5 deletions(-)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 0c50c443d456..e3be12596cc3 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -845,6 +845,7 @@ static void __evsel__config_callchain(struct evsel *evsel, struct record_opts *o
 {
 	bool function = evsel__is_function_event(evsel);
 	struct perf_event_attr *attr = &evsel->core.attr;
+	const char *arch = perf_env__arch(evsel__env(evsel));
 
 	evsel__set_sample_bit(evsel, CALLCHAIN);
 
@@ -877,8 +878,9 @@ static void __evsel__config_callchain(struct evsel *evsel, struct record_opts *o
 		if (!function) {
 			evsel__set_sample_bit(evsel, REGS_USER);
 			evsel__set_sample_bit(evsel, STACK_USER);
-			if (opts->sample_user_regs && DWARF_MINIMAL_REGS != PERF_REGS_MASK) {
-				attr->sample_regs_user |= DWARF_MINIMAL_REGS;
+			if (opts->sample_user_regs &&
+			    DWARF_MINIMAL_REGS(arch) != PERF_REGS_MASK) {
+				attr->sample_regs_user |= DWARF_MINIMAL_REGS(arch);
 				pr_warning("WARNING: The use of --call-graph=dwarf may require all the user registers, "
 					   "specifying a subset with --user-regs may render DWARF unwinding unreliable, "
 					   "so the minimal registers set (IP, SP) is explicitly forced.\n");
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_aarch64.c b/tools/perf/util/perf-regs-arch/perf_regs_aarch64.c
index c02c045af46e..696566c54768 100644
--- a/tools/perf/util/perf-regs-arch/perf_regs_aarch64.c
+++ b/tools/perf/util/perf-regs-arch/perf_regs_aarch64.c
@@ -83,4 +83,14 @@ const char *__perf_reg_name_arm64(int id)
 	return NULL;
 }
 
+uint64_t __perf_reg_ip_arm64(void)
+{
+	return PERF_REG_ARM64_PC;
+}
+
+uint64_t __perf_reg_sp_arm64(void)
+{
+	return PERF_REG_ARM64_SP;
+}
+
 #endif
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_arm.c b/tools/perf/util/perf-regs-arch/perf_regs_arm.c
index e8b0fcd72f34..700fd07cd2aa 100644
--- a/tools/perf/util/perf-regs-arch/perf_regs_arm.c
+++ b/tools/perf/util/perf-regs-arch/perf_regs_arm.c
@@ -47,4 +47,14 @@ const char *__perf_reg_name_arm(int id)
 	return NULL;
 }
 
+uint64_t __perf_reg_ip_arm(void)
+{
+	return PERF_REG_ARM_PC;
+}
+
+uint64_t __perf_reg_sp_arm(void)
+{
+	return PERF_REG_ARM_SP;
+}
+
 #endif
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_csky.c b/tools/perf/util/perf-regs-arch/perf_regs_csky.c
index e343b1cef7ba..a2841094e096 100644
--- a/tools/perf/util/perf-regs-arch/perf_regs_csky.c
+++ b/tools/perf/util/perf-regs-arch/perf_regs_csky.c
@@ -87,4 +87,14 @@ const char *__perf_reg_name_csky(int id)
 	return NULL;
 }
 
+uint64_t __perf_reg_ip_csky(void)
+{
+	return PERF_REG_CSKY_PC;
+}
+
+uint64_t __perf_reg_sp_csky(void)
+{
+	return PERF_REG_CSKY_SP;
+}
+
 #endif
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_loongarch.c b/tools/perf/util/perf-regs-arch/perf_regs_loongarch.c
index 6f937464067b..a9ba0f934123 100644
--- a/tools/perf/util/perf-regs-arch/perf_regs_loongarch.c
+++ b/tools/perf/util/perf-regs-arch/perf_regs_loongarch.c
@@ -78,4 +78,14 @@ const char *__perf_reg_name_loongarch(int id)
 	return NULL;
 }
 
+uint64_t __perf_reg_ip_loongarch(void)
+{
+	return PERF_REG_LOONGARCH_PC;
+}
+
+uint64_t __perf_reg_sp_loongarch(void)
+{
+	return PERF_REG_LOONGARCH_R3;
+}
+
 #endif
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_mips.c b/tools/perf/util/perf-regs-arch/perf_regs_mips.c
index f48fbca2f947..5a45830cfbf5 100644
--- a/tools/perf/util/perf-regs-arch/perf_regs_mips.c
+++ b/tools/perf/util/perf-regs-arch/perf_regs_mips.c
@@ -74,4 +74,14 @@ const char *__perf_reg_name_mips(int id)
 	return NULL;
 }
 
+uint64_t __perf_reg_ip_mips(void)
+{
+	return PERF_REG_MIPS_PC;
+}
+
+uint64_t __perf_reg_sp_mips(void)
+{
+	return PERF_REG_MIPS_R29;
+}
+
 #endif
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_powerpc.c b/tools/perf/util/perf-regs-arch/perf_regs_powerpc.c
index dda1b4b169fc..1f0d682db74a 100644
--- a/tools/perf/util/perf-regs-arch/perf_regs_powerpc.c
+++ b/tools/perf/util/perf-regs-arch/perf_regs_powerpc.c
@@ -132,4 +132,14 @@ const char *__perf_reg_name_powerpc(int id)
 	return NULL;
 }
 
+uint64_t __perf_reg_ip_powerpc(void)
+{
+	return PERF_REG_POWERPC_NIP;
+}
+
+uint64_t __perf_reg_sp_powerpc(void)
+{
+	return PERF_REG_POWERPC_R1;
+}
+
 #endif
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_riscv.c b/tools/perf/util/perf-regs-arch/perf_regs_riscv.c
index c504b047cac2..e432630be4c5 100644
--- a/tools/perf/util/perf-regs-arch/perf_regs_riscv.c
+++ b/tools/perf/util/perf-regs-arch/perf_regs_riscv.c
@@ -79,4 +79,14 @@ const char *__perf_reg_name_riscv(int id)
 	return NULL;
 }
 
+uint64_t __perf_reg_ip_riscv(void)
+{
+	return PERF_REG_RISCV_PC;
+}
+
+uint64_t __perf_reg_sp_riscv(void)
+{
+	return PERF_REG_RISCV_SP;
+}
+
 #endif
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_s390.c b/tools/perf/util/perf-regs-arch/perf_regs_s390.c
index e71e2302394c..1c7a46db778c 100644
--- a/tools/perf/util/perf-regs-arch/perf_regs_s390.c
+++ b/tools/perf/util/perf-regs-arch/perf_regs_s390.c
@@ -83,4 +83,14 @@ const char *__perf_reg_name_s390(int id)
 	return NULL;
 }
 
+uint64_t __perf_reg_ip_s390(void)
+{
+	return PERF_REG_S390_PC;
+}
+
+uint64_t __perf_reg_sp_s390(void)
+{
+	return PERF_REG_S390_R15;
+}
+
 #endif
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_x86.c b/tools/perf/util/perf-regs-arch/perf_regs_x86.c
index eb5d249afa70..873c620f0634 100644
--- a/tools/perf/util/perf-regs-arch/perf_regs_x86.c
+++ b/tools/perf/util/perf-regs-arch/perf_regs_x86.c
@@ -85,4 +85,14 @@ const char *__perf_reg_name_x86(int id)
 	return NULL;
 }
 
+uint64_t __perf_reg_ip_x86(void)
+{
+	return PERF_REG_X86_IP;
+}
+
+uint64_t __perf_reg_sp_x86(void)
+{
+	return PERF_REG_X86_SP;
+}
+
 #endif
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
index 5af1b95c3d01..23584efd4886 100644
--- a/tools/perf/util/perf_regs.c
+++ b/tools/perf/util/perf_regs.c
@@ -3,6 +3,7 @@
 #include <string.h>
 #include "perf_regs.h"
 #include "util/sample.h"
+#include "debug.h"
 
 int __weak arch_sdt_arg_parse_op(char *old_op __maybe_unused,
 				 char **new_op __maybe_unused)
@@ -74,4 +75,55 @@ out:
 	*valp = regs->cache_regs[id];
 	return 0;
 }
+
+uint64_t perf_arch_reg_ip(const char *arch)
+{
+	if (!strcmp(arch, "arm"))
+		return __perf_reg_ip_arm();
+	else if (!strcmp(arch, "arm64"))
+		return __perf_reg_ip_arm64();
+	else if (!strcmp(arch, "csky"))
+		return __perf_reg_ip_csky();
+	else if (!strcmp(arch, "loongarch"))
+		return __perf_reg_ip_loongarch();
+	else if (!strcmp(arch, "mips"))
+		return __perf_reg_ip_mips();
+	else if (!strcmp(arch, "powerpc"))
+		return __perf_reg_ip_powerpc();
+	else if (!strcmp(arch, "riscv"))
+		return __perf_reg_ip_riscv();
+	else if (!strcmp(arch, "s390"))
+		return __perf_reg_ip_s390();
+	else if (!strcmp(arch, "x86"))
+		return __perf_reg_ip_x86();
+
+	pr_err("Fail to find IP register for arch %s, returns 0\n", arch);
+	return 0;
+}
+
+uint64_t perf_arch_reg_sp(const char *arch)
+{
+	if (!strcmp(arch, "arm"))
+		return __perf_reg_sp_arm();
+	else if (!strcmp(arch, "arm64"))
+		return __perf_reg_sp_arm64();
+	else if (!strcmp(arch, "csky"))
+		return __perf_reg_sp_csky();
+	else if (!strcmp(arch, "loongarch"))
+		return __perf_reg_sp_loongarch();
+	else if (!strcmp(arch, "mips"))
+		return __perf_reg_sp_mips();
+	else if (!strcmp(arch, "powerpc"))
+		return __perf_reg_sp_powerpc();
+	else if (!strcmp(arch, "riscv"))
+		return __perf_reg_sp_riscv();
+	else if (!strcmp(arch, "s390"))
+		return __perf_reg_sp_s390();
+	else if (!strcmp(arch, "x86"))
+		return __perf_reg_sp_x86();
+
+	pr_err("Fail to find SP register for arch %s, returns 0\n", arch);
+	return 0;
+}
+
 #endif
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index 6b19a2867171..de1673057e50 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -32,25 +32,51 @@ extern const struct sample_reg sample_reg_masks[];
 
 #include <perf_regs.h>
 
-#define DWARF_MINIMAL_REGS ((1ULL << PERF_REG_IP) | (1ULL << PERF_REG_SP))
-
 const char *perf_reg_name(int id, const char *arch);
 int perf_reg_value(u64 *valp, struct regs_dump *regs, int id);
+uint64_t perf_arch_reg_ip(const char *arch);
+uint64_t perf_arch_reg_sp(const char *arch);
 const char *__perf_reg_name_arm64(int id);
+uint64_t __perf_reg_ip_arm64(void);
+uint64_t __perf_reg_sp_arm64(void);
 const char *__perf_reg_name_arm(int id);
+uint64_t __perf_reg_ip_arm(void);
+uint64_t __perf_reg_sp_arm(void);
 const char *__perf_reg_name_csky(int id);
+uint64_t __perf_reg_ip_csky(void);
+uint64_t __perf_reg_sp_csky(void);
 const char *__perf_reg_name_loongarch(int id);
+uint64_t __perf_reg_ip_loongarch(void);
+uint64_t __perf_reg_sp_loongarch(void);
 const char *__perf_reg_name_mips(int id);
+uint64_t __perf_reg_ip_mips(void);
+uint64_t __perf_reg_sp_mips(void);
 const char *__perf_reg_name_powerpc(int id);
+uint64_t __perf_reg_ip_powerpc(void);
+uint64_t __perf_reg_sp_powerpc(void);
 const char *__perf_reg_name_riscv(int id);
+uint64_t __perf_reg_ip_riscv(void);
+uint64_t __perf_reg_sp_riscv(void);
 const char *__perf_reg_name_s390(int id);
+uint64_t __perf_reg_ip_s390(void);
+uint64_t __perf_reg_sp_s390(void);
 const char *__perf_reg_name_x86(int id);
+uint64_t __perf_reg_ip_x86(void);
+uint64_t __perf_reg_sp_x86(void);
+
+static inline uint64_t DWARF_MINIMAL_REGS(const char *arch)
+{
+	return (1ULL << perf_arch_reg_ip(arch)) | (1ULL << perf_arch_reg_sp(arch));
+}
 
 #else
 #define PERF_REGS_MASK	0
 #define PERF_REGS_MAX	0
 
-#define DWARF_MINIMAL_REGS PERF_REGS_MASK
+static inline uint64_t DWARF_MINIMAL_REGS(const char *arch __maybe_unused)
+{
+	return PERF_REGS_MASK;
+}
 
 static inline const char *perf_reg_name(int id __maybe_unused, const char *arch __maybe_unused)
 {
@@ -63,5 +89,16 @@ static inline int perf_reg_value(u64 *valp __maybe_unused,
 {
 	return 0;
 }
+
+static inline uint64_t perf_arch_reg_ip(const char *arch __maybe_unused)
+{
+	return 0;
+}
+
+static inline uint64_t perf_arch_reg_sp(const char *arch __maybe_unused)
+{
+	return 0;
+}
+
 #endif /* HAVE_PERF_REGS_SUPPORT */
 #endif /* __PERF_REGS_H */

From d8f69fb6faeb919d081d0c8dbe974f27b67513f6 Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@linaro.org>
Date: Tue, 6 Jun 2023 09:45:56 +0800
Subject: [PATCH 0439/1189] perf unwind: Use perf_arch_reg_{ip|sp}() to
 substitute macros

We use perf_arch_reg_ip() and perf_arch_reg_sp() to substitute macros
for obtaining the register numbers of SP and IP.  This modification
enables cross analysis in the unwinding, therefore, the unwinding is
not restricted to the predefined values by the macros.

Consequently, the macros LIBUNWIND__ARCH_REG_{IP|SP} are removed since
they are no longer used.

Committer notes:

Add missing "util/env.h" header to make sure we have the definition for
perf_env__arch(), that when built with NO_LIBUNWIND=1 isn't available,
i.e. it was being included by sheer luck.

Signed-off-by: Leo Yan <leo.yan@linaro.org>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Eric Lin <eric.lin@sifive.com>
Cc: Fangrui Song <maskray@google.com>
Cc: Guo Ren <guoren@kernel.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ivan Babrou <ivan@cloudflare.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-csky@vger.kernel.org
Cc: linux-riscv@lists.infradead.org
Link: https://lore.kernel.org/r/20230606014559.21783-4-leo.yan@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/libunwind/arm64.c        | 2 --
 tools/perf/util/libunwind/x86_32.c       | 2 --
 tools/perf/util/unwind-libdw.c           | 8 ++++++--
 tools/perf/util/unwind-libunwind-local.c | 6 ++++--
 tools/perf/util/unwind.h                 | 8 --------
 5 files changed, 10 insertions(+), 16 deletions(-)

diff --git a/tools/perf/util/libunwind/arm64.c b/tools/perf/util/libunwind/arm64.c
index 014d82159656..37ecef0c53b9 100644
--- a/tools/perf/util/libunwind/arm64.c
+++ b/tools/perf/util/libunwind/arm64.c
@@ -18,8 +18,6 @@
  * defined before including "unwind.h"
  */
 #define LIBUNWIND__ARCH_REG_ID(regnum) libunwind__arm64_reg_id(regnum)
-#define LIBUNWIND__ARCH_REG_IP PERF_REG_ARM64_PC
-#define LIBUNWIND__ARCH_REG_SP PERF_REG_ARM64_SP
 
 #include "unwind.h"
 #include "libunwind-aarch64.h"
diff --git a/tools/perf/util/libunwind/x86_32.c b/tools/perf/util/libunwind/x86_32.c
index b2b92d030aef..1697dece1b74 100644
--- a/tools/perf/util/libunwind/x86_32.c
+++ b/tools/perf/util/libunwind/x86_32.c
@@ -18,8 +18,6 @@
  * defined before including "unwind.h"
  */
 #define LIBUNWIND__ARCH_REG_ID(regnum) libunwind__x86_reg_id(regnum)
-#define LIBUNWIND__ARCH_REG_IP PERF_REG_X86_IP
-#define LIBUNWIND__ARCH_REG_SP PERF_REG_X86_SP
 
 #include "unwind.h"
 #include "libunwind-x86.h"
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 2a96df4c8d42..8554db3fc0d7 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -17,6 +17,7 @@
 #include "event.h"
 #include "perf_regs.h"
 #include "callchain.h"
+#include "util/env.h"
 
 static char *debuginfo_path;
 
@@ -170,12 +171,14 @@ static bool memory_read(Dwfl *dwfl __maybe_unused, Dwarf_Addr addr, Dwarf_Word *
 			void *arg)
 {
 	struct unwind_info *ui = arg;
+	const char *arch = perf_env__arch(ui->machine->env);
 	struct stack_dump *stack = &ui->sample->user_stack;
 	u64 start, end;
 	int offset;
 	int ret;
 
-	ret = perf_reg_value(&start, &ui->sample->user_regs, PERF_REG_SP);
+	ret = perf_reg_value(&start, &ui->sample->user_regs,
+			     perf_arch_reg_sp(arch));
 	if (ret)
 		return false;
 
@@ -253,6 +256,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 		.max_stack	= max_stack,
 		.best_effort    = best_effort
 	};
+	const char *arch = perf_env__arch(ui_buf.machine->env);
 	Dwarf_Word ip;
 	int err = -EINVAL, i;
 
@@ -269,7 +273,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 	if (!ui->dwfl)
 		goto out;
 
-	err = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP);
+	err = perf_reg_value(&ip, &data->user_regs, perf_arch_reg_ip(arch));
 	if (err)
 		goto out;
 
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index ebfde537b99b..c0641882fd2f 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -553,6 +553,7 @@ static int access_mem(unw_addr_space_t __maybe_unused as,
 		      int __write, void *arg)
 {
 	struct unwind_info *ui = arg;
+	const char *arch = perf_env__arch(ui->machine->env);
 	struct stack_dump *stack = &ui->sample->user_stack;
 	u64 start, end;
 	int offset;
@@ -565,7 +566,7 @@ static int access_mem(unw_addr_space_t __maybe_unused as,
 	}
 
 	ret = perf_reg_value(&start, &ui->sample->user_regs,
-			     LIBUNWIND__ARCH_REG_SP);
+			     perf_arch_reg_sp(arch));
 	if (ret)
 		return ret;
 
@@ -714,6 +715,7 @@ static void _unwind__finish_access(struct maps *maps)
 static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 		       void *arg, int max_stack)
 {
+	const char *arch = perf_env__arch(ui->machine->env);
 	u64 val;
 	unw_word_t ips[max_stack];
 	unw_addr_space_t addr_space;
@@ -721,7 +723,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 	int ret, i = 0;
 
 	ret = perf_reg_value(&val, &ui->sample->user_regs,
-			     LIBUNWIND__ARCH_REG_IP);
+			     perf_arch_reg_ip(arch));
 	if (ret)
 		return ret;
 
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index b2a03fa5289b..9f7164c6d9aa 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -42,14 +42,6 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 #define LIBUNWIND__ARCH_REG_ID(regnum) libunwind__arch_reg_id(regnum)
 #endif
 
-#ifndef LIBUNWIND__ARCH_REG_SP
-#define LIBUNWIND__ARCH_REG_SP PERF_REG_SP
-#endif
-
-#ifndef LIBUNWIND__ARCH_REG_IP
-#define LIBUNWIND__ARCH_REG_IP PERF_REG_IP
-#endif
-
 int LIBUNWIND__ARCH_REG_ID(int regnum);
 int unwind__prepare_access(struct maps *maps, struct map *map, bool *initialized);
 void unwind__flush_access(struct maps *maps);

From 6a87e0f0ce1ae8d70566935215430e718ea776ff Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@linaro.org>
Date: Tue, 6 Jun 2023 09:45:57 +0800
Subject: [PATCH 0440/1189] perf parse-regs: Remove unused macros
 PERF_REG_{IP|SP}

The macros PERF_REG_{IP|SP} have been replaced by using functions
perf_arch_reg_{ip|sp}(), remove them!

Signed-off-by: Leo Yan <leo.yan@linaro.org>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Eric Lin <eric.lin@sifive.com>
Cc: Fangrui Song <maskray@google.com>
Cc: Guo Ren <guoren@kernel.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ivan Babrou <ivan@cloudflare.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-csky@vger.kernel.org
Cc: linux-riscv@lists.infradead.org
Link: https://lore.kernel.org/r/20230606014559.21783-5-leo.yan@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/arm/include/perf_regs.h       | 3 ---
 tools/perf/arch/arm64/include/perf_regs.h     | 3 ---
 tools/perf/arch/csky/include/perf_regs.h      | 3 ---
 tools/perf/arch/loongarch/include/perf_regs.h | 2 --
 tools/perf/arch/mips/include/perf_regs.h      | 2 --
 tools/perf/arch/powerpc/include/perf_regs.h   | 3 ---
 tools/perf/arch/riscv/include/perf_regs.h     | 3 ---
 tools/perf/arch/s390/include/perf_regs.h      | 3 ---
 tools/perf/arch/x86/include/perf_regs.h       | 2 --
 9 files changed, 24 deletions(-)

diff --git a/tools/perf/arch/arm/include/perf_regs.h b/tools/perf/arch/arm/include/perf_regs.h
index 99a06550e25d..75ce1c370114 100644
--- a/tools/perf/arch/arm/include/perf_regs.h
+++ b/tools/perf/arch/arm/include/perf_regs.h
@@ -12,7 +12,4 @@ void perf_regs_load(u64 *regs);
 #define PERF_REGS_MAX	PERF_REG_ARM_MAX
 #define PERF_SAMPLE_REGS_ABI	PERF_SAMPLE_REGS_ABI_32
 
-#define PERF_REG_IP	PERF_REG_ARM_PC
-#define PERF_REG_SP	PERF_REG_ARM_SP
-
 #endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/arm64/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h
index 35a3cc775b39..58639ee9f7ea 100644
--- a/tools/perf/arch/arm64/include/perf_regs.h
+++ b/tools/perf/arch/arm64/include/perf_regs.h
@@ -14,7 +14,4 @@ void perf_regs_load(u64 *regs);
 #define PERF_REGS_MAX	PERF_REG_ARM64_MAX
 #define PERF_SAMPLE_REGS_ABI	PERF_SAMPLE_REGS_ABI_64
 
-#define PERF_REG_IP	PERF_REG_ARM64_PC
-#define PERF_REG_SP	PERF_REG_ARM64_SP
-
 #endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/csky/include/perf_regs.h b/tools/perf/arch/csky/include/perf_regs.h
index 1afcc0e916c2..076c7746c8a2 100644
--- a/tools/perf/arch/csky/include/perf_regs.h
+++ b/tools/perf/arch/csky/include/perf_regs.h
@@ -12,7 +12,4 @@
 #define PERF_REGS_MAX	PERF_REG_CSKY_MAX
 #define PERF_SAMPLE_REGS_ABI	PERF_SAMPLE_REGS_ABI_32
 
-#define PERF_REG_IP	PERF_REG_CSKY_PC
-#define PERF_REG_SP	PERF_REG_CSKY_SP
-
 #endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/loongarch/include/perf_regs.h b/tools/perf/arch/loongarch/include/perf_regs.h
index 7833c7dbd38d..45c799fa5330 100644
--- a/tools/perf/arch/loongarch/include/perf_regs.h
+++ b/tools/perf/arch/loongarch/include/perf_regs.h
@@ -7,8 +7,6 @@
 #include <asm/perf_regs.h>
 
 #define PERF_REGS_MAX PERF_REG_LOONGARCH_MAX
-#define PERF_REG_IP PERF_REG_LOONGARCH_PC
-#define PERF_REG_SP PERF_REG_LOONGARCH_R3
 
 #define PERF_REGS_MASK ((1ULL << PERF_REG_LOONGARCH_MAX) - 1)
 
diff --git a/tools/perf/arch/mips/include/perf_regs.h b/tools/perf/arch/mips/include/perf_regs.h
index b8cd8bbb37ba..7082e91e0ed1 100644
--- a/tools/perf/arch/mips/include/perf_regs.h
+++ b/tools/perf/arch/mips/include/perf_regs.h
@@ -7,8 +7,6 @@
 #include <asm/perf_regs.h>
 
 #define PERF_REGS_MAX PERF_REG_MIPS_MAX
-#define PERF_REG_IP PERF_REG_MIPS_PC
-#define PERF_REG_SP PERF_REG_MIPS_R29
 
 #define PERF_REGS_MASK ((1ULL << PERF_REG_MIPS_MAX) - 1)
 
diff --git a/tools/perf/arch/powerpc/include/perf_regs.h b/tools/perf/arch/powerpc/include/perf_regs.h
index 9bb17c3f370b..1c66f6ba6773 100644
--- a/tools/perf/arch/powerpc/include/perf_regs.h
+++ b/tools/perf/arch/powerpc/include/perf_regs.h
@@ -16,7 +16,4 @@ void perf_regs_load(u64 *regs);
 	#define PERF_SAMPLE_REGS_ABI	PERF_SAMPLE_REGS_ABI_32
 #endif
 
-#define PERF_REG_IP     PERF_REG_POWERPC_NIP
-#define PERF_REG_SP     PERF_REG_POWERPC_R1
-
 #endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/riscv/include/perf_regs.h b/tools/perf/arch/riscv/include/perf_regs.h
index 6944bf0de53e..d482edb413e5 100644
--- a/tools/perf/arch/riscv/include/perf_regs.h
+++ b/tools/perf/arch/riscv/include/perf_regs.h
@@ -16,7 +16,4 @@
 #define PERF_SAMPLE_REGS_ABI	PERF_SAMPLE_REGS_ABI_32
 #endif
 
-#define PERF_REG_IP	PERF_REG_RISCV_PC
-#define PERF_REG_SP	PERF_REG_RISCV_SP
-
 #endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/s390/include/perf_regs.h b/tools/perf/arch/s390/include/perf_regs.h
index 52fcc0891da6..130dfad2b96a 100644
--- a/tools/perf/arch/s390/include/perf_regs.h
+++ b/tools/perf/arch/s390/include/perf_regs.h
@@ -11,7 +11,4 @@ void perf_regs_load(u64 *regs);
 #define PERF_REGS_MAX PERF_REG_S390_MAX
 #define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_64
 
-#define PERF_REG_IP PERF_REG_S390_PC
-#define PERF_REG_SP PERF_REG_S390_R15
-
 #endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h
index 16e23b722042..f209ce2c1dd9 100644
--- a/tools/perf/arch/x86/include/perf_regs.h
+++ b/tools/perf/arch/x86/include/perf_regs.h
@@ -20,7 +20,5 @@ void perf_regs_load(u64 *regs);
 #define PERF_REGS_MASK (((1ULL << PERF_REG_X86_64_MAX) - 1) & ~REG_NOSUPPORT)
 #define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_64
 #endif
-#define PERF_REG_IP PERF_REG_X86_IP
-#define PERF_REG_SP PERF_REG_X86_SP
 
 #endif /* ARCH_PERF_REGS_H */

From 856caabf729f40ba0be975620ccafd03941a3b92 Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@linaro.org>
Date: Tue, 6 Jun 2023 09:45:58 +0800
Subject: [PATCH 0441/1189] perf parse-regs: Remove PERF_REGS_{MAX|MASK} from
 common code

The macros PERF_REGS_MAX and PERF_REGS_MASK are architecture specific,
let's remove them from the common file util/perf_regs.c.

As a side effect, the weak functions arch__intr_reg_mask() and
arch__user_reg_mask() just return zeros, every arch defines its own
functions in the 'arch' folder for returning right values.

Note, we don't need to return intr/user register masks dynamically, this
is because these two functions are invoked during recording phase but
not decoding phase, they are always invoked on the native environment,
thus we don't need to parse them dynamically.

Signed-off-by: Leo Yan <leo.yan@linaro.org>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Eric Lin <eric.lin@sifive.com>
Cc: Fangrui Song <maskray@google.com>
Cc: Guo Ren <guoren@kernel.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ivan Babrou <ivan@cloudflare.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-csky@vger.kernel.org
Cc: linux-riscv@lists.infradead.org
Link: https://lore.kernel.org/r/20230606014559.21783-6-leo.yan@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/arm/util/perf_regs.c       | 10 ++++++++++
 tools/perf/arch/arm64/util/perf_regs.c     |  5 +++++
 tools/perf/arch/csky/util/perf_regs.c      | 10 ++++++++++
 tools/perf/arch/loongarch/util/perf_regs.c | 10 ++++++++++
 tools/perf/arch/mips/util/perf_regs.c      | 10 ++++++++++
 tools/perf/arch/powerpc/util/perf_regs.c   |  5 +++++
 tools/perf/arch/riscv/util/perf_regs.c     | 10 ++++++++++
 tools/perf/arch/s390/util/perf_regs.c      | 10 ++++++++++
 tools/perf/arch/x86/util/perf_regs.c       |  5 +++++
 tools/perf/util/evsel.c                    |  2 +-
 tools/perf/util/perf_regs.c                |  4 ++--
 tools/perf/util/perf_regs.h                |  4 +---
 12 files changed, 79 insertions(+), 6 deletions(-)

diff --git a/tools/perf/arch/arm/util/perf_regs.c b/tools/perf/arch/arm/util/perf_regs.c
index 2833e101a7c6..d9d4777bf7f9 100644
--- a/tools/perf/arch/arm/util/perf_regs.c
+++ b/tools/perf/arch/arm/util/perf_regs.c
@@ -4,3 +4,13 @@
 const struct sample_reg sample_reg_masks[] = {
 	SMPL_REG_END
 };
+
+uint64_t arch__intr_reg_mask(void)
+{
+	return PERF_REGS_MASK;
+}
+
+uint64_t arch__user_reg_mask(void)
+{
+	return PERF_REGS_MASK;
+}
diff --git a/tools/perf/arch/arm64/util/perf_regs.c b/tools/perf/arch/arm64/util/perf_regs.c
index 006692c9b040..76e2e30702cd 100644
--- a/tools/perf/arch/arm64/util/perf_regs.c
+++ b/tools/perf/arch/arm64/util/perf_regs.c
@@ -139,6 +139,11 @@ int arch_sdt_arg_parse_op(char *old_op, char **new_op)
 	return SDT_ARG_VALID;
 }
 
+uint64_t arch__intr_reg_mask(void)
+{
+	return PERF_REGS_MASK;
+}
+
 uint64_t arch__user_reg_mask(void)
 {
 	struct perf_event_attr attr = {
diff --git a/tools/perf/arch/csky/util/perf_regs.c b/tools/perf/arch/csky/util/perf_regs.c
index 2864e2e3776d..b17fc30abb29 100644
--- a/tools/perf/arch/csky/util/perf_regs.c
+++ b/tools/perf/arch/csky/util/perf_regs.c
@@ -4,3 +4,13 @@
 const struct sample_reg sample_reg_masks[] = {
 	SMPL_REG_END
 };
+
+uint64_t arch__intr_reg_mask(void)
+{
+	return PERF_REGS_MASK;
+}
+
+uint64_t arch__user_reg_mask(void)
+{
+	return PERF_REGS_MASK;
+}
diff --git a/tools/perf/arch/loongarch/util/perf_regs.c b/tools/perf/arch/loongarch/util/perf_regs.c
index 2833e101a7c6..d9d4777bf7f9 100644
--- a/tools/perf/arch/loongarch/util/perf_regs.c
+++ b/tools/perf/arch/loongarch/util/perf_regs.c
@@ -4,3 +4,13 @@
 const struct sample_reg sample_reg_masks[] = {
 	SMPL_REG_END
 };
+
+uint64_t arch__intr_reg_mask(void)
+{
+	return PERF_REGS_MASK;
+}
+
+uint64_t arch__user_reg_mask(void)
+{
+	return PERF_REGS_MASK;
+}
diff --git a/tools/perf/arch/mips/util/perf_regs.c b/tools/perf/arch/mips/util/perf_regs.c
index 2864e2e3776d..b17fc30abb29 100644
--- a/tools/perf/arch/mips/util/perf_regs.c
+++ b/tools/perf/arch/mips/util/perf_regs.c
@@ -4,3 +4,13 @@
 const struct sample_reg sample_reg_masks[] = {
 	SMPL_REG_END
 };
+
+uint64_t arch__intr_reg_mask(void)
+{
+	return PERF_REGS_MASK;
+}
+
+uint64_t arch__user_reg_mask(void)
+{
+	return PERF_REGS_MASK;
+}
diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c
index 8d07a78e742a..1d264bf55955 100644
--- a/tools/perf/arch/powerpc/util/perf_regs.c
+++ b/tools/perf/arch/powerpc/util/perf_regs.c
@@ -226,3 +226,8 @@ uint64_t arch__intr_reg_mask(void)
 	}
 	return mask;
 }
+
+uint64_t arch__user_reg_mask(void)
+{
+	return PERF_REGS_MASK;
+}
diff --git a/tools/perf/arch/riscv/util/perf_regs.c b/tools/perf/arch/riscv/util/perf_regs.c
index 2864e2e3776d..b17fc30abb29 100644
--- a/tools/perf/arch/riscv/util/perf_regs.c
+++ b/tools/perf/arch/riscv/util/perf_regs.c
@@ -4,3 +4,13 @@
 const struct sample_reg sample_reg_masks[] = {
 	SMPL_REG_END
 };
+
+uint64_t arch__intr_reg_mask(void)
+{
+	return PERF_REGS_MASK;
+}
+
+uint64_t arch__user_reg_mask(void)
+{
+	return PERF_REGS_MASK;
+}
diff --git a/tools/perf/arch/s390/util/perf_regs.c b/tools/perf/arch/s390/util/perf_regs.c
index 2864e2e3776d..b17fc30abb29 100644
--- a/tools/perf/arch/s390/util/perf_regs.c
+++ b/tools/perf/arch/s390/util/perf_regs.c
@@ -4,3 +4,13 @@
 const struct sample_reg sample_reg_masks[] = {
 	SMPL_REG_END
 };
+
+uint64_t arch__intr_reg_mask(void)
+{
+	return PERF_REGS_MASK;
+}
+
+uint64_t arch__user_reg_mask(void)
+{
+	return PERF_REGS_MASK;
+}
diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c
index 8ad4112ad10c..218747a8b039 100644
--- a/tools/perf/arch/x86/util/perf_regs.c
+++ b/tools/perf/arch/x86/util/perf_regs.c
@@ -317,3 +317,8 @@ uint64_t arch__intr_reg_mask(void)
 
 	return PERF_REGS_MASK;
 }
+
+uint64_t arch__user_reg_mask(void)
+{
+	return PERF_REGS_MASK;
+}
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index e3be12596cc3..a8a5ff87cc1f 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -879,7 +879,7 @@ static void __evsel__config_callchain(struct evsel *evsel, struct record_opts *o
 			evsel__set_sample_bit(evsel, REGS_USER);
 			evsel__set_sample_bit(evsel, STACK_USER);
 			if (opts->sample_user_regs &&
-			    DWARF_MINIMAL_REGS(arch) != PERF_REGS_MASK) {
+			    DWARF_MINIMAL_REGS(arch) != arch__user_reg_mask()) {
 				attr->sample_regs_user |= DWARF_MINIMAL_REGS(arch);
 				pr_warning("WARNING: The use of --call-graph=dwarf may require all the user registers, "
 					   "specifying a subset with --user-regs may render DWARF unwinding unreliable, "
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
index 23584efd4886..e2275856b570 100644
--- a/tools/perf/util/perf_regs.c
+++ b/tools/perf/util/perf_regs.c
@@ -13,12 +13,12 @@ int __weak arch_sdt_arg_parse_op(char *old_op __maybe_unused,
 
 uint64_t __weak arch__intr_reg_mask(void)
 {
-	return PERF_REGS_MASK;
+	return 0;
 }
 
 uint64_t __weak arch__user_reg_mask(void)
 {
-	return PERF_REGS_MASK;
+	return 0;
 }
 
 #ifdef HAVE_PERF_REGS_SUPPORT
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index de1673057e50..cd9fb673c407 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -70,12 +70,10 @@ static inline uint64_t DWARF_MINIMAL_REGS(const char *arch)
 }
 
 #else
-#define PERF_REGS_MASK	0
-#define PERF_REGS_MAX	0
 
 static inline uint64_t DWARF_MINIMAL_REGS(const char *arch __maybe_unused)
 {
-	return PERF_REGS_MASK;
+	return 0;
 }
 
 static inline const char *perf_reg_name(int id __maybe_unused, const char *arch __maybe_unused)

From ff382c1ce876b6e0ccf1a484e78fa07d57e3863f Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@linaro.org>
Date: Tue, 6 Jun 2023 09:45:59 +0800
Subject: [PATCH 0442/1189] perf parse-regs: Move out arch specific header from
 util/perf_regs.h

util/perf_regs.h includes another perf_regs.h:

  #include <perf_regs.h>

Here it includes architecture specific header, for example, if we build
arm64 target, the header tools/perf/arch/arm64/include/perf_regs.h is
included.

We use this implicit way to include architecture specific header, which
is not directive; furthermore, util/perf_regs.c is coupled with the
architecture specific definitions.

This patch moves out arch specific header from util/perf_regs.h for
generalizing the 'util' folder, as a result, the source files in 'arch'
folder explicitly include architecture's perf_regs.h.

Signed-off-by: Leo Yan <leo.yan@linaro.org>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Eric Lin <eric.lin@sifive.com>
Cc: Fangrui Song <maskray@google.com>
Cc: Guo Ren <guoren@kernel.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ivan Babrou <ivan@cloudflare.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-csky@vger.kernel.org
Cc: linux-riscv@lists.infradead.org
Link: https://lore.kernel.org/r/20230606014559.21783-7-leo.yan@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/arm/util/perf_regs.c          | 1 +
 tools/perf/arch/arm/util/unwind-libdw.c       | 1 +
 tools/perf/arch/arm64/util/machine.c          | 1 +
 tools/perf/arch/arm64/util/perf_regs.c        | 1 +
 tools/perf/arch/arm64/util/unwind-libdw.c     | 1 +
 tools/perf/arch/csky/util/perf_regs.c         | 1 +
 tools/perf/arch/csky/util/unwind-libdw.c      | 1 +
 tools/perf/arch/loongarch/util/perf_regs.c    | 1 +
 tools/perf/arch/loongarch/util/unwind-libdw.c | 1 +
 tools/perf/arch/mips/util/perf_regs.c         | 1 +
 tools/perf/arch/powerpc/util/perf_regs.c      | 1 +
 tools/perf/arch/powerpc/util/unwind-libdw.c   | 1 +
 tools/perf/arch/riscv/util/perf_regs.c        | 1 +
 tools/perf/arch/riscv/util/unwind-libdw.c     | 1 +
 tools/perf/arch/s390/util/perf_regs.c         | 1 +
 tools/perf/arch/s390/util/unwind-libdw.c      | 1 +
 tools/perf/arch/x86/util/perf_regs.c          | 1 +
 tools/perf/arch/x86/util/unwind-libdw.c       | 1 +
 tools/perf/util/perf_regs.h                   | 2 --
 19 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/tools/perf/arch/arm/util/perf_regs.c b/tools/perf/arch/arm/util/perf_regs.c
index d9d4777bf7f9..2c56e8b56ddf 100644
--- a/tools/perf/arch/arm/util/perf_regs.c
+++ b/tools/perf/arch/arm/util/perf_regs.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include "perf_regs.h"
 #include "../../../util/perf_regs.h"
 
 const struct sample_reg sample_reg_masks[] = {
diff --git a/tools/perf/arch/arm/util/unwind-libdw.c b/tools/perf/arch/arm/util/unwind-libdw.c
index 1834a0cd9ce3..4e02cef461e3 100644
--- a/tools/perf/arch/arm/util/unwind-libdw.c
+++ b/tools/perf/arch/arm/util/unwind-libdw.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <elfutils/libdwfl.h>
+#include "perf_regs.h"
 #include "../../../util/unwind-libdw.h"
 #include "../../../util/perf_regs.h"
 #include "../../../util/sample.h"
diff --git a/tools/perf/arch/arm64/util/machine.c b/tools/perf/arch/arm64/util/machine.c
index 235a0a1e1ec7..ba1144366e85 100644
--- a/tools/perf/arch/arm64/util/machine.c
+++ b/tools/perf/arch/arm64/util/machine.c
@@ -6,6 +6,7 @@
 #include "debug.h"
 #include "symbol.h"
 #include "callchain.h"
+#include "perf_regs.h"
 #include "record.h"
 #include "util/perf_regs.h"
 
diff --git a/tools/perf/arch/arm64/util/perf_regs.c b/tools/perf/arch/arm64/util/perf_regs.c
index 76e2e30702cd..1b79d8eab22f 100644
--- a/tools/perf/arch/arm64/util/perf_regs.c
+++ b/tools/perf/arch/arm64/util/perf_regs.c
@@ -6,6 +6,7 @@
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
 
+#include "perf_regs.h"
 #include "../../../perf-sys.h"
 #include "../../../util/debug.h"
 #include "../../../util/event.h"
diff --git a/tools/perf/arch/arm64/util/unwind-libdw.c b/tools/perf/arch/arm64/util/unwind-libdw.c
index 09385081bb03..e056d50ab42e 100644
--- a/tools/perf/arch/arm64/util/unwind-libdw.c
+++ b/tools/perf/arch/arm64/util/unwind-libdw.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <elfutils/libdwfl.h>
+#include "perf_regs.h"
 #include "../../../util/unwind-libdw.h"
 #include "../../../util/perf_regs.h"
 #include "../../../util/sample.h"
diff --git a/tools/perf/arch/csky/util/perf_regs.c b/tools/perf/arch/csky/util/perf_regs.c
index b17fc30abb29..c0877c264d49 100644
--- a/tools/perf/arch/csky/util/perf_regs.c
+++ b/tools/perf/arch/csky/util/perf_regs.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include "perf_regs.h"
 #include "../../util/perf_regs.h"
 
 const struct sample_reg sample_reg_masks[] = {
diff --git a/tools/perf/arch/csky/util/unwind-libdw.c b/tools/perf/arch/csky/util/unwind-libdw.c
index 4bb4a06776e4..79df4374ab18 100644
--- a/tools/perf/arch/csky/util/unwind-libdw.c
+++ b/tools/perf/arch/csky/util/unwind-libdw.c
@@ -2,6 +2,7 @@
 // Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd.
 
 #include <elfutils/libdwfl.h>
+#include "perf_regs.h"
 #include "../../util/unwind-libdw.h"
 #include "../../util/perf_regs.h"
 #include "../../util/event.h"
diff --git a/tools/perf/arch/loongarch/util/perf_regs.c b/tools/perf/arch/loongarch/util/perf_regs.c
index d9d4777bf7f9..2c56e8b56ddf 100644
--- a/tools/perf/arch/loongarch/util/perf_regs.c
+++ b/tools/perf/arch/loongarch/util/perf_regs.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include "perf_regs.h"
 #include "../../../util/perf_regs.h"
 
 const struct sample_reg sample_reg_masks[] = {
diff --git a/tools/perf/arch/loongarch/util/unwind-libdw.c b/tools/perf/arch/loongarch/util/unwind-libdw.c
index a9415385230a..7b3b9a4b21f8 100644
--- a/tools/perf/arch/loongarch/util/unwind-libdw.c
+++ b/tools/perf/arch/loongarch/util/unwind-libdw.c
@@ -2,6 +2,7 @@
 /* Copyright (C) 2020-2023 Loongson Technology Corporation Limited */
 
 #include <elfutils/libdwfl.h>
+#include "perf_regs.h"
 #include "../../util/unwind-libdw.h"
 #include "../../util/perf_regs.h"
 #include "../../util/sample.h"
diff --git a/tools/perf/arch/mips/util/perf_regs.c b/tools/perf/arch/mips/util/perf_regs.c
index b17fc30abb29..c0877c264d49 100644
--- a/tools/perf/arch/mips/util/perf_regs.c
+++ b/tools/perf/arch/mips/util/perf_regs.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include "perf_regs.h"
 #include "../../util/perf_regs.h"
 
 const struct sample_reg sample_reg_masks[] = {
diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c
index 1d264bf55955..b38aa056eea0 100644
--- a/tools/perf/arch/powerpc/util/perf_regs.c
+++ b/tools/perf/arch/powerpc/util/perf_regs.c
@@ -4,6 +4,7 @@
 #include <regex.h>
 #include <linux/zalloc.h>
 
+#include "perf_regs.h"
 #include "../../../util/perf_regs.h"
 #include "../../../util/debug.h"
 #include "../../../util/event.h"
diff --git a/tools/perf/arch/powerpc/util/unwind-libdw.c b/tools/perf/arch/powerpc/util/unwind-libdw.c
index e616642c754c..e9a5a8bb67d9 100644
--- a/tools/perf/arch/powerpc/util/unwind-libdw.c
+++ b/tools/perf/arch/powerpc/util/unwind-libdw.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <elfutils/libdwfl.h>
 #include <linux/kernel.h>
+#include "perf_regs.h"
 #include "../../../util/unwind-libdw.h"
 #include "../../../util/perf_regs.h"
 #include "../../../util/sample.h"
diff --git a/tools/perf/arch/riscv/util/perf_regs.c b/tools/perf/arch/riscv/util/perf_regs.c
index b17fc30abb29..c0877c264d49 100644
--- a/tools/perf/arch/riscv/util/perf_regs.c
+++ b/tools/perf/arch/riscv/util/perf_regs.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include "perf_regs.h"
 #include "../../util/perf_regs.h"
 
 const struct sample_reg sample_reg_masks[] = {
diff --git a/tools/perf/arch/riscv/util/unwind-libdw.c b/tools/perf/arch/riscv/util/unwind-libdw.c
index 54a198714eb8..5c98010d8b59 100644
--- a/tools/perf/arch/riscv/util/unwind-libdw.c
+++ b/tools/perf/arch/riscv/util/unwind-libdw.c
@@ -2,6 +2,7 @@
 /* Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. */
 
 #include <elfutils/libdwfl.h>
+#include "perf_regs.h"
 #include "../../util/unwind-libdw.h"
 #include "../../util/perf_regs.h"
 #include "../../util/sample.h"
diff --git a/tools/perf/arch/s390/util/perf_regs.c b/tools/perf/arch/s390/util/perf_regs.c
index b17fc30abb29..c0877c264d49 100644
--- a/tools/perf/arch/s390/util/perf_regs.c
+++ b/tools/perf/arch/s390/util/perf_regs.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include "perf_regs.h"
 #include "../../util/perf_regs.h"
 
 const struct sample_reg sample_reg_masks[] = {
diff --git a/tools/perf/arch/s390/util/unwind-libdw.c b/tools/perf/arch/s390/util/unwind-libdw.c
index 7d92452d5287..f50fb6dbb35c 100644
--- a/tools/perf/arch/s390/util/unwind-libdw.c
+++ b/tools/perf/arch/s390/util/unwind-libdw.c
@@ -5,6 +5,7 @@
 #include "../../util/event.h"
 #include "../../util/sample.h"
 #include "dwarf-regs-table.h"
+#include "perf_regs.h"
 
 
 bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c
index 218747a8b039..b813502a2727 100644
--- a/tools/perf/arch/x86/util/perf_regs.c
+++ b/tools/perf/arch/x86/util/perf_regs.c
@@ -5,6 +5,7 @@
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
 
+#include "perf_regs.h"
 #include "../../../perf-sys.h"
 #include "../../../util/perf_regs.h"
 #include "../../../util/debug.h"
diff --git a/tools/perf/arch/x86/util/unwind-libdw.c b/tools/perf/arch/x86/util/unwind-libdw.c
index ef71e8bf80bf..edb77e20e083 100644
--- a/tools/perf/arch/x86/util/unwind-libdw.c
+++ b/tools/perf/arch/x86/util/unwind-libdw.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <elfutils/libdwfl.h>
+#include "perf_regs.h"
 #include "../../../util/unwind-libdw.h"
 #include "../../../util/perf_regs.h"
 #include "util/sample.h"
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index cd9fb673c407..ecd2a5362042 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -30,8 +30,6 @@ uint64_t arch__user_reg_mask(void);
 #ifdef HAVE_PERF_REGS_SUPPORT
 extern const struct sample_reg sample_reg_masks[];
 
-#include <perf_regs.h>
-
 const char *perf_reg_name(int id, const char *arch);
 int perf_reg_value(u64 *valp, struct regs_dump *regs, int id);
 uint64_t perf_arch_reg_ip(const char *arch);

From 159a8bb06f7bb298da1aacc99975e9817e2cf02c Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Wed, 2 Aug 2023 10:03:27 +0200
Subject: [PATCH 0443/1189] libperf: Implement riscv mmap support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

riscv now supports mmaping hardware counters so add what's needed to
take advantage of that in libperf.

Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Atish Patra <atishp@atishpatra.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rob Herring <robh@kernel.org>
Cc: Rémi Denis-Courmont <remi@remlab.net>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-doc@vger.kernel.org
Cc: linux-riscv@lists.infradead.org
Link: https://lore.kernel.org/r/20230802080328.1213905-10-alexghiti@rivosinc.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/perf/mmap.c | 66 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 66 insertions(+)

diff --git a/tools/lib/perf/mmap.c b/tools/lib/perf/mmap.c
index 0d1634cedf44..2184814b37dd 100644
--- a/tools/lib/perf/mmap.c
+++ b/tools/lib/perf/mmap.c
@@ -392,6 +392,72 @@ static u64 read_perf_counter(unsigned int counter)
 
 static u64 read_timestamp(void) { return read_sysreg(cntvct_el0); }
 
+/* __riscv_xlen contains the witdh of the native base integer, here 64-bit */
+#elif defined(__riscv) && __riscv_xlen == 64
+
+/* TODO: implement rv32 support */
+
+#define CSR_CYCLE	0xc00
+#define CSR_TIME	0xc01
+
+#define csr_read(csr)						\
+({								\
+	register unsigned long __v;				\
+		__asm__ __volatile__ ("csrr %0, %1"		\
+		 : "=r" (__v)					\
+		 : "i" (csr) : );				\
+		 __v;						\
+})
+
+static unsigned long csr_read_num(int csr_num)
+{
+#define switchcase_csr_read(__csr_num, __val)           {\
+	case __csr_num:                                 \
+		__val = csr_read(__csr_num);            \
+		break; }
+#define switchcase_csr_read_2(__csr_num, __val)         {\
+	switchcase_csr_read(__csr_num + 0, __val)        \
+	switchcase_csr_read(__csr_num + 1, __val)}
+#define switchcase_csr_read_4(__csr_num, __val)         {\
+	switchcase_csr_read_2(__csr_num + 0, __val)      \
+	switchcase_csr_read_2(__csr_num + 2, __val)}
+#define switchcase_csr_read_8(__csr_num, __val)         {\
+	switchcase_csr_read_4(__csr_num + 0, __val)      \
+	switchcase_csr_read_4(__csr_num + 4, __val)}
+#define switchcase_csr_read_16(__csr_num, __val)        {\
+	switchcase_csr_read_8(__csr_num + 0, __val)      \
+	switchcase_csr_read_8(__csr_num + 8, __val)}
+#define switchcase_csr_read_32(__csr_num, __val)        {\
+	switchcase_csr_read_16(__csr_num + 0, __val)     \
+	switchcase_csr_read_16(__csr_num + 16, __val)}
+
+	unsigned long ret = 0;
+
+	switch (csr_num) {
+	switchcase_csr_read_32(CSR_CYCLE, ret)
+	default:
+		break;
+	}
+
+	return ret;
+#undef switchcase_csr_read_32
+#undef switchcase_csr_read_16
+#undef switchcase_csr_read_8
+#undef switchcase_csr_read_4
+#undef switchcase_csr_read_2
+#undef switchcase_csr_read
+}
+
+static u64 read_perf_counter(unsigned int counter)
+{
+	return csr_read_num(CSR_CYCLE + counter);
+}
+
+static u64 read_timestamp(void)
+{
+	return csr_read_num(CSR_TIME);
+}
+
 #else
 static u64 read_perf_counter(unsigned int counter __maybe_unused) { return 0; }
 static u64 read_timestamp(void) { return 0; }

From 10da1b8ed79f7fca4e46c926ef109b753f290976 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Wed, 2 Aug 2023 10:03:28 +0200
Subject: [PATCH 0444/1189] perf tests mmap-basic: Adapt for riscv
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

riscv now supports mmaping hardware counters to userspace so adapt the
test to run on this architecture.

Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Atish Patra <atishp@atishpatra.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rob Herring <robh@kernel.org>
Cc: Rémi Denis-Courmont <remi@remlab.net>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-doc@vger.kernel.org
Cc: linux-riscv@lists.infradead.org
Link: https://lore.kernel.org/r/20230802080328.1213905-11-alexghiti@rivosinc.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/mmap-basic.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index e68ca6229756..886a13a77a16 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -284,7 +284,8 @@ static struct test_case tests__basic_mmap[] = {
 			 "permissions"),
 	TEST_CASE_REASON("User space counter reading of instructions",
 			 mmap_user_read_instr,
-#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__)
+#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) || \
+			 (defined(__riscv) && __riscv_xlen == 64)
 			 "permissions"
 #else
 			 "unsupported"
@@ -292,7 +293,8 @@ static struct test_case tests__basic_mmap[] = {
 		),
 	TEST_CASE_REASON("User space counter reading of cycles",
 			 mmap_user_read_cycles,
-#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__)
+#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) || \
+			 (defined(__riscv) && __riscv_xlen == 64)
 			 "permissions"
 #else
 			 "unsupported"

From 3286f88f31da060ac2789cee247153961ba57e49 Mon Sep 17 00:00:00 2001
From: Kajol Jain <kjain@linux.ibm.com>
Date: Mon, 14 Aug 2023 16:57:57 +0530
Subject: [PATCH 0445/1189] perf vendor events: Update the JSON/events
 descriptions for power10 platform

Update the description for some of the JSON/events for power10 platform.

Fixes: 32daa5d7899e0343 ("perf vendor events: Initial JSON/events list for power10 platform")
Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Disha Goel <disgoel@linux.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230814112803.1508296-1-kjain@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../arch/powerpc/power10/cache.json           |  4 +-
 .../arch/powerpc/power10/frontend.json        | 30 ++++++------
 .../arch/powerpc/power10/marked.json          | 20 ++++----
 .../arch/powerpc/power10/memory.json          |  6 +--
 .../arch/powerpc/power10/others.json          | 48 +++++++++----------
 .../arch/powerpc/power10/pipeline.json        | 20 ++++----
 .../pmu-events/arch/powerpc/power10/pmc.json  |  4 +-
 .../arch/powerpc/power10/translation.json     |  6 +--
 8 files changed, 69 insertions(+), 69 deletions(-)

diff --git a/tools/perf/pmu-events/arch/powerpc/power10/cache.json b/tools/perf/pmu-events/arch/powerpc/power10/cache.json
index 605be14f441c..9cb929bb64af 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/cache.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/cache.json
@@ -17,7 +17,7 @@
   {
     "EventCode": "0x34056",
     "EventName": "PM_EXEC_STALL_LOAD_FINISH",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was finishing a load after its data was reloaded from a data source beyond the local L1; cycles in which the LSU was processing an L1-hit; cycles in which the NTF instruction merged with another load in the LMQ; cycles in which the NTF instruction is waiting for a data reload for a load miss, but the data comes back with a non-NTF instruction."
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was finishing a load after its data was reloaded from a data source beyond the local L1; cycles in which the LSU was processing an L1-hit; cycles in which the next-to-finish (NTF) instruction merged with another load in the LMQ; cycles in which the NTF instruction is waiting for a data reload for a load miss, but the data comes back with a non-NTF instruction."
   },
   {
     "EventCode": "0x3006C",
@@ -27,7 +27,7 @@
   {
     "EventCode": "0x300F4",
     "EventName": "PM_RUN_INST_CMPL_CONC",
-    "BriefDescription": "PowerPC instructions completed by this thread when all threads in the core had the run-latch set."
+    "BriefDescription": "PowerPC instruction completed by this thread when all threads in the core had the run-latch set."
   },
   {
     "EventCode": "0x4C016",
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/frontend.json b/tools/perf/pmu-events/arch/powerpc/power10/frontend.json
index 558f9530f54e..61e9e0222c87 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/frontend.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/frontend.json
@@ -7,7 +7,7 @@
   {
     "EventCode": "0x10006",
     "EventName": "PM_DISP_STALL_HELD_OTHER_CYC",
-    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch for any other reason."
+    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch for any other reason."
   },
   {
     "EventCode": "0x10010",
@@ -32,12 +32,12 @@
   {
     "EventCode": "0x1D05E",
     "EventName": "PM_DISP_STALL_HELD_HALT_CYC",
-    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because of power management."
+    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because of power management."
   },
   {
     "EventCode": "0x1E050",
     "EventName": "PM_DISP_STALL_HELD_STF_MAPPER_CYC",
-    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because the STF mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR."
+    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because the STF mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR."
   },
   {
     "EventCode": "0x1F054",
@@ -67,7 +67,7 @@
   {
     "EventCode": "0x100F6",
     "EventName": "PM_IERAT_MISS",
-    "BriefDescription": "IERAT Reloaded to satisfy an IERAT miss. All page sizes are counted by this event."
+    "BriefDescription": "IERAT Reloaded to satisfy an IERAT miss. All page sizes are counted by this event. This event only counts instruction demand access."
   },
   {
     "EventCode": "0x100F8",
@@ -77,7 +77,7 @@
   {
     "EventCode": "0x20006",
     "EventName": "PM_DISP_STALL_HELD_ISSQ_FULL_CYC",
-    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch due to Issue queue full. Includes issue queue and branch queue."
+    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch due to Issue queue full. Includes issue queue and branch queue."
   },
   {
     "EventCode": "0x20114",
@@ -102,7 +102,7 @@
   {
     "EventCode": "0x2D01A",
     "EventName": "PM_DISP_STALL_IC_MISS",
-    "BriefDescription": "Cycles when dispatch was stalled for this thread due to an Icache Miss."
+    "BriefDescription": "Cycles when dispatch was stalled for this thread due to an instruction cache miss."
   },
   {
     "EventCode": "0x2E018",
@@ -112,7 +112,7 @@
   {
     "EventCode": "0x2E01A",
     "EventName": "PM_DISP_STALL_HELD_XVFC_MAPPER_CYC",
-    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because the XVFC mapper/SRB was full."
+    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because the XVFC mapper/SRB was full."
   },
   {
     "EventCode": "0x2C142",
@@ -137,7 +137,7 @@
   {
     "EventCode": "0x30004",
     "EventName": "PM_DISP_STALL_FLUSH",
-    "BriefDescription": "Cycles when dispatch was stalled because of a flush that happened to an instruction(s) that was not yet NTC. PM_EXEC_STALL_NTC_FLUSH only includes instructions that were flushed after becoming NTC."
+    "BriefDescription": "Cycles when dispatch was stalled because of a flush that happened to an instruction(s) that was not yet next-to-complete (NTC). PM_EXEC_STALL_NTC_FLUSH only includes instructions that were flushed after becoming NTC."
   },
   {
     "EventCode": "0x3000A",
@@ -157,7 +157,7 @@
   {
     "EventCode": "0x30018",
     "EventName": "PM_DISP_STALL_HELD_SCOREBOARD_CYC",
-    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch while waiting on the Scoreboard. This event combines VSCR and FPSCR together."
+    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch while waiting on the Scoreboard. This event combines VSCR and FPSCR together."
   },
   {
     "EventCode": "0x30026",
@@ -182,7 +182,7 @@
   {
     "EventCode": "0x3D05C",
     "EventName": "PM_DISP_STALL_HELD_RENAME_CYC",
-    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because the mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR and XVFC."
+    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because the mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR and XVFC."
   },
   {
     "EventCode": "0x3E052",
@@ -192,7 +192,7 @@
   {
     "EventCode": "0x3E054",
     "EventName": "PM_LD_MISS_L1",
-    "BriefDescription": "Load Missed L1, counted at execution time (can be greater than loads finished). LMQ merges are not included in this count. i.e. if a load instruction misses on an address that is already allocated on the LMQ, this event will not increment for that load). Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load."
+    "BriefDescription": "Load missed L1, counted at finish time. LMQ merges are not included in this count. i.e. if a load instruction misses on an address that is already allocated on the LMQ, this event will not increment for that load). Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load."
   },
   {
     "EventCode": "0x301EA",
@@ -202,7 +202,7 @@
   {
     "EventCode": "0x300FA",
     "EventName": "PM_INST_FROM_L3MISS",
-    "BriefDescription": "The processor's instruction cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss."
+    "BriefDescription": "The processor's instruction cache was reloaded from beyond the local core's L3 due to a demand miss."
   },
   {
     "EventCode": "0x40006",
@@ -232,16 +232,16 @@
   {
     "EventCode": "0x4E01A",
     "EventName": "PM_DISP_STALL_HELD_CYC",
-    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch for any reason."
+    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch for any reason."
   },
   {
     "EventCode": "0x4003C",
     "EventName": "PM_DISP_STALL_HELD_SYNC_CYC",
-    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because of a synchronizing instruction that requires the ICT to be empty before dispatch."
+    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because of a synchronizing instruction that requires the ICT to be empty before dispatch."
   },
   {
     "EventCode": "0x44056",
     "EventName": "PM_VECTOR_ST_CMPL",
-    "BriefDescription": "Vector store instructions completed."
+    "BriefDescription": "Vector store instruction completed."
   }
 ]
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/marked.json b/tools/perf/pmu-events/arch/powerpc/power10/marked.json
index 58b5dfe3a273..131f8d0e8831 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/marked.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/marked.json
@@ -62,7 +62,7 @@
   {
     "EventCode": "0x200FD",
     "EventName": "PM_L1_ICACHE_MISS",
-    "BriefDescription": "Demand iCache Miss."
+    "BriefDescription": "Demand instruction cache miss."
   },
   {
     "EventCode": "0x30130",
@@ -72,7 +72,7 @@
   {
     "EventCode": "0x34146",
     "EventName": "PM_MRK_LD_CMPL",
-    "BriefDescription": "Marked loads completed."
+    "BriefDescription": "Marked load instruction completed."
   },
   {
     "EventCode": "0x3E158",
@@ -82,12 +82,12 @@
   {
     "EventCode": "0x3E15A",
     "EventName": "PM_MRK_ST_FIN",
-    "BriefDescription": "The marked instruction was a store of any kind."
+    "BriefDescription": "Marked store instruction finished."
   },
   {
     "EventCode": "0x30068",
     "EventName": "PM_L1_ICACHE_RELOADED_PREF",
-    "BriefDescription": "Counts all Icache prefetch reloads ( includes demand turned into prefetch)."
+    "BriefDescription": "Counts all instruction cache prefetch reloads (includes demand turned into prefetch)."
   },
   {
     "EventCode": "0x301E4",
@@ -102,12 +102,12 @@
   {
     "EventCode": "0x300FE",
     "EventName": "PM_DATA_FROM_L3MISS",
-    "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss."
+    "BriefDescription": "The processor's L1 data cache was reloaded from beyond the local core's L3 due to a demand miss."
   },
   {
     "EventCode": "0x40012",
     "EventName": "PM_L1_ICACHE_RELOADED_ALL",
-    "BriefDescription": "Counts all Icache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch."
+    "BriefDescription": "Counts all instruction cache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch."
   },
   {
     "EventCode": "0x40134",
@@ -117,22 +117,22 @@
   {
     "EventCode": "0x4505A",
     "EventName": "PM_SP_FLOP_CMPL",
-    "BriefDescription": "Single Precision floating point instructions completed."
+    "BriefDescription": "Single Precision floating point instruction completed."
   },
   {
     "EventCode": "0x4D058",
     "EventName": "PM_VECTOR_FLOP_CMPL",
-    "BriefDescription": "Vector floating point instructions completed."
+    "BriefDescription": "Vector floating point instruction completed."
   },
   {
     "EventCode": "0x4D05A",
     "EventName": "PM_NON_MATH_FLOP_CMPL",
-    "BriefDescription": "Non Math instructions completed."
+    "BriefDescription": "Non Math instruction completed."
   },
   {
     "EventCode": "0x401E0",
     "EventName": "PM_MRK_INST_CMPL",
-    "BriefDescription": "marked instruction completed."
+    "BriefDescription": "Marked instruction completed."
   },
   {
     "EventCode": "0x400FE",
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/memory.json b/tools/perf/pmu-events/arch/powerpc/power10/memory.json
index 843b51f531e9..c4c10ca98cad 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/memory.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/memory.json
@@ -47,7 +47,7 @@
   {
     "EventCode": "0x10062",
     "EventName": "PM_LD_L3MISS_PEND_CYC",
-    "BriefDescription": "Cycles L3 miss was pending for this thread."
+    "BriefDescription": "Cycles in which an L3 miss was pending for this thread."
   },
   {
     "EventCode": "0x20010",
@@ -132,7 +132,7 @@
   {
     "EventCode": "0x300FC",
     "EventName": "PM_DTLB_MISS",
-    "BriefDescription": "The DPTEG required for the load/store instruction in execution was missing from the TLB. It includes pages of all sizes for demand and prefetch activity."
+    "BriefDescription": "The DPTEG required for the load/store instruction in execution was missing from the TLB. This event only counts for demand misses."
   },
   {
     "EventCode": "0x4D02C",
@@ -142,7 +142,7 @@
   {
     "EventCode": "0x4003E",
     "EventName": "PM_LD_CMPL",
-    "BriefDescription": "Loads completed."
+    "BriefDescription": "Load instruction completed."
   },
   {
     "EventCode": "0x4C040",
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/others.json b/tools/perf/pmu-events/arch/powerpc/power10/others.json
index a771e4b6bec5..a5319cdba89b 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/others.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/others.json
@@ -2,12 +2,12 @@
   {
     "EventCode": "0x10016",
     "EventName": "PM_VSU0_ISSUE",
-    "BriefDescription": "VSU instructions issued to VSU pipe 0."
+    "BriefDescription": "VSU instruction issued to VSU pipe 0."
   },
   {
     "EventCode": "0x1001C",
     "EventName": "PM_ULTRAVISOR_INST_CMPL",
-    "BriefDescription": "PowerPC instructions that completed while the thread was in ultravisor state."
+    "BriefDescription": "PowerPC instruction completed while the thread was in ultravisor state."
   },
   {
     "EventCode": "0x100F0",
@@ -17,12 +17,12 @@
   {
     "EventCode": "0x10134",
     "EventName": "PM_MRK_ST_DONE_L2",
-    "BriefDescription": "Marked stores completed in L2 (RC machine done)."
+    "BriefDescription": "Marked store completed in L2."
   },
   {
     "EventCode": "0x1505E",
     "EventName": "PM_LD_HIT_L1",
-    "BriefDescription": "Loads that finished without experiencing an L1 miss."
+    "BriefDescription": "Load finished without experiencing an L1 miss."
   },
   {
     "EventCode": "0x1F056",
@@ -42,7 +42,7 @@
   {
     "EventCode": "0x101E4",
     "EventName": "PM_MRK_L1_ICACHE_MISS",
-    "BriefDescription": "Marked Instruction suffered an icache Miss."
+    "BriefDescription": "Marked instruction suffered an instruction cache miss."
   },
   {
     "EventCode": "0x101EA",
@@ -72,7 +72,7 @@
   {
     "EventCode": "0x2E010",
     "EventName": "PM_ADJUNCT_INST_CMPL",
-    "BriefDescription": "PowerPC instructions that completed while the thread is in Adjunct state."
+    "BriefDescription": "PowerPC instruction completed while the thread was in Adjunct state."
   },
   {
     "EventCode": "0x2E014",
@@ -122,7 +122,7 @@
   {
     "EventCode": "0x201E4",
     "EventName": "PM_MRK_DATA_FROM_L3MISS",
-    "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss for a marked load."
+    "BriefDescription": "The processor's L1 data cache was reloaded from beyond the local core's L3 due to a demand miss for a marked instruction."
   },
   {
     "EventCode": "0x201E8",
@@ -132,17 +132,17 @@
   {
     "EventCode": "0x200F2",
     "EventName": "PM_INST_DISP",
-    "BriefDescription": "PowerPC instructions dispatched."
+    "BriefDescription": "PowerPC instruction dispatched."
   },
   {
     "EventCode": "0x30132",
     "EventName": "PM_MRK_VSU_FIN",
-    "BriefDescription": "VSU marked instructions finished. Excludes simple FX instructions issued to the Store Unit."
+    "BriefDescription": "VSU marked instruction finished. Excludes simple FX instructions issued to the Store Unit."
   },
   {
     "EventCode": "0x30038",
     "EventName": "PM_EXEC_STALL_DMISS_LMEM",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local memory, local OpenCapp cache, or local OpenCapp memory."
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local memory, local OpenCAPI cache, or local OpenCAPI memory."
   },
   {
     "EventCode": "0x3F04A",
@@ -152,12 +152,12 @@
   {
     "EventCode": "0x3405A",
     "EventName": "PM_PRIVILEGED_INST_CMPL",
-    "BriefDescription": "PowerPC Instructions that completed while the thread is in Privileged state."
+    "BriefDescription": "PowerPC instruction completed while the thread was in Privileged state."
   },
   {
     "EventCode": "0x3F150",
     "EventName": "PM_MRK_ST_DRAIN_CYC",
-    "BriefDescription": "cycles to drain st from core to L2."
+    "BriefDescription": "Cycles in which the marked store drained from the core to the L2."
   },
   {
     "EventCode": "0x3F054",
@@ -182,7 +182,7 @@
   {
     "EventCode": "0x4001C",
     "EventName": "PM_VSU_FIN",
-    "BriefDescription": "VSU instructions finished."
+    "BriefDescription": "VSU instruction finished."
   },
   {
     "EventCode": "0x4C01A",
@@ -197,7 +197,7 @@
   {
     "EventCode": "0x4D022",
     "EventName": "PM_HYPERVISOR_INST_CMPL",
-    "BriefDescription": "PowerPC instructions that completed while the thread is in hypervisor state."
+    "BriefDescription": "PowerPC instruction completed while the thread was in hypervisor state."
   },
   {
     "EventCode": "0x4D026",
@@ -212,32 +212,32 @@
   {
     "EventCode": "0x40030",
     "EventName": "PM_INST_FIN",
-    "BriefDescription": "Instructions finished."
+    "BriefDescription": "Instruction finished."
   },
   {
     "EventCode": "0x44146",
     "EventName": "PM_MRK_STCX_CORE_CYC",
-    "BriefDescription": "Cycles spent in the core portion of a marked Stcx instruction. It starts counting when the instruction is decoded and stops counting when it drains into the L2."
+    "BriefDescription": "Cycles spent in the core portion of a marked STCX instruction. It starts counting when the instruction is decoded and stops counting when it drains into the L2."
   },
   {
     "EventCode": "0x44054",
     "EventName": "PM_VECTOR_LD_CMPL",
-    "BriefDescription": "Vector load instructions completed."
+    "BriefDescription": "Vector load instruction completed."
   },
   {
     "EventCode": "0x45054",
     "EventName": "PM_FMA_CMPL",
-    "BriefDescription": "Two floating point instructions completed (FMA class of instructions: fmadd, fnmadd, fmsub, fnmsub). Scalar instructions only."
+    "BriefDescription": "Two floating point instruction completed (FMA class of instructions: fmadd, fnmadd, fmsub, fnmsub). Scalar instructions only."
   },
   {
     "EventCode": "0x45056",
     "EventName": "PM_SCALAR_FLOP_CMPL",
-    "BriefDescription": "Scalar floating point instructions completed."
+    "BriefDescription": "Scalar floating point instruction completed."
   },
   {
     "EventCode": "0x4505C",
     "EventName": "PM_MATH_FLOP_CMPL",
-    "BriefDescription": "Math floating point instructions completed."
+    "BriefDescription": "Math floating point instruction completed."
   },
   {
     "EventCode": "0x4D05E",
@@ -252,21 +252,21 @@
   {
     "EventCode": "0x401E6",
     "EventName": "PM_MRK_INST_FROM_L3MISS",
-    "BriefDescription": "The processor's instruction cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss for a marked instruction."
+    "BriefDescription": "The processor's instruction cache was reloaded from beyond the local core's L3 due to a demand miss for a marked instruction."
   },
   {
     "EventCode": "0x401E8",
     "EventName": "PM_MRK_DATA_FROM_L2MISS",
-    "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1 or L2 due to a demand miss for a marked load."
+    "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L2 due to a demand miss for a marked instruction."
   },
   {
     "EventCode": "0x400F0",
     "EventName": "PM_LD_DEMAND_MISS_L1_FIN",
-    "BriefDescription": "Load Missed L1, counted at finish time."
+    "BriefDescription": "Load missed L1, counted at finish time."
   },
   {
     "EventCode": "0x500FA",
     "EventName": "PM_RUN_INST_CMPL",
-    "BriefDescription": "Completed PowerPC instructions gated by the run latch."
+    "BriefDescription": "PowerPC instruction completed while the run latch is set."
   }
 ]
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json b/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json
index b8aded6045fa..449f57e8ba6a 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json
@@ -2,7 +2,7 @@
   {
     "EventCode": "0x100FE",
     "EventName": "PM_INST_CMPL",
-    "BriefDescription": "PowerPC instructions completed."
+    "BriefDescription": "PowerPC instruction completed."
   },
   {
     "EventCode": "0x1000C",
@@ -12,7 +12,7 @@
   {
     "EventCode": "0x1000E",
     "EventName": "PM_MMA_ISSUED",
-    "BriefDescription": "MMA instructions issued."
+    "BriefDescription": "MMA instruction issued."
   },
   {
     "EventCode": "0x10012",
@@ -107,7 +107,7 @@
   {
     "EventCode": "0x2D012",
     "EventName": "PM_VSU1_ISSUE",
-    "BriefDescription": "VSU instructions issued to VSU pipe 1."
+    "BriefDescription": "VSU instruction issued to VSU pipe 1."
   },
   {
     "EventCode": "0x2D018",
@@ -122,7 +122,7 @@
   {
     "EventCode": "0x2E01E",
     "EventName": "PM_EXEC_STALL_NTC_FLUSH",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in any unit before it was flushed. Note that if the flush of the oldest instruction happens after finish, the cycles from dispatch to issue will be included in PM_DISP_STALL and the cycles from issue to finish will be included in PM_EXEC_STALL and its corresponding children. This event will also count cycles when the previous NTF instruction is still completing and the new NTF instruction is stalled at dispatch."
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in any unit before it was flushed. Note that if the flush of the oldest instruction happens after finish, the cycles from dispatch to issue will be included in PM_DISP_STALL and the cycles from issue to finish will be included in PM_EXEC_STALL and its corresponding children. This event will also count cycles when the previous next-to-finish (NTF) instruction is still completing and the new NTF instruction is stalled at dispatch."
   },
   {
     "EventCode": "0x2013C",
@@ -137,7 +137,7 @@
   {
     "EventCode": "0x201E2",
     "EventName": "PM_MRK_LD_MISS_L1",
-    "BriefDescription": "Marked DL1 Demand Miss counted at finish time."
+    "BriefDescription": "Marked demand data load miss counted at finish time."
   },
   {
     "EventCode": "0x200F4",
@@ -172,7 +172,7 @@
   {
     "EventCode": "0x30028",
     "EventName": "PM_CMPL_STALL_MEM_ECC",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for the non-speculative finish of either a stcx waiting for its result or a load waiting for non-critical sectors of data and ECC."
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for the non-speculative finish of either a STCX waiting for its result or a load waiting for non-critical sectors of data and ECC."
   },
   {
     "EventCode": "0x30036",
@@ -187,12 +187,12 @@
   {
     "EventCode": "0x3F044",
     "EventName": "PM_VSU2_ISSUE",
-    "BriefDescription": "VSU instructions issued to VSU pipe 2."
+    "BriefDescription": "VSU instruction issued to VSU pipe 2."
   },
   {
     "EventCode": "0x30058",
     "EventName": "PM_TLBIE_FIN",
-    "BriefDescription": "TLBIE instructions finished in the LSU. Two TLBIEs can finish each cycle. All will be counted."
+    "BriefDescription": "TLBIE instruction finished in the LSU. Two TLBIEs can finish each cycle. All will be counted."
   },
   {
     "EventCode": "0x3D058",
@@ -252,7 +252,7 @@
   {
     "EventCode": "0x4E012",
     "EventName": "PM_EXEC_STALL_UNKNOWN",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline completed without an ntf_type pulse. The ntf_pulse was missed by the ISU because the NTF finishes and completions came too close together."
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline completed without an ntf_type pulse. The ntf_pulse was missed by the ISU because the next-to-finish (NTF) instruction finishes and completions came too close together."
   },
   {
     "EventCode": "0x4D020",
@@ -267,7 +267,7 @@
   {
     "EventCode": "0x45058",
     "EventName": "PM_IC_MISS_CMPL",
-    "BriefDescription": "Non-speculative icache miss, counted at completion."
+    "BriefDescription": "Non-speculative instruction cache miss, counted at completion."
   },
   {
     "EventCode": "0x4D050",
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/pmc.json b/tools/perf/pmu-events/arch/powerpc/power10/pmc.json
index b5d1bd39cfb2..364fedbfb490 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/pmc.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/pmc.json
@@ -12,11 +12,11 @@
   {
     "EventCode": "0x45052",
     "EventName": "PM_4FLOP_CMPL",
-    "BriefDescription": "Four floating point instructions completed (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg)."
+    "BriefDescription": "Four floating point instruction completed (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg)."
   },
   {
     "EventCode": "0x4D054",
     "EventName": "PM_8FLOP_CMPL",
-    "BriefDescription": "Four Double Precision vector instructions completed."
+    "BriefDescription": "Four Double Precision vector instruction completed."
   }
 ]
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/translation.json b/tools/perf/pmu-events/arch/powerpc/power10/translation.json
index db3766dca07c..3e47b804a0a8 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/translation.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/translation.json
@@ -17,7 +17,7 @@
   {
     "EventCode": "0x2011C",
     "EventName": "PM_MRK_NTF_CYC",
-    "BriefDescription": "Cycles during which the marked instruction is the oldest in the pipeline (NTF or NTC)."
+    "BriefDescription": "Cycles in which the marked instruction is the oldest in the pipeline (next-to-finish or next-to-complete)."
   },
   {
     "EventCode": "0x2E01C",
@@ -37,7 +37,7 @@
   {
     "EventCode": "0x200FE",
     "EventName": "PM_DATA_FROM_L2MISS",
-    "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1 or L2 due to a demand miss."
+    "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L2 due to a demand miss."
   },
   {
     "EventCode": "0x30010",
@@ -52,6 +52,6 @@
   {
     "EventCode": "0x4D05C",
     "EventName": "PM_DPP_FLOP_CMPL",
-    "BriefDescription": "Double-Precision or Quad-Precision instructions completed."
+    "BriefDescription": "Double-Precision or Quad-Precision instruction completed."
   }
 ]

From e104df97b8dcfbab2e42de634b99bf03f0805d85 Mon Sep 17 00:00:00 2001
From: Kajol Jain <kjain@linux.ibm.com>
Date: Mon, 14 Aug 2023 16:57:58 +0530
Subject: [PATCH 0446/1189] perf vendor events: Drop some of the JSON/events
 for power10 platform

Drop some of the JSON/events for power10 platform due to counter
data mismatch.

Fixes: 32daa5d7899e0343 ("perf vendor events: Initial JSON/events list for power10 platform")
Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Disha Goel <disgoel@linux.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230814112803.1508296-2-kjain@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../arch/powerpc/power10/floating_point.json           |  7 -------
 tools/perf/pmu-events/arch/powerpc/power10/marked.json | 10 ----------
 tools/perf/pmu-events/arch/powerpc/power10/others.json |  5 -----
 .../perf/pmu-events/arch/powerpc/power10/pipeline.json | 10 ----------
 .../pmu-events/arch/powerpc/power10/translation.json   |  5 -----
 5 files changed, 37 deletions(-)
 delete mode 100644 tools/perf/pmu-events/arch/powerpc/power10/floating_point.json

diff --git a/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json b/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json
deleted file mode 100644
index 54acb55e2c8c..000000000000
--- a/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json
+++ /dev/null
@@ -1,7 +0,0 @@
-[
-  {
-    "EventCode": "0x4016E",
-    "EventName": "PM_THRESH_NOT_MET",
-    "BriefDescription": "Threshold counter did not meet threshold."
-  }
-]
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/marked.json b/tools/perf/pmu-events/arch/powerpc/power10/marked.json
index 131f8d0e8831..f2436fc5537c 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/marked.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/marked.json
@@ -19,11 +19,6 @@
     "EventName": "PM_MRK_BR_TAKEN_CMPL",
     "BriefDescription": "Marked Branch Taken instruction completed."
   },
-  {
-    "EventCode": "0x20112",
-    "EventName": "PM_MRK_NTF_FIN",
-    "BriefDescription": "The marked instruction became the oldest in the pipeline before it finished. It excludes instructions that finish at dispatch."
-  },
   {
     "EventCode": "0x2C01C",
     "EventName": "PM_EXEC_STALL_DMISS_OFF_CHIP",
@@ -64,11 +59,6 @@
     "EventName": "PM_L1_ICACHE_MISS",
     "BriefDescription": "Demand instruction cache miss."
   },
-  {
-    "EventCode": "0x30130",
-    "EventName": "PM_MRK_INST_FIN",
-    "BriefDescription": "marked instruction finished. Excludes instructions that finish at dispatch. Note that stores always finish twice since the address gets issued to the LSU and the data gets issued to the VSU."
-  },
   {
     "EventCode": "0x34146",
     "EventName": "PM_MRK_LD_CMPL",
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/others.json b/tools/perf/pmu-events/arch/powerpc/power10/others.json
index a5319cdba89b..17c5424ef1ac 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/others.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/others.json
@@ -29,11 +29,6 @@
     "EventName": "PM_DISP_SS0_2_INSTR_CYC",
     "BriefDescription": "Cycles in which Superslice 0 dispatches either 1 or 2 instructions."
   },
-  {
-    "EventCode": "0x1F15C",
-    "EventName": "PM_MRK_STCX_L2_CYC",
-    "BriefDescription": "Cycles spent in the nest portion of a marked Stcx instruction. It starts counting when the operation starts to drain to the L2 and it stops counting when the instruction retires from the Instruction Completion Table (ICT) in the Instruction Sequencing Unit (ISU)."
-  },
   {
     "EventCode": "0x10066",
     "EventName": "PM_ADJUNCT_CYC",
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json b/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json
index 449f57e8ba6a..799893c56f32 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json
@@ -194,11 +194,6 @@
     "EventName": "PM_TLBIE_FIN",
     "BriefDescription": "TLBIE instruction finished in the LSU. Two TLBIEs can finish each cycle. All will be counted."
   },
-  {
-    "EventCode": "0x3D058",
-    "EventName": "PM_SCALAR_FSQRT_FDIV_ISSUE",
-    "BriefDescription": "Scalar versions of four floating point operations: fdiv,fsqrt (xvdivdp, xvdivsp, xvsqrtdp, xvsqrtsp)."
-  },
   {
     "EventCode": "0x30066",
     "EventName": "PM_LSU_FIN",
@@ -269,11 +264,6 @@
     "EventName": "PM_IC_MISS_CMPL",
     "BriefDescription": "Non-speculative instruction cache miss, counted at completion."
   },
-  {
-    "EventCode": "0x4D050",
-    "EventName": "PM_VSU_NON_FLOP_CMPL",
-    "BriefDescription": "Non-floating point VSU instructions completed."
-  },
   {
     "EventCode": "0x4D052",
     "EventName": "PM_2FLOP_CMPL",
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/translation.json b/tools/perf/pmu-events/arch/powerpc/power10/translation.json
index 3e47b804a0a8..961e2491e73f 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/translation.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/translation.json
@@ -4,11 +4,6 @@
     "EventName": "PM_MRK_START_PROBE_NOP_CMPL",
     "BriefDescription": "Marked Start probe nop (AND R0,R0,R0) completed."
   },
-  {
-    "EventCode": "0x20016",
-    "EventName": "PM_ST_FIN",
-    "BriefDescription": "Store finish count. Includes speculative activity."
-  },
   {
     "EventCode": "0x20018",
     "EventName": "PM_ST_FWD",

From 4836b9a85ef148c7c9779b66fab3f7279e488d90 Mon Sep 17 00:00:00 2001
From: Kajol Jain <kjain@linux.ibm.com>
Date: Mon, 14 Aug 2023 16:57:59 +0530
Subject: [PATCH 0447/1189] perf vendor events: Drop STORES_PER_INST metric
 event for power10 platform

Drop STORES_PER_INST metric event for the power10 platform, as the
metric expression of STORES_PER_INST metric event using dropped event
PM_ST_FIN.

Fixes: 3ca3af7d1f230d1f ("perf vendor events power10: Add metric events JSON file for power10 platform")
Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Disha Goel <disgoel@linux.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230814112803.1508296-3-kjain@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/arch/powerpc/power10/metrics.json | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/tools/perf/pmu-events/arch/powerpc/power10/metrics.json b/tools/perf/pmu-events/arch/powerpc/power10/metrics.json
index 6f53583a0c62..e3087eb1ccff 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/metrics.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/metrics.json
@@ -453,12 +453,6 @@
         "MetricGroup": "General",
         "MetricName": "LOADS_PER_INST"
     },
-    {
-        "BriefDescription": "Average number of finished stores per completed instruction",
-        "MetricExpr": "PM_ST_FIN / PM_RUN_INST_CMPL",
-        "MetricGroup": "General",
-        "MetricName": "STORES_PER_INST"
-    },
     {
         "BriefDescription": "Percentage of demand loads that reloaded from beyond the L2 per completed instruction",
         "MetricExpr": "PM_DATA_FROM_L2MISS / PM_RUN_INST_CMPL * 100",

From 7d473f475b2aff7e7c5d63b6f701c54590f84781 Mon Sep 17 00:00:00 2001
From: Kajol Jain <kjain@linux.ibm.com>
Date: Mon, 14 Aug 2023 16:58:00 +0530
Subject: [PATCH 0448/1189] perf vendor events: Move JSON/events to appropriate
 files for power10 platform

Move some of the power10 JSON/events to appropriate files.

Fixes: 32daa5d7899e0343 ("perf vendor events: Initial JSON/events list for power10 platform")
Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Disha Goel <disgoel@linux.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230814112803.1508296-4-kjain@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../arch/powerpc/power10/cache.json           |  45 ----
 .../arch/powerpc/power10/floating_point.json  |  67 +++++
 .../arch/powerpc/power10/frontend.json        | 180 -------------
 .../arch/powerpc/power10/marked.json          | 186 ++++++++++---
 .../arch/powerpc/power10/memory.json          |  85 ------
 .../arch/powerpc/power10/others.json          | 192 ++------------
 .../arch/powerpc/power10/pipeline.json        | 249 ++++++++++++++----
 .../pmu-events/arch/powerpc/power10/pmc.json  | 193 +++++++++++++-
 .../arch/powerpc/power10/translation.json     |  35 ---
 9 files changed, 617 insertions(+), 615 deletions(-)
 create mode 100644 tools/perf/pmu-events/arch/powerpc/power10/floating_point.json

diff --git a/tools/perf/pmu-events/arch/powerpc/power10/cache.json b/tools/perf/pmu-events/arch/powerpc/power10/cache.json
index 9cb929bb64af..839ae26945fb 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/cache.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/cache.json
@@ -1,54 +1,9 @@
 [
-  {
-    "EventCode": "0x1003C",
-    "EventName": "PM_EXEC_STALL_DMISS_L2L3",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from either the local L2 or local L3."
-  },
-  {
-    "EventCode": "0x1E054",
-    "EventName": "PM_EXEC_STALL_DMISS_L21_L31",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from another core's L2 or L3 on the same chip."
-  },
-  {
-    "EventCode": "0x34054",
-    "EventName": "PM_EXEC_STALL_DMISS_L2L3_NOCONFLICT",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local L2 or local L3, without a dispatch conflict."
-  },
-  {
-    "EventCode": "0x34056",
-    "EventName": "PM_EXEC_STALL_LOAD_FINISH",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was finishing a load after its data was reloaded from a data source beyond the local L1; cycles in which the LSU was processing an L1-hit; cycles in which the next-to-finish (NTF) instruction merged with another load in the LMQ; cycles in which the NTF instruction is waiting for a data reload for a load miss, but the data comes back with a non-NTF instruction."
-  },
-  {
-    "EventCode": "0x3006C",
-    "EventName": "PM_RUN_CYC_SMT2_MODE",
-    "BriefDescription": "Cycles when this thread's run latch is set and the core is in SMT2 mode."
-  },
   {
     "EventCode": "0x300F4",
     "EventName": "PM_RUN_INST_CMPL_CONC",
     "BriefDescription": "PowerPC instruction completed by this thread when all threads in the core had the run-latch set."
   },
-  {
-    "EventCode": "0x4C016",
-    "EventName": "PM_EXEC_STALL_DMISS_L2L3_CONFLICT",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local L2 or local L3, with a dispatch conflict."
-  },
-  {
-    "EventCode": "0x4D014",
-    "EventName": "PM_EXEC_STALL_LOAD",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a load instruction executing in the Load Store Unit."
-  },
-  {
-    "EventCode": "0x4D016",
-    "EventName": "PM_EXEC_STALL_PTESYNC",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a PTESYNC instruction executing in the Load Store Unit."
-  },
-  {
-    "EventCode": "0x401EA",
-    "EventName": "PM_THRESH_EXC_128",
-    "BriefDescription": "Threshold counter exceeded a value of 128."
-  },
   {
     "EventCode": "0x400F6",
     "EventName": "PM_BR_MPRED_CMPL",
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json b/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json
new file mode 100644
index 000000000000..e816cd10c129
--- /dev/null
+++ b/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json
@@ -0,0 +1,67 @@
+[
+  {
+    "EventCode": "0x100F4",
+    "EventName": "PM_FLOP_CMPL",
+    "BriefDescription": "Floating Point Operations Completed. Includes any type. It counts once for each 1, 2, 4 or 8 flop instruction. Use PM_1|2|4|8_FLOP_CMPL events to count flops."
+  },
+  {
+    "EventCode": "0x45050",
+    "EventName": "PM_1FLOP_CMPL",
+    "BriefDescription": "One floating point instruction completed (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg)."
+  },
+  {
+    "EventCode": "0x45052",
+    "EventName": "PM_4FLOP_CMPL",
+    "BriefDescription": "Four floating point instruction completed (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg)."
+  },
+  {
+    "EventCode": "0x45054",
+    "EventName": "PM_FMA_CMPL",
+    "BriefDescription": "Two floating point instruction completed (FMA class of instructions: fmadd, fnmadd, fmsub, fnmsub). Scalar instructions only."
+  },
+  {
+    "EventCode": "0x45056",
+    "EventName": "PM_SCALAR_FLOP_CMPL",
+    "BriefDescription": "Scalar floating point instruction completed."
+  },
+  {
+    "EventCode": "0x4505A",
+    "EventName": "PM_SP_FLOP_CMPL",
+    "BriefDescription": "Single Precision floating point instruction completed."
+  },
+  {
+    "EventCode": "0x4505C",
+    "EventName": "PM_MATH_FLOP_CMPL",
+    "BriefDescription": "Math floating point instruction completed."
+  },
+  {
+    "EventCode": "0x4D052",
+    "EventName": "PM_2FLOP_CMPL",
+    "BriefDescription": "Double Precision vector version of fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg completed."
+  },
+  {
+    "EventCode": "0x4D054",
+    "EventName": "PM_8FLOP_CMPL",
+    "BriefDescription": "Four Double Precision vector instruction completed."
+  },
+  {
+    "EventCode": "0x4D056",
+    "EventName": "PM_NON_FMA_FLOP_CMPL",
+    "BriefDescription": "Non FMA instruction completed."
+  },
+  {
+    "EventCode": "0x4D058",
+    "EventName": "PM_VECTOR_FLOP_CMPL",
+    "BriefDescription": "Vector floating point instruction completed."
+  },
+  {
+    "EventCode": "0x4D05A",
+    "EventName": "PM_NON_MATH_FLOP_CMPL",
+    "BriefDescription": "Non Math instruction completed."
+  },
+  {
+    "EventCode": "0x4D05C",
+    "EventName": "PM_DPP_FLOP_CMPL",
+    "BriefDescription": "Double-Precision or Quad-Precision instruction completed."
+  }
+]
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/frontend.json b/tools/perf/pmu-events/arch/powerpc/power10/frontend.json
index 61e9e0222c87..dc0bb6c6338b 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/frontend.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/frontend.json
@@ -1,64 +1,9 @@
 [
-  {
-    "EventCode": "0x10004",
-    "EventName": "PM_EXEC_STALL_TRANSLATION",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline suffered a TLB miss or ERAT miss and waited for it to resolve."
-  },
-  {
-    "EventCode": "0x10006",
-    "EventName": "PM_DISP_STALL_HELD_OTHER_CYC",
-    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch for any other reason."
-  },
-  {
-    "EventCode": "0x10010",
-    "EventName": "PM_PMC4_OVERFLOW",
-    "BriefDescription": "The event selected for PMC4 caused the event counter to overflow."
-  },
-  {
-    "EventCode": "0x10020",
-    "EventName": "PM_PMC4_REWIND",
-    "BriefDescription": "The speculative event selected for PMC4 rewinds and the counter for PMC4 is not charged."
-  },
-  {
-    "EventCode": "0x10038",
-    "EventName": "PM_DISP_STALL_TRANSLATION",
-    "BriefDescription": "Cycles when dispatch was stalled for this thread because the MMU was handling a translation miss."
-  },
-  {
-    "EventCode": "0x1003A",
-    "EventName": "PM_DISP_STALL_BR_MPRED_IC_L2",
-    "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L2 after suffering a branch mispredict."
-  },
-  {
-    "EventCode": "0x1D05E",
-    "EventName": "PM_DISP_STALL_HELD_HALT_CYC",
-    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because of power management."
-  },
-  {
-    "EventCode": "0x1E050",
-    "EventName": "PM_DISP_STALL_HELD_STF_MAPPER_CYC",
-    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because the STF mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR."
-  },
   {
     "EventCode": "0x1F054",
     "EventName": "PM_DTLB_HIT",
     "BriefDescription": "The PTE required by the instruction was resident in the TLB (data TLB access). When MMCR1[16]=0 this event counts only demand hits. When MMCR1[16]=1 this event includes demand and prefetch. Applies to both HPT and RPT."
   },
-  {
-    "EventCode": "0x10064",
-    "EventName": "PM_DISP_STALL_IC_L2",
-    "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L2."
-  },
-  {
-    "EventCode": "0x101E8",
-    "EventName": "PM_THRESH_EXC_256",
-    "BriefDescription": "Threshold counter exceeded a count of 256."
-  },
-  {
-    "EventCode": "0x101EC",
-    "EventName": "PM_THRESH_MET",
-    "BriefDescription": "Threshold exceeded."
-  },
   {
     "EventCode": "0x100F2",
     "EventName": "PM_1PLUS_PPC_CMPL",
@@ -69,56 +14,6 @@
     "EventName": "PM_IERAT_MISS",
     "BriefDescription": "IERAT Reloaded to satisfy an IERAT miss. All page sizes are counted by this event. This event only counts instruction demand access."
   },
-  {
-    "EventCode": "0x100F8",
-    "EventName": "PM_DISP_STALL_CYC",
-    "BriefDescription": "Cycles the ICT has no itags assigned to this thread (no instructions were dispatched during these cycles)."
-  },
-  {
-    "EventCode": "0x20006",
-    "EventName": "PM_DISP_STALL_HELD_ISSQ_FULL_CYC",
-    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch due to Issue queue full. Includes issue queue and branch queue."
-  },
-  {
-    "EventCode": "0x20114",
-    "EventName": "PM_MRK_L2_RC_DISP",
-    "BriefDescription": "Marked instruction RC dispatched in L2."
-  },
-  {
-    "EventCode": "0x2C010",
-    "EventName": "PM_EXEC_STALL_LSU",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the Load Store Unit. This does not include simple fixed point instructions."
-  },
-  {
-    "EventCode": "0x2C016",
-    "EventName": "PM_DISP_STALL_IERAT_ONLY_MISS",
-    "BriefDescription": "Cycles when dispatch was stalled while waiting to resolve an instruction ERAT miss."
-  },
-  {
-    "EventCode": "0x2C01E",
-    "EventName": "PM_DISP_STALL_BR_MPRED_IC_L3",
-    "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L3 after suffering a branch mispredict."
-  },
-  {
-    "EventCode": "0x2D01A",
-    "EventName": "PM_DISP_STALL_IC_MISS",
-    "BriefDescription": "Cycles when dispatch was stalled for this thread due to an instruction cache miss."
-  },
-  {
-    "EventCode": "0x2E018",
-    "EventName": "PM_DISP_STALL_FETCH",
-    "BriefDescription": "Cycles when dispatch was stalled for this thread because Fetch was being held."
-  },
-  {
-    "EventCode": "0x2E01A",
-    "EventName": "PM_DISP_STALL_HELD_XVFC_MAPPER_CYC",
-    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because the XVFC mapper/SRB was full."
-  },
-  {
-    "EventCode": "0x2C142",
-    "EventName": "PM_MRK_XFER_FROM_SRC_PMC2",
-    "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[15:27]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
-  },
   {
     "EventCode": "0x24050",
     "EventName": "PM_IOPS_DISP",
@@ -134,11 +29,6 @@
     "EventName": "PM_BR_TAKEN_CMPL",
     "BriefDescription": "Branch Taken instruction completed."
   },
-  {
-    "EventCode": "0x30004",
-    "EventName": "PM_DISP_STALL_FLUSH",
-    "BriefDescription": "Cycles when dispatch was stalled because of a flush that happened to an instruction(s) that was not yet next-to-complete (NTC). PM_EXEC_STALL_NTC_FLUSH only includes instructions that were flushed after becoming NTC."
-  },
   {
     "EventCode": "0x3000A",
     "EventName": "PM_DISP_STALL_ITLB_MISS",
@@ -149,56 +39,16 @@
     "EventName": "PM_FLUSH_COMPLETION",
     "BriefDescription": "The instruction that was next to complete (oldest in the pipeline) did not complete because it suffered a flush."
   },
-  {
-    "EventCode": "0x30014",
-    "EventName": "PM_EXEC_STALL_STORE",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a store instruction executing in the Load Store Unit."
-  },
-  {
-    "EventCode": "0x30018",
-    "EventName": "PM_DISP_STALL_HELD_SCOREBOARD_CYC",
-    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch while waiting on the Scoreboard. This event combines VSCR and FPSCR together."
-  },
-  {
-    "EventCode": "0x30026",
-    "EventName": "PM_EXEC_STALL_STORE_MISS",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a store whose cache line was not resident in the L1 and was waiting for allocation of the missing line into the L1."
-  },
-  {
-    "EventCode": "0x3012A",
-    "EventName": "PM_MRK_L2_RC_DONE",
-    "BriefDescription": "L2 RC machine completed the transaction for the marked instruction."
-  },
   {
     "EventCode": "0x3F046",
     "EventName": "PM_ITLB_HIT_1G",
     "BriefDescription": "Instruction TLB hit (IERAT reload) page size 1G, which implies Radix Page Table translation is in use. When MMCR1[17]=0 this event counts only for demand misses. When MMCR1[17]=1 this event includes demand misses and prefetches."
   },
-  {
-    "EventCode": "0x34058",
-    "EventName": "PM_DISP_STALL_BR_MPRED_ICMISS",
-    "BriefDescription": "Cycles when dispatch was stalled after a mispredicted branch resulted in an instruction cache miss."
-  },
-  {
-    "EventCode": "0x3D05C",
-    "EventName": "PM_DISP_STALL_HELD_RENAME_CYC",
-    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because the mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR and XVFC."
-  },
-  {
-    "EventCode": "0x3E052",
-    "EventName": "PM_DISP_STALL_IC_L3",
-    "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L3."
-  },
   {
     "EventCode": "0x3E054",
     "EventName": "PM_LD_MISS_L1",
     "BriefDescription": "Load missed L1, counted at finish time. LMQ merges are not included in this count. i.e. if a load instruction misses on an address that is already allocated on the LMQ, this event will not increment for that load). Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load."
   },
-  {
-    "EventCode": "0x301EA",
-    "EventName": "PM_THRESH_EXC_1024",
-    "BriefDescription": "Threshold counter exceeded a value of 1024."
-  },
   {
     "EventCode": "0x300FA",
     "EventName": "PM_INST_FROM_L3MISS",
@@ -209,36 +59,6 @@
     "EventName": "PM_ISSUE_KILL",
     "BriefDescription": "Cycles in which an instruction or group of instructions were cancelled after being issued. This event increments once per occurrence, regardless of how many instructions are included in the issue group."
   },
-  {
-    "EventCode": "0x40116",
-    "EventName": "PM_MRK_LARX_FIN",
-    "BriefDescription": "Marked load and reserve instruction (LARX) finished. LARX and STCX are instructions used to acquire a lock."
-  },
-  {
-    "EventCode": "0x4C010",
-    "EventName": "PM_DISP_STALL_BR_MPRED_IC_L3MISS",
-    "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from sources beyond the local L3 after suffering a mispredicted branch."
-  },
-  {
-    "EventCode": "0x4D01E",
-    "EventName": "PM_DISP_STALL_BR_MPRED",
-    "BriefDescription": "Cycles when dispatch was stalled for this thread due to a mispredicted branch."
-  },
-  {
-    "EventCode": "0x4E010",
-    "EventName": "PM_DISP_STALL_IC_L3MISS",
-    "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from any source beyond the local L3."
-  },
-  {
-    "EventCode": "0x4E01A",
-    "EventName": "PM_DISP_STALL_HELD_CYC",
-    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch for any reason."
-  },
-  {
-    "EventCode": "0x4003C",
-    "EventName": "PM_DISP_STALL_HELD_SYNC_CYC",
-    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because of a synchronizing instruction that requires the ICT to be empty before dispatch."
-  },
   {
     "EventCode": "0x44056",
     "EventName": "PM_VECTOR_ST_CMPL",
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/marked.json b/tools/perf/pmu-events/arch/powerpc/power10/marked.json
index f2436fc5537c..913b6515b870 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/marked.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/marked.json
@@ -1,14 +1,29 @@
 [
-  {
-    "EventCode": "0x1002C",
-    "EventName": "PM_LD_PREFETCH_CACHE_LINE_MISS",
-    "BriefDescription": "The L1 cache was reloaded with a line that fulfills a prefetch request."
-  },
   {
     "EventCode": "0x10132",
     "EventName": "PM_MRK_INST_ISSUED",
     "BriefDescription": "Marked instruction issued. Note that stores always get issued twice, the address gets issued to the LSU and the data gets issued to the VSU. Also, issues can sometimes get killed/cancelled and cause multiple sequential issues for the same instruction."
   },
+  {
+    "EventCode": "0x10134",
+    "EventName": "PM_MRK_ST_DONE_L2",
+    "BriefDescription": "Marked store completed in L2."
+  },
+  {
+    "EventCode": "0x1C142",
+    "EventName": "PM_MRK_XFER_FROM_SRC_PMC1",
+    "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[0:12]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
+  },
+  {
+    "EventCode": "0x1C144",
+    "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC1",
+    "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[0:12]."
+  },
+  {
+    "EventCode": "0x1F150",
+    "EventName": "PM_MRK_ST_L2_CYC",
+    "BriefDescription": "Cycles from L2 RC dispatch to L2 RC completion."
+  },
   {
     "EventCode": "0x101E0",
     "EventName": "PM_MRK_INST_DISP",
@@ -20,9 +35,39 @@
     "BriefDescription": "Marked Branch Taken instruction completed."
   },
   {
-    "EventCode": "0x2C01C",
-    "EventName": "PM_EXEC_STALL_DMISS_OFF_CHIP",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from a remote chip."
+    "EventCode": "0x101E4",
+    "EventName": "PM_MRK_L1_ICACHE_MISS",
+    "BriefDescription": "Marked instruction suffered an instruction cache miss."
+  },
+  {
+    "EventCode": "0x101EA",
+    "EventName": "PM_MRK_L1_RELOAD_VALID",
+    "BriefDescription": "Marked demand reload."
+  },
+  {
+    "EventCode": "0x20114",
+    "EventName": "PM_MRK_L2_RC_DISP",
+    "BriefDescription": "Marked instruction RC dispatched in L2."
+  },
+  {
+    "EventCode": "0x2011C",
+    "EventName": "PM_MRK_NTF_CYC",
+    "BriefDescription": "Cycles in which the marked instruction is the oldest in the pipeline (next-to-finish or next-to-complete)."
+  },
+  {
+    "EventCode": "0x20130",
+    "EventName": "PM_MRK_INST_DECODED",
+    "BriefDescription": "An instruction was marked at decode time. Random Instruction Sampling (RIS) only."
+  },
+  {
+    "EventCode": "0x20132",
+    "EventName": "PM_MRK_DFU_ISSUE",
+    "BriefDescription": "The marked instruction was a decimal floating point operation issued to the VSU. Measured at issue time."
+  },
+  {
+    "EventCode": "0x20134",
+    "EventName": "PM_MRK_FXU_ISSUE",
+    "BriefDescription": "The marked instruction was a fixed point operation issued to the VSU. Measured at issue time."
   },
   {
     "EventCode": "0x20138",
@@ -34,6 +79,16 @@
     "EventName": "PM_MRK_BRU_FIN",
     "BriefDescription": "Marked Branch instruction finished."
   },
+  {
+    "EventCode": "0x2013C",
+    "EventName": "PM_MRK_FX_LSU_FIN",
+    "BriefDescription": "The marked instruction was simple fixed point that was issued to the store unit. Measured at finish time."
+  },
+  {
+    "EventCode": "0x2C142",
+    "EventName": "PM_MRK_XFER_FROM_SRC_PMC2",
+    "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[15:27]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
+  },
   {
     "EventCode": "0x2C144",
     "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC2",
@@ -55,15 +110,50 @@
     "BriefDescription": "A marked branch completed. All branches are included."
   },
   {
-    "EventCode": "0x200FD",
-    "EventName": "PM_L1_ICACHE_MISS",
-    "BriefDescription": "Demand instruction cache miss."
+    "EventCode": "0x2D154",
+    "EventName": "PM_MRK_DERAT_MISS_64K",
+    "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 64K for a marked instruction. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
+  },
+  {
+    "EventCode": "0x201E0",
+    "EventName": "PM_MRK_DATA_FROM_MEMORY",
+    "BriefDescription": "The processor's data cache was reloaded from local, remote, or distant memory due to a demand miss for a marked load."
+  },
+  {
+    "EventCode": "0x201E2",
+    "EventName": "PM_MRK_LD_MISS_L1",
+    "BriefDescription": "Marked demand data load miss counted at finish time."
+  },
+  {
+    "EventCode": "0x201E4",
+    "EventName": "PM_MRK_DATA_FROM_L3MISS",
+    "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss for a marked load."
+  },
+  {
+    "EventCode": "0x3012A",
+    "EventName": "PM_MRK_L2_RC_DONE",
+    "BriefDescription": "L2 RC machine completed the transaction for the marked instruction."
+  },
+  {
+    "EventCode": "0x30132",
+    "EventName": "PM_MRK_VSU_FIN",
+    "BriefDescription": "VSU marked instruction finished. Excludes simple FX instructions issued to the Store Unit."
   },
   {
     "EventCode": "0x34146",
     "EventName": "PM_MRK_LD_CMPL",
     "BriefDescription": "Marked load instruction completed."
   },
+  {
+    "EventCode": "0x3C142",
+    "EventName": "PM_MRK_XFER_FROM_SRC_PMC3",
+    "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[30:42]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
+  },
+  {
+    "EventCode": "0x3C144",
+    "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC3",
+    "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[30:42]."
+  },
   {
     "EventCode": "0x3E158",
     "EventName": "PM_MRK_STCX_FAIL",
@@ -75,9 +165,19 @@
     "BriefDescription": "Marked store instruction finished."
   },
   {
-    "EventCode": "0x30068",
-    "EventName": "PM_L1_ICACHE_RELOADED_PREF",
-    "BriefDescription": "Counts all instruction cache prefetch reloads (includes demand turned into prefetch)."
+    "EventCode": "0x3F150",
+    "EventName": "PM_MRK_ST_DRAIN_CYC",
+    "BriefDescription": "Cycles in which the marked store drained from the core to the L2."
+  },
+  {
+    "EventCode": "0x30162",
+    "EventName": "PM_MRK_ISSUE_DEPENDENT_LOAD",
+    "BriefDescription": "The marked instruction was dependent on a load. It is eligible for issue kill."
+  },
+  {
+    "EventCode": "0x301E2",
+    "EventName": "PM_MRK_ST_CMPL",
+    "BriefDescription": "Marked store completed and sent to nest. Note that this count excludes cache-inhibited stores."
   },
   {
     "EventCode": "0x301E4",
@@ -85,39 +185,44 @@
     "BriefDescription": "Marked Branch Mispredicted. Includes direction and target."
   },
   {
-    "EventCode": "0x300F6",
-    "EventName": "PM_LD_DEMAND_MISS_L1",
-    "BriefDescription": "The L1 cache was reloaded with a line that fulfills a demand miss request. Counted at reload time, before finish."
+    "EventCode": "0x40116",
+    "EventName": "PM_MRK_LARX_FIN",
+    "BriefDescription": "Marked load and reserve instruction (LARX) finished. LARX and STCX are instructions used to acquire a lock."
   },
   {
-    "EventCode": "0x300FE",
-    "EventName": "PM_DATA_FROM_L3MISS",
-    "BriefDescription": "The processor's L1 data cache was reloaded from beyond the local core's L3 due to a demand miss."
+    "EventCode": "0x40132",
+    "EventName": "PM_MRK_LSU_FIN",
+    "BriefDescription": "LSU marked instruction finish."
   },
   {
-    "EventCode": "0x40012",
-    "EventName": "PM_L1_ICACHE_RELOADED_ALL",
-    "BriefDescription": "Counts all instruction cache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch."
+    "EventCode": "0x44146",
+    "EventName": "PM_MRK_STCX_CORE_CYC",
+    "BriefDescription": "Cycles spent in the core portion of a marked STCX instruction. It starts counting when the instruction is decoded and stops counting when it drains into the L2."
   },
   {
-    "EventCode": "0x40134",
-    "EventName": "PM_MRK_INST_TIMEO",
-    "BriefDescription": "Marked instruction finish timeout (instruction was lost)."
+    "EventCode": "0x4C142",
+    "EventName": "PM_MRK_XFER_FROM_SRC_PMC4",
+    "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[45:57]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
   },
   {
-    "EventCode": "0x4505A",
-    "EventName": "PM_SP_FLOP_CMPL",
-    "BriefDescription": "Single Precision floating point instruction completed."
+    "EventCode": "0x4C144",
+    "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC4",
+    "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[45:57]."
   },
   {
-    "EventCode": "0x4D058",
-    "EventName": "PM_VECTOR_FLOP_CMPL",
-    "BriefDescription": "Vector floating point instruction completed."
+    "EventCode": "0x4C15E",
+    "EventName": "PM_MRK_DTLB_MISS_64K",
+    "BriefDescription": "Marked Data TLB reload (after a miss) page size 64K. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
   },
   {
-    "EventCode": "0x4D05A",
-    "EventName": "PM_NON_MATH_FLOP_CMPL",
-    "BriefDescription": "Non Math instruction completed."
+    "EventCode": "0x4E15E",
+    "EventName": "PM_MRK_INST_FLUSHED",
+    "BriefDescription": "The marked instruction was flushed."
+  },
+  {
+    "EventCode": "0x40164",
+    "EventName": "PM_MRK_DERAT_MISS_2M",
+    "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 2M for a marked instruction. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
   },
   {
     "EventCode": "0x401E0",
@@ -125,8 +230,13 @@
     "BriefDescription": "Marked instruction completed."
   },
   {
-    "EventCode": "0x400FE",
-    "EventName": "PM_DATA_FROM_MEMORY",
-    "BriefDescription": "The processor's data cache was reloaded from local, remote, or distant memory due to a demand miss."
+    "EventCode": "0x401E6",
+    "EventName": "PM_MRK_INST_FROM_L3MISS",
+    "BriefDescription": "The processor's instruction cache was reloaded from beyond the local core's L3 due to a demand miss for a marked instruction."
+  },
+  {
+    "EventCode": "0x401E8",
+    "EventName": "PM_MRK_DATA_FROM_L2MISS",
+    "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L2 due to a demand miss for a marked instruction."
   }
 ]
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/memory.json b/tools/perf/pmu-events/arch/powerpc/power10/memory.json
index c4c10ca98cad..b95a547a704b 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/memory.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/memory.json
@@ -1,24 +1,9 @@
 [
-  {
-    "EventCode": "0x1000A",
-    "EventName": "PM_PMC3_REWIND",
-    "BriefDescription": "The speculative event selected for PMC3 rewinds and the counter for PMC3 is not charged."
-  },
   {
     "EventCode": "0x1C040",
     "EventName": "PM_XFER_FROM_SRC_PMC1",
     "BriefDescription": "The processor's L1 data cache was reloaded from the source specified in MMCR3[0:12]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
   },
-  {
-    "EventCode": "0x1C142",
-    "EventName": "PM_MRK_XFER_FROM_SRC_PMC1",
-    "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[0:12]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
-  },
-  {
-    "EventCode": "0x1C144",
-    "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC1",
-    "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[0:12]."
-  },
   {
     "EventCode": "0x1C056",
     "EventName": "PM_DERAT_MISS_4K",
@@ -34,26 +19,11 @@
     "EventName": "PM_DTLB_MISS_2M",
     "BriefDescription": "Data TLB reload (after a miss) page size 2M. Implies radix translation was used. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
   },
-  {
-    "EventCode": "0x1E056",
-    "EventName": "PM_EXEC_STALL_STORE_PIPE",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the store unit. This does not include cycles spent handling store misses, PTESYNC instructions or TLBIE instructions."
-  },
-  {
-    "EventCode": "0x1F150",
-    "EventName": "PM_MRK_ST_L2_CYC",
-    "BriefDescription": "Cycles from L2 RC dispatch to L2 RC completion."
-  },
   {
     "EventCode": "0x10062",
     "EventName": "PM_LD_L3MISS_PEND_CYC",
     "BriefDescription": "Cycles in which an L3 miss was pending for this thread."
   },
-  {
-    "EventCode": "0x20010",
-    "EventName": "PM_PMC1_OVERFLOW",
-    "BriefDescription": "The event selected for PMC1 caused the event counter to overflow."
-  },
   {
     "EventCode": "0x2001A",
     "EventName": "PM_ITLB_HIT",
@@ -79,36 +49,16 @@
     "EventName": "PM_DTLB_MISS_4K",
     "BriefDescription": "Data TLB reload (after a miss) page size 4K. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
   },
-  {
-    "EventCode": "0x2D154",
-    "EventName": "PM_MRK_DERAT_MISS_64K",
-    "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 64K for a marked instruction. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
-  },
   {
     "EventCode": "0x200F6",
     "EventName": "PM_DERAT_MISS",
     "BriefDescription": "DERAT Reloaded to satisfy a DERAT miss. All page sizes are counted by this event. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
   },
-  {
-    "EventCode": "0x30016",
-    "EventName": "PM_EXEC_STALL_DERAT_DTLB_MISS",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline suffered a TLB miss and waited for it resolve."
-  },
   {
     "EventCode": "0x3C040",
     "EventName": "PM_XFER_FROM_SRC_PMC3",
     "BriefDescription": "The processor's L1 data cache was reloaded from the source specified in MMCR3[30:42]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
   },
-  {
-    "EventCode": "0x3C142",
-    "EventName": "PM_MRK_XFER_FROM_SRC_PMC3",
-    "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[30:42]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
-  },
-  {
-    "EventCode": "0x3C144",
-    "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC3",
-    "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[30:42]."
-  },
   {
     "EventCode": "0x3C054",
     "EventName": "PM_DERAT_MISS_16M",
@@ -124,21 +74,11 @@
     "EventName": "PM_LARX_FIN",
     "BriefDescription": "Load and reserve instruction (LARX) finished. LARX and STCX are instructions used to acquire a lock."
   },
-  {
-    "EventCode": "0x301E2",
-    "EventName": "PM_MRK_ST_CMPL",
-    "BriefDescription": "Marked store completed and sent to nest. Note that this count excludes cache-inhibited stores."
-  },
   {
     "EventCode": "0x300FC",
     "EventName": "PM_DTLB_MISS",
     "BriefDescription": "The DPTEG required for the load/store instruction in execution was missing from the TLB. This event only counts for demand misses."
   },
-  {
-    "EventCode": "0x4D02C",
-    "EventName": "PM_PMC1_REWIND",
-    "BriefDescription": "The speculative event selected for PMC1 rewinds and the counter for PMC1 is not charged."
-  },
   {
     "EventCode": "0x4003E",
     "EventName": "PM_LD_CMPL",
@@ -149,16 +89,6 @@
     "EventName": "PM_XFER_FROM_SRC_PMC4",
     "BriefDescription": "The processor's L1 data cache was reloaded from the source specified in MMCR3[45:57]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
   },
-  {
-    "EventCode": "0x4C142",
-    "EventName": "PM_MRK_XFER_FROM_SRC_PMC4",
-    "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[45:57]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
-  },
-  {
-    "EventCode": "0x4C144",
-    "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC4",
-    "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[45:57]."
-  },
   {
     "EventCode": "0x4C056",
     "EventName": "PM_DTLB_MISS_16M",
@@ -168,20 +98,5 @@
     "EventCode": "0x4C05A",
     "EventName": "PM_DTLB_MISS_1G",
     "BriefDescription": "Data TLB reload (after a miss) page size 1G. Implies radix translation was used. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
-  },
-  {
-    "EventCode": "0x4C15E",
-    "EventName": "PM_MRK_DTLB_MISS_64K",
-    "BriefDescription": "Marked Data TLB reload (after a miss) page size 64K. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
-  },
-  {
-    "EventCode": "0x4D056",
-    "EventName": "PM_NON_FMA_FLOP_CMPL",
-    "BriefDescription": "Non FMA instruction completed."
-  },
-  {
-    "EventCode": "0x40164",
-    "EventName": "PM_MRK_DERAT_MISS_2M",
-    "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 2M for a marked instruction. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
   }
 ]
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/others.json b/tools/perf/pmu-events/arch/powerpc/power10/others.json
index 17c5424ef1ac..f09c00c89322 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/others.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/others.json
@@ -1,23 +1,8 @@
 [
   {
-    "EventCode": "0x10016",
-    "EventName": "PM_VSU0_ISSUE",
-    "BriefDescription": "VSU instruction issued to VSU pipe 0."
-  },
-  {
-    "EventCode": "0x1001C",
-    "EventName": "PM_ULTRAVISOR_INST_CMPL",
-    "BriefDescription": "PowerPC instruction completed while the thread was in ultravisor state."
-  },
-  {
-    "EventCode": "0x100F0",
-    "EventName": "PM_CYC",
-    "BriefDescription": "Processor cycles."
-  },
-  {
-    "EventCode": "0x10134",
-    "EventName": "PM_MRK_ST_DONE_L2",
-    "BriefDescription": "Marked store completed in L2."
+    "EventCode": "0x1002C",
+    "EventName": "PM_LD_PREFETCH_CACHE_LINE_MISS",
+    "BriefDescription": "The L1 cache was reloaded with a line that fulfills a prefetch request."
   },
   {
     "EventCode": "0x1505E",
@@ -34,36 +19,11 @@
     "EventName": "PM_ADJUNCT_CYC",
     "BriefDescription": "Cycles in which the thread is in Adjunct state. MSR[S HV PR] bits = 011."
   },
-  {
-    "EventCode": "0x101E4",
-    "EventName": "PM_MRK_L1_ICACHE_MISS",
-    "BriefDescription": "Marked instruction suffered an instruction cache miss."
-  },
-  {
-    "EventCode": "0x101EA",
-    "EventName": "PM_MRK_L1_RELOAD_VALID",
-    "BriefDescription": "Marked demand reload."
-  },
-  {
-    "EventCode": "0x100F4",
-    "EventName": "PM_FLOP_CMPL",
-    "BriefDescription": "Floating Point Operations Completed. Includes any type. It counts once for each 1, 2, 4 or 8 flop instruction. Use PM_1|2|4|8_FLOP_CMPL events to count flops."
-  },
-  {
-    "EventCode": "0x100FA",
-    "EventName": "PM_RUN_LATCH_ANY_THREAD_CYC",
-    "BriefDescription": "Cycles when at least one thread has the run latch set."
-  },
   {
     "EventCode": "0x100FC",
     "EventName": "PM_LD_REF_L1",
     "BriefDescription": "All L1 D cache load references counted at finish, gated by reject. In P9 and earlier this event counted only cacheable loads but in P10 both cacheable and non-cacheable loads are included."
   },
-  {
-    "EventCode": "0x2000C",
-    "EventName": "PM_RUN_LATCH_ALL_THREADS_CYC",
-    "BriefDescription": "Cycles when the run latch is set for all threads."
-  },
   {
     "EventCode": "0x2E010",
     "EventName": "PM_ADJUNCT_INST_CMPL",
@@ -74,26 +34,6 @@
     "EventName": "PM_STCX_FIN",
     "BriefDescription": "Conditional store instruction (STCX) finished. LARX and STCX are instructions used to acquire a lock."
   },
-  {
-    "EventCode": "0x20130",
-    "EventName": "PM_MRK_INST_DECODED",
-    "BriefDescription": "An instruction was marked at decode time. Random Instruction Sampling (RIS) only."
-  },
-  {
-    "EventCode": "0x20132",
-    "EventName": "PM_MRK_DFU_ISSUE",
-    "BriefDescription": "The marked instruction was a decimal floating point operation issued to the VSU. Measured at issue time."
-  },
-  {
-    "EventCode": "0x20134",
-    "EventName": "PM_MRK_FXU_ISSUE",
-    "BriefDescription": "The marked instruction was a fixed point operation issued to the VSU. Measured at issue time."
-  },
-  {
-    "EventCode": "0x2505C",
-    "EventName": "PM_VSU_ISSUE",
-    "BriefDescription": "At least one VSU instruction was issued to one of the VSU pipes. Up to 4 per cycle. Includes fixed point operations."
-  },
   {
     "EventCode": "0x2F054",
     "EventName": "PM_DISP_SS1_2_INSTR_CYC",
@@ -104,40 +44,15 @@
     "EventName": "PM_DISP_SS1_4_INSTR_CYC",
     "BriefDescription": "Cycles in which Superslice 1 dispatches either 3 or 4 instructions."
   },
-  {
-    "EventCode": "0x2006C",
-    "EventName": "PM_RUN_CYC_SMT4_MODE",
-    "BriefDescription": "Cycles when this thread's run latch is set and the core is in SMT4 mode."
-  },
-  {
-    "EventCode": "0x201E0",
-    "EventName": "PM_MRK_DATA_FROM_MEMORY",
-    "BriefDescription": "The processor's data cache was reloaded from local, remote, or distant memory due to a demand miss for a marked load."
-  },
-  {
-    "EventCode": "0x201E4",
-    "EventName": "PM_MRK_DATA_FROM_L3MISS",
-    "BriefDescription": "The processor's L1 data cache was reloaded from beyond the local core's L3 due to a demand miss for a marked instruction."
-  },
-  {
-    "EventCode": "0x201E8",
-    "EventName": "PM_THRESH_EXC_512",
-    "BriefDescription": "Threshold counter exceeded a value of 512."
-  },
   {
     "EventCode": "0x200F2",
     "EventName": "PM_INST_DISP",
     "BriefDescription": "PowerPC instruction dispatched."
   },
   {
-    "EventCode": "0x30132",
-    "EventName": "PM_MRK_VSU_FIN",
-    "BriefDescription": "VSU marked instruction finished. Excludes simple FX instructions issued to the Store Unit."
-  },
-  {
-    "EventCode": "0x30038",
-    "EventName": "PM_EXEC_STALL_DMISS_LMEM",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local memory, local OpenCAPI cache, or local OpenCAPI memory."
+    "EventCode": "0x200FD",
+    "EventName": "PM_L1_ICACHE_MISS",
+    "BriefDescription": "Demand instruction cache miss."
   },
   {
     "EventCode": "0x3F04A",
@@ -149,11 +64,6 @@
     "EventName": "PM_PRIVILEGED_INST_CMPL",
     "BriefDescription": "PowerPC instruction completed while the thread was in Privileged state."
   },
-  {
-    "EventCode": "0x3F150",
-    "EventName": "PM_MRK_ST_DRAIN_CYC",
-    "BriefDescription": "Cycles in which the marked store drained from the core to the L2."
-  },
   {
     "EventCode": "0x3F054",
     "EventName": "PM_DISP_SS0_4_INSTR_CYC",
@@ -165,103 +75,43 @@
     "BriefDescription": "Cycles in which Superslice 0 dispatches either 5, 6, 7 or 8 instructions."
   },
   {
-    "EventCode": "0x30162",
-    "EventName": "PM_MRK_ISSUE_DEPENDENT_LOAD",
-    "BriefDescription": "The marked instruction was dependent on a load. It is eligible for issue kill."
+    "EventCode": "0x30068",
+    "EventName": "PM_L1_ICACHE_RELOADED_PREF",
+    "BriefDescription": "Counts all instruction cache prefetch reloads (includes demand turned into prefetch)."
   },
   {
-    "EventCode": "0x40114",
-    "EventName": "PM_MRK_START_PROBE_NOP_DISP",
-    "BriefDescription": "Marked Start probe nop dispatched. Instruction AND R0,R0,R0."
+    "EventCode": "0x300F6",
+    "EventName": "PM_LD_DEMAND_MISS_L1",
+    "BriefDescription": "The L1 cache was reloaded with a line that fulfills a demand miss request. Counted at reload time, before finish."
   },
   {
-    "EventCode": "0x4001C",
-    "EventName": "PM_VSU_FIN",
-    "BriefDescription": "VSU instruction finished."
+    "EventCode": "0x300FE",
+    "EventName": "PM_DATA_FROM_L3MISS",
+    "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss."
   },
   {
-    "EventCode": "0x4C01A",
-    "EventName": "PM_EXEC_STALL_DMISS_OFF_NODE",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from a distant chip."
-  },
-  {
-    "EventCode": "0x4D012",
-    "EventName": "PM_PMC3_SAVED",
-    "BriefDescription": "The conditions for the speculative event selected for PMC3 are met and PMC3 is charged."
-  },
-  {
-    "EventCode": "0x4D022",
-    "EventName": "PM_HYPERVISOR_INST_CMPL",
-    "BriefDescription": "PowerPC instruction completed while the thread was in hypervisor state."
-  },
-  {
-    "EventCode": "0x4D026",
-    "EventName": "PM_ULTRAVISOR_CYC",
-    "BriefDescription": "Cycles when the thread is in Ultravisor state. MSR[S HV PR]=110."
-  },
-  {
-    "EventCode": "0x4D028",
-    "EventName": "PM_PRIVILEGED_CYC",
-    "BriefDescription": "Cycles when the thread is in Privileged state. MSR[S HV PR]=x00."
-  },
-  {
-    "EventCode": "0x40030",
-    "EventName": "PM_INST_FIN",
-    "BriefDescription": "Instruction finished."
-  },
-  {
-    "EventCode": "0x44146",
-    "EventName": "PM_MRK_STCX_CORE_CYC",
-    "BriefDescription": "Cycles spent in the core portion of a marked STCX instruction. It starts counting when the instruction is decoded and stops counting when it drains into the L2."
+    "EventCode": "0x40012",
+    "EventName": "PM_L1_ICACHE_RELOADED_ALL",
+    "BriefDescription": "Counts all instruction cache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch."
   },
   {
     "EventCode": "0x44054",
     "EventName": "PM_VECTOR_LD_CMPL",
     "BriefDescription": "Vector load instruction completed."
   },
-  {
-    "EventCode": "0x45054",
-    "EventName": "PM_FMA_CMPL",
-    "BriefDescription": "Two floating point instruction completed (FMA class of instructions: fmadd, fnmadd, fmsub, fnmsub). Scalar instructions only."
-  },
-  {
-    "EventCode": "0x45056",
-    "EventName": "PM_SCALAR_FLOP_CMPL",
-    "BriefDescription": "Scalar floating point instruction completed."
-  },
-  {
-    "EventCode": "0x4505C",
-    "EventName": "PM_MATH_FLOP_CMPL",
-    "BriefDescription": "Math floating point instruction completed."
-  },
   {
     "EventCode": "0x4D05E",
     "EventName": "PM_BR_CMPL",
     "BriefDescription": "A branch completed. All branches are included."
   },
-  {
-    "EventCode": "0x4E15E",
-    "EventName": "PM_MRK_INST_FLUSHED",
-    "BriefDescription": "The marked instruction was flushed."
-  },
-  {
-    "EventCode": "0x401E6",
-    "EventName": "PM_MRK_INST_FROM_L3MISS",
-    "BriefDescription": "The processor's instruction cache was reloaded from beyond the local core's L3 due to a demand miss for a marked instruction."
-  },
-  {
-    "EventCode": "0x401E8",
-    "EventName": "PM_MRK_DATA_FROM_L2MISS",
-    "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L2 due to a demand miss for a marked instruction."
-  },
   {
     "EventCode": "0x400F0",
     "EventName": "PM_LD_DEMAND_MISS_L1_FIN",
     "BriefDescription": "Load missed L1, counted at finish time."
   },
   {
-    "EventCode": "0x500FA",
-    "EventName": "PM_RUN_INST_CMPL",
-    "BriefDescription": "PowerPC instruction completed while the run latch is set."
+    "EventCode": "0x400FE",
+    "EventName": "PM_DATA_FROM_MEMORY",
+    "BriefDescription": "The processor's data cache was reloaded from local, remote, or distant memory due to a demand miss."
   }
 ]
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json b/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json
index 799893c56f32..a8272a2f0517 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json
@@ -1,8 +1,13 @@
 [
   {
-    "EventCode": "0x100FE",
-    "EventName": "PM_INST_CMPL",
-    "BriefDescription": "PowerPC instruction completed."
+    "EventCode": "0x10004",
+    "EventName": "PM_EXEC_STALL_TRANSLATION",
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline suffered a TLB miss or ERAT miss and waited for it to resolve."
+  },
+  {
+    "EventCode": "0x10006",
+    "EventName": "PM_DISP_STALL_HELD_OTHER_CYC",
+    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch for any other reason."
   },
   {
     "EventCode": "0x1000C",
@@ -30,14 +35,19 @@
     "BriefDescription": "Cycles in which an instruction reload is pending to satisfy a demand miss."
   },
   {
-    "EventCode": "0x10022",
-    "EventName": "PM_PMC2_SAVED",
-    "BriefDescription": "The conditions for the speculative event selected for PMC2 are met and PMC2 is charged."
+    "EventCode": "0x10038",
+    "EventName": "PM_DISP_STALL_TRANSLATION",
+    "BriefDescription": "Cycles when dispatch was stalled for this thread because the MMU was handling a translation miss."
   },
   {
-    "EventCode": "0x10024",
-    "EventName": "PM_PMC5_OVERFLOW",
-    "BriefDescription": "The event selected for PMC5 caused the event counter to overflow."
+    "EventCode": "0x1003A",
+    "EventName": "PM_DISP_STALL_BR_MPRED_IC_L2",
+    "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L2 after suffering a branch mispredict."
+  },
+  {
+    "EventCode": "0x1003C",
+    "EventName": "PM_EXEC_STALL_DMISS_L2L3",
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from either the local L2 or local L3."
   },
   {
     "EventCode": "0x10058",
@@ -54,11 +64,36 @@
     "EventName": "PM_DERAT_MISS_2M",
     "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 2M. Implies radix translation. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
   },
+  {
+    "EventCode": "0x1D05E",
+    "EventName": "PM_DISP_STALL_HELD_HALT_CYC",
+    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because of power management."
+  },
+  {
+    "EventCode": "0x1E050",
+    "EventName": "PM_DISP_STALL_HELD_STF_MAPPER_CYC",
+    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because the STF mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR."
+  },
+  {
+    "EventCode": "0x1E054",
+    "EventName": "PM_EXEC_STALL_DMISS_L21_L31",
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from another core's L2 or L3 on the same chip."
+  },
+  {
+    "EventCode": "0x1E056",
+    "EventName": "PM_EXEC_STALL_STORE_PIPE",
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the store unit. This does not include cycles spent handling store misses, PTESYNC instructions or TLBIE instructions."
+  },
   {
     "EventCode": "0x1E05A",
     "EventName": "PM_CMPL_STALL_LWSYNC",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a lwsync waiting to complete."
   },
+  {
+    "EventCode": "0x10064",
+    "EventName": "PM_DISP_STALL_IC_L2",
+    "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L2."
+  },
   {
     "EventCode": "0x10068",
     "EventName": "PM_BR_FIN",
@@ -70,9 +105,9 @@
     "BriefDescription": "Simple fixed point instruction issued to the store unit. Measured at finish time."
   },
   {
-    "EventCode": "0x1006C",
-    "EventName": "PM_RUN_CYC_ST_MODE",
-    "BriefDescription": "Cycles when the run latch is set and the core is in ST mode."
+    "EventCode": "0x100F8",
+    "EventName": "PM_DISP_STALL_CYC",
+    "BriefDescription": "Cycles the ICT has no itags assigned to this thread (no instructions were dispatched during these cycles)."
   },
   {
     "EventCode": "0x20004",
@@ -80,94 +115,144 @@
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was dispatched but not issued yet."
   },
   {
-    "EventCode": "0x2000A",
-    "EventName": "PM_HYPERVISOR_CYC",
-    "BriefDescription": "Cycles when the thread is in Hypervisor state. MSR[S HV PR]=010."
+    "EventCode": "0x20006",
+    "EventName": "PM_DISP_STALL_HELD_ISSQ_FULL_CYC",
+    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch due to Issue queue full. Includes issue queue and branch queue."
   },
   {
     "EventCode": "0x2000E",
     "EventName": "PM_LSU_LD1_FIN",
     "BriefDescription": "LSU Finished an internal operation in LD1 port."
   },
+  {
+    "EventCode": "0x2C010",
+    "EventName": "PM_EXEC_STALL_LSU",
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the Load Store Unit. This does not include simple fixed point instructions."
+  },
   {
     "EventCode": "0x2C014",
     "EventName": "PM_CMPL_STALL_SPECIAL",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline required special handling before completing."
   },
+  {
+    "EventCode": "0x2C016",
+    "EventName": "PM_DISP_STALL_IERAT_ONLY_MISS",
+    "BriefDescription": "Cycles when dispatch was stalled while waiting to resolve an instruction ERAT miss."
+  },
   {
     "EventCode": "0x2C018",
     "EventName": "PM_EXEC_STALL_DMISS_L3MISS",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from a source beyond the local L2 or local L3."
   },
+  {
+    "EventCode": "0x2C01C",
+    "EventName": "PM_EXEC_STALL_DMISS_OFF_CHIP",
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from a remote chip."
+  },
+  {
+    "EventCode": "0x2C01E",
+    "EventName": "PM_DISP_STALL_BR_MPRED_IC_L3",
+    "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L3 after suffering a branch mispredict."
+  },
   {
     "EventCode": "0x2D010",
     "EventName": "PM_LSU_ST1_FIN",
     "BriefDescription": "LSU Finished an internal operation in ST1 port."
   },
+  {
+    "EventCode": "0x10016",
+    "EventName": "PM_VSU0_ISSUE",
+    "BriefDescription": "VSU instruction issued to VSU pipe 0."
+  },
   {
     "EventCode": "0x2D012",
     "EventName": "PM_VSU1_ISSUE",
     "BriefDescription": "VSU instruction issued to VSU pipe 1."
   },
+  {
+    "EventCode": "0x2505C",
+    "EventName": "PM_VSU_ISSUE",
+    "BriefDescription": "At least one VSU instruction was issued to one of the VSU pipes. Up to 4 per cycle. Includes fixed point operations."
+  },
+  {
+    "EventCode": "0x4001C",
+    "EventName": "PM_VSU_FIN",
+    "BriefDescription": "VSU instruction finished."
+  },
   {
     "EventCode": "0x2D018",
     "EventName": "PM_EXEC_STALL_VSU",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the VSU (includes FXU, VSU, CRU)."
   },
+  {
+    "EventCode": "0x2D01A",
+    "EventName": "PM_DISP_STALL_IC_MISS",
+    "BriefDescription": "Cycles when dispatch was stalled for this thread due to an instruction cache miss."
+  },
   {
     "EventCode": "0x2D01C",
     "EventName": "PM_CMPL_STALL_STCX",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a stcx waiting for resolution from the nest before completing."
   },
+  {
+    "EventCode": "0x2E018",
+    "EventName": "PM_DISP_STALL_FETCH",
+    "BriefDescription": "Cycles when dispatch was stalled for this thread because Fetch was being held."
+  },
+  {
+    "EventCode": "0x2E01A",
+    "EventName": "PM_DISP_STALL_HELD_XVFC_MAPPER_CYC",
+    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because the XVFC mapper/SRB was full."
+  },
+  {
+    "EventCode": "0x2E01C",
+    "EventName": "PM_EXEC_STALL_TLBIE",
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a TLBIE instruction executing in the Load Store Unit."
+  },
   {
     "EventCode": "0x2E01E",
     "EventName": "PM_EXEC_STALL_NTC_FLUSH",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in any unit before it was flushed. Note that if the flush of the oldest instruction happens after finish, the cycles from dispatch to issue will be included in PM_DISP_STALL and the cycles from issue to finish will be included in PM_EXEC_STALL and its corresponding children. This event will also count cycles when the previous next-to-finish (NTF) instruction is still completing and the new NTF instruction is stalled at dispatch."
   },
-  {
-    "EventCode": "0x2013C",
-    "EventName": "PM_MRK_FX_LSU_FIN",
-    "BriefDescription": "The marked instruction was simple fixed point that was issued to the store unit. Measured at finish time."
-  },
   {
     "EventCode": "0x2405A",
     "EventName": "PM_NTC_FIN",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline (NTC) finishes. Note that instructions can finish out of order, therefore not all the instructions that finish have a Next-to-complete status."
   },
   {
-    "EventCode": "0x201E2",
-    "EventName": "PM_MRK_LD_MISS_L1",
-    "BriefDescription": "Marked demand data load miss counted at finish time."
-  },
-  {
-    "EventCode": "0x200F4",
-    "EventName": "PM_RUN_CYC",
-    "BriefDescription": "Processor cycles gated by the run latch."
+    "EventCode": "0x30004",
+    "EventName": "PM_DISP_STALL_FLUSH",
+    "BriefDescription": "Cycles when dispatch was stalled because of a flush that happened to an instruction(s) that was not yet next-to-complete (NTC). PM_EXEC_STALL_NTC_FLUSH only includes instructions that were flushed after becoming NTC."
   },
   {
     "EventCode": "0x30008",
     "EventName": "PM_EXEC_STALL",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting to finish in one of the execution units (BRU, LSU, VSU). Only cycles between issue and finish are counted in this category."
   },
+  {
+    "EventCode": "0x30014",
+    "EventName": "PM_EXEC_STALL_STORE",
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a store instruction executing in the Load Store Unit."
+  },
+  {
+    "EventCode": "0x30016",
+    "EventName": "PM_EXEC_STALL_DERAT_DTLB_MISS",
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline suffered a TLB miss and waited for it resolve."
+  },
+  {
+    "EventCode": "0x30018",
+    "EventName": "PM_DISP_STALL_HELD_SCOREBOARD_CYC",
+    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch while waiting on the Scoreboard. This event combines VSCR and FPSCR together."
+  },
   {
     "EventCode": "0x3001A",
     "EventName": "PM_LSU_ST2_FIN",
     "BriefDescription": "LSU Finished an internal operation in ST2 port."
   },
   {
-    "EventCode": "0x30020",
-    "EventName": "PM_PMC2_REWIND",
-    "BriefDescription": "The speculative event selected for PMC2 rewinds and the counter for PMC2 is not charged."
-  },
-  {
-    "EventCode": "0x30022",
-    "EventName": "PM_PMC4_SAVED",
-    "BriefDescription": "The conditions for the speculative event selected for PMC4 are met and PMC4 is charged."
-  },
-  {
-    "EventCode": "0x30024",
-    "EventName": "PM_PMC6_OVERFLOW",
-    "BriefDescription": "The event selected for PMC6 caused the event counter to overflow."
+    "EventCode": "0x30026",
+    "EventName": "PM_EXEC_STALL_STORE_MISS",
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a store whose cache line was not resident in the L1 and was waiting for allocation of the missing line into the L1."
   },
   {
     "EventCode": "0x30028",
@@ -179,6 +264,11 @@
     "EventName": "PM_EXEC_STALL_SIMPLE_FX",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a simple fixed point instruction executing in the Load Store Unit."
   },
+  {
+    "EventCode": "0x30038",
+    "EventName": "PM_EXEC_STALL_DMISS_LMEM",
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local memory, local OpenCAPI cache, or local OpenCAPI memory."
+  },
   {
     "EventCode": "0x3003A",
     "EventName": "PM_CMPL_STALL_EXCEPTION",
@@ -194,6 +284,31 @@
     "EventName": "PM_TLBIE_FIN",
     "BriefDescription": "TLBIE instruction finished in the LSU. Two TLBIEs can finish each cycle. All will be counted."
   },
+  {
+    "EventCode": "0x34054",
+    "EventName": "PM_EXEC_STALL_DMISS_L2L3_NOCONFLICT",
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local L2 or local L3, without a dispatch conflict."
+  },
+  {
+    "EventCode": "0x34056",
+    "EventName": "PM_EXEC_STALL_LOAD_FINISH",
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was finishing a load after its data was reloaded from a data source beyond the local L1; cycles in which the LSU was processing an L1-hit; cycles in which the next-to-finish (NTF) instruction merged with another load in the LMQ; cycles in which the NTF instruction is waiting for a data reload for a load miss, but the data comes back with a non-NTF instruction."
+  },
+  {
+    "EventCode": "0x34058",
+    "EventName": "PM_DISP_STALL_BR_MPRED_ICMISS",
+    "BriefDescription": "Cycles when dispatch was stalled after a mispredicted branch resulted in an instruction cache miss."
+  },
+  {
+    "EventCode": "0x3D05C",
+    "EventName": "PM_DISP_STALL_HELD_RENAME_CYC",
+    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because the mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR and XVFC."
+  },
+  {
+    "EventCode": "0x3E052",
+    "EventName": "PM_DISP_STALL_IC_L3",
+    "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L3."
+  },
   {
     "EventCode": "0x30066",
     "EventName": "PM_LSU_FIN",
@@ -210,25 +325,45 @@
     "BriefDescription": "Cycles in which both instructions in the ICT entry pair show as finished. These are the cycles between finish and completion for the oldest pair of instructions in the pipeline."
   },
   {
-    "EventCode": "0x40010",
-    "EventName": "PM_PMC3_OVERFLOW",
-    "BriefDescription": "The event selected for PMC3 caused the event counter to overflow."
+    "EventCode": "0x4C010",
+    "EventName": "PM_DISP_STALL_BR_MPRED_IC_L3MISS",
+    "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from sources beyond the local L3 after suffering a mispredicted branch."
   },
   {
     "EventCode": "0x4C012",
     "EventName": "PM_EXEC_STALL_DERAT_ONLY_MISS",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline suffered an ERAT miss and waited for it resolve."
   },
+  {
+    "EventCode": "0x4C016",
+    "EventName": "PM_EXEC_STALL_DMISS_L2L3_CONFLICT",
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local L2 or local L3, with a dispatch conflict."
+  },
   {
     "EventCode": "0x4C018",
     "EventName": "PM_CMPL_STALL",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline cannot complete because the thread was blocked for any reason."
   },
+  {
+    "EventCode": "0x4C01A",
+    "EventName": "PM_EXEC_STALL_DMISS_OFF_NODE",
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from a distant chip."
+  },
   {
     "EventCode": "0x4C01E",
     "EventName": "PM_LSU_ST3_FIN",
     "BriefDescription": "LSU Finished an internal operation in ST3 port."
   },
+  {
+    "EventCode": "0x4D014",
+    "EventName": "PM_EXEC_STALL_LOAD",
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a load instruction executing in the Load Store Unit."
+  },
+  {
+    "EventCode": "0x4D016",
+    "EventName": "PM_EXEC_STALL_PTESYNC",
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a PTESYNC instruction executing in the Load Store Unit."
+  },
   {
     "EventCode": "0x4D018",
     "EventName": "PM_EXEC_STALL_BRU",
@@ -244,31 +379,41 @@
     "EventName": "PM_EXEC_STALL_TLBIEL",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a TLBIEL instruction executing in the Load Store Unit. TLBIEL instructions have lower overhead than TLBIE instructions because they don't get set to the nest."
   },
+  {
+    "EventCode": "0x4D01E",
+    "EventName": "PM_DISP_STALL_BR_MPRED",
+    "BriefDescription": "Cycles when dispatch was stalled for this thread due to a mispredicted branch."
+  },
+  {
+    "EventCode": "0x4E010",
+    "EventName": "PM_DISP_STALL_IC_L3MISS",
+    "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from any source beyond the local L3."
+  },
   {
     "EventCode": "0x4E012",
     "EventName": "PM_EXEC_STALL_UNKNOWN",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline completed without an ntf_type pulse. The ntf_pulse was missed by the ISU because the next-to-finish (NTF) instruction finishes and completions came too close together."
   },
+  {
+    "EventCode": "0x4E01A",
+    "EventName": "PM_DISP_STALL_HELD_CYC",
+    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch for any reason."
+  },
   {
     "EventCode": "0x4D020",
     "EventName": "PM_VSU3_ISSUE",
     "BriefDescription": "VSU instruction was issued to VSU pipe 3."
   },
   {
-    "EventCode": "0x40132",
-    "EventName": "PM_MRK_LSU_FIN",
-    "BriefDescription": "LSU marked instruction finish."
+    "EventCode": "0x4003C",
+    "EventName": "PM_DISP_STALL_HELD_SYNC_CYC",
+    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because of a synchronizing instruction that requires the ICT to be empty before dispatch."
   },
   {
     "EventCode": "0x45058",
     "EventName": "PM_IC_MISS_CMPL",
     "BriefDescription": "Non-speculative instruction cache miss, counted at completion."
   },
-  {
-    "EventCode": "0x4D052",
-    "EventName": "PM_2FLOP_CMPL",
-    "BriefDescription": "Double Precision vector version of fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg completed."
-  },
   {
     "EventCode": "0x400F2",
     "EventName": "PM_1PLUS_PPC_DISP",
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/pmc.json b/tools/perf/pmu-events/arch/powerpc/power10/pmc.json
index 364fedbfb490..0a2bf56ee7c1 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/pmc.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/pmc.json
@@ -1,22 +1,197 @@
 [
+  {
+    "EventCode": "0x100FE",
+    "EventName": "PM_INST_CMPL",
+    "BriefDescription": "PowerPC instruction completed."
+  },
+  {
+    "EventCode": "0x1000A",
+    "EventName": "PM_PMC3_REWIND",
+    "BriefDescription": "The speculative event selected for PMC3 rewinds and the counter for PMC3 is not charged."
+  },
+  {
+    "EventCode": "0x10010",
+    "EventName": "PM_PMC4_OVERFLOW",
+    "BriefDescription": "The event selected for PMC4 caused the event counter to overflow."
+  },
+  {
+    "EventCode": "0x1001C",
+    "EventName": "PM_ULTRAVISOR_INST_CMPL",
+    "BriefDescription": "PowerPC instruction completed while the thread was in ultravisor state."
+  },
+  {
+    "EventCode": "0x100F0",
+    "EventName": "PM_CYC",
+    "BriefDescription": "Processor cycles."
+  },
+  {
+    "EventCode": "0x10020",
+    "EventName": "PM_PMC4_REWIND",
+    "BriefDescription": "The speculative event selected for PMC4 rewinds and the counter for PMC4 is not charged."
+  },
+  {
+    "EventCode": "0x10022",
+    "EventName": "PM_PMC2_SAVED",
+    "BriefDescription": "The conditions for the speculative event selected for PMC2 are met and PMC2 is charged."
+  },
+  {
+    "EventCode": "0x10024",
+    "EventName": "PM_PMC5_OVERFLOW",
+    "BriefDescription": "The event selected for PMC5 caused the event counter to overflow."
+  },
+  {
+    "EventCode": "0x1F15E",
+    "EventName": "PM_MRK_START_PROBE_NOP_CMPL",
+    "BriefDescription": "Marked Start probe nop (AND R0,R0,R0) completed."
+  },
+  {
+    "EventCode": "0x1006C",
+    "EventName": "PM_RUN_CYC_ST_MODE",
+    "BriefDescription": "Cycles when the run latch is set and the core is in ST mode."
+  },
+  {
+    "EventCode": "0x101E8",
+    "EventName": "PM_THRESH_EXC_256",
+    "BriefDescription": "Threshold counter exceeded a count of 256."
+  },
+  {
+    "EventCode": "0x101EC",
+    "EventName": "PM_THRESH_MET",
+    "BriefDescription": "Threshold exceeded."
+  },
+  {
+    "EventCode": "0x100FA",
+    "EventName": "PM_RUN_LATCH_ANY_THREAD_CYC",
+    "BriefDescription": "Cycles when at least one thread has the run latch set."
+  },
+  {
+    "EventCode": "0x2000A",
+    "EventName": "PM_HYPERVISOR_CYC",
+    "BriefDescription": "Cycles when the thread is in Hypervisor state. MSR[S HV PR]=010."
+  },
+  {
+    "EventCode": "0x2000C",
+    "EventName": "PM_RUN_LATCH_ALL_THREADS_CYC",
+    "BriefDescription": "Cycles when the run latch is set for all threads."
+  },
+  {
+    "EventCode": "0x20010",
+    "EventName": "PM_PMC1_OVERFLOW",
+    "BriefDescription": "The event selected for PMC1 caused the event counter to overflow."
+  },
+  {
+    "EventCode": "0x2006C",
+    "EventName": "PM_RUN_CYC_SMT4_MODE",
+    "BriefDescription": "Cycles when this thread's run latch is set and the core is in SMT4 mode."
+  },
+  {
+    "EventCode": "0x201E6",
+    "EventName": "PM_THRESH_EXC_32",
+    "BriefDescription": "Threshold counter exceeded a value of 32."
+  },
+  {
+    "EventCode": "0x201E8",
+    "EventName": "PM_THRESH_EXC_512",
+    "BriefDescription": "Threshold counter exceeded a value of 512."
+  },
+  {
+    "EventCode": "0x200F4",
+    "EventName": "PM_RUN_CYC",
+    "BriefDescription": "Processor cycles gated by the run latch."
+  },
+  {
+    "EventCode": "0x30010",
+    "EventName": "PM_PMC2_OVERFLOW",
+    "BriefDescription": "The event selected for PMC2 caused the event counter to overflow."
+  },
+  {
+    "EventCode": "0x30020",
+    "EventName": "PM_PMC2_REWIND",
+    "BriefDescription": "The speculative event selected for PMC2 rewinds and the counter for PMC2 is not charged."
+  },
+  {
+    "EventCode": "0x30022",
+    "EventName": "PM_PMC4_SAVED",
+    "BriefDescription": "The conditions for the speculative event selected for PMC4 are met and PMC4 is charged."
+  },
+  {
+    "EventCode": "0x30024",
+    "EventName": "PM_PMC6_OVERFLOW",
+    "BriefDescription": "The event selected for PMC6 caused the event counter to overflow."
+  },
+  {
+    "EventCode": "0x3006C",
+    "EventName": "PM_RUN_CYC_SMT2_MODE",
+    "BriefDescription": "Cycles when this thread's run latch is set and the core is in SMT2 mode."
+  },
   {
     "EventCode": "0x301E8",
     "EventName": "PM_THRESH_EXC_64",
     "BriefDescription": "Threshold counter exceeded a value of 64."
   },
   {
-    "EventCode": "0x45050",
-    "EventName": "PM_1FLOP_CMPL",
-    "BriefDescription": "One floating point instruction completed (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg)."
+    "EventCode": "0x301EA",
+    "EventName": "PM_THRESH_EXC_1024",
+    "BriefDescription": "Threshold counter exceeded a value of 1024."
   },
   {
-    "EventCode": "0x45052",
-    "EventName": "PM_4FLOP_CMPL",
-    "BriefDescription": "Four floating point instruction completed (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg)."
+    "EventCode": "0x40010",
+    "EventName": "PM_PMC3_OVERFLOW",
+    "BriefDescription": "The event selected for PMC3 caused the event counter to overflow."
   },
   {
-    "EventCode": "0x4D054",
-    "EventName": "PM_8FLOP_CMPL",
-    "BriefDescription": "Four Double Precision vector instruction completed."
+    "EventCode": "0x40114",
+    "EventName": "PM_MRK_START_PROBE_NOP_DISP",
+    "BriefDescription": "Marked Start probe nop dispatched. Instruction AND R0,R0,R0."
+  },
+  {
+    "EventCode": "0x4D010",
+    "EventName": "PM_PMC1_SAVED",
+    "BriefDescription": "The conditions for the speculative event selected for PMC1 are met and PMC1 is charged."
+  },
+  {
+    "EventCode": "0x4D012",
+    "EventName": "PM_PMC3_SAVED",
+    "BriefDescription": "The conditions for the speculative event selected for PMC3 are met and PMC3 is charged."
+  },
+  {
+    "EventCode": "0x4D022",
+    "EventName": "PM_HYPERVISOR_INST_CMPL",
+    "BriefDescription": "PowerPC instruction completed while the thread was in hypervisor state."
+  },
+  {
+    "EventCode": "0x4D026",
+    "EventName": "PM_ULTRAVISOR_CYC",
+    "BriefDescription": "Cycles when the thread is in Ultravisor state. MSR[S HV PR]=110."
+  },
+  {
+    "EventCode": "0x4D028",
+    "EventName": "PM_PRIVILEGED_CYC",
+    "BriefDescription": "Cycles when the thread is in Privileged state. MSR[S HV PR]=x00."
+  },
+  {
+    "EventCode": "0x4D02C",
+    "EventName": "PM_PMC1_REWIND",
+    "BriefDescription": "The speculative event selected for PMC1 rewinds and the counter for PMC1 is not charged."
+  },
+  {
+    "EventCode": "0x40030",
+    "EventName": "PM_INST_FIN",
+    "BriefDescription": "Instruction finished."
+  },
+  {
+    "EventCode": "0x40134",
+    "EventName": "PM_MRK_INST_TIMEO",
+    "BriefDescription": "Marked instruction finish timeout (instruction was lost)."
+  },
+  {
+    "EventCode": "0x401EA",
+    "EventName": "PM_THRESH_EXC_128",
+    "BriefDescription": "Threshold counter exceeded a value of 128."
+  },
+  {
+    "EventCode": "0x400FA",
+    "EventName": "PM_RUN_INST_CMPL",
+    "BriefDescription": "PowerPC instruction completed while the run latch is set."
   }
 ]
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/translation.json b/tools/perf/pmu-events/arch/powerpc/power10/translation.json
index 961e2491e73f..170c9aeb30d8 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/translation.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/translation.json
@@ -1,29 +1,9 @@
 [
-  {
-    "EventCode": "0x1F15E",
-    "EventName": "PM_MRK_START_PROBE_NOP_CMPL",
-    "BriefDescription": "Marked Start probe nop (AND R0,R0,R0) completed."
-  },
   {
     "EventCode": "0x20018",
     "EventName": "PM_ST_FWD",
     "BriefDescription": "Store forwards that finished."
   },
-  {
-    "EventCode": "0x2011C",
-    "EventName": "PM_MRK_NTF_CYC",
-    "BriefDescription": "Cycles in which the marked instruction is the oldest in the pipeline (next-to-finish or next-to-complete)."
-  },
-  {
-    "EventCode": "0x2E01C",
-    "EventName": "PM_EXEC_STALL_TLBIE",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a TLBIE instruction executing in the Load Store Unit."
-  },
-  {
-    "EventCode": "0x201E6",
-    "EventName": "PM_THRESH_EXC_32",
-    "BriefDescription": "Threshold counter exceeded a value of 32."
-  },
   {
     "EventCode": "0x200F0",
     "EventName": "PM_ST_CMPL",
@@ -33,20 +13,5 @@
     "EventCode": "0x200FE",
     "EventName": "PM_DATA_FROM_L2MISS",
     "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L2 due to a demand miss."
-  },
-  {
-    "EventCode": "0x30010",
-    "EventName": "PM_PMC2_OVERFLOW",
-    "BriefDescription": "The event selected for PMC2 caused the event counter to overflow."
-  },
-  {
-    "EventCode": "0x4D010",
-    "EventName": "PM_PMC1_SAVED",
-    "BriefDescription": "The conditions for the speculative event selected for PMC1 are met and PMC1 is charged."
-  },
-  {
-    "EventCode": "0x4D05C",
-    "EventName": "PM_DPP_FLOP_CMPL",
-    "BriefDescription": "Double-Precision or Quad-Precision instruction completed."
   }
 ]

From 426c804b5a1ba623c44407d93946a3443b352fd5 Mon Sep 17 00:00:00 2001
From: Kajol Jain <kjain@linux.ibm.com>
Date: Mon, 14 Aug 2023 16:58:01 +0530
Subject: [PATCH 0449/1189] perf vendor events: Update JSON/events for power10
 platform

Update JSON/events for power10 platform with additional events.

Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Disha Goel <disgoel@linux.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230814112803.1508296-5-kjain@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../arch/powerpc/power10/frontend.json        | 25 +++++++++++++
 .../arch/powerpc/power10/marked.json          | 30 ++++++++++++++++
 .../arch/powerpc/power10/memory.json          | 10 ++++++
 .../arch/powerpc/power10/others.json          |  5 +++
 .../arch/powerpc/power10/pipeline.json        | 35 +++++++++++++++++++
 .../pmu-events/arch/powerpc/power10/pmc.json  |  5 +++
 .../arch/powerpc/power10/translation.json     |  5 +++
 7 files changed, 115 insertions(+)

diff --git a/tools/perf/pmu-events/arch/powerpc/power10/frontend.json b/tools/perf/pmu-events/arch/powerpc/power10/frontend.json
index dc0bb6c6338b..5977f5e64212 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/frontend.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/frontend.json
@@ -1,4 +1,14 @@
 [
+  {
+    "EventCode": "0x1D054",
+    "EventName": "PM_DTLB_HIT_2M",
+    "BriefDescription": "Data TLB hit (DERAT reload) page size 2M. Implies radix translation. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
+  },
+  {
+    "EventCode": "0x1D058",
+    "EventName": "PM_ITLB_HIT_64K",
+    "BriefDescription": "Instruction TLB hit (IERAT reload) page size 64K. When MMCR1[17]=0 this event counts only for demand misses. When MMCR1[17]=1 this event includes demand misses and prefetches."
+  },
   {
     "EventCode": "0x1F054",
     "EventName": "PM_DTLB_HIT",
@@ -44,6 +54,11 @@
     "EventName": "PM_ITLB_HIT_1G",
     "BriefDescription": "Instruction TLB hit (IERAT reload) page size 1G, which implies Radix Page Table translation is in use. When MMCR1[17]=0 this event counts only for demand misses. When MMCR1[17]=1 this event includes demand misses and prefetches."
   },
+  {
+    "EventCode": "0x3C05A",
+    "EventName": "PM_DTLB_HIT_64K",
+    "BriefDescription": "Data TLB hit (DERAT reload) page size 64K. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
+  },
   {
     "EventCode": "0x3E054",
     "EventName": "PM_LD_MISS_L1",
@@ -63,5 +78,15 @@
     "EventCode": "0x44056",
     "EventName": "PM_VECTOR_ST_CMPL",
     "BriefDescription": "Vector store instruction completed."
+  },
+  {
+    "EventCode": "0x4E054",
+    "EventName": "PM_DTLB_HIT_1G",
+    "BriefDescription": "Data TLB hit (DERAT reload) page size 1G. Implies radix translation. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
+  },
+  {
+    "EventCode": "0x400FC",
+    "EventName": "PM_ITLB_MISS",
+    "BriefDescription": "Instruction TLB reload (after a miss), all page sizes. Includes only demand misses."
   }
 ]
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/marked.json b/tools/perf/pmu-events/arch/powerpc/power10/marked.json
index 913b6515b870..78f71a9eadfd 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/marked.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/marked.json
@@ -19,6 +19,11 @@
     "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC1",
     "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[0:12]."
   },
+  {
+    "EventCode": "0x1D15C",
+    "EventName": "PM_MRK_DTLB_MISS_1G",
+    "BriefDescription": "Marked Data TLB reload (after a miss) page size 1G. Implies radix translation was used. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
+  },
   {
     "EventCode": "0x1F150",
     "EventName": "PM_MRK_ST_L2_CYC",
@@ -134,6 +139,11 @@
     "EventName": "PM_MRK_L2_RC_DONE",
     "BriefDescription": "L2 RC machine completed the transaction for the marked instruction."
   },
+  {
+    "EventCode": "0x3012E",
+    "EventName": "PM_MRK_DTLB_MISS_2M",
+    "BriefDescription": "Marked Data TLB reload (after a miss) page size 2M, which implies Radix Page Table translation was used. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
+  },
   {
     "EventCode": "0x30132",
     "EventName": "PM_MRK_VSU_FIN",
@@ -184,6 +194,16 @@
     "EventName": "PM_MRK_BR_MPRED_CMPL",
     "BriefDescription": "Marked Branch Mispredicted. Includes direction and target."
   },
+  {
+    "EventCode": "0x301E6",
+    "EventName": "PM_MRK_DERAT_MISS",
+    "BriefDescription": "Marked Erat Miss (Data TLB Access) All page sizes. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
+  },
+  {
+    "EventCode": "0x4010E",
+    "EventName": "PM_MRK_TLBIE_FIN",
+    "BriefDescription": "Marked TLBIE instruction finished. Includes TLBIE and TLBIEL instructions."
+  },
   {
     "EventCode": "0x40116",
     "EventName": "PM_MRK_LARX_FIN",
@@ -209,6 +229,11 @@
     "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC4",
     "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[45:57]."
   },
+  {
+    "EventCode": "0x4C15C",
+    "EventName": "PM_MRK_DERAT_MISS_1G",
+    "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 1G for a marked instruction. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
+  },
   {
     "EventCode": "0x4C15E",
     "EventName": "PM_MRK_DTLB_MISS_64K",
@@ -229,6 +254,11 @@
     "EventName": "PM_MRK_INST_CMPL",
     "BriefDescription": "Marked instruction completed."
   },
+  {
+    "EventCode": "0x401E4",
+    "EventName": "PM_MRK_DTLB_MISS",
+    "BriefDescription": "The DPTEG required for the marked load/store instruction in execution was missing from the TLB. This event only counts for demand misses."
+  },
   {
     "EventCode": "0x401E6",
     "EventName": "PM_MRK_INST_FROM_L3MISS",
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/memory.json b/tools/perf/pmu-events/arch/powerpc/power10/memory.json
index b95a547a704b..885262957beb 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/memory.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/memory.json
@@ -49,11 +49,21 @@
     "EventName": "PM_DTLB_MISS_4K",
     "BriefDescription": "Data TLB reload (after a miss) page size 4K. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
   },
+  {
+    "EventCode": "0x2C05A",
+    "EventName": "PM_DERAT_MISS_1G",
+    "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 1G. Implies radix translation. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
+  },
   {
     "EventCode": "0x200F6",
     "EventName": "PM_DERAT_MISS",
     "BriefDescription": "DERAT Reloaded to satisfy a DERAT miss. All page sizes are counted by this event. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
   },
+  {
+    "EventCode": "0x34044",
+    "EventName": "PM_DERAT_MISS_PREF",
+    "BriefDescription": "DERAT miss (TLB access) while servicing a data prefetch."
+  },
   {
     "EventCode": "0x3C040",
     "EventName": "PM_XFER_FROM_SRC_PMC3",
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/others.json b/tools/perf/pmu-events/arch/powerpc/power10/others.json
index f09c00c89322..0e21e7ba1959 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/others.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/others.json
@@ -14,6 +14,11 @@
     "EventName": "PM_DISP_SS0_2_INSTR_CYC",
     "BriefDescription": "Cycles in which Superslice 0 dispatches either 1 or 2 instructions."
   },
+  {
+    "EventCode": "0x1F05A",
+    "EventName": "PM_DISP_HELD_SYNC_CYC",
+    "BriefDescription": "Cycles dispatch is held because of a synchronizing instruction that requires the ICT to be empty before dispatch."
+  },
   {
     "EventCode": "0x10066",
     "EventName": "PM_ADJUNCT_CYC",
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json b/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json
index a8272a2f0517..21b23bb55d0d 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json
@@ -34,6 +34,11 @@
     "EventName": "PM_IC_DEMAND_CYC",
     "BriefDescription": "Cycles in which an instruction reload is pending to satisfy a demand miss."
   },
+  {
+    "EventCode": "0x10028",
+    "EventName": "PM_NTC_FLUSH",
+    "BriefDescription": "The instruction was flushed after becoming next-to-complete (NTC)."
+  },
   {
     "EventCode": "0x10038",
     "EventName": "PM_DISP_STALL_TRANSLATION",
@@ -89,6 +94,11 @@
     "EventName": "PM_CMPL_STALL_LWSYNC",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a lwsync waiting to complete."
   },
+  {
+    "EventCode": "0x1F058",
+    "EventName": "PM_DISP_HELD_CYC",
+    "BriefDescription": "Cycles dispatch is held."
+  },
   {
     "EventCode": "0x10064",
     "EventName": "PM_DISP_STALL_IC_L2",
@@ -219,6 +229,16 @@
     "EventName": "PM_NTC_FIN",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline (NTC) finishes. Note that instructions can finish out of order, therefore not all the instructions that finish have a Next-to-complete status."
   },
+  {
+    "EventCode": "0x20066",
+    "EventName": "PM_DISP_HELD_OTHER_CYC",
+    "BriefDescription": "Cycles dispatch is held for any other reason."
+  },
+  {
+    "EventCode": "0x2006A",
+    "EventName": "PM_DISP_HELD_STF_MAPPER_CYC",
+    "BriefDescription": "Cycles dispatch is held because the STF mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR."
+  },
   {
     "EventCode": "0x30004",
     "EventName": "PM_DISP_STALL_FLUSH",
@@ -309,6 +329,11 @@
     "EventName": "PM_DISP_STALL_IC_L3",
     "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L3."
   },
+  {
+    "EventCode": "0x30060",
+    "EventName": "PM_DISP_HELD_XVFC_MAPPER_CYC",
+    "BriefDescription": "Cycles dispatch is held because the XVFC mapper/SRB was full."
+  },
   {
     "EventCode": "0x30066",
     "EventName": "PM_LSU_FIN",
@@ -414,6 +439,16 @@
     "EventName": "PM_IC_MISS_CMPL",
     "BriefDescription": "Non-speculative instruction cache miss, counted at completion."
   },
+  {
+    "EventCode": "0x40060",
+    "EventName": "PM_DISP_HELD_SCOREBOARD_CYC",
+    "BriefDescription": "Cycles dispatch is held while waiting on the Scoreboard. This event combines VSCR and FPSCR together."
+  },
+  {
+    "EventCode": "0x40062",
+    "EventName": "PM_DISP_HELD_RENAME_CYC",
+    "BriefDescription": "Cycles dispatch is held because the mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR and XVFC."
+  },
   {
     "EventCode": "0x400F2",
     "EventName": "PM_1PLUS_PPC_DISP",
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/pmc.json b/tools/perf/pmu-events/arch/powerpc/power10/pmc.json
index 0a2bf56ee7c1..c606ae03cd27 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/pmc.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/pmc.json
@@ -39,6 +39,11 @@
     "EventName": "PM_PMC5_OVERFLOW",
     "BriefDescription": "The event selected for PMC5 caused the event counter to overflow."
   },
+  {
+    "EventCode": "0x1002A",
+    "EventName": "PM_PMC3_HELD_CYC",
+    "BriefDescription": "Cycles when the speculative counter for PMC3 is frozen."
+  },
   {
     "EventCode": "0x1F15E",
     "EventName": "PM_MRK_START_PROBE_NOP_CMPL",
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/translation.json b/tools/perf/pmu-events/arch/powerpc/power10/translation.json
index 170c9aeb30d8..ea73900d248a 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/translation.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/translation.json
@@ -13,5 +13,10 @@
     "EventCode": "0x200FE",
     "EventName": "PM_DATA_FROM_L2MISS",
     "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L2 due to a demand miss."
+  },
+  {
+    "EventCode": "0x300F0",
+    "EventName": "PM_ST_MISS_L1",
+    "BriefDescription": "Store Missed L1."
   }
 ]

From edd65d2bc55fb84d7b80c2ffe3b74d9b11ac4e2f Mon Sep 17 00:00:00 2001
From: Kajol Jain <kjain@linux.ibm.com>
Date: Mon, 14 Aug 2023 16:58:02 +0530
Subject: [PATCH 0450/1189] perf vendor events: Update metric event names for
 power10 platform

Update metric event name for some of the JSON/metric events for
power10 platform.

Fixes: 3ca3af7d1f230d1f ("perf vendor events power10: Add metric events JSON file for power10 platform")
Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Disha Goel <disgoel@linux.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230814112803.1508296-6-kjain@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../arch/powerpc/power10/metrics.json         | 50 +++++++++----------
 1 file changed, 25 insertions(+), 25 deletions(-)

diff --git a/tools/perf/pmu-events/arch/powerpc/power10/metrics.json b/tools/perf/pmu-events/arch/powerpc/power10/metrics.json
index e3087eb1ccff..182369076d95 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/metrics.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/metrics.json
@@ -16,133 +16,133 @@
         "BriefDescription": "Average cycles per completed instruction when dispatch was stalled for any reason",
         "MetricExpr": "PM_DISP_STALL_CYC / PM_RUN_INST_CMPL",
         "MetricGroup": "CPI;CPI_STALL_RATIO",
-        "MetricName": "DISPATCHED_CPI"
+        "MetricName": "DISPATCH_STALL_CPI"
     },
     {
         "BriefDescription": "Average cycles per completed instruction when dispatch was stalled because there was a flush",
         "MetricExpr": "PM_DISP_STALL_FLUSH / PM_RUN_INST_CMPL",
         "MetricGroup": "CPI",
-        "MetricName": "DISPATCHED_FLUSH_CPI"
+        "MetricName": "DISPATCH_STALL_FLUSH_CPI"
     },
     {
         "BriefDescription": "Average cycles per completed instruction when dispatch was stalled because the MMU was handling a translation miss",
         "MetricExpr": "PM_DISP_STALL_TRANSLATION / PM_RUN_INST_CMPL",
         "MetricGroup": "CPI",
-        "MetricName": "DISPATCHED_TRANSLATION_CPI"
+        "MetricName": "DISPATCH_STALL_TRANSLATION_CPI"
     },
     {
         "BriefDescription": "Average cycles per completed instruction when dispatch was stalled waiting to resolve an instruction ERAT miss",
         "MetricExpr": "PM_DISP_STALL_IERAT_ONLY_MISS / PM_RUN_INST_CMPL",
         "MetricGroup": "CPI",
-        "MetricName": "DISPATCHED_IERAT_ONLY_MISS_CPI"
+        "MetricName": "DISPATCH_STALL_IERAT_ONLY_MISS_CPI"
     },
     {
         "BriefDescription": "Average cycles per completed instruction when dispatch was stalled waiting to resolve an instruction TLB miss",
         "MetricExpr": "PM_DISP_STALL_ITLB_MISS / PM_RUN_INST_CMPL",
         "MetricGroup": "CPI",
-        "MetricName": "DISPATCHED_ITLB_MISS_CPI"
+        "MetricName": "DISPATCH_STALL_ITLB_MISS_CPI"
     },
     {
         "BriefDescription": "Average cycles per completed instruction when dispatch was stalled due to an icache miss",
         "MetricExpr": "PM_DISP_STALL_IC_MISS / PM_RUN_INST_CMPL",
         "MetricGroup": "CPI",
-        "MetricName": "DISPATCHED_IC_MISS_CPI"
+        "MetricName": "DISPATCH_STALL_IC_MISS_CPI"
     },
     {
         "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while the instruction was fetched from the local L2",
         "MetricExpr": "PM_DISP_STALL_IC_L2 / PM_RUN_INST_CMPL",
         "MetricGroup": "CPI",
-        "MetricName": "DISPATCHED_IC_L2_CPI"
+        "MetricName": "DISPATCH_STALL_IC_L2_CPI"
     },
     {
         "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while the instruction was fetched from the local L3",
         "MetricExpr": "PM_DISP_STALL_IC_L3 / PM_RUN_INST_CMPL",
         "MetricGroup": "CPI",
-        "MetricName": "DISPATCHED_IC_L3_CPI"
+        "MetricName": "DISPATCH_STALL_IC_L3_CPI"
     },
     {
         "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while the instruction was fetched from any source beyond the local L3",
         "MetricExpr": "PM_DISP_STALL_IC_L3MISS / PM_RUN_INST_CMPL",
         "MetricGroup": "CPI",
-        "MetricName": "DISPATCHED_IC_L3MISS_CPI"
+        "MetricName": "DISPATCH_STALL_IC_L3MISS_CPI"
     },
     {
         "BriefDescription": "Average cycles per completed instruction when dispatch was stalled due to an icache miss after a branch mispredict",
         "MetricExpr": "PM_DISP_STALL_BR_MPRED_ICMISS / PM_RUN_INST_CMPL",
         "MetricGroup": "CPI",
-        "MetricName": "DISPATCHED_BR_MPRED_ICMISS_CPI"
+        "MetricName": "DISPATCH_STALL_BR_MPRED_ICMISS_CPI"
     },
     {
         "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while instruction was fetched from the local L2 after suffering a branch mispredict",
         "MetricExpr": "PM_DISP_STALL_BR_MPRED_IC_L2 / PM_RUN_INST_CMPL",
         "MetricGroup": "CPI",
-        "MetricName": "DISPATCHED_BR_MPRED_IC_L2_CPI"
+        "MetricName": "DISPATCH_STALL_BR_MPRED_IC_L2_CPI"
     },
     {
         "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while instruction was fetched from the local L3 after suffering a branch mispredict",
         "MetricExpr": "PM_DISP_STALL_BR_MPRED_IC_L3 / PM_RUN_INST_CMPL",
         "MetricGroup": "CPI",
-        "MetricName": "DISPATCHED_BR_MPRED_IC_L3_CPI"
+        "MetricName": "DISPATCH_STALL_BR_MPRED_IC_L3_CPI"
     },
     {
         "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while instruction was fetched from any source beyond the local L3 after suffering a branch mispredict",
         "MetricExpr": "PM_DISP_STALL_BR_MPRED_IC_L3MISS / PM_RUN_INST_CMPL",
         "MetricGroup": "CPI",
-        "MetricName": "DISPATCHED_BR_MPRED_IC_L3MISS_CPI"
+        "MetricName": "DISPATCH_STALL_BR_MPRED_IC_L3MISS_CPI"
     },
     {
         "BriefDescription": "Average cycles per completed instruction when dispatch was stalled due to a branch mispredict",
         "MetricExpr": "PM_DISP_STALL_BR_MPRED / PM_RUN_INST_CMPL",
         "MetricGroup": "CPI",
-        "MetricName": "DISPATCHED_BR_MPRED_CPI"
+        "MetricName": "DISPATCH_STALL_BR_MPRED_CPI"
     },
     {
         "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch for any reason",
         "MetricExpr": "PM_DISP_STALL_HELD_CYC / PM_RUN_INST_CMPL",
         "MetricGroup": "CPI",
-        "MetricName": "DISPATCHED_HELD_CPI"
+        "MetricName": "DISPATCH_STALL_HELD_CPI"
     },
     {
         "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because of a synchronizing instruction that requires the ICT to be empty before dispatch",
         "MetricExpr": "PM_DISP_STALL_HELD_SYNC_CYC / PM_RUN_INST_CMPL",
         "MetricGroup": "CPI",
-        "MetricName": "DISP_HELD_STALL_SYNC_CPI"
+        "MetricName": "DISPATCH_STALL_HELD_SYNC_CPI"
     },
     {
         "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch while waiting on the scoreboard",
         "MetricExpr": "PM_DISP_STALL_HELD_SCOREBOARD_CYC / PM_RUN_INST_CMPL",
         "MetricGroup": "CPI",
-        "MetricName": "DISP_HELD_STALL_SCOREBOARD_CPI"
+        "MetricName": "DISPATCH_STALL_HELD_SCOREBOARD_CPI"
     },
     {
         "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch due to issue queue full",
         "MetricExpr": "PM_DISP_STALL_HELD_ISSQ_FULL_CYC / PM_RUN_INST_CMPL",
         "MetricGroup": "CPI",
-        "MetricName": "DISP_HELD_STALL_ISSQ_FULL_CPI"
+        "MetricName": "DISPATCH_STALL_HELD_ISSQ_FULL_CPI"
     },
     {
         "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because the mapper/SRB was full",
         "MetricExpr": "PM_DISP_STALL_HELD_RENAME_CYC / PM_RUN_INST_CMPL",
         "MetricGroup": "CPI",
-        "MetricName": "DISPATCHED_HELD_RENAME_CPI"
+        "MetricName": "DISPATCH_STALL_HELD_RENAME_CPI"
     },
     {
         "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because the STF mapper/SRB was full",
         "MetricExpr": "PM_DISP_STALL_HELD_STF_MAPPER_CYC / PM_RUN_INST_CMPL",
         "MetricGroup": "CPI",
-        "MetricName": "DISPATCHED_HELD_STF_MAPPER_CPI"
+        "MetricName": "DISPATCH_STALL_HELD_STF_MAPPER_CPI"
     },
     {
         "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because the XVFC mapper/SRB was full",
         "MetricExpr": "PM_DISP_STALL_HELD_XVFC_MAPPER_CYC / PM_RUN_INST_CMPL",
         "MetricGroup": "CPI",
-        "MetricName": "DISPATCHED_HELD_XVFC_MAPPER_CPI"
+        "MetricName": "DISPATCH_STALL_HELD_XVFC_MAPPER_CPI"
     },
     {
         "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch for any other reason",
         "MetricExpr": "PM_DISP_STALL_HELD_OTHER_CYC / PM_RUN_INST_CMPL",
         "MetricGroup": "CPI",
-        "MetricName": "DISPATCHED_HELD_OTHER_CPI"
+        "MetricName": "DISPATCH_STALL_HELD_OTHER_CPI"
     },
     {
         "BriefDescription": "Average cycles per completed instruction when the NTC instruction has been dispatched but not issued for any reason",
@@ -352,13 +352,13 @@
         "BriefDescription": "Average cycles per completed instruction when dispatch was stalled because fetch was being held, so there was nothing in the pipeline for this thread",
         "MetricExpr": "PM_DISP_STALL_FETCH / PM_RUN_INST_CMPL",
         "MetricGroup": "CPI",
-        "MetricName": "DISPATCHED_FETCH_CPI"
+        "MetricName": "DISPATCH_STALL_FETCH_CPI"
     },
     {
         "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because of power management",
         "MetricExpr": "PM_DISP_STALL_HELD_HALT_CYC / PM_RUN_INST_CMPL",
         "MetricGroup": "CPI",
-        "MetricName": "DISPATCHED_HELD_HALT_CPI"
+        "MetricName": "DISPATCH_STALL_HELD_HALT_CPI"
     },
     {
         "BriefDescription": "Percentage of flushes per completed instruction",
@@ -560,7 +560,7 @@
         "BriefDescription": "Average number of STCX instructions finshed per completed instruction",
         "MetricExpr": "PM_STCX_FIN / PM_RUN_INST_CMPL",
         "MetricGroup": "General",
-        "MetricName": "STXC_PER_INST"
+        "MetricName": "STCX_PER_INST"
     },
     {
         "BriefDescription": "Average number of LARX instructions finshed per completed instruction",

From 5ceb8b5b7d8768e8cc4ab0a7858fa017f0189375 Mon Sep 17 00:00:00 2001
From: Kajol Jain <kjain@linux.ibm.com>
Date: Mon, 14 Aug 2023 16:58:03 +0530
Subject: [PATCH 0451/1189] perf vendor events: Update metric events for
 power10 platform

Update JSON/events for power10 platform with additional metrics.

Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Disha Goel <disgoel@linux.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230814112803.1508296-7-kjain@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../arch/powerpc/power10/metrics.json         | 33 +++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/tools/perf/pmu-events/arch/powerpc/power10/metrics.json b/tools/perf/pmu-events/arch/powerpc/power10/metrics.json
index 182369076d95..4d66b75c6ad5 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/metrics.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/metrics.json
@@ -24,6 +24,12 @@
         "MetricGroup": "CPI",
         "MetricName": "DISPATCH_STALL_FLUSH_CPI"
     },
+    {
+        "BriefDescription": "Average cycles per completed instruction when dispatch was stalled because Fetch was being held,  so there was nothing in the pipeline for this thread",
+        "MetricExpr": "PM_DISP_STALL_FETCH / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DISPATCH_STALL_FETCH_CPI"
+    },
     {
         "BriefDescription": "Average cycles per completed instruction when dispatch was stalled because the MMU was handling a translation miss",
         "MetricExpr": "PM_DISP_STALL_TRANSLATION / PM_RUN_INST_CMPL",
@@ -394,6 +400,13 @@
         "MetricName": "L1_LD_MISS_RATE",
         "ScaleUnit": "1%"
     },
+    {
+        "BriefDescription": "Percentage of completed instructions that were stores that missed the L1",
+        "MetricExpr": "PM_ST_MISS_L1 * 100 / PM_RUN_INST_CMPL",
+        "MetricGroup": "Others",
+        "MetricName": "L1_ST_MISS_RATE",
+        "ScaleUnit": "1%"
+    },
     {
         "BriefDescription": "Percentage of completed instructions when the DPTEG required for the load/store instruction in execution was missing from the TLB",
         "MetricExpr": "PM_DTLB_MISS / PM_RUN_INST_CMPL * 100",
@@ -467,6 +480,13 @@
         "MetricName": "DL1_RELOAD_FROM_L3_MISS_RATE",
         "ScaleUnit": "1%"
     },
+    {
+        "BriefDescription": "Percentage of ITLB misses per completed run instruction",
+        "MetricExpr": "PM_ITLB_MISS / PM_RUN_INST_CMPL * 100",
+        "MetricGroup": "General",
+        "MetricName": "ITLB_MISS_RATE",
+        "ScaleUnit": "1%"
+    },
     {
         "BriefDescription": "Percentage of DERAT misses with 4k page size per completed instruction",
         "MetricExpr": "PM_DERAT_MISS_4K / PM_RUN_INST_CMPL * 100",
@@ -622,6 +642,13 @@
         "MetricName": "DERAT_16M_MISS_RATE",
         "ScaleUnit": "1%"
     },
+    {
+        "BriefDescription": "Percentage of DERAT misses with 1G page size per completed run instruction",
+        "MetricExpr": "PM_DERAT_MISS_1G * 100 / PM_RUN_INST_CMPL",
+        "MetricGroup": "Translation",
+        "MetricName": "DERAT_1G_MISS_RATE",
+        "ScaleUnit": "1%"
+    },
     {
         "BriefDescription": "DERAT miss ratio for 4K page size",
         "MetricExpr": "PM_DERAT_MISS_4K / PM_DERAT_MISS",
@@ -640,6 +667,12 @@
         "MetricGroup": "Translation",
         "MetricName": "DERAT_16M_MISS_RATIO"
     },
+    {
+        "BriefDescription": "DERAT miss ratio for 1G page size",
+        "MetricExpr": "PM_DERAT_MISS_1G / PM_DERAT_MISS",
+        "MetricGroup": "Translation",
+        "MetricName": "DERAT_1G_MISS_RATIO"
+    },
     {
         "BriefDescription": "DERAT miss ratio for 64K page size",
         "MetricExpr": "PM_DERAT_MISS_64K / PM_DERAT_MISS",

From 1836480429d173c01664a633b61e525b13d41a2a Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 16 Aug 2023 13:53:26 -0300
Subject: [PATCH 0452/1189] perf bpf_skel augmented_raw_syscalls: Cap the
 socklen parameter using &= sizeof(saddr)

This works with:

  $ clang -v
  clang version 14.0.5 (Fedora 14.0.5-2.fc36)
  $

But not with:

  $ clang -v
  clang version 16.0.6 (Fedora 16.0.6-2.fc38)
  $

  [root@quaco ~]# perf trace -e connect*,sendto* ping -c 10 localhost
  libbpf: prog 'sys_enter_sendto': BPF program load failed: Permission denied
  libbpf: prog 'sys_enter_sendto': -- BEGIN PROG LOAD LOG --
  reg type unsupported for arg#0 function sys_enter_sendto#59
  0: R1=ctx(off=0,imm=0) R10=fp0
  ; int sys_enter_sendto(struct syscall_enter_args *args)
  0: (bf) r6 = r1                       ; R1=ctx(off=0,imm=0) R6_w=ctx(off=0,imm=0)
  1: (b7) r1 = 0                        ; R1_w=0
  ; int key = 0;
  2: (63) *(u32 *)(r10 -4) = r1         ; R1_w=0 R10=fp0 fp-8=0000????
  3: (bf) r2 = r10                      ; R2_w=fp0 R10=fp0
  ;
  4: (07) r2 += -4                      ; R2_w=fp-4
  ; return bpf_map_lookup_elem(&augmented_args_tmp, &key);
  5: (18) r1 = 0xffff8de5a5b8bc00       ; R1_w=map_ptr(off=0,ks=4,vs=8272,imm=0)
  7: (85) call bpf_map_lookup_elem#1    ; R0_w=map_value_or_null(id=1,off=0,ks=4,vs=8272,imm=0)
  8: (bf) r7 = r0                       ; R0_w=map_value_or_null(id=1,off=0,ks=4,vs=8272,imm=0) R7_w=map_value_or_null(id=1,off=0,ks=4,vs=8272,imm=0)
  9: (b7) r0 = 1                        ; R0_w=1
  ; if (augmented_args == NULL)
  10: (15) if r7 == 0x0 goto pc+25      ; R7_w=map_value(off=0,ks=4,vs=8272,imm=0)
  ; unsigned int socklen = args->args[5];
  11: (79) r1 = *(u64 *)(r6 +56)        ; R1_w=scalar() R6_w=ctx(off=0,imm=0)
  ;
  12: (bf) r2 = r1                      ; R1_w=scalar(id=2) R2_w=scalar(id=2)
  13: (67) r2 <<= 32                    ; R2_w=scalar(smax=9223372032559808512,umax=18446744069414584320,var_off=(0x0; 0xffffffff00000000),s32_min=0,s32_max=0,u32_max=0)
  14: (77) r2 >>= 32                    ; R2_w=scalar(umax=4294967295,var_off=(0x0; 0xffffffff))
  15: (b7) r8 = 128                     ; R8=128
  ; if (socklen > sizeof(augmented_args->saddr))
  16: (25) if r2 > 0x80 goto pc+1       ; R2=scalar(umax=128,var_off=(0x0; 0xff))
  17: (bf) r8 = r1                      ; R1=scalar(id=2) R8_w=scalar(id=2)
  ; const void *sockaddr_arg = (const void *)args->args[4];
  18: (79) r3 = *(u64 *)(r6 +48)        ; R3_w=scalar() R6=ctx(off=0,imm=0)
  ; bpf_probe_read(&augmented_args->saddr, socklen, sockaddr_arg);
  19: (bf) r1 = r7                      ; R1_w=map_value(off=0,ks=4,vs=8272,imm=0) R7=map_value(off=0,ks=4,vs=8272,imm=0)
  20: (07) r1 += 64                     ; R1_w=map_value(off=64,ks=4,vs=8272,imm=0)
  ; bpf_probe_read(&augmented_args->saddr, socklen, sockaddr_arg);
  21: (bf) r2 = r8                      ; R2_w=scalar(id=2) R8_w=scalar(id=2)
  22: (85) call bpf_probe_read#4
  R2 min value is negative, either use unsigned or 'var &= const'
  processed 22 insns (limit 1000000) max_states_per_insn 0 total_states 1 peak_states 1 mark_read 1
  -- END PROG LOAD LOG --
  libbpf: prog 'sys_enter_sendto': failed to load: -13
  libbpf: failed to load object 'augmented_raw_syscalls_bpf'
  libbpf: failed to load BPF skeleton 'augmented_raw_syscalls_bpf': -13

So use the suggested &= variant since sizeof(saddr) == 128 bytes.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
index 0586c4118656..9c1d0b271b20 100644
--- a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
+++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
@@ -187,8 +187,7 @@ int sys_enter_connect(struct syscall_enter_args *args)
         if (augmented_args == NULL)
                 return 1; /* Failure: don't filter */
 
-	if (socklen > sizeof(augmented_args->saddr))
-		socklen = sizeof(augmented_args->saddr);
+	socklen &= sizeof(augmented_args->saddr) - 1;
 
 	bpf_probe_read(&augmented_args->saddr, socklen, sockaddr_arg);
 
@@ -206,8 +205,7 @@ int sys_enter_sendto(struct syscall_enter_args *args)
         if (augmented_args == NULL)
                 return 1; /* Failure: don't filter */
 
-	if (socklen > sizeof(augmented_args->saddr))
-		socklen = sizeof(augmented_args->saddr);
+	socklen &= sizeof(augmented_args->saddr) - 1;
 
 	bpf_probe_read(&augmented_args->saddr, socklen, sockaddr_arg);
 

From 2cf2a1acc6ebdffc6363de9156db8737f33c1803 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Tue, 15 Aug 2023 15:16:41 -0700
Subject: [PATCH 0453/1189] rtc: stm32: Use NOIRQ_SYSTEM_SLEEP_PM_OPS()

After the switch to SET_NOIRQ_SYSTEM_SLEEP_PM_OPS() and a subsequent
fix, stm32_rtc_{suspend,resume}() are unused when CONFIG_PM_SLEEP is not
set because SET_NOIRQ_SYSTEM_SLEEP_PM_OPS() is a no-op in that
configuration:

  drivers/rtc/rtc-stm32.c:904:12: error: 'stm32_rtc_resume' defined but not used [-Werror=unused-function]
    904 | static int stm32_rtc_resume(struct device *dev)
        |            ^~~~~~~~~~~~~~~~
  drivers/rtc/rtc-stm32.c:894:12: error: 'stm32_rtc_suspend' defined but not used [-Werror=unused-function]
    894 | static int stm32_rtc_suspend(struct device *dev)
        |            ^~~~~~~~~~~~~~~~~
  cc1: all warnings being treated as errors

The non-"SET_" version of this macro, NOIRQ_SYSTEM_SLEEP_PM_OPS(), is
designed to handle this situation by only assigning the callbacks when
CONFIG_PM_SLEEP is set while allowing the functions to appear used to
the compiler. Switch to that macro to resolve the warnings. There is no
functional change with this, as SET_NOIRQ_SYSTEM_SLEEP_PM_OPS() is
defined using NOIRQ_SYSTEM_SLEEP_PM_OPS() when CONFIG_PM_SLEEP is set.

Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20230815-rtc-stm32-unused-pm-funcs-v1-1-82eb8e02d903@kernel.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-stm32.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/rtc/rtc-stm32.c b/drivers/rtc/rtc-stm32.c
index 3ce4b3d08155..76753c71d92e 100644
--- a/drivers/rtc/rtc-stm32.c
+++ b/drivers/rtc/rtc-stm32.c
@@ -923,7 +923,7 @@ static int stm32_rtc_resume(struct device *dev)
 }
 
 static const struct dev_pm_ops stm32_rtc_pm_ops = {
-	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(stm32_rtc_suspend, stm32_rtc_resume)
+	NOIRQ_SYSTEM_SLEEP_PM_OPS(stm32_rtc_suspend, stm32_rtc_resume)
 };
 
 static struct platform_driver stm32_rtc_driver = {

From d890cfc25fe9421ffdff3a9ea678172addb36762 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Mon, 7 Aug 2023 09:31:06 +0200
Subject: [PATCH 0454/1189] rtc: ds2404: Convert to GPIO descriptors

This converts the DS2404 to use GPIO descriptors instead of
hard-coded global GPIO numbers.

The platform data can be deleted because there are no in-tree
users and it only contained GPIO numbers which are now
passed using descriptor tables (or device tree or ACPI).

The driver was rewritten to use a state container for the
device driver state (struct ds2404 *chip) and pass that
around instead of using a global singleton storage for the
GPIO handles.

When declaring GPIO descriptor tables or other hardware
descriptions for the RTC driver, implementers should take care
to flag the RESET line as active low, such as by using the
GPIOD_ACTIVE_LOW flag in the descriptor table.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20230807-descriptors-rtc-v1-1-ce0f9187576e@linaro.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-ds2404.c                 | 169 +++++++++--------------
 include/linux/platform_data/rtc-ds2404.h |  20 ---
 2 files changed, 69 insertions(+), 120 deletions(-)
 delete mode 100644 include/linux/platform_data/rtc-ds2404.h

diff --git a/drivers/rtc/rtc-ds2404.c b/drivers/rtc/rtc-ds2404.c
index 0480f592307e..3231fd9f61da 100644
--- a/drivers/rtc/rtc-ds2404.c
+++ b/drivers/rtc/rtc-ds2404.c
@@ -7,9 +7,8 @@
 #include <linux/rtc.h>
 #include <linux/types.h>
 #include <linux/bcd.h>
-#include <linux/platform_data/rtc-ds2404.h>
 #include <linux/delay.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/slab.h>
 
 #include <linux/io.h>
@@ -27,164 +26,140 @@
 #define DS2404_CLK	1
 #define DS2404_DQ	2
 
-struct ds2404_gpio {
-	const char *name;
-	unsigned int gpio;
-};
-
 struct ds2404 {
-	struct ds2404_gpio *gpio;
+	struct device *dev;
+	struct gpio_desc *rst_gpiod;
+	struct gpio_desc *clk_gpiod;
+	struct gpio_desc *dq_gpiod;
 	struct rtc_device *rtc;
 };
 
-static struct ds2404_gpio ds2404_gpio[] = {
-	{ "RTC RST", 0 },
-	{ "RTC CLK", 0 },
-	{ "RTC DQ", 0 },
-};
-
-static int ds2404_gpio_map(struct ds2404 *chip, struct platform_device *pdev,
-			  struct ds2404_platform_data *pdata)
+static int ds2404_gpio_map(struct ds2404 *chip, struct platform_device *pdev)
 {
-	int i, err;
+	struct device *dev = &pdev->dev;
 
-	ds2404_gpio[DS2404_RST].gpio = pdata->gpio_rst;
-	ds2404_gpio[DS2404_CLK].gpio = pdata->gpio_clk;
-	ds2404_gpio[DS2404_DQ].gpio = pdata->gpio_dq;
+	/* This will de-assert RESET, declare this GPIO as GPIOD_ACTIVE_LOW */
+	chip->rst_gpiod = devm_gpiod_get(dev, "rst", GPIOD_OUT_LOW);
+	if (IS_ERR(chip->rst_gpiod))
+		return PTR_ERR(chip->rst_gpiod);
 
-	for (i = 0; i < ARRAY_SIZE(ds2404_gpio); i++) {
-		err = gpio_request(ds2404_gpio[i].gpio, ds2404_gpio[i].name);
-		if (err) {
-			dev_err(&pdev->dev, "error mapping gpio %s: %d\n",
-				ds2404_gpio[i].name, err);
-			goto err_request;
-		}
-		if (i != DS2404_DQ)
-			gpio_direction_output(ds2404_gpio[i].gpio, 1);
-	}
+	chip->clk_gpiod = devm_gpiod_get(dev, "clk", GPIOD_OUT_HIGH);
+	if (IS_ERR(chip->clk_gpiod))
+		return PTR_ERR(chip->clk_gpiod);
+
+	chip->dq_gpiod = devm_gpiod_get(dev, "dq", GPIOD_ASIS);
+	if (IS_ERR(chip->dq_gpiod))
+		return PTR_ERR(chip->dq_gpiod);
 
-	chip->gpio = ds2404_gpio;
 	return 0;
-
-err_request:
-	while (--i >= 0)
-		gpio_free(ds2404_gpio[i].gpio);
-	return err;
 }
 
-static void ds2404_gpio_unmap(void *data)
+static void ds2404_reset(struct ds2404 *chip)
 {
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(ds2404_gpio); i++)
-		gpio_free(ds2404_gpio[i].gpio);
-}
-
-static void ds2404_reset(struct device *dev)
-{
-	gpio_set_value(ds2404_gpio[DS2404_RST].gpio, 0);
+	gpiod_set_value(chip->rst_gpiod, 1);
 	udelay(1000);
-	gpio_set_value(ds2404_gpio[DS2404_RST].gpio, 1);
-	gpio_set_value(ds2404_gpio[DS2404_CLK].gpio, 0);
-	gpio_direction_output(ds2404_gpio[DS2404_DQ].gpio, 0);
+	gpiod_set_value(chip->rst_gpiod, 0);
+	gpiod_set_value(chip->clk_gpiod, 0);
+	gpiod_direction_output(chip->dq_gpiod, 0);
 	udelay(10);
 }
 
-static void ds2404_write_byte(struct device *dev, u8 byte)
+static void ds2404_write_byte(struct ds2404 *chip, u8 byte)
 {
 	int i;
 
-	gpio_direction_output(ds2404_gpio[DS2404_DQ].gpio, 1);
+	gpiod_direction_output(chip->dq_gpiod, 1);
 	for (i = 0; i < 8; i++) {
-		gpio_set_value(ds2404_gpio[DS2404_DQ].gpio, byte & (1 << i));
+		gpiod_set_value(chip->dq_gpiod, byte & (1 << i));
 		udelay(10);
-		gpio_set_value(ds2404_gpio[DS2404_CLK].gpio, 1);
+		gpiod_set_value(chip->clk_gpiod, 1);
 		udelay(10);
-		gpio_set_value(ds2404_gpio[DS2404_CLK].gpio, 0);
+		gpiod_set_value(chip->clk_gpiod, 0);
 		udelay(10);
 	}
 }
 
-static u8 ds2404_read_byte(struct device *dev)
+static u8 ds2404_read_byte(struct ds2404 *chip)
 {
 	int i;
 	u8 ret = 0;
 
-	gpio_direction_input(ds2404_gpio[DS2404_DQ].gpio);
+	gpiod_direction_input(chip->dq_gpiod);
 
 	for (i = 0; i < 8; i++) {
-		gpio_set_value(ds2404_gpio[DS2404_CLK].gpio, 0);
+		gpiod_set_value(chip->clk_gpiod, 0);
 		udelay(10);
-		if (gpio_get_value(ds2404_gpio[DS2404_DQ].gpio))
+		if (gpiod_get_value(chip->dq_gpiod))
 			ret |= 1 << i;
-		gpio_set_value(ds2404_gpio[DS2404_CLK].gpio, 1);
+		gpiod_set_value(chip->clk_gpiod, 1);
 		udelay(10);
 	}
 	return ret;
 }
 
-static void ds2404_read_memory(struct device *dev, u16 offset,
+static void ds2404_read_memory(struct ds2404 *chip, u16 offset,
 			       int length, u8 *out)
 {
-	ds2404_reset(dev);
-	ds2404_write_byte(dev, DS2404_READ_MEMORY_CMD);
-	ds2404_write_byte(dev, offset & 0xff);
-	ds2404_write_byte(dev, (offset >> 8) & 0xff);
+	ds2404_reset(chip);
+	ds2404_write_byte(chip, DS2404_READ_MEMORY_CMD);
+	ds2404_write_byte(chip, offset & 0xff);
+	ds2404_write_byte(chip, (offset >> 8) & 0xff);
 	while (length--)
-		*out++ = ds2404_read_byte(dev);
+		*out++ = ds2404_read_byte(chip);
 }
 
-static void ds2404_write_memory(struct device *dev, u16 offset,
+static void ds2404_write_memory(struct ds2404 *chip, u16 offset,
 				int length, u8 *out)
 {
 	int i;
 	u8 ta01, ta02, es;
 
-	ds2404_reset(dev);
-	ds2404_write_byte(dev, DS2404_WRITE_SCRATCHPAD_CMD);
-	ds2404_write_byte(dev, offset & 0xff);
-	ds2404_write_byte(dev, (offset >> 8) & 0xff);
+	ds2404_reset(chip);
+	ds2404_write_byte(chip, DS2404_WRITE_SCRATCHPAD_CMD);
+	ds2404_write_byte(chip, offset & 0xff);
+	ds2404_write_byte(chip, (offset >> 8) & 0xff);
 
 	for (i = 0; i < length; i++)
-		ds2404_write_byte(dev, out[i]);
+		ds2404_write_byte(chip, out[i]);
 
-	ds2404_reset(dev);
-	ds2404_write_byte(dev, DS2404_READ_SCRATCHPAD_CMD);
+	ds2404_reset(chip);
+	ds2404_write_byte(chip, DS2404_READ_SCRATCHPAD_CMD);
 
-	ta01 = ds2404_read_byte(dev);
-	ta02 = ds2404_read_byte(dev);
-	es = ds2404_read_byte(dev);
+	ta01 = ds2404_read_byte(chip);
+	ta02 = ds2404_read_byte(chip);
+	es = ds2404_read_byte(chip);
 
 	for (i = 0; i < length; i++) {
-		if (out[i] != ds2404_read_byte(dev)) {
-			dev_err(dev, "read invalid data\n");
+		if (out[i] != ds2404_read_byte(chip)) {
+			dev_err(chip->dev, "read invalid data\n");
 			return;
 		}
 	}
 
-	ds2404_reset(dev);
-	ds2404_write_byte(dev, DS2404_COPY_SCRATCHPAD_CMD);
-	ds2404_write_byte(dev, ta01);
-	ds2404_write_byte(dev, ta02);
-	ds2404_write_byte(dev, es);
+	ds2404_reset(chip);
+	ds2404_write_byte(chip, DS2404_COPY_SCRATCHPAD_CMD);
+	ds2404_write_byte(chip, ta01);
+	ds2404_write_byte(chip, ta02);
+	ds2404_write_byte(chip, es);
 
-	gpio_direction_input(ds2404_gpio[DS2404_DQ].gpio);
-	while (gpio_get_value(ds2404_gpio[DS2404_DQ].gpio))
+	while (gpiod_get_value(chip->dq_gpiod))
 		;
 }
 
-static void ds2404_enable_osc(struct device *dev)
+static void ds2404_enable_osc(struct ds2404 *chip)
 {
 	u8 in[1] = { 0x10 }; /* enable oscillator */
-	ds2404_write_memory(dev, 0x201, 1, in);
+
+	ds2404_write_memory(chip, 0x201, 1, in);
 }
 
 static int ds2404_read_time(struct device *dev, struct rtc_time *dt)
 {
+	struct ds2404 *chip = dev_get_drvdata(dev);
 	unsigned long time = 0;
 	__le32 hw_time = 0;
 
-	ds2404_read_memory(dev, 0x203, 4, (u8 *)&hw_time);
+	ds2404_read_memory(chip, 0x203, 4, (u8 *)&hw_time);
 	time = le32_to_cpu(hw_time);
 
 	rtc_time64_to_tm(time, dt);
@@ -193,8 +168,9 @@ static int ds2404_read_time(struct device *dev, struct rtc_time *dt)
 
 static int ds2404_set_time(struct device *dev, struct rtc_time *dt)
 {
+	struct ds2404 *chip = dev_get_drvdata(dev);
 	u32 time = cpu_to_le32(rtc_tm_to_time64(dt));
-	ds2404_write_memory(dev, 0x203, 4, (u8 *)&time);
+	ds2404_write_memory(chip, 0x203, 4, (u8 *)&time);
 	return 0;
 }
 
@@ -205,7 +181,6 @@ static const struct rtc_class_ops ds2404_rtc_ops = {
 
 static int rtc_probe(struct platform_device *pdev)
 {
-	struct ds2404_platform_data *pdata = dev_get_platdata(&pdev->dev);
 	struct ds2404 *chip;
 	int retval = -EBUSY;
 
@@ -213,22 +188,16 @@ static int rtc_probe(struct platform_device *pdev)
 	if (!chip)
 		return -ENOMEM;
 
+	chip->dev = &pdev->dev;
+
 	chip->rtc = devm_rtc_allocate_device(&pdev->dev);
 	if (IS_ERR(chip->rtc))
 		return PTR_ERR(chip->rtc);
 
-	retval = ds2404_gpio_map(chip, pdev, pdata);
+	retval = ds2404_gpio_map(chip, pdev);
 	if (retval)
 		return retval;
 
-	retval = devm_add_action_or_reset(&pdev->dev, ds2404_gpio_unmap, chip);
-	if (retval)
-		return retval;
-
-	dev_info(&pdev->dev, "using GPIOs RST:%d, CLK:%d, DQ:%d\n",
-		 chip->gpio[DS2404_RST].gpio, chip->gpio[DS2404_CLK].gpio,
-		 chip->gpio[DS2404_DQ].gpio);
-
 	platform_set_drvdata(pdev, chip);
 
 	chip->rtc->ops = &ds2404_rtc_ops;
@@ -238,7 +207,7 @@ static int rtc_probe(struct platform_device *pdev)
 	if (retval)
 		return retval;
 
-	ds2404_enable_osc(&pdev->dev);
+	ds2404_enable_osc(chip);
 	return 0;
 }
 
diff --git a/include/linux/platform_data/rtc-ds2404.h b/include/linux/platform_data/rtc-ds2404.h
deleted file mode 100644
index 22c53825528f..000000000000
--- a/include/linux/platform_data/rtc-ds2404.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * ds2404.h - platform data structure for the DS2404 RTC.
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2012 Sven Schnelle <svens@stackframe.org>
- */
-
-#ifndef __LINUX_DS2404_H
-#define __LINUX_DS2404_H
-
-struct ds2404_platform_data {
-
-	unsigned int gpio_rst;
-	unsigned int gpio_clk;
-	unsigned int gpio_dq;
-};
-#endif

From 4e5eb7ef73c4c45e2e621eb51a76565153b63afe Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Mon, 31 Jul 2023 17:09:30 +0300
Subject: [PATCH 0455/1189] rtc: pcf2127: fix error code in pcf2127_enable_ts()

This error path accidentally returns success.  Return -EINVAL instead.

Fixes: 420cc9e850db ("rtc: pcf2127: add support for multiple TS functions")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Bruno Thomsen <bruno.thomsen@gmail.com>
Reviewed-by: Hugo Villeneuve <hugo@hugovil.com>
Reviewed-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/55b9c84b-9d21-444f-b91a-cf9316b65833@moroto.mountain
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-pcf2127.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index 78141bb06ab0..988cad171174 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -1060,7 +1060,7 @@ static int pcf2127_enable_ts(struct device *dev, int ts_id)
 	if (pcf2127->cfg->ts[ts_id].gnd_detect_bit == 0) {
 		dev_err(dev, "%s: tamper detection to GND configuration invalid\n",
 			__func__);
-		return ret;
+		return -EINVAL;
 	}
 
 	/*

From e4163fc59d088caf3250cc9c9862239a954d85b5 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Fri, 28 Jul 2023 13:12:12 -0400
Subject: [PATCH 0456/1189] rtc: pcf2127: add error checking when disabling
 POR0

If PCF2127 device is absent from the I2C bus, or if there is a
communication problem, disabling POR0 may fail silently and we
still continue with probing the device. In that case, abort probe
operation.

Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20230728171211.3016019-1-hugo@hugovil.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-pcf2127.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index 988cad171174..f10bffc9e487 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -1192,8 +1192,10 @@ static int pcf2127_probe(struct device *dev, struct regmap *regmap,
 	 * The "Power-On Reset Override" facility prevents the RTC to do a reset
 	 * after power on. For normal operation the PORO must be disabled.
 	 */
-	regmap_clear_bits(pcf2127->regmap, PCF2127_REG_CTRL1,
+	ret = regmap_clear_bits(pcf2127->regmap, PCF2127_REG_CTRL1,
 				PCF2127_BIT_CTRL1_POR_OVRD);
+	if (ret < 0)
+		return ret;
 
 	ret = regmap_read(pcf2127->regmap, pcf2127->cfg->reg_clkout, &val);
 	if (ret < 0)

From 58dffa96e62ccf30ecba718f124ce822ddc1150a Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Tue, 1 Aug 2023 15:04:32 -0400
Subject: [PATCH 0457/1189] rtc: pcf2127: remove unused function argument
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fixes the following W=1 kernel build warning(s):

drivers/rtc/rtc-pcf2127.c: In function ‘pcf2127_probe’:
drivers/rtc/rtc-pcf2127.c:635:32: warning: unused parameter ‘name’ [-Wunused-parameter]
  635 |     int alarm_irq, const char *name, bool is_pcf2127)
      |                    ~~~~~~~~~~~~^~~~

Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20230801190432.3340545-1-hugo@hugovil.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-pcf2127.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index f10bffc9e487..de8164e1b562 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -1103,7 +1103,7 @@ static int pcf2127_configure_interrupt_pins(struct device *dev)
 }
 
 static int pcf2127_probe(struct device *dev, struct regmap *regmap,
-			 int alarm_irq, const char *name, const struct pcf21xx_config *config)
+			 int alarm_irq, const struct pcf21xx_config *config)
 {
 	struct pcf2127 *pcf2127;
 	int ret = 0;
@@ -1402,8 +1402,7 @@ static int pcf2127_i2c_probe(struct i2c_client *client)
 		return PTR_ERR(regmap);
 	}
 
-	return pcf2127_probe(&client->dev, regmap, client->irq,
-			     pcf2127_i2c_driver.driver.name, variant);
+	return pcf2127_probe(&client->dev, regmap, client->irq, variant);
 }
 
 static struct i2c_driver pcf2127_i2c_driver = {
@@ -1475,9 +1474,7 @@ static int pcf2127_spi_probe(struct spi_device *spi)
 		return PTR_ERR(regmap);
 	}
 
-	return pcf2127_probe(&spi->dev, regmap, spi->irq,
-			     pcf2127_spi_driver.driver.name,
-			     variant);
+	return pcf2127_probe(&spi->dev, regmap, spi->irq, variant);
 }
 
 static const struct spi_device_id pcf2127_spi_id[] = {

From ed17a2bcbb75505bb979e3e8ecb6c5fb2518bf3b Mon Sep 17 00:00:00 2001
From: Samuel Holland <samuel.holland@sifive.com>
Date: Mon, 17 Jul 2023 12:09:37 -0700
Subject: [PATCH 0458/1189] rtc: da9063: Mark the alarm IRQ as a wake IRQ

This keeps the IRQ enabled during system suspend, if the RTC's wakeup
source is enabled. Since the IRQ is not required to wake from shutdown,
continue to add the wakeup source even if registering the wakeirq fails.
See commit 029d3a6f2f3c ("rtc: da9063: add as wakeup source").

Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
Link: https://lore.kernel.org/r/20230717190937.1301509-1-samuel.holland@sifive.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-da9063.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/rtc/rtc-da9063.c b/drivers/rtc/rtc-da9063.c
index ee2efb496174..2f5d60622564 100644
--- a/drivers/rtc/rtc-da9063.c
+++ b/drivers/rtc/rtc-da9063.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
+#include <linux/pm_wakeirq.h>
 #include <linux/regmap.h>
 #include <linux/rtc.h>
 #include <linux/slab.h>
@@ -496,6 +497,12 @@ static int da9063_rtc_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev, "Failed to request ALARM IRQ %d: %d\n",
 			irq_alarm, ret);
 
+	ret = dev_pm_set_wake_irq(&pdev->dev, irq_alarm);
+	if (ret)
+		dev_warn(&pdev->dev,
+			 "Failed to set IRQ %d as a wake IRQ: %d\n",
+			 irq_alarm, ret);
+
 	device_init_wakeup(&pdev->dev, true);
 
 	return devm_rtc_register_device(rtc->rtc_dev);

From 0197a7cb44872e49919b0068a512aaf4e06f1850 Mon Sep 17 00:00:00 2001
From: Varshini Rajendran <varshini.rajendran@microchip.com>
Date: Fri, 28 Jul 2023 15:57:10 +0530
Subject: [PATCH 0459/1189] dt-bindings: rtc: at91rm9200: add sam9x7 compatible

Add compatible for SAM9X7 RTC.

Signed-off-by: Varshini Rajendran <varshini.rajendran@microchip.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20230728102710.266457-1-varshini.rajendran@microchip.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 .../bindings/rtc/atmel,at91rm9200-rtc.yaml     | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/Documentation/devicetree/bindings/rtc/atmel,at91rm9200-rtc.yaml b/Documentation/devicetree/bindings/rtc/atmel,at91rm9200-rtc.yaml
index 4d2bef15fb7a..c8bb2eef442d 100644
--- a/Documentation/devicetree/bindings/rtc/atmel,at91rm9200-rtc.yaml
+++ b/Documentation/devicetree/bindings/rtc/atmel,at91rm9200-rtc.yaml
@@ -14,13 +14,17 @@ maintainers:
 
 properties:
   compatible:
-    enum:
-      - atmel,at91rm9200-rtc
-      - atmel,at91sam9x5-rtc
-      - atmel,sama5d4-rtc
-      - atmel,sama5d2-rtc
-      - microchip,sam9x60-rtc
-      - microchip,sama7g5-rtc
+    oneOf:
+      - enum:
+          - atmel,at91rm9200-rtc
+          - atmel,at91sam9x5-rtc
+          - atmel,sama5d4-rtc
+          - atmel,sama5d2-rtc
+          - microchip,sam9x60-rtc
+          - microchip,sama7g5-rtc
+      - items:
+          - const: microchip,sam9x7-rtc
+          - const: microchip,sam9x60-rtc
 
   reg:
     maxItems: 1

From 4d349a5793f7a42da27ea56d9f6e2f9488d44e0d Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Thu, 3 Aug 2023 16:07:12 +0800
Subject: [PATCH 0460/1189] rtc: omap: Do not check for 0 return after calling
 platform_get_irq()

It is not possible for platform_get_irq() to return 0. Use the
return value from platform_get_irq().

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Link: https://lore.kernel.org/r/20230803080713.4061782-2-ruanjinjie@huawei.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-omap.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/rtc/rtc-omap.c b/drivers/rtc/rtc-omap.c
index 8ae4d7824ec9..5b10ab06cd2e 100644
--- a/drivers/rtc/rtc-omap.c
+++ b/drivers/rtc/rtc-omap.c
@@ -747,12 +747,12 @@ static int omap_rtc_probe(struct platform_device *pdev)
 	}
 
 	rtc->irq_timer = platform_get_irq(pdev, 0);
-	if (rtc->irq_timer <= 0)
-		return -ENOENT;
+	if (rtc->irq_timer < 0)
+		return rtc->irq_timer;
 
 	rtc->irq_alarm = platform_get_irq(pdev, 1);
-	if (rtc->irq_alarm <= 0)
-		return -ENOENT;
+	if (rtc->irq_alarm < 0)
+		return rtc->irq_alarm;
 
 	rtc->clk = devm_clk_get(&pdev->dev, "ext-clk");
 	if (!IS_ERR(rtc->clk))

From dac7837848485bf1d0bd3aa56923f8bf5075682f Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Thu, 3 Aug 2023 16:07:13 +0800
Subject: [PATCH 0461/1189] rtc: tps65910: Remove redundant dev_warn() and do
 not check for 0 return after calling platform_get_irq()

It is not possible for platform_get_irq() to return 0. Use the
return value from platform_get_irq().

And there is no need to call the dev_warn() function directly to print
a custom message when handling an error from platform_get_irq()
function as it is going to display an appropriate error message
in case of a failure.

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Link: https://lore.kernel.org/r/20230803080713.4061782-3-ruanjinjie@huawei.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-tps65910.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/rtc/rtc-tps65910.c b/drivers/rtc/rtc-tps65910.c
index 75e4c2d777b9..411ff66c0468 100644
--- a/drivers/rtc/rtc-tps65910.c
+++ b/drivers/rtc/rtc-tps65910.c
@@ -406,11 +406,8 @@ static int tps65910_rtc_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, tps_rtc);
 
 	irq  = platform_get_irq(pdev, 0);
-	if (irq <= 0) {
-		dev_warn(&pdev->dev, "Wake up is not possible as irq = %d\n",
-			irq);
-		return -ENXIO;
-	}
+	if (irq < 0)
+		return irq;
 
 	ret = devm_request_threaded_irq(&pdev->dev, irq, NULL,
 		tps65910_rtc_interrupt, IRQF_TRIGGER_LOW,

From a1342c8027288e345cc5fd16c6800f9d4eb788ed Mon Sep 17 00:00:00 2001
From: David Matlack <dmatlack@google.com>
Date: Fri, 11 Aug 2023 04:51:14 +0000
Subject: [PATCH 0462/1189] KVM: Rename kvm_arch_flush_remote_tlb() to
 kvm_arch_flush_remote_tlbs()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Rename kvm_arch_flush_remote_tlb() and the associated macro
__KVM_HAVE_ARCH_FLUSH_REMOTE_TLB to kvm_arch_flush_remote_tlbs() and
__KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS respectively.

Making the name plural matches kvm_flush_remote_tlbs() and makes it more
clear that this function can affect more than one remote TLB.

No functional change intended.

Signed-off-by: David Matlack <dmatlack@google.com>
Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Acked-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230811045127.3308641-2-rananta@google.com
---
 arch/mips/include/asm/kvm_host.h | 4 ++--
 arch/mips/kvm/mips.c             | 2 +-
 arch/x86/include/asm/kvm_host.h  | 4 ++--
 include/linux/kvm_host.h         | 4 ++--
 virt/kvm/kvm_main.c              | 2 +-
 5 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 04cedf9f8811..9b0ad8f3bf32 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -896,7 +896,7 @@ static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
 
-#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLB
-int kvm_arch_flush_remote_tlb(struct kvm *kvm);
+#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS
+int kvm_arch_flush_remote_tlbs(struct kvm *kvm);
 
 #endif /* __MIPS_KVM_HOST_H__ */
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index aa5583a7b05b..4b7bc39a4173 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -981,7 +981,7 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
 
 }
 
-int kvm_arch_flush_remote_tlb(struct kvm *kvm)
+int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
 {
 	kvm_mips_callbacks->prepare_flush_shadow(kvm);
 	return 1;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 28bd38303d70..a2d3cfc2eb75 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1794,8 +1794,8 @@ static inline struct kvm *kvm_arch_alloc_vm(void)
 #define __KVM_HAVE_ARCH_VM_FREE
 void kvm_arch_free_vm(struct kvm *kvm);
 
-#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLB
-static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm)
+#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS
+static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
 {
 	if (kvm_x86_ops.flush_remote_tlbs &&
 	    !static_call(kvm_x86_flush_remote_tlbs)(kvm))
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 9d3ac7720da9..e3f968b38ae9 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1479,8 +1479,8 @@ static inline void kvm_arch_free_vm(struct kvm *kvm)
 }
 #endif
 
-#ifndef __KVM_HAVE_ARCH_FLUSH_REMOTE_TLB
-static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm)
+#ifndef __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS
+static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
 {
 	return -ENOTSUPP;
 }
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index dfbaafbe3a00..70e5479797ac 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -361,7 +361,7 @@ void kvm_flush_remote_tlbs(struct kvm *kvm)
 	 * kvm_make_all_cpus_request() reads vcpu->mode. We reuse that
 	 * barrier here.
 	 */
-	if (!kvm_arch_flush_remote_tlb(kvm)
+	if (!kvm_arch_flush_remote_tlbs(kvm)
 	    || kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))
 		++kvm->stat.generic.remote_tlb_flush;
 }

From cfb0c08e80120928dda1e951718be135abd49bae Mon Sep 17 00:00:00 2001
From: Raghavendra Rao Ananta <rananta@google.com>
Date: Fri, 11 Aug 2023 04:51:15 +0000
Subject: [PATCH 0463/1189] KVM: Declare kvm_arch_flush_remote_tlbs() globally

There's no reason for the architectures to declare
kvm_arch_flush_remote_tlbs() in their own headers. Hence to
avoid this duplication, make the declaration global, leaving
the architectures to define only __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS
as needed.

Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230811045127.3308641-3-rananta@google.com
---
 arch/mips/include/asm/kvm_host.h | 1 -
 include/linux/kvm_host.h         | 2 ++
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 9b0ad8f3bf32..54a85f1d4f2c 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -897,6 +897,5 @@ static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
 
 #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS
-int kvm_arch_flush_remote_tlbs(struct kvm *kvm);
 
 #endif /* __MIPS_KVM_HOST_H__ */
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index e3f968b38ae9..ade5d4500c2c 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1484,6 +1484,8 @@ static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
 {
 	return -ENOTSUPP;
 }
+#else
+int kvm_arch_flush_remote_tlbs(struct kvm *kvm);
 #endif
 
 #ifdef __KVM_HAVE_ARCH_NONCOHERENT_DMA

From 32121c813818a87ba7565b3afce93a9cc3610a22 Mon Sep 17 00:00:00 2001
From: Raghavendra Rao Ananta <rananta@google.com>
Date: Fri, 11 Aug 2023 04:51:16 +0000
Subject: [PATCH 0464/1189] KVM: arm64: Use kvm_arch_flush_remote_tlbs()

Stop depending on CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL and opt to
standardize on kvm_arch_flush_remote_tlbs() since it avoids
duplicating the generic TLB stats across architectures that implement
their own remote TLB flush.

This adds an extra function call to the ARM64 kvm_flush_remote_tlbs()
path, but that is a small cost in comparison to flushing remote TLBs.

In addition, instead of just incrementing remote_tlb_flush_requests
stat, the generic interface would also increment the
remote_tlb_flush stat.

Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230811045127.3308641-4-rananta@google.com
---
 arch/arm64/include/asm/kvm_host.h | 2 ++
 arch/arm64/kvm/Kconfig            | 1 -
 arch/arm64/kvm/mmu.c              | 6 +++---
 3 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index d3dd05bbfe23..44ae44b502cf 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1113,6 +1113,8 @@ int __init kvm_set_ipa_limit(void);
 #define __KVM_HAVE_ARCH_VM_ALLOC
 struct kvm *kvm_arch_alloc_vm(void);
 
+#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS
+
 static inline bool kvm_vm_is_protected(struct kvm *kvm)
 {
 	return false;
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index f531da6b362e..6b730fcfee37 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -25,7 +25,6 @@ menuconfig KVM
 	select MMU_NOTIFIER
 	select PREEMPT_NOTIFIERS
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
-	select HAVE_KVM_ARCH_TLB_FLUSH_ALL
 	select KVM_MMIO
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_XFER_TO_GUEST_WORK
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index d3b4feed460c..3494659d939c 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -161,15 +161,15 @@ static bool memslot_is_logging(struct kvm_memory_slot *memslot)
 }
 
 /**
- * kvm_flush_remote_tlbs() - flush all VM TLB entries for v7/8
+ * kvm_arch_flush_remote_tlbs() - flush all VM TLB entries for v7/8
  * @kvm:	pointer to kvm structure.
  *
  * Interface to HYP function to flush all VM TLB entries
  */
-void kvm_flush_remote_tlbs(struct kvm *kvm)
+int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
 {
-	++kvm->stat.generic.remote_tlb_flush_requests;
 	kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu);
+	return 0;
 }
 
 static bool kvm_is_device_pfn(unsigned long pfn)

From eddd21481011008792f4e647a5244f6e15970abc Mon Sep 17 00:00:00 2001
From: Raghavendra Rao Ananta <rananta@google.com>
Date: Fri, 11 Aug 2023 04:51:17 +0000
Subject: [PATCH 0465/1189] KVM: Remove CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

kvm_arch_flush_remote_tlbs() or CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL
are two mechanisms to solve the same problem, allowing
architecture-specific code to provide a non-IPI implementation of
remote TLB flushing.

Dropping CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL allows KVM to standardize
all architectures on kvm_arch_flush_remote_tlbs() instead of
maintaining two mechanisms.

Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230811045127.3308641-5-rananta@google.com
---
 virt/kvm/Kconfig    | 3 ---
 virt/kvm/kvm_main.c | 2 --
 2 files changed, 5 deletions(-)

diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index b74916de5183..484d0873061c 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -62,9 +62,6 @@ config HAVE_KVM_CPU_RELAX_INTERCEPT
 config KVM_VFIO
        bool
 
-config HAVE_KVM_ARCH_TLB_FLUSH_ALL
-       bool
-
 config HAVE_KVM_INVALID_WAKEUPS
        bool
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 70e5479797ac..d6b050786155 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -345,7 +345,6 @@ bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req)
 }
 EXPORT_SYMBOL_GPL(kvm_make_all_cpus_request);
 
-#ifndef CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL
 void kvm_flush_remote_tlbs(struct kvm *kvm)
 {
 	++kvm->stat.generic.remote_tlb_flush_requests;
@@ -366,7 +365,6 @@ void kvm_flush_remote_tlbs(struct kvm *kvm)
 		++kvm->stat.generic.remote_tlb_flush;
 }
 EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs);
-#endif
 
 static void kvm_flush_shadow_all(struct kvm *kvm)
 {

From d4788996051e3c07fadc6d9b214073fcf78810a8 Mon Sep 17 00:00:00 2001
From: David Matlack <dmatlack@google.com>
Date: Fri, 11 Aug 2023 04:51:18 +0000
Subject: [PATCH 0466/1189] KVM: Allow range-based TLB invalidation from common
 code

Make kvm_flush_remote_tlbs_range() visible in common code and create a
default implementation that just invalidates the whole TLB.

This paves the way for several future features/cleanups:

 - Introduction of range-based TLBI on ARM.
 - Eliminating kvm_arch_flush_remote_tlbs_memslot()
 - Moving the KVM/x86 TDP MMU to common code.

No functional change intended.

Signed-off-by: David Matlack <dmatlack@google.com>
Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Acked-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230811045127.3308641-6-rananta@google.com
---
 arch/x86/include/asm/kvm_host.h |  2 ++
 arch/x86/kvm/mmu/mmu.c          | 12 ++++--------
 arch/x86/kvm/mmu/mmu_internal.h |  3 ---
 include/linux/kvm_host.h        | 11 +++++++++++
 virt/kvm/kvm_main.c             | 13 +++++++++++++
 5 files changed, 30 insertions(+), 11 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index a2d3cfc2eb75..b547d17c58f6 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1804,6 +1804,8 @@ static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
 		return -ENOTSUPP;
 }
 
+#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE
+
 #define kvm_arch_pmi_in_guest(vcpu) \
 	((vcpu) && (vcpu)->arch.handling_intr_from_guest)
 
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index ec169f5c7dce..46ae672668e1 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -278,16 +278,12 @@ static inline bool kvm_available_flush_remote_tlbs_range(void)
 	return kvm_x86_ops.flush_remote_tlbs_range;
 }
 
-void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t start_gfn,
-				 gfn_t nr_pages)
+int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages)
 {
-	int ret = -EOPNOTSUPP;
+	if (!kvm_x86_ops.flush_remote_tlbs_range)
+		return -EOPNOTSUPP;
 
-	if (kvm_x86_ops.flush_remote_tlbs_range)
-		ret = static_call(kvm_x86_flush_remote_tlbs_range)(kvm, start_gfn,
-								   nr_pages);
-	if (ret)
-		kvm_flush_remote_tlbs(kvm);
+	return static_call(kvm_x86_flush_remote_tlbs_range)(kvm, gfn, nr_pages);
 }
 
 static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index);
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index d39af5639ce9..86cb83bb3480 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -170,9 +170,6 @@ bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
 				    struct kvm_memory_slot *slot, u64 gfn,
 				    int min_level);
 
-void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t start_gfn,
-				 gfn_t nr_pages);
-
 /* Flush the given page (huge or not) of guest memory. */
 static inline void kvm_flush_remote_tlbs_gfn(struct kvm *kvm, gfn_t gfn, int level)
 {
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index ade5d4500c2c..89d2614e4b7a 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1359,6 +1359,7 @@ int kvm_vcpu_yield_to(struct kvm_vcpu *target);
 void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool yield_to_kernel_mode);
 
 void kvm_flush_remote_tlbs(struct kvm *kvm);
+void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages);
 
 #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE
 int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min);
@@ -1488,6 +1489,16 @@ static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
 int kvm_arch_flush_remote_tlbs(struct kvm *kvm);
 #endif
 
+#ifndef __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE
+static inline int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm,
+						    gfn_t gfn, u64 nr_pages)
+{
+	return -EOPNOTSUPP;
+}
+#else
+int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages);
+#endif
+
 #ifdef __KVM_HAVE_ARCH_NONCOHERENT_DMA
 void kvm_arch_register_noncoherent_dma(struct kvm *kvm);
 void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index d6b050786155..26e91000f579 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -366,6 +366,19 @@ void kvm_flush_remote_tlbs(struct kvm *kvm)
 }
 EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs);
 
+void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages)
+{
+	if (!kvm_arch_flush_remote_tlbs_range(kvm, gfn, nr_pages))
+		return;
+
+	/*
+	 * Fall back to a flushing entire TLBs if the architecture range-based
+	 * TLB invalidation is unsupported or can't be performed for whatever
+	 * reason.
+	 */
+	kvm_flush_remote_tlbs(kvm);
+}
+
 static void kvm_flush_shadow_all(struct kvm *kvm)
 {
 	kvm_arch_flush_shadow_all(kvm);

From 619b5072443c05cf18c31b2c0320cdb42396d411 Mon Sep 17 00:00:00 2001
From: David Matlack <dmatlack@google.com>
Date: Fri, 11 Aug 2023 04:51:19 +0000
Subject: [PATCH 0467/1189] KVM: Move kvm_arch_flush_remote_tlbs_memslot() to
 common code

Move kvm_arch_flush_remote_tlbs_memslot() to common code and drop
"arch_" from the name. kvm_arch_flush_remote_tlbs_memslot() is just a
range-based TLB invalidation where the range is defined by the memslot.
Now that kvm_flush_remote_tlbs_range() can be called from common code we
can just use that and drop a bunch of duplicate code from the arch
directories.

Note this adds a lockdep assertion for slots_lock being held when
calling kvm_flush_remote_tlbs_memslot(), which was previously only
asserted on x86. MIPS has calls to kvm_flush_remote_tlbs_memslot(),
but they all hold the slots_lock, so the lockdep assertion continues to
hold true.

Also drop the CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT ifdef gating
kvm_flush_remote_tlbs_memslot(), since it is no longer necessary.

Signed-off-by: David Matlack <dmatlack@google.com>
Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Acked-by: Anup Patel <anup@brainfault.org>
Acked-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230811045127.3308641-7-rananta@google.com
---
 arch/arm64/kvm/arm.c     |  6 ------
 arch/mips/kvm/mips.c     | 10 ++--------
 arch/riscv/kvm/mmu.c     |  6 ------
 arch/x86/kvm/mmu/mmu.c   | 16 +---------------
 arch/x86/kvm/x86.c       |  2 +-
 include/linux/kvm_host.h |  7 +++----
 virt/kvm/kvm_main.c      | 18 ++++++++++++++++--
 7 files changed, 23 insertions(+), 42 deletions(-)

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 72dc53a75d1c..fd2af63d788d 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -1532,12 +1532,6 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
 
 }
 
-void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm,
-					const struct kvm_memory_slot *memslot)
-{
-	kvm_flush_remote_tlbs(kvm);
-}
-
 static int kvm_vm_ioctl_set_device_addr(struct kvm *kvm,
 					struct kvm_arm_device_addr *dev_addr)
 {
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 4b7bc39a4173..231ac052b506 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -199,7 +199,7 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 	/* Flush slot from GPA */
 	kvm_mips_flush_gpa_pt(kvm, slot->base_gfn,
 			      slot->base_gfn + slot->npages - 1);
-	kvm_arch_flush_remote_tlbs_memslot(kvm, slot);
+	kvm_flush_remote_tlbs_memslot(kvm, slot);
 	spin_unlock(&kvm->mmu_lock);
 }
 
@@ -235,7 +235,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 		needs_flush = kvm_mips_mkclean_gpa_pt(kvm, new->base_gfn,
 					new->base_gfn + new->npages - 1);
 		if (needs_flush)
-			kvm_arch_flush_remote_tlbs_memslot(kvm, new);
+			kvm_flush_remote_tlbs_memslot(kvm, new);
 		spin_unlock(&kvm->mmu_lock);
 	}
 }
@@ -987,12 +987,6 @@ int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
 	return 1;
 }
 
-void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm,
-					const struct kvm_memory_slot *memslot)
-{
-	kvm_flush_remote_tlbs(kvm);
-}
-
 int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 {
 	int r;
diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index f2eb47925806..97e129620686 100644
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -406,12 +406,6 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
 {
 }
 
-void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm,
-					const struct kvm_memory_slot *memslot)
-{
-	kvm_flush_remote_tlbs(kvm);
-}
-
 void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free)
 {
 }
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 46ae672668e1..dbf3c6c2316c 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -6666,7 +6666,7 @@ static void kvm_rmap_zap_collapsible_sptes(struct kvm *kvm,
 	 */
 	if (walk_slot_rmaps(kvm, slot, kvm_mmu_zap_collapsible_spte,
 			    PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL - 1, true))
-		kvm_arch_flush_remote_tlbs_memslot(kvm, slot);
+		kvm_flush_remote_tlbs_memslot(kvm, slot);
 }
 
 void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
@@ -6685,20 +6685,6 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
 	}
 }
 
-void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm,
-					const struct kvm_memory_slot *memslot)
-{
-	/*
-	 * All current use cases for flushing the TLBs for a specific memslot
-	 * related to dirty logging, and many do the TLB flush out of mmu_lock.
-	 * The interaction between the various operations on memslot must be
-	 * serialized by slots_locks to ensure the TLB flush from one operation
-	 * is observed by any other operation on the same memslot.
-	 */
-	lockdep_assert_held(&kvm->slots_lock);
-	kvm_flush_remote_tlbs_range(kvm, memslot->base_gfn, memslot->npages);
-}
-
 void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
 				   const struct kvm_memory_slot *memslot)
 {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a6b9bea62fb8..faeb2e307b36 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12751,7 +12751,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm,
 		 * See is_writable_pte() for more details (the case involving
 		 * access-tracked SPTEs is particularly relevant).
 		 */
-		kvm_arch_flush_remote_tlbs_memslot(kvm, new);
+		kvm_flush_remote_tlbs_memslot(kvm, new);
 	}
 }
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 89d2614e4b7a..394db2ce11e2 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1360,6 +1360,8 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool yield_to_kernel_mode);
 
 void kvm_flush_remote_tlbs(struct kvm *kvm);
 void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages);
+void kvm_flush_remote_tlbs_memslot(struct kvm *kvm,
+				   const struct kvm_memory_slot *memslot);
 
 #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE
 int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min);
@@ -1388,10 +1390,7 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 					unsigned long mask);
 void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot);
 
-#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
-void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm,
-					const struct kvm_memory_slot *memslot);
-#else /* !CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */
+#ifndef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
 int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log);
 int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log,
 		      int *is_dirty, struct kvm_memory_slot **memslot);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 26e91000f579..5d4d2e051aa0 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -379,6 +379,20 @@ void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages)
 	kvm_flush_remote_tlbs(kvm);
 }
 
+void kvm_flush_remote_tlbs_memslot(struct kvm *kvm,
+				   const struct kvm_memory_slot *memslot)
+{
+	/*
+	 * All current use cases for flushing the TLBs for a specific memslot
+	 * are related to dirty logging, and many do the TLB flush out of
+	 * mmu_lock. The interaction between the various operations on memslot
+	 * must be serialized by slots_locks to ensure the TLB flush from one
+	 * operation is observed by any other operation on the same memslot.
+	 */
+	lockdep_assert_held(&kvm->slots_lock);
+	kvm_flush_remote_tlbs_range(kvm, memslot->base_gfn, memslot->npages);
+}
+
 static void kvm_flush_shadow_all(struct kvm *kvm)
 {
 	kvm_arch_flush_shadow_all(kvm);
@@ -2191,7 +2205,7 @@ static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log)
 	}
 
 	if (flush)
-		kvm_arch_flush_remote_tlbs_memslot(kvm, memslot);
+		kvm_flush_remote_tlbs_memslot(kvm, memslot);
 
 	if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n))
 		return -EFAULT;
@@ -2308,7 +2322,7 @@ static int kvm_clear_dirty_log_protect(struct kvm *kvm,
 	KVM_MMU_UNLOCK(kvm);
 
 	if (flush)
-		kvm_arch_flush_remote_tlbs_memslot(kvm, memslot);
+		kvm_flush_remote_tlbs_memslot(kvm, memslot);
 
 	return 0;
 }

From 360839027a6e4c022e8cbaa373dd747185f1e0a5 Mon Sep 17 00:00:00 2001
From: Raghavendra Rao Ananta <rananta@google.com>
Date: Fri, 11 Aug 2023 04:51:20 +0000
Subject: [PATCH 0468/1189] arm64: tlb: Refactor the core flush algorithm of
 __flush_tlb_range

Currently, the core TLB flush functionality of __flush_tlb_range()
hardcodes vae1is (and variants) for the flush operation. In the
upcoming patches, the KVM code reuses this core algorithm with
ipas2e1is for range based TLB invalidations based on the IPA.
Hence, extract the core flush functionality of __flush_tlb_range()
into its own macro that accepts an 'op' argument to pass any
TLBI operation, such that other callers (KVM) can benefit.

No functional changes intended.

Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230811045127.3308641-8-rananta@google.com
---
 arch/arm64/include/asm/tlbflush.h | 119 +++++++++++++++++-------------
 1 file changed, 67 insertions(+), 52 deletions(-)

diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index 412a3b9a3c25..b9475a852d5b 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -278,14 +278,74 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
  */
 #define MAX_TLBI_OPS	PTRS_PER_PTE
 
+/*
+ * __flush_tlb_range_op - Perform TLBI operation upon a range
+ *
+ * @op:	TLBI instruction that operates on a range (has 'r' prefix)
+ * @start:	The start address of the range
+ * @pages:	Range as the number of pages from 'start'
+ * @stride:	Flush granularity
+ * @asid:	The ASID of the task (0 for IPA instructions)
+ * @tlb_level:	Translation Table level hint, if known
+ * @tlbi_user:	If 'true', call an additional __tlbi_user()
+ *              (typically for user ASIDs). 'flase' for IPA instructions
+ *
+ * When the CPU does not support TLB range operations, flush the TLB
+ * entries one by one at the granularity of 'stride'. If the TLB
+ * range ops are supported, then:
+ *
+ * 1. If 'pages' is odd, flush the first page through non-range
+ *    operations;
+ *
+ * 2. For remaining pages: the minimum range granularity is decided
+ *    by 'scale', so multiple range TLBI operations may be required.
+ *    Start from scale = 0, flush the corresponding number of pages
+ *    ((num+1)*2^(5*scale+1) starting from 'addr'), then increase it
+ *    until no pages left.
+ *
+ * Note that certain ranges can be represented by either num = 31 and
+ * scale or num = 0 and scale + 1. The loop below favours the latter
+ * since num is limited to 30 by the __TLBI_RANGE_NUM() macro.
+ */
+#define __flush_tlb_range_op(op, start, pages, stride,			\
+				asid, tlb_level, tlbi_user)		\
+do {									\
+	int num = 0;							\
+	int scale = 0;							\
+	unsigned long addr;						\
+									\
+	while (pages > 0) {						\
+		if (!system_supports_tlb_range() ||			\
+		    pages % 2 == 1) {					\
+			addr = __TLBI_VADDR(start, asid);		\
+			__tlbi_level(op, addr, tlb_level);		\
+			if (tlbi_user)					\
+				__tlbi_user_level(op, addr, tlb_level);	\
+			start += stride;				\
+			pages -= stride >> PAGE_SHIFT;			\
+			continue;					\
+		}							\
+									\
+		num = __TLBI_RANGE_NUM(pages, scale);			\
+		if (num >= 0) {						\
+			addr = __TLBI_VADDR_RANGE(start, asid, scale,	\
+						  num, tlb_level);	\
+			__tlbi(r##op, addr);				\
+			if (tlbi_user)					\
+				__tlbi_user(r##op, addr);		\
+			start += __TLBI_RANGE_PAGES(num, scale) << PAGE_SHIFT; \
+			pages -= __TLBI_RANGE_PAGES(num, scale);	\
+		}							\
+		scale++;						\
+	}								\
+} while (0)
+
 static inline void __flush_tlb_range(struct vm_area_struct *vma,
 				     unsigned long start, unsigned long end,
 				     unsigned long stride, bool last_level,
 				     int tlb_level)
 {
-	int num = 0;
-	int scale = 0;
-	unsigned long asid, addr, pages;
+	unsigned long asid, pages;
 
 	start = round_down(start, stride);
 	end = round_up(end, stride);
@@ -307,56 +367,11 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma,
 	dsb(ishst);
 	asid = ASID(vma->vm_mm);
 
-	/*
-	 * When the CPU does not support TLB range operations, flush the TLB
-	 * entries one by one at the granularity of 'stride'. If the TLB
-	 * range ops are supported, then:
-	 *
-	 * 1. If 'pages' is odd, flush the first page through non-range
-	 *    operations;
-	 *
-	 * 2. For remaining pages: the minimum range granularity is decided
-	 *    by 'scale', so multiple range TLBI operations may be required.
-	 *    Start from scale = 0, flush the corresponding number of pages
-	 *    ((num+1)*2^(5*scale+1) starting from 'addr'), then increase it
-	 *    until no pages left.
-	 *
-	 * Note that certain ranges can be represented by either num = 31 and
-	 * scale or num = 0 and scale + 1. The loop below favours the latter
-	 * since num is limited to 30 by the __TLBI_RANGE_NUM() macro.
-	 */
-	while (pages > 0) {
-		if (!system_supports_tlb_range() ||
-		    pages % 2 == 1) {
-			addr = __TLBI_VADDR(start, asid);
-			if (last_level) {
-				__tlbi_level(vale1is, addr, tlb_level);
-				__tlbi_user_level(vale1is, addr, tlb_level);
-			} else {
-				__tlbi_level(vae1is, addr, tlb_level);
-				__tlbi_user_level(vae1is, addr, tlb_level);
-			}
-			start += stride;
-			pages -= stride >> PAGE_SHIFT;
-			continue;
-		}
+	if (last_level)
+		__flush_tlb_range_op(vale1is, start, pages, stride, asid, tlb_level, true);
+	else
+		__flush_tlb_range_op(vae1is, start, pages, stride, asid, tlb_level, true);
 
-		num = __TLBI_RANGE_NUM(pages, scale);
-		if (num >= 0) {
-			addr = __TLBI_VADDR_RANGE(start, asid, scale,
-						  num, tlb_level);
-			if (last_level) {
-				__tlbi(rvale1is, addr);
-				__tlbi_user(rvale1is, addr);
-			} else {
-				__tlbi(rvae1is, addr);
-				__tlbi_user(rvae1is, addr);
-			}
-			start += __TLBI_RANGE_PAGES(num, scale) << PAGE_SHIFT;
-			pages -= __TLBI_RANGE_PAGES(num, scale);
-		}
-		scale++;
-	}
 	dsb(ish);
 }
 

From 4d73a9c13aaa78b149ac04b02f0ee7973f233bfa Mon Sep 17 00:00:00 2001
From: Raghavendra Rao Ananta <rananta@google.com>
Date: Fri, 11 Aug 2023 04:51:21 +0000
Subject: [PATCH 0469/1189] arm64: tlb: Implement __flush_s2_tlb_range_op()

Define __flush_s2_tlb_range_op(), as a wrapper over
__flush_tlb_range_op(), for stage-2 specific range-based TLBI
operations that doesn't necessarily have to deal with 'asid'
and 'tlbi_user' arguments.

Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230811045127.3308641-9-rananta@google.com
---
 arch/arm64/include/asm/tlbflush.h | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index b9475a852d5b..93f4b397f9a1 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -340,6 +340,9 @@ do {									\
 	}								\
 } while (0)
 
+#define __flush_s2_tlb_range_op(op, start, pages, stride, tlb_level) \
+	__flush_tlb_range_op(op, start, pages, stride, 0, tlb_level, false)
+
 static inline void __flush_tlb_range(struct vm_area_struct *vma,
 				     unsigned long start, unsigned long end,
 				     unsigned long stride, bool last_level,

From 6354d15052ec88273c24beae4c99e31c3d3889b6 Mon Sep 17 00:00:00 2001
From: Raghavendra Rao Ananta <rananta@google.com>
Date: Fri, 11 Aug 2023 04:51:22 +0000
Subject: [PATCH 0470/1189] KVM: arm64: Implement __kvm_tlb_flush_vmid_range()

Define  __kvm_tlb_flush_vmid_range() (for VHE and nVHE)
to flush a range of stage-2 page-tables using IPA in one go.
If the system supports FEAT_TLBIRANGE, the following patches
would conveniently replace global TLBI such as vmalls12e1is
in the map, unmap, and dirty-logging paths with ripas2e1is
instead.

Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230811045127.3308641-10-rananta@google.com
---
 arch/arm64/include/asm/kvm_asm.h   |  3 +++
 arch/arm64/kvm/hyp/nvhe/hyp-main.c | 11 +++++++++++
 arch/arm64/kvm/hyp/nvhe/tlb.c      | 30 ++++++++++++++++++++++++++++++
 arch/arm64/kvm/hyp/vhe/tlb.c       | 28 ++++++++++++++++++++++++++++
 4 files changed, 72 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 7d170aaa2db4..2c27cb8cf442 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -70,6 +70,7 @@ enum __kvm_host_smccc_func {
 	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa,
 	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa_nsh,
 	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid,
+	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_range,
 	__KVM_HOST_SMCCC_FUNC___kvm_flush_cpu_context,
 	__KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff,
 	__KVM_HOST_SMCCC_FUNC___vgic_v3_read_vmcr,
@@ -229,6 +230,8 @@ extern void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa,
 extern void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu,
 					 phys_addr_t ipa,
 					 int level);
+extern void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
+					phys_addr_t start, unsigned long pages);
 extern void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu);
 
 extern void __kvm_timer_set_cntvoff(u64 cntvoff);
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index a169c619db60..857d9bc04fd4 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -135,6 +135,16 @@ static void handle___kvm_tlb_flush_vmid_ipa_nsh(struct kvm_cpu_context *host_ctx
 	__kvm_tlb_flush_vmid_ipa_nsh(kern_hyp_va(mmu), ipa, level);
 }
 
+static void
+handle___kvm_tlb_flush_vmid_range(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
+	DECLARE_REG(phys_addr_t, start, host_ctxt, 2);
+	DECLARE_REG(unsigned long, pages, host_ctxt, 3);
+
+	__kvm_tlb_flush_vmid_range(kern_hyp_va(mmu), start, pages);
+}
+
 static void handle___kvm_tlb_flush_vmid(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
@@ -327,6 +337,7 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa),
 	HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa_nsh),
 	HANDLE_FUNC(__kvm_tlb_flush_vmid),
+	HANDLE_FUNC(__kvm_tlb_flush_vmid_range),
 	HANDLE_FUNC(__kvm_flush_cpu_context),
 	HANDLE_FUNC(__kvm_timer_set_cntvoff),
 	HANDLE_FUNC(__vgic_v3_read_vmcr),
diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
index b9991bbd8e3f..1b265713d6be 100644
--- a/arch/arm64/kvm/hyp/nvhe/tlb.c
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -182,6 +182,36 @@ void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu,
 	__tlb_switch_to_host(&cxt);
 }
 
+void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
+				phys_addr_t start, unsigned long pages)
+{
+	struct tlb_inv_context cxt;
+	unsigned long stride;
+
+	/*
+	 * Since the range of addresses may not be mapped at
+	 * the same level, assume the worst case as PAGE_SIZE
+	 */
+	stride = PAGE_SIZE;
+	start = round_down(start, stride);
+
+	/* Switch to requested VMID */
+	__tlb_switch_to_guest(mmu, &cxt, false);
+
+	__flush_s2_tlb_range_op(ipas2e1is, start, pages, stride, 0);
+
+	dsb(ish);
+	__tlbi(vmalle1is);
+	dsb(ish);
+	isb();
+
+	/* See the comment in __kvm_tlb_flush_vmid_ipa() */
+	if (icache_is_vpipt())
+		icache_inval_all_pou();
+
+	__tlb_switch_to_host(&cxt);
+}
+
 void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 {
 	struct tlb_inv_context cxt;
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
index e69da550cdc5..46bd43f61d76 100644
--- a/arch/arm64/kvm/hyp/vhe/tlb.c
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -143,6 +143,34 @@ void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu,
 	__tlb_switch_to_host(&cxt);
 }
 
+void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
+				phys_addr_t start, unsigned long pages)
+{
+	struct tlb_inv_context cxt;
+	unsigned long stride;
+
+	/*
+	 * Since the range of addresses may not be mapped at
+	 * the same level, assume the worst case as PAGE_SIZE
+	 */
+	stride = PAGE_SIZE;
+	start = round_down(start, stride);
+
+	dsb(ishst);
+
+	/* Switch to requested VMID */
+	__tlb_switch_to_guest(mmu, &cxt);
+
+	__flush_s2_tlb_range_op(ipas2e1is, start, pages, stride, 0);
+
+	dsb(ish);
+	__tlbi(vmalle1is);
+	dsb(ish);
+	isb();
+
+	__tlb_switch_to_host(&cxt);
+}
+
 void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 {
 	struct tlb_inv_context cxt;

From 117940aa6e5f8308f1529e1313660980f1dae771 Mon Sep 17 00:00:00 2001
From: Raghavendra Rao Ananta <rananta@google.com>
Date: Fri, 11 Aug 2023 04:51:23 +0000
Subject: [PATCH 0471/1189] KVM: arm64: Define kvm_tlb_flush_vmid_range()

Implement the helper kvm_tlb_flush_vmid_range() that acts
as a wrapper for range-based TLB invalidations. For the
given VMID, use the range-based TLBI instructions to do
the job or fallback to invalidating all the TLB entries.

Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230811045127.3308641-11-rananta@google.com
---
 arch/arm64/include/asm/kvm_pgtable.h | 10 ++++++++++
 arch/arm64/kvm/hyp/pgtable.c         | 20 ++++++++++++++++++++
 2 files changed, 30 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index 929d355eae0a..d3e354bb8351 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -746,4 +746,14 @@ enum kvm_pgtable_prot kvm_pgtable_stage2_pte_prot(kvm_pte_t pte);
  *	   kvm_pgtable_prot format.
  */
 enum kvm_pgtable_prot kvm_pgtable_hyp_pte_prot(kvm_pte_t pte);
+
+/**
+ * kvm_tlb_flush_vmid_range() - Invalidate/flush a range of TLB entries
+ *
+ * @mmu:	Stage-2 KVM MMU struct
+ * @addr:	The base Intermediate physical address from which to invalidate
+ * @size:	Size of the range from the base to invalidate
+ */
+void kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
+				phys_addr_t addr, size_t size);
 #endif	/* __ARM64_KVM_PGTABLE_H__ */
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index f7a93ef29250..fb58a229b744 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -670,6 +670,26 @@ static bool stage2_has_fwb(struct kvm_pgtable *pgt)
 	return !(pgt->flags & KVM_PGTABLE_S2_NOFWB);
 }
 
+void kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
+				phys_addr_t addr, size_t size)
+{
+	unsigned long pages, inval_pages;
+
+	if (!system_supports_tlb_range()) {
+		kvm_call_hyp(__kvm_tlb_flush_vmid, mmu);
+		return;
+	}
+
+	pages = size >> PAGE_SHIFT;
+	while (pages > 0) {
+		inval_pages = min(pages, MAX_TLBI_RANGE_PAGES);
+		kvm_call_hyp(__kvm_tlb_flush_vmid_range, mmu, addr, inval_pages);
+
+		addr += inval_pages << PAGE_SHIFT;
+		pages -= inval_pages;
+	}
+}
+
 #define KVM_S2_MEMATTR(pgt, attr) PAGE_S2_MEMATTR(attr, stage2_has_fwb(pgt))
 
 static int stage2_set_prot_attr(struct kvm_pgtable *pgt, enum kvm_pgtable_prot prot,

From c42b6f0b1cde4dd19e6b5dd052e67b87cc331b01 Mon Sep 17 00:00:00 2001
From: Raghavendra Rao Ananta <rananta@google.com>
Date: Fri, 11 Aug 2023 04:51:24 +0000
Subject: [PATCH 0472/1189] KVM: arm64: Implement
 kvm_arch_flush_remote_tlbs_range()

Implement kvm_arch_flush_remote_tlbs_range() for arm64
to invalidate the given range in the TLB.

Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230811045127.3308641-12-rananta@google.com
---
 arch/arm64/include/asm/kvm_host.h | 2 ++
 arch/arm64/kvm/mmu.c              | 8 ++++++++
 2 files changed, 10 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 44ae44b502cf..f623b989ddd1 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1115,6 +1115,8 @@ struct kvm *kvm_arch_alloc_vm(void);
 
 #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS
 
+#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE
+
 static inline bool kvm_vm_is_protected(struct kvm *kvm)
 {
 	return false;
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 3494659d939c..c73cec797519 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -172,6 +172,14 @@ int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
 	return 0;
 }
 
+int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm,
+				      gfn_t gfn, u64 nr_pages)
+{
+	kvm_tlb_flush_vmid_range(&kvm->arch.mmu,
+				gfn << PAGE_SHIFT, nr_pages << PAGE_SHIFT);
+	return 0;
+}
+
 static bool kvm_is_device_pfn(unsigned long pfn)
 {
 	return !pfn_is_map_memory(pfn);

From 3756b6f2bb3a242fef0867b39a23607f5aeca138 Mon Sep 17 00:00:00 2001
From: Raghavendra Rao Ananta <rananta@google.com>
Date: Fri, 11 Aug 2023 04:51:25 +0000
Subject: [PATCH 0473/1189] KVM: arm64: Flush only the memslot after
 write-protect

After write-protecting the region, currently KVM invalidates
the entire TLB entries using kvm_flush_remote_tlbs(). Instead,
scope the invalidation only to the targeted memslot. If
supported, the architecture would use the range-based TLBI
instructions to flush the memslot or else fallback to flushing
all of the TLBs.

Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230811045127.3308641-13-rananta@google.com
---
 arch/arm64/kvm/mmu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index c73cec797519..b16aff3f65f6 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1083,7 +1083,7 @@ static void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot)
 	write_lock(&kvm->mmu_lock);
 	stage2_wp_range(&kvm->arch.mmu, start, end);
 	write_unlock(&kvm->mmu_lock);
-	kvm_flush_remote_tlbs(kvm);
+	kvm_flush_remote_tlbs_memslot(kvm, memslot);
 }
 
 /**

From defc8cc7abf0fcee8d73e440ee02827348d060e0 Mon Sep 17 00:00:00 2001
From: Raghavendra Rao Ananta <rananta@google.com>
Date: Fri, 11 Aug 2023 04:51:26 +0000
Subject: [PATCH 0474/1189] KVM: arm64: Invalidate the table entries upon a
 range

Currently, during the operations such as a hugepage collapse,
KVM would flush the entire VM's context using 'vmalls12e1is'
TLBI operation. Specifically, if the VM is faulting on many
hugepages (say after dirty-logging), it creates a performance
penalty for the guest whose pages have already been faulted
earlier as they would have to refill their TLBs again.

Instead, leverage kvm_tlb_flush_vmid_range() for table entries.
If the system supports it, only the required range will be
flushed. Else, it'll fallback to the previous mechanism.

Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230811045127.3308641-14-rananta@google.com
---
 arch/arm64/kvm/hyp/pgtable.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index fb58a229b744..1a4af37fd8c0 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -806,7 +806,8 @@ static bool stage2_try_break_pte(const struct kvm_pgtable_visit_ctx *ctx,
 		 * evicted pte value (if any).
 		 */
 		if (kvm_pte_table(ctx->old, ctx->level))
-			kvm_call_hyp(__kvm_tlb_flush_vmid, mmu);
+			kvm_tlb_flush_vmid_range(mmu, ctx->addr,
+						kvm_granule_size(ctx->level));
 		else if (kvm_pte_valid(ctx->old))
 			kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu,
 				     ctx->addr, ctx->level);

From 7657ea920c54218f123ddc1b572821695b669c13 Mon Sep 17 00:00:00 2001
From: Raghavendra Rao Ananta <rananta@google.com>
Date: Fri, 11 Aug 2023 04:51:27 +0000
Subject: [PATCH 0475/1189] KVM: arm64: Use TLBI range-based instructions for
 unmap

The current implementation of the stage-2 unmap walker traverses
the given range and, as a part of break-before-make, performs
TLB invalidations with a DSB for every PTE. A multitude of this
combination could cause a performance bottleneck on some systems.

Hence, if the system supports FEAT_TLBIRANGE, defer the TLB
invalidations until the entire walk is finished, and then
use range-based instructions to invalidate the TLBs in one go.
Condition deferred TLB invalidation on the system supporting FWB,
as the optimization is entirely pointless when the unmap walker
needs to perform CMOs.

Rename stage2_put_pte() to stage2_unmap_put_pte() as the function
now serves the stage-2 unmap walker specifically, rather than
acting generic.

Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230811045127.3308641-15-rananta@google.com
---
 arch/arm64/kvm/hyp/pgtable.c | 40 +++++++++++++++++++++++++++++-------
 1 file changed, 33 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 1a4af37fd8c0..f155b8c9e98c 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -831,16 +831,36 @@ static void stage2_make_pte(const struct kvm_pgtable_visit_ctx *ctx, kvm_pte_t n
 	smp_store_release(ctx->ptep, new);
 }
 
-static void stage2_put_pte(const struct kvm_pgtable_visit_ctx *ctx, struct kvm_s2_mmu *mmu,
-			   struct kvm_pgtable_mm_ops *mm_ops)
+static bool stage2_unmap_defer_tlb_flush(struct kvm_pgtable *pgt)
 {
 	/*
-	 * Clear the existing PTE, and perform break-before-make with
-	 * TLB maintenance if it was valid.
+	 * If FEAT_TLBIRANGE is implemented, defer the individual
+	 * TLB invalidations until the entire walk is finished, and
+	 * then use the range-based TLBI instructions to do the
+	 * invalidations. Condition deferred TLB invalidation on the
+	 * system supporting FWB as the optimization is entirely
+	 * pointless when the unmap walker needs to perform CMOs.
+	 */
+	return system_supports_tlb_range() && stage2_has_fwb(pgt);
+}
+
+static void stage2_unmap_put_pte(const struct kvm_pgtable_visit_ctx *ctx,
+				struct kvm_s2_mmu *mmu,
+				struct kvm_pgtable_mm_ops *mm_ops)
+{
+	struct kvm_pgtable *pgt = ctx->arg;
+
+	/*
+	 * Clear the existing PTE, and perform break-before-make if it was
+	 * valid. Depending on the system support, defer the TLB maintenance
+	 * for the same until the entire unmap walk is completed.
 	 */
 	if (kvm_pte_valid(ctx->old)) {
 		kvm_clear_pte(ctx->ptep);
-		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, ctx->level);
+
+		if (!stage2_unmap_defer_tlb_flush(pgt))
+			kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu,
+					ctx->addr, ctx->level);
 	}
 
 	mm_ops->put_page(ctx->ptep);
@@ -1098,7 +1118,7 @@ static int stage2_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx,
 	 * block entry and rely on the remaining portions being faulted
 	 * back lazily.
 	 */
-	stage2_put_pte(ctx, mmu, mm_ops);
+	stage2_unmap_put_pte(ctx, mmu, mm_ops);
 
 	if (need_flush && mm_ops->dcache_clean_inval_poc)
 		mm_ops->dcache_clean_inval_poc(kvm_pte_follow(ctx->old, mm_ops),
@@ -1112,13 +1132,19 @@ static int stage2_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx,
 
 int kvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size)
 {
+	int ret;
 	struct kvm_pgtable_walker walker = {
 		.cb	= stage2_unmap_walker,
 		.arg	= pgt,
 		.flags	= KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST,
 	};
 
-	return kvm_pgtable_walk(pgt, addr, size, &walker);
+	ret = kvm_pgtable_walk(pgt, addr, size, &walker);
+	if (stage2_unmap_defer_tlb_flush(pgt))
+		/* Perform the deferred TLB invalidations */
+		kvm_tlb_flush_vmid_range(pgt->mmu, addr, size);
+
+	return ret;
 }
 
 struct stage2_attr_data {

From 21f74a51373791732baa0d672a604afa76d5718d Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 15 Aug 2023 19:38:35 +0100
Subject: [PATCH 0476/1189] arm64: Add missing VA CMO encodings

Add the missing VA-based CMOs encodings.

Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Miguel Luis <miguel.luis@oracle.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Reviewed-by: Jing Zhang <jingzhangos@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230815183903.2735724-2-maz@kernel.org
---
 arch/arm64/include/asm/sysreg.h | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index b481935e9314..85447e68951a 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -124,6 +124,32 @@
 #define SYS_DC_CIGSW			sys_insn(1, 0, 7, 14, 4)
 #define SYS_DC_CIGDSW			sys_insn(1, 0, 7, 14, 6)
 
+#define SYS_IC_IALLUIS			sys_insn(1, 0, 7, 1, 0)
+#define SYS_IC_IALLU			sys_insn(1, 0, 7, 5, 0)
+#define SYS_IC_IVAU			sys_insn(1, 3, 7, 5, 1)
+
+#define SYS_DC_IVAC			sys_insn(1, 0, 7, 6, 1)
+#define SYS_DC_IGVAC			sys_insn(1, 0, 7, 6, 3)
+#define SYS_DC_IGDVAC			sys_insn(1, 0, 7, 6, 5)
+
+#define SYS_DC_CVAC			sys_insn(1, 3, 7, 10, 1)
+#define SYS_DC_CGVAC			sys_insn(1, 3, 7, 10, 3)
+#define SYS_DC_CGDVAC			sys_insn(1, 3, 7, 10, 5)
+
+#define SYS_DC_CVAU			sys_insn(1, 3, 7, 11, 1)
+
+#define SYS_DC_CVAP			sys_insn(1, 3, 7, 12, 1)
+#define SYS_DC_CGVAP			sys_insn(1, 3, 7, 12, 3)
+#define SYS_DC_CGDVAP			sys_insn(1, 3, 7, 12, 5)
+
+#define SYS_DC_CVADP			sys_insn(1, 3, 7, 13, 1)
+#define SYS_DC_CGVADP			sys_insn(1, 3, 7, 13, 3)
+#define SYS_DC_CGDVADP			sys_insn(1, 3, 7, 13, 5)
+
+#define SYS_DC_CIVAC			sys_insn(1, 3, 7, 14, 1)
+#define SYS_DC_CIGVAC			sys_insn(1, 3, 7, 14, 3)
+#define SYS_DC_CIGDVAC			sys_insn(1, 3, 7, 14, 5)
+
 /*
  * Automatically generated definitions for system registers, the
  * manual encodings below are in the process of being converted to

From 464f2164da7e4cb50faec9d56226b22c9b36cdda Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 15 Aug 2023 19:38:36 +0100
Subject: [PATCH 0477/1189] arm64: Add missing ERX*_EL1 encodings

We only describe a few of the ERX*_EL1 registers. Add the missing
ones (ERXPFGF_EL1, ERXPFGCTL_EL1, ERXPFGCDN_EL1, ERXMISC2_EL1 and
ERXMISC3_EL1).

Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Miguel Luis <miguel.luis@oracle.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Reviewed-by: Jing Zhang <jingzhangos@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230815183903.2735724-3-maz@kernel.org
---
 arch/arm64/include/asm/sysreg.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 85447e68951a..ed2739897859 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -229,8 +229,13 @@
 #define SYS_ERXCTLR_EL1			sys_reg(3, 0, 5, 4, 1)
 #define SYS_ERXSTATUS_EL1		sys_reg(3, 0, 5, 4, 2)
 #define SYS_ERXADDR_EL1			sys_reg(3, 0, 5, 4, 3)
+#define SYS_ERXPFGF_EL1			sys_reg(3, 0, 5, 4, 4)
+#define SYS_ERXPFGCTL_EL1		sys_reg(3, 0, 5, 4, 5)
+#define SYS_ERXPFGCDN_EL1		sys_reg(3, 0, 5, 4, 6)
 #define SYS_ERXMISC0_EL1		sys_reg(3, 0, 5, 5, 0)
 #define SYS_ERXMISC1_EL1		sys_reg(3, 0, 5, 5, 1)
+#define SYS_ERXMISC2_EL1		sys_reg(3, 0, 5, 5, 2)
+#define SYS_ERXMISC3_EL1		sys_reg(3, 0, 5, 5, 3)
 #define SYS_TFSR_EL1			sys_reg(3, 0, 5, 6, 0)
 #define SYS_TFSRE0_EL1			sys_reg(3, 0, 5, 6, 1)
 

From 6ddea24dfd59f0fc78a87df54d428e3a6cf3e11f Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 15 Aug 2023 19:38:37 +0100
Subject: [PATCH 0478/1189] arm64: Add missing DC ZVA/GVA/GZVA encodings

Add the missing DC *VA encodings.

Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Miguel Luis <miguel.luis@oracle.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Reviewed-by: Jing Zhang <jingzhangos@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230815183903.2735724-4-maz@kernel.org
---
 arch/arm64/include/asm/sysreg.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index ed2739897859..5084add86897 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -150,6 +150,11 @@
 #define SYS_DC_CIGVAC			sys_insn(1, 3, 7, 14, 3)
 #define SYS_DC_CIGDVAC			sys_insn(1, 3, 7, 14, 5)
 
+/* Data cache zero operations */
+#define SYS_DC_ZVA			sys_insn(1, 3, 7, 4, 1)
+#define SYS_DC_GVA			sys_insn(1, 3, 7, 4, 3)
+#define SYS_DC_GZVA			sys_insn(1, 3, 7, 4, 4)
+
 /*
  * Automatically generated definitions for system registers, the
  * manual encodings below are in the process of being converted to

From fb1926cccd70a5032448968dfd639187cd894cb7 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 15 Aug 2023 19:38:38 +0100
Subject: [PATCH 0479/1189] arm64: Add TLBI operation encodings

Add all the TLBI encodings that are usable from Non-Secure.

Reviewed-by: Eric Auger <eric.auger@redhat.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Miguel Luis <miguel.luis@oracle.com>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Reviewed-by: Jing Zhang <jingzhangos@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230815183903.2735724-5-maz@kernel.org
---
 arch/arm64/include/asm/sysreg.h | 128 ++++++++++++++++++++++++++++++++
 1 file changed, 128 insertions(+)

diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 5084add86897..72e18480ce62 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -514,6 +514,134 @@
 
 #define SYS_SP_EL2			sys_reg(3, 6,  4, 1, 0)
 
+/* TLBI instructions */
+#define OP_TLBI_VMALLE1OS		sys_insn(1, 0, 8, 1, 0)
+#define OP_TLBI_VAE1OS			sys_insn(1, 0, 8, 1, 1)
+#define OP_TLBI_ASIDE1OS		sys_insn(1, 0, 8, 1, 2)
+#define OP_TLBI_VAAE1OS			sys_insn(1, 0, 8, 1, 3)
+#define OP_TLBI_VALE1OS			sys_insn(1, 0, 8, 1, 5)
+#define OP_TLBI_VAALE1OS		sys_insn(1, 0, 8, 1, 7)
+#define OP_TLBI_RVAE1IS			sys_insn(1, 0, 8, 2, 1)
+#define OP_TLBI_RVAAE1IS		sys_insn(1, 0, 8, 2, 3)
+#define OP_TLBI_RVALE1IS		sys_insn(1, 0, 8, 2, 5)
+#define OP_TLBI_RVAALE1IS		sys_insn(1, 0, 8, 2, 7)
+#define OP_TLBI_VMALLE1IS		sys_insn(1, 0, 8, 3, 0)
+#define OP_TLBI_VAE1IS			sys_insn(1, 0, 8, 3, 1)
+#define OP_TLBI_ASIDE1IS		sys_insn(1, 0, 8, 3, 2)
+#define OP_TLBI_VAAE1IS			sys_insn(1, 0, 8, 3, 3)
+#define OP_TLBI_VALE1IS			sys_insn(1, 0, 8, 3, 5)
+#define OP_TLBI_VAALE1IS		sys_insn(1, 0, 8, 3, 7)
+#define OP_TLBI_RVAE1OS			sys_insn(1, 0, 8, 5, 1)
+#define OP_TLBI_RVAAE1OS		sys_insn(1, 0, 8, 5, 3)
+#define OP_TLBI_RVALE1OS		sys_insn(1, 0, 8, 5, 5)
+#define OP_TLBI_RVAALE1OS		sys_insn(1, 0, 8, 5, 7)
+#define OP_TLBI_RVAE1			sys_insn(1, 0, 8, 6, 1)
+#define OP_TLBI_RVAAE1			sys_insn(1, 0, 8, 6, 3)
+#define OP_TLBI_RVALE1			sys_insn(1, 0, 8, 6, 5)
+#define OP_TLBI_RVAALE1			sys_insn(1, 0, 8, 6, 7)
+#define OP_TLBI_VMALLE1			sys_insn(1, 0, 8, 7, 0)
+#define OP_TLBI_VAE1			sys_insn(1, 0, 8, 7, 1)
+#define OP_TLBI_ASIDE1			sys_insn(1, 0, 8, 7, 2)
+#define OP_TLBI_VAAE1			sys_insn(1, 0, 8, 7, 3)
+#define OP_TLBI_VALE1			sys_insn(1, 0, 8, 7, 5)
+#define OP_TLBI_VAALE1			sys_insn(1, 0, 8, 7, 7)
+#define OP_TLBI_VMALLE1OSNXS		sys_insn(1, 0, 9, 1, 0)
+#define OP_TLBI_VAE1OSNXS		sys_insn(1, 0, 9, 1, 1)
+#define OP_TLBI_ASIDE1OSNXS		sys_insn(1, 0, 9, 1, 2)
+#define OP_TLBI_VAAE1OSNXS		sys_insn(1, 0, 9, 1, 3)
+#define OP_TLBI_VALE1OSNXS		sys_insn(1, 0, 9, 1, 5)
+#define OP_TLBI_VAALE1OSNXS		sys_insn(1, 0, 9, 1, 7)
+#define OP_TLBI_RVAE1ISNXS		sys_insn(1, 0, 9, 2, 1)
+#define OP_TLBI_RVAAE1ISNXS		sys_insn(1, 0, 9, 2, 3)
+#define OP_TLBI_RVALE1ISNXS		sys_insn(1, 0, 9, 2, 5)
+#define OP_TLBI_RVAALE1ISNXS		sys_insn(1, 0, 9, 2, 7)
+#define OP_TLBI_VMALLE1ISNXS		sys_insn(1, 0, 9, 3, 0)
+#define OP_TLBI_VAE1ISNXS		sys_insn(1, 0, 9, 3, 1)
+#define OP_TLBI_ASIDE1ISNXS		sys_insn(1, 0, 9, 3, 2)
+#define OP_TLBI_VAAE1ISNXS		sys_insn(1, 0, 9, 3, 3)
+#define OP_TLBI_VALE1ISNXS		sys_insn(1, 0, 9, 3, 5)
+#define OP_TLBI_VAALE1ISNXS		sys_insn(1, 0, 9, 3, 7)
+#define OP_TLBI_RVAE1OSNXS		sys_insn(1, 0, 9, 5, 1)
+#define OP_TLBI_RVAAE1OSNXS		sys_insn(1, 0, 9, 5, 3)
+#define OP_TLBI_RVALE1OSNXS		sys_insn(1, 0, 9, 5, 5)
+#define OP_TLBI_RVAALE1OSNXS		sys_insn(1, 0, 9, 5, 7)
+#define OP_TLBI_RVAE1NXS		sys_insn(1, 0, 9, 6, 1)
+#define OP_TLBI_RVAAE1NXS		sys_insn(1, 0, 9, 6, 3)
+#define OP_TLBI_RVALE1NXS		sys_insn(1, 0, 9, 6, 5)
+#define OP_TLBI_RVAALE1NXS		sys_insn(1, 0, 9, 6, 7)
+#define OP_TLBI_VMALLE1NXS		sys_insn(1, 0, 9, 7, 0)
+#define OP_TLBI_VAE1NXS			sys_insn(1, 0, 9, 7, 1)
+#define OP_TLBI_ASIDE1NXS		sys_insn(1, 0, 9, 7, 2)
+#define OP_TLBI_VAAE1NXS		sys_insn(1, 0, 9, 7, 3)
+#define OP_TLBI_VALE1NXS		sys_insn(1, 0, 9, 7, 5)
+#define OP_TLBI_VAALE1NXS		sys_insn(1, 0, 9, 7, 7)
+#define OP_TLBI_IPAS2E1IS		sys_insn(1, 4, 8, 0, 1)
+#define OP_TLBI_RIPAS2E1IS		sys_insn(1, 4, 8, 0, 2)
+#define OP_TLBI_IPAS2LE1IS		sys_insn(1, 4, 8, 0, 5)
+#define OP_TLBI_RIPAS2LE1IS		sys_insn(1, 4, 8, 0, 6)
+#define OP_TLBI_ALLE2OS			sys_insn(1, 4, 8, 1, 0)
+#define OP_TLBI_VAE2OS			sys_insn(1, 4, 8, 1, 1)
+#define OP_TLBI_ALLE1OS			sys_insn(1, 4, 8, 1, 4)
+#define OP_TLBI_VALE2OS			sys_insn(1, 4, 8, 1, 5)
+#define OP_TLBI_VMALLS12E1OS		sys_insn(1, 4, 8, 1, 6)
+#define OP_TLBI_RVAE2IS			sys_insn(1, 4, 8, 2, 1)
+#define OP_TLBI_RVALE2IS		sys_insn(1, 4, 8, 2, 5)
+#define OP_TLBI_ALLE2IS			sys_insn(1, 4, 8, 3, 0)
+#define OP_TLBI_VAE2IS			sys_insn(1, 4, 8, 3, 1)
+#define OP_TLBI_ALLE1IS			sys_insn(1, 4, 8, 3, 4)
+#define OP_TLBI_VALE2IS			sys_insn(1, 4, 8, 3, 5)
+#define OP_TLBI_VMALLS12E1IS		sys_insn(1, 4, 8, 3, 6)
+#define OP_TLBI_IPAS2E1OS		sys_insn(1, 4, 8, 4, 0)
+#define OP_TLBI_IPAS2E1			sys_insn(1, 4, 8, 4, 1)
+#define OP_TLBI_RIPAS2E1		sys_insn(1, 4, 8, 4, 2)
+#define OP_TLBI_RIPAS2E1OS		sys_insn(1, 4, 8, 4, 3)
+#define OP_TLBI_IPAS2LE1OS		sys_insn(1, 4, 8, 4, 4)
+#define OP_TLBI_IPAS2LE1		sys_insn(1, 4, 8, 4, 5)
+#define OP_TLBI_RIPAS2LE1		sys_insn(1, 4, 8, 4, 6)
+#define OP_TLBI_RIPAS2LE1OS		sys_insn(1, 4, 8, 4, 7)
+#define OP_TLBI_RVAE2OS			sys_insn(1, 4, 8, 5, 1)
+#define OP_TLBI_RVALE2OS		sys_insn(1, 4, 8, 5, 5)
+#define OP_TLBI_RVAE2			sys_insn(1, 4, 8, 6, 1)
+#define OP_TLBI_RVALE2			sys_insn(1, 4, 8, 6, 5)
+#define OP_TLBI_ALLE2			sys_insn(1, 4, 8, 7, 0)
+#define OP_TLBI_VAE2			sys_insn(1, 4, 8, 7, 1)
+#define OP_TLBI_ALLE1			sys_insn(1, 4, 8, 7, 4)
+#define OP_TLBI_VALE2			sys_insn(1, 4, 8, 7, 5)
+#define OP_TLBI_VMALLS12E1		sys_insn(1, 4, 8, 7, 6)
+#define OP_TLBI_IPAS2E1ISNXS		sys_insn(1, 4, 9, 0, 1)
+#define OP_TLBI_RIPAS2E1ISNXS		sys_insn(1, 4, 9, 0, 2)
+#define OP_TLBI_IPAS2LE1ISNXS		sys_insn(1, 4, 9, 0, 5)
+#define OP_TLBI_RIPAS2LE1ISNXS		sys_insn(1, 4, 9, 0, 6)
+#define OP_TLBI_ALLE2OSNXS		sys_insn(1, 4, 9, 1, 0)
+#define OP_TLBI_VAE2OSNXS		sys_insn(1, 4, 9, 1, 1)
+#define OP_TLBI_ALLE1OSNXS		sys_insn(1, 4, 9, 1, 4)
+#define OP_TLBI_VALE2OSNXS		sys_insn(1, 4, 9, 1, 5)
+#define OP_TLBI_VMALLS12E1OSNXS		sys_insn(1, 4, 9, 1, 6)
+#define OP_TLBI_RVAE2ISNXS		sys_insn(1, 4, 9, 2, 1)
+#define OP_TLBI_RVALE2ISNXS		sys_insn(1, 4, 9, 2, 5)
+#define OP_TLBI_ALLE2ISNXS		sys_insn(1, 4, 9, 3, 0)
+#define OP_TLBI_VAE2ISNXS		sys_insn(1, 4, 9, 3, 1)
+#define OP_TLBI_ALLE1ISNXS		sys_insn(1, 4, 9, 3, 4)
+#define OP_TLBI_VALE2ISNXS		sys_insn(1, 4, 9, 3, 5)
+#define OP_TLBI_VMALLS12E1ISNXS		sys_insn(1, 4, 9, 3, 6)
+#define OP_TLBI_IPAS2E1OSNXS		sys_insn(1, 4, 9, 4, 0)
+#define OP_TLBI_IPAS2E1NXS		sys_insn(1, 4, 9, 4, 1)
+#define OP_TLBI_RIPAS2E1NXS		sys_insn(1, 4, 9, 4, 2)
+#define OP_TLBI_RIPAS2E1OSNXS		sys_insn(1, 4, 9, 4, 3)
+#define OP_TLBI_IPAS2LE1OSNXS		sys_insn(1, 4, 9, 4, 4)
+#define OP_TLBI_IPAS2LE1NXS		sys_insn(1, 4, 9, 4, 5)
+#define OP_TLBI_RIPAS2LE1NXS		sys_insn(1, 4, 9, 4, 6)
+#define OP_TLBI_RIPAS2LE1OSNXS		sys_insn(1, 4, 9, 4, 7)
+#define OP_TLBI_RVAE2OSNXS		sys_insn(1, 4, 9, 5, 1)
+#define OP_TLBI_RVALE2OSNXS		sys_insn(1, 4, 9, 5, 5)
+#define OP_TLBI_RVAE2NXS		sys_insn(1, 4, 9, 6, 1)
+#define OP_TLBI_RVALE2NXS		sys_insn(1, 4, 9, 6, 5)
+#define OP_TLBI_ALLE2NXS		sys_insn(1, 4, 9, 7, 0)
+#define OP_TLBI_VAE2NXS			sys_insn(1, 4, 9, 7, 1)
+#define OP_TLBI_ALLE1NXS		sys_insn(1, 4, 9, 7, 4)
+#define OP_TLBI_VALE2NXS		sys_insn(1, 4, 9, 7, 5)
+#define OP_TLBI_VMALLS12E1NXS		sys_insn(1, 4, 9, 7, 6)
+
 /* Common SCTLR_ELx flags. */
 #define SCTLR_ELx_ENTP2	(BIT(60))
 #define SCTLR_ELx_DSSBS	(BIT(44))

From 2b97411fef8ff9dafc862971f08382f780dc5357 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 15 Aug 2023 19:38:39 +0100
Subject: [PATCH 0480/1189] arm64: Add AT operation encodings

Add the encodings for the AT operation that are usable from NS.

Reviewed-by: Eric Auger <eric.auger@redhat.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Miguel Luis <miguel.luis@oracle.com>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Reviewed-by: Jing Zhang <jingzhangos@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230815183903.2735724-6-maz@kernel.org
---
 arch/arm64/include/asm/sysreg.h | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 72e18480ce62..76289339b43b 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -514,6 +514,23 @@
 
 #define SYS_SP_EL2			sys_reg(3, 6,  4, 1, 0)
 
+/* AT instructions */
+#define AT_Op0 1
+#define AT_CRn 7
+
+#define OP_AT_S1E1R	sys_insn(AT_Op0, 0, AT_CRn, 8, 0)
+#define OP_AT_S1E1W	sys_insn(AT_Op0, 0, AT_CRn, 8, 1)
+#define OP_AT_S1E0R	sys_insn(AT_Op0, 0, AT_CRn, 8, 2)
+#define OP_AT_S1E0W	sys_insn(AT_Op0, 0, AT_CRn, 8, 3)
+#define OP_AT_S1E1RP	sys_insn(AT_Op0, 0, AT_CRn, 9, 0)
+#define OP_AT_S1E1WP	sys_insn(AT_Op0, 0, AT_CRn, 9, 1)
+#define OP_AT_S1E2R	sys_insn(AT_Op0, 4, AT_CRn, 8, 0)
+#define OP_AT_S1E2W	sys_insn(AT_Op0, 4, AT_CRn, 8, 1)
+#define OP_AT_S12E1R	sys_insn(AT_Op0, 4, AT_CRn, 8, 4)
+#define OP_AT_S12E1W	sys_insn(AT_Op0, 4, AT_CRn, 8, 5)
+#define OP_AT_S12E0R	sys_insn(AT_Op0, 4, AT_CRn, 8, 6)
+#define OP_AT_S12E0W	sys_insn(AT_Op0, 4, AT_CRn, 8, 7)
+
 /* TLBI instructions */
 #define OP_TLBI_VMALLE1OS		sys_insn(1, 0, 8, 1, 0)
 #define OP_TLBI_VAE1OS			sys_insn(1, 0, 8, 1, 1)

From 57596c8f991c9aace47d75b31249b8ec36b3b899 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 15 Aug 2023 19:38:40 +0100
Subject: [PATCH 0481/1189] arm64: Add debug registers affected by HDFGxTR_EL2

The HDFGxTR_EL2 registers trap a (huge) set of debug and trace
related registers. Add their encodings (and only that, because
we really don't care about what these registers actually do at
this stage).

Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Jing Zhang <jingzhangos@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230815183903.2735724-7-maz@kernel.org
---
 arch/arm64/include/asm/sysreg.h | 76 +++++++++++++++++++++++++++++++++
 1 file changed, 76 insertions(+)

diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 76289339b43b..bb5a0877a210 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -194,6 +194,82 @@
 #define SYS_DBGDTRTX_EL0		sys_reg(2, 3, 0, 5, 0)
 #define SYS_DBGVCR32_EL2		sys_reg(2, 4, 0, 7, 0)
 
+#define SYS_BRBINF_EL1(n)		sys_reg(2, 1, 8, (n & 15), (((n & 16) >> 2) | 0))
+#define SYS_BRBINFINJ_EL1		sys_reg(2, 1, 9, 1, 0)
+#define SYS_BRBSRC_EL1(n)		sys_reg(2, 1, 8, (n & 15), (((n & 16) >> 2) | 1))
+#define SYS_BRBSRCINJ_EL1		sys_reg(2, 1, 9, 1, 1)
+#define SYS_BRBTGT_EL1(n)		sys_reg(2, 1, 8, (n & 15), (((n & 16) >> 2) | 2))
+#define SYS_BRBTGTINJ_EL1		sys_reg(2, 1, 9, 1, 2)
+#define SYS_BRBTS_EL1			sys_reg(2, 1, 9, 0, 2)
+
+#define SYS_BRBCR_EL1			sys_reg(2, 1, 9, 0, 0)
+#define SYS_BRBFCR_EL1			sys_reg(2, 1, 9, 0, 1)
+#define SYS_BRBIDR0_EL1			sys_reg(2, 1, 9, 2, 0)
+
+#define SYS_TRCITECR_EL1		sys_reg(3, 0, 1, 2, 3)
+#define SYS_TRCACATR(m)			sys_reg(2, 1, 2, ((m & 7) << 1), (2 | (m >> 3)))
+#define SYS_TRCACVR(m)			sys_reg(2, 1, 2, ((m & 7) << 1), (0 | (m >> 3)))
+#define SYS_TRCAUTHSTATUS		sys_reg(2, 1, 7, 14, 6)
+#define SYS_TRCAUXCTLR			sys_reg(2, 1, 0, 6, 0)
+#define SYS_TRCBBCTLR			sys_reg(2, 1, 0, 15, 0)
+#define SYS_TRCCCCTLR			sys_reg(2, 1, 0, 14, 0)
+#define SYS_TRCCIDCCTLR0		sys_reg(2, 1, 3, 0, 2)
+#define SYS_TRCCIDCCTLR1		sys_reg(2, 1, 3, 1, 2)
+#define SYS_TRCCIDCVR(m)		sys_reg(2, 1, 3, ((m & 7) << 1), 0)
+#define SYS_TRCCLAIMCLR			sys_reg(2, 1, 7, 9, 6)
+#define SYS_TRCCLAIMSET			sys_reg(2, 1, 7, 8, 6)
+#define SYS_TRCCNTCTLR(m)		sys_reg(2, 1, 0, (4 | (m & 3)), 5)
+#define SYS_TRCCNTRLDVR(m)		sys_reg(2, 1, 0, (0 | (m & 3)), 5)
+#define SYS_TRCCNTVR(m)			sys_reg(2, 1, 0, (8 | (m & 3)), 5)
+#define SYS_TRCCONFIGR			sys_reg(2, 1, 0, 4, 0)
+#define SYS_TRCDEVARCH			sys_reg(2, 1, 7, 15, 6)
+#define SYS_TRCDEVID			sys_reg(2, 1, 7, 2, 7)
+#define SYS_TRCEVENTCTL0R		sys_reg(2, 1, 0, 8, 0)
+#define SYS_TRCEVENTCTL1R		sys_reg(2, 1, 0, 9, 0)
+#define SYS_TRCEXTINSELR(m)		sys_reg(2, 1, 0, (8 | (m & 3)), 4)
+#define SYS_TRCIDR0			sys_reg(2, 1, 0, 8, 7)
+#define SYS_TRCIDR10			sys_reg(2, 1, 0, 2, 6)
+#define SYS_TRCIDR11			sys_reg(2, 1, 0, 3, 6)
+#define SYS_TRCIDR12			sys_reg(2, 1, 0, 4, 6)
+#define SYS_TRCIDR13			sys_reg(2, 1, 0, 5, 6)
+#define SYS_TRCIDR1			sys_reg(2, 1, 0, 9, 7)
+#define SYS_TRCIDR2			sys_reg(2, 1, 0, 10, 7)
+#define SYS_TRCIDR3			sys_reg(2, 1, 0, 11, 7)
+#define SYS_TRCIDR4			sys_reg(2, 1, 0, 12, 7)
+#define SYS_TRCIDR5			sys_reg(2, 1, 0, 13, 7)
+#define SYS_TRCIDR6			sys_reg(2, 1, 0, 14, 7)
+#define SYS_TRCIDR7			sys_reg(2, 1, 0, 15, 7)
+#define SYS_TRCIDR8			sys_reg(2, 1, 0, 0, 6)
+#define SYS_TRCIDR9			sys_reg(2, 1, 0, 1, 6)
+#define SYS_TRCIMSPEC(m)		sys_reg(2, 1, 0, (m & 7), 7)
+#define SYS_TRCITEEDCR			sys_reg(2, 1, 0, 2, 1)
+#define SYS_TRCOSLSR			sys_reg(2, 1, 1, 1, 4)
+#define SYS_TRCPRGCTLR			sys_reg(2, 1, 0, 1, 0)
+#define SYS_TRCQCTLR			sys_reg(2, 1, 0, 1, 1)
+#define SYS_TRCRSCTLR(m)		sys_reg(2, 1, 1, (m & 15), (0 | (m >> 4)))
+#define SYS_TRCRSR			sys_reg(2, 1, 0, 10, 0)
+#define SYS_TRCSEQEVR(m)		sys_reg(2, 1, 0, (m & 3), 4)
+#define SYS_TRCSEQRSTEVR		sys_reg(2, 1, 0, 6, 4)
+#define SYS_TRCSEQSTR			sys_reg(2, 1, 0, 7, 4)
+#define SYS_TRCSSCCR(m)			sys_reg(2, 1, 1, (m & 7), 2)
+#define SYS_TRCSSCSR(m)			sys_reg(2, 1, 1, (8 | (m & 7)), 2)
+#define SYS_TRCSSPCICR(m)		sys_reg(2, 1, 1, (m & 7), 3)
+#define SYS_TRCSTALLCTLR		sys_reg(2, 1, 0, 11, 0)
+#define SYS_TRCSTATR			sys_reg(2, 1, 0, 3, 0)
+#define SYS_TRCSYNCPR			sys_reg(2, 1, 0, 13, 0)
+#define SYS_TRCTRACEIDR			sys_reg(2, 1, 0, 0, 1)
+#define SYS_TRCTSCTLR			sys_reg(2, 1, 0, 12, 0)
+#define SYS_TRCVICTLR			sys_reg(2, 1, 0, 0, 2)
+#define SYS_TRCVIIECTLR			sys_reg(2, 1, 0, 1, 2)
+#define SYS_TRCVIPCSSCTLR		sys_reg(2, 1, 0, 3, 2)
+#define SYS_TRCVISSCTLR			sys_reg(2, 1, 0, 2, 2)
+#define SYS_TRCVMIDCCTLR0		sys_reg(2, 1, 3, 2, 2)
+#define SYS_TRCVMIDCCTLR1		sys_reg(2, 1, 3, 3, 2)
+#define SYS_TRCVMIDCVR(m)		sys_reg(2, 1, 3, ((m & 7) << 1), 1)
+
+/* ETM */
+#define SYS_TRCOSLAR			sys_reg(2, 1, 1, 0, 4)
+
 #define SYS_MIDR_EL1			sys_reg(3, 0, 0, 0, 0)
 #define SYS_MPIDR_EL1			sys_reg(3, 0, 0, 0, 5)
 #define SYS_REVIDR_EL1			sys_reg(3, 0, 0, 0, 6)

From 2b062ed483ebd625b6c6054b9d29d600bd755a86 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 15 Aug 2023 19:38:41 +0100
Subject: [PATCH 0482/1189] arm64: Add missing BRB/CFP/DVP/CPP instructions

HFGITR_EL2 traps a bunch of instructions for which we don't have
encodings yet. Add them.

Reviewed-by: Miguel Luis <miguel.luis@oracle.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Jing Zhang <jingzhangos@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230815183903.2735724-8-maz@kernel.org
---
 arch/arm64/include/asm/sysreg.h | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index bb5a0877a210..6d9d7ac4b31c 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -735,6 +735,13 @@
 #define OP_TLBI_VALE2NXS		sys_insn(1, 4, 9, 7, 5)
 #define OP_TLBI_VMALLS12E1NXS		sys_insn(1, 4, 9, 7, 6)
 
+/* Misc instructions */
+#define OP_BRB_IALL			sys_insn(1, 1, 7, 2, 4)
+#define OP_BRB_INJ			sys_insn(1, 1, 7, 2, 5)
+#define OP_CFP_RCTX			sys_insn(1, 3, 7, 3, 4)
+#define OP_DVP_RCTX			sys_insn(1, 3, 7, 3, 5)
+#define OP_CPP_RCTX			sys_insn(1, 3, 7, 3, 7)
+
 /* Common SCTLR_ELx flags. */
 #define SCTLR_ELx_ENTP2	(BIT(60))
 #define SCTLR_ELx_DSSBS	(BIT(44))

From cc24f656f7cf834f384a43fc6fe68ec62730743d Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 15 Aug 2023 19:38:42 +0100
Subject: [PATCH 0483/1189] arm64: Add HDFGRTR_EL2 and HDFGWTR_EL2 layouts

As we're about to implement full support for FEAT_FGT, add the
full HDFGRTR_EL2 and HDFGWTR_EL2 layouts.

Reviewed-by: Mark Brown <broonie@kernel.org>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Miguel Luis <miguel.luis@oracle.com>
Reviewed-by: Jing Zhang <jingzhangos@google.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230815183903.2735724-9-maz@kernel.org
---
 arch/arm64/include/asm/sysreg.h |   2 -
 arch/arm64/tools/sysreg         | 129 ++++++++++++++++++++++++++++++++
 2 files changed, 129 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 6d9d7ac4b31c..043c677e9f04 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -495,8 +495,6 @@
 #define SYS_VTCR_EL2			sys_reg(3, 4, 2, 1, 2)
 
 #define SYS_TRFCR_EL2			sys_reg(3, 4, 1, 2, 1)
-#define SYS_HDFGRTR_EL2			sys_reg(3, 4, 3, 1, 4)
-#define SYS_HDFGWTR_EL2			sys_reg(3, 4, 3, 1, 5)
 #define SYS_HAFGRTR_EL2			sys_reg(3, 4, 3, 1, 6)
 #define SYS_SPSR_EL2			sys_reg(3, 4, 4, 0, 0)
 #define SYS_ELR_EL2			sys_reg(3, 4, 4, 0, 1)
diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg
index 65866bf819c3..2517ef7c21cf 100644
--- a/arch/arm64/tools/sysreg
+++ b/arch/arm64/tools/sysreg
@@ -2156,6 +2156,135 @@ Field	1	ICIALLU
 Field	0	ICIALLUIS
 EndSysreg
 
+Sysreg HDFGRTR_EL2	3	4	3	1	4
+Field	63	PMBIDR_EL1
+Field	62	nPMSNEVFR_EL1
+Field	61	nBRBDATA
+Field	60	nBRBCTL
+Field	59	nBRBIDR
+Field	58	PMCEIDn_EL0
+Field	57	PMUSERENR_EL0
+Field	56	TRBTRG_EL1
+Field	55	TRBSR_EL1
+Field	54	TRBPTR_EL1
+Field	53	TRBMAR_EL1
+Field	52	TRBLIMITR_EL1
+Field	51	TRBIDR_EL1
+Field	50	TRBBASER_EL1
+Res0	49
+Field	48	TRCVICTLR
+Field	47	TRCSTATR
+Field	46	TRCSSCSRn
+Field	45	TRCSEQSTR
+Field	44	TRCPRGCTLR
+Field	43	TRCOSLSR
+Res0	42
+Field	41	TRCIMSPECn
+Field	40	TRCID
+Res0	39:38
+Field	37	TRCCNTVRn
+Field	36	TRCCLAIM
+Field	35	TRCAUXCTLR
+Field	34	TRCAUTHSTATUS
+Field	33	TRC
+Field	32	PMSLATFR_EL1
+Field	31	PMSIRR_EL1
+Field	30	PMSIDR_EL1
+Field	29	PMSICR_EL1
+Field	28	PMSFCR_EL1
+Field	27	PMSEVFR_EL1
+Field	26	PMSCR_EL1
+Field	25	PMBSR_EL1
+Field	24	PMBPTR_EL1
+Field	23	PMBLIMITR_EL1
+Field	22	PMMIR_EL1
+Res0	21:20
+Field	19	PMSELR_EL0
+Field	18	PMOVS
+Field	17	PMINTEN
+Field	16	PMCNTEN
+Field	15	PMCCNTR_EL0
+Field	14	PMCCFILTR_EL0
+Field	13	PMEVTYPERn_EL0
+Field	12	PMEVCNTRn_EL0
+Field	11	OSDLR_EL1
+Field	10	OSECCR_EL1
+Field	9	OSLSR_EL1
+Res0	8
+Field	7	DBGPRCR_EL1
+Field	6	DBGAUTHSTATUS_EL1
+Field	5	DBGCLAIM
+Field	4	MDSCR_EL1
+Field	3	DBGWVRn_EL1
+Field	2	DBGWCRn_EL1
+Field	1	DBGBVRn_EL1
+Field	0	DBGBCRn_EL1
+EndSysreg
+
+Sysreg HDFGWTR_EL2	3	4	3	1	5
+Res0	63
+Field	62	nPMSNEVFR_EL1
+Field	61	nBRBDATA
+Field	60	nBRBCTL
+Res0	59:58
+Field	57	PMUSERENR_EL0
+Field	56	TRBTRG_EL1
+Field	55	TRBSR_EL1
+Field	54	TRBPTR_EL1
+Field	53	TRBMAR_EL1
+Field	52	TRBLIMITR_EL1
+Res0	51
+Field	50	TRBBASER_EL1
+Field	49	TRFCR_EL1
+Field	48	TRCVICTLR
+Res0	47
+Field	46	TRCSSCSRn
+Field	45	TRCSEQSTR
+Field	44	TRCPRGCTLR
+Res0	43
+Field	42	TRCOSLAR
+Field	41	TRCIMSPECn
+Res0	40:38
+Field	37	TRCCNTVRn
+Field	36	TRCCLAIM
+Field	35	TRCAUXCTLR
+Res0	34
+Field	33	TRC
+Field	32	PMSLATFR_EL1
+Field	31	PMSIRR_EL1
+Res0	30
+Field	29	PMSICR_EL1
+Field	28	PMSFCR_EL1
+Field	27	PMSEVFR_EL1
+Field	26	PMSCR_EL1
+Field	25	PMBSR_EL1
+Field	24	PMBPTR_EL1
+Field	23	PMBLIMITR_EL1
+Res0	22
+Field	21	PMCR_EL0
+Field	20	PMSWINC_EL0
+Field	19	PMSELR_EL0
+Field	18	PMOVS
+Field	17	PMINTEN
+Field	16	PMCNTEN
+Field	15	PMCCNTR_EL0
+Field	14	PMCCFILTR_EL0
+Field	13	PMEVTYPERn_EL0
+Field	12	PMEVCNTRn_EL0
+Field	11	OSDLR_EL1
+Field	10	OSECCR_EL1
+Res0	9
+Field	8	OSLAR_EL1
+Field	7	DBGPRCR_EL1
+Res0	6
+Field	5	DBGCLAIM
+Field	4	MDSCR_EL1
+Field	3	DBGWVRn_EL1
+Field	2	DBGWCRn_EL1
+Field	1	DBGBVRn_EL1
+Field	0	DBGBCRn_EL1
+EndSysreg
+
 Sysreg	ZCR_EL2	3	4	1	2	0
 Fields	ZCR_ELx
 EndSysreg

From b206a708cbfb352f2191089678ab595d24563011 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Tue, 15 Aug 2023 19:38:43 +0100
Subject: [PATCH 0484/1189] arm64: Add feature detection for fine grained traps

In order to allow us to have shared code for managing fine grained traps
for KVM guests add it as a detected feature rather than relying on it
being a dependency of other features.

Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
[maz: converted to ARM64_CPUID_FIELDS()]
Link: https://lore.kernel.org/r/20230301-kvm-arm64-fgt-v4-1-1bf8d235ac1f@kernel.org
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Reviewed-by: Miguel Luis <miguel.luis@oracle.com>
Reviewed-by: Jing Zhang <jingzhangos@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230815183903.2735724-10-maz@kernel.org
---
 arch/arm64/kernel/cpufeature.c | 7 +++++++
 arch/arm64/tools/cpucaps       | 1 +
 2 files changed, 8 insertions(+)

diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index f9d456fe132d..668e2872a086 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -2627,6 +2627,13 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = has_cpuid_feature,
 		ARM64_CPUID_FIELDS(ID_AA64ISAR1_EL1, LRCPC, IMP)
 	},
+	{
+		.desc = "Fine Grained Traps",
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.capability = ARM64_HAS_FGT,
+		.matches = has_cpuid_feature,
+		ARM64_CPUID_FIELDS(ID_AA64MMFR0_EL1, FGT, IMP)
+	},
 #ifdef CONFIG_ARM64_SME
 	{
 		.desc = "Scalable Matrix Extension",
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index c80ed4f3cbce..c3f06fdef609 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -26,6 +26,7 @@ HAS_ECV
 HAS_ECV_CNTPOFF
 HAS_EPAN
 HAS_EVT
+HAS_FGT
 HAS_GENERIC_AUTH
 HAS_GENERIC_AUTH_ARCH_QARMA3
 HAS_GENERIC_AUTH_ARCH_QARMA5

From 484f86824a3d94c6d9412618dd70b1d5923fff6f Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 15 Aug 2023 19:38:44 +0100
Subject: [PATCH 0485/1189] KVM: arm64: Correctly handle ACCDATA_EL1 traps

As we blindly reset some HFGxTR_EL2 bits to 0, we also randomly trap
unsuspecting sysregs that have their trap bits with a negative
polarity.

ACCDATA_EL1 is one such register that can be accessed by the guest,
causing a splat on the host as we don't have a proper handler for
it.

Adding such handler addresses the issue, though there are a number
of other registers missing as the current architecture documentation
doesn't describe them yet.

Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Miguel Luis <miguel.luis@oracle.com>
Reviewed-by: Jing Zhang <jingzhangos@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230815183903.2735724-11-maz@kernel.org
---
 arch/arm64/include/asm/sysreg.h | 2 ++
 arch/arm64/kvm/sys_regs.c       | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 043c677e9f04..818c111009ca 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -387,6 +387,8 @@
 #define SYS_ICC_IGRPEN0_EL1		sys_reg(3, 0, 12, 12, 6)
 #define SYS_ICC_IGRPEN1_EL1		sys_reg(3, 0, 12, 12, 7)
 
+#define SYS_ACCDATA_EL1			sys_reg(3, 0, 13, 0, 5)
+
 #define SYS_CNTKCTL_EL1			sys_reg(3, 0, 14, 1, 0)
 
 #define SYS_AIDR_EL1			sys_reg(3, 1, 0, 0, 7)
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 2ca2973abe66..38f221f9fc98 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2151,6 +2151,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_CONTEXTIDR_EL1), access_vm_reg, reset_val, CONTEXTIDR_EL1, 0 },
 	{ SYS_DESC(SYS_TPIDR_EL1), NULL, reset_unknown, TPIDR_EL1 },
 
+	{ SYS_DESC(SYS_ACCDATA_EL1), undef_access },
+
 	{ SYS_DESC(SYS_SCXTNUM_EL1), undef_access },
 
 	{ SYS_DESC(SYS_CNTKCTL_EL1), NULL, reset_val, CNTKCTL_EL1, 0},

From 3ea84b4fe446319625be64945793b8540ca15f84 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 15 Aug 2023 19:38:45 +0100
Subject: [PATCH 0486/1189] KVM: arm64: Add missing HCR_EL2 trap bits

We're still missing a handfull of HCR_EL2 trap bits. Add them.

Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Miguel Luis <miguel.luis@oracle.com>
Reviewed-by: Jing Zhang <jingzhangos@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230815183903.2735724-12-maz@kernel.org
---
 arch/arm64/include/asm/kvm_arm.h | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 58e5eb27da68..028049b147df 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -18,10 +18,19 @@
 #define HCR_DCT		(UL(1) << 57)
 #define HCR_ATA_SHIFT	56
 #define HCR_ATA		(UL(1) << HCR_ATA_SHIFT)
+#define HCR_TTLBOS	(UL(1) << 55)
+#define HCR_TTLBIS	(UL(1) << 54)
+#define HCR_ENSCXT	(UL(1) << 53)
+#define HCR_TOCU	(UL(1) << 52)
 #define HCR_AMVOFFEN	(UL(1) << 51)
+#define HCR_TICAB	(UL(1) << 50)
 #define HCR_TID4	(UL(1) << 49)
 #define HCR_FIEN	(UL(1) << 47)
 #define HCR_FWB		(UL(1) << 46)
+#define HCR_NV2		(UL(1) << 45)
+#define HCR_AT		(UL(1) << 44)
+#define HCR_NV1		(UL(1) << 43)
+#define HCR_NV		(UL(1) << 42)
 #define HCR_API		(UL(1) << 41)
 #define HCR_APK		(UL(1) << 40)
 #define HCR_TEA		(UL(1) << 37)

From 50d2fe4648c50e7d33fa576f6b078f22ad973670 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 15 Aug 2023 19:38:46 +0100
Subject: [PATCH 0487/1189] KVM: arm64: nv: Add FGT registers

Add the 5 registers covering FEAT_FGT. The AMU-related registers
are currently left out as we don't have a plan for them. Yet.

Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Miguel Luis <miguel.luis@oracle.com>
Reviewed-by: Jing Zhang <jingzhangos@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230815183903.2735724-13-maz@kernel.org
---
 arch/arm64/include/asm/kvm_host.h | 5 +++++
 arch/arm64/kvm/sys_regs.c         | 5 +++++
 2 files changed, 10 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index d3dd05bbfe23..721680da1011 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -400,6 +400,11 @@ enum vcpu_sysreg {
 	TPIDR_EL2,	/* EL2 Software Thread ID Register */
 	CNTHCTL_EL2,	/* Counter-timer Hypervisor Control register */
 	SP_EL2,		/* EL2 Stack Pointer */
+	HFGRTR_EL2,
+	HFGWTR_EL2,
+	HFGITR_EL2,
+	HDFGRTR_EL2,
+	HDFGWTR_EL2,
 	CNTHP_CTL_EL2,
 	CNTHP_CVAL_EL2,
 	CNTHV_CTL_EL2,
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 38f221f9fc98..f5baaa508926 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2367,6 +2367,9 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	EL2_REG(MDCR_EL2, access_rw, reset_val, 0),
 	EL2_REG(CPTR_EL2, access_rw, reset_val, CPTR_NVHE_EL2_RES1),
 	EL2_REG(HSTR_EL2, access_rw, reset_val, 0),
+	EL2_REG(HFGRTR_EL2, access_rw, reset_val, 0),
+	EL2_REG(HFGWTR_EL2, access_rw, reset_val, 0),
+	EL2_REG(HFGITR_EL2, access_rw, reset_val, 0),
 	EL2_REG(HACR_EL2, access_rw, reset_val, 0),
 
 	EL2_REG(TTBR0_EL2, access_rw, reset_val, 0),
@@ -2376,6 +2379,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	EL2_REG(VTCR_EL2, access_rw, reset_val, 0),
 
 	{ SYS_DESC(SYS_DACR32_EL2), NULL, reset_unknown, DACR32_EL2 },
+	EL2_REG(HDFGRTR_EL2, access_rw, reset_val, 0),
+	EL2_REG(HDFGWTR_EL2, access_rw, reset_val, 0),
 	EL2_REG(SPSR_EL2, access_rw, reset_val, 0),
 	EL2_REG(ELR_EL2, access_rw, reset_val, 0),
 	{ SYS_DESC(SYS_SP_EL1), access_sp_el1},

From e930694e6145eb210c9931914a7801cc61016a82 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 15 Aug 2023 19:38:47 +0100
Subject: [PATCH 0488/1189] KVM: arm64: Restructure FGT register switching

As we're about to majorly extend the handling of FGT registers,
restructure the code to actually save/restore the registers
as required. This is made easy thanks to the previous addition
of the EL2 registers, allowing us to use the host context for
this purpose.

Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Reviewed-by: Miguel Luis <miguel.luis@oracle.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230815183903.2735724-14-maz@kernel.org
---
 arch/arm64/include/asm/kvm_arm.h        | 21 +++++++++
 arch/arm64/kvm/hyp/include/hyp/switch.h | 60 +++++++++++++------------
 2 files changed, 52 insertions(+), 29 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 028049b147df..85908aa18908 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -333,6 +333,27 @@
 				 BIT(18) |		\
 				 GENMASK(16, 15))
 
+/*
+ * FGT register definitions
+ *
+ * RES0 and polarity masks as of DDI0487J.a, to be updated as needed.
+ * We're not using the generated masks as they are usually ahead of
+ * the published ARM ARM, which we use as a reference.
+ *
+ * Once we get to a point where the two describe the same thing, we'll
+ * merge the definitions. One day.
+ */
+#define __HFGRTR_EL2_RES0	(GENMASK(63, 56) | GENMASK(53, 51))
+#define __HFGRTR_EL2_MASK	GENMASK(49, 0)
+#define __HFGRTR_EL2_nMASK	(GENMASK(55, 54) | BIT(50))
+
+#define __HFGWTR_EL2_RES0	(GENMASK(63, 56) | GENMASK(53, 51) |	\
+				 BIT(46) | BIT(42) | BIT(40) | BIT(28) | \
+				 GENMASK(26, 25) | BIT(21) | BIT(18) |	\
+				 GENMASK(15, 14) | GENMASK(10, 9) | BIT(2))
+#define __HFGWTR_EL2_MASK	GENMASK(49, 0)
+#define __HFGWTR_EL2_nMASK	(GENMASK(55, 54) | BIT(50))
+
 /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
 #define HPFAR_MASK	(~UL(0xf))
 /*
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 4bddb8541bec..e096b16e85fd 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -70,20 +70,19 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
 	}
 }
 
-static inline bool __hfgxtr_traps_required(void)
-{
-	if (cpus_have_final_cap(ARM64_SME))
-		return true;
-
-	if (cpus_have_final_cap(ARM64_WORKAROUND_AMPERE_AC03_CPU_38))
-		return true;
-
-	return false;
-}
-
-static inline void __activate_traps_hfgxtr(void)
+
+
+static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 {
+	struct kvm_cpu_context *hctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
 	u64 r_clr = 0, w_clr = 0, r_set = 0, w_set = 0, tmp;
+	u64 r_val, w_val;
+
+	if (!cpus_have_final_cap(ARM64_HAS_FGT))
+		return;
+
+	ctxt_sys_reg(hctxt, HFGRTR_EL2) = read_sysreg_s(SYS_HFGRTR_EL2);
+	ctxt_sys_reg(hctxt, HFGWTR_EL2) = read_sysreg_s(SYS_HFGWTR_EL2);
 
 	if (cpus_have_final_cap(ARM64_SME)) {
 		tmp = HFGxTR_EL2_nSMPRI_EL1_MASK | HFGxTR_EL2_nTPIDR2_EL0_MASK;
@@ -98,26 +97,31 @@ static inline void __activate_traps_hfgxtr(void)
 	if (cpus_have_final_cap(ARM64_WORKAROUND_AMPERE_AC03_CPU_38))
 		w_set |= HFGxTR_EL2_TCR_EL1_MASK;
 
-	sysreg_clear_set_s(SYS_HFGRTR_EL2, r_clr, r_set);
-	sysreg_clear_set_s(SYS_HFGWTR_EL2, w_clr, w_set);
+
+	/* The default is not to trap anything but ACCDATA_EL1 */
+	r_val = __HFGRTR_EL2_nMASK & ~HFGxTR_EL2_nACCDATA_EL1;
+	r_val |= r_set;
+	r_val &= ~r_clr;
+
+	w_val = __HFGWTR_EL2_nMASK & ~HFGxTR_EL2_nACCDATA_EL1;
+	w_val |= w_set;
+	w_val &= ~w_clr;
+
+	write_sysreg_s(r_val, SYS_HFGRTR_EL2);
+	write_sysreg_s(w_val, SYS_HFGWTR_EL2);
 }
 
-static inline void __deactivate_traps_hfgxtr(void)
+static inline void __deactivate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 {
-	u64 r_clr = 0, w_clr = 0, r_set = 0, w_set = 0, tmp;
+	struct kvm_cpu_context *hctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
 
-	if (cpus_have_final_cap(ARM64_SME)) {
-		tmp = HFGxTR_EL2_nSMPRI_EL1_MASK | HFGxTR_EL2_nTPIDR2_EL0_MASK;
+	if (!cpus_have_final_cap(ARM64_HAS_FGT))
+		return;
 
-		r_set |= tmp;
-		w_set |= tmp;
-	}
+	write_sysreg_s(ctxt_sys_reg(hctxt, HFGRTR_EL2), SYS_HFGRTR_EL2);
+	write_sysreg_s(ctxt_sys_reg(hctxt, HFGWTR_EL2), SYS_HFGWTR_EL2);
 
-	if (cpus_have_final_cap(ARM64_WORKAROUND_AMPERE_AC03_CPU_38))
-		w_clr |= HFGxTR_EL2_TCR_EL1_MASK;
 
-	sysreg_clear_set_s(SYS_HFGRTR_EL2, r_clr, r_set);
-	sysreg_clear_set_s(SYS_HFGWTR_EL2, w_clr, w_set);
 }
 
 static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
@@ -145,8 +149,7 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
 	vcpu->arch.mdcr_el2_host = read_sysreg(mdcr_el2);
 	write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
 
-	if (__hfgxtr_traps_required())
-		__activate_traps_hfgxtr();
+	__activate_traps_hfgxtr(vcpu);
 }
 
 static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu)
@@ -162,8 +165,7 @@ static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu)
 		vcpu_clear_flag(vcpu, PMUSERENR_ON_CPU);
 	}
 
-	if (__hfgxtr_traps_required())
-		__deactivate_traps_hfgxtr();
+	__deactivate_traps_hfgxtr(vcpu);
 }
 
 static inline void ___activate_traps(struct kvm_vcpu *vcpu)

From e58ec47bf68d2bcaaa97d80cc13aca4bc4abe07b Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 15 Aug 2023 19:38:48 +0100
Subject: [PATCH 0489/1189] KVM: arm64: nv: Add trap forwarding infrastructure

A significant part of what a NV hypervisor needs to do is to decide
whether a trap from a L2+ guest has to be forwarded to a L1 guest
or handled locally. This is done by checking for the trap bits that
the guest hypervisor has set and acting accordingly, as described by
the architecture.

A previous approach was to sprinkle a bunch of checks in all the
system register accessors, but this is pretty error prone and doesn't
help getting an overview of what is happening.

Instead, implement a set of global tables that describe a trap bit,
combinations of trap bits, behaviours on trap, and what bits must
be evaluated on a system register trap.

Although this is painful to describe, this allows to specify each
and every control bit in a static manner. To make it efficient,
the table is inserted in an xarray that is global to the system,
and checked each time we trap a system register while running
a L2 guest.

Add the basic infrastructure for now, while additional patches will
implement configuration registers.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Jing Zhang <jingzhangos@google.com>
Reviewed-by: Miguel Luis <miguel.luis@oracle.com>
Link: https://lore.kernel.org/r/20230815183903.2735724-15-maz@kernel.org
---
 arch/arm64/include/asm/kvm_host.h   |   1 +
 arch/arm64/include/asm/kvm_nested.h |   2 +
 arch/arm64/kvm/emulate-nested.c     | 282 ++++++++++++++++++++++++++++
 arch/arm64/kvm/sys_regs.c           |   6 +
 arch/arm64/kvm/trace_arm.h          |  26 +++
 5 files changed, 317 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 721680da1011..cb1c5c54cedd 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -988,6 +988,7 @@ int kvm_handle_cp10_id(struct kvm_vcpu *vcpu);
 void kvm_reset_sys_regs(struct kvm_vcpu *vcpu);
 
 int __init kvm_sys_reg_table_init(void);
+int __init populate_nv_trap_config(void);
 
 bool lock_all_vcpus(struct kvm *kvm);
 void unlock_all_vcpus(struct kvm *kvm);
diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 8fb67f032fd1..fa23cc9c2adc 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -11,6 +11,8 @@ static inline bool vcpu_has_nv(const struct kvm_vcpu *vcpu)
 		test_bit(KVM_ARM_VCPU_HAS_EL2, vcpu->arch.features));
 }
 
+extern bool __check_nv_sr_forward(struct kvm_vcpu *vcpu);
+
 struct sys_reg_params;
 struct sys_reg_desc;
 
diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index b96662029fb1..d5837ed0077c 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -14,6 +14,288 @@
 
 #include "trace.h"
 
+enum trap_behaviour {
+	BEHAVE_HANDLE_LOCALLY	= 0,
+	BEHAVE_FORWARD_READ	= BIT(0),
+	BEHAVE_FORWARD_WRITE	= BIT(1),
+	BEHAVE_FORWARD_ANY	= BEHAVE_FORWARD_READ | BEHAVE_FORWARD_WRITE,
+};
+
+struct trap_bits {
+	const enum vcpu_sysreg		index;
+	const enum trap_behaviour	behaviour;
+	const u64			value;
+	const u64			mask;
+};
+
+/* Coarse Grained Trap definitions */
+enum cgt_group_id {
+	/* Indicates no coarse trap control */
+	__RESERVED__,
+
+	/*
+	 * The first batch of IDs denote coarse trapping that are used
+	 * on their own instead of being part of a combination of
+	 * trap controls.
+	 */
+
+	/*
+	 * Anything after this point is a combination of coarse trap
+	 * controls, which must all be evaluated to decide what to do.
+	 */
+	__MULTIPLE_CONTROL_BITS__,
+
+	/*
+	 * Anything after this point requires a callback evaluating a
+	 * complex trap condition. Hopefully we'll never need this...
+	 */
+	__COMPLEX_CONDITIONS__,
+
+	/* Must be last */
+	__NR_CGT_GROUP_IDS__
+};
+
+static const struct trap_bits coarse_trap_bits[] = {
+};
+
+#define MCB(id, ...)						\
+	[id - __MULTIPLE_CONTROL_BITS__]	=		\
+		(const enum cgt_group_id[]){			\
+		__VA_ARGS__, __RESERVED__			\
+		}
+
+static const enum cgt_group_id *coarse_control_combo[] = {
+};
+
+typedef enum trap_behaviour (*complex_condition_check)(struct kvm_vcpu *);
+
+#define CCC(id, fn)				\
+	[id - __COMPLEX_CONDITIONS__] = fn
+
+static const complex_condition_check ccc[] = {
+};
+
+/*
+ * Bit assignment for the trap controls. We use a 64bit word with the
+ * following layout for each trapped sysreg:
+ *
+ * [9:0]	enum cgt_group_id (10 bits)
+ * [62:10]	Unused (53 bits)
+ * [63]		RES0 - Must be zero, as lost on insertion in the xarray
+ */
+#define TC_CGT_BITS	10
+
+union trap_config {
+	u64	val;
+	struct {
+		unsigned long	cgt:TC_CGT_BITS; /* Coarse Grained Trap id */
+		unsigned long	unused:53;	 /* Unused, should be zero */
+		unsigned long	mbz:1;		 /* Must Be Zero */
+	};
+};
+
+struct encoding_to_trap_config {
+	const u32			encoding;
+	const u32			end;
+	const union trap_config		tc;
+	const unsigned int		line;
+};
+
+#define SR_RANGE_TRAP(sr_start, sr_end, trap_id)			\
+	{								\
+		.encoding	= sr_start,				\
+		.end		= sr_end,				\
+		.tc		= {					\
+			.cgt		= trap_id,			\
+		},							\
+		.line = __LINE__,					\
+	}
+
+#define SR_TRAP(sr, trap_id)		SR_RANGE_TRAP(sr, sr, trap_id)
+
+/*
+ * Map encoding to trap bits for exception reported with EC=0x18.
+ * These must only be evaluated when running a nested hypervisor, but
+ * that the current context is not a hypervisor context. When the
+ * trapped access matches one of the trap controls, the exception is
+ * re-injected in the nested hypervisor.
+ */
+static const struct encoding_to_trap_config encoding_to_cgt[] __initconst = {
+};
+
+static DEFINE_XARRAY(sr_forward_xa);
+
+static union trap_config get_trap_config(u32 sysreg)
+{
+	return (union trap_config) {
+		.val = xa_to_value(xa_load(&sr_forward_xa, sysreg)),
+	};
+}
+
+static __init void print_nv_trap_error(const struct encoding_to_trap_config *tc,
+				       const char *type, int err)
+{
+	kvm_err("%s line %d encoding range "
+		"(%d, %d, %d, %d, %d) - (%d, %d, %d, %d, %d) (err=%d)\n",
+		type, tc->line,
+		sys_reg_Op0(tc->encoding), sys_reg_Op1(tc->encoding),
+		sys_reg_CRn(tc->encoding), sys_reg_CRm(tc->encoding),
+		sys_reg_Op2(tc->encoding),
+		sys_reg_Op0(tc->end), sys_reg_Op1(tc->end),
+		sys_reg_CRn(tc->end), sys_reg_CRm(tc->end),
+		sys_reg_Op2(tc->end),
+		err);
+}
+
+int __init populate_nv_trap_config(void)
+{
+	int ret = 0;
+
+	BUILD_BUG_ON(sizeof(union trap_config) != sizeof(void *));
+	BUILD_BUG_ON(__NR_CGT_GROUP_IDS__ > BIT(TC_CGT_BITS));
+
+	for (int i = 0; i < ARRAY_SIZE(encoding_to_cgt); i++) {
+		const struct encoding_to_trap_config *cgt = &encoding_to_cgt[i];
+		void *prev;
+
+		if (cgt->tc.val & BIT(63)) {
+			kvm_err("CGT[%d] has MBZ bit set\n", i);
+			ret = -EINVAL;
+		}
+
+		if (cgt->encoding != cgt->end) {
+			prev = xa_store_range(&sr_forward_xa,
+					      cgt->encoding, cgt->end,
+					      xa_mk_value(cgt->tc.val),
+					      GFP_KERNEL);
+		} else {
+			prev = xa_store(&sr_forward_xa, cgt->encoding,
+					xa_mk_value(cgt->tc.val), GFP_KERNEL);
+			if (prev && !xa_is_err(prev)) {
+				ret = -EINVAL;
+				print_nv_trap_error(cgt, "Duplicate CGT", ret);
+			}
+		}
+
+		if (xa_is_err(prev)) {
+			ret = xa_err(prev);
+			print_nv_trap_error(cgt, "Failed CGT insertion", ret);
+		}
+	}
+
+	kvm_info("nv: %ld coarse grained trap handlers\n",
+		 ARRAY_SIZE(encoding_to_cgt));
+
+	for (int id = __MULTIPLE_CONTROL_BITS__; id < __COMPLEX_CONDITIONS__; id++) {
+		const enum cgt_group_id *cgids;
+
+		cgids = coarse_control_combo[id - __MULTIPLE_CONTROL_BITS__];
+
+		for (int i = 0; cgids[i] != __RESERVED__; i++) {
+			if (cgids[i] >= __MULTIPLE_CONTROL_BITS__) {
+				kvm_err("Recursive MCB %d/%d\n", id, cgids[i]);
+				ret = -EINVAL;
+			}
+		}
+	}
+
+	if (ret)
+		xa_destroy(&sr_forward_xa);
+
+	return ret;
+}
+
+static enum trap_behaviour get_behaviour(struct kvm_vcpu *vcpu,
+					 const struct trap_bits *tb)
+{
+	enum trap_behaviour b = BEHAVE_HANDLE_LOCALLY;
+	u64 val;
+
+	val = __vcpu_sys_reg(vcpu, tb->index);
+	if ((val & tb->mask) == tb->value)
+		b |= tb->behaviour;
+
+	return b;
+}
+
+static enum trap_behaviour __compute_trap_behaviour(struct kvm_vcpu *vcpu,
+						    const enum cgt_group_id id,
+						    enum trap_behaviour b)
+{
+	switch (id) {
+		const enum cgt_group_id *cgids;
+
+	case __RESERVED__ ... __MULTIPLE_CONTROL_BITS__ - 1:
+		if (likely(id != __RESERVED__))
+			b |= get_behaviour(vcpu, &coarse_trap_bits[id]);
+		break;
+	case __MULTIPLE_CONTROL_BITS__ ... __COMPLEX_CONDITIONS__ - 1:
+		/* Yes, this is recursive. Don't do anything stupid. */
+		cgids = coarse_control_combo[id - __MULTIPLE_CONTROL_BITS__];
+		for (int i = 0; cgids[i] != __RESERVED__; i++)
+			b |= __compute_trap_behaviour(vcpu, cgids[i], b);
+		break;
+	default:
+		if (ARRAY_SIZE(ccc))
+			b |= ccc[id -  __COMPLEX_CONDITIONS__](vcpu);
+		break;
+	}
+
+	return b;
+}
+
+static enum trap_behaviour compute_trap_behaviour(struct kvm_vcpu *vcpu,
+						  const union trap_config tc)
+{
+	enum trap_behaviour b = BEHAVE_HANDLE_LOCALLY;
+
+	return __compute_trap_behaviour(vcpu, tc.cgt, b);
+}
+
+bool __check_nv_sr_forward(struct kvm_vcpu *vcpu)
+{
+	union trap_config tc;
+	enum trap_behaviour b;
+	bool is_read;
+	u32 sysreg;
+	u64 esr;
+
+	if (!vcpu_has_nv(vcpu) || is_hyp_ctxt(vcpu))
+		return false;
+
+	esr = kvm_vcpu_get_esr(vcpu);
+	sysreg = esr_sys64_to_sysreg(esr);
+	is_read = (esr & ESR_ELx_SYS64_ISS_DIR_MASK) == ESR_ELx_SYS64_ISS_DIR_READ;
+
+	tc = get_trap_config(sysreg);
+
+	/*
+	 * A value of 0 for the whole entry means that we know nothing
+	 * for this sysreg, and that it cannot be re-injected into the
+	 * nested hypervisor. In this situation, let's cut it short.
+	 *
+	 * Note that ultimately, we could also make use of the xarray
+	 * to store the index of the sysreg in the local descriptor
+	 * array, avoiding another search... Hint, hint...
+	 */
+	if (!tc.val)
+		return false;
+
+	b = compute_trap_behaviour(vcpu, tc);
+
+	if (((b & BEHAVE_FORWARD_READ) && is_read) ||
+	    ((b & BEHAVE_FORWARD_WRITE) && !is_read))
+		goto inject;
+
+	return false;
+
+inject:
+	trace_kvm_forward_sysreg_trap(vcpu, sysreg, is_read);
+
+	kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
+	return true;
+}
+
 static u64 kvm_check_illegal_exception_return(struct kvm_vcpu *vcpu, u64 spsr)
 {
 	u64 mode = spsr & PSR_MODE_MASK;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index f5baaa508926..9556896311db 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -3177,6 +3177,9 @@ int kvm_handle_sys_reg(struct kvm_vcpu *vcpu)
 
 	trace_kvm_handle_sys_reg(esr);
 
+	if (__check_nv_sr_forward(vcpu))
+		return 1;
+
 	params = esr_sys64_to_params(esr);
 	params.regval = vcpu_get_reg(vcpu, Rt);
 
@@ -3594,5 +3597,8 @@ int __init kvm_sys_reg_table_init(void)
 	if (!first_idreg)
 		return -EINVAL;
 
+	if (kvm_get_mode() == KVM_MODE_NV)
+		return populate_nv_trap_config();
+
 	return 0;
 }
diff --git a/arch/arm64/kvm/trace_arm.h b/arch/arm64/kvm/trace_arm.h
index 6ce5c025218d..8ad53104934d 100644
--- a/arch/arm64/kvm/trace_arm.h
+++ b/arch/arm64/kvm/trace_arm.h
@@ -364,6 +364,32 @@ TRACE_EVENT(kvm_inject_nested_exception,
 		  __entry->hcr_el2)
 );
 
+TRACE_EVENT(kvm_forward_sysreg_trap,
+	    TP_PROTO(struct kvm_vcpu *vcpu, u32 sysreg, bool is_read),
+	    TP_ARGS(vcpu, sysreg, is_read),
+
+	    TP_STRUCT__entry(
+		__field(u64,	pc)
+		__field(u32,	sysreg)
+		__field(bool,	is_read)
+	    ),
+
+	    TP_fast_assign(
+		__entry->pc = *vcpu_pc(vcpu);
+		__entry->sysreg = sysreg;
+		__entry->is_read = is_read;
+	    ),
+
+	    TP_printk("%llx %c (%d,%d,%d,%d,%d)",
+		      __entry->pc,
+		      __entry->is_read ? 'R' : 'W',
+		      sys_reg_Op0(__entry->sysreg),
+		      sys_reg_Op1(__entry->sysreg),
+		      sys_reg_CRn(__entry->sysreg),
+		      sys_reg_CRm(__entry->sysreg),
+		      sys_reg_Op2(__entry->sysreg))
+);
+
 #endif /* _TRACE_ARM_ARM64_KVM_H */
 
 #undef TRACE_INCLUDE_PATH

From d0fc0a2519a6dd906aac448e742958d30b5787ac Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 15 Aug 2023 19:38:49 +0100
Subject: [PATCH 0490/1189] KVM: arm64: nv: Add trap forwarding for HCR_EL2

Describe the HCR_EL2 register, and associate it with all the sysregs
it allows to trap.

Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Jing Zhang <jingzhangos@google.com>
Link: https://lore.kernel.org/r/20230815183903.2735724-16-maz@kernel.org
---
 arch/arm64/kvm/emulate-nested.c | 488 ++++++++++++++++++++++++++++++++
 1 file changed, 488 insertions(+)

diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index d5837ed0077c..975a30ef874a 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -38,12 +38,48 @@ enum cgt_group_id {
 	 * on their own instead of being part of a combination of
 	 * trap controls.
 	 */
+	CGT_HCR_TID1,
+	CGT_HCR_TID2,
+	CGT_HCR_TID3,
+	CGT_HCR_IMO,
+	CGT_HCR_FMO,
+	CGT_HCR_TIDCP,
+	CGT_HCR_TACR,
+	CGT_HCR_TSW,
+	CGT_HCR_TPC,
+	CGT_HCR_TPU,
+	CGT_HCR_TTLB,
+	CGT_HCR_TVM,
+	CGT_HCR_TDZ,
+	CGT_HCR_TRVM,
+	CGT_HCR_TLOR,
+	CGT_HCR_TERR,
+	CGT_HCR_APK,
+	CGT_HCR_NV,
+	CGT_HCR_NV_nNV2,
+	CGT_HCR_NV1_nNV2,
+	CGT_HCR_AT,
+	CGT_HCR_nFIEN,
+	CGT_HCR_TID4,
+	CGT_HCR_TICAB,
+	CGT_HCR_TOCU,
+	CGT_HCR_ENSCXT,
+	CGT_HCR_TTLBIS,
+	CGT_HCR_TTLBOS,
 
 	/*
 	 * Anything after this point is a combination of coarse trap
 	 * controls, which must all be evaluated to decide what to do.
 	 */
 	__MULTIPLE_CONTROL_BITS__,
+	CGT_HCR_IMO_FMO = __MULTIPLE_CONTROL_BITS__,
+	CGT_HCR_TID2_TID4,
+	CGT_HCR_TTLB_TTLBIS,
+	CGT_HCR_TTLB_TTLBOS,
+	CGT_HCR_TVM_TRVM,
+	CGT_HCR_TPU_TICAB,
+	CGT_HCR_TPU_TOCU,
+	CGT_HCR_NV1_nNV2_ENSCXT,
 
 	/*
 	 * Anything after this point requires a callback evaluating a
@@ -56,6 +92,174 @@ enum cgt_group_id {
 };
 
 static const struct trap_bits coarse_trap_bits[] = {
+	[CGT_HCR_TID1] = {
+		.index		= HCR_EL2,
+		.value 		= HCR_TID1,
+		.mask		= HCR_TID1,
+		.behaviour	= BEHAVE_FORWARD_READ,
+	},
+	[CGT_HCR_TID2] = {
+		.index		= HCR_EL2,
+		.value 		= HCR_TID2,
+		.mask		= HCR_TID2,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_HCR_TID3] = {
+		.index		= HCR_EL2,
+		.value 		= HCR_TID3,
+		.mask		= HCR_TID3,
+		.behaviour	= BEHAVE_FORWARD_READ,
+	},
+	[CGT_HCR_IMO] = {
+		.index		= HCR_EL2,
+		.value 		= HCR_IMO,
+		.mask		= HCR_IMO,
+		.behaviour	= BEHAVE_FORWARD_WRITE,
+	},
+	[CGT_HCR_FMO] = {
+		.index		= HCR_EL2,
+		.value 		= HCR_FMO,
+		.mask		= HCR_FMO,
+		.behaviour	= BEHAVE_FORWARD_WRITE,
+	},
+	[CGT_HCR_TIDCP] = {
+		.index		= HCR_EL2,
+		.value		= HCR_TIDCP,
+		.mask		= HCR_TIDCP,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_HCR_TACR] = {
+		.index		= HCR_EL2,
+		.value		= HCR_TACR,
+		.mask		= HCR_TACR,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_HCR_TSW] = {
+		.index		= HCR_EL2,
+		.value		= HCR_TSW,
+		.mask		= HCR_TSW,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_HCR_TPC] = { /* Also called TCPC when FEAT_DPB is implemented */
+		.index		= HCR_EL2,
+		.value		= HCR_TPC,
+		.mask		= HCR_TPC,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_HCR_TPU] = {
+		.index		= HCR_EL2,
+		.value		= HCR_TPU,
+		.mask		= HCR_TPU,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_HCR_TTLB] = {
+		.index		= HCR_EL2,
+		.value		= HCR_TTLB,
+		.mask		= HCR_TTLB,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_HCR_TVM] = {
+		.index		= HCR_EL2,
+		.value		= HCR_TVM,
+		.mask		= HCR_TVM,
+		.behaviour	= BEHAVE_FORWARD_WRITE,
+	},
+	[CGT_HCR_TDZ] = {
+		.index		= HCR_EL2,
+		.value		= HCR_TDZ,
+		.mask		= HCR_TDZ,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_HCR_TRVM] = {
+		.index		= HCR_EL2,
+		.value		= HCR_TRVM,
+		.mask		= HCR_TRVM,
+		.behaviour	= BEHAVE_FORWARD_READ,
+	},
+	[CGT_HCR_TLOR] = {
+		.index		= HCR_EL2,
+		.value		= HCR_TLOR,
+		.mask		= HCR_TLOR,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_HCR_TERR] = {
+		.index		= HCR_EL2,
+		.value		= HCR_TERR,
+		.mask		= HCR_TERR,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_HCR_APK] = {
+		.index		= HCR_EL2,
+		.value		= 0,
+		.mask		= HCR_APK,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_HCR_NV] = {
+		.index		= HCR_EL2,
+		.value		= HCR_NV,
+		.mask		= HCR_NV,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_HCR_NV_nNV2] = {
+		.index		= HCR_EL2,
+		.value		= HCR_NV,
+		.mask		= HCR_NV | HCR_NV2,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_HCR_NV1_nNV2] = {
+		.index		= HCR_EL2,
+		.value		= HCR_NV | HCR_NV1,
+		.mask		= HCR_NV | HCR_NV1 | HCR_NV2,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_HCR_AT] = {
+		.index		= HCR_EL2,
+		.value		= HCR_AT,
+		.mask		= HCR_AT,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_HCR_nFIEN] = {
+		.index		= HCR_EL2,
+		.value		= 0,
+		.mask		= HCR_FIEN,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_HCR_TID4] = {
+		.index		= HCR_EL2,
+		.value 		= HCR_TID4,
+		.mask		= HCR_TID4,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_HCR_TICAB] = {
+		.index		= HCR_EL2,
+		.value 		= HCR_TICAB,
+		.mask		= HCR_TICAB,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_HCR_TOCU] = {
+		.index		= HCR_EL2,
+		.value 		= HCR_TOCU,
+		.mask		= HCR_TOCU,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_HCR_ENSCXT] = {
+		.index		= HCR_EL2,
+		.value 		= 0,
+		.mask		= HCR_ENSCXT,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_HCR_TTLBIS] = {
+		.index		= HCR_EL2,
+		.value		= HCR_TTLBIS,
+		.mask		= HCR_TTLBIS,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_HCR_TTLBOS] = {
+		.index		= HCR_EL2,
+		.value		= HCR_TTLBOS,
+		.mask		= HCR_TTLBOS,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
 };
 
 #define MCB(id, ...)						\
@@ -65,6 +269,14 @@ static const struct trap_bits coarse_trap_bits[] = {
 		}
 
 static const enum cgt_group_id *coarse_control_combo[] = {
+	MCB(CGT_HCR_IMO_FMO,		CGT_HCR_IMO, CGT_HCR_FMO),
+	MCB(CGT_HCR_TID2_TID4,		CGT_HCR_TID2, CGT_HCR_TID4),
+	MCB(CGT_HCR_TTLB_TTLBIS,	CGT_HCR_TTLB, CGT_HCR_TTLBIS),
+	MCB(CGT_HCR_TTLB_TTLBOS,	CGT_HCR_TTLB, CGT_HCR_TTLBOS),
+	MCB(CGT_HCR_TVM_TRVM,		CGT_HCR_TVM, CGT_HCR_TRVM),
+	MCB(CGT_HCR_TPU_TICAB,		CGT_HCR_TPU, CGT_HCR_TICAB),
+	MCB(CGT_HCR_TPU_TOCU,		CGT_HCR_TPU, CGT_HCR_TOCU),
+	MCB(CGT_HCR_NV1_nNV2_ENSCXT,	CGT_HCR_NV1_nNV2, CGT_HCR_ENSCXT),
 };
 
 typedef enum trap_behaviour (*complex_condition_check)(struct kvm_vcpu *);
@@ -121,6 +333,282 @@ struct encoding_to_trap_config {
  * re-injected in the nested hypervisor.
  */
 static const struct encoding_to_trap_config encoding_to_cgt[] __initconst = {
+	SR_TRAP(SYS_REVIDR_EL1,		CGT_HCR_TID1),
+	SR_TRAP(SYS_AIDR_EL1,		CGT_HCR_TID1),
+	SR_TRAP(SYS_SMIDR_EL1,		CGT_HCR_TID1),
+	SR_TRAP(SYS_CTR_EL0,		CGT_HCR_TID2),
+	SR_TRAP(SYS_CCSIDR_EL1,		CGT_HCR_TID2_TID4),
+	SR_TRAP(SYS_CCSIDR2_EL1,	CGT_HCR_TID2_TID4),
+	SR_TRAP(SYS_CLIDR_EL1,		CGT_HCR_TID2_TID4),
+	SR_TRAP(SYS_CSSELR_EL1,		CGT_HCR_TID2_TID4),
+	SR_RANGE_TRAP(SYS_ID_PFR0_EL1,
+		      sys_reg(3, 0, 0, 7, 7), CGT_HCR_TID3),
+	SR_TRAP(SYS_ICC_SGI0R_EL1,	CGT_HCR_IMO_FMO),
+	SR_TRAP(SYS_ICC_ASGI1R_EL1,	CGT_HCR_IMO_FMO),
+	SR_TRAP(SYS_ICC_SGI1R_EL1,	CGT_HCR_IMO_FMO),
+	SR_RANGE_TRAP(sys_reg(3, 0, 11, 0, 0),
+		      sys_reg(3, 0, 11, 15, 7), CGT_HCR_TIDCP),
+	SR_RANGE_TRAP(sys_reg(3, 1, 11, 0, 0),
+		      sys_reg(3, 1, 11, 15, 7), CGT_HCR_TIDCP),
+	SR_RANGE_TRAP(sys_reg(3, 2, 11, 0, 0),
+		      sys_reg(3, 2, 11, 15, 7), CGT_HCR_TIDCP),
+	SR_RANGE_TRAP(sys_reg(3, 3, 11, 0, 0),
+		      sys_reg(3, 3, 11, 15, 7), CGT_HCR_TIDCP),
+	SR_RANGE_TRAP(sys_reg(3, 4, 11, 0, 0),
+		      sys_reg(3, 4, 11, 15, 7), CGT_HCR_TIDCP),
+	SR_RANGE_TRAP(sys_reg(3, 5, 11, 0, 0),
+		      sys_reg(3, 5, 11, 15, 7), CGT_HCR_TIDCP),
+	SR_RANGE_TRAP(sys_reg(3, 6, 11, 0, 0),
+		      sys_reg(3, 6, 11, 15, 7), CGT_HCR_TIDCP),
+	SR_RANGE_TRAP(sys_reg(3, 7, 11, 0, 0),
+		      sys_reg(3, 7, 11, 15, 7), CGT_HCR_TIDCP),
+	SR_RANGE_TRAP(sys_reg(3, 0, 15, 0, 0),
+		      sys_reg(3, 0, 15, 15, 7), CGT_HCR_TIDCP),
+	SR_RANGE_TRAP(sys_reg(3, 1, 15, 0, 0),
+		      sys_reg(3, 1, 15, 15, 7), CGT_HCR_TIDCP),
+	SR_RANGE_TRAP(sys_reg(3, 2, 15, 0, 0),
+		      sys_reg(3, 2, 15, 15, 7), CGT_HCR_TIDCP),
+	SR_RANGE_TRAP(sys_reg(3, 3, 15, 0, 0),
+		      sys_reg(3, 3, 15, 15, 7), CGT_HCR_TIDCP),
+	SR_RANGE_TRAP(sys_reg(3, 4, 15, 0, 0),
+		      sys_reg(3, 4, 15, 15, 7), CGT_HCR_TIDCP),
+	SR_RANGE_TRAP(sys_reg(3, 5, 15, 0, 0),
+		      sys_reg(3, 5, 15, 15, 7), CGT_HCR_TIDCP),
+	SR_RANGE_TRAP(sys_reg(3, 6, 15, 0, 0),
+		      sys_reg(3, 6, 15, 15, 7), CGT_HCR_TIDCP),
+	SR_RANGE_TRAP(sys_reg(3, 7, 15, 0, 0),
+		      sys_reg(3, 7, 15, 15, 7), CGT_HCR_TIDCP),
+	SR_TRAP(SYS_ACTLR_EL1,		CGT_HCR_TACR),
+	SR_TRAP(SYS_DC_ISW,		CGT_HCR_TSW),
+	SR_TRAP(SYS_DC_CSW,		CGT_HCR_TSW),
+	SR_TRAP(SYS_DC_CISW,		CGT_HCR_TSW),
+	SR_TRAP(SYS_DC_IGSW,		CGT_HCR_TSW),
+	SR_TRAP(SYS_DC_IGDSW,		CGT_HCR_TSW),
+	SR_TRAP(SYS_DC_CGSW,		CGT_HCR_TSW),
+	SR_TRAP(SYS_DC_CGDSW,		CGT_HCR_TSW),
+	SR_TRAP(SYS_DC_CIGSW,		CGT_HCR_TSW),
+	SR_TRAP(SYS_DC_CIGDSW,		CGT_HCR_TSW),
+	SR_TRAP(SYS_DC_CIVAC,		CGT_HCR_TPC),
+	SR_TRAP(SYS_DC_CVAC,		CGT_HCR_TPC),
+	SR_TRAP(SYS_DC_CVAP,		CGT_HCR_TPC),
+	SR_TRAP(SYS_DC_CVADP,		CGT_HCR_TPC),
+	SR_TRAP(SYS_DC_IVAC,		CGT_HCR_TPC),
+	SR_TRAP(SYS_DC_CIGVAC,		CGT_HCR_TPC),
+	SR_TRAP(SYS_DC_CIGDVAC,		CGT_HCR_TPC),
+	SR_TRAP(SYS_DC_IGVAC,		CGT_HCR_TPC),
+	SR_TRAP(SYS_DC_IGDVAC,		CGT_HCR_TPC),
+	SR_TRAP(SYS_DC_CGVAC,		CGT_HCR_TPC),
+	SR_TRAP(SYS_DC_CGDVAC,		CGT_HCR_TPC),
+	SR_TRAP(SYS_DC_CGVAP,		CGT_HCR_TPC),
+	SR_TRAP(SYS_DC_CGDVAP,		CGT_HCR_TPC),
+	SR_TRAP(SYS_DC_CGVADP,		CGT_HCR_TPC),
+	SR_TRAP(SYS_DC_CGDVADP,		CGT_HCR_TPC),
+	SR_TRAP(SYS_IC_IVAU,		CGT_HCR_TPU_TOCU),
+	SR_TRAP(SYS_IC_IALLU,		CGT_HCR_TPU_TOCU),
+	SR_TRAP(SYS_IC_IALLUIS,		CGT_HCR_TPU_TICAB),
+	SR_TRAP(SYS_DC_CVAU,		CGT_HCR_TPU_TOCU),
+	SR_TRAP(OP_TLBI_RVAE1,		CGT_HCR_TTLB),
+	SR_TRAP(OP_TLBI_RVAAE1,		CGT_HCR_TTLB),
+	SR_TRAP(OP_TLBI_RVALE1,		CGT_HCR_TTLB),
+	SR_TRAP(OP_TLBI_RVAALE1,	CGT_HCR_TTLB),
+	SR_TRAP(OP_TLBI_VMALLE1,	CGT_HCR_TTLB),
+	SR_TRAP(OP_TLBI_VAE1,		CGT_HCR_TTLB),
+	SR_TRAP(OP_TLBI_ASIDE1,		CGT_HCR_TTLB),
+	SR_TRAP(OP_TLBI_VAAE1,		CGT_HCR_TTLB),
+	SR_TRAP(OP_TLBI_VALE1,		CGT_HCR_TTLB),
+	SR_TRAP(OP_TLBI_VAALE1,		CGT_HCR_TTLB),
+	SR_TRAP(OP_TLBI_RVAE1NXS,	CGT_HCR_TTLB),
+	SR_TRAP(OP_TLBI_RVAAE1NXS,	CGT_HCR_TTLB),
+	SR_TRAP(OP_TLBI_RVALE1NXS,	CGT_HCR_TTLB),
+	SR_TRAP(OP_TLBI_RVAALE1NXS,	CGT_HCR_TTLB),
+	SR_TRAP(OP_TLBI_VMALLE1NXS,	CGT_HCR_TTLB),
+	SR_TRAP(OP_TLBI_VAE1NXS,	CGT_HCR_TTLB),
+	SR_TRAP(OP_TLBI_ASIDE1NXS,	CGT_HCR_TTLB),
+	SR_TRAP(OP_TLBI_VAAE1NXS,	CGT_HCR_TTLB),
+	SR_TRAP(OP_TLBI_VALE1NXS,	CGT_HCR_TTLB),
+	SR_TRAP(OP_TLBI_VAALE1NXS,	CGT_HCR_TTLB),
+	SR_TRAP(OP_TLBI_RVAE1IS,	CGT_HCR_TTLB_TTLBIS),
+	SR_TRAP(OP_TLBI_RVAAE1IS,	CGT_HCR_TTLB_TTLBIS),
+	SR_TRAP(OP_TLBI_RVALE1IS,	CGT_HCR_TTLB_TTLBIS),
+	SR_TRAP(OP_TLBI_RVAALE1IS,	CGT_HCR_TTLB_TTLBIS),
+	SR_TRAP(OP_TLBI_VMALLE1IS,	CGT_HCR_TTLB_TTLBIS),
+	SR_TRAP(OP_TLBI_VAE1IS,		CGT_HCR_TTLB_TTLBIS),
+	SR_TRAP(OP_TLBI_ASIDE1IS,	CGT_HCR_TTLB_TTLBIS),
+	SR_TRAP(OP_TLBI_VAAE1IS,	CGT_HCR_TTLB_TTLBIS),
+	SR_TRAP(OP_TLBI_VALE1IS,	CGT_HCR_TTLB_TTLBIS),
+	SR_TRAP(OP_TLBI_VAALE1IS,	CGT_HCR_TTLB_TTLBIS),
+	SR_TRAP(OP_TLBI_RVAE1ISNXS,	CGT_HCR_TTLB_TTLBIS),
+	SR_TRAP(OP_TLBI_RVAAE1ISNXS,	CGT_HCR_TTLB_TTLBIS),
+	SR_TRAP(OP_TLBI_RVALE1ISNXS,	CGT_HCR_TTLB_TTLBIS),
+	SR_TRAP(OP_TLBI_RVAALE1ISNXS,	CGT_HCR_TTLB_TTLBIS),
+	SR_TRAP(OP_TLBI_VMALLE1ISNXS,	CGT_HCR_TTLB_TTLBIS),
+	SR_TRAP(OP_TLBI_VAE1ISNXS,	CGT_HCR_TTLB_TTLBIS),
+	SR_TRAP(OP_TLBI_ASIDE1ISNXS,	CGT_HCR_TTLB_TTLBIS),
+	SR_TRAP(OP_TLBI_VAAE1ISNXS,	CGT_HCR_TTLB_TTLBIS),
+	SR_TRAP(OP_TLBI_VALE1ISNXS,	CGT_HCR_TTLB_TTLBIS),
+	SR_TRAP(OP_TLBI_VAALE1ISNXS,	CGT_HCR_TTLB_TTLBIS),
+	SR_TRAP(OP_TLBI_VMALLE1OS,	CGT_HCR_TTLB_TTLBOS),
+	SR_TRAP(OP_TLBI_VAE1OS,		CGT_HCR_TTLB_TTLBOS),
+	SR_TRAP(OP_TLBI_ASIDE1OS,	CGT_HCR_TTLB_TTLBOS),
+	SR_TRAP(OP_TLBI_VAAE1OS,	CGT_HCR_TTLB_TTLBOS),
+	SR_TRAP(OP_TLBI_VALE1OS,	CGT_HCR_TTLB_TTLBOS),
+	SR_TRAP(OP_TLBI_VAALE1OS,	CGT_HCR_TTLB_TTLBOS),
+	SR_TRAP(OP_TLBI_RVAE1OS,	CGT_HCR_TTLB_TTLBOS),
+	SR_TRAP(OP_TLBI_RVAAE1OS,	CGT_HCR_TTLB_TTLBOS),
+	SR_TRAP(OP_TLBI_RVALE1OS,	CGT_HCR_TTLB_TTLBOS),
+	SR_TRAP(OP_TLBI_RVAALE1OS,	CGT_HCR_TTLB_TTLBOS),
+	SR_TRAP(OP_TLBI_VMALLE1OSNXS,	CGT_HCR_TTLB_TTLBOS),
+	SR_TRAP(OP_TLBI_VAE1OSNXS,	CGT_HCR_TTLB_TTLBOS),
+	SR_TRAP(OP_TLBI_ASIDE1OSNXS,	CGT_HCR_TTLB_TTLBOS),
+	SR_TRAP(OP_TLBI_VAAE1OSNXS,	CGT_HCR_TTLB_TTLBOS),
+	SR_TRAP(OP_TLBI_VALE1OSNXS,	CGT_HCR_TTLB_TTLBOS),
+	SR_TRAP(OP_TLBI_VAALE1OSNXS,	CGT_HCR_TTLB_TTLBOS),
+	SR_TRAP(OP_TLBI_RVAE1OSNXS,	CGT_HCR_TTLB_TTLBOS),
+	SR_TRAP(OP_TLBI_RVAAE1OSNXS,	CGT_HCR_TTLB_TTLBOS),
+	SR_TRAP(OP_TLBI_RVALE1OSNXS,	CGT_HCR_TTLB_TTLBOS),
+	SR_TRAP(OP_TLBI_RVAALE1OSNXS,	CGT_HCR_TTLB_TTLBOS),
+	SR_TRAP(SYS_SCTLR_EL1,		CGT_HCR_TVM_TRVM),
+	SR_TRAP(SYS_TTBR0_EL1,		CGT_HCR_TVM_TRVM),
+	SR_TRAP(SYS_TTBR1_EL1,		CGT_HCR_TVM_TRVM),
+	SR_TRAP(SYS_TCR_EL1,		CGT_HCR_TVM_TRVM),
+	SR_TRAP(SYS_ESR_EL1,		CGT_HCR_TVM_TRVM),
+	SR_TRAP(SYS_FAR_EL1,		CGT_HCR_TVM_TRVM),
+	SR_TRAP(SYS_AFSR0_EL1,		CGT_HCR_TVM_TRVM),
+	SR_TRAP(SYS_AFSR1_EL1,		CGT_HCR_TVM_TRVM),
+	SR_TRAP(SYS_MAIR_EL1,		CGT_HCR_TVM_TRVM),
+	SR_TRAP(SYS_AMAIR_EL1,		CGT_HCR_TVM_TRVM),
+	SR_TRAP(SYS_CONTEXTIDR_EL1,	CGT_HCR_TVM_TRVM),
+	SR_TRAP(SYS_DC_ZVA,		CGT_HCR_TDZ),
+	SR_TRAP(SYS_DC_GVA,		CGT_HCR_TDZ),
+	SR_TRAP(SYS_DC_GZVA,		CGT_HCR_TDZ),
+	SR_TRAP(SYS_LORSA_EL1,		CGT_HCR_TLOR),
+	SR_TRAP(SYS_LOREA_EL1, 		CGT_HCR_TLOR),
+	SR_TRAP(SYS_LORN_EL1, 		CGT_HCR_TLOR),
+	SR_TRAP(SYS_LORC_EL1, 		CGT_HCR_TLOR),
+	SR_TRAP(SYS_LORID_EL1,		CGT_HCR_TLOR),
+	SR_TRAP(SYS_ERRIDR_EL1,		CGT_HCR_TERR),
+	SR_TRAP(SYS_ERRSELR_EL1,	CGT_HCR_TERR),
+	SR_TRAP(SYS_ERXADDR_EL1,	CGT_HCR_TERR),
+	SR_TRAP(SYS_ERXCTLR_EL1,	CGT_HCR_TERR),
+	SR_TRAP(SYS_ERXFR_EL1,		CGT_HCR_TERR),
+	SR_TRAP(SYS_ERXMISC0_EL1,	CGT_HCR_TERR),
+	SR_TRAP(SYS_ERXMISC1_EL1,	CGT_HCR_TERR),
+	SR_TRAP(SYS_ERXMISC2_EL1,	CGT_HCR_TERR),
+	SR_TRAP(SYS_ERXMISC3_EL1,	CGT_HCR_TERR),
+	SR_TRAP(SYS_ERXSTATUS_EL1,	CGT_HCR_TERR),
+	SR_TRAP(SYS_APIAKEYLO_EL1,	CGT_HCR_APK),
+	SR_TRAP(SYS_APIAKEYHI_EL1,	CGT_HCR_APK),
+	SR_TRAP(SYS_APIBKEYLO_EL1,	CGT_HCR_APK),
+	SR_TRAP(SYS_APIBKEYHI_EL1,	CGT_HCR_APK),
+	SR_TRAP(SYS_APDAKEYLO_EL1,	CGT_HCR_APK),
+	SR_TRAP(SYS_APDAKEYHI_EL1,	CGT_HCR_APK),
+	SR_TRAP(SYS_APDBKEYLO_EL1,	CGT_HCR_APK),
+	SR_TRAP(SYS_APDBKEYHI_EL1,	CGT_HCR_APK),
+	SR_TRAP(SYS_APGAKEYLO_EL1,	CGT_HCR_APK),
+	SR_TRAP(SYS_APGAKEYHI_EL1,	CGT_HCR_APK),
+	/* All _EL2 registers */
+	SR_RANGE_TRAP(sys_reg(3, 4, 0, 0, 0),
+		      sys_reg(3, 4, 3, 15, 7), CGT_HCR_NV),
+	/* Skip the SP_EL1 encoding... */
+	SR_RANGE_TRAP(sys_reg(3, 4, 4, 1, 1),
+		      sys_reg(3, 4, 10, 15, 7), CGT_HCR_NV),
+	SR_RANGE_TRAP(sys_reg(3, 4, 12, 0, 0),
+		      sys_reg(3, 4, 14, 15, 7), CGT_HCR_NV),
+	/* All _EL02, _EL12 registers */
+	SR_RANGE_TRAP(sys_reg(3, 5, 0, 0, 0),
+		      sys_reg(3, 5, 10, 15, 7), CGT_HCR_NV),
+	SR_RANGE_TRAP(sys_reg(3, 5, 12, 0, 0),
+		      sys_reg(3, 5, 14, 15, 7), CGT_HCR_NV),
+	SR_TRAP(OP_AT_S1E2R,		CGT_HCR_NV),
+	SR_TRAP(OP_AT_S1E2W,		CGT_HCR_NV),
+	SR_TRAP(OP_AT_S12E1R,		CGT_HCR_NV),
+	SR_TRAP(OP_AT_S12E1W,		CGT_HCR_NV),
+	SR_TRAP(OP_AT_S12E0R,		CGT_HCR_NV),
+	SR_TRAP(OP_AT_S12E0W,		CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_IPAS2E1,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_RIPAS2E1,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_IPAS2LE1,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_RIPAS2LE1,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_RVAE2,		CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_RVALE2,		CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_ALLE2,		CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_VAE2,		CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_ALLE1,		CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_VALE2,		CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_VMALLS12E1,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_IPAS2E1NXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_RIPAS2E1NXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_IPAS2LE1NXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_RIPAS2LE1NXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_RVAE2NXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_RVALE2NXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_ALLE2NXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_VAE2NXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_ALLE1NXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_VALE2NXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_VMALLS12E1NXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_IPAS2E1IS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_RIPAS2E1IS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_IPAS2LE1IS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_RIPAS2LE1IS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_RVAE2IS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_RVALE2IS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_ALLE2IS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_VAE2IS,		CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_ALLE1IS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_VALE2IS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_VMALLS12E1IS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_IPAS2E1ISNXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_RIPAS2E1ISNXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_IPAS2LE1ISNXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_RIPAS2LE1ISNXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_RVAE2ISNXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_RVALE2ISNXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_ALLE2ISNXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_VAE2ISNXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_ALLE1ISNXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_VALE2ISNXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_VMALLS12E1ISNXS,CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_ALLE2OS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_VAE2OS,		CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_ALLE1OS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_VALE2OS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_VMALLS12E1OS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_IPAS2E1OS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_RIPAS2E1OS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_IPAS2LE1OS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_RIPAS2LE1OS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_RVAE2OS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_RVALE2OS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_ALLE2OSNXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_VAE2OSNXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_ALLE1OSNXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_VALE2OSNXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_VMALLS12E1OSNXS,CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_IPAS2E1OSNXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_RIPAS2E1OSNXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_IPAS2LE1OSNXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_RIPAS2LE1OSNXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_RVAE2OSNXS,	CGT_HCR_NV),
+	SR_TRAP(OP_TLBI_RVALE2OSNXS,	CGT_HCR_NV),
+	SR_TRAP(OP_CPP_RCTX, 		CGT_HCR_NV),
+	SR_TRAP(OP_DVP_RCTX, 		CGT_HCR_NV),
+	SR_TRAP(OP_CFP_RCTX, 		CGT_HCR_NV),
+	SR_TRAP(SYS_SP_EL1,		CGT_HCR_NV_nNV2),
+	SR_TRAP(SYS_VBAR_EL1,		CGT_HCR_NV1_nNV2),
+	SR_TRAP(SYS_ELR_EL1,		CGT_HCR_NV1_nNV2),
+	SR_TRAP(SYS_SPSR_EL1,		CGT_HCR_NV1_nNV2),
+	SR_TRAP(SYS_SCXTNUM_EL1,	CGT_HCR_NV1_nNV2_ENSCXT),
+	SR_TRAP(SYS_SCXTNUM_EL0,	CGT_HCR_ENSCXT),
+	SR_TRAP(OP_AT_S1E1R, 		CGT_HCR_AT),
+	SR_TRAP(OP_AT_S1E1W, 		CGT_HCR_AT),
+	SR_TRAP(OP_AT_S1E0R, 		CGT_HCR_AT),
+	SR_TRAP(OP_AT_S1E0W, 		CGT_HCR_AT),
+	SR_TRAP(OP_AT_S1E1RP, 		CGT_HCR_AT),
+	SR_TRAP(OP_AT_S1E1WP, 		CGT_HCR_AT),
+	SR_TRAP(SYS_ERXPFGF_EL1,	CGT_HCR_nFIEN),
+	SR_TRAP(SYS_ERXPFGCTL_EL1,	CGT_HCR_nFIEN),
+	SR_TRAP(SYS_ERXPFGCDN_EL1,	CGT_HCR_nFIEN),
 };
 
 static DEFINE_XARRAY(sr_forward_xa);

From a0b70fb00db83e678f92b8aed0a9a9e4ffcffb82 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 15 Aug 2023 19:38:50 +0100
Subject: [PATCH 0491/1189] KVM: arm64: nv: Expose FEAT_EVT to nested guests

Now that we properly implement FEAT_EVT (as we correctly forward
traps), expose it to guests.

Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Jing Zhang <jingzhangos@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230815183903.2735724-17-maz@kernel.org
---
 arch/arm64/kvm/nested.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 315354d27978..7f80f385d9e8 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -124,8 +124,7 @@ void access_nested_id_reg(struct kvm_vcpu *v, struct sys_reg_params *p,
 		break;
 
 	case SYS_ID_AA64MMFR2_EL1:
-		val &= ~(NV_FTR(MMFR2, EVT)	|
-			 NV_FTR(MMFR2, BBM)	|
+		val &= ~(NV_FTR(MMFR2, BBM)	|
 			 NV_FTR(MMFR2, TTL)	|
 			 GENMASK_ULL(47, 44)	|
 			 NV_FTR(MMFR2, ST)	|

From cb31632c44529048c052a2961b3adf62a2c89b17 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 15 Aug 2023 19:38:51 +0100
Subject: [PATCH 0492/1189] KVM: arm64: nv: Add trap forwarding for MDCR_EL2

Describe the MDCR_EL2 register, and associate it with all the sysregs
it allows to trap.

Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Jing Zhang <jingzhangos@google.com>
Link: https://lore.kernel.org/r/20230815183903.2735724-18-maz@kernel.org
---
 arch/arm64/kvm/emulate-nested.c | 268 ++++++++++++++++++++++++++++++++
 1 file changed, 268 insertions(+)

diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index 975a30ef874a..241e44eeed6d 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -67,6 +67,18 @@ enum cgt_group_id {
 	CGT_HCR_TTLBIS,
 	CGT_HCR_TTLBOS,
 
+	CGT_MDCR_TPMCR,
+	CGT_MDCR_TPM,
+	CGT_MDCR_TDE,
+	CGT_MDCR_TDA,
+	CGT_MDCR_TDOSA,
+	CGT_MDCR_TDRA,
+	CGT_MDCR_E2PB,
+	CGT_MDCR_TPMS,
+	CGT_MDCR_TTRF,
+	CGT_MDCR_E2TB,
+	CGT_MDCR_TDCC,
+
 	/*
 	 * Anything after this point is a combination of coarse trap
 	 * controls, which must all be evaluated to decide what to do.
@@ -80,6 +92,11 @@ enum cgt_group_id {
 	CGT_HCR_TPU_TICAB,
 	CGT_HCR_TPU_TOCU,
 	CGT_HCR_NV1_nNV2_ENSCXT,
+	CGT_MDCR_TPM_TPMCR,
+	CGT_MDCR_TDE_TDA,
+	CGT_MDCR_TDE_TDOSA,
+	CGT_MDCR_TDE_TDRA,
+	CGT_MDCR_TDCC_TDE_TDA,
 
 	/*
 	 * Anything after this point requires a callback evaluating a
@@ -260,6 +277,72 @@ static const struct trap_bits coarse_trap_bits[] = {
 		.mask		= HCR_TTLBOS,
 		.behaviour	= BEHAVE_FORWARD_ANY,
 	},
+	[CGT_MDCR_TPMCR] = {
+		.index		= MDCR_EL2,
+		.value		= MDCR_EL2_TPMCR,
+		.mask		= MDCR_EL2_TPMCR,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_MDCR_TPM] = {
+		.index		= MDCR_EL2,
+		.value		= MDCR_EL2_TPM,
+		.mask		= MDCR_EL2_TPM,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_MDCR_TDE] = {
+		.index		= MDCR_EL2,
+		.value		= MDCR_EL2_TDE,
+		.mask		= MDCR_EL2_TDE,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_MDCR_TDA] = {
+		.index		= MDCR_EL2,
+		.value		= MDCR_EL2_TDA,
+		.mask		= MDCR_EL2_TDA,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_MDCR_TDOSA] = {
+		.index		= MDCR_EL2,
+		.value		= MDCR_EL2_TDOSA,
+		.mask		= MDCR_EL2_TDOSA,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_MDCR_TDRA] = {
+		.index		= MDCR_EL2,
+		.value		= MDCR_EL2_TDRA,
+		.mask		= MDCR_EL2_TDRA,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_MDCR_E2PB] = {
+		.index		= MDCR_EL2,
+		.value		= 0,
+		.mask		= BIT(MDCR_EL2_E2PB_SHIFT),
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_MDCR_TPMS] = {
+		.index		= MDCR_EL2,
+		.value		= MDCR_EL2_TPMS,
+		.mask		= MDCR_EL2_TPMS,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_MDCR_TTRF] = {
+		.index		= MDCR_EL2,
+		.value		= MDCR_EL2_TTRF,
+		.mask		= MDCR_EL2_TTRF,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_MDCR_E2TB] = {
+		.index		= MDCR_EL2,
+		.value		= 0,
+		.mask		= BIT(MDCR_EL2_E2TB_SHIFT),
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_MDCR_TDCC] = {
+		.index		= MDCR_EL2,
+		.value		= MDCR_EL2_TDCC,
+		.mask		= MDCR_EL2_TDCC,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
 };
 
 #define MCB(id, ...)						\
@@ -277,6 +360,11 @@ static const enum cgt_group_id *coarse_control_combo[] = {
 	MCB(CGT_HCR_TPU_TICAB,		CGT_HCR_TPU, CGT_HCR_TICAB),
 	MCB(CGT_HCR_TPU_TOCU,		CGT_HCR_TPU, CGT_HCR_TOCU),
 	MCB(CGT_HCR_NV1_nNV2_ENSCXT,	CGT_HCR_NV1_nNV2, CGT_HCR_ENSCXT),
+	MCB(CGT_MDCR_TPM_TPMCR,		CGT_MDCR_TPM, CGT_MDCR_TPMCR),
+	MCB(CGT_MDCR_TDE_TDA,		CGT_MDCR_TDE, CGT_MDCR_TDA),
+	MCB(CGT_MDCR_TDE_TDOSA,		CGT_MDCR_TDE, CGT_MDCR_TDOSA),
+	MCB(CGT_MDCR_TDE_TDRA,		CGT_MDCR_TDE, CGT_MDCR_TDRA),
+	MCB(CGT_MDCR_TDCC_TDE_TDA,	CGT_MDCR_TDCC, CGT_MDCR_TDE, CGT_MDCR_TDA),
 };
 
 typedef enum trap_behaviour (*complex_condition_check)(struct kvm_vcpu *);
@@ -609,6 +697,186 @@ static const struct encoding_to_trap_config encoding_to_cgt[] __initconst = {
 	SR_TRAP(SYS_ERXPFGF_EL1,	CGT_HCR_nFIEN),
 	SR_TRAP(SYS_ERXPFGCTL_EL1,	CGT_HCR_nFIEN),
 	SR_TRAP(SYS_ERXPFGCDN_EL1,	CGT_HCR_nFIEN),
+	SR_TRAP(SYS_PMCR_EL0,		CGT_MDCR_TPM_TPMCR),
+	SR_TRAP(SYS_PMCNTENSET_EL0,	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMCNTENCLR_EL0,	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMOVSSET_EL0,	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMOVSCLR_EL0,	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMCEID0_EL0,	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMCEID1_EL0,	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMXEVTYPER_EL0,	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMSWINC_EL0,	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMSELR_EL0,		CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMXEVCNTR_EL0,	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMCCNTR_EL0,	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMUSERENR_EL0,	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMINTENSET_EL1,	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMINTENCLR_EL1,	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMMIR_EL1,		CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(0),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(1),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(2),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(3),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(4),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(5),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(6),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(7),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(8),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(9),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(10),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(11),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(12),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(13),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(14),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(15),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(16),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(17),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(18),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(19),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(20),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(21),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(22),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(23),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(24),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(25),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(26),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(27),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(28),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(29),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVCNTRn_EL0(30),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(0),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(1),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(2),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(3),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(4),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(5),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(6),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(7),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(8),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(9),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(10),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(11),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(12),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(13),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(14),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(15),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(16),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(17),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(18),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(19),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(20),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(21),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(22),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(23),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(24),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(25),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(26),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(27),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(28),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(29),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMEVTYPERn_EL0(30),	CGT_MDCR_TPM),
+	SR_TRAP(SYS_PMCCFILTR_EL0,	CGT_MDCR_TPM),
+	SR_TRAP(SYS_MDCCSR_EL0,		CGT_MDCR_TDCC_TDE_TDA),
+	SR_TRAP(SYS_MDCCINT_EL1,	CGT_MDCR_TDCC_TDE_TDA),
+	SR_TRAP(SYS_OSDTRRX_EL1,	CGT_MDCR_TDCC_TDE_TDA),
+	SR_TRAP(SYS_OSDTRTX_EL1,	CGT_MDCR_TDCC_TDE_TDA),
+	SR_TRAP(SYS_DBGDTR_EL0,		CGT_MDCR_TDCC_TDE_TDA),
+	/*
+	 * Also covers DBGDTRRX_EL0, which has the same encoding as
+	 * SYS_DBGDTRTX_EL0...
+	 */
+	SR_TRAP(SYS_DBGDTRTX_EL0,	CGT_MDCR_TDCC_TDE_TDA),
+	SR_TRAP(SYS_MDSCR_EL1,		CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_OSECCR_EL1,		CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBVRn_EL1(0),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBVRn_EL1(1),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBVRn_EL1(2),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBVRn_EL1(3),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBVRn_EL1(4),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBVRn_EL1(5),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBVRn_EL1(6),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBVRn_EL1(7),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBVRn_EL1(8),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBVRn_EL1(9),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBVRn_EL1(10),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBVRn_EL1(11),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBVRn_EL1(12),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBVRn_EL1(13),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBVRn_EL1(14),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBVRn_EL1(15),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBCRn_EL1(0),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBCRn_EL1(1),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBCRn_EL1(2),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBCRn_EL1(3),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBCRn_EL1(4),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBCRn_EL1(5),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBCRn_EL1(6),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBCRn_EL1(7),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBCRn_EL1(8),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBCRn_EL1(9),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBCRn_EL1(10),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBCRn_EL1(11),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBCRn_EL1(12),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBCRn_EL1(13),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBCRn_EL1(14),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGBCRn_EL1(15),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWVRn_EL1(0),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWVRn_EL1(1),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWVRn_EL1(2),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWVRn_EL1(3),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWVRn_EL1(4),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWVRn_EL1(5),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWVRn_EL1(6),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWVRn_EL1(7),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWVRn_EL1(8),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWVRn_EL1(9),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWVRn_EL1(10),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWVRn_EL1(11),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWVRn_EL1(12),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWVRn_EL1(13),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWVRn_EL1(14),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWVRn_EL1(15),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWCRn_EL1(0),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWCRn_EL1(1),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWCRn_EL1(2),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWCRn_EL1(3),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWCRn_EL1(4),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWCRn_EL1(5),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWCRn_EL1(6),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWCRn_EL1(7),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWCRn_EL1(8),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWCRn_EL1(9),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWCRn_EL1(10),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWCRn_EL1(11),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWCRn_EL1(12),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWCRn_EL1(13),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWCRn_EL1(14),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGCLAIMSET_EL1,	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGCLAIMCLR_EL1,	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGAUTHSTATUS_EL1,	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_OSLAR_EL1,		CGT_MDCR_TDE_TDOSA),
+	SR_TRAP(SYS_OSLSR_EL1,		CGT_MDCR_TDE_TDOSA),
+	SR_TRAP(SYS_OSDLR_EL1,		CGT_MDCR_TDE_TDOSA),
+	SR_TRAP(SYS_DBGPRCR_EL1,	CGT_MDCR_TDE_TDOSA),
+	SR_TRAP(SYS_MDRAR_EL1,		CGT_MDCR_TDE_TDRA),
+	SR_TRAP(SYS_PMBLIMITR_EL1,	CGT_MDCR_E2PB),
+	SR_TRAP(SYS_PMBPTR_EL1,		CGT_MDCR_E2PB),
+	SR_TRAP(SYS_PMBSR_EL1,		CGT_MDCR_E2PB),
+	SR_TRAP(SYS_PMSCR_EL1,		CGT_MDCR_TPMS),
+	SR_TRAP(SYS_PMSEVFR_EL1,	CGT_MDCR_TPMS),
+	SR_TRAP(SYS_PMSFCR_EL1,		CGT_MDCR_TPMS),
+	SR_TRAP(SYS_PMSICR_EL1,		CGT_MDCR_TPMS),
+	SR_TRAP(SYS_PMSIDR_EL1,		CGT_MDCR_TPMS),
+	SR_TRAP(SYS_PMSIRR_EL1,		CGT_MDCR_TPMS),
+	SR_TRAP(SYS_PMSLATFR_EL1,	CGT_MDCR_TPMS),
+	SR_TRAP(SYS_PMSNEVFR_EL1,	CGT_MDCR_TPMS),
+	SR_TRAP(SYS_TRFCR_EL1,		CGT_MDCR_TTRF),
+	SR_TRAP(SYS_TRBBASER_EL1,	CGT_MDCR_E2TB),
+	SR_TRAP(SYS_TRBLIMITR_EL1,	CGT_MDCR_E2TB),
+	SR_TRAP(SYS_TRBMAR_EL1, 	CGT_MDCR_E2TB),
+	SR_TRAP(SYS_TRBPTR_EL1, 	CGT_MDCR_E2TB),
+	SR_TRAP(SYS_TRBSR_EL1, 		CGT_MDCR_E2TB),
+	SR_TRAP(SYS_TRBTRG_EL1,		CGT_MDCR_E2TB),
 };
 
 static DEFINE_XARRAY(sr_forward_xa);

From e880bd3363237ed8abbe623d1b49d59d5f6fe0d1 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 15 Aug 2023 19:38:52 +0100
Subject: [PATCH 0493/1189] KVM: arm64: nv: Add trap forwarding for CNTHCTL_EL2

Describe the CNTHCTL_EL2 register, and associate it with all the sysregs
it allows to trap.

Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Jing Zhang <jingzhangos@google.com>
Link: https://lore.kernel.org/r/20230815183903.2735724-19-maz@kernel.org
---
 arch/arm64/kvm/emulate-nested.c | 50 ++++++++++++++++++++++++++++++++-
 1 file changed, 49 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index 241e44eeed6d..860910386b5b 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -100,9 +100,11 @@ enum cgt_group_id {
 
 	/*
 	 * Anything after this point requires a callback evaluating a
-	 * complex trap condition. Hopefully we'll never need this...
+	 * complex trap condition. Ugly stuff.
 	 */
 	__COMPLEX_CONDITIONS__,
+	CGT_CNTHCTL_EL1PCTEN = __COMPLEX_CONDITIONS__,
+	CGT_CNTHCTL_EL1PTEN,
 
 	/* Must be last */
 	__NR_CGT_GROUP_IDS__
@@ -369,10 +371,51 @@ static const enum cgt_group_id *coarse_control_combo[] = {
 
 typedef enum trap_behaviour (*complex_condition_check)(struct kvm_vcpu *);
 
+/*
+ * Warning, maximum confusion ahead.
+ *
+ * When E2H=0, CNTHCTL_EL2[1:0] are defined as EL1PCEN:EL1PCTEN
+ * When E2H=1, CNTHCTL_EL2[11:10] are defined as EL1PTEN:EL1PCTEN
+ *
+ * Note the single letter difference? Yet, the bits have the same
+ * function despite a different layout and a different name.
+ *
+ * We don't try to reconcile this mess. We just use the E2H=0 bits
+ * to generate something that is in the E2H=1 format, and live with
+ * it. You're welcome.
+ */
+static u64 get_sanitized_cnthctl(struct kvm_vcpu *vcpu)
+{
+	u64 val = __vcpu_sys_reg(vcpu, CNTHCTL_EL2);
+
+	if (!vcpu_el2_e2h_is_set(vcpu))
+		val = (val & (CNTHCTL_EL1PCEN | CNTHCTL_EL1PCTEN)) << 10;
+
+	return val & ((CNTHCTL_EL1PCEN | CNTHCTL_EL1PCTEN) << 10);
+}
+
+static enum trap_behaviour check_cnthctl_el1pcten(struct kvm_vcpu *vcpu)
+{
+	if (get_sanitized_cnthctl(vcpu) & (CNTHCTL_EL1PCTEN << 10))
+		return BEHAVE_HANDLE_LOCALLY;
+
+	return BEHAVE_FORWARD_ANY;
+}
+
+static enum trap_behaviour check_cnthctl_el1pten(struct kvm_vcpu *vcpu)
+{
+	if (get_sanitized_cnthctl(vcpu) & (CNTHCTL_EL1PCEN << 10))
+		return BEHAVE_HANDLE_LOCALLY;
+
+	return BEHAVE_FORWARD_ANY;
+}
+
 #define CCC(id, fn)				\
 	[id - __COMPLEX_CONDITIONS__] = fn
 
 static const complex_condition_check ccc[] = {
+	CCC(CGT_CNTHCTL_EL1PCTEN, check_cnthctl_el1pcten),
+	CCC(CGT_CNTHCTL_EL1PTEN, check_cnthctl_el1pten),
 };
 
 /*
@@ -877,6 +920,11 @@ static const struct encoding_to_trap_config encoding_to_cgt[] __initconst = {
 	SR_TRAP(SYS_TRBPTR_EL1, 	CGT_MDCR_E2TB),
 	SR_TRAP(SYS_TRBSR_EL1, 		CGT_MDCR_E2TB),
 	SR_TRAP(SYS_TRBTRG_EL1,		CGT_MDCR_E2TB),
+	SR_TRAP(SYS_CNTP_TVAL_EL0,	CGT_CNTHCTL_EL1PTEN),
+	SR_TRAP(SYS_CNTP_CVAL_EL0,	CGT_CNTHCTL_EL1PTEN),
+	SR_TRAP(SYS_CNTP_CTL_EL0,	CGT_CNTHCTL_EL1PTEN),
+	SR_TRAP(SYS_CNTPCT_EL0,		CGT_CNTHCTL_EL1PCTEN),
+	SR_TRAP(SYS_CNTPCTSS_EL0,	CGT_CNTHCTL_EL1PCTEN),
 };
 
 static DEFINE_XARRAY(sr_forward_xa);

From 15b4d82d69d7b0e5833b7a023dff3d7bbae5ccfc Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 15 Aug 2023 19:38:53 +0100
Subject: [PATCH 0494/1189] KVM: arm64: nv: Add fine grained trap forwarding
 infrastructure

Fine Grained Traps are fun. Not.

Implement the fine grained trap forwarding, reusing the Coarse Grained
Traps infrastructure previously implemented.

Each sysreg/instruction inserted in the xarray gets a FGT group
(vaguely equivalent to a register number), a bit number in that register,
and a polarity.

It is then pretty easy to check the FGT state at handling time, just
like we do for the coarse version (it is just faster).

Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Jing Zhang <jingzhangos@google.com>
Link: https://lore.kernel.org/r/20230815183903.2735724-20-maz@kernel.org
---
 arch/arm64/kvm/emulate-nested.c | 90 +++++++++++++++++++++++++++++++--
 1 file changed, 87 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index 860910386b5b..0da9d92ed921 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -423,16 +423,23 @@ static const complex_condition_check ccc[] = {
  * following layout for each trapped sysreg:
  *
  * [9:0]	enum cgt_group_id (10 bits)
- * [62:10]	Unused (53 bits)
+ * [13:10]	enum fgt_group_id (4 bits)
+ * [19:14]	bit number in the FGT register (6 bits)
+ * [20]		trap polarity (1 bit)
+ * [62:21]	Unused (42 bits)
  * [63]		RES0 - Must be zero, as lost on insertion in the xarray
  */
 #define TC_CGT_BITS	10
+#define TC_FGT_BITS	4
 
 union trap_config {
 	u64	val;
 	struct {
 		unsigned long	cgt:TC_CGT_BITS; /* Coarse Grained Trap id */
-		unsigned long	unused:53;	 /* Unused, should be zero */
+		unsigned long	fgt:TC_FGT_BITS; /* Fine Grained Trap id */
+		unsigned long	bit:6;		 /* Bit number */
+		unsigned long	pol:1;		 /* Polarity */
+		unsigned long	unused:42;	 /* Unused, should be zero */
 		unsigned long	mbz:1;		 /* Must Be Zero */
 	};
 };
@@ -929,6 +936,28 @@ static const struct encoding_to_trap_config encoding_to_cgt[] __initconst = {
 
 static DEFINE_XARRAY(sr_forward_xa);
 
+enum fgt_group_id {
+	__NO_FGT_GROUP__,
+
+	/* Must be last */
+	__NR_FGT_GROUP_IDS__
+};
+
+#define SR_FGT(sr, g, b, p)					\
+	{							\
+		.encoding	= sr,				\
+		.end		= sr,				\
+		.tc		= {				\
+			.fgt = g ## _GROUP,			\
+			.bit = g ## _EL2_ ## b ## _SHIFT,	\
+			.pol = p,				\
+		},						\
+		.line = __LINE__,				\
+	}
+
+static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
+};
+
 static union trap_config get_trap_config(u32 sysreg)
 {
 	return (union trap_config) {
@@ -957,6 +986,7 @@ int __init populate_nv_trap_config(void)
 
 	BUILD_BUG_ON(sizeof(union trap_config) != sizeof(void *));
 	BUILD_BUG_ON(__NR_CGT_GROUP_IDS__ > BIT(TC_CGT_BITS));
+	BUILD_BUG_ON(__NR_FGT_GROUP_IDS__ > BIT(TC_FGT_BITS));
 
 	for (int i = 0; i < ARRAY_SIZE(encoding_to_cgt); i++) {
 		const struct encoding_to_trap_config *cgt = &encoding_to_cgt[i];
@@ -990,6 +1020,34 @@ int __init populate_nv_trap_config(void)
 	kvm_info("nv: %ld coarse grained trap handlers\n",
 		 ARRAY_SIZE(encoding_to_cgt));
 
+	if (!cpus_have_final_cap(ARM64_HAS_FGT))
+		goto check_mcb;
+
+	for (int i = 0; i < ARRAY_SIZE(encoding_to_fgt); i++) {
+		const struct encoding_to_trap_config *fgt = &encoding_to_fgt[i];
+		union trap_config tc;
+
+		if (fgt->tc.fgt >= __NR_FGT_GROUP_IDS__) {
+			ret = -EINVAL;
+			print_nv_trap_error(fgt, "Invalid FGT", ret);
+		}
+
+		tc = get_trap_config(fgt->encoding);
+
+		if (tc.fgt) {
+			ret = -EINVAL;
+			print_nv_trap_error(fgt, "Duplicate FGT", ret);
+		}
+
+		tc.val |= fgt->tc.val;
+		xa_store(&sr_forward_xa, fgt->encoding,
+			 xa_mk_value(tc.val), GFP_KERNEL);
+	}
+
+	kvm_info("nv: %ld fine grained trap handlers\n",
+		 ARRAY_SIZE(encoding_to_fgt));
+
+check_mcb:
 	for (int id = __MULTIPLE_CONTROL_BITS__; id < __COMPLEX_CONDITIONS__; id++) {
 		const enum cgt_group_id *cgids;
 
@@ -1056,13 +1114,26 @@ static enum trap_behaviour compute_trap_behaviour(struct kvm_vcpu *vcpu,
 	return __compute_trap_behaviour(vcpu, tc.cgt, b);
 }
 
+static bool check_fgt_bit(u64 val, const union trap_config tc)
+{
+	return ((val >> tc.bit) & 1) == tc.pol;
+}
+
+#define sanitised_sys_reg(vcpu, reg)			\
+	({						\
+		u64 __val;				\
+		__val = __vcpu_sys_reg(vcpu, reg);	\
+		__val &= ~__ ## reg ## _RES0;		\
+		(__val);				\
+	})
+
 bool __check_nv_sr_forward(struct kvm_vcpu *vcpu)
 {
 	union trap_config tc;
 	enum trap_behaviour b;
 	bool is_read;
 	u32 sysreg;
-	u64 esr;
+	u64 esr, val;
 
 	if (!vcpu_has_nv(vcpu) || is_hyp_ctxt(vcpu))
 		return false;
@@ -1085,6 +1156,19 @@ bool __check_nv_sr_forward(struct kvm_vcpu *vcpu)
 	if (!tc.val)
 		return false;
 
+	switch ((enum fgt_group_id)tc.fgt) {
+	case __NO_FGT_GROUP__:
+		break;
+
+	case __NR_FGT_GROUP_IDS__:
+		/* Something is really wrong, bail out */
+		WARN_ONCE(1, "__NR_FGT_GROUP_IDS__");
+		return false;
+	}
+
+	if (tc.fgt != __NO_FGT_GROUP__ && check_fgt_bit(val, tc))
+		goto inject;
+
 	b = compute_trap_behaviour(vcpu, tc);
 
 	if (((b & BEHAVE_FORWARD_READ) && is_read) ||

From 5a24ea7869857251a83da1512209f76003bc09db Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 15 Aug 2023 19:38:54 +0100
Subject: [PATCH 0495/1189] KVM: arm64: nv: Add trap forwarding for HFGxTR_EL2

Implement the trap forwarding for traps described by HFGxTR_EL2,
reusing the Fine Grained Traps infrastructure previously implemented.

Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Jing Zhang <jingzhangos@google.com>
Link: https://lore.kernel.org/r/20230815183903.2735724-21-maz@kernel.org
---
 arch/arm64/kvm/emulate-nested.c | 71 +++++++++++++++++++++++++++++++++
 1 file changed, 71 insertions(+)

diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index 0da9d92ed921..0e34797515b6 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -938,6 +938,7 @@ static DEFINE_XARRAY(sr_forward_xa);
 
 enum fgt_group_id {
 	__NO_FGT_GROUP__,
+	HFGxTR_GROUP,
 
 	/* Must be last */
 	__NR_FGT_GROUP_IDS__
@@ -956,6 +957,69 @@ enum fgt_group_id {
 	}
 
 static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
+	/* HFGRTR_EL2, HFGWTR_EL2 */
+	SR_FGT(SYS_TPIDR2_EL0,		HFGxTR, nTPIDR2_EL0, 0),
+	SR_FGT(SYS_SMPRI_EL1,		HFGxTR, nSMPRI_EL1, 0),
+	SR_FGT(SYS_ACCDATA_EL1,		HFGxTR, nACCDATA_EL1, 0),
+	SR_FGT(SYS_ERXADDR_EL1,		HFGxTR, ERXADDR_EL1, 1),
+	SR_FGT(SYS_ERXPFGCDN_EL1,	HFGxTR, ERXPFGCDN_EL1, 1),
+	SR_FGT(SYS_ERXPFGCTL_EL1,	HFGxTR, ERXPFGCTL_EL1, 1),
+	SR_FGT(SYS_ERXPFGF_EL1,		HFGxTR, ERXPFGF_EL1, 1),
+	SR_FGT(SYS_ERXMISC0_EL1,	HFGxTR, ERXMISCn_EL1, 1),
+	SR_FGT(SYS_ERXMISC1_EL1,	HFGxTR, ERXMISCn_EL1, 1),
+	SR_FGT(SYS_ERXMISC2_EL1,	HFGxTR, ERXMISCn_EL1, 1),
+	SR_FGT(SYS_ERXMISC3_EL1,	HFGxTR, ERXMISCn_EL1, 1),
+	SR_FGT(SYS_ERXSTATUS_EL1,	HFGxTR, ERXSTATUS_EL1, 1),
+	SR_FGT(SYS_ERXCTLR_EL1,		HFGxTR, ERXCTLR_EL1, 1),
+	SR_FGT(SYS_ERXFR_EL1,		HFGxTR, ERXFR_EL1, 1),
+	SR_FGT(SYS_ERRSELR_EL1,		HFGxTR, ERRSELR_EL1, 1),
+	SR_FGT(SYS_ERRIDR_EL1,		HFGxTR, ERRIDR_EL1, 1),
+	SR_FGT(SYS_ICC_IGRPEN0_EL1,	HFGxTR, ICC_IGRPENn_EL1, 1),
+	SR_FGT(SYS_ICC_IGRPEN1_EL1,	HFGxTR, ICC_IGRPENn_EL1, 1),
+	SR_FGT(SYS_VBAR_EL1,		HFGxTR, VBAR_EL1, 1),
+	SR_FGT(SYS_TTBR1_EL1,		HFGxTR, TTBR1_EL1, 1),
+	SR_FGT(SYS_TTBR0_EL1,		HFGxTR, TTBR0_EL1, 1),
+	SR_FGT(SYS_TPIDR_EL0,		HFGxTR, TPIDR_EL0, 1),
+	SR_FGT(SYS_TPIDRRO_EL0,		HFGxTR, TPIDRRO_EL0, 1),
+	SR_FGT(SYS_TPIDR_EL1,		HFGxTR, TPIDR_EL1, 1),
+	SR_FGT(SYS_TCR_EL1,		HFGxTR, TCR_EL1, 1),
+	SR_FGT(SYS_SCXTNUM_EL0,		HFGxTR, SCXTNUM_EL0, 1),
+	SR_FGT(SYS_SCXTNUM_EL1, 	HFGxTR, SCXTNUM_EL1, 1),
+	SR_FGT(SYS_SCTLR_EL1, 		HFGxTR, SCTLR_EL1, 1),
+	SR_FGT(SYS_REVIDR_EL1, 		HFGxTR, REVIDR_EL1, 1),
+	SR_FGT(SYS_PAR_EL1, 		HFGxTR, PAR_EL1, 1),
+	SR_FGT(SYS_MPIDR_EL1, 		HFGxTR, MPIDR_EL1, 1),
+	SR_FGT(SYS_MIDR_EL1, 		HFGxTR, MIDR_EL1, 1),
+	SR_FGT(SYS_MAIR_EL1, 		HFGxTR, MAIR_EL1, 1),
+	SR_FGT(SYS_LORSA_EL1, 		HFGxTR, LORSA_EL1, 1),
+	SR_FGT(SYS_LORN_EL1, 		HFGxTR, LORN_EL1, 1),
+	SR_FGT(SYS_LORID_EL1, 		HFGxTR, LORID_EL1, 1),
+	SR_FGT(SYS_LOREA_EL1, 		HFGxTR, LOREA_EL1, 1),
+	SR_FGT(SYS_LORC_EL1, 		HFGxTR, LORC_EL1, 1),
+	SR_FGT(SYS_ISR_EL1, 		HFGxTR, ISR_EL1, 1),
+	SR_FGT(SYS_FAR_EL1, 		HFGxTR, FAR_EL1, 1),
+	SR_FGT(SYS_ESR_EL1, 		HFGxTR, ESR_EL1, 1),
+	SR_FGT(SYS_DCZID_EL0, 		HFGxTR, DCZID_EL0, 1),
+	SR_FGT(SYS_CTR_EL0, 		HFGxTR, CTR_EL0, 1),
+	SR_FGT(SYS_CSSELR_EL1, 		HFGxTR, CSSELR_EL1, 1),
+	SR_FGT(SYS_CPACR_EL1, 		HFGxTR, CPACR_EL1, 1),
+	SR_FGT(SYS_CONTEXTIDR_EL1, 	HFGxTR, CONTEXTIDR_EL1, 1),
+	SR_FGT(SYS_CLIDR_EL1, 		HFGxTR, CLIDR_EL1, 1),
+	SR_FGT(SYS_CCSIDR_EL1, 		HFGxTR, CCSIDR_EL1, 1),
+	SR_FGT(SYS_APIBKEYLO_EL1, 	HFGxTR, APIBKey, 1),
+	SR_FGT(SYS_APIBKEYHI_EL1, 	HFGxTR, APIBKey, 1),
+	SR_FGT(SYS_APIAKEYLO_EL1, 	HFGxTR, APIAKey, 1),
+	SR_FGT(SYS_APIAKEYHI_EL1, 	HFGxTR, APIAKey, 1),
+	SR_FGT(SYS_APGAKEYLO_EL1, 	HFGxTR, APGAKey, 1),
+	SR_FGT(SYS_APGAKEYHI_EL1, 	HFGxTR, APGAKey, 1),
+	SR_FGT(SYS_APDBKEYLO_EL1, 	HFGxTR, APDBKey, 1),
+	SR_FGT(SYS_APDBKEYHI_EL1, 	HFGxTR, APDBKey, 1),
+	SR_FGT(SYS_APDAKEYLO_EL1, 	HFGxTR, APDAKey, 1),
+	SR_FGT(SYS_APDAKEYHI_EL1, 	HFGxTR, APDAKey, 1),
+	SR_FGT(SYS_AMAIR_EL1, 		HFGxTR, AMAIR_EL1, 1),
+	SR_FGT(SYS_AIDR_EL1, 		HFGxTR, AIDR_EL1, 1),
+	SR_FGT(SYS_AFSR1_EL1, 		HFGxTR, AFSR1_EL1, 1),
+	SR_FGT(SYS_AFSR0_EL1, 		HFGxTR, AFSR0_EL1, 1),
 };
 
 static union trap_config get_trap_config(u32 sysreg)
@@ -1160,6 +1224,13 @@ bool __check_nv_sr_forward(struct kvm_vcpu *vcpu)
 	case __NO_FGT_GROUP__:
 		break;
 
+	case HFGxTR_GROUP:
+		if (is_read)
+			val = sanitised_sys_reg(vcpu, HFGRTR_EL2);
+		else
+			val = sanitised_sys_reg(vcpu, HFGWTR_EL2);
+		break;
+
 	case __NR_FGT_GROUP_IDS__:
 		/* Something is really wrong, bail out */
 		WARN_ONCE(1, "__NR_FGT_GROUP_IDS__");

From 039f9f12de5fc761d2b32fa072071533aa8cbb3b Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 15 Aug 2023 19:38:55 +0100
Subject: [PATCH 0496/1189] KVM: arm64: nv: Add trap forwarding for HFGITR_EL2

Similarly, implement the trap forwarding for instructions affected
by HFGITR_EL2.

Note that the TLBI*nXS instructions should be affected by HCRX_EL2,
which will be dealt with down the line. Also, ERET* and SVC traps
are handled separately.

Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Jing Zhang <jingzhangos@google.com>
Link: https://lore.kernel.org/r/20230815183903.2735724-22-maz@kernel.org
---
 arch/arm64/include/asm/kvm_arm.h |   4 ++
 arch/arm64/kvm/emulate-nested.c  | 109 +++++++++++++++++++++++++++++++
 2 files changed, 113 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 85908aa18908..809bc86acefd 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -354,6 +354,10 @@
 #define __HFGWTR_EL2_MASK	GENMASK(49, 0)
 #define __HFGWTR_EL2_nMASK	(GENMASK(55, 54) | BIT(50))
 
+#define __HFGITR_EL2_RES0	GENMASK(63, 57)
+#define __HFGITR_EL2_MASK	GENMASK(54, 0)
+#define __HFGITR_EL2_nMASK	GENMASK(56, 55)
+
 /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
 #define HPFAR_MASK	(~UL(0xf))
 /*
diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index 0e34797515b6..a1a7792db412 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -939,6 +939,7 @@ static DEFINE_XARRAY(sr_forward_xa);
 enum fgt_group_id {
 	__NO_FGT_GROUP__,
 	HFGxTR_GROUP,
+	HFGITR_GROUP,
 
 	/* Must be last */
 	__NR_FGT_GROUP_IDS__
@@ -1020,6 +1021,110 @@ static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
 	SR_FGT(SYS_AIDR_EL1, 		HFGxTR, AIDR_EL1, 1),
 	SR_FGT(SYS_AFSR1_EL1, 		HFGxTR, AFSR1_EL1, 1),
 	SR_FGT(SYS_AFSR0_EL1, 		HFGxTR, AFSR0_EL1, 1),
+	/* HFGITR_EL2 */
+	SR_FGT(OP_BRB_IALL, 		HFGITR, nBRBIALL, 0),
+	SR_FGT(OP_BRB_INJ, 		HFGITR, nBRBINJ, 0),
+	SR_FGT(SYS_DC_CVAC, 		HFGITR, DCCVAC, 1),
+	SR_FGT(SYS_DC_CGVAC, 		HFGITR, DCCVAC, 1),
+	SR_FGT(SYS_DC_CGDVAC, 		HFGITR, DCCVAC, 1),
+	SR_FGT(OP_CPP_RCTX, 		HFGITR, CPPRCTX, 1),
+	SR_FGT(OP_DVP_RCTX, 		HFGITR, DVPRCTX, 1),
+	SR_FGT(OP_CFP_RCTX, 		HFGITR, CFPRCTX, 1),
+	SR_FGT(OP_TLBI_VAALE1, 		HFGITR, TLBIVAALE1, 1),
+	SR_FGT(OP_TLBI_VALE1, 		HFGITR, TLBIVALE1, 1),
+	SR_FGT(OP_TLBI_VAAE1, 		HFGITR, TLBIVAAE1, 1),
+	SR_FGT(OP_TLBI_ASIDE1, 		HFGITR, TLBIASIDE1, 1),
+	SR_FGT(OP_TLBI_VAE1, 		HFGITR, TLBIVAE1, 1),
+	SR_FGT(OP_TLBI_VMALLE1, 	HFGITR, TLBIVMALLE1, 1),
+	SR_FGT(OP_TLBI_RVAALE1, 	HFGITR, TLBIRVAALE1, 1),
+	SR_FGT(OP_TLBI_RVALE1, 		HFGITR, TLBIRVALE1, 1),
+	SR_FGT(OP_TLBI_RVAAE1, 		HFGITR, TLBIRVAAE1, 1),
+	SR_FGT(OP_TLBI_RVAE1, 		HFGITR, TLBIRVAE1, 1),
+	SR_FGT(OP_TLBI_RVAALE1IS, 	HFGITR, TLBIRVAALE1IS, 1),
+	SR_FGT(OP_TLBI_RVALE1IS, 	HFGITR, TLBIRVALE1IS, 1),
+	SR_FGT(OP_TLBI_RVAAE1IS, 	HFGITR, TLBIRVAAE1IS, 1),
+	SR_FGT(OP_TLBI_RVAE1IS, 	HFGITR, TLBIRVAE1IS, 1),
+	SR_FGT(OP_TLBI_VAALE1IS, 	HFGITR, TLBIVAALE1IS, 1),
+	SR_FGT(OP_TLBI_VALE1IS, 	HFGITR, TLBIVALE1IS, 1),
+	SR_FGT(OP_TLBI_VAAE1IS, 	HFGITR, TLBIVAAE1IS, 1),
+	SR_FGT(OP_TLBI_ASIDE1IS, 	HFGITR, TLBIASIDE1IS, 1),
+	SR_FGT(OP_TLBI_VAE1IS, 		HFGITR, TLBIVAE1IS, 1),
+	SR_FGT(OP_TLBI_VMALLE1IS, 	HFGITR, TLBIVMALLE1IS, 1),
+	SR_FGT(OP_TLBI_RVAALE1OS, 	HFGITR, TLBIRVAALE1OS, 1),
+	SR_FGT(OP_TLBI_RVALE1OS, 	HFGITR, TLBIRVALE1OS, 1),
+	SR_FGT(OP_TLBI_RVAAE1OS, 	HFGITR, TLBIRVAAE1OS, 1),
+	SR_FGT(OP_TLBI_RVAE1OS, 	HFGITR, TLBIRVAE1OS, 1),
+	SR_FGT(OP_TLBI_VAALE1OS, 	HFGITR, TLBIVAALE1OS, 1),
+	SR_FGT(OP_TLBI_VALE1OS, 	HFGITR, TLBIVALE1OS, 1),
+	SR_FGT(OP_TLBI_VAAE1OS, 	HFGITR, TLBIVAAE1OS, 1),
+	SR_FGT(OP_TLBI_ASIDE1OS, 	HFGITR, TLBIASIDE1OS, 1),
+	SR_FGT(OP_TLBI_VAE1OS, 		HFGITR, TLBIVAE1OS, 1),
+	SR_FGT(OP_TLBI_VMALLE1OS, 	HFGITR, TLBIVMALLE1OS, 1),
+	/* FIXME: nXS variants must be checked against HCRX_EL2.FGTnXS */
+	SR_FGT(OP_TLBI_VAALE1NXS, 	HFGITR, TLBIVAALE1, 1),
+	SR_FGT(OP_TLBI_VALE1NXS, 	HFGITR, TLBIVALE1, 1),
+	SR_FGT(OP_TLBI_VAAE1NXS, 	HFGITR, TLBIVAAE1, 1),
+	SR_FGT(OP_TLBI_ASIDE1NXS, 	HFGITR, TLBIASIDE1, 1),
+	SR_FGT(OP_TLBI_VAE1NXS, 	HFGITR, TLBIVAE1, 1),
+	SR_FGT(OP_TLBI_VMALLE1NXS, 	HFGITR, TLBIVMALLE1, 1),
+	SR_FGT(OP_TLBI_RVAALE1NXS, 	HFGITR, TLBIRVAALE1, 1),
+	SR_FGT(OP_TLBI_RVALE1NXS, 	HFGITR, TLBIRVALE1, 1),
+	SR_FGT(OP_TLBI_RVAAE1NXS, 	HFGITR, TLBIRVAAE1, 1),
+	SR_FGT(OP_TLBI_RVAE1NXS, 	HFGITR, TLBIRVAE1, 1),
+	SR_FGT(OP_TLBI_RVAALE1ISNXS, 	HFGITR, TLBIRVAALE1IS, 1),
+	SR_FGT(OP_TLBI_RVALE1ISNXS, 	HFGITR, TLBIRVALE1IS, 1),
+	SR_FGT(OP_TLBI_RVAAE1ISNXS, 	HFGITR, TLBIRVAAE1IS, 1),
+	SR_FGT(OP_TLBI_RVAE1ISNXS, 	HFGITR, TLBIRVAE1IS, 1),
+	SR_FGT(OP_TLBI_VAALE1ISNXS, 	HFGITR, TLBIVAALE1IS, 1),
+	SR_FGT(OP_TLBI_VALE1ISNXS, 	HFGITR, TLBIVALE1IS, 1),
+	SR_FGT(OP_TLBI_VAAE1ISNXS, 	HFGITR, TLBIVAAE1IS, 1),
+	SR_FGT(OP_TLBI_ASIDE1ISNXS, 	HFGITR, TLBIASIDE1IS, 1),
+	SR_FGT(OP_TLBI_VAE1ISNXS, 	HFGITR, TLBIVAE1IS, 1),
+	SR_FGT(OP_TLBI_VMALLE1ISNXS, 	HFGITR, TLBIVMALLE1IS, 1),
+	SR_FGT(OP_TLBI_RVAALE1OSNXS, 	HFGITR, TLBIRVAALE1OS, 1),
+	SR_FGT(OP_TLBI_RVALE1OSNXS, 	HFGITR, TLBIRVALE1OS, 1),
+	SR_FGT(OP_TLBI_RVAAE1OSNXS, 	HFGITR, TLBIRVAAE1OS, 1),
+	SR_FGT(OP_TLBI_RVAE1OSNXS, 	HFGITR, TLBIRVAE1OS, 1),
+	SR_FGT(OP_TLBI_VAALE1OSNXS, 	HFGITR, TLBIVAALE1OS, 1),
+	SR_FGT(OP_TLBI_VALE1OSNXS, 	HFGITR, TLBIVALE1OS, 1),
+	SR_FGT(OP_TLBI_VAAE1OSNXS, 	HFGITR, TLBIVAAE1OS, 1),
+	SR_FGT(OP_TLBI_ASIDE1OSNXS, 	HFGITR, TLBIASIDE1OS, 1),
+	SR_FGT(OP_TLBI_VAE1OSNXS, 	HFGITR, TLBIVAE1OS, 1),
+	SR_FGT(OP_TLBI_VMALLE1OSNXS, 	HFGITR, TLBIVMALLE1OS, 1),
+	SR_FGT(OP_AT_S1E1WP, 		HFGITR, ATS1E1WP, 1),
+	SR_FGT(OP_AT_S1E1RP, 		HFGITR, ATS1E1RP, 1),
+	SR_FGT(OP_AT_S1E0W, 		HFGITR, ATS1E0W, 1),
+	SR_FGT(OP_AT_S1E0R, 		HFGITR, ATS1E0R, 1),
+	SR_FGT(OP_AT_S1E1W, 		HFGITR, ATS1E1W, 1),
+	SR_FGT(OP_AT_S1E1R, 		HFGITR, ATS1E1R, 1),
+	SR_FGT(SYS_DC_ZVA, 		HFGITR, DCZVA, 1),
+	SR_FGT(SYS_DC_GVA, 		HFGITR, DCZVA, 1),
+	SR_FGT(SYS_DC_GZVA, 		HFGITR, DCZVA, 1),
+	SR_FGT(SYS_DC_CIVAC, 		HFGITR, DCCIVAC, 1),
+	SR_FGT(SYS_DC_CIGVAC, 		HFGITR, DCCIVAC, 1),
+	SR_FGT(SYS_DC_CIGDVAC, 		HFGITR, DCCIVAC, 1),
+	SR_FGT(SYS_DC_CVADP, 		HFGITR, DCCVADP, 1),
+	SR_FGT(SYS_DC_CGVADP, 		HFGITR, DCCVADP, 1),
+	SR_FGT(SYS_DC_CGDVADP, 		HFGITR, DCCVADP, 1),
+	SR_FGT(SYS_DC_CVAP, 		HFGITR, DCCVAP, 1),
+	SR_FGT(SYS_DC_CGVAP, 		HFGITR, DCCVAP, 1),
+	SR_FGT(SYS_DC_CGDVAP, 		HFGITR, DCCVAP, 1),
+	SR_FGT(SYS_DC_CVAU, 		HFGITR, DCCVAU, 1),
+	SR_FGT(SYS_DC_CISW, 		HFGITR, DCCISW, 1),
+	SR_FGT(SYS_DC_CIGSW, 		HFGITR, DCCISW, 1),
+	SR_FGT(SYS_DC_CIGDSW, 		HFGITR, DCCISW, 1),
+	SR_FGT(SYS_DC_CSW, 		HFGITR, DCCSW, 1),
+	SR_FGT(SYS_DC_CGSW, 		HFGITR, DCCSW, 1),
+	SR_FGT(SYS_DC_CGDSW, 		HFGITR, DCCSW, 1),
+	SR_FGT(SYS_DC_ISW, 		HFGITR, DCISW, 1),
+	SR_FGT(SYS_DC_IGSW, 		HFGITR, DCISW, 1),
+	SR_FGT(SYS_DC_IGDSW, 		HFGITR, DCISW, 1),
+	SR_FGT(SYS_DC_IVAC, 		HFGITR, DCIVAC, 1),
+	SR_FGT(SYS_DC_IGVAC, 		HFGITR, DCIVAC, 1),
+	SR_FGT(SYS_DC_IGDVAC, 		HFGITR, DCIVAC, 1),
+	SR_FGT(SYS_IC_IVAU, 		HFGITR, ICIVAU, 1),
+	SR_FGT(SYS_IC_IALLU, 		HFGITR, ICIALLU, 1),
+	SR_FGT(SYS_IC_IALLUIS, 		HFGITR, ICIALLUIS, 1),
 };
 
 static union trap_config get_trap_config(u32 sysreg)
@@ -1231,6 +1336,10 @@ bool __check_nv_sr_forward(struct kvm_vcpu *vcpu)
 			val = sanitised_sys_reg(vcpu, HFGWTR_EL2);
 		break;
 
+	case HFGITR_GROUP:
+		val = sanitised_sys_reg(vcpu, HFGITR_EL2);
+		break;
+
 	case __NR_FGT_GROUP_IDS__:
 		/* Something is really wrong, bail out */
 		WARN_ONCE(1, "__NR_FGT_GROUP_IDS__");

From d0be0b2ede13247c53745d50e2a5993f2b27c802 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 15 Aug 2023 19:38:56 +0100
Subject: [PATCH 0497/1189] KVM: arm64: nv: Add trap forwarding for HDFGxTR_EL2

... and finally, the Debug version of FGT, with its *enormous*
list of trapped registers.

Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Jing Zhang <jingzhangos@google.com>
Link: https://lore.kernel.org/r/20230815183903.2735724-23-maz@kernel.org
---
 arch/arm64/include/asm/kvm_arm.h |  11 +
 arch/arm64/kvm/emulate-nested.c  | 474 +++++++++++++++++++++++++++++++
 2 files changed, 485 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 809bc86acefd..d229f238c3b6 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -358,6 +358,17 @@
 #define __HFGITR_EL2_MASK	GENMASK(54, 0)
 #define __HFGITR_EL2_nMASK	GENMASK(56, 55)
 
+#define __HDFGRTR_EL2_RES0	(BIT(49) | BIT(42) | GENMASK(39, 38) |	\
+				 GENMASK(21, 20) | BIT(8))
+#define __HDFGRTR_EL2_MASK	~__HDFGRTR_EL2_nMASK
+#define __HDFGRTR_EL2_nMASK	GENMASK(62, 59)
+
+#define __HDFGWTR_EL2_RES0	(BIT(63) | GENMASK(59, 58) | BIT(51) | BIT(47) | \
+				 BIT(43) | GENMASK(40, 38) | BIT(34) | BIT(30) | \
+				 BIT(22) | BIT(9) | BIT(6))
+#define __HDFGWTR_EL2_MASK	~__HDFGWTR_EL2_nMASK
+#define __HDFGWTR_EL2_nMASK	GENMASK(62, 60)
+
 /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
 #define HPFAR_MASK	(~UL(0xf))
 /*
diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index a1a7792db412..c9662f9a345e 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -939,6 +939,8 @@ static DEFINE_XARRAY(sr_forward_xa);
 enum fgt_group_id {
 	__NO_FGT_GROUP__,
 	HFGxTR_GROUP,
+	HDFGRTR_GROUP,
+	HDFGWTR_GROUP,
 	HFGITR_GROUP,
 
 	/* Must be last */
@@ -1125,6 +1127,470 @@ static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
 	SR_FGT(SYS_IC_IVAU, 		HFGITR, ICIVAU, 1),
 	SR_FGT(SYS_IC_IALLU, 		HFGITR, ICIALLU, 1),
 	SR_FGT(SYS_IC_IALLUIS, 		HFGITR, ICIALLUIS, 1),
+	/* HDFGRTR_EL2 */
+	SR_FGT(SYS_PMBIDR_EL1, 		HDFGRTR, PMBIDR_EL1, 1),
+	SR_FGT(SYS_PMSNEVFR_EL1, 	HDFGRTR, nPMSNEVFR_EL1, 0),
+	SR_FGT(SYS_BRBINF_EL1(0), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(1), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(2), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(3), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(4), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(5), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(6), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(7), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(8), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(9), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(10), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(11), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(12), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(13), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(14), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(15), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(16), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(17), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(18), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(19), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(20), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(21), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(22), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(23), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(24), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(25), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(26), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(27), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(28), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(29), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(30), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINF_EL1(31), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBINFINJ_EL1, 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(0), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(1), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(2), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(3), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(4), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(5), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(6), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(7), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(8), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(9), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(10), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(11), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(12), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(13), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(14), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(15), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(16), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(17), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(18), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(19), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(20), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(21), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(22), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(23), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(24), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(25), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(26), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(27), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(28), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(29), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(30), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRC_EL1(31), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBSRCINJ_EL1, 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(0), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(1), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(2), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(3), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(4), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(5), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(6), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(7), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(8), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(9), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(10), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(11), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(12), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(13), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(14), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(15), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(16), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(17), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(18), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(19), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(20), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(21), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(22), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(23), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(24), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(25), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(26), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(27), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(28), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(29), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(30), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGT_EL1(31), 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTGTINJ_EL1, 	HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBTS_EL1, 		HDFGRTR, nBRBDATA, 0),
+	SR_FGT(SYS_BRBCR_EL1, 		HDFGRTR, nBRBCTL, 0),
+	SR_FGT(SYS_BRBFCR_EL1, 		HDFGRTR, nBRBCTL, 0),
+	SR_FGT(SYS_BRBIDR0_EL1, 	HDFGRTR, nBRBIDR, 0),
+	SR_FGT(SYS_PMCEID0_EL0, 	HDFGRTR, PMCEIDn_EL0, 1),
+	SR_FGT(SYS_PMCEID1_EL0, 	HDFGRTR, PMCEIDn_EL0, 1),
+	SR_FGT(SYS_PMUSERENR_EL0, 	HDFGRTR, PMUSERENR_EL0, 1),
+	SR_FGT(SYS_TRBTRG_EL1, 		HDFGRTR, TRBTRG_EL1, 1),
+	SR_FGT(SYS_TRBSR_EL1, 		HDFGRTR, TRBSR_EL1, 1),
+	SR_FGT(SYS_TRBPTR_EL1, 		HDFGRTR, TRBPTR_EL1, 1),
+	SR_FGT(SYS_TRBMAR_EL1, 		HDFGRTR, TRBMAR_EL1, 1),
+	SR_FGT(SYS_TRBLIMITR_EL1, 	HDFGRTR, TRBLIMITR_EL1, 1),
+	SR_FGT(SYS_TRBIDR_EL1, 		HDFGRTR, TRBIDR_EL1, 1),
+	SR_FGT(SYS_TRBBASER_EL1, 	HDFGRTR, TRBBASER_EL1, 1),
+	SR_FGT(SYS_TRCVICTLR, 		HDFGRTR, TRCVICTLR, 1),
+	SR_FGT(SYS_TRCSTATR, 		HDFGRTR, TRCSTATR, 1),
+	SR_FGT(SYS_TRCSSCSR(0), 	HDFGRTR, TRCSSCSRn, 1),
+	SR_FGT(SYS_TRCSSCSR(1), 	HDFGRTR, TRCSSCSRn, 1),
+	SR_FGT(SYS_TRCSSCSR(2), 	HDFGRTR, TRCSSCSRn, 1),
+	SR_FGT(SYS_TRCSSCSR(3), 	HDFGRTR, TRCSSCSRn, 1),
+	SR_FGT(SYS_TRCSSCSR(4), 	HDFGRTR, TRCSSCSRn, 1),
+	SR_FGT(SYS_TRCSSCSR(5), 	HDFGRTR, TRCSSCSRn, 1),
+	SR_FGT(SYS_TRCSSCSR(6), 	HDFGRTR, TRCSSCSRn, 1),
+	SR_FGT(SYS_TRCSSCSR(7), 	HDFGRTR, TRCSSCSRn, 1),
+	SR_FGT(SYS_TRCSEQSTR, 		HDFGRTR, TRCSEQSTR, 1),
+	SR_FGT(SYS_TRCPRGCTLR, 		HDFGRTR, TRCPRGCTLR, 1),
+	SR_FGT(SYS_TRCOSLSR, 		HDFGRTR, TRCOSLSR, 1),
+	SR_FGT(SYS_TRCIMSPEC(0), 	HDFGRTR, TRCIMSPECn, 1),
+	SR_FGT(SYS_TRCIMSPEC(1), 	HDFGRTR, TRCIMSPECn, 1),
+	SR_FGT(SYS_TRCIMSPEC(2), 	HDFGRTR, TRCIMSPECn, 1),
+	SR_FGT(SYS_TRCIMSPEC(3), 	HDFGRTR, TRCIMSPECn, 1),
+	SR_FGT(SYS_TRCIMSPEC(4), 	HDFGRTR, TRCIMSPECn, 1),
+	SR_FGT(SYS_TRCIMSPEC(5), 	HDFGRTR, TRCIMSPECn, 1),
+	SR_FGT(SYS_TRCIMSPEC(6), 	HDFGRTR, TRCIMSPECn, 1),
+	SR_FGT(SYS_TRCIMSPEC(7), 	HDFGRTR, TRCIMSPECn, 1),
+	SR_FGT(SYS_TRCDEVARCH, 		HDFGRTR, TRCID, 1),
+	SR_FGT(SYS_TRCDEVID, 		HDFGRTR, TRCID, 1),
+	SR_FGT(SYS_TRCIDR0, 		HDFGRTR, TRCID, 1),
+	SR_FGT(SYS_TRCIDR1, 		HDFGRTR, TRCID, 1),
+	SR_FGT(SYS_TRCIDR2, 		HDFGRTR, TRCID, 1),
+	SR_FGT(SYS_TRCIDR3, 		HDFGRTR, TRCID, 1),
+	SR_FGT(SYS_TRCIDR4, 		HDFGRTR, TRCID, 1),
+	SR_FGT(SYS_TRCIDR5, 		HDFGRTR, TRCID, 1),
+	SR_FGT(SYS_TRCIDR6, 		HDFGRTR, TRCID, 1),
+	SR_FGT(SYS_TRCIDR7, 		HDFGRTR, TRCID, 1),
+	SR_FGT(SYS_TRCIDR8, 		HDFGRTR, TRCID, 1),
+	SR_FGT(SYS_TRCIDR9, 		HDFGRTR, TRCID, 1),
+	SR_FGT(SYS_TRCIDR10, 		HDFGRTR, TRCID, 1),
+	SR_FGT(SYS_TRCIDR11, 		HDFGRTR, TRCID, 1),
+	SR_FGT(SYS_TRCIDR12, 		HDFGRTR, TRCID, 1),
+	SR_FGT(SYS_TRCIDR13, 		HDFGRTR, TRCID, 1),
+	SR_FGT(SYS_TRCCNTVR(0), 	HDFGRTR, TRCCNTVRn, 1),
+	SR_FGT(SYS_TRCCNTVR(1), 	HDFGRTR, TRCCNTVRn, 1),
+	SR_FGT(SYS_TRCCNTVR(2), 	HDFGRTR, TRCCNTVRn, 1),
+	SR_FGT(SYS_TRCCNTVR(3), 	HDFGRTR, TRCCNTVRn, 1),
+	SR_FGT(SYS_TRCCLAIMCLR, 	HDFGRTR, TRCCLAIM, 1),
+	SR_FGT(SYS_TRCCLAIMSET, 	HDFGRTR, TRCCLAIM, 1),
+	SR_FGT(SYS_TRCAUXCTLR, 		HDFGRTR, TRCAUXCTLR, 1),
+	SR_FGT(SYS_TRCAUTHSTATUS, 	HDFGRTR, TRCAUTHSTATUS, 1),
+	SR_FGT(SYS_TRCACATR(0), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACATR(1), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACATR(2), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACATR(3), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACATR(4), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACATR(5), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACATR(6), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACATR(7), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACATR(8), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACATR(9), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACATR(10), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACATR(11), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACATR(12), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACATR(13), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACATR(14), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACATR(15), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACVR(0), 		HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACVR(1), 		HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACVR(2), 		HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACVR(3), 		HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACVR(4), 		HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACVR(5), 		HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACVR(6), 		HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACVR(7), 		HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACVR(8), 		HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACVR(9), 		HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACVR(10), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACVR(11), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACVR(12), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACVR(13), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACVR(14), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCACVR(15), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCBBCTLR, 		HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCCCCTLR, 		HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCCIDCCTLR0, 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCCIDCCTLR1, 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCCIDCVR(0), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCCIDCVR(1), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCCIDCVR(2), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCCIDCVR(3), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCCIDCVR(4), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCCIDCVR(5), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCCIDCVR(6), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCCIDCVR(7), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCCNTCTLR(0), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCCNTCTLR(1), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCCNTCTLR(2), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCCNTCTLR(3), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCCNTRLDVR(0), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCCNTRLDVR(1), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCCNTRLDVR(2), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCCNTRLDVR(3), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCCONFIGR, 		HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCEVENTCTL0R, 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCEVENTCTL1R, 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCEXTINSELR(0), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCEXTINSELR(1), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCEXTINSELR(2), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCEXTINSELR(3), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCQCTLR, 		HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(2), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(3), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(4), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(5), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(6), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(7), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(8), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(9), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(10), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(11), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(12), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(13), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(14), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(15), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(16), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(17), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(18), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(19), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(20), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(21), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(22), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(23), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(24), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(25), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(26), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(27), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(28), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(29), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(30), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSCTLR(31), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCRSR, 		HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCSEQEVR(0), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCSEQEVR(1), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCSEQEVR(2), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCSEQRSTEVR, 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCSSCCR(0), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCSSCCR(1), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCSSCCR(2), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCSSCCR(3), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCSSCCR(4), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCSSCCR(5), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCSSCCR(6), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCSSCCR(7), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCSSPCICR(0), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCSSPCICR(1), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCSSPCICR(2), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCSSPCICR(3), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCSSPCICR(4), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCSSPCICR(5), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCSSPCICR(6), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCSSPCICR(7), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCSTALLCTLR, 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCSYNCPR, 		HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCTRACEIDR, 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCTSCTLR, 		HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCVIIECTLR, 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCVIPCSSCTLR, 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCVISSCTLR, 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCVMIDCCTLR0, 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCVMIDCCTLR1, 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCVMIDCVR(0), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCVMIDCVR(1), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCVMIDCVR(2), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCVMIDCVR(3), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCVMIDCVR(4), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCVMIDCVR(5), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCVMIDCVR(6), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_TRCVMIDCVR(7), 	HDFGRTR, TRC, 1),
+	SR_FGT(SYS_PMSLATFR_EL1, 	HDFGRTR, PMSLATFR_EL1, 1),
+	SR_FGT(SYS_PMSIRR_EL1, 		HDFGRTR, PMSIRR_EL1, 1),
+	SR_FGT(SYS_PMSIDR_EL1, 		HDFGRTR, PMSIDR_EL1, 1),
+	SR_FGT(SYS_PMSICR_EL1, 		HDFGRTR, PMSICR_EL1, 1),
+	SR_FGT(SYS_PMSFCR_EL1, 		HDFGRTR, PMSFCR_EL1, 1),
+	SR_FGT(SYS_PMSEVFR_EL1, 	HDFGRTR, PMSEVFR_EL1, 1),
+	SR_FGT(SYS_PMSCR_EL1, 		HDFGRTR, PMSCR_EL1, 1),
+	SR_FGT(SYS_PMBSR_EL1, 		HDFGRTR, PMBSR_EL1, 1),
+	SR_FGT(SYS_PMBPTR_EL1, 		HDFGRTR, PMBPTR_EL1, 1),
+	SR_FGT(SYS_PMBLIMITR_EL1, 	HDFGRTR, PMBLIMITR_EL1, 1),
+	SR_FGT(SYS_PMMIR_EL1, 		HDFGRTR, PMMIR_EL1, 1),
+	SR_FGT(SYS_PMSELR_EL0, 		HDFGRTR, PMSELR_EL0, 1),
+	SR_FGT(SYS_PMOVSCLR_EL0, 	HDFGRTR, PMOVS, 1),
+	SR_FGT(SYS_PMOVSSET_EL0, 	HDFGRTR, PMOVS, 1),
+	SR_FGT(SYS_PMINTENCLR_EL1, 	HDFGRTR, PMINTEN, 1),
+	SR_FGT(SYS_PMINTENSET_EL1, 	HDFGRTR, PMINTEN, 1),
+	SR_FGT(SYS_PMCNTENCLR_EL0, 	HDFGRTR, PMCNTEN, 1),
+	SR_FGT(SYS_PMCNTENSET_EL0, 	HDFGRTR, PMCNTEN, 1),
+	SR_FGT(SYS_PMCCNTR_EL0, 	HDFGRTR, PMCCNTR_EL0, 1),
+	SR_FGT(SYS_PMCCFILTR_EL0, 	HDFGRTR, PMCCFILTR_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(0), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(1), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(2), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(3), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(4), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(5), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(6), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(7), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(8), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(9), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(10), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(11), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(12), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(13), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(14), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(15), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(16), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(17), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(18), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(19), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(20), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(21), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(22), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(23), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(24), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(25), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(26), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(27), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(28), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(29), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVTYPERn_EL0(30), 	HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(0), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(1), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(2), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(3), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(4), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(5), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(6), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(7), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(8), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(9), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(10), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(11), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(12), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(13), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(14), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(15), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(16), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(17), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(18), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(19), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(20), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(21), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(22), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(23), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(24), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(25), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(26), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(27), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(28), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(29), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_PMEVCNTRn_EL0(30), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT(SYS_OSDLR_EL1, 		HDFGRTR, OSDLR_EL1, 1),
+	SR_FGT(SYS_OSECCR_EL1, 		HDFGRTR, OSECCR_EL1, 1),
+	SR_FGT(SYS_OSLSR_EL1, 		HDFGRTR, OSLSR_EL1, 1),
+	SR_FGT(SYS_DBGPRCR_EL1, 	HDFGRTR, DBGPRCR_EL1, 1),
+	SR_FGT(SYS_DBGAUTHSTATUS_EL1, 	HDFGRTR, DBGAUTHSTATUS_EL1, 1),
+	SR_FGT(SYS_DBGCLAIMSET_EL1, 	HDFGRTR, DBGCLAIM, 1),
+	SR_FGT(SYS_DBGCLAIMCLR_EL1, 	HDFGRTR, DBGCLAIM, 1),
+	SR_FGT(SYS_MDSCR_EL1, 		HDFGRTR, MDSCR_EL1, 1),
+	/*
+	 * The trap bits capture *64* debug registers per bit, but the
+	 * ARM ARM only describes the encoding for the first 16, and
+	 * we don't really support more than that anyway.
+	 */
+	SR_FGT(SYS_DBGWVRn_EL1(0), 	HDFGRTR, DBGWVRn_EL1, 1),
+	SR_FGT(SYS_DBGWVRn_EL1(1), 	HDFGRTR, DBGWVRn_EL1, 1),
+	SR_FGT(SYS_DBGWVRn_EL1(2), 	HDFGRTR, DBGWVRn_EL1, 1),
+	SR_FGT(SYS_DBGWVRn_EL1(3), 	HDFGRTR, DBGWVRn_EL1, 1),
+	SR_FGT(SYS_DBGWVRn_EL1(4), 	HDFGRTR, DBGWVRn_EL1, 1),
+	SR_FGT(SYS_DBGWVRn_EL1(5), 	HDFGRTR, DBGWVRn_EL1, 1),
+	SR_FGT(SYS_DBGWVRn_EL1(6), 	HDFGRTR, DBGWVRn_EL1, 1),
+	SR_FGT(SYS_DBGWVRn_EL1(7), 	HDFGRTR, DBGWVRn_EL1, 1),
+	SR_FGT(SYS_DBGWVRn_EL1(8), 	HDFGRTR, DBGWVRn_EL1, 1),
+	SR_FGT(SYS_DBGWVRn_EL1(9), 	HDFGRTR, DBGWVRn_EL1, 1),
+	SR_FGT(SYS_DBGWVRn_EL1(10), 	HDFGRTR, DBGWVRn_EL1, 1),
+	SR_FGT(SYS_DBGWVRn_EL1(11), 	HDFGRTR, DBGWVRn_EL1, 1),
+	SR_FGT(SYS_DBGWVRn_EL1(12), 	HDFGRTR, DBGWVRn_EL1, 1),
+	SR_FGT(SYS_DBGWVRn_EL1(13), 	HDFGRTR, DBGWVRn_EL1, 1),
+	SR_FGT(SYS_DBGWVRn_EL1(14), 	HDFGRTR, DBGWVRn_EL1, 1),
+	SR_FGT(SYS_DBGWVRn_EL1(15), 	HDFGRTR, DBGWVRn_EL1, 1),
+	SR_FGT(SYS_DBGWCRn_EL1(0), 	HDFGRTR, DBGWCRn_EL1, 1),
+	SR_FGT(SYS_DBGWCRn_EL1(1), 	HDFGRTR, DBGWCRn_EL1, 1),
+	SR_FGT(SYS_DBGWCRn_EL1(2), 	HDFGRTR, DBGWCRn_EL1, 1),
+	SR_FGT(SYS_DBGWCRn_EL1(3), 	HDFGRTR, DBGWCRn_EL1, 1),
+	SR_FGT(SYS_DBGWCRn_EL1(4), 	HDFGRTR, DBGWCRn_EL1, 1),
+	SR_FGT(SYS_DBGWCRn_EL1(5), 	HDFGRTR, DBGWCRn_EL1, 1),
+	SR_FGT(SYS_DBGWCRn_EL1(6), 	HDFGRTR, DBGWCRn_EL1, 1),
+	SR_FGT(SYS_DBGWCRn_EL1(7), 	HDFGRTR, DBGWCRn_EL1, 1),
+	SR_FGT(SYS_DBGWCRn_EL1(8), 	HDFGRTR, DBGWCRn_EL1, 1),
+	SR_FGT(SYS_DBGWCRn_EL1(9), 	HDFGRTR, DBGWCRn_EL1, 1),
+	SR_FGT(SYS_DBGWCRn_EL1(10), 	HDFGRTR, DBGWCRn_EL1, 1),
+	SR_FGT(SYS_DBGWCRn_EL1(11), 	HDFGRTR, DBGWCRn_EL1, 1),
+	SR_FGT(SYS_DBGWCRn_EL1(12), 	HDFGRTR, DBGWCRn_EL1, 1),
+	SR_FGT(SYS_DBGWCRn_EL1(13), 	HDFGRTR, DBGWCRn_EL1, 1),
+	SR_FGT(SYS_DBGWCRn_EL1(14), 	HDFGRTR, DBGWCRn_EL1, 1),
+	SR_FGT(SYS_DBGWCRn_EL1(15), 	HDFGRTR, DBGWCRn_EL1, 1),
+	SR_FGT(SYS_DBGBVRn_EL1(0), 	HDFGRTR, DBGBVRn_EL1, 1),
+	SR_FGT(SYS_DBGBVRn_EL1(1), 	HDFGRTR, DBGBVRn_EL1, 1),
+	SR_FGT(SYS_DBGBVRn_EL1(2), 	HDFGRTR, DBGBVRn_EL1, 1),
+	SR_FGT(SYS_DBGBVRn_EL1(3), 	HDFGRTR, DBGBVRn_EL1, 1),
+	SR_FGT(SYS_DBGBVRn_EL1(4), 	HDFGRTR, DBGBVRn_EL1, 1),
+	SR_FGT(SYS_DBGBVRn_EL1(5), 	HDFGRTR, DBGBVRn_EL1, 1),
+	SR_FGT(SYS_DBGBVRn_EL1(6), 	HDFGRTR, DBGBVRn_EL1, 1),
+	SR_FGT(SYS_DBGBVRn_EL1(7), 	HDFGRTR, DBGBVRn_EL1, 1),
+	SR_FGT(SYS_DBGBVRn_EL1(8), 	HDFGRTR, DBGBVRn_EL1, 1),
+	SR_FGT(SYS_DBGBVRn_EL1(9), 	HDFGRTR, DBGBVRn_EL1, 1),
+	SR_FGT(SYS_DBGBVRn_EL1(10), 	HDFGRTR, DBGBVRn_EL1, 1),
+	SR_FGT(SYS_DBGBVRn_EL1(11), 	HDFGRTR, DBGBVRn_EL1, 1),
+	SR_FGT(SYS_DBGBVRn_EL1(12), 	HDFGRTR, DBGBVRn_EL1, 1),
+	SR_FGT(SYS_DBGBVRn_EL1(13), 	HDFGRTR, DBGBVRn_EL1, 1),
+	SR_FGT(SYS_DBGBVRn_EL1(14), 	HDFGRTR, DBGBVRn_EL1, 1),
+	SR_FGT(SYS_DBGBVRn_EL1(15), 	HDFGRTR, DBGBVRn_EL1, 1),
+	SR_FGT(SYS_DBGBCRn_EL1(0), 	HDFGRTR, DBGBCRn_EL1, 1),
+	SR_FGT(SYS_DBGBCRn_EL1(1), 	HDFGRTR, DBGBCRn_EL1, 1),
+	SR_FGT(SYS_DBGBCRn_EL1(2), 	HDFGRTR, DBGBCRn_EL1, 1),
+	SR_FGT(SYS_DBGBCRn_EL1(3), 	HDFGRTR, DBGBCRn_EL1, 1),
+	SR_FGT(SYS_DBGBCRn_EL1(4), 	HDFGRTR, DBGBCRn_EL1, 1),
+	SR_FGT(SYS_DBGBCRn_EL1(5), 	HDFGRTR, DBGBCRn_EL1, 1),
+	SR_FGT(SYS_DBGBCRn_EL1(6), 	HDFGRTR, DBGBCRn_EL1, 1),
+	SR_FGT(SYS_DBGBCRn_EL1(7), 	HDFGRTR, DBGBCRn_EL1, 1),
+	SR_FGT(SYS_DBGBCRn_EL1(8), 	HDFGRTR, DBGBCRn_EL1, 1),
+	SR_FGT(SYS_DBGBCRn_EL1(9), 	HDFGRTR, DBGBCRn_EL1, 1),
+	SR_FGT(SYS_DBGBCRn_EL1(10), 	HDFGRTR, DBGBCRn_EL1, 1),
+	SR_FGT(SYS_DBGBCRn_EL1(11), 	HDFGRTR, DBGBCRn_EL1, 1),
+	SR_FGT(SYS_DBGBCRn_EL1(12), 	HDFGRTR, DBGBCRn_EL1, 1),
+	SR_FGT(SYS_DBGBCRn_EL1(13), 	HDFGRTR, DBGBCRn_EL1, 1),
+	SR_FGT(SYS_DBGBCRn_EL1(14), 	HDFGRTR, DBGBCRn_EL1, 1),
+	SR_FGT(SYS_DBGBCRn_EL1(15), 	HDFGRTR, DBGBCRn_EL1, 1),
+	/*
+	 * HDFGWTR_EL2
+	 *
+	 * Although HDFGRTR_EL2 and HDFGWTR_EL2 registers largely
+	 * overlap in their bit assignment, there are a number of bits
+	 * that are RES0 on one side, and an actual trap bit on the
+	 * other.  The policy chosen here is to describe all the
+	 * read-side mappings, and only the write-side mappings that
+	 * differ from the read side, and the trap handler will pick
+	 * the correct shadow register based on the access type.
+	 */
+	SR_FGT(SYS_TRFCR_EL1,		HDFGWTR, TRFCR_EL1, 1),
+	SR_FGT(SYS_TRCOSLAR,		HDFGWTR, TRCOSLAR, 1),
+	SR_FGT(SYS_PMCR_EL0,		HDFGWTR, PMCR_EL0, 1),
+	SR_FGT(SYS_PMSWINC_EL0,		HDFGWTR, PMSWINC_EL0, 1),
+	SR_FGT(SYS_OSLAR_EL1,		HDFGWTR, OSLAR_EL1, 1),
 };
 
 static union trap_config get_trap_config(u32 sysreg)
@@ -1336,6 +1802,14 @@ bool __check_nv_sr_forward(struct kvm_vcpu *vcpu)
 			val = sanitised_sys_reg(vcpu, HFGWTR_EL2);
 		break;
 
+	case HDFGRTR_GROUP:
+	case HDFGWTR_GROUP:
+		if (is_read)
+			val = sanitised_sys_reg(vcpu, HDFGRTR_EL2);
+		else
+			val = sanitised_sys_reg(vcpu, HDFGWTR_EL2);
+		break;
+
 	case HFGITR_GROUP:
 		val = sanitised_sys_reg(vcpu, HFGITR_EL2);
 		break;

From a77b31dce4375be15014b10e8f94a149592ea6b6 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 15 Aug 2023 19:38:57 +0100
Subject: [PATCH 0498/1189] KVM: arm64: nv: Add SVC trap forwarding

HFGITR_EL2 allows the trap of SVC instructions to EL2. Allow these
traps to be forwarded. Take this opportunity to deny any 32bit activity
when NV is enabled.

Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Jing Zhang <jingzhangos@google.com>
Link: https://lore.kernel.org/r/20230815183903.2735724-24-maz@kernel.org
---
 arch/arm64/kvm/arm.c         |  4 ++++
 arch/arm64/kvm/handle_exit.c | 12 ++++++++++++
 2 files changed, 16 insertions(+)

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 72dc53a75d1c..8b51570a76f8 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -36,6 +36,7 @@
 #include <asm/kvm_arm.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmu.h>
+#include <asm/kvm_nested.h>
 #include <asm/kvm_pkvm.h>
 #include <asm/kvm_emulate.h>
 #include <asm/sections.h>
@@ -818,6 +819,9 @@ static bool vcpu_mode_is_bad_32bit(struct kvm_vcpu *vcpu)
 	if (likely(!vcpu_mode_is_32bit(vcpu)))
 		return false;
 
+	if (vcpu_has_nv(vcpu))
+		return true;
+
 	return !kvm_supports_32bit_el0();
 }
 
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 6dcd6604b6bc..3b86d534b995 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -226,6 +226,17 @@ static int kvm_handle_eret(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static int handle_svc(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * So far, SVC traps only for NV via HFGITR_EL2. A SVC from a
+	 * 32bit guest would be caught by vpcu_mode_is_bad_32bit(), so
+	 * we should only have to deal with a 64 bit exception.
+	 */
+	kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
+	return 1;
+}
+
 static exit_handle_fn arm_exit_handlers[] = {
 	[0 ... ESR_ELx_EC_MAX]	= kvm_handle_unknown_ec,
 	[ESR_ELx_EC_WFx]	= kvm_handle_wfx,
@@ -239,6 +250,7 @@ static exit_handle_fn arm_exit_handlers[] = {
 	[ESR_ELx_EC_SMC32]	= handle_smc,
 	[ESR_ELx_EC_HVC64]	= handle_hvc,
 	[ESR_ELx_EC_SMC64]	= handle_smc,
+	[ESR_ELx_EC_SVC64]	= handle_svc,
 	[ESR_ELx_EC_SYS64]	= kvm_handle_sys_reg,
 	[ESR_ELx_EC_SVE]	= handle_sve,
 	[ESR_ELx_EC_ERET]	= kvm_handle_eret,

From ea3b27d8dea081f1693b310322ae71fa75d1875b Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 15 Aug 2023 19:38:58 +0100
Subject: [PATCH 0499/1189] KVM: arm64: nv: Expand ERET trap forwarding to
 handle FGT

We already handle ERET being trapped from a L1 guest in hyp context.
However, with FGT, we can also have ERET being trapped from L2, and
this needs to be reinjected into L1.

Add the required exception routing.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Jing Zhang <jingzhangos@google.com>
Link: https://lore.kernel.org/r/20230815183903.2735724-25-maz@kernel.org
---
 arch/arm64/kvm/handle_exit.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 3b86d534b995..617ae6dea5d5 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -222,7 +222,22 @@ static int kvm_handle_eret(struct kvm_vcpu *vcpu)
 	if (kvm_vcpu_get_esr(vcpu) & ESR_ELx_ERET_ISS_ERET)
 		return kvm_handle_ptrauth(vcpu);
 
-	kvm_emulate_nested_eret(vcpu);
+	/*
+	 * If we got here, two possibilities:
+	 *
+	 * - the guest is in EL2, and we need to fully emulate ERET
+	 *
+	 * - the guest is in EL1, and we need to reinject the
+         *   exception into the L1 hypervisor.
+	 *
+	 * If KVM ever traps ERET for its own use, we'll have to
+	 * revisit this.
+	 */
+	if (is_hyp_ctxt(vcpu))
+		kvm_emulate_nested_eret(vcpu);
+	else
+		kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
+
 	return 1;
 }
 

From d4d2dacc7cddc37aaa7c6eed8665d533d1037e1e Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 15 Aug 2023 19:38:59 +0100
Subject: [PATCH 0500/1189] KVM: arm64: nv: Add switching support for
 HFGxTR/HDFGxTR

Now that we can evaluate the FGT registers, allow them to be merged
with the hypervisor's own configuration (in the case of HFG{RW}TR_EL2)
or simply set for HFGITR_EL2, HDGFRTR_EL2 and HDFGWTR_EL2.

Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Jing Zhang <jingzhangos@google.com>
Link: https://lore.kernel.org/r/20230815183903.2735724-26-maz@kernel.org
---
 arch/arm64/kvm/hyp/include/hyp/switch.h | 48 +++++++++++++++++++++++++
 1 file changed, 48 insertions(+)

diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index e096b16e85fd..a4750070563f 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -70,6 +70,13 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
 	}
 }
 
+#define compute_clr_set(vcpu, reg, clr, set)				\
+	do {								\
+		u64 hfg;						\
+		hfg = __vcpu_sys_reg(vcpu, reg) & ~__ ## reg ## _RES0;	\
+		set |= hfg & __ ## reg ## _MASK; 			\
+		clr |= ~hfg & __ ## reg ## _nMASK; 			\
+	} while(0)
 
 
 static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu)
@@ -97,6 +104,10 @@ static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 	if (cpus_have_final_cap(ARM64_WORKAROUND_AMPERE_AC03_CPU_38))
 		w_set |= HFGxTR_EL2_TCR_EL1_MASK;
 
+	if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) {
+		compute_clr_set(vcpu, HFGRTR_EL2, r_clr, r_set);
+		compute_clr_set(vcpu, HFGWTR_EL2, w_clr, w_set);
+	}
 
 	/* The default is not to trap anything but ACCDATA_EL1 */
 	r_val = __HFGRTR_EL2_nMASK & ~HFGxTR_EL2_nACCDATA_EL1;
@@ -109,6 +120,38 @@ static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 
 	write_sysreg_s(r_val, SYS_HFGRTR_EL2);
 	write_sysreg_s(w_val, SYS_HFGWTR_EL2);
+
+	if (!vcpu_has_nv(vcpu) || is_hyp_ctxt(vcpu))
+		return;
+
+	ctxt_sys_reg(hctxt, HFGITR_EL2) = read_sysreg_s(SYS_HFGITR_EL2);
+
+	r_set = r_clr = 0;
+	compute_clr_set(vcpu, HFGITR_EL2, r_clr, r_set);
+	r_val = __HFGITR_EL2_nMASK;
+	r_val |= r_set;
+	r_val &= ~r_clr;
+
+	write_sysreg_s(r_val, SYS_HFGITR_EL2);
+
+	ctxt_sys_reg(hctxt, HDFGRTR_EL2) = read_sysreg_s(SYS_HDFGRTR_EL2);
+	ctxt_sys_reg(hctxt, HDFGWTR_EL2) = read_sysreg_s(SYS_HDFGWTR_EL2);
+
+	r_clr = r_set = w_clr = w_set = 0;
+
+	compute_clr_set(vcpu, HDFGRTR_EL2, r_clr, r_set);
+	compute_clr_set(vcpu, HDFGWTR_EL2, w_clr, w_set);
+
+	r_val = __HDFGRTR_EL2_nMASK;
+	r_val |= r_set;
+	r_val &= ~r_clr;
+
+	w_val = __HDFGWTR_EL2_nMASK;
+	w_val |= w_set;
+	w_val &= ~w_clr;
+
+	write_sysreg_s(r_val, SYS_HDFGRTR_EL2);
+	write_sysreg_s(w_val, SYS_HDFGWTR_EL2);
 }
 
 static inline void __deactivate_traps_hfgxtr(struct kvm_vcpu *vcpu)
@@ -121,7 +164,12 @@ static inline void __deactivate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 	write_sysreg_s(ctxt_sys_reg(hctxt, HFGRTR_EL2), SYS_HFGRTR_EL2);
 	write_sysreg_s(ctxt_sys_reg(hctxt, HFGWTR_EL2), SYS_HFGWTR_EL2);
 
+	if (!vcpu_has_nv(vcpu) || is_hyp_ctxt(vcpu))
+		return;
 
+	write_sysreg_s(ctxt_sys_reg(hctxt, HFGITR_EL2), SYS_HFGITR_EL2);
+	write_sysreg_s(ctxt_sys_reg(hctxt, HDFGRTR_EL2), SYS_HDFGRTR_EL2);
+	write_sysreg_s(ctxt_sys_reg(hctxt, HDFGWTR_EL2), SYS_HDFGWTR_EL2);
 }
 
 static inline void __activate_traps_common(struct kvm_vcpu *vcpu)

From 0a5d28433ad94cc38ecb3dbb5138b8ae30ffb98a Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 15 Aug 2023 19:39:00 +0100
Subject: [PATCH 0501/1189] KVM: arm64: nv: Expose FGT to nested guests

Now that we have FGT support, expose the feature to NV guests.

Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Jing Zhang <jingzhangos@google.com>
Link: https://lore.kernel.org/r/20230815183903.2735724-27-maz@kernel.org
---
 arch/arm64/kvm/nested.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 7f80f385d9e8..3facd8918ae3 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -71,8 +71,9 @@ void access_nested_id_reg(struct kvm_vcpu *v, struct sys_reg_params *p,
 		break;
 
 	case SYS_ID_AA64MMFR0_EL1:
-		/* Hide ECV, FGT, ExS, Secure Memory */
-		val &= ~(GENMASK_ULL(63, 43)		|
+		/* Hide ECV, ExS, Secure Memory */
+		val &= ~(NV_FTR(MMFR0, ECV)		|
+			 NV_FTR(MMFR0, EXS)		|
 			 NV_FTR(MMFR0, TGRAN4_2)	|
 			 NV_FTR(MMFR0, TGRAN16_2)	|
 			 NV_FTR(MMFR0, TGRAN64_2)	|

From a63cf31139b7f41d468dc8ef63dbf6bae213d960 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 15 Aug 2023 19:39:01 +0100
Subject: [PATCH 0502/1189] KVM: arm64: Move HCRX_EL2 switch to load/put on VHE
 systems

Although the nVHE behaviour requires HCRX_EL2 to be switched
on each switch between host and guest, there is nothing in
this register that would affect a VHE host.

It is thus possible to save/restore this register on load/put
on VHE systems, avoiding unnecessary sysreg access on the hot
path. Additionally, it avoids unnecessary traps when running
with NV.

To achieve this, simply move the read/writes to the *_common()
helpers, which are called on load/put on VHE, and more eagerly
on nVHE.

Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Jing Zhang <jingzhangos@google.com>
Link: https://lore.kernel.org/r/20230815183903.2735724-28-maz@kernel.org
---
 arch/arm64/kvm/hyp/include/hyp/switch.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index a4750070563f..060c5a0409e5 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -197,6 +197,9 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
 	vcpu->arch.mdcr_el2_host = read_sysreg(mdcr_el2);
 	write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
 
+	if (cpus_have_final_cap(ARM64_HAS_HCX))
+		write_sysreg_s(HCRX_GUEST_FLAGS, SYS_HCRX_EL2);
+
 	__activate_traps_hfgxtr(vcpu);
 }
 
@@ -213,6 +216,9 @@ static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu)
 		vcpu_clear_flag(vcpu, PMUSERENR_ON_CPU);
 	}
 
+	if (cpus_have_final_cap(ARM64_HAS_HCX))
+		write_sysreg_s(HCRX_HOST_FLAGS, SYS_HCRX_EL2);
+
 	__deactivate_traps_hfgxtr(vcpu);
 }
 
@@ -227,9 +233,6 @@ static inline void ___activate_traps(struct kvm_vcpu *vcpu)
 
 	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE))
 		write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2);
-
-	if (cpus_have_final_cap(ARM64_HAS_HCX))
-		write_sysreg_s(HCRX_GUEST_FLAGS, SYS_HCRX_EL2);
 }
 
 static inline void ___deactivate_traps(struct kvm_vcpu *vcpu)
@@ -244,9 +247,6 @@ static inline void ___deactivate_traps(struct kvm_vcpu *vcpu)
 		vcpu->arch.hcr_el2 &= ~HCR_VSE;
 		vcpu->arch.hcr_el2 |= read_sysreg(hcr_el2) & HCR_VSE;
 	}
-
-	if (cpus_have_final_cap(ARM64_HAS_HCX))
-		write_sysreg_s(HCRX_HOST_FLAGS, SYS_HCRX_EL2);
 }
 
 static inline bool __populate_fault_info(struct kvm_vcpu *vcpu)

From 03fb54d0aa73cc14e51f6611eb3289e4fec15184 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 15 Aug 2023 19:39:02 +0100
Subject: [PATCH 0503/1189] KVM: arm64: nv: Add support for HCRX_EL2

HCRX_EL2 has an interesting effect on HFGITR_EL2, as it conditions
the traps of TLBI*nXS.

Expand the FGT support to add a new Fine Grained Filter that will
get checked when the instruction gets trapped, allowing the shadow
register to override the trap as needed.

Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Jing Zhang <jingzhangos@google.com>
Link: https://lore.kernel.org/r/20230815183903.2735724-29-maz@kernel.org
---
 arch/arm64/include/asm/kvm_arm.h        |  5 ++
 arch/arm64/include/asm/kvm_host.h       |  1 +
 arch/arm64/kvm/emulate-nested.c         | 94 ++++++++++++++++---------
 arch/arm64/kvm/hyp/include/hyp/switch.h | 15 +++-
 arch/arm64/kvm/nested.c                 |  3 +-
 arch/arm64/kvm/sys_regs.c               |  2 +
 6 files changed, 83 insertions(+), 37 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index d229f238c3b6..137f732789c9 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -369,6 +369,11 @@
 #define __HDFGWTR_EL2_MASK	~__HDFGWTR_EL2_nMASK
 #define __HDFGWTR_EL2_nMASK	GENMASK(62, 60)
 
+/* Similar definitions for HCRX_EL2 */
+#define __HCRX_EL2_RES0		(GENMASK(63, 16) | GENMASK(13, 12))
+#define __HCRX_EL2_MASK		(0)
+#define __HCRX_EL2_nMASK	(GENMASK(15, 14) | GENMASK(4, 0))
+
 /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
 #define HPFAR_MASK	(~UL(0xf))
 /*
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index cb1c5c54cedd..93c541111dea 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -380,6 +380,7 @@ enum vcpu_sysreg {
 	CPTR_EL2,	/* Architectural Feature Trap Register (EL2) */
 	HSTR_EL2,	/* Hypervisor System Trap Register */
 	HACR_EL2,	/* Hypervisor Auxiliary Control Register */
+	HCRX_EL2,	/* Extended Hypervisor Configuration Register */
 	TTBR0_EL2,	/* Translation Table Base Register 0 (EL2) */
 	TTBR1_EL2,	/* Translation Table Base Register 1 (EL2) */
 	TCR_EL2,	/* Translation Control Register (EL2) */
diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index c9662f9a345e..1cc606c16416 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -426,11 +426,13 @@ static const complex_condition_check ccc[] = {
  * [13:10]	enum fgt_group_id (4 bits)
  * [19:14]	bit number in the FGT register (6 bits)
  * [20]		trap polarity (1 bit)
- * [62:21]	Unused (42 bits)
+ * [25:21]	FG filter (5 bits)
+ * [62:26]	Unused (37 bits)
  * [63]		RES0 - Must be zero, as lost on insertion in the xarray
  */
 #define TC_CGT_BITS	10
 #define TC_FGT_BITS	4
+#define TC_FGF_BITS	5
 
 union trap_config {
 	u64	val;
@@ -439,7 +441,8 @@ union trap_config {
 		unsigned long	fgt:TC_FGT_BITS; /* Fine Grained Trap id */
 		unsigned long	bit:6;		 /* Bit number */
 		unsigned long	pol:1;		 /* Polarity */
-		unsigned long	unused:42;	 /* Unused, should be zero */
+		unsigned long	fgf:TC_FGF_BITS; /* Fine Grained Filter */
+		unsigned long	unused:37;	 /* Unused, should be zero */
 		unsigned long	mbz:1;		 /* Must Be Zero */
 	};
 };
@@ -947,7 +950,15 @@ enum fgt_group_id {
 	__NR_FGT_GROUP_IDS__
 };
 
-#define SR_FGT(sr, g, b, p)					\
+enum fg_filter_id {
+	__NO_FGF__,
+	HCRX_FGTnXS,
+
+	/* Must be last */
+	__NR_FG_FILTER_IDS__
+};
+
+#define SR_FGF(sr, g, b, p, f)					\
 	{							\
 		.encoding	= sr,				\
 		.end		= sr,				\
@@ -955,10 +966,13 @@ enum fgt_group_id {
 			.fgt = g ## _GROUP,			\
 			.bit = g ## _EL2_ ## b ## _SHIFT,	\
 			.pol = p,				\
+			.fgf = f,				\
 		},						\
 		.line = __LINE__,				\
 	}
 
+#define SR_FGT(sr, g, b, p)	SR_FGF(sr, g, b, p, __NO_FGF__)
+
 static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
 	/* HFGRTR_EL2, HFGWTR_EL2 */
 	SR_FGT(SYS_TPIDR2_EL0,		HFGxTR, nTPIDR2_EL0, 0),
@@ -1062,37 +1076,37 @@ static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
 	SR_FGT(OP_TLBI_ASIDE1OS, 	HFGITR, TLBIASIDE1OS, 1),
 	SR_FGT(OP_TLBI_VAE1OS, 		HFGITR, TLBIVAE1OS, 1),
 	SR_FGT(OP_TLBI_VMALLE1OS, 	HFGITR, TLBIVMALLE1OS, 1),
-	/* FIXME: nXS variants must be checked against HCRX_EL2.FGTnXS */
-	SR_FGT(OP_TLBI_VAALE1NXS, 	HFGITR, TLBIVAALE1, 1),
-	SR_FGT(OP_TLBI_VALE1NXS, 	HFGITR, TLBIVALE1, 1),
-	SR_FGT(OP_TLBI_VAAE1NXS, 	HFGITR, TLBIVAAE1, 1),
-	SR_FGT(OP_TLBI_ASIDE1NXS, 	HFGITR, TLBIASIDE1, 1),
-	SR_FGT(OP_TLBI_VAE1NXS, 	HFGITR, TLBIVAE1, 1),
-	SR_FGT(OP_TLBI_VMALLE1NXS, 	HFGITR, TLBIVMALLE1, 1),
-	SR_FGT(OP_TLBI_RVAALE1NXS, 	HFGITR, TLBIRVAALE1, 1),
-	SR_FGT(OP_TLBI_RVALE1NXS, 	HFGITR, TLBIRVALE1, 1),
-	SR_FGT(OP_TLBI_RVAAE1NXS, 	HFGITR, TLBIRVAAE1, 1),
-	SR_FGT(OP_TLBI_RVAE1NXS, 	HFGITR, TLBIRVAE1, 1),
-	SR_FGT(OP_TLBI_RVAALE1ISNXS, 	HFGITR, TLBIRVAALE1IS, 1),
-	SR_FGT(OP_TLBI_RVALE1ISNXS, 	HFGITR, TLBIRVALE1IS, 1),
-	SR_FGT(OP_TLBI_RVAAE1ISNXS, 	HFGITR, TLBIRVAAE1IS, 1),
-	SR_FGT(OP_TLBI_RVAE1ISNXS, 	HFGITR, TLBIRVAE1IS, 1),
-	SR_FGT(OP_TLBI_VAALE1ISNXS, 	HFGITR, TLBIVAALE1IS, 1),
-	SR_FGT(OP_TLBI_VALE1ISNXS, 	HFGITR, TLBIVALE1IS, 1),
-	SR_FGT(OP_TLBI_VAAE1ISNXS, 	HFGITR, TLBIVAAE1IS, 1),
-	SR_FGT(OP_TLBI_ASIDE1ISNXS, 	HFGITR, TLBIASIDE1IS, 1),
-	SR_FGT(OP_TLBI_VAE1ISNXS, 	HFGITR, TLBIVAE1IS, 1),
-	SR_FGT(OP_TLBI_VMALLE1ISNXS, 	HFGITR, TLBIVMALLE1IS, 1),
-	SR_FGT(OP_TLBI_RVAALE1OSNXS, 	HFGITR, TLBIRVAALE1OS, 1),
-	SR_FGT(OP_TLBI_RVALE1OSNXS, 	HFGITR, TLBIRVALE1OS, 1),
-	SR_FGT(OP_TLBI_RVAAE1OSNXS, 	HFGITR, TLBIRVAAE1OS, 1),
-	SR_FGT(OP_TLBI_RVAE1OSNXS, 	HFGITR, TLBIRVAE1OS, 1),
-	SR_FGT(OP_TLBI_VAALE1OSNXS, 	HFGITR, TLBIVAALE1OS, 1),
-	SR_FGT(OP_TLBI_VALE1OSNXS, 	HFGITR, TLBIVALE1OS, 1),
-	SR_FGT(OP_TLBI_VAAE1OSNXS, 	HFGITR, TLBIVAAE1OS, 1),
-	SR_FGT(OP_TLBI_ASIDE1OSNXS, 	HFGITR, TLBIASIDE1OS, 1),
-	SR_FGT(OP_TLBI_VAE1OSNXS, 	HFGITR, TLBIVAE1OS, 1),
-	SR_FGT(OP_TLBI_VMALLE1OSNXS, 	HFGITR, TLBIVMALLE1OS, 1),
+	/* nXS variants must be checked against HCRX_EL2.FGTnXS */
+	SR_FGF(OP_TLBI_VAALE1NXS, 	HFGITR, TLBIVAALE1, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_VALE1NXS, 	HFGITR, TLBIVALE1, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_VAAE1NXS, 	HFGITR, TLBIVAAE1, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_ASIDE1NXS, 	HFGITR, TLBIASIDE1, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_VAE1NXS, 	HFGITR, TLBIVAE1, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_VMALLE1NXS, 	HFGITR, TLBIVMALLE1, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_RVAALE1NXS, 	HFGITR, TLBIRVAALE1, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_RVALE1NXS, 	HFGITR, TLBIRVALE1, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_RVAAE1NXS, 	HFGITR, TLBIRVAAE1, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_RVAE1NXS, 	HFGITR, TLBIRVAE1, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_RVAALE1ISNXS, 	HFGITR, TLBIRVAALE1IS, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_RVALE1ISNXS, 	HFGITR, TLBIRVALE1IS, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_RVAAE1ISNXS, 	HFGITR, TLBIRVAAE1IS, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_RVAE1ISNXS, 	HFGITR, TLBIRVAE1IS, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_VAALE1ISNXS, 	HFGITR, TLBIVAALE1IS, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_VALE1ISNXS, 	HFGITR, TLBIVALE1IS, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_VAAE1ISNXS, 	HFGITR, TLBIVAAE1IS, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_ASIDE1ISNXS, 	HFGITR, TLBIASIDE1IS, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_VAE1ISNXS, 	HFGITR, TLBIVAE1IS, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_VMALLE1ISNXS, 	HFGITR, TLBIVMALLE1IS, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_RVAALE1OSNXS, 	HFGITR, TLBIRVAALE1OS, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_RVALE1OSNXS, 	HFGITR, TLBIRVALE1OS, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_RVAAE1OSNXS, 	HFGITR, TLBIRVAAE1OS, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_RVAE1OSNXS, 	HFGITR, TLBIRVAE1OS, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_VAALE1OSNXS, 	HFGITR, TLBIVAALE1OS, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_VALE1OSNXS, 	HFGITR, TLBIVALE1OS, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_VAAE1OSNXS, 	HFGITR, TLBIVAAE1OS, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_ASIDE1OSNXS, 	HFGITR, TLBIASIDE1OS, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_VAE1OSNXS, 	HFGITR, TLBIVAE1OS, 1, HCRX_FGTnXS),
+	SR_FGF(OP_TLBI_VMALLE1OSNXS, 	HFGITR, TLBIVMALLE1OS, 1, HCRX_FGTnXS),
 	SR_FGT(OP_AT_S1E1WP, 		HFGITR, ATS1E1WP, 1),
 	SR_FGT(OP_AT_S1E1RP, 		HFGITR, ATS1E1RP, 1),
 	SR_FGT(OP_AT_S1E0W, 		HFGITR, ATS1E0W, 1),
@@ -1622,6 +1636,7 @@ int __init populate_nv_trap_config(void)
 	BUILD_BUG_ON(sizeof(union trap_config) != sizeof(void *));
 	BUILD_BUG_ON(__NR_CGT_GROUP_IDS__ > BIT(TC_CGT_BITS));
 	BUILD_BUG_ON(__NR_FGT_GROUP_IDS__ > BIT(TC_FGT_BITS));
+	BUILD_BUG_ON(__NR_FG_FILTER_IDS__ > BIT(TC_FGF_BITS));
 
 	for (int i = 0; i < ARRAY_SIZE(encoding_to_cgt); i++) {
 		const struct encoding_to_trap_config *cgt = &encoding_to_cgt[i];
@@ -1812,6 +1827,17 @@ bool __check_nv_sr_forward(struct kvm_vcpu *vcpu)
 
 	case HFGITR_GROUP:
 		val = sanitised_sys_reg(vcpu, HFGITR_EL2);
+		switch (tc.fgf) {
+			u64 tmp;
+
+		case __NO_FGF__:
+			break;
+
+		case HCRX_FGTnXS:
+			tmp = sanitised_sys_reg(vcpu, HCRX_EL2);
+			if (tmp & HCRX_EL2_FGTnXS)
+				tc.fgt = __NO_FGT_GROUP__;
+		}
 		break;
 
 	case __NR_FGT_GROUP_IDS__:
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 060c5a0409e5..3acf6d77e324 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -197,8 +197,19 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
 	vcpu->arch.mdcr_el2_host = read_sysreg(mdcr_el2);
 	write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
 
-	if (cpus_have_final_cap(ARM64_HAS_HCX))
-		write_sysreg_s(HCRX_GUEST_FLAGS, SYS_HCRX_EL2);
+	if (cpus_have_final_cap(ARM64_HAS_HCX)) {
+		u64 hcrx = HCRX_GUEST_FLAGS;
+		if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) {
+			u64 clr = 0, set = 0;
+
+			compute_clr_set(vcpu, HCRX_EL2, clr, set);
+
+			hcrx |= set;
+			hcrx &= ~clr;
+		}
+
+		write_sysreg_s(hcrx, SYS_HCRX_EL2);
+	}
 
 	__activate_traps_hfgxtr(vcpu);
 }
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 3facd8918ae3..042695a210ce 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -117,7 +117,8 @@ void access_nested_id_reg(struct kvm_vcpu *v, struct sys_reg_params *p,
 		break;
 
 	case SYS_ID_AA64MMFR1_EL1:
-		val &= (NV_FTR(MMFR1, PAN)	|
+		val &= (NV_FTR(MMFR1, HCX)	|
+			NV_FTR(MMFR1, PAN)	|
 			NV_FTR(MMFR1, LO)	|
 			NV_FTR(MMFR1, HPDS)	|
 			NV_FTR(MMFR1, VH)	|
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 9556896311db..e92ec810d449 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2372,6 +2372,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	EL2_REG(HFGITR_EL2, access_rw, reset_val, 0),
 	EL2_REG(HACR_EL2, access_rw, reset_val, 0),
 
+	EL2_REG(HCRX_EL2, access_rw, reset_val, 0),
+
 	EL2_REG(TTBR0_EL2, access_rw, reset_val, 0),
 	EL2_REG(TTBR1_EL2, access_rw, reset_val, 0),
 	EL2_REG(TCR_EL2, access_rw, reset_val, TCR_EL2_RES1),

From 60046980bf60ed8846113b484d666a5fdf413be4 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 16 Aug 2023 14:09:49 -0700
Subject: [PATCH 0504/1189] KVM: arm64: nv: Select XARRAY_MULTI to fix build
 error

populate_nv_trap_config() uses xa_store_range(), which is only built
when XARRAY_MULTI is set, so select that symbol to prevent the build error.

aarch64-linux-ld: arch/arm64/kvm/emulate-nested.o: in function `populate_nv_trap_config':
emulate-nested.c:(.init.text+0x17c): undefined reference to `xa_store_range'

Fixes: e58ec47bf68d ("KVM: arm64: nv: Add trap forwarding infrastructure")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: kvmarm@lists.linux.dev
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230816210949.17117-1-rdunlap@infradead.org
---
 arch/arm64/kvm/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index f531da6b362e..f4f0b19d755b 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -43,6 +43,7 @@ menuconfig KVM
 	select SCHED_INFO
 	select GUEST_PERF_EVENTS if PERF_EVENTS
 	select INTERVAL_TREE
+	select XARRAY_MULTI
 	help
 	  Support hosting virtualized guest machines.
 

From c3e1e8cf006bf8ed7e32b57ed00a1fe3ed2b1a08 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@arm.com>
Date: Wed, 16 Aug 2023 12:47:43 +0100
Subject: [PATCH 0505/1189] perf arm64: Allow version comparisons of CPU IDs

Currently variant and revision fields are masked out of the MIDR so
it's not possible to compare different versions of the same CPU.
In a later commit a workaround will be removed just for N2 r0p3, so
enable comparisons on version.

This has the side effect of changing the MIDR stored in the header of
the perf.data file to no longer have masked version fields. It also
affects the lookups in mapfile.csv, but as that currently only has
zeroed version fields, it has no actual effect. The mapfile.csv
documentation also states to zero the version fields, so unless this
isn't done it will continue to have no effect.

There is an existing weak default strcmp_cpuid_str() function, and an
x86 version. This adds another version for arm64.

Signed-off-by: James Clark <james.clark@arm.com>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Haixin Yu <yuhaixin.yhx@linux.alibaba.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Forrington <nick.forrington@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rob Herring <robh@kernel.org>
Cc: Sohom Datta <sohomdatta1@gmail.com>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20230816114841.1679234-2-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/arm64/util/header.c | 67 ++++++++++++++++++++++-------
 1 file changed, 52 insertions(+), 15 deletions(-)

diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c
index 80b9f6287fe2..a2eef9ec5491 100644
--- a/tools/perf/arch/arm64/util/header.c
+++ b/tools/perf/arch/arm64/util/header.c
@@ -1,3 +1,6 @@
+#include <linux/kernel.h>
+#include <linux/bits.h>
+#include <linux/bitfield.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <perf/cpumap.h>
@@ -10,15 +13,14 @@
 
 #define MIDR "/regs/identification/midr_el1"
 #define MIDR_SIZE 19
-#define MIDR_REVISION_MASK      0xf
-#define MIDR_VARIANT_SHIFT      20
-#define MIDR_VARIANT_MASK       (0xf << MIDR_VARIANT_SHIFT)
+#define MIDR_REVISION_MASK      GENMASK(3, 0)
+#define MIDR_VARIANT_MASK	GENMASK(23, 20)
 
 static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus)
 {
 	const char *sysfs = sysfs__mountpoint();
-	u64 midr = 0;
 	int cpu;
+	int ret = EINVAL;
 
 	if (!sysfs || sz < MIDR_SIZE)
 		return EINVAL;
@@ -44,22 +46,13 @@ static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus)
 		}
 		fclose(file);
 
-		/* Ignore/clear Variant[23:20] and
-		 * Revision[3:0] of MIDR
-		 */
-		midr = strtoul(buf, NULL, 16);
-		midr &= (~(MIDR_VARIANT_MASK | MIDR_REVISION_MASK));
-		scnprintf(buf, MIDR_SIZE, "0x%016lx", midr);
 		/* got midr break loop */
+		ret = 0;
 		break;
 	}
 
 	perf_cpu_map__put(cpus);
-
-	if (!midr)
-		return EINVAL;
-
-	return 0;
+	return ret;
 }
 
 int get_cpuid(char *buf, size_t sz)
@@ -99,3 +92,47 @@ char *get_cpuid_str(struct perf_pmu *pmu)
 
 	return buf;
 }
+
+/*
+ * Return 0 if idstr is a higher or equal to version of the same part as
+ * mapcpuid. Therefore, if mapcpuid has 0 for revision and variant then any
+ * version of idstr will match as long as it's the same CPU type.
+ *
+ * Return 1 if the CPU type is different or the version of idstr is lower.
+ */
+int strcmp_cpuid_str(const char *mapcpuid, const char *idstr)
+{
+	u64 map_id = strtoull(mapcpuid, NULL, 16);
+	char map_id_variant = FIELD_GET(MIDR_VARIANT_MASK, map_id);
+	char map_id_revision = FIELD_GET(MIDR_REVISION_MASK, map_id);
+	u64 id = strtoull(idstr, NULL, 16);
+	char id_variant = FIELD_GET(MIDR_VARIANT_MASK, id);
+	char id_revision = FIELD_GET(MIDR_REVISION_MASK, id);
+	u64 id_fields = ~(MIDR_VARIANT_MASK | MIDR_REVISION_MASK);
+
+	/* Compare without version first */
+	if ((map_id & id_fields) != (id & id_fields))
+		return 1;
+
+	/*
+	 * ID matches, now compare version.
+	 *
+	 * Arm revisions (like r0p0) are compared here like two digit semver
+	 * values eg. 1.3 < 2.0 < 2.1 < 2.2.
+	 *
+	 *  r = high value = 'Variant' field in MIDR
+	 *  p = low value  = 'Revision' field in MIDR
+	 *
+	 */
+	if (id_variant > map_id_variant)
+		return 0;
+
+	if (id_variant == map_id_variant && id_revision >= map_id_revision)
+		return 0;
+
+	/*
+	 * variant is less than mapfile variant or variants are the same but
+	 * the revision doesn't match. Return no match.
+	 */
+	return 1;
+}

From 81f7da549af472180ac2635b4b335a01fd8ee866 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@arm.com>
Date: Wed, 16 Aug 2023 12:47:44 +0100
Subject: [PATCH 0506/1189] perf test: Add a test for the new Arm CPU ID
 comparison behavior

Now that variant and revision fields are taken into account the behavior
is slightly more complicated so add a test to ensure that this behaves
as expected.

Reviewed-by: John Garry <john.g.garry@oracle.com>
Signed-off-by: James Clark <james.clark@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Haixin Yu <yuhaixin.yhx@linux.alibaba.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Forrington <nick.forrington@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rob Herring <robh@kernel.org>
Cc: Sohom Datta <sohomdatta1@gmail.com>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20230816114841.1679234-3-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/arm64/include/arch-tests.h |  3 ++
 tools/perf/arch/arm64/tests/Build          |  1 +
 tools/perf/arch/arm64/tests/arch-tests.c   |  4 +++
 tools/perf/arch/arm64/tests/cpuid-match.c  | 37 ++++++++++++++++++++++
 4 files changed, 45 insertions(+)
 create mode 100644 tools/perf/arch/arm64/tests/cpuid-match.c

diff --git a/tools/perf/arch/arm64/include/arch-tests.h b/tools/perf/arch/arm64/include/arch-tests.h
index 452b3d904521..474d7cf5afbd 100644
--- a/tools/perf/arch/arm64/include/arch-tests.h
+++ b/tools/perf/arch/arm64/include/arch-tests.h
@@ -2,6 +2,9 @@
 #ifndef ARCH_TESTS_H
 #define ARCH_TESTS_H
 
+struct test_suite;
+
+int test__cpuid_match(struct test_suite *test, int subtest);
 extern struct test_suite *arch_tests[];
 
 #endif
diff --git a/tools/perf/arch/arm64/tests/Build b/tools/perf/arch/arm64/tests/Build
index a61c06bdb757..e337c09e7f56 100644
--- a/tools/perf/arch/arm64/tests/Build
+++ b/tools/perf/arch/arm64/tests/Build
@@ -2,3 +2,4 @@ perf-y += regs_load.o
 perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
 
 perf-y += arch-tests.o
+perf-y += cpuid-match.o
diff --git a/tools/perf/arch/arm64/tests/arch-tests.c b/tools/perf/arch/arm64/tests/arch-tests.c
index ad16b4f8f63e..74932e72c727 100644
--- a/tools/perf/arch/arm64/tests/arch-tests.c
+++ b/tools/perf/arch/arm64/tests/arch-tests.c
@@ -3,9 +3,13 @@
 #include "tests/tests.h"
 #include "arch-tests.h"
 
+
+DEFINE_SUITE("arm64 CPUID matching", cpuid_match);
+
 struct test_suite *arch_tests[] = {
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 	&suite__dwarf_unwind,
 #endif
+	&suite__cpuid_match,
 	NULL,
 };
diff --git a/tools/perf/arch/arm64/tests/cpuid-match.c b/tools/perf/arch/arm64/tests/cpuid-match.c
new file mode 100644
index 000000000000..e8e3947cca18
--- /dev/null
+++ b/tools/perf/arch/arm64/tests/cpuid-match.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/compiler.h>
+
+#include "arch-tests.h"
+#include "tests/tests.h"
+#include "util/header.h"
+
+int test__cpuid_match(struct test_suite *test __maybe_unused,
+			     int subtest __maybe_unused)
+{
+	/* midr with no leading zeros matches */
+	if (strcmp_cpuid_str("0x410fd0c0", "0x00000000410fd0c0"))
+		return -1;
+	/* Upper case matches */
+	if (strcmp_cpuid_str("0x410fd0c0", "0x00000000410FD0C0"))
+		return -1;
+	/* r0p0 = r0p0 matches */
+	if (strcmp_cpuid_str("0x00000000410fd480", "0x00000000410fd480"))
+		return -1;
+	/* r0p1 > r0p0 matches */
+	if (strcmp_cpuid_str("0x00000000410fd480", "0x00000000410fd481"))
+		return -1;
+	/* r1p0 > r0p0 matches*/
+	if (strcmp_cpuid_str("0x00000000410fd480", "0x00000000411fd480"))
+		return -1;
+	/* r0p0 < r0p1 doesn't match */
+	if (!strcmp_cpuid_str("0x00000000410fd481", "0x00000000410fd480"))
+		return -1;
+	/* r0p0 < r1p0 doesn't match */
+	if (!strcmp_cpuid_str("0x00000000411fd480", "0x00000000410fd480"))
+		return -1;
+	/* Different CPU doesn't match */
+	if (!strcmp_cpuid_str("0x00000000410fd4c0", "0x00000000430f0af0"))
+		return -1;
+
+	return 0;
+}

From 9d5da30e4ae9910ed5dd15636534a22a46f0066f Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@arm.com>
Date: Wed, 16 Aug 2023 12:47:46 +0100
Subject: [PATCH 0507/1189] perf jevents: Add a new expression builtin
 strcmp_cpuid_str()

This will allow writing formulas that are conditional on a specific
CPU type or CPU version. It calls through to the existing
strcmp_cpuid_str() function in Perf which has a default weak version,
and an arch specific version for x86 and arm64.

The function takes an 'ID' type value, which is a string. But in this
case Arm CPU IDs are hex numbers prefixed with '0x'. metric.py
assumes strings are only used by event names, and that they can't start
with a number ('0'), so an additional change has to be made to the
regex to convert hex numbers back to 'ID' types.

Signed-off-by: James Clark <james.clark@arm.com>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Haixin Yu <yuhaixin.yhx@linux.alibaba.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Forrington <nick.forrington@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rob Herring <robh@kernel.org>
Cc: Sohom Datta <sohomdatta1@gmail.com>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20230816114841.1679234-5-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/arm64/util/pmu.c | 18 +-----------------
 tools/perf/pmu-events/metric.py  | 17 +++++++++++++++--
 tools/perf/util/expr.c           | 18 ++++++++++++++++++
 tools/perf/util/expr.h           |  1 +
 tools/perf/util/expr.l           |  1 +
 tools/perf/util/expr.y           |  8 +++++++-
 tools/perf/util/pmu.c            | 17 +++++++++++++++++
 tools/perf/util/pmu.h            |  1 +
 8 files changed, 61 insertions(+), 20 deletions(-)

diff --git a/tools/perf/arch/arm64/util/pmu.c b/tools/perf/arch/arm64/util/pmu.c
index 512a8f13c4de..615084eb88d8 100644
--- a/tools/perf/arch/arm64/util/pmu.c
+++ b/tools/perf/arch/arm64/util/pmu.c
@@ -2,28 +2,12 @@
 
 #include <internal/cpumap.h>
 #include "../../../util/cpumap.h"
+#include "../../../util/header.h"
 #include "../../../util/pmu.h"
 #include "../../../util/pmus.h"
 #include <api/fs/fs.h>
 #include <math.h>
 
-static struct perf_pmu *pmu__find_core_pmu(void)
-{
-	struct perf_pmu *pmu = NULL;
-
-	while ((pmu = perf_pmus__scan_core(pmu))) {
-		/*
-		 * The cpumap should cover all CPUs. Otherwise, some CPUs may
-		 * not support some events or have different event IDs.
-		 */
-		if (RC_CHK_ACCESS(pmu->cpus)->nr != cpu__max_cpu().cpu)
-			return NULL;
-
-		return pmu;
-	}
-	return NULL;
-}
-
 const struct pmu_metrics_table *pmu_metrics_table__find(void)
 {
 	struct perf_pmu *pmu = pmu__find_core_pmu();
diff --git a/tools/perf/pmu-events/metric.py b/tools/perf/pmu-events/metric.py
index 85a3545f5b6a..0e9ec65d92ae 100644
--- a/tools/perf/pmu-events/metric.py
+++ b/tools/perf/pmu-events/metric.py
@@ -413,6 +413,10 @@ def has_event(event: Event) -> Function:
   # pylint: disable=invalid-name
   return Function('has_event', event)
 
+def strcmp_cpuid_str(event: str) -> Function:
+  # pylint: disable=redefined-builtin
+  # pylint: disable=invalid-name
+  return Function('strcmp_cpuid_str', event)
 
 class Metric:
   """An individual metric that will specifiable on the perf command line."""
@@ -541,14 +545,23 @@ def ParsePerfJson(orig: str) -> Expression:
   """
   # pylint: disable=eval-used
   py = orig.strip()
+  # First try to convert everything that looks like a string (event name) into Event(r"EVENT_NAME").
+  # This isn't very selective so is followed up by converting some unwanted conversions back again
   py = re.sub(r'([a-zA-Z][^-+/\* \\\(\),]*(?:\\.[^-+/\* \\\(\),]*)*)',
               r'Event(r"\1")', py)
+  # If it started with a # it should have been a literal, rather than an event name
   py = re.sub(r'#Event\(r"([^"]*)"\)', r'Literal("#\1")', py)
+  # Convert accidentally converted hex constants ("0Event(r"xDEADBEEF)"") back to a constant,
+  # but keep it wrapped in Event(), otherwise Python drops the 0x prefix and it gets interpreted as
+  # a double by the Bison parser
+  py = re.sub(r'0Event\(r"[xX]([0-9a-fA-F]*)"\)', r'Event("0x\1")', py)
+  # Convert accidentally converted scientific notation constants back
   py = re.sub(r'([0-9]+)Event\(r"(e[0-9]+)"\)', r'\1\2', py)
-  keywords = ['if', 'else', 'min', 'max', 'd_ratio', 'source_count', 'has_event']
+  # Convert all the known keywords back from events to just the keyword
+  keywords = ['if', 'else', 'min', 'max', 'd_ratio', 'source_count', 'has_event', 'strcmp_cpuid_str',
+              'cpuid_not_more_than']
   for kw in keywords:
     py = re.sub(rf'Event\(r"{kw}"\)', kw, py)
-
   try:
     parsed = ast.parse(py, mode='eval')
   except SyntaxError as e:
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index 7410a165f68b..0985a3cbc6f9 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -13,6 +13,8 @@
 #include <util/expr-bison.h>
 #include <util/expr-flex.h>
 #include "util/hashmap.h"
+#include "util/header.h"
+#include "util/pmu.h"
 #include "smt.h"
 #include "tsc.h"
 #include <api/fs/fs.h>
@@ -495,3 +497,19 @@ double expr__has_event(const struct expr_parse_ctx *ctx, bool compute_ids, const
 	evlist__delete(tmp);
 	return ret;
 }
+
+double expr__strcmp_cpuid_str(const struct expr_parse_ctx *ctx __maybe_unused,
+		       bool compute_ids __maybe_unused, const char *test_id)
+{
+	double ret;
+	struct perf_pmu *pmu = pmu__find_core_pmu();
+	char *cpuid = perf_pmu__getcpuid(pmu);
+
+	if (!cpuid)
+		return NAN;
+
+	ret = !strcmp_cpuid_str(test_id, cpuid);
+
+	free(cpuid);
+	return ret;
+}
diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h
index 3c1e49b3e35d..c0cec29ddc29 100644
--- a/tools/perf/util/expr.h
+++ b/tools/perf/util/expr.h
@@ -55,5 +55,6 @@ double expr_id_data__value(const struct expr_id_data *data);
 double expr_id_data__source_count(const struct expr_id_data *data);
 double expr__get_literal(const char *literal, const struct expr_scanner_ctx *ctx);
 double expr__has_event(const struct expr_parse_ctx *ctx, bool compute_ids, const char *id);
+double expr__strcmp_cpuid_str(const struct expr_parse_ctx *ctx, bool compute_ids, const char *id);
 
 #endif
diff --git a/tools/perf/util/expr.l b/tools/perf/util/expr.l
index dbb117414710..0feef0726c48 100644
--- a/tools/perf/util/expr.l
+++ b/tools/perf/util/expr.l
@@ -114,6 +114,7 @@ if		{ return IF; }
 else		{ return ELSE; }
 source_count	{ return SOURCE_COUNT; }
 has_event	{ return HAS_EVENT; }
+strcmp_cpuid_str	{ return STRCMP_CPUID_STR; }
 {literal}	{ return literal(yyscanner, sctx); }
 {number}	{ return value(yyscanner); }
 {symbol}	{ return str(yyscanner, ID, sctx->runtime); }
diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y
index 65d54a6f29ad..6c93b358cc2d 100644
--- a/tools/perf/util/expr.y
+++ b/tools/perf/util/expr.y
@@ -39,7 +39,7 @@ int expr_lex(YYSTYPE * yylval_param , void *yyscanner);
 	} ids;
 }
 
-%token ID NUMBER MIN MAX IF ELSE LITERAL D_RATIO SOURCE_COUNT HAS_EVENT EXPR_ERROR
+%token ID NUMBER MIN MAX IF ELSE LITERAL D_RATIO SOURCE_COUNT HAS_EVENT STRCMP_CPUID_STR EXPR_ERROR
 %left MIN MAX IF
 %left '|'
 %left '^'
@@ -207,6 +207,12 @@ expr: NUMBER
 	$$.ids = NULL;
 	free($3);
 }
+| STRCMP_CPUID_STR '(' ID ')'
+{
+	$$.val = expr__strcmp_cpuid_str(ctx, compute_ids, $3);
+	$$.ids = NULL;
+	free($3);
+}
 | expr '|' expr
 {
 	if (is_const($1.val) && is_const($3.val)) {
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index d5406effc169..a7f05e4dda97 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1790,3 +1790,20 @@ void perf_pmu__delete(struct perf_pmu *pmu)
 	zfree(&pmu->alias_name);
 	free(pmu);
 }
+
+struct perf_pmu *pmu__find_core_pmu(void)
+{
+	struct perf_pmu *pmu = NULL;
+
+	while ((pmu = perf_pmus__scan_core(pmu))) {
+		/*
+		 * The cpumap should cover all CPUs. Otherwise, some CPUs may
+		 * not support some events or have different event IDs.
+		 */
+		if (RC_CHK_ACCESS(pmu->cpus)->nr != cpu__max_cpu().cpu)
+			return NULL;
+
+		return pmu;
+	}
+	return NULL;
+}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 6b414cecbad2..7ff925224165 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -289,5 +289,6 @@ int perf_pmu__pathname_fd(int dirfd, const char *pmu_name, const char *filename,
 struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *lookup_name);
 struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pmus);
 void perf_pmu__delete(struct perf_pmu *pmu);
+struct perf_pmu *pmu__find_core_pmu(void);
 
 #endif /* __PMU_H */

From d43f5491210197196458c1454f2be0eb66d3e4d1 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@arm.com>
Date: Wed, 16 Aug 2023 12:47:47 +0100
Subject: [PATCH 0508/1189] perf vendor events arm64: Update stall_slot
 workaround for N2 r0p3

N2 r0p3 doesn't require the workaround [1], so gating on (#slots - 5) no
longer works because all N2s have 5 slots. Use the new expression
builtin that allows calling strcmp_cpuid_str() and comparing CPUIDs in
metric formulas.

In this case, the commented formula looks like this:

  strcmp_cpuid_str(0x410fd493)        # greater than or equal to N2 r0p3
  | strcmp_cpuid_str(0x410fd490) ^ 1  # OR NOT any version of N2

[1]: https://gitlab.arm.com/telemetry-solution/telemetry-solution/-/blob/main/data/pmu/cpu/neoverse/neoverse-n2-r0p3.json

Signed-off-by: James Clark <james.clark@arm.com>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Haixin Yu <yuhaixin.yhx@linux.alibaba.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Forrington <nick.forrington@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rob Herring <robh@kernel.org>
Cc: Sohom Datta <sohomdatta1@gmail.com>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20230816114841.1679234-6-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json
index 8ad15b726dca..9757cc178bdf 100644
--- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json
@@ -1,15 +1,15 @@
 [
     {
         "ArchStdEvent": "FRONTEND_BOUND",
-        "MetricExpr": "((stall_slot_frontend) if (#slots - 5) else (stall_slot_frontend - cpu_cycles)) / (#slots * cpu_cycles)"
+        "MetricExpr": "((stall_slot_frontend) if (strcmp_cpuid_str(0x410fd493) | strcmp_cpuid_str(0x410fd490) ^ 1) else (stall_slot_frontend - cpu_cycles)) / (#slots * cpu_cycles)"
     },
     {
         "ArchStdEvent": "BAD_SPECULATION",
-        "MetricExpr": "(1 - op_retired / op_spec) * (1 - (stall_slot if (#slots - 5) else (stall_slot - cpu_cycles)) / (#slots * cpu_cycles))"
+        "MetricExpr": "(1 - op_retired / op_spec) * (1 - (stall_slot if (strcmp_cpuid_str(0x410fd493) | strcmp_cpuid_str(0x410fd490) ^ 1) else (stall_slot - cpu_cycles)) / (#slots * cpu_cycles))"
     },
     {
         "ArchStdEvent": "RETIRING",
-        "MetricExpr": "(op_retired / op_spec) * (1 - (stall_slot if (#slots - 5) else (stall_slot - cpu_cycles)) / (#slots * cpu_cycles))"
+        "MetricExpr": "(op_retired / op_spec) * (1 - (stall_slot if (strcmp_cpuid_str(0x410fd493) | strcmp_cpuid_str(0x410fd490) ^ 1) else (stall_slot - cpu_cycles)) / (#slots * cpu_cycles))"
     },
     {
         "ArchStdEvent": "BACKEND_BOUND"
@@ -201,7 +201,7 @@
         "ScaleUnit": "100%"
     },
     {
-        "MetricExpr": "OP_RETIRED / OP_SPEC * (1 - (STALL_SLOT if (#slots - 5) else (STALL_SLOT - CPU_CYCLES)) / (#slots * CPU_CYCLES))",
+        "MetricExpr": "OP_RETIRED / OP_SPEC * (1 - (STALL_SLOT if (strcmp_cpuid_str(0x410fd493) | strcmp_cpuid_str(0x410fd490) ^ 1) else (STALL_SLOT - CPU_CYCLES)) / (#slots * CPU_CYCLES))",
         "BriefDescription": "The truly effective ratio of micro-operations executed by the CPU, which means that misprediction and stall are not included",
         "MetricGroup": "PEutilization",
         "MetricName": "cpu_utilization",

From 4473949074c35072f598bd525ae51d5455f05745 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@arm.com>
Date: Wed, 16 Aug 2023 12:47:48 +0100
Subject: [PATCH 0509/1189] perf vendor events arm64: Update N2 and V2 metrics
 and events using Arm telemetry repo

Apart from some slight naming and grouping differences, the new metrics
are functionally the same as the existing ones. Any missing metrics were
manually appended to the end of the auto generated file.

For the events, the new data includes descriptions that may have product
specific details and new groupings that will be consistent with other
products.

After generating the metrics from the telemetry repo [1], the following
manual steps were performed:

 * Change the topdown expressions to compare on CPUID and use
   #slots so that the same data can be shared between N2 and V2. Apart
   from these modifications, the expressions now match more closely with
   the Arm telemetry data which will hopefully make future updates
   easier.

 * Append some metrics from the old N2/V2 data that aren't present in
   the telemetry data. These will possibly be added to the
   telemetry-solution repo at a later time:

    l3d_cache_mpki, l3d_cache_miss_rate, branch_pki, ipc_rate, spec_ipc,
    retired_rate, wasted_rate, branch_immed_spec_rate,
    branch_return_spec_rate, branch_indirect_spec_rate

[1]: https://gitlab.arm.com/telemetry-solution/telemetry-solution/-/blob/main/data/pmu/cpu/neoverse/neoverse-n2.json

Signed-off-by: James Clark <james.clark@arm.com>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Haixin Yu <yuhaixin.yhx@linux.alibaba.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Forrington <nick.forrington@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rob Herring <robh@kernel.org>
Cc: Sohom Datta <sohomdatta1@gmail.com>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20230816114841.1679234-7-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../arch/arm64/arm/neoverse-n2-v2/branch.json |   8 -
 .../arch/arm64/arm/neoverse-n2-v2/bus.json    |  18 +-
 .../arch/arm64/arm/neoverse-n2-v2/cache.json  | 155 -------
 .../arm64/arm/neoverse-n2-v2/exception.json   |  45 +-
 .../arm/neoverse-n2-v2/fp_operation.json      |  22 +
 .../arm64/arm/neoverse-n2-v2/general.json     |  10 +
 .../arm64/arm/neoverse-n2-v2/instruction.json | 143 -------
 .../arm64/arm/neoverse-n2-v2/l1d_cache.json   |  54 +++
 .../arm64/arm/neoverse-n2-v2/l1i_cache.json   |  14 +
 .../arm64/arm/neoverse-n2-v2/l2_cache.json    |  50 +++
 .../arm64/arm/neoverse-n2-v2/l3_cache.json    |  22 +
 .../arm64/arm/neoverse-n2-v2/ll_cache.json    |  10 +
 .../arch/arm64/arm/neoverse-n2-v2/memory.json |  39 +-
 .../arm64/arm/neoverse-n2-v2/metrics.json     | 387 ++++++++++--------
 .../arm64/arm/neoverse-n2-v2/pipeline.json    |  23 --
 .../arm64/arm/neoverse-n2-v2/retired.json     |  30 ++
 .../arch/arm64/arm/neoverse-n2-v2/spe.json    |  12 +-
 .../arm/neoverse-n2-v2/spec_operation.json    | 110 +++++
 .../arch/arm64/arm/neoverse-n2-v2/stall.json  |  30 ++
 .../arch/arm64/arm/neoverse-n2-v2/sve.json    |  50 +++
 .../arch/arm64/arm/neoverse-n2-v2/tlb.json    |  66 +++
 .../arch/arm64/arm/neoverse-n2-v2/trace.json  |  27 +-
 22 files changed, 763 insertions(+), 562 deletions(-)
 delete mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/branch.json
 delete mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/cache.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/fp_operation.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/general.json
 delete mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/instruction.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l1d_cache.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l1i_cache.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l2_cache.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l3_cache.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/ll_cache.json
 delete mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/pipeline.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/retired.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/spec_operation.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/stall.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/sve.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/tlb.json

diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/branch.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/branch.json
deleted file mode 100644
index 79f2016c53b0..000000000000
--- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/branch.json
+++ /dev/null
@@ -1,8 +0,0 @@
-[
-    {
-        "ArchStdEvent": "BR_MIS_PRED"
-    },
-    {
-        "ArchStdEvent": "BR_PRED"
-    }
-]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/bus.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/bus.json
index 579c1c993d17..2e11a8c4a484 100644
--- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/bus.json
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/bus.json
@@ -1,20 +1,18 @@
 [
     {
-        "ArchStdEvent": "CPU_CYCLES"
+        "ArchStdEvent": "BUS_ACCESS",
+        "PublicDescription": "Counts memory transactions issued by the CPU to the external bus, including snoop requests and snoop responses. Each beat of data is counted individually."
     },
     {
-        "ArchStdEvent": "BUS_ACCESS"
+        "ArchStdEvent": "BUS_CYCLES",
+        "PublicDescription": "Counts bus cycles in the CPU. Bus cycles represent a clock cycle in which a transaction could be sent or received on the interface from the CPU to the external bus. Since that interface is driven at the same clock speed as the CPU, this event is a duplicate of CPU_CYCLES."
     },
     {
-        "ArchStdEvent": "BUS_CYCLES"
+        "ArchStdEvent": "BUS_ACCESS_RD",
+        "PublicDescription": "Counts memory read transactions seen on the external bus. Each beat of data is counted individually."
     },
     {
-        "ArchStdEvent": "BUS_ACCESS_RD"
-    },
-    {
-        "ArchStdEvent": "BUS_ACCESS_WR"
-    },
-    {
-        "ArchStdEvent": "CNT_CYCLES"
+        "ArchStdEvent": "BUS_ACCESS_WR",
+        "PublicDescription": "Counts memory write transactions seen on the external bus. Each beat of data is counted individually."
     }
 ]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/cache.json
deleted file mode 100644
index 0141f749bff3..000000000000
--- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/cache.json
+++ /dev/null
@@ -1,155 +0,0 @@
-[
-    {
-        "ArchStdEvent": "L1I_CACHE_REFILL"
-    },
-    {
-        "ArchStdEvent": "L1I_TLB_REFILL"
-    },
-    {
-        "ArchStdEvent": "L1D_CACHE_REFILL"
-    },
-    {
-        "ArchStdEvent": "L1D_CACHE"
-    },
-    {
-        "ArchStdEvent": "L1D_TLB_REFILL"
-    },
-    {
-        "ArchStdEvent": "L1I_CACHE"
-    },
-    {
-        "ArchStdEvent": "L1D_CACHE_WB"
-    },
-    {
-        "ArchStdEvent": "L2D_CACHE"
-    },
-    {
-        "ArchStdEvent": "L2D_CACHE_REFILL"
-    },
-    {
-        "ArchStdEvent": "L2D_CACHE_WB"
-    },
-    {
-        "ArchStdEvent": "L2D_CACHE_ALLOCATE"
-    },
-    {
-        "ArchStdEvent": "L1D_TLB"
-    },
-    {
-        "ArchStdEvent": "L1I_TLB"
-    },
-    {
-        "ArchStdEvent": "L3D_CACHE_ALLOCATE"
-    },
-    {
-        "ArchStdEvent": "L3D_CACHE_REFILL"
-    },
-    {
-        "ArchStdEvent": "L3D_CACHE"
-    },
-    {
-        "ArchStdEvent": "L2D_TLB_REFILL"
-    },
-    {
-        "ArchStdEvent": "L2D_TLB"
-    },
-    {
-        "ArchStdEvent": "DTLB_WALK"
-    },
-    {
-        "ArchStdEvent": "ITLB_WALK"
-    },
-    {
-        "ArchStdEvent": "LL_CACHE_RD"
-    },
-    {
-        "ArchStdEvent": "LL_CACHE_MISS_RD"
-    },
-    {
-        "ArchStdEvent": "L1D_CACHE_LMISS_RD"
-    },
-    {
-        "ArchStdEvent": "L1D_CACHE_RD"
-    },
-    {
-        "ArchStdEvent": "L1D_CACHE_WR"
-    },
-    {
-        "ArchStdEvent": "L1D_CACHE_REFILL_RD"
-    },
-    {
-        "ArchStdEvent": "L1D_CACHE_REFILL_WR"
-    },
-    {
-        "ArchStdEvent": "L1D_CACHE_REFILL_INNER"
-    },
-    {
-        "ArchStdEvent": "L1D_CACHE_REFILL_OUTER"
-    },
-    {
-        "ArchStdEvent": "L1D_CACHE_WB_VICTIM"
-    },
-    {
-        "ArchStdEvent": "L1D_CACHE_WB_CLEAN"
-    },
-    {
-        "ArchStdEvent": "L1D_CACHE_INVAL"
-    },
-    {
-        "ArchStdEvent": "L1D_TLB_REFILL_RD"
-    },
-    {
-        "ArchStdEvent": "L1D_TLB_REFILL_WR"
-    },
-    {
-        "ArchStdEvent": "L1D_TLB_RD"
-    },
-    {
-        "ArchStdEvent": "L1D_TLB_WR"
-    },
-    {
-        "ArchStdEvent": "L2D_CACHE_RD"
-    },
-    {
-        "ArchStdEvent": "L2D_CACHE_WR"
-    },
-    {
-        "ArchStdEvent": "L2D_CACHE_REFILL_RD"
-    },
-    {
-        "ArchStdEvent": "L2D_CACHE_REFILL_WR"
-    },
-    {
-        "ArchStdEvent": "L2D_CACHE_WB_VICTIM"
-    },
-    {
-        "ArchStdEvent": "L2D_CACHE_WB_CLEAN"
-    },
-    {
-        "ArchStdEvent": "L2D_CACHE_INVAL"
-    },
-    {
-        "ArchStdEvent": "L2D_TLB_REFILL_RD"
-    },
-    {
-        "ArchStdEvent": "L2D_TLB_REFILL_WR"
-    },
-    {
-        "ArchStdEvent": "L2D_TLB_RD"
-    },
-    {
-        "ArchStdEvent": "L2D_TLB_WR"
-    },
-    {
-        "ArchStdEvent": "L3D_CACHE_RD"
-    },
-    {
-        "ArchStdEvent": "L1I_CACHE_LMISS"
-    },
-    {
-        "ArchStdEvent": "L2D_CACHE_LMISS_RD"
-    },
-    {
-        "ArchStdEvent": "L3D_CACHE_LMISS_RD"
-    }
-]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/exception.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/exception.json
index 344a2d552ad5..4404b8e91690 100644
--- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/exception.json
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/exception.json
@@ -1,47 +1,62 @@
 [
     {
-        "ArchStdEvent": "EXC_TAKEN"
+        "ArchStdEvent": "EXC_TAKEN",
+        "PublicDescription": "Counts any taken architecturally visible exceptions such as IRQ, FIQ, SError, and other synchronous exceptions. Exceptions are counted whether or not they are taken locally."
     },
     {
-        "ArchStdEvent": "MEMORY_ERROR"
+        "ArchStdEvent": "EXC_RETURN",
+        "PublicDescription": "Counts any architecturally executed exception return instructions. Eg: AArch64: ERET"
     },
     {
-        "ArchStdEvent": "EXC_UNDEF"
+        "ArchStdEvent": "EXC_UNDEF",
+        "PublicDescription": "Counts the number of synchronous exceptions which are taken locally that are due to attempting to execute an instruction that is UNDEFINED. Attempting to execute instruction bit patterns that have not been allocated. Attempting to execute instructions when they are disabled. Attempting to execute instructions at an inappropriate Exception level. Attempting to execute an instruction when the value of PSTATE.IL is 1."
     },
     {
-        "ArchStdEvent": "EXC_SVC"
+        "ArchStdEvent": "EXC_SVC",
+        "PublicDescription": "Counts SVC exceptions taken locally."
     },
     {
-        "ArchStdEvent": "EXC_PABORT"
+        "ArchStdEvent": "EXC_PABORT",
+        "PublicDescription": "Counts synchronous exceptions that are taken locally and caused by Instruction Aborts."
     },
     {
-        "ArchStdEvent": "EXC_DABORT"
+        "ArchStdEvent": "EXC_DABORT",
+        "PublicDescription": "Counts exceptions that are taken locally and are caused by data aborts or SErrors. Conditions that could cause those exceptions are attempting to read or write memory where the MMU generates a fault, attempting to read or write memory with a misaligned address, interrupts from the nSEI inputs and internally generated SErrors."
     },
     {
-        "ArchStdEvent": "EXC_IRQ"
+        "ArchStdEvent": "EXC_IRQ",
+        "PublicDescription": "Counts IRQ exceptions including the virtual IRQs that are taken locally."
     },
     {
-        "ArchStdEvent": "EXC_FIQ"
+        "ArchStdEvent": "EXC_FIQ",
+        "PublicDescription": "Counts FIQ exceptions including the virtual FIQs that are taken locally."
     },
     {
-        "ArchStdEvent": "EXC_SMC"
+        "ArchStdEvent": "EXC_SMC",
+        "PublicDescription": "Counts SMC exceptions take to EL3."
     },
     {
-        "ArchStdEvent": "EXC_HVC"
+        "ArchStdEvent": "EXC_HVC",
+        "PublicDescription": "Counts HVC exceptions taken to EL2."
     },
     {
-        "ArchStdEvent": "EXC_TRAP_PABORT"
+        "ArchStdEvent": "EXC_TRAP_PABORT",
+        "PublicDescription": "Counts exceptions which are traps not taken locally and are caused by Instruction Aborts. For example, attempting to execute an instruction with a misaligned PC."
     },
     {
-        "ArchStdEvent": "EXC_TRAP_DABORT"
+        "ArchStdEvent": "EXC_TRAP_DABORT",
+        "PublicDescription": "Counts exceptions which are traps not taken locally and are caused by Data Aborts or SError interrupts. Conditions that could cause those exceptions are:\n\n1. Attempting to read or write memory where the MMU generates a fault,\n2. Attempting to read or write memory with a misaligned address,\n3. Interrupts from the SEI input.\n4. internally generated SErrors."
     },
     {
-        "ArchStdEvent": "EXC_TRAP_OTHER"
+        "ArchStdEvent": "EXC_TRAP_OTHER",
+        "PublicDescription": "Counts the number of synchronous trap exceptions which are not taken locally and are not SVC, SMC, HVC, data aborts, Instruction Aborts, or interrupts."
     },
     {
-        "ArchStdEvent": "EXC_TRAP_IRQ"
+        "ArchStdEvent": "EXC_TRAP_IRQ",
+        "PublicDescription": "Counts IRQ exceptions including the virtual IRQs that are not taken locally."
     },
     {
-        "ArchStdEvent": "EXC_TRAP_FIQ"
+        "ArchStdEvent": "EXC_TRAP_FIQ",
+        "PublicDescription": "Counts FIQs which are not taken locally but taken from EL0, EL1,\n or EL2 to EL3 (which would be the normal behavior for FIQs when not executing\n in EL3)."
     }
 ]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/fp_operation.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/fp_operation.json
new file mode 100644
index 000000000000..cec3435ac766
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/fp_operation.json
@@ -0,0 +1,22 @@
+[
+    {
+        "ArchStdEvent": "FP_HP_SPEC",
+        "PublicDescription": "Counts speculatively executed half precision floating point operations."
+    },
+    {
+        "ArchStdEvent": "FP_SP_SPEC",
+        "PublicDescription": "Counts speculatively executed single precision floating point operations."
+    },
+    {
+        "ArchStdEvent": "FP_DP_SPEC",
+        "PublicDescription": "Counts speculatively executed double precision floating point operations."
+    },
+    {
+        "ArchStdEvent": "FP_SCALE_OPS_SPEC",
+        "PublicDescription": "Counts speculatively executed scalable single precision floating point operations."
+    },
+    {
+        "ArchStdEvent": "FP_FIXED_OPS_SPEC",
+        "PublicDescription": "Counts speculatively executed non-scalable single precision floating point operations."
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/general.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/general.json
new file mode 100644
index 000000000000..428810f855b8
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/general.json
@@ -0,0 +1,10 @@
+[
+    {
+        "ArchStdEvent": "CPU_CYCLES",
+        "PublicDescription": "Counts CPU clock cycles (not timer cycles). The clock measured by this event is defined as the physical clock driving the CPU logic."
+    },
+    {
+        "ArchStdEvent": "CNT_CYCLES",
+        "PublicDescription": "Counts constant frequency cycles"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/instruction.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/instruction.json
deleted file mode 100644
index e57cd55937c6..000000000000
--- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/instruction.json
+++ /dev/null
@@ -1,143 +0,0 @@
-[
-    {
-        "ArchStdEvent": "SW_INCR"
-    },
-    {
-        "ArchStdEvent": "INST_RETIRED"
-    },
-    {
-        "ArchStdEvent": "EXC_RETURN"
-    },
-    {
-        "ArchStdEvent": "CID_WRITE_RETIRED"
-    },
-    {
-        "ArchStdEvent": "INST_SPEC"
-    },
-    {
-        "ArchStdEvent": "TTBR_WRITE_RETIRED"
-    },
-    {
-        "ArchStdEvent": "BR_RETIRED"
-    },
-    {
-        "ArchStdEvent": "BR_MIS_PRED_RETIRED"
-    },
-    {
-        "ArchStdEvent": "OP_RETIRED"
-    },
-    {
-        "ArchStdEvent": "OP_SPEC"
-    },
-    {
-        "ArchStdEvent": "LDREX_SPEC"
-    },
-    {
-        "ArchStdEvent": "STREX_PASS_SPEC"
-    },
-    {
-        "ArchStdEvent": "STREX_FAIL_SPEC"
-    },
-    {
-        "ArchStdEvent": "STREX_SPEC"
-    },
-    {
-        "ArchStdEvent": "LD_SPEC"
-    },
-    {
-        "ArchStdEvent": "ST_SPEC"
-    },
-    {
-        "ArchStdEvent": "DP_SPEC"
-    },
-    {
-        "ArchStdEvent": "ASE_SPEC"
-    },
-    {
-        "ArchStdEvent": "VFP_SPEC"
-    },
-    {
-        "ArchStdEvent": "PC_WRITE_SPEC"
-    },
-    {
-        "ArchStdEvent": "CRYPTO_SPEC"
-    },
-    {
-        "ArchStdEvent": "BR_IMMED_SPEC"
-    },
-    {
-        "ArchStdEvent": "BR_RETURN_SPEC"
-    },
-    {
-        "ArchStdEvent": "BR_INDIRECT_SPEC"
-    },
-    {
-        "ArchStdEvent": "ISB_SPEC"
-    },
-    {
-        "ArchStdEvent": "DSB_SPEC"
-    },
-    {
-        "ArchStdEvent": "DMB_SPEC"
-    },
-    {
-        "ArchStdEvent": "RC_LD_SPEC"
-    },
-    {
-        "ArchStdEvent": "RC_ST_SPEC"
-    },
-    {
-        "ArchStdEvent": "ASE_INST_SPEC"
-    },
-    {
-        "ArchStdEvent": "SVE_INST_SPEC"
-    },
-    {
-        "ArchStdEvent": "FP_HP_SPEC"
-    },
-    {
-        "ArchStdEvent": "FP_SP_SPEC"
-    },
-    {
-        "ArchStdEvent": "FP_DP_SPEC"
-    },
-    {
-        "ArchStdEvent": "SVE_PRED_SPEC"
-    },
-    {
-        "ArchStdEvent": "SVE_PRED_EMPTY_SPEC"
-    },
-    {
-        "ArchStdEvent": "SVE_PRED_FULL_SPEC"
-    },
-    {
-        "ArchStdEvent": "SVE_PRED_PARTIAL_SPEC"
-    },
-    {
-        "ArchStdEvent": "SVE_PRED_NOT_FULL_SPEC"
-    },
-    {
-        "ArchStdEvent": "SVE_LDFF_SPEC"
-    },
-    {
-        "ArchStdEvent": "SVE_LDFF_FAULT_SPEC"
-    },
-    {
-        "ArchStdEvent": "FP_SCALE_OPS_SPEC"
-    },
-    {
-        "ArchStdEvent": "FP_FIXED_OPS_SPEC"
-    },
-    {
-        "ArchStdEvent": "ASE_SVE_INT8_SPEC"
-    },
-    {
-        "ArchStdEvent": "ASE_SVE_INT16_SPEC"
-    },
-    {
-        "ArchStdEvent": "ASE_SVE_INT32_SPEC"
-    },
-    {
-        "ArchStdEvent": "ASE_SVE_INT64_SPEC"
-    }
-]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l1d_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l1d_cache.json
new file mode 100644
index 000000000000..da7c129f2569
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l1d_cache.json
@@ -0,0 +1,54 @@
+[
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL",
+        "PublicDescription": "Counts level 1 data cache refills caused by speculatively executed load or store operations that missed in the level 1 data cache. This event only counts one event per cache line. This event does not count cache line allocations from preload instructions or from hardware cache prefetching."
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE",
+        "PublicDescription": "Counts level 1 data cache accesses from any load/store operations. Atomic operations that resolve in the CPUs caches (near atomic operations) count as both a write access and read access. Each access to a cache line is counted including the multiple accesses caused by single instructions such as LDM or STM. Each access to other level 1 data or unified memory structures, for example refill buffers, write buffers, and write-back buffers, are also counted."
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WB",
+        "PublicDescription": "Counts write-backs of dirty data from the L1 data cache to the L2 cache. This occurs when either a dirty cache line is evicted from L1 data cache and allocated in the L2 cache or dirty data is written to the L2 and possibly to the next level of cache. This event counts both victim cache line evictions and cache write-backs from snoops or cache maintenance operations. The following cache operations are not counted:\n\n1. Invalidations which do not result in data being transferred out of the L1 (such as evictions of clean data),\n2. Full line writes which write to L2 without writing L1, such as write streaming mode."
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_LMISS_RD",
+        "PublicDescription": "Counts cache line refills into the level 1 data cache from any memory read operations, that incurred additional latency."
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_RD",
+        "PublicDescription": "Counts level 1 data cache accesses from any load operation. Atomic load operations that resolve in the CPUs caches count as both a write access and read access."
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WR",
+        "PublicDescription": "Counts level 1 data cache accesses generated by store operations. This event also counts accesses caused by a DC ZVA (data cache zero, specified by virtual address) instruction. Near atomic operations that resolve in the CPUs caches count as a write access and read access."
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_RD",
+        "PublicDescription": "Counts level 1 data cache refills caused by speculatively executed load instructions where the memory read operation misses in the level 1 data cache. This event only counts one event per cache line."
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_WR",
+        "PublicDescription": "Counts level 1 data cache refills caused by speculatively executed store instructions where the memory write operation misses in the level 1 data cache. This event only counts one event per cache line."
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_INNER",
+        "PublicDescription": "Counts level 1 data cache refills where the cache line data came from caches inside the immediate cluster of the core."
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_OUTER",
+        "PublicDescription": "Counts level 1 data cache refills for which the cache line data came from outside the immediate cluster of the core, like an SLC in the system interconnect or DRAM."
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WB_VICTIM",
+        "PublicDescription": "Counts dirty cache line evictions from the level 1 data cache caused by a new cache line allocation. This event does not count evictions caused by cache maintenance operations."
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WB_CLEAN",
+        "PublicDescription": "Counts write-backs from the level 1 data cache that are a result of a coherency operation made by another CPU. Event count includes cache maintenance operations."
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_INVAL",
+        "PublicDescription": "Counts each explicit invalidation of a cache line in the level 1 data cache caused by:\n\n- Cache Maintenance Operations (CMO) that operate by a virtual address.\n- Broadcast cache coherency operations from another CPU in the system.\n\nThis event does not count for the following conditions:\n\n1. A cache refill invalidates a cache line.\n2. A CMO which is executed on that CPU and invalidates a cache line specified by set/way.\n\nNote that CMOs that operate by set/way cannot be broadcast from one CPU to another."
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l1i_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l1i_cache.json
new file mode 100644
index 000000000000..633f1030359d
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l1i_cache.json
@@ -0,0 +1,14 @@
+[
+    {
+        "ArchStdEvent": "L1I_CACHE_REFILL",
+        "PublicDescription": "Counts cache line refills in the level 1 instruction cache caused by a missed instruction fetch. Instruction fetches may include accessing multiple instructions, but the single cache line allocation is counted once."
+    },
+    {
+        "ArchStdEvent": "L1I_CACHE",
+        "PublicDescription": "Counts instruction fetches which access the level 1 instruction cache. Instruction cache accesses caused by cache maintenance operations are not counted."
+    },
+    {
+        "ArchStdEvent": "L1I_CACHE_LMISS",
+        "PublicDescription": "Counts cache line refills into the level 1 instruction cache, that incurred additional latency."
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l2_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l2_cache.json
new file mode 100644
index 000000000000..0e31d0daf88b
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l2_cache.json
@@ -0,0 +1,50 @@
+[
+    {
+        "ArchStdEvent": "L2D_CACHE",
+        "PublicDescription": "Counts level 2 cache accesses. level 2 cache is a unified cache for data and instruction accesses. Accesses are for misses in the first level caches or translation resolutions due to accesses. This event also counts write back of dirty data from level 1 data cache to the L2 cache."
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_REFILL",
+        "PublicDescription": "Counts cache line refills into the level 2 cache. level 2 cache is a unified cache for data and instruction accesses. Accesses are for misses in the level 1 caches or translation resolutions due to accesses."
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WB",
+        "PublicDescription": "Counts write-backs of data from the L2 cache to outside the CPU. This includes snoops to the L2 (from other CPUs) which return data even if the snoops cause an invalidation. L2 cache line invalidations which do not write data outside the CPU and snoops which return data from an L1 cache are not counted. Data would not be written outside the cache when invalidating a clean cache line."
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_ALLOCATE",
+        "PublicDescription": "TBD"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_RD",
+        "PublicDescription": "Counts level 2 cache accesses due to memory read operations. level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 caches or translation resolutions due to accesses."
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WR",
+        "PublicDescription": "Counts level 2 cache accesses due to memory write operations. level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 caches or translation resolutions due to accesses."
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_REFILL_RD",
+        "PublicDescription": "Counts refills for memory accesses due to memory read operation counted by L2D_CACHE_RD. level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 caches or translation resolutions due to accesses."
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_REFILL_WR",
+        "PublicDescription": "Counts refills for memory accesses due to memory write operation counted by L2D_CACHE_WR. level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 caches or translation resolutions due to accesses."
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WB_VICTIM",
+        "PublicDescription": "Counts evictions from the level 2 cache because of a line being allocated into the L2 cache."
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WB_CLEAN",
+        "PublicDescription": "Counts write-backs from the level 2 cache that are a result of either:\n\n1. Cache maintenance operations,\n\n2. Snoop responses or,\n\n3. Direct cache transfers to another CPU due to a forwarding snoop request."
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_INVAL",
+        "PublicDescription": "Counts each explicit invalidation of a cache line in the level 2 cache by cache maintenance operations that operate by a virtual address, or by external coherency operations. This event does not count if either:\n\n1. A cache refill invalidates a cache line or,\n2. A Cache Maintenance Operation (CMO), which invalidates a cache line specified by set/way, is executed on that CPU.\n\nCMOs that operate by set/way cannot be broadcast from one CPU to another."
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_LMISS_RD",
+        "PublicDescription": "Counts cache line refills into the level 2 unified cache from any memory read operations that incurred additional latency."
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l3_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l3_cache.json
new file mode 100644
index 000000000000..45bfba532df7
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l3_cache.json
@@ -0,0 +1,22 @@
+[
+    {
+        "ArchStdEvent": "L3D_CACHE_ALLOCATE",
+        "PublicDescription": "Counts level 3 cache line allocates that do not fetch data from outside the level 3 data or unified cache. For example, allocates due to streaming stores."
+    },
+    {
+        "ArchStdEvent": "L3D_CACHE_REFILL",
+        "PublicDescription": "Counts level 3 accesses that receive data from outside the L3 cache."
+    },
+    {
+        "ArchStdEvent": "L3D_CACHE",
+        "PublicDescription": "Counts level 3 cache accesses. level 3 cache is a unified cache for data and instruction accesses. Accesses are for misses in the lower level caches or translation resolutions due to accesses."
+    },
+    {
+        "ArchStdEvent": "L3D_CACHE_RD",
+        "PublicDescription": "TBD"
+    },
+    {
+        "ArchStdEvent": "L3D_CACHE_LMISS_RD",
+        "PublicDescription": "Counts any cache line refill into the level 3 cache from memory read operations that incurred additional latency."
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/ll_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/ll_cache.json
new file mode 100644
index 000000000000..bb712d57d58a
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/ll_cache.json
@@ -0,0 +1,10 @@
+[
+    {
+        "ArchStdEvent": "LL_CACHE_RD",
+        "PublicDescription": "Counts read transactions that were returned from outside the core cluster. This event counts when the system register CPUECTLR.EXTLLC bit is set. This event counts read transactions returned from outside the core if those transactions are either hit in the system level cache or missed in the SLC and are returned from any other external sources."
+    },
+    {
+        "ArchStdEvent": "LL_CACHE_MISS_RD",
+        "PublicDescription": "Counts read transactions that were returned from outside the core cluster but missed in the system level cache. This event counts when the system register CPUECTLR.EXTLLC bit is set. This event counts read transactions returned from outside the core if those transactions are missed in the System level Cache. The data source of the transaction is indicated by a field in the CHI transaction returning to the CPU. This event does not count reads caused by cache maintenance operations."
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/memory.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/memory.json
index 7b2b21ac150f..106a97f8b2e7 100644
--- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/memory.json
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/memory.json
@@ -1,41 +1,46 @@
 [
     {
-        "ArchStdEvent": "MEM_ACCESS"
+        "ArchStdEvent": "MEM_ACCESS",
+        "PublicDescription": "Counts memory accesses issued by the CPU load store unit, where those accesses are issued due to load or store operations. This event counts memory accesses no matter whether the data is received from any level of cache hierarchy or external memory. If memory accesses are broken up into smaller transactions than what were specified in the load or store instructions, then the event counts those smaller memory transactions."
     },
     {
-        "ArchStdEvent": "REMOTE_ACCESS"
+        "ArchStdEvent": "MEMORY_ERROR",
+        "PublicDescription": "Counts any detected correctable or uncorrectable physical memory errors (ECC or parity) in protected CPUs RAMs. On the core, this event counts errors in the caches (including data and tag rams). Any detected memory error (from either a speculative and abandoned access, or an architecturally executed access) is counted. Note that errors are only detected when the actual protected memory is accessed by an operation."
     },
     {
-        "ArchStdEvent": "MEM_ACCESS_RD"
+        "ArchStdEvent": "REMOTE_ACCESS",
+        "PublicDescription": "Counts accesses to another chip, which is implemented as a different CMN mesh in the system. If the CHI bus response back to the core indicates that the data source is from another chip (mesh), then the counter is updated. If no data is returned, even if the system snoops another chip/mesh, then the counter is not updated."
     },
     {
-        "ArchStdEvent": "MEM_ACCESS_WR"
+        "ArchStdEvent": "MEM_ACCESS_RD",
+        "PublicDescription": "Counts memory accesses issued by the CPU due to load operations. The event counts any memory load access, no matter whether the data is received from any level of cache hierarchy or external memory. The event also counts atomic load operations. If memory accesses are broken up by the load/store unit into smaller transactions that are issued by the bus interface, then the event counts those smaller transactions."
     },
     {
-        "ArchStdEvent": "UNALIGNED_LD_SPEC"
+        "ArchStdEvent": "MEM_ACCESS_WR",
+        "PublicDescription": "Counts memory accesses issued by the CPU due to store operations. The event counts any memory store access, no matter whether the data is located in any level of cache or external memory. The event also counts atomic load and store operations. If memory accesses are broken up by the load/store unit into smaller transactions that are issued by the bus interface, then the event counts those smaller transactions."
     },
     {
-        "ArchStdEvent": "UNALIGNED_ST_SPEC"
+        "ArchStdEvent": "LDST_ALIGN_LAT",
+        "PublicDescription": "Counts the number of memory read and write accesses in a cycle that incurred additional latency, due to the alignment of the address and the size of data being accessed, which results in store crossing a single cache line."
     },
     {
-        "ArchStdEvent": "UNALIGNED_LDST_SPEC"
+        "ArchStdEvent": "LD_ALIGN_LAT",
+        "PublicDescription": "Counts the number of memory read accesses in a cycle that incurred additional latency, due to the alignment of the address and size of data being accessed, which results in load crossing a single cache line."
     },
     {
-        "ArchStdEvent": "LDST_ALIGN_LAT"
+        "ArchStdEvent": "ST_ALIGN_LAT",
+        "PublicDescription": "Counts the number of memory write access in a cycle that incurred additional latency, due to the alignment of the address and size of data being accessed incurred additional latency."
     },
     {
-        "ArchStdEvent": "LD_ALIGN_LAT"
+        "ArchStdEvent": "MEM_ACCESS_CHECKED",
+        "PublicDescription": "Counts the number of memory read and write accesses in a cycle that are tag checked by the Memory Tagging Extension (MTE)."
     },
     {
-        "ArchStdEvent": "ST_ALIGN_LAT"
+        "ArchStdEvent": "MEM_ACCESS_CHECKED_RD",
+        "PublicDescription": "Counts the number of memory read accesses in a cycle that are tag checked by the Memory Tagging Extension (MTE)."
     },
     {
-        "ArchStdEvent": "MEM_ACCESS_CHECKED"
-    },
-    {
-        "ArchStdEvent": "MEM_ACCESS_CHECKED_RD"
-    },
-    {
-        "ArchStdEvent": "MEM_ACCESS_CHECKED_WR"
+        "ArchStdEvent": "MEM_ACCESS_CHECKED_WR",
+        "PublicDescription": "Counts the number of memory write accesses in a cycle that is tag checked by the Memory Tagging Extension (MTE)."
     }
 ]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json
index 9757cc178bdf..5f449270b448 100644
--- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json
@@ -1,272 +1,303 @@
 [
     {
-        "ArchStdEvent": "FRONTEND_BOUND",
-        "MetricExpr": "((stall_slot_frontend) if (strcmp_cpuid_str(0x410fd493) | strcmp_cpuid_str(0x410fd490) ^ 1) else (stall_slot_frontend - cpu_cycles)) / (#slots * cpu_cycles)"
+        "ArchStdEvent": "backend_bound",
+        "MetricExpr": "(100 * ((STALL_SLOT_BACKEND / (CPU_CYCLES * #slots)) - ((BR_MIS_PRED * 3) / CPU_CYCLES)))"
     },
     {
-        "ArchStdEvent": "BAD_SPECULATION",
-        "MetricExpr": "(1 - op_retired / op_spec) * (1 - (stall_slot if (strcmp_cpuid_str(0x410fd493) | strcmp_cpuid_str(0x410fd490) ^ 1) else (stall_slot - cpu_cycles)) / (#slots * cpu_cycles))"
+        "MetricName": "backend_stalled_cycles",
+        "MetricExpr": "((STALL_BACKEND / CPU_CYCLES) * 100)",
+        "BriefDescription": "This metric is the percentage of cycles that were stalled due to resource constraints in the backend unit of the processor.",
+        "MetricGroup": "Cycle_Accounting",
+        "ScaleUnit": "1percent of cycles"
     },
     {
-        "ArchStdEvent": "RETIRING",
-        "MetricExpr": "(op_retired / op_spec) * (1 - (stall_slot if (strcmp_cpuid_str(0x410fd493) | strcmp_cpuid_str(0x410fd490) ^ 1) else (stall_slot - cpu_cycles)) / (#slots * cpu_cycles))"
+        "ArchStdEvent": "bad_speculation",
+        "MetricExpr": "(100 * (((1 - (OP_RETIRED / OP_SPEC)) * (1 - (((STALL_SLOT) if (strcmp_cpuid_str(0x410fd493) | strcmp_cpuid_str(0x410fd490) ^ 1) else (STALL_SLOT - CPU_CYCLES)) / (CPU_CYCLES * #slots)))) + ((BR_MIS_PRED * 4) / CPU_CYCLES)))"
     },
     {
-        "ArchStdEvent": "BACKEND_BOUND"
+        "MetricName": "branch_misprediction_ratio",
+        "MetricExpr": "(BR_MIS_PRED_RETIRED / BR_RETIRED)",
+        "BriefDescription": "This metric measures the ratio of branches mispredicted to the total number of branches architecturally executed. This gives an indication of the effectiveness of the branch prediction unit.",
+        "MetricGroup": "Miss_Ratio;Branch_Effectiveness",
+        "ScaleUnit": "1per branch"
     },
     {
-        "MetricExpr": "L1D_TLB_REFILL / L1D_TLB",
-        "BriefDescription": "The rate of L1D TLB refill to the overall L1D TLB lookups",
-        "MetricGroup": "TLB",
-        "MetricName": "l1d_tlb_miss_rate",
-        "ScaleUnit": "100%"
+        "MetricName": "branch_mpki",
+        "MetricExpr": "((BR_MIS_PRED_RETIRED / INST_RETIRED) * 1000)",
+        "BriefDescription": "This metric measures the number of branch mispredictions per thousand instructions executed.",
+        "MetricGroup": "MPKI;Branch_Effectiveness",
+        "ScaleUnit": "1MPKI"
     },
     {
-        "MetricExpr": "L1I_TLB_REFILL / L1I_TLB",
-        "BriefDescription": "The rate of L1I TLB refill to the overall L1I TLB lookups",
-        "MetricGroup": "TLB",
-        "MetricName": "l1i_tlb_miss_rate",
-        "ScaleUnit": "100%"
+        "MetricName": "branch_percentage",
+        "MetricExpr": "(((BR_IMMED_SPEC + BR_INDIRECT_SPEC) / INST_SPEC) * 100)",
+        "BriefDescription": "This metric measures branch operations as a percentage of operations speculatively executed.",
+        "MetricGroup": "Operation_Mix",
+        "ScaleUnit": "1percent of operations"
     },
     {
-        "MetricExpr": "L2D_TLB_REFILL / L2D_TLB",
-        "BriefDescription": "The rate of L2D TLB refill to the overall L2D TLB lookups",
-        "MetricGroup": "TLB",
-        "MetricName": "l2_tlb_miss_rate",
-        "ScaleUnit": "100%"
+        "MetricName": "crypto_percentage",
+        "MetricExpr": "((CRYPTO_SPEC / INST_SPEC) * 100)",
+        "BriefDescription": "This metric measures crypto operations as a percentage of operations speculatively executed.",
+        "MetricGroup": "Operation_Mix",
+        "ScaleUnit": "1percent of operations"
     },
     {
-        "MetricExpr": "DTLB_WALK / INST_RETIRED * 1000",
-        "BriefDescription": "The rate of TLB Walks per kilo instructions for data accesses",
-        "MetricGroup": "TLB",
         "MetricName": "dtlb_mpki",
+        "MetricExpr": "((DTLB_WALK / INST_RETIRED) * 1000)",
+        "BriefDescription": "This metric measures the number of data TLB Walks per thousand instructions executed.",
+        "MetricGroup": "MPKI;DTLB_Effectiveness",
         "ScaleUnit": "1MPKI"
     },
     {
-        "MetricExpr": "DTLB_WALK / L1D_TLB",
-        "BriefDescription": "The rate of DTLB Walks to the overall L1D TLB lookups",
-        "MetricGroup": "TLB",
-        "MetricName": "dtlb_walk_rate",
-        "ScaleUnit": "100%"
+        "MetricName": "dtlb_walk_ratio",
+        "MetricExpr": "(DTLB_WALK / L1D_TLB)",
+        "BriefDescription": "This metric measures the ratio of data TLB Walks to the total number of data TLB accesses. This gives an indication of the effectiveness of the data TLB accesses.",
+        "MetricGroup": "Miss_Ratio;DTLB_Effectiveness",
+        "ScaleUnit": "1per TLB access"
+    },
+    {
+        "ArchStdEvent": "frontend_bound",
+        "MetricExpr": "(100 * ((((STALL_SLOT_FRONTEND) if (strcmp_cpuid_str(0x410fd493) | strcmp_cpuid_str(0x410fd490) ^ 1) else (STALL_SLOT_FRONTEND - CPU_CYCLES)) / (CPU_CYCLES * #slots)) - (BR_MIS_PRED / CPU_CYCLES)))"
+    },
+    {
+        "MetricName": "frontend_stalled_cycles",
+        "MetricExpr": "((STALL_FRONTEND / CPU_CYCLES) * 100)",
+        "BriefDescription": "This metric is the percentage of cycles that were stalled due to resource constraints in the frontend unit of the processor.",
+        "MetricGroup": "Cycle_Accounting",
+        "ScaleUnit": "1percent of cycles"
+    },
+    {
+        "MetricName": "integer_dp_percentage",
+        "MetricExpr": "((DP_SPEC / INST_SPEC) * 100)",
+        "BriefDescription": "This metric measures scalar integer operations as a percentage of operations speculatively executed.",
+        "MetricGroup": "Operation_Mix",
+        "ScaleUnit": "1percent of operations"
+    },
+    {
+        "MetricName": "ipc",
+        "MetricExpr": "(INST_RETIRED / CPU_CYCLES)",
+        "BriefDescription": "This metric measures the number of instructions retired per cycle.",
+        "MetricGroup": "General",
+        "ScaleUnit": "1per cycle"
     },
     {
-        "MetricExpr": "ITLB_WALK / INST_RETIRED * 1000",
-        "BriefDescription": "The rate of TLB Walks per kilo instructions for instruction accesses",
-        "MetricGroup": "TLB",
         "MetricName": "itlb_mpki",
+        "MetricExpr": "((ITLB_WALK / INST_RETIRED) * 1000)",
+        "BriefDescription": "This metric measures the number of instruction TLB Walks per thousand instructions executed.",
+        "MetricGroup": "MPKI;ITLB_Effectiveness",
         "ScaleUnit": "1MPKI"
     },
     {
-        "MetricExpr": "ITLB_WALK / L1I_TLB",
-        "BriefDescription": "The rate of ITLB Walks to the overall L1I TLB lookups",
-        "MetricGroup": "TLB",
-        "MetricName": "itlb_walk_rate",
-        "ScaleUnit": "100%"
+        "MetricName": "itlb_walk_ratio",
+        "MetricExpr": "(ITLB_WALK / L1I_TLB)",
+        "BriefDescription": "This metric measures the ratio of instruction TLB Walks to the total number of instruction TLB accesses. This gives an indication of the effectiveness of the instruction TLB accesses.",
+        "MetricGroup": "Miss_Ratio;ITLB_Effectiveness",
+        "ScaleUnit": "1per TLB access"
     },
     {
-        "MetricExpr": "L1I_CACHE_REFILL / INST_RETIRED * 1000",
-        "BriefDescription": "The rate of L1 I-Cache misses per kilo instructions",
-        "MetricGroup": "Cache",
-        "MetricName": "l1i_cache_mpki",
-        "ScaleUnit": "1MPKI"
+        "MetricName": "l1d_cache_miss_ratio",
+        "MetricExpr": "(L1D_CACHE_REFILL / L1D_CACHE)",
+        "BriefDescription": "This metric measures the ratio of level 1 data cache accesses missed to the total number of level 1 data cache accesses. This gives an indication of the effectiveness of the level 1 data cache.",
+        "MetricGroup": "Miss_Ratio;L1D_Cache_Effectiveness",
+        "ScaleUnit": "1per cache access"
     },
     {
-        "MetricExpr": "L1I_CACHE_REFILL / L1I_CACHE",
-        "BriefDescription": "The rate of L1 I-Cache misses to the overall L1 I-Cache",
-        "MetricGroup": "Cache",
-        "MetricName": "l1i_cache_miss_rate",
-        "ScaleUnit": "100%"
-    },
-    {
-        "MetricExpr": "L1D_CACHE_REFILL / INST_RETIRED * 1000",
-        "BriefDescription": "The rate of L1 D-Cache misses per kilo instructions",
-        "MetricGroup": "Cache",
         "MetricName": "l1d_cache_mpki",
+        "MetricExpr": "((L1D_CACHE_REFILL / INST_RETIRED) * 1000)",
+        "BriefDescription": "This metric measures the number of level 1 data cache accesses missed per thousand instructions executed.",
+        "MetricGroup": "MPKI;L1D_Cache_Effectiveness",
         "ScaleUnit": "1MPKI"
     },
     {
-        "MetricExpr": "L1D_CACHE_REFILL / L1D_CACHE",
-        "BriefDescription": "The rate of L1 D-Cache misses to the overall L1 D-Cache",
-        "MetricGroup": "Cache",
-        "MetricName": "l1d_cache_miss_rate",
-        "ScaleUnit": "100%"
+        "MetricName": "l1d_tlb_miss_ratio",
+        "MetricExpr": "(L1D_TLB_REFILL / L1D_TLB)",
+        "BriefDescription": "This metric measures the ratio of level 1 data TLB accesses missed to the total number of level 1 data TLB accesses. This gives an indication of the effectiveness of the level 1 data TLB.",
+        "MetricGroup": "Miss_Ratio;DTLB_Effectiveness",
+        "ScaleUnit": "1per TLB access"
     },
     {
-        "MetricExpr": "L2D_CACHE_REFILL / INST_RETIRED * 1000",
-        "BriefDescription": "The rate of L2 D-Cache misses per kilo instructions",
-        "MetricGroup": "Cache",
-        "MetricName": "l2d_cache_mpki",
+        "MetricName": "l1d_tlb_mpki",
+        "MetricExpr": "((L1D_TLB_REFILL / INST_RETIRED) * 1000)",
+        "BriefDescription": "This metric measures the number of level 1 instruction TLB accesses missed per thousand instructions executed.",
+        "MetricGroup": "MPKI;DTLB_Effectiveness",
         "ScaleUnit": "1MPKI"
     },
     {
-        "MetricExpr": "L2D_CACHE_REFILL / L2D_CACHE",
-        "BriefDescription": "The rate of L2 D-Cache misses to the overall L2 D-Cache",
-        "MetricGroup": "Cache",
-        "MetricName": "l2d_cache_miss_rate",
-        "ScaleUnit": "100%"
+        "MetricName": "l1i_cache_miss_ratio",
+        "MetricExpr": "(L1I_CACHE_REFILL / L1I_CACHE)",
+        "BriefDescription": "This metric measures the ratio of level 1 instruction cache accesses missed to the total number of level 1 instruction cache accesses. This gives an indication of the effectiveness of the level 1 instruction cache.",
+        "MetricGroup": "Miss_Ratio;L1I_Cache_Effectiveness",
+        "ScaleUnit": "1per cache access"
+    },
+    {
+        "MetricName": "l1i_cache_mpki",
+        "MetricExpr": "((L1I_CACHE_REFILL / INST_RETIRED) * 1000)",
+        "BriefDescription": "This metric measures the number of level 1 instruction cache accesses missed per thousand instructions executed.",
+        "MetricGroup": "MPKI;L1I_Cache_Effectiveness",
+        "ScaleUnit": "1MPKI"
+    },
+    {
+        "MetricName": "l1i_tlb_miss_ratio",
+        "MetricExpr": "(L1I_TLB_REFILL / L1I_TLB)",
+        "BriefDescription": "This metric measures the ratio of level 1 instruction TLB accesses missed to the total number of level 1 instruction TLB accesses. This gives an indication of the effectiveness of the level 1 instruction TLB.",
+        "MetricGroup": "Miss_Ratio;ITLB_Effectiveness",
+        "ScaleUnit": "1per TLB access"
+    },
+    {
+        "MetricName": "l1i_tlb_mpki",
+        "MetricExpr": "((L1I_TLB_REFILL / INST_RETIRED) * 1000)",
+        "BriefDescription": "This metric measures the number of level 1 instruction TLB accesses missed per thousand instructions executed.",
+        "MetricGroup": "MPKI;ITLB_Effectiveness",
+        "ScaleUnit": "1MPKI"
+    },
+    {
+        "MetricName": "l2_cache_miss_ratio",
+        "MetricExpr": "(L2D_CACHE_REFILL / L2D_CACHE)",
+        "BriefDescription": "This metric measures the ratio of level 2 cache accesses missed to the total number of level 2 cache accesses. This gives an indication of the effectiveness of the level 2 cache, which is a unified cache that stores both data and instruction. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a unified cache.",
+        "MetricGroup": "Miss_Ratio;L2_Cache_Effectiveness",
+        "ScaleUnit": "1per cache access"
+    },
+    {
+        "MetricName": "l2_cache_mpki",
+        "MetricExpr": "((L2D_CACHE_REFILL / INST_RETIRED) * 1000)",
+        "BriefDescription": "This metric measures the number of level 2 unified cache accesses missed per thousand instructions executed. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a unified cache.",
+        "MetricGroup": "MPKI;L2_Cache_Effectiveness",
+        "ScaleUnit": "1MPKI"
+    },
+    {
+        "MetricName": "l2_tlb_miss_ratio",
+        "MetricExpr": "(L2D_TLB_REFILL / L2D_TLB)",
+        "BriefDescription": "This metric measures the ratio of level 2 unified TLB accesses missed to the total number of level 2 unified TLB accesses. This gives an indication of the effectiveness of the level 2 TLB.",
+        "MetricGroup": "Miss_Ratio;ITLB_Effectiveness;DTLB_Effectiveness",
+        "ScaleUnit": "1per TLB access"
+    },
+    {
+        "MetricName": "l2_tlb_mpki",
+        "MetricExpr": "((L2D_TLB_REFILL / INST_RETIRED) * 1000)",
+        "BriefDescription": "This metric measures the number of level 2 unified TLB accesses missed per thousand instructions executed.",
+        "MetricGroup": "MPKI;ITLB_Effectiveness;DTLB_Effectiveness",
+        "ScaleUnit": "1MPKI"
+    },
+    {
+        "MetricName": "ll_cache_read_hit_ratio",
+        "MetricExpr": "((LL_CACHE_RD - LL_CACHE_MISS_RD) / LL_CACHE_RD)",
+        "BriefDescription": "This metric measures the ratio of last level cache read accesses hit in the cache to the total number of last level cache accesses. This gives an indication of the effectiveness of the last level cache for read traffic. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a system level cache.",
+        "MetricGroup": "LL_Cache_Effectiveness",
+        "ScaleUnit": "1per cache access"
+    },
+    {
+        "MetricName": "ll_cache_read_miss_ratio",
+        "MetricExpr": "(LL_CACHE_MISS_RD / LL_CACHE_RD)",
+        "BriefDescription": "This metric measures the ratio of last level cache read accesses missed to the total number of last level cache accesses. This gives an indication of the effectiveness of the last level cache for read traffic. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a system level cache.",
+        "MetricGroup": "Miss_Ratio;LL_Cache_Effectiveness",
+        "ScaleUnit": "1per cache access"
+    },
+    {
+        "MetricName": "ll_cache_read_mpki",
+        "MetricExpr": "((LL_CACHE_MISS_RD / INST_RETIRED) * 1000)",
+        "BriefDescription": "This metric measures the number of last level cache read accesses missed per thousand instructions executed.",
+        "MetricGroup": "MPKI;LL_Cache_Effectiveness",
+        "ScaleUnit": "1MPKI"
+    },
+    {
+        "MetricName": "load_percentage",
+        "MetricExpr": "((LD_SPEC / INST_SPEC) * 100)",
+        "BriefDescription": "This metric measures load operations as a percentage of operations speculatively executed.",
+        "MetricGroup": "Operation_Mix",
+        "ScaleUnit": "1percent of operations"
+    },
+    {
+        "ArchStdEvent": "retiring",
+        "MetricExpr": "(100 * ((OP_RETIRED / OP_SPEC) * (1 - (((STALL_SLOT) if (strcmp_cpuid_str(0x410fd493) | strcmp_cpuid_str(0x410fd490) ^ 1) else (STALL_SLOT - CPU_CYCLES)) / (CPU_CYCLES * #slots)))))"
+    },
+    {
+        "MetricName": "scalar_fp_percentage",
+        "MetricExpr": "((VFP_SPEC / INST_SPEC) * 100)",
+        "BriefDescription": "This metric measures scalar floating point operations as a percentage of operations speculatively executed.",
+        "MetricGroup": "Operation_Mix",
+        "ScaleUnit": "1percent of operations"
+    },
+    {
+        "MetricName": "simd_percentage",
+        "MetricExpr": "((ASE_SPEC / INST_SPEC) * 100)",
+        "BriefDescription": "This metric measures advanced SIMD operations as a percentage of total operations speculatively executed.",
+        "MetricGroup": "Operation_Mix",
+        "ScaleUnit": "1percent of operations"
+    },
+    {
+        "MetricName": "store_percentage",
+        "MetricExpr": "((ST_SPEC / INST_SPEC) * 100)",
+        "BriefDescription": "This metric measures store operations as a percentage of operations speculatively executed.",
+        "MetricGroup": "Operation_Mix",
+        "ScaleUnit": "1percent of operations"
     },
     {
         "MetricExpr": "L3D_CACHE_REFILL / INST_RETIRED * 1000",
         "BriefDescription": "The rate of L3 D-Cache misses per kilo instructions",
-        "MetricGroup": "Cache",
+        "MetricGroup": "MPKI;L3_Cache_Effectiveness",
         "MetricName": "l3d_cache_mpki",
         "ScaleUnit": "1MPKI"
     },
     {
         "MetricExpr": "L3D_CACHE_REFILL / L3D_CACHE",
         "BriefDescription": "The rate of L3 D-Cache misses to the overall L3 D-Cache",
-        "MetricGroup": "Cache",
+        "MetricGroup": "Miss_Ratio;L3_Cache_Effectiveness",
         "MetricName": "l3d_cache_miss_rate",
         "ScaleUnit": "100%"
     },
-    {
-        "MetricExpr": "LL_CACHE_MISS_RD / INST_RETIRED * 1000",
-        "BriefDescription": "The rate of LL Cache read misses per kilo instructions",
-        "MetricGroup": "Cache",
-        "MetricName": "ll_cache_read_mpki",
-        "ScaleUnit": "1MPKI"
-    },
-    {
-        "MetricExpr": "LL_CACHE_MISS_RD / LL_CACHE_RD",
-        "BriefDescription": "The rate of LL Cache read misses to the overall LL Cache read",
-        "MetricGroup": "Cache",
-        "MetricName": "ll_cache_read_miss_rate",
-        "ScaleUnit": "100%"
-    },
-    {
-        "MetricExpr": "(LL_CACHE_RD - LL_CACHE_MISS_RD) / LL_CACHE_RD",
-        "BriefDescription": "The rate of LL Cache read hit to the overall LL Cache read",
-        "MetricGroup": "Cache",
-        "MetricName": "ll_cache_read_hit_rate",
-        "ScaleUnit": "100%"
-    },
-    {
-        "MetricExpr": "BR_MIS_PRED_RETIRED / INST_RETIRED * 1000",
-        "BriefDescription": "The rate of branches mis-predicted per kilo instructions",
-        "MetricGroup": "Branch",
-        "MetricName": "branch_mpki",
-        "ScaleUnit": "1MPKI"
-    },
     {
         "MetricExpr": "BR_RETIRED / INST_RETIRED * 1000",
         "BriefDescription": "The rate of branches retired per kilo instructions",
-        "MetricGroup": "Branch",
+        "MetricGroup": "MPKI;Branch_Effectiveness",
         "MetricName": "branch_pki",
         "ScaleUnit": "1PKI"
     },
     {
-        "MetricExpr": "BR_MIS_PRED_RETIRED / BR_RETIRED",
-        "BriefDescription": "The rate of branches mis-predited to the overall branches",
-        "MetricGroup": "Branch",
-        "MetricName": "branch_miss_pred_rate",
-        "ScaleUnit": "100%"
-    },
-    {
-        "MetricExpr": "instructions / CPU_CYCLES",
-        "BriefDescription": "The average number of instructions executed for each cycle.",
-        "MetricGroup": "PEutilization",
-        "MetricName": "ipc"
-    },
-    {
-        "MetricExpr": "ipc / 5",
-        "BriefDescription": "IPC percentage of peak. The peak of IPC is 5.",
-        "MetricGroup": "PEutilization",
+        "MetricExpr": "ipc / #slots",
+        "BriefDescription": "IPC percentage of peak. The peak of IPC is the number of slots.",
+        "MetricGroup": "General",
         "MetricName": "ipc_rate",
         "ScaleUnit": "100%"
     },
-    {
-        "MetricExpr": "INST_RETIRED / CPU_CYCLES",
-        "BriefDescription": "Architecturally executed Instructions Per Cycle (IPC)",
-        "MetricGroup": "PEutilization",
-        "MetricName": "retired_ipc"
-    },
     {
         "MetricExpr": "INST_SPEC / CPU_CYCLES",
         "BriefDescription": "Speculatively executed Instructions Per Cycle (IPC)",
-        "MetricGroup": "PEutilization",
+        "MetricGroup": "General",
         "MetricName": "spec_ipc"
     },
     {
         "MetricExpr": "OP_RETIRED / OP_SPEC",
         "BriefDescription": "Of all the micro-operations issued, what percentage are retired(committed)",
-        "MetricGroup": "PEutilization",
+        "MetricGroup": "General",
         "MetricName": "retired_rate",
         "ScaleUnit": "100%"
     },
     {
         "MetricExpr": "1 - OP_RETIRED / OP_SPEC",
         "BriefDescription": "Of all the micro-operations issued, what percentage are not retired(committed)",
-        "MetricGroup": "PEutilization",
+        "MetricGroup": "General",
         "MetricName": "wasted_rate",
         "ScaleUnit": "100%"
     },
-    {
-        "MetricExpr": "OP_RETIRED / OP_SPEC * (1 - (STALL_SLOT if (strcmp_cpuid_str(0x410fd493) | strcmp_cpuid_str(0x410fd490) ^ 1) else (STALL_SLOT - CPU_CYCLES)) / (#slots * CPU_CYCLES))",
-        "BriefDescription": "The truly effective ratio of micro-operations executed by the CPU, which means that misprediction and stall are not included",
-        "MetricGroup": "PEutilization",
-        "MetricName": "cpu_utilization",
-        "ScaleUnit": "100%"
-    },
-    {
-        "MetricExpr": "LD_SPEC / INST_SPEC",
-        "BriefDescription": "The rate of load instructions speculatively executed to overall instructions speclatively executed",
-        "MetricGroup": "InstructionMix",
-        "MetricName": "load_spec_rate",
-        "ScaleUnit": "100%"
-    },
-    {
-        "MetricExpr": "ST_SPEC / INST_SPEC",
-        "BriefDescription": "The rate of store instructions speculatively executed to overall instructions speclatively executed",
-        "MetricGroup": "InstructionMix",
-        "MetricName": "store_spec_rate",
-        "ScaleUnit": "100%"
-    },
-    {
-        "MetricExpr": "DP_SPEC / INST_SPEC",
-        "BriefDescription": "The rate of integer data-processing instructions speculatively executed to overall instructions speclatively executed",
-        "MetricGroup": "InstructionMix",
-        "MetricName": "data_process_spec_rate",
-        "ScaleUnit": "100%"
-    },
-    {
-        "MetricExpr": "ASE_SPEC / INST_SPEC",
-        "BriefDescription": "The rate of advanced SIMD instructions speculatively executed to overall instructions speclatively executed",
-        "MetricGroup": "InstructionMix",
-        "MetricName": "advanced_simd_spec_rate",
-        "ScaleUnit": "100%"
-    },
-    {
-        "MetricExpr": "VFP_SPEC / INST_SPEC",
-        "BriefDescription": "The rate of floating point instructions speculatively executed to overall instructions speclatively executed",
-        "MetricGroup": "InstructionMix",
-        "MetricName": "float_point_spec_rate",
-        "ScaleUnit": "100%"
-    },
-    {
-        "MetricExpr": "CRYPTO_SPEC / INST_SPEC",
-        "BriefDescription": "The rate of crypto instructions speculatively executed to overall instructions speclatively executed",
-        "MetricGroup": "InstructionMix",
-        "MetricName": "crypto_spec_rate",
-        "ScaleUnit": "100%"
-    },
     {
         "MetricExpr": "BR_IMMED_SPEC / INST_SPEC",
-        "BriefDescription": "The rate of branch immediate instructions speculatively executed to overall instructions speclatively executed",
-        "MetricGroup": "InstructionMix",
+        "BriefDescription": "The rate of branch immediate instructions speculatively executed to overall instructions speculatively executed",
+        "MetricGroup": "Operation_Mix",
         "MetricName": "branch_immed_spec_rate",
         "ScaleUnit": "100%"
     },
     {
         "MetricExpr": "BR_RETURN_SPEC / INST_SPEC",
-        "BriefDescription": "The rate of procedure return instructions speculatively executed to overall instructions speclatively executed",
-        "MetricGroup": "InstructionMix",
+        "BriefDescription": "The rate of procedure return instructions speculatively executed to overall instructions speculatively executed",
+        "MetricGroup": "Operation_Mix",
         "MetricName": "branch_return_spec_rate",
         "ScaleUnit": "100%"
     },
     {
         "MetricExpr": "BR_INDIRECT_SPEC / INST_SPEC",
-        "BriefDescription": "The rate of indirect branch instructions speculatively executed to overall instructions speclatively executed",
-        "MetricGroup": "InstructionMix",
+        "BriefDescription": "The rate of indirect branch instructions speculatively executed to overall instructions speculatively executed",
+        "MetricGroup": "Operation_Mix",
         "MetricName": "branch_indirect_spec_rate",
         "ScaleUnit": "100%"
     }
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/pipeline.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/pipeline.json
deleted file mode 100644
index f9fae15f7555..000000000000
--- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/pipeline.json
+++ /dev/null
@@ -1,23 +0,0 @@
-[
-    {
-        "ArchStdEvent": "STALL_FRONTEND"
-    },
-    {
-        "ArchStdEvent": "STALL_BACKEND"
-    },
-    {
-        "ArchStdEvent": "STALL"
-    },
-    {
-        "ArchStdEvent": "STALL_SLOT_BACKEND"
-    },
-    {
-        "ArchStdEvent": "STALL_SLOT_FRONTEND"
-    },
-    {
-        "ArchStdEvent": "STALL_SLOT"
-    },
-    {
-        "ArchStdEvent": "STALL_BACKEND_MEM"
-    }
-]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/retired.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/retired.json
new file mode 100644
index 000000000000..f297b049b62f
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/retired.json
@@ -0,0 +1,30 @@
+[
+    {
+        "ArchStdEvent": "SW_INCR",
+        "PublicDescription": "Counts software writes to the PMSWINC_EL0 (software PMU increment) register. The PMSWINC_EL0 register is a manually updated counter for use by application software.\n\nThis event could be used to measure any user program event, such as accesses to a particular data structure (by writing to the PMSWINC_EL0 register each time the data structure is accessed).\n\nTo use the PMSWINC_EL0 register and event, developers must insert instructions that write to the PMSWINC_EL0 register into the source code.\n\nSince the SW_INCR event records writes to the PMSWINC_EL0 register, there is no need to do a read/increment/write sequence to the PMSWINC_EL0 register."
+    },
+    {
+        "ArchStdEvent": "INST_RETIRED",
+        "PublicDescription": "Counts instructions that have been architecturally executed."
+    },
+    {
+        "ArchStdEvent": "CID_WRITE_RETIRED",
+        "PublicDescription": "Counts architecturally executed writes to the CONTEXTIDR register, which usually contain the kernel PID and can be output with hardware trace."
+    },
+    {
+        "ArchStdEvent": "TTBR_WRITE_RETIRED",
+        "PublicDescription": "Counts architectural writes to TTBR0/1_EL1. If virtualization host extensions are enabled (by setting the HCR_EL2.E2H bit to 1), then accesses to TTBR0/1_EL1 that are redirected to TTBR0/1_EL2, or accesses to TTBR0/1_EL12, are counted. TTBRn registers are typically updated when the kernel is swapping user-space threads or applications."
+    },
+    {
+        "ArchStdEvent": "BR_RETIRED",
+        "PublicDescription": "Counts architecturally executed branches, whether the branch is taken or not. Instructions that explicitly write to the PC are also counted."
+    },
+    {
+        "ArchStdEvent": "BR_MIS_PRED_RETIRED",
+        "PublicDescription": "Counts branches counted by BR_RETIRED which were mispredicted and caused a pipeline flush."
+    },
+    {
+        "ArchStdEvent": "OP_RETIRED",
+        "PublicDescription": "Counts micro-operations that are architecturally executed. This is a count of number of micro-operations retired from the commit queue in a single cycle."
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/spe.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/spe.json
index 20f2165c85fe..5de8b0f3a440 100644
--- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/spe.json
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/spe.json
@@ -1,14 +1,18 @@
 [
     {
-        "ArchStdEvent": "SAMPLE_POP"
+        "ArchStdEvent": "SAMPLE_POP",
+        "PublicDescription": "Counts statistical profiling sample population, the count of all operations that could be sampled but may or may not be chosen for sampling."
     },
     {
-        "ArchStdEvent": "SAMPLE_FEED"
+        "ArchStdEvent": "SAMPLE_FEED",
+        "PublicDescription": "Counts statistical profiling samples taken for sampling."
     },
     {
-        "ArchStdEvent": "SAMPLE_FILTRATE"
+        "ArchStdEvent": "SAMPLE_FILTRATE",
+        "PublicDescription": "Counts statistical profiling samples taken which are not removed by filtering."
     },
     {
-        "ArchStdEvent": "SAMPLE_COLLISION"
+        "ArchStdEvent": "SAMPLE_COLLISION",
+        "PublicDescription": "Counts statistical profiling samples that have collided with a previous sample and so therefore not taken."
     }
 ]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/spec_operation.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/spec_operation.json
new file mode 100644
index 000000000000..1af961f8a6c8
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/spec_operation.json
@@ -0,0 +1,110 @@
+[
+    {
+        "ArchStdEvent": "BR_MIS_PRED",
+        "PublicDescription": "Counts branches which are speculatively executed and mispredicted."
+    },
+    {
+        "ArchStdEvent": "BR_PRED",
+        "PublicDescription": "Counts branches speculatively executed and were predicted right."
+    },
+    {
+        "ArchStdEvent": "INST_SPEC",
+        "PublicDescription": "Counts operations that have been speculatively executed."
+    },
+    {
+        "ArchStdEvent": "OP_SPEC",
+        "PublicDescription": "Counts micro-operations speculatively executed. This is the count of the number of micro-operations dispatched in a cycle."
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_LD_SPEC",
+        "PublicDescription": "Counts unaligned memory read operations issued by the CPU. This event counts unaligned accesses (as defined by the actual instruction), even if they are subsequently issued as multiple aligned accesses. The event does not count preload operations (PLD, PLI)."
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_ST_SPEC",
+        "PublicDescription": "Counts unaligned memory write operations issued by the CPU. This event counts unaligned accesses (as defined by the actual instruction), even if they are subsequently issued as multiple aligned accesses."
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_LDST_SPEC",
+        "PublicDescription": "Counts unaligned memory operations issued by the CPU. This event counts unaligned accesses (as defined by the actual instruction), even if they are subsequently issued as multiple aligned accesses."
+    },
+    {
+        "ArchStdEvent": "LDREX_SPEC",
+        "PublicDescription": "Counts Load-Exclusive operations that have been speculatively executed. Eg: LDREX, LDX"
+    },
+    {
+        "ArchStdEvent": "STREX_PASS_SPEC",
+        "PublicDescription": "Counts store-exclusive operations that have been speculatively executed and have successfully completed the store operation."
+    },
+    {
+        "ArchStdEvent": "STREX_FAIL_SPEC",
+        "PublicDescription": "Counts store-exclusive operations that have been speculatively executed and have not successfully completed the store operation."
+    },
+    {
+        "ArchStdEvent": "STREX_SPEC",
+        "PublicDescription": "Counts store-exclusive operations that have been speculatively executed."
+    },
+    {
+        "ArchStdEvent": "LD_SPEC",
+        "PublicDescription": "Counts speculatively executed load operations including Single Instruction Multiple Data (SIMD) load operations."
+    },
+    {
+        "ArchStdEvent": "ST_SPEC",
+        "PublicDescription": "Counts speculatively executed store operations including Single Instruction Multiple Data (SIMD) store operations."
+    },
+    {
+        "ArchStdEvent": "DP_SPEC",
+        "PublicDescription": "Counts speculatively executed logical or arithmetic instructions such as MOV/MVN operations."
+    },
+    {
+        "ArchStdEvent": "ASE_SPEC",
+        "PublicDescription": "Counts speculatively executed Advanced SIMD operations excluding load, store and move micro-operations that move data to or from SIMD (vector) registers."
+    },
+    {
+        "ArchStdEvent": "VFP_SPEC",
+        "PublicDescription": "Counts speculatively executed floating point operations. This event does not count operations that move data to or from floating point (vector) registers."
+    },
+    {
+        "ArchStdEvent": "PC_WRITE_SPEC",
+        "PublicDescription": "Counts speculatively executed operations which cause software changes of the PC. Those operations include all taken branch operations."
+    },
+    {
+        "ArchStdEvent": "CRYPTO_SPEC",
+        "PublicDescription": "Counts speculatively executed cryptographic operations except for PMULL and VMULL operations."
+    },
+    {
+        "ArchStdEvent": "BR_IMMED_SPEC",
+        "PublicDescription": "Counts immediate branch operations which are speculatively executed."
+    },
+    {
+        "ArchStdEvent": "BR_RETURN_SPEC",
+        "PublicDescription": "Counts procedure return operations (RET) which are speculatively executed."
+    },
+    {
+        "ArchStdEvent": "BR_INDIRECT_SPEC",
+        "PublicDescription": "Counts indirect branch operations including procedure returns, which are speculatively executed. This includes operations that force a software change of the PC, other than exception-generating operations.  Eg: BR Xn, RET"
+    },
+    {
+        "ArchStdEvent": "ISB_SPEC",
+        "PublicDescription": "Counts ISB operations that are executed."
+    },
+    {
+        "ArchStdEvent": "DSB_SPEC",
+        "PublicDescription": "Counts DSB operations that are speculatively issued to Load/Store unit in the CPU."
+    },
+    {
+        "ArchStdEvent": "DMB_SPEC",
+        "PublicDescription": "Counts DMB operations that are speculatively issued to the Load/Store unit in the CPU. This event does not count implied barriers from load acquire/store release operations."
+    },
+    {
+        "ArchStdEvent": "RC_LD_SPEC",
+        "PublicDescription": "Counts any load acquire operations that are speculatively executed. Eg: LDAR, LDARH, LDARB"
+    },
+    {
+        "ArchStdEvent": "RC_ST_SPEC",
+        "PublicDescription": "Counts any store release operations that are speculatively executed. Eg: STLR, STLRH, STLRB'"
+    },
+    {
+        "ArchStdEvent": "ASE_INST_SPEC",
+        "PublicDescription": "Counts speculatively executed Advanced SIMD operations."
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/stall.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/stall.json
new file mode 100644
index 000000000000..bbbebc805034
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/stall.json
@@ -0,0 +1,30 @@
+[
+    {
+        "ArchStdEvent": "STALL_FRONTEND",
+        "PublicDescription": "Counts cycles when frontend could not send any micro-operations to the rename stage because of frontend resource stalls caused by fetch memory latency or branch prediction flow stalls. All the frontend slots were empty during the cycle when this event counts."
+    },
+    {
+        "ArchStdEvent": "STALL_BACKEND",
+        "PublicDescription": "Counts cycles whenever the rename unit is unable to send any micro-operations to the backend of the pipeline because of backend resource constraints. Backend resource constraints can include issue stage fullness, execution stage fullness, or other internal pipeline resource fullness. All the backend slots were empty during the cycle when this event counts."
+    },
+    {
+        "ArchStdEvent": "STALL",
+        "PublicDescription": "Counts cycles when no operations are sent to the rename unit from the frontend or from the rename unit to the backend for any reason (either frontend or backend stall)."
+    },
+    {
+        "ArchStdEvent": "STALL_SLOT_BACKEND",
+        "PublicDescription": "Counts slots per cycle in which no operations are sent from the rename unit to the backend due to backend resource constraints."
+    },
+    {
+        "ArchStdEvent": "STALL_SLOT_FRONTEND",
+        "PublicDescription": "Counts slots per cycle in which no operations are sent to the rename unit from the frontend due to frontend resource constraints."
+    },
+    {
+        "ArchStdEvent": "STALL_SLOT",
+        "PublicDescription": "Counts slots per cycle in which no operations are sent to the rename unit from the frontend or from the rename unit to the backend for any reason (either frontend or backend stall)."
+    },
+    {
+        "ArchStdEvent": "STALL_BACKEND_MEM",
+        "PublicDescription": "Counts cycles when the backend is stalled because there is a pending demand load request in progress in the last level core cache."
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/sve.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/sve.json
new file mode 100644
index 000000000000..51dab48cb2ba
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/sve.json
@@ -0,0 +1,50 @@
+[
+    {
+        "ArchStdEvent": "SVE_INST_SPEC",
+        "PublicDescription": "Counts speculatively executed operations that are SVE operations."
+    },
+    {
+        "ArchStdEvent": "SVE_PRED_SPEC",
+        "PublicDescription": "Counts speculatively executed predicated SVE operations."
+    },
+    {
+        "ArchStdEvent": "SVE_PRED_EMPTY_SPEC",
+        "PublicDescription": "Counts speculatively executed predicated SVE operations with no active predicate elements."
+    },
+    {
+        "ArchStdEvent": "SVE_PRED_FULL_SPEC",
+        "PublicDescription": "Counts speculatively executed predicated SVE operations with all predicate elements active."
+    },
+    {
+        "ArchStdEvent": "SVE_PRED_PARTIAL_SPEC",
+        "PublicDescription": "Counts speculatively executed predicated SVE operations with at least one but not all active predicate elements."
+    },
+    {
+        "ArchStdEvent": "SVE_PRED_NOT_FULL_SPEC",
+        "PublicDescription": "Counts speculatively executed predicated SVE operations with at least one non active predicate elements."
+    },
+    {
+        "ArchStdEvent": "SVE_LDFF_SPEC",
+        "PublicDescription": "Counts speculatively executed SVE first fault or non-fault load operations."
+    },
+    {
+        "ArchStdEvent": "SVE_LDFF_FAULT_SPEC",
+        "PublicDescription": "Counts speculatively executed SVE first fault or non-fault load operations that clear at least one bit in the FFR."
+    },
+    {
+        "ArchStdEvent": "ASE_SVE_INT8_SPEC",
+        "PublicDescription": "Counts speculatively executed Advanced SIMD or SVE integer operations with the largest data type an 8-bit integer."
+    },
+    {
+        "ArchStdEvent": "ASE_SVE_INT16_SPEC",
+        "PublicDescription": "Counts speculatively executed Advanced SIMD or SVE integer operations with the largest data type a 16-bit integer."
+    },
+    {
+        "ArchStdEvent": "ASE_SVE_INT32_SPEC",
+        "PublicDescription": "Counts speculatively executed Advanced SIMD or SVE integer operations with the largest data type a 32-bit integer."
+    },
+    {
+        "ArchStdEvent": "ASE_SVE_INT64_SPEC",
+        "PublicDescription": "Counts speculatively executed Advanced SIMD or SVE integer operations with the largest data type a 64-bit integer."
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/tlb.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/tlb.json
new file mode 100644
index 000000000000..b550af1831f5
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/tlb.json
@@ -0,0 +1,66 @@
+[
+    {
+        "ArchStdEvent": "L1I_TLB_REFILL",
+        "PublicDescription": "Counts level 1 instruction TLB refills from any Instruction fetch. If there are multiple misses in the TLB that are resolved by the refill, then this event only counts once. This event will not count if the translation table walk results in a fault (such as a translation or access fault), since there is no new translation created for the TLB."
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_REFILL",
+        "PublicDescription": "Counts level 1 data TLB accesses that resulted in TLB refills. If there are multiple misses in the TLB that are resolved by the refill, then this event only counts once. This event counts for refills caused by preload instructions or hardware prefetch accesses. This event counts regardless of whether the miss hits in L2 or results in a translation table walk. This event will not count if the translation table walk results in a fault (such as a translation or access fault), since there is no new translation created for the TLB. This event will not count on an access from an AT(address translation) instruction."
+    },
+    {
+        "ArchStdEvent": "L1D_TLB",
+        "PublicDescription": "Counts level 1 data TLB accesses caused by any memory load or store operation. Note that load or store instructions can be broken up into multiple memory operations. This event does not count TLB maintenance operations."
+    },
+    {
+        "ArchStdEvent": "L1I_TLB",
+        "PublicDescription": "Counts level 1 instruction TLB accesses, whether the access hits or misses in the TLB. This event counts both demand accesses and prefetch or preload generated accesses."
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_REFILL",
+        "PublicDescription": "Counts level 2 TLB refills caused by memory operations from both data and instruction fetch, except for those caused by TLB maintenance operations and hardware prefetches."
+    },
+    {
+        "ArchStdEvent": "L2D_TLB",
+        "PublicDescription": "Counts level 2 TLB accesses except those caused by TLB maintenance operations."
+    },
+    {
+        "ArchStdEvent": "DTLB_WALK",
+        "PublicDescription": "Counts data memory translation table walks caused by a miss in the L2 TLB driven by a memory access. Note that partial translations that also cause a table walk are counted. This event does not count table walks caused by TLB maintenance operations."
+    },
+    {
+        "ArchStdEvent": "ITLB_WALK",
+        "PublicDescription": "Counts instruction memory translation table walks caused by a miss in the L2 TLB driven by a memory access. Partial translations that also cause a table walk are counted. This event does not count table walks caused by TLB maintenance operations."
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_REFILL_RD",
+        "PublicDescription": "Counts level 1 data TLB refills caused by memory read operations. If there are multiple misses in the TLB that are resolved by the refill, then this event only counts once. This event counts for refills caused by preload instructions or hardware prefetch accesses. This event counts regardless of whether the miss hits in L2 or results in a translation table walk. This event will not count if the translation table walk results in a fault (such as a translation or access fault), since there is no new translation created for the TLB. This event will not count on an access from an Address Translation (AT) instruction."
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_REFILL_WR",
+        "PublicDescription": "Counts level 1 data TLB refills caused by data side memory write operations. If there are multiple misses in the TLB that are resolved by the refill, then this event only counts once. This event counts for refills caused by preload instructions or hardware prefetch accesses. This event counts regardless of whether the miss hits in L2 or results in a translation table walk. This event will not count if the table walk results in a fault (such as a translation or access fault), since there is no new translation created for the TLB. This event will not count with an access from an Address Translation (AT) instruction."
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_RD",
+        "PublicDescription": "Counts level 1 data TLB accesses caused by memory read operations. This event counts whether the access hits or misses in the TLB. This event does not count TLB maintenance operations."
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_WR",
+        "PublicDescription": "Counts any L1 data side TLB accesses caused by memory write operations. This event counts whether the access hits or misses in the TLB. This event does not count TLB maintenance operations."
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_REFILL_RD",
+        "PublicDescription": "Counts level 2 TLB refills caused by memory read operations from both data and instruction fetch except for those caused by TLB maintenance operations or hardware prefetches."
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_REFILL_WR",
+        "PublicDescription": "Counts level 2 TLB refills caused by memory write operations from both data and instruction fetch except for those caused by TLB maintenance operations."
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_RD",
+        "PublicDescription": "Counts level 2 TLB accesses caused by memory read operations from both data and instruction fetch except for those caused by TLB maintenance operations."
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_WR",
+        "PublicDescription": "Counts level 2 TLB accesses caused by memory write operations from both data and instruction fetch except for those caused by TLB maintenance operations."
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/trace.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/trace.json
index 3116135c59e2..98f6fabfebc7 100644
--- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/trace.json
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/trace.json
@@ -1,29 +1,38 @@
 [
     {
-        "ArchStdEvent": "TRB_WRAP"
+        "ArchStdEvent": "TRB_WRAP",
+        "PublicDescription": "This event is generated each time the current write pointer is wrapped to the base pointer."
     },
     {
-        "ArchStdEvent": "TRCEXTOUT0"
+        "ArchStdEvent": "TRCEXTOUT0",
+        "PublicDescription": "This event is generated each time an event is signaled by ETE external event 0."
     },
     {
-        "ArchStdEvent": "TRCEXTOUT1"
+        "ArchStdEvent": "TRCEXTOUT1",
+        "PublicDescription": "This event is generated each time an event is signaled by ETE external event 1."
     },
     {
-        "ArchStdEvent": "TRCEXTOUT2"
+        "ArchStdEvent": "TRCEXTOUT2",
+        "PublicDescription": "This event is generated each time an event is signaled by ETE external event 2."
     },
     {
-        "ArchStdEvent": "TRCEXTOUT3"
+        "ArchStdEvent": "TRCEXTOUT3",
+        "PublicDescription": "This event is generated each time an event is signaled by ETE external event 3."
     },
     {
-        "ArchStdEvent": "CTI_TRIGOUT4"
+        "ArchStdEvent": "CTI_TRIGOUT4",
+        "PublicDescription": "This event is generated each time an event is signaled on CTI output trigger 4."
     },
     {
-        "ArchStdEvent": "CTI_TRIGOUT5"
+        "ArchStdEvent": "CTI_TRIGOUT5",
+        "PublicDescription": "This event is generated each time an event is signaled on CTI output trigger 5."
     },
     {
-        "ArchStdEvent": "CTI_TRIGOUT6"
+        "ArchStdEvent": "CTI_TRIGOUT6",
+        "PublicDescription": "This event is generated each time an event is signaled on CTI output trigger 6."
     },
     {
-        "ArchStdEvent": "CTI_TRIGOUT7"
+        "ArchStdEvent": "CTI_TRIGOUT7",
+        "PublicDescription": "This event is generated each time an event is signaled on CTI output trigger 7."
     }
 ]

From ef23cb593304bde0cc046fd4cc83ae7ea2e24f16 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 17 Aug 2023 09:11:21 -0300
Subject: [PATCH 0510/1189] perf top: Don't pass an ERR_PTR() directly to
 perf_session__delete()

While debugging a segfault on 'perf lock contention' without an
available perf.data file I noticed that it was basically calling:

	perf_session__delete(ERR_PTR(-1))

Resulting in:

  (gdb) run lock contention
  Starting program: /root/bin/perf lock contention
  [Thread debugging using libthread_db enabled]
  Using host libthread_db library "/lib64/libthread_db.so.1".
  failed to open perf.data: No such file or directory  (try 'perf record' first)
  Initializing perf session failed

  Program received signal SIGSEGV, Segmentation fault.
  0x00000000005e7515 in auxtrace__free (session=0xffffffffffffffff) at util/auxtrace.c:2858
  2858		if (!session->auxtrace)
  (gdb) p session
  $1 = (struct perf_session *) 0xffffffffffffffff
  (gdb) bt
  #0  0x00000000005e7515 in auxtrace__free (session=0xffffffffffffffff) at util/auxtrace.c:2858
  #1  0x000000000057bb4d in perf_session__delete (session=0xffffffffffffffff) at util/session.c:300
  #2  0x000000000047c421 in __cmd_contention (argc=0, argv=0x7fffffffe200) at builtin-lock.c:2161
  #3  0x000000000047dc95 in cmd_lock (argc=0, argv=0x7fffffffe200) at builtin-lock.c:2604
  #4  0x0000000000501466 in run_builtin (p=0xe597a8 <commands+552>, argc=2, argv=0x7fffffffe200) at perf.c:322
  #5  0x00000000005016d5 in handle_internal_command (argc=2, argv=0x7fffffffe200) at perf.c:375
  #6  0x0000000000501824 in run_argv (argcp=0x7fffffffe02c, argv=0x7fffffffe020) at perf.c:419
  #7  0x0000000000501b11 in main (argc=2, argv=0x7fffffffe200) at perf.c:535
  (gdb)

So just set it to NULL after using PTR_ERR(session) to decode the error
as perf_session__delete(NULL) is supported.

The same problem was found in 'perf top' after an audit of all
perf_session__new() failure handling.

Fixes: 6ef81c55a2b6584c ("perf session: Return error code for perf_session__new() function on failure")
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jeremie Galarneau <jeremie.galarneau@efficios.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kate Stewart <kstewart@linuxfoundation.org>
Cc: Mamatha Inamdar <mamatha4@linux.vnet.ibm.com>
Cc: Mukesh Ojha <mojha@codeaurora.org>
Cc: Nageswara R Sastry <rnsastry@linux.vnet.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Cc: Shawn Landden <shawn@git.icu>
Cc: Song Liu <songliubraving@fb.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tzvetomir Stoyanov <tstoyanov@vmware.com>
Link: https://lore.kernel.org/lkml/ZN4Q2rxxsL08A8rd@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-top.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 1baa2acb3ced..ea8c7eca5eee 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1805,6 +1805,7 @@ int cmd_top(int argc, const char **argv)
 	top.session = perf_session__new(NULL, NULL);
 	if (IS_ERR(top.session)) {
 		status = PTR_ERR(top.session);
+		top.session = NULL;
 		goto out_delete_evlist;
 	}
 

From abaf1e0355abb050f9c11d2d13a513caec80f7ad Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 17 Aug 2023 09:11:21 -0300
Subject: [PATCH 0511/1189] perf lock: Don't pass an ERR_PTR() directly to
 perf_session__delete()

While debugging a segfault on 'perf lock contention' without an
available perf.data file I noticed that it was basically calling:

	perf_session__delete(ERR_PTR(-1))

Resulting in:

  (gdb) run lock contention
  Starting program: /root/bin/perf lock contention
  [Thread debugging using libthread_db enabled]
  Using host libthread_db library "/lib64/libthread_db.so.1".
  failed to open perf.data: No such file or directory  (try 'perf record' first)
  Initializing perf session failed

  Program received signal SIGSEGV, Segmentation fault.
  0x00000000005e7515 in auxtrace__free (session=0xffffffffffffffff) at util/auxtrace.c:2858
  2858		if (!session->auxtrace)
  (gdb) p session
  $1 = (struct perf_session *) 0xffffffffffffffff
  (gdb) bt
  #0  0x00000000005e7515 in auxtrace__free (session=0xffffffffffffffff) at util/auxtrace.c:2858
  #1  0x000000000057bb4d in perf_session__delete (session=0xffffffffffffffff) at util/session.c:300
  #2  0x000000000047c421 in __cmd_contention (argc=0, argv=0x7fffffffe200) at builtin-lock.c:2161
  #3  0x000000000047dc95 in cmd_lock (argc=0, argv=0x7fffffffe200) at builtin-lock.c:2604
  #4  0x0000000000501466 in run_builtin (p=0xe597a8 <commands+552>, argc=2, argv=0x7fffffffe200) at perf.c:322
  #5  0x00000000005016d5 in handle_internal_command (argc=2, argv=0x7fffffffe200) at perf.c:375
  #6  0x0000000000501824 in run_argv (argcp=0x7fffffffe02c, argv=0x7fffffffe020) at perf.c:419
  #7  0x0000000000501b11 in main (argc=2, argv=0x7fffffffe200) at perf.c:535
  (gdb)

So just set it to NULL after using PTR_ERR(session) to decode the error
as perf_session__delete(NULL) is supported.

Fixes: eef4fee5e52071d5 ("perf lock: Dynamically allocate lockhash_table")
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mamatha Inamdar <mamatha4@linux.vnet.ibm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Ross Zwisler <zwisler@chromium.org>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: Tiezhu Yang <yangtiezhu@loongson.cn>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/lkml/ZN4R1AYfsD2J8lRs@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-lock.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index c15386cb1033..0cf1c5a2e032 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -2052,6 +2052,7 @@ static int __cmd_contention(int argc, const char **argv)
 	if (IS_ERR(session)) {
 		pr_err("Initializing perf session failed\n");
 		err = PTR_ERR(session);
+		session = NULL;
 		goto out_delete;
 	}
 

From 3e1efe2b67d3d38116ec010968dbcd89d29e4561 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:41:44 -0700
Subject: [PATCH 0512/1189] KVM: Wrap kvm_{gfn,hva}_range.pte in a per-action
 union

Wrap kvm_{gfn,hva}_range.pte in a union so that future notifier events can
pass event specific information up and down the stack without needing to
constantly expand and churn the APIs.  Lockless aging of SPTEs will pass
around a bitmap, and support for memory attributes will pass around the
new attributes for the range.

Add a "KVM_NO_ARG" placeholder to simplify handling events without an
argument (creating a dummy union variable is midly annoying).

Opportunstically drop explicit zero-initialization of the "pte" field, as
omitting the field (now a union) has the same effect.

Cc: Yu Zhao <yuzhao@google.com>
Link: https://lore.kernel.org/all/CAOUHufagkd2Jk3_HrVoFFptRXM=hX2CV8f+M-dka-hJU4bP8kw@mail.gmail.com
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Acked-by: Yu Zhao <yuzhao@google.com>
Link: https://lore.kernel.org/r/20230729004144.1054885-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/arm64/kvm/mmu.c       |  2 +-
 arch/mips/kvm/mmu.c        |  2 +-
 arch/riscv/kvm/mmu.c       |  2 +-
 arch/x86/kvm/mmu/mmu.c     |  2 +-
 arch/x86/kvm/mmu/tdp_mmu.c |  6 +++---
 include/linux/kvm_host.h   |  6 +++++-
 virt/kvm/kvm_main.c        | 19 ++++++++++---------
 7 files changed, 22 insertions(+), 17 deletions(-)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 6db9ef288ec3..55f03a68f1cd 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1721,7 +1721,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 
 bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 {
-	kvm_pfn_t pfn = pte_pfn(range->pte);
+	kvm_pfn_t pfn = pte_pfn(range->arg.pte);
 
 	if (!kvm->arch.mmu.pgt)
 		return false;
diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c
index e8c08988ed37..7b2ac1319d70 100644
--- a/arch/mips/kvm/mmu.c
+++ b/arch/mips/kvm/mmu.c
@@ -447,7 +447,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 {
 	gpa_t gpa = range->start << PAGE_SHIFT;
-	pte_t hva_pte = range->pte;
+	pte_t hva_pte = range->arg.pte;
 	pte_t *gpa_pte = kvm_mips_pte_for_gpa(kvm, NULL, gpa);
 	pte_t old_pte;
 
diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index f2eb47925806..857f4312b0f8 100644
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -559,7 +559,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 {
 	int ret;
-	kvm_pfn_t pfn = pte_pfn(range->pte);
+	kvm_pfn_t pfn = pte_pfn(range->arg.pte);
 
 	if (!kvm->arch.pgd)
 		return false;
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index ec169f5c7dce..d72f2b20f430 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1588,7 +1588,7 @@ static __always_inline bool kvm_handle_gfn_range(struct kvm *kvm,
 	for_each_slot_rmap_range(range->slot, PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL,
 				 range->start, range->end - 1, &iterator)
 		ret |= handler(kvm, iterator.rmap, range->slot, iterator.gfn,
-			       iterator.level, range->pte);
+			       iterator.level, range->arg.pte);
 
 	return ret;
 }
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 512163d52194..6250bd3d20c1 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1241,7 +1241,7 @@ static bool set_spte_gfn(struct kvm *kvm, struct tdp_iter *iter,
 	u64 new_spte;
 
 	/* Huge pages aren't expected to be modified without first being zapped. */
-	WARN_ON(pte_huge(range->pte) || range->start + 1 != range->end);
+	WARN_ON(pte_huge(range->arg.pte) || range->start + 1 != range->end);
 
 	if (iter->level != PG_LEVEL_4K ||
 	    !is_shadow_present_pte(iter->old_spte))
@@ -1255,9 +1255,9 @@ static bool set_spte_gfn(struct kvm *kvm, struct tdp_iter *iter,
 	 */
 	tdp_mmu_iter_set_spte(kvm, iter, 0);
 
-	if (!pte_write(range->pte)) {
+	if (!pte_write(range->arg.pte)) {
 		new_spte = kvm_mmu_changed_pte_notifier_make_spte(iter->old_spte,
-								  pte_pfn(range->pte));
+								  pte_pfn(range->arg.pte));
 
 		tdp_mmu_iter_set_spte(kvm, iter, new_spte);
 	}
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 9d3ac7720da9..9125d0ab642d 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -256,11 +256,15 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
 #endif
 
 #ifdef KVM_ARCH_WANT_MMU_NOTIFIER
+union kvm_mmu_notifier_arg {
+	pte_t pte;
+};
+
 struct kvm_gfn_range {
 	struct kvm_memory_slot *slot;
 	gfn_t start;
 	gfn_t end;
-	pte_t pte;
+	union kvm_mmu_notifier_arg arg;
 	bool may_block;
 };
 bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index dfbaafbe3a00..92c50dc159e8 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -526,7 +526,7 @@ typedef void (*on_unlock_fn_t)(struct kvm *kvm);
 struct kvm_hva_range {
 	unsigned long start;
 	unsigned long end;
-	pte_t pte;
+	union kvm_mmu_notifier_arg arg;
 	hva_handler_t handler;
 	on_lock_fn_t on_lock;
 	on_unlock_fn_t on_unlock;
@@ -547,6 +547,8 @@ static void kvm_null_fn(void)
 }
 #define IS_KVM_NULL_FN(fn) ((fn) == (void *)kvm_null_fn)
 
+static const union kvm_mmu_notifier_arg KVM_MMU_NOTIFIER_NO_ARG;
+
 /* Iterate over each memslot intersecting [start, last] (inclusive) range */
 #define kvm_for_each_memslot_in_hva_range(node, slots, start, last)	     \
 	for (node = interval_tree_iter_first(&slots->hva_tree, start, last); \
@@ -591,7 +593,7 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
 			 * bother making these conditional (to avoid writes on
 			 * the second or later invocation of the handler).
 			 */
-			gfn_range.pte = range->pte;
+			gfn_range.arg = range->arg;
 			gfn_range.may_block = range->may_block;
 
 			/*
@@ -632,14 +634,14 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
 static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn,
 						unsigned long start,
 						unsigned long end,
-						pte_t pte,
+						union kvm_mmu_notifier_arg arg,
 						hva_handler_t handler)
 {
 	struct kvm *kvm = mmu_notifier_to_kvm(mn);
 	const struct kvm_hva_range range = {
 		.start		= start,
 		.end		= end,
-		.pte		= pte,
+		.arg		= arg,
 		.handler	= handler,
 		.on_lock	= (void *)kvm_null_fn,
 		.on_unlock	= (void *)kvm_null_fn,
@@ -659,7 +661,6 @@ static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn
 	const struct kvm_hva_range range = {
 		.start		= start,
 		.end		= end,
-		.pte		= __pte(0),
 		.handler	= handler,
 		.on_lock	= (void *)kvm_null_fn,
 		.on_unlock	= (void *)kvm_null_fn,
@@ -693,6 +694,7 @@ static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
 					pte_t pte)
 {
 	struct kvm *kvm = mmu_notifier_to_kvm(mn);
+	const union kvm_mmu_notifier_arg arg = { .pte = pte };
 
 	trace_kvm_set_spte_hva(address);
 
@@ -708,7 +710,7 @@ static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
 	if (!READ_ONCE(kvm->mmu_invalidate_in_progress))
 		return;
 
-	kvm_handle_hva_range(mn, address, address + 1, pte, kvm_change_spte_gfn);
+	kvm_handle_hva_range(mn, address, address + 1, arg, kvm_change_spte_gfn);
 }
 
 void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
@@ -747,7 +749,6 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	const struct kvm_hva_range hva_range = {
 		.start		= range->start,
 		.end		= range->end,
-		.pte		= __pte(0),
 		.handler	= kvm_unmap_gfn_range,
 		.on_lock	= kvm_mmu_invalidate_begin,
 		.on_unlock	= kvm_arch_guest_memory_reclaimed,
@@ -812,7 +813,6 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 	const struct kvm_hva_range hva_range = {
 		.start		= range->start,
 		.end		= range->end,
-		.pte		= __pte(0),
 		.handler	= (void *)kvm_null_fn,
 		.on_lock	= kvm_mmu_invalidate_end,
 		.on_unlock	= (void *)kvm_null_fn,
@@ -845,7 +845,8 @@ static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
 {
 	trace_kvm_age_hva(start, end);
 
-	return kvm_handle_hva_range(mn, start, end, __pte(0), kvm_age_gfn);
+	return kvm_handle_hva_range(mn, start, end, KVM_MMU_NOTIFIER_NO_ARG,
+				    kvm_age_gfn);
 }
 
 static int kvm_mmu_notifier_clear_young(struct mmu_notifier *mn,

From 765da7fe0e76ed41eea9514433f4ca8cdb5312b1 Mon Sep 17 00:00:00 2001
From: Like Xu <likexu@tencent.com>
Date: Mon, 7 Aug 2023 17:42:43 +0800
Subject: [PATCH 0513/1189] KVM: x86: Remove break statements that will never
 be executed

Fix compiler warnings when compiling KVM with [-Wunreachable-code-break].
No functional change intended.

Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Like Xu <likexu@tencent.com>
Link: https://lore.kernel.org/r/20230807094243.32516-1-likexu@tencent.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/emulate.c | 2 --
 arch/x86/kvm/hyperv.c  | 1 -
 arch/x86/kvm/x86.c     | 1 -
 3 files changed, 4 deletions(-)

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 936a397a08cd..2673cd5c46cb 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1799,13 +1799,11 @@ static int writeback(struct x86_emulate_ctxt *ctxt, struct operand *op)
 					       op->addr.mem,
 					       &op->val,
 					       op->bytes);
-		break;
 	case OP_MEM_STR:
 		return segmented_write(ctxt,
 				       op->addr.mem,
 				       op->data,
 				       op->bytes * op->count);
-		break;
 	case OP_XMM:
 		kvm_write_sse_reg(op->addr.xmm, &op->vec_val);
 		break;
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index b28fd020066f..7c2dac6824e2 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1293,7 +1293,6 @@ static bool hv_check_msr_access(struct kvm_vcpu_hv *hv_vcpu, u32 msr)
 	case HV_X64_MSR_VP_ASSIST_PAGE:
 		return hv_vcpu->cpuid_cache.features_eax &
 			HV_MSR_APIC_ACCESS_AVAILABLE;
-		break;
 	case HV_X64_MSR_TSC_FREQUENCY:
 	case HV_X64_MSR_APIC_FREQUENCY:
 		return hv_vcpu->cpuid_cache.features_eax &
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 80ec33fc823b..5ff77a70b382 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4646,7 +4646,6 @@ static int kvm_x86_dev_get_attr(struct kvm_device_attr *attr)
 		return 0;
 	default:
 		return -ENXIO;
-		break;
 	}
 }
 

From 7b0151caf73a656b75b550e361648430233455a0 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 8 Aug 2023 16:20:57 -0700
Subject: [PATCH 0514/1189] KVM: x86: Remove WARN sanity check on hypervisor
 timer vs. UNINITIALIZED vCPU

Drop the WARN in KVM_RUN that asserts that KVM isn't using the hypervisor
timer, a.k.a. the VMX preemption timer, for a vCPU that is in the
UNINITIALIZIED activity state.  The intent of the WARN is to sanity check
that KVM won't drop a timer interrupt due to an unexpected transition to
UNINITIALIZED, but unfortunately userspace can use various ioctl()s to
force the unexpected state.

Drop the sanity check instead of switching from the hypervisor timer to a
software based timer, as the only reason to switch to a software timer
when a vCPU is blocking is to ensure the timer interrupt wakes the vCPU,
but said interrupt isn't a valid wake event for vCPUs in UNINITIALIZED
state *and* the interrupt will be dropped in the end.

Reported-by: Yikebaer Aizezi <yikebaer61@gmail.com>
Closes: https://lore.kernel.org/all/CALcu4rbFrU4go8sBHk3FreP+qjgtZCGcYNpSiEXOLm==qFv7iQ@mail.gmail.com
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Link: https://lore.kernel.org/r/20230808232057.2498287-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/x86.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 5ff77a70b382..d293adc05145 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -11084,12 +11084,17 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 			r = -EINTR;
 			goto out;
 		}
-		/*
-		 * It should be impossible for the hypervisor timer to be in
-		 * use before KVM has ever run the vCPU.
-		 */
-		WARN_ON_ONCE(kvm_lapic_hv_timer_in_use(vcpu));
 
+		/*
+		 * Don't bother switching APIC timer emulation from the
+		 * hypervisor timer to the software timer, the only way for the
+		 * APIC timer to be active is if userspace stuffed vCPU state,
+		 * i.e. put the vCPU into a nonsensical state.  Only an INIT
+		 * will transition the vCPU out of UNINITIALIZED (without more
+		 * state stuffing from userspace), which will reset the local
+		 * APIC and thus cancel the timer or drop the IRQ (if the timer
+		 * already expired).
+		 */
 		kvm_vcpu_srcu_read_unlock(vcpu);
 		kvm_vcpu_block(vcpu);
 		kvm_vcpu_srcu_read_lock(vcpu);

From 4c08e737f056fec930b416a2bd37ed266d724f95 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 8 Aug 2023 16:31:31 -0700
Subject: [PATCH 0515/1189] KVM: SVM: Take and hold ir_list_lock when updating
 vCPU's Physical ID entry

Hoist the acquisition of ir_list_lock from avic_update_iommu_vcpu_affinity()
to its two callers, avic_vcpu_load() and avic_vcpu_put(), specifically to
encapsulate the write to the vCPU's entry in the AVIC Physical ID table.
This will allow a future fix to pull information from the Physical ID entry
when updating the IRTE, without potentially consuming stale information,
i.e. without racing with the vCPU being (un)loaded.

Add a comment to call out that ir_list_lock does NOT protect against
multiple writers, specifically that reading the Physical ID entry in
avic_vcpu_put() outside of the lock is safe.

To preserve some semblance of independence from ir_list_lock, keep the
READ_ONCE() in avic_vcpu_load() even though acuiring the spinlock
effectively ensures the load(s) will be generated after acquiring the
lock.

Cc: stable@vger.kernel.org
Tested-by: Alejandro Jimenez <alejandro.j.jimenez@oracle.com>
Reviewed-by: Joao Martins <joao.m.martins@oracle.com>
Link: https://lore.kernel.org/r/20230808233132.2499764-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/avic.c | 31 +++++++++++++++++++++++--------
 1 file changed, 23 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index cfc8ab773025..8e041b215ddb 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -986,10 +986,11 @@ static inline int
 avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r)
 {
 	int ret = 0;
-	unsigned long flags;
 	struct amd_svm_iommu_ir *ir;
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	lockdep_assert_held(&svm->ir_list_lock);
+
 	if (!kvm_arch_has_assigned_device(vcpu->kvm))
 		return 0;
 
@@ -997,19 +998,15 @@ avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r)
 	 * Here, we go through the per-vcpu ir_list to update all existing
 	 * interrupt remapping table entry targeting this vcpu.
 	 */
-	spin_lock_irqsave(&svm->ir_list_lock, flags);
-
 	if (list_empty(&svm->ir_list))
-		goto out;
+		return 0;
 
 	list_for_each_entry(ir, &svm->ir_list, node) {
 		ret = amd_iommu_update_ga(cpu, r, ir->data);
 		if (ret)
-			break;
+			return ret;
 	}
-out:
-	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
-	return ret;
+	return 0;
 }
 
 void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
@@ -1017,6 +1014,7 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	u64 entry;
 	int h_physical_id = kvm_cpu_get_apicid(cpu);
 	struct vcpu_svm *svm = to_svm(vcpu);
+	unsigned long flags;
 
 	lockdep_assert_preemption_disabled();
 
@@ -1033,6 +1031,8 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	if (kvm_vcpu_is_blocking(vcpu))
 		return;
 
+	spin_lock_irqsave(&svm->ir_list_lock, flags);
+
 	entry = READ_ONCE(*(svm->avic_physical_id_cache));
 	WARN_ON_ONCE(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK);
 
@@ -1042,25 +1042,40 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
 	avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, true);
+
+	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
 }
 
 void avic_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	u64 entry;
 	struct vcpu_svm *svm = to_svm(vcpu);
+	unsigned long flags;
 
 	lockdep_assert_preemption_disabled();
 
+	/*
+	 * Note, reading the Physical ID entry outside of ir_list_lock is safe
+	 * as only the pCPU that has loaded (or is loading) the vCPU is allowed
+	 * to modify the entry, and preemption is disabled.  I.e. the vCPU
+	 * can't be scheduled out and thus avic_vcpu_{put,load}() can't run
+	 * recursively.
+	 */
 	entry = READ_ONCE(*(svm->avic_physical_id_cache));
 
 	/* Nothing to do if IsRunning == '0' due to vCPU blocking. */
 	if (!(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK))
 		return;
 
+	spin_lock_irqsave(&svm->ir_list_lock, flags);
+
 	avic_update_iommu_vcpu_affinity(vcpu, -1, 0);
 
 	entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
 	WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
+
+	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
+
 }
 
 void avic_refresh_virtual_apic_mode(struct kvm_vcpu *vcpu)

From f3cebc75e7425d6949d726bb8e937095b0aef025 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 8 Aug 2023 16:31:32 -0700
Subject: [PATCH 0516/1189] KVM: SVM: Set target pCPU during IRTE update if
 target vCPU is running

Update the target pCPU for IOMMU doorbells when updating IRTE routing if
KVM is actively running the associated vCPU.  KVM currently only updates
the pCPU when loading the vCPU (via avic_vcpu_load()), and so doorbell
events will be delayed until the vCPU goes through a put+load cycle (which
might very well "never" happen for the lifetime of the VM).

To avoid inserting a stale pCPU, e.g. due to racing between updating IRTE
routing and vCPU load/put, get the pCPU information from the vCPU's
Physical APIC ID table entry (a.k.a. avic_physical_id_cache in KVM) and
update the IRTE while holding ir_list_lock.  Add comments with --verbose
enabled to explain exactly what is and isn't protected by ir_list_lock.

Fixes: 411b44ba80ab ("svm: Implements update_pi_irte hook to setup posted interrupt")
Reported-by: dengqiao.joey <dengqiao.joey@bytedance.com>
Cc: stable@vger.kernel.org
Cc: Alejandro Jimenez <alejandro.j.jimenez@oracle.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Maxim Levitsky <mlevitsk@redhat.com>
Cc: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Tested-by: Alejandro Jimenez <alejandro.j.jimenez@oracle.com>
Reviewed-by: Joao Martins <joao.m.martins@oracle.com>
Link: https://lore.kernel.org/r/20230808233132.2499764-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/avic.c | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 8e041b215ddb..2092db892d7d 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -791,6 +791,7 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
 	int ret = 0;
 	unsigned long flags;
 	struct amd_svm_iommu_ir *ir;
+	u64 entry;
 
 	/**
 	 * In some cases, the existing irte is updated and re-set,
@@ -824,6 +825,18 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
 	ir->data = pi->ir_data;
 
 	spin_lock_irqsave(&svm->ir_list_lock, flags);
+
+	/*
+	 * Update the target pCPU for IOMMU doorbells if the vCPU is running.
+	 * If the vCPU is NOT running, i.e. is blocking or scheduled out, KVM
+	 * will update the pCPU info when the vCPU awkened and/or scheduled in.
+	 * See also avic_vcpu_load().
+	 */
+	entry = READ_ONCE(*(svm->avic_physical_id_cache));
+	if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)
+		amd_iommu_update_ga(entry & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK,
+				    true, pi->ir_data);
+
 	list_add(&ir->node, &svm->ir_list);
 	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
 out:
@@ -1031,6 +1044,13 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	if (kvm_vcpu_is_blocking(vcpu))
 		return;
 
+	/*
+	 * Grab the per-vCPU interrupt remapping lock even if the VM doesn't
+	 * _currently_ have assigned devices, as that can change.  Holding
+	 * ir_list_lock ensures that either svm_ir_list_add() will consume
+	 * up-to-date entry information, or that this task will wait until
+	 * svm_ir_list_add() completes to set the new target pCPU.
+	 */
 	spin_lock_irqsave(&svm->ir_list_lock, flags);
 
 	entry = READ_ONCE(*(svm->avic_physical_id_cache));
@@ -1067,6 +1087,14 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu)
 	if (!(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK))
 		return;
 
+	/*
+	 * Take and hold the per-vCPU interrupt remapping lock while updating
+	 * the Physical ID entry even though the lock doesn't protect against
+	 * multiple writers (see above).  Holding ir_list_lock ensures that
+	 * either svm_ir_list_add() will consume up-to-date entry information,
+	 * or that this task will wait until svm_ir_list_add() completes to
+	 * mark the vCPU as not running.
+	 */
 	spin_lock_irqsave(&svm->ir_list_lock, flags);
 
 	avic_update_iommu_vcpu_affinity(vcpu, -1, 0);

From 7d18eef13622d84af93086ae79f081692516ba85 Mon Sep 17 00:00:00 2001
From: Shiyuan Gao <gaoshiyuan@baidu.com>
Date: Thu, 10 Aug 2023 19:38:53 +0800
Subject: [PATCH 0517/1189] KVM: VMX: Rename vmx_get_max_tdp_level() to
 vmx_get_max_ept_level()

In VMX, ept_level looks better than tdp_level and is consistent with
SVM's get_npt_level().

Signed-off-by: Shiyuan Gao <gaoshiyuan@baidu.com>
Link: https://lore.kernel.org/r/20230810113853.98114-1-gaoshiyuan@baidu.com
[sean: massage changelog]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/vmx/vmx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 3f868826db7d..f848f43fa3e2 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -3315,7 +3315,7 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	vmx->emulation_required = vmx_emulation_required(vcpu);
 }
 
-static int vmx_get_max_tdp_level(void)
+static int vmx_get_max_ept_level(void)
 {
 	if (cpu_has_vmx_ept_5levels())
 		return 5;
@@ -8498,7 +8498,7 @@ static __init int hardware_setup(void)
 	 */
 	vmx_setup_me_spte_mask();
 
-	kvm_configure_mmu(enable_ept, 0, vmx_get_max_tdp_level(),
+	kvm_configure_mmu(enable_ept, 0, vmx_get_max_ept_level(),
 			  ept_caps_to_lpage_level(vmx_capability.ept));
 
 	/*

From 392a53246257a9f89ef421b60af62056ce374285 Mon Sep 17 00:00:00 2001
From: Li zeming <zeming@nfschina.com>
Date: Thu, 17 Aug 2023 08:26:31 +0800
Subject: [PATCH 0518/1189] x86: kvm: x86: Remove unnecessary initial values of
 variables

bitmap and khz is assigned first, so it does not need to initialize the
assignment.

Signed-off-by: Li zeming <zeming@nfschina.com>
Link: https://lore.kernel.org/r/20230817002631.2885-1-zeming@nfschina.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/x86.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d293adc05145..c91de9897e32 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6512,7 +6512,7 @@ static void kvm_free_msr_filter(struct kvm_x86_msr_filter *msr_filter)
 static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter,
 			      struct kvm_msr_filter_range *user_range)
 {
-	unsigned long *bitmap = NULL;
+	unsigned long *bitmap;
 	size_t bitmap_size;
 
 	if (!user_range->nmsrs)
@@ -9146,7 +9146,7 @@ static int kvmclock_cpu_down_prep(unsigned int cpu)
 static void tsc_khz_changed(void *data)
 {
 	struct cpufreq_freqs *freq = data;
-	unsigned long khz = 0;
+	unsigned long khz;
 
 	WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_CONSTANT_TSC));
 

From f67063414c0e83bb4a9e12358cc179af53c2a8bb Mon Sep 17 00:00:00 2001
From: Manali Shukla <manali.shukla@amd.com>
Date: Mon, 17 Jul 2023 04:19:03 +0000
Subject: [PATCH 0519/1189] KVM: SVM: correct the size of spec_ctrl field in
 VMCB save area

Correct the spec_ctrl field in the VMCB save area based on the AMD
Programmer's manual.

Originally, the spec_ctrl was listed as u32 with 4 bytes of reserved
area.  The AMD Programmer's Manual now lists the spec_ctrl as 8 bytes
in VMCB save area.

The Public Processor Programming reference for Genoa, shows SPEC_CTRL
as 64b register, but the AMD Programmer's Manual lists SPEC_CTRL as
32b register. This discrepancy will be cleaned up in next revision of
the AMD Programmer's Manual.

Since remaining bits above bit 7 are reserved bits in SPEC_CTRL MSR
and thus, not being used, the spec_ctrl added as u32 in the VMCB save
area is currently not an issue.

Fixes: 3dd2775b74c9 ("KVM: SVM: Create a separate mapping for the SEV-ES save area")
Suggested-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Manali Shukla <manali.shukla@amd.com>
Link: https://lore.kernel.org/r/20230717041903.85480-1-manali.shukla@amd.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/svm.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 72ebd5e4e975..19bf955b67e0 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -346,7 +346,7 @@ struct vmcb_save_area {
 	u64 last_excp_from;
 	u64 last_excp_to;
 	u8 reserved_0x298[72];
-	u32 spec_ctrl;		/* Guest version of SPEC_CTRL at 0x2E0 */
+	u64 spec_ctrl;		/* Guest version of SPEC_CTRL at 0x2E0 */
 } __packed;
 
 /* Save area definition for SEV-ES and SEV-SNP guests */
@@ -513,7 +513,7 @@ struct ghcb {
 } __packed;
 
 
-#define EXPECTED_VMCB_SAVE_AREA_SIZE		740
+#define EXPECTED_VMCB_SAVE_AREA_SIZE		744
 #define EXPECTED_GHCB_SAVE_AREA_SIZE		1032
 #define EXPECTED_SEV_ES_SAVE_AREA_SIZE		1648
 #define EXPECTED_VMCB_CONTROL_AREA_SIZE		1024

From 42764413d19585caff1321823b376c0bd0a597af Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 15 Aug 2023 13:36:39 -0700
Subject: [PATCH 0520/1189] KVM: x86: Add a framework for enabling KVM-governed
 x86 features

Introduce yet another X86_FEATURE flag framework to manage and cache KVM
governed features (for lack of a better name).  "Governed" in this case
means that KVM has some level of involvement and/or vested interest in
whether or not an X86_FEATURE can be used by the guest.  The intent of the
framework is twofold: to simplify caching of guest CPUID flags that KVM
needs to frequently query, and to add clarity to such caching, e.g. it
isn't immediately obvious that SVM's bundle of flags for "optional nested
SVM features" track whether or not a flag is exposed to L1.

Begrudgingly define KVM_MAX_NR_GOVERNED_FEATURES for the size of the
bitmap to avoid exposing governed_features.h in arch/x86/include/asm/, but
add a FIXME to call out that it can and should be cleaned up once
"struct kvm_vcpu_arch" is no longer expose to the kernel at large.

Cc: Zeng Guang <guang.zeng@intel.com>
Reviewed-by: Binbin Wu <binbin.wu@linux.intel.com>
Reviewed-by: Kai Huang <kai.huang@intel.com>
Reviewed-by: Yuan Yao <yuan.yao@intel.com>
Link: https://lore.kernel.org/r/20230815203653.519297-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/kvm_host.h  | 19 +++++++++++++
 arch/x86/kvm/cpuid.c             |  4 +++
 arch/x86/kvm/cpuid.h             | 46 ++++++++++++++++++++++++++++++++
 arch/x86/kvm/governed_features.h |  9 +++++++
 4 files changed, 78 insertions(+)
 create mode 100644 arch/x86/kvm/governed_features.h

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index dad9331c5270..007fa8bfd634 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -831,6 +831,25 @@ struct kvm_vcpu_arch {
 	struct kvm_cpuid_entry2 *cpuid_entries;
 	struct kvm_hypervisor_cpuid kvm_cpuid;
 
+	/*
+	 * FIXME: Drop this macro and use KVM_NR_GOVERNED_FEATURES directly
+	 * when "struct kvm_vcpu_arch" is no longer defined in an
+	 * arch/x86/include/asm header.  The max is mostly arbitrary, i.e.
+	 * can be increased as necessary.
+	 */
+#define KVM_MAX_NR_GOVERNED_FEATURES BITS_PER_LONG
+
+	/*
+	 * Track whether or not the guest is allowed to use features that are
+	 * governed by KVM, where "governed" means KVM needs to manage state
+	 * and/or explicitly enable the feature in hardware.  Typically, but
+	 * not always, governed features can be used by the guest if and only
+	 * if both KVM and userspace want to expose the feature to the guest.
+	 */
+	struct {
+		DECLARE_BITMAP(enabled, KVM_MAX_NR_GOVERNED_FEATURES);
+	} governed_features;
+
 	u64 reserved_gpa_bits;
 	int maxphyaddr;
 
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 5a88affb2e1a..4ba43ae008cb 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -313,6 +313,10 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	struct kvm_cpuid_entry2 *best;
 
+	BUILD_BUG_ON(KVM_NR_GOVERNED_FEATURES > KVM_MAX_NR_GOVERNED_FEATURES);
+	bitmap_zero(vcpu->arch.governed_features.enabled,
+		    KVM_MAX_NR_GOVERNED_FEATURES);
+
 	best = kvm_find_cpuid_entry(vcpu, 1);
 	if (best && apic) {
 		if (cpuid_entry_has(best, X86_FEATURE_TSC_DEADLINE_TIMER))
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index b1658c0de847..284fa4704553 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -232,4 +232,50 @@ static __always_inline bool guest_pv_has(struct kvm_vcpu *vcpu,
 	return vcpu->arch.pv_cpuid.features & (1u << kvm_feature);
 }
 
+enum kvm_governed_features {
+#define KVM_GOVERNED_FEATURE(x) KVM_GOVERNED_##x,
+#include "governed_features.h"
+	KVM_NR_GOVERNED_FEATURES
+};
+
+static __always_inline int kvm_governed_feature_index(unsigned int x86_feature)
+{
+	switch (x86_feature) {
+#define KVM_GOVERNED_FEATURE(x) case x: return KVM_GOVERNED_##x;
+#include "governed_features.h"
+	default:
+		return -1;
+	}
+}
+
+static __always_inline bool kvm_is_governed_feature(unsigned int x86_feature)
+{
+	return kvm_governed_feature_index(x86_feature) >= 0;
+}
+
+static __always_inline void kvm_governed_feature_set(struct kvm_vcpu *vcpu,
+						     unsigned int x86_feature)
+{
+	BUILD_BUG_ON(!kvm_is_governed_feature(x86_feature));
+
+	__set_bit(kvm_governed_feature_index(x86_feature),
+		  vcpu->arch.governed_features.enabled);
+}
+
+static __always_inline void kvm_governed_feature_check_and_set(struct kvm_vcpu *vcpu,
+							       unsigned int x86_feature)
+{
+	if (kvm_cpu_cap_has(x86_feature) && guest_cpuid_has(vcpu, x86_feature))
+		kvm_governed_feature_set(vcpu, x86_feature);
+}
+
+static __always_inline bool guest_can_use(struct kvm_vcpu *vcpu,
+					  unsigned int x86_feature)
+{
+	BUILD_BUG_ON(!kvm_is_governed_feature(x86_feature));
+
+	return test_bit(kvm_governed_feature_index(x86_feature),
+			vcpu->arch.governed_features.enabled);
+}
+
 #endif
diff --git a/arch/x86/kvm/governed_features.h b/arch/x86/kvm/governed_features.h
new file mode 100644
index 000000000000..40ce8e6608cd
--- /dev/null
+++ b/arch/x86/kvm/governed_features.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#if !defined(KVM_GOVERNED_FEATURE) || defined(KVM_GOVERNED_X86_FEATURE)
+BUILD_BUG()
+#endif
+
+#define KVM_GOVERNED_X86_FEATURE(x) KVM_GOVERNED_FEATURE(X86_FEATURE_##x)
+
+#undef KVM_GOVERNED_X86_FEATURE
+#undef KVM_GOVERNED_FEATURE

From ccf31d6e6cc53e50cc42845061174082fd229c79 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 15 Aug 2023 13:36:40 -0700
Subject: [PATCH 0521/1189] KVM: x86/mmu: Use KVM-governed feature framework to
 track "GBPAGES enabled"

Use the governed feature framework to track whether or not the guest can
use 1GiB pages, and drop the one-off helper that wraps the surprisingly
non-trivial logic surrounding 1GiB page usage in the guest.

No functional change intended.

Reviewed-by: Yuan Yao <yuan.yao@intel.com>
Link: https://lore.kernel.org/r/20230815203653.519297-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/cpuid.c             | 17 +++++++++++++++++
 arch/x86/kvm/governed_features.h |  2 ++
 arch/x86/kvm/mmu/mmu.c           | 20 +++-----------------
 3 files changed, 22 insertions(+), 17 deletions(-)

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 4ba43ae008cb..67e9f79fe059 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -312,11 +312,28 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	struct kvm_cpuid_entry2 *best;
+	bool allow_gbpages;
 
 	BUILD_BUG_ON(KVM_NR_GOVERNED_FEATURES > KVM_MAX_NR_GOVERNED_FEATURES);
 	bitmap_zero(vcpu->arch.governed_features.enabled,
 		    KVM_MAX_NR_GOVERNED_FEATURES);
 
+	/*
+	 * If TDP is enabled, let the guest use GBPAGES if they're supported in
+	 * hardware.  The hardware page walker doesn't let KVM disable GBPAGES,
+	 * i.e. won't treat them as reserved, and KVM doesn't redo the GVA->GPA
+	 * walk for performance and complexity reasons.  Not to mention KVM
+	 * _can't_ solve the problem because GVA->GPA walks aren't visible to
+	 * KVM once a TDP translation is installed.  Mimic hardware behavior so
+	 * that KVM's is at least consistent, i.e. doesn't randomly inject #PF.
+	 * If TDP is disabled, honor *only* guest CPUID as KVM has full control
+	 * and can install smaller shadow pages if the host lacks 1GiB support.
+	 */
+	allow_gbpages = tdp_enabled ? boot_cpu_has(X86_FEATURE_GBPAGES) :
+				      guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES);
+	if (allow_gbpages)
+		kvm_governed_feature_set(vcpu, X86_FEATURE_GBPAGES);
+
 	best = kvm_find_cpuid_entry(vcpu, 1);
 	if (best && apic) {
 		if (cpuid_entry_has(best, X86_FEATURE_TSC_DEADLINE_TIMER))
diff --git a/arch/x86/kvm/governed_features.h b/arch/x86/kvm/governed_features.h
index 40ce8e6608cd..b29c15d5e038 100644
--- a/arch/x86/kvm/governed_features.h
+++ b/arch/x86/kvm/governed_features.h
@@ -5,5 +5,7 @@ BUILD_BUG()
 
 #define KVM_GOVERNED_X86_FEATURE(x) KVM_GOVERNED_FEATURE(X86_FEATURE_##x)
 
+KVM_GOVERNED_X86_FEATURE(GBPAGES)
+
 #undef KVM_GOVERNED_X86_FEATURE
 #undef KVM_GOVERNED_FEATURE
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 31d9cbe817a2..a0c2acb323eb 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4808,28 +4808,13 @@ static void __reset_rsvds_bits_mask(struct rsvd_bits_validate *rsvd_check,
 	}
 }
 
-static bool guest_can_use_gbpages(struct kvm_vcpu *vcpu)
-{
-	/*
-	 * If TDP is enabled, let the guest use GBPAGES if they're supported in
-	 * hardware.  The hardware page walker doesn't let KVM disable GBPAGES,
-	 * i.e. won't treat them as reserved, and KVM doesn't redo the GVA->GPA
-	 * walk for performance and complexity reasons.  Not to mention KVM
-	 * _can't_ solve the problem because GVA->GPA walks aren't visible to
-	 * KVM once a TDP translation is installed.  Mimic hardware behavior so
-	 * that KVM's is at least consistent, i.e. doesn't randomly inject #PF.
-	 */
-	return tdp_enabled ? boot_cpu_has(X86_FEATURE_GBPAGES) :
-			     guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES);
-}
-
 static void reset_guest_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 					struct kvm_mmu *context)
 {
 	__reset_rsvds_bits_mask(&context->guest_rsvd_check,
 				vcpu->arch.reserved_gpa_bits,
 				context->cpu_role.base.level, is_efer_nx(context),
-				guest_can_use_gbpages(vcpu),
+				guest_can_use(vcpu, X86_FEATURE_GBPAGES),
 				is_cr4_pse(context),
 				guest_cpuid_is_amd_or_hygon(vcpu));
 }
@@ -4906,7 +4891,8 @@ static void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
 	__reset_rsvds_bits_mask(shadow_zero_check, reserved_hpa_bits(),
 				context->root_role.level,
 				context->root_role.efer_nx,
-				guest_can_use_gbpages(vcpu), is_pse, is_amd);
+				guest_can_use(vcpu, X86_FEATURE_GBPAGES),
+				is_pse, is_amd);
 
 	if (!shadow_me_mask)
 		return;

From 1143c0b85c07fc45daf1c33b26ba9320becd6748 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 15 Aug 2023 13:36:41 -0700
Subject: [PATCH 0522/1189] KVM: VMX: Recompute "XSAVES enabled" only after
 CPUID update

Recompute whether or not XSAVES is enabled for the guest only if the
guest's CPUID model changes instead of redoing the computation every time
KVM generates vmcs01's secondary execution controls.  The boot_cpu_has()
and cpu_has_vmx_xsaves() checks should never change after KVM is loaded,
and if they do the kernel/KVM is hosed.

Opportunistically add a comment explaining _why_ XSAVES is effectively
exposed to the guest if and only if XSAVE is also exposed to the guest.

Practically speaking, no functional change intended (KVM will do fewer
computations, but should still see the same xsaves_enabled value whenever
KVM looks at it).

Reviewed-by: Yuan Yao <yuan.yao@intel.com>
Link: https://lore.kernel.org/r/20230815203653.519297-4-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/vmx/vmx.c | 24 +++++++++++-------------
 1 file changed, 11 insertions(+), 13 deletions(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 3235998ca261..159a58c12115 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -4612,19 +4612,10 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
 	if (!enable_pml || !atomic_read(&vcpu->kvm->nr_memslots_dirty_logging))
 		exec_control &= ~SECONDARY_EXEC_ENABLE_PML;
 
-	if (cpu_has_vmx_xsaves()) {
-		/* Exposing XSAVES only when XSAVE is exposed */
-		bool xsaves_enabled =
-			boot_cpu_has(X86_FEATURE_XSAVE) &&
-			guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
-			guest_cpuid_has(vcpu, X86_FEATURE_XSAVES);
-
-		vcpu->arch.xsaves_enabled = xsaves_enabled;
-
+	if (cpu_has_vmx_xsaves())
 		vmx_adjust_secondary_exec_control(vmx, &exec_control,
 						  SECONDARY_EXEC_XSAVES,
-						  xsaves_enabled, false);
-	}
+						  vcpu->arch.xsaves_enabled, false);
 
 	/*
 	 * RDPID is also gated by ENABLE_RDTSCP, turn on the control if either
@@ -7747,8 +7738,15 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	/* xsaves_enabled is recomputed in vmx_compute_secondary_exec_control(). */
-	vcpu->arch.xsaves_enabled = false;
+	/*
+	 * XSAVES is effectively enabled if and only if XSAVE is also exposed
+	 * to the guest.  XSAVES depends on CR4.OSXSAVE, and CR4.OSXSAVE can be
+	 * set if and only if XSAVE is supported.
+	 */
+	vcpu->arch.xsaves_enabled = cpu_has_vmx_xsaves() &&
+				    boot_cpu_has(X86_FEATURE_XSAVE) &&
+				    guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
+				    guest_cpuid_has(vcpu, X86_FEATURE_XSAVES);
 
 	vmx_setup_uret_msrs(vmx);
 

From 0497d2ac9b26d015cfafc4655ad9308c30a61810 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 15 Aug 2023 13:36:42 -0700
Subject: [PATCH 0523/1189] KVM: VMX: Check KVM CPU caps, not just VMX MSR
 support, for XSAVE enabling

Check KVM CPU capabilities instead of raw VMX support for XSAVES when
determining whether or not XSAVER can/should be exposed to the guest.
Practically speaking, it's nonsensical/impossible for a CPU to support
"enable XSAVES" without XSAVES being supported natively.  The real
motivation for checking kvm_cpu_cap_has() is to allow using the governed
feature's standard check-and-set logic.

Reviewed-by: Yuan Yao <yuan.yao@intel.com>
Link: https://lore.kernel.org/r/20230815203653.519297-5-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/vmx/vmx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 159a58c12115..968401b2efcd 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -7743,7 +7743,7 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	 * to the guest.  XSAVES depends on CR4.OSXSAVE, and CR4.OSXSAVE can be
 	 * set if and only if XSAVE is supported.
 	 */
-	vcpu->arch.xsaves_enabled = cpu_has_vmx_xsaves() &&
+	vcpu->arch.xsaves_enabled = kvm_cpu_cap_has(X86_FEATURE_XSAVES) &&
 				    boot_cpu_has(X86_FEATURE_XSAVE) &&
 				    guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
 				    guest_cpuid_has(vcpu, X86_FEATURE_XSAVES);

From 662f6815786efc9a60ee374142b3fd70db4637be Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 15 Aug 2023 13:36:43 -0700
Subject: [PATCH 0524/1189] KVM: VMX: Rename XSAVES control to follow KVM's
 preferred "ENABLE_XYZ"

Rename the XSAVES secondary execution control to follow KVM's preferred
style so that XSAVES related logic can use common macros that depend on
KVM's preferred style.

No functional change intended.

Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://lore.kernel.org/r/20230815203653.519297-6-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/vmx.h      | 2 +-
 arch/x86/kvm/vmx/capabilities.h | 2 +-
 arch/x86/kvm/vmx/hyperv.c       | 2 +-
 arch/x86/kvm/vmx/nested.c       | 6 +++---
 arch/x86/kvm/vmx/nested.h       | 2 +-
 arch/x86/kvm/vmx/vmx.c          | 2 +-
 arch/x86/kvm/vmx/vmx.h          | 2 +-
 7 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 0d02c4aafa6f..0e73616b82f3 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -71,7 +71,7 @@
 #define SECONDARY_EXEC_RDSEED_EXITING		VMCS_CONTROL_BIT(RDSEED_EXITING)
 #define SECONDARY_EXEC_ENABLE_PML               VMCS_CONTROL_BIT(PAGE_MOD_LOGGING)
 #define SECONDARY_EXEC_PT_CONCEAL_VMX		VMCS_CONTROL_BIT(PT_CONCEAL_VMX)
-#define SECONDARY_EXEC_XSAVES			VMCS_CONTROL_BIT(XSAVES)
+#define SECONDARY_EXEC_ENABLE_XSAVES		VMCS_CONTROL_BIT(XSAVES)
 #define SECONDARY_EXEC_MODE_BASED_EPT_EXEC	VMCS_CONTROL_BIT(MODE_BASED_EPT_EXEC)
 #define SECONDARY_EXEC_PT_USE_GPA		VMCS_CONTROL_BIT(PT_USE_GPA)
 #define SECONDARY_EXEC_TSC_SCALING              VMCS_CONTROL_BIT(TSC_SCALING)
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index d0abee35d7ba..41a4533f9989 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -252,7 +252,7 @@ static inline bool cpu_has_vmx_pml(void)
 static inline bool cpu_has_vmx_xsaves(void)
 {
 	return vmcs_config.cpu_based_2nd_exec_ctrl &
-		SECONDARY_EXEC_XSAVES;
+		SECONDARY_EXEC_ENABLE_XSAVES;
 }
 
 static inline bool cpu_has_vmx_waitpkg(void)
diff --git a/arch/x86/kvm/vmx/hyperv.c b/arch/x86/kvm/vmx/hyperv.c
index 79450e1ed7cf..313b8bb5b8a7 100644
--- a/arch/x86/kvm/vmx/hyperv.c
+++ b/arch/x86/kvm/vmx/hyperv.c
@@ -78,7 +78,7 @@
 	 SECONDARY_EXEC_DESC |						\
 	 SECONDARY_EXEC_ENABLE_RDTSCP |					\
 	 SECONDARY_EXEC_ENABLE_INVPCID |				\
-	 SECONDARY_EXEC_XSAVES |					\
+	 SECONDARY_EXEC_ENABLE_XSAVES |					\
 	 SECONDARY_EXEC_RDSEED_EXITING |				\
 	 SECONDARY_EXEC_RDRAND_EXITING |				\
 	 SECONDARY_EXEC_TSC_SCALING |					\
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 516391cc0d64..22e08d30baef 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2307,7 +2307,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0
 				  SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
 				  SECONDARY_EXEC_ENABLE_INVPCID |
 				  SECONDARY_EXEC_ENABLE_RDTSCP |
-				  SECONDARY_EXEC_XSAVES |
+				  SECONDARY_EXEC_ENABLE_XSAVES |
 				  SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE |
 				  SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
 				  SECONDARY_EXEC_APIC_REGISTER_VIRT |
@@ -6331,7 +6331,7 @@ static bool nested_vmx_l1_wants_exit(struct kvm_vcpu *vcpu,
 		 * If if it were, XSS would have to be checked against
 		 * the XSS exit bitmap in vmcs12.
 		 */
-		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES);
+		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_XSAVES);
 	case EXIT_REASON_UMWAIT:
 	case EXIT_REASON_TPAUSE:
 		return nested_cpu_has2(vmcs12,
@@ -6874,7 +6874,7 @@ static void nested_vmx_setup_secondary_ctls(u32 ept_caps,
 		SECONDARY_EXEC_ENABLE_INVPCID |
 		SECONDARY_EXEC_ENABLE_VMFUNC |
 		SECONDARY_EXEC_RDSEED_EXITING |
-		SECONDARY_EXEC_XSAVES |
+		SECONDARY_EXEC_ENABLE_XSAVES |
 		SECONDARY_EXEC_TSC_SCALING |
 		SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE;
 
diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h
index 96952263b029..b4b9d51438c6 100644
--- a/arch/x86/kvm/vmx/nested.h
+++ b/arch/x86/kvm/vmx/nested.h
@@ -168,7 +168,7 @@ static inline int nested_cpu_has_ept(struct vmcs12 *vmcs12)
 
 static inline bool nested_cpu_has_xsaves(struct vmcs12 *vmcs12)
 {
-	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES);
+	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_XSAVES);
 }
 
 static inline bool nested_cpu_has_pml(struct vmcs12 *vmcs12)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 968401b2efcd..d0bba4a34824 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -4614,7 +4614,7 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
 
 	if (cpu_has_vmx_xsaves())
 		vmx_adjust_secondary_exec_control(vmx, &exec_control,
-						  SECONDARY_EXEC_XSAVES,
+						  SECONDARY_EXEC_ENABLE_XSAVES,
 						  vcpu->arch.xsaves_enabled, false);
 
 	/*
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 32384ba38499..cde902b44d97 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -562,7 +562,7 @@ static inline u8 vmx_get_rvi(void)
 	 SECONDARY_EXEC_APIC_REGISTER_VIRT |				\
 	 SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |				\
 	 SECONDARY_EXEC_SHADOW_VMCS |					\
-	 SECONDARY_EXEC_XSAVES |					\
+	 SECONDARY_EXEC_ENABLE_XSAVES |					\
 	 SECONDARY_EXEC_RDSEED_EXITING |				\
 	 SECONDARY_EXEC_RDRAND_EXITING |				\
 	 SECONDARY_EXEC_ENABLE_PML |					\

From fe60e8f65f79138ffdcc8a9155036cc35f6079ac Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 15 Aug 2023 13:36:44 -0700
Subject: [PATCH 0525/1189] KVM: x86: Use KVM-governed feature framework to
 track "XSAVES enabled"

Use the governed feature framework to track if XSAVES is "enabled", i.e.
if XSAVES can be used by the guest.  Add a comment in the SVM code to
explain the very unintuitive logic of deliberately NOT checking if XSAVES
is enumerated in the guest CPUID model.

No functional change intended.

Reviewed-by: Yuan Yao <yuan.yao@intel.com>
Link: https://lore.kernel.org/r/20230815203653.519297-7-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/kvm_host.h  |  1 -
 arch/x86/kvm/governed_features.h |  1 +
 arch/x86/kvm/svm/svm.c           | 17 ++++++++++++---
 arch/x86/kvm/vmx/vmx.c           | 36 ++++++++++++++++----------------
 arch/x86/kvm/x86.c               |  4 ++--
 5 files changed, 35 insertions(+), 24 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 007fa8bfd634..771adf2438bc 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -746,7 +746,6 @@ struct kvm_vcpu_arch {
 	u64 smi_count;
 	bool at_instruction_boundary;
 	bool tpr_access_reporting;
-	bool xsaves_enabled;
 	bool xfd_no_write_intercept;
 	u64 ia32_xss;
 	u64 microcode_version;
diff --git a/arch/x86/kvm/governed_features.h b/arch/x86/kvm/governed_features.h
index b29c15d5e038..b896a64e4ac3 100644
--- a/arch/x86/kvm/governed_features.h
+++ b/arch/x86/kvm/governed_features.h
@@ -6,6 +6,7 @@ BUILD_BUG()
 #define KVM_GOVERNED_X86_FEATURE(x) KVM_GOVERNED_FEATURE(X86_FEATURE_##x)
 
 KVM_GOVERNED_X86_FEATURE(GBPAGES)
+KVM_GOVERNED_X86_FEATURE(XSAVES)
 
 #undef KVM_GOVERNED_X86_FEATURE
 #undef KVM_GOVERNED_FEATURE
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 6d8932e05753..1c6b1175016d 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4244,9 +4244,20 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct kvm_cpuid_entry2 *best;
 
-	vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
-				    boot_cpu_has(X86_FEATURE_XSAVE) &&
-				    boot_cpu_has(X86_FEATURE_XSAVES);
+	/*
+	 * SVM doesn't provide a way to disable just XSAVES in the guest, KVM
+	 * can only disable all variants of by disallowing CR4.OSXSAVE from
+	 * being set.  As a result, if the host has XSAVE and XSAVES, and the
+	 * guest has XSAVE enabled, the guest can execute XSAVES without
+	 * faulting.  Treat XSAVES as enabled in this case regardless of
+	 * whether it's advertised to the guest so that KVM context switches
+	 * XSS on VM-Enter/VM-Exit.  Failure to do so would effectively give
+	 * the guest read/write access to the host's XSS.
+	 */
+	if (boot_cpu_has(X86_FEATURE_XSAVE) &&
+	    boot_cpu_has(X86_FEATURE_XSAVES) &&
+	    guest_cpuid_has(vcpu, X86_FEATURE_XSAVE))
+		kvm_governed_feature_set(vcpu, X86_FEATURE_XSAVES);
 
 	/* Update nrips enabled cache */
 	svm->nrips_enabled = kvm_cpu_cap_has(X86_FEATURE_NRIPS) &&
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index d0bba4a34824..55cd17231867 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -4543,16 +4543,19 @@ vmx_adjust_secondary_exec_control(struct vcpu_vmx *vmx, u32 *exec_control,
  * based on a single guest CPUID bit, with a dedicated feature bit.  This also
  * verifies that the control is actually supported by KVM and hardware.
  */
-#define vmx_adjust_sec_exec_control(vmx, exec_control, name, feat_name, ctrl_name, exiting) \
-({									 \
-	bool __enabled;							 \
-									 \
-	if (cpu_has_vmx_##name()) {					 \
-		__enabled = guest_cpuid_has(&(vmx)->vcpu,		 \
-					    X86_FEATURE_##feat_name);	 \
-		vmx_adjust_secondary_exec_control(vmx, exec_control,	 \
-			SECONDARY_EXEC_##ctrl_name, __enabled, exiting); \
-	}								 \
+#define vmx_adjust_sec_exec_control(vmx, exec_control, name, feat_name, ctrl_name, exiting)	\
+({												\
+	struct kvm_vcpu *__vcpu = &(vmx)->vcpu;							\
+	bool __enabled;										\
+												\
+	if (cpu_has_vmx_##name()) {								\
+		if (kvm_is_governed_feature(X86_FEATURE_##feat_name))				\
+			__enabled = guest_can_use(__vcpu, X86_FEATURE_##feat_name);		\
+		else										\
+			__enabled = guest_cpuid_has(__vcpu, X86_FEATURE_##feat_name);		\
+		vmx_adjust_secondary_exec_control(vmx, exec_control, SECONDARY_EXEC_##ctrl_name,\
+						  __enabled, exiting);				\
+	}											\
 })
 
 /* More macro magic for ENABLE_/opt-in versus _EXITING/opt-out controls. */
@@ -4612,10 +4615,7 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
 	if (!enable_pml || !atomic_read(&vcpu->kvm->nr_memslots_dirty_logging))
 		exec_control &= ~SECONDARY_EXEC_ENABLE_PML;
 
-	if (cpu_has_vmx_xsaves())
-		vmx_adjust_secondary_exec_control(vmx, &exec_control,
-						  SECONDARY_EXEC_ENABLE_XSAVES,
-						  vcpu->arch.xsaves_enabled, false);
+	vmx_adjust_sec_exec_feature(vmx, &exec_control, xsaves, XSAVES);
 
 	/*
 	 * RDPID is also gated by ENABLE_RDTSCP, turn on the control if either
@@ -4634,6 +4634,7 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
 						  SECONDARY_EXEC_ENABLE_RDTSCP,
 						  rdpid_or_rdtscp_enabled, false);
 	}
+
 	vmx_adjust_sec_exec_feature(vmx, &exec_control, invpcid, INVPCID);
 
 	vmx_adjust_sec_exec_exiting(vmx, &exec_control, rdrand, RDRAND);
@@ -7743,10 +7744,9 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	 * to the guest.  XSAVES depends on CR4.OSXSAVE, and CR4.OSXSAVE can be
 	 * set if and only if XSAVE is supported.
 	 */
-	vcpu->arch.xsaves_enabled = kvm_cpu_cap_has(X86_FEATURE_XSAVES) &&
-				    boot_cpu_has(X86_FEATURE_XSAVE) &&
-				    guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
-				    guest_cpuid_has(vcpu, X86_FEATURE_XSAVES);
+	if (boot_cpu_has(X86_FEATURE_XSAVE) &&
+	    guest_cpuid_has(vcpu, X86_FEATURE_XSAVE))
+		kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_XSAVES);
 
 	vmx_setup_uret_msrs(vmx);
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c91de9897e32..7849ea0b0bf7 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1015,7 +1015,7 @@ void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu)
 		if (vcpu->arch.xcr0 != host_xcr0)
 			xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0);
 
-		if (vcpu->arch.xsaves_enabled &&
+		if (guest_can_use(vcpu, X86_FEATURE_XSAVES) &&
 		    vcpu->arch.ia32_xss != host_xss)
 			wrmsrl(MSR_IA32_XSS, vcpu->arch.ia32_xss);
 	}
@@ -1046,7 +1046,7 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu)
 		if (vcpu->arch.xcr0 != host_xcr0)
 			xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0);
 
-		if (vcpu->arch.xsaves_enabled &&
+		if (guest_can_use(vcpu, X86_FEATURE_XSAVES) &&
 		    vcpu->arch.ia32_xss != host_xss)
 			wrmsrl(MSR_IA32_XSS, host_xss);
 	}

From 1c18efdaa3148605071ae8b3551ee86c95c8807b Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 15 Aug 2023 13:36:45 -0700
Subject: [PATCH 0526/1189] KVM: nVMX: Use KVM-governed feature framework to
 track "nested VMX enabled"

Track "VMX exposed to L1" via a governed feature flag instead of using a
dedicated helper to provide the same functionality.  The main goal is to
drive convergence between VMX and SVM with respect to querying features
that are controllable via module param (SVM likes to cache nested
features), avoiding the guest CPUID lookups at runtime is just a bonus
and unlikely to provide any meaningful performance benefits.

Note, X86_FEATURE_VMX is set in kvm_cpu_caps if and only if "nested" is
true, and the CPU obviously supports VMX if KVM+VMX is running.  I.e. the
check on "nested" is now implicitly down by the kvm_cpu_cap_has() check
in kvm_governed_feature_check_and_set().

No functional change intended.

Reviewed-by: Yuan Yao <yuan.yao@intel.com>
Reviwed-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/r/20230815203653.519297-8-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/governed_features.h |  1 +
 arch/x86/kvm/vmx/nested.c        |  7 ++++---
 arch/x86/kvm/vmx/vmx.c           | 21 ++++++---------------
 arch/x86/kvm/vmx/vmx.h           |  1 -
 4 files changed, 11 insertions(+), 19 deletions(-)

diff --git a/arch/x86/kvm/governed_features.h b/arch/x86/kvm/governed_features.h
index b896a64e4ac3..22446614bf49 100644
--- a/arch/x86/kvm/governed_features.h
+++ b/arch/x86/kvm/governed_features.h
@@ -7,6 +7,7 @@ BUILD_BUG()
 
 KVM_GOVERNED_X86_FEATURE(GBPAGES)
 KVM_GOVERNED_X86_FEATURE(XSAVES)
+KVM_GOVERNED_X86_FEATURE(VMX)
 
 #undef KVM_GOVERNED_X86_FEATURE
 #undef KVM_GOVERNED_FEATURE
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 22e08d30baef..c5ec0ef51ff7 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -6426,7 +6426,7 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
 	vmx = to_vmx(vcpu);
 	vmcs12 = get_vmcs12(vcpu);
 
-	if (nested_vmx_allowed(vcpu) &&
+	if (guest_can_use(vcpu, X86_FEATURE_VMX) &&
 	    (vmx->nested.vmxon || vmx->nested.smm.vmxon)) {
 		kvm_state.hdr.vmx.vmxon_pa = vmx->nested.vmxon_ptr;
 		kvm_state.hdr.vmx.vmcs12_pa = vmx->nested.current_vmptr;
@@ -6567,7 +6567,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 		if (kvm_state->flags & ~KVM_STATE_NESTED_EVMCS)
 			return -EINVAL;
 	} else {
-		if (!nested_vmx_allowed(vcpu))
+		if (!guest_can_use(vcpu, X86_FEATURE_VMX))
 			return -EINVAL;
 
 		if (!page_address_valid(vcpu, kvm_state->hdr.vmx.vmxon_pa))
@@ -6601,7 +6601,8 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 
 	if ((kvm_state->flags & KVM_STATE_NESTED_EVMCS) &&
-		(!nested_vmx_allowed(vcpu) || !vmx->nested.enlightened_vmcs_enabled))
+	    (!guest_can_use(vcpu, X86_FEATURE_VMX) ||
+	     !vmx->nested.enlightened_vmcs_enabled))
 			return -EINVAL;
 
 	vmx_leave_nested(vcpu);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 55cd17231867..e9386afd1521 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1908,17 +1908,6 @@ static void vmx_write_tsc_multiplier(struct kvm_vcpu *vcpu)
 	vmcs_write64(TSC_MULTIPLIER, vcpu->arch.tsc_scaling_ratio);
 }
 
-/*
- * nested_vmx_allowed() checks whether a guest should be allowed to use VMX
- * instructions and MSRs (i.e., nested VMX). Nested VMX is disabled for
- * all guests if the "nested" module option is off, and can also be disabled
- * for a single guest by disabling its VMX cpuid bit.
- */
-bool nested_vmx_allowed(struct kvm_vcpu *vcpu)
-{
-	return nested && guest_cpuid_has(vcpu, X86_FEATURE_VMX);
-}
-
 /*
  * Userspace is allowed to set any supported IA32_FEATURE_CONTROL regardless of
  * guest CPUID.  Note, KVM allows userspace to set "VMX in SMX" to maintain
@@ -2046,7 +2035,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			[msr_info->index - MSR_IA32_SGXLEPUBKEYHASH0];
 		break;
 	case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR:
-		if (!nested_vmx_allowed(vcpu))
+		if (!guest_can_use(vcpu, X86_FEATURE_VMX))
 			return 1;
 		if (vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index,
 				    &msr_info->data))
@@ -2354,7 +2343,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR:
 		if (!msr_info->host_initiated)
 			return 1; /* they are read-only */
-		if (!nested_vmx_allowed(vcpu))
+		if (!guest_can_use(vcpu, X86_FEATURE_VMX))
 			return 1;
 		return vmx_set_vmx_msr(vcpu, msr_index, data);
 	case MSR_IA32_RTIT_CTL:
@@ -7748,13 +7737,15 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	    guest_cpuid_has(vcpu, X86_FEATURE_XSAVE))
 		kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_XSAVES);
 
+	kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_VMX);
+
 	vmx_setup_uret_msrs(vmx);
 
 	if (cpu_has_secondary_exec_ctrls())
 		vmcs_set_secondary_exec_control(vmx,
 						vmx_secondary_exec_control(vmx));
 
-	if (nested_vmx_allowed(vcpu))
+	if (guest_can_use(vcpu, X86_FEATURE_VMX))
 		vmx->msr_ia32_feature_control_valid_bits |=
 			FEAT_CTL_VMX_ENABLED_INSIDE_SMX |
 			FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX;
@@ -7763,7 +7754,7 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 			~(FEAT_CTL_VMX_ENABLED_INSIDE_SMX |
 			  FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX);
 
-	if (nested_vmx_allowed(vcpu))
+	if (guest_can_use(vcpu, X86_FEATURE_VMX))
 		nested_vmx_cr_fixed1_bits_update(vcpu);
 
 	if (boot_cpu_has(X86_FEATURE_INTEL_PT) &&
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index cde902b44d97..c2130d2c8e24 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -374,7 +374,6 @@ struct kvm_vmx {
 	u64 *pid_table;
 };
 
-bool nested_vmx_allowed(struct kvm_vcpu *vcpu);
 void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
 			struct loaded_vmcs *buddy);
 int allocate_vpid(void);

From 7a6a6a3bf5d8c32a91d8fabb0e2d31f3bd23a412 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 15 Aug 2023 13:36:46 -0700
Subject: [PATCH 0527/1189] KVM: nSVM: Use KVM-governed feature framework to
 track "NRIPS enabled"

Track "NRIPS exposed to L1" via a governed feature flag instead of using
a dedicated bit/flag in vcpu_svm.

No functional change intended.

Reviewed-by: Yuan Yao <yuan.yao@intel.com>
Link: https://lore.kernel.org/r/20230815203653.519297-9-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/governed_features.h | 1 +
 arch/x86/kvm/svm/nested.c        | 6 +++---
 arch/x86/kvm/svm/svm.c           | 4 +---
 arch/x86/kvm/svm/svm.h           | 1 -
 4 files changed, 5 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kvm/governed_features.h b/arch/x86/kvm/governed_features.h
index 22446614bf49..722b66af412c 100644
--- a/arch/x86/kvm/governed_features.h
+++ b/arch/x86/kvm/governed_features.h
@@ -8,6 +8,7 @@ BUILD_BUG()
 KVM_GOVERNED_X86_FEATURE(GBPAGES)
 KVM_GOVERNED_X86_FEATURE(XSAVES)
 KVM_GOVERNED_X86_FEATURE(VMX)
+KVM_GOVERNED_X86_FEATURE(NRIPS)
 
 #undef KVM_GOVERNED_X86_FEATURE
 #undef KVM_GOVERNED_FEATURE
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 3342cc4a5189..9092f3f8dccf 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -716,7 +716,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,
 	 * what a nrips=0 CPU would do (L1 is responsible for advancing RIP
 	 * prior to injecting the event).
 	 */
-	if (svm->nrips_enabled)
+	if (guest_can_use(vcpu, X86_FEATURE_NRIPS))
 		vmcb02->control.next_rip    = svm->nested.ctl.next_rip;
 	else if (boot_cpu_has(X86_FEATURE_NRIPS))
 		vmcb02->control.next_rip    = vmcb12_rip;
@@ -726,7 +726,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,
 		svm->soft_int_injected = true;
 		svm->soft_int_csbase = vmcb12_csbase;
 		svm->soft_int_old_rip = vmcb12_rip;
-		if (svm->nrips_enabled)
+		if (guest_can_use(vcpu, X86_FEATURE_NRIPS))
 			svm->soft_int_next_rip = svm->nested.ctl.next_rip;
 		else
 			svm->soft_int_next_rip = vmcb12_rip;
@@ -1026,7 +1026,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	if (vmcb12->control.exit_code != SVM_EXIT_ERR)
 		nested_save_pending_event_to_vmcb12(svm, vmcb12);
 
-	if (svm->nrips_enabled)
+	if (guest_can_use(vcpu, X86_FEATURE_NRIPS))
 		vmcb12->control.next_rip  = vmcb02->control.next_rip;
 
 	vmcb12->control.int_ctl           = svm->nested.ctl.int_ctl;
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 1c6b1175016d..de69e98a7c6a 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4259,9 +4259,7 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	    guest_cpuid_has(vcpu, X86_FEATURE_XSAVE))
 		kvm_governed_feature_set(vcpu, X86_FEATURE_XSAVES);
 
-	/* Update nrips enabled cache */
-	svm->nrips_enabled = kvm_cpu_cap_has(X86_FEATURE_NRIPS) &&
-			     guest_cpuid_has(vcpu, X86_FEATURE_NRIPS);
+	kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_NRIPS);
 
 	svm->tsc_scaling_enabled = tsc_scaling && guest_cpuid_has(vcpu, X86_FEATURE_TSCRATEMSR);
 	svm->lbrv_enabled = lbrv && guest_cpuid_has(vcpu, X86_FEATURE_LBRV);
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 5829a1801862..c06de55425d4 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -259,7 +259,6 @@ struct vcpu_svm {
 	bool soft_int_injected;
 
 	/* optional nested SVM features that are enabled for this guest  */
-	bool nrips_enabled                : 1;
 	bool tsc_scaling_enabled          : 1;
 	bool v_vmload_vmsave_enabled      : 1;
 	bool lbrv_enabled                 : 1;

From 4365a45571c791a2fbeb81cf27738960c5456f57 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 15 Aug 2023 13:36:47 -0700
Subject: [PATCH 0528/1189] KVM: nSVM: Use KVM-governed feature framework to
 track "TSC scaling enabled"

Track "TSC scaling exposed to L1" via a governed feature flag instead of
using a dedicated bit/flag in vcpu_svm.

Note, this fixes a benign bug where KVM would mark TSC scaling as exposed
to L1 even if overall nested SVM supported is disabled, i.e. KVM would let
L1 write MSR_AMD64_TSC_RATIO even when KVM didn't advertise TSCRATEMSR
support to userspace.

Reviewed-by: Yuan Yao <yuan.yao@intel.com>
Link: https://lore.kernel.org/r/20230815203653.519297-10-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/governed_features.h |  1 +
 arch/x86/kvm/svm/nested.c        |  2 +-
 arch/x86/kvm/svm/svm.c           | 10 ++++++----
 arch/x86/kvm/svm/svm.h           |  1 -
 4 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/governed_features.h b/arch/x86/kvm/governed_features.h
index 722b66af412c..32c0469cf952 100644
--- a/arch/x86/kvm/governed_features.h
+++ b/arch/x86/kvm/governed_features.h
@@ -9,6 +9,7 @@ KVM_GOVERNED_X86_FEATURE(GBPAGES)
 KVM_GOVERNED_X86_FEATURE(XSAVES)
 KVM_GOVERNED_X86_FEATURE(VMX)
 KVM_GOVERNED_X86_FEATURE(NRIPS)
+KVM_GOVERNED_X86_FEATURE(TSCRATEMSR)
 
 #undef KVM_GOVERNED_X86_FEATURE
 #undef KVM_GOVERNED_FEATURE
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 9092f3f8dccf..da65948064dc 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -695,7 +695,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,
 
 	vmcb02->control.tsc_offset = vcpu->arch.tsc_offset;
 
-	if (svm->tsc_scaling_enabled &&
+	if (guest_can_use(vcpu, X86_FEATURE_TSCRATEMSR) &&
 	    svm->tsc_ratio_msr != kvm_caps.default_tsc_scaling_ratio)
 		nested_svm_update_tsc_ratio_msr(vcpu);
 
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index de69e98a7c6a..0d5cca0bb5fb 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -2795,7 +2795,8 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 
 	switch (msr_info->index) {
 	case MSR_AMD64_TSC_RATIO:
-		if (!msr_info->host_initiated && !svm->tsc_scaling_enabled)
+		if (!msr_info->host_initiated &&
+		    !guest_can_use(vcpu, X86_FEATURE_TSCRATEMSR))
 			return 1;
 		msr_info->data = svm->tsc_ratio_msr;
 		break;
@@ -2937,7 +2938,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	switch (ecx) {
 	case MSR_AMD64_TSC_RATIO:
 
-		if (!svm->tsc_scaling_enabled) {
+		if (!guest_can_use(vcpu, X86_FEATURE_TSCRATEMSR)) {
 
 			if (!msr->host_initiated)
 				return 1;
@@ -2959,7 +2960,8 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 
 		svm->tsc_ratio_msr = data;
 
-		if (svm->tsc_scaling_enabled && is_guest_mode(vcpu))
+		if (guest_can_use(vcpu, X86_FEATURE_TSCRATEMSR) &&
+		    is_guest_mode(vcpu))
 			nested_svm_update_tsc_ratio_msr(vcpu);
 
 		break;
@@ -4260,8 +4262,8 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 		kvm_governed_feature_set(vcpu, X86_FEATURE_XSAVES);
 
 	kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_NRIPS);
+	kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_TSCRATEMSR);
 
-	svm->tsc_scaling_enabled = tsc_scaling && guest_cpuid_has(vcpu, X86_FEATURE_TSCRATEMSR);
 	svm->lbrv_enabled = lbrv && guest_cpuid_has(vcpu, X86_FEATURE_LBRV);
 
 	svm->v_vmload_vmsave_enabled = vls && guest_cpuid_has(vcpu, X86_FEATURE_V_VMSAVE_VMLOAD);
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index c06de55425d4..4e7332f77702 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -259,7 +259,6 @@ struct vcpu_svm {
 	bool soft_int_injected;
 
 	/* optional nested SVM features that are enabled for this guest  */
-	bool tsc_scaling_enabled          : 1;
 	bool v_vmload_vmsave_enabled      : 1;
 	bool lbrv_enabled                 : 1;
 	bool pause_filter_enabled         : 1;

From 4d2a1560ffc29525493829ee31dc069c00c52c69 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 15 Aug 2023 13:36:48 -0700
Subject: [PATCH 0529/1189] KVM: nSVM: Use KVM-governed feature framework to
 track "vVM{SAVE,LOAD} enabled"

Track "virtual VMSAVE/VMLOAD exposed to L1" via a governed feature flag
instead of using a dedicated bit/flag in vcpu_svm.

Opportunistically add a comment explaining why KVM disallows virtual
VMLOAD/VMSAVE when the vCPU model is Intel.

No functional change intended.

Link: https://lore.kernel.org/r/20230815203653.519297-11-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/governed_features.h |  1 +
 arch/x86/kvm/svm/nested.c        |  2 +-
 arch/x86/kvm/svm/svm.c           | 10 +++++++---
 arch/x86/kvm/svm/svm.h           |  1 -
 4 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/governed_features.h b/arch/x86/kvm/governed_features.h
index 32c0469cf952..f01a95fd0071 100644
--- a/arch/x86/kvm/governed_features.h
+++ b/arch/x86/kvm/governed_features.h
@@ -10,6 +10,7 @@ KVM_GOVERNED_X86_FEATURE(XSAVES)
 KVM_GOVERNED_X86_FEATURE(VMX)
 KVM_GOVERNED_X86_FEATURE(NRIPS)
 KVM_GOVERNED_X86_FEATURE(TSCRATEMSR)
+KVM_GOVERNED_X86_FEATURE(V_VMSAVE_VMLOAD)
 
 #undef KVM_GOVERNED_X86_FEATURE
 #undef KVM_GOVERNED_FEATURE
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index da65948064dc..24d47ebeb0e0 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -107,7 +107,7 @@ static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu)
 
 static bool nested_vmcb_needs_vls_intercept(struct vcpu_svm *svm)
 {
-	if (!svm->v_vmload_vmsave_enabled)
+	if (!guest_can_use(&svm->vcpu, X86_FEATURE_V_VMSAVE_VMLOAD))
 		return true;
 
 	if (!nested_npt_enabled(svm))
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 0d5cca0bb5fb..78d53ea513f4 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1194,8 +1194,6 @@ static inline void init_vmcb_after_set_cpuid(struct kvm_vcpu *vcpu)
 
 		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_EIP, 0, 0);
 		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_ESP, 0, 0);
-
-		svm->v_vmload_vmsave_enabled = false;
 	} else {
 		/*
 		 * If hardware supports Virtual VMLOAD VMSAVE then enable it
@@ -4266,7 +4264,13 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 
 	svm->lbrv_enabled = lbrv && guest_cpuid_has(vcpu, X86_FEATURE_LBRV);
 
-	svm->v_vmload_vmsave_enabled = vls && guest_cpuid_has(vcpu, X86_FEATURE_V_VMSAVE_VMLOAD);
+	/*
+	 * Intercept VMLOAD if the vCPU mode is Intel in order to emulate that
+	 * VMLOAD drops bits 63:32 of SYSENTER (ignoring the fact that exposing
+	 * SVM on Intel is bonkers and extremely unlikely to work).
+	 */
+	if (!guest_cpuid_is_intel(vcpu))
+		kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_V_VMSAVE_VMLOAD);
 
 	svm->pause_filter_enabled = kvm_cpu_cap_has(X86_FEATURE_PAUSEFILTER) &&
 			guest_cpuid_has(vcpu, X86_FEATURE_PAUSEFILTER);
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 4e7332f77702..b475241df6dc 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -259,7 +259,6 @@ struct vcpu_svm {
 	bool soft_int_injected;
 
 	/* optional nested SVM features that are enabled for this guest  */
-	bool v_vmload_vmsave_enabled      : 1;
 	bool lbrv_enabled                 : 1;
 	bool pause_filter_enabled         : 1;
 	bool pause_threshold_enabled      : 1;

From e183d17ac362655e5ef061760245b4402b9c04f8 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 15 Aug 2023 13:36:49 -0700
Subject: [PATCH 0530/1189] KVM: nSVM: Use KVM-governed feature framework to
 track "LBRv enabled"

Track "LBR virtualization exposed to L1" via a governed feature flag
instead of using a dedicated bit/flag in vcpu_svm.

Note, checking KVM's capabilities instead of the "lbrv" param means that
the code isn't strictly equivalent, as lbrv_enabled could have been set
if nested=false where as that the governed feature cannot.  But that's a
glorified nop as the feature/flag is consumed only by paths that are
gated by nSVM being enabled.

Link: https://lore.kernel.org/r/20230815203653.519297-12-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/governed_features.h |  1 +
 arch/x86/kvm/svm/nested.c        | 23 +++++++++++++----------
 arch/x86/kvm/svm/svm.c           |  5 ++---
 arch/x86/kvm/svm/svm.h           |  1 -
 4 files changed, 16 insertions(+), 14 deletions(-)

diff --git a/arch/x86/kvm/governed_features.h b/arch/x86/kvm/governed_features.h
index f01a95fd0071..3a4c0e40e1e0 100644
--- a/arch/x86/kvm/governed_features.h
+++ b/arch/x86/kvm/governed_features.h
@@ -11,6 +11,7 @@ KVM_GOVERNED_X86_FEATURE(VMX)
 KVM_GOVERNED_X86_FEATURE(NRIPS)
 KVM_GOVERNED_X86_FEATURE(TSCRATEMSR)
 KVM_GOVERNED_X86_FEATURE(V_VMSAVE_VMLOAD)
+KVM_GOVERNED_X86_FEATURE(LBRV)
 
 #undef KVM_GOVERNED_X86_FEATURE
 #undef KVM_GOVERNED_FEATURE
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 24d47ebeb0e0..f50f74b1a04e 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -552,6 +552,7 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12
 	bool new_vmcb12 = false;
 	struct vmcb *vmcb01 = svm->vmcb01.ptr;
 	struct vmcb *vmcb02 = svm->nested.vmcb02.ptr;
+	struct kvm_vcpu *vcpu = &svm->vcpu;
 
 	nested_vmcb02_compute_g_pat(svm);
 
@@ -577,18 +578,18 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12
 		vmcb_mark_dirty(vmcb02, VMCB_DT);
 	}
 
-	kvm_set_rflags(&svm->vcpu, vmcb12->save.rflags | X86_EFLAGS_FIXED);
+	kvm_set_rflags(vcpu, vmcb12->save.rflags | X86_EFLAGS_FIXED);
 
-	svm_set_efer(&svm->vcpu, svm->nested.save.efer);
+	svm_set_efer(vcpu, svm->nested.save.efer);
 
-	svm_set_cr0(&svm->vcpu, svm->nested.save.cr0);
-	svm_set_cr4(&svm->vcpu, svm->nested.save.cr4);
+	svm_set_cr0(vcpu, svm->nested.save.cr0);
+	svm_set_cr4(vcpu, svm->nested.save.cr4);
 
 	svm->vcpu.arch.cr2 = vmcb12->save.cr2;
 
-	kvm_rax_write(&svm->vcpu, vmcb12->save.rax);
-	kvm_rsp_write(&svm->vcpu, vmcb12->save.rsp);
-	kvm_rip_write(&svm->vcpu, vmcb12->save.rip);
+	kvm_rax_write(vcpu, vmcb12->save.rax);
+	kvm_rsp_write(vcpu, vmcb12->save.rsp);
+	kvm_rip_write(vcpu, vmcb12->save.rip);
 
 	/* In case we don't even reach vcpu_run, the fields are not updated */
 	vmcb02->save.rax = vmcb12->save.rax;
@@ -602,7 +603,8 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12
 		vmcb_mark_dirty(vmcb02, VMCB_DR);
 	}
 
-	if (unlikely(svm->lbrv_enabled && (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))) {
+	if (unlikely(guest_can_use(vcpu, X86_FEATURE_LBRV) &&
+		     (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))) {
 		/*
 		 * Reserved bits of DEBUGCTL are ignored.  Be consistent with
 		 * svm_set_msr's definition of reserved bits.
@@ -734,7 +736,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,
 
 	vmcb02->control.virt_ext            = vmcb01->control.virt_ext &
 					      LBR_CTL_ENABLE_MASK;
-	if (svm->lbrv_enabled)
+	if (guest_can_use(vcpu, X86_FEATURE_LBRV))
 		vmcb02->control.virt_ext  |=
 			(svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK);
 
@@ -1065,7 +1067,8 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	if (!nested_exit_on_intr(svm))
 		kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);
 
-	if (unlikely(svm->lbrv_enabled && (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))) {
+	if (unlikely(guest_can_use(vcpu, X86_FEATURE_LBRV) &&
+		     (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))) {
 		svm_copy_lbrs(vmcb12, vmcb02);
 		svm_update_lbrv(vcpu);
 	} else if (unlikely(vmcb01->control.virt_ext & LBR_CTL_ENABLE_MASK)) {
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 78d53ea513f4..3b8e412238d3 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1024,7 +1024,7 @@ void svm_update_lbrv(struct kvm_vcpu *vcpu)
 	bool current_enable_lbrv = !!(svm->vmcb->control.virt_ext &
 				      LBR_CTL_ENABLE_MASK);
 
-	if (unlikely(is_guest_mode(vcpu) && svm->lbrv_enabled))
+	if (unlikely(is_guest_mode(vcpu) && guest_can_use(vcpu, X86_FEATURE_LBRV)))
 		if (unlikely(svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))
 			enable_lbrv = true;
 
@@ -4261,8 +4261,7 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 
 	kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_NRIPS);
 	kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_TSCRATEMSR);
-
-	svm->lbrv_enabled = lbrv && guest_cpuid_has(vcpu, X86_FEATURE_LBRV);
+	kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_LBRV);
 
 	/*
 	 * Intercept VMLOAD if the vCPU mode is Intel in order to emulate that
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index b475241df6dc..0e21823e8a19 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -259,7 +259,6 @@ struct vcpu_svm {
 	bool soft_int_injected;
 
 	/* optional nested SVM features that are enabled for this guest  */
-	bool lbrv_enabled                 : 1;
 	bool pause_filter_enabled         : 1;
 	bool pause_threshold_enabled      : 1;
 	bool vgif_enabled                 : 1;

From 59d67fc1f0dbb5ee8841d62140efe0fdc4fbabf5 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 15 Aug 2023 13:36:50 -0700
Subject: [PATCH 0531/1189] KVM: nSVM: Use KVM-governed feature framework to
 track "Pause Filter enabled"

Track "Pause Filtering is exposed to L1" via governed feature flags
instead of using dedicated bits/flags in vcpu_svm.

No functional change intended.

Reviewed-by: Yuan Yao <yuan.yao@intel.com>
Link: https://lore.kernel.org/r/20230815203653.519297-13-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/governed_features.h |  2 ++
 arch/x86/kvm/svm/nested.c        | 10 ++++++++--
 arch/x86/kvm/svm/svm.c           |  7 ++-----
 arch/x86/kvm/svm/svm.h           |  2 --
 4 files changed, 12 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kvm/governed_features.h b/arch/x86/kvm/governed_features.h
index 3a4c0e40e1e0..9afd34f30599 100644
--- a/arch/x86/kvm/governed_features.h
+++ b/arch/x86/kvm/governed_features.h
@@ -12,6 +12,8 @@ KVM_GOVERNED_X86_FEATURE(NRIPS)
 KVM_GOVERNED_X86_FEATURE(TSCRATEMSR)
 KVM_GOVERNED_X86_FEATURE(V_VMSAVE_VMLOAD)
 KVM_GOVERNED_X86_FEATURE(LBRV)
+KVM_GOVERNED_X86_FEATURE(PAUSEFILTER)
+KVM_GOVERNED_X86_FEATURE(PFTHRESHOLD)
 
 #undef KVM_GOVERNED_X86_FEATURE
 #undef KVM_GOVERNED_FEATURE
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index f50f74b1a04e..ac03b2bc5b2c 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -743,8 +743,14 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,
 	if (!nested_vmcb_needs_vls_intercept(svm))
 		vmcb02->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK;
 
-	pause_count12 = svm->pause_filter_enabled ? svm->nested.ctl.pause_filter_count : 0;
-	pause_thresh12 = svm->pause_threshold_enabled ? svm->nested.ctl.pause_filter_thresh : 0;
+	if (guest_can_use(vcpu, X86_FEATURE_PAUSEFILTER))
+		pause_count12 = svm->nested.ctl.pause_filter_count;
+	else
+		pause_count12 = 0;
+	if (guest_can_use(vcpu, X86_FEATURE_PFTHRESHOLD))
+		pause_thresh12 = svm->nested.ctl.pause_filter_thresh;
+	else
+		pause_thresh12 = 0;
 	if (kvm_pause_in_guest(svm->vcpu.kvm)) {
 		/* use guest values since host doesn't intercept PAUSE */
 		vmcb02->control.pause_filter_count = pause_count12;
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 3b8e412238d3..0dc70ad88d29 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4271,11 +4271,8 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	if (!guest_cpuid_is_intel(vcpu))
 		kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_V_VMSAVE_VMLOAD);
 
-	svm->pause_filter_enabled = kvm_cpu_cap_has(X86_FEATURE_PAUSEFILTER) &&
-			guest_cpuid_has(vcpu, X86_FEATURE_PAUSEFILTER);
-
-	svm->pause_threshold_enabled = kvm_cpu_cap_has(X86_FEATURE_PFTHRESHOLD) &&
-			guest_cpuid_has(vcpu, X86_FEATURE_PFTHRESHOLD);
+	kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_PAUSEFILTER);
+	kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_PFTHRESHOLD);
 
 	svm->vgif_enabled = vgif && guest_cpuid_has(vcpu, X86_FEATURE_VGIF);
 
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 0e21823e8a19..fb438439b61e 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -259,8 +259,6 @@ struct vcpu_svm {
 	bool soft_int_injected;
 
 	/* optional nested SVM features that are enabled for this guest  */
-	bool pause_filter_enabled         : 1;
-	bool pause_threshold_enabled      : 1;
 	bool vgif_enabled                 : 1;
 	bool vnmi_enabled                 : 1;
 

From b89456aee78d22b20c6c83c4d75af7985ae5be8d Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 15 Aug 2023 13:36:51 -0700
Subject: [PATCH 0532/1189] KVM: nSVM: Use KVM-governed feature framework to
 track "vGIF enabled"

Track "virtual GIF exposed to L1" via a governed feature flag instead of
using a dedicated bit/flag in vcpu_svm.

Note, checking KVM's capabilities instead of the "vgif" param means that
the code isn't strictly equivalent, as vgif_enabled could have been set
if nested=false where as that the governed feature cannot.  But that's a
glorified nop as the feature/flag is consumed only by paths that are

Link: https://lore.kernel.org/r/20230815203653.519297-14-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/governed_features.h | 1 +
 arch/x86/kvm/svm/nested.c        | 3 ++-
 arch/x86/kvm/svm/svm.c           | 3 +--
 arch/x86/kvm/svm/svm.h           | 5 +++--
 4 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/governed_features.h b/arch/x86/kvm/governed_features.h
index 9afd34f30599..368696c2e96b 100644
--- a/arch/x86/kvm/governed_features.h
+++ b/arch/x86/kvm/governed_features.h
@@ -14,6 +14,7 @@ KVM_GOVERNED_X86_FEATURE(V_VMSAVE_VMLOAD)
 KVM_GOVERNED_X86_FEATURE(LBRV)
 KVM_GOVERNED_X86_FEATURE(PAUSEFILTER)
 KVM_GOVERNED_X86_FEATURE(PFTHRESHOLD)
+KVM_GOVERNED_X86_FEATURE(VGIF)
 
 #undef KVM_GOVERNED_X86_FEATURE
 #undef KVM_GOVERNED_FEATURE
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index ac03b2bc5b2c..dd496c9e5f91 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -660,7 +660,8 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,
 	 * exit_int_info, exit_int_info_err, next_rip, insn_len, insn_bytes.
 	 */
 
-	if (svm->vgif_enabled && (svm->nested.ctl.int_ctl & V_GIF_ENABLE_MASK))
+	if (guest_can_use(vcpu, X86_FEATURE_VGIF) &&
+	    (svm->nested.ctl.int_ctl & V_GIF_ENABLE_MASK))
 		int_ctl_vmcb12_bits |= (V_GIF_MASK | V_GIF_ENABLE_MASK);
 	else
 		int_ctl_vmcb01_bits |= (V_GIF_MASK | V_GIF_ENABLE_MASK);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 0dc70ad88d29..d8b7e0c71313 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4273,8 +4273,7 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 
 	kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_PAUSEFILTER);
 	kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_PFTHRESHOLD);
-
-	svm->vgif_enabled = vgif && guest_cpuid_has(vcpu, X86_FEATURE_VGIF);
+	kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_VGIF);
 
 	svm->vnmi_enabled = vnmi && guest_cpuid_has(vcpu, X86_FEATURE_VNMI);
 
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index fb438439b61e..6eb5877cc6c3 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -22,6 +22,7 @@
 #include <asm/svm.h>
 #include <asm/sev-common.h>
 
+#include "cpuid.h"
 #include "kvm_cache_regs.h"
 
 #define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT)
@@ -259,7 +260,6 @@ struct vcpu_svm {
 	bool soft_int_injected;
 
 	/* optional nested SVM features that are enabled for this guest  */
-	bool vgif_enabled                 : 1;
 	bool vnmi_enabled                 : 1;
 
 	u32 ldr_reg;
@@ -485,7 +485,8 @@ static inline bool svm_is_intercept(struct vcpu_svm *svm, int bit)
 
 static inline bool nested_vgif_enabled(struct vcpu_svm *svm)
 {
-	return svm->vgif_enabled && (svm->nested.ctl.int_ctl & V_GIF_ENABLE_MASK);
+	return guest_can_use(&svm->vcpu, X86_FEATURE_VGIF) &&
+	       (svm->nested.ctl.int_ctl & V_GIF_ENABLE_MASK);
 }
 
 static inline struct vmcb *get_vgif_vmcb(struct vcpu_svm *svm)

From ee785c870d6f80380be6549772137a41c527d0ba Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 15 Aug 2023 13:36:52 -0700
Subject: [PATCH 0533/1189] KVM: nSVM: Use KVM-governed feature framework to
 track "vNMI enabled"

Track "virtual NMI exposed to L1" via a governed feature flag instead of
using a dedicated bit/flag in vcpu_svm.

Note, checking KVM's capabilities instead of the "vnmi" param means that
the code isn't strictly equivalent, as vnmi_enabled could have been set
if nested=false where as that the governed feature cannot.  But that's a
glorified nop as the feature/flag is consumed only by paths that are
gated by nSVM being enabled.

Link: https://lore.kernel.org/r/20230815203653.519297-15-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/governed_features.h | 1 +
 arch/x86/kvm/svm/svm.c           | 3 +--
 arch/x86/kvm/svm/svm.h           | 5 +----
 3 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/governed_features.h b/arch/x86/kvm/governed_features.h
index 368696c2e96b..423a73395c10 100644
--- a/arch/x86/kvm/governed_features.h
+++ b/arch/x86/kvm/governed_features.h
@@ -15,6 +15,7 @@ KVM_GOVERNED_X86_FEATURE(LBRV)
 KVM_GOVERNED_X86_FEATURE(PAUSEFILTER)
 KVM_GOVERNED_X86_FEATURE(PFTHRESHOLD)
 KVM_GOVERNED_X86_FEATURE(VGIF)
+KVM_GOVERNED_X86_FEATURE(VNMI)
 
 #undef KVM_GOVERNED_X86_FEATURE
 #undef KVM_GOVERNED_FEATURE
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index d8b7e0c71313..226b3a780d0f 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4274,8 +4274,7 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_PAUSEFILTER);
 	kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_PFTHRESHOLD);
 	kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_VGIF);
-
-	svm->vnmi_enabled = vnmi && guest_cpuid_has(vcpu, X86_FEATURE_VNMI);
+	kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_VNMI);
 
 	svm_recalc_instruction_intercepts(vcpu, svm);
 
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 6eb5877cc6c3..06400cfe2244 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -259,9 +259,6 @@ struct vcpu_svm {
 	unsigned long soft_int_next_rip;
 	bool soft_int_injected;
 
-	/* optional nested SVM features that are enabled for this guest  */
-	bool vnmi_enabled                 : 1;
-
 	u32 ldr_reg;
 	u32 dfr_reg;
 	struct page *avic_backing_page;
@@ -537,7 +534,7 @@ static inline bool nested_npt_enabled(struct vcpu_svm *svm)
 
 static inline bool nested_vnmi_enabled(struct vcpu_svm *svm)
 {
-	return svm->vnmi_enabled &&
+	return guest_can_use(&svm->vcpu, X86_FEATURE_VNMI) &&
 	       (svm->nested.ctl.int_ctl & V_NMI_ENABLE_MASK);
 }
 

From 9717efbe5ba3f52d4b3cc637c7f7f6149ea264bb Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 15 Aug 2023 13:36:53 -0700
Subject: [PATCH 0534/1189] KVM: x86: Disallow guest CPUID lookups when IRQs
 are disabled

Now that KVM has a framework for caching guest CPUID feature flags, add
a "rule" that IRQs must be enabled when doing guest CPUID lookups, and
enforce the rule via a lockdep assertion.  CPUID lookups are slow, and
within KVM, IRQs are only ever disabled in hot paths, e.g. the core run
loop, fast page fault handling, etc.  I.e. querying guest CPUID with IRQs
disabled, especially in the run loop, should be avoided.

Link: https://lore.kernel.org/r/20230815203653.519297-16-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/cpuid.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 67e9f79fe059..e961e9a05847 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -11,6 +11,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/kvm_host.h>
+#include "linux/lockdep.h"
 #include <linux/export.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
@@ -84,6 +85,18 @@ static inline struct kvm_cpuid_entry2 *cpuid_entry2_find(
 	struct kvm_cpuid_entry2 *e;
 	int i;
 
+	/*
+	 * KVM has a semi-arbitrary rule that querying the guest's CPUID model
+	 * with IRQs disabled is disallowed.  The CPUID model can legitimately
+	 * have over one hundred entries, i.e. the lookup is slow, and IRQs are
+	 * typically disabled in KVM only when KVM is in a performance critical
+	 * path, e.g. the core VM-Enter/VM-Exit run loop.  Nothing will break
+	 * if this rule is violated, this assertion is purely to flag potential
+	 * performance issues.  If this fires, consider moving the lookup out
+	 * of the hotpath, e.g. by caching information during CPUID updates.
+	 */
+	lockdep_assert_irqs_enabled();
+
 	for (i = 0; i < nent; i++) {
 		e = &entries[i];
 

From 1f8403953f05af591ab72cf749b9b9b837ea9595 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Mon, 14 Aug 2023 22:03:39 +0800
Subject: [PATCH 0535/1189] KVM: Remove unused kvm_device_{get,put}()
 declarations

Commit 07f0a7bdec5c ("kvm: destroy emulated devices on VM exit") removed the
functions but not these declarations.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Link: https://lore.kernel.org/r/20230814140339.47732-1-yuehaibing@huawei.com
[sean: split to separate patch]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 include/linux/kvm_host.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 9125d0ab642d..a973a7cb45e0 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2152,8 +2152,6 @@ struct kvm_device_ops {
 	int (*mmap)(struct kvm_device *dev, struct vm_area_struct *vma);
 };
 
-void kvm_device_get(struct kvm_device *dev);
-void kvm_device_put(struct kvm_device *dev);
 struct kvm_device *kvm_device_from_filp(struct file *filp);
 int kvm_register_device_ops(const struct kvm_device_ops *ops, u32 type);
 void kvm_unregister_device_ops(u32 type);

From 458933d33af2cb3663bd8c0080c1efd1f9483db4 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Mon, 14 Aug 2023 22:03:39 +0800
Subject: [PATCH 0536/1189] KVM: Remove unused kvm_make_cpus_request_mask()
 declaration

Commit 7ee30bc132c6 ("KVM: x86: deliver KVM IOAPIC scan request to target
vCPUs") declared but never implemented kvm_make_cpus_request_mask() as
kvm_make_vcpus_request_mask() already existed.

Note, KVM's APIs are painfully inconsistent, as the inclusive variant uses
"vcpus", whereas the exclusive/all variants use "cpus", which is likely
what led to the spurious declaration.  The "vcpus" terminology is more
correct, especially since the helpers will kick _physical_ CPUs by calling
kvm_kick_many_cpus().  But that's a cleanup for the future.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Link: https://lore.kernel.org/r/20230814140339.47732-1-yuehaibing@huawei.com
[sean: split to separate patch, call out inconsistent naming]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 include/linux/kvm_host.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index a973a7cb45e0..199698a5ffa6 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -190,8 +190,6 @@ bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
 bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req);
 bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req,
 				      struct kvm_vcpu *except);
-bool kvm_make_cpus_request_mask(struct kvm *kvm, unsigned int req,
-				unsigned long *vcpu_bitmap);
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID		0
 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID	1

From cf6d80c0eb95900e19e1ad54c686a1877dda4276 Mon Sep 17 00:00:00 2001
From: Jinrong Liang <cloudliang@tencent.com>
Date: Thu, 10 Aug 2023 17:09:40 +0800
Subject: [PATCH 0537/1189] KVM: selftests: Add x86 properties for Intel PMU in
 processor.h

Add x86 properties for Intel PMU so that tests don't have to manually
retrieve the correct CPUID leaf+register, and so that the resulting code
is self-documenting.

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Jinrong Liang <cloudliang@tencent.com>
Link: https://lore.kernel.org/r/20230810090945.16053-2-cloudliang@tencent.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/include/x86_64/processor.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index aa434c8f19c5..4fd042112526 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -239,7 +239,12 @@ struct kvm_x86_cpu_property {
 #define X86_PROPERTY_MAX_BASIC_LEAF		KVM_X86_CPU_PROPERTY(0, 0, EAX, 0, 31)
 #define X86_PROPERTY_PMU_VERSION		KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 0, 7)
 #define X86_PROPERTY_PMU_NR_GP_COUNTERS		KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 8, 15)
+#define X86_PROPERTY_PMU_GP_COUNTERS_BIT_WIDTH	KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 16, 23)
 #define X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH	KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 24, 31)
+#define X86_PROPERTY_PMU_EVENTS_MASK		KVM_X86_CPU_PROPERTY(0xa, 0, EBX, 0, 7)
+#define X86_PROPERTY_PMU_FIXED_COUNTERS_BITMASK	KVM_X86_CPU_PROPERTY(0xa, 0, ECX, 0, 31)
+#define X86_PROPERTY_PMU_NR_FIXED_COUNTERS	KVM_X86_CPU_PROPERTY(0xa, 0, EDX, 0, 4)
+#define X86_PROPERTY_PMU_FIXED_COUNTERS_BIT_WIDTH	KVM_X86_CPU_PROPERTY(0xa, 0, EDX, 5, 12)
 
 #define X86_PROPERTY_SUPPORTED_XCR0_LO		KVM_X86_CPU_PROPERTY(0xd,  0, EAX,  0, 31)
 #define X86_PROPERTY_XSTATE_MAX_SIZE_XCR0	KVM_X86_CPU_PROPERTY(0xd,  0, EBX,  0, 31)

From c853be2265ccd497ff17b878962a2dbcb4873abf Mon Sep 17 00:00:00 2001
From: Jinrong Liang <cloudliang@tencent.com>
Date: Thu, 10 Aug 2023 17:09:41 +0800
Subject: [PATCH 0538/1189] KVM: selftests: Drop the return of remove_event()

None of the callers consume remove_event(), and it incorrectly implies
that the incoming filter isn't modified. Drop the return.

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Jinrong Liang <cloudliang@tencent.com>
Link: https://lore.kernel.org/r/20230810090945.16053-3-cloudliang@tencent.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
index 40507ed9fe8a..5ac05e64bec9 100644
--- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
+++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
@@ -265,8 +265,7 @@ static struct kvm_pmu_event_filter *event_filter(uint32_t action)
  * Remove the first occurrence of 'event' (if any) from the filter's
  * event list.
  */
-static struct kvm_pmu_event_filter *remove_event(struct kvm_pmu_event_filter *f,
-						 uint64_t event)
+static void remove_event(struct kvm_pmu_event_filter *f, uint64_t event)
 {
 	bool found = false;
 	int i;
@@ -279,7 +278,6 @@ static struct kvm_pmu_event_filter *remove_event(struct kvm_pmu_event_filter *f,
 	}
 	if (found)
 		f->nevents--;
-	return f;
 }
 
 #define ASSERT_PMC_COUNTING_INSTRUCTIONS()						\

From de527b1daf69a41a265f48ad7bb9207ca7b7d29b Mon Sep 17 00:00:00 2001
From: Jinrong Liang <cloudliang@tencent.com>
Date: Thu, 10 Aug 2023 17:09:42 +0800
Subject: [PATCH 0539/1189] KVM: selftests: Introduce "struct
 __kvm_pmu_event_filter" to manipulate filter

Add custom "__kvm_pmu_event_filter" structure to improve pmu event
filter settings. Simplifies event filter setup by organizing event
filter parameters in a cleaner, more organized way.

Alternatively, selftests could use a struct overlay ala vcpu_set_msr()
to avoid dynamically allocating the array:

        struct {
                struct kvm_msrs header;
                struct kvm_msr_entry entry;
        } buffer = {};

        memset(&buffer, 0, sizeof(buffer));
        buffer.header.nmsrs = 1;
        buffer.entry.index = msr_index;
        buffer.entry.data = msr_value;

but the extra layer added by the nested structs is counterproductive
to writing efficient, clean code.

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Jinrong Liang <cloudliang@tencent.com>
Link: https://lore.kernel.org/r/20230810090945.16053-4-cloudliang@tencent.com
[sean: massage changelog to explain alternative]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../kvm/x86_64/pmu_event_filter_test.c        | 182 +++++++++---------
 1 file changed, 90 insertions(+), 92 deletions(-)

diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
index 5ac05e64bec9..fcb6cf9ae4a9 100644
--- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
+++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
@@ -28,6 +28,10 @@
 
 #define NUM_BRANCHES 42
 
+/* Matches KVM_PMU_EVENT_FILTER_MAX_EVENTS in pmu.c */
+#define MAX_FILTER_EVENTS		300
+#define MAX_TEST_EVENTS		10
+
 /*
  * This is how the event selector and unit mask are stored in an AMD
  * core performance event-select register. Intel's format is similar,
@@ -69,21 +73,33 @@
 
 #define INST_RETIRED EVENT(0xc0, 0)
 
+struct __kvm_pmu_event_filter {
+	__u32 action;
+	__u32 nevents;
+	__u32 fixed_counter_bitmap;
+	__u32 flags;
+	__u32 pad[4];
+	__u64 events[MAX_FILTER_EVENTS];
+};
+
 /*
  * This event list comprises Intel's eight architectural events plus
  * AMD's "retired branch instructions" for Zen[123] (and possibly
  * other AMD CPUs).
  */
-static const uint64_t event_list[] = {
-	EVENT(0x3c, 0),
-	INST_RETIRED,
-	EVENT(0x3c, 1),
-	EVENT(0x2e, 0x4f),
-	EVENT(0x2e, 0x41),
-	EVENT(0xc4, 0),
-	EVENT(0xc5, 0),
-	EVENT(0xa4, 1),
-	AMD_ZEN_BR_RETIRED,
+static const struct __kvm_pmu_event_filter base_event_filter = {
+	.nevents = ARRAY_SIZE(base_event_filter.events),
+	.events = {
+		EVENT(0x3c, 0),
+		INST_RETIRED,
+		EVENT(0x3c, 1),
+		EVENT(0x2e, 0x4f),
+		EVENT(0x2e, 0x41),
+		EVENT(0xc4, 0),
+		EVENT(0xc5, 0),
+		EVENT(0xa4, 1),
+		AMD_ZEN_BR_RETIRED,
+	},
 };
 
 struct {
@@ -225,47 +241,11 @@ static bool sanity_check_pmu(struct kvm_vcpu *vcpu)
 	return !r;
 }
 
-static struct kvm_pmu_event_filter *alloc_pmu_event_filter(uint32_t nevents)
-{
-	struct kvm_pmu_event_filter *f;
-	int size = sizeof(*f) + nevents * sizeof(f->events[0]);
-
-	f = malloc(size);
-	TEST_ASSERT(f, "Out of memory");
-	memset(f, 0, size);
-	f->nevents = nevents;
-	return f;
-}
-
-
-static struct kvm_pmu_event_filter *
-create_pmu_event_filter(const uint64_t event_list[], int nevents,
-			uint32_t action, uint32_t flags)
-{
-	struct kvm_pmu_event_filter *f;
-	int i;
-
-	f = alloc_pmu_event_filter(nevents);
-	f->action = action;
-	f->flags = flags;
-	for (i = 0; i < nevents; i++)
-		f->events[i] = event_list[i];
-
-	return f;
-}
-
-static struct kvm_pmu_event_filter *event_filter(uint32_t action)
-{
-	return create_pmu_event_filter(event_list,
-				       ARRAY_SIZE(event_list),
-				       action, 0);
-}
-
 /*
  * Remove the first occurrence of 'event' (if any) from the filter's
  * event list.
  */
-static void remove_event(struct kvm_pmu_event_filter *f, uint64_t event)
+static void remove_event(struct __kvm_pmu_event_filter *f, uint64_t event)
 {
 	bool found = false;
 	int i;
@@ -313,66 +293,73 @@ static void test_without_filter(struct kvm_vcpu *vcpu)
 }
 
 static void test_with_filter(struct kvm_vcpu *vcpu,
-			     struct kvm_pmu_event_filter *f)
+			     struct __kvm_pmu_event_filter *__f)
 {
+	struct kvm_pmu_event_filter *f = (void *)__f;
+
 	vm_ioctl(vcpu->vm, KVM_SET_PMU_EVENT_FILTER, f);
 	run_vcpu_and_sync_pmc_results(vcpu);
 }
 
 static void test_amd_deny_list(struct kvm_vcpu *vcpu)
 {
-	uint64_t event = EVENT(0x1C2, 0);
-	struct kvm_pmu_event_filter *f;
+	struct __kvm_pmu_event_filter f = {
+		.action = KVM_PMU_EVENT_DENY,
+		.nevents = 1,
+		.events = {
+			EVENT(0x1C2, 0),
+		},
+	};
 
-	f = create_pmu_event_filter(&event, 1, KVM_PMU_EVENT_DENY, 0);
-	test_with_filter(vcpu, f);
-	free(f);
+	test_with_filter(vcpu, &f);
 
 	ASSERT_PMC_COUNTING_INSTRUCTIONS();
 }
 
 static void test_member_deny_list(struct kvm_vcpu *vcpu)
 {
-	struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_DENY);
+	struct __kvm_pmu_event_filter f = base_event_filter;
 
-	test_with_filter(vcpu, f);
-	free(f);
+	f.action = KVM_PMU_EVENT_DENY;
+	test_with_filter(vcpu, &f);
 
 	ASSERT_PMC_NOT_COUNTING_INSTRUCTIONS();
 }
 
 static void test_member_allow_list(struct kvm_vcpu *vcpu)
 {
-	struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_ALLOW);
+	struct __kvm_pmu_event_filter f = base_event_filter;
 
-	test_with_filter(vcpu, f);
-	free(f);
+	f.action = KVM_PMU_EVENT_ALLOW;
+	test_with_filter(vcpu, &f);
 
 	ASSERT_PMC_COUNTING_INSTRUCTIONS();
 }
 
 static void test_not_member_deny_list(struct kvm_vcpu *vcpu)
 {
-	struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_DENY);
+	struct __kvm_pmu_event_filter f = base_event_filter;
 
-	remove_event(f, INST_RETIRED);
-	remove_event(f, INTEL_BR_RETIRED);
-	remove_event(f, AMD_ZEN_BR_RETIRED);
-	test_with_filter(vcpu, f);
-	free(f);
+	f.action = KVM_PMU_EVENT_DENY;
+
+	remove_event(&f, INST_RETIRED);
+	remove_event(&f, INTEL_BR_RETIRED);
+	remove_event(&f, AMD_ZEN_BR_RETIRED);
+	test_with_filter(vcpu, &f);
 
 	ASSERT_PMC_COUNTING_INSTRUCTIONS();
 }
 
 static void test_not_member_allow_list(struct kvm_vcpu *vcpu)
 {
-	struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_ALLOW);
+	struct __kvm_pmu_event_filter f = base_event_filter;
 
-	remove_event(f, INST_RETIRED);
-	remove_event(f, INTEL_BR_RETIRED);
-	remove_event(f, AMD_ZEN_BR_RETIRED);
-	test_with_filter(vcpu, f);
-	free(f);
+	f.action = KVM_PMU_EVENT_ALLOW;
+
+	remove_event(&f, INST_RETIRED);
+	remove_event(&f, INTEL_BR_RETIRED);
+	remove_event(&f, AMD_ZEN_BR_RETIRED);
+	test_with_filter(vcpu, &f);
 
 	ASSERT_PMC_NOT_COUNTING_INSTRUCTIONS();
 }
@@ -567,19 +554,16 @@ static void run_masked_events_test(struct kvm_vcpu *vcpu,
 				   const uint64_t masked_events[],
 				   const int nmasked_events)
 {
-	struct kvm_pmu_event_filter *f;
+	struct __kvm_pmu_event_filter f = {
+		.nevents = nmasked_events,
+		.action = KVM_PMU_EVENT_ALLOW,
+		.flags = KVM_PMU_EVENT_FLAG_MASKED_EVENTS,
+	};
 
-	f = create_pmu_event_filter(masked_events, nmasked_events,
-				    KVM_PMU_EVENT_ALLOW,
-				    KVM_PMU_EVENT_FLAG_MASKED_EVENTS);
-	test_with_filter(vcpu, f);
-	free(f);
+	memcpy(f.events, masked_events, sizeof(uint64_t) * nmasked_events);
+	test_with_filter(vcpu, &f);
 }
 
-/* Matches KVM_PMU_EVENT_FILTER_MAX_EVENTS in pmu.c */
-#define MAX_FILTER_EVENTS	300
-#define MAX_TEST_EVENTS		10
-
 #define ALLOW_LOADS		BIT(0)
 #define ALLOW_STORES		BIT(1)
 #define ALLOW_LOADS_STORES	BIT(2)
@@ -751,17 +735,27 @@ static void test_masked_events(struct kvm_vcpu *vcpu)
 	run_masked_events_tests(vcpu, events, nevents);
 }
 
-static int run_filter_test(struct kvm_vcpu *vcpu, const uint64_t *events,
-			   int nevents, uint32_t flags)
+static int set_pmu_event_filter(struct kvm_vcpu *vcpu,
+				struct __kvm_pmu_event_filter *__f)
 {
-	struct kvm_pmu_event_filter *f;
-	int r;
+	struct kvm_pmu_event_filter *f = (void *)__f;
 
-	f = create_pmu_event_filter(events, nevents, KVM_PMU_EVENT_ALLOW, flags);
-	r = __vm_ioctl(vcpu->vm, KVM_SET_PMU_EVENT_FILTER, f);
-	free(f);
+	return __vm_ioctl(vcpu->vm, KVM_SET_PMU_EVENT_FILTER, f);
+}
 
-	return r;
+static int set_pmu_single_event_filter(struct kvm_vcpu *vcpu, uint64_t event,
+				       uint32_t flags, uint32_t action)
+{
+	struct __kvm_pmu_event_filter f = {
+		.nevents = 1,
+		.flags = flags,
+		.action = action,
+		.events = {
+			event,
+		},
+	};
+
+	return set_pmu_event_filter(vcpu, &f);
 }
 
 static void test_filter_ioctl(struct kvm_vcpu *vcpu)
@@ -773,14 +767,18 @@ static void test_filter_ioctl(struct kvm_vcpu *vcpu)
 	 * Unfortunately having invalid bits set in event data is expected to
 	 * pass when flags == 0 (bits other than eventsel+umask).
 	 */
-	r = run_filter_test(vcpu, &e, 1, 0);
+	r = set_pmu_single_event_filter(vcpu, e, 0, KVM_PMU_EVENT_ALLOW);
 	TEST_ASSERT(r == 0, "Valid PMU Event Filter is failing");
 
-	r = run_filter_test(vcpu, &e, 1, KVM_PMU_EVENT_FLAG_MASKED_EVENTS);
+	r = set_pmu_single_event_filter(vcpu, e,
+					KVM_PMU_EVENT_FLAG_MASKED_EVENTS,
+					KVM_PMU_EVENT_ALLOW);
 	TEST_ASSERT(r != 0, "Invalid PMU Event Filter is expected to fail");
 
 	e = KVM_PMU_ENCODE_MASKED_ENTRY(0xff, 0xff, 0xff, 0xf);
-	r = run_filter_test(vcpu, &e, 1, KVM_PMU_EVENT_FLAG_MASKED_EVENTS);
+	r = set_pmu_single_event_filter(vcpu, e,
+					KVM_PMU_EVENT_FLAG_MASKED_EVENTS,
+					KVM_PMU_EVENT_ALLOW);
 	TEST_ASSERT(r == 0, "Valid PMU Event Filter is failing");
 }
 

From 86ab6af8b96a6a6c8f86f1b0ea1dd386f43930db Mon Sep 17 00:00:00 2001
From: Jinrong Liang <cloudliang@tencent.com>
Date: Thu, 10 Aug 2023 17:09:43 +0800
Subject: [PATCH 0540/1189] KVM: selftests: Add test cases for unsupported PMU
 event filter input values

Add test cases to verify the handling of unsupported input values for the
PMU event filter. The tests cover unsupported "action" values, unsupported
"flags" values, and unsupported "nevents" values. All these cases should
return an error, as they are currently not supported by the filter.
Furthermore, the tests also cover the case where setting non-existent
fixed counters in the fixed bitmap does not fail.

Signed-off-by: Jinrong Liang <cloudliang@tencent.com>
Reviewed-by: Isaku Yamahata <isaku.yamahata@intel.com>
Link: https://lore.kernel.org/r/20230810090945.16053-5-cloudliang@tencent.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../kvm/x86_64/pmu_event_filter_test.c        | 26 +++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
index fcb6cf9ae4a9..ca4ff5ad613a 100644
--- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
+++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
@@ -32,6 +32,10 @@
 #define MAX_FILTER_EVENTS		300
 #define MAX_TEST_EVENTS		10
 
+#define PMU_EVENT_FILTER_INVALID_ACTION		(KVM_PMU_EVENT_DENY + 1)
+#define PMU_EVENT_FILTER_INVALID_FLAGS			(KVM_PMU_EVENT_FLAGS_VALID_MASK << 1)
+#define PMU_EVENT_FILTER_INVALID_NEVENTS		(MAX_FILTER_EVENTS + 1)
+
 /*
  * This is how the event selector and unit mask are stored in an AMD
  * core performance event-select register. Intel's format is similar,
@@ -760,6 +764,8 @@ static int set_pmu_single_event_filter(struct kvm_vcpu *vcpu, uint64_t event,
 
 static void test_filter_ioctl(struct kvm_vcpu *vcpu)
 {
+	uint8_t nr_fixed_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS);
+	struct __kvm_pmu_event_filter f;
 	uint64_t e = ~0ul;
 	int r;
 
@@ -780,6 +786,26 @@ static void test_filter_ioctl(struct kvm_vcpu *vcpu)
 					KVM_PMU_EVENT_FLAG_MASKED_EVENTS,
 					KVM_PMU_EVENT_ALLOW);
 	TEST_ASSERT(r == 0, "Valid PMU Event Filter is failing");
+
+	f = base_event_filter;
+	f.action = PMU_EVENT_FILTER_INVALID_ACTION;
+	r = set_pmu_event_filter(vcpu, &f);
+	TEST_ASSERT(r, "Set invalid action is expected to fail");
+
+	f = base_event_filter;
+	f.flags = PMU_EVENT_FILTER_INVALID_FLAGS;
+	r = set_pmu_event_filter(vcpu, &f);
+	TEST_ASSERT(r, "Set invalid flags is expected to fail");
+
+	f = base_event_filter;
+	f.nevents = PMU_EVENT_FILTER_INVALID_NEVENTS;
+	r = set_pmu_event_filter(vcpu, &f);
+	TEST_ASSERT(r, "Exceeding the max number of filter events should fail");
+
+	f = base_event_filter;
+	f.fixed_counter_bitmap = ~GENMASK_ULL(nr_fixed_counters, 0);
+	r = set_pmu_event_filter(vcpu, &f);
+	TEST_ASSERT(!r, "Masking non-existent fixed counters should be allowed");
 }
 
 int main(int argc, char *argv[])

From d4e36166820a089f6300dc59dbb641e8c150bec1 Mon Sep 17 00:00:00 2001
From: Jinrong Liang <cloudliang@tencent.com>
Date: Thu, 10 Aug 2023 17:09:44 +0800
Subject: [PATCH 0541/1189] KVM: selftests: Test if event filter meets
 expectations on fixed counters

Add tests to cover that pmu event_filter works as expected when it's
applied to fixed performance counters, even if there is none fixed
counter exists (e.g. Intel guest pmu version=1 or AMD guest).

Signed-off-by: Jinrong Liang <cloudliang@tencent.com>
Reviewed-by: Isaku Yamahata <isaku.yamahata@intel.com>
Link: https://lore.kernel.org/r/20230810090945.16053-6-cloudliang@tencent.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../kvm/x86_64/pmu_event_filter_test.c        | 80 +++++++++++++++++++
 1 file changed, 80 insertions(+)

diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
index ca4ff5ad613a..c9355ca4cd50 100644
--- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
+++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
@@ -27,6 +27,7 @@
 #define ARCH_PERFMON_BRANCHES_RETIRED		5
 
 #define NUM_BRANCHES 42
+#define INTEL_PMC_IDX_FIXED		32
 
 /* Matches KVM_PMU_EVENT_FILTER_MAX_EVENTS in pmu.c */
 #define MAX_FILTER_EVENTS		300
@@ -808,6 +809,84 @@ static void test_filter_ioctl(struct kvm_vcpu *vcpu)
 	TEST_ASSERT(!r, "Masking non-existent fixed counters should be allowed");
 }
 
+static void intel_run_fixed_counter_guest_code(uint8_t fixed_ctr_idx)
+{
+	for (;;) {
+		wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0);
+		wrmsr(MSR_CORE_PERF_FIXED_CTR0 + fixed_ctr_idx, 0);
+
+		/* Only OS_EN bit is enabled for fixed counter[idx]. */
+		wrmsr(MSR_CORE_PERF_FIXED_CTR_CTRL, BIT_ULL(4 * fixed_ctr_idx));
+		wrmsr(MSR_CORE_PERF_GLOBAL_CTRL,
+		      BIT_ULL(INTEL_PMC_IDX_FIXED + fixed_ctr_idx));
+		__asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES}));
+		wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0);
+
+		GUEST_SYNC(rdmsr(MSR_CORE_PERF_FIXED_CTR0 + fixed_ctr_idx));
+	}
+}
+
+static uint64_t test_with_fixed_counter_filter(struct kvm_vcpu *vcpu,
+					       uint32_t action, uint32_t bitmap)
+{
+	struct __kvm_pmu_event_filter f = {
+		.action = action,
+		.fixed_counter_bitmap = bitmap,
+	};
+	set_pmu_event_filter(vcpu, &f);
+
+	return run_vcpu_to_sync(vcpu);
+}
+
+static void __test_fixed_counter_bitmap(struct kvm_vcpu *vcpu, uint8_t idx,
+					uint8_t nr_fixed_counters)
+{
+	unsigned int i;
+	uint32_t bitmap;
+	uint64_t count;
+
+	TEST_ASSERT(nr_fixed_counters < sizeof(bitmap) * 8,
+		    "Invalid nr_fixed_counters");
+
+	/*
+	 * Check the fixed performance counter can count normally when KVM
+	 * userspace doesn't set any pmu filter.
+	 */
+	count = run_vcpu_to_sync(vcpu);
+	TEST_ASSERT(count, "Unexpected count value: %ld\n", count);
+
+	for (i = 0; i < BIT(nr_fixed_counters); i++) {
+		bitmap = BIT(i);
+		count = test_with_fixed_counter_filter(vcpu, KVM_PMU_EVENT_ALLOW,
+						       bitmap);
+		TEST_ASSERT_EQ(!!count, !!(bitmap & BIT(idx)));
+
+		count = test_with_fixed_counter_filter(vcpu, KVM_PMU_EVENT_DENY,
+						       bitmap);
+		TEST_ASSERT_EQ(!!count, !(bitmap & BIT(idx)));
+	}
+}
+
+static void test_fixed_counter_bitmap(void)
+{
+	uint8_t nr_fixed_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS);
+	struct kvm_vm *vm;
+	struct kvm_vcpu *vcpu;
+	uint8_t idx;
+
+	/*
+	 * Check that pmu_event_filter works as expected when it's applied to
+	 * fixed performance counters.
+	 */
+	for (idx = 0; idx < nr_fixed_counters; idx++) {
+		vm = vm_create_with_one_vcpu(&vcpu,
+					     intel_run_fixed_counter_guest_code);
+		vcpu_args_set(vcpu, 1, idx);
+		__test_fixed_counter_bitmap(vcpu, idx, nr_fixed_counters);
+		kvm_vm_free(vm);
+	}
+}
+
 int main(int argc, char *argv[])
 {
 	void (*guest_code)(void);
@@ -851,6 +930,7 @@ int main(int argc, char *argv[])
 	kvm_vm_free(vm);
 
 	test_pmu_config_disable(guest_code);
+	test_fixed_counter_bitmap();
 
 	return 0;
 }

From 740d087e7fff2a68fb1c7f01efb239e45f217485 Mon Sep 17 00:00:00 2001
From: Jinrong Liang <cloudliang@tencent.com>
Date: Thu, 10 Aug 2023 17:09:45 +0800
Subject: [PATCH 0542/1189] KVM: selftests: Test gp event filters don't affect
 fixed event filters

Add a test to ensure that setting both generic and fixed performance
event filters does not affect the consistency of the fixed event filter
behavior in KVM.

Signed-off-by: Jinrong Liang <cloudliang@tencent.com>
Link: https://lore.kernel.org/r/20230810090945.16053-7-cloudliang@tencent.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../kvm/x86_64/pmu_event_filter_test.c        | 27 +++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
index c9355ca4cd50..283cc55597a4 100644
--- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
+++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
@@ -838,6 +838,19 @@ static uint64_t test_with_fixed_counter_filter(struct kvm_vcpu *vcpu,
 	return run_vcpu_to_sync(vcpu);
 }
 
+static uint64_t test_set_gp_and_fixed_event_filter(struct kvm_vcpu *vcpu,
+						   uint32_t action,
+						   uint32_t bitmap)
+{
+	struct __kvm_pmu_event_filter f = base_event_filter;
+
+	f.action = action;
+	f.fixed_counter_bitmap = bitmap;
+	set_pmu_event_filter(vcpu, &f);
+
+	return run_vcpu_to_sync(vcpu);
+}
+
 static void __test_fixed_counter_bitmap(struct kvm_vcpu *vcpu, uint8_t idx,
 					uint8_t nr_fixed_counters)
 {
@@ -864,6 +877,20 @@ static void __test_fixed_counter_bitmap(struct kvm_vcpu *vcpu, uint8_t idx,
 		count = test_with_fixed_counter_filter(vcpu, KVM_PMU_EVENT_DENY,
 						       bitmap);
 		TEST_ASSERT_EQ(!!count, !(bitmap & BIT(idx)));
+
+		/*
+		 * Check that fixed_counter_bitmap has higher priority than
+		 * events[] when both are set.
+		 */
+		count = test_set_gp_and_fixed_event_filter(vcpu,
+							   KVM_PMU_EVENT_ALLOW,
+							   bitmap);
+		TEST_ASSERT_EQ(!!count, !!(bitmap & BIT(idx)));
+
+		count = test_set_gp_and_fixed_event_filter(vcpu,
+							   KVM_PMU_EVENT_DENY,
+							   bitmap);
+		TEST_ASSERT_EQ(!!count, !(bitmap & BIT(idx)));
 	}
 }
 

From 246c713a3655c840337c4b24d3838558673c0d6b Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 17 Aug 2023 14:03:01 -0700
Subject: [PATCH 0543/1189] landlock: Annotate struct landlock_rule with
 __counted_by
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prepare for the coming implementation by GCC and Clang of the __counted_by
attribute. Flexible array members annotated with __counted_by can have
their accesses bounds-checked at run-time checking via CONFIG_UBSAN_BOUNDS
(for array indexing) and CONFIG_FORTIFY_SOURCE (for strcpy/memcpy-family
functions).

As found with Coccinelle[1], add __counted_by for struct landlock_rule.

[1] https://github.com/kees/kernel-tools/blob/trunk/coccinelle/examples/counted_by.cocci

Cc: Paul Moore <paul@paul-moore.com>
Cc: James Morris <jmorris@namei.org>
Cc: "Serge E. Hallyn" <serge@hallyn.com>
Cc: linux-security-module@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Justin Stitt <justinstitt@google.com>
Reviewed-by: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Link: https://lore.kernel.org/r/20230817210257.never.920-kees@kernel.org
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 security/landlock/ruleset.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/security/landlock/ruleset.h b/security/landlock/ruleset.h
index d43231b783e4..55b1df8f66a8 100644
--- a/security/landlock/ruleset.h
+++ b/security/landlock/ruleset.h
@@ -67,7 +67,7 @@ struct landlock_rule {
 	 * @layers: Stack of layers, from the latest to the newest, implemented
 	 * as a flexible array member (FAM).
 	 */
-	struct landlock_layer layers[];
+	struct landlock_layer layers[] __counted_by(num_layers);
 };
 
 /**

From f7d067041e35a8c25a8429ddac97dcca7cf28da2 Mon Sep 17 00:00:00 2001
From: Wang Ming <machel@vivo.com>
Date: Thu, 13 Jul 2023 16:56:06 +0800
Subject: [PATCH 0544/1189] ntb: Remove error checking for debugfs_create_dir()

It is expected that most callers should _ignore_ the errors
return by debugfs_create_dir() in tool_setup_dbgfs()

Signed-off-by: Wang Ming <machel@vivo.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
---
 drivers/ntb/test/ntb_tool.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/ntb/test/ntb_tool.c b/drivers/ntb/test/ntb_tool.c
index eeeb4b1c97d2..e0acc11d29ba 100644
--- a/drivers/ntb/test/ntb_tool.c
+++ b/drivers/ntb/test/ntb_tool.c
@@ -1495,8 +1495,6 @@ static void tool_setup_dbgfs(struct tool_ctx *tc)
 
 	tc->dbgfs_dir = debugfs_create_dir(dev_name(&tc->ntb->dev),
 					   tool_dbgfs_topdir);
-	if (!tc->dbgfs_dir)
-		return;
 
 	debugfs_create_file("port", 0600, tc->dbgfs_dir,
 			    tc, &tool_port_fops);

From 45191087c3e2866e4fbcd775e443ee0380211ed1 Mon Sep 17 00:00:00 2001
From: Minjie Du <duminjie@vivo.com>
Date: Thu, 13 Jul 2023 11:47:27 +0800
Subject: [PATCH 0545/1189] dtivers: ntb: fix parameter check in
 perf_setup_dbgfs()

Make IS_ERR() judge the debugfs_create_dir() function return
in perf_setup_dbgfs().

Signed-off-by: Minjie Du <duminjie@vivo.com>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
---
 drivers/ntb/test/ntb_perf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c
index 65e1e5cf1b29..553f1f46bc66 100644
--- a/drivers/ntb/test/ntb_perf.c
+++ b/drivers/ntb/test/ntb_perf.c
@@ -1355,7 +1355,7 @@ static void perf_setup_dbgfs(struct perf_ctx *perf)
 	struct pci_dev *pdev = perf->ntb->pdev;
 
 	perf->dbgfs_dir = debugfs_create_dir(pci_name(pdev), perf_dbgfs_topdir);
-	if (!perf->dbgfs_dir) {
+	if (IS_ERR(perf->dbgfs_dir)) {
 		dev_warn(&perf->ntb->dev, "DebugFS unsupported\n");
 		return;
 	}

From 03c9e6f0e0ab3fb6129b8a9f064b7d7957aa969a Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Thu, 10 Aug 2023 19:14:02 +0800
Subject: [PATCH 0546/1189] NTB: ntb_tool: Switch to memdup_user_nul() helper

Use memdup_user_nul() helper instead of open-coding to simplify the code.

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
---
 drivers/ntb/test/ntb_tool.c | 13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)

diff --git a/drivers/ntb/test/ntb_tool.c b/drivers/ntb/test/ntb_tool.c
index e0acc11d29ba..641cb7e05a47 100644
--- a/drivers/ntb/test/ntb_tool.c
+++ b/drivers/ntb/test/ntb_tool.c
@@ -370,16 +370,9 @@ static ssize_t tool_fn_write(struct tool_ctx *tc,
 	if (*offp)
 		return 0;
 
-	buf = kmalloc(size + 1, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	if (copy_from_user(buf, ubuf, size)) {
-		kfree(buf);
-		return -EFAULT;
-	}
-
-	buf[size] = 0;
+	buf = memdup_user_nul(ubuf, size);
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
 
 	n = sscanf(buf, "%c %lli", &cmd, &bits);
 

From 28e70ed9d0fab935f78b565d9c026585559b86a4 Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Thu, 17 Aug 2023 14:32:19 +0800
Subject: [PATCH 0547/1189] ntb: amd: Drop unnecessary error check for
 debugfs_create_dir

This patch removes the error checking for debugfs_create_dir in
ntb_hw_amd.c. This is because the DebugFS kernel API is developed
in a way that the caller can safely ignore the errors that
occur during the creation of DebugFS nodes. The debugfs APIs have
a IS_ERR() judge in start_creating() which can handle it
gracefully. so these checks are unnecessary.

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Acked-by: Sanjay R Mehta <sanju.mehta@amd.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
---
 drivers/ntb/hw/amd/ntb_hw_amd.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.c b/drivers/ntb/hw/amd/ntb_hw_amd.c
index 4940b6301d83..d687e8c2cc78 100644
--- a/drivers/ntb/hw/amd/ntb_hw_amd.c
+++ b/drivers/ntb/hw/amd/ntb_hw_amd.c
@@ -941,13 +941,10 @@ static void ndev_init_debugfs(struct amd_ntb_dev *ndev)
 		ndev->debugfs_dir =
 			debugfs_create_dir(pci_name(ndev->ntb.pdev),
 					   debugfs_dir);
-		if (IS_ERR(ndev->debugfs_dir))
-			ndev->debugfs_info = NULL;
-		else
-			ndev->debugfs_info =
-				debugfs_create_file("info", S_IRUSR,
-						    ndev->debugfs_dir, ndev,
-						    &amd_ntb_debugfs_info);
+		ndev->debugfs_info =
+			debugfs_create_file("info", S_IRUSR,
+					    ndev->debugfs_dir, ndev,
+					    &amd_ntb_debugfs_info);
 	}
 }
 

From dfd122fe8591d513b5e51313601217b67ae98d13 Mon Sep 17 00:00:00 2001
From: Artur Weber <aweber.kernel@gmail.com>
Date: Wed, 9 Aug 2023 13:42:16 +0200
Subject: [PATCH 0548/1189] backlight: lp855x: Drop ret variable in brightness
 change function

Fixes the following warning:

drivers/video/backlight/lp855x_bl.c:252:7: warning: variable 'ret' is used
uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized]

Signed-off-by: Artur Weber <aweber.kernel@gmail.com>
Fixes: 5145531be5fb ("backlight: lp855x: Catch errors when changing brightness")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202308091728.NEJhgUPP-lkp@intel.com/
Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Link: https://lore.kernel.org/r/20230809114216.4078-1-aweber.kernel@gmail.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/video/backlight/lp855x_bl.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/video/backlight/lp855x_bl.c b/drivers/video/backlight/lp855x_bl.c
index 61a7f45bfad8..da1f124db69c 100644
--- a/drivers/video/backlight/lp855x_bl.c
+++ b/drivers/video/backlight/lp855x_bl.c
@@ -241,19 +241,17 @@ static int lp855x_bl_update_status(struct backlight_device *bl)
 {
 	struct lp855x *lp = bl_get_data(bl);
 	int brightness = bl->props.brightness;
-	int ret;
 
 	if (bl->props.state & (BL_CORE_SUSPENDED | BL_CORE_FBBLANK))
 		brightness = 0;
 
 	if (lp->mode == PWM_BASED)
-		ret = lp855x_pwm_ctrl(lp, brightness,
+		return lp855x_pwm_ctrl(lp, brightness,
 				      bl->props.max_brightness);
 	else if (lp->mode == REGISTER_BASED)
-		ret = lp855x_write_byte(lp, lp->cfg->reg_brightness,
+		return lp855x_write_byte(lp, lp->cfg->reg_brightness,
 					(u8)brightness);
-
-	return ret;
+	return -EINVAL;
 }
 
 static const struct backlight_ops lp855x_bl_ops = {

From 83a0943b1870944612a8aa0049f910826ebfd4f7 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 17 Aug 2023 12:11:51 -0300
Subject: [PATCH 0549/1189] perf trace: Use the augmented_raw_syscall BPF skel
 only for tracing syscalls

It is possible to use 'perf trace' with tracepoints and in that case we
can't initialize/use the augmented_raw_syscalls BPF skel.

For instance, this usecase:

  # perf trace -e sched:*exec --max-events=5
         ? (         ): NetworkManager/1183  ... [continued]: poll())                                             = 1
     0.043 ( 0.007 ms): NetworkManager/1183 epoll_wait(epfd: 17<anon_inode:[eventpoll]>, events: 0x55555f90e920, maxevents: 6) = 0
     0.060 ( 0.007 ms): NetworkManager/1183 write(fd: 3<anon_inode:[eventfd]>, buf: 0x7ffc5a27cd30, count: 8)     = 8
     0.073 ( 0.005 ms): NetworkManager/1183 epoll_wait(epfd: 24<anon_inode:[eventpoll]>, events: 0x7ffc5a27cd20, maxevents: 2) = 1
     0.082 ( 0.010 ms): NetworkManager/1183 recvmmsg(fd: 26<socket:[30298]>, mmsg: 0x7ffc5a27caa0, vlen: 8)       = 1
  #

Where we want to trace just some sched tracepoints ending in 'exec' ends
up tracing all syscalls.

Fix it by checking existing trace->trace_syscalls boolean to see if we
need the augmenter.

A followup patch will move those sections of code used only with the
augmenter to separate functions, to get it cleaner and remove the goto,
done just for reviewing purposes.

With this patch in place the previous behaviour is restored: no syscalls
when we have other events and no syscall names:

  [root@quaco ~]# perf probe do_filp_open "filename=pathname->name:string"
  Added new event:
    probe:do_filp_open   (on do_filp_open with filename=pathname->name:string)

  You can now use it in all perf tools, such as:

	  perf record -e probe:do_filp_open -aR sleep 1

  [root@quaco ~]# perf trace --max-events=10 -e probe:do_filp_open sleep 1
     0.000 sleep/455122 probe:do_filp_open(__probe_ip: -1186560412, filename: "/etc/ld.so.cache")
     0.056 sleep/455122 probe:do_filp_open(__probe_ip: -1186560412, filename: "/lib64/libc.so.6")
     0.481 sleep/455122 probe:do_filp_open(__probe_ip: -1186560412, filename: "/usr/lib/locale/locale-archive")
     0.501 sleep/455122 probe:do_filp_open(__probe_ip: -1186560412, filename: "/usr/share/locale/locale.alias")
     0.572 sleep/455122 probe:do_filp_open(__probe_ip: -1186560412, filename: "/usr/lib/locale/en_US.UTF-8/LC_IDENTIFICATION")
     0.581 sleep/455122 probe:do_filp_open(__probe_ip: -1186560412, filename: "/usr/lib/locale/en_US.utf8/LC_IDENTIFICATION")
     0.616 sleep/455122 probe:do_filp_open(__probe_ip: -1186560412, filename: "/usr/lib64/gconv/gconv-modules.cache")
     0.656 sleep/455122 probe:do_filp_open(__probe_ip: -1186560412, filename: "/usr/lib/locale/en_US.UTF-8/LC_MEASUREMENT")
     0.664 sleep/455122 probe:do_filp_open(__probe_ip: -1186560412, filename: "/usr/lib/locale/en_US.utf8/LC_MEASUREMENT")
     0.696 sleep/455122 probe:do_filp_open(__probe_ip: -1186560412, filename: "/usr/lib/locale/en_US.UTF-8/LC_TELEPHONE")
  [root@quaco ~]#

As well as mixing syscalls with tracepoints, getting the syscall
tracepoints used augmented using the BPF skel:

  [root@quaco ~]# perf trace --max-events=10 -e open*,probe:do_filp_open sleep 1
     0.000 (         ): sleep/455124 openat(dfd: CWD, filename: "/etc/ld.so.cache", flags: RDONLY|CLOEXEC) ...
     0.005 (         ): sleep/455124 probe:do_filp_open(__probe_ip: -1186560412, filename: "/etc/ld.so.cache")
     0.000 ( 0.011 ms): sleep/455124  ... [continued]: openat())                                           = 3
     0.031 (         ): sleep/455124 openat(dfd: CWD, filename: "/lib64/libc.so.6", flags: RDONLY|CLOEXEC) ...
     0.033 (         ): sleep/455124 probe:do_filp_open(__probe_ip: -1186560412, filename: "/lib64/libc.so.6")
     0.031 ( 0.006 ms): sleep/455124  ... [continued]: openat())                                           = 3
     0.258 (         ): sleep/455124 openat(dfd: CWD, filename: "/usr/lib/locale/locale-archive", flags: RDONLY|CLOEXEC) ...
     0.261 (         ): sleep/455124 probe:do_filp_open(__probe_ip: -1186560412, filename: "/usr/lib/locale/locale-archive")
     0.258 ( 0.006 ms): sleep/455124  ... [continued]: openat())                                           = -1 ENOENT (No such file or directory)
     0.272 (         ): sleep/455124 openat(dfd: CWD, filename: "/usr/share/locale/locale.alias", flags: RDONLY|CLOEXEC) ...
     0.273  (        ): sleep/455124 probe:do_filp_open(__probe_ip: -1186560412, filename: "/usr/share/locale/locale.alias")

A final note: the probe:do_filp_open uses a kprobe (probably optimized
as its in the start of a function) that uses the kprobe_tracer mechanism
in the kernel to collect the pathname->name string and stash it into the
tracepoint created by 'perf probe' for that:

  [root@quaco ~]# cat /sys/kernel/debug/tracing/kprobe_events
  p:probe/do_filp_open _text+4621920 filename=+0(+0(%si)):string
  [root@quaco ~]#

While the syscalls:sys_enter_openat tracepoint gets its string from a
BPF program attached to raw_syscalls:sys_enter that tail calls into
another BPF program that knows the types for the openat syscall args and
thus can bpf_probe_read it right after the normal
sys_enter/sys_enter_openat tracepoint payload that comes prefixed with
whatever perf_event_open asked for (CPU, timestamp, etc):

  [root@quaco ~]# bpftool prog | grep -E "sys_enter |sys_enter_opena" -A3
  3176: tracepoint  name sys_enter  tag 0bc3fc9d11754ba1  gpl
	loaded_at 2023-08-17T12:32:20-0300  uid 0
	xlated 272B  jited 257B  memlock 4096B  map_ids 2462,2466,2463
	btf_id 2976
  --
  3180: tracepoint  name sys_enter_opena  tag 19dd077f00ec2f58  gpl
	  loaded_at 2023-08-17T12:32:20-0300  uid 0
	  xlated 328B  jited 206B  memlock 4096B  map_ids 2466,2465
	  btf_id 2976
  [root@quaco ~]#

Fixes: 5e6da6be3082f77b ("perf trace: Migrate BPF augmentation to use a skeleton")
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Carsten Haitzler <carsten.haitzler@arm.com>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Fangrui Song <maskray@google.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Cc: Tiezhu Yang <yangtiezhu@loongson.cn>
Cc: Tom Rix <trix@redhat.com>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Wang ShaoBo <bobo.shaobowang@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: Yonghong Song <yhs@fb.com>
Cc: YueHaibing <yuehaibing@huawei.com>
Link: https://lore.kernel.org/lkml/ZN4+s2Wl+zYmXTDj@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 0ebfa95895e0..3964cf44cdbc 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -3895,7 +3895,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	if (err < 0)
 		goto out_error_open;
 #ifdef HAVE_BPF_SKEL
-	{
+	if (trace->syscalls.events.bpf_output) {
 		struct perf_cpu cpu;
 
 		/*
@@ -3916,7 +3916,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 		goto out_error_mem;
 
 #ifdef HAVE_BPF_SKEL
-	if (trace->skel->progs.sys_enter)
+	if (trace->skel && trace->skel->progs.sys_enter)
 		trace__init_syscalls_bpf_prog_array_maps(trace);
 #endif
 
@@ -4850,6 +4850,9 @@ int cmd_trace(int argc, const char **argv)
 	}
 
 #ifdef HAVE_BPF_SKEL
+	if (!trace.trace_syscalls)
+		goto skip_augmentation;
+
 	trace.skel = augmented_raw_syscalls_bpf__open();
 	if (!trace.skel) {
 		pr_debug("Failed to open augmented syscalls BPF skeleton");
@@ -4884,6 +4887,7 @@ int cmd_trace(int argc, const char **argv)
 	}
 	trace.syscalls.events.bpf_output = evlist__last(trace.evlist);
 	assert(!strcmp(evsel__name(trace.syscalls.events.bpf_output), "__augmented_syscalls__"));
+skip_augmentation:
 #endif
 	err = -1;
 

From 64917f4df048a0649ea7901c2321f020e71e6f24 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 17 Aug 2023 15:14:21 -0300
Subject: [PATCH 0550/1189] perf trace: Use heuristic when deciding if a
 syscall tracepoint "const char *" field is really a string

'perf trace' tries to find BPF progs associated with a syscall that have
a signature that is similar to syscalls without one to try and reuse,
so, for instance, the 'open' signature can be reused with many other
syscalls that have as its first arg a string.

It uses the tracefs events format file for finding a signature that can
be reused, but then comes the "write" syscall with its second argument
as a "const char *":

  # cat /sys/kernel/debug/tracing/events/syscalls/sys_enter_write/format
  name: sys_enter_write
  ID: 746
  format:
  	field:unsigned short common_type;	offset:0;	size:2;	signed:0;
  	field:unsigned char common_flags;	offset:2;	size:1;	signed:0;
  	field:unsigned char common_preempt_count;	offset:3;	size:1;	signed:0;
  	field:int common_pid;	offset:4;	size:4;	signed:1;

  	field:int __syscall_nr;	offset:8;	size:4;	signed:1;
  	field:unsigned int fd;	offset:16;	size:8;	signed:0;
  	field:const char * buf;	offset:24;	size:8;	signed:0;
  	field:size_t count;	offset:32;	size:8;	signed:0;

  print fmt: "fd: 0x%08lx, buf: 0x%08lx, count: 0x%08lx", ((unsigned long)(REC->fd)), ((unsigned long)(REC->buf)), ((unsigned long)(REC->count))
  #

Which isn't a string (the man page for glibc has buf as "void *"), so we
have to use the name of the argument as an heuristic, to consider a
string just args that are "const char *" and that have in its name  the
"path", "file", etc substrings.

With that now it reuses:

  [root@quaco ~]# perf trace -v --max-events=1 |& grep Reus
  Reusing "open" BPF sys_enter augmenter for "stat"
  Reusing "open" BPF sys_enter augmenter for "lstat"
  Reusing "open" BPF sys_enter augmenter for "access"
  Reusing "connect" BPF sys_enter augmenter for "accept"
  Reusing "sendto" BPF sys_enter augmenter for "recvfrom"
  Reusing "connect" BPF sys_enter augmenter for "bind"
  Reusing "connect" BPF sys_enter augmenter for "getsockname"
  Reusing "connect" BPF sys_enter augmenter for "getpeername"
  Reusing "open" BPF sys_enter augmenter for "execve"
  Reusing "open" BPF sys_enter augmenter for "truncate"
  Reusing "open" BPF sys_enter augmenter for "chdir"
  Reusing "open" BPF sys_enter augmenter for "mkdir"
  Reusing "open" BPF sys_enter augmenter for "rmdir"
  Reusing "open" BPF sys_enter augmenter for "creat"
  Reusing "open" BPF sys_enter augmenter for "link"
  Reusing "open" BPF sys_enter augmenter for "unlink"
  Reusing "open" BPF sys_enter augmenter for "symlink"
  Reusing "open" BPF sys_enter augmenter for "readlink"
  Reusing "open" BPF sys_enter augmenter for "chmod"
  Reusing "open" BPF sys_enter augmenter for "chown"
  Reusing "open" BPF sys_enter augmenter for "lchown"
  Reusing "open" BPF sys_enter augmenter for "mknod"
  Reusing "open" BPF sys_enter augmenter for "statfs"
  Reusing "open" BPF sys_enter augmenter for "pivot_root"
  Reusing "open" BPF sys_enter augmenter for "chroot"
  Reusing "open" BPF sys_enter augmenter for "acct"
  Reusing "open" BPF sys_enter augmenter for "swapon"
  Reusing "open" BPF sys_enter augmenter for "swapoff"
  Reusing "open" BPF sys_enter augmenter for "delete_module"
  Reusing "open" BPF sys_enter augmenter for "setxattr"
  Reusing "open" BPF sys_enter augmenter for "lsetxattr"
  Reusing "openat" BPF sys_enter augmenter for "fsetxattr"
  Reusing "open" BPF sys_enter augmenter for "getxattr"
  Reusing "open" BPF sys_enter augmenter for "lgetxattr"
  Reusing "openat" BPF sys_enter augmenter for "fgetxattr"
  Reusing "open" BPF sys_enter augmenter for "listxattr"
  Reusing "open" BPF sys_enter augmenter for "llistxattr"
  Reusing "open" BPF sys_enter augmenter for "removexattr"
  Reusing "open" BPF sys_enter augmenter for "lremovexattr"
  Reusing "fsetxattr" BPF sys_enter augmenter for "fremovexattr"
  Reusing "open" BPF sys_enter augmenter for "mq_open"
  Reusing "open" BPF sys_enter augmenter for "mq_unlink"
  Reusing "fsetxattr" BPF sys_enter augmenter for "add_key"
  Reusing "fremovexattr" BPF sys_enter augmenter for "request_key"
  Reusing "fremovexattr" BPF sys_enter augmenter for "inotify_add_watch"
  Reusing "fremovexattr" BPF sys_enter augmenter for "mkdirat"
  Reusing "fremovexattr" BPF sys_enter augmenter for "mknodat"
  Reusing "fremovexattr" BPF sys_enter augmenter for "fchownat"
  Reusing "fremovexattr" BPF sys_enter augmenter for "futimesat"
  Reusing "fremovexattr" BPF sys_enter augmenter for "newfstatat"
  Reusing "fremovexattr" BPF sys_enter augmenter for "unlinkat"
  Reusing "fremovexattr" BPF sys_enter augmenter for "linkat"
  Reusing "open" BPF sys_enter augmenter for "symlinkat"
  Reusing "fremovexattr" BPF sys_enter augmenter for "readlinkat"
  Reusing "fremovexattr" BPF sys_enter augmenter for "fchmodat"
  Reusing "fremovexattr" BPF sys_enter augmenter for "faccessat"
  Reusing "fremovexattr" BPF sys_enter augmenter for "utimensat"
  Reusing "connect" BPF sys_enter augmenter for "accept4"
  Reusing "fremovexattr" BPF sys_enter augmenter for "name_to_handle_at"
  Reusing "fremovexattr" BPF sys_enter augmenter for "renameat2"
  Reusing "open" BPF sys_enter augmenter for "memfd_create"
  Reusing "fremovexattr" BPF sys_enter augmenter for "execveat"
  Reusing "fremovexattr" BPF sys_enter augmenter for "statx"
  [root@quaco ~]#

Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alan Maguire <alan.maguire@oracle.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/ZN5lrdeEdSMCn7hk@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 3964cf44cdbc..e541d0e2777a 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -3398,6 +3398,19 @@ try_to_find_pair:
 			if (strcmp(field->type, candidate_field->type))
 				goto next_candidate;
 
+			/*
+			 * This is limited in the BPF program but sys_write
+			 * uses "const char *" for its "buf" arg so we need to
+			 * use some heuristic that is kinda future proof...
+			 */
+			if (strcmp(field->type, "const char *") == 0 &&
+			    !(strstr(field->name, "name") ||
+			      strstr(field->name, "path") ||
+			      strstr(field->name, "file") ||
+			      strstr(field->name, "root") ||
+			      strstr(field->name, "description")))
+				goto next_candidate;
+
 			is_candidate = true;
 		}
 

From 11efe9e3f80a994aed1276bfce5c3b01884fa984 Mon Sep 17 00:00:00 2001
From: Li Hua Qian <huaqian.li@siemens.com>
Date: Tue, 18 Jul 2023 10:10:05 +0800
Subject: [PATCH 0551/1189] dt-bindings: watchdog: ti,rti-wdt: Add support for
 WDIOF_CARDRESET

TI RTI (Real Time Interrupt) Watchdog doesn't support to record the
watchdog cause. Add a reserved memory to know the last reboot was caused
by the watchdog card. In the reserved memory, some specific info will be
saved to indicate whether the watchdog reset was triggered in last
boot.

Signed-off-by: Li Hua Qian <huaqian.li@siemens.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20230718021007.1338761-2-huaqian.li@siemens.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 .../bindings/watchdog/ti,rti-wdt.yaml         | 28 ++++++++++++++++++-
 1 file changed, 27 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/watchdog/ti,rti-wdt.yaml b/Documentation/devicetree/bindings/watchdog/ti,rti-wdt.yaml
index fc553211e42d..62ddc284a524 100644
--- a/Documentation/devicetree/bindings/watchdog/ti,rti-wdt.yaml
+++ b/Documentation/devicetree/bindings/watchdog/ti,rti-wdt.yaml
@@ -34,6 +34,20 @@ properties:
   power-domains:
     maxItems: 1
 
+  memory-region:
+    maxItems: 1
+    description:
+      Contains the watchdog reserved memory. It is optional.
+      In the reserved memory, the specified values, which are
+      PON_REASON_SOF_NUM(0xBBBBCCCC), PON_REASON_MAGIC_NUM(0xDDDDDDDD),
+      and PON_REASON_EOF_NUM(0xCCCCBBBB), are pre-stored at the first
+      3 * 4 bytes to tell that last boot was caused by watchdog reset.
+      Once the PON reason is captured by driver(rti_wdt.c), the driver
+      is supposed to wipe the whole memory region. Surely, if this
+      property is set, at least 12 bytes reserved memory starting from
+      specific memory address(0xa220000) should be set. More please
+      refer to example.
+
 required:
   - compatible
   - reg
@@ -47,7 +61,18 @@ examples:
     /*
      * RTI WDT in main domain on J721e SoC. Assigned clocks are used to
      * select the source clock for the watchdog, forcing it to tick with
-     * a 32kHz clock in this case.
+     * a 32kHz clock in this case. Add a reserved memory(optional) to keep
+     * the watchdog reset cause persistent, which was be written in 12 bytes
+     * starting from 0xa2200000 by RTI Watchdog Firmware, then make it
+     * possible to get watchdog reset cause in driver.
+     *
+     * Reserved memory should be defined as follows:
+     * reserved-memory {
+     *     wdt_reset_memory_region: wdt-memory@a2200000 {
+     *         reg = <0x00 0xa2200000 0x00 0x1000>;
+     *         no-map;
+     *     };
+     * }
      */
     #include <dt-bindings/soc/ti,sci_pm_domain.h>
 
@@ -58,4 +83,5 @@ examples:
         power-domains = <&k3_pds 252 TI_SCI_PD_EXCLUSIVE>;
         assigned-clocks = <&k3_clks 252 1>;
         assigned-clock-parents = <&k3_clks 252 5>;
+        memory-region = <&wdt_reset_memory_region>;
     };

From f20ca595ae23314db0383940a184317333c46662 Mon Sep 17 00:00:00 2001
From: Li Hua Qian <huaqian.li@siemens.com>
Date: Tue, 18 Jul 2023 10:10:07 +0800
Subject: [PATCH 0552/1189] watchdog:rit_wdt: Add support for WDIOF_CARDRESET

This patch adds the WDIOF_CARDRESET support for the platform watchdog
whose hardware does not support this feature, to know if the board
reboot is due to a watchdog reset.

This is done via reserved memory(RAM), which indicates if specific
info saved, triggering the watchdog reset in last boot.

Signed-off-by: Li Hua Qian <huaqian.li@siemens.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20230718021007.1338761-4-huaqian.li@siemens.com
[groeck: vaddr == NULL --> !vaddr]
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/rti_wdt.c | 48 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)

diff --git a/drivers/watchdog/rti_wdt.c b/drivers/watchdog/rti_wdt.c
index ce8f18e93aa9..8e1be7ba0103 100644
--- a/drivers/watchdog/rti_wdt.c
+++ b/drivers/watchdog/rti_wdt.c
@@ -14,6 +14,8 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/types.h>
@@ -52,6 +54,11 @@
 
 #define DWDST			BIT(1)
 
+#define PON_REASON_SOF_NUM	0xBBBBCCCC
+#define PON_REASON_MAGIC_NUM	0xDDDDDDDD
+#define PON_REASON_EOF_NUM	0xCCCCBBBB
+#define RESERVED_MEM_MIN_SIZE	12
+
 static int heartbeat = DEFAULT_HEARTBEAT;
 
 /*
@@ -198,6 +205,11 @@ static int rti_wdt_probe(struct platform_device *pdev)
 	struct rti_wdt_device *wdt;
 	struct clk *clk;
 	u32 last_ping = 0;
+	struct device_node *node;
+	u32 reserved_mem_size;
+	struct resource res;
+	u32 *vaddr;
+	u64 paddr;
 
 	wdt = devm_kzalloc(dev, sizeof(*wdt), GFP_KERNEL);
 	if (!wdt)
@@ -284,6 +296,42 @@ static int rti_wdt_probe(struct platform_device *pdev)
 		}
 	}
 
+	node = of_parse_phandle(pdev->dev.of_node, "memory-region", 0);
+	if (node) {
+		ret = of_address_to_resource(node, 0, &res);
+		if (ret) {
+			dev_err(dev, "No memory address assigned to the region.\n");
+			goto err_iomap;
+		}
+
+		/*
+		 * If reserved memory is defined for watchdog reset cause.
+		 * Readout the Power-on(PON) reason and pass to bootstatus.
+		 */
+		paddr = res.start;
+		reserved_mem_size = resource_size(&res);
+		if (reserved_mem_size < RESERVED_MEM_MIN_SIZE) {
+			dev_err(dev, "The size of reserved memory is too small.\n");
+			ret = -EINVAL;
+			goto err_iomap;
+		}
+
+		vaddr = memremap(paddr, reserved_mem_size, MEMREMAP_WB);
+		if (!vaddr) {
+			dev_err(dev, "Failed to map memory-region.\n");
+			ret = -ENOMEM;
+			goto err_iomap;
+		}
+
+		if (vaddr[0] == PON_REASON_SOF_NUM &&
+		    vaddr[1] == PON_REASON_MAGIC_NUM &&
+		    vaddr[2] == PON_REASON_EOF_NUM) {
+			wdd->bootstatus |= WDIOF_CARDRESET;
+		}
+		memset(vaddr, 0, reserved_mem_size);
+		memunmap(vaddr);
+	}
+
 	watchdog_init_timeout(wdd, heartbeat, dev);
 
 	ret = watchdog_register_device(wdd);

From aeb3ef51b602dce456c850414aa1becd0e7aeab1 Mon Sep 17 00:00:00 2001
From: Chengfeng Ye <dg573847474@gmail.com>
Date: Wed, 5 Jul 2023 09:09:51 +0000
Subject: [PATCH 0553/1189] watchdog: s3c2410: Fix potential deadlock on
 &wdt->lock

As &wdt->lock is acquired by hard irq s3c2410wdt_irq(),
other acquisition of the same lock under process context should
disable irq, otherwise deadlock could happen if the
irq preempt the execution while the lock is held in process context
on the same CPU.

[Deadlock Scenario]
s3c2410wdt_suspend()
    -> s3c2410wdt_stop()
    -> spin_lock(&wdt->lock)
        <irq iterrupt>
        -> s3c2410wdt_irq()
        -> s3c2410wdt_keepalive()
        -> spin_lock(&wdt->lock) (deadlock here)

[Deadlock Scenario]
s3c2410wdt_probe()
    -> s3c2410wdt_start()
    -> spin_lock(&wdt->lock)
        <irq iterrupt>
        -> s3c2410wdt_irq()
        -> s3c2410wdt_keepalive()
        -> spin_lock(&wdt->lock) (deadlock here)

[Deadlock Scenario]
s3c2410wdt_keepalive()
    -> spin_lock(&wdt->lock)
        <irq iterrupt>
        -> s3c2410wdt_irq()
        -> s3c2410wdt_keepalive()
        -> spin_lock(&wdt->lock) (deadlock here)

This flaw was found by an experimental static analysis tool I am
developing for irq-related deadlock, which reported the above
warning when analyzing the linux kernel 6.4-rc7 release.

The tentative patch fix the potential deadlock by spin_lock_irqsave()
under process context.

Signed-off-by: Chengfeng Ye <dg573847474@gmail.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20230705090951.63762-1-dg573847474@gmail.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/s3c2410_wdt.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/watchdog/s3c2410_wdt.c b/drivers/watchdog/s3c2410_wdt.c
index 2bcc8faa7fa5..0b4bd883ff28 100644
--- a/drivers/watchdog/s3c2410_wdt.c
+++ b/drivers/watchdog/s3c2410_wdt.c
@@ -378,10 +378,11 @@ static int s3c2410wdt_enable(struct s3c2410_wdt *wdt, bool en)
 static int s3c2410wdt_keepalive(struct watchdog_device *wdd)
 {
 	struct s3c2410_wdt *wdt = watchdog_get_drvdata(wdd);
+	unsigned long flags;
 
-	spin_lock(&wdt->lock);
+	spin_lock_irqsave(&wdt->lock, flags);
 	writel(wdt->count, wdt->reg_base + S3C2410_WTCNT);
-	spin_unlock(&wdt->lock);
+	spin_unlock_irqrestore(&wdt->lock, flags);
 
 	return 0;
 }
@@ -398,10 +399,11 @@ static void __s3c2410wdt_stop(struct s3c2410_wdt *wdt)
 static int s3c2410wdt_stop(struct watchdog_device *wdd)
 {
 	struct s3c2410_wdt *wdt = watchdog_get_drvdata(wdd);
+	unsigned long flags;
 
-	spin_lock(&wdt->lock);
+	spin_lock_irqsave(&wdt->lock, flags);
 	__s3c2410wdt_stop(wdt);
-	spin_unlock(&wdt->lock);
+	spin_unlock_irqrestore(&wdt->lock, flags);
 
 	return 0;
 }
@@ -410,8 +412,9 @@ static int s3c2410wdt_start(struct watchdog_device *wdd)
 {
 	unsigned long wtcon;
 	struct s3c2410_wdt *wdt = watchdog_get_drvdata(wdd);
+	unsigned long flags;
 
-	spin_lock(&wdt->lock);
+	spin_lock_irqsave(&wdt->lock, flags);
 
 	__s3c2410wdt_stop(wdt);
 
@@ -432,7 +435,7 @@ static int s3c2410wdt_start(struct watchdog_device *wdd)
 	writel(wdt->count, wdt->reg_base + S3C2410_WTDAT);
 	writel(wdt->count, wdt->reg_base + S3C2410_WTCNT);
 	writel(wtcon, wdt->reg_base + S3C2410_WTCON);
-	spin_unlock(&wdt->lock);
+	spin_unlock_irqrestore(&wdt->lock, flags);
 
 	return 0;
 }

From 8b3c3662186046c440ffbb7f5efc5595b1696e9d Mon Sep 17 00:00:00 2001
From: Paul Cercueil <paul@crapouillou.net>
Date: Thu, 6 Jul 2023 10:29:28 +0200
Subject: [PATCH 0554/1189] watchdog: starfive: Remove #ifdef guards for PM
 related functions

Use the new PM macros for the suspend and resume functions to be
automatically dropped by the compiler when CONFIG_PM or
CONFIG_PM_SLEEP are disabled, without having to use #ifdef guards.

This has the advantage of always compiling these functions in,
independently of any Kconfig option. Thanks to that, bugs and other
regressions are subsequently easier to catch.

Signed-off-by: Paul Cercueil <paul@crapouillou.net>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20230706082928.10869-1-paul@crapouillou.net
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/starfive-wdt.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/drivers/watchdog/starfive-wdt.c b/drivers/watchdog/starfive-wdt.c
index 9e6db8e0164f..5f501b41faf9 100644
--- a/drivers/watchdog/starfive-wdt.c
+++ b/drivers/watchdog/starfive-wdt.c
@@ -527,7 +527,6 @@ static void starfive_wdt_shutdown(struct platform_device *pdev)
 	starfive_wdt_pm_stop(&wdt->wdd);
 }
 
-#ifdef CONFIG_PM_SLEEP
 static int starfive_wdt_suspend(struct device *dev)
 {
 	struct starfive_wdt *wdt = dev_get_drvdata(dev);
@@ -557,9 +556,7 @@ static int starfive_wdt_resume(struct device *dev)
 
 	return starfive_wdt_start(wdt);
 }
-#endif /* CONFIG_PM_SLEEP */
 
-#ifdef CONFIG_PM
 static int starfive_wdt_runtime_suspend(struct device *dev)
 {
 	struct starfive_wdt *wdt = dev_get_drvdata(dev);
@@ -575,11 +572,10 @@ static int starfive_wdt_runtime_resume(struct device *dev)
 
 	return starfive_wdt_enable_clock(wdt);
 }
-#endif /* CONFIG_PM */
 
 static const struct dev_pm_ops starfive_wdt_pm_ops = {
-	SET_RUNTIME_PM_OPS(starfive_wdt_runtime_suspend, starfive_wdt_runtime_resume, NULL)
-	SET_SYSTEM_SLEEP_PM_OPS(starfive_wdt_suspend, starfive_wdt_resume)
+	RUNTIME_PM_OPS(starfive_wdt_runtime_suspend, starfive_wdt_runtime_resume, NULL)
+	SYSTEM_SLEEP_PM_OPS(starfive_wdt_suspend, starfive_wdt_resume)
 };
 
 static const struct of_device_id starfive_wdt_match[] = {
@@ -595,7 +591,7 @@ static struct platform_driver starfive_wdt_driver = {
 	.shutdown = starfive_wdt_shutdown,
 	.driver = {
 		.name = "starfive-wdt",
-		.pm = &starfive_wdt_pm_ops,
+		.pm = pm_ptr(&starfive_wdt_pm_ops),
 		.of_match_table = starfive_wdt_match,
 	},
 };

From 98334dc292fddba043fef8f6ebc84b22d42baca9 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Tue, 15 Aug 2023 12:06:50 -0700
Subject: [PATCH 0555/1189] watchdog: xilinx_wwdt: Use div_u64() in
 xilinx_wwdt_start()

After commit f1a43aadb5a6 ("watchdog: Enable COMPILE_TEST for more
drivers"), it is possible to enable this driver on 32-bit architectures.
When building for those architectures with clang, there is an error due
to a 64-bit division in xilinx_wwdt_start():

  ERROR: modpost: "__aeabi_uldivmod" [drivers/watchdog/xilinx_wwdt.ko] undefined!

Use div_u64() to fix this, which takes a 64-bit dividend and 32-bit
divisor. GCC likely avoids the same error due to optimizations it
employs to transform division by a constant into other equivalent
operations, which may be different than what is implemented in clang.

Link: https://github.com/ClangBuiltLinux/linux/issues/1915
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20230815-watchdog-xilinx-div_u64-v1-1-20b0b5a65c2e@kernel.org
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/xilinx_wwdt.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/watchdog/xilinx_wwdt.c b/drivers/watchdog/xilinx_wwdt.c
index 1d998db41533..d271e2e8d6e2 100644
--- a/drivers/watchdog/xilinx_wwdt.c
+++ b/drivers/watchdog/xilinx_wwdt.c
@@ -9,6 +9,7 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/ioport.h>
+#include <linux/math64.h>
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
@@ -71,7 +72,7 @@ static int xilinx_wwdt_start(struct watchdog_device *wdd)
 
 	/* Calculate timeout count */
 	time_out = xdev->freq * wdd->timeout;
-	closed_timeout = (time_out * xdev->close_percent) / 100;
+	closed_timeout = div_u64(time_out * xdev->close_percent, 100);
 	open_timeout = time_out - closed_timeout;
 	wdd->min_hw_heartbeat_ms = xdev->close_percent * 10 * wdd->timeout;
 

From 89e5e28e40320c38c0aa67e42032799ba8571ce8 Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Fri, 11 Aug 2023 14:27:07 +0800
Subject: [PATCH 0556/1189] watchdog: pm8916_wdt: Remove redundant
 of_match_ptr()

The driver depends on CONFIG_OF, it is not necessary to use
of_match_ptr() here.

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20230811062707.2301583-1-ruanjinjie@huawei.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/pm8916_wdt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/watchdog/pm8916_wdt.c b/drivers/watchdog/pm8916_wdt.c
index f4bfbffaf49c..f3fcbeb0852c 100644
--- a/drivers/watchdog/pm8916_wdt.c
+++ b/drivers/watchdog/pm8916_wdt.c
@@ -266,7 +266,7 @@ static struct platform_driver pm8916_wdt_driver = {
 	.probe = pm8916_wdt_probe,
 	.driver = {
 		.name = "pm8916-wdt",
-		.of_match_table = of_match_ptr(pm8916_wdt_id_table),
+		.of_match_table = pm8916_wdt_id_table,
 		.pm = &pm8916_wdt_pm_ops,
 	},
 };

From 486a64b29c5f43a9671713e781779863dda9bbc9 Mon Sep 17 00:00:00 2001
From: Meng Li <meng.li@windriver.com>
Date: Mon, 14 Aug 2023 17:06:16 +0800
Subject: [PATCH 0557/1189] watchdog: core: stop watchdog when executing
 poweroff command

On some platforms, for example, Intel SoC FPGA platform, the watchdog
is started in u-boot, and so kernel will create a timer and work to
keep watchdog alive. But when user executes commands "poweroff" or
"shutdown -h", the system is reset when watchdog triggers timeout even
if WDOG_STOP_ON_REBOOT is set in watchdog driver. The root cause is
that the watchdog is not stopped properly because the SYS_POWER_OFF case
is not supported in notify callback function. So, add this case to stop
watchdog when executing poweroff command.

Signed-off-by: Meng Li <Meng.Li@windriver.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20230814090616.1853263-1-Meng.Li@windriver.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/watchdog_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/watchdog/watchdog_core.c b/drivers/watchdog/watchdog_core.c
index d4c5a736fdcb..5b55ccae06d4 100644
--- a/drivers/watchdog/watchdog_core.c
+++ b/drivers/watchdog/watchdog_core.c
@@ -161,7 +161,7 @@ static int watchdog_reboot_notifier(struct notifier_block *nb,
 	struct watchdog_device *wdd;
 
 	wdd = container_of(nb, struct watchdog_device, reboot_nb);
-	if (code == SYS_DOWN || code == SYS_HALT) {
+	if (code == SYS_DOWN || code == SYS_HALT || code == SYS_POWER_OFF) {
 		if (watchdog_hw_running(wdd)) {
 			int ret;
 

From cf38e7691c85f1b09973b22a0b89bf1e1228d2f9 Mon Sep 17 00:00:00 2001
From: Raag Jadav <raag.jadav@intel.com>
Date: Fri, 11 Aug 2023 17:32:20 +0530
Subject: [PATCH 0558/1189] watchdog: intel-mid_wdt: add MODULE_ALIAS() to
 allow auto-load

When built with CONFIG_INTEL_MID_WATCHDOG=m, currently the driver
needs to be loaded manually, for the lack of module alias.
This causes unintended resets in cases where watchdog timer is
set-up by bootloader and the driver is not explicitly loaded.
Add MODULE_ALIAS() to load the driver automatically at boot and
avoid this issue.

Fixes: 87a1ef8058d9 ("watchdog: add Intel MID watchdog driver support")
Signed-off-by: Raag Jadav <raag.jadav@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20230811120220.31578-1-raag.jadav@intel.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/intel-mid_wdt.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/watchdog/intel-mid_wdt.c b/drivers/watchdog/intel-mid_wdt.c
index 9b2173f765c8..fb7fae750181 100644
--- a/drivers/watchdog/intel-mid_wdt.c
+++ b/drivers/watchdog/intel-mid_wdt.c
@@ -203,3 +203,4 @@ module_platform_driver(mid_wdt_driver);
 MODULE_AUTHOR("David Cohen <david.a.cohen@linux.intel.com>");
 MODULE_DESCRIPTION("Watchdog Driver for Intel MID platform");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:intel_mid_wdt");

From 266da53c35fce128ce47d8aa93e316e0a94f2f60 Mon Sep 17 00:00:00 2001
From: Mathieu Othacehe <othacehe@gnu.org>
Date: Sat, 19 Aug 2023 10:47:26 +0200
Subject: [PATCH 0559/1189] watchdog: sama5d4: readout initial state

Readout the AT91_WDT_MR bit at probe so that it becomes possible to get the
pre-userspace handler working.

Signed-off-by: Mathieu Othacehe <othacehe@gnu.org>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20230819084726.11037-1-othacehe@gnu.org
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/sama5d4_wdt.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/watchdog/sama5d4_wdt.c b/drivers/watchdog/sama5d4_wdt.c
index 71e8b5fbf51f..13e72918338a 100644
--- a/drivers/watchdog/sama5d4_wdt.c
+++ b/drivers/watchdog/sama5d4_wdt.c
@@ -254,6 +254,7 @@ static int sama5d4_wdt_probe(struct platform_device *pdev)
 	struct sama5d4_wdt *wdt;
 	void __iomem *regs;
 	u32 irq = 0;
+	u32 reg;
 	int ret;
 
 	wdt = devm_kzalloc(dev, sizeof(*wdt), GFP_KERNEL);
@@ -304,6 +305,12 @@ static int sama5d4_wdt_probe(struct platform_device *pdev)
 
 	watchdog_init_timeout(wdd, wdt_timeout, dev);
 
+	reg = wdt_read(wdt, AT91_WDT_MR);
+	if (!(reg & AT91_WDT_WDDIS)) {
+		wdt->mr &= ~AT91_WDT_WDDIS;
+		set_bit(WDOG_HW_RUNNING, &wdd->status);
+	}
+
 	ret = sama5d4_wdt_init(wdt);
 	if (ret)
 		return ret;

From ec3eb9ed6081bea8ebf603ff545dba127071b928 Mon Sep 17 00:00:00 2001
From: Reiji Watanabe <reijiw@google.com>
Date: Fri, 18 Aug 2023 21:39:44 -0700
Subject: [PATCH 0560/1189] KVM: arm64: PMU: Disallow vPMU on non-uniform
 PMUVer

Disallow userspace from configuring vPMU for guests on systems
where the PMUVer is not uniform across all PEs.
KVM has not been advertising PMUv3 to the guests with vPMU on
such systems anyway, and such systems would be extremely
uncommon and unlikely to even use KVM.

Signed-off-by: Reiji Watanabe <reijiw@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230819043947.4100985-2-reijiw@google.com
---
 arch/arm64/kvm/pmu-emul.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 560650972478..689bbd88fd69 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -14,6 +14,7 @@
 #include <asm/kvm_emulate.h>
 #include <kvm/arm_pmu.h>
 #include <kvm/arm_vgic.h>
+#include <asm/arm_pmuv3.h>
 
 #define PERF_ATTR_CFG1_COUNTER_64BIT	BIT(0)
 
@@ -672,8 +673,11 @@ void kvm_host_pmu_init(struct arm_pmu *pmu)
 {
 	struct arm_pmu_entry *entry;
 
-	if (pmu->pmuver == ID_AA64DFR0_EL1_PMUVer_NI ||
-	    pmu->pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF)
+	/*
+	 * Check the sanitised PMU version for the system, as KVM does not
+	 * support implementations where PMUv3 exists on a subset of CPUs.
+	 */
+	if (!pmuv3_implemented(kvm_arm_pmu_get_pmuver_limit()))
 		return;
 
 	mutex_lock(&arm_pmus_lock);

From 335ca49ff31f145c0f08540614062197a334e064 Mon Sep 17 00:00:00 2001
From: Reiji Watanabe <reijiw@google.com>
Date: Fri, 18 Aug 2023 21:39:45 -0700
Subject: [PATCH 0561/1189] KVM: arm64: PMU: Avoid inappropriate use of host's
 PMUVer

Avoid using the PMUVer of the host's PMU hardware to determine
the PMU event mask, except in one case, as the value of host's
PMUVer may differ from the value of ID_AA64DFR0_EL1.PMUVer for
the guest.

The exception case is when using the PMUVer to determine the
valid range of events for KVM_ARM_VCPU_PMU_V3_FILTER, as it has
been allowing userspace to specify events that are valid for
the PMU hardware, regardless of the value of the guest's
ID_AA64DFR0_EL1.PMUVer.  KVM will use a valid range of events
based on the value of the guest's ID_AA64DFR0_EL1.PMUVer,
in order to effectively filter events that the guest attempts
to program though.

Signed-off-by: Reiji Watanabe <reijiw@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230819043947.4100985-3-reijiw@google.com
---
 arch/arm64/kvm/pmu-emul.c | 22 ++++++++++++++++------
 1 file changed, 16 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 689bbd88fd69..eaeb8fea7971 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -36,12 +36,8 @@ static struct kvm_pmc *kvm_vcpu_idx_to_pmc(struct kvm_vcpu *vcpu, int cnt_idx)
 	return &vcpu->arch.pmu.pmc[cnt_idx];
 }
 
-static u32 kvm_pmu_event_mask(struct kvm *kvm)
+static u32 __kvm_pmu_event_mask(unsigned int pmuver)
 {
-	unsigned int pmuver;
-
-	pmuver = kvm->arch.arm_pmu->pmuver;
-
 	switch (pmuver) {
 	case ID_AA64DFR0_EL1_PMUVer_IMP:
 		return GENMASK(9, 0);
@@ -56,6 +52,14 @@ static u32 kvm_pmu_event_mask(struct kvm *kvm)
 	}
 }
 
+static u32 kvm_pmu_event_mask(struct kvm *kvm)
+{
+	u64 dfr0 = IDREG(kvm, SYS_ID_AA64DFR0_EL1);
+	u8 pmuver = SYS_FIELD_GET(ID_AA64DFR0_EL1, PMUVer, dfr0);
+
+	return __kvm_pmu_event_mask(pmuver);
+}
+
 /**
  * kvm_pmc_is_64bit - determine if counter is 64bit
  * @pmc: counter context
@@ -954,11 +958,17 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 		return 0;
 	}
 	case KVM_ARM_VCPU_PMU_V3_FILTER: {
+		u8 pmuver = kvm_arm_pmu_get_pmuver_limit();
 		struct kvm_pmu_event_filter __user *uaddr;
 		struct kvm_pmu_event_filter filter;
 		int nr_events;
 
-		nr_events = kvm_pmu_event_mask(kvm) + 1;
+		/*
+		 * Allow userspace to specify an event filter for the entire
+		 * event range supported by PMUVer of the hardware, rather
+		 * than the guest's PMUVer for KVM backward compatibility.
+		 */
+		nr_events = __kvm_pmu_event_mask(pmuver) + 1;
 
 		uaddr = (struct kvm_pmu_event_filter __user *)(long)attr->addr;
 

From 8c694f557fd80ca9815ddb1cf5de10d8bf168110 Mon Sep 17 00:00:00 2001
From: Reiji Watanabe <reijiw@google.com>
Date: Fri, 18 Aug 2023 21:39:46 -0700
Subject: [PATCH 0562/1189] KVM: arm64: PMU: Don't advertise the STALL_SLOT
 event

Currently, KVM hides the STALL_SLOT event for guests if the
host PMU version is PMUv3p4 or newer, as PMMIR_EL1 is handled
as RAZ for the guests. But, this should be based on the guests'
PMU version (instead of the host PMU version), as an older PMU
that doesn't support PMMIR_EL1 could support the STALL_SLOT
event, according to the Arm ARM. Exposing the STALL_SLOT event
without PMMIR_EL1 won't be very useful anyway though.

Stop advertising the STALL_SLOT event for guests unconditionally,
rather than fixing or keeping the inaccurate checking to
advertise the event for the case, where it is not very useful.

Suggested-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Reiji Watanabe <reijiw@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230819043947.4100985-4-reijiw@google.com
---
 arch/arm64/kvm/pmu-emul.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index eaeb8fea7971..b9633deff32a 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -761,8 +761,7 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
 		 * Don't advertise STALL_SLOT, as PMMIR_EL0 is handled
 		 * as RAZ
 		 */
-		if (vcpu->kvm->arch.arm_pmu->pmuver >= ID_AA64DFR0_EL1_PMUVer_V3P4)
-			val &= ~BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT - 32);
+		val &= ~BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT - 32);
 		base = 32;
 	}
 

From 64b81000b60b70f10a5834023fe100902d9f7a57 Mon Sep 17 00:00:00 2001
From: Reiji Watanabe <reijiw@google.com>
Date: Fri, 18 Aug 2023 21:39:47 -0700
Subject: [PATCH 0563/1189] KVM: arm64: PMU: Don't advertise
 STALL_SLOT_{FRONTEND,BACKEND}

Don't advertise STALL_SLOT_{FRONT,BACK}END events to the guest,
similar to STALL_SLOT event, as when any of these three events
are implemented, all three of them should be implemented,
according to the Arm ARM.

Suggested-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Reiji Watanabe <reijiw@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230819043947.4100985-5-reijiw@google.com
---
 arch/arm64/kvm/pmu-emul.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index b9633deff32a..6b066e04dc5d 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -758,10 +758,12 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
 	} else {
 		val = read_sysreg(pmceid1_el0);
 		/*
-		 * Don't advertise STALL_SLOT, as PMMIR_EL0 is handled
+		 * Don't advertise STALL_SLOT*, as PMMIR_EL0 is handled
 		 * as RAZ
 		 */
-		val &= ~BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT - 32);
+		val &= ~(BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT - 32) |
+			 BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND - 32) |
+			 BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND - 32));
 		base = 32;
 	}
 

From a4464092f2c514a7f0788906d340f0bab59fdd73 Mon Sep 17 00:00:00 2001
From: Ruan Jinjie <ruanjinjie@huawei.com>
Date: Fri, 18 Aug 2023 09:23:08 +0800
Subject: [PATCH 0564/1189] backlight: led_bl: Remove redundant of_match_ptr()

The driver depends on CONFIG_OF, it is not necessary to use
of_match_ptr() here.

Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org>
Link: https://lore.kernel.org/r/20230818012308.2058373-1-ruanjinjie@huawei.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/video/backlight/led_bl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/video/backlight/led_bl.c b/drivers/video/backlight/led_bl.c
index 3259292fda76..032f8bddf872 100644
--- a/drivers/video/backlight/led_bl.c
+++ b/drivers/video/backlight/led_bl.c
@@ -243,7 +243,7 @@ MODULE_DEVICE_TABLE(of, led_bl_of_match);
 static struct platform_driver led_bl_driver = {
 	.driver		= {
 		.name		= "led-backlight",
-		.of_match_table	= of_match_ptr(led_bl_of_match),
+		.of_match_table	= led_bl_of_match,
 	},
 	.probe		= led_bl_probe,
 	.remove_new	= led_bl_remove,

From 7298e876075eea8d2e782bf846ab0b4721afac92 Mon Sep 17 00:00:00 2001
From: John Garry <john.g.garry@oracle.com>
Date: Mon, 7 Aug 2023 11:16:31 +0000
Subject: [PATCH 0565/1189] perf jevents: Raise exception for no definition of
 a arch std event

Recently Ilkka reported that the JSONs for the AmpereOne arm64-based
platform included a dud event which referenced a non-existent arch std
event [0].

Previously in the times of jevents.c, we would raise an exception for this.

This is still invalid, even though the current code just ignores such an
event.

Re-introduce code to raise an exception for when no definition exists to
help catch as many invalid JSONs as possible.

[0] https://lore.kernel.org/linux-perf-users/9e851e2a-26c7-ba78-cb20-be4337b2916a@oracle.com/

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: John Garry <john.g.garry@oracle.com>
Tested-by: Ilkka Koskinen <ilkka@os.amperecomputing.com>
Link: https://lore.kernel.org/r/20230807111631.3033102-1-john.g.garry@oracle.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/jevents.py | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index 8cd561aa606a..98cccc3fcbbd 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -347,12 +347,15 @@ class JsonEvent:
       if self.desc and not self.desc.endswith('. '):
         self.desc += '. '
       self.desc = (self.desc if self.desc else '') + ('Unit: ' + self.pmu + ' ')
-    if arch_std and arch_std.lower() in _arch_std_events:
-      event = _arch_std_events[arch_std.lower()].event
-      # Copy from the architecture standard event to self for undefined fields.
-      for attr, value in _arch_std_events[arch_std.lower()].__dict__.items():
-        if hasattr(self, attr) and not getattr(self, attr):
-          setattr(self, attr, value)
+    if arch_std:
+      if arch_std.lower() in _arch_std_events:
+        event = _arch_std_events[arch_std.lower()].event
+        # Copy from the architecture standard event to self for undefined fields.
+        for attr, value in _arch_std_events[arch_std.lower()].__dict__.items():
+          if hasattr(self, attr) and not getattr(self, attr):
+            setattr(self, attr, value)
+      else:
+        raise argparse.ArgumentTypeError('Cannot find arch std event:', arch_std)
 
     self.event = real_event(self.name, event)
 

From b8af10062df3c23fe002c3f187389bb263b3eb20 Mon Sep 17 00:00:00 2001
From: Ilkka Koskinen <ilkka@os.amperecomputing.com>
Date: Thu, 3 Aug 2023 14:13:28 -0700
Subject: [PATCH 0566/1189] perf vendor events arm64: Remove L1D_CACHE_LMISS
 from AmpereOne list

amperene/cache.json file tried to include L1D_CACHE_LMISS while it
doesn't exist in common-and-microarch.json. While this bug doesn't seem to
cause issue in newer kernels with jevents.py script, it prevents building
older perf tools with the backported patch.

Fixes: a9650b7f6fc09d16 ("perf vendor events arm64: Add AmpereOne core PMU events")
Reported-by: Dave Kleikamp <dave.kleikamp@oracle.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Signed-off-by: Ilkka Koskinen <ilkka@os.amperecomputing.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ilkka Koskinen <ilkka@os.amperecomputing.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Closes: https://lore.kernel.org/all/76bb2e47-ce44-76ae-838e-53279047084d@oracle.com/
Link: https://lore.kernel.org/r/20230803211331.140553-2-ilkka@os.amperecomputing.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/arch/arm64/ampere/ampereone/cache.json | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/cache.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/cache.json
index fc0633054211..7a2b7b200f14 100644
--- a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/cache.json
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/cache.json
@@ -92,9 +92,6 @@
     {
         "ArchStdEvent": "L1D_CACHE_LMISS_RD"
     },
-    {
-        "ArchStdEvent": "L1D_CACHE_LMISS"
-    },
     {
         "ArchStdEvent": "L1I_CACHE_LMISS"
     },

From 47715f2b624d7c7f6fca96b1863db45b67f6710e Mon Sep 17 00:00:00 2001
From: Ilkka Koskinen <ilkka@os.amperecomputing.com>
Date: Thu, 3 Aug 2023 14:13:29 -0700
Subject: [PATCH 0567/1189] perf vendor events arm64: AmpereOne: Mark affected
 STALL_* events impacted by errata

Per errata AC03_CPU_29, STALL_SLOT_FRONTEND, STALL_FRONTEND, and STALL
events are not counting as expected. The follow up metrics patch will
include correct way to calculate the impacted events.

Reviewed-by: John Garry <john.g.garry@oracle.com>
Signed-off-by: Ilkka Koskinen <ilkka@os.amperecomputing.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Dave Kleikamp <dave.kleikamp@oracle.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20230803211331.140553-3-ilkka@os.amperecomputing.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../arch/arm64/ampere/ampereone/pipeline.json        | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/pipeline.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/pipeline.json
index f9fae15f7555..711028377f3e 100644
--- a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/pipeline.json
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/pipeline.json
@@ -1,18 +1,24 @@
 [
     {
-        "ArchStdEvent": "STALL_FRONTEND"
+        "ArchStdEvent": "STALL_FRONTEND",
+        "Errata": "Errata AC03_CPU_29",
+        "BriefDescription": "Impacted by errata, use metrics instead -"
     },
     {
         "ArchStdEvent": "STALL_BACKEND"
     },
     {
-        "ArchStdEvent": "STALL"
+        "ArchStdEvent": "STALL",
+        "Errata": "Errata AC03_CPU_29",
+        "BriefDescription": "Impacted by errata, use metrics instead -"
     },
     {
         "ArchStdEvent": "STALL_SLOT_BACKEND"
     },
     {
-        "ArchStdEvent": "STALL_SLOT_FRONTEND"
+        "ArchStdEvent": "STALL_SLOT_FRONTEND",
+        "Errata": "Errata AC03_CPU_29",
+        "BriefDescription": "Impacted by errata, use metrics instead -"
     },
     {
         "ArchStdEvent": "STALL_SLOT"

From 705ed549148fad1bea526a9102fa202905bdc86f Mon Sep 17 00:00:00 2001
From: Ilkka Koskinen <ilkka@os.amperecomputing.com>
Date: Thu, 3 Aug 2023 14:13:30 -0700
Subject: [PATCH 0568/1189] perf vendor events arm64: Add AmpereOne metrics

This patch adds AmpereOne metrics. The metrics also work around
the issue related to some of the events.

Signed-off-by: Ilkka Koskinen <ilkka@os.amperecomputing.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Dave Kleikamp <dave.kleikamp@oracle.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20230803211331.140553-4-ilkka@os.amperecomputing.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../arch/arm64/ampere/ampereone/metrics.json  | 362 ++++++++++++++++++
 1 file changed, 362 insertions(+)
 create mode 100644 tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json

diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json
new file mode 100644
index 000000000000..1e7e8901a445
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json
@@ -0,0 +1,362 @@
+[
+    {
+	"MetricExpr": "BR_MIS_PRED / BR_PRED",
+	"BriefDescription": "Branch predictor misprediction rate. May not count branches that are never resolved because they are in the misprediction shadow of an earlier branch",
+	"MetricGroup": "Branch Prediction",
+	"MetricName": "Misprediction"
+    },
+    {
+	"MetricExpr": "BR_MIS_PRED_RETIRED / BR_RETIRED",
+	"BriefDescription": "Branch predictor misprediction rate",
+	"MetricGroup": "Branch Prediction",
+	"MetricName": "Misprediction (retired)"
+    },
+    {
+	"MetricExpr": "BUS_ACCESS / ( BUS_CYCLES * 1)",
+	"BriefDescription": "Core-to-uncore bus utilization",
+	"MetricGroup": "Bus",
+	"MetricName": "Bus utilization"
+    },
+    {
+	"MetricExpr": "L1D_CACHE_REFILL / L1D_CACHE",
+	"BriefDescription": "L1D cache miss rate",
+	"MetricGroup": "Cache",
+	"MetricName": "L1D cache miss"
+    },
+    {
+	"MetricExpr": "L1D_CACHE_LMISS_RD / L1D_CACHE_RD",
+	"BriefDescription": "L1D cache read miss rate",
+	"MetricGroup": "Cache",
+	"MetricName": "L1D cache read miss"
+    },
+    {
+	"MetricExpr": "L1I_CACHE_REFILL / L1I_CACHE",
+	"BriefDescription": "L1I cache miss rate",
+	"MetricGroup": "Cache",
+	"MetricName": "L1I cache miss"
+    },
+    {
+	"MetricExpr": "L2D_CACHE_REFILL / L2D_CACHE",
+	"BriefDescription": "L2 cache miss rate",
+	"MetricGroup": "Cache",
+	"MetricName": "L2 cache miss"
+    },
+    {
+	"MetricExpr": "L1I_CACHE_LMISS / L1I_CACHE",
+	"BriefDescription": "L1I cache read miss rate",
+	"MetricGroup": "Cache",
+	"MetricName": "L1I cache read miss"
+    },
+    {
+	"MetricExpr": "L2D_CACHE_LMISS_RD / L2D_CACHE_RD",
+	"BriefDescription": "L2 cache read miss rate",
+	"MetricGroup": "Cache",
+	"MetricName": "L2 cache read miss"
+    },
+    {
+	"MetricExpr": "(L1D_CACHE_LMISS_RD * 1000) / INST_RETIRED",
+	"BriefDescription": "Misses per thousand instructions (data)",
+	"MetricGroup": "Cache",
+	"MetricName": "MPKI data"
+    },
+    {
+	"MetricExpr": "(L1I_CACHE_LMISS * 1000) / INST_RETIRED",
+	"BriefDescription": "Misses per thousand instructions (instruction)",
+	"MetricGroup": "Cache",
+	"MetricName": "MPKI instruction"
+    },
+    {
+	"MetricExpr": "ASE_SPEC / OP_SPEC",
+	"BriefDescription": "Proportion of advanced SIMD data processing operations (excluding DP_SPEC/LD_SPEC) operations",
+	"MetricGroup": "Instruction",
+	"MetricName": "ASE mix"
+    },
+    {
+	"MetricExpr": "CRYPTO_SPEC / OP_SPEC",
+	"BriefDescription": "Proportion of crypto data processing operations",
+	"MetricGroup": "Instruction",
+	"MetricName": "Crypto mix"
+    },
+    {
+	"MetricExpr": "VFP_SPEC / (duration_time *1000000000)",
+	"BriefDescription": "Giga-floating point operations per second",
+	"MetricGroup": "Instruction",
+	"MetricName": "GFLOPS_ISSUED"
+    },
+    {
+	"MetricExpr": "DP_SPEC / OP_SPEC",
+	"BriefDescription": "Proportion of integer data processing operations",
+	"MetricGroup": "Instruction",
+	"MetricName": "Integer mix"
+    },
+    {
+	"MetricExpr": "INST_RETIRED / CPU_CYCLES",
+	"BriefDescription": "Instructions per cycle",
+	"MetricGroup": "Instruction",
+	"MetricName": "IPC"
+    },
+    {
+	"MetricExpr": "LD_SPEC / OP_SPEC",
+	"BriefDescription": "Proportion of load operations",
+	"MetricGroup": "Instruction",
+	"MetricName": "Load mix"
+    },
+    {
+	"MetricExpr": "LDST_SPEC/ OP_SPEC",
+	"BriefDescription": "Proportion of load & store operations",
+	"MetricGroup": "Instruction",
+	"MetricName": "Load-store mix"
+    },
+    {
+	"MetricExpr": "INST_RETIRED / (duration_time * 1000000)",
+	"BriefDescription": "Millions of instructions per second",
+	"MetricGroup": "Instruction",
+	"MetricName": "MIPS_RETIRED"
+    },
+    {
+	"MetricExpr": "INST_SPEC / (duration_time * 1000000)",
+	"BriefDescription": "Millions of instructions per second",
+	"MetricGroup": "Instruction",
+	"MetricName": "MIPS_UTILIZATION"
+    },
+    {
+	"MetricExpr": "PC_WRITE_SPEC / OP_SPEC",
+	"BriefDescription": "Proportion of software change of PC operations",
+	"MetricGroup": "Instruction",
+	"MetricName": "PC write mix"
+    },
+    {
+	"MetricExpr": "ST_SPEC / OP_SPEC",
+	"BriefDescription": "Proportion of store operations",
+	"MetricGroup": "Instruction",
+	"MetricName": "Store mix"
+    },
+    {
+	"MetricExpr": "VFP_SPEC / OP_SPEC",
+	"BriefDescription": "Proportion of FP operations",
+	"MetricGroup": "Instruction",
+	"MetricName": "VFP mix"
+    },
+    {
+	"MetricExpr": "1 - (OP_RETIRED/ (CPU_CYCLES * 4))",
+	"BriefDescription": "Proportion of slots lost",
+	"MetricGroup": "Speculation / TDA",
+	"MetricName": "CPU lost"
+    },
+    {
+	"MetricExpr": "OP_RETIRED/ (CPU_CYCLES * 4)",
+	"BriefDescription": "Proportion of slots retiring",
+	"MetricGroup": "Speculation / TDA",
+	"MetricName": "CPU utilization"
+    },
+    {
+	"MetricExpr": "OP_RETIRED - OP_SPEC",
+	"BriefDescription": "Operations lost due to misspeculation",
+	"MetricGroup": "Speculation / TDA",
+	"MetricName": "Operations lost"
+    },
+    {
+	"MetricExpr": "1 - (OP_RETIRED / OP_SPEC)",
+	"BriefDescription": "Proportion of operations lost",
+	"MetricGroup": "Speculation / TDA",
+	"MetricName": "Operations lost (ratio)"
+    },
+    {
+	"MetricExpr": "OP_RETIRED / OP_SPEC",
+	"BriefDescription": "Proportion of operations retired",
+	"MetricGroup": "Speculation / TDA",
+	"MetricName": "Operations retired"
+    },
+    {
+	"MetricExpr": "STALL_BACKEND_CACHE / CPU_CYCLES",
+	"BriefDescription": "Proportion of cycles stalled and no operations issued to backend and cache miss",
+	"MetricGroup": "Stall",
+	"MetricName": "Stall backend cache cycles"
+    },
+    {
+	"MetricExpr": "STALL_BACKEND_RESOURCE / CPU_CYCLES",
+	"BriefDescription": "Proportion of cycles stalled and no operations issued to backend and resource full",
+	"MetricGroup": "Stall",
+	"MetricName": "Stall backend resource cycles"
+    },
+    {
+	"MetricExpr": "STALL_BACKEND_TLB / CPU_CYCLES",
+	"BriefDescription": "Proportion of cycles stalled and no operations issued to backend and TLB miss",
+	"MetricGroup": "Stall",
+	"MetricName": "Stall backend tlb cycles"
+    },
+    {
+	"MetricExpr": "STALL_FRONTEND_CACHE / CPU_CYCLES",
+	"BriefDescription": "Proportion of cycles stalled and no ops delivered from frontend and cache miss",
+	"MetricGroup": "Stall",
+	"MetricName": "Stall frontend cache cycles"
+    },
+    {
+	"MetricExpr": "STALL_FRONTEND_TLB / CPU_CYCLES",
+	"BriefDescription": "Proportion of cycles stalled and no ops delivered from frontend and TLB miss",
+	"MetricGroup": "Stall",
+	"MetricName": "Stall frontend tlb cycles"
+    },
+    {
+	"MetricExpr": "DTLB_WALK / L1D_TLB",
+	"BriefDescription": "D-side walk per d-side translation request",
+	"MetricGroup": "TLB",
+	"MetricName": "DTLB walks"
+    },
+    {
+	"MetricExpr": "ITLB_WALK / L1I_TLB",
+	"BriefDescription": "I-side walk per i-side translation request",
+	"MetricGroup": "TLB",
+	"MetricName": "ITLB walks"
+    },
+    {
+        "MetricExpr": "STALL_SLOT_BACKEND / (CPU_CYCLES * 4)",
+        "BriefDescription": "Fraction of slots backend bound",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "backend"
+    },
+    {
+        "MetricExpr": "1 - (retiring + lost + backend)",
+        "BriefDescription": "Fraction of slots frontend bound",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "frontend"
+    },
+    {
+        "MetricExpr": "((OP_SPEC - OP_RETIRED) / (CPU_CYCLES * 4))",
+        "BriefDescription": "Fraction of slots lost due to misspeculation",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "lost"
+    },
+    {
+        "MetricExpr": "(OP_RETIRED / (CPU_CYCLES * 4))",
+        "BriefDescription": "Fraction of slots retiring, useful work",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "retiring"
+    },
+    {
+        "MetricExpr": "backend - backend_memory",
+        "BriefDescription": "Fraction of slots the CPU was stalled due to backend non-memory subsystem issues",
+        "MetricGroup": "TopDownL2",
+        "MetricName": "backend_core"
+    },
+    {
+        "MetricExpr": "(STALL_BACKEND_TLB + STALL_BACKEND_CACHE + STALL_BACKEND_MEM) / CPU_CYCLES ",
+        "BriefDescription": "Fraction of slots the CPU was stalled due to backend memory subsystem issues (cache/tlb miss)",
+        "MetricGroup": "TopDownL2",
+        "MetricName": "backend_memory"
+    },
+    {
+        "MetricExpr": " (BR_MIS_PRED_RETIRED / GPC_FLUSH) * lost",
+        "BriefDescription": "Fraction of slots lost due to branch misprediciton",
+        "MetricGroup": "TopDownL2",
+        "MetricName": "branch_mispredict"
+    },
+    {
+        "MetricExpr": "frontend - frontend_latency",
+        "BriefDescription": "Fraction of slots the CPU did not dispatch at full bandwidth - able to dispatch partial slots only (1, 2, or 3 uops)",
+        "MetricGroup": "TopDownL2",
+        "MetricName": "frontend_bandwidth"
+    },
+    {
+        "MetricExpr": "(STALL_FRONTEND - ((STALL_SLOT_FRONTEND - (frontend * CPU_CYCLES * 4)) / 4)) / CPU_CYCLES",
+        "BriefDescription": "Fraction of slots the CPU was stalled due to frontend latency issues (cache/tlb miss); nothing to dispatch",
+        "MetricGroup": "TopDownL2",
+        "MetricName": "frontend_latency"
+    },
+    {
+        "MetricExpr": "lost - branch_mispredict",
+        "BriefDescription": "Fraction of slots lost due to other/non-branch misprediction misspeculation",
+        "MetricGroup": "TopDownL2",
+        "MetricName": "other_clears"
+    },
+    {
+        "MetricExpr": "(IXU_NUM_UOPS_ISSUED + FSU_ISSUED) / (CPU_CYCLES * 6)",
+        "BriefDescription": "Fraction of execute slots utilized",
+        "MetricGroup": "TopDownL2",
+        "MetricName": "pipe_utilization"
+    },
+    {
+        "MetricExpr": "STALL_BACKEND_MEM / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled due to data L2 cache miss",
+        "MetricGroup": "TopDownL3",
+        "MetricName": "d_cache_l2_miss"
+    },
+    {
+        "MetricExpr": "STALL_BACKEND_CACHE / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled due to data cache miss",
+        "MetricGroup": "TopDownL3",
+        "MetricName": "d_cache_miss"
+    },
+    {
+        "MetricExpr": "STALL_BACKEND_TLB / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled due to data TLB miss",
+        "MetricGroup": "TopDownL3",
+        "MetricName": "d_tlb_miss"
+    },
+    {
+        "MetricExpr": "FSU_ISSUED / (CPU_CYCLES * 2)",
+        "BriefDescription": "Fraction of FSU execute slots utilized",
+        "MetricGroup": "TopDownL3",
+        "MetricName": "fsu_pipe_utilization"
+    },
+    {
+        "MetricExpr": "STALL_FRONTEND_CACHE / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled due to instruction cache miss",
+        "MetricGroup": "TopDownL3",
+        "MetricName": "i_cache_miss"
+    },
+    {
+        "MetricExpr": " STALL_FRONTEND_TLB / CPU_CYCLES ",
+        "BriefDescription": "Fraction of cycles the CPU was stalled due to instruction TLB miss",
+        "MetricGroup": "TopDownL3",
+        "MetricName": "i_tlb_miss"
+    },
+    {
+        "MetricExpr": "IXU_NUM_UOPS_ISSUED / (CPU_CYCLES / 4)",
+        "BriefDescription": "Fraction of IXU execute slots utilized",
+        "MetricGroup": "TopDownL3",
+        "MetricName": "ixu_pipe_utilization"
+    },
+    {
+        "MetricExpr": "IDR_STALL_FLUSH / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled due to flush recovery",
+        "MetricGroup": "TopDownL3",
+        "MetricName": "recovery"
+    },
+    {
+        "MetricExpr": "STALL_BACKEND_RESOURCE / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled due to core resource shortage",
+        "MetricGroup": "TopDownL3",
+        "MetricName": "resource"
+    },
+    {
+        "MetricExpr": "IDR_STALL_FSU_SCHED / CPU_CYCLES ",
+        "BriefDescription": "Fraction of cycles the CPU was stalled and FSU was full",
+        "MetricGroup": "TopDownL4",
+        "MetricName": "stall_fsu_sched"
+    },
+    {
+        "MetricExpr": "IDR_STALL_IXU_SCHED / CPU_CYCLES ",
+        "BriefDescription": "Fraction of cycles the CPU was stalled and IXU was full",
+        "MetricGroup": "TopDownL4",
+        "MetricName": "stall_ixu_sched"
+    },
+    {
+        "MetricExpr": "IDR_STALL_LOB_ID / CPU_CYCLES ",
+        "BriefDescription": "Fraction of cycles the CPU was stalled and LOB was full",
+        "MetricGroup": "TopDownL4",
+        "MetricName": "stall_lob_id"
+    },
+    {
+        "MetricExpr": "IDR_STALL_ROB_ID / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled and ROB was full",
+        "MetricGroup": "TopDownL4",
+        "MetricName": "stall_rob_id"
+    },
+    {
+        "MetricExpr": "IDR_STALL_SOB_ID / CPU_CYCLES ",
+        "BriefDescription": "Fraction of cycles the CPU was stalled and SOB was full",
+        "MetricGroup": "TopDownL4",
+        "MetricName": "stall_sob_id"
+    }
+]

From a50b8db3ea358b01f3c83e1e1c063e75352dcb3b Mon Sep 17 00:00:00 2001
From: Ilkka Koskinen <ilkka@os.amperecomputing.com>
Date: Thu, 3 Aug 2023 14:13:31 -0700
Subject: [PATCH 0569/1189] perf vendor events arm64: AmpereOne: Remove
 unsupported events

Some of the events included in the ampereone/core-imp-def are not
supported on AmpereOne, remove them.

Signed-off-by: Ilkka Koskinen <ilkka@os.amperecomputing.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Dave Kleikamp <dave.kleikamp@oracle.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20230803211331.140553-5-ilkka@os.amperecomputing.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../arm64/ampere/ampereone/core-imp-def.json  | 120 ------------------
 1 file changed, 120 deletions(-)

diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/core-imp-def.json
index 95c30243f2b2..88b23b85e33c 100644
--- a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/core-imp-def.json
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/core-imp-def.json
@@ -533,66 +533,6 @@
         "EventName": "MMU_D_OTB_ALLOC",
         "BriefDescription": "L2D OTB allocate"
     },
-    {
-        "PublicDescription": "DTLB Translation cache hit on S1L2 walk cache entry",
-        "EventCode": "0xD801",
-        "EventName": "MMU_D_TRANS_CACHE_HIT_S1L2_WALK",
-        "BriefDescription": "DTLB Translation cache hit on S1L2 walk cache entry"
-    },
-    {
-        "PublicDescription": "DTLB Translation cache hit on S1L1 walk cache entry",
-        "EventCode": "0xD802",
-        "EventName": "MMU_D_TRANS_CACHE_HIT_S1L1_WALK",
-        "BriefDescription": "DTLB Translation cache hit on S1L1 walk cache entry"
-    },
-    {
-        "PublicDescription": "DTLB Translation cache hit on S1L0 walk cache entry",
-        "EventCode": "0xD803",
-        "EventName": "MMU_D_TRANS_CACHE_HIT_S1L0_WALK",
-        "BriefDescription": "DTLB Translation cache hit on S1L0 walk cache entry"
-    },
-    {
-        "PublicDescription": "DTLB Translation cache hit on S2L2 walk cache entry",
-        "EventCode": "0xD804",
-        "EventName": "MMU_D_TRANS_CACHE_HIT_S2L2_WALK",
-        "BriefDescription": "DTLB Translation cache hit on S2L2 walk cache entry"
-    },
-    {
-        "PublicDescription": "DTLB Translation cache hit on S2L1 walk cache entry",
-        "EventCode": "0xD805",
-        "EventName": "MMU_D_TRANS_CACHE_HIT_S2L1_WALK",
-        "BriefDescription": "DTLB Translation cache hit on S2L1 walk cache entry"
-    },
-    {
-        "PublicDescription": "DTLB Translation cache hit on S2L0 walk cache entry",
-        "EventCode": "0xD806",
-        "EventName": "MMU_D_TRANS_CACHE_HIT_S2L0_WALK",
-        "BriefDescription": "DTLB Translation cache hit on S2L0 walk cache entry"
-    },
-    {
-        "PublicDescription": "D-side S1 Page walk cache lookup",
-        "EventCode": "0xD807",
-        "EventName": "MMU_D_S1_WALK_CACHE_LOOKUP",
-        "BriefDescription": "D-side S1 Page walk cache lookup"
-    },
-    {
-        "PublicDescription": "D-side S1 Page walk cache refill",
-        "EventCode": "0xD808",
-        "EventName": "MMU_D_S1_WALK_CACHE_REFILL",
-        "BriefDescription": "D-side S1 Page walk cache refill"
-    },
-    {
-        "PublicDescription": "D-side S2 Page walk cache lookup",
-        "EventCode": "0xD809",
-        "EventName": "MMU_D_S2_WALK_CACHE_LOOKUP",
-        "BriefDescription": "D-side S2 Page walk cache lookup"
-    },
-    {
-        "PublicDescription": "D-side S2 Page walk cache refill",
-        "EventCode": "0xD80A",
-        "EventName": "MMU_D_S2_WALK_CACHE_REFILL",
-        "BriefDescription": "D-side S2 Page walk cache refill"
-    },
     {
         "PublicDescription": "D-side Stage1 tablewalk fault",
         "EventCode": "0xD80B",
@@ -617,66 +557,6 @@
         "EventName": "MMU_I_OTB_ALLOC",
         "BriefDescription": "L2I OTB allocate"
     },
-    {
-        "PublicDescription": "ITLB Translation cache hit on S1L2 walk cache entry",
-        "EventCode": "0xD901",
-        "EventName": "MMU_I_TRANS_CACHE_HIT_S1L2_WALK",
-        "BriefDescription": "ITLB Translation cache hit on S1L2 walk cache entry"
-    },
-    {
-        "PublicDescription": "ITLB Translation cache hit on S1L1 walk cache entry",
-        "EventCode": "0xD902",
-        "EventName": "MMU_I_TRANS_CACHE_HIT_S1L1_WALK",
-        "BriefDescription": "ITLB Translation cache hit on S1L1 walk cache entry"
-    },
-    {
-        "PublicDescription": "ITLB Translation cache hit on S1L0 walk cache entry",
-        "EventCode": "0xD903",
-        "EventName": "MMU_I_TRANS_CACHE_HIT_S1L0_WALK",
-        "BriefDescription": "ITLB Translation cache hit on S1L0 walk cache entry"
-    },
-    {
-        "PublicDescription": "ITLB Translation cache hit on S2L2 walk cache entry",
-        "EventCode": "0xD904",
-        "EventName": "MMU_I_TRANS_CACHE_HIT_S2L2_WALK",
-        "BriefDescription": "ITLB Translation cache hit on S2L2 walk cache entry"
-    },
-    {
-        "PublicDescription": "ITLB Translation cache hit on S2L1 walk cache entry",
-        "EventCode": "0xD905",
-        "EventName": "MMU_I_TRANS_CACHE_HIT_S2L1_WALK",
-        "BriefDescription": "ITLB Translation cache hit on S2L1 walk cache entry"
-    },
-    {
-        "PublicDescription": "ITLB Translation cache hit on S2L0 walk cache entry",
-        "EventCode": "0xD906",
-        "EventName": "MMU_I_TRANS_CACHE_HIT_S2L0_WALK",
-        "BriefDescription": "ITLB Translation cache hit on S2L0 walk cache entry"
-    },
-    {
-        "PublicDescription": "I-side S1 Page walk cache lookup",
-        "EventCode": "0xD907",
-        "EventName": "MMU_I_S1_WALK_CACHE_LOOKUP",
-        "BriefDescription": "I-side S1 Page walk cache lookup"
-    },
-    {
-        "PublicDescription": "I-side S1 Page walk cache refill",
-        "EventCode": "0xD908",
-        "EventName": "MMU_I_S1_WALK_CACHE_REFILL",
-        "BriefDescription": "I-side S1 Page walk cache refill"
-    },
-    {
-        "PublicDescription": "I-side S2 Page walk cache lookup",
-        "EventCode": "0xD909",
-        "EventName": "MMU_I_S2_WALK_CACHE_LOOKUP",
-        "BriefDescription": "I-side S2 Page walk cache lookup"
-    },
-    {
-        "PublicDescription": "I-side S2 Page walk cache refill",
-        "EventCode": "0xD90A",
-        "EventName": "MMU_I_S2_WALK_CACHE_REFILL",
-        "BriefDescription": "I-side S2 Page walk cache refill"
-    },
     {
         "PublicDescription": "I-side Stage1 tablewalk fault",
         "EventCode": "0xD90B",

From 262b54b6c9396823ab06df46a1be475c44b28b5f Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 21 Aug 2023 10:40:09 -0300
Subject: [PATCH 0570/1189] perf bpf augmented_raw_syscalls: Add an assert to
 make sure sizeof(saddr) is a power of two.

We're using the BPF verifier suggestion:

    22: (85) call bpf_probe_read#4
    R2 min value is negative, either use unsigned or 'var &= const'

That works only when const is a (power of two - 1) so add an assert to
make sure that that is the case.

Suggested-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/ZONrFmJBNlQpSpZj@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
index 9c1d0b271b20..43549b63b433 100644
--- a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
+++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
@@ -10,6 +10,16 @@
 #include <bpf/bpf_helpers.h>
 #include <linux/limits.h>
 
+/**
+ * is_power_of_2() - check if a value is a power of two
+ * @n: the value to check
+ *
+ * Determine whether some value is a power of two, where zero is *not*
+ * considered a power of two.  Return: true if @n is a power of 2, otherwise
+ * false.
+ */
+#define is_power_of_2(n) (n != 0 && ((n & (n - 1)) == 0))
+
 #define MAX_CPUS  4096
 
 // FIXME: These should come from system headers
@@ -187,6 +197,7 @@ int sys_enter_connect(struct syscall_enter_args *args)
         if (augmented_args == NULL)
                 return 1; /* Failure: don't filter */
 
+	_Static_assert(is_power_of_2(sizeof(augmented_args->saddr)), "sizeof(augmented_args->saddr) needs to be a power of two");
 	socklen &= sizeof(augmented_args->saddr) - 1;
 
 	bpf_probe_read(&augmented_args->saddr, socklen, sockaddr_arg);

From 7d9642311b6d9d319a6948581244561d2a0890a1 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 21 Aug 2023 10:40:09 -0300
Subject: [PATCH 0571/1189] perf bpf augmented_raw_syscalls: Add an assert to
 make sure sizeof(augmented_arg->value) is a power of two.

Similar to what was done in the previous cset for sizeof(saddr), we need
to make sure sizeof(augmented_arg->value) is a power of two to do bounds
checking using &=:

  augmented_len &= sizeof(augmented_arg->value) - 1;

Suggested-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/ZONrPo0NSqdbXiGx@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
index 43549b63b433..90ce22f9c1a9 100644
--- a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
+++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
@@ -160,6 +160,7 @@ unsigned int augmented_arg__read_str(struct augmented_arg *augmented_arg, const
 	 */
 	if (string_len > 0) {
 		augmented_len -= sizeof(augmented_arg->value) - string_len;
+		_Static_assert(is_power_of_2(sizeof(augmented_arg->value)), "sizeof(augmented_arg->value) needs to be a power of two");
 		augmented_len &= sizeof(augmented_arg->value) - 1;
 		augmented_arg->size = string_len;
 	} else {

From 58a8d2edd57b35307d81ec6c304697707e6067c1 Mon Sep 17 00:00:00 2001
From: Kaige Ye <ye@kaige.org>
Date: Fri, 4 Aug 2023 10:09:08 +0800
Subject: [PATCH 0572/1189] perf stat-display: Check if snprintf()'s fmt
 argument is NULL

It is undefined behavior to pass NULL as snprintf()'s fmt argument.
Here is an example to trigger the problem:

  $ perf stat --metric-only -x, -e instructions -- sleep 1
  insn per cycle,
  Segmentation fault (core dumped)

With this patch:

  $ perf stat --metric-only -x, -e instructions -- sleep 1
  insn per cycle,
  ,

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Kaige Ye <ye@kaige.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/01CA7674B690CA24+20230804020907.144562-2-ye@kaige.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/stat-display.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index d45d5dcb0e2b..afe6db8e7bf4 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -578,7 +578,7 @@ static void print_metric_only_csv(struct perf_stat_config *config __maybe_unused
 	if (!valid_only_metric(unit))
 		return;
 	unit = fixunit(tbuf, os->evsel, unit);
-	snprintf(buf, sizeof buf, fmt, val);
+	snprintf(buf, sizeof(buf), fmt ?: "", val);
 	ends = vals = skip_spaces(buf);
 	while (isdigit(*ends) || *ends == '.')
 		ends++;
@@ -600,7 +600,7 @@ static void print_metric_only_json(struct perf_stat_config *config __maybe_unuse
 	if (!valid_only_metric(unit))
 		return;
 	unit = fixunit(tbuf, os->evsel, unit);
-	snprintf(buf, sizeof(buf), fmt, val);
+	snprintf(buf, sizeof(buf), fmt ?: "", val);
 	ends = vals = skip_spaces(buf);
 	while (isdigit(*ends) || *ends == '.')
 		ends++;

From efeda3bf912f269bcae16816683f432f58d68075 Mon Sep 17 00:00:00 2001
From: Quinn Tran <qutran@marvell.com>
Date: Thu, 17 Aug 2023 12:01:31 +0530
Subject: [PATCH 0573/1189] scsi: qla2xxx: Move resource to allow code reuse

dsd_list contains a list of dsd buffer resources allocated during traffic
time. It resides in the qla_hw_data location where some of the code is not
reusable.

Move this list to qpair to allow reuse by either single queue or multi
queue adapter / code.

Signed-off-by: Quinn Tran <qutran@marvell.com>
Signed-off-by: Nilesh Javali <njavali@marvell.com>
Link: https://lore.kernel.org/r/20230817063132.21900-2-njavali@marvell.com
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_def.h  | 11 ++++++-----
 drivers/scsi/qla2xxx/qla_init.c | 14 ++++++++++++++
 drivers/scsi/qla2xxx/qla_iocb.c | 20 +++++++++----------
 drivers/scsi/qla2xxx/qla_os.c   | 34 ++++++++++++++++-----------------
 4 files changed, 46 insertions(+), 33 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index b3b1df34afd3..97ecb2158c8a 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -3787,6 +3787,12 @@ struct qla_qpair {
 
 	uint16_t id;			/* qp number used with FW */
 	uint16_t vp_idx;		/* vport ID */
+
+	uint16_t dsd_inuse;
+	uint16_t dsd_avail;
+	struct list_head dsd_list;
+#define NUM_DSD_CHAIN 4096
+
 	mempool_t *srb_mempool;
 
 	struct pci_dev  *pdev;
@@ -4715,11 +4721,6 @@ struct qla_hw_data {
 	struct fw_blob	*hablob;
 	struct qla82xx_legacy_intr_set nx_legacy_intr;
 
-	uint16_t	gbl_dsd_inuse;
-	uint16_t	gbl_dsd_avail;
-	struct list_head gbl_dsd_list;
-#define NUM_DSD_CHAIN 4096
-
 	uint8_t fw_type;
 	uint32_t file_prd_off;	/* File firmware product offset */
 
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 059175f2c8f5..53e76bbee915 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -9643,6 +9643,7 @@ struct qla_qpair *qla2xxx_create_qpair(struct scsi_qla_host *vha, int qos,
 		qpair->vp_idx = vp_idx;
 		qpair->fw_started = ha->flags.fw_started;
 		INIT_LIST_HEAD(&qpair->hints_list);
+		INIT_LIST_HEAD(&qpair->dsd_list);
 		qpair->chip_reset = ha->base_qpair->chip_reset;
 		qpair->enable_class_2 = ha->base_qpair->enable_class_2;
 		qpair->enable_explicit_conf =
@@ -9771,6 +9772,19 @@ int qla2xxx_delete_qpair(struct scsi_qla_host *vha, struct qla_qpair *qpair)
 	if (ret != QLA_SUCCESS)
 		goto fail;
 
+	if (!list_empty(&qpair->dsd_list)) {
+		struct dsd_dma *dsd_ptr, *tdsd_ptr;
+
+		/* clean up allocated prev pool */
+		list_for_each_entry_safe(dsd_ptr, tdsd_ptr,
+					 &qpair->dsd_list, list) {
+			dma_pool_free(ha->dl_dma_pool, dsd_ptr->dsd_addr,
+				      dsd_ptr->dsd_list_dma);
+			list_del(&dsd_ptr->list);
+			kfree(dsd_ptr);
+		}
+	}
+
 	mutex_lock(&ha->mq_lock);
 	ha->queue_pair_map[qpair->id] = NULL;
 	clear_bit(qpair->id, ha->qpair_qid_map);
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index 1c6e300ed3ab..fee5174911b8 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -636,14 +636,13 @@ qla24xx_build_scsi_type_6_iocbs(srb_t *sp, struct cmd_type_6 *cmd_pkt,
 		tot_dsds -= avail_dsds;
 		dsd_list_len = (avail_dsds + 1) * QLA_DSD_SIZE;
 
-		dsd_ptr = list_first_entry(&ha->gbl_dsd_list,
-		    struct dsd_dma, list);
+		dsd_ptr = list_first_entry(&qpair->dsd_list, struct dsd_dma, list);
 		next_dsd = dsd_ptr->dsd_addr;
 		list_del(&dsd_ptr->list);
-		ha->gbl_dsd_avail--;
+		qpair->dsd_avail--;
 		list_add_tail(&dsd_ptr->list, &ctx->dsd_list);
 		ctx->dsd_use_cnt++;
-		ha->gbl_dsd_inuse++;
+		qpair->dsd_inuse++;
 
 		if (first_iocb) {
 			first_iocb = 0;
@@ -3367,6 +3366,7 @@ qla82xx_start_scsi(srb_t *sp)
 	struct qla_hw_data *ha = vha->hw;
 	struct req_que *req = NULL;
 	struct rsp_que *rsp = NULL;
+	struct qla_qpair *qpair = sp->qpair;
 
 	/* Setup device pointers. */
 	reg = &ha->iobase->isp82;
@@ -3415,18 +3415,18 @@ qla82xx_start_scsi(srb_t *sp)
 		uint16_t i;
 
 		more_dsd_lists = qla24xx_calc_dsd_lists(tot_dsds);
-		if ((more_dsd_lists + ha->gbl_dsd_inuse) >= NUM_DSD_CHAIN) {
+		if ((more_dsd_lists + qpair->dsd_inuse) >= NUM_DSD_CHAIN) {
 			ql_dbg(ql_dbg_io, vha, 0x300d,
 			    "Num of DSD list %d is than %d for cmd=%p.\n",
-			    more_dsd_lists + ha->gbl_dsd_inuse, NUM_DSD_CHAIN,
+			    more_dsd_lists + qpair->dsd_inuse, NUM_DSD_CHAIN,
 			    cmd);
 			goto queuing_error;
 		}
 
-		if (more_dsd_lists <= ha->gbl_dsd_avail)
+		if (more_dsd_lists <= qpair->dsd_avail)
 			goto sufficient_dsds;
 		else
-			more_dsd_lists -= ha->gbl_dsd_avail;
+			more_dsd_lists -= qpair->dsd_avail;
 
 		for (i = 0; i < more_dsd_lists; i++) {
 			dsd_ptr = kzalloc(sizeof(struct dsd_dma), GFP_ATOMIC);
@@ -3446,8 +3446,8 @@ qla82xx_start_scsi(srb_t *sp)
 				    "for cmd=%p.\n", cmd);
 				goto queuing_error;
 			}
-			list_add_tail(&dsd_ptr->list, &ha->gbl_dsd_list);
-			ha->gbl_dsd_avail++;
+			list_add_tail(&dsd_ptr->list, &qpair->dsd_list);
+			qpair->dsd_avail++;
 		}
 
 sufficient_dsds:
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 03bc3a0b45b6..f31d0ead8919 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -432,6 +432,7 @@ static void qla_init_base_qpair(struct scsi_qla_host *vha, struct req_que *req,
 	ha->base_qpair->msix = &ha->msix_entries[QLA_MSIX_RSP_Q];
 	ha->base_qpair->srb_mempool = ha->srb_mempool;
 	INIT_LIST_HEAD(&ha->base_qpair->hints_list);
+	INIT_LIST_HEAD(&ha->base_qpair->dsd_list);
 	ha->base_qpair->enable_class_2 = ql2xenableclass2;
 	/* init qpair to this cpu. Will adjust at run time. */
 	qla_cpu_update(rsp->qpair, raw_smp_processor_id());
@@ -750,9 +751,9 @@ void qla2x00_sp_free_dma(srb_t *sp)
 
 		dma_pool_free(ha->fcp_cmnd_dma_pool, ctx1->fcp_cmnd,
 		    ctx1->fcp_cmnd_dma);
-		list_splice(&ctx1->dsd_list, &ha->gbl_dsd_list);
-		ha->gbl_dsd_inuse -= ctx1->dsd_use_cnt;
-		ha->gbl_dsd_avail += ctx1->dsd_use_cnt;
+		list_splice(&ctx1->dsd_list, &sp->qpair->dsd_list);
+		sp->qpair->dsd_inuse -= ctx1->dsd_use_cnt;
+		sp->qpair->dsd_avail += ctx1->dsd_use_cnt;
 	}
 
 	if (sp->flags & SRB_GOT_BUF)
@@ -836,9 +837,9 @@ void qla2xxx_qpair_sp_free_dma(srb_t *sp)
 
 		dma_pool_free(ha->fcp_cmnd_dma_pool, ctx1->fcp_cmnd,
 		    ctx1->fcp_cmnd_dma);
-		list_splice(&ctx1->dsd_list, &ha->gbl_dsd_list);
-		ha->gbl_dsd_inuse -= ctx1->dsd_use_cnt;
-		ha->gbl_dsd_avail += ctx1->dsd_use_cnt;
+		list_splice(&ctx1->dsd_list, &sp->qpair->dsd_list);
+		sp->qpair->dsd_inuse -= ctx1->dsd_use_cnt;
+		sp->qpair->dsd_avail += ctx1->dsd_use_cnt;
 		sp->flags &= ~SRB_FCP_CMND_DMA_VALID;
 	}
 
@@ -4402,7 +4403,6 @@ qla2x00_mem_alloc(struct qla_hw_data *ha, uint16_t req_len, uint16_t rsp_len,
 			   "sf_init_cb=%p.\n", ha->sf_init_cb);
 	}
 
-	INIT_LIST_HEAD(&ha->gbl_dsd_list);
 
 	/* Get consistent memory allocated for Async Port-Database. */
 	if (!IS_FWI2_CAPABLE(ha)) {
@@ -4934,18 +4934,16 @@ qla2x00_mem_free(struct qla_hw_data *ha)
 	ha->gid_list = NULL;
 	ha->gid_list_dma = 0;
 
-	if (IS_QLA82XX(ha)) {
-		if (!list_empty(&ha->gbl_dsd_list)) {
-			struct dsd_dma *dsd_ptr, *tdsd_ptr;
+	if (!list_empty(&ha->base_qpair->dsd_list)) {
+		struct dsd_dma *dsd_ptr, *tdsd_ptr;
 
-			/* clean up allocated prev pool */
-			list_for_each_entry_safe(dsd_ptr,
-				tdsd_ptr, &ha->gbl_dsd_list, list) {
-				dma_pool_free(ha->dl_dma_pool,
-				dsd_ptr->dsd_addr, dsd_ptr->dsd_list_dma);
-				list_del(&dsd_ptr->list);
-				kfree(dsd_ptr);
-			}
+		/* clean up allocated prev pool */
+		list_for_each_entry_safe(dsd_ptr, tdsd_ptr,
+					 &ha->base_qpair->dsd_list, list) {
+			dma_pool_free(ha->dl_dma_pool, dsd_ptr->dsd_addr,
+				      dsd_ptr->dsd_list_dma);
+			list_del(&dsd_ptr->list);
+			kfree(dsd_ptr);
 		}
 	}
 

From ae25f65a351ca9c650887c2b37319fa9a41ec258 Mon Sep 17 00:00:00 2001
From: Quinn Tran <qutran@marvell.com>
Date: Thu, 17 Aug 2023 12:01:32 +0530
Subject: [PATCH 0574/1189] scsi: qla2xxx: Allow 32-byte CDBs

System crashes when a 32-byte CDB was sent to a non T10 PI disk:

[  177.143279]  ? qla2xxx_dif_start_scsi_mq+0xcd8/0xce0 [qla2xxx]
[  177.149165]  ? internal_add_timer+0x42/0x70
[  177.153372]  qla2xxx_mqueuecommand+0x207/0x2b0 [qla2xxx]
[  177.158730]  scsi_queue_rq+0x2b7/0xc00
[  177.162501]  blk_mq_dispatch_rq_list+0x3ea/0x7e0

Current code attempted to use CRC IOCB to send the command but failed.
Instead, type 6 IOCB should be used to send the I/O.

Clone existing type 6 IOCB code with addition of MQ support to allow
32-byte CDBs to go through.

Signed-off-by: Quinn Tran <qutran@marvell.com>
Cc: Laurence Oberman <loberman@redhat.com>
Signed-off-by: Nilesh Javali <njavali@marvell.com>
Link: https://lore.kernel.org/r/20230817063132.21900-3-njavali@marvell.com
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_iocb.c | 269 ++++++++++++++++++++++++++++++++
 drivers/scsi/qla2xxx/qla_nx.h   |   4 +-
 2 files changed, 272 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index fee5174911b8..d0b12c746a8a 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -11,6 +11,7 @@
 
 #include <scsi/scsi_tcq.h>
 
+static int qla_start_scsi_type6(srb_t *sp);
 /**
  * qla2x00_get_cmd_direction() - Determine control_flag data direction.
  * @sp: SCSI command
@@ -1721,6 +1722,8 @@ qla24xx_dif_start_scsi(srb_t *sp)
 	if (scsi_get_prot_op(cmd) == SCSI_PROT_NORMAL) {
 		if (cmd->cmd_len <= 16)
 			return qla24xx_start_scsi(sp);
+		else
+			return qla_start_scsi_type6(sp);
 	}
 
 	/* Setup device pointers. */
@@ -2100,6 +2103,8 @@ qla2xxx_dif_start_scsi_mq(srb_t *sp)
 	if (scsi_get_prot_op(cmd) == SCSI_PROT_NORMAL) {
 		if (cmd->cmd_len <= 16)
 			return qla2xxx_start_scsi_mq(sp);
+		else
+			return qla_start_scsi_type6(sp);
 	}
 
 	spin_lock_irqsave(&qpair->qp_lock, flags);
@@ -4197,3 +4202,267 @@ queuing_error:
 
 	return rval;
 }
+
+/**
+ * qla_start_scsi_type6() - Send a SCSI command to the ISP
+ * @sp: command to send to the ISP
+ *
+ * Returns non-zero if a failure occurred, else zero.
+ */
+static int
+qla_start_scsi_type6(srb_t *sp)
+{
+	int		nseg;
+	unsigned long   flags;
+	uint32_t	*clr_ptr;
+	uint32_t	handle;
+	struct cmd_type_6 *cmd_pkt;
+	uint16_t	cnt;
+	uint16_t	req_cnt;
+	uint16_t	tot_dsds;
+	struct req_que *req = NULL;
+	struct rsp_que *rsp;
+	struct scsi_cmnd *cmd = GET_CMD_SP(sp);
+	struct scsi_qla_host *vha = sp->fcport->vha;
+	struct qla_hw_data *ha = vha->hw;
+	struct qla_qpair *qpair = sp->qpair;
+	uint16_t more_dsd_lists = 0;
+	struct dsd_dma *dsd_ptr;
+	uint16_t i;
+	__be32 *fcp_dl;
+	uint8_t additional_cdb_len;
+	struct ct6_dsd *ctx;
+
+	/* Acquire qpair specific lock */
+	spin_lock_irqsave(&qpair->qp_lock, flags);
+
+	/* Setup qpair pointers */
+	req = qpair->req;
+	rsp = qpair->rsp;
+
+	/* So we know we haven't pci_map'ed anything yet */
+	tot_dsds = 0;
+
+	/* Send marker if required */
+	if (vha->marker_needed != 0) {
+		if (__qla2x00_marker(vha, qpair, 0, 0, MK_SYNC_ALL) != QLA_SUCCESS) {
+			spin_unlock_irqrestore(&qpair->qp_lock, flags);
+			return QLA_FUNCTION_FAILED;
+		}
+		vha->marker_needed = 0;
+	}
+
+	handle = qla2xxx_get_next_handle(req);
+	if (handle == 0)
+		goto queuing_error;
+
+	/* Map the sg table so we have an accurate count of sg entries needed */
+	if (scsi_sg_count(cmd)) {
+		nseg = dma_map_sg(&ha->pdev->dev, scsi_sglist(cmd),
+				  scsi_sg_count(cmd), cmd->sc_data_direction);
+		if (unlikely(!nseg))
+			goto queuing_error;
+	} else {
+		nseg = 0;
+	}
+
+	tot_dsds = nseg;
+
+	/* eventhough driver only need 1 T6 IOCB, FW still convert DSD to Continueation IOCB */
+	req_cnt = qla24xx_calc_iocbs(vha, tot_dsds);
+
+	sp->iores.res_type = RESOURCE_IOCB | RESOURCE_EXCH;
+	sp->iores.exch_cnt = 1;
+	sp->iores.iocb_cnt = req_cnt;
+
+	if (qla_get_fw_resources(sp->qpair, &sp->iores))
+		goto queuing_error;
+
+	more_dsd_lists = qla24xx_calc_dsd_lists(tot_dsds);
+	if ((more_dsd_lists + qpair->dsd_inuse) >= NUM_DSD_CHAIN) {
+		ql_dbg(ql_dbg_io, vha, 0x3028,
+		       "Num of DSD list %d is than %d for cmd=%p.\n",
+		       more_dsd_lists + qpair->dsd_inuse, NUM_DSD_CHAIN, cmd);
+		goto queuing_error;
+	}
+
+	if (more_dsd_lists <= qpair->dsd_avail)
+		goto sufficient_dsds;
+	else
+		more_dsd_lists -= qpair->dsd_avail;
+
+	for (i = 0; i < more_dsd_lists; i++) {
+		dsd_ptr = kzalloc(sizeof(*dsd_ptr), GFP_ATOMIC);
+		if (!dsd_ptr) {
+			ql_log(ql_log_fatal, vha, 0x3029,
+			    "Failed to allocate memory for dsd_dma for cmd=%p.\n", cmd);
+			goto queuing_error;
+		}
+		INIT_LIST_HEAD(&dsd_ptr->list);
+
+		dsd_ptr->dsd_addr = dma_pool_alloc(ha->dl_dma_pool,
+			GFP_ATOMIC, &dsd_ptr->dsd_list_dma);
+		if (!dsd_ptr->dsd_addr) {
+			kfree(dsd_ptr);
+			ql_log(ql_log_fatal, vha, 0x302a,
+			    "Failed to allocate memory for dsd_addr for cmd=%p.\n", cmd);
+			goto queuing_error;
+		}
+		list_add_tail(&dsd_ptr->list, &qpair->dsd_list);
+		qpair->dsd_avail++;
+	}
+
+sufficient_dsds:
+	req_cnt = 1;
+
+	if (req->cnt < (req_cnt + 2)) {
+		if (IS_SHADOW_REG_CAPABLE(ha)) {
+			cnt = *req->out_ptr;
+		} else {
+			cnt = (uint16_t)rd_reg_dword_relaxed(req->req_q_out);
+			if (qla2x00_check_reg16_for_disconnect(vha, cnt))
+				goto queuing_error;
+		}
+
+		if (req->ring_index < cnt)
+			req->cnt = cnt - req->ring_index;
+		else
+			req->cnt = req->length - (req->ring_index - cnt);
+		if (req->cnt < (req_cnt + 2))
+			goto queuing_error;
+	}
+
+	ctx = &sp->u.scmd.ct6_ctx;
+
+	memset(ctx, 0, sizeof(struct ct6_dsd));
+	ctx->fcp_cmnd = dma_pool_zalloc(ha->fcp_cmnd_dma_pool,
+		GFP_ATOMIC, &ctx->fcp_cmnd_dma);
+	if (!ctx->fcp_cmnd) {
+		ql_log(ql_log_fatal, vha, 0x3031,
+		    "Failed to allocate fcp_cmnd for cmd=%p.\n", cmd);
+		goto queuing_error;
+	}
+
+	/* Initialize the DSD list and dma handle */
+	INIT_LIST_HEAD(&ctx->dsd_list);
+	ctx->dsd_use_cnt = 0;
+
+	if (cmd->cmd_len > 16) {
+		additional_cdb_len = cmd->cmd_len - 16;
+		if (cmd->cmd_len % 4 ||
+		    cmd->cmd_len > QLA_CDB_BUF_SIZE) {
+			/*
+			 * SCSI command bigger than 16 bytes must be
+			 * multiple of 4 or too big.
+			 */
+			ql_log(ql_log_warn, vha, 0x3033,
+			    "scsi cmd len %d not multiple of 4 for cmd=%p.\n",
+			    cmd->cmd_len, cmd);
+			goto queuing_error_fcp_cmnd;
+		}
+		ctx->fcp_cmnd_len = 12 + cmd->cmd_len + 4;
+	} else {
+		additional_cdb_len = 0;
+		ctx->fcp_cmnd_len = 12 + 16 + 4;
+	}
+
+	/* Build command packet. */
+	req->current_outstanding_cmd = handle;
+	req->outstanding_cmds[handle] = sp;
+	sp->handle = handle;
+	cmd->host_scribble = (unsigned char *)(unsigned long)handle;
+	req->cnt -= req_cnt;
+
+	cmd_pkt = (struct cmd_type_6 *)req->ring_ptr;
+	cmd_pkt->handle = make_handle(req->id, handle);
+
+	/* tagged queuing modifier -- default is TSK_SIMPLE (0). */
+	clr_ptr = (uint32_t *)cmd_pkt + 2;
+	memset(clr_ptr, 0, REQUEST_ENTRY_SIZE - 8);
+	cmd_pkt->dseg_count = cpu_to_le16(tot_dsds);
+
+	/* Set NPORT-ID and LUN number */
+	cmd_pkt->nport_handle = cpu_to_le16(sp->fcport->loop_id);
+	cmd_pkt->port_id[0] = sp->fcport->d_id.b.al_pa;
+	cmd_pkt->port_id[1] = sp->fcport->d_id.b.area;
+	cmd_pkt->port_id[2] = sp->fcport->d_id.b.domain;
+	cmd_pkt->vp_index = sp->vha->vp_idx;
+
+	/* Build IOCB segments */
+	qla24xx_build_scsi_type_6_iocbs(sp, cmd_pkt, tot_dsds);
+
+	int_to_scsilun(cmd->device->lun, &cmd_pkt->lun);
+	host_to_fcp_swap((uint8_t *)&cmd_pkt->lun, sizeof(cmd_pkt->lun));
+
+	/* build FCP_CMND IU */
+	int_to_scsilun(cmd->device->lun, &ctx->fcp_cmnd->lun);
+	ctx->fcp_cmnd->additional_cdb_len = additional_cdb_len;
+
+	if (cmd->sc_data_direction == DMA_TO_DEVICE)
+		ctx->fcp_cmnd->additional_cdb_len |= 1;
+	else if (cmd->sc_data_direction == DMA_FROM_DEVICE)
+		ctx->fcp_cmnd->additional_cdb_len |= 2;
+
+	/* Populate the FCP_PRIO. */
+	if (ha->flags.fcp_prio_enabled)
+		ctx->fcp_cmnd->task_attribute |=
+		    sp->fcport->fcp_prio << 3;
+
+	memcpy(ctx->fcp_cmnd->cdb, cmd->cmnd, cmd->cmd_len);
+
+	fcp_dl = (__be32 *)(ctx->fcp_cmnd->cdb + 16 +
+	    additional_cdb_len);
+	*fcp_dl = htonl((uint32_t)scsi_bufflen(cmd));
+
+	cmd_pkt->fcp_cmnd_dseg_len = cpu_to_le16(ctx->fcp_cmnd_len);
+	put_unaligned_le64(ctx->fcp_cmnd_dma,
+			   &cmd_pkt->fcp_cmnd_dseg_address);
+
+	sp->flags |= SRB_FCP_CMND_DMA_VALID;
+	cmd_pkt->byte_count = cpu_to_le32((uint32_t)scsi_bufflen(cmd));
+	/* Set total data segment count. */
+	cmd_pkt->entry_count = (uint8_t)req_cnt;
+
+	wmb();
+	/* Adjust ring index. */
+	req->ring_index++;
+	if (req->ring_index == req->length) {
+		req->ring_index = 0;
+		req->ring_ptr = req->ring;
+	} else {
+		req->ring_ptr++;
+	}
+
+	sp->qpair->cmd_cnt++;
+	sp->flags |= SRB_DMA_VALID;
+
+	/* Set chip new ring index. */
+	wrt_reg_dword(req->req_q_in, req->ring_index);
+
+	/* Manage unprocessed RIO/ZIO commands in response queue. */
+	if (vha->flags.process_response_queue &&
+	    rsp->ring_ptr->signature != RESPONSE_PROCESSED)
+		qla24xx_process_response_queue(vha, rsp);
+
+	spin_unlock_irqrestore(&qpair->qp_lock, flags);
+
+	return QLA_SUCCESS;
+
+queuing_error_fcp_cmnd:
+	dma_pool_free(ha->fcp_cmnd_dma_pool, ctx->fcp_cmnd, ctx->fcp_cmnd_dma);
+
+queuing_error:
+	if (tot_dsds)
+		scsi_dma_unmap(cmd);
+
+	qla_put_fw_resources(sp->qpair, &sp->iores);
+
+	if (sp->u.scmd.crc_ctx) {
+		mempool_free(sp->u.scmd.crc_ctx, ha->ctx_mempool);
+		sp->u.scmd.crc_ctx = NULL;
+	}
+
+	spin_unlock_irqrestore(&qpair->qp_lock, flags);
+
+	return QLA_FUNCTION_FAILED;
+}
diff --git a/drivers/scsi/qla2xxx/qla_nx.h b/drivers/scsi/qla2xxx/qla_nx.h
index 6dc80c8ddf79..5d1bdc15b75c 100644
--- a/drivers/scsi/qla2xxx/qla_nx.h
+++ b/drivers/scsi/qla2xxx/qla_nx.h
@@ -857,7 +857,9 @@ struct fcp_cmnd {
 	uint8_t task_attribute;
 	uint8_t task_management;
 	uint8_t additional_cdb_len;
-	uint8_t cdb[260]; /* 256 for CDB len and 4 for FCP_DL */
+#define QLA_CDB_BUF_SIZE  256
+#define QLA_FCP_DL_SIZE   4
+	uint8_t cdb[QLA_CDB_BUF_SIZE + QLA_FCP_DL_SIZE]; /* 256 for CDB len and 4 for FCP_DL */
 };
 
 struct dsd_dma {

From 875386b98857822b77ac7f95bdf367b70af5b78c Mon Sep 17 00:00:00 2001
From: Manish Rangankar <mrangankar@marvell.com>
Date: Mon, 21 Aug 2023 18:30:37 +0530
Subject: [PATCH 0575/1189] scsi: qla2xxx: Add Unsolicited LS Request and
 Response Support for NVMe

Introduce infrastructure in the driver to support the processing of
unsolicited LS (Link Service) requests. This will involve the utilization
of a new pass-up of unsolicited FC-NVMe request IOCB interface. Unsolicited
requests will be submitted to the NVMe transport layer through
nvme_fc_rcv_ls_req(). Any received LS responses, which are sent using
xmt_ls_rsp(), will be forwarded to the firmware through the existing
Pass-Through IOCB interface, responsible for sending FC-NVMe Link Service
requests and responses.

Signed-off-by: Manish Rangankar <mrangankar@marvell.com>
Signed-off-by: Nilesh Javali <njavali@marvell.com>
Link: https://lore.kernel.org/r/20230821130045.34850-2-njavali@marvell.com
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_dbg.c  |   5 +-
 drivers/scsi/qla2xxx/qla_dbg.h  |   1 +
 drivers/scsi/qla2xxx/qla_def.h  |  34 ++-
 drivers/scsi/qla2xxx/qla_gbl.h  |  14 +-
 drivers/scsi/qla2xxx/qla_init.c |   1 +
 drivers/scsi/qla2xxx/qla_iocb.c |  29 ++-
 drivers/scsi/qla2xxx/qla_isr.c  | 144 +++++++++++-
 drivers/scsi/qla2xxx/qla_nvme.c | 401 +++++++++++++++++++++++++++++++-
 drivers/scsi/qla2xxx/qla_nvme.h |  17 +-
 drivers/scsi/qla2xxx/qla_os.c   |  24 +-
 include/linux/nvme-fc-driver.h  |   6 +-
 11 files changed, 642 insertions(+), 34 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c
index d7e8454304ce..4d104425146b 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.c
+++ b/drivers/scsi/qla2xxx/qla_dbg.c
@@ -12,9 +12,8 @@
  * ----------------------------------------------------------------------
  * | Module Init and Probe        |       0x0199       |                |
  * | Mailbox commands             |       0x1206       | 0x11a5-0x11ff	|
- * | Device Discovery             |       0x2134       | 0x210e-0x2115  |
- * |                              |                    | 0x211c-0x2128  |
- * |                              |                    | 0x212c-0x2134  |
+ * | Device Discovery             |       0x2134       | 0x2112-0x2115  |
+ * |                              |                    | 0x2127-0x2128  |
  * | Queue Command and IO tracing |       0x3074       | 0x300b         |
  * |                              |                    | 0x3027-0x3028  |
  * |                              |                    | 0x303d-0x3041  |
diff --git a/drivers/scsi/qla2xxx/qla_dbg.h b/drivers/scsi/qla2xxx/qla_dbg.h
index 70482b55d240..54f0a412226f 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.h
+++ b/drivers/scsi/qla2xxx/qla_dbg.h
@@ -368,6 +368,7 @@ ql_log_qp(uint32_t, struct qla_qpair *, int32_t, const char *fmt, ...);
 #define ql_dbg_tgt_tmr	0x00001000 /* Target mode task management */
 #define ql_dbg_tgt_dif  0x00000800 /* Target mode dif */
 #define ql_dbg_edif	0x00000400 /* edif and purex debug */
+#define ql_dbg_unsol	0x00000100 /* Unsolicited path debug */
 
 extern int qla27xx_dump_mpi_ram(struct qla_hw_data *, uint32_t, uint32_t *,
 	uint32_t, void **);
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 97ecb2158c8a..2007d5bb5f9f 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -346,6 +346,12 @@ struct name_list_extended {
 	u8			sent;
 };
 
+struct qla_nvme_fc_rjt {
+	struct fcnvme_ls_rjt *c;
+	dma_addr_t  cdma;
+	u16 size;
+};
+
 struct els_reject {
 	struct fc_els_ls_rjt *c;
 	dma_addr_t  cdma;
@@ -503,6 +509,20 @@ struct ct_arg {
 	port_id_t	id;
 };
 
+struct qla_nvme_lsrjt_pt_arg {
+	struct fc_port *fcport;
+	u8 opcode;
+	u8 vp_idx;
+	u8 reason;
+	u8 explanation;
+	__le16 nport_handle;
+	u16 control_flags;
+	__le16 ox_id;
+	__le32 xchg_address;
+	u32 tx_byte_count, rx_byte_count;
+	dma_addr_t tx_addr, rx_addr;
+};
+
 /*
  * SRB extensions.
  */
@@ -611,13 +631,16 @@ struct srb_iocb {
 			void *desc;
 
 			/* These are only used with ls4 requests */
-			int cmd_len;
-			int rsp_len;
+			__le32 cmd_len;
+			__le32 rsp_len;
 			dma_addr_t cmd_dma;
 			dma_addr_t rsp_dma;
 			enum nvmefc_fcp_datadir dir;
 			uint32_t dl;
 			uint32_t timeout_sec;
+			__le32 exchange_address;
+			__le16 nport_handle;
+			__le16 ox_id;
 			struct	list_head   entry;
 		} nvme;
 		struct {
@@ -707,6 +730,10 @@ typedef struct srb {
 	struct fc_port *fcport;
 	struct scsi_qla_host *vha;
 	unsigned int start_timer:1;
+	unsigned int abort:1;
+	unsigned int aborted:1;
+	unsigned int completed:1;
+	unsigned int unsol_rsp:1;
 
 	uint32_t handle;
 	uint16_t flags;
@@ -2542,6 +2569,7 @@ enum rscn_addr_format {
 typedef struct fc_port {
 	struct list_head list;
 	struct scsi_qla_host *vha;
+	struct list_head unsol_ctx_head;
 
 	unsigned int conf_compl_supported:1;
 	unsigned int deleted:2;
@@ -4802,6 +4830,7 @@ struct qla_hw_data {
 	struct els_reject elsrej;
 	u8 edif_post_stop_cnt_down;
 	struct qla_vp_map *vp_map;
+	struct qla_nvme_fc_rjt lsrjt;
 };
 
 #define RX_ELS_SIZE (roundup(sizeof(struct enode) + ELS_MAX_PAYLOAD, SMP_CACHE_BYTES))
@@ -4834,6 +4863,7 @@ struct active_regions {
  * is variable) starting at "iocb".
  */
 struct purex_item {
+	void *purls_context;
 	struct list_head list;
 	struct scsi_qla_host *vha;
 	void (*process_item)(struct scsi_qla_host *vha,
diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h
index 33fba9d62969..911e9adf41d3 100644
--- a/drivers/scsi/qla2xxx/qla_gbl.h
+++ b/drivers/scsi/qla2xxx/qla_gbl.h
@@ -611,7 +611,11 @@ qla2xxx_msix_rsp_q_hs(int irq, void *dev_id);
 fc_port_t *qla2x00_find_fcport_by_loopid(scsi_qla_host_t *, uint16_t);
 fc_port_t *qla2x00_find_fcport_by_wwpn(scsi_qla_host_t *, u8 *, u8);
 fc_port_t *qla2x00_find_fcport_by_nportid(scsi_qla_host_t *, port_id_t *, u8);
-void __qla_consume_iocb(struct scsi_qla_host *vha, void **pkt, struct rsp_que **rsp);
+void qla24xx_queue_purex_item(scsi_qla_host_t *, struct purex_item *,
+			      void (*process_item)(struct scsi_qla_host *,
+			      struct purex_item *));
+void __qla_consume_iocb(struct scsi_qla_host *, void **, struct rsp_que **);
+void qla2xxx_process_purls_iocb(void **pkt, struct rsp_que **rsp);
 
 /*
  * Global Function Prototypes in qla_sup.c source file.
@@ -674,9 +678,11 @@ extern int qla2xxx_get_vpd_field(scsi_qla_host_t *, char *, char *, size_t);
 extern void qla2xxx_flash_npiv_conf(scsi_qla_host_t *);
 extern int qla24xx_read_fcp_prio_cfg(scsi_qla_host_t *);
 extern int qla2x00_mailbox_passthru(struct bsg_job *bsg_job);
-int __qla_copy_purex_to_buffer(struct scsi_qla_host *vha, void **pkt,
-	struct rsp_que **rsp, u8 *buf, u32 buf_len);
-
+int qla2x00_sys_ld_info(struct bsg_job *bsg_job);
+int __qla_copy_purex_to_buffer(struct scsi_qla_host *, void **,
+	struct rsp_que **, u8 *, u32);
+struct purex_item *qla27xx_copy_multiple_pkt(struct scsi_qla_host *vha,
+	void **pkt, struct rsp_que **rsp, bool is_purls, bool byte_order);
 int qla_mailbox_passthru(scsi_qla_host_t *vha, uint16_t *mbx_in,
 			 uint16_t *mbx_out);
 
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 53e76bbee915..27644957ae4e 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -5554,6 +5554,7 @@ qla2x00_alloc_fcport(scsi_qla_host_t *vha, gfp_t flags)
 	INIT_WORK(&fcport->reg_work, qla_register_fcport_fn);
 	INIT_LIST_HEAD(&fcport->gnl_entry);
 	INIT_LIST_HEAD(&fcport->list);
+	INIT_LIST_HEAD(&fcport->unsol_ctx_head);
 
 	INIT_LIST_HEAD(&fcport->sess_cmd_list);
 	spin_lock_init(&fcport->sess_cmd_lock);
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index d0b12c746a8a..7fbd917f6e1f 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -3771,21 +3771,28 @@ qla_nvme_ls(srb_t *sp, struct pt_ls4_request *cmd_pkt)
 	nvme = &sp->u.iocb_cmd;
 	cmd_pkt->entry_type = PT_LS4_REQUEST;
 	cmd_pkt->entry_count = 1;
-	cmd_pkt->control_flags = cpu_to_le16(CF_LS4_ORIGINATOR << CF_LS4_SHIFT);
-
 	cmd_pkt->timeout = cpu_to_le16(nvme->u.nvme.timeout_sec);
-	cmd_pkt->nport_handle = cpu_to_le16(sp->fcport->loop_id);
 	cmd_pkt->vp_index = sp->fcport->vha->vp_idx;
 
-	cmd_pkt->tx_dseg_count = cpu_to_le16(1);
-	cmd_pkt->tx_byte_count = cpu_to_le32(nvme->u.nvme.cmd_len);
-	cmd_pkt->dsd[0].length = cpu_to_le32(nvme->u.nvme.cmd_len);
-	put_unaligned_le64(nvme->u.nvme.cmd_dma, &cmd_pkt->dsd[0].address);
+	if (sp->unsol_rsp) {
+		cmd_pkt->control_flags =
+				cpu_to_le16(CF_LS4_RESPONDER << CF_LS4_SHIFT);
+		cmd_pkt->nport_handle = nvme->u.nvme.nport_handle;
+		cmd_pkt->exchange_address = nvme->u.nvme.exchange_address;
+	} else {
+		cmd_pkt->control_flags =
+				cpu_to_le16(CF_LS4_ORIGINATOR << CF_LS4_SHIFT);
+		cmd_pkt->nport_handle = cpu_to_le16(sp->fcport->loop_id);
+		cmd_pkt->rx_dseg_count = cpu_to_le16(1);
+		cmd_pkt->rx_byte_count = nvme->u.nvme.rsp_len;
+		cmd_pkt->dsd[1].length  = nvme->u.nvme.rsp_len;
+		put_unaligned_le64(nvme->u.nvme.rsp_dma, &cmd_pkt->dsd[1].address);
+	}
 
-	cmd_pkt->rx_dseg_count = cpu_to_le16(1);
-	cmd_pkt->rx_byte_count = cpu_to_le32(nvme->u.nvme.rsp_len);
-	cmd_pkt->dsd[1].length = cpu_to_le32(nvme->u.nvme.rsp_len);
-	put_unaligned_le64(nvme->u.nvme.rsp_dma, &cmd_pkt->dsd[1].address);
+	cmd_pkt->tx_dseg_count = cpu_to_le16(1);
+	cmd_pkt->tx_byte_count = nvme->u.nvme.cmd_len;
+	cmd_pkt->dsd[0].length = nvme->u.nvme.cmd_len;
+	put_unaligned_le64(nvme->u.nvme.cmd_dma, &cmd_pkt->dsd[0].address);
 }
 
 static void
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 1f42a413b598..867025c89909 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -823,6 +823,135 @@ qla83xx_handle_8200_aen(scsi_qla_host_t *vha, uint16_t *mb)
 	}
 }
 
+/**
+ * qla27xx_copy_multiple_pkt() - Copy over purex/purls packets that can
+ * span over multiple IOCBs.
+ * @vha: SCSI driver HA context
+ * @pkt: ELS packet
+ * @rsp: Response queue
+ * @is_purls: True, for Unsolicited Received FC-NVMe LS rsp IOCB
+ *            false, for Unsolicited Received ELS IOCB
+ * @byte_order: True, to change the byte ordering of iocb payload
+ */
+struct purex_item *
+qla27xx_copy_multiple_pkt(struct scsi_qla_host *vha, void **pkt,
+			  struct rsp_que **rsp, bool is_purls,
+			  bool byte_order)
+{
+	struct purex_entry_24xx *purex = NULL;
+	struct pt_ls4_rx_unsol *purls = NULL;
+	struct rsp_que *rsp_q = *rsp;
+	sts_cont_entry_t *new_pkt;
+	uint16_t no_bytes = 0, total_bytes = 0, pending_bytes = 0;
+	uint16_t buffer_copy_offset = 0, payload_size = 0;
+	uint16_t entry_count, entry_count_remaining;
+	struct purex_item *item;
+	void *iocb_pkt = NULL;
+
+	if (is_purls) {
+		purls = *pkt;
+		total_bytes = (le16_to_cpu(purls->frame_size) & 0x0FFF) -
+			      PURX_ELS_HEADER_SIZE;
+		entry_count = entry_count_remaining = purls->entry_count;
+		payload_size = sizeof(purls->payload);
+	} else {
+		purex = *pkt;
+		total_bytes = (le16_to_cpu(purex->frame_size) & 0x0FFF) -
+			      PURX_ELS_HEADER_SIZE;
+		entry_count = entry_count_remaining = purex->entry_count;
+		payload_size = sizeof(purex->els_frame_payload);
+	}
+
+	pending_bytes = total_bytes;
+	no_bytes = (pending_bytes > payload_size) ? payload_size :
+		   pending_bytes;
+	ql_dbg(ql_dbg_async, vha, 0x509a,
+	       "%s LS, frame_size 0x%x, entry count %d\n",
+	       (is_purls ? "PURLS" : "FPIN"), total_bytes, entry_count);
+
+	item = qla24xx_alloc_purex_item(vha, total_bytes);
+	if (!item)
+		return item;
+
+	iocb_pkt = &item->iocb;
+
+	if (is_purls)
+		memcpy(iocb_pkt, &purls->payload[0], no_bytes);
+	else
+		memcpy(iocb_pkt, &purex->els_frame_payload[0], no_bytes);
+	buffer_copy_offset += no_bytes;
+	pending_bytes -= no_bytes;
+	--entry_count_remaining;
+
+	if (is_purls)
+		((response_t *)purls)->signature = RESPONSE_PROCESSED;
+	else
+		((response_t *)purex)->signature = RESPONSE_PROCESSED;
+	wmb();
+
+	do {
+		while ((total_bytes > 0) && (entry_count_remaining > 0)) {
+			if (rsp_q->ring_ptr->signature == RESPONSE_PROCESSED) {
+				ql_dbg(ql_dbg_async, vha, 0x5084,
+				       "Ran out of IOCBs, partial data 0x%x\n",
+				       buffer_copy_offset);
+				cpu_relax();
+				continue;
+			}
+
+			new_pkt = (sts_cont_entry_t *)rsp_q->ring_ptr;
+			*pkt = new_pkt;
+
+			if (new_pkt->entry_type != STATUS_CONT_TYPE) {
+				ql_log(ql_log_warn, vha, 0x507a,
+				       "Unexpected IOCB type, partial data 0x%x\n",
+				       buffer_copy_offset);
+				break;
+			}
+
+			rsp_q->ring_index++;
+			if (rsp_q->ring_index == rsp_q->length) {
+				rsp_q->ring_index = 0;
+				rsp_q->ring_ptr = rsp_q->ring;
+			} else {
+				rsp_q->ring_ptr++;
+			}
+			no_bytes = (pending_bytes > sizeof(new_pkt->data)) ?
+				sizeof(new_pkt->data) : pending_bytes;
+			if ((buffer_copy_offset + no_bytes) <= total_bytes) {
+				memcpy(((uint8_t *)iocb_pkt + buffer_copy_offset),
+				       new_pkt->data, no_bytes);
+				buffer_copy_offset += no_bytes;
+				pending_bytes -= no_bytes;
+				--entry_count_remaining;
+			} else {
+				ql_log(ql_log_warn, vha, 0x5044,
+				       "Attempt to copy more that we got, optimizing..%x\n",
+				       buffer_copy_offset);
+				memcpy(((uint8_t *)iocb_pkt + buffer_copy_offset),
+				       new_pkt->data,
+				       total_bytes - buffer_copy_offset);
+			}
+
+			((response_t *)new_pkt)->signature = RESPONSE_PROCESSED;
+			wmb();
+		}
+
+		if (pending_bytes != 0 || entry_count_remaining != 0) {
+			ql_log(ql_log_fatal, vha, 0x508b,
+			       "Dropping partial FPIN, underrun bytes = 0x%x, entry cnts 0x%x\n",
+			       total_bytes, entry_count_remaining);
+			qla24xx_free_purex_item(item);
+			return NULL;
+		}
+	} while (entry_count_remaining > 0);
+
+	if (byte_order)
+		host_to_fcp_swap((uint8_t *)&item->iocb, total_bytes);
+
+	return item;
+}
+
 int
 qla2x00_is_a_vp_did(scsi_qla_host_t *vha, uint32_t rscn_entry)
 {
@@ -958,7 +1087,7 @@ initialize_purex_header:
 	return item;
 }
 
-static void
+void
 qla24xx_queue_purex_item(scsi_qla_host_t *vha, struct purex_item *pkt,
 			 void (*process_item)(struct scsi_qla_host *vha,
 					      struct purex_item *pkt))
@@ -3811,6 +3940,7 @@ void qla24xx_process_response_queue(struct scsi_qla_host *vha,
 	struct qla_hw_data *ha = vha->hw;
 	struct purex_entry_24xx *purex_entry;
 	struct purex_item *pure_item;
+	struct pt_ls4_rx_unsol *p;
 	u16 rsp_in = 0, cur_ring_index;
 	int is_shadow_hba;
 
@@ -3983,7 +4113,19 @@ process_err:
 			qla28xx_sa_update_iocb_entry(vha, rsp->req,
 				(struct sa_update_28xx *)pkt);
 			break;
+		case PT_LS4_UNSOL:
+			p = (void *)pkt;
+			if (qla_chk_cont_iocb_avail(vha, rsp, (response_t *)pkt, rsp_in)) {
+				rsp->ring_ptr = (response_t *)pkt;
+				rsp->ring_index = cur_ring_index;
 
+				ql_dbg(ql_dbg_init, vha, 0x2124,
+				       "Defer processing UNSOL LS req opcode %#x...\n",
+				       p->payload[0]);
+				return;
+			}
+			qla2xxx_process_purls_iocb((void **)&pkt, &rsp);
+			break;
 		default:
 			/* Type Not Supported. */
 			ql_dbg(ql_dbg_async, vha, 0x5042,
diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c
index 9941b38eac93..1a31e877e6cb 100644
--- a/drivers/scsi/qla2xxx/qla_nvme.c
+++ b/drivers/scsi/qla2xxx/qla_nvme.c
@@ -12,6 +12,26 @@
 #include <linux/blk-mq.h>
 
 static struct nvme_fc_port_template qla_nvme_fc_transport;
+static int qla_nvme_ls_reject_iocb(struct scsi_qla_host *vha,
+				   struct qla_qpair *qp,
+				   struct qla_nvme_lsrjt_pt_arg *a,
+				   bool is_xchg_terminate);
+
+struct qla_nvme_unsol_ctx {
+	struct list_head elem;
+	struct scsi_qla_host *vha;
+	struct fc_port *fcport;
+	struct srb *sp;
+	struct nvmefc_ls_rsp lsrsp;
+	struct nvmefc_ls_rsp *fd_rsp;
+	struct work_struct lsrsp_work;
+	struct work_struct abort_work;
+	__le32 exchange_address;
+	__le16 nport_handle;
+	__le16 ox_id;
+	int comp_status;
+	spinlock_t cmd_lock;
+};
 
 int qla_nvme_register_remote(struct scsi_qla_host *vha, struct fc_port *fcport)
 {
@@ -216,6 +236,55 @@ static void qla_nvme_sp_ls_done(srb_t *sp, int res)
 	schedule_work(&priv->ls_work);
 }
 
+static void qla_nvme_release_lsrsp_cmd_kref(struct kref *kref)
+{
+	struct srb *sp = container_of(kref, struct srb, cmd_kref);
+	struct qla_nvme_unsol_ctx *uctx = sp->priv;
+	struct nvmefc_ls_rsp *fd_rsp;
+	unsigned long flags;
+
+	if (!uctx) {
+		qla2x00_rel_sp(sp);
+		return;
+	}
+
+	spin_lock_irqsave(&uctx->cmd_lock, flags);
+	uctx->sp = NULL;
+	sp->priv = NULL;
+	spin_unlock_irqrestore(&uctx->cmd_lock, flags);
+
+	fd_rsp = uctx->fd_rsp;
+
+	list_del(&uctx->elem);
+
+	fd_rsp->done(fd_rsp);
+	kfree(uctx);
+	qla2x00_rel_sp(sp);
+}
+
+static void qla_nvme_lsrsp_complete(struct work_struct *work)
+{
+	struct qla_nvme_unsol_ctx *uctx =
+		container_of(work, struct qla_nvme_unsol_ctx, lsrsp_work);
+
+	kref_put(&uctx->sp->cmd_kref, qla_nvme_release_lsrsp_cmd_kref);
+}
+
+static void qla_nvme_sp_lsrsp_done(srb_t *sp, int res)
+{
+	struct qla_nvme_unsol_ctx *uctx = sp->priv;
+
+	if (WARN_ON_ONCE(kref_read(&sp->cmd_kref) == 0))
+		return;
+
+	if (res)
+		res = -EINVAL;
+
+	uctx->comp_status = res;
+	INIT_WORK(&uctx->lsrsp_work, qla_nvme_lsrsp_complete);
+	schedule_work(&uctx->lsrsp_work);
+}
+
 /* it assumed that QPair lock is held. */
 static void qla_nvme_sp_done(srb_t *sp, int res)
 {
@@ -288,6 +357,92 @@ out:
 	kref_put(&sp->cmd_kref, sp->put_fn);
 }
 
+static int qla_nvme_xmt_ls_rsp(struct nvme_fc_local_port *lport,
+			       struct nvme_fc_remote_port *rport,
+			       struct nvmefc_ls_rsp *fd_resp)
+{
+	struct qla_nvme_unsol_ctx *uctx = container_of(fd_resp,
+				struct qla_nvme_unsol_ctx, lsrsp);
+	struct qla_nvme_rport *qla_rport = rport->private;
+	fc_port_t *fcport = qla_rport->fcport;
+	struct scsi_qla_host *vha = uctx->vha;
+	struct qla_hw_data *ha = vha->hw;
+	struct qla_nvme_lsrjt_pt_arg a;
+	struct srb_iocb *nvme;
+	srb_t *sp;
+	int rval = QLA_FUNCTION_FAILED;
+	uint8_t cnt = 0;
+
+	if (!fcport || fcport->deleted)
+		goto out;
+
+	if (!ha->flags.fw_started)
+		goto out;
+
+	/* Alloc SRB structure */
+	sp = qla2x00_get_sp(vha, fcport, GFP_ATOMIC);
+	if (!sp)
+		goto out;
+
+	sp->type = SRB_NVME_LS;
+	sp->name = "nvme_ls";
+	sp->done = qla_nvme_sp_lsrsp_done;
+	sp->put_fn = qla_nvme_release_lsrsp_cmd_kref;
+	sp->priv = (void *)uctx;
+	sp->unsol_rsp = 1;
+	uctx->sp = sp;
+	spin_lock_init(&uctx->cmd_lock);
+	nvme = &sp->u.iocb_cmd;
+	uctx->fd_rsp = fd_resp;
+	nvme->u.nvme.desc = fd_resp;
+	nvme->u.nvme.dir = 0;
+	nvme->u.nvme.dl = 0;
+	nvme->u.nvme.timeout_sec = 0;
+	nvme->u.nvme.cmd_dma = fd_resp->rspdma;
+	nvme->u.nvme.cmd_len = fd_resp->rsplen;
+	nvme->u.nvme.rsp_len = 0;
+	nvme->u.nvme.rsp_dma = 0;
+	nvme->u.nvme.exchange_address = uctx->exchange_address;
+	nvme->u.nvme.nport_handle = uctx->nport_handle;
+	nvme->u.nvme.ox_id = uctx->ox_id;
+	dma_sync_single_for_device(&ha->pdev->dev, nvme->u.nvme.cmd_dma,
+				   le32_to_cpu(fd_resp->rsplen), DMA_TO_DEVICE);
+
+	ql_dbg(ql_dbg_unsol, vha, 0x2122,
+	       "Unsol lsreq portid=%06x %8phC exchange_address 0x%x ox_id 0x%x hdl 0x%x\n",
+	       fcport->d_id.b24, fcport->port_name, uctx->exchange_address,
+	       uctx->ox_id, uctx->nport_handle);
+retry:
+	rval = qla2x00_start_sp(sp);
+	switch (rval) {
+	case QLA_SUCCESS:
+		break;
+	case EAGAIN:
+		msleep(PURLS_MSLEEP_INTERVAL);
+		cnt++;
+		if (cnt < PURLS_RETRY_COUNT)
+			goto retry;
+
+		fallthrough;
+	default:
+		ql_dbg(ql_log_warn, vha, 0x2123,
+		       "Failed to xmit Unsol ls response = %d\n", rval);
+		rval = -EIO;
+		qla2x00_rel_sp(sp);
+		goto out;
+	}
+
+	return 0;
+out:
+	memset((void *)&a, 0, sizeof(a));
+	a.vp_idx = vha->vp_idx;
+	a.nport_handle = uctx->nport_handle;
+	a.xchg_address = uctx->exchange_address;
+	qla_nvme_ls_reject_iocb(vha, ha->base_qpair, &a, true);
+	kfree(uctx);
+	return rval;
+}
+
 static void qla_nvme_ls_abort(struct nvme_fc_local_port *lport,
     struct nvme_fc_remote_port *rport, struct nvmefc_ls_req *fd)
 {
@@ -355,7 +510,7 @@ static int qla_nvme_ls_req(struct nvme_fc_local_port *lport,
 	nvme->u.nvme.timeout_sec = fd->timeout;
 	nvme->u.nvme.cmd_dma = fd->rqstdma;
 	dma_sync_single_for_device(&ha->pdev->dev, nvme->u.nvme.cmd_dma,
-	    fd->rqstlen, DMA_TO_DEVICE);
+	    le32_to_cpu(fd->rqstlen), DMA_TO_DEVICE);
 
 	rval = qla2x00_start_sp(sp);
 	if (rval != QLA_SUCCESS) {
@@ -720,6 +875,7 @@ static struct nvme_fc_port_template qla_nvme_fc_transport = {
 	.ls_abort	= qla_nvme_ls_abort,
 	.fcp_io		= qla_nvme_post_cmd,
 	.fcp_abort	= qla_nvme_fcp_abort,
+	.xmt_ls_rsp	= qla_nvme_xmt_ls_rsp,
 	.map_queues	= qla_nvme_map_queues,
 	.max_hw_queues  = DEF_NVME_HW_QUEUES,
 	.max_sgl_segments = 1024,
@@ -924,3 +1080,246 @@ inline void qla_wait_nvme_release_cmd_kref(srb_t *orig_sp)
 		return;
 	kref_put(&orig_sp->cmd_kref, orig_sp->put_fn);
 }
+
+static void qla_nvme_fc_format_rjt(void *buf, u8 ls_cmd, u8 reason,
+				   u8 explanation, u8 vendor)
+{
+	struct fcnvme_ls_rjt *rjt = buf;
+
+	rjt->w0.ls_cmd = FCNVME_LSDESC_RQST;
+	rjt->desc_list_len = fcnvme_lsdesc_len(sizeof(struct fcnvme_ls_rjt));
+	rjt->rqst.desc_tag = cpu_to_be32(FCNVME_LSDESC_RQST);
+	rjt->rqst.desc_len =
+		fcnvme_lsdesc_len(sizeof(struct fcnvme_lsdesc_rqst));
+	rjt->rqst.w0.ls_cmd = ls_cmd;
+	rjt->rjt.desc_tag = cpu_to_be32(FCNVME_LSDESC_RJT);
+	rjt->rjt.desc_len = fcnvme_lsdesc_len(sizeof(struct fcnvme_lsdesc_rjt));
+	rjt->rjt.reason_code = reason;
+	rjt->rjt.reason_explanation = explanation;
+	rjt->rjt.vendor = vendor;
+}
+
+static void qla_nvme_lsrjt_pt_iocb(struct scsi_qla_host *vha,
+				   struct pt_ls4_request *lsrjt_iocb,
+				   struct qla_nvme_lsrjt_pt_arg *a)
+{
+	lsrjt_iocb->entry_type = PT_LS4_REQUEST;
+	lsrjt_iocb->entry_count = 1;
+	lsrjt_iocb->sys_define = 0;
+	lsrjt_iocb->entry_status = 0;
+	lsrjt_iocb->handle = QLA_SKIP_HANDLE;
+	lsrjt_iocb->nport_handle = a->nport_handle;
+	lsrjt_iocb->exchange_address = a->xchg_address;
+	lsrjt_iocb->vp_index = a->vp_idx;
+
+	lsrjt_iocb->control_flags = cpu_to_le16(a->control_flags);
+
+	put_unaligned_le64(a->tx_addr, &lsrjt_iocb->dsd[0].address);
+	lsrjt_iocb->dsd[0].length = cpu_to_le32(a->tx_byte_count);
+	lsrjt_iocb->tx_dseg_count = cpu_to_le16(1);
+	lsrjt_iocb->tx_byte_count = cpu_to_le32(a->tx_byte_count);
+
+	put_unaligned_le64(a->rx_addr, &lsrjt_iocb->dsd[1].address);
+	lsrjt_iocb->dsd[1].length = 0;
+	lsrjt_iocb->rx_dseg_count = 0;
+	lsrjt_iocb->rx_byte_count = 0;
+}
+
+static int
+qla_nvme_ls_reject_iocb(struct scsi_qla_host *vha, struct qla_qpair *qp,
+			struct qla_nvme_lsrjt_pt_arg *a, bool is_xchg_terminate)
+{
+	struct pt_ls4_request *lsrjt_iocb;
+
+	lsrjt_iocb = __qla2x00_alloc_iocbs(qp, NULL);
+	if (!lsrjt_iocb) {
+		ql_log(ql_log_warn, vha, 0x210e,
+		       "qla2x00_alloc_iocbs failed.\n");
+		return QLA_FUNCTION_FAILED;
+	}
+
+	if (!is_xchg_terminate) {
+		qla_nvme_fc_format_rjt((void *)vha->hw->lsrjt.c, a->opcode,
+				       a->reason, a->explanation, 0);
+
+		a->tx_byte_count = sizeof(struct fcnvme_ls_rjt);
+		a->tx_addr = vha->hw->lsrjt.cdma;
+		a->control_flags = CF_LS4_RESPONDER << CF_LS4_SHIFT;
+
+		ql_dbg(ql_dbg_unsol, vha, 0x211f,
+		       "Sending nvme fc ls reject ox_id %04x op %04x\n",
+		       a->ox_id, a->opcode);
+		ql_dump_buffer(ql_dbg_unsol + ql_dbg_verbose, vha, 0x210f,
+			       vha->hw->lsrjt.c, sizeof(*vha->hw->lsrjt.c));
+	} else {
+		a->tx_byte_count = 0;
+		a->control_flags = CF_LS4_RESPONDER_TERM << CF_LS4_SHIFT;
+		ql_dbg(ql_dbg_unsol, vha, 0x2110,
+		       "Terminate nvme ls xchg 0x%x\n", a->xchg_address);
+	}
+
+	qla_nvme_lsrjt_pt_iocb(vha, lsrjt_iocb, a);
+	/* flush iocb to mem before notifying hw doorbell */
+	wmb();
+	qla2x00_start_iocbs(vha, qp->req);
+	return 0;
+}
+
+/*
+ * qla2xxx_process_purls_pkt() - Pass-up Unsolicited
+ * Received FC-NVMe Link Service pkt to nvme_fc_rcv_ls_req().
+ * LLDD need to provide memory for response buffer, which
+ * will be used to reference the exchange corresponding
+ * to the LS when issuing an ls response. LLDD will have to free
+ * response buffer in lport->ops->xmt_ls_rsp().
+ *
+ * @vha: SCSI qla host
+ * @item: ptr to purex_item
+ */
+static void
+qla2xxx_process_purls_pkt(struct scsi_qla_host *vha, struct purex_item *item)
+{
+	struct qla_nvme_unsol_ctx *uctx = item->purls_context;
+	fc_port_t *fcport = uctx->fcport;
+	struct qla_nvme_lsrjt_pt_arg a;
+	int ret;
+
+	ret = nvme_fc_rcv_ls_req(fcport->nvme_remote_port, &uctx->lsrsp,
+				 &item->iocb, item->size);
+	if (ret) {
+		ql_dbg(ql_dbg_unsol, vha, 0x2125, "NVMe tranport ls_req failed\n");
+		memset((void *)&a, 0, sizeof(a));
+		a.vp_idx = vha->vp_idx;
+		a.nport_handle = uctx->nport_handle;
+		a.xchg_address = uctx->exchange_address;
+		qla_nvme_ls_reject_iocb(vha, vha->hw->base_qpair, &a, true);
+		list_del(&uctx->elem);
+		kfree(uctx);
+	}
+}
+
+static scsi_qla_host_t *
+qla2xxx_get_vha_from_vp_idx(struct qla_hw_data *ha, uint16_t vp_index)
+{
+	scsi_qla_host_t *base_vha, *vha, *tvp;
+	unsigned long flags;
+
+	base_vha = pci_get_drvdata(ha->pdev);
+
+	if (!vp_index && !ha->num_vhosts)
+		return base_vha;
+
+	spin_lock_irqsave(&ha->vport_slock, flags);
+	list_for_each_entry_safe(vha, tvp, &ha->vp_list, list) {
+		if (vha->vp_idx == vp_index) {
+			spin_unlock_irqrestore(&ha->vport_slock, flags);
+			return vha;
+		}
+	}
+	spin_unlock_irqrestore(&ha->vport_slock, flags);
+
+	return NULL;
+}
+
+void qla2xxx_process_purls_iocb(void **pkt, struct rsp_que **rsp)
+{
+	struct nvme_fc_remote_port *rport;
+	struct qla_nvme_rport *qla_rport;
+	struct qla_nvme_lsrjt_pt_arg a;
+	struct pt_ls4_rx_unsol *p = *pkt;
+	struct qla_nvme_unsol_ctx *uctx;
+	struct rsp_que *rsp_q = *rsp;
+	struct qla_hw_data *ha;
+	scsi_qla_host_t	*vha;
+	fc_port_t *fcport = NULL;
+	struct purex_item *item;
+	port_id_t d_id = {0};
+	port_id_t id = {0};
+	u8 *opcode;
+	bool xmt_reject = false;
+
+	ha = rsp_q->hw;
+
+	vha = qla2xxx_get_vha_from_vp_idx(ha, p->vp_index);
+	if (!vha) {
+		ql_log(ql_log_warn, NULL, 0x2110, "Invalid vp index %d\n", p->vp_index);
+		WARN_ON_ONCE(1);
+		return;
+	}
+
+	memset((void *)&a, 0, sizeof(a));
+	opcode = (u8 *)&p->payload[0];
+	a.opcode = opcode[3];
+	a.vp_idx = p->vp_index;
+	a.nport_handle = p->nport_handle;
+	a.ox_id = p->ox_id;
+	a.xchg_address = p->exchange_address;
+
+	id.b.domain = p->s_id.domain;
+	id.b.area   = p->s_id.area;
+	id.b.al_pa  = p->s_id.al_pa;
+	d_id.b.domain = p->d_id[2];
+	d_id.b.area   = p->d_id[1];
+	d_id.b.al_pa  = p->d_id[0];
+
+	fcport = qla2x00_find_fcport_by_nportid(vha, &id, 0);
+	if (!fcport) {
+		ql_dbg(ql_dbg_unsol, vha, 0x211e,
+		       "Failed to find sid=%06x did=%06x\n",
+		       id.b24, d_id.b24);
+		a.reason = FCNVME_RJT_RC_INV_ASSOC;
+		a.explanation = FCNVME_RJT_EXP_NONE;
+		xmt_reject = true;
+		goto out;
+	}
+	rport = fcport->nvme_remote_port;
+	qla_rport = rport->private;
+
+	item = qla27xx_copy_multiple_pkt(vha, pkt, rsp, true, false);
+	if (!item) {
+		a.reason = FCNVME_RJT_RC_LOGIC;
+		a.explanation = FCNVME_RJT_EXP_NONE;
+		xmt_reject = true;
+		goto out;
+	}
+
+	uctx = kzalloc(sizeof(*uctx), GFP_ATOMIC);
+	if (!uctx) {
+		ql_log(ql_log_info, vha, 0x2126, "Failed allocate memory\n");
+		a.reason = FCNVME_RJT_RC_LOGIC;
+		a.explanation = FCNVME_RJT_EXP_NONE;
+		xmt_reject = true;
+		kfree(item);
+		goto out;
+	}
+
+	uctx->vha = vha;
+	uctx->fcport = fcport;
+	uctx->exchange_address = p->exchange_address;
+	uctx->nport_handle = p->nport_handle;
+	uctx->ox_id = p->ox_id;
+	qla_rport->uctx = uctx;
+	INIT_LIST_HEAD(&uctx->elem);
+	list_add_tail(&uctx->elem, &fcport->unsol_ctx_head);
+	item->purls_context = (void *)uctx;
+
+	ql_dbg(ql_dbg_unsol, vha, 0x2121,
+	       "PURLS OP[%01x] size %d xchg addr 0x%x portid %06x\n",
+	       item->iocb.iocb[3], item->size, uctx->exchange_address,
+	       fcport->d_id.b24);
+	/* +48    0  1  2  3  4  5  6  7  8  9  A  B  C  D  E  F
+	 * ----- -----------------------------------------------
+	 * 0000: 00 00 00 05 28 00 00 00 07 00 00 00 08 00 00 00
+	 * 0010: ab ec 0f cc 00 00 8d 7d 05 00 00 00 10 00 00 00
+	 * 0020: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
+	 */
+	ql_dump_buffer(ql_dbg_unsol + ql_dbg_verbose, vha, 0x2120,
+		       &item->iocb, item->size);
+
+	qla24xx_queue_purex_item(vha, item, qla2xxx_process_purls_pkt);
+out:
+	if (xmt_reject) {
+		qla_nvme_ls_reject_iocb(vha, (*rsp)->qpair, &a, false);
+		__qla_consume_iocb(vha, pkt, rsp);
+	}
+}
diff --git a/drivers/scsi/qla2xxx/qla_nvme.h b/drivers/scsi/qla2xxx/qla_nvme.h
index d299478371b2..a253ac55171b 100644
--- a/drivers/scsi/qla2xxx/qla_nvme.h
+++ b/drivers/scsi/qla2xxx/qla_nvme.h
@@ -21,6 +21,7 @@
 #define Q2T_NVME_NUM_TAGS 2048
 #define QLA_MAX_FC_SEGMENTS 64
 
+struct qla_nvme_unsol_ctx;
 struct scsi_qla_host;
 struct qla_hw_data;
 struct req_que;
@@ -37,6 +38,7 @@ struct nvme_private {
 
 struct qla_nvme_rport {
 	struct fc_port *fcport;
+	struct qla_nvme_unsol_ctx *uctx;
 };
 
 #define COMMAND_NVME    0x88            /* Command Type FC-NVMe IOCB */
@@ -75,6 +77,9 @@ struct cmd_nvme {
 	struct dsd64 nvme_dsd;
 };
 
+#define PURLS_MSLEEP_INTERVAL	1
+#define PURLS_RETRY_COUNT	5
+
 #define PT_LS4_REQUEST 0x89	/* Link Service pass-through IOCB (request) */
 struct pt_ls4_request {
 	uint8_t entry_type;
@@ -118,21 +123,19 @@ struct pt_ls4_rx_unsol {
 	__le32	exchange_address;
 	uint8_t d_id[3];
 	uint8_t r_ctl;
-	be_id_t s_id;
+	le_id_t s_id;
 	uint8_t cs_ctl;
 	uint8_t f_ctl[3];
 	uint8_t type;
 	__le16	seq_cnt;
 	uint8_t df_ctl;
 	uint8_t seq_id;
-	__le16	rx_id;
-	__le16	ox_id;
-	__le32	param;
-	__le32	desc0;
+	__le16 rx_id;
+	__le16 ox_id;
+	__le32  desc0;
 #define PT_LS4_PAYLOAD_OFFSET 0x2c
 #define PT_LS4_FIRST_PACKET_LEN 20
-	__le32	desc_len;
-	__le32	payload[3];
+	__le32 payload[5];
 };
 
 /*
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index f31d0ead8919..aa492489a4b8 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -4457,8 +4457,9 @@ qla2x00_mem_alloc(struct qla_hw_data *ha, uint16_t req_len, uint16_t rsp_len,
 
 	ha->elsrej.size = sizeof(struct fc_els_ls_rjt) + 16;
 	ha->elsrej.c = dma_alloc_coherent(&ha->pdev->dev,
-	    ha->elsrej.size, &ha->elsrej.cdma, GFP_KERNEL);
-
+					  ha->elsrej.size,
+					  &ha->elsrej.cdma,
+					  GFP_KERNEL);
 	if (!ha->elsrej.c) {
 		ql_dbg_pci(ql_dbg_init, ha->pdev, 0xffff,
 		    "Alloc failed for els reject cmd.\n");
@@ -4467,8 +4468,21 @@ qla2x00_mem_alloc(struct qla_hw_data *ha, uint16_t req_len, uint16_t rsp_len,
 	ha->elsrej.c->er_cmd = ELS_LS_RJT;
 	ha->elsrej.c->er_reason = ELS_RJT_LOGIC;
 	ha->elsrej.c->er_explan = ELS_EXPL_UNAB_DATA;
+
+	ha->lsrjt.size = sizeof(struct fcnvme_ls_rjt);
+	ha->lsrjt.c = dma_alloc_coherent(&ha->pdev->dev, ha->lsrjt.size,
+			&ha->lsrjt.cdma, GFP_KERNEL);
+	if (!ha->lsrjt.c) {
+		ql_dbg_pci(ql_dbg_init, ha->pdev, 0xffff,
+			   "Alloc failed for nvme fc reject cmd.\n");
+		goto fail_lsrjt;
+	}
+
 	return 0;
 
+fail_lsrjt:
+	dma_free_coherent(&ha->pdev->dev, ha->elsrej.size,
+			  ha->elsrej.c, ha->elsrej.cdma);
 fail_elsrej:
 	dma_pool_destroy(ha->purex_dma_pool);
 fail_flt:
@@ -4998,6 +5012,12 @@ qla2x00_mem_free(struct qla_hw_data *ha)
 		ha->elsrej.c = NULL;
 	}
 
+	if (ha->lsrjt.c) {
+		dma_free_coherent(&ha->pdev->dev, ha->lsrjt.size, ha->lsrjt.c,
+				  ha->lsrjt.cdma);
+		ha->lsrjt.c = NULL;
+	}
+
 	ha->init_cb = NULL;
 	ha->init_cb_dma = 0;
 
diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h
index 4109f1bd6128..f6ef8cf5d774 100644
--- a/include/linux/nvme-fc-driver.h
+++ b/include/linux/nvme-fc-driver.h
@@ -53,10 +53,10 @@
 struct nvmefc_ls_req {
 	void			*rqstaddr;
 	dma_addr_t		rqstdma;
-	u32			rqstlen;
+	__le32			rqstlen;
 	void			*rspaddr;
 	dma_addr_t		rspdma;
-	u32			rsplen;
+	__le32			rsplen;
 	u32			timeout;
 
 	void			*private;
@@ -120,7 +120,7 @@ struct nvmefc_ls_req {
 struct nvmefc_ls_rsp {
 	void		*rspbuf;
 	dma_addr_t	rspdma;
-	u16		rsplen;
+	__le32		rsplen;
 
 	void (*done)(struct nvmefc_ls_rsp *rsp);
 	void		*nvme_fc_private;	/* LLDD is not to access !! */

From 6d0b65569c0a10b27c49bacd8d25bcd406003533 Mon Sep 17 00:00:00 2001
From: Quinn Tran <qutran@marvell.com>
Date: Mon, 21 Aug 2023 18:30:38 +0530
Subject: [PATCH 0576/1189] scsi: qla2xxx: Flush mailbox commands on chip reset

Fix race condition between Interrupt thread and Chip reset thread in trying
to flush the same mailbox. With the race condition, the "ha->mbx_intr_comp"
will get an extra complete() call. The extra complete call create erroneous
mailbox timeout condition when the next mailbox is sent where the mailbox
call does not wait for interrupt to arrive. Instead, it advances without
waiting.

Add lock protection around the check for mailbox completion.

Cc: stable@vger.kernel.org
Fixes: b2000805a975 ("scsi: qla2xxx: Flush mailbox commands on chip reset")
Signed-off-by: Quinn Tran <quinn.tran@marvell.com>
Signed-off-by: Nilesh Javali <njavali@marvell.com>
Link: https://lore.kernel.org/r/20230821130045.34850-3-njavali@marvell.com
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_def.h  | 1 -
 drivers/scsi/qla2xxx/qla_init.c | 7 ++++---
 drivers/scsi/qla2xxx/qla_mbx.c  | 4 ----
 drivers/scsi/qla2xxx/qla_os.c   | 1 -
 4 files changed, 4 insertions(+), 9 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 2007d5bb5f9f..f1cf921068e3 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -4418,7 +4418,6 @@ struct qla_hw_data {
 	uint8_t		aen_mbx_count;
 	atomic_t	num_pend_mbx_stage1;
 	atomic_t	num_pend_mbx_stage2;
-	atomic_t	num_pend_mbx_stage3;
 	uint16_t	frame_payload_size;
 
 	uint32_t	login_retry_count;
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 27644957ae4e..d38b77a29637 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -7391,14 +7391,15 @@ qla2x00_abort_isp_cleanup(scsi_qla_host_t *vha)
 	}
 
 	/* purge MBox commands */
-	if (atomic_read(&ha->num_pend_mbx_stage3)) {
+	spin_lock_irqsave(&ha->hardware_lock, flags);
+	if (test_bit(MBX_INTR_WAIT, &ha->mbx_cmd_flags)) {
 		clear_bit(MBX_INTR_WAIT, &ha->mbx_cmd_flags);
 		complete(&ha->mbx_intr_comp);
 	}
+	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
 	i = 0;
-	while (atomic_read(&ha->num_pend_mbx_stage3) ||
-	    atomic_read(&ha->num_pend_mbx_stage2) ||
+	while (atomic_read(&ha->num_pend_mbx_stage2) ||
 	    atomic_read(&ha->num_pend_mbx_stage1)) {
 		msleep(20);
 		i++;
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index b05f93037875..21ec32b4fb28 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -273,7 +273,6 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 		spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
 		wait_time = jiffies;
-		atomic_inc(&ha->num_pend_mbx_stage3);
 		if (!wait_for_completion_timeout(&ha->mbx_intr_comp,
 		    mcp->tov * HZ)) {
 			ql_dbg(ql_dbg_mbx, vha, 0x117a,
@@ -290,7 +289,6 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 				spin_unlock_irqrestore(&ha->hardware_lock,
 				    flags);
 				atomic_dec(&ha->num_pend_mbx_stage2);
-				atomic_dec(&ha->num_pend_mbx_stage3);
 				rval = QLA_ABORTED;
 				goto premature_exit;
 			}
@@ -302,11 +300,9 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 			ha->flags.mbox_busy = 0;
 			spin_unlock_irqrestore(&ha->hardware_lock, flags);
 			atomic_dec(&ha->num_pend_mbx_stage2);
-			atomic_dec(&ha->num_pend_mbx_stage3);
 			rval = QLA_ABORTED;
 			goto premature_exit;
 		}
-		atomic_dec(&ha->num_pend_mbx_stage3);
 
 		if (time_after(jiffies, wait_time + 5 * HZ))
 			ql_log(ql_log_warn, vha, 0x1015, "cmd=0x%x, waited %d msecs\n",
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index aa492489a4b8..e380634c8e25 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -3008,7 +3008,6 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	ha->max_exchg = FW_MAX_EXCHANGES_CNT;
 	atomic_set(&ha->num_pend_mbx_stage1, 0);
 	atomic_set(&ha->num_pend_mbx_stage2, 0);
-	atomic_set(&ha->num_pend_mbx_stage3, 0);
 	atomic_set(&ha->zio_threshold, DEFAULT_ZIO_THRESHOLD);
 	ha->last_zio_threshold = DEFAULT_ZIO_THRESHOLD;
 	INIT_LIST_HEAD(&ha->tmf_pending);

From e370b64c7db96384a0886a09a9d80406e4c663d7 Mon Sep 17 00:00:00 2001
From: Quinn Tran <qutran@marvell.com>
Date: Mon, 21 Aug 2023 18:30:39 +0530
Subject: [PATCH 0577/1189] scsi: qla2xxx: Fix firmware resource tracking

The storage was not draining I/Os and the work load was not spread out
across different CPUs evenly. This led to firmware resource counters
getting overrun on the busy CPU. This overrun prevented error recovery from
happening in a timely manner.

By switching the counter to atomic, it allows the count to be little more
accurate to prevent the overrun.

Cc: stable@vger.kernel.org
Fixes: da7c21b72aa8 ("scsi: qla2xxx: Fix command flush during TMF")
Signed-off-by: Quinn Tran <qutran@marvell.com>
Signed-off-by: Nilesh Javali <njavali@marvell.com>
Link: https://lore.kernel.org/r/20230821130045.34850-4-njavali@marvell.com
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_def.h    | 11 ++++++
 drivers/scsi/qla2xxx/qla_dfs.c    | 10 ++++++
 drivers/scsi/qla2xxx/qla_init.c   |  8 +++++
 drivers/scsi/qla2xxx/qla_inline.h | 57 ++++++++++++++++++++++++++++++-
 drivers/scsi/qla2xxx/qla_os.c     |  5 +--
 5 files changed, 88 insertions(+), 3 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index f1cf921068e3..9ec39bcd41b5 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -3770,6 +3770,16 @@ struct qla_fw_resources {
 	u16 pad;
 };
 
+struct qla_fw_res {
+	u16      iocb_total;
+	u16      iocb_limit;
+	atomic_t iocb_used;
+
+	u16      exch_total;
+	u16      exch_limit;
+	atomic_t exch_used;
+};
+
 #define QLA_IOCB_PCT_LIMIT 95
 
 struct  qla_buf_pool {
@@ -4830,6 +4840,7 @@ struct qla_hw_data {
 	u8 edif_post_stop_cnt_down;
 	struct qla_vp_map *vp_map;
 	struct qla_nvme_fc_rjt lsrjt;
+	struct qla_fw_res fwres ____cacheline_aligned;
 };
 
 #define RX_ELS_SIZE (roundup(sizeof(struct enode) + ELS_MAX_PAYLOAD, SMP_CACHE_BYTES))
diff --git a/drivers/scsi/qla2xxx/qla_dfs.c b/drivers/scsi/qla2xxx/qla_dfs.c
index 1925cc6897b6..f060e593685d 100644
--- a/drivers/scsi/qla2xxx/qla_dfs.c
+++ b/drivers/scsi/qla2xxx/qla_dfs.c
@@ -276,6 +276,16 @@ qla_dfs_fw_resource_cnt_show(struct seq_file *s, void *unused)
 
 		seq_printf(s, "estimate exchange used[%d] high water limit [%d] n",
 			   exch_used, ha->base_qpair->fwres.exch_limit);
+
+		if (ql2xenforce_iocb_limit == 2) {
+			iocbs_used = atomic_read(&ha->fwres.iocb_used);
+			exch_used  = atomic_read(&ha->fwres.exch_used);
+			seq_printf(s, "        estimate iocb2 used [%d] high water limit [%d]\n",
+					iocbs_used, ha->fwres.iocb_limit);
+
+			seq_printf(s, "        estimate exchange2 used[%d] high water limit [%d] \n",
+					exch_used, ha->fwres.exch_limit);
+		}
 	}
 
 	return 0;
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index d38b77a29637..d9a7d63001bd 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -4214,6 +4214,14 @@ void qla_init_iocb_limit(scsi_qla_host_t *vha)
 			ha->queue_pair_map[i]->fwres.exch_used = 0;
 		}
 	}
+
+	ha->fwres.iocb_total = ha->orig_fw_iocb_count;
+	ha->fwres.iocb_limit = (ha->orig_fw_iocb_count * QLA_IOCB_PCT_LIMIT) / 100;
+	ha->fwres.exch_total = ha->orig_fw_xcb_count;
+	ha->fwres.exch_limit = (ha->orig_fw_xcb_count * QLA_IOCB_PCT_LIMIT) / 100;
+
+	atomic_set(&ha->fwres.iocb_used, 0);
+	atomic_set(&ha->fwres.exch_used, 0);
 }
 
 void qla_adjust_iocb_limit(scsi_qla_host_t *vha)
diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h
index 0167e85ba058..0556969f6dc1 100644
--- a/drivers/scsi/qla2xxx/qla_inline.h
+++ b/drivers/scsi/qla2xxx/qla_inline.h
@@ -386,6 +386,7 @@ enum {
 	RESOURCE_IOCB = BIT_0,
 	RESOURCE_EXCH = BIT_1,  /* exchange */
 	RESOURCE_FORCE = BIT_2,
+	RESOURCE_HA = BIT_3,
 };
 
 static inline int
@@ -393,7 +394,7 @@ qla_get_fw_resources(struct qla_qpair *qp, struct iocb_resource *iores)
 {
 	u16 iocbs_used, i;
 	u16 exch_used;
-	struct qla_hw_data *ha = qp->vha->hw;
+	struct qla_hw_data *ha = qp->hw;
 
 	if (!ql2xenforce_iocb_limit) {
 		iores->res_type = RESOURCE_NONE;
@@ -428,15 +429,69 @@ qla_get_fw_resources(struct qla_qpair *qp, struct iocb_resource *iores)
 			return -ENOSPC;
 		}
 	}
+
+	if (ql2xenforce_iocb_limit == 2) {
+		if ((iores->iocb_cnt + atomic_read(&ha->fwres.iocb_used)) >=
+		    ha->fwres.iocb_limit) {
+			iores->res_type = RESOURCE_NONE;
+			return -ENOSPC;
+		}
+
+		if (iores->res_type & RESOURCE_EXCH) {
+			if ((iores->exch_cnt + atomic_read(&ha->fwres.exch_used)) >=
+			    ha->fwres.exch_limit) {
+				iores->res_type = RESOURCE_NONE;
+				return -ENOSPC;
+			}
+		}
+	}
+
 force:
 	qp->fwres.iocbs_used += iores->iocb_cnt;
 	qp->fwres.exch_used += iores->exch_cnt;
+	if (ql2xenforce_iocb_limit == 2) {
+		atomic_add(iores->iocb_cnt, &ha->fwres.iocb_used);
+		atomic_add(iores->exch_cnt, &ha->fwres.exch_used);
+		iores->res_type |= RESOURCE_HA;
+	}
 	return 0;
 }
 
+/*
+ * decrement to zero.  This routine will not decrement below zero
+ * @v:  pointer of type atomic_t
+ * @amount: amount to decrement from v
+ */
+static void qla_atomic_dtz(atomic_t *v, int amount)
+{
+	int c, old, dec;
+
+	c = atomic_read(v);
+	for (;;) {
+		dec = c - amount;
+		if (unlikely(dec < 0))
+			dec = 0;
+
+		old = atomic_cmpxchg((v), c, dec);
+		if (likely(old == c))
+			break;
+		c = old;
+	}
+}
+
 static inline void
 qla_put_fw_resources(struct qla_qpair *qp, struct iocb_resource *iores)
 {
+	struct qla_hw_data *ha = qp->hw;
+
+	if (iores->res_type & RESOURCE_HA) {
+		if (iores->res_type & RESOURCE_IOCB)
+			qla_atomic_dtz(&ha->fwres.iocb_used, iores->iocb_cnt);
+
+		if (iores->res_type & RESOURCE_EXCH)
+			qla_atomic_dtz(&ha->fwres.exch_used, iores->exch_cnt);
+	}
+
 	if (iores->res_type & RESOURCE_IOCB) {
 		if (qp->fwres.iocbs_used >= iores->iocb_cnt) {
 			qp->fwres.iocbs_used -= iores->iocb_cnt;
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index e380634c8e25..9311d1b19532 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -44,10 +44,11 @@ module_param(ql2xfulldump_on_mpifail, int, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(ql2xfulldump_on_mpifail,
 		 "Set this to take full dump on MPI hang.");
 
-int ql2xenforce_iocb_limit = 1;
+int ql2xenforce_iocb_limit = 2;
 module_param(ql2xenforce_iocb_limit, int, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(ql2xenforce_iocb_limit,
-		 "Enforce IOCB throttling, to avoid FW congestion. (default: 1)");
+		 "Enforce IOCB throttling, to avoid FW congestion. (default: 2) "
+		 "1: track usage per queue, 2: track usage per adapter");
 
 /*
  * CT6 CTX allocation cache

From cd248a95f86df2523056ef8ad895e8ee0c17be53 Mon Sep 17 00:00:00 2001
From: Bikash Hazarika <bhazarika@marvell.com>
Date: Mon, 21 Aug 2023 18:30:40 +0530
Subject: [PATCH 0578/1189] scsi: qla2xxx: Add logs for SFP temperature
 monitoring

Add logs for SFP Temperature Alert async event to check if laser is
enabled/disabled.

Signed-off-by: Bikash Hazarika <bhazarika@marvell.com>
Signed-off-by: Nilesh Javali <njavali@marvell.com>
Link: https://lore.kernel.org/r/20230821130045.34850-5-njavali@marvell.com
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_isr.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 867025c89909..e98788191897 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -56,6 +56,22 @@ const char *const port_state_str[] = {
 	[FCS_ONLINE]		= "ONLINE"
 };
 
+#define SFP_DISABLE_LASER_INITIATED    0x15  /* Sub code of 8070 AEN */
+#define SFP_ENABLE_LASER_INITIATED     0x16  /* Sub code of 8070 AEN */
+
+static inline void display_Laser_info(scsi_qla_host_t *vha,
+				      u16 mb1, u16 mb2, u16 mb3) {
+
+	if (mb1 == SFP_DISABLE_LASER_INITIATED)
+		ql_log(ql_log_warn, vha, 0xf0a2,
+		       "SFP temperature (%d C) reached/exceeded the threshold (%d C). Laser is disabled.\n",
+		       mb3, mb2);
+	if (mb1 == SFP_ENABLE_LASER_INITIATED)
+		ql_log(ql_log_warn, vha, 0xf0a3,
+		       "SFP temperature (%d C) reached normal operating level. Laser is enabled.\n",
+		       mb3);
+}
+
 static void
 qla24xx_process_abts(struct scsi_qla_host *vha, struct purex_item *pkt)
 {
@@ -1927,6 +1943,8 @@ global_port_update:
 		break;
 
 	case MBA_TEMPERATURE_ALERT:
+		if (IS_QLA27XX(ha) || IS_QLA28XX(ha))
+			display_Laser_info(vha, mb[1], mb[2], mb[3]);
 		ql_dbg(ql_dbg_async, vha, 0x505e,
 		    "TEMPERATURE ALERT: %04x %04x %04x\n", mb[1], mb[2], mb[3]);
 		break;

From 0ba0b018f94525a6b32f5930f980ce9b62b72e6f Mon Sep 17 00:00:00 2001
From: Quinn Tran <qutran@marvell.com>
Date: Mon, 21 Aug 2023 18:30:41 +0530
Subject: [PATCH 0579/1189] scsi: qla2xxx: Error code did not return to upper
 layer

TMF was returned with an error code. The error code was not preserved to be
returned to upper layer. Instead, the error code from the Marker was
returned.

Preserve error code from TMF and return it to upper layer.

Cc: stable@vger.kernel.org
Fixes: da7c21b72aa8 ("scsi: qla2xxx: Fix command flush during TMF")
Signed-off-by: Quinn Tran <qutran@marvell.com>
Signed-off-by: Nilesh Javali <njavali@marvell.com>
Link: https://lore.kernel.org/r/20230821130045.34850-6-njavali@marvell.com
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_init.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index d9a7d63001bd..e733be74de16 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -2223,6 +2223,8 @@ __qla2x00_async_tm_cmd(struct tmf_arg *arg)
 			rval = QLA_FUNCTION_FAILED;
 		}
 	}
+	if (tm_iocb->u.tmf.data)
+		rval = tm_iocb->u.tmf.data;
 
 done_free_sp:
 	/* ref: INIT */

From e9105c4b7a9208a21a9bda133707624f12ddabc2 Mon Sep 17 00:00:00 2001
From: Manish Rangankar <mrangankar@marvell.com>
Date: Mon, 21 Aug 2023 18:30:42 +0530
Subject: [PATCH 0580/1189] scsi: qla2xxx: Remove unsupported ql2xenabledif
 option

User accidently passed module parameter ql2xenabledif=1 which is
unsupported. However, driver still initialized which lead to guard tag
errors during device discovery.

Remove unsupported ql2xenabledif=1 option and validate the user input.

Cc: stable@vger.kernel.org
Signed-off-by: Manish Rangankar <mrangankar@marvell.com>
Signed-off-by: Nilesh Javali <njavali@marvell.com>
Link: https://lore.kernel.org/r/20230821130045.34850-7-njavali@marvell.com
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_attr.c | 2 --
 drivers/scsi/qla2xxx/qla_dbg.c  | 2 +-
 drivers/scsi/qla2xxx/qla_os.c   | 9 +++++++--
 3 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index b00222459607..44449c70a375 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -3093,8 +3093,6 @@ qla24xx_vport_create(struct fc_vport *fc_vport, bool disable)
 			vha->flags.difdix_supported = 1;
 			ql_dbg(ql_dbg_user, vha, 0x7082,
 			    "Registered for DIF/DIX type 1 and 3 protection.\n");
-			if (ql2xenabledif == 1)
-				prot = SHOST_DIX_TYPE0_PROTECTION;
 			scsi_host_set_prot(vha->host,
 			    prot | SHOST_DIF_TYPE1_PROTECTION
 			    | SHOST_DIF_TYPE2_PROTECTION
diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c
index 4d104425146b..691ef827a5ab 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.c
+++ b/drivers/scsi/qla2xxx/qla_dbg.c
@@ -17,7 +17,7 @@
  * | Queue Command and IO tracing |       0x3074       | 0x300b         |
  * |                              |                    | 0x3027-0x3028  |
  * |                              |                    | 0x303d-0x3041  |
- * |                              |                    | 0x302d,0x3033  |
+ * |                              |                    | 0x302e,0x3033  |
  * |                              |                    | 0x3036,0x3038  |
  * |                              |                    | 0x303a		|
  * | DPC Thread                   |       0x4023       | 0x4002,0x4013  |
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 9311d1b19532..50db08265c51 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -3289,6 +3289,13 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	host->max_id = ha->max_fibre_devices;
 	host->cmd_per_lun = 3;
 	host->unique_id = host->host_no;
+
+	if (ql2xenabledif && ql2xenabledif != 2) {
+		ql_log(ql_log_warn, base_vha, 0x302d,
+		       "Invalid value for ql2xenabledif, resetting it to default (2)\n");
+		ql2xenabledif = 2;
+	}
+
 	if (IS_T10_PI_CAPABLE(ha) && ql2xenabledif)
 		host->max_cmd_len = 32;
 	else
@@ -3525,8 +3532,6 @@ skip_dpc:
 			base_vha->flags.difdix_supported = 1;
 			ql_dbg(ql_dbg_init, base_vha, 0x00f1,
 			    "Registering for DIF/DIX type 1 and 3 protection.\n");
-			if (ql2xenabledif == 1)
-				prot = SHOST_DIX_TYPE0_PROTECTION;
 			if (ql2xprotmask)
 				scsi_host_set_prot(host, ql2xprotmask);
 			else

From b496953dd0444001b12f425ea07d78c1f47e3193 Mon Sep 17 00:00:00 2001
From: Nilesh Javali <njavali@marvell.com>
Date: Mon, 21 Aug 2023 18:30:43 +0530
Subject: [PATCH 0581/1189] scsi: qla2xxx: Fix smatch warn for
 qla_init_iocb_limit()

Fix indentation for warning reported by smatch:

drivers/scsi/qla2xxx/qla_init.c:4199 qla_init_iocb_limit() warn: inconsistent indenting

Fixes: efa74a62aaa2 ("scsi: qla2xxx: Adjust IOCB resource on qpair create")
Signed-off-by: Nilesh Javali <njavali@marvell.com>
Link: https://lore.kernel.org/r/20230821130045.34850-8-njavali@marvell.com
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_init.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index e733be74de16..df2c69c08137 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -4205,7 +4205,7 @@ void qla_init_iocb_limit(scsi_qla_host_t *vha)
 	u8 i;
 	struct qla_hw_data *ha = vha->hw;
 
-	 __qla_adjust_iocb_limit(ha->base_qpair);
+	__qla_adjust_iocb_limit(ha->base_qpair);
 	ha->base_qpair->fwres.iocbs_used = 0;
 	ha->base_qpair->fwres.exch_used  = 0;
 

From 641671d97b9199f1ba35ccc2222d4b189a6a5de5 Mon Sep 17 00:00:00 2001
From: Nilesh Javali <njavali@marvell.com>
Date: Mon, 21 Aug 2023 18:30:44 +0530
Subject: [PATCH 0582/1189] Revert "scsi: qla2xxx: Fix buffer overrun"

Revert due to Get PLOGI Template failed.
This reverts commit b68710a8094fdffe8dd4f7a82c82649f479bb453.

Cc: stable@vger.kernel.org
Signed-off-by: Nilesh Javali <njavali@marvell.com>
Link: https://lore.kernel.org/r/20230821130045.34850-9-njavali@marvell.com
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_init.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index df2c69c08137..82077edfda1f 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -5607,7 +5607,7 @@ static void qla_get_login_template(scsi_qla_host_t *vha)
 	__be32 *q;
 
 	memset(ha->init_cb, 0, ha->init_cb_size);
-	sz = min_t(int, sizeof(struct fc_els_csp), ha->init_cb_size);
+	sz = min_t(int, sizeof(struct fc_els_flogi), ha->init_cb_size);
 	rval = qla24xx_get_port_login_templ(vha, ha->init_cb_dma,
 					    ha->init_cb, sz);
 	if (rval != QLA_SUCCESS) {

From cc6e67e60fe749ee6aa1c92000c372e0e6ad7ae1 Mon Sep 17 00:00:00 2001
From: Nilesh Javali <njavali@marvell.com>
Date: Mon, 21 Aug 2023 18:30:45 +0530
Subject: [PATCH 0583/1189] scsi: qla2xxx: Update version to 10.02.09.100-k

Signed-off-by: Nilesh Javali <njavali@marvell.com>
Link: https://lore.kernel.org/r/20230821130045.34850-10-njavali@marvell.com
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_version.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_version.h b/drivers/scsi/qla2xxx/qla_version.h
index 81bdf6b03241..d903563e969e 100644
--- a/drivers/scsi/qla2xxx/qla_version.h
+++ b/drivers/scsi/qla2xxx/qla_version.h
@@ -6,9 +6,9 @@
 /*
  * Driver version
  */
-#define QLA2XXX_VERSION      "10.02.08.500-k"
+#define QLA2XXX_VERSION      "10.02.09.100-k"
 
 #define QLA_DRIVER_MAJOR_VER	10
 #define QLA_DRIVER_MINOR_VER	2
-#define QLA_DRIVER_PATCH_VER	8
-#define QLA_DRIVER_BETA_VER	500
+#define QLA_DRIVER_PATCH_VER	9
+#define QLA_DRIVER_BETA_VER	100

From 08b8a0440eeec83f8330349f829908858fd52d31 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Mon, 14 Mar 2022 15:47:18 -0400
Subject: [PATCH 0584/1189] libceph: add spinlock around osd->o_requests
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In a later patch, we're going to need to search for a request in
the rbtree, but taking the o_mutex is inconvenient as we already
hold the con mutex at the point where we need it.

Add a new spinlock that we take when inserting and erasing entries from
the o_requests tree. Search of the rbtree can be done with either the
mutex or the spinlock, but insertion and removal requires both.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/osd_client.h | 8 +++++++-
 net/ceph/osd_client.c           | 5 +++++
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index fb6be72104df..92addef18738 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -29,7 +29,12 @@ typedef void (*ceph_osdc_callback_t)(struct ceph_osd_request *);
 
 #define CEPH_HOMELESS_OSD	-1
 
-/* a given osd we're communicating with */
+/*
+ * A given osd we're communicating with.
+ *
+ * Note that the o_requests tree can be searched while holding the "lock" mutex
+ * or the "o_requests_lock" spinlock. Insertion or removal requires both!
+ */
 struct ceph_osd {
 	refcount_t o_ref;
 	struct ceph_osd_client *o_osdc;
@@ -37,6 +42,7 @@ struct ceph_osd {
 	int o_incarnation;
 	struct rb_node o_node;
 	struct ceph_connection o_con;
+	spinlock_t o_requests_lock;
 	struct rb_root o_requests;
 	struct rb_root o_linger_requests;
 	struct rb_root o_backoff_mappings;
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 658a6f2320cf..6d7a430bfed8 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1177,6 +1177,7 @@ static void osd_init(struct ceph_osd *osd)
 {
 	refcount_set(&osd->o_ref, 1);
 	RB_CLEAR_NODE(&osd->o_node);
+	spin_lock_init(&osd->o_requests_lock);
 	osd->o_requests = RB_ROOT;
 	osd->o_linger_requests = RB_ROOT;
 	osd->o_backoff_mappings = RB_ROOT;
@@ -1406,7 +1407,9 @@ static void link_request(struct ceph_osd *osd, struct ceph_osd_request *req)
 		atomic_inc(&osd->o_osdc->num_homeless);
 
 	get_osd(osd);
+	spin_lock(&osd->o_requests_lock);
 	insert_request(&osd->o_requests, req);
+	spin_unlock(&osd->o_requests_lock);
 	req->r_osd = osd;
 }
 
@@ -1418,7 +1421,9 @@ static void unlink_request(struct ceph_osd *osd, struct ceph_osd_request *req)
 	     req, req->r_tid);
 
 	req->r_osd = NULL;
+	spin_lock(&osd->o_requests_lock);
 	erase_request(&osd->o_requests, req);
+	spin_unlock(&osd->o_requests_lock);
 	put_osd(osd);
 
 	if (!osd_homeless(osd))

From a679e50f728648f7b2f3b349e082448abd388038 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Wed, 16 Mar 2022 15:23:00 -0400
Subject: [PATCH 0585/1189] libceph: define struct ceph_sparse_extent and add
 some helpers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When the OSD sends back a sparse read reply, it contains an array of
these structures. Define the structure and add a couple of helpers for
dealing with them.

Also add a place in struct ceph_osd_req_op to store the extent buffer,
and code to free it if it's populated when the req is torn down.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/osd_client.h | 43 ++++++++++++++++++++++++++++++++-
 net/ceph/osd_client.c           | 13 ++++++++++
 2 files changed, 55 insertions(+), 1 deletion(-)

diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 92addef18738..05da1e755b7b 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -29,6 +29,17 @@ typedef void (*ceph_osdc_callback_t)(struct ceph_osd_request *);
 
 #define CEPH_HOMELESS_OSD	-1
 
+/*
+ * A single extent in a SPARSE_READ reply.
+ *
+ * Note that these come from the OSD as little-endian values. On BE arches,
+ * we convert them in-place after receipt.
+ */
+struct ceph_sparse_extent {
+	u64	off;
+	u64	len;
+} __packed;
+
 /*
  * A given osd we're communicating with.
  *
@@ -104,6 +115,8 @@ struct ceph_osd_req_op {
 			u64 offset, length;
 			u64 truncate_size;
 			u32 truncate_seq;
+			int sparse_ext_cnt;
+			struct ceph_sparse_extent *sparse_ext;
 			struct ceph_osd_data osd_data;
 		} extent;
 		struct {
@@ -510,6 +523,20 @@ extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *,
 				      u32 truncate_seq, u64 truncate_size,
 				      bool use_mempool);
 
+int __ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op, int cnt);
+
+/*
+ * How big an extent array should we preallocate for a sparse read? This is
+ * just a starting value.  If we get more than this back from the OSD, the
+ * receiver will reallocate.
+ */
+#define CEPH_SPARSE_EXT_ARRAY_INITIAL  16
+
+static inline int ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op)
+{
+	return __ceph_alloc_sparse_ext_map(op, CEPH_SPARSE_EXT_ARRAY_INITIAL);
+}
+
 extern void ceph_osdc_get_request(struct ceph_osd_request *req);
 extern void ceph_osdc_put_request(struct ceph_osd_request *req);
 
@@ -564,5 +591,19 @@ int ceph_osdc_list_watchers(struct ceph_osd_client *osdc,
 			    struct ceph_object_locator *oloc,
 			    struct ceph_watch_item **watchers,
 			    u32 *num_watchers);
-#endif
 
+/* Find offset into the buffer of the end of the extent map */
+static inline u64 ceph_sparse_ext_map_end(struct ceph_osd_req_op *op)
+{
+	struct ceph_sparse_extent *ext;
+
+	/* No extents? No data */
+	if (op->extent.sparse_ext_cnt == 0)
+		return 0;
+
+	ext = &op->extent.sparse_ext[op->extent.sparse_ext_cnt - 1];
+
+	return ext->off + ext->len - op->extent.offset;
+}
+
+#endif
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 6d7a430bfed8..3e03ae68722c 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -378,6 +378,7 @@ static void osd_req_op_data_release(struct ceph_osd_request *osd_req,
 	case CEPH_OSD_OP_READ:
 	case CEPH_OSD_OP_WRITE:
 	case CEPH_OSD_OP_WRITEFULL:
+		kfree(op->extent.sparse_ext);
 		ceph_osd_data_release(&op->extent.osd_data);
 		break;
 	case CEPH_OSD_OP_CALL:
@@ -1120,6 +1121,18 @@ fail:
 }
 EXPORT_SYMBOL(ceph_osdc_new_request);
 
+int __ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op, int cnt)
+{
+	op->extent.sparse_ext_cnt = cnt;
+	op->extent.sparse_ext = kmalloc_array(cnt,
+					      sizeof(*op->extent.sparse_ext),
+					      GFP_NOFS);
+	if (!op->extent.sparse_ext)
+		return -ENOMEM;
+	return 0;
+}
+EXPORT_SYMBOL(__ceph_alloc_sparse_ext_map);
+
 /*
  * We keep osd requests in an rbtree, sorted by ->r_tid.
  */

From ec3bc567eac12c557a2b99bd0b34b5dff12cab23 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Tue, 25 Jan 2022 08:26:31 -0500
Subject: [PATCH 0586/1189] libceph: new sparse_read op, support sparse reads
 on msgr2 crc codepath
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add support for a new sparse_read ceph_connection operation. The idea is
that the client driver can define this operation use it to do special
handling for incoming reads.

The alloc_msg routine will look at the request and determine whether the
reply is expected to be sparse. If it is, then we'll dispatch to a
different set of state machine states that will repeatedly call the
driver's sparse_read op to get length and placement info for reading the
extent map, and the extents themselves.

This necessitates adding some new field to some other structs:

- The msg gets a new bool to track whether it's a sparse_read request.

- A new field is added to the cursor to track the amount remaining in the
current extent. This is used to cap the read from the socket into the
msg_data

- Handing a revoke with all of this is particularly difficult, so I've
added a new data_len_remain field to the v2 connection info, and then
use that to skip that much on a revoke. We may want to expand the use of
that to the normal read path as well, just for consistency's sake.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/messenger.h |  28 ++++++
 net/ceph/messenger.c           |   1 +
 net/ceph/messenger_v2.c        | 167 +++++++++++++++++++++++++++++++--
 3 files changed, 187 insertions(+), 9 deletions(-)

diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 99c1726be6ee..8a6938fa324e 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -17,6 +17,7 @@
 
 struct ceph_msg;
 struct ceph_connection;
+struct ceph_msg_data_cursor;
 
 /*
  * Ceph defines these callbacks for handling connection events.
@@ -70,6 +71,30 @@ struct ceph_connection_operations {
 				      int used_proto, int result,
 				      const int *allowed_protos, int proto_cnt,
 				      const int *allowed_modes, int mode_cnt);
+
+	/**
+	 * sparse_read: read sparse data
+	 * @con: connection we're reading from
+	 * @cursor: data cursor for reading extents
+	 * @buf: optional buffer to read into
+	 *
+	 * This should be called more than once, each time setting up to
+	 * receive an extent into the current cursor position, and zeroing
+	 * the holes between them.
+	 *
+	 * Returns amount of data to be read (in bytes), 0 if reading is
+	 * complete, or -errno if there was an error.
+	 *
+	 * If @buf is set on a >0 return, then the data should be read into
+	 * the provided buffer. Otherwise, it should be read into the cursor.
+	 *
+	 * The sparse read operation is expected to initialize the cursor
+	 * with a length covering up to the end of the last extent.
+	 */
+	int (*sparse_read)(struct ceph_connection *con,
+			   struct ceph_msg_data_cursor *cursor,
+			   char **buf);
+
 };
 
 /* use format string %s%lld */
@@ -207,6 +232,7 @@ struct ceph_msg_data_cursor {
 
 	struct ceph_msg_data	*data;		/* current data item */
 	size_t			resid;		/* bytes not yet consumed */
+	int			sr_resid;	/* residual sparse_read len */
 	bool			need_crc;	/* crc update needed */
 	union {
 #ifdef CONFIG_BLOCK
@@ -251,6 +277,7 @@ struct ceph_msg {
 	struct kref kref;
 	bool more_to_follow;
 	bool needs_out_seq;
+	bool sparse_read;
 	int front_alloc_len;
 
 	struct ceph_msgpool *pool;
@@ -395,6 +422,7 @@ struct ceph_connection_v2_info {
 
 	void *conn_bufs[16];
 	int conn_buf_cnt;
+	int data_len_remain;
 
 	struct kvec in_sign_kvecs[8];
 	struct kvec out_sign_kvecs[8];
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 5eb4898cccd4..2eb10d7518e8 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -1013,6 +1013,7 @@ void ceph_msg_data_cursor_init(struct ceph_msg_data_cursor *cursor,
 
 	cursor->total_resid = length;
 	cursor->data = msg->data;
+	cursor->sr_resid = 0;
 
 	__ceph_msg_data_cursor_init(cursor);
 }
diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index 1df1d29dee92..17c9a858bfbd 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -52,14 +52,16 @@
 #define FRAME_LATE_STATUS_COMPLETE	0xe
 #define FRAME_LATE_STATUS_ABORTED_MASK	0xf
 
-#define IN_S_HANDLE_PREAMBLE		1
-#define IN_S_HANDLE_CONTROL		2
-#define IN_S_HANDLE_CONTROL_REMAINDER	3
-#define IN_S_PREPARE_READ_DATA		4
-#define IN_S_PREPARE_READ_DATA_CONT	5
-#define IN_S_PREPARE_READ_ENC_PAGE	6
-#define IN_S_HANDLE_EPILOGUE		7
-#define IN_S_FINISH_SKIP		8
+#define IN_S_HANDLE_PREAMBLE			1
+#define IN_S_HANDLE_CONTROL			2
+#define IN_S_HANDLE_CONTROL_REMAINDER		3
+#define IN_S_PREPARE_READ_DATA			4
+#define IN_S_PREPARE_READ_DATA_CONT		5
+#define IN_S_PREPARE_READ_ENC_PAGE		6
+#define IN_S_PREPARE_SPARSE_DATA		7
+#define IN_S_PREPARE_SPARSE_DATA_CONT		8
+#define IN_S_HANDLE_EPILOGUE			9
+#define IN_S_FINISH_SKIP			10
 
 #define OUT_S_QUEUE_DATA		1
 #define OUT_S_QUEUE_DATA_CONT		2
@@ -1825,6 +1827,123 @@ static void prepare_read_data_cont(struct ceph_connection *con)
 	con->v2.in_state = IN_S_HANDLE_EPILOGUE;
 }
 
+static int prepare_sparse_read_cont(struct ceph_connection *con)
+{
+	int ret;
+	struct bio_vec bv;
+	char *buf = NULL;
+	struct ceph_msg_data_cursor *cursor = &con->v2.in_cursor;
+
+	WARN_ON(con->v2.in_state != IN_S_PREPARE_SPARSE_DATA_CONT);
+
+	if (iov_iter_is_bvec(&con->v2.in_iter)) {
+		if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE)) {
+			con->in_data_crc = crc32c(con->in_data_crc,
+						  page_address(con->bounce_page),
+						  con->v2.in_bvec.bv_len);
+			get_bvec_at(cursor, &bv);
+			memcpy_to_page(bv.bv_page, bv.bv_offset,
+				       page_address(con->bounce_page),
+				       con->v2.in_bvec.bv_len);
+		} else {
+			con->in_data_crc = ceph_crc32c_page(con->in_data_crc,
+							    con->v2.in_bvec.bv_page,
+							    con->v2.in_bvec.bv_offset,
+							    con->v2.in_bvec.bv_len);
+		}
+
+		ceph_msg_data_advance(cursor, con->v2.in_bvec.bv_len);
+		cursor->sr_resid -= con->v2.in_bvec.bv_len;
+		dout("%s: advance by 0x%x sr_resid 0x%x\n", __func__,
+		     con->v2.in_bvec.bv_len, cursor->sr_resid);
+		WARN_ON_ONCE(cursor->sr_resid > cursor->total_resid);
+		if (cursor->sr_resid) {
+			get_bvec_at(cursor, &bv);
+			if (bv.bv_len > cursor->sr_resid)
+				bv.bv_len = cursor->sr_resid;
+			if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE)) {
+				bv.bv_page = con->bounce_page;
+				bv.bv_offset = 0;
+			}
+			set_in_bvec(con, &bv);
+			con->v2.data_len_remain -= bv.bv_len;
+			return 0;
+		}
+	} else if (iov_iter_is_kvec(&con->v2.in_iter)) {
+		/* On first call, we have no kvec so don't compute crc */
+		if (con->v2.in_kvec_cnt) {
+			WARN_ON_ONCE(con->v2.in_kvec_cnt > 1);
+			con->in_data_crc = crc32c(con->in_data_crc,
+						  con->v2.in_kvecs[0].iov_base,
+						  con->v2.in_kvecs[0].iov_len);
+		}
+	} else {
+		return -EIO;
+	}
+
+	/* get next extent */
+	ret = con->ops->sparse_read(con, cursor, &buf);
+	if (ret <= 0) {
+		if (ret < 0)
+			return ret;
+
+		reset_in_kvecs(con);
+		add_in_kvec(con, con->v2.in_buf, CEPH_EPILOGUE_PLAIN_LEN);
+		con->v2.in_state = IN_S_HANDLE_EPILOGUE;
+		return 0;
+	}
+
+	if (buf) {
+		/* receive into buffer */
+		reset_in_kvecs(con);
+		add_in_kvec(con, buf, ret);
+		con->v2.data_len_remain -= ret;
+		return 0;
+	}
+
+	if (ret > cursor->total_resid) {
+		pr_warn("%s: ret 0x%x total_resid 0x%zx resid 0x%zx\n",
+			__func__, ret, cursor->total_resid, cursor->resid);
+		return -EIO;
+	}
+	get_bvec_at(cursor, &bv);
+	if (bv.bv_len > cursor->sr_resid)
+		bv.bv_len = cursor->sr_resid;
+	if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE)) {
+		if (unlikely(!con->bounce_page)) {
+			con->bounce_page = alloc_page(GFP_NOIO);
+			if (!con->bounce_page) {
+				pr_err("failed to allocate bounce page\n");
+				return -ENOMEM;
+			}
+		}
+
+		bv.bv_page = con->bounce_page;
+		bv.bv_offset = 0;
+	}
+	set_in_bvec(con, &bv);
+	con->v2.data_len_remain -= ret;
+	return ret;
+}
+
+static int prepare_sparse_read_data(struct ceph_connection *con)
+{
+	struct ceph_msg *msg = con->in_msg;
+
+	dout("%s: starting sparse read\n", __func__);
+
+	if (WARN_ON_ONCE(!con->ops->sparse_read))
+		return -EOPNOTSUPP;
+
+	if (!con_secure(con))
+		con->in_data_crc = -1;
+
+	reset_in_kvecs(con);
+	con->v2.in_state = IN_S_PREPARE_SPARSE_DATA_CONT;
+	con->v2.data_len_remain = data_len(msg);
+	return prepare_sparse_read_cont(con);
+}
+
 static int prepare_read_tail_plain(struct ceph_connection *con)
 {
 	struct ceph_msg *msg = con->in_msg;
@@ -1845,7 +1964,10 @@ static int prepare_read_tail_plain(struct ceph_connection *con)
 	}
 
 	if (data_len(msg)) {
-		con->v2.in_state = IN_S_PREPARE_READ_DATA;
+		if (msg->sparse_read)
+			con->v2.in_state = IN_S_PREPARE_SPARSE_DATA;
+		else
+			con->v2.in_state = IN_S_PREPARE_READ_DATA;
 	} else {
 		add_in_kvec(con, con->v2.in_buf, CEPH_EPILOGUE_PLAIN_LEN);
 		con->v2.in_state = IN_S_HANDLE_EPILOGUE;
@@ -2898,6 +3020,12 @@ static int populate_in_iter(struct ceph_connection *con)
 			prepare_read_enc_page(con);
 			ret = 0;
 			break;
+		case IN_S_PREPARE_SPARSE_DATA:
+			ret = prepare_sparse_read_data(con);
+			break;
+		case IN_S_PREPARE_SPARSE_DATA_CONT:
+			ret = prepare_sparse_read_cont(con);
+			break;
 		case IN_S_HANDLE_EPILOGUE:
 			ret = handle_epilogue(con);
 			break;
@@ -3489,6 +3617,23 @@ static void revoke_at_prepare_read_enc_page(struct ceph_connection *con)
 	con->v2.in_state = IN_S_FINISH_SKIP;
 }
 
+static void revoke_at_prepare_sparse_data(struct ceph_connection *con)
+{
+	int resid;  /* current piece of data */
+	int remaining;
+
+	WARN_ON(con_secure(con));
+	WARN_ON(!data_len(con->in_msg));
+	WARN_ON(!iov_iter_is_bvec(&con->v2.in_iter));
+	resid = iov_iter_count(&con->v2.in_iter);
+	dout("%s con %p resid %d\n", __func__, con, resid);
+
+	remaining = CEPH_EPILOGUE_PLAIN_LEN + con->v2.data_len_remain;
+	con->v2.in_iter.count -= resid;
+	set_in_skip(con, resid + remaining);
+	con->v2.in_state = IN_S_FINISH_SKIP;
+}
+
 static void revoke_at_handle_epilogue(struct ceph_connection *con)
 {
 	int resid;
@@ -3505,6 +3650,7 @@ static void revoke_at_handle_epilogue(struct ceph_connection *con)
 void ceph_con_v2_revoke_incoming(struct ceph_connection *con)
 {
 	switch (con->v2.in_state) {
+	case IN_S_PREPARE_SPARSE_DATA:
 	case IN_S_PREPARE_READ_DATA:
 		revoke_at_prepare_read_data(con);
 		break;
@@ -3514,6 +3660,9 @@ void ceph_con_v2_revoke_incoming(struct ceph_connection *con)
 	case IN_S_PREPARE_READ_ENC_PAGE:
 		revoke_at_prepare_read_enc_page(con);
 		break;
+	case IN_S_PREPARE_SPARSE_DATA_CONT:
+		revoke_at_prepare_sparse_data(con);
+		break;
 	case IN_S_HANDLE_EPILOGUE:
 		revoke_at_handle_epilogue(con);
 		break;

From f36217e35ce13fe284fe9481711614200badebb0 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Wed, 23 Mar 2022 12:17:15 -0400
Subject: [PATCH 0587/1189] libceph: support sparse reads on msgr2 secure
 codepath
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a new init_sgs_pages helper that populates the scatterlist from
an arbitrary point in an array of pages.

Change setup_message_sgs to take an optional pointer to an array of
pages. If that's set, then the scatterlist will be set using that
array instead of the cursor.

When given a sparse read on a secure connection, decrypt the data
in-place rather than into the final destination, by passing it the
in_enc_pages array.

After decrypting, run the sparse_read state machine in a loop, copying
data from the decrypted pages until it's complete.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 net/ceph/messenger_v2.c | 120 ++++++++++++++++++++++++++++++++++++----
 1 file changed, 110 insertions(+), 10 deletions(-)

diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index 17c9a858bfbd..d0a1fb422617 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -969,12 +969,48 @@ static void init_sgs_cursor(struct scatterlist **sg,
 	}
 }
 
+/**
+ * init_sgs_pages: set up scatterlist on an array of page pointers
+ * @sg:		scatterlist to populate
+ * @pages:	pointer to page array
+ * @dpos:	position in the array to start (bytes)
+ * @dlen:	len to add to sg (bytes)
+ * @pad:	pointer to pad destination (if any)
+ *
+ * Populate the scatterlist from the page array, starting at an arbitrary
+ * byte in the array and running for a specified length.
+ */
+static void init_sgs_pages(struct scatterlist **sg, struct page **pages,
+			   int dpos, int dlen, u8 *pad)
+{
+	int idx = dpos >> PAGE_SHIFT;
+	int off = offset_in_page(dpos);
+	int resid = dlen;
+
+	do {
+		int len = min(resid, (int)PAGE_SIZE - off);
+
+		sg_set_page(*sg, pages[idx], len, off);
+		*sg = sg_next(*sg);
+		off = 0;
+		++idx;
+		resid -= len;
+	} while (resid);
+
+	if (need_padding(dlen)) {
+		sg_set_buf(*sg, pad, padding_len(dlen));
+		*sg = sg_next(*sg);
+	}
+}
+
 static int setup_message_sgs(struct sg_table *sgt, struct ceph_msg *msg,
 			     u8 *front_pad, u8 *middle_pad, u8 *data_pad,
-			     void *epilogue, bool add_tag)
+			     void *epilogue, struct page **pages, int dpos,
+			     bool add_tag)
 {
 	struct ceph_msg_data_cursor cursor;
 	struct scatterlist *cur_sg;
+	int dlen = data_len(msg);
 	int sg_cnt;
 	int ret;
 
@@ -988,9 +1024,15 @@ static int setup_message_sgs(struct sg_table *sgt, struct ceph_msg *msg,
 	if (middle_len(msg))
 		sg_cnt += calc_sg_cnt(msg->middle->vec.iov_base,
 				      middle_len(msg));
-	if (data_len(msg)) {
-		ceph_msg_data_cursor_init(&cursor, msg, data_len(msg));
-		sg_cnt += calc_sg_cnt_cursor(&cursor);
+	if (dlen) {
+		if (pages) {
+			sg_cnt += calc_pages_for(dpos, dlen);
+			if (need_padding(dlen))
+				sg_cnt++;
+		} else {
+			ceph_msg_data_cursor_init(&cursor, msg, dlen);
+			sg_cnt += calc_sg_cnt_cursor(&cursor);
+		}
 	}
 
 	ret = sg_alloc_table(sgt, sg_cnt, GFP_NOIO);
@@ -1004,9 +1046,13 @@ static int setup_message_sgs(struct sg_table *sgt, struct ceph_msg *msg,
 	if (middle_len(msg))
 		init_sgs(&cur_sg, msg->middle->vec.iov_base, middle_len(msg),
 			 middle_pad);
-	if (data_len(msg)) {
-		ceph_msg_data_cursor_init(&cursor, msg, data_len(msg));
-		init_sgs_cursor(&cur_sg, &cursor, data_pad);
+	if (dlen) {
+		if (pages) {
+			init_sgs_pages(&cur_sg, pages, dpos, dlen, data_pad);
+		} else {
+			ceph_msg_data_cursor_init(&cursor, msg, dlen);
+			init_sgs_cursor(&cur_sg, &cursor, data_pad);
+		}
 	}
 
 	WARN_ON(!sg_is_last(cur_sg));
@@ -1041,10 +1087,53 @@ static int decrypt_control_remainder(struct ceph_connection *con)
 			 padded_len(rem_len) + CEPH_GCM_TAG_LEN);
 }
 
+/* Process sparse read data that lives in a buffer */
+static int process_v2_sparse_read(struct ceph_connection *con,
+				  struct page **pages, int spos)
+{
+	struct ceph_msg_data_cursor *cursor = &con->v2.in_cursor;
+	int ret;
+
+	for (;;) {
+		char *buf = NULL;
+
+		ret = con->ops->sparse_read(con, cursor, &buf);
+		if (ret <= 0)
+			return ret;
+
+		dout("%s: sparse_read return %x buf %p\n", __func__, ret, buf);
+
+		do {
+			int idx = spos >> PAGE_SHIFT;
+			int soff = offset_in_page(spos);
+			struct page *spage = con->v2.in_enc_pages[idx];
+			int len = min_t(int, ret, PAGE_SIZE - soff);
+
+			if (buf) {
+				memcpy_from_page(buf, spage, soff, len);
+				buf += len;
+			} else {
+				struct bio_vec bv;
+
+				get_bvec_at(cursor, &bv);
+				len = min_t(int, len, bv.bv_len);
+				memcpy_page(bv.bv_page, bv.bv_offset,
+					    spage, soff, len);
+				ceph_msg_data_advance(cursor, len);
+			}
+			spos += len;
+			ret -= len;
+		} while (ret);
+	}
+}
+
 static int decrypt_tail(struct ceph_connection *con)
 {
 	struct sg_table enc_sgt = {};
 	struct sg_table sgt = {};
+	struct page **pages = NULL;
+	bool sparse = con->in_msg->sparse_read;
+	int dpos = 0;
 	int tail_len;
 	int ret;
 
@@ -1055,9 +1144,14 @@ static int decrypt_tail(struct ceph_connection *con)
 	if (ret)
 		goto out;
 
+	if (sparse) {
+		dpos = padded_len(front_len(con->in_msg) + padded_len(middle_len(con->in_msg)));
+		pages = con->v2.in_enc_pages;
+	}
+
 	ret = setup_message_sgs(&sgt, con->in_msg, FRONT_PAD(con->v2.in_buf),
-			MIDDLE_PAD(con->v2.in_buf), DATA_PAD(con->v2.in_buf),
-			con->v2.in_buf, true);
+				MIDDLE_PAD(con->v2.in_buf), DATA_PAD(con->v2.in_buf),
+				con->v2.in_buf, pages, dpos, true);
 	if (ret)
 		goto out;
 
@@ -1067,6 +1161,12 @@ static int decrypt_tail(struct ceph_connection *con)
 	if (ret)
 		goto out;
 
+	if (sparse && data_len(con->in_msg)) {
+		ret = process_v2_sparse_read(con, con->v2.in_enc_pages, dpos);
+		if (ret)
+			goto out;
+	}
+
 	WARN_ON(!con->v2.in_enc_page_cnt);
 	ceph_release_page_vector(con->v2.in_enc_pages,
 				 con->v2.in_enc_page_cnt);
@@ -1590,7 +1690,7 @@ static int prepare_message_secure(struct ceph_connection *con)
 
 	encode_epilogue_secure(con, false);
 	ret = setup_message_sgs(&sgt, con->out_msg, zerop, zerop, zerop,
-				&con->v2.out_epil, false);
+				&con->v2.out_epil, NULL, 0, false);
 	if (ret)
 		goto out;
 

From d396f89db39a2f259e2125ca43b4c31bb65afcad Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Thu, 24 Mar 2022 13:33:06 -0400
Subject: [PATCH 0588/1189] libceph: add sparse read support to msgr1
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add 2 new fields to ceph_connection_v1_info to track the necessary info
in sparse reads. Skip initializing the cursor for a sparse read.

Break out read_partial_message_section into a wrapper around a new
read_partial_message_chunk function that doesn't zero out the crc first.

Add new helper functions to drive receiving into the destinations
provided by the sparse_read state machine.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/messenger.h |  4 ++
 net/ceph/messenger_v1.c        | 98 +++++++++++++++++++++++++++++++---
 2 files changed, 94 insertions(+), 8 deletions(-)

diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 8a6938fa324e..9fd7255172ad 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -336,6 +336,10 @@ struct ceph_connection_v1_info {
 
 	int in_base_pos;     /* bytes read */
 
+	/* sparse reads */
+	struct kvec in_sr_kvec; /* current location to receive into */
+	u64 in_sr_len;		/* amount of data in this extent */
+
 	/* message in temps */
 	u8 in_tag;           /* protocol control byte */
 	struct ceph_msg_header in_hdr;
diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c
index 3d57bb48a2b4..f9a50d7f0d20 100644
--- a/net/ceph/messenger_v1.c
+++ b/net/ceph/messenger_v1.c
@@ -159,9 +159,9 @@ static size_t sizeof_footer(struct ceph_connection *con)
 
 static void prepare_message_data(struct ceph_msg *msg, u32 data_len)
 {
-	/* Initialize data cursor */
-
-	ceph_msg_data_cursor_init(&msg->cursor, msg, data_len);
+	/* Initialize data cursor if it's not a sparse read */
+	if (!msg->sparse_read)
+		ceph_msg_data_cursor_init(&msg->cursor, msg, data_len);
 }
 
 /*
@@ -960,9 +960,9 @@ static void process_ack(struct ceph_connection *con)
 	prepare_read_tag(con);
 }
 
-static int read_partial_message_section(struct ceph_connection *con,
-					struct kvec *section,
-					unsigned int sec_len, u32 *crc)
+static int read_partial_message_chunk(struct ceph_connection *con,
+				      struct kvec *section,
+				      unsigned int sec_len, u32 *crc)
 {
 	int ret, left;
 
@@ -978,11 +978,91 @@ static int read_partial_message_section(struct ceph_connection *con,
 		section->iov_len += ret;
 	}
 	if (section->iov_len == sec_len)
-		*crc = crc32c(0, section->iov_base, section->iov_len);
+		*crc = crc32c(*crc, section->iov_base, section->iov_len);
 
 	return 1;
 }
 
+static inline int read_partial_message_section(struct ceph_connection *con,
+					       struct kvec *section,
+					       unsigned int sec_len, u32 *crc)
+{
+	*crc = 0;
+	return read_partial_message_chunk(con, section, sec_len, crc);
+}
+
+static int read_sparse_msg_extent(struct ceph_connection *con, u32 *crc)
+{
+	struct ceph_msg_data_cursor *cursor = &con->in_msg->cursor;
+	bool do_bounce = ceph_test_opt(from_msgr(con->msgr), RXBOUNCE);
+
+	if (do_bounce && unlikely(!con->bounce_page)) {
+		con->bounce_page = alloc_page(GFP_NOIO);
+		if (!con->bounce_page) {
+			pr_err("failed to allocate bounce page\n");
+			return -ENOMEM;
+		}
+	}
+
+	while (cursor->sr_resid > 0) {
+		struct page *page, *rpage;
+		size_t off, len;
+		int ret;
+
+		page = ceph_msg_data_next(cursor, &off, &len);
+		rpage = do_bounce ? con->bounce_page : page;
+
+		/* clamp to what remains in extent */
+		len = min_t(int, len, cursor->sr_resid);
+		ret = ceph_tcp_recvpage(con->sock, rpage, (int)off, len);
+		if (ret <= 0)
+			return ret;
+		*crc = ceph_crc32c_page(*crc, rpage, off, ret);
+		ceph_msg_data_advance(cursor, (size_t)ret);
+		cursor->sr_resid -= ret;
+		if (do_bounce)
+			memcpy_page(page, off, rpage, off, ret);
+	}
+	return 1;
+}
+
+static int read_sparse_msg_data(struct ceph_connection *con)
+{
+	struct ceph_msg_data_cursor *cursor = &con->in_msg->cursor;
+	bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC);
+	u32 crc = 0;
+	int ret = 1;
+
+	if (do_datacrc)
+		crc = con->in_data_crc;
+
+	do {
+		if (con->v1.in_sr_kvec.iov_base)
+			ret = read_partial_message_chunk(con,
+							 &con->v1.in_sr_kvec,
+							 con->v1.in_sr_len,
+							 &crc);
+		else if (cursor->sr_resid > 0)
+			ret = read_sparse_msg_extent(con, &crc);
+
+		if (ret <= 0) {
+			if (do_datacrc)
+				con->in_data_crc = crc;
+			return ret;
+		}
+
+		memset(&con->v1.in_sr_kvec, 0, sizeof(con->v1.in_sr_kvec));
+		ret = con->ops->sparse_read(con, cursor,
+				(char **)&con->v1.in_sr_kvec.iov_base);
+		con->v1.in_sr_len = ret;
+	} while (ret > 0);
+
+	if (do_datacrc)
+		con->in_data_crc = crc;
+
+	return ret < 0 ? ret : 1;  /* must return > 0 to indicate success */
+}
+
 static int read_partial_msg_data(struct ceph_connection *con)
 {
 	struct ceph_msg_data_cursor *cursor = &con->in_msg->cursor;
@@ -1173,7 +1253,9 @@ static int read_partial_message(struct ceph_connection *con)
 		if (!m->num_data_items)
 			return -EIO;
 
-		if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE))
+		if (m->sparse_read)
+			ret = read_sparse_msg_data(con);
+		else if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE))
 			ret = read_partial_msg_data_bounce(con);
 		else
 			ret = read_partial_msg_data(con);

From f628d799972799023d32c2542bb2639eb8c4f84e Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Fri, 11 Feb 2022 11:38:02 -0500
Subject: [PATCH 0589/1189] libceph: add sparse read support to OSD client
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Have get_reply check for the presence of sparse read ops in the
request and set the sparse_read boolean in the msg. That will queue the
messenger layer to use the sparse read codepath instead of the normal
data receive.

Add a new sparse_read operation for the OSD client, driven by its own
state machine. The messenger will repeatedly call the sparse_read
operation, and it will pass back the necessary info to set up to read
the next extent of data, while zero-filling the sparse regions.

The state machine will stop at the end of the last extent, and will
attach the extent map buffer to the ceph_osd_req_op so that the caller
can use it.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/osd_client.h |  32 ++++
 net/ceph/osd_client.c           | 257 +++++++++++++++++++++++++++++++-
 2 files changed, 285 insertions(+), 4 deletions(-)

diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 05da1e755b7b..bfa4813590da 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -40,6 +40,36 @@ struct ceph_sparse_extent {
 	u64	len;
 } __packed;
 
+/* Sparse read state machine state values */
+enum ceph_sparse_read_state {
+	CEPH_SPARSE_READ_HDR	= 0,
+	CEPH_SPARSE_READ_EXTENTS,
+	CEPH_SPARSE_READ_DATA_LEN,
+	CEPH_SPARSE_READ_DATA,
+};
+
+/*
+ * A SPARSE_READ reply is a 32-bit count of extents, followed by an array of
+ * 64-bit offset/length pairs, and then all of the actual file data
+ * concatenated after it (sans holes).
+ *
+ * Unfortunately, we don't know how long the extent array is until we've
+ * started reading the data section of the reply. The caller should send down
+ * a destination buffer for the array, but we'll alloc one if it's too small
+ * or if the caller doesn't.
+ */
+struct ceph_sparse_read {
+	enum ceph_sparse_read_state	sr_state;    /* state machine state */
+	u64				sr_req_off;  /* orig request offset */
+	u64				sr_req_len;  /* orig request length */
+	u64				sr_pos;      /* current pos in buffer */
+	int				sr_index;    /* current extent index */
+	__le32				sr_datalen;  /* length of actual data */
+	u32				sr_count;    /* extent count in reply */
+	int				sr_ext_len;  /* length of extent array */
+	struct ceph_sparse_extent	*sr_extent;  /* extent array */
+};
+
 /*
  * A given osd we're communicating with.
  *
@@ -48,6 +78,7 @@ struct ceph_sparse_extent {
  */
 struct ceph_osd {
 	refcount_t o_ref;
+	int o_sparse_op_idx;
 	struct ceph_osd_client *o_osdc;
 	int o_osd;
 	int o_incarnation;
@@ -63,6 +94,7 @@ struct ceph_osd {
 	unsigned long lru_ttl;
 	struct list_head o_keepalive_item;
 	struct mutex lock;
+	struct ceph_sparse_read	o_sparse_read;
 };
 
 #define CEPH_OSD_SLAB_OPS	2
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 3e03ae68722c..0aacbadcab06 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -376,6 +376,7 @@ static void osd_req_op_data_release(struct ceph_osd_request *osd_req,
 
 	switch (op->op) {
 	case CEPH_OSD_OP_READ:
+	case CEPH_OSD_OP_SPARSE_READ:
 	case CEPH_OSD_OP_WRITE:
 	case CEPH_OSD_OP_WRITEFULL:
 		kfree(op->extent.sparse_ext);
@@ -670,6 +671,7 @@ static void get_num_data_items(struct ceph_osd_request *req,
 		/* reply */
 		case CEPH_OSD_OP_STAT:
 		case CEPH_OSD_OP_READ:
+		case CEPH_OSD_OP_SPARSE_READ:
 		case CEPH_OSD_OP_LIST_WATCHERS:
 			*num_reply_data_items += 1;
 			break;
@@ -739,7 +741,7 @@ void osd_req_op_extent_init(struct ceph_osd_request *osd_req,
 
 	BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE &&
 	       opcode != CEPH_OSD_OP_WRITEFULL && opcode != CEPH_OSD_OP_ZERO &&
-	       opcode != CEPH_OSD_OP_TRUNCATE);
+	       opcode != CEPH_OSD_OP_TRUNCATE && opcode != CEPH_OSD_OP_SPARSE_READ);
 
 	op->extent.offset = offset;
 	op->extent.length = length;
@@ -964,6 +966,7 @@ static u32 osd_req_encode_op(struct ceph_osd_op *dst,
 	case CEPH_OSD_OP_STAT:
 		break;
 	case CEPH_OSD_OP_READ:
+	case CEPH_OSD_OP_SPARSE_READ:
 	case CEPH_OSD_OP_WRITE:
 	case CEPH_OSD_OP_WRITEFULL:
 	case CEPH_OSD_OP_ZERO:
@@ -1060,7 +1063,8 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 
 	BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE &&
 	       opcode != CEPH_OSD_OP_ZERO && opcode != CEPH_OSD_OP_TRUNCATE &&
-	       opcode != CEPH_OSD_OP_CREATE && opcode != CEPH_OSD_OP_DELETE);
+	       opcode != CEPH_OSD_OP_CREATE && opcode != CEPH_OSD_OP_DELETE &&
+	       opcode != CEPH_OSD_OP_SPARSE_READ);
 
 	req = ceph_osdc_alloc_request(osdc, snapc, num_ops, use_mempool,
 					GFP_NOFS);
@@ -1201,6 +1205,13 @@ static void osd_init(struct ceph_osd *osd)
 	mutex_init(&osd->lock);
 }
 
+static void ceph_init_sparse_read(struct ceph_sparse_read *sr)
+{
+	kfree(sr->sr_extent);
+	memset(sr, '\0', sizeof(*sr));
+	sr->sr_state = CEPH_SPARSE_READ_HDR;
+}
+
 static void osd_cleanup(struct ceph_osd *osd)
 {
 	WARN_ON(!RB_EMPTY_NODE(&osd->o_node));
@@ -1211,6 +1222,8 @@ static void osd_cleanup(struct ceph_osd *osd)
 	WARN_ON(!list_empty(&osd->o_osd_lru));
 	WARN_ON(!list_empty(&osd->o_keepalive_item));
 
+	ceph_init_sparse_read(&osd->o_sparse_read);
+
 	if (osd->o_auth.authorizer) {
 		WARN_ON(osd_homeless(osd));
 		ceph_auth_destroy_authorizer(osd->o_auth.authorizer);
@@ -1230,6 +1243,9 @@ static struct ceph_osd *create_osd(struct ceph_osd_client *osdc, int onum)
 	osd_init(osd);
 	osd->o_osdc = osdc;
 	osd->o_osd = onum;
+	osd->o_sparse_op_idx = -1;
+
+	ceph_init_sparse_read(&osd->o_sparse_read);
 
 	ceph_con_init(&osd->o_con, osd, &osd_con_ops, &osdc->client->msgr);
 
@@ -2034,6 +2050,7 @@ static void setup_request_data(struct ceph_osd_request *req)
 					       &op->raw_data_in);
 			break;
 		case CEPH_OSD_OP_READ:
+		case CEPH_OSD_OP_SPARSE_READ:
 			ceph_osdc_msg_data_add(reply_msg,
 					       &op->extent.osd_data);
 			break;
@@ -2453,8 +2470,10 @@ static void finish_request(struct ceph_osd_request *req)
 
 	req->r_end_latency = ktime_get();
 
-	if (req->r_osd)
+	if (req->r_osd) {
+		ceph_init_sparse_read(&req->r_osd->o_sparse_read);
 		unlink_request(req->r_osd, req);
+	}
 	atomic_dec(&osdc->num_requests);
 
 	/*
@@ -5366,6 +5385,24 @@ static void osd_dispatch(struct ceph_connection *con, struct ceph_msg *msg)
 	ceph_msg_put(msg);
 }
 
+/* How much sparse data was requested? */
+static u64 sparse_data_requested(struct ceph_osd_request *req)
+{
+	u64 len = 0;
+
+	if (req->r_flags & CEPH_OSD_FLAG_READ) {
+		int i;
+
+		for (i = 0; i < req->r_num_ops; ++i) {
+			struct ceph_osd_req_op *op = &req->r_ops[i];
+
+			if (op->op == CEPH_OSD_OP_SPARSE_READ)
+				len += op->extent.length;
+		}
+	}
+	return len;
+}
+
 /*
  * Lookup and return message for incoming reply.  Don't try to do
  * anything about a larger than preallocated data portion of the
@@ -5382,6 +5419,7 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
 	int front_len = le32_to_cpu(hdr->front_len);
 	int data_len = le32_to_cpu(hdr->data_len);
 	u64 tid = le64_to_cpu(hdr->tid);
+	u64 srlen;
 
 	down_read(&osdc->lock);
 	if (!osd_registered(osd)) {
@@ -5414,7 +5452,8 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
 		req->r_reply = m;
 	}
 
-	if (data_len > req->r_reply->data_length) {
+	srlen = sparse_data_requested(req);
+	if (!srlen && data_len > req->r_reply->data_length) {
 		pr_warn("%s osd%d tid %llu data %d > preallocated %zu, skipping\n",
 			__func__, osd->o_osd, req->r_tid, data_len,
 			req->r_reply->data_length);
@@ -5424,6 +5463,8 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
 	}
 
 	m = ceph_msg_get(req->r_reply);
+	m->sparse_read = (bool)srlen;
+
 	dout("get_reply tid %lld %p\n", tid, m);
 
 out_unlock_session:
@@ -5656,9 +5697,217 @@ static int osd_check_message_signature(struct ceph_msg *msg)
 	return ceph_auth_check_message_signature(auth, msg);
 }
 
+static void advance_cursor(struct ceph_msg_data_cursor *cursor, size_t len,
+			   bool zero)
+{
+	while (len) {
+		struct page *page;
+		size_t poff, plen;
+
+		page = ceph_msg_data_next(cursor, &poff, &plen);
+		if (plen > len)
+			plen = len;
+		if (zero)
+			zero_user_segment(page, poff, poff + plen);
+		len -= plen;
+		ceph_msg_data_advance(cursor, plen);
+	}
+}
+
+static int prep_next_sparse_read(struct ceph_connection *con,
+				 struct ceph_msg_data_cursor *cursor)
+{
+	struct ceph_osd *o = con->private;
+	struct ceph_sparse_read *sr = &o->o_sparse_read;
+	struct ceph_osd_request *req;
+	struct ceph_osd_req_op *op;
+
+	spin_lock(&o->o_requests_lock);
+	req = lookup_request(&o->o_requests, le64_to_cpu(con->in_msg->hdr.tid));
+	if (!req) {
+		spin_unlock(&o->o_requests_lock);
+		return -EBADR;
+	}
+
+	if (o->o_sparse_op_idx < 0) {
+		u64 srlen = sparse_data_requested(req);
+
+		dout("%s: [%d] starting new sparse read req. srlen=0x%llx\n",
+		     __func__, o->o_osd, srlen);
+		ceph_msg_data_cursor_init(cursor, con->in_msg, srlen);
+	} else {
+		u64 end;
+
+		op = &req->r_ops[o->o_sparse_op_idx];
+
+		WARN_ON_ONCE(op->extent.sparse_ext);
+
+		/* hand back buffer we took earlier */
+		op->extent.sparse_ext = sr->sr_extent;
+		sr->sr_extent = NULL;
+		op->extent.sparse_ext_cnt = sr->sr_count;
+		sr->sr_ext_len = 0;
+		dout("%s: [%d] completed extent array len %d cursor->resid %zd\n",
+		     __func__, o->o_osd, op->extent.sparse_ext_cnt, cursor->resid);
+		/* Advance to end of data for this operation */
+		end = ceph_sparse_ext_map_end(op);
+		if (end < sr->sr_req_len)
+			advance_cursor(cursor, sr->sr_req_len - end, false);
+	}
+
+	ceph_init_sparse_read(sr);
+
+	/* find next op in this request (if any) */
+	while (++o->o_sparse_op_idx < req->r_num_ops) {
+		op = &req->r_ops[o->o_sparse_op_idx];
+		if (op->op == CEPH_OSD_OP_SPARSE_READ)
+			goto found;
+	}
+
+	/* reset for next sparse read request */
+	spin_unlock(&o->o_requests_lock);
+	o->o_sparse_op_idx = -1;
+	return 0;
+found:
+	sr->sr_req_off = op->extent.offset;
+	sr->sr_req_len = op->extent.length;
+	sr->sr_pos = sr->sr_req_off;
+	dout("%s: [%d] new sparse read op at idx %d 0x%llx~0x%llx\n", __func__,
+	     o->o_osd, o->o_sparse_op_idx, sr->sr_req_off, sr->sr_req_len);
+
+	/* hand off request's sparse extent map buffer */
+	sr->sr_ext_len = op->extent.sparse_ext_cnt;
+	op->extent.sparse_ext_cnt = 0;
+	sr->sr_extent = op->extent.sparse_ext;
+	op->extent.sparse_ext = NULL;
+
+	spin_unlock(&o->o_requests_lock);
+	return 1;
+}
+
+#ifdef __BIG_ENDIAN
+static inline void convert_extent_map(struct ceph_sparse_read *sr)
+{
+	int i;
+
+	for (i = 0; i < sr->sr_count; i++) {
+		struct ceph_sparse_extent *ext = &sr->sr_extent[i];
+
+		ext->off = le64_to_cpu((__force __le64)ext->off);
+		ext->len = le64_to_cpu((__force __le64)ext->len);
+	}
+}
+#else
+static inline void convert_extent_map(struct ceph_sparse_read *sr)
+{
+}
+#endif
+
+#define MAX_EXTENTS 4096
+
+static int osd_sparse_read(struct ceph_connection *con,
+			   struct ceph_msg_data_cursor *cursor,
+			   char **pbuf)
+{
+	struct ceph_osd *o = con->private;
+	struct ceph_sparse_read *sr = &o->o_sparse_read;
+	u32 count = sr->sr_count;
+	u64 eoff, elen;
+	int ret;
+
+	switch (sr->sr_state) {
+	case CEPH_SPARSE_READ_HDR:
+next_op:
+		ret = prep_next_sparse_read(con, cursor);
+		if (ret <= 0)
+			return ret;
+
+		/* number of extents */
+		ret = sizeof(sr->sr_count);
+		*pbuf = (char *)&sr->sr_count;
+		sr->sr_state = CEPH_SPARSE_READ_EXTENTS;
+		break;
+	case CEPH_SPARSE_READ_EXTENTS:
+		/* Convert sr_count to host-endian */
+		count = le32_to_cpu((__force __le32)sr->sr_count);
+		sr->sr_count = count;
+		dout("[%d] got %u extents\n", o->o_osd, count);
+
+		if (count > 0) {
+			if (!sr->sr_extent || count > sr->sr_ext_len) {
+				/*
+				 * Apply a hard cap to the number of extents.
+				 * If we have more, assume something is wrong.
+				 */
+				if (count > MAX_EXTENTS) {
+					dout("%s: OSD returned 0x%x extents in a single reply!\n",
+					     __func__, count);
+					return -EREMOTEIO;
+				}
+
+				/* no extent array provided, or too short */
+				kfree(sr->sr_extent);
+				sr->sr_extent = kmalloc_array(count,
+							      sizeof(*sr->sr_extent),
+							      GFP_NOIO);
+				if (!sr->sr_extent)
+					return -ENOMEM;
+				sr->sr_ext_len = count;
+			}
+			ret = count * sizeof(*sr->sr_extent);
+			*pbuf = (char *)sr->sr_extent;
+			sr->sr_state = CEPH_SPARSE_READ_DATA_LEN;
+			break;
+		}
+		/* No extents? Read data len */
+		fallthrough;
+	case CEPH_SPARSE_READ_DATA_LEN:
+		convert_extent_map(sr);
+		ret = sizeof(sr->sr_datalen);
+		*pbuf = (char *)&sr->sr_datalen;
+		sr->sr_state = CEPH_SPARSE_READ_DATA;
+		break;
+	case CEPH_SPARSE_READ_DATA:
+		if (sr->sr_index >= count) {
+			sr->sr_state = CEPH_SPARSE_READ_HDR;
+			goto next_op;
+		}
+
+		eoff = sr->sr_extent[sr->sr_index].off;
+		elen = sr->sr_extent[sr->sr_index].len;
+
+		dout("[%d] ext %d off 0x%llx len 0x%llx\n",
+		     o->o_osd, sr->sr_index, eoff, elen);
+
+		if (elen > INT_MAX) {
+			dout("Sparse read extent length too long (0x%llx)\n",
+			     elen);
+			return -EREMOTEIO;
+		}
+
+		/* zero out anything from sr_pos to start of extent */
+		if (sr->sr_pos < eoff)
+			advance_cursor(cursor, eoff - sr->sr_pos, true);
+
+		/* Set position to end of extent */
+		sr->sr_pos = eoff + elen;
+
+		/* send back the new length and nullify the ptr */
+		cursor->sr_resid = elen;
+		ret = elen;
+		*pbuf = NULL;
+
+		/* Bump the array index */
+		++sr->sr_index;
+		break;
+	}
+	return ret;
+}
+
 static const struct ceph_connection_operations osd_con_ops = {
 	.get = osd_get_con,
 	.put = osd_put_con,
+	.sparse_read = osd_sparse_read,
 	.alloc_msg = osd_alloc_msg,
 	.dispatch = osd_dispatch,
 	.fault = osd_fault,

From 03bc06c7b0bd8d86b9f17f459acaeb1283ba2700 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Sat, 26 Feb 2022 06:33:03 -0500
Subject: [PATCH 0590/1189] ceph: add new mount option to enable sparse reads
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a new mount option that has the client issue sparse reads instead of
normal ones. The callers now preallocate an sparse extent buffer that
the libceph receive code can populate and hand back after the operation
completes.

After a successful sparse read, we can't use the req->r_result value to
determine the amount of data "read", so instead we set the received
length to be from the end of the last extent in the buffer. Any
interstitial holes will have been filled by the receive code.

[ xiubli: fix a double free on req reported by Ilya ]

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/addr.c  | 15 +++++++++++++--
 fs/ceph/file.c  | 51 +++++++++++++++++++++++++++++++++++++++++--------
 fs/ceph/super.c | 16 +++++++++++++++-
 fs/ceph/super.h |  1 +
 4 files changed, 72 insertions(+), 11 deletions(-)

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 59cbfb80edbd..f45ebe957bbe 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -245,8 +245,10 @@ static void finish_netfs_read(struct ceph_osd_request *req)
 	struct ceph_fs_client *fsc = ceph_inode_to_client(req->r_inode);
 	struct ceph_osd_data *osd_data = osd_req_op_extent_osd_data(req, 0);
 	struct netfs_io_subrequest *subreq = req->r_priv;
+	struct ceph_osd_req_op *op = &req->r_ops[0];
 	int num_pages;
 	int err = req->r_result;
+	bool sparse = (op->op == CEPH_OSD_OP_SPARSE_READ);
 
 	ceph_update_read_metrics(&fsc->mdsc->metric, req->r_start_latency,
 				 req->r_end_latency, osd_data->length, err);
@@ -255,7 +257,9 @@ static void finish_netfs_read(struct ceph_osd_request *req)
 	     subreq->len, i_size_read(req->r_inode));
 
 	/* no object means success but no data */
-	if (err == -ENOENT)
+	if (sparse && err >= 0)
+		err = ceph_sparse_ext_map_end(op);
+	else if (err == -ENOENT)
 		err = 0;
 	else if (err == -EBLOCKLISTED)
 		fsc->blocklisted = true;
@@ -338,6 +342,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 	size_t page_off;
 	int err = 0;
 	u64 len = subreq->len;
+	bool sparse = ceph_test_mount_opt(fsc, SPARSEREAD);
 
 	if (ceph_inode_is_shutdown(inode)) {
 		err = -EIO;
@@ -348,7 +353,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 		return;
 
 	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino, subreq->start, &len,
-			0, 1, CEPH_OSD_OP_READ,
+			0, 1, sparse ? CEPH_OSD_OP_SPARSE_READ : CEPH_OSD_OP_READ,
 			CEPH_OSD_FLAG_READ | fsc->client->osdc.client->options->read_from_replica,
 			NULL, ci->i_truncate_seq, ci->i_truncate_size, false);
 	if (IS_ERR(req)) {
@@ -357,6 +362,12 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 		goto out;
 	}
 
+	if (sparse) {
+		err = ceph_alloc_sparse_ext_map(&req->r_ops[0]);
+		if (err)
+			goto out;
+	}
+
 	dout("%s: pos=%llu orig_len=%zu len=%llu\n", __func__, subreq->start, subreq->len, len);
 	iov_iter_xarray(&iter, ITER_DEST, &rreq->mapping->i_pages, subreq->start, len);
 	err = iov_iter_get_pages_alloc2(&iter, &pages, len, &page_off);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 63efe5389783..e3671678b233 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -936,6 +936,7 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
 	u64 off = iocb->ki_pos;
 	u64 len = iov_iter_count(to);
 	u64 i_size = i_size_read(inode);
+	bool sparse = ceph_test_mount_opt(fsc, SPARSEREAD);
 
 	dout("sync_read on file %p %llu~%u %s\n", file, off, (unsigned)len,
 	     (file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
@@ -962,10 +963,12 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
 		bool more;
 		int idx;
 		size_t left;
+		struct ceph_osd_req_op *op;
 
 		req = ceph_osdc_new_request(osdc, &ci->i_layout,
 					ci->i_vino, off, &len, 0, 1,
-					CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ,
+					sparse ? CEPH_OSD_OP_SPARSE_READ : CEPH_OSD_OP_READ,
+					CEPH_OSD_FLAG_READ,
 					NULL, ci->i_truncate_seq,
 					ci->i_truncate_size, false);
 		if (IS_ERR(req)) {
@@ -986,6 +989,16 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
 
 		osd_req_op_extent_osd_data_pages(req, 0, pages, len, page_off,
 						 false, false);
+
+		op = &req->r_ops[0];
+		if (sparse) {
+			ret = ceph_alloc_sparse_ext_map(op);
+			if (ret) {
+				ceph_osdc_put_request(req);
+				break;
+			}
+		}
+
 		ceph_osdc_start_request(osdc, req);
 		ret = ceph_osdc_wait_request(osdc, req);
 
@@ -994,19 +1007,24 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
 					 req->r_end_latency,
 					 len, ret);
 
-		ceph_osdc_put_request(req);
-
 		i_size = i_size_read(inode);
 		dout("sync_read %llu~%llu got %zd i_size %llu%s\n",
 		     off, len, ret, i_size, (more ? " MORE" : ""));
 
-		if (ret == -ENOENT)
+		/* Fix it to go to end of extent map */
+		if (sparse && ret >= 0)
+			ret = ceph_sparse_ext_map_end(op);
+		else if (ret == -ENOENT)
 			ret = 0;
+
+		ceph_osdc_put_request(req);
+
 		if (ret >= 0 && ret < len && (off + ret < i_size)) {
 			int zlen = min(len - ret, i_size - off - ret);
 			int zoff = page_off + ret;
+
 			dout("sync_read zero gap %llu~%llu\n",
-                             off + ret, off + ret + zlen);
+				off + ret, off + ret + zlen);
 			ceph_zero_page_vector_range(zoff, zlen, pages);
 			ret += zlen;
 		}
@@ -1125,8 +1143,10 @@ static void ceph_aio_complete_req(struct ceph_osd_request *req)
 	struct inode *inode = req->r_inode;
 	struct ceph_aio_request *aio_req = req->r_priv;
 	struct ceph_osd_data *osd_data = osd_req_op_extent_osd_data(req, 0);
+	struct ceph_osd_req_op *op = &req->r_ops[0];
 	struct ceph_client_metric *metric = &ceph_sb_to_mdsc(inode->i_sb)->metric;
 	unsigned int len = osd_data->bvec_pos.iter.bi_size;
+	bool sparse = (op->op == CEPH_OSD_OP_SPARSE_READ);
 
 	BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_BVECS);
 	BUG_ON(!osd_data->num_bvecs);
@@ -1147,6 +1167,8 @@ static void ceph_aio_complete_req(struct ceph_osd_request *req)
 		}
 		rc = -ENOMEM;
 	} else if (!aio_req->write) {
+		if (sparse && rc >= 0)
+			rc = ceph_sparse_ext_map_end(op);
 		if (rc == -ENOENT)
 			rc = 0;
 		if (rc >= 0 && len > rc) {
@@ -1283,6 +1305,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 	loff_t pos = iocb->ki_pos;
 	bool write = iov_iter_rw(iter) == WRITE;
 	bool should_dirty = !write && user_backed_iter(iter);
+	bool sparse = ceph_test_mount_opt(fsc, SPARSEREAD);
 
 	if (write && ceph_snap(file_inode(file)) != CEPH_NOSNAP)
 		return -EROFS;
@@ -1310,6 +1333,8 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 	while (iov_iter_count(iter) > 0) {
 		u64 size = iov_iter_count(iter);
 		ssize_t len;
+		struct ceph_osd_req_op *op;
+		int readop = sparse ? CEPH_OSD_OP_SPARSE_READ : CEPH_OSD_OP_READ;
 
 		if (write)
 			size = min_t(u64, size, fsc->mount_options->wsize);
@@ -1320,8 +1345,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 		req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
 					    vino, pos, &size, 0,
 					    1,
-					    write ? CEPH_OSD_OP_WRITE :
-						    CEPH_OSD_OP_READ,
+					    write ? CEPH_OSD_OP_WRITE : readop,
 					    flags, snapc,
 					    ci->i_truncate_seq,
 					    ci->i_truncate_size,
@@ -1372,6 +1396,14 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 		}
 
 		osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len);
+		op = &req->r_ops[0];
+		if (sparse) {
+			ret = ceph_alloc_sparse_ext_map(op);
+			if (ret) {
+				ceph_osdc_put_request(req);
+				break;
+			}
+		}
 
 		if (aio_req) {
 			aio_req->total_len += len;
@@ -1399,8 +1431,11 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 
 		size = i_size_read(inode);
 		if (!write) {
-			if (ret == -ENOENT)
+			if (sparse && ret >= 0)
+				ret = ceph_sparse_ext_map_end(op);
+			else if (ret == -ENOENT)
 				ret = 0;
+
 			if (ret >= 0 && ret < len && pos + ret < size) {
 				struct iov_iter i;
 				int zlen = min_t(size_t, len - ret,
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index a5f52013314d..d6a1790f6923 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -165,6 +165,7 @@ enum {
 	Opt_copyfrom,
 	Opt_wsync,
 	Opt_pagecache,
+	Opt_sparseread,
 };
 
 enum ceph_recover_session_mode {
@@ -207,6 +208,7 @@ static const struct fs_parameter_spec ceph_mount_parameters[] = {
 	fsparam_u32	("wsize",			Opt_wsize),
 	fsparam_flag_no	("wsync",			Opt_wsync),
 	fsparam_flag_no	("pagecache",			Opt_pagecache),
+	fsparam_flag_no	("sparseread",			Opt_sparseread),
 	{}
 };
 
@@ -576,6 +578,12 @@ static int ceph_parse_mount_param(struct fs_context *fc,
 		else
 			fsopt->flags &= ~CEPH_MOUNT_OPT_NOPAGECACHE;
 		break;
+	case Opt_sparseread:
+		if (result.negated)
+			fsopt->flags &= ~CEPH_MOUNT_OPT_SPARSEREAD;
+		else
+			fsopt->flags |= CEPH_MOUNT_OPT_SPARSEREAD;
+		break;
 	default:
 		BUG();
 	}
@@ -710,9 +718,10 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
 
 	if (!(fsopt->flags & CEPH_MOUNT_OPT_ASYNC_DIROPS))
 		seq_puts(m, ",wsync");
-
 	if (fsopt->flags & CEPH_MOUNT_OPT_NOPAGECACHE)
 		seq_puts(m, ",nopagecache");
+	if (fsopt->flags & CEPH_MOUNT_OPT_SPARSEREAD)
+		seq_puts(m, ",sparseread");
 
 	if (fsopt->wsize != CEPH_MAX_WRITE_SIZE)
 		seq_printf(m, ",wsize=%u", fsopt->wsize);
@@ -1296,6 +1305,11 @@ static int ceph_reconfigure_fc(struct fs_context *fc)
 	else
 		ceph_clear_mount_opt(fsc, ASYNC_DIROPS);
 
+	if (fsopt->flags & CEPH_MOUNT_OPT_SPARSEREAD)
+		ceph_set_mount_opt(fsc, SPARSEREAD);
+	else
+		ceph_clear_mount_opt(fsc, SPARSEREAD);
+
 	if (strcmp_null(fsc->mount_options->mon_addr, fsopt->mon_addr)) {
 		kfree(fsc->mount_options->mon_addr);
 		fsc->mount_options->mon_addr = fsopt->mon_addr;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 3bfddf34d488..b9cad57ce606 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -42,6 +42,7 @@
 #define CEPH_MOUNT_OPT_NOCOPYFROM      (1<<14) /* don't use RADOS 'copy-from' op */
 #define CEPH_MOUNT_OPT_ASYNC_DIROPS    (1<<15) /* allow async directory ops */
 #define CEPH_MOUNT_OPT_NOPAGECACHE     (1<<16) /* bypass pagecache altogether */
+#define CEPH_MOUNT_OPT_SPARSEREAD      (1<<17) /* always do sparse reads */
 
 #define CEPH_MOUNT_OPT_DEFAULT			\
 	(CEPH_MOUNT_OPT_DCACHE |		\

From ec9595c080c6f0ba3ebcfc3013eac8f38b868b78 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Wed, 26 Aug 2020 13:11:00 -0400
Subject: [PATCH 0591/1189] ceph: preallocate inode for ops that may create one
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When creating a new inode, we need to determine the crypto context
before we can transmit the RPC. The fscrypt API has a routine for getting
a crypto context before a create occurs, but it requires an inode.

Change the ceph code to preallocate an inode in advance of a create of
any sort (open(), mknod(), symlink(), etc). Move the existing code that
generates the ACL and SELinux blobs into this routine since that's
mostly common across all the different codepaths.

In most cases, we just want to allow ceph_fill_trace to use that inode
after the reply comes in, so add a new field to the MDS request for it
(r_new_inode).

The async create codepath is a bit different though. In that case, we
want to hash the inode in advance of the RPC so that it can be used
before the reply comes in. If the call subsequently fails with
-EJUKEBOX, then just put the references and clean up the as_ctx. Note
that with this change, we now need to regenerate the as_ctx when this
occurs, but it's quite rare for it to happen.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/dir.c        | 70 +++++++++++++++++++-----------------
 fs/ceph/file.c       | 65 +++++++++++++++++++++-------------
 fs/ceph/inode.c      | 84 ++++++++++++++++++++++++++++++++++++++++----
 fs/ceph/mds_client.c | 17 +++++++--
 fs/ceph/mds_client.h |  1 +
 fs/ceph/super.h      |  9 ++++-
 6 files changed, 179 insertions(+), 67 deletions(-)

diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index bdcffb04513f..31fac215a6a0 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -865,13 +865,6 @@ static int ceph_mknod(struct mnt_idmap *idmap, struct inode *dir,
 		goto out;
 	}
 
-	err = ceph_pre_init_acls(dir, &mode, &as_ctx);
-	if (err < 0)
-		goto out;
-	err = ceph_security_init_secctx(dentry, mode, &as_ctx);
-	if (err < 0)
-		goto out;
-
 	dout("mknod in dir %p dentry %p mode 0%ho rdev %d\n",
 	     dir, dentry, mode, rdev);
 	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_MKNOD, USE_AUTH_MDS);
@@ -879,6 +872,14 @@ static int ceph_mknod(struct mnt_idmap *idmap, struct inode *dir,
 		err = PTR_ERR(req);
 		goto out;
 	}
+
+	req->r_new_inode = ceph_new_inode(dir, dentry, &mode, &as_ctx);
+	if (IS_ERR(req->r_new_inode)) {
+		err = PTR_ERR(req->r_new_inode);
+		req->r_new_inode = NULL;
+		goto out_req;
+	}
+
 	req->r_dentry = dget(dentry);
 	req->r_num_caps = 2;
 	req->r_parent = dir;
@@ -889,13 +890,13 @@ static int ceph_mknod(struct mnt_idmap *idmap, struct inode *dir,
 	req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL |
 			     CEPH_CAP_XATTR_EXCL;
 	req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
-	if (as_ctx.pagelist) {
-		req->r_pagelist = as_ctx.pagelist;
-		as_ctx.pagelist = NULL;
-	}
+
+	ceph_as_ctx_to_req(req, &as_ctx);
+
 	err = ceph_mdsc_do_request(mdsc, dir, req);
 	if (!err && !req->r_reply_info.head->is_dentry)
 		err = ceph_handle_notrace_create(dir, dentry);
+out_req:
 	ceph_mdsc_put_request(req);
 out:
 	if (!err)
@@ -918,6 +919,7 @@ static int ceph_symlink(struct mnt_idmap *idmap, struct inode *dir,
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb);
 	struct ceph_mds_request *req;
 	struct ceph_acl_sec_ctx as_ctx = {};
+	umode_t mode = S_IFLNK | 0777;
 	int err;
 
 	if (ceph_snap(dir) != CEPH_NOSNAP)
@@ -932,21 +934,24 @@ static int ceph_symlink(struct mnt_idmap *idmap, struct inode *dir,
 		goto out;
 	}
 
-	err = ceph_security_init_secctx(dentry, S_IFLNK | 0777, &as_ctx);
-	if (err < 0)
-		goto out;
-
 	dout("symlink in dir %p dentry %p to '%s'\n", dir, dentry, dest);
 	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SYMLINK, USE_AUTH_MDS);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		goto out;
 	}
+
+	req->r_new_inode = ceph_new_inode(dir, dentry, &mode, &as_ctx);
+	if (IS_ERR(req->r_new_inode)) {
+		err = PTR_ERR(req->r_new_inode);
+		req->r_new_inode = NULL;
+		goto out_req;
+	}
+
 	req->r_path2 = kstrdup(dest, GFP_KERNEL);
 	if (!req->r_path2) {
 		err = -ENOMEM;
-		ceph_mdsc_put_request(req);
-		goto out;
+		goto out_req;
 	}
 	req->r_parent = dir;
 	ihold(dir);
@@ -957,13 +962,13 @@ static int ceph_symlink(struct mnt_idmap *idmap, struct inode *dir,
 	req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL |
 			     CEPH_CAP_XATTR_EXCL;
 	req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
-	if (as_ctx.pagelist) {
-		req->r_pagelist = as_ctx.pagelist;
-		as_ctx.pagelist = NULL;
-	}
+
+	ceph_as_ctx_to_req(req, &as_ctx);
+
 	err = ceph_mdsc_do_request(mdsc, dir, req);
 	if (!err && !req->r_reply_info.head->is_dentry)
 		err = ceph_handle_notrace_create(dir, dentry);
+out_req:
 	ceph_mdsc_put_request(req);
 out:
 	if (err)
@@ -1004,13 +1009,6 @@ static int ceph_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 		goto out;
 	}
 
-	mode |= S_IFDIR;
-	err = ceph_pre_init_acls(dir, &mode, &as_ctx);
-	if (err < 0)
-		goto out;
-	err = ceph_security_init_secctx(dentry, mode, &as_ctx);
-	if (err < 0)
-		goto out;
 
 	req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
 	if (IS_ERR(req)) {
@@ -1018,6 +1016,14 @@ static int ceph_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 		goto out;
 	}
 
+	mode |= S_IFDIR;
+	req->r_new_inode = ceph_new_inode(dir, dentry, &mode, &as_ctx);
+	if (IS_ERR(req->r_new_inode)) {
+		err = PTR_ERR(req->r_new_inode);
+		req->r_new_inode = NULL;
+		goto out_req;
+	}
+
 	req->r_dentry = dget(dentry);
 	req->r_num_caps = 2;
 	req->r_parent = dir;
@@ -1027,15 +1033,15 @@ static int ceph_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 	req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL |
 			     CEPH_CAP_XATTR_EXCL;
 	req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
-	if (as_ctx.pagelist) {
-		req->r_pagelist = as_ctx.pagelist;
-		as_ctx.pagelist = NULL;
-	}
+
+	ceph_as_ctx_to_req(req, &as_ctx);
+
 	err = ceph_mdsc_do_request(mdsc, dir, req);
 	if (!err &&
 	    !req->r_reply_info.head->is_target &&
 	    !req->r_reply_info.head->is_dentry)
 		err = ceph_handle_notrace_create(dir, dentry);
+out_req:
 	ceph_mdsc_put_request(req);
 out:
 	if (!err)
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index e3671678b233..dddced525b69 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -604,7 +604,8 @@ out:
 	ceph_mdsc_release_dir_caps(req);
 }
 
-static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry,
+static int ceph_finish_async_create(struct inode *dir, struct inode *inode,
+				    struct dentry *dentry,
 				    struct file *file, umode_t mode,
 				    struct ceph_mds_request *req,
 				    struct ceph_acl_sec_ctx *as_ctx,
@@ -616,7 +617,6 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry,
 	struct ceph_mds_reply_info_in iinfo = { .in = &in };
 	struct ceph_inode_info *ci = ceph_inode(dir);
 	struct ceph_dentry_info *di = ceph_dentry(dentry);
-	struct inode *inode;
 	struct timespec64 now;
 	struct ceph_string *pool_ns;
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb);
@@ -625,10 +625,6 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry,
 
 	ktime_get_real_ts64(&now);
 
-	inode = ceph_get_inode(dentry->d_sb, vino);
-	if (IS_ERR(inode))
-		return PTR_ERR(inode);
-
 	iinfo.inline_version = CEPH_INLINE_NONE;
 	iinfo.change_attr = 1;
 	ceph_encode_timespec64(&iinfo.btime, &now);
@@ -686,8 +682,7 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry,
 		ceph_dir_clear_complete(dir);
 		if (!d_unhashed(dentry))
 			d_drop(dentry);
-		if (inode->i_state & I_NEW)
-			discard_new_inode(inode);
+		discard_new_inode(inode);
 	} else {
 		struct dentry *dn;
 
@@ -733,6 +728,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
+	struct inode *new_inode = NULL;
 	struct dentry *dn;
 	struct ceph_acl_sec_ctx as_ctx = {};
 	bool try_async = ceph_test_mount_opt(fsc, ASYNC_DIROPS);
@@ -755,15 +751,16 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 	 */
 	flags &= ~O_TRUNC;
 
+retry:
 	if (flags & O_CREAT) {
 		if (ceph_quota_is_max_files_exceeded(dir))
 			return -EDQUOT;
-		err = ceph_pre_init_acls(dir, &mode, &as_ctx);
-		if (err < 0)
-			return err;
-		err = ceph_security_init_secctx(dentry, mode, &as_ctx);
-		if (err < 0)
+
+		new_inode = ceph_new_inode(dir, dentry, &mode, &as_ctx);
+		if (IS_ERR(new_inode)) {
+			err = PTR_ERR(new_inode);
 			goto out_ctx;
+		}
 		/* Async create can't handle more than a page of xattrs */
 		if (as_ctx.pagelist &&
 		    !list_is_singular(&as_ctx.pagelist->head))
@@ -772,7 +769,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 		/* If it's not being looked up, it's negative */
 		return -ENOENT;
 	}
-retry:
+
 	/* do the open */
 	req = prepare_open_request(dir->i_sb, flags, mode);
 	if (IS_ERR(req)) {
@@ -794,32 +791,47 @@ retry:
 		req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL |
 				     CEPH_CAP_XATTR_EXCL;
 		req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
-		if (as_ctx.pagelist) {
-			req->r_pagelist = as_ctx.pagelist;
-			as_ctx.pagelist = NULL;
-		}
-		if (try_async &&
-		    (req->r_dir_caps =
-		      try_prep_async_create(dir, dentry, &lo,
-					    &req->r_deleg_ino))) {
+
+		ceph_as_ctx_to_req(req, &as_ctx);
+
+		if (try_async && (req->r_dir_caps =
+				  try_prep_async_create(dir, dentry, &lo,
+							&req->r_deleg_ino))) {
+			struct ceph_vino vino = { .ino = req->r_deleg_ino,
+						  .snap = CEPH_NOSNAP };
 			struct ceph_dentry_info *di = ceph_dentry(dentry);
 
 			set_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags);
 			req->r_args.open.flags |= cpu_to_le32(CEPH_O_EXCL);
 			req->r_callback = ceph_async_create_cb;
 
+			/* Hash inode before RPC */
+			new_inode = ceph_get_inode(dir->i_sb, vino, new_inode);
+			if (IS_ERR(new_inode)) {
+				err = PTR_ERR(new_inode);
+				new_inode = NULL;
+				goto out_req;
+			}
+			WARN_ON_ONCE(!(new_inode->i_state & I_NEW));
+
 			spin_lock(&dentry->d_lock);
 			di->flags |= CEPH_DENTRY_ASYNC_CREATE;
 			spin_unlock(&dentry->d_lock);
 
 			err = ceph_mdsc_submit_request(mdsc, dir, req);
 			if (!err) {
-				err = ceph_finish_async_create(dir, dentry,
-							file, mode, req,
-							&as_ctx, &lo);
+				err = ceph_finish_async_create(dir, new_inode,
+							       dentry, file,
+							       mode, req,
+							       &as_ctx, &lo);
+				new_inode = NULL;
 			} else if (err == -EJUKEBOX) {
 				restore_deleg_ino(dir, req->r_deleg_ino);
 				ceph_mdsc_put_request(req);
+				discard_new_inode(new_inode);
+				ceph_release_acl_sec_ctx(&as_ctx);
+				memset(&as_ctx, 0, sizeof(as_ctx));
+				new_inode = NULL;
 				try_async = false;
 				ceph_put_string(rcu_dereference_raw(lo.pool_ns));
 				goto retry;
@@ -830,6 +842,8 @@ retry:
 	}
 
 	set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
+	req->r_new_inode = new_inode;
+	new_inode = NULL;
 	err = ceph_mdsc_do_request(mdsc, (flags & O_CREAT) ? dir : NULL, req);
 	if (err == -ENOENT) {
 		dentry = ceph_handle_snapdir(req, dentry);
@@ -870,6 +884,7 @@ retry:
 	}
 out_req:
 	ceph_mdsc_put_request(req);
+	iput(new_inode);
 out_ctx:
 	ceph_release_acl_sec_ctx(&as_ctx);
 	dout("atomic_open result=%d\n", err);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 8e5f41d45283..e23172024707 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -52,17 +52,87 @@ static int ceph_set_ino_cb(struct inode *inode, void *data)
 	return 0;
 }
 
-struct inode *ceph_get_inode(struct super_block *sb, struct ceph_vino vino)
+/**
+ * ceph_new_inode - allocate a new inode in advance of an expected create
+ * @dir: parent directory for new inode
+ * @dentry: dentry that may eventually point to new inode
+ * @mode: mode of new inode
+ * @as_ctx: pointer to inherited security context
+ *
+ * Allocate a new inode in advance of an operation to create a new inode.
+ * This allocates the inode and sets up the acl_sec_ctx with appropriate
+ * info for the new inode.
+ *
+ * Returns a pointer to the new inode or an ERR_PTR.
+ */
+struct inode *ceph_new_inode(struct inode *dir, struct dentry *dentry,
+			     umode_t *mode, struct ceph_acl_sec_ctx *as_ctx)
+{
+	int err;
+	struct inode *inode;
+
+	inode = new_inode(dir->i_sb);
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+
+	if (!S_ISLNK(*mode)) {
+		err = ceph_pre_init_acls(dir, mode, as_ctx);
+		if (err < 0)
+			goto out_err;
+	}
+
+	err = ceph_security_init_secctx(dentry, *mode, as_ctx);
+	if (err < 0)
+		goto out_err;
+
+	inode->i_state = 0;
+	inode->i_mode = *mode;
+	return inode;
+out_err:
+	iput(inode);
+	return ERR_PTR(err);
+}
+
+void ceph_as_ctx_to_req(struct ceph_mds_request *req,
+			struct ceph_acl_sec_ctx *as_ctx)
+{
+	if (as_ctx->pagelist) {
+		req->r_pagelist = as_ctx->pagelist;
+		as_ctx->pagelist = NULL;
+	}
+}
+
+/**
+ * ceph_get_inode - find or create/hash a new inode
+ * @sb: superblock to search and allocate in
+ * @vino: vino to search for
+ * @newino: optional new inode to insert if one isn't found (may be NULL)
+ *
+ * Search for or insert a new inode into the hash for the given vino, and
+ * return a reference to it. If new is non-NULL, its reference is consumed.
+ */
+struct inode *ceph_get_inode(struct super_block *sb, struct ceph_vino vino,
+			     struct inode *newino)
 {
 	struct inode *inode;
 
 	if (ceph_vino_is_reserved(vino))
 		return ERR_PTR(-EREMOTEIO);
 
-	inode = iget5_locked(sb, (unsigned long)vino.ino, ceph_ino_compare,
-			     ceph_set_ino_cb, &vino);
-	if (!inode)
+	if (newino) {
+		inode = inode_insert5(newino, (unsigned long)vino.ino,
+				      ceph_ino_compare, ceph_set_ino_cb, &vino);
+		if (inode != newino)
+			iput(newino);
+	} else {
+		inode = iget5_locked(sb, (unsigned long)vino.ino,
+				     ceph_ino_compare, ceph_set_ino_cb, &vino);
+	}
+
+	if (!inode) {
+		dout("No inode found for %llx.%llx\n", vino.ino, vino.snap);
 		return ERR_PTR(-ENOMEM);
+	}
 
 	dout("get_inode on %llu=%llx.%llx got %p new %d\n", ceph_present_inode(inode),
 	     ceph_vinop(inode), inode, !!(inode->i_state & I_NEW));
@@ -78,7 +148,7 @@ struct inode *ceph_get_snapdir(struct inode *parent)
 		.ino = ceph_ino(parent),
 		.snap = CEPH_SNAPDIR,
 	};
-	struct inode *inode = ceph_get_inode(parent->i_sb, vino);
+	struct inode *inode = ceph_get_inode(parent->i_sb, vino, NULL);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 
 	if (IS_ERR(inode))
@@ -1551,7 +1621,7 @@ static int readdir_prepopulate_inodes_only(struct ceph_mds_request *req,
 		vino.ino = le64_to_cpu(rde->inode.in->ino);
 		vino.snap = le64_to_cpu(rde->inode.in->snapid);
 
-		in = ceph_get_inode(req->r_dentry->d_sb, vino);
+		in = ceph_get_inode(req->r_dentry->d_sb, vino, NULL);
 		if (IS_ERR(in)) {
 			err = PTR_ERR(in);
 			dout("new_inode badness got %d\n", err);
@@ -1753,7 +1823,7 @@ retry_lookup:
 		if (d_really_is_positive(dn)) {
 			in = d_inode(dn);
 		} else {
-			in = ceph_get_inode(parent->d_sb, tvino);
+			in = ceph_get_inode(parent->d_sb, tvino, NULL);
 			if (IS_ERR(in)) {
 				dout("new_inode badness\n");
 				d_drop(dn);
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 5fb367b1d4b0..73dfea88bb88 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -945,6 +945,7 @@ void ceph_mdsc_release_request(struct kref *kref)
 		iput(req->r_parent);
 	}
 	iput(req->r_target_inode);
+	iput(req->r_new_inode);
 	if (req->r_dentry)
 		dput(req->r_dentry);
 	if (req->r_old_dentry)
@@ -3357,13 +3358,25 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 
 	/* Must find target inode outside of mutexes to avoid deadlocks */
 	if ((err >= 0) && rinfo->head->is_target) {
-		struct inode *in;
+		struct inode *in = xchg(&req->r_new_inode, NULL);
 		struct ceph_vino tvino = {
 			.ino  = le64_to_cpu(rinfo->targeti.in->ino),
 			.snap = le64_to_cpu(rinfo->targeti.in->snapid)
 		};
 
-		in = ceph_get_inode(mdsc->fsc->sb, tvino);
+		/*
+		 * If we ended up opening an existing inode, discard
+		 * r_new_inode
+		 */
+		if (req->r_op == CEPH_MDS_OP_CREATE &&
+		    !req->r_reply_info.has_create_ino) {
+			/* This should never happen on an async create */
+			WARN_ON_ONCE(req->r_deleg_ino);
+			iput(in);
+			in = NULL;
+		}
+
+		in = ceph_get_inode(mdsc->fsc->sb, tvino, in);
 		if (IS_ERR(in)) {
 			err = PTR_ERR(in);
 			mutex_lock(&session->s_mutex);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 86d2965e68a1..3c1aa99c1876 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -263,6 +263,7 @@ struct ceph_mds_request {
 
 	struct inode *r_parent;		    /* parent dir inode */
 	struct inode *r_target_inode;       /* resulting inode */
+	struct inode *r_new_inode;	    /* new inode (for creates) */
 
 #define CEPH_MDS_R_DIRECT_IS_HASH	(1) /* r_direct_hash is valid */
 #define CEPH_MDS_R_ABORTED		(2) /* call was aborted */
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index b9cad57ce606..eb621bb276bd 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -999,6 +999,7 @@ static inline bool __ceph_have_pending_cap_snap(struct ceph_inode_info *ci)
 /* inode.c */
 struct ceph_mds_reply_info_in;
 struct ceph_mds_reply_dirfrag;
+struct ceph_acl_sec_ctx;
 
 extern const struct inode_operations ceph_file_iops;
 
@@ -1006,8 +1007,14 @@ extern struct inode *ceph_alloc_inode(struct super_block *sb);
 extern void ceph_evict_inode(struct inode *inode);
 extern void ceph_free_inode(struct inode *inode);
 
+struct inode *ceph_new_inode(struct inode *dir, struct dentry *dentry,
+			     umode_t *mode, struct ceph_acl_sec_ctx *as_ctx);
+void ceph_as_ctx_to_req(struct ceph_mds_request *req,
+			struct ceph_acl_sec_ctx *as_ctx);
+
 extern struct inode *ceph_get_inode(struct super_block *sb,
-				    struct ceph_vino vino);
+				    struct ceph_vino vino,
+				    struct inode *newino);
 extern struct inode *ceph_get_snapdir(struct inode *parent);
 extern int ceph_fill_file_size(struct inode *inode, int issued,
 			       u32 truncate_seq, u64 truncate_size, u64 size);

From 4c793d4c58b7e57e1eb616e3d032df6b3789a4a3 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Wed, 5 Aug 2020 14:50:48 -0400
Subject: [PATCH 0592/1189] ceph: make ceph_msdc_build_path use ref-walk
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Encryption potentially requires allocation, at which point we'll need to
be in a non-atomic context. Convert ceph_msdc_build_path to take dentry
spinlocks and references instead of using rcu_read_lock to walk the
path.

This is slightly less efficient, and we may want to eventually allow
using RCU when the leaf dentry isn't encrypted.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c | 35 +++++++++++++++++++----------------
 1 file changed, 19 insertions(+), 16 deletions(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 73dfea88bb88..77b5e7b2e5dd 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2387,7 +2387,8 @@ static inline  u64 __get_oldest_tid(struct ceph_mds_client *mdsc)
 char *ceph_mdsc_build_path(struct dentry *dentry, int *plen, u64 *pbase,
 			   int stop_on_nosnap)
 {
-	struct dentry *temp;
+	struct dentry *cur;
+	struct inode *inode;
 	char *path;
 	int pos;
 	unsigned seq;
@@ -2404,34 +2405,35 @@ retry:
 	path[pos] = '\0';
 
 	seq = read_seqbegin(&rename_lock);
-	rcu_read_lock();
-	temp = dentry;
+	cur = dget(dentry);
 	for (;;) {
-		struct inode *inode;
+		struct dentry *temp;
 
-		spin_lock(&temp->d_lock);
-		inode = d_inode(temp);
+		spin_lock(&cur->d_lock);
+		inode = d_inode(cur);
 		if (inode && ceph_snap(inode) == CEPH_SNAPDIR) {
 			dout("build_path path+%d: %p SNAPDIR\n",
-			     pos, temp);
-		} else if (stop_on_nosnap && inode && dentry != temp &&
+			     pos, cur);
+		} else if (stop_on_nosnap && inode && dentry != cur &&
 			   ceph_snap(inode) == CEPH_NOSNAP) {
-			spin_unlock(&temp->d_lock);
+			spin_unlock(&cur->d_lock);
 			pos++; /* get rid of any prepended '/' */
 			break;
 		} else {
-			pos -= temp->d_name.len;
+			pos -= cur->d_name.len;
 			if (pos < 0) {
-				spin_unlock(&temp->d_lock);
+				spin_unlock(&cur->d_lock);
 				break;
 			}
-			memcpy(path + pos, temp->d_name.name, temp->d_name.len);
+			memcpy(path + pos, cur->d_name.name, cur->d_name.len);
 		}
+		temp = cur;
 		spin_unlock(&temp->d_lock);
-		temp = READ_ONCE(temp->d_parent);
+		cur = dget_parent(temp);
+		dput(temp);
 
 		/* Are we at the root? */
-		if (IS_ROOT(temp))
+		if (IS_ROOT(cur))
 			break;
 
 		/* Are we out of buffer? */
@@ -2440,8 +2442,9 @@ retry:
 
 		path[pos] = '/';
 	}
-	base = ceph_ino(d_inode(temp));
-	rcu_read_unlock();
+	inode = d_inode(cur);
+	base = inode ? ceph_ino(inode) : 0;
+	dput(cur);
 
 	if (read_seqretry(&rename_lock, seq))
 		goto retry;

From dee0c5f834605ce9b384ee8b9c7032ffd8db4eca Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Fri, 1 Jul 2022 06:30:12 -0400
Subject: [PATCH 0593/1189] libceph: add new iov_iter-based ceph_msg_data_type
 and ceph_osd_data_type
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add an iov_iter to the unions in ceph_msg_data and ceph_msg_data_cursor.
Instead of requiring a list of pages or bvecs, we can just use an
iov_iter directly, and avoid extra allocations.

We assume that the pages represented by the iter are pinned such that
they shouldn't incur page faults, which is the case for the iov_iters
created by netfs.

While working on this, Al Viro informed me that he was going to change
iov_iter_get_pages to auto-advance the iterator as that pattern is more
or less required for ITER_PIPE anyway. We emulate that here for now by
advancing in the _next op and tracking that amount in the "lastlen"
field.

In the event that _next is called twice without an intervening
_advance, we revert the iov_iter by the remaining lastlen before
calling iov_iter_get_pages.

Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/messenger.h  |  8 ++++
 include/linux/ceph/osd_client.h |  4 ++
 net/ceph/messenger.c            | 77 +++++++++++++++++++++++++++++++++
 net/ceph/osd_client.c           | 27 ++++++++++++
 4 files changed, 116 insertions(+)

diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 9fd7255172ad..2eaaabbe98cb 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -123,6 +123,7 @@ enum ceph_msg_data_type {
 	CEPH_MSG_DATA_BIO,	/* data source/destination is a bio list */
 #endif /* CONFIG_BLOCK */
 	CEPH_MSG_DATA_BVECS,	/* data source/destination is a bio_vec array */
+	CEPH_MSG_DATA_ITER,	/* data source/destination is an iov_iter */
 };
 
 #ifdef CONFIG_BLOCK
@@ -224,6 +225,7 @@ struct ceph_msg_data {
 			bool		own_pages;
 		};
 		struct ceph_pagelist	*pagelist;
+		struct iov_iter		iter;
 	};
 };
 
@@ -248,6 +250,10 @@ struct ceph_msg_data_cursor {
 			struct page	*page;		/* page from list */
 			size_t		offset;		/* bytes from list */
 		};
+		struct {
+			struct iov_iter		iov_iter;
+			unsigned int		lastlen;
+		};
 	};
 };
 
@@ -605,6 +611,8 @@ void ceph_msg_data_add_bio(struct ceph_msg *msg, struct ceph_bio_iter *bio_pos,
 #endif /* CONFIG_BLOCK */
 void ceph_msg_data_add_bvecs(struct ceph_msg *msg,
 			     struct ceph_bvec_iter *bvec_pos);
+void ceph_msg_data_add_iter(struct ceph_msg *msg,
+			    struct iov_iter *iter);
 
 struct ceph_msg *ceph_msg_new2(int type, int front_len, int max_data_items,
 			       gfp_t flags, bool can_fail);
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index bfa4813590da..8f5d2b5bbba2 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -108,6 +108,7 @@ enum ceph_osd_data_type {
 	CEPH_OSD_DATA_TYPE_BIO,
 #endif /* CONFIG_BLOCK */
 	CEPH_OSD_DATA_TYPE_BVECS,
+	CEPH_OSD_DATA_TYPE_ITER,
 };
 
 struct ceph_osd_data {
@@ -131,6 +132,7 @@ struct ceph_osd_data {
 			struct ceph_bvec_iter	bvec_pos;
 			u32			num_bvecs;
 		};
+		struct iov_iter		iter;
 	};
 };
 
@@ -501,6 +503,8 @@ void osd_req_op_extent_osd_data_bvecs(struct ceph_osd_request *osd_req,
 void osd_req_op_extent_osd_data_bvec_pos(struct ceph_osd_request *osd_req,
 					 unsigned int which,
 					 struct ceph_bvec_iter *bvec_pos);
+void osd_req_op_extent_osd_iter(struct ceph_osd_request *osd_req,
+				unsigned int which, struct iov_iter *iter);
 
 extern void osd_req_op_cls_request_data_pagelist(struct ceph_osd_request *,
 					unsigned int which,
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 2eb10d7518e8..10a41cd9c523 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -969,6 +969,62 @@ static bool ceph_msg_data_pagelist_advance(struct ceph_msg_data_cursor *cursor,
 	return true;
 }
 
+static void ceph_msg_data_iter_cursor_init(struct ceph_msg_data_cursor *cursor,
+					   size_t length)
+{
+	struct ceph_msg_data *data = cursor->data;
+
+	cursor->iov_iter = data->iter;
+	cursor->lastlen = 0;
+	iov_iter_truncate(&cursor->iov_iter, length);
+	cursor->resid = iov_iter_count(&cursor->iov_iter);
+}
+
+static struct page *ceph_msg_data_iter_next(struct ceph_msg_data_cursor *cursor,
+					    size_t *page_offset, size_t *length)
+{
+	struct page *page;
+	ssize_t len;
+
+	if (cursor->lastlen)
+		iov_iter_revert(&cursor->iov_iter, cursor->lastlen);
+
+	len = iov_iter_get_pages2(&cursor->iov_iter, &page, PAGE_SIZE,
+				  1, page_offset);
+	BUG_ON(len < 0);
+
+	cursor->lastlen = len;
+
+	/*
+	 * FIXME: The assumption is that the pages represented by the iov_iter
+	 *	  are pinned, with the references held by the upper-level
+	 *	  callers, or by virtue of being under writeback. Eventually,
+	 *	  we'll get an iov_iter_get_pages2 variant that doesn't take
+	 *	  page refs. Until then, just put the page ref.
+	 */
+	VM_BUG_ON_PAGE(!PageWriteback(page) && page_count(page) < 2, page);
+	put_page(page);
+
+	*length = min_t(size_t, len, cursor->resid);
+	return page;
+}
+
+static bool ceph_msg_data_iter_advance(struct ceph_msg_data_cursor *cursor,
+				       size_t bytes)
+{
+	BUG_ON(bytes > cursor->resid);
+	cursor->resid -= bytes;
+
+	if (bytes < cursor->lastlen) {
+		cursor->lastlen -= bytes;
+	} else {
+		iov_iter_advance(&cursor->iov_iter, bytes - cursor->lastlen);
+		cursor->lastlen = 0;
+	}
+
+	return cursor->resid;
+}
+
 /*
  * Message data is handled (sent or received) in pieces, where each
  * piece resides on a single page.  The network layer might not
@@ -996,6 +1052,9 @@ static void __ceph_msg_data_cursor_init(struct ceph_msg_data_cursor *cursor)
 	case CEPH_MSG_DATA_BVECS:
 		ceph_msg_data_bvecs_cursor_init(cursor, length);
 		break;
+	case CEPH_MSG_DATA_ITER:
+		ceph_msg_data_iter_cursor_init(cursor, length);
+		break;
 	case CEPH_MSG_DATA_NONE:
 	default:
 		/* BUG(); */
@@ -1043,6 +1102,9 @@ struct page *ceph_msg_data_next(struct ceph_msg_data_cursor *cursor,
 	case CEPH_MSG_DATA_BVECS:
 		page = ceph_msg_data_bvecs_next(cursor, page_offset, length);
 		break;
+	case CEPH_MSG_DATA_ITER:
+		page = ceph_msg_data_iter_next(cursor, page_offset, length);
+		break;
 	case CEPH_MSG_DATA_NONE:
 	default:
 		page = NULL;
@@ -1081,6 +1143,9 @@ void ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor, size_t bytes)
 	case CEPH_MSG_DATA_BVECS:
 		new_piece = ceph_msg_data_bvecs_advance(cursor, bytes);
 		break;
+	case CEPH_MSG_DATA_ITER:
+		new_piece = ceph_msg_data_iter_advance(cursor, bytes);
+		break;
 	case CEPH_MSG_DATA_NONE:
 	default:
 		BUG();
@@ -1880,6 +1945,18 @@ void ceph_msg_data_add_bvecs(struct ceph_msg *msg,
 }
 EXPORT_SYMBOL(ceph_msg_data_add_bvecs);
 
+void ceph_msg_data_add_iter(struct ceph_msg *msg,
+			    struct iov_iter *iter)
+{
+	struct ceph_msg_data *data;
+
+	data = ceph_msg_data_add(msg);
+	data->type = CEPH_MSG_DATA_ITER;
+	data->iter = *iter;
+
+	msg->data_length += iov_iter_count(&data->iter);
+}
+
 /*
  * construct a new message with given type, size
  * the new msg has a ref count of 1.
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 0aacbadcab06..684faf8553de 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -171,6 +171,13 @@ static void ceph_osd_data_bvecs_init(struct ceph_osd_data *osd_data,
 	osd_data->num_bvecs = num_bvecs;
 }
 
+static void ceph_osd_iter_init(struct ceph_osd_data *osd_data,
+			       struct iov_iter *iter)
+{
+	osd_data->type = CEPH_OSD_DATA_TYPE_ITER;
+	osd_data->iter = *iter;
+}
+
 static struct ceph_osd_data *
 osd_req_op_raw_data_in(struct ceph_osd_request *osd_req, unsigned int which)
 {
@@ -264,6 +271,22 @@ void osd_req_op_extent_osd_data_bvec_pos(struct ceph_osd_request *osd_req,
 }
 EXPORT_SYMBOL(osd_req_op_extent_osd_data_bvec_pos);
 
+/**
+ * osd_req_op_extent_osd_iter - Set up an operation with an iterator buffer
+ * @osd_req: The request to set up
+ * @which: Index of the operation in which to set the iter
+ * @iter: The buffer iterator
+ */
+void osd_req_op_extent_osd_iter(struct ceph_osd_request *osd_req,
+				unsigned int which, struct iov_iter *iter)
+{
+	struct ceph_osd_data *osd_data;
+
+	osd_data = osd_req_op_data(osd_req, which, extent, osd_data);
+	ceph_osd_iter_init(osd_data, iter);
+}
+EXPORT_SYMBOL(osd_req_op_extent_osd_iter);
+
 static void osd_req_op_cls_request_info_pagelist(
 			struct ceph_osd_request *osd_req,
 			unsigned int which, struct ceph_pagelist *pagelist)
@@ -346,6 +369,8 @@ static u64 ceph_osd_data_length(struct ceph_osd_data *osd_data)
 #endif /* CONFIG_BLOCK */
 	case CEPH_OSD_DATA_TYPE_BVECS:
 		return osd_data->bvec_pos.iter.bi_size;
+	case CEPH_OSD_DATA_TYPE_ITER:
+		return iov_iter_count(&osd_data->iter);
 	default:
 		WARN(true, "unrecognized data type %d\n", (int)osd_data->type);
 		return 0;
@@ -954,6 +979,8 @@ static void ceph_osdc_msg_data_add(struct ceph_msg *msg,
 #endif
 	} else if (osd_data->type == CEPH_OSD_DATA_TYPE_BVECS) {
 		ceph_msg_data_add_bvecs(msg, &osd_data->bvec_pos);
+	} else if (osd_data->type == CEPH_OSD_DATA_TYPE_ITER) {
+		ceph_msg_data_add_iter(msg, &osd_data->iter);
 	} else {
 		BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_NONE);
 	}

From 4de77f25fd857a9dd0614416025af51b45c1cb2a Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Mon, 2 Jan 2023 12:36:14 +0100
Subject: [PATCH 0594/1189] ceph: use osd_req_op_extent_osd_iter for netfs
 reads
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The netfs layer has already pinned the pages involved before calling
issue_op, so we can just pass down the iter directly instead of calling
iov_iter_get_pages_alloc.

Instead of having to allocate a page array, use CEPH_MSG_DATA_ITER and
pass it the iov_iter directly to clone.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/addr.c | 19 +------------------
 1 file changed, 1 insertion(+), 18 deletions(-)

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index f45ebe957bbe..611443d06330 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -246,7 +246,6 @@ static void finish_netfs_read(struct ceph_osd_request *req)
 	struct ceph_osd_data *osd_data = osd_req_op_extent_osd_data(req, 0);
 	struct netfs_io_subrequest *subreq = req->r_priv;
 	struct ceph_osd_req_op *op = &req->r_ops[0];
-	int num_pages;
 	int err = req->r_result;
 	bool sparse = (op->op == CEPH_OSD_OP_SPARSE_READ);
 
@@ -268,9 +267,6 @@ static void finish_netfs_read(struct ceph_osd_request *req)
 		__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
 
 	netfs_subreq_terminated(subreq, err, false);
-
-	num_pages = calc_pages_for(osd_data->alignment, osd_data->length);
-	ceph_put_page_vector(osd_data->pages, num_pages, false);
 	iput(req->r_inode);
 }
 
@@ -338,8 +334,6 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 	struct ceph_osd_request *req = NULL;
 	struct ceph_vino vino = ceph_vino(inode);
 	struct iov_iter iter;
-	struct page **pages;
-	size_t page_off;
 	int err = 0;
 	u64 len = subreq->len;
 	bool sparse = ceph_test_mount_opt(fsc, SPARSEREAD);
@@ -370,18 +364,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 
 	dout("%s: pos=%llu orig_len=%zu len=%llu\n", __func__, subreq->start, subreq->len, len);
 	iov_iter_xarray(&iter, ITER_DEST, &rreq->mapping->i_pages, subreq->start, len);
-	err = iov_iter_get_pages_alloc2(&iter, &pages, len, &page_off);
-	if (err < 0) {
-		dout("%s: iov_ter_get_pages_alloc returned %d\n", __func__, err);
-		goto out;
-	}
-
-	/* should always give us a page-aligned read */
-	WARN_ON_ONCE(page_off);
-	len = err;
-	err = 0;
-
-	osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0, false, false);
+	osd_req_op_extent_osd_iter(req, 0, &iter);
 	req->r_callback = finish_netfs_read;
 	req->r_priv = subreq;
 	req->r_inode = inode;

From 2d332d5bc424404911540006a8bb450fbb96b178 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Mon, 27 Jul 2020 10:16:09 -0400
Subject: [PATCH 0595/1189] ceph: fscrypt_auth handling for ceph
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Most fscrypt-enabled filesystems store the crypto context in an xattr,
but that's problematic for ceph as xatts are governed by the XATTR cap,
but we really want the crypto context as part of the AUTH cap.

Because of this, the MDS has added two new inode metadata fields:
fscrypt_auth and fscrypt_file. The former is used to hold the crypto
context, and the latter is used to track the real file size.

Parse new fscrypt_auth and fscrypt_file fields in inode traces. For now,
we don't use fscrypt_file, but fscrypt_auth is used to hold the fscrypt
context.

Allow the client to use a setattr request for setting the fscrypt_auth
field. Since this is not a standard setattr request from the VFS, we add
a new field to __ceph_setattr that carries ceph-specific inode attrs.

Have the set_context op do a setattr that sets the fscrypt_auth value,
and get_context just return the contents of that field (since it should
always be available).

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/Makefile             |   1 +
 fs/ceph/acl.c                |   4 +-
 fs/ceph/caps.c               |  78 ++++++++++++++++++++----
 fs/ceph/crypto.c             |  77 +++++++++++++++++++++++
 fs/ceph/crypto.h             |  36 +++++++++++
 fs/ceph/inode.c              |  64 +++++++++++++++++++-
 fs/ceph/mds_client.c         | 114 ++++++++++++++++++++++++++++++++---
 fs/ceph/mds_client.h         |   7 +++
 fs/ceph/super.c              |   3 +
 fs/ceph/super.h              |  15 ++++-
 include/linux/ceph/ceph_fs.h |  21 ++++---
 11 files changed, 385 insertions(+), 35 deletions(-)
 create mode 100644 fs/ceph/crypto.c
 create mode 100644 fs/ceph/crypto.h

diff --git a/fs/ceph/Makefile b/fs/ceph/Makefile
index 50c635dc7f71..1f77ca04c426 100644
--- a/fs/ceph/Makefile
+++ b/fs/ceph/Makefile
@@ -12,3 +12,4 @@ ceph-y := super.o inode.o dir.o file.o locks.o addr.o ioctl.o \
 
 ceph-$(CONFIG_CEPH_FSCACHE) += cache.o
 ceph-$(CONFIG_CEPH_FS_POSIX_ACL) += acl.o
+ceph-$(CONFIG_FS_ENCRYPTION) += crypto.o
diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c
index 6945a938d396..8a56f979c7cb 100644
--- a/fs/ceph/acl.c
+++ b/fs/ceph/acl.c
@@ -140,7 +140,7 @@ int ceph_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 		newattrs.ia_ctime = current_time(inode);
 		newattrs.ia_mode = new_mode;
 		newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
-		ret = __ceph_setattr(inode, &newattrs);
+		ret = __ceph_setattr(inode, &newattrs, NULL);
 		if (ret)
 			goto out_free;
 	}
@@ -151,7 +151,7 @@ int ceph_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 			newattrs.ia_ctime = old_ctime;
 			newattrs.ia_mode = old_mode;
 			newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
-			__ceph_setattr(inode, &newattrs);
+			__ceph_setattr(inode, &newattrs, NULL);
 		}
 		goto out_free;
 	}
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index e2bb0d0072da..1c62ef339bc6 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -14,6 +14,7 @@
 #include "super.h"
 #include "mds_client.h"
 #include "cache.h"
+#include "crypto.h"
 #include <linux/ceph/decode.h>
 #include <linux/ceph/messenger.h>
 
@@ -1216,15 +1217,12 @@ struct cap_msg_args {
 	umode_t			mode;
 	bool			inline_data;
 	bool			wake;
+	u32			fscrypt_auth_len;
+	u32			fscrypt_file_len;
+	u8			fscrypt_auth[sizeof(struct ceph_fscrypt_auth)]; // for context
+	u8			fscrypt_file[sizeof(u64)]; // for size
 };
 
-/*
- * cap struct size + flock buffer size + inline version + inline data size +
- * osd_epoch_barrier + oldest_flush_tid
- */
-#define CAP_MSG_SIZE (sizeof(struct ceph_mds_caps) + \
-		      4 + 8 + 4 + 4 + 8 + 4 + 4 + 4 + 8 + 8 + 4)
-
 /* Marshal up the cap msg to the MDS */
 static void encode_cap_msg(struct ceph_msg *msg, struct cap_msg_args *arg)
 {
@@ -1240,7 +1238,7 @@ static void encode_cap_msg(struct ceph_msg *msg, struct cap_msg_args *arg)
 	     arg->size, arg->max_size, arg->xattr_version,
 	     arg->xattr_buf ? (int)arg->xattr_buf->vec.iov_len : 0);
 
-	msg->hdr.version = cpu_to_le16(10);
+	msg->hdr.version = cpu_to_le16(12);
 	msg->hdr.tid = cpu_to_le64(arg->flush_tid);
 
 	fc = msg->front.iov_base;
@@ -1311,6 +1309,21 @@ static void encode_cap_msg(struct ceph_msg *msg, struct cap_msg_args *arg)
 
 	/* Advisory flags (version 10) */
 	ceph_encode_32(&p, arg->flags);
+
+	/* dirstats (version 11) - these are r/o on the client */
+	ceph_encode_64(&p, 0);
+	ceph_encode_64(&p, 0);
+
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+	/* fscrypt_auth and fscrypt_file (version 12) */
+	ceph_encode_32(&p, arg->fscrypt_auth_len);
+	ceph_encode_copy(&p, arg->fscrypt_auth, arg->fscrypt_auth_len);
+	ceph_encode_32(&p, arg->fscrypt_file_len);
+	ceph_encode_copy(&p, arg->fscrypt_file, arg->fscrypt_file_len);
+#else /* CONFIG_FS_ENCRYPTION */
+	ceph_encode_32(&p, 0);
+	ceph_encode_32(&p, 0);
+#endif /* CONFIG_FS_ENCRYPTION */
 }
 
 /*
@@ -1432,8 +1445,38 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap,
 		}
 	}
 	arg->flags = flags;
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+	if (ci->fscrypt_auth_len &&
+	    WARN_ON_ONCE(ci->fscrypt_auth_len > sizeof(struct ceph_fscrypt_auth))) {
+		/* Don't set this if it's too big */
+		arg->fscrypt_auth_len = 0;
+	} else {
+		arg->fscrypt_auth_len = ci->fscrypt_auth_len;
+		memcpy(arg->fscrypt_auth, ci->fscrypt_auth,
+		       min_t(size_t, ci->fscrypt_auth_len,
+			     sizeof(arg->fscrypt_auth)));
+	}
+	/* FIXME: use this to track "real" size */
+	arg->fscrypt_file_len = 0;
+#endif /* CONFIG_FS_ENCRYPTION */
 }
 
+#define CAP_MSG_FIXED_FIELDS (sizeof(struct ceph_mds_caps) + \
+		      4 + 8 + 4 + 4 + 8 + 4 + 4 + 4 + 8 + 8 + 4 + 8 + 8 + 4 + 4)
+
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+static inline int cap_msg_size(struct cap_msg_args *arg)
+{
+	return CAP_MSG_FIXED_FIELDS + arg->fscrypt_auth_len +
+			arg->fscrypt_file_len;
+}
+#else
+static inline int cap_msg_size(struct cap_msg_args *arg)
+{
+	return CAP_MSG_FIXED_FIELDS;
+}
+#endif /* CONFIG_FS_ENCRYPTION */
+
 /*
  * Send a cap msg on the given inode.
  *
@@ -1444,7 +1487,8 @@ static void __send_cap(struct cap_msg_args *arg, struct ceph_inode_info *ci)
 	struct ceph_msg *msg;
 	struct inode *inode = &ci->netfs.inode;
 
-	msg = ceph_msg_new(CEPH_MSG_CLIENT_CAPS, CAP_MSG_SIZE, GFP_NOFS, false);
+	msg = ceph_msg_new(CEPH_MSG_CLIENT_CAPS, cap_msg_size(arg), GFP_NOFS,
+			   false);
 	if (!msg) {
 		pr_err("error allocating cap msg: ino (%llx.%llx) flushing %s tid %llu, requeuing cap.\n",
 		       ceph_vinop(inode), ceph_cap_string(arg->dirty),
@@ -1470,10 +1514,6 @@ static inline int __send_flush_snap(struct inode *inode,
 	struct cap_msg_args	arg;
 	struct ceph_msg		*msg;
 
-	msg = ceph_msg_new(CEPH_MSG_CLIENT_CAPS, CAP_MSG_SIZE, GFP_NOFS, false);
-	if (!msg)
-		return -ENOMEM;
-
 	arg.session = session;
 	arg.ino = ceph_vino(inode).ino;
 	arg.cid = 0;
@@ -1511,6 +1551,18 @@ static inline int __send_flush_snap(struct inode *inode,
 	arg.flags = 0;
 	arg.wake = false;
 
+	/*
+	 * No fscrypt_auth changes from a capsnap. It will need
+	 * to update fscrypt_file on size changes (TODO).
+	 */
+	arg.fscrypt_auth_len = 0;
+	arg.fscrypt_file_len = 0;
+
+	msg = ceph_msg_new(CEPH_MSG_CLIENT_CAPS, cap_msg_size(&arg),
+			   GFP_NOFS, false);
+	if (!msg)
+		return -ENOMEM;
+
 	encode_cap_msg(msg, &arg);
 	ceph_con_send(&arg.session->s_con, msg);
 	return 0;
diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c
new file mode 100644
index 000000000000..b17a6ee16cf0
--- /dev/null
+++ b/fs/ceph/crypto.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ceph/ceph_debug.h>
+#include <linux/xattr.h>
+#include <linux/fscrypt.h>
+
+#include "super.h"
+#include "crypto.h"
+
+static int ceph_crypt_get_context(struct inode *inode, void *ctx, size_t len)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_fscrypt_auth *cfa = (struct ceph_fscrypt_auth *)ci->fscrypt_auth;
+	u32 ctxlen;
+
+	/* Non existent or too short? */
+	if (!cfa || (ci->fscrypt_auth_len < (offsetof(struct ceph_fscrypt_auth, cfa_blob) + 1)))
+		return -ENOBUFS;
+
+	/* Some format we don't recognize? */
+	if (le32_to_cpu(cfa->cfa_version) != CEPH_FSCRYPT_AUTH_VERSION)
+		return -ENOBUFS;
+
+	ctxlen = le32_to_cpu(cfa->cfa_blob_len);
+	if (len < ctxlen)
+		return -ERANGE;
+
+	memcpy(ctx, cfa->cfa_blob, ctxlen);
+	return ctxlen;
+}
+
+static int ceph_crypt_set_context(struct inode *inode, const void *ctx,
+				  size_t len, void *fs_data)
+{
+	int ret;
+	struct iattr attr = { };
+	struct ceph_iattr cia = { };
+	struct ceph_fscrypt_auth *cfa;
+
+	WARN_ON_ONCE(fs_data);
+
+	if (len > FSCRYPT_SET_CONTEXT_MAX_SIZE)
+		return -EINVAL;
+
+	cfa = kzalloc(sizeof(*cfa), GFP_KERNEL);
+	if (!cfa)
+		return -ENOMEM;
+
+	cfa->cfa_version = cpu_to_le32(CEPH_FSCRYPT_AUTH_VERSION);
+	cfa->cfa_blob_len = cpu_to_le32(len);
+	memcpy(cfa->cfa_blob, ctx, len);
+
+	cia.fscrypt_auth = cfa;
+
+	ret = __ceph_setattr(inode, &attr, &cia);
+	if (ret == 0)
+		inode_set_flags(inode, S_ENCRYPTED, S_ENCRYPTED);
+	kfree(cia.fscrypt_auth);
+	return ret;
+}
+
+static bool ceph_crypt_empty_dir(struct inode *inode)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	return ci->i_rsubdirs + ci->i_rfiles == 1;
+}
+
+static struct fscrypt_operations ceph_fscrypt_ops = {
+	.get_context		= ceph_crypt_get_context,
+	.set_context		= ceph_crypt_set_context,
+	.empty_dir		= ceph_crypt_empty_dir,
+};
+
+void ceph_fscrypt_set_ops(struct super_block *sb)
+{
+	fscrypt_set_ops(sb, &ceph_fscrypt_ops);
+}
diff --git a/fs/ceph/crypto.h b/fs/ceph/crypto.h
new file mode 100644
index 000000000000..6dca674f79b8
--- /dev/null
+++ b/fs/ceph/crypto.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Ceph fscrypt functionality
+ */
+
+#ifndef _CEPH_CRYPTO_H
+#define _CEPH_CRYPTO_H
+
+#include <linux/fscrypt.h>
+
+struct ceph_fscrypt_auth {
+	__le32	cfa_version;
+	__le32	cfa_blob_len;
+	u8	cfa_blob[FSCRYPT_SET_CONTEXT_MAX_SIZE];
+} __packed;
+
+#define CEPH_FSCRYPT_AUTH_VERSION	1
+static inline u32 ceph_fscrypt_auth_len(struct ceph_fscrypt_auth *fa)
+{
+	u32 ctxsize = le32_to_cpu(fa->cfa_blob_len);
+
+	return offsetof(struct ceph_fscrypt_auth, cfa_blob) + ctxsize;
+}
+
+#ifdef CONFIG_FS_ENCRYPTION
+void ceph_fscrypt_set_ops(struct super_block *sb);
+
+#else /* CONFIG_FS_ENCRYPTION */
+
+static inline void ceph_fscrypt_set_ops(struct super_block *sb)
+{
+}
+
+#endif /* CONFIG_FS_ENCRYPTION */
+
+#endif
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index e23172024707..a3aa7870a6a2 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -14,10 +14,12 @@
 #include <linux/random.h>
 #include <linux/sort.h>
 #include <linux/iversion.h>
+#include <linux/fscrypt.h>
 
 #include "super.h"
 #include "mds_client.h"
 #include "cache.h"
+#include "crypto.h"
 #include <linux/ceph/decode.h>
 
 /*
@@ -617,6 +619,10 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 	INIT_WORK(&ci->i_work, ceph_inode_work);
 	ci->i_work_mask = 0;
 	memset(&ci->i_btime, '\0', sizeof(ci->i_btime));
+#ifdef CONFIG_FS_ENCRYPTION
+	ci->fscrypt_auth = NULL;
+	ci->fscrypt_auth_len = 0;
+#endif
 	return &ci->netfs.inode;
 }
 
@@ -625,6 +631,9 @@ void ceph_free_inode(struct inode *inode)
 	struct ceph_inode_info *ci = ceph_inode(inode);
 
 	kfree(ci->i_symlink);
+#ifdef CONFIG_FS_ENCRYPTION
+	kfree(ci->fscrypt_auth);
+#endif
 	kmem_cache_free(ceph_inode_cachep, ci);
 }
 
@@ -645,6 +654,7 @@ void ceph_evict_inode(struct inode *inode)
 	clear_inode(inode);
 
 	ceph_fscache_unregister_inode_cookie(ci);
+	fscrypt_put_encryption_info(inode);
 
 	__ceph_remove_caps(ci);
 
@@ -935,6 +945,17 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 
 	__ceph_update_quota(ci, iinfo->max_bytes, iinfo->max_files);
 
+#ifdef CONFIG_FS_ENCRYPTION
+	if (iinfo->fscrypt_auth_len && (inode->i_state & I_NEW)) {
+		kfree(ci->fscrypt_auth);
+		ci->fscrypt_auth_len = iinfo->fscrypt_auth_len;
+		ci->fscrypt_auth = iinfo->fscrypt_auth;
+		iinfo->fscrypt_auth = NULL;
+		iinfo->fscrypt_auth_len = 0;
+		inode_set_flags(inode, S_ENCRYPTED, S_ENCRYPTED);
+	}
+#endif
+
 	if ((new_version || (new_issued & CEPH_CAP_AUTH_SHARED)) &&
 	    (issued & CEPH_CAP_AUTH_EXCL) == 0) {
 		inode->i_mode = mode;
@@ -2079,7 +2100,8 @@ static const struct inode_operations ceph_symlink_iops = {
 	.listxattr = ceph_listxattr,
 };
 
-int __ceph_setattr(struct inode *inode, struct iattr *attr)
+int __ceph_setattr(struct inode *inode, struct iattr *attr,
+		   struct ceph_iattr *cia)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	unsigned int ia_valid = attr->ia_valid;
@@ -2119,6 +2141,43 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr)
 	}
 
 	dout("setattr %p issued %s\n", inode, ceph_cap_string(issued));
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+	if (cia && cia->fscrypt_auth) {
+		u32 len = ceph_fscrypt_auth_len(cia->fscrypt_auth);
+
+		if (len > sizeof(*cia->fscrypt_auth)) {
+			err = -EINVAL;
+			spin_unlock(&ci->i_ceph_lock);
+			goto out;
+		}
+
+		dout("setattr %llx:%llx fscrypt_auth len %u to %u)\n",
+			ceph_vinop(inode), ci->fscrypt_auth_len, len);
+
+		/* It should never be re-set once set */
+		WARN_ON_ONCE(ci->fscrypt_auth);
+
+		if (issued & CEPH_CAP_AUTH_EXCL) {
+			dirtied |= CEPH_CAP_AUTH_EXCL;
+			kfree(ci->fscrypt_auth);
+			ci->fscrypt_auth = (u8 *)cia->fscrypt_auth;
+			ci->fscrypt_auth_len = len;
+		} else if ((issued & CEPH_CAP_AUTH_SHARED) == 0 ||
+			   ci->fscrypt_auth_len != len ||
+			   memcmp(ci->fscrypt_auth, cia->fscrypt_auth, len)) {
+			req->r_fscrypt_auth = cia->fscrypt_auth;
+			mask |= CEPH_SETATTR_FSCRYPT_AUTH;
+			release |= CEPH_CAP_AUTH_SHARED;
+		}
+		cia->fscrypt_auth = NULL;
+	}
+#else
+	if (cia && cia->fscrypt_auth) {
+		err = -EINVAL;
+		spin_unlock(&ci->i_ceph_lock);
+		goto out;
+	}
+#endif /* CONFIG_FS_ENCRYPTION */
 
 	if (ia_valid & ATTR_UID) {
 		dout("setattr %p uid %d -> %d\n", inode,
@@ -2282,6 +2341,7 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr)
 		req->r_stamp = attr->ia_ctime;
 		err = ceph_mdsc_do_request(mdsc, NULL, req);
 	}
+out:
 	dout("setattr %p result=%d (%s locally, %d remote)\n", inode, err,
 	     ceph_cap_string(dirtied), mask);
 
@@ -2322,7 +2382,7 @@ int ceph_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	    ceph_quota_is_max_bytes_exceeded(inode, attr->ia_size))
 		return -EDQUOT;
 
-	err = __ceph_setattr(inode, attr);
+	err = __ceph_setattr(inode, attr, NULL);
 
 	if (err >= 0 && (attr->ia_valid & ATTR_MODE))
 		err = posix_acl_chmod(&nop_mnt_idmap, dentry, attr->ia_mode);
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 77b5e7b2e5dd..c3927dab5a3b 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -15,6 +15,7 @@
 
 #include "super.h"
 #include "mds_client.h"
+#include "crypto.h"
 
 #include <linux/ceph/ceph_features.h>
 #include <linux/ceph/messenger.h>
@@ -184,8 +185,54 @@ static int parse_reply_info_in(void **p, void *end,
 			info->rsnaps = 0;
 		}
 
+		if (struct_v >= 5) {
+			u32 alen;
+
+			ceph_decode_32_safe(p, end, alen, bad);
+
+			while (alen--) {
+				u32 len;
+
+				/* key */
+				ceph_decode_32_safe(p, end, len, bad);
+				ceph_decode_skip_n(p, end, len, bad);
+				/* value */
+				ceph_decode_32_safe(p, end, len, bad);
+				ceph_decode_skip_n(p, end, len, bad);
+			}
+		}
+
+		/* fscrypt flag -- ignore */
+		if (struct_v >= 6)
+			ceph_decode_skip_8(p, end, bad);
+
+		info->fscrypt_auth = NULL;
+		info->fscrypt_auth_len = 0;
+		info->fscrypt_file = NULL;
+		info->fscrypt_file_len = 0;
+		if (struct_v >= 7) {
+			ceph_decode_32_safe(p, end, info->fscrypt_auth_len, bad);
+			if (info->fscrypt_auth_len) {
+				info->fscrypt_auth = kmalloc(info->fscrypt_auth_len,
+							     GFP_KERNEL);
+				if (!info->fscrypt_auth)
+					return -ENOMEM;
+				ceph_decode_copy_safe(p, end, info->fscrypt_auth,
+						      info->fscrypt_auth_len, bad);
+			}
+			ceph_decode_32_safe(p, end, info->fscrypt_file_len, bad);
+			if (info->fscrypt_file_len) {
+				info->fscrypt_file = kmalloc(info->fscrypt_file_len,
+							     GFP_KERNEL);
+				if (!info->fscrypt_file)
+					return -ENOMEM;
+				ceph_decode_copy_safe(p, end, info->fscrypt_file,
+						      info->fscrypt_file_len, bad);
+			}
+		}
 		*p = end;
 	} else {
+		/* legacy (unversioned) struct */
 		if (features & CEPH_FEATURE_MDS_INLINE_DATA) {
 			ceph_decode_64_safe(p, end, info->inline_version, bad);
 			ceph_decode_32_safe(p, end, info->inline_len, bad);
@@ -651,8 +698,21 @@ out_bad:
 
 static void destroy_reply_info(struct ceph_mds_reply_info_parsed *info)
 {
+	int i;
+
+	kfree(info->diri.fscrypt_auth);
+	kfree(info->diri.fscrypt_file);
+	kfree(info->targeti.fscrypt_auth);
+	kfree(info->targeti.fscrypt_file);
 	if (!info->dir_entries)
 		return;
+
+	for (i = 0; i < info->dir_nr; i++) {
+		struct ceph_mds_reply_dir_entry *rde = info->dir_entries + i;
+
+		kfree(rde->inode.fscrypt_auth);
+		kfree(rde->inode.fscrypt_file);
+	}
 	free_pages((unsigned long)info->dir_entries, get_order(info->dir_buf_size));
 }
 
@@ -966,6 +1026,7 @@ void ceph_mdsc_release_request(struct kref *kref)
 	put_cred(req->r_cred);
 	if (req->r_pagelist)
 		ceph_pagelist_release(req->r_pagelist);
+	kfree(req->r_fscrypt_auth);
 	put_request_session(req);
 	ceph_unreserve_caps(req->r_mdsc, &req->r_caps_reservation);
 	WARN_ON_ONCE(!list_empty(&req->r_wait));
@@ -2543,8 +2604,8 @@ static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry,
 	return r;
 }
 
-static void encode_timestamp_and_gids(void **p,
-				      const struct ceph_mds_request *req)
+static void encode_mclientrequest_tail(void **p,
+				       const struct ceph_mds_request *req)
 {
 	struct ceph_timespec ts;
 	int i;
@@ -2557,6 +2618,20 @@ static void encode_timestamp_and_gids(void **p,
 	for (i = 0; i < req->r_cred->group_info->ngroups; i++)
 		ceph_encode_64(p, from_kgid(&init_user_ns,
 					    req->r_cred->group_info->gid[i]));
+
+	/* v5: altname (TODO: skip for now) */
+	ceph_encode_32(p, 0);
+
+	/* v6: fscrypt_auth and fscrypt_file */
+	if (req->r_fscrypt_auth) {
+		u32 authlen = ceph_fscrypt_auth_len(req->r_fscrypt_auth);
+
+		ceph_encode_32(p, authlen);
+		ceph_encode_copy(p, req->r_fscrypt_auth, authlen);
+	} else {
+		ceph_encode_32(p, 0);
+	}
+	ceph_encode_32(p, 0); // fscrypt_file for now
 }
 
 /*
@@ -2605,12 +2680,14 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 		goto out_free1;
 	}
 
+	/* head */
 	len = legacy ? sizeof(*head) : sizeof(struct ceph_mds_request_head);
-	len += pathlen1 + pathlen2 + 2*(1 + sizeof(u32) + sizeof(u64)) +
-		sizeof(struct ceph_timespec);
-	len += sizeof(u32) + (sizeof(u64) * req->r_cred->group_info->ngroups);
 
-	/* calculate (max) length for cap releases */
+	/* filepaths */
+	len += 2 * (1 + sizeof(u32) + sizeof(u64));
+	len += pathlen1 + pathlen2;
+
+	/* cap releases */
 	len += sizeof(struct ceph_mds_request_release) *
 		(!!req->r_inode_drop + !!req->r_dentry_drop +
 		 !!req->r_old_inode_drop + !!req->r_old_dentry_drop);
@@ -2620,6 +2697,25 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 	if (req->r_old_dentry_drop)
 		len += pathlen2;
 
+	/* MClientRequest tail */
+
+	/* req->r_stamp */
+	len += sizeof(struct ceph_timespec);
+
+	/* gid list */
+	len += sizeof(u32) + (sizeof(u64) * req->r_cred->group_info->ngroups);
+
+	/* alternate name */
+	len += sizeof(u32);	// TODO
+
+	/* fscrypt_auth */
+	len += sizeof(u32); // fscrypt_auth
+	if (req->r_fscrypt_auth)
+		len += ceph_fscrypt_auth_len(req->r_fscrypt_auth);
+
+	/* fscrypt_file */
+	len += sizeof(u32);
+
 	msg = ceph_msg_new2(CEPH_MSG_CLIENT_REQUEST, len, 1, GFP_NOFS, false);
 	if (!msg) {
 		msg = ERR_PTR(-ENOMEM);
@@ -2639,7 +2735,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 	} else {
 		struct ceph_mds_request_head *new_head = msg->front.iov_base;
 
-		msg->hdr.version = cpu_to_le16(4);
+		msg->hdr.version = cpu_to_le16(6);
 		new_head->version = cpu_to_le16(CEPH_MDS_REQUEST_HEAD_VERSION);
 		head = (struct ceph_mds_request_head_old *)&new_head->oldest_client_tid;
 		p = msg->front.iov_base + sizeof(*new_head);
@@ -2690,7 +2786,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 
 	head->num_releases = cpu_to_le16(releases);
 
-	encode_timestamp_and_gids(&p, req);
+	encode_mclientrequest_tail(&p, req);
 
 	if (WARN_ON_ONCE(p > end)) {
 		ceph_msg_put(msg);
@@ -2820,7 +2916,7 @@ static int __prepare_send_request(struct ceph_mds_session *session,
 		rhead->num_releases = 0;
 
 		p = msg->front.iov_base + req->r_request_release_offset;
-		encode_timestamp_and_gids(&p, req);
+		encode_mclientrequest_tail(&p, req);
 
 		msg->front.iov_len = p - msg->front.iov_base;
 		msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 3c1aa99c1876..a2e85fb5aab1 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -86,6 +86,10 @@ struct ceph_mds_reply_info_in {
 	s32 dir_pin;
 	struct ceph_timespec btime;
 	struct ceph_timespec snap_btime;
+	u8 *fscrypt_auth;
+	u8 *fscrypt_file;
+	u32 fscrypt_auth_len;
+	u32 fscrypt_file_len;
 	u64 rsnaps;
 	u64 change_attr;
 };
@@ -278,6 +282,9 @@ struct ceph_mds_request {
 	struct mutex r_fill_mutex;
 
 	union ceph_mds_request_args r_args;
+
+	struct ceph_fscrypt_auth *r_fscrypt_auth;
+
 	int r_fmode;        /* file mode, if expecting cap */
 	int r_request_release_offset;
 	const struct cred *r_cred;
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index d6a1790f6923..c4ab2db85ef0 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -20,6 +20,7 @@
 #include "super.h"
 #include "mds_client.h"
 #include "cache.h"
+#include "crypto.h"
 
 #include <linux/ceph/ceph_features.h>
 #include <linux/ceph/decode.h>
@@ -1135,6 +1136,8 @@ static int ceph_set_super(struct super_block *s, struct fs_context *fc)
 	s->s_time_max = U32_MAX;
 	s->s_flags |= SB_NODIRATIME | SB_NOATIME;
 
+	ceph_fscrypt_set_ops(s);
+
 	ret = set_anon_super_fc(s, fc);
 	if (ret != 0)
 		fsc->sb = NULL;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index eb621bb276bd..3a39a9b3bc33 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -450,6 +450,13 @@ struct ceph_inode_info {
 
 	struct work_struct i_work;
 	unsigned long  i_work_mask;
+
+#ifdef CONFIG_FS_ENCRYPTION
+	u32 fscrypt_auth_len;
+	u32 fscrypt_file_len;
+	u8 *fscrypt_auth;
+	u8 *fscrypt_file;
+#endif
 };
 
 struct ceph_netfs_request_data {
@@ -1073,7 +1080,13 @@ static inline int ceph_do_getattr(struct inode *inode, int mask, bool force)
 }
 extern int ceph_permission(struct mnt_idmap *idmap,
 			   struct inode *inode, int mask);
-extern int __ceph_setattr(struct inode *inode, struct iattr *attr);
+
+struct ceph_iattr {
+	struct ceph_fscrypt_auth	*fscrypt_auth;
+};
+
+extern int __ceph_setattr(struct inode *inode, struct iattr *attr,
+			  struct ceph_iattr *cia);
 extern int ceph_setattr(struct mnt_idmap *idmap,
 			struct dentry *dentry, struct iattr *attr);
 extern int ceph_getattr(struct mnt_idmap *idmap,
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index 49586ff26152..45f8ce61e103 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -359,14 +359,19 @@ enum {
 
 extern const char *ceph_mds_op_name(int op);
 
-
-#define CEPH_SETATTR_MODE   1
-#define CEPH_SETATTR_UID    2
-#define CEPH_SETATTR_GID    4
-#define CEPH_SETATTR_MTIME  8
-#define CEPH_SETATTR_ATIME 16
-#define CEPH_SETATTR_SIZE  32
-#define CEPH_SETATTR_CTIME 64
+#define CEPH_SETATTR_MODE              (1 << 0)
+#define CEPH_SETATTR_UID               (1 << 1)
+#define CEPH_SETATTR_GID               (1 << 2)
+#define CEPH_SETATTR_MTIME             (1 << 3)
+#define CEPH_SETATTR_ATIME             (1 << 4)
+#define CEPH_SETATTR_SIZE              (1 << 5)
+#define CEPH_SETATTR_CTIME             (1 << 6)
+#define CEPH_SETATTR_MTIME_NOW         (1 << 7)
+#define CEPH_SETATTR_ATIME_NOW         (1 << 8)
+#define CEPH_SETATTR_BTIME             (1 << 9)
+#define CEPH_SETATTR_KILL_SGUID        (1 << 10)
+#define CEPH_SETATTR_FSCRYPT_AUTH      (1 << 11)
+#define CEPH_SETATTR_FSCRYPT_FILE      (1 << 12)
 
 /*
  * Ceph setxattr request flags.

From 6b5717bd30ab7f35792d20b71211055bdb43e6de Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Tue, 8 Sep 2020 09:47:40 -0400
Subject: [PATCH 0596/1189] ceph: implement -o test_dummy_encryption mount
 option
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add support for the test_dummy_encryption mount option. This allows us
to test the encrypted codepaths in ceph without having to manually set
keys, etc.

[ lhenriques: fix potential fsc->fsc_dummy_enc_policy memory leak in
  ceph_real_mount() ]

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/crypto.c | 56 +++++++++++++++++++++++++++++++
 fs/ceph/crypto.h | 28 ++++++++++++++++
 fs/ceph/inode.c  | 10 ++++--
 fs/ceph/super.c  | 86 ++++++++++++++++++++++++++++++++++++++++++++++--
 fs/ceph/super.h  |  9 ++++-
 fs/ceph/xattr.c  |  3 ++
 6 files changed, 186 insertions(+), 6 deletions(-)

diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c
index b17a6ee16cf0..b65e31c5c503 100644
--- a/fs/ceph/crypto.c
+++ b/fs/ceph/crypto.c
@@ -4,6 +4,7 @@
 #include <linux/fscrypt.h>
 
 #include "super.h"
+#include "mds_client.h"
 #include "crypto.h"
 
 static int ceph_crypt_get_context(struct inode *inode, void *ctx, size_t len)
@@ -65,9 +66,15 @@ static bool ceph_crypt_empty_dir(struct inode *inode)
 	return ci->i_rsubdirs + ci->i_rfiles == 1;
 }
 
+static const union fscrypt_policy *ceph_get_dummy_policy(struct super_block *sb)
+{
+	return ceph_sb_to_client(sb)->fsc_dummy_enc_policy.policy;
+}
+
 static struct fscrypt_operations ceph_fscrypt_ops = {
 	.get_context		= ceph_crypt_get_context,
 	.set_context		= ceph_crypt_set_context,
+	.get_dummy_policy	= ceph_get_dummy_policy,
 	.empty_dir		= ceph_crypt_empty_dir,
 };
 
@@ -75,3 +82,52 @@ void ceph_fscrypt_set_ops(struct super_block *sb)
 {
 	fscrypt_set_ops(sb, &ceph_fscrypt_ops);
 }
+
+void ceph_fscrypt_free_dummy_policy(struct ceph_fs_client *fsc)
+{
+	fscrypt_free_dummy_policy(&fsc->fsc_dummy_enc_policy);
+}
+
+int ceph_fscrypt_prepare_context(struct inode *dir, struct inode *inode,
+				 struct ceph_acl_sec_ctx *as)
+{
+	int ret, ctxsize;
+	bool encrypted = false;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	ret = fscrypt_prepare_new_inode(dir, inode, &encrypted);
+	if (ret)
+		return ret;
+	if (!encrypted)
+		return 0;
+
+	as->fscrypt_auth = kzalloc(sizeof(*as->fscrypt_auth), GFP_KERNEL);
+	if (!as->fscrypt_auth)
+		return -ENOMEM;
+
+	ctxsize = fscrypt_context_for_new_inode(as->fscrypt_auth->cfa_blob,
+						inode);
+	if (ctxsize < 0)
+		return ctxsize;
+
+	as->fscrypt_auth->cfa_version = cpu_to_le32(CEPH_FSCRYPT_AUTH_VERSION);
+	as->fscrypt_auth->cfa_blob_len = cpu_to_le32(ctxsize);
+
+	WARN_ON_ONCE(ci->fscrypt_auth);
+	kfree(ci->fscrypt_auth);
+	ci->fscrypt_auth_len = ceph_fscrypt_auth_len(as->fscrypt_auth);
+	ci->fscrypt_auth = kmemdup(as->fscrypt_auth, ci->fscrypt_auth_len,
+				   GFP_KERNEL);
+	if (!ci->fscrypt_auth)
+		return -ENOMEM;
+
+	inode->i_flags |= S_ENCRYPTED;
+
+	return 0;
+}
+
+void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req,
+				struct ceph_acl_sec_ctx *as)
+{
+	swap(req->r_fscrypt_auth, as->fscrypt_auth);
+}
diff --git a/fs/ceph/crypto.h b/fs/ceph/crypto.h
index 6dca674f79b8..642963f5442e 100644
--- a/fs/ceph/crypto.h
+++ b/fs/ceph/crypto.h
@@ -8,6 +8,10 @@
 
 #include <linux/fscrypt.h>
 
+struct ceph_fs_client;
+struct ceph_acl_sec_ctx;
+struct ceph_mds_request;
+
 struct ceph_fscrypt_auth {
 	__le32	cfa_version;
 	__le32	cfa_blob_len;
@@ -25,12 +29,36 @@ static inline u32 ceph_fscrypt_auth_len(struct ceph_fscrypt_auth *fa)
 #ifdef CONFIG_FS_ENCRYPTION
 void ceph_fscrypt_set_ops(struct super_block *sb);
 
+void ceph_fscrypt_free_dummy_policy(struct ceph_fs_client *fsc);
+
+int ceph_fscrypt_prepare_context(struct inode *dir, struct inode *inode,
+				 struct ceph_acl_sec_ctx *as);
+void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req,
+				struct ceph_acl_sec_ctx *as);
+
 #else /* CONFIG_FS_ENCRYPTION */
 
 static inline void ceph_fscrypt_set_ops(struct super_block *sb)
 {
 }
 
+static inline void ceph_fscrypt_free_dummy_policy(struct ceph_fs_client *fsc)
+{
+}
+
+static inline int ceph_fscrypt_prepare_context(struct inode *dir,
+					       struct inode *inode,
+					       struct ceph_acl_sec_ctx *as)
+{
+	if (IS_ENCRYPTED(dir))
+		return -EOPNOTSUPP;
+	return 0;
+}
+
+static inline void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req,
+						struct ceph_acl_sec_ctx *as_ctx)
+{
+}
 #endif /* CONFIG_FS_ENCRYPTION */
 
 #endif
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index a3aa7870a6a2..50ff641865e0 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -83,12 +83,17 @@ struct inode *ceph_new_inode(struct inode *dir, struct dentry *dentry,
 			goto out_err;
 	}
 
+	inode->i_state = 0;
+	inode->i_mode = *mode;
+
 	err = ceph_security_init_secctx(dentry, *mode, as_ctx);
 	if (err < 0)
 		goto out_err;
 
-	inode->i_state = 0;
-	inode->i_mode = *mode;
+	err = ceph_fscrypt_prepare_context(dir, inode, as_ctx);
+	if (err)
+		goto out_err;
+
 	return inode;
 out_err:
 	iput(inode);
@@ -102,6 +107,7 @@ void ceph_as_ctx_to_req(struct ceph_mds_request *req,
 		req->r_pagelist = as_ctx->pagelist;
 		as_ctx->pagelist = NULL;
 	}
+	ceph_fscrypt_as_ctx_to_req(req, as_ctx);
 }
 
 /**
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index c4ab2db85ef0..75dd1b6b3d01 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -47,6 +47,7 @@ static void ceph_put_super(struct super_block *s)
 	struct ceph_fs_client *fsc = ceph_sb_to_client(s);
 
 	dout("put_super\n");
+	ceph_fscrypt_free_dummy_policy(fsc);
 	ceph_mdsc_close_sessions(fsc->mdsc);
 }
 
@@ -152,6 +153,7 @@ enum {
 	Opt_recover_session,
 	Opt_source,
 	Opt_mon_addr,
+	Opt_test_dummy_encryption,
 	/* string args above */
 	Opt_dirstat,
 	Opt_rbytes,
@@ -194,6 +196,7 @@ static const struct fs_parameter_spec ceph_mount_parameters[] = {
 	fsparam_string	("fsc",				Opt_fscache), // fsc=...
 	fsparam_flag_no ("ino32",			Opt_ino32),
 	fsparam_string	("mds_namespace",		Opt_mds_namespace),
+	fsparam_string	("mon_addr",			Opt_mon_addr),
 	fsparam_flag_no ("poolperm",			Opt_poolperm),
 	fsparam_flag_no ("quotadf",			Opt_quotadf),
 	fsparam_u32	("rasize",			Opt_rasize),
@@ -205,7 +208,8 @@ static const struct fs_parameter_spec ceph_mount_parameters[] = {
 	fsparam_u32	("rsize",			Opt_rsize),
 	fsparam_string	("snapdirname",			Opt_snapdirname),
 	fsparam_string	("source",			Opt_source),
-	fsparam_string	("mon_addr",			Opt_mon_addr),
+	fsparam_flag	("test_dummy_encryption",	Opt_test_dummy_encryption),
+	fsparam_string	("test_dummy_encryption",	Opt_test_dummy_encryption),
 	fsparam_u32	("wsize",			Opt_wsize),
 	fsparam_flag_no	("wsync",			Opt_wsync),
 	fsparam_flag_no	("pagecache",			Opt_pagecache),
@@ -585,6 +589,23 @@ static int ceph_parse_mount_param(struct fs_context *fc,
 		else
 			fsopt->flags |= CEPH_MOUNT_OPT_SPARSEREAD;
 		break;
+	case Opt_test_dummy_encryption:
+#ifdef CONFIG_FS_ENCRYPTION
+		fscrypt_free_dummy_policy(&fsopt->dummy_enc_policy);
+		ret = fscrypt_parse_test_dummy_encryption(param,
+						&fsopt->dummy_enc_policy);
+		if (ret == -EINVAL) {
+			warnfc(fc, "Value of option \"%s\" is unrecognized",
+			       param->key);
+		} else if (ret == -EEXIST) {
+			warnfc(fc, "Conflicting test_dummy_encryption options");
+			ret = -EINVAL;
+		}
+#else
+		warnfc(fc,
+		       "FS encryption not supported: test_dummy_encryption mount option ignored");
+#endif
+		break;
 	default:
 		BUG();
 	}
@@ -605,6 +626,7 @@ static void destroy_mount_options(struct ceph_mount_options *args)
 	kfree(args->server_path);
 	kfree(args->fscache_uniq);
 	kfree(args->mon_addr);
+	fscrypt_free_dummy_policy(&args->dummy_enc_policy);
 	kfree(args);
 }
 
@@ -724,6 +746,8 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
 	if (fsopt->flags & CEPH_MOUNT_OPT_SPARSEREAD)
 		seq_puts(m, ",sparseread");
 
+	fscrypt_show_test_dummy_encryption(m, ',', root->d_sb);
+
 	if (fsopt->wsize != CEPH_MAX_WRITE_SIZE)
 		seq_printf(m, ",wsize=%u", fsopt->wsize);
 	if (fsopt->rsize != CEPH_MAX_READ_SIZE)
@@ -1062,6 +1086,50 @@ out:
 	return root;
 }
 
+#ifdef CONFIG_FS_ENCRYPTION
+static int ceph_apply_test_dummy_encryption(struct super_block *sb,
+					    struct fs_context *fc,
+					    struct ceph_mount_options *fsopt)
+{
+	struct ceph_fs_client *fsc = sb->s_fs_info;
+
+	if (!fscrypt_is_dummy_policy_set(&fsopt->dummy_enc_policy))
+		return 0;
+
+	/* No changing encryption context on remount. */
+	if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE &&
+	    !fscrypt_is_dummy_policy_set(&fsc->fsc_dummy_enc_policy)) {
+		if (fscrypt_dummy_policies_equal(&fsopt->dummy_enc_policy,
+						 &fsc->fsc_dummy_enc_policy))
+			return 0;
+		errorfc(fc, "Can't set test_dummy_encryption on remount");
+		return -EINVAL;
+	}
+
+	/* Also make sure fsopt doesn't contain a conflicting value. */
+	if (fscrypt_is_dummy_policy_set(&fsc->fsc_dummy_enc_policy)) {
+		if (fscrypt_dummy_policies_equal(&fsopt->dummy_enc_policy,
+						 &fsc->fsc_dummy_enc_policy))
+			return 0;
+		errorfc(fc, "Conflicting test_dummy_encryption options");
+		return -EINVAL;
+	}
+
+	fsc->fsc_dummy_enc_policy = fsopt->dummy_enc_policy;
+	memset(&fsopt->dummy_enc_policy, 0, sizeof(fsopt->dummy_enc_policy));
+
+	warnfc(fc, "test_dummy_encryption mode enabled");
+	return 0;
+}
+#else
+static int ceph_apply_test_dummy_encryption(struct super_block *sb,
+					    struct fs_context *fc,
+					    struct ceph_mount_options *fsopt)
+{
+	return 0;
+}
+#endif
+
 /*
  * mount: join the ceph cluster, and open root directory.
  */
@@ -1090,6 +1158,11 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc,
 				goto out;
 		}
 
+		err = ceph_apply_test_dummy_encryption(fsc->sb, fc,
+						       fsc->mount_options);
+		if (err)
+			goto out;
+
 		dout("mount opening path '%s'\n", path);
 
 		ceph_fs_debugfs_init(fsc);
@@ -1111,6 +1184,7 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc,
 
 out:
 	mutex_unlock(&fsc->client->mount_mutex);
+	ceph_fscrypt_free_dummy_policy(fsc);
 	return ERR_PTR(err);
 }
 
@@ -1299,9 +1373,15 @@ static void ceph_free_fc(struct fs_context *fc)
 
 static int ceph_reconfigure_fc(struct fs_context *fc)
 {
+	int err;
 	struct ceph_parse_opts_ctx *pctx = fc->fs_private;
 	struct ceph_mount_options *fsopt = pctx->opts;
-	struct ceph_fs_client *fsc = ceph_sb_to_client(fc->root->d_sb);
+	struct super_block *sb = fc->root->d_sb;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
+
+	err = ceph_apply_test_dummy_encryption(sb, fc, fsopt);
+	if (err)
+		return err;
 
 	if (fsopt->flags & CEPH_MOUNT_OPT_ASYNC_DIROPS)
 		ceph_set_mount_opt(fsc, ASYNC_DIROPS);
@@ -1320,7 +1400,7 @@ static int ceph_reconfigure_fc(struct fs_context *fc)
 		pr_notice("ceph: monitor addresses recorded, but not used for reconnection");
 	}
 
-	sync_filesystem(fc->root->d_sb);
+	sync_filesystem(sb);
 	return 0;
 }
 
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 3a39a9b3bc33..11483855897e 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -22,6 +22,7 @@
 #include <linux/hashtable.h>
 
 #include <linux/ceph/libceph.h>
+#include "crypto.h"
 
 /* large granularity for statfs utilization stats to facilitate
  * large volume sizes on 32-bit machines. */
@@ -99,6 +100,7 @@ struct ceph_mount_options {
 	char *server_path;    /* default NULL (means "/") */
 	char *fscache_uniq;   /* default NULL */
 	char *mon_addr;
+	struct fscrypt_dummy_policy dummy_enc_policy;
 };
 
 /* mount state */
@@ -155,9 +157,11 @@ struct ceph_fs_client {
 #ifdef CONFIG_CEPH_FSCACHE
 	struct fscache_volume *fscache;
 #endif
+#ifdef CONFIG_FS_ENCRYPTION
+	struct fscrypt_dummy_policy fsc_dummy_enc_policy;
+#endif
 };
 
-
 /*
  * File i/o capability.  This tracks shared state with the metadata
  * server that allows us to cache or writeback attributes or to read
@@ -1120,6 +1124,9 @@ struct ceph_acl_sec_ctx {
 #ifdef CONFIG_CEPH_FS_SECURITY_LABEL
 	void *sec_ctx;
 	u32 sec_ctxlen;
+#endif
+#ifdef CONFIG_FS_ENCRYPTION
+	struct ceph_fscrypt_auth *fscrypt_auth;
 #endif
 	struct ceph_pagelist *pagelist;
 };
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 806183959c47..ddc9090a1465 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -1407,6 +1407,9 @@ void ceph_release_acl_sec_ctx(struct ceph_acl_sec_ctx *as_ctx)
 #endif
 #ifdef CONFIG_CEPH_FS_SECURITY_LABEL
 	security_release_secctx(as_ctx->sec_ctx, as_ctx->sec_ctxlen);
+#endif
+#ifdef CONFIG_FS_ENCRYPTION
+	kfree(as_ctx->fscrypt_auth);
 #endif
 	if (as_ctx->pagelist)
 		ceph_pagelist_release(as_ctx->pagelist);

From f061feda6c54ccb02b0f2c09926fb8edd4882fbb Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Tue, 28 Jul 2020 09:58:43 -0400
Subject: [PATCH 0597/1189] ceph: add fscrypt ioctls and ceph.fscrypt.auth
 vxattr
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We gate most of the ioctls on MDS feature support. The exception is the
key removal and status functions that we still want to work if the MDS's
were to (inexplicably) lose the feature.

For the set_policy ioctl, we take Fs caps to ensure that nothing can
create files in the directory while the ioctl is running. That should
be enough to ensure that the "empty_dir" check is reliable.

The vxattr is read-only, added mostly for future debugging purposes.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/ioctl.c | 84 +++++++++++++++++++++++++++++++++++++++++++++++++
 fs/ceph/xattr.c | 27 ++++++++++++++++
 2 files changed, 111 insertions(+)

diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index deac817647eb..9bb37bcab05a 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -6,6 +6,7 @@
 #include "mds_client.h"
 #include "ioctl.h"
 #include <linux/ceph/striper.h>
+#include <linux/fscrypt.h>
 
 /*
  * ioctls
@@ -268,8 +269,54 @@ static long ceph_ioctl_syncio(struct file *file)
 	return 0;
 }
 
+static int vet_mds_for_fscrypt(struct file *file)
+{
+	int i, ret = -EOPNOTSUPP;
+	struct ceph_mds_client	*mdsc = ceph_sb_to_mdsc(file_inode(file)->i_sb);
+
+	mutex_lock(&mdsc->mutex);
+	for (i = 0; i < mdsc->max_sessions; i++) {
+		struct ceph_mds_session *s = mdsc->sessions[i];
+
+		if (!s)
+			continue;
+		if (test_bit(CEPHFS_FEATURE_ALTERNATE_NAME, &s->s_features))
+			ret = 0;
+		break;
+	}
+	mutex_unlock(&mdsc->mutex);
+	return ret;
+}
+
+static long ceph_set_encryption_policy(struct file *file, unsigned long arg)
+{
+	int ret, got = 0;
+	struct inode *inode = file_inode(file);
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	ret = vet_mds_for_fscrypt(file);
+	if (ret)
+		return ret;
+
+	/*
+	 * Ensure we hold these caps so that we _know_ that the rstats check
+	 * in the empty_dir check is reliable.
+	 */
+	ret = ceph_get_caps(file, CEPH_CAP_FILE_SHARED, 0, -1, &got);
+	if (ret)
+		return ret;
+
+	ret = fscrypt_ioctl_set_policy(file, (const void __user *)arg);
+	if (got)
+		ceph_put_cap_refs(ci, got);
+
+	return ret;
+}
+
 long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
+	int ret;
+
 	dout("ioctl file %p cmd %u arg %lu\n", file, cmd, arg);
 	switch (cmd) {
 	case CEPH_IOC_GET_LAYOUT:
@@ -289,6 +336,43 @@ long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 
 	case CEPH_IOC_SYNCIO:
 		return ceph_ioctl_syncio(file);
+
+	case FS_IOC_SET_ENCRYPTION_POLICY:
+		return ceph_set_encryption_policy(file, arg);
+
+	case FS_IOC_GET_ENCRYPTION_POLICY:
+		ret = vet_mds_for_fscrypt(file);
+		if (ret)
+			return ret;
+		return fscrypt_ioctl_get_policy(file, (void __user *)arg);
+
+	case FS_IOC_GET_ENCRYPTION_POLICY_EX:
+		ret = vet_mds_for_fscrypt(file);
+		if (ret)
+			return ret;
+		return fscrypt_ioctl_get_policy_ex(file, (void __user *)arg);
+
+	case FS_IOC_ADD_ENCRYPTION_KEY:
+		ret = vet_mds_for_fscrypt(file);
+		if (ret)
+			return ret;
+		return fscrypt_ioctl_add_key(file, (void __user *)arg);
+
+	case FS_IOC_REMOVE_ENCRYPTION_KEY:
+		return fscrypt_ioctl_remove_key(file, (void __user *)arg);
+
+	case FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS:
+		return fscrypt_ioctl_remove_key_all_users(file,
+							  (void __user *)arg);
+
+	case FS_IOC_GET_ENCRYPTION_KEY_STATUS:
+		return fscrypt_ioctl_get_key_status(file, (void __user *)arg);
+
+	case FS_IOC_GET_ENCRYPTION_NONCE:
+		ret = vet_mds_for_fscrypt(file);
+		if (ret)
+			return ret;
+		return fscrypt_ioctl_get_nonce(file, (void __user *)arg);
 	}
 
 	return -ENOTTY;
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index ddc9090a1465..6cd82404202a 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -352,6 +352,24 @@ static ssize_t ceph_vxattrcb_auth_mds(struct ceph_inode_info *ci,
 	return ret;
 }
 
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+static bool ceph_vxattrcb_fscrypt_auth_exists(struct ceph_inode_info *ci)
+{
+	return ci->fscrypt_auth_len;
+}
+
+static ssize_t ceph_vxattrcb_fscrypt_auth(struct ceph_inode_info *ci,
+					  char *val, size_t size)
+{
+	if (size) {
+		if (size < ci->fscrypt_auth_len)
+			return -ERANGE;
+		memcpy(val, ci->fscrypt_auth, ci->fscrypt_auth_len);
+	}
+	return ci->fscrypt_auth_len;
+}
+#endif /* CONFIG_FS_ENCRYPTION */
+
 #define CEPH_XATTR_NAME(_type, _name)	XATTR_CEPH_PREFIX #_type "." #_name
 #define CEPH_XATTR_NAME2(_type, _name, _name2)	\
 	XATTR_CEPH_PREFIX #_type "." #_name "." #_name2
@@ -500,6 +518,15 @@ static struct ceph_vxattr ceph_common_vxattrs[] = {
 		.exists_cb = NULL,
 		.flags = VXATTR_FLAG_READONLY,
 	},
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+	{
+		.name = "ceph.fscrypt.auth",
+		.name_size = sizeof("ceph.fscrypt.auth"),
+		.getxattr_cb = ceph_vxattrcb_fscrypt_auth,
+		.exists_cb = ceph_vxattrcb_fscrypt_auth_exists,
+		.flags = VXATTR_FLAG_READONLY,
+	},
+#endif /* CONFIG_FS_ENCRYPTION */
 	{ .name = NULL, 0 }	/* Required table terminator */
 };
 

From b7b53361c80b16ad461dbcb8a93e6e37578bac9b Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Wed, 16 Mar 2022 14:49:34 +0800
Subject: [PATCH 0598/1189] ceph: make ioctl cmds more readable in debug log
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

    ioctl file 0000000004e6b054 cmd 2148296211 arg 824635143532

The numerical cmd value in the ioctl debug log message is too hard to
understand even when you look at it in the code. Make it more readable.

[ idryomov: add missing _ in ceph_ioctl_cmd_name() ]

Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/ioctl.c | 39 ++++++++++++++++++++++++++++++++++++++-
 1 file changed, 38 insertions(+), 1 deletion(-)

diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index 9bb37bcab05a..11d37d307382 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -313,11 +313,48 @@ static long ceph_set_encryption_policy(struct file *file, unsigned long arg)
 	return ret;
 }
 
+static const char *ceph_ioctl_cmd_name(const unsigned int cmd)
+{
+	switch (cmd) {
+	case CEPH_IOC_GET_LAYOUT:
+		return "get_layout";
+	case CEPH_IOC_SET_LAYOUT:
+		return "set_layout";
+	case CEPH_IOC_SET_LAYOUT_POLICY:
+		return "set_layout_policy";
+	case CEPH_IOC_GET_DATALOC:
+		return "get_dataloc";
+	case CEPH_IOC_LAZYIO:
+		return "lazyio";
+	case CEPH_IOC_SYNCIO:
+		return "syncio";
+	case FS_IOC_SET_ENCRYPTION_POLICY:
+		return "set_encryption_policy";
+	case FS_IOC_GET_ENCRYPTION_POLICY:
+		return "get_encryption_policy";
+	case FS_IOC_GET_ENCRYPTION_POLICY_EX:
+		return "get_encryption_policy_ex";
+	case FS_IOC_ADD_ENCRYPTION_KEY:
+		return "add_encryption_key";
+	case FS_IOC_REMOVE_ENCRYPTION_KEY:
+		return "remove_encryption_key";
+	case FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS:
+		return "remove_encryption_key_all_users";
+	case FS_IOC_GET_ENCRYPTION_KEY_STATUS:
+		return "get_encryption_key_status";
+	case FS_IOC_GET_ENCRYPTION_NONCE:
+		return "get_encryption_nonce";
+	default:
+		return "unknown";
+	}
+}
+
 long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	int ret;
 
-	dout("ioctl file %p cmd %u arg %lu\n", file, cmd, arg);
+	dout("ioctl file %p cmd %s arg %lu\n", file,
+	     ceph_ioctl_cmd_name(cmd), arg);
 	switch (cmd) {
 	case CEPH_IOC_GET_LAYOUT:
 		return ceph_ioctl_get_layout(file, (void __user *)arg);

From 64e86f632bf148d007946c52781781eb8380d416 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Lu=C3=ADs=20Henriques?= <lhenriques@suse.de>
Date: Mon, 18 Apr 2022 14:59:56 +0100
Subject: [PATCH 0599/1189] ceph: add base64 endcoding routines for encrypted
 names
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The base64url encoding used by fscrypt includes the '_' character, which
may cause problems in snapshot names (if the name starts with '_').
Thus, use the base64 encoding defined for IMAP mailbox names (RFC 3501),
which uses '+' and ',' instead of '-' and '_'.

Signed-off-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/crypto.c | 60 ++++++++++++++++++++++++++++++++++++++++++++++++
 fs/ceph/crypto.h | 32 ++++++++++++++++++++++++++
 2 files changed, 92 insertions(+)

diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c
index b65e31c5c503..0bb4d8e9f3b0 100644
--- a/fs/ceph/crypto.c
+++ b/fs/ceph/crypto.c
@@ -1,4 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
+/*
+ * The base64 encode/decode code was copied from fscrypt:
+ * Copyright (C) 2015, Google, Inc.
+ * Copyright (C) 2015, Motorola Mobility
+ * Written by Uday Savagaonkar, 2014.
+ * Modified by Jaegeuk Kim, 2015.
+ */
 #include <linux/ceph/ceph_debug.h>
 #include <linux/xattr.h>
 #include <linux/fscrypt.h>
@@ -7,6 +14,59 @@
 #include "mds_client.h"
 #include "crypto.h"
 
+/*
+ * The base64url encoding used by fscrypt includes the '_' character, which may
+ * cause problems in snapshot names (which can not start with '_').  Thus, we
+ * used the base64 encoding defined for IMAP mailbox names (RFC 3501) instead,
+ * which replaces '-' and '_' by '+' and ','.
+ */
+static const char base64_table[65] =
+	"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+,";
+
+int ceph_base64_encode(const u8 *src, int srclen, char *dst)
+{
+	u32 ac = 0;
+	int bits = 0;
+	int i;
+	char *cp = dst;
+
+	for (i = 0; i < srclen; i++) {
+		ac = (ac << 8) | src[i];
+		bits += 8;
+		do {
+			bits -= 6;
+			*cp++ = base64_table[(ac >> bits) & 0x3f];
+		} while (bits >= 6);
+	}
+	if (bits)
+		*cp++ = base64_table[(ac << (6 - bits)) & 0x3f];
+	return cp - dst;
+}
+
+int ceph_base64_decode(const char *src, int srclen, u8 *dst)
+{
+	u32 ac = 0;
+	int bits = 0;
+	int i;
+	u8 *bp = dst;
+
+	for (i = 0; i < srclen; i++) {
+		const char *p = strchr(base64_table, src[i]);
+
+		if (p == NULL || src[i] == 0)
+			return -1;
+		ac = (ac << 6) | (p - base64_table);
+		bits += 6;
+		if (bits >= 8) {
+			bits -= 8;
+			*bp++ = (u8)(ac >> bits);
+		}
+	}
+	if (ac & ((1 << bits) - 1))
+		return -1;
+	return bp - dst;
+}
+
 static int ceph_crypt_get_context(struct inode *inode, void *ctx, size_t len)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
diff --git a/fs/ceph/crypto.h b/fs/ceph/crypto.h
index 642963f5442e..44eb3f9f8287 100644
--- a/fs/ceph/crypto.h
+++ b/fs/ceph/crypto.h
@@ -27,6 +27,38 @@ static inline u32 ceph_fscrypt_auth_len(struct ceph_fscrypt_auth *fa)
 }
 
 #ifdef CONFIG_FS_ENCRYPTION
+/*
+ * We want to encrypt filenames when creating them, but the encrypted
+ * versions of those names may have illegal characters in them. To mitigate
+ * that, we base64 encode them, but that gives us a result that can exceed
+ * NAME_MAX.
+ *
+ * Follow a similar scheme to fscrypt itself, and cap the filename to a
+ * smaller size. If the ciphertext name is longer than the value below, then
+ * sha256 hash the remaining bytes.
+ *
+ * For the fscrypt_nokey_name struct the dirhash[2] member is useless in ceph
+ * so the corresponding struct will be:
+ *
+ * struct fscrypt_ceph_nokey_name {
+ *	u8 bytes[157];
+ *	u8 sha256[SHA256_DIGEST_SIZE];
+ * }; // 180 bytes => 240 bytes base64-encoded, which is <= NAME_MAX (255)
+ *
+ * (240 bytes is the maximum size allowed for snapshot names to take into
+ *  account the format: '_<SNAPSHOT-NAME>_<INODE-NUMBER>'.)
+ *
+ * Note that for long names that end up having their tail portion hashed, we
+ * must also store the full encrypted name (in the dentry's alternate_name
+ * field).
+ */
+#define CEPH_NOHASH_NAME_MAX (180 - SHA256_DIGEST_SIZE)
+
+#define CEPH_BASE64_CHARS(nbytes) DIV_ROUND_UP((nbytes) * 4, 3)
+
+int ceph_base64_encode(const u8 *src, int srclen, char *dst);
+int ceph_base64_decode(const char *src, int srclen, u8 *dst);
+
 void ceph_fscrypt_set_ops(struct super_block *sb);
 
 void ceph_fscrypt_free_dummy_policy(struct ceph_fs_client *fsc);

From 4aae44f65827f0213a7361cf9c32cfe06114473f Mon Sep 17 00:00:00 2001
From: Vladimir Zapolskiy <vz@mleia.com>
Date: Mon, 17 Jul 2023 17:52:57 +0200
Subject: [PATCH 0600/1189] pwm: lpc32xx: Remove handling of PWM channels
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Because LPC32xx PWM controllers have only a single output which is
registered as the only PWM device/channel per controller, it is known in
advance that pwm->hwpwm value is always 0. On basis of this fact
simplify the code by removing operations with pwm->hwpwm, there is no
controls which require channel number as input.

Even though I wasn't aware at the time when I forward ported that patch,
this fixes a null pointer dereference as lpc32xx->chip.pwms is NULL
before devm_pwmchip_add() is called.

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Vladimir Zapolskiy <vz@mleia.com>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Fixes: 3d2813fb17e5 ("pwm: lpc32xx: Don't modify HW state in .probe() after the PWM chip was registered")
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-lpc32xx.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/pwm/pwm-lpc32xx.c b/drivers/pwm/pwm-lpc32xx.c
index 86a0ea0f6955..806f0bb3ad6d 100644
--- a/drivers/pwm/pwm-lpc32xx.c
+++ b/drivers/pwm/pwm-lpc32xx.c
@@ -51,10 +51,10 @@ static int lpc32xx_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
 	if (duty_cycles > 255)
 		duty_cycles = 255;
 
-	val = readl(lpc32xx->base + (pwm->hwpwm << 2));
+	val = readl(lpc32xx->base);
 	val &= ~0xFFFF;
 	val |= (period_cycles << 8) | duty_cycles;
-	writel(val, lpc32xx->base + (pwm->hwpwm << 2));
+	writel(val, lpc32xx->base);
 
 	return 0;
 }
@@ -69,9 +69,9 @@ static int lpc32xx_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm)
 	if (ret)
 		return ret;
 
-	val = readl(lpc32xx->base + (pwm->hwpwm << 2));
+	val = readl(lpc32xx->base);
 	val |= PWM_ENABLE;
-	writel(val, lpc32xx->base + (pwm->hwpwm << 2));
+	writel(val, lpc32xx->base);
 
 	return 0;
 }
@@ -81,9 +81,9 @@ static void lpc32xx_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
 	struct lpc32xx_pwm_chip *lpc32xx = to_lpc32xx_pwm_chip(chip);
 	u32 val;
 
-	val = readl(lpc32xx->base + (pwm->hwpwm << 2));
+	val = readl(lpc32xx->base);
 	val &= ~PWM_ENABLE;
-	writel(val, lpc32xx->base + (pwm->hwpwm << 2));
+	writel(val, lpc32xx->base);
 
 	clk_disable_unprepare(lpc32xx->clk);
 }
@@ -141,9 +141,9 @@ static int lpc32xx_pwm_probe(struct platform_device *pdev)
 	lpc32xx->chip.npwm = 1;
 
 	/* If PWM is disabled, configure the output to the default value */
-	val = readl(lpc32xx->base + (lpc32xx->chip.pwms[0].hwpwm << 2));
+	val = readl(lpc32xx->base);
 	val &= ~PWM_PIN_LEVEL;
-	writel(val, lpc32xx->base + (lpc32xx->chip.pwms[0].hwpwm << 2));
+	writel(val, lpc32xx->base);
 
 	ret = devm_pwmchip_add(&pdev->dev, &lpc32xx->chip);
 	if (ret < 0) {

From b1f778a223a2a8ad6262e5233cfc3483bcf6e213 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 20 Aug 2023 10:01:08 +0100
Subject: [PATCH 0601/1189] KVM: arm64: pmu: Resync EL0 state on counter
 rotation

Huang Shijie reports that, when profiling a guest from the host
with a number of events that exceeds the number of available
counters, the reported counts are wildly inaccurate. Without
the counter oversubscription, the reported counts are correct.

Their investigation indicates that upon counter rotation (which
takes place on the back of a timer interrupt), we fail to
re-apply the guest EL0 enabling, leading to the counting of host
events instead of guest events.

In order to solve this, add yet another hook between the host PMU
driver and KVM, re-applying the guest EL0 configuration if the
right conditions apply (the host is VHE, we are in interrupt
context, and we interrupted a running vcpu). This triggers a new
vcpu request which will apply the correct configuration on guest
reentry.

With this, we have the correct counts, even when the counters are
oversubscribed.

Reported-by: Huang Shijie <shijie@os.amperecomputing.com>
Suggested-by: Oliver Upton <oliver.upton@linux.dev>
Tested_by: Huang Shijie <shijie@os.amperecomputing.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20230809013953.7692-1-shijie@os.amperecomputing.com
Acked-by: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/r/20230820090108.177817-1-maz@kernel.org
---
 arch/arm/include/asm/arm_pmuv3.h  |  2 ++
 arch/arm64/include/asm/kvm_host.h |  1 +
 arch/arm64/kvm/arm.c              |  3 +++
 arch/arm64/kvm/pmu.c              | 18 ++++++++++++++++++
 drivers/perf/arm_pmuv3.c          |  2 ++
 include/kvm/arm_pmu.h             |  2 ++
 6 files changed, 28 insertions(+)

diff --git a/arch/arm/include/asm/arm_pmuv3.h b/arch/arm/include/asm/arm_pmuv3.h
index f3cd04ff022d..72529f5e2bed 100644
--- a/arch/arm/include/asm/arm_pmuv3.h
+++ b/arch/arm/include/asm/arm_pmuv3.h
@@ -227,6 +227,8 @@ static inline bool kvm_set_pmuserenr(u64 val)
 	return false;
 }
 
+static inline void kvm_vcpu_pmu_resync_el0(void) {}
+
 /* PMU Version in DFR Register */
 #define ARMV8_PMU_DFR_VER_NI        0
 #define ARMV8_PMU_DFR_VER_V3P4      0x5
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index d3dd05bbfe23..553040e0e375 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -49,6 +49,7 @@
 #define KVM_REQ_RELOAD_GICv4	KVM_ARCH_REQ(4)
 #define KVM_REQ_RELOAD_PMU	KVM_ARCH_REQ(5)
 #define KVM_REQ_SUSPEND		KVM_ARCH_REQ(6)
+#define KVM_REQ_RESYNC_PMU_EL0	KVM_ARCH_REQ(7)
 
 #define KVM_DIRTY_LOG_MANUAL_CAPS   (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
 				     KVM_DIRTY_LOG_INITIALLY_SET)
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 72dc53a75d1c..978b0411082f 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -803,6 +803,9 @@ static int check_vcpu_requests(struct kvm_vcpu *vcpu)
 			kvm_pmu_handle_pmcr(vcpu,
 					    __vcpu_sys_reg(vcpu, PMCR_EL0));
 
+		if (kvm_check_request(KVM_REQ_RESYNC_PMU_EL0, vcpu))
+			kvm_vcpu_pmu_restore_guest(vcpu);
+
 		if (kvm_check_request(KVM_REQ_SUSPEND, vcpu))
 			return kvm_vcpu_suspend(vcpu);
 
diff --git a/arch/arm64/kvm/pmu.c b/arch/arm64/kvm/pmu.c
index 121f1a14c829..0eea225fd09a 100644
--- a/arch/arm64/kvm/pmu.c
+++ b/arch/arm64/kvm/pmu.c
@@ -236,3 +236,21 @@ bool kvm_set_pmuserenr(u64 val)
 	ctxt_sys_reg(hctxt, PMUSERENR_EL0) = val;
 	return true;
 }
+
+/*
+ * If we interrupted the guest to update the host PMU context, make
+ * sure we re-apply the guest EL0 state.
+ */
+void kvm_vcpu_pmu_resync_el0(void)
+{
+	struct kvm_vcpu *vcpu;
+
+	if (!has_vhe() || !in_interrupt())
+		return;
+
+	vcpu = kvm_get_running_vcpu();
+	if (!vcpu)
+		return;
+
+	kvm_make_request(KVM_REQ_RESYNC_PMU_EL0, vcpu);
+}
diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
index 08b3a1bf0ef6..6a3d8176f54a 100644
--- a/drivers/perf/arm_pmuv3.c
+++ b/drivers/perf/arm_pmuv3.c
@@ -772,6 +772,8 @@ static void armv8pmu_start(struct arm_pmu *cpu_pmu)
 
 	/* Enable all counters */
 	armv8pmu_pmcr_write(armv8pmu_pmcr_read() | ARMV8_PMU_PMCR_E);
+
+	kvm_vcpu_pmu_resync_el0();
 }
 
 static void armv8pmu_stop(struct arm_pmu *cpu_pmu)
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 847da6fc2713..3a8a70a60794 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -74,6 +74,7 @@ int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu);
 struct kvm_pmu_events *kvm_get_pmu_events(void);
 void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu);
 void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu);
+void kvm_vcpu_pmu_resync_el0(void);
 
 #define kvm_vcpu_has_pmu(vcpu)					\
 	(test_bit(KVM_ARM_VCPU_PMU_V3, (vcpu)->arch.features))
@@ -171,6 +172,7 @@ static inline u8 kvm_arm_pmu_get_pmuver_limit(void)
 {
 	return 0;
 }
+static inline void kvm_vcpu_pmu_resync_el0(void) {}
 
 #endif
 

From cc79bd2738c2d40aba58b2be6ce47dc0e471df0e Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Tue, 22 Aug 2023 09:04:45 -0700
Subject: [PATCH 0602/1189] ntb: Clean up tx tail index on link down

The tx tail index is not reset when the link goes down. This causes the
tail index to go out of sync when the link goes down and comes back up.
Refactor the ntb_qp_link_down_reset() and reset the tail index as well.

Fixes: 2849b5d70641 ("NTB: Reset transport QP link stats on down")
Reported-by: Yuan Y Lu <yuan.y.lu@intel.com>
Tested-by: Yuan Y Lu <yuan.y.lu@intel.com>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
---
 drivers/ntb/ntb_transport.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index 2abd2235bbca..3e7a6a8a9c87 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -909,7 +909,7 @@ static int ntb_set_mw(struct ntb_transport_ctx *nt, int num_mw,
 	return 0;
 }
 
-static void ntb_qp_link_down_reset(struct ntb_transport_qp *qp)
+static void ntb_qp_link_context_reset(struct ntb_transport_qp *qp)
 {
 	qp->link_is_up = false;
 	qp->active = false;
@@ -932,6 +932,13 @@ static void ntb_qp_link_down_reset(struct ntb_transport_qp *qp)
 	qp->tx_async = 0;
 }
 
+static void ntb_qp_link_down_reset(struct ntb_transport_qp *qp)
+{
+	ntb_qp_link_context_reset(qp);
+	if (qp->remote_rx_info)
+		qp->remote_rx_info->entry = qp->rx_max_entry - 1;
+}
+
 static void ntb_qp_link_cleanup(struct ntb_transport_qp *qp)
 {
 	struct ntb_transport_ctx *nt = qp->transport;
@@ -1174,7 +1181,7 @@ static int ntb_transport_init_queue(struct ntb_transport_ctx *nt,
 	qp->ndev = nt->ndev;
 	qp->client_ready = false;
 	qp->event_handler = NULL;
-	ntb_qp_link_down_reset(qp);
+	ntb_qp_link_context_reset(qp);
 
 	if (mw_num < qp_count % mw_count)
 		num_qps_mw = qp_count / mw_count + 1;

From f195a1a6fe416882984f8bd6c61afc1383171860 Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Tue, 22 Aug 2023 09:04:51 -0700
Subject: [PATCH 0603/1189] ntb: Drop packets when qp link is down

Currently when the transport receive packets after netdev has closed the
transport returns error and triggers tx errors to be incremented and
carrier to be stopped. There is no reason to return error if the device is
already closed. Drop the packet and return 0.

Fixes: e26a5843f7f5 ("NTB: Split ntb_hw_intel and ntb_transport drivers")
Reported-by: Yuan Y Lu <yuan.y.lu@intel.com>
Tested-by: Yuan Y Lu <yuan.y.lu@intel.com>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
---
 drivers/ntb/ntb_transport.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index 3e7a6a8a9c87..7884ea9c7643 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -2283,9 +2283,13 @@ int ntb_transport_tx_enqueue(struct ntb_transport_qp *qp, void *cb, void *data,
 	struct ntb_queue_entry *entry;
 	int rc;
 
-	if (!qp || !qp->link_is_up || !len)
+	if (!qp || !len)
 		return -EINVAL;
 
+	/* If the qp link is down already, just ignore. */
+	if (!qp->link_is_up)
+		return 0;
+
 	entry = ntb_list_rm(&qp->ntb_tx_free_q_lock, &qp->tx_free_q);
 	if (!entry) {
 		qp->tx_err_no_buf++;

From 5a7693e6bbf19b22fd6c1d2c4b7beb0a03969e2c Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Tue, 22 Aug 2023 09:04:57 -0700
Subject: [PATCH 0604/1189] ntb: Fix calculation ntb_transport_tx_free_entry()

ntb_transport_tx_free_entry() never returns 0 with the current
calculation. If head == tail, then it would return qp->tx_max_entry.
Change compare to tail >= head and when they are equal, a 0 would be
returned.

Fixes: e74bfeedad08 ("NTB: Add flow control to the ntb_netdev")
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: renlonglong <ren.longlong@h3c.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
---
 drivers/ntb/ntb_transport.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index 7884ea9c7643..9532108d2dce 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -2429,7 +2429,7 @@ unsigned int ntb_transport_tx_free_entry(struct ntb_transport_qp *qp)
 	unsigned int head = qp->tx_index;
 	unsigned int tail = qp->remote_rx_info->entry;
 
-	return tail > head ? tail - head : qp->tx_max_entry + tail - head;
+	return tail >= head ? tail - head : qp->tx_max_entry + tail - head;
 }
 EXPORT_SYMBOL_GPL(ntb_transport_tx_free_entry);
 

From 643982232860887fed493144957ea5794b6557d1 Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Tue, 22 Aug 2023 09:05:02 -0700
Subject: [PATCH 0605/1189] ntb: Check tx descriptors outstanding instead of
 head/tail for tx queue

Use existing function ntb_transport_tx_free_entry() instead of open coding
the check to see if there are outstanding tx descriptors.

Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
---
 drivers/ntb/ntb_transport.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index 9532108d2dce..f9e7847a378e 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -1901,7 +1901,7 @@ err:
 static int ntb_process_tx(struct ntb_transport_qp *qp,
 			  struct ntb_queue_entry *entry)
 {
-	if (qp->tx_index == qp->remote_rx_info->entry) {
+	if (!ntb_transport_tx_free_entry(qp)) {
 		qp->tx_ring_full++;
 		return -EAGAIN;
 	}

From 7a46404b3c01e61807f69a02c81a9e3f3a1b9b0f Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 22 Aug 2023 15:46:48 -0300
Subject: [PATCH 0606/1189] perf lzma: Convert some pr_err() to pr_debug() as
 callers already use pr_debug()

I noticed some error with:

  # perf list ex_ret_brn
  lzma: fopen failed on /usr/lib/modules/5.15.14-100.fc34.x86_64/kernel/net/bluetooth/bnep/bnep.ko.xz: 'No such file or directory'
  lzma: fopen failed on /usr/lib/modules/5.16.16-200.fc35.x86_64/kernel/drivers/gpu/drm/drm_kms_helper.ko.xz: 'No such file or directory'
  lzma: fopen failed on /usr/lib/modules/5.18.16-200.fc36.x86_64/kernel/arch/x86/crypto/crct10dif-pclmul.ko.xz: 'No such file or directory'
  lzma: fopen failed on /usr/lib/modules/5.16.16-200.fc35.x86_64/kernel/drivers/i2c/busses/i2c-piix4.ko.xz: 'No such file or directory'
  <BIG SNIP>

Then using 'perf probe' + 'perf trace' to debug 'perf list', it seems
its some inconsistency in the ~/.debug/ cache where broken build id
symlinks that ends up making it try to uncompress some kernel modules
using the lzma routines:

   395.309 perf/3594447 probe_perf:lzma_decompress_to_file(__probe_ip: 6118448, input_string: "/usr/lib/modules/5.18.17-200.fc36.x86_64/kernel/drivers/nvme/host/nvme.ko.xz")
                                       lzma_decompress_to_file (/var/home/acme/bin/perf)
                                       filename__decompress (/var/home/acme/bin/perf)
                                       filename__read_build_id (/var/home/acme/bin/perf)
                                       filename__sprintf_build_id (inlined)
                                       build_id_cache__valid_id (inlined)
                                       build_id_cache__list_all (/var/home/acme/bin/perf)
                                       print_sdt_events (/var/home/acme/bin/perf)
                                       cmd_list (/var/home/acme/bin/perf)
                                       run_builtin (/var/home/acme/bin/perf)
                                       handle_internal_command (inlined)
                                       run_argv (inlined)
                                       main (/var/home/acme/bin/perf)
                                       __libc_start_call_main (/usr/lib64/libc.so.6)
                                       __libc_start_main@@GLIBC_2.34 (/usr/lib64/libc.so.6)
                                       _start (/var/home/acme/bin/perf)

But callers of filename__decompress() already check its return and use
pr_debug(), so be consistent and make functions it calls also use
pr_debug().

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/ZOUD0+GkuCVkYF7n@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/lzma.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c
index 51424cdc3b68..af9a97612f9d 100644
--- a/tools/perf/util/lzma.c
+++ b/tools/perf/util/lzma.c
@@ -45,15 +45,13 @@ int lzma_decompress_to_file(const char *input, int output_fd)
 
 	infile = fopen(input, "rb");
 	if (!infile) {
-		pr_err("lzma: fopen failed on %s: '%s'\n",
-		       input, strerror(errno));
+		pr_debug("lzma: fopen failed on %s: '%s'\n", input, strerror(errno));
 		return -1;
 	}
 
 	ret = lzma_stream_decoder(&strm, UINT64_MAX, LZMA_CONCATENATED);
 	if (ret != LZMA_OK) {
-		pr_err("lzma: lzma_stream_decoder failed %s (%d)\n",
-			lzma_strerror(ret), ret);
+		pr_debug("lzma: lzma_stream_decoder failed %s (%d)\n", lzma_strerror(ret), ret);
 		goto err_fclose;
 	}
 
@@ -68,7 +66,7 @@ int lzma_decompress_to_file(const char *input, int output_fd)
 			strm.avail_in = fread(buf_in, 1, sizeof(buf_in), infile);
 
 			if (ferror(infile)) {
-				pr_err("lzma: read error: %s\n", strerror(errno));
+				pr_debug("lzma: read error: %s\n", strerror(errno));
 				goto err_lzma_end;
 			}
 
@@ -82,7 +80,7 @@ int lzma_decompress_to_file(const char *input, int output_fd)
 			ssize_t write_size = sizeof(buf_out) - strm.avail_out;
 
 			if (writen(output_fd, buf_out, write_size) != write_size) {
-				pr_err("lzma: write error: %s\n", strerror(errno));
+				pr_debug("lzma: write error: %s\n", strerror(errno));
 				goto err_lzma_end;
 			}
 
@@ -94,7 +92,7 @@ int lzma_decompress_to_file(const char *input, int output_fd)
 			if (ret == LZMA_STREAM_END)
 				break;
 
-			pr_err("lzma: failed %s\n", lzma_strerror(ret));
+			pr_debug("lzma: failed %s\n", lzma_strerror(ret));
 			goto err_lzma_end;
 		}
 	}

From 971fe5095f78b6475c88270aa4b6ee77a791cf25 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Wed, 16 Aug 2023 14:59:23 -0700
Subject: [PATCH 0607/1189] MIPS: VDSO: Conditionally export
 __vdso_gettimeofday()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

ld.lld 16.0.0 and newer defaults to '--no-undefined-version', which
causes the following error when CONFIG_MIPS_CLOCK_VSYSCALL is not set:

  ld.lld: error: version script assignment of 'LINUX_2.6' to symbol '__vdso_gettimeofday' failed: symbol not defined

Only export __vdso_gettimeofday() when it will be present in the final
object file, which clears up the error.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202308170532.zxFFv25c-lkp@intel.com/
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Fangrui Song <maskray@google.com>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/vdso/vdso.lds.S | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/mips/vdso/vdso.lds.S b/arch/mips/vdso/vdso.lds.S
index d90b65724d78..836465e3bcb8 100644
--- a/arch/mips/vdso/vdso.lds.S
+++ b/arch/mips/vdso/vdso.lds.S
@@ -94,7 +94,9 @@ VERSION
 #ifndef CONFIG_MIPS_DISABLE_VDSO
 	global:
 		__vdso_clock_gettime;
+#ifdef CONFIG_MIPS_CLOCK_VSYSCALL
 		__vdso_gettimeofday;
+#endif
 		__vdso_clock_getres;
 #if _MIPS_SIM != _MIPS_SIM_ABI64
 		__vdso_clock_gettime64;

From d913ff561140dd89104dcb01846d789835a5cdc3 Mon Sep 17 00:00:00 2001
From: Trevor Woerner <twoerner@gmail.com>
Date: Thu, 17 Aug 2023 07:50:13 -0400
Subject: [PATCH 0608/1189] arch/mips/configs/*_defconfig cleanup
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Drop CONFIG_IP_NF_TARGET_CLUSTERIP from any remaining mips defconfigs as it
was removed in commit 9db5d918e2c0 ("netfilter: ip_tables: remove clusterip
target").

Signed-off-by: Trevor Woerner <twoerner@gmail.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/configs/ip22_defconfig        | 1 -
 arch/mips/configs/malta_defconfig       | 1 -
 arch/mips/configs/malta_kvm_defconfig   | 1 -
 arch/mips/configs/maltaup_xpa_defconfig | 1 -
 arch/mips/configs/rm200_defconfig       | 1 -
 5 files changed, 5 deletions(-)

diff --git a/arch/mips/configs/ip22_defconfig b/arch/mips/configs/ip22_defconfig
index 897e55579af0..965dfc30417d 100644
--- a/arch/mips/configs/ip22_defconfig
+++ b/arch/mips/configs/ip22_defconfig
@@ -127,7 +127,6 @@ CONFIG_IP_NF_MATCH_TTL=m
 CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_TARGET_REJECT=m
 CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_CLUSTERIP=m
 CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IP_NF_RAW=m
diff --git a/arch/mips/configs/malta_defconfig b/arch/mips/configs/malta_defconfig
index 743209047792..ae1a7793e810 100644
--- a/arch/mips/configs/malta_defconfig
+++ b/arch/mips/configs/malta_defconfig
@@ -127,7 +127,6 @@ CONFIG_IP_NF_MATCH_TTL=m
 CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_TARGET_REJECT=m
 CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_CLUSTERIP=m
 CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IP_NF_RAW=m
diff --git a/arch/mips/configs/malta_kvm_defconfig b/arch/mips/configs/malta_kvm_defconfig
index dd2b9c181f32..c07e30f63d8b 100644
--- a/arch/mips/configs/malta_kvm_defconfig
+++ b/arch/mips/configs/malta_kvm_defconfig
@@ -131,7 +131,6 @@ CONFIG_IP_NF_MATCH_TTL=m
 CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_TARGET_REJECT=m
 CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_CLUSTERIP=m
 CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IP_NF_RAW=m
diff --git a/arch/mips/configs/maltaup_xpa_defconfig b/arch/mips/configs/maltaup_xpa_defconfig
index 97c2d7f530b3..0a5701020d3f 100644
--- a/arch/mips/configs/maltaup_xpa_defconfig
+++ b/arch/mips/configs/maltaup_xpa_defconfig
@@ -128,7 +128,6 @@ CONFIG_IP_NF_MATCH_TTL=m
 CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_TARGET_REJECT=m
 CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_CLUSTERIP=m
 CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IP_NF_RAW=m
diff --git a/arch/mips/configs/rm200_defconfig b/arch/mips/configs/rm200_defconfig
index 7475c2cbea89..d14aae37ed74 100644
--- a/arch/mips/configs/rm200_defconfig
+++ b/arch/mips/configs/rm200_defconfig
@@ -90,7 +90,6 @@ CONFIG_IP_NF_MATCH_TTL=m
 CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_TARGET_REJECT=m
 CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_CLUSTERIP=m
 CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IP_NF_RAW=m

From 9823ae6f68786aff4fbe870897aee1abc0b01fda Mon Sep 17 00:00:00 2001
From: Kajol Jain <kjain@linux.ibm.com>
Date: Wed, 23 Aug 2023 13:21:03 +0530
Subject: [PATCH 0609/1189] perf bench breakpoint: Skip run if no breakpoints
 available

Based on commit 7d54a4acd8c1de3e ("perf test: Skip watchpoint tests if
no watchpoints available"), hardware breakpoints are not available for
power9 platform and because of that 'perf bench breakpoint' run fails on
power9 platform.

Add code to check for the return value of perf_event_open() in the
breakpoint run and skip the 'perf bench breakpoint' run, if hardware
breakpoints are not available.

Result on power9 system before patch changes:

  [command]# perf bench breakpoint thread
  perf_event_open: No such device

Result on power9 system after patch changes:

  [command]# ./perf bench breakpoint thread
  Skipping perf bench breakpoint thread: No hardware support

Reported-by: Disha Goel <disgoel@linux.vnet.ibm.com>
Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Acked-by: Naveen N Rao <naveen@kernel.org>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Disha Goel <disgoel@linux.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230823075103.190565-1-kjain@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/bench/breakpoint.c | 24 +++++++++++++++++++++---
 1 file changed, 21 insertions(+), 3 deletions(-)

diff --git a/tools/perf/bench/breakpoint.c b/tools/perf/bench/breakpoint.c
index 41385f89ffc7..dfd18f5db97d 100644
--- a/tools/perf/bench/breakpoint.c
+++ b/tools/perf/bench/breakpoint.c
@@ -47,6 +47,7 @@ struct breakpoint {
 static int breakpoint_setup(void *addr)
 {
 	struct perf_event_attr attr = { .size = 0, };
+	int fd;
 
 	attr.type = PERF_TYPE_BREAKPOINT;
 	attr.size = sizeof(attr);
@@ -56,7 +57,12 @@ static int breakpoint_setup(void *addr)
 	attr.bp_addr = (unsigned long)addr;
 	attr.bp_type = HW_BREAKPOINT_RW;
 	attr.bp_len = HW_BREAKPOINT_LEN_1;
-	return syscall(SYS_perf_event_open, &attr, 0, -1, -1, 0);
+	fd = syscall(SYS_perf_event_open, &attr, 0, -1, -1, 0);
+
+	if (fd < 0)
+		fd = -errno;
+
+	return fd;
 }
 
 static void *passive_thread(void *arg)
@@ -122,8 +128,14 @@ int bench_breakpoint_thread(int argc, const char **argv)
 
 	for (i = 0; i < thread_params.nbreakpoints; i++) {
 		breakpoints[i].fd = breakpoint_setup(&breakpoints[i].watched);
-		if (breakpoints[i].fd == -1)
+
+		if (breakpoints[i].fd < 0) {
+			if (breakpoints[i].fd == -ENODEV) {
+				printf("Skipping perf bench breakpoint thread: No hardware support\n");
+				return 0;
+			}
 			exit((perror("perf_event_open"), EXIT_FAILURE));
+		}
 	}
 	gettimeofday(&start, NULL);
 	for (i = 0; i < thread_params.nparallel; i++) {
@@ -196,8 +208,14 @@ int bench_breakpoint_enable(int argc, const char **argv)
 		exit(EXIT_FAILURE);
 	}
 	fd = breakpoint_setup(&watched);
-	if (fd == -1)
+
+	if (fd < 0) {
+		if (fd == -ENODEV) {
+			printf("Skipping perf bench breakpoint enable: No hardware support\n");
+			return 0;
+		}
 		exit((perror("perf_event_open"), EXIT_FAILURE));
+	}
 	nthreads = enable_params.npassive + enable_params.nactive;
 	threads = calloc(nthreads, sizeof(threads[0]));
 	if (!threads)

From 91e2e9f0b881295b960b88373f15e5630891c12e Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 23 Aug 2023 01:08:04 -0700
Subject: [PATCH 0610/1189] perf script ibs: Remove unused include

Done to reduce dependencies on pmu-events.h.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230823080828.1460376-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/amd-sample-raw.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/perf/util/amd-sample-raw.c b/tools/perf/util/amd-sample-raw.c
index 6a6ddba76c75..9d0ce88e90e4 100644
--- a/tools/perf/util/amd-sample-raw.c
+++ b/tools/perf/util/amd-sample-raw.c
@@ -15,7 +15,6 @@
 #include "session.h"
 #include "evlist.h"
 #include "sample-raw.h"
-#include "pmu-events/pmu-events.h"
 #include "util/sample.h"
 
 static u32 cpu_family, cpu_model, ibs_fetch_type, ibs_op_type;

From e1a3aad31c3b4b4d3cbd38bc010bb63ba9f63dfa Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 23 Aug 2023 01:08:05 -0700
Subject: [PATCH 0611/1189] perf pmu: Avoid a path name copy

Rather than read a base path and append into a 2nd path, read the base
path directly into output buffer and append to that.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230823080828.1460376-3-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/pmu.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index a7f05e4dda97..7683c6749d66 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1756,17 +1756,19 @@ int perf_pmu__event_source_devices_fd(void)
  * then pathname will be filled with
  * "/sys/bus/event_source/devices/cs_etm/format"
  *
- * Return 0 if the sysfs mountpoint couldn't be found or if no
- * characters were written.
+ * Return 0 if the sysfs mountpoint couldn't be found, if no characters were
+ * written or if the buffer size is exceeded.
  */
 int perf_pmu__pathname_scnprintf(char *buf, size_t size,
 				 const char *pmu_name, const char *filename)
 {
-	char base_path[PATH_MAX];
+	size_t len;
 
-	if (!perf_pmu__event_source_devices_scnprintf(base_path, sizeof(base_path)))
+	len = perf_pmu__event_source_devices_scnprintf(buf, size);
+	if (!len || (len + strlen(pmu_name) + strlen(filename) + 1)  >= size)
 		return 0;
-	return scnprintf(buf, size, "%s%s/%s", base_path, pmu_name, filename);
+
+	return scnprintf(buf + len, size - len, "%s/%s", pmu_name, filename);
 }
 
 int perf_pmu__pathname_fd(int dirfd, const char *pmu_name, const char *filename, int flags)

From cc5adb7347bed620182b345e6a3726d8f4acce01 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 23 Aug 2023 01:08:06 -0700
Subject: [PATCH 0612/1189] perf pmu: Move perf_pmu__set_format to pmu.y

Avoid having the function in the C and header file, as it is only used
locally by pmu.y.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230823080828.1460376-4-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/pmu.c | 12 ------------
 tools/perf/util/pmu.h |  1 -
 tools/perf/util/pmu.y | 12 ++++++++++++
 3 files changed, 12 insertions(+), 13 deletions(-)

diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 7683c6749d66..40999e1fab8f 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1417,18 +1417,6 @@ int perf_pmu__new_format(struct list_head *list, char *name,
 	return 0;
 }
 
-void perf_pmu__set_format(unsigned long *bits, long from, long to)
-{
-	long b;
-
-	if (!to)
-		to = from;
-
-	memset(bits, 0, BITS_TO_BYTES(PERF_PMU_FORMAT_BITS));
-	for (b = from; b <= to; b++)
-		__set_bit(b, bits);
-}
-
 void perf_pmu__del_formats(struct list_head *formats)
 {
 	struct perf_pmu_format *fmt, *tmp;
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 7ff925224165..9c9ea40b9c71 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -231,7 +231,6 @@ void perf_pmu_error(struct list_head *list, char *name, void *scanner, char cons
 
 int perf_pmu__new_format(struct list_head *list, char *name,
 			 int config, unsigned long *bits);
-void perf_pmu__set_format(unsigned long *bits, long from, long to);
 int perf_pmu__format_parse(int dirfd, struct list_head *head);
 void perf_pmu__del_formats(struct list_head *formats);
 bool perf_pmu__has_format(const struct perf_pmu *pmu, const char *name);
diff --git a/tools/perf/util/pmu.y b/tools/perf/util/pmu.y
index 3d46cca3bb94..9bd9e30791ff 100644
--- a/tools/perf/util/pmu.y
+++ b/tools/perf/util/pmu.y
@@ -21,6 +21,18 @@ do { \
                 YYABORT; \
 } while (0)
 
+static void perf_pmu__set_format(unsigned long *bits, long from, long to)
+{
+	long b;
+
+	if (!to)
+		to = from;
+
+	memset(bits, 0, BITS_TO_BYTES(PERF_PMU_FORMAT_BITS));
+	for (b = from; b <= to; b++)
+		__set_bit(b, bits);
+}
+
 %}
 
 %token PP_CONFIG

From 6f2f6eafcd0d54e2c9bdbd4f89732df2a9b6fb76 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 23 Aug 2023 01:08:07 -0700
Subject: [PATCH 0613/1189] perf pmu: Reduce scope of perf_pmu_error()

Move declaration from header file to pmu.y and make static.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230823080828.1460376-5-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/pmu.h | 1 -
 tools/perf/util/pmu.y | 4 +++-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 9c9ea40b9c71..5394c85d20b9 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -227,7 +227,6 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 			  struct perf_pmu_info *info);
 struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
 				  struct list_head *head_terms);
-void perf_pmu_error(struct list_head *list, char *name, void *scanner, char const *msg);
 
 int perf_pmu__new_format(struct list_head *list, char *name,
 			 int config, unsigned long *bits);
diff --git a/tools/perf/util/pmu.y b/tools/perf/util/pmu.y
index 9bd9e30791ff..d861a5bfa3bd 100644
--- a/tools/perf/util/pmu.y
+++ b/tools/perf/util/pmu.y
@@ -21,6 +21,8 @@ do { \
                 YYABORT; \
 } while (0)
 
+static void perf_pmu_error(struct list_head *list, char *name, void *scanner, char const *msg);
+
 static void perf_pmu__set_format(unsigned long *bits, long from, long to)
 {
 	long b;
@@ -93,7 +95,7 @@ PP_VALUE
 
 %%
 
-void perf_pmu_error(struct list_head *list __maybe_unused,
+static void perf_pmu_error(struct list_head *list __maybe_unused,
 		    char *name __maybe_unused,
 		    void *scanner __maybe_unused,
 		    char const *msg __maybe_unused)

From 804fee5d0f7f14d9328efc1edfed1dba39aba532 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 23 Aug 2023 01:08:08 -0700
Subject: [PATCH 0614/1189] perf pmu: Avoid passing format list to
 perf_pmu__config_terms()

Abstract the format list better, hiding it in the PMU, by changing
perf_pmu__config_terms() the PMU rather than the format list in the PMU.

Change the PMU test to pass a dummy PMU for this purpose. Changing the
test allows perf_pmu__del_formats() to become static.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230823080828.1460376-6-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/x86/util/intel-pt.c | 30 +++++--------
 tools/perf/tests/pmu.c              | 70 ++++++++++++++++-------------
 tools/perf/util/pmu.c               | 19 ++++----
 tools/perf/util/pmu.h               |  3 +-
 4 files changed, 58 insertions(+), 64 deletions(-)

diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 74b70fd379df..0da76f848cbc 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -60,8 +60,7 @@ struct intel_pt_recording {
 	size_t				priv_size;
 };
 
-static int intel_pt_parse_terms_with_default(const char *pmu_name,
-					     struct list_head *formats,
+static int intel_pt_parse_terms_with_default(struct perf_pmu *pmu,
 					     const char *str,
 					     u64 *config)
 {
@@ -80,8 +79,7 @@ static int intel_pt_parse_terms_with_default(const char *pmu_name,
 		goto out_free;
 
 	attr.config = *config;
-	err = perf_pmu__config_terms(pmu_name, formats, &attr, terms, true,
-				     NULL);
+	err = perf_pmu__config_terms(pmu, &attr, terms, /*zero=*/true, /*err=*/NULL);
 	if (err)
 		goto out_free;
 
@@ -91,12 +89,10 @@ out_free:
 	return err;
 }
 
-static int intel_pt_parse_terms(const char *pmu_name, struct list_head *formats,
-				const char *str, u64 *config)
+static int intel_pt_parse_terms(struct perf_pmu *pmu, const char *str, u64 *config)
 {
 	*config = 0;
-	return intel_pt_parse_terms_with_default(pmu_name, formats, str,
-						 config);
+	return intel_pt_parse_terms_with_default(pmu, str, config);
 }
 
 static u64 intel_pt_masked_bits(u64 mask, u64 bits)
@@ -236,8 +232,7 @@ static u64 intel_pt_default_config(struct perf_pmu *intel_pt_pmu)
 
 	pr_debug2("%s default config: %s\n", intel_pt_pmu->name, buf);
 
-	intel_pt_parse_terms(intel_pt_pmu->name, &intel_pt_pmu->format, buf,
-			     &config);
+	intel_pt_parse_terms(intel_pt_pmu, buf, &config);
 
 	close(dirfd);
 	return config;
@@ -348,16 +343,12 @@ static int intel_pt_info_fill(struct auxtrace_record *itr,
 	if (priv_size != ptr->priv_size)
 		return -EINVAL;
 
-	intel_pt_parse_terms(intel_pt_pmu->name, &intel_pt_pmu->format,
-			     "tsc", &tsc_bit);
-	intel_pt_parse_terms(intel_pt_pmu->name, &intel_pt_pmu->format,
-			     "noretcomp", &noretcomp_bit);
-	intel_pt_parse_terms(intel_pt_pmu->name, &intel_pt_pmu->format,
-			     "mtc", &mtc_bit);
+	intel_pt_parse_terms(intel_pt_pmu, "tsc", &tsc_bit);
+	intel_pt_parse_terms(intel_pt_pmu, "noretcomp", &noretcomp_bit);
+	intel_pt_parse_terms(intel_pt_pmu, "mtc", &mtc_bit);
 	mtc_freq_bits = perf_pmu__format_bits(&intel_pt_pmu->format,
 					      "mtc_period");
-	intel_pt_parse_terms(intel_pt_pmu->name, &intel_pt_pmu->format,
-			     "cyc", &cyc_bit);
+	intel_pt_parse_terms(intel_pt_pmu, "cyc", &cyc_bit);
 
 	intel_pt_tsc_ctc_ratio(&tsc_ctc_ratio_n, &tsc_ctc_ratio_d);
 
@@ -781,8 +772,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 		intel_pt_evsel->core.attr.aux_watermark = aux_watermark;
 	}
 
-	intel_pt_parse_terms(intel_pt_pmu->name, &intel_pt_pmu->format,
-			     "tsc", &tsc_bit);
+	intel_pt_parse_terms(intel_pt_pmu, "tsc", &tsc_bit);
 
 	if (opts->full_auxtrace && (intel_pt_evsel->core.attr.config & tsc_bit))
 		have_timing_info = true;
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index a4452639a3d4..a4a43db76012 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -7,6 +7,7 @@
 #include <stdio.h>
 #include <linux/kernel.h>
 #include <linux/limits.h>
+#include <linux/zalloc.h>
 
 /* Simulated format definitions. */
 static struct test_format {
@@ -141,48 +142,55 @@ static struct list_head *test_terms_list(void)
 static int test__pmu(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	char dir[PATH_MAX];
-	char *format = test_format_dir_get(dir, sizeof(dir));
-	LIST_HEAD(formats);
+	char *format;
 	struct list_head *terms = test_terms_list();
+	struct perf_event_attr attr;
+	struct perf_pmu *pmu;
+	int fd;
 	int ret;
 
-	if (!format)
+	pmu = zalloc(sizeof(*pmu));
+	if (!pmu)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&pmu->format);
+	INIT_LIST_HEAD(&pmu->aliases);
+	INIT_LIST_HEAD(&pmu->caps);
+	format = test_format_dir_get(dir, sizeof(dir));
+	if (!format) {
+		free(pmu);
 		return -EINVAL;
+	}
 
-	do {
-		struct perf_event_attr attr;
-		int fd;
+	memset(&attr, 0, sizeof(attr));
 
-		memset(&attr, 0, sizeof(attr));
+	fd = open(format, O_DIRECTORY);
+	if (fd < 0) {
+		ret = fd;
+		goto out;
+	}
 
-		fd = open(format, O_DIRECTORY);
-		if (fd < 0) {
-			ret = fd;
-			break;
-		}
-		ret = perf_pmu__format_parse(fd, &formats);
-		if (ret)
-			break;
+	pmu->name = strdup("perf-pmu-test");
+	ret = perf_pmu__format_parse(fd, &pmu->format);
+	if (ret)
+		goto out;
 
-		ret = perf_pmu__config_terms("perf-pmu-test", &formats, &attr,
-					     terms, false, NULL);
-		if (ret)
-			break;
+	ret = perf_pmu__config_terms(pmu, &attr, terms, /*zero=*/false, /*err=*/NULL);
+	if (ret)
+		goto out;
 
-		ret = -EINVAL;
+	ret = -EINVAL;
+	if (attr.config  != 0xc00000000002a823)
+		goto out;
+	if (attr.config1 != 0x8000400000000145)
+		goto out;
+	if (attr.config2 != 0x0400000020041d07)
+		goto out;
 
-		if (attr.config  != 0xc00000000002a823)
-			break;
-		if (attr.config1 != 0x8000400000000145)
-			break;
-		if (attr.config2 != 0x0400000020041d07)
-			break;
-
-		ret = 0;
-	} while (0);
-
-	perf_pmu__del_formats(&formats);
+	ret = 0;
+out:
 	test_format_dir_put(format);
+	perf_pmu__delete(pmu);
 	return ret;
 }
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 40999e1fab8f..89573a8eaf0b 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1135,8 +1135,7 @@ error:
  * Setup one of config[12] attr members based on the
  * user input data - term parameter.
  */
-static int pmu_config_term(const char *pmu_name,
-			   struct list_head *formats,
+static int pmu_config_term(struct perf_pmu *pmu,
 			   struct perf_event_attr *attr,
 			   struct parse_events_term *term,
 			   struct list_head *head_terms,
@@ -1160,15 +1159,15 @@ static int pmu_config_term(const char *pmu_name,
 	if (parse_events__is_hardcoded_term(term))
 		return 0;
 
-	format = pmu_find_format(formats, term->config);
+	format = pmu_find_format(&pmu->format, term->config);
 	if (!format) {
-		char *pmu_term = pmu_formats_string(formats);
+		char *pmu_term = pmu_formats_string(&pmu->format);
 		char *unknown_term;
 		char *help_msg;
 
 		if (asprintf(&unknown_term,
 				"unknown term '%s' for pmu '%s'",
-				term->config, pmu_name) < 0)
+				term->config, pmu->name) < 0)
 			unknown_term = NULL;
 		help_msg = parse_events_formats_error_string(pmu_term);
 		if (err) {
@@ -1259,7 +1258,7 @@ static int pmu_config_term(const char *pmu_name,
 	return 0;
 }
 
-int perf_pmu__config_terms(const char *pmu_name, struct list_head *formats,
+int perf_pmu__config_terms(struct perf_pmu *pmu,
 			   struct perf_event_attr *attr,
 			   struct list_head *head_terms,
 			   bool zero, struct parse_events_error *err)
@@ -1267,8 +1266,7 @@ int perf_pmu__config_terms(const char *pmu_name, struct list_head *formats,
 	struct parse_events_term *term;
 
 	list_for_each_entry(term, head_terms, list) {
-		if (pmu_config_term(pmu_name, formats, attr, term, head_terms,
-				    zero, err))
+		if (pmu_config_term(pmu, attr, term, head_terms, zero, err))
 			return -EINVAL;
 	}
 
@@ -1286,8 +1284,7 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 {
 	bool zero = !!pmu->default_config;
 
-	return perf_pmu__config_terms(pmu->name, &pmu->format, attr,
-				      head_terms, zero, err);
+	return perf_pmu__config_terms(pmu, attr, head_terms, zero, err);
 }
 
 static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
@@ -1417,7 +1414,7 @@ int perf_pmu__new_format(struct list_head *list, char *name,
 	return 0;
 }
 
-void perf_pmu__del_formats(struct list_head *formats)
+static void perf_pmu__del_formats(struct list_head *formats)
 {
 	struct perf_pmu_format *fmt, *tmp;
 
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 5394c85d20b9..eb26c8bc079f 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -217,7 +217,7 @@ void pmu_add_sys_aliases(struct list_head *head, struct perf_pmu *pmu);
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 		     struct list_head *head_terms,
 		     struct parse_events_error *error);
-int perf_pmu__config_terms(const char *pmu_name, struct list_head *formats,
+int perf_pmu__config_terms(struct perf_pmu *pmu,
 			   struct perf_event_attr *attr,
 			   struct list_head *head_terms,
 			   bool zero, struct parse_events_error *error);
@@ -231,7 +231,6 @@ struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
 int perf_pmu__new_format(struct list_head *list, char *name,
 			 int config, unsigned long *bits);
 int perf_pmu__format_parse(int dirfd, struct list_head *head);
-void perf_pmu__del_formats(struct list_head *formats);
 bool perf_pmu__has_format(const struct perf_pmu *pmu, const char *name);
 
 bool is_pmu_core(const char *name);

From 7eb5473314b5e1111364c109fa1cde8de1e51739 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 23 Aug 2023 01:08:09 -0700
Subject: [PATCH 0615/1189] perf pmu: Avoid passing format list to
 perf_pmu__format_type

Pass the pmu so the format list can be better abstracted and later
lazily loaded.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230823080828.1460376-7-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.c | 2 +-
 tools/perf/util/pmu.c          | 4 ++--
 tools/perf/util/pmu.h          | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 00a8ec94f5b2..8ede27089766 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1159,7 +1159,7 @@ static int get_config_chgs(struct perf_pmu *pmu, struct list_head *head_config,
 	list_for_each_entry(term, head_config, list) {
 		switch (term->type_term) {
 		case PARSE_EVENTS__TERM_TYPE_USER:
-			type = perf_pmu__format_type(&pmu->format, term->config);
+			type = perf_pmu__format_type(pmu, term->config);
 			if (type != PERF_PMU_FORMAT_VALUE_CONFIG)
 				continue;
 			bits |= perf_pmu__format_bits(&pmu->format, term->config);
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 89573a8eaf0b..96189afe54b0 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1038,9 +1038,9 @@ __u64 perf_pmu__format_bits(struct list_head *formats, const char *name)
 	return bits;
 }
 
-int perf_pmu__format_type(struct list_head *formats, const char *name)
+int perf_pmu__format_type(struct perf_pmu *pmu, const char *name)
 {
-	struct perf_pmu_format *format = pmu_find_format(formats, name);
+	struct perf_pmu_format *format = pmu_find_format(&pmu->format, name);
 
 	if (!format)
 		return -1;
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index eb26c8bc079f..1ea78d2fa531 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -222,7 +222,7 @@ int perf_pmu__config_terms(struct perf_pmu *pmu,
 			   struct list_head *head_terms,
 			   bool zero, struct parse_events_error *error);
 __u64 perf_pmu__format_bits(struct list_head *formats, const char *name);
-int perf_pmu__format_type(struct list_head *formats, const char *name);
+int perf_pmu__format_type(struct perf_pmu *pmu, const char *name);
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 			  struct perf_pmu_info *info);
 struct list_head *perf_pmu__alias(struct perf_pmu *pmu,

From da6a5afda54d478980fb82c45390f4a4c4cfa431 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 23 Aug 2023 01:08:10 -0700
Subject: [PATCH 0616/1189] perf pmu: Avoid passing format list to
 perf_pmu__format_bits()

Pass the PMU so the format list can be better abstracted and later
lazily loaded.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230823080828.1460376-8-irogers@google.com
[ Did missing conversions in tools/perf/arch/arm*/util/cs-etm.c ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/arm/util/cs-etm.c    | 12 ++++++------
 tools/perf/arch/arm64/util/arm-spe.c |  2 +-
 tools/perf/arch/x86/util/intel-pt.c  |  7 +++----
 tools/perf/util/parse-events.c       |  2 +-
 tools/perf/util/pmu.c                |  6 +++---
 tools/perf/util/pmu.h                |  2 +-
 6 files changed, 15 insertions(+), 16 deletions(-)

diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 7c51fa182b51..b8d6a953fd74 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -79,9 +79,9 @@ static int cs_etm_validate_context_id(struct auxtrace_record *itr,
 	int err;
 	u32 val;
 	u64 contextid = evsel->core.attr.config &
-		(perf_pmu__format_bits(&cs_etm_pmu->format, "contextid") |
-		 perf_pmu__format_bits(&cs_etm_pmu->format, "contextid1") |
-		 perf_pmu__format_bits(&cs_etm_pmu->format, "contextid2"));
+		(perf_pmu__format_bits(cs_etm_pmu, "contextid") |
+		 perf_pmu__format_bits(cs_etm_pmu, "contextid1") |
+		 perf_pmu__format_bits(cs_etm_pmu, "contextid2"));
 
 	if (!contextid)
 		return 0;
@@ -106,7 +106,7 @@ static int cs_etm_validate_context_id(struct auxtrace_record *itr,
 	}
 
 	if (contextid &
-	    perf_pmu__format_bits(&cs_etm_pmu->format, "contextid1")) {
+	    perf_pmu__format_bits(cs_etm_pmu, "contextid1")) {
 		/*
 		 * TRCIDR2.CIDSIZE, bit [9-5], indicates whether contextID
 		 * tracing is supported:
@@ -122,7 +122,7 @@ static int cs_etm_validate_context_id(struct auxtrace_record *itr,
 	}
 
 	if (contextid &
-	    perf_pmu__format_bits(&cs_etm_pmu->format, "contextid2")) {
+	    perf_pmu__format_bits(cs_etm_pmu, "contextid2")) {
 		/*
 		 * TRCIDR2.VMIDOPT[30:29] != 0 and
 		 * TRCIDR2.VMIDSIZE[14:10] == 0b00100 (32bit virtual contextid)
@@ -151,7 +151,7 @@ static int cs_etm_validate_timestamp(struct auxtrace_record *itr,
 	u32 val;
 
 	if (!(evsel->core.attr.config &
-	      perf_pmu__format_bits(&cs_etm_pmu->format, "timestamp")))
+	      perf_pmu__format_bits(cs_etm_pmu, "timestamp")))
 		return 0;
 
 	if (!cs_etm_is_etmv4(itr, cpu)) {
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index 3b1676ff03f9..9cc3d6dcb849 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -230,7 +230,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 	 * inform that the resulting output's SPE samples contain physical addresses
 	 * where applicable.
 	 */
-	bit = perf_pmu__format_bits(&arm_spe_pmu->format, "pa_enable");
+	bit = perf_pmu__format_bits(arm_spe_pmu, "pa_enable");
 	if (arm_spe_evsel->core.attr.config & bit)
 		evsel__set_sample_bit(arm_spe_evsel, PHYS_ADDR);
 
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 0da76f848cbc..27944c15ac14 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -122,7 +122,7 @@ static int intel_pt_read_config(struct perf_pmu *intel_pt_pmu, const char *str,
 
 	*res = 0;
 
-	mask = perf_pmu__format_bits(&intel_pt_pmu->format, str);
+	mask = perf_pmu__format_bits(intel_pt_pmu, str);
 	if (!mask)
 		return -EINVAL;
 
@@ -346,8 +346,7 @@ static int intel_pt_info_fill(struct auxtrace_record *itr,
 	intel_pt_parse_terms(intel_pt_pmu, "tsc", &tsc_bit);
 	intel_pt_parse_terms(intel_pt_pmu, "noretcomp", &noretcomp_bit);
 	intel_pt_parse_terms(intel_pt_pmu, "mtc", &mtc_bit);
-	mtc_freq_bits = perf_pmu__format_bits(&intel_pt_pmu->format,
-					      "mtc_period");
+	mtc_freq_bits = perf_pmu__format_bits(intel_pt_pmu, "mtc_period");
 	intel_pt_parse_terms(intel_pt_pmu, "cyc", &cyc_bit);
 
 	intel_pt_tsc_ctc_ratio(&tsc_ctc_ratio_n, &tsc_ctc_ratio_d);
@@ -502,7 +501,7 @@ static int intel_pt_val_config_term(struct perf_pmu *intel_pt_pmu, int dirfd,
 
 	valid |= 1;
 
-	bits = perf_pmu__format_bits(&intel_pt_pmu->format, name);
+	bits = perf_pmu__format_bits(intel_pt_pmu, name);
 
 	config &= bits;
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 8ede27089766..7d9d687d9191 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1162,7 +1162,7 @@ static int get_config_chgs(struct perf_pmu *pmu, struct list_head *head_config,
 			type = perf_pmu__format_type(pmu, term->config);
 			if (type != PERF_PMU_FORMAT_VALUE_CONFIG)
 				continue;
-			bits |= perf_pmu__format_bits(&pmu->format, term->config);
+			bits |= perf_pmu__format_bits(pmu, term->config);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_CONFIG:
 			bits = ~(u64)0;
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 96189afe54b0..1839c3668ec5 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1000,7 +1000,7 @@ void evsel__set_config_if_unset(struct perf_pmu *pmu, struct evsel *evsel,
 	if (term)
 		user_bits = term->val.cfg_chg;
 
-	bits = perf_pmu__format_bits(&pmu->format, config_name);
+	bits = perf_pmu__format_bits(pmu, config_name);
 
 	/* Do nothing if the user changed the value */
 	if (bits & user_bits)
@@ -1023,9 +1023,9 @@ pmu_find_format(struct list_head *formats, const char *name)
 	return NULL;
 }
 
-__u64 perf_pmu__format_bits(struct list_head *formats, const char *name)
+__u64 perf_pmu__format_bits(struct perf_pmu *pmu, const char *name)
 {
-	struct perf_pmu_format *format = pmu_find_format(formats, name);
+	struct perf_pmu_format *format = pmu_find_format(&pmu->format, name);
 	__u64 bits = 0;
 	int fbit;
 
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 1ea78d2fa531..1249fca02ffd 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -221,7 +221,7 @@ int perf_pmu__config_terms(struct perf_pmu *pmu,
 			   struct perf_event_attr *attr,
 			   struct list_head *head_terms,
 			   bool zero, struct parse_events_error *error);
-__u64 perf_pmu__format_bits(struct list_head *formats, const char *name);
+__u64 perf_pmu__format_bits(struct perf_pmu *pmu, const char *name);
 int perf_pmu__format_type(struct perf_pmu *pmu, const char *name);
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 			  struct perf_pmu_info *info);

From 838a8c5f40dd272f0b684cde6bf681c5a4d33c0d Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 23 Aug 2023 01:08:11 -0700
Subject: [PATCH 0617/1189] perf pmu: Pass PMU rather than aliases and format

Pass the pmu so the aliases and format list can be better abstracted
and later lazily loaded.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230823080828.1460376-9-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/pmu-events.c | 47 ++++++++------------
 tools/perf/tests/pmu.c        |  2 +-
 tools/perf/util/pmu.c         | 81 +++++++++++++++++++----------------
 tools/perf/util/pmu.h         |  9 ++--
 4 files changed, 68 insertions(+), 71 deletions(-)

diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
index 64383fc34ef1..05d6e6e21c6f 100644
--- a/tools/perf/tests/pmu-events.c
+++ b/tools/perf/tests/pmu-events.c
@@ -496,26 +496,13 @@ static int test__pmu_event_table(struct test_suite *test __maybe_unused,
 	return 0;
 }
 
-static struct perf_pmu_alias *find_alias(const char *test_event, struct list_head *aliases)
-{
-	struct perf_pmu_alias *alias;
-
-	list_for_each_entry(alias, aliases, list)
-		if (!strcmp(test_event, alias->name))
-			return alias;
-
-	return NULL;
-}
-
 /* Verify aliases are as expected */
 static int __test_core_pmu_event_aliases(char *pmu_name, int *count)
 {
 	struct perf_pmu_test_event const **test_event_table;
 	struct perf_pmu *pmu;
-	LIST_HEAD(aliases);
 	int res = 0;
 	const struct pmu_events_table *table = find_core_events_table("testarch", "testcpu");
-	struct perf_pmu_alias *a, *tmp;
 
 	if (!table)
 		return -1;
@@ -526,14 +513,18 @@ static int __test_core_pmu_event_aliases(char *pmu_name, int *count)
 	if (!pmu)
 		return -1;
 
-	pmu->name = pmu_name;
+	INIT_LIST_HEAD(&pmu->format);
+	INIT_LIST_HEAD(&pmu->aliases);
+	INIT_LIST_HEAD(&pmu->caps);
+	INIT_LIST_HEAD(&pmu->list);
+	pmu->name = strdup(pmu_name);
 
-	pmu_add_cpu_aliases_table(&aliases, pmu, table);
+	pmu_add_cpu_aliases_table(pmu, table);
 
 	for (; *test_event_table; test_event_table++) {
 		struct perf_pmu_test_event const *test_event = *test_event_table;
 		struct pmu_event const *event = &test_event->event;
-		struct perf_pmu_alias *alias = find_alias(event->name, &aliases);
+		struct perf_pmu_alias *alias = perf_pmu__find_alias(pmu, event->name);
 
 		if (!alias) {
 			pr_debug("testing aliases core PMU %s: no alias, alias_table->name=%s\n",
@@ -551,12 +542,8 @@ static int __test_core_pmu_event_aliases(char *pmu_name, int *count)
 		pr_debug2("testing aliases core PMU %s: matched event %s\n",
 			  pmu_name, alias->name);
 	}
+	perf_pmu__delete(pmu);
 
-	list_for_each_entry_safe(a, tmp, &aliases, list) {
-		list_del(&a->list);
-		perf_pmu_free_alias(a);
-	}
-	free(pmu);
 	return res;
 }
 
@@ -568,17 +555,16 @@ static int __test_uncore_pmu_event_aliases(struct perf_pmu_test_pmu *test_pmu)
 	const char *pmu_name = pmu->name;
 	struct perf_pmu_alias *a, *tmp, *alias;
 	const struct pmu_events_table *events_table;
-	LIST_HEAD(aliases);
 	int res = 0;
 
 	events_table = find_core_events_table("testarch", "testcpu");
 	if (!events_table)
 		return -1;
-	pmu_add_cpu_aliases_table(&aliases, pmu, events_table);
-	pmu_add_sys_aliases(&aliases, pmu);
+	pmu_add_cpu_aliases_table(pmu, events_table);
+	pmu_add_sys_aliases(pmu);
 
 	/* Count how many aliases we generated */
-	list_for_each_entry(alias, &aliases, list)
+	list_for_each_entry(alias, &pmu->aliases, list)
 		alias_count++;
 
 	/* Count how many aliases we expect from the known table */
@@ -592,7 +578,7 @@ static int __test_uncore_pmu_event_aliases(struct perf_pmu_test_pmu *test_pmu)
 		goto out;
 	}
 
-	list_for_each_entry(alias, &aliases, list) {
+	list_for_each_entry(alias, &pmu->aliases, list) {
 		bool matched = false;
 
 		for (table = &test_pmu->aliases[0]; *table; table++) {
@@ -625,7 +611,7 @@ static int __test_uncore_pmu_event_aliases(struct perf_pmu_test_pmu *test_pmu)
 	}
 
 out:
-	list_for_each_entry_safe(a, tmp, &aliases, list) {
+	list_for_each_entry_safe(a, tmp, &pmu->aliases, list) {
 		list_del(&a->list);
 		perf_pmu_free_alias(a);
 	}
@@ -732,8 +718,13 @@ static int test__aliases(struct test_suite *test __maybe_unused,
 	}
 
 	for (i = 0; i < ARRAY_SIZE(test_pmus); i++) {
-		int res = __test_uncore_pmu_event_aliases(&test_pmus[i]);
+		int res;
 
+		INIT_LIST_HEAD(&test_pmus[i].pmu.format);
+		INIT_LIST_HEAD(&test_pmus[i].pmu.aliases);
+		INIT_LIST_HEAD(&test_pmus[i].pmu.caps);
+
+		res = __test_uncore_pmu_event_aliases(&test_pmus[i]);
 		if (res)
 			return res;
 	}
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index a4a43db76012..2c1c349a42e2 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -171,7 +171,7 @@ static int test__pmu(struct test_suite *test __maybe_unused, int subtest __maybe
 	}
 
 	pmu->name = strdup("perf-pmu-test");
-	ret = perf_pmu__format_parse(fd, &pmu->format);
+	ret = perf_pmu__format_parse(pmu, fd);
 	if (ret)
 		goto out;
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 1839c3668ec5..42f3249994ab 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -58,7 +58,7 @@ struct perf_pmu_format {
  * Parse & process all the sysfs attributes located under
  * the directory specified in 'dir' parameter.
  */
-int perf_pmu__format_parse(int dirfd, struct list_head *head)
+int perf_pmu__format_parse(struct perf_pmu *pmu, int dirfd)
 {
 	struct dirent *evt_ent;
 	DIR *format_dir;
@@ -96,7 +96,7 @@ int perf_pmu__format_parse(int dirfd, struct list_head *head)
 		}
 
 		perf_pmu_set_in(file, scanner);
-		ret = perf_pmu_parse(head, name, scanner);
+		ret = perf_pmu_parse(&pmu->format, name, scanner);
 		perf_pmu_lex_destroy(scanner);
 		fclose(file);
 	}
@@ -110,7 +110,7 @@ int perf_pmu__format_parse(int dirfd, struct list_head *head)
  * located at:
  * /sys/bus/event_source/devices/<dev>/format as sysfs group attributes.
  */
-static int pmu_format(int dirfd, const char *name, struct list_head *format)
+static int pmu_format(struct perf_pmu *pmu, int dirfd, const char *name)
 {
 	int fd;
 
@@ -119,7 +119,7 @@ static int pmu_format(int dirfd, const char *name, struct list_head *format)
 		return 0;
 
 	/* it'll close the fd */
-	if (perf_pmu__format_parse(fd, format))
+	if (perf_pmu__format_parse(pmu, fd))
 		return -1;
 
 	return 0;
@@ -508,7 +508,7 @@ static int pmu_aliases_parse(int dirfd, struct list_head *head)
  * Reading the pmu event aliases definition, which should be located at:
  * /sys/bus/event_source/devices/<dev>/events as sysfs group attributes.
  */
-static int pmu_aliases(int dirfd, const char *name, struct list_head *head)
+static int pmu_aliases(struct perf_pmu *pmu, int dirfd, const char *name)
 {
 	int fd;
 
@@ -517,7 +517,7 @@ static int pmu_aliases(int dirfd, const char *name, struct list_head *head)
 		return 0;
 
 	/* it'll close the fd */
-	if (pmu_aliases_parse(fd, head))
+	if (pmu_aliases_parse(fd, &pmu->aliases))
 		return -1;
 
 	return 0;
@@ -770,11 +770,10 @@ static int pmu_add_cpu_aliases_map_callback(const struct pmu_event *pe,
  * From the pmu_events_table, find the events that correspond to the given
  * PMU and add them to the list 'head'.
  */
-void pmu_add_cpu_aliases_table(struct list_head *head, struct perf_pmu *pmu,
-			const struct pmu_events_table *table)
+void pmu_add_cpu_aliases_table(struct perf_pmu *pmu, const struct pmu_events_table *table)
 {
 	struct pmu_add_cpu_aliases_map_data data = {
-		.head = head,
+		.head = &pmu->aliases,
 		.default_pmu_name = perf_pmus__default_pmu_name(),
 		.pmu = pmu,
 	};
@@ -783,7 +782,7 @@ void pmu_add_cpu_aliases_table(struct list_head *head, struct perf_pmu *pmu,
 	free(data.default_pmu_name);
 }
 
-static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
+static void pmu_add_cpu_aliases(struct perf_pmu *pmu)
 {
 	const struct pmu_events_table *table;
 
@@ -791,7 +790,7 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
 	if (!table)
 		return;
 
-	pmu_add_cpu_aliases_table(head, pmu, table);
+	pmu_add_cpu_aliases_table(pmu, table);
 }
 
 struct pmu_sys_event_iter_data {
@@ -821,10 +820,10 @@ static int pmu_add_sys_aliases_iter_fn(const struct pmu_event *pe,
 	return 0;
 }
 
-void pmu_add_sys_aliases(struct list_head *head, struct perf_pmu *pmu)
+void pmu_add_sys_aliases(struct perf_pmu *pmu)
 {
 	struct pmu_sys_event_iter_data idata = {
-		.head = head,
+		.head = &pmu->aliases,
 		.pmu = pmu,
 	};
 
@@ -863,30 +862,33 @@ static int pmu_max_precise(int dirfd, struct perf_pmu *pmu)
 struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *lookup_name)
 {
 	struct perf_pmu *pmu;
-	LIST_HEAD(format);
-	LIST_HEAD(aliases);
 	__u32 type;
 	char *name = pmu_find_real_name(lookup_name);
 	char *alias_name;
 
-	/*
-	 * The pmu data we store & need consists of the pmu
-	 * type value and format definitions. Load both right
-	 * now.
-	 */
-	if (pmu_format(dirfd, name, &format))
-		return NULL;
-
-	/*
-	 * Check the aliases first to avoid unnecessary work.
-	 */
-	if (pmu_aliases(dirfd, name, &aliases))
-		return NULL;
-
 	pmu = zalloc(sizeof(*pmu));
 	if (!pmu)
 		return NULL;
 
+	INIT_LIST_HEAD(&pmu->format);
+	INIT_LIST_HEAD(&pmu->aliases);
+	INIT_LIST_HEAD(&pmu->caps);
+	/*
+	 * The pmu data we store & need consists of the pmu
+	 * type value and format definitions. Load both right
+	 * now.
+	 */
+	if (pmu_format(pmu, dirfd, name)) {
+		free(pmu);
+		return NULL;
+	}
+	/*
+	 * Check the aliases first to avoid unnecessary work.
+	 */
+	if (pmu_aliases(pmu, dirfd, name)) {
+		free(pmu);
+		return NULL;
+	}
 	pmu->is_core = is_pmu_core(name);
 	pmu->cpus = pmu_cpumask(dirfd, name, pmu->is_core);
 	pmu->name = strdup(name);
@@ -909,14 +911,8 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char
 	if (pmu->is_uncore)
 		pmu->id = pmu_id(name);
 	pmu->max_precise = pmu_max_precise(dirfd, pmu);
-	pmu_add_cpu_aliases(&aliases, pmu);
-	pmu_add_sys_aliases(&aliases, pmu);
-
-	INIT_LIST_HEAD(&pmu->format);
-	INIT_LIST_HEAD(&pmu->aliases);
-	INIT_LIST_HEAD(&pmu->caps);
-	list_splice(&format, &pmu->format);
-	list_splice(&aliases, &pmu->aliases);
+	pmu_add_cpu_aliases(pmu);
+	pmu_add_sys_aliases(pmu);
 	list_add_tail(&pmu->list, pmus);
 
 	pmu->default_config = perf_pmu__get_default_config(pmu);
@@ -1397,6 +1393,17 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 	return 0;
 }
 
+struct perf_pmu_alias *perf_pmu__find_alias(struct perf_pmu *pmu, const char *event)
+{
+	struct perf_pmu_alias *alias;
+
+	list_for_each_entry(alias, &pmu->aliases, list)
+		if (!strcmp(event, alias->name))
+			return alias;
+
+	return NULL;
+}
+
 int perf_pmu__new_format(struct list_head *list, char *name,
 			 int config, unsigned long *bits)
 {
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 1249fca02ffd..c4268053c979 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -213,7 +213,7 @@ struct perf_pmu_alias {
 	char *pmu_name;
 };
 
-void pmu_add_sys_aliases(struct list_head *head, struct perf_pmu *pmu);
+void pmu_add_sys_aliases(struct perf_pmu *pmu);
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 		     struct list_head *head_terms,
 		     struct parse_events_error *error);
@@ -225,12 +225,11 @@ __u64 perf_pmu__format_bits(struct perf_pmu *pmu, const char *name);
 int perf_pmu__format_type(struct perf_pmu *pmu, const char *name);
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 			  struct perf_pmu_info *info);
-struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
-				  struct list_head *head_terms);
+struct perf_pmu_alias *perf_pmu__find_alias(struct perf_pmu *pmu, const char *event);
 
 int perf_pmu__new_format(struct list_head *list, char *name,
 			 int config, unsigned long *bits);
-int perf_pmu__format_parse(int dirfd, struct list_head *head);
+int perf_pmu__format_parse(struct perf_pmu *pmu, int dirfd);
 bool perf_pmu__has_format(const struct perf_pmu *pmu, const char *name);
 
 bool is_pmu_core(const char *name);
@@ -255,7 +254,7 @@ bool perf_pmu__file_exists(struct perf_pmu *pmu, const char *name);
 int perf_pmu__test(void);
 
 struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu);
-void pmu_add_cpu_aliases_table(struct list_head *head, struct perf_pmu *pmu,
+void pmu_add_cpu_aliases_table(struct perf_pmu *pmu,
 			       const struct pmu_events_table *table);
 
 char *perf_pmu__getcpuid(struct perf_pmu *pmu);

From 9e1f16939b3ea08e6685ecd1f6d9fe5d8c7c7a48 Mon Sep 17 00:00:00 2001
From: Guilherme Amadio <amadio@gentoo.org>
Date: Mon, 29 May 2023 19:56:04 +0200
Subject: [PATCH 0618/1189] perf build: Allow customization of clang options
 for BPF target

This also puts an unconditional -Werror under control of WERROR. The
clang includes added during the build can lead to a warning that may be
turned into an error. In addition, hardened clang produces a warning
about lack of support for -fstack-protector* options for the BPF target:

  clang -g -O2 -target bpf -Wall -Werror -Ilinux/tools/perf/util/bpf_skel/.tmp/.. \
    -I -idirafter /usr/lib/llvm/16/bin/../../../../lib/clang/16/include -idirafter /usr/local/include \
    -idirafter /usr/include  -Ilinux/tools/include/uapi -c util/bpf_skel/bperf_follower.bpf.c \
    -o linux/tools/perf/util/bpf_skel/.tmp/bperf_follower.bpf.o && llvm-strip -g linux/tools/perf/util/bpf_skel/.tmp/bperf_follower.bpf.o
  clang-16: error: /usr/lib/llvm/16/bin/../../../../lib/clang/16/include: 'linker' input unused [-Werror,-Wunused-command-line-argument]
  clang-16: error: ignoring '-fstack-protector-strong' option as it is not currently supported for target 'bpf' [-Werror,-Woption-ignored]
  make[1]: *** [Makefile.perf:1082: linux/tools/perf/util/bpf_skel/.tmp/bpf_prog_profiler.bpf.o] Error 1

Signed-off-by: Guilherme Amadio <amadio@gentoo.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/ZOZQ2LDA+3Wg8x2T@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Makefile.perf | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index a5dd1ba0fb5f..37af6df7b978 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -1056,10 +1056,15 @@ ifneq ($(CROSS_COMPILE),)
 CLANG_TARGET_ARCH = --target=$(notdir $(CROSS_COMPILE:%-=%))
 endif
 
+CLANG_OPTIONS = -Wall
 CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH))
 BPF_INCLUDE := -I$(SKEL_TMP_OUT)/.. -I$(LIBBPF_INCLUDE) $(CLANG_SYS_INCLUDES)
 TOOLS_UAPI_INCLUDE := -I$(srctree)/tools/include/uapi
 
+ifneq ($(WERROR),0)
+  CLANG_OPTIONS += -Werror
+endif
+
 $(BPFTOOL): | $(SKEL_TMP_OUT)
 	$(Q)CFLAGS= $(MAKE) -C ../bpf/bpftool \
 		OUTPUT=$(SKEL_TMP_OUT)/ bootstrap
@@ -1101,7 +1106,7 @@ else
 endif
 
 $(SKEL_TMP_OUT)/%.bpf.o: util/bpf_skel/%.bpf.c $(LIBBPF) $(SKEL_OUT)/vmlinux.h | $(SKEL_TMP_OUT)
-	$(QUIET_CLANG)$(CLANG) -g -O2 --target=bpf -Wall -Werror $(BPF_INCLUDE) $(TOOLS_UAPI_INCLUDE) \
+	$(QUIET_CLANG)$(CLANG) -g -O2 --target=bpf $(CLANG_OPTIONS) $(BPF_INCLUDE) $(TOOLS_UAPI_INCLUDE) \
 	  -c $(filter util/bpf_skel/%.bpf.c,$^) -o $@
 
 $(SKEL_OUT)/%.skel.h: $(SKEL_TMP_OUT)/%.bpf.o | $(BPFTOOL)

From 9b80b9676be901eb980c48543a19d7026d2f84b8 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 23 Aug 2023 10:14:48 +0100
Subject: [PATCH 0619/1189] KVM: arm64: pmu: Guard PMU emulation definitions
 with CONFIG_KVM

Most of the internal definitions for PMU emulation are guarded with
CONFIG_HW_PERF_EVENTS. However, this isn't enough, and leads to
these definitions leaking if CONFIG_KVM isn't enabled.

This leads to some compilation breakage in this exact configuration.
Fix it by falling back to the dummy stubs if either perf or KVM
isn't selected.

Reported-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Tested-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 include/kvm/arm_pmu.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 3a8a70a60794..31029f4f7be8 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -12,7 +12,7 @@
 
 #define ARMV8_PMU_CYCLE_IDX		(ARMV8_PMU_MAX_COUNTERS - 1)
 
-#ifdef CONFIG_HW_PERF_EVENTS
+#if IS_ENABLED(CONFIG_HW_PERF_EVENTS) && IS_ENABLED(CONFIG_KVM)
 
 struct kvm_pmc {
 	u8 idx;	/* index into the pmu->pmc array */

From c948a0a2f5dc729411a6cfbe0348c0aac5d8a07a Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Mon, 21 Aug 2023 18:44:15 +0100
Subject: [PATCH 0620/1189] KVM: arm64: nv: Add trap description for SPSR_EL2
 and ELR_EL2

Having carved a hole for SP_EL1, we are now missing the entries
for SPSR_EL2 and ELR_EL2. Add them back.

Reported-by: Miguel Luis <miguel.luis@oracle.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/emulate-nested.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index 1cc606c16416..9ced1bf0c2b7 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -651,6 +651,8 @@ static const struct encoding_to_trap_config encoding_to_cgt[] __initconst = {
 	SR_RANGE_TRAP(sys_reg(3, 4, 0, 0, 0),
 		      sys_reg(3, 4, 3, 15, 7), CGT_HCR_NV),
 	/* Skip the SP_EL1 encoding... */
+	SR_TRAP(SYS_SPSR_EL2,		CGT_HCR_NV),
+	SR_TRAP(SYS_ELR_EL2,		CGT_HCR_NV),
 	SR_RANGE_TRAP(sys_reg(3, 4, 4, 1, 1),
 		      sys_reg(3, 4, 10, 15, 7), CGT_HCR_NV),
 	SR_RANGE_TRAP(sys_reg(3, 4, 12, 0, 0),

From 3fd945a79e147ee10f84213976889b29049c3519 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Fri, 7 Aug 2020 09:28:31 -0400
Subject: [PATCH 0621/1189] ceph: encode encrypted name in ceph_mdsc_build_path
 and dentry release
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Allow ceph_mdsc_build_path to encrypt and base64 encode the filename
when the parent is encrypted and we're sending the path to the MDS. In
a similar fashion, encode encrypted dentry names if including a dentry
release in a request.

In most cases, we just encrypt the filenames and base64 encode them,
but when the name is longer than CEPH_NOHASH_NAME_MAX, we use a similar
scheme to fscrypt proper, and hash the remaning bits with sha256.

When doing this, we then send along the full crypttext of the name in
the new alternate_name field of the MClientRequest. The MDS can then
send that along in readdir responses and traces.

[ idryomov: drop duplicate include reported by Abaci Robot ]

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/caps.c       |  32 ++++++++++++--
 fs/ceph/crypto.c     |  53 +++++++++++++++++++++++
 fs/ceph/crypto.h     |   9 ++++
 fs/ceph/mds_client.c | 101 ++++++++++++++++++++++++++++++++++---------
 fs/ceph/mds_client.h |   2 +-
 5 files changed, 172 insertions(+), 25 deletions(-)

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 1c62ef339bc6..4738be54dc73 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -4663,6 +4663,18 @@ int ceph_encode_inode_release(void **p, struct inode *inode,
 	return ret;
 }
 
+/**
+ * ceph_encode_dentry_release - encode a dentry release into an outgoing request
+ * @p: outgoing request buffer
+ * @dentry: dentry to release
+ * @dir: dir to release it from
+ * @mds: mds that we're speaking to
+ * @drop: caps being dropped
+ * @unless: unless we have these caps
+ *
+ * Encode a dentry release into an outgoing request buffer. Returns 1 if the
+ * thing was released, or a negative error code otherwise.
+ */
 int ceph_encode_dentry_release(void **p, struct dentry *dentry,
 			       struct inode *dir,
 			       int mds, int drop, int unless)
@@ -4695,13 +4707,25 @@ int ceph_encode_dentry_release(void **p, struct dentry *dentry,
 	if (ret && di->lease_session && di->lease_session->s_mds == mds) {
 		dout("encode_dentry_release %p mds%d seq %d\n",
 		     dentry, mds, (int)di->lease_seq);
-		rel->dname_len = cpu_to_le32(dentry->d_name.len);
-		memcpy(*p, dentry->d_name.name, dentry->d_name.len);
-		*p += dentry->d_name.len;
 		rel->dname_seq = cpu_to_le32(di->lease_seq);
 		__ceph_mdsc_drop_dentry_lease(dentry);
+		spin_unlock(&dentry->d_lock);
+		if (IS_ENCRYPTED(dir) && fscrypt_has_encryption_key(dir)) {
+			int ret2 = ceph_encode_encrypted_fname(dir, dentry, *p);
+
+			if (ret2 < 0)
+				return ret2;
+
+			rel->dname_len = cpu_to_le32(ret2);
+			*p += ret2;
+		} else {
+			rel->dname_len = cpu_to_le32(dentry->d_name.len);
+			memcpy(*p, dentry->d_name.name, dentry->d_name.len);
+			*p += dentry->d_name.len;
+		}
+	} else {
+		spin_unlock(&dentry->d_lock);
 	}
-	spin_unlock(&dentry->d_lock);
 	return ret;
 }
 
diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c
index 0bb4d8e9f3b0..6dc723e8d395 100644
--- a/fs/ceph/crypto.c
+++ b/fs/ceph/crypto.c
@@ -191,3 +191,56 @@ void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req,
 {
 	swap(req->r_fscrypt_auth, as->fscrypt_auth);
 }
+
+int ceph_encode_encrypted_fname(const struct inode *parent,
+				struct dentry *dentry, char *buf)
+{
+	u32 len;
+	int elen;
+	int ret;
+	u8 *cryptbuf;
+
+	WARN_ON_ONCE(!fscrypt_has_encryption_key(parent));
+
+	/*
+	 * Convert cleartext d_name to ciphertext. If result is longer than
+	 * CEPH_NOHASH_NAME_MAX, sha256 the remaining bytes
+	 *
+	 * See: fscrypt_setup_filename
+	 */
+	if (!fscrypt_fname_encrypted_size(parent, dentry->d_name.len, NAME_MAX,
+					  &len))
+		return -ENAMETOOLONG;
+
+	/* Allocate a buffer appropriate to hold the result */
+	cryptbuf = kmalloc(len > CEPH_NOHASH_NAME_MAX ? NAME_MAX : len,
+			   GFP_KERNEL);
+	if (!cryptbuf)
+		return -ENOMEM;
+
+	ret = fscrypt_fname_encrypt(parent, &dentry->d_name, cryptbuf, len);
+	if (ret) {
+		kfree(cryptbuf);
+		return ret;
+	}
+
+	/* hash the end if the name is long enough */
+	if (len > CEPH_NOHASH_NAME_MAX) {
+		u8 hash[SHA256_DIGEST_SIZE];
+		u8 *extra = cryptbuf + CEPH_NOHASH_NAME_MAX;
+
+		/*
+		 * hash the extra bytes and overwrite crypttext beyond that
+		 * point with it
+		 */
+		sha256(extra, len - CEPH_NOHASH_NAME_MAX, hash);
+		memcpy(extra, hash, SHA256_DIGEST_SIZE);
+		len = CEPH_NOHASH_NAME_MAX + SHA256_DIGEST_SIZE;
+	}
+
+	/* base64 encode the encrypted name */
+	elen = ceph_base64_encode(cryptbuf, len, buf);
+	kfree(cryptbuf);
+	dout("base64-encoded ciphertext name = %.*s\n", elen, buf);
+	return elen;
+}
diff --git a/fs/ceph/crypto.h b/fs/ceph/crypto.h
index 44eb3f9f8287..176731f64997 100644
--- a/fs/ceph/crypto.h
+++ b/fs/ceph/crypto.h
@@ -6,6 +6,7 @@
 #ifndef _CEPH_CRYPTO_H
 #define _CEPH_CRYPTO_H
 
+#include <crypto/sha2.h>
 #include <linux/fscrypt.h>
 
 struct ceph_fs_client;
@@ -67,6 +68,8 @@ int ceph_fscrypt_prepare_context(struct inode *dir, struct inode *inode,
 				 struct ceph_acl_sec_ctx *as);
 void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req,
 				struct ceph_acl_sec_ctx *as);
+int ceph_encode_encrypted_fname(const struct inode *parent,
+				struct dentry *dentry, char *buf);
 
 #else /* CONFIG_FS_ENCRYPTION */
 
@@ -91,6 +94,12 @@ static inline void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req,
 						struct ceph_acl_sec_ctx *as_ctx)
 {
 }
+
+static inline int ceph_encode_encrypted_fname(const struct inode *parent,
+					      struct dentry *dentry, char *buf)
+{
+	return -EOPNOTSUPP;
+}
 #endif /* CONFIG_FS_ENCRYPTION */
 
 #endif
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index c3927dab5a3b..882c01a64498 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2435,18 +2435,29 @@ static inline  u64 __get_oldest_tid(struct ceph_mds_client *mdsc)
 	return mdsc->oldest_tid;
 }
 
-/*
- * Build a dentry's path.  Allocate on heap; caller must kfree.  Based
- * on build_path_from_dentry in fs/cifs/dir.c.
+/**
+ * ceph_mdsc_build_path - build a path string to a given dentry
+ * @dentry: dentry to which path should be built
+ * @plen: returned length of string
+ * @pbase: returned base inode number
+ * @for_wire: is this path going to be sent to the MDS?
  *
- * If @stop_on_nosnap, generate path relative to the first non-snapped
- * inode.
+ * Build a string that represents the path to the dentry. This is mostly called
+ * for two different purposes:
+ *
+ * 1) we need to build a path string to send to the MDS (for_wire == true)
+ * 2) we need a path string for local presentation (e.g. debugfs)
+ *    (for_wire == false)
+ *
+ * The path is built in reverse, starting with the dentry. Walk back up toward
+ * the root, building the path until the first non-snapped inode is reached
+ * (for_wire) or the root inode is reached (!for_wire).
  *
  * Encode hidden .snap dirs as a double /, i.e.
  *   foo/.snap/bar -> foo//bar
  */
 char *ceph_mdsc_build_path(struct dentry *dentry, int *plen, u64 *pbase,
-			   int stop_on_nosnap)
+			   int for_wire)
 {
 	struct dentry *cur;
 	struct inode *inode;
@@ -2468,30 +2479,67 @@ retry:
 	seq = read_seqbegin(&rename_lock);
 	cur = dget(dentry);
 	for (;;) {
-		struct dentry *temp;
+		struct dentry *parent;
 
 		spin_lock(&cur->d_lock);
 		inode = d_inode(cur);
 		if (inode && ceph_snap(inode) == CEPH_SNAPDIR) {
 			dout("build_path path+%d: %p SNAPDIR\n",
 			     pos, cur);
-		} else if (stop_on_nosnap && inode && dentry != cur &&
+			spin_unlock(&cur->d_lock);
+			parent = dget_parent(cur);
+		} else if (for_wire && inode && dentry != cur &&
 			   ceph_snap(inode) == CEPH_NOSNAP) {
 			spin_unlock(&cur->d_lock);
 			pos++; /* get rid of any prepended '/' */
 			break;
-		} else {
+		} else if (!for_wire || !IS_ENCRYPTED(d_inode(cur->d_parent))) {
 			pos -= cur->d_name.len;
 			if (pos < 0) {
 				spin_unlock(&cur->d_lock);
 				break;
 			}
 			memcpy(path + pos, cur->d_name.name, cur->d_name.len);
+			spin_unlock(&cur->d_lock);
+			parent = dget_parent(cur);
+		} else {
+			int len, ret;
+			char buf[NAME_MAX];
+
+			/*
+			 * Proactively copy name into buf, in case we need to
+			 * present it as-is.
+			 */
+			memcpy(buf, cur->d_name.name, cur->d_name.len);
+			len = cur->d_name.len;
+			spin_unlock(&cur->d_lock);
+			parent = dget_parent(cur);
+
+			ret = __fscrypt_prepare_readdir(d_inode(parent));
+			if (ret < 0) {
+				dput(parent);
+				dput(cur);
+				return ERR_PTR(ret);
+			}
+
+			if (fscrypt_has_encryption_key(d_inode(parent))) {
+				len = ceph_encode_encrypted_fname(d_inode(parent),
+								  cur, buf);
+				if (len < 0) {
+					dput(parent);
+					dput(cur);
+					return ERR_PTR(len);
+				}
+			}
+			pos -= len;
+			if (pos < 0) {
+				dput(parent);
+				break;
+			}
+			memcpy(path + pos, buf, len);
 		}
-		temp = cur;
-		spin_unlock(&temp->d_lock);
-		cur = dget_parent(temp);
-		dput(temp);
+		dput(cur);
+		cur = parent;
 
 		/* Are we at the root? */
 		if (IS_ROOT(cur))
@@ -2515,8 +2563,8 @@ retry:
 		 * A rename didn't occur, but somehow we didn't end up where
 		 * we thought we would. Throw a warning and try again.
 		 */
-		pr_warn("build_path did not end path lookup where "
-			"expected, pos is %d\n", pos);
+		pr_warn("build_path did not end path lookup where expected (pos = %d)\n",
+			pos);
 		goto retry;
 	}
 
@@ -2536,7 +2584,8 @@ static int build_dentry_path(struct dentry *dentry, struct inode *dir,
 	rcu_read_lock();
 	if (!dir)
 		dir = d_inode_rcu(dentry->d_parent);
-	if (dir && parent_locked && ceph_snap(dir) == CEPH_NOSNAP) {
+	if (dir && parent_locked && ceph_snap(dir) == CEPH_NOSNAP &&
+	    !IS_ENCRYPTED(dir)) {
 		*pino = ceph_ino(dir);
 		rcu_read_unlock();
 		*ppath = dentry->d_name.name;
@@ -2765,15 +2814,23 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 		      req->r_inode ? req->r_inode : d_inode(req->r_dentry),
 		      mds, req->r_inode_drop, req->r_inode_unless,
 		      req->r_op == CEPH_MDS_OP_READDIR);
-	if (req->r_dentry_drop)
-		releases += ceph_encode_dentry_release(&p, req->r_dentry,
+	if (req->r_dentry_drop) {
+		ret = ceph_encode_dentry_release(&p, req->r_dentry,
 				req->r_parent, mds, req->r_dentry_drop,
 				req->r_dentry_unless);
-	if (req->r_old_dentry_drop)
-		releases += ceph_encode_dentry_release(&p, req->r_old_dentry,
+		if (ret < 0)
+			goto out_err;
+		releases += ret;
+	}
+	if (req->r_old_dentry_drop) {
+		ret = ceph_encode_dentry_release(&p, req->r_old_dentry,
 				req->r_old_dentry_dir, mds,
 				req->r_old_dentry_drop,
 				req->r_old_dentry_unless);
+		if (ret < 0)
+			goto out_err;
+		releases += ret;
+	}
 	if (req->r_old_inode_drop)
 		releases += ceph_encode_inode_release(&p,
 		      d_inode(req->r_old_dentry),
@@ -2815,6 +2872,10 @@ out_free1:
 		ceph_mdsc_free_path((char *)path1, pathlen1);
 out:
 	return msg;
+out_err:
+	ceph_msg_put(msg);
+	msg = ERR_PTR(ret);
+	goto out_free2;
 }
 
 /*
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index a2e85fb5aab1..1105baa97d49 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -565,7 +565,7 @@ static inline void ceph_mdsc_free_path(char *path, int len)
 }
 
 extern char *ceph_mdsc_build_path(struct dentry *dentry, int *plen, u64 *base,
-				  int stop_on_nosnap);
+				  int for_wire);
 
 extern void __ceph_mdsc_drop_dentry_lease(struct dentry *dentry);
 extern void ceph_mdsc_lease_send_msg(struct ceph_mds_session *session,

From 24865e75c1a4e70ac9e8328dae8b5e03712a6e8c Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Thu, 14 Jan 2021 10:39:22 -0500
Subject: [PATCH 0622/1189] ceph: send alternate_name in MClientRequest
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In the event that we have a filename longer than CEPH_NOHASH_NAME_MAX,
we'll need to hash the tail of the filename. The client however will
still need to know the full name of the file if it has a key.

To support this, the MClientRequest field has grown a new alternate_name
field that we populate with the full (binary) crypttext of the filename.
This is then transmitted to the clients in readdir or traces as part of
the dentry lease.

Add support for populating this field when the filenames are very long.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c | 76 +++++++++++++++++++++++++++++++++++++++++---
 fs/ceph/mds_client.h |  3 ++
 2 files changed, 74 insertions(+), 5 deletions(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 882c01a64498..126529ec7ca9 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1027,6 +1027,7 @@ void ceph_mdsc_release_request(struct kref *kref)
 	if (req->r_pagelist)
 		ceph_pagelist_release(req->r_pagelist);
 	kfree(req->r_fscrypt_auth);
+	kfree(req->r_altname);
 	put_request_session(req);
 	ceph_unreserve_caps(req->r_mdsc, &req->r_caps_reservation);
 	WARN_ON_ONCE(!list_empty(&req->r_wait));
@@ -2435,6 +2436,64 @@ static inline  u64 __get_oldest_tid(struct ceph_mds_client *mdsc)
 	return mdsc->oldest_tid;
 }
 
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen)
+{
+	struct inode *dir = req->r_parent;
+	struct dentry *dentry = req->r_dentry;
+	u8 *cryptbuf = NULL;
+	u32 len = 0;
+	int ret = 0;
+
+	/* only encode if we have parent and dentry */
+	if (!dir || !dentry)
+		goto success;
+
+	/* No-op unless this is encrypted */
+	if (!IS_ENCRYPTED(dir))
+		goto success;
+
+	ret = __fscrypt_prepare_readdir(dir);
+	if (ret)
+		return ERR_PTR(ret);
+
+	/* No key? Just ignore it. */
+	if (!fscrypt_has_encryption_key(dir))
+		goto success;
+
+	if (!fscrypt_fname_encrypted_size(dir, dentry->d_name.len, NAME_MAX,
+					  &len)) {
+		WARN_ON_ONCE(1);
+		return ERR_PTR(-ENAMETOOLONG);
+	}
+
+	/* No need to append altname if name is short enough */
+	if (len <= CEPH_NOHASH_NAME_MAX) {
+		len = 0;
+		goto success;
+	}
+
+	cryptbuf = kmalloc(len, GFP_KERNEL);
+	if (!cryptbuf)
+		return ERR_PTR(-ENOMEM);
+
+	ret = fscrypt_fname_encrypt(dir, &dentry->d_name, cryptbuf, len);
+	if (ret) {
+		kfree(cryptbuf);
+		return ERR_PTR(ret);
+	}
+success:
+	*plen = len;
+	return cryptbuf;
+}
+#else
+static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen)
+{
+	*plen = 0;
+	return NULL;
+}
+#endif
+
 /**
  * ceph_mdsc_build_path - build a path string to a given dentry
  * @dentry: dentry to which path should be built
@@ -2662,14 +2721,15 @@ static void encode_mclientrequest_tail(void **p,
 	ceph_encode_timespec64(&ts, &req->r_stamp);
 	ceph_encode_copy(p, &ts, sizeof(ts));
 
-	/* gid_list */
+	/* v4: gid_list */
 	ceph_encode_32(p, req->r_cred->group_info->ngroups);
 	for (i = 0; i < req->r_cred->group_info->ngroups; i++)
 		ceph_encode_64(p, from_kgid(&init_user_ns,
 					    req->r_cred->group_info->gid[i]));
 
-	/* v5: altname (TODO: skip for now) */
-	ceph_encode_32(p, 0);
+	/* v5: altname */
+	ceph_encode_32(p, req->r_altname_len);
+	ceph_encode_copy(p, req->r_altname, req->r_altname_len);
 
 	/* v6: fscrypt_auth and fscrypt_file */
 	if (req->r_fscrypt_auth) {
@@ -2729,7 +2789,13 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 		goto out_free1;
 	}
 
-	/* head */
+	req->r_altname = get_fscrypt_altname(req, &req->r_altname_len);
+	if (IS_ERR(req->r_altname)) {
+		msg = ERR_CAST(req->r_altname);
+		req->r_altname = NULL;
+		goto out_free2;
+	}
+
 	len = legacy ? sizeof(*head) : sizeof(struct ceph_mds_request_head);
 
 	/* filepaths */
@@ -2755,7 +2821,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 	len += sizeof(u32) + (sizeof(u64) * req->r_cred->group_info->ngroups);
 
 	/* alternate name */
-	len += sizeof(u32);	// TODO
+	len += sizeof(u32) + req->r_altname_len;
 
 	/* fscrypt_auth */
 	len += sizeof(u32); // fscrypt_auth
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 1105baa97d49..3cf874925519 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -285,6 +285,9 @@ struct ceph_mds_request {
 
 	struct ceph_fscrypt_auth *r_fscrypt_auth;
 
+	u8 *r_altname;		    /* fscrypt binary crypttext for long filenames */
+	u32 r_altname_len;	    /* length of r_altname */
+
 	int r_fmode;        /* file mode, if expecting cap */
 	int r_request_release_offset;
 	const struct cred *r_cred;

From 4ac4c23eaa389859f746a6ef31e1c71d880312f4 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Mon, 11 Jan 2021 12:35:48 -0500
Subject: [PATCH 0623/1189] ceph: decode alternate_name in lease info
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Ceph is a bit different from local filesystems, in that we don't want
to store filenames as raw binary data, since we may also be dealing
with clients that don't support fscrypt.

We could just base64-encode the encrypted filenames, but that could
leave us with filenames longer than NAME_MAX. It turns out that the
MDS doesn't care much about filename length, but the clients do.

To manage this, we've added a new "alternate name" field that can be
optionally added to any dentry that we'll use to store the binary
crypttext of the filename if its base64-encoded value will be longer
than NAME_MAX. When a dentry has one of these names attached, the MDS
will send it along in the lease info, which we can then store for
later usage.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c | 43 +++++++++++++++++++++++++++++++++----------
 fs/ceph/mds_client.h |  5 +++++
 2 files changed, 38 insertions(+), 10 deletions(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 126529ec7ca9..34b8c0273427 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -310,27 +310,47 @@ bad:
 
 static int parse_reply_info_lease(void **p, void *end,
 				  struct ceph_mds_reply_lease **lease,
-				  u64 features)
+				  u64 features, u32 *altname_len, u8 **altname)
 {
+	u8 struct_v;
+	u32 struct_len;
+	void *lend;
+
 	if (features == (u64)-1) {
-		u8 struct_v, struct_compat;
-		u32 struct_len;
+		u8 struct_compat;
+
 		ceph_decode_8_safe(p, end, struct_v, bad);
 		ceph_decode_8_safe(p, end, struct_compat, bad);
+
 		/* struct_v is expected to be >= 1. we only understand
 		 * encoding whose struct_compat == 1. */
 		if (!struct_v || struct_compat != 1)
 			goto bad;
+
 		ceph_decode_32_safe(p, end, struct_len, bad);
-		ceph_decode_need(p, end, struct_len, bad);
-		end = *p + struct_len;
+	} else {
+		struct_len = sizeof(**lease);
+		*altname_len = 0;
+		*altname = NULL;
 	}
 
-	ceph_decode_need(p, end, sizeof(**lease), bad);
+	lend = *p + struct_len;
+	ceph_decode_need(p, end, struct_len, bad);
 	*lease = *p;
 	*p += sizeof(**lease);
-	if (features == (u64)-1)
-		*p = end;
+
+	if (features == (u64)-1) {
+		if (struct_v >= 2) {
+			ceph_decode_32_safe(p, end, *altname_len, bad);
+			ceph_decode_need(p, end, *altname_len, bad);
+			*altname = *p;
+			*p += *altname_len;
+		} else {
+			*altname = NULL;
+			*altname_len = 0;
+		}
+	}
+	*p = lend;
 	return 0;
 bad:
 	return -EIO;
@@ -360,7 +380,8 @@ static int parse_reply_info_trace(void **p, void *end,
 		info->dname = *p;
 		*p += info->dname_len;
 
-		err = parse_reply_info_lease(p, end, &info->dlease, features);
+		err = parse_reply_info_lease(p, end, &info->dlease, features,
+					     &info->altname_len, &info->altname);
 		if (err < 0)
 			goto out_bad;
 	}
@@ -427,9 +448,11 @@ static int parse_reply_info_readdir(void **p, void *end,
 		dout("parsed dir dname '%.*s'\n", rde->name_len, rde->name);
 
 		/* dentry lease */
-		err = parse_reply_info_lease(p, end, &rde->lease, features);
+		err = parse_reply_info_lease(p, end, &rde->lease, features,
+					     &rde->altname_len, &rde->altname);
 		if (err)
 			goto out_bad;
+
 		/* inode */
 		err = parse_reply_info_in(p, end, &rde->inode, features);
 		if (err < 0)
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 3cf874925519..a4a6f7893b9e 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -44,6 +44,7 @@ enum ceph_feature_type {
 	CEPHFS_FEATURE_MULTI_RECONNECT,		\
 	CEPHFS_FEATURE_DELEG_INO,		\
 	CEPHFS_FEATURE_METRIC_COLLECT,		\
+	CEPHFS_FEATURE_ALTERNATE_NAME,		\
 	CEPHFS_FEATURE_NOTIFY_SESSION_STATE,	\
 	CEPHFS_FEATURE_OP_GETVXATTR,		\
 }
@@ -96,7 +97,9 @@ struct ceph_mds_reply_info_in {
 
 struct ceph_mds_reply_dir_entry {
 	char                          *name;
+	u8			      *altname;
 	u32                           name_len;
+	u32			      altname_len;
 	struct ceph_mds_reply_lease   *lease;
 	struct ceph_mds_reply_info_in inode;
 	loff_t			      offset;
@@ -120,7 +123,9 @@ struct ceph_mds_reply_info_parsed {
 	struct ceph_mds_reply_info_in diri, targeti;
 	struct ceph_mds_reply_dirfrag *dirfrag;
 	char                          *dname;
+	u8			      *altname;
 	u32                           dname_len;
+	u32                           altname_len;
 	struct ceph_mds_reply_lease   *dlease;
 	struct ceph_mds_reply_xattr   xattr_info;
 

From cb3524a8bd96fbc614e0f9295866c28dc17cafe6 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Tue, 26 Jan 2021 14:12:24 -0500
Subject: [PATCH 0624/1189] ceph: set DCACHE_NOKEY_NAME flag in
 ceph_lookup/atomic_open()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This is required so that we know to invalidate these dentries when the
directory is unlocked.

Atomic open can act as a lookup if handed a dentry that is negative on
the MDS. Ensure that we set DCACHE_NOKEY_NAME on the dentry in
atomic_open, if we don't have the key for the parent. Otherwise, we can
end up validating the dentry inappropriately if someone later adds a
key.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/dir.c  | 11 +++++++++++
 fs/ceph/file.c |  7 +++++++
 2 files changed, 18 insertions(+)

diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 31fac215a6a0..cd2ca26e3159 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -760,6 +760,17 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
 	if (dentry->d_name.len > NAME_MAX)
 		return ERR_PTR(-ENAMETOOLONG);
 
+	if (IS_ENCRYPTED(dir)) {
+		err = __fscrypt_prepare_readdir(dir);
+		if (err)
+			return ERR_PTR(err);
+		if (!fscrypt_has_encryption_key(dir)) {
+			spin_lock(&dentry->d_lock);
+			dentry->d_flags |= DCACHE_NOKEY_NAME;
+			spin_unlock(&dentry->d_lock);
+		}
+	}
+
 	/* can we conclude ENOENT locally? */
 	if (d_really_is_negative(dentry)) {
 		struct ceph_inode_info *ci = ceph_inode(dir);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index dddced525b69..9383ec312a04 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -784,6 +784,13 @@ retry:
 	req->r_args.open.mask = cpu_to_le32(mask);
 	req->r_parent = dir;
 	ihold(dir);
+	if (IS_ENCRYPTED(dir)) {
+		if (!fscrypt_has_encryption_key(dir)) {
+			spin_lock(&dentry->d_lock);
+			dentry->d_flags |= DCACHE_NOKEY_NAME;
+			spin_unlock(&dentry->d_lock);
+		}
+	}
 
 	if (flags & O_CREAT) {
 		struct ceph_file_layout lo;

From c526760181ca083dbd607d2e694b43080a8b1585 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Fri, 7 Aug 2020 15:47:17 -0400
Subject: [PATCH 0625/1189] ceph: make d_revalidate call fscrypt revalidator
 for encrypted dentries
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If we have a dentry which represents a no-key name, then we need to test
whether the parent directory's encryption key has since been added.  Do
that before we test anything else about the dentry.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/dir.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index cd2ca26e3159..9a0342697595 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1782,6 +1782,10 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 	struct inode *dir, *inode;
 	struct ceph_mds_client *mdsc;
 
+	valid = fscrypt_d_revalidate(dentry, flags);
+	if (valid <= 0)
+		return valid;
+
 	if (flags & LOOKUP_RCU) {
 		parent = READ_ONCE(dentry->d_parent);
 		dir = d_inode_rcu(parent);
@@ -1794,8 +1798,9 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 		inode = d_inode(dentry);
 	}
 
-	dout("d_revalidate %p '%pd' inode %p offset 0x%llx\n", dentry,
-	     dentry, inode, ceph_dentry(dentry)->offset);
+	dout("d_revalidate %p '%pd' inode %p offset 0x%llx nokey %d\n", dentry,
+	     dentry, inode, ceph_dentry(dentry)->offset,
+	     !!(dentry->d_flags & DCACHE_NOKEY_NAME));
 
 	mdsc = ceph_sb_to_client(dir->i_sb)->mdsc;
 

From 457117f077c6749d1e28469eae91fb69c9806768 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Fri, 26 Mar 2021 12:26:18 -0400
Subject: [PATCH 0626/1189] ceph: add helpers for converting names for userland
 presentation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Define a new ceph_fname struct that we can use to carry information
about encrypted dentry names. Add helpers for working with these
objects, including ceph_fname_to_usr which formats an encrypted filename
for userland presentation.

[ xiubli: fix resulting name length check -- neither name_len nor
  ctext_len should exceed NAME_MAX ]

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/crypto.c | 77 ++++++++++++++++++++++++++++++++++++++++++++++++
 fs/ceph/crypto.h | 46 +++++++++++++++++++++++++++++
 2 files changed, 123 insertions(+)

diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c
index 6dc723e8d395..e2a461960955 100644
--- a/fs/ceph/crypto.c
+++ b/fs/ceph/crypto.c
@@ -244,3 +244,80 @@ int ceph_encode_encrypted_fname(const struct inode *parent,
 	dout("base64-encoded ciphertext name = %.*s\n", elen, buf);
 	return elen;
 }
+
+/**
+ * ceph_fname_to_usr - convert a filename for userland presentation
+ * @fname: ceph_fname to be converted
+ * @tname: temporary name buffer to use for conversion (may be NULL)
+ * @oname: where converted name should be placed
+ * @is_nokey: set to true if key wasn't available during conversion (may be NULL)
+ *
+ * Given a filename (usually from the MDS), format it for presentation to
+ * userland. If @parent is not encrypted, just pass it back as-is.
+ *
+ * Otherwise, base64 decode the string, and then ask fscrypt to format it
+ * for userland presentation.
+ *
+ * Returns 0 on success or negative error code on error.
+ */
+int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname,
+		      struct fscrypt_str *oname, bool *is_nokey)
+{
+	int ret;
+	struct fscrypt_str _tname = FSTR_INIT(NULL, 0);
+	struct fscrypt_str iname;
+
+	if (!IS_ENCRYPTED(fname->dir)) {
+		oname->name = fname->name;
+		oname->len = fname->name_len;
+		return 0;
+	}
+
+	/* Sanity check that the resulting name will fit in the buffer */
+	if (fname->name_len > NAME_MAX || fname->ctext_len > NAME_MAX)
+		return -EIO;
+
+	ret = __fscrypt_prepare_readdir(fname->dir);
+	if (ret)
+		return ret;
+
+	/*
+	 * Use the raw dentry name as sent by the MDS instead of
+	 * generating a nokey name via fscrypt.
+	 */
+	if (!fscrypt_has_encryption_key(fname->dir)) {
+		memcpy(oname->name, fname->name, fname->name_len);
+		oname->len = fname->name_len;
+		if (is_nokey)
+			*is_nokey = true;
+		return 0;
+	}
+
+	if (fname->ctext_len == 0) {
+		int declen;
+
+		if (!tname) {
+			ret = fscrypt_fname_alloc_buffer(NAME_MAX, &_tname);
+			if (ret)
+				return ret;
+			tname = &_tname;
+		}
+
+		declen = ceph_base64_decode(fname->name, fname->name_len,
+					    tname->name);
+		if (declen <= 0) {
+			ret = -EIO;
+			goto out;
+		}
+		iname.name = tname->name;
+		iname.len = declen;
+	} else {
+		iname.name = fname->ctext;
+		iname.len = fname->ctext_len;
+	}
+
+	ret = fscrypt_fname_disk_to_usr(fname->dir, 0, 0, &iname, oname);
+out:
+	fscrypt_fname_free_buffer(&_tname);
+	return ret;
+}
diff --git a/fs/ceph/crypto.h b/fs/ceph/crypto.h
index 176731f64997..a53645123248 100644
--- a/fs/ceph/crypto.h
+++ b/fs/ceph/crypto.h
@@ -13,6 +13,14 @@ struct ceph_fs_client;
 struct ceph_acl_sec_ctx;
 struct ceph_mds_request;
 
+struct ceph_fname {
+	struct inode	*dir;
+	char		*name;		// b64 encoded, possibly hashed
+	unsigned char	*ctext;		// binary crypttext (if any)
+	u32		name_len;	// length of name buffer
+	u32		ctext_len;	// length of crypttext
+};
+
 struct ceph_fscrypt_auth {
 	__le32	cfa_version;
 	__le32	cfa_blob_len;
@@ -71,6 +79,24 @@ void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req,
 int ceph_encode_encrypted_fname(const struct inode *parent,
 				struct dentry *dentry, char *buf);
 
+static inline int ceph_fname_alloc_buffer(struct inode *parent,
+					  struct fscrypt_str *fname)
+{
+	if (!IS_ENCRYPTED(parent))
+		return 0;
+	return fscrypt_fname_alloc_buffer(NAME_MAX, fname);
+}
+
+static inline void ceph_fname_free_buffer(struct inode *parent,
+					  struct fscrypt_str *fname)
+{
+	if (IS_ENCRYPTED(parent))
+		fscrypt_fname_free_buffer(fname);
+}
+
+int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname,
+		      struct fscrypt_str *oname, bool *is_nokey);
+
 #else /* CONFIG_FS_ENCRYPTION */
 
 static inline void ceph_fscrypt_set_ops(struct super_block *sb)
@@ -100,6 +126,26 @@ static inline int ceph_encode_encrypted_fname(const struct inode *parent,
 {
 	return -EOPNOTSUPP;
 }
+
+static inline int ceph_fname_alloc_buffer(struct inode *parent,
+					  struct fscrypt_str *fname)
+{
+	return 0;
+}
+
+static inline void ceph_fname_free_buffer(struct inode *parent,
+					  struct fscrypt_str *fname)
+{
+}
+
+static inline int ceph_fname_to_usr(const struct ceph_fname *fname,
+				    struct fscrypt_str *tname,
+				    struct fscrypt_str *oname, bool *is_nokey)
+{
+	oname->name = fname->name;
+	oname->len = fname->name_len;
+	return 0;
+}
 #endif /* CONFIG_FS_ENCRYPTION */
 
 #endif

From 855290962c5581289dcf5365894a87b911e4c4d5 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Mon, 10 Aug 2020 15:13:29 -0400
Subject: [PATCH 0627/1189] ceph: make ceph_fill_trace and ceph_get_name
 decrypt names
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When we get a dentry in a trace, decrypt the name so we can properly
instantiate the dentry or fill out ceph_get_name() buffer.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/export.c | 44 ++++++++++++++++++++++++++++++++------------
 fs/ceph/inode.c  | 30 ++++++++++++++++++++++++++++--
 2 files changed, 60 insertions(+), 14 deletions(-)

diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index f780e4e0d062..8559990a59a5 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -7,6 +7,7 @@
 
 #include "super.h"
 #include "mds_client.h"
+#include "crypto.h"
 
 /*
  * Basic fh
@@ -535,7 +536,9 @@ static int ceph_get_name(struct dentry *parent, char *name,
 {
 	struct ceph_mds_client *mdsc;
 	struct ceph_mds_request *req;
+	struct inode *dir = d_inode(parent);
 	struct inode *inode = d_inode(child);
+	struct ceph_mds_reply_info_parsed *rinfo;
 	int err;
 
 	if (ceph_snap(inode) != CEPH_NOSNAP)
@@ -547,30 +550,47 @@ static int ceph_get_name(struct dentry *parent, char *name,
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
-	inode_lock(d_inode(parent));
-
+	inode_lock(dir);
 	req->r_inode = inode;
 	ihold(inode);
 	req->r_ino2 = ceph_vino(d_inode(parent));
-	req->r_parent = d_inode(parent);
-	ihold(req->r_parent);
+	req->r_parent = dir;
+	ihold(dir);
 	set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
 	req->r_num_caps = 2;
 	err = ceph_mdsc_do_request(mdsc, NULL, req);
+	inode_unlock(dir);
 
-	inode_unlock(d_inode(parent));
+	if (err)
+		goto out;
 
-	if (!err) {
-		struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
+	rinfo = &req->r_reply_info;
+	if (!IS_ENCRYPTED(dir)) {
 		memcpy(name, rinfo->dname, rinfo->dname_len);
 		name[rinfo->dname_len] = 0;
-		dout("get_name %p ino %llx.%llx name %s\n",
-		     child, ceph_vinop(inode), name);
 	} else {
-		dout("get_name %p ino %llx.%llx err %d\n",
-		     child, ceph_vinop(inode), err);
-	}
+		struct fscrypt_str oname = FSTR_INIT(NULL, 0);
+		struct ceph_fname fname = { .dir	= dir,
+					    .name	= rinfo->dname,
+					    .ctext	= rinfo->altname,
+					    .name_len	= rinfo->dname_len,
+					    .ctext_len	= rinfo->altname_len };
 
+		err = ceph_fname_alloc_buffer(dir, &oname);
+		if (err < 0)
+			goto out;
+
+		err = ceph_fname_to_usr(&fname, NULL, &oname, NULL);
+		if (!err) {
+			memcpy(name, oname.name, oname.len);
+			name[oname.len] = 0;
+		}
+		ceph_fname_free_buffer(dir, &oname);
+	}
+out:
+	dout("get_name %p ino %llx.%llx err %d %s%s\n",
+		     child, ceph_vinop(inode), err,
+		     err ? "" : "name ", err ? "" : name);
 	ceph_mdsc_put_request(req);
 	return err;
 }
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 50ff641865e0..a6e9a41020d5 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1406,8 +1406,15 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
 		if (dir && req->r_op == CEPH_MDS_OP_LOOKUPNAME &&
 		    test_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags) &&
 		    !test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags)) {
+			bool is_nokey = false;
 			struct qstr dname;
 			struct dentry *dn, *parent;
+			struct fscrypt_str oname = FSTR_INIT(NULL, 0);
+			struct ceph_fname fname = { .dir	= dir,
+						    .name	= rinfo->dname,
+						    .ctext	= rinfo->altname,
+						    .name_len	= rinfo->dname_len,
+						    .ctext_len	= rinfo->altname_len };
 
 			BUG_ON(!rinfo->head->is_target);
 			BUG_ON(req->r_dentry);
@@ -1415,8 +1422,20 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
 			parent = d_find_any_alias(dir);
 			BUG_ON(!parent);
 
-			dname.name = rinfo->dname;
-			dname.len = rinfo->dname_len;
+			err = ceph_fname_alloc_buffer(dir, &oname);
+			if (err < 0) {
+				dput(parent);
+				goto done;
+			}
+
+			err = ceph_fname_to_usr(&fname, NULL, &oname, &is_nokey);
+			if (err < 0) {
+				dput(parent);
+				ceph_fname_free_buffer(dir, &oname);
+				goto done;
+			}
+			dname.name = oname.name;
+			dname.len = oname.len;
 			dname.hash = full_name_hash(parent, dname.name, dname.len);
 			tvino.ino = le64_to_cpu(rinfo->targeti.in->ino);
 			tvino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
@@ -1431,9 +1450,15 @@ retry_lookup:
 				     dname.len, dname.name, dn);
 				if (!dn) {
 					dput(parent);
+					ceph_fname_free_buffer(dir, &oname);
 					err = -ENOMEM;
 					goto done;
 				}
+				if (is_nokey) {
+					spin_lock(&dn->d_lock);
+					dn->d_flags |= DCACHE_NOKEY_NAME;
+					spin_unlock(&dn->d_lock);
+				}
 				err = 0;
 			} else if (d_really_is_positive(dn) &&
 				   (ceph_ino(d_inode(dn)) != tvino.ino ||
@@ -1445,6 +1470,7 @@ retry_lookup:
 				dput(dn);
 				goto retry_lookup;
 			}
+			ceph_fname_free_buffer(dir, &oname);
 
 			req->r_dentry = dn;
 			dput(parent);

From 3859af9eba958cec91e4908f64787f190254f565 Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Mon, 14 Mar 2022 10:28:34 +0800
Subject: [PATCH 0628/1189] ceph: pass the request to
 parse_reply_info_readdir()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Instead of passing just the r_reply_info to the readdir reply parser,
pass the request pointer directly instead. This will facilitate
implementing readdir on fscrypted directories.

Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c | 23 +++++++++++++----------
 1 file changed, 13 insertions(+), 10 deletions(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 34b8c0273427..8709fc1b2523 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -407,9 +407,10 @@ out_bad:
  * parse readdir results
  */
 static int parse_reply_info_readdir(void **p, void *end,
-				struct ceph_mds_reply_info_parsed *info,
-				u64 features)
+				    struct ceph_mds_request *req,
+				    u64 features)
 {
+	struct ceph_mds_reply_info_parsed *info = &req->r_reply_info;
 	u32 num, i = 0;
 	int err;
 
@@ -651,15 +652,16 @@ bad:
  * parse extra results
  */
 static int parse_reply_info_extra(void **p, void *end,
-				  struct ceph_mds_reply_info_parsed *info,
+				  struct ceph_mds_request *req,
 				  u64 features, struct ceph_mds_session *s)
 {
+	struct ceph_mds_reply_info_parsed *info = &req->r_reply_info;
 	u32 op = le32_to_cpu(info->head->op);
 
 	if (op == CEPH_MDS_OP_GETFILELOCK)
 		return parse_reply_info_filelock(p, end, info, features);
 	else if (op == CEPH_MDS_OP_READDIR || op == CEPH_MDS_OP_LSSNAP)
-		return parse_reply_info_readdir(p, end, info, features);
+		return parse_reply_info_readdir(p, end, req, features);
 	else if (op == CEPH_MDS_OP_CREATE)
 		return parse_reply_info_create(p, end, info, features, s);
 	else if (op == CEPH_MDS_OP_GETVXATTR)
@@ -672,9 +674,9 @@ static int parse_reply_info_extra(void **p, void *end,
  * parse entire mds reply
  */
 static int parse_reply_info(struct ceph_mds_session *s, struct ceph_msg *msg,
-			    struct ceph_mds_reply_info_parsed *info,
-			    u64 features)
+			    struct ceph_mds_request *req, u64 features)
 {
+	struct ceph_mds_reply_info_parsed *info = &req->r_reply_info;
 	void *p, *end;
 	u32 len;
 	int err;
@@ -696,7 +698,7 @@ static int parse_reply_info(struct ceph_mds_session *s, struct ceph_msg *msg,
 	ceph_decode_32_safe(&p, end, len, bad);
 	if (len > 0) {
 		ceph_decode_need(&p, end, len, bad);
-		err = parse_reply_info_extra(&p, p+len, info, features, s);
+		err = parse_reply_info_extra(&p, p+len, req, features, s);
 		if (err < 0)
 			goto out_bad;
 	}
@@ -3598,14 +3600,15 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 	}
 
 	dout("handle_reply tid %lld result %d\n", tid, result);
-	rinfo = &req->r_reply_info;
 	if (test_bit(CEPHFS_FEATURE_REPLY_ENCODING, &session->s_features))
-		err = parse_reply_info(session, msg, rinfo, (u64)-1);
+		err = parse_reply_info(session, msg, req, (u64)-1);
 	else
-		err = parse_reply_info(session, msg, rinfo, session->s_con.peer_features);
+		err = parse_reply_info(session, msg, req,
+				       session->s_con.peer_features);
 	mutex_unlock(&mdsc->mutex);
 
 	/* Must find target inode outside of mutexes to avoid deadlocks */
+	rinfo = &req->r_reply_info;
 	if ((err >= 0) && rinfo->head->is_target) {
 		struct inode *in = xchg(&req->r_new_inode, NULL);
 		struct ceph_vino tvino = {

From af9ffa6df7e337599ce41165d9e6166a330c7b96 Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Mon, 14 Mar 2022 10:28:35 +0800
Subject: [PATCH 0629/1189] ceph: add support to readdir for encrypted names
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To make it simpler to decrypt names in a readdir reply (i.e. before
we have a dentry), add a new ceph_encode_encrypted_fname()-like helper
that takes a qstr pointer instead of a dentry pointer.

Once we've decrypted the names in a readdir reply, we no longer need the
crypttext, so overwrite them in ceph_mds_reply_dir_entry with the
unencrypted names. Then in both ceph_readdir_prepopulate() and
ceph_readdir() we will use the dencrypted name directly.

[ jlayton: convert some BUG_ONs into error returns ]

Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/crypto.c     | 27 +++++++++++----
 fs/ceph/crypto.h     | 10 ++++++
 fs/ceph/dir.c        | 36 ++++++++++++++++----
 fs/ceph/inode.c      | 12 ++++---
 fs/ceph/mds_client.c | 81 ++++++++++++++++++++++++++++++++++++++++----
 fs/ceph/mds_client.h |  4 +--
 6 files changed, 144 insertions(+), 26 deletions(-)

diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c
index e2a461960955..a08978a0ed4d 100644
--- a/fs/ceph/crypto.c
+++ b/fs/ceph/crypto.c
@@ -192,15 +192,18 @@ void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req,
 	swap(req->r_fscrypt_auth, as->fscrypt_auth);
 }
 
-int ceph_encode_encrypted_fname(const struct inode *parent,
-				struct dentry *dentry, char *buf)
+int ceph_encode_encrypted_dname(const struct inode *parent,
+				struct qstr *d_name, char *buf)
 {
 	u32 len;
 	int elen;
 	int ret;
 	u8 *cryptbuf;
 
-	WARN_ON_ONCE(!fscrypt_has_encryption_key(parent));
+	if (!fscrypt_has_encryption_key(parent)) {
+		memcpy(buf, d_name->name, d_name->len);
+		return d_name->len;
+	}
 
 	/*
 	 * Convert cleartext d_name to ciphertext. If result is longer than
@@ -208,8 +211,7 @@ int ceph_encode_encrypted_fname(const struct inode *parent,
 	 *
 	 * See: fscrypt_setup_filename
 	 */
-	if (!fscrypt_fname_encrypted_size(parent, dentry->d_name.len, NAME_MAX,
-					  &len))
+	if (!fscrypt_fname_encrypted_size(parent, d_name->len, NAME_MAX, &len))
 		return -ENAMETOOLONG;
 
 	/* Allocate a buffer appropriate to hold the result */
@@ -218,7 +220,7 @@ int ceph_encode_encrypted_fname(const struct inode *parent,
 	if (!cryptbuf)
 		return -ENOMEM;
 
-	ret = fscrypt_fname_encrypt(parent, &dentry->d_name, cryptbuf, len);
+	ret = fscrypt_fname_encrypt(parent, d_name, cryptbuf, len);
 	if (ret) {
 		kfree(cryptbuf);
 		return ret;
@@ -245,6 +247,14 @@ int ceph_encode_encrypted_fname(const struct inode *parent,
 	return elen;
 }
 
+int ceph_encode_encrypted_fname(const struct inode *parent,
+				struct dentry *dentry, char *buf)
+{
+	WARN_ON_ONCE(!fscrypt_has_encryption_key(parent));
+
+	return ceph_encode_encrypted_dname(parent, &dentry->d_name, buf);
+}
+
 /**
  * ceph_fname_to_usr - convert a filename for userland presentation
  * @fname: ceph_fname to be converted
@@ -286,7 +296,10 @@ int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname,
 	 * generating a nokey name via fscrypt.
 	 */
 	if (!fscrypt_has_encryption_key(fname->dir)) {
-		memcpy(oname->name, fname->name, fname->name_len);
+		if (fname->no_copy)
+			oname->name = fname->name;
+		else
+			memcpy(oname->name, fname->name, fname->name_len);
 		oname->len = fname->name_len;
 		if (is_nokey)
 			*is_nokey = true;
diff --git a/fs/ceph/crypto.h b/fs/ceph/crypto.h
index a53645123248..3269fc8f8cf3 100644
--- a/fs/ceph/crypto.h
+++ b/fs/ceph/crypto.h
@@ -19,6 +19,7 @@ struct ceph_fname {
 	unsigned char	*ctext;		// binary crypttext (if any)
 	u32		name_len;	// length of name buffer
 	u32		ctext_len;	// length of crypttext
+	bool		no_copy;
 };
 
 struct ceph_fscrypt_auth {
@@ -76,6 +77,8 @@ int ceph_fscrypt_prepare_context(struct inode *dir, struct inode *inode,
 				 struct ceph_acl_sec_ctx *as);
 void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req,
 				struct ceph_acl_sec_ctx *as);
+int ceph_encode_encrypted_dname(const struct inode *parent,
+				struct qstr *d_name, char *buf);
 int ceph_encode_encrypted_fname(const struct inode *parent,
 				struct dentry *dentry, char *buf);
 
@@ -121,6 +124,13 @@ static inline void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req,
 {
 }
 
+static inline int ceph_encode_encrypted_dname(const struct inode *parent,
+					      struct qstr *d_name, char *buf)
+{
+	memcpy(buf, d_name->name, d_name->len);
+	return d_name->len;
+}
+
 static inline int ceph_encode_encrypted_fname(const struct inode *parent,
 					      struct dentry *dentry, char *buf)
 {
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 9a0342697595..ee5c8b9c8630 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -9,6 +9,7 @@
 
 #include "super.h"
 #include "mds_client.h"
+#include "crypto.h"
 
 /*
  * Directory operations: readdir, lookup, create, link, unlink,
@@ -241,7 +242,9 @@ static int __dcache_readdir(struct file *file,  struct dir_context *ctx,
 		di = ceph_dentry(dentry);
 		if (d_unhashed(dentry) ||
 		    d_really_is_negative(dentry) ||
-		    di->lease_shared_gen != shared_gen) {
+		    di->lease_shared_gen != shared_gen ||
+		    ((dentry->d_flags & DCACHE_NOKEY_NAME) &&
+		     fscrypt_has_encryption_key(dir))) {
 			spin_unlock(&dentry->d_lock);
 			dput(dentry);
 			err = -EAGAIN;
@@ -340,6 +343,10 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 		ctx->pos = 2;
 	}
 
+	err = fscrypt_prepare_readdir(inode);
+	if (err)
+		return err;
+
 	spin_lock(&ci->i_ceph_lock);
 	/* request Fx cap. if have Fx, we don't need to release Fs cap
 	 * for later create/unlink. */
@@ -389,6 +396,7 @@ more:
 		req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
 		if (IS_ERR(req))
 			return PTR_ERR(req);
+
 		err = ceph_alloc_readdir_reply_buffer(req, inode);
 		if (err) {
 			ceph_mdsc_put_request(req);
@@ -402,11 +410,21 @@ more:
 			req->r_inode_drop = CEPH_CAP_FILE_EXCL;
 		}
 		if (dfi->last_name) {
-			req->r_path2 = kstrdup(dfi->last_name, GFP_KERNEL);
+			struct qstr d_name = { .name = dfi->last_name,
+					       .len = strlen(dfi->last_name) };
+
+			req->r_path2 = kzalloc(NAME_MAX + 1, GFP_KERNEL);
 			if (!req->r_path2) {
 				ceph_mdsc_put_request(req);
 				return -ENOMEM;
 			}
+
+			err = ceph_encode_encrypted_dname(inode, &d_name,
+							  req->r_path2);
+			if (err < 0) {
+				ceph_mdsc_put_request(req);
+				return err;
+			}
 		} else if (is_hash_order(ctx->pos)) {
 			req->r_args.readdir.offset_hash =
 				cpu_to_le32(fpos_hash(ctx->pos));
@@ -511,15 +529,20 @@ more:
 	for (; i < rinfo->dir_nr; i++) {
 		struct ceph_mds_reply_dir_entry *rde = rinfo->dir_entries + i;
 
-		BUG_ON(rde->offset < ctx->pos);
+		if (rde->offset < ctx->pos) {
+			pr_warn("%s: rde->offset 0x%llx ctx->pos 0x%llx\n",
+				__func__, rde->offset, ctx->pos);
+			return -EIO;
+		}
+
+		if (WARN_ON_ONCE(!rde->inode.in))
+			return -EIO;
 
 		ctx->pos = rde->offset;
 		dout("readdir (%d/%d) -> %llx '%.*s' %p\n",
 		     i, rinfo->dir_nr, ctx->pos,
 		     rde->name_len, rde->name, &rde->inode.in);
 
-		BUG_ON(!rde->inode.in);
-
 		if (!dir_emit(ctx, rde->name, rde->name_len,
 			      ceph_present_ino(inode->i_sb, le64_to_cpu(rde->inode.in->ino)),
 			      le32_to_cpu(rde->inode.in->mode) >> 12)) {
@@ -532,6 +555,8 @@ more:
 			dout("filldir stopping us...\n");
 			return 0;
 		}
+
+		/* Reset the lengths to their original allocated vals */
 		ctx->pos++;
 	}
 
@@ -586,7 +611,6 @@ more:
 					dfi->dir_ordered_count);
 		spin_unlock(&ci->i_ceph_lock);
 	}
-
 	dout("readdir %p file %p done.\n", inode, file);
 	return 0;
 }
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index a6e9a41020d5..0c33809f8e22 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1752,7 +1752,8 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 			     struct ceph_mds_session *session)
 {
 	struct dentry *parent = req->r_dentry;
-	struct ceph_inode_info *ci = ceph_inode(d_inode(parent));
+	struct inode *inode = d_inode(parent);
+	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
 	struct qstr dname;
 	struct dentry *dn;
@@ -1826,9 +1827,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 		tvino.snap = le64_to_cpu(rde->inode.in->snapid);
 
 		if (rinfo->hash_order) {
-			u32 hash = ceph_str_hash(ci->i_dir_layout.dl_dir_hash,
-						 rde->name, rde->name_len);
-			hash = ceph_frag_value(hash);
+			u32 hash = ceph_frag_value(rde->raw_hash);
 			if (hash != last_hash)
 				fpos_offset = 2;
 			last_hash = hash;
@@ -1851,6 +1850,11 @@ retry_lookup:
 				err = -ENOMEM;
 				goto out;
 			}
+			if (rde->is_nokey) {
+				spin_lock(&dn->d_lock);
+				dn->d_flags |= DCACHE_NOKEY_NAME;
+				spin_unlock(&dn->d_lock);
+			}
 		} else if (d_really_is_positive(dn) &&
 			   (ceph_ino(d_inode(dn)) != tvino.ino ||
 			    ceph_snap(d_inode(dn)) != tvino.snap)) {
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 8709fc1b2523..447acc4a0fbd 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -440,20 +440,87 @@ static int parse_reply_info_readdir(void **p, void *end,
 
 	info->dir_nr = num;
 	while (num) {
+		struct inode *inode = d_inode(req->r_dentry);
+		struct ceph_inode_info *ci = ceph_inode(inode);
 		struct ceph_mds_reply_dir_entry *rde = info->dir_entries + i;
+		struct fscrypt_str tname = FSTR_INIT(NULL, 0);
+		struct fscrypt_str oname = FSTR_INIT(NULL, 0);
+		struct ceph_fname fname;
+		u32 altname_len, _name_len;
+		u8 *altname, *_name;
+
 		/* dentry */
-		ceph_decode_32_safe(p, end, rde->name_len, bad);
-		ceph_decode_need(p, end, rde->name_len, bad);
-		rde->name = *p;
-		*p += rde->name_len;
-		dout("parsed dir dname '%.*s'\n", rde->name_len, rde->name);
+		ceph_decode_32_safe(p, end, _name_len, bad);
+		ceph_decode_need(p, end, _name_len, bad);
+		_name = *p;
+		*p += _name_len;
+		dout("parsed dir dname '%.*s'\n", _name_len, _name);
+
+		if (info->hash_order)
+			rde->raw_hash = ceph_str_hash(ci->i_dir_layout.dl_dir_hash,
+						      _name, _name_len);
 
 		/* dentry lease */
 		err = parse_reply_info_lease(p, end, &rde->lease, features,
-					     &rde->altname_len, &rde->altname);
+					     &altname_len, &altname);
 		if (err)
 			goto out_bad;
 
+		/*
+		 * Try to dencrypt the dentry names and update them
+		 * in the ceph_mds_reply_dir_entry struct.
+		 */
+		fname.dir = inode;
+		fname.name = _name;
+		fname.name_len = _name_len;
+		fname.ctext = altname;
+		fname.ctext_len = altname_len;
+		/*
+		 * The _name_len maybe larger than altname_len, such as
+		 * when the human readable name length is in range of
+		 * (CEPH_NOHASH_NAME_MAX, CEPH_NOHASH_NAME_MAX + SHA256_DIGEST_SIZE),
+		 * then the copy in ceph_fname_to_usr will corrupt the
+		 * data if there has no encryption key.
+		 *
+		 * Just set the no_copy flag and then if there has no
+		 * encryption key the oname.name will be assigned to
+		 * _name always.
+		 */
+		fname.no_copy = true;
+		if (altname_len == 0) {
+			/*
+			 * Set tname to _name, and this will be used
+			 * to do the base64_decode in-place. It's
+			 * safe because the decoded string should
+			 * always be shorter, which is 3/4 of origin
+			 * string.
+			 */
+			tname.name = _name;
+
+			/*
+			 * Set oname to _name too, and this will be
+			 * used to do the dencryption in-place.
+			 */
+			oname.name = _name;
+			oname.len = _name_len;
+		} else {
+			/*
+			 * This will do the decryption only in-place
+			 * from altname cryptext directly.
+			 */
+			oname.name = altname;
+			oname.len = altname_len;
+		}
+		rde->is_nokey = false;
+		err = ceph_fname_to_usr(&fname, &tname, &oname, &rde->is_nokey);
+		if (err) {
+			pr_err("%s unable to decode %.*s, got %d\n", __func__,
+			       _name_len, _name, err);
+			goto out_bad;
+		}
+		rde->name = oname.name;
+		rde->name_len = oname.len;
+
 		/* inode */
 		err = parse_reply_info_in(p, end, &rde->inode, features);
 		if (err < 0)
@@ -3671,7 +3738,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 	if (err == 0) {
 		if (result == 0 && (req->r_op == CEPH_MDS_OP_READDIR ||
 				    req->r_op == CEPH_MDS_OP_LSSNAP))
-			ceph_readdir_prepopulate(req, req->r_session);
+			err = ceph_readdir_prepopulate(req, req->r_session);
 	}
 	current->journal_info = NULL;
 	mutex_unlock(&req->r_fill_mutex);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index a4a6f7893b9e..a8f622439f38 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -96,10 +96,10 @@ struct ceph_mds_reply_info_in {
 };
 
 struct ceph_mds_reply_dir_entry {
+	bool			      is_nokey;
 	char                          *name;
-	u8			      *altname;
 	u32                           name_len;
-	u32			      altname_len;
+	u32			      raw_hash;
 	struct ceph_mds_reply_lease   *lease;
 	struct ceph_mds_reply_info_in inode;
 	loff_t			      offset;

From 79f2f6ad878c1f2cb9edc674c6a263ff2ef6d1fd Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Thu, 3 Sep 2020 13:31:10 -0400
Subject: [PATCH 0630/1189] ceph: create symlinks with encrypted and
 base64-encoded targets
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When creating symlinks in encrypted directories, encrypt and
base64-encode the target with the new inode's key before sending to the
MDS.

When filling a symlinked inode, base64-decode it into a buffer that
we'll keep in ci->i_symlink. When get_link is called, decrypt the buffer
into a new one that will hang off i_link.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/dir.c   |  54 ++++++++++++++++++++---
 fs/ceph/inode.c | 113 +++++++++++++++++++++++++++++++++++++++++++-----
 2 files changed, 150 insertions(+), 17 deletions(-)

diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index ee5c8b9c8630..7e064c024d2a 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -948,6 +948,43 @@ static int ceph_create(struct mnt_idmap *idmap, struct inode *dir,
 	return ceph_mknod(idmap, dir, dentry, mode, 0);
 }
 
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+static int prep_encrypted_symlink_target(struct ceph_mds_request *req,
+					 const char *dest)
+{
+	int err;
+	int len = strlen(dest);
+	struct fscrypt_str osd_link = FSTR_INIT(NULL, 0);
+
+	err = fscrypt_prepare_symlink(req->r_parent, dest, len, PATH_MAX,
+				      &osd_link);
+	if (err)
+		goto out;
+
+	err = fscrypt_encrypt_symlink(req->r_new_inode, dest, len, &osd_link);
+	if (err)
+		goto out;
+
+	req->r_path2 = kmalloc(CEPH_BASE64_CHARS(osd_link.len) + 1, GFP_KERNEL);
+	if (!req->r_path2) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	len = ceph_base64_encode(osd_link.name, osd_link.len, req->r_path2);
+	req->r_path2[len] = '\0';
+out:
+	fscrypt_fname_free_buffer(&osd_link);
+	return err;
+}
+#else
+static int prep_encrypted_symlink_target(struct ceph_mds_request *req,
+					 const char *dest)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
 static int ceph_symlink(struct mnt_idmap *idmap, struct inode *dir,
 			struct dentry *dentry, const char *dest)
 {
@@ -983,14 +1020,21 @@ static int ceph_symlink(struct mnt_idmap *idmap, struct inode *dir,
 		goto out_req;
 	}
 
-	req->r_path2 = kstrdup(dest, GFP_KERNEL);
-	if (!req->r_path2) {
-		err = -ENOMEM;
-		goto out_req;
-	}
 	req->r_parent = dir;
 	ihold(dir);
 
+	if (IS_ENCRYPTED(req->r_new_inode)) {
+		err = prep_encrypted_symlink_target(req, dest);
+		if (err)
+			goto out_req;
+	} else {
+		req->r_path2 = kstrdup(dest, GFP_KERNEL);
+		if (!req->r_path2) {
+			err = -ENOMEM;
+			goto out_req;
+		}
+	}
+
 	set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
 	req->r_dentry = dget(dentry);
 	req->r_num_caps = 2;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 0c33809f8e22..5423c69ac434 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -35,6 +35,7 @@
  */
 
 static const struct inode_operations ceph_symlink_iops;
+static const struct inode_operations ceph_encrypted_symlink_iops;
 
 static void ceph_inode_work(struct work_struct *work);
 
@@ -640,6 +641,7 @@ void ceph_free_inode(struct inode *inode)
 #ifdef CONFIG_FS_ENCRYPTION
 	kfree(ci->fscrypt_auth);
 #endif
+	fscrypt_free_inode(inode);
 	kmem_cache_free(ceph_inode_cachep, ci);
 }
 
@@ -837,6 +839,34 @@ void ceph_fill_file_time(struct inode *inode, int issued,
 		     inode, time_warp_seq, ci->i_time_warp_seq);
 }
 
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+static int decode_encrypted_symlink(const char *encsym, int enclen, u8 **decsym)
+{
+	int declen;
+	u8 *sym;
+
+	sym = kmalloc(enclen + 1, GFP_NOFS);
+	if (!sym)
+		return -ENOMEM;
+
+	declen = ceph_base64_decode(encsym, enclen, sym);
+	if (declen < 0) {
+		pr_err("%s: can't decode symlink (%d). Content: %.*s\n",
+		       __func__, declen, enclen, encsym);
+		kfree(sym);
+		return -EIO;
+	}
+	sym[declen + 1] = '\0';
+	*decsym = sym;
+	return declen;
+}
+#else
+static int decode_encrypted_symlink(const char *encsym, int symlen, u8 **decsym)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
 /*
  * Populate an inode based on info from mds.  May be called on new or
  * existing inodes.
@@ -1071,26 +1101,42 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 		inode->i_fop = &ceph_file_fops;
 		break;
 	case S_IFLNK:
-		inode->i_op = &ceph_symlink_iops;
 		if (!ci->i_symlink) {
 			u32 symlen = iinfo->symlink_len;
 			char *sym;
 
 			spin_unlock(&ci->i_ceph_lock);
 
-			if (symlen != i_size_read(inode)) {
-				pr_err("%s %llx.%llx BAD symlink "
-					"size %lld\n", __func__,
-					ceph_vinop(inode),
-					i_size_read(inode));
+			if (IS_ENCRYPTED(inode)) {
+				if (symlen != i_size_read(inode))
+					pr_err("%s %llx.%llx BAD symlink size %lld\n",
+						__func__, ceph_vinop(inode),
+						i_size_read(inode));
+
+				err = decode_encrypted_symlink(iinfo->symlink,
+							       symlen, (u8 **)&sym);
+				if (err < 0) {
+					pr_err("%s decoding encrypted symlink failed: %d\n",
+						__func__, err);
+					goto out;
+				}
+				symlen = err;
 				i_size_write(inode, symlen);
 				inode->i_blocks = calc_inode_blocks(symlen);
-			}
+			} else {
+				if (symlen != i_size_read(inode)) {
+					pr_err("%s %llx.%llx BAD symlink size %lld\n",
+						__func__, ceph_vinop(inode),
+						i_size_read(inode));
+					i_size_write(inode, symlen);
+					inode->i_blocks = calc_inode_blocks(symlen);
+				}
 
-			err = -ENOMEM;
-			sym = kstrndup(iinfo->symlink, symlen, GFP_NOFS);
-			if (!sym)
-				goto out;
+				err = -ENOMEM;
+				sym = kstrndup(iinfo->symlink, symlen, GFP_NOFS);
+				if (!sym)
+					goto out;
+			}
 
 			spin_lock(&ci->i_ceph_lock);
 			if (!ci->i_symlink)
@@ -1098,7 +1144,17 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 			else
 				kfree(sym); /* lost a race */
 		}
-		inode->i_link = ci->i_symlink;
+
+		if (IS_ENCRYPTED(inode)) {
+			/*
+			 * Encrypted symlinks need to be decrypted before we can
+			 * cache their targets in i_link. Don't touch it here.
+			 */
+			inode->i_op = &ceph_encrypted_symlink_iops;
+		} else {
+			inode->i_link = ci->i_symlink;
+			inode->i_op = &ceph_symlink_iops;
+		}
 		break;
 	case S_IFDIR:
 		inode->i_op = &ceph_dir_iops;
@@ -2126,6 +2182,32 @@ static void ceph_inode_work(struct work_struct *work)
 	iput(inode);
 }
 
+static const char *ceph_encrypted_get_link(struct dentry *dentry,
+					   struct inode *inode,
+					   struct delayed_call *done)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
+	return fscrypt_get_symlink(inode, ci->i_symlink, i_size_read(inode),
+				   done);
+}
+
+static int ceph_encrypted_symlink_getattr(struct mnt_idmap *idmap,
+					  const struct path *path,
+					  struct kstat *stat, u32 request_mask,
+					  unsigned int query_flags)
+{
+	int ret;
+
+	ret = ceph_getattr(idmap, path, stat, request_mask, query_flags);
+	if (ret)
+		return ret;
+	return fscrypt_symlink_getattr(path, stat);
+}
+
 /*
  * symlinks
  */
@@ -2136,6 +2218,13 @@ static const struct inode_operations ceph_symlink_iops = {
 	.listxattr = ceph_listxattr,
 };
 
+static const struct inode_operations ceph_encrypted_symlink_iops = {
+	.get_link = ceph_encrypted_get_link,
+	.setattr = ceph_setattr,
+	.getattr = ceph_encrypted_symlink_getattr,
+	.listxattr = ceph_listxattr,
+};
+
 int __ceph_setattr(struct inode *inode, struct iattr *attr,
 		   struct ceph_iattr *cia)
 {

From 94af0470924c6368b07f9125fde29d6698ed1558 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Thu, 1 Jul 2021 14:40:51 -0400
Subject: [PATCH 0631/1189] ceph: add some fscrypt guardrails
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add the appropriate calls into fscrypt for various actions, including
link, rename, setattr, and the open codepaths.

Disable fallocate for encrypted inodes -- hopefully, just for now.

If we have an encrypted inode, then the client will need to re-encrypt
the contents of the new object. Disable copy offload to or from
encrypted inodes.

Set i_blkbits to crypto block size for encrypted inodes -- some of the
underlying infrastructure for fscrypt relies on i_blkbits being aligned
to crypto blocksize.

Report STATX_ATTR_ENCRYPTED on encrypted inodes.

[ lhenriques: forbid encryption with striped layouts ]

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/crypto.h |  4 ++++
 fs/ceph/dir.c    |  9 +++++++++
 fs/ceph/file.c   | 21 ++++++++++++++++++++-
 fs/ceph/inode.c  | 26 ++++++++++++++++++--------
 fs/ceph/ioctl.c  |  4 ++++
 5 files changed, 55 insertions(+), 9 deletions(-)

diff --git a/fs/ceph/crypto.h b/fs/ceph/crypto.h
index 3269fc8f8cf3..21694df7dfbf 100644
--- a/fs/ceph/crypto.h
+++ b/fs/ceph/crypto.h
@@ -9,6 +9,10 @@
 #include <crypto/sha2.h>
 #include <linux/fscrypt.h>
 
+#define CEPH_FSCRYPT_BLOCK_SHIFT   12
+#define CEPH_FSCRYPT_BLOCK_SIZE    (_AC(1, UL) << CEPH_FSCRYPT_BLOCK_SHIFT)
+#define CEPH_FSCRYPT_BLOCK_MASK	   (~(CEPH_FSCRYPT_BLOCK_SIZE-1))
+
 struct ceph_fs_client;
 struct ceph_acl_sec_ctx;
 struct ceph_mds_request;
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 7e064c024d2a..99fdc777dccd 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1148,6 +1148,10 @@ static int ceph_link(struct dentry *old_dentry, struct inode *dir,
 	if (ceph_snap(dir) != CEPH_NOSNAP)
 		return -EROFS;
 
+	err = fscrypt_prepare_link(old_dentry, dir, dentry);
+	if (err)
+		return err;
+
 	dout("link in dir %p %llx.%llx old_dentry %p:'%pd' dentry %p:'%pd'\n",
 	     dir, ceph_vinop(dir), old_dentry, old_dentry, dentry, dentry);
 	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LINK, USE_AUTH_MDS);
@@ -1395,6 +1399,11 @@ static int ceph_rename(struct mnt_idmap *idmap, struct inode *old_dir,
 	if (err)
 		return err;
 
+	err = fscrypt_prepare_rename(old_dir, old_dentry, new_dir, new_dentry,
+				     flags);
+	if (err)
+		return err;
+
 	dout("rename dir %p dentry %p to dir %p dentry %p\n",
 	     old_dir, old_dentry, new_dir, new_dentry);
 	req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 9383ec312a04..6e9ae398ef2c 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -366,8 +366,13 @@ int ceph_open(struct inode *inode, struct file *file)
 
 	/* filter out O_CREAT|O_EXCL; vfs did that already.  yuck. */
 	flags = file->f_flags & ~(O_CREAT|O_EXCL);
-	if (S_ISDIR(inode->i_mode))
+	if (S_ISDIR(inode->i_mode)) {
 		flags = O_DIRECTORY;  /* mds likes to know */
+	} else if (S_ISREG(inode->i_mode)) {
+		err = fscrypt_file_open(inode, file);
+		if (err)
+			return err;
+	}
 
 	dout("open inode %p ino %llx.%llx file %p flags %d (%d)\n", inode,
 	     ceph_vinop(inode), file, flags, file->f_flags);
@@ -879,6 +884,13 @@ retry:
 		dout("atomic_open finish_no_open on dn %p\n", dn);
 		err = finish_no_open(file, dn);
 	} else {
+		if (IS_ENCRYPTED(dir) &&
+		    !fscrypt_has_permitted_context(dir, d_inode(dentry))) {
+			pr_warn("Inconsistent encryption context (parent %llx:%llx child %llx:%llx)\n",
+				ceph_vinop(dir), ceph_vinop(d_inode(dentry)));
+			goto out_req;
+		}
+
 		dout("atomic_open finish_open on dn %p\n", dn);
 		if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
 			struct inode *newino = d_inode(dentry);
@@ -2222,6 +2234,9 @@ static long ceph_fallocate(struct file *file, int mode,
 	if (!S_ISREG(inode->i_mode))
 		return -EOPNOTSUPP;
 
+	if (IS_ENCRYPTED(inode))
+		return -EOPNOTSUPP;
+
 	prealloc_cf = ceph_alloc_cap_flush();
 	if (!prealloc_cf)
 		return -ENOMEM;
@@ -2543,6 +2558,10 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
 		return -EOPNOTSUPP;
 	}
 
+	/* Every encrypted inode gets its own key, so we can't offload them */
+	if (IS_ENCRYPTED(src_inode) || IS_ENCRYPTED(dst_inode))
+		return -EOPNOTSUPP;
+
 	if (len < src_ci->i_layout.object_size)
 		return -EOPNOTSUPP; /* no remote copy will be done */
 
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 5423c69ac434..828badfe62a8 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -972,13 +972,6 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 	issued |= __ceph_caps_dirty(ci);
 	new_issued = ~issued & info_caps;
 
-	/* directories have fl_stripe_unit set to zero */
-	if (le32_to_cpu(info->layout.fl_stripe_unit))
-		inode->i_blkbits =
-			fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1;
-	else
-		inode->i_blkbits = CEPH_BLOCK_SHIFT;
-
 	__ceph_update_quota(ci, iinfo->max_bytes, iinfo->max_files);
 
 #ifdef CONFIG_FS_ENCRYPTION
@@ -1004,6 +997,15 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 		ceph_decode_timespec64(&ci->i_snap_btime, &iinfo->snap_btime);
 	}
 
+	/* directories have fl_stripe_unit set to zero */
+	if (IS_ENCRYPTED(inode))
+		inode->i_blkbits = CEPH_FSCRYPT_BLOCK_SHIFT;
+	else if (le32_to_cpu(info->layout.fl_stripe_unit))
+		inode->i_blkbits =
+			fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1;
+	else
+		inode->i_blkbits = CEPH_BLOCK_SHIFT;
+
 	if ((new_version || (new_issued & CEPH_CAP_LINK_SHARED)) &&
 	    (issued & CEPH_CAP_LINK_EXCL) == 0)
 		set_nlink(inode, le32_to_cpu(info->nlink));
@@ -2495,6 +2497,10 @@ int ceph_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	if (ceph_inode_is_shutdown(inode))
 		return -ESTALE;
 
+	err = fscrypt_prepare_setattr(dentry, attr);
+	if (err)
+		return err;
+
 	err = setattr_prepare(&nop_mnt_idmap, dentry, attr);
 	if (err != 0)
 		return err;
@@ -2778,8 +2784,12 @@ int ceph_getattr(struct mnt_idmap *idmap, const struct path *path,
 			stat->nlink = 1 + 1 + ci->i_subdirs;
 	}
 
-	stat->attributes_mask |= STATX_ATTR_CHANGE_MONOTONIC;
 	stat->attributes |= STATX_ATTR_CHANGE_MONOTONIC;
+	if (IS_ENCRYPTED(inode))
+		stat->attributes |= STATX_ATTR_ENCRYPTED;
+	stat->attributes_mask |= (STATX_ATTR_CHANGE_MONOTONIC |
+				  STATX_ATTR_ENCRYPTED);
+
 	stat->result_mask = request_mask & valid_mask;
 	return err;
 }
diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index 11d37d307382..91a84917d203 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -294,6 +294,10 @@ static long ceph_set_encryption_policy(struct file *file, unsigned long arg)
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 
+	/* encrypted directories can't have striped layout */
+	if (ci->i_layout.stripe_count > 1)
+		return -EINVAL;
+
 	ret = vet_mds_for_fscrypt(file);
 	if (ret)
 		return ret;

From e127e03009a3a3c26f00d0b2703c6e0e47927aec Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Lu=C3=ADs=20Henriques?= <lhenriques@suse.de>
Date: Thu, 3 Nov 2022 14:06:40 +0000
Subject: [PATCH 0632/1189] ceph: allow encrypting a directory while not having
 Ax caps
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If a client doesn't have Fx caps on a directory, it will get errors while
trying encrypt it:

ceph: handle_cap_grant: cap grant attempt to change fscrypt_auth on non-I_NEW inode (old len 0 new len 48)
fscrypt (ceph, inode 1099511627812): Error -105 getting encryption context

A simple way to reproduce this is to use two clients:

    client1 # mkdir /mnt/mydir

    client2 # ls /mnt/mydir

    client1 # fscrypt encrypt /mnt/mydir
    client1 # echo hello > /mnt/mydir/world

This happens because, in __ceph_setattr(), we only initialize
ci->fscrypt_auth if we have Ax and ceph_fill_inode() won't use the
fscrypt_auth received if the inode state isn't I_NEW.  Fix it by allowing
ceph_fill_inode() to also set ci->fscrypt_auth if the inode doesn't have
it set already.

Signed-off-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/inode.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 828badfe62a8..9ec4ebe5ccaf 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -975,7 +975,8 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 	__ceph_update_quota(ci, iinfo->max_bytes, iinfo->max_files);
 
 #ifdef CONFIG_FS_ENCRYPTION
-	if (iinfo->fscrypt_auth_len && (inode->i_state & I_NEW)) {
+	if (iinfo->fscrypt_auth_len &&
+	    ((inode->i_state & I_NEW) || (ci->fscrypt_auth_len == 0))) {
 		kfree(ci->fscrypt_auth);
 		ci->fscrypt_auth_len = iinfo->fscrypt_auth_len;
 		ci->fscrypt_auth = iinfo->fscrypt_auth;

From 14e034a61c908d4479be1a7ee9fe5b8d3d1f09b8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Lu=C3=ADs=20Henriques?= <lhenriques@suse.de>
Date: Tue, 29 Nov 2022 10:39:49 +0000
Subject: [PATCH 0633/1189] ceph: mark directory as non-complete after loading
 key
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When setting a directory's crypt context, ceph_dir_clear_complete()
needs to be called otherwise if it was complete before, any existing
(old) dentry will still be valid.

This patch adds a wrapper around __fscrypt_prepare_readdir() which will
ensure a directory is marked as non-complete if key status changes.

[ xiubli: revise commit title per Milind ]

Signed-off-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/crypto.c     | 35 +++++++++++++++++++++++++++++++++--
 fs/ceph/crypto.h     |  6 ++++++
 fs/ceph/dir.c        |  8 ++++----
 fs/ceph/mds_client.c |  6 +++---
 4 files changed, 46 insertions(+), 9 deletions(-)

diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c
index a08978a0ed4d..5df2c52b384f 100644
--- a/fs/ceph/crypto.c
+++ b/fs/ceph/crypto.c
@@ -287,8 +287,8 @@ int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname,
 	if (fname->name_len > NAME_MAX || fname->ctext_len > NAME_MAX)
 		return -EIO;
 
-	ret = __fscrypt_prepare_readdir(fname->dir);
-	if (ret)
+	ret = ceph_fscrypt_prepare_readdir(fname->dir);
+	if (ret < 0)
 		return ret;
 
 	/*
@@ -334,3 +334,34 @@ out:
 	fscrypt_fname_free_buffer(&_tname);
 	return ret;
 }
+
+/**
+ * ceph_fscrypt_prepare_readdir - simple __fscrypt_prepare_readdir() wrapper
+ * @dir: directory inode for readdir prep
+ *
+ * Simple wrapper around __fscrypt_prepare_readdir() that will mark directory as
+ * non-complete if this call results in having the directory unlocked.
+ *
+ * Returns:
+ *     1 - if directory was locked and key is now loaded (i.e. dir is unlocked)
+ *     0 - if directory is still locked
+ *   < 0 - if __fscrypt_prepare_readdir() fails
+ */
+int ceph_fscrypt_prepare_readdir(struct inode *dir)
+{
+	bool had_key = fscrypt_has_encryption_key(dir);
+	int err;
+
+	if (!IS_ENCRYPTED(dir))
+		return 0;
+
+	err = __fscrypt_prepare_readdir(dir);
+	if (err)
+		return err;
+	if (!had_key && fscrypt_has_encryption_key(dir)) {
+		/* directory just got unlocked, mark it as not complete */
+		ceph_dir_clear_complete(dir);
+		return 1;
+	}
+	return 0;
+}
diff --git a/fs/ceph/crypto.h b/fs/ceph/crypto.h
index 21694df7dfbf..b5413ec95b1a 100644
--- a/fs/ceph/crypto.h
+++ b/fs/ceph/crypto.h
@@ -103,6 +103,7 @@ static inline void ceph_fname_free_buffer(struct inode *parent,
 
 int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname,
 		      struct fscrypt_str *oname, bool *is_nokey);
+int ceph_fscrypt_prepare_readdir(struct inode *dir);
 
 #else /* CONFIG_FS_ENCRYPTION */
 
@@ -160,6 +161,11 @@ static inline int ceph_fname_to_usr(const struct ceph_fname *fname,
 	oname->len = fname->name_len;
 	return 0;
 }
+
+static inline int ceph_fscrypt_prepare_readdir(struct inode *dir)
+{
+	return 0;
+}
 #endif /* CONFIG_FS_ENCRYPTION */
 
 #endif
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 99fdc777dccd..08504afbe242 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -343,8 +343,8 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 		ctx->pos = 2;
 	}
 
-	err = fscrypt_prepare_readdir(inode);
-	if (err)
+	err = ceph_fscrypt_prepare_readdir(inode);
+	if (err < 0)
 		return err;
 
 	spin_lock(&ci->i_ceph_lock);
@@ -785,8 +785,8 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
 		return ERR_PTR(-ENAMETOOLONG);
 
 	if (IS_ENCRYPTED(dir)) {
-		err = __fscrypt_prepare_readdir(dir);
-		if (err)
+		err = ceph_fscrypt_prepare_readdir(dir);
+		if (err < 0)
 			return ERR_PTR(err);
 		if (!fscrypt_has_encryption_key(dir)) {
 			spin_lock(&dentry->d_lock);
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 447acc4a0fbd..7de22052ee22 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2545,8 +2545,8 @@ static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen)
 	if (!IS_ENCRYPTED(dir))
 		goto success;
 
-	ret = __fscrypt_prepare_readdir(dir);
-	if (ret)
+	ret = ceph_fscrypt_prepare_readdir(dir);
+	if (ret < 0)
 		return ERR_PTR(ret);
 
 	/* No key? Just ignore it. */
@@ -2666,7 +2666,7 @@ retry:
 			spin_unlock(&cur->d_lock);
 			parent = dget_parent(cur);
 
-			ret = __fscrypt_prepare_readdir(d_inode(parent));
+			ret = ceph_fscrypt_prepare_readdir(d_inode(parent));
 			if (ret < 0) {
 				dput(parent);
 				dput(cur);

From 16be62fc8a53482529201b4be6bbcd0de3a058cb Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Thu, 25 Aug 2022 09:31:06 -0400
Subject: [PATCH 0634/1189] ceph: size handling in MClientRequest, cap updates
 and inode traces
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For encrypted inodes, transmit a rounded-up size to the MDS as the
normal file size and send the real inode size in fscrypt_file field.
Also, fix up creates and truncates to also transmit fscrypt_file.

When we get an inode trace from the MDS, grab the fscrypt_file field if
the inode is encrypted, and use it to populate the i_size field instead
of the regular inode size field.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/caps.c       | 50 +++++++++++++++++++++++++-------------------
 fs/ceph/dir.c        |  3 +++
 fs/ceph/file.c       |  1 +
 fs/ceph/inode.c      | 33 ++++++++++++++++++++++++++---
 fs/ceph/mds_client.c |  9 +++++++-
 fs/ceph/mds_client.h |  2 ++
 6 files changed, 73 insertions(+), 25 deletions(-)

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 4738be54dc73..aff256274415 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1217,10 +1217,9 @@ struct cap_msg_args {
 	umode_t			mode;
 	bool			inline_data;
 	bool			wake;
+	bool			encrypted;
 	u32			fscrypt_auth_len;
-	u32			fscrypt_file_len;
 	u8			fscrypt_auth[sizeof(struct ceph_fscrypt_auth)]; // for context
-	u8			fscrypt_file[sizeof(u64)]; // for size
 };
 
 /* Marshal up the cap msg to the MDS */
@@ -1255,7 +1254,13 @@ static void encode_cap_msg(struct ceph_msg *msg, struct cap_msg_args *arg)
 	fc->ino = cpu_to_le64(arg->ino);
 	fc->snap_follows = cpu_to_le64(arg->follows);
 
-	fc->size = cpu_to_le64(arg->size);
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+	if (arg->encrypted)
+		fc->size = cpu_to_le64(round_up(arg->size,
+						CEPH_FSCRYPT_BLOCK_SIZE));
+	else
+#endif
+		fc->size = cpu_to_le64(arg->size);
 	fc->max_size = cpu_to_le64(arg->max_size);
 	ceph_encode_timespec64(&fc->mtime, &arg->mtime);
 	ceph_encode_timespec64(&fc->atime, &arg->atime);
@@ -1315,11 +1320,17 @@ static void encode_cap_msg(struct ceph_msg *msg, struct cap_msg_args *arg)
 	ceph_encode_64(&p, 0);
 
 #if IS_ENABLED(CONFIG_FS_ENCRYPTION)
-	/* fscrypt_auth and fscrypt_file (version 12) */
+	/*
+	 * fscrypt_auth and fscrypt_file (version 12)
+	 *
+	 * fscrypt_auth holds the crypto context (if any). fscrypt_file
+	 * tracks the real i_size as an __le64 field (and we use a rounded-up
+	 * i_size in the traditional size field).
+	 */
 	ceph_encode_32(&p, arg->fscrypt_auth_len);
 	ceph_encode_copy(&p, arg->fscrypt_auth, arg->fscrypt_auth_len);
-	ceph_encode_32(&p, arg->fscrypt_file_len);
-	ceph_encode_copy(&p, arg->fscrypt_file, arg->fscrypt_file_len);
+	ceph_encode_32(&p, sizeof(__le64));
+	ceph_encode_64(&p, arg->size);
 #else /* CONFIG_FS_ENCRYPTION */
 	ceph_encode_32(&p, 0);
 	ceph_encode_32(&p, 0);
@@ -1391,7 +1402,6 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap,
 	arg->follows = flushing ? ci->i_head_snapc->seq : 0;
 	arg->flush_tid = flush_tid;
 	arg->oldest_flush_tid = oldest_flush_tid;
-
 	arg->size = i_size_read(inode);
 	ci->i_reported_size = arg->size;
 	arg->max_size = ci->i_wanted_max_size;
@@ -1445,6 +1455,7 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap,
 		}
 	}
 	arg->flags = flags;
+	arg->encrypted = IS_ENCRYPTED(inode);
 #if IS_ENABLED(CONFIG_FS_ENCRYPTION)
 	if (ci->fscrypt_auth_len &&
 	    WARN_ON_ONCE(ci->fscrypt_auth_len > sizeof(struct ceph_fscrypt_auth))) {
@@ -1456,21 +1467,21 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap,
 		       min_t(size_t, ci->fscrypt_auth_len,
 			     sizeof(arg->fscrypt_auth)));
 	}
-	/* FIXME: use this to track "real" size */
-	arg->fscrypt_file_len = 0;
 #endif /* CONFIG_FS_ENCRYPTION */
 }
 
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+#define CAP_MSG_FIXED_FIELDS (sizeof(struct ceph_mds_caps) + \
+		      4 + 8 + 4 + 4 + 8 + 4 + 4 + 4 + 8 + 8 + 4 + 8 + 8 + 4 + 4 + 8)
+
+static inline int cap_msg_size(struct cap_msg_args *arg)
+{
+	return CAP_MSG_FIXED_FIELDS + arg->fscrypt_auth_len;
+}
+#else
 #define CAP_MSG_FIXED_FIELDS (sizeof(struct ceph_mds_caps) + \
 		      4 + 8 + 4 + 4 + 8 + 4 + 4 + 4 + 8 + 8 + 4 + 8 + 8 + 4 + 4)
 
-#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
-static inline int cap_msg_size(struct cap_msg_args *arg)
-{
-	return CAP_MSG_FIXED_FIELDS + arg->fscrypt_auth_len +
-			arg->fscrypt_file_len;
-}
-#else
 static inline int cap_msg_size(struct cap_msg_args *arg)
 {
 	return CAP_MSG_FIXED_FIELDS;
@@ -1550,13 +1561,10 @@ static inline int __send_flush_snap(struct inode *inode,
 	arg.inline_data = capsnap->inline_data;
 	arg.flags = 0;
 	arg.wake = false;
+	arg.encrypted = IS_ENCRYPTED(inode);
 
-	/*
-	 * No fscrypt_auth changes from a capsnap. It will need
-	 * to update fscrypt_file on size changes (TODO).
-	 */
+	/* No fscrypt_auth changes from a capsnap.*/
 	arg.fscrypt_auth_len = 0;
-	arg.fscrypt_file_len = 0;
 
 	msg = ceph_msg_new(CEPH_MSG_CLIENT_CAPS, cap_msg_size(&arg),
 			   GFP_NOFS, false);
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 08504afbe242..4990886a366c 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -915,6 +915,9 @@ static int ceph_mknod(struct mnt_idmap *idmap, struct inode *dir,
 		goto out_req;
 	}
 
+	if (S_ISREG(mode) && IS_ENCRYPTED(dir))
+		set_bit(CEPH_MDS_R_FSCRYPT_FILE, &req->r_req_flags);
+
 	req->r_dentry = dget(dentry);
 	req->r_num_caps = 2;
 	req->r_parent = dir;
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 6e9ae398ef2c..c3ce224db032 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -790,6 +790,7 @@ retry:
 	req->r_parent = dir;
 	ihold(dir);
 	if (IS_ENCRYPTED(dir)) {
+		set_bit(CEPH_MDS_R_FSCRYPT_FILE, &req->r_req_flags);
 		if (!fscrypt_has_encryption_key(dir)) {
 			spin_lock(&dentry->d_lock);
 			dentry->d_flags |= DCACHE_NOKEY_NAME;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 9ec4ebe5ccaf..841f60e8de6a 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1028,6 +1028,7 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 
 	if (new_version ||
 	    (new_issued & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR))) {
+		u64 size = le64_to_cpu(info->size);
 		s64 old_pool = ci->i_layout.pool_id;
 		struct ceph_string *old_ns;
 
@@ -1041,10 +1042,22 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 
 		pool_ns = old_ns;
 
+		if (IS_ENCRYPTED(inode) && size &&
+		    iinfo->fscrypt_file_len == sizeof(__le64)) {
+			u64 fsize = __le64_to_cpu(*(__le64 *)iinfo->fscrypt_file);
+
+			if (size == round_up(fsize, CEPH_FSCRYPT_BLOCK_SIZE)) {
+				size = fsize;
+			} else {
+				pr_warn("fscrypt size mismatch: size=%llu fscrypt_file=%llu, discarding fscrypt_file size.\n",
+					info->size, size);
+			}
+		}
+
 		queue_trunc = ceph_fill_file_size(inode, issued,
 					le32_to_cpu(info->truncate_seq),
 					le64_to_cpu(info->truncate_size),
-					le64_to_cpu(info->size));
+					size);
 		/* only update max_size on auth cap */
 		if ((info->cap.flags & CEPH_CAP_FLAG_AUTH) &&
 		    ci->i_max_size != le64_to_cpu(info->max_size)) {
@@ -2388,11 +2401,25 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr,
 			}
 		} else if ((issued & CEPH_CAP_FILE_SHARED) == 0 ||
 			   attr->ia_size != isize) {
-			req->r_args.setattr.size = cpu_to_le64(attr->ia_size);
-			req->r_args.setattr.old_size = cpu_to_le64(isize);
 			mask |= CEPH_SETATTR_SIZE;
 			release |= CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_EXCL |
 				   CEPH_CAP_FILE_RD | CEPH_CAP_FILE_WR;
+			if (IS_ENCRYPTED(inode) && attr->ia_size) {
+				set_bit(CEPH_MDS_R_FSCRYPT_FILE, &req->r_req_flags);
+				mask |= CEPH_SETATTR_FSCRYPT_FILE;
+				req->r_args.setattr.size =
+					cpu_to_le64(round_up(attr->ia_size,
+							     CEPH_FSCRYPT_BLOCK_SIZE));
+				req->r_args.setattr.old_size =
+					cpu_to_le64(round_up(isize,
+							     CEPH_FSCRYPT_BLOCK_SIZE));
+				req->r_fscrypt_file = attr->ia_size;
+				/* FIXME: client must zero out any partial blocks! */
+			} else {
+				req->r_args.setattr.size = cpu_to_le64(attr->ia_size);
+				req->r_args.setattr.old_size = cpu_to_le64(isize);
+				req->r_fscrypt_file = 0;
+			}
 		}
 	}
 	if (ia_valid & ATTR_MTIME) {
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 7de22052ee22..c257d75c5757 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2832,7 +2832,12 @@ static void encode_mclientrequest_tail(void **p,
 	} else {
 		ceph_encode_32(p, 0);
 	}
-	ceph_encode_32(p, 0); // fscrypt_file for now
+	if (test_bit(CEPH_MDS_R_FSCRYPT_FILE, &req->r_req_flags)) {
+		ceph_encode_32(p, sizeof(__le64));
+		ceph_encode_64(p, req->r_fscrypt_file);
+	} else {
+		ceph_encode_32(p, 0);
+	}
 }
 
 /*
@@ -2922,6 +2927,8 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 
 	/* fscrypt_file */
 	len += sizeof(u32);
+	if (test_bit(CEPH_MDS_R_FSCRYPT_FILE, &req->r_req_flags))
+		len += sizeof(__le64);
 
 	msg = ceph_msg_new2(CEPH_MSG_CLIENT_REQUEST, len, 1, GFP_NOFS, false);
 	if (!msg) {
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index a8f622439f38..0477388a0d1c 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -282,6 +282,7 @@ struct ceph_mds_request {
 #define CEPH_MDS_R_DID_PREPOPULATE	(6) /* prepopulated readdir */
 #define CEPH_MDS_R_PARENT_LOCKED	(7) /* is r_parent->i_rwsem wlocked? */
 #define CEPH_MDS_R_ASYNC		(8) /* async request */
+#define CEPH_MDS_R_FSCRYPT_FILE		(9) /* must marshal fscrypt_file field */
 	unsigned long	r_req_flags;
 
 	struct mutex r_fill_mutex;
@@ -289,6 +290,7 @@ struct ceph_mds_request {
 	union ceph_mds_request_args r_args;
 
 	struct ceph_fscrypt_auth *r_fscrypt_auth;
+	u64	r_fscrypt_file;
 
 	u8 *r_altname;		    /* fscrypt binary crypttext for long filenames */
 	u32 r_altname_len;	    /* length of r_altname */

From 0d91f0ad6a01c8c64a84c5255c5ab95133d0fed5 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Thu, 25 Aug 2022 09:31:09 -0400
Subject: [PATCH 0635/1189] ceph: handle fscrypt fields in cap messages from
 MDS
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Handle the new fscrypt_file and fscrypt_auth fields in cap messages. Use
them to populate new fields in cap_extra_info and update the inode with
those values.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/caps.c | 85 ++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 83 insertions(+), 2 deletions(-)

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index aff256274415..ee61b539a8ec 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -3383,6 +3383,9 @@ struct cap_extra_info {
 	/* currently issued */
 	int issued;
 	struct timespec64 btime;
+	u8 *fscrypt_auth;
+	u32 fscrypt_auth_len;
+	u64 fscrypt_file_size;
 };
 
 /*
@@ -3415,6 +3418,14 @@ static void handle_cap_grant(struct inode *inode,
 	bool deleted_inode = false;
 	bool fill_inline = false;
 
+	/*
+	 * If there is at least one crypto block then we'll trust
+	 * fscrypt_file_size. If the real length of the file is 0, then
+	 * ignore it (it has probably been truncated down to 0 by the MDS).
+	 */
+	if (IS_ENCRYPTED(inode) && size)
+		size = extra_info->fscrypt_file_size;
+
 	dout("handle_cap_grant inode %p cap %p mds%d seq %d %s\n",
 	     inode, cap, session->s_mds, seq, ceph_cap_string(newcaps));
 	dout(" size %llu max_size %llu, i_size %llu\n", size, max_size,
@@ -3481,6 +3492,14 @@ static void handle_cap_grant(struct inode *inode,
 		dout("%p mode 0%o uid.gid %d.%d\n", inode, inode->i_mode,
 		     from_kuid(&init_user_ns, inode->i_uid),
 		     from_kgid(&init_user_ns, inode->i_gid));
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+		if (ci->fscrypt_auth_len != extra_info->fscrypt_auth_len ||
+		    memcmp(ci->fscrypt_auth, extra_info->fscrypt_auth,
+			   ci->fscrypt_auth_len))
+			pr_warn_ratelimited("%s: cap grant attempt to change fscrypt_auth on non-I_NEW inode (old len %d new len %d)\n",
+				__func__, ci->fscrypt_auth_len,
+				extra_info->fscrypt_auth_len);
+#endif
 	}
 
 	if ((newcaps & CEPH_CAP_LINK_SHARED) &&
@@ -3897,7 +3916,8 @@ static void handle_cap_flushsnap_ack(struct inode *inode, u64 flush_tid,
  */
 static bool handle_cap_trunc(struct inode *inode,
 			     struct ceph_mds_caps *trunc,
-			     struct ceph_mds_session *session)
+			     struct ceph_mds_session *session,
+			     struct cap_extra_info *extra_info)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	int mds = session->s_mds;
@@ -3914,6 +3934,14 @@ static bool handle_cap_trunc(struct inode *inode,
 
 	issued |= implemented | dirty;
 
+	/*
+	 * If there is at least one crypto block then we'll trust
+	 * fscrypt_file_size. If the real length of the file is 0, then
+	 * ignore it (it has probably been truncated down to 0 by the MDS).
+	 */
+	if (IS_ENCRYPTED(inode) && size)
+		size = extra_info->fscrypt_file_size;
+
 	dout("handle_cap_trunc inode %p mds%d seq %d to %lld seq %d\n",
 	     inode, mds, seq, truncate_size, truncate_seq);
 	queue_trunc = ceph_fill_file_size(inode, issued,
@@ -4135,6 +4163,52 @@ retry:
 	*target_cap = cap;
 }
 
+#ifdef CONFIG_FS_ENCRYPTION
+static int parse_fscrypt_fields(void **p, void *end,
+				struct cap_extra_info *extra)
+{
+	u32 len;
+
+	ceph_decode_32_safe(p, end, extra->fscrypt_auth_len, bad);
+	if (extra->fscrypt_auth_len) {
+		ceph_decode_need(p, end, extra->fscrypt_auth_len, bad);
+		extra->fscrypt_auth = kmalloc(extra->fscrypt_auth_len,
+					      GFP_KERNEL);
+		if (!extra->fscrypt_auth)
+			return -ENOMEM;
+		ceph_decode_copy_safe(p, end, extra->fscrypt_auth,
+					extra->fscrypt_auth_len, bad);
+	}
+
+	ceph_decode_32_safe(p, end, len, bad);
+	if (len >= sizeof(u64)) {
+		ceph_decode_64_safe(p, end, extra->fscrypt_file_size, bad);
+		len -= sizeof(u64);
+	}
+	ceph_decode_skip_n(p, end, len, bad);
+	return 0;
+bad:
+	return -EIO;
+}
+#else
+static int parse_fscrypt_fields(void **p, void *end,
+				struct cap_extra_info *extra)
+{
+	u32 len;
+
+	/* Don't care about these fields unless we're encryption-capable */
+	ceph_decode_32_safe(p, end, len, bad);
+	if (len)
+		ceph_decode_skip_n(p, end, len, bad);
+	ceph_decode_32_safe(p, end, len, bad);
+	if (len)
+		ceph_decode_skip_n(p, end, len, bad);
+	return 0;
+bad:
+	return -EIO;
+}
+#endif
+
 /*
  * Handle a caps message from the MDS.
  *
@@ -4255,6 +4329,11 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 		ceph_decode_64_safe(&p, end, extra_info.nsubdirs, bad);
 	}
 
+	if (msg_version >= 12) {
+		if (parse_fscrypt_fields(&p, end, &extra_info))
+			goto bad;
+	}
+
 	/* lookup ino */
 	inode = ceph_find_inode(mdsc->fsc->sb, vino);
 	dout(" op %s ino %llx.%llx inode %p\n", ceph_cap_op_name(op), vino.ino,
@@ -4352,7 +4431,8 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 		break;
 
 	case CEPH_CAP_OP_TRUNC:
-		queue_trunc = handle_cap_trunc(inode, h, session);
+		queue_trunc = handle_cap_trunc(inode, h, session,
+						&extra_info);
 		spin_unlock(&ci->i_ceph_lock);
 		if (queue_trunc)
 			ceph_queue_vmtruncate(inode);
@@ -4375,6 +4455,7 @@ out:
 	if (close_sessions)
 		ceph_mdsc_close_sessions(mdsc);
 
+	kfree(extra_info.fscrypt_auth);
 	return;
 
 flush_cap_releases:

From 77cdb7e17e39ebb986f60bbd3c2b3507687bf475 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Thu, 25 Aug 2022 09:31:14 -0400
Subject: [PATCH 0636/1189] ceph: add infrastructure for file encryption and
 decryption
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

...and allow test_dummy_encryption to bypass content encryption
if mounted with test_dummy_encryption=clear.

[ xiubli: remove test_dummy_encryption=clear support per Ilya ]

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/crypto.c | 171 +++++++++++++++++++++++++++++++++++++++++++++++
 fs/ceph/crypto.h |  80 ++++++++++++++++++++++
 2 files changed, 251 insertions(+)

diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c
index 5df2c52b384f..9494bf485f6a 100644
--- a/fs/ceph/crypto.c
+++ b/fs/ceph/crypto.c
@@ -9,6 +9,7 @@
 #include <linux/ceph/ceph_debug.h>
 #include <linux/xattr.h>
 #include <linux/fscrypt.h>
+#include <linux/ceph/striper.h>
 
 #include "super.h"
 #include "mds_client.h"
@@ -365,3 +366,173 @@ int ceph_fscrypt_prepare_readdir(struct inode *dir)
 	}
 	return 0;
 }
+
+int ceph_fscrypt_decrypt_block_inplace(const struct inode *inode,
+				  struct page *page, unsigned int len,
+				  unsigned int offs, u64 lblk_num)
+{
+	dout("%s: len %u offs %u blk %llu\n", __func__, len, offs, lblk_num);
+	return fscrypt_decrypt_block_inplace(inode, page, len, offs, lblk_num);
+}
+
+int ceph_fscrypt_encrypt_block_inplace(const struct inode *inode,
+				  struct page *page, unsigned int len,
+				  unsigned int offs, u64 lblk_num,
+				  gfp_t gfp_flags)
+{
+	dout("%s: len %u offs %u blk %llu\n", __func__, len, offs, lblk_num);
+	return fscrypt_encrypt_block_inplace(inode, page, len, offs, lblk_num,
+					     gfp_flags);
+}
+
+/**
+ * ceph_fscrypt_decrypt_pages - decrypt an array of pages
+ * @inode: pointer to inode associated with these pages
+ * @page: pointer to page array
+ * @off: offset into the file that the read data starts
+ * @len: max length to decrypt
+ *
+ * Decrypt an array of fscrypt'ed pages and return the amount of
+ * data decrypted. Any data in the page prior to the start of the
+ * first complete block in the read is ignored. Any incomplete
+ * crypto blocks at the end of the array are ignored (and should
+ * probably be zeroed by the caller).
+ *
+ * Returns the length of the decrypted data or a negative errno.
+ */
+int ceph_fscrypt_decrypt_pages(struct inode *inode, struct page **page,
+			       u64 off, int len)
+{
+	int i, num_blocks;
+	u64 baseblk = off >> CEPH_FSCRYPT_BLOCK_SHIFT;
+	int ret = 0;
+
+	/*
+	 * We can't deal with partial blocks on an encrypted file, so mask off
+	 * the last bit.
+	 */
+	num_blocks = ceph_fscrypt_blocks(off, len & CEPH_FSCRYPT_BLOCK_MASK);
+
+	/* Decrypt each block */
+	for (i = 0; i < num_blocks; ++i) {
+		int blkoff = i << CEPH_FSCRYPT_BLOCK_SHIFT;
+		int pgidx = blkoff >> PAGE_SHIFT;
+		unsigned int pgoffs = offset_in_page(blkoff);
+		int fret;
+
+		fret = ceph_fscrypt_decrypt_block_inplace(inode, page[pgidx],
+				CEPH_FSCRYPT_BLOCK_SIZE, pgoffs,
+				baseblk + i);
+		if (fret < 0) {
+			if (ret == 0)
+				ret = fret;
+			break;
+		}
+		ret += CEPH_FSCRYPT_BLOCK_SIZE;
+	}
+	return ret;
+}
+
+/**
+ * ceph_fscrypt_decrypt_extents: decrypt received extents in given buffer
+ * @inode: inode associated with pages being decrypted
+ * @page: pointer to page array
+ * @off: offset into the file that the data in page[0] starts
+ * @map: pointer to extent array
+ * @ext_cnt: length of extent array
+ *
+ * Given an extent map and a page array, decrypt the received data in-place,
+ * skipping holes. Returns the offset into buffer of end of last decrypted
+ * block.
+ */
+int ceph_fscrypt_decrypt_extents(struct inode *inode, struct page **page,
+				 u64 off, struct ceph_sparse_extent *map,
+				 u32 ext_cnt)
+{
+	int i, ret = 0;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	u64 objno, objoff;
+	u32 xlen;
+
+	/* Nothing to do for empty array */
+	if (ext_cnt == 0) {
+		dout("%s: empty array, ret 0\n", __func__);
+		return 0;
+	}
+
+	ceph_calc_file_object_mapping(&ci->i_layout, off, map[0].len,
+				      &objno, &objoff, &xlen);
+
+	for (i = 0; i < ext_cnt; ++i) {
+		struct ceph_sparse_extent *ext = &map[i];
+		int pgsoff = ext->off - objoff;
+		int pgidx = pgsoff >> PAGE_SHIFT;
+		int fret;
+
+		if ((ext->off | ext->len) & ~CEPH_FSCRYPT_BLOCK_MASK) {
+			pr_warn("%s: bad encrypted sparse extent idx %d off %llx len %llx\n",
+				__func__, i, ext->off, ext->len);
+			return -EIO;
+		}
+		fret = ceph_fscrypt_decrypt_pages(inode, &page[pgidx],
+						 off + pgsoff, ext->len);
+		dout("%s: [%d] 0x%llx~0x%llx fret %d\n", __func__, i,
+				ext->off, ext->len, fret);
+		if (fret < 0) {
+			if (ret == 0)
+				ret = fret;
+			break;
+		}
+		ret = pgsoff + fret;
+	}
+	dout("%s: ret %d\n", __func__, ret);
+	return ret;
+}
+
+/**
+ * ceph_fscrypt_encrypt_pages - encrypt an array of pages
+ * @inode: pointer to inode associated with these pages
+ * @page: pointer to page array
+ * @off: offset into the file that the data starts
+ * @len: max length to encrypt
+ * @gfp: gfp flags to use for allocation
+ *
+ * Decrypt an array of cleartext pages and return the amount of
+ * data encrypted. Any data in the page prior to the start of the
+ * first complete block in the read is ignored. Any incomplete
+ * crypto blocks at the end of the array are ignored.
+ *
+ * Returns the length of the encrypted data or a negative errno.
+ */
+int ceph_fscrypt_encrypt_pages(struct inode *inode, struct page **page, u64 off,
+				int len, gfp_t gfp)
+{
+	int i, num_blocks;
+	u64 baseblk = off >> CEPH_FSCRYPT_BLOCK_SHIFT;
+	int ret = 0;
+
+	/*
+	 * We can't deal with partial blocks on an encrypted file, so mask off
+	 * the last bit.
+	 */
+	num_blocks = ceph_fscrypt_blocks(off, len & CEPH_FSCRYPT_BLOCK_MASK);
+
+	/* Encrypt each block */
+	for (i = 0; i < num_blocks; ++i) {
+		int blkoff = i << CEPH_FSCRYPT_BLOCK_SHIFT;
+		int pgidx = blkoff >> PAGE_SHIFT;
+		unsigned int pgoffs = offset_in_page(blkoff);
+		int fret;
+
+		fret = ceph_fscrypt_encrypt_block_inplace(inode, page[pgidx],
+				CEPH_FSCRYPT_BLOCK_SIZE, pgoffs,
+				baseblk + i, gfp);
+		if (fret < 0) {
+			if (ret == 0)
+				ret = fret;
+			break;
+		}
+		ret += CEPH_FSCRYPT_BLOCK_SIZE;
+	}
+	return ret;
+}
diff --git a/fs/ceph/crypto.h b/fs/ceph/crypto.h
index b5413ec95b1a..7a03275f3ad5 100644
--- a/fs/ceph/crypto.h
+++ b/fs/ceph/crypto.h
@@ -105,6 +105,44 @@ int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname,
 		      struct fscrypt_str *oname, bool *is_nokey);
 int ceph_fscrypt_prepare_readdir(struct inode *dir);
 
+static inline unsigned int ceph_fscrypt_blocks(u64 off, u64 len)
+{
+	/* crypto blocks cannot span more than one page */
+	BUILD_BUG_ON(CEPH_FSCRYPT_BLOCK_SHIFT > PAGE_SHIFT);
+
+	return ((off+len+CEPH_FSCRYPT_BLOCK_SIZE-1) >> CEPH_FSCRYPT_BLOCK_SHIFT) -
+		(off >> CEPH_FSCRYPT_BLOCK_SHIFT);
+}
+
+/*
+ * If we have an encrypted inode then we must adjust the offset and
+ * range of the on-the-wire read to cover an entire encryption block.
+ * The copy will be done using the original offset and length, after
+ * we've decrypted the result.
+ */
+static inline void ceph_fscrypt_adjust_off_and_len(struct inode *inode,
+						   u64 *off, u64 *len)
+{
+	if (IS_ENCRYPTED(inode)) {
+		*len = ceph_fscrypt_blocks(*off, *len) * CEPH_FSCRYPT_BLOCK_SIZE;
+		*off &= CEPH_FSCRYPT_BLOCK_MASK;
+	}
+}
+
+int ceph_fscrypt_decrypt_block_inplace(const struct inode *inode,
+				  struct page *page, unsigned int len,
+				  unsigned int offs, u64 lblk_num);
+int ceph_fscrypt_encrypt_block_inplace(const struct inode *inode,
+				  struct page *page, unsigned int len,
+				  unsigned int offs, u64 lblk_num,
+				  gfp_t gfp_flags);
+int ceph_fscrypt_decrypt_pages(struct inode *inode, struct page **page,
+			       u64 off, int len);
+int ceph_fscrypt_decrypt_extents(struct inode *inode, struct page **page,
+				 u64 off, struct ceph_sparse_extent *map,
+				 u32 ext_cnt);
+int ceph_fscrypt_encrypt_pages(struct inode *inode, struct page **page, u64 off,
+			       int len, gfp_t gfp);
 #else /* CONFIG_FS_ENCRYPTION */
 
 static inline void ceph_fscrypt_set_ops(struct super_block *sb)
@@ -166,6 +204,48 @@ static inline int ceph_fscrypt_prepare_readdir(struct inode *dir)
 {
 	return 0;
 }
+
+static inline void ceph_fscrypt_adjust_off_and_len(struct inode *inode,
+						   u64 *off, u64 *len)
+{
+}
+
+static inline int ceph_fscrypt_decrypt_block_inplace(const struct inode *inode,
+					  struct page *page, unsigned int len,
+					  unsigned int offs, u64 lblk_num)
+{
+	return 0;
+}
+
+static inline int ceph_fscrypt_encrypt_block_inplace(const struct inode *inode,
+					  struct page *page, unsigned int len,
+					  unsigned int offs, u64 lblk_num,
+					  gfp_t gfp_flags)
+{
+	return 0;
+}
+
+static inline int ceph_fscrypt_decrypt_pages(struct inode *inode,
+					     struct page **page, u64 off,
+					     int len)
+{
+	return 0;
+}
+
+static inline int ceph_fscrypt_decrypt_extents(struct inode *inode,
+					       struct page **page, u64 off,
+					       struct ceph_sparse_extent *map,
+					       u32 ext_cnt)
+{
+	return 0;
+}
+
+static inline int ceph_fscrypt_encrypt_pages(struct inode *inode,
+					     struct page **page, u64 off,
+					     int len, gfp_t gfp)
+{
+	return 0;
+}
 #endif /* CONFIG_FS_ENCRYPTION */
 
 #endif

From 69dd3b3930f96b624228000921f417fb0919a6ab Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Thu, 25 Aug 2022 09:31:05 -0400
Subject: [PATCH 0637/1189] libceph: add CEPH_OSD_OP_ASSERT_VER support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

...and record the user_version in the reply in a new field in
ceph_osd_request, so we can populate the assert_ver appropriately.
Shuffle the fields a bit too so that the new field fits in an
existing hole on x86_64.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/osd_client.h | 6 +++++-
 include/linux/ceph/rados.h      | 4 ++++
 net/ceph/osd_client.c           | 5 +++++
 3 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 8f5d2b5bbba2..bf9823956758 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -198,6 +198,9 @@ struct ceph_osd_req_op {
 			u32 src_fadvise_flags;
 			struct ceph_osd_data osd_data;
 		} copy_from;
+		struct {
+			u64 ver;
+		} assert_ver;
 	};
 };
 
@@ -252,6 +255,7 @@ struct ceph_osd_request {
 	struct ceph_osd_client *r_osdc;
 	struct kref       r_kref;
 	bool              r_mempool;
+	bool		  r_linger;           /* don't resend on failure */
 	struct completion r_completion;       /* private to osd_client.c */
 	ceph_osdc_callback_t r_callback;
 
@@ -264,9 +268,9 @@ struct ceph_osd_request {
 	struct ceph_snap_context *r_snapc;    /* for writes */
 	struct timespec64 r_mtime;            /* ditto */
 	u64 r_data_offset;                    /* ditto */
-	bool r_linger;                        /* don't resend on failure */
 
 	/* internal */
+	u64 r_version;			      /* data version sent in reply */
 	unsigned long r_stamp;                /* jiffies, send or check time */
 	unsigned long r_start_stamp;          /* jiffies */
 	ktime_t r_start_latency;              /* ktime_t */
diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h
index 43a7a1573b51..73c3efbec36c 100644
--- a/include/linux/ceph/rados.h
+++ b/include/linux/ceph/rados.h
@@ -523,6 +523,10 @@ struct ceph_osd_op {
 		struct {
 			__le64 cookie;
 		} __attribute__ ((packed)) notify;
+		struct {
+			__le64 unused;
+			__le64 ver;
+		} __attribute__ ((packed)) assert_ver;
 		struct {
 			__le64 offset, length;
 			__le64 src_offset;
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 684faf8553de..7f159e40cf9c 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1048,6 +1048,10 @@ static u32 osd_req_encode_op(struct ceph_osd_op *dst,
 		dst->copy_from.src_fadvise_flags =
 			cpu_to_le32(src->copy_from.src_fadvise_flags);
 		break;
+	case CEPH_OSD_OP_ASSERT_VER:
+		dst->assert_ver.unused = cpu_to_le64(0);
+		dst->assert_ver.ver = cpu_to_le64(src->assert_ver.ver);
+		break;
 	default:
 		pr_err("unsupported osd opcode %s\n",
 			ceph_osd_op_name(src->op));
@@ -3859,6 +3863,7 @@ static void handle_reply(struct ceph_osd *osd, struct ceph_msg *msg)
 	 * one (type of) reply back.
 	 */
 	WARN_ON(!(m.flags & CEPH_OSD_FLAG_ONDISK));
+	req->r_version = m.user_version;
 	req->r_result = m.result ?: data_len;
 	finish_request(req);
 	mutex_unlock(&osd->lock);

From 4e8c4c235578b4d44bd6676df3a01dce98d0f7dd Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Thu, 25 Aug 2022 09:31:16 -0400
Subject: [PATCH 0638/1189] libceph: allow ceph_osdc_new_request to accept a
 multi-op read
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently we have some special-casing for multi-op writes, but in the
case of a read, we can't really handle it. All of the current multi-op
callers call it with CEPH_OSD_FLAG_WRITE set.

Have ceph_osdc_new_request check for CEPH_OSD_FLAG_READ and if it's set,
allocate multiple reply ops instead of multiple request ops. If neither
flag is set, return -EINVAL.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 net/ceph/osd_client.c | 27 +++++++++++++++++++++------
 1 file changed, 21 insertions(+), 6 deletions(-)

diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 7f159e40cf9c..d3a759e052c8 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1136,15 +1136,30 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 	if (flags & CEPH_OSD_FLAG_WRITE)
 		req->r_data_offset = off;
 
-	if (num_ops > 1)
+	if (num_ops > 1) {
+		int num_req_ops, num_rep_ops;
+
 		/*
-		 * This is a special case for ceph_writepages_start(), but it
-		 * also covers ceph_uninline_data().  If more multi-op request
-		 * use cases emerge, we will need a separate helper.
+		 * If this is a multi-op write request, assume that we'll need
+		 * request ops. If it's a multi-op read then assume we'll need
+		 * reply ops. Anything else and call it -EINVAL.
 		 */
-		r = __ceph_osdc_alloc_messages(req, GFP_NOFS, num_ops, 0);
-	else
+		if (flags & CEPH_OSD_FLAG_WRITE) {
+			num_req_ops = num_ops;
+			num_rep_ops = 0;
+		} else if (flags & CEPH_OSD_FLAG_READ) {
+			num_req_ops = 0;
+			num_rep_ops = num_ops;
+		} else {
+			r = -EINVAL;
+			goto fail;
+		}
+
+		r = __ceph_osdc_alloc_messages(req, GFP_NOFS, num_req_ops,
+					       num_rep_ops);
+	} else {
 		r = ceph_osdc_alloc_messages(req, GFP_NOFS);
+	}
 	if (r)
 		goto fail;
 

From d4d518871574ebbd53f054c16c085caa0a77b83d Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Thu, 25 Aug 2022 09:31:12 -0400
Subject: [PATCH 0639/1189] ceph: add object version support for sync read
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Turn the guts of ceph_sync_read into a new helper that takes an inode
and an offset instead of a kiocb struct, and make ceph_sync_read call
the helper as a wrapper.

Make the new helper always return the last object's version.

Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/file.c  | 44 ++++++++++++++++++++++++++++++++------------
 fs/ceph/super.h |  3 +++
 2 files changed, 35 insertions(+), 12 deletions(-)

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index c3ce224db032..24ee84f257fb 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -959,22 +959,24 @@ enum {
  * If we get a short result from the OSD, check against i_size; we need to
  * only return a short read to the caller if we hit EOF.
  */
-static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
-			      int *retry_op)
+ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
+			 struct iov_iter *to, int *retry_op,
+			 u64 *last_objver)
 {
-	struct file *file = iocb->ki_filp;
-	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	struct ceph_osd_client *osdc = &fsc->client->osdc;
 	ssize_t ret;
-	u64 off = iocb->ki_pos;
+	u64 off = *ki_pos;
 	u64 len = iov_iter_count(to);
 	u64 i_size = i_size_read(inode);
 	bool sparse = ceph_test_mount_opt(fsc, SPARSEREAD);
+	u64 objver = 0;
 
-	dout("sync_read on file %p %llu~%u %s\n", file, off, (unsigned)len,
-	     (file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
+	dout("sync_read on inode %p %llx~%llx\n", inode, *ki_pos, len);
+
+	if (ceph_inode_is_shutdown(inode))
+		return -EIO;
 
 	if (!len)
 		return 0;
@@ -1042,6 +1044,9 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
 					 req->r_end_latency,
 					 len, ret);
 
+		if (ret > 0)
+			objver = req->r_version;
+
 		i_size = i_size_read(inode);
 		dout("sync_read %llu~%llu got %zd i_size %llu%s\n",
 		     off, len, ret, i_size, (more ? " MORE" : ""));
@@ -1092,21 +1097,36 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
 			break;
 	}
 
-	if (off > iocb->ki_pos) {
+	if (off > *ki_pos) {
 		if (off >= i_size) {
 			*retry_op = CHECK_EOF;
-			ret = i_size - iocb->ki_pos;
-			iocb->ki_pos = i_size;
+			ret = i_size - *ki_pos;
+			*ki_pos = i_size;
 		} else {
-			ret = off - iocb->ki_pos;
-			iocb->ki_pos = off;
+			ret = off - *ki_pos;
+			*ki_pos = off;
 		}
 	}
 
+	if (last_objver && ret > 0)
+		*last_objver = objver;
+
 	dout("sync_read result %zd retry_op %d\n", ret, *retry_op);
 	return ret;
 }
 
+static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
+			      int *retry_op)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
+
+	dout("sync_read on file %p %llx~%zx %s\n", file, iocb->ki_pos,
+	     iov_iter_count(to), (file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
+
+	return __ceph_sync_read(inode, &iocb->ki_pos, to, retry_op, NULL);
+}
+
 struct ceph_aio_request {
 	struct kiocb *iocb;
 	size_t total_len;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 11483855897e..d60342cc6f33 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -1300,6 +1300,9 @@ extern int ceph_renew_caps(struct inode *inode, int fmode);
 extern int ceph_open(struct inode *inode, struct file *file);
 extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 			    struct file *file, unsigned flags, umode_t mode);
+extern ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
+				struct iov_iter *to, int *retry_op,
+				u64 *last_objver);
 extern int ceph_release(struct inode *inode, struct file *filp);
 extern void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
 				  char *data, size_t len);

From 5c64737d253683b7d138dde0da513a9ade16a170 Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Thu, 25 Aug 2022 09:31:11 -0400
Subject: [PATCH 0640/1189] ceph: add truncate size handling support for
 fscrypt
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This will transfer the encrypted last block contents to the MDS
along with the truncate request only when the new size is smaller
and not aligned to the fscrypt BLOCK size. When the last block is
located in the file hole, the truncate request will only contain
the header.

The MDS could fail to do the truncate if there has another client
or process has already updated the RADOS object which contains
the last block, and will return -EAGAIN, then the kclient needs
to retry it. The RMW will take around 50ms, and will let it retry
20 times for now.

Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/caps.c   |  18 +++--
 fs/ceph/crypto.h |  21 +++++
 fs/ceph/inode.c  | 200 +++++++++++++++++++++++++++++++++++++++++++++--
 fs/ceph/super.h  |   7 ++
 4 files changed, 234 insertions(+), 12 deletions(-)

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index ee61b539a8ec..5c2b28ac9410 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2960,10 +2960,9 @@ int ceph_try_get_caps(struct inode *inode, int need, int want,
  * due to a small max_size, make sure we check_max_size (and possibly
  * ask the mds) so we don't get hung up indefinitely.
  */
-int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got)
+int __ceph_get_caps(struct inode *inode, struct ceph_file_info *fi, int need,
+		    int want, loff_t endoff, int *got)
 {
-	struct ceph_file_info *fi = filp->private_data;
-	struct inode *inode = file_inode(filp);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	int ret, _got, flags;
@@ -2972,7 +2971,7 @@ int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got
 	if (ret < 0)
 		return ret;
 
-	if ((fi->fmode & CEPH_FILE_MODE_WR) &&
+	if (fi && (fi->fmode & CEPH_FILE_MODE_WR) &&
 	    fi->filp_gen != READ_ONCE(fsc->filp_gen))
 		return -EBADF;
 
@@ -3025,7 +3024,7 @@ int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got
 				continue;
 		}
 
-		if ((fi->fmode & CEPH_FILE_MODE_WR) &&
+		if (fi && (fi->fmode & CEPH_FILE_MODE_WR) &&
 		    fi->filp_gen != READ_ONCE(fsc->filp_gen)) {
 			if (ret >= 0 && _got)
 				ceph_put_cap_refs(ci, _got);
@@ -3088,6 +3087,15 @@ int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got
 	return 0;
 }
 
+int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff,
+		  int *got)
+{
+	struct ceph_file_info *fi = filp->private_data;
+	struct inode *inode = file_inode(filp);
+
+	return __ceph_get_caps(inode, fi, need, want, endoff, got);
+}
+
 /*
  * Take cap refs.  Caller must already know we hold at least one ref
  * on the caps in question or we don't know this is safe.
diff --git a/fs/ceph/crypto.h b/fs/ceph/crypto.h
index 7a03275f3ad5..b735b3f144a7 100644
--- a/fs/ceph/crypto.h
+++ b/fs/ceph/crypto.h
@@ -26,6 +26,27 @@ struct ceph_fname {
 	bool		no_copy;
 };
 
+/*
+ * Header for the crypted file when truncating the size, this
+ * will be sent to MDS, and the MDS will update the encrypted
+ * last block and then truncate the size.
+ */
+struct ceph_fscrypt_truncate_size_header {
+	__u8  ver;
+	__u8  compat;
+
+	/*
+	 * It will be sizeof(assert_ver + file_offset + block_size)
+	 * if the last block is empty when it's located in a file
+	 * hole. Or the data_len will plus CEPH_FSCRYPT_BLOCK_SIZE.
+	 */
+	__le32 data_len;
+
+	__le64 change_attr;
+	__le64 file_offset;
+	__le32 block_size;
+} __packed;
+
 struct ceph_fscrypt_auth {
 	__le32	cfa_version;
 	__le32	cfa_blob_len;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 841f60e8de6a..054fd66609b7 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -596,6 +596,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 	ci->i_truncate_seq = 0;
 	ci->i_truncate_size = 0;
 	ci->i_truncate_pending = 0;
+	ci->i_truncate_pagecache_size = 0;
 
 	ci->i_max_size = 0;
 	ci->i_reported_size = 0;
@@ -767,6 +768,10 @@ int ceph_fill_file_size(struct inode *inode, int issued,
 		dout("truncate_size %lld -> %llu\n", ci->i_truncate_size,
 		     truncate_size);
 		ci->i_truncate_size = truncate_size;
+		if (IS_ENCRYPTED(inode))
+			ci->i_truncate_pagecache_size = size;
+		else
+			ci->i_truncate_pagecache_size = truncate_size;
 	}
 	return queue_trunc;
 }
@@ -2147,7 +2152,7 @@ retry:
 	/* there should be no reader or writer */
 	WARN_ON_ONCE(ci->i_rd_ref || ci->i_wr_ref);
 
-	to = ci->i_truncate_size;
+	to = ci->i_truncate_pagecache_size;
 	wrbuffer_refs = ci->i_wrbuffer_ref;
 	dout("__do_pending_vmtruncate %p (%d) to %lld\n", inode,
 	     ci->i_truncate_pending, to);
@@ -2157,7 +2162,7 @@ retry:
 	truncate_pagecache(inode, to);
 
 	spin_lock(&ci->i_ceph_lock);
-	if (to == ci->i_truncate_size) {
+	if (to == ci->i_truncate_pagecache_size) {
 		ci->i_truncate_pending = 0;
 		finish = 1;
 	}
@@ -2241,6 +2246,144 @@ static const struct inode_operations ceph_encrypted_symlink_iops = {
 	.listxattr = ceph_listxattr,
 };
 
+/*
+ * Transfer the encrypted last block to the MDS and the MDS
+ * will help update it when truncating a smaller size.
+ *
+ * We don't support a PAGE_SIZE that is smaller than the
+ * CEPH_FSCRYPT_BLOCK_SIZE.
+ */
+static int fill_fscrypt_truncate(struct inode *inode,
+				 struct ceph_mds_request *req,
+				 struct iattr *attr)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	int boff = attr->ia_size % CEPH_FSCRYPT_BLOCK_SIZE;
+	loff_t pos, orig_pos = round_down(attr->ia_size,
+					  CEPH_FSCRYPT_BLOCK_SIZE);
+	u64 block = orig_pos >> CEPH_FSCRYPT_BLOCK_SHIFT;
+	struct ceph_pagelist *pagelist = NULL;
+	struct kvec iov = {0};
+	struct iov_iter iter;
+	struct page *page = NULL;
+	struct ceph_fscrypt_truncate_size_header header;
+	int retry_op = 0;
+	int len = CEPH_FSCRYPT_BLOCK_SIZE;
+	loff_t i_size = i_size_read(inode);
+	int got, ret, issued;
+	u64 objver;
+
+	ret = __ceph_get_caps(inode, NULL, CEPH_CAP_FILE_RD, 0, -1, &got);
+	if (ret < 0)
+		return ret;
+
+	issued = __ceph_caps_issued(ci, NULL);
+
+	dout("%s size %lld -> %lld got cap refs on %s, issued %s\n", __func__,
+	     i_size, attr->ia_size, ceph_cap_string(got),
+	     ceph_cap_string(issued));
+
+	/* Try to writeback the dirty pagecaches */
+	if (issued & (CEPH_CAP_FILE_BUFFER)) {
+		loff_t lend = orig_pos + CEPH_FSCRYPT_BLOCK_SHIFT - 1;
+
+		ret = filemap_write_and_wait_range(inode->i_mapping,
+						   orig_pos, lend);
+		if (ret < 0)
+			goto out;
+	}
+
+	page = __page_cache_alloc(GFP_KERNEL);
+	if (page == NULL) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	pagelist = ceph_pagelist_alloc(GFP_KERNEL);
+	if (!pagelist) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	iov.iov_base = kmap_local_page(page);
+	iov.iov_len = len;
+	iov_iter_kvec(&iter, READ, &iov, 1, len);
+
+	pos = orig_pos;
+	ret = __ceph_sync_read(inode, &pos, &iter, &retry_op, &objver);
+	if (ret < 0)
+		goto out;
+
+	/* Insert the header first */
+	header.ver = 1;
+	header.compat = 1;
+	header.change_attr = cpu_to_le64(inode_peek_iversion_raw(inode));
+
+	/*
+	 * Always set the block_size to CEPH_FSCRYPT_BLOCK_SIZE,
+	 * because in MDS it may need this to do the truncate.
+	 */
+	header.block_size = cpu_to_le32(CEPH_FSCRYPT_BLOCK_SIZE);
+
+	/*
+	 * If we hit a hole here, we should just skip filling
+	 * the fscrypt for the request, because once the fscrypt
+	 * is enabled, the file will be split into many blocks
+	 * with the size of CEPH_FSCRYPT_BLOCK_SIZE, if there
+	 * has a hole, the hole size should be multiple of block
+	 * size.
+	 *
+	 * If the Rados object doesn't exist, it will be set to 0.
+	 */
+	if (!objver) {
+		dout("%s hit hole, ppos %lld < size %lld\n", __func__,
+		     pos, i_size);
+
+		header.data_len = cpu_to_le32(8 + 8 + 4);
+		header.file_offset = 0;
+		ret = 0;
+	} else {
+		header.data_len = cpu_to_le32(8 + 8 + 4 + CEPH_FSCRYPT_BLOCK_SIZE);
+		header.file_offset = cpu_to_le64(orig_pos);
+
+		/* truncate and zero out the extra contents for the last block */
+		memset(iov.iov_base + boff, 0, PAGE_SIZE - boff);
+
+		/* encrypt the last block */
+		ret = ceph_fscrypt_encrypt_block_inplace(inode, page,
+						    CEPH_FSCRYPT_BLOCK_SIZE,
+						    0, block,
+						    GFP_KERNEL);
+		if (ret)
+			goto out;
+	}
+
+	/* Insert the header */
+	ret = ceph_pagelist_append(pagelist, &header, sizeof(header));
+	if (ret)
+		goto out;
+
+	if (header.block_size) {
+		/* Append the last block contents to pagelist */
+		ret = ceph_pagelist_append(pagelist, iov.iov_base,
+					   CEPH_FSCRYPT_BLOCK_SIZE);
+		if (ret)
+			goto out;
+	}
+	req->r_pagelist = pagelist;
+out:
+	dout("%s %p size dropping cap refs on %s\n", __func__,
+	     inode, ceph_cap_string(got));
+	ceph_put_cap_refs(ci, got);
+	if (iov.iov_base)
+		kunmap_local(iov.iov_base);
+	if (page)
+		__free_pages(page, 0);
+	if (ret && pagelist)
+		ceph_pagelist_release(pagelist);
+	return ret;
+}
+
 int __ceph_setattr(struct inode *inode, struct iattr *attr,
 		   struct ceph_iattr *cia)
 {
@@ -2249,13 +2392,17 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr,
 	struct ceph_mds_request *req;
 	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
 	struct ceph_cap_flush *prealloc_cf;
+	loff_t isize = i_size_read(inode);
 	int issued;
 	int release = 0, dirtied = 0;
 	int mask = 0;
 	int err = 0;
 	int inode_dirty_flags = 0;
 	bool lock_snap_rwsem = false;
+	bool fill_fscrypt;
+	int truncate_retry = 20; /* The RMW will take around 50ms */
 
+retry:
 	prealloc_cf = ceph_alloc_cap_flush();
 	if (!prealloc_cf)
 		return -ENOMEM;
@@ -2267,6 +2414,7 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr,
 		return PTR_ERR(req);
 	}
 
+	fill_fscrypt = false;
 	spin_lock(&ci->i_ceph_lock);
 	issued = __ceph_caps_issued(ci, NULL);
 
@@ -2388,10 +2536,27 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr,
 		}
 	}
 	if (ia_valid & ATTR_SIZE) {
-		loff_t isize = i_size_read(inode);
-
 		dout("setattr %p size %lld -> %lld\n", inode, isize, attr->ia_size);
-		if ((issued & CEPH_CAP_FILE_EXCL) && attr->ia_size >= isize) {
+		/*
+		 * Only when the new size is smaller and not aligned to
+		 * CEPH_FSCRYPT_BLOCK_SIZE will the RMW is needed.
+		 */
+		if (IS_ENCRYPTED(inode) && attr->ia_size < isize &&
+		    (attr->ia_size % CEPH_FSCRYPT_BLOCK_SIZE)) {
+			mask |= CEPH_SETATTR_SIZE;
+			release |= CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_EXCL |
+				   CEPH_CAP_FILE_RD | CEPH_CAP_FILE_WR;
+			set_bit(CEPH_MDS_R_FSCRYPT_FILE, &req->r_req_flags);
+			mask |= CEPH_SETATTR_FSCRYPT_FILE;
+			req->r_args.setattr.size =
+				cpu_to_le64(round_up(attr->ia_size,
+						     CEPH_FSCRYPT_BLOCK_SIZE));
+			req->r_args.setattr.old_size =
+				cpu_to_le64(round_up(isize,
+						     CEPH_FSCRYPT_BLOCK_SIZE));
+			req->r_fscrypt_file = attr->ia_size;
+			fill_fscrypt = true;
+		} else if ((issued & CEPH_CAP_FILE_EXCL) && attr->ia_size >= isize) {
 			if (attr->ia_size > isize) {
 				i_size_write(inode, attr->ia_size);
 				inode->i_blocks = calc_inode_blocks(attr->ia_size);
@@ -2414,7 +2579,6 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr,
 					cpu_to_le64(round_up(isize,
 							     CEPH_FSCRYPT_BLOCK_SIZE));
 				req->r_fscrypt_file = attr->ia_size;
-				/* FIXME: client must zero out any partial blocks! */
 			} else {
 				req->r_args.setattr.size = cpu_to_le64(attr->ia_size);
 				req->r_args.setattr.old_size = cpu_to_le64(isize);
@@ -2481,8 +2645,10 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr,
 
 	release &= issued;
 	spin_unlock(&ci->i_ceph_lock);
-	if (lock_snap_rwsem)
+	if (lock_snap_rwsem) {
 		up_read(&mdsc->snap_rwsem);
+		lock_snap_rwsem = false;
+	}
 
 	if (inode_dirty_flags)
 		__mark_inode_dirty(inode, inode_dirty_flags);
@@ -2494,7 +2660,27 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr,
 		req->r_args.setattr.mask = cpu_to_le32(mask);
 		req->r_num_caps = 1;
 		req->r_stamp = attr->ia_ctime;
+		if (fill_fscrypt) {
+			err = fill_fscrypt_truncate(inode, req, attr);
+			if (err)
+				goto out;
+		}
+
+		/*
+		 * The truncate request will return -EAGAIN when the
+		 * last block has been updated just before the MDS
+		 * successfully gets the xlock for the FILE lock. To
+		 * avoid corrupting the file contents we need to retry
+		 * it.
+		 */
 		err = ceph_mdsc_do_request(mdsc, NULL, req);
+		if (err == -EAGAIN && truncate_retry--) {
+			dout("setattr %p result=%d (%s locally, %d remote), retry it!\n",
+			     inode, err, ceph_cap_string(dirtied), mask);
+			ceph_mdsc_put_request(req);
+			ceph_free_cap_flush(prealloc_cf);
+			goto retry;
+		}
 	}
 out:
 	dout("setattr %p result=%d (%s locally, %d remote)\n", inode, err,
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index d60342cc6f33..b5e54c8f010b 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -424,6 +424,11 @@ struct ceph_inode_info {
 	u32 i_truncate_seq;        /* last truncate to smaller size */
 	u64 i_truncate_size;       /*  and the size we last truncated down to */
 	int i_truncate_pending;    /*  still need to call vmtruncate */
+	/*
+	 * For none fscrypt case it equals to i_truncate_size or it will
+	 * equals to fscrypt_file_size
+	 */
+	u64 i_truncate_pagecache_size;
 
 	u64 i_max_size;            /* max file size authorized by mds */
 	u64 i_reported_size; /* (max_)size reported to or requested of mds */
@@ -1265,6 +1270,8 @@ extern int ceph_encode_dentry_release(void **p, struct dentry *dn,
 				      struct inode *dir,
 				      int mds, int drop, int unless);
 
+extern int __ceph_get_caps(struct inode *inode, struct ceph_file_info *fi,
+			   int need, int want, loff_t endoff, int *got);
 extern int ceph_get_caps(struct file *filp, int need, int want,
 			 loff_t endoff, int *got);
 extern int ceph_try_get_caps(struct inode *inode,

From 8cff8f5374c7974ab9b9726c5b7c50f10466047e Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Thu, 25 Aug 2022 09:31:19 -0400
Subject: [PATCH 0641/1189] ceph: don't use special DIO path for encrypted
 inodes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Eventually I want to merge the synchronous and direct read codepaths,
possibly via new netfs infrastructure. For now, the direct path is not
crypto-enabled, so use the sync read/write paths instead.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/file.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 24ee84f257fb..f4c3da5b38fe 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1738,7 +1738,9 @@ again:
 		     ceph_cap_string(got));
 
 		if (!ceph_has_inline_data(ci)) {
-			if (!retry_op && (iocb->ki_flags & IOCB_DIRECT)) {
+			if (!retry_op &&
+			    (iocb->ki_flags & IOCB_DIRECT) &&
+			    !IS_ENCRYPTED(inode)) {
 				ret = ceph_direct_read_write(iocb, to,
 							     NULL, NULL);
 				if (ret >= 0 && ret < len)
@@ -2024,7 +2026,7 @@ retry_snap:
 
 		/* we might need to revert back to that point */
 		data = *from;
-		if (iocb->ki_flags & IOCB_DIRECT)
+		if ((iocb->ki_flags & IOCB_DIRECT) && !IS_ENCRYPTED(inode))
 			written = ceph_direct_read_write(iocb, &data, snapc,
 							 &prealloc_cf);
 		else

From b294fa295ff47a1fdf4db5e8c9275cc7af328c5e Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Thu, 25 Aug 2022 09:31:20 -0400
Subject: [PATCH 0642/1189] ceph: align data in pages in ceph_sync_write
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Encrypted files will need to be dealt with in block-sized chunks and
once we do that, the way that ceph_sync_write aligns the data in the
bounce buffer won't be acceptable.

Change it to align the data the same way it would be aligned in the
pagecache.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/file.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index f4c3da5b38fe..0abe36379fdf 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1582,6 +1582,7 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 	bool check_caps = false;
 	struct timespec64 mtime = current_time(inode);
 	size_t count = iov_iter_count(from);
+	size_t off;
 
 	if (ceph_snap(file_inode(file)) != CEPH_NOSNAP)
 		return -EROFS;
@@ -1619,12 +1620,7 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 			break;
 		}
 
-		/*
-		 * write from beginning of first page,
-		 * regardless of io alignment
-		 */
-		num_pages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
-
+		num_pages = calc_pages_for(pos, len);
 		pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL);
 		if (IS_ERR(pages)) {
 			ret = PTR_ERR(pages);
@@ -1632,9 +1628,12 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 		}
 
 		left = len;
+		off = offset_in_page(pos);
 		for (n = 0; n < num_pages; n++) {
-			size_t plen = min_t(size_t, left, PAGE_SIZE);
-			ret = copy_page_from_iter(pages[n], 0, plen, from);
+			size_t plen = min_t(size_t, left, PAGE_SIZE - off);
+
+			ret = copy_page_from_iter(pages[n], off, plen, from);
+			off = 0;
 			if (ret != plen) {
 				ret = -EFAULT;
 				break;
@@ -1649,8 +1648,9 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 
 		req->r_inode = inode;
 
-		osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0,
-						false, true);
+		osd_req_op_extent_osd_data_pages(req, 0, pages, len,
+						 offset_in_page(pos),
+						 false, true);
 
 		req->r_mtime = mtime;
 		ceph_osdc_start_request(&fsc->client->osdc, req);

From 33a5f1709a44efa7253b84832fe4a49fccf4924b Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Thu, 25 Aug 2022 09:31:21 -0400
Subject: [PATCH 0643/1189] ceph: add read/modify/write to ceph_sync_write
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When doing a synchronous write on an encrypted inode, we have no
guarantee that the caller is writing crypto block-aligned data. When
that happens, we must do a read/modify/write cycle.

First, expand the range to cover complete blocks. If we had to change
the original pos or length, issue a read to fill the first and/or last
pages, and fetch the version of the object from the result.

We then copy data into the pages as usual, encrypt the result and issue
a write prefixed by an assertion that the version hasn't changed. If it has
changed then we restart the whole thing again.

If there is no object at that position in the file (-ENOENT), we prefix
the write on an exclusive create of the object instead.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/file.c | 320 ++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 291 insertions(+), 29 deletions(-)

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 0abe36379fdf..45e00e42960b 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1571,18 +1571,16 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
-	struct ceph_vino vino;
+	struct ceph_osd_client *osdc = &fsc->client->osdc;
 	struct ceph_osd_request *req;
 	struct page **pages;
 	u64 len;
 	int num_pages;
 	int written = 0;
-	int flags;
 	int ret;
 	bool check_caps = false;
 	struct timespec64 mtime = current_time(inode);
 	size_t count = iov_iter_count(from);
-	size_t off;
 
 	if (ceph_snap(file_inode(file)) != CEPH_NOSNAP)
 		return -EROFS;
@@ -1602,29 +1600,235 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 	if (ret < 0)
 		dout("invalidate_inode_pages2_range returned %d\n", ret);
 
-	flags = /* CEPH_OSD_FLAG_ORDERSNAP | */ CEPH_OSD_FLAG_WRITE;
-
 	while ((len = iov_iter_count(from)) > 0) {
 		size_t left;
 		int n;
+		u64 write_pos = pos;
+		u64 write_len = len;
+		u64 objnum, objoff;
+		u32 xlen;
+		u64 assert_ver = 0;
+		bool rmw;
+		bool first, last;
+		struct iov_iter saved_iter = *from;
+		size_t off;
 
-		vino = ceph_vino(inode);
-		req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
-					    vino, pos, &len, 0, 1,
-					    CEPH_OSD_OP_WRITE, flags, snapc,
-					    ci->i_truncate_seq,
-					    ci->i_truncate_size,
-					    false);
-		if (IS_ERR(req)) {
-			ret = PTR_ERR(req);
-			break;
-		}
+		ceph_fscrypt_adjust_off_and_len(inode, &write_pos, &write_len);
 
-		num_pages = calc_pages_for(pos, len);
+		/* clamp the length to the end of first object */
+		ceph_calc_file_object_mapping(&ci->i_layout, write_pos,
+					      write_len, &objnum, &objoff,
+					      &xlen);
+		write_len = xlen;
+
+		/* adjust len downward if it goes beyond current object */
+		if (pos + len > write_pos + write_len)
+			len = write_pos + write_len - pos;
+
+		/*
+		 * If we had to adjust the length or position to align with a
+		 * crypto block, then we must do a read/modify/write cycle. We
+		 * use a version assertion to redrive the thing if something
+		 * changes in between.
+		 */
+		first = pos != write_pos;
+		last = (pos + len) != (write_pos + write_len);
+		rmw = first || last;
+
+		dout("sync_write ino %llx %lld~%llu adjusted %lld~%llu -- %srmw\n",
+		     ci->i_vino.ino, pos, len, write_pos, write_len,
+		     rmw ? "" : "no ");
+
+		/*
+		 * The data is emplaced into the page as it would be if it were
+		 * in an array of pagecache pages.
+		 */
+		num_pages = calc_pages_for(write_pos, write_len);
 		pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL);
 		if (IS_ERR(pages)) {
 			ret = PTR_ERR(pages);
-			goto out;
+			break;
+		}
+
+		/* Do we need to preload the pages? */
+		if (rmw) {
+			u64 first_pos = write_pos;
+			u64 last_pos = (write_pos + write_len) - CEPH_FSCRYPT_BLOCK_SIZE;
+			u64 read_len = CEPH_FSCRYPT_BLOCK_SIZE;
+			struct ceph_osd_req_op *op;
+
+			/* We should only need to do this for encrypted inodes */
+			WARN_ON_ONCE(!IS_ENCRYPTED(inode));
+
+			/* No need to do two reads if first and last blocks are same */
+			if (first && last_pos == first_pos)
+				last = false;
+
+			/*
+			 * Allocate a read request for one or two extents,
+			 * depending on how the request was aligned.
+			 */
+			req = ceph_osdc_new_request(osdc, &ci->i_layout,
+					ci->i_vino, first ? first_pos : last_pos,
+					&read_len, 0, (first && last) ? 2 : 1,
+					CEPH_OSD_OP_SPARSE_READ, CEPH_OSD_FLAG_READ,
+					NULL, ci->i_truncate_seq,
+					ci->i_truncate_size, false);
+			if (IS_ERR(req)) {
+				ceph_release_page_vector(pages, num_pages);
+				ret = PTR_ERR(req);
+				break;
+			}
+
+			/* Something is misaligned! */
+			if (read_len != CEPH_FSCRYPT_BLOCK_SIZE) {
+				ceph_osdc_put_request(req);
+				ceph_release_page_vector(pages, num_pages);
+				ret = -EIO;
+				break;
+			}
+
+			/* Add extent for first block? */
+			op = &req->r_ops[0];
+
+			if (first) {
+				osd_req_op_extent_osd_data_pages(req, 0, pages,
+							 CEPH_FSCRYPT_BLOCK_SIZE,
+							 offset_in_page(first_pos),
+							 false, false);
+				/* We only expect a single extent here */
+				ret = __ceph_alloc_sparse_ext_map(op, 1);
+				if (ret) {
+					ceph_osdc_put_request(req);
+					ceph_release_page_vector(pages, num_pages);
+					break;
+				}
+			}
+
+			/* Add extent for last block */
+			if (last) {
+				/* Init the other extent if first extent has been used */
+				if (first) {
+					op = &req->r_ops[1];
+					osd_req_op_extent_init(req, 1,
+							CEPH_OSD_OP_SPARSE_READ,
+							last_pos, CEPH_FSCRYPT_BLOCK_SIZE,
+							ci->i_truncate_size,
+							ci->i_truncate_seq);
+				}
+
+				ret = __ceph_alloc_sparse_ext_map(op, 1);
+				if (ret) {
+					ceph_osdc_put_request(req);
+					ceph_release_page_vector(pages, num_pages);
+					break;
+				}
+
+				osd_req_op_extent_osd_data_pages(req, first ? 1 : 0,
+							&pages[num_pages - 1],
+							CEPH_FSCRYPT_BLOCK_SIZE,
+							offset_in_page(last_pos),
+							false, false);
+			}
+
+			ceph_osdc_start_request(osdc, req);
+			ret = ceph_osdc_wait_request(osdc, req);
+
+			/* FIXME: length field is wrong if there are 2 extents */
+			ceph_update_read_metrics(&fsc->mdsc->metric,
+						 req->r_start_latency,
+						 req->r_end_latency,
+						 read_len, ret);
+
+			/* Ok if object is not already present */
+			if (ret == -ENOENT) {
+				/*
+				 * If there is no object, then we can't assert
+				 * on its version. Set it to 0, and we'll use an
+				 * exclusive create instead.
+				 */
+				ceph_osdc_put_request(req);
+				ret = 0;
+
+				/*
+				 * zero out the soon-to-be uncopied parts of the
+				 * first and last pages.
+				 */
+				if (first)
+					zero_user_segment(pages[0], 0,
+							  offset_in_page(first_pos));
+				if (last)
+					zero_user_segment(pages[num_pages - 1],
+							  offset_in_page(last_pos),
+							  PAGE_SIZE);
+			} else {
+				if (ret < 0) {
+					ceph_osdc_put_request(req);
+					ceph_release_page_vector(pages, num_pages);
+					break;
+				}
+
+				op = &req->r_ops[0];
+				if (op->extent.sparse_ext_cnt == 0) {
+					if (first)
+						zero_user_segment(pages[0], 0,
+								  offset_in_page(first_pos));
+					else
+						zero_user_segment(pages[num_pages - 1],
+								  offset_in_page(last_pos),
+								  PAGE_SIZE);
+				} else if (op->extent.sparse_ext_cnt != 1 ||
+					   ceph_sparse_ext_map_end(op) !=
+						CEPH_FSCRYPT_BLOCK_SIZE) {
+					ret = -EIO;
+					ceph_osdc_put_request(req);
+					ceph_release_page_vector(pages, num_pages);
+					break;
+				}
+
+				if (first && last) {
+					op = &req->r_ops[1];
+					if (op->extent.sparse_ext_cnt == 0) {
+						zero_user_segment(pages[num_pages - 1],
+								  offset_in_page(last_pos),
+								  PAGE_SIZE);
+					} else if (op->extent.sparse_ext_cnt != 1 ||
+						   ceph_sparse_ext_map_end(op) !=
+							CEPH_FSCRYPT_BLOCK_SIZE) {
+						ret = -EIO;
+						ceph_osdc_put_request(req);
+						ceph_release_page_vector(pages, num_pages);
+						break;
+					}
+				}
+
+				/* Grab assert version. It must be non-zero. */
+				assert_ver = req->r_version;
+				WARN_ON_ONCE(ret > 0 && assert_ver == 0);
+
+				ceph_osdc_put_request(req);
+				if (first) {
+					ret = ceph_fscrypt_decrypt_block_inplace(inode,
+							pages[0], CEPH_FSCRYPT_BLOCK_SIZE,
+							offset_in_page(first_pos),
+							first_pos >> CEPH_FSCRYPT_BLOCK_SHIFT);
+					if (ret < 0) {
+						ceph_release_page_vector(pages, num_pages);
+						break;
+					}
+				}
+				if (last) {
+					ret = ceph_fscrypt_decrypt_block_inplace(inode,
+							pages[num_pages - 1],
+							CEPH_FSCRYPT_BLOCK_SIZE,
+							offset_in_page(last_pos),
+							last_pos >> CEPH_FSCRYPT_BLOCK_SHIFT);
+					if (ret < 0) {
+						ceph_release_page_vector(pages, num_pages);
+						break;
+					}
+				}
+			}
 		}
 
 		left = len;
@@ -1632,35 +1836,91 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 		for (n = 0; n < num_pages; n++) {
 			size_t plen = min_t(size_t, left, PAGE_SIZE - off);
 
+			/* copy the data */
 			ret = copy_page_from_iter(pages[n], off, plen, from);
-			off = 0;
 			if (ret != plen) {
 				ret = -EFAULT;
 				break;
 			}
+			off = 0;
 			left -= ret;
 		}
-
 		if (ret < 0) {
+			dout("sync_write write failed with %d\n", ret);
 			ceph_release_page_vector(pages, num_pages);
-			goto out;
+			break;
 		}
 
+		if (IS_ENCRYPTED(inode)) {
+			ret = ceph_fscrypt_encrypt_pages(inode, pages,
+							 write_pos, write_len,
+							 GFP_KERNEL);
+			if (ret < 0) {
+				dout("encryption failed with %d\n", ret);
+				ceph_release_page_vector(pages, num_pages);
+				break;
+			}
+		}
+
+		req = ceph_osdc_new_request(osdc, &ci->i_layout,
+					    ci->i_vino, write_pos, &write_len,
+					    rmw ? 1 : 0, rmw ? 2 : 1,
+					    CEPH_OSD_OP_WRITE,
+					    CEPH_OSD_FLAG_WRITE,
+					    snapc, ci->i_truncate_seq,
+					    ci->i_truncate_size, false);
+		if (IS_ERR(req)) {
+			ret = PTR_ERR(req);
+			ceph_release_page_vector(pages, num_pages);
+			break;
+		}
+
+		dout("sync_write write op %lld~%llu\n", write_pos, write_len);
+		osd_req_op_extent_osd_data_pages(req, rmw ? 1 : 0, pages, write_len,
+						 offset_in_page(write_pos), false,
+						 true);
 		req->r_inode = inode;
-
-		osd_req_op_extent_osd_data_pages(req, 0, pages, len,
-						 offset_in_page(pos),
-						 false, true);
-
 		req->r_mtime = mtime;
-		ceph_osdc_start_request(&fsc->client->osdc, req);
-		ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
+
+		/* Set up the assertion */
+		if (rmw) {
+			/*
+			 * Set up the assertion. If we don't have a version
+			 * number, then the object doesn't exist yet. Use an
+			 * exclusive create instead of a version assertion in
+			 * that case.
+			 */
+			if (assert_ver) {
+				osd_req_op_init(req, 0, CEPH_OSD_OP_ASSERT_VER, 0);
+				req->r_ops[0].assert_ver.ver = assert_ver;
+			} else {
+				osd_req_op_init(req, 0, CEPH_OSD_OP_CREATE,
+						CEPH_OSD_OP_FLAG_EXCL);
+			}
+		}
+
+		ceph_osdc_start_request(osdc, req);
+		ret = ceph_osdc_wait_request(osdc, req);
 
 		ceph_update_write_metrics(&fsc->mdsc->metric, req->r_start_latency,
 					  req->r_end_latency, len, ret);
-out:
 		ceph_osdc_put_request(req);
 		if (ret != 0) {
+			dout("sync_write osd write returned %d\n", ret);
+			/* Version changed! Must re-do the rmw cycle */
+			if ((assert_ver && (ret == -ERANGE || ret == -EOVERFLOW)) ||
+			    (!assert_ver && ret == -EEXIST)) {
+				/* We should only ever see this on a rmw */
+				WARN_ON_ONCE(!rmw);
+
+				/* The version should never go backward */
+				WARN_ON_ONCE(ret == -EOVERFLOW);
+
+				*from = saved_iter;
+
+				/* FIXME: limit number of times we loop? */
+				continue;
+			}
 			ceph_set_error_write(ci);
 			break;
 		}
@@ -1668,6 +1928,7 @@ out:
 		ceph_clear_error_write(ci);
 		pos += len;
 		written += len;
+		dout("sync_write written %d\n", written);
 		if (pos > i_size_read(inode)) {
 			check_caps = ceph_inode_set_size(inode, pos);
 			if (check_caps)
@@ -1681,6 +1942,7 @@ out:
 		ret = written;
 		iocb->ki_pos = pos;
 	}
+	dout("sync_write returning %d\n", ret);
 	return ret;
 }
 

From d55207717ded95c8f2760a30e93319fa313186e6 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Thu, 25 Aug 2022 09:31:25 -0400
Subject: [PATCH 0644/1189] ceph: add encryption support to writepage and
 writepages
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Allow writepage to issue encrypted writes. Extend out the requested size
and offset to cover complete blocks, and then encrypt and write them to
the OSDs.

Add the appropriate machinery to write back dirty data with encryption.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/addr.c   | 101 +++++++++++++++++++++++++++++++++++++----------
 fs/ceph/crypto.h |  18 ++++++++-
 2 files changed, 98 insertions(+), 21 deletions(-)

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 611443d06330..89ca27848325 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -565,10 +565,12 @@ static u64 get_writepages_data_length(struct inode *inode,
 				      struct page *page, u64 start)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_snap_context *snapc = page_snap_context(page);
+	struct ceph_snap_context *snapc;
 	struct ceph_cap_snap *capsnap = NULL;
 	u64 end = i_size_read(inode);
+	u64 ret;
 
+	snapc = page_snap_context(ceph_fscrypt_pagecache_page(page));
 	if (snapc != ci->i_head_snapc) {
 		bool found = false;
 		spin_lock(&ci->i_ceph_lock);
@@ -583,9 +585,12 @@ static u64 get_writepages_data_length(struct inode *inode,
 		spin_unlock(&ci->i_ceph_lock);
 		WARN_ON(!found);
 	}
-	if (end > page_offset(page) + thp_size(page))
-		end = page_offset(page) + thp_size(page);
-	return end > start ? end - start : 0;
+	if (end > ceph_fscrypt_page_offset(page) + thp_size(page))
+		end = ceph_fscrypt_page_offset(page) + thp_size(page);
+	ret = end > start ? end - start : 0;
+	if (ret && fscrypt_is_bounce_page(page))
+		ret = round_up(ret, CEPH_FSCRYPT_BLOCK_SIZE);
+	return ret;
 }
 
 /*
@@ -604,10 +609,12 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	loff_t page_off = page_offset(page);
 	int err;
 	loff_t len = thp_size(page);
+	loff_t wlen;
 	struct ceph_writeback_ctl ceph_wbc;
 	struct ceph_osd_client *osdc = &fsc->client->osdc;
 	struct ceph_osd_request *req;
 	bool caching = ceph_is_cache_enabled(inode);
+	struct page *bounce_page = NULL;
 
 	dout("writepage %p idx %lu\n", page, page->index);
 
@@ -643,31 +650,51 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	if (ceph_wbc.i_size < page_off + len)
 		len = ceph_wbc.i_size - page_off;
 
+	wlen = IS_ENCRYPTED(inode) ? round_up(len, CEPH_FSCRYPT_BLOCK_SIZE) : len;
 	dout("writepage %p page %p index %lu on %llu~%llu snapc %p seq %lld\n",
-	     inode, page, page->index, page_off, len, snapc, snapc->seq);
+	     inode, page, page->index, page_off, wlen, snapc, snapc->seq);
 
 	if (atomic_long_inc_return(&fsc->writeback_count) >
 	    CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))
 		fsc->write_congested = true;
 
-	req = ceph_osdc_new_request(osdc, &ci->i_layout, ceph_vino(inode), page_off, &len, 0, 1,
-				    CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE, snapc,
-				    ceph_wbc.truncate_seq, ceph_wbc.truncate_size,
-				    true);
+	req = ceph_osdc_new_request(osdc, &ci->i_layout, ceph_vino(inode),
+				    page_off, &wlen, 0, 1, CEPH_OSD_OP_WRITE,
+				    CEPH_OSD_FLAG_WRITE, snapc,
+				    ceph_wbc.truncate_seq,
+				    ceph_wbc.truncate_size, true);
 	if (IS_ERR(req)) {
 		redirty_page_for_writepage(wbc, page);
 		return PTR_ERR(req);
 	}
 
+	if (wlen < len)
+		len = wlen;
+
 	set_page_writeback(page);
 	if (caching)
 		ceph_set_page_fscache(page);
 	ceph_fscache_write_to_cache(inode, page_off, len, caching);
 
+	if (IS_ENCRYPTED(inode)) {
+		bounce_page = fscrypt_encrypt_pagecache_blocks(page,
+						    CEPH_FSCRYPT_BLOCK_SIZE, 0,
+						    GFP_NOFS);
+		if (IS_ERR(bounce_page)) {
+			redirty_page_for_writepage(wbc, page);
+			end_page_writeback(page);
+			ceph_osdc_put_request(req);
+			return PTR_ERR(bounce_page);
+		}
+	}
+
 	/* it may be a short write due to an object boundary */
 	WARN_ON_ONCE(len > thp_size(page));
-	osd_req_op_extent_osd_data_pages(req, 0, &page, len, 0, false, false);
-	dout("writepage %llu~%llu (%llu bytes)\n", page_off, len, len);
+	osd_req_op_extent_osd_data_pages(req, 0,
+			bounce_page ? &bounce_page : &page, wlen, 0,
+			false, false);
+	dout("writepage %llu~%llu (%llu bytes, %sencrypted)\n",
+	     page_off, len, wlen, IS_ENCRYPTED(inode) ? "" : "not ");
 
 	req->r_mtime = inode->i_mtime;
 	ceph_osdc_start_request(osdc, req);
@@ -675,7 +702,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 
 	ceph_update_write_metrics(&fsc->mdsc->metric, req->r_start_latency,
 				  req->r_end_latency, len, err);
-
+	fscrypt_free_bounce_page(bounce_page);
 	ceph_osdc_put_request(req);
 	if (err == 0)
 		err = len;
@@ -794,6 +821,11 @@ static void writepages_finish(struct ceph_osd_request *req)
 		total_pages += num_pages;
 		for (j = 0; j < num_pages; j++) {
 			page = osd_data->pages[j];
+			if (fscrypt_is_bounce_page(page)) {
+				page = fscrypt_pagecache_page(page);
+				fscrypt_free_bounce_page(osd_data->pages[j]);
+				osd_data->pages[j] = page;
+			}
 			BUG_ON(!page);
 			WARN_ON(!PageUptodate(page));
 
@@ -1064,9 +1096,28 @@ get_more_pages:
 				    fsc->mount_options->congestion_kb))
 				fsc->write_congested = true;
 
-			pages[locked_pages++] = page;
-			fbatch.folios[i] = NULL;
+			if (IS_ENCRYPTED(inode)) {
+				pages[locked_pages] =
+					fscrypt_encrypt_pagecache_blocks(page,
+						PAGE_SIZE, 0,
+						locked_pages ? GFP_NOWAIT : GFP_NOFS);
+				if (IS_ERR(pages[locked_pages])) {
+					if (PTR_ERR(pages[locked_pages]) == -EINVAL)
+						pr_err("%s: inode->i_blkbits=%hhu\n",
+							__func__, inode->i_blkbits);
+					/* better not fail on first page! */
+					BUG_ON(locked_pages == 0);
+					pages[locked_pages] = NULL;
+					redirty_page_for_writepage(wbc, page);
+					unlock_page(page);
+					break;
+				}
+				++locked_pages;
+			} else {
+				pages[locked_pages++] = page;
+			}
 
+			fbatch.folios[i] = NULL;
 			len += thp_size(page);
 		}
 
@@ -1094,7 +1145,7 @@ get_more_pages:
 		}
 
 new_request:
-		offset = page_offset(pages[0]);
+		offset = ceph_fscrypt_page_offset(pages[0]);
 		len = wsize;
 
 		req = ceph_osdc_new_request(&fsc->client->osdc,
@@ -1115,8 +1166,8 @@ new_request:
 						ceph_wbc.truncate_size, true);
 			BUG_ON(IS_ERR(req));
 		}
-		BUG_ON(len < page_offset(pages[locked_pages - 1]) +
-			     thp_size(page) - offset);
+		BUG_ON(len < ceph_fscrypt_page_offset(pages[locked_pages - 1]) +
+			     thp_size(pages[locked_pages - 1]) - offset);
 
 		req->r_callback = writepages_finish;
 		req->r_inode = inode;
@@ -1126,7 +1177,9 @@ new_request:
 		data_pages = pages;
 		op_idx = 0;
 		for (i = 0; i < locked_pages; i++) {
-			u64 cur_offset = page_offset(pages[i]);
+			struct page *page = ceph_fscrypt_pagecache_page(pages[i]);
+
+			u64 cur_offset = page_offset(page);
 			/*
 			 * Discontinuity in page range? Ceph can handle that by just passing
 			 * multiple extents in the write op.
@@ -1155,9 +1208,9 @@ new_request:
 				op_idx++;
 			}
 
-			set_page_writeback(pages[i]);
+			set_page_writeback(page);
 			if (caching)
-				ceph_set_page_fscache(pages[i]);
+				ceph_set_page_fscache(page);
 			len += thp_size(page);
 		}
 		ceph_fscache_write_to_cache(inode, offset, len, caching);
@@ -1173,8 +1226,16 @@ new_request:
 							 offset);
 			len = max(len, min_len);
 		}
+		if (IS_ENCRYPTED(inode))
+			len = round_up(len, CEPH_FSCRYPT_BLOCK_SIZE);
+
 		dout("writepages got pages at %llu~%llu\n", offset, len);
 
+		if (IS_ENCRYPTED(inode) &&
+		    ((offset | len) & ~CEPH_FSCRYPT_BLOCK_MASK))
+			pr_warn("%s: bad encrypted write offset=%lld len=%llu\n",
+				__func__, offset, len);
+
 		osd_req_op_extent_osd_data_pages(req, op_idx, data_pages, len,
 						 0, from_pool, false);
 		osd_req_op_extent_update(req, op_idx, len);
diff --git a/fs/ceph/crypto.h b/fs/ceph/crypto.h
index b735b3f144a7..6afa6d888fe0 100644
--- a/fs/ceph/crypto.h
+++ b/fs/ceph/crypto.h
@@ -164,6 +164,12 @@ int ceph_fscrypt_decrypt_extents(struct inode *inode, struct page **page,
 				 u32 ext_cnt);
 int ceph_fscrypt_encrypt_pages(struct inode *inode, struct page **page, u64 off,
 			       int len, gfp_t gfp);
+
+static inline struct page *ceph_fscrypt_pagecache_page(struct page *page)
+{
+	return fscrypt_is_bounce_page(page) ? fscrypt_pagecache_page(page) : page;
+}
+
 #else /* CONFIG_FS_ENCRYPTION */
 
 static inline void ceph_fscrypt_set_ops(struct super_block *sb)
@@ -267,6 +273,16 @@ static inline int ceph_fscrypt_encrypt_pages(struct inode *inode,
 {
 	return 0;
 }
+
+static inline struct page *ceph_fscrypt_pagecache_page(struct page *page)
+{
+	return page;
+}
 #endif /* CONFIG_FS_ENCRYPTION */
 
-#endif
+static inline loff_t ceph_fscrypt_page_offset(struct page *page)
+{
+	return page_offset(ceph_fscrypt_pagecache_page(page));
+}
+
+#endif /* _CEPH_CRYPTO_H */

From f0fe1e54cfcf5209a88d720671dc6637774b8757 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Thu, 25 Aug 2022 09:31:22 -0400
Subject: [PATCH 0645/1189] ceph: plumb in decryption during reads
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Force the use of sparse reads when the inode is encrypted, and add the
appropriate code to decrypt the extent map after receiving.

Note that the crypto block may be smaller than a page, but the reverse
cannot be true.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/addr.c | 69 ++++++++++++++++++++++++++++++++------
 fs/ceph/file.c | 90 ++++++++++++++++++++++++++++++++++++--------------
 2 files changed, 125 insertions(+), 34 deletions(-)

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 89ca27848325..95ff84930dcf 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -18,6 +18,7 @@
 #include "mds_client.h"
 #include "cache.h"
 #include "metric.h"
+#include "crypto.h"
 #include <linux/ceph/osd_client.h>
 #include <linux/ceph/striper.h>
 
@@ -242,7 +243,8 @@ static bool ceph_netfs_clamp_length(struct netfs_io_subrequest *subreq)
 
 static void finish_netfs_read(struct ceph_osd_request *req)
 {
-	struct ceph_fs_client *fsc = ceph_inode_to_client(req->r_inode);
+	struct inode *inode = req->r_inode;
+	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	struct ceph_osd_data *osd_data = osd_req_op_extent_osd_data(req, 0);
 	struct netfs_io_subrequest *subreq = req->r_priv;
 	struct ceph_osd_req_op *op = &req->r_ops[0];
@@ -256,16 +258,31 @@ static void finish_netfs_read(struct ceph_osd_request *req)
 	     subreq->len, i_size_read(req->r_inode));
 
 	/* no object means success but no data */
-	if (sparse && err >= 0)
-		err = ceph_sparse_ext_map_end(op);
-	else if (err == -ENOENT)
+	if (err == -ENOENT)
 		err = 0;
 	else if (err == -EBLOCKLISTED)
 		fsc->blocklisted = true;
 
-	if (err >= 0 && err < subreq->len)
-		__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+	if (err >= 0) {
+		if (sparse && err > 0)
+			err = ceph_sparse_ext_map_end(op);
+		if (err < subreq->len)
+			__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+		if (IS_ENCRYPTED(inode) && err > 0) {
+			err = ceph_fscrypt_decrypt_extents(inode,
+					osd_data->pages, subreq->start,
+					op->extent.sparse_ext,
+					op->extent.sparse_ext_cnt);
+			if (err > subreq->len)
+				err = subreq->len;
+		}
+	}
 
+	if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGES) {
+		ceph_put_page_vector(osd_data->pages,
+				     calc_pages_for(osd_data->alignment,
+					osd_data->length), false);
+	}
 	netfs_subreq_terminated(subreq, err, false);
 	iput(req->r_inode);
 }
@@ -336,7 +353,8 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 	struct iov_iter iter;
 	int err = 0;
 	u64 len = subreq->len;
-	bool sparse = ceph_test_mount_opt(fsc, SPARSEREAD);
+	bool sparse = IS_ENCRYPTED(inode) || ceph_test_mount_opt(fsc, SPARSEREAD);
+	u64 off = subreq->start;
 
 	if (ceph_inode_is_shutdown(inode)) {
 		err = -EIO;
@@ -346,8 +364,10 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 	if (ceph_has_inline_data(ci) && ceph_netfs_issue_op_inline(subreq))
 		return;
 
-	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino, subreq->start, &len,
-			0, 1, sparse ? CEPH_OSD_OP_SPARSE_READ : CEPH_OSD_OP_READ,
+	ceph_fscrypt_adjust_off_and_len(inode, &off, &len);
+
+	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino,
+			off, &len, 0, 1, sparse ? CEPH_OSD_OP_SPARSE_READ : CEPH_OSD_OP_READ,
 			CEPH_OSD_FLAG_READ | fsc->client->osdc.client->options->read_from_replica,
 			NULL, ci->i_truncate_seq, ci->i_truncate_size, false);
 	if (IS_ERR(req)) {
@@ -363,8 +383,37 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 	}
 
 	dout("%s: pos=%llu orig_len=%zu len=%llu\n", __func__, subreq->start, subreq->len, len);
+
 	iov_iter_xarray(&iter, ITER_DEST, &rreq->mapping->i_pages, subreq->start, len);
-	osd_req_op_extent_osd_iter(req, 0, &iter);
+
+	/*
+	 * FIXME: For now, use CEPH_OSD_DATA_TYPE_PAGES instead of _ITER for
+	 * encrypted inodes. We'd need infrastructure that handles an iov_iter
+	 * instead of page arrays, and we don't have that as of yet. Once the
+	 * dust settles on the write helpers and encrypt/decrypt routines for
+	 * netfs, we should be able to rework this.
+	 */
+	if (IS_ENCRYPTED(inode)) {
+		struct page **pages;
+		size_t page_off;
+
+		err = iov_iter_get_pages_alloc2(&iter, &pages, len, &page_off);
+		if (err < 0) {
+			dout("%s: iov_ter_get_pages_alloc returned %d\n",
+			     __func__, err);
+			goto out;
+		}
+
+		/* should always give us a page-aligned read */
+		WARN_ON_ONCE(page_off);
+		len = err;
+		err = 0;
+
+		osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0, false,
+						 false);
+	} else {
+		osd_req_op_extent_osd_iter(req, 0, &iter);
+	}
 	req->r_callback = finish_netfs_read;
 	req->r_priv = subreq;
 	req->r_inode = inode;
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 45e00e42960b..9d1a77cdc494 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -970,7 +970,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 	u64 off = *ki_pos;
 	u64 len = iov_iter_count(to);
 	u64 i_size = i_size_read(inode);
-	bool sparse = ceph_test_mount_opt(fsc, SPARSEREAD);
+	bool sparse = IS_ENCRYPTED(inode) || ceph_test_mount_opt(fsc, SPARSEREAD);
 	u64 objver = 0;
 
 	dout("sync_read on inode %p %llx~%llx\n", inode, *ki_pos, len);
@@ -1001,10 +1001,19 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 		int idx;
 		size_t left;
 		struct ceph_osd_req_op *op;
+		u64 read_off = off;
+		u64 read_len = len;
+
+		/* determine new offset/length if encrypted */
+		ceph_fscrypt_adjust_off_and_len(inode, &read_off, &read_len);
+
+		dout("sync_read orig %llu~%llu reading %llu~%llu",
+		     off, len, read_off, read_len);
 
 		req = ceph_osdc_new_request(osdc, &ci->i_layout,
-					ci->i_vino, off, &len, 0, 1,
-					sparse ? CEPH_OSD_OP_SPARSE_READ : CEPH_OSD_OP_READ,
+					ci->i_vino, read_off, &read_len, 0, 1,
+					sparse ? CEPH_OSD_OP_SPARSE_READ :
+						 CEPH_OSD_OP_READ,
 					CEPH_OSD_FLAG_READ,
 					NULL, ci->i_truncate_seq,
 					ci->i_truncate_size, false);
@@ -1013,10 +1022,13 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 			break;
 		}
 
+		/* adjust len downward if the request truncated the len */
+		if (off + len > read_off + read_len)
+			len = read_off + read_len - off;
 		more = len < iov_iter_count(to);
 
-		num_pages = calc_pages_for(off, len);
-		page_off = off & ~PAGE_MASK;
+		num_pages = calc_pages_for(read_off, read_len);
+		page_off = offset_in_page(off);
 		pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL);
 		if (IS_ERR(pages)) {
 			ceph_osdc_put_request(req);
@@ -1024,7 +1036,8 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 			break;
 		}
 
-		osd_req_op_extent_osd_data_pages(req, 0, pages, len, page_off,
+		osd_req_op_extent_osd_data_pages(req, 0, pages, read_len,
+						 offset_in_page(read_off),
 						 false, false);
 
 		op = &req->r_ops[0];
@@ -1042,7 +1055,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 		ceph_update_read_metrics(&fsc->mdsc->metric,
 					 req->r_start_latency,
 					 req->r_end_latency,
-					 len, ret);
+					 read_len, ret);
 
 		if (ret > 0)
 			objver = req->r_version;
@@ -1057,8 +1070,35 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 		else if (ret == -ENOENT)
 			ret = 0;
 
+		if (ret > 0 && IS_ENCRYPTED(inode)) {
+			int fret;
+
+			fret = ceph_fscrypt_decrypt_extents(inode, pages,
+					read_off, op->extent.sparse_ext,
+					op->extent.sparse_ext_cnt);
+			if (fret < 0) {
+				ret = fret;
+				ceph_osdc_put_request(req);
+				break;
+			}
+
+			/* account for any partial block at the beginning */
+			fret -= (off - read_off);
+
+			/*
+			 * Short read after big offset adjustment?
+			 * Nothing is usable, just call it a zero
+			 * len read.
+			 */
+			fret = max(fret, 0);
+
+			/* account for partial block at the end */
+			ret = min_t(ssize_t, fret, len);
+		}
+
 		ceph_osdc_put_request(req);
 
+		/* Short read but not EOF? Zero out the remainder. */
 		if (ret >= 0 && ret < len && (off + ret < i_size)) {
 			int zlen = min(len - ret, i_size - off - ret);
 			int zoff = page_off + ret;
@@ -1072,15 +1112,16 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 		idx = 0;
 		left = ret > 0 ? ret : 0;
 		while (left > 0) {
-			size_t len, copied;
-			page_off = off & ~PAGE_MASK;
-			len = min_t(size_t, left, PAGE_SIZE - page_off);
+			size_t plen, copied;
+
+			plen = min_t(size_t, left, PAGE_SIZE - page_off);
 			SetPageUptodate(pages[idx]);
 			copied = copy_page_to_iter(pages[idx++],
-						   page_off, len, to);
+						   page_off, plen, to);
 			off += copied;
 			left -= copied;
-			if (copied < len) {
+			page_off = 0;
+			if (copied < plen) {
 				ret = -EFAULT;
 				break;
 			}
@@ -1097,20 +1138,21 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 			break;
 	}
 
-	if (off > *ki_pos) {
-		if (off >= i_size) {
-			*retry_op = CHECK_EOF;
-			ret = i_size - *ki_pos;
-			*ki_pos = i_size;
-		} else {
-			ret = off - *ki_pos;
-			*ki_pos = off;
+	if (ret > 0) {
+		if (off > *ki_pos) {
+			if (off >= i_size) {
+				*retry_op = CHECK_EOF;
+				ret = i_size - *ki_pos;
+				*ki_pos = i_size;
+			} else {
+				ret = off - *ki_pos;
+				*ki_pos = off;
+			}
 		}
+
+		if (last_objver)
+			*last_objver = objver;
 	}
-
-	if (last_objver && ret > 0)
-		*last_objver = objver;
-
 	dout("sync_read result %zd retry_op %d\n", ret, *retry_op);
 	return ret;
 }

From b422f115044328e1753d6c1e3bb4955b4ca5df27 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Lu=C3=ADs=20Henriques?= <lhenriques@suse.de>
Date: Thu, 25 Aug 2022 09:31:27 -0400
Subject: [PATCH 0646/1189] ceph: invalidate pages when doing direct/sync
 writes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When doing a direct/sync write, we need to invalidate the page cache in
the range being written to. If we don't do this, the cache will include
invalid data as we just did a write that avoided the page cache.

In the event that invalidation fails, just ignore the error. That likely
just means that we raced with another task doing a buffered write, in
which case we want to leave the page intact anyway.

[ jlayton: minor comment update ]

Signed-off-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/file.c | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 9d1a77cdc494..e58787233e42 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1636,11 +1636,6 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 		return ret;
 
 	ceph_fscache_invalidate(inode, false);
-	ret = invalidate_inode_pages2_range(inode->i_mapping,
-					    pos >> PAGE_SHIFT,
-					    (pos + count - 1) >> PAGE_SHIFT);
-	if (ret < 0)
-		dout("invalidate_inode_pages2_range returned %d\n", ret);
 
 	while ((len = iov_iter_count(from)) > 0) {
 		size_t left;
@@ -1968,6 +1963,20 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 		}
 
 		ceph_clear_error_write(ci);
+
+		/*
+		 * We successfully wrote to a range of the file. Declare
+		 * that region of the pagecache invalid.
+		 */
+		ret = invalidate_inode_pages2_range(
+				inode->i_mapping,
+				pos >> PAGE_SHIFT,
+				(pos + len - 1) >> PAGE_SHIFT);
+		if (ret < 0) {
+			dout("invalidate_inode_pages2_range returned %d\n",
+			     ret);
+			ret = 0;
+		}
 		pos += len;
 		written += len;
 		dout("sync_write written %d\n", written);

From dd66df0053ef84add5e684df517aa9b498342381 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Lu=C3=ADs=20Henriques?= <lhenriques@suse.de>
Date: Thu, 25 Aug 2022 09:31:28 -0400
Subject: [PATCH 0647/1189] ceph: add support for encrypted snapshot names
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since filenames in encrypted directories are encrypted and shown as
a base64-encoded string when the directory is locked, make snapshot
names show a similar behaviour.

When creating a snapshot, .snap directories for every subdirectory will
show the snapshot name in the "long format":

  # mkdir .snap/my-snap
  # ls my-dir/.snap/
  _my-snap_1099511627782

Encrypted snapshots will need to be able to handle these by
encrypting/decrypting only the snapshot part of the string ('my-snap').

Also, since the MDS prevents snapshot names to be bigger than 240
characters it is necessary to adapt CEPH_NOHASH_NAME_MAX to accommodate
this extra limitation.

[ idryomov: drop const on !CONFIG_FS_ENCRYPTION branch too ]

Signed-off-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/crypto.c | 197 +++++++++++++++++++++++++++++++++++++++--------
 fs/ceph/crypto.h |  12 +--
 fs/ceph/inode.c  |  33 +++++++-
 3 files changed, 201 insertions(+), 41 deletions(-)

diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c
index 9494bf485f6a..e4d5cd56a80b 100644
--- a/fs/ceph/crypto.c
+++ b/fs/ceph/crypto.c
@@ -193,17 +193,101 @@ void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req,
 	swap(req->r_fscrypt_auth, as->fscrypt_auth);
 }
 
-int ceph_encode_encrypted_dname(const struct inode *parent,
-				struct qstr *d_name, char *buf)
+/*
+ * User-created snapshots can't start with '_'.  Snapshots that start with this
+ * character are special (hint: there aren't real snapshots) and use the
+ * following format:
+ *
+ *   _<SNAPSHOT-NAME>_<INODE-NUMBER>
+ *
+ * where:
+ *  - <SNAPSHOT-NAME> - the real snapshot name that may need to be decrypted,
+ *  - <INODE-NUMBER> - the inode number (in decimal) for the actual snapshot
+ *
+ * This function parses these snapshot names and returns the inode
+ * <INODE-NUMBER>.  'name_len' will also bet set with the <SNAPSHOT-NAME>
+ * length.
+ */
+static struct inode *parse_longname(const struct inode *parent,
+				    const char *name, int *name_len)
 {
+	struct inode *dir = NULL;
+	struct ceph_vino vino = { .snap = CEPH_NOSNAP };
+	char *inode_number;
+	char *name_end;
+	int orig_len = *name_len;
+	int ret = -EIO;
+
+	/* Skip initial '_' */
+	name++;
+	name_end = strrchr(name, '_');
+	if (!name_end) {
+		dout("Failed to parse long snapshot name: %s\n", name);
+		return ERR_PTR(-EIO);
+	}
+	*name_len = (name_end - name);
+	if (*name_len <= 0) {
+		pr_err("Failed to parse long snapshot name\n");
+		return ERR_PTR(-EIO);
+	}
+
+	/* Get the inode number */
+	inode_number = kmemdup_nul(name_end + 1,
+				   orig_len - *name_len - 2,
+				   GFP_KERNEL);
+	if (!inode_number)
+		return ERR_PTR(-ENOMEM);
+	ret = kstrtou64(inode_number, 10, &vino.ino);
+	if (ret) {
+		dout("Failed to parse inode number: %s\n", name);
+		dir = ERR_PTR(ret);
+		goto out;
+	}
+
+	/* And finally the inode */
+	dir = ceph_find_inode(parent->i_sb, vino);
+	if (!dir) {
+		/* This can happen if we're not mounting cephfs on the root */
+		dir = ceph_get_inode(parent->i_sb, vino, NULL);
+		if (!dir)
+			dir = ERR_PTR(-ENOENT);
+	}
+	if (IS_ERR(dir))
+		dout("Can't find inode %s (%s)\n", inode_number, name);
+
+out:
+	kfree(inode_number);
+	return dir;
+}
+
+int ceph_encode_encrypted_dname(struct inode *parent, struct qstr *d_name,
+				char *buf)
+{
+	struct inode *dir = parent;
+	struct qstr iname;
 	u32 len;
+	int name_len;
 	int elen;
 	int ret;
-	u8 *cryptbuf;
+	u8 *cryptbuf = NULL;
 
-	if (!fscrypt_has_encryption_key(parent)) {
+	iname.name = d_name->name;
+	name_len = d_name->len;
+
+	/* Handle the special case of snapshot names that start with '_' */
+	if ((ceph_snap(dir) == CEPH_SNAPDIR) && (name_len > 0) &&
+	    (iname.name[0] == '_')) {
+		dir = parse_longname(parent, iname.name, &name_len);
+		if (IS_ERR(dir))
+			return PTR_ERR(dir);
+		iname.name++; /* skip initial '_' */
+	}
+	iname.len = name_len;
+
+	if (!fscrypt_has_encryption_key(dir)) {
 		memcpy(buf, d_name->name, d_name->len);
-		return d_name->len;
+		elen = d_name->len;
+		goto out;
 	}
 
 	/*
@@ -212,19 +296,23 @@ int ceph_encode_encrypted_dname(const struct inode *parent,
 	 *
 	 * See: fscrypt_setup_filename
 	 */
-	if (!fscrypt_fname_encrypted_size(parent, d_name->len, NAME_MAX, &len))
-		return -ENAMETOOLONG;
+	if (!fscrypt_fname_encrypted_size(dir, iname.len, NAME_MAX, &len)) {
+		elen = -ENAMETOOLONG;
+		goto out;
+	}
 
 	/* Allocate a buffer appropriate to hold the result */
 	cryptbuf = kmalloc(len > CEPH_NOHASH_NAME_MAX ? NAME_MAX : len,
 			   GFP_KERNEL);
-	if (!cryptbuf)
-		return -ENOMEM;
+	if (!cryptbuf) {
+		elen = -ENOMEM;
+		goto out;
+	}
 
-	ret = fscrypt_fname_encrypt(parent, d_name, cryptbuf, len);
+	ret = fscrypt_fname_encrypt(dir, &iname, cryptbuf, len);
 	if (ret) {
-		kfree(cryptbuf);
-		return ret;
+		elen = ret;
+		goto out;
 	}
 
 	/* hash the end if the name is long enough */
@@ -243,13 +331,31 @@ int ceph_encode_encrypted_dname(const struct inode *parent,
 
 	/* base64 encode the encrypted name */
 	elen = ceph_base64_encode(cryptbuf, len, buf);
-	kfree(cryptbuf);
 	dout("base64-encoded ciphertext name = %.*s\n", elen, buf);
+
+	/* To understand the 240 limit, see CEPH_NOHASH_NAME_MAX comments */
+	WARN_ON(elen > 240);
+	if ((elen > 0) && (dir != parent)) {
+		char tmp_buf[NAME_MAX];
+
+		elen = snprintf(tmp_buf, sizeof(tmp_buf), "_%.*s_%ld",
+				elen, buf, dir->i_ino);
+		memcpy(buf, tmp_buf, elen);
+	}
+
+out:
+	kfree(cryptbuf);
+	if (dir != parent) {
+		if ((dir->i_state & I_NEW))
+			discard_new_inode(dir);
+		else
+			iput(dir);
+	}
 	return elen;
 }
 
-int ceph_encode_encrypted_fname(const struct inode *parent,
-				struct dentry *dentry, char *buf)
+int ceph_encode_encrypted_fname(struct inode *parent, struct dentry *dentry,
+				char *buf)
 {
 	WARN_ON_ONCE(!fscrypt_has_encryption_key(parent));
 
@@ -274,29 +380,42 @@ int ceph_encode_encrypted_fname(const struct inode *parent,
 int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname,
 		      struct fscrypt_str *oname, bool *is_nokey)
 {
-	int ret;
+	struct inode *dir = fname->dir;
 	struct fscrypt_str _tname = FSTR_INIT(NULL, 0);
 	struct fscrypt_str iname;
-
-	if (!IS_ENCRYPTED(fname->dir)) {
-		oname->name = fname->name;
-		oname->len = fname->name_len;
-		return 0;
-	}
+	char *name = fname->name;
+	int name_len = fname->name_len;
+	int ret;
 
 	/* Sanity check that the resulting name will fit in the buffer */
 	if (fname->name_len > NAME_MAX || fname->ctext_len > NAME_MAX)
 		return -EIO;
 
-	ret = ceph_fscrypt_prepare_readdir(fname->dir);
-	if (ret < 0)
-		return ret;
+	/* Handle the special case of snapshot names that start with '_' */
+	if ((ceph_snap(dir) == CEPH_SNAPDIR) && (name_len > 0) &&
+	    (name[0] == '_')) {
+		dir = parse_longname(dir, name, &name_len);
+		if (IS_ERR(dir))
+			return PTR_ERR(dir);
+		name++; /* skip initial '_' */
+	}
+
+	if (!IS_ENCRYPTED(dir)) {
+		oname->name = fname->name;
+		oname->len = fname->name_len;
+		ret = 0;
+		goto out_inode;
+	}
+
+	ret = ceph_fscrypt_prepare_readdir(dir);
+	if (ret)
+		goto out_inode;
 
 	/*
 	 * Use the raw dentry name as sent by the MDS instead of
 	 * generating a nokey name via fscrypt.
 	 */
-	if (!fscrypt_has_encryption_key(fname->dir)) {
+	if (!fscrypt_has_encryption_key(dir)) {
 		if (fname->no_copy)
 			oname->name = fname->name;
 		else
@@ -304,7 +423,8 @@ int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname,
 		oname->len = fname->name_len;
 		if (is_nokey)
 			*is_nokey = true;
-		return 0;
+		ret = 0;
+		goto out_inode;
 	}
 
 	if (fname->ctext_len == 0) {
@@ -313,12 +433,11 @@ int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname,
 		if (!tname) {
 			ret = fscrypt_fname_alloc_buffer(NAME_MAX, &_tname);
 			if (ret)
-				return ret;
+				goto out_inode;
 			tname = &_tname;
 		}
 
-		declen = ceph_base64_decode(fname->name, fname->name_len,
-					    tname->name);
+		declen = ceph_base64_decode(name, name_len, tname->name);
 		if (declen <= 0) {
 			ret = -EIO;
 			goto out;
@@ -330,9 +449,25 @@ int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname,
 		iname.len = fname->ctext_len;
 	}
 
-	ret = fscrypt_fname_disk_to_usr(fname->dir, 0, 0, &iname, oname);
+	ret = fscrypt_fname_disk_to_usr(dir, 0, 0, &iname, oname);
+	if (!ret && (dir != fname->dir)) {
+		char tmp_buf[CEPH_BASE64_CHARS(NAME_MAX)];
+
+		name_len = snprintf(tmp_buf, sizeof(tmp_buf), "_%.*s_%ld",
+				    oname->len, oname->name, dir->i_ino);
+		memcpy(oname->name, tmp_buf, name_len);
+		oname->len = name_len;
+	}
+
 out:
 	fscrypt_fname_free_buffer(&_tname);
+out_inode:
+	if ((dir != fname->dir) && !IS_ERR(dir)) {
+		if ((dir->i_state & I_NEW))
+			discard_new_inode(dir);
+		else
+			iput(dir);
+	}
 	return ret;
 }
 
diff --git a/fs/ceph/crypto.h b/fs/ceph/crypto.h
index 6afa6d888fe0..47e0c319fc68 100644
--- a/fs/ceph/crypto.h
+++ b/fs/ceph/crypto.h
@@ -102,10 +102,10 @@ int ceph_fscrypt_prepare_context(struct inode *dir, struct inode *inode,
 				 struct ceph_acl_sec_ctx *as);
 void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req,
 				struct ceph_acl_sec_ctx *as);
-int ceph_encode_encrypted_dname(const struct inode *parent,
-				struct qstr *d_name, char *buf);
-int ceph_encode_encrypted_fname(const struct inode *parent,
-				struct dentry *dentry, char *buf);
+int ceph_encode_encrypted_dname(struct inode *parent, struct qstr *d_name,
+				char *buf);
+int ceph_encode_encrypted_fname(struct inode *parent, struct dentry *dentry,
+				char *buf);
 
 static inline int ceph_fname_alloc_buffer(struct inode *parent,
 					  struct fscrypt_str *fname)
@@ -194,14 +194,14 @@ static inline void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req,
 {
 }
 
-static inline int ceph_encode_encrypted_dname(const struct inode *parent,
+static inline int ceph_encode_encrypted_dname(struct inode *parent,
 					      struct qstr *d_name, char *buf)
 {
 	memcpy(buf, d_name->name, d_name->len);
 	return d_name->len;
 }
 
-static inline int ceph_encode_encrypted_fname(const struct inode *parent,
+static inline int ceph_encode_encrypted_fname(struct inode *parent,
 					      struct dentry *dentry, char *buf)
 {
 	return -EOPNOTSUPP;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 054fd66609b7..83c420646f90 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -91,9 +91,15 @@ struct inode *ceph_new_inode(struct inode *dir, struct dentry *dentry,
 	if (err < 0)
 		goto out_err;
 
-	err = ceph_fscrypt_prepare_context(dir, inode, as_ctx);
-	if (err)
-		goto out_err;
+	/*
+	 * We'll skip setting fscrypt context for snapshots, leaving that for
+	 * the handle_reply().
+	 */
+	if (ceph_snap(dir) != CEPH_SNAPDIR) {
+		err = ceph_fscrypt_prepare_context(dir, inode, as_ctx);
+		if (err)
+			goto out_err;
+	}
 
 	return inode;
 out_err:
@@ -159,6 +165,7 @@ struct inode *ceph_get_snapdir(struct inode *parent)
 	};
 	struct inode *inode = ceph_get_inode(parent->i_sb, vino, NULL);
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	int ret = -ENOTDIR;
 
 	if (IS_ERR(inode))
 		return inode;
@@ -184,6 +191,24 @@ struct inode *ceph_get_snapdir(struct inode *parent)
 	ci->i_rbytes = 0;
 	ci->i_btime = ceph_inode(parent)->i_btime;
 
+#ifdef CONFIG_FS_ENCRYPTION
+	/* if encrypted, just borrow fscrypt_auth from parent */
+	if (IS_ENCRYPTED(parent)) {
+		struct ceph_inode_info *pci = ceph_inode(parent);
+
+		ci->fscrypt_auth = kmemdup(pci->fscrypt_auth,
+					   pci->fscrypt_auth_len,
+					   GFP_KERNEL);
+		if (ci->fscrypt_auth) {
+			inode->i_flags |= S_ENCRYPTED;
+			ci->fscrypt_auth_len = pci->fscrypt_auth_len;
+		} else {
+			dout("Failed to alloc snapdir fscrypt_auth\n");
+			ret = -ENOMEM;
+			goto err;
+		}
+	}
+#endif
 	if (inode->i_state & I_NEW) {
 		inode->i_op = &ceph_snapdir_iops;
 		inode->i_fop = &ceph_snapdir_fops;
@@ -197,7 +222,7 @@ err:
 		discard_new_inode(inode);
 	else
 		iput(inode);
-	return ERR_PTR(-ENOTDIR);
+	return ERR_PTR(ret);
 }
 
 const struct inode_operations ceph_file_iops = {

From abd4fc775857cda97cde08d500a60b00617b8168 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Lu=C3=ADs=20Henriques?= <lhenriques@suse.de>
Date: Thu, 25 Aug 2022 09:31:31 -0400
Subject: [PATCH 0648/1189] ceph: prevent snapshot creation in encrypted locked
 directories
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

With snapshot names encryption we can not allow snapshots to be created in
locked directories because the names wouldn't be encrypted.  This patch
forces the directory to be unlocked to allow a snapshot to be created.

Signed-off-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/dir.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 4990886a366c..0e4f8e07022d 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1090,6 +1090,11 @@ static int ceph_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 		err = -EDQUOT;
 		goto out;
 	}
+	if ((op == CEPH_MDS_OP_MKSNAP) && IS_ENCRYPTED(dir) &&
+	    !fscrypt_has_encryption_key(dir)) {
+		err = -ENOKEY;
+		goto out;
+	}
 
 
 	req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);

From 230bd8b98ddfae3b7093671d4973236dc724d0bb Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Lu=C3=ADs=20Henriques?= <lhenriques@suse.de>
Date: Thu, 25 Aug 2022 09:31:30 -0400
Subject: [PATCH 0649/1189] ceph: update documentation regarding snapshot
 naming limitations
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 Documentation/filesystems/ceph.rst | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/Documentation/filesystems/ceph.rst b/Documentation/filesystems/ceph.rst
index 76ce938e7024..085f309ece60 100644
--- a/Documentation/filesystems/ceph.rst
+++ b/Documentation/filesystems/ceph.rst
@@ -57,6 +57,16 @@ a snapshot on any subdirectory (and its nested contents) in the
 system.  Snapshot creation and deletion are as simple as 'mkdir
 .snap/foo' and 'rmdir .snap/foo'.
 
+Snapshot names have two limitations:
+
+* They can not start with an underscore ('_'), as these names are reserved
+  for internal usage by the MDS.
+* They can not exceed 240 characters in size.  This is because the MDS makes
+  use of long snapshot names internally, which follow the format:
+  `_<SNAPSHOT-NAME>_<INODE-NUMBER>`.  Since filenames in general can't have
+  more than 255 characters, and `<node-id>` takes 13 characters, the long
+  snapshot names can take as much as 255 - 1 - 1 - 13 = 240.
+
 Ceph also provides some recursive accounting on directories for nested
 files and bytes.  That is, a 'getfattr -d foo' on any directory in the
 system will reveal the total number of nested regular files and

From e3dfcab2080dc1f9a4b09cc1327361bc2845bfcd Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Wed, 21 Dec 2022 14:13:51 +0800
Subject: [PATCH 0650/1189] ceph: drop messages from MDS when unmounting
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When unmounting all the dirty buffers will be flushed and after
the last osd request is finished the last reference of the i_count
will be released. Then it will flush the dirty cap/snap to MDSs,
and the unmounting won't wait the possible acks, which will ihold
the inodes when updating the metadata locally but makes no sense
any more, of this. This will make the evict_inodes() to skip these
inodes.

If encrypt is enabled the kernel generate a warning when removing
the encrypt keys when the skipped inodes still hold the keyring:

WARNING: CPU: 4 PID: 168846 at fs/crypto/keyring.c:242 fscrypt_destroy_keyring+0x7e/0xd0
CPU: 4 PID: 168846 Comm: umount Tainted: G S  6.1.0-rc5-ceph-g72ead199864c #1
Hardware name: Supermicro SYS-5018R-WR/X10SRW-F, BIOS 2.0 12/17/2015
RIP: 0010:fscrypt_destroy_keyring+0x7e/0xd0
RSP: 0018:ffffc9000b277e28 EFLAGS: 00010202
RAX: 0000000000000002 RBX: ffff88810d52ac00 RCX: ffff88810b56aa00
RDX: 0000000080000000 RSI: ffffffff822f3a09 RDI: ffff888108f59000
RBP: ffff8881d394fb88 R08: 0000000000000028 R09: 0000000000000000
R10: 0000000000000001 R11: 11ff4fe6834fcd91 R12: ffff8881d394fc40
R13: ffff888108f59000 R14: ffff8881d394f800 R15: 0000000000000000
FS:  00007fd83f6f1080(0000) GS:ffff88885fd00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f918d417000 CR3: 000000017f89a005 CR4: 00000000003706e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
<TASK>
generic_shutdown_super+0x47/0x120
kill_anon_super+0x14/0x30
ceph_kill_sb+0x36/0x90 [ceph]
deactivate_locked_super+0x29/0x60
cleanup_mnt+0xb8/0x140
task_work_run+0x67/0xb0
exit_to_user_mode_prepare+0x23d/0x240
syscall_exit_to_user_mode+0x25/0x60
do_syscall_64+0x40/0x80
entry_SYSCALL_64_after_hwframe+0x63/0xcd
RIP: 0033:0x7fd83dc39e9b

Later the kernel will crash when iput() the inodes and dereferencing
the "sb->s_master_keys", which has been released by the
generic_shutdown_super().

Link: https://tracker.ceph.com/issues/59162
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/caps.c       |  6 +++-
 fs/ceph/mds_client.c | 12 +++++--
 fs/ceph/mds_client.h | 11 +++++--
 fs/ceph/quota.c      | 14 ++++-----
 fs/ceph/snap.c       | 10 +++---
 fs/ceph/super.c      | 75 +++++++++++++++++++++++++++++++++++++++++---
 fs/ceph/super.h      |  3 ++
 7 files changed, 109 insertions(+), 22 deletions(-)

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 5c2b28ac9410..54041d9c1e25 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -4247,6 +4247,9 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 
 	dout("handle_caps from mds%d\n", session->s_mds);
 
+	if (!ceph_inc_mds_stopping_blocker(mdsc, session))
+		return;
+
 	/* decode */
 	end = msg->front.iov_base + msg->front.iov_len;
 	if (msg->front.iov_len < sizeof(*h))
@@ -4348,7 +4351,6 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 	     vino.snap, inode);
 
 	mutex_lock(&session->s_mutex);
-	inc_session_sequence(session);
 	dout(" mds%d seq %lld cap seq %u\n", session->s_mds, session->s_seq,
 	     (unsigned)seq);
 
@@ -4457,6 +4459,8 @@ done:
 done_unlocked:
 	iput(inode);
 out:
+	ceph_dec_mds_stopping_blocker(mdsc);
+
 	ceph_put_string(extra_info.pool_ns);
 
 	/* Defer closing the sessions after s_mutex lock being released */
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index c257d75c5757..04a881343e43 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -4889,6 +4889,9 @@ static void handle_lease(struct ceph_mds_client *mdsc,
 
 	dout("handle_lease from mds%d\n", mds);
 
+	if (!ceph_inc_mds_stopping_blocker(mdsc, session))
+		return;
+
 	/* decode */
 	if (msg->front.iov_len < sizeof(*h) + sizeof(u32))
 		goto bad;
@@ -4907,8 +4910,6 @@ static void handle_lease(struct ceph_mds_client *mdsc,
 	     dname.len, dname.name);
 
 	mutex_lock(&session->s_mutex);
-	inc_session_sequence(session);
-
 	if (!inode) {
 		dout("handle_lease no inode %llx\n", vino.ino);
 		goto release;
@@ -4970,9 +4971,13 @@ release:
 out:
 	mutex_unlock(&session->s_mutex);
 	iput(inode);
+
+	ceph_dec_mds_stopping_blocker(mdsc);
 	return;
 
 bad:
+	ceph_dec_mds_stopping_blocker(mdsc);
+
 	pr_err("corrupt lease message\n");
 	ceph_msg_dump(msg);
 }
@@ -5168,6 +5173,9 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc)
 	}
 
 	init_completion(&mdsc->safe_umount_waiters);
+	spin_lock_init(&mdsc->stopping_lock);
+	atomic_set(&mdsc->stopping_blockers, 0);
+	init_completion(&mdsc->stopping_waiter);
 	init_waitqueue_head(&mdsc->session_close_wq);
 	INIT_LIST_HEAD(&mdsc->waiting_for_map);
 	mdsc->quotarealms_inodes = RB_ROOT;
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 0477388a0d1c..1fa0f78b7b79 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -399,8 +399,9 @@ struct cap_wait {
 };
 
 enum {
-       CEPH_MDSC_STOPPING_BEGIN = 1,
-       CEPH_MDSC_STOPPING_FLUSHED = 2,
+	CEPH_MDSC_STOPPING_BEGIN = 1,
+	CEPH_MDSC_STOPPING_FLUSHING = 2,
+	CEPH_MDSC_STOPPING_FLUSHED = 3,
 };
 
 /*
@@ -419,7 +420,11 @@ struct ceph_mds_client {
 	struct ceph_mds_session **sessions;    /* NULL for mds if no session */
 	atomic_t		num_sessions;
 	int                     max_sessions;  /* len of sessions array */
-	int                     stopping;      /* true if shutting down */
+
+	spinlock_t              stopping_lock;  /* protect snap_empty */
+	int                     stopping;      /* the stage of shutting down */
+	atomic_t                stopping_blockers;
+	struct completion	stopping_waiter;
 
 	atomic64_t		quotarealms_count; /* # realms with quota */
 	/*
diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c
index 64592adfe48f..f7fcf7f08ec6 100644
--- a/fs/ceph/quota.c
+++ b/fs/ceph/quota.c
@@ -47,25 +47,23 @@ void ceph_handle_quota(struct ceph_mds_client *mdsc,
 	struct inode *inode;
 	struct ceph_inode_info *ci;
 
+	if (!ceph_inc_mds_stopping_blocker(mdsc, session))
+		return;
+
 	if (msg->front.iov_len < sizeof(*h)) {
 		pr_err("%s corrupt message mds%d len %d\n", __func__,
 		       session->s_mds, (int)msg->front.iov_len);
 		ceph_msg_dump(msg);
-		return;
+		goto out;
 	}
 
-	/* increment msg sequence number */
-	mutex_lock(&session->s_mutex);
-	inc_session_sequence(session);
-	mutex_unlock(&session->s_mutex);
-
 	/* lookup inode */
 	vino.ino = le64_to_cpu(h->ino);
 	vino.snap = CEPH_NOSNAP;
 	inode = ceph_find_inode(sb, vino);
 	if (!inode) {
 		pr_warn("Failed to find inode %llu\n", vino.ino);
-		return;
+		goto out;
 	}
 	ci = ceph_inode(inode);
 
@@ -78,6 +76,8 @@ void ceph_handle_quota(struct ceph_mds_client *mdsc,
 	spin_unlock(&ci->i_ceph_lock);
 
 	iput(inode);
+out:
+	ceph_dec_mds_stopping_blocker(mdsc);
 }
 
 static struct ceph_quotarealm_inode *
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 343d738448dc..7ddc6bad77ef 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -1015,6 +1015,9 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc,
 	int locked_rwsem = 0;
 	bool close_sessions = false;
 
+	if (!ceph_inc_mds_stopping_blocker(mdsc, session))
+		return;
+
 	/* decode */
 	if (msg->front.iov_len < sizeof(*h))
 		goto bad;
@@ -1030,10 +1033,6 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc,
 	dout("%s from mds%d op %s split %llx tracelen %d\n", __func__,
 	     mds, ceph_snap_op_name(op), split, trace_len);
 
-	mutex_lock(&session->s_mutex);
-	inc_session_sequence(session);
-	mutex_unlock(&session->s_mutex);
-
 	down_write(&mdsc->snap_rwsem);
 	locked_rwsem = 1;
 
@@ -1151,6 +1150,7 @@ skip_inode:
 	up_write(&mdsc->snap_rwsem);
 
 	flush_snaps(mdsc);
+	ceph_dec_mds_stopping_blocker(mdsc);
 	return;
 
 bad:
@@ -1160,6 +1160,8 @@ out:
 	if (locked_rwsem)
 		up_write(&mdsc->snap_rwsem);
 
+	ceph_dec_mds_stopping_blocker(mdsc);
+
 	if (close_sessions)
 		ceph_mdsc_close_sessions(mdsc);
 	return;
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 75dd1b6b3d01..1c14d87ed871 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -1462,25 +1462,90 @@ nomem:
 	return -ENOMEM;
 }
 
+/*
+ * Return true if it successfully increases the blocker counter,
+ * or false if the mdsc is in stopping and flushed state.
+ */
+static bool __inc_stopping_blocker(struct ceph_mds_client *mdsc)
+{
+	spin_lock(&mdsc->stopping_lock);
+	if (mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHING) {
+		spin_unlock(&mdsc->stopping_lock);
+		return false;
+	}
+	atomic_inc(&mdsc->stopping_blockers);
+	spin_unlock(&mdsc->stopping_lock);
+	return true;
+}
+
+static void __dec_stopping_blocker(struct ceph_mds_client *mdsc)
+{
+	spin_lock(&mdsc->stopping_lock);
+	if (!atomic_dec_return(&mdsc->stopping_blockers) &&
+	    mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHING)
+		complete_all(&mdsc->stopping_waiter);
+	spin_unlock(&mdsc->stopping_lock);
+}
+
+/* For metadata IO requests */
+bool ceph_inc_mds_stopping_blocker(struct ceph_mds_client *mdsc,
+				   struct ceph_mds_session *session)
+{
+	mutex_lock(&session->s_mutex);
+	inc_session_sequence(session);
+	mutex_unlock(&session->s_mutex);
+
+	return __inc_stopping_blocker(mdsc);
+}
+
+void ceph_dec_mds_stopping_blocker(struct ceph_mds_client *mdsc)
+{
+	__dec_stopping_blocker(mdsc);
+}
+
 static void ceph_kill_sb(struct super_block *s)
 {
 	struct ceph_fs_client *fsc = ceph_sb_to_client(s);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
+	bool wait;
 
 	dout("kill_sb %p\n", s);
 
-	ceph_mdsc_pre_umount(fsc->mdsc);
+	ceph_mdsc_pre_umount(mdsc);
 	flush_fs_workqueues(fsc);
 
 	/*
 	 * Though the kill_anon_super() will finally trigger the
-	 * sync_filesystem() anyway, we still need to do it here
-	 * and then bump the stage of shutdown to stop the work
-	 * queue as earlier as possible.
+	 * sync_filesystem() anyway, we still need to do it here and
+	 * then bump the stage of shutdown. This will allow us to
+	 * drop any further message, which will increase the inodes'
+	 * i_count reference counters but makes no sense any more,
+	 * from MDSs.
+	 *
+	 * Without this when evicting the inodes it may fail in the
+	 * kill_anon_super(), which will trigger a warning when
+	 * destroying the fscrypt keyring and then possibly trigger
+	 * a further crash in ceph module when the iput() tries to
+	 * evict the inodes later.
 	 */
 	sync_filesystem(s);
 
-	fsc->mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHED;
+	spin_lock(&mdsc->stopping_lock);
+	mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHING;
+	wait = !!atomic_read(&mdsc->stopping_blockers);
+	spin_unlock(&mdsc->stopping_lock);
 
+	if (wait && atomic_read(&mdsc->stopping_blockers)) {
+		long timeleft = wait_for_completion_killable_timeout(
+					&mdsc->stopping_waiter,
+					fsc->client->options->mount_timeout);
+		if (!timeleft) /* timed out */
+			pr_warn("umount timed out, %ld\n", timeleft);
+		else if (timeleft < 0) /* killed */
+			pr_warn("umount was killed, %ld\n", timeleft);
+	}
+
+	mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHED;
 	kill_anon_super(s);
 
 	fsc->client->extra_mon_dispatch = NULL;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index b5e54c8f010b..d8eb35d73a23 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -1413,4 +1413,7 @@ extern bool ceph_quota_update_statfs(struct ceph_fs_client *fsc,
 				     struct kstatfs *buf);
 extern void ceph_cleanup_quotarealms_inodes(struct ceph_mds_client *mdsc);
 
+bool ceph_inc_mds_stopping_blocker(struct ceph_mds_client *mdsc,
+			       struct ceph_mds_session *session);
+void ceph_dec_mds_stopping_blocker(struct ceph_mds_client *mdsc);
 #endif /* _FS_CEPH_SUPER_H */

From 1464de9f813e35559ff049f1f1f20f1e2a31d6b8 Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Tue, 9 May 2023 16:38:49 +0800
Subject: [PATCH 0651/1189] ceph: wait for OSD requests' callbacks to finish
 when unmounting
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The sync_filesystem() will flush all the dirty buffer and submit the
osd reqs to the osdc and then is blocked to wait for all the reqs to
finish. But the when the reqs' replies come, the reqs will be removed
from osdc just before the req->r_callback()s are called. Which means
the sync_filesystem() will be woke up by leaving the req->r_callback()s
are still running.

This will be buggy when the waiter require the req->r_callback()s to
release some resources before continuing. So we need to make sure the
req->r_callback()s are called before removing the reqs from the osdc.

WARNING: CPU: 4 PID: 168846 at fs/crypto/keyring.c:242 fscrypt_destroy_keyring+0x7e/0xd0
CPU: 4 PID: 168846 Comm: umount Tainted: G S  6.1.0-rc5-ceph-g72ead199864c #1
Hardware name: Supermicro SYS-5018R-WR/X10SRW-F, BIOS 2.0 12/17/2015
RIP: 0010:fscrypt_destroy_keyring+0x7e/0xd0
RSP: 0018:ffffc9000b277e28 EFLAGS: 00010202
RAX: 0000000000000002 RBX: ffff88810d52ac00 RCX: ffff88810b56aa00
RDX: 0000000080000000 RSI: ffffffff822f3a09 RDI: ffff888108f59000
RBP: ffff8881d394fb88 R08: 0000000000000028 R09: 0000000000000000
R10: 0000000000000001 R11: 11ff4fe6834fcd91 R12: ffff8881d394fc40
R13: ffff888108f59000 R14: ffff8881d394f800 R15: 0000000000000000
FS:  00007fd83f6f1080(0000) GS:ffff88885fd00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f918d417000 CR3: 000000017f89a005 CR4: 00000000003706e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
<TASK>
generic_shutdown_super+0x47/0x120
kill_anon_super+0x14/0x30
ceph_kill_sb+0x36/0x90 [ceph]
deactivate_locked_super+0x29/0x60
cleanup_mnt+0xb8/0x140
task_work_run+0x67/0xb0
exit_to_user_mode_prepare+0x23d/0x240
syscall_exit_to_user_mode+0x25/0x60
do_syscall_64+0x40/0x80
entry_SYSCALL_64_after_hwframe+0x63/0xcd
RIP: 0033:0x7fd83dc39e9b

We need to increase the blocker counter to make sure all the osd
requests' callbacks have been finished just before calling the
kill_anon_super() when unmounting.

Link: https://tracker.ceph.com/issues/58126
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/addr.c  | 10 ++++++++++
 fs/ceph/super.c | 11 +++++++++++
 fs/ceph/super.h |  2 ++
 3 files changed, 23 insertions(+)

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 95ff84930dcf..f4863078f7fe 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -285,6 +285,7 @@ static void finish_netfs_read(struct ceph_osd_request *req)
 	}
 	netfs_subreq_terminated(subreq, err, false);
 	iput(req->r_inode);
+	ceph_dec_osd_stopping_blocker(fsc->mdsc);
 }
 
 static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq)
@@ -414,6 +415,10 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 	} else {
 		osd_req_op_extent_osd_iter(req, 0, &iter);
 	}
+	if (!ceph_inc_osd_stopping_blocker(fsc->mdsc)) {
+		err = -EIO;
+		goto out;
+	}
 	req->r_callback = finish_netfs_read;
 	req->r_priv = subreq;
 	req->r_inode = inode;
@@ -910,6 +915,7 @@ static void writepages_finish(struct ceph_osd_request *req)
 	else
 		kfree(osd_data->pages);
 	ceph_osdc_put_request(req);
+	ceph_dec_osd_stopping_blocker(fsc->mdsc);
 }
 
 /*
@@ -1218,6 +1224,10 @@ new_request:
 		BUG_ON(len < ceph_fscrypt_page_offset(pages[locked_pages - 1]) +
 			     thp_size(pages[locked_pages - 1]) - offset);
 
+		if (!ceph_inc_osd_stopping_blocker(fsc->mdsc)) {
+			rc = -EIO;
+			goto release_folios;
+		}
 		req->r_callback = writepages_finish;
 		req->r_inode = inode;
 
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 1c14d87ed871..2d7f5a8d4a92 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -1503,6 +1503,17 @@ void ceph_dec_mds_stopping_blocker(struct ceph_mds_client *mdsc)
 	__dec_stopping_blocker(mdsc);
 }
 
+/* For data IO requests */
+bool ceph_inc_osd_stopping_blocker(struct ceph_mds_client *mdsc)
+{
+	return __inc_stopping_blocker(mdsc);
+}
+
+void ceph_dec_osd_stopping_blocker(struct ceph_mds_client *mdsc)
+{
+	__dec_stopping_blocker(mdsc);
+}
+
 static void ceph_kill_sb(struct super_block *s)
 {
 	struct ceph_fs_client *fsc = ceph_sb_to_client(s);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index d8eb35d73a23..51c7f2b14f6f 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -1416,4 +1416,6 @@ extern void ceph_cleanup_quotarealms_inodes(struct ceph_mds_client *mdsc);
 bool ceph_inc_mds_stopping_blocker(struct ceph_mds_client *mdsc,
 			       struct ceph_mds_session *session);
 void ceph_dec_mds_stopping_blocker(struct ceph_mds_client *mdsc);
+bool ceph_inc_osd_stopping_blocker(struct ceph_mds_client *mdsc);
+void ceph_dec_osd_stopping_blocker(struct ceph_mds_client *mdsc);
 #endif /* _FS_CEPH_SUPER_H */

From 295fc4aa7de4b72cfd764b75a238f79b9433e3ec Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Mon, 6 Mar 2023 15:01:15 +0800
Subject: [PATCH 0652/1189] ceph: fix updating i_truncate_pagecache_size for
 fscrypt
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When fscrypt is enabled we will align the truncate size up to the
CEPH_FSCRYPT_BLOCK_SIZE always, so if we truncate the size in the
same block more than once, the latter ones will be skipped being
invalidated from the page caches.

This will force invalidating the page caches by using the smaller
size than the real file size.

At the same time add more debug log and fix the debug log for
truncate code.

Link: https://tracker.ceph.com/issues/58834
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-and-tested-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/caps.c  |  4 ++--
 fs/ceph/inode.c | 35 ++++++++++++++++++++++++-----------
 2 files changed, 26 insertions(+), 13 deletions(-)

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 54041d9c1e25..028b5140a85d 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -3950,8 +3950,8 @@ static bool handle_cap_trunc(struct inode *inode,
 	if (IS_ENCRYPTED(inode) && size)
 		size = extra_info->fscrypt_file_size;
 
-	dout("handle_cap_trunc inode %p mds%d seq %d to %lld seq %d\n",
-	     inode, mds, seq, truncate_size, truncate_seq);
+	dout("%s inode %p mds%d seq %d to %lld truncate seq %d\n",
+	     __func__, inode, mds, seq, truncate_size, truncate_seq);
 	queue_trunc = ceph_fill_file_size(inode, issued,
 					  truncate_seq, truncate_size, size);
 	return queue_trunc;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 83c420646f90..ea6f966dacd5 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -764,7 +764,7 @@ int ceph_fill_file_size(struct inode *inode, int issued,
 			ceph_fscache_update(inode);
 		ci->i_reported_size = size;
 		if (truncate_seq != ci->i_truncate_seq) {
-			dout("truncate_seq %u -> %u\n",
+			dout("%s truncate_seq %u -> %u\n", __func__,
 			     ci->i_truncate_seq, truncate_seq);
 			ci->i_truncate_seq = truncate_seq;
 
@@ -788,15 +788,26 @@ int ceph_fill_file_size(struct inode *inode, int issued,
 			}
 		}
 	}
-	if (ceph_seq_cmp(truncate_seq, ci->i_truncate_seq) >= 0 &&
-	    ci->i_truncate_size != truncate_size) {
-		dout("truncate_size %lld -> %llu\n", ci->i_truncate_size,
-		     truncate_size);
+
+	/*
+	 * It's possible that the new sizes of the two consecutive
+	 * size truncations will be in the same fscrypt last block,
+	 * and we need to truncate the corresponding page caches
+	 * anyway.
+	 */
+	if (ceph_seq_cmp(truncate_seq, ci->i_truncate_seq) >= 0) {
+		dout("%s truncate_size %lld -> %llu, encrypted %d\n", __func__,
+		     ci->i_truncate_size, truncate_size, !!IS_ENCRYPTED(inode));
+
 		ci->i_truncate_size = truncate_size;
-		if (IS_ENCRYPTED(inode))
+
+		if (IS_ENCRYPTED(inode)) {
+			dout("%s truncate_pagecache_size %lld -> %llu\n",
+			     __func__, ci->i_truncate_pagecache_size, size);
 			ci->i_truncate_pagecache_size = size;
-		else
+		} else {
 			ci->i_truncate_pagecache_size = truncate_size;
+		}
 	}
 	return queue_trunc;
 }
@@ -2155,7 +2166,7 @@ void __ceph_do_pending_vmtruncate(struct inode *inode)
 retry:
 	spin_lock(&ci->i_ceph_lock);
 	if (ci->i_truncate_pending == 0) {
-		dout("__do_pending_vmtruncate %p none pending\n", inode);
+		dout("%s %p none pending\n", __func__, inode);
 		spin_unlock(&ci->i_ceph_lock);
 		mutex_unlock(&ci->i_truncate_mutex);
 		return;
@@ -2167,8 +2178,7 @@ retry:
 	 */
 	if (ci->i_wrbuffer_ref_head < ci->i_wrbuffer_ref) {
 		spin_unlock(&ci->i_ceph_lock);
-		dout("__do_pending_vmtruncate %p flushing snaps first\n",
-		     inode);
+		dout("%s %p flushing snaps first\n", __func__, inode);
 		filemap_write_and_wait_range(&inode->i_data, 0,
 					     inode->i_sb->s_maxbytes);
 		goto retry;
@@ -2179,7 +2189,7 @@ retry:
 
 	to = ci->i_truncate_pagecache_size;
 	wrbuffer_refs = ci->i_wrbuffer_ref;
-	dout("__do_pending_vmtruncate %p (%d) to %lld\n", inode,
+	dout("%s %p (%d) to %lld\n", __func__, inode,
 	     ci->i_truncate_pending, to);
 	spin_unlock(&ci->i_ceph_lock);
 
@@ -2371,6 +2381,9 @@ static int fill_fscrypt_truncate(struct inode *inode,
 		header.data_len = cpu_to_le32(8 + 8 + 4 + CEPH_FSCRYPT_BLOCK_SIZE);
 		header.file_offset = cpu_to_le64(orig_pos);
 
+		dout("%s encrypt block boff/bsize %d/%lu\n", __func__,
+		     boff, CEPH_FSCRYPT_BLOCK_SIZE);
+
 		/* truncate and zero out the extra contents for the last block */
 		memset(iov.iov_base + boff, 0, PAGE_SIZE - boff);
 

From d9ae977d2d5635bde4fe75657417f5cffb14c954 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Lu=C3=ADs=20Henriques?= <lhenriques@suse.de>
Date: Thu, 16 Mar 2023 18:14:12 +0000
Subject: [PATCH 0653/1189] ceph: switch ceph_lookup/atomic_open() to use new
 fscrypt helper
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Instead of setting the no-key dentry, use the new
fscrypt_prepare_lookup_partial() helper.  We still need to mark the
directory as incomplete if the directory was just unlocked.

In ceph_atomic_open() this fixes a bug where a dentry is incorrectly
set with DCACHE_NOKEY_NAME when 'dir' has been evicted but the key is
still available (for example, where there's a drop_caches).

Signed-off-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/dir.c  | 13 +++++++------
 fs/ceph/file.c |  8 +++-----
 2 files changed, 10 insertions(+), 11 deletions(-)

diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 0e4f8e07022d..854cbdd66661 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -785,14 +785,15 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
 		return ERR_PTR(-ENAMETOOLONG);
 
 	if (IS_ENCRYPTED(dir)) {
-		err = ceph_fscrypt_prepare_readdir(dir);
+		bool had_key = fscrypt_has_encryption_key(dir);
+
+		err = fscrypt_prepare_lookup_partial(dir, dentry);
 		if (err < 0)
 			return ERR_PTR(err);
-		if (!fscrypt_has_encryption_key(dir)) {
-			spin_lock(&dentry->d_lock);
-			dentry->d_flags |= DCACHE_NOKEY_NAME;
-			spin_unlock(&dentry->d_lock);
-		}
+
+		/* mark directory as incomplete if it has been unlocked */
+		if (!had_key && fscrypt_has_encryption_key(dir))
+			ceph_dir_clear_complete(dir);
 	}
 
 	/* can we conclude ENOENT locally? */
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index e58787233e42..b1da02f5dbe3 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -791,11 +791,9 @@ retry:
 	ihold(dir);
 	if (IS_ENCRYPTED(dir)) {
 		set_bit(CEPH_MDS_R_FSCRYPT_FILE, &req->r_req_flags);
-		if (!fscrypt_has_encryption_key(dir)) {
-			spin_lock(&dentry->d_lock);
-			dentry->d_flags |= DCACHE_NOKEY_NAME;
-			spin_unlock(&dentry->d_lock);
-		}
+		err = fscrypt_prepare_lookup_partial(dir, dentry);
+		if (err < 0)
+			goto out_req;
 	}
 
 	if (flags & O_CREAT) {

From e6a28d6303a987a922b9107321d87592b2e6da77 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Wed, 23 Aug 2023 18:32:21 +0800
Subject: [PATCH 0654/1189] libceph: do not include crypto/algapi.h

The header file crypto/algapi.h is for internal use only.  Use the
header file crypto/utils.h instead.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 net/ceph/messenger_v2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index d0a1fb422617..d09a39ff2cf0 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -8,9 +8,9 @@
 #include <linux/ceph/ceph_debug.h>
 
 #include <crypto/aead.h>
-#include <crypto/algapi.h>  /* for crypto_memneq() */
 #include <crypto/hash.h>
 #include <crypto/sha2.h>
+#include <crypto/utils.h>
 #include <linux/bvec.h>
 #include <linux/crc32c.h>
 #include <linux/net.h>

From 50402641216292db807d286c44e6426cc3fcbf1e Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 23 Aug 2023 21:13:13 -0700
Subject: [PATCH 0655/1189] perf pmu: Make the loading of formats lazy

The sysfs format files are loaded eagerly in a PMU. Add a flag so that
we create the format but only load the contents when necessary.

Reduce the size of the value in struct perf_pmu_format and avoid holes
so there is no additional space requirement.

For "perf stat -e cycles true" this reduces the number of openat calls
from 648 to 573 (about 12%). The benchmark pmu scan speed is improved
by roughly 5%.

Before:

  $ perf bench internals pmu-scan
  Computing performance of sysfs PMU event scan for 100 times
    Average core PMU scanning took: 1061.100 usec (+- 9.965 usec)
    Average PMU scanning took: 4725.300 usec (+- 260.599 usec)

After:

  $ perf bench internals pmu-scan
  Computing performance of sysfs PMU event scan for 100 times
    Average core PMU scanning took: 989.170 usec (+- 6.873 usec)
    Average PMU scanning took: 4520.960 usec (+- 251.272 usec)

Committer testing:

On a AMD Ryzen 5950x:

Before:

  $ perf bench internals pmu-scan -i1000
  # Running 'internals/pmu-scan' benchmark:
  Computing performance of sysfs PMU event scan for 1000 times
    Average core PMU scanning took: 563.466 usec (+- 1.008 usec)
    Average PMU scanning took: 1619.174 usec (+- 23.627 usec)
  $ perf stat -r5 perf bench internals pmu-scan -i1000
  # Running 'internals/pmu-scan' benchmark:
  Computing performance of sysfs PMU event scan for 1000 times
    Average core PMU scanning took: 583.401 usec (+- 2.098 usec)
    Average PMU scanning took: 1677.352 usec (+- 24.636 usec)
  # Running 'internals/pmu-scan' benchmark:
  Computing performance of sysfs PMU event scan for 1000 times
    Average core PMU scanning took: 553.254 usec (+- 0.825 usec)
    Average PMU scanning took: 1635.655 usec (+- 24.312 usec)
  # Running 'internals/pmu-scan' benchmark:
  Computing performance of sysfs PMU event scan for 1000 times
    Average core PMU scanning took: 557.733 usec (+- 0.980 usec)
    Average PMU scanning took: 1600.659 usec (+- 23.344 usec)
  # Running 'internals/pmu-scan' benchmark:
  Computing performance of sysfs PMU event scan for 1000 times
    Average core PMU scanning took: 554.906 usec (+- 0.774 usec)
    Average PMU scanning took: 1595.338 usec (+- 23.288 usec)
  # Running 'internals/pmu-scan' benchmark:
  Computing performance of sysfs PMU event scan for 1000 times
    Average core PMU scanning took: 551.798 usec (+- 0.967 usec)
    Average PMU scanning took: 1623.213 usec (+- 23.998 usec)

   Performance counter stats for 'perf bench internals pmu-scan -i1000' (5 runs):

             3276.82 msec task-clock:u                     #    0.990 CPUs utilized               ( +-  0.82% )
                   0      context-switches:u               #    0.000 /sec
                   0      cpu-migrations:u                 #    0.000 /sec
                1008      page-faults:u                    #  307.615 /sec                        ( +-  0.04% )
         12049614778      cycles:u                         #    3.677 GHz                         ( +-  0.07% )  (83.34%)
           117507478      stalled-cycles-frontend:u        #    0.98% frontend cycles idle        ( +-  0.33% )  (83.32%)
            27106761      stalled-cycles-backend:u         #    0.22% backend cycles idle         ( +-  9.55% )  (83.36%)
         33294953848      instructions:u                   #    2.76  insn per cycle
                                                           #    0.00  stalled cycles per insn     ( +-  0.03% )  (83.31%)
          6849825049      branches:u                       #    2.090 G/sec                       ( +-  0.03% )  (83.37%)
            71533903      branch-misses:u                  #    1.04% of all branches             ( +-  0.20% )  (83.30%)

              3.3088 +- 0.0302 seconds time elapsed  ( +-  0.91% )

  $

After:

  $ perf stat -r5 perf bench internals pmu-scan -i1000
  # Running 'internals/pmu-scan' benchmark:
  Computing performance of sysfs PMU event scan for 1000 times
    Average core PMU scanning took: 550.702 usec (+- 0.958 usec)
    Average PMU scanning took: 1566.577 usec (+- 22.747 usec)
  # Running 'internals/pmu-scan' benchmark:
  Computing performance of sysfs PMU event scan for 1000 times
    Average core PMU scanning took: 548.315 usec (+- 0.555 usec)
    Average PMU scanning took: 1565.499 usec (+- 22.760 usec)
  # Running 'internals/pmu-scan' benchmark:
  Computing performance of sysfs PMU event scan for 1000 times
    Average core PMU scanning took: 548.073 usec (+- 0.555 usec)
    Average PMU scanning took: 1586.097 usec (+- 23.299 usec)
  # Running 'internals/pmu-scan' benchmark:
  Computing performance of sysfs PMU event scan for 1000 times
    Average core PMU scanning took: 561.184 usec (+- 2.709 usec)
    Average PMU scanning took: 1567.153 usec (+- 22.548 usec)
  # Running 'internals/pmu-scan' benchmark:
  Computing performance of sysfs PMU event scan for 1000 times
    Average core PMU scanning took: 546.987 usec (+- 0.553 usec)
    Average PMU scanning took: 1562.814 usec (+- 22.729 usec)

   Performance counter stats for 'perf bench internals pmu-scan -i1000' (5 runs):

             3170.86 msec task-clock:u                     #    0.992 CPUs utilized               ( +-  0.22% )
                   0      context-switches:u               #    0.000 /sec
                   0      cpu-migrations:u                 #    0.000 /sec
                1010      page-faults:u                    #  318.526 /sec                        ( +-  0.04% )
         11890047674      cycles:u                         #    3.750 GHz                         ( +-  0.14% )  (83.27%)
           119090499      stalled-cycles-frontend:u        #    1.00% frontend cycles idle        ( +-  0.46% )  (83.40%)
            32502449      stalled-cycles-backend:u         #    0.27% backend cycles idle         ( +-  8.32% )  (83.30%)
         33119141261      instructions:u                   #    2.79  insn per cycle
                                                    #    0.00  stalled cycles per insn     ( +-  0.01% )  (83.37%)
          6812816561      branches:u                       #    2.149 G/sec                       ( +-  0.01% )  (83.29%)
            70157855      branch-misses:u                  #    1.03% of all branches             ( +-  0.28% )  (83.38%)

             3.19710 +- 0.00826 seconds time elapsed  ( +-  0.26% )

  $

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230824041330.266337-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/pmu.c |   2 +-
 tools/perf/util/pmu.c  | 144 +++++++++++++++++++++++++++--------------
 tools/perf/util/pmu.h  |   5 +-
 tools/perf/util/pmu.y  |  20 ++----
 4 files changed, 106 insertions(+), 65 deletions(-)

diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index 2c1c349a42e2..c204ed1f1a8b 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -171,7 +171,7 @@ static int test__pmu(struct test_suite *test __maybe_unused, int subtest __maybe
 	}
 
 	pmu->name = strdup("perf-pmu-test");
-	ret = perf_pmu__format_parse(pmu, fd);
+	ret = perf_pmu__format_parse(pmu, fd, /*eager_load=*/true);
 	if (ret)
 		goto out;
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 42f3249994ab..3cfd3e58da23 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -40,6 +40,10 @@ struct perf_pmu perf_pmu__fake;
  * value=PERF_PMU_FORMAT_VALUE_CONFIG and bits 0 to 7 will be set.
  */
 struct perf_pmu_format {
+	/** @list: Element on list within struct perf_pmu. */
+	struct list_head list;
+	/** @bits: Which config bits are set by this format value. */
+	DECLARE_BITMAP(bits, PERF_PMU_FORMAT_BITS);
 	/** @name: The modifier/file name. */
 	char *name;
 	/**
@@ -47,18 +51,79 @@ struct perf_pmu_format {
 	 * are from PERF_PMU_FORMAT_VALUE_CONFIG to
 	 * PERF_PMU_FORMAT_VALUE_CONFIG_END.
 	 */
-	int value;
-	/** @bits: Which config bits are set by this format value. */
-	DECLARE_BITMAP(bits, PERF_PMU_FORMAT_BITS);
-	/** @list: Element on list within struct perf_pmu. */
-	struct list_head list;
+	u16 value;
+	/** @loaded: Has the contents been loaded/parsed. */
+	bool loaded;
 };
 
+static struct perf_pmu_format *perf_pmu__new_format(struct list_head *list, char *name)
+{
+	struct perf_pmu_format *format;
+
+	format = zalloc(sizeof(*format));
+	if (!format)
+		return NULL;
+
+	format->name = strdup(name);
+	if (!format->name) {
+		free(format);
+		return NULL;
+	}
+	list_add_tail(&format->list, list);
+	return format;
+}
+
+/* Called at the end of parsing a format. */
+void perf_pmu_format__set_value(void *vformat, int config, unsigned long *bits)
+{
+	struct perf_pmu_format *format = vformat;
+
+	format->value = config;
+	memcpy(format->bits, bits, sizeof(format->bits));
+}
+
+static void __perf_pmu_format__load(struct perf_pmu_format *format, FILE *file)
+{
+	void *scanner;
+	int ret;
+
+	ret = perf_pmu_lex_init(&scanner);
+	if (ret)
+		return;
+
+	perf_pmu_set_in(file, scanner);
+	ret = perf_pmu_parse(format, scanner);
+	perf_pmu_lex_destroy(scanner);
+	format->loaded = true;
+}
+
+static void perf_pmu_format__load(struct perf_pmu *pmu, struct perf_pmu_format *format)
+{
+	char path[PATH_MAX];
+	FILE *file = NULL;
+
+	if (format->loaded)
+		return;
+
+	if (!perf_pmu__pathname_scnprintf(path, sizeof(path), pmu->name, "format"))
+		return;
+
+	assert(strlen(path) + strlen(format->name) + 2 < sizeof(path));
+	strcat(path, "/");
+	strcat(path, format->name);
+
+	file = fopen(path, "r");
+	if (!file)
+		return;
+	__perf_pmu_format__load(format, file);
+	fclose(file);
+}
+
 /*
  * Parse & process all the sysfs attributes located under
  * the directory specified in 'dir' parameter.
  */
-int perf_pmu__format_parse(struct perf_pmu *pmu, int dirfd)
+int perf_pmu__format_parse(struct perf_pmu *pmu, int dirfd, bool eager_load)
 {
 	struct dirent *evt_ent;
 	DIR *format_dir;
@@ -68,37 +133,35 @@ int perf_pmu__format_parse(struct perf_pmu *pmu, int dirfd)
 	if (!format_dir)
 		return -EINVAL;
 
-	while (!ret && (evt_ent = readdir(format_dir))) {
+	while ((evt_ent = readdir(format_dir)) != NULL) {
+		struct perf_pmu_format *format;
 		char *name = evt_ent->d_name;
-		int fd;
-		void *scanner;
-		FILE *file;
 
 		if (!strcmp(name, ".") || !strcmp(name, ".."))
 			continue;
 
-
-		ret = -EINVAL;
-		fd = openat(dirfd, name, O_RDONLY);
-		if (fd < 0)
-			break;
-
-		file = fdopen(fd, "r");
-		if (!file) {
-			close(fd);
+		format = perf_pmu__new_format(&pmu->format, name);
+		if (!format) {
+			ret = -ENOMEM;
 			break;
 		}
 
-		ret = perf_pmu_lex_init(&scanner);
-		if (ret) {
+		if (eager_load) {
+			FILE *file;
+			int fd = openat(dirfd, name, O_RDONLY);
+
+			if (fd < 0) {
+				ret = -errno;
+				break;
+			}
+			file = fdopen(fd, "r");
+			if (!file) {
+				close(fd);
+				break;
+			}
+			__perf_pmu_format__load(format, file);
 			fclose(file);
-			break;
 		}
-
-		perf_pmu_set_in(file, scanner);
-		ret = perf_pmu_parse(&pmu->format, name, scanner);
-		perf_pmu_lex_destroy(scanner);
-		fclose(file);
 	}
 
 	closedir(format_dir);
@@ -119,7 +182,7 @@ static int pmu_format(struct perf_pmu *pmu, int dirfd, const char *name)
 		return 0;
 
 	/* it'll close the fd */
-	if (perf_pmu__format_parse(pmu, fd))
+	if (perf_pmu__format_parse(pmu, fd, /*eager_load=*/false))
 		return -1;
 
 	return 0;
@@ -962,13 +1025,15 @@ void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu)
 	if (pmu == &perf_pmu__fake)
 		return;
 
-	list_for_each_entry(format, &pmu->format, list)
+	list_for_each_entry(format, &pmu->format, list) {
+		perf_pmu_format__load(pmu, format);
 		if (format->value >= PERF_PMU_FORMAT_VALUE_CONFIG_END) {
 			pr_warning("WARNING: '%s' format '%s' requires 'perf_event_attr::config%d'"
 				   "which is not supported by this version of perf!\n",
 				   pmu->name, format->name, format->value);
 			return;
 		}
+	}
 }
 
 bool evsel__is_aux_event(const struct evsel *evsel)
@@ -1041,6 +1106,7 @@ int perf_pmu__format_type(struct perf_pmu *pmu, const char *name)
 	if (!format)
 		return -1;
 
+	perf_pmu_format__load(pmu, format);
 	return format->value;
 }
 
@@ -1177,7 +1243,7 @@ static int pmu_config_term(struct perf_pmu *pmu,
 		free(pmu_term);
 		return -EINVAL;
 	}
-
+	perf_pmu_format__load(pmu, format);
 	switch (format->value) {
 	case PERF_PMU_FORMAT_VALUE_CONFIG:
 		vp = &attr->config;
@@ -1403,24 +1469,6 @@ struct perf_pmu_alias *perf_pmu__find_alias(struct perf_pmu *pmu, const char *ev
 
 	return NULL;
 }
-
-int perf_pmu__new_format(struct list_head *list, char *name,
-			 int config, unsigned long *bits)
-{
-	struct perf_pmu_format *format;
-
-	format = zalloc(sizeof(*format));
-	if (!format)
-		return -ENOMEM;
-
-	format->name = strdup(name);
-	format->value = config;
-	memcpy(format->bits, bits, sizeof(format->bits));
-
-	list_add_tail(&format->list, list);
-	return 0;
-}
-
 static void perf_pmu__del_formats(struct list_head *formats)
 {
 	struct perf_pmu_format *fmt, *tmp;
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index c4268053c979..675c9b97f7bf 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -227,9 +227,8 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 			  struct perf_pmu_info *info);
 struct perf_pmu_alias *perf_pmu__find_alias(struct perf_pmu *pmu, const char *event);
 
-int perf_pmu__new_format(struct list_head *list, char *name,
-			 int config, unsigned long *bits);
-int perf_pmu__format_parse(struct perf_pmu *pmu, int dirfd);
+int perf_pmu__format_parse(struct perf_pmu *pmu, int dirfd, bool eager_load);
+void perf_pmu_format__set_value(void *format, int config, unsigned long *bits);
 bool perf_pmu__has_format(const struct perf_pmu *pmu, const char *name);
 
 bool is_pmu_core(const char *name);
diff --git a/tools/perf/util/pmu.y b/tools/perf/util/pmu.y
index d861a5bfa3bd..600c8c158c8e 100644
--- a/tools/perf/util/pmu.y
+++ b/tools/perf/util/pmu.y
@@ -1,6 +1,5 @@
 %define api.pure full
-%parse-param {struct list_head *format}
-%parse-param {char *name}
+%parse-param {void *format}
 %parse-param {void *scanner}
 %lex-param {void* scanner}
 
@@ -21,7 +20,7 @@ do { \
                 YYABORT; \
 } while (0)
 
-static void perf_pmu_error(struct list_head *list, char *name, void *scanner, char const *msg);
+static void perf_pmu_error(void *format, void *scanner, const char *msg);
 
 static void perf_pmu__set_format(unsigned long *bits, long from, long to)
 {
@@ -59,16 +58,12 @@ format_term
 format_term:
 PP_CONFIG ':' bits
 {
-	ABORT_ON(perf_pmu__new_format(format, name,
-				      PERF_PMU_FORMAT_VALUE_CONFIG,
-				      $3));
+	perf_pmu_format__set_value(format, PERF_PMU_FORMAT_VALUE_CONFIG, $3);
 }
 |
 PP_CONFIG PP_VALUE ':' bits
 {
-	ABORT_ON(perf_pmu__new_format(format, name,
-				      $2,
-				      $4));
+	perf_pmu_format__set_value(format, $2, $4);
 }
 
 bits:
@@ -95,9 +90,8 @@ PP_VALUE
 
 %%
 
-static void perf_pmu_error(struct list_head *list __maybe_unused,
-		    char *name __maybe_unused,
-		    void *scanner __maybe_unused,
-		    char const *msg __maybe_unused)
+static void perf_pmu_error(void *format __maybe_unused,
+			   void *scanner __maybe_unused,
+			   const char *msg __maybe_unused)
 {
 }

From c3245d2093c16c60bddc2ec5e945354ffe16bb95 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 23 Aug 2023 21:13:14 -0700
Subject: [PATCH 0656/1189] perf pmu: Abstract alias/event struct

In order to be able to lazily compute aliases/events for a PMU, move
the struct perf_pmu_alias into pmu.c.

Add perf_pmu__find_event and perf_pmu__for_each_event that take a
callback that is called for the found event or for each event.

The layout of struct pmu and the event/alias list is unchanged but the
API is altered so that aliases are no longer directly accessed, allowing
for later changes.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230824041330.266337-3-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/bench/pmu-scan.c    |   8 +-
 tools/perf/tests/pmu-events.c  |  97 +++++++-------
 tools/perf/util/parse-events.c |  67 ++++------
 tools/perf/util/pmu.c          | 212 +++++++++++++++++++++++++++---
 tools/perf/util/pmu.h          |  71 +++-------
 tools/perf/util/pmus.c         | 232 +++++++++++----------------------
 6 files changed, 365 insertions(+), 322 deletions(-)

diff --git a/tools/perf/bench/pmu-scan.c b/tools/perf/bench/pmu-scan.c
index c7d207f8e13c..9e4d36486f62 100644
--- a/tools/perf/bench/pmu-scan.c
+++ b/tools/perf/bench/pmu-scan.c
@@ -57,9 +57,7 @@ static int save_result(void)
 		r->is_core = pmu->is_core;
 		r->nr_caps = pmu->nr_caps;
 
-		r->nr_aliases = 0;
-		list_for_each(list, &pmu->aliases)
-			r->nr_aliases++;
+		r->nr_aliases = perf_pmu__num_events(pmu);
 
 		r->nr_formats = 0;
 		list_for_each(list, &pmu->format)
@@ -98,9 +96,7 @@ static int check_result(bool core_only)
 			return -1;
 		}
 
-		nr = 0;
-		list_for_each(list, &pmu->aliases)
-			nr++;
+		nr = perf_pmu__num_events(pmu);
 		if (nr != r->nr_aliases) {
 			pr_err("Unmatched number of event aliases in %s: expect %d vs got %d\n",
 				pmu->name, r->nr_aliases, nr);
diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
index 05d6e6e21c6f..dc87e66fb118 100644
--- a/tools/perf/tests/pmu-events.c
+++ b/tools/perf/tests/pmu-events.c
@@ -341,7 +341,7 @@ static int compare_pmu_events(const struct pmu_event *e1, const struct pmu_event
 	return 0;
 }
 
-static int compare_alias_to_test_event(struct perf_pmu_alias *alias,
+static int compare_alias_to_test_event(struct pmu_event_info *alias,
 				struct perf_pmu_test_event const *test_event,
 				char const *pmu_name)
 {
@@ -496,6 +496,23 @@ static int test__pmu_event_table(struct test_suite *test __maybe_unused,
 	return 0;
 }
 
+struct test_core_pmu_event_aliases_cb_args {
+	struct perf_pmu_test_event const *test_event;
+	int *count;
+};
+
+static int test_core_pmu_event_aliases_cb(void *state, struct pmu_event_info *alias)
+{
+	struct test_core_pmu_event_aliases_cb_args *args = state;
+
+	if (compare_alias_to_test_event(alias, args->test_event, alias->pmu->name))
+		return -1;
+	(*args->count)++;
+	pr_debug2("testing aliases core PMU %s: matched event %s\n",
+		alias->pmu_name, alias->name);
+	return 0;
+}
+
 /* Verify aliases are as expected */
 static int __test_core_pmu_event_aliases(char *pmu_name, int *count)
 {
@@ -522,25 +539,19 @@ static int __test_core_pmu_event_aliases(char *pmu_name, int *count)
 	pmu_add_cpu_aliases_table(pmu, table);
 
 	for (; *test_event_table; test_event_table++) {
-		struct perf_pmu_test_event const *test_event = *test_event_table;
-		struct pmu_event const *event = &test_event->event;
-		struct perf_pmu_alias *alias = perf_pmu__find_alias(pmu, event->name);
+		struct perf_pmu_test_event test_event = **test_event_table;
+		struct pmu_event const *event = &test_event.event;
+		struct test_core_pmu_event_aliases_cb_args args = {
+			.test_event = &test_event,
+			.count = count,
+		};
+		int err;
 
-		if (!alias) {
-			pr_debug("testing aliases core PMU %s: no alias, alias_table->name=%s\n",
-				  pmu_name, event->name);
-			res = -1;
-			break;
-		}
-
-		if (compare_alias_to_test_event(alias, test_event, pmu_name)) {
-			res = -1;
-			break;
-		}
-
-		(*count)++;
-		pr_debug2("testing aliases core PMU %s: matched event %s\n",
-			  pmu_name, alias->name);
+		test_event.event.pmu = pmu_name;
+		err = perf_pmu__find_event(pmu, event->name, &args,
+					   test_core_pmu_event_aliases_cb);
+		if (err)
+			res = err;
 	}
 	perf_pmu__delete(pmu);
 
@@ -553,7 +564,6 @@ static int __test_uncore_pmu_event_aliases(struct perf_pmu_test_pmu *test_pmu)
 	struct perf_pmu_test_event const **table;
 	struct perf_pmu *pmu = &test_pmu->pmu;
 	const char *pmu_name = pmu->name;
-	struct perf_pmu_alias *a, *tmp, *alias;
 	const struct pmu_events_table *events_table;
 	int res = 0;
 
@@ -564,8 +574,7 @@ static int __test_uncore_pmu_event_aliases(struct perf_pmu_test_pmu *test_pmu)
 	pmu_add_sys_aliases(pmu);
 
 	/* Count how many aliases we generated */
-	list_for_each_entry(alias, &pmu->aliases, list)
-		alias_count++;
+	alias_count = perf_pmu__num_events(pmu);
 
 	/* Count how many aliases we expect from the known table */
 	for (table = &test_pmu->aliases[0]; *table; table++)
@@ -574,33 +583,25 @@ static int __test_uncore_pmu_event_aliases(struct perf_pmu_test_pmu *test_pmu)
 	if (alias_count != to_match_count) {
 		pr_debug("testing aliases uncore PMU %s: mismatch expected aliases (%d) vs found (%d)\n",
 			 pmu_name, to_match_count, alias_count);
-		res = -1;
-		goto out;
+		return -1;
 	}
 
-	list_for_each_entry(alias, &pmu->aliases, list) {
-		bool matched = false;
+	for (table = &test_pmu->aliases[0]; *table; table++) {
+		struct perf_pmu_test_event test_event = **table;
+		struct pmu_event const *event = &test_event.event;
+		int err;
+		struct test_core_pmu_event_aliases_cb_args args = {
+			.test_event = &test_event,
+			.count = &matched_count,
+		};
 
-		for (table = &test_pmu->aliases[0]; *table; table++) {
-			struct perf_pmu_test_event const *test_event = *table;
-			struct pmu_event const *event = &test_event->event;
-
-			if (!strcmp(event->name, alias->name)) {
-				if (compare_alias_to_test_event(alias,
-							test_event,
-							pmu_name)) {
-					continue;
-				}
-				matched = true;
-				matched_count++;
-			}
-		}
-
-		if (matched == false) {
+		err = perf_pmu__find_event(pmu, event->name, &args,
+					   test_core_pmu_event_aliases_cb);
+		if (err) {
+			res = err;
 			pr_debug("testing aliases uncore PMU %s: could not match alias %s\n",
-				 pmu_name, alias->name);
-			res = -1;
-			goto out;
+				 pmu_name, event->name);
+			return -1;
 		}
 	}
 
@@ -609,12 +610,6 @@ static int __test_uncore_pmu_event_aliases(struct perf_pmu_test_pmu *test_pmu)
 			 pmu_name, matched_count, alias_count);
 		res = -1;
 	}
-
-out:
-	list_for_each_entry_safe(a, tmp, &pmu->aliases, list) {
-		list_del(&a->list);
-		perf_pmu_free_alias(a);
-	}
 	return res;
 }
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 7d9d687d9191..7cad82a9f578 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -193,38 +193,31 @@ static void fix_raw(struct list_head *config_terms, struct perf_pmu *pmu)
 	struct parse_events_term *term;
 
 	list_for_each_entry(term, config_terms, list) {
-		struct perf_pmu_alias *alias;
-		bool matched = false;
+		u64 num;
 
 		if (term->type_term != PARSE_EVENTS__TERM_TYPE_RAW)
 			continue;
 
-		list_for_each_entry(alias, &pmu->aliases, list) {
-			if (!strcmp(alias->name, term->val.str)) {
-				free(term->config);
-				term->config = term->val.str;
-				term->type_val = PARSE_EVENTS__TERM_TYPE_NUM;
-				term->type_term = PARSE_EVENTS__TERM_TYPE_USER;
-				term->val.num = 1;
-				term->no_value = true;
-				matched = true;
-				break;
-			}
-		}
-		if (!matched) {
-			u64 num;
-
+		if (perf_pmu__have_event(pmu, term->val.str)) {
 			free(term->config);
-			term->config = strdup("config");
-			errno = 0;
-			num = strtoull(term->val.str + 1, NULL, 16);
-			assert(errno == 0);
-			free(term->val.str);
+			term->config = term->val.str;
 			term->type_val = PARSE_EVENTS__TERM_TYPE_NUM;
-			term->type_term = PARSE_EVENTS__TERM_TYPE_CONFIG;
-			term->val.num = num;
-			term->no_value = false;
+			term->type_term = PARSE_EVENTS__TERM_TYPE_USER;
+			term->val.num = 1;
+			term->no_value = true;
+			continue;
 		}
+
+		free(term->config);
+		term->config = strdup("config");
+		errno = 0;
+		num = strtoull(term->val.str + 1, NULL, 16);
+		assert(errno == 0);
+		free(term->val.str);
+		term->type_val = PARSE_EVENTS__TERM_TYPE_NUM;
+		term->type_term = PARSE_EVENTS__TERM_TYPE_CONFIG;
+		term->val.num = num;
+		term->no_value = false;
 	}
 }
 
@@ -1458,28 +1451,22 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 	INIT_LIST_HEAD(list);
 
 	while ((pmu = perf_pmus__scan(pmu)) != NULL) {
-		struct perf_pmu_alias *alias;
 		bool auto_merge_stats;
 
 		if (parse_events__filter_pmu(parse_state, pmu))
 			continue;
 
-		auto_merge_stats = perf_pmu__auto_merge_stats(pmu);
+		if (!perf_pmu__have_event(pmu, str))
+			continue;
 
-		list_for_each_entry(alias, &pmu->aliases, list) {
-			if (!strcasecmp(alias->name, str)) {
-				parse_events_copy_term_list(head, &orig_head);
-				if (!parse_events_add_pmu(parse_state, list,
-							  pmu->name, orig_head,
-							  auto_merge_stats, loc)) {
-					pr_debug("%s -> %s/%s/\n", str,
-						 pmu->name, alias->str);
-					parse_state->wild_card_pmus = true;
-					ok++;
-				}
-				parse_events_terms__delete(orig_head);
-			}
+		auto_merge_stats = perf_pmu__auto_merge_stats(pmu);
+		parse_events_copy_term_list(head, &orig_head);
+		if (!parse_events_add_pmu(parse_state, list, pmu->name,
+					  orig_head, auto_merge_stats, loc)) {
+			pr_debug("%s -> %s/%s/\n", str, pmu->name, str);
+			ok++;
 		}
+		parse_events_terms__delete(orig_head);
 	}
 
 	if (parse_state->fake_pmu) {
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 3cfd3e58da23..268aaebfa70c 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -31,6 +31,61 @@
 
 struct perf_pmu perf_pmu__fake;
 
+#define UNIT_MAX_LEN	31 /* max length for event unit name */
+
+/**
+ * struct perf_pmu_alias - An event either read from sysfs or builtin in
+ * pmu-events.c, created by parsing the pmu-events json files.
+ */
+struct perf_pmu_alias {
+	/** @name: Name of the event like "mem-loads". */
+	char *name;
+	/** @desc: Optional short description of the event. */
+	char *desc;
+	/** @long_desc: Optional long description. */
+	char *long_desc;
+	/**
+	 * @topic: Optional topic such as cache or pipeline, particularly for
+	 * json events.
+	 */
+	char *topic;
+	/**
+	 * @str: Comma separated parameter list like
+	 * "event=0xcd,umask=0x1,ldlat=0x3".
+	 */
+	char *str;
+	/** @terms: Owned list of the original parsed parameters. */
+	struct list_head terms;
+	/** @list: List element of struct perf_pmu aliases. */
+	struct list_head list;
+	/** @unit: Units for the event, such as bytes or cache lines. */
+	char unit[UNIT_MAX_LEN+1];
+	/** @scale: Value to scale read counter values by. */
+	double scale;
+	/**
+	 * @per_pkg: Does the file
+	 * <sysfs>/bus/event_source/devices/<pmu_name>/events/<name>.per-pkg or
+	 * equivalent json value exist and have the value 1.
+	 */
+	bool per_pkg;
+	/**
+	 * @snapshot: Does the file
+	 * <sysfs>/bus/event_source/devices/<pmu_name>/events/<name>.snapshot
+	 * exist and have the value 1.
+	 */
+	bool snapshot;
+	/**
+	 * @deprecated: Is the event hidden and so not shown in perf list by
+	 * default.
+	 */
+	bool deprecated;
+	/**
+	 * @pmu_name: The name copied from the json struct pmu_event. This can
+	 * differ from the PMU name as it won't have suffixes.
+	 */
+	char *pmu_name;
+};
+
 /**
  * struct perf_pmu_format - Values from a format file read from
  * <sysfs>/devices/cpu/format/ held in struct perf_pmu.
@@ -355,7 +410,7 @@ static void perf_pmu_update_alias(struct perf_pmu_alias *old,
 }
 
 /* Delete an alias entry. */
-void perf_pmu_free_alias(struct perf_pmu_alias *newalias)
+static void perf_pmu_free_alias(struct perf_pmu_alias *newalias)
 {
 	zfree(&newalias->name);
 	zfree(&newalias->desc);
@@ -1349,10 +1404,20 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 	return perf_pmu__config_terms(pmu, attr, head_terms, zero, err);
 }
 
+static struct perf_pmu_alias *perf_pmu__find_alias(const struct perf_pmu *pmu, const char *str)
+{
+	struct perf_pmu_alias *alias;
+
+	list_for_each_entry(alias, &pmu->aliases, list) {
+		if (!strcasecmp(alias->name, str))
+			return alias;
+	}
+	return NULL;
+}
+
 static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
 					     struct parse_events_term *term)
 {
-	struct perf_pmu_alias *alias;
 	char *name;
 
 	if (parse_events__is_hardcoded_term(term))
@@ -1364,6 +1429,7 @@ static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
 		if (pmu_find_format(&pmu->format, term->config))
 			return NULL;
 		name = term->config;
+
 	} else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) {
 		if (strcasecmp(term->config, "event"))
 			return NULL;
@@ -1372,11 +1438,7 @@ static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
 		return NULL;
 	}
 
-	list_for_each_entry(alias, &pmu->aliases, list) {
-		if (!strcasecmp(alias->name, name))
-			return alias;
-	}
-	return NULL;
+	return perf_pmu__find_alias(pmu, name);
 }
 
 
@@ -1459,16 +1521,33 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 	return 0;
 }
 
-struct perf_pmu_alias *perf_pmu__find_alias(struct perf_pmu *pmu, const char *event)
+struct find_event_args {
+	const char *event;
+	void *state;
+	pmu_event_callback cb;
+};
+
+static int find_event_callback(void *state, struct pmu_event_info *info)
 {
-	struct perf_pmu_alias *alias;
+	struct find_event_args *args = state;
 
-	list_for_each_entry(alias, &pmu->aliases, list)
-		if (!strcmp(event, alias->name))
-			return alias;
+	if (!strcmp(args->event, info->name))
+		return args->cb(args->state, info);
 
-	return NULL;
+	return 0;
 }
+
+int perf_pmu__find_event(struct perf_pmu *pmu, const char *event, void *state, pmu_event_callback cb)
+{
+	struct find_event_args args = {
+		.event = event,
+		.state = state,
+		.cb = cb,
+	};
+
+	return perf_pmu__for_each_event(pmu, &args, find_event_callback);
+}
+
 static void perf_pmu__del_formats(struct list_head *formats)
 {
 	struct perf_pmu_format *fmt, *tmp;
@@ -1508,13 +1587,110 @@ bool perf_pmu__auto_merge_stats(const struct perf_pmu *pmu)
 
 bool perf_pmu__have_event(const struct perf_pmu *pmu, const char *name)
 {
-	struct perf_pmu_alias *alias;
+	return perf_pmu__find_alias(pmu, name) != NULL;
+}
 
-	list_for_each_entry(alias, &pmu->aliases, list) {
-		if (!strcmp(alias->name, name))
-			return true;
+size_t perf_pmu__num_events(const struct perf_pmu *pmu)
+{
+	struct list_head *list;
+	size_t nr = 0;
+
+	list_for_each(list, &pmu->aliases)
+		nr++;
+
+	return pmu->selectable ? nr + 1 : nr;
+}
+
+static int sub_non_neg(int a, int b)
+{
+	if (b > a)
+		return 0;
+	return a - b;
+}
+
+static char *format_alias(char *buf, int len, const struct perf_pmu *pmu,
+			  const struct perf_pmu_alias *alias)
+{
+	struct parse_events_term *term;
+	int used = snprintf(buf, len, "%s/%s", pmu->name, alias->name);
+
+	list_for_each_entry(term, &alias->terms, list) {
+		if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR)
+			used += snprintf(buf + used, sub_non_neg(len, used),
+					",%s=%s", term->config,
+					term->val.str);
 	}
-	return false;
+
+	if (sub_non_neg(len, used) > 0) {
+		buf[used] = '/';
+		used++;
+	}
+	if (sub_non_neg(len, used) > 0) {
+		buf[used] = '\0';
+		used++;
+	} else
+		buf[len - 1] = '\0';
+
+	return buf;
+}
+
+int perf_pmu__for_each_event(const struct perf_pmu *pmu, void *state, pmu_event_callback cb)
+{
+	char buf[1024];
+	struct perf_pmu_alias *event;
+	struct pmu_event_info info = {
+		.pmu = pmu,
+	};
+	int ret = 0;
+
+	list_for_each_entry(event, &pmu->aliases, list) {
+		size_t buf_used;
+
+		info.pmu_name = event->pmu_name ?: pmu->name;
+		info.alias = NULL;
+		if (event->desc) {
+			info.name = event->name;
+			buf_used = 0;
+		} else {
+			info.name = format_alias(buf, sizeof(buf), pmu, event);
+			if (pmu->is_core) {
+				info.alias = info.name;
+				info.name = event->name;
+			}
+			buf_used = strlen(buf) + 1;
+		}
+		info.scale_unit = NULL;
+		if (strlen(event->unit) || event->scale != 1.0) {
+			info.scale_unit = buf + buf_used;
+			buf_used += snprintf(buf + buf_used, sizeof(buf) - buf_used,
+					"%G%s", event->scale, event->unit) + 1;
+		}
+		info.desc = event->desc;
+		info.long_desc = event->long_desc;
+		info.encoding_desc = buf + buf_used;
+		buf_used += snprintf(buf + buf_used, sizeof(buf) - buf_used,
+				"%s/%s/", info.pmu_name, event->str) + 1;
+		info.topic = event->topic;
+		info.str = event->str;
+		info.deprecated = event->deprecated;
+		ret = cb(state, &info);
+		if (ret)
+			return ret;
+	}
+	if (pmu->selectable) {
+		info.name = buf;
+		snprintf(buf, sizeof(buf), "%s//", pmu->name);
+		info.alias = NULL;
+		info.scale_unit = NULL;
+		info.desc = NULL;
+		info.long_desc = NULL;
+		info.encoding_desc = NULL;
+		info.topic = NULL;
+		info.pmu_name = pmu->name;
+		info.deprecated = false;
+		ret = cb(state, &info);
+	}
+	return ret;
 }
 
 bool perf_pmu__is_software(const struct perf_pmu *pmu)
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 675c9b97f7bf..f37e3d75094f 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -158,61 +158,22 @@ struct perf_pmu_info {
 	bool snapshot;
 };
 
-#define UNIT_MAX_LEN	31 /* max length for event unit name */
-
-/**
- * struct perf_pmu_alias - An event either read from sysfs or builtin in
- * pmu-events.c, created by parsing the pmu-events json files.
- */
-struct perf_pmu_alias {
-	/** @name: Name of the event like "mem-loads". */
-	char *name;
-	/** @desc: Optional short description of the event. */
-	char *desc;
-	/** @long_desc: Optional long description. */
-	char *long_desc;
-	/**
-	 * @topic: Optional topic such as cache or pipeline, particularly for
-	 * json events.
-	 */
-	char *topic;
-	/**
-	 * @str: Comma separated parameter list like
-	 * "event=0xcd,umask=0x1,ldlat=0x3".
-	 */
-	char *str;
-	/** @terms: Owned list of the original parsed parameters. */
-	struct list_head terms;
-	/** @list: List element of struct perf_pmu aliases. */
-	struct list_head list;
-	/** @unit: Units for the event, such as bytes or cache lines. */
-	char unit[UNIT_MAX_LEN+1];
-	/** @scale: Value to scale read counter values by. */
-	double scale;
-	/**
-	 * @per_pkg: Does the file
-	 * <sysfs>/bus/event_source/devices/<pmu_name>/events/<name>.per-pkg or
-	 * equivalent json value exist and have the value 1.
-	 */
-	bool per_pkg;
-	/**
-	 * @snapshot: Does the file
-	 * <sysfs>/bus/event_source/devices/<pmu_name>/events/<name>.snapshot
-	 * exist and have the value 1.
-	 */
-	bool snapshot;
-	/**
-	 * @deprecated: Is the event hidden and so not shown in perf list by
-	 * default.
-	 */
+struct pmu_event_info {
+	const struct perf_pmu *pmu;
+	const char *name;
+	const char* alias;
+	const char *scale_unit;
+	const char *desc;
+	const char *long_desc;
+	const char *encoding_desc;
+	const char *topic;
+	const char *pmu_name;
+	const char *str;
 	bool deprecated;
-	/**
-	 * @pmu_name: The name copied from the json struct pmu_event. This can
-	 * differ from the PMU name as it won't have suffixes.
-	 */
-	char *pmu_name;
 };
 
+typedef int (*pmu_event_callback)(void *state, struct pmu_event_info *info);
+
 void pmu_add_sys_aliases(struct perf_pmu *pmu);
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 		     struct list_head *head_terms,
@@ -225,7 +186,7 @@ __u64 perf_pmu__format_bits(struct perf_pmu *pmu, const char *name);
 int perf_pmu__format_type(struct perf_pmu *pmu, const char *name);
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 			  struct perf_pmu_info *info);
-struct perf_pmu_alias *perf_pmu__find_alias(struct perf_pmu *pmu, const char *event);
+int perf_pmu__find_event(struct perf_pmu *pmu, const char *event, void *state, pmu_event_callback cb);
 
 int perf_pmu__format_parse(struct perf_pmu *pmu, int dirfd, bool eager_load);
 void perf_pmu_format__set_value(void *format, int config, unsigned long *bits);
@@ -235,6 +196,9 @@ bool is_pmu_core(const char *name);
 bool perf_pmu__supports_legacy_cache(const struct perf_pmu *pmu);
 bool perf_pmu__auto_merge_stats(const struct perf_pmu *pmu);
 bool perf_pmu__have_event(const struct perf_pmu *pmu, const char *name);
+size_t perf_pmu__num_events(const struct perf_pmu *pmu);
+int perf_pmu__for_each_event(const struct perf_pmu *pmu, void *state, pmu_event_callback cb);
+
 /**
  * perf_pmu_is_software - is the PMU a software PMU as in it uses the
  *                        perf_sw_context in the kernel?
@@ -259,7 +223,6 @@ void pmu_add_cpu_aliases_table(struct perf_pmu *pmu,
 char *perf_pmu__getcpuid(struct perf_pmu *pmu);
 const struct pmu_events_table *pmu_events_table__find(void);
 const struct pmu_metrics_table *pmu_metrics_table__find(void);
-void perf_pmu_free_alias(struct perf_pmu_alias *alias);
 
 int perf_pmu__convert_scale(const char *scale, char **end, double *sval);
 
diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c
index c58ba9fb6a36..4dd5912617ff 100644
--- a/tools/perf/util/pmus.c
+++ b/tools/perf/util/pmus.c
@@ -258,219 +258,145 @@ int __weak perf_pmus__num_mem_pmus(void)
 struct sevent {
 	/** PMU for event. */
 	const struct perf_pmu *pmu;
-	/**
-	 * Optional event for name, desc, etc. If not present then this is a
-	 * selectable PMU and the event name is shown as "//".
-	 */
-	const struct perf_pmu_alias *event;
-	/** Is the PMU for the CPU? */
-	bool is_cpu;
+	const char *name;
+	const char* alias;
+	const char *scale_unit;
+	const char *desc;
+	const char *long_desc;
+	const char *encoding_desc;
+	const char *topic;
+	const char *pmu_name;
+	bool deprecated;
 };
 
 static int cmp_sevent(const void *a, const void *b)
 {
 	const struct sevent *as = a;
 	const struct sevent *bs = b;
-	const char *a_pmu_name = NULL, *b_pmu_name = NULL;
-	const char *a_name = "//", *a_desc = NULL, *a_topic = "";
-	const char *b_name = "//", *b_desc = NULL, *b_topic = "";
+	bool a_iscpu, b_iscpu;
 	int ret;
 
-	if (as->event) {
-		a_name = as->event->name;
-		a_desc = as->event->desc;
-		a_topic = as->event->topic ?: "";
-		a_pmu_name = as->event->pmu_name;
-	}
-	if (bs->event) {
-		b_name = bs->event->name;
-		b_desc = bs->event->desc;
-		b_topic = bs->event->topic ?: "";
-		b_pmu_name = bs->event->pmu_name;
-	}
 	/* Put extra events last. */
-	if (!!a_desc != !!b_desc)
-		return !!a_desc - !!b_desc;
+	if (!!as->desc != !!bs->desc)
+		return !!as->desc - !!bs->desc;
 
 	/* Order by topics. */
-	ret = strcmp(a_topic, b_topic);
+	ret = strcmp(as->topic ?: "", bs->topic ?: "");
 	if (ret)
 		return ret;
 
 	/* Order CPU core events to be first */
-	if (as->is_cpu != bs->is_cpu)
-		return as->is_cpu ? -1 : 1;
+	a_iscpu = as->pmu ? as->pmu->is_core : true;
+	b_iscpu = bs->pmu ? bs->pmu->is_core : true;
+	if (a_iscpu != b_iscpu)
+		return a_iscpu ? -1 : 1;
 
 	/* Order by PMU name. */
 	if (as->pmu != bs->pmu) {
-		a_pmu_name = a_pmu_name ?: (as->pmu->name ?: "");
-		b_pmu_name = b_pmu_name ?: (bs->pmu->name ?: "");
-		ret = strcmp(a_pmu_name, b_pmu_name);
+		ret = strcmp(as->pmu_name ?: "", bs->pmu_name ?: "");
 		if (ret)
 			return ret;
 	}
 
 	/* Order by event name. */
-	return strcmp(a_name, b_name);
+	return strcmp(as->name, bs->name);
 }
 
-static bool pmu_alias_is_duplicate(struct sevent *alias_a,
-				   struct sevent *alias_b)
+static bool pmu_alias_is_duplicate(struct sevent *a, struct sevent *b)
 {
-	const char *a_pmu_name = NULL, *b_pmu_name = NULL;
-	const char *a_name = "//", *b_name = "//";
-
-
-	if (alias_a->event) {
-		a_name = alias_a->event->name;
-		a_pmu_name = alias_a->event->pmu_name;
-	}
-	if (alias_b->event) {
-		b_name = alias_b->event->name;
-		b_pmu_name = alias_b->event->pmu_name;
-	}
-
 	/* Different names -> never duplicates */
-	if (strcmp(a_name, b_name))
+	if (strcmp(a->name ?: "//", b->name ?: "//"))
 		return false;
 
 	/* Don't remove duplicates for different PMUs */
-	a_pmu_name = a_pmu_name ?: (alias_a->pmu->name ?: "");
-	b_pmu_name = b_pmu_name ?: (alias_b->pmu->name ?: "");
-	return strcmp(a_pmu_name, b_pmu_name) == 0;
+	return strcmp(a->pmu_name, b->pmu_name) == 0;
 }
 
-static int sub_non_neg(int a, int b)
+struct events_callback_state {
+	struct sevent *aliases;
+	size_t aliases_len;
+	size_t index;
+};
+
+static int perf_pmus__print_pmu_events__callback(void *vstate,
+						struct pmu_event_info *info)
 {
-	if (b > a)
-		return 0;
-	return a - b;
-}
+	struct events_callback_state *state = vstate;
+	struct sevent *s;
 
-static char *format_alias(char *buf, int len, const struct perf_pmu *pmu,
-			  const struct perf_pmu_alias *alias)
-{
-	struct parse_events_term *term;
-	int used = snprintf(buf, len, "%s/%s", pmu->name, alias->name);
-
-	list_for_each_entry(term, &alias->terms, list) {
-		if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR)
-			used += snprintf(buf + used, sub_non_neg(len, used),
-					",%s=%s", term->config,
-					term->val.str);
+	if (state->index >= state->aliases_len) {
+		pr_err("Unexpected event %s/%s/\n", info->pmu->name, info->name);
+		return 1;
 	}
-
-	if (sub_non_neg(len, used) > 0) {
-		buf[used] = '/';
-		used++;
-	}
-	if (sub_non_neg(len, used) > 0) {
-		buf[used] = '\0';
-		used++;
-	} else
-		buf[len - 1] = '\0';
-
-	return buf;
+	s = &state->aliases[state->index];
+	s->pmu = info->pmu;
+#define COPY_STR(str) s->str = info->str ? strdup(info->str) : NULL
+	COPY_STR(name);
+	COPY_STR(alias);
+	COPY_STR(scale_unit);
+	COPY_STR(desc);
+	COPY_STR(long_desc);
+	COPY_STR(encoding_desc);
+	COPY_STR(topic);
+	COPY_STR(pmu_name);
+#undef COPY_STR
+	s->deprecated = info->deprecated;
+	state->index++;
+	return 0;
 }
 
 void perf_pmus__print_pmu_events(const struct print_callbacks *print_cb, void *print_state)
 {
 	struct perf_pmu *pmu;
-	struct perf_pmu_alias *event;
-	char buf[1024];
 	int printed = 0;
-	int len, j;
+	int len;
 	struct sevent *aliases;
+	struct events_callback_state state;
 
 	pmu = NULL;
 	len = 0;
-	while ((pmu = perf_pmus__scan(pmu)) != NULL) {
-		list_for_each_entry(event, &pmu->aliases, list)
-			len++;
-		if (pmu->selectable)
-			len++;
-	}
+	while ((pmu = perf_pmus__scan(pmu)) != NULL)
+		len += perf_pmu__num_events(pmu);
+
 	aliases = zalloc(sizeof(struct sevent) * len);
 	if (!aliases) {
 		pr_err("FATAL: not enough memory to print PMU events\n");
 		return;
 	}
 	pmu = NULL;
-	j = 0;
+	state = (struct events_callback_state) {
+		.aliases = aliases,
+		.aliases_len = len,
+		.index = 0,
+	};
 	while ((pmu = perf_pmus__scan(pmu)) != NULL) {
-		bool is_cpu = pmu->is_core;
-
-		list_for_each_entry(event, &pmu->aliases, list) {
-			aliases[j].event = event;
-			aliases[j].pmu = pmu;
-			aliases[j].is_cpu = is_cpu;
-			j++;
-		}
-		if (pmu->selectable) {
-			aliases[j].event = NULL;
-			aliases[j].pmu = pmu;
-			aliases[j].is_cpu = is_cpu;
-			j++;
-		}
+		perf_pmu__for_each_event(pmu, &state, perf_pmus__print_pmu_events__callback);
 	}
-	len = j;
 	qsort(aliases, len, sizeof(struct sevent), cmp_sevent);
-	for (j = 0; j < len; j++) {
-		const char *name, *alias = NULL, *scale_unit = NULL,
-			*desc = NULL, *long_desc = NULL,
-			*encoding_desc = NULL, *topic = NULL,
-			*pmu_name = NULL;
-		bool deprecated = false;
-		size_t buf_used;
-
+	for (int j = 0; j < len; j++) {
 		/* Skip duplicates */
 		if (j > 0 && pmu_alias_is_duplicate(&aliases[j], &aliases[j - 1]))
 			continue;
 
-		if (!aliases[j].event) {
-			/* A selectable event. */
-			pmu_name = aliases[j].pmu->name;
-			buf_used = snprintf(buf, sizeof(buf), "%s//", pmu_name) + 1;
-			name = buf;
-		} else {
-			if (aliases[j].event->desc) {
-				name = aliases[j].event->name;
-				buf_used = 0;
-			} else {
-				name = format_alias(buf, sizeof(buf), aliases[j].pmu,
-						    aliases[j].event);
-				if (aliases[j].is_cpu) {
-					alias = name;
-					name = aliases[j].event->name;
-				}
-				buf_used = strlen(buf) + 1;
-			}
-			pmu_name = aliases[j].event->pmu_name ?: (aliases[j].pmu->name ?: "");
-			if (strlen(aliases[j].event->unit) || aliases[j].event->scale != 1.0) {
-				scale_unit = buf + buf_used;
-				buf_used += snprintf(buf + buf_used, sizeof(buf) - buf_used,
-						"%G%s", aliases[j].event->scale,
-						aliases[j].event->unit) + 1;
-			}
-			desc = aliases[j].event->desc;
-			long_desc = aliases[j].event->long_desc;
-			topic = aliases[j].event->topic;
-			encoding_desc = buf + buf_used;
-			buf_used += snprintf(buf + buf_used, sizeof(buf) - buf_used,
-					"%s/%s/", pmu_name, aliases[j].event->str) + 1;
-			deprecated = aliases[j].event->deprecated;
-		}
 		print_cb->print_event(print_state,
-				pmu_name,
-				topic,
-				name,
-				alias,
-				scale_unit,
-				deprecated,
+				aliases[j].pmu_name,
+				aliases[j].topic,
+				aliases[j].name,
+				aliases[j].alias,
+				aliases[j].scale_unit,
+				aliases[j].deprecated,
 				"Kernel PMU event",
-				desc,
-				long_desc,
-				encoding_desc);
+				aliases[j].desc,
+				aliases[j].long_desc,
+				aliases[j].encoding_desc);
+		zfree(&aliases[j].name);
+		zfree(&aliases[j].alias);
+		zfree(&aliases[j].scale_unit);
+		zfree(&aliases[j].desc);
+		zfree(&aliases[j].long_desc);
+		zfree(&aliases[j].encoding_desc);
+		zfree(&aliases[j].topic);
+		zfree(&aliases[j].pmu_name);
 	}
 	if (printed && pager_in_use())
 		printf("\n");

From 4000519eb0c665947c9cb581b7fb8fdd89e92f4c Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 23 Aug 2023 21:13:15 -0700
Subject: [PATCH 0657/1189] perf pmu-events: Add extra underscore to function
 names

Add extra underscore before "for" of pmu_events_table_for_each_event
and pmu_metrics_table_for_each_metric.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230824041330.266337-4-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/empty-pmu-events.c | 10 +++++-----
 tools/perf/pmu-events/jevents.py         | 12 ++++++------
 tools/perf/pmu-events/pmu-events.h       |  4 ++--
 tools/perf/tests/pmu-events.c            |  4 ++--
 tools/perf/util/metricgroup.c            | 10 +++++-----
 tools/perf/util/pmu.c                    |  2 +-
 tools/perf/util/s390-sample-raw.c        |  2 +-
 7 files changed, 22 insertions(+), 22 deletions(-)

diff --git a/tools/perf/pmu-events/empty-pmu-events.c b/tools/perf/pmu-events/empty-pmu-events.c
index a630c617e879..807f2e55c17c 100644
--- a/tools/perf/pmu-events/empty-pmu-events.c
+++ b/tools/perf/pmu-events/empty-pmu-events.c
@@ -266,7 +266,7 @@ static const struct pmu_sys_events pmu_sys_event_tables[] = {
 	},
 };
 
-int pmu_events_table_for_each_event(const struct pmu_events_table *table, pmu_event_iter_fn fn,
+int pmu_events_table__for_each_event(const struct pmu_events_table *table, pmu_event_iter_fn fn,
 				    void *data)
 {
 	for (const struct pmu_event *pe = &table->entries[0]; pe->name; pe++) {
@@ -278,7 +278,7 @@ int pmu_events_table_for_each_event(const struct pmu_events_table *table, pmu_ev
 	return 0;
 }
 
-int pmu_metrics_table_for_each_metric(const struct pmu_metrics_table *table, pmu_metric_iter_fn fn,
+int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table, pmu_metric_iter_fn fn,
 				      void *data)
 {
 	for (const struct pmu_metric *pm = &table->entries[0]; pm->metric_expr; pm++) {
@@ -371,7 +371,7 @@ const struct pmu_metrics_table *find_core_metrics_table(const char *arch, const
 int pmu_for_each_core_event(pmu_event_iter_fn fn, void *data)
 {
 	for (const struct pmu_events_map *tables = &pmu_events_map[0]; tables->arch; tables++) {
-		int ret = pmu_events_table_for_each_event(&tables->event_table, fn, data);
+		int ret = pmu_events_table__for_each_event(&tables->event_table, fn, data);
 
 		if (ret)
 			return ret;
@@ -384,7 +384,7 @@ int pmu_for_each_core_metric(pmu_metric_iter_fn fn, void *data)
 	for (const struct pmu_events_map *tables = &pmu_events_map[0];
 	     tables->arch;
 	     tables++) {
-		int ret = pmu_metrics_table_for_each_metric(&tables->metric_table, fn, data);
+		int ret = pmu_metrics_table__for_each_metric(&tables->metric_table, fn, data);
 
 		if (ret)
 			return ret;
@@ -408,7 +408,7 @@ int pmu_for_each_sys_event(pmu_event_iter_fn fn, void *data)
 	for (const struct pmu_sys_events *tables = &pmu_sys_event_tables[0];
 	     tables->name;
 	     tables++) {
-		int ret = pmu_events_table_for_each_event(&tables->table, fn, data);
+		int ret = pmu_events_table__for_each_event(&tables->table, fn, data);
 
 		if (ret)
 			return ret;
diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index 98cccc3fcbbd..aae5334099b1 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -753,7 +753,7 @@ static void decompress_metric(int offset, struct pmu_metric *pm)
       _args.output_file.write('\twhile (*p++);')
   _args.output_file.write("""}
 
-int pmu_events_table_for_each_event(const struct pmu_events_table *table,
+int pmu_events_table__for_each_event(const struct pmu_events_table *table,
                                     pmu_event_iter_fn fn,
                                     void *data)
 {
@@ -771,7 +771,7 @@ int pmu_events_table_for_each_event(const struct pmu_events_table *table,
         return 0;
 }
 
-int pmu_metrics_table_for_each_metric(const struct pmu_metrics_table *table,
+int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table,
                                      pmu_metric_iter_fn fn,
                                      void *data)
 {
@@ -870,7 +870,7 @@ int pmu_for_each_core_event(pmu_event_iter_fn fn, void *data)
         for (const struct pmu_events_map *tables = &pmu_events_map[0];
              tables->arch;
              tables++) {
-                int ret = pmu_events_table_for_each_event(&tables->event_table, fn, data);
+                int ret = pmu_events_table__for_each_event(&tables->event_table, fn, data);
 
                 if (ret)
                         return ret;
@@ -883,7 +883,7 @@ int pmu_for_each_core_metric(pmu_metric_iter_fn fn, void *data)
         for (const struct pmu_events_map *tables = &pmu_events_map[0];
              tables->arch;
              tables++) {
-                int ret = pmu_metrics_table_for_each_metric(&tables->metric_table, fn, data);
+                int ret = pmu_metrics_table__for_each_metric(&tables->metric_table, fn, data);
 
                 if (ret)
                         return ret;
@@ -907,7 +907,7 @@ int pmu_for_each_sys_event(pmu_event_iter_fn fn, void *data)
         for (const struct pmu_sys_events *tables = &pmu_sys_event_tables[0];
              tables->name;
              tables++) {
-                int ret = pmu_events_table_for_each_event(&tables->event_table, fn, data);
+                int ret = pmu_events_table__for_each_event(&tables->event_table, fn, data);
 
                 if (ret)
                         return ret;
@@ -920,7 +920,7 @@ int pmu_for_each_sys_metric(pmu_metric_iter_fn fn, void *data)
         for (const struct pmu_sys_events *tables = &pmu_sys_event_tables[0];
              tables->name;
              tables++) {
-                int ret = pmu_metrics_table_for_each_metric(&tables->metric_table, fn, data);
+                int ret = pmu_metrics_table__for_each_metric(&tables->metric_table, fn, data);
 
                 if (ret)
                         return ret;
diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h
index caf59f23cd64..6557381b7de1 100644
--- a/tools/perf/pmu-events/pmu-events.h
+++ b/tools/perf/pmu-events/pmu-events.h
@@ -77,9 +77,9 @@ typedef int (*pmu_metric_iter_fn)(const struct pmu_metric *pm,
 				  const struct pmu_metrics_table *table,
 				  void *data);
 
-int pmu_events_table_for_each_event(const struct pmu_events_table *table, pmu_event_iter_fn fn,
+int pmu_events_table__for_each_event(const struct pmu_events_table *table, pmu_event_iter_fn fn,
 				    void *data);
-int pmu_metrics_table_for_each_metric(const struct pmu_metrics_table *table, pmu_metric_iter_fn fn,
+int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table, pmu_metric_iter_fn fn,
 				     void *data);
 
 const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu);
diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
index dc87e66fb118..5f541eadc088 100644
--- a/tools/perf/tests/pmu-events.c
+++ b/tools/perf/tests/pmu-events.c
@@ -477,12 +477,12 @@ static int test__pmu_event_table(struct test_suite *test __maybe_unused,
 	if (!table || !sys_event_table)
 		return -1;
 
-	err = pmu_events_table_for_each_event(table, test__pmu_event_table_core_callback,
+	err = pmu_events_table__for_each_event(table, test__pmu_event_table_core_callback,
 					      &map_events);
 	if (err)
 		return err;
 
-	err = pmu_events_table_for_each_event(sys_event_table, test__pmu_event_table_sys_callback,
+	err = pmu_events_table__for_each_event(sys_event_table, test__pmu_event_table_sys_callback,
 					      &map_events);
 	if (err)
 		return err;
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index a6a5ed44a679..6231044a491e 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -527,7 +527,7 @@ void metricgroup__print(const struct print_callbacks *print_cb, void *print_stat
 	groups.node_delete = mep_delete;
 	table = pmu_metrics_table__find();
 	if (table) {
-		pmu_metrics_table_for_each_metric(table,
+		pmu_metrics_table__for_each_metric(table,
 						 metricgroup__add_to_mep_groups_callback,
 						 &groups);
 	}
@@ -1069,7 +1069,7 @@ static bool metricgroup__find_metric(const char *pmu,
 		.pm = pm,
 	};
 
-	return pmu_metrics_table_for_each_metric(table, metricgroup__find_metric_callback, &data)
+	return pmu_metrics_table__for_each_metric(table, metricgroup__find_metric_callback, &data)
 		? true : false;
 }
 
@@ -1255,7 +1255,7 @@ static int metricgroup__add_metric(const char *pmu, const char *metric_name, con
 		 * Iterate over all metrics seeing if metric matches either the
 		 * name or group. When it does add the metric to the list.
 		 */
-		ret = pmu_metrics_table_for_each_metric(table, metricgroup__add_metric_callback,
+		ret = pmu_metrics_table__for_each_metric(table, metricgroup__add_metric_callback,
 						       &data);
 		if (ret)
 			goto out;
@@ -1740,7 +1740,7 @@ bool metricgroup__has_metric(const char *pmu, const char *metric)
 	if (!table)
 		return false;
 
-	return pmu_metrics_table_for_each_metric(table, metricgroup__has_metric_callback, &data)
+	return pmu_metrics_table__for_each_metric(table, metricgroup__has_metric_callback, &data)
 		? true : false;
 }
 
@@ -1770,7 +1770,7 @@ unsigned int metricgroups__topdown_max_level(void)
 	if (!table)
 		return false;
 
-	pmu_metrics_table_for_each_metric(table, metricgroup__topdown_max_level_callback,
+	pmu_metrics_table__for_each_metric(table, metricgroup__topdown_max_level_callback,
 					  &max_level);
 	return max_level;
 }
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 268aaebfa70c..d91367155e29 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -896,7 +896,7 @@ void pmu_add_cpu_aliases_table(struct perf_pmu *pmu, const struct pmu_events_tab
 		.pmu = pmu,
 	};
 
-	pmu_events_table_for_each_event(table, pmu_add_cpu_aliases_map_callback, &data);
+	pmu_events_table__for_each_event(table, pmu_add_cpu_aliases_map_callback, &data);
 	free(data.default_pmu_name);
 }
 
diff --git a/tools/perf/util/s390-sample-raw.c b/tools/perf/util/s390-sample-raw.c
index c10b891dbad6..91330c874170 100644
--- a/tools/perf/util/s390-sample-raw.c
+++ b/tools/perf/util/s390-sample-raw.c
@@ -168,7 +168,7 @@ static const char *get_counter_name(int set, int nr, const struct pmu_events_tab
 	if (!table)
 		return NULL;
 
-	pmu_events_table_for_each_event(table, get_counter_name_callback, &data);
+	pmu_events_table__for_each_event(table, get_counter_name_callback, &data);
 	return data.result;
 }
 

From 2e255b4f9f41f137d9e3dc4fae3603a9c2c3dd28 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 23 Aug 2023 21:13:16 -0700
Subject: [PATCH 0658/1189] perf jevents: Group events by PMU

Prior to this change a cpuid would map to a list of events where the PMU
would be encoded alongside the event information. This change breaks
apart each group of events so that there is a group per PMU. A new table
is added with the PMU's name and the list of events, the original table
now holding an array of these per PMU tables.

These changes are to make it easier to get per PMU information about
events, rather than the current approach of scanning all events. The
perf binary size with BPF skeletons on x86 is reduced by about 1%. The
unidentified PMU is now always expanded to "cpu".

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230824041330.266337-5-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/jevents.py | 181 +++++++++++++++++++++++--------
 tools/perf/tests/pmu-events.c    |  30 +++--
 2 files changed, 154 insertions(+), 57 deletions(-)

diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index aae5334099b1..1ad20140114c 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -42,7 +42,7 @@ _metricgroups = {}
 # Order specific JsonEvent attributes will be visited.
 _json_event_attributes = [
     # cmp_sevent related attributes.
-    'name', 'pmu', 'topic', 'desc',
+    'name', 'topic', 'desc',
     # Seems useful, put it early.
     'event',
     # Short things in alphabetical order.
@@ -53,7 +53,7 @@ _json_event_attributes = [
 
 # Attributes that are in pmu_metric rather than pmu_event.
 _json_metric_attributes = [
-    'pmu', 'metric_name', 'metric_group', 'metric_expr', 'metric_threshold',
+    'metric_name', 'metric_group', 'metric_expr', 'metric_threshold',
     'desc', 'long_desc', 'unit', 'compat', 'metricgroup_no_group',
     'default_metricgroup_name', 'aggr_mode', 'event_grouping'
 ]
@@ -252,7 +252,7 @@ class JsonEvent:
     def unit_to_pmu(unit: str) -> Optional[str]:
       """Convert a JSON Unit to Linux PMU name."""
       if not unit:
-        return None
+        return 'cpu'
       # Comment brought over from jevents.c:
       # it's not realistic to keep adding these, we need something more scalable ...
       table = {
@@ -343,10 +343,13 @@ class JsonEvent:
       self.desc += extra_desc
     if self.long_desc and extra_desc:
       self.long_desc += extra_desc
-    if self.pmu:
-      if self.desc and not self.desc.endswith('. '):
-        self.desc += '. '
-      self.desc = (self.desc if self.desc else '') + ('Unit: ' + self.pmu + ' ')
+    if self.pmu and self.pmu != 'cpu':
+      if not self.desc:
+        self.desc = 'Unit: ' + self.pmu
+      else:
+        if not self.desc.endswith('. '):
+          self.desc += '. '
+      self.desc += 'Unit: ' + self.pmu
     if arch_std:
       if arch_std.lower() in _arch_std_events:
         event = _arch_std_events[arch_std.lower()].event
@@ -437,13 +440,13 @@ def add_events_table_entries(item: os.DirEntry, topic: str) -> None:
 def print_pending_events() -> None:
   """Optionally close events table."""
 
-  def event_cmp_key(j: JsonEvent) -> Tuple[bool, str, str, str, str]:
+  def event_cmp_key(j: JsonEvent) -> Tuple[str, str, bool, str, str]:
     def fix_none(s: Optional[str]) -> str:
       if s is None:
         return ''
       return s
 
-    return (j.desc is not None, fix_none(j.topic), fix_none(j.name), fix_none(j.pmu),
+    return (fix_none(j.pmu).replace(',','_'), fix_none(j.name), j.desc is not None, fix_none(j.topic),
             fix_none(j.metric_name))
 
   global _pending_events
@@ -458,13 +461,36 @@ def print_pending_events() -> None:
     global event_tables
     _event_tables.append(_pending_events_tblname)
 
-  _args.output_file.write(
-      f'static const struct compact_pmu_event {_pending_events_tblname}[] = {{\n')
-
+  first = True
+  last_pmu = None
+  pmus = set()
   for event in sorted(_pending_events, key=event_cmp_key):
+    if event.pmu != last_pmu:
+      if not first:
+        _args.output_file.write('};\n')
+      pmu_name = event.pmu.replace(',', '_')
+      _args.output_file.write(
+          f'static const struct compact_pmu_event {_pending_events_tblname}_{pmu_name}[] = {{\n')
+      first = False
+      last_pmu = event.pmu
+      pmus.add((event.pmu, pmu_name))
+
     _args.output_file.write(event.to_c_string(metric=False))
   _pending_events = []
 
+  _args.output_file.write(f"""
+}};
+
+const struct pmu_table_entry {_pending_events_tblname}[] = {{
+""")
+  for (pmu, tbl_pmu) in sorted(pmus):
+    pmu_name = f"{pmu}\\000"
+    _args.output_file.write(f"""{{
+     .entries = {_pending_events_tblname}_{tbl_pmu},
+     .num_entries = ARRAY_SIZE({_pending_events_tblname}_{tbl_pmu}),
+     .pmu_name = {{ {_bcs.offsets[pmu_name]} /* {pmu_name} */ }},
+}},
+""")
   _args.output_file.write('};\n\n')
 
 def print_pending_metrics() -> None:
@@ -490,13 +516,36 @@ def print_pending_metrics() -> None:
     global metric_tables
     _metric_tables.append(_pending_metrics_tblname)
 
-  _args.output_file.write(
-      f'static const struct compact_pmu_event {_pending_metrics_tblname}[] = {{\n')
-
+  first = True
+  last_pmu = None
+  pmus = set()
   for metric in sorted(_pending_metrics, key=metric_cmp_key):
+    if metric.pmu != last_pmu:
+      if not first:
+        _args.output_file.write('};\n')
+      pmu_name = metric.pmu.replace(',', '_')
+      _args.output_file.write(
+          f'static const struct compact_pmu_event {_pending_metrics_tblname}_{pmu_name}[] = {{\n')
+      first = False
+      last_pmu = metric.pmu
+      pmus.add((metric.pmu, pmu_name))
+
     _args.output_file.write(metric.to_c_string(metric=True))
   _pending_metrics = []
 
+  _args.output_file.write(f"""
+}};
+
+const struct pmu_table_entry {_pending_metrics_tblname}[] = {{
+""")
+  for (pmu, tbl_pmu) in sorted(pmus):
+    pmu_name = f"{pmu}\\000"
+    _args.output_file.write(f"""{{
+     .entries = {_pending_metrics_tblname}_{tbl_pmu},
+     .num_entries = ARRAY_SIZE({_pending_metrics_tblname}_{tbl_pmu}),
+     .pmu_name = {{ {_bcs.offsets[pmu_name]} /* {pmu_name} */ }},
+}},
+""")
   _args.output_file.write('};\n\n')
 
 def get_topic(topic: str) -> str:
@@ -532,6 +581,8 @@ def preprocess_one_file(parents: Sequence[str], item: os.DirEntry) -> None:
 
   topic = get_topic(item.name)
   for event in read_json_events(item.path, topic):
+    pmu_name = f"{event.pmu}\\000"
+    _bcs.add(pmu_name)
     if event.name:
       _bcs.add(event.build_c_string(metric=False))
     if event.metric_name:
@@ -577,14 +628,14 @@ def print_mapping_table(archs: Sequence[str]) -> None:
   _args.output_file.write("""
 /* Struct used to make the PMU event table implementation opaque to callers. */
 struct pmu_events_table {
-        const struct compact_pmu_event *entries;
-        size_t length;
+        const struct pmu_table_entry *pmus;
+        uint32_t num_pmus;
 };
 
 /* Struct used to make the PMU metric table implementation opaque to callers. */
 struct pmu_metrics_table {
-        const struct compact_pmu_event *entries;
-        size_t length;
+        const struct pmu_table_entry *pmus;
+        uint32_t num_pmus;
 };
 
 /*
@@ -614,12 +665,12 @@ const struct pmu_events_map pmu_events_map[] = {
 \t.arch = "testarch",
 \t.cpuid = "testcpu",
 \t.event_table = {
-\t\t.entries = pmu_events__test_soc_cpu,
-\t\t.length = ARRAY_SIZE(pmu_events__test_soc_cpu),
+\t\t.pmus = pmu_events__test_soc_cpu,
+\t\t.num_pmus = ARRAY_SIZE(pmu_events__test_soc_cpu),
 \t},
 \t.metric_table = {
-\t\t.entries = pmu_metrics__test_soc_cpu,
-\t\t.length = ARRAY_SIZE(pmu_metrics__test_soc_cpu),
+\t\t.pmus = pmu_metrics__test_soc_cpu,
+\t\t.num_pmus = ARRAY_SIZE(pmu_metrics__test_soc_cpu),
 \t}
 },
 """)
@@ -649,12 +700,12 @@ const struct pmu_events_map pmu_events_map[] = {
 \t.arch = "{arch}",
 \t.cpuid = "{cpuid}",
 \t.event_table = {{
-\t\t.entries = {event_tblname},
-\t\t.length = {event_size}
+\t\t.pmus = {event_tblname},
+\t\t.num_pmus = {event_size}
 \t}},
 \t.metric_table = {{
-\t\t.entries = {metric_tblname},
-\t\t.length = {metric_size}
+\t\t.pmus = {metric_tblname},
+\t\t.num_pmus = {metric_size}
 \t}}
 }},
 """)
@@ -685,15 +736,15 @@ static const struct pmu_sys_events pmu_sys_event_tables[] = {
   for tblname in _sys_event_tables:
     _args.output_file.write(f"""\t{{
 \t\t.event_table = {{
-\t\t\t.entries = {tblname},
-\t\t\t.length = ARRAY_SIZE({tblname})
+\t\t\t.pmus = {tblname},
+\t\t\t.num_pmus = ARRAY_SIZE({tblname})
 \t\t}},""")
     metric_tblname = _sys_event_table_to_metric_table_mapping[tblname]
     if metric_tblname in _sys_metric_tables:
       _args.output_file.write(f"""
 \t\t.metric_table = {{
-\t\t\t.entries = {metric_tblname},
-\t\t\t.length = ARRAY_SIZE({metric_tblname})
+\t\t\t.pmus = {metric_tblname},
+\t\t\t.num_pmus = ARRAY_SIZE({metric_tblname})
 \t\t}},""")
       printed_metric_tables.append(metric_tblname)
     _args.output_file.write(f"""
@@ -753,18 +804,56 @@ static void decompress_metric(int offset, struct pmu_metric *pm)
       _args.output_file.write('\twhile (*p++);')
   _args.output_file.write("""}
 
+static int pmu_events_table__for_each_event_pmu(const struct pmu_events_table *table,
+                                                const struct pmu_table_entry *pmu,
+                                                pmu_event_iter_fn fn,
+                                                void *data)
+{
+        int ret;
+        struct pmu_event pe = {
+                .pmu = &big_c_string[pmu->pmu_name.offset],
+        };
+
+        for (uint32_t i = 0; i < pmu->num_entries; i++) {
+                decompress_event(pmu->entries[i].offset, &pe);
+                if (!pe.name)
+                        continue;
+                ret = fn(&pe, table, data);
+                if (ret)
+                        return ret;
+        }
+        return 0;
+ }
+
 int pmu_events_table__for_each_event(const struct pmu_events_table *table,
                                     pmu_event_iter_fn fn,
                                     void *data)
 {
-        for (size_t i = 0; i < table->length; i++) {
-                struct pmu_event pe;
-                int ret;
+        for (size_t i = 0; i < table->num_pmus; i++) {
+                int ret = pmu_events_table__for_each_event_pmu(table, &table->pmus[i],
+                                                               fn, data);
 
-                decompress_event(table->entries[i].offset, &pe);
-                if (!pe.name)
+                if (ret)
+                        return ret;
+        }
+        return 0;
+}
+
+static int pmu_metrics_table__for_each_metric_pmu(const struct pmu_metrics_table *table,
+                                                const struct pmu_table_entry *pmu,
+                                                pmu_metric_iter_fn fn,
+                                                void *data)
+{
+        int ret;
+        struct pmu_metric pm = {
+                .pmu = &big_c_string[pmu->pmu_name.offset],
+        };
+
+        for (uint32_t i = 0; i < pmu->num_entries; i++) {
+                decompress_metric(pmu->entries[i].offset, &pm);
+                if (!pm.metric_expr)
                         continue;
-                ret = fn(&pe, table, data);
+                ret = fn(&pm, table, data);
                 if (ret)
                         return ret;
         }
@@ -775,14 +864,10 @@ int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table,
                                      pmu_metric_iter_fn fn,
                                      void *data)
 {
-        for (size_t i = 0; i < table->length; i++) {
-                struct pmu_metric pm;
-                int ret;
+        for (size_t i = 0; i < table->num_pmus; i++) {
+                int ret = pmu_metrics_table__for_each_metric_pmu(table, &table->pmus[i],
+                                                                 fn, data);
 
-                decompress_metric(table->entries[i].offset, &pm);
-                if (!pm.metric_expr)
-                        continue;
-                ret = fn(&pm, table, data);
                 if (ret)
                         return ret;
         }
@@ -1010,7 +1095,13 @@ such as "arm/cortex-a34".''',
 #include <stddef.h>
 
 struct compact_pmu_event {
-  int offset;
+        int offset;
+};
+
+struct pmu_table_entry {
+        const struct compact_pmu_event *entries;
+        uint32_t num_entries;
+        struct compact_pmu_event pmu_name;
 };
 
 """)
diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
index 5f541eadc088..0b6efabc3d20 100644
--- a/tools/perf/tests/pmu-events.c
+++ b/tools/perf/tests/pmu-events.c
@@ -44,6 +44,7 @@ struct perf_pmu_test_pmu {
 
 static const struct perf_pmu_test_event bp_l1_btb_correct = {
 	.event = {
+		.pmu = "cpu",
 		.name = "bp_l1_btb_correct",
 		.event = "event=0x8a",
 		.desc = "L1 BTB Correction",
@@ -55,6 +56,7 @@ static const struct perf_pmu_test_event bp_l1_btb_correct = {
 
 static const struct perf_pmu_test_event bp_l2_btb_correct = {
 	.event = {
+		.pmu = "cpu",
 		.name = "bp_l2_btb_correct",
 		.event = "event=0x8b",
 		.desc = "L2 BTB Correction",
@@ -66,6 +68,7 @@ static const struct perf_pmu_test_event bp_l2_btb_correct = {
 
 static const struct perf_pmu_test_event segment_reg_loads_any = {
 	.event = {
+		.pmu = "cpu",
 		.name = "segment_reg_loads.any",
 		.event = "event=0x6,period=200000,umask=0x80",
 		.desc = "Number of segment register loads",
@@ -77,6 +80,7 @@ static const struct perf_pmu_test_event segment_reg_loads_any = {
 
 static const struct perf_pmu_test_event dispatch_blocked_any = {
 	.event = {
+		.pmu = "cpu",
 		.name = "dispatch_blocked.any",
 		.event = "event=0x9,period=200000,umask=0x20",
 		.desc = "Memory cluster signals to block micro-op dispatch for any reason",
@@ -88,6 +92,7 @@ static const struct perf_pmu_test_event dispatch_blocked_any = {
 
 static const struct perf_pmu_test_event eist_trans = {
 	.event = {
+		.pmu = "cpu",
 		.name = "eist_trans",
 		.event = "event=0x3a,period=200000,umask=0x0",
 		.desc = "Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions",
@@ -99,6 +104,7 @@ static const struct perf_pmu_test_event eist_trans = {
 
 static const struct perf_pmu_test_event l3_cache_rd = {
 	.event = {
+		.pmu = "cpu",
 		.name = "l3_cache_rd",
 		.event = "event=0x40",
 		.desc = "L3 cache access, read",
@@ -123,7 +129,7 @@ static const struct perf_pmu_test_event uncore_hisi_ddrc_flux_wcmd = {
 	.event = {
 		.name = "uncore_hisi_ddrc.flux_wcmd",
 		.event = "event=0x2",
-		.desc = "DDRC write commands. Unit: hisi_sccl,ddrc ",
+		.desc = "DDRC write commands. Unit: hisi_sccl,ddrc",
 		.topic = "uncore",
 		.long_desc = "DDRC write commands",
 		.pmu = "hisi_sccl,ddrc",
@@ -137,7 +143,7 @@ static const struct perf_pmu_test_event unc_cbo_xsnp_response_miss_eviction = {
 	.event = {
 		.name = "unc_cbo_xsnp_response.miss_eviction",
 		.event = "event=0x22,umask=0x81",
-		.desc = "A cross-core snoop resulted from L3 Eviction which misses in some processor core. Unit: uncore_cbox ",
+		.desc = "A cross-core snoop resulted from L3 Eviction which misses in some processor core. Unit: uncore_cbox",
 		.topic = "uncore",
 		.long_desc = "A cross-core snoop resulted from L3 Eviction which misses in some processor core",
 		.pmu = "uncore_cbox",
@@ -151,7 +157,7 @@ static const struct perf_pmu_test_event uncore_hyphen = {
 	.event = {
 		.name = "event-hyphen",
 		.event = "event=0xe0,umask=0x00",
-		.desc = "UNC_CBO_HYPHEN. Unit: uncore_cbox ",
+		.desc = "UNC_CBO_HYPHEN. Unit: uncore_cbox",
 		.topic = "uncore",
 		.long_desc = "UNC_CBO_HYPHEN",
 		.pmu = "uncore_cbox",
@@ -165,7 +171,7 @@ static const struct perf_pmu_test_event uncore_two_hyph = {
 	.event = {
 		.name = "event-two-hyph",
 		.event = "event=0xc0,umask=0x00",
-		.desc = "UNC_CBO_TWO_HYPH. Unit: uncore_cbox ",
+		.desc = "UNC_CBO_TWO_HYPH. Unit: uncore_cbox",
 		.topic = "uncore",
 		.long_desc = "UNC_CBO_TWO_HYPH",
 		.pmu = "uncore_cbox",
@@ -179,7 +185,7 @@ static const struct perf_pmu_test_event uncore_hisi_l3c_rd_hit_cpipe = {
 	.event = {
 		.name = "uncore_hisi_l3c.rd_hit_cpipe",
 		.event = "event=0x7",
-		.desc = "Total read hits. Unit: hisi_sccl,l3c ",
+		.desc = "Total read hits. Unit: hisi_sccl,l3c",
 		.topic = "uncore",
 		.long_desc = "Total read hits",
 		.pmu = "hisi_sccl,l3c",
@@ -193,7 +199,7 @@ static const struct perf_pmu_test_event uncore_imc_free_running_cache_miss = {
 	.event = {
 		.name = "uncore_imc_free_running.cache_miss",
 		.event = "event=0x12",
-		.desc = "Total cache misses. Unit: uncore_imc_free_running ",
+		.desc = "Total cache misses. Unit: uncore_imc_free_running",
 		.topic = "uncore",
 		.long_desc = "Total cache misses",
 		.pmu = "uncore_imc_free_running",
@@ -207,7 +213,7 @@ static const struct perf_pmu_test_event uncore_imc_cache_hits = {
 	.event = {
 		.name = "uncore_imc.cache_hits",
 		.event = "event=0x34",
-		.desc = "Total cache hits. Unit: uncore_imc ",
+		.desc = "Total cache hits. Unit: uncore_imc",
 		.topic = "uncore",
 		.long_desc = "Total cache hits",
 		.pmu = "uncore_imc",
@@ -232,13 +238,13 @@ static const struct perf_pmu_test_event sys_ddr_pmu_write_cycles = {
 	.event = {
 		.name = "sys_ddr_pmu.write_cycles",
 		.event = "event=0x2b",
-		.desc = "ddr write-cycles event. Unit: uncore_sys_ddr_pmu ",
+		.desc = "ddr write-cycles event. Unit: uncore_sys_ddr_pmu",
 		.topic = "uncore",
 		.pmu = "uncore_sys_ddr_pmu",
 		.compat = "v8",
 	},
 	.alias_str = "event=0x2b",
-	.alias_long_desc = "ddr write-cycles event. Unit: uncore_sys_ddr_pmu ",
+	.alias_long_desc = "ddr write-cycles event. Unit: uncore_sys_ddr_pmu",
 	.matching_pmu = "uncore_sys_ddr_pmu",
 };
 
@@ -246,13 +252,13 @@ static const struct perf_pmu_test_event sys_ccn_pmu_read_cycles = {
 	.event = {
 		.name = "sys_ccn_pmu.read_cycles",
 		.event = "config=0x2c",
-		.desc = "ccn read-cycles event. Unit: uncore_sys_ccn_pmu ",
+		.desc = "ccn read-cycles event. Unit: uncore_sys_ccn_pmu",
 		.topic = "uncore",
 		.pmu = "uncore_sys_ccn_pmu",
 		.compat = "0x01",
 	},
 	.alias_str = "config=0x2c",
-	.alias_long_desc = "ccn read-cycles event. Unit: uncore_sys_ccn_pmu ",
+	.alias_long_desc = "ccn read-cycles event. Unit: uncore_sys_ccn_pmu",
 	.matching_pmu = "uncore_sys_ccn_pmu",
 };
 
@@ -403,7 +409,7 @@ static int test__pmu_event_table_core_callback(const struct pmu_event *pe,
 	struct perf_pmu_test_event const **test_event_table;
 	bool found = false;
 
-	if (pe->pmu)
+	if (strcmp(pe->pmu, "cpu"))
 		test_event_table = &uncore_events[0];
 	else
 		test_event_table = &core_events[0];

From 9d31cb9395447a62a00402be549f7a55a738d874 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 23 Aug 2023 21:13:17 -0700
Subject: [PATCH 0659/1189] perf parse-events: Improve error message for double
 setting

Double setting information for an event would produce an error message
associated with the PMU rather than the term that was double setting.
Improve the error message to be on the term.

Before:

  $ perf stat -e 'cpu/inst_retired.any,inst_retired.any/' true
  event syntax error: 'cpu/inst_retired.any,inst_retired.any/'
                       \___ Bad event or PMU

  Unabled to find PMU or event on a PMU of 'cpu'
  Run 'perf list' for a list of valid events
  $

After:

  $ perf stat -e 'cpu/inst_retired.any,inst_retired.any/' true
  event syntax error: '..etired.any,inst_retired.any/'
                                    \___ Bad event or PMU

  Unabled to find PMU or event on a PMU of 'cpu'

  Initial error:

  event syntax error: '..etired.any,inst_retired.any/'
                                    \___ Attempt to set event's scale twice
  Run 'perf list' for a list of valid events

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230824041330.266337-6-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.c |  2 +-
 tools/perf/util/pmu.c          | 34 +++++++++++++++++++++++++++-------
 tools/perf/util/pmu.h          |  2 +-
 3 files changed, 29 insertions(+), 9 deletions(-)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 7cad82a9f578..781747bedc3e 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1348,7 +1348,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 		return evsel ? 0 : -ENOMEM;
 	}
 
-	if (!parse_state->fake_pmu && perf_pmu__check_alias(pmu, head_config, &info))
+	if (!parse_state->fake_pmu && perf_pmu__check_alias(pmu, head_config, &info, err))
 		return -EINVAL;
 
 	if (verbose > 1) {
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index d91367155e29..0c82bbeea7d6 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1443,17 +1443,33 @@ static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
 
 
 static int check_info_data(struct perf_pmu_alias *alias,
-			   struct perf_pmu_info *info)
+			   struct perf_pmu_info *info,
+			   struct parse_events_error *err,
+			   int column)
 {
 	/*
 	 * Only one term in event definition can
 	 * define unit, scale and snapshot, fail
 	 * if there's more than one.
 	 */
-	if ((info->unit && alias->unit[0]) ||
-	    (info->scale && alias->scale) ||
-	    (info->snapshot && alias->snapshot))
+	if (info->unit && alias->unit[0]) {
+		parse_events_error__handle(err, column,
+					strdup("Attempt to set event's unit twice"),
+					NULL);
 		return -EINVAL;
+	}
+	if (info->scale && alias->scale) {
+		parse_events_error__handle(err, column,
+					strdup("Attempt to set event's scale twice"),
+					NULL);
+		return -EINVAL;
+	}
+	if (info->snapshot && alias->snapshot) {
+		parse_events_error__handle(err, column,
+					strdup("Attempt to set event snapshot twice"),
+					NULL);
+		return -EINVAL;
+	}
 
 	if (alias->unit[0])
 		info->unit = alias->unit;
@@ -1472,7 +1488,7 @@ static int check_info_data(struct perf_pmu_alias *alias,
  * defined for the alias
  */
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
-			  struct perf_pmu_info *info)
+			  struct perf_pmu_info *info, struct parse_events_error *err)
 {
 	struct parse_events_term *term, *h;
 	struct perf_pmu_alias *alias;
@@ -1493,10 +1509,14 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 		if (!alias)
 			continue;
 		ret = pmu_alias_terms(alias, &term->list);
-		if (ret)
+		if (ret) {
+			parse_events_error__handle(err, term->err_term,
+						strdup("Failure to duplicate terms"),
+						NULL);
 			return ret;
+		}
 
-		ret = check_info_data(alias, info);
+		ret = check_info_data(alias, info, err, term->err_term);
 		if (ret)
 			return ret;
 
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index f37e3d75094f..03211de345c1 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -185,7 +185,7 @@ int perf_pmu__config_terms(struct perf_pmu *pmu,
 __u64 perf_pmu__format_bits(struct perf_pmu *pmu, const char *name);
 int perf_pmu__format_type(struct perf_pmu *pmu, const char *name);
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
-			  struct perf_pmu_info *info);
+			  struct perf_pmu_info *info, struct parse_events_error *err);
 int perf_pmu__find_event(struct perf_pmu *pmu, const char *event, void *state, pmu_event_callback cb);
 
 int perf_pmu__format_parse(struct perf_pmu *pmu, int dirfd, bool eager_load);

From c4ac7f7542e7bc958453f8fdcb528348308539dc Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 23 Aug 2023 21:13:18 -0700
Subject: [PATCH 0660/1189] perf s390 s390_cpumcfdg_dump: Don't scan all PMUs

Rather than scanning all PMUs for a counter name, scan the PMU
associated with the evsel of the sample. This is done to remove a
dependence on pmu-events.h.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230824041330.266337-7-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/s390-sample-raw.c | 50 ++++++++++++++++---------------
 1 file changed, 26 insertions(+), 24 deletions(-)

diff --git a/tools/perf/util/s390-sample-raw.c b/tools/perf/util/s390-sample-raw.c
index 91330c874170..dc1ed3e95d4d 100644
--- a/tools/perf/util/s390-sample-raw.c
+++ b/tools/perf/util/s390-sample-raw.c
@@ -27,7 +27,7 @@
 #include "color.h"
 #include "sample-raw.h"
 #include "s390-cpumcf-kernel.h"
-#include "pmu-events/pmu-events.h"
+#include "util/pmu.h"
 #include "util/sample.h"
 
 static size_t ctrset_size(struct cf_ctrset_entry *set)
@@ -132,56 +132,57 @@ static int get_counterset_start(int setnr)
 
 struct get_counter_name_data {
 	int wanted;
-	const char *result;
+	char *result;
 };
 
-static int get_counter_name_callback(const struct pmu_event *evp,
-				     const struct pmu_events_table *table __maybe_unused,
-				     void *vdata)
+static int get_counter_name_callback(void *vdata, struct pmu_event_info *info)
 {
 	struct get_counter_name_data *data = vdata;
 	int rc, event_nr;
+	const char *event_str;
 
-	if (evp->name == NULL || evp->event == NULL)
+	if (info->str == NULL)
 		return 0;
-	rc = sscanf(evp->event, "event=%x", &event_nr);
+
+	event_str = strstr(info->str, "event=");
+	if (!event_str)
+		return 0;
+
+	rc = sscanf(event_str, "event=%x", &event_nr);
 	if (rc == 1 && event_nr == data->wanted) {
-		data->result = evp->name;
+		data->result = strdup(info->name);
 		return 1; /* Terminate the search. */
 	}
 	return 0;
 }
 
-/* Scan the PMU table and extract the logical name of a counter from the
- * PMU events table. Input is the counter set and counter number with in the
- * set. Construct the event number and use this as key. If they match return
- * the name of this counter.
+/* Scan the PMU and extract the logical name of a counter from the event. Input
+ * is the counter set and counter number with in the set. Construct the event
+ * number and use this as key. If they match return the name of this counter.
  * If no match is found a NULL pointer is returned.
  */
-static const char *get_counter_name(int set, int nr, const struct pmu_events_table *table)
+static char *get_counter_name(int set, int nr, struct perf_pmu *pmu)
 {
 	struct get_counter_name_data data = {
 		.wanted = get_counterset_start(set) + nr,
 		.result = NULL,
 	};
 
-	if (!table)
+	if (!pmu)
 		return NULL;
 
-	pmu_events_table__for_each_event(table, get_counter_name_callback, &data);
+	perf_pmu__for_each_event(pmu, &data, get_counter_name_callback);
 	return data.result;
 }
 
-static void s390_cpumcfdg_dump(struct perf_sample *sample)
+static void s390_cpumcfdg_dump(struct perf_pmu *pmu, struct perf_sample *sample)
 {
 	size_t i, len = sample->raw_size, offset = 0;
 	unsigned char *buf = sample->raw_data;
 	const char *color = PERF_COLOR_BLUE;
 	struct cf_ctrset_entry *cep, ce;
-	const struct pmu_events_table *table;
 	u64 *p;
 
-	table = pmu_events_table__find();
 	while (offset < len) {
 		cep = (struct cf_ctrset_entry *)(buf + offset);
 
@@ -199,11 +200,12 @@ static void s390_cpumcfdg_dump(struct perf_sample *sample)
 		color_fprintf(stdout, color, "    [%#08zx] Counterset:%d"
 			      " Counters:%d\n", offset, ce.set, ce.ctr);
 		for (i = 0, p = (u64 *)(cep + 1); i < ce.ctr; ++i, ++p) {
-			const char *ev_name = get_counter_name(ce.set, i, table);
+			char *ev_name = get_counter_name(ce.set, i, pmu);
 
 			color_fprintf(stdout, color,
 				      "\tCounter:%03d %s Value:%#018lx\n", i,
 				      ev_name ?: "<unknown>", be64_to_cpu(*p));
+			free(ev_name);
 		}
 		offset += ctrset_size(&ce);
 	}
@@ -216,14 +218,14 @@ static void s390_cpumcfdg_dump(struct perf_sample *sample)
  */
 void evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event, struct perf_sample *sample)
 {
-	struct evsel *ev_bc000;
+	struct evsel *evsel;
 
 	if (event->header.type != PERF_RECORD_SAMPLE)
 		return;
 
-	ev_bc000 = evlist__event2evsel(evlist, event);
-	if (ev_bc000 == NULL ||
-	    ev_bc000->core.attr.config != PERF_EVENT_CPUM_CF_DIAG)
+	evsel = evlist__event2evsel(evlist, event);
+	if (evsel == NULL ||
+	    evsel->core.attr.config != PERF_EVENT_CPUM_CF_DIAG)
 		return;
 
 	/* Display raw data on screen */
@@ -231,5 +233,5 @@ void evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event, str
 		pr_err("Invalid counter set data encountered\n");
 		return;
 	}
-	s390_cpumcfdg_dump(sample);
+	s390_cpumcfdg_dump(evsel->pmu, sample);
 }

From e3edd6cf6399f17114081d0e20f31ddadafb70b5 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 23 Aug 2023 21:13:19 -0700
Subject: [PATCH 0661/1189] perf pmu-events: Reduce processed events by passing
 PMU

Pass the PMU to pmu_events_table__for_each_event so that entries that
don't match don't need to be processed by callback.

If a NULL PMU is passed then all PMUs are processed.

'perf bench internals pmu-scan's "Average PMU scanning" performance is
reduced by about 5% on an Intel tigerlake.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230824041330.266337-8-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/empty-pmu-events.c | 15 ++++++----
 tools/perf/pmu-events/jevents.py         | 18 ++++++++----
 tools/perf/pmu-events/pmu-events.h       |  4 ++-
 tools/perf/tests/pmu-events.c            |  6 ++--
 tools/perf/util/pmu.c                    | 35 +++++++-----------------
 tools/perf/util/pmu.h                    |  1 +
 6 files changed, 41 insertions(+), 38 deletions(-)

diff --git a/tools/perf/pmu-events/empty-pmu-events.c b/tools/perf/pmu-events/empty-pmu-events.c
index 807f2e55c17c..2d6f748280ac 100644
--- a/tools/perf/pmu-events/empty-pmu-events.c
+++ b/tools/perf/pmu-events/empty-pmu-events.c
@@ -266,12 +266,16 @@ static const struct pmu_sys_events pmu_sys_event_tables[] = {
 	},
 };
 
-int pmu_events_table__for_each_event(const struct pmu_events_table *table, pmu_event_iter_fn fn,
-				    void *data)
+int pmu_events_table__for_each_event(const struct pmu_events_table *table, struct perf_pmu *pmu,
+				     pmu_event_iter_fn fn, void *data)
 {
 	for (const struct pmu_event *pe = &table->entries[0]; pe->name; pe++) {
-		int ret = fn(pe, table, data);
+		int ret;
 
+                if (pmu && !pmu__name_match(pmu, pe->pmu))
+                        continue;
+
+		ret = fn(pe, table, data);
 		if (ret)
 			return ret;
 	}
@@ -371,7 +375,8 @@ const struct pmu_metrics_table *find_core_metrics_table(const char *arch, const
 int pmu_for_each_core_event(pmu_event_iter_fn fn, void *data)
 {
 	for (const struct pmu_events_map *tables = &pmu_events_map[0]; tables->arch; tables++) {
-		int ret = pmu_events_table__for_each_event(&tables->event_table, fn, data);
+		int ret = pmu_events_table__for_each_event(&tables->event_table,
+							   /*pmu=*/ NULL, fn, data);
 
 		if (ret)
 			return ret;
@@ -408,7 +413,7 @@ int pmu_for_each_sys_event(pmu_event_iter_fn fn, void *data)
 	for (const struct pmu_sys_events *tables = &pmu_sys_event_tables[0];
 	     tables->name;
 	     tables++) {
-		int ret = pmu_events_table__for_each_event(&tables->table, fn, data);
+		int ret = pmu_events_table__for_each_event(&tables->table, /*pmu=*/ NULL, fn, data);
 
 		if (ret)
 			return ret;
diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index 1ad20140114c..396af53e0e45 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -826,14 +826,20 @@ static int pmu_events_table__for_each_event_pmu(const struct pmu_events_table *t
  }
 
 int pmu_events_table__for_each_event(const struct pmu_events_table *table,
+                                    struct perf_pmu *pmu,
                                     pmu_event_iter_fn fn,
                                     void *data)
 {
         for (size_t i = 0; i < table->num_pmus; i++) {
-                int ret = pmu_events_table__for_each_event_pmu(table, &table->pmus[i],
-                                                               fn, data);
+                const struct pmu_table_entry *table_pmu = &table->pmus[i];
+                const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset];
+                int ret;
 
-                if (ret)
+                if (pmu && !pmu__name_match(pmu, pmu_name))
+                        continue;
+
+                ret = pmu_events_table__for_each_event_pmu(table, table_pmu, fn, data);
+                if (pmu || ret)
                         return ret;
         }
         return 0;
@@ -955,7 +961,8 @@ int pmu_for_each_core_event(pmu_event_iter_fn fn, void *data)
         for (const struct pmu_events_map *tables = &pmu_events_map[0];
              tables->arch;
              tables++) {
-                int ret = pmu_events_table__for_each_event(&tables->event_table, fn, data);
+                int ret = pmu_events_table__for_each_event(&tables->event_table,
+                                                           /*pmu=*/ NULL, fn, data);
 
                 if (ret)
                         return ret;
@@ -992,7 +999,8 @@ int pmu_for_each_sys_event(pmu_event_iter_fn fn, void *data)
         for (const struct pmu_sys_events *tables = &pmu_sys_event_tables[0];
              tables->name;
              tables++) {
-                int ret = pmu_events_table__for_each_event(&tables->event_table, fn, data);
+                int ret = pmu_events_table__for_each_event(&tables->event_table,
+                                                           /*pmu=*/ NULL, fn, data);
 
                 if (ret)
                         return ret;
diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h
index 6557381b7de1..c0303ba42e97 100644
--- a/tools/perf/pmu-events/pmu-events.h
+++ b/tools/perf/pmu-events/pmu-events.h
@@ -77,7 +77,9 @@ typedef int (*pmu_metric_iter_fn)(const struct pmu_metric *pm,
 				  const struct pmu_metrics_table *table,
 				  void *data);
 
-int pmu_events_table__for_each_event(const struct pmu_events_table *table, pmu_event_iter_fn fn,
+int pmu_events_table__for_each_event(const struct pmu_events_table *table,
+				    struct perf_pmu *pmu,
+				    pmu_event_iter_fn fn,
 				    void *data);
 int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table, pmu_metric_iter_fn fn,
 				     void *data);
diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
index 0b6efabc3d20..92d1f6f0e666 100644
--- a/tools/perf/tests/pmu-events.c
+++ b/tools/perf/tests/pmu-events.c
@@ -483,12 +483,14 @@ static int test__pmu_event_table(struct test_suite *test __maybe_unused,
 	if (!table || !sys_event_table)
 		return -1;
 
-	err = pmu_events_table__for_each_event(table, test__pmu_event_table_core_callback,
+	err = pmu_events_table__for_each_event(table, /*pmu=*/ NULL,
+					      test__pmu_event_table_core_callback,
 					      &map_events);
 	if (err)
 		return err;
 
-	err = pmu_events_table__for_each_event(sys_event_table, test__pmu_event_table_sys_callback,
+	err = pmu_events_table__for_each_event(sys_event_table, /*pmu=*/ NULL,
+					      test__pmu_event_table_sys_callback,
 					      &map_events);
 	if (err)
 		return err;
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 0c82bbeea7d6..9ba9ac3d3d96 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -859,28 +859,14 @@ out:
 	return res;
 }
 
-struct pmu_add_cpu_aliases_map_data {
-	/* List being added to. */
-	struct list_head *head;
-	/* If a pmu_event lacks a given PMU the default used. */
-	char *default_pmu_name;
-	/* The PMU that we're searching for events for. */
-	struct perf_pmu *pmu;
-};
-
 static int pmu_add_cpu_aliases_map_callback(const struct pmu_event *pe,
 					const struct pmu_events_table *table __maybe_unused,
 					void *vdata)
 {
-	struct pmu_add_cpu_aliases_map_data *data = vdata;
-	const char *pname = pe->pmu ?: data->default_pmu_name;
+	struct list_head *head = vdata;
 
-	if (!strcmp(pname, data->pmu->name) ||
-	    (data->pmu->is_uncore && pmu_uncore_alias_match(pname, data->pmu->name))) {
-		/* need type casts to override 'const' */
-		__perf_pmu__new_alias(data->head, -1, (char *)pe->name, (char *)pe->desc,
-				      (char *)pe->event, pe);
-	}
+	/* need type casts to override 'const' */
+	__perf_pmu__new_alias(head, -1, (char *)pe->name, (char *)pe->desc, (char *)pe->event, pe);
 	return 0;
 }
 
@@ -890,14 +876,7 @@ static int pmu_add_cpu_aliases_map_callback(const struct pmu_event *pe,
  */
 void pmu_add_cpu_aliases_table(struct perf_pmu *pmu, const struct pmu_events_table *table)
 {
-	struct pmu_add_cpu_aliases_map_data data = {
-		.head = &pmu->aliases,
-		.default_pmu_name = perf_pmus__default_pmu_name(),
-		.pmu = pmu,
-	};
-
-	pmu_events_table__for_each_event(table, pmu_add_cpu_aliases_map_callback, &data);
-	free(data.default_pmu_name);
+	pmu_events_table__for_each_event(table, pmu, pmu_add_cpu_aliases_map_callback, &pmu->aliases);
 }
 
 static void pmu_add_cpu_aliases(struct perf_pmu *pmu)
@@ -1713,6 +1692,12 @@ int perf_pmu__for_each_event(const struct perf_pmu *pmu, void *state, pmu_event_
 	return ret;
 }
 
+bool pmu__name_match(const struct perf_pmu *pmu, const char *pmu_name)
+{
+	return !strcmp(pmu->name, pmu_name) ||
+		(pmu->is_uncore && pmu_uncore_alias_match(pmu_name, pmu->name));
+}
+
 bool perf_pmu__is_software(const struct perf_pmu *pmu)
 {
 	if (pmu->is_core || pmu->is_uncore || pmu->auxtrace)
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 03211de345c1..2b1730152bc0 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -198,6 +198,7 @@ bool perf_pmu__auto_merge_stats(const struct perf_pmu *pmu);
 bool perf_pmu__have_event(const struct perf_pmu *pmu, const char *name);
 size_t perf_pmu__num_events(const struct perf_pmu *pmu);
 int perf_pmu__for_each_event(const struct perf_pmu *pmu, void *state, pmu_event_callback cb);
+bool pmu__name_match(const struct perf_pmu *pmu, const char *pmu_name);
 
 /**
  * perf_pmu_is_software - is the PMU a software PMU as in it uses the

From 3d5045492ab209163714c70aa48e4ab6275ecca4 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 23 Aug 2023 21:13:20 -0700
Subject: [PATCH 0662/1189] perf pmu-events: Add pmu_events_table__find_event()

jevents stores events sorted by name. Add a find function that will
binary search event names avoiding the need to linearly search through
events.

Add a test in tests/pmu-events.c. If the PMU or event aren't found -1000
is returned. If the event is found but no callback function given, 0 is
returned.

This allows the find function also act as a test for existence.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230824041330.266337-9-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/empty-pmu-events.c | 16 ++++++
 tools/perf/pmu-events/jevents.py         | 64 ++++++++++++++++++++++++
 tools/perf/pmu-events/pmu-events.h       |  5 ++
 tools/perf/tests/pmu-events.c            |  5 ++
 4 files changed, 90 insertions(+)

diff --git a/tools/perf/pmu-events/empty-pmu-events.c b/tools/perf/pmu-events/empty-pmu-events.c
index 2d6f748280ac..ef18d403f25f 100644
--- a/tools/perf/pmu-events/empty-pmu-events.c
+++ b/tools/perf/pmu-events/empty-pmu-events.c
@@ -282,6 +282,22 @@ int pmu_events_table__for_each_event(const struct pmu_events_table *table, struc
 	return 0;
 }
 
+int pmu_events_table__find_event(const struct pmu_events_table *table,
+                                 struct perf_pmu *pmu,
+                                 const char *name,
+                                 pmu_event_iter_fn fn,
+                                 void *data)
+{
+	for (const struct pmu_event *pe = &table->entries[0]; pe->name; pe++) {
+                if (pmu && !pmu__name_match(pmu, pe->pmu))
+                        continue;
+
+		if (!strcasecmp(pe->name, name))
+			return fn(pe, table, data);
+	}
+        return -1000;
+}
+
 int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table, pmu_metric_iter_fn fn,
 				      void *data)
 {
diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index 396af53e0e45..991fcf6cca64 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -825,6 +825,49 @@ static int pmu_events_table__for_each_event_pmu(const struct pmu_events_table *t
         return 0;
  }
 
+static int pmu_events_table__find_event_pmu(const struct pmu_events_table *table,
+                                            const struct pmu_table_entry *pmu,
+                                            const char *name,
+                                            pmu_event_iter_fn fn,
+                                            void *data)
+{
+        struct pmu_event pe = {
+                .pmu = &big_c_string[pmu->pmu_name.offset],
+        };
+        int low = 0, high = pmu->num_entries - 1;
+
+        while (low <= high) {
+                int cmp, mid = (low + high) / 2;
+
+                decompress_event(pmu->entries[mid].offset, &pe);
+
+                if (!pe.name && !name)
+                        goto do_call;
+
+                if (!pe.name && name) {
+                        low = mid + 1;
+                        continue;
+                }
+                if (pe.name && !name) {
+                        high = mid - 1;
+                        continue;
+                }
+
+                cmp = strcasecmp(pe.name, name);
+                if (cmp < 0) {
+                        low = mid + 1;
+                        continue;
+                }
+                if (cmp > 0) {
+                        high = mid - 1;
+                        continue;
+                }
+  do_call:
+                return fn ? fn(&pe, table, data) : 0;
+        }
+        return -1000;
+}
+
 int pmu_events_table__for_each_event(const struct pmu_events_table *table,
                                     struct perf_pmu *pmu,
                                     pmu_event_iter_fn fn,
@@ -845,6 +888,27 @@ int pmu_events_table__for_each_event(const struct pmu_events_table *table,
         return 0;
 }
 
+int pmu_events_table__find_event(const struct pmu_events_table *table,
+                                 struct perf_pmu *pmu,
+                                 const char *name,
+                                 pmu_event_iter_fn fn,
+                                 void *data)
+{
+        for (size_t i = 0; i < table->num_pmus; i++) {
+                const struct pmu_table_entry *table_pmu = &table->pmus[i];
+                const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset];
+                int ret;
+
+                if (!pmu__name_match(pmu, pmu_name))
+                        continue;
+
+                ret = pmu_events_table__find_event_pmu(table, table_pmu, name, fn, data);
+                if (ret != -1000)
+                        return ret;
+        }
+        return -1000;
+}
+
 static int pmu_metrics_table__for_each_metric_pmu(const struct pmu_metrics_table *table,
                                                 const struct pmu_table_entry *pmu,
                                                 pmu_metric_iter_fn fn,
diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h
index c0303ba42e97..9882b7125761 100644
--- a/tools/perf/pmu-events/pmu-events.h
+++ b/tools/perf/pmu-events/pmu-events.h
@@ -81,6 +81,11 @@ int pmu_events_table__for_each_event(const struct pmu_events_table *table,
 				    struct perf_pmu *pmu,
 				    pmu_event_iter_fn fn,
 				    void *data);
+int pmu_events_table__find_event(const struct pmu_events_table *table,
+                                 struct perf_pmu *pmu,
+                                 const char *name,
+                                 pmu_event_iter_fn fn,
+				 void *data);
 int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table, pmu_metric_iter_fn fn,
 				     void *data);
 
diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
index 92d1f6f0e666..34f0de182fa9 100644
--- a/tools/perf/tests/pmu-events.c
+++ b/tools/perf/tests/pmu-events.c
@@ -546,6 +546,11 @@ static int __test_core_pmu_event_aliases(char *pmu_name, int *count)
 
 	pmu_add_cpu_aliases_table(pmu, table);
 
+	res = pmu_events_table__find_event(table, pmu, "bp_l1_btb_correct", NULL, NULL);
+	if (res != 0) {
+		pr_debug("Missing test event in test architecture");
+		return res;
+	}
 	for (; *test_event_table; test_event_table++) {
 		struct perf_pmu_test_event test_event = **test_event_table;
 		struct pmu_event const *event = &test_event.event;

From edb217ff14fb98c74373f65f8ac08b9bfe26e344 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 23 Aug 2023 21:13:21 -0700
Subject: [PATCH 0663/1189] perf pmu: Parse sysfs events directly from a file

Rather than read a sysfs events file into a 256 byte char buffer, pass
the FILE* directly to the lex/yacc parser.

This avoids there being a maximum events file size.

While changing the API, constify some arguments to remove unnecessary
casts.

Allocating the read buffer decreases the performance of pmu-scan by
around 3%.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230824041330.266337-10-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/x86/util/intel-pt.c |  2 +-
 tools/perf/tests/parse-events.c     |  2 +-
 tools/perf/util/parse-events.c      | 18 +++++++----
 tools/perf/util/parse-events.h      |  3 +-
 tools/perf/util/pmu.c               | 48 ++++++++++-------------------
 5 files changed, 33 insertions(+), 40 deletions(-)

diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 27944c15ac14..31807791589e 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -74,7 +74,7 @@ static int intel_pt_parse_terms_with_default(struct perf_pmu *pmu,
 
 	INIT_LIST_HEAD(terms);
 
-	err = parse_events_terms(terms, str);
+	err = parse_events_terms(terms, str, /*input=*/ NULL);
 	if (err)
 		goto out_free;
 
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 658fb9599d95..d86076d575ed 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -2472,7 +2472,7 @@ static int test_term(const struct terms_test *t)
 
 	INIT_LIST_HEAD(&terms);
 
-	ret = parse_events_terms(&terms, t->str);
+	ret = parse_events_terms(&terms, t->str, /*input=*/ NULL);
 	if (ret) {
 		pr_debug("failed to parse terms '%s', err %d\n",
 			 t->str , ret);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 781747bedc3e..c71e135d7335 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1715,6 +1715,7 @@ int parse_events_name(struct list_head *list, const char *name)
 }
 
 static int parse_events__scanner(const char *str,
+				 FILE *input,
 				 struct parse_events_state *parse_state)
 {
 	YY_BUFFER_STATE buffer;
@@ -1725,7 +1726,10 @@ static int parse_events__scanner(const char *str,
 	if (ret)
 		return ret;
 
-	buffer = parse_events__scan_string(str, scanner);
+	if (str)
+		buffer = parse_events__scan_string(str, scanner);
+	else
+	        parse_events_set_in(input, scanner);
 
 #ifdef PARSER_DEBUG
 	parse_events_debug = 1;
@@ -1733,8 +1737,10 @@ static int parse_events__scanner(const char *str,
 #endif
 	ret = parse_events_parse(parse_state, scanner);
 
-	parse_events__flush_buffer(buffer, scanner);
-	parse_events__delete_buffer(buffer, scanner);
+	if (str) {
+		parse_events__flush_buffer(buffer, scanner);
+		parse_events__delete_buffer(buffer, scanner);
+	}
 	parse_events_lex_destroy(scanner);
 	return ret;
 }
@@ -1742,7 +1748,7 @@ static int parse_events__scanner(const char *str,
 /*
  * parse event config string, return a list of event terms.
  */
-int parse_events_terms(struct list_head *terms, const char *str)
+int parse_events_terms(struct list_head *terms, const char *str, FILE *input)
 {
 	struct parse_events_state parse_state = {
 		.terms  = NULL,
@@ -1750,7 +1756,7 @@ int parse_events_terms(struct list_head *terms, const char *str)
 	};
 	int ret;
 
-	ret = parse_events__scanner(str, &parse_state);
+	ret = parse_events__scanner(str, input, &parse_state);
 
 	if (!ret) {
 		list_splice(parse_state.terms, terms);
@@ -2001,7 +2007,7 @@ int __parse_events(struct evlist *evlist, const char *str, const char *pmu_filte
 	};
 	int ret, ret2;
 
-	ret = parse_events__scanner(str, &parse_state);
+	ret = parse_events__scanner(str, /*input=*/ NULL, &parse_state);
 
 	if (!ret && list_empty(&parse_state.list)) {
 		WARN_ONCE(true, "WARNING: event parser found nothing\n");
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 411f69b2ac3a..c7f779420723 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -9,6 +9,7 @@
 #include <stdbool.h>
 #include <linux/types.h>
 #include <linux/perf_event.h>
+#include <stdio.h>
 #include <string.h>
 
 struct evsel;
@@ -42,7 +43,7 @@ static inline int parse_events(struct evlist *evlist, const char *str,
 
 int parse_event(struct evlist *evlist, const char *str);
 
-int parse_events_terms(struct list_head *terms, const char *str);
+int parse_events_terms(struct list_head *terms, const char *str, FILE *input);
 int parse_filter(const struct option *opt, const char *str, int unset);
 int exclude_perf(const struct option *opt, const char *arg, int unset);
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 9ba9ac3d3d96..263c63eabc2e 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -280,7 +280,7 @@ out:
 	return ret;
 }
 
-static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, int dirfd, char *name)
+static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, int dirfd, const char *name)
 {
 	struct stat st;
 	ssize_t sret;
@@ -312,7 +312,7 @@ error:
 	return ret;
 }
 
-static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, int dirfd, char *name)
+static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, int dirfd, const char *name)
 {
 	char path[PATH_MAX];
 	ssize_t sret;
@@ -343,7 +343,7 @@ error:
 }
 
 static int
-perf_pmu__parse_per_pkg(struct perf_pmu_alias *alias, int dirfd, char *name)
+perf_pmu__parse_per_pkg(struct perf_pmu_alias *alias, int dirfd, const char *name)
 {
 	char path[PATH_MAX];
 	int fd;
@@ -361,7 +361,7 @@ perf_pmu__parse_per_pkg(struct perf_pmu_alias *alias, int dirfd, char *name)
 }
 
 static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias,
-				    int dirfd, char *name)
+				    int dirfd, const char *name)
 {
 	char path[PATH_MAX];
 	int fd;
@@ -454,8 +454,9 @@ static bool perf_pmu_merge_alias(struct perf_pmu_alias *newalias,
 	return false;
 }
 
-static int __perf_pmu__new_alias(struct list_head *list, int dirfd, char *name,
-				 char *desc, char *val, const struct pmu_event *pe)
+static int perf_pmu__new_alias(struct list_head *list, int dirfd, const char *name,
+				const char *desc, const char *val, FILE *val_fd,
+				const struct pmu_event *pe)
 {
 	struct parse_events_term *term;
 	struct perf_pmu_alias *alias;
@@ -484,7 +485,7 @@ static int __perf_pmu__new_alias(struct list_head *list, int dirfd, char *name,
 	alias->snapshot = false;
 	alias->deprecated = deprecated;
 
-	ret = parse_events_terms(&alias->terms, val);
+	ret = parse_events_terms(&alias->terms, val, val_fd);
 	if (ret) {
 		pr_err("Cannot parse alias %s: %d\n", val, ret);
 		free(alias);
@@ -541,23 +542,6 @@ static int __perf_pmu__new_alias(struct list_head *list, int dirfd, char *name,
 	return 0;
 }
 
-static int perf_pmu__new_alias(struct list_head *list, int dirfd, char *name, FILE *file)
-{
-	char buf[256];
-	int ret;
-
-	ret = fread(buf, 1, sizeof(buf), file);
-	if (ret == 0)
-		return -EINVAL;
-
-	buf[ret] = 0;
-
-	/* Remove trailing newline from sysfs file */
-	strim(buf);
-
-	return __perf_pmu__new_alias(list, dirfd, name, NULL, buf, NULL);
-}
-
 static inline bool pmu_alias_info_file(char *name)
 {
 	size_t len;
@@ -613,7 +597,8 @@ static int pmu_aliases_parse(int dirfd, struct list_head *head)
 			continue;
 		}
 
-		if (perf_pmu__new_alias(head, dirfd, name, file) < 0)
+		if (perf_pmu__new_alias(head, dirfd, name, /*desc=*/ NULL,
+					/*val=*/ NULL, file, /*pe=*/ NULL) < 0)
 			pr_debug("Cannot set up %s\n", name);
 		fclose(file);
 	}
@@ -866,7 +851,7 @@ static int pmu_add_cpu_aliases_map_callback(const struct pmu_event *pe,
 	struct list_head *head = vdata;
 
 	/* need type casts to override 'const' */
-	__perf_pmu__new_alias(head, -1, (char *)pe->name, (char *)pe->desc, (char *)pe->event, pe);
+	perf_pmu__new_alias(head, -1, pe->name, pe->desc, pe->event, /*val_fd=*/ NULL, pe);
 	return 0;
 }
 
@@ -907,11 +892,12 @@ static int pmu_add_sys_aliases_iter_fn(const struct pmu_event *pe,
 
 	if (!strcmp(pmu->id, pe->compat) &&
 	    pmu_uncore_alias_match(pe->pmu, pmu->name)) {
-		__perf_pmu__new_alias(idata->head, -1,
-				      (char *)pe->name,
-				      (char *)pe->desc,
-				      (char *)pe->event,
-				      pe);
+		perf_pmu__new_alias(idata->head, -1,
+				pe->name,
+				pe->desc,
+				pe->event,
+				/*val_fd=*/ NULL,
+				pe);
 	}
 
 	return 0;

From f26d22f1bac8d57a1bfbea0513285d9347fde95d Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 23 Aug 2023 21:13:22 -0700
Subject: [PATCH 0664/1189] perf pmu: Prefer passing pmu to aliases list

The aliases list is part of the PMU. Rather than pass the aliases
list, pass the full PMU simplifying some callbacks.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230824041330.266337-11-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/pmu.c | 44 ++++++++++++++++---------------------------
 1 file changed, 16 insertions(+), 28 deletions(-)

diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 263c63eabc2e..c37d98a11861 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -435,12 +435,12 @@ static void perf_pmu__del_aliases(struct perf_pmu *pmu)
 /* Merge an alias, search in alias list. If this name is already
  * present merge both of them to combine all information.
  */
-static bool perf_pmu_merge_alias(struct perf_pmu_alias *newalias,
-				 struct list_head *alist)
+static bool perf_pmu_merge_alias(struct perf_pmu *pmu,
+				 struct perf_pmu_alias *newalias)
 {
 	struct perf_pmu_alias *a;
 
-	list_for_each_entry(a, alist, list) {
+	list_for_each_entry(a, &pmu->aliases, list) {
 		if (!strcasecmp(newalias->name, a->name)) {
 			if (newalias->pmu_name && a->pmu_name &&
 			    !strcasecmp(newalias->pmu_name, a->pmu_name)) {
@@ -454,7 +454,7 @@ static bool perf_pmu_merge_alias(struct perf_pmu_alias *newalias,
 	return false;
 }
 
-static int perf_pmu__new_alias(struct list_head *list, int dirfd, const char *name,
+static int perf_pmu__new_alias(struct perf_pmu *pmu, int dirfd, const char *name,
 				const char *desc, const char *val, FILE *val_fd,
 				const struct pmu_event *pe)
 {
@@ -536,8 +536,8 @@ static int perf_pmu__new_alias(struct list_head *list, int dirfd, const char *na
 	alias->str = strdup(newval);
 	alias->pmu_name = pmu_name ? strdup(pmu_name) : NULL;
 
-	if (!perf_pmu_merge_alias(alias, list))
-		list_add_tail(&alias->list, list);
+	if (!perf_pmu_merge_alias(pmu, alias))
+		list_add_tail(&alias->list, &pmu->aliases);
 
 	return 0;
 }
@@ -563,7 +563,7 @@ static inline bool pmu_alias_info_file(char *name)
  * Process all the sysfs attributes located under the directory
  * specified in 'dir' parameter.
  */
-static int pmu_aliases_parse(int dirfd, struct list_head *head)
+static int pmu_aliases_parse(struct perf_pmu *pmu, int dirfd)
 {
 	struct dirent *evt_ent;
 	DIR *event_dir;
@@ -597,7 +597,7 @@ static int pmu_aliases_parse(int dirfd, struct list_head *head)
 			continue;
 		}
 
-		if (perf_pmu__new_alias(head, dirfd, name, /*desc=*/ NULL,
+		if (perf_pmu__new_alias(pmu, dirfd, name, /*desc=*/ NULL,
 					/*val=*/ NULL, file, /*pe=*/ NULL) < 0)
 			pr_debug("Cannot set up %s\n", name);
 		fclose(file);
@@ -620,7 +620,7 @@ static int pmu_aliases(struct perf_pmu *pmu, int dirfd, const char *name)
 		return 0;
 
 	/* it'll close the fd */
-	if (pmu_aliases_parse(fd, &pmu->aliases))
+	if (pmu_aliases_parse(pmu, fd))
 		return -1;
 
 	return 0;
@@ -848,10 +848,9 @@ static int pmu_add_cpu_aliases_map_callback(const struct pmu_event *pe,
 					const struct pmu_events_table *table __maybe_unused,
 					void *vdata)
 {
-	struct list_head *head = vdata;
+	struct perf_pmu *pmu = vdata;
 
-	/* need type casts to override 'const' */
-	perf_pmu__new_alias(head, -1, pe->name, pe->desc, pe->event, /*val_fd=*/ NULL, pe);
+	perf_pmu__new_alias(pmu, -1, pe->name, pe->desc, pe->event, /*val_fd=*/ NULL, pe);
 	return 0;
 }
 
@@ -861,7 +860,7 @@ static int pmu_add_cpu_aliases_map_callback(const struct pmu_event *pe,
  */
 void pmu_add_cpu_aliases_table(struct perf_pmu *pmu, const struct pmu_events_table *table)
 {
-	pmu_events_table__for_each_event(table, pmu, pmu_add_cpu_aliases_map_callback, &pmu->aliases);
+	pmu_events_table__for_each_event(table, pmu, pmu_add_cpu_aliases_map_callback, pmu);
 }
 
 static void pmu_add_cpu_aliases(struct perf_pmu *pmu)
@@ -875,24 +874,18 @@ static void pmu_add_cpu_aliases(struct perf_pmu *pmu)
 	pmu_add_cpu_aliases_table(pmu, table);
 }
 
-struct pmu_sys_event_iter_data {
-	struct list_head *head;
-	struct perf_pmu *pmu;
-};
-
 static int pmu_add_sys_aliases_iter_fn(const struct pmu_event *pe,
 				       const struct pmu_events_table *table __maybe_unused,
-				       void *data)
+				       void *vdata)
 {
-	struct pmu_sys_event_iter_data *idata = data;
-	struct perf_pmu *pmu = idata->pmu;
+	struct perf_pmu *pmu = vdata;
 
 	if (!pe->compat || !pe->pmu)
 		return 0;
 
 	if (!strcmp(pmu->id, pe->compat) &&
 	    pmu_uncore_alias_match(pe->pmu, pmu->name)) {
-		perf_pmu__new_alias(idata->head, -1,
+		perf_pmu__new_alias(pmu, -1,
 				pe->name,
 				pe->desc,
 				pe->event,
@@ -905,15 +898,10 @@ static int pmu_add_sys_aliases_iter_fn(const struct pmu_event *pe,
 
 void pmu_add_sys_aliases(struct perf_pmu *pmu)
 {
-	struct pmu_sys_event_iter_data idata = {
-		.head = &pmu->aliases,
-		.pmu = pmu,
-	};
-
 	if (!pmu->id)
 		return;
 
-	pmu_for_each_sys_event(pmu_add_sys_aliases_iter_fn, &idata);
+	pmu_for_each_sys_event(pmu_add_sys_aliases_iter_fn, pmu);
 }
 
 struct perf_event_attr * __weak

From f63a536f03a2f64fa9a75369e2d006d77f90c156 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 23 Aug 2023 21:13:23 -0700
Subject: [PATCH 0665/1189] perf pmu: Merge JSON events with sysfs at load time

Rather than load all sysfs events then parsing all JSON events and
merging with ones that already exist. When a sysfs event is loaded, look
for a corresponding JSON event and merge immediately.

To simplify the logic, early exit the perf_pmu__new_alias function if an
alias is attempted to be added twice - as merging has already been
explicitly handled.

Fix the copying of terms to a merged alias and some ENOMEM paths.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230824041330.266337-12-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/pmu.c | 179 +++++++++++++++++++++---------------------
 1 file changed, 89 insertions(+), 90 deletions(-)

diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index c37d98a11861..bc2dd8f94bcf 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -377,38 +377,6 @@ static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias,
 	return 0;
 }
 
-static void perf_pmu_assign_str(char *name, const char *field, char **old_str,
-				char **new_str)
-{
-	if (!*old_str)
-		goto set_new;
-
-	if (*new_str) {	/* Have new string, check with old */
-		if (strcasecmp(*old_str, *new_str))
-			pr_debug("alias %s differs in field '%s'\n",
-				 name, field);
-		zfree(old_str);
-	} else		/* Nothing new --> keep old string */
-		return;
-set_new:
-	*old_str = *new_str;
-	*new_str = NULL;
-}
-
-static void perf_pmu_update_alias(struct perf_pmu_alias *old,
-				  struct perf_pmu_alias *newalias)
-{
-	perf_pmu_assign_str(old->name, "desc", &old->desc, &newalias->desc);
-	perf_pmu_assign_str(old->name, "long_desc", &old->long_desc,
-			    &newalias->long_desc);
-	perf_pmu_assign_str(old->name, "topic", &old->topic, &newalias->topic);
-	perf_pmu_assign_str(old->name, "value", &old->str, &newalias->str);
-	old->scale = newalias->scale;
-	old->per_pkg = newalias->per_pkg;
-	old->snapshot = newalias->snapshot;
-	memcpy(old->unit, newalias->unit, sizeof(old->unit));
-}
-
 /* Delete an alias entry. */
 static void perf_pmu_free_alias(struct perf_pmu_alias *newalias)
 {
@@ -432,26 +400,58 @@ static void perf_pmu__del_aliases(struct perf_pmu *pmu)
 	}
 }
 
-/* Merge an alias, search in alias list. If this name is already
- * present merge both of them to combine all information.
- */
-static bool perf_pmu_merge_alias(struct perf_pmu *pmu,
-				 struct perf_pmu_alias *newalias)
+static struct perf_pmu_alias *perf_pmu__find_alias(const struct perf_pmu *pmu, const char *name)
 {
-	struct perf_pmu_alias *a;
+	struct perf_pmu_alias *alias;
 
-	list_for_each_entry(a, &pmu->aliases, list) {
-		if (!strcasecmp(newalias->name, a->name)) {
-			if (newalias->pmu_name && a->pmu_name &&
-			    !strcasecmp(newalias->pmu_name, a->pmu_name)) {
-				continue;
-			}
-			perf_pmu_update_alias(a, newalias);
-			perf_pmu_free_alias(newalias);
-			return true;
-		}
+	list_for_each_entry(alias, &pmu->aliases, list) {
+		if (!strcasecmp(alias->name, name))
+			return alias;
 	}
-	return false;
+	return NULL;
+}
+
+static bool assign_str(const char *name, const char *field, char **old_str,
+				const char *new_str)
+{
+	if (!*old_str && new_str) {
+		*old_str = strdup(new_str);
+		return true;
+	}
+
+	if (!new_str || !strcasecmp(*old_str, new_str))
+		return false; /* Nothing to update. */
+
+	pr_debug("alias %s differs in field '%s' ('%s' != '%s')\n",
+		name, field, *old_str, new_str);
+	zfree(old_str);
+	*old_str = strdup(new_str);
+	return true;
+}
+
+static int update_alias(const struct pmu_event *pe,
+			const struct pmu_events_table *table __maybe_unused,
+			void *vdata)
+{
+	struct perf_pmu_alias *alias = vdata;
+	int ret = 0;
+
+	assign_str(pe->name, "desc", &alias->desc, pe->desc);
+	assign_str(pe->name, "long_desc", &alias->long_desc, pe->long_desc);
+	assign_str(pe->name, "topic", &alias->topic, pe->topic);
+	alias->per_pkg = pe->perpkg;
+	if (assign_str(pe->name, "value", &alias->str, pe->event)) {
+		parse_events_terms__purge(&alias->terms);
+		ret = parse_events_terms(&alias->terms, pe->event, /*input=*/NULL);
+	}
+	if (!ret && pe->unit) {
+		char *unit;
+
+		ret = perf_pmu__convert_scale(pe->unit, &unit, &alias->scale);
+		if (!ret)
+			snprintf(alias->unit, sizeof(alias->unit), "%s", unit);
+	}
+	return ret;
 }
 
 static int perf_pmu__new_alias(struct perf_pmu *pmu, int dirfd, const char *name,
@@ -465,6 +465,11 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, int dirfd, const char *name
 	const char *long_desc = NULL, *topic = NULL, *unit = NULL, *pmu_name = NULL;
 	bool deprecated = false, perpkg = false;
 
+	if (perf_pmu__find_alias(pmu, name)) {
+		/* Alias was already created/loaded. */
+		return 0;
+	}
+
 	if (pe) {
 		long_desc = pe->long_desc;
 		topic = pe->topic;
@@ -492,27 +497,6 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, int dirfd, const char *name
 		return ret;
 	}
 
-	/* Scan event and remove leading zeroes, spaces, newlines, some
-	 * platforms have terms specified as
-	 * event=0x0091 (read from files ../<PMU>/events/<FILE>
-	 * and terms specified as event=0x91 (read from JSON files).
-	 *
-	 * Rebuild string to make alias->str member comparable.
-	 */
-	memset(newval, 0, sizeof(newval));
-	ret = 0;
-	list_for_each_entry(term, &alias->terms, list) {
-		if (ret)
-			ret += scnprintf(newval + ret, sizeof(newval) - ret,
-					 ",");
-		if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM)
-			ret += scnprintf(newval + ret, sizeof(newval) - ret,
-					 "%s=%#x", term->config, term->val.num);
-		else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR)
-			ret += scnprintf(newval + ret, sizeof(newval) - ret,
-					 "%s=%s", term->config, term->val.str);
-	}
-
 	alias->name = strdup(name);
 	if (dirfd >= 0) {
 		/*
@@ -528,17 +512,43 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, int dirfd, const char *name
 	alias->long_desc = long_desc ? strdup(long_desc) :
 				desc ? strdup(desc) : NULL;
 	alias->topic = topic ? strdup(topic) : NULL;
+	alias->pmu_name = pmu_name ? strdup(pmu_name) : NULL;
 	if (unit) {
-		if (perf_pmu__convert_scale(unit, (char **)&unit, &alias->scale) < 0)
+		if (perf_pmu__convert_scale(unit, (char **)&unit, &alias->scale) < 0) {
+			perf_pmu_free_alias(alias);
 			return -1;
+		}
 		snprintf(alias->unit, sizeof(alias->unit), "%s", unit);
 	}
+	if (!pe) {
+		/* Update an event from sysfs with json data. */
+		const struct pmu_events_table *table = perf_pmu__find_events_table(pmu);
+
+		if (table)
+			pmu_events_table__find_event(table, pmu, name, update_alias, alias);
+	}
+
+	/* Scan event and remove leading zeroes, spaces, newlines, some
+	 * platforms have terms specified as
+	 * event=0x0091 (read from files ../<PMU>/events/<FILE>
+	 * and terms specified as event=0x91 (read from JSON files).
+	 *
+	 * Rebuild string to make alias->str member comparable.
+	 */
+	ret = 0;
+	list_for_each_entry(term, &alias->terms, list) {
+		if (ret)
+			ret += scnprintf(newval + ret, sizeof(newval) - ret,
+					 ",");
+		if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM)
+			ret += scnprintf(newval + ret, sizeof(newval) - ret,
+					 "%s=%#x", term->config, term->val.num);
+		else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR)
+			ret += scnprintf(newval + ret, sizeof(newval) - ret,
+					 "%s=%s", term->config, term->val.str);
+	}
 	alias->str = strdup(newval);
-	alias->pmu_name = pmu_name ? strdup(pmu_name) : NULL;
-
-	if (!perf_pmu_merge_alias(pmu, alias))
-		list_add_tail(&alias->list, &pmu->aliases);
-
+	list_add_tail(&alias->list, &pmu->aliases);
 	return 0;
 }
 
@@ -944,6 +954,9 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char
 	INIT_LIST_HEAD(&pmu->format);
 	INIT_LIST_HEAD(&pmu->aliases);
 	INIT_LIST_HEAD(&pmu->caps);
+	pmu->name = strdup(name);
+	if (!pmu->name)
+		goto err;
 	/*
 	 * The pmu data we store & need consists of the pmu
 	 * type value and format definitions. Load both right
@@ -962,9 +975,6 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char
 	}
 	pmu->is_core = is_pmu_core(name);
 	pmu->cpus = pmu_cpumask(dirfd, name, pmu->is_core);
-	pmu->name = strdup(name);
-	if (!pmu->name)
-		goto err;
 
 	/* Read type, and ensure that type value is successfully assigned (return 1) */
 	if (perf_pmu__scan_file_at(pmu, dirfd, "type", "%u", &type) != 1)
@@ -1357,17 +1367,6 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 	return perf_pmu__config_terms(pmu, attr, head_terms, zero, err);
 }
 
-static struct perf_pmu_alias *perf_pmu__find_alias(const struct perf_pmu *pmu, const char *str)
-{
-	struct perf_pmu_alias *alias;
-
-	list_for_each_entry(alias, &pmu->aliases, list) {
-		if (!strcasecmp(alias->name, str))
-			return alias;
-	}
-	return NULL;
-}
-
 static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
 					     struct parse_events_term *term)
 {

From 7c52f10c0d4d8db86ef94b40446efbe291d067dc Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 23 Aug 2023 21:13:24 -0700
Subject: [PATCH 0666/1189] perf pmu: Cache JSON events table

Cache the JSON events table so that finding it isn't done per
event/alias.

Change the events table find so that when the PMU is given, if the PMU
has no JSON events return null.

Update usage to always use the PMU variable.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230824041330.266337-13-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/jevents.py | 14 ++++++++++++--
 tools/perf/tests/pmu-events.c    |  2 ++
 tools/perf/util/pmu.c            | 16 +++++++---------
 tools/perf/util/pmu.h            |  4 ++++
 4 files changed, 25 insertions(+), 11 deletions(-)

diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index 991fcf6cca64..f07864fabd54 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -948,7 +948,7 @@ const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu)
 {
         const struct pmu_events_table *table = NULL;
         char *cpuid = perf_pmu__getcpuid(pmu);
-        int i;
+        size_t i;
 
         /* on some platforms which uses cpus map, cpuid can be NULL for
          * PMUs other than CORE PMUs.
@@ -968,7 +968,17 @@ const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu)
                 }
         }
         free(cpuid);
-        return table;
+        if (!pmu)
+                return table;
+
+        for (i = 0; i < table->num_pmus; i++) {
+                const struct pmu_table_entry *table_pmu = &table->pmus[i];
+                const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset];
+
+                if (pmu__name_match(pmu, pmu_name))
+                        return table;
+        }
+        return NULL;
 }
 
 const struct pmu_metrics_table *perf_pmu__find_metrics_table(struct perf_pmu *pmu)
diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
index 34f0de182fa9..4fcb84fd1f65 100644
--- a/tools/perf/tests/pmu-events.c
+++ b/tools/perf/tests/pmu-events.c
@@ -544,6 +544,7 @@ static int __test_core_pmu_event_aliases(char *pmu_name, int *count)
 	INIT_LIST_HEAD(&pmu->list);
 	pmu->name = strdup(pmu_name);
 
+	pmu->events_table = table;
 	pmu_add_cpu_aliases_table(pmu, table);
 
 	res = pmu_events_table__find_event(table, pmu, "bp_l1_btb_correct", NULL, NULL);
@@ -583,6 +584,7 @@ static int __test_uncore_pmu_event_aliases(struct perf_pmu_test_pmu *test_pmu)
 	events_table = find_core_events_table("testarch", "testcpu");
 	if (!events_table)
 		return -1;
+	pmu->events_table = events_table;
 	pmu_add_cpu_aliases_table(pmu, events_table);
 	pmu_add_sys_aliases(pmu);
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index bc2dd8f94bcf..685903c1970b 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -522,10 +522,10 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, int dirfd, const char *name
 	}
 	if (!pe) {
 		/* Update an event from sysfs with json data. */
-		const struct pmu_events_table *table = perf_pmu__find_events_table(pmu);
-
-		if (table)
-			pmu_events_table__find_event(table, pmu, name, update_alias, alias);
+		if (pmu->events_table) {
+			pmu_events_table__find_event(pmu->events_table, pmu, name,
+						     update_alias, alias);
+		}
 	}
 
 	/* Scan event and remove leading zeroes, spaces, newlines, some
@@ -875,13 +875,10 @@ void pmu_add_cpu_aliases_table(struct perf_pmu *pmu, const struct pmu_events_tab
 
 static void pmu_add_cpu_aliases(struct perf_pmu *pmu)
 {
-	const struct pmu_events_table *table;
-
-	table = perf_pmu__find_events_table(pmu);
-	if (!table)
+	if (!pmu->events_table)
 		return;
 
-	pmu_add_cpu_aliases_table(pmu, table);
+	pmu_add_cpu_aliases_table(pmu, pmu->events_table);
 }
 
 static int pmu_add_sys_aliases_iter_fn(const struct pmu_event *pe,
@@ -992,6 +989,7 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char
 	if (pmu->is_uncore)
 		pmu->id = pmu_id(name);
 	pmu->max_precise = pmu_max_precise(dirfd, pmu);
+	pmu->events_table = perf_pmu__find_events_table(pmu);
 	pmu_add_cpu_aliases(pmu);
 	pmu_add_sys_aliases(pmu);
 	list_add_tail(&pmu->list, pmus);
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 2b1730152bc0..6bf0fbde4e85 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -114,6 +114,10 @@ struct perf_pmu {
 	 * from json events in pmu-events.c.
 	 */
 	struct list_head aliases;
+	/**
+	 * @events_table: The events table for json events in pmu-events.c.
+	 */
+	const struct pmu_events_table *events_table;
 	/** @caps_initialized: Has the list caps been initialized? */
 	bool caps_initialized;
 	/** @nr_caps: The length of the list caps. */

From e6ff1eed3584362dcf5ffb6b9daf497183b4d3a8 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 23 Aug 2023 21:13:25 -0700
Subject: [PATCH 0667/1189] perf pmu: Lazily add JSON events

Rather than scanning all JSON events and adding them when a PMU is
created, add the alias when the JSON event is needed.

Average core PMU scanning run time reduced by 60.2%. Average PMU
scanning run time reduced by 15%. Page faults with no events reduced by
74 page faults, 4% of total.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230824041330.266337-14-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/empty-pmu-events.c | 14 +++++++
 tools/perf/pmu-events/jevents.py         | 15 +++++++
 tools/perf/pmu-events/pmu-events.h       |  4 ++
 tools/perf/tests/pmu-events.c            |  2 +
 tools/perf/util/pmu.c                    | 50 ++++++++++++++++++------
 tools/perf/util/pmu.h                    | 15 +++++--
 6 files changed, 85 insertions(+), 15 deletions(-)

diff --git a/tools/perf/pmu-events/empty-pmu-events.c b/tools/perf/pmu-events/empty-pmu-events.c
index ef18d403f25f..12bd043a05e3 100644
--- a/tools/perf/pmu-events/empty-pmu-events.c
+++ b/tools/perf/pmu-events/empty-pmu-events.c
@@ -298,6 +298,20 @@ int pmu_events_table__find_event(const struct pmu_events_table *table,
         return -1000;
 }
 
+size_t pmu_events_table__num_events(const struct pmu_events_table *table,
+                                    struct perf_pmu *pmu)
+{
+        size_t count = 0;
+
+	for (const struct pmu_event *pe = &table->entries[0]; pe->name; pe++) {
+                if (pmu && !pmu__name_match(pmu, pe->pmu))
+                        continue;
+
+		count++;
+	}
+        return count;
+}
+
 int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table, pmu_metric_iter_fn fn,
 				      void *data)
 {
diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index f07864fabd54..01335a452e70 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -909,6 +909,21 @@ int pmu_events_table__find_event(const struct pmu_events_table *table,
         return -1000;
 }
 
+size_t pmu_events_table__num_events(const struct pmu_events_table *table,
+                                    struct perf_pmu *pmu)
+{
+        size_t count = 0;
+
+        for (size_t i = 0; i < table->num_pmus; i++) {
+                const struct pmu_table_entry *table_pmu = &table->pmus[i];
+                const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset];
+
+                if (pmu__name_match(pmu, pmu_name))
+                        count += table_pmu->num_entries;
+        }
+        return count;
+}
+
 static int pmu_metrics_table__for_each_metric_pmu(const struct pmu_metrics_table *table,
                                                 const struct pmu_table_entry *pmu,
                                                 pmu_metric_iter_fn fn,
diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h
index 9882b7125761..f5aa96f1685c 100644
--- a/tools/perf/pmu-events/pmu-events.h
+++ b/tools/perf/pmu-events/pmu-events.h
@@ -3,6 +3,7 @@
 #define PMU_EVENTS_H
 
 #include <stdbool.h>
+#include <stddef.h>
 
 struct perf_pmu;
 
@@ -86,6 +87,9 @@ int pmu_events_table__find_event(const struct pmu_events_table *table,
                                  const char *name,
                                  pmu_event_iter_fn fn,
 				 void *data);
+size_t pmu_events_table__num_events(const struct pmu_events_table *table,
+				    struct perf_pmu *pmu);
+
 int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table, pmu_metric_iter_fn fn,
 				     void *data);
 
diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
index 4fcb84fd1f65..9ac893ae5f0d 100644
--- a/tools/perf/tests/pmu-events.c
+++ b/tools/perf/tests/pmu-events.c
@@ -546,6 +546,7 @@ static int __test_core_pmu_event_aliases(char *pmu_name, int *count)
 
 	pmu->events_table = table;
 	pmu_add_cpu_aliases_table(pmu, table);
+	pmu->cpu_aliases_added = true;
 
 	res = pmu_events_table__find_event(table, pmu, "bp_l1_btb_correct", NULL, NULL);
 	if (res != 0) {
@@ -586,6 +587,7 @@ static int __test_uncore_pmu_event_aliases(struct perf_pmu_test_pmu *test_pmu)
 		return -1;
 	pmu->events_table = events_table;
 	pmu_add_cpu_aliases_table(pmu, events_table);
+	pmu->cpu_aliases_added = true;
 	pmu_add_sys_aliases(pmu);
 
 	/* Count how many aliases we generated */
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 685903c1970b..b6a118226541 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -523,8 +523,9 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, int dirfd, const char *name
 	if (!pe) {
 		/* Update an event from sysfs with json data. */
 		if (pmu->events_table) {
-			pmu_events_table__find_event(pmu->events_table, pmu, name,
-						     update_alias, alias);
+			if (pmu_events_table__find_event(pmu->events_table, pmu, name,
+							 update_alias, alias) == 0)
+				pmu->loaded_json_aliases++;
 		}
 	}
 
@@ -548,6 +549,10 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, int dirfd, const char *name
 					 "%s=%s", term->config, term->val.str);
 	}
 	alias->str = strdup(newval);
+	if (!pe)
+		pmu->sysfs_aliases++;
+	else
+		pmu->loaded_json_aliases++;
 	list_add_tail(&alias->list, &pmu->aliases);
 	return 0;
 }
@@ -878,7 +883,11 @@ static void pmu_add_cpu_aliases(struct perf_pmu *pmu)
 	if (!pmu->events_table)
 		return;
 
+	if (pmu->cpu_aliases_added)
+		return;
+
 	pmu_add_cpu_aliases_table(pmu, pmu->events_table);
+	pmu->cpu_aliases_added = true;
 }
 
 static int pmu_add_sys_aliases_iter_fn(const struct pmu_event *pe,
@@ -990,7 +999,6 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char
 		pmu->id = pmu_id(name);
 	pmu->max_precise = pmu_max_precise(dirfd, pmu);
 	pmu->events_table = perf_pmu__find_events_table(pmu);
-	pmu_add_cpu_aliases(pmu);
 	pmu_add_sys_aliases(pmu);
 	list_add_tail(&pmu->list, pmus);
 
@@ -1368,6 +1376,7 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
 					     struct parse_events_term *term)
 {
+	struct perf_pmu_alias *alias;
 	char *name;
 
 	if (parse_events__is_hardcoded_term(term))
@@ -1388,7 +1397,18 @@ static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
 		return NULL;
 	}
 
-	return perf_pmu__find_alias(pmu, name);
+	alias = perf_pmu__find_alias(pmu, name);
+	if (alias || pmu->cpu_aliases_added)
+		return alias;
+
+	/* Alias doesn't exist, try to get it from the json events. */
+	if (pmu->events_table &&
+	    pmu_events_table__find_event(pmu->events_table, pmu, name,
+				         pmu_add_cpu_aliases_map_callback,
+				         pmu) == 0) {
+		alias = perf_pmu__find_alias(pmu, name);
+	}
+	return alias;
 }
 
 
@@ -1555,18 +1575,23 @@ bool perf_pmu__auto_merge_stats(const struct perf_pmu *pmu)
 	return !pmu->is_core || perf_pmus__num_core_pmus() == 1;
 }
 
-bool perf_pmu__have_event(const struct perf_pmu *pmu, const char *name)
+bool perf_pmu__have_event(struct perf_pmu *pmu, const char *name)
 {
-	return perf_pmu__find_alias(pmu, name) != NULL;
+	if (perf_pmu__find_alias(pmu, name) != NULL)
+		return true;
+	if (pmu->cpu_aliases_added || !pmu->events_table)
+		return false;
+	return pmu_events_table__find_event(pmu->events_table, pmu, name, NULL, NULL) == 0;
 }
 
-size_t perf_pmu__num_events(const struct perf_pmu *pmu)
+size_t perf_pmu__num_events(struct perf_pmu *pmu)
 {
-	struct list_head *list;
-	size_t nr = 0;
+	size_t nr = pmu->sysfs_aliases;
 
-	list_for_each(list, &pmu->aliases)
-		nr++;
+	if (pmu->cpu_aliases_added)
+		 nr += pmu->loaded_json_aliases;
+	else if (pmu->events_table)
+		nr += pmu_events_table__num_events(pmu->events_table, pmu) - pmu->loaded_json_aliases;
 
 	return pmu->selectable ? nr + 1 : nr;
 }
@@ -1604,7 +1629,7 @@ static char *format_alias(char *buf, int len, const struct perf_pmu *pmu,
 	return buf;
 }
 
-int perf_pmu__for_each_event(const struct perf_pmu *pmu, void *state, pmu_event_callback cb)
+int perf_pmu__for_each_event(struct perf_pmu *pmu, void *state, pmu_event_callback cb)
 {
 	char buf[1024];
 	struct perf_pmu_alias *event;
@@ -1613,6 +1638,7 @@ int perf_pmu__for_each_event(const struct perf_pmu *pmu, void *state, pmu_event_
 	};
 	int ret = 0;
 
+	pmu_add_cpu_aliases(pmu);
 	list_for_each_entry(event, &pmu->aliases, list) {
 		size_t buf_used;
 
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 6bf0fbde4e85..288d2908382a 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -118,6 +118,15 @@ struct perf_pmu {
 	 * @events_table: The events table for json events in pmu-events.c.
 	 */
 	const struct pmu_events_table *events_table;
+	/** @sysfs_aliases: Number of sysfs aliases loaded. */
+	uint32_t sysfs_aliases;
+	/** @sysfs_aliases: Number of json event aliases loaded. */
+	uint32_t loaded_json_aliases;
+	/**
+	 * @cpu_aliases_added: Have all json events table entries for the PMU
+	 * been added?
+	 */
+	bool cpu_aliases_added;
 	/** @caps_initialized: Has the list caps been initialized? */
 	bool caps_initialized;
 	/** @nr_caps: The length of the list caps. */
@@ -199,9 +208,9 @@ bool perf_pmu__has_format(const struct perf_pmu *pmu, const char *name);
 bool is_pmu_core(const char *name);
 bool perf_pmu__supports_legacy_cache(const struct perf_pmu *pmu);
 bool perf_pmu__auto_merge_stats(const struct perf_pmu *pmu);
-bool perf_pmu__have_event(const struct perf_pmu *pmu, const char *name);
-size_t perf_pmu__num_events(const struct perf_pmu *pmu);
-int perf_pmu__for_each_event(const struct perf_pmu *pmu, void *state, pmu_event_callback cb);
+bool perf_pmu__have_event(struct perf_pmu *pmu, const char *name);
+size_t perf_pmu__num_events(struct perf_pmu *pmu);
+int perf_pmu__for_each_event(struct perf_pmu *pmu, void *state, pmu_event_callback cb);
 bool pmu__name_match(const struct perf_pmu *pmu, const char *pmu_name);
 
 /**

From 88ed91848db2f631403f61987c1093b18042a8d0 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 23 Aug 2023 21:13:26 -0700
Subject: [PATCH 0668/1189] perf pmu: Scan type early to fail an invalid PMU
 quickly

Scan sysfs PMU's type early so that format and aliases aren't
attempted to be loaded if the PMU name is invalid.

This is the case for event_pmu tokens in parse-events.y where a wildcard
name is first assumed to be a PMU name.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230824041330.266337-15-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/pmu.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index b6a118226541..9e3b72d84168 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -957,12 +957,21 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char
 	if (!pmu)
 		return NULL;
 
-	INIT_LIST_HEAD(&pmu->format);
-	INIT_LIST_HEAD(&pmu->aliases);
-	INIT_LIST_HEAD(&pmu->caps);
 	pmu->name = strdup(name);
 	if (!pmu->name)
 		goto err;
+
+	/*
+	 * Read type early to fail fast if a lookup name isn't a PMU. Ensure
+	 * that type value is successfully assigned (return 1).
+	 */
+	if (perf_pmu__scan_file_at(pmu, dirfd, "type", "%u", &type) != 1)
+		goto err;
+
+	INIT_LIST_HEAD(&pmu->format);
+	INIT_LIST_HEAD(&pmu->aliases);
+	INIT_LIST_HEAD(&pmu->caps);
+
 	/*
 	 * The pmu data we store & need consists of the pmu
 	 * type value and format definitions. Load both right
@@ -982,10 +991,6 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char
 	pmu->is_core = is_pmu_core(name);
 	pmu->cpus = pmu_cpumask(dirfd, name, pmu->is_core);
 
-	/* Read type, and ensure that type value is successfully assigned (return 1) */
-	if (perf_pmu__scan_file_at(pmu, dirfd, "type", "%u", &type) != 1)
-		goto err;
-
 	alias_name = pmu_find_alias_name(name);
 	if (alias_name) {
 		pmu->alias_name = strdup(alias_name);

From 7b723dbb96e85a63a8f01e2b3fdfb76aa5d418a8 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 23 Aug 2023 21:13:27 -0700
Subject: [PATCH 0669/1189] perf pmu: Be lazy about loading event info files
 from sysfs

Event info is only needed when an event is parsed or when merging data
from an JSON and sysfs event. Be lazy in its loading to reduce file
accesses.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230824041330.266337-16-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/pmu.c | 128 +++++++++++++++++++++++++++---------------
 1 file changed, 83 insertions(+), 45 deletions(-)

diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 9e3b72d84168..493d3e59fd50 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -58,6 +58,11 @@ struct perf_pmu_alias {
 	struct list_head terms;
 	/** @list: List element of struct perf_pmu aliases. */
 	struct list_head list;
+	/**
+	 * @pmu_name: The name copied from the json struct pmu_event. This can
+	 * differ from the PMU name as it won't have suffixes.
+	 */
+	char *pmu_name;
 	/** @unit: Units for the event, such as bytes or cache lines. */
 	char unit[UNIT_MAX_LEN+1];
 	/** @scale: Value to scale read counter values by. */
@@ -79,11 +84,10 @@ struct perf_pmu_alias {
 	 * default.
 	 */
 	bool deprecated;
-	/**
-	 * @pmu_name: The name copied from the json struct pmu_event. This can
-	 * differ from the PMU name as it won't have suffixes.
-	 */
-	char *pmu_name;
+	/** @from_sysfs: Was the alias from sysfs or a json event? */
+	bool from_sysfs;
+	/** @info_loaded: Have the scale, unit and other values been read from disk? */
+	bool info_loaded;
 };
 
 /**
@@ -280,17 +284,21 @@ out:
 	return ret;
 }
 
-static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, int dirfd, const char *name)
+static int perf_pmu__parse_scale(struct perf_pmu *pmu, struct perf_pmu_alias *alias)
 {
 	struct stat st;
 	ssize_t sret;
+	size_t len;
 	char scale[128];
 	int fd, ret = -1;
 	char path[PATH_MAX];
 
-	scnprintf(path, PATH_MAX, "%s.scale", name);
+	len = perf_pmu__event_source_devices_scnprintf(path, sizeof(path));
+	if (!len)
+		return 0;
+	scnprintf(path + len, sizeof(path) - len, "%s/%s.scale", pmu->name, alias->name);
 
-	fd = openat(dirfd, path, O_RDONLY);
+	fd = open(path, O_RDONLY);
 	if (fd == -1)
 		return -1;
 
@@ -312,15 +320,20 @@ error:
 	return ret;
 }
 
-static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, int dirfd, const char *name)
+static int perf_pmu__parse_unit(struct perf_pmu *pmu, struct perf_pmu_alias *alias)
 {
 	char path[PATH_MAX];
+	size_t len;
 	ssize_t sret;
 	int fd;
 
-	scnprintf(path, PATH_MAX, "%s.unit", name);
 
-	fd = openat(dirfd, path, O_RDONLY);
+	len = perf_pmu__event_source_devices_scnprintf(path, sizeof(path));
+	if (!len)
+		return 0;
+	scnprintf(path + len, sizeof(path) - len, "%s/%s.unit", pmu->name, alias->name);
+
+	fd = open(path, O_RDONLY);
 	if (fd == -1)
 		return -1;
 
@@ -343,14 +356,18 @@ error:
 }
 
 static int
-perf_pmu__parse_per_pkg(struct perf_pmu_alias *alias, int dirfd, const char *name)
+perf_pmu__parse_per_pkg(struct perf_pmu *pmu, struct perf_pmu_alias *alias)
 {
 	char path[PATH_MAX];
+	size_t len;
 	int fd;
 
-	scnprintf(path, PATH_MAX, "%s.per-pkg", name);
+	len = perf_pmu__event_source_devices_scnprintf(path, sizeof(path));
+	if (!len)
+		return 0;
+	scnprintf(path + len, sizeof(path) - len, "%s/%s.per-pkg", pmu->name, alias->name);
 
-	fd = openat(dirfd, path, O_RDONLY);
+	fd = open(path, O_RDONLY);
 	if (fd == -1)
 		return -1;
 
@@ -360,15 +377,18 @@ perf_pmu__parse_per_pkg(struct perf_pmu_alias *alias, int dirfd, const char *nam
 	return 0;
 }
 
-static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias,
-				    int dirfd, const char *name)
+static int perf_pmu__parse_snapshot(struct perf_pmu *pmu, struct perf_pmu_alias *alias)
 {
 	char path[PATH_MAX];
+	size_t len;
 	int fd;
 
-	scnprintf(path, PATH_MAX, "%s.snapshot", name);
+	len = perf_pmu__event_source_devices_scnprintf(path, sizeof(path));
+	if (!len)
+		return 0;
+	scnprintf(path + len, sizeof(path) - len, "%s/%s.snapshot", pmu->name, alias->name);
 
-	fd = openat(dirfd, path, O_RDONLY);
+	fd = open(path, O_RDONLY);
 	if (fd == -1)
 		return -1;
 
@@ -429,32 +449,52 @@ static bool assign_str(const char *name, const char *field, char **old_str,
 	return true;
 }
 
+static void read_alias_info(struct perf_pmu *pmu, struct perf_pmu_alias *alias)
+{
+	if (!alias->from_sysfs || alias->info_loaded)
+		return;
+
+	/*
+	 * load unit name and scale if available
+	 */
+	perf_pmu__parse_unit(pmu, alias);
+	perf_pmu__parse_scale(pmu, alias);
+	perf_pmu__parse_per_pkg(pmu, alias);
+	perf_pmu__parse_snapshot(pmu, alias);
+}
+
+struct update_alias_data {
+	struct perf_pmu *pmu;
+	struct perf_pmu_alias *alias;
+};
+
 static int update_alias(const struct pmu_event *pe,
 			const struct pmu_events_table *table __maybe_unused,
 			void *vdata)
 {
-	struct perf_pmu_alias *alias = vdata;
+	struct update_alias_data *data = vdata;
 	int ret = 0;
 
-	assign_str(pe->name, "desc", &alias->desc, pe->desc);
-	assign_str(pe->name, "long_desc", &alias->long_desc, pe->long_desc);
-	assign_str(pe->name, "topic", &alias->topic, pe->topic);
-	alias->per_pkg = pe->perpkg;
-	if (assign_str(pe->name, "value", &alias->str, pe->event)) {
-		parse_events_terms__purge(&alias->terms);
-		ret = parse_events_terms(&alias->terms, pe->event, /*input=*/NULL);
+	read_alias_info(data->pmu, data->alias);
+	assign_str(pe->name, "desc", &data->alias->desc, pe->desc);
+	assign_str(pe->name, "long_desc", &data->alias->long_desc, pe->long_desc);
+	assign_str(pe->name, "topic", &data->alias->topic, pe->topic);
+	data->alias->per_pkg = pe->perpkg;
+	if (assign_str(pe->name, "value", &data->alias->str, pe->event)) {
+		parse_events_terms__purge(&data->alias->terms);
+		ret = parse_events_terms(&data->alias->terms, pe->event, /*input=*/NULL);
 	}
 	if (!ret && pe->unit) {
 		char *unit;
 
-		ret = perf_pmu__convert_scale(pe->unit, &unit, &alias->scale);
+		ret = perf_pmu__convert_scale(pe->unit, &unit, &data->alias->scale);
 		if (!ret)
-			snprintf(alias->unit, sizeof(alias->unit), "%s", unit);
+			snprintf(data->alias->unit, sizeof(data->alias->unit), "%s", unit);
 	}
 	return ret;
 }
 
-static int perf_pmu__new_alias(struct perf_pmu *pmu, int dirfd, const char *name,
+static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name,
 				const char *desc, const char *val, FILE *val_fd,
 				const struct pmu_event *pe)
 {
@@ -498,16 +538,6 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, int dirfd, const char *name
 	}
 
 	alias->name = strdup(name);
-	if (dirfd >= 0) {
-		/*
-		 * load unit name and scale if available
-		 */
-		perf_pmu__parse_unit(alias, dirfd, name);
-		perf_pmu__parse_scale(alias, dirfd, name);
-		perf_pmu__parse_per_pkg(alias, dirfd, name);
-		perf_pmu__parse_snapshot(alias, dirfd, name);
-	}
-
 	alias->desc = desc ? strdup(desc) : NULL;
 	alias->long_desc = long_desc ? strdup(long_desc) :
 				desc ? strdup(desc) : NULL;
@@ -522,9 +552,15 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, int dirfd, const char *name
 	}
 	if (!pe) {
 		/* Update an event from sysfs with json data. */
+		struct update_alias_data data = {
+			.pmu = pmu,
+			.alias = alias,
+		};
+
+		alias->from_sysfs = true;
 		if (pmu->events_table) {
 			if (pmu_events_table__find_event(pmu->events_table, pmu, name,
-							 update_alias, alias) == 0)
+							 update_alias, &data) == 0)
 				pmu->loaded_json_aliases++;
 		}
 	}
@@ -612,7 +648,7 @@ static int pmu_aliases_parse(struct perf_pmu *pmu, int dirfd)
 			continue;
 		}
 
-		if (perf_pmu__new_alias(pmu, dirfd, name, /*desc=*/ NULL,
+		if (perf_pmu__new_alias(pmu, name, /*desc=*/ NULL,
 					/*val=*/ NULL, file, /*pe=*/ NULL) < 0)
 			pr_debug("Cannot set up %s\n", name);
 		fclose(file);
@@ -865,7 +901,7 @@ static int pmu_add_cpu_aliases_map_callback(const struct pmu_event *pe,
 {
 	struct perf_pmu *pmu = vdata;
 
-	perf_pmu__new_alias(pmu, -1, pe->name, pe->desc, pe->event, /*val_fd=*/ NULL, pe);
+	perf_pmu__new_alias(pmu, pe->name, pe->desc, pe->event, /*val_fd=*/ NULL, pe);
 	return 0;
 }
 
@@ -901,7 +937,7 @@ static int pmu_add_sys_aliases_iter_fn(const struct pmu_event *pe,
 
 	if (!strcmp(pmu->id, pe->compat) &&
 	    pmu_uncore_alias_match(pe->pmu, pmu->name)) {
-		perf_pmu__new_alias(pmu, -1,
+		perf_pmu__new_alias(pmu,
 				pe->name,
 				pe->desc,
 				pe->event,
@@ -1417,11 +1453,13 @@ static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
 }
 
 
-static int check_info_data(struct perf_pmu_alias *alias,
+static int check_info_data(struct perf_pmu *pmu,
+			   struct perf_pmu_alias *alias,
 			   struct perf_pmu_info *info,
 			   struct parse_events_error *err,
 			   int column)
 {
+	read_alias_info(pmu, alias);
 	/*
 	 * Only one term in event definition can
 	 * define unit, scale and snapshot, fail
@@ -1491,7 +1529,7 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 			return ret;
 		}
 
-		ret = check_info_data(alias, info, err, term->err_term);
+		ret = check_info_data(pmu, alias, info, err, term->err_term);
 		if (ret)
 			return ret;
 

From 8d4b6d37ea7862d230ad2e1bd4c7d2ff5e9acd53 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 23 Aug 2023 21:13:28 -0700
Subject: [PATCH 0670/1189] perf pmu: Lazily load sysfs aliases

Don't load sysfs aliases for a PMU when the PMU is first created, defer
until an alias needs to be found. For the pmu-scan benchmark, average
core PMU scanning is reduced by 30.8%, and average PMU scanning by
12.6%.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230824041330.266337-17-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/pmu-events.c |  2 +
 tools/perf/util/pmu.c         | 81 ++++++++++++++++++-----------------
 tools/perf/util/pmu.h         |  2 +
 3 files changed, 46 insertions(+), 39 deletions(-)

diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
index 9ac893ae5f0d..3dc1ebee4d9f 100644
--- a/tools/perf/tests/pmu-events.c
+++ b/tools/perf/tests/pmu-events.c
@@ -547,6 +547,7 @@ static int __test_core_pmu_event_aliases(char *pmu_name, int *count)
 	pmu->events_table = table;
 	pmu_add_cpu_aliases_table(pmu, table);
 	pmu->cpu_aliases_added = true;
+	pmu->sysfs_aliases_loaded = true;
 
 	res = pmu_events_table__find_event(table, pmu, "bp_l1_btb_correct", NULL, NULL);
 	if (res != 0) {
@@ -588,6 +589,7 @@ static int __test_uncore_pmu_event_aliases(struct perf_pmu_test_pmu *test_pmu)
 	pmu->events_table = events_table;
 	pmu_add_cpu_aliases_table(pmu, events_table);
 	pmu->cpu_aliases_added = true;
+	pmu->sysfs_aliases_loaded = true;
 	pmu_add_sys_aliases(pmu);
 
 	/* Count how many aliases we generated */
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 493d3e59fd50..bb2ca29cd7bd 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -115,6 +115,8 @@ struct perf_pmu_format {
 	bool loaded;
 };
 
+static int pmu_aliases_parse(struct perf_pmu *pmu);
+
 static struct perf_pmu_format *perf_pmu__new_format(struct list_head *list, char *name)
 {
 	struct perf_pmu_format *format;
@@ -420,10 +422,15 @@ static void perf_pmu__del_aliases(struct perf_pmu *pmu)
 	}
 }
 
-static struct perf_pmu_alias *perf_pmu__find_alias(const struct perf_pmu *pmu, const char *name)
+static struct perf_pmu_alias *perf_pmu__find_alias(struct perf_pmu *pmu,
+						   const char *name,
+						   bool load)
 {
 	struct perf_pmu_alias *alias;
 
+	if (load && !pmu->sysfs_aliases_loaded)
+		pmu_aliases_parse(pmu);
+
 	list_for_each_entry(alias, &pmu->aliases, list) {
 		if (!strcasecmp(alias->name, name))
 			return alias;
@@ -505,7 +512,7 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name,
 	const char *long_desc = NULL, *topic = NULL, *unit = NULL, *pmu_name = NULL;
 	bool deprecated = false, perpkg = false;
 
-	if (perf_pmu__find_alias(pmu, name)) {
+	if (perf_pmu__find_alias(pmu, name, /*load=*/ false)) {
 		/* Alias was already created/loaded. */
 		return 0;
 	}
@@ -611,18 +618,33 @@ static inline bool pmu_alias_info_file(char *name)
 }
 
 /*
- * Process all the sysfs attributes located under the directory
- * specified in 'dir' parameter.
+ * Reading the pmu event aliases definition, which should be located at:
+ * /sys/bus/event_source/devices/<dev>/events as sysfs group attributes.
  */
-static int pmu_aliases_parse(struct perf_pmu *pmu, int dirfd)
+static int pmu_aliases_parse(struct perf_pmu *pmu)
 {
+	char path[PATH_MAX];
 	struct dirent *evt_ent;
 	DIR *event_dir;
-	int fd;
+	size_t len;
+	int fd, dir_fd;
 
-	event_dir = fdopendir(dirfd);
-	if (!event_dir)
+	len = perf_pmu__event_source_devices_scnprintf(path, sizeof(path));
+	if (!len)
+		return 0;
+	scnprintf(path + len, sizeof(path) - len, "%s/events", pmu->name);
+
+	dir_fd = open(path, O_DIRECTORY);
+	if (dir_fd == -1) {
+		pmu->sysfs_aliases_loaded = true;
+		return 0;
+	}
+
+	event_dir = fdopendir(dir_fd);
+	if (!event_dir){
+		close (dir_fd);
 		return -EINVAL;
+	}
 
 	while ((evt_ent = readdir(event_dir))) {
 		char *name = evt_ent->d_name;
@@ -637,7 +659,7 @@ static int pmu_aliases_parse(struct perf_pmu *pmu, int dirfd)
 		if (pmu_alias_info_file(name))
 			continue;
 
-		fd = openat(dirfd, name, O_RDONLY);
+		fd = openat(dir_fd, name, O_RDONLY);
 		if (fd == -1) {
 			pr_debug("Cannot open %s\n", name);
 			continue;
@@ -655,25 +677,8 @@ static int pmu_aliases_parse(struct perf_pmu *pmu, int dirfd)
 	}
 
 	closedir(event_dir);
-	return 0;
-}
-
-/*
- * Reading the pmu event aliases definition, which should be located at:
- * /sys/bus/event_source/devices/<dev>/events as sysfs group attributes.
- */
-static int pmu_aliases(struct perf_pmu *pmu, int dirfd, const char *name)
-{
-	int fd;
-
-	fd = perf_pmu__pathname_fd(dirfd, name, "events", O_DIRECTORY);
-	if (fd < 0)
-		return 0;
-
-	/* it'll close the fd */
-	if (pmu_aliases_parse(pmu, fd))
-		return -1;
-
+	close (dir_fd);
+	pmu->sysfs_aliases_loaded = true;
 	return 0;
 }
 
@@ -1017,13 +1022,6 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char
 		free(pmu);
 		return NULL;
 	}
-	/*
-	 * Check the aliases first to avoid unnecessary work.
-	 */
-	if (pmu_aliases(pmu, dirfd, name)) {
-		free(pmu);
-		return NULL;
-	}
 	pmu->is_core = is_pmu_core(name);
 	pmu->cpus = pmu_cpumask(dirfd, name, pmu->is_core);
 
@@ -1438,7 +1436,7 @@ static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
 		return NULL;
 	}
 
-	alias = perf_pmu__find_alias(pmu, name);
+	alias = perf_pmu__find_alias(pmu, name, /*load=*/ true);
 	if (alias || pmu->cpu_aliases_added)
 		return alias;
 
@@ -1447,7 +1445,7 @@ static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
 	    pmu_events_table__find_event(pmu->events_table, pmu, name,
 				         pmu_add_cpu_aliases_map_callback,
 				         pmu) == 0) {
-		alias = perf_pmu__find_alias(pmu, name);
+		alias = perf_pmu__find_alias(pmu, name, /*load=*/ false);
 	}
 	return alias;
 }
@@ -1620,7 +1618,7 @@ bool perf_pmu__auto_merge_stats(const struct perf_pmu *pmu)
 
 bool perf_pmu__have_event(struct perf_pmu *pmu, const char *name)
 {
-	if (perf_pmu__find_alias(pmu, name) != NULL)
+	if (perf_pmu__find_alias(pmu, name, /*load=*/ true) != NULL)
 		return true;
 	if (pmu->cpu_aliases_added || !pmu->events_table)
 		return false;
@@ -1629,7 +1627,12 @@ bool perf_pmu__have_event(struct perf_pmu *pmu, const char *name)
 
 size_t perf_pmu__num_events(struct perf_pmu *pmu)
 {
-	size_t nr = pmu->sysfs_aliases;
+	size_t nr;
+
+	if (!pmu->sysfs_aliases_loaded)
+		pmu_aliases_parse(pmu);
+
+	nr = pmu->sysfs_aliases;
 
 	if (pmu->cpu_aliases_added)
 		 nr += pmu->loaded_json_aliases;
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 288d2908382a..bae0de3ed7a5 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -122,6 +122,8 @@ struct perf_pmu {
 	uint32_t sysfs_aliases;
 	/** @sysfs_aliases: Number of json event aliases loaded. */
 	uint32_t loaded_json_aliases;
+	/** @sysfs_aliases_loaded: Are sysfs aliases loaded from disk? */
+	bool sysfs_aliases_loaded;
 	/**
 	 * @cpu_aliases_added: Have all json events table entries for the PMU
 	 * been added?

From f85d120c46e7e31e0516b15a9a11f6721150eb3b Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 23 Aug 2023 21:13:29 -0700
Subject: [PATCH 0671/1189] perf jevents: Sort strings in the big C string to
 reduce faults

Sort the strings within the big C string based on whether they were
for a metric and then by when they were added. This helps group
related strings and reduce minor faults by approximately 10 in 1740,
about 0.57%.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230824041330.266337-18-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/jevents.py | 31 +++++++++++++++++++++++--------
 1 file changed, 23 insertions(+), 8 deletions(-)

diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index 01335a452e70..e5bce57f5688 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -113,13 +113,24 @@ class BigCString:
   strings: Set[str]
   big_string: Sequence[str]
   offsets: Dict[str, int]
+  insert_number: int
+  insert_point: Dict[str, int]
+  metrics: Set[str]
 
   def __init__(self):
     self.strings = set()
+    self.insert_number = 0;
+    self.insert_point = {}
+    self.metrics = set()
 
-  def add(self, s: str) -> None:
+  def add(self, s: str, metric: bool) -> None:
     """Called to add to the big string."""
-    self.strings.add(s)
+    if s not in self.strings:
+      self.strings.add(s)
+      self.insert_point[s] = self.insert_number
+      self.insert_number += 1
+      if metric:
+        self.metrics.add(s)
 
   def compute(self) -> None:
     """Called once all strings are added to compute the string and offsets."""
@@ -160,8 +171,11 @@ class BigCString:
     self.big_string = []
     self.offsets = {}
 
+    def string_cmp_key(s: str) -> Tuple[bool, int, str]:
+      return (s in self.metrics, self.insert_point[s], s)
+
     # Emit all strings that aren't folded in a sorted manner.
-    for s in sorted(self.strings):
+    for s in sorted(self.strings, key=string_cmp_key):
       if s not in folded_strings:
         self.offsets[s] = big_string_offset
         self.big_string.append(f'/* offset={big_string_offset} */ "')
@@ -574,19 +588,20 @@ def preprocess_one_file(parents: Sequence[str], item: os.DirEntry) -> None:
       assert len(mgroup) > 1, parents
       description = f"{metricgroup_descriptions[mgroup]}\\000"
       mgroup = f"{mgroup}\\000"
-      _bcs.add(mgroup)
-      _bcs.add(description)
+      _bcs.add(mgroup, metric=True)
+      _bcs.add(description, metric=True)
       _metricgroups[mgroup] = description
     return
 
   topic = get_topic(item.name)
   for event in read_json_events(item.path, topic):
     pmu_name = f"{event.pmu}\\000"
-    _bcs.add(pmu_name)
     if event.name:
-      _bcs.add(event.build_c_string(metric=False))
+      _bcs.add(pmu_name, metric=False)
+      _bcs.add(event.build_c_string(metric=False), metric=False)
     if event.metric_name:
-      _bcs.add(event.build_c_string(metric=True))
+      _bcs.add(pmu_name, metric=True)
+      _bcs.add(event.build_c_string(metric=True), metric=True)
 
 def process_one_file(parents: Sequence[str], item: os.DirEntry) -> None:
   """Process a JSON file during the main walk."""

From 43803cb16f997794a256483f29beb68abef2fa9e Mon Sep 17 00:00:00 2001
From: Anup Sharma <anupnewsmail@gmail.com>
Date: Sun, 13 Aug 2023 03:06:27 +0530
Subject: [PATCH 0672/1189] perf scripts python: Add support for input args in
 gecko script

Refines the argument handling mechanism in the "gecko-report" script to
enable better compatibility and improved user experience.

The script now differentiates between scenarios where arguments are
provided for record and report cases where gecko.py arguments are
passed.

Signed-off-by: Anup Sharma <anupnewsmail@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/ZNf7W+EIrrCSHZN0@yoga
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/bin/gecko-report | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)
 mode change 100644 => 100755 tools/perf/scripts/python/bin/gecko-report

diff --git a/tools/perf/scripts/python/bin/gecko-report b/tools/perf/scripts/python/bin/gecko-report
old mode 100644
new mode 100755
index 0c12cc08f3ab..1867ec8d9757
--- a/tools/perf/scripts/python/bin/gecko-report
+++ b/tools/perf/scripts/python/bin/gecko-report
@@ -1,3 +1,7 @@
 #!/bin/bash
 # description: create firefox gecko profile json format from perf.data
-perf script "$@" -s "$PERF_EXEC_PATH"/scripts/python/gecko.py
+if [ "$*" = "-i -" ]; then
+perf script -s "$PERF_EXEC_PATH"/scripts/python/gecko.py
+else
+perf script -s "$PERF_EXEC_PATH"/scripts/python/gecko.py -- "$@"
+fi

From f208b2c6f984f9c8086205e826985ab4441ce2da Mon Sep 17 00:00:00 2001
From: Anup Sharma <anupnewsmail@gmail.com>
Date: Wed, 9 Aug 2023 18:51:22 +0530
Subject: [PATCH 0673/1189] perf scripts python gecko: Launch the profiler UI
 on the default browser with the appropriate URL

All required libraries have been imported and make sure that none of
them are external dependencies. To achieve this, created a virt env and
verified.

Modified usage information and added combined command.

Modified the main() function to read the --save-only command-line option
and set the output_file variable accordingly.

Modified the trace_end() function to check for the output_file variable.
If it is set, the profiler data is saved to a local file in Gecko
Profile format, or the profiler.firefox.com is opened on the default
browser.

Included trace_begin() to initialize the Firefox Profiler and launch the
default browser to display the profiler.firefox.com.

Added a new function launchFirefox() to start a local server and launch
the profiler UI on the default browser with the appropriate URL.

Created the "CORSRequestHandler" class to enable Cross-Origin Resource
Sharing.

Summary:

This integration now includes a exiting feature to conveniently host the
Gecko Profile data on a local server and open it directly in the default
web browser.

This means that users can now effortlessly visualize and analyze the
profiler results with just a single click.

The addition of the --save-only command-line option allows users to save
the profiler output to a local file in Gecko Profile format, but the
real highlight lies in the capability to seamlessly launch a local
server, making the data accessible to Firefox Profiler via a web
browser.

In addition, it's important to highlight that all data are hosted
locally, eliminating any concerns about data privacy rules and
regulations.

Signed-off-by: Anup Sharma <anupnewsmail@gmail.com>
Tested-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/ZNOS0vo58DnVLpD8@yoga
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/gecko.py | 70 +++++++++++++++++++++++++++---
 1 file changed, 63 insertions(+), 7 deletions(-)

diff --git a/tools/perf/scripts/python/gecko.py b/tools/perf/scripts/python/gecko.py
index 278c3aed282a..bc5a72f94bfa 100644
--- a/tools/perf/scripts/python/gecko.py
+++ b/tools/perf/scripts/python/gecko.py
@@ -1,4 +1,4 @@
-# firefox-gecko-converter.py - Convert perf record output to Firefox's gecko profile format
+# gecko.py - Convert perf record output to Firefox's gecko profile format
 # SPDX-License-Identifier: GPL-2.0
 #
 # The script converts perf.data to Gecko Profile Format,
@@ -7,14 +7,26 @@
 # Usage:
 #
 #     perf record -a -g -F 99 sleep 60
-#     perf script report gecko > output.json
+#     perf script report gecko
+#
+# Combined:
+#
+#     perf script gecko -F 99 -a sleep 60
 
 import os
 import sys
+import time
 import json
+import string
+import random
 import argparse
+import threading
+import webbrowser
+import urllib.parse
+from os import system
 from functools import reduce
 from dataclasses import dataclass, field
+from http.server import HTTPServer, SimpleHTTPRequestHandler, test
 from typing import List, Dict, Optional, NamedTuple, Set, Tuple, Any
 
 # Add the Perf-Trace-Util library to the Python path
@@ -40,9 +52,15 @@ CATEGORIES = None
 # The product name is used by the profiler UI to show the Operating system and Processor.
 PRODUCT = os.popen('uname -op').read().strip()
 
+# store the output file
+output_file = None
+
 # Here key = tid, value = Thread
 tid_to_thread = dict()
 
+# The HTTP server is used to serve the profile to the profiler UI.
+http_server_thread = None
+
 # The category index is used by the profiler UI to show the color of the flame graph.
 USER_CATEGORY_INDEX = 0
 KERNEL_CATEGORY_INDEX = 1
@@ -278,9 +296,19 @@ def process_event(param_dict: Dict) -> None:
 		tid_to_thread[tid] = thread
 	thread._add_sample(comm=comm, stack=stack, time_ms=time_stamp)
 
+def trace_begin() -> None:
+	global output_file
+	if (output_file is None):
+		print("Staring Firefox Profiler on your default browser...")
+		global http_server_thread
+		http_server_thread = threading.Thread(target=test, args=(CORSRequestHandler, HTTPServer,))
+		http_server_thread.daemon = True
+		http_server_thread.start()
+
 # Trace_end runs at the end and will be used to aggregate
 # the data into the final json object and print it out to stdout.
 def trace_end() -> None:
+	global output_file
 	threads = [thread._to_json_dict() for thread in tid_to_thread.values()]
 
 	# Schema: https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L305
@@ -305,22 +333,50 @@ def trace_end() -> None:
 		"processes": [],
 		"pausedRanges": [],
 	}
-	json.dump(gecko_profile_with_meta, sys.stdout, indent=2)
+	# launch the profiler on local host if not specified --save-only args, otherwise print to file
+	if (output_file is None):
+		output_file = 'gecko_profile.json'
+		with open(output_file, 'w') as f:
+			json.dump(gecko_profile_with_meta, f, indent=2)
+		launchFirefox(output_file)
+		time.sleep(1)
+		print(f'[ perf gecko: Captured and wrote into {output_file} ]')
+	else:
+		print(f'[ perf gecko: Captured and wrote into {output_file} ]')
+		with open(output_file, 'w') as f:
+			json.dump(gecko_profile_with_meta, f, indent=2)
+
+# Used to enable Cross-Origin Resource Sharing (CORS) for requests coming from 'https://profiler.firefox.com', allowing it to access resources from this server.
+class CORSRequestHandler(SimpleHTTPRequestHandler):
+	def end_headers (self):
+		self.send_header('Access-Control-Allow-Origin', 'https://profiler.firefox.com')
+		SimpleHTTPRequestHandler.end_headers(self)
+
+# start a local server to serve the gecko_profile.json file to the profiler.firefox.com
+def launchFirefox(file):
+	safe_string = urllib.parse.quote_plus(f'http://localhost:8000/{file}')
+	url = 'https://profiler.firefox.com/from-url/' + safe_string
+	webbrowser.open(f'{url}')
 
 def main() -> None:
+	global output_file
 	global CATEGORIES
-	parser = argparse.ArgumentParser(description="Convert perf.data to Firefox\'s Gecko Profile format")
+	parser = argparse.ArgumentParser(description="Convert perf.data to Firefox\'s Gecko Profile format which can be uploaded to profiler.firefox.com for visualization")
 
 	# Add the command-line options
 	# Colors must be defined according to this:
 	# https://github.com/firefox-devtools/profiler/blob/50124adbfa488adba6e2674a8f2618cf34b59cd2/res/css/categories.css
-	parser.add_argument('--user-color', default='yellow', help='Color for the User category')
-	parser.add_argument('--kernel-color', default='orange', help='Color for the Kernel category')
+	parser.add_argument('--user-color', default='yellow', help='Color for the User category', choices=['yellow', 'blue', 'purple', 'green', 'orange', 'red', 'grey', 'magenta'])
+	parser.add_argument('--kernel-color', default='orange', help='Color for the Kernel category', choices=['yellow', 'blue', 'purple', 'green', 'orange', 'red', 'grey', 'magenta'])
+	# If --save-only is specified, the output will be saved to a file instead of opening Firefox's profiler directly.
+	parser.add_argument('--save-only', help='Save the output to a file instead of opening Firefox\'s profiler')
+
 	# Parse the command-line arguments
 	args = parser.parse_args()
 	# Access the values provided by the user
 	user_color = args.user_color
 	kernel_color = args.kernel_color
+	output_file = args.save_only
 
 	CATEGORIES = [
 		{
@@ -336,4 +392,4 @@ def main() -> None:
 	]
 
 if __name__ == '__main__':
-    main()
+	main()

From eeb6b12992c4a348af6773e50084f981dc3dda76 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 24 Aug 2023 11:32:12 -0700
Subject: [PATCH 0674/1189] perf jevents: Don't append Unit to desc

Unit with the PMU name is appended to desc in jevents.py, but on
hybrid platforms it causes the desc to differ from the regular
non-hybrid system with a PMU of 'cpu'. Having differing descs means
the events don't deduplicate. To make the perf list output not differ,
append the Unit on again in the perf list printing code.

On x86 reduces the binary size by 409,600 bytes or about 4%. Update
pmu-events test expectations to match the differently generated
pmu-events.c code.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230824183212.374787-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-list.c        | 13 ++++++++++++-
 tools/perf/pmu-events/jevents.py |  7 -------
 tools/perf/tests/pmu-events.c    | 22 +++++++++++-----------
 3 files changed, 23 insertions(+), 19 deletions(-)

diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index 7fec2cca759f..d8b9f606e734 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -145,9 +145,20 @@ static void default_print_event(void *ps, const char *pmu_name, const char *topi
 		putchar('\n');
 
 	if (desc && print_state->desc) {
+		char *desc_with_unit = NULL;
+		int desc_len = -1;
+
+		if (pmu_name && strcmp(pmu_name, "cpu")) {
+			desc_len = strlen(desc);
+			desc_len = asprintf(&desc_with_unit,
+					    desc[desc_len - 1] != '.'
+					      ? "%s. Unit: %s" : "%s Unit: %s",
+					    desc, pmu_name);
+		}
 		printf("%*s", 8, "[");
-		wordwrap(desc, 8, pager_get_columns(), 0);
+		wordwrap(desc_len > 0 ? desc_with_unit : desc, 8, pager_get_columns(), 0);
 		printf("]\n");
+		free(desc_with_unit);
 	}
 	long_desc = long_desc ?: desc;
 	if (long_desc && print_state->long_desc) {
diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index e5bce57f5688..712f80d7d071 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -357,13 +357,6 @@ class JsonEvent:
       self.desc += extra_desc
     if self.long_desc and extra_desc:
       self.long_desc += extra_desc
-    if self.pmu and self.pmu != 'cpu':
-      if not self.desc:
-        self.desc = 'Unit: ' + self.pmu
-      else:
-        if not self.desc.endswith('. '):
-          self.desc += '. '
-      self.desc += 'Unit: ' + self.pmu
     if arch_std:
       if arch_std.lower() in _arch_std_events:
         event = _arch_std_events[arch_std.lower()].event
diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
index 3dc1ebee4d9f..28c8789c4305 100644
--- a/tools/perf/tests/pmu-events.c
+++ b/tools/perf/tests/pmu-events.c
@@ -129,7 +129,7 @@ static const struct perf_pmu_test_event uncore_hisi_ddrc_flux_wcmd = {
 	.event = {
 		.name = "uncore_hisi_ddrc.flux_wcmd",
 		.event = "event=0x2",
-		.desc = "DDRC write commands. Unit: hisi_sccl,ddrc",
+		.desc = "DDRC write commands",
 		.topic = "uncore",
 		.long_desc = "DDRC write commands",
 		.pmu = "hisi_sccl,ddrc",
@@ -143,7 +143,7 @@ static const struct perf_pmu_test_event unc_cbo_xsnp_response_miss_eviction = {
 	.event = {
 		.name = "unc_cbo_xsnp_response.miss_eviction",
 		.event = "event=0x22,umask=0x81",
-		.desc = "A cross-core snoop resulted from L3 Eviction which misses in some processor core. Unit: uncore_cbox",
+		.desc = "A cross-core snoop resulted from L3 Eviction which misses in some processor core",
 		.topic = "uncore",
 		.long_desc = "A cross-core snoop resulted from L3 Eviction which misses in some processor core",
 		.pmu = "uncore_cbox",
@@ -157,7 +157,7 @@ static const struct perf_pmu_test_event uncore_hyphen = {
 	.event = {
 		.name = "event-hyphen",
 		.event = "event=0xe0,umask=0x00",
-		.desc = "UNC_CBO_HYPHEN. Unit: uncore_cbox",
+		.desc = "UNC_CBO_HYPHEN",
 		.topic = "uncore",
 		.long_desc = "UNC_CBO_HYPHEN",
 		.pmu = "uncore_cbox",
@@ -171,7 +171,7 @@ static const struct perf_pmu_test_event uncore_two_hyph = {
 	.event = {
 		.name = "event-two-hyph",
 		.event = "event=0xc0,umask=0x00",
-		.desc = "UNC_CBO_TWO_HYPH. Unit: uncore_cbox",
+		.desc = "UNC_CBO_TWO_HYPH",
 		.topic = "uncore",
 		.long_desc = "UNC_CBO_TWO_HYPH",
 		.pmu = "uncore_cbox",
@@ -185,7 +185,7 @@ static const struct perf_pmu_test_event uncore_hisi_l3c_rd_hit_cpipe = {
 	.event = {
 		.name = "uncore_hisi_l3c.rd_hit_cpipe",
 		.event = "event=0x7",
-		.desc = "Total read hits. Unit: hisi_sccl,l3c",
+		.desc = "Total read hits",
 		.topic = "uncore",
 		.long_desc = "Total read hits",
 		.pmu = "hisi_sccl,l3c",
@@ -199,7 +199,7 @@ static const struct perf_pmu_test_event uncore_imc_free_running_cache_miss = {
 	.event = {
 		.name = "uncore_imc_free_running.cache_miss",
 		.event = "event=0x12",
-		.desc = "Total cache misses. Unit: uncore_imc_free_running",
+		.desc = "Total cache misses",
 		.topic = "uncore",
 		.long_desc = "Total cache misses",
 		.pmu = "uncore_imc_free_running",
@@ -213,7 +213,7 @@ static const struct perf_pmu_test_event uncore_imc_cache_hits = {
 	.event = {
 		.name = "uncore_imc.cache_hits",
 		.event = "event=0x34",
-		.desc = "Total cache hits. Unit: uncore_imc",
+		.desc = "Total cache hits",
 		.topic = "uncore",
 		.long_desc = "Total cache hits",
 		.pmu = "uncore_imc",
@@ -238,13 +238,13 @@ static const struct perf_pmu_test_event sys_ddr_pmu_write_cycles = {
 	.event = {
 		.name = "sys_ddr_pmu.write_cycles",
 		.event = "event=0x2b",
-		.desc = "ddr write-cycles event. Unit: uncore_sys_ddr_pmu",
+		.desc = "ddr write-cycles event",
 		.topic = "uncore",
 		.pmu = "uncore_sys_ddr_pmu",
 		.compat = "v8",
 	},
 	.alias_str = "event=0x2b",
-	.alias_long_desc = "ddr write-cycles event. Unit: uncore_sys_ddr_pmu",
+	.alias_long_desc = "ddr write-cycles event",
 	.matching_pmu = "uncore_sys_ddr_pmu",
 };
 
@@ -252,13 +252,13 @@ static const struct perf_pmu_test_event sys_ccn_pmu_read_cycles = {
 	.event = {
 		.name = "sys_ccn_pmu.read_cycles",
 		.event = "config=0x2c",
-		.desc = "ccn read-cycles event. Unit: uncore_sys_ccn_pmu",
+		.desc = "ccn read-cycles event",
 		.topic = "uncore",
 		.pmu = "uncore_sys_ccn_pmu",
 		.compat = "0x01",
 	},
 	.alias_str = "config=0x2c",
-	.alias_long_desc = "ccn read-cycles event. Unit: uncore_sys_ccn_pmu",
+	.alias_long_desc = "ccn read-cycles event",
 	.matching_pmu = "uncore_sys_ccn_pmu",
 };
 

From 73c7881b50667f4f8322c6e1bb51624f0f4085a8 Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Tue, 22 Aug 2023 08:48:17 +0200
Subject: [PATCH 0675/1189] scsi: xen-scsifront: shost_priv() can never return
 NULL

There is no need to check whether shost_priv() returns a non-NULL value, as
the pointer returned is just an offset to the passed in parameter.

While at it replace an open coded shost_priv() instance.

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Juergen Gross <jgross@suse.com>
Link: https://lore.kernel.org/r/20230822064817.27257-1-jgross@suse.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/xen-scsifront.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/scsi/xen-scsifront.c b/drivers/scsi/xen-scsifront.c
index caae61aa2afe..9ec55ddc1204 100644
--- a/drivers/scsi/xen-scsifront.c
+++ b/drivers/scsi/xen-scsifront.c
@@ -743,7 +743,7 @@ static int scsifront_sdev_configure(struct scsi_device *sdev)
 	if (info->host_active == STATE_ERROR)
 		return -EIO;
 
-	if (info && current == info->curr) {
+	if (current == info->curr) {
 		err = xenbus_printf(XBT_NIL, info->dev->nodename,
 			      info->dev_state_path, "%d", XenbusStateConnected);
 		if (err) {
@@ -761,7 +761,7 @@ static void scsifront_sdev_destroy(struct scsi_device *sdev)
 	struct vscsifrnt_info *info = shost_priv(sdev->host);
 	int err;
 
-	if (info && current == info->curr) {
+	if (current == info->curr) {
 		err = xenbus_printf(XBT_NIL, info->dev->nodename,
 			      info->dev_state_path, "%d", XenbusStateClosed);
 		if (err)
@@ -903,7 +903,7 @@ static int scsifront_probe(struct xenbus_device *dev,
 		xenbus_dev_fatal(dev, err, "fail to allocate scsi host");
 		return err;
 	}
-	info = (struct vscsifrnt_info *)host->hostdata;
+	info = shost_priv(host);
 
 	dev_set_drvdata(&dev->dev, info);
 	info->dev = dev;

From 11443b539e9ea6c1a4564d100cba02cc2e162f68 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Tue, 22 Aug 2023 22:33:38 +0800
Subject: [PATCH 0676/1189] scsi: qedf: Remove unused declaration

This declaration was never implemented, remove it.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Link: https://lore.kernel.org/r/20230822143338.19120-1-yuehaibing@huawei.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qedf/qedf.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/scsi/qedf/qedf.h b/drivers/scsi/qedf/qedf.h
index c5c0bbdafc4e..1619cc33034f 100644
--- a/drivers/scsi/qedf/qedf.h
+++ b/drivers/scsi/qedf/qedf.h
@@ -548,7 +548,6 @@ extern void qedf_get_generic_tlv_data(void *dev, struct qed_generic_tlvs *data);
 extern void qedf_wq_grcdump(struct work_struct *work);
 void qedf_stag_change_work(struct work_struct *work);
 void qedf_ctx_soft_reset(struct fc_lport *lport);
-extern void qedf_board_disable_work(struct work_struct *work);
 extern void qedf_schedule_hw_err_handler(void *dev,
 		enum qed_hw_err_type err_type);
 

From e1a87e29fbc8ff3507e16df312d52190efa5963d Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Tue, 22 Aug 2023 22:33:38 +0800
Subject: [PATCH 0677/1189] scsi: qedi: Remove unused declarations

These declarations were never implemented, remove them.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Link: https://lore.kernel.org/r/20230822143338.19120-1-yuehaibing@huawei.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qedi/qedi_gbl.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/scsi/qedi/qedi_gbl.h b/drivers/scsi/qedi/qedi_gbl.h
index 0e316cc24b19..772218445a56 100644
--- a/drivers/scsi/qedi/qedi_gbl.h
+++ b/drivers/scsi/qedi/qedi_gbl.h
@@ -67,8 +67,6 @@ void qedi_trace_io(struct qedi_ctx *qedi, struct iscsi_task *task,
 int qedi_alloc_id(struct qedi_portid_tbl *id_tbl, u16 id);
 u16 qedi_alloc_new_id(struct qedi_portid_tbl *id_tbl);
 void qedi_free_id(struct qedi_portid_tbl *id_tbl, u16 id);
-int qedi_create_sysfs_ctx_attr(struct qedi_ctx *qedi);
-void qedi_remove_sysfs_ctx_attr(struct qedi_ctx *qedi);
 void qedi_clearsq(struct qedi_ctx *qedi,
 		  struct qedi_conn *qedi_conn,
 		  struct iscsi_task *task);

From 79519528a180c64a90863db2ce70887de6c49d16 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Tue, 22 Aug 2023 08:30:41 -0700
Subject: [PATCH 0678/1189] scsi: core: Improve type safety of
 scsi_rescan_device()

Most callers of scsi_rescan_device() have the scsi_device pointer readily
available. Pass a struct scsi_device pointer to scsi_rescan_device()
instead of a struct device pointer. This change prevents that a pointer to
another struct device would be passed accidentally to scsi_rescan_device().

Remove the scsi_rescan_device() declaration from the scsi_priv.h header
file since it duplicates the declaration in <scsi/scsi_host.h>.

Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Cc: Mike Christie <michael.christie@oracle.com>
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20230822153043.4046244-1-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ata/libata-scsi.c             | 2 +-
 drivers/scsi/aacraid/commsup.c        | 2 +-
 drivers/scsi/mvumi.c                  | 2 +-
 drivers/scsi/scsi_lib.c               | 2 +-
 drivers/scsi/scsi_priv.h              | 1 -
 drivers/scsi/scsi_scan.c              | 4 ++--
 drivers/scsi/scsi_sysfs.c             | 4 ++--
 drivers/scsi/smartpqi/smartpqi_init.c | 2 +-
 drivers/scsi/storvsc_drv.c            | 2 +-
 drivers/scsi/virtio_scsi.c            | 2 +-
 include/scsi/scsi_host.h              | 2 +-
 11 files changed, 12 insertions(+), 13 deletions(-)

diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 370d18aca71e..f5c36c8c243a 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -4884,7 +4884,7 @@ void ata_scsi_dev_rescan(struct work_struct *work)
 			}
 
 			spin_unlock_irqrestore(ap->lock, flags);
-			scsi_rescan_device(&(sdev->sdev_gendev));
+			scsi_rescan_device(sdev);
 			scsi_device_put(sdev);
 			spin_lock_irqsave(ap->lock, flags);
 		}
diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index 3f062e4013ab..013a9a334972 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -1451,7 +1451,7 @@ retry_next:
 #endif
 				break;
 			}
-			scsi_rescan_device(&device->sdev_gendev);
+			scsi_rescan_device(device);
 			break;
 
 		default:
diff --git a/drivers/scsi/mvumi.c b/drivers/scsi/mvumi.c
index 97f9d2fa6429..d9d366ec17dc 100644
--- a/drivers/scsi/mvumi.c
+++ b/drivers/scsi/mvumi.c
@@ -1500,7 +1500,7 @@ static void mvumi_rescan_devices(struct mvumi_hba *mhba, int id)
 
 	sdev = scsi_device_lookup(mhba->shost, 0, id, 0);
 	if (sdev) {
-		scsi_rescan_device(&sdev->sdev_gendev);
+		scsi_rescan_device(sdev);
 		scsi_device_put(sdev);
 	}
 }
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index ad9afae49544..ca5eb058d5c7 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -2458,7 +2458,7 @@ static void scsi_evt_emit(struct scsi_device *sdev, struct scsi_event *evt)
 		envp[idx++] = "SDEV_MEDIA_CHANGE=1";
 		break;
 	case SDEV_EVT_INQUIRY_CHANGE_REPORTED:
-		scsi_rescan_device(&sdev->sdev_gendev);
+		scsi_rescan_device(sdev);
 		envp[idx++] = "SDEV_UA=INQUIRY_DATA_HAS_CHANGED";
 		break;
 	case SDEV_EVT_CAPACITY_CHANGE_REPORTED:
diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h
index 118855576ca8..3f0dfb97db6b 100644
--- a/drivers/scsi/scsi_priv.h
+++ b/drivers/scsi/scsi_priv.h
@@ -137,7 +137,6 @@ extern int scsi_complete_async_scans(void);
 extern int scsi_scan_host_selected(struct Scsi_Host *, unsigned int,
 				   unsigned int, u64, enum scsi_scan_mode);
 extern void scsi_forget_host(struct Scsi_Host *);
-extern void scsi_rescan_device(struct device *);
 
 /* scsi_sysctl.c */
 #ifdef CONFIG_SYSCTL
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index aa13feb17c62..52014b2d39e1 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -1619,9 +1619,9 @@ int scsi_add_device(struct Scsi_Host *host, uint channel,
 }
 EXPORT_SYMBOL(scsi_add_device);
 
-void scsi_rescan_device(struct device *dev)
+void scsi_rescan_device(struct scsi_device *sdev)
 {
-	struct scsi_device *sdev = to_scsi_device(dev);
+	struct device *dev = &sdev->sdev_gendev;
 
 	device_lock(dev);
 
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index 60317676e45f..24f6eefb6803 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -747,7 +747,7 @@ static ssize_t
 store_rescan_field (struct device *dev, struct device_attribute *attr,
 		    const char *buf, size_t count)
 {
-	scsi_rescan_device(dev);
+	scsi_rescan_device(to_scsi_device(dev));
 	return count;
 }
 static DEVICE_ATTR(rescan, S_IWUSR, NULL, store_rescan_field);
@@ -840,7 +840,7 @@ store_state_field(struct device *dev, struct device_attribute *attr,
 		 * waiting for pending I/O to finish.
 		 */
 		blk_mq_run_hw_queues(sdev->request_queue, true);
-		scsi_rescan_device(dev);
+		scsi_rescan_device(sdev);
 	}
 
 	return ret == 0 ? count : -EINVAL;
diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index 6aaaa7ebca37..ed694d939964 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -2257,7 +2257,7 @@ static void pqi_update_device_list(struct pqi_ctrl_info *ctrl_info,
 			device->advertised_queue_depth = device->queue_depth;
 			scsi_change_queue_depth(device->sdev, device->advertised_queue_depth);
 			if (device->rescan) {
-				scsi_rescan_device(&device->sdev->sdev_gendev);
+				scsi_rescan_device(device->sdev);
 				device->rescan = false;
 			}
 		}
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 659196a2f63a..6bfd88495edb 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -470,7 +470,7 @@ static void storvsc_device_scan(struct work_struct *work)
 	sdev = scsi_device_lookup(wrk->host, 0, wrk->tgt_id, wrk->lun);
 	if (!sdev)
 		goto done;
-	scsi_rescan_device(&sdev->sdev_gendev);
+	scsi_rescan_device(sdev);
 	scsi_device_put(sdev);
 
 done:
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index bd5633667d01..9d1bdcdc1331 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -325,7 +325,7 @@ static void virtscsi_handle_param_change(struct virtio_scsi *vscsi,
 	/* Handle "Parameters changed", "Mode parameters changed", and
 	   "Capacity data has changed".  */
 	if (asc == 0x2a && (ascq == 0x00 || ascq == 0x01 || ascq == 0x09))
-		scsi_rescan_device(&sdev->sdev_gendev);
+		scsi_rescan_device(sdev);
 
 	scsi_device_put(sdev);
 }
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index a2b8d30c4c80..49f768d0ff37 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -764,7 +764,7 @@ scsi_template_proc_dir(const struct scsi_host_template *sht);
 #define scsi_template_proc_dir(sht) NULL
 #endif
 extern void scsi_scan_host(struct Scsi_Host *);
-extern void scsi_rescan_device(struct device *);
+extern void scsi_rescan_device(struct scsi_device *);
 extern void scsi_remove_host(struct Scsi_Host *);
 extern struct Scsi_Host *scsi_host_get(struct Scsi_Host *);
 extern int scsi_host_busy(struct Scsi_Host *shost);

From 90f359c1aa4ace0fb5f03796a7ee97c2ad2e42cc Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Tue, 22 Aug 2023 09:38:10 -0700
Subject: [PATCH 0679/1189] scsi: core: Report error list information in
 debugfs

Provide information in debugfs about SCSI error handling to make it easier
to debug the SCSI error handler. Additionally, report the maximum number of
retries in debugfs (.allowed).

Reviewed-by: John Garry <john.g.garry@oracle.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Damien Le Moal <damien.lemoal@opensource.wdc.com>
Cc: Mike Christie <michael.christie@oracle.com>
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20230822163811.219569-1-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_debugfs.c | 26 +++++++++++++++++++++++---
 1 file changed, 23 insertions(+), 3 deletions(-)

diff --git a/drivers/scsi/scsi_debugfs.c b/drivers/scsi/scsi_debugfs.c
index 217b70c678c3..f795848b316c 100644
--- a/drivers/scsi/scsi_debugfs.c
+++ b/drivers/scsi/scsi_debugfs.c
@@ -3,6 +3,7 @@
 #include <linux/seq_file.h>
 #include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_dbg.h>
+#include <scsi/scsi_host.h>
 #include "scsi_debugfs.h"
 
 #define SCSI_CMD_FLAG_NAME(name)[const_ilog2(SCMD_##name)] = #name
@@ -33,14 +34,33 @@ static int scsi_flags_show(struct seq_file *m, const unsigned long flags,
 
 void scsi_show_rq(struct seq_file *m, struct request *rq)
 {
-	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
+	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq), *cmd2;
+	struct Scsi_Host *shost = cmd->device->host;
 	int alloc_ms = jiffies_to_msecs(jiffies - cmd->jiffies_at_alloc);
 	int timeout_ms = jiffies_to_msecs(rq->timeout);
+	const char *list_info = NULL;
 	char buf[80] = "(?)";
 
+	spin_lock_irq(shost->host_lock);
+	list_for_each_entry(cmd2, &shost->eh_abort_list, eh_entry) {
+		if (cmd == cmd2) {
+			list_info = "on eh_abort_list";
+			goto unlock;
+		}
+	}
+	list_for_each_entry(cmd2, &shost->eh_cmd_q, eh_entry) {
+		if (cmd == cmd2) {
+			list_info = "on eh_cmd_q";
+			goto unlock;
+		}
+	}
+unlock:
+	spin_unlock_irq(shost->host_lock);
+
 	__scsi_format_command(buf, sizeof(buf), cmd->cmnd, cmd->cmd_len);
-	seq_printf(m, ", .cmd=%s, .retries=%d, .result = %#x, .flags=", buf,
-		   cmd->retries, cmd->result);
+	seq_printf(m, ", .cmd=%s, .retries=%d, .allowed=%d, .result = %#x, %s%s.flags=",
+		   buf, cmd->retries, cmd->allowed, cmd->result,
+		   list_info ? : "", list_info ? ", " : "");
 	scsi_flags_show(m, cmd->flags, scsi_cmd_flags,
 			ARRAY_SIZE(scsi_cmd_flags));
 	seq_printf(m, ", .timeout=%d.%03d, allocated %d.%03d s ago",

From 9604eea5bd3ae1fa3c098294f4fc29ad687141ea Mon Sep 17 00:00:00 2001
From: John Meneghini <jmeneghi@redhat.com>
Date: Tue, 22 Aug 2023 14:14:12 -0400
Subject: [PATCH 0680/1189] scsi: st: Add third party poweron reset handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Many tape devices will automatically rewind following a poweron/reset.
This can result in data loss as other operations in the driver can write to
the tape when the position is unknown. E.g. MTEOM can write a filemark at
the beginning of the tape. This patch adds code to detect poweron/reset
unit attentions and prevents the driver from writing to the tape when the
position could be unknown.

Customer reported problem description:

We have experienced an issue with the SCSI tape driver (st) which has led
to data loss for us on two separate occasions in production, as well as in
a third case in which we were able to reproduce the failure in our test
environment.

The tape device involved is an Amazon Tape Gateway, a virtual tape library
(VTL) appliance which presents as a series of iSCSI targets (multiple tape
drives and a changer) and is backed by storage in Amazon S3. The problem is
a general one and not limited to any particular SCSI transport or tape
device, though the nature of both iSCSI and the VTL make data loss somewhat
more likely with this combination than with a physical tape drive.

The observed behavior occurs when an error causes the VTL tape gateway
process (on the appliance) to crash and restart. This interrupts the iSCSI
TCP connections and, when it occurs during a write, causes the write to
fail with EIO. However, we then find that the virtual tape in question is
now completely blank. We raised this issue with AWS support, thinking this
must be a bug in the VTL appliance, but that turns out not to be the case.

Per AWS support, when the gateway crashes in this manner, its notion of the
current tape position is reset to the beginning of the tape. It also sets a
unit attention condition, such that the next request results in a CHECK
CONDITION status with sense key UNIT ATTENTION and asc/ascq indicating a
device reset. According to their logs the next command being sent is WRITE
FILEMARK, which results in writing an FM at the beginning of the tape,
effectively discarding its contents.

In fact, once the write fails with EIO, our software attempts to recover by
rewinding and repositioning the tape, then resuming operation. If this
fails, it attempts to rewind and reposition again, write a marker at the
end of the tape, and then unmount. It does not under any circumstances
write either data or filemarks without having successfully positioned the
tape to a known point.

What actually happens is that, since the last operation was a write, the
kernel executes an implied MTWEOF operation (which translate to a Write
Filemarks command) before the rewind that was actually requested. This
seems not entirely unreasonable, provided the tape position is known.
However, once this request fails (due to the unit attention condition), our
next rewind attempt also triggers an implied MTWEOF, which does _not_ fail
(the unit attention condition persists only until the initiator has been
notified); this is the command that unexpectedly erases the tape.

Our analysis is that the st driver is in fact completely ignoring the UNIT
ATTENTION and associated reset notification from the device. This is not a
condition that can be detected in the transport or mid-layer, as it occurs
entirely within the target and is reported only via the UNIT ATTENTION
sense key. The upper driver (i.e. st) needs to detect this indication and
reset its internal model of the device to an unknown state.

Suggested-by: Jeffrey Hutzelman <jhutz@cmu.edu>
Signed-off-by: John Meneghini <jmeneghi@redhat.com>
Link: https://lore.kernel.org/r/20230822181413.1210647-1-jmeneghi@redhat.com
Acked-by: Kai Mäkisara <kai.makisara@kolumbus.fi>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/st.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 14d7981ddcdd..338aa8c42968 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -414,6 +414,8 @@ static int st_chk_result(struct scsi_tape *STp, struct st_request * SRpnt)
 	if (cmdstatp->have_sense &&
 	    cmdstatp->sense_hdr.asc == 0 && cmdstatp->sense_hdr.ascq == 0x17)
 		STp->cleaning_req = 1; /* ASC and ASCQ => cleaning requested */
+	if (cmdstatp->have_sense && scode == UNIT_ATTENTION && cmdstatp->sense_hdr.asc == 0x29)
+		STp->pos_unknown = 1; /* ASC => power on / reset */
 
 	STp->pos_unknown |= STp->device->was_reset;
 

From efcf965a127823f63a70ec52f2c4bec3d722b6b5 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Wed, 23 Aug 2023 14:06:28 -0700
Subject: [PATCH 0681/1189] scsi: sd: Remove the number of forward declarations

Move the sd_pm_ops and sd_template data structures to just above init_sd()
such that the number of forward function declarations can be reduced.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20230823210628.523244-1-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/sd.c | 66 +++++++++++++++++++----------------------------
 1 file changed, 27 insertions(+), 39 deletions(-)

diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 68b12afa0721..4cd281368826 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -104,19 +104,7 @@ static void sd_config_discard(struct scsi_disk *, unsigned int);
 static void sd_config_write_same(struct scsi_disk *);
 static int  sd_revalidate_disk(struct gendisk *);
 static void sd_unlock_native_capacity(struct gendisk *disk);
-static int  sd_probe(struct device *);
-static int  sd_remove(struct device *);
 static void sd_shutdown(struct device *);
-static int sd_suspend_system(struct device *);
-static int sd_suspend_runtime(struct device *);
-static int sd_resume_system(struct device *);
-static int sd_resume_runtime(struct device *);
-static void sd_rescan(struct device *);
-static blk_status_t sd_init_command(struct scsi_cmnd *SCpnt);
-static void sd_uninit_command(struct scsi_cmnd *SCpnt);
-static int sd_done(struct scsi_cmnd *);
-static void sd_eh_reset(struct scsi_cmnd *);
-static int sd_eh_action(struct scsi_cmnd *, int);
 static void sd_read_capacity(struct scsi_disk *sdkp, unsigned char *buffer);
 static void scsi_disk_release(struct device *cdev);
 
@@ -592,33 +580,6 @@ static struct class sd_disk_class = {
 	.dev_groups	= sd_disk_groups,
 };
 
-static const struct dev_pm_ops sd_pm_ops = {
-	.suspend		= sd_suspend_system,
-	.resume			= sd_resume_system,
-	.poweroff		= sd_suspend_system,
-	.restore		= sd_resume_system,
-	.runtime_suspend	= sd_suspend_runtime,
-	.runtime_resume		= sd_resume_runtime,
-};
-
-static struct scsi_driver sd_template = {
-	.gendrv = {
-		.name		= "sd",
-		.owner		= THIS_MODULE,
-		.probe		= sd_probe,
-		.probe_type	= PROBE_PREFER_ASYNCHRONOUS,
-		.remove		= sd_remove,
-		.shutdown	= sd_shutdown,
-		.pm		= &sd_pm_ops,
-	},
-	.rescan			= sd_rescan,
-	.init_command		= sd_init_command,
-	.uninit_command		= sd_uninit_command,
-	.done			= sd_done,
-	.eh_action		= sd_eh_action,
-	.eh_reset		= sd_eh_reset,
-};
-
 /*
  * Don't request a new module, as that could deadlock in multipath
  * environment.
@@ -3926,6 +3887,33 @@ static int sd_resume_runtime(struct device *dev)
 	return sd_resume(dev);
 }
 
+static const struct dev_pm_ops sd_pm_ops = {
+	.suspend		= sd_suspend_system,
+	.resume			= sd_resume_system,
+	.poweroff		= sd_suspend_system,
+	.restore		= sd_resume_system,
+	.runtime_suspend	= sd_suspend_runtime,
+	.runtime_resume		= sd_resume_runtime,
+};
+
+static struct scsi_driver sd_template = {
+	.gendrv = {
+		.name		= "sd",
+		.owner		= THIS_MODULE,
+		.probe		= sd_probe,
+		.probe_type	= PROBE_PREFER_ASYNCHRONOUS,
+		.remove		= sd_remove,
+		.shutdown	= sd_shutdown,
+		.pm		= &sd_pm_ops,
+	},
+	.rescan			= sd_rescan,
+	.init_command		= sd_init_command,
+	.uninit_command		= sd_uninit_command,
+	.done			= sd_done,
+	.eh_action		= sd_eh_action,
+	.eh_reset		= sd_eh_reset,
+};
+
 /**
  *	init_sd - entry point for this driver (both when built in or when
  *	a module).

From 153c45dd63ef33ffb3d78307db5aa6131b2fdefc Mon Sep 17 00:00:00 2001
From: Kevin Barnett <kevin.barnett@microchip.com>
Date: Thu, 24 Aug 2023 10:58:05 -0500
Subject: [PATCH 0682/1189] scsi: smartpqi: Add abort handler

Implement aborts as resets.

Avoid I/O stalls across all devices attached to a controller when device
I/O requests time out.

Reviewed-by: Mahesh Rajashekhara <mahesh.rajashekhara@microchip.com>
Reviewed-by: Scott Teel <scott.teel@microchip.com>
Reviewed-by: Scott Benesh <scott.benesh@microchip.com>
Reviewed-by: Mike McGowen <mike.mcgowen@microchip.com>
Signed-off-by: Kevin Barnett <kevin.barnett@microchip.com>
Signed-off-by: Don Brace <don.brace@microchip.com>
Link: https://lore.kernel.org/r/20230824155812.789913-2-don.brace@microchip.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/smartpqi/smartpqi.h      |  14 ++-
 drivers/scsi/smartpqi/smartpqi_init.c | 171 ++++++++++++++++++++------
 2 files changed, 149 insertions(+), 36 deletions(-)

diff --git a/drivers/scsi/smartpqi/smartpqi.h b/drivers/scsi/smartpqi/smartpqi.h
index e392eaf5b2bf..e560d99efa95 100644
--- a/drivers/scsi/smartpqi/smartpqi.h
+++ b/drivers/scsi/smartpqi/smartpqi.h
@@ -1085,7 +1085,16 @@ struct pqi_stream_data {
 	u32	last_accessed;
 };
 
-#define PQI_MAX_LUNS_PER_DEVICE         256
+#define PQI_MAX_LUNS_PER_DEVICE		256
+
+struct pqi_tmf_work {
+	struct work_struct work_struct;
+	struct scsi_cmnd *scmd;
+	struct pqi_ctrl_info *ctrl_info;
+	struct pqi_scsi_dev *device;
+	u8	lun;
+	u8	scsi_opcode;
+};
 
 struct pqi_scsi_dev {
 	int	devtype;		/* as reported by INQUIRY command */
@@ -1111,6 +1120,7 @@ struct pqi_scsi_dev {
 	u8	erase_in_progress : 1;
 	bool	aio_enabled;		/* only valid for physical disks */
 	bool	in_remove;
+	bool	in_reset[PQI_MAX_LUNS_PER_DEVICE];
 	bool	device_offline;
 	u8	vendor[8];		/* bytes 8-15 of inquiry data */
 	u8	model[16];		/* bytes 16-31 of inquiry data */
@@ -1149,6 +1159,8 @@ struct pqi_scsi_dev {
 	struct pqi_stream_data stream_data[NUM_STREAMS_PER_LUN];
 	atomic_t scsi_cmds_outstanding[PQI_MAX_LUNS_PER_DEVICE];
 	unsigned int raid_bypass_cnt;
+
+	struct pqi_tmf_work tmf_work[PQI_MAX_LUNS_PER_DEVICE];
 };
 
 /* VPD inquiry pages */
diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index 6aaaa7ebca37..60cdc06ace61 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -48,6 +48,8 @@
 #define PQI_POST_RESET_DELAY_SECS			5
 #define PQI_POST_OFA_RESET_DELAY_UPON_TIMEOUT_SECS	10
 
+#define PQI_NO_COMPLETION	((void *)-1)
+
 MODULE_AUTHOR("Microchip");
 MODULE_DESCRIPTION("Driver for Microchip Smart Family Controller version "
 	DRIVER_VERSION);
@@ -96,6 +98,7 @@ static int pqi_ofa_host_memory_update(struct pqi_ctrl_info *ctrl_info);
 static int pqi_device_wait_for_pending_io(struct pqi_ctrl_info *ctrl_info,
 	struct pqi_scsi_dev *device, u8 lun, unsigned long timeout_msecs);
 static void pqi_fail_all_outstanding_requests(struct pqi_ctrl_info *ctrl_info);
+static void pqi_tmf_worker(struct work_struct *work);
 
 /* for flags argument to pqi_submit_raid_request_synchronous() */
 #define PQI_SYNC_FLAGS_INTERRUPTABLE	0x1
@@ -455,6 +458,21 @@ static inline bool pqi_device_in_remove(struct pqi_scsi_dev *device)
 	return device->in_remove;
 }
 
+static inline void pqi_device_reset_start(struct pqi_scsi_dev *device, u8 lun)
+{
+	device->in_reset[lun] = true;
+}
+
+static inline void pqi_device_reset_done(struct pqi_scsi_dev *device, u8 lun)
+{
+	device->in_reset[lun] = false;
+}
+
+static inline bool pqi_device_in_reset(struct pqi_scsi_dev *device, u8 lun)
+{
+	return device->in_reset[lun];
+}
+
 static inline int pqi_event_type_to_event_index(unsigned int event_type)
 {
 	int index;
@@ -2137,6 +2155,15 @@ static inline bool pqi_is_device_added(struct pqi_scsi_dev *device)
 	return device->sdev != NULL;
 }
 
+static inline void pqi_init_device_tmf_work(struct pqi_scsi_dev *device)
+{
+	unsigned int lun;
+	struct pqi_tmf_work *tmf_work;
+
+	for (lun = 0, tmf_work = device->tmf_work; lun < PQI_MAX_LUNS_PER_DEVICE; lun++, tmf_work++)
+		INIT_WORK(&tmf_work->work_struct, pqi_tmf_worker);
+}
+
 static void pqi_update_device_list(struct pqi_ctrl_info *ctrl_info,
 	struct pqi_scsi_dev *new_device_list[], unsigned int num_new_devices)
 {
@@ -2217,6 +2244,7 @@ static void pqi_update_device_list(struct pqi_ctrl_info *ctrl_info,
 		list_add_tail(&device->add_list_entry, &add_list);
 		/* To prevent this device structure from being freed later. */
 		device->keep_device = true;
+		pqi_init_device_tmf_work(device);
 	}
 
 	spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags);
@@ -5850,6 +5878,7 @@ static inline bool pqi_is_bypass_eligible_request(struct scsi_cmnd *scmd)
 void pqi_prep_for_scsi_done(struct scsi_cmnd *scmd)
 {
 	struct pqi_scsi_dev *device;
+	struct completion *wait;
 
 	if (!scmd->device) {
 		set_host_byte(scmd, DID_NO_CONNECT);
@@ -5863,6 +5892,10 @@ void pqi_prep_for_scsi_done(struct scsi_cmnd *scmd)
 	}
 
 	atomic_dec(&device->scsi_cmds_outstanding[scmd->device->lun]);
+
+	wait = (struct completion *)xchg(&scmd->host_scribble, NULL);
+	if (wait != PQI_NO_COMPLETION)
+		complete(wait);
 }
 
 static bool pqi_is_parity_write_stream(struct pqi_ctrl_info *ctrl_info,
@@ -5948,6 +5981,9 @@ static int pqi_scsi_queue_command(struct Scsi_Host *shost, struct scsi_cmnd *scm
 	u16 hw_queue;
 	struct pqi_queue_group *queue_group;
 	bool raid_bypassed;
+	u8 lun;
+
+	scmd->host_scribble = PQI_NO_COMPLETION;
 
 	device = scmd->device->hostdata;
 
@@ -5957,7 +5993,9 @@ static int pqi_scsi_queue_command(struct Scsi_Host *shost, struct scsi_cmnd *scm
 		return 0;
 	}
 
-	atomic_inc(&device->scsi_cmds_outstanding[scmd->device->lun]);
+	lun = (u8)scmd->device->lun;
+
+	atomic_inc(&device->scsi_cmds_outstanding[lun]);
 
 	ctrl_info = shost_to_hba(shost);
 
@@ -5967,7 +6005,7 @@ static int pqi_scsi_queue_command(struct Scsi_Host *shost, struct scsi_cmnd *scm
 		return 0;
 	}
 
-	if (pqi_ctrl_blocked(ctrl_info)) {
+	if (pqi_ctrl_blocked(ctrl_info) || pqi_device_in_reset(device, lun)) {
 		rc = SCSI_MLQUEUE_HOST_BUSY;
 		goto out;
 	}
@@ -6002,8 +6040,10 @@ static int pqi_scsi_queue_command(struct Scsi_Host *shost, struct scsi_cmnd *scm
 	}
 
 out:
-	if (rc)
-		atomic_dec(&device->scsi_cmds_outstanding[scmd->device->lun]);
+	if (rc) {
+		scmd->host_scribble = NULL;
+		atomic_dec(&device->scsi_cmds_outstanding[lun]);
+	}
 
 	return rc;
 }
@@ -6097,7 +6137,7 @@ static int pqi_wait_until_inbound_queues_empty(struct pqi_ctrl_info *ctrl_info)
 }
 
 static void pqi_fail_io_queued_for_device(struct pqi_ctrl_info *ctrl_info,
-	struct pqi_scsi_dev *device)
+	struct pqi_scsi_dev *device, u8 lun)
 {
 	unsigned int i;
 	unsigned int path;
@@ -6127,6 +6167,9 @@ static void pqi_fail_io_queued_for_device(struct pqi_ctrl_info *ctrl_info,
 				if (scsi_device != device)
 					continue;
 
+				if ((u8)scmd->device->lun != lun)
+					continue;
+
 				list_del(&io_request->request_list_entry);
 				set_host_byte(scmd, DID_RESET);
 				pqi_free_io_request(io_request);
@@ -6224,15 +6267,13 @@ static int pqi_wait_for_lun_reset_completion(struct pqi_ctrl_info *ctrl_info,
 
 #define PQI_LUN_RESET_FIRMWARE_TIMEOUT_SECS	30
 
-static int pqi_lun_reset(struct pqi_ctrl_info *ctrl_info, struct scsi_cmnd *scmd)
+static int pqi_lun_reset(struct pqi_ctrl_info *ctrl_info, struct pqi_scsi_dev *device, u8 lun)
 {
 	int rc;
 	struct pqi_io_request *io_request;
 	DECLARE_COMPLETION_ONSTACK(wait);
 	struct pqi_task_management_request *request;
-	struct pqi_scsi_dev *device;
 
-	device = scmd->device->hostdata;
 	io_request = pqi_alloc_io_request(ctrl_info, NULL);
 	io_request->io_complete_callback = pqi_lun_reset_complete;
 	io_request->context = &wait;
@@ -6247,7 +6288,7 @@ static int pqi_lun_reset(struct pqi_ctrl_info *ctrl_info, struct scsi_cmnd *scmd
 	memcpy(request->lun_number, device->scsi3addr,
 		sizeof(request->lun_number));
 	if (!pqi_is_logical_device(device) && ctrl_info->multi_lun_device_supported)
-		request->ml_device_lun_number = (u8)scmd->device->lun;
+		request->ml_device_lun_number = lun;
 	request->task_management_function = SOP_TASK_MANAGEMENT_LUN_RESET;
 	if (ctrl_info->tmf_iu_timeout_supported)
 		put_unaligned_le16(PQI_LUN_RESET_FIRMWARE_TIMEOUT_SECS, &request->timeout);
@@ -6255,7 +6296,7 @@ static int pqi_lun_reset(struct pqi_ctrl_info *ctrl_info, struct scsi_cmnd *scmd
 	pqi_start_io(ctrl_info, &ctrl_info->queue_groups[PQI_DEFAULT_QUEUE_GROUP], RAID_PATH,
 		io_request);
 
-	rc = pqi_wait_for_lun_reset_completion(ctrl_info, device, (u8)scmd->device->lun, &wait);
+	rc = pqi_wait_for_lun_reset_completion(ctrl_info, device, lun, &wait);
 	if (rc == 0)
 		rc = io_request->status;
 
@@ -6269,18 +6310,16 @@ static int pqi_lun_reset(struct pqi_ctrl_info *ctrl_info, struct scsi_cmnd *scmd
 #define PQI_LUN_RESET_PENDING_IO_TIMEOUT_MSECS		(10 * 60 * 1000)
 #define PQI_LUN_RESET_FAILED_PENDING_IO_TIMEOUT_MSECS	(2 * 60 * 1000)
 
-static int pqi_lun_reset_with_retries(struct pqi_ctrl_info *ctrl_info, struct scsi_cmnd *scmd)
+static int pqi_lun_reset_with_retries(struct pqi_ctrl_info *ctrl_info, struct pqi_scsi_dev *device, u8 lun)
 {
 	int reset_rc;
 	int wait_rc;
 	unsigned int retries;
 	unsigned long timeout_msecs;
-	struct pqi_scsi_dev *device;
 
-	device = scmd->device->hostdata;
 	for (retries = 0;;) {
-		reset_rc = pqi_lun_reset(ctrl_info, scmd);
-		if (reset_rc == 0 || reset_rc == -ENODEV || ++retries > PQI_LUN_RESET_RETRIES)
+		reset_rc = pqi_lun_reset(ctrl_info, device, lun);
+		if (reset_rc == 0 || reset_rc == -ENODEV || reset_rc == -ENXIO || ++retries > PQI_LUN_RESET_RETRIES)
 			break;
 		msleep(PQI_LUN_RESET_RETRY_INTERVAL_MSECS);
 	}
@@ -6288,60 +6327,53 @@ static int pqi_lun_reset_with_retries(struct pqi_ctrl_info *ctrl_info, struct sc
 	timeout_msecs = reset_rc ? PQI_LUN_RESET_FAILED_PENDING_IO_TIMEOUT_MSECS :
 		PQI_LUN_RESET_PENDING_IO_TIMEOUT_MSECS;
 
-	wait_rc = pqi_device_wait_for_pending_io(ctrl_info, device, scmd->device->lun, timeout_msecs);
+	wait_rc = pqi_device_wait_for_pending_io(ctrl_info, device, lun, timeout_msecs);
 	if (wait_rc && reset_rc == 0)
 		reset_rc = wait_rc;
 
 	return reset_rc == 0 ? SUCCESS : FAILED;
 }
 
-static int pqi_device_reset(struct pqi_ctrl_info *ctrl_info, struct scsi_cmnd *scmd)
+static int pqi_device_reset(struct pqi_ctrl_info *ctrl_info, struct pqi_scsi_dev *device, u8 lun)
 {
 	int rc;
-	struct pqi_scsi_dev *device;
 
-	device = scmd->device->hostdata;
 	pqi_ctrl_block_requests(ctrl_info);
 	pqi_ctrl_wait_until_quiesced(ctrl_info);
-	pqi_fail_io_queued_for_device(ctrl_info, device);
+	pqi_fail_io_queued_for_device(ctrl_info, device, lun);
 	rc = pqi_wait_until_inbound_queues_empty(ctrl_info);
+	pqi_device_reset_start(device, lun);
+	pqi_ctrl_unblock_requests(ctrl_info);
 	if (rc)
 		rc = FAILED;
 	else
-		rc = pqi_lun_reset_with_retries(ctrl_info, scmd);
-	pqi_ctrl_unblock_requests(ctrl_info);
+		rc = pqi_lun_reset_with_retries(ctrl_info, device, lun);
+	pqi_device_reset_done(device, lun);
 
 	return rc;
 }
 
-static int pqi_eh_device_reset_handler(struct scsi_cmnd *scmd)
+static int pqi_device_reset_handler(struct pqi_ctrl_info *ctrl_info, struct pqi_scsi_dev *device, u8 lun, struct scsi_cmnd *scmd, u8 scsi_opcode)
 {
 	int rc;
-	struct Scsi_Host *shost;
-	struct pqi_ctrl_info *ctrl_info;
-	struct pqi_scsi_dev *device;
-
-	shost = scmd->device->host;
-	ctrl_info = shost_to_hba(shost);
-	device = scmd->device->hostdata;
 
 	mutex_lock(&ctrl_info->lun_reset_mutex);
 
 	dev_err(&ctrl_info->pci_dev->dev,
 		"resetting scsi %d:%d:%d:%d due to cmd 0x%02x\n",
-		shost->host_no,
-		device->bus, device->target, (u32)scmd->device->lun,
+		ctrl_info->scsi_host->host_no,
+		device->bus, device->target, lun,
 		scmd->cmd_len > 0 ? scmd->cmnd[0] : 0xff);
 
 	pqi_check_ctrl_health(ctrl_info);
 	if (pqi_ctrl_offline(ctrl_info))
 		rc = FAILED;
 	else
-		rc = pqi_device_reset(ctrl_info, scmd);
+		rc = pqi_device_reset(ctrl_info, device, lun);
 
 	dev_err(&ctrl_info->pci_dev->dev,
-		"reset of scsi %d:%d:%d:%d: %s\n",
-		shost->host_no, device->bus, device->target, (u32)scmd->device->lun,
+		"reset of scsi %d:%d:%d:%u: %s\n",
+		ctrl_info->scsi_host->host_no, device->bus, device->target, lun,
 		rc == SUCCESS ? "SUCCESS" : "FAILED");
 
 	mutex_unlock(&ctrl_info->lun_reset_mutex);
@@ -6349,6 +6381,74 @@ static int pqi_eh_device_reset_handler(struct scsi_cmnd *scmd)
 	return rc;
 }
 
+static int pqi_eh_device_reset_handler(struct scsi_cmnd *scmd)
+{
+	struct Scsi_Host *shost;
+	struct pqi_ctrl_info *ctrl_info;
+	struct pqi_scsi_dev *device;
+	u8 scsi_opcode;
+
+	shost = scmd->device->host;
+	ctrl_info = shost_to_hba(shost);
+	device = scmd->device->hostdata;
+	scsi_opcode = scmd->cmd_len > 0 ? scmd->cmnd[0] : 0xff;
+
+	return pqi_device_reset_handler(ctrl_info, device, (u8)scmd->device->lun, scmd, scsi_opcode);
+}
+
+static void pqi_tmf_worker(struct work_struct *work)
+{
+	struct pqi_tmf_work *tmf_work;
+	struct scsi_cmnd *scmd;
+
+	tmf_work = container_of(work, struct pqi_tmf_work, work_struct);
+	scmd = (struct scsi_cmnd *)xchg(&tmf_work->scmd, NULL);
+
+	pqi_device_reset_handler(tmf_work->ctrl_info, tmf_work->device, tmf_work->lun, scmd, tmf_work->scsi_opcode);
+}
+
+static int pqi_eh_abort_handler(struct scsi_cmnd *scmd)
+{
+	struct Scsi_Host *shost;
+	struct pqi_ctrl_info *ctrl_info;
+	struct pqi_scsi_dev *device;
+	struct pqi_tmf_work *tmf_work;
+	DECLARE_COMPLETION_ONSTACK(wait);
+
+	shost = scmd->device->host;
+	ctrl_info = shost_to_hba(shost);
+
+	dev_err(&ctrl_info->pci_dev->dev,
+		"attempting TASK ABORT on SCSI cmd at %p\n", scmd);
+
+	if (cmpxchg(&scmd->host_scribble, PQI_NO_COMPLETION, (void *)&wait) == NULL) {
+		dev_err(&ctrl_info->pci_dev->dev,
+			"SCSI cmd at %p already completed\n", scmd);
+		scmd->result = DID_RESET << 16;
+		goto out;
+	}
+
+	device = scmd->device->hostdata;
+	tmf_work = &device->tmf_work[scmd->device->lun];
+
+	if (cmpxchg(&tmf_work->scmd, NULL, scmd) == NULL) {
+		tmf_work->ctrl_info = ctrl_info;
+		tmf_work->device = device;
+		tmf_work->lun = (u8)scmd->device->lun;
+		tmf_work->scsi_opcode = scmd->cmd_len > 0 ? scmd->cmnd[0] : 0xff;
+		schedule_work(&tmf_work->work_struct);
+	}
+
+	wait_for_completion(&wait);
+
+	dev_err(&ctrl_info->pci_dev->dev,
+		"TASK ABORT on SCSI cmd at %p: SUCCESS\n", scmd);
+
+out:
+
+	return SUCCESS;
+}
+
 static int pqi_slave_alloc(struct scsi_device *sdev)
 {
 	struct pqi_scsi_dev *device;
@@ -7362,6 +7462,7 @@ static const struct scsi_host_template pqi_driver_template = {
 	.scan_finished = pqi_scan_finished,
 	.this_id = -1,
 	.eh_device_reset_handler = pqi_eh_device_reset_handler,
+	.eh_abort_handler = pqi_eh_abort_handler,
 	.ioctl = pqi_ioctl,
 	.slave_alloc = pqi_slave_alloc,
 	.slave_configure = pqi_slave_configure,

From 43cf3a6eab58b80515fd80b9026e5392d0f83aed Mon Sep 17 00:00:00 2001
From: Kevin Barnett <kevin.barnett@microchip.com>
Date: Thu, 24 Aug 2023 10:58:06 -0500
Subject: [PATCH 0683/1189] scsi: smartpqi: Rename MACRO to clarify purpose

Rename SOP_RC_INCORRECT_LOGICAL_UNIT to SOP_TMF_INCORRECT_LOGICAL_UNIT to
clarify the intended purpose.

Reviewed-by: Mahesh Rajashekhara <mahesh.rajashekhara@microchip.com>
Reviewed-by: Scott Teel <scott.teel@microchip.com>
Reviewed-by: Scott Benesh <scott.benesh@microchip.com>
Reviewed-by: Mike McGowen <mike.mcgowen@microchip.com>
Signed-off-by: Kevin Barnett <kevin.barnett@microchip.com>
Signed-off-by: Don Brace <don.brace@microchip.com>
Link: https://lore.kernel.org/r/20230824155812.789913-3-don.brace@microchip.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/smartpqi/smartpqi.h      | 2 +-
 drivers/scsi/smartpqi/smartpqi_init.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/smartpqi/smartpqi.h b/drivers/scsi/smartpqi/smartpqi.h
index e560d99efa95..041940183516 100644
--- a/drivers/scsi/smartpqi/smartpqi.h
+++ b/drivers/scsi/smartpqi/smartpqi.h
@@ -710,7 +710,7 @@ typedef u32 pqi_index_t;
 #define SOP_TMF_COMPLETE		0x0
 #define SOP_TMF_REJECTED		0x4
 #define SOP_TMF_FUNCTION_SUCCEEDED	0x8
-#define SOP_RC_INCORRECT_LOGICAL_UNIT	0x9
+#define SOP_TMF_INCORRECT_LOGICAL_UNIT	0x9
 
 /* additional CDB bytes usage field codes */
 #define SOP_ADDITIONAL_CDB_BYTES_0	0	/* 16-byte CDB */
diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index 60cdc06ace61..97322ebd77cf 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -3358,7 +3358,7 @@ static int pqi_interpret_task_management_response(struct pqi_ctrl_info *ctrl_inf
 	case SOP_TMF_REJECTED:
 		rc = -EAGAIN;
 		break;
-	case SOP_RC_INCORRECT_LOGICAL_UNIT:
+	case SOP_TMF_INCORRECT_LOGICAL_UNIT:
 		rc = -ENODEV;
 		break;
 	default:

From e9c39117b448938e8750a77a661b56a59b28dde8 Mon Sep 17 00:00:00 2001
From: Kevin Barnett <kevin.barnett@microchip.com>
Date: Thu, 24 Aug 2023 10:58:07 -0500
Subject: [PATCH 0684/1189] scsi: smartpqi: Rename pciinfo to pci_info

Make pci device structure names consistent and readable.

Reviewed-by: Scott Benesh <scott.benesh@microchip.com>
Reviewed-by: Mike McGowen <mike.mcgowen@microchip.com>
Signed-off-by: Kevin Barnett <kevin.barnett@microchip.com>
Signed-off-by: Don Brace <don.brace@microchip.com>
Link: https://lore.kernel.org/r/20230824155812.789913-4-don.brace@microchip.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/smartpqi/smartpqi_init.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index 97322ebd77cf..2ebc72270746 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -6570,21 +6570,21 @@ static int pqi_getpciinfo_ioctl(struct pqi_ctrl_info *ctrl_info, void __user *ar
 	struct pci_dev *pci_dev;
 	u32 subsystem_vendor;
 	u32 subsystem_device;
-	cciss_pci_info_struct pciinfo;
+	cciss_pci_info_struct pci_info;
 
 	if (!arg)
 		return -EINVAL;
 
 	pci_dev = ctrl_info->pci_dev;
 
-	pciinfo.domain = pci_domain_nr(pci_dev->bus);
-	pciinfo.bus = pci_dev->bus->number;
-	pciinfo.dev_fn = pci_dev->devfn;
+	pci_info.domain = pci_domain_nr(pci_dev->bus);
+	pci_info.bus = pci_dev->bus->number;
+	pci_info.dev_fn = pci_dev->devfn;
 	subsystem_vendor = pci_dev->subsystem_vendor;
 	subsystem_device = pci_dev->subsystem_device;
-	pciinfo.board_id = ((subsystem_device << 16) & 0xffff0000) | subsystem_vendor;
+	pci_info.board_id = ((subsystem_device << 16) & 0xffff0000) | subsystem_vendor;
 
-	if (copy_to_user(arg, &pciinfo, sizeof(pciinfo)))
+	if (copy_to_user(arg, &pci_info, sizeof(pci_info)))
 		return -EFAULT;
 
 	return 0;

From dad662c9fe50088d4d42dd7321d7e92a9663c681 Mon Sep 17 00:00:00 2001
From: David Strahan <David.Strahan@microchip.com>
Date: Thu, 24 Aug 2023 10:58:08 -0500
Subject: [PATCH 0685/1189] scsi: smartpqi: Simplify lun_number assignment

Simplify lun_number assignment. lun_number assignment is only required for
non-AIO requests.

Reviewed-by: Scott Benesh <scott.benesh@microchip.com>
Reviewed-by: Mike McGowen <mike.mcgowen@microchip.com>
Reviewed-by: Kevin Barnett <kevin.barnett@microchip.com>
Signed-off-by: David Strahan <David.Strahan@microchip.com>
Signed-off-by: Don Brace <don.brace@microchip.com>
Link: https://lore.kernel.org/r/20230824155812.789913-5-don.brace@microchip.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/smartpqi/smartpqi_init.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index 2ebc72270746..999bed578138 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -5656,7 +5656,6 @@ static int pqi_aio_submit_io(struct pqi_ctrl_info *ctrl_info,
 	int rc;
 	struct pqi_io_request *io_request;
 	struct pqi_aio_path_request *request;
-	struct pqi_scsi_dev *device;
 
 	io_request = pqi_alloc_io_request(ctrl_info, scmd);
 	if (!io_request)
@@ -5676,9 +5675,8 @@ static int pqi_aio_submit_io(struct pqi_ctrl_info *ctrl_info,
 	request->command_priority = io_high_prio;
 	put_unaligned_le16(io_request->index, &request->request_id);
 	request->error_index = request->request_id;
-	device = scmd->device->hostdata;
-	if (!pqi_is_logical_device(device) && ctrl_info->multi_lun_device_supported)
-		put_unaligned_le64(((scmd->device->lun) << 8), &request->lun_number);
+	if (!raid_bypass && ctrl_info->multi_lun_device_supported)
+		put_unaligned_le64(scmd->device->lun << 8, &request->lun_number);
 	if (cdb_length > sizeof(request->cdb))
 		cdb_length = sizeof(request->cdb);
 	request->cdb_length = cdb_length;

From 276395d024cc1bd39edafc97b1e6a48e61dc057a Mon Sep 17 00:00:00 2001
From: David Strahan <David.Strahan@microchip.com>
Date: Thu, 24 Aug 2023 10:58:09 -0500
Subject: [PATCH 0686/1189] scsi: smartpqi: Enhance shutdown notification

Provide more detailed information about cache flush errors during shutdown.

Reviewed-by: Mahesh Rajashekhara <mahesh.rajashekhara@microchip.com>
Reviewed-by: Scott Benesh <scott.benesh@microchip.com>
Reviewed-by: Scott Teel <scott.teel@microchip.com>
Reviewed-by: Mike McGowen <mike.mcgowen@microchip.com>
Reviewed-by: Kevin Barnett <kevin.barnett@microchip.com>
Signed-off-by: David Strahan <David.Strahan@microchip.com>
Signed-off-by: Don Brace <don.brace@microchip.com>
Link: https://lore.kernel.org/r/20230824155812.789913-6-don.brace@microchip.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/smartpqi/smartpqi_init.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index 999bed578138..aacb40cb6b79 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -9161,7 +9161,7 @@ static void pqi_shutdown(struct pci_dev *pci_dev)
 	rc = pqi_flush_cache(ctrl_info, shutdown_event);
 	if (rc)
 		dev_err(&pci_dev->dev,
-			"unable to flush controller cache\n");
+			"unable to flush controller cache during shutdown\n");
 
 	pqi_crash_if_pending_command(ctrl_info);
 	pqi_reset(ctrl_info);

From 72b737fa73bf6c5c9b702a7ed51ecdccfc99c0d8 Mon Sep 17 00:00:00 2001
From: David Strahan <David.Strahan@microchip.com>
Date: Thu, 24 Aug 2023 10:58:10 -0500
Subject: [PATCH 0687/1189] scsi: smartpqi: Enhance controller offline
 notification

Add a description for the reason the controller has been taken off-line.

Reviewed-by: Scott Benesh <scott.benesh@microchip.com>
Reviewed-by: Scott Teel <scott.teel@microchip.com>
Reviewed-by: Mike McGowen <mike.mcgowen@microchip.com>
Signed-off-by: David Strahan <David.Strahan@microchip.com>
Signed-off-by: Don Brace <don.brace@microchip.com>
Link: https://lore.kernel.org/r/20230824155812.789913-7-don.brace@microchip.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/smartpqi/smartpqi_init.c | 50 ++++++++++++++++++++++++++-
 1 file changed, 49 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index aacb40cb6b79..f1b393459f34 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -9003,6 +9003,52 @@ static void pqi_ctrl_offline_worker(struct work_struct *work)
 	pqi_take_ctrl_offline_deferred(ctrl_info);
 }
 
+static char *pqi_ctrl_shutdown_reason_to_string(enum pqi_ctrl_shutdown_reason ctrl_shutdown_reason)
+{
+	char *string;
+
+	switch (ctrl_shutdown_reason) {
+	case PQI_IQ_NOT_DRAINED_TIMEOUT:
+		string = "inbound queue not drained timeout";
+		break;
+	case PQI_LUN_RESET_TIMEOUT:
+		string = "LUN reset timeout";
+		break;
+	case PQI_IO_PENDING_POST_LUN_RESET_TIMEOUT:
+		string = "I/O pending timeout after LUN reset";
+		break;
+	case PQI_NO_HEARTBEAT:
+		string = "no controller heartbeat detected";
+		break;
+	case PQI_FIRMWARE_KERNEL_NOT_UP:
+		string = "firmware kernel not ready";
+		break;
+	case PQI_OFA_RESPONSE_TIMEOUT:
+		string = "OFA response timeout";
+		break;
+	case PQI_INVALID_REQ_ID:
+		string = "invalid request ID";
+		break;
+	case PQI_UNMATCHED_REQ_ID:
+		string = "unmatched request ID";
+		break;
+	case PQI_IO_PI_OUT_OF_RANGE:
+		string = "I/O queue producer index out of range";
+		break;
+	case PQI_EVENT_PI_OUT_OF_RANGE:
+		string = "event queue producer index out of range";
+		break;
+	case PQI_UNEXPECTED_IU_TYPE:
+		string = "unexpected IU type";
+		break;
+	default:
+		string = "unknown reason";
+		break;
+	}
+
+	return string;
+}
+
 static void pqi_take_ctrl_offline(struct pqi_ctrl_info *ctrl_info,
 	enum pqi_ctrl_shutdown_reason ctrl_shutdown_reason)
 {
@@ -9015,7 +9061,9 @@ static void pqi_take_ctrl_offline(struct pqi_ctrl_info *ctrl_info,
 	if (!pqi_disable_ctrl_shutdown)
 		sis_shutdown_ctrl(ctrl_info, ctrl_shutdown_reason);
 	pci_disable_device(ctrl_info->pci_dev);
-	dev_err(&ctrl_info->pci_dev->dev, "controller offline\n");
+	dev_err(&ctrl_info->pci_dev->dev,
+		"controller offline: reason code 0x%x (%s)\n",
+		ctrl_shutdown_reason, pqi_ctrl_shutdown_reason_to_string(ctrl_shutdown_reason));
 	schedule_work(&ctrl_info->ctrl_offline_work);
 }
 

From e1b919494aa9520c62742b1c59181476520c7863 Mon Sep 17 00:00:00 2001
From: Mahesh Rajashekhara <Mahesh.Rajashekhara@microchip.com>
Date: Thu, 24 Aug 2023 10:58:11 -0500
Subject: [PATCH 0688/1189] scsi: smartpqi: Enhance error messages

Add more detail to some TMF messages.

Reviewed-by: Scott Benesh <scott.benesh@microchip.com>
Reviewed-by: Mike McGowen <mike.mcgowen@microchip.com>
Reviewed-by: Kevin Barnett <kevin.barnett@microchip.com>
Signed-off-by: Mahesh Rajashekhara <Mahesh.Rajashekhara@microchip.com>
Signed-off-by: Don Brace <don.brace@microchip.com>
Link: https://lore.kernel.org/r/20230824155812.789913-8-don.brace@microchip.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/smartpqi/smartpqi_init.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index f1b393459f34..e288ba9af1a7 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -6358,10 +6358,8 @@ static int pqi_device_reset_handler(struct pqi_ctrl_info *ctrl_info, struct pqi_
 	mutex_lock(&ctrl_info->lun_reset_mutex);
 
 	dev_err(&ctrl_info->pci_dev->dev,
-		"resetting scsi %d:%d:%d:%d due to cmd 0x%02x\n",
-		ctrl_info->scsi_host->host_no,
-		device->bus, device->target, lun,
-		scmd->cmd_len > 0 ? scmd->cmnd[0] : 0xff);
+		"resetting scsi %d:%d:%d:%u SCSI cmd at %p due to cmd opcode 0x%02x\n",
+		ctrl_info->scsi_host->host_no, device->bus, device->target, lun, scmd, scsi_opcode);
 
 	pqi_check_ctrl_health(ctrl_info);
 	if (pqi_ctrl_offline(ctrl_info))
@@ -6415,18 +6413,20 @@ static int pqi_eh_abort_handler(struct scsi_cmnd *scmd)
 
 	shost = scmd->device->host;
 	ctrl_info = shost_to_hba(shost);
+	device = scmd->device->hostdata;
 
 	dev_err(&ctrl_info->pci_dev->dev,
-		"attempting TASK ABORT on SCSI cmd at %p\n", scmd);
+		"attempting TASK ABORT on scsi %d:%d:%d:%d for SCSI cmd at %p\n",
+		shost->host_no, device->bus, device->target, (int)scmd->device->lun, scmd);
 
 	if (cmpxchg(&scmd->host_scribble, PQI_NO_COMPLETION, (void *)&wait) == NULL) {
 		dev_err(&ctrl_info->pci_dev->dev,
-			"SCSI cmd at %p already completed\n", scmd);
+			"scsi %d:%d:%d:%d for SCSI cmd at %p already completed\n",
+			shost->host_no, device->bus, device->target, (int)scmd->device->lun, scmd);
 		scmd->result = DID_RESET << 16;
 		goto out;
 	}
 
-	device = scmd->device->hostdata;
 	tmf_work = &device->tmf_work[scmd->device->lun];
 
 	if (cmpxchg(&tmf_work->scmd, NULL, scmd) == NULL) {
@@ -6440,7 +6440,8 @@ static int pqi_eh_abort_handler(struct scsi_cmnd *scmd)
 	wait_for_completion(&wait);
 
 	dev_err(&ctrl_info->pci_dev->dev,
-		"TASK ABORT on SCSI cmd at %p: SUCCESS\n", scmd);
+		"TASK ABORT on scsi %d:%d:%d:%d for SCSI cmd at %p: SUCCESS\n",
+		shost->host_no, device->bus, device->target, (int)scmd->device->lun, scmd);
 
 out:
 

From 08b7ad50c8bc497efeb33b97cfba15a23c053a5c Mon Sep 17 00:00:00 2001
From: Don Brace <don.brace@microchip.com>
Date: Thu, 24 Aug 2023 10:58:12 -0500
Subject: [PATCH 0689/1189] scsi: smartpqi: Change driver version to 2.1.24-046

Reviewed-by: Gerry Morong <gerry.morong@microchip.com>
Reviewed-by: Scott Benesh <scott.benesh@microchip.com>
Reviewed-by: Scott Teel <scott.teel@microchip.com>
Reviewed-by: Mike McGowen <mike.mcgowen@microchip.com>
Reviewed-by: Kevin Barnett <kevin.barnett@microchip.com>
Signed-off-by: Don Brace <don.brace@microchip.com>
Link: https://lore.kernel.org/r/20230824155812.789913-9-don.brace@microchip.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/smartpqi/smartpqi_init.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index e288ba9af1a7..9ec018259860 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -33,11 +33,11 @@
 #define BUILD_TIMESTAMP
 #endif
 
-#define DRIVER_VERSION		"2.1.22-040"
+#define DRIVER_VERSION		"2.1.24-046"
 #define DRIVER_MAJOR		2
 #define DRIVER_MINOR		1
-#define DRIVER_RELEASE		22
-#define DRIVER_REVISION		40
+#define DRIVER_RELEASE		24
+#define DRIVER_REVISION		46
 
 #define DRIVER_NAME		"Microchip SmartPQI Driver (v" \
 				DRIVER_VERSION BUILD_TIMESTAMP ")"

From 4b2fd81f2af7147e844ecec0c5c07a16bca6b86e Mon Sep 17 00:00:00 2001
From: Justin Stitt <justinstitt@google.com>
Date: Thu, 24 Aug 2023 21:20:25 +0000
Subject: [PATCH 0690/1189] accel/ivpu: refactor deprecated strncpy

`strncpy` is deprecated for use on NUL-terminated destination strings [1].

A suitable replacement is `strscpy` [2] due to the fact that it
guarantees NUL-termination on its destination buffer argument which is
_not_ the case for `strncpy`!

Also remove extraneous if-statement as it can never be entered. The
return value from `strncpy` is it's first argument. In this case,
`...dyndbg_cmd` is an array:
| 	char dyndbg_cmd[VPU_DYNDBG_CMD_MAX_LEN];
             ^^^^^^^^^^
This can never be NULL which means `strncpy`'s return value cannot be
NULL here. Just use `strscpy` which is more robust and results in
simpler and less ambiguous code.

Moreover, remove needless `... - 1` as `strscpy`'s implementation
ensures NUL-termination and we do not need to carefully dance around
ending boundaries with a "- 1" anymore.

Fixes: 5d7422cfb498 ("accel/ivpu: Add IPC driver and JSM messages")
Link: www.kernel.org/doc/html/latest/process/deprecated.html#strncpy-on-nul-terminated-strings [1]
Link: https://manpages.debian.org/testing/linux-manual-4.8/strscpy.9.en.html [2]
Link: https://github.com/KSPP/linux/issues/90
Cc: linux-hardening@vger.kernel.org
Signed-off-by: Justin Stitt <justinstitt@google.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230824-strncpy-drivers-accel-ivpu-ivpu_jsm_msg-c-v1-1-12d9b52d2dff@google.com
---
 drivers/accel/ivpu/ivpu_jsm_msg.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/accel/ivpu/ivpu_jsm_msg.c b/drivers/accel/ivpu/ivpu_jsm_msg.c
index 831bfd2b2d39..bdddef2c59ee 100644
--- a/drivers/accel/ivpu/ivpu_jsm_msg.c
+++ b/drivers/accel/ivpu/ivpu_jsm_msg.c
@@ -118,8 +118,7 @@ int ivpu_jsm_dyndbg_control(struct ivpu_device *vdev, char *command, size_t size
 	struct vpu_jsm_msg resp;
 	int ret;
 
-	if (!strncpy(req.payload.dyndbg_control.dyndbg_cmd, command, VPU_DYNDBG_CMD_MAX_LEN - 1))
-		return -ENOMEM;
+	strscpy(req.payload.dyndbg_control.dyndbg_cmd, command, VPU_DYNDBG_CMD_MAX_LEN);
 
 	ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_DYNDBG_CONTROL_RSP, &resp,
 				    VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);

From 9897009eecae821efc684ecdd1d04584f5501509 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 24 Aug 2023 19:39:57 -0700
Subject: [PATCH 0691/1189] perf header: Fix missing PMU caps

PMU caps are written as HEADER_PMU_CAPS or for the special case of the
PMU "cpu" as HEADER_CPU_PMU_CAPS. As the PMU "cpu" is special, and not
any "core" PMU, the logic had become broken and core PMUs not called
"cpu" were not having their caps written.

This affects ARM and s390 non-hybrid PMUs.

Simplify the PMU caps writing logic to scan one fewer time and to be
more explicit in its behavior.

Fixes: 178ddf3bad981380 ("perf header: Avoid hybrid PMU list in write_pmu_caps")
Reported-by: Wei Li <liwei391@huawei.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20230825024002.801955-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/header.c | 31 ++++++++++++++++---------------
 1 file changed, 16 insertions(+), 15 deletions(-)

diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 52fbf526fe74..13c71d28e0eb 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1605,8 +1605,15 @@ static int write_pmu_caps(struct feat_fd *ff,
 	int ret;
 
 	while ((pmu = perf_pmus__scan(pmu))) {
-		if (!pmu->name || !strcmp(pmu->name, "cpu") ||
-		    perf_pmu__caps_parse(pmu) <= 0)
+		if (!strcmp(pmu->name, "cpu")) {
+			/*
+			 * The "cpu" PMU is special and covered by
+			 * HEADER_CPU_PMU_CAPS. Note, core PMUs are
+			 * counted/written here for ARM, s390 and Intel hybrid.
+			 */
+			continue;
+		}
+		if (perf_pmu__caps_parse(pmu) <= 0)
 			continue;
 		nr_pmu++;
 	}
@@ -1619,23 +1626,17 @@ static int write_pmu_caps(struct feat_fd *ff,
 		return 0;
 
 	/*
-	 * Write hybrid pmu caps first to maintain compatibility with
-	 * older perf tool.
+	 * Note older perf tools assume core PMUs come first, this is a property
+	 * of perf_pmus__scan.
 	 */
-	if (perf_pmus__num_core_pmus() > 1) {
-		pmu = NULL;
-		while ((pmu = perf_pmus__scan_core(pmu))) {
-			ret = __write_pmu_caps(ff, pmu, true);
-			if (ret < 0)
-				return ret;
-		}
-	}
-
 	pmu = NULL;
 	while ((pmu = perf_pmus__scan(pmu))) {
-		if (pmu->is_core || !pmu->nr_caps)
+		if (!strcmp(pmu->name, "cpu")) {
+			/* Skip as above. */
+			continue;
+		}
+		if (perf_pmu__caps_parse(pmu) <= 0)
 			continue;
-
 		ret = __write_pmu_caps(ff, pmu, true);
 		if (ret < 0)
 			return ret;

From c091ee90897aacf60aee510464cfc28b4041186f Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 24 Aug 2023 19:39:58 -0700
Subject: [PATCH 0692/1189] perf pmu: Remove logic for PMU name being NULL

The PMU name could be NULL in the case of the fake_pmu. Initialize the
name for the fake_pmu to "fake" so that all other logic can assume it
is initialized. Add a const to the type of name so that a literal can
be used to avoid additional initialization code. Propagate the cost
through related routines and remove now unnecessary "(char *)"
casts. Doing this located a bug in builtin-list for the pmu_glob that
was missing a strdup.

Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20230825024002.801955-3-irogers@google.com
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: James Clark <james.clark@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Wei Li <liwei391@huawei.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Ming Wang <wangming01@loongson.cn>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: linux-kernel@vger.kernel.org
Cc: linux-perf-users@vger.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/arm64/util/mem-events.c   |  2 +-
 tools/perf/arch/powerpc/util/mem-events.c |  6 +++---
 tools/perf/arch/x86/util/mem-events.c     |  8 ++++----
 tools/perf/arch/x86/util/pmu.c            | 10 +++++-----
 tools/perf/builtin-list.c                 |  2 +-
 tools/perf/tests/pmu-events.c             | 16 ++++++++--------
 tools/perf/util/env.c                     |  8 ++------
 tools/perf/util/header.c                  |  8 +-------
 tools/perf/util/mem-events.c              | 16 ++++++++--------
 tools/perf/util/mem-events.h              |  2 +-
 tools/perf/util/parse-events.c            |  7 ++-----
 tools/perf/util/parse-events.h            |  2 +-
 tools/perf/util/parse-events.y            |  2 +-
 tools/perf/util/pmu.c                     | 16 +++++++++-------
 tools/perf/util/pmu.h                     |  8 ++++----
 15 files changed, 51 insertions(+), 62 deletions(-)

diff --git a/tools/perf/arch/arm64/util/mem-events.c b/tools/perf/arch/arm64/util/mem-events.c
index df817d1f9f3e..3bcc5c7035c2 100644
--- a/tools/perf/arch/arm64/util/mem-events.c
+++ b/tools/perf/arch/arm64/util/mem-events.c
@@ -20,7 +20,7 @@ struct perf_mem_event *perf_mem_events__ptr(int i)
 	return &perf_mem_events[i];
 }
 
-char *perf_mem_events__name(int i, char *pmu_name __maybe_unused)
+const char *perf_mem_events__name(int i, const char *pmu_name __maybe_unused)
 {
 	struct perf_mem_event *e = perf_mem_events__ptr(i);
 
diff --git a/tools/perf/arch/powerpc/util/mem-events.c b/tools/perf/arch/powerpc/util/mem-events.c
index 4120fafe0be4..78b986e5268d 100644
--- a/tools/perf/arch/powerpc/util/mem-events.c
+++ b/tools/perf/arch/powerpc/util/mem-events.c
@@ -3,10 +3,10 @@
 #include "mem-events.h"
 
 /* PowerPC does not support 'ldlat' parameter. */
-char *perf_mem_events__name(int i, char *pmu_name __maybe_unused)
+const char *perf_mem_events__name(int i, const char *pmu_name __maybe_unused)
 {
 	if (i == PERF_MEM_EVENTS__LOAD)
-		return (char *) "cpu/mem-loads/";
+		return "cpu/mem-loads/";
 
-	return (char *) "cpu/mem-stores/";
+	return "cpu/mem-stores/";
 }
diff --git a/tools/perf/arch/x86/util/mem-events.c b/tools/perf/arch/x86/util/mem-events.c
index a8a782bcb121..191b372f9a2d 100644
--- a/tools/perf/arch/x86/util/mem-events.c
+++ b/tools/perf/arch/x86/util/mem-events.c
@@ -52,7 +52,7 @@ bool is_mem_loads_aux_event(struct evsel *leader)
 	return leader->core.attr.config == MEM_LOADS_AUX;
 }
 
-char *perf_mem_events__name(int i, char *pmu_name)
+const char *perf_mem_events__name(int i, const char *pmu_name)
 {
 	struct perf_mem_event *e = perf_mem_events__ptr(i);
 
@@ -65,7 +65,7 @@ char *perf_mem_events__name(int i, char *pmu_name)
 
 		if (!pmu_name) {
 			mem_loads_name__init = true;
-			pmu_name = (char *)"cpu";
+			pmu_name = "cpu";
 		}
 
 		if (perf_pmus__have_event(pmu_name, "mem-loads-aux")) {
@@ -82,12 +82,12 @@ char *perf_mem_events__name(int i, char *pmu_name)
 
 	if (i == PERF_MEM_EVENTS__STORE) {
 		if (!pmu_name)
-			pmu_name = (char *)"cpu";
+			pmu_name = "cpu";
 
 		scnprintf(mem_stores_name, sizeof(mem_stores_name),
 			  e->name, pmu_name);
 		return mem_stores_name;
 	}
 
-	return (char *)e->name;
+	return e->name;
 }
diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c
index 65d8cdff4d5f..f428cffb0378 100644
--- a/tools/perf/arch/x86/util/pmu.c
+++ b/tools/perf/arch/x86/util/pmu.c
@@ -126,7 +126,7 @@ close_dir:
 	return ret;
 }
 
-static char *__pmu_find_real_name(const char *name)
+static const char *__pmu_find_real_name(const char *name)
 {
 	struct pmu_alias *pmu_alias;
 
@@ -135,10 +135,10 @@ static char *__pmu_find_real_name(const char *name)
 			return pmu_alias->name;
 	}
 
-	return (char *)name;
+	return name;
 }
 
-char *pmu_find_real_name(const char *name)
+const char *pmu_find_real_name(const char *name)
 {
 	if (cached_list)
 		return __pmu_find_real_name(name);
@@ -149,7 +149,7 @@ char *pmu_find_real_name(const char *name)
 	return __pmu_find_real_name(name);
 }
 
-static char *__pmu_find_alias_name(const char *name)
+static const char *__pmu_find_alias_name(const char *name)
 {
 	struct pmu_alias *pmu_alias;
 
@@ -160,7 +160,7 @@ static char *__pmu_find_alias_name(const char *name)
 	return NULL;
 }
 
-char *pmu_find_alias_name(const char *name)
+const char *pmu_find_alias_name(const char *name)
 {
 	if (cached_list)
 		return __pmu_find_alias_name(name);
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index d8b9f606e734..8ac97a82744d 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -513,7 +513,7 @@ int cmd_list(int argc, const char **argv)
 				ret = -1;
 				goto out;
 			}
-			default_ps.pmu_glob = pmu->name;
+			default_ps.pmu_glob = strdup(pmu->name);
 		}
 	}
 	print_cb.print_start(ps);
diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
index 28c8789c4305..d92de3d5365e 100644
--- a/tools/perf/tests/pmu-events.c
+++ b/tools/perf/tests/pmu-events.c
@@ -522,7 +522,7 @@ static int test_core_pmu_event_aliases_cb(void *state, struct pmu_event_info *al
 }
 
 /* Verify aliases are as expected */
-static int __test_core_pmu_event_aliases(char *pmu_name, int *count)
+static int __test_core_pmu_event_aliases(const char *pmu_name, int *count)
 {
 	struct perf_pmu_test_event const **test_event_table;
 	struct perf_pmu *pmu;
@@ -635,7 +635,7 @@ static int __test_uncore_pmu_event_aliases(struct perf_pmu_test_pmu *test_pmu)
 static struct perf_pmu_test_pmu test_pmus[] = {
 	{
 		.pmu = {
-			.name = (char *)"hisi_sccl1_ddrc2",
+			.name = "hisi_sccl1_ddrc2",
 			.is_uncore = 1,
 		},
 		.aliases = {
@@ -644,7 +644,7 @@ static struct perf_pmu_test_pmu test_pmus[] = {
 	},
 	{
 		.pmu = {
-			.name = (char *)"uncore_cbox_0",
+			.name = "uncore_cbox_0",
 			.is_uncore = 1,
 		},
 		.aliases = {
@@ -655,7 +655,7 @@ static struct perf_pmu_test_pmu test_pmus[] = {
 	},
 	{
 		.pmu = {
-			.name = (char *)"hisi_sccl3_l3c7",
+			.name = "hisi_sccl3_l3c7",
 			.is_uncore = 1,
 		},
 		.aliases = {
@@ -664,7 +664,7 @@ static struct perf_pmu_test_pmu test_pmus[] = {
 	},
 	{
 		.pmu = {
-			.name = (char *)"uncore_imc_free_running_0",
+			.name = "uncore_imc_free_running_0",
 			.is_uncore = 1,
 		},
 		.aliases = {
@@ -673,7 +673,7 @@ static struct perf_pmu_test_pmu test_pmus[] = {
 	},
 	{
 		.pmu = {
-			.name = (char *)"uncore_imc_0",
+			.name = "uncore_imc_0",
 			.is_uncore = 1,
 		},
 		.aliases = {
@@ -682,7 +682,7 @@ static struct perf_pmu_test_pmu test_pmus[] = {
 	},
 	{
 		.pmu = {
-			.name = (char *)"uncore_sys_ddr_pmu0",
+			.name = "uncore_sys_ddr_pmu0",
 			.is_uncore = 1,
 			.id = (char *)"v8",
 		},
@@ -692,7 +692,7 @@ static struct perf_pmu_test_pmu test_pmus[] = {
 	},
 	{
 		.pmu = {
-			.name = (char *)"uncore_sys_ccn_pmu4",
+			.name = "uncore_sys_ccn_pmu4",
 			.is_uncore = 1,
 			.id = (char *)"0x01",
 		},
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 9eabf3ec56e9..a164164001fb 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -324,11 +324,9 @@ int perf_env__read_pmu_mappings(struct perf_env *env)
 	u32 pmu_num = 0;
 	struct strbuf sb;
 
-	while ((pmu = perf_pmus__scan(pmu))) {
-		if (!pmu->name)
-			continue;
+	while ((pmu = perf_pmus__scan(pmu)))
 		pmu_num++;
-	}
+
 	if (!pmu_num) {
 		pr_debug("pmu mappings not available\n");
 		return -ENOENT;
@@ -339,8 +337,6 @@ int perf_env__read_pmu_mappings(struct perf_env *env)
 		return -ENOMEM;
 
 	while ((pmu = perf_pmus__scan(pmu))) {
-		if (!pmu->name)
-			continue;
 		if (strbuf_addf(&sb, "%u:%s", pmu->type, pmu->name) < 0)
 			goto error;
 		/* include a NULL character at the end */
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 13c71d28e0eb..9f35d86a3351 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -746,20 +746,14 @@ static int write_pmu_mappings(struct feat_fd *ff,
 	 * Do a first pass to count number of pmu to avoid lseek so this
 	 * works in pipe mode as well.
 	 */
-	while ((pmu = perf_pmus__scan(pmu))) {
-		if (!pmu->name)
-			continue;
+	while ((pmu = perf_pmus__scan(pmu)))
 		pmu_num++;
-	}
 
 	ret = do_write(ff, &pmu_num, sizeof(pmu_num));
 	if (ret < 0)
 		return ret;
 
 	while ((pmu = perf_pmus__scan(pmu))) {
-		if (!pmu->name)
-			continue;
-
 		ret = do_write(ff, &pmu->type, sizeof(pmu->type));
 		if (ret < 0)
 			return ret;
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index c07fe3a90722..39ffe8ceb380 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -37,7 +37,7 @@ struct perf_mem_event * __weak perf_mem_events__ptr(int i)
 	return &perf_mem_events[i];
 }
 
-char * __weak perf_mem_events__name(int i, char *pmu_name  __maybe_unused)
+const char * __weak perf_mem_events__name(int i, const char *pmu_name  __maybe_unused)
 {
 	struct perf_mem_event *e = perf_mem_events__ptr(i);
 
@@ -53,7 +53,7 @@ char * __weak perf_mem_events__name(int i, char *pmu_name  __maybe_unused)
 		return mem_loads_name;
 	}
 
-	return (char *)e->name;
+	return e->name;
 }
 
 __weak bool is_mem_loads_aux_event(struct evsel *leader __maybe_unused)
@@ -186,7 +186,6 @@ int perf_mem_events__record_args(const char **rec_argv, int *argv_nr,
 	int i = *argv_nr, k = 0;
 	struct perf_mem_event *e;
 	struct perf_pmu *pmu;
-	char *s;
 
 	for (int j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
 		e = perf_mem_events__ptr(j);
@@ -209,15 +208,16 @@ int perf_mem_events__record_args(const char **rec_argv, int *argv_nr,
 			}
 
 			while ((pmu = perf_pmus__scan(pmu)) != NULL) {
+				const char *s = perf_mem_events__name(j, pmu->name);
+
 				rec_argv[i++] = "-e";
-				s = perf_mem_events__name(j, pmu->name);
 				if (s) {
-					s = strdup(s);
-					if (!s)
+					char *copy = strdup(s);
+					if (!copy)
 						return -1;
 
-					rec_argv[i++] = s;
-					rec_tmp[k++] = s;
+					rec_argv[i++] = copy;
+					rec_tmp[k++] = copy;
 				}
 			}
 		}
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index 12372309d60e..b40ad6ea93fc 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -38,7 +38,7 @@ extern unsigned int perf_mem_events__loads_ldlat;
 int perf_mem_events__parse(const char *str);
 int perf_mem_events__init(void);
 
-char *perf_mem_events__name(int i, char *pmu_name);
+const char *perf_mem_events__name(int i, const char *pmu_name);
 struct perf_mem_event *perf_mem_events__ptr(int i);
 bool is_mem_loads_aux_event(struct evsel *leader);
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index c71e135d7335..621bdd157a0f 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -262,7 +262,7 @@ __add_event(struct list_head *list, int *idx,
 	evsel->core.is_pmu_core = pmu ? pmu->is_core : false;
 	evsel->auto_merge_stats = auto_merge_stats;
 	evsel->pmu = pmu;
-	evsel->pmu_name = pmu && pmu->name ? strdup(pmu->name) : NULL;
+	evsel->pmu_name = pmu ? strdup(pmu->name) : NULL;
 
 	if (name)
 		evsel->name = strdup(name);
@@ -437,9 +437,6 @@ bool parse_events__filter_pmu(const struct parse_events_state *parse_state,
 	if (parse_state->pmu_filter == NULL)
 		return false;
 
-	if (pmu->name == NULL)
-		return true;
-
 	return strcmp(parse_state->pmu_filter, pmu->name) != 0;
 }
 
@@ -1292,7 +1289,7 @@ static bool config_term_percore(struct list_head *config_terms)
 }
 
 int parse_events_add_pmu(struct parse_events_state *parse_state,
-			 struct list_head *list, char *name,
+			 struct list_head *list, const char *name,
 			 struct list_head *head_config,
 			 bool auto_merge_stats, void *loc_)
 {
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index c7f779420723..c4e8d8e94b28 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -176,7 +176,7 @@ int parse_events_add_breakpoint(struct parse_events_state *parse_state,
 				u64 addr, char *type, u64 len,
 				struct list_head *head_config);
 int parse_events_add_pmu(struct parse_events_state *parse_state,
-			 struct list_head *list, char *name,
+			 struct list_head *list, const char *name,
 			 struct list_head *head_config,
 			bool auto_merge_stats, void *loc);
 
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 00da1f8c0baf..3a9d4e2513b5 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -307,7 +307,7 @@ PE_NAME opt_pmu_config
 		}
 
 		while ((pmu = perf_pmus__scan(pmu)) != NULL) {
-			char *name = pmu->name;
+			const char *name = pmu->name;
 
 			if (parse_events__filter_pmu(parse_state, pmu))
 				continue;
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index bb2ca29cd7bd..a96ccc5c3b51 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -29,7 +29,9 @@
 #include "fncache.h"
 #include "util/evsel_config.h"
 
-struct perf_pmu perf_pmu__fake;
+struct perf_pmu perf_pmu__fake = {
+	.name = "fake",
+};
 
 #define UNIT_MAX_LEN	31 /* max length for event unit name */
 
@@ -967,13 +969,13 @@ perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
 	return NULL;
 }
 
-char * __weak
+const char * __weak
 pmu_find_real_name(const char *name)
 {
-	return (char *)name;
+	return name;
 }
 
-char * __weak
+const char * __weak
 pmu_find_alias_name(const char *name __maybe_unused)
 {
 	return NULL;
@@ -991,8 +993,8 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char
 {
 	struct perf_pmu *pmu;
 	__u32 type;
-	char *name = pmu_find_real_name(lookup_name);
-	char *alias_name;
+	const char *name = pmu_find_real_name(lookup_name);
+	const char *alias_name;
 
 	pmu = zalloc(sizeof(*pmu));
 	if (!pmu)
@@ -1974,7 +1976,7 @@ void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config,
 		   name ?: "N/A", buf, config_name, config);
 }
 
-int perf_pmu__match(char *pattern, char *name, char *tok)
+int perf_pmu__match(const char *pattern, const char *name, const char *tok)
 {
 	if (!name)
 		return -1;
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index bae0de3ed7a5..e90169ab3dc2 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -39,7 +39,7 @@ struct perf_pmu_caps {
  */
 struct perf_pmu {
 	/** @name: The name of the PMU such as "cpu". */
-	char *name;
+	const char *name;
 	/**
 	 * @alias_name: Optional alternate name for the PMU determined in
 	 * architecture specific code.
@@ -249,10 +249,10 @@ void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config,
 				   const char *config_name);
 void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu);
 
-int perf_pmu__match(char *pattern, char *name, char *tok);
+int perf_pmu__match(const char *pattern, const char *name, const char *tok);
 
-char *pmu_find_real_name(const char *name);
-char *pmu_find_alias_name(const char *name);
+const char *pmu_find_real_name(const char *name);
+const char *pmu_find_alias_name(const char *name);
 double perf_pmu__cpu_slots_per_cycle(void);
 int perf_pmu__event_source_devices_scnprintf(char *pathname, size_t size);
 int perf_pmu__pathname_scnprintf(char *buf, size_t size,

From 970ef02e980aea5391d87e425defc5e814823b3a Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 24 Aug 2023 19:39:59 -0700
Subject: [PATCH 0693/1189] perf parse-events: Make term's config const

This avoids casts in tests. Use zfree in a few places to avoid
warnings about a freeing a const pointer.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Wei Li <liwei391@huawei.com>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20230825024002.801955-4-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/pmu.c         | 18 +++++++++---------
 tools/perf/util/parse-events.c | 10 +++++-----
 tools/perf/util/parse-events.h |  4 ++--
 tools/perf/util/pmu.c          |  2 +-
 4 files changed, 17 insertions(+), 17 deletions(-)

diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index c204ed1f1a8b..eb60e5f66859 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -28,55 +28,55 @@ static struct test_format {
 /* Simulated users input. */
 static struct parse_events_term test_terms[] = {
 	{
-		.config    = (char *) "krava01",
+		.config    = "krava01",
 		.val.num   = 15,
 		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
 		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
 	},
 	{
-		.config    = (char *) "krava02",
+		.config    = "krava02",
 		.val.num   = 170,
 		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
 		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
 	},
 	{
-		.config    = (char *) "krava03",
+		.config    = "krava03",
 		.val.num   = 1,
 		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
 		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
 	},
 	{
-		.config    = (char *) "krava11",
+		.config    = "krava11",
 		.val.num   = 27,
 		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
 		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
 	},
 	{
-		.config    = (char *) "krava12",
+		.config    = "krava12",
 		.val.num   = 1,
 		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
 		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
 	},
 	{
-		.config    = (char *) "krava13",
+		.config    = "krava13",
 		.val.num   = 2,
 		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
 		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
 	},
 	{
-		.config    = (char *) "krava21",
+		.config    = "krava21",
 		.val.num   = 119,
 		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
 		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
 	},
 	{
-		.config    = (char *) "krava22",
+		.config    = "krava22",
 		.val.num   = 11,
 		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
 		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
 	},
 	{
-		.config    = (char *) "krava23",
+		.config    = "krava23",
 		.val.num   = 2,
 		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
 		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 621bdd157a0f..4c812fbe0cf9 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -199,7 +199,7 @@ static void fix_raw(struct list_head *config_terms, struct perf_pmu *pmu)
 			continue;
 
 		if (perf_pmu__have_event(pmu, term->val.str)) {
-			free(term->config);
+			zfree(&term->config);
 			term->config = term->val.str;
 			term->type_val = PARSE_EVENTS__TERM_TYPE_NUM;
 			term->type_term = PARSE_EVENTS__TERM_TYPE_USER;
@@ -208,7 +208,7 @@ static void fix_raw(struct list_head *config_terms, struct perf_pmu *pmu)
 			continue;
 		}
 
-		free(term->config);
+		zfree(&term->config);
 		term->config = strdup("config");
 		errno = 0;
 		num = strtoull(term->val.str + 1, NULL, 16);
@@ -1416,7 +1416,7 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 	struct perf_pmu *pmu = NULL;
 	YYLTYPE *loc = loc_;
 	int ok = 0;
-	char *config;
+	const char *config;
 
 	*listp = NULL;
 
@@ -1435,7 +1435,7 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 				   PARSE_EVENTS__TERM_TYPE_USER,
 				   config, 1, false, NULL,
 					NULL) < 0) {
-		free(config);
+		zfree(&config);
 		goto out_err;
 	}
 	list_add_tail(&term->list, head);
@@ -2378,7 +2378,7 @@ static int new_term(struct parse_events_term **_term,
 }
 
 int parse_events_term__num(struct parse_events_term **term,
-			   int type_term, char *config, u64 num,
+			   int type_term, const char *config, u64 num,
 			   bool no_value,
 			   void *loc_term_, void *loc_val_)
 {
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index c4e8d8e94b28..6d75d853ce00 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -83,7 +83,7 @@ enum {
 };
 
 struct parse_events_term {
-	char *config;
+	const char *config;
 	union {
 		char *str;
 		u64  num;
@@ -138,7 +138,7 @@ bool parse_events__filter_pmu(const struct parse_events_state *parse_state,
 void parse_events__shrink_config_terms(void);
 int parse_events__is_hardcoded_term(struct parse_events_term *term);
 int parse_events_term__num(struct parse_events_term **term,
-			   int type_term, char *config, u64 num,
+			   int type_term, const char *config, u64 num,
 			   bool novalue,
 			   void *loc_term, void *loc_val);
 int parse_events_term__str(struct parse_events_term **term,
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index a96ccc5c3b51..eb42f9830be7 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1418,7 +1418,7 @@ static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
 					     struct parse_events_term *term)
 {
 	struct perf_pmu_alias *alias;
-	char *name;
+	const char *name;
 
 	if (parse_events__is_hardcoded_term(term))
 		return NULL;

From b7823045ec1ab7bb79e206a17705f92d6ff4ff32 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 24 Aug 2023 19:40:00 -0700
Subject: [PATCH 0694/1189] perf pmu: Make id const and add missing free

The struct pmu id is initialized from pmu_id that is read into allocated
memory from a file, as such it needs free-ing in pmu__delete().

Make the id value const so that we can remove casts in tests.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Wei Li <liwei391@huawei.com>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20230825024002.801955-5-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/pmu-events.c | 4 ++--
 tools/perf/util/pmu.c         | 1 +
 tools/perf/util/pmu.h         | 2 +-
 3 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
index d92de3d5365e..ce4da9b1d115 100644
--- a/tools/perf/tests/pmu-events.c
+++ b/tools/perf/tests/pmu-events.c
@@ -684,7 +684,7 @@ static struct perf_pmu_test_pmu test_pmus[] = {
 		.pmu = {
 			.name = "uncore_sys_ddr_pmu0",
 			.is_uncore = 1,
-			.id = (char *)"v8",
+			.id = "v8",
 		},
 		.aliases = {
 			&sys_ddr_pmu_write_cycles,
@@ -694,7 +694,7 @@ static struct perf_pmu_test_pmu test_pmus[] = {
 		.pmu = {
 			.name = "uncore_sys_ccn_pmu4",
 			.is_uncore = 1,
-			.id = (char *)"0x01",
+			.id = "0x01",
 		},
 		.aliases = {
 			&sys_ccn_pmu_read_cycles,
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index eb42f9830be7..b92dc7237f3b 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -2056,6 +2056,7 @@ void perf_pmu__delete(struct perf_pmu *pmu)
 	zfree(&pmu->default_config);
 	zfree(&pmu->name);
 	zfree(&pmu->alias_name);
+	zfree(&pmu->id);
 	free(pmu);
 }
 
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index e90169ab3dc2..73965f208009 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -49,7 +49,7 @@ struct perf_pmu {
 	 * @id: Optional PMU identifier read from
 	 * <sysfs>/bus/event_source/devices/<name>/identifier.
 	 */
-	char *id;
+	const char *id;
 	/**
 	 * @type: Perf event attributed type value, read from
 	 * <sysfs>/bus/event_source/devices/<name>/type.

From 7512e969579544496ac91087d1342905d89d6f40 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 24 Aug 2023 19:40:01 -0700
Subject: [PATCH 0695/1189] perf build-id: Simplify build_id_cache__cachedir()

Initialize realname to NULL, rather than name.

This avoids a cast and as realpath is either NULL or an allocated
string, free can be called unconditionally.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Wei Li <liwei391@huawei.com>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20230825024002.801955-6-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/build-id.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 36728222a5b4..03c64b85383b 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -560,7 +560,7 @@ char *build_id_cache__cachedir(const char *sbuild_id, const char *name,
 			       struct nsinfo *nsi, bool is_kallsyms,
 			       bool is_vdso)
 {
-	char *realname = (char *)name, *filename;
+	char *realname = NULL, *filename;
 	bool slash = is_kallsyms || is_vdso;
 
 	if (!slash)
@@ -571,9 +571,7 @@ char *build_id_cache__cachedir(const char *sbuild_id, const char *name,
 		     sbuild_id ? "/" : "", sbuild_id ?: "") < 0)
 		filename = NULL;
 
-	if (!slash)
-		free(realname);
-
+	free(realname);
 	return filename;
 }
 

From 520da457f9b883e541c36c8f55e7590848b7aa64 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 24 Aug 2023 19:40:02 -0700
Subject: [PATCH 0696/1189] perf tui slang: Tidy casts

Casts were necessary for older versions of libslang, however, these
are now 15 years old and so we no longer need to care about supporting
them. Tidy the casts and remove unnecessary logic.

Move the ENABLE_SLFUTURE_CONST to the libslang.h common include file,
and also enable ENABLE_SLFUTURE_VOID.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Wei Li <liwei391@huawei.com>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20230825024002.801955-7-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/ui/Build          |  2 --
 tools/perf/ui/browser.c      |  6 +++---
 tools/perf/ui/browsers/Build |  5 -----
 tools/perf/ui/libslang.h     | 20 ++++----------------
 tools/perf/ui/tui/helpline.c |  2 +-
 tools/perf/ui/tui/setup.c    |  2 +-
 tools/perf/ui/tui/util.c     | 12 ++++++------
 7 files changed, 15 insertions(+), 34 deletions(-)

diff --git a/tools/perf/ui/Build b/tools/perf/ui/Build
index 3aff83c3275f..6b6d7143a37b 100644
--- a/tools/perf/ui/Build
+++ b/tools/perf/ui/Build
@@ -10,5 +10,3 @@ CFLAGS_setup.o += -DLIBDIR="BUILD_STR($(LIBDIR))"
 perf-$(CONFIG_SLANG) += browser.o
 perf-$(CONFIG_SLANG) += browsers/
 perf-$(CONFIG_SLANG) += tui/
-
-CFLAGS_browser.o += -DENABLE_SLFUTURE_CONST
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index 78fb01d6ad63..603d11283cbd 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -57,12 +57,12 @@ void ui_browser__gotorc(struct ui_browser *browser, int y, int x)
 void ui_browser__write_nstring(struct ui_browser *browser __maybe_unused, const char *msg,
 			       unsigned int width)
 {
-	slsmg_write_nstring(msg, width);
+	SLsmg_write_nstring(msg, width);
 }
 
 void ui_browser__vprintf(struct ui_browser *browser __maybe_unused, const char *fmt, va_list args)
 {
-	slsmg_vprintf(fmt, args);
+	SLsmg_vprintf(fmt, args);
 }
 
 void ui_browser__printf(struct ui_browser *browser __maybe_unused, const char *fmt, ...)
@@ -808,6 +808,6 @@ void ui_browser__init(void)
 
 	while (ui_browser__colorsets[i].name) {
 		struct ui_browser_colorset *c = &ui_browser__colorsets[i++];
-		sltt_set_color(c->colorset, c->name, c->fg, c->bg);
+		SLtt_set_color(c->colorset, c->name, c->fg, c->bg);
 	}
 }
diff --git a/tools/perf/ui/browsers/Build b/tools/perf/ui/browsers/Build
index fdf86f7981ca..7a1d5ddaf688 100644
--- a/tools/perf/ui/browsers/Build
+++ b/tools/perf/ui/browsers/Build
@@ -4,8 +4,3 @@ perf-y += map.o
 perf-y += scripts.o
 perf-y += header.o
 perf-y += res_sample.o
-
-CFLAGS_annotate.o += -DENABLE_SLFUTURE_CONST
-CFLAGS_hists.o    += -DENABLE_SLFUTURE_CONST
-CFLAGS_map.o      += -DENABLE_SLFUTURE_CONST
-CFLAGS_scripts.o  += -DENABLE_SLFUTURE_CONST
diff --git a/tools/perf/ui/libslang.h b/tools/perf/ui/libslang.h
index 991e692b9b46..1dff3020e9d5 100644
--- a/tools/perf/ui/libslang.h
+++ b/tools/perf/ui/libslang.h
@@ -11,28 +11,16 @@
 #define HAVE_LONG_LONG __GLIBC_HAVE_LONG_LONG
 #endif
 
+/* Enable future slang's corrected function prototypes. */
+#define ENABLE_SLFUTURE_CONST 1
+#define ENABLE_SLFUTURE_VOID 1
+
 #ifdef HAVE_SLANG_INCLUDE_SUBDIR
 #include <slang/slang.h>
 #else
 #include <slang.h>
 #endif
 
-#if SLANG_VERSION < 20104
-#define slsmg_printf(msg, args...) \
-	SLsmg_printf((char *)(msg), ##args)
-#define slsmg_vprintf(msg, vargs) \
-	SLsmg_vprintf((char *)(msg), vargs)
-#define slsmg_write_nstring(msg, len) \
-	SLsmg_write_nstring((char *)(msg), len)
-#define sltt_set_color(obj, name, fg, bg) \
-	SLtt_set_color(obj,(char *)(name), (char *)(fg), (char *)(bg))
-#else
-#define slsmg_printf SLsmg_printf
-#define slsmg_vprintf SLsmg_vprintf
-#define slsmg_write_nstring SLsmg_write_nstring
-#define sltt_set_color SLtt_set_color
-#endif
-
 #define SL_KEY_UNTAB 0x1000
 
 #endif /* _PERF_UI_SLANG_H_ */
diff --git a/tools/perf/ui/tui/helpline.c b/tools/perf/ui/tui/helpline.c
index db4952f5990b..b39451314f43 100644
--- a/tools/perf/ui/tui/helpline.c
+++ b/tools/perf/ui/tui/helpline.c
@@ -22,7 +22,7 @@ static void tui_helpline__push(const char *msg)
 
 	SLsmg_gotorc(SLtt_Screen_Rows - 1, 0);
 	SLsmg_set_color(0);
-	SLsmg_write_nstring((char *)msg, SLtt_Screen_Cols);
+	SLsmg_write_nstring(msg, SLtt_Screen_Cols);
 	SLsmg_refresh();
 	strlcpy(ui_helpline__current, msg, sz);
 }
diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c
index c1886aa184b3..605d9e175ea7 100644
--- a/tools/perf/ui/tui/setup.c
+++ b/tools/perf/ui/tui/setup.c
@@ -142,7 +142,7 @@ int ui__init(void)
 		goto out;
 	}
 
-	SLkp_define_keysym((char *)"^(kB)", SL_KEY_UNTAB);
+	SLkp_define_keysym("^(kB)", SL_KEY_UNTAB);
 
 	signal(SIGSEGV, ui__signal_backtrace);
 	signal(SIGFPE, ui__signal_backtrace);
diff --git a/tools/perf/ui/tui/util.c b/tools/perf/ui/tui/util.c
index 3c5174854ac8..e4d322ce0b54 100644
--- a/tools/perf/ui/tui/util.c
+++ b/tools/perf/ui/tui/util.c
@@ -106,7 +106,7 @@ int ui_browser__input_window(const char *title, const char *text, char *input,
 	SLsmg_draw_box(y, x++, nr_lines, max_len);
 	if (title) {
 		SLsmg_gotorc(y, x + 1);
-		SLsmg_write_string((char *)title);
+		SLsmg_write_string(title);
 	}
 	SLsmg_gotorc(++y, x);
 	nr_lines -= 7;
@@ -117,12 +117,12 @@ int ui_browser__input_window(const char *title, const char *text, char *input,
 	len = 5;
 	while (len--) {
 		SLsmg_gotorc(y + len - 1, x);
-		SLsmg_write_nstring((char *)" ", max_len);
+		SLsmg_write_nstring(" ", max_len);
 	}
 	SLsmg_draw_box(y++, x + 1, 3, max_len - 2);
 
 	SLsmg_gotorc(y + 3, x);
-	SLsmg_write_nstring((char *)exit_msg, max_len);
+	SLsmg_write_nstring(exit_msg, max_len);
 	SLsmg_refresh();
 
 	mutex_unlock(&ui__lock);
@@ -197,7 +197,7 @@ void __ui__info_window(const char *title, const char *text, const char *exit_msg
 	SLsmg_draw_box(y, x++, nr_lines, max_len);
 	if (title) {
 		SLsmg_gotorc(y, x + 1);
-		SLsmg_write_string((char *)title);
+		SLsmg_write_string(title);
 	}
 	SLsmg_gotorc(++y, x);
 	if (exit_msg)
@@ -207,9 +207,9 @@ void __ui__info_window(const char *title, const char *text, const char *exit_msg
 				   nr_lines, max_len, 1);
 	if (exit_msg) {
 		SLsmg_gotorc(y + nr_lines - 2, x);
-		SLsmg_write_nstring((char *)" ", max_len);
+		SLsmg_write_nstring(" ", max_len);
 		SLsmg_gotorc(y + nr_lines - 1, x);
-		SLsmg_write_nstring((char *)exit_msg, max_len);
+		SLsmg_write_nstring(exit_msg, max_len);
 	}
 }
 

From 0f2418fddb6dddd5f6f9fc4e2375bdaa0d7e0174 Mon Sep 17 00:00:00 2001
From: Kajol Jain <kjain@linux.ibm.com>
Date: Fri, 25 Aug 2023 16:17:00 +0530
Subject: [PATCH 0697/1189] perf lock contention: Fix typo in max-stack option
 description

Fix typo in max-stack option description by changing lopck contention
to lock contention.

Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Disha Goel <disgoel@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20230825104700.440809-1-kjain@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-lock.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 0cf1c5a2e032..b141f2134274 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -2507,7 +2507,7 @@ int cmd_lock(int argc, const char **argv)
 	OPT_CALLBACK('M', "map-nr-entries", &bpf_map_entries, "num",
 		     "Max number of BPF map entries", parse_map_entry),
 	OPT_CALLBACK(0, "max-stack", &max_stack_depth, "num",
-		     "Set the maximum stack depth when collecting lopck contention, "
+		     "Set the maximum stack depth when collecting lock contention, "
 		     "Default: " __stringify(CONTENTION_STACK_DEPTH), parse_max_stack),
 	OPT_INTEGER(0, "stack-skip", &stack_skip,
 		    "Set the number of stack depth to skip when finding a lock caller, "

From d889540247f9d549332a3dd5ca1b88a662119186 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Wed, 23 Aug 2023 10:10:59 -0500
Subject: [PATCH 0698/1189] watchdog: stm32: Drop unnecessary of_match_ptr()

With COMPILE_TEST recently enabled, 0-day reports a warning:

drivers/watchdog/stm32_iwdg.c:215:34: warning: 'stm32_iwdg_of_match' defined but not used [-Wunused-const-variable=]

As STM32 platforms are always used with DT, drop the of_match_ptr().

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202308211837.4VBSUAtZ-lkp@intel.com/
Signed-off-by: Rob Herring <robh@kernel.org>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20230823151059.2356881-1-robh@kernel.org
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/stm32_iwdg.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/watchdog/stm32_iwdg.c b/drivers/watchdog/stm32_iwdg.c
index fa5e70c4b93a..d9fd50df9802 100644
--- a/drivers/watchdog/stm32_iwdg.c
+++ b/drivers/watchdog/stm32_iwdg.c
@@ -287,7 +287,7 @@ static struct platform_driver stm32_iwdg_driver = {
 	.probe		= stm32_iwdg_probe,
 	.driver = {
 		.name	= "iwdg",
-		.of_match_table = of_match_ptr(stm32_iwdg_of_match),
+		.of_match_table = stm32_iwdg_of_match,
 	},
 };
 module_platform_driver(stm32_iwdg_driver);

From 8d668bad7a2d85e74042db3e0a336e078be9442e Mon Sep 17 00:00:00 2001
From: Fabio Estevam <festevam@denx.de>
Date: Tue, 22 Aug 2023 10:52:55 -0300
Subject: [PATCH 0699/1189] watchdog: imx2_wdt: Improve dev_crit() message

After issuing a "poweroff" command the board goes through the
expected power-off sequence and turns it off completely:

systemd-shutdown[1]: Powering off.
imx2-wdt 30280000.watchdog: Device shutdown: Expect reboot!
reboot: Power down

The "Expect reboot!" message is misleading because in the
power-off case, no reboot is expected to happen at all.

Avoid the confusion by removing the "Expect reboot!" message.

Signed-off-by: Fabio Estevam <festevam@denx.de>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20230822135255.1013981-1-festevam@gmail.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/imx2_wdt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/watchdog/imx2_wdt.c b/drivers/watchdog/imx2_wdt.c
index 1a27665a2f53..42e8ffae18dd 100644
--- a/drivers/watchdog/imx2_wdt.c
+++ b/drivers/watchdog/imx2_wdt.c
@@ -374,7 +374,7 @@ static void imx2_wdt_shutdown(struct platform_device *pdev)
 		 */
 		imx2_wdt_set_timeout(wdog, IMX2_WDT_MAX_TIME);
 		imx2_wdt_ping(wdog);
-		dev_crit(&pdev->dev, "Device shutdown: Expect reboot!\n");
+		dev_crit(&pdev->dev, "Device shutdown.\n");
 	}
 }
 

From c6b7c79846972f3ac52a6c373f1b684306d8433a Mon Sep 17 00:00:00 2001
From: Robert Marko <robimarko@gmail.com>
Date: Wed, 16 Aug 2023 18:13:59 +0200
Subject: [PATCH 0700/1189] dt-bindings: watchdog: qcom-wdt: document IPQ5018

Document the IPQ5018 watchdog compatible.

Signed-off-by: Robert Marko <robimarko@gmail.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20230816161455.3310629-1-robimarko@gmail.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml b/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml
index 6d0fe6abd06a..5046dfa55f13 100644
--- a/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml
+++ b/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml
@@ -18,6 +18,7 @@ properties:
       - items:
           - enum:
               - qcom,kpss-wdt-ipq4019
+              - qcom,apss-wdt-ipq5018
               - qcom,apss-wdt-ipq5332
               - qcom,apss-wdt-ipq9574
               - qcom,apss-wdt-msm8994

From 05c74a23407ccdba4ddfb02b1cb42cc9d28514ab Mon Sep 17 00:00:00 2001
From: Huqiang Qin <huqiang.qin@amlogic.com>
Date: Wed, 2 Aug 2023 11:32:19 +0800
Subject: [PATCH 0701/1189] dt-bindings: watchdog: Add support for Amlogic-T7
 SoCs

Update dt-binding document for watchdog of Amlogic-T7 SoCs.

Signed-off-by: Huqiang Qin <huqiang.qin@amlogic.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Dmitry Rokosov <ddrokosov@sberdevices.ru>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20230802033222.4024946-2-huqiang.qin@amlogic.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 .../devicetree/bindings/watchdog/amlogic,meson-gxbb-wdt.yaml     | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/watchdog/amlogic,meson-gxbb-wdt.yaml b/Documentation/devicetree/bindings/watchdog/amlogic,meson-gxbb-wdt.yaml
index f5cc7aa1b93b..443e2e7ab467 100644
--- a/Documentation/devicetree/bindings/watchdog/amlogic,meson-gxbb-wdt.yaml
+++ b/Documentation/devicetree/bindings/watchdog/amlogic,meson-gxbb-wdt.yaml
@@ -17,6 +17,7 @@ properties:
   compatible:
     enum:
       - amlogic,meson-gxbb-wdt
+      - amlogic,t7-wdt
 
   reg:
     maxItems: 1

From 55908e388b5daef8b0ca2b8091b3ad76e68af7ce Mon Sep 17 00:00:00 2001
From: Huqiang Qin <huqiang.qin@amlogic.com>
Date: Wed, 2 Aug 2023 11:32:20 +0800
Subject: [PATCH 0702/1189] watchdog: Add a new struct for Amlogic-GXBB driver

Add a new structure wdt_params to describe the watchdog difference
of different chips.

Signed-off-by: Huqiang Qin <huqiang.qin@amlogic.com>
Reviewed-by: Dmitry Rokosov <ddrokosov@sberdevices.ru>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20230802033222.4024946-3-huqiang.qin@amlogic.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/meson_gxbb_wdt.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/watchdog/meson_gxbb_wdt.c b/drivers/watchdog/meson_gxbb_wdt.c
index 35d80cb39856..18180d91543e 100644
--- a/drivers/watchdog/meson_gxbb_wdt.c
+++ b/drivers/watchdog/meson_gxbb_wdt.c
@@ -22,7 +22,6 @@
 
 #define GXBB_WDT_CTRL_CLKDIV_EN			BIT(25)
 #define GXBB_WDT_CTRL_CLK_EN			BIT(24)
-#define GXBB_WDT_CTRL_EE_RESET			BIT(21)
 #define GXBB_WDT_CTRL_EN			BIT(18)
 #define GXBB_WDT_CTRL_DIV_MASK			(BIT(18) - 1)
 
@@ -45,6 +44,10 @@ struct meson_gxbb_wdt {
 	struct clk *clk;
 };
 
+struct wdt_params {
+	u32 rst;
+};
+
 static int meson_gxbb_wdt_start(struct watchdog_device *wdt_dev)
 {
 	struct meson_gxbb_wdt *data = watchdog_get_drvdata(wdt_dev);
@@ -140,8 +143,12 @@ static const struct dev_pm_ops meson_gxbb_wdt_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(meson_gxbb_wdt_suspend, meson_gxbb_wdt_resume)
 };
 
+static const struct wdt_params gxbb_params = {
+	.rst = BIT(21),
+};
+
 static const struct of_device_id meson_gxbb_wdt_dt_ids[] = {
-	 { .compatible = "amlogic,meson-gxbb-wdt", },
+	 { .compatible = "amlogic,meson-gxbb-wdt", .data = &gxbb_params, },
 	 { /* sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, meson_gxbb_wdt_dt_ids);
@@ -150,6 +157,7 @@ static int meson_gxbb_wdt_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct meson_gxbb_wdt *data;
+	struct wdt_params *params;
 	u32 ctrl_reg;
 
 	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
@@ -164,6 +172,8 @@ static int meson_gxbb_wdt_probe(struct platform_device *pdev)
 	if (IS_ERR(data->clk))
 		return PTR_ERR(data->clk);
 
+	params = (struct wdt_params *)of_device_get_match_data(dev);
+
 	platform_set_drvdata(pdev, data);
 
 	data->wdt_dev.parent = dev;
@@ -191,7 +201,7 @@ static int meson_gxbb_wdt_probe(struct platform_device *pdev)
 	/* Setup with 1ms timebase */
 	ctrl_reg |= ((clk_get_rate(data->clk) / 1000) &
 			GXBB_WDT_CTRL_DIV_MASK) |
-			GXBB_WDT_CTRL_EE_RESET |
+			params->rst |
 			GXBB_WDT_CTRL_CLK_EN |
 			GXBB_WDT_CTRL_CLKDIV_EN;
 

From 8c776a0401f1dcfcfc8e5549c5260668bec59c0e Mon Sep 17 00:00:00 2001
From: Huqiang Qin <huqiang.qin@amlogic.com>
Date: Wed, 2 Aug 2023 11:32:21 +0800
Subject: [PATCH 0703/1189] watchdog: Add support for Amlogic-T7 SoCs

Compared with the previous Amlogic-GXBB, the watchdog of Amlogic-T7
has a different reset enable bit.

Signed-off-by: Huqiang Qin <huqiang.qin@amlogic.com>
Reviewed-by: Dmitry Rokosov <ddrokosov@sberdevices.ru>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20230802033222.4024946-4-huqiang.qin@amlogic.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/meson_gxbb_wdt.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/watchdog/meson_gxbb_wdt.c b/drivers/watchdog/meson_gxbb_wdt.c
index 18180d91543e..a48622d11ad7 100644
--- a/drivers/watchdog/meson_gxbb_wdt.c
+++ b/drivers/watchdog/meson_gxbb_wdt.c
@@ -147,8 +147,13 @@ static const struct wdt_params gxbb_params = {
 	.rst = BIT(21),
 };
 
+static const struct wdt_params t7_params = {
+	.rst = BIT(22),
+};
+
 static const struct of_device_id meson_gxbb_wdt_dt_ids[] = {
 	 { .compatible = "amlogic,meson-gxbb-wdt", .data = &gxbb_params, },
+	 { .compatible = "amlogic,t7-wdt", .data = &t7_params, },
 	 { /* sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, meson_gxbb_wdt_dt_ids);

From f1187ef24eb8f36e8ad8106d22615ceddeea6097 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 24 Aug 2023 19:23:56 -0700
Subject: [PATCH 0704/1189] KVM: SVM: Get source vCPUs from source VM for
 SEV-ES intrahost migration

Fix a goof where KVM tries to grab source vCPUs from the destination VM
when doing intrahost migration.  Grabbing the wrong vCPU not only hoses
the guest, it also crashes the host due to the VMSA pointer being left
NULL.

  BUG: unable to handle page fault for address: ffffe38687000000
  #PF: supervisor read access in kernel mode
  #PF: error_code(0x0000) - not-present page
  PGD 0 P4D 0
  Oops: 0000 [#1] SMP NOPTI
  CPU: 39 PID: 17143 Comm: sev_migrate_tes Tainted: GO       6.5.0-smp--fff2e47e6c3b-next #151
  Hardware name: Google, Inc. Arcadia_IT_80/Arcadia_IT_80, BIOS 34.28.0 07/10/2023
  RIP: 0010:__free_pages+0x15/0xd0
  RSP: 0018:ffff923fcf6e3c78 EFLAGS: 00010246
  RAX: 0000000000000000 RBX: ffffe38687000000 RCX: 0000000000000100
  RDX: 0000000000000100 RSI: 0000000000000000 RDI: ffffe38687000000
  RBP: ffff923fcf6e3c88 R08: ffff923fcafb0000 R09: 0000000000000000
  R10: 0000000000000000 R11: ffffffff83619b90 R12: ffff923fa9540000
  R13: 0000000000080007 R14: ffff923f6d35d000 R15: 0000000000000000
  FS:  0000000000000000(0000) GS:ffff929d0d7c0000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: ffffe38687000000 CR3: 0000005224c34005 CR4: 0000000000770ee0
  PKRU: 55555554
  Call Trace:
   <TASK>
   sev_free_vcpu+0xcb/0x110 [kvm_amd]
   svm_vcpu_free+0x75/0xf0 [kvm_amd]
   kvm_arch_vcpu_destroy+0x36/0x140 [kvm]
   kvm_destroy_vcpus+0x67/0x100 [kvm]
   kvm_arch_destroy_vm+0x161/0x1d0 [kvm]
   kvm_put_kvm+0x276/0x560 [kvm]
   kvm_vm_release+0x25/0x30 [kvm]
   __fput+0x106/0x280
   ____fput+0x12/0x20
   task_work_run+0x86/0xb0
   do_exit+0x2e3/0x9c0
   do_group_exit+0xb1/0xc0
   __x64_sys_exit_group+0x1b/0x20
   do_syscall_64+0x41/0x90
   entry_SYSCALL_64_after_hwframe+0x63/0xcd
   </TASK>
  CR2: ffffe38687000000

Fixes: 6defa24d3b12 ("KVM: SEV: Init target VMCBs in sev_migrate_from")
Cc: stable@vger.kernel.org
Cc: Peter Gonda <pgonda@google.com>
Reviewed-by: Peter Gonda <pgonda@google.com>
Reviewed-by: Pankaj Gupta <pankaj.gupta@amd.com>
Link: https://lore.kernel.org/r/20230825022357.2852133-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/sev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 2cd15783dfb9..acc700bcb299 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -1739,7 +1739,7 @@ static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm)
 		 * Note, the source is not required to have the same number of
 		 * vCPUs as the destination when migrating a vanilla SEV VM.
 		 */
-		src_vcpu = kvm_get_vcpu(dst_kvm, i);
+		src_vcpu = kvm_get_vcpu(src_kvm, i);
 		src_svm = to_svm(src_vcpu);
 
 		/*

From 1952e74da96fb3e48b72a2d0ece78c688a5848c1 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 24 Aug 2023 19:23:57 -0700
Subject: [PATCH 0705/1189] KVM: SVM: Skip VMSA init in sev_es_init_vmcb() if
 pointer is NULL

Skip initializing the VMSA physical address in the VMCB if the VMSA is
NULL, which occurs during intrahost migration as KVM initializes the VMCB
before copying over state from the source to the destination (including
the VMSA and its physical address).

In normal builds, __pa() is just math, so the bug isn't fatal, but with
CONFIG_DEBUG_VIRTUAL=y, the validity of the virtual address is verified
and passing in NULL will make the kernel unhappy.

Fixes: 6defa24d3b12 ("KVM: SEV: Init target VMCBs in sev_migrate_from")
Cc: stable@vger.kernel.org
Cc: Peter Gonda <pgonda@google.com>
Reviewed-by: Peter Gonda <pgonda@google.com>
Reviewed-by: Pankaj Gupta <pankaj.gupta@amd.com>
Link: https://lore.kernel.org/r/20230825022357.2852133-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/sev.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index acc700bcb299..5585a3556179 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2975,9 +2975,12 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
 	/*
 	 * An SEV-ES guest requires a VMSA area that is a separate from the
 	 * VMCB page. Do not include the encryption mask on the VMSA physical
-	 * address since hardware will access it using the guest key.
+	 * address since hardware will access it using the guest key.  Note,
+	 * the VMSA will be NULL if this vCPU is the destination for intrahost
+	 * migration, and will be copied later.
 	 */
-	svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);
+	if (svm->sev_es.vmsa)
+		svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);
 
 	/* Can't intercept CR register access, HV can't modify CR registers */
 	svm_clr_intercept(svm, INTERCEPT_CR0_READ);

From cb49631ad111570f1bad37702c11c2ae07fa2e3c Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 24 Aug 2023 18:36:18 -0700
Subject: [PATCH 0706/1189] KVM: SVM: Don't inject #UD if KVM attempts to skip
 SEV guest insn

Don't inject a #UD if KVM attempts to "emulate" to skip an instruction
for an SEV guest, and instead resume the guest and hope that it can make
forward progress.  When commit 04c40f344def ("KVM: SVM: Inject #UD on
attempted emulation for SEV guest w/o insn buffer") added the completely
arbitrary #UD behavior, there were no known scenarios where a well-behaved
guest would induce a VM-Exit that triggered emulation, i.e. it was thought
that injecting #UD would be helpful.

However, now that KVM (correctly) attempts to re-inject INT3/INTO, e.g. if
a #NPF is encountered when attempting to deliver the INT3/INTO, an SEV
guest can trigger emulation without a buffer, through no fault of its own.
Resuming the guest and retrying the INT3/INTO is architecturally wrong,
e.g. the vCPU will incorrectly re-hit code #DBs, but for SEV guests there
is literally no other option that has a chance of making forward progress.

Drop the #UD injection for all "skip" emulation, not just those related to
INT3/INTO, even though that means that the guest will likely end up in an
infinite loop instead of getting a #UD (the vCPU may also crash, e.g. if
KVM emulated everything about an instruction except for advancing RIP).
There's no evidence that suggests that an unexpected #UD is actually
better than hanging the vCPU, e.g. a soft-hung vCPU can still respond to
IRQs and NMIs to generate a backtrace.

Reported-by: Wu Zongyo <wuzongyo@mail.ustc.edu.cn>
Closes: https://lore.kernel.org/all/8eb933fd-2cf3-d7a9-32fe-2a1d82eac42a@mail.ustc.edu.cn
Fixes: 6ef88d6e36c2 ("KVM: SVM: Re-inject INT3/INTO instead of retrying the instruction")
Cc: stable@vger.kernel.org
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Link: https://lore.kernel.org/r/20230825013621.2845700-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.c | 35 +++++++++++++++++++++++++++--------
 1 file changed, 27 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index d76c8a0764f1..d7a474571ff1 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -365,6 +365,8 @@ static void svm_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
 		svm->vmcb->control.int_state |= SVM_INTERRUPT_SHADOW_MASK;
 
 }
+static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
+					void *insn, int insn_len);
 
 static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu,
 					   bool commit_side_effects)
@@ -385,6 +387,14 @@ static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu,
 	}
 
 	if (!svm->next_rip) {
+		/*
+		 * FIXME: Drop this when kvm_emulate_instruction() does the
+		 * right thing and treats "can't emulate" as outright failure
+		 * for EMULTYPE_SKIP.
+		 */
+		if (!svm_can_emulate_instruction(vcpu, EMULTYPE_SKIP, NULL, 0))
+			return 0;
+
 		if (unlikely(!commit_side_effects))
 			old_rflags = svm->vmcb->save.rflags;
 
@@ -4677,16 +4687,25 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
 	 * and cannot be decrypted by KVM, i.e. KVM would read cyphertext and
 	 * decode garbage.
 	 *
-	 * Inject #UD if KVM reached this point without an instruction buffer.
-	 * In practice, this path should never be hit by a well-behaved guest,
-	 * e.g. KVM doesn't intercept #UD or #GP for SEV guests, but this path
-	 * is still theoretically reachable, e.g. via unaccelerated fault-like
-	 * AVIC access, and needs to be handled by KVM to avoid putting the
-	 * guest into an infinite loop.   Injecting #UD is somewhat arbitrary,
-	 * but its the least awful option given lack of insight into the guest.
+	 * If KVM is NOT trying to simply skip an instruction, inject #UD if
+	 * KVM reached this point without an instruction buffer.  In practice,
+	 * this path should never be hit by a well-behaved guest, e.g. KVM
+	 * doesn't intercept #UD or #GP for SEV guests, but this path is still
+	 * theoretically reachable, e.g. via unaccelerated fault-like AVIC
+	 * access, and needs to be handled by KVM to avoid putting the guest
+	 * into an infinite loop.   Injecting #UD is somewhat arbitrary, but
+	 * its the least awful option given lack of insight into the guest.
+	 *
+	 * If KVM is trying to skip an instruction, simply resume the guest.
+	 * If a #NPF occurs while the guest is vectoring an INT3/INTO, then KVM
+	 * will attempt to re-inject the INT3/INTO and skip the instruction.
+	 * In that scenario, retrying the INT3/INTO and hoping the guest will
+	 * make forward progress is the only option that has a chance of
+	 * success (and in practice it will work the vast majority of the time).
 	 */
 	if (unlikely(!insn)) {
-		kvm_queue_exception(vcpu, UD_VECTOR);
+		if (!(emul_type & EMULTYPE_SKIP))
+			kvm_queue_exception(vcpu, UD_VECTOR);
 		return false;
 	}
 

From 80d0f521d59e08eeaa0bc5d624da139448fb99b8 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 24 Aug 2023 18:36:19 -0700
Subject: [PATCH 0707/1189] KVM: SVM: Require nrips support for SEV guests (and
 beyond)

Disallow SEV (and beyond) if nrips is disabled via module param, as KVM
can't read guest memory to partially emulate and skip an instruction.  All
CPUs that support SEV support NRIPS, i.e. this is purely stopping the user
from shooting themselves in the foot.

Cc: Tom Lendacky <thomas.lendacky@amd.com>
Link: https://lore.kernel.org/r/20230825013621.2845700-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/sev.c |  2 +-
 arch/x86/kvm/svm/svm.c | 11 ++++-------
 arch/x86/kvm/svm/svm.h |  1 +
 3 files changed, 6 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 5585a3556179..85d1abdf7d7d 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2185,7 +2185,7 @@ void __init sev_hardware_setup(void)
 	bool sev_es_supported = false;
 	bool sev_supported = false;
 
-	if (!sev_enabled || !npt_enabled)
+	if (!sev_enabled || !npt_enabled || !nrips)
 		goto out;
 
 	/*
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index d7a474571ff1..5cf2380c89dd 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -203,7 +203,7 @@ static int nested = true;
 module_param(nested, int, S_IRUGO);
 
 /* enable/disable Next RIP Save */
-static int nrips = true;
+int nrips = true;
 module_param(nrips, int, 0444);
 
 /* enable/disable Virtual VMLOAD VMSAVE */
@@ -5156,9 +5156,11 @@ static __init int svm_hardware_setup(void)
 
 	svm_adjust_mmio_mask();
 
+	nrips = nrips && boot_cpu_has(X86_FEATURE_NRIPS);
+
 	/*
 	 * Note, SEV setup consumes npt_enabled and enable_mmio_caching (which
-	 * may be modified by svm_adjust_mmio_mask()).
+	 * may be modified by svm_adjust_mmio_mask()), as well as nrips.
 	 */
 	sev_hardware_setup();
 
@@ -5170,11 +5172,6 @@ static __init int svm_hardware_setup(void)
 			goto err;
 	}
 
-	if (nrips) {
-		if (!boot_cpu_has(X86_FEATURE_NRIPS))
-			nrips = false;
-	}
-
 	enable_apicv = avic = avic && avic_hardware_setup();
 
 	if (!enable_apicv) {
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 800ca1776b59..1498956a589f 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -33,6 +33,7 @@
 #define MSRPM_OFFSETS	32
 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
 extern bool npt_enabled;
+extern int nrips;
 extern int vgif;
 extern bool intercept_smi;
 extern bool x2avic_enabled;

From 5002b112a5ad23579b7c3a36c9748740bcdfc88e Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 17 Aug 2023 16:34:29 -0700
Subject: [PATCH 0708/1189] KVM: selftests: Reload "good" vCPU state if vCPU
 hits shutdown

Reload known good vCPU state if the vCPU triple faults in any of the
race_sync_regs() subtests, e.g. if KVM successfully injects an exception
(the vCPU isn't configured to handle exceptions).  On Intel, the VMCS
is preserved even after shutdown, but AMD's APM states that the VMCB is
undefined after a shutdown and so KVM synthesizes an INIT to sanitize
vCPU/VMCB state, e.g. to guard against running with a garbage VMCB.

The synthetic INIT results in the vCPU never exiting to userspace, as it
gets put into Real Mode at the reset vector, which is full of zeros (as is
GPA 0 and beyond), and so executes ADD for a very, very long time.

Fixes: 60c4063b4752 ("KVM: selftests: Extend x86's sync_regs_test to check for event vector races")
Cc: Michal Luczaj <mhal@rbox.co>
Link: https://lore.kernel.org/r/20230817233430.1416463-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../testing/selftests/kvm/x86_64/sync_regs_test.c  | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
index 93fac74ca0a7..21e99dae2ff2 100644
--- a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
@@ -152,6 +152,7 @@ static noinline void *race_sregs_cr4(void *arg)
 static void race_sync_regs(void *racer)
 {
 	const time_t TIMEOUT = 2; /* seconds, roughly */
+	struct kvm_x86_state *state;
 	struct kvm_translation tr;
 	struct kvm_vcpu *vcpu;
 	struct kvm_run *run;
@@ -166,6 +167,9 @@ static void race_sync_regs(void *racer)
 	vcpu_run(vcpu);
 	run->kvm_valid_regs = 0;
 
+	/* Save state *before* spawning the thread that mucks with vCPU state. */
+	state = vcpu_save_state(vcpu);
+
 	/*
 	 * Selftests run 64-bit guests by default, both EFER.LME and CR4.PAE
 	 * should already be set in guest state.
@@ -179,7 +183,14 @@ static void race_sync_regs(void *racer)
 	TEST_ASSERT_EQ(pthread_create(&thread, NULL, racer, (void *)run), 0);
 
 	for (t = time(NULL) + TIMEOUT; time(NULL) < t;) {
-		__vcpu_run(vcpu);
+		/*
+		 * Reload known good state if the vCPU triple faults, e.g. due
+		 * to the unhandled #GPs being injected.  VMX preserves state
+		 * on shutdown, but SVM synthesizes an INIT as the VMCB state
+		 * is architecturally undefined on triple fault.
+		 */
+		if (!__vcpu_run(vcpu) && run->exit_reason == KVM_EXIT_SHUTDOWN)
+			vcpu_load_state(vcpu, state);
 
 		if (racer == race_sregs_cr4) {
 			tr = (struct kvm_translation) { .linear_address = 0 };
@@ -190,6 +201,7 @@ static void race_sync_regs(void *racer)
 	TEST_ASSERT_EQ(pthread_cancel(thread), 0);
 	TEST_ASSERT_EQ(pthread_join(thread, NULL), 0);
 
+	kvm_x86_state_cleanup(state);
 	kvm_vm_free(vm);
 }
 

From 02dc2543e3795867260826983bf3f20b282c8fc3 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 17 Aug 2023 16:34:30 -0700
Subject: [PATCH 0709/1189] KVM: selftests: Explicit set #UD when *potentially*
 injecting exception

Explicitly set the exception vector to #UD when potentially injecting an
exception in sync_regs_test's subtests that try to detect TOCTOU bugs
in KVM's handling of exceptions injected by userspace.  A side effect of
the original KVM bug was that KVM would clear the vector, but relying on
KVM to clear the vector (i.e. make it #DE) makes it less likely that the
test would ever find *new* KVM bugs, e.g. because only the first iteration
would run with a legal vector to start.

Explicitly inject #UD for race_events_inj_pen() as well, e.g. so that it
doesn't inherit the illegal 255 vector from race_events_exc(), which
currently runs first.

Link: https://lore.kernel.org/r/20230817233430.1416463-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/x86_64/sync_regs_test.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
index 21e99dae2ff2..00965ba33f73 100644
--- a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
@@ -91,6 +91,8 @@ static void *race_events_inj_pen(void *arg)
 	struct kvm_run *run = (struct kvm_run *)arg;
 	struct kvm_vcpu_events *events = &run->s.regs.events;
 
+	WRITE_ONCE(events->exception.nr, UD_VECTOR);
+
 	for (;;) {
 		WRITE_ONCE(run->kvm_dirty_regs, KVM_SYNC_X86_EVENTS);
 		WRITE_ONCE(events->flags, 0);
@@ -115,6 +117,7 @@ static void *race_events_exc(void *arg)
 	for (;;) {
 		WRITE_ONCE(run->kvm_dirty_regs, KVM_SYNC_X86_EVENTS);
 		WRITE_ONCE(events->flags, 0);
+		WRITE_ONCE(events->exception.nr, UD_VECTOR);
 		WRITE_ONCE(events->exception.pending, 1);
 		WRITE_ONCE(events->exception.nr, 255);
 

From c92b922a8c526e1bb11945a703cba9f85976de7e Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 17 Aug 2023 16:41:14 -0700
Subject: [PATCH 0710/1189] KVM: x86: Update MAINTAINTERS to include selftests

Give KVM x86 the same treatment as all other KVM architectures, and
officially take ownership of x86 specific KVM selftests (changes have
been routed through kvm and/or kvm-x86 for quite some time).

Cc: kvm@vger.kernel.org
Link: https://lore.kernel.org/r/20230817234114.1420092-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 MAINTAINERS | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index aee340630eca..2adf76b044c8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11498,6 +11498,8 @@ F:	arch/x86/include/uapi/asm/svm.h
 F:	arch/x86/include/uapi/asm/vmx.h
 F:	arch/x86/kvm/
 F:	arch/x86/kvm/*/
+F:	tools/testing/selftests/kvm/*/x86_64/
+F:	tools/testing/selftests/kvm/x86_64/
 
 KERNFS
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>

From 9ca0c1a1265c03d54f1c71005ea0375f9bccabee Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 15 Aug 2023 10:42:15 -0700
Subject: [PATCH 0711/1189] KVM: VMX: Delete ancient pr_warn() about
 KVM_SET_TSS_ADDR not being set

Delete KVM's printk about KVM_SET_TSS_ADDR not being called.  When the
printk was added by commit 776e58ea3d37 ("KVM: unbreak userspace that does
not sets tss address"), KVM also stuffed a "hopefully safe" value, i.e.
the message wasn't purely informational.  For reasons unknown, ostensibly
to try and help people running outdated qemu-kvm versions, the message got
left behind when KVM's stuffing was removed by commit 4918c6ca6838
("KVM: VMX: Require KVM_SET_TSS_ADDR being called prior to running a VCPU").

Today, the message is completely nonsensical, as it has been over a decade
since KVM supported userspace running a Real Mode guest, on a CPU without
unrestricted guest support, without doing KVM_SET_TSS_ADDR before KVM_RUN.
I.e. KVM's ABI has required KVM_SET_TSS_ADDR for 10+ years.

To make matters worse, the message is prone to false positives as it
triggers when simply *creating* a vCPU due to RESET putting vCPUs into
Real Mode, even when the user has no intention of ever *running* the vCPU
in a Real Mode.  E.g. KVM selftests stuff 64-bit mode and never touch Real
Mode, but trigger the message even though they run just fine without
doing KVM_SET_TSS_ADDR.  Creating "dummy" vCPUs, e.g. to probe features,
can also trigger the message.  In both scenarios, the message confuses
users and falsely implies that they've done something wrong.

Reported-by: Thorsten Glaser <t.glaser@tarent.de>
Closes: https://lkml.kernel.org/r/f1afa6c0-cde2-ab8b-ea71-bfa62a45b956%40tarent.de
Link: https://lore.kernel.org/r/20230815174215.433222-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/vmx/vmx.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index f848f43fa3e2..b0093b8a72d2 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -3047,13 +3047,6 @@ static void enter_rmode(struct kvm_vcpu *vcpu)
 
 	vmx->rmode.vm86_active = 1;
 
-	/*
-	 * Very old userspace does not call KVM_SET_TSS_ADDR before entering
-	 * vcpu. Warn the user that an update is overdue.
-	 */
-	if (!kvm_vmx->tss_addr)
-		pr_warn_once("KVM_SET_TSS_ADDR needs to be called before running vCPU\n");
-
 	vmx_segment_cache_clear(vmx);
 
 	vmcs_writel(GUEST_TR_BASE, kvm_vmx->tss_addr);

From 27177862de9676c8c35b86bf89c38864fbe5ed71 Mon Sep 17 00:00:00 2001
From: Nilesh Javali <njavali@marvell.com>
Date: Thu, 24 Aug 2023 20:45:21 +0530
Subject: [PATCH 0712/1189] scsi: qla2xxx: Fix nvme_fc_rcv_ls_req() undefined
 error

The kernel robot reported below build error,

>> ERROR: modpost: "nvme_fc_rcv_ls_req" [drivers/scsi/qla2xxx/qla2xxx.ko] undefined!

Use CONFIG_NVME_FC enabled check to fix the build error.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202308021445.txlNq7UC-lkp@intel.com/
Signed-off-by: Nilesh Javali <njavali@marvell.com>
Link: https://lore.kernel.org/r/20230824151521.35261-1-njavali@marvell.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_nvme.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c
index 1a31e877e6cb..62a67662cbf3 100644
--- a/drivers/scsi/qla2xxx/qla_nvme.c
+++ b/drivers/scsi/qla2xxx/qla_nvme.c
@@ -1182,10 +1182,12 @@ qla2xxx_process_purls_pkt(struct scsi_qla_host *vha, struct purex_item *item)
 	struct qla_nvme_unsol_ctx *uctx = item->purls_context;
 	fc_port_t *fcport = uctx->fcport;
 	struct qla_nvme_lsrjt_pt_arg a;
-	int ret;
+	int ret = 1;
 
+#if (IS_ENABLED(CONFIG_NVME_FC))
 	ret = nvme_fc_rcv_ls_req(fcport->nvme_remote_port, &uctx->lsrsp,
 				 &item->iocb, item->size);
+#endif
 	if (ret) {
 		ql_dbg(ql_dbg_unsol, vha, 0x2125, "NVMe tranport ls_req failed\n");
 		memset((void *)&a, 0, sizeof(a));

From 659d36cc732a7de8c6ca2ae347db1a5401a1b93c Mon Sep 17 00:00:00 2001
From: Nilesh Javali <njavali@marvell.com>
Date: Fri, 25 Aug 2023 12:30:17 +0530
Subject: [PATCH 0713/1189] scsi: qla2xxx: Remove unused variables in
 qla24xx_build_scsi_type_6_iocbs()

Sparse warning reported,

drivers/scsi/qla2xxx/qla_iocb.c: In function 'qla24xx_build_scsi_type_6_iocbs':
>> drivers/scsi/qla2xxx/qla_iocb.c:594:29: warning: variable 'ha' set but not used [-Wunused-but-set-variable]
     594 |         struct qla_hw_data *ha;
         |                             ^~

Remove unused variables 'vha' and 'ha'.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202308230757.VKMIztAB-lkp@intel.com/
Signed-off-by: Nilesh Javali <njavali@marvell.com>
Link: https://lore.kernel.org/r/20230825070017.46066-1-njavali@marvell.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_iocb.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index 7fbd917f6e1f..4450c0d000cc 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -591,8 +591,6 @@ qla24xx_build_scsi_type_6_iocbs(srb_t *sp, struct cmd_type_6 *cmd_pkt,
 	uint16_t tot_dsds)
 {
 	struct dsd64 *cur_dsd = NULL, *next_dsd;
-	scsi_qla_host_t	*vha;
-	struct qla_hw_data *ha;
 	struct scsi_cmnd *cmd;
 	struct	scatterlist *cur_seg;
 	uint8_t avail_dsds;
@@ -614,9 +612,6 @@ qla24xx_build_scsi_type_6_iocbs(srb_t *sp, struct cmd_type_6 *cmd_pkt,
 		return 0;
 	}
 
-	vha = sp->vha;
-	ha = vha->hw;
-
 	/* Set transfer direction */
 	if (cmd->sc_data_direction == DMA_TO_DEVICE) {
 		cmd_pkt->control_flags = cpu_to_le16(CF_WRITE_DATA);

From 15924b0503630016dee4dbb945a8df4df659070b Mon Sep 17 00:00:00 2001
From: Karan Tilak Kumar <kartilak@cisco.com>
Date: Thu, 17 Aug 2023 11:21:46 -0700
Subject: [PATCH 0714/1189] scsi: fnic: Replace sgreset tag with max_tag_id

sgreset is issued with a SCSI command pointer. The device reset code
assumes that it was issued on a hardware queue, and calls block multiqueue
layer. However, the assumption is broken, and there is no hardware queue
associated with the sgreset, and this leads to a crash due to a null
pointer exception.

Fix the code to use the max_tag_id as a tag which does not overlap with the
other tags issued by mid layer.

Tested by running FC traffic for a few minutes, and by issuing sgreset on
the device in parallel.  Without the fix, the crash is observed right away.
With this fix, no crash is observed.

Reviewed-by: Sesidhar Baddela <sebaddel@cisco.com>
Tested-by: Karan Tilak Kumar <kartilak@cisco.com>
Signed-off-by: Karan Tilak Kumar <kartilak@cisco.com>
Link: https://lore.kernel.org/r/20230817182146.229059-1-kartilak@cisco.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/fnic/fnic.h      |  3 ++-
 drivers/scsi/fnic/fnic_scsi.c | 20 +++++++++-----------
 2 files changed, 11 insertions(+), 12 deletions(-)

diff --git a/drivers/scsi/fnic/fnic.h b/drivers/scsi/fnic/fnic.h
index d82de34f6fd7..93c68931a593 100644
--- a/drivers/scsi/fnic/fnic.h
+++ b/drivers/scsi/fnic/fnic.h
@@ -27,7 +27,7 @@
 
 #define DRV_NAME		"fnic"
 #define DRV_DESCRIPTION		"Cisco FCoE HBA Driver"
-#define DRV_VERSION		"1.6.0.54"
+#define DRV_VERSION		"1.6.0.56"
 #define PFX			DRV_NAME ": "
 #define DFX                     DRV_NAME "%d: "
 
@@ -236,6 +236,7 @@ struct fnic {
 	unsigned int wq_count;
 	unsigned int cq_count;
 
+	struct mutex sgreset_mutex;
 	struct dentry *fnic_stats_debugfs_host;
 	struct dentry *fnic_stats_debugfs_file;
 	struct dentry *fnic_reset_debugfs_file;
diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c
index 26dbd347156e..8ce3e3c3a882 100644
--- a/drivers/scsi/fnic/fnic_scsi.c
+++ b/drivers/scsi/fnic/fnic_scsi.c
@@ -2220,7 +2220,6 @@ int fnic_device_reset(struct scsi_cmnd *sc)
 	struct reset_stats *reset_stats;
 	int tag = rq->tag;
 	DECLARE_COMPLETION_ONSTACK(tm_done);
-	int tag_gen_flag = 0;   /*to track tags allocated by fnic driver*/
 	bool new_sc = 0;
 
 	/* Wait for rport to unblock */
@@ -2250,17 +2249,17 @@ int fnic_device_reset(struct scsi_cmnd *sc)
 	}
 
 	fnic_priv(sc)->flags = FNIC_DEVICE_RESET;
-	/* Allocate tag if not present */
 
 	if (unlikely(tag < 0)) {
 		/*
-		 * Really should fix the midlayer to pass in a proper
-		 * request for ioctls...
+		 * For device reset issued through sg3utils, we let
+		 * only one LUN_RESET to go through and use a special
+		 * tag equal to max_tag_id so that we don't have to allocate
+		 * or free it. It won't interact with tags
+		 * allocated by mid layer.
 		 */
-		tag = fnic_scsi_host_start_tag(fnic, sc);
-		if (unlikely(tag == SCSI_NO_TAG))
-			goto fnic_device_reset_end;
-		tag_gen_flag = 1;
+		mutex_lock(&fnic->sgreset_mutex);
+		tag = fnic->fnic_max_tag_id;
 		new_sc = 1;
 	}
 	io_lock = fnic_io_lock_hash(fnic, sc);
@@ -2432,9 +2431,8 @@ fnic_device_reset_end:
 		  (u64)sc->cmnd[4] << 8 | sc->cmnd[5]),
 		  fnic_flags_and_state(sc));
 
-	/* free tag if it is allocated */
-	if (unlikely(tag_gen_flag))
-		fnic_scsi_host_end_tag(fnic, sc);
+	if (new_sc)
+		mutex_unlock(&fnic->sgreset_mutex);
 
 	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
 		      "Returning from device reset %s\n",

From f156a7d13fc35d0078cd644b8cf0a6f97cbbe2e2 Mon Sep 17 00:00:00 2001
From: Vincent Donnefort <vdonnefort@google.com>
Date: Fri, 11 Aug 2023 12:20:37 +0100
Subject: [PATCH 0715/1189] KVM: arm64: Remove size-order align in the nVHE hyp
 private VA range

commit f922c13e778d ("KVM: arm64: Introduce
pkvm_alloc_private_va_range()") and commit 92abe0f81e13 ("KVM: arm64:
Introduce hyp_alloc_private_va_range()") added an alignment for the
start address of any allocation into the nVHE hypervisor private VA
range.

This alignment (order of the size of the allocation) intends to enable
efficient stack verification (if the PAGE_SHIFT bit is zero, the stack
pointer is on the guard page and a stack overflow occurred).

But this is only necessary for stack allocation and can waste a lot of
VA space. So instead make stack-specific functions, handling the guard
page requirements, while other users (e.g.  fixmap) will only get page
alignment.

Reviewed-by: Kalesh Singh <kaleshsingh@google.com>
Signed-off-by: Vincent Donnefort <vdonnefort@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230811112037.1147863-1-vdonnefort@google.com
---
 arch/arm64/include/asm/kvm_mmu.h     |  1 +
 arch/arm64/kvm/arm.c                 | 26 +--------
 arch/arm64/kvm/hyp/include/nvhe/mm.h |  1 +
 arch/arm64/kvm/hyp/nvhe/mm.c         | 83 +++++++++++++++++++++------
 arch/arm64/kvm/hyp/nvhe/setup.c      | 27 +--------
 arch/arm64/kvm/mmu.c                 | 85 ++++++++++++++++++++++------
 6 files changed, 138 insertions(+), 85 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 0e1e1ab17b4d..96a80e8f6226 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -168,6 +168,7 @@ int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size,
 			   void __iomem **haddr);
 int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
 			     void **haddr);
+int create_hyp_stack(phys_addr_t phys_addr, unsigned long *haddr);
 void __init free_hyp_pgds(void);
 
 void stage2_unmap_vm(struct kvm *kvm);
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 3c015bdd35ee..93ada0aae507 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -2283,30 +2283,8 @@ static int __init init_hyp_mode(void)
 	for_each_possible_cpu(cpu) {
 		struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu);
 		char *stack_page = (char *)per_cpu(kvm_arm_hyp_stack_page, cpu);
-		unsigned long hyp_addr;
 
-		/*
-		 * Allocate a contiguous HYP private VA range for the stack
-		 * and guard page. The allocation is also aligned based on
-		 * the order of its size.
-		 */
-		err = hyp_alloc_private_va_range(PAGE_SIZE * 2, &hyp_addr);
-		if (err) {
-			kvm_err("Cannot allocate hyp stack guard page\n");
-			goto out_err;
-		}
-
-		/*
-		 * Since the stack grows downwards, map the stack to the page
-		 * at the higher address and leave the lower guard page
-		 * unbacked.
-		 *
-		 * Any valid stack address now has the PAGE_SHIFT bit as 1
-		 * and addresses corresponding to the guard page have the
-		 * PAGE_SHIFT bit as 0 - this is used for overflow detection.
-		 */
-		err = __create_hyp_mappings(hyp_addr + PAGE_SIZE, PAGE_SIZE,
-					    __pa(stack_page), PAGE_HYP);
+		err = create_hyp_stack(__pa(stack_page), &params->stack_hyp_va);
 		if (err) {
 			kvm_err("Cannot map hyp stack\n");
 			goto out_err;
@@ -2319,8 +2297,6 @@ static int __init init_hyp_mode(void)
 		 * has been mapped in the flexible private VA space.
 		 */
 		params->stack_pa = __pa(stack_page);
-
-		params->stack_hyp_va = hyp_addr + (2 * PAGE_SIZE);
 	}
 
 	for_each_possible_cpu(cpu) {
diff --git a/arch/arm64/kvm/hyp/include/nvhe/mm.h b/arch/arm64/kvm/hyp/include/nvhe/mm.h
index d5ec972b5c1e..230e4f2527de 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/mm.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/mm.h
@@ -26,6 +26,7 @@ int pkvm_create_mappings_locked(void *from, void *to, enum kvm_pgtable_prot prot
 int __pkvm_create_private_mapping(phys_addr_t phys, size_t size,
 				  enum kvm_pgtable_prot prot,
 				  unsigned long *haddr);
+int pkvm_create_stack(phys_addr_t phys, unsigned long *haddr);
 int pkvm_alloc_private_va_range(size_t size, unsigned long *haddr);
 
 #endif /* __KVM_HYP_MM_H */
diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c
index 318298eb3d6b..65a7a186d7b2 100644
--- a/arch/arm64/kvm/hyp/nvhe/mm.c
+++ b/arch/arm64/kvm/hyp/nvhe/mm.c
@@ -44,6 +44,27 @@ static int __pkvm_create_mappings(unsigned long start, unsigned long size,
 	return err;
 }
 
+static int __pkvm_alloc_private_va_range(unsigned long start, size_t size)
+{
+	unsigned long cur;
+
+	hyp_assert_lock_held(&pkvm_pgd_lock);
+
+	if (!start || start < __io_map_base)
+		return -EINVAL;
+
+	/* The allocated size is always a multiple of PAGE_SIZE */
+	cur = start + PAGE_ALIGN(size);
+
+	/* Are we overflowing on the vmemmap ? */
+	if (cur > __hyp_vmemmap)
+		return -ENOMEM;
+
+	__io_map_base = cur;
+
+	return 0;
+}
+
 /**
  * pkvm_alloc_private_va_range - Allocates a private VA range.
  * @size:	The size of the VA range to reserve.
@@ -56,27 +77,16 @@ static int __pkvm_create_mappings(unsigned long start, unsigned long size,
  */
 int pkvm_alloc_private_va_range(size_t size, unsigned long *haddr)
 {
-	unsigned long base, addr;
-	int ret = 0;
+	unsigned long addr;
+	int ret;
 
 	hyp_spin_lock(&pkvm_pgd_lock);
-
-	/* Align the allocation based on the order of its size */
-	addr = ALIGN(__io_map_base, PAGE_SIZE << get_order(size));
-
-	/* The allocated size is always a multiple of PAGE_SIZE */
-	base = addr + PAGE_ALIGN(size);
-
-	/* Are we overflowing on the vmemmap ? */
-	if (!addr || base > __hyp_vmemmap)
-		ret = -ENOMEM;
-	else {
-		__io_map_base = base;
-		*haddr = addr;
-	}
-
+	addr = __io_map_base;
+	ret = __pkvm_alloc_private_va_range(addr, size);
 	hyp_spin_unlock(&pkvm_pgd_lock);
 
+	*haddr = addr;
+
 	return ret;
 }
 
@@ -340,6 +350,45 @@ int hyp_create_idmap(u32 hyp_va_bits)
 	return __pkvm_create_mappings(start, end - start, start, PAGE_HYP_EXEC);
 }
 
+int pkvm_create_stack(phys_addr_t phys, unsigned long *haddr)
+{
+	unsigned long addr, prev_base;
+	size_t size;
+	int ret;
+
+	hyp_spin_lock(&pkvm_pgd_lock);
+
+	prev_base = __io_map_base;
+	/*
+	 * Efficient stack verification using the PAGE_SHIFT bit implies
+	 * an alignment of our allocation on the order of the size.
+	 */
+	size = PAGE_SIZE * 2;
+	addr = ALIGN(__io_map_base, size);
+
+	ret = __pkvm_alloc_private_va_range(addr, size);
+	if (!ret) {
+		/*
+		 * Since the stack grows downwards, map the stack to the page
+		 * at the higher address and leave the lower guard page
+		 * unbacked.
+		 *
+		 * Any valid stack address now has the PAGE_SHIFT bit as 1
+		 * and addresses corresponding to the guard page have the
+		 * PAGE_SHIFT bit as 0 - this is used for overflow detection.
+		 */
+		ret = kvm_pgtable_hyp_map(&pkvm_pgtable, addr + PAGE_SIZE,
+					  PAGE_SIZE, phys, PAGE_HYP);
+		if (ret)
+			__io_map_base = prev_base;
+	}
+	hyp_spin_unlock(&pkvm_pgd_lock);
+
+	*haddr = addr + size;
+
+	return ret;
+}
+
 static void *admit_host_page(void *arg)
 {
 	struct kvm_hyp_memcache *host_mc = arg;
diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
index bb98630dfeaf..0d5e0a89ddce 100644
--- a/arch/arm64/kvm/hyp/nvhe/setup.c
+++ b/arch/arm64/kvm/hyp/nvhe/setup.c
@@ -113,7 +113,6 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
 
 	for (i = 0; i < hyp_nr_cpus; i++) {
 		struct kvm_nvhe_init_params *params = per_cpu_ptr(&kvm_init_params, i);
-		unsigned long hyp_addr;
 
 		start = (void *)kern_hyp_va(per_cpu_base[i]);
 		end = start + PAGE_ALIGN(hyp_percpu_size);
@@ -121,33 +120,9 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
 		if (ret)
 			return ret;
 
-		/*
-		 * Allocate a contiguous HYP private VA range for the stack
-		 * and guard page. The allocation is also aligned based on
-		 * the order of its size.
-		 */
-		ret = pkvm_alloc_private_va_range(PAGE_SIZE * 2, &hyp_addr);
+		ret = pkvm_create_stack(params->stack_pa, &params->stack_hyp_va);
 		if (ret)
 			return ret;
-
-		/*
-		 * Since the stack grows downwards, map the stack to the page
-		 * at the higher address and leave the lower guard page
-		 * unbacked.
-		 *
-		 * Any valid stack address now has the PAGE_SHIFT bit as 1
-		 * and addresses corresponding to the guard page have the
-		 * PAGE_SHIFT bit as 0 - this is used for overflow detection.
-		 */
-		hyp_spin_lock(&pkvm_pgd_lock);
-		ret = kvm_pgtable_hyp_map(&pkvm_pgtable, hyp_addr + PAGE_SIZE,
-					PAGE_SIZE, params->stack_pa, PAGE_HYP);
-		hyp_spin_unlock(&pkvm_pgd_lock);
-		if (ret)
-			return ret;
-
-		/* Update stack_hyp_va to end of the stack's private VA range */
-		params->stack_hyp_va = hyp_addr + (2 * PAGE_SIZE);
 	}
 
 	/*
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 137b775d238b..499555e04732 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -592,6 +592,25 @@ int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot)
 	return 0;
 }
 
+static int __hyp_alloc_private_va_range(unsigned long base)
+{
+	lockdep_assert_held(&kvm_hyp_pgd_mutex);
+
+	if (!PAGE_ALIGNED(base))
+		return -EINVAL;
+
+	/*
+	 * Verify that BIT(VA_BITS - 1) hasn't been flipped by
+	 * allocating the new area, as it would indicate we've
+	 * overflowed the idmap/IO address range.
+	 */
+	if ((base ^ io_map_base) & BIT(VA_BITS - 1))
+		return -ENOMEM;
+
+	io_map_base = base;
+
+	return 0;
+}
 
 /**
  * hyp_alloc_private_va_range - Allocates a private VA range.
@@ -612,26 +631,16 @@ int hyp_alloc_private_va_range(size_t size, unsigned long *haddr)
 
 	/*
 	 * This assumes that we have enough space below the idmap
-	 * page to allocate our VAs. If not, the check below will
-	 * kick. A potential alternative would be to detect that
-	 * overflow and switch to an allocation above the idmap.
+	 * page to allocate our VAs. If not, the check in
+	 * __hyp_alloc_private_va_range() will kick. A potential
+	 * alternative would be to detect that overflow and switch
+	 * to an allocation above the idmap.
 	 *
 	 * The allocated size is always a multiple of PAGE_SIZE.
 	 */
-	base = io_map_base - PAGE_ALIGN(size);
-
-	/* Align the allocation based on the order of its size */
-	base = ALIGN_DOWN(base, PAGE_SIZE << get_order(size));
-
-	/*
-	 * Verify that BIT(VA_BITS - 1) hasn't been flipped by
-	 * allocating the new area, as it would indicate we've
-	 * overflowed the idmap/IO address range.
-	 */
-	if ((base ^ io_map_base) & BIT(VA_BITS - 1))
-		ret = -ENOMEM;
-	else
-		*haddr = io_map_base = base;
+	size = PAGE_ALIGN(size);
+	base = io_map_base - size;
+	ret = __hyp_alloc_private_va_range(base);
 
 	mutex_unlock(&kvm_hyp_pgd_mutex);
 
@@ -668,6 +677,48 @@ static int __create_hyp_private_mapping(phys_addr_t phys_addr, size_t size,
 	return ret;
 }
 
+int create_hyp_stack(phys_addr_t phys_addr, unsigned long *haddr)
+{
+	unsigned long base;
+	size_t size;
+	int ret;
+
+	mutex_lock(&kvm_hyp_pgd_mutex);
+	/*
+	 * Efficient stack verification using the PAGE_SHIFT bit implies
+	 * an alignment of our allocation on the order of the size.
+	 */
+	size = PAGE_SIZE * 2;
+	base = ALIGN_DOWN(io_map_base - size, size);
+
+	ret = __hyp_alloc_private_va_range(base);
+
+	mutex_unlock(&kvm_hyp_pgd_mutex);
+
+	if (ret) {
+		kvm_err("Cannot allocate hyp stack guard page\n");
+		return ret;
+	}
+
+	/*
+	 * Since the stack grows downwards, map the stack to the page
+	 * at the higher address and leave the lower guard page
+	 * unbacked.
+	 *
+	 * Any valid stack address now has the PAGE_SHIFT bit as 1
+	 * and addresses corresponding to the guard page have the
+	 * PAGE_SHIFT bit as 0 - this is used for overflow detection.
+	 */
+	ret = __create_hyp_mappings(base + PAGE_SIZE, PAGE_SIZE, phys_addr,
+				    PAGE_HYP);
+	if (ret)
+		kvm_err("Cannot map hyp stack\n");
+
+	*haddr = base + size;
+
+	return ret;
+}
+
 /**
  * create_hyp_io_mappings - Map IO into both kernel and HYP
  * @phys_addr:	The physical start address which gets mapped

From 45cc2a7de905a1f3bb38fb7d6f68a204c71630be Mon Sep 17 00:00:00 2001
From: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Date: Fri, 25 Aug 2023 07:39:10 +0200
Subject: [PATCH 0716/1189] MAINTAINERS: remove obsolete pattern in RTC
 SUBSYSTEM section

Commit d890cfc25fe9 ("rtc: ds2404: Convert to GPIO descriptors") removes
the rtc-ds2404.h platform data and with that, there is no file remaining
matching the pattern 'include/linux/platform_data/rtc-*'. Hence,
./scripts/get_maintainer.pl --self-test=patterns complains about a broken
reference.

Remove the obsolete file pattern in the REAL TIME CLOCK (RTC) SUBSYSTEM.

Signed-off-by: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20230825053910.17941-1-lukas.bulwahn@gmail.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 3be1bdfe8ecc..03cbac3b7211 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17928,7 +17928,6 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/abelloni/linux.git
 F:	Documentation/admin-guide/rtc.rst
 F:	Documentation/devicetree/bindings/rtc/
 F:	drivers/rtc/
-F:	include/linux/platform_data/rtc-*
 F:	include/linux/rtc.h
 F:	include/linux/rtc/
 F:	include/uapi/linux/rtc.h

From f45d32d2cd183c09b6c9aa8689a91d6f2760b557 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Thu, 17 Aug 2023 17:10:38 +0100
Subject: [PATCH 0717/1189] rtc: isl1208: Fix incorrect logic in
 isl1208_set_xtoscb()

The XTOSCB bit is not bit 0, but xtosb_val is either 0 or 1. If it is 1,
test will never succeed. Fix this issue by using double negation.

While at it, remove unnecessary blank line from probe().

Reported-by: Pavel Machek <pavel@denx.de>
Closes: https://lore.kernel.org/all/ZN4BgzG2xmzOzdFZ@duo.ucw.cz/
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Reviewed-by: Pavel Machek <pavel@denx.de>
Link: https://lore.kernel.org/r/20230817161038.407960-1-biju.das.jz@bp.renesas.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-isl1208.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/rtc/rtc-isl1208.c b/drivers/rtc/rtc-isl1208.c
index 712ca652d6d3..e50c23ee1646 100644
--- a/drivers/rtc/rtc-isl1208.c
+++ b/drivers/rtc/rtc-isl1208.c
@@ -188,7 +188,7 @@ isl1208_i2c_validate_client(struct i2c_client *client)
 static int isl1208_set_xtoscb(struct i2c_client *client, int sr, int xtosb_val)
 {
 	/* Do nothing if bit is already set to desired value */
-	if ((sr & ISL1208_REG_SR_XTOSCB) == xtosb_val)
+	if (!!(sr & ISL1208_REG_SR_XTOSCB) == xtosb_val)
 		return 0;
 
 	if (xtosb_val)
@@ -944,7 +944,6 @@ isl1208_probe(struct i2c_client *client)
 		rc = isl1208_setup_irq(client, client->irq);
 		if (rc)
 			return rc;
-
 	} else {
 		clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, isl1208->rtc->features);
 	}

From 781589e40ac5f929f58824c15448e1ba49c3ac32 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Thu, 17 Aug 2023 15:55:31 -0700
Subject: [PATCH 0718/1189] rtc: Add support for limited alarm timer offsets

Some alarm timers are based on time offsets, not on absolute times.
In some situations, the amount of time that can be scheduled in the
future is limited. This may result in a refusal to suspend the system,
causing substantial battery drain.

Some RTC alarm drivers remedy the situation by setting the alarm time
to the maximum supported time if a request for an out-of-range timeout
is made. This is not really desirable since it may result in unexpected
early wakeups.

To reduce the impact of this problem, let RTC drivers report the maximum
supported alarm timer offset. The code setting alarm timers can then
decide if it wants to reject setting alarm timers to a larger value, if it
wants to implement recurring alarms until the actually requested alarm
time is met, or if it wants to accept the limited alarm time.

Only introduce the necessary variable into struct rtc_device.
Code to set and use the variable will follow with subsequent patches.

Cc: Brian Norris <briannorris@chromium.org>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20230817225537.4053865-2-linux@roeck-us.net
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 include/linux/rtc.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index 1fd9c6a21ebe..4c0bcbeb1f00 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -146,6 +146,7 @@ struct rtc_device {
 
 	time64_t range_min;
 	timeu64_t range_max;
+	timeu64_t alarm_offset_max;
 	time64_t start_secs;
 	time64_t offset_secs;
 	bool set_start_time;

From 00c3092d881bc9d63dc36eecd140cdb38962c7ec Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Thu, 17 Aug 2023 15:55:33 -0700
Subject: [PATCH 0719/1189] rtc: cros-ec: Detect and report supported alarm
 window size

The RTC on some older Chromebooks can only handle alarms less than
24 hours in the future. The only way to find out is to try to set
an alarm further in the future. If that fails, assume that the RTC
connected to the EC can only handle less than 24 hours of alarm
window, and report that value to the RTC core.

After that change, it is no longer necessary to limit the alarm time
when setting it. Report any excessive alarms to the caller instead.

Cc: Brian Norris <briannorris@chromium.org>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20230817225537.4053865-4-linux@roeck-us.net
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-cros-ec.c | 38 +++++++++++++++++++++++---------------
 1 file changed, 23 insertions(+), 15 deletions(-)

diff --git a/drivers/rtc/rtc-cros-ec.c b/drivers/rtc/rtc-cros-ec.c
index 998ab8606f0b..0cd397c04ff0 100644
--- a/drivers/rtc/rtc-cros-ec.c
+++ b/drivers/rtc/rtc-cros-ec.c
@@ -182,21 +182,15 @@ static int cros_ec_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 
 	ret = cros_ec_rtc_set(cros_ec, EC_CMD_RTC_SET_ALARM, alarm_offset);
 	if (ret < 0) {
-		if (ret == -EINVAL && alarm_offset >= SECS_PER_DAY) {
-			/*
-			 * RTC chips on some older Chromebooks can only handle
-			 * alarms up to 24h in the future. Try to set an alarm
-			 * below that limit to avoid suspend failures.
-			 */
-			ret = cros_ec_rtc_set(cros_ec, EC_CMD_RTC_SET_ALARM,
-					      SECS_PER_DAY - 1);
-		}
-
-		if (ret < 0) {
-			dev_err(dev, "error setting alarm in %u seconds: %d\n",
-				alarm_offset, ret);
-			return ret;
-		}
+		dev_err(dev, "error setting alarm in %u seconds: %d\n",
+			alarm_offset, ret);
+		/*
+		 * The EC code returns -EINVAL if the alarm time is too
+		 * far in the future. Convert it to the expected error code.
+		 */
+		if (ret == -EINVAL)
+			ret = -ERANGE;
+		return ret;
 	}
 
 	return 0;
@@ -355,6 +349,20 @@ static int cros_ec_rtc_probe(struct platform_device *pdev)
 	cros_ec_rtc->rtc->ops = &cros_ec_rtc_ops;
 	cros_ec_rtc->rtc->range_max = U32_MAX;
 
+	/*
+	 * The RTC on some older Chromebooks can only handle alarms less than
+	 * 24 hours in the future. The only way to find out is to try to set an
+	 * alarm further in the future. If that fails, assume that the RTC
+	 * connected to the EC can only handle less than 24 hours of alarm
+	 * window.
+	 */
+	ret = cros_ec_rtc_set(cros_ec, EC_CMD_RTC_SET_ALARM, SECS_PER_DAY * 2);
+	if (ret == -EINVAL)
+		cros_ec_rtc->rtc->alarm_offset_max = SECS_PER_DAY - 1;
+
+	(void)cros_ec_rtc_set(cros_ec, EC_CMD_RTC_SET_ALARM,
+			      EC_RTC_ALARM_CLEAR);
+
 	ret = devm_rtc_register_device(cros_ec_rtc->rtc);
 	if (ret)
 		return ret;

From 2546e7083f2ea96bdd6157961dc2748d65a9e487 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Thu, 17 Aug 2023 15:55:34 -0700
Subject: [PATCH 0720/1189] rtc: cmos: Report supported alarm limit to rtc
 infrastructure

The alarm window supported by the cmos RTC depends on the chip
and its configuration. Report the limit to the RTC core.

Cc: Brian Norris <briannorris@chromium.org>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20230817225537.4053865-5-linux@roeck-us.net
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-cmos.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index c9416fe8542d..228fb2d11c70 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -913,6 +913,10 @@ static inline void cmos_check_acpi_rtc_status(struct device *dev,
 #define	INITSECTION	__init
 #endif
 
+#define SECS_PER_DAY	(24 * 60 * 60)
+#define SECS_PER_MONTH	(28 * SECS_PER_DAY)
+#define SECS_PER_YEAR	(365 * SECS_PER_DAY)
+
 static int INITSECTION
 cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq)
 {
@@ -1019,6 +1023,13 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq)
 		goto cleanup0;
 	}
 
+	if (cmos_rtc.mon_alrm)
+		cmos_rtc.rtc->alarm_offset_max = SECS_PER_YEAR - 1;
+	else if (cmos_rtc.day_alrm)
+		cmos_rtc.rtc->alarm_offset_max = SECS_PER_MONTH - 1;
+	else
+		cmos_rtc.rtc->alarm_offset_max = SECS_PER_DAY - 1;
+
 	rename_region(ports, dev_name(&cmos_rtc.rtc->dev));
 
 	if (!mc146818_does_rtc_work()) {

From 3637bbdc8a446b8edb369383d2abc816c96ee864 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Thu, 17 Aug 2023 15:55:35 -0700
Subject: [PATCH 0721/1189] rtc: tps6586x: Report maximum alarm limit to rtc
 core

tps6586x only supports alarms up to 16,383 seconds in the future.
Report the limit to the RTC core.

Cc: Brian Norris <briannorris@chromium.org>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20230817225537.4053865-6-linux@roeck-us.net
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-tps6586x.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/rtc/rtc-tps6586x.c b/drivers/rtc/rtc-tps6586x.c
index 9f14e2475747..20faf08c254c 100644
--- a/drivers/rtc/rtc-tps6586x.c
+++ b/drivers/rtc/rtc-tps6586x.c
@@ -252,6 +252,7 @@ static int tps6586x_rtc_probe(struct platform_device *pdev)
 
 	rtc->rtc->ops = &tps6586x_rtc_ops;
 	rtc->rtc->range_max = (1ULL << 30) - 1; /* 30-bit seconds */
+	rtc->rtc->alarm_offset_max = ALM1_VALID_RANGE_IN_SEC;
 	rtc->rtc->start_secs = mktime64(2009, 1, 1, 0, 0, 0);
 	rtc->rtc->set_start_time = true;
 

From 46b79ac0b463e155b098805ff66f1f22ff249b45 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Thu, 17 Aug 2023 15:55:36 -0700
Subject: [PATCH 0722/1189] rtc: ds1305: Report maximum alarm limit to rtc core

DS1305 only supports alarms up to 24 hours in the future.
Report the limit to the RTC core, and use the reported limit
to validate the requested alarm time when setting it.

If the alarm is too large when trying to set an alarm, return -ERANGE
instead of -EDOM to align with error codes returned by other rtc drivers.

Cc: Brian Norris <briannorris@chromium.org>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20230817225537.4053865-7-linux@roeck-us.net
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-ds1305.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/rtc/rtc-ds1305.c b/drivers/rtc/rtc-ds1305.c
index ed9360486953..d4de401548b4 100644
--- a/drivers/rtc/rtc-ds1305.c
+++ b/drivers/rtc/rtc-ds1305.c
@@ -336,8 +336,8 @@ static int ds1305_set_alarm(struct device *dev, struct rtc_wkalrm *alm)
 	/* make sure alarm fires within the next 24 hours */
 	if (later <= now)
 		return -EINVAL;
-	if ((later - now) > 24 * 60 * 60)
-		return -EDOM;
+	if ((later - now) > ds1305->rtc->alarm_offset_max)
+		return -ERANGE;
 
 	/* disable alarm if needed */
 	if (ds1305->ctrl[0] & DS1305_AEI0) {
@@ -691,6 +691,7 @@ static int ds1305_probe(struct spi_device *spi)
 	ds1305->rtc->ops = &ds1305_ops;
 	ds1305->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	ds1305->rtc->range_max = RTC_TIMESTAMP_END_2099;
+	ds1305->rtc->alarm_offset_max = 24 * 60 * 60;
 
 	ds1305_nvmem_cfg.priv = ds1305;
 	status = devm_rtc_register_device(ds1305->rtc);

From 2b0386d578836b9cd5d2e63cff38b7229c319e4a Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Thu, 17 Aug 2023 15:55:37 -0700
Subject: [PATCH 0723/1189] rtc: rzn1: Report maximum alarm limit to rtc core

RZN1 only supports alarms up to one week in the future.
Report the limit to the RTC core and use the reported limit
to validate the requested alarm time when setting it.

Cc: Brian Norris <briannorris@chromium.org>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/r/20230817225537.4053865-8-linux@roeck-us.net
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-rzn1.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/rtc/rtc-rzn1.c b/drivers/rtc/rtc-rzn1.c
index 6f98969eedca..56ebbd4d0481 100644
--- a/drivers/rtc/rtc-rzn1.c
+++ b/drivers/rtc/rtc-rzn1.c
@@ -227,7 +227,7 @@ static int rzn1_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 		return ret;
 
 	/* We cannot set alarms more than one week ahead */
-	farest = rtc_tm_to_time64(&tm_now) + (7 * 86400);
+	farest = rtc_tm_to_time64(&tm_now) + rtc->rtcdev->alarm_offset_max;
 	alarm = rtc_tm_to_time64(tm);
 	if (time_after(alarm, farest))
 		return -ERANGE;
@@ -351,6 +351,7 @@ static int rzn1_rtc_probe(struct platform_device *pdev)
 
 	rtc->rtcdev->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	rtc->rtcdev->range_max = RTC_TIMESTAMP_END_2099;
+	rtc->rtcdev->alarm_offset_max = 7 * 86400;
 	rtc->rtcdev->ops = &rzn1_rtc_ops;
 	set_bit(RTC_FEATURE_ALARM_RES_MINUTE, rtc->rtcdev->features);
 	clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->rtcdev->features);

From eeeb77716f5f7c03d157980c7ad3af037c61c8ae Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Sun, 27 Aug 2023 23:46:49 +0200
Subject: [PATCH 0724/1189] rtc: pcf2127: remove useless check

This check is only useful when introducing support for a new RTC in the
driver. Cut down the number of strings in th driver.

Link: https://lore.kernel.org/r/20230827214649.537095-1-alexandre.belloni@bootlin.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-pcf2127.c | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index de8164e1b562..9c04c4e1a49c 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -1054,15 +1054,6 @@ static int pcf2127_enable_ts(struct device *dev, int ts_id)
 		return ret;
 	}
 
-	/* TS input pin driven to GND detection is supported by all variants.
-	 * Make sure that interrupt bit is defined.
-	 */
-	if (pcf2127->cfg->ts[ts_id].gnd_detect_bit == 0) {
-		dev_err(dev, "%s: tamper detection to GND configuration invalid\n",
-			__func__);
-		return -EINVAL;
-	}
-
 	/*
 	 * Enable interrupt generation when TSF timestamp flag is set.
 	 * Interrupt signals are open-drain outputs and can be left floating if

From a5aeccabb53673331f78a97ce492ce6d01f1e036 Mon Sep 17 00:00:00 2001
From: Nikita Shubin <nikita.shubin@maquefel.me>
Date: Fri, 25 Aug 2023 11:43:25 +0300
Subject: [PATCH 0725/1189] dt-bindings: rtc: Add ST M48T86

Add YAML bindings for ST M48T86 / Dallas DS12887 RTC.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/lkml/61b9e036-7864-65c6-d43b-463fff896ddc@linaro.org/
Signed-off-by: Nikita Shubin <nikita.shubin@maquefel.me>
Link: https://lore.kernel.org/r/20230823-m48t86_device_tree-v2-1-21ff275f949d@maquefel.me
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 .../devicetree/bindings/rtc/st,m48t86.yaml    | 38 +++++++++++++++++++
 1 file changed, 38 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/rtc/st,m48t86.yaml

diff --git a/Documentation/devicetree/bindings/rtc/st,m48t86.yaml b/Documentation/devicetree/bindings/rtc/st,m48t86.yaml
new file mode 100644
index 000000000000..e3e12fa23380
--- /dev/null
+++ b/Documentation/devicetree/bindings/rtc/st,m48t86.yaml
@@ -0,0 +1,38 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/rtc/st,m48t86.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: ST M48T86 / Dallas DS12887 RTC with SRAM
+
+maintainers:
+  - Alexandre Belloni <alexandre.belloni@bootlin.com>
+
+allOf:
+  - $ref: rtc.yaml
+
+properties:
+  compatible:
+    enum:
+      - st,m48t86
+
+  reg:
+    items:
+      - description: index register
+      - description: data register
+
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    rtc@10800000 {
+      compatible = "st,m48t86";
+      reg = <0x10800000 0x1>, <0x11700000 0x1>;
+    };
+
+...

From 6ec3f5ec2eecabab065a39f5e04562c8c3c81ece Mon Sep 17 00:00:00 2001
From: Nikita Shubin <nikita.shubin@maquefel.me>
Date: Fri, 25 Aug 2023 11:43:26 +0300
Subject: [PATCH 0726/1189] rtc: m48t86: add DT support for m48t86

Add OF ID match table.

Acked-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/lkml/20230601054549.10843-12-nikita.shubin@maquefel.me/
Signed-off-by: Nikita Shubin <nikita.shubin@maquefel.me>
Link: https://lore.kernel.org/r/20230823-m48t86_device_tree-v2-2-21ff275f949d@maquefel.me
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-m48t86.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/rtc/rtc-m48t86.c b/drivers/rtc/rtc-m48t86.c
index 481c9525b1dd..dd4a62e2d39c 100644
--- a/drivers/rtc/rtc-m48t86.c
+++ b/drivers/rtc/rtc-m48t86.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/mod_devicetable.h>
 #include <linux/rtc.h>
 #include <linux/platform_device.h>
 #include <linux/bcd.h>
@@ -269,9 +270,16 @@ static int m48t86_rtc_probe(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct of_device_id m48t86_rtc_of_ids[] = {
+	{ .compatible = "st,m48t86" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, m48t86_rtc_of_ids);
+
 static struct platform_driver m48t86_rtc_platform_driver = {
 	.driver		= {
 		.name	= "rtc-m48t86",
+		.of_match_table = m48t86_rtc_of_ids,
 	},
 	.probe		= m48t86_rtc_probe,
 };

From 1e786b03705938870dafb629f2248f88d507a0ff Mon Sep 17 00:00:00 2001
From: Mike Looijmans <mike.looijmans@topic.nl>
Date: Mon, 21 Aug 2023 09:20:13 +0200
Subject: [PATCH 0727/1189] rtc: pcf85363: Allow to wake up system without IRQ

When wakeup-source is set in the devicetree, set up the device for
using the output as interrupt instead of clock. This is similar to
how other RTC devices handle this.

This allows the clock chip to turn on the board when wired to do
so in hardware.

Signed-off-by: Mike Looijmans <mike.looijmans@topic.nl>
Link: https://lore.kernel.org/r/20230821072013.7072-1-mike.looijmans@topic.nl
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-pcf85363.c | 30 +++++++++++++++++++++---------
 1 file changed, 21 insertions(+), 9 deletions(-)

diff --git a/drivers/rtc/rtc-pcf85363.c b/drivers/rtc/rtc-pcf85363.c
index 569c79bac0ee..06194674d71c 100644
--- a/drivers/rtc/rtc-pcf85363.c
+++ b/drivers/rtc/rtc-pcf85363.c
@@ -402,6 +402,7 @@ static int pcf85363_probe(struct i2c_client *client)
 		},
 	};
 	int ret, i, err;
+	bool wakeup_source;
 
 	if (data)
 		config = data;
@@ -431,25 +432,36 @@ static int pcf85363_probe(struct i2c_client *client)
 	pcf85363->rtc->ops = &rtc_ops;
 	pcf85363->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	pcf85363->rtc->range_max = RTC_TIMESTAMP_END_2099;
-	clear_bit(RTC_FEATURE_ALARM, pcf85363->rtc->features);
+
+	wakeup_source = device_property_read_bool(&client->dev,
+						  "wakeup-source");
+	if (client->irq > 0 || wakeup_source) {
+		regmap_write(pcf85363->regmap, CTRL_FLAGS, 0);
+		regmap_update_bits(pcf85363->regmap, CTRL_PIN_IO,
+				   PIN_IO_INTA_OUT, PIN_IO_INTAPM);
+	}
 
 	if (client->irq > 0) {
 		unsigned long irqflags = IRQF_TRIGGER_LOW;
 
 		if (dev_fwnode(&client->dev))
 			irqflags = 0;
-
-		regmap_write(pcf85363->regmap, CTRL_FLAGS, 0);
-		regmap_update_bits(pcf85363->regmap, CTRL_PIN_IO,
-				   PIN_IO_INTA_OUT, PIN_IO_INTAPM);
 		ret = devm_request_threaded_irq(&client->dev, client->irq,
 						NULL, pcf85363_rtc_handle_irq,
 						irqflags | IRQF_ONESHOT,
 						"pcf85363", client);
-		if (ret)
-			dev_warn(&client->dev, "unable to request IRQ, alarms disabled\n");
-		else
-			set_bit(RTC_FEATURE_ALARM, pcf85363->rtc->features);
+		if (ret) {
+			dev_warn(&client->dev,
+				 "unable to request IRQ, alarms disabled\n");
+			client->irq = 0;
+		}
+	}
+
+	if (client->irq > 0 || wakeup_source) {
+		device_init_wakeup(&client->dev, true);
+		set_bit(RTC_FEATURE_ALARM, pcf85363->rtc->features);
+	} else {
+		clear_bit(RTC_FEATURE_ALARM, pcf85363->rtc->features);
 	}
 
 	ret = devm_rtc_register_device(pcf85363->rtc);

From 7130856f56054a031c492d37896cbcbfd04a61b5 Mon Sep 17 00:00:00 2001
From: Ladislav Michl <ladis@linux-mips.org>
Date: Sat, 28 May 2022 19:36:13 +0200
Subject: [PATCH 0728/1189] rtc: twl: add NVRAM support

Export SRAM using nvmem.

Signed-off-by: Ladislav Michl <ladis@linux-mips.org>
Reviewed-by: Tony Lindgren <tony@atomide.com>
Link: https://lore.kernel.org/r/ZDf7qZTiml0ijD2g@lenoch
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-twl.c | 37 +++++++++++++++++++++++++++++++++++++
 1 file changed, 37 insertions(+)

diff --git a/drivers/rtc/rtc-twl.c b/drivers/rtc/rtc-twl.c
index 81b36948c2fa..f8f0d774a06e 100644
--- a/drivers/rtc/rtc-twl.c
+++ b/drivers/rtc/rtc-twl.c
@@ -487,11 +487,24 @@ static const struct rtc_class_ops twl_rtc_ops = {
 	.alarm_irq_enable = twl_rtc_alarm_irq_enable,
 };
 
+static int twl_nvram_read(void *priv, unsigned int offset, void *val,
+			  size_t bytes)
+{
+	return twl_i2c_read((long)priv, val, offset, bytes);
+}
+
+static int twl_nvram_write(void *priv, unsigned int offset, void *val,
+			   size_t bytes)
+{
+	return twl_i2c_write((long)priv, val, offset, bytes);
+}
+
 /*----------------------------------------------------------------------*/
 
 static int twl_rtc_probe(struct platform_device *pdev)
 {
 	struct twl_rtc *twl_rtc;
+	struct nvmem_config nvmem_cfg;
 	struct device_node *np = pdev->dev.of_node;
 	int ret = -EINVAL;
 	int irq = platform_get_irq(pdev, 0);
@@ -579,6 +592,30 @@ static int twl_rtc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	memset(&nvmem_cfg, 0, sizeof(nvmem_cfg));
+	nvmem_cfg.name = "twl-secured-";
+	nvmem_cfg.type = NVMEM_TYPE_BATTERY_BACKED;
+	nvmem_cfg.reg_read = twl_nvram_read,
+	nvmem_cfg.reg_write = twl_nvram_write,
+	nvmem_cfg.word_size = 1;
+	nvmem_cfg.stride = 1;
+	if (twl_class_is_4030()) {
+		/* 20 bytes SECURED_REG area */
+		nvmem_cfg.size = 20;
+		nvmem_cfg.priv = (void *)TWL_MODULE_SECURED_REG;
+		devm_rtc_nvmem_register(twl_rtc->rtc, &nvmem_cfg);
+		/* 8 bytes BACKUP area */
+		nvmem_cfg.name = "twl-backup-";
+		nvmem_cfg.size = 8;
+		nvmem_cfg.priv = (void *)TWL4030_MODULE_BACKUP;
+		devm_rtc_nvmem_register(twl_rtc->rtc, &nvmem_cfg);
+	} else {
+		/* 8 bytes SECURED_REG area */
+		nvmem_cfg.size = 8;
+		nvmem_cfg.priv = (void *)TWL_MODULE_SECURED_REG;
+		devm_rtc_nvmem_register(twl_rtc->rtc, &nvmem_cfg);
+	}
+
 	return 0;
 }
 

From 5496eac6ad7428fa06811a8c34b3a15beb93b86d Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 17 Aug 2023 12:18:53 +0200
Subject: [PATCH 0729/1189] i3c: master: svc: Describe member 'saved_regs'

The 'saved_regs' member of the 'svc_i3c_master'	structure is not
described in the kernel doc, which produces the following warning:

    Function parameter or member 'saved_regs' not described in 'svc_i3c_master'

Add the missing line in the kernel documentation of the parent
structure.

Fixes: 1c5ee2a77b1b ("i3c: master: svc: fix i3c suspend/resume issue")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202308171435.0xQ82lvu-lkp@intel.com/
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/r/20230817101853.16805-1-miquel.raynal@bootlin.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/svc-i3c-master.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c
index 770b40e28015..17b4ce12aef3 100644
--- a/drivers/i3c/master/svc-i3c-master.c
+++ b/drivers/i3c/master/svc-i3c-master.c
@@ -156,6 +156,7 @@ struct svc_i3c_regs_save {
  * @base: I3C master controller
  * @dev: Corresponding device
  * @regs: Memory mapping
+ * @saved_regs: Volatile values for PM operations
  * @free_slots: Bit array of available slots
  * @addrs: Array containing the dynamic addresses of each attached device
  * @descs: Array of descriptors, one per attached device

From 32e6b31a6a80ba9493fad802d68d41f4d63230cc Mon Sep 17 00:00:00 2001
From: Aniket <aniketmaurya@google.com>
Date: Tue, 22 Aug 2023 05:12:09 +0000
Subject: [PATCH 0730/1189] dt-bindings: i3c: Fix description for
 assigned-address

assigned-address is a valid property for I3C device with or without
static address. Fix the description and an example for the same.

Signed-off-by: Aniket <aniketmaurya@google.com>
Acked-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230822051209.2837818-1-aniketmaurya@google.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 Documentation/devicetree/bindings/i3c/i3c.yaml | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/Documentation/devicetree/bindings/i3c/i3c.yaml b/Documentation/devicetree/bindings/i3c/i3c.yaml
index fdb4212149e7..ab69f4115de4 100644
--- a/Documentation/devicetree/bindings/i3c/i3c.yaml
+++ b/Documentation/devicetree/bindings/i3c/i3c.yaml
@@ -135,9 +135,10 @@ patternProperties:
         minimum: 0x1
         maximum: 0xff
         description: |
-          Dynamic address to be assigned to this device. This property is only
-          valid if the I3C device has a static address (first cell of the reg
-          property != 0).
+          Dynamic address to be assigned to this device. In case static address is
+          present (first cell of the reg property != 0), this address is assigned
+          through SETDASA. If static address is not present, this address is assigned
+          through SETNEWDA after assigning a temporary address via ENTDAA.
 
     required:
       - reg
@@ -163,12 +164,18 @@ examples:
             pagesize = <0x8>;
         };
 
-        /* I3C device with a static I2C address. */
+        /* I3C device with a static I2C address and assigned address. */
         thermal_sensor: sensor@68,39200144004 {
             reg = <0x68 0x392 0x144004>;
             assigned-address = <0xa>;
         };
 
+        /* I3C device with only assigned address. */
+        pressure_sensor: sensor@0,39200124004 {
+            reg = <0x0 0x392 0x124000>;
+            assigned-address = <0xc>;
+        };
+
         /*
          * I3C device without a static I2C address but requiring
          * resources described in the DT.

From c6a7550458922181bb922863d5f5feaf3c453fe5 Mon Sep 17 00:00:00 2001
From: Aniket <aniketmaurya@google.com>
Date: Tue, 22 Aug 2023 05:19:38 +0000
Subject: [PATCH 0731/1189] i3c: master: Fix SETDASA process

When a I3C DT node has a static_addr and an init_dyn_addr,the
init_dyn_addr is reserved in i3c_master_bus_init() and then
the static_addr is reserved in i3c_master_early_i3c_dev_add().
But if the dynamic address is same as static then above
procedure would fail.
Add a check to pass i3c_bus_get_addr_slot_status() when static
and dynamic address are equal.

Signed-off-by: Aniket <aniketmaurya@google.com>
Link: https://lore.kernel.org/r/20230822051938.2852567-1-aniketmaurya@google.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c
index 08aeb69a7800..87283e4a4607 100644
--- a/drivers/i3c/master.c
+++ b/drivers/i3c/master.c
@@ -1308,7 +1308,11 @@ static int i3c_master_get_i3c_addrs(struct i3c_dev_desc *dev)
 	if (dev->info.static_addr) {
 		status = i3c_bus_get_addr_slot_status(&master->bus,
 						      dev->info.static_addr);
-		if (status != I3C_ADDR_SLOT_FREE)
+		/* Since static address and assigned dynamic address can be
+		 * equal, allow this case to pass.
+		 */
+		if (status != I3C_ADDR_SLOT_FREE &&
+		    dev->info.static_addr != dev->boardinfo->init_dyn_addr)
 			return -EBUSY;
 
 		i3c_bus_set_addr_slot_status(&master->bus,

From 687eb3c42f4ad81e7c947c50e2d865f692064291 Mon Sep 17 00:00:00 2001
From: Max Filippov <jcmvbkbc@gmail.com>
Date: Mon, 24 Jul 2023 00:58:24 -0700
Subject: [PATCH 0732/1189] xtensa: PMU: fix base address for the newer
 hardware

With introduction of ERI access control in RG.0 base address of the PMU
unit registers has changed. Add support for the new PMU configuration.

Cc: stable@vger.kernel.org
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
---
 arch/xtensa/include/asm/core.h  |  9 +++++++++
 arch/xtensa/kernel/perf_event.c | 17 +++++++++++++----
 2 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/arch/xtensa/include/asm/core.h b/arch/xtensa/include/asm/core.h
index 0e1bb6f019d6..3f5ffae89b58 100644
--- a/arch/xtensa/include/asm/core.h
+++ b/arch/xtensa/include/asm/core.h
@@ -52,4 +52,13 @@
 #define XTENSA_STACK_ALIGNMENT	16
 #endif
 
+#ifndef XCHAL_HW_MIN_VERSION
+#if defined(XCHAL_HW_MIN_VERSION_MAJOR) && defined(XCHAL_HW_MIN_VERSION_MINOR)
+#define XCHAL_HW_MIN_VERSION (XCHAL_HW_MIN_VERSION_MAJOR * 100 + \
+			      XCHAL_HW_MIN_VERSION_MINOR)
+#else
+#define XCHAL_HW_MIN_VERSION 0
+#endif
+#endif
+
 #endif
diff --git a/arch/xtensa/kernel/perf_event.c b/arch/xtensa/kernel/perf_event.c
index a0d05c8598d0..183618090d05 100644
--- a/arch/xtensa/kernel/perf_event.c
+++ b/arch/xtensa/kernel/perf_event.c
@@ -13,17 +13,26 @@
 #include <linux/perf_event.h>
 #include <linux/platform_device.h>
 
+#include <asm/core.h>
 #include <asm/processor.h>
 #include <asm/stacktrace.h>
 
+#define XTENSA_HWVERSION_RG_2015_0	260000
+
+#if XCHAL_HW_MIN_VERSION >= XTENSA_HWVERSION_RG_2015_0
+#define XTENSA_PMU_ERI_BASE		0x00101000
+#else
+#define XTENSA_PMU_ERI_BASE		0x00001000
+#endif
+
 /* Global control/status for all perf counters */
-#define XTENSA_PMU_PMG			0x1000
+#define XTENSA_PMU_PMG			XTENSA_PMU_ERI_BASE
 /* Perf counter values */
-#define XTENSA_PMU_PM(i)		(0x1080 + (i) * 4)
+#define XTENSA_PMU_PM(i)		(XTENSA_PMU_ERI_BASE + 0x80 + (i) * 4)
 /* Perf counter control registers */
-#define XTENSA_PMU_PMCTRL(i)		(0x1100 + (i) * 4)
+#define XTENSA_PMU_PMCTRL(i)		(XTENSA_PMU_ERI_BASE + 0x100 + (i) * 4)
 /* Perf counter status registers */
-#define XTENSA_PMU_PMSTAT(i)		(0x1180 + (i) * 4)
+#define XTENSA_PMU_PMSTAT(i)		(XTENSA_PMU_ERI_BASE + 0x180 + (i) * 4)
 
 #define XTENSA_PMU_PMG_PMEN		0x1
 

From e7513eccb7d7f82e28f4730210b42da71edaa6a6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Sun, 27 Aug 2023 16:36:59 +0300
Subject: [PATCH 0733/1189] MIPS: TXx9: Do PCI error checks on own line
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Instead of if conditions with line splits, use the usual error handling
pattern with a separate variable to improve readability.

The second check can use reverse logic which reduces indentation level.

No functional changes intended.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/txx9/generic/pci.c | 43 +++++++++++++++++++-----------------
 1 file changed, 23 insertions(+), 20 deletions(-)

diff --git a/arch/mips/txx9/generic/pci.c b/arch/mips/txx9/generic/pci.c
index e98845543b77..5ae30b78d38d 100644
--- a/arch/mips/txx9/generic/pci.c
+++ b/arch/mips/txx9/generic/pci.c
@@ -51,6 +51,7 @@ int __init txx9_pci66_check(struct pci_controller *hose, int top_bus,
 	unsigned short vid;
 	int cap66 = -1;
 	u16 stat;
+	int ret;
 
 	/* It seems SLC90E66 needs some time after PCI reset... */
 	mdelay(80);
@@ -60,9 +61,9 @@ int __init txx9_pci66_check(struct pci_controller *hose, int top_bus,
 	for (pci_devfn = 0; pci_devfn < 0xff; pci_devfn++) {
 		if (PCI_FUNC(pci_devfn))
 			continue;
-		if (early_read_config_word(hose, top_bus, current_bus,
-					   pci_devfn, PCI_VENDOR_ID, &vid) !=
-		    PCIBIOS_SUCCESSFUL)
+		ret = early_read_config_word(hose, top_bus, current_bus,
+					     pci_devfn, PCI_VENDOR_ID, &vid);
+		if (ret != PCIBIOS_SUCCESSFUL)
 			continue;
 		if (vid == 0xffff)
 			continue;
@@ -343,26 +344,28 @@ static void tc35815_fixup(struct pci_dev *dev)
 
 static void final_fixup(struct pci_dev *dev)
 {
+	unsigned long timeout;
 	unsigned char bist;
+	int ret;
 
 	/* Do build-in self test */
-	if (pci_read_config_byte(dev, PCI_BIST, &bist) == PCIBIOS_SUCCESSFUL &&
-	    (bist & PCI_BIST_CAPABLE)) {
-		unsigned long timeout;
-		pci_set_power_state(dev, PCI_D0);
-		pr_info("PCI: %s BIST...", pci_name(dev));
-		pci_write_config_byte(dev, PCI_BIST, PCI_BIST_START);
-		timeout = jiffies + HZ * 2;	/* timeout after 2 sec */
-		do {
-			pci_read_config_byte(dev, PCI_BIST, &bist);
-			if (time_after(jiffies, timeout))
-				break;
-		} while (bist & PCI_BIST_START);
-		if (bist & (PCI_BIST_CODE_MASK | PCI_BIST_START))
-			pr_cont("failed. (0x%x)\n", bist);
-		else
-			pr_cont("OK.\n");
-	}
+	ret = pci_read_config_byte(dev, PCI_BIST, &bist);
+	if ((ret != PCIBIOS_SUCCESSFUL) || !(bist & PCI_BIST_CAPABLE))
+		return;
+
+	pci_set_power_state(dev, PCI_D0);
+	pr_info("PCI: %s BIST...", pci_name(dev));
+	pci_write_config_byte(dev, PCI_BIST, PCI_BIST_START);
+	timeout = jiffies + HZ * 2;	/* timeout after 2 sec */
+	do {
+		pci_read_config_byte(dev, PCI_BIST, &bist);
+		if (time_after(jiffies, timeout))
+			break;
+	} while (bist & PCI_BIST_START);
+	if (bist & (PCI_BIST_CODE_MASK | PCI_BIST_START))
+		pr_cont("failed. (0x%x)\n", bist);
+	else
+		pr_cont("OK.\n");
 }
 
 #ifdef CONFIG_TOSHIBA_FPCIB0

From 16631c42e6ff4f5acf30998fda6c2ea09d1adbfe Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Tue, 25 Jul 2023 16:37:16 +0200
Subject: [PATCH 0734/1189] KVM: s390: interrupt: Fix single-stepping into
 interrupt handlers

After single-stepping an instruction that generates an interrupt, GDB
ends up on the second instruction of the respective interrupt handler.

The reason is that vcpu_pre_run() manually delivers the interrupt, and
then __vcpu_run() runs the first handler instruction using the
CPUSTAT_P flag. This causes a KVM_SINGLESTEP exit on the second handler
instruction.

Fix by delaying the KVM_SINGLESTEP exit until after the manual
interrupt delivery.

Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Message-ID: <20230725143857.228626-2-iii@linux.ibm.com>
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
---
 arch/s390/kvm/interrupt.c | 14 ++++++++++++++
 arch/s390/kvm/kvm-s390.c  |  4 ++--
 2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 9bd0a873f3b1..85e39f472bb4 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -1392,6 +1392,7 @@ int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 	int rc = 0;
+	bool delivered = false;
 	unsigned long irq_type;
 	unsigned long irqs;
 
@@ -1465,6 +1466,19 @@ int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
 			WARN_ONCE(1, "Unknown pending irq type %ld", irq_type);
 			clear_bit(irq_type, &li->pending_irqs);
 		}
+		delivered |= !rc;
+	}
+
+	/*
+	 * We delivered at least one interrupt and modified the PC. Force a
+	 * singlestep event now.
+	 */
+	if (delivered && guestdbg_sstep_enabled(vcpu)) {
+		struct kvm_debug_exit_arch *debug_exit = &vcpu->run->debug.arch;
+
+		debug_exit->addr = vcpu->arch.sie_block->gpsw.addr;
+		debug_exit->type = KVM_SINGLESTEP;
+		vcpu->guest_debug |= KVM_GUESTDBG_EXIT_PENDING;
 	}
 
 	set_intercept_indicators(vcpu);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index d1e768bcfe1d..0c6333b108ba 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -4611,7 +4611,7 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu)
 
 	if (!kvm_is_ucontrol(vcpu->kvm)) {
 		rc = kvm_s390_deliver_pending_interrupts(vcpu);
-		if (rc)
+		if (rc || guestdbg_exit_pending(vcpu))
 			return rc;
 	}
 
@@ -4738,7 +4738,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 
 	do {
 		rc = vcpu_pre_run(vcpu);
-		if (rc)
+		if (rc || guestdbg_exit_pending(vcpu))
 			break;
 
 		kvm_vcpu_srcu_read_unlock(vcpu);

From 74a439ef7b67d89d29ec7485c3aeca20a64449c5 Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Tue, 25 Jul 2023 16:37:17 +0200
Subject: [PATCH 0735/1189] KVM: s390: interrupt: Fix single-stepping into
 program interrupt handlers

Currently, after single-stepping an instruction that generates a
specification exception, GDB ends up on the instruction immediately
following it.

The reason is that vcpu_post_run() injects the interrupt and sets
KVM_GUESTDBG_EXIT_PENDING, causing a KVM_SINGLESTEP exit. The
interrupt is not delivered, however, therefore userspace sees the
address of the next instruction.

Fix by letting the __vcpu_run() loop go into the next iteration,
where vcpu_pre_run() delivers the interrupt and sets
KVM_GUESTDBG_EXIT_PENDING.

Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Message-ID: <20230725143857.228626-3-iii@linux.ibm.com>
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
---
 arch/s390/kvm/intercept.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 954d39adf85c..e54496740859 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -228,6 +228,21 @@ static int handle_itdb(struct kvm_vcpu *vcpu)
 
 #define per_event(vcpu) (vcpu->arch.sie_block->iprcc & PGM_PER)
 
+static bool should_handle_per_event(const struct kvm_vcpu *vcpu)
+{
+	if (!guestdbg_enabled(vcpu) || !per_event(vcpu))
+		return false;
+	if (guestdbg_sstep_enabled(vcpu) &&
+	    vcpu->arch.sie_block->iprcc != PGM_PER) {
+		/*
+		 * __vcpu_run() will exit after delivering the concurrently
+		 * indicated condition.
+		 */
+		return false;
+	}
+	return true;
+}
+
 static int handle_prog(struct kvm_vcpu *vcpu)
 {
 	psw_t psw;
@@ -242,7 +257,7 @@ static int handle_prog(struct kvm_vcpu *vcpu)
 	if (kvm_s390_pv_cpu_is_protected(vcpu))
 		return -EOPNOTSUPP;
 
-	if (guestdbg_enabled(vcpu) && per_event(vcpu)) {
+	if (should_handle_per_event(vcpu)) {
 		rc = kvm_s390_handle_per_event(vcpu);
 		if (rc)
 			return rc;

From ba853a4e1c7addc631df55535bf0b04c62dc79d8 Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Tue, 25 Jul 2023 16:37:18 +0200
Subject: [PATCH 0736/1189] KVM: s390: interrupt: Fix single-stepping
 kernel-emulated instructions

Single-stepping a kernel-emulated instruction that generates an
interrupt causes GDB to land on the instruction following it instead of
the respective interrupt handler.

The reason is that kvm_handle_sie_intercept(), after injecting the
interrupt, also processes the PER event and arranges a KVM_SINGLESTEP
exit. The interrupt is not yet delivered, however, so the userspace
sees the next instruction.

Fix by avoiding the KVM_SINGLESTEP exit when there is a pending
interrupt. The next __vcpu_run() loop iteration will arrange a
KVM_SINGLESTEP exit after delivering the interrupt.

Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Message-ID: <20230725143857.228626-4-iii@linux.ibm.com>
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
---
 arch/s390/kvm/intercept.c | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index e54496740859..db222c749e5e 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -583,6 +583,19 @@ static int handle_pv_notification(struct kvm_vcpu *vcpu)
 	return handle_instruction(vcpu);
 }
 
+static bool should_handle_per_ifetch(const struct kvm_vcpu *vcpu, int rc)
+{
+	/* Process PER, also if the instruction is processed in user space. */
+	if (!(vcpu->arch.sie_block->icptstatus & 0x02))
+		return false;
+	if (rc != 0 && rc != -EOPNOTSUPP)
+		return false;
+	if (guestdbg_sstep_enabled(vcpu) && vcpu->arch.local_int.pending_irqs)
+		/* __vcpu_run() will exit after delivering the interrupt. */
+		return false;
+	return true;
+}
+
 int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu)
 {
 	int rc, per_rc = 0;
@@ -645,9 +658,7 @@ int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu)
 		return -EOPNOTSUPP;
 	}
 
-	/* process PER, also if the instruction is processed in user space */
-	if (vcpu->arch.sie_block->icptstatus & 0x02 &&
-	    (!rc || rc == -EOPNOTSUPP))
+	if (should_handle_per_ifetch(vcpu, rc))
 		per_rc = kvm_s390_handle_per_ifetch_icpt(vcpu);
 	return per_rc ? per_rc : rc;
 }

From 1ad1fa820e6424ae75d3d9f59774e40c9c7ec1e5 Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Tue, 25 Jul 2023 16:37:19 +0200
Subject: [PATCH 0737/1189] KVM: s390: interrupt: Fix single-stepping
 userspace-emulated instructions

Single-stepping a userspace-emulated instruction that generates an
interrupt causes GDB to land on the instruction following it instead of
the respective interrupt handler.

The reason is that after arranging a KVM_EXIT_S390_SIEIC exit,
kvm_handle_sie_intercept() calls kvm_s390_handle_per_ifetch_icpt(),
which sets KVM_GUESTDBG_EXIT_PENDING. This bit, however, is not
processed immediately, but rather persists until the next ioctl(),
causing a spurious single-step exit.

Fix by clearing this bit in ioctl().

Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Message-ID: <20230725143857.228626-5-iii@linux.ibm.com>
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
---
 arch/s390/kvm/kvm-s390.c | 23 ++++++++++++++++++++---
 1 file changed, 20 insertions(+), 3 deletions(-)

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 0c6333b108ba..e6511608280c 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -5383,6 +5383,7 @@ long kvm_arch_vcpu_async_ioctl(struct file *filp,
 {
 	struct kvm_vcpu *vcpu = filp->private_data;
 	void __user *argp = (void __user *)arg;
+	int rc;
 
 	switch (ioctl) {
 	case KVM_S390_IRQ: {
@@ -5390,7 +5391,8 @@ long kvm_arch_vcpu_async_ioctl(struct file *filp,
 
 		if (copy_from_user(&s390irq, argp, sizeof(s390irq)))
 			return -EFAULT;
-		return kvm_s390_inject_vcpu(vcpu, &s390irq);
+		rc = kvm_s390_inject_vcpu(vcpu, &s390irq);
+		break;
 	}
 	case KVM_S390_INTERRUPT: {
 		struct kvm_s390_interrupt s390int;
@@ -5400,10 +5402,25 @@ long kvm_arch_vcpu_async_ioctl(struct file *filp,
 			return -EFAULT;
 		if (s390int_to_s390irq(&s390int, &s390irq))
 			return -EINVAL;
-		return kvm_s390_inject_vcpu(vcpu, &s390irq);
+		rc = kvm_s390_inject_vcpu(vcpu, &s390irq);
+		break;
 	}
+	default:
+		rc = -ENOIOCTLCMD;
+		break;
 	}
-	return -ENOIOCTLCMD;
+
+	/*
+	 * To simplify single stepping of userspace-emulated instructions,
+	 * KVM_EXIT_S390_SIEIC exit sets KVM_GUESTDBG_EXIT_PENDING (see
+	 * should_handle_per_ifetch()). However, if userspace emulation injects
+	 * an interrupt, it needs to be cleared, so that KVM_EXIT_DEBUG happens
+	 * after (and not before) the interrupt delivery.
+	 */
+	if (!rc)
+		vcpu->guest_debug &= ~KVM_GUESTDBG_EXIT_PENDING;
+
+	return rc;
 }
 
 static int kvm_s390_handle_pv_vcpu_dump(struct kvm_vcpu *vcpu,

From fdbeb55ebdf1d83e610303f7e5c50a4d6904b7fa Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Tue, 25 Jul 2023 16:37:20 +0200
Subject: [PATCH 0738/1189] KVM: s390: interrupt: Fix single-stepping keyless
 mode exits

kvm_s390_skey_check_enable() does not emulate any instructions, rather,
it clears CPUSTAT_KSS and arranges the instruction that caused the exit
(e.g., ISKE, SSKE, RRBE or LPSWE with a keyed PSW) to run again.

Therefore, skip the PER check and let the instruction execution happen.
Otherwise, a debugger will see two single-step events on the same
instruction.

Reviewed-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Message-ID: <20230725143857.228626-6-iii@linux.ibm.com>
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
---
 arch/s390/kvm/intercept.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index db222c749e5e..9f64f27f086e 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -630,8 +630,8 @@ int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu)
 		rc = handle_partial_execution(vcpu);
 		break;
 	case ICPT_KSS:
-		rc = kvm_s390_skey_check_enable(vcpu);
-		break;
+		/* Instruction will be redriven, skip the PER check. */
+		return kvm_s390_skey_check_enable(vcpu);
 	case ICPT_MCHKREQ:
 	case ICPT_INT_ENABLE:
 		/*

From 642dbc0312d67781dabf97a70b43810165f21527 Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Tue, 25 Jul 2023 16:37:21 +0200
Subject: [PATCH 0739/1189] KVM: s390: selftests: Add selftest for
 single-stepping

Test different variations of single-stepping into interrupts:

- SVC and PGM interrupts;
- Interrupts generated by ISKE;
- Interrupts generated by instructions emulated by KVM;
- Interrupts generated by instructions emulated by userspace.

Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Message-ID: <20230725143857.228626-7-iii@linux.ibm.com>
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
[frankja@de.igm.com: s/ASSERT_EQ/TEST_ASSERT_EQ/ because function was
renamed in the selftest printf series]
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
---
 tools/testing/selftests/kvm/Makefile          |   1 +
 .../testing/selftests/kvm/s390x/debug_test.c  | 160 ++++++++++++++++++
 2 files changed, 161 insertions(+)
 create mode 100644 tools/testing/selftests/kvm/s390x/debug_test.c

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 77026907968f..6092ccfc49ac 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -169,6 +169,7 @@ TEST_GEN_PROGS_s390x += s390x/resets
 TEST_GEN_PROGS_s390x += s390x/sync_regs_test
 TEST_GEN_PROGS_s390x += s390x/tprot
 TEST_GEN_PROGS_s390x += s390x/cmma_test
+TEST_GEN_PROGS_s390x += s390x/debug_test
 TEST_GEN_PROGS_s390x += demand_paging_test
 TEST_GEN_PROGS_s390x += dirty_log_test
 TEST_GEN_PROGS_s390x += guest_print_test
diff --git a/tools/testing/selftests/kvm/s390x/debug_test.c b/tools/testing/selftests/kvm/s390x/debug_test.c
new file mode 100644
index 000000000000..84313fb27529
--- /dev/null
+++ b/tools/testing/selftests/kvm/s390x/debug_test.c
@@ -0,0 +1,160 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Test KVM debugging features. */
+#include "kvm_util.h"
+#include "test_util.h"
+
+#include <linux/kvm.h>
+
+#define __LC_SVC_NEW_PSW 0x1c0
+#define __LC_PGM_NEW_PSW 0x1d0
+#define ICPT_INSTRUCTION 0x04
+#define IPA0_DIAG 0x8300
+#define PGM_SPECIFICATION 0x06
+
+/* Common code for testing single-stepping interruptions. */
+extern char int_handler[];
+asm("int_handler:\n"
+    "j .\n");
+
+static struct kvm_vm *test_step_int_1(struct kvm_vcpu **vcpu, void *guest_code,
+				      size_t new_psw_off, uint64_t *new_psw)
+{
+	struct kvm_guest_debug debug = {};
+	struct kvm_regs regs;
+	struct kvm_vm *vm;
+	char *lowcore;
+
+	vm = vm_create_with_one_vcpu(vcpu, guest_code);
+	lowcore = addr_gpa2hva(vm, 0);
+	new_psw[0] = (*vcpu)->run->psw_mask;
+	new_psw[1] = (uint64_t)int_handler;
+	memcpy(lowcore + new_psw_off, new_psw, 16);
+	vcpu_regs_get(*vcpu, &regs);
+	regs.gprs[2] = -1;
+	vcpu_regs_set(*vcpu, &regs);
+	debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_SINGLESTEP;
+	vcpu_guest_debug_set(*vcpu, &debug);
+	vcpu_run(*vcpu);
+
+	return vm;
+}
+
+static void test_step_int(void *guest_code, size_t new_psw_off)
+{
+	struct kvm_vcpu *vcpu;
+	uint64_t new_psw[2];
+	struct kvm_vm *vm;
+
+	vm = test_step_int_1(&vcpu, guest_code, new_psw_off, new_psw);
+	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_DEBUG);
+	TEST_ASSERT_EQ(vcpu->run->psw_mask, new_psw[0]);
+	TEST_ASSERT_EQ(vcpu->run->psw_addr, new_psw[1]);
+	kvm_vm_free(vm);
+}
+
+/* Test single-stepping "boring" program interruptions. */
+extern char test_step_pgm_guest_code[];
+asm("test_step_pgm_guest_code:\n"
+    ".insn rr,0x1d00,%r1,%r0 /* dr %r1,%r0 */\n"
+    "j .\n");
+
+static void test_step_pgm(void)
+{
+	test_step_int(test_step_pgm_guest_code, __LC_PGM_NEW_PSW);
+}
+
+/*
+ * Test single-stepping program interruptions caused by DIAG.
+ * Userspace emulation must not interfere with single-stepping.
+ */
+extern char test_step_pgm_diag_guest_code[];
+asm("test_step_pgm_diag_guest_code:\n"
+    "diag %r0,%r0,0\n"
+    "j .\n");
+
+static void test_step_pgm_diag(void)
+{
+	struct kvm_s390_irq irq = {
+		.type = KVM_S390_PROGRAM_INT,
+		.u.pgm.code = PGM_SPECIFICATION,
+	};
+	struct kvm_vcpu *vcpu;
+	uint64_t new_psw[2];
+	struct kvm_vm *vm;
+
+	vm = test_step_int_1(&vcpu, test_step_pgm_diag_guest_code,
+			     __LC_PGM_NEW_PSW, new_psw);
+	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC);
+	TEST_ASSERT_EQ(vcpu->run->s390_sieic.icptcode, ICPT_INSTRUCTION);
+	TEST_ASSERT_EQ(vcpu->run->s390_sieic.ipa & 0xff00, IPA0_DIAG);
+	vcpu_ioctl(vcpu, KVM_S390_IRQ, &irq);
+	vcpu_run(vcpu);
+	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_DEBUG);
+	TEST_ASSERT_EQ(vcpu->run->psw_mask, new_psw[0]);
+	TEST_ASSERT_EQ(vcpu->run->psw_addr, new_psw[1]);
+	kvm_vm_free(vm);
+}
+
+/*
+ * Test single-stepping program interruptions caused by ISKE.
+ * CPUSTAT_KSS handling must not interfere with single-stepping.
+ */
+extern char test_step_pgm_iske_guest_code[];
+asm("test_step_pgm_iske_guest_code:\n"
+    "iske %r2,%r2\n"
+    "j .\n");
+
+static void test_step_pgm_iske(void)
+{
+	test_step_int(test_step_pgm_iske_guest_code, __LC_PGM_NEW_PSW);
+}
+
+/*
+ * Test single-stepping program interruptions caused by LCTL.
+ * KVM emulation must not interfere with single-stepping.
+ */
+extern char test_step_pgm_lctl_guest_code[];
+asm("test_step_pgm_lctl_guest_code:\n"
+    "lctl %c0,%c0,1\n"
+    "j .\n");
+
+static void test_step_pgm_lctl(void)
+{
+	test_step_int(test_step_pgm_lctl_guest_code, __LC_PGM_NEW_PSW);
+}
+
+/* Test single-stepping supervisor-call interruptions. */
+extern char test_step_svc_guest_code[];
+asm("test_step_svc_guest_code:\n"
+    "svc 0\n"
+    "j .\n");
+
+static void test_step_svc(void)
+{
+	test_step_int(test_step_svc_guest_code, __LC_SVC_NEW_PSW);
+}
+
+/* Run all tests above. */
+static struct testdef {
+	const char *name;
+	void (*test)(void);
+} testlist[] = {
+	{ "single-step pgm", test_step_pgm },
+	{ "single-step pgm caused by diag", test_step_pgm_diag },
+	{ "single-step pgm caused by iske", test_step_pgm_iske },
+	{ "single-step pgm caused by lctl", test_step_pgm_lctl },
+	{ "single-step svc", test_step_svc },
+};
+
+int main(int argc, char *argv[])
+{
+	int idx;
+
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(testlist));
+	for (idx = 0; idx < ARRAY_SIZE(testlist); idx++) {
+		testlist[idx].test();
+		ksft_test_result_pass("%s\n", testlist[idx].name);
+	}
+	ksft_finished();
+}

From b1e428615f154c87a94267b67e819644b50948f8 Mon Sep 17 00:00:00 2001
From: Viktor Mihajlovski <mihajlov@linux.ibm.com>
Date: Tue, 15 Aug 2023 17:14:12 +0200
Subject: [PATCH 0740/1189] KVM: s390: pv: relax WARN_ONCE condition for
 destroy fast

Destroy configuration fast may return with RC 0x104 if there
are still bound APQNs in the configuration. The final cleanup
will occur with the standard destroy configuration UVC as
at this point in time all APQNs have been reset and thus
unbound. Therefore, don't warn if RC 0x104 is reported.

Signed-off-by: Viktor Mihajlovski <mihajlov@linux.ibm.com>
Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Reviewed-by: Janosch Frank <frankja@linux.ibm.com>
Reviewed-by: Steffen Eiden <seiden@linux.ibm.com>
Reviewed-by: Michael Mueller <mimu@linux.ibm.com>
Link: https://lore.kernel.org/r/20230815151415.379760-2-seiden@linux.ibm.com
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Message-ID: <20230815151415.379760-2-seiden@linux.ibm.com>
---
 arch/s390/kvm/pv.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c
index 856140e9942e..beeebc11b1a1 100644
--- a/arch/s390/kvm/pv.c
+++ b/arch/s390/kvm/pv.c
@@ -285,7 +285,8 @@ static int kvm_s390_pv_deinit_vm_fast(struct kvm *kvm, u16 *rc, u16 *rrc)
 	WRITE_ONCE(kvm->arch.gmap->guest_handle, 0);
 	KVM_UV_EVENT(kvm, 3, "PROTVIRT DESTROY VM FAST: rc %x rrc %x",
 		     uvcb.header.rc, uvcb.header.rrc);
-	WARN_ONCE(cc, "protvirt destroy vm fast failed handle %llx rc %x rrc %x",
+	WARN_ONCE(cc && uvcb.header.rc != 0x104,
+		  "protvirt destroy vm fast failed handle %llx rc %x rrc %x",
 		  kvm_s390_pv_get_handle(kvm), uvcb.header.rc, uvcb.header.rrc);
 	/* Intended memory leak on "impossible" error */
 	if (!cc)

From 59a881402cc89788652fa2c2ce7421d14f131c34 Mon Sep 17 00:00:00 2001
From: Steffen Eiden <seiden@linux.ibm.com>
Date: Tue, 15 Aug 2023 17:14:13 +0200
Subject: [PATCH 0741/1189] s390/uv: UV feature check utility

Introduces a function to check the existence of an UV feature.
Refactor feature bit checks to use the new function.

Signed-off-by: Steffen Eiden <seiden@linux.ibm.com>
Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Reviewed-by: Janosch Frank <frankja@linux.ibm.com>
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Reviewed-by: Michael Mueller <mimu@linux.ibm.com>
Link: https://lore.kernel.org/r/20230815151415.379760-3-seiden@linux.ibm.com
Message-Id: <20230815151415.379760-3-seiden@linux.ibm.com>
---
 arch/s390/include/asm/uv.h | 7 +++++++
 arch/s390/kernel/uv.c      | 2 +-
 arch/s390/kvm/kvm-s390.c   | 2 +-
 arch/s390/mm/fault.c       | 2 +-
 4 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h
index d2cd42bb2c26..823adfff7315 100644
--- a/arch/s390/include/asm/uv.h
+++ b/arch/s390/include/asm/uv.h
@@ -397,6 +397,13 @@ struct uv_info {
 
 extern struct uv_info uv_info;
 
+static inline bool uv_has_feature(u8 feature_bit)
+{
+	if (feature_bit >= sizeof(uv_info.uv_feature_indications) * 8)
+		return false;
+	return test_bit_inv(feature_bit, &uv_info.uv_feature_indications);
+}
+
 #ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST
 extern int prot_virt_guest;
 
diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
index b771f1b4cdd1..fc07bc39e698 100644
--- a/arch/s390/kernel/uv.c
+++ b/arch/s390/kernel/uv.c
@@ -258,7 +258,7 @@ static bool should_export_before_import(struct uv_cb_header *uvcb, struct mm_str
 	 * shared page from a different protected VM will automatically also
 	 * transfer its ownership.
 	 */
-	if (test_bit_inv(BIT_UV_FEAT_MISC, &uv_info.uv_feature_indications))
+	if (uv_has_feature(BIT_UV_FEAT_MISC))
 		return false;
 	if (uvcb->cmd == UVC_CMD_UNPIN_PAGE_SHARED)
 		return false;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index e6511608280c..813cc3d59c90 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -2406,7 +2406,7 @@ static int kvm_s390_cpus_to_pv(struct kvm *kvm, u16 *rc, u16 *rrc)
 	struct kvm_vcpu *vcpu;
 
 	/* Disable the GISA if the ultravisor does not support AIV. */
-	if (!test_bit_inv(BIT_UV_FEAT_AIV, &uv_info.uv_feature_indications))
+	if (!uv_has_feature(BIT_UV_FEAT_AIV))
 		kvm_s390_gisa_disable(kvm);
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index dbe8394234e2..390819d03215 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -825,7 +825,7 @@ void do_secure_storage_access(struct pt_regs *regs)
 	 * reliable without the misc UV feature so we need to check
 	 * for that as well.
 	 */
-	if (test_bit_inv(BIT_UV_FEAT_MISC, &uv_info.uv_feature_indications) &&
+	if (uv_has_feature(BIT_UV_FEAT_MISC) &&
 	    !test_bit_inv(61, &regs->int_parm_long)) {
 		/*
 		 * When this happens, userspace did something that it

From 19c654bf05ae33ad0a2a9c039d5fe7d411a8bb06 Mon Sep 17 00:00:00 2001
From: Steffen Eiden <seiden@linux.ibm.com>
Date: Tue, 15 Aug 2023 17:14:14 +0200
Subject: [PATCH 0742/1189] KVM: s390: Add UV feature negotiation

Add a uv_feature list for pv-guests to the KVM cpu-model.
The feature bits 'AP-interpretation for secure guests' and
'AP-interrupt for secure guests' are available.

Signed-off-by: Steffen Eiden <seiden@linux.ibm.com>
Reviewed-by: Janosch Frank <frankja@linux.ibm.com>
Reviewed-by: Michael Mueller <mimu@linux.ibm.com>
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Link: https://lore.kernel.org/r/20230815151415.379760-4-seiden@linux.ibm.com
Message-Id: <20230815151415.379760-4-seiden@linux.ibm.com>
---
 arch/s390/include/asm/kvm_host.h |  2 +
 arch/s390/include/uapi/asm/kvm.h | 16 +++++++
 arch/s390/kvm/kvm-s390.c         | 73 ++++++++++++++++++++++++++++++++
 3 files changed, 91 insertions(+)

diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 91bfecb91321..427f9528a7b6 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -817,6 +817,8 @@ struct kvm_s390_cpu_model {
 	__u64 *fac_list;
 	u64 cpuid;
 	unsigned short ibc;
+	/* subset of available UV-features for pv-guests enabled by user space */
+	struct kvm_s390_vm_cpu_uv_feat uv_feat_guest;
 };
 
 typedef int (*crypto_hook)(struct kvm_vcpu *vcpu);
diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h
index a73cf01a1606..abe926d43cbe 100644
--- a/arch/s390/include/uapi/asm/kvm.h
+++ b/arch/s390/include/uapi/asm/kvm.h
@@ -159,6 +159,22 @@ struct kvm_s390_vm_cpu_subfunc {
 	__u8 reserved[1728];
 };
 
+#define KVM_S390_VM_CPU_PROCESSOR_UV_FEAT_GUEST	6
+#define KVM_S390_VM_CPU_MACHINE_UV_FEAT_GUEST	7
+
+#define KVM_S390_VM_CPU_UV_FEAT_NR_BITS	64
+struct kvm_s390_vm_cpu_uv_feat {
+	union {
+		struct {
+			__u64 : 4;
+			__u64 ap : 1;		/* bit 4 */
+			__u64 ap_intr : 1;	/* bit 5 */
+			__u64 : 58;
+		};
+		__u64 feat;
+	};
+};
+
 /* kvm attributes for crypto */
 #define KVM_S390_VM_CRYPTO_ENABLE_AES_KW	0
 #define KVM_S390_VM_CRYPTO_ENABLE_DEA_KW	1
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 813cc3d59c90..b3f17e014cab 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1531,6 +1531,39 @@ static int kvm_s390_set_processor_subfunc(struct kvm *kvm,
 	return 0;
 }
 
+#define KVM_S390_VM_CPU_UV_FEAT_GUEST_MASK	\
+(						\
+	((struct kvm_s390_vm_cpu_uv_feat){	\
+		.ap = 1,			\
+		.ap_intr = 1,			\
+	})					\
+	.feat					\
+)
+
+static int kvm_s390_set_uv_feat(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+	struct kvm_s390_vm_cpu_uv_feat __user *ptr = (void __user *)attr->addr;
+	unsigned long data, filter;
+
+	filter = uv_info.uv_feature_indications & KVM_S390_VM_CPU_UV_FEAT_GUEST_MASK;
+	if (get_user(data, &ptr->feat))
+		return -EFAULT;
+	if (!bitmap_subset(&data, &filter, KVM_S390_VM_CPU_UV_FEAT_NR_BITS))
+		return -EINVAL;
+
+	mutex_lock(&kvm->lock);
+	if (kvm->created_vcpus) {
+		mutex_unlock(&kvm->lock);
+		return -EBUSY;
+	}
+	kvm->arch.model.uv_feat_guest.feat = data;
+	mutex_unlock(&kvm->lock);
+
+	VM_EVENT(kvm, 3, "SET: guest UV-feat: 0x%16.16lx", data);
+
+	return 0;
+}
+
 static int kvm_s390_set_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr)
 {
 	int ret = -ENXIO;
@@ -1545,6 +1578,9 @@ static int kvm_s390_set_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr)
 	case KVM_S390_VM_CPU_PROCESSOR_SUBFUNC:
 		ret = kvm_s390_set_processor_subfunc(kvm, attr);
 		break;
+	case KVM_S390_VM_CPU_PROCESSOR_UV_FEAT_GUEST:
+		ret = kvm_s390_set_uv_feat(kvm, attr);
+		break;
 	}
 	return ret;
 }
@@ -1777,6 +1813,33 @@ static int kvm_s390_get_machine_subfunc(struct kvm *kvm,
 	return 0;
 }
 
+static int kvm_s390_get_processor_uv_feat(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+	struct kvm_s390_vm_cpu_uv_feat __user *dst = (void __user *)attr->addr;
+	unsigned long feat = kvm->arch.model.uv_feat_guest.feat;
+
+	if (put_user(feat, &dst->feat))
+		return -EFAULT;
+	VM_EVENT(kvm, 3, "GET: guest UV-feat: 0x%16.16lx", feat);
+
+	return 0;
+}
+
+static int kvm_s390_get_machine_uv_feat(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+	struct kvm_s390_vm_cpu_uv_feat __user *dst = (void __user *)attr->addr;
+	unsigned long feat;
+
+	BUILD_BUG_ON(sizeof(*dst) != sizeof(uv_info.uv_feature_indications));
+
+	feat = uv_info.uv_feature_indications & KVM_S390_VM_CPU_UV_FEAT_GUEST_MASK;
+	if (put_user(feat, &dst->feat))
+		return -EFAULT;
+	VM_EVENT(kvm, 3, "GET: guest UV-feat: 0x%16.16lx", feat);
+
+	return 0;
+}
+
 static int kvm_s390_get_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr)
 {
 	int ret = -ENXIO;
@@ -1800,6 +1863,12 @@ static int kvm_s390_get_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr)
 	case KVM_S390_VM_CPU_MACHINE_SUBFUNC:
 		ret = kvm_s390_get_machine_subfunc(kvm, attr);
 		break;
+	case KVM_S390_VM_CPU_PROCESSOR_UV_FEAT_GUEST:
+		ret = kvm_s390_get_processor_uv_feat(kvm, attr);
+		break;
+	case KVM_S390_VM_CPU_MACHINE_UV_FEAT_GUEST:
+		ret = kvm_s390_get_machine_uv_feat(kvm, attr);
+		break;
 	}
 	return ret;
 }
@@ -1952,6 +2021,8 @@ static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr)
 		case KVM_S390_VM_CPU_MACHINE_FEAT:
 		case KVM_S390_VM_CPU_MACHINE_SUBFUNC:
 		case KVM_S390_VM_CPU_PROCESSOR_SUBFUNC:
+		case KVM_S390_VM_CPU_MACHINE_UV_FEAT_GUEST:
+		case KVM_S390_VM_CPU_PROCESSOR_UV_FEAT_GUEST:
 			ret = 0;
 			break;
 		default:
@@ -3296,6 +3367,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	kvm->arch.model.cpuid = kvm_s390_get_initial_cpuid();
 	kvm->arch.model.ibc = sclp.ibc & 0x0fff;
 
+	kvm->arch.model.uv_feat_guest.feat = 0;
+
 	kvm_s390_crypto_init(kvm);
 
 	if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) {

From 899e2206f46aece42d8194c350bc1de71344dbc7 Mon Sep 17 00:00:00 2001
From: Steffen Eiden <seiden@linux.ibm.com>
Date: Tue, 15 Aug 2023 17:14:15 +0200
Subject: [PATCH 0743/1189] KVM: s390: pv: Allow AP-instructions for pv-guests

Introduces new feature bits and enablement flags for AP and AP IRQ
support.

Signed-off-by: Steffen Eiden <seiden@linux.ibm.com>
Reviewed-by: Janosch Frank <frankja@linux.ibm.com>
Reviewed-by: Michael Mueller <mimu@linux.ibm.com>
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Link: https://lore.kernel.org/r/20230815151415.379760-5-seiden@linux.ibm.com
Message-Id: <20230815151415.379760-5-seiden@linux.ibm.com>
---
 arch/s390/include/asm/uv.h | 12 +++++++++++-
 arch/s390/kvm/pv.c         |  6 ++++--
 2 files changed, 15 insertions(+), 3 deletions(-)

diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h
index 823adfff7315..0e7bd3873907 100644
--- a/arch/s390/include/asm/uv.h
+++ b/arch/s390/include/asm/uv.h
@@ -99,6 +99,8 @@ enum uv_cmds_inst {
 enum uv_feat_ind {
 	BIT_UV_FEAT_MISC = 0,
 	BIT_UV_FEAT_AIV = 1,
+	BIT_UV_FEAT_AP = 4,
+	BIT_UV_FEAT_AP_INTR = 5,
 };
 
 struct uv_cb_header {
@@ -159,7 +161,15 @@ struct uv_cb_cgc {
 	u64 guest_handle;
 	u64 conf_base_stor_origin;
 	u64 conf_virt_stor_origin;
-	u64 reserved30;
+	u8  reserved30[6];
+	union {
+		struct {
+			u16 : 14;
+			u16 ap_instr_intr : 1;
+			u16 ap_allow_instr : 1;
+		};
+		u16 raw;
+	} flags;
 	u64 guest_stor_origin;
 	u64 guest_stor_len;
 	u64 guest_sca;
diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c
index beeebc11b1a1..22fb482f042d 100644
--- a/arch/s390/kvm/pv.c
+++ b/arch/s390/kvm/pv.c
@@ -572,12 +572,14 @@ int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
 	uvcb.conf_base_stor_origin =
 		virt_to_phys((void *)kvm->arch.pv.stor_base);
 	uvcb.conf_virt_stor_origin = (u64)kvm->arch.pv.stor_var;
+	uvcb.flags.ap_allow_instr = kvm->arch.model.uv_feat_guest.ap;
+	uvcb.flags.ap_instr_intr = kvm->arch.model.uv_feat_guest.ap_intr;
 
 	cc = uv_call_sched(0, (u64)&uvcb);
 	*rc = uvcb.header.rc;
 	*rrc = uvcb.header.rrc;
-	KVM_UV_EVENT(kvm, 3, "PROTVIRT CREATE VM: handle %llx len %llx rc %x rrc %x",
-		     uvcb.guest_handle, uvcb.guest_stor_len, *rc, *rrc);
+	KVM_UV_EVENT(kvm, 3, "PROTVIRT CREATE VM: handle %llx len %llx rc %x rrc %x flags %04x",
+		     uvcb.guest_handle, uvcb.guest_stor_len, *rc, *rrc, uvcb.flags.raw);
 
 	/* Outputs */
 	kvm->arch.pv.handle = uvcb.guest_handle;

From 11b0b802f8e38d48ca74d520028add81263f003e Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Mon, 28 Aug 2023 15:23:16 +0200
Subject: [PATCH 0744/1189] ASoC: codecs: wcd93xx: fix object added to multiple
 drivers

Three Qualcomm audio codecs (WCD9355, WCD934x and WCD938x) use the same
object file wcd-clsh-v2.o leading to warnings:

  Makefile: wcd-clsh-v2.o is added to multiple modules: snd-soc-wcd9335 snd-soc-wcd934x snd-soc-wcd938x

Convert the wcd-clsh-v2.o to a module to solve it.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org
Link: https://lore.kernel.org/r/20230828132316.190386-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org
---
 sound/soc/codecs/Kconfig       | 6 ++++++
 sound/soc/codecs/Makefile      | 8 +++++---
 sound/soc/codecs/wcd-clsh-v2.c | 8 ++++++++
 3 files changed, 19 insertions(+), 3 deletions(-)

diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index 95b5bd883215..f1e1dbc509f6 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -1968,11 +1968,15 @@ config SND_SOC_UDA1380
 	tristate
 	depends on I2C
 
+config SND_SOC_WCD_CLASSH
+	tristate
+
 config SND_SOC_WCD9335
 	tristate "WCD9335 Codec"
 	depends on SLIMBUS
 	select REGMAP_SLIMBUS
 	select REGMAP_IRQ
+	select SND_SOC_WCD_CLASSH
 	help
 	  The WCD9335 is a standalone Hi-Fi audio CODEC IC, supports
 	  Qualcomm Technologies, Inc. (QTI) multimedia solutions,
@@ -1987,6 +1991,7 @@ config SND_SOC_WCD934X
 	depends on SLIMBUS
 	select REGMAP_IRQ
 	select REGMAP_SLIMBUS
+	select SND_SOC_WCD_CLASSH
 	select SND_SOC_WCD_MBHC
 	depends on MFD_WCD934X || COMPILE_TEST
 	help
@@ -1997,6 +2002,7 @@ config SND_SOC_WCD938X
 	depends on SND_SOC_WCD938X_SDW
 	tristate
 	depends on SOUNDWIRE || !SOUNDWIRE
+	select SND_SOC_WCD_CLASSH
 
 config SND_SOC_WCD938X_SDW
 	tristate "WCD9380/WCD9385 Codec - SDW"
diff --git a/sound/soc/codecs/Makefile b/sound/soc/codecs/Makefile
index c8502a49b40a..a87e56938ce5 100644
--- a/sound/soc/codecs/Makefile
+++ b/sound/soc/codecs/Makefile
@@ -303,10 +303,11 @@ snd-soc-twl4030-objs := twl4030.o
 snd-soc-twl6040-objs := twl6040.o
 snd-soc-uda1334-objs := uda1334.o
 snd-soc-uda1380-objs := uda1380.o
+snd-soc-wcd-classh-objs := wcd-clsh-v2.o
 snd-soc-wcd-mbhc-objs := wcd-mbhc-v2.o
-snd-soc-wcd9335-objs := wcd-clsh-v2.o wcd9335.o
-snd-soc-wcd934x-objs := wcd-clsh-v2.o wcd934x.o
-snd-soc-wcd938x-objs := wcd938x.o wcd-clsh-v2.o
+snd-soc-wcd9335-objs := wcd9335.o
+snd-soc-wcd934x-objs := wcd934x.o
+snd-soc-wcd938x-objs := wcd938x.o
 snd-soc-wcd938x-sdw-objs := wcd938x-sdw.o
 snd-soc-wl1273-objs := wl1273.o
 snd-soc-wm-adsp-objs := wm_adsp.o
@@ -685,6 +686,7 @@ obj-$(CONFIG_SND_SOC_TWL4030)	+= snd-soc-twl4030.o
 obj-$(CONFIG_SND_SOC_TWL6040)	+= snd-soc-twl6040.o
 obj-$(CONFIG_SND_SOC_UDA1334)	+= snd-soc-uda1334.o
 obj-$(CONFIG_SND_SOC_UDA1380)	+= snd-soc-uda1380.o
+obj-$(CONFIG_SND_SOC_WCD_CLASSH)	+= snd-soc-wcd-classh.o
 obj-$(CONFIG_SND_SOC_WCD_MBHC)	+= snd-soc-wcd-mbhc.o
 obj-$(CONFIG_SND_SOC_WCD9335)	+= snd-soc-wcd9335.o
 obj-$(CONFIG_SND_SOC_WCD934X)	+= snd-soc-wcd934x.o
diff --git a/sound/soc/codecs/wcd-clsh-v2.c b/sound/soc/codecs/wcd-clsh-v2.c
index a75db27e5205..d96e23ec43d4 100644
--- a/sound/soc/codecs/wcd-clsh-v2.c
+++ b/sound/soc/codecs/wcd-clsh-v2.c
@@ -355,6 +355,7 @@ void wcd_clsh_set_hph_mode(struct wcd_clsh_ctrl *ctrl, int mode)
 		wcd_clsh_v2_set_hph_mode(comp, mode);
 
 }
+EXPORT_SYMBOL_GPL(wcd_clsh_set_hph_mode);
 
 static void wcd_clsh_set_flyback_current(struct snd_soc_component *comp,
 					 int mode)
@@ -869,11 +870,13 @@ int wcd_clsh_ctrl_set_state(struct wcd_clsh_ctrl *ctrl,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(wcd_clsh_ctrl_set_state);
 
 int wcd_clsh_ctrl_get_state(struct wcd_clsh_ctrl *ctrl)
 {
 	return ctrl->state;
 }
+EXPORT_SYMBOL_GPL(wcd_clsh_ctrl_get_state);
 
 struct wcd_clsh_ctrl *wcd_clsh_ctrl_alloc(struct snd_soc_component *comp,
 					  int version)
@@ -890,8 +893,13 @@ struct wcd_clsh_ctrl *wcd_clsh_ctrl_alloc(struct snd_soc_component *comp,
 
 	return ctrl;
 }
+EXPORT_SYMBOL_GPL(wcd_clsh_ctrl_alloc);
 
 void wcd_clsh_ctrl_free(struct wcd_clsh_ctrl *ctrl)
 {
 	kfree(ctrl);
 }
+EXPORT_SYMBOL_GPL(wcd_clsh_ctrl_free);
+
+MODULE_DESCRIPTION("WCD93XX Class-H driver");
+MODULE_LICENSE("GPL");

From 03ce34cf8f50e4c62f9a4b62caffdba1165ca977 Mon Sep 17 00:00:00 2001
From: Max Filippov <jcmvbkbc@gmail.com>
Date: Fri, 31 Jan 2020 21:33:28 -0800
Subject: [PATCH 0745/1189] xtensa: add XIP-aware MTD support

Add Kconfig symbol, asm/mtd-xip.h header and define related macros:
xip_cpu_idle, xip_irqpending, xip_currtime and xip_elapsed_since.
Append .xiptext to the vectors when separate vectors are configured
because otherwise they are appended to the data and data may not even be
executable in XIP configuration.

Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
---
 arch/xtensa/Kconfig                |  3 +++
 arch/xtensa/include/asm/mtd-xip.h  | 14 ++++++++++++++
 arch/xtensa/include/asm/sections.h |  4 ++++
 arch/xtensa/kernel/setup.c         |  3 +++
 arch/xtensa/kernel/vmlinux.lds.S   | 11 ++++++++++-
 5 files changed, 34 insertions(+), 1 deletion(-)
 create mode 100644 arch/xtensa/include/asm/mtd-xip.h

diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 2a51a466779f..070a112b7dbe 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -70,6 +70,9 @@ config ARCH_HAS_ILOG2_U32
 config ARCH_HAS_ILOG2_U64
 	def_bool n
 
+config ARCH_MTD_XIP
+	def_bool y
+
 config NO_IOPORT_MAP
 	def_bool n
 
diff --git a/arch/xtensa/include/asm/mtd-xip.h b/arch/xtensa/include/asm/mtd-xip.h
new file mode 100644
index 000000000000..514325155cf8
--- /dev/null
+++ b/arch/xtensa/include/asm/mtd-xip.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef _ASM_MTD_XIP_H
+#define _ASM_MTD_XIP_H
+
+#include <asm/processor.h>
+
+#define xip_irqpending()	(xtensa_get_sr(interrupt) & xtensa_get_sr(intenable))
+#define xip_currtime()		(xtensa_get_sr(ccount))
+#define xip_elapsed_since(x)	((xtensa_get_sr(ccount) - (x)) / 1000) /* should work up to 1GHz */
+#define xip_cpu_idle()		do { asm volatile ("waiti 0"); } while (0)
+
+#endif /* _ASM_MTD_XIP_H */
+
diff --git a/arch/xtensa/include/asm/sections.h b/arch/xtensa/include/asm/sections.h
index 3bc6b9afa993..e5da6d7092be 100644
--- a/arch/xtensa/include/asm/sections.h
+++ b/arch/xtensa/include/asm/sections.h
@@ -34,6 +34,10 @@ extern char _SecondaryResetVector_text_start[];
 extern char _SecondaryResetVector_text_end[];
 #endif
 #ifdef CONFIG_XIP_KERNEL
+#ifdef CONFIG_VECTORS_ADDR
+extern char _xip_text_start[];
+extern char _xip_text_end[];
+#endif
 extern char _xip_start[];
 extern char _xip_end[];
 #endif
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index aba3ff4e60d8..52d6e4870a04 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -311,6 +311,9 @@ void __init setup_arch(char **cmdline_p)
 
 	mem_reserve(__pa(_stext), __pa(_end));
 #ifdef CONFIG_XIP_KERNEL
+#ifdef CONFIG_VECTORS_ADDR
+	mem_reserve(__pa(_xip_text_start), __pa(_xip_text_end));
+#endif
 	mem_reserve(__pa(_xip_start), __pa(_xip_end));
 #endif
 
diff --git a/arch/xtensa/kernel/vmlinux.lds.S b/arch/xtensa/kernel/vmlinux.lds.S
index c14fd96f459d..f47e9bbbd291 100644
--- a/arch/xtensa/kernel/vmlinux.lds.S
+++ b/arch/xtensa/kernel/vmlinux.lds.S
@@ -118,6 +118,7 @@ SECTIONS
     SECTION_VECTOR2 (.DoubleExceptionVector.text, DOUBLEEXC_VECTOR_VADDR)
 
     *(.exception.text)
+    *(.xiptext)
 #endif
 
     IRQENTRY_TEXT
@@ -201,6 +202,9 @@ SECTIONS
 		   .DebugInterruptVector.text);
     RELOCATE_ENTRY(_exception_text,
 		   .exception.text);
+#ifdef CONFIG_XIP_KERNEL
+    RELOCATE_ENTRY(_xip_text, .xiptext);
+#endif
 #endif
 #ifdef CONFIG_XIP_KERNEL
     RELOCATE_ENTRY(_xip_data, .data);
@@ -319,7 +323,12 @@ SECTIONS
 		  LAST)
 #undef LAST
 #define LAST .exception.text
-
+  SECTION_VECTOR4 (_xip_text,
+		  .xiptext,
+		  ,
+		  LAST)
+#undef LAST
+#define LAST .xiptext
 #endif
   . = (LOADADDR(LAST) + SIZEOF(LAST) + 3) & ~ 3;
 

From 50011c2a245792993f2756e5b5b571512bfa409e Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 24 Aug 2023 18:45:32 -0700
Subject: [PATCH 0746/1189] KVM: VMX: Refresh available regs and IDT vectoring
 info before NMI handling

Reset the mask of available "registers" and refresh the IDT vectoring
info snapshot in vmx_vcpu_enter_exit(), before KVM potentially handles a
an NMI VM-Exit.  One of the "registers" that KVM VMX lazily loads is the
vmcs.VM_EXIT_INTR_INFO field, which is holds the vector+type on "exception
or NMI" VM-Exits, i.e. is needed to identify NMIs.  Clearing the available
registers bitmask after handling NMIs results in KVM querying info from
the last VM-Exit that read vmcs.VM_EXIT_INTR_INFO, and leads to both
missed NMIs and spurious NMIs in the host.

Opportunistically grab vmcs.IDT_VECTORING_INFO_FIELD early in the VM-Exit
path too, e.g. to guard against similar consumption of stale data.  The
field is read on every "normal" VM-Exit, and there's no point in delaying
the inevitable.

Reported-by: Like Xu <like.xu.linux@gmail.com>
Fixes: 11df586d774f ("KVM: VMX: Handle NMI VM-Exits in noinstr region")
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230825014532.2846714-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/vmx/vmx.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index b0093b8a72d2..7625d74c056a 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -7209,13 +7209,20 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 				   flags);
 
 	vcpu->arch.cr2 = native_read_cr2();
+	vcpu->arch.regs_avail &= ~VMX_REGS_LAZY_LOAD_SET;
+
+	vmx->idt_vectoring_info = 0;
 
 	vmx_enable_fb_clear(vmx);
 
-	if (unlikely(vmx->fail))
+	if (unlikely(vmx->fail)) {
 		vmx->exit_reason.full = 0xdead;
-	else
-		vmx->exit_reason.full = vmcs_read32(VM_EXIT_REASON);
+		goto out;
+	}
+
+	vmx->exit_reason.full = vmcs_read32(VM_EXIT_REASON);
+	if (likely(!vmx->exit_reason.failed_vmentry))
+		vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
 
 	if ((u16)vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI &&
 	    is_nmi(vmx_get_intr_info(vcpu))) {
@@ -7224,6 +7231,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 		kvm_after_interrupt(vcpu);
 	}
 
+out:
 	guest_state_exit_irqoff();
 }
 
@@ -7345,8 +7353,6 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	loadsegment(es, __USER_DS);
 #endif
 
-	vcpu->arch.regs_avail &= ~VMX_REGS_LAZY_LOAD_SET;
-
 	pt_guest_exit(vmx);
 
 	kvm_load_host_xsave_state(vcpu);
@@ -7363,17 +7369,12 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		vmx->nested.nested_run_pending = 0;
 	}
 
-	vmx->idt_vectoring_info = 0;
-
 	if (unlikely(vmx->fail))
 		return EXIT_FASTPATH_NONE;
 
 	if (unlikely((u16)vmx->exit_reason.basic == EXIT_REASON_MCE_DURING_VMENTRY))
 		kvm_machine_check();
 
-	if (likely(!vmx->exit_reason.failed_vmentry))
-		vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
-
 	trace_kvm_exit(vcpu, KVM_ISA_VMX);
 
 	if (unlikely(vmx->exit_reason.failed_vmentry))

From bfd73b601ac880d7cfbafbb770c3d6195e73add3 Mon Sep 17 00:00:00 2001
From: Vlad Karpovich <vkarpovi@opensource.cirrus.com>
Date: Mon, 28 Aug 2023 12:05:19 -0500
Subject: [PATCH 0747/1189] ASoC: cs35l45: Add support for Chip ID 0x35A460

The 0x35A460 chip is a different variant of the cs35l45.

Signed-off-by: Vlad Karpovich <vkarpovi@opensource.cirrus.com
Acked-by: Charles Keepax <ckeepax@opensource.cirrus.com
Link: https://lore.kernel.org/r/20230828170525.335671-1-vkarpovi@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org
---
 sound/soc/codecs/cs35l45.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/codecs/cs35l45.c b/sound/soc/codecs/cs35l45.c
index d1edb9876c10..aa5a54e960b0 100644
--- a/sound/soc/codecs/cs35l45.c
+++ b/sound/soc/codecs/cs35l45.c
@@ -1078,6 +1078,7 @@ static int cs35l45_initialize(struct cs35l45_private *cs35l45)
 
 	switch (dev_id[0]) {
 	case 0x35A450:
+	case 0x35A460:
 		break;
 	default:
 		dev_err(cs35l45->dev, "Bad DEVID 0x%x\n", dev_id[0]);

From a47f7bf97c9836ff312b421fe392f13401c60c7b Mon Sep 17 00:00:00 2001
From: Vlad Karpovich <vkarpovi@opensource.cirrus.com>
Date: Mon, 28 Aug 2023 12:05:20 -0500
Subject: [PATCH 0748/1189] ASoC: cs35l45: Fix "Dead assigment" warning

Value stored to 'ret' is never read. Remove it.

Signed-off-by: Vlad Karpovich <vkarpovi@opensource.cirrus.com
Acked-by: Charles Keepax <ckeepax@opensource.cirrus.com
Link: https://lore.kernel.org/r/20230828170525.335671-2-vkarpovi@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org
---
 sound/soc/codecs/cs35l45.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/cs35l45.c b/sound/soc/codecs/cs35l45.c
index aa5a54e960b0..3daec251a42d 100644
--- a/sound/soc/codecs/cs35l45.c
+++ b/sound/soc/codecs/cs35l45.c
@@ -969,7 +969,7 @@ static irqreturn_t cs35l45_dsp_virt2_mbox_cb(int irq, void *data)
 
 	ret = regmap_read(cs35l45->regmap, CS35L45_DSP_VIRT2_MBOX_3, &mbox_val);
 	if (!ret && mbox_val)
-		ret = cs35l45_dsp_virt2_mbox3_irq_handle(cs35l45, mbox_val & CS35L45_MBOX3_CMD_MASK,
+		cs35l45_dsp_virt2_mbox3_irq_handle(cs35l45, mbox_val & CS35L45_MBOX3_CMD_MASK,
 				(mbox_val & CS35L45_MBOX3_DATA_MASK) >> CS35L45_MBOX3_DATA_SHIFT);
 
 	/* Handle DSP trace log IRQ */

From e041b85006f40a4f9799c385ec1a7fb8bdb0c228 Mon Sep 17 00:00:00 2001
From: Vlad Karpovich <vkarpovi@opensource.cirrus.com>
Date: Mon, 28 Aug 2023 12:05:23 -0500
Subject: [PATCH 0749/1189] ASoC: cs35l45: Rename DACPCM1 Source control

Rename control to "DACPCM Source" for backward compatibility
with previous implementation.

Signed-off-by: Vlad Karpovich <vkarpovi@opensource.cirrus.com
Acked-by: Charles Keepax <ckeepax@opensource.cirrus.com
Link: https://lore.kernel.org/r/20230828170525.335671-5-vkarpovi@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org
---
 sound/soc/codecs/cs35l45.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/sound/soc/codecs/cs35l45.c b/sound/soc/codecs/cs35l45.c
index 3daec251a42d..be4f4229576c 100644
--- a/sound/soc/codecs/cs35l45.c
+++ b/sound/soc/codecs/cs35l45.c
@@ -279,7 +279,7 @@ static const struct snd_kcontrol_new cs35l45_dsp_muxes[] = {
 };
 
 static const struct snd_kcontrol_new cs35l45_dac_muxes[] = {
-	SOC_DAPM_ENUM("DACPCM1 Source", cs35l45_dacpcm_enums[0]),
+	SOC_DAPM_ENUM("DACPCM Source", cs35l45_dacpcm_enums[0]),
 };
 
 static const struct snd_soc_dapm_widget cs35l45_dapm_widgets[] = {
@@ -333,7 +333,7 @@ static const struct snd_soc_dapm_widget cs35l45_dapm_widgets[] = {
 	SND_SOC_DAPM_MUX("DSP_RX7 Source", SND_SOC_NOPM, 0, 0, &cs35l45_dsp_muxes[6]),
 	SND_SOC_DAPM_MUX("DSP_RX8 Source", SND_SOC_NOPM, 0, 0, &cs35l45_dsp_muxes[7]),
 
-	SND_SOC_DAPM_MUX("DACPCM1 Source", SND_SOC_NOPM, 0, 0, &cs35l45_dac_muxes[0]),
+	SND_SOC_DAPM_MUX("DACPCM Source", SND_SOC_NOPM, 0, 0, &cs35l45_dac_muxes[0]),
 
 	SND_SOC_DAPM_OUT_DRV("AMP", SND_SOC_NOPM, 0, 0, NULL, 0),
 
@@ -403,7 +403,7 @@ static const struct snd_soc_dapm_route cs35l45_dapm_routes[] = {
 	{ "ASP_RX1", NULL, "ASP_EN" },
 	{ "ASP_RX2", NULL, "ASP_EN" },
 
-	{ "AMP", NULL, "DACPCM1 Source"},
+	{ "AMP", NULL, "DACPCM Source"},
 	{ "AMP", NULL, "GLOBAL_EN"},
 
 	CS35L45_DSP_MUX_ROUTE("DSP_RX1"),
@@ -427,7 +427,7 @@ static const struct snd_soc_dapm_route cs35l45_dapm_routes[] = {
 	{"DSP1 Preload", NULL, "DSP1 Preloader"},
 	{"DSP1", NULL, "DSP1 Preloader"},
 
-	CS35L45_DAC_MUX_ROUTE("DACPCM1"),
+	CS35L45_DAC_MUX_ROUTE("DACPCM"),
 
 	{ "SPK", NULL, "AMP"},
 };

From 9e07f8bfd959d2d09823430eab35d12182446dcf Mon Sep 17 00:00:00 2001
From: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Date: Tue, 29 Aug 2023 00:36:35 -0700
Subject: [PATCH 0750/1189] ASoC: cs42l43: Fix missing error code in
 cs42l43_codec_probe()

When clk_get_optional() fails, the error handling code does a 'goto
err_pm' with ret = 0, which is resturning success on a failure path.

Fix this by assigning the PTR_ERR(priv-mclk) to ret variable.

Fixes: fc918cbe874e ("ASoC: cs42l43: Add support for the cs42l43")
Signed-off-by: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com
Acked-by: Charles Keepax <ckeepax@opensource.cirrus.com
Link: https://lore.kernel.org/r/20230829073635.1877367-1-harshit.m.mogalapalli@oracle.com
Signed-off-by: Mark Brown <broonie@kernel.org
---
 sound/soc/codecs/cs42l43.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/sound/soc/codecs/cs42l43.c b/sound/soc/codecs/cs42l43.c
index 24e718e51174..1a95c370fc4c 100644
--- a/sound/soc/codecs/cs42l43.c
+++ b/sound/soc/codecs/cs42l43.c
@@ -2205,7 +2205,8 @@ static int cs42l43_codec_probe(struct platform_device *pdev)
 	// Don't use devm as we need to get against the MFD device
 	priv->mclk = clk_get_optional(cs42l43->dev, "mclk");
 	if (IS_ERR(priv->mclk)) {
-		dev_err_probe(priv->dev, PTR_ERR(priv->mclk), "Failed to get mclk\n");
+		ret = PTR_ERR(priv->mclk);
+		dev_err_probe(priv->dev, ret, "Failed to get mclk\n");
 		goto err_pm;
 	}
 

From b5f3cec3159dd28563e5a88096769f7b77272790 Mon Sep 17 00:00:00 2001
From: Adam Ford <aford173@gmail.com>
Date: Sat, 26 Aug 2023 21:31:53 -0500
Subject: [PATCH 0751/1189] ASoC: dt-bindings: fsl_easrc: Add support for
 imx8mp-easrc

The i.MX8MP appears to have the same easrc support as the Nano, so
add imx8mp as an option with a fallback to imx8mn.

Signed-off-by: Adam Ford <aford173@gmail.com
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org
Acked-by: Conor Dooley <conor.dooley@microchip.com
Link: https://lore.kernel.org/r/20230827023155.467807-1-aford173@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org
---
 Documentation/devicetree/bindings/sound/fsl,easrc.yaml | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/sound/fsl,easrc.yaml b/Documentation/devicetree/bindings/sound/fsl,easrc.yaml
index bdde68a1059c..a680d7aff237 100644
--- a/Documentation/devicetree/bindings/sound/fsl,easrc.yaml
+++ b/Documentation/devicetree/bindings/sound/fsl,easrc.yaml
@@ -14,7 +14,13 @@ properties:
     pattern: "^easrc@.*"
 
   compatible:
-    const: fsl,imx8mn-easrc
+    oneOf:
+      - enum:
+          - fsl,imx8mn-easrc
+      - items:
+          - enum:
+              - fsl,imx8mp-easrc
+          - const: fsl,imx8mn-easrc
 
   reg:
     maxItems: 1

From c56f286f24c4b56d9ae81fa381c02af56ab9bfb2 Mon Sep 17 00:00:00 2001
From: Yanteng Si <siyanteng@loongson.cn>
Date: Fri, 25 Aug 2023 19:28:02 +0800
Subject: [PATCH 0752/1189] perf tools: Allow to use cpuinfo on LoongArch

Define these macros so that the CPU name can be displayed when running
'perf report' and 'perf timechart'.

Committer notes:

No need to have:

	if (strcasestr(buf, "Model Name")) {
		strlcpy(cpu_m, &buf[13], 255);
		break;
	} else if (strcasestr(buf, "model name")) {
		strlcpy(cpu_m, &buf[13], 255);
		break;
	}

As the point of strcasestr() is to be case insensitive to both the
haystack and the needle, so simplify the above to just:

	if (strcasestr(buf, "model name")) {
		strlcpy(cpu_m, &buf[13], 255);
		break;
	}

Signed-off-by: Yanteng Si <siyanteng@loongson.cn>
Acked-by: Huacai Chen <chenhuacai@loongson.cn>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: loongarch@lists.linux.dev
Cc: loongson-kernel@lists.loongnix.cn
Link: https://lore.kernel.org/r/db968a186a10e4629fe10c26a1210f7126ad41ec.1692962043.git.siyanteng@loongson.cn
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/header.c    | 2 ++
 tools/perf/util/svghelper.c | 2 +-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 9f35d86a3351..99c61cdffa54 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -456,6 +456,8 @@ static int write_cpudesc(struct feat_fd *ff,
 #define CPUINFO_PROC	{ "Processor", }
 #elif defined(__xtensa__)
 #define CPUINFO_PROC	{ "core ID", }
+#elif defined(__loongarch__)
+#define CPUINFO_PROC	{ "Model Name", }
 #else
 #define CPUINFO_PROC	{ "model name", }
 #endif
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 5c62d3118c41..0e4dc31c6c9c 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -331,7 +331,7 @@ static char *cpu_model(void)
 	file = fopen("/proc/cpuinfo", "r");
 	if (file) {
 		while (fgets(buf, 255, file)) {
-			if (strstr(buf, "model name")) {
+			if (strcasestr(buf, "model name")) {
 				strlcpy(cpu_m, &buf[13], 255);
 				break;
 			}

From 49cf0bf6379d95fc4124adf5a5eef22ff2e1795e Mon Sep 17 00:00:00 2001
From: Yanteng Si <siyanteng@loongson.cn>
Date: Fri, 25 Aug 2023 19:28:03 +0800
Subject: [PATCH 0753/1189] perf beauty mmap_flags: Fix script for archs that
 use the generic mman.h

To address this error:

  grep: /root/linux-next/tools/arch/xxxxx/include/uapi/asm//mman.h:
  No such file or directory

Signed-off-by: Yanteng Si <siyanteng@loongson.cn>
Acked-by: Huacai Chen <chenhuacai@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: loongarch@lists.linux.dev
Cc: loongson-kernel@lists.loongnix.cn
Link: https://lore.kernel.org/r/42e8e3565d6035302907426c1e65483b2a4007f5.1692962043.git.siyanteng@loongson.cn
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/mmap_flags.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/trace/beauty/mmap_flags.sh b/tools/perf/trace/beauty/mmap_flags.sh
index 3022597c8c17..d035b29fc5ec 100755
--- a/tools/perf/trace/beauty/mmap_flags.sh
+++ b/tools/perf/trace/beauty/mmap_flags.sh
@@ -19,7 +19,7 @@ arch_mman=${arch_header_dir}/mman.h
 
 printf "static const char *mmap_flags[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MAP_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*'
-grep -E -q $regex ${arch_mman} && \
+([ -f ${arch_mman} ] && grep -E -q $regex ${arch_mman}) && \
 (grep -E $regex ${arch_mman} | \
 	sed -r "s/$regex/\2 \1 \1 \1 \2/g"	| \
 	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n#ifndef MAP_%s\n#define MAP_%s %s\n#endif\n")

From f703073efff531c58d59fbc971598edb18933c66 Mon Sep 17 00:00:00 2001
From: Yanteng Si <siyanteng@loongson.cn>
Date: Fri, 25 Aug 2023 19:28:04 +0800
Subject: [PATCH 0754/1189] perf beauty mmap_flags: Use "test -f" instead of
 "[-f FILE]"

"[" is part of the shell builtin test (and a synonym for it),
 not a link to the external command /usr/bin/test.

Using the "test" is simpler because it avoids a lot of "[]".

Suggested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Yanteng Si <siyanteng@loongson.cn>
Acked-by: Huacai Chen <chenhuacai@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: loongarch@lists.linux.dev
Cc: loongson-kernel@lists.loongnix.cn
Link: https://lore.kernel.org/r/c50bc0a92dce0ff0fa6504c1a52fb53e2ac007bf.1692962043.git.siyanteng@loongson.cn
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/mmap_flags.sh | 9 ++++++---
 tools/perf/trace/beauty/mmap_prot.sh  | 5 +++--
 2 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/tools/perf/trace/beauty/mmap_flags.sh b/tools/perf/trace/beauty/mmap_flags.sh
index d035b29fc5ec..6ecdb3c5a99e 100755
--- a/tools/perf/trace/beauty/mmap_flags.sh
+++ b/tools/perf/trace/beauty/mmap_flags.sh
@@ -19,7 +19,8 @@ arch_mman=${arch_header_dir}/mman.h
 
 printf "static const char *mmap_flags[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MAP_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*'
-([ -f ${arch_mman} ] && grep -E -q $regex ${arch_mman}) && \
+test -f ${arch_mman} && \
+grep -E -q $regex ${arch_mman} && \
 (grep -E $regex ${arch_mman} | \
 	sed -r "s/$regex/\2 \1 \1 \1 \2/g"	| \
 	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n#ifndef MAP_%s\n#define MAP_%s %s\n#endif\n")
@@ -28,12 +29,14 @@ grep -E -q $regex ${linux_mman} && \
 	grep -E -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \
 	sed -r "s/$regex/\2 \1 \1 \1 \2/g" | \
 	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n#ifndef MAP_%s\n#define MAP_%s %s\n#endif\n")
-([ ! -f ${arch_mman} ] || grep -E -q '#[[:space:]]*include[[:space:]]+.*uapi/asm-generic/mman.*' ${arch_mman}) &&
+( ! test -f ${arch_mman} || \
+grep -E -q '#[[:space:]]*include[[:space:]]+.*uapi/asm-generic/mman.*' ${arch_mman}) &&
 (grep -E $regex ${header_dir}/mman-common.h | \
 	grep -E -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \
 	sed -r "s/$regex/\2 \1 \1 \1 \2/g"	| \
 	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n#ifndef MAP_%s\n#define MAP_%s %s\n#endif\n")
-([ ! -f ${arch_mman} ] || grep -E -q '#[[:space:]]*include[[:space:]]+.*uapi/asm-generic/mman.h>.*' ${arch_mman}) &&
+( ! test -f ${arch_mman} || \
+grep -E -q '#[[:space:]]*include[[:space:]]+.*uapi/asm-generic/mman.h>.*' ${arch_mman}) &&
 (grep -E $regex ${header_dir}/mman.h | \
 	sed -r "s/$regex/\2 \1 \1 \1 \2/g"	| \
 	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n#ifndef MAP_%s\n#define MAP_%s %s\n#endif\n")
diff --git a/tools/perf/trace/beauty/mmap_prot.sh b/tools/perf/trace/beauty/mmap_prot.sh
index 49e8c865214b..4436fcd6e861 100755
--- a/tools/perf/trace/beauty/mmap_prot.sh
+++ b/tools/perf/trace/beauty/mmap_prot.sh
@@ -17,12 +17,13 @@ prefix="PROT"
 
 printf "static const char *mmap_prot[] = {\n"
 regex=`printf '^[[:space:]]*#[[:space:]]*define[[:space:]]+%s_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*' ${prefix}`
-([ ! -f ${arch_mman} ] || grep -E -q '#[[:space:]]*include[[:space:]]+.*uapi/asm-generic/mman.*' ${arch_mman}) &&
+( ! test -f ${arch_mman} \
+|| grep -E -q '#[[:space:]]*include[[:space:]]+.*uapi/asm-generic/mman.*' ${arch_mman}) &&
 (grep -E $regex ${common_mman} | \
 	grep -E -vw PROT_NONE | \
 	sed -r "s/$regex/\2 \1 \1 \1 \2/g"	| \
 	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n#ifndef ${prefix}_%s\n#define ${prefix}_%s %s\n#endif\n")
-[ -f ${arch_mman} ] && grep -E -q $regex ${arch_mman} &&
+test -f ${arch_mman} && grep -E -q $regex ${arch_mman} &&
 (grep -E $regex ${arch_mman} | \
 	grep -E -vw PROT_NONE | \
 	sed -r "s/$regex/\2 \1 \1 \1 \2/g"	| \

From 8d9f5146f5dae2d80217f204d9abd83ef704aa12 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 25 Aug 2023 06:52:36 -0700
Subject: [PATCH 0755/1189] perf pmus: Sort pmus by name then suffix

Sort PMUs by name. If two PMUs have the same name but differ by
suffix, sort the suffixes numerically.

For example, "breakpoint" comes before "cpu",
"uncore_imc_free_running_0" comes before "uncore_imc_free_running_1".

Suffixes need to be treated specially as otherwise they will be ordered
like 0, 1, 10, 11, .., 2, 20, 21, .., etc. Only PMUs starting 'uncore_'
are considered to have a potential suffix.

Sorting of PMUs is done so that later patches can skip duplicate uncore
PMUs that differ only by there suffix.

Committer notes:

Used the more compact, intention revealing strstarts() function we got
from the kernel sources:

-       if (strncmp(str, "uncore_", 7))
+       if (!strstarts(str, "uncore_"))

Also in pmus_cmp() the lhs_num and rhs_num variables may end up not
being set for non "uncore_" prefixed PMUs in pmu_name_len_no_suffix(),
or at least gcc 7.5 in some distros (opensuse 15.5, to be EOLed in
Dec/2024) thins so, so initialize both to zero.

Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20230825135237.921058-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/pmus.c | 49 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 49 insertions(+)

diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c
index 4dd5912617ff..7316da1c0ddb 100644
--- a/tools/perf/util/pmus.c
+++ b/tools/perf/util/pmus.c
@@ -1,8 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/list.h>
+#include <linux/list_sort.h>
+#include <linux/string.h>
 #include <linux/zalloc.h>
 #include <subcmd/pager.h>
 #include <sys/types.h>
+#include <ctype.h>
 #include <dirent.h>
 #include <pthread.h>
 #include <string.h>
@@ -33,6 +36,31 @@ static LIST_HEAD(other_pmus);
 static bool read_sysfs_core_pmus;
 static bool read_sysfs_all_pmus;
 
+static int pmu_name_len_no_suffix(const char *str, unsigned long *num)
+{
+	int orig_len, len;
+
+	orig_len = len = strlen(str);
+
+	/* Non-uncore PMUs have their full length, for example, i915. */
+	if (!strstarts(str, "uncore_"))
+		return len;
+
+	/*
+	 * Count trailing digits and '_', if '_{num}' suffix isn't present use
+	 * the full length.
+	 */
+	while (len > 0 && isdigit(str[len - 1]))
+		len--;
+
+	if (len > 0 && len != orig_len && str[len - 1] == '_') {
+		if (num)
+			*num = strtoul(&str[len], NULL, 10);
+		return len - 1;
+	}
+	return orig_len;
+}
+
 void perf_pmus__destroy(void)
 {
 	struct perf_pmu *pmu, *tmp;
@@ -122,6 +150,25 @@ static struct perf_pmu *perf_pmu__find2(int dirfd, const char *name)
 	return perf_pmu__lookup(core_pmu ? &core_pmus : &other_pmus, dirfd, name);
 }
 
+static int pmus_cmp(void *priv __maybe_unused,
+		    const struct list_head *lhs, const struct list_head *rhs)
+{
+	unsigned long lhs_num = 0, rhs_num = 0;
+	struct perf_pmu *lhs_pmu = container_of(lhs, struct perf_pmu, list);
+	struct perf_pmu *rhs_pmu = container_of(rhs, struct perf_pmu, list);
+	const char *lhs_pmu_name = lhs_pmu->name ?: "";
+	const char *rhs_pmu_name = rhs_pmu->name ?: "";
+	int lhs_pmu_name_len = pmu_name_len_no_suffix(lhs_pmu_name, &lhs_num);
+	int rhs_pmu_name_len = pmu_name_len_no_suffix(rhs_pmu_name, &rhs_num);
+	int ret = strncmp(lhs_pmu_name, rhs_pmu_name,
+			lhs_pmu_name_len < rhs_pmu_name_len ? lhs_pmu_name_len : rhs_pmu_name_len);
+
+	if (lhs_pmu_name_len != rhs_pmu_name_len || ret != 0 || lhs_pmu_name_len == 0)
+		return ret;
+
+	return lhs_num < rhs_num ? -1 : (lhs_num > rhs_num ? 1 : 0);
+}
+
 /* Add all pmus in sysfs to pmu list: */
 static void pmu_read_sysfs(bool core_only)
 {
@@ -156,6 +203,8 @@ static void pmu_read_sysfs(bool core_only)
 		if (!perf_pmu__create_placeholder_core_pmu(&core_pmus))
 			pr_err("Failure to set up any core PMUs\n");
 	}
+	list_sort(NULL, &core_pmus, pmus_cmp);
+	list_sort(NULL, &other_pmus, pmus_cmp);
 	if (!list_empty(&core_pmus)) {
 		read_sysfs_core_pmus = true;
 		if (!core_only)

From cd4e1efbbc4037c440b84f6be5aff8938c204c9c Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 25 Aug 2023 06:52:37 -0700
Subject: [PATCH 0756/1189] perf pmus: Skip duplicate PMUs and don't print list
 suffix by default

Add a PMUs scan that ignores duplicates. When there are multiple PMUs
that differ only by suffix, by default just list the first one and
skip all others. The scan routine checks that the PMU names match but
doesn't enforce that the numbers are consecutive as for some PMUs
there are gaps. If "-v" is passed to "perf list" then list all PMUs.

With the previous change duplicate PMUs are no longer printed but the
suffix of the first is printed. When duplicate PMUs are being skipped
avoid printing the suffix.

Before:

  $ perf list
  ...
    uncore_imc_free_running_0/data_read/               [Kernel PMU event]
    uncore_imc_free_running_0/data_total/              [Kernel PMU event]
    uncore_imc_free_running_0/data_write/              [Kernel PMU event]
    uncore_imc_free_running_1/data_read/               [Kernel PMU event]
    uncore_imc_free_running_1/data_total/              [Kernel PMU event]
    uncore_imc_free_running_1/data_write/              [Kernel PMU event]

After:

  $ perf list
  ...
    uncore_imc_free_running/data_read/                 [Kernel PMU event]
    uncore_imc_free_running/data_total/                [Kernel PMU event]
    uncore_imc_free_running/data_write/                [Kernel PMU event]
  ...
  $ perf list -v
    uncore_imc_free_running_0/data_read/               [Kernel PMU event]
    uncore_imc_free_running_0/data_total/              [Kernel PMU event]
    uncore_imc_free_running_0/data_write/              [Kernel PMU event]
    uncore_imc_free_running_1/data_read/               [Kernel PMU event]
    uncore_imc_free_running_1/data_total/              [Kernel PMU event]
    uncore_imc_free_running_1/data_write/              [Kernel PMU event]
  ...

Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20230825135237.921058-3-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-list.c         |  8 +++++
 tools/perf/util/pmu.c             | 17 +++++++---
 tools/perf/util/pmu.h             |  3 +-
 tools/perf/util/pmus.c            | 53 ++++++++++++++++++++++++++++---
 tools/perf/util/pmus.h            |  2 ++
 tools/perf/util/print-events.h    |  1 +
 tools/perf/util/s390-sample-raw.c |  3 +-
 7 files changed, 76 insertions(+), 11 deletions(-)

diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index 8ac97a82744d..1ac47db4d66a 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -434,6 +434,13 @@ static void json_print_metric(void *ps __maybe_unused, const char *group,
 	strbuf_release(&buf);
 }
 
+static bool default_skip_duplicate_pmus(void *ps)
+{
+	struct print_state *print_state = ps;
+
+	return !print_state->long_desc;
+}
+
 int cmd_list(int argc, const char **argv)
 {
 	int i, ret = 0;
@@ -445,6 +452,7 @@ int cmd_list(int argc, const char **argv)
 		.print_end = default_print_end,
 		.print_event = default_print_event,
 		.print_metric = default_print_metric,
+		.skip_duplicate_pmus = default_skip_duplicate_pmus,
 	};
 	const char *cputype = NULL;
 	const char *unit_name = NULL;
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index b92dc7237f3b..502fd58c3ea7 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1578,7 +1578,9 @@ int perf_pmu__find_event(struct perf_pmu *pmu, const char *event, void *state, p
 		.cb = cb,
 	};
 
-	return perf_pmu__for_each_event(pmu, &args, find_event_callback);
+	/* Sub-optimal, but function is only used by tests. */
+	return perf_pmu__for_each_event(pmu, /*skip_duplicate_pmus=*/ false,
+					&args, find_event_callback);
 }
 
 static void perf_pmu__del_formats(struct list_head *formats)
@@ -1652,10 +1654,13 @@ static int sub_non_neg(int a, int b)
 }
 
 static char *format_alias(char *buf, int len, const struct perf_pmu *pmu,
-			  const struct perf_pmu_alias *alias)
+			  const struct perf_pmu_alias *alias, bool skip_duplicate_pmus)
 {
 	struct parse_events_term *term;
-	int used = snprintf(buf, len, "%s/%s", pmu->name, alias->name);
+	int pmu_name_len = skip_duplicate_pmus
+		? pmu_name_len_no_suffix(pmu->name, /*num=*/NULL)
+		: (int)strlen(pmu->name);
+	int used = snprintf(buf, len, "%.*s/%s", pmu_name_len, pmu->name, alias->name);
 
 	list_for_each_entry(term, &alias->terms, list) {
 		if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR)
@@ -1677,7 +1682,8 @@ static char *format_alias(char *buf, int len, const struct perf_pmu *pmu,
 	return buf;
 }
 
-int perf_pmu__for_each_event(struct perf_pmu *pmu, void *state, pmu_event_callback cb)
+int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus,
+			     void *state, pmu_event_callback cb)
 {
 	char buf[1024];
 	struct perf_pmu_alias *event;
@@ -1696,7 +1702,8 @@ int perf_pmu__for_each_event(struct perf_pmu *pmu, void *state, pmu_event_callba
 			info.name = event->name;
 			buf_used = 0;
 		} else {
-			info.name = format_alias(buf, sizeof(buf), pmu, event);
+			info.name = format_alias(buf, sizeof(buf), pmu, event,
+						 skip_duplicate_pmus);
 			if (pmu->is_core) {
 				info.alias = info.name;
 				info.name = event->name;
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 73965f208009..6a4e170c61d6 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -212,7 +212,8 @@ bool perf_pmu__supports_legacy_cache(const struct perf_pmu *pmu);
 bool perf_pmu__auto_merge_stats(const struct perf_pmu *pmu);
 bool perf_pmu__have_event(struct perf_pmu *pmu, const char *name);
 size_t perf_pmu__num_events(struct perf_pmu *pmu);
-int perf_pmu__for_each_event(struct perf_pmu *pmu, void *state, pmu_event_callback cb);
+int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus,
+			     void *state, pmu_event_callback cb);
 bool pmu__name_match(const struct perf_pmu *pmu, const char *pmu_name);
 
 /**
diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c
index 7316da1c0ddb..6631367c756f 100644
--- a/tools/perf/util/pmus.c
+++ b/tools/perf/util/pmus.c
@@ -36,7 +36,7 @@ static LIST_HEAD(other_pmus);
 static bool read_sysfs_core_pmus;
 static bool read_sysfs_all_pmus;
 
-static int pmu_name_len_no_suffix(const char *str, unsigned long *num)
+int pmu_name_len_no_suffix(const char *str, unsigned long *num)
 {
 	int orig_len, len;
 
@@ -276,6 +276,43 @@ struct perf_pmu *perf_pmus__scan_core(struct perf_pmu *pmu)
 	return NULL;
 }
 
+static struct perf_pmu *perf_pmus__scan_skip_duplicates(struct perf_pmu *pmu)
+{
+	bool use_core_pmus = !pmu || pmu->is_core;
+	int last_pmu_name_len = 0;
+	const char *last_pmu_name = (pmu && pmu->name) ? pmu->name : "";
+
+	if (!pmu) {
+		pmu_read_sysfs(/*core_only=*/false);
+		pmu = list_prepare_entry(pmu, &core_pmus, list);
+	} else
+		last_pmu_name_len = pmu_name_len_no_suffix(pmu->name ?: "", NULL);
+
+	if (use_core_pmus) {
+		list_for_each_entry_continue(pmu, &core_pmus, list) {
+			int pmu_name_len = pmu_name_len_no_suffix(pmu->name ?: "", /*num=*/NULL);
+
+			if (last_pmu_name_len == pmu_name_len &&
+			    !strncmp(last_pmu_name, pmu->name ?: "", pmu_name_len))
+				continue;
+
+			return pmu;
+		}
+		pmu = NULL;
+		pmu = list_prepare_entry(pmu, &other_pmus, list);
+	}
+	list_for_each_entry_continue(pmu, &other_pmus, list) {
+		int pmu_name_len = pmu_name_len_no_suffix(pmu->name ?: "", /*num=*/NULL);
+
+		if (last_pmu_name_len == pmu_name_len &&
+		    !strncmp(last_pmu_name, pmu->name ?: "", pmu_name_len))
+			continue;
+
+		return pmu;
+	}
+	return NULL;
+}
+
 const struct perf_pmu *perf_pmus__pmu_for_pmu_filter(const char *str)
 {
 	struct perf_pmu *pmu = NULL;
@@ -401,10 +438,17 @@ void perf_pmus__print_pmu_events(const struct print_callbacks *print_cb, void *p
 	int len;
 	struct sevent *aliases;
 	struct events_callback_state state;
+	bool skip_duplicate_pmus = print_cb->skip_duplicate_pmus(print_state);
+	struct perf_pmu *(*scan_fn)(struct perf_pmu *);
+
+	if (skip_duplicate_pmus)
+		scan_fn = perf_pmus__scan_skip_duplicates;
+	else
+		scan_fn = perf_pmus__scan;
 
 	pmu = NULL;
 	len = 0;
-	while ((pmu = perf_pmus__scan(pmu)) != NULL)
+	while ((pmu = scan_fn(pmu)) != NULL)
 		len += perf_pmu__num_events(pmu);
 
 	aliases = zalloc(sizeof(struct sevent) * len);
@@ -418,8 +462,9 @@ void perf_pmus__print_pmu_events(const struct print_callbacks *print_cb, void *p
 		.aliases_len = len,
 		.index = 0,
 	};
-	while ((pmu = perf_pmus__scan(pmu)) != NULL) {
-		perf_pmu__for_each_event(pmu, &state, perf_pmus__print_pmu_events__callback);
+	while ((pmu = scan_fn(pmu)) != NULL) {
+		perf_pmu__for_each_event(pmu, skip_duplicate_pmus, &state,
+					 perf_pmus__print_pmu_events__callback);
 	}
 	qsort(aliases, len, sizeof(struct sevent), cmp_sevent);
 	for (int j = 0; j < len; j++) {
diff --git a/tools/perf/util/pmus.h b/tools/perf/util/pmus.h
index a21464432d0f..4c67153ac257 100644
--- a/tools/perf/util/pmus.h
+++ b/tools/perf/util/pmus.h
@@ -5,6 +5,8 @@
 struct perf_pmu;
 struct print_callbacks;
 
+int pmu_name_len_no_suffix(const char *str, unsigned long *num);
+
 void perf_pmus__destroy(void);
 
 struct perf_pmu *perf_pmus__find(const char *name);
diff --git a/tools/perf/util/print-events.h b/tools/perf/util/print-events.h
index d7fab411e75c..bf4290bef0cd 100644
--- a/tools/perf/util/print-events.h
+++ b/tools/perf/util/print-events.h
@@ -26,6 +26,7 @@ struct print_callbacks {
 			const char *expr,
 			const char *threshold,
 			const char *unit);
+	bool (*skip_duplicate_pmus)(void *print_state);
 };
 
 /** Print all events, the default when no options are specified. */
diff --git a/tools/perf/util/s390-sample-raw.c b/tools/perf/util/s390-sample-raw.c
index dc1ed3e95d4d..115b16edb451 100644
--- a/tools/perf/util/s390-sample-raw.c
+++ b/tools/perf/util/s390-sample-raw.c
@@ -171,7 +171,8 @@ static char *get_counter_name(int set, int nr, struct perf_pmu *pmu)
 	if (!pmu)
 		return NULL;
 
-	perf_pmu__for_each_event(pmu, &data, get_counter_name_callback);
+	perf_pmu__for_each_event(pmu, /*skip_duplicate_pmus=*/ true,
+				 &data, get_counter_name_callback);
 	return data.result;
 }
 

From 9bf63282ea77a531ea58acb42fb3f40d2d1e4497 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Fri, 25 Aug 2023 08:25:49 -0700
Subject: [PATCH 0757/1189] perf tools: Handle old data in PERF_RECORD_ATTR

The PERF_RECORD_ATTR is used for a pipe mode to describe an event with
attribute and IDs.  The ID table comes after the attr and it calculate
size of the table using the total record size and the attr size.

  n_ids = (total_record_size - end_of_the_attr_field) / sizeof(u64)

This is fine for most use cases, but sometimes it saves the pipe output
in a file and then process it later.  And it becomes a problem if there
is a change in attr size between the record and report.

  $ perf record -o- > perf-pipe.data  # old version
  $ perf report -i- < perf-pipe.data  # new version

For example, if the attr size is 128 and it has 4 IDs, then it would
save them in 168 byte like below:

   8 byte: perf event header { .type = PERF_RECORD_ATTR, .size = 168 },
 128 byte: perf event attr { .size = 128, ... },
  32 byte: event IDs [] = { 1234, 1235, 1236, 1237 },

But when report later, it thinks the attr size is 136 then it only read
the last 3 entries as ID.

   8 byte: perf event header { .type = PERF_RECORD_ATTR, .size = 168 },
 136 byte: perf event attr { .size = 136, ... },
  24 byte: event IDs [] = { 1235, 1236, 1237 },  // 1234 is missing

So it should use the recorded version of the attr.  The attr has the
size field already then it should honor the size when reading data.

Fixes: 2c46dbb517a10b18 ("perf: Convert perf header attrs into attr events")
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tom Zanussi <zanussi@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230825152552.112913-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/header.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 99c61cdffa54..e13f4bab7c49 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -4378,7 +4378,8 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
 			     struct evlist **pevlist)
 {
-	u32 i, ids, n_ids;
+	u32 i, n_ids;
+	u64 *ids;
 	struct evsel *evsel;
 	struct evlist *evlist = *pevlist;
 
@@ -4394,9 +4395,8 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
 
 	evlist__add(evlist, evsel);
 
-	ids = event->header.size;
-	ids -= (void *)&event->attr.id - (void *)event;
-	n_ids = ids / sizeof(u64);
+	n_ids = event->header.size - sizeof(event->header) - event->attr.attr.size;
+	n_ids = n_ids / sizeof(u64);
 	/*
 	 * We don't have the cpu and thread maps on the header, so
 	 * for allocating the perf_sample_id table we fake 1 cpu and
@@ -4405,8 +4405,9 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
 	if (perf_evsel__alloc_id(&evsel->core, 1, n_ids))
 		return -ENOMEM;
 
+	ids = (void *)&event->attr.attr + event->attr.attr.size;
 	for (i = 0; i < n_ids; i++) {
-		perf_evlist__id_add(&evlist->core, &evsel->core, 0, i, event->attr.id[i]);
+		perf_evlist__id_add(&evlist->core, &evsel->core, 0, i, ids[i]);
 	}
 
 	return 0;

From baec60800dd4a379546f3ba311574d907a01a77d Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Fri, 25 Aug 2023 08:25:50 -0700
Subject: [PATCH 0758/1189] libperf: Add perf_record_header_attr_id()

The HEADER_ATTR record has an event attr followed by the id array.  But
perf data from a different version could have different size of attr.

So it cannot just use event->attr.id to access the array.  Let's add the
perf_record_header_attr_id() macro to calculate the start of the array.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230825152552.112913-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/perf/include/perf/event.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h
index ba2dcf64f4e6..e563dd8c3628 100644
--- a/tools/lib/perf/include/perf/event.h
+++ b/tools/lib/perf/include/perf/event.h
@@ -151,6 +151,10 @@ struct perf_record_header_attr {
 	__u64			 id[];
 };
 
+/* Returns the pointer to id array based on the actual attr size. */
+#define perf_record_header_attr_id(evt)			\
+	((void *)&(evt)->attr.attr + (evt)->attr.attr.size)
+
 enum {
 	PERF_CPU_MAP__CPUS = 0,
 	PERF_CPU_MAP__MASK = 1,

From f174341d0da1cb2fb8888e1fa228c31523eaec90 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Fri, 25 Aug 2023 08:25:51 -0700
Subject: [PATCH 0759/1189] perf tools: Convert to perf_record_header_attr_id()

Instead of accessing the attr.id directly, use the
perf_record_header_attr_id() helper to handle old versions.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230825152552.112913-3-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/header.c           | 2 +-
 tools/perf/util/session.c          | 4 ++--
 tools/perf/util/synthetic-events.c | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index e13f4bab7c49..d812e1e371a7 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -4405,7 +4405,7 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
 	if (perf_evsel__alloc_id(&evsel->core, 1, n_ids))
 		return -ENOMEM;
 
-	ids = (void *)&event->attr.attr + event->attr.attr.size;
+	ids = perf_record_header_attr_id(event);
 	for (i = 0; i < n_ids; i++) {
 		perf_evlist__id_add(&evlist->core, &evsel->core, 0, i, ids[i]);
 	}
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 00d18c74c090..1e9aa8ed15b6 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -833,8 +833,8 @@ static void perf_event__hdr_attr_swap(union perf_event *event,
 	perf_event__attr_swap(&event->attr.attr);
 
 	size = event->header.size;
-	size -= (void *)&event->attr.id - (void *)event;
-	mem_bswap_64(event->attr.id, size);
+	size -= perf_record_header_attr_id(event) - (void *)event;
+	mem_bswap_64(perf_record_header_attr_id(event), size);
 }
 
 static void perf_event__event_update_swap(union perf_event *event,
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index 45714a2785fd..a0579c7d7b9e 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -2145,7 +2145,7 @@ int perf_event__synthesize_attr(struct perf_tool *tool, struct perf_event_attr *
 		return -ENOMEM;
 
 	ev->attr.attr = *attr;
-	memcpy(ev->attr.id, id, ids * sizeof(u64));
+	memcpy(perf_record_header_attr_id(ev), id, ids * sizeof(u64));
 
 	ev->attr.header.type = PERF_RECORD_HEADER_ATTR;
 	ev->attr.header.size = (u16)size;

From c091c78b73c82f1e2811ab19b8e287ddc7807651 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Fri, 25 Aug 2023 08:25:52 -0700
Subject: [PATCH 0760/1189] libperf: Get rid of attr.id field

Now there's no in-tree user of the field.  To remove the possible bug
later, let's get rid of the 'id' field and add a comment for that.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230825152552.112913-4-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/perf/include/perf/event.h | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h
index e563dd8c3628..ae64090184d3 100644
--- a/tools/lib/perf/include/perf/event.h
+++ b/tools/lib/perf/include/perf/event.h
@@ -148,7 +148,13 @@ struct perf_record_switch {
 struct perf_record_header_attr {
 	struct perf_event_header header;
 	struct perf_event_attr	 attr;
-	__u64			 id[];
+	/*
+	 * Array of u64 id follows here but we cannot use a flexible array
+	 * because size of attr in the data can be different then current
+	 * version.  Please use perf_record_header_attr_id() below.
+	 *
+	 * __u64		 id[];  // do not use this
+	 */
 };
 
 /* Returns the pointer to id array based on the actual attr size. */

From 11f5710d96afcd569a7c8e00395b714bbea3ce5d Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Fri, 25 Aug 2023 09:41:50 -0700
Subject: [PATCH 0761/1189] perf test shell record_bpf_filter: Skip 6.2 kernel

The BPF sample filtering requires two kernel changes below:

 * bpf_cast_to_kernel_ctx() kfunc (added in v6.2)

 * setting perf_sample_data->sample_flags (finished in v6.3)

The perf tools can check bpf_cast_to_kernel_ctx() easily so it can
refuse BPF filters on those old kernels (v6.1 and earlier).

But checking sample_flags appears to be difficult so current code won't
work on v6.2 kernel.  That's unfortunate but I don't know what's the
correct way to handle it.

For now, let's skip v6.2 kernels explicitly (if failed) in the test.

Fixes: 9575ecdd198a50e9 ("perf test: Add perf record sample filtering test")
Reported-by: Arnaldo Carvalho de Melo <acme@kernel.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20230825164152.165610-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/record_bpf_filter.sh | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/tools/perf/tests/shell/record_bpf_filter.sh b/tools/perf/tests/shell/record_bpf_filter.sh
index e76ea861b92c..31c593966e8c 100755
--- a/tools/perf/tests/shell/record_bpf_filter.sh
+++ b/tools/perf/tests/shell/record_bpf_filter.sh
@@ -49,6 +49,12 @@ test_bpf_filter_basic() {
   fi
   if perf script -i "${perfdata}" -F ip | grep 'ffffffff[0-9a-f]*'
   then
+    if uname -r | grep -q ^6.2
+    then
+      echo "Basic bpf-filter test [Skipped unsupported kernel]"
+      err=2
+      return
+    fi
     echo "Basic bpf-filter test [Failed invalid output]"
     err=1
     return

From 68ca249c964f520af7f8763e22f12bd26b57b870 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Fri, 25 Aug 2023 09:41:51 -0700
Subject: [PATCH 0762/1189] perf test shell stat_bpf_counters: Fix test on
 Intel

As of now, bpf counters (bperf) don't support event groups.  But the
default perf stat includes topdown metrics if supported (on recent Intel
machines) which require groups.  That makes perf stat exiting.

  $ sudo perf stat --bpf-counter true
  bpf managed perf events do not yet support groups.

Actually the test explicitly uses cycles event only, but it missed to
pass the option when it checks the availability of the command.

Fixes: 2c0cb9f56020d2ea ("perf test: Add a shell test for 'perf stat --bpf-counters' new option")
Reviewed-by: Song Liu <song@kernel.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: bpf@vger.kernel.org
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230825164152.165610-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/stat_bpf_counters.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/tests/shell/stat_bpf_counters.sh b/tools/perf/tests/shell/stat_bpf_counters.sh
index 513cd1e58e0e..a87bb2814b4c 100755
--- a/tools/perf/tests/shell/stat_bpf_counters.sh
+++ b/tools/perf/tests/shell/stat_bpf_counters.sh
@@ -22,10 +22,10 @@ compare_number()
 }
 
 # skip if --bpf-counters is not supported
-if ! perf stat --bpf-counters true > /dev/null 2>&1; then
+if ! perf stat -e cycles --bpf-counters true > /dev/null 2>&1; then
 	if [ "$1" = "-v" ]; then
 		echo "Skipping: --bpf-counters not supported"
-		perf --no-pager stat --bpf-counters true || true
+		perf --no-pager stat -e cycles --bpf-counters true || true
 	fi
 	exit 2
 fi

From a84260e314029e6dc9904fd6eabf8d9fd7965351 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Fri, 25 Aug 2023 09:41:52 -0700
Subject: [PATCH 0763/1189] perf test stat_bpf_counters_cgrp: Enhance perf stat
 cgroup BPF counter test

It has system-wide test and cpu-list test but the cpu-list test fails
sometimes.  It runs sleep command on CPU1 and measure both user.slice
and system.slice cgroups by default (on systemd-based systems).

But if the system was idle enough, sometime the system.slice gets no
count and it makes the test failing.  Maybe that's because it only looks
at the CPU1, let's add CPU0 to increase the chance it finds some tasks.

Fixes: 7901086014bbaa3a ("perf test: Add a new test for perf stat cgroup BPF counter")
Reported-by: Arnaldo Carvalho de Melo <acme@kernel.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20230825164152.165610-3-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/stat_bpf_counters_cgrp.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh
index a74440a00b6b..e75d0780dc78 100755
--- a/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh
+++ b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh
@@ -60,7 +60,7 @@ check_system_wide_counted()
 
 check_cpu_list_counted()
 {
-	check_cpu_list_counted_output=$(perf stat -C 1 --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, taskset -c 1 sleep 1  2>&1)
+	check_cpu_list_counted_output=$(perf stat -C 0,1 --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, taskset -c 1 sleep 1  2>&1)
 	if echo ${check_cpu_list_counted_output} | grep -q -F "<not "; then
 		echo "Some CPU events are not counted"
 		if [ "${verbose}" = "1" ]; then

From d2045f87154bf67a50ebefe28d2ca0e1e3f8eef1 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 25 Aug 2023 23:22:03 -0700
Subject: [PATCH 0764/1189] perf jevents: Use "default_core" for events with no
 Unit

The JSON Unit field encodes the name of the PMU to match the events
to. When no name is given it has meant the "cpu" core PMU except for
tests.

On ARM, Intel hybrid and s390 the core PMU is named differently which
means that using "cpu" for this case causes the events not to get
matched to the PMU.

Introduce a new "default_core" string for this case and in the
pmu__name_match force all core PMUs to match this name.

Fixes: 2e255b4f9f41f137 ("perf jevents: Group events by PMU")
Reported-by: Arnaldo Carvalho de Melo <acme@kernel.org>
Reported-by: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20230826062203.1058041-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/jevents.py |  2 +-
 tools/perf/tests/pmu-events.c    | 19 ++++++++++---------
 tools/perf/util/pmu.c            |  7 ++++++-
 3 files changed, 17 insertions(+), 11 deletions(-)

diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index 712f80d7d071..a7e88332276d 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -266,7 +266,7 @@ class JsonEvent:
     def unit_to_pmu(unit: str) -> Optional[str]:
       """Convert a JSON Unit to Linux PMU name."""
       if not unit:
-        return 'cpu'
+        return 'default_core'
       # Comment brought over from jevents.c:
       # it's not realistic to keep adding these, we need something more scalable ...
       table = {
diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
index ce4da9b1d115..f5321fbdee79 100644
--- a/tools/perf/tests/pmu-events.c
+++ b/tools/perf/tests/pmu-events.c
@@ -44,7 +44,7 @@ struct perf_pmu_test_pmu {
 
 static const struct perf_pmu_test_event bp_l1_btb_correct = {
 	.event = {
-		.pmu = "cpu",
+		.pmu = "default_core",
 		.name = "bp_l1_btb_correct",
 		.event = "event=0x8a",
 		.desc = "L1 BTB Correction",
@@ -56,7 +56,7 @@ static const struct perf_pmu_test_event bp_l1_btb_correct = {
 
 static const struct perf_pmu_test_event bp_l2_btb_correct = {
 	.event = {
-		.pmu = "cpu",
+		.pmu = "default_core",
 		.name = "bp_l2_btb_correct",
 		.event = "event=0x8b",
 		.desc = "L2 BTB Correction",
@@ -68,7 +68,7 @@ static const struct perf_pmu_test_event bp_l2_btb_correct = {
 
 static const struct perf_pmu_test_event segment_reg_loads_any = {
 	.event = {
-		.pmu = "cpu",
+		.pmu = "default_core",
 		.name = "segment_reg_loads.any",
 		.event = "event=0x6,period=200000,umask=0x80",
 		.desc = "Number of segment register loads",
@@ -80,7 +80,7 @@ static const struct perf_pmu_test_event segment_reg_loads_any = {
 
 static const struct perf_pmu_test_event dispatch_blocked_any = {
 	.event = {
-		.pmu = "cpu",
+		.pmu = "default_core",
 		.name = "dispatch_blocked.any",
 		.event = "event=0x9,period=200000,umask=0x20",
 		.desc = "Memory cluster signals to block micro-op dispatch for any reason",
@@ -92,7 +92,7 @@ static const struct perf_pmu_test_event dispatch_blocked_any = {
 
 static const struct perf_pmu_test_event eist_trans = {
 	.event = {
-		.pmu = "cpu",
+		.pmu = "default_core",
 		.name = "eist_trans",
 		.event = "event=0x3a,period=200000,umask=0x0",
 		.desc = "Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions",
@@ -104,7 +104,7 @@ static const struct perf_pmu_test_event eist_trans = {
 
 static const struct perf_pmu_test_event l3_cache_rd = {
 	.event = {
-		.pmu = "cpu",
+		.pmu = "default_core",
 		.name = "l3_cache_rd",
 		.event = "event=0x40",
 		.desc = "L3 cache access, read",
@@ -391,8 +391,8 @@ static int compare_alias_to_test_event(struct pmu_event_info *alias,
 		return -1;
 	}
 
-
-	if (!is_same(alias->pmu_name, test_event->event.pmu)) {
+	if (!is_same(alias->pmu_name, test_event->event.pmu) &&
+	    !is_same(alias->pmu_name, "default_core")) {
 		pr_debug("testing aliases PMU %s: mismatched pmu_name, %s vs %s\n",
 			  pmu_name, alias->pmu_name, test_event->event.pmu);
 		return -1;
@@ -409,7 +409,7 @@ static int test__pmu_event_table_core_callback(const struct pmu_event *pe,
 	struct perf_pmu_test_event const **test_event_table;
 	bool found = false;
 
-	if (strcmp(pe->pmu, "cpu"))
+	if (strcmp(pe->pmu, "default_core"))
 		test_event_table = &uncore_events[0];
 	else
 		test_event_table = &core_events[0];
@@ -543,6 +543,7 @@ static int __test_core_pmu_event_aliases(const char *pmu_name, int *count)
 	INIT_LIST_HEAD(&pmu->caps);
 	INIT_LIST_HEAD(&pmu->list);
 	pmu->name = strdup(pmu_name);
+	pmu->is_core = true;
 
 	pmu->events_table = table;
 	pmu_add_cpu_aliases_table(pmu, table);
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 502fd58c3ea7..cde33e01959a 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1747,7 +1747,12 @@ int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus,
 bool pmu__name_match(const struct perf_pmu *pmu, const char *pmu_name)
 {
 	return !strcmp(pmu->name, pmu_name) ||
-		(pmu->is_uncore && pmu_uncore_alias_match(pmu_name, pmu->name));
+		(pmu->is_uncore && pmu_uncore_alias_match(pmu_name, pmu->name)) ||
+		/*
+		 * jevents and tests use default_core as a marker for any core
+		 * PMU as the PMU name varies across architectures.
+		 */
+	        (pmu->is_core && !strcmp(pmu_name, "default_core"));
 }
 
 bool perf_pmu__is_software(const struct perf_pmu *pmu)

From 0119c894ab0dc468bcb03f28063239c0a4cf970f Mon Sep 17 00:00:00 2001
From: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Date: Fri, 11 Aug 2023 14:19:53 -0300
Subject: [PATCH 0765/1189] drm: Add initial ci/ subdirectory

Developers can easily execute several tests on different devices
by just pushing their branch to their fork in a repository hosted
on gitlab.freedesktop.org which has an infrastructure to run jobs
in several runners and farms with different devices.

There are also other automated tools that uprev dependencies,
monitor the infra, and so on that are already used by the Mesa
project, and we can reuse them too.

Also, store expectations about what the DRM drivers are supposed
to pass in the IGT test suite. By storing the test expectations
along with the code, we can make sure both stay in sync with each
other so we can know when a code change breaks those expectations.

Also, include a configuration file that points to the out-of-tree
CI scripts.

This will allow all contributors to drm to reuse the infrastructure
already in gitlab.freedesktop.org to test the driver on several
generations of the hardware.

Signed-off-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Signed-off-by: Helen Koike <helen.koike@collabora.com>
Acked-by: Daniel Stone <daniels@collabora.com>
Acked-by: Rob Clark <robdclark@gmail.com>
Tested-by: Rob Clark <robdclark@gmail.com>
[sima: Remove top-level empty file test, spotted by sfr]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20230811171953.176431-1-helen.koike@collabora.com
---
 Documentation/gpu/automated_testing.rst       |  144 +
 Documentation/gpu/index.rst                   |    1 +
 MAINTAINERS                                   |    8 +
 drivers/gpu/drm/ci/arm.config                 |   69 +
 drivers/gpu/drm/ci/arm64.config               |  199 ++
 drivers/gpu/drm/ci/build-igt.sh               |   35 +
 drivers/gpu/drm/ci/build.sh                   |  157 +
 drivers/gpu/drm/ci/build.yml                  |  110 +
 drivers/gpu/drm/ci/check-patch.py             |   57 +
 drivers/gpu/drm/ci/container.yml              |   65 +
 drivers/gpu/drm/ci/gitlab-ci.yml              |  251 ++
 drivers/gpu/drm/ci/igt_runner.sh              |   77 +
 drivers/gpu/drm/ci/image-tags.yml             |   15 +
 drivers/gpu/drm/ci/lava-submit.sh             |   57 +
 drivers/gpu/drm/ci/static-checks.yml          |   12 +
 drivers/gpu/drm/ci/test.yml                   |  335 ++
 drivers/gpu/drm/ci/testlist.txt               | 2912 +++++++++++++++++
 drivers/gpu/drm/ci/x86_64.config              |  111 +
 .../gpu/drm/ci/xfails/amdgpu-stoney-fails.txt |   19 +
 .../drm/ci/xfails/amdgpu-stoney-flakes.txt    |   21 +
 .../gpu/drm/ci/xfails/amdgpu-stoney-skips.txt |    2 +
 drivers/gpu/drm/ci/xfails/i915-amly-fails.txt |   17 +
 .../gpu/drm/ci/xfails/i915-amly-flakes.txt    |   32 +
 drivers/gpu/drm/ci/xfails/i915-amly-skips.txt |    4 +
 drivers/gpu/drm/ci/xfails/i915-apl-fails.txt  |   58 +
 drivers/gpu/drm/ci/xfails/i915-apl-flakes.txt |    1 +
 drivers/gpu/drm/ci/xfails/i915-apl-skips.txt  |    6 +
 drivers/gpu/drm/ci/xfails/i915-cml-fails.txt  |   18 +
 drivers/gpu/drm/ci/xfails/i915-cml-flakes.txt |   38 +
 drivers/gpu/drm/ci/xfails/i915-cml-skips.txt  |    2 +
 drivers/gpu/drm/ci/xfails/i915-glk-fails.txt  |   19 +
 drivers/gpu/drm/ci/xfails/i915-glk-flakes.txt |   41 +
 drivers/gpu/drm/ci/xfails/i915-glk-skips.txt  |    5 +
 drivers/gpu/drm/ci/xfails/i915-kbl-fails.txt  |   25 +
 drivers/gpu/drm/ci/xfails/i915-kbl-flakes.txt |   26 +
 drivers/gpu/drm/ci/xfails/i915-kbl-skips.txt  |    5 +
 drivers/gpu/drm/ci/xfails/i915-tgl-fails.txt  |   37 +
 drivers/gpu/drm/ci/xfails/i915-tgl-flakes.txt |    5 +
 drivers/gpu/drm/ci/xfails/i915-tgl-skips.txt  |   11 +
 drivers/gpu/drm/ci/xfails/i915-whl-fails.txt  |   48 +
 drivers/gpu/drm/ci/xfails/i915-whl-flakes.txt |    1 +
 drivers/gpu/drm/ci/xfails/i915-whl-skips.txt  |    2 +
 .../drm/ci/xfails/mediatek-mt8173-fails.txt   |   29 +
 .../drm/ci/xfails/mediatek-mt8173-flakes.txt  |    0
 .../drm/ci/xfails/mediatek-mt8183-fails.txt   |   10 +
 .../drm/ci/xfails/mediatek-mt8183-flakes.txt  |   14 +
 .../gpu/drm/ci/xfails/meson-g12b-fails.txt    |   12 +
 .../gpu/drm/ci/xfails/meson-g12b-flakes.txt   |    4 +
 .../gpu/drm/ci/xfails/msm-apq8016-fails.txt   |   15 +
 .../gpu/drm/ci/xfails/msm-apq8016-flakes.txt  |    4 +
 .../gpu/drm/ci/xfails/msm-apq8096-fails.txt   |    2 +
 .../gpu/drm/ci/xfails/msm-apq8096-flakes.txt  |    4 +
 .../gpu/drm/ci/xfails/msm-apq8096-skips.txt   |    2 +
 .../gpu/drm/ci/xfails/msm-sc7180-fails.txt    |   25 +
 .../gpu/drm/ci/xfails/msm-sc7180-flakes.txt   |    7 +
 .../gpu/drm/ci/xfails/msm-sc7180-skips.txt    |   23 +
 .../gpu/drm/ci/xfails/msm-sdm845-fails.txt    |   68 +
 .../gpu/drm/ci/xfails/msm-sdm845-flakes.txt   |   11 +
 .../gpu/drm/ci/xfails/msm-sdm845-skips.txt    |    2 +
 .../drm/ci/xfails/rockchip-rk3288-fails.txt   |   48 +
 .../drm/ci/xfails/rockchip-rk3288-flakes.txt  |    9 +
 .../drm/ci/xfails/rockchip-rk3288-skips.txt   |   52 +
 .../drm/ci/xfails/rockchip-rk3399-fails.txt   |   37 +
 .../drm/ci/xfails/rockchip-rk3399-flakes.txt  |   23 +
 .../drm/ci/xfails/rockchip-rk3399-skips.txt   |    5 +
 .../drm/ci/xfails/virtio_gpu-none-fails.txt   |   38 +
 .../drm/ci/xfails/virtio_gpu-none-flakes.txt  |    0
 .../drm/ci/xfails/virtio_gpu-none-skips.txt   |    6 +
 68 files changed, 5508 insertions(+)
 create mode 100644 Documentation/gpu/automated_testing.rst
 create mode 100644 drivers/gpu/drm/ci/arm.config
 create mode 100644 drivers/gpu/drm/ci/arm64.config
 create mode 100644 drivers/gpu/drm/ci/build-igt.sh
 create mode 100644 drivers/gpu/drm/ci/build.sh
 create mode 100644 drivers/gpu/drm/ci/build.yml
 create mode 100755 drivers/gpu/drm/ci/check-patch.py
 create mode 100644 drivers/gpu/drm/ci/container.yml
 create mode 100644 drivers/gpu/drm/ci/gitlab-ci.yml
 create mode 100755 drivers/gpu/drm/ci/igt_runner.sh
 create mode 100644 drivers/gpu/drm/ci/image-tags.yml
 create mode 100755 drivers/gpu/drm/ci/lava-submit.sh
 create mode 100644 drivers/gpu/drm/ci/static-checks.yml
 create mode 100644 drivers/gpu/drm/ci/test.yml
 create mode 100644 drivers/gpu/drm/ci/testlist.txt
 create mode 100644 drivers/gpu/drm/ci/x86_64.config
 create mode 100644 drivers/gpu/drm/ci/xfails/amdgpu-stoney-fails.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/amdgpu-stoney-flakes.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/amdgpu-stoney-skips.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/i915-amly-fails.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/i915-amly-flakes.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/i915-amly-skips.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/i915-apl-fails.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/i915-apl-flakes.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/i915-apl-skips.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/i915-cml-fails.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/i915-cml-flakes.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/i915-cml-skips.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/i915-glk-fails.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/i915-glk-flakes.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/i915-glk-skips.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/i915-kbl-fails.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/i915-kbl-flakes.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/i915-kbl-skips.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/i915-tgl-fails.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/i915-tgl-flakes.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/i915-tgl-skips.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/i915-whl-fails.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/i915-whl-flakes.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/i915-whl-skips.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/mediatek-mt8173-fails.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/mediatek-mt8173-flakes.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/mediatek-mt8183-fails.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/mediatek-mt8183-flakes.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/meson-g12b-fails.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/meson-g12b-flakes.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/msm-apq8016-fails.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/msm-apq8016-flakes.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/msm-apq8096-fails.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/msm-apq8096-flakes.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/msm-apq8096-skips.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/msm-sc7180-fails.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/msm-sc7180-flakes.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/msm-sc7180-skips.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/msm-sdm845-fails.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/msm-sdm845-flakes.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/msm-sdm845-skips.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/rockchip-rk3288-fails.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/rockchip-rk3288-flakes.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/rockchip-rk3288-skips.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/rockchip-rk3399-fails.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/rockchip-rk3399-flakes.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/rockchip-rk3399-skips.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/virtio_gpu-none-fails.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/virtio_gpu-none-flakes.txt
 create mode 100644 drivers/gpu/drm/ci/xfails/virtio_gpu-none-skips.txt

diff --git a/Documentation/gpu/automated_testing.rst b/Documentation/gpu/automated_testing.rst
new file mode 100644
index 000000000000..1b87b802ac7f
--- /dev/null
+++ b/Documentation/gpu/automated_testing.rst
@@ -0,0 +1,144 @@
+.. SPDX-License-Identifier: GPL-2.0+
+
+=========================================
+Automated testing of the DRM subsystem
+=========================================
+
+Introduction
+============
+
+Making sure that changes to the core or drivers don't introduce regressions can
+be very time-consuming when lots of different hardware configurations need to
+be tested. Moreover, it isn't practical for each person interested in this
+testing to have to acquire and maintain what can be a considerable amount of
+hardware.
+
+Also, it is desirable for developers to check for regressions in their code by
+themselves, instead of relying on the maintainers to find them and then
+reporting back.
+
+There are facilities in gitlab.freedesktop.org to automatically test Mesa that
+can be used as well for testing the DRM subsystem. This document explains how
+people interested in testing it can use this shared infrastructure to save
+quite some time and effort.
+
+
+Relevant files
+==============
+
+drivers/gpu/drm/ci/gitlab-ci.yml
+--------------------------------
+
+This is the root configuration file for GitLab CI. Among other less interesting
+bits, it specifies the specific version of the scripts to be used. There are
+some variables that can be modified to change the behavior of the pipeline:
+
+DRM_CI_PROJECT_PATH
+    Repository that contains the Mesa software infrastructure for CI
+
+DRM_CI_COMMIT_SHA
+    A particular revision to use from that repository
+
+UPSTREAM_REPO
+    URL to git repository containing the target branch
+
+TARGET_BRANCH
+    Branch to which this branch is to be merged into
+
+IGT_VERSION
+    Revision of igt-gpu-tools being used, from
+    https://gitlab.freedesktop.org/drm/igt-gpu-tools
+
+drivers/gpu/drm/ci/testlist.txt
+-------------------------------
+
+IGT tests to be run on all drivers (unless mentioned in a driver's *-skips.txt
+file, see below).
+
+drivers/gpu/drm/ci/${DRIVER_NAME}-${HW_REVISION}-fails.txt
+----------------------------------------------------------
+
+Lists the known failures for a given driver on a specific hardware revision.
+
+drivers/gpu/drm/ci/${DRIVER_NAME}-${HW_REVISION}-flakes.txt
+-----------------------------------------------------------
+
+Lists the tests that for a given driver on a specific hardware revision are
+known to behave unreliably. These tests won't cause a job to fail regardless of
+the result. They will still be run.
+
+drivers/gpu/drm/ci/${DRIVER_NAME}-${HW_REVISION}-skips.txt
+-----------------------------------------------------------
+
+Lists the tests that won't be run for a given driver on a specific hardware
+revision. These are usually tests that interfere with the running of the test
+list due to hanging the machine, causing OOM, taking too long, etc.
+
+
+How to enable automated testing on your tree
+============================================
+
+1. Create a Linux tree in https://gitlab.freedesktop.org/ if you don't have one
+yet
+
+2. In your kernel repo's configuration (eg.
+https://gitlab.freedesktop.org/janedoe/linux/-/settings/ci_cd), change the
+CI/CD configuration file from .gitlab-ci.yml to
+drivers/gpu/drm/ci/gitlab-ci.yml.
+
+3. Next time you push to this repository, you will see a CI pipeline being
+created (eg. https://gitlab.freedesktop.org/janedoe/linux/-/pipelines)
+
+4. The various jobs will be run and when the pipeline is finished, all jobs
+should be green unless a regression has been found.
+
+
+How to update test expectations
+===============================
+
+If your changes to the code fix any tests, you will have to remove one or more
+lines from one or more of the files in
+drivers/gpu/drm/ci/${DRIVER_NAME}_*_fails.txt, for each of the test platforms
+affected by the change.
+
+
+How to expand coverage
+======================
+
+If your code changes make it possible to run more tests (by solving reliability
+issues, for example), you can remove tests from the flakes and/or skips lists,
+and then the expected results if there are any known failures.
+
+If there is a need for updating the version of IGT being used (maybe you have
+added more tests to it), update the IGT_VERSION variable at the top of the
+gitlab-ci.yml file.
+
+
+How to test your changes to the scripts
+=======================================
+
+For testing changes to the scripts in the drm-ci repo, change the
+DRM_CI_PROJECT_PATH and DRM_CI_COMMIT_SHA variables in
+drivers/gpu/drm/ci/gitlab-ci.yml to match your fork of the project (eg.
+janedoe/drm-ci). This fork needs to be in https://gitlab.freedesktop.org/.
+
+
+How to incorporate external fixes in your testing
+=================================================
+
+Often, regressions in other trees will prevent testing changes local to the
+tree under test. These fixes will be automatically merged in during the build
+jobs from a branch in the target tree that is named as
+${TARGET_BRANCH}-external-fixes.
+
+If the pipeline is not in a merge request and a branch with the same name
+exists in the local tree, commits from that branch will be merged in as well.
+
+
+How to deal with automated testing labs that may be down
+========================================================
+
+If a hardware farm is down and thus causing pipelines to fail that would
+otherwise pass, one can disable all jobs that would be submitted to that farm
+by editing the file at
+https://gitlab.freedesktop.org/gfx-ci/lab-status/-/blob/main/lab-status.yml.
diff --git a/Documentation/gpu/index.rst b/Documentation/gpu/index.rst
index eee5996acf2c..e45ff0915246 100644
--- a/Documentation/gpu/index.rst
+++ b/Documentation/gpu/index.rst
@@ -17,6 +17,7 @@ GPU Driver Developer's Guide
    backlight
    vga-switcheroo
    vgaarbiter
+   automated_testing
    todo
    rfc/index
 
diff --git a/MAINTAINERS b/MAINTAINERS
index 231a5e6fd52e..0f66c7ab69cf 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7132,6 +7132,14 @@ T:	git git://anongit.freedesktop.org/drm/drm-misc
 F:	drivers/gpu/drm/ttm/
 F:	include/drm/ttm/
 
+DRM AUTOMATED TESTING
+M:	Helen Koike <helen.koike@collabora.com>
+L:	dri-devel@lists.freedesktop.org
+S:	Maintained
+T:	git git://anongit.freedesktop.org/drm/drm-misc
+F:	Documentation/gpu/automated_testing.rst
+F:	drivers/gpu/drm/ci/
+
 DSBR100 USB FM RADIO DRIVER
 M:	Alexey Klimov <klimov.linux@gmail.com>
 L:	linux-media@vger.kernel.org
diff --git a/drivers/gpu/drm/ci/arm.config b/drivers/gpu/drm/ci/arm.config
new file mode 100644
index 000000000000..871f4de063ad
--- /dev/null
+++ b/drivers/gpu/drm/ci/arm.config
@@ -0,0 +1,69 @@
+CONFIG_LOCALVERSION_AUTO=y
+CONFIG_DEBUG_KERNEL=y
+
+CONFIG_CRYPTO_ZSTD=y
+CONFIG_ZRAM_MEMORY_TRACKING=y
+CONFIG_ZRAM_WRITEBACK=y
+CONFIG_ZRAM=y
+CONFIG_ZSMALLOC_STAT=y
+
+# abootimg with a 'dummy' rootfs fails with root=/dev/nfs
+CONFIG_BLK_DEV_INITRD=n
+
+CONFIG_DEVFREQ_GOV_PERFORMANCE=y
+CONFIG_DEVFREQ_GOV_POWERSAVE=y
+CONFIG_DEVFREQ_GOV_USERSPACE=y
+CONFIG_DEVFREQ_GOV_PASSIVE=y
+CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND=y
+
+CONFIG_DRM=y
+CONFIG_DRM_ETNAVIV=y
+CONFIG_DRM_ROCKCHIP=y
+CONFIG_DRM_PANFROST=y
+CONFIG_DRM_LIMA=y
+CONFIG_DRM_PANEL_SIMPLE=y
+CONFIG_PWM_CROS_EC=y
+CONFIG_BACKLIGHT_PWM=y
+
+CONFIG_ROCKCHIP_CDN_DP=n
+
+CONFIG_SPI_ROCKCHIP=y
+CONFIG_PWM_ROCKCHIP=y
+CONFIG_PHY_ROCKCHIP_DP=y
+CONFIG_DWMAC_ROCKCHIP=y
+
+CONFIG_MFD_RK808=y
+CONFIG_REGULATOR_RK808=y
+CONFIG_RTC_DRV_RK808=y
+CONFIG_COMMON_CLK_RK808=y
+
+CONFIG_REGULATOR_FAN53555=y
+CONFIG_REGULATOR=y
+
+CONFIG_REGULATOR_VCTRL=y
+
+CONFIG_KASAN=n
+CONFIG_KASAN_INLINE=n
+CONFIG_STACKTRACE=n
+
+CONFIG_TMPFS=y
+
+CONFIG_PROVE_LOCKING=n
+CONFIG_DEBUG_LOCKDEP=n
+CONFIG_SOFTLOCKUP_DETECTOR=n
+CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=n
+
+CONFIG_FW_LOADER_COMPRESS=y
+
+CONFIG_USB_USBNET=y
+CONFIG_NETDEVICES=y
+CONFIG_USB_NET_DRIVERS=y
+CONFIG_USB_RTL8152=y
+CONFIG_USB_NET_AX8817X=y
+CONFIG_USB_NET_SMSC95XX=y
+
+# TK1
+CONFIG_ARM_TEGRA_DEVFREQ=y
+
+# 32-bit build failure
+CONFIG_DRM_MSM=n
diff --git a/drivers/gpu/drm/ci/arm64.config b/drivers/gpu/drm/ci/arm64.config
new file mode 100644
index 000000000000..817e18ddfd4f
--- /dev/null
+++ b/drivers/gpu/drm/ci/arm64.config
@@ -0,0 +1,199 @@
+CONFIG_LOCALVERSION_AUTO=y
+CONFIG_DEBUG_KERNEL=y
+
+CONFIG_CRYPTO_ZSTD=y
+CONFIG_ZRAM_MEMORY_TRACKING=y
+CONFIG_ZRAM_WRITEBACK=y
+CONFIG_ZRAM=y
+CONFIG_ZSMALLOC_STAT=y
+
+# abootimg with a 'dummy' rootfs fails with root=/dev/nfs
+CONFIG_BLK_DEV_INITRD=n
+
+CONFIG_DEVFREQ_GOV_PERFORMANCE=y
+CONFIG_DEVFREQ_GOV_POWERSAVE=y
+CONFIG_DEVFREQ_GOV_USERSPACE=y
+CONFIG_DEVFREQ_GOV_PASSIVE=y
+
+CONFIG_DRM=y
+CONFIG_DRM_ROCKCHIP=y
+CONFIG_DRM_PANFROST=y
+CONFIG_DRM_LIMA=y
+CONFIG_DRM_PANEL_SIMPLE=y
+CONFIG_DRM_PANEL_EDP=y
+CONFIG_DRM_MSM=y
+CONFIG_DRM_ETNAVIV=y
+CONFIG_DRM_I2C_ADV7511=y
+CONFIG_PWM_CROS_EC=y
+CONFIG_BACKLIGHT_PWM=y
+
+CONFIG_ROCKCHIP_CDN_DP=n
+
+CONFIG_SPI_ROCKCHIP=y
+CONFIG_PWM_ROCKCHIP=y
+CONFIG_PHY_ROCKCHIP_DP=y
+CONFIG_DWMAC_ROCKCHIP=y
+CONFIG_STMMAC_ETH=y
+CONFIG_TYPEC_FUSB302=y
+CONFIG_TYPEC=y
+CONFIG_TYPEC_TCPM=y
+
+# MSM platform bits
+
+# For CONFIG_QCOM_LMH
+CONFIG_OF=y
+
+CONFIG_ARM_SMMU_QCOM=y
+CONFIG_QCOM_COMMAND_DB=y
+CONFIG_QCOM_RPMHPD=y
+CONFIG_QCOM_RPMPD=y
+CONFIG_QCOM_OCMEM=y
+CONFIG_SDM_GPUCC_845=y
+CONFIG_SDM_VIDEOCC_845=y
+CONFIG_SDM_DISPCC_845=y
+CONFIG_SDM_LPASSCC_845=y
+CONFIG_SDM_CAMCC_845=y
+CONFIG_RESET_QCOM_PDC=y
+CONFIG_DRM_TI_SN65DSI86=y
+CONFIG_I2C_QCOM_GENI=y
+CONFIG_SPI_QCOM_GENI=y
+CONFIG_PHY_QCOM_QUSB2=y
+CONFIG_PHY_QCOM_QMP=y
+CONFIG_MSM_GCC_8996=y
+CONFIG_QCOM_CLK_APCC_MSM8996=y
+CONFIG_QCOM_LLCC=y
+CONFIG_QCOM_LMH=y
+CONFIG_QCOM_SPMI_TEMP_ALARM=y
+CONFIG_QCOM_WDT=y
+CONFIG_POWER_RESET_QCOM_PON=y
+CONFIG_RTC_DRV_PM8XXX=y
+CONFIG_INTERCONNECT=y
+CONFIG_INTERCONNECT_QCOM=y
+CONFIG_INTERCONNECT_QCOM_MSM8996=y
+CONFIG_INTERCONNECT_QCOM_SDM845=y
+CONFIG_INTERCONNECT_QCOM_MSM8916=y
+CONFIG_INTERCONNECT_QCOM_MSM8996=y
+CONFIG_INTERCONNECT_QCOM_OSM_L3=y
+CONFIG_INTERCONNECT_QCOM_SC7180=y
+CONFIG_INTERCONNECT_QCOM_SM8350=y
+CONFIG_CRYPTO_DEV_QCOM_RNG=y
+CONFIG_SC_DISPCC_7180=y
+CONFIG_SC_GPUCC_7180=y
+CONFIG_SM_GPUCC_8350=y
+CONFIG_QCOM_SPMI_ADC5=y
+CONFIG_DRM_PARADE_PS8640=y
+CONFIG_DRM_LONTIUM_LT9611UXC=y
+CONFIG_PHY_QCOM_USB_HS=y
+CONFIG_QCOM_GPI_DMA=y
+CONFIG_USB_ONBOARD_HUB=y
+CONFIG_NVMEM_QCOM_QFPROM=y
+CONFIG_PHY_QCOM_USB_SNPS_FEMTO_V2=y
+
+
+# db410c ethernet
+CONFIG_USB_RTL8152=y
+# db820c ethernet
+CONFIG_ATL1C=y
+# Chromebooks ethernet
+CONFIG_USB_ONBOARD_HUB=y
+# 888 HDK ethernet
+CONFIG_USB_LAN78XX=y
+
+CONFIG_ARCH_ALPINE=n
+CONFIG_ARCH_BCM2835=y
+CONFIG_ARCH_BCM_IPROC=n
+CONFIG_ARCH_BERLIN=n
+CONFIG_ARCH_BRCMSTB=n
+CONFIG_ARCH_EXYNOS=n
+CONFIG_ARCH_K3=n
+CONFIG_ARCH_LAYERSCAPE=n
+CONFIG_ARCH_LG1K=n
+CONFIG_ARCH_HISI=n
+CONFIG_ARCH_MVEBU=n
+CONFIG_ARCH_SEATTLE=n
+CONFIG_ARCH_SYNQUACER=n
+CONFIG_ARCH_RENESAS=n
+CONFIG_ARCH_R8A774A1=n
+CONFIG_ARCH_R8A774C0=n
+CONFIG_ARCH_R8A7795=n
+CONFIG_ARCH_R8A7796=n
+CONFIG_ARCH_R8A77965=n
+CONFIG_ARCH_R8A77970=n
+CONFIG_ARCH_R8A77980=n
+CONFIG_ARCH_R8A77990=n
+CONFIG_ARCH_R8A77995=n
+CONFIG_ARCH_STRATIX10=n
+CONFIG_ARCH_TEGRA=n
+CONFIG_ARCH_SPRD=n
+CONFIG_ARCH_THUNDER=n
+CONFIG_ARCH_THUNDER2=n
+CONFIG_ARCH_UNIPHIER=n
+CONFIG_ARCH_VEXPRESS=n
+CONFIG_ARCH_XGENE=n
+CONFIG_ARCH_ZX=n
+CONFIG_ARCH_ZYNQMP=n
+
+# Strip out some stuff we don't need for graphics testing, to reduce
+# the build.
+CONFIG_CAN=n
+CONFIG_WIRELESS=n
+CONFIG_RFKILL=n
+CONFIG_WLAN=n
+
+CONFIG_REGULATOR_FAN53555=y
+CONFIG_REGULATOR=y
+
+CONFIG_REGULATOR_VCTRL=y
+
+CONFIG_KASAN=n
+CONFIG_KASAN_INLINE=n
+CONFIG_STACKTRACE=n
+
+CONFIG_TMPFS=y
+
+CONFIG_PROVE_LOCKING=n
+CONFIG_DEBUG_LOCKDEP=n
+CONFIG_SOFTLOCKUP_DETECTOR=y
+CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y
+
+CONFIG_DETECT_HUNG_TASK=y
+
+CONFIG_FW_LOADER_COMPRESS=y
+CONFIG_FW_LOADER_USER_HELPER=n
+
+CONFIG_USB_USBNET=y
+CONFIG_NETDEVICES=y
+CONFIG_USB_NET_DRIVERS=y
+CONFIG_USB_RTL8152=y
+CONFIG_USB_NET_AX8817X=y
+CONFIG_USB_NET_SMSC95XX=y
+
+# For amlogic
+CONFIG_MESON_GXL_PHY=y
+CONFIG_MDIO_BUS_MUX_MESON_G12A=y
+CONFIG_DRM_MESON=y
+
+# For Mediatek
+CONFIG_DRM_MEDIATEK=y
+CONFIG_PWM_MEDIATEK=y
+CONFIG_DRM_MEDIATEK_HDMI=y
+CONFIG_GNSS=y
+CONFIG_GNSS_MTK_SERIAL=y
+CONFIG_HW_RANDOM=y
+CONFIG_HW_RANDOM_MTK=y
+CONFIG_MTK_DEVAPC=y
+CONFIG_PWM_MTK_DISP=y
+CONFIG_MTK_CMDQ=y
+
+# For nouveau.  Note that DRM must be a module so that it's loaded after NFS is up to provide the firmware.
+CONFIG_ARCH_TEGRA=y
+CONFIG_DRM_NOUVEAU=m
+CONFIG_DRM_TEGRA=m
+CONFIG_R8169=y
+CONFIG_STAGING=y
+CONFIG_DRM_TEGRA_STAGING=y
+CONFIG_TEGRA_HOST1X=y
+CONFIG_ARM_TEGRA_DEVFREQ=y
+CONFIG_TEGRA_SOCTHERM=y
+CONFIG_DRM_TEGRA_DEBUG=y
+CONFIG_PWM_TEGRA=y
diff --git a/drivers/gpu/drm/ci/build-igt.sh b/drivers/gpu/drm/ci/build-igt.sh
new file mode 100644
index 000000000000..500fa4f5c30a
--- /dev/null
+++ b/drivers/gpu/drm/ci/build-igt.sh
@@ -0,0 +1,35 @@
+#!/bin/bash
+# SPDX-License-Identifier: MIT
+
+set -ex
+
+git clone https://gitlab.freedesktop.org/drm/igt-gpu-tools.git --single-branch --no-checkout
+cd igt-gpu-tools
+git checkout $IGT_VERSION
+
+if [[ "$KERNEL_ARCH" = "arm" ]]; then
+    . ../.gitlab-ci/container/create-cross-file.sh armhf
+    EXTRA_MESON_ARGS="--cross-file /cross_file-armhf.txt"
+fi
+
+MESON_OPTIONS="-Doverlay=disabled                    \
+               -Dchamelium=disabled                  \
+               -Dvalgrind=disabled                   \
+               -Dman=enabled                         \
+               -Dtests=enabled                       \
+               -Drunner=enabled                      \
+               -Dlibunwind=enabled                   \
+               -Dprefix=/igt"
+
+mkdir -p /igt
+meson build $MESON_OPTIONS $EXTRA_MESON_ARGS
+ninja -C build -j${FDO_CI_CONCURRENT:-4} || ninja -C build -j 1
+ninja -C build install
+
+mkdir -p artifacts/
+tar -cf artifacts/igt.tar /igt
+
+# Pass needed files to the test stage
+S3_ARTIFACT_NAME="igt.tar.gz"
+gzip -c artifacts/igt.tar > ${S3_ARTIFACT_NAME}
+ci-fairy s3cp --token-file "${CI_JOB_JWT_FILE}" ${S3_ARTIFACT_NAME} https://${PIPELINE_ARTIFACTS_BASE}/${KERNEL_ARCH}/${S3_ARTIFACT_NAME}
diff --git a/drivers/gpu/drm/ci/build.sh b/drivers/gpu/drm/ci/build.sh
new file mode 100644
index 000000000000..7b014287a041
--- /dev/null
+++ b/drivers/gpu/drm/ci/build.sh
@@ -0,0 +1,157 @@
+#!/bin/bash
+# SPDX-License-Identifier: MIT
+
+set -ex
+
+# Clean up stale rebases that GitLab might not have removed when reusing a checkout dir
+rm -rf .git/rebase-apply
+
+. .gitlab-ci/container/container_pre_build.sh
+
+# libssl-dev was uninstalled because it was considered an ephemeral package
+apt-get update
+apt-get install -y libssl-dev
+
+if [[ "$KERNEL_ARCH" = "arm64" ]]; then
+    GCC_ARCH="aarch64-linux-gnu"
+    DEBIAN_ARCH="arm64"
+    DEVICE_TREES="arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dtb"
+    DEVICE_TREES+=" arch/arm64/boot/dts/amlogic/meson-gxl-s805x-libretech-ac.dtb"
+    DEVICE_TREES+=" arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dtb"
+    DEVICE_TREES+=" arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dtb"
+    DEVICE_TREES+=" arch/arm64/boot/dts/qcom/apq8016-sbc.dtb"
+    DEVICE_TREES+=" arch/arm64/boot/dts/qcom/apq8096-db820c.dtb"
+    DEVICE_TREES+=" arch/arm64/boot/dts/amlogic/meson-g12b-a311d-khadas-vim3.dtb"
+    DEVICE_TREES+=" arch/arm64/boot/dts/mediatek/mt8173-elm-hana.dtb"
+    DEVICE_TREES+=" arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-juniper-sku16.dtb"
+    DEVICE_TREES+=" arch/arm64/boot/dts/mediatek/mt8192-asurada-spherion-r0.dtb"
+    DEVICE_TREES+=" arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-limozeen-nots-r5.dtb"
+elif [[ "$KERNEL_ARCH" = "arm" ]]; then
+    GCC_ARCH="arm-linux-gnueabihf"
+    DEBIAN_ARCH="armhf"
+    DEVICE_TREES="arch/arm/boot/dts/rockchip/rk3288-veyron-jaq.dtb"
+    DEVICE_TREES+=" arch/arm/boot/dts/allwinner/sun8i-h3-libretech-all-h3-cc.dtb"
+    DEVICE_TREES+=" arch/arm/boot/dts/nxp/imx/imx6q-cubox-i.dtb"
+    apt-get install -y libssl-dev:armhf
+else
+    GCC_ARCH="x86_64-linux-gnu"
+    DEBIAN_ARCH="x86_64"
+    DEVICE_TREES=""
+fi
+
+export ARCH=${KERNEL_ARCH}
+export CROSS_COMPILE="${GCC_ARCH}-"
+
+# The kernel doesn't like the gold linker (or the old lld in our debians).
+# Sneak in some override symlinks during kernel build until we can update
+# debian.
+mkdir -p ld-links
+for i in /usr/bin/*-ld /usr/bin/ld; do
+    i=$(basename $i)
+    ln -sf /usr/bin/$i.bfd ld-links/$i
+done
+
+NEWPATH=$(pwd)/ld-links
+export PATH=$NEWPATH:$PATH
+
+git config --global user.email "fdo@example.com"
+git config --global user.name "freedesktop.org CI"
+git config --global pull.rebase true
+
+# Try to merge fixes from target repo
+if [ "$(git ls-remote --exit-code --heads ${UPSTREAM_REPO} ${TARGET_BRANCH}-external-fixes)" ]; then
+    git pull ${UPSTREAM_REPO} ${TARGET_BRANCH}-external-fixes
+fi
+
+# Try to merge fixes from local repo if this isn't a merge request
+if [ -z "$CI_MERGE_REQUEST_PROJECT_PATH" ]; then
+    if [ "$(git ls-remote --exit-code --heads origin ${TARGET_BRANCH}-external-fixes)" ]; then
+        git pull origin ${TARGET_BRANCH}-external-fixes
+    fi
+fi
+
+for opt in $ENABLE_KCONFIGS; do
+  echo CONFIG_$opt=y >> drivers/gpu/drm/ci/${KERNEL_ARCH}.config
+done
+for opt in $DISABLE_KCONFIGS; do
+  echo CONFIG_$opt=n >> drivers/gpu/drm/ci/${KERNEL_ARCH}.config
+done
+
+if [[ -n "${MERGE_FRAGMENT}" ]]; then
+    ./scripts/kconfig/merge_config.sh ${DEFCONFIG} drivers/gpu/drm/ci/${MERGE_FRAGMENT}
+else
+    make `basename ${DEFCONFIG}`
+fi
+
+make ${KERNEL_IMAGE_NAME}
+
+mkdir -p /lava-files/
+for image in ${KERNEL_IMAGE_NAME}; do
+    cp arch/${KERNEL_ARCH}/boot/${image} /lava-files/.
+done
+
+if [[ -n ${DEVICE_TREES} ]]; then
+    make dtbs
+    cp ${DEVICE_TREES} /lava-files/.
+fi
+
+make modules
+mkdir -p install/modules/
+INSTALL_MOD_PATH=install/modules/ make modules_install
+
+if [[ ${DEBIAN_ARCH} = "arm64" ]]; then
+    make Image.lzma
+    mkimage \
+        -f auto \
+        -A arm \
+        -O linux \
+        -d arch/arm64/boot/Image.lzma \
+        -C lzma\
+        -b arch/arm64/boot/dts/qcom/sdm845-cheza-r3.dtb \
+        /lava-files/cheza-kernel
+    KERNEL_IMAGE_NAME+=" cheza-kernel"
+
+    # Make a gzipped copy of the Image for db410c.
+    gzip -k /lava-files/Image
+    KERNEL_IMAGE_NAME+=" Image.gz"
+fi
+
+# Pass needed files to the test stage
+mkdir -p install
+cp -rfv .gitlab-ci/* install/.
+cp -rfv install/common install/ci-common
+cp -rfv drivers/gpu/drm/ci/* install/.
+
+. .gitlab-ci/container/container_post_build.sh
+
+if [[ "$UPLOAD_TO_MINIO" = "1" ]]; then
+    xz -7 -c -T${FDO_CI_CONCURRENT:-4} vmlinux > /lava-files/vmlinux.xz
+    FILES_TO_UPLOAD="$KERNEL_IMAGE_NAME vmlinux.xz"
+
+    if [[ -n $DEVICE_TREES ]]; then
+        FILES_TO_UPLOAD="$FILES_TO_UPLOAD $(basename -a $DEVICE_TREES)"
+    fi
+
+    for f in $FILES_TO_UPLOAD; do
+        ci-fairy s3cp --token-file "${CI_JOB_JWT_FILE}" /lava-files/$f \
+                https://${PIPELINE_ARTIFACTS_BASE}/${DEBIAN_ARCH}/$f
+    done
+
+    S3_ARTIFACT_NAME="kernel-files.tar.zst"
+    tar --zstd -cf $S3_ARTIFACT_NAME install
+    ci-fairy s3cp --token-file "${CI_JOB_JWT_FILE}" ${S3_ARTIFACT_NAME} https://${PIPELINE_ARTIFACTS_BASE}/${DEBIAN_ARCH}/${S3_ARTIFACT_NAME}
+
+    echo "Download vmlinux.xz from https://${PIPELINE_ARTIFACTS_BASE}/${DEBIAN_ARCH}/vmlinux.xz"
+fi
+
+mkdir -p artifacts/install/lib
+mv install/* artifacts/install/.
+rm -rf artifacts/install/modules
+ln -s common artifacts/install/ci-common
+
+for image in ${KERNEL_IMAGE_NAME}; do
+    cp /lava-files/$image artifacts/install/.
+done
+
+tar -C artifacts -cf artifacts/install.tar install
+rm -rf artifacts/install
diff --git a/drivers/gpu/drm/ci/build.yml b/drivers/gpu/drm/ci/build.yml
new file mode 100644
index 000000000000..e6503f1c5927
--- /dev/null
+++ b/drivers/gpu/drm/ci/build.yml
@@ -0,0 +1,110 @@
+.build:
+  extends:
+    - .build-rules
+  stage: build
+  artifacts:
+    paths:
+      - artifacts
+  script:
+    - FDO_CI_CONCURRENT=${FDO_CI_CONCURRENT} bash drivers/gpu/drm/ci/build.sh
+
+.build:arm32:
+  extends:
+    - .build
+    - .use-debian/arm64_build
+  tags:
+    - aarch64
+  variables:
+    DEFCONFIG: "arch/arm/configs/multi_v7_defconfig"
+    KERNEL_IMAGE_NAME: "zImage"
+    KERNEL_ARCH: "arm"
+
+.build:arm64:
+  extends:
+    - .build
+    - .use-debian/arm64_build
+  tags:
+    - aarch64
+  variables:
+    DEFCONFIG: "arch/arm64/configs/defconfig"
+    KERNEL_IMAGE_NAME: "Image"
+    KERNEL_ARCH: "arm64"
+
+.build:x86_64:
+  extends:
+    - .build
+    - .use-debian/x86_64_build
+  variables:
+    DEFCONFIG: "arch/x86/configs/x86_64_defconfig"
+    KERNEL_IMAGE_NAME: "bzImage"
+    KERNEL_ARCH: "x86_64"
+
+
+# Build IGT for testing on devices
+
+igt:arm32:
+  extends: .build:arm32
+  script:
+    - FDO_CI_CONCURRENT=${FDO_CI_CONCURRENT} bash drivers/gpu/drm/ci/build-igt.sh
+
+igt:arm64:
+  extends: .build:arm64
+  script:
+    - FDO_CI_CONCURRENT=${FDO_CI_CONCURRENT} bash drivers/gpu/drm/ci/build-igt.sh
+
+igt:x86_64:
+  extends: .build:x86_64
+  script:
+    - FDO_CI_CONCURRENT=${FDO_CI_CONCURRENT} bash drivers/gpu/drm/ci/build-igt.sh
+
+# Build kernels for testing on devices
+
+testing:arm32:
+  extends: .build:arm32
+  variables:
+    # Would be good to have DEBUG_KMEMLEAK, but it doesn't work well with any of
+    # PROVE_LOCKING and KASAN as of 5.17.
+    #
+    # db410c and db820c don't boot with KASAN_INLINE, probably due to the kernel
+    # becoming too big for their bootloaders.
+    ENABLE_KCONFIGS: "PROVE_LOCKING DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT"
+    UPLOAD_TO_MINIO: 1
+    MERGE_FRAGMENT: arm.config
+
+testing:arm64:
+  extends: .build:arm64
+  variables:
+    # Would be good to have DEBUG_KMEMLEAK, but it doesn't work well with any of
+    # PROVE_LOCKING and KASAN as of 5.17.
+    #
+    # db410c and db820c don't boot with KASAN_INLINE, probably due to the kernel
+    # becoming too big for their bootloaders.
+    ENABLE_KCONFIGS: "PROVE_LOCKING DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT"
+    UPLOAD_TO_MINIO: 1
+    MERGE_FRAGMENT: arm64.config
+
+testing:x86_64:
+  extends: .build:x86_64
+  variables:
+    # Would be good to have DEBUG_KMEMLEAK, but it doesn't work well with any of
+    # PROVE_LOCKING and KASAN as of 5.17.
+    #
+    # db410c and db820c don't boot with KASAN_INLINE, probably due to the kernel
+    # becoming too big for their bootloaders.
+    ENABLE_KCONFIGS: "PROVE_LOCKING DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT"
+    UPLOAD_TO_MINIO: 1
+    MERGE_FRAGMENT: x86_64.config
+
+
+# Jobs for build-testing different configurations
+
+build:arm32:
+  extends: .build:arm32
+
+build-nodebugfs:arm64:
+  extends: .build:arm64
+  variables:
+    DISABLE_KCONFIGS: "DEBUG_FS"
+
+build:x86_64:
+  extends: .build:x86_64
diff --git a/drivers/gpu/drm/ci/check-patch.py b/drivers/gpu/drm/ci/check-patch.py
new file mode 100755
index 000000000000..a5f399a20e25
--- /dev/null
+++ b/drivers/gpu/drm/ci/check-patch.py
@@ -0,0 +1,57 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0-or-later
+#
+# check-patch.py: run checkpatch.pl across all commits in a branch
+#
+# Based on qemu/.gitlab-ci.d/check-patch.py
+#
+# Copyright (C) 2020 Red Hat, Inc.
+# Copyright (C) 2022 Collabora Ltd.
+
+import os
+import os.path
+import sys
+import subprocess
+
+repourl = "https://gitlab.freedesktop.org/%s.git" % os.environ["CI_MERGE_REQUEST_PROJECT_PATH"]
+
+# GitLab CI environment does not give us any direct info about the
+# base for the user's branch. We thus need to figure out a common
+# ancestor between the user's branch and current git master.
+os.environ["GIT_DEPTH"] = "1000"
+subprocess.call(["git", "remote", "remove", "check-patch"], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
+subprocess.check_call(["git", "remote", "add", "check-patch", repourl])
+subprocess.check_call(["git", "fetch", "check-patch", os.environ["CI_MERGE_REQUEST_TARGET_BRANCH_NAME"]],
+                      stdout=subprocess.DEVNULL,
+                      stderr=subprocess.DEVNULL)
+
+ancestor = subprocess.check_output(["git", "merge-base",
+                                    "check-patch/%s" % os.environ["CI_MERGE_REQUEST_TARGET_BRANCH_NAME"], "HEAD"],
+                                   universal_newlines=True)
+
+ancestor = ancestor.strip()
+
+log = subprocess.check_output(["git", "log", "--format=%H %s",
+                               ancestor + "..."],
+                              universal_newlines=True)
+
+subprocess.check_call(["git", "remote", "rm", "check-patch"])
+
+if log == "":
+    print("\nNo commits since %s, skipping checks\n" % ancestor)
+    sys.exit(0)
+
+errors = False
+
+print("\nChecking all commits since %s...\n" % ancestor, flush=True)
+
+ret = subprocess.run(["scripts/checkpatch.pl",
+                      "--terse",
+                      "--types", os.environ["CHECKPATCH_TYPES"],
+                      "--git", ancestor + "..."])
+
+if ret.returncode != 0:
+    print("    ❌ FAIL one or more commits failed scripts/checkpatch.pl")
+    sys.exit(1)
+
+sys.exit(0)
diff --git a/drivers/gpu/drm/ci/container.yml b/drivers/gpu/drm/ci/container.yml
new file mode 100644
index 000000000000..9764e7921a4f
--- /dev/null
+++ b/drivers/gpu/drm/ci/container.yml
@@ -0,0 +1,65 @@
+.container:
+  variables:
+    CI_REPOSITORY_URL: ${DRM_CI_PROJECT_URL}.git # So ci-templates clones drm-ci instead of the repo to test
+    CI_COMMIT_SHA: ${DRM_CI_COMMIT_SHA}
+
+debian/x86_64_build-base:
+  variables:
+    EXTRA_LOCAL_PACKAGES: "libcairo-dev libdw-dev libjson-c-dev libkmod2 libkmod-dev libpciaccess-dev libproc2-dev libudev-dev libunwind-dev python3-docutils bc python3-ply libssl-dev bc"
+
+debian/x86_64_test-gl:
+  variables:
+    EXTRA_LOCAL_PACKAGES: "jq libasound2 libcairo2 libdw1 libglib2.0-0 libjson-c5 libkmod-dev libkmod2 libgles2 libproc2-dev"
+
+debian/arm64_build:
+  variables:
+    EXTRA_LOCAL_PACKAGES: "libcairo-dev libdw-dev libjson-c-dev libproc2-dev libkmod2 libkmod-dev libpciaccess-dev libudev-dev libunwind-dev python3-docutils libssl-dev crossbuild-essential-armhf libkmod-dev:armhf libproc2-dev:armhf libunwind-dev:armhf libdw-dev:armhf libpixman-1-dev:armhf libcairo-dev:armhf libudev-dev:armhf libjson-c-dev:armhf"
+
+.kernel+rootfs:
+  variables:
+    EXTRA_LOCAL_PACKAGES: "jq libasound2 libcairo2 libdw1 libglib2.0-0 libjson-c5"
+
+# Disable container jobs that we won't use
+alpine/x86_64_build:
+  rules:
+    - when: never
+
+debian/x86_64_test-vk:
+  rules:
+    - when: never
+
+fedora/x86_64_build:
+  rules:
+    - when: never
+
+debian/android_build:
+  rules:
+    - when: never
+
+debian/x86_64_test-android:
+  rules:
+    - when: never
+
+windows_build_vs2019:
+  rules:
+    - when: never
+
+windows_test_vs2019:
+  rules:
+    - when: never
+
+.debian/x86_64_build-mingw:
+   rules:
+    - when: never
+
+rustfmt:
+   rules:
+    - when: never
+
+windows_vs2019:
+   rules:
+    - when: never
+
+clang-format:
+   rules:
+    - when: never
\ No newline at end of file
diff --git a/drivers/gpu/drm/ci/gitlab-ci.yml b/drivers/gpu/drm/ci/gitlab-ci.yml
new file mode 100644
index 000000000000..2c4df53f5dfe
--- /dev/null
+++ b/drivers/gpu/drm/ci/gitlab-ci.yml
@@ -0,0 +1,251 @@
+variables:
+  DRM_CI_PROJECT_PATH: &drm-ci-project-path mesa/mesa
+  DRM_CI_COMMIT_SHA: &drm-ci-commit-sha 0dc961645c4f0241f8512cb0ec3ad59635842072
+
+  UPSTREAM_REPO: git://anongit.freedesktop.org/drm/drm
+  TARGET_BRANCH: drm-next
+
+  IGT_VERSION: 471bfababd070e1dac0ebb87470ac4f2ae85e663
+
+  DEQP_RUNNER_GIT_URL: https://gitlab.freedesktop.org/anholt/deqp-runner.git
+  DEQP_RUNNER_GIT_TAG: v0.15.0
+
+  FDO_UPSTREAM_REPO: helen.fornazier/linux   # The repo where the git-archive daily runs
+  MESA_TEMPLATES_COMMIT: &ci-templates-commit d5aa3941aa03c2f716595116354fb81eb8012acb
+  DRM_CI_PROJECT_URL: https://gitlab.freedesktop.org/${DRM_CI_PROJECT_PATH}
+  CI_PRE_CLONE_SCRIPT: |-
+          set -o xtrace
+          curl -L --retry 4 -f --retry-all-errors --retry-delay 60 -s ${DRM_CI_PROJECT_URL}/-/raw/${DRM_CI_COMMIT_SHA}/.gitlab-ci/download-git-cache.sh -o download-git-cache.sh
+          bash download-git-cache.sh
+          rm download-git-cache.sh
+          set +o xtrace
+  S3_HOST: s3.freedesktop.org
+  # per-pipeline artifact storage on MinIO
+  PIPELINE_ARTIFACTS_BASE: ${S3_HOST}/artifacts/${CI_PROJECT_PATH}/${CI_PIPELINE_ID}
+  # per-job artifact storage on MinIO
+  JOB_ARTIFACTS_BASE: ${PIPELINE_ARTIFACTS_BASE}/${CI_JOB_ID}
+
+  LAVA_JOB_PRIORITY: 30
+
+default:
+  before_script:
+    - export SCRIPTS_DIR=$(mktemp -d)
+    - curl -L -s --retry 4 -f --retry-all-errors --retry-delay 60 -O --output-dir "${SCRIPTS_DIR}" "${DRM_CI_PROJECT_URL}/-/raw/${DRM_CI_COMMIT_SHA}/.gitlab-ci/setup-test-env.sh"
+    - source ${SCRIPTS_DIR}/setup-test-env.sh
+    - echo -e "\e[0Ksection_start:$(date +%s):unset_env_vars_section[collapsed=true]\r\e[0KUnsetting vulnerable environment variables"
+    - export CI_JOB_JWT_FILE="${CI_JOB_JWT_FILE:-$(mktemp)}"
+    - echo -n "${CI_JOB_JWT}" > "${CI_JOB_JWT_FILE}"
+    - unset CI_JOB_JWT
+    - echo -e "\e[0Ksection_end:$(date +%s):unset_env_vars_section\r\e[0K"
+
+    - echo -e "\e[0Ksection_start:$(date +%s):drm_ci_download_section[collapsed=true]\r\e[0KDownloading mesa from $DRM_CI_PROJECT_URL/-/archive/$DRM_CI_COMMIT_SHA/mesa-$DRM_CI_COMMIT_SHA.tar.gz"
+    - cd $CI_PROJECT_DIR
+    - curl --output - $DRM_CI_PROJECT_URL/-/archive/$DRM_CI_COMMIT_SHA/mesa-$DRM_CI_COMMIT_SHA.tar.gz | tar -xz
+    - mv mesa-$DRM_CI_COMMIT_SHA/.gitlab-ci* .
+    - rm -rf mesa-$DRM_CI_COMMIT_SHA/
+    - echo -e "\e[0Ksection_end:$(date +%s):drm_ci_download_section\r\e[0K"
+
+  after_script:
+    - >
+      set +x
+
+      test -e "${CI_JOB_JWT_FILE}" &&
+      export CI_JOB_JWT="$(<${CI_JOB_JWT_FILE})" &&
+      rm "${CI_JOB_JWT_FILE}"
+
+  # Retry when job fails.
+  retry:
+    max: 1
+    # Ignore runner_unsupported, stale_schedule, archived_failure, or
+    # unmet_prerequisites
+    when:
+      - api_failure
+      - runner_system_failure
+      - script_failure
+      - job_execution_timeout
+      - scheduler_failure
+      - data_integrity_failure
+      - unknown_failure
+
+include:
+  - project: 'freedesktop/ci-templates'
+    ref: 16bc29078de5e0a067ff84a1a199a3760d3b3811
+    file:
+      - '/templates/ci-fairy.yml'
+  - project: 'freedesktop/ci-templates'
+    ref: *ci-templates-commit
+    file:
+      - '/templates/alpine.yml'
+      - '/templates/debian.yml'
+      - '/templates/fedora.yml'
+  - project: *drm-ci-project-path
+    ref: *drm-ci-commit-sha
+    file:
+      - '/.gitlab-ci/farm-rules.yml'
+      - '/.gitlab-ci/test-source-dep.yml'
+      - '/.gitlab-ci/container/gitlab-ci.yml'
+      - '/.gitlab-ci/test/gitlab-ci.yml'
+      - '/.gitlab-ci/lava/lava-gitlab-ci.yml'
+  - drivers/gpu/drm/ci/image-tags.yml
+  - drivers/gpu/drm/ci/container.yml
+  - drivers/gpu/drm/ci/static-checks.yml
+  - drivers/gpu/drm/ci/build.yml
+  - drivers/gpu/drm/ci/test.yml
+  - 'https://gitlab.freedesktop.org/gfx-ci/lab-status/-/raw/main/lab-status.yml'
+
+
+stages:
+  - sanity
+  - container
+  - git-archive
+  - build
+  - amdgpu
+  - i915
+  - mediatek
+  - meson
+  - msm
+  - rockchip
+  - virtio-gpu
+  - lint
+
+# YAML anchors for rule conditions
+# --------------------------------
+.rules-anchors:
+  rules:
+    # Pipeline for forked project branch
+    - if: &is-forked-branch '$CI_COMMIT_BRANCH && $CI_PROJECT_NAMESPACE != "mesa"'
+      when: manual
+    # Forked project branch / pre-merge pipeline not for Marge bot
+    - if: &is-forked-branch-or-pre-merge-not-for-marge '$CI_PROJECT_NAMESPACE != "mesa" || ($GITLAB_USER_LOGIN != "marge-bot" && $CI_PIPELINE_SOURCE == "merge_request_event")'
+      when: manual
+    # Pipeline runs for the main branch of the upstream Mesa project
+    - if: &is-mesa-main '$CI_PROJECT_NAMESPACE == "mesa" && $CI_COMMIT_REF_NAME == $CI_DEFAULT_BRANCH && $CI_COMMIT_BRANCH'
+      when: always
+    # Post-merge pipeline
+    - if: &is-post-merge '$CI_PROJECT_NAMESPACE == "mesa" && $CI_COMMIT_BRANCH'
+      when: on_success
+    # Post-merge pipeline, not for Marge Bot
+    - if: &is-post-merge-not-for-marge '$CI_PROJECT_NAMESPACE == "mesa" && $GITLAB_USER_LOGIN != "marge-bot" && $CI_COMMIT_BRANCH'
+      when: on_success
+    # Pre-merge pipeline
+    - if: &is-pre-merge '$CI_PIPELINE_SOURCE == "merge_request_event"'
+      when: on_success
+    # Pre-merge pipeline for Marge Bot
+    - if: &is-pre-merge-for-marge '$GITLAB_USER_LOGIN == "marge-bot" && $CI_PIPELINE_SOURCE == "merge_request_event"'
+      when: on_success
+
+# Rule to filter for only scheduled pipelines.
+.scheduled_pipeline-rules:
+  rules:
+    - if: &is-scheduled-pipeline '$CI_PIPELINE_SOURCE == "schedule"'
+      when: on_success
+
+# Generic rule to not run the job during scheduled pipelines. Jobs that aren't
+# something like a nightly run should include this rule.
+.no_scheduled_pipelines-rules:
+  rules:
+    - if: *is-scheduled-pipeline
+      when: never
+
+# When to automatically run the CI for build jobs
+.build-rules:
+  rules:
+    - !reference [.no_scheduled_pipelines-rules, rules]
+    # Run automatically once all dependency jobs have passed
+    - when: on_success
+
+
+.ci-deqp-artifacts:
+  artifacts:
+    name: "mesa_${CI_JOB_NAME}"
+    when: always
+    untracked: false
+    paths:
+      # Watch out!  Artifacts are relative to the build dir.
+      # https://gitlab.com/gitlab-org/gitlab-ce/commit/8788fb925706cad594adf6917a6c5f6587dd1521
+      - artifacts
+      - _build/meson-logs/*.txt
+      - _build/meson-logs/strace
+
+
+.container-rules:
+  rules:
+    - !reference [.no_scheduled_pipelines-rules, rules]
+    # Run pipeline by default in the main project if any CI pipeline
+    # configuration files were changed, to ensure docker images are up to date
+    - if: *is-post-merge
+      changes:
+      - drivers/gpu/drm/ci/**/*
+      when: on_success
+    # Run pipeline by default if it was triggered by Marge Bot, is for a
+    # merge request, and any files affecting the pipeline were changed
+    - if: *is-pre-merge-for-marge
+      when: on_success
+    # Run pipeline by default in the main project if it was not triggered by
+    # Marge Bot, and any files affecting the pipeline were changed
+    - if: *is-post-merge-not-for-marge
+      when: on_success
+    # Allow triggering jobs manually in other cases
+    - when: manual
+
+
+
+# Git archive
+
+make git archive:
+  extends:
+    - .fdo.ci-fairy
+  stage: git-archive
+  rules:
+    - !reference [.scheduled_pipeline-rules, rules]
+  # ensure we are running on packet
+  tags:
+    - packet.net
+  script:
+    # Remove drm-ci files we just added
+    - rm -rf .gitlab-ci.*
+
+    # Compactify the .git directory
+    - git gc --aggressive
+    # compress the current folder
+    - tar -cvzf ../$CI_PROJECT_NAME.tar.gz .
+
+    # login with the JWT token file
+    - ci-fairy s3cp --token-file "${CI_JOB_JWT_FILE}" ../$CI_PROJECT_NAME.tar.gz https://$S3_HOST/git-cache/$CI_PROJECT_NAMESPACE/$CI_PROJECT_NAME/$CI_PROJECT_NAME.tar.gz
+
+
+# Sanity checks of MR settings and commit logs
+sanity:
+  extends:
+    - .fdo.ci-fairy
+  stage: sanity
+  rules:
+    - if: *is-pre-merge
+      when: on_success
+    # Other cases default to never
+  variables:
+    GIT_STRATEGY: none
+  script:
+    # ci-fairy check-commits --junit-xml=check-commits.xml
+    - ci-fairy check-merge-request --require-allow-collaboration --junit-xml=check-merge-request.xml
+  artifacts:
+    when: on_failure
+    reports:
+      junit: check-*.xml
+
+# Rules for tests that should not block merging, but should be available to
+# optionally run with the "play" button in the UI in pre-merge non-marge
+# pipelines.  This should appear in "extends:" after any includes of
+# test-source-dep.yml rules, so that these rules replace those.
+.test-manual-mr:
+  rules:
+    - !reference [.no_scheduled_pipelines-rules, rules]
+    - if: *is-forked-branch-or-pre-merge-not-for-marge
+      when: manual
+  variables:
+    JOB_TIMEOUT: 80
+
+
+# Jobs that need to pass before spending hardware resources on further testing
+.required-for-hardware-jobs:
+  needs: []
\ No newline at end of file
diff --git a/drivers/gpu/drm/ci/igt_runner.sh b/drivers/gpu/drm/ci/igt_runner.sh
new file mode 100755
index 000000000000..2bb759165063
--- /dev/null
+++ b/drivers/gpu/drm/ci/igt_runner.sh
@@ -0,0 +1,77 @@
+#!/bin/sh
+# SPDX-License-Identifier: MIT
+
+set -ex
+
+export IGT_FORCE_DRIVER=${DRIVER_NAME}
+export PATH=$PATH:/igt/bin/
+export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/igt/lib/aarch64-linux-gnu/:/igt/lib/x86_64-linux-gnu:/igt/lib:/igt/lib64
+
+# Uncomment the below to debug problems with driver probing
+: '
+ls -l /dev/dri/
+cat /sys/kernel/debug/devices_deferred
+cat /sys/kernel/debug/device_component/*
+'
+
+# Dump drm state to confirm that kernel was able to find a connected display:
+# TODO this path might not exist for all drivers.. maybe run modetest instead?
+set +e
+cat /sys/kernel/debug/dri/*/state
+set -e
+
+# Cannot use HWCI_KERNEL_MODULES as at that point we don't have the module in /lib
+if [ "$IGT_FORCE_DRIVER" = "amdgpu" ]; then
+    mv /install/modules/lib/modules/* /lib/modules/.
+    modprobe amdgpu
+fi
+
+if [ -e "/install/xfails/$DRIVER_NAME-$GPU_VERSION-skips.txt" ]; then
+    IGT_SKIPS="--skips /install/xfails/$DRIVER_NAME-$GPU_VERSION-skips.txt"
+fi
+
+if [ -e "/install/xfails/$DRIVER_NAME-$GPU_VERSION-flakes.txt" ]; then
+    IGT_FLAKES="--flakes /install/xfails/$DRIVER_NAME-$GPU_VERSION-flakes.txt"
+fi
+
+if [ -e "/install/xfails/$DRIVER_NAME-$GPU_VERSION-fails.txt" ]; then
+    IGT_FAILS="--baseline /install/xfails/$DRIVER_NAME-$GPU_VERSION-fails.txt"
+fi
+
+if [ "`uname -m`" = "aarch64" ]; then
+    ARCH="arm64"
+elif [ "`uname -m`" = "armv7l" ]; then
+    ARCH="arm"
+else
+    ARCH="x86_64"
+fi
+
+curl -L --retry 4 -f --retry-all-errors --retry-delay 60 -s ${FDO_HTTP_CACHE_URI:-}$PIPELINE_ARTIFACTS_BASE/$ARCH/igt.tar.gz | tar --zstd -v -x -C /
+
+set +e
+igt-runner \
+    run \
+    --igt-folder /igt/libexec/igt-gpu-tools \
+    --caselist /install/testlist.txt \
+    --output /results \
+    $IGT_SKIPS \
+    $IGT_FLAKES \
+    $IGT_FAILS \
+    --fraction-start $CI_NODE_INDEX \
+    --fraction $CI_NODE_TOTAL \
+    --jobs 1
+ret=$?
+set -e
+
+deqp-runner junit \
+   --testsuite IGT \
+   --results /results/failures.csv \
+   --output /results/junit.xml \
+   --limit 50 \
+   --template "See https://$CI_PROJECT_ROOT_NAMESPACE.pages.freedesktop.org/-/$CI_PROJECT_NAME/-/jobs/$CI_JOB_ID/artifacts/results/{{testcase}}.xml"
+
+# Store the results also in the simpler format used by the runner in ChromeOS CI
+#sed -r 's/(dmesg-warn|pass)/success/g' /results/results.txt > /results/results_simple.txt
+
+cd $oldpath
+exit $ret
diff --git a/drivers/gpu/drm/ci/image-tags.yml b/drivers/gpu/drm/ci/image-tags.yml
new file mode 100644
index 000000000000..f051b6c547c5
--- /dev/null
+++ b/drivers/gpu/drm/ci/image-tags.yml
@@ -0,0 +1,15 @@
+variables:
+   CONTAINER_TAG: "2023-08-10-mesa-uprev"
+   DEBIAN_X86_64_BUILD_BASE_IMAGE: "debian/x86_64_build-base"
+   DEBIAN_BASE_TAG: "${CONTAINER_TAG}"
+
+   DEBIAN_X86_64_BUILD_IMAGE_PATH: "debian/x86_64_build"
+   DEBIAN_BUILD_TAG: "${CONTAINER_TAG}"
+
+   KERNEL_ROOTFS_TAG: "${CONTAINER_TAG}"
+
+   DEBIAN_X86_64_TEST_BASE_IMAGE: "debian/x86_64_test-base"
+   DEBIAN_X86_64_TEST_IMAGE_GL_PATH: "debian/x86_64_test-gl"
+   DEBIAN_X86_64_TEST_GL_TAG: "${CONTAINER_TAG}"
+
+   ALPINE_X86_64_LAVA_SSH_TAG: "${CONTAINER_TAG}"
\ No newline at end of file
diff --git a/drivers/gpu/drm/ci/lava-submit.sh b/drivers/gpu/drm/ci/lava-submit.sh
new file mode 100755
index 000000000000..0c4456b21b0f
--- /dev/null
+++ b/drivers/gpu/drm/ci/lava-submit.sh
@@ -0,0 +1,57 @@
+#!/bin/bash
+# SPDX-License-Identifier: MIT
+
+set -e
+set -x
+
+# Try to use the kernel and rootfs built in mainline first, so we're more
+# likely to hit cache
+if curl -L --retry 4 -f --retry-all-errors --retry-delay 60 -s "https://${BASE_SYSTEM_MAINLINE_HOST_PATH}/done"; then
+	BASE_SYSTEM_HOST_PATH="${BASE_SYSTEM_MAINLINE_HOST_PATH}"
+else
+	BASE_SYSTEM_HOST_PATH="${BASE_SYSTEM_FORK_HOST_PATH}"
+fi
+
+rm -rf results
+mkdir -p results/job-rootfs-overlay/
+
+cp artifacts/ci-common/capture-devcoredump.sh results/job-rootfs-overlay/
+cp artifacts/ci-common/init-*.sh results/job-rootfs-overlay/
+cp artifacts/ci-common/intel-gpu-freq.sh results/job-rootfs-overlay/
+cp "$SCRIPTS_DIR"/setup-test-env.sh results/job-rootfs-overlay/
+
+# Prepare env vars for upload.
+section_start variables "Variables passed through:"
+KERNEL_IMAGE_BASE_URL="https://${BASE_SYSTEM_HOST_PATH}" \
+	artifacts/ci-common/generate-env.sh | tee results/job-rootfs-overlay/set-job-env-vars.sh
+section_end variables
+
+tar zcf job-rootfs-overlay.tar.gz -C results/job-rootfs-overlay/ .
+ci-fairy s3cp --token-file "${CI_JOB_JWT_FILE}" job-rootfs-overlay.tar.gz "https://${JOB_ROOTFS_OVERLAY_PATH}"
+
+touch results/lava.log
+tail -f results/lava.log &
+
+PYTHONPATH=artifacts/ artifacts/lava/lava_job_submitter.py \
+	submit \
+	--dump-yaml \
+	--pipeline-info "$CI_JOB_NAME: $CI_PIPELINE_URL on $CI_COMMIT_REF_NAME ${CI_NODE_INDEX}/${CI_NODE_TOTAL}" \
+	--rootfs-url-prefix "https://${BASE_SYSTEM_HOST_PATH}" \
+	--kernel-url-prefix "https://${PIPELINE_ARTIFACTS_BASE}/${ARCH}" \
+	--build-url "${FDO_HTTP_CACHE_URI:-}https://${PIPELINE_ARTIFACTS_BASE}/${ARCH}/kernel-files.tar.zst" \
+	--job-rootfs-overlay-url "${FDO_HTTP_CACHE_URI:-}https://${JOB_ROOTFS_OVERLAY_PATH}" \
+	--job-timeout-min ${JOB_TIMEOUT:-80} \
+	--first-stage-init artifacts/ci-common/init-stage1.sh \
+	--ci-project-dir "${CI_PROJECT_DIR}" \
+	--device-type "${DEVICE_TYPE}" \
+	--dtb-filename "${DTB}" \
+	--jwt-file "${CI_JOB_JWT_FILE}" \
+	--kernel-image-name "${KERNEL_IMAGE_NAME}" \
+	--kernel-image-type "${KERNEL_IMAGE_TYPE}" \
+	--boot-method "${BOOT_METHOD}" \
+	--visibility-group "${VISIBILITY_GROUP}" \
+	--lava-tags "${LAVA_TAGS}" \
+	--mesa-job-name "$CI_JOB_NAME" \
+	--structured-log-file "results/lava_job_detail.json" \
+	--ssh-client-image "${LAVA_SSH_CLIENT_IMAGE}" \
+	>> results/lava.log
diff --git a/drivers/gpu/drm/ci/static-checks.yml b/drivers/gpu/drm/ci/static-checks.yml
new file mode 100644
index 000000000000..13ffa827b7fa
--- /dev/null
+++ b/drivers/gpu/drm/ci/static-checks.yml
@@ -0,0 +1,12 @@
+check-patch:
+  extends:
+    - .build
+    - .use-debian/x86_64_build
+  script:
+    - drivers/gpu/drm/ci/check-patch.py
+  variables:
+    CHECKPATCH_TYPES: "BAD_SIGN_OFF,BAD_STABLE_ADDRESS_STYLE,COMMIT_COMMENT_SYMBOL,COMMIT_MESSAGE,EMAIL_SUBJECT,FROM_SIGN_OFF_MISMATCH,MISSING_SIGN_OFF,NO_AUTHOR_SIGN_OFF,DIFF_IN_COMMIT_MSG,GERRIT_CHANGE_ID,GIT_COMMIT_ID,UNKNOWN_COMMIT_ID,CODE_INDENT,BIT_MACRO,DOS_LINE_ENDINGS"
+  rules:
+    - if: '$CI_PIPELINE_SOURCE == "merge_request_event"'
+      when: on_success
+    # Other cases default to never
diff --git a/drivers/gpu/drm/ci/test.yml b/drivers/gpu/drm/ci/test.yml
new file mode 100644
index 000000000000..6473cddaa7a9
--- /dev/null
+++ b/drivers/gpu/drm/ci/test.yml
@@ -0,0 +1,335 @@
+.test-rules:
+  rules:
+    - if: '$FD_FARM == "offline" && $RUNNER_TAG =~ /^google-freedreno-/'
+      when: never
+    - if: '$COLLABORA_FARM == "offline" && $RUNNER_TAG =~ /^mesa-ci-x86-64-lava-/'
+      when: never
+    - !reference [.no_scheduled_pipelines-rules, rules]
+    - when: on_success
+
+.lava-test:
+  extends:
+    - .test-rules
+  script:
+    # Note: Build dir (and thus install) may be dirty due to GIT_STRATEGY
+    - rm -rf install
+    - tar -xf artifacts/install.tar
+    - mv install/* artifacts/.
+    # Override it with our lava-submit.sh script
+    - ./artifacts/lava-submit.sh
+
+.lava-igt:arm32:
+  extends:
+    - .lava-test:arm32
+  variables:
+    HWCI_TEST_SCRIPT: "/install/igt_runner.sh"
+    ARCH: "armhf"
+  dependencies:
+    - testing:arm32
+  needs:
+    - alpine/x86_64_lava_ssh_client
+    - kernel+rootfs_arm32
+    - debian/x86_64_build
+    - testing:arm32
+    - igt:arm32
+
+.lava-igt:arm64:
+  extends:
+    - .lava-test:arm64
+  variables:
+    HWCI_TEST_SCRIPT: "/install/igt_runner.sh"
+    ARCH: "arm64"
+  dependencies:
+    - testing:arm64
+  needs:
+    - alpine/x86_64_lava_ssh_client
+    - kernel+rootfs_arm64
+    - debian/x86_64_build
+    - testing:arm64
+    - igt:arm64
+
+.lava-igt:x86_64:
+  extends:
+    - .lava-test:x86_64
+  variables:
+    HWCI_TEST_SCRIPT: "/install/igt_runner.sh"
+    ARCH: "x86_64"
+  dependencies:
+    - testing:x86_64
+  needs:
+    - alpine/x86_64_lava_ssh_client
+    - kernel+rootfs_x86_64
+    - debian/x86_64_build
+    - testing:x86_64
+    - igt:x86_64
+
+.baremetal-igt-arm64:
+  extends:
+    - .baremetal-test-arm64
+    - .use-debian/arm64_test
+    - .test-rules
+  variables:
+    FDO_CI_CONCURRENT: 10
+    HWCI_TEST_SCRIPT: "/install/igt_runner.sh"
+    S3_ARTIFACT_NAME: "arm64/kernel-files"
+    BM_KERNEL: https://${PIPELINE_ARTIFACTS_BASE}/arm64/Image.gz
+    BM_CMDLINE: "ip=dhcp console=ttyMSM0,115200n8 $BM_KERNEL_EXTRA_ARGS root=/dev/nfs rw nfsrootdebug nfsroot=,tcp,nfsvers=4.2 init=/init $BM_KERNELARGS"
+  needs:
+    - debian/arm64_test
+    - job: testing:arm64
+      artifacts: false
+    - igt:arm64
+  tags:
+    - $RUNNER_TAG
+
+msm:sc7180:
+  extends:
+    - .lava-igt:arm64
+  stage: msm
+  parallel: 2
+  variables:
+    DRIVER_NAME: msm
+    DEVICE_TYPE: sc7180-trogdor-lazor-limozeen
+    DTB: sc7180-trogdor-lazor-limozeen-nots-r5
+    BOOT_METHOD: depthcharge
+    KERNEL_IMAGE_TYPE: ""
+    GPU_VERSION: sc7180
+    RUNNER_TAG: mesa-ci-x86-64-lava-sc7180-trogdor-lazor-limozeen
+
+msm:apq8016:
+  extends:
+    - .baremetal-igt-arm64
+  stage: msm
+  variables:
+    DRIVER_NAME: msm
+    BM_DTB: https://${PIPELINE_ARTIFACTS_BASE}/arm64/apq8016-sbc.dtb
+    GPU_VERSION: apq8016
+    BM_CMDLINE: "ip=dhcp console=ttyMSM0,115200n8 $BM_KERNEL_EXTRA_ARGS root=/dev/nfs rw nfsrootdebug nfsroot=,tcp,nfsvers=4.2 init=/init $BM_KERNELARGS"
+    RUNNER_TAG: google-freedreno-db410c
+  script:
+    - ./install/bare-metal/fastboot.sh
+  rules:
+    # TODO: current issue: it is not fiding the NFS root. Fix and remove this rule.
+    - when: never
+
+msm:apq8096:
+  extends:
+    - .baremetal-igt-arm64
+  stage: msm
+  variables:
+    DRIVER_NAME: msm
+    BM_KERNEL_EXTRA_ARGS: maxcpus=2
+    BM_DTB: https://${PIPELINE_ARTIFACTS_BASE}/arm64/apq8096-db820c.dtb
+    GPU_VERSION: apq8096
+    RUNNER_TAG: google-freedreno-db820c
+  script:
+    - ./install/bare-metal/fastboot.sh
+
+msm:sdm845:
+  extends:
+    - .baremetal-igt-arm64
+  stage: msm
+  parallel: 6
+  variables:
+    DRIVER_NAME: msm
+    BM_KERNEL: https://${PIPELINE_ARTIFACTS_BASE}/arm64/cheza-kernel
+    GPU_VERSION: sdm845
+    RUNNER_TAG: google-freedreno-cheza
+  script:
+    - ./install/bare-metal/cros-servo.sh
+
+rockchip:rk3288:
+  extends:
+    - .lava-igt:arm32
+  stage: rockchip
+  variables:
+    DRIVER_NAME: rockchip
+    DEVICE_TYPE: rk3288-veyron-jaq
+    DTB: ${DEVICE_TYPE}
+    BOOT_METHOD: depthcharge
+    KERNEL_IMAGE_TYPE: "zimage"
+    GPU_VERSION: rk3288
+    RUNNER_TAG: mesa-ci-x86-64-lava-rk3288-veyron-jaq
+
+rockchip:rk3399:
+  extends:
+    - .lava-igt:arm64
+  stage: rockchip
+  parallel: 3
+  variables:
+    DRIVER_NAME: rockchip
+    DEVICE_TYPE: rk3399-gru-kevin
+    DTB: ${DEVICE_TYPE}
+    BOOT_METHOD: depthcharge
+    KERNEL_IMAGE_TYPE: ""
+    GPU_VERSION: rk3399
+    RUNNER_TAG: mesa-ci-x86-64-lava-rk3399-gru-kevin
+
+.i915:
+  extends:
+    - .lava-igt:x86_64
+  stage: i915
+  variables:
+    DRIVER_NAME: i915
+    DTB: ""
+    BOOT_METHOD: depthcharge
+    KERNEL_IMAGE_TYPE: ""
+
+i915:apl:
+  extends:
+    - .i915
+  parallel: 12
+  variables:
+    DEVICE_TYPE: asus-C523NA-A20057-coral
+    GPU_VERSION: apl
+    RUNNER_TAG: mesa-ci-x86-64-lava-asus-C523NA-A20057-coral
+
+i915:glk:
+  extends:
+    - .i915
+  parallel: 5
+  variables:
+    DEVICE_TYPE: hp-x360-12b-ca0010nr-n4020-octopus
+    GPU_VERSION: glk
+    RUNNER_TAG: mesa-ci-x86-64-lava-hp-x360-12b-ca0010nr-n4020-octopus
+
+i915:amly:
+  extends:
+    - .i915
+  parallel: 8
+  variables:
+    DEVICE_TYPE: asus-C433TA-AJ0005-rammus
+    GPU_VERSION: amly
+    RUNNER_TAG: mesa-ci-x86-64-lava-asus-C433TA-AJ0005-rammus
+
+i915:kbl:
+  extends:
+    - .i915
+  parallel: 5
+  variables:
+    DEVICE_TYPE: hp-x360-14-G1-sona
+    GPU_VERSION: kbl
+    RUNNER_TAG: mesa-ci-x86-64-lava-hp-x360-14-G1-sona
+
+i915:whl:
+  extends:
+    - .i915
+  parallel: 8
+  variables:
+    DEVICE_TYPE: dell-latitude-5400-8665U-sarien
+    GPU_VERSION: whl
+    RUNNER_TAG: mesa-ci-x86-64-lava-dell-latitude-5400-8665U-sarien
+
+i915:cml:
+  extends:
+    - .i915
+  parallel: 6
+  variables:
+    DEVICE_TYPE: asus-C436FA-Flip-hatch
+    GPU_VERSION: cml
+    RUNNER_TAG: mesa-ci-x86-64-lava-asus-C436FA-flip-hatch
+
+i915:tgl:
+  extends:
+    - .i915
+  parallel: 6
+  variables:
+    DEVICE_TYPE: asus-cx9400-volteer
+    GPU_VERSION: tgl
+    RUNNER_TAG: mesa-ci-x86-64-lava-asus-cx9400-volteer
+
+.amdgpu:
+  extends:
+    - .lava-igt:x86_64
+  stage: amdgpu
+  variables:
+    DRIVER_NAME: amdgpu
+    DTB: ""
+    BOOT_METHOD: depthcharge
+    KERNEL_IMAGE_TYPE: ""
+
+amdgpu:stoney:
+  extends:
+    - .amdgpu
+  variables:
+    DEVICE_TYPE: hp-11A-G6-EE-grunt
+    GPU_VERSION: stoney
+    RUNNER_TAG: mesa-ci-x86-64-lava-hp-11A-G6-EE-grunt
+
+.mediatek:
+  extends:
+    - .lava-igt:arm64
+  stage: mediatek
+  variables:
+    DRIVER_NAME: mediatek
+    DTB: ${DEVICE_TYPE}
+    BOOT_METHOD: depthcharge
+    KERNEL_IMAGE_TYPE: ""
+
+mediatek:mt8173:
+  extends:
+    - .mediatek
+  variables:
+    DEVICE_TYPE: mt8173-elm-hana
+    GPU_VERSION: mt8173
+    RUNNER_TAG: mesa-ci-x86-64-lava-mt8173-elm-hana
+  rules:
+    # TODO: current issue: device is hanging. Fix and remove this rule.
+    - when: never
+
+mediatek:mt8183:
+  extends:
+    - .mediatek
+  variables:
+    DEVICE_TYPE: mt8183-kukui-jacuzzi-juniper-sku16
+    GPU_VERSION: mt8183
+    RUNNER_TAG: mesa-ci-x86-64-lava-mt8183-kukui-jacuzzi-juniper-sku16
+
+# drm-mtk doesn't even probe yet in mainline for mt8192
+.mediatek:mt8192:
+  extends:
+    - .mediatek
+  variables:
+    DEVICE_TYPE: mt8192-asurada-spherion-r0
+    GPU_VERSION: mt8192
+    RUNNER_TAG: mesa-ci-x86-64-lava-mt8192-asurada-spherion-r0
+
+.meson:
+  extends:
+    - .lava-igt:arm64
+  stage: meson
+  variables:
+    DRIVER_NAME: meson
+    DTB: ${DEVICE_TYPE}
+    BOOT_METHOD: u-boot
+    KERNEL_IMAGE_TYPE: "image"
+
+meson:g12b:
+  extends:
+    - .meson
+  variables:
+    DEVICE_TYPE: meson-g12b-a311d-khadas-vim3
+    GPU_VERSION: g12b
+    RUNNER_TAG: mesa-ci-x86-64-lava-meson-g12b-a311d-khadas-vim3
+
+virtio_gpu:none:
+  stage: virtio-gpu
+  variables:
+    CROSVM_GALLIUM_DRIVER: llvmpipe
+    DRIVER_NAME: virtio_gpu
+    GPU_VERSION: none
+  extends:
+    - .test-gl
+  tags:
+    - kvm
+  script:
+    - ln -sf $CI_PROJECT_DIR/install /install
+    - mv install/bzImage /lava-files/bzImage
+    - install/crosvm-runner.sh install/igt_runner.sh
+  needs:
+    - debian/x86_64_test-gl
+    - testing:x86_64
+    - igt:x86_64
+  rules:
+    # TODO: current issue: malloc(): corrupted top size. Fix and remove this rule.
+    - when: never
\ No newline at end of file
diff --git a/drivers/gpu/drm/ci/testlist.txt b/drivers/gpu/drm/ci/testlist.txt
new file mode 100644
index 000000000000..f82cd90372f4
--- /dev/null
+++ b/drivers/gpu/drm/ci/testlist.txt
@@ -0,0 +1,2912 @@
+core_auth@getclient-simple
+core_auth@getclient-master-drop
+core_auth@basic-auth
+core_auth@many-magics
+core_getclient
+core_getstats
+core_getversion
+core_setmaster_vs_auth
+drm_read@invalid-buffer
+drm_read@fault-buffer
+drm_read@empty-block
+drm_read@empty-nonblock
+drm_read@short-buffer-block
+drm_read@short-buffer-nonblock
+drm_read@short-buffer-wakeup
+gem_eio@throttle
+gem_eio@create
+gem_eio@create-ext
+gem_eio@context-create
+gem_eio@execbuf
+gem_eio@banned
+gem_eio@suspend
+gem_eio@hibernate
+gem_eio@in-flight-external
+gem_eio@in-flight-suspend
+gem_eio@reset-stress
+gem_eio@unwedge-stress
+gem_eio@wait-immediate
+gem_eio@wait-wedge-immediate
+gem_eio@in-flight-immediate
+gem_eio@in-flight-contexts-immediate
+gem_eio@in-flight-internal-immediate
+gem_eio@wait-1us
+gem_eio@wait-wedge-1us
+gem_eio@in-flight-1us
+gem_eio@in-flight-contexts-1us
+gem_eio@in-flight-internal-1us
+gem_eio@wait-10ms
+gem_eio@wait-wedge-10ms
+gem_eio@in-flight-10ms
+gem_eio@in-flight-contexts-10ms
+gem_eio@in-flight-internal-10ms
+gem_eio@kms
+kms_3d
+kms_addfb_basic@unused-handle
+kms_addfb_basic@unused-pitches
+kms_addfb_basic@unused-offsets
+kms_addfb_basic@unused-modifier
+kms_addfb_basic@clobberred-modifier
+kms_addfb_basic@invalid-smem-bo-on-discrete
+kms_addfb_basic@legacy-format
+kms_addfb_basic@no-handle
+kms_addfb_basic@basic
+kms_addfb_basic@bad-pitch-0
+kms_addfb_basic@bad-pitch-32
+kms_addfb_basic@bad-pitch-63
+kms_addfb_basic@bad-pitch-128
+kms_addfb_basic@bad-pitch-256
+kms_addfb_basic@bad-pitch-1024
+kms_addfb_basic@bad-pitch-999
+kms_addfb_basic@bad-pitch-65536
+kms_addfb_basic@invalid-get-prop-any
+kms_addfb_basic@invalid-get-prop
+kms_addfb_basic@invalid-set-prop-any
+kms_addfb_basic@invalid-set-prop
+kms_addfb_basic@master-rmfb
+kms_addfb_basic@addfb25-modifier-no-flag
+kms_addfb_basic@addfb25-bad-modifier
+kms_addfb_basic@addfb25-x-tiled-mismatch-legacy
+kms_addfb_basic@addfb25-x-tiled-legacy
+kms_addfb_basic@addfb25-framebuffer-vs-set-tiling
+kms_addfb_basic@basic-x-tiled-legacy
+kms_addfb_basic@framebuffer-vs-set-tiling
+kms_addfb_basic@tile-pitch-mismatch
+kms_addfb_basic@basic-y-tiled-legacy
+kms_addfb_basic@size-max
+kms_addfb_basic@too-wide
+kms_addfb_basic@too-high
+kms_addfb_basic@bo-too-small
+kms_addfb_basic@small-bo
+kms_addfb_basic@bo-too-small-due-to-tiling
+kms_addfb_basic@addfb25-y-tiled-legacy
+kms_addfb_basic@addfb25-yf-tiled-legacy
+kms_addfb_basic@addfb25-y-tiled-small-legacy
+kms_addfb_basic@addfb25-4-tiled
+kms_async_flips@async-flip-with-page-flip-events
+kms_async_flips@alternate-sync-async-flip
+kms_async_flips@test-time-stamp
+kms_async_flips@test-cursor
+kms_async_flips@invalid-async-flip
+kms_async_flips@crc
+kms_atomic@plane-overlay-legacy
+kms_atomic@plane-primary-legacy
+kms_atomic@plane-primary-overlay-mutable-zpos
+kms_atomic@plane-immutable-zpos
+kms_atomic@test-only
+kms_atomic@plane-cursor-legacy
+kms_atomic@plane-invalid-params
+kms_atomic@plane-invalid-params-fence
+kms_atomic@crtc-invalid-params
+kms_atomic@crtc-invalid-params-fence
+kms_atomic@atomic-invalid-params
+kms_atomic@atomic_plane_damage
+kms_atomic_interruptible@legacy-setmode
+kms_atomic_interruptible@atomic-setmode
+kms_atomic_interruptible@legacy-dpms
+kms_atomic_interruptible@legacy-pageflip
+kms_atomic_interruptible@legacy-cursor
+kms_atomic_interruptible@universal-setplane-primary
+kms_atomic_interruptible@universal-setplane-cursor
+kms_atomic_transition@plane-primary-toggle-with-vblank-wait
+kms_atomic_transition@plane-all-transition
+kms_atomic_transition@plane-all-transition-fencing
+kms_atomic_transition@plane-all-transition-nonblocking
+kms_atomic_transition@plane-all-transition-nonblocking-fencing
+kms_atomic_transition@plane-use-after-nonblocking-unbind
+kms_atomic_transition@plane-use-after-nonblocking-unbind-fencing
+kms_atomic_transition@plane-all-modeset-transition
+kms_atomic_transition@plane-all-modeset-transition-fencing
+kms_atomic_transition@plane-all-modeset-transition-internal-panels
+kms_atomic_transition@plane-all-modeset-transition-fencing-internal-panels
+kms_atomic_transition@plane-toggle-modeset-transition
+kms_atomic_transition@modeset-transition
+kms_atomic_transition@modeset-transition-fencing
+kms_atomic_transition@modeset-transition-nonblocking
+kms_atomic_transition@modeset-transition-nonblocking-fencing
+kms_big_fb@x-tiled-addfb-size-overflow
+kms_big_fb@y-tiled-addfb-size-overflow
+kms_big_fb@yf-tiled-addfb-size-overflow
+kms_big_fb@4-tiled-addfb-size-overflow
+kms_big_fb@x-tiled-addfb-size-offset-overflow
+kms_big_fb@y-tiled-addfb-size-offset-overflow
+kms_big_fb@yf-tiled-addfb-size-offset-overflow
+kms_big_fb@4-tiled-addfb-size-offset-overflow
+kms_big_fb@linear-addfb
+kms_big_fb@x-tiled-addfb
+kms_big_fb@y-tiled-addfb
+kms_big_fb@yf-tiled-addfb
+kms_big_fb@4-tiled-addfb
+kms_big_fb@linear-8bpp-rotate-0
+kms_big_fb@linear-8bpp-rotate-90
+kms_big_fb@linear-8bpp-rotate-180
+kms_big_fb@linear-8bpp-rotate-270
+kms_big_fb@linear-16bpp-rotate-0
+kms_big_fb@linear-16bpp-rotate-90
+kms_big_fb@linear-16bpp-rotate-180
+kms_big_fb@linear-16bpp-rotate-270
+kms_big_fb@linear-32bpp-rotate-0
+kms_big_fb@linear-32bpp-rotate-90
+kms_big_fb@linear-32bpp-rotate-180
+kms_big_fb@linear-32bpp-rotate-270
+kms_big_fb@linear-64bpp-rotate-0
+kms_big_fb@linear-64bpp-rotate-90
+kms_big_fb@linear-64bpp-rotate-180
+kms_big_fb@linear-64bpp-rotate-270
+kms_big_fb@x-tiled-8bpp-rotate-0
+kms_big_fb@x-tiled-8bpp-rotate-90
+kms_big_fb@x-tiled-8bpp-rotate-180
+kms_big_fb@x-tiled-8bpp-rotate-270
+kms_big_fb@x-tiled-16bpp-rotate-0
+kms_big_fb@x-tiled-16bpp-rotate-90
+kms_big_fb@x-tiled-16bpp-rotate-180
+kms_big_fb@x-tiled-16bpp-rotate-270
+kms_big_fb@x-tiled-32bpp-rotate-0
+kms_big_fb@x-tiled-32bpp-rotate-90
+kms_big_fb@x-tiled-32bpp-rotate-180
+kms_big_fb@x-tiled-32bpp-rotate-270
+kms_big_fb@x-tiled-64bpp-rotate-0
+kms_big_fb@x-tiled-64bpp-rotate-90
+kms_big_fb@x-tiled-64bpp-rotate-180
+kms_big_fb@x-tiled-64bpp-rotate-270
+kms_big_fb@y-tiled-8bpp-rotate-0
+kms_big_fb@y-tiled-8bpp-rotate-90
+kms_big_fb@y-tiled-8bpp-rotate-180
+kms_big_fb@y-tiled-8bpp-rotate-270
+kms_big_fb@y-tiled-16bpp-rotate-0
+kms_big_fb@y-tiled-16bpp-rotate-90
+kms_big_fb@y-tiled-16bpp-rotate-180
+kms_big_fb@y-tiled-16bpp-rotate-270
+kms_big_fb@y-tiled-32bpp-rotate-0
+kms_big_fb@y-tiled-32bpp-rotate-90
+kms_big_fb@y-tiled-32bpp-rotate-180
+kms_big_fb@y-tiled-32bpp-rotate-270
+kms_big_fb@y-tiled-64bpp-rotate-0
+kms_big_fb@y-tiled-64bpp-rotate-90
+kms_big_fb@y-tiled-64bpp-rotate-180
+kms_big_fb@y-tiled-64bpp-rotate-270
+kms_big_fb@yf-tiled-8bpp-rotate-0
+kms_big_fb@yf-tiled-8bpp-rotate-90
+kms_big_fb@yf-tiled-8bpp-rotate-180
+kms_big_fb@yf-tiled-8bpp-rotate-270
+kms_big_fb@yf-tiled-16bpp-rotate-0
+kms_big_fb@yf-tiled-16bpp-rotate-90
+kms_big_fb@yf-tiled-16bpp-rotate-180
+kms_big_fb@yf-tiled-16bpp-rotate-270
+kms_big_fb@yf-tiled-32bpp-rotate-0
+kms_big_fb@yf-tiled-32bpp-rotate-90
+kms_big_fb@yf-tiled-32bpp-rotate-180
+kms_big_fb@yf-tiled-32bpp-rotate-270
+kms_big_fb@yf-tiled-64bpp-rotate-0
+kms_big_fb@yf-tiled-64bpp-rotate-90
+kms_big_fb@yf-tiled-64bpp-rotate-180
+kms_big_fb@yf-tiled-64bpp-rotate-270
+kms_big_fb@4-tiled-8bpp-rotate-0
+kms_big_fb@4-tiled-8bpp-rotate-90
+kms_big_fb@4-tiled-8bpp-rotate-180
+kms_big_fb@4-tiled-8bpp-rotate-270
+kms_big_fb@4-tiled-16bpp-rotate-0
+kms_big_fb@4-tiled-16bpp-rotate-90
+kms_big_fb@4-tiled-16bpp-rotate-180
+kms_big_fb@4-tiled-16bpp-rotate-270
+kms_big_fb@4-tiled-32bpp-rotate-0
+kms_big_fb@4-tiled-32bpp-rotate-90
+kms_big_fb@4-tiled-32bpp-rotate-180
+kms_big_fb@4-tiled-32bpp-rotate-270
+kms_big_fb@4-tiled-64bpp-rotate-0
+kms_big_fb@4-tiled-64bpp-rotate-90
+kms_big_fb@4-tiled-64bpp-rotate-180
+kms_big_fb@4-tiled-64bpp-rotate-270
+kms_big_fb@linear-max-hw-stride-32bpp-rotate-0
+kms_big_fb@linear-max-hw-stride-32bpp-rotate-180
+kms_big_fb@linear-max-hw-stride-64bpp-rotate-0
+kms_big_fb@linear-max-hw-stride-64bpp-rotate-180
+kms_big_fb@x-tiled-max-hw-stride-32bpp-rotate-0
+kms_big_fb@x-tiled-max-hw-stride-32bpp-rotate-0-async-flip
+kms_big_fb@x-tiled-max-hw-stride-32bpp-rotate-180
+kms_big_fb@x-tiled-max-hw-stride-32bpp-rotate-180-async-flip
+kms_big_fb@x-tiled-max-hw-stride-64bpp-rotate-0
+kms_big_fb@x-tiled-max-hw-stride-64bpp-rotate-0-async-flip
+kms_big_fb@x-tiled-max-hw-stride-64bpp-rotate-180
+kms_big_fb@x-tiled-max-hw-stride-64bpp-rotate-180-async-flip
+kms_big_fb@x-tiled-max-hw-stride-32bpp-rotate-0-hflip
+kms_big_fb@x-tiled-max-hw-stride-32bpp-rotate-0-hflip-async-flip
+kms_big_fb@x-tiled-max-hw-stride-32bpp-rotate-180-hflip
+kms_big_fb@x-tiled-max-hw-stride-32bpp-rotate-180-hflip-async-flip
+kms_big_fb@x-tiled-max-hw-stride-64bpp-rotate-0-hflip
+kms_big_fb@x-tiled-max-hw-stride-64bpp-rotate-0-hflip-async-flip
+kms_big_fb@x-tiled-max-hw-stride-64bpp-rotate-180-hflip
+kms_big_fb@x-tiled-max-hw-stride-64bpp-rotate-180-hflip-async-flip
+kms_big_fb@y-tiled-max-hw-stride-32bpp-rotate-0
+kms_big_fb@y-tiled-max-hw-stride-32bpp-rotate-0-async-flip
+kms_big_fb@y-tiled-max-hw-stride-32bpp-rotate-180
+kms_big_fb@y-tiled-max-hw-stride-32bpp-rotate-180-async-flip
+kms_big_fb@y-tiled-max-hw-stride-64bpp-rotate-0
+kms_big_fb@y-tiled-max-hw-stride-64bpp-rotate-0-async-flip
+kms_big_fb@y-tiled-max-hw-stride-64bpp-rotate-180
+kms_big_fb@y-tiled-max-hw-stride-64bpp-rotate-180-async-flip
+kms_big_fb@y-tiled-max-hw-stride-32bpp-rotate-0-hflip
+kms_big_fb@y-tiled-max-hw-stride-32bpp-rotate-0-hflip-async-flip
+kms_big_fb@y-tiled-max-hw-stride-32bpp-rotate-180-hflip
+kms_big_fb@y-tiled-max-hw-stride-32bpp-rotate-180-hflip-async-flip
+kms_big_fb@y-tiled-max-hw-stride-64bpp-rotate-0-hflip
+kms_big_fb@y-tiled-max-hw-stride-64bpp-rotate-0-hflip-async-flip
+kms_big_fb@y-tiled-max-hw-stride-64bpp-rotate-180-hflip
+kms_big_fb@y-tiled-max-hw-stride-64bpp-rotate-180-hflip-async-flip
+kms_big_fb@yf-tiled-max-hw-stride-32bpp-rotate-0
+kms_big_fb@yf-tiled-max-hw-stride-32bpp-rotate-0-async-flip
+kms_big_fb@yf-tiled-max-hw-stride-32bpp-rotate-180
+kms_big_fb@yf-tiled-max-hw-stride-32bpp-rotate-180-async-flip
+kms_big_fb@yf-tiled-max-hw-stride-64bpp-rotate-0
+kms_big_fb@yf-tiled-max-hw-stride-64bpp-rotate-0-async-flip
+kms_big_fb@yf-tiled-max-hw-stride-64bpp-rotate-180
+kms_big_fb@yf-tiled-max-hw-stride-64bpp-rotate-180-async-flip
+kms_big_fb@yf-tiled-max-hw-stride-32bpp-rotate-0-hflip
+kms_big_fb@yf-tiled-max-hw-stride-32bpp-rotate-0-hflip-async-flip
+kms_big_fb@yf-tiled-max-hw-stride-32bpp-rotate-180-hflip
+kms_big_fb@yf-tiled-max-hw-stride-32bpp-rotate-180-hflip-async-flip
+kms_big_fb@yf-tiled-max-hw-stride-64bpp-rotate-0-hflip
+kms_big_fb@yf-tiled-max-hw-stride-64bpp-rotate-0-hflip-async-flip
+kms_big_fb@yf-tiled-max-hw-stride-64bpp-rotate-180-hflip
+kms_big_fb@yf-tiled-max-hw-stride-64bpp-rotate-180-hflip-async-flip
+kms_big_fb@4-tiled-max-hw-stride-32bpp-rotate-0
+kms_big_fb@4-tiled-max-hw-stride-32bpp-rotate-0-async-flip
+kms_big_fb@4-tiled-max-hw-stride-32bpp-rotate-180
+kms_big_fb@4-tiled-max-hw-stride-32bpp-rotate-180-async-flip
+kms_big_fb@4-tiled-max-hw-stride-64bpp-rotate-0
+kms_big_fb@4-tiled-max-hw-stride-64bpp-rotate-0-async-flip
+kms_big_fb@4-tiled-max-hw-stride-64bpp-rotate-180
+kms_big_fb@4-tiled-max-hw-stride-64bpp-rotate-180-async-flip
+kms_big_fb@4-tiled-max-hw-stride-32bpp-rotate-0-hflip
+kms_big_fb@4-tiled-max-hw-stride-32bpp-rotate-0-hflip-async-flip
+kms_big_fb@4-tiled-max-hw-stride-32bpp-rotate-180-hflip
+kms_big_fb@4-tiled-max-hw-stride-32bpp-rotate-180-hflip-async-flip
+kms_big_fb@4-tiled-max-hw-stride-64bpp-rotate-0-hflip
+kms_big_fb@4-tiled-max-hw-stride-64bpp-rotate-0-hflip-async-flip
+kms_big_fb@4-tiled-max-hw-stride-64bpp-rotate-180-hflip
+kms_big_fb@4-tiled-max-hw-stride-64bpp-rotate-180-hflip-async-flip
+kms_big_joiner@basic
+kms_big_joiner@invalid-modeset
+kms_big_joiner@2x-modeset
+kms_busy@basic
+kms_busy@basic-hang
+kms_busy@extended-pageflip-modeset-hang-oldfb
+kms_busy@extended-pageflip-hang-oldfb
+kms_busy@extended-pageflip-hang-newfb
+kms_busy@extended-modeset-hang-oldfb
+kms_busy@extended-modeset-hang-newfb
+kms_busy@extended-modeset-hang-oldfb-with-reset
+kms_busy@extended-modeset-hang-newfb-with-reset
+kms_bw@linear-tiling-1-displays-1920x1080p
+kms_bw@linear-tiling-1-displays-2560x1440p
+kms_bw@linear-tiling-1-displays-3840x2160p
+kms_bw@linear-tiling-2-displays-1920x1080p
+kms_bw@linear-tiling-2-displays-2560x1440p
+kms_bw@linear-tiling-2-displays-3840x2160p
+kms_bw@linear-tiling-3-displays-1920x1080p
+kms_bw@linear-tiling-3-displays-2560x1440p
+kms_bw@linear-tiling-3-displays-3840x2160p
+kms_bw@linear-tiling-4-displays-1920x1080p
+kms_bw@linear-tiling-4-displays-2560x1440p
+kms_bw@linear-tiling-4-displays-3840x2160p
+kms_bw@linear-tiling-5-displays-1920x1080p
+kms_bw@linear-tiling-5-displays-2560x1440p
+kms_bw@linear-tiling-5-displays-3840x2160p
+kms_bw@linear-tiling-6-displays-1920x1080p
+kms_bw@linear-tiling-6-displays-2560x1440p
+kms_bw@linear-tiling-6-displays-3840x2160p
+kms_bw@linear-tiling-7-displays-1920x1080p
+kms_bw@linear-tiling-7-displays-2560x1440p
+kms_bw@linear-tiling-7-displays-3840x2160p
+kms_bw@linear-tiling-8-displays-1920x1080p
+kms_bw@linear-tiling-8-displays-2560x1440p
+kms_bw@linear-tiling-8-displays-3840x2160p
+kms_ccs@pipe-A-bad-pixel-format-y_tiled_ccs
+kms_ccs@pipe-A-bad-pixel-format-yf_tiled_ccs
+kms_ccs@pipe-A-bad-pixel-format-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-A-bad-pixel-format-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-A-bad-pixel-format-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-A-bad-pixel-format-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-A-bad-pixel-format-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-A-bad-pixel-format-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-A-bad-pixel-format-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-A-bad-pixel-format-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-A-bad-pixel-format-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-A-bad-rotation-90-y_tiled_ccs
+kms_ccs@pipe-A-bad-rotation-90-yf_tiled_ccs
+kms_ccs@pipe-A-bad-rotation-90-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-A-bad-rotation-90-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-A-bad-rotation-90-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-A-bad-rotation-90-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-A-bad-rotation-90-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-A-bad-rotation-90-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-A-bad-rotation-90-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-A-bad-rotation-90-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-A-bad-rotation-90-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-A-crc-primary-basic-y_tiled_ccs
+kms_ccs@pipe-A-crc-primary-basic-yf_tiled_ccs
+kms_ccs@pipe-A-crc-primary-basic-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-A-crc-primary-basic-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-A-crc-primary-basic-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-A-crc-primary-basic-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-A-crc-primary-basic-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-A-crc-primary-basic-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-A-crc-primary-basic-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-A-crc-primary-basic-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-A-crc-primary-basic-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-A-crc-primary-rotation-180-y_tiled_ccs
+kms_ccs@pipe-A-crc-primary-rotation-180-yf_tiled_ccs
+kms_ccs@pipe-A-crc-primary-rotation-180-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-A-crc-primary-rotation-180-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-A-crc-primary-rotation-180-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-A-crc-primary-rotation-180-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-A-crc-primary-rotation-180-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-A-crc-primary-rotation-180-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-A-crc-primary-rotation-180-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-A-crc-primary-rotation-180-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-A-crc-primary-rotation-180-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-A-random-ccs-data-y_tiled_ccs
+kms_ccs@pipe-A-random-ccs-data-yf_tiled_ccs
+kms_ccs@pipe-A-random-ccs-data-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-A-random-ccs-data-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-A-random-ccs-data-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-A-random-ccs-data-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-A-random-ccs-data-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-A-random-ccs-data-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-A-random-ccs-data-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-A-random-ccs-data-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-A-random-ccs-data-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-A-missing-ccs-buffer-y_tiled_ccs
+kms_ccs@pipe-A-missing-ccs-buffer-yf_tiled_ccs
+kms_ccs@pipe-A-missing-ccs-buffer-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-A-missing-ccs-buffer-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-A-missing-ccs-buffer-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-A-missing-ccs-buffer-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-A-missing-ccs-buffer-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-A-missing-ccs-buffer-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-A-ccs-on-another-bo-y_tiled_ccs
+kms_ccs@pipe-A-ccs-on-another-bo-yf_tiled_ccs
+kms_ccs@pipe-A-ccs-on-another-bo-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-A-ccs-on-another-bo-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-A-ccs-on-another-bo-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-A-ccs-on-another-bo-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-A-ccs-on-another-bo-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-A-ccs-on-another-bo-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-A-bad-aux-stride-y_tiled_ccs
+kms_ccs@pipe-A-bad-aux-stride-yf_tiled_ccs
+kms_ccs@pipe-A-bad-aux-stride-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-A-bad-aux-stride-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-A-bad-aux-stride-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-A-bad-aux-stride-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-A-bad-aux-stride-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-A-bad-aux-stride-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-A-crc-sprite-planes-basic-y_tiled_ccs
+kms_ccs@pipe-A-crc-sprite-planes-basic-yf_tiled_ccs
+kms_ccs@pipe-A-crc-sprite-planes-basic-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-A-crc-sprite-planes-basic-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-A-crc-sprite-planes-basic-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-A-crc-sprite-planes-basic-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-A-crc-sprite-planes-basic-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-A-crc-sprite-planes-basic-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-A-crc-sprite-planes-basic-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-A-crc-sprite-planes-basic-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-A-crc-sprite-planes-basic-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-B-bad-pixel-format-y_tiled_ccs
+kms_ccs@pipe-B-bad-pixel-format-yf_tiled_ccs
+kms_ccs@pipe-B-bad-pixel-format-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-B-bad-pixel-format-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-B-bad-pixel-format-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-B-bad-pixel-format-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-B-bad-pixel-format-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-B-bad-pixel-format-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-B-bad-pixel-format-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-B-bad-pixel-format-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-B-bad-pixel-format-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-B-bad-rotation-90-y_tiled_ccs
+kms_ccs@pipe-B-bad-rotation-90-yf_tiled_ccs
+kms_ccs@pipe-B-bad-rotation-90-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-B-bad-rotation-90-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-B-bad-rotation-90-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-B-bad-rotation-90-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-B-bad-rotation-90-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-B-bad-rotation-90-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-B-bad-rotation-90-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-B-bad-rotation-90-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-B-bad-rotation-90-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-B-crc-primary-basic-y_tiled_ccs
+kms_ccs@pipe-B-crc-primary-basic-yf_tiled_ccs
+kms_ccs@pipe-B-crc-primary-basic-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-B-crc-primary-basic-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-B-crc-primary-basic-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-B-crc-primary-basic-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-B-crc-primary-basic-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-B-crc-primary-basic-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-B-crc-primary-basic-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-B-crc-primary-basic-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-B-crc-primary-basic-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-B-crc-primary-rotation-180-y_tiled_ccs
+kms_ccs@pipe-B-crc-primary-rotation-180-yf_tiled_ccs
+kms_ccs@pipe-B-crc-primary-rotation-180-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-B-crc-primary-rotation-180-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-B-crc-primary-rotation-180-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-B-crc-primary-rotation-180-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-B-crc-primary-rotation-180-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-B-crc-primary-rotation-180-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-B-crc-primary-rotation-180-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-B-crc-primary-rotation-180-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-B-crc-primary-rotation-180-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-B-random-ccs-data-y_tiled_ccs
+kms_ccs@pipe-B-random-ccs-data-yf_tiled_ccs
+kms_ccs@pipe-B-random-ccs-data-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-B-random-ccs-data-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-B-random-ccs-data-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-B-random-ccs-data-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-B-random-ccs-data-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-B-random-ccs-data-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-B-random-ccs-data-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-B-random-ccs-data-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-B-random-ccs-data-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-B-missing-ccs-buffer-y_tiled_ccs
+kms_ccs@pipe-B-missing-ccs-buffer-yf_tiled_ccs
+kms_ccs@pipe-B-missing-ccs-buffer-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-B-missing-ccs-buffer-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-B-missing-ccs-buffer-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-B-missing-ccs-buffer-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-B-missing-ccs-buffer-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-B-missing-ccs-buffer-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-B-ccs-on-another-bo-y_tiled_ccs
+kms_ccs@pipe-B-ccs-on-another-bo-yf_tiled_ccs
+kms_ccs@pipe-B-ccs-on-another-bo-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-B-ccs-on-another-bo-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-B-ccs-on-another-bo-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-B-ccs-on-another-bo-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-B-ccs-on-another-bo-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-B-ccs-on-another-bo-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-B-bad-aux-stride-y_tiled_ccs
+kms_ccs@pipe-B-bad-aux-stride-yf_tiled_ccs
+kms_ccs@pipe-B-bad-aux-stride-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-B-bad-aux-stride-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-B-bad-aux-stride-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-B-bad-aux-stride-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-B-bad-aux-stride-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-B-bad-aux-stride-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-B-crc-sprite-planes-basic-y_tiled_ccs
+kms_ccs@pipe-B-crc-sprite-planes-basic-yf_tiled_ccs
+kms_ccs@pipe-B-crc-sprite-planes-basic-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-B-crc-sprite-planes-basic-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-B-crc-sprite-planes-basic-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-B-crc-sprite-planes-basic-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-B-crc-sprite-planes-basic-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-B-crc-sprite-planes-basic-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-B-crc-sprite-planes-basic-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-B-crc-sprite-planes-basic-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-B-crc-sprite-planes-basic-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-C-bad-pixel-format-y_tiled_ccs
+kms_ccs@pipe-C-bad-pixel-format-yf_tiled_ccs
+kms_ccs@pipe-C-bad-pixel-format-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-C-bad-pixel-format-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-C-bad-pixel-format-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-C-bad-pixel-format-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-C-bad-pixel-format-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-C-bad-pixel-format-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-C-bad-pixel-format-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-C-bad-pixel-format-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-C-bad-pixel-format-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-C-bad-rotation-90-y_tiled_ccs
+kms_ccs@pipe-C-bad-rotation-90-yf_tiled_ccs
+kms_ccs@pipe-C-bad-rotation-90-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-C-bad-rotation-90-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-C-bad-rotation-90-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-C-bad-rotation-90-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-C-bad-rotation-90-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-C-bad-rotation-90-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-C-bad-rotation-90-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-C-bad-rotation-90-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-C-bad-rotation-90-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-C-crc-primary-basic-y_tiled_ccs
+kms_ccs@pipe-C-crc-primary-basic-yf_tiled_ccs
+kms_ccs@pipe-C-crc-primary-basic-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-C-crc-primary-basic-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-C-crc-primary-basic-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-C-crc-primary-basic-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-C-crc-primary-basic-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-C-crc-primary-basic-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-C-crc-primary-basic-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-C-crc-primary-basic-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-C-crc-primary-basic-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-C-crc-primary-rotation-180-y_tiled_ccs
+kms_ccs@pipe-C-crc-primary-rotation-180-yf_tiled_ccs
+kms_ccs@pipe-C-crc-primary-rotation-180-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-C-crc-primary-rotation-180-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-C-crc-primary-rotation-180-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-C-crc-primary-rotation-180-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-C-crc-primary-rotation-180-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-C-crc-primary-rotation-180-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-C-crc-primary-rotation-180-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-C-crc-primary-rotation-180-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-C-crc-primary-rotation-180-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-C-random-ccs-data-y_tiled_ccs
+kms_ccs@pipe-C-random-ccs-data-yf_tiled_ccs
+kms_ccs@pipe-C-random-ccs-data-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-C-random-ccs-data-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-C-random-ccs-data-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-C-random-ccs-data-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-C-random-ccs-data-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-C-random-ccs-data-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-C-random-ccs-data-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-C-random-ccs-data-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-C-random-ccs-data-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-C-missing-ccs-buffer-y_tiled_ccs
+kms_ccs@pipe-C-missing-ccs-buffer-yf_tiled_ccs
+kms_ccs@pipe-C-missing-ccs-buffer-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-C-missing-ccs-buffer-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-C-missing-ccs-buffer-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-C-missing-ccs-buffer-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-C-missing-ccs-buffer-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-C-missing-ccs-buffer-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-C-ccs-on-another-bo-y_tiled_ccs
+kms_ccs@pipe-C-ccs-on-another-bo-yf_tiled_ccs
+kms_ccs@pipe-C-ccs-on-another-bo-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-C-ccs-on-another-bo-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-C-ccs-on-another-bo-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-C-ccs-on-another-bo-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-C-ccs-on-another-bo-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-C-ccs-on-another-bo-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-C-bad-aux-stride-y_tiled_ccs
+kms_ccs@pipe-C-bad-aux-stride-yf_tiled_ccs
+kms_ccs@pipe-C-bad-aux-stride-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-C-bad-aux-stride-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-C-bad-aux-stride-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-C-bad-aux-stride-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-C-bad-aux-stride-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-C-bad-aux-stride-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-C-crc-sprite-planes-basic-y_tiled_ccs
+kms_ccs@pipe-C-crc-sprite-planes-basic-yf_tiled_ccs
+kms_ccs@pipe-C-crc-sprite-planes-basic-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-C-crc-sprite-planes-basic-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-C-crc-sprite-planes-basic-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-C-crc-sprite-planes-basic-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-C-crc-sprite-planes-basic-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-C-crc-sprite-planes-basic-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-C-crc-sprite-planes-basic-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-C-crc-sprite-planes-basic-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-C-crc-sprite-planes-basic-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-D-bad-pixel-format-y_tiled_ccs
+kms_ccs@pipe-D-bad-pixel-format-yf_tiled_ccs
+kms_ccs@pipe-D-bad-pixel-format-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-D-bad-pixel-format-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-D-bad-pixel-format-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-D-bad-pixel-format-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-D-bad-pixel-format-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-D-bad-pixel-format-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-D-bad-pixel-format-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-D-bad-pixel-format-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-D-bad-pixel-format-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-D-bad-rotation-90-y_tiled_ccs
+kms_ccs@pipe-D-bad-rotation-90-yf_tiled_ccs
+kms_ccs@pipe-D-bad-rotation-90-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-D-bad-rotation-90-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-D-bad-rotation-90-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-D-bad-rotation-90-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-D-bad-rotation-90-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-D-bad-rotation-90-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-D-bad-rotation-90-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-D-bad-rotation-90-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-D-bad-rotation-90-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-D-crc-primary-basic-y_tiled_ccs
+kms_ccs@pipe-D-crc-primary-basic-yf_tiled_ccs
+kms_ccs@pipe-D-crc-primary-basic-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-D-crc-primary-basic-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-D-crc-primary-basic-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-D-crc-primary-basic-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-D-crc-primary-basic-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-D-crc-primary-basic-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-D-crc-primary-basic-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-D-crc-primary-basic-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-D-crc-primary-basic-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-D-crc-primary-rotation-180-y_tiled_ccs
+kms_ccs@pipe-D-crc-primary-rotation-180-yf_tiled_ccs
+kms_ccs@pipe-D-crc-primary-rotation-180-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-D-crc-primary-rotation-180-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-D-crc-primary-rotation-180-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-D-crc-primary-rotation-180-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-D-crc-primary-rotation-180-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-D-crc-primary-rotation-180-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-D-crc-primary-rotation-180-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-D-crc-primary-rotation-180-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-D-crc-primary-rotation-180-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-D-random-ccs-data-y_tiled_ccs
+kms_ccs@pipe-D-random-ccs-data-yf_tiled_ccs
+kms_ccs@pipe-D-random-ccs-data-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-D-random-ccs-data-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-D-random-ccs-data-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-D-random-ccs-data-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-D-random-ccs-data-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-D-random-ccs-data-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-D-random-ccs-data-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-D-random-ccs-data-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-D-random-ccs-data-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-D-missing-ccs-buffer-y_tiled_ccs
+kms_ccs@pipe-D-missing-ccs-buffer-yf_tiled_ccs
+kms_ccs@pipe-D-missing-ccs-buffer-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-D-missing-ccs-buffer-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-D-missing-ccs-buffer-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-D-missing-ccs-buffer-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-D-missing-ccs-buffer-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-D-missing-ccs-buffer-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-D-ccs-on-another-bo-y_tiled_ccs
+kms_ccs@pipe-D-ccs-on-another-bo-yf_tiled_ccs
+kms_ccs@pipe-D-ccs-on-another-bo-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-D-ccs-on-another-bo-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-D-ccs-on-another-bo-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-D-ccs-on-another-bo-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-D-ccs-on-another-bo-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-D-ccs-on-another-bo-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-D-bad-aux-stride-y_tiled_ccs
+kms_ccs@pipe-D-bad-aux-stride-yf_tiled_ccs
+kms_ccs@pipe-D-bad-aux-stride-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-D-bad-aux-stride-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-D-bad-aux-stride-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-D-bad-aux-stride-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-D-bad-aux-stride-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-D-bad-aux-stride-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-D-crc-sprite-planes-basic-y_tiled_ccs
+kms_ccs@pipe-D-crc-sprite-planes-basic-yf_tiled_ccs
+kms_ccs@pipe-D-crc-sprite-planes-basic-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-D-crc-sprite-planes-basic-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-D-crc-sprite-planes-basic-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-D-crc-sprite-planes-basic-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-D-crc-sprite-planes-basic-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-D-crc-sprite-planes-basic-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-D-crc-sprite-planes-basic-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-D-crc-sprite-planes-basic-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-D-crc-sprite-planes-basic-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-E-bad-pixel-format-y_tiled_ccs
+kms_ccs@pipe-E-bad-pixel-format-yf_tiled_ccs
+kms_ccs@pipe-E-bad-pixel-format-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-E-bad-pixel-format-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-E-bad-pixel-format-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-E-bad-pixel-format-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-E-bad-pixel-format-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-E-bad-pixel-format-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-E-bad-pixel-format-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-E-bad-pixel-format-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-E-bad-pixel-format-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-E-bad-rotation-90-y_tiled_ccs
+kms_ccs@pipe-E-bad-rotation-90-yf_tiled_ccs
+kms_ccs@pipe-E-bad-rotation-90-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-E-bad-rotation-90-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-E-bad-rotation-90-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-E-bad-rotation-90-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-E-bad-rotation-90-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-E-bad-rotation-90-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-E-bad-rotation-90-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-E-bad-rotation-90-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-E-bad-rotation-90-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-E-crc-primary-basic-y_tiled_ccs
+kms_ccs@pipe-E-crc-primary-basic-yf_tiled_ccs
+kms_ccs@pipe-E-crc-primary-basic-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-E-crc-primary-basic-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-E-crc-primary-basic-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-E-crc-primary-basic-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-E-crc-primary-basic-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-E-crc-primary-basic-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-E-crc-primary-basic-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-E-crc-primary-basic-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-E-crc-primary-basic-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-E-crc-primary-rotation-180-y_tiled_ccs
+kms_ccs@pipe-E-crc-primary-rotation-180-yf_tiled_ccs
+kms_ccs@pipe-E-crc-primary-rotation-180-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-E-crc-primary-rotation-180-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-E-crc-primary-rotation-180-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-E-crc-primary-rotation-180-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-E-crc-primary-rotation-180-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-E-crc-primary-rotation-180-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-E-crc-primary-rotation-180-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-E-crc-primary-rotation-180-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-E-crc-primary-rotation-180-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-E-random-ccs-data-y_tiled_ccs
+kms_ccs@pipe-E-random-ccs-data-yf_tiled_ccs
+kms_ccs@pipe-E-random-ccs-data-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-E-random-ccs-data-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-E-random-ccs-data-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-E-random-ccs-data-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-E-random-ccs-data-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-E-random-ccs-data-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-E-random-ccs-data-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-E-random-ccs-data-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-E-random-ccs-data-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-E-missing-ccs-buffer-y_tiled_ccs
+kms_ccs@pipe-E-missing-ccs-buffer-yf_tiled_ccs
+kms_ccs@pipe-E-missing-ccs-buffer-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-E-missing-ccs-buffer-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-E-missing-ccs-buffer-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-E-missing-ccs-buffer-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-E-missing-ccs-buffer-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-E-missing-ccs-buffer-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-E-ccs-on-another-bo-y_tiled_ccs
+kms_ccs@pipe-E-ccs-on-another-bo-yf_tiled_ccs
+kms_ccs@pipe-E-ccs-on-another-bo-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-E-ccs-on-another-bo-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-E-ccs-on-another-bo-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-E-ccs-on-another-bo-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-E-ccs-on-another-bo-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-E-ccs-on-another-bo-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-E-bad-aux-stride-y_tiled_ccs
+kms_ccs@pipe-E-bad-aux-stride-yf_tiled_ccs
+kms_ccs@pipe-E-bad-aux-stride-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-E-bad-aux-stride-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-E-bad-aux-stride-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-E-bad-aux-stride-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-E-bad-aux-stride-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-E-bad-aux-stride-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-E-crc-sprite-planes-basic-y_tiled_ccs
+kms_ccs@pipe-E-crc-sprite-planes-basic-yf_tiled_ccs
+kms_ccs@pipe-E-crc-sprite-planes-basic-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-E-crc-sprite-planes-basic-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-E-crc-sprite-planes-basic-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-E-crc-sprite-planes-basic-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-E-crc-sprite-planes-basic-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-E-crc-sprite-planes-basic-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-E-crc-sprite-planes-basic-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-E-crc-sprite-planes-basic-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-E-crc-sprite-planes-basic-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-F-bad-pixel-format-y_tiled_ccs
+kms_ccs@pipe-F-bad-pixel-format-yf_tiled_ccs
+kms_ccs@pipe-F-bad-pixel-format-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-F-bad-pixel-format-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-F-bad-pixel-format-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-F-bad-pixel-format-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-F-bad-pixel-format-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-F-bad-pixel-format-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-F-bad-pixel-format-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-F-bad-pixel-format-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-F-bad-pixel-format-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-F-bad-rotation-90-y_tiled_ccs
+kms_ccs@pipe-F-bad-rotation-90-yf_tiled_ccs
+kms_ccs@pipe-F-bad-rotation-90-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-F-bad-rotation-90-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-F-bad-rotation-90-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-F-bad-rotation-90-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-F-bad-rotation-90-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-F-bad-rotation-90-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-F-bad-rotation-90-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-F-bad-rotation-90-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-F-bad-rotation-90-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-F-crc-primary-basic-y_tiled_ccs
+kms_ccs@pipe-F-crc-primary-basic-yf_tiled_ccs
+kms_ccs@pipe-F-crc-primary-basic-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-F-crc-primary-basic-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-F-crc-primary-basic-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-F-crc-primary-basic-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-F-crc-primary-basic-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-F-crc-primary-basic-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-F-crc-primary-basic-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-F-crc-primary-basic-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-F-crc-primary-basic-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-F-crc-primary-rotation-180-y_tiled_ccs
+kms_ccs@pipe-F-crc-primary-rotation-180-yf_tiled_ccs
+kms_ccs@pipe-F-crc-primary-rotation-180-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-F-crc-primary-rotation-180-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-F-crc-primary-rotation-180-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-F-crc-primary-rotation-180-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-F-crc-primary-rotation-180-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-F-crc-primary-rotation-180-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-F-crc-primary-rotation-180-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-F-crc-primary-rotation-180-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-F-crc-primary-rotation-180-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-F-random-ccs-data-y_tiled_ccs
+kms_ccs@pipe-F-random-ccs-data-yf_tiled_ccs
+kms_ccs@pipe-F-random-ccs-data-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-F-random-ccs-data-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-F-random-ccs-data-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-F-random-ccs-data-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-F-random-ccs-data-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-F-random-ccs-data-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-F-random-ccs-data-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-F-random-ccs-data-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-F-random-ccs-data-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-F-missing-ccs-buffer-y_tiled_ccs
+kms_ccs@pipe-F-missing-ccs-buffer-yf_tiled_ccs
+kms_ccs@pipe-F-missing-ccs-buffer-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-F-missing-ccs-buffer-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-F-missing-ccs-buffer-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-F-missing-ccs-buffer-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-F-missing-ccs-buffer-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-F-missing-ccs-buffer-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-F-ccs-on-another-bo-y_tiled_ccs
+kms_ccs@pipe-F-ccs-on-another-bo-yf_tiled_ccs
+kms_ccs@pipe-F-ccs-on-another-bo-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-F-ccs-on-another-bo-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-F-ccs-on-another-bo-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-F-ccs-on-another-bo-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-F-ccs-on-another-bo-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-F-ccs-on-another-bo-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-F-bad-aux-stride-y_tiled_ccs
+kms_ccs@pipe-F-bad-aux-stride-yf_tiled_ccs
+kms_ccs@pipe-F-bad-aux-stride-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-F-bad-aux-stride-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-F-bad-aux-stride-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-F-bad-aux-stride-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-F-bad-aux-stride-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-F-bad-aux-stride-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-F-crc-sprite-planes-basic-y_tiled_ccs
+kms_ccs@pipe-F-crc-sprite-planes-basic-yf_tiled_ccs
+kms_ccs@pipe-F-crc-sprite-planes-basic-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-F-crc-sprite-planes-basic-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-F-crc-sprite-planes-basic-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-F-crc-sprite-planes-basic-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-F-crc-sprite-planes-basic-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-F-crc-sprite-planes-basic-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-F-crc-sprite-planes-basic-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-F-crc-sprite-planes-basic-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-F-crc-sprite-planes-basic-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-G-bad-pixel-format-y_tiled_ccs
+kms_ccs@pipe-G-bad-pixel-format-yf_tiled_ccs
+kms_ccs@pipe-G-bad-pixel-format-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-G-bad-pixel-format-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-G-bad-pixel-format-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-G-bad-pixel-format-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-G-bad-pixel-format-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-G-bad-pixel-format-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-G-bad-pixel-format-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-G-bad-pixel-format-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-G-bad-pixel-format-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-G-bad-rotation-90-y_tiled_ccs
+kms_ccs@pipe-G-bad-rotation-90-yf_tiled_ccs
+kms_ccs@pipe-G-bad-rotation-90-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-G-bad-rotation-90-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-G-bad-rotation-90-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-G-bad-rotation-90-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-G-bad-rotation-90-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-G-bad-rotation-90-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-G-bad-rotation-90-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-G-bad-rotation-90-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-G-bad-rotation-90-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-G-crc-primary-basic-y_tiled_ccs
+kms_ccs@pipe-G-crc-primary-basic-yf_tiled_ccs
+kms_ccs@pipe-G-crc-primary-basic-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-G-crc-primary-basic-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-G-crc-primary-basic-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-G-crc-primary-basic-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-G-crc-primary-basic-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-G-crc-primary-basic-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-G-crc-primary-basic-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-G-crc-primary-basic-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-G-crc-primary-basic-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-G-crc-primary-rotation-180-y_tiled_ccs
+kms_ccs@pipe-G-crc-primary-rotation-180-yf_tiled_ccs
+kms_ccs@pipe-G-crc-primary-rotation-180-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-G-crc-primary-rotation-180-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-G-crc-primary-rotation-180-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-G-crc-primary-rotation-180-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-G-crc-primary-rotation-180-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-G-crc-primary-rotation-180-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-G-crc-primary-rotation-180-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-G-crc-primary-rotation-180-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-G-crc-primary-rotation-180-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-G-random-ccs-data-y_tiled_ccs
+kms_ccs@pipe-G-random-ccs-data-yf_tiled_ccs
+kms_ccs@pipe-G-random-ccs-data-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-G-random-ccs-data-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-G-random-ccs-data-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-G-random-ccs-data-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-G-random-ccs-data-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-G-random-ccs-data-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-G-random-ccs-data-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-G-random-ccs-data-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-G-random-ccs-data-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-G-missing-ccs-buffer-y_tiled_ccs
+kms_ccs@pipe-G-missing-ccs-buffer-yf_tiled_ccs
+kms_ccs@pipe-G-missing-ccs-buffer-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-G-missing-ccs-buffer-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-G-missing-ccs-buffer-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-G-missing-ccs-buffer-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-G-missing-ccs-buffer-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-G-missing-ccs-buffer-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-G-ccs-on-another-bo-y_tiled_ccs
+kms_ccs@pipe-G-ccs-on-another-bo-yf_tiled_ccs
+kms_ccs@pipe-G-ccs-on-another-bo-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-G-ccs-on-another-bo-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-G-ccs-on-another-bo-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-G-ccs-on-another-bo-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-G-ccs-on-another-bo-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-G-ccs-on-another-bo-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-G-bad-aux-stride-y_tiled_ccs
+kms_ccs@pipe-G-bad-aux-stride-yf_tiled_ccs
+kms_ccs@pipe-G-bad-aux-stride-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-G-bad-aux-stride-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-G-bad-aux-stride-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-G-bad-aux-stride-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-G-bad-aux-stride-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-G-bad-aux-stride-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-G-crc-sprite-planes-basic-y_tiled_ccs
+kms_ccs@pipe-G-crc-sprite-planes-basic-yf_tiled_ccs
+kms_ccs@pipe-G-crc-sprite-planes-basic-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-G-crc-sprite-planes-basic-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-G-crc-sprite-planes-basic-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-G-crc-sprite-planes-basic-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-G-crc-sprite-planes-basic-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-G-crc-sprite-planes-basic-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-G-crc-sprite-planes-basic-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-G-crc-sprite-planes-basic-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-G-crc-sprite-planes-basic-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-H-bad-pixel-format-y_tiled_ccs
+kms_ccs@pipe-H-bad-pixel-format-yf_tiled_ccs
+kms_ccs@pipe-H-bad-pixel-format-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-H-bad-pixel-format-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-H-bad-pixel-format-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-H-bad-pixel-format-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-H-bad-pixel-format-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-H-bad-pixel-format-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-H-bad-pixel-format-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-H-bad-pixel-format-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-H-bad-pixel-format-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-H-bad-rotation-90-y_tiled_ccs
+kms_ccs@pipe-H-bad-rotation-90-yf_tiled_ccs
+kms_ccs@pipe-H-bad-rotation-90-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-H-bad-rotation-90-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-H-bad-rotation-90-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-H-bad-rotation-90-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-H-bad-rotation-90-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-H-bad-rotation-90-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-H-bad-rotation-90-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-H-bad-rotation-90-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-H-bad-rotation-90-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-H-crc-primary-basic-y_tiled_ccs
+kms_ccs@pipe-H-crc-primary-basic-yf_tiled_ccs
+kms_ccs@pipe-H-crc-primary-basic-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-H-crc-primary-basic-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-H-crc-primary-basic-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-H-crc-primary-basic-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-H-crc-primary-basic-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-H-crc-primary-basic-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-H-crc-primary-basic-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-H-crc-primary-basic-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-H-crc-primary-basic-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-H-crc-primary-rotation-180-y_tiled_ccs
+kms_ccs@pipe-H-crc-primary-rotation-180-yf_tiled_ccs
+kms_ccs@pipe-H-crc-primary-rotation-180-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-H-crc-primary-rotation-180-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-H-crc-primary-rotation-180-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-H-crc-primary-rotation-180-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-H-crc-primary-rotation-180-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-H-crc-primary-rotation-180-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-H-crc-primary-rotation-180-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-H-crc-primary-rotation-180-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-H-crc-primary-rotation-180-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-H-random-ccs-data-y_tiled_ccs
+kms_ccs@pipe-H-random-ccs-data-yf_tiled_ccs
+kms_ccs@pipe-H-random-ccs-data-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-H-random-ccs-data-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-H-random-ccs-data-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-H-random-ccs-data-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-H-random-ccs-data-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-H-random-ccs-data-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-H-random-ccs-data-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-H-random-ccs-data-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-H-random-ccs-data-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-H-missing-ccs-buffer-y_tiled_ccs
+kms_ccs@pipe-H-missing-ccs-buffer-yf_tiled_ccs
+kms_ccs@pipe-H-missing-ccs-buffer-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-H-missing-ccs-buffer-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-H-missing-ccs-buffer-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-H-missing-ccs-buffer-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-H-missing-ccs-buffer-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-H-missing-ccs-buffer-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-H-ccs-on-another-bo-y_tiled_ccs
+kms_ccs@pipe-H-ccs-on-another-bo-yf_tiled_ccs
+kms_ccs@pipe-H-ccs-on-another-bo-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-H-ccs-on-another-bo-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-H-ccs-on-another-bo-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-H-ccs-on-another-bo-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-H-ccs-on-another-bo-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-H-ccs-on-another-bo-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-H-bad-aux-stride-y_tiled_ccs
+kms_ccs@pipe-H-bad-aux-stride-yf_tiled_ccs
+kms_ccs@pipe-H-bad-aux-stride-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-H-bad-aux-stride-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-H-bad-aux-stride-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-H-bad-aux-stride-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-H-bad-aux-stride-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-H-bad-aux-stride-4_tiled_mtl_rc_ccs_cc
+kms_ccs@pipe-H-crc-sprite-planes-basic-y_tiled_ccs
+kms_ccs@pipe-H-crc-sprite-planes-basic-yf_tiled_ccs
+kms_ccs@pipe-H-crc-sprite-planes-basic-y_tiled_gen12_rc_ccs
+kms_ccs@pipe-H-crc-sprite-planes-basic-y_tiled_gen12_rc_ccs_cc
+kms_ccs@pipe-H-crc-sprite-planes-basic-y_tiled_gen12_mc_ccs
+kms_ccs@pipe-H-crc-sprite-planes-basic-4_tiled_dg2_rc_ccs
+kms_ccs@pipe-H-crc-sprite-planes-basic-4_tiled_dg2_mc_ccs
+kms_ccs@pipe-H-crc-sprite-planes-basic-4_tiled_dg2_rc_ccs_cc
+kms_ccs@pipe-H-crc-sprite-planes-basic-4_tiled_mtl_rc_ccs
+kms_ccs@pipe-H-crc-sprite-planes-basic-4_tiled_mtl_mc_ccs
+kms_ccs@pipe-H-crc-sprite-planes-basic-4_tiled_mtl_rc_ccs_cc
+kms_cdclk@plane-scaling
+kms_cdclk@mode-transition
+kms_cdclk@mode-transition-all-outputs
+kms_color@degamma
+kms_color@gamma
+kms_color@legacy-gamma
+kms_color@legacy-gamma-reset
+kms_color@ctm-red-to-blue
+kms_color@ctm-green-to-red
+kms_color@ctm-blue-to-red
+kms_color@ctm-max
+kms_color@ctm-negative
+kms_color@ctm-0-25
+kms_color@ctm-0-50
+kms_color@ctm-0-75
+kms_color@ctm-signed
+kms_color@deep-color
+kms_color@invalid-gamma-lut-sizes
+kms_color@invalid-degamma-lut-sizes
+kms_color@invalid-ctm-matrix-sizes
+kms_concurrent@pipe-A
+kms_concurrent@pipe-B
+kms_concurrent@pipe-C
+kms_concurrent@pipe-D
+kms_concurrent@pipe-E
+kms_concurrent@pipe-F
+kms_concurrent@pipe-G
+kms_concurrent@pipe-H
+kms_content_protection@legacy
+kms_content_protection@atomic
+kms_content_protection@atomic-dpms
+kms_content_protection@LIC
+kms_content_protection@type1
+kms_content_protection@mei_interface
+kms_content_protection@content_type_change
+kms_content_protection@uevent
+kms_content_protection@srm
+kms_content_protection@dp-mst-type-0
+kms_content_protection@dp-mst-lic-type-0
+kms_content_protection@dp-mst-type-1
+kms_content_protection@dp-mst-lic-type-1
+kms_cursor_crc@cursor-size-change
+kms_cursor_crc@cursor-alpha-opaque
+kms_cursor_crc@cursor-alpha-transparent
+kms_cursor_crc@cursor-dpms
+kms_cursor_crc@cursor-suspend
+kms_cursor_crc@cursor-onscreen-32x32
+kms_cursor_crc@cursor-offscreen-32x32
+kms_cursor_crc@cursor-sliding-32x32
+kms_cursor_crc@cursor-random-32x32
+kms_cursor_crc@cursor-rapid-movement-32x32
+kms_cursor_crc@cursor-onscreen-32x10
+kms_cursor_crc@cursor-offscreen-32x10
+kms_cursor_crc@cursor-sliding-32x10
+kms_cursor_crc@cursor-random-32x10
+kms_cursor_crc@cursor-rapid-movement-32x10
+kms_cursor_crc@cursor-onscreen-64x64
+kms_cursor_crc@cursor-offscreen-64x64
+kms_cursor_crc@cursor-sliding-64x64
+kms_cursor_crc@cursor-random-64x64
+kms_cursor_crc@cursor-rapid-movement-64x64
+kms_cursor_crc@cursor-onscreen-64x21
+kms_cursor_crc@cursor-offscreen-64x21
+kms_cursor_crc@cursor-sliding-64x21
+kms_cursor_crc@cursor-random-64x21
+kms_cursor_crc@cursor-rapid-movement-64x21
+kms_cursor_crc@cursor-onscreen-128x128
+kms_cursor_crc@cursor-offscreen-128x128
+kms_cursor_crc@cursor-sliding-128x128
+kms_cursor_crc@cursor-random-128x128
+kms_cursor_crc@cursor-rapid-movement-128x128
+kms_cursor_crc@cursor-onscreen-128x42
+kms_cursor_crc@cursor-offscreen-128x42
+kms_cursor_crc@cursor-sliding-128x42
+kms_cursor_crc@cursor-random-128x42
+kms_cursor_crc@cursor-rapid-movement-128x42
+kms_cursor_crc@cursor-onscreen-256x256
+kms_cursor_crc@cursor-offscreen-256x256
+kms_cursor_crc@cursor-sliding-256x256
+kms_cursor_crc@cursor-random-256x256
+kms_cursor_crc@cursor-rapid-movement-256x256
+kms_cursor_crc@cursor-onscreen-256x85
+kms_cursor_crc@cursor-offscreen-256x85
+kms_cursor_crc@cursor-sliding-256x85
+kms_cursor_crc@cursor-random-256x85
+kms_cursor_crc@cursor-rapid-movement-256x85
+kms_cursor_crc@cursor-onscreen-512x512
+kms_cursor_crc@cursor-offscreen-512x512
+kms_cursor_crc@cursor-sliding-512x512
+kms_cursor_crc@cursor-random-512x512
+kms_cursor_crc@cursor-rapid-movement-512x512
+kms_cursor_crc@cursor-onscreen-512x170
+kms_cursor_crc@cursor-offscreen-512x170
+kms_cursor_crc@cursor-sliding-512x170
+kms_cursor_crc@cursor-random-512x170
+kms_cursor_crc@cursor-rapid-movement-512x170
+kms_cursor_crc@cursor-onscreen-max-size
+kms_cursor_crc@cursor-offscreen-max-size
+kms_cursor_crc@cursor-sliding-max-size
+kms_cursor_crc@cursor-random-max-size
+kms_cursor_crc@cursor-rapid-movement-max-size
+kms_cursor_legacy@single-bo
+kms_cursor_legacy@single-move
+kms_cursor_legacy@forked-bo
+kms_cursor_legacy@forked-move
+kms_cursor_legacy@torture-bo
+kms_cursor_legacy@torture-move
+kms_cursor_legacy@nonblocking-modeset-vs-cursor-atomic
+kms_cursor_legacy@long-nonblocking-modeset-vs-cursor-atomic
+kms_cursor_legacy@2x-flip-vs-cursor-legacy
+kms_cursor_legacy@2x-flip-vs-cursor-atomic
+kms_cursor_legacy@2x-long-flip-vs-cursor-legacy
+kms_cursor_legacy@2x-long-flip-vs-cursor-atomic
+kms_cursor_legacy@2x-nonblocking-modeset-vs-cursor-atomic
+kms_cursor_legacy@2x-long-nonblocking-modeset-vs-cursor-atomic
+kms_cursor_legacy@2x-cursor-vs-flip-legacy
+kms_cursor_legacy@2x-long-cursor-vs-flip-legacy
+kms_cursor_legacy@2x-cursor-vs-flip-atomic
+kms_cursor_legacy@2x-long-cursor-vs-flip-atomic
+kms_cursor_legacy@flip-vs-cursor-crc-legacy
+kms_cursor_legacy@flip-vs-cursor-crc-atomic
+kms_cursor_legacy@flip-vs-cursor-busy-crc-legacy
+kms_cursor_legacy@flip-vs-cursor-busy-crc-atomic
+kms_cursor_legacy@basic-flip-before-cursor-legacy
+kms_cursor_legacy@basic-busy-flip-before-cursor-legacy
+kms_cursor_legacy@basic-flip-after-cursor-legacy
+kms_cursor_legacy@basic-flip-before-cursor-varying-size
+kms_cursor_legacy@basic-busy-flip-before-cursor-varying-size
+kms_cursor_legacy@basic-flip-after-cursor-varying-size
+kms_cursor_legacy@short-flip-before-cursor-toggle
+kms_cursor_legacy@short-busy-flip-before-cursor-toggle
+kms_cursor_legacy@short-flip-after-cursor-toggle
+kms_cursor_legacy@basic-flip-before-cursor-atomic
+kms_cursor_legacy@basic-busy-flip-before-cursor-atomic
+kms_cursor_legacy@basic-flip-after-cursor-atomic
+kms_cursor_legacy@short-flip-before-cursor-atomic-transitions
+kms_cursor_legacy@short-busy-flip-before-cursor-atomic-transitions
+kms_cursor_legacy@short-flip-after-cursor-atomic-transitions
+kms_cursor_legacy@short-flip-before-cursor-atomic-transitions-varying-size
+kms_cursor_legacy@short-busy-flip-before-cursor-atomic-transitions-varying-size
+kms_cursor_legacy@short-flip-after-cursor-atomic-transitions-varying-size
+kms_cursor_legacy@cursor-vs-flip-legacy
+kms_cursor_legacy@flip-vs-cursor-legacy
+kms_cursor_legacy@cursorA-vs-flipA-legacy
+kms_cursor_legacy@cursorA-vs-flipB-legacy
+kms_cursor_legacy@cursorB-vs-flipA-legacy
+kms_cursor_legacy@cursorB-vs-flipB-legacy
+kms_cursor_legacy@cursor-vs-flip-varying-size
+kms_cursor_legacy@flip-vs-cursor-varying-size
+kms_cursor_legacy@cursorA-vs-flipA-varying-size
+kms_cursor_legacy@cursorA-vs-flipB-varying-size
+kms_cursor_legacy@cursorB-vs-flipA-varying-size
+kms_cursor_legacy@cursorB-vs-flipB-varying-size
+kms_cursor_legacy@cursor-vs-flip-toggle
+kms_cursor_legacy@flip-vs-cursor-toggle
+kms_cursor_legacy@cursorA-vs-flipA-toggle
+kms_cursor_legacy@cursorA-vs-flipB-toggle
+kms_cursor_legacy@cursorB-vs-flipA-toggle
+kms_cursor_legacy@cursorB-vs-flipB-toggle
+kms_cursor_legacy@cursor-vs-flip-atomic
+kms_cursor_legacy@flip-vs-cursor-atomic
+kms_cursor_legacy@cursorA-vs-flipA-atomic
+kms_cursor_legacy@cursorA-vs-flipB-atomic
+kms_cursor_legacy@cursorB-vs-flipA-atomic
+kms_cursor_legacy@cursorB-vs-flipB-atomic
+kms_cursor_legacy@cursor-vs-flip-atomic-transitions
+kms_cursor_legacy@flip-vs-cursor-atomic-transitions
+kms_cursor_legacy@cursorA-vs-flipA-atomic-transitions
+kms_cursor_legacy@cursorA-vs-flipB-atomic-transitions
+kms_cursor_legacy@cursorB-vs-flipA-atomic-transitions
+kms_cursor_legacy@cursorB-vs-flipB-atomic-transitions
+kms_cursor_legacy@cursor-vs-flip-atomic-transitions-varying-size
+kms_cursor_legacy@flip-vs-cursor-atomic-transitions-varying-size
+kms_cursor_legacy@cursorA-vs-flipA-atomic-transitions-varying-size
+kms_cursor_legacy@cursorA-vs-flipB-atomic-transitions-varying-size
+kms_cursor_legacy@cursorB-vs-flipA-atomic-transitions-varying-size
+kms_cursor_legacy@cursorB-vs-flipB-atomic-transitions-varying-size
+kms_dither@FB-8BPC-Vs-Panel-6BPC
+kms_dither@FB-8BPC-Vs-Panel-8BPC
+kms_dp_aux_dev
+kms_tiled_display@basic-test-pattern
+kms_tiled_display@basic-test-pattern-with-chamelium
+kms_draw_crc@draw-method-mmap-cpu
+kms_draw_crc@draw-method-mmap-gtt
+kms_draw_crc@draw-method-mmap-wc
+kms_draw_crc@draw-method-pwrite
+kms_draw_crc@draw-method-blt
+kms_draw_crc@draw-method-render
+kms_draw_crc@fill-fb
+kms_dsc@dsc-basic
+kms_dsc@dsc-with-formats
+kms_dsc@dsc-with-bpc
+kms_dsc@dsc-with-bpc-formats
+kms_dsc@dsc-with-output-formats
+kms_fbcon_fbt@fbc
+kms_fbcon_fbt@psr
+kms_fbcon_fbt@fbc-suspend
+kms_fbcon_fbt@psr-suspend
+kms_fence_pin_leak
+kms_flip@nonblocking-read
+kms_flip@wf_vblank-ts-check
+kms_flip@2x-wf_vblank-ts-check
+kms_flip@blocking-wf_vblank
+kms_flip@2x-blocking-wf_vblank
+kms_flip@absolute-wf_vblank
+kms_flip@2x-absolute-wf_vblank
+kms_flip@blocking-absolute-wf_vblank
+kms_flip@2x-blocking-absolute-wf_vblank
+kms_flip@basic-plain-flip
+kms_flip@2x-plain-flip
+kms_flip@busy-flip
+kms_flip@2x-busy-flip
+kms_flip@flip-vs-fences
+kms_flip@2x-flip-vs-fences
+kms_flip@plain-flip-ts-check
+kms_flip@2x-plain-flip-ts-check
+kms_flip@plain-flip-fb-recreate
+kms_flip@2x-plain-flip-fb-recreate
+kms_flip@flip-vs-rmfb
+kms_flip@2x-flip-vs-rmfb
+kms_flip@basic-flip-vs-dpms
+kms_flip@2x-flip-vs-dpms
+kms_flip@flip-vs-panning
+kms_flip@2x-flip-vs-panning
+kms_flip@basic-flip-vs-modeset
+kms_flip@2x-flip-vs-modeset
+kms_flip@flip-vs-expired-vblank
+kms_flip@2x-flip-vs-expired-vblank
+kms_flip@flip-vs-absolute-wf_vblank
+kms_flip@2x-flip-vs-absolute-wf_vblank
+kms_flip@basic-flip-vs-wf_vblank
+kms_flip@2x-flip-vs-wf_vblank
+kms_flip@flip-vs-blocking-wf-vblank
+kms_flip@2x-flip-vs-blocking-wf-vblank
+kms_flip@flip-vs-modeset-vs-hang
+kms_flip@2x-flip-vs-modeset-vs-hang
+kms_flip@flip-vs-panning-vs-hang
+kms_flip@2x-flip-vs-panning-vs-hang
+kms_flip@flip-vs-dpms-off-vs-modeset
+kms_flip@2x-flip-vs-dpms-off-vs-modeset
+kms_flip@single-buffer-flip-vs-dpms-off-vs-modeset
+kms_flip@2x-single-buffer-flip-vs-dpms-off-vs-modeset
+kms_flip@dpms-off-confusion
+kms_flip@nonexisting-fb
+kms_flip@2x-nonexisting-fb
+kms_flip@dpms-vs-vblank-race
+kms_flip@2x-dpms-vs-vblank-race
+kms_flip@modeset-vs-vblank-race
+kms_flip@2x-modeset-vs-vblank-race
+kms_flip@bo-too-big
+kms_flip@flip-vs-suspend
+kms_flip@2x-flip-vs-suspend
+kms_flip@wf_vblank-ts-check-interruptible
+kms_flip@2x-wf_vblank-ts-check-interruptible
+kms_flip@absolute-wf_vblank-interruptible
+kms_flip@2x-absolute-wf_vblank-interruptible
+kms_flip@blocking-absolute-wf_vblank-interruptible
+kms_flip@2x-blocking-absolute-wf_vblank-interruptible
+kms_flip@plain-flip-interruptible
+kms_flip@2x-plain-flip-interruptible
+kms_flip@flip-vs-fences-interruptible
+kms_flip@2x-flip-vs-fences-interruptible
+kms_flip@plain-flip-ts-check-interruptible
+kms_flip@2x-plain-flip-ts-check-interruptible
+kms_flip@plain-flip-fb-recreate-interruptible
+kms_flip@2x-plain-flip-fb-recreate-interruptible
+kms_flip@flip-vs-rmfb-interruptible
+kms_flip@2x-flip-vs-rmfb-interruptible
+kms_flip@flip-vs-panning-interruptible
+kms_flip@2x-flip-vs-panning-interruptible
+kms_flip@flip-vs-expired-vblank-interruptible
+kms_flip@2x-flip-vs-expired-vblank-interruptible
+kms_flip@flip-vs-absolute-wf_vblank-interruptible
+kms_flip@2x-flip-vs-absolute-wf_vblank-interruptible
+kms_flip@flip-vs-wf_vblank-interruptible
+kms_flip@2x-flip-vs-wf_vblank-interruptible
+kms_flip@flip-vs-dpms-off-vs-modeset-interruptible
+kms_flip@2x-flip-vs-dpms-off-vs-modeset-interruptible
+kms_flip@single-buffer-flip-vs-dpms-off-vs-modeset-interruptible
+kms_flip@2x-single-buffer-flip-vs-dpms-off-vs-modeset-interruptible
+kms_flip@dpms-off-confusion-interruptible
+kms_flip@nonexisting-fb-interruptible
+kms_flip@2x-nonexisting-fb-interruptible
+kms_flip@dpms-vs-vblank-race-interruptible
+kms_flip@2x-dpms-vs-vblank-race-interruptible
+kms_flip@modeset-vs-vblank-race-interruptible
+kms_flip@2x-modeset-vs-vblank-race-interruptible
+kms_flip@bo-too-big-interruptible
+kms_flip@flip-vs-suspend-interruptible
+kms_flip@2x-flip-vs-suspend-interruptible
+kms_flip_event_leak@basic
+kms_flip_scaled_crc@flip-32bpp-ytile-to-64bpp-ytile-downscaling
+kms_flip_scaled_crc@flip-32bpp-yftile-to-64bpp-yftile-downscaling
+kms_flip_scaled_crc@flip-32bpp-xtile-to-64bpp-xtile-downscaling
+kms_flip_scaled_crc@flip-32bpp-4tile-to-64bpp-4tile-downscaling
+kms_flip_scaled_crc@flip-32bpp-linear-to-64bpp-linear-downscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytile-downscaling
+kms_flip_scaled_crc@flip-64bpp-yftile-to-32bpp-yftile-downscaling
+kms_flip_scaled_crc@flip-64bpp-xtile-to-32bpp-xtile-downscaling
+kms_flip_scaled_crc@flip-64bpp-4tile-to-32bpp-4tile-downscaling
+kms_flip_scaled_crc@flip-64bpp-linear-to-32bpp-linear-downscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-16bpp-ytile-downscaling
+kms_flip_scaled_crc@flip-64bpp-yftile-to-16bpp-yftile-downscaling
+kms_flip_scaled_crc@flip-64bpp-xtile-to-16bpp-xtile-downscaling
+kms_flip_scaled_crc@flip-64bpp-4tile-to-16bpp-4tile-downscaling
+kms_flip_scaled_crc@flip-64bpp-linear-to-16bpp-linear-downscaling
+kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile-downscaling
+kms_flip_scaled_crc@flip-32bpp-yftileccs-to-64bpp-yftile-downscaling
+kms_flip_scaled_crc@flip-32bpp-ytile-to-32bpp-ytilegen12rcccs-downscaling
+kms_flip_scaled_crc@flip-32bpp-4tile-to-32bpp-4tiledg2rcccs-downscaling
+kms_flip_scaled_crc@flip-32bpp-ytile-to-32bpp-ytileccs-downscaling
+kms_flip_scaled_crc@flip-32bpp-yftile-to-32bpp-yftileccs-downscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytilercccs-downscaling
+kms_flip_scaled_crc@flip-64bpp-4tile-to-32bpp-4tiledg2rcccs-downscaling
+kms_flip_scaled_crc@flip-32bpp-ytile-to-64bpp-ytile-upscaling
+kms_flip_scaled_crc@flip-32bpp-yftile-to-64bpp-yftile-upscaling
+kms_flip_scaled_crc@flip-32bpp-xtile-to-64bpp-xtile-upscaling
+kms_flip_scaled_crc@flip-32bpp-4tile-to-64bpp-4tile-upscaling
+kms_flip_scaled_crc@flip-32bpp-linear-to-64bpp-linear-upscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytile-upscaling
+kms_flip_scaled_crc@flip-64bpp-yftile-to-32bpp-yftile-upscaling
+kms_flip_scaled_crc@flip-64bpp-xtile-to-32bpp-xtile-upscaling
+kms_flip_scaled_crc@flip-64bpp-4tile-to-32bpp-4tile-upscaling
+kms_flip_scaled_crc@flip-64bpp-linear-to-32bpp-linear-upscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-16bpp-ytile-upscaling
+kms_flip_scaled_crc@flip-64bpp-yftile-to-16bpp-yftile-upscaling
+kms_flip_scaled_crc@flip-64bpp-xtile-to-16bpp-xtile-upscaling
+kms_flip_scaled_crc@flip-64bpp-4tile-to-16bpp-4tile-upscaling
+kms_flip_scaled_crc@flip-64bpp-linear-to-16bpp-linear-upscaling
+kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile-upscaling
+kms_flip_scaled_crc@flip-32bpp-yftileccs-to-64bpp-yftile-upscaling
+kms_flip_scaled_crc@flip-32bpp-ytile-to-32bpp-ytilegen12rcccs-upscaling
+kms_flip_scaled_crc@flip-32bpp-4tile-to-32bpp-4tiledg2rcccs-upscaling
+kms_flip_scaled_crc@flip-32bpp-ytile-to-32bpp-ytileccs-upscaling
+kms_flip_scaled_crc@flip-32bpp-yftile-to-32bpp-yftileccs-upscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytilegen12rcccs-upscaling
+kms_flip_scaled_crc@flip-64bpp-4tile-to-32bpp-4tiledg2rcccs-upscaling
+kms_force_connector_basic@force-load-detect
+kms_force_connector_basic@force-connector-state
+kms_force_connector_basic@force-edid
+kms_force_connector_basic@prune-stale-modes
+kms_frontbuffer_tracking@fbc-1p-rte
+kms_frontbuffer_tracking@fbc-2p-rte
+kms_frontbuffer_tracking@psr-1p-rte
+kms_frontbuffer_tracking@psr-2p-rte
+kms_frontbuffer_tracking@fbcpsr-1p-rte
+kms_frontbuffer_tracking@fbcpsr-2p-rte
+kms_frontbuffer_tracking@drrs-1p-rte
+kms_frontbuffer_tracking@drrs-2p-rte
+kms_frontbuffer_tracking@fbcdrrs-1p-rte
+kms_frontbuffer_tracking@fbcdrrs-2p-rte
+kms_frontbuffer_tracking@psrdrrs-1p-rte
+kms_frontbuffer_tracking@psrdrrs-2p-rte
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-rte
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-rte
+kms_frontbuffer_tracking@fbc-1p-primscrn-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbc-1p-primscrn-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbc-1p-primscrn-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbc-1p-primscrn-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbc-1p-primscrn-pri-indfb-draw-blt
+kms_frontbuffer_tracking@fbc-1p-primscrn-pri-indfb-draw-render
+kms_frontbuffer_tracking@fbc-1p-primscrn-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbc-1p-primscrn-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbc-1p-primscrn-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbc-1p-primscrn-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@fbc-1p-primscrn-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@fbc-1p-primscrn-pri-shrfb-draw-render
+kms_frontbuffer_tracking@fbc-1p-primscrn-cur-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbc-1p-primscrn-cur-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbc-1p-primscrn-cur-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbc-1p-primscrn-cur-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbc-1p-primscrn-cur-indfb-draw-blt
+kms_frontbuffer_tracking@fbc-1p-primscrn-cur-indfb-draw-render
+kms_frontbuffer_tracking@fbc-1p-primscrn-spr-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbc-1p-primscrn-spr-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbc-1p-primscrn-spr-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbc-1p-primscrn-spr-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbc-1p-primscrn-spr-indfb-draw-blt
+kms_frontbuffer_tracking@fbc-1p-primscrn-spr-indfb-draw-render
+kms_frontbuffer_tracking@fbc-1p-offscren-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbc-1p-offscren-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbc-1p-offscren-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbc-1p-offscren-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbc-1p-offscren-pri-indfb-draw-blt
+kms_frontbuffer_tracking@fbc-1p-offscren-pri-indfb-draw-render
+kms_frontbuffer_tracking@fbc-1p-offscren-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbc-1p-offscren-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbc-1p-offscren-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbc-1p-offscren-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@fbc-1p-offscren-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@fbc-1p-offscren-pri-shrfb-draw-render
+kms_frontbuffer_tracking@fbc-2p-primscrn-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbc-2p-primscrn-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbc-2p-primscrn-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbc-2p-primscrn-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbc-2p-primscrn-pri-indfb-draw-blt
+kms_frontbuffer_tracking@fbc-2p-primscrn-pri-indfb-draw-render
+kms_frontbuffer_tracking@fbc-2p-primscrn-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbc-2p-primscrn-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbc-2p-primscrn-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbc-2p-primscrn-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@fbc-2p-primscrn-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@fbc-2p-primscrn-pri-shrfb-draw-render
+kms_frontbuffer_tracking@fbc-2p-primscrn-cur-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbc-2p-primscrn-cur-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbc-2p-primscrn-cur-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbc-2p-primscrn-cur-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbc-2p-primscrn-cur-indfb-draw-blt
+kms_frontbuffer_tracking@fbc-2p-primscrn-cur-indfb-draw-render
+kms_frontbuffer_tracking@fbc-2p-primscrn-spr-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbc-2p-primscrn-spr-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbc-2p-primscrn-spr-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbc-2p-primscrn-spr-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbc-2p-primscrn-spr-indfb-draw-blt
+kms_frontbuffer_tracking@fbc-2p-primscrn-spr-indfb-draw-render
+kms_frontbuffer_tracking@fbc-2p-scndscrn-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbc-2p-scndscrn-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbc-2p-scndscrn-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbc-2p-scndscrn-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbc-2p-scndscrn-pri-indfb-draw-blt
+kms_frontbuffer_tracking@fbc-2p-scndscrn-pri-indfb-draw-render
+kms_frontbuffer_tracking@fbc-2p-scndscrn-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbc-2p-scndscrn-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbc-2p-scndscrn-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbc-2p-scndscrn-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@fbc-2p-scndscrn-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@fbc-2p-scndscrn-pri-shrfb-draw-render
+kms_frontbuffer_tracking@fbc-2p-scndscrn-cur-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbc-2p-scndscrn-cur-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbc-2p-scndscrn-cur-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbc-2p-scndscrn-cur-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbc-2p-scndscrn-cur-indfb-draw-blt
+kms_frontbuffer_tracking@fbc-2p-scndscrn-cur-indfb-draw-render
+kms_frontbuffer_tracking@fbc-2p-scndscrn-spr-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbc-2p-scndscrn-spr-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbc-2p-scndscrn-spr-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbc-2p-scndscrn-spr-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbc-2p-scndscrn-spr-indfb-draw-blt
+kms_frontbuffer_tracking@fbc-2p-scndscrn-spr-indfb-draw-render
+kms_frontbuffer_tracking@psr-1p-primscrn-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psr-1p-primscrn-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psr-1p-primscrn-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@psr-1p-primscrn-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@psr-1p-primscrn-pri-indfb-draw-blt
+kms_frontbuffer_tracking@psr-1p-primscrn-pri-indfb-draw-render
+kms_frontbuffer_tracking@psr-1p-primscrn-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psr-1p-primscrn-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psr-1p-primscrn-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@psr-1p-primscrn-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@psr-1p-primscrn-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@psr-1p-primscrn-pri-shrfb-draw-render
+kms_frontbuffer_tracking@psr-1p-primscrn-cur-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psr-1p-primscrn-cur-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psr-1p-primscrn-cur-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@psr-1p-primscrn-cur-indfb-draw-pwrite
+kms_frontbuffer_tracking@psr-1p-primscrn-cur-indfb-draw-blt
+kms_frontbuffer_tracking@psr-1p-primscrn-cur-indfb-draw-render
+kms_frontbuffer_tracking@psr-1p-primscrn-spr-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psr-1p-primscrn-spr-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psr-1p-primscrn-spr-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@psr-1p-primscrn-spr-indfb-draw-pwrite
+kms_frontbuffer_tracking@psr-1p-primscrn-spr-indfb-draw-blt
+kms_frontbuffer_tracking@psr-1p-primscrn-spr-indfb-draw-render
+kms_frontbuffer_tracking@psr-1p-offscren-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psr-1p-offscren-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psr-1p-offscren-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@psr-1p-offscren-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@psr-1p-offscren-pri-indfb-draw-blt
+kms_frontbuffer_tracking@psr-1p-offscren-pri-indfb-draw-render
+kms_frontbuffer_tracking@psr-1p-offscren-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psr-1p-offscren-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psr-1p-offscren-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@psr-1p-offscren-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@psr-1p-offscren-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@psr-1p-offscren-pri-shrfb-draw-render
+kms_frontbuffer_tracking@psr-2p-primscrn-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psr-2p-primscrn-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psr-2p-primscrn-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@psr-2p-primscrn-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@psr-2p-primscrn-pri-indfb-draw-blt
+kms_frontbuffer_tracking@psr-2p-primscrn-pri-indfb-draw-render
+kms_frontbuffer_tracking@psr-2p-primscrn-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psr-2p-primscrn-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psr-2p-primscrn-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@psr-2p-primscrn-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@psr-2p-primscrn-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@psr-2p-primscrn-pri-shrfb-draw-render
+kms_frontbuffer_tracking@psr-2p-primscrn-cur-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psr-2p-primscrn-cur-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psr-2p-primscrn-cur-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@psr-2p-primscrn-cur-indfb-draw-pwrite
+kms_frontbuffer_tracking@psr-2p-primscrn-cur-indfb-draw-blt
+kms_frontbuffer_tracking@psr-2p-primscrn-cur-indfb-draw-render
+kms_frontbuffer_tracking@psr-2p-primscrn-spr-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psr-2p-primscrn-spr-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psr-2p-primscrn-spr-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@psr-2p-primscrn-spr-indfb-draw-pwrite
+kms_frontbuffer_tracking@psr-2p-primscrn-spr-indfb-draw-blt
+kms_frontbuffer_tracking@psr-2p-primscrn-spr-indfb-draw-render
+kms_frontbuffer_tracking@psr-2p-scndscrn-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psr-2p-scndscrn-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psr-2p-scndscrn-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@psr-2p-scndscrn-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@psr-2p-scndscrn-pri-indfb-draw-blt
+kms_frontbuffer_tracking@psr-2p-scndscrn-pri-indfb-draw-render
+kms_frontbuffer_tracking@psr-2p-scndscrn-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psr-2p-scndscrn-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psr-2p-scndscrn-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@psr-2p-scndscrn-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@psr-2p-scndscrn-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@psr-2p-scndscrn-pri-shrfb-draw-render
+kms_frontbuffer_tracking@psr-2p-scndscrn-cur-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psr-2p-scndscrn-cur-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psr-2p-scndscrn-cur-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@psr-2p-scndscrn-cur-indfb-draw-pwrite
+kms_frontbuffer_tracking@psr-2p-scndscrn-cur-indfb-draw-blt
+kms_frontbuffer_tracking@psr-2p-scndscrn-cur-indfb-draw-render
+kms_frontbuffer_tracking@psr-2p-scndscrn-spr-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psr-2p-scndscrn-spr-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psr-2p-scndscrn-spr-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@psr-2p-scndscrn-spr-indfb-draw-pwrite
+kms_frontbuffer_tracking@psr-2p-scndscrn-spr-indfb-draw-blt
+kms_frontbuffer_tracking@psr-2p-scndscrn-spr-indfb-draw-render
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-pri-indfb-draw-blt
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-pri-indfb-draw-render
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-pri-shrfb-draw-render
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-cur-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-cur-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-cur-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-cur-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-cur-indfb-draw-blt
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-cur-indfb-draw-render
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-spr-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-spr-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-spr-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-spr-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-spr-indfb-draw-blt
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-spr-indfb-draw-render
+kms_frontbuffer_tracking@fbcpsr-1p-offscren-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsr-1p-offscren-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsr-1p-offscren-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsr-1p-offscren-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsr-1p-offscren-pri-indfb-draw-blt
+kms_frontbuffer_tracking@fbcpsr-1p-offscren-pri-indfb-draw-render
+kms_frontbuffer_tracking@fbcpsr-1p-offscren-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsr-1p-offscren-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsr-1p-offscren-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsr-1p-offscren-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsr-1p-offscren-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@fbcpsr-1p-offscren-pri-shrfb-draw-render
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-pri-indfb-draw-blt
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-pri-indfb-draw-render
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-pri-shrfb-draw-render
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-cur-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-cur-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-cur-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-cur-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-cur-indfb-draw-blt
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-cur-indfb-draw-render
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-spr-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-spr-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-spr-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-spr-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-spr-indfb-draw-blt
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-spr-indfb-draw-render
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-pri-indfb-draw-blt
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-pri-indfb-draw-render
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-pri-shrfb-draw-render
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-cur-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-cur-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-cur-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-cur-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-cur-indfb-draw-blt
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-cur-indfb-draw-render
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-spr-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-spr-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-spr-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-spr-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-spr-indfb-draw-blt
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-spr-indfb-draw-render
+kms_frontbuffer_tracking@drrs-1p-primscrn-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@drrs-1p-primscrn-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@drrs-1p-primscrn-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@drrs-1p-primscrn-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@drrs-1p-primscrn-pri-indfb-draw-blt
+kms_frontbuffer_tracking@drrs-1p-primscrn-pri-indfb-draw-render
+kms_frontbuffer_tracking@drrs-1p-primscrn-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@drrs-1p-primscrn-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@drrs-1p-primscrn-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@drrs-1p-primscrn-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@drrs-1p-primscrn-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@drrs-1p-primscrn-pri-shrfb-draw-render
+kms_frontbuffer_tracking@drrs-1p-primscrn-cur-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@drrs-1p-primscrn-cur-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@drrs-1p-primscrn-cur-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@drrs-1p-primscrn-cur-indfb-draw-pwrite
+kms_frontbuffer_tracking@drrs-1p-primscrn-cur-indfb-draw-blt
+kms_frontbuffer_tracking@drrs-1p-primscrn-cur-indfb-draw-render
+kms_frontbuffer_tracking@drrs-1p-primscrn-spr-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@drrs-1p-primscrn-spr-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@drrs-1p-primscrn-spr-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@drrs-1p-primscrn-spr-indfb-draw-pwrite
+kms_frontbuffer_tracking@drrs-1p-primscrn-spr-indfb-draw-blt
+kms_frontbuffer_tracking@drrs-1p-primscrn-spr-indfb-draw-render
+kms_frontbuffer_tracking@drrs-1p-offscren-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@drrs-1p-offscren-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@drrs-1p-offscren-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@drrs-1p-offscren-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@drrs-1p-offscren-pri-indfb-draw-blt
+kms_frontbuffer_tracking@drrs-1p-offscren-pri-indfb-draw-render
+kms_frontbuffer_tracking@drrs-1p-offscren-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@drrs-1p-offscren-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@drrs-1p-offscren-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@drrs-1p-offscren-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@drrs-1p-offscren-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@drrs-1p-offscren-pri-shrfb-draw-render
+kms_frontbuffer_tracking@drrs-2p-primscrn-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@drrs-2p-primscrn-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@drrs-2p-primscrn-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@drrs-2p-primscrn-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@drrs-2p-primscrn-pri-indfb-draw-blt
+kms_frontbuffer_tracking@drrs-2p-primscrn-pri-indfb-draw-render
+kms_frontbuffer_tracking@drrs-2p-primscrn-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@drrs-2p-primscrn-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@drrs-2p-primscrn-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@drrs-2p-primscrn-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@drrs-2p-primscrn-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@drrs-2p-primscrn-pri-shrfb-draw-render
+kms_frontbuffer_tracking@drrs-2p-primscrn-cur-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@drrs-2p-primscrn-cur-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@drrs-2p-primscrn-cur-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@drrs-2p-primscrn-cur-indfb-draw-pwrite
+kms_frontbuffer_tracking@drrs-2p-primscrn-cur-indfb-draw-blt
+kms_frontbuffer_tracking@drrs-2p-primscrn-cur-indfb-draw-render
+kms_frontbuffer_tracking@drrs-2p-primscrn-spr-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@drrs-2p-primscrn-spr-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@drrs-2p-primscrn-spr-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@drrs-2p-primscrn-spr-indfb-draw-pwrite
+kms_frontbuffer_tracking@drrs-2p-primscrn-spr-indfb-draw-blt
+kms_frontbuffer_tracking@drrs-2p-primscrn-spr-indfb-draw-render
+kms_frontbuffer_tracking@drrs-2p-scndscrn-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@drrs-2p-scndscrn-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@drrs-2p-scndscrn-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@drrs-2p-scndscrn-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@drrs-2p-scndscrn-pri-indfb-draw-blt
+kms_frontbuffer_tracking@drrs-2p-scndscrn-pri-indfb-draw-render
+kms_frontbuffer_tracking@drrs-2p-scndscrn-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@drrs-2p-scndscrn-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@drrs-2p-scndscrn-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@drrs-2p-scndscrn-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@drrs-2p-scndscrn-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@drrs-2p-scndscrn-pri-shrfb-draw-render
+kms_frontbuffer_tracking@drrs-2p-scndscrn-cur-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@drrs-2p-scndscrn-cur-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@drrs-2p-scndscrn-cur-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@drrs-2p-scndscrn-cur-indfb-draw-pwrite
+kms_frontbuffer_tracking@drrs-2p-scndscrn-cur-indfb-draw-blt
+kms_frontbuffer_tracking@drrs-2p-scndscrn-cur-indfb-draw-render
+kms_frontbuffer_tracking@drrs-2p-scndscrn-spr-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@drrs-2p-scndscrn-spr-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@drrs-2p-scndscrn-spr-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@drrs-2p-scndscrn-spr-indfb-draw-pwrite
+kms_frontbuffer_tracking@drrs-2p-scndscrn-spr-indfb-draw-blt
+kms_frontbuffer_tracking@drrs-2p-scndscrn-spr-indfb-draw-render
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-pri-indfb-draw-blt
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-pri-indfb-draw-render
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-pri-shrfb-draw-render
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-cur-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-cur-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-cur-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-cur-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-cur-indfb-draw-blt
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-cur-indfb-draw-render
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-spr-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-spr-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-spr-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-spr-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-spr-indfb-draw-blt
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-spr-indfb-draw-render
+kms_frontbuffer_tracking@fbcdrrs-1p-offscren-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcdrrs-1p-offscren-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcdrrs-1p-offscren-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcdrrs-1p-offscren-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcdrrs-1p-offscren-pri-indfb-draw-blt
+kms_frontbuffer_tracking@fbcdrrs-1p-offscren-pri-indfb-draw-render
+kms_frontbuffer_tracking@fbcdrrs-1p-offscren-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcdrrs-1p-offscren-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcdrrs-1p-offscren-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcdrrs-1p-offscren-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@fbcdrrs-1p-offscren-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@fbcdrrs-1p-offscren-pri-shrfb-draw-render
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-pri-indfb-draw-blt
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-pri-indfb-draw-render
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-pri-shrfb-draw-render
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-cur-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-cur-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-cur-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-cur-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-cur-indfb-draw-blt
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-cur-indfb-draw-render
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-spr-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-spr-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-spr-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-spr-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-spr-indfb-draw-blt
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-spr-indfb-draw-render
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-pri-indfb-draw-blt
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-pri-indfb-draw-render
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-pri-shrfb-draw-render
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-cur-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-cur-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-cur-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-cur-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-cur-indfb-draw-blt
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-cur-indfb-draw-render
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-spr-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-spr-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-spr-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-spr-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-spr-indfb-draw-blt
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-spr-indfb-draw-render
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-pri-indfb-draw-blt
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-pri-indfb-draw-render
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-pri-shrfb-draw-render
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-cur-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-cur-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-cur-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-cur-indfb-draw-pwrite
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-cur-indfb-draw-blt
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-cur-indfb-draw-render
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-spr-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-spr-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-spr-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-spr-indfb-draw-pwrite
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-spr-indfb-draw-blt
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-spr-indfb-draw-render
+kms_frontbuffer_tracking@psrdrrs-1p-offscren-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psrdrrs-1p-offscren-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psrdrrs-1p-offscren-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@psrdrrs-1p-offscren-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@psrdrrs-1p-offscren-pri-indfb-draw-blt
+kms_frontbuffer_tracking@psrdrrs-1p-offscren-pri-indfb-draw-render
+kms_frontbuffer_tracking@psrdrrs-1p-offscren-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psrdrrs-1p-offscren-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psrdrrs-1p-offscren-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@psrdrrs-1p-offscren-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@psrdrrs-1p-offscren-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@psrdrrs-1p-offscren-pri-shrfb-draw-render
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-pri-indfb-draw-blt
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-pri-indfb-draw-render
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-pri-shrfb-draw-render
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-cur-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-cur-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-cur-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-cur-indfb-draw-pwrite
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-cur-indfb-draw-blt
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-cur-indfb-draw-render
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-spr-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-spr-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-spr-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-spr-indfb-draw-pwrite
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-spr-indfb-draw-blt
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-spr-indfb-draw-render
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-pri-indfb-draw-blt
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-pri-indfb-draw-render
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-pri-shrfb-draw-render
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-cur-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-cur-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-cur-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-cur-indfb-draw-pwrite
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-cur-indfb-draw-blt
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-cur-indfb-draw-render
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-spr-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-spr-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-spr-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-spr-indfb-draw-pwrite
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-spr-indfb-draw-blt
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-spr-indfb-draw-render
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-pri-indfb-draw-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-pri-indfb-draw-render
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-pri-shrfb-draw-render
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-cur-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-cur-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-cur-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-cur-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-cur-indfb-draw-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-cur-indfb-draw-render
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-spr-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-spr-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-spr-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-spr-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-spr-indfb-draw-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-spr-indfb-draw-render
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-offscren-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-offscren-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-offscren-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-offscren-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-offscren-pri-indfb-draw-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-offscren-pri-indfb-draw-render
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-offscren-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-offscren-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-offscren-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-offscren-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-offscren-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-offscren-pri-shrfb-draw-render
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-pri-indfb-draw-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-pri-indfb-draw-render
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-pri-shrfb-draw-render
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-cur-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-cur-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-cur-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-cur-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-cur-indfb-draw-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-cur-indfb-draw-render
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-spr-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-spr-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-spr-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-spr-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-spr-indfb-draw-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-spr-indfb-draw-render
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-pri-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-pri-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-pri-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-pri-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-pri-indfb-draw-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-pri-indfb-draw-render
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-pri-shrfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-pri-shrfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-pri-shrfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-pri-shrfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-pri-shrfb-draw-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-pri-shrfb-draw-render
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-cur-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-cur-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-cur-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-cur-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-cur-indfb-draw-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-cur-indfb-draw-render
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-spr-indfb-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-spr-indfb-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-spr-indfb-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-spr-indfb-draw-pwrite
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-spr-indfb-draw-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-spr-indfb-draw-render
+kms_frontbuffer_tracking@fbc-1p-primscrn-indfb-pgflip-blt
+kms_frontbuffer_tracking@fbc-1p-primscrn-indfb-msflip-blt
+kms_frontbuffer_tracking@fbc-1p-primscrn-indfb-plflip-blt
+kms_frontbuffer_tracking@fbc-1p-primscrn-shrfb-pgflip-blt
+kms_frontbuffer_tracking@fbc-1p-primscrn-shrfb-msflip-blt
+kms_frontbuffer_tracking@fbc-1p-primscrn-shrfb-plflip-blt
+kms_frontbuffer_tracking@fbc-2p-primscrn-indfb-pgflip-blt
+kms_frontbuffer_tracking@fbc-2p-primscrn-indfb-msflip-blt
+kms_frontbuffer_tracking@fbc-2p-primscrn-indfb-plflip-blt
+kms_frontbuffer_tracking@fbc-2p-primscrn-shrfb-pgflip-blt
+kms_frontbuffer_tracking@fbc-2p-primscrn-shrfb-msflip-blt
+kms_frontbuffer_tracking@fbc-2p-primscrn-shrfb-plflip-blt
+kms_frontbuffer_tracking@fbc-2p-scndscrn-indfb-pgflip-blt
+kms_frontbuffer_tracking@fbc-2p-scndscrn-indfb-msflip-blt
+kms_frontbuffer_tracking@fbc-2p-scndscrn-indfb-plflip-blt
+kms_frontbuffer_tracking@fbc-2p-scndscrn-shrfb-pgflip-blt
+kms_frontbuffer_tracking@fbc-2p-scndscrn-shrfb-msflip-blt
+kms_frontbuffer_tracking@fbc-2p-scndscrn-shrfb-plflip-blt
+kms_frontbuffer_tracking@psr-1p-primscrn-indfb-pgflip-blt
+kms_frontbuffer_tracking@psr-1p-primscrn-indfb-msflip-blt
+kms_frontbuffer_tracking@psr-1p-primscrn-indfb-plflip-blt
+kms_frontbuffer_tracking@psr-1p-primscrn-shrfb-pgflip-blt
+kms_frontbuffer_tracking@psr-1p-primscrn-shrfb-msflip-blt
+kms_frontbuffer_tracking@psr-1p-primscrn-shrfb-plflip-blt
+kms_frontbuffer_tracking@psr-2p-primscrn-indfb-pgflip-blt
+kms_frontbuffer_tracking@psr-2p-primscrn-indfb-msflip-blt
+kms_frontbuffer_tracking@psr-2p-primscrn-indfb-plflip-blt
+kms_frontbuffer_tracking@psr-2p-primscrn-shrfb-pgflip-blt
+kms_frontbuffer_tracking@psr-2p-primscrn-shrfb-msflip-blt
+kms_frontbuffer_tracking@psr-2p-primscrn-shrfb-plflip-blt
+kms_frontbuffer_tracking@psr-2p-scndscrn-indfb-pgflip-blt
+kms_frontbuffer_tracking@psr-2p-scndscrn-indfb-msflip-blt
+kms_frontbuffer_tracking@psr-2p-scndscrn-indfb-plflip-blt
+kms_frontbuffer_tracking@psr-2p-scndscrn-shrfb-pgflip-blt
+kms_frontbuffer_tracking@psr-2p-scndscrn-shrfb-msflip-blt
+kms_frontbuffer_tracking@psr-2p-scndscrn-shrfb-plflip-blt
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-indfb-pgflip-blt
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-indfb-msflip-blt
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-indfb-plflip-blt
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-shrfb-pgflip-blt
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-shrfb-msflip-blt
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-shrfb-plflip-blt
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-indfb-pgflip-blt
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-indfb-msflip-blt
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-indfb-plflip-blt
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-shrfb-pgflip-blt
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-shrfb-msflip-blt
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-shrfb-plflip-blt
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-indfb-pgflip-blt
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-indfb-msflip-blt
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-indfb-plflip-blt
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-shrfb-pgflip-blt
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-shrfb-msflip-blt
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-shrfb-plflip-blt
+kms_frontbuffer_tracking@drrs-1p-primscrn-indfb-pgflip-blt
+kms_frontbuffer_tracking@drrs-1p-primscrn-indfb-msflip-blt
+kms_frontbuffer_tracking@drrs-1p-primscrn-indfb-plflip-blt
+kms_frontbuffer_tracking@drrs-1p-primscrn-shrfb-pgflip-blt
+kms_frontbuffer_tracking@drrs-1p-primscrn-shrfb-msflip-blt
+kms_frontbuffer_tracking@drrs-1p-primscrn-shrfb-plflip-blt
+kms_frontbuffer_tracking@drrs-2p-primscrn-indfb-pgflip-blt
+kms_frontbuffer_tracking@drrs-2p-primscrn-indfb-msflip-blt
+kms_frontbuffer_tracking@drrs-2p-primscrn-indfb-plflip-blt
+kms_frontbuffer_tracking@drrs-2p-primscrn-shrfb-pgflip-blt
+kms_frontbuffer_tracking@drrs-2p-primscrn-shrfb-msflip-blt
+kms_frontbuffer_tracking@drrs-2p-primscrn-shrfb-plflip-blt
+kms_frontbuffer_tracking@drrs-2p-scndscrn-indfb-pgflip-blt
+kms_frontbuffer_tracking@drrs-2p-scndscrn-indfb-msflip-blt
+kms_frontbuffer_tracking@drrs-2p-scndscrn-indfb-plflip-blt
+kms_frontbuffer_tracking@drrs-2p-scndscrn-shrfb-pgflip-blt
+kms_frontbuffer_tracking@drrs-2p-scndscrn-shrfb-msflip-blt
+kms_frontbuffer_tracking@drrs-2p-scndscrn-shrfb-plflip-blt
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-indfb-pgflip-blt
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-indfb-msflip-blt
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-indfb-plflip-blt
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-shrfb-pgflip-blt
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-shrfb-msflip-blt
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-shrfb-plflip-blt
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-indfb-pgflip-blt
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-indfb-msflip-blt
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-indfb-plflip-blt
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-shrfb-pgflip-blt
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-shrfb-msflip-blt
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-shrfb-plflip-blt
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-indfb-pgflip-blt
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-indfb-msflip-blt
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-indfb-plflip-blt
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-shrfb-pgflip-blt
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-shrfb-msflip-blt
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-shrfb-plflip-blt
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-indfb-pgflip-blt
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-indfb-msflip-blt
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-indfb-plflip-blt
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-shrfb-pgflip-blt
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-shrfb-msflip-blt
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-shrfb-plflip-blt
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-indfb-pgflip-blt
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-indfb-msflip-blt
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-indfb-plflip-blt
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-shrfb-pgflip-blt
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-shrfb-msflip-blt
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-shrfb-plflip-blt
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-indfb-pgflip-blt
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-indfb-msflip-blt
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-indfb-plflip-blt
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-shrfb-pgflip-blt
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-shrfb-msflip-blt
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-shrfb-plflip-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-indfb-pgflip-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-indfb-msflip-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-indfb-plflip-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-shrfb-pgflip-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-shrfb-msflip-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-shrfb-plflip-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-indfb-pgflip-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-indfb-msflip-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-indfb-plflip-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-shrfb-pgflip-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-shrfb-msflip-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-shrfb-plflip-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-indfb-pgflip-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-indfb-msflip-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-indfb-plflip-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-shrfb-pgflip-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-shrfb-msflip-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-shrfb-plflip-blt
+kms_frontbuffer_tracking@fbc-1p-indfb-fliptrack-mmap-gtt
+kms_frontbuffer_tracking@fbc-1p-shrfb-fliptrack-mmap-gtt
+kms_frontbuffer_tracking@fbc-2p-indfb-fliptrack-mmap-gtt
+kms_frontbuffer_tracking@fbc-2p-shrfb-fliptrack-mmap-gtt
+kms_frontbuffer_tracking@fbcpsr-1p-indfb-fliptrack-mmap-gtt
+kms_frontbuffer_tracking@fbcpsr-1p-shrfb-fliptrack-mmap-gtt
+kms_frontbuffer_tracking@fbcpsr-2p-indfb-fliptrack-mmap-gtt
+kms_frontbuffer_tracking@fbcpsr-2p-shrfb-fliptrack-mmap-gtt
+kms_frontbuffer_tracking@fbcdrrs-1p-indfb-fliptrack-mmap-gtt
+kms_frontbuffer_tracking@fbcdrrs-1p-shrfb-fliptrack-mmap-gtt
+kms_frontbuffer_tracking@fbcdrrs-2p-indfb-fliptrack-mmap-gtt
+kms_frontbuffer_tracking@fbcdrrs-2p-shrfb-fliptrack-mmap-gtt
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-indfb-fliptrack-mmap-gtt
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-shrfb-fliptrack-mmap-gtt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-indfb-fliptrack-mmap-gtt
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-shrfb-fliptrack-mmap-gtt
+kms_frontbuffer_tracking@fbc-1p-primscrn-cur-indfb-move
+kms_frontbuffer_tracking@fbc-1p-primscrn-cur-indfb-onoff
+kms_frontbuffer_tracking@fbc-1p-primscrn-spr-indfb-move
+kms_frontbuffer_tracking@fbc-1p-primscrn-spr-indfb-onoff
+kms_frontbuffer_tracking@fbc-2p-primscrn-cur-indfb-move
+kms_frontbuffer_tracking@fbc-2p-primscrn-cur-indfb-onoff
+kms_frontbuffer_tracking@fbc-2p-primscrn-spr-indfb-move
+kms_frontbuffer_tracking@fbc-2p-primscrn-spr-indfb-onoff
+kms_frontbuffer_tracking@fbc-2p-scndscrn-cur-indfb-move
+kms_frontbuffer_tracking@fbc-2p-scndscrn-cur-indfb-onoff
+kms_frontbuffer_tracking@fbc-2p-scndscrn-spr-indfb-move
+kms_frontbuffer_tracking@fbc-2p-scndscrn-spr-indfb-onoff
+kms_frontbuffer_tracking@psr-1p-primscrn-cur-indfb-move
+kms_frontbuffer_tracking@psr-1p-primscrn-cur-indfb-onoff
+kms_frontbuffer_tracking@psr-1p-primscrn-spr-indfb-move
+kms_frontbuffer_tracking@psr-1p-primscrn-spr-indfb-onoff
+kms_frontbuffer_tracking@psr-2p-primscrn-cur-indfb-move
+kms_frontbuffer_tracking@psr-2p-primscrn-cur-indfb-onoff
+kms_frontbuffer_tracking@psr-2p-primscrn-spr-indfb-move
+kms_frontbuffer_tracking@psr-2p-primscrn-spr-indfb-onoff
+kms_frontbuffer_tracking@psr-2p-scndscrn-cur-indfb-move
+kms_frontbuffer_tracking@psr-2p-scndscrn-cur-indfb-onoff
+kms_frontbuffer_tracking@psr-2p-scndscrn-spr-indfb-move
+kms_frontbuffer_tracking@psr-2p-scndscrn-spr-indfb-onoff
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-cur-indfb-move
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-cur-indfb-onoff
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-spr-indfb-move
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-spr-indfb-onoff
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-cur-indfb-move
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-cur-indfb-onoff
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-spr-indfb-move
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-spr-indfb-onoff
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-cur-indfb-move
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-cur-indfb-onoff
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-spr-indfb-move
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-spr-indfb-onoff
+kms_frontbuffer_tracking@drrs-1p-primscrn-cur-indfb-move
+kms_frontbuffer_tracking@drrs-1p-primscrn-cur-indfb-onoff
+kms_frontbuffer_tracking@drrs-1p-primscrn-spr-indfb-move
+kms_frontbuffer_tracking@drrs-1p-primscrn-spr-indfb-onoff
+kms_frontbuffer_tracking@drrs-2p-primscrn-cur-indfb-move
+kms_frontbuffer_tracking@drrs-2p-primscrn-cur-indfb-onoff
+kms_frontbuffer_tracking@drrs-2p-primscrn-spr-indfb-move
+kms_frontbuffer_tracking@drrs-2p-primscrn-spr-indfb-onoff
+kms_frontbuffer_tracking@drrs-2p-scndscrn-cur-indfb-move
+kms_frontbuffer_tracking@drrs-2p-scndscrn-cur-indfb-onoff
+kms_frontbuffer_tracking@drrs-2p-scndscrn-spr-indfb-move
+kms_frontbuffer_tracking@drrs-2p-scndscrn-spr-indfb-onoff
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-cur-indfb-move
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-cur-indfb-onoff
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-spr-indfb-move
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-spr-indfb-onoff
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-cur-indfb-move
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-cur-indfb-onoff
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-spr-indfb-move
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-spr-indfb-onoff
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-cur-indfb-move
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-cur-indfb-onoff
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-spr-indfb-move
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-spr-indfb-onoff
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-cur-indfb-move
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-cur-indfb-onoff
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-spr-indfb-move
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-spr-indfb-onoff
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-cur-indfb-move
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-cur-indfb-onoff
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-spr-indfb-move
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-spr-indfb-onoff
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-cur-indfb-move
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-cur-indfb-onoff
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-spr-indfb-move
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-spr-indfb-onoff
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-cur-indfb-move
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-cur-indfb-onoff
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-spr-indfb-move
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-spr-indfb-onoff
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-cur-indfb-move
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-cur-indfb-onoff
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-spr-indfb-move
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-spr-indfb-onoff
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-cur-indfb-move
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-cur-indfb-onoff
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-spr-indfb-move
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-spr-indfb-onoff
+kms_frontbuffer_tracking@fbc-1p-primscrn-spr-indfb-fullscreen
+kms_frontbuffer_tracking@fbc-2p-primscrn-spr-indfb-fullscreen
+kms_frontbuffer_tracking@fbc-2p-scndscrn-spr-indfb-fullscreen
+kms_frontbuffer_tracking@psr-1p-primscrn-spr-indfb-fullscreen
+kms_frontbuffer_tracking@psr-2p-primscrn-spr-indfb-fullscreen
+kms_frontbuffer_tracking@psr-2p-scndscrn-spr-indfb-fullscreen
+kms_frontbuffer_tracking@fbcpsr-1p-primscrn-spr-indfb-fullscreen
+kms_frontbuffer_tracking@fbcpsr-2p-primscrn-spr-indfb-fullscreen
+kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-spr-indfb-fullscreen
+kms_frontbuffer_tracking@drrs-1p-primscrn-spr-indfb-fullscreen
+kms_frontbuffer_tracking@drrs-2p-primscrn-spr-indfb-fullscreen
+kms_frontbuffer_tracking@drrs-2p-scndscrn-spr-indfb-fullscreen
+kms_frontbuffer_tracking@fbcdrrs-1p-primscrn-spr-indfb-fullscreen
+kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-spr-indfb-fullscreen
+kms_frontbuffer_tracking@fbcdrrs-2p-scndscrn-spr-indfb-fullscreen
+kms_frontbuffer_tracking@psrdrrs-1p-primscrn-spr-indfb-fullscreen
+kms_frontbuffer_tracking@psrdrrs-2p-primscrn-spr-indfb-fullscreen
+kms_frontbuffer_tracking@psrdrrs-2p-scndscrn-spr-indfb-fullscreen
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-primscrn-spr-indfb-fullscreen
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-primscrn-spr-indfb-fullscreen
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-scndscrn-spr-indfb-fullscreen
+kms_frontbuffer_tracking@fbc-1p-pri-indfb-multidraw
+kms_frontbuffer_tracking@fbc-2p-pri-indfb-multidraw
+kms_frontbuffer_tracking@psr-1p-pri-indfb-multidraw
+kms_frontbuffer_tracking@psr-2p-pri-indfb-multidraw
+kms_frontbuffer_tracking@fbcpsr-1p-pri-indfb-multidraw
+kms_frontbuffer_tracking@fbcpsr-2p-pri-indfb-multidraw
+kms_frontbuffer_tracking@drrs-1p-pri-indfb-multidraw
+kms_frontbuffer_tracking@drrs-2p-pri-indfb-multidraw
+kms_frontbuffer_tracking@fbcdrrs-1p-pri-indfb-multidraw
+kms_frontbuffer_tracking@fbcdrrs-2p-pri-indfb-multidraw
+kms_frontbuffer_tracking@psrdrrs-1p-pri-indfb-multidraw
+kms_frontbuffer_tracking@psrdrrs-2p-pri-indfb-multidraw
+kms_frontbuffer_tracking@fbcpsrdrrs-1p-pri-indfb-multidraw
+kms_frontbuffer_tracking@fbcpsrdrrs-2p-pri-indfb-multidraw
+kms_frontbuffer_tracking@fbc-farfromfence-mmap-gtt
+kms_frontbuffer_tracking@psr-farfromfence-mmap-gtt
+kms_frontbuffer_tracking@fbcpsr-farfromfence-mmap-gtt
+kms_frontbuffer_tracking@drrs-farfromfence-mmap-gtt
+kms_frontbuffer_tracking@fbcdrrs-farfromfence-mmap-gtt
+kms_frontbuffer_tracking@psrdrrs-farfromfence-mmap-gtt
+kms_frontbuffer_tracking@fbcpsrdrrs-farfromfence-mmap-gtt
+kms_frontbuffer_tracking@fbc-rgb565-draw-mmap-cpu
+kms_frontbuffer_tracking@fbc-rgb101010-draw-mmap-cpu
+kms_frontbuffer_tracking@fbc-rgb565-draw-mmap-gtt
+kms_frontbuffer_tracking@fbc-rgb101010-draw-mmap-gtt
+kms_frontbuffer_tracking@fbc-rgb565-draw-mmap-wc
+kms_frontbuffer_tracking@fbc-rgb101010-draw-mmap-wc
+kms_frontbuffer_tracking@fbc-rgb565-draw-pwrite
+kms_frontbuffer_tracking@fbc-rgb101010-draw-pwrite
+kms_frontbuffer_tracking@fbc-rgb565-draw-blt
+kms_frontbuffer_tracking@fbc-rgb101010-draw-blt
+kms_frontbuffer_tracking@fbc-rgb565-draw-render
+kms_frontbuffer_tracking@fbc-rgb101010-draw-render
+kms_frontbuffer_tracking@psr-rgb565-draw-mmap-cpu
+kms_frontbuffer_tracking@psr-rgb101010-draw-mmap-cpu
+kms_frontbuffer_tracking@psr-rgb565-draw-mmap-gtt
+kms_frontbuffer_tracking@psr-rgb101010-draw-mmap-gtt
+kms_frontbuffer_tracking@psr-rgb565-draw-mmap-wc
+kms_frontbuffer_tracking@psr-rgb101010-draw-mmap-wc
+kms_frontbuffer_tracking@psr-rgb565-draw-pwrite
+kms_frontbuffer_tracking@psr-rgb101010-draw-pwrite
+kms_frontbuffer_tracking@psr-rgb565-draw-blt
+kms_frontbuffer_tracking@psr-rgb101010-draw-blt
+kms_frontbuffer_tracking@psr-rgb565-draw-render
+kms_frontbuffer_tracking@psr-rgb101010-draw-render
+kms_frontbuffer_tracking@fbcpsr-rgb565-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsr-rgb101010-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsr-rgb565-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsr-rgb101010-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsr-rgb565-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsr-rgb101010-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsr-rgb565-draw-pwrite
+kms_frontbuffer_tracking@fbcpsr-rgb101010-draw-pwrite
+kms_frontbuffer_tracking@fbcpsr-rgb565-draw-blt
+kms_frontbuffer_tracking@fbcpsr-rgb101010-draw-blt
+kms_frontbuffer_tracking@fbcpsr-rgb565-draw-render
+kms_frontbuffer_tracking@fbcpsr-rgb101010-draw-render
+kms_frontbuffer_tracking@drrs-rgb565-draw-mmap-cpu
+kms_frontbuffer_tracking@drrs-rgb101010-draw-mmap-cpu
+kms_frontbuffer_tracking@drrs-rgb565-draw-mmap-gtt
+kms_frontbuffer_tracking@drrs-rgb101010-draw-mmap-gtt
+kms_frontbuffer_tracking@drrs-rgb565-draw-mmap-wc
+kms_frontbuffer_tracking@drrs-rgb101010-draw-mmap-wc
+kms_frontbuffer_tracking@drrs-rgb565-draw-pwrite
+kms_frontbuffer_tracking@drrs-rgb101010-draw-pwrite
+kms_frontbuffer_tracking@drrs-rgb565-draw-blt
+kms_frontbuffer_tracking@drrs-rgb101010-draw-blt
+kms_frontbuffer_tracking@drrs-rgb565-draw-render
+kms_frontbuffer_tracking@drrs-rgb101010-draw-render
+kms_frontbuffer_tracking@fbcdrrs-rgb565-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcdrrs-rgb101010-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcdrrs-rgb565-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcdrrs-rgb101010-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcdrrs-rgb565-draw-mmap-wc
+kms_frontbuffer_tracking@fbcdrrs-rgb101010-draw-mmap-wc
+kms_frontbuffer_tracking@fbcdrrs-rgb565-draw-pwrite
+kms_frontbuffer_tracking@fbcdrrs-rgb101010-draw-pwrite
+kms_frontbuffer_tracking@fbcdrrs-rgb565-draw-blt
+kms_frontbuffer_tracking@fbcdrrs-rgb101010-draw-blt
+kms_frontbuffer_tracking@fbcdrrs-rgb565-draw-render
+kms_frontbuffer_tracking@fbcdrrs-rgb101010-draw-render
+kms_frontbuffer_tracking@psrdrrs-rgb565-draw-mmap-cpu
+kms_frontbuffer_tracking@psrdrrs-rgb101010-draw-mmap-cpu
+kms_frontbuffer_tracking@psrdrrs-rgb565-draw-mmap-gtt
+kms_frontbuffer_tracking@psrdrrs-rgb101010-draw-mmap-gtt
+kms_frontbuffer_tracking@psrdrrs-rgb565-draw-mmap-wc
+kms_frontbuffer_tracking@psrdrrs-rgb101010-draw-mmap-wc
+kms_frontbuffer_tracking@psrdrrs-rgb565-draw-pwrite
+kms_frontbuffer_tracking@psrdrrs-rgb101010-draw-pwrite
+kms_frontbuffer_tracking@psrdrrs-rgb565-draw-blt
+kms_frontbuffer_tracking@psrdrrs-rgb101010-draw-blt
+kms_frontbuffer_tracking@psrdrrs-rgb565-draw-render
+kms_frontbuffer_tracking@psrdrrs-rgb101010-draw-render
+kms_frontbuffer_tracking@fbcpsrdrrs-rgb565-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsrdrrs-rgb101010-draw-mmap-cpu
+kms_frontbuffer_tracking@fbcpsrdrrs-rgb565-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsrdrrs-rgb101010-draw-mmap-gtt
+kms_frontbuffer_tracking@fbcpsrdrrs-rgb565-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsrdrrs-rgb101010-draw-mmap-wc
+kms_frontbuffer_tracking@fbcpsrdrrs-rgb565-draw-pwrite
+kms_frontbuffer_tracking@fbcpsrdrrs-rgb101010-draw-pwrite
+kms_frontbuffer_tracking@fbcpsrdrrs-rgb565-draw-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-rgb101010-draw-blt
+kms_frontbuffer_tracking@fbcpsrdrrs-rgb565-draw-render
+kms_frontbuffer_tracking@fbcpsrdrrs-rgb101010-draw-render
+kms_frontbuffer_tracking@fbc-indfb-scaledprimary
+kms_frontbuffer_tracking@fbc-shrfb-scaledprimary
+kms_frontbuffer_tracking@psr-indfb-scaledprimary
+kms_frontbuffer_tracking@psr-shrfb-scaledprimary
+kms_frontbuffer_tracking@fbcpsr-indfb-scaledprimary
+kms_frontbuffer_tracking@fbcpsr-shrfb-scaledprimary
+kms_frontbuffer_tracking@drrs-indfb-scaledprimary
+kms_frontbuffer_tracking@drrs-shrfb-scaledprimary
+kms_frontbuffer_tracking@fbcdrrs-indfb-scaledprimary
+kms_frontbuffer_tracking@fbcdrrs-shrfb-scaledprimary
+kms_frontbuffer_tracking@psrdrrs-indfb-scaledprimary
+kms_frontbuffer_tracking@psrdrrs-shrfb-scaledprimary
+kms_frontbuffer_tracking@fbcpsrdrrs-indfb-scaledprimary
+kms_frontbuffer_tracking@fbcpsrdrrs-shrfb-scaledprimary
+kms_frontbuffer_tracking@fbc-modesetfrombusy
+kms_frontbuffer_tracking@fbc-badstride
+kms_frontbuffer_tracking@fbc-stridechange
+kms_frontbuffer_tracking@fbc-tiling-linear
+kms_frontbuffer_tracking@fbc-tiling-y
+kms_frontbuffer_tracking@fbc-tiling-4
+kms_frontbuffer_tracking@fbc-suspend
+kms_frontbuffer_tracking@psr-modesetfrombusy
+kms_frontbuffer_tracking@psr-slowdraw
+kms_frontbuffer_tracking@psr-suspend
+kms_frontbuffer_tracking@fbcpsr-modesetfrombusy
+kms_frontbuffer_tracking@fbcpsr-badstride
+kms_frontbuffer_tracking@fbcpsr-stridechange
+kms_frontbuffer_tracking@fbcpsr-tiling-linear
+kms_frontbuffer_tracking@fbcpsr-tiling-y
+kms_frontbuffer_tracking@fbcpsr-tiling-4
+kms_frontbuffer_tracking@fbcpsr-slowdraw
+kms_frontbuffer_tracking@fbcpsr-suspend
+kms_frontbuffer_tracking@drrs-modesetfrombusy
+kms_frontbuffer_tracking@drrs-slowdraw
+kms_frontbuffer_tracking@drrs-suspend
+kms_frontbuffer_tracking@fbcdrrs-modesetfrombusy
+kms_frontbuffer_tracking@fbcdrrs-badstride
+kms_frontbuffer_tracking@fbcdrrs-stridechange
+kms_frontbuffer_tracking@fbcdrrs-tiling-linear
+kms_frontbuffer_tracking@fbcdrrs-tiling-y
+kms_frontbuffer_tracking@fbcdrrs-tiling-4
+kms_frontbuffer_tracking@fbcdrrs-slowdraw
+kms_frontbuffer_tracking@fbcdrrs-suspend
+kms_frontbuffer_tracking@psrdrrs-modesetfrombusy
+kms_frontbuffer_tracking@psrdrrs-slowdraw
+kms_frontbuffer_tracking@psrdrrs-suspend
+kms_frontbuffer_tracking@fbcpsrdrrs-modesetfrombusy
+kms_frontbuffer_tracking@fbcpsrdrrs-badstride
+kms_frontbuffer_tracking@fbcpsrdrrs-stridechange
+kms_frontbuffer_tracking@fbcpsrdrrs-tiling-linear
+kms_frontbuffer_tracking@fbcpsrdrrs-tiling-y
+kms_frontbuffer_tracking@fbcpsrdrrs-tiling-4
+kms_frontbuffer_tracking@fbcpsrdrrs-slowdraw
+kms_frontbuffer_tracking@fbcpsrdrrs-suspend
+kms_frontbuffer_tracking@basic
+kms_getfb@getfb-handle-zero
+kms_getfb@getfb-handle-valid
+kms_getfb@getfb-handle-closed
+kms_getfb@getfb-handle-not-fb
+kms_getfb@getfb-addfb-different-handles
+kms_getfb@getfb-repeated-different-handles
+kms_getfb@getfb-reject-ccs
+kms_getfb@getfb2-handle-zero
+kms_getfb@getfb2-handle-closed
+kms_getfb@getfb2-handle-not-fb
+kms_getfb@getfb2-accept-ccs
+kms_getfb@getfb2-into-addfb2
+kms_getfb@getfb-handle-protection
+kms_getfb@getfb2-handle-protection
+kms_hdmi_inject@inject-4k
+kms_hdmi_inject@inject-audio
+kms_hdr@bpc-switch
+kms_hdr@bpc-switch-dpms
+kms_hdr@bpc-switch-suspend
+kms_hdr@static-toggle
+kms_hdr@static-toggle-dpms
+kms_hdr@static-toggle-suspend
+kms_hdr@static-swap
+kms_hdr@invalid-metadata-sizes
+kms_hdr@invalid-hdr
+kms_invalid_mode@clock-too-high
+kms_invalid_mode@zero-clock
+kms_invalid_mode@int-max-clock
+kms_invalid_mode@uint-max-clock
+kms_invalid_mode@zero-hdisplay
+kms_invalid_mode@zero-vdisplay
+kms_invalid_mode@bad-hsync-start
+kms_invalid_mode@bad-vsync-start
+kms_invalid_mode@bad-hsync-end
+kms_invalid_mode@bad-vsync-end
+kms_invalid_mode@bad-htotal
+kms_invalid_mode@bad-vtotal
+kms_legacy_colorkey@basic
+kms_legacy_colorkey@invalid-plane
+kms_multipipe_modeset@basic-max-pipe-crc-check
+kms_panel_fitting@legacy
+kms_panel_fitting@atomic-fastset
+kms_pipe_b_c_ivb@pipe-B-dpms-off-modeset-pipe-C
+kms_pipe_b_c_ivb@pipe-B-double-modeset-then-modeset-pipe-C
+kms_pipe_b_c_ivb@disable-pipe-B-enable-pipe-C
+kms_pipe_b_c_ivb@from-pipe-C-to-B-with-3-lanes
+kms_pipe_b_c_ivb@enable-pipe-C-while-B-has-3-lanes
+kms_pipe_crc_basic@bad-source
+kms_pipe_crc_basic@read-crc
+kms_pipe_crc_basic@read-crc-frame-sequence
+kms_pipe_crc_basic@nonblocking-crc
+kms_pipe_crc_basic@nonblocking-crc-frame-sequence
+kms_pipe_crc_basic@suspend-read-crc
+kms_pipe_crc_basic@hang-read-crc
+kms_pipe_crc_basic@disable-crc-after-crtc
+kms_pipe_crc_basic@compare-crc-sanitycheck-xr24
+kms_pipe_crc_basic@compare-crc-sanitycheck-nv12
+kms_plane@pixel-format
+kms_plane@pixel-format-source-clamping
+kms_plane@plane-position-covered
+kms_plane@plane-position-hole
+kms_plane@plane-position-hole-dpms
+kms_plane@plane-panning-top-left
+kms_plane@plane-panning-bottom-right
+kms_plane@plane-panning-bottom-right-suspend
+kms_plane@invalid-pixel-format-settings
+kms_plane_alpha_blend@alpha-basic
+kms_plane_alpha_blend@alpha-7efc
+kms_plane_alpha_blend@coverage-7efc
+kms_plane_alpha_blend@coverage-vs-premult-vs-constant
+kms_plane_alpha_blend@alpha-transparent-fb
+kms_plane_alpha_blend@alpha-opaque-fb
+kms_plane_alpha_blend@constant-alpha-min
+kms_plane_alpha_blend@constant-alpha-mid
+kms_plane_alpha_blend@constant-alpha-max
+kms_plane_cursor@primary
+kms_plane_cursor@overlay
+kms_plane_cursor@viewport
+kms_plane_lowres@tiling-none
+kms_plane_lowres@tiling-x
+kms_plane_lowres@tiling-y
+kms_plane_lowres@tiling-yf
+kms_plane_lowres@tiling-4
+kms_plane_multiple@tiling-none
+kms_plane_multiple@tiling-x
+kms_plane_multiple@tiling-y
+kms_plane_multiple@tiling-yf
+kms_plane_multiple@tiling-4
+kms_plane_scaling@plane-upscale-with-pixel-format-20x20
+kms_plane_scaling@plane-upscale-with-pixel-format-factor-0-25
+kms_plane_scaling@plane-downscale-with-pixel-format-factor-0-25
+kms_plane_scaling@plane-downscale-with-pixel-format-factor-0-5
+kms_plane_scaling@plane-downscale-with-pixel-format-factor-0-75
+kms_plane_scaling@plane-scaler-with-pixel-format-unity-scaling
+kms_plane_scaling@plane-upscale-with-rotation-20x20
+kms_plane_scaling@plane-upscale-with-rotation-factor-0-25
+kms_plane_scaling@plane-downscale-with-rotation-factor-0-25
+kms_plane_scaling@plane-downscale-with-rotation-factor-0-5
+kms_plane_scaling@plane-downscale-with-rotation-factor-0-75
+kms_plane_scaling@plane-scaler-with-rotation-unity-scaling
+kms_plane_scaling@plane-upscale-with-modifiers-20x20
+kms_plane_scaling@plane-upscale-with-modifiers-factor-0-25
+kms_plane_scaling@plane-downscale-with-modifiers-factor-0-25
+kms_plane_scaling@plane-downscale-with-modifiers-factor-0-5
+kms_plane_scaling@plane-downscale-with-modifiers-factor-0-75
+kms_plane_scaling@plane-scaler-with-modifiers-unity-scaling
+kms_plane_scaling@plane-scaler-with-clipping-clamping-pixel-formats
+kms_plane_scaling@plane-scaler-with-clipping-clamping-rotation
+kms_plane_scaling@plane-scaler-with-clipping-clamping-modifiers
+kms_plane_scaling@planes-upscale-20x20
+kms_plane_scaling@planes-upscale-factor-0-25
+kms_plane_scaling@planes-scaler-unity-scaling
+kms_plane_scaling@planes-downscale-factor-0-25
+kms_plane_scaling@planes-downscale-factor-0-5
+kms_plane_scaling@planes-downscale-factor-0-75
+kms_plane_scaling@planes-upscale-20x20-downscale-factor-0-25
+kms_plane_scaling@planes-upscale-20x20-downscale-factor-0-5
+kms_plane_scaling@planes-upscale-20x20-downscale-factor-0-75
+kms_plane_scaling@planes-upscale-factor-0-25-downscale-factor-0-25
+kms_plane_scaling@planes-upscale-factor-0-25-downscale-factor-0-5
+kms_plane_scaling@planes-upscale-factor-0-25-downscale-factor-0-75
+kms_plane_scaling@planes-unity-scaling-downscale-factor-0-25
+kms_plane_scaling@planes-unity-scaling-downscale-factor-0-5
+kms_plane_scaling@planes-unity-scaling-downscale-factor-0-75
+kms_plane_scaling@planes-downscale-factor-0-25-upscale-20x20
+kms_plane_scaling@planes-downscale-factor-0-25-upscale-factor-0-25
+kms_plane_scaling@planes-downscale-factor-0-25-unity-scaling
+kms_plane_scaling@planes-downscale-factor-0-5-upscale-20x20
+kms_plane_scaling@planes-downscale-factor-0-5-upscale-factor-0-25
+kms_plane_scaling@planes-downscale-factor-0-5-unity-scaling
+kms_plane_scaling@planes-downscale-factor-0-75-upscale-20x20
+kms_plane_scaling@planes-downscale-factor-0-75-upscale-factor-0-25
+kms_plane_scaling@planes-downscale-factor-0-75-unity-scaling
+kms_plane_scaling@intel-max-src-size
+kms_plane_scaling@invalid-num-scalers
+kms_plane_scaling@invalid-parameters
+kms_plane_scaling@2x-scaler-multi-pipe
+kms_prime@basic-crc-hybrid
+kms_prime@basic-modeset-hybrid
+kms_prime@D3hot
+kms_prime@basic-crc-vgem
+kms_prop_blob@basic
+kms_prop_blob@blob-prop-core
+kms_prop_blob@blob-prop-validate
+kms_prop_blob@blob-prop-lifetime
+kms_prop_blob@blob-multiple
+kms_prop_blob@invalid-get-prop-any
+kms_prop_blob@invalid-get-prop
+kms_prop_blob@invalid-set-prop-any
+kms_prop_blob@invalid-set-prop
+kms_properties@plane-properties-legacy
+kms_properties@plane-properties-atomic
+kms_properties@crtc-properties-legacy
+kms_properties@crtc-properties-atomic
+kms_properties@connector-properties-legacy
+kms_properties@connector-properties-atomic
+kms_properties@invalid-properties-legacy
+kms_properties@invalid-properties-atomic
+kms_properties@get_properties-sanity-atomic
+kms_properties@get_properties-sanity-non-atomic
+kms_psr@basic
+kms_psr@no_drrs
+kms_psr@primary_page_flip
+kms_psr@primary_mmap_gtt
+kms_psr@primary_mmap_cpu
+kms_psr@primary_blt
+kms_psr@primary_render
+kms_psr@sprite_mmap_gtt
+kms_psr@cursor_mmap_gtt
+kms_psr@sprite_mmap_cpu
+kms_psr@cursor_mmap_cpu
+kms_psr@sprite_blt
+kms_psr@cursor_blt
+kms_psr@sprite_render
+kms_psr@cursor_render
+kms_psr@sprite_plane_move
+kms_psr@cursor_plane_move
+kms_psr@sprite_plane_onoff
+kms_psr@cursor_plane_onoff
+kms_psr@dpms
+kms_psr@suspend
+kms_psr@psr2_basic
+kms_psr@psr2_no_drrs
+kms_psr@psr2_primary_page_flip
+kms_psr@psr2_primary_mmap_gtt
+kms_psr@psr2_primary_mmap_cpu
+kms_psr@psr2_primary_blt
+kms_psr@psr2_primary_render
+kms_psr@psr2_sprite_mmap_gtt
+kms_psr@psr2_cursor_mmap_gtt
+kms_psr@psr2_sprite_mmap_cpu
+kms_psr@psr2_cursor_mmap_cpu
+kms_psr@psr2_sprite_blt
+kms_psr@psr2_cursor_blt
+kms_psr@psr2_sprite_render
+kms_psr@psr2_cursor_render
+kms_psr@psr2_sprite_plane_move
+kms_psr@psr2_cursor_plane_move
+kms_psr@psr2_sprite_plane_onoff
+kms_psr@psr2_cursor_plane_onoff
+kms_psr@psr2_dpms
+kms_psr@psr2_suspend
+kms_psr2_sf@primary-plane-update-sf-dmg-area
+kms_psr2_sf@primary-plane-update-sf-dmg-area-big-fb
+kms_psr2_sf@overlay-plane-update-sf-dmg-area
+kms_psr2_sf@cursor-plane-update-sf
+kms_psr2_sf@cursor-plane-move-continuous-sf
+kms_psr2_sf@cursor-plane-move-continuous-exceed-sf
+kms_psr2_sf@cursor-plane-move-continuous-exceed-fully-sf
+kms_psr2_sf@plane-move-sf-dmg-area
+kms_psr2_sf@overlay-plane-move-continuous-sf
+kms_psr2_sf@overlay-plane-move-continuous-exceed-sf
+kms_psr2_sf@overlay-plane-move-continuous-exceed-fully-sf
+kms_psr2_sf@overlay-primary-update-sf-dmg-area
+kms_psr2_sf@overlay-plane-update-continuous-sf
+kms_psr2_su@page_flip-XRGB8888
+kms_psr2_su@page_flip-NV12
+kms_psr2_su@page_flip-P010
+kms_psr2_su@frontbuffer-XRGB8888
+kms_pwrite_crc
+kms_rmfb@rmfb-ioctl
+kms_rmfb@close-fd
+kms_rotation_crc@primary-rotation-90
+kms_rotation_crc@primary-rotation-180
+kms_rotation_crc@primary-rotation-270
+kms_rotation_crc@sprite-rotation-90
+kms_rotation_crc@sprite-rotation-180
+kms_rotation_crc@sprite-rotation-270
+kms_rotation_crc@cursor-rotation-180
+kms_rotation_crc@sprite-rotation-90-pos-100-0
+kms_rotation_crc@bad-pixel-format
+kms_rotation_crc@bad-tiling
+kms_rotation_crc@primary-x-tiled-reflect-x-0
+kms_rotation_crc@primary-x-tiled-reflect-x-180
+kms_rotation_crc@primary-y-tiled-reflect-x-0
+kms_rotation_crc@primary-y-tiled-reflect-x-90
+kms_rotation_crc@primary-y-tiled-reflect-x-180
+kms_rotation_crc@primary-y-tiled-reflect-x-270
+kms_rotation_crc@primary-yf-tiled-reflect-x-0
+kms_rotation_crc@primary-yf-tiled-reflect-x-90
+kms_rotation_crc@primary-yf-tiled-reflect-x-180
+kms_rotation_crc@primary-yf-tiled-reflect-x-270
+kms_rotation_crc@primary-4-tiled-reflect-x-0
+kms_rotation_crc@primary-4-tiled-reflect-x-180
+kms_rotation_crc@multiplane-rotation
+kms_rotation_crc@multiplane-rotation-cropping-top
+kms_rotation_crc@multiplane-rotation-cropping-bottom
+kms_rotation_crc@exhaust-fences
+kms_scaling_modes@scaling-mode-full
+kms_scaling_modes@scaling-mode-center
+kms_scaling_modes@scaling-mode-full-aspect
+kms_scaling_modes@scaling-mode-none
+kms_selftest@drm_cmdline
+kms_selftest@drm_damage
+kms_selftest@drm_dp_mst
+kms_selftest@drm_format_helper
+kms_selftest@drm_format
+kms_selftest@framebuffer
+kms_selftest@drm_plane
+kms_setmode@basic
+kms_setmode@basic-clone-single-crtc
+kms_setmode@invalid-clone-single-crtc
+kms_setmode@invalid-clone-exclusive-crtc
+kms_setmode@clone-exclusive-crtc
+kms_setmode@invalid-clone-single-crtc-stealing
+kms_sysfs_edid_timing
+kms_tv_load_detect@load-detect
+kms_universal_plane@universal-plane-pipe-A-functional
+kms_universal_plane@universal-plane-pipe-A-sanity
+kms_universal_plane@disable-primary-vs-flip-pipe-A
+kms_universal_plane@cursor-fb-leak-pipe-A
+kms_universal_plane@universal-plane-pageflip-windowed-pipe-A
+kms_universal_plane@universal-plane-pipe-B-functional
+kms_universal_plane@universal-plane-pipe-B-sanity
+kms_universal_plane@disable-primary-vs-flip-pipe-B
+kms_universal_plane@cursor-fb-leak-pipe-B
+kms_universal_plane@universal-plane-pageflip-windowed-pipe-B
+kms_universal_plane@universal-plane-pipe-C-functional
+kms_universal_plane@universal-plane-pipe-C-sanity
+kms_universal_plane@disable-primary-vs-flip-pipe-C
+kms_universal_plane@cursor-fb-leak-pipe-C
+kms_universal_plane@universal-plane-pageflip-windowed-pipe-C
+kms_universal_plane@universal-plane-pipe-D-functional
+kms_universal_plane@universal-plane-pipe-D-sanity
+kms_universal_plane@disable-primary-vs-flip-pipe-D
+kms_universal_plane@cursor-fb-leak-pipe-D
+kms_universal_plane@universal-plane-pageflip-windowed-pipe-D
+kms_universal_plane@universal-plane-pipe-E-functional
+kms_universal_plane@universal-plane-pipe-E-sanity
+kms_universal_plane@disable-primary-vs-flip-pipe-E
+kms_universal_plane@cursor-fb-leak-pipe-E
+kms_universal_plane@universal-plane-pageflip-windowed-pipe-E
+kms_universal_plane@universal-plane-pipe-F-functional
+kms_universal_plane@universal-plane-pipe-F-sanity
+kms_universal_plane@disable-primary-vs-flip-pipe-F
+kms_universal_plane@cursor-fb-leak-pipe-F
+kms_universal_plane@universal-plane-pageflip-windowed-pipe-F
+kms_universal_plane@universal-plane-pipe-G-functional
+kms_universal_plane@universal-plane-pipe-G-sanity
+kms_universal_plane@disable-primary-vs-flip-pipe-G
+kms_universal_plane@cursor-fb-leak-pipe-G
+kms_universal_plane@universal-plane-pageflip-windowed-pipe-G
+kms_universal_plane@universal-plane-pipe-H-functional
+kms_universal_plane@universal-plane-pipe-H-sanity
+kms_universal_plane@disable-primary-vs-flip-pipe-H
+kms_universal_plane@cursor-fb-leak-pipe-H
+kms_universal_plane@universal-plane-pageflip-windowed-pipe-H
+kms_vblank@invalid
+kms_vblank@crtc-id
+kms_vblank@pipe-A-accuracy-idle
+kms_vblank@pipe-A-query-idle
+kms_vblank@pipe-A-query-idle-hang
+kms_vblank@pipe-A-query-forked
+kms_vblank@pipe-A-query-forked-hang
+kms_vblank@pipe-A-query-busy
+kms_vblank@pipe-A-query-busy-hang
+kms_vblank@pipe-A-query-forked-busy
+kms_vblank@pipe-A-query-forked-busy-hang
+kms_vblank@pipe-A-wait-idle
+kms_vblank@pipe-A-wait-idle-hang
+kms_vblank@pipe-A-wait-forked
+kms_vblank@pipe-A-wait-forked-hang
+kms_vblank@pipe-A-wait-busy
+kms_vblank@pipe-A-wait-busy-hang
+kms_vblank@pipe-A-wait-forked-busy
+kms_vblank@pipe-A-wait-forked-busy-hang
+kms_vblank@pipe-A-ts-continuation-idle
+kms_vblank@pipe-A-ts-continuation-idle-hang
+kms_vblank@pipe-A-ts-continuation-dpms-rpm
+kms_vblank@pipe-A-ts-continuation-dpms-suspend
+kms_vblank@pipe-A-ts-continuation-suspend
+kms_vblank@pipe-A-ts-continuation-modeset
+kms_vblank@pipe-A-ts-continuation-modeset-hang
+kms_vblank@pipe-A-ts-continuation-modeset-rpm
+kms_vblank@pipe-B-accuracy-idle
+kms_vblank@pipe-B-query-idle
+kms_vblank@pipe-B-query-idle-hang
+kms_vblank@pipe-B-query-forked
+kms_vblank@pipe-B-query-forked-hang
+kms_vblank@pipe-B-query-busy
+kms_vblank@pipe-B-query-busy-hang
+kms_vblank@pipe-B-query-forked-busy
+kms_vblank@pipe-B-query-forked-busy-hang
+kms_vblank@pipe-B-wait-idle
+kms_vblank@pipe-B-wait-idle-hang
+kms_vblank@pipe-B-wait-forked
+kms_vblank@pipe-B-wait-forked-hang
+kms_vblank@pipe-B-wait-busy
+kms_vblank@pipe-B-wait-busy-hang
+kms_vblank@pipe-B-wait-forked-busy
+kms_vblank@pipe-B-wait-forked-busy-hang
+kms_vblank@pipe-B-ts-continuation-idle
+kms_vblank@pipe-B-ts-continuation-idle-hang
+kms_vblank@pipe-B-ts-continuation-dpms-rpm
+kms_vblank@pipe-B-ts-continuation-dpms-suspend
+kms_vblank@pipe-B-ts-continuation-suspend
+kms_vblank@pipe-B-ts-continuation-modeset
+kms_vblank@pipe-B-ts-continuation-modeset-hang
+kms_vblank@pipe-B-ts-continuation-modeset-rpm
+kms_vblank@pipe-C-accuracy-idle
+kms_vblank@pipe-C-query-idle
+kms_vblank@pipe-C-query-idle-hang
+kms_vblank@pipe-C-query-forked
+kms_vblank@pipe-C-query-forked-hang
+kms_vblank@pipe-C-query-busy
+kms_vblank@pipe-C-query-busy-hang
+kms_vblank@pipe-C-query-forked-busy
+kms_vblank@pipe-C-query-forked-busy-hang
+kms_vblank@pipe-C-wait-idle
+kms_vblank@pipe-C-wait-idle-hang
+kms_vblank@pipe-C-wait-forked
+kms_vblank@pipe-C-wait-forked-hang
+kms_vblank@pipe-C-wait-busy
+kms_vblank@pipe-C-wait-busy-hang
+kms_vblank@pipe-C-wait-forked-busy
+kms_vblank@pipe-C-wait-forked-busy-hang
+kms_vblank@pipe-C-ts-continuation-idle
+kms_vblank@pipe-C-ts-continuation-idle-hang
+kms_vblank@pipe-C-ts-continuation-dpms-rpm
+kms_vblank@pipe-C-ts-continuation-dpms-suspend
+kms_vblank@pipe-C-ts-continuation-suspend
+kms_vblank@pipe-C-ts-continuation-modeset
+kms_vblank@pipe-C-ts-continuation-modeset-hang
+kms_vblank@pipe-C-ts-continuation-modeset-rpm
+kms_vblank@pipe-D-accuracy-idle
+kms_vblank@pipe-D-query-idle
+kms_vblank@pipe-D-query-idle-hang
+kms_vblank@pipe-D-query-forked
+kms_vblank@pipe-D-query-forked-hang
+kms_vblank@pipe-D-query-busy
+kms_vblank@pipe-D-query-busy-hang
+kms_vblank@pipe-D-query-forked-busy
+kms_vblank@pipe-D-query-forked-busy-hang
+kms_vblank@pipe-D-wait-idle
+kms_vblank@pipe-D-wait-idle-hang
+kms_vblank@pipe-D-wait-forked
+kms_vblank@pipe-D-wait-forked-hang
+kms_vblank@pipe-D-wait-busy
+kms_vblank@pipe-D-wait-busy-hang
+kms_vblank@pipe-D-wait-forked-busy
+kms_vblank@pipe-D-wait-forked-busy-hang
+kms_vblank@pipe-D-ts-continuation-idle
+kms_vblank@pipe-D-ts-continuation-idle-hang
+kms_vblank@pipe-D-ts-continuation-dpms-rpm
+kms_vblank@pipe-D-ts-continuation-dpms-suspend
+kms_vblank@pipe-D-ts-continuation-suspend
+kms_vblank@pipe-D-ts-continuation-modeset
+kms_vblank@pipe-D-ts-continuation-modeset-hang
+kms_vblank@pipe-D-ts-continuation-modeset-rpm
+kms_vblank@pipe-E-accuracy-idle
+kms_vblank@pipe-E-query-idle
+kms_vblank@pipe-E-query-idle-hang
+kms_vblank@pipe-E-query-forked
+kms_vblank@pipe-E-query-forked-hang
+kms_vblank@pipe-E-query-busy
+kms_vblank@pipe-E-query-busy-hang
+kms_vblank@pipe-E-query-forked-busy
+kms_vblank@pipe-E-query-forked-busy-hang
+kms_vblank@pipe-E-wait-idle
+kms_vblank@pipe-E-wait-idle-hang
+kms_vblank@pipe-E-wait-forked
+kms_vblank@pipe-E-wait-forked-hang
+kms_vblank@pipe-E-wait-busy
+kms_vblank@pipe-E-wait-busy-hang
+kms_vblank@pipe-E-wait-forked-busy
+kms_vblank@pipe-E-wait-forked-busy-hang
+kms_vblank@pipe-E-ts-continuation-idle
+kms_vblank@pipe-E-ts-continuation-idle-hang
+kms_vblank@pipe-E-ts-continuation-dpms-rpm
+kms_vblank@pipe-E-ts-continuation-dpms-suspend
+kms_vblank@pipe-E-ts-continuation-suspend
+kms_vblank@pipe-E-ts-continuation-modeset
+kms_vblank@pipe-E-ts-continuation-modeset-hang
+kms_vblank@pipe-E-ts-continuation-modeset-rpm
+kms_vblank@pipe-F-accuracy-idle
+kms_vblank@pipe-F-query-idle
+kms_vblank@pipe-F-query-idle-hang
+kms_vblank@pipe-F-query-forked
+kms_vblank@pipe-F-query-forked-hang
+kms_vblank@pipe-F-query-busy
+kms_vblank@pipe-F-query-busy-hang
+kms_vblank@pipe-F-query-forked-busy
+kms_vblank@pipe-F-query-forked-busy-hang
+kms_vblank@pipe-F-wait-idle
+kms_vblank@pipe-F-wait-idle-hang
+kms_vblank@pipe-F-wait-forked
+kms_vblank@pipe-F-wait-forked-hang
+kms_vblank@pipe-F-wait-busy
+kms_vblank@pipe-F-wait-busy-hang
+kms_vblank@pipe-F-wait-forked-busy
+kms_vblank@pipe-F-wait-forked-busy-hang
+kms_vblank@pipe-F-ts-continuation-idle
+kms_vblank@pipe-F-ts-continuation-idle-hang
+kms_vblank@pipe-F-ts-continuation-dpms-rpm
+kms_vblank@pipe-F-ts-continuation-dpms-suspend
+kms_vblank@pipe-F-ts-continuation-suspend
+kms_vblank@pipe-F-ts-continuation-modeset
+kms_vblank@pipe-F-ts-continuation-modeset-hang
+kms_vblank@pipe-F-ts-continuation-modeset-rpm
+kms_vblank@pipe-G-accuracy-idle
+kms_vblank@pipe-G-query-idle
+kms_vblank@pipe-G-query-idle-hang
+kms_vblank@pipe-G-query-forked
+kms_vblank@pipe-G-query-forked-hang
+kms_vblank@pipe-G-query-busy
+kms_vblank@pipe-G-query-busy-hang
+kms_vblank@pipe-G-query-forked-busy
+kms_vblank@pipe-G-query-forked-busy-hang
+kms_vblank@pipe-G-wait-idle
+kms_vblank@pipe-G-wait-idle-hang
+kms_vblank@pipe-G-wait-forked
+kms_vblank@pipe-G-wait-forked-hang
+kms_vblank@pipe-G-wait-busy
+kms_vblank@pipe-G-wait-busy-hang
+kms_vblank@pipe-G-wait-forked-busy
+kms_vblank@pipe-G-wait-forked-busy-hang
+kms_vblank@pipe-G-ts-continuation-idle
+kms_vblank@pipe-G-ts-continuation-idle-hang
+kms_vblank@pipe-G-ts-continuation-dpms-rpm
+kms_vblank@pipe-G-ts-continuation-dpms-suspend
+kms_vblank@pipe-G-ts-continuation-suspend
+kms_vblank@pipe-G-ts-continuation-modeset
+kms_vblank@pipe-G-ts-continuation-modeset-hang
+kms_vblank@pipe-G-ts-continuation-modeset-rpm
+kms_vblank@pipe-H-accuracy-idle
+kms_vblank@pipe-H-query-idle
+kms_vblank@pipe-H-query-idle-hang
+kms_vblank@pipe-H-query-forked
+kms_vblank@pipe-H-query-forked-hang
+kms_vblank@pipe-H-query-busy
+kms_vblank@pipe-H-query-busy-hang
+kms_vblank@pipe-H-query-forked-busy
+kms_vblank@pipe-H-query-forked-busy-hang
+kms_vblank@pipe-H-wait-idle
+kms_vblank@pipe-H-wait-idle-hang
+kms_vblank@pipe-H-wait-forked
+kms_vblank@pipe-H-wait-forked-hang
+kms_vblank@pipe-H-wait-busy
+kms_vblank@pipe-H-wait-busy-hang
+kms_vblank@pipe-H-wait-forked-busy
+kms_vblank@pipe-H-wait-forked-busy-hang
+kms_vblank@pipe-H-ts-continuation-idle
+kms_vblank@pipe-H-ts-continuation-idle-hang
+kms_vblank@pipe-H-ts-continuation-dpms-rpm
+kms_vblank@pipe-H-ts-continuation-dpms-suspend
+kms_vblank@pipe-H-ts-continuation-suspend
+kms_vblank@pipe-H-ts-continuation-modeset
+kms_vblank@pipe-H-ts-continuation-modeset-hang
+kms_vblank@pipe-H-ts-continuation-modeset-rpm
+kms_vrr@flip-basic
+kms_vrr@flip-dpms
+kms_vrr@flip-suspend
+kms_vrr@flipline
+kms_vrr@negative-basic
+kms_writeback@writeback-pixel-formats
+kms_writeback@writeback-invalid-parameters
+kms_writeback@writeback-fb-id
+kms_writeback@writeback-check-output
+prime_mmap_kms@buffer-sharing
diff --git a/drivers/gpu/drm/ci/x86_64.config b/drivers/gpu/drm/ci/x86_64.config
new file mode 100644
index 000000000000..1cbd49a5b23a
--- /dev/null
+++ b/drivers/gpu/drm/ci/x86_64.config
@@ -0,0 +1,111 @@
+CONFIG_LOCALVERSION_AUTO=y
+CONFIG_DEBUG_KERNEL=y
+
+CONFIG_CRYPTO_ZSTD=y
+CONFIG_ZRAM_MEMORY_TRACKING=y
+CONFIG_ZRAM_WRITEBACK=y
+CONFIG_ZRAM=y
+CONFIG_ZSMALLOC_STAT=y
+
+CONFIG_PWM=y
+CONFIG_PM_DEVFREQ=y
+CONFIG_OF=y
+CONFIG_CROS_EC=y
+
+# abootimg with a 'dummy' rootfs fails with root=/dev/nfs
+CONFIG_BLK_DEV_INITRD=n
+
+CONFIG_DEVFREQ_GOV_PERFORMANCE=y
+CONFIG_DEVFREQ_GOV_POWERSAVE=y
+CONFIG_DEVFREQ_GOV_USERSPACE=y
+CONFIG_DEVFREQ_GOV_PASSIVE=y
+
+CONFIG_DRM=y
+CONFIG_DRM_PANEL_SIMPLE=y
+CONFIG_PWM_CROS_EC=y
+CONFIG_BACKLIGHT_PWM=y
+
+# Strip out some stuff we don't need for graphics testing, to reduce
+# the build.
+CONFIG_CAN=n
+CONFIG_WIRELESS=n
+CONFIG_RFKILL=n
+CONFIG_WLAN=n
+
+CONFIG_REGULATOR_FAN53555=y
+CONFIG_REGULATOR=y
+
+CONFIG_REGULATOR_VCTRL=y
+
+CONFIG_KASAN=n
+CONFIG_KASAN_INLINE=n
+CONFIG_STACKTRACE=n
+
+CONFIG_TMPFS=y
+
+CONFIG_PROVE_LOCKING=n
+CONFIG_DEBUG_LOCKDEP=n
+CONFIG_SOFTLOCKUP_DETECTOR=y
+CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y
+
+CONFIG_DETECT_HUNG_TASK=y
+
+CONFIG_USB_USBNET=y
+CONFIG_NETDEVICES=y
+CONFIG_USB_NET_DRIVERS=y
+CONFIG_USB_RTL8152=y
+CONFIG_USB_NET_AX8817X=y
+CONFIG_USB_NET_SMSC95XX=y
+CONFIG_USB_GADGET=y
+CONFIG_USB_ETH=y
+
+CONFIG_FW_LOADER_COMPRESS=y
+
+# options for AMD devices
+CONFIG_X86_AMD_PLATFORM_DEVICE=y
+CONFIG_ACPI_VIDEO=y
+CONFIG_X86_AMD_FREQ_SENSITIVITY=y
+CONFIG_PINCTRL=y
+CONFIG_PINCTRL_AMD=y
+CONFIG_DRM_AMDGPU=m
+CONFIG_DRM_AMDGPU_SI=y
+CONFIG_DRM_AMDGPU_USERPTR=y
+CONFIG_DRM_AMD_ACP=n
+CONFIG_ACPI_WMI=y
+CONFIG_MXM_WMI=y
+CONFIG_PARPORT=y
+CONFIG_PARPORT_PC=y
+CONFIG_PARPORT_SERIAL=y
+CONFIG_SERIAL_8250_DW=y
+CONFIG_CHROME_PLATFORMS=y
+CONFIG_KVM_AMD=m
+
+#options for Intel devices
+CONFIG_MFD_INTEL_LPSS_PCI=y
+CONFIG_KVM_INTEL=m
+
+#options for KVM guests
+CONFIG_FUSE_FS=y
+CONFIG_HYPERVISOR_GUEST=y
+CONFIG_KVM=y
+CONFIG_KVM_GUEST=y
+CONFIG_VIRT_DRIVERS=y
+CONFIG_VIRTIO_FS=y
+CONFIG_DRM_VIRTIO_GPU=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_VIRTIO_NET=y
+CONFIG_VIRTIO_CONSOLE=y
+CONFIG_PARAVIRT=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_VIRTUALIZATION=y
+CONFIG_VIRTIO=y
+CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y
+CONFIG_CRYPTO_DEV_VIRTIO=y
+CONFIG_HW_RANDOM_VIRTIO=y
+CONFIG_BLK_MQ_VIRTIO=y
+CONFIG_TUN=y
+CONFIG_VSOCKETS=y
+CONFIG_VIRTIO_VSOCKETS=y
+CONFIG_VHOST_VSOCK=m
diff --git a/drivers/gpu/drm/ci/xfails/amdgpu-stoney-fails.txt b/drivers/gpu/drm/ci/xfails/amdgpu-stoney-fails.txt
new file mode 100644
index 000000000000..bd9392536e7c
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/amdgpu-stoney-fails.txt
@@ -0,0 +1,19 @@
+kms_addfb_basic@bad-pitch-65536,Fail
+kms_addfb_basic@bo-too-small,Fail
+kms_async_flips@invalid-async-flip,Fail
+kms_atomic@plane-immutable-zpos,Fail
+kms_atomic_transition@plane-toggle-modeset-transition,Fail
+kms_bw@linear-tiling-1-displays-2560x1440p,Fail
+kms_bw@linear-tiling-1-displays-3840x2160p,Fail
+kms_bw@linear-tiling-2-displays-3840x2160p,Fail
+kms_bw@linear-tiling-3-displays-1920x1080p,Fail
+kms_color@degamma,Fail
+kms_cursor_crc@cursor-size-change,Fail
+kms_cursor_crc@pipe-A-cursor-size-change,Fail
+kms_cursor_crc@pipe-B-cursor-size-change,Fail
+kms_cursor_legacy@forked-move,Fail
+kms_hdr@bpc-switch,Fail
+kms_hdr@bpc-switch-dpms,Fail
+kms_plane_multiple@atomic-pipe-A-tiling-none,Fail
+kms_rmfb@close-fd,Fail
+kms_rotation_crc@primary-rotation-180,Fail
diff --git a/drivers/gpu/drm/ci/xfails/amdgpu-stoney-flakes.txt b/drivers/gpu/drm/ci/xfails/amdgpu-stoney-flakes.txt
new file mode 100644
index 000000000000..f8defa0f9e67
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/amdgpu-stoney-flakes.txt
@@ -0,0 +1,21 @@
+kms_addfb_basic@too-high
+kms_async_flips@alternate-sync-async-flip
+kms_async_flips@async-flip-with-page-flip-events
+kms_async_flips@crc
+kms_async_flips@test-cursor
+kms_async_flips@test-time-stamp
+kms_atomic_transition@plane-all-modeset-transition-internal-panels
+kms_atomic_transition@plane-all-transition
+kms_atomic_transition@plane-use-after-nonblocking-unbind
+kms_bw@linear-tiling-1-displays-1920x1080p
+kms_bw@linear-tiling-2-displays-1920x1080p
+kms_bw@linear-tiling-2-displays-2560x1440p
+kms_bw@linear-tiling-3-displays-2560x1440p
+kms_bw@linear-tiling-3-displays-3840x2160p
+kms_cursor_crc@pipe-A-cursor-alpha-opaque
+kms_cursor_crc@pipe-B-cursor-alpha-opaque
+kms_plane@pixel-format
+kms_plane_multiple@atomic-pipe-B-tiling-none
+kms_plane_scaling@downscale-with-rotation-factor-0-5
+kms_universal_plane@disable-primary-vs-flip-pipe-A
+kms_universal_plane@disable-primary-vs-flip-pipe-B
diff --git a/drivers/gpu/drm/ci/xfails/amdgpu-stoney-skips.txt b/drivers/gpu/drm/ci/xfails/amdgpu-stoney-skips.txt
new file mode 100644
index 000000000000..e2c538a0f954
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/amdgpu-stoney-skips.txt
@@ -0,0 +1,2 @@
+# Suspend to RAM seems to be broken on this machine
+.*suspend.*
\ No newline at end of file
diff --git a/drivers/gpu/drm/ci/xfails/i915-amly-fails.txt b/drivers/gpu/drm/ci/xfails/i915-amly-fails.txt
new file mode 100644
index 000000000000..5f513c638beb
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/i915-amly-fails.txt
@@ -0,0 +1,17 @@
+kms_flip_scaled_crc@flip-32bpp-linear-to-64bpp-linear-downscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-linear-to-64bpp-linear-upscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-xtile-to-64bpp-xtile-downscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-xtile-to-64bpp-xtile-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-16bpp-linear-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-16bpp-linear-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-32bpp-linear-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-32bpp-linear-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-16bpp-xtile-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-16bpp-xtile-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-32bpp-xtile-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-32bpp-xtile-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytilegen12rcccs-upscaling,Fail
+kms_plane_alpha_blend@alpha-basic,Fail
+kms_plane_alpha_blend@alpha-opaque-fb,Fail
+kms_plane_alpha_blend@alpha-transparent-fb,Fail
+kms_plane_alpha_blend@constant-alpha-max,Fail
diff --git a/drivers/gpu/drm/ci/xfails/i915-amly-flakes.txt b/drivers/gpu/drm/ci/xfails/i915-amly-flakes.txt
new file mode 100644
index 000000000000..d5000515a315
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/i915-amly-flakes.txt
@@ -0,0 +1,32 @@
+kms_bw@linear-tiling-2-displays-1920x1080p
+kms_bw@linear-tiling-2-displays-2560x1440p
+kms_bw@linear-tiling-2-displays-3840x2160p
+kms_bw@linear-tiling-3-displays-1920x1080p
+kms_bw@linear-tiling-3-displays-2560x1440p
+kms_bw@linear-tiling-3-displays-3840x2160p
+kms_bw@linear-tiling-4-displays-1920x1080p
+kms_bw@linear-tiling-4-displays-2560x1440p
+kms_bw@linear-tiling-4-displays-3840x2160p
+kms_flip_scaled_crc@flip-32bpp-ytile-to-64bpp-ytile-downscaling
+kms_flip_scaled_crc@flip-32bpp-ytile-to-64bpp-ytile-upscaling
+kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile-downscaling
+kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile-upscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-16bpp-ytile-downscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-16bpp-ytile-upscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytile-downscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytile-upscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytilercccs-downscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytilercccs-upscaling
+kms_plane_alpha_blend@pipe-A-alpha-basic
+kms_plane_alpha_blend@pipe-A-alpha-opaque-fb
+kms_plane_alpha_blend@pipe-A-alpha-transparent-fb
+kms_plane_alpha_blend@pipe-A-constant-alpha-max
+kms_plane_alpha_blend@pipe-B-alpha-basic
+kms_plane_alpha_blend@pipe-B-alpha-opaque-fb
+kms_plane_alpha_blend@pipe-B-alpha-transparent-fb
+kms_plane_alpha_blend@pipe-B-constant-alpha-max
+kms_plane_alpha_blend@pipe-C-alpha-basic
+kms_plane_alpha_blend@pipe-C-alpha-opaque-fb
+kms_plane_alpha_blend@pipe-C-alpha-transparent-fb
+kms_plane_alpha_blend@pipe-C-constant-alpha-max
+kms_sysfs_edid_timing
diff --git a/drivers/gpu/drm/ci/xfails/i915-amly-skips.txt b/drivers/gpu/drm/ci/xfails/i915-amly-skips.txt
new file mode 100644
index 000000000000..fe55540a3f9a
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/i915-amly-skips.txt
@@ -0,0 +1,4 @@
+# Suspend to RAM seems to be broken on this machine
+.*suspend.*
+# This is generating kernel oops with divide error
+kms_plane_scaling@invalid-parameters
\ No newline at end of file
diff --git a/drivers/gpu/drm/ci/xfails/i915-apl-fails.txt b/drivers/gpu/drm/ci/xfails/i915-apl-fails.txt
new file mode 100644
index 000000000000..46397ce38d5a
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/i915-apl-fails.txt
@@ -0,0 +1,58 @@
+kms_3d,Timeout
+kms_bw@linear-tiling-2-displays-1920x1080p,Fail
+kms_bw@linear-tiling-2-displays-2560x1440p,Fail
+kms_bw@linear-tiling-2-displays-3840x2160p,Fail
+kms_bw@linear-tiling-3-displays-1920x1080p,Fail
+kms_bw@linear-tiling-3-displays-2560x1440p,Fail
+kms_bw@linear-tiling-3-displays-3840x2160p,Fail
+kms_bw@linear-tiling-4-displays-1920x1080p,Fail
+kms_bw@linear-tiling-4-displays-2560x1440p,Fail
+kms_bw@linear-tiling-4-displays-3840x2160p,Fail
+kms_color@ctm-0-25,Fail
+kms_color@ctm-0-50,Fail
+kms_color@ctm-0-75,Fail
+kms_color@ctm-max,Fail
+kms_color@ctm-negative,Fail
+kms_color@ctm-red-to-blue,Fail
+kms_color@ctm-signed,Fail
+kms_flip_scaled_crc@flip-32bpp-linear-to-64bpp-linear-downscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-linear-to-64bpp-linear-upscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-xtile-to-64bpp-xtile-downscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-xtile-to-64bpp-xtile-upscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-ytile-to-64bpp-ytile-downscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-ytile-to-64bpp-ytile-upscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile-downscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-16bpp-linear-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-16bpp-linear-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-32bpp-linear-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-32bpp-linear-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-16bpp-xtile-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-16bpp-xtile-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-32bpp-xtile-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-32bpp-xtile-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-ytile-to-16bpp-ytile-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-ytile-to-16bpp-ytile-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytile-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytile-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytilegen12rcccs-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytilercccs-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytilercccs-upscaling,Fail
+kms_hdmi_inject@inject-4k,Timeout
+kms_plane@plane-position-hole,Timeout
+kms_plane_alpha_blend@alpha-basic,Fail
+kms_plane_alpha_blend@alpha-opaque-fb,Fail
+kms_plane_alpha_blend@alpha-transparent-fb,Fail
+kms_plane_alpha_blend@constant-alpha-max,Fail
+kms_plane_alpha_blend@pipe-A-alpha-opaque-fb,Fail
+kms_plane_alpha_blend@pipe-A-alpha-transparent-fb,Fail
+kms_plane_alpha_blend@pipe-A-constant-alpha-max,Fail
+kms_plane_alpha_blend@pipe-B-alpha-opaque-fb,Fail
+kms_plane_alpha_blend@pipe-B-alpha-transparent-fb,Fail
+kms_plane_alpha_blend@pipe-B-constant-alpha-max,Fail
+kms_plane_alpha_blend@pipe-C-alpha-opaque-fb,Fail
+kms_plane_alpha_blend@pipe-C-alpha-transparent-fb,Fail
+kms_plane_alpha_blend@pipe-C-constant-alpha-max,Fail
+kms_plane_multiple@tiling-y,Timeout
+kms_pwrite_crc,Timeout
+kms_sysfs_edid_timing,Fail
diff --git a/drivers/gpu/drm/ci/xfails/i915-apl-flakes.txt b/drivers/gpu/drm/ci/xfails/i915-apl-flakes.txt
new file mode 100644
index 000000000000..331c5841bb41
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/i915-apl-flakes.txt
@@ -0,0 +1 @@
+kms_frontbuffer_tracking@fbc-tiling-linear
diff --git a/drivers/gpu/drm/ci/xfails/i915-apl-skips.txt b/drivers/gpu/drm/ci/xfails/i915-apl-skips.txt
new file mode 100644
index 000000000000..3430b215c06e
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/i915-apl-skips.txt
@@ -0,0 +1,6 @@
+# Suspend to RAM seems to be broken on this machine
+.*suspend.*
+# This is generating kernel oops with divide error
+kms_plane_scaling@invalid-parameters
+# This is cascading issues
+kms_3d
\ No newline at end of file
diff --git a/drivers/gpu/drm/ci/xfails/i915-cml-fails.txt b/drivers/gpu/drm/ci/xfails/i915-cml-fails.txt
new file mode 100644
index 000000000000..6139b410e767
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/i915-cml-fails.txt
@@ -0,0 +1,18 @@
+kms_color@ctm-0-25,Fail
+kms_flip_scaled_crc@flip-32bpp-linear-to-64bpp-linear-downscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-linear-to-64bpp-linear-upscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-xtile-to-64bpp-xtile-downscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-xtile-to-64bpp-xtile-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-16bpp-linear-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-16bpp-linear-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-32bpp-linear-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-32bpp-linear-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-16bpp-xtile-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-16bpp-xtile-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-32bpp-xtile-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-32bpp-xtile-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytilegen12rcccs-upscaling,Fail
+kms_plane_alpha_blend@alpha-basic,Fail
+kms_plane_alpha_blend@alpha-opaque-fb,Fail
+kms_plane_alpha_blend@alpha-transparent-fb,Fail
+kms_plane_alpha_blend@constant-alpha-max,Fail
diff --git a/drivers/gpu/drm/ci/xfails/i915-cml-flakes.txt b/drivers/gpu/drm/ci/xfails/i915-cml-flakes.txt
new file mode 100644
index 000000000000..0514a7b3fdb0
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/i915-cml-flakes.txt
@@ -0,0 +1,38 @@
+kms_bw@linear-tiling-2-displays-1920x1080p
+kms_bw@linear-tiling-2-displays-2560x1440p
+kms_bw@linear-tiling-2-displays-3840x2160p
+kms_bw@linear-tiling-3-displays-1920x1080p
+kms_bw@linear-tiling-3-displays-2560x1440p
+kms_bw@linear-tiling-3-displays-3840x2160p
+kms_bw@linear-tiling-4-displays-1920x1080p
+kms_bw@linear-tiling-4-displays-2560x1440p
+kms_bw@linear-tiling-4-displays-3840x2160p
+kms_draw_crc@draw-method-xrgb8888-render-xtiled
+kms_flip@flip-vs-suspend
+kms_flip_scaled_crc@flip-32bpp-ytile-to-64bpp-ytile-downscaling
+kms_flip_scaled_crc@flip-32bpp-ytile-to-64bpp-ytile-upscaling
+kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile-downscaling
+kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile-upscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-16bpp-ytile-downscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-16bpp-ytile-upscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytile-downscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytile-upscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytilercccs-downscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytilercccs-upscaling
+kms_hdr@bpc-switch-suspend
+kms_plane_alpha_blend@constant-alpha-min
+kms_plane_alpha_blend@pipe-A-alpha-basic
+kms_plane_alpha_blend@pipe-A-alpha-opaque-fb
+kms_plane_alpha_blend@pipe-A-alpha-transparent-fb
+kms_plane_alpha_blend@pipe-A-constant-alpha-max
+kms_plane_alpha_blend@pipe-B-alpha-basic
+kms_plane_alpha_blend@pipe-B-alpha-opaque-fb
+kms_plane_alpha_blend@pipe-B-alpha-transparent-fb
+kms_plane_alpha_blend@pipe-B-constant-alpha-max
+kms_plane_alpha_blend@pipe-C-alpha-basic
+kms_plane_alpha_blend@pipe-C-alpha-opaque-fb
+kms_plane_alpha_blend@pipe-C-alpha-transparent-fb
+kms_plane_alpha_blend@pipe-C-constant-alpha-max
+kms_psr2_su@page_flip-NV12
+kms_psr2_su@page_flip-P010
+kms_setmode@basic
diff --git a/drivers/gpu/drm/ci/xfails/i915-cml-skips.txt b/drivers/gpu/drm/ci/xfails/i915-cml-skips.txt
new file mode 100644
index 000000000000..6d3d7ddc377f
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/i915-cml-skips.txt
@@ -0,0 +1,2 @@
+# This is generating kernel oops with divide error
+kms_plane_scaling@invalid-parameters
diff --git a/drivers/gpu/drm/ci/xfails/i915-glk-fails.txt b/drivers/gpu/drm/ci/xfails/i915-glk-fails.txt
new file mode 100644
index 000000000000..5bd432e78129
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/i915-glk-fails.txt
@@ -0,0 +1,19 @@
+kms_fbcon_fbt@fbc,Fail
+kms_flip_scaled_crc@flip-32bpp-linear-to-64bpp-linear-downscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-linear-to-64bpp-linear-upscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-xtile-to-64bpp-xtile-downscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-xtile-to-64bpp-xtile-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-16bpp-linear-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-16bpp-linear-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-32bpp-linear-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-32bpp-linear-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-16bpp-xtile-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-16bpp-xtile-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-32bpp-xtile-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-32bpp-xtile-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytilegen12rcccs-upscaling,Fail
+kms_frontbuffer_tracking@fbcdrrs-tiling-linear,Fail
+kms_plane_alpha_blend@alpha-basic,Fail
+kms_plane_alpha_blend@alpha-opaque-fb,Fail
+kms_plane_alpha_blend@alpha-transparent-fb,Fail
+kms_plane_alpha_blend@constant-alpha-max,Fail
diff --git a/drivers/gpu/drm/ci/xfails/i915-glk-flakes.txt b/drivers/gpu/drm/ci/xfails/i915-glk-flakes.txt
new file mode 100644
index 000000000000..fc41d13a2d56
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/i915-glk-flakes.txt
@@ -0,0 +1,41 @@
+kms_bw@linear-tiling-1-displays-3840x2160p
+kms_bw@linear-tiling-2-displays-1920x1080p
+kms_bw@linear-tiling-2-displays-2560x1440p
+kms_bw@linear-tiling-2-displays-3840x2160p
+kms_bw@linear-tiling-3-displays-1920x1080p
+kms_bw@linear-tiling-3-displays-2560x1440p
+kms_bw@linear-tiling-3-displays-3840x2160p
+kms_bw@linear-tiling-4-displays-1920x1080p
+kms_bw@linear-tiling-4-displays-2560x1440p
+kms_bw@linear-tiling-4-displays-3840x2160p
+kms_flip@blocking-wf_vblank
+kms_flip@wf_vblank-ts-check
+kms_flip@wf_vblank-ts-check-interruptible
+kms_flip_scaled_crc@flip-32bpp-ytile-to-64bpp-ytile-downscaling
+kms_flip_scaled_crc@flip-32bpp-ytile-to-64bpp-ytile-upscaling
+kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile-downscaling
+kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile-upscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-16bpp-ytile-downscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-16bpp-ytile-upscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytile-downscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytile-upscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytilercccs-downscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytilercccs-upscaling
+kms_frontbuffer_tracking@fbc-tiling-linear
+kms_plane_alpha_blend@pipe-A-alpha-basic
+kms_plane_alpha_blend@pipe-A-alpha-opaque-fb
+kms_plane_alpha_blend@pipe-A-alpha-transparent-fb
+kms_plane_alpha_blend@pipe-A-constant-alpha-max
+kms_plane_alpha_blend@pipe-B-alpha-basic
+kms_plane_alpha_blend@pipe-B-alpha-opaque-fb
+kms_plane_alpha_blend@pipe-B-alpha-transparent-fb
+kms_plane_alpha_blend@pipe-B-constant-alpha-max
+kms_plane_alpha_blend@pipe-C-alpha-basic
+kms_plane_alpha_blend@pipe-C-alpha-opaque-fb
+kms_plane_alpha_blend@pipe-C-alpha-transparent-fb
+kms_plane_alpha_blend@pipe-C-constant-alpha-max
+kms_prop_blob@invalid-set-prop-any
+kms_rotation_crc@multiplane-rotation
+kms_rotation_crc@multiplane-rotation-cropping-bottom
+kms_rotation_crc@multiplane-rotation-cropping-top
+kms_setmode@basic
diff --git a/drivers/gpu/drm/ci/xfails/i915-glk-skips.txt b/drivers/gpu/drm/ci/xfails/i915-glk-skips.txt
new file mode 100644
index 000000000000..4c7d00ce14bc
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/i915-glk-skips.txt
@@ -0,0 +1,5 @@
+# Suspend to RAM seems to be broken on this machine
+.*suspend.*
+
+# This is generating kernel oops with divide error
+kms_plane_scaling@invalid-parameters
\ No newline at end of file
diff --git a/drivers/gpu/drm/ci/xfails/i915-kbl-fails.txt b/drivers/gpu/drm/ci/xfails/i915-kbl-fails.txt
new file mode 100644
index 000000000000..56ec021a7679
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/i915-kbl-fails.txt
@@ -0,0 +1,25 @@
+kms_bw@linear-tiling-2-displays-2560x1440p,Fail
+kms_bw@linear-tiling-4-displays-2560x1440p,Fail
+kms_flip_scaled_crc@flip-32bpp-linear-to-64bpp-linear-downscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-linear-to-64bpp-linear-upscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-xtile-to-64bpp-xtile-downscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-xtile-to-64bpp-xtile-upscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-ytile-to-64bpp-ytile-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-16bpp-linear-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-16bpp-linear-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-32bpp-linear-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-32bpp-linear-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-16bpp-xtile-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-16bpp-xtile-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-32bpp-xtile-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-32bpp-xtile-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytile-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytilegen12rcccs-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytilercccs-upscaling,Fail
+kms_plane_alpha_blend@alpha-basic,Fail
+kms_plane_alpha_blend@alpha-opaque-fb,Fail
+kms_plane_alpha_blend@alpha-transparent-fb,Fail
+kms_plane_alpha_blend@constant-alpha-max,Fail
+kms_plane_alpha_blend@pipe-A-constant-alpha-max,Fail
+kms_plane_alpha_blend@pipe-B-alpha-opaque-fb,Fail
+kms_plane_alpha_blend@pipe-C-constant-alpha-max,Fail
diff --git a/drivers/gpu/drm/ci/xfails/i915-kbl-flakes.txt b/drivers/gpu/drm/ci/xfails/i915-kbl-flakes.txt
new file mode 100644
index 000000000000..f3ba1c4c5d46
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/i915-kbl-flakes.txt
@@ -0,0 +1,26 @@
+kms_async_flips@crc
+kms_bw@linear-tiling-2-displays-1920x1080p
+kms_bw@linear-tiling-2-displays-3840x2160p
+kms_bw@linear-tiling-3-displays-1920x1080p
+kms_bw@linear-tiling-3-displays-2560x1440p
+kms_bw@linear-tiling-3-displays-3840x2160p
+kms_bw@linear-tiling-4-displays-1920x1080p
+kms_bw@linear-tiling-4-displays-3840x2160p
+kms_color@ctm-0-25
+kms_flip_scaled_crc@flip-32bpp-ytile-to-64bpp-ytile-downscaling
+kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile-downscaling
+kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile-upscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-16bpp-ytile-downscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-16bpp-ytile-upscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytile-upscaling
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytilercccs-downscaling
+kms_plane_alpha_blend@pipe-A-alpha-basic
+kms_plane_alpha_blend@pipe-A-alpha-opaque-fb
+kms_plane_alpha_blend@pipe-A-alpha-transparent-fb
+kms_plane_alpha_blend@pipe-B-alpha-basic
+kms_plane_alpha_blend@pipe-B-alpha-transparent-fb
+kms_plane_alpha_blend@pipe-B-constant-alpha-max
+kms_plane_alpha_blend@pipe-C-alpha-basic
+kms_plane_alpha_blend@pipe-C-alpha-opaque-fb
+kms_plane_alpha_blend@pipe-C-alpha-transparent-fb
+kms_sysfs_edid_timing
diff --git a/drivers/gpu/drm/ci/xfails/i915-kbl-skips.txt b/drivers/gpu/drm/ci/xfails/i915-kbl-skips.txt
new file mode 100644
index 000000000000..4c7d00ce14bc
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/i915-kbl-skips.txt
@@ -0,0 +1,5 @@
+# Suspend to RAM seems to be broken on this machine
+.*suspend.*
+
+# This is generating kernel oops with divide error
+kms_plane_scaling@invalid-parameters
\ No newline at end of file
diff --git a/drivers/gpu/drm/ci/xfails/i915-tgl-fails.txt b/drivers/gpu/drm/ci/xfails/i915-tgl-fails.txt
new file mode 100644
index 000000000000..a6da5544e198
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/i915-tgl-fails.txt
@@ -0,0 +1,37 @@
+kms_bw@linear-tiling-2-displays-3840x2160p,Fail
+kms_bw@linear-tiling-3-displays-1920x1080p,Fail
+kms_bw@linear-tiling-3-displays-2560x1440p,Fail
+kms_bw@linear-tiling-3-displays-3840x2160p,Fail
+kms_bw@linear-tiling-4-displays-1920x1080p,Fail
+kms_bw@linear-tiling-4-displays-2560x1440p,Fail
+kms_bw@linear-tiling-4-displays-3840x2160p,Fail
+kms_bw@linear-tiling-5-displays-1920x1080p,Fail
+kms_bw@linear-tiling-5-displays-2560x1440p,Fail
+kms_bw@linear-tiling-5-displays-3840x2160p,Fail
+kms_color@ctm-0-25,Fail
+kms_flip@flip-vs-panning-vs-hang,Timeout
+kms_flip_scaled_crc@flip-32bpp-linear-to-64bpp-linear-downscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-linear-to-64bpp-linear-upscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-xtile-to-64bpp-xtile-downscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-xtile-to-64bpp-xtile-upscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-ytile-to-64bpp-ytile-downscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-ytile-to-64bpp-ytile-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-16bpp-linear-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-16bpp-linear-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-32bpp-linear-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-32bpp-linear-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-16bpp-xtile-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-16bpp-xtile-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-32bpp-xtile-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-32bpp-xtile-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-ytile-to-16bpp-ytile-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-ytile-to-16bpp-ytile-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytile-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytile-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytilegen12rcccs-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytilercccs-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytilercccs-upscaling,Fail
+kms_rotation_crc@bad-pixel-format,Fail
+kms_rotation_crc@multiplane-rotation,Fail
+kms_rotation_crc@multiplane-rotation-cropping-bottom,Fail
+kms_rotation_crc@multiplane-rotation-cropping-top,Fail
diff --git a/drivers/gpu/drm/ci/xfails/i915-tgl-flakes.txt b/drivers/gpu/drm/ci/xfails/i915-tgl-flakes.txt
new file mode 100644
index 000000000000..1cd910ee06df
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/i915-tgl-flakes.txt
@@ -0,0 +1,5 @@
+kms_draw_crc@.*
+kms_flip@blocking-absolute-wf_vblank
+kms_flip@bo-too-big-interruptible
+kms_flip@busy-flip
+kms_flip@flip-vs-rmfb-interruptible
diff --git a/drivers/gpu/drm/ci/xfails/i915-tgl-skips.txt b/drivers/gpu/drm/ci/xfails/i915-tgl-skips.txt
new file mode 100644
index 000000000000..1d0621750b14
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/i915-tgl-skips.txt
@@ -0,0 +1,11 @@
+# Suspend to RAM seems to be broken on this machine
+.*suspend.*
+
+# GPU hangs, then the whole machine
+gem_eio.*
+
+# Whole machine hangs
+kms_flip@absolute-wf_vblank@a-edp1
+
+# This is generating kernel oops with divide error
+kms_plane_scaling@invalid-parameters
\ No newline at end of file
diff --git a/drivers/gpu/drm/ci/xfails/i915-whl-fails.txt b/drivers/gpu/drm/ci/xfails/i915-whl-fails.txt
new file mode 100644
index 000000000000..967327ddc1ac
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/i915-whl-fails.txt
@@ -0,0 +1,48 @@
+kms_bw@linear-tiling-2-displays-1920x1080p,Fail
+kms_bw@linear-tiling-2-displays-2560x1440p,Fail
+kms_bw@linear-tiling-2-displays-3840x2160p,Fail
+kms_bw@linear-tiling-3-displays-1920x1080p,Fail
+kms_bw@linear-tiling-3-displays-2560x1440p,Fail
+kms_bw@linear-tiling-3-displays-3840x2160p,Fail
+kms_bw@linear-tiling-4-displays-1920x1080p,Fail
+kms_bw@linear-tiling-4-displays-2560x1440p,Fail
+kms_bw@linear-tiling-4-displays-3840x2160p,Fail
+kms_fbcon_fbt@fbc,Fail
+kms_fbcon_fbt@fbc-suspend,Fail
+kms_flip_scaled_crc@flip-32bpp-linear-to-64bpp-linear-downscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-linear-to-64bpp-linear-upscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-xtile-to-64bpp-xtile-downscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-xtile-to-64bpp-xtile-upscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-ytile-to-64bpp-ytile-downscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-ytile-to-64bpp-ytile-upscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile-downscaling,Fail
+kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-16bpp-linear-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-16bpp-linear-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-32bpp-linear-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-linear-to-32bpp-linear-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-16bpp-xtile-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-16bpp-xtile-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-32bpp-xtile-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-xtile-to-32bpp-xtile-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-ytile-to-16bpp-ytile-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-ytile-to-16bpp-ytile-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytile-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytile-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytilegen12rcccs-upscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytilercccs-downscaling,Fail
+kms_flip_scaled_crc@flip-64bpp-ytile-to-32bpp-ytilercccs-upscaling,Fail
+kms_frontbuffer_tracking@fbc-tiling-linear,Fail
+kms_plane_alpha_blend@alpha-basic,Fail
+kms_plane_alpha_blend@alpha-opaque-fb,Fail
+kms_plane_alpha_blend@alpha-transparent-fb,Fail
+kms_plane_alpha_blend@constant-alpha-max,Fail
+kms_plane_alpha_blend@pipe-A-alpha-opaque-fb,Fail
+kms_plane_alpha_blend@pipe-A-alpha-transparent-fb,Fail
+kms_plane_alpha_blend@pipe-A-constant-alpha-max,Fail
+kms_plane_alpha_blend@pipe-B-alpha-opaque-fb,Fail
+kms_plane_alpha_blend@pipe-B-alpha-transparent-fb,Fail
+kms_plane_alpha_blend@pipe-B-constant-alpha-max,Fail
+kms_plane_alpha_blend@pipe-C-alpha-opaque-fb,Fail
+kms_plane_alpha_blend@pipe-C-alpha-transparent-fb,Fail
+kms_plane_alpha_blend@pipe-C-constant-alpha-max,Fail
diff --git a/drivers/gpu/drm/ci/xfails/i915-whl-flakes.txt b/drivers/gpu/drm/ci/xfails/i915-whl-flakes.txt
new file mode 100644
index 000000000000..c33202e7e2a1
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/i915-whl-flakes.txt
@@ -0,0 +1 @@
+kms_flip@flip-vs-suspend
diff --git a/drivers/gpu/drm/ci/xfails/i915-whl-skips.txt b/drivers/gpu/drm/ci/xfails/i915-whl-skips.txt
new file mode 100644
index 000000000000..f3be0888a214
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/i915-whl-skips.txt
@@ -0,0 +1,2 @@
+# This is generating kernel oops with divide error
+kms_plane_scaling@invalid-parameters
\ No newline at end of file
diff --git a/drivers/gpu/drm/ci/xfails/mediatek-mt8173-fails.txt b/drivers/gpu/drm/ci/xfails/mediatek-mt8173-fails.txt
new file mode 100644
index 000000000000..671916067dba
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/mediatek-mt8173-fails.txt
@@ -0,0 +1,29 @@
+kms_3d,Fail
+kms_addfb_basic@addfb25-bad-modifier,Fail
+kms_bw@linear-tiling-1-displays-1920x1080p,Fail
+kms_bw@linear-tiling-1-displays-2560x1440p,Fail
+kms_bw@linear-tiling-1-displays-3840x2160p,Fail
+kms_bw@linear-tiling-2-displays-1920x1080p,Fail
+kms_bw@linear-tiling-2-displays-2560x1440p,Fail
+kms_bw@linear-tiling-2-displays-3840x2160p,Fail
+kms_bw@linear-tiling-3-displays-1920x1080p,Fail
+kms_bw@linear-tiling-3-displays-2560x1440p,Fail
+kms_bw@linear-tiling-3-displays-3840x2160p,Fail
+kms_color@pipe-A-invalid-gamma-lut-sizes,Fail
+kms_color@pipe-B-invalid-gamma-lut-sizes,Fail
+kms_force_connector_basic@force-connector-state,Fail
+kms_force_connector_basic@force-edid,Fail
+kms_force_connector_basic@force-load-detect,Fail
+kms_force_connector_basic@prune-stale-modes,Fail
+kms_invalid_mode@int-max-clock,Fail
+kms_plane_scaling@planes-upscale-20x20,Fail
+kms_plane_scaling@planes-upscale-20x20-downscale-factor-0-25,Fail
+kms_plane_scaling@planes-upscale-20x20-downscale-factor-0-5,Fail
+kms_plane_scaling@planes-upscale-20x20-downscale-factor-0-75,Fail
+kms_plane_scaling@upscale-with-modifier-20x20,Fail
+kms_plane_scaling@upscale-with-pixel-format-20x20,Fail
+kms_plane_scaling@upscale-with-rotation-20x20,Fail
+kms_properties@get_properties-sanity-atomic,Fail
+kms_properties@plane-properties-atomic,Fail
+kms_properties@plane-properties-legacy,Fail
+kms_rmfb@close-fd,Fail
diff --git a/drivers/gpu/drm/ci/xfails/mediatek-mt8173-flakes.txt b/drivers/gpu/drm/ci/xfails/mediatek-mt8173-flakes.txt
new file mode 100644
index 000000000000..e69de29bb2d1
diff --git a/drivers/gpu/drm/ci/xfails/mediatek-mt8183-fails.txt b/drivers/gpu/drm/ci/xfails/mediatek-mt8183-fails.txt
new file mode 100644
index 000000000000..6ff81d00e84e
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/mediatek-mt8183-fails.txt
@@ -0,0 +1,10 @@
+kms_addfb_basic@addfb25-bad-modifier,Fail
+kms_bw@linear-tiling-1-displays-2560x1440p,Fail
+kms_bw@linear-tiling-2-displays-1920x1080p,Fail
+kms_bw@linear-tiling-2-displays-2560x1440p,Fail
+kms_bw@linear-tiling-2-displays-3840x2160p,Fail
+kms_bw@linear-tiling-3-displays-2560x1440p,Fail
+kms_bw@linear-tiling-3-displays-3840x2160p,Fail
+kms_color@pipe-A-invalid-gamma-lut-sizes,Fail
+kms_plane_scaling@upscale-with-rotation-20x20,Fail
+kms_rmfb@close-fd,Fail
\ No newline at end of file
diff --git a/drivers/gpu/drm/ci/xfails/mediatek-mt8183-flakes.txt b/drivers/gpu/drm/ci/xfails/mediatek-mt8183-flakes.txt
new file mode 100644
index 000000000000..208890b79eb0
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/mediatek-mt8183-flakes.txt
@@ -0,0 +1,14 @@
+core_setmaster_vs_auth
+kms_bw@linear-tiling-1-displays-1920x1080p
+kms_bw@linear-tiling-1-displays-3840x2160p
+kms_bw@linear-tiling-3-displays-1920x1080p
+kms_cursor_legacy@cursor-vs-flip-atomic
+kms_plane_scaling@invalid-num-scalers
+kms_plane_scaling@planes-upscale-20x20
+kms_plane_scaling@planes-upscale-20x20-downscale-factor-0-5
+kms_plane_scaling@upscale-with-modifier-20x20
+kms_plane_scaling@upscale-with-pixel-format-20x20
+kms_prop_blob@invalid-set-prop-any
+kms_properties@get_properties-sanity-atomic
+kms_properties@plane-properties-atomic
+kms_properties@plane-properties-legacy
\ No newline at end of file
diff --git a/drivers/gpu/drm/ci/xfails/meson-g12b-fails.txt b/drivers/gpu/drm/ci/xfails/meson-g12b-fails.txt
new file mode 100644
index 000000000000..860e702091e2
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/meson-g12b-fails.txt
@@ -0,0 +1,12 @@
+kms_3d,Fail
+kms_properties@connector-properties-atomic,Fail
+kms_properties@get_properties-sanity-atomic,Fail
+kms_properties@get_properties-sanity-non-atomic,Fail
+kms_properties@connector-properties-legacy,Fail
+kms_cursor_legacy@forked-bo,Fail
+kms_cursor_legacy@forked-move,Fail
+kms_cursor_legacy@single-bo,Fail
+kms_cursor_legacy@single-move,Fail
+kms_cursor_legacy@torture-bo,Fail
+kms_cursor_legacy@torture-move,Fail
+kms_hdmi_inject@inject-4k,Fail
\ No newline at end of file
diff --git a/drivers/gpu/drm/ci/xfails/meson-g12b-flakes.txt b/drivers/gpu/drm/ci/xfails/meson-g12b-flakes.txt
new file mode 100644
index 000000000000..b63329d06767
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/meson-g12b-flakes.txt
@@ -0,0 +1,4 @@
+kms_force_connector_basic@force-connector-state
+kms_force_connector_basic@force-edid
+kms_force_connector_basic@force-load-detect
+kms_force_connector_basic@prune-stale-modes
\ No newline at end of file
diff --git a/drivers/gpu/drm/ci/xfails/msm-apq8016-fails.txt b/drivers/gpu/drm/ci/xfails/msm-apq8016-fails.txt
new file mode 100644
index 000000000000..9981682feab2
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/msm-apq8016-fails.txt
@@ -0,0 +1,15 @@
+kms_3d,Fail
+kms_addfb_basic@addfb25-bad-modifier,Fail
+kms_cursor_legacy@all-pipes-forked-bo,Fail
+kms_cursor_legacy@all-pipes-forked-move,Fail
+kms_cursor_legacy@all-pipes-single-bo,Fail
+kms_cursor_legacy@all-pipes-single-move,Fail
+kms_cursor_legacy@all-pipes-torture-bo,Fail
+kms_cursor_legacy@all-pipes-torture-move,Fail
+kms_cursor_legacy@pipe-A-forked-bo,Fail
+kms_cursor_legacy@pipe-A-forked-move,Fail
+kms_cursor_legacy@pipe-A-single-bo,Fail
+kms_cursor_legacy@pipe-A-single-move,Fail
+kms_cursor_legacy@pipe-A-torture-bo,Fail
+kms_cursor_legacy@pipe-A-torture-move,Fail
+kms_hdmi_inject@inject-4k,Fail
diff --git a/drivers/gpu/drm/ci/xfails/msm-apq8016-flakes.txt b/drivers/gpu/drm/ci/xfails/msm-apq8016-flakes.txt
new file mode 100644
index 000000000000..0e3b60d3fade
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/msm-apq8016-flakes.txt
@@ -0,0 +1,4 @@
+kms_force_connector_basic@force-connector-state
+kms_force_connector_basic@force-edid
+kms_force_connector_basic@force-load-detect
+kms_force_connector_basic@prune-stale-modes
diff --git a/drivers/gpu/drm/ci/xfails/msm-apq8096-fails.txt b/drivers/gpu/drm/ci/xfails/msm-apq8096-fails.txt
new file mode 100644
index 000000000000..88a1fc0a3b0d
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/msm-apq8096-fails.txt
@@ -0,0 +1,2 @@
+kms_3d,Fail
+kms_addfb_basic@addfb25-bad-modifier,Fail
diff --git a/drivers/gpu/drm/ci/xfails/msm-apq8096-flakes.txt b/drivers/gpu/drm/ci/xfails/msm-apq8096-flakes.txt
new file mode 100644
index 000000000000..0e3b60d3fade
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/msm-apq8096-flakes.txt
@@ -0,0 +1,4 @@
+kms_force_connector_basic@force-connector-state
+kms_force_connector_basic@force-edid
+kms_force_connector_basic@force-load-detect
+kms_force_connector_basic@prune-stale-modes
diff --git a/drivers/gpu/drm/ci/xfails/msm-apq8096-skips.txt b/drivers/gpu/drm/ci/xfails/msm-apq8096-skips.txt
new file mode 100644
index 000000000000..cd49c8ce2059
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/msm-apq8096-skips.txt
@@ -0,0 +1,2 @@
+# Whole machine hangs
+kms_cursor_legacy@all-pipes-torture-move
\ No newline at end of file
diff --git a/drivers/gpu/drm/ci/xfails/msm-sc7180-fails.txt b/drivers/gpu/drm/ci/xfails/msm-sc7180-fails.txt
new file mode 100644
index 000000000000..14adeba3b62d
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/msm-sc7180-fails.txt
@@ -0,0 +1,25 @@
+kms_cursor_legacy@cursor-vs-flip-toggle,Fail
+kms_cursor_legacy@cursor-vs-flip-varying-size,Fail
+kms_cursor_legacy@cursorA-vs-flipA-atomic-transitions,Crash
+kms_pipe_crc_basic@compare-crc-sanitycheck-nv12,Fail
+kms_plane@pixel-format,Fail
+kms_plane@pixel-format-source-clamping,Fail
+kms_plane@plane-position-covered,Fail
+kms_plane@plane-position-hole,Fail
+kms_plane@plane-position-hole-dpms,Fail
+kms_plane_alpha_blend@alpha-7efc,Fail
+kms_plane_alpha_blend@coverage-7efc,Fail
+kms_plane_alpha_blend@coverage-vs-premult-vs-constant,Fail
+kms_plane_alpha_blend@pipe-A-alpha-7efc,Fail
+kms_plane_alpha_blend@pipe-A-coverage-7efc,Fail
+kms_plane_alpha_blend@pipe-A-coverage-vs-premult-vs-constant,Fail
+kms_plane_alpha_blend@pipe-B-alpha-7efc,Fail
+kms_plane_alpha_blend@pipe-B-alpha-basic,Fail
+kms_plane_alpha_blend@pipe-B-alpha-opaque-fb,Fail
+kms_plane_alpha_blend@pipe-B-constant-alpha-max,Fail
+kms_plane_alpha_blend@pipe-B-constant-alpha-mid,Fail
+kms_plane_alpha_blend@pipe-B-coverage-7efc,Fail
+kms_plane_alpha_blend@pipe-B-coverage-vs-premult-vs-constant,Fail
+kms_rmfb@close-fd,Fail
+kms_universal_plane@disable-primary-vs-flip-pipe-b,Fail
+kms_universal_plane@universal-plane-pipe-B-sanity,Fail
diff --git a/drivers/gpu/drm/ci/xfails/msm-sc7180-flakes.txt b/drivers/gpu/drm/ci/xfails/msm-sc7180-flakes.txt
new file mode 100644
index 000000000000..636563d3e59a
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/msm-sc7180-flakes.txt
@@ -0,0 +1,7 @@
+
+# Test ends up reading CRC from frame before cursor update
+# bug
+# sometimes.. tbd if this is a kernel CRC bug or a test
+kms_cursor_crc@.*
+kms_plane_multiple@atomic-pipe-A-tiling-none
+kms_atomic_transition@modeset-transition-nonblocking-fencing,Fail
\ No newline at end of file
diff --git a/drivers/gpu/drm/ci/xfails/msm-sc7180-skips.txt b/drivers/gpu/drm/ci/xfails/msm-sc7180-skips.txt
new file mode 100644
index 000000000000..410e0eeb3161
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/msm-sc7180-skips.txt
@@ -0,0 +1,23 @@
+# Suspend to RAM seems to be broken on this machine
+.*suspend.*
+
+# Test incorrectly assumes that CTM support implies gamma/degamma
+# LUT support.  None of the subtests handle the case of only having
+# CTM support
+kms_color.*
+
+# 4k@60 is not supported on this hw, but driver doesn't handle it
+# too gracefully.. https://gitlab.freedesktop.org/drm/msm/-/issues/15
+kms_bw@linear-tiling-.*-displays-3840x2160p
+
+# Until igt fix lands: https://patchwork.freedesktop.org/patch/493175/
+kms_bw@linear-tiling-2.*
+kms_bw@linear-tiling-3.*
+kms_bw@linear-tiling-4.*
+kms_bw@linear-tiling-5.*
+kms_bw@linear-tiling-6.*
+
+# igt fix posted: https://patchwork.freedesktop.org/patch/499926/
+# failure mode is flakey due to randomization but fails frequently
+# enough to be detected as a Crash or occasionally UnexpectedPass.
+kms_plane_multiple@atomic-pipe-A-tiling-none
diff --git a/drivers/gpu/drm/ci/xfails/msm-sdm845-fails.txt b/drivers/gpu/drm/ci/xfails/msm-sdm845-fails.txt
new file mode 100644
index 000000000000..09c0c623cd75
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/msm-sdm845-fails.txt
@@ -0,0 +1,68 @@
+kms_color@ctm-0-25,Fail
+kms_color@ctm-0-50,Fail
+kms_color@ctm-0-75,Fail
+kms_color@ctm-blue-to-red,Fail
+kms_color@ctm-green-to-red,Fail
+kms_color@ctm-negative,Fail
+kms_color@ctm-red-to-blue,Fail
+kms_color@ctm-signed,Fail
+kms_color@pipe-A-ctm-0-25,Fail
+kms_color@pipe-A-ctm-0-5,Fail
+kms_color@pipe-A-ctm-0-75,Fail
+kms_color@pipe-A-ctm-blue-to-red,Fail
+kms_color@pipe-A-ctm-green-to-red,Fail
+kms_color@pipe-A-ctm-max,Fail
+kms_color@pipe-A-ctm-negative,Fail
+kms_color@pipe-A-ctm-red-to-blue,Fail
+kms_color@pipe-A-legacy-gamma,Fail
+kms_cursor_legacy@basic-flip-after-cursor-atomic,Fail
+kms_cursor_legacy@basic-flip-after-cursor-legacy,Fail
+kms_cursor_legacy@basic-flip-after-cursor-varying-size,Fail
+kms_cursor_legacy@basic-flip-before-cursor-atomic,Fail
+kms_cursor_legacy@basic-flip-before-cursor-legacy,Fail
+kms_cursor_legacy@basic-flip-before-cursor-varying-size,Fail
+kms_cursor_legacy@cursor-vs-flip-atomic,Fail
+kms_cursor_legacy@cursor-vs-flip-atomic-transitions,Fail
+kms_cursor_legacy@cursor-vs-flip-atomic-transitions-varying-size,Fail
+kms_cursor_legacy@cursor-vs-flip-legacy,Fail
+kms_cursor_legacy@cursor-vs-flip-toggle,Fail
+kms_cursor_legacy@cursor-vs-flip-varying-size,Fail
+kms_cursor_legacy@cursorA-vs-flipA-toggle,Fail
+kms_cursor_legacy@flip-vs-cursor-atomic,Fail
+kms_cursor_legacy@flip-vs-cursor-crc-atomic,Fail
+kms_cursor_legacy@flip-vs-cursor-crc-legacy,Fail
+kms_cursor_legacy@flip-vs-cursor-legacy,Fail
+kms_cursor_legacy@short-flip-after-cursor-atomic-transitions,Fail
+kms_cursor_legacy@short-flip-after-cursor-atomic-transitions-varying-size,Fail
+kms_cursor_legacy@short-flip-after-cursor-toggle,Fail
+kms_cursor_legacy@short-flip-before-cursor-atomic-transitions,Fail
+kms_cursor_legacy@short-flip-before-cursor-atomic-transitions-varying-size,Fail
+kms_pipe_crc_basic@compare-crc-sanitycheck-nv12,Fail
+kms_plane@pixel-format,Fail
+kms_plane@pixel-format-source-clamping,Fail
+kms_plane_alpha_blend@alpha-7efc,Fail
+kms_plane_alpha_blend@coverage-7efc,Fail
+kms_plane_alpha_blend@coverage-vs-premult-vs-constant,Fail
+kms_plane_alpha_blend@pipe-A-alpha-7efc,Fail
+kms_plane_alpha_blend@pipe-A-coverage-7efc,Fail
+kms_plane_alpha_blend@pipe-A-coverage-vs-premult-vs-constant,Fail
+kms_plane_cursor@overlay,Fail
+kms_plane_cursor@pipe-A-overlay-size-128,Fail
+kms_plane_cursor@pipe-A-overlay-size-256,Fail
+kms_plane_cursor@pipe-A-overlay-size-64,Fail
+kms_plane_cursor@pipe-A-viewport-size-128,Fail
+kms_plane_cursor@pipe-A-viewport-size-256,Fail
+kms_plane_cursor@pipe-A-viewport-size-64,Fail
+kms_plane_cursor@viewport,Fail
+kms_plane_scaling@downscale-with-pixel-format-factor-0-25,Timeout
+kms_plane_scaling@downscale-with-pixel-format-factor-0-5,Timeout
+kms_plane_scaling@downscale-with-pixel-format-factor-0-75,Timeout
+kms_plane_scaling@plane-downscale-with-pixel-format-factor-0-25,Timeout
+kms_plane_scaling@plane-downscale-with-pixel-format-factor-0-5,Timeout
+kms_plane_scaling@plane-downscale-with-pixel-format-factor-0-75,Timeout
+kms_plane_scaling@plane-scaler-with-clipping-clamping-pixel-formats,Timeout
+kms_plane_scaling@plane-scaler-with-pixel-format-unity-scaling,Timeout
+kms_plane_scaling@planes-downscale-factor-0-25,Fail
+kms_plane_scaling@scaler-with-clipping-clamping,Timeout
+kms_plane_scaling@scaler-with-pixel-format-unity-scaling,Timeout
+kms_rmfb@close-fd,Fail
diff --git a/drivers/gpu/drm/ci/xfails/msm-sdm845-flakes.txt b/drivers/gpu/drm/ci/xfails/msm-sdm845-flakes.txt
new file mode 100644
index 000000000000..5b3aaab7ac3f
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/msm-sdm845-flakes.txt
@@ -0,0 +1,11 @@
+
+
+# Test ends up reading CRC from frame before cursor update
+# bug
+# sometimes.. tbd if this is a kernel CRC bug or a test
+kms_cursor_crc@.*
+kms_cursor_legacy@flip-vs-cursor-toggle
+kms_cursor_legacy@pipe-A-forked-bo
+kms_cursor_legacy@pipe-A-forked-move
+kms_cursor_legacy@short-flip-before-cursor-toggle
+kms_flip@dpms-vs-vblank-race-interruptible
diff --git a/drivers/gpu/drm/ci/xfails/msm-sdm845-skips.txt b/drivers/gpu/drm/ci/xfails/msm-sdm845-skips.txt
new file mode 100644
index 000000000000..42675f1c6d76
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/msm-sdm845-skips.txt
@@ -0,0 +1,2 @@
+# Hangs machine
+kms_bw.*
\ No newline at end of file
diff --git a/drivers/gpu/drm/ci/xfails/rockchip-rk3288-fails.txt b/drivers/gpu/drm/ci/xfails/rockchip-rk3288-fails.txt
new file mode 100644
index 000000000000..2a1baa948e12
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/rockchip-rk3288-fails.txt
@@ -0,0 +1,48 @@
+kms_3d,Crash
+kms_bw@linear-tiling-2-displays-1920x1080p,Fail
+kms_bw@linear-tiling-2-displays-2560x1440p,Fail
+kms_bw@linear-tiling-2-displays-3840x2160p,Fail
+kms_bw@linear-tiling-3-displays-1920x1080p,Fail
+kms_bw@linear-tiling-3-displays-2560x1440p,Fail
+kms_bw@linear-tiling-3-displays-3840x2160p,Fail
+kms_force_connector_basic@force-load-detect,Fail
+kms_invalid_mode@int-max-clock,Crash
+kms_plane@pixel-format,Crash
+kms_plane@pixel-format-source-clamping,Crash
+kms_plane@plane-position-hole,Crash
+kms_plane@plane-position-hole-dpms,Crash
+kms_plane_cursor@overlay,Crash
+kms_plane_cursor@pipe-A-overlay-size-128,Fail
+kms_plane_cursor@pipe-A-overlay-size-256,Fail
+kms_plane_cursor@pipe-A-overlay-size-64,Fail
+kms_plane_cursor@pipe-A-primary-size-128,Fail
+kms_plane_cursor@pipe-A-primary-size-256,Fail
+kms_plane_cursor@pipe-A-primary-size-64,Fail
+kms_plane_cursor@pipe-A-viewport-size-128,Fail
+kms_plane_cursor@pipe-A-viewport-size-256,Fail
+kms_plane_cursor@pipe-A-viewport-size-64,Fail
+kms_plane_cursor@pipe-B-overlay-size-128,Fail
+kms_plane_cursor@pipe-B-overlay-size-256,Fail
+kms_plane_cursor@pipe-B-overlay-size-64,Fail
+kms_plane_cursor@pipe-B-primary-size-128,Fail
+kms_plane_cursor@pipe-B-primary-size-256,Fail
+kms_plane_cursor@pipe-B-primary-size-64,Fail
+kms_plane_cursor@pipe-B-viewport-size-128,Fail
+kms_plane_cursor@pipe-B-viewport-size-256,Fail
+kms_plane_cursor@pipe-B-viewport-size-64,Fail
+kms_plane_cursor@primary,Crash
+kms_plane_cursor@viewport,Crash
+kms_plane_lowres@tiling-none,Fail
+kms_plane_scaling@downscale-with-modifier-factor-0-25,Fail
+kms_plane_scaling@downscale-with-rotation-factor-0-25,Fail
+kms_plane_scaling@upscale-with-modifier-20x20,Fail
+kms_plane_scaling@upscale-with-modifier-factor-0-25,Fail
+kms_plane_scaling@upscale-with-pixel-format-20x20,Fail
+kms_plane_scaling@upscale-with-pixel-format-factor-0-25,Fail
+kms_plane_scaling@upscale-with-rotation-20x20,Fail
+kms_prime@basic-crc,Fail
+kms_properties@connector-properties-atomic,Crash
+kms_properties@connector-properties-legacy,Crash
+kms_properties@get_properties-sanity-atomic,Crash
+kms_properties@get_properties-sanity-non-atomic,Crash
+kms_setmode@invalid-clone-single-crtc,Crash
diff --git a/drivers/gpu/drm/ci/xfails/rockchip-rk3288-flakes.txt b/drivers/gpu/drm/ci/xfails/rockchip-rk3288-flakes.txt
new file mode 100644
index 000000000000..45c54c75c899
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/rockchip-rk3288-flakes.txt
@@ -0,0 +1,9 @@
+kms_addfb_basic@addfb25-bad-modifier
+kms_cursor_crc@.*
+kms_flip@basic-flip-vs-wf_vblank
+kms_invalid_mode@int-max-clock,Crash
+kms_pipe_crc_basic@.*
+kms_properties@connector-properties-atomic,Crash
+kms_properties@get_properties-sanity-atomic,Crash
+kms_properties@get_properties-sanity-non-atomic,Crash
+kms_rmfb@close-fd
diff --git a/drivers/gpu/drm/ci/xfails/rockchip-rk3288-skips.txt b/drivers/gpu/drm/ci/xfails/rockchip-rk3288-skips.txt
new file mode 100644
index 000000000000..f20c3574b75a
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/rockchip-rk3288-skips.txt
@@ -0,0 +1,52 @@
+# Suspend to RAM seems to be broken on this machine
+.*suspend.*
+
+# Too unstable, machine ends up hanging after lots of Oopses
+kms_cursor_legacy.*
+
+# Started hanging the machine on Linux 5.19-rc2:
+#
+# [IGT] kms_plane_lowres: executing
+# [IGT] kms_plane_lowres: starting subtest pipe-F-tiling-y
+# [IGT] kms_plane_lowres: exiting, ret=77
+# Console: switching to colour frame buffer device 170x48
+# rockchip-drm display-subsystem: [drm] *ERROR* flip_done timed out
+# rockchip-drm display-subsystem: [drm] *ERROR* [CRTC:35:crtc-0] commit wait timed out
+# BUG: spinlock bad magic on CPU#3, kms_plane_lowre/482
+# 8<--- cut here ---
+# Unable to handle kernel paging request at virtual address 7812078e
+# [7812078e] *pgd=00000000
+# Internal error: Oops: 5 [#1] SMP ARM
+# Modules linked in:
+# CPU: 3 PID: 482 Comm: kms_plane_lowre Tainted: G        W         5.19.0-rc2-323596-g00535de92171 #1
+# Hardware name: Rockchip (Device Tree)
+# Process kms_plane_lowre (pid: 482, stack limit = 0x1193ac2b)
+#  spin_dump from do_raw_spin_lock+0xa4/0xe8
+#  do_raw_spin_lock from wait_for_completion_timeout+0x2c/0x120
+#  wait_for_completion_timeout from drm_crtc_commit_wait+0x18/0x7c
+#  drm_crtc_commit_wait from drm_atomic_helper_wait_for_dependencies+0x44/0x168
+#  drm_atomic_helper_wait_for_dependencies from commit_tail+0x34/0x180
+#  commit_tail from drm_atomic_helper_commit+0x164/0x18c
+#  drm_atomic_helper_commit from drm_atomic_commit+0xac/0xe4
+#  drm_atomic_commit from drm_client_modeset_commit_atomic+0x23c/0x284
+#  drm_client_modeset_commit_atomic from drm_client_modeset_commit_locked+0x60/0x1c8
+#  drm_client_modeset_commit_locked from drm_client_modeset_commit+0x24/0x40
+#  drm_client_modeset_commit from drm_fbdev_client_restore+0x58/0x94
+#  drm_fbdev_client_restore from drm_client_dev_restore+0x70/0xbc
+#  drm_client_dev_restore from drm_release+0xf4/0x114
+#  drm_release from __fput+0x74/0x240
+#  __fput from task_work_run+0x84/0xb4
+#  task_work_run from do_exit+0x34c/0xa20
+#  do_exit from do_group_exit+0x34/0x98
+#  do_group_exit from __wake_up_parent+0x0/0x18
+# Code: e595c008 12843d19 03e00000 03093168 (15940508)
+# ---[ end trace 0000000000000000 ]---
+# note: kms_plane_lowre[482] exited with preempt_count 1
+# Fixing recursive fault but reboot is needed!
+kms_plane_lowres@pipe-F-tiling-y
+
+# Take too long, we have only two machines, and these are very flaky
+kms_cursor_crc.*
+
+# Machine is hanging in this test, so skip it
+kms_pipe_crc_basic@disable-crc-after-crtc
\ No newline at end of file
diff --git a/drivers/gpu/drm/ci/xfails/rockchip-rk3399-fails.txt b/drivers/gpu/drm/ci/xfails/rockchip-rk3399-fails.txt
new file mode 100644
index 000000000000..6db08ba6b008
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/rockchip-rk3399-fails.txt
@@ -0,0 +1,37 @@
+kms_color@legacy-gamma,Fail
+kms_color@pipe-A-legacy-gamma,Fail
+kms_color@pipe-B-legacy-gamma,Fail
+kms_flip@basic-flip-vs-wf_vblank,Fail
+kms_flip@blocking-wf_vblank,Fail
+kms_flip@dpms-vs-vblank-race,Fail
+kms_flip@flip-vs-absolute-wf_vblank,Fail
+kms_flip@flip-vs-absolute-wf_vblank-interruptible,Fail
+kms_flip@flip-vs-blocking-wf-vblank,Fail
+kms_flip@flip-vs-panning,Fail
+kms_flip@flip-vs-panning-interruptible,Fail
+kms_flip@flip-vs-wf_vblank-interruptible,Fail
+kms_flip@plain-flip-fb-recreate,Fail
+kms_flip@plain-flip-fb-recreate-interruptible,Fail
+kms_flip@plain-flip-ts-check,Fail
+kms_flip@plain-flip-ts-check-interruptible,Fail
+kms_flip@wf_vblank-ts-check,Fail
+kms_flip@wf_vblank-ts-check-interruptible,Fail
+kms_invalid_mode@int-max-clock,Fail
+kms_plane@pixel-format,Fail
+kms_plane@pixel-format-source-clamping,Fail
+kms_plane@plane-panning-bottom-right,Fail
+kms_plane@plane-panning-top-left,Fail
+kms_plane@plane-position-covered,Fail
+kms_plane_cursor@pipe-B-overlay-size-128,Fail
+kms_plane_cursor@pipe-B-overlay-size-256,Fail
+kms_plane_cursor@pipe-B-overlay-size-64,Fail
+kms_plane_cursor@pipe-B-primary-size-128,Fail
+kms_plane_cursor@pipe-B-primary-size-256,Fail
+kms_plane_cursor@pipe-B-primary-size-64,Fail
+kms_plane_cursor@pipe-B-viewport-size-128,Fail
+kms_plane_cursor@pipe-B-viewport-size-256,Fail
+kms_plane_cursor@pipe-B-viewport-size-64,Fail
+kms_plane_multiple@atomic-pipe-B-tiling-none,Fail
+kms_plane_multiple@tiling-none,Fail
+kms_prime@basic-crc,Fail
+kms_rmfb@close-fd,Fail
diff --git a/drivers/gpu/drm/ci/xfails/rockchip-rk3399-flakes.txt b/drivers/gpu/drm/ci/xfails/rockchip-rk3399-flakes.txt
new file mode 100644
index 000000000000..4c0539b4beaf
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/rockchip-rk3399-flakes.txt
@@ -0,0 +1,23 @@
+
+kms_cursor_crc@.*
+kms_flip@dpms-vs-vblank-race-interruptible
+kms_flip@flip-vs-expired-vblank
+kms_flip@modeset-vs-vblank-race-interruptible
+kms_pipe_crc_basic@.*
+kms_pipe_crc_basic@compare-crc-sanitycheck-pipe-A
+kms_pipe_crc_basic@compare-crc-sanitycheck-pipe-B
+kms_plane@plane-position-hole
+kms_plane_multiple@atomic-pipe-A-tiling-none
+kms_plane_multiple@atomic-pipe-B-tiling-none
+kms_sequence@get-forked
+kms_sequence@get-forked-busy
+kms_setmode@basic
+kms_universal_plane@universal-plane-pipe-B-functional,UnexpectedPass
+kms_vblank@pipe-A-accuracy-idle
+kms_vblank@pipe-A-query-busy
+kms_vblank@pipe-A-query-forked-busy
+kms_vblank@pipe-A-wait-idle
+kms_vblank@pipe-B-accuracy-idle
+kms_vblank@pipe-B-query-busy
+kms_vblank@pipe-B-query-forked-busy
+kms_vblank@pipe-B-wait-idle
diff --git a/drivers/gpu/drm/ci/xfails/rockchip-rk3399-skips.txt b/drivers/gpu/drm/ci/xfails/rockchip-rk3399-skips.txt
new file mode 100644
index 000000000000..10c3d81a919a
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/rockchip-rk3399-skips.txt
@@ -0,0 +1,5 @@
+# Suspend to RAM seems to be broken on this machine
+.*suspend.*
+
+# Too unstable, machine ends up hanging after lots of Oopses
+kms_cursor_legacy.*
diff --git a/drivers/gpu/drm/ci/xfails/virtio_gpu-none-fails.txt b/drivers/gpu/drm/ci/xfails/virtio_gpu-none-fails.txt
new file mode 100644
index 000000000000..9586b2339f6f
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/virtio_gpu-none-fails.txt
@@ -0,0 +1,38 @@
+kms_addfb_basic@addfb25-bad-modifier,Fail
+kms_addfb_basic@bad-pitch-65536,Fail
+kms_addfb_basic@bo-too-small,Fail
+kms_addfb_basic@size-max,Fail
+kms_addfb_basic@too-high,Fail
+kms_atomic_transition@plane-primary-toggle-with-vblank-wait,Fail
+kms_bw@linear-tiling-1-displays-1920x1080p,Fail
+kms_bw@linear-tiling-1-displays-2560x1440p,Fail
+kms_bw@linear-tiling-1-displays-3840x2160p,Fail
+kms_bw@linear-tiling-2-displays-1920x1080p,Fail
+kms_bw@linear-tiling-2-displays-2560x1440p,Fail
+kms_bw@linear-tiling-2-displays-3840x2160p,Fail
+kms_invalid_mode@int-max-clock,Fail
+kms_plane_scaling@downscale-with-modifier-factor-0-25,Fail
+kms_plane_scaling@downscale-with-rotation-factor-0-25,Fail
+kms_plane_scaling@planes-upscale-20x20,Fail
+kms_plane_scaling@planes-upscale-20x20-downscale-factor-0-25,Fail
+kms_plane_scaling@planes-upscale-20x20-downscale-factor-0-5,Fail
+kms_plane_scaling@planes-upscale-20x20-downscale-factor-0-75,Fail
+kms_plane_scaling@upscale-with-modifier-20x20,Fail
+kms_plane_scaling@upscale-with-modifier-factor-0-25,Fail
+kms_plane_scaling@upscale-with-pixel-format-20x20,Fail
+kms_plane_scaling@upscale-with-pixel-format-factor-0-25,Fail
+kms_plane_scaling@upscale-with-rotation-20x20,Fail
+kms_vblank@crtc-id,Fail
+kms_vblank@invalid,Fail
+kms_vblank@pipe-A-accuracy-idle,Fail
+kms_vblank@pipe-A-query-busy,Fail
+kms_vblank@pipe-A-query-forked,Fail
+kms_vblank@pipe-A-query-forked-busy,Fail
+kms_vblank@pipe-A-query-idle,Fail
+kms_vblank@pipe-A-ts-continuation-idle,Fail
+kms_vblank@pipe-A-ts-continuation-modeset,Fail
+kms_vblank@pipe-A-ts-continuation-suspend,Fail
+kms_vblank@pipe-A-wait-busy,Fail
+kms_vblank@pipe-A-wait-forked,Fail
+kms_vblank@pipe-A-wait-forked-busy,Fail
+kms_vblank@pipe-A-wait-idle,Fail
diff --git a/drivers/gpu/drm/ci/xfails/virtio_gpu-none-flakes.txt b/drivers/gpu/drm/ci/xfails/virtio_gpu-none-flakes.txt
new file mode 100644
index 000000000000..e69de29bb2d1
diff --git a/drivers/gpu/drm/ci/xfails/virtio_gpu-none-skips.txt b/drivers/gpu/drm/ci/xfails/virtio_gpu-none-skips.txt
new file mode 100644
index 000000000000..78be18174012
--- /dev/null
+++ b/drivers/gpu/drm/ci/xfails/virtio_gpu-none-skips.txt
@@ -0,0 +1,6 @@
+# Hits a "refcount_t: underflow; use-after-free" in virtio_gpu_fence_event_process
+# When run in a particular order with other tests
+kms_cursor_legacy.*
+
+# Job just hangs without any output
+kms_flip@flip-vs-suspend.*
\ No newline at end of file

From ad6bfe1b66a5c146ec236847eca7af4c8806d666 Mon Sep 17 00:00:00 2001
From: Helen Koike <helen.koike@collabora.com>
Date: Thu, 24 Aug 2023 13:42:30 -0300
Subject: [PATCH 0766/1189] drm: ci: docs: fix build warning - add missing
 escape

Fix the following warning:

Documentation/gpu/automated_testing.rst:55: WARNING: Inline emphasis start-string without end-string.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Helen Koike <helen.koike@collabora.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20230824164230.48470-1-helen.koike@collabora.com
---
 Documentation/gpu/automated_testing.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/gpu/automated_testing.rst b/Documentation/gpu/automated_testing.rst
index 1b87b802ac7f..469b6fb65c30 100644
--- a/Documentation/gpu/automated_testing.rst
+++ b/Documentation/gpu/automated_testing.rst
@@ -52,7 +52,7 @@ IGT_VERSION
 drivers/gpu/drm/ci/testlist.txt
 -------------------------------
 
-IGT tests to be run on all drivers (unless mentioned in a driver's *-skips.txt
+IGT tests to be run on all drivers (unless mentioned in a driver's \*-skips.txt
 file, see below).
 
 drivers/gpu/drm/ci/${DRIVER_NAME}-${HW_REVISION}-fails.txt

From c69290557c7571dff3d995fa27619b965915e8a1 Mon Sep 17 00:00:00 2001
From: Vincent Whitchurch <vincent.whitchurch@axis.com>
Date: Tue, 29 Aug 2023 16:04:12 +0200
Subject: [PATCH 0767/1189] regulator: tps6287x: Fix n_voltages

There are 256 possible voltage settings for each range, not 256 possible
voltage settings in total.

Fixes: 15a1cd245d5b ("regulator: tps6287x: Fix missing .n_voltages setting")
Signed-off-by: Vincent Whitchurch <vincent.whitchurch@axis.com
Link: https://lore.kernel.org/r/20230829-tps-voltages-v1-1-7ba4f958a194@axis.com
Signed-off-by: Mark Brown <broonie@kernel.org
---
 drivers/regulator/tps6287x-regulator.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/regulator/tps6287x-regulator.c b/drivers/regulator/tps6287x-regulator.c
index d022184a8e7d..9b7c3d77789e 100644
--- a/drivers/regulator/tps6287x-regulator.c
+++ b/drivers/regulator/tps6287x-regulator.c
@@ -119,7 +119,7 @@ static struct regulator_desc tps6287x_reg = {
 	.ramp_mask = TPS6287X_CTRL1_VRAMP,
 	.ramp_delay_table = tps6287x_ramp_table,
 	.n_ramp_values = ARRAY_SIZE(tps6287x_ramp_table),
-	.n_voltages = 256,
+	.n_voltages = 256 * ARRAY_SIZE(tps6287x_voltage_ranges),
 	.linear_ranges = tps6287x_voltage_ranges,
 	.n_linear_ranges = ARRAY_SIZE(tps6287x_voltage_ranges),
 	.linear_range_selectors_bitfield = tps6287x_voltage_range_sel,

From 06afec5c988acb2c4f566eac2f6ec53d30d3a1b5 Mon Sep 17 00:00:00 2001
From: Simon Trimmer <simont@opensource.cirrus.com>
Date: Tue, 29 Aug 2023 17:04:33 +0100
Subject: [PATCH 0768/1189] ASoC: cs35l56: Waiting for firmware to boot must be
 tolerant of I/O errors

Ignore failure to read from the cs35l56 when polling as the device will
NAK i2c accesses until it has booted and this would terminate the poll
of regmap_read_poll_timeout().

Fixes: 8a731fd37f8b ("ASoC: cs35l56: Move utility functions to shared file")
Signed-off-by: Simon Trimmer <simont@opensource.cirrus.com
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com
Link: https://lore.kernel.org/r/20230829160433.2647889-1-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org
---
 sound/soc/codecs/cs35l56-shared.c | 27 ++++++++++++++-------------
 1 file changed, 14 insertions(+), 13 deletions(-)

diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c
index ae373f335ea8..98b1e63360ae 100644
--- a/sound/soc/codecs/cs35l56-shared.c
+++ b/sound/soc/codecs/cs35l56-shared.c
@@ -243,26 +243,27 @@ int cs35l56_wait_for_firmware_boot(struct cs35l56_base *cs35l56_base)
 {
 	unsigned int reg;
 	unsigned int val;
-	int ret;
+	int read_ret, poll_ret;
 
 	if (cs35l56_base->rev < CS35L56_REVID_B0)
 		reg = CS35L56_DSP1_HALO_STATE_A1;
 	else
 		reg = CS35L56_DSP1_HALO_STATE;
 
-	ret = regmap_read_poll_timeout(cs35l56_base->regmap, reg,
-				       val,
-				       (val < 0xFFFF) && (val >= CS35L56_HALO_STATE_BOOT_DONE),
-				       CS35L56_HALO_STATE_POLL_US,
-				       CS35L56_HALO_STATE_TIMEOUT_US);
+	/*
+	 * This can't be a regmap_read_poll_timeout() because cs35l56 will NAK
+	 * I2C until it has booted which would terminate the poll
+	 */
+	poll_ret = read_poll_timeout(regmap_read, read_ret,
+				     (val < 0xFFFF) && (val >= CS35L56_HALO_STATE_BOOT_DONE),
+				     CS35L56_HALO_STATE_POLL_US,
+				     CS35L56_HALO_STATE_TIMEOUT_US,
+				     false,
+				     cs35l56_base->regmap, reg, &val);
 
-	if ((ret < 0) && (ret != -ETIMEDOUT)) {
-		dev_err(cs35l56_base->dev, "Failed to read HALO_STATE: %d\n", ret);
-		return ret;
-	}
-
-	if ((ret == -ETIMEDOUT) || (val != CS35L56_HALO_STATE_BOOT_DONE)) {
-		dev_err(cs35l56_base->dev, "Firmware boot fail: HALO_STATE=%#x\n", val);
+	if (poll_ret) {
+		dev_err(cs35l56_base->dev, "Firmware boot timed out(%d): HALO_STATE=%#x\n",
+			read_ret, val);
 		return -EIO;
 	}
 

From 32337c0a28242f725c2c499c15100d67a4133050 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Sat, 26 Aug 2023 13:08:43 -0700
Subject: [PATCH 0769/1189] bpf: Prevent inlining of bpf_fentry_test7()

With latest clang18, I hit test_progs failures for the following test:

  #13/2    bpf_cookie/multi_kprobe_link_api:FAIL
  #13/3    bpf_cookie/multi_kprobe_attach_api:FAIL
  #13      bpf_cookie:FAIL
  #75      fentry_fexit:FAIL
  #76/1    fentry_test/fentry:FAIL
  #76      fentry_test:FAIL
  #80/1    fexit_test/fexit:FAIL
  #80      fexit_test:FAIL
  #110/1   kprobe_multi_test/skel_api:FAIL
  #110/2   kprobe_multi_test/link_api_addrs:FAIL
  #110/3   kprobe_multi_test/link_api_syms:FAIL
  #110/4   kprobe_multi_test/attach_api_pattern:FAIL
  #110/5   kprobe_multi_test/attach_api_addrs:FAIL
  #110/6   kprobe_multi_test/attach_api_syms:FAIL
  #110     kprobe_multi_test:FAIL

For example, for #13/2, the error messages are:

  [...]
  kprobe_multi_test_run:FAIL:kprobe_test7_result unexpected kprobe_test7_result: actual 0 != expected 1
  [...]
  kprobe_multi_test_run:FAIL:kretprobe_test7_result unexpected kretprobe_test7_result: actual 0 != expected 1

clang17 does not have this issue.

Further investigation shows that kernel func bpf_fentry_test7(), used in
the above tests, is inlined by the compiler although it is marked as
noinline.

  int noinline bpf_fentry_test7(struct bpf_fentry_test_t *arg)
  {
        return (long)arg;
  }

It is known that for simple functions like the above (e.g. just returning
a constant or an input argument), the clang compiler may still do inlining
for a noinline function. Adding 'asm volatile ("")' in the beginning of the
bpf_fentry_test7() can prevent inlining.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/bpf/20230826200843.2210074-1-yonghong.song@linux.dev
---
 net/bpf/test_run.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 57a7a64b84ed..0841f8d82419 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -543,6 +543,7 @@ struct bpf_fentry_test_t {
 
 int noinline bpf_fentry_test7(struct bpf_fentry_test_t *arg)
 {
+	asm volatile ("");
 	return (long)arg;
 }
 

From 6a8faf10709161e7138202a8cf052b070971239f Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Wed, 30 Aug 2023 03:03:25 +0000
Subject: [PATCH 0770/1189] bpftool: Fix build warnings with -Wtype-limits
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Quentin reported build warnings when building bpftool :

    link.c: In function ‘perf_config_hw_cache_str’:
    link.c:86:18: warning: comparison of unsigned expression in ‘>= 0’ is always true [-Wtype-limits]
       86 |         if ((id) >= 0 && (id) < ARRAY_SIZE(array))      \
          |                  ^~
    link.c:320:20: note: in expansion of macro ‘perf_event_name’
      320 |         hw_cache = perf_event_name(evsel__hw_cache, config & 0xff);
          |                    ^~~~~~~~~~~~~~~
    [... more of the same for the other calls to perf_event_name ...]

He also pointed out the reason and the solution:

  We're always passing unsigned, so it should be safe to drop the check on
  (id) >= 0.

Fixes: 62b57e3ddd64 ("bpftool: Add perf event names")
Reported-by: Quentin Monnet <quentin@isovalent.com>
Suggested-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Quentin Monnet <quentin@isovalent.com>
Closes: https://lore.kernel.org/bpf/a35d9a2d-54a0-49ec-9ed1-8fcf1369d3cc@isovalent.com
Link: https://lore.kernel.org/bpf/20230830030325.3786-1-laoar.shao@gmail.com
---
 tools/bpf/bpftool/link.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c
index 0b214f6ab5c8..2e5c231e08ac 100644
--- a/tools/bpf/bpftool/link.c
+++ b/tools/bpf/bpftool/link.c
@@ -83,7 +83,7 @@ const char *evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
 #define perf_event_name(array, id) ({			\
 	const char *event_str = NULL;			\
 							\
-	if ((id) >= 0 && (id) < ARRAY_SIZE(array))	\
+	if ((id) < ARRAY_SIZE(array))			\
 		event_str = array[id];			\
 	event_str;					\
 })

From 9d0a67b9d42c630d5013ef81587335d975a7a4a9 Mon Sep 17 00:00:00 2001
From: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Date: Wed, 23 Aug 2023 20:17:13 +0530
Subject: [PATCH 0771/1189] xsk: Fix xsk_build_skb() error: 'skb' dereferencing
 possible ERR_PTR()

Currently, xsk_build_skb() is a function that builds skb in two possible
ways and then is ended with common error handling.

We can distinguish four possible error paths and handling in xsk_build_skb():

 1. sock_alloc_send_skb fails: Retry (skb is NULL).
 2. skb_store_bits fails : Free skb and retry.
 3. MAX_SKB_FRAGS exceeded: Free skb, cleanup and drop packet.
 4. alloc_page fails for frag: Retry page allocation w/o freeing skb

1] and 3] can happen in xsk_build_skb_zerocopy(), which is one of the
two code paths responsible for building skb. Common error path in
xsk_build_skb() assumes that in case errno != -EAGAIN, skb is a valid
pointer, which is wrong as kernel test robot reports that in
xsk_build_skb_zerocopy() other errno values are returned for skb being
NULL.

To fix this, set -EOVERFLOW as error when MAX_SKB_FRAGS are exceeded
and packet needs to be dropped in both xsk_build_skb() and
xsk_build_skb_zerocopy() and use this to distinguish against all other
error cases. Also, add explicit kfree_skb() for 3] so that handling
of 1], 2], and 3] becomes identical where allocation needs to be retried.

Fixes: cf24f5a5feea ("xsk: add support for AF_XDP multi-buffer on Tx path")
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Closes: https://lore.kernel.org/r/202307210434.OjgqFcbB-lkp@intel.com
Link: https://lore.kernel.org/bpf/20230823144713.2231808-1-tirthendu.sarkar@intel.com
---
 net/xdp/xsk.c | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index fcfc8472f73d..55f8b9b0e06d 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -602,7 +602,7 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
 
 	for (copied = 0, i = skb_shinfo(skb)->nr_frags; copied < len; i++) {
 		if (unlikely(i >= MAX_SKB_FRAGS))
-			return ERR_PTR(-EFAULT);
+			return ERR_PTR(-EOVERFLOW);
 
 		page = pool->umem->pgs[addr >> PAGE_SHIFT];
 		get_page(page);
@@ -655,15 +655,17 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 			skb_put(skb, len);
 
 			err = skb_store_bits(skb, 0, buffer, len);
-			if (unlikely(err))
+			if (unlikely(err)) {
+				kfree_skb(skb);
 				goto free_err;
+			}
 		} else {
 			int nr_frags = skb_shinfo(skb)->nr_frags;
 			struct page *page;
 			u8 *vaddr;
 
 			if (unlikely(nr_frags == (MAX_SKB_FRAGS - 1) && xp_mb_desc(desc))) {
-				err = -EFAULT;
+				err = -EOVERFLOW;
 				goto free_err;
 			}
 
@@ -690,12 +692,14 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 	return skb;
 
 free_err:
-	if (err == -EAGAIN) {
-		xsk_cq_cancel_locked(xs, 1);
-	} else {
-		xsk_set_destructor_arg(skb);
-		xsk_drop_skb(skb);
+	if (err == -EOVERFLOW) {
+		/* Drop the packet */
+		xsk_set_destructor_arg(xs->skb);
+		xsk_drop_skb(xs->skb);
 		xskq_cons_release(xs->tx);
+	} else {
+		/* Let application retry */
+		xsk_cq_cancel_locked(xs, 1);
 	}
 
 	return ERR_PTR(err);
@@ -738,7 +742,7 @@ static int __xsk_generic_xmit(struct sock *sk)
 		skb = xsk_build_skb(xs, &desc);
 		if (IS_ERR(skb)) {
 			err = PTR_ERR(skb);
-			if (err == -EAGAIN)
+			if (err != -EOVERFLOW)
 				goto out;
 			err = 0;
 			continue;

From 5439cfa7fe612e7d02d5a1234feda3fa6e483ba7 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Sun, 27 Aug 2023 08:05:51 -0700
Subject: [PATCH 0772/1189] selftests/bpf: Fix flaky cgroup_iter_sleepable
 subtest

Occasionally, with './test_progs -j' on my vm, I will hit the
following failure:

  test_cgrp_local_storage:PASS:join_cgroup /cgrp_local_storage 0 nsec
  test_cgroup_iter_sleepable:PASS:skel_open 0 nsec
  test_cgroup_iter_sleepable:PASS:skel_load 0 nsec
  test_cgroup_iter_sleepable:PASS:attach_iter 0 nsec
  test_cgroup_iter_sleepable:PASS:iter_create 0 nsec
  test_cgroup_iter_sleepable:FAIL:cgroup_id unexpected cgroup_id: actual 1 != expected 2812
  #48/5    cgrp_local_storage/cgroup_iter_sleepable:FAIL
  #48      cgrp_local_storage:FAIL

Finally, I decided to do some investigation since the test is introduced
by myself. It turns out the reason is due to cgroup_fd with value 0.
In cgroup_iter, a cgroup_fd of value 0 means the root cgroup.

	/* from cgroup_iter.c */
        if (fd)
                cgrp = cgroup_v1v2_get_from_fd(fd);
        else if (id)
                cgrp = cgroup_get_from_id(id);
        else /* walk the entire hierarchy by default. */
                cgrp = cgroup_get_from_path("/");

That is why we got cgroup_id 1 instead of expected 2812.

Why we got a cgroup_fd 0? Nobody should really touch 'stdin' (fd 0) in
test_progs. I traced 'close' syscall with stack trace and found the root
cause, which is a bug in bpf_obj_pinning.c. Basically, the code closed
fd 0 although it should not. Fixing the bug in bpf_obj_pinning.c also
resolved the above cgroup_iter_sleepable subtest failure.

Fixes: 3b22f98e5a05 ("selftests/bpf: Add path_fd-based BPF_OBJ_PIN and BPF_OBJ_GET tests")
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20230827150551.1743497-1-yonghong.song@linux.dev
---
 tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c
index 31f1e815f671..ee0458a5ce78 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c
@@ -8,6 +8,7 @@
 #include <linux/unistd.h>
 #include <linux/mount.h>
 #include <sys/syscall.h>
+#include "bpf/libbpf_internal.h"
 
 static inline int sys_fsopen(const char *fsname, unsigned flags)
 {
@@ -155,7 +156,7 @@ static void validate_pin(int map_fd, const char *map_name, int src_value,
 	ASSERT_OK(err, "obj_pin");
 
 	/* cleanup */
-	if (pin_opts.path_fd >= 0)
+	if (path_kind == PATH_FD_REL && pin_opts.path_fd >= 0)
 		close(pin_opts.path_fd);
 	if (old_cwd[0])
 		ASSERT_OK(chdir(old_cwd), "restore_cwd");
@@ -220,7 +221,7 @@ static void validate_get(int map_fd, const char *map_name, int src_value,
 		goto cleanup;
 
 	/* cleanup */
-	if (get_opts.path_fd >= 0)
+	if (path_kind == PATH_FD_REL && get_opts.path_fd >= 0)
 		close(get_opts.path_fd);
 	if (old_cwd[0])
 		ASSERT_OK(chdir(old_cwd), "restore_cwd");

From 2d71a90f7e0fa3cd348602a36f6eb1237ab7cebb Mon Sep 17 00:00:00 2001
From: Will Hawkins <hawkinsw@obs.cr>
Date: Sat, 26 Aug 2023 01:32:54 -0400
Subject: [PATCH 0773/1189] bpf, docs: Correct source of offset for
 program-local call

The offset to use when calculating the target of a program-local call is
in the instruction's imm field, not its offset field.

Signed-off-by: Will Hawkins <hawkinsw@obs.cr>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Acked-by: David Vernet <void@manifault.com>
Link: https://lore.kernel.org/bpf/20230826053258.1860167-1-hawkinsw@obs.cr
---
 Documentation/bpf/standardization/instruction-set.rst | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/Documentation/bpf/standardization/instruction-set.rst b/Documentation/bpf/standardization/instruction-set.rst
index 4f73e9dc8d9e..c5b0b2011f16 100644
--- a/Documentation/bpf/standardization/instruction-set.rst
+++ b/Documentation/bpf/standardization/instruction-set.rst
@@ -373,7 +373,7 @@ BPF_JNE   0x5    any  PC += offset if dst != src
 BPF_JSGT  0x6    any  PC += offset if dst > src                    signed
 BPF_JSGE  0x7    any  PC += offset if dst >= src                   signed
 BPF_CALL  0x8    0x0  call helper function by address              see `Helper functions`_
-BPF_CALL  0x8    0x1  call PC += offset                            see `Program-local functions`_
+BPF_CALL  0x8    0x1  call PC += imm                               see `Program-local functions`_
 BPF_CALL  0x8    0x2  call helper function by BTF ID               see `Helper functions`_
 BPF_EXIT  0x9    0x0  return                                       BPF_JMP only
 BPF_JLT   0xa    any  PC += offset if dst < src                    unsigned
@@ -424,8 +424,8 @@ Program-local functions
 ~~~~~~~~~~~~~~~~~~~~~~~
 Program-local functions are functions exposed by the same BPF program as the
 caller, and are referenced by offset from the call instruction, similar to
-``BPF_JA``.  A ``BPF_EXIT`` within the program-local function will return to
-the caller.
+``BPF_JA``.  The offset is encoded in the imm field of the call instruction.
+A ``BPF_EXIT`` within the program-local function will return to the caller.
 
 Load and store instructions
 ===========================

From be4033d36070e44fba766a21ef2d0c24fa04c377 Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Sun, 27 Aug 2023 01:29:12 +0300
Subject: [PATCH 0774/1189] docs/bpf: Add description for CO-RE relocations

Add a section on CO-RE relocations to llvm_relo.rst. Describe relevant .BTF.ext
structure, `enum bpf_core_relo_kind` and `struct bpf_core_relo` in some detail.

Description is based on doc-strings from:

  - include/uapi/linux/bpf.h:struct bpf_core_relo
  - tools/lib/bpf/relo_core.c:__bpf_core_types_match()

Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/bpf/20230826222912.2560865-2-eddyz87@gmail.com
---
 Documentation/bpf/btf.rst        |  31 +++-
 Documentation/bpf/llvm_reloc.rst | 304 +++++++++++++++++++++++++++++++
 2 files changed, 329 insertions(+), 6 deletions(-)

diff --git a/Documentation/bpf/btf.rst b/Documentation/bpf/btf.rst
index f32db1f44ae9..ffc11afee569 100644
--- a/Documentation/bpf/btf.rst
+++ b/Documentation/bpf/btf.rst
@@ -726,8 +726,8 @@ same as the one describe in :ref:`BTF_Type_String`.
 4.2 .BTF.ext section
 --------------------
 
-The .BTF.ext section encodes func_info and line_info which needs loader
-manipulation before loading into the kernel.
+The .BTF.ext section encodes func_info, line_info and CO-RE relocations
+which needs loader manipulation before loading into the kernel.
 
 The specification for .BTF.ext section is defined at ``tools/lib/bpf/btf.h``
 and ``tools/lib/bpf/btf.c``.
@@ -745,15 +745,20 @@ The current header of .BTF.ext section::
         __u32   func_info_len;
         __u32   line_info_off;
         __u32   line_info_len;
+
+        /* optional part of .BTF.ext header */
+        __u32   core_relo_off;
+        __u32   core_relo_len;
     };
 
 It is very similar to .BTF section. Instead of type/string section, it
-contains func_info and line_info section. See :ref:`BPF_Prog_Load` for details
-about func_info and line_info record format.
+contains func_info, line_info and core_relo sub-sections.
+See :ref:`BPF_Prog_Load` for details about func_info and line_info
+record format.
 
 The func_info is organized as below.::
 
-     func_info_rec_size
+     func_info_rec_size              /* __u32 value */
      btf_ext_info_sec for section #1 /* func_info for section #1 */
      btf_ext_info_sec for section #2 /* func_info for section #2 */
      ...
@@ -773,7 +778,7 @@ Here, num_info must be greater than 0.
 
 The line_info is organized as below.::
 
-     line_info_rec_size
+     line_info_rec_size              /* __u32 value */
      btf_ext_info_sec for section #1 /* line_info for section #1 */
      btf_ext_info_sec for section #2 /* line_info for section #2 */
      ...
@@ -787,6 +792,20 @@ kernel API, the ``insn_off`` is the instruction offset in the unit of ``struct
 bpf_insn``. For ELF API, the ``insn_off`` is the byte offset from the
 beginning of section (``btf_ext_info_sec->sec_name_off``).
 
+The core_relo is organized as below.::
+
+     core_relo_rec_size              /* __u32 value */
+     btf_ext_info_sec for section #1 /* core_relo for section #1 */
+     btf_ext_info_sec for section #2 /* core_relo for section #2 */
+
+``core_relo_rec_size`` specifies the size of ``bpf_core_relo``
+structure when .BTF.ext is generated. All ``bpf_core_relo`` structures
+within a single ``btf_ext_info_sec`` describe relocations applied to
+section named by ``btf_ext_info_sec->sec_name_off``.
+
+See :ref:`Documentation/bpf/llvm_reloc <btf-co-re-relocations>`
+for more information on CO-RE relocations.
+
 4.2 .BTF_ids section
 --------------------
 
diff --git a/Documentation/bpf/llvm_reloc.rst b/Documentation/bpf/llvm_reloc.rst
index 450e6403fe3d..73bf805000f2 100644
--- a/Documentation/bpf/llvm_reloc.rst
+++ b/Documentation/bpf/llvm_reloc.rst
@@ -240,3 +240,307 @@ The .BTF/.BTF.ext sections has R_BPF_64_NODYLD32 relocations::
       Offset             Info             Type               Symbol's Value  Symbol's Name
   000000000000002c  0000000200000004 R_BPF_64_NODYLD32      0000000000000000 .text
   0000000000000040  0000000200000004 R_BPF_64_NODYLD32      0000000000000000 .text
+
+.. _btf-co-re-relocations:
+
+=================
+CO-RE Relocations
+=================
+
+From object file point of view CO-RE mechanism is implemented as a set
+of CO-RE specific relocation records. These relocation records are not
+related to ELF relocations and are encoded in .BTF.ext section.
+See :ref:`Documentation/bpf/btf <BTF_Ext_Section>` for more
+information on .BTF.ext structure.
+
+CO-RE relocations are applied to BPF instructions to update immediate
+or offset fields of the instruction at load time with information
+relevant for target kernel.
+
+Field to patch is selected basing on the instruction class:
+
+* For BPF_ALU, BPF_ALU64, BPF_LD `immediate` field is patched;
+* For BPF_LDX, BPF_STX, BPF_ST `offset` field is patched;
+* BPF_JMP, BPF_JMP32 instructions **should not** be patched.
+
+Relocation kinds
+================
+
+There are several kinds of CO-RE relocations that could be split in
+three groups:
+
+* Field-based - patch instruction with field related information, e.g.
+  change offset field of the BPF_LDX instruction to reflect offset
+  of a specific structure field in the target kernel.
+
+* Type-based - patch instruction with type related information, e.g.
+  change immediate field of the BPF_ALU move instruction to 0 or 1 to
+  reflect if specific type is present in the target kernel.
+
+* Enum-based - patch instruction with enum related information, e.g.
+  change immediate field of the BPF_LD_IMM64 instruction to reflect
+  value of a specific enum literal in the target kernel.
+
+The complete list of relocation kinds is represented by the following enum:
+
+.. code-block:: c
+
+ enum bpf_core_relo_kind {
+	BPF_CORE_FIELD_BYTE_OFFSET = 0,  /* field byte offset */
+	BPF_CORE_FIELD_BYTE_SIZE   = 1,  /* field size in bytes */
+	BPF_CORE_FIELD_EXISTS      = 2,  /* field existence in target kernel */
+	BPF_CORE_FIELD_SIGNED      = 3,  /* field signedness (0 - unsigned, 1 - signed) */
+	BPF_CORE_FIELD_LSHIFT_U64  = 4,  /* bitfield-specific left bitshift */
+	BPF_CORE_FIELD_RSHIFT_U64  = 5,  /* bitfield-specific right bitshift */
+	BPF_CORE_TYPE_ID_LOCAL     = 6,  /* type ID in local BPF object */
+	BPF_CORE_TYPE_ID_TARGET    = 7,  /* type ID in target kernel */
+	BPF_CORE_TYPE_EXISTS       = 8,  /* type existence in target kernel */
+	BPF_CORE_TYPE_SIZE         = 9,  /* type size in bytes */
+	BPF_CORE_ENUMVAL_EXISTS    = 10, /* enum value existence in target kernel */
+	BPF_CORE_ENUMVAL_VALUE     = 11, /* enum value integer value */
+	BPF_CORE_TYPE_MATCHES      = 12, /* type match in target kernel */
+ };
+
+Notes:
+
+* ``BPF_CORE_FIELD_LSHIFT_U64`` and ``BPF_CORE_FIELD_RSHIFT_U64`` are
+  supposed to be used to read bitfield values using the following
+  algorithm:
+
+  .. code-block:: c
+
+     // To read bitfield ``f`` from ``struct s``
+     is_signed = relo(s->f, BPF_CORE_FIELD_SIGNED)
+     off = relo(s->f, BPF_CORE_FIELD_BYTE_OFFSET)
+     sz  = relo(s->f, BPF_CORE_FIELD_BYTE_SIZE)
+     l   = relo(s->f, BPF_CORE_FIELD_LSHIFT_U64)
+     r   = relo(s->f, BPF_CORE_FIELD_RSHIFT_U64)
+     // define ``v`` as signed or unsigned integer of size ``sz``
+     v = *({s|u}<sz> *)((void *)s + off)
+     v <<= l
+     v >>= r
+
+* The ``BPF_CORE_TYPE_MATCHES`` queries matching relation, defined as
+  follows:
+
+  * for integers: types match if size and signedness match;
+  * for arrays & pointers: target types are recursively matched;
+  * for structs & unions:
+
+    * local members need to exist in target with the same name;
+
+    * for each member we recursively check match unless it is already behind a
+      pointer, in which case we only check matching names and compatible kind;
+
+  * for enums:
+
+    * local variants have to have a match in target by symbolic name (but not
+      numeric value);
+
+    * size has to match (but enum may match enum64 and vice versa);
+
+  * for function pointers:
+
+    * number and position of arguments in local type has to match target;
+    * for each argument and the return value we recursively check match.
+
+CO-RE Relocation Record
+=======================
+
+Relocation record is encoded as the following structure:
+
+.. code-block:: c
+
+ struct bpf_core_relo {
+	__u32 insn_off;
+	__u32 type_id;
+	__u32 access_str_off;
+	enum bpf_core_relo_kind kind;
+ };
+
+* ``insn_off`` - instruction offset (in bytes) within a code section
+  associated with this relocation;
+
+* ``type_id`` - BTF type ID of the "root" (containing) entity of a
+  relocatable type or field;
+
+* ``access_str_off`` - offset into corresponding .BTF string section.
+  String interpretation depends on specific relocation kind:
+
+  * for field-based relocations, string encodes an accessed field using
+    a sequence of field and array indices, separated by colon (:). It's
+    conceptually very close to LLVM's `getelementptr <GEP_>`_ instruction's
+    arguments for identifying offset to a field. For example, consider the
+    following C code:
+
+    .. code-block:: c
+
+       struct sample {
+           int a;
+           int b;
+           struct { int c[10]; };
+       } __attribute__((preserve_access_index));
+       struct sample *s;
+
+    * Access to ``s[0].a`` would be encoded as ``0:0``:
+
+      * ``0``: first element of ``s`` (as if ``s`` is an array);
+      * ``0``: index of field ``a`` in ``struct sample``.
+
+    * Access to ``s->a`` would be encoded as ``0:0`` as well.
+    * Access to ``s->b`` would be encoded as ``0:1``:
+
+      * ``0``: first element of ``s``;
+      * ``1``: index of field ``b`` in ``struct sample``.
+
+    * Access to ``s[1].c[5]`` would be encoded as ``1:2:0:5``:
+
+      * ``1``: second element of ``s``;
+      * ``2``: index of anonymous structure field in ``struct sample``;
+      * ``0``: index of field ``c`` in anonymous structure;
+      * ``5``: access to array element #5.
+
+  * for type-based relocations, string is expected to be just "0";
+
+  * for enum value-based relocations, string contains an index of enum
+     value within its enum type;
+
+* ``kind`` - one of ``enum bpf_core_relo_kind``.
+
+.. _GEP: https://llvm.org/docs/LangRef.html#getelementptr-instruction
+
+.. _btf_co_re_relocation_examples:
+
+CO-RE Relocation Examples
+=========================
+
+For the following C code:
+
+.. code-block:: c
+
+ struct foo {
+   int a;
+   int b;
+   unsigned c:15;
+ } __attribute__((preserve_access_index));
+
+ enum bar { U, V };
+
+With the following BTF definitions:
+
+.. code-block::
+
+ ...
+ [2] STRUCT 'foo' size=8 vlen=2
+        'a' type_id=3 bits_offset=0
+        'b' type_id=3 bits_offset=32
+        'c' type_id=4 bits_offset=64 bitfield_size=15
+ [3] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED
+ [4] INT 'unsigned int' size=4 bits_offset=0 nr_bits=32 encoding=(none)
+ ...
+ [16] ENUM 'bar' encoding=UNSIGNED size=4 vlen=2
+        'U' val=0
+        'V' val=1
+
+Field offset relocations are generated automatically when
+``__attribute__((preserve_access_index))`` is used, for example:
+
+.. code-block:: c
+
+  void alpha(struct foo *s, volatile unsigned long *g) {
+    *g = s->a;
+    s->a = 1;
+  }
+
+  00 <alpha>:
+    0:  r3 = *(s32 *)(r1 + 0x0)
+           00:  CO-RE <byte_off> [2] struct foo::a (0:0)
+    1:  *(u64 *)(r2 + 0x0) = r3
+    2:  *(u32 *)(r1 + 0x0) = 0x1
+           10:  CO-RE <byte_off> [2] struct foo::a (0:0)
+    3:  exit
+
+
+All relocation kinds could be requested via built-in functions.
+E.g. field-based relocations:
+
+.. code-block:: c
+
+  void bravo(struct foo *s, volatile unsigned long *g) {
+    *g = __builtin_preserve_field_info(s->b, 0 /* field byte offset */);
+    *g = __builtin_preserve_field_info(s->b, 1 /* field byte size */);
+    *g = __builtin_preserve_field_info(s->b, 2 /* field existence */);
+    *g = __builtin_preserve_field_info(s->b, 3 /* field signedness */);
+    *g = __builtin_preserve_field_info(s->c, 4 /* bitfield left shift */);
+    *g = __builtin_preserve_field_info(s->c, 5 /* bitfield right shift */);
+  }
+
+  20 <bravo>:
+     4:     r1 = 0x4
+            20:  CO-RE <byte_off> [2] struct foo::b (0:1)
+     5:     *(u64 *)(r2 + 0x0) = r1
+     6:     r1 = 0x4
+            30:  CO-RE <byte_sz> [2] struct foo::b (0:1)
+     7:     *(u64 *)(r2 + 0x0) = r1
+     8:     r1 = 0x1
+            40:  CO-RE <field_exists> [2] struct foo::b (0:1)
+     9:     *(u64 *)(r2 + 0x0) = r1
+    10:     r1 = 0x1
+            50:  CO-RE <signed> [2] struct foo::b (0:1)
+    11:     *(u64 *)(r2 + 0x0) = r1
+    12:     r1 = 0x31
+            60:  CO-RE <lshift_u64> [2] struct foo::c (0:2)
+    13:     *(u64 *)(r2 + 0x0) = r1
+    14:     r1 = 0x31
+            70:  CO-RE <rshift_u64> [2] struct foo::c (0:2)
+    15:     *(u64 *)(r2 + 0x0) = r1
+    16:     exit
+
+
+Type-based relocations:
+
+.. code-block:: c
+
+  void charlie(struct foo *s, volatile unsigned long *g) {
+    *g = __builtin_preserve_type_info(*s, 0 /* type existence */);
+    *g = __builtin_preserve_type_info(*s, 1 /* type size */);
+    *g = __builtin_preserve_type_info(*s, 2 /* type matches */);
+    *g = __builtin_btf_type_id(*s, 0 /* type id in this object file */);
+    *g = __builtin_btf_type_id(*s, 1 /* type id in target kernel */);
+  }
+
+  88 <charlie>:
+    17:     r1 = 0x1
+            88:  CO-RE <type_exists> [2] struct foo
+    18:     *(u64 *)(r2 + 0x0) = r1
+    19:     r1 = 0xc
+            98:  CO-RE <type_size> [2] struct foo
+    20:     *(u64 *)(r2 + 0x0) = r1
+    21:     r1 = 0x1
+            a8:  CO-RE <type_matches> [2] struct foo
+    22:     *(u64 *)(r2 + 0x0) = r1
+    23:     r1 = 0x2 ll
+            b8:  CO-RE <local_type_id> [2] struct foo
+    25:     *(u64 *)(r2 + 0x0) = r1
+    26:     r1 = 0x2 ll
+            d0:  CO-RE <target_type_id> [2] struct foo
+    28:     *(u64 *)(r2 + 0x0) = r1
+    29:     exit
+
+Enum-based relocations:
+
+.. code-block:: c
+
+  void delta(struct foo *s, volatile unsigned long *g) {
+    *g = __builtin_preserve_enum_value(*(enum bar *)U, 0 /* enum literal existence */);
+    *g = __builtin_preserve_enum_value(*(enum bar *)V, 1 /* enum literal value */);
+  }
+
+  f0 <delta>:
+    30:     r1 = 0x1 ll
+            f0:  CO-RE <enumval_exists> [16] enum bar::U = 0
+    32:     *(u64 *)(r2 + 0x0) = r1
+    33:     r1 = 0x1 ll
+            108:  CO-RE <enumval_value> [16] enum bar::V = 1
+    35:     *(u64 *)(r2 + 0x0) = r1
+    36:     exit

From 35d2b7ffffc1d9b3dc6c761010aa3338da49165b Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Tue, 29 Aug 2023 22:35:17 -0700
Subject: [PATCH 0775/1189] bpf, sockmap: Fix preempt_rt splat when using
 raw_spin_lock_t

Sockmap and sockhash maps are a collection of psocks that are
objects representing a socket plus a set of metadata needed
to manage the BPF programs associated with the socket. These
maps use the stab->lock to protect from concurrent operations
on the maps, e.g. trying to insert to objects into the array
at the same time in the same slot. Additionally, a sockhash map
has a bucket lock to protect iteration and insert/delete into
the hash entry.

Each psock has a psock->link which is a linked list of all the
maps that a psock is attached to. This allows a psock (socket)
to be included in multiple sockmap and sockhash maps. This
linked list is protected the psock->link_lock.

They _must_ be nested correctly to avoid deadlock:

  lock(stab->lock)
    : do BPF map operations and psock insert/delete
    lock(psock->link_lock)
       : add map to psock linked list of maps
    unlock(psock->link_lock)
  unlock(stab->lock)

For non PREEMPT_RT kernels both raw_spin_lock_t and spin_lock_t
are guaranteed to not sleep. But, with PREEMPT_RT kernels the
spin_lock_t variants may sleep. In the current code we have
many patterns like this:

   rcu_critical_section:
      raw_spin_lock(stab->lock)
         spin_lock(psock->link_lock) <- may sleep ouch
         spin_unlock(psock->link_lock)
      raw_spin_unlock(stab->lock)
   rcu_critical_section

Nesting spin_lock() inside a raw_spin_lock() violates locking
rules for PREEMPT_RT kernels. And additionally we do alloc(GFP_ATOMICS)
inside the stab->lock, but those might sleep on PREEMPT_RT kernels.
The result is splats like this:

./test_progs -t sockmap_basic
[   33.344330] bpf_testmod: loading out-of-tree module taints kernel.
[   33.441933]
[   33.442089] =============================
[   33.442421] [ BUG: Invalid wait context ]
[   33.442763] 6.5.0-rc5-01731-gec0ded2e0282 #4958 Tainted: G           O
[   33.443320] -----------------------------
[   33.443624] test_progs/2073 is trying to lock:
[   33.443960] ffff888102a1c290 (&psock->link_lock){....}-{3:3}, at: sock_map_update_common+0x2c2/0x3d0
[   33.444636] other info that might help us debug this:
[   33.444991] context-{5:5}
[   33.445183] 3 locks held by test_progs/2073:
[   33.445498]  #0: ffff88811a208d30 (sk_lock-AF_INET){+.+.}-{0:0}, at: sock_map_update_elem_sys+0xff/0x330
[   33.446159]  #1: ffffffff842539e0 (rcu_read_lock){....}-{1:3}, at: sock_map_update_elem_sys+0xf5/0x330
[   33.446809]  #2: ffff88810d687240 (&stab->lock){+...}-{2:2}, at: sock_map_update_common+0x177/0x3d0
[   33.447445] stack backtrace:
[   33.447655] CPU: 10 PID

To fix observe we can't readily remove the allocations (for that
we would need to use/create something similar to bpf_map_alloc). So
convert raw_spin_lock_t to spin_lock_t. We note that sock_map_update
that would trigger the allocate and potential sleep is only allowed
through sys_bpf ops and via sock_ops which precludes hw interrupts
and low level atomic sections in RT preempt kernel. On non RT
preempt kernel there are no changes here and spin locks sections
and alloc(GFP_ATOMIC) are still not sleepable.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20230830053517.166611-1-john.fastabend@gmail.com
---
 net/core/sock_map.c | 36 ++++++++++++++++++------------------
 1 file changed, 18 insertions(+), 18 deletions(-)

diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 8f07fea39d9e..cb11750b1df5 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -18,7 +18,7 @@ struct bpf_stab {
 	struct bpf_map map;
 	struct sock **sks;
 	struct sk_psock_progs progs;
-	raw_spinlock_t lock;
+	spinlock_t lock;
 };
 
 #define SOCK_CREATE_FLAG_MASK				\
@@ -44,7 +44,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
 		return ERR_PTR(-ENOMEM);
 
 	bpf_map_init_from_attr(&stab->map, attr);
-	raw_spin_lock_init(&stab->lock);
+	spin_lock_init(&stab->lock);
 
 	stab->sks = bpf_map_area_alloc((u64) stab->map.max_entries *
 				       sizeof(struct sock *),
@@ -411,7 +411,7 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test,
 	struct sock *sk;
 	int err = 0;
 
-	raw_spin_lock_bh(&stab->lock);
+	spin_lock_bh(&stab->lock);
 	sk = *psk;
 	if (!sk_test || sk_test == sk)
 		sk = xchg(psk, NULL);
@@ -421,7 +421,7 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test,
 	else
 		err = -EINVAL;
 
-	raw_spin_unlock_bh(&stab->lock);
+	spin_unlock_bh(&stab->lock);
 	return err;
 }
 
@@ -487,7 +487,7 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx,
 	psock = sk_psock(sk);
 	WARN_ON_ONCE(!psock);
 
-	raw_spin_lock_bh(&stab->lock);
+	spin_lock_bh(&stab->lock);
 	osk = stab->sks[idx];
 	if (osk && flags == BPF_NOEXIST) {
 		ret = -EEXIST;
@@ -501,10 +501,10 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx,
 	stab->sks[idx] = sk;
 	if (osk)
 		sock_map_unref(osk, &stab->sks[idx]);
-	raw_spin_unlock_bh(&stab->lock);
+	spin_unlock_bh(&stab->lock);
 	return 0;
 out_unlock:
-	raw_spin_unlock_bh(&stab->lock);
+	spin_unlock_bh(&stab->lock);
 	if (psock)
 		sk_psock_put(sk, psock);
 out_free:
@@ -835,7 +835,7 @@ struct bpf_shtab_elem {
 
 struct bpf_shtab_bucket {
 	struct hlist_head head;
-	raw_spinlock_t lock;
+	spinlock_t lock;
 };
 
 struct bpf_shtab {
@@ -910,7 +910,7 @@ static void sock_hash_delete_from_link(struct bpf_map *map, struct sock *sk,
 	 * is okay since it's going away only after RCU grace period.
 	 * However, we need to check whether it's still present.
 	 */
-	raw_spin_lock_bh(&bucket->lock);
+	spin_lock_bh(&bucket->lock);
 	elem_probe = sock_hash_lookup_elem_raw(&bucket->head, elem->hash,
 					       elem->key, map->key_size);
 	if (elem_probe && elem_probe == elem) {
@@ -918,7 +918,7 @@ static void sock_hash_delete_from_link(struct bpf_map *map, struct sock *sk,
 		sock_map_unref(elem->sk, elem);
 		sock_hash_free_elem(htab, elem);
 	}
-	raw_spin_unlock_bh(&bucket->lock);
+	spin_unlock_bh(&bucket->lock);
 }
 
 static long sock_hash_delete_elem(struct bpf_map *map, void *key)
@@ -932,7 +932,7 @@ static long sock_hash_delete_elem(struct bpf_map *map, void *key)
 	hash = sock_hash_bucket_hash(key, key_size);
 	bucket = sock_hash_select_bucket(htab, hash);
 
-	raw_spin_lock_bh(&bucket->lock);
+	spin_lock_bh(&bucket->lock);
 	elem = sock_hash_lookup_elem_raw(&bucket->head, hash, key, key_size);
 	if (elem) {
 		hlist_del_rcu(&elem->node);
@@ -940,7 +940,7 @@ static long sock_hash_delete_elem(struct bpf_map *map, void *key)
 		sock_hash_free_elem(htab, elem);
 		ret = 0;
 	}
-	raw_spin_unlock_bh(&bucket->lock);
+	spin_unlock_bh(&bucket->lock);
 	return ret;
 }
 
@@ -1000,7 +1000,7 @@ static int sock_hash_update_common(struct bpf_map *map, void *key,
 	hash = sock_hash_bucket_hash(key, key_size);
 	bucket = sock_hash_select_bucket(htab, hash);
 
-	raw_spin_lock_bh(&bucket->lock);
+	spin_lock_bh(&bucket->lock);
 	elem = sock_hash_lookup_elem_raw(&bucket->head, hash, key, key_size);
 	if (elem && flags == BPF_NOEXIST) {
 		ret = -EEXIST;
@@ -1026,10 +1026,10 @@ static int sock_hash_update_common(struct bpf_map *map, void *key,
 		sock_map_unref(elem->sk, elem);
 		sock_hash_free_elem(htab, elem);
 	}
-	raw_spin_unlock_bh(&bucket->lock);
+	spin_unlock_bh(&bucket->lock);
 	return 0;
 out_unlock:
-	raw_spin_unlock_bh(&bucket->lock);
+	spin_unlock_bh(&bucket->lock);
 	sk_psock_put(sk, psock);
 out_free:
 	sk_psock_free_link(link);
@@ -1115,7 +1115,7 @@ static struct bpf_map *sock_hash_alloc(union bpf_attr *attr)
 
 	for (i = 0; i < htab->buckets_num; i++) {
 		INIT_HLIST_HEAD(&htab->buckets[i].head);
-		raw_spin_lock_init(&htab->buckets[i].lock);
+		spin_lock_init(&htab->buckets[i].lock);
 	}
 
 	return &htab->map;
@@ -1147,11 +1147,11 @@ static void sock_hash_free(struct bpf_map *map)
 		 * exists, psock exists and holds a ref to socket. That
 		 * lets us to grab a socket ref too.
 		 */
-		raw_spin_lock_bh(&bucket->lock);
+		spin_lock_bh(&bucket->lock);
 		hlist_for_each_entry(elem, &bucket->head, node)
 			sock_hold(elem->sk);
 		hlist_move_list(&bucket->head, &unlink_list);
-		raw_spin_unlock_bh(&bucket->lock);
+		spin_unlock_bh(&bucket->lock);
 
 		/* Process removed entries out of atomic context to
 		 * block for socket lock before deleting the psock's

From e4da8c78973c1e307c0431e0b99a969ffb8aa3f1 Mon Sep 17 00:00:00 2001
From: Heng Guo <heng.guo@windriver.com>
Date: Fri, 25 Aug 2023 15:55:05 +0800
Subject: [PATCH 0776/1189] net: ipv4, ipv6: fix IPSTATS_MIB_OUTOCTETS
 increment duplicated

commit edf391ff1723 ("snmp: add missing counters for RFC 4293") had
already added OutOctets for RFC 4293. In commit 2d8dbb04c63e ("snmp: fix
OutOctets counter to include forwarded datagrams"), OutOctets was
counted again, but not removed from ip_output().

According to RFC 4293 "3.2.3. IP Statistics Tables",
ipipIfStatsOutTransmits is not equal to ipIfStatsOutForwDatagrams. So
"IPSTATS_MIB_OUTOCTETS must be incremented when incrementing" is not
accurate. And IPSTATS_MIB_OUTOCTETS should be counted after fragment.

This patch reverts commit 2d8dbb04c63e ("snmp: fix OutOctets counter to
include forwarded datagrams") and move IPSTATS_MIB_OUTOCTETS to
ip_finish_output2 for ipv4.

Reviewed-by: Filip Pudak <filip.pudak@windriver.com>
Signed-off-by: Heng Guo <heng.guo@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_forward.c | 1 -
 net/ipv4/ip_output.c  | 7 +++----
 net/ipv4/ipmr.c       | 1 -
 net/ipv6/ip6_output.c | 1 -
 net/ipv6/ip6mr.c      | 2 --
 5 files changed, 3 insertions(+), 9 deletions(-)

diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index e18931a6d153..66fac1216d46 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -67,7 +67,6 @@ static int ip_forward_finish(struct net *net, struct sock *sk, struct sk_buff *s
 	struct ip_options *opt	= &(IPCB(skb)->opt);
 
 	__IP_INC_STATS(net, IPSTATS_MIB_OUTFORWDATAGRAMS);
-	__IP_ADD_STATS(net, IPSTATS_MIB_OUTOCTETS, skb->len);
 
 #ifdef CONFIG_NET_SWITCHDEV
 	if (skb->offload_l3_fwd_mark) {
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 43ba4b77b248..b2e0ad312028 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -207,6 +207,9 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s
 	} else if (rt->rt_type == RTN_BROADCAST)
 		IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTBCAST, skb->len);
 
+	/* OUTOCTETS should be counted after fragment */
+	IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len);
+
 	if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
 		skb = skb_expand_head(skb, hh_len);
 		if (!skb)
@@ -366,8 +369,6 @@ int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 	/*
 	 *	If the indicated interface is up and running, send the packet.
 	 */
-	IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len);
-
 	skb->dev = dev;
 	skb->protocol = htons(ETH_P_IP);
 
@@ -424,8 +425,6 @@ int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	struct net_device *dev = skb_dst(skb)->dev, *indev = skb->dev;
 
-	IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len);
-
 	skb->dev = dev;
 	skb->protocol = htons(ETH_P_IP);
 
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 3f0c6d602fb7..9e222a57bc2b 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1804,7 +1804,6 @@ static inline int ipmr_forward_finish(struct net *net, struct sock *sk,
 	struct ip_options *opt = &(IPCB(skb)->opt);
 
 	IP_INC_STATS(net, IPSTATS_MIB_OUTFORWDATAGRAMS);
-	IP_ADD_STATS(net, IPSTATS_MIB_OUTOCTETS, skb->len);
 
 	if (unlikely(opt->optlen))
 		ip_forward_options(skb);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 0665e8b09968..4ab50169a5a9 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -451,7 +451,6 @@ static inline int ip6_forward_finish(struct net *net, struct sock *sk,
 	struct dst_entry *dst = skb_dst(skb);
 
 	__IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
-	__IP6_ADD_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len);
 
 #ifdef CONFIG_NET_SWITCHDEV
 	if (skb->offload_l3_fwd_mark) {
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 67a3b8f6e72b..30ca064b76ef 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -2010,8 +2010,6 @@ static inline int ip6mr_forward2_finish(struct net *net, struct sock *sk, struct
 {
 	IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
 		      IPSTATS_MIB_OUTFORWDATAGRAMS);
-	IP6_ADD_STATS(net, ip6_dst_idev(skb_dst(skb)),
-		      IPSTATS_MIB_OUTOCTETS, skb->len);
 	return dst_output(net, sk, skb);
 }
 

From 67ce50ce01d8abfa36612bcef9ec56e37b9fc247 Mon Sep 17 00:00:00 2001
From: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Date: Mon, 21 Aug 2023 15:57:39 +0200
Subject: [PATCH 0777/1189] s390/monreader: fix virtual vs physical address
 confusion

Fix virtual vs physical address confusion (which currently are the same).

Acked-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 drivers/s390/char/monreader.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/s390/char/monreader.c b/drivers/s390/char/monreader.c
index 9fa92e45e0ee..7207a7f5842a 100644
--- a/drivers/s390/char/monreader.c
+++ b/drivers/s390/char/monreader.c
@@ -111,7 +111,7 @@ static inline unsigned long mon_mca_end(struct mon_msg *monmsg)
 
 static inline u8 mon_mca_type(struct mon_msg *monmsg, u8 index)
 {
-	return *((u8 *) mon_mca_start(monmsg) + monmsg->mca_offset + index);
+	return *((u8 *)__va(mon_mca_start(monmsg)) + monmsg->mca_offset + index);
 }
 
 static inline u32 mon_mca_size(struct mon_msg *monmsg)
@@ -121,12 +121,12 @@ static inline u32 mon_mca_size(struct mon_msg *monmsg)
 
 static inline u32 mon_rec_start(struct mon_msg *monmsg)
 {
-	return *((u32 *) (mon_mca_start(monmsg) + monmsg->mca_offset + 4));
+	return *((u32 *)(__va(mon_mca_start(monmsg)) + monmsg->mca_offset + 4));
 }
 
 static inline u32 mon_rec_end(struct mon_msg *monmsg)
 {
-	return *((u32 *) (mon_mca_start(monmsg) + monmsg->mca_offset + 8));
+	return *((u32 *)(__va(mon_mca_start(monmsg)) + monmsg->mca_offset + 8));
 }
 
 static int mon_check_mca(struct mon_msg *monmsg)
@@ -392,8 +392,7 @@ static ssize_t mon_read(struct file *filp, char __user *data,
 	mce_start = mon_mca_start(monmsg) + monmsg->mca_offset;
 	if ((monmsg->pos >= mce_start) && (monmsg->pos < mce_start + 12)) {
 		count = min(count, (size_t) mce_start + 12 - monmsg->pos);
-		ret = copy_to_user(data, (void *) (unsigned long) monmsg->pos,
-				   count);
+		ret = copy_to_user(data, __va(monmsg->pos), count);
 		if (ret)
 			return -EFAULT;
 		monmsg->pos += count;
@@ -406,8 +405,7 @@ static ssize_t mon_read(struct file *filp, char __user *data,
 	if (monmsg->pos <= mon_rec_end(monmsg)) {
 		count = min(count, (size_t) mon_rec_end(monmsg) - monmsg->pos
 					    + 1);
-		ret = copy_to_user(data, (void *) (unsigned long) monmsg->pos,
-				   count);
+		ret = copy_to_user(data, __va(monmsg->pos), count);
 		if (ret)
 			return -EFAULT;
 		monmsg->pos += count;

From 789dd8cb1eb1503c8167bf2ffc88f74a70245044 Mon Sep 17 00:00:00 2001
From: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Date: Tue, 22 Aug 2023 17:19:32 +0200
Subject: [PATCH 0778/1189] s390/dcssblk: fix lockdep warning

dcssblk_remove_store() holds the dcssblk_devices_sem semaphore while
calling del_gendisk(dev_info->gd), which in turn tries to acquire
disk->open_mutex. Then there is dcssblk_release(), which is called
with disk->open_mutex held, and tries to acquire dcssblk_devices_sem.

Lockdep reports this as possible circular locking dependency (CPU0 =
dcssblk_remove_store, CPU1 = dcssblk_release):

[   44.948865]  Possible unsafe locking scenario:

[   44.948866]        CPU0                    CPU1
[   44.948867]        ----                    ----
[   44.948868]   lock(&dcssblk_devices_sem);
[   44.948870]                                lock(&disk->open_mutex);
[   44.948872]                                lock(&dcssblk_devices_sem);
[   44.948874]   lock(&disk->open_mutex);
[   44.948876]
                *** DEADLOCK ***

In practice, this deadlock should not happen, since dcssblk_remove_store()
checks for dev_info->use_count != 0 after acquiring dcssblk_devices_sem,
and breaks out before calling del_gendisk(). dev_info->use_count will be
decremented in dcssblk_release(), protected by dcssblk_devices_sem.

Still there is no need for dcssblk_remove_store() to hold the
dcssblk_devices_sem until after calling del_gendisk(), as this only
protects dcssblk internal data. So fix the lockdep warning by releasing
dcssblk_devices_sem earlier. Also move the segment_unload() loop up,
similar to dcssblk_shared_store() error path, no need to do that after
calling del_gendisk().

Also change dcssblk_shared_store() error path, where dcssblk_devices_sem
was also released only after calling del_gendisk(), and a similar lockdep
warning could be triggered (but also deadlock prevented by check for
dev_info->use_count).

Acked-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 drivers/s390/block/dcssblk.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index 06bcb6c78909..4b7ecd4fd431 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -411,13 +411,13 @@ removeseg:
 			segment_unload(entry->segment_name);
 	}
 	list_del(&dev_info->lh);
+	up_write(&dcssblk_devices_sem);
 
 	dax_remove_host(dev_info->gd);
 	kill_dax(dev_info->dax_dev);
 	put_dax(dev_info->dax_dev);
 	del_gendisk(dev_info->gd);
 	put_disk(dev_info->gd);
-	up_write(&dcssblk_devices_sem);
 
 	if (device_remove_file_self(dev, attr)) {
 		device_unregister(dev);
@@ -790,18 +790,17 @@ dcssblk_remove_store(struct device *dev, struct device_attribute *attr, const ch
 	}
 
 	list_del(&dev_info->lh);
+	/* unload all related segments */
+	list_for_each_entry(entry, &dev_info->seg_list, lh)
+		segment_unload(entry->segment_name);
+	up_write(&dcssblk_devices_sem);
+
 	dax_remove_host(dev_info->gd);
 	kill_dax(dev_info->dax_dev);
 	put_dax(dev_info->dax_dev);
 	del_gendisk(dev_info->gd);
 	put_disk(dev_info->gd);
 
-	/* unload all related segments */
-	list_for_each_entry(entry, &dev_info->seg_list, lh)
-		segment_unload(entry->segment_name);
-
-	up_write(&dcssblk_devices_sem);
-
 	device_unregister(&dev_info->dev);
 	put_device(&dev_info->dev);
 

From 7b03942ff33c3b242eb4b52d83dac8fa106c063c Mon Sep 17 00:00:00 2001
From: Alexander Gordeev <agordeev@linux.ibm.com>
Date: Thu, 3 Aug 2023 17:53:20 +0200
Subject: [PATCH 0779/1189] s390/vmem: fix virtual vs physical address
 confusion

Fix virtual vs physical address confusion (which currently are the same).

Reviewed-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/mm/vmem.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index e44243b9c0a4..0ae363cb47bc 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -747,8 +747,10 @@ void __init vmem_map_init(void)
 	}
 
 #ifdef CONFIG_KASAN
-	for_each_mem_range(i, &base, &end)
-		set_memory_kasan(base, end);
+	for_each_mem_range(i, &base, &end) {
+		set_memory_kasan((unsigned long)__va(base),
+				 (unsigned long)__va(end));
+	}
 #endif
 	set_memory_rox((unsigned long)_stext,
 		       (unsigned long)(_etext - _stext) >> PAGE_SHIFT);
@@ -763,8 +765,10 @@ void __init vmem_map_init(void)
 	if (static_key_enabled(&cpu_has_bear))
 		set_memory_nx(0, 1);
 	set_memory_nx(PAGE_SIZE, 1);
-	if (debug_pagealloc_enabled())
-		set_memory_4k(0, ident_map_size >> PAGE_SHIFT);
+	if (debug_pagealloc_enabled()) {
+		set_memory_4k((unsigned long)__va(0),
+			      ident_map_size >> PAGE_SHIFT);
+	}
 
 	pr_info("Write protected kernel read-only data: %luk\n",
 		(unsigned long)(__end_rodata - _stext) >> 10);

From b6f10e2f66e43b903b1f37b643d353fe364190cd Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Fri, 25 Aug 2023 14:29:47 +0200
Subject: [PATCH 0780/1189] s390: remove "noexec" option

Do the same like x86 with commit 76ea0025a214 ("x86/cpu: Remove "noexec"")
and remove the "noexec" kernel command line option.

Reviewed-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/boot/ipl_parm.c     | 7 -------
 arch/s390/boot/startup.c      | 2 +-
 arch/s390/include/asm/setup.h | 1 -
 arch/s390/kernel/early.c      | 3 +--
 arch/s390/kernel/setup.c      | 1 -
 5 files changed, 2 insertions(+), 12 deletions(-)

diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c
index 8753cb0339e5..7b7521762633 100644
--- a/arch/s390/boot/ipl_parm.c
+++ b/arch/s390/boot/ipl_parm.c
@@ -19,7 +19,6 @@ struct parmarea parmarea __section(".parmarea") = {
 };
 
 char __bootdata(early_command_line)[COMMAND_LINE_SIZE];
-int __bootdata(noexec_disabled);
 
 unsigned int __bootdata_preserved(zlib_dfltcc_support) = ZLIB_DFLTCC_FULL;
 struct ipl_parameter_block __bootdata_preserved(ipl_block);
@@ -290,12 +289,6 @@ void parse_boot_command_line(void)
 				zlib_dfltcc_support = ZLIB_DFLTCC_FULL_DEBUG;
 		}
 
-		if (!strcmp(param, "noexec")) {
-			rc = kstrtobool(val, &enabled);
-			if (!rc && !enabled)
-				noexec_disabled = 1;
-		}
-
 		if (!strcmp(param, "facilities") && val)
 			modify_fac_list(val);
 
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index b9681cb22753..caf562be3531 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -53,7 +53,7 @@ static void detect_facilities(void)
 	}
 	if (test_facility(78))
 		machine.has_edat2 = 1;
-	if (!noexec_disabled && test_facility(130)) {
+	if (test_facility(130)) {
 		machine.has_nx = 1;
 		__ctl_set_bit(0, 20);
 	}
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index b30fe91166e3..25cadc2b9cff 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -72,7 +72,6 @@ extern unsigned int zlib_dfltcc_support;
 #define ZLIB_DFLTCC_INFLATE_ONLY	3
 #define ZLIB_DFLTCC_FULL_DEBUG		4
 
-extern int noexec_disabled;
 extern unsigned long ident_map_size;
 extern unsigned long max_mappable;
 
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 2dd5976a55ac..3dccc6eb24a8 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -44,7 +44,6 @@ early_param(#param, ignore_decompressor_param_##param)
 decompressor_handled_param(mem);
 decompressor_handled_param(vmalloc);
 decompressor_handled_param(dfltcc);
-decompressor_handled_param(noexec);
 decompressor_handled_param(facilities);
 decompressor_handled_param(nokaslr);
 #if IS_ENABLED(CONFIG_KVM)
@@ -233,7 +232,7 @@ static __init void detect_machine_facilities(void)
 		S390_lowcore.machine_flags |= MACHINE_FLAG_VX;
 		__ctl_set_bit(0, 17);
 	}
-	if (test_facility(130) && !noexec_disabled) {
+	if (test_facility(130)) {
 		S390_lowcore.machine_flags |= MACHINE_FLAG_NX;
 		__ctl_set_bit(0, 20);
 	}
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index c744104e4a9c..5b18f8b1f318 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -145,7 +145,6 @@ static u32 __amode31_ref *__ctl_duald = __ctl_duald_amode31;
 static u32 __amode31_ref *__ctl_linkage_stack = __ctl_linkage_stack_amode31;
 static u32 __amode31_ref *__ctl_duct = __ctl_duct_amode31;
 
-int __bootdata(noexec_disabled);
 unsigned long __bootdata_preserved(max_mappable);
 unsigned long __bootdata(ident_map_size);
 struct physmem_info __bootdata(physmem_info);

From c0f1d478121131c2a97cab24148bf7ebb7ed3434 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Fri, 25 Aug 2023 14:29:48 +0200
Subject: [PATCH 0781/1189] s390/mm: simplify kernel mapping setup

The kernel mapping is setup in two stages: in the decompressor map all
pages with RWX permissions, and within the kernel change all mappings to
their final permissions, where most of the mappings are changed from RWX to
RWNX.

Change this and map all pages RWNX from the beginning, however without
enabling noexec via control register modification. This means that
effectively all pages are used with RWX permissions like before. When the
final permissions have been applied to the kernel mapping enable noexec via
control register modification.

This allows to remove quite a bit of non-obvious code.

Reviewed-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/boot/startup.c |   4 +-
 arch/s390/boot/vmem.c    |  12 +++--
 arch/s390/kernel/early.c |   4 +-
 arch/s390/mm/vmem.c      | 109 ++-------------------------------------
 4 files changed, 15 insertions(+), 114 deletions(-)

diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index caf562be3531..d3e48bd9c394 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -53,10 +53,8 @@ static void detect_facilities(void)
 	}
 	if (test_facility(78))
 		machine.has_edat2 = 1;
-	if (test_facility(130)) {
+	if (test_facility(130))
 		machine.has_nx = 1;
-		__ctl_set_bit(0, 20);
-	}
 }
 
 static void setup_lpp(void)
diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c
index c67f59db7a51..01257ce3b89c 100644
--- a/arch/s390/boot/vmem.c
+++ b/arch/s390/boot/vmem.c
@@ -287,7 +287,9 @@ static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long e
 			if (kasan_pte_populate_zero_shadow(pte, mode))
 				continue;
 			entry = __pte(_pa(addr, PAGE_SIZE, mode));
-			entry = set_pte_bit(entry, PAGE_KERNEL_EXEC);
+			entry = set_pte_bit(entry, PAGE_KERNEL);
+			if (!machine.has_nx)
+				entry = clear_pte_bit(entry, __pgprot(_PAGE_NOEXEC));
 			set_pte(pte, entry);
 			pages++;
 		}
@@ -311,7 +313,9 @@ static void pgtable_pmd_populate(pud_t *pud, unsigned long addr, unsigned long e
 				continue;
 			if (can_large_pmd(pmd, addr, next)) {
 				entry = __pmd(_pa(addr, _SEGMENT_SIZE, mode));
-				entry = set_pmd_bit(entry, SEGMENT_KERNEL_EXEC);
+				entry = set_pmd_bit(entry, SEGMENT_KERNEL);
+				if (!machine.has_nx)
+					entry = clear_pmd_bit(entry, __pgprot(_SEGMENT_ENTRY_NOEXEC));
 				set_pmd(pmd, entry);
 				pages++;
 				continue;
@@ -342,7 +346,9 @@ static void pgtable_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long e
 				continue;
 			if (can_large_pud(pud, addr, next)) {
 				entry = __pud(_pa(addr, _REGION3_SIZE, mode));
-				entry = set_pud_bit(entry, REGION3_KERNEL_EXEC);
+				entry = set_pud_bit(entry, REGION3_KERNEL);
+				if (!machine.has_nx)
+					entry = clear_pud_bit(entry, __pgprot(_REGION_ENTRY_NOEXEC));
 				set_pud(pud, entry);
 				pages++;
 				continue;
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 3dccc6eb24a8..442ce0489e1a 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -232,10 +232,8 @@ static __init void detect_machine_facilities(void)
 		S390_lowcore.machine_flags |= MACHINE_FLAG_VX;
 		__ctl_set_bit(0, 17);
 	}
-	if (test_facility(130)) {
+	if (test_facility(130))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_NX;
-		__ctl_set_bit(0, 20);
-	}
 	if (test_facility(133))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_GS;
 	if (test_facility(139) && (tod_clock_base.tod >> 63)) {
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index 0ae363cb47bc..261eea21ca10 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -5,7 +5,6 @@
 
 #include <linux/memory_hotplug.h>
 #include <linux/memblock.h>
-#include <linux/kasan.h>
 #include <linux/pfn.h>
 #include <linux/mm.h>
 #include <linux/init.h>
@@ -650,108 +649,8 @@ void vmem_unmap_4k_page(unsigned long addr)
 	mutex_unlock(&vmem_mutex);
 }
 
-static int __init memblock_region_cmp(const void *a, const void *b)
-{
-	const struct memblock_region *r1 = a;
-	const struct memblock_region *r2 = b;
-
-	if (r1->base < r2->base)
-		return -1;
-	if (r1->base > r2->base)
-		return 1;
-	return 0;
-}
-
-static void __init memblock_region_swap(void *a, void *b, int size)
-{
-	swap(*(struct memblock_region *)a, *(struct memblock_region *)b);
-}
-
-#ifdef CONFIG_KASAN
-#define __sha(x)	((unsigned long)kasan_mem_to_shadow((void *)x))
-
-static inline int set_memory_kasan(unsigned long start, unsigned long end)
-{
-	start = PAGE_ALIGN_DOWN(__sha(start));
-	end = PAGE_ALIGN(__sha(end));
-	return set_memory_rwnx(start, (end - start) >> PAGE_SHIFT);
-}
-#endif
-
-/*
- * map whole physical memory to virtual memory (identity mapping)
- * we reserve enough space in the vmalloc area for vmemmap to hotplug
- * additional memory segments.
- */
 void __init vmem_map_init(void)
 {
-	struct memblock_region memory_rwx_regions[] = {
-		{
-			.base	= 0,
-			.size	= sizeof(struct lowcore),
-			.flags	= MEMBLOCK_NONE,
-#ifdef CONFIG_NUMA
-			.nid	= NUMA_NO_NODE,
-#endif
-		},
-		{
-			.base	= __pa(_stext),
-			.size	= _etext - _stext,
-			.flags	= MEMBLOCK_NONE,
-#ifdef CONFIG_NUMA
-			.nid	= NUMA_NO_NODE,
-#endif
-		},
-		{
-			.base	= __pa(_sinittext),
-			.size	= _einittext - _sinittext,
-			.flags	= MEMBLOCK_NONE,
-#ifdef CONFIG_NUMA
-			.nid	= NUMA_NO_NODE,
-#endif
-		},
-		{
-			.base	= __stext_amode31,
-			.size	= __etext_amode31 - __stext_amode31,
-			.flags	= MEMBLOCK_NONE,
-#ifdef CONFIG_NUMA
-			.nid	= NUMA_NO_NODE,
-#endif
-		},
-	};
-	struct memblock_type memory_rwx = {
-		.regions	= memory_rwx_regions,
-		.cnt		= ARRAY_SIZE(memory_rwx_regions),
-		.max		= ARRAY_SIZE(memory_rwx_regions),
-	};
-	phys_addr_t base, end;
-	u64 i;
-
-	/*
-	 * Set RW+NX attribute on all memory, except regions enumerated with
-	 * memory_rwx exclude type. These regions need different attributes,
-	 * which are enforced afterwards.
-	 *
-	 * __for_each_mem_range() iterate and exclude types should be sorted.
-	 * The relative location of _stext and _sinittext is hardcoded in the
-	 * linker script. However a location of __stext_amode31 and the kernel
-	 * image itself are chosen dynamically. Thus, sort the exclude type.
-	 */
-	sort(&memory_rwx_regions,
-	     ARRAY_SIZE(memory_rwx_regions), sizeof(memory_rwx_regions[0]),
-	     memblock_region_cmp, memblock_region_swap);
-	__for_each_mem_range(i, &memblock.memory, &memory_rwx,
-			     NUMA_NO_NODE, MEMBLOCK_NONE, &base, &end, NULL) {
-		set_memory_rwnx((unsigned long)__va(base),
-				(end - base) >> PAGE_SHIFT);
-	}
-
-#ifdef CONFIG_KASAN
-	for_each_mem_range(i, &base, &end) {
-		set_memory_kasan((unsigned long)__va(base),
-				 (unsigned long)__va(end));
-	}
-#endif
 	set_memory_rox((unsigned long)_stext,
 		       (unsigned long)(_etext - _stext) >> PAGE_SHIFT);
 	set_memory_ro((unsigned long)_etext,
@@ -762,14 +661,14 @@ void __init vmem_map_init(void)
 		       (__etext_amode31 - __stext_amode31) >> PAGE_SHIFT);
 
 	/* lowcore must be executable for LPSWE */
-	if (static_key_enabled(&cpu_has_bear))
-		set_memory_nx(0, 1);
-	set_memory_nx(PAGE_SIZE, 1);
+	if (!static_key_enabled(&cpu_has_bear))
+		set_memory_x(0, 1);
 	if (debug_pagealloc_enabled()) {
 		set_memory_4k((unsigned long)__va(0),
 			      ident_map_size >> PAGE_SHIFT);
 	}
-
+	if (MACHINE_HAS_NX)
+		ctl_set_bit(0, 20);
 	pr_info("Write protected kernel read-only data: %luk\n",
 		(unsigned long)(__end_rodata - _stext) >> 10);
 }

From 3eeb07788ff05b30e2ddad39561d53495563e63a Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Fri, 25 Aug 2023 14:29:49 +0200
Subject: [PATCH 0782/1189] s390/amode31: change type of __samode31,
 __eamode31, etc

For consistencs reasons change the type of __samode31, __eamode31,
__stext_amode31, and __etext_amode31 to a char pointer so they
(nearly) match the type of all other sections.

This allows for code simplifications with follow-on patches.

Reviewed-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/include/asm/sections.h |  4 ++--
 arch/s390/kernel/machine_kexec.c |  4 ++--
 arch/s390/kernel/setup.c         | 16 ++++++++--------
 arch/s390/mm/dump_pagetables.c   |  4 ++--
 arch/s390/mm/vmem.c              |  4 ++--
 5 files changed, 16 insertions(+), 16 deletions(-)

diff --git a/arch/s390/include/asm/sections.h b/arch/s390/include/asm/sections.h
index 3fecaa4e8b74..0486e6ef62bf 100644
--- a/arch/s390/include/asm/sections.h
+++ b/arch/s390/include/asm/sections.h
@@ -23,7 +23,7 @@
  */
 #define __bootdata_preserved(var) __section(".boot.preserved.data." #var) var
 
-extern unsigned long __samode31, __eamode31;
-extern unsigned long __stext_amode31, __etext_amode31;
+extern char *__samode31, *__eamode31;
+extern char *__stext_amode31, *__etext_amode31;
 
 #endif
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index 12a2bd4fc88c..ce65fc01671f 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -216,8 +216,8 @@ void arch_crash_save_vmcoreinfo(void)
 	VMCOREINFO_SYMBOL(lowcore_ptr);
 	VMCOREINFO_SYMBOL(high_memory);
 	VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS);
-	vmcoreinfo_append_str("SAMODE31=%lx\n", __samode31);
-	vmcoreinfo_append_str("EAMODE31=%lx\n", __eamode31);
+	vmcoreinfo_append_str("SAMODE31=%lx\n", (unsigned long)__samode31);
+	vmcoreinfo_append_str("EAMODE31=%lx\n", (unsigned long)__eamode31);
 	vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
 	abs_lc = get_abs_lowcore();
 	abs_lc->vmcore_info = paddr_vmcoreinfo_note();
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 5b18f8b1f318..de6ad0fb2328 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -97,10 +97,10 @@ EXPORT_SYMBOL(console_irq);
  * relocated above 2 GB, because it has to use 31 bit addresses.
  * Such code and data is part of the .amode31 section.
  */
-unsigned long __amode31_ref __samode31 = (unsigned long)&_samode31;
-unsigned long __amode31_ref __eamode31 = (unsigned long)&_eamode31;
-unsigned long __amode31_ref __stext_amode31 = (unsigned long)&_stext_amode31;
-unsigned long __amode31_ref __etext_amode31 = (unsigned long)&_etext_amode31;
+char __amode31_ref *__samode31 = _samode31;
+char __amode31_ref *__eamode31 = _eamode31;
+char __amode31_ref *__stext_amode31 = _stext_amode31;
+char __amode31_ref *__etext_amode31 = _etext_amode31;
 struct exception_table_entry __amode31_ref *__start_amode31_ex_table = _start_amode31_ex_table;
 struct exception_table_entry __amode31_ref *__stop_amode31_ex_table = _stop_amode31_ex_table;
 
@@ -770,15 +770,15 @@ static void __init setup_memory(void)
 static void __init relocate_amode31_section(void)
 {
 	unsigned long amode31_size = __eamode31 - __samode31;
-	long amode31_offset = physmem_info.reserved[RR_AMODE31].start - __samode31;
-	long *ptr;
+	long amode31_offset, *ptr;
 
+	amode31_offset = physmem_info.reserved[RR_AMODE31].start - (unsigned long)__samode31;
 	pr_info("Relocating AMODE31 section of size 0x%08lx\n", amode31_size);
 
 	/* Move original AMODE31 section to the new one */
-	memmove((void *)physmem_info.reserved[RR_AMODE31].start, (void *)__samode31, amode31_size);
+	memmove((void *)physmem_info.reserved[RR_AMODE31].start, __samode31, amode31_size);
 	/* Zero out the old AMODE31 section to catch invalid accesses within it */
-	memset((void *)__samode31, 0, amode31_size);
+	memset(__samode31, 0, amode31_size);
 
 	/* Update all AMODE31 region references */
 	for (ptr = _start_amode31_refs; ptr != _end_amode31_refs; ptr++)
diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c
index afa5db750d92..b51666967aa1 100644
--- a/arch/s390/mm/dump_pagetables.c
+++ b/arch/s390/mm/dump_pagetables.c
@@ -290,8 +290,8 @@ static int pt_dump_init(void)
 	max_addr = (S390_lowcore.kernel_asce & _REGION_ENTRY_TYPE_MASK) >> 2;
 	max_addr = 1UL << (max_addr * 11 + 31);
 	address_markers[IDENTITY_AFTER_END_NR].start_address = ident_map_size;
-	address_markers[AMODE31_START_NR].start_address = __samode31;
-	address_markers[AMODE31_END_NR].start_address = __eamode31;
+	address_markers[AMODE31_START_NR].start_address = (unsigned long)__samode31;
+	address_markers[AMODE31_END_NR].start_address = (unsigned long)__eamode31;
 	address_markers[MODULES_NR].start_address = MODULES_VADDR;
 	address_markers[MODULES_END_NR].start_address = MODULES_END;
 	address_markers[ABS_LOWCORE_NR].start_address = __abs_lowcore;
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index 261eea21ca10..9b31dc565bc5 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -657,8 +657,8 @@ void __init vmem_map_init(void)
 		      (unsigned long)(__end_rodata - _etext) >> PAGE_SHIFT);
 	set_memory_rox((unsigned long)_sinittext,
 		       (unsigned long)(_einittext - _sinittext) >> PAGE_SHIFT);
-	set_memory_rox(__stext_amode31,
-		       (__etext_amode31 - __stext_amode31) >> PAGE_SHIFT);
+	set_memory_rox((unsigned long)__stext_amode31,
+		       (unsigned long)(__etext_amode31 - __stext_amode31) >> PAGE_SHIFT);
 
 	/* lowcore must be executable for LPSWE */
 	if (!static_key_enabled(&cpu_has_bear))

From a6e49f10f4411ec87f16ccb1b0ce5ea7e4a04a95 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Fri, 25 Aug 2023 14:29:50 +0200
Subject: [PATCH 0783/1189] s390/mm: improve description of mapping permissions
 of prefix pages

Slightly improve the description which explains why the first prefix
page must be mapped executable when the BEAR-enhancement facility is
not installed.

Reviewed-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/mm/vmem.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index 9b31dc565bc5..a1e01542790b 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -659,8 +659,11 @@ void __init vmem_map_init(void)
 		       (unsigned long)(_einittext - _sinittext) >> PAGE_SHIFT);
 	set_memory_rox((unsigned long)__stext_amode31,
 		       (unsigned long)(__etext_amode31 - __stext_amode31) >> PAGE_SHIFT);
-
-	/* lowcore must be executable for LPSWE */
+	/*
+	 * If the BEAR-enhancement facility is not installed the first
+	 * prefix page is used to return to the previous context with
+	 * an LPSWE instruction and therefore must be executable.
+	 */
 	if (!static_key_enabled(&cpu_has_bear))
 		set_memory_x(0, 1);
 	if (debug_pagealloc_enabled()) {

From c22a4c8aaf60780ce21fb2b5c8019e12457ee949 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Fri, 25 Aug 2023 14:29:51 +0200
Subject: [PATCH 0784/1189] s390/set_memory: generate all set_memory()
 functions

The set_memory() functions all follow the same pattern. Use a macro to
generate them, and in result remove a bit of code.

Reviewed-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/include/asm/set_memory.h | 44 ++++++++----------------------
 1 file changed, 12 insertions(+), 32 deletions(-)

diff --git a/arch/s390/include/asm/set_memory.h b/arch/s390/include/asm/set_memory.h
index 7a3eefd7a242..9f6c329a0d4e 100644
--- a/arch/s390/include/asm/set_memory.h
+++ b/arch/s390/include/asm/set_memory.h
@@ -26,41 +26,21 @@ enum {
 
 int __set_memory(unsigned long addr, int numpages, unsigned long flags);
 
-static inline int set_memory_ro(unsigned long addr, int numpages)
-{
-	return __set_memory(addr, numpages, SET_MEMORY_RO);
-}
-
-static inline int set_memory_rw(unsigned long addr, int numpages)
-{
-	return __set_memory(addr, numpages, SET_MEMORY_RW);
-}
-
-static inline int set_memory_nx(unsigned long addr, int numpages)
-{
-	return __set_memory(addr, numpages, SET_MEMORY_NX);
-}
-
-static inline int set_memory_x(unsigned long addr, int numpages)
-{
-	return __set_memory(addr, numpages, SET_MEMORY_X);
-}
-
 #define set_memory_rox set_memory_rox
-static inline int set_memory_rox(unsigned long addr, int numpages)
-{
-	return __set_memory(addr, numpages, SET_MEMORY_RO | SET_MEMORY_X);
+
+#define __SET_MEMORY_FUNC(fname, flags)				\
+static inline int fname(unsigned long addr, int numpages)	\
+{								\
+	return __set_memory(addr, numpages, (flags));		\
 }
 
-static inline int set_memory_rwnx(unsigned long addr, int numpages)
-{
-	return __set_memory(addr, numpages, SET_MEMORY_RW | SET_MEMORY_NX);
-}
-
-static inline int set_memory_4k(unsigned long addr, int numpages)
-{
-	return __set_memory(addr, numpages, SET_MEMORY_4K);
-}
+__SET_MEMORY_FUNC(set_memory_ro, SET_MEMORY_RO)
+__SET_MEMORY_FUNC(set_memory_rw, SET_MEMORY_RW)
+__SET_MEMORY_FUNC(set_memory_nx, SET_MEMORY_NX)
+__SET_MEMORY_FUNC(set_memory_x, SET_MEMORY_X)
+__SET_MEMORY_FUNC(set_memory_rox, SET_MEMORY_RO | SET_MEMORY_X)
+__SET_MEMORY_FUNC(set_memory_rwnx, SET_MEMORY_RW | SET_MEMORY_NX)
+__SET_MEMORY_FUNC(set_memory_4k, SET_MEMORY_4K)
 
 int set_direct_map_invalid_noflush(struct page *page);
 int set_direct_map_default_noflush(struct page *page);

From 850612c8e4fb048905af597cbd25dfbb40d9ffdf Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Fri, 25 Aug 2023 14:29:52 +0200
Subject: [PATCH 0785/1189] s390/set_memory: add __set_memory() variant

Add a __set_memory_yy() variant for all set_memory_yy()
implementations. The new variant takes start and end void pointers,
which allows them to be used without the usual unsigned long cast.

However more important: the new variant can be used for areas larger
than 8TB. The old variant comes with an "int numpages" parameter, which
overflows with more than 8TB. Given that for debug_pagealloc
set_memory_4k() is used on the whole kernel mapping this is not only a
theoretical problem, but must be fixed.

Changing all set_memory_yy() variants only on s390 to take an "unsigned
long numpages" parameter is not possible, since the common module code
requires an int parameter from all architectures on these functions.
See module_set_memory().

Therefore change/fix this on s390 only with a new interface, and address
common code later.

Reviewed-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/include/asm/set_memory.h | 28 +++++++++++++++++++++++-----
 arch/s390/mm/pageattr.c            |  2 +-
 2 files changed, 24 insertions(+), 6 deletions(-)

diff --git a/arch/s390/include/asm/set_memory.h b/arch/s390/include/asm/set_memory.h
index 9f6c329a0d4e..06fbabe2f66c 100644
--- a/arch/s390/include/asm/set_memory.h
+++ b/arch/s390/include/asm/set_memory.h
@@ -24,14 +24,32 @@ enum {
 #define SET_MEMORY_INV	BIT(_SET_MEMORY_INV_BIT)
 #define SET_MEMORY_DEF	BIT(_SET_MEMORY_DEF_BIT)
 
-int __set_memory(unsigned long addr, int numpages, unsigned long flags);
+int __set_memory(unsigned long addr, unsigned long numpages, unsigned long flags);
 
 #define set_memory_rox set_memory_rox
 
-#define __SET_MEMORY_FUNC(fname, flags)				\
-static inline int fname(unsigned long addr, int numpages)	\
-{								\
-	return __set_memory(addr, numpages, (flags));		\
+/*
+ * Generate two variants of each set_memory() function:
+ *
+ * set_memory_yy(unsigned long addr, int numpages);
+ * __set_memory_yy(void *start, void *end);
+ *
+ * The second variant exists for both convenience to avoid the usual
+ * (unsigned long) casts, but unlike the first variant it can also be used
+ * for areas larger than 8TB, which may happen at memory initialization.
+ */
+#define __SET_MEMORY_FUNC(fname, flags)					\
+static inline int fname(unsigned long addr, int numpages)		\
+{									\
+	return __set_memory(addr, numpages, (flags));			\
+}									\
+									\
+static inline int __##fname(void *start, void *end)			\
+{									\
+	unsigned long numpages;						\
+									\
+	numpages = (end - start) >> PAGE_SHIFT;				\
+	return __set_memory((unsigned long)start, numpages, (flags));	\
 }
 
 __SET_MEMORY_FUNC(set_memory_ro, SET_MEMORY_RO)
diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c
index ca5a418c58a8..43c919c7bafb 100644
--- a/arch/s390/mm/pageattr.c
+++ b/arch/s390/mm/pageattr.c
@@ -373,7 +373,7 @@ static int change_page_attr_alias(unsigned long addr, unsigned long end,
 	return rc;
 }
 
-int __set_memory(unsigned long addr, int numpages, unsigned long flags)
+int __set_memory(unsigned long addr, unsigned long numpages, unsigned long flags)
 {
 	unsigned long end;
 	int rc;

From a7eb28801b692df2496e21ff9af6ab0dc1969133 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Fri, 25 Aug 2023 14:29:53 +0200
Subject: [PATCH 0786/1189] s390/mm: use __set_memory() variants where useful

Use the __set_memory_yy() variants instead of set_memory_yy() where
useful. This allows to make the code a bit more readable.

This also fixes the debug pagealloc case, where set_memory_4k() might be
called for an area larger than 8TB which would lead to an overflow of
the num_pages parameter of set_memory_4k().

However RELOC_HIDE() has to be used for the __set_memory_4k() case for
the time being, to avoid compiler warnings because of performing pointer
arithmetic on a NULL pointer, which has undefined behavior. This happens
because __va(0) always translates to NULL. However this will change, and
as soon as this happens the RELOC_HIDE() hack can be removed again.

Reviewed-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/mm/init.c |  2 +-
 arch/s390/mm/vmem.c | 20 ++++++++++----------
 2 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 8d94e29adcdb..d1631f8e53b5 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -107,7 +107,7 @@ void mark_rodata_ro(void)
 {
 	unsigned long size = __end_ro_after_init - __start_ro_after_init;
 
-	set_memory_ro((unsigned long)__start_ro_after_init, size >> PAGE_SHIFT);
+	__set_memory_ro(__start_ro_after_init, __end_ro_after_init);
 	pr_info("Write protected read-only-after-init data: %luk\n", size >> 10);
 	debug_checkwx();
 }
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index a1e01542790b..d734058f28d3 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -651,14 +651,10 @@ void vmem_unmap_4k_page(unsigned long addr)
 
 void __init vmem_map_init(void)
 {
-	set_memory_rox((unsigned long)_stext,
-		       (unsigned long)(_etext - _stext) >> PAGE_SHIFT);
-	set_memory_ro((unsigned long)_etext,
-		      (unsigned long)(__end_rodata - _etext) >> PAGE_SHIFT);
-	set_memory_rox((unsigned long)_sinittext,
-		       (unsigned long)(_einittext - _sinittext) >> PAGE_SHIFT);
-	set_memory_rox((unsigned long)__stext_amode31,
-		       (unsigned long)(__etext_amode31 - __stext_amode31) >> PAGE_SHIFT);
+	__set_memory_rox(_stext, _etext);
+	__set_memory_ro(_etext, __end_rodata);
+	__set_memory_rox(_sinittext, _einittext);
+	__set_memory_rox(__stext_amode31, __etext_amode31);
 	/*
 	 * If the BEAR-enhancement facility is not installed the first
 	 * prefix page is used to return to the previous context with
@@ -667,8 +663,12 @@ void __init vmem_map_init(void)
 	if (!static_key_enabled(&cpu_has_bear))
 		set_memory_x(0, 1);
 	if (debug_pagealloc_enabled()) {
-		set_memory_4k((unsigned long)__va(0),
-			      ident_map_size >> PAGE_SHIFT);
+		/*
+		 * Use RELOC_HIDE() as long as __va(0) translates to NULL,
+		 * since performing pointer arithmetic on a NULL pointer
+		 * has undefined behavior and generates compiler warnings.
+		 */
+		__set_memory_4k(__va(0), RELOC_HIDE(__va(0), ident_map_size));
 	}
 	if (MACHINE_HAS_NX)
 		ctl_set_bit(0, 20);

From acf00b5ef9f83069ddbea274ab32931f8573e98b Mon Sep 17 00:00:00 2001
From: Benjamin Block <bblock@linux.ibm.com>
Date: Thu, 17 Aug 2023 19:18:13 +0200
Subject: [PATCH 0787/1189] s390/airq: remove lsi_mask from airq_struct

Remove the field `lsi_mask` from `struct airq_struct` as it is not
utilized for any adapter interrupt, other than setting it to the default
value of 0xff.

Because nobody is using this functionality, all it does is cost a little
bit of time with each delivered adapter interrupt.

Reviewed-by: Michael Mueller <mimu@linux.ibm.com>
Tested-by: Michael Mueller <mimu@linux.ibm.com>
Acked-by: Peter Oberparleiter <oberpar@linux.ibm.com>
Signed-off-by: Benjamin Block <bblock@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/include/asm/airq.h     | 1 -
 arch/s390/kvm/interrupt.c        | 3 ++-
 drivers/s390/cio/airq.c          | 4 +---
 drivers/s390/virtio/virtio_ccw.c | 1 -
 4 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/arch/s390/include/asm/airq.h b/arch/s390/include/asm/airq.h
index e82e5626e139..c4c28c2609a5 100644
--- a/arch/s390/include/asm/airq.h
+++ b/arch/s390/include/asm/airq.h
@@ -18,7 +18,6 @@ struct airq_struct {
 	struct hlist_node list;		/* Handler queueing. */
 	void (*handler)(struct airq_struct *airq, struct tpi_info *tpi_info);
 	u8 *lsi_ptr;			/* Local-Summary-Indicator pointer */
-	u8 lsi_mask;			/* Local-Summary-Indicator mask */
 	u8 isc;				/* Interrupt-subclass */
 	u8 flags;
 };
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 9bd0a873f3b1..6fa6a4b0b9a8 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -3398,7 +3398,6 @@ static void gib_alert_irq_handler(struct airq_struct *airq,
 
 static struct airq_struct gib_alert_irq = {
 	.handler = gib_alert_irq_handler,
-	.lsi_ptr = &gib_alert_irq.lsi_mask,
 };
 
 void kvm_s390_gib_destroy(void)
@@ -3438,6 +3437,8 @@ int __init kvm_s390_gib_init(u8 nisc)
 		rc = -EIO;
 		goto out_free_gib;
 	}
+	/* adapter interrupts used for AP (applicable here) don't use the LSI */
+	*gib_alert_irq.lsi_ptr = 0xff;
 
 	gib->nisc = nisc;
 	gib_origin = virt_to_phys(gib);
diff --git a/drivers/s390/cio/airq.c b/drivers/s390/cio/airq.c
index 34967e67249e..a108f2bf5b33 100644
--- a/drivers/s390/cio/airq.c
+++ b/drivers/s390/cio/airq.c
@@ -49,8 +49,6 @@ int register_adapter_interrupt(struct airq_struct *airq)
 			return -ENOMEM;
 		airq->flags |= AIRQ_PTR_ALLOCATED;
 	}
-	if (!airq->lsi_mask)
-		airq->lsi_mask = 0xff;
 	snprintf(dbf_txt, sizeof(dbf_txt), "rairq:%p", airq);
 	CIO_TRACE_EVENT(4, dbf_txt);
 	isc_register(airq->isc);
@@ -98,7 +96,7 @@ static irqreturn_t do_airq_interrupt(int irq, void *dummy)
 	head = &airq_lists[tpi_info->isc];
 	rcu_read_lock();
 	hlist_for_each_entry_rcu(airq, head, list)
-		if ((*airq->lsi_ptr & airq->lsi_mask) != 0)
+		if (*airq->lsi_ptr != 0)
 			airq->handler(airq, tpi_info);
 	rcu_read_unlock();
 
diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c
index 02922768b129..ac67576301bf 100644
--- a/drivers/s390/virtio/virtio_ccw.c
+++ b/drivers/s390/virtio/virtio_ccw.c
@@ -250,7 +250,6 @@ static struct airq_info *new_airq_info(int index)
 	info->airq.handler = virtio_airq_handler;
 	info->summary_indicator_idx = index;
 	info->airq.lsi_ptr = get_summary_indicator(info);
-	info->airq.lsi_mask = 0xff;
 	info->airq.isc = VIRTIO_AIRQ_ISC;
 	rc = register_adapter_interrupt(&info->airq);
 	if (rc) {

From fb5a4315591dae307a65fc246ca80b5159d296e1 Mon Sep 17 00:00:00 2001
From: Sergey Senozhatsky <senozhatsky@chromium.org>
Date: Wed, 16 Aug 2023 11:32:21 +0900
Subject: [PATCH 0788/1189] dma-debug: don't call
 __dma_entry_alloc_check_leak() under free_entries_lock

__dma_entry_alloc_check_leak() calls into printk -> serial console
output (qcom geni) and grabs port->lock under free_entries_lock
spin lock, which is a reverse locking dependency chain as qcom_geni
IRQ handler can call into dma-debug code and grab free_entries_lock
under port->lock.

Move __dma_entry_alloc_check_leak() call out of free_entries_lock
scope so that we don't acquire serial console's port->lock under it.

Trimmed-down lockdep splat:

 The existing dependency chain (in reverse order) is:

               -> #2 (free_entries_lock){-.-.}-{2:2}:
        _raw_spin_lock_irqsave+0x60/0x80
        dma_entry_alloc+0x38/0x110
        debug_dma_map_page+0x60/0xf8
        dma_map_page_attrs+0x1e0/0x230
        dma_map_single_attrs.constprop.0+0x6c/0xc8
        geni_se_rx_dma_prep+0x40/0xcc
        qcom_geni_serial_isr+0x310/0x510
        __handle_irq_event_percpu+0x110/0x244
        handle_irq_event_percpu+0x20/0x54
        handle_irq_event+0x50/0x88
        handle_fasteoi_irq+0xa4/0xcc
        handle_irq_desc+0x28/0x40
        generic_handle_domain_irq+0x24/0x30
        gic_handle_irq+0xc4/0x148
        do_interrupt_handler+0xa4/0xb0
        el1_interrupt+0x34/0x64
        el1h_64_irq_handler+0x18/0x24
        el1h_64_irq+0x64/0x68
        arch_local_irq_enable+0x4/0x8
        ____do_softirq+0x18/0x24
        ...

               -> #1 (&port_lock_key){-.-.}-{2:2}:
        _raw_spin_lock_irqsave+0x60/0x80
        qcom_geni_serial_console_write+0x184/0x1dc
        console_flush_all+0x344/0x454
        console_unlock+0x94/0xf0
        vprintk_emit+0x238/0x24c
        vprintk_default+0x3c/0x48
        vprintk+0xb4/0xbc
        _printk+0x68/0x90
        register_console+0x230/0x38c
        uart_add_one_port+0x338/0x494
        qcom_geni_serial_probe+0x390/0x424
        platform_probe+0x70/0xc0
        really_probe+0x148/0x280
        __driver_probe_device+0xfc/0x114
        driver_probe_device+0x44/0x100
        __device_attach_driver+0x64/0xdc
        bus_for_each_drv+0xb0/0xd8
        __device_attach+0xe4/0x140
        device_initial_probe+0x1c/0x28
        bus_probe_device+0x44/0xb0
        device_add+0x538/0x668
        of_device_add+0x44/0x50
        of_platform_device_create_pdata+0x94/0xc8
        of_platform_bus_create+0x270/0x304
        of_platform_populate+0xac/0xc4
        devm_of_platform_populate+0x60/0xac
        geni_se_probe+0x154/0x160
        platform_probe+0x70/0xc0
        ...

               -> #0 (console_owner){-...}-{0:0}:
        __lock_acquire+0xdf8/0x109c
        lock_acquire+0x234/0x284
        console_flush_all+0x330/0x454
        console_unlock+0x94/0xf0
        vprintk_emit+0x238/0x24c
        vprintk_default+0x3c/0x48
        vprintk+0xb4/0xbc
        _printk+0x68/0x90
        dma_entry_alloc+0xb4/0x110
        debug_dma_map_sg+0xdc/0x2f8
        __dma_map_sg_attrs+0xac/0xe4
        dma_map_sgtable+0x30/0x4c
        get_pages+0x1d4/0x1e4 [msm]
        msm_gem_pin_pages_locked+0x38/0xac [msm]
        msm_gem_pin_vma_locked+0x58/0x88 [msm]
        msm_ioctl_gem_submit+0xde4/0x13ac [msm]
        drm_ioctl_kernel+0xe0/0x15c
        drm_ioctl+0x2e8/0x3f4
        vfs_ioctl+0x30/0x50
        ...

 Chain exists of:
   console_owner --> &port_lock_key --> free_entries_lock

  Possible unsafe locking scenario:

        CPU0                    CPU1
        ----                    ----
   lock(free_entries_lock);
                                lock(&port_lock_key);
                                lock(free_entries_lock);
   lock(console_owner);

                *** DEADLOCK ***

 Call trace:
  dump_backtrace+0xb4/0xf0
  show_stack+0x20/0x30
  dump_stack_lvl+0x60/0x84
  dump_stack+0x18/0x24
  print_circular_bug+0x1cc/0x234
  check_noncircular+0x78/0xac
  __lock_acquire+0xdf8/0x109c
  lock_acquire+0x234/0x284
  console_flush_all+0x330/0x454
  console_unlock+0x94/0xf0
  vprintk_emit+0x238/0x24c
  vprintk_default+0x3c/0x48
  vprintk+0xb4/0xbc
  _printk+0x68/0x90
  dma_entry_alloc+0xb4/0x110
  debug_dma_map_sg+0xdc/0x2f8
  __dma_map_sg_attrs+0xac/0xe4
  dma_map_sgtable+0x30/0x4c
  get_pages+0x1d4/0x1e4 [msm]
  msm_gem_pin_pages_locked+0x38/0xac [msm]
  msm_gem_pin_vma_locked+0x58/0x88 [msm]
  msm_ioctl_gem_submit+0xde4/0x13ac [msm]
  drm_ioctl_kernel+0xe0/0x15c
  drm_ioctl+0x2e8/0x3f4
  vfs_ioctl+0x30/0x50
  ...

Reported-by: Rob Clark <robdclark@chromium.org>
Signed-off-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Acked-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 kernel/dma/debug.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index f190651bcadd..06366acd27b0 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -637,15 +637,19 @@ static struct dma_debug_entry *__dma_entry_alloc(void)
 	return entry;
 }
 
-static void __dma_entry_alloc_check_leak(void)
+/*
+ * This should be called outside of free_entries_lock scope to avoid potential
+ * deadlocks with serial consoles that use DMA.
+ */
+static void __dma_entry_alloc_check_leak(u32 nr_entries)
 {
-	u32 tmp = nr_total_entries % nr_prealloc_entries;
+	u32 tmp = nr_entries % nr_prealloc_entries;
 
 	/* Shout each time we tick over some multiple of the initial pool */
 	if (tmp < DMA_DEBUG_DYNAMIC_ENTRIES) {
 		pr_info("dma_debug_entry pool grown to %u (%u00%%)\n",
-			nr_total_entries,
-			(nr_total_entries / nr_prealloc_entries));
+			nr_entries,
+			(nr_entries / nr_prealloc_entries));
 	}
 }
 
@@ -656,8 +660,10 @@ static void __dma_entry_alloc_check_leak(void)
  */
 static struct dma_debug_entry *dma_entry_alloc(void)
 {
+	bool alloc_check_leak = false;
 	struct dma_debug_entry *entry;
 	unsigned long flags;
+	u32 nr_entries;
 
 	spin_lock_irqsave(&free_entries_lock, flags);
 	if (num_free_entries == 0) {
@@ -667,13 +673,17 @@ static struct dma_debug_entry *dma_entry_alloc(void)
 			pr_err("debugging out of memory - disabling\n");
 			return NULL;
 		}
-		__dma_entry_alloc_check_leak();
+		alloc_check_leak = true;
+		nr_entries = nr_total_entries;
 	}
 
 	entry = __dma_entry_alloc();
 
 	spin_unlock_irqrestore(&free_entries_lock, flags);
 
+	if (alloc_check_leak)
+		__dma_entry_alloc_check_leak(nr_entries);
+
 #ifdef CONFIG_STACKTRACE
 	entry->stack_len = stack_trace_save(entry->stack_entries,
 					    ARRAY_SIZE(entry->stack_entries),

From cd59cdefc2f101bfc99ee5bd38512ebba7b75471 Mon Sep 17 00:00:00 2001
From: Jinjie Ruan <ruanjinjie@huawei.com>
Date: Wed, 30 Aug 2023 16:59:29 +0800
Subject: [PATCH 0789/1189] rbd: use list_for_each_entry() helper

Convert list_for_each() to list_for_each_entry() so that the tmp
list_head pointer and list_entry() call are no longer needed, which
can reduce a few lines of code. No functional changed.

Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 drivers/block/rbd.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 2328cc05be36..3de11f077144 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -7199,7 +7199,6 @@ static void rbd_dev_remove_parent(struct rbd_device *rbd_dev)
 static ssize_t do_rbd_remove(const char *buf, size_t count)
 {
 	struct rbd_device *rbd_dev = NULL;
-	struct list_head *tmp;
 	int dev_id;
 	char opt_buf[6];
 	bool force = false;
@@ -7226,8 +7225,7 @@ static ssize_t do_rbd_remove(const char *buf, size_t count)
 
 	ret = -ENOENT;
 	spin_lock(&rbd_dev_list_lock);
-	list_for_each(tmp, &rbd_dev_list) {
-		rbd_dev = list_entry(tmp, struct rbd_device, node);
+	list_for_each_entry(rbd_dev, &rbd_dev_list, node) {
 		if (rbd_dev->dev_id == dev_id) {
 			ret = 0;
 			break;

From 2dcdf8c18d5c1835571bfa40f40ac134c8a1f0f5 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 30 Aug 2023 11:25:25 +0200
Subject: [PATCH 0790/1189] dma-contiguous: fix the Kconfig entry for
 CONFIG_DMA_NUMA_CMA

It makes no sense to expose CONFIG_DMA_NUMA_CMA if CONFIG_NUMA is not
enabled, and random config options shouldn't be default unless there
is a good reason.  Replace the default NUMA with a depends on to fix both
issues.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Robin Murphy <roin.murphy@arm.com>
---
 kernel/dma/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index 4c1e9a3c0ab6..f488997b0717 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -160,7 +160,7 @@ if  DMA_CMA
 
 config DMA_NUMA_CMA
 	bool "Enable separate DMA Contiguous Memory Area for NUMA Node"
-	default NUMA
+	depends on NUMA
 	help
 	  Enable this option to get numa CMA areas so that NUMA devices
 	  can get local memory by DMA coherent APIs.

From aee1720eeb87a3adc242eb07e5d4f7ba3eb8c736 Mon Sep 17 00:00:00 2001
From: David Vernet <void@manifault.com>
Date: Mon, 28 Aug 2023 10:59:46 -0500
Subject: [PATCH 0791/1189] bpf, docs: Move linux-notes.rst to root bpf docs
 tree

In commit 4d496be9ca05 ("bpf,docs: Create new standardization
subdirectory"), I added a standardization/ directory to the BPF
documentation, which will contain the docs that will be standardized
as part of the effort with the IETF.

I included linux-notes.rst in that directory, but I shouldn't have. It
doesn't contain anything that will be standardized. Let's move it back
to Documentation/bpf.

Signed-off-by: David Vernet <void@manifault.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20230828155948.123405-2-void@manifault.com
---
 Documentation/bpf/index.rst                             | 1 +
 Documentation/bpf/{standardization => }/linux-notes.rst | 0
 Documentation/bpf/standardization/index.rst             | 1 -
 3 files changed, 1 insertion(+), 1 deletion(-)
 rename Documentation/bpf/{standardization => }/linux-notes.rst (100%)

diff --git a/Documentation/bpf/index.rst b/Documentation/bpf/index.rst
index 1ff177b89d66..aeaeb35e6d4a 100644
--- a/Documentation/bpf/index.rst
+++ b/Documentation/bpf/index.rst
@@ -29,6 +29,7 @@ that goes into great technical depth about the BPF Architecture.
    bpf_licensing
    test_debug
    clang-notes
+   linux-notes
    other
    redirect
 
diff --git a/Documentation/bpf/standardization/linux-notes.rst b/Documentation/bpf/linux-notes.rst
similarity index 100%
rename from Documentation/bpf/standardization/linux-notes.rst
rename to Documentation/bpf/linux-notes.rst
diff --git a/Documentation/bpf/standardization/index.rst b/Documentation/bpf/standardization/index.rst
index 09c6ba055fd7..d7b946f71261 100644
--- a/Documentation/bpf/standardization/index.rst
+++ b/Documentation/bpf/standardization/index.rst
@@ -12,7 +12,6 @@ for the working group charter, documents, and more.
    :maxdepth: 1
 
    instruction-set
-   linux-notes
 
 .. Links:
 .. _IETF BPF Working Group: https://datatracker.ietf.org/wg/bpf/about/

From deb88407254621bf926658cff49a7ba01b59dec6 Mon Sep 17 00:00:00 2001
From: David Vernet <void@manifault.com>
Date: Mon, 28 Aug 2023 10:59:47 -0500
Subject: [PATCH 0792/1189] bpf, docs: Add abi.rst document to standardization
 subdirectory

As specified in the IETF BPF charter, the BPF working group has plans to
add one or more informational documents that recommend conventions and
guidelines for producing portable BPF program binaries. The
instruction-set.rst document currently contains a "Registers and calling
convention" subsection which dictates a calling convention that belongs
in an ABI document, rather than an instruction set document. Let's move
it to a new abi.rst document so we can clean it up. The abi.rst document
will of course be significantly changed and expanded upon over time. For
now, it's really just a placeholder which will contain ABI-specific
language that doesn't belong in other documents.

Signed-off-by: David Vernet <void@manifault.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20230828155948.123405-3-void@manifault.com
---
 Documentation/bpf/standardization/abi.rst     | 25 +++++++++++++++++++
 Documentation/bpf/standardization/index.rst   |  1 +
 .../bpf/standardization/instruction-set.rst   | 16 ------------
 3 files changed, 26 insertions(+), 16 deletions(-)
 create mode 100644 Documentation/bpf/standardization/abi.rst

diff --git a/Documentation/bpf/standardization/abi.rst b/Documentation/bpf/standardization/abi.rst
new file mode 100644
index 000000000000..0c2e10eeb89a
--- /dev/null
+++ b/Documentation/bpf/standardization/abi.rst
@@ -0,0 +1,25 @@
+.. contents::
+.. sectnum::
+
+===================================================
+BPF ABI Recommended Conventions and Guidelines v1.0
+===================================================
+
+This is version 1.0 of an informational document containing recommended
+conventions and guidelines for producing portable BPF program binaries.
+
+Registers and calling convention
+================================
+
+BPF has 10 general purpose registers and a read-only frame pointer register,
+all of which are 64-bits wide.
+
+The BPF calling convention is defined as:
+
+* R0: return value from function calls, and exit value for BPF programs
+* R1 - R5: arguments for function calls
+* R6 - R9: callee saved registers that function calls will preserve
+* R10: read-only frame pointer to access stack
+
+R0 - R5 are scratch registers and BPF programs needs to spill/fill them if
+necessary across calls.
diff --git a/Documentation/bpf/standardization/index.rst b/Documentation/bpf/standardization/index.rst
index d7b946f71261..a50c3baf6345 100644
--- a/Documentation/bpf/standardization/index.rst
+++ b/Documentation/bpf/standardization/index.rst
@@ -12,6 +12,7 @@ for the working group charter, documents, and more.
    :maxdepth: 1
 
    instruction-set
+   abi
 
 .. Links:
 .. _IETF BPF Working Group: https://datatracker.ietf.org/wg/bpf/about/
diff --git a/Documentation/bpf/standardization/instruction-set.rst b/Documentation/bpf/standardization/instruction-set.rst
index c5b0b2011f16..83583d735e38 100644
--- a/Documentation/bpf/standardization/instruction-set.rst
+++ b/Documentation/bpf/standardization/instruction-set.rst
@@ -97,22 +97,6 @@ Definitions
     A:          10000110
     B: 11111111 10000110
 
-Registers and calling convention
-================================
-
-eBPF has 10 general purpose registers and a read-only frame pointer register,
-all of which are 64-bits wide.
-
-The eBPF calling convention is defined as:
-
-* R0: return value from function calls, and exit value for eBPF programs
-* R1 - R5: arguments for function calls
-* R6 - R9: callee saved registers that function calls will preserve
-* R10: read-only frame pointer to access stack
-
-R0 - R5 are scratch registers and eBPF programs needs to spill/fill them if
-necessary across calls.
-
 Instruction encoding
 ====================
 

From 7d35eb1a184a3f0759ad9e9cde4669b5c55b2063 Mon Sep 17 00:00:00 2001
From: David Vernet <void@manifault.com>
Date: Mon, 28 Aug 2023 10:59:48 -0500
Subject: [PATCH 0793/1189] bpf, docs: s/eBPF/BPF in standards documents

There isn't really anything other than just "BPF" at this point,
so referring to it as "eBPF" in our standards document just causes
unnecessary confusion. Let's just be consistent and use "BPF".

Suggested-by: Will Hawkins <hawkinsw@obs.cr>
Signed-off-by: David Vernet <void@manifault.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20230828155948.123405-4-void@manifault.com
---
 .../bpf/standardization/instruction-set.rst   | 22 +++++++++----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/Documentation/bpf/standardization/instruction-set.rst b/Documentation/bpf/standardization/instruction-set.rst
index 83583d735e38..c5d53a6e8c79 100644
--- a/Documentation/bpf/standardization/instruction-set.rst
+++ b/Documentation/bpf/standardization/instruction-set.rst
@@ -1,11 +1,11 @@
 .. contents::
 .. sectnum::
 
-========================================
-eBPF Instruction Set Specification, v1.0
-========================================
+=======================================
+BPF Instruction Set Specification, v1.0
+=======================================
 
-This document specifies version 1.0 of the eBPF instruction set.
+This document specifies version 1.0 of the BPF instruction set.
 
 Documentation conventions
 =========================
@@ -100,7 +100,7 @@ Definitions
 Instruction encoding
 ====================
 
-eBPF has two instruction encodings:
+BPF has two instruction encodings:
 
 * the basic instruction encoding, which uses 64 bits to encode an instruction
 * the wide instruction encoding, which appends a second 64-bit immediate (i.e.,
@@ -244,7 +244,7 @@ BPF_END    0xd0   0        byte swap operations (see `Byte swap instructions`_ b
 =========  =====  =======  ==========================================================
 
 Underflow and overflow are allowed during arithmetic operations, meaning
-the 64-bit or 32-bit value will wrap. If eBPF program execution would
+the 64-bit or 32-bit value will wrap. If BPF program execution would
 result in division by zero, the destination register is instead set to zero.
 If execution would result in modulo by zero, for ``BPF_ALU64`` the value of
 the destination register is unchanged whereas for ``BPF_ALU`` the upper
@@ -366,7 +366,7 @@ BPF_JSLT  0xc    any  PC += offset if dst < src                    signed
 BPF_JSLE  0xd    any  PC += offset if dst <= src                   signed
 ========  =====  ===  ===========================================  =========================================
 
-The eBPF program needs to store the return value into register R0 before doing a
+The BPF program needs to store the return value into register R0 before doing a
 ``BPF_EXIT``.
 
 Example:
@@ -486,9 +486,9 @@ Atomic operations
 
 Atomic operations are operations that operate on memory and can not be
 interrupted or corrupted by other access to the same memory region
-by other eBPF programs or means outside of this specification.
+by other BPF programs or means outside of this specification.
 
-All atomic operations supported by eBPF are encoded as store operations
+All atomic operations supported by BPF are encoded as store operations
 that use the ``BPF_ATOMIC`` mode modifier as follows:
 
 * ``BPF_ATOMIC | BPF_W | BPF_STX`` for 32-bit operations
@@ -578,7 +578,7 @@ where
 Maps
 ~~~~
 
-Maps are shared memory regions accessible by eBPF programs on some platforms.
+Maps are shared memory regions accessible by BPF programs on some platforms.
 A map can have various semantics as defined in a separate document, and may or
 may not have a single contiguous memory region, but the 'map_val(map)' is
 currently only defined for maps that do have a single contiguous memory region.
@@ -600,6 +600,6 @@ identified by the given id.
 Legacy BPF Packet access instructions
 -------------------------------------
 
-eBPF previously introduced special instructions for access to packet data that were
+BPF previously introduced special instructions for access to packet data that were
 carried over from classic BPF. However, these instructions are
 deprecated and should no longer be used.

From 5eefc5307c983b59344a4cb89009819f580c84fa Mon Sep 17 00:00:00 2001
From: Andrzej Hajda <andrzej.hajda@intel.com>
Date: Mon, 21 Aug 2023 17:30:35 +0200
Subject: [PATCH 0794/1189] drm/i915: mark requests for GuC virtual engines to
 avoid use-after-free

References to i915_requests may be trapped by userspace inside a
sync_file or dmabuf (dma-resv) and held indefinitely across different
proceses. To counter-act the memory leaks, we try to not to keep
references from the request past their completion.
On the other side on fence release we need to know if rq->engine
is valid and points to hw engine (true for non-virtual requests).
To make it possible extra bit has been added to rq->execution_mask,
for marking virtual engines.

Fixes: bcb9aa45d5a0 ("Revert "drm/i915: Hold reference to intel_context over life of i915_request"")
Signed-off-by: Chris Wilson <chris.p.wilson@linux.intel.com>
Signed-off-by: Andrzej Hajda <andrzej.hajda@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230821153035.3903006-1-andrzej.hajda@intel.com
(cherry picked from commit 280410677af763f3871b93e794a199cfcf6fb580)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_engine_types.h      | 1 +
 drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c | 3 +++
 drivers/gpu/drm/i915/i915_request.c               | 7 ++-----
 3 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index e99a6fa03d45..a7e677598004 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -58,6 +58,7 @@ struct i915_perf_group;
 
 typedef u32 intel_engine_mask_t;
 #define ALL_ENGINES ((intel_engine_mask_t)~0ul)
+#define VIRTUAL_ENGINES BIT(BITS_PER_TYPE(intel_engine_mask_t) - 1)
 
 struct intel_hw_status_page {
 	struct list_head timelines;
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index a0e3ef1c65d2..b5b7f2fe8c78 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -5470,6 +5470,9 @@ guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count,
 
 	ve->base.flags = I915_ENGINE_IS_VIRTUAL;
 
+	BUILD_BUG_ON(ilog2(VIRTUAL_ENGINES) < I915_NUM_ENGINES);
+	ve->base.mask = VIRTUAL_ENGINES;
+
 	intel_context_init(&ve->context, &ve->base);
 
 	for (n = 0; n < count; n++) {
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 7c7da284990d..f59081066a19 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -134,9 +134,7 @@ static void i915_fence_release(struct dma_fence *fence)
 	i915_sw_fence_fini(&rq->semaphore);
 
 	/*
-	 * Keep one request on each engine for reserved use under mempressure
-	 * do not use with virtual engines as this really is only needed for
-	 * kernel contexts.
+	 * Keep one request on each engine for reserved use under mempressure.
 	 *
 	 * We do not hold a reference to the engine here and so have to be
 	 * very careful in what rq->engine we poke. The virtual engine is
@@ -166,8 +164,7 @@ static void i915_fence_release(struct dma_fence *fence)
 	 * know that if the rq->execution_mask is a single bit, rq->engine
 	 * can be a physical engine with the exact corresponding mask.
 	 */
-	if (!intel_engine_is_virtual(rq->engine) &&
-	    is_power_of_2(rq->execution_mask) &&
+	if (is_power_of_2(rq->execution_mask) &&
 	    !cmpxchg(&rq->engine->request_pool, NULL, rq))
 		return;
 

From 28427f368f0e08d504ed06e74bc7cc79d6d06511 Mon Sep 17 00:00:00 2001
From: Xiao Liang <shaw.leon@gmail.com>
Date: Fri, 25 Aug 2023 13:33:27 +0800
Subject: [PATCH 0795/1189] netfilter: nft_exthdr: Fix non-linear header
 modification

Fix skb_ensure_writable() size. Don't use nft_tcp_header_pointer() to
make it explicit that pointers point to the packet (not local buffer).

Fixes: 99d1712bc41c ("netfilter: exthdr: tcp option set support")
Fixes: 7890cbea66e7 ("netfilter: exthdr: add support for tcp option removal")
Cc: stable@vger.kernel.org
Signed-off-by: Xiao Liang <shaw.leon@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_exthdr.c | 20 ++++++++------------
 1 file changed, 8 insertions(+), 12 deletions(-)

diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index 7f856ceb3a66..a9844eefedeb 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -238,7 +238,12 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr,
 	if (!tcph)
 		goto err;
 
+	if (skb_ensure_writable(pkt->skb, nft_thoff(pkt) + tcphdr_len))
+		goto err;
+
+	tcph = (struct tcphdr *)(pkt->skb->data + nft_thoff(pkt));
 	opt = (u8 *)tcph;
+
 	for (i = sizeof(*tcph); i < tcphdr_len - 1; i += optl) {
 		union {
 			__be16 v16;
@@ -253,15 +258,6 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr,
 		if (i + optl > tcphdr_len || priv->len + priv->offset > optl)
 			goto err;
 
-		if (skb_ensure_writable(pkt->skb,
-					nft_thoff(pkt) + i + priv->len))
-			goto err;
-
-		tcph = nft_tcp_header_pointer(pkt, sizeof(buff), buff,
-					      &tcphdr_len);
-		if (!tcph)
-			goto err;
-
 		offset = i + priv->offset;
 
 		switch (priv->len) {
@@ -325,9 +321,9 @@ static void nft_exthdr_tcp_strip_eval(const struct nft_expr *expr,
 	if (skb_ensure_writable(pkt->skb, nft_thoff(pkt) + tcphdr_len))
 		goto drop;
 
-	opt = (u8 *)nft_tcp_header_pointer(pkt, sizeof(buff), buff, &tcphdr_len);
-	if (!opt)
-		goto err;
+	tcph = (struct tcphdr *)(pkt->skb->data + nft_thoff(pkt));
+	opt = (u8 *)tcph;
+
 	for (i = sizeof(*tcph); i < tcphdr_len - 1; i += optl) {
 		unsigned int j;
 

From e99476497687ef9e850748fe6d232264f30bc8f9 Mon Sep 17 00:00:00 2001
From: Wander Lairson Costa <wander@redhat.com>
Date: Mon, 28 Aug 2023 19:12:55 -0300
Subject: [PATCH 0796/1189] netfilter: xt_sctp: validate the flag_info count

sctp_mt_check doesn't validate the flag_count field. An attacker can
take advantage of that to trigger a OOB read and leak memory
information.

Add the field validation in the checkentry function.

Fixes: 2e4e6a17af35 ("[NETFILTER] x_tables: Abstraction layer for {ip,ip6,arp}_tables")
Cc: stable@vger.kernel.org
Reported-by: Lucas Leong <wmliang@infosec.exchange>
Signed-off-by: Wander Lairson Costa <wander@redhat.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/xt_sctp.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/netfilter/xt_sctp.c b/net/netfilter/xt_sctp.c
index e8961094a282..b46a6a512058 100644
--- a/net/netfilter/xt_sctp.c
+++ b/net/netfilter/xt_sctp.c
@@ -149,6 +149,8 @@ static int sctp_mt_check(const struct xt_mtchk_param *par)
 {
 	const struct xt_sctp_info *info = par->matchinfo;
 
+	if (info->flag_count > ARRAY_SIZE(info->flag_info))
+		return -EINVAL;
 	if (info->flags & ~XT_SCTP_VALID_FLAGS)
 		return -EINVAL;
 	if (info->invflags & ~XT_SCTP_VALID_FLAGS)

From 69c5d284f67089b4750d28ff6ac6f52ec224b330 Mon Sep 17 00:00:00 2001
From: Wander Lairson Costa <wander@redhat.com>
Date: Mon, 28 Aug 2023 10:21:07 -0300
Subject: [PATCH 0797/1189] netfilter: xt_u32: validate user space input

The xt_u32 module doesn't validate the fields in the xt_u32 structure.
An attacker may take advantage of this to trigger an OOB read by setting
the size fields with a value beyond the arrays boundaries.

Add a checkentry function to validate the structure.

This was originally reported by the ZDI project (ZDI-CAN-18408).

Fixes: 1b50b8a371e9 ("[NETFILTER]: Add u32 match")
Cc: stable@vger.kernel.org
Signed-off-by: Wander Lairson Costa <wander@redhat.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/xt_u32.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/net/netfilter/xt_u32.c b/net/netfilter/xt_u32.c
index 177b40d08098..117d4615d668 100644
--- a/net/netfilter/xt_u32.c
+++ b/net/netfilter/xt_u32.c
@@ -96,11 +96,32 @@ static bool u32_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	return ret ^ data->invert;
 }
 
+static int u32_mt_checkentry(const struct xt_mtchk_param *par)
+{
+	const struct xt_u32 *data = par->matchinfo;
+	const struct xt_u32_test *ct;
+	unsigned int i;
+
+	if (data->ntests > ARRAY_SIZE(data->tests))
+		return -EINVAL;
+
+	for (i = 0; i < data->ntests; ++i) {
+		ct = &data->tests[i];
+
+		if (ct->nnums > ARRAY_SIZE(ct->location) ||
+		    ct->nvalues > ARRAY_SIZE(ct->value))
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 static struct xt_match xt_u32_mt_reg __read_mostly = {
 	.name       = "u32",
 	.revision   = 0,
 	.family     = NFPROTO_UNSPEC,
 	.match      = u32_mt,
+	.checkentry = u32_mt_checkentry,
 	.matchsize  = sizeof(struct xt_u32),
 	.me         = THIS_MODULE,
 };

From bd6fc5da4c51107e1e0cec4a3a07963d1dae2c84 Mon Sep 17 00:00:00 2001
From: Gabriel Krisman Bertazi <krisman@suse.de>
Date: Mon, 28 Aug 2023 19:42:49 -0400
Subject: [PATCH 0798/1189] io_uring: Don't set affinity on a dying sqpoll
 thread

Syzbot reported a null-ptr-deref of sqd->thread inside
io_sqpoll_wq_cpu_affinity.  It turns out the sqd->thread can go away
from under us during io_uring_register, in case the process gets a
fatal signal during io_uring_register.

It is not particularly hard to hit the race, and while I am not sure
this is the exact case hit by syzbot, it solves it.  Finally, checking
->thread is enough to close the race because we locked sqd while
"parking" the thread, thus preventing it from going away.

I reproduced it fairly consistently with a program that does:

int main(void) {
  ...
  io_uring_queue_init(RING_LEN, &ring1, IORING_SETUP_SQPOLL);
  while (1) {
    io_uring_register_iowq_aff(ring, 1, &mask);
  }
}

Executed in a loop with timeout to trigger SIGTERM:
  while true; do timeout 1 /a.out ; done

This will hit the following BUG() in very few attempts.

BUG: kernel NULL pointer dereference, address: 00000000000007a8
PGD 800000010e949067 P4D 800000010e949067 PUD 10e46e067 PMD 0
Oops: 0000 [#1] PREEMPT SMP PTI
CPU: 0 PID: 15715 Comm: dead-sqpoll Not tainted 6.5.0-rc7-next-20230825-g193296236fa0-dirty #23
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015
RIP: 0010:io_sqpoll_wq_cpu_affinity+0x27/0x70
Code: 90 90 90 0f 1f 44 00 00 55 53 48 8b 9f 98 03 00 00 48 85 db 74 4f
48 89 df 48 89 f5 e8 e2 f8 ff ff 48 8b 43 38 48 85 c0 74 22 <48> 8b b8
a8 07 00 00 48 89 ee e8 ba b1 00 00 48 89 df 89 c5 e8 70
RSP: 0018:ffffb04040ea7e70 EFLAGS: 00010282
RAX: 0000000000000000 RBX: ffff93c010749e40 RCX: 0000000000000001
RDX: 0000000000000000 RSI: ffffffffa7653331 RDI: 00000000ffffffff
RBP: ffffb04040ea7eb8 R08: 0000000000000000 R09: c0000000ffffdfff
R10: ffff93c01141b600 R11: ffffb04040ea7d18 R12: ffff93c00ea74840
R13: 0000000000000011 R14: 0000000000000000 R15: ffff93c00ea74800
FS:  00007fb7c276ab80(0000) GS:ffff93c36f200000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000000007a8 CR3: 0000000111634003 CR4: 0000000000370ef0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <TASK>
 ? __die_body+0x1a/0x60
 ? page_fault_oops+0x154/0x440
 ? do_user_addr_fault+0x174/0x7b0
 ? exc_page_fault+0x63/0x140
 ? asm_exc_page_fault+0x22/0x30
 ? io_sqpoll_wq_cpu_affinity+0x27/0x70
 __io_register_iowq_aff+0x2b/0x60
 __io_uring_register+0x614/0xa70
 __x64_sys_io_uring_register+0xaa/0x1a0
 do_syscall_64+0x3a/0x90
 entry_SYSCALL_64_after_hwframe+0x6e/0xd8
RIP: 0033:0x7fb7c226fec9
Code: 2e 00 b8 ca 00 00 00 0f 05 eb a5 66 0f 1f 44 00 00 48 89 f8 48 89
f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01
f0 ff ff 73 01 c3 48 8b 0d 97 7f 2d 00 f7 d8 64 89 01 48
RSP: 002b:00007ffe2c0674f8 EFLAGS: 00000246 ORIG_RAX: 00000000000001ab
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007fb7c226fec9
RDX: 00007ffe2c067530 RSI: 0000000000000011 RDI: 0000000000000003
RBP: 00007ffe2c0675d0 R08: 00007ffe2c067550 R09: 00007ffe2c067550
R10: 0000000000000001 R11: 0000000000000246 R12: 0000000000000000
R13: 00007ffe2c067750 R14: 0000000000000000 R15: 0000000000000000
 </TASK>
Modules linked in:
CR2: 00000000000007a8
---[ end trace 0000000000000000 ]---

Reported-by: syzbot+c74fea926a78b8a91042@syzkaller.appspotmail.com
Fixes: ebdfefc09c6d ("io_uring/sqpoll: fix io-wq affinity when IORING_SETUP_SQPOLL is used")
Signed-off-by: Gabriel Krisman Bertazi <krisman@suse.de>
Link: https://lore.kernel.org/r/87v8cybuo6.fsf@suse.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/sqpoll.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
index ee2d2c687fda..bd6c2c7959a5 100644
--- a/io_uring/sqpoll.c
+++ b/io_uring/sqpoll.c
@@ -430,7 +430,9 @@ __cold int io_sqpoll_wq_cpu_affinity(struct io_ring_ctx *ctx,
 
 	if (sqd) {
 		io_sq_thread_park(sqd);
-		ret = io_wq_cpu_affinity(sqd->thread->io_uring, mask);
+		/* Don't set affinity for a dying thread */
+		if (sqd->thread)
+			ret = io_wq_cpu_affinity(sqd->thread->io_uring, mask);
 		io_sq_thread_unpark(sqd);
 	}
 

From ef100397fac3e2e403d5d510e66f36e242654073 Mon Sep 17 00:00:00 2001
From: Yu Kuai <yukuai3@huawei.com>
Date: Wed, 16 Aug 2023 09:27:05 +0800
Subject: [PATCH 0799/1189] blk-throttle: print signed value
 'carryover_bytes/ios' for user

'carryover_bytes/ios' can be negative, indicate that some bio is
dispatched in advance within slice while configuration is updated.
Print a huge value is not user-friendly.

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20230816012708.1193747-2-yukuai1@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-throttle.c | 2 +-
 block/blk-throttle.h | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 7397ff199d66..5184f17f5129 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -816,7 +816,7 @@ static void tg_update_carryover(struct throtl_grp *tg)
 		__tg_update_carryover(tg, WRITE);
 
 	/* see comments in struct throtl_grp for meaning of these fields. */
-	throtl_log(&tg->service_queue, "%s: %llu %llu %u %u\n", __func__,
+	throtl_log(&tg->service_queue, "%s: %lld %lld %d %d\n", __func__,
 		   tg->carryover_bytes[READ], tg->carryover_bytes[WRITE],
 		   tg->carryover_ios[READ], tg->carryover_ios[WRITE]);
 }
diff --git a/block/blk-throttle.h b/block/blk-throttle.h
index d1ccbfe9f797..bffbc9cfc8ab 100644
--- a/block/blk-throttle.h
+++ b/block/blk-throttle.h
@@ -127,8 +127,8 @@ struct throtl_grp {
 	 * bytes/ios are waited already in previous configuration, and they will
 	 * be used to calculate wait time under new configuration.
 	 */
-	uint64_t carryover_bytes[2];
-	unsigned int carryover_ios[2];
+	long long carryover_bytes[2];
+	int carryover_ios[2];
 
 	unsigned long last_check_time;
 

From bb8d5587bdc3ab211e1eae2eeb966f7a7d1f9c0b Mon Sep 17 00:00:00 2001
From: Yu Kuai <yukuai3@huawei.com>
Date: Wed, 16 Aug 2023 09:27:06 +0800
Subject: [PATCH 0800/1189] blk-throttle: fix wrong comparation while
 'carryover_ios/bytes' is negative

carryover_ios/bytes[] can be negative in the case that ios are
dispatched in the slice in advance, and then configuration is updated.
For example:

1) set iops limit to 1000, and slice start is 0, slice end is 100ms;
2) current time is 0, and 100 ios are dispatched, those ios will not be
   throttled, hence io_disp is 100;
3) still at current time 0, update iops limit to 100, then carryover_ios
   is (0 - 100) = -100;
4) then, dispatch a new io at time 0, the expected result is that this
   io will wait for 1s. The calculation in tg_within_iops_limit:

   io_disp = 0;
   io_allowed = calculate_io_allowed + carryover_ios
	      = 10 + (-100) = -90;
   io won't be throttled if (io_disp + 1 < io_allowed) passed.

Before this patch, in step 4) (io_disp + 1 < io_allowed) is passed,
because -90 for unsigned value is very huge, and such io won't be
throttled.

Fix this problem by checking if 'io/bytes_allowed' is negative first.

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20230816012708.1193747-3-yukuai1@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-throttle.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 5184f17f5129..7c93144d03da 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -825,7 +825,7 @@ static unsigned long tg_within_iops_limit(struct throtl_grp *tg, struct bio *bio
 				 u32 iops_limit)
 {
 	bool rw = bio_data_dir(bio);
-	unsigned int io_allowed;
+	int io_allowed;
 	unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd;
 
 	if (iops_limit == UINT_MAX) {
@@ -838,9 +838,8 @@ static unsigned long tg_within_iops_limit(struct throtl_grp *tg, struct bio *bio
 	jiffy_elapsed_rnd = roundup(jiffy_elapsed + 1, tg->td->throtl_slice);
 	io_allowed = calculate_io_allowed(iops_limit, jiffy_elapsed_rnd) +
 		     tg->carryover_ios[rw];
-	if (tg->io_disp[rw] + 1 <= io_allowed) {
+	if (io_allowed > 0 && tg->io_disp[rw] + 1 <= io_allowed)
 		return 0;
-	}
 
 	/* Calc approx time to dispatch */
 	jiffy_wait = jiffy_elapsed_rnd - jiffy_elapsed;
@@ -851,7 +850,8 @@ static unsigned long tg_within_bps_limit(struct throtl_grp *tg, struct bio *bio,
 				u64 bps_limit)
 {
 	bool rw = bio_data_dir(bio);
-	u64 bytes_allowed, extra_bytes;
+	long long bytes_allowed;
+	u64 extra_bytes;
 	unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd;
 	unsigned int bio_size = throtl_bio_data_size(bio);
 
@@ -869,9 +869,8 @@ static unsigned long tg_within_bps_limit(struct throtl_grp *tg, struct bio *bio,
 	jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, tg->td->throtl_slice);
 	bytes_allowed = calculate_bytes_allowed(bps_limit, jiffy_elapsed_rnd) +
 			tg->carryover_bytes[rw];
-	if (tg->bytes_disp[rw] + bio_size <= bytes_allowed) {
+	if (bytes_allowed > 0 && tg->bytes_disp[rw] + bio_size <= bytes_allowed)
 		return 0;
-	}
 
 	/* Calc approx time to dispatch */
 	extra_bytes = tg->bytes_disp[rw] + bio_size - bytes_allowed;

From e8368b57c006dc0e02dcd8a9dc9f2060ff5476fe Mon Sep 17 00:00:00 2001
From: Yu Kuai <yukuai3@huawei.com>
Date: Wed, 16 Aug 2023 09:27:07 +0800
Subject: [PATCH 0801/1189] blk-throttle: use calculate_io/bytes_allowed() for
 throtl_trim_slice()

There are no functional changes, just make the code cleaner.

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20230816012708.1193747-4-yukuai1@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-throttle.c | 116 +++++++++++++++++++++----------------------
 1 file changed, 56 insertions(+), 60 deletions(-)

diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 7c93144d03da..69a994156772 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -697,66 +697,6 @@ static bool throtl_slice_used(struct throtl_grp *tg, bool rw)
 	return true;
 }
 
-/* Trim the used slices and adjust slice start accordingly */
-static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw)
-{
-	unsigned long nr_slices, time_elapsed, io_trim;
-	u64 bytes_trim, tmp;
-
-	BUG_ON(time_before(tg->slice_end[rw], tg->slice_start[rw]));
-
-	/*
-	 * If bps are unlimited (-1), then time slice don't get
-	 * renewed. Don't try to trim the slice if slice is used. A new
-	 * slice will start when appropriate.
-	 */
-	if (throtl_slice_used(tg, rw))
-		return;
-
-	/*
-	 * A bio has been dispatched. Also adjust slice_end. It might happen
-	 * that initially cgroup limit was very low resulting in high
-	 * slice_end, but later limit was bumped up and bio was dispatched
-	 * sooner, then we need to reduce slice_end. A high bogus slice_end
-	 * is bad because it does not allow new slice to start.
-	 */
-
-	throtl_set_slice_end(tg, rw, jiffies + tg->td->throtl_slice);
-
-	time_elapsed = jiffies - tg->slice_start[rw];
-
-	nr_slices = time_elapsed / tg->td->throtl_slice;
-
-	if (!nr_slices)
-		return;
-	tmp = tg_bps_limit(tg, rw) * tg->td->throtl_slice * nr_slices;
-	do_div(tmp, HZ);
-	bytes_trim = tmp;
-
-	io_trim = (tg_iops_limit(tg, rw) * tg->td->throtl_slice * nr_slices) /
-		HZ;
-
-	if (!bytes_trim && !io_trim)
-		return;
-
-	if (tg->bytes_disp[rw] >= bytes_trim)
-		tg->bytes_disp[rw] -= bytes_trim;
-	else
-		tg->bytes_disp[rw] = 0;
-
-	if (tg->io_disp[rw] >= io_trim)
-		tg->io_disp[rw] -= io_trim;
-	else
-		tg->io_disp[rw] = 0;
-
-	tg->slice_start[rw] += nr_slices * tg->td->throtl_slice;
-
-	throtl_log(&tg->service_queue,
-		   "[%c] trim slice nr=%lu bytes=%llu io=%lu start=%lu end=%lu jiffies=%lu",
-		   rw == READ ? 'R' : 'W', nr_slices, bytes_trim, io_trim,
-		   tg->slice_start[rw], tg->slice_end[rw], jiffies);
-}
-
 static unsigned int calculate_io_allowed(u32 iops_limit,
 					 unsigned long jiffy_elapsed)
 {
@@ -786,6 +726,62 @@ static u64 calculate_bytes_allowed(u64 bps_limit, unsigned long jiffy_elapsed)
 	return mul_u64_u64_div_u64(bps_limit, (u64)jiffy_elapsed, (u64)HZ);
 }
 
+/* Trim the used slices and adjust slice start accordingly */
+static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw)
+{
+	unsigned long time_elapsed, io_trim;
+	u64 bytes_trim;
+
+	BUG_ON(time_before(tg->slice_end[rw], tg->slice_start[rw]));
+
+	/*
+	 * If bps are unlimited (-1), then time slice don't get
+	 * renewed. Don't try to trim the slice if slice is used. A new
+	 * slice will start when appropriate.
+	 */
+	if (throtl_slice_used(tg, rw))
+		return;
+
+	/*
+	 * A bio has been dispatched. Also adjust slice_end. It might happen
+	 * that initially cgroup limit was very low resulting in high
+	 * slice_end, but later limit was bumped up and bio was dispatched
+	 * sooner, then we need to reduce slice_end. A high bogus slice_end
+	 * is bad because it does not allow new slice to start.
+	 */
+
+	throtl_set_slice_end(tg, rw, jiffies + tg->td->throtl_slice);
+
+	time_elapsed = rounddown(jiffies - tg->slice_start[rw],
+				 tg->td->throtl_slice);
+	if (!time_elapsed)
+		return;
+
+	bytes_trim = calculate_bytes_allowed(tg_bps_limit(tg, rw),
+					     time_elapsed);
+	io_trim = calculate_io_allowed(tg_iops_limit(tg, rw), time_elapsed);
+	if (!bytes_trim && !io_trim)
+		return;
+
+	if (tg->bytes_disp[rw] >= bytes_trim)
+		tg->bytes_disp[rw] -= bytes_trim;
+	else
+		tg->bytes_disp[rw] = 0;
+
+	if (tg->io_disp[rw] >= io_trim)
+		tg->io_disp[rw] -= io_trim;
+	else
+		tg->io_disp[rw] = 0;
+
+	tg->slice_start[rw] += time_elapsed;
+
+	throtl_log(&tg->service_queue,
+		   "[%c] trim slice nr=%lu bytes=%llu io=%lu start=%lu end=%lu jiffies=%lu",
+		   rw == READ ? 'R' : 'W', time_elapsed / tg->td->throtl_slice,
+		   bytes_trim, io_trim, tg->slice_start[rw], tg->slice_end[rw],
+		   jiffies);
+}
+
 static void __tg_update_carryover(struct throtl_grp *tg, bool rw)
 {
 	unsigned long jiffy_elapsed = jiffies - tg->slice_start[rw];

From eead0056648cef49d7b15c07ae612fa217083165 Mon Sep 17 00:00:00 2001
From: Yu Kuai <yukuai3@huawei.com>
Date: Wed, 16 Aug 2023 09:27:08 +0800
Subject: [PATCH 0802/1189] blk-throttle: consider 'carryover_ios/bytes' in
 throtl_trim_slice()

Currently, 'carryover_ios/bytes' is not handled in throtl_trim_slice(),
for consequence, 'carryover_ios/bytes' will be used to throttle bio
multiple times, for example:

1) set iops limit to 100, and slice start is 0, slice end is 100ms;
2) current time is 0, and 10 ios are dispatched, those io won't be
   throttled and io_disp is 10;
3) still at current time 0, update iops limit to 1000, carryover_ios is
   updated to (0 - 10) = -10;
4) in this slice(0 - 100ms), io_allowed = 100 + (-10) = 90, which means
   only 90 ios can be dispatched without waiting;
5) assume that io is throttled in slice(0 - 100ms), and
   throtl_trim_slice() update silce to (100ms - 200ms). In this case,
   'carryover_ios/bytes' is not cleared and still only 90 ios can be
   dispatched between 100ms - 200ms.

Fix this problem by updating 'carryover_ios/bytes' in
throtl_trim_slice().

Fixes: a880ae93e5b5 ("blk-throttle: fix io hung due to configuration updates")
Reported-by: zhuxiaohui <zhuxiaohui.400@bytedance.com>
Link: https://lore.kernel.org/all/20230812072116.42321-1-zhuxiaohui.400@bytedance.com/
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20230816012708.1193747-5-yukuai1@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-throttle.c | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 69a994156772..38a881cf97d0 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -729,8 +729,9 @@ static u64 calculate_bytes_allowed(u64 bps_limit, unsigned long jiffy_elapsed)
 /* Trim the used slices and adjust slice start accordingly */
 static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw)
 {
-	unsigned long time_elapsed, io_trim;
-	u64 bytes_trim;
+	unsigned long time_elapsed;
+	long long bytes_trim;
+	int io_trim;
 
 	BUG_ON(time_before(tg->slice_end[rw], tg->slice_start[rw]));
 
@@ -758,17 +759,21 @@ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw)
 		return;
 
 	bytes_trim = calculate_bytes_allowed(tg_bps_limit(tg, rw),
-					     time_elapsed);
-	io_trim = calculate_io_allowed(tg_iops_limit(tg, rw), time_elapsed);
-	if (!bytes_trim && !io_trim)
+					     time_elapsed) +
+		     tg->carryover_bytes[rw];
+	io_trim = calculate_io_allowed(tg_iops_limit(tg, rw), time_elapsed) +
+		  tg->carryover_ios[rw];
+	if (bytes_trim <= 0 && io_trim <= 0)
 		return;
 
-	if (tg->bytes_disp[rw] >= bytes_trim)
+	tg->carryover_bytes[rw] = 0;
+	if ((long long)tg->bytes_disp[rw] >= bytes_trim)
 		tg->bytes_disp[rw] -= bytes_trim;
 	else
 		tg->bytes_disp[rw] = 0;
 
-	if (tg->io_disp[rw] >= io_trim)
+	tg->carryover_ios[rw] = 0;
+	if ((int)tg->io_disp[rw] >= io_trim)
 		tg->io_disp[rw] -= io_trim;
 	else
 		tg->io_disp[rw] = 0;
@@ -776,7 +781,7 @@ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw)
 	tg->slice_start[rw] += time_elapsed;
 
 	throtl_log(&tg->service_queue,
-		   "[%c] trim slice nr=%lu bytes=%llu io=%lu start=%lu end=%lu jiffies=%lu",
+		   "[%c] trim slice nr=%lu bytes=%lld io=%d start=%lu end=%lu jiffies=%lu",
 		   rw == READ ? 'R' : 'W', time_elapsed / tg->td->throtl_slice,
 		   bytes_trim, io_trim, tg->slice_start[rw], tg->slice_end[rw],
 		   jiffies);

From 2a2015495142ee0a35711b5dcf7b215c31489f27 Mon Sep 17 00:00:00 2001
From: Ding Xiang <dingxiang@cmss.chinamobile.com>
Date: Wed, 30 Aug 2023 18:11:48 +0800
Subject: [PATCH 0803/1189] selftests/landlock: Fix a resource leak
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The opened file should be closed before return, otherwise resource leak
will occur.

Signed-off-by: Ding Xiang <dingxiang@cmss.chinamobile.com>
Link: https://lore.kernel.org/r/20230830101148.3738-1-dingxiang@cmss.chinamobile.com
Fixes: 3de64b656b3c ("selftests/landlock: Add supports_filesystem() helper")
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 tools/testing/selftests/landlock/fs_test.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c
index 83d565569512..251594306d40 100644
--- a/tools/testing/selftests/landlock/fs_test.c
+++ b/tools/testing/selftests/landlock/fs_test.c
@@ -113,7 +113,7 @@ static bool supports_filesystem(const char *const filesystem)
 {
 	char str[32];
 	int len;
-	bool res;
+	bool res = true;
 	FILE *const inf = fopen("/proc/filesystems", "r");
 
 	/*
@@ -125,14 +125,16 @@ static bool supports_filesystem(const char *const filesystem)
 
 	/* filesystem can be null for bind mounts. */
 	if (!filesystem)
-		return true;
+		goto out;
 
 	len = snprintf(str, sizeof(str), "nodev\t%s\n", filesystem);
 	if (len >= sizeof(str))
 		/* Ignores too-long filesystem names. */
-		return true;
+		goto out;
 
 	res = fgrep(inf, str);
+
+out:
 	fclose(inf);
 	return res;
 }

From 978474dc8278f661930e02e08d292a45a45fa01a Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@redhat.com>
Date: Wed, 30 Aug 2023 00:38:02 +0200
Subject: [PATCH 0804/1189] drm/nouveau: fence: fix undefined fence state after
 emit

nouveau_fence_emit() can fail before and after initializing the
dma-fence and hence before and after initializing the dma-fence' kref.

In order to avoid nouveau_fence_emit() potentially failing before
dma-fence initialization pass the channel to nouveau_fence_new() already
and perform the required check before even allocating the fence.

While at it, restore the original behavior of nouveau_fence_new() and
add nouveau_fence_create() for separate (pre-)allocation instead. Always
splitting up allocation end emit wasn't a good idea in the first place.
Hence, limit it to the places where we actually need to pre-allocate.

Fixes: 7f2a0b50b2b2 ("drm/nouveau: fence: separate fence alloc and emit")
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230829223847.4406-1-dakr@redhat.com
---
 drivers/gpu/drm/nouveau/dispnv04/crtc.c |  9 +------
 drivers/gpu/drm/nouveau/nouveau_bo.c    |  8 +------
 drivers/gpu/drm/nouveau/nouveau_chan.c  |  6 ++---
 drivers/gpu/drm/nouveau/nouveau_dmem.c  |  9 +++----
 drivers/gpu/drm/nouveau/nouveau_exec.c  | 11 ++++++---
 drivers/gpu/drm/nouveau/nouveau_fence.c | 32 ++++++++++++++++++++-----
 drivers/gpu/drm/nouveau/nouveau_fence.h |  5 ++--
 drivers/gpu/drm/nouveau/nouveau_gem.c   |  5 +---
 8 files changed, 45 insertions(+), 40 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/dispnv04/crtc.c b/drivers/gpu/drm/nouveau/dispnv04/crtc.c
index a34924523133..a34917b048f9 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/crtc.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/crtc.c
@@ -1122,18 +1122,11 @@ nv04_page_flip_emit(struct nouveau_channel *chan,
 	PUSH_NVSQ(push, NV_SW, NV_SW_PAGE_FLIP, 0x00000000);
 	PUSH_KICK(push);
 
-	ret = nouveau_fence_new(pfence);
+	ret = nouveau_fence_new(pfence, chan);
 	if (ret)
 		goto fail;
 
-	ret = nouveau_fence_emit(*pfence, chan);
-	if (ret)
-		goto fail_fence_unref;
-
 	return 0;
-
-fail_fence_unref:
-	nouveau_fence_unref(pfence);
 fail:
 	spin_lock_irqsave(&dev->event_lock, flags);
 	list_del(&s->head);
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 19cab37ac69c..0f3bd187ede6 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -875,16 +875,10 @@ nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict,
 	if (ret)
 		goto out_unlock;
 
-	ret = nouveau_fence_new(&fence);
+	ret = nouveau_fence_new(&fence, chan);
 	if (ret)
 		goto out_unlock;
 
-	ret = nouveau_fence_emit(fence, chan);
-	if (ret) {
-		nouveau_fence_unref(&fence);
-		goto out_unlock;
-	}
-
 	/* TODO: figure out a better solution here
 	 *
 	 * wait on the fence here explicitly as going through
diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.c b/drivers/gpu/drm/nouveau/nouveau_chan.c
index 1fd5ccf41128..bb3d6e5c122f 100644
--- a/drivers/gpu/drm/nouveau/nouveau_chan.c
+++ b/drivers/gpu/drm/nouveau/nouveau_chan.c
@@ -70,11 +70,9 @@ nouveau_channel_idle(struct nouveau_channel *chan)
 		struct nouveau_fence *fence = NULL;
 		int ret;
 
-		ret = nouveau_fence_new(&fence);
+		ret = nouveau_fence_new(&fence, chan);
 		if (!ret) {
-			ret = nouveau_fence_emit(fence, chan);
-			if (!ret)
-				ret = nouveau_fence_wait(fence, false, false);
+			ret = nouveau_fence_wait(fence, false, false);
 			nouveau_fence_unref(&fence);
 		}
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c
index 61e84562094a..12feecf71e75 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dmem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c
@@ -209,8 +209,7 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf)
 		goto done;
 	}
 
-	if (!nouveau_fence_new(&fence))
-		nouveau_fence_emit(fence, dmem->migrate.chan);
+	nouveau_fence_new(&fence, dmem->migrate.chan);
 	migrate_vma_pages(&args);
 	nouveau_dmem_fence_done(&fence);
 	dma_unmap_page(drm->dev->dev, dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL);
@@ -403,8 +402,7 @@ nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk)
 		}
 	}
 
-	if (!nouveau_fence_new(&fence))
-		nouveau_fence_emit(fence, chunk->drm->dmem->migrate.chan);
+	nouveau_fence_new(&fence, chunk->drm->dmem->migrate.chan);
 	migrate_device_pages(src_pfns, dst_pfns, npages);
 	nouveau_dmem_fence_done(&fence);
 	migrate_device_finalize(src_pfns, dst_pfns, npages);
@@ -677,8 +675,7 @@ static void nouveau_dmem_migrate_chunk(struct nouveau_drm *drm,
 		addr += PAGE_SIZE;
 	}
 
-	if (!nouveau_fence_new(&fence))
-		nouveau_fence_emit(fence, drm->dmem->migrate.chan);
+	nouveau_fence_new(&fence, drm->dmem->migrate.chan);
 	migrate_vma_pages(args);
 	nouveau_dmem_fence_done(&fence);
 	nouveau_pfns_map(svmm, args->vma->vm_mm, args->start, pfns, i);
diff --git a/drivers/gpu/drm/nouveau/nouveau_exec.c b/drivers/gpu/drm/nouveau/nouveau_exec.c
index a90c4cd8cbb2..19024ce21fbb 100644
--- a/drivers/gpu/drm/nouveau/nouveau_exec.c
+++ b/drivers/gpu/drm/nouveau/nouveau_exec.c
@@ -96,7 +96,8 @@ nouveau_exec_job_submit(struct nouveau_job *job)
 	unsigned long index;
 	int ret;
 
-	ret = nouveau_fence_new(&exec_job->fence);
+	/* Create a new fence, but do not emit yet. */
+	ret = nouveau_fence_create(&exec_job->fence, exec_job->chan);
 	if (ret)
 		return ret;
 
@@ -170,13 +171,17 @@ nouveau_exec_job_run(struct nouveau_job *job)
 		nv50_dma_push(chan, p->va, p->va_len, no_prefetch);
 	}
 
-	ret = nouveau_fence_emit(fence, chan);
+	ret = nouveau_fence_emit(fence);
 	if (ret) {
+		nouveau_fence_unref(&exec_job->fence);
 		NV_PRINTK(err, job->cli, "error fencing pushbuf: %d\n", ret);
 		WIND_RING(chan);
 		return ERR_PTR(ret);
 	}
 
+	/* The fence was emitted successfully, set the job's fence pointer to
+	 * NULL in order to avoid freeing it up when the job is cleaned up.
+	 */
 	exec_job->fence = NULL;
 
 	return &fence->base;
@@ -189,7 +194,7 @@ nouveau_exec_job_free(struct nouveau_job *job)
 
 	nouveau_job_free(job);
 
-	nouveau_fence_unref(&exec_job->fence);
+	kfree(exec_job->fence);
 	kfree(exec_job->push.s);
 	kfree(exec_job);
 }
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index 77c739a55b19..61d9e70da9fd 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -205,16 +205,13 @@ nouveau_fence_context_new(struct nouveau_channel *chan, struct nouveau_fence_cha
 }
 
 int
-nouveau_fence_emit(struct nouveau_fence *fence, struct nouveau_channel *chan)
+nouveau_fence_emit(struct nouveau_fence *fence)
 {
+	struct nouveau_channel *chan = fence->channel;
 	struct nouveau_fence_chan *fctx = chan->fence;
 	struct nouveau_fence_priv *priv = (void*)chan->drm->fence;
 	int ret;
 
-	if (unlikely(!chan->fence))
-		return -ENODEV;
-
-	fence->channel  = chan;
 	fence->timeout  = jiffies + (15 * HZ);
 
 	if (priv->uevent)
@@ -406,18 +403,41 @@ nouveau_fence_unref(struct nouveau_fence **pfence)
 }
 
 int
-nouveau_fence_new(struct nouveau_fence **pfence)
+nouveau_fence_create(struct nouveau_fence **pfence,
+		     struct nouveau_channel *chan)
 {
 	struct nouveau_fence *fence;
 
+	if (unlikely(!chan->fence))
+		return -ENODEV;
+
 	fence = kzalloc(sizeof(*fence), GFP_KERNEL);
 	if (!fence)
 		return -ENOMEM;
 
+	fence->channel = chan;
+
 	*pfence = fence;
 	return 0;
 }
 
+int
+nouveau_fence_new(struct nouveau_fence **pfence,
+		  struct nouveau_channel *chan)
+{
+	int ret = 0;
+
+	ret = nouveau_fence_create(pfence, chan);
+	if (ret)
+		return ret;
+
+	ret = nouveau_fence_emit(*pfence);
+	if (ret)
+		nouveau_fence_unref(pfence);
+
+	return ret;
+}
+
 static const char *nouveau_fence_get_get_driver_name(struct dma_fence *fence)
 {
 	return "nouveau";
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h
index 2c72d96ef17d..64d33ae7f356 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.h
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.h
@@ -17,10 +17,11 @@ struct nouveau_fence {
 	unsigned long timeout;
 };
 
-int  nouveau_fence_new(struct nouveau_fence **);
+int  nouveau_fence_create(struct nouveau_fence **, struct nouveau_channel *);
+int  nouveau_fence_new(struct nouveau_fence **, struct nouveau_channel *);
 void nouveau_fence_unref(struct nouveau_fence **);
 
-int  nouveau_fence_emit(struct nouveau_fence *, struct nouveau_channel *);
+int  nouveau_fence_emit(struct nouveau_fence *);
 bool nouveau_fence_done(struct nouveau_fence *);
 int  nouveau_fence_wait(struct nouveau_fence *, bool lazy, bool intr);
 int  nouveau_fence_sync(struct nouveau_bo *, struct nouveau_channel *, bool exclusive, bool intr);
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index c0b10d8d3d03..a0d303e5ce3d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -914,11 +914,8 @@ revalidate:
 		}
 	}
 
-	ret = nouveau_fence_new(&fence);
-	if (!ret)
-		ret = nouveau_fence_emit(fence, chan);
+	ret = nouveau_fence_new(&fence, chan);
 	if (ret) {
-		nouveau_fence_unref(&fence);
 		NV_PRINTK(err, cli, "error fencing pushbuf: %d\n", ret);
 		WIND_RING(chan);
 		goto out;

From 7e9be1124dbe7888907e82cab20164578e3f9ab7 Mon Sep 17 00:00:00 2001
From: Phil Sutter <phil@nwl.cc>
Date: Tue, 29 Aug 2023 19:51:57 +0200
Subject: [PATCH 0805/1189] netfilter: nf_tables: Audit log setelem reset

Since set element reset is not integrated into nf_tables' transaction
logic, an explicit log call is needed, similar to NFT_MSG_GETOBJ_RESET
handling.

For the sake of simplicity, catchall element reset will always generate
a dedicated log entry. This relieves nf_tables_dump_set() from having to
adjust the logged element count depending on whether a catchall element
was found or not.

Fixes: 079cd633219d7 ("netfilter: nf_tables: Introduce NFT_MSG_GETSETELEM_RESET")
Signed-off-by: Phil Sutter <phil@nwl.cc>
Reviewed-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/audit.h         |  1 +
 kernel/auditsc.c              |  1 +
 net/netfilter/nf_tables_api.c | 31 ++++++++++++++++++++++++++++---
 3 files changed, 30 insertions(+), 3 deletions(-)

diff --git a/include/linux/audit.h b/include/linux/audit.h
index 6a3a9e122bb5..192bf03aacc5 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -117,6 +117,7 @@ enum audit_nfcfgop {
 	AUDIT_NFT_OP_OBJ_RESET,
 	AUDIT_NFT_OP_FLOWTABLE_REGISTER,
 	AUDIT_NFT_OP_FLOWTABLE_UNREGISTER,
+	AUDIT_NFT_OP_SETELEM_RESET,
 	AUDIT_NFT_OP_INVALID,
 };
 
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index addeed3df15d..38481e318197 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -143,6 +143,7 @@ static const struct audit_nfcfgop_tab audit_nfcfgs[] = {
 	{ AUDIT_NFT_OP_OBJ_RESET,		"nft_reset_obj"		   },
 	{ AUDIT_NFT_OP_FLOWTABLE_REGISTER,	"nft_register_flowtable"   },
 	{ AUDIT_NFT_OP_FLOWTABLE_UNREGISTER,	"nft_unregister_flowtable" },
+	{ AUDIT_NFT_OP_SETELEM_RESET,		"nft_reset_setelem"        },
 	{ AUDIT_NFT_OP_INVALID,			"nft_invalid"		   },
 };
 
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 41b826dff6f5..361e98e71692 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -102,6 +102,7 @@ static const u8 nft2audit_op[NFT_MSG_MAX] = { // enum nf_tables_msg_types
 	[NFT_MSG_NEWFLOWTABLE]	= AUDIT_NFT_OP_FLOWTABLE_REGISTER,
 	[NFT_MSG_GETFLOWTABLE]	= AUDIT_NFT_OP_INVALID,
 	[NFT_MSG_DELFLOWTABLE]	= AUDIT_NFT_OP_FLOWTABLE_UNREGISTER,
+	[NFT_MSG_GETSETELEM_RESET] = AUDIT_NFT_OP_SETELEM_RESET,
 };
 
 static void nft_validate_state_update(struct nft_table *table, u8 new_validate_state)
@@ -5624,13 +5625,25 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx,
 	return nf_tables_fill_setelem(args->skb, set, elem, args->reset);
 }
 
+static void audit_log_nft_set_reset(const struct nft_table *table,
+				    unsigned int base_seq,
+				    unsigned int nentries)
+{
+	char *buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, base_seq);
+
+	audit_log_nfcfg(buf, table->family, nentries,
+			AUDIT_NFT_OP_SETELEM_RESET, GFP_ATOMIC);
+	kfree(buf);
+}
+
 struct nft_set_dump_ctx {
 	const struct nft_set	*set;
 	struct nft_ctx		ctx;
 };
 
 static int nft_set_catchall_dump(struct net *net, struct sk_buff *skb,
-				 const struct nft_set *set, bool reset)
+				 const struct nft_set *set, bool reset,
+				 unsigned int base_seq)
 {
 	struct nft_set_elem_catchall *catchall;
 	u8 genmask = nft_genmask_cur(net);
@@ -5646,6 +5659,8 @@ static int nft_set_catchall_dump(struct net *net, struct sk_buff *skb,
 
 		elem.priv = catchall->elem;
 		ret = nf_tables_fill_setelem(skb, set, &elem, reset);
+		if (reset && !ret)
+			audit_log_nft_set_reset(set->table, base_seq, 1);
 		break;
 	}
 
@@ -5725,12 +5740,17 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
 	set->ops->walk(&dump_ctx->ctx, set, &args.iter);
 
 	if (!args.iter.err && args.iter.count == cb->args[0])
-		args.iter.err = nft_set_catchall_dump(net, skb, set, reset);
+		args.iter.err = nft_set_catchall_dump(net, skb, set,
+						      reset, cb->seq);
 	rcu_read_unlock();
 
 	nla_nest_end(skb, nest);
 	nlmsg_end(skb, nlh);
 
+	if (reset && args.iter.count > args.iter.skip)
+		audit_log_nft_set_reset(table, cb->seq,
+					args.iter.count - args.iter.skip);
+
 	if (args.iter.err && args.iter.err != -EMSGSIZE)
 		return args.iter.err;
 	if (args.iter.count == cb->args[0])
@@ -5955,13 +5975,13 @@ static int nf_tables_getsetelem(struct sk_buff *skb,
 	struct netlink_ext_ack *extack = info->extack;
 	u8 genmask = nft_genmask_cur(info->net);
 	u8 family = info->nfmsg->nfgen_family;
+	int rem, err = 0, nelems = 0;
 	struct net *net = info->net;
 	struct nft_table *table;
 	struct nft_set *set;
 	struct nlattr *attr;
 	struct nft_ctx ctx;
 	bool reset = false;
-	int rem, err = 0;
 
 	table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family,
 				 genmask, 0);
@@ -6004,8 +6024,13 @@ static int nf_tables_getsetelem(struct sk_buff *skb,
 			NL_SET_BAD_ATTR(extack, attr);
 			break;
 		}
+		nelems++;
 	}
 
+	if (reset)
+		audit_log_nft_set_reset(table, nft_pernet(net)->base_seq,
+					nelems);
+
 	return err;
 }
 

From ea078ae9108e25fc881c84369f7c03931d22e555 Mon Sep 17 00:00:00 2001
From: Phil Sutter <phil@nwl.cc>
Date: Tue, 29 Aug 2023 19:51:58 +0200
Subject: [PATCH 0806/1189] netfilter: nf_tables: Audit log rule reset

Resetting rules' stateful data happens outside of the transaction logic,
so 'get' and 'dump' handlers have to emit audit log entries themselves.

Fixes: 8daa8fde3fc3f ("netfilter: nf_tables: Introduce NFT_MSG_GETRULE_RESET")
Signed-off-by: Phil Sutter <phil@nwl.cc>
Reviewed-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/audit.h         |  1 +
 kernel/auditsc.c              |  1 +
 net/netfilter/nf_tables_api.c | 18 ++++++++++++++++++
 3 files changed, 20 insertions(+)

diff --git a/include/linux/audit.h b/include/linux/audit.h
index 192bf03aacc5..51b1b7054a23 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -118,6 +118,7 @@ enum audit_nfcfgop {
 	AUDIT_NFT_OP_FLOWTABLE_REGISTER,
 	AUDIT_NFT_OP_FLOWTABLE_UNREGISTER,
 	AUDIT_NFT_OP_SETELEM_RESET,
+	AUDIT_NFT_OP_RULE_RESET,
 	AUDIT_NFT_OP_INVALID,
 };
 
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 38481e318197..fc0c7c03eeab 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -144,6 +144,7 @@ static const struct audit_nfcfgop_tab audit_nfcfgs[] = {
 	{ AUDIT_NFT_OP_FLOWTABLE_REGISTER,	"nft_register_flowtable"   },
 	{ AUDIT_NFT_OP_FLOWTABLE_UNREGISTER,	"nft_unregister_flowtable" },
 	{ AUDIT_NFT_OP_SETELEM_RESET,		"nft_reset_setelem"        },
+	{ AUDIT_NFT_OP_RULE_RESET,		"nft_reset_rule"           },
 	{ AUDIT_NFT_OP_INVALID,			"nft_invalid"		   },
 };
 
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 361e98e71692..2c81cee858d6 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -3422,6 +3422,18 @@ err:
 	nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS);
 }
 
+static void audit_log_rule_reset(const struct nft_table *table,
+				 unsigned int base_seq,
+				 unsigned int nentries)
+{
+	char *buf = kasprintf(GFP_ATOMIC, "%s:%u",
+			      table->name, base_seq);
+
+	audit_log_nfcfg(buf, table->family, nentries,
+			AUDIT_NFT_OP_RULE_RESET, GFP_ATOMIC);
+	kfree(buf);
+}
+
 struct nft_rule_dump_ctx {
 	char *table;
 	char *chain;
@@ -3528,6 +3540,9 @@ static int nf_tables_dump_rules(struct sk_buff *skb,
 done:
 	rcu_read_unlock();
 
+	if (reset && idx > cb->args[0])
+		audit_log_rule_reset(table, cb->seq, idx - cb->args[0]);
+
 	cb->args[0] = idx;
 	return skb->len;
 }
@@ -3635,6 +3650,9 @@ static int nf_tables_getrule(struct sk_buff *skb, const struct nfnl_info *info,
 	if (err < 0)
 		goto err_fill_rule_info;
 
+	if (reset)
+		audit_log_rule_reset(table, nft_pernet(net)->base_seq, 1);
+
 	return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid);
 
 err_fill_rule_info:

From 7a5dee9b72e9aafaa684dea8bf55aac91997b319 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Mon, 28 Aug 2023 22:31:01 +0100
Subject: [PATCH 0807/1189] scsi: qla2xxx: Fix spelling mistake "tranport" ->
 "transport"

There is a spelling mistake in a ql_dbg message. Fix it.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Link: https://lore.kernel.org/r/20230828213101.758609-1-colin.i.king@gmail.com
Acked-by: Nilesh Javali <njavali@marvell.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_nvme.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c
index 62a67662cbf3..04e02de36100 100644
--- a/drivers/scsi/qla2xxx/qla_nvme.c
+++ b/drivers/scsi/qla2xxx/qla_nvme.c
@@ -1189,7 +1189,7 @@ qla2xxx_process_purls_pkt(struct scsi_qla_host *vha, struct purex_item *item)
 				 &item->iocb, item->size);
 #endif
 	if (ret) {
-		ql_dbg(ql_dbg_unsol, vha, 0x2125, "NVMe tranport ls_req failed\n");
+		ql_dbg(ql_dbg_unsol, vha, 0x2125, "NVMe transport ls_req failed\n");
 		memset((void *)&a, 0, sizeof(a));
 		a.vp_idx = vha->vp_idx;
 		a.nport_handle = uctx->nport_handle;

From e7cf3a35b38ef3c8ee74e6cfe1fd6a62c7f34a02 Mon Sep 17 00:00:00 2001
From: Yang Li <yang.lee@linux.alibaba.com>
Date: Tue, 29 Aug 2023 09:02:22 +0800
Subject: [PATCH 0808/1189] scsi: fnic: Remove unused functions
 fnic_scsi_host_start/end_tag()

The functions fnic_scsi_host_start_tag() and fnic_scsi_host_end_tag() are
not used anywhere, so remove them.

silence the warnings:
drivers/scsi/fnic/fnic_scsi.c:2175:1: warning: unused function 'fnic_scsi_host_start_tag'
drivers/scsi/fnic/fnic_scsi.c:2196:1: warning: unused function 'fnic_scsi_host_end_tag'

Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
Link: https://lore.kernel.org/r/20230829010222.33393-1-yang.lee@linux.alibaba.com
Acked-by: Karan Tilak Kumar <kartilak@cisco.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/fnic/fnic_scsi.c | 33 ---------------------------------
 1 file changed, 33 deletions(-)

diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c
index 185142efee3d..9761b2c9db48 100644
--- a/drivers/scsi/fnic/fnic_scsi.c
+++ b/drivers/scsi/fnic/fnic_scsi.c
@@ -2167,39 +2167,6 @@ clean_pending_aborts_end:
 	return ret;
 }
 
-/*
- * fnic_scsi_host_start_tag
- * Allocates tagid from host's tag list
- **/
-static inline int
-fnic_scsi_host_start_tag(struct fnic *fnic, struct scsi_cmnd *sc)
-{
-	struct request *rq = scsi_cmd_to_rq(sc);
-	struct request_queue *q = rq->q;
-	struct request *dummy;
-
-	dummy = blk_mq_alloc_request(q, REQ_OP_WRITE, BLK_MQ_REQ_NOWAIT);
-	if (IS_ERR(dummy))
-		return SCSI_NO_TAG;
-
-	rq->tag = dummy->tag;
-	sc->host_scribble = (unsigned char *)dummy;
-
-	return dummy->tag;
-}
-
-/*
- * fnic_scsi_host_end_tag
- * frees tag allocated by fnic_scsi_host_start_tag.
- **/
-static inline void
-fnic_scsi_host_end_tag(struct fnic *fnic, struct scsi_cmnd *sc)
-{
-	struct request *dummy = (struct request *)sc->host_scribble;
-
-	blk_mq_free_request(dummy);
-}
-
 /*
  * SCSI Eh thread issues a Lun Reset when one or more commands on a LUN
  * fail to get aborted. It calls driver's eh_device_reset with a SCSI command

From d4781807f0505526e293802d8509f31c4dfb8f54 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Tue, 29 Aug 2023 07:35:06 -0700
Subject: [PATCH 0809/1189] scsi: qla2xxx: Fix unused variable warning in
 qla2xxx_process_purls_pkt()

When CONFIG_NVME_FC is not set, fcport is unused:

  drivers/scsi/qla2xxx/qla_nvme.c: In function 'qla2xxx_process_purls_pkt':
  drivers/scsi/qla2xxx/qla_nvme.c:1183:20: warning: unused variable 'fcport' [-Wunused-variable]
   1183 |         fc_port_t *fcport = uctx->fcport;
        |                    ^~~~~~

While this preprocessor usage could be converted to a normal if
statement to allow the compiler to always see fcport as used, it is
equally easy to just eliminate the fcport variable and use uctx->fcport
directly.

Fixes: 27177862de96 ("scsi: qla2xxx: Fix nvme_fc_rcv_ls_req() undefined error")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Closes: https://lore.kernel.org/linux-next/20230828131304.269a2a40@canb.auug.org.au/
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202308290833.sKkoSSeO-lkp@intel.com/
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Link: https://lore.kernel.org/r/20230829-qla_nvme-fix-unused-fcport-v1-1-51c7560ecaee@kernel.org
Acked-by: Nilesh Javali <njavali@marvell.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_nvme.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c
index 04e02de36100..db753d712991 100644
--- a/drivers/scsi/qla2xxx/qla_nvme.c
+++ b/drivers/scsi/qla2xxx/qla_nvme.c
@@ -1180,12 +1180,11 @@ static void
 qla2xxx_process_purls_pkt(struct scsi_qla_host *vha, struct purex_item *item)
 {
 	struct qla_nvme_unsol_ctx *uctx = item->purls_context;
-	fc_port_t *fcport = uctx->fcport;
 	struct qla_nvme_lsrjt_pt_arg a;
 	int ret = 1;
 
 #if (IS_ENABLED(CONFIG_NVME_FC))
-	ret = nvme_fc_rcv_ls_req(fcport->nvme_remote_port, &uctx->lsrsp,
+	ret = nvme_fc_rcv_ls_req(uctx->fcport->nvme_remote_port, &uctx->lsrsp,
 				 &item->iocb, item->size);
 #endif
 	if (ret) {

From d0bac0ec89d66f656f77443c8000fa6c36139b66 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Tue, 29 Aug 2023 09:35:42 -0700
Subject: [PATCH 0810/1189] scsi: ufs: Fix the build for the old ARM OABI

All structs and unions are word aligned when using the OABI. Mark the union
in struct utp_upiu_header as packed to prevent that the compiler inserts
padding bytes.

Cc: Arnd Bergmann <arnd@arndb.de>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202308251634.tuRn4OVv-lkp@intel.com/
Fixes: 617bfaa8dd50 ("scsi: ufs: Simplify response header parsing")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20230829163547.1200183-1-bvanassche@acm.org
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Bean Huo <beanhuo@micron.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 include/uapi/scsi/scsi_bsg_ufs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/uapi/scsi/scsi_bsg_ufs.h b/include/uapi/scsi/scsi_bsg_ufs.h
index 7c7975f9905e..03f2beadf201 100644
--- a/include/uapi/scsi/scsi_bsg_ufs.h
+++ b/include/uapi/scsi/scsi_bsg_ufs.h
@@ -83,7 +83,7 @@ struct utp_upiu_header {
 			union {
 				__u8 tm_function;
 				__u8 query_function;
-			};
+			} __attribute__((packed));
 			__u8 response;
 			__u8 status;
 			__u8 ehs_length;

From be946e31bcf2b1c01f1af443c238bc15fe9f6294 Mon Sep 17 00:00:00 2001
From: Wenchao Hao <haowenchao2@huawei.com>
Date: Sat, 29 Jul 2023 18:24:51 +0800
Subject: [PATCH 0811/1189] scsi: libsas: Simplify sas_queue_reset() and remove
 unused code

sas_queue_reset() is always called with param "wait" set to 0, so remove it
from this function's parameter list. Also remove unused function
sas_wait_eh().

Signed-off-by: Wenchao Hao <haowenchao2@huawei.com>
Link: https://lore.kernel.org/r/20230729102451.2452826-1-haowenchao2@huawei.com
Reviewed-by: Jason Yan <yanaijie@huawei.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/libsas/sas_scsi_host.c | 41 +++--------------------------
 1 file changed, 3 insertions(+), 38 deletions(-)

diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c
index 0c103f4523b8..9047cfcd1072 100644
--- a/drivers/scsi/libsas/sas_scsi_host.c
+++ b/drivers/scsi/libsas/sas_scsi_host.c
@@ -386,37 +386,7 @@ struct sas_phy *sas_get_local_phy(struct domain_device *dev)
 }
 EXPORT_SYMBOL_GPL(sas_get_local_phy);
 
-static void sas_wait_eh(struct domain_device *dev)
-{
-	struct sas_ha_struct *ha = dev->port->ha;
-	DEFINE_WAIT(wait);
-
-	if (dev_is_sata(dev)) {
-		ata_port_wait_eh(dev->sata_dev.ap);
-		return;
-	}
- retry:
-	spin_lock_irq(&ha->lock);
-
-	while (test_bit(SAS_DEV_EH_PENDING, &dev->state)) {
-		prepare_to_wait(&ha->eh_wait_q, &wait, TASK_UNINTERRUPTIBLE);
-		spin_unlock_irq(&ha->lock);
-		schedule();
-		spin_lock_irq(&ha->lock);
-	}
-	finish_wait(&ha->eh_wait_q, &wait);
-
-	spin_unlock_irq(&ha->lock);
-
-	/* make sure SCSI EH is complete */
-	if (scsi_host_in_recovery(ha->shost)) {
-		msleep(10);
-		goto retry;
-	}
-}
-
-static int sas_queue_reset(struct domain_device *dev, int reset_type,
-			   u64 lun, int wait)
+static int sas_queue_reset(struct domain_device *dev, int reset_type, u64 lun)
 {
 	struct sas_ha_struct *ha = dev->port->ha;
 	int scheduled = 0, tries = 100;
@@ -424,8 +394,6 @@ static int sas_queue_reset(struct domain_device *dev, int reset_type,
 	/* ata: promote lun reset to bus reset */
 	if (dev_is_sata(dev)) {
 		sas_ata_schedule_reset(dev);
-		if (wait)
-			sas_ata_wait_eh(dev);
 		return SUCCESS;
 	}
 
@@ -443,9 +411,6 @@ static int sas_queue_reset(struct domain_device *dev, int reset_type,
 		}
 		spin_unlock_irq(&ha->lock);
 
-		if (wait)
-			sas_wait_eh(dev);
-
 		if (scheduled)
 			return SUCCESS;
 	}
@@ -498,7 +463,7 @@ int sas_eh_device_reset_handler(struct scsi_cmnd *cmd)
 	struct sas_internal *i = to_sas_internal(host->transportt);
 
 	if (current != host->ehandler)
-		return sas_queue_reset(dev, SAS_DEV_LU_RESET, cmd->device->lun, 0);
+		return sas_queue_reset(dev, SAS_DEV_LU_RESET, cmd->device->lun);
 
 	int_to_scsilun(cmd->device->lun, &lun);
 
@@ -521,7 +486,7 @@ int sas_eh_target_reset_handler(struct scsi_cmnd *cmd)
 	struct sas_internal *i = to_sas_internal(host->transportt);
 
 	if (current != host->ehandler)
-		return sas_queue_reset(dev, SAS_DEV_RESET, 0, 0);
+		return sas_queue_reset(dev, SAS_DEV_RESET, 0);
 
 	if (!i->dft->lldd_I_T_nexus_reset)
 		return FAILED;

From b5947239bfa666afd05ce0fc02b9c41ec8209e88 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Tue, 29 Aug 2023 14:29:50 +0100
Subject: [PATCH 0812/1189] net: stmmac: failure to probe without MAC interface
 specified

Alexander Stein reports that commit a014c35556b9 ("net: stmmac: clarify
difference between "interface" and "phy_interface"") caused breakage,
because plat->mac_interface will never be negative. Fix this by using
the "rc" temporary variable in stmmac_probe_config_dt().

Reported-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Tested-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Link: https://lore.kernel.org/r/E1qayn0-006Q8J-GE@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 35f4b1484029..0f28795e581c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -419,9 +419,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 		return ERR_PTR(phy_mode);
 
 	plat->phy_interface = phy_mode;
-	plat->mac_interface = stmmac_of_get_mac_mode(np);
-	if (plat->mac_interface < 0)
-		plat->mac_interface = plat->phy_interface;
+	rc = stmmac_of_get_mac_mode(np);
+	plat->mac_interface = rc < 0 ? plat->phy_interface : rc;
 
 	/* Some wrapper drivers still rely on phy_node. Let's save it while
 	 * they are not converted to phylink. */

From 8b72d2a1c6cc148320a93d029eb3a7e721f951f6 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Tue, 29 Aug 2023 10:47:17 +0200
Subject: [PATCH 0813/1189] NFC: nxp: add NXP1002

It is backwards compatible

Signed-off-by: Oliver Neukum <oneukum@suse.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20230829084717.961-1-oneukum@suse.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/nfc/nxp-nci/i2c.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/nfc/nxp-nci/i2c.c b/drivers/nfc/nxp-nci/i2c.c
index dca25a0c2f33..3ae4b41c59ac 100644
--- a/drivers/nfc/nxp-nci/i2c.c
+++ b/drivers/nfc/nxp-nci/i2c.c
@@ -336,6 +336,7 @@ MODULE_DEVICE_TABLE(of, of_nxp_nci_i2c_match);
 #ifdef CONFIG_ACPI
 static const struct acpi_device_id acpi_id[] = {
 	{ "NXP1001" },
+	{ "NXP1002" },
 	{ "NXP7471" },
 	{ }
 };

From ee940b57a92965b76e05075e0a20f7d16a1cf976 Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Tue, 29 Aug 2023 09:55:39 +0100
Subject: [PATCH 0814/1189] doc/netlink: Fix missing classic_netlink doc
 reference

Add missing cross-reference label for classic_netlink.

Fixes: 2db8abf0b455 ("doc/netlink: Document the netlink-raw schema extensions")
Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://lore.kernel.org/r/20230829085539.36354-1-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/userspace-api/netlink/intro.rst | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/userspace-api/netlink/intro.rst b/Documentation/userspace-api/netlink/intro.rst
index 0955e9f203d3..3ea70ad53c58 100644
--- a/Documentation/userspace-api/netlink/intro.rst
+++ b/Documentation/userspace-api/netlink/intro.rst
@@ -528,6 +528,8 @@ families may, however, require a larger buffer. 32kB buffer is recommended
 for most efficient handling of dumps (larger buffer fits more dumped
 objects and therefore fewer recvmsg() calls are needed).
 
+.. _classic_netlink:
+
 Classic Netlink
 ===============
 

From 4ca10f3e31745d35249a727ecd108eb58f0a8c5e Mon Sep 17 00:00:00 2001
From: Ranjan Kumar <ranjan.kumar@broadcom.com>
Date: Tue, 29 Aug 2023 14:30:19 +0530
Subject: [PATCH 0815/1189] scsi: mpt3sas: Perform additional retries if
 doorbell read returns 0

The driver retries certain register reads 3 times if the returned value is
0. This was done because the controller could return 0 for certain
registers if other registers were being accessed concurrently by the BMC.

In certain systems with increased BMC interactions, the register values
returned can be 0 for longer than 3 retries. Change the retry count from 3
to 30 for the affected registers to prevent problems with out-of-band
management.

Fixes: b899202901a8 ("scsi: mpt3sas: Add separate function for aero doorbell reads")
Cc: stable@vger.kernel.org
Signed-off-by: Ranjan Kumar <ranjan.kumar@broadcom.com>
Link: https://lore.kernel.org/r/20230829090020.5417-2-ranjan.kumar@broadcom.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mpt3sas/mpt3sas_base.c | 46 +++++++++++++++++++++--------
 drivers/scsi/mpt3sas/mpt3sas_base.h |  1 +
 2 files changed, 34 insertions(+), 13 deletions(-)

diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 53f5492579cb..5284584e4cd2 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -138,6 +138,9 @@ _base_get_ioc_facts(struct MPT3SAS_ADAPTER *ioc);
 static void
 _base_clear_outstanding_commands(struct MPT3SAS_ADAPTER *ioc);
 
+static u32
+_base_readl_ext_retry(const volatile void __iomem *addr);
+
 /**
  * mpt3sas_base_check_cmd_timeout - Function
  *		to check timeout and command termination due
@@ -213,6 +216,20 @@ _base_readl_aero(const volatile void __iomem *addr)
 	return ret_val;
 }
 
+static u32
+_base_readl_ext_retry(const volatile void __iomem *addr)
+{
+	u32 i, ret_val;
+
+	for (i = 0 ; i < 30 ; i++) {
+		ret_val = readl(addr);
+		if (ret_val == 0)
+			continue;
+	}
+
+	return ret_val;
+}
+
 static inline u32
 _base_readl(const volatile void __iomem *addr)
 {
@@ -940,7 +957,7 @@ mpt3sas_halt_firmware(struct MPT3SAS_ADAPTER *ioc)
 
 	dump_stack();
 
-	doorbell = ioc->base_readl(&ioc->chip->Doorbell);
+	doorbell = ioc->base_readl_ext_retry(&ioc->chip->Doorbell);
 	if ((doorbell & MPI2_IOC_STATE_MASK) == MPI2_IOC_STATE_FAULT) {
 		mpt3sas_print_fault_code(ioc, doorbell &
 		    MPI2_DOORBELL_DATA_MASK);
@@ -6686,7 +6703,7 @@ mpt3sas_base_get_iocstate(struct MPT3SAS_ADAPTER *ioc, int cooked)
 {
 	u32 s, sc;
 
-	s = ioc->base_readl(&ioc->chip->Doorbell);
+	s = ioc->base_readl_ext_retry(&ioc->chip->Doorbell);
 	sc = s & MPI2_IOC_STATE_MASK;
 	return cooked ? sc : s;
 }
@@ -6831,7 +6848,7 @@ _base_wait_for_doorbell_ack(struct MPT3SAS_ADAPTER *ioc, int timeout)
 					   __func__, count, timeout));
 			return 0;
 		} else if (int_status & MPI2_HIS_IOC2SYS_DB_STATUS) {
-			doorbell = ioc->base_readl(&ioc->chip->Doorbell);
+			doorbell = ioc->base_readl_ext_retry(&ioc->chip->Doorbell);
 			if ((doorbell & MPI2_IOC_STATE_MASK) ==
 			    MPI2_IOC_STATE_FAULT) {
 				mpt3sas_print_fault_code(ioc, doorbell);
@@ -6871,7 +6888,7 @@ _base_wait_for_doorbell_not_used(struct MPT3SAS_ADAPTER *ioc, int timeout)
 	count = 0;
 	cntdn = 1000 * timeout;
 	do {
-		doorbell_reg = ioc->base_readl(&ioc->chip->Doorbell);
+		doorbell_reg = ioc->base_readl_ext_retry(&ioc->chip->Doorbell);
 		if (!(doorbell_reg & MPI2_DOORBELL_USED)) {
 			dhsprintk(ioc,
 				  ioc_info(ioc, "%s: successful count(%d), timeout(%d)\n",
@@ -7019,7 +7036,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
 	__le32 *mfp;
 
 	/* make sure doorbell is not in use */
-	if ((ioc->base_readl(&ioc->chip->Doorbell) & MPI2_DOORBELL_USED)) {
+	if ((ioc->base_readl_ext_retry(&ioc->chip->Doorbell) & MPI2_DOORBELL_USED)) {
 		ioc_err(ioc, "doorbell is in use (line=%d)\n", __LINE__);
 		return -EFAULT;
 	}
@@ -7068,7 +7085,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
 	}
 
 	/* read the first two 16-bits, it gives the total length of the reply */
-	reply[0] = le16_to_cpu(ioc->base_readl(&ioc->chip->Doorbell)
+	reply[0] = le16_to_cpu(ioc->base_readl_ext_retry(&ioc->chip->Doorbell)
 	    & MPI2_DOORBELL_DATA_MASK);
 	writel(0, &ioc->chip->HostInterruptStatus);
 	if ((_base_wait_for_doorbell_int(ioc, 5))) {
@@ -7076,7 +7093,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
 			__LINE__);
 		return -EFAULT;
 	}
-	reply[1] = le16_to_cpu(ioc->base_readl(&ioc->chip->Doorbell)
+	reply[1] = le16_to_cpu(ioc->base_readl_ext_retry(&ioc->chip->Doorbell)
 	    & MPI2_DOORBELL_DATA_MASK);
 	writel(0, &ioc->chip->HostInterruptStatus);
 
@@ -7087,10 +7104,10 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
 			return -EFAULT;
 		}
 		if (i >=  reply_bytes/2) /* overflow case */
-			ioc->base_readl(&ioc->chip->Doorbell);
+			ioc->base_readl_ext_retry(&ioc->chip->Doorbell);
 		else
 			reply[i] = le16_to_cpu(
-			    ioc->base_readl(&ioc->chip->Doorbell)
+			    ioc->base_readl_ext_retry(&ioc->chip->Doorbell)
 			    & MPI2_DOORBELL_DATA_MASK);
 		writel(0, &ioc->chip->HostInterruptStatus);
 	}
@@ -7949,7 +7966,7 @@ _base_diag_reset(struct MPT3SAS_ADAPTER *ioc)
 			goto out;
 		}
 
-		host_diagnostic = ioc->base_readl(&ioc->chip->HostDiagnostic);
+		host_diagnostic = ioc->base_readl_ext_retry(&ioc->chip->HostDiagnostic);
 		drsprintk(ioc,
 			  ioc_info(ioc, "wrote magic sequence: count(%d), host_diagnostic(0x%08x)\n",
 				   count, host_diagnostic));
@@ -7969,7 +7986,7 @@ _base_diag_reset(struct MPT3SAS_ADAPTER *ioc)
 	for (count = 0; count < (300000000 /
 		MPI2_HARD_RESET_PCIE_SECOND_READ_DELAY_MICRO_SEC); count++) {
 
-		host_diagnostic = ioc->base_readl(&ioc->chip->HostDiagnostic);
+		host_diagnostic = ioc->base_readl_ext_retry(&ioc->chip->HostDiagnostic);
 
 		if (host_diagnostic == 0xFFFFFFFF) {
 			ioc_info(ioc,
@@ -8359,10 +8376,13 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc)
 	ioc->rdpq_array_enable_assigned = 0;
 	ioc->use_32bit_dma = false;
 	ioc->dma_mask = 64;
-	if (ioc->is_aero_ioc)
+	if (ioc->is_aero_ioc) {
 		ioc->base_readl = &_base_readl_aero;
-	else
+		ioc->base_readl_ext_retry = &_base_readl_ext_retry;
+	} else {
 		ioc->base_readl = &_base_readl;
+		ioc->base_readl_ext_retry = &_base_readl;
+	}
 	r = mpt3sas_base_map_resources(ioc);
 	if (r)
 		goto out_free_resources;
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index 05364aa15ecd..10055c7e4a9f 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -1618,6 +1618,7 @@ struct MPT3SAS_ADAPTER {
 	u8		diag_trigger_active;
 	u8		atomic_desc_capable;
 	BASE_READ_REG	base_readl;
+	BASE_READ_REG	base_readl_ext_retry;
 	struct SL_WH_MASTER_TRIGGER_T diag_trigger_master;
 	struct SL_WH_EVENT_TRIGGERS_T diag_trigger_event;
 	struct SL_WH_SCSI_TRIGGERS_T diag_trigger_scsi;

From 0854065092a7a49a88bb592473abafb0cecd9f1c Mon Sep 17 00:00:00 2001
From: Ranjan Kumar <ranjan.kumar@broadcom.com>
Date: Tue, 29 Aug 2023 14:30:20 +0530
Subject: [PATCH 0816/1189] scsi: mpt3sas: Remove volatile qualifier

Remove reduntant volatile qualifier.

Signed-off-by: Ranjan Kumar <ranjan.kumar@broadcom.com>
Link: https://lore.kernel.org/r/20230829090020.5417-3-ranjan.kumar@broadcom.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mpt3sas/mpi/mpi2.h     | 2 +-
 drivers/scsi/mpt3sas/mpt3sas_base.c | 8 ++++----
 drivers/scsi/mpt3sas/mpt3sas_base.h | 2 +-
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/scsi/mpt3sas/mpi/mpi2.h b/drivers/scsi/mpt3sas/mpi/mpi2.h
index ed3923f8db4f..6de35b32223c 100644
--- a/drivers/scsi/mpt3sas/mpi/mpi2.h
+++ b/drivers/scsi/mpt3sas/mpi/mpi2.h
@@ -199,7 +199,7 @@
 *
 *****************************************************************************/
 
-typedef volatile struct _MPI2_SYSTEM_INTERFACE_REGS {
+typedef struct _MPI2_SYSTEM_INTERFACE_REGS {
 	U32 Doorbell;		/*0x00 */
 	U32 WriteSequence;	/*0x04 */
 	U32 HostDiagnostic;	/*0x08 */
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 5284584e4cd2..61a32bf00747 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -139,7 +139,7 @@ static void
 _base_clear_outstanding_commands(struct MPT3SAS_ADAPTER *ioc);
 
 static u32
-_base_readl_ext_retry(const volatile void __iomem *addr);
+_base_readl_ext_retry(const void __iomem *addr);
 
 /**
  * mpt3sas_base_check_cmd_timeout - Function
@@ -204,7 +204,7 @@ module_param_call(mpt3sas_fwfault_debug, _scsih_set_fwfault_debug,
  * while reading the system interface register.
  */
 static inline u32
-_base_readl_aero(const volatile void __iomem *addr)
+_base_readl_aero(const void __iomem *addr)
 {
 	u32 i = 0, ret_val;
 
@@ -217,7 +217,7 @@ _base_readl_aero(const volatile void __iomem *addr)
 }
 
 static u32
-_base_readl_ext_retry(const volatile void __iomem *addr)
+_base_readl_ext_retry(const void __iomem *addr)
 {
 	u32 i, ret_val;
 
@@ -231,7 +231,7 @@ _base_readl_ext_retry(const volatile void __iomem *addr)
 }
 
 static inline u32
-_base_readl(const volatile void __iomem *addr)
+_base_readl(const void __iomem *addr)
 {
 	return readl(addr);
 }
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index 10055c7e4a9f..1be0850ca17a 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -994,7 +994,7 @@ typedef void (*NVME_BUILD_PRP)(struct MPT3SAS_ADAPTER *ioc, u16 smid,
 typedef void (*PUT_SMID_IO_FP_HIP) (struct MPT3SAS_ADAPTER *ioc, u16 smid,
 	u16 funcdep);
 typedef void (*PUT_SMID_DEFAULT) (struct MPT3SAS_ADAPTER *ioc, u16 smid);
-typedef u32 (*BASE_READ_REG) (const volatile void __iomem *addr);
+typedef u32 (*BASE_READ_REG) (const void __iomem *addr);
 /*
  * To get high iops reply queue's msix index when high iops mode is enabled
  * else get the msix index of general reply queues.

From c91e585cfb3dd7d076e9ba0967908fc504d32def Mon Sep 17 00:00:00 2001
From: Bean Huo <beanhuo@micron.com>
Date: Wed, 9 Aug 2023 20:18:46 +0200
Subject: [PATCH 0817/1189] scsi: ufs: core: Add advanced RPMB support where
 UFSHCI 4.0 does not support EHS length in UTRD
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

According to UFSHCI 4.0 specification:

5.2 Host Controller Capabilities Registers
5.2.1 Offset 00h: CAP – Controller Capabilities:

 "EHS Length in UTRD Supported (EHSLUTRDS): Indicates whether the host
  controller supports EHS Length field in UTRD.

  0 – Host controller takes EHS length from CMD UPIU, and SW driver use EHS
  Length field in CMD UPIU.

  1 – HW controller takes EHS length from UTRD, and SW driver use EHS
  Length field in UTRD.

  NOTE Recommend Host controllers move to taking EHS length from UTRD, and
  in UFS-5, it will be mandatory."

So, when UFSHCI 4.0 doesn't support EHS Length field in UTRD, we could use
EHS Length field in CMD UPIU. Remove the limitation that advanced RPMB only
works when EHS length is supported in UTRD.

Fixes: 6ff265fc5ef6 ("scsi: ufs: core: bsg: Add advanced RPMB support in ufs_bsg")
Co-developed-by: "jonghwi.rha" <jonghwi.rha@samsung.com>
Signed-off-by: "jonghwi.rha" <jonghwi.rha@samsung.com>
Signed-off-by: Bean Huo <beanhuo@micron.com>
Link: https://lore.kernel.org/r/20230809181847.102123-2-beanhuo@iokpp.de
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufs_bsg.c |  3 +--
 drivers/ufs/core/ufshcd.c  | 10 +++++++++-
 2 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/ufs/core/ufs_bsg.c b/drivers/ufs/core/ufs_bsg.c
index 34e423924e06..374e5aae4e7e 100644
--- a/drivers/ufs/core/ufs_bsg.c
+++ b/drivers/ufs/core/ufs_bsg.c
@@ -76,8 +76,7 @@ static int ufs_bsg_exec_advanced_rpmb_req(struct ufs_hba *hba, struct bsg_job *j
 	int ret;
 	int data_len;
 
-	if (hba->ufs_version < ufshci_version(4, 0) || !hba->dev_info.b_advanced_rpmb_en ||
-	    !(hba->capabilities & MASK_EHSLUTRD_SUPPORTED))
+	if (hba->ufs_version < ufshci_version(4, 0) || !hba->dev_info.b_advanced_rpmb_en)
 		return -EINVAL;
 
 	if (rpmb_request->ehs_req.length != 2 || rpmb_request->ehs_req.ehs_type != 1)
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index e4318171381b..f774169bf04f 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -7240,7 +7240,15 @@ int ufshcd_advanced_rpmb_req_handler(struct ufs_hba *hba, struct utp_upiu_req *r
 	/* Advanced RPMB starts from UFS 4.0, so its command type is UTP_CMD_TYPE_UFS_STORAGE */
 	lrbp->command_type = UTP_CMD_TYPE_UFS_STORAGE;
 
-	ufshcd_prepare_req_desc_hdr(lrbp, &upiu_flags, dir, 2);
+	/*
+	 * According to UFSHCI 4.0 specification page 24, if EHSLUTRDS is 0, host controller takes
+	 * EHS length from CMD UPIU, and SW driver use EHS Length field in CMD UPIU. if it is 1,
+	 * HW controller takes EHS length from UTRD.
+	 */
+	if (hba->capabilities & MASK_EHSLUTRD_SUPPORTED)
+		ufshcd_prepare_req_desc_hdr(lrbp, &upiu_flags, dir, 2);
+	else
+		ufshcd_prepare_req_desc_hdr(lrbp, &upiu_flags, dir, 0);
 
 	/* update the task tag and LUN in the request upiu */
 	req_upiu->header.flags = upiu_flags;

From 9f6fec65661381e301ae0f9ee8b4c12b0214a579 Mon Sep 17 00:00:00 2001
From: Bean Huo <beanhuo@micron.com>
Date: Wed, 9 Aug 2023 20:18:47 +0200
Subject: [PATCH 0818/1189] scsi: ufs: core: No need to update
 UPIU.header.flags and lun in advanced RPMB handler

For advanced RPMB requests, its UPIU package should be fully initialized in
its ufs-bsg-based application, except for task tag. in ufshcd.c, we just
copy UPIU (with CDB) request as-is.

Signed-off-by: Bean Huo <beanhuo@micron.com>
Link: https://lore.kernel.org/r/20230809181847.102123-3-beanhuo@iokpp.de
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index f774169bf04f..93417518c04d 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -7250,9 +7250,7 @@ int ufshcd_advanced_rpmb_req_handler(struct ufs_hba *hba, struct utp_upiu_req *r
 	else
 		ufshcd_prepare_req_desc_hdr(lrbp, &upiu_flags, dir, 0);
 
-	/* update the task tag and LUN in the request upiu */
-	req_upiu->header.flags = upiu_flags;
-	req_upiu->header.lun = UFS_UPIU_RPMB_WLUN;
+	/* update the task tag */
 	req_upiu->header.task_tag = tag;
 
 	/* copy the UPIU(contains CDB) request as it is */

From 196e355877a767674ea9c35af1686e642294885a Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 29 Aug 2023 17:05:45 -0700
Subject: [PATCH 0819/1189] perf pmu: Avoid uninitialized use of alias->str

alias is allocated with malloc allowing uninitialized memory to be
accessed.

The initialization of str was moved late after it could have been
updated by a JSON event, however, this create a potential for an
uninitialized use.

Fix this by assigning str to NULL early.

Testing on ARM (Raspberry Pi) showed a memory leak in the same code so
add a zfree.

Fixes: f63a536f03a2f64f ("perf pmu: Merge JSON events with sysfs at load time")
Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Link: https://lore.kernel.org/r/20230830000545.1638964-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/pmu.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index cde33e01959a..b3f8f3f1e900 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -532,6 +532,7 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name,
 	if (!alias)
 		return -ENOMEM;
 
+	alias->str = NULL;
 	INIT_LIST_HEAD(&alias->terms);
 	alias->scale = 1.0;
 	alias->unit[0] = '\0';
@@ -593,6 +594,7 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name,
 			ret += scnprintf(newval + ret, sizeof(newval) - ret,
 					 "%s=%s", term->config, term->val.str);
 	}
+	zfree(&alias->str);
 	alias->str = strdup(newval);
 	if (!pe)
 		pmu->sysfs_aliases++;

From 6beb6cfddff98cb53e01c0bebb0da8030506fb76 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 30 Aug 2023 00:07:51 -0700
Subject: [PATCH 0820/1189] perf parse-events: Minor help message improvements

Be more specific and fix a typo.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20230830070753.1821629-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.y | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 3a9d4e2513b5..4a370c36a0d5 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -342,7 +342,7 @@ PE_NAME opt_pmu_config
 			struct parse_events_error *error = parse_state->error;
 			char *help;
 
-			if (asprintf(&help, "Unabled to find PMU or event on a PMU of '%s'", $1) < 0)
+			if (asprintf(&help, "Unable to find PMU or event on a PMU of '%s'", $1) < 0)
 				help = NULL;
 			parse_events_error__handle(error, @1.first_column,
 						   strdup("Bad event or PMU"),
@@ -368,7 +368,7 @@ PE_NAME sep_dc
 		struct parse_events_error *error = parse_state->error;
 		char *help;
 
-		if (asprintf(&help, "Unabled to find PMU or event on a PMU of '%s'", $1) < 0)
+		if (asprintf(&help, "Unable to find event on a PMU of '%s'", $1) < 0)
 			help = NULL;
 		parse_events_error__handle(error, @1.first_column, strdup("Bad event name"), help);
 		free($1);

From 7a6e91644708d514082a00fce3cd509960935fb8 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 30 Aug 2023 00:07:52 -0700
Subject: [PATCH 0821/1189] perf parse-events: Make common term list to strbuf
 helper

A term list is turned into a string for debug output and for the str
value in the alias.

Add a helper to do this based on existing code, but then fix for
situations like events being identified.

Use strbuf to manage the dynamic memory allocation and remove the 256
byte limit.

Use in various places the string of the term list is required.

Before:

  $ sudo perf stat -vv -e inst_retired.any true
  Using CPUID GenuineIntel-6-8D-1
  intel_pt default config: tsc,mtc,mtc_period=3,psb_period=3,pt,branch
  Attempting to add event pmu 'cpu' with 'inst_retired.any,' that may result in non-fatal errors
  After aliases, add event pmu 'cpu' with 'event,period,' that may result in non-fatal errors
  inst_retired.any -> cpu/inst_retired.any/
  ...

After:

$ sudo perf stat -vv -e inst_retired.any true

  Using CPUID GenuineIntel-6-8D-1
  intel_pt default config: tsc,mtc,mtc_period=3,psb_period=3,pt,branch
  Attempt to add: cpu/inst_retired.any/
  ..after resolving event: cpu/event=0xc0,period=0x1e8483/
  inst_retired.any -> cpu/event=0xc0,period=0x1e8483/
  ...

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20230830070753.1821629-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.c | 101 ++++++++++++++++++++++++---------
 tools/perf/util/parse-events.h |   2 +
 tools/perf/util/pmu.c          |  19 ++-----
 3 files changed, 81 insertions(+), 41 deletions(-)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 4c812fbe0cf9..0b941b58bdc0 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -13,7 +13,7 @@
 #include <subcmd/parse-options.h>
 #include "parse-events.h"
 #include "string2.h"
-#include "strlist.h"
+#include "strbuf.h"
 #include "debug.h"
 #include <api/fs/tracing_path.h>
 #include <perf/cpumap.h>
@@ -1303,19 +1303,6 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 
 	pmu = parse_state->fake_pmu ?: perf_pmus__find(name);
 
-	if (verbose > 1 && !(pmu && pmu->selectable)) {
-		fprintf(stderr, "Attempting to add event pmu '%s' with '",
-			name);
-		if (head_config) {
-			struct parse_events_term *term;
-
-			list_for_each_entry(term, head_config, list) {
-				fprintf(stderr, "%s,", term->config);
-			}
-		}
-		fprintf(stderr, "' that may result in non-fatal errors\n");
-	}
-
 	if (!pmu) {
 		char *err_str;
 
@@ -1325,6 +1312,21 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 			parse_events_error__handle(err, loc->first_column, err_str, NULL);
 		return -EINVAL;
 	}
+
+	if (verbose > 1) {
+		struct strbuf sb;
+
+		strbuf_init(&sb, /*hint=*/ 0);
+		if (pmu->selectable && !head_config) {
+			strbuf_addf(&sb, "%s//", name);
+		} else {
+			strbuf_addf(&sb, "%s/", name);
+			parse_events_term__to_strbuf(head_config, &sb);
+			strbuf_addch(&sb, '/');
+		}
+		fprintf(stderr, "Attempt to add: %s\n", sb.buf);
+		strbuf_release(&sb);
+	}
 	if (head_config)
 		fix_raw(head_config, pmu);
 
@@ -1349,16 +1351,12 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 		return -EINVAL;
 
 	if (verbose > 1) {
-		fprintf(stderr, "After aliases, add event pmu '%s' with '",
-			name);
-		if (head_config) {
-			struct parse_events_term *term;
+		struct strbuf sb;
 
-			list_for_each_entry(term, head_config, list) {
-				fprintf(stderr, "%s,", term->config);
-			}
-		}
-		fprintf(stderr, "' that may result in non-fatal errors\n");
+		strbuf_init(&sb, /*hint=*/ 0);
+		parse_events_term__to_strbuf(head_config, &sb);
+		fprintf(stderr, "..after resolving event: %s/%s/\n", name, sb.buf);
+		strbuf_release(&sb);
 	}
 
 	/*
@@ -1460,7 +1458,12 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 		parse_events_copy_term_list(head, &orig_head);
 		if (!parse_events_add_pmu(parse_state, list, pmu->name,
 					  orig_head, auto_merge_stats, loc)) {
-			pr_debug("%s -> %s/%s/\n", str, pmu->name, str);
+			struct strbuf sb;
+
+			strbuf_init(&sb, /*hint=*/ 0);
+			parse_events_term__to_strbuf(orig_head, &sb);
+			pr_debug("%s -> %s/%s/\n", str, pmu->name, sb.buf);
+			strbuf_release(&sb);
 			ok++;
 		}
 		parse_events_terms__delete(orig_head);
@@ -1469,7 +1472,12 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 	if (parse_state->fake_pmu) {
 		if (!parse_events_add_pmu(parse_state, list, str, head,
 					  /*auto_merge_stats=*/true, loc)) {
-			pr_debug("%s -> %s/%s/\n", str, "fake_pmu", str);
+			struct strbuf sb;
+
+			strbuf_init(&sb, /*hint=*/ 0);
+			parse_events_term__to_strbuf(head, &sb);
+			pr_debug("%s -> %s/%s/\n", str, "fake_pmu", sb.buf);
+			strbuf_release(&sb);
 			ok++;
 		}
 	}
@@ -2085,7 +2093,7 @@ void parse_events_error__handle(struct parse_events_error *err, int idx,
 		break;
 	default:
 		pr_debug("Multiple errors dropping message: %s (%s)\n",
-			err->str, err->help);
+			err->str, err->help ?: "<no help>");
 		free(err->str);
 		err->str = str;
 		free(err->help);
@@ -2502,6 +2510,47 @@ void parse_events_terms__delete(struct list_head *terms)
 	free(terms);
 }
 
+int parse_events_term__to_strbuf(struct list_head *term_list, struct strbuf *sb)
+{
+	struct parse_events_term *term;
+	bool first = true;
+
+	if (!term_list)
+		return 0;
+
+	list_for_each_entry(term, term_list, list) {
+		int ret;
+
+		if (!first) {
+			ret = strbuf_addch(sb, ',');
+			if (ret < 0)
+				return ret;
+		}
+		first = false;
+
+		if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM)
+			if (term->type_term == PARSE_EVENTS__TERM_TYPE_USER && term->val.num == 1)
+				ret = strbuf_addf(sb, "%s", term->config);
+			else
+				ret = strbuf_addf(sb, "%s=%#"PRIx64, term->config, term->val.num);
+		else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) {
+			if (term->config) {
+				ret = strbuf_addf(sb, "%s=", term->config);
+				if (ret < 0)
+					return ret;
+			} else if (term->type_term < __PARSE_EVENTS__TERM_TYPE_NR) {
+				ret = strbuf_addf(sb, "%s=", config_term_names[term->type_term]);
+				if (ret < 0)
+					return ret;
+			}
+			ret = strbuf_addf(sb, "%s", term->val.str);
+		}
+		if (ret < 0)
+			return ret;
+	}
+	return 0;
+}
+
 void parse_events_evlist_error(struct parse_events_state *parse_state,
 			       int idx, const char *str)
 {
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 6d75d853ce00..20bdc35d6112 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -18,6 +18,7 @@ struct parse_events_error;
 
 struct option;
 struct perf_pmu;
+struct strbuf;
 
 const char *event_type(int type);
 
@@ -152,6 +153,7 @@ int parse_events_term__clone(struct parse_events_term **new,
 void parse_events_term__delete(struct parse_events_term *term);
 void parse_events_terms__delete(struct list_head *terms);
 void parse_events_terms__purge(struct list_head *terms);
+int parse_events_term__to_strbuf(struct list_head *term_list, struct strbuf *sb);
 int parse_events__modifier_event(struct list_head *list, char *str, bool add);
 int parse_events__modifier_group(struct list_head *list, char *event_mod);
 int parse_events_name(struct list_head *list, const char *name);
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index b3f8f3f1e900..8dbb7008877e 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -507,12 +507,11 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name,
 				const char *desc, const char *val, FILE *val_fd,
 				const struct pmu_event *pe)
 {
-	struct parse_events_term *term;
 	struct perf_pmu_alias *alias;
 	int ret;
-	char newval[256];
 	const char *long_desc = NULL, *topic = NULL, *unit = NULL, *pmu_name = NULL;
 	bool deprecated = false, perpkg = false;
+	struct strbuf sb;
 
 	if (perf_pmu__find_alias(pmu, name, /*load=*/ false)) {
 		/* Alias was already created/loaded. */
@@ -582,20 +581,10 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name,
 	 *
 	 * Rebuild string to make alias->str member comparable.
 	 */
-	ret = 0;
-	list_for_each_entry(term, &alias->terms, list) {
-		if (ret)
-			ret += scnprintf(newval + ret, sizeof(newval) - ret,
-					 ",");
-		if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM)
-			ret += scnprintf(newval + ret, sizeof(newval) - ret,
-					 "%s=%#x", term->config, term->val.num);
-		else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR)
-			ret += scnprintf(newval + ret, sizeof(newval) - ret,
-					 "%s=%s", term->config, term->val.str);
-	}
 	zfree(&alias->str);
-	alias->str = strdup(newval);
+	strbuf_init(&sb, /*hint=*/ 0);
+	parse_events_term__to_strbuf(&alias->terms, &sb);
+	alias->str = strbuf_detach(&sb, /*sz=*/ NULL);
 	if (!pe)
 		pmu->sysfs_aliases++;
 	else

From 30f0b435bbf2b83cf822dbe40d23b41bdcae7156 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 30 Aug 2023 00:07:53 -0700
Subject: [PATCH 0822/1189] perf pmu: Remove str from perf_pmu_alias

Currently the value is only used in perf list.

Compute the value just when needed to avoid unnecessary overhead.

Recycle the strbuf to avoid memory allocation overhead.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20230830070753.1821629-3-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/pmu.c | 33 ++++++++++-----------------------
 1 file changed, 10 insertions(+), 23 deletions(-)

diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 8dbb7008877e..152cda84f273 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -51,11 +51,6 @@ struct perf_pmu_alias {
 	 * json events.
 	 */
 	char *topic;
-	/**
-	 * @str: Comma separated parameter list like
-	 * "event=0xcd,umask=0x1,ldlat=0x3".
-	 */
-	char *str;
 	/** @terms: Owned list of the original parsed parameters. */
 	struct list_head terms;
 	/** @list: List element of struct perf_pmu aliases. */
@@ -408,7 +403,6 @@ static void perf_pmu_free_alias(struct perf_pmu_alias *newalias)
 	zfree(&newalias->desc);
 	zfree(&newalias->long_desc);
 	zfree(&newalias->topic);
-	zfree(&newalias->str);
 	zfree(&newalias->pmu_name);
 	parse_events_terms__purge(&newalias->terms);
 	free(newalias);
@@ -489,7 +483,7 @@ static int update_alias(const struct pmu_event *pe,
 	assign_str(pe->name, "long_desc", &data->alias->long_desc, pe->long_desc);
 	assign_str(pe->name, "topic", &data->alias->topic, pe->topic);
 	data->alias->per_pkg = pe->perpkg;
-	if (assign_str(pe->name, "value", &data->alias->str, pe->event)) {
+	if (pe->event) {
 		parse_events_terms__purge(&data->alias->terms);
 		ret = parse_events_terms(&data->alias->terms, pe->event, /*input=*/NULL);
 	}
@@ -511,7 +505,6 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name,
 	int ret;
 	const char *long_desc = NULL, *topic = NULL, *unit = NULL, *pmu_name = NULL;
 	bool deprecated = false, perpkg = false;
-	struct strbuf sb;
 
 	if (perf_pmu__find_alias(pmu, name, /*load=*/ false)) {
 		/* Alias was already created/loaded. */
@@ -531,7 +524,6 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name,
 	if (!alias)
 		return -ENOMEM;
 
-	alias->str = NULL;
 	INIT_LIST_HEAD(&alias->terms);
 	alias->scale = 1.0;
 	alias->unit[0] = '\0';
@@ -574,17 +566,6 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name,
 		}
 	}
 
-	/* Scan event and remove leading zeroes, spaces, newlines, some
-	 * platforms have terms specified as
-	 * event=0x0091 (read from files ../<PMU>/events/<FILE>
-	 * and terms specified as event=0x91 (read from JSON files).
-	 *
-	 * Rebuild string to make alias->str member comparable.
-	 */
-	zfree(&alias->str);
-	strbuf_init(&sb, /*hint=*/ 0);
-	parse_events_term__to_strbuf(&alias->terms, &sb);
-	alias->str = strbuf_detach(&sb, /*sz=*/ NULL);
 	if (!pe)
 		pmu->sysfs_aliases++;
 	else
@@ -1682,7 +1663,9 @@ int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus,
 		.pmu = pmu,
 	};
 	int ret = 0;
+	struct strbuf sb;
 
+	strbuf_init(&sb, /*hint=*/ 0);
 	pmu_add_cpu_aliases(pmu);
 	list_for_each_entry(event, &pmu->aliases, list) {
 		size_t buf_used;
@@ -1710,14 +1693,16 @@ int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus,
 		info.desc = event->desc;
 		info.long_desc = event->long_desc;
 		info.encoding_desc = buf + buf_used;
+		parse_events_term__to_strbuf(&event->terms, &sb);
 		buf_used += snprintf(buf + buf_used, sizeof(buf) - buf_used,
-				"%s/%s/", info.pmu_name, event->str) + 1;
+				"%s/%s/", info.pmu_name, sb.buf) + 1;
 		info.topic = event->topic;
-		info.str = event->str;
+		info.str = sb.buf;
 		info.deprecated = event->deprecated;
 		ret = cb(state, &info);
 		if (ret)
-			return ret;
+			goto out;
+		strbuf_setlen(&sb, /*len=*/ 0);
 	}
 	if (pmu->selectable) {
 		info.name = buf;
@@ -1732,6 +1717,8 @@ int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus,
 		info.deprecated = false;
 		ret = cb(state, &info);
 	}
+out:
+	strbuf_release(&sb);
 	return ret;
 }
 

From f0005f1732245533f0bfa5bad4803c30a0e9f4e0 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 30 Aug 2023 00:30:26 -0700
Subject: [PATCH 0823/1189] perf metric: Add #num_cpus_online literal

Returns the number of CPUs online, unlike #num_cpus that returns the
number present.

Add a test of the property.

This will be used in future Intel metrics.

Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20230830073026.1829912-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/expr.c | 5 ++++-
 tools/perf/util/expr.c  | 7 +++++++
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
index c1c3fcbc2753..81229fa4f1e9 100644
--- a/tools/perf/tests/expr.c
+++ b/tools/perf/tests/expr.c
@@ -70,7 +70,7 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u
 {
 	struct expr_id_data *val_ptr;
 	const char *p;
-	double val, num_cpus, num_cores, num_dies, num_packages;
+	double val, num_cpus_online, num_cpus, num_cores, num_dies, num_packages;
 	int ret;
 	struct expr_parse_ctx *ctx;
 	bool is_intel = false;
@@ -227,7 +227,10 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u
 
 	/* Test toplogy constants appear well ordered. */
 	expr__ctx_clear(ctx);
+	TEST_ASSERT_VAL("#num_cpus_online",
+			expr__parse(&num_cpus_online, ctx, "#num_cpus_online") == 0);
 	TEST_ASSERT_VAL("#num_cpus", expr__parse(&num_cpus, ctx, "#num_cpus") == 0);
+	TEST_ASSERT_VAL("#num_cpus >= #num_cpus_online", num_cpus >= num_cpus_online);
 	TEST_ASSERT_VAL("#num_cores", expr__parse(&num_cores, ctx, "#num_cores") == 0);
 	TEST_ASSERT_VAL("#num_cpus >= #num_cores", num_cpus >= num_cores);
 	TEST_ASSERT_VAL("#num_dies", expr__parse(&num_dies, ctx, "#num_dies") == 0);
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index 0985a3cbc6f9..4488f306de78 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -427,6 +427,13 @@ double expr__get_literal(const char *literal, const struct expr_scanner_ctx *ctx
 		result = cpu__max_present_cpu().cpu;
 		goto out;
 	}
+	if (!strcmp("#num_cpus_online", literal)) {
+		struct perf_cpu_map *online = cpu_map__online();
+
+		if (online)
+			result = perf_cpu_map__nr(online);
+		goto out;
+	}
 
 	if (!strcasecmp("#system_tsc_freq", literal)) {
 		result = arch_get_tsc_freq();

From 45210e1ada6d7889e573e993b66ed0e958aaa8ec Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Wed, 30 Aug 2023 12:05:39 +0300
Subject: [PATCH 0824/1189] perf dlfilter: Avoid leak in v0 API test use of
 resolve_address()

The introduction of reference counting causes the v0 API
perf_dlfilter_fns.resolve_address() to leak.

v2 API introduced perf_dlfilter_fns.al_cleanup() to prevent that.

For the v0 API, avoid the leak by exiting the addr_location immediately,
since the documentation makes it clear that pointers obtained via
perf_dlfilter_fns are not necessarily valid (dereferenceable) after
'filter_event' and 'filter_event_early' return.

Reported-by: kernel test robot <oliver.sang@intel.com>
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Closes: https://lore.kernel.org/oe-lkp/202308232146.94d82cb4-oliver.sang@intel.com
Link: http://lore.kernel.org/lkml/20230830090539.68206-1-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/dlfilter.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/perf/util/dlfilter.c b/tools/perf/util/dlfilter.c
index e0f822ebb9b9..1dbf27822ee2 100644
--- a/tools/perf/util/dlfilter.c
+++ b/tools/perf/util/dlfilter.c
@@ -187,6 +187,8 @@ static __s32 dlfilter__resolve_address(void *ctx, __u64 address, struct perf_dlf
 
 	if (has_priv(d_al_p))
 		d_al_p->priv = memdup(&al, sizeof(al));
+	else /* Avoid leak for v0 API */
+		addr_location__exit(&al);
 
 	return 0;
 }

From bdc60129915fb4ff7832f4833512779c6a94eb5f Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 30 Aug 2023 10:55:43 -0700
Subject: [PATCH 0825/1189] perf vendor events intel: Fix modifier in
 tma_info_system_mem_parallel_reads for skylake

The metric is using the wrong format encoding. This fix is in the
converter script PR: https://github.com/intel/perfmon/pull/101

Committer testing:

Tested on a Lenovo t480s, before 'perf test 100' was failing with:

 # perf test 100
  100: perf all metrics test                                           : FAILED!

With 'perf test -vv 100' we can see:

<SNIP>
  Testing MemoryBW
  Not grouping metric tma_fb_full's events.
  Try disabling the NMI watchdog to comply NO_NMI_WATCHDOG metric constraint:
      echo 0 > /proc/sys/kernel/nmi_watchdog
      perf stat ...
      echo 1 > /proc/sys/kernel/nmi_watchdog
  event syntax error: '...DATA_READ/thresh=1,metric-id=UNC_ARB_TRK_OCCUPANCY.DATA_READ!3thresh!21!3/,UNC_ARB_TRK_OCCUPANCY.DATA_READ/metric-id=UNC_ARB_TRK_OCCUPANCY.DATA_READ/}:W,duration_time'
                                    \___ Bad event or PMU

  Unable to find PMU or event on a PMU of 'UNC_ARB_TRK_OCCUPANCY.DATA_READ'
<SNIP>

With the patch this problem is gone.

Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Samantha Alt <samantha.alt@intel.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Link: https://lore.kernel.org/r/20230830175543.1911892-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
index 94cb38540b5a..2795a404bb58 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
@@ -923,7 +923,7 @@
     },
     {
         "BriefDescription": "Average number of parallel data read requests to external memory",
-        "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.DATA_READ / UNC_ARB_TRK_OCCUPANCY.DATA_READ@thresh\\=1@",
+        "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.DATA_READ / UNC_ARB_TRK_OCCUPANCY.DATA_READ@cmask\\=1@",
         "MetricGroup": "Mem;MemoryBW;SoC",
         "MetricName": "tma_info_system_mem_parallel_reads",
         "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches"

From efc0b0bcffcba60d9c6301063d25a22a4744b499 Mon Sep 17 00:00:00 2001
From: Katya Orlova <e.orlova@ispras.ru>
Date: Tue, 15 Aug 2023 16:38:31 +0300
Subject: [PATCH 0826/1189] smb: propagate error code of extract_sharename()

In addition to the EINVAL, there may be an ENOMEM.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Fixes: 70431bfd825d ("cifs: Support fscache indexing rewrite")
Signed-off-by: Katya Orlova <e.orlova@ispras.ru>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/fscache.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/smb/client/fscache.c b/fs/smb/client/fscache.c
index 3677525ee993..e5cad149f5a2 100644
--- a/fs/smb/client/fscache.c
+++ b/fs/smb/client/fscache.c
@@ -48,7 +48,7 @@ int cifs_fscache_get_super_cookie(struct cifs_tcon *tcon)
 	sharename = extract_sharename(tcon->tree_name);
 	if (IS_ERR(sharename)) {
 		cifs_dbg(FYI, "%s: couldn't extract sharename\n", __func__);
-		return -EINVAL;
+		return PTR_ERR(sharename);
 	}
 
 	slen = strlen(sharename);

From 8c21ab1bae945686c602c5bfa4e3f3352c2452c5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 29 Aug 2023 12:35:41 +0000
Subject: [PATCH 0827/1189] net/sched: fq_pie: avoid stalls in fq_pie_timer()

When setting a high number of flows (limit being 65536),
fq_pie_timer() is currently using too much time as syzbot reported.

Add logic to yield the cpu every 2048 flows (less than 150 usec
on debug kernels).
It should also help by not blocking qdisc fast paths for too long.
Worst case (65536 flows) would need 31 jiffies for a complete scan.

Relevant extract from syzbot report:

rcu: INFO: rcu_preempt detected expedited stalls on CPUs/tasks: { 0-.... } 2663 jiffies s: 873 root: 0x1/.
rcu: blocking rcu_node structures (internal RCU debug):
Sending NMI from CPU 1 to CPUs 0:
NMI backtrace for cpu 0
CPU: 0 PID: 5177 Comm: syz-executor273 Not tainted 6.5.0-syzkaller-00453-g727dbda16b83 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/26/2023
RIP: 0010:check_kcov_mode kernel/kcov.c:173 [inline]
RIP: 0010:write_comp_data+0x21/0x90 kernel/kcov.c:236
Code: 2e 0f 1f 84 00 00 00 00 00 65 8b 05 01 b2 7d 7e 49 89 f1 89 c6 49 89 d2 81 e6 00 01 00 00 49 89 f8 65 48 8b 14 25 80 b9 03 00 <a9> 00 01 ff 00 74 0e 85 f6 74 59 8b 82 04 16 00 00 85 c0 74 4f 8b
RSP: 0018:ffffc90000007bb8 EFLAGS: 00000206
RAX: 0000000000000101 RBX: ffffc9000dc0d140 RCX: ffffffff885893b0
RDX: ffff88807c075940 RSI: 0000000000000100 RDI: 0000000000000001
RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: ffffc9000dc0d178
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
FS:  0000555555d54380(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f6b442f6130 CR3: 000000006fe1c000 CR4: 00000000003506f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <NMI>
 </NMI>
 <IRQ>
 pie_calculate_probability+0x480/0x850 net/sched/sch_pie.c:415
 fq_pie_timer+0x1da/0x4f0 net/sched/sch_fq_pie.c:387
 call_timer_fn+0x1a0/0x580 kernel/time/timer.c:1700

Fixes: ec97ecf1ebe4 ("net: sched: add Flow Queue PIE packet scheduler")
Link: https://lore.kernel.org/lkml/00000000000017ad3f06040bf394@google.com/
Reported-by: syzbot+e46fbd5289363464bc13@syzkaller.appspotmail.com
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://lore.kernel.org/r/20230829123541.3745013-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/sched/sch_fq_pie.c | 27 +++++++++++++++++++--------
 1 file changed, 19 insertions(+), 8 deletions(-)

diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c
index 591d87d5e5c0..68e6acd0f130 100644
--- a/net/sched/sch_fq_pie.c
+++ b/net/sched/sch_fq_pie.c
@@ -61,6 +61,7 @@ struct fq_pie_sched_data {
 	struct pie_params p_params;
 	u32 ecn_prob;
 	u32 flows_cnt;
+	u32 flows_cursor;
 	u32 quantum;
 	u32 memory_limit;
 	u32 new_flow_count;
@@ -375,22 +376,32 @@ flow_error:
 static void fq_pie_timer(struct timer_list *t)
 {
 	struct fq_pie_sched_data *q = from_timer(q, t, adapt_timer);
+	unsigned long next, tupdate;
 	struct Qdisc *sch = q->sch;
 	spinlock_t *root_lock; /* to lock qdisc for probability calculations */
-	u32 idx;
+	int max_cnt, i;
 
 	rcu_read_lock();
 	root_lock = qdisc_lock(qdisc_root_sleeping(sch));
 	spin_lock(root_lock);
 
-	for (idx = 0; idx < q->flows_cnt; idx++)
-		pie_calculate_probability(&q->p_params, &q->flows[idx].vars,
-					  q->flows[idx].backlog);
-
-	/* reset the timer to fire after 'tupdate' jiffies. */
-	if (q->p_params.tupdate)
-		mod_timer(&q->adapt_timer, jiffies + q->p_params.tupdate);
+	/* Limit this expensive loop to 2048 flows per round. */
+	max_cnt = min_t(int, q->flows_cnt - q->flows_cursor, 2048);
+	for (i = 0; i < max_cnt; i++) {
+		pie_calculate_probability(&q->p_params,
+					  &q->flows[q->flows_cursor].vars,
+					  q->flows[q->flows_cursor].backlog);
+		q->flows_cursor++;
+	}
 
+	tupdate = q->p_params.tupdate;
+	next = 0;
+	if (q->flows_cursor >= q->flows_cnt) {
+		q->flows_cursor = 0;
+		next = tupdate;
+	}
+	if (tupdate)
+		mod_timer(&q->adapt_timer, jiffies + next);
 	spin_unlock(root_lock);
 	rcu_read_unlock();
 }

From dc9511dd6f37fe803f6b15b61b030728d7057417 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 30 Aug 2023 09:45:19 +0000
Subject: [PATCH 0828/1189] sctp: annotate data-races around sk->sk_wmem_queued

sk->sk_wmem_queued can be read locklessly from sctp_poll()

Use sk_wmem_queued_add() when the field is changed,
and add READ_ONCE() annotations in sctp_writeable()
and sctp_assocs_seq_show()

syzbot reported:

BUG: KCSAN: data-race in sctp_poll / sctp_wfree

read-write to 0xffff888149d77810 of 4 bytes by interrupt on cpu 0:
sctp_wfree+0x170/0x4a0 net/sctp/socket.c:9147
skb_release_head_state+0xb7/0x1a0 net/core/skbuff.c:988
skb_release_all net/core/skbuff.c:1000 [inline]
__kfree_skb+0x16/0x140 net/core/skbuff.c:1016
consume_skb+0x57/0x180 net/core/skbuff.c:1232
sctp_chunk_destroy net/sctp/sm_make_chunk.c:1503 [inline]
sctp_chunk_put+0xcd/0x130 net/sctp/sm_make_chunk.c:1530
sctp_datamsg_put+0x29a/0x300 net/sctp/chunk.c:128
sctp_chunk_free+0x34/0x50 net/sctp/sm_make_chunk.c:1515
sctp_outq_sack+0xafa/0xd70 net/sctp/outqueue.c:1381
sctp_cmd_process_sack net/sctp/sm_sideeffect.c:834 [inline]
sctp_cmd_interpreter net/sctp/sm_sideeffect.c:1366 [inline]
sctp_side_effects net/sctp/sm_sideeffect.c:1198 [inline]
sctp_do_sm+0x12c7/0x31b0 net/sctp/sm_sideeffect.c:1169
sctp_assoc_bh_rcv+0x2b2/0x430 net/sctp/associola.c:1051
sctp_inq_push+0x108/0x120 net/sctp/inqueue.c:80
sctp_rcv+0x116e/0x1340 net/sctp/input.c:243
sctp6_rcv+0x25/0x40 net/sctp/ipv6.c:1120
ip6_protocol_deliver_rcu+0x92f/0xf30 net/ipv6/ip6_input.c:437
ip6_input_finish net/ipv6/ip6_input.c:482 [inline]
NF_HOOK include/linux/netfilter.h:303 [inline]
ip6_input+0xbd/0x1b0 net/ipv6/ip6_input.c:491
dst_input include/net/dst.h:468 [inline]
ip6_rcv_finish+0x1e2/0x2e0 net/ipv6/ip6_input.c:79
NF_HOOK include/linux/netfilter.h:303 [inline]
ipv6_rcv+0x74/0x150 net/ipv6/ip6_input.c:309
__netif_receive_skb_one_core net/core/dev.c:5452 [inline]
__netif_receive_skb+0x90/0x1b0 net/core/dev.c:5566
process_backlog+0x21f/0x380 net/core/dev.c:5894
__napi_poll+0x60/0x3b0 net/core/dev.c:6460
napi_poll net/core/dev.c:6527 [inline]
net_rx_action+0x32b/0x750 net/core/dev.c:6660
__do_softirq+0xc1/0x265 kernel/softirq.c:553
run_ksoftirqd+0x17/0x20 kernel/softirq.c:921
smpboot_thread_fn+0x30a/0x4a0 kernel/smpboot.c:164
kthread+0x1d7/0x210 kernel/kthread.c:389
ret_from_fork+0x2e/0x40 arch/x86/kernel/process.c:145
ret_from_fork_asm+0x11/0x20 arch/x86/entry/entry_64.S:304

read to 0xffff888149d77810 of 4 bytes by task 17828 on cpu 1:
sctp_writeable net/sctp/socket.c:9304 [inline]
sctp_poll+0x265/0x410 net/sctp/socket.c:8671
sock_poll+0x253/0x270 net/socket.c:1374
vfs_poll include/linux/poll.h:88 [inline]
do_pollfd fs/select.c:873 [inline]
do_poll fs/select.c:921 [inline]
do_sys_poll+0x636/0xc00 fs/select.c:1015
__do_sys_ppoll fs/select.c:1121 [inline]
__se_sys_ppoll+0x1af/0x1f0 fs/select.c:1101
__x64_sys_ppoll+0x67/0x80 fs/select.c:1101
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd

value changed: 0x00019e80 -> 0x0000cc80

Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 17828 Comm: syz-executor.1 Not tainted 6.5.0-rc7-syzkaller-00185-g28f20a19294d #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/26/2023

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Xin Long <lucien.xin@gmail.com>
Link: https://lore.kernel.org/r/20230830094519.950007-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/sctp/proc.c   |  2 +-
 net/sctp/socket.c | 10 +++++-----
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/sctp/proc.c b/net/sctp/proc.c
index f13d6a34f32f..ec00ee75d59a 100644
--- a/net/sctp/proc.c
+++ b/net/sctp/proc.c
@@ -282,7 +282,7 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v)
 		assoc->init_retries, assoc->shutdown_retries,
 		assoc->rtx_data_chunks,
 		refcount_read(&sk->sk_wmem_alloc),
-		sk->sk_wmem_queued,
+		READ_ONCE(sk->sk_wmem_queued),
 		sk->sk_sndbuf,
 		sk->sk_rcvbuf);
 	seq_printf(seq, "\n");
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index fd0631e70d46..ab943e8fb1db 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -69,7 +69,7 @@
 #include <net/sctp/stream_sched.h>
 
 /* Forward declarations for internal helper functions. */
-static bool sctp_writeable(struct sock *sk);
+static bool sctp_writeable(const struct sock *sk);
 static void sctp_wfree(struct sk_buff *skb);
 static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
 				size_t msg_len);
@@ -140,7 +140,7 @@ static inline void sctp_set_owner_w(struct sctp_chunk *chunk)
 
 	refcount_add(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc);
 	asoc->sndbuf_used += chunk->skb->truesize + sizeof(struct sctp_chunk);
-	sk->sk_wmem_queued += chunk->skb->truesize + sizeof(struct sctp_chunk);
+	sk_wmem_queued_add(sk, chunk->skb->truesize + sizeof(struct sctp_chunk));
 	sk_mem_charge(sk, chunk->skb->truesize);
 }
 
@@ -9144,7 +9144,7 @@ static void sctp_wfree(struct sk_buff *skb)
 	struct sock *sk = asoc->base.sk;
 
 	sk_mem_uncharge(sk, skb->truesize);
-	sk->sk_wmem_queued -= skb->truesize + sizeof(struct sctp_chunk);
+	sk_wmem_queued_add(sk, -(skb->truesize + sizeof(struct sctp_chunk)));
 	asoc->sndbuf_used -= skb->truesize + sizeof(struct sctp_chunk);
 	WARN_ON(refcount_sub_and_test(sizeof(struct sctp_chunk),
 				      &sk->sk_wmem_alloc));
@@ -9299,9 +9299,9 @@ void sctp_write_space(struct sock *sk)
  * UDP-style sockets or TCP-style sockets, this code should work.
  *  - Daisy
  */
-static bool sctp_writeable(struct sock *sk)
+static bool sctp_writeable(const struct sock *sk)
 {
-	return sk->sk_sndbuf > sk->sk_wmem_queued;
+	return READ_ONCE(sk->sk_sndbuf) > READ_ONCE(sk->sk_wmem_queued);
 }
 
 /* Wait for an association to go into ESTABLISHED state. If timeout is 0,

From fce92af1c29d90184dfec638b5738831097d66e9 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 30 Aug 2023 09:55:20 +0000
Subject: [PATCH 0829/1189] ipv4: annotate data-races around fi->fib_dead

syzbot complained about a data-race in fib_table_lookup() [1]

Add appropriate annotations to document it.

[1]
BUG: KCSAN: data-race in fib_release_info / fib_table_lookup

write to 0xffff888150f31744 of 1 bytes by task 1189 on cpu 0:
fib_release_info+0x3a0/0x460 net/ipv4/fib_semantics.c:281
fib_table_delete+0x8d2/0x900 net/ipv4/fib_trie.c:1777
fib_magic+0x1c1/0x1f0 net/ipv4/fib_frontend.c:1106
fib_del_ifaddr+0x8cf/0xa60 net/ipv4/fib_frontend.c:1317
fib_inetaddr_event+0x77/0x200 net/ipv4/fib_frontend.c:1448
notifier_call_chain kernel/notifier.c:93 [inline]
blocking_notifier_call_chain+0x90/0x200 kernel/notifier.c:388
__inet_del_ifa+0x4df/0x800 net/ipv4/devinet.c:432
inet_del_ifa net/ipv4/devinet.c:469 [inline]
inetdev_destroy net/ipv4/devinet.c:322 [inline]
inetdev_event+0x553/0xaf0 net/ipv4/devinet.c:1606
notifier_call_chain kernel/notifier.c:93 [inline]
raw_notifier_call_chain+0x6b/0x1c0 kernel/notifier.c:461
call_netdevice_notifiers_info net/core/dev.c:1962 [inline]
call_netdevice_notifiers_mtu+0xd2/0x130 net/core/dev.c:2037
dev_set_mtu_ext+0x30b/0x3e0 net/core/dev.c:8673
do_setlink+0x5be/0x2430 net/core/rtnetlink.c:2837
rtnl_setlink+0x255/0x300 net/core/rtnetlink.c:3177
rtnetlink_rcv_msg+0x807/0x8c0 net/core/rtnetlink.c:6445
netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2549
rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6463
netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline]
netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365
netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1914
sock_sendmsg_nosec net/socket.c:725 [inline]
sock_sendmsg net/socket.c:748 [inline]
sock_write_iter+0x1aa/0x230 net/socket.c:1129
do_iter_write+0x4b4/0x7b0 fs/read_write.c:860
vfs_writev+0x1a8/0x320 fs/read_write.c:933
do_writev+0xf8/0x220 fs/read_write.c:976
__do_sys_writev fs/read_write.c:1049 [inline]
__se_sys_writev fs/read_write.c:1046 [inline]
__x64_sys_writev+0x45/0x50 fs/read_write.c:1046
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd

read to 0xffff888150f31744 of 1 bytes by task 21839 on cpu 1:
fib_table_lookup+0x2bf/0xd50 net/ipv4/fib_trie.c:1585
fib_lookup include/net/ip_fib.h:383 [inline]
ip_route_output_key_hash_rcu+0x38c/0x12c0 net/ipv4/route.c:2751
ip_route_output_key_hash net/ipv4/route.c:2641 [inline]
__ip_route_output_key include/net/route.h:134 [inline]
ip_route_output_flow+0xa6/0x150 net/ipv4/route.c:2869
send4+0x1e7/0x500 drivers/net/wireguard/socket.c:61
wg_socket_send_skb_to_peer+0x94/0x130 drivers/net/wireguard/socket.c:175
wg_socket_send_buffer_to_peer+0xd6/0x100 drivers/net/wireguard/socket.c:200
wg_packet_send_handshake_initiation drivers/net/wireguard/send.c:40 [inline]
wg_packet_handshake_send_worker+0x10c/0x150 drivers/net/wireguard/send.c:51
process_one_work+0x434/0x860 kernel/workqueue.c:2600
worker_thread+0x5f2/0xa10 kernel/workqueue.c:2751
kthread+0x1d7/0x210 kernel/kthread.c:389
ret_from_fork+0x2e/0x40 arch/x86/kernel/process.c:145
ret_from_fork_asm+0x11/0x20 arch/x86/entry/entry_64.S:304

value changed: 0x00 -> 0x01

Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 21839 Comm: kworker/u4:18 Tainted: G W 6.5.0-syzkaller #0

Fixes: dccd9ecc3744 ("ipv4: Do not use dead fib_info entries.")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20230830095520.1046984-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv4/fib_semantics.c | 5 ++++-
 net/ipv4/fib_trie.c      | 3 ++-
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 65ba18a91865..eafa4a033515 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -278,7 +278,8 @@ void fib_release_info(struct fib_info *fi)
 				hlist_del(&nexthop_nh->nh_hash);
 			} endfor_nexthops(fi)
 		}
-		fi->fib_dead = 1;
+		/* Paired with READ_ONCE() from fib_table_lookup() */
+		WRITE_ONCE(fi->fib_dead, 1);
 		fib_info_put(fi);
 	}
 	spin_unlock_bh(&fib_info_lock);
@@ -1581,6 +1582,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 link_it:
 	ofi = fib_find_info(fi);
 	if (ofi) {
+		/* fib_table_lookup() should not see @fi yet. */
 		fi->fib_dead = 1;
 		free_fib_info(fi);
 		refcount_inc(&ofi->fib_treeref);
@@ -1619,6 +1621,7 @@ err_inval:
 
 failure:
 	if (fi) {
+		/* fib_table_lookup() should not see @fi yet. */
 		fi->fib_dead = 1;
 		free_fib_info(fi);
 	}
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 74d403dbd2b4..d13fb9e76b97 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1582,7 +1582,8 @@ found:
 		if (fa->fa_dscp &&
 		    inet_dscp_to_dsfield(fa->fa_dscp) != flp->flowi4_tos)
 			continue;
-		if (fi->fib_dead)
+		/* Paired with WRITE_ONCE() in fib_release_info() */
+		if (READ_ONCE(fi->fib_dead))
 			continue;
 		if (fa->fa_info->fib_scope < flp->flowi4_scope)
 			continue;

From a3e0fdf71bbe031de845e8e08ed7fba49f9c702c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 30 Aug 2023 10:12:44 +0000
Subject: [PATCH 0830/1189] net: read sk->sk_family once in sk_mc_loop()

syzbot is playing with IPV6_ADDRFORM quite a lot these days,
and managed to hit the WARN_ON_ONCE(1) in sk_mc_loop()

We have many more similar issues to fix.

WARNING: CPU: 1 PID: 1593 at net/core/sock.c:782 sk_mc_loop+0x165/0x260
Modules linked in:
CPU: 1 PID: 1593 Comm: kworker/1:3 Not tainted 6.1.40-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/26/2023
Workqueue: events_power_efficient gc_worker
RIP: 0010:sk_mc_loop+0x165/0x260 net/core/sock.c:782
Code: 34 1b fd 49 81 c7 18 05 00 00 4c 89 f8 48 c1 e8 03 42 80 3c 20 00 74 08 4c 89 ff e8 25 36 6d fd 4d 8b 37 eb 13 e8 db 33 1b fd <0f> 0b b3 01 eb 34 e8 d0 33 1b fd 45 31 f6 49 83 c6 38 4c 89 f0 48
RSP: 0018:ffffc90000388530 EFLAGS: 00010246
RAX: ffffffff846d9b55 RBX: 0000000000000011 RCX: ffff88814f884980
RDX: 0000000000000102 RSI: ffffffff87ae5160 RDI: 0000000000000011
RBP: ffffc90000388550 R08: 0000000000000003 R09: ffffffff846d9a65
R10: 0000000000000002 R11: ffff88814f884980 R12: dffffc0000000000
R13: ffff88810dbee000 R14: 0000000000000010 R15: ffff888150084000
FS: 0000000000000000(0000) GS:ffff8881f6b00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000020000180 CR3: 000000014ee5b000 CR4: 00000000003506e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
<IRQ>
[<ffffffff8507734f>] ip6_finish_output2+0x33f/0x1ae0 net/ipv6/ip6_output.c:83
[<ffffffff85062766>] __ip6_finish_output net/ipv6/ip6_output.c:200 [inline]
[<ffffffff85062766>] ip6_finish_output+0x6c6/0xb10 net/ipv6/ip6_output.c:211
[<ffffffff85061f8c>] NF_HOOK_COND include/linux/netfilter.h:298 [inline]
[<ffffffff85061f8c>] ip6_output+0x2bc/0x3d0 net/ipv6/ip6_output.c:232
[<ffffffff852071cf>] dst_output include/net/dst.h:444 [inline]
[<ffffffff852071cf>] ip6_local_out+0x10f/0x140 net/ipv6/output_core.c:161
[<ffffffff83618fb4>] ipvlan_process_v6_outbound drivers/net/ipvlan/ipvlan_core.c:483 [inline]
[<ffffffff83618fb4>] ipvlan_process_outbound drivers/net/ipvlan/ipvlan_core.c:529 [inline]
[<ffffffff83618fb4>] ipvlan_xmit_mode_l3 drivers/net/ipvlan/ipvlan_core.c:602 [inline]
[<ffffffff83618fb4>] ipvlan_queue_xmit+0x1174/0x1be0 drivers/net/ipvlan/ipvlan_core.c:677
[<ffffffff8361ddd9>] ipvlan_start_xmit+0x49/0x100 drivers/net/ipvlan/ipvlan_main.c:229
[<ffffffff84763fc0>] netdev_start_xmit include/linux/netdevice.h:4925 [inline]
[<ffffffff84763fc0>] xmit_one net/core/dev.c:3644 [inline]
[<ffffffff84763fc0>] dev_hard_start_xmit+0x320/0x980 net/core/dev.c:3660
[<ffffffff8494c650>] sch_direct_xmit+0x2a0/0x9c0 net/sched/sch_generic.c:342
[<ffffffff8494d883>] qdisc_restart net/sched/sch_generic.c:407 [inline]
[<ffffffff8494d883>] __qdisc_run+0xb13/0x1e70 net/sched/sch_generic.c:415
[<ffffffff8478c426>] qdisc_run+0xd6/0x260 include/net/pkt_sched.h:125
[<ffffffff84796eac>] net_tx_action+0x7ac/0x940 net/core/dev.c:5247
[<ffffffff858002bd>] __do_softirq+0x2bd/0x9bd kernel/softirq.c:599
[<ffffffff814c3fe8>] invoke_softirq kernel/softirq.c:430 [inline]
[<ffffffff814c3fe8>] __irq_exit_rcu+0xc8/0x170 kernel/softirq.c:683
[<ffffffff814c3f09>] irq_exit_rcu+0x9/0x20 kernel/softirq.c:695

Fixes: 7ad6848c7e81 ("ip: fix mc_loop checks for tunnels with multicast outer addresses")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20230830101244.1146934-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/sock.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index 666a17cab4f5..b0dd501dabd6 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -765,7 +765,8 @@ bool sk_mc_loop(struct sock *sk)
 		return false;
 	if (!sk)
 		return true;
-	switch (sk->sk_family) {
+	/* IPV6_ADDRFORM can change sk->sk_family under us. */
+	switch (READ_ONCE(sk->sk_family)) {
 	case AF_INET:
 		return inet_test_bit(MC_LOOP, sk);
 #if IS_ENABLED(CONFIG_IPV6)

From 8aae7625ff3f0bd5484d01f1b8d5af82e44bec2d Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 30 Aug 2023 13:00:37 +0200
Subject: [PATCH 0831/1189] net: fib: avoid warn splat in flow dissector

New skbs allocated via nf_send_reset() have skb->dev == NULL.

fib*_rules_early_flow_dissect helpers already have a 'struct net'
argument but its not passed down to the flow dissector core, which
will then WARN as it can't derive a net namespace to use:

 WARNING: CPU: 0 PID: 0 at net/core/flow_dissector.c:1016 __skb_flow_dissect+0xa91/0x1cd0
 [..]
  ip_route_me_harder+0x143/0x330
  nf_send_reset+0x17c/0x2d0 [nf_reject_ipv4]
  nft_reject_inet_eval+0xa9/0xf2 [nft_reject_inet]
  nft_do_chain+0x198/0x5d0 [nf_tables]
  nft_do_chain_inet+0xa4/0x110 [nf_tables]
  nf_hook_slow+0x41/0xc0
  ip_local_deliver+0xce/0x110
  ..

Cc: Stanislav Fomichev <sdf@google.com>
Cc: David Ahern <dsahern@kernel.org>
Cc: Ido Schimmel <idosch@nvidia.com>
Fixes: 812fa71f0d96 ("netfilter: Dissect flow after packet mangling")
Link: https://bugzilla.kernel.org/show_bug.cgi?id=217826
Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20230830110043.30497-1-fw@strlen.de
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/ip6_fib.h | 5 ++++-
 include/net/ip_fib.h  | 5 ++++-
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index c9ff23cf313e..1ba9f4ddf2f6 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -642,7 +642,10 @@ static inline bool fib6_rules_early_flow_dissect(struct net *net,
 	if (!net->ipv6.fib6_rules_require_fldissect)
 		return false;
 
-	skb_flow_dissect_flow_keys(skb, flkeys, flag);
+	memset(flkeys, 0, sizeof(*flkeys));
+	__skb_flow_dissect(net, skb, &flow_keys_dissector,
+			   flkeys, NULL, 0, 0, 0, flag);
+
 	fl6->fl6_sport = flkeys->ports.src;
 	fl6->fl6_dport = flkeys->ports.dst;
 	fl6->flowi6_proto = flkeys->basic.ip_proto;
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index a378eff827c7..f0c13864180e 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -418,7 +418,10 @@ static inline bool fib4_rules_early_flow_dissect(struct net *net,
 	if (!net->ipv4.fib_rules_require_fldissect)
 		return false;
 
-	skb_flow_dissect_flow_keys(skb, flkeys, flag);
+	memset(flkeys, 0, sizeof(*flkeys));
+	__skb_flow_dissect(net, skb, &flow_keys_dissector,
+			   flkeys, NULL, 0, 0, 0, flag);
+
 	fl4->fl4_sport = flkeys->ports.src;
 	fl4->fl4_dport = flkeys->ports.dst;
 	fl4->flowi4_proto = flkeys->basic.ip_proto;

From 3e019d8a05a38abb5c85d4f1e85fda964610aa14 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Thu, 31 Aug 2023 12:01:17 +0200
Subject: [PATCH 0832/1189] xsk: Fix xsk_diag use-after-free error during
 socket cleanup

Fix a use-after-free error that is possible if the xsk_diag interface
is used after the socket has been unbound from the device. This can
happen either due to the socket being closed or the device
disappearing. In the early days of AF_XDP, the way we tested that a
socket was not bound to a device was to simply check if the netdevice
pointer in the xsk socket structure was NULL. Later, a better system
was introduced by having an explicit state variable in the xsk socket
struct. For example, the state of a socket that is on the way to being
closed and has been unbound from the device is XSK_UNBOUND.

The commit in the Fixes tag below deleted the old way of signalling
that a socket is unbound, setting dev to NULL. This in the belief that
all code using the old way had been exterminated. That was
unfortunately not true as the xsk diagnostics code was still using the
old way and thus does not work as intended when a socket is going
down. Fix this by introducing a test against the state variable. If
the socket is in the state XSK_UNBOUND, simply abort the diagnostic's
netlink operation.

Fixes: 18b1ab7aa76b ("xsk: Fix race at socket teardown")
Reported-by: syzbot+822d1359297e2694f873@syzkaller.appspotmail.com
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: syzbot+822d1359297e2694f873@syzkaller.appspotmail.com
Tested-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20230831100119.17408-1-magnus.karlsson@gmail.com
---
 net/xdp/xsk_diag.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/xdp/xsk_diag.c b/net/xdp/xsk_diag.c
index c014217f5fa7..22b36c8143cf 100644
--- a/net/xdp/xsk_diag.c
+++ b/net/xdp/xsk_diag.c
@@ -111,6 +111,9 @@ static int xsk_diag_fill(struct sock *sk, struct sk_buff *nlskb,
 	sock_diag_save_cookie(sk, msg->xdiag_cookie);
 
 	mutex_lock(&xs->mutex);
+	if (READ_ONCE(xs->state) == XSK_UNBOUND)
+		goto out_nlmsg_trim;
+
 	if ((req->xdiag_show & XDP_SHOW_INFO) && xsk_diag_put_info(xs, nlskb))
 		goto out_nlmsg_trim;
 

From 121fd33bf2d99007f8fe2a155c291a30baca3f52 Mon Sep 17 00:00:00 2001
From: Vishal Chourasia <vishalc@linux.ibm.com>
Date: Tue, 29 Aug 2023 13:19:31 +0530
Subject: [PATCH 0833/1189] bpf, docs: Fix invalid escape sequence warnings in
 bpf_doc.py

The script bpf_doc.py generates multiple SyntaxWarnings related to invalid
escape sequences when executed with Python 3.12. These warnings do not appear
in Python 3.10 and 3.11 and do not affect the kernel build, which completes
successfully.

This patch resolves these SyntaxWarnings by converting the relevant string
literals to raw strings or by escaping backslashes. This ensures that
backslashes are interpreted as literal characters, eliminating the warnings.

Reported-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Vishal Chourasia <vishalc@linux.ibm.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Quentin Monnet <quentin@isovalent.com>
Link: https://lore.kernel.org/bpf/20230829074931.2511204-1-vishalc@linux.ibm.com
---
 scripts/bpf_doc.py | 56 +++++++++++++++++++++++-----------------------
 1 file changed, 28 insertions(+), 28 deletions(-)

diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py
index eaae2ce78381..61b7dddedc46 100755
--- a/scripts/bpf_doc.py
+++ b/scripts/bpf_doc.py
@@ -59,9 +59,9 @@ class Helper(APIElement):
         Break down helper function protocol into smaller chunks: return type,
         name, distincts arguments.
         """
-        arg_re = re.compile('((\w+ )*?(\w+|...))( (\**)(\w+))?$')
+        arg_re = re.compile(r'((\w+ )*?(\w+|...))( (\**)(\w+))?$')
         res = {}
-        proto_re = re.compile('(.+) (\**)(\w+)\(((([^,]+)(, )?){1,5})\)$')
+        proto_re = re.compile(r'(.+) (\**)(\w+)\(((([^,]+)(, )?){1,5})\)$')
 
         capture = proto_re.match(self.proto)
         res['ret_type'] = capture.group(1)
@@ -114,11 +114,11 @@ class HeaderParser(object):
         return Helper(proto=proto, desc=desc, ret=ret)
 
     def parse_symbol(self):
-        p = re.compile(' \* ?(BPF\w+)$')
+        p = re.compile(r' \* ?(BPF\w+)$')
         capture = p.match(self.line)
         if not capture:
             raise NoSyscallCommandFound
-        end_re = re.compile(' \* ?NOTES$')
+        end_re = re.compile(r' \* ?NOTES$')
         end = end_re.match(self.line)
         if end:
             raise NoSyscallCommandFound
@@ -133,7 +133,7 @@ class HeaderParser(object):
         #   - Same as above, with "const" and/or "struct" in front of type
         #   - "..." (undefined number of arguments, for bpf_trace_printk())
         # There is at least one term ("void"), and at most five arguments.
-        p = re.compile(' \* ?((.+) \**\w+\((((const )?(struct )?(\w+|\.\.\.)( \**\w+)?)(, )?){1,5}\))$')
+        p = re.compile(r' \* ?((.+) \**\w+\((((const )?(struct )?(\w+|\.\.\.)( \**\w+)?)(, )?){1,5}\))$')
         capture = p.match(self.line)
         if not capture:
             raise NoHelperFound
@@ -141,7 +141,7 @@ class HeaderParser(object):
         return capture.group(1)
 
     def parse_desc(self, proto):
-        p = re.compile(' \* ?(?:\t| {5,8})Description$')
+        p = re.compile(r' \* ?(?:\t| {5,8})Description$')
         capture = p.match(self.line)
         if not capture:
             raise Exception("No description section found for " + proto)
@@ -154,7 +154,7 @@ class HeaderParser(object):
             if self.line == ' *\n':
                 desc += '\n'
             else:
-                p = re.compile(' \* ?(?:\t| {5,8})(?:\t| {8})(.*)')
+                p = re.compile(r' \* ?(?:\t| {5,8})(?:\t| {8})(.*)')
                 capture = p.match(self.line)
                 if capture:
                     desc_present = True
@@ -167,7 +167,7 @@ class HeaderParser(object):
         return desc
 
     def parse_ret(self, proto):
-        p = re.compile(' \* ?(?:\t| {5,8})Return$')
+        p = re.compile(r' \* ?(?:\t| {5,8})Return$')
         capture = p.match(self.line)
         if not capture:
             raise Exception("No return section found for " + proto)
@@ -180,7 +180,7 @@ class HeaderParser(object):
             if self.line == ' *\n':
                 ret += '\n'
             else:
-                p = re.compile(' \* ?(?:\t| {5,8})(?:\t| {8})(.*)')
+                p = re.compile(r' \* ?(?:\t| {5,8})(?:\t| {8})(.*)')
                 capture = p.match(self.line)
                 if capture:
                     ret_present = True
@@ -219,12 +219,12 @@ class HeaderParser(object):
         self.seek_to('enum bpf_cmd {',
                      'Could not find start of bpf_cmd enum', 0)
         # Searches for either one or more BPF\w+ enums
-        bpf_p = re.compile('\s*(BPF\w+)+')
+        bpf_p = re.compile(r'\s*(BPF\w+)+')
         # Searches for an enum entry assigned to another entry,
         # for e.g. BPF_PROG_RUN = BPF_PROG_TEST_RUN, which is
         # not documented hence should be skipped in check to
         # determine if the right number of syscalls are documented
-        assign_p = re.compile('\s*(BPF\w+)\s*=\s*(BPF\w+)')
+        assign_p = re.compile(r'\s*(BPF\w+)\s*=\s*(BPF\w+)')
         bpf_cmd_str = ''
         while True:
             capture = assign_p.match(self.line)
@@ -239,7 +239,7 @@ class HeaderParser(object):
                 break
             self.line = self.reader.readline()
         # Find the number of occurences of BPF\w+
-        self.enum_syscalls = re.findall('(BPF\w+)+', bpf_cmd_str)
+        self.enum_syscalls = re.findall(r'(BPF\w+)+', bpf_cmd_str)
 
     def parse_desc_helpers(self):
         self.seek_to(helpersDocStart,
@@ -263,7 +263,7 @@ class HeaderParser(object):
         self.seek_to('#define ___BPF_FUNC_MAPPER(FN, ctx...)',
                      'Could not find start of eBPF helper definition list')
         # Searches for one FN(\w+) define or a backslash for newline
-        p = re.compile('\s*FN\((\w+), (\d+), ##ctx\)|\\\\')
+        p = re.compile(r'\s*FN\((\w+), (\d+), ##ctx\)|\\\\')
         fn_defines_str = ''
         i = 0
         while True:
@@ -278,7 +278,7 @@ class HeaderParser(object):
                 break
             self.line = self.reader.readline()
         # Find the number of occurences of FN(\w+)
-        self.define_unique_helpers = re.findall('FN\(\w+, \d+, ##ctx\)', fn_defines_str)
+        self.define_unique_helpers = re.findall(r'FN\(\w+, \d+, ##ctx\)', fn_defines_str)
 
     def validate_helpers(self):
         last_helper = ''
@@ -425,7 +425,7 @@ class PrinterRST(Printer):
         try:
             cmd = ['git', 'log', '-1', '--pretty=format:%cs', '--no-patch',
                    '-L',
-                   '/{}/,/\*\//:include/uapi/linux/bpf.h'.format(delimiter)]
+                   '/{}/,/\\*\\//:include/uapi/linux/bpf.h'.format(delimiter)]
             date = subprocess.run(cmd, cwd=linuxRoot,
                                   capture_output=True, check=True)
             return date.stdout.decode().rstrip()
@@ -516,7 +516,7 @@ as "Dual BSD/GPL", may be used). Some helper functions are only accessible to
 programs that are compatible with the GNU Privacy License (GPL).
 
 In order to use such helpers, the eBPF program must be loaded with the correct
-license string passed (via **attr**) to the **bpf**\ () system call, and this
+license string passed (via **attr**) to the **bpf**\\ () system call, and this
 generally translates into the C source code of the program containing a line
 similar to the following:
 
@@ -550,7 +550,7 @@ may be interested in:
 * The bpftool utility can be used to probe the availability of helper functions
   on the system (as well as supported program and map types, and a number of
   other parameters). To do so, run **bpftool feature probe** (see
-  **bpftool-feature**\ (8) for details). Add the **unprivileged** keyword to
+  **bpftool-feature**\\ (8) for details). Add the **unprivileged** keyword to
   list features available to unprivileged users.
 
 Compatibility between helper functions and program types can generally be found
@@ -562,23 +562,23 @@ other functions, themselves allowing access to additional helpers. The
 requirement for GPL license is also in those **struct bpf_func_proto**.
 
 Compatibility between helper functions and map types can be found in the
-**check_map_func_compatibility**\ () function in file *kernel/bpf/verifier.c*.
+**check_map_func_compatibility**\\ () function in file *kernel/bpf/verifier.c*.
 
 Helper functions that invalidate the checks on **data** and **data_end**
 pointers for network processing are listed in function
-**bpf_helper_changes_pkt_data**\ () in file *net/core/filter.c*.
+**bpf_helper_changes_pkt_data**\\ () in file *net/core/filter.c*.
 
 SEE ALSO
 ========
 
-**bpf**\ (2),
-**bpftool**\ (8),
-**cgroups**\ (7),
-**ip**\ (8),
-**perf_event_open**\ (2),
-**sendmsg**\ (2),
-**socket**\ (7),
-**tc-bpf**\ (8)'''
+**bpf**\\ (2),
+**bpftool**\\ (8),
+**cgroups**\\ (7),
+**ip**\\ (8),
+**perf_event_open**\\ (2),
+**sendmsg**\\ (2),
+**socket**\\ (7),
+**tc-bpf**\\ (8)'''
         print(footer)
 
     def print_proto(self, helper):
@@ -598,7 +598,7 @@ SEE ALSO
             one_arg = '{}{}'.format(comma, a['type'])
             if a['name']:
                 if a['star']:
-                    one_arg += ' {}**\ '.format(a['star'].replace('*', '\\*'))
+                    one_arg += ' {}**\\ '.format(a['star'].replace('*', '\\*'))
                 else:
                     one_arg += '** '
                 one_arg += '*{}*\\ **'.format(a['name'])

From 765aa6b3a462ed69ddcb1c41a6f7f93b8abb7d43 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 30 Aug 2023 11:22:59 +0200
Subject: [PATCH 0834/1189] dma-pool: remove a __maybe_unused label in
 atomic_pool_expand

Move the #endif a line so that free_page label is only seen by the
compile pass when actually used.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Chunhui He <hchunhui@mail.ustc.edu.cn>
Reviewed-by: Robin Murphy <roin.murphy@arm.com>
---
 kernel/dma/pool.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
index 1acec2e22827..b481c48a31a6 100644
--- a/kernel/dma/pool.c
+++ b/kernel/dma/pool.c
@@ -135,9 +135,9 @@ encrypt_mapping:
 remove_mapping:
 #ifdef CONFIG_DMA_DIRECT_REMAP
 	dma_common_free_remap(addr, pool_size);
-#endif
-free_page: __maybe_unused
+free_page:
 	__free_pages(page, order);
+#endif
 out:
 	return ret;
 }

From da42bcb30e001d676a1c4cf7f26d15d775279f6c Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 31 Aug 2023 14:36:20 +0200
Subject: [PATCH 0835/1189] ALSA: hda/tas2781: Use standard clamp() macro

Instead of the home-made clamp() function, use the standard macro().

Fixes: 5be27f1e3ec9 ("ALSA: hda/tas2781: Add tas2781 HDA driver")
Link: https://lore.kernel.org/r/20230831123620.23064-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/tas2781_hda_i2c.c | 16 +++-------------
 1 file changed, 3 insertions(+), 13 deletions(-)

diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c
index 37114fd61a38..fb802802939e 100644
--- a/sound/pci/hda/tas2781_hda_i2c.c
+++ b/sound/pci/hda/tas2781_hda_i2c.c
@@ -173,16 +173,6 @@ static int tasdevice_get_profile_id(struct snd_kcontrol *kcontrol,
 	return 0;
 }
 
-static int tasdevice_hda_clamp(int val, int max)
-{
-	if (val > max)
-		val = max;
-
-	if (val < 0)
-		val = 0;
-	return val;
-}
-
 static int tasdevice_set_profile_id(struct snd_kcontrol *kcontrol,
 		struct snd_ctl_elem_value *ucontrol)
 {
@@ -191,7 +181,7 @@ static int tasdevice_set_profile_id(struct snd_kcontrol *kcontrol,
 	int max = tas_priv->rcabin.ncfgs - 1;
 	int val, ret = 0;
 
-	val = tasdevice_hda_clamp(nr_profile, max);
+	val = clamp(nr_profile, 0, max);
 
 	if (tas_priv->rcabin.profile_cfg_id != val) {
 		tas_priv->rcabin.profile_cfg_id = val;
@@ -248,7 +238,7 @@ static int tasdevice_program_put(struct snd_kcontrol *kcontrol,
 	int max = tas_fw->nr_programs - 1;
 	int val, ret = 0;
 
-	val = tasdevice_hda_clamp(nr_program, max);
+	val = clamp(nr_program, 0, max);
 
 	if (tas_priv->cur_prog != val) {
 		tas_priv->cur_prog = val;
@@ -277,7 +267,7 @@ static int tasdevice_config_put(struct snd_kcontrol *kcontrol,
 	int max = tas_fw->nr_configurations - 1;
 	int val, ret = 0;
 
-	val = tasdevice_hda_clamp(nr_config, max);
+	val = clamp(nr_config, 0, max);
 
 	if (tas_priv->cur_conf != val) {
 		tas_priv->cur_conf = val;

From 3af5ae22030cb59fab4fba35f5a2b62f47e14df9 Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Tue, 25 Jul 2023 09:44:40 +0800
Subject: [PATCH 0836/1189] ceph: make members in struct
 ceph_mds_request_args_ext a union

In ceph mainline it will allow to set the btime in the setattr request
and just add a 'btime' member in the union 'ceph_mds_request_args' and
then bump up the header version to 4. That means the total size of union
'ceph_mds_request_args' will increase sizeof(struct ceph_timespec) bytes,
but in kclient it will increase the sizeof(setattr_ext) bytes for each
request.

Since the MDS will always depend on the header's vesion and front_len
members to decode the 'ceph_mds_request_head' struct, at the same time
kclient hasn't supported the 'btime' feature yet in setattr request,
so it's safe to do this change here.

This will save 48 bytes memories for each request.

Fixes: 4f1ddb1ea874 ("ceph: implement updated ceph_mds_request_head structure")
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/ceph_fs.h | 24 +++++++++++++-----------
 1 file changed, 13 insertions(+), 11 deletions(-)

diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index 45f8ce61e103..ae44812eb6d4 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -467,17 +467,19 @@ union ceph_mds_request_args {
 } __attribute__ ((packed));
 
 union ceph_mds_request_args_ext {
-	union ceph_mds_request_args old;
-	struct {
-		__le32 mode;
-		__le32 uid;
-		__le32 gid;
-		struct ceph_timespec mtime;
-		struct ceph_timespec atime;
-		__le64 size, old_size;       /* old_size needed by truncate */
-		__le32 mask;                 /* CEPH_SETATTR_* */
-		struct ceph_timespec btime;
-	} __attribute__ ((packed)) setattr_ext;
+	union {
+		union ceph_mds_request_args old;
+		struct {
+			__le32 mode;
+			__le32 uid;
+			__le32 gid;
+			struct ceph_timespec mtime;
+			struct ceph_timespec atime;
+			__le64 size, old_size;       /* old_size needed by truncate */
+			__le32 mask;                 /* CEPH_SETATTR_* */
+			struct ceph_timespec btime;
+		} __attribute__ ((packed)) setattr_ext;
+	};
 };
 
 #define CEPH_MDS_FLAG_REPLAY		1 /* this is a replayed op */

From ce0d5bd3a6c176f9a3bf867624a07119dd4d0878 Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Tue, 25 Jul 2023 17:51:59 +0800
Subject: [PATCH 0837/1189] ceph: make num_fwd and num_retry to __u32

The num_fwd in MClientRequestForward is int32_t, while the num_fwd
in ceph_mds_request_head is __u8. This is buggy when the num_fwd
is larger than 256 it will always be truncate to 0 again. But the
client couldn't recoginize this.

This will make them to __u32 instead. Because the old cephs will
directly copy the raw memories when decoding the reqeust's head,
so we need to make sure this kclient will be compatible with old
cephs. For newer cephs they will decode the requests depending
the version, which will be much simpler and easier to extend new
members.

Link: https://tracker.ceph.com/issues/62145
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c         | 189 +++++++++++++++++++----------------
 fs/ceph/mds_client.h         |   4 +-
 include/linux/ceph/ceph_fs.h |  23 ++++-
 3 files changed, 126 insertions(+), 90 deletions(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 04a881343e43..615db141b6c4 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2840,6 +2840,18 @@ static void encode_mclientrequest_tail(void **p,
 	}
 }
 
+static struct ceph_mds_request_head_legacy *
+find_legacy_request_head(void *p, u64 features)
+{
+	bool legacy = !(features & CEPH_FEATURE_FS_BTIME);
+	struct ceph_mds_request_head_old *ohead;
+
+	if (legacy)
+		return (struct ceph_mds_request_head_legacy *)p;
+	ohead = (struct ceph_mds_request_head_old *)p;
+	return (struct ceph_mds_request_head_legacy *)&ohead->oldest_client_tid;
+}
+
 /*
  * called under mdsc->mutex
  */
@@ -2850,7 +2862,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 	int mds = session->s_mds;
 	struct ceph_mds_client *mdsc = session->s_mdsc;
 	struct ceph_msg *msg;
-	struct ceph_mds_request_head_old *head;
+	struct ceph_mds_request_head_legacy *lhead;
 	const char *path1 = NULL;
 	const char *path2 = NULL;
 	u64 ino1 = 0, ino2 = 0;
@@ -2862,6 +2874,8 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 	void *p, *end;
 	int ret;
 	bool legacy = !(session->s_con.peer_features & CEPH_FEATURE_FS_BTIME);
+	bool old_version = !test_bit(CEPHFS_FEATURE_32BITS_RETRY_FWD,
+				     &session->s_features);
 
 	ret = set_request_path_attr(req->r_inode, req->r_dentry,
 			      req->r_parent, req->r_path1, req->r_ino1.ino,
@@ -2893,7 +2907,19 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 		goto out_free2;
 	}
 
-	len = legacy ? sizeof(*head) : sizeof(struct ceph_mds_request_head);
+	/*
+	 * For old cephs without supporting the 32bit retry/fwd feature
+	 * it will copy the raw memories directly when decoding the
+	 * requests. While new cephs will decode the head depending the
+	 * version member, so we need to make sure it will be compatible
+	 * with them both.
+	 */
+	if (legacy)
+		len = sizeof(struct ceph_mds_request_head_legacy);
+	else if (old_version)
+		len = sizeof(struct ceph_mds_request_head_old);
+	else
+		len = sizeof(struct ceph_mds_request_head);
 
 	/* filepaths */
 	len += 2 * (1 + sizeof(u32) + sizeof(u64));
@@ -2938,33 +2964,40 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 
 	msg->hdr.tid = cpu_to_le64(req->r_tid);
 
+	lhead = find_legacy_request_head(msg->front.iov_base,
+					 session->s_con.peer_features);
+
 	/*
-	 * The old ceph_mds_request_head didn't contain a version field, and
+	 * The ceph_mds_request_head_legacy didn't contain a version field, and
 	 * one was added when we moved the message version from 3->4.
 	 */
 	if (legacy) {
 		msg->hdr.version = cpu_to_le16(3);
-		head = msg->front.iov_base;
-		p = msg->front.iov_base + sizeof(*head);
+		p = msg->front.iov_base + sizeof(*lhead);
+	} else if (old_version) {
+		struct ceph_mds_request_head_old *ohead = msg->front.iov_base;
+
+		msg->hdr.version = cpu_to_le16(4);
+		ohead->version = cpu_to_le16(1);
+		p = msg->front.iov_base + sizeof(*ohead);
 	} else {
-		struct ceph_mds_request_head *new_head = msg->front.iov_base;
+		struct ceph_mds_request_head *nhead = msg->front.iov_base;
 
 		msg->hdr.version = cpu_to_le16(6);
-		new_head->version = cpu_to_le16(CEPH_MDS_REQUEST_HEAD_VERSION);
-		head = (struct ceph_mds_request_head_old *)&new_head->oldest_client_tid;
-		p = msg->front.iov_base + sizeof(*new_head);
+		nhead->version = cpu_to_le16(CEPH_MDS_REQUEST_HEAD_VERSION);
+		p = msg->front.iov_base + sizeof(*nhead);
 	}
 
 	end = msg->front.iov_base + msg->front.iov_len;
 
-	head->mdsmap_epoch = cpu_to_le32(mdsc->mdsmap->m_epoch);
-	head->op = cpu_to_le32(req->r_op);
-	head->caller_uid = cpu_to_le32(from_kuid(&init_user_ns,
-						 req->r_cred->fsuid));
-	head->caller_gid = cpu_to_le32(from_kgid(&init_user_ns,
-						 req->r_cred->fsgid));
-	head->ino = cpu_to_le64(req->r_deleg_ino);
-	head->args = req->r_args;
+	lhead->mdsmap_epoch = cpu_to_le32(mdsc->mdsmap->m_epoch);
+	lhead->op = cpu_to_le32(req->r_op);
+	lhead->caller_uid = cpu_to_le32(from_kuid(&init_user_ns,
+						  req->r_cred->fsuid));
+	lhead->caller_gid = cpu_to_le32(from_kgid(&init_user_ns,
+						  req->r_cred->fsgid));
+	lhead->ino = cpu_to_le64(req->r_deleg_ino);
+	lhead->args = req->r_args;
 
 	ceph_encode_filepath(&p, end, ino1, path1);
 	ceph_encode_filepath(&p, end, ino2, path2);
@@ -3006,7 +3039,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 		p = msg->front.iov_base + req->r_request_release_offset;
 	}
 
-	head->num_releases = cpu_to_le16(releases);
+	lhead->num_releases = cpu_to_le16(releases);
 
 	encode_mclientrequest_tail(&p, req);
 
@@ -3057,18 +3090,6 @@ static void complete_request(struct ceph_mds_client *mdsc,
 	complete_all(&req->r_completion);
 }
 
-static struct ceph_mds_request_head_old *
-find_old_request_head(void *p, u64 features)
-{
-	bool legacy = !(features & CEPH_FEATURE_FS_BTIME);
-	struct ceph_mds_request_head *new_head;
-
-	if (legacy)
-		return (struct ceph_mds_request_head_old *)p;
-	new_head = (struct ceph_mds_request_head *)p;
-	return (struct ceph_mds_request_head_old *)&new_head->oldest_client_tid;
-}
-
 /*
  * called under mdsc->mutex
  */
@@ -3078,29 +3099,28 @@ static int __prepare_send_request(struct ceph_mds_session *session,
 {
 	int mds = session->s_mds;
 	struct ceph_mds_client *mdsc = session->s_mdsc;
-	struct ceph_mds_request_head_old *rhead;
+	struct ceph_mds_request_head_legacy *lhead;
+	struct ceph_mds_request_head *nhead;
 	struct ceph_msg *msg;
-	int flags = 0, max_retry;
+	int flags = 0, old_max_retry;
+	bool old_version = !test_bit(CEPHFS_FEATURE_32BITS_RETRY_FWD,
+				     &session->s_features);
 
 	/*
-	 * The type of 'r_attempts' in kernel 'ceph_mds_request'
-	 * is 'int', while in 'ceph_mds_request_head' the type of
-	 * 'num_retry' is '__u8'. So in case the request retries
-	 *  exceeding 256 times, the MDS will receive a incorrect
-	 *  retry seq.
-	 *
-	 * In this case it's ususally a bug in MDS and continue
-	 * retrying the request makes no sense.
-	 *
-	 * In future this could be fixed in ceph code, so avoid
-	 * using the hardcode here.
+	 * Avoid inifinite retrying after overflow. The client will
+	 * increase the retry count and if the MDS is old version,
+	 * so we limit to retry at most 256 times.
 	 */
-	max_retry = sizeof_field(struct ceph_mds_request_head, num_retry);
-	max_retry = 1 << (max_retry * BITS_PER_BYTE);
-	if (req->r_attempts >= max_retry) {
-		pr_warn_ratelimited("%s request tid %llu seq overflow\n",
-				    __func__, req->r_tid);
-		return -EMULTIHOP;
+	if (req->r_attempts) {
+	       old_max_retry = sizeof_field(struct ceph_mds_request_head_old,
+					    num_retry);
+	       old_max_retry = 1 << (old_max_retry * BITS_PER_BYTE);
+	       if ((old_version && req->r_attempts >= old_max_retry) ||
+		   ((uint32_t)req->r_attempts >= U32_MAX)) {
+			pr_warn_ratelimited("%s request tid %llu seq overflow\n",
+					    __func__, req->r_tid);
+			return -EMULTIHOP;
+	       }
 	}
 
 	req->r_attempts++;
@@ -3126,20 +3146,24 @@ static int __prepare_send_request(struct ceph_mds_session *session,
 		 * d_move mangles the src name.
 		 */
 		msg = req->r_request;
-		rhead = find_old_request_head(msg->front.iov_base,
-					      session->s_con.peer_features);
+		lhead = find_legacy_request_head(msg->front.iov_base,
+						 session->s_con.peer_features);
 
-		flags = le32_to_cpu(rhead->flags);
+		flags = le32_to_cpu(lhead->flags);
 		flags |= CEPH_MDS_FLAG_REPLAY;
-		rhead->flags = cpu_to_le32(flags);
+		lhead->flags = cpu_to_le32(flags);
 
 		if (req->r_target_inode)
-			rhead->ino = cpu_to_le64(ceph_ino(req->r_target_inode));
+			lhead->ino = cpu_to_le64(ceph_ino(req->r_target_inode));
 
-		rhead->num_retry = req->r_attempts - 1;
+		lhead->num_retry = req->r_attempts - 1;
+		if (!old_version) {
+			nhead = (struct ceph_mds_request_head*)msg->front.iov_base;
+			nhead->ext_num_retry = cpu_to_le32(req->r_attempts - 1);
+		}
 
 		/* remove cap/dentry releases from message */
-		rhead->num_releases = 0;
+		lhead->num_releases = 0;
 
 		p = msg->front.iov_base + req->r_request_release_offset;
 		encode_mclientrequest_tail(&p, req);
@@ -3160,18 +3184,23 @@ static int __prepare_send_request(struct ceph_mds_session *session,
 	}
 	req->r_request = msg;
 
-	rhead = find_old_request_head(msg->front.iov_base,
-				      session->s_con.peer_features);
-	rhead->oldest_client_tid = cpu_to_le64(__get_oldest_tid(mdsc));
+	lhead = find_legacy_request_head(msg->front.iov_base,
+					 session->s_con.peer_features);
+	lhead->oldest_client_tid = cpu_to_le64(__get_oldest_tid(mdsc));
 	if (test_bit(CEPH_MDS_R_GOT_UNSAFE, &req->r_req_flags))
 		flags |= CEPH_MDS_FLAG_REPLAY;
 	if (test_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags))
 		flags |= CEPH_MDS_FLAG_ASYNC;
 	if (req->r_parent)
 		flags |= CEPH_MDS_FLAG_WANT_DENTRY;
-	rhead->flags = cpu_to_le32(flags);
-	rhead->num_fwd = req->r_num_fwd;
-	rhead->num_retry = req->r_attempts - 1;
+	lhead->flags = cpu_to_le32(flags);
+	lhead->num_fwd = req->r_num_fwd;
+	lhead->num_retry = req->r_attempts - 1;
+	if (!old_version) {
+		nhead = (struct ceph_mds_request_head*)msg->front.iov_base;
+		nhead->ext_num_fwd = cpu_to_le32(req->r_num_fwd);
+		nhead->ext_num_retry = cpu_to_le32(req->r_attempts - 1);
+	}
 
 	dout(" r_parent = %p\n", req->r_parent);
 	return 0;
@@ -3830,33 +3859,21 @@ static void handle_forward(struct ceph_mds_client *mdsc,
 	if (test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags)) {
 		dout("forward tid %llu aborted, unregistering\n", tid);
 		__unregister_request(mdsc, req);
-	} else if (fwd_seq <= req->r_num_fwd) {
+	} else if (fwd_seq <= req->r_num_fwd || (uint32_t)fwd_seq >= U32_MAX) {
 		/*
-		 * The type of 'num_fwd' in ceph 'MClientRequestForward'
-		 * is 'int32_t', while in 'ceph_mds_request_head' the
-		 * type is '__u8'. So in case the request bounces between
-		 * MDSes exceeding 256 times, the client will get stuck.
+		 * Avoid inifinite retrying after overflow.
 		 *
-		 * In this case it's ususally a bug in MDS and continue
-		 * bouncing the request makes no sense.
-		 *
-		 * In future this could be fixed in ceph code, so avoid
-		 * using the hardcode here.
+		 * The MDS will increase the fwd count and in client side
+		 * if the num_fwd is less than the one saved in request
+		 * that means the MDS is an old version and overflowed of
+		 * 8 bits.
 		 */
-		int max = sizeof_field(struct ceph_mds_request_head, num_fwd);
-		max = 1 << (max * BITS_PER_BYTE);
-		if (req->r_num_fwd >= max) {
-			mutex_lock(&req->r_fill_mutex);
-			req->r_err = -EMULTIHOP;
-			set_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags);
-			mutex_unlock(&req->r_fill_mutex);
-			aborted = true;
-			pr_warn_ratelimited("forward tid %llu seq overflow\n",
-					    tid);
-		} else {
-			dout("forward tid %llu to mds%d - old seq %d <= %d\n",
-			     tid, next_mds, req->r_num_fwd, fwd_seq);
-		}
+		mutex_lock(&req->r_fill_mutex);
+		req->r_err = -EMULTIHOP;
+		set_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags);
+		mutex_unlock(&req->r_fill_mutex);
+		aborted = true;
+		pr_warn_ratelimited("forward tid %llu seq overflow\n", tid);
 	} else {
 		/* resend. forward race not possible; mds would drop */
 		dout("forward tid %llu to mds%d (we resend)\n", tid, next_mds);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 1fa0f78b7b79..5a3714bdd64a 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -32,8 +32,9 @@ enum ceph_feature_type {
 	CEPHFS_FEATURE_ALTERNATE_NAME,
 	CEPHFS_FEATURE_NOTIFY_SESSION_STATE,
 	CEPHFS_FEATURE_OP_GETVXATTR,
+	CEPHFS_FEATURE_32BITS_RETRY_FWD,
 
-	CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_OP_GETVXATTR,
+	CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_32BITS_RETRY_FWD,
 };
 
 #define CEPHFS_FEATURES_CLIENT_SUPPORTED {	\
@@ -47,6 +48,7 @@ enum ceph_feature_type {
 	CEPHFS_FEATURE_ALTERNATE_NAME,		\
 	CEPHFS_FEATURE_NOTIFY_SESSION_STATE,	\
 	CEPHFS_FEATURE_OP_GETVXATTR,		\
+	CEPHFS_FEATURE_32BITS_RETRY_FWD,	\
 }
 
 /*
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index ae44812eb6d4..5f2301ee88bc 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -486,7 +486,7 @@ union ceph_mds_request_args_ext {
 #define CEPH_MDS_FLAG_WANT_DENTRY	2 /* want dentry in reply */
 #define CEPH_MDS_FLAG_ASYNC		4 /* request is asynchronous */
 
-struct ceph_mds_request_head_old {
+struct ceph_mds_request_head_legacy {
 	__le64 oldest_client_tid;
 	__le32 mdsmap_epoch;           /* on client */
 	__le32 flags;                  /* CEPH_MDS_FLAG_* */
@@ -499,9 +499,9 @@ struct ceph_mds_request_head_old {
 	union ceph_mds_request_args args;
 } __attribute__ ((packed));
 
-#define CEPH_MDS_REQUEST_HEAD_VERSION  1
+#define CEPH_MDS_REQUEST_HEAD_VERSION  2
 
-struct ceph_mds_request_head {
+struct ceph_mds_request_head_old {
 	__le16 version;                /* struct version */
 	__le64 oldest_client_tid;
 	__le32 mdsmap_epoch;           /* on client */
@@ -515,6 +515,23 @@ struct ceph_mds_request_head {
 	union ceph_mds_request_args_ext args;
 } __attribute__ ((packed));
 
+struct ceph_mds_request_head {
+	__le16 version;                /* struct version */
+	__le64 oldest_client_tid;
+	__le32 mdsmap_epoch;           /* on client */
+	__le32 flags;                  /* CEPH_MDS_FLAG_* */
+	__u8 num_retry, num_fwd;       /* legacy count retry and fwd attempts */
+	__le16 num_releases;           /* # include cap/lease release records */
+	__le32 op;                     /* mds op code */
+	__le32 caller_uid, caller_gid;
+	__le64 ino;                    /* use this ino for openc, mkdir, mknod,
+					  etc. (if replaying) */
+	union ceph_mds_request_args_ext args;
+
+	__le32 ext_num_retry;          /* new count retry attempts */
+	__le32 ext_num_fwd;            /* new count fwd attempts */
+} __attribute__ ((packed));
+
 /* cap/lease release record */
 struct ceph_mds_request_release {
 	__le64 ino, cap_id;            /* ino and unique cap id */

From 0d997f1de89970bff4be1b6f0142c0bd036c3ee8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 31 Aug 2023 14:19:11 +0200
Subject: [PATCH 0838/1189] block: remove the call to file_remove_privs in
 blkdev_write_iter

file_remove_privs instantly returns 0 when not called for regular files,
so don't bother.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Link: https://lore.kernel.org/r/20230831121911.280155-1-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/fops.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/block/fops.c b/block/fops.c
index a24a624d3bf7..acff3d5d22d4 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -671,10 +671,6 @@ static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		iov_iter_truncate(from, size);
 	}
 
-	ret = file_remove_privs(file);
-	if (ret)
-		return ret;
-
 	ret = file_update_time(file);
 	if (ret)
 		return ret;

From 1a721de8489fa559ff4471f73c58bb74ac5580d3 Mon Sep 17 00:00:00 2001
From: Li Lingfeng <lilingfeng3@huawei.com>
Date: Thu, 31 Aug 2023 15:59:00 +0800
Subject: [PATCH 0839/1189] block: don't add or resize partition on the disk
 with GENHD_FL_NO_PART

Commit a33df75c6328 ("block: use an xarray for disk->part_tbl") remove
disk_expand_part_tbl() in add_partition(), which means all kinds of
devices will support extended dynamic `dev_t`.
However, some devices with GENHD_FL_NO_PART are not expected to add or
resize partition.
Fix this by adding check of GENHD_FL_NO_PART before add or resize
partition.

Fixes: a33df75c6328 ("block: use an xarray for disk->part_tbl")
Signed-off-by: Li Lingfeng <lilingfeng3@huawei.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20230831075900.1725842-1-lilingfeng@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/ioctl.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/block/ioctl.c b/block/ioctl.c
index 648670ddb164..d5f5cd61efd7 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -20,6 +20,8 @@ static int blkpg_do_ioctl(struct block_device *bdev,
 	struct blkpg_partition p;
 	long long start, length;
 
+	if (disk->flags & GENHD_FL_NO_PART)
+		return -EINVAL;
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
 	if (copy_from_user(&p, upart, sizeof(struct blkpg_partition)))

From 238b351d0935df568ecb3dc5aef25971778f0f7c Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Wed, 30 Aug 2023 22:48:41 -0500
Subject: [PATCH 0840/1189] smb3: allow controlling length of time directory
 entries are cached with dir leases

Currently with directory leases we cache directory contents for a fixed period
of time (default 30 seconds) but for many workloads this is too short.  Allow
configuring the maximum amount of time directory entries are cached when a
directory lease is held on that directory. Add module load parm "max_dir_cache"

For example to set the timeout to 10 minutes you would do:

  echo 600 > /sys/module/cifs/parameters/dir_cache_timeout

or to disable caching directory contents:

  echo 0 > /sys/module/cifs/parameters/dir_cache_timeout

Reviewed-by: Bharath SM <bharathsm@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cached_dir.c |  4 ++--
 fs/smb/client/cifsfs.c     | 10 ++++++++++
 fs/smb/client/cifsglob.h   |  1 +
 3 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c
index 2d5e9a9d5b8b..9d84c4a7bd0c 100644
--- a/fs/smb/client/cached_dir.c
+++ b/fs/smb/client/cached_dir.c
@@ -145,7 +145,7 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon,
 	const char *npath;
 
 	if (tcon == NULL || tcon->cfids == NULL || tcon->nohandlecache ||
-	    is_smb1_server(tcon->ses->server))
+	    is_smb1_server(tcon->ses->server) || (dir_cache_timeout == 0))
 		return -EOPNOTSUPP;
 
 	ses = tcon->ses;
@@ -582,7 +582,7 @@ cifs_cfids_laundromat_thread(void *p)
 			return 0;
 		spin_lock(&cfids->cfid_list_lock);
 		list_for_each_entry_safe(cfid, q, &cfids->entries, entry) {
-			if (time_after(jiffies, cfid->time + HZ * 30)) {
+			if (time_after(jiffies, cfid->time + HZ * dir_cache_timeout)) {
 				list_del(&cfid->entry);
 				list_add(&cfid->entry, &entry);
 				cfids->num_entries--;
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index 73c44e097a69..52612bb52bd7 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -117,6 +117,10 @@ module_param(cifs_max_pending, uint, 0444);
 MODULE_PARM_DESC(cifs_max_pending, "Simultaneous requests to server for "
 				   "CIFS/SMB1 dialect (N/A for SMB3) "
 				   "Default: 32767 Range: 2 to 32767.");
+unsigned int dir_cache_timeout = 30;
+module_param(dir_cache_timeout, uint, 0644);
+MODULE_PARM_DESC(dir_cache_timeout, "Number of seconds to cache directory contents for which we have a lease. Default: 30 "
+				 "Range: 1 to 65000 seconds, 0 to disable caching dir contents");
 #ifdef CONFIG_CIFS_STATS2
 unsigned int slow_rsp_threshold = 1;
 module_param(slow_rsp_threshold, uint, 0644);
@@ -1679,6 +1683,12 @@ init_cifs(void)
 			 CIFS_MAX_REQ);
 	}
 
+	/* Limit max to about 18 hours, and setting to zero disables directory entry caching */
+	if (dir_cache_timeout > 65000) {
+		dir_cache_timeout = 65000;
+		cifs_dbg(VFS, "dir_cache_timeout set to max of 65000 seconds\n");
+	}
+
 	cifsiod_wq = alloc_workqueue("cifsiod", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
 	if (!cifsiod_wq) {
 		rc = -ENOMEM;
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 259e231f8b4f..501426ee39e7 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -2016,6 +2016,7 @@ extern unsigned int CIFSMaxBufSize;  /* max size not including hdr */
 extern unsigned int cifs_min_rcv;    /* min size of big ntwrk buf pool */
 extern unsigned int cifs_min_small;  /* min size of small buf pool */
 extern unsigned int cifs_max_pending; /* MAX requests at once to server*/
+extern unsigned int dir_cache_timeout; /* max time for directory lease caching of dir */
 extern bool disable_legacy_dialects;  /* forbid vers=1.0 and vers=2.0 mounts */
 extern atomic_t mid_count;
 

From d11ae1b16b0a57fac524cad8e277a20ec62600d1 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 31 Aug 2023 16:11:03 +0200
Subject: [PATCH 0841/1189] selftests/bpf: Fix d_path test

Recent commit [1] broke d_path test, because now filp_close is not called
directly from sys_close, but eventually later when the file is finally
released.

As suggested by Hou Tao we don't need to re-hook the bpf program, but just
instead we can use sys_close_range to trigger filp_close synchronously.

  [1] 021a160abf62 ("fs: use __fput_sync in close(2)")

Suggested-by: Hou Tao <houtao@huaweicloud.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20230831141103.359810-1-jolsa@kernel.org
---
 .../testing/selftests/bpf/prog_tests/d_path.c | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/d_path.c b/tools/testing/selftests/bpf/prog_tests/d_path.c
index 911345c526e6..ccc768592e66 100644
--- a/tools/testing/selftests/bpf/prog_tests/d_path.c
+++ b/tools/testing/selftests/bpf/prog_tests/d_path.c
@@ -12,6 +12,17 @@
 #include "test_d_path_check_rdonly_mem.skel.h"
 #include "test_d_path_check_types.skel.h"
 
+/* sys_close_range is not around for long time, so let's
+ * make sure we can call it on systems with older glibc
+ */
+#ifndef __NR_close_range
+#ifdef __alpha__
+#define __NR_close_range 546
+#else
+#define __NR_close_range 436
+#endif
+#endif
+
 static int duration;
 
 static struct {
@@ -90,7 +101,11 @@ static int trigger_fstat_events(pid_t pid)
 	fstat(indicatorfd, &fileStat);
 
 out_close:
-	/* triggers filp_close */
+	/* sys_close no longer triggers filp_close, but we can
+	 * call sys_close_range instead which still does
+	 */
+#define close(fd) syscall(__NR_close_range, fd, fd, 0)
+
 	close(pipefd[0]);
 	close(pipefd[1]);
 	close(sockfd);
@@ -98,6 +113,8 @@ out_close:
 	close(devfd);
 	close(localfd);
 	close(indicatorfd);
+
+#undef close
 	return ret;
 }
 

From f48d4d35ad7b965d7945df75a34eec20761612f2 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Thu, 31 Aug 2023 13:15:54 +0100
Subject: [PATCH 0842/1189] nls: Hide new NLS_UCS2_UTILS

NLS_UCS2_UTILS is an option selected by filesystems that need it,
don't expose it to users.

Fixes: 089f7f591348 ("fs/smb: Swing unicode common code from smb->NLS")
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/nls/Kconfig | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/fs/nls/Kconfig b/fs/nls/Kconfig
index a0d0e2f7ec83..2a601af6f3bd 100644
--- a/fs/nls/Kconfig
+++ b/fs/nls/Kconfig
@@ -618,11 +618,6 @@ config NLS_UTF8
 	  the Unicode/ISO9646 universal character set.
 
 config NLS_UCS2_UTILS
-	tristate "NLS UCS-2 UTILS"
-	help
-	  Set of older UCS-2 conversion utilities and tables used by some
-	  filesystems including SMB/CIFS.  This includes upper case conversion
-	  tables. This will automatically be selected when the filesystem
-	  that uses it is selected.
+	tristate
 
 endif # NLS

From 91303f800e76517d1e96d47dec290c5d5dbf1230 Mon Sep 17 00:00:00 2001
From: Like Xu <likexu@tencent.com>
Date: Tue, 27 Jun 2023 12:26:39 +0800
Subject: [PATCH 0843/1189] KVM: x86/mmu: Move the lockdep_assert of mmu_lock
 to inside clear_dirty_pt_masked()

Move the lockdep_assert_held_write(&kvm->mmu_lock) from the only one caller
kvm_tdp_mmu_clear_dirty_pt_masked() to inside clear_dirty_pt_masked().

This change makes it more obvious why it's safe for clear_dirty_pt_masked()
to use the non-atomic (for non-volatile SPTEs) tdp_mmu_clear_spte_bits()
helper. for_each_tdp_mmu_root() does its own lockdep, so the only "loss"
in lockdep coverage is if the list is completely empty.

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Like Xu <likexu@tencent.com>
Link: https://lore.kernel.org/r/20230627042639.12636-1-likexu@tencent.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/tdp_mmu.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 6250bd3d20c1..639c5f2c88f8 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1600,6 +1600,8 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root,
 						   shadow_dirty_mask;
 	struct tdp_iter iter;
 
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
 	rcu_read_lock();
 
 	tdp_root_for_each_leaf_pte(iter, root, gfn + __ffs(mask),
@@ -1646,7 +1648,6 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
 {
 	struct kvm_mmu_page *root;
 
-	lockdep_assert_held_write(&kvm->mmu_lock);
 	for_each_tdp_mmu_root(kvm, root, slot->as_id)
 		clear_dirty_pt_masked(kvm, root, gfn, mask, wrprot);
 }

From d09f711233a43869725abc44102117d2a8fae6fe Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 21 Jul 2023 15:37:11 -0700
Subject: [PATCH 0844/1189] KVM: x86/mmu: Guard against collision with
 KVM-defined PFERR_IMPLICIT_ACCESS

Add an assertion in kvm_mmu_page_fault() to ensure the error code provided
by hardware doesn't conflict with KVM's software-defined IMPLICIT_ACCESS
flag.  In the unlikely scenario that future hardware starts using bit 48
for a hardware-defined flag, preserving the bit could result in KVM
incorrectly interpreting the unknown flag as KVM's IMPLICIT_ACCESS flag.

WARN so that any such conflict can be surfaced to KVM developers and
resolved, but otherwise ignore the bit as KVM can't possibly rely on a
flag it knows nothing about.

Fixes: 4f4aa80e3b88 ("KVM: X86: Handle implicit supervisor access with SMAP")
Acked-by: Kai Huang <kai.huang@intel.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Link: https://lore.kernel.org/r/20230721223711.2334426-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 276157f8496c..862604b6e6a3 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5724,6 +5724,17 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err
 	int r, emulation_type = EMULTYPE_PF;
 	bool direct = vcpu->arch.mmu->root_role.direct;
 
+	/*
+	 * IMPLICIT_ACCESS is a KVM-defined flag used to correctly perform SMAP
+	 * checks when emulating instructions that triggers implicit access.
+	 * WARN if hardware generates a fault with an error code that collides
+	 * with the KVM-defined value.  Clear the flag and continue on, i.e.
+	 * don't terminate the VM, as KVM can't possibly be relying on a flag
+	 * that KVM doesn't know about.
+	 */
+	if (WARN_ON_ONCE(error_code & PFERR_IMPLICIT_ACCESS))
+		error_code &= ~PFERR_IMPLICIT_ACCESS;
+
 	if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root.hpa)))
 		return RET_PF_RETRY;
 

From a98b889492a61a0220f26d8692ec744f1830a172 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:47:11 -0700
Subject: [PATCH 0845/1189] KVM: x86/mmu: Delete pgprintk() and all its usage

Delete KVM's pgprintk() and all its usage, as the code is very prone
to bitrot due to being buried behind MMU_DEBUG, and the functionality has
been rendered almost entirely obsolete by the tracepoints KVM has gained
over the years.  And for the situations where the information provided by
KVM's tracepoints is insufficient, pgprintk() rarely fills in the gaps,
and is almost always far too noisy, i.e. developers end up implementing
custom prints anyways.

Link: https://lore.kernel.org/r/20230729004722.1056172-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c          | 17 -----------------
 arch/x86/kvm/mmu/mmu_internal.h |  2 --
 arch/x86/kvm/mmu/paging_tmpl.h  |  7 -------
 arch/x86/kvm/mmu/spte.c         |  2 --
 4 files changed, 28 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 862604b6e6a3..63a8b82120fe 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -2771,12 +2771,9 @@ int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 	LIST_HEAD(invalid_list);
 	int r;
 
-	pgprintk("%s: looking for gfn %llx\n", __func__, gfn);
 	r = 0;
 	write_lock(&kvm->mmu_lock);
 	for_each_gfn_valid_sp_with_gptes(kvm, sp, gfn) {
-		pgprintk("%s: gfn %llx role %x\n", __func__, gfn,
-			 sp->role.word);
 		r = 1;
 		kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
 	}
@@ -2934,9 +2931,6 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
 	bool prefetch = !fault || fault->prefetch;
 	bool write_fault = fault && fault->write;
 
-	pgprintk("%s: spte %llx write_fault %d gfn %llx\n", __func__,
-		 *sptep, write_fault, gfn);
-
 	if (unlikely(is_noslot_pfn(pfn))) {
 		vcpu->stat.pf_mmio_spte_created++;
 		mark_mmio_spte(vcpu, sptep, gfn, pte_access);
@@ -2956,8 +2950,6 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
 			drop_parent_pte(child, sptep);
 			flush = true;
 		} else if (pfn != spte_to_pfn(*sptep)) {
-			pgprintk("hfn old %llx new %llx\n",
-				 spte_to_pfn(*sptep), pfn);
 			drop_spte(vcpu->kvm, sptep);
 			flush = true;
 		} else
@@ -2982,8 +2974,6 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
 	if (flush)
 		kvm_flush_remote_tlbs_gfn(vcpu->kvm, gfn, level);
 
-	pgprintk("%s: setting spte %llx\n", __func__, *sptep);
-
 	if (!was_rmapped) {
 		WARN_ON_ONCE(ret == RET_PF_SPURIOUS);
 		rmap_add(vcpu, slot, sptep, gfn, pte_access);
@@ -4439,8 +4429,6 @@ out_unlock:
 static int nonpaging_page_fault(struct kvm_vcpu *vcpu,
 				struct kvm_page_fault *fault)
 {
-	pgprintk("%s: gva %lx error %x\n", __func__, fault->addr, fault->error_code);
-
 	/* This path builds a PAE pagetable, we can map 2mb pages at maximum. */
 	fault->max_level = PG_LEVEL_2M;
 	return direct_page_fault(vcpu, fault);
@@ -5616,9 +5604,6 @@ static bool detect_write_misaligned(struct kvm_mmu_page *sp, gpa_t gpa,
 {
 	unsigned offset, pte_size, misaligned;
 
-	pgprintk("misaligned: gpa %llx bytes %d role %x\n",
-		 gpa, bytes, sp->role.word);
-
 	offset = offset_in_page(gpa);
 	pte_size = sp->role.has_4_byte_gpte ? 4 : 8;
 
@@ -5684,8 +5669,6 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	if (!READ_ONCE(vcpu->kvm->arch.indirect_shadow_pages))
 		return;
 
-	pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes);
-
 	write_lock(&vcpu->kvm->mmu_lock);
 
 	gentry = mmu_pte_write_fetch_gpte(vcpu, &gpa, &bytes);
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 86cb83bb3480..2d6bbf35520f 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -11,11 +11,9 @@
 #ifdef MMU_DEBUG
 extern bool dbg;
 
-#define pgprintk(x...) do { if (dbg) printk(x); } while (0)
 #define rmap_printk(fmt, args...) do { if (dbg) printk("%s: " fmt, __func__, ## args); } while (0)
 #define MMU_WARN_ON(x) WARN_ON(x)
 #else
-#define pgprintk(x...) do { } while (0)
 #define rmap_printk(x...) do { } while (0)
 #define MMU_WARN_ON(x) do { } while (0)
 #endif
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 0662e0278e70..7a97f769a7cb 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -456,9 +456,6 @@ retry_walk:
 			goto retry_walk;
 	}
 
-	pgprintk("%s: pte %llx pte_access %x pt_access %x\n",
-		 __func__, (u64)pte, walker->pte_access,
-		 walker->pt_access[walker->level - 1]);
 	return 1;
 
 error:
@@ -529,8 +526,6 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 	if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte))
 		return false;
 
-	pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte);
-
 	gfn = gpte_to_gfn(gpte);
 	pte_access = sp->role.access & FNAME(gpte_access)(gpte);
 	FNAME(protect_clean_gpte)(vcpu->arch.mmu, &pte_access, gpte);
@@ -758,7 +753,6 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	struct guest_walker walker;
 	int r;
 
-	pgprintk("%s: addr %lx err %x\n", __func__, fault->addr, fault->error_code);
 	WARN_ON_ONCE(fault->is_tdp);
 
 	/*
@@ -773,7 +767,6 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	 * The page is not mapped by the guest.  Let the guest handle it.
 	 */
 	if (!r) {
-		pgprintk("%s: guest page fault\n", __func__);
 		if (!fault->prefetch)
 			kvm_inject_emulated_page_fault(vcpu, &walker.fault);
 
diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index cf2c6426a6fc..438a86bda9f3 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -221,8 +221,6 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 		 * shadow pages and unsync'ing pages is not allowed.
 		 */
 		if (mmu_try_to_unsync_pages(vcpu->kvm, slot, gfn, can_unsync, prefetch)) {
-			pgprintk("%s: found shadow page for %llx, marking ro\n",
-				 __func__, gfn);
 			wrprot = true;
 			pte_access &= ~ACC_WRITE_MASK;
 			spte &= ~(PT_WRITABLE_MASK | shadow_mmu_writable_mask);

From 350c49fdea222193e886ddfa8cc55989853a05f5 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:47:12 -0700
Subject: [PATCH 0846/1189] KVM: x86/mmu: Delete rmap_printk() and all its
 usage

Delete rmap_printk() so that MMU_WARN_ON() and MMU_DEBUG can be morphed
into something that can be regularly enabled for debug kernels.  The
information provided by rmap_printk() isn't all that useful now that the
rmap and unsync code is mature, as the prints are simultaneously too
verbose (_lots_ of message) and yet not verbose enough to be helpful for
debug (most instances print just the SPTE pointer/value, which is rarely
sufficient to root cause anything but trivial bugs).

Alternatively, rmap_printk() could be reworked to into tracepoints, but
it's not clear there is a real need as rmap bugs rarely escape initial
development, and when bugs do escape to production, they are often edge
cases and/or reside in code that isn't directly related to the rmaps.
In other words, the problems with rmap_printk() being unhelpful also apply
to tracepoints.  And deleting rmap_printk() doesn't preclude adding
tracepoints in the future.

Link: https://lore.kernel.org/r/20230729004722.1056172-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c          | 12 ------------
 arch/x86/kvm/mmu/mmu_internal.h |  2 --
 2 files changed, 14 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 63a8b82120fe..d8c060071c2b 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -937,10 +937,8 @@ static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte,
 	int count = 0;
 
 	if (!rmap_head->val) {
-		rmap_printk("%p %llx 0->1\n", spte, *spte);
 		rmap_head->val = (unsigned long)spte;
 	} else if (!(rmap_head->val & 1)) {
-		rmap_printk("%p %llx 1->many\n", spte, *spte);
 		desc = kvm_mmu_memory_cache_alloc(cache);
 		desc->sptes[0] = (u64 *)rmap_head->val;
 		desc->sptes[1] = spte;
@@ -949,7 +947,6 @@ static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte,
 		rmap_head->val = (unsigned long)desc | 1;
 		++count;
 	} else {
-		rmap_printk("%p %llx many->many\n", spte, *spte);
 		desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
 		count = desc->tail_count + desc->spte_count;
 
@@ -1014,14 +1011,12 @@ static void pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head)
 		pr_err("%s: %p 0->BUG\n", __func__, spte);
 		BUG();
 	} else if (!(rmap_head->val & 1)) {
-		rmap_printk("%p 1->0\n", spte);
 		if ((u64 *)rmap_head->val != spte) {
 			pr_err("%s:  %p 1->BUG\n", __func__, spte);
 			BUG();
 		}
 		rmap_head->val = 0;
 	} else {
-		rmap_printk("%p many->many\n", spte);
 		desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
 		while (desc) {
 			for (i = 0; i < desc->spte_count; ++i) {
@@ -1237,8 +1232,6 @@ static bool spte_write_protect(u64 *sptep, bool pt_protect)
 	    !(pt_protect && is_mmu_writable_spte(spte)))
 		return false;
 
-	rmap_printk("spte %p %llx\n", sptep, *sptep);
-
 	if (pt_protect)
 		spte &= ~shadow_mmu_writable_mask;
 	spte = spte & ~PT_WRITABLE_MASK;
@@ -1263,8 +1256,6 @@ static bool spte_clear_dirty(u64 *sptep)
 {
 	u64 spte = *sptep;
 
-	rmap_printk("spte %p %llx\n", sptep, *sptep);
-
 	MMU_WARN_ON(!spte_ad_enabled(spte));
 	spte &= ~shadow_dirty_mask;
 	return mmu_spte_update(sptep, spte);
@@ -1476,9 +1467,6 @@ static bool kvm_set_pte_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
 
 restart:
 	for_each_rmap_spte(rmap_head, &iter, sptep) {
-		rmap_printk("spte %p %llx gfn %llx (%d)\n",
-			    sptep, *sptep, gfn, level);
-
 		need_flush = true;
 
 		if (pte_write(pte)) {
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 2d6bbf35520f..01c906e1d16d 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -11,10 +11,8 @@
 #ifdef MMU_DEBUG
 extern bool dbg;
 
-#define rmap_printk(fmt, args...) do { if (dbg) printk("%s: " fmt, __func__, ## args); } while (0)
 #define MMU_WARN_ON(x) WARN_ON(x)
 #else
-#define rmap_printk(x...) do { } while (0)
 #define MMU_WARN_ON(x) do { } while (0)
 #endif
 

From c4f92cfe021d9263a554f8adcd7c49ef52e485bb Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:47:13 -0700
Subject: [PATCH 0847/1189] KVM: x86/mmu: Delete the "dbg" module param

Delete KVM's "dbg" module param now that its usage in KVM is gone (it
used to guard pgprintk() and rmap_printk()).

Link: https://lore.kernel.org/r/20230729004722.1056172-4-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c          | 5 -----
 arch/x86/kvm/mmu/mmu_internal.h | 2 --
 2 files changed, 7 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index d8c060071c2b..8e0b7ad64333 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -115,11 +115,6 @@ static int max_huge_page_level __read_mostly;
 static int tdp_root_level __read_mostly;
 static int max_tdp_level __read_mostly;
 
-#ifdef MMU_DEBUG
-bool dbg = 0;
-module_param(dbg, bool, 0644);
-#endif
-
 #define PTE_PREFETCH_NUM		8
 
 #include <trace/events/kvm.h>
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 01c906e1d16d..9599e7eb6d85 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -9,8 +9,6 @@
 #undef MMU_DEBUG
 
 #ifdef MMU_DEBUG
-extern bool dbg;
-
 #define MMU_WARN_ON(x) WARN_ON(x)
 #else
 #define MMU_WARN_ON(x) do { } while (0)

From 242a6dd8daddbc718a3ad585ce4dce042c13e208 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:47:14 -0700
Subject: [PATCH 0848/1189] KVM: x86/mmu: Avoid pointer arithmetic when
 iterating over SPTEs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace the pointer arithmetic used to iterate over SPTEs in
is_empty_shadow_page() with more standard interger-based iteration.

No functional change intended.

Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Link: https://lore.kernel.org/r/20230729004722.1056172-5-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 8e0b7ad64333..3749ccdef6ce 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1692,15 +1692,15 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 #ifdef MMU_DEBUG
 static int is_empty_shadow_page(u64 *spt)
 {
-	u64 *pos;
-	u64 *end;
+	int i;
 
-	for (pos = spt, end = pos + SPTE_ENT_PER_PAGE; pos != end; pos++)
-		if (is_shadow_present_pte(*pos)) {
+	for (i = 0; i < SPTE_ENT_PER_PAGE; i++) {
+		if (is_shadow_present_pte(spt[i])) {
 			printk(KERN_ERR "%s: %p %llx\n", __func__,
-			       pos, *pos);
+			       &spt[i], spt[i]);
 			return 0;
 		}
+	}
 	return 1;
 }
 #endif

From 58da926caad9c6ecba70202a3775f2fd9b476cfc Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:47:15 -0700
Subject: [PATCH 0849/1189] KVM: x86/mmu: Cleanup sanity check of SPTEs at SP
 free

Massage the error message for the sanity check on SPTEs when freeing a
shadow page to be more verbose, and to print out all shadow-present SPTEs,
not just the first SPTE encountered.  Printing all SPTEs can be quite
valuable for debug, e.g. highlights whether the leak is a one-off or
widepsread, or possibly the result of memory corruption (something else
in the kernel stomping on KVM's SPTEs).

Opportunistically move the MMU_WARN_ON() into the helper itself, which
will allow a future cleanup to use BUILD_BUG_ON_INVALID() as the stub for
MMU_WARN_ON().  BUILD_BUG_ON_INVALID() works as intended and results in
the compiler complaining about is_empty_shadow_page() not being declared.

Link: https://lore.kernel.org/r/20230729004722.1056172-6-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 3749ccdef6ce..cb3adaa69350 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1689,21 +1689,19 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 	return young;
 }
 
-#ifdef MMU_DEBUG
-static int is_empty_shadow_page(u64 *spt)
+static void kvm_mmu_check_sptes_at_free(struct kvm_mmu_page *sp)
 {
+#ifdef MMU_DEBUG
 	int i;
 
 	for (i = 0; i < SPTE_ENT_PER_PAGE; i++) {
-		if (is_shadow_present_pte(spt[i])) {
-			printk(KERN_ERR "%s: %p %llx\n", __func__,
-			       &spt[i], spt[i]);
-			return 0;
-		}
+		if (MMU_WARN_ON(is_shadow_present_pte(sp->spt[i])))
+			pr_err_ratelimited("SPTE %llx (@ %p) for gfn %llx shadow-present at free",
+					   sp->spt[i], &sp->spt[i],
+					   kvm_mmu_page_get_gfn(sp, i));
 	}
-	return 1;
-}
 #endif
+}
 
 /*
  * This value is the sum of all of the kvm instances's
@@ -1731,7 +1729,8 @@ static void kvm_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
 
 static void kvm_mmu_free_shadow_page(struct kvm_mmu_page *sp)
 {
-	MMU_WARN_ON(!is_empty_shadow_page(sp->spt));
+	kvm_mmu_check_sptes_at_free(sp);
+
 	hlist_del(&sp->hash_link);
 	list_del(&sp->link);
 	free_page((unsigned long)sp->spt);

From 0fe6370eb3d5603e2e41bfca00043ed8b8f90cfb Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:47:16 -0700
Subject: [PATCH 0850/1189] KVM: x86/mmu: Rename MMU_WARN_ON() to
 KVM_MMU_WARN_ON()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Rename MMU_WARN_ON() to make it super obvious that the assertions are
all about KVM's MMU, not the primary MMU.

Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Link: https://lore.kernel.org/r/20230729004722.1056172-7-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c          | 4 ++--
 arch/x86/kvm/mmu/mmu_internal.h | 4 ++--
 arch/x86/kvm/mmu/spte.h         | 8 ++++----
 arch/x86/kvm/mmu/tdp_mmu.c      | 8 ++++----
 4 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index cb3adaa69350..8dc40d023742 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1251,7 +1251,7 @@ static bool spte_clear_dirty(u64 *sptep)
 {
 	u64 spte = *sptep;
 
-	MMU_WARN_ON(!spte_ad_enabled(spte));
+	KVM_MMU_WARN_ON(!spte_ad_enabled(spte));
 	spte &= ~shadow_dirty_mask;
 	return mmu_spte_update(sptep, spte);
 }
@@ -1695,7 +1695,7 @@ static void kvm_mmu_check_sptes_at_free(struct kvm_mmu_page *sp)
 	int i;
 
 	for (i = 0; i < SPTE_ENT_PER_PAGE; i++) {
-		if (MMU_WARN_ON(is_shadow_present_pte(sp->spt[i])))
+		if (KVM_MMU_WARN_ON(is_shadow_present_pte(sp->spt[i])))
 			pr_err_ratelimited("SPTE %llx (@ %p) for gfn %llx shadow-present at free",
 					   sp->spt[i], &sp->spt[i],
 					   kvm_mmu_page_get_gfn(sp, i));
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 9599e7eb6d85..d5ef61635b94 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -9,9 +9,9 @@
 #undef MMU_DEBUG
 
 #ifdef MMU_DEBUG
-#define MMU_WARN_ON(x) WARN_ON(x)
+#define KVM_MMU_WARN_ON(x) WARN_ON(x)
 #else
-#define MMU_WARN_ON(x) do { } while (0)
+#define KVM_MMU_WARN_ON(x) do { } while (0)
 #endif
 
 /* Page table builder macros common to shadow (host) PTEs and guest PTEs. */
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index 1279db2eab44..83e6614f3720 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -265,13 +265,13 @@ static inline bool sp_ad_disabled(struct kvm_mmu_page *sp)
 
 static inline bool spte_ad_enabled(u64 spte)
 {
-	MMU_WARN_ON(!is_shadow_present_pte(spte));
+	KVM_MMU_WARN_ON(!is_shadow_present_pte(spte));
 	return (spte & SPTE_TDP_AD_MASK) != SPTE_TDP_AD_DISABLED;
 }
 
 static inline bool spte_ad_need_write_protect(u64 spte)
 {
-	MMU_WARN_ON(!is_shadow_present_pte(spte));
+	KVM_MMU_WARN_ON(!is_shadow_present_pte(spte));
 	/*
 	 * This is benign for non-TDP SPTEs as SPTE_TDP_AD_ENABLED is '0',
 	 * and non-TDP SPTEs will never set these bits.  Optimize for 64-bit
@@ -282,13 +282,13 @@ static inline bool spte_ad_need_write_protect(u64 spte)
 
 static inline u64 spte_shadow_accessed_mask(u64 spte)
 {
-	MMU_WARN_ON(!is_shadow_present_pte(spte));
+	KVM_MMU_WARN_ON(!is_shadow_present_pte(spte));
 	return spte_ad_enabled(spte) ? shadow_accessed_mask : 0;
 }
 
 static inline u64 spte_shadow_dirty_mask(u64 spte)
 {
-	MMU_WARN_ON(!is_shadow_present_pte(spte));
+	KVM_MMU_WARN_ON(!is_shadow_present_pte(spte));
 	return spte_ad_enabled(spte) ? shadow_dirty_mask : 0;
 }
 
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 639c5f2c88f8..e54d5f442426 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1548,8 +1548,8 @@ retry:
 		if (!is_shadow_present_pte(iter.old_spte))
 			continue;
 
-		MMU_WARN_ON(kvm_ad_enabled() &&
-			    spte_ad_need_write_protect(iter.old_spte));
+		KVM_MMU_WARN_ON(kvm_ad_enabled() &&
+				spte_ad_need_write_protect(iter.old_spte));
 
 		if (!(iter.old_spte & dbit))
 			continue;
@@ -1609,8 +1609,8 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root,
 		if (!mask)
 			break;
 
-		MMU_WARN_ON(kvm_ad_enabled() &&
-			    spte_ad_need_write_protect(iter.old_spte));
+		KVM_MMU_WARN_ON(kvm_ad_enabled() &&
+				spte_ad_need_write_protect(iter.old_spte));
 
 		if (iter.level > PG_LEVEL_4K ||
 		    !(mask & (1UL << (iter.gfn - gfn))))

From 20ba462dfda6a95cb3bfb5577da813acf3dc4b40 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:47:17 -0700
Subject: [PATCH 0851/1189] KVM: x86/mmu: Convert "runtime" WARN_ON()
 assertions to WARN_ON_ONCE()

Convert all "runtime" assertions, i.e. assertions that can be triggered
while running vCPUs, from WARN_ON() to WARN_ON_ONCE().  Every WARN in the
MMU that is tied to running vCPUs, i.e. not contained to loading and
initializing KVM, is likely to fire _a lot_ when it does trigger.  E.g. if
KVM ends up with a bug that causes a root to be invalidated before the
page fault handler is invoked, pretty much _every_ page fault VM-Exit
triggers the WARN.

If a WARN is triggered frequently, the resulting spam usually causes a lot
of damage of its own, e.g. consumes resources to log the WARN and pollutes
the kernel log, often to the point where other useful information can be
lost.  In many case, the damage caused by the spam is actually worse than
the bug itself, e.g. KVM can almost always recover from an unexpectedly
invalid root.

On the flip side, warning every time is rarely helpful for debug and
triage, i.e. a single splat is usually sufficient to point a debugger in
the right direction, and automated testing, e.g. syzkaller, typically runs
with warn_on_panic=1, i.e. will never get past the first WARN anyways.

Lastly, when an assertions fails multiple times, the stack traces in KVM
are almost always identical, i.e. the full splat only needs to be captured
once.  And _if_ there is value in captruing information about the failed
assert, a ratelimited printk() is sufficient and less likely to rack up a
large amount of collateral damage.

Link: https://lore.kernel.org/r/20230729004722.1056172-8-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c          | 48 ++++++++++++++++-----------------
 arch/x86/kvm/mmu/mmu_internal.h |  2 +-
 arch/x86/kvm/mmu/page_track.c   | 16 +++++------
 arch/x86/kvm/mmu/paging_tmpl.h  |  4 +--
 arch/x86/kvm/mmu/spte.c         |  4 +--
 arch/x86/kvm/mmu/tdp_iter.c     |  4 +--
 arch/x86/kvm/mmu/tdp_mmu.c      | 20 +++++++-------
 7 files changed, 49 insertions(+), 49 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 8dc40d023742..ab3325981f9a 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -481,7 +481,7 @@ retry:
  */
 static void mmu_spte_set(u64 *sptep, u64 new_spte)
 {
-	WARN_ON(is_shadow_present_pte(*sptep));
+	WARN_ON_ONCE(is_shadow_present_pte(*sptep));
 	__set_spte(sptep, new_spte);
 }
 
@@ -493,7 +493,7 @@ static u64 mmu_spte_update_no_track(u64 *sptep, u64 new_spte)
 {
 	u64 old_spte = *sptep;
 
-	WARN_ON(!is_shadow_present_pte(new_spte));
+	WARN_ON_ONCE(!is_shadow_present_pte(new_spte));
 	check_spte_writable_invariants(new_spte);
 
 	if (!is_shadow_present_pte(old_spte)) {
@@ -506,7 +506,7 @@ static u64 mmu_spte_update_no_track(u64 *sptep, u64 new_spte)
 	else
 		old_spte = __update_clear_spte_slow(sptep, new_spte);
 
-	WARN_ON(spte_to_pfn(old_spte) != spte_to_pfn(new_spte));
+	WARN_ON_ONCE(spte_to_pfn(old_spte) != spte_to_pfn(new_spte));
 
 	return old_spte;
 }
@@ -588,7 +588,7 @@ static u64 mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep)
 	 * by a refcounted page, the refcount is elevated.
 	 */
 	page = kvm_pfn_to_refcounted_page(pfn);
-	WARN_ON(page && !page_count(page));
+	WARN_ON_ONCE(page && !page_count(page));
 
 	if (is_accessed_spte(old_spte))
 		kvm_set_pfn_accessed(pfn);
@@ -803,7 +803,7 @@ static void update_gfn_disallow_lpage_count(const struct kvm_memory_slot *slot,
 	for (i = PG_LEVEL_2M; i <= KVM_MAX_HUGEPAGE_LEVEL; ++i) {
 		linfo = lpage_info_slot(gfn, slot, i);
 		linfo->disallow_lpage += count;
-		WARN_ON(linfo->disallow_lpage < 0);
+		WARN_ON_ONCE(linfo->disallow_lpage < 0);
 	}
 }
 
@@ -1198,7 +1198,7 @@ static void drop_large_spte(struct kvm *kvm, u64 *sptep, bool flush)
 	struct kvm_mmu_page *sp;
 
 	sp = sptep_to_sp(sptep);
-	WARN_ON(sp->role.level == PG_LEVEL_4K);
+	WARN_ON_ONCE(sp->role.level == PG_LEVEL_4K);
 
 	drop_spte(kvm, sptep);
 
@@ -1457,7 +1457,7 @@ static bool kvm_set_pte_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
 	u64 new_spte;
 	kvm_pfn_t new_pfn;
 
-	WARN_ON(pte_huge(pte));
+	WARN_ON_ONCE(pte_huge(pte));
 	new_pfn = pte_pfn(pte);
 
 restart:
@@ -1818,7 +1818,7 @@ static int mmu_pages_add(struct kvm_mmu_pages *pvec, struct kvm_mmu_page *sp,
 static inline void clear_unsync_child_bit(struct kvm_mmu_page *sp, int idx)
 {
 	--sp->unsync_children;
-	WARN_ON((int)sp->unsync_children < 0);
+	WARN_ON_ONCE((int)sp->unsync_children < 0);
 	__clear_bit(idx, sp->unsync_child_bitmap);
 }
 
@@ -1876,7 +1876,7 @@ static int mmu_unsync_walk(struct kvm_mmu_page *sp,
 
 static void kvm_unlink_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
-	WARN_ON(!sp->unsync);
+	WARN_ON_ONCE(!sp->unsync);
 	trace_kvm_mmu_sync_page(sp);
 	sp->unsync = 0;
 	--kvm->stat.mmu_unsync;
@@ -2051,11 +2051,11 @@ static int mmu_pages_first(struct kvm_mmu_pages *pvec,
 	if (pvec->nr == 0)
 		return 0;
 
-	WARN_ON(pvec->page[0].idx != INVALID_INDEX);
+	WARN_ON_ONCE(pvec->page[0].idx != INVALID_INDEX);
 
 	sp = pvec->page[0].sp;
 	level = sp->role.level;
-	WARN_ON(level == PG_LEVEL_4K);
+	WARN_ON_ONCE(level == PG_LEVEL_4K);
 
 	parents->parent[level-2] = sp;
 
@@ -2077,7 +2077,7 @@ static void mmu_pages_clear_parents(struct mmu_page_path *parents)
 		if (!sp)
 			return;
 
-		WARN_ON(idx == INVALID_INDEX);
+		WARN_ON_ONCE(idx == INVALID_INDEX);
 		clear_unsync_child_bit(sp, idx);
 		level++;
 	} while (!sp->unsync_children);
@@ -2198,7 +2198,7 @@ static struct kvm_mmu_page *kvm_mmu_find_shadow_page(struct kvm *kvm,
 			if (ret < 0)
 				break;
 
-			WARN_ON(!list_empty(&invalid_list));
+			WARN_ON_ONCE(!list_empty(&invalid_list));
 			if (ret > 0)
 				kvm_flush_remote_tlbs(kvm);
 		}
@@ -2653,7 +2653,7 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm,
 	kvm_flush_remote_tlbs(kvm);
 
 	list_for_each_entry_safe(sp, nsp, invalid_list, link) {
-		WARN_ON(!sp->role.invalid || sp->root_count);
+		WARN_ON_ONCE(!sp->role.invalid || sp->root_count);
 		kvm_mmu_free_shadow_page(sp);
 	}
 }
@@ -2848,7 +2848,7 @@ int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot,
 				continue;
 		}
 
-		WARN_ON(sp->role.level != PG_LEVEL_4K);
+		WARN_ON_ONCE(sp->role.level != PG_LEVEL_4K);
 		kvm_unsync_page(kvm, sp);
 	}
 	if (locked)
@@ -3001,7 +3001,7 @@ static void __direct_pte_prefetch(struct kvm_vcpu *vcpu,
 	u64 *spte, *start = NULL;
 	int i;
 
-	WARN_ON(!sp->role.direct);
+	WARN_ON_ONCE(!sp->role.direct);
 
 	i = spte_index(sptep) & ~(PTE_PREFETCH_NUM - 1);
 	spte = sp->spt + i;
@@ -3547,7 +3547,7 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa,
 	 * SPTE to ensure any non-PA bits are dropped.
 	 */
 	sp = spte_to_child_sp(*root_hpa);
-	if (WARN_ON(!sp))
+	if (WARN_ON_ONCE(!sp))
 		return;
 
 	if (is_tdp_mmu_page(sp))
@@ -4162,7 +4162,7 @@ static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct)
 		return RET_PF_EMULATE;
 
 	reserved = get_mmio_spte(vcpu, addr, &spte);
-	if (WARN_ON(reserved))
+	if (WARN_ON_ONCE(reserved))
 		return -EINVAL;
 
 	if (is_mmio_spte(spte)) {
@@ -5483,9 +5483,9 @@ void kvm_mmu_unload(struct kvm_vcpu *vcpu)
 	struct kvm *kvm = vcpu->kvm;
 
 	kvm_mmu_free_roots(kvm, &vcpu->arch.root_mmu, KVM_MMU_ROOTS_ALL);
-	WARN_ON(VALID_PAGE(vcpu->arch.root_mmu.root.hpa));
+	WARN_ON_ONCE(VALID_PAGE(vcpu->arch.root_mmu.root.hpa));
 	kvm_mmu_free_roots(kvm, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);
-	WARN_ON(VALID_PAGE(vcpu->arch.guest_mmu.root.hpa));
+	WARN_ON_ONCE(VALID_PAGE(vcpu->arch.guest_mmu.root.hpa));
 	vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY);
 }
 
@@ -5700,7 +5700,7 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err
 	if (WARN_ON_ONCE(error_code & PFERR_IMPLICIT_ACCESS))
 		error_code &= ~PFERR_IMPLICIT_ACCESS;
 
-	if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root.hpa)))
+	if (WARN_ON_ONCE(!VALID_PAGE(vcpu->arch.mmu->root.hpa)))
 		return RET_PF_RETRY;
 
 	r = RET_PF_INVALID;
@@ -6057,7 +6057,7 @@ restart:
 		 * pages.  Skip the bogus page, otherwise we'll get stuck in an
 		 * infinite loop if the page gets put back on the list (again).
 		 */
-		if (WARN_ON(sp->role.invalid))
+		if (WARN_ON_ONCE(sp->role.invalid))
 			continue;
 
 		/*
@@ -6685,7 +6685,7 @@ void kvm_mmu_zap_all(struct kvm *kvm)
 	write_lock(&kvm->mmu_lock);
 restart:
 	list_for_each_entry_safe(sp, node, &kvm->arch.active_mmu_pages, link) {
-		if (WARN_ON(sp->role.invalid))
+		if (WARN_ON_ONCE(sp->role.invalid))
 			continue;
 		if (__kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list, &ign))
 			goto restart;
@@ -6703,7 +6703,7 @@ restart:
 
 void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen)
 {
-	WARN_ON(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS);
+	WARN_ON_ONCE(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS);
 
 	gen &= MMIO_SPTE_GEN_MASK;
 
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index d5ef61635b94..6b6cd30bcf4b 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -9,7 +9,7 @@
 #undef MMU_DEBUG
 
 #ifdef MMU_DEBUG
-#define KVM_MMU_WARN_ON(x) WARN_ON(x)
+#define KVM_MMU_WARN_ON(x) WARN_ON_ONCE(x)
 #else
 #define KVM_MMU_WARN_ON(x) do { } while (0)
 #endif
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index 0a2ac438d647..fd16918b3a7a 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -94,7 +94,7 @@ static void update_gfn_track(struct kvm_memory_slot *slot, gfn_t gfn,
 
 	val = slot->arch.gfn_track[mode][index];
 
-	if (WARN_ON(val + count < 0 || val + count > USHRT_MAX))
+	if (WARN_ON_ONCE(val + count < 0 || val + count > USHRT_MAX))
 		return;
 
 	slot->arch.gfn_track[mode][index] += count;
@@ -117,11 +117,11 @@ void kvm_slot_page_track_add_page(struct kvm *kvm,
 				  enum kvm_page_track_mode mode)
 {
 
-	if (WARN_ON(!page_track_mode_is_valid(mode)))
+	if (WARN_ON_ONCE(!page_track_mode_is_valid(mode)))
 		return;
 
-	if (WARN_ON(mode == KVM_PAGE_TRACK_WRITE &&
-		    !kvm_page_track_write_tracking_enabled(kvm)))
+	if (WARN_ON_ONCE(mode == KVM_PAGE_TRACK_WRITE &&
+			 !kvm_page_track_write_tracking_enabled(kvm)))
 		return;
 
 	update_gfn_track(slot, gfn, mode, 1);
@@ -155,11 +155,11 @@ void kvm_slot_page_track_remove_page(struct kvm *kvm,
 				     struct kvm_memory_slot *slot, gfn_t gfn,
 				     enum kvm_page_track_mode mode)
 {
-	if (WARN_ON(!page_track_mode_is_valid(mode)))
+	if (WARN_ON_ONCE(!page_track_mode_is_valid(mode)))
 		return;
 
-	if (WARN_ON(mode == KVM_PAGE_TRACK_WRITE &&
-		    !kvm_page_track_write_tracking_enabled(kvm)))
+	if (WARN_ON_ONCE(mode == KVM_PAGE_TRACK_WRITE &&
+			 !kvm_page_track_write_tracking_enabled(kvm)))
 		return;
 
 	update_gfn_track(slot, gfn, mode, -1);
@@ -181,7 +181,7 @@ bool kvm_slot_page_track_is_active(struct kvm *kvm,
 {
 	int index;
 
-	if (WARN_ON(!page_track_mode_is_valid(mode)))
+	if (WARN_ON_ONCE(!page_track_mode_is_valid(mode)))
 		return false;
 
 	if (!slot)
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 7a97f769a7cb..a3fc7c1a7f8d 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -633,7 +633,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 	if (FNAME(gpte_changed)(vcpu, gw, top_level))
 		goto out_gpte_changed;
 
-	if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root.hpa)))
+	if (WARN_ON_ONCE(!VALID_PAGE(vcpu->arch.mmu->root.hpa)))
 		goto out_gpte_changed;
 
 	for_each_shadow_entry(vcpu, fault->addr, it) {
@@ -830,7 +830,7 @@ static gpa_t FNAME(get_level1_sp_gpa)(struct kvm_mmu_page *sp)
 {
 	int offset = 0;
 
-	WARN_ON(sp->role.level != PG_LEVEL_4K);
+	WARN_ON_ONCE(sp->role.level != PG_LEVEL_4K);
 
 	if (PTTYPE == 32)
 		offset = sp->role.quadrant << SPTE_LEVEL_BITS;
diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index 438a86bda9f3..4a599130e9c9 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -61,7 +61,7 @@ static u64 generation_mmio_spte_mask(u64 gen)
 {
 	u64 mask;
 
-	WARN_ON(gen & ~MMIO_SPTE_GEN_MASK);
+	WARN_ON_ONCE(gen & ~MMIO_SPTE_GEN_MASK);
 
 	mask = (gen << MMIO_SPTE_GEN_LOW_SHIFT) & MMIO_SPTE_GEN_LOW_MASK;
 	mask |= (gen << MMIO_SPTE_GEN_HIGH_SHIFT) & MMIO_SPTE_GEN_HIGH_MASK;
@@ -240,7 +240,7 @@ out:
 
 	if ((spte & PT_WRITABLE_MASK) && kvm_slot_dirty_track_enabled(slot)) {
 		/* Enforced by kvm_mmu_hugepage_adjust. */
-		WARN_ON(level > PG_LEVEL_4K);
+		WARN_ON_ONCE(level > PG_LEVEL_4K);
 		mark_page_dirty_in_slot(vcpu->kvm, slot, gfn);
 	}
 
diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c
index d2eb0d4f8710..5bb09f8d9fc6 100644
--- a/arch/x86/kvm/mmu/tdp_iter.c
+++ b/arch/x86/kvm/mmu/tdp_iter.c
@@ -41,8 +41,8 @@ void tdp_iter_start(struct tdp_iter *iter, struct kvm_mmu_page *root,
 {
 	int root_level = root->role.level;
 
-	WARN_ON(root_level < 1);
-	WARN_ON(root_level > PT64_ROOT_MAX_LEVEL);
+	WARN_ON_ONCE(root_level < 1);
+	WARN_ON_ONCE(root_level > PT64_ROOT_MAX_LEVEL);
 
 	iter->next_last_level_gfn = next_last_level_gfn;
 	iter->root_level = root_level;
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index e54d5f442426..fda32a72b406 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -475,9 +475,9 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
 	bool is_leaf = is_present && is_last_spte(new_spte, level);
 	bool pfn_changed = spte_to_pfn(old_spte) != spte_to_pfn(new_spte);
 
-	WARN_ON(level > PT64_ROOT_MAX_LEVEL);
-	WARN_ON(level < PG_LEVEL_4K);
-	WARN_ON(gfn & (KVM_PAGES_PER_HPAGE(level) - 1));
+	WARN_ON_ONCE(level > PT64_ROOT_MAX_LEVEL);
+	WARN_ON_ONCE(level < PG_LEVEL_4K);
+	WARN_ON_ONCE(gfn & (KVM_PAGES_PER_HPAGE(level) - 1));
 
 	/*
 	 * If this warning were to trigger it would indicate that there was a
@@ -522,9 +522,9 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
 		 * impact the guest since both the former and current SPTEs
 		 * are nonpresent.
 		 */
-		if (WARN_ON(!is_mmio_spte(old_spte) &&
-			    !is_mmio_spte(new_spte) &&
-			    !is_removed_spte(new_spte)))
+		if (WARN_ON_ONCE(!is_mmio_spte(old_spte) &&
+				 !is_mmio_spte(new_spte) &&
+				 !is_removed_spte(new_spte)))
 			pr_err("Unexpected SPTE change! Nonpresent SPTEs\n"
 			       "should not be replaced with another,\n"
 			       "different nonpresent SPTE, unless one or both\n"
@@ -661,7 +661,7 @@ static u64 tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep,
 	 * should be used. If operating under the MMU lock in write mode, the
 	 * use of the removed SPTE should not be necessary.
 	 */
-	WARN_ON(is_removed_spte(old_spte) || is_removed_spte(new_spte));
+	WARN_ON_ONCE(is_removed_spte(old_spte) || is_removed_spte(new_spte));
 
 	old_spte = kvm_tdp_mmu_write_spte(sptep, old_spte, new_spte, level);
 
@@ -709,7 +709,7 @@ static inline bool __must_check tdp_mmu_iter_cond_resched(struct kvm *kvm,
 							  struct tdp_iter *iter,
 							  bool flush, bool shared)
 {
-	WARN_ON(iter->yielded);
+	WARN_ON_ONCE(iter->yielded);
 
 	/* Ensure forward progress has been made before yielding. */
 	if (iter->next_last_level_gfn == iter->yielded_gfn)
@@ -728,7 +728,7 @@ static inline bool __must_check tdp_mmu_iter_cond_resched(struct kvm *kvm,
 
 		rcu_read_lock();
 
-		WARN_ON(iter->gfn > iter->next_last_level_gfn);
+		WARN_ON_ONCE(iter->gfn > iter->next_last_level_gfn);
 
 		iter->yielded = true;
 	}
@@ -1241,7 +1241,7 @@ static bool set_spte_gfn(struct kvm *kvm, struct tdp_iter *iter,
 	u64 new_spte;
 
 	/* Huge pages aren't expected to be modified without first being zapped. */
-	WARN_ON(pte_huge(range->arg.pte) || range->start + 1 != range->end);
+	WARN_ON_ONCE(pte_huge(range->arg.pte) || range->start + 1 != range->end);
 
 	if (iter->level != PG_LEVEL_4K ||
 	    !is_shadow_present_pte(iter->old_spte))

From 72e2fb24a0b0528bcc16a8f6ad2cf336ac361525 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:47:18 -0700
Subject: [PATCH 0852/1189] KVM: x86/mmu: Bug the VM if a vCPU ends up in long
 mode without PAE enabled

Promote the ASSERT(), which is quite dead code in KVM, into a KVM_BUG_ON()
for KVM's sanity check that CR4.PAE=1 if the vCPU is in long mode when
performing a walk of guest page tables.  The sanity is quite cheap since
neither EFER nor CR4.PAE requires a VMREAD, especially relative to the
cost of walking the guest page tables.

More importantly, the sanity check would have prevented the true badness
fixed by commit 112e66017bff ("KVM: nVMX: add missing consistency checks
for CR0 and CR4").  The missed consistency check resulted in some versions
of KVM corrupting the on-stack guest_walker structure due to KVM thinking
there are 4/5 levels of page tables, but wiring up the MMU hooks to point
at the paging32 implementation, which only allocates space for two levels
of page tables in "struct guest_walker32".

Queue a page fault for injection if the assertion fails, as both callers,
FNAME(gva_to_gpa) and FNAME(walk_addr_generic), assume that walker.fault
contains sane info on a walk failure.  E.g. not populating the fault info
could result in KVM consuming and/or exposing uninitialized stack data
before the vCPU is kicked out to userspace, which doesn't happen until
KVM checks for KVM_REQ_VM_DEAD on the next enter.

Move the check below the initialization of "pte_access" so that the
aforementioned to-be-injected page fault doesn't consume uninitialized
stack data.  The information _shouldn't_ reach the guest or userspace,
but there's zero downside to being paranoid in this case.

Link: https://lore.kernel.org/r/20230729004722.1056172-9-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/paging_tmpl.h | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index a3fc7c1a7f8d..f8d358226ac6 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -338,7 +338,6 @@ retry_walk:
 	}
 #endif
 	walker->max_level = walker->level;
-	ASSERT(!(is_long_mode(vcpu) && !is_pae(vcpu)));
 
 	/*
 	 * FIXME: on Intel processors, loads of the PDPTE registers for PAE paging
@@ -348,6 +347,17 @@ retry_walk:
 	nested_access = (have_ad ? PFERR_WRITE_MASK : 0) | PFERR_USER_MASK;
 
 	pte_access = ~0;
+
+	/*
+	 * Queue a page fault for injection if this assertion fails, as callers
+	 * assume that walker.fault contains sane info on a walk failure.  I.e.
+	 * avoid making the situation worse by inducing even worse badness
+	 * between when the assertion fails and when KVM kicks the vCPU out to
+	 * userspace (because the VM is bugged).
+	 */
+	if (KVM_BUG_ON(is_long_mode(vcpu) && !is_pae(vcpu), vcpu->kvm))
+		goto error;
+
 	++walker->level;
 
 	do {

From 870d4d4ed82779e717ec7fb0f9b64f43bd7a736b Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:47:19 -0700
Subject: [PATCH 0853/1189] KVM: x86/mmu: Replace MMU_DEBUG with proper
 KVM_PROVE_MMU Kconfig
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace MMU_DEBUG, which requires manually modifying KVM to enable the
macro, with a proper Kconfig, KVM_PROVE_MMU.  Now that pgprintk() and
rmap_printk() are gone, i.e. the macro guards only KVM_MMU_WARN_ON() and
won't flood the kernel logs, enabling the option for debug kernels is both
desirable and feasible.

Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Link: https://lore.kernel.org/r/20230729004722.1056172-10-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/Kconfig            | 13 +++++++++++++
 arch/x86/kvm/mmu/mmu.c          |  2 +-
 arch/x86/kvm/mmu/mmu_internal.h |  4 +---
 3 files changed, 15 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 66dbd1f4d57d..ed90f148140d 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -138,6 +138,19 @@ config KVM_XEN
 
 	  If in doubt, say "N".
 
+config KVM_PROVE_MMU
+	bool "Prove KVM MMU correctness"
+	depends on DEBUG_KERNEL
+	depends on KVM
+	depends on EXPERT
+	help
+	  Enables runtime assertions in KVM's MMU that are too costly to enable
+	  in anything remotely resembling a production environment, e.g. this
+	  gates code that verifies a to-be-freed page table doesn't have any
+	  present SPTEs.
+
+	  If in doubt, say "N".
+
 config KVM_EXTERNAL_WRITE_TRACKING
 	bool
 
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index ab3325981f9a..baa312388721 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1691,7 +1691,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 
 static void kvm_mmu_check_sptes_at_free(struct kvm_mmu_page *sp)
 {
-#ifdef MMU_DEBUG
+#ifdef CONFIG_KVM_PROVE_MMU
 	int i;
 
 	for (i = 0; i < SPTE_ENT_PER_PAGE; i++) {
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 6b6cd30bcf4b..606f343d99c1 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -6,9 +6,7 @@
 #include <linux/kvm_host.h>
 #include <asm/kvm_host.h>
 
-#undef MMU_DEBUG
-
-#ifdef MMU_DEBUG
+#ifdef CONFIG_KVM_PROVE_MMU
 #define KVM_MMU_WARN_ON(x) WARN_ON_ONCE(x)
 #else
 #define KVM_MMU_WARN_ON(x) do { } while (0)

From 3328dfe0eac38df388a0cded8e3f3cd307ca0be3 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:47:20 -0700
Subject: [PATCH 0854/1189] KVM: x86/mmu: Use BUILD_BUG_ON_INVALID() for
 KVM_MMU_WARN_ON() stub
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use BUILD_BUG_ON_INVALID() instead of an empty do-while loop to stub out
KVM_MMU_WARN_ON() when CONFIG_KVM_PROVE_MMU=n, that way _some_ build
issues with the usage of KVM_MMU_WARN_ON() will be dected even if the
kernel is using the stubs, e.g. basic syntax errors will be detected.

Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Link: https://lore.kernel.org/r/20230729004722.1056172-11-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu_internal.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 606f343d99c1..95846c40e79e 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -9,7 +9,7 @@
 #ifdef CONFIG_KVM_PROVE_MMU
 #define KVM_MMU_WARN_ON(x) WARN_ON_ONCE(x)
 #else
-#define KVM_MMU_WARN_ON(x) do { } while (0)
+#define KVM_MMU_WARN_ON(x) BUILD_BUG_ON_INVALID(x)
 #endif
 
 /* Page table builder macros common to shadow (host) PTEs and guest PTEs. */

From 069f30c619792d5202d72fecd842cacbee260561 Mon Sep 17 00:00:00 2001
From: Mingwei Zhang <mizhang@google.com>
Date: Fri, 28 Jul 2023 17:47:21 -0700
Subject: [PATCH 0855/1189] KVM: x86/mmu: Plumb "struct kvm" all the way to
 pte_list_remove()

Plumb "struct kvm" all the way to pte_list_remove() to allow the usage of
KVM_BUG() and/or KVM_BUG_ON().  This will allow killing only the offending
VM instead of doing BUG() if the kernel is built with
CONFIG_BUG_ON_DATA_CORRUPTION=n, i.e. does NOT want to BUG() if KVM's data
structures (rmaps) appear to be corrupted.

Signed-off-by: Mingwei Zhang <mizhang@google.com>
[sean: tweak changelog]
Link: https://lore.kernel.org/r/20230729004722.1056172-12-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c | 33 ++++++++++++++++++---------------
 1 file changed, 18 insertions(+), 15 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index baa312388721..f518dd569a14 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -961,7 +961,8 @@ static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte,
 	return count;
 }
 
-static void pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head,
+static void pte_list_desc_remove_entry(struct kvm *kvm,
+				       struct kvm_rmap_head *rmap_head,
 				       struct pte_list_desc *desc, int i)
 {
 	struct pte_list_desc *head_desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
@@ -997,7 +998,8 @@ static void pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head,
 	mmu_free_pte_list_desc(head_desc);
 }
 
-static void pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head)
+static void pte_list_remove(struct kvm *kvm, u64 *spte,
+			    struct kvm_rmap_head *rmap_head)
 {
 	struct pte_list_desc *desc;
 	int i;
@@ -1016,7 +1018,8 @@ static void pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head)
 		while (desc) {
 			for (i = 0; i < desc->spte_count; ++i) {
 				if (desc->sptes[i] == spte) {
-					pte_list_desc_remove_entry(rmap_head, desc, i);
+					pte_list_desc_remove_entry(kvm, rmap_head,
+								   desc, i);
 					return;
 				}
 			}
@@ -1031,7 +1034,7 @@ static void kvm_zap_one_rmap_spte(struct kvm *kvm,
 				  struct kvm_rmap_head *rmap_head, u64 *sptep)
 {
 	mmu_spte_clear_track_bits(kvm, sptep);
-	pte_list_remove(sptep, rmap_head);
+	pte_list_remove(kvm, sptep, rmap_head);
 }
 
 /* Return true if at least one SPTE was zapped, false otherwise */
@@ -1106,7 +1109,7 @@ static void rmap_remove(struct kvm *kvm, u64 *spte)
 	slot = __gfn_to_memslot(slots, gfn);
 	rmap_head = gfn_to_rmap(gfn, sp->role.level, slot);
 
-	pte_list_remove(spte, rmap_head);
+	pte_list_remove(kvm, spte, rmap_head);
 }
 
 /*
@@ -1753,16 +1756,16 @@ static void mmu_page_add_parent_pte(struct kvm_mmu_memory_cache *cache,
 	pte_list_add(cache, parent_pte, &sp->parent_ptes);
 }
 
-static void mmu_page_remove_parent_pte(struct kvm_mmu_page *sp,
+static void mmu_page_remove_parent_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
 				       u64 *parent_pte)
 {
-	pte_list_remove(parent_pte, &sp->parent_ptes);
+	pte_list_remove(kvm, parent_pte, &sp->parent_ptes);
 }
 
-static void drop_parent_pte(struct kvm_mmu_page *sp,
+static void drop_parent_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
 			    u64 *parent_pte)
 {
-	mmu_page_remove_parent_pte(sp, parent_pte);
+	mmu_page_remove_parent_pte(kvm, sp, parent_pte);
 	mmu_spte_clear_no_track(parent_pte);
 }
 
@@ -2477,7 +2480,7 @@ static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		if (child->role.access == direct_access)
 			return;
 
-		drop_parent_pte(child, sptep);
+		drop_parent_pte(vcpu->kvm, child, sptep);
 		kvm_flush_remote_tlbs_sptep(vcpu->kvm, sptep);
 	}
 }
@@ -2495,7 +2498,7 @@ static int mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
 			drop_spte(kvm, spte);
 		} else {
 			child = spte_to_child_sp(pte);
-			drop_parent_pte(child, spte);
+			drop_parent_pte(kvm, child, spte);
 
 			/*
 			 * Recursively zap nested TDP SPs, parentless SPs are
@@ -2526,13 +2529,13 @@ static int kvm_mmu_page_unlink_children(struct kvm *kvm,
 	return zapped;
 }
 
-static void kvm_mmu_unlink_parents(struct kvm_mmu_page *sp)
+static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
 
 	while ((sptep = rmap_get_first(&sp->parent_ptes, &iter)))
-		drop_parent_pte(sp, sptep);
+		drop_parent_pte(kvm, sp, sptep);
 }
 
 static int mmu_zap_unsync_children(struct kvm *kvm,
@@ -2571,7 +2574,7 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm,
 	++kvm->stat.mmu_shadow_zapped;
 	*nr_zapped = mmu_zap_unsync_children(kvm, sp, invalid_list);
 	*nr_zapped += kvm_mmu_page_unlink_children(kvm, sp, invalid_list);
-	kvm_mmu_unlink_parents(sp);
+	kvm_mmu_unlink_parents(kvm, sp);
 
 	/* Zapping children means active_mmu_pages has become unstable. */
 	list_unstable = *nr_zapped;
@@ -2929,7 +2932,7 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
 			u64 pte = *sptep;
 
 			child = spte_to_child_sp(pte);
-			drop_parent_pte(child, sptep);
+			drop_parent_pte(vcpu->kvm, child, sptep);
 			flush = true;
 		} else if (pfn != spte_to_pfn(*sptep)) {
 			drop_spte(vcpu->kvm, sptep);

From 52e322eda3d475614210efbc0f2793a1da9d367a Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:47:22 -0700
Subject: [PATCH 0856/1189] KVM: x86/mmu: BUG() in rmap helpers iff
 CONFIG_BUG_ON_DATA_CORRUPTION=y

Introduce KVM_BUG_ON_DATA_CORRUPTION() and use it in the low-level rmap
helpers to convert the existing BUG()s to WARN_ON_ONCE() when the kernel
is built with CONFIG_BUG_ON_DATA_CORRUPTION=n, i.e. does NOT want to BUG()
on corruption of host kernel data structures.  Environments that don't
have infrastructure to automatically capture crash dumps, i.e. aren't
likely to enable CONFIG_BUG_ON_DATA_CORRUPTION=y, are typically better
served overall by WARN-and-continue behavior (for the kernel, the VM is
dead regardless), as a BUG() while holding mmu_lock all but guarantees
the _best_ case scenario is a panic().

Make the BUG()s conditional instead of removing/replacing them entirely as
there's a non-zero chance (though by no means a guarantee) that the damage
isn't contained to the target VM, e.g. if no rmap is found for a SPTE then
KVM may be double-zapping the SPTE, i.e. has already freed the memory the
SPTE pointed at and thus KVM is reading/writing memory that KVM no longer
owns.

Link: https://lore.kernel.org/all/20221129191237.31447-1-mizhang@google.com
Suggested-by: Mingwei Zhang <mizhang@google.com>
Cc: David Matlack <dmatlack@google.com>
Cc: Jim Mattson <jmattson@google.com>
Reviewed-by: Mingwei Zhang <mizhang@google.com>
Link: https://lore.kernel.org/r/20230729004722.1056172-13-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c   | 21 ++++++++++-----------
 include/linux/kvm_host.h | 19 +++++++++++++++++++
 2 files changed, 29 insertions(+), 11 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index f518dd569a14..0420944da242 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -973,7 +973,7 @@ static void pte_list_desc_remove_entry(struct kvm *kvm,
 	 * when adding an entry and the previous head is full, and heads are
 	 * removed (this flow) when they become empty.
 	 */
-	BUG_ON(j < 0);
+	KVM_BUG_ON_DATA_CORRUPTION(j < 0, kvm);
 
 	/*
 	 * Replace the to-be-freed SPTE with the last valid entry from the head
@@ -1004,14 +1004,13 @@ static void pte_list_remove(struct kvm *kvm, u64 *spte,
 	struct pte_list_desc *desc;
 	int i;
 
-	if (!rmap_head->val) {
-		pr_err("%s: %p 0->BUG\n", __func__, spte);
-		BUG();
-	} else if (!(rmap_head->val & 1)) {
-		if ((u64 *)rmap_head->val != spte) {
-			pr_err("%s:  %p 1->BUG\n", __func__, spte);
-			BUG();
-		}
+	if (KVM_BUG_ON_DATA_CORRUPTION(!rmap_head->val, kvm))
+		return;
+
+	if (!(rmap_head->val & 1)) {
+		if (KVM_BUG_ON_DATA_CORRUPTION((u64 *)rmap_head->val != spte, kvm))
+			return;
+
 		rmap_head->val = 0;
 	} else {
 		desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
@@ -1025,8 +1024,8 @@ static void pte_list_remove(struct kvm *kvm, u64 *spte,
 			}
 			desc = desc->more;
 		}
-		pr_err("%s: %p many->many\n", __func__, spte);
-		BUG();
+
+		KVM_BUG_ON_DATA_CORRUPTION(true, kvm);
 	}
 }
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 1b583f35547e..fb6c6109fdca 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -867,6 +867,25 @@ static inline void kvm_vm_bugged(struct kvm *kvm)
 	unlikely(__ret);					\
 })
 
+/*
+ * Note, "data corruption" refers to corruption of host kernel data structures,
+ * not guest data.  Guest data corruption, suspected or confirmed, that is tied
+ * and contained to a single VM should *never* BUG() and potentially panic the
+ * host, i.e. use this variant of KVM_BUG() if and only if a KVM data structure
+ * is corrupted and that corruption can have a cascading effect to other parts
+ * of the hosts and/or to other VMs.
+ */
+#define KVM_BUG_ON_DATA_CORRUPTION(cond, kvm)			\
+({								\
+	bool __ret = !!(cond);					\
+								\
+	if (IS_ENABLED(CONFIG_BUG_ON_DATA_CORRUPTION))		\
+		BUG_ON(__ret);					\
+	else if (WARN_ON_ONCE(__ret && !(kvm)->vm_bugged))	\
+		kvm_vm_bugged(kvm);				\
+	unlikely(__ret);					\
+})
+
 static inline void kvm_vcpu_srcu_read_lock(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_PROVE_RCU

From f046923af79158361295ed4f0a588c80b9fdcc1d Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:07 -0700
Subject: [PATCH 0857/1189] drm/i915/gvt: Verify pfn is "valid" before
 dereferencing "struct page"

Check that the pfn found by gfn_to_pfn() is actually backed by "struct
page" memory prior to retrieving and dereferencing the page.  KVM
supports backing guest memory with VM_PFNMAP, VM_IO, etc., and so
there is no guarantee the pfn returned by gfn_to_pfn() has an associated
"struct page".

Fixes: b901b252b6cf ("drm/i915/gvt: Add 2M huge gtt support")
Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Reviewed-by: Zhi Wang <zhi.a.wang@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 drivers/gpu/drm/i915/gvt/gtt.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 4ec85308379a..58b9b316ae46 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -1183,6 +1183,10 @@ static int is_2MB_gtt_possible(struct intel_vgpu *vgpu,
 	pfn = gfn_to_pfn(vgpu->vfio_device.kvm, ops->get_pfn(entry));
 	if (is_error_noslot_pfn(pfn))
 		return -EINVAL;
+
+	if (!pfn_valid(pfn))
+		return -EINVAL;
+
 	return PageTransHuge(pfn_to_page(pfn));
 }
 

From 1e557c1cd0549b30fa4bc3e9aa46c5eeadaa63f5 Mon Sep 17 00:00:00 2001
From: Yan Zhao <yan.y.zhao@intel.com>
Date: Fri, 28 Jul 2023 18:35:08 -0700
Subject: [PATCH 0858/1189] drm/i915/gvt: remove interface
 intel_gvt_is_valid_gfn

Currently intel_gvt_is_valid_gfn() is called in two places:
(1) shadowing guest GGTT entry
(2) shadowing guest PPGTT leaf entry,
which was introduced in commit cc753fbe1ac4
("drm/i915/gvt: validate gfn before set shadow page entry").

However, now it's not necessary to call this interface any more, because
a. GGTT partial write issue has been fixed by
   commit bc0686ff5fad
   ("drm/i915/gvt: support inconsecutive partial gtt entry write")
   commit 510fe10b6180
   ("drm/i915/gvt: fix a bug of partially write ggtt enties")
b. PPGTT resides in normal guest RAM and we only treat 8-byte writes
   as valid page table writes. Any invalid GPA found is regarded as
   an error, either due to guest misbehavior/attack or bug in host
   shadow code.
   So,rather than do GFN pre-checking and replace invalid GFNs with
   scratch GFN and continue silently, just remove the pre-checking and
   abort PPGTT shadowing on error detected.
c. GFN validity check is still performed in
   intel_gvt_dma_map_guest_page() --> gvt_pin_guest_page().
   It's more desirable to call VFIO interface to do both validity check
   and mapping.
   Calling intel_gvt_is_valid_gfn() to do GFN validity check from KVM side
   while later mapping the GFN through VFIO interface is unnecessarily
   fragile and confusing for unaware readers.

Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
[sean: remove now-unused local variables]
Acked-by: Zhi Wang <zhi.a.wang@intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 drivers/gpu/drm/i915/gvt/gtt.c | 36 +---------------------------------
 1 file changed, 1 insertion(+), 35 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 58b9b316ae46..f30922c55a0c 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -49,22 +49,6 @@
 static bool enable_out_of_sync = false;
 static int preallocated_oos_pages = 8192;
 
-static bool intel_gvt_is_valid_gfn(struct intel_vgpu *vgpu, unsigned long gfn)
-{
-	struct kvm *kvm = vgpu->vfio_device.kvm;
-	int idx;
-	bool ret;
-
-	if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
-		return false;
-
-	idx = srcu_read_lock(&kvm->srcu);
-	ret = kvm_is_visible_gfn(kvm, gfn);
-	srcu_read_unlock(&kvm->srcu, idx);
-
-	return ret;
-}
-
 /*
  * validate a gm address and related range size,
  * translate it to host gm address
@@ -1333,11 +1317,9 @@ static int ppgtt_populate_shadow_entry(struct intel_vgpu *vgpu,
 static int ppgtt_populate_spt(struct intel_vgpu_ppgtt_spt *spt)
 {
 	struct intel_vgpu *vgpu = spt->vgpu;
-	struct intel_gvt *gvt = vgpu->gvt;
-	const struct intel_gvt_gtt_pte_ops *ops = gvt->gtt.pte_ops;
 	struct intel_vgpu_ppgtt_spt *s;
 	struct intel_gvt_gtt_entry se, ge;
-	unsigned long gfn, i;
+	unsigned long i;
 	int ret;
 
 	trace_spt_change(spt->vgpu->id, "born", spt,
@@ -1354,13 +1336,6 @@ static int ppgtt_populate_spt(struct intel_vgpu_ppgtt_spt *spt)
 			ppgtt_generate_shadow_entry(&se, s, &ge);
 			ppgtt_set_shadow_entry(spt, &se, i);
 		} else {
-			gfn = ops->get_pfn(&ge);
-			if (!intel_gvt_is_valid_gfn(vgpu, gfn)) {
-				ops->set_pfn(&se, gvt->gtt.scratch_mfn);
-				ppgtt_set_shadow_entry(spt, &se, i);
-				continue;
-			}
-
 			ret = ppgtt_populate_shadow_entry(vgpu, spt, i, &ge);
 			if (ret)
 				goto fail;
@@ -2335,14 +2310,6 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off,
 		m.val64 = e.val64;
 		m.type = e.type;
 
-		/* one PTE update may be issued in multiple writes and the
-		 * first write may not construct a valid gfn
-		 */
-		if (!intel_gvt_is_valid_gfn(vgpu, gfn)) {
-			ops->set_pfn(&m, gvt->gtt.scratch_mfn);
-			goto out;
-		}
-
 		ret = intel_gvt_dma_map_guest_page(vgpu, gfn, PAGE_SIZE,
 						   &dma_addr);
 		if (ret) {
@@ -2359,7 +2326,6 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off,
 		ops->clear_present(&m);
 	}
 
-out:
 	ggtt_set_guest_entry(ggtt_mm, &e, g_gtt_index);
 
 	ggtt_get_host_entry(ggtt_mm, &e, g_gtt_index);

From adc7b226b7d675d011fe86447a5a36b932f1b061 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:09 -0700
Subject: [PATCH 0859/1189] drm/i915/gvt: Verify hugepages are contiguous in
 physical address space

When shadowing a GTT entry with a 2M page, verify that the pfns are
contiguous, not just that the struct page pointers are contiguous.  The
memory map is virtual contiguous if "CONFIG_FLATMEM=y ||
CONFIG_SPARSEMEM_VMEMMAP=y", but not for "CONFIG_SPARSEMEM=y &&
CONFIG_SPARSEMEM_VMEMMAP=n", so theoretically KVMGT could encounter struct
pages that are virtually contiguous, but not physically contiguous.

In practice, this flaw is likely a non-issue as it would cause functional
problems iff a section isn't 2M aligned _and_ is directly adjacent to
another section with discontiguous pfns.

Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Reviewed-by: Zhi Wang <zhi.a.wang@intel.com>
Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-4-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 drivers/gpu/drm/i915/gvt/kvmgt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index de675d799c7d..429f0f993a13 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -161,7 +161,7 @@ static int gvt_pin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn,
 
 		if (npage == 0)
 			base_page = cur_page;
-		else if (base_page + npage != cur_page) {
+		else if (page_to_pfn(base_page) + npage != page_to_pfn(cur_page)) {
 			gvt_vgpu_err("The pages are not continuous\n");
 			ret = -EINVAL;
 			npage++;

From a15e61f3371b35b7db2d7890fdc68e5f7678e49f Mon Sep 17 00:00:00 2001
From: Yan Zhao <yan.y.zhao@intel.com>
Date: Fri, 28 Jul 2023 18:35:10 -0700
Subject: [PATCH 0860/1189] drm/i915/gvt: Don't try to unpin an empty page
 range

Attempt to unpin pages in the error path of gvt_pin_guest_page() if and
only if at least one page was successfully pinned.  Unpinning doesn't
cause functional problems, but vfio_device_container_unpin_pages()
rightfully warns about being asked to unpin zero pages.

Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
[sean: write changelog]
Reviewed-by: Zhi Wang <zhi.a.wang@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-5-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 drivers/gpu/drm/i915/gvt/kvmgt.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index 429f0f993a13..0366a699baf5 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -172,7 +172,8 @@ static int gvt_pin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn,
 	*page = base_page;
 	return 0;
 err:
-	gvt_unpin_guest_page(vgpu, gfn, npage * PAGE_SIZE);
+	if (npage)
+		gvt_unpin_guest_page(vgpu, gfn, npage * PAGE_SIZE);
 	return ret;
 }
 

From 708e49583d7da863898b25dafe4bcd799c414278 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:11 -0700
Subject: [PATCH 0861/1189] drm/i915/gvt: Put the page reference obtained by
 KVM's gfn_to_pfn()

Put the struct page reference acquired by gfn_to_pfn(), KVM's API is that
the caller is ultimately responsible for dropping any reference.

Note, kvm_release_pfn_clean() ensures the pfn is actually a refcounted
struct page before trying to put any references.

Fixes: b901b252b6cf ("drm/i915/gvt: Add 2M huge gtt support")
Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Reviewed-by: Zhi Wang <zhi.a.wang@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-6-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 drivers/gpu/drm/i915/gvt/gtt.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index f30922c55a0c..5426a27c1b71 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -1158,6 +1158,7 @@ static int is_2MB_gtt_possible(struct intel_vgpu *vgpu,
 {
 	const struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
 	kvm_pfn_t pfn;
+	int ret;
 
 	if (!HAS_PAGE_SIZES(vgpu->gvt->gt->i915, I915_GTT_PAGE_SIZE_2M))
 		return 0;
@@ -1171,7 +1172,9 @@ static int is_2MB_gtt_possible(struct intel_vgpu *vgpu,
 	if (!pfn_valid(pfn))
 		return -EINVAL;
 
-	return PageTransHuge(pfn_to_page(pfn));
+	ret = PageTransHuge(pfn_to_page(pfn));
+	kvm_release_pfn_clean(pfn);
+	return ret;
 }
 
 static int split_2MB_gtt_entry(struct intel_vgpu *vgpu,

From 96b138cd23e978cd0975d1f4d5709dae2e061fd1 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 3 Aug 2023 15:32:06 -0700
Subject: [PATCH 0862/1189] drm/i915/gvt: Explicitly check that vGPU is
 attached before shadowing

Move the check that a vGPU is attached from is_2MB_gtt_possible() all the
way up to shadow_ppgtt_mm() to avoid unnecessary work, and to make it more
obvious that a future cleanup of is_2MB_gtt_possible() isn't introducing a
bug.

is_2MB_gtt_possible() has only one caller, ppgtt_populate_shadow_entry(),
and all paths in ppgtt_populate_shadow_entry() eventually check for
attachment by way of intel_gvt_dma_map_guest_page().

And of the paths that lead to ppgtt_populate_shadow_entry(),
shadow_ppgtt_mm() is the only one that doesn't already check for
INTEL_VGPU_STATUS_ACTIVE or INTEL_VGPU_STATUS_ATTACHED.

  workload_thread() <= pick_next_workload() => INTEL_VGPU_STATUS_ACTIVE
  |
  -> dispatch_workload()
     |
     |-> prepare_workload()
         |
         -> intel_vgpu_sync_oos_pages()
         |  |
         |  |-> ppgtt_set_guest_page_sync()
         |      |
         |      |-> sync_oos_page()
         |          |
         |          |-> ppgtt_populate_shadow_entry()
         |
         |-> intel_vgpu_flush_post_shadow()
             |
  1:         |-> ppgtt_handle_guest_write_page_table()
                 |
                 |-> ppgtt_handle_guest_entry_add()
                     |
  2:                 | -> ppgtt_populate_spt_by_guest_entry()
                     |    |
                     |    |-> ppgtt_populate_spt()
                     |        |
                     |        |-> ppgtt_populate_shadow_entry()
                     |            |
                     |            |-> ppgtt_populate_spt_by_guest_entry() [see 2]
                     |
                     |-> ppgtt_populate_shadow_entry()

  kvmgt_page_track_write()  <= KVM callback => INTEL_VGPU_STATUS_ATTACHED
  |
  |-> intel_vgpu_page_track_handler()
      |
      |-> ppgtt_write_protection_handler()
          |
          |-> ppgtt_handle_guest_write_page_table_bytes()
              |
              |-> ppgtt_handle_guest_write_page_table() [see 1]

Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yan Zhao <yan.y.zhao@intel.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 drivers/gpu/drm/i915/gvt/gtt.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 5426a27c1b71..de6a484090d7 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -1163,8 +1163,6 @@ static int is_2MB_gtt_possible(struct intel_vgpu *vgpu,
 	if (!HAS_PAGE_SIZES(vgpu->gvt->gt->i915, I915_GTT_PAGE_SIZE_2M))
 		return 0;
 
-	if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
-		return -EINVAL;
 	pfn = gfn_to_pfn(vgpu->vfio_device.kvm, ops->get_pfn(entry));
 	if (is_error_noslot_pfn(pfn))
 		return -EINVAL;
@@ -1827,6 +1825,9 @@ static int shadow_ppgtt_mm(struct intel_vgpu_mm *mm)
 	if (mm->ppgtt_mm.shadowed)
 		return 0;
 
+	if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
+		return -EINVAL;
+
 	mm->ppgtt_mm.shadowed = true;
 
 	for (index = 0; index < ARRAY_SIZE(mm->ppgtt_mm.guest_pdps); index++) {

From 241f0aadb8577dd17fa521bf19ba7ae85dc33d41 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:13 -0700
Subject: [PATCH 0863/1189] drm/i915/gvt: Error out on an attempt to shadowing
 an unknown GTT entry type

Bail from ppgtt_populate_shadow_entry() if an unexpected GTT entry type
is encountered instead of subtly falling through to the common "direct
shadow" path.  Eliminating the default/error path's reliance on the common
handling will allow hoisting intel_gvt_dma_map_guest_page() into the case
statements so that the 2MiB case can try intel_gvt_dma_map_guest_page()
and fallback to splitting the entry on failure.

Reviewed-by: Zhi Wang <zhi.a.wang@intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-8-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 drivers/gpu/drm/i915/gvt/gtt.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index de6a484090d7..eab844dffb8c 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -1303,6 +1303,7 @@ static int ppgtt_populate_shadow_entry(struct intel_vgpu *vgpu,
 		return -EINVAL;
 	default:
 		GEM_BUG_ON(1);
+		return -EINVAL;
 	}
 
 	/* direct shadow */

From ba193f62c075768b475efbaec32481a20869813f Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:14 -0700
Subject: [PATCH 0864/1189] drm/i915/gvt: Don't rely on KVM's gfn_to_pfn() to
 query possible 2M GTT

Now that gvt_pin_guest_page() explicitly verifies the pinned PFN is a
transparent hugepage page, don't use KVM's gfn_to_pfn() to pre-check if a
2MiB GTT entry is possible and instead just try to map the GFN with a 2MiB
entry.  Using KVM to query pfn that is ultimately managed through VFIO is
odd, and KVM's gfn_to_pfn() is not intended for non-KVM consumption; it's
exported only because of KVM vendor modules (x86 and PPC).

Open code the check on 2MiB support instead of keeping
is_2MB_gtt_possible() around for a single line of code.

Move the call to intel_gvt_dma_map_guest_page() for a 4KiB entry into its
case statement, i.e. fork the common path into the 4KiB and 2MiB "direct"
shadow paths.  Keeping the call in the "common" path is arguably more in
the spirit of "one change per patch", but retaining the local "page_size"
variable is silly, i.e. the call site will be changed either way, and
jumping around the no-longer-common code is more subtle and rather odd,
i.e. would just need to be immediately cleaned up.

Drop the error message from gvt_pin_guest_page() when KVMGT attempts to
shadow a 2MiB guest page that isn't backed by a compatible hugepage in the
host.  Dropping the pre-check on a THP makes it much more likely that the
"error" will be encountered in normal operation.

Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Reviewed-by: Zhi Wang <zhi.a.wang@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-9-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 drivers/gpu/drm/i915/gvt/gtt.c   | 49 ++++++--------------------------
 drivers/gpu/drm/i915/gvt/kvmgt.c |  1 -
 2 files changed, 8 insertions(+), 42 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index eab844dffb8c..dc5ad590ad03 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -1145,36 +1145,6 @@ static inline void ppgtt_generate_shadow_entry(struct intel_gvt_gtt_entry *se,
 	ops->set_pfn(se, s->shadow_page.mfn);
 }
 
-/*
- * Check if can do 2M page
- * @vgpu: target vgpu
- * @entry: target pfn's gtt entry
- *
- * Return 1 if 2MB huge gtt shadowing is possible, 0 if miscondition,
- * negative if found err.
- */
-static int is_2MB_gtt_possible(struct intel_vgpu *vgpu,
-	struct intel_gvt_gtt_entry *entry)
-{
-	const struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
-	kvm_pfn_t pfn;
-	int ret;
-
-	if (!HAS_PAGE_SIZES(vgpu->gvt->gt->i915, I915_GTT_PAGE_SIZE_2M))
-		return 0;
-
-	pfn = gfn_to_pfn(vgpu->vfio_device.kvm, ops->get_pfn(entry));
-	if (is_error_noslot_pfn(pfn))
-		return -EINVAL;
-
-	if (!pfn_valid(pfn))
-		return -EINVAL;
-
-	ret = PageTransHuge(pfn_to_page(pfn));
-	kvm_release_pfn_clean(pfn);
-	return ret;
-}
-
 static int split_2MB_gtt_entry(struct intel_vgpu *vgpu,
 	struct intel_vgpu_ppgtt_spt *spt, unsigned long index,
 	struct intel_gvt_gtt_entry *se)
@@ -1268,7 +1238,7 @@ static int ppgtt_populate_shadow_entry(struct intel_vgpu *vgpu,
 {
 	const struct intel_gvt_gtt_pte_ops *pte_ops = vgpu->gvt->gtt.pte_ops;
 	struct intel_gvt_gtt_entry se = *ge;
-	unsigned long gfn, page_size = PAGE_SIZE;
+	unsigned long gfn;
 	dma_addr_t dma_addr;
 	int ret;
 
@@ -1280,6 +1250,9 @@ static int ppgtt_populate_shadow_entry(struct intel_vgpu *vgpu,
 	switch (ge->type) {
 	case GTT_TYPE_PPGTT_PTE_4K_ENTRY:
 		gvt_vdbg_mm("shadow 4K gtt entry\n");
+		ret = intel_gvt_dma_map_guest_page(vgpu, gfn, PAGE_SIZE, &dma_addr);
+		if (ret)
+			return -ENXIO;
 		break;
 	case GTT_TYPE_PPGTT_PTE_64K_ENTRY:
 		gvt_vdbg_mm("shadow 64K gtt entry\n");
@@ -1291,12 +1264,10 @@ static int ppgtt_populate_shadow_entry(struct intel_vgpu *vgpu,
 		return split_64KB_gtt_entry(vgpu, spt, index, &se);
 	case GTT_TYPE_PPGTT_PTE_2M_ENTRY:
 		gvt_vdbg_mm("shadow 2M gtt entry\n");
-		ret = is_2MB_gtt_possible(vgpu, ge);
-		if (ret == 0)
+		if (!HAS_PAGE_SIZES(vgpu->gvt->gt->i915, I915_GTT_PAGE_SIZE_2M) ||
+		    intel_gvt_dma_map_guest_page(vgpu, gfn,
+						 I915_GTT_PAGE_SIZE_2M, &dma_addr))
 			return split_2MB_gtt_entry(vgpu, spt, index, &se);
-		else if (ret < 0)
-			return ret;
-		page_size = I915_GTT_PAGE_SIZE_2M;
 		break;
 	case GTT_TYPE_PPGTT_PTE_1G_ENTRY:
 		gvt_vgpu_err("GVT doesn't support 1GB entry\n");
@@ -1306,11 +1277,7 @@ static int ppgtt_populate_shadow_entry(struct intel_vgpu *vgpu,
 		return -EINVAL;
 	}
 
-	/* direct shadow */
-	ret = intel_gvt_dma_map_guest_page(vgpu, gfn, page_size, &dma_addr);
-	if (ret)
-		return -ENXIO;
-
+	/* Successfully shadowed a 4K or 2M page (without splitting). */
 	pte_ops->set_pfn(&se, dma_addr >> PAGE_SHIFT);
 	ppgtt_set_shadow_entry(spt, &se, index);
 	return 0;
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index 0366a699baf5..97c6d3c53710 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -162,7 +162,6 @@ static int gvt_pin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn,
 		if (npage == 0)
 			base_page = cur_page;
 		else if (page_to_pfn(base_page) + npage != page_to_pfn(cur_page)) {
-			gvt_vgpu_err("The pages are not continuous\n");
 			ret = -EINVAL;
 			npage++;
 			goto err;

From 16735297fdce2c7952dbe23288aad0d327fc444b Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:15 -0700
Subject: [PATCH 0865/1189] drm/i915/gvt: Use an "unsigned long" to iterate
 over memslot gfns

Use an "unsigned long" instead of an "int" when iterating over the gfns
in a memslot.  The number of pages in the memslot is tracked as an
"unsigned long", e.g. KVMGT could theoretically break if a KVM memslot
larger than 16TiB were deleted (2^32 * 4KiB).

Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Reviewed-by: Zhi Wang <zhi.a.wang@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-10-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 drivers/gpu/drm/i915/gvt/kvmgt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index 97c6d3c53710..6f52886c4051 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -1620,7 +1620,7 @@ static void kvmgt_page_track_flush_slot(struct kvm *kvm,
 		struct kvm_memory_slot *slot,
 		struct kvm_page_track_notifier_node *node)
 {
-	int i;
+	unsigned long i;
 	gfn_t gfn;
 	struct intel_vgpu *info =
 		container_of(node, struct intel_vgpu, track_node);

From a90c367e5af63880008e21dd199dac839e0e9e0f Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:16 -0700
Subject: [PATCH 0866/1189] drm/i915/gvt: Drop unused helper
 intel_vgpu_reset_gtt()

Drop intel_vgpu_reset_gtt() as it no longer has any callers.  In addition
to eliminating dead code, this eliminates the last possible scenario where
__kvmgt_protect_table_find() can be reached without holding vgpu_lock.
Requiring vgpu_lock to be held when calling __kvmgt_protect_table_find()
will allow a protecting the gfn hash with vgpu_lock without too much fuss.

No functional change intended.

Fixes: ba25d977571e ("drm/i915/gvt: Do not destroy ppgtt_mm during vGPU D3->D0.")
Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Reviewed-by: Zhi Wang <zhi.a.wang@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-11-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 drivers/gpu/drm/i915/gvt/gtt.c | 18 ------------------
 drivers/gpu/drm/i915/gvt/gtt.h |  1 -
 2 files changed, 19 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index dc5ad590ad03..094fca9b0e73 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -2817,24 +2817,6 @@ void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu, bool invalidate_old)
 	ggtt_invalidate(gvt->gt);
 }
 
-/**
- * intel_vgpu_reset_gtt - reset the all GTT related status
- * @vgpu: a vGPU
- *
- * This function is called from vfio core to reset reset all
- * GTT related status, including GGTT, PPGTT, scratch page.
- *
- */
-void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu)
-{
-	/* Shadow pages are only created when there is no page
-	 * table tracking data, so remove page tracking data after
-	 * removing the shadow pages.
-	 */
-	intel_vgpu_destroy_all_ppgtt_mm(vgpu);
-	intel_vgpu_reset_ggtt(vgpu, true);
-}
-
 /**
  * intel_gvt_restore_ggtt - restore all vGPU's ggtt entries
  * @gvt: intel gvt device
diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h
index a3b0f59ec8bd..4cb183e06e95 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.h
+++ b/drivers/gpu/drm/i915/gvt/gtt.h
@@ -224,7 +224,6 @@ void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu, bool invalidate_old);
 void intel_vgpu_invalidate_ppgtt(struct intel_vgpu *vgpu);
 
 int intel_gvt_init_gtt(struct intel_gvt *gvt);
-void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu);
 void intel_gvt_clean_gtt(struct intel_gvt *gvt);
 
 struct intel_vgpu_mm *intel_gvt_find_ppgtt_mm(struct intel_vgpu *vgpu,

From 3cca6b262876d30aae423431e8392d8b97b044fd Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:17 -0700
Subject: [PATCH 0867/1189] drm/i915/gvt: Protect gfn hash table with vgpu_lock

Use vgpu_lock instead of KVM's mmu_lock to protect accesses to the hash
table used to track which gfns are write-protected when shadowing the
guest's GTT, and hoist the acquisition of vgpu_lock from
intel_vgpu_page_track_handler() out to its sole caller,
kvmgt_page_track_write().

This fixes a bug where kvmgt_page_track_write(), which doesn't hold
kvm->mmu_lock, could race with intel_gvt_page_track_remove() and trigger
a use-after-free.

Fixing kvmgt_page_track_write() by taking kvm->mmu_lock is not an option
as mmu_lock is a r/w spinlock, and intel_vgpu_page_track_handler() might
sleep when acquiring vgpu->cache_lock deep down the callstack:

  intel_vgpu_page_track_handler()
  |
  |->  page_track->handler / ppgtt_write_protection_handler()
       |
       |-> ppgtt_handle_guest_write_page_table_bytes()
           |
           |->  ppgtt_handle_guest_write_page_table()
                |
                |-> ppgtt_handle_guest_entry_removal()
                    |
                    |-> ppgtt_invalidate_pte()
                        |
                        |-> intel_gvt_dma_unmap_guest_page()
                            |
                            |-> mutex_lock(&vgpu->cache_lock);

Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Reviewed-by: Zhi Wang <zhi.a.wang@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-12-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 drivers/gpu/drm/i915/gvt/kvmgt.c      | 39 ++++++++++++++++-----------
 drivers/gpu/drm/i915/gvt/page_track.c | 10 ++-----
 2 files changed, 25 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index 6f52886c4051..034be0655daa 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -352,6 +352,8 @@ __kvmgt_protect_table_find(struct intel_vgpu *info, gfn_t gfn)
 {
 	struct kvmgt_pgfn *p, *res = NULL;
 
+	lockdep_assert_held(&info->vgpu_lock);
+
 	hash_for_each_possible(info->ptable, p, hnode, gfn) {
 		if (gfn == p->gfn) {
 			res = p;
@@ -1553,6 +1555,9 @@ int intel_gvt_page_track_add(struct intel_vgpu *info, u64 gfn)
 	if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, info->status))
 		return -ESRCH;
 
+	if (kvmgt_gfn_is_write_protected(info, gfn))
+		return 0;
+
 	idx = srcu_read_lock(&kvm->srcu);
 	slot = gfn_to_memslot(kvm, gfn);
 	if (!slot) {
@@ -1561,16 +1566,12 @@ int intel_gvt_page_track_add(struct intel_vgpu *info, u64 gfn)
 	}
 
 	write_lock(&kvm->mmu_lock);
-
-	if (kvmgt_gfn_is_write_protected(info, gfn))
-		goto out;
-
 	kvm_slot_page_track_add_page(kvm, slot, gfn, KVM_PAGE_TRACK_WRITE);
-	kvmgt_protect_table_add(info, gfn);
-
-out:
 	write_unlock(&kvm->mmu_lock);
+
 	srcu_read_unlock(&kvm->srcu, idx);
+
+	kvmgt_protect_table_add(info, gfn);
 	return 0;
 }
 
@@ -1583,6 +1584,9 @@ int intel_gvt_page_track_remove(struct intel_vgpu *info, u64 gfn)
 	if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, info->status))
 		return -ESRCH;
 
+	if (!kvmgt_gfn_is_write_protected(info, gfn))
+		return 0;
+
 	idx = srcu_read_lock(&kvm->srcu);
 	slot = gfn_to_memslot(kvm, gfn);
 	if (!slot) {
@@ -1591,16 +1595,11 @@ int intel_gvt_page_track_remove(struct intel_vgpu *info, u64 gfn)
 	}
 
 	write_lock(&kvm->mmu_lock);
-
-	if (!kvmgt_gfn_is_write_protected(info, gfn))
-		goto out;
-
 	kvm_slot_page_track_remove_page(kvm, slot, gfn, KVM_PAGE_TRACK_WRITE);
-	kvmgt_protect_table_del(info, gfn);
-
-out:
 	write_unlock(&kvm->mmu_lock);
 	srcu_read_unlock(&kvm->srcu, idx);
+
+	kvmgt_protect_table_del(info, gfn);
 	return 0;
 }
 
@@ -1611,9 +1610,13 @@ static void kvmgt_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	struct intel_vgpu *info =
 		container_of(node, struct intel_vgpu, track_node);
 
+	mutex_lock(&info->vgpu_lock);
+
 	if (kvmgt_gfn_is_write_protected(info, gpa_to_gfn(gpa)))
 		intel_vgpu_page_track_handler(info, gpa,
 						     (void *)val, len);
+
+	mutex_unlock(&info->vgpu_lock);
 }
 
 static void kvmgt_page_track_flush_slot(struct kvm *kvm,
@@ -1625,16 +1628,20 @@ static void kvmgt_page_track_flush_slot(struct kvm *kvm,
 	struct intel_vgpu *info =
 		container_of(node, struct intel_vgpu, track_node);
 
-	write_lock(&kvm->mmu_lock);
+	mutex_lock(&info->vgpu_lock);
+
 	for (i = 0; i < slot->npages; i++) {
 		gfn = slot->base_gfn + i;
 		if (kvmgt_gfn_is_write_protected(info, gfn)) {
+			write_lock(&kvm->mmu_lock);
 			kvm_slot_page_track_remove_page(kvm, slot, gfn,
 						KVM_PAGE_TRACK_WRITE);
+			write_unlock(&kvm->mmu_lock);
+
 			kvmgt_protect_table_del(info, gfn);
 		}
 	}
-	write_unlock(&kvm->mmu_lock);
+	mutex_unlock(&info->vgpu_lock);
 }
 
 void intel_vgpu_detach_regions(struct intel_vgpu *vgpu)
diff --git a/drivers/gpu/drm/i915/gvt/page_track.c b/drivers/gpu/drm/i915/gvt/page_track.c
index df34e73cba41..60a65435556d 100644
--- a/drivers/gpu/drm/i915/gvt/page_track.c
+++ b/drivers/gpu/drm/i915/gvt/page_track.c
@@ -162,13 +162,9 @@ int intel_vgpu_page_track_handler(struct intel_vgpu *vgpu, u64 gpa,
 	struct intel_vgpu_page_track *page_track;
 	int ret = 0;
 
-	mutex_lock(&vgpu->vgpu_lock);
-
 	page_track = intel_vgpu_find_page_track(vgpu, gpa >> PAGE_SHIFT);
-	if (!page_track) {
-		ret = -ENXIO;
-		goto out;
-	}
+	if (!page_track)
+		return -ENXIO;
 
 	if (unlikely(vgpu->failsafe)) {
 		/* Remove write protection to prevent furture traps. */
@@ -179,7 +175,5 @@ int intel_vgpu_page_track_handler(struct intel_vgpu *vgpu, u64 gpa,
 			gvt_err("guest page write error, gpa %llx\n", gpa);
 	}
 
-out:
-	mutex_unlock(&vgpu->vgpu_lock);
 	return ret;
 }

From db0d70e61082a71e32147733ac082030cdbff0af Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:18 -0700
Subject: [PATCH 0868/1189] KVM: x86/mmu: Move
 kvm_arch_flush_shadow_{all,memslot}() to mmu.c

Move x86's implementation of kvm_arch_flush_shadow_{all,memslot}() into
mmu.c, and make kvm_mmu_zap_all() static as it was globally visible only
for kvm_arch_flush_shadow_all().  This will allow refactoring
kvm_arch_flush_shadow_memslot() to call kvm_mmu_zap_all() directly without
having to expose kvm_mmu_zap_all_fast() outside of mmu.c.  Keeping
everything in mmu.c will also likely simplify supporting TDX, which
intends to do zap only relevant SPTEs on memslot updates.

No functional change intended.

Suggested-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-13-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_host.h |  1 -
 arch/x86/kvm/mmu/mmu.c          | 13 ++++++++++++-
 arch/x86/kvm/x86.c              | 11 -----------
 3 files changed, 12 insertions(+), 13 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index e3c9ff4146fc..9e76c910e52c 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1853,7 +1853,6 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
 				   const struct kvm_memory_slot *memslot);
 void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
 				   const struct kvm_memory_slot *memslot);
-void kvm_mmu_zap_all(struct kvm *kvm);
 void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen);
 void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages);
 
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 0420944da242..acb99a9c41ba 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -6678,7 +6678,7 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
 	 */
 }
 
-void kvm_mmu_zap_all(struct kvm *kvm)
+static void kvm_mmu_zap_all(struct kvm *kvm)
 {
 	struct kvm_mmu_page *sp, *node;
 	LIST_HEAD(invalid_list);
@@ -6703,6 +6703,17 @@ restart:
 	write_unlock(&kvm->mmu_lock);
 }
 
+void kvm_arch_flush_shadow_all(struct kvm *kvm)
+{
+	kvm_mmu_zap_all(kvm);
+}
+
+void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
+				   struct kvm_memory_slot *slot)
+{
+	kvm_page_track_flush_slot(kvm, slot);
+}
+
 void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen)
 {
 	WARN_ON_ONCE(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0b38a046690e..36f0ba21661d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12802,17 +12802,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 		kvm_arch_free_memslot(kvm, old);
 }
 
-void kvm_arch_flush_shadow_all(struct kvm *kvm)
-{
-	kvm_mmu_zap_all(kvm);
-}
-
-void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
-				   struct kvm_memory_slot *slot)
-{
-	kvm_page_track_flush_slot(kvm, slot);
-}
-
 static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
 {
 	return (is_guest_mode(vcpu) &&

From eeb87272a364311dbfe1b10dd896c3e09a02cd03 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:19 -0700
Subject: [PATCH 0869/1189] KVM: x86/mmu: Don't rely on page-track mechanism to
 flush on memslot change

Call kvm_mmu_zap_all_fast() directly when flushing a memslot instead of
bouncing through the page-track mechanism.  KVM (unfortunately) needs to
zap and flush all page tables on memslot DELETE/MOVE irrespective of
whether KVM is shadowing guest page tables.

This will allow changing KVM to register a page-track notifier on the
first shadow root allocation, and will also allow deleting the misguided
kvm_page_track_flush_slot() hook itself once KVM-GT also moves to a
different method for reacting to memslot changes.

No functional change intended.

Cc: Yan Zhao <yan.y.zhao@intel.com>
Link: https://lore.kernel.org/r/20221110014821.1548347-2-seanjc@google.com
Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-14-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index acb99a9c41ba..eabd5b13970d 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -6159,13 +6159,6 @@ static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm)
 	return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages));
 }
 
-static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm,
-			struct kvm_memory_slot *slot,
-			struct kvm_page_track_notifier_node *node)
-{
-	kvm_mmu_zap_all_fast(kvm);
-}
-
 int kvm_mmu_init_vm(struct kvm *kvm)
 {
 	struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
@@ -6183,7 +6176,6 @@ int kvm_mmu_init_vm(struct kvm *kvm)
 	}
 
 	node->track_write = kvm_mmu_pte_write;
-	node->track_flush_slot = kvm_mmu_invalidate_zap_pages_in_memslot;
 	kvm_page_track_register_notifier(kvm, node);
 
 	kvm->arch.split_page_header_cache.kmem_cache = mmu_page_header_cache;
@@ -6711,6 +6703,8 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm)
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 				   struct kvm_memory_slot *slot)
 {
+	kvm_mmu_zap_all_fast(kvm);
+
 	kvm_page_track_flush_slot(kvm, slot);
 }
 

From 932844462ae310493d0d21b1c5d7464d59702b4d Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:20 -0700
Subject: [PATCH 0870/1189] KVM: x86/mmu: Don't bounce through page-track
 mechanism for guest PTEs

Don't use the generic page-track mechanism to handle writes to guest PTEs
in KVM's MMU.  KVM's MMU needs access to information that should not be
exposed to external page-track users, e.g. KVM needs (for some definitions
of "need") the vCPU to query the current paging mode, whereas external
users, i.e. KVMGT, have no ties to the current vCPU and so should never
need the vCPU.

Moving away from the page-track mechanism will allow dropping use of the
page-track mechanism for KVM's own MMU, and will also allow simplifying
and cleaning up the page-track APIs.

Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-15-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_host.h |  1 -
 arch/x86/kvm/mmu.h              |  2 ++
 arch/x86/kvm/mmu/mmu.c          | 13 ++-----------
 arch/x86/kvm/mmu/page_track.c   |  2 ++
 4 files changed, 6 insertions(+), 12 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 9e76c910e52c..93fdc42458cc 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1265,7 +1265,6 @@ struct kvm_arch {
 	 * create an NX huge page (without hanging the guest).
 	 */
 	struct list_head possible_nx_huge_pages;
-	struct kvm_page_track_notifier_node mmu_sp_tracker;
 	struct kvm_page_track_notifier_head track_notifier_head;
 	/*
 	 * Protects marking pages unsync during page faults, as TDP MMU page
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 92d5a1924fc1..253fb2093d5d 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -121,6 +121,8 @@ void kvm_mmu_unload(struct kvm_vcpu *vcpu);
 void kvm_mmu_free_obsolete_roots(struct kvm_vcpu *vcpu);
 void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu);
 void kvm_mmu_sync_prev_roots(struct kvm_vcpu *vcpu);
+void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
+			 int bytes);
 
 static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu)
 {
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index eabd5b13970d..28385642eb98 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5635,9 +5635,8 @@ static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte)
 	return spte;
 }
 
-static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
-			      const u8 *new, int bytes,
-			      struct kvm_page_track_notifier_node *node)
+void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
+			 int bytes)
 {
 	gfn_t gfn = gpa >> PAGE_SHIFT;
 	struct kvm_mmu_page *sp;
@@ -6161,7 +6160,6 @@ static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm)
 
 int kvm_mmu_init_vm(struct kvm *kvm)
 {
-	struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
 	int r;
 
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
@@ -6175,9 +6173,6 @@ int kvm_mmu_init_vm(struct kvm *kvm)
 			return r;
 	}
 
-	node->track_write = kvm_mmu_pte_write;
-	kvm_page_track_register_notifier(kvm, node);
-
 	kvm->arch.split_page_header_cache.kmem_cache = mmu_page_header_cache;
 	kvm->arch.split_page_header_cache.gfp_zero = __GFP_ZERO;
 
@@ -6198,10 +6193,6 @@ static void mmu_free_vm_memory_caches(struct kvm *kvm)
 
 void kvm_mmu_uninit_vm(struct kvm *kvm)
 {
-	struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
-
-	kvm_page_track_unregister_notifier(kvm, node);
-
 	if (tdp_mmu_enabled)
 		kvm_mmu_uninit_tdp_mmu(kvm);
 
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index fd16918b3a7a..bca0994ea157 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -274,6 +274,8 @@ void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
 		if (n->track_write)
 			n->track_write(vcpu, gpa, new, bytes, n);
 	srcu_read_unlock(&head->track_srcu, idx);
+
+	kvm_mmu_track_write(vcpu, gpa, new, bytes);
 }
 
 /*

From b271e17defb07560399734c7aefbdd0fc961c601 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:21 -0700
Subject: [PATCH 0871/1189] KVM: drm/i915/gvt: Drop @vcpu from KVM's
 ->track_write() hook

Drop @vcpu from KVM's ->track_write() hook provided for external users of
the page-track APIs now that KVM itself doesn't use the page-track
mechanism.

Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Reviewed-by: Zhi Wang <zhi.a.wang@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-16-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_page_track.h |  5 ++---
 arch/x86/kvm/mmu/page_track.c         |  2 +-
 drivers/gpu/drm/i915/gvt/kvmgt.c      | 10 ++++------
 3 files changed, 7 insertions(+), 10 deletions(-)

diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
index eb186bc57f6a..8c4d216e3b2b 100644
--- a/arch/x86/include/asm/kvm_page_track.h
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -26,14 +26,13 @@ struct kvm_page_track_notifier_node {
 	 * It is called when guest is writing the write-tracked page
 	 * and write emulation is finished at that time.
 	 *
-	 * @vcpu: the vcpu where the write access happened.
 	 * @gpa: the physical address written by guest.
 	 * @new: the data was written to the address.
 	 * @bytes: the written length.
 	 * @node: this node
 	 */
-	void (*track_write)(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
-			    int bytes, struct kvm_page_track_notifier_node *node);
+	void (*track_write)(gpa_t gpa, const u8 *new, int bytes,
+			    struct kvm_page_track_notifier_node *node);
 	/*
 	 * It is called when memory slot is being moved or removed
 	 * users can drop write-protection for the pages in that memory slot
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index bca0994ea157..772be81f97cc 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -272,7 +272,7 @@ void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
 	hlist_for_each_entry_srcu(n, &head->track_notifier_list, node,
 				srcu_read_lock_held(&head->track_srcu))
 		if (n->track_write)
-			n->track_write(vcpu, gpa, new, bytes, n);
+			n->track_write(gpa, new, bytes, n);
 	srcu_read_unlock(&head->track_srcu, idx);
 
 	kvm_mmu_track_write(vcpu, gpa, new, bytes);
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index 034be0655daa..e9276500435d 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -106,9 +106,8 @@ struct gvt_dma {
 #define vfio_dev_to_vgpu(vfio_dev) \
 	container_of((vfio_dev), struct intel_vgpu, vfio_device)
 
-static void kvmgt_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa,
-		const u8 *val, int len,
-		struct kvm_page_track_notifier_node *node);
+static void kvmgt_page_track_write(gpa_t gpa, const u8 *val, int len,
+				   struct kvm_page_track_notifier_node *node);
 static void kvmgt_page_track_flush_slot(struct kvm *kvm,
 		struct kvm_memory_slot *slot,
 		struct kvm_page_track_notifier_node *node);
@@ -1603,9 +1602,8 @@ int intel_gvt_page_track_remove(struct intel_vgpu *info, u64 gfn)
 	return 0;
 }
 
-static void kvmgt_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa,
-		const u8 *val, int len,
-		struct kvm_page_track_notifier_node *node)
+static void kvmgt_page_track_write(gpa_t gpa, const u8 *val, int len,
+				   struct kvm_page_track_notifier_node *node)
 {
 	struct intel_vgpu *info =
 		container_of(node, struct intel_vgpu, track_node);

From c70934e0ab2d2c4bb16bf70c3e3db8c064a1761b Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:22 -0700
Subject: [PATCH 0872/1189] KVM: x86: Reject memslot MOVE operations if KVMGT
 is attached

Disallow moving memslots if the VM has external page-track users, i.e. if
KVMGT is being used to expose a virtual GPU to the guest, as KVMGT doesn't
correctly handle moving memory regions.

Note, this is potential ABI breakage!  E.g. userspace could move regions
that aren't shadowed by KVMGT without harming the guest.  However, the
only known user of KVMGT is QEMU, and QEMU doesn't move generic memory
regions.  KVM's own support for moving memory regions was also broken for
multiple years (albeit for an edge case, but arguably moving RAM is
itself an edge case), e.g. see commit edd4fa37baa6 ("KVM: x86: Allocate
new rmap and large page tracking when moving memslot").

Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-17-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_page_track.h | 3 +++
 arch/x86/kvm/mmu/page_track.c         | 5 +++++
 arch/x86/kvm/x86.c                    | 7 +++++++
 3 files changed, 15 insertions(+)

diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
index 8c4d216e3b2b..f744682648e7 100644
--- a/arch/x86/include/asm/kvm_page_track.h
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -75,4 +75,7 @@ kvm_page_track_unregister_notifier(struct kvm *kvm,
 void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
 			  int bytes);
 void kvm_page_track_flush_slot(struct kvm *kvm, struct kvm_memory_slot *slot);
+
+bool kvm_page_track_has_external_user(struct kvm *kvm);
+
 #endif
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index 772be81f97cc..cfd0b8092d06 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -303,3 +303,8 @@ void kvm_page_track_flush_slot(struct kvm *kvm, struct kvm_memory_slot *slot)
 			n->track_flush_slot(kvm, slot, n);
 	srcu_read_unlock(&head->track_srcu, idx);
 }
+
+bool kvm_page_track_has_external_user(struct kvm *kvm)
+{
+	return !hlist_empty(&kvm->arch.track_notifier_head.track_notifier_list);
+}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 36f0ba21661d..161e97e6caa9 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12632,6 +12632,13 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				   struct kvm_memory_slot *new,
 				   enum kvm_mr_change change)
 {
+	/*
+	 * KVM doesn't support moving memslots when there are external page
+	 * trackers attached to the VM, i.e. if KVMGT is in use.
+	 */
+	if (change == KVM_MR_MOVE && kvm_page_track_has_external_user(kvm))
+		return -EINVAL;
+
 	if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) {
 		if ((new->base_gfn + new->npages - 1) > kvm_mmu_max_gfn())
 			return -EINVAL;

From 2ee05a4c275a54d9b64599bcbf7117a9490c9e43 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:23 -0700
Subject: [PATCH 0873/1189] drm/i915/gvt: Don't bother removing
 write-protection on to-be-deleted slot

When handling a slot "flush", don't call back into KVM to drop write
protection for gfns in the slot.  Now that KVM rejects attempts to move
memory slots while KVMGT is attached, the only time a slot is "flushed"
is when it's being removed, i.e. the memslot and all its write-tracking
metadata is about to be deleted.

Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Reviewed-by: Zhi Wang <zhi.a.wang@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-18-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 drivers/gpu/drm/i915/gvt/kvmgt.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index e9276500435d..3ea3cb9eb599 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -1630,14 +1630,8 @@ static void kvmgt_page_track_flush_slot(struct kvm *kvm,
 
 	for (i = 0; i < slot->npages; i++) {
 		gfn = slot->base_gfn + i;
-		if (kvmgt_gfn_is_write_protected(info, gfn)) {
-			write_lock(&kvm->mmu_lock);
-			kvm_slot_page_track_remove_page(kvm, slot, gfn,
-						KVM_PAGE_TRACK_WRITE);
-			write_unlock(&kvm->mmu_lock);
-
+		if (kvmgt_gfn_is_write_protected(info, gfn))
 			kvmgt_protect_table_del(info, gfn);
-		}
 	}
 	mutex_unlock(&info->vgpu_lock);
 }

From b83ab124ded3c17f911668522a2e916ca8d3c523 Mon Sep 17 00:00:00 2001
From: Yan Zhao <yan.y.zhao@intel.com>
Date: Fri, 28 Jul 2023 18:35:24 -0700
Subject: [PATCH 0874/1189] KVM: x86: Add a new page-track hook to handle
 memslot deletion

Add a new page-track hook, track_remove_region(), that is called when a
memslot DELETE operation is about to be committed.  The "remove" hook
will be used by KVMGT and will effectively replace the existing
track_flush_slot() altogether now that KVM itself doesn't rely on the
"flush" hook either.

The "flush" hook is flawed as it's invoked before the memslot operation
is guaranteed to succeed, i.e. KVM might ultimately keep the existing
memslot without notifying external page track users, a.k.a. KVMGT.  In
practice, this can't currently happen on x86, but there are no guarantees
that won't change in the future, not to mention that "flush" does a very
poor job of describing what is happening.

Pass in the gfn+nr_pages instead of the slot itself so external users,
i.e. KVMGT, don't need to exposed to KVM internals (memslots).  This will
help set the stage for additional cleanups to the page-track APIs.

Opportunistically align the existing srcu_read_lock_held() usage so that
the new case doesn't stand out like a sore thumb (and not aligning the
new code makes bots unhappy).

Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-19-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_page_track.h | 12 ++++++++++++
 arch/x86/kvm/mmu/page_track.c         | 27 +++++++++++++++++++++++++--
 arch/x86/kvm/x86.c                    |  3 +++
 3 files changed, 40 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
index f744682648e7..cfd36c22b467 100644
--- a/arch/x86/include/asm/kvm_page_track.h
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -43,6 +43,17 @@ struct kvm_page_track_notifier_node {
 	 */
 	void (*track_flush_slot)(struct kvm *kvm, struct kvm_memory_slot *slot,
 			    struct kvm_page_track_notifier_node *node);
+
+	/*
+	 * Invoked when a memory region is removed from the guest.  Or in KVM
+	 * terms, when a memslot is deleted.
+	 *
+	 * @gfn:       base gfn of the region being removed
+	 * @nr_pages:  number of pages in the to-be-removed region
+	 * @node:      this node
+	 */
+	void (*track_remove_region)(gfn_t gfn, unsigned long nr_pages,
+				    struct kvm_page_track_notifier_node *node);
 };
 
 int kvm_page_track_init(struct kvm *kvm);
@@ -75,6 +86,7 @@ kvm_page_track_unregister_notifier(struct kvm *kvm,
 void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
 			  int bytes);
 void kvm_page_track_flush_slot(struct kvm *kvm, struct kvm_memory_slot *slot);
+void kvm_page_track_delete_slot(struct kvm *kvm, struct kvm_memory_slot *slot);
 
 bool kvm_page_track_has_external_user(struct kvm *kvm);
 
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index cfd0b8092d06..640e383b5252 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -270,7 +270,7 @@ void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
 
 	idx = srcu_read_lock(&head->track_srcu);
 	hlist_for_each_entry_srcu(n, &head->track_notifier_list, node,
-				srcu_read_lock_held(&head->track_srcu))
+				  srcu_read_lock_held(&head->track_srcu))
 		if (n->track_write)
 			n->track_write(gpa, new, bytes, n);
 	srcu_read_unlock(&head->track_srcu, idx);
@@ -298,12 +298,35 @@ void kvm_page_track_flush_slot(struct kvm *kvm, struct kvm_memory_slot *slot)
 
 	idx = srcu_read_lock(&head->track_srcu);
 	hlist_for_each_entry_srcu(n, &head->track_notifier_list, node,
-				srcu_read_lock_held(&head->track_srcu))
+				  srcu_read_lock_held(&head->track_srcu))
 		if (n->track_flush_slot)
 			n->track_flush_slot(kvm, slot, n);
 	srcu_read_unlock(&head->track_srcu, idx);
 }
 
+/*
+ * Notify external page track nodes that a memory region is being removed from
+ * the VM, e.g. so that users can free any associated metadata.
+ */
+void kvm_page_track_delete_slot(struct kvm *kvm, struct kvm_memory_slot *slot)
+{
+	struct kvm_page_track_notifier_head *head;
+	struct kvm_page_track_notifier_node *n;
+	int idx;
+
+	head = &kvm->arch.track_notifier_head;
+
+	if (hlist_empty(&head->track_notifier_list))
+		return;
+
+	idx = srcu_read_lock(&head->track_srcu);
+	hlist_for_each_entry_srcu(n, &head->track_notifier_list, node,
+				  srcu_read_lock_held(&head->track_srcu))
+		if (n->track_remove_region)
+			n->track_remove_region(slot->base_gfn, slot->npages, n);
+	srcu_read_unlock(&head->track_srcu, idx);
+}
+
 bool kvm_page_track_has_external_user(struct kvm *kvm)
 {
 	return !hlist_empty(&kvm->arch.track_notifier_head.track_notifier_list);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 161e97e6caa9..792846447593 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12793,6 +12793,9 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 				const struct kvm_memory_slot *new,
 				enum kvm_mr_change change)
 {
+	if (change == KVM_MR_DELETE)
+		kvm_page_track_delete_slot(kvm, old);
+
 	if (!kvm->arch.n_requested_mmu_pages &&
 	    (change == KVM_MR_CREATE || change == KVM_MR_DELETE)) {
 		unsigned long nr_mmu_pages;

From c15fcf12ffb37be314752202fb02cf16138e66fb Mon Sep 17 00:00:00 2001
From: Yan Zhao <yan.y.zhao@intel.com>
Date: Fri, 28 Jul 2023 18:35:25 -0700
Subject: [PATCH 0875/1189] drm/i915/gvt: switch from ->track_flush_slot() to
 ->track_remove_region()

Switch from the poorly named and flawed ->track_flush_slot() to the newly
introduced ->track_remove_region().  From KVMGT's perspective, the two
hooks are functionally equivalent, the only difference being that
->track_remove_region() is called only when KVM is 100% certain the
memory region will be removed, i.e. is invoked slightly later in KVM's
memslot modification flow.

Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
[sean: handle name change, massage changelog, rebase]
Tested-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Reviewed-by: Zhi Wang <zhi.a.wang@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-20-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 drivers/gpu/drm/i915/gvt/kvmgt.c | 21 +++++++++------------
 1 file changed, 9 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index 3ea3cb9eb599..3f2327455d85 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -108,9 +108,8 @@ struct gvt_dma {
 
 static void kvmgt_page_track_write(gpa_t gpa, const u8 *val, int len,
 				   struct kvm_page_track_notifier_node *node);
-static void kvmgt_page_track_flush_slot(struct kvm *kvm,
-		struct kvm_memory_slot *slot,
-		struct kvm_page_track_notifier_node *node);
+static void kvmgt_page_track_remove_region(gfn_t gfn, unsigned long nr_pages,
+					   struct kvm_page_track_notifier_node *node);
 
 static ssize_t intel_vgpu_show_description(struct mdev_type *mtype, char *buf)
 {
@@ -666,7 +665,7 @@ static int intel_vgpu_open_device(struct vfio_device *vfio_dev)
 		return -EEXIST;
 
 	vgpu->track_node.track_write = kvmgt_page_track_write;
-	vgpu->track_node.track_flush_slot = kvmgt_page_track_flush_slot;
+	vgpu->track_node.track_remove_region = kvmgt_page_track_remove_region;
 	kvm_get_kvm(vgpu->vfio_device.kvm);
 	kvm_page_track_register_notifier(vgpu->vfio_device.kvm,
 					 &vgpu->track_node);
@@ -1617,22 +1616,20 @@ static void kvmgt_page_track_write(gpa_t gpa, const u8 *val, int len,
 	mutex_unlock(&info->vgpu_lock);
 }
 
-static void kvmgt_page_track_flush_slot(struct kvm *kvm,
-		struct kvm_memory_slot *slot,
-		struct kvm_page_track_notifier_node *node)
+static void kvmgt_page_track_remove_region(gfn_t gfn, unsigned long nr_pages,
+					   struct kvm_page_track_notifier_node *node)
 {
 	unsigned long i;
-	gfn_t gfn;
 	struct intel_vgpu *info =
 		container_of(node, struct intel_vgpu, track_node);
 
 	mutex_lock(&info->vgpu_lock);
 
-	for (i = 0; i < slot->npages; i++) {
-		gfn = slot->base_gfn + i;
-		if (kvmgt_gfn_is_write_protected(info, gfn))
-			kvmgt_protect_table_del(info, gfn);
+	for (i = 0; i < nr_pages; i++) {
+		if (kvmgt_gfn_is_write_protected(info, gfn + i))
+			kvmgt_protect_table_del(info, gfn + i);
 	}
+
 	mutex_unlock(&info->vgpu_lock);
 }
 

From d104d5bbbc2de62fafe0e391dbc7b1e99a58722e Mon Sep 17 00:00:00 2001
From: Yan Zhao <yan.y.zhao@intel.com>
Date: Fri, 28 Jul 2023 18:35:26 -0700
Subject: [PATCH 0876/1189] KVM: x86: Remove the unused page-track hook
 track_flush_slot()

Remove ->track_remove_slot(), there are no longer any users and it's
unlikely a "flush" hook will ever be the correct API to provide to an
external page-track user.

Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-21-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_page_track.h | 11 -----------
 arch/x86/kvm/mmu/mmu.c                |  2 --
 arch/x86/kvm/mmu/page_track.c         | 26 --------------------------
 3 files changed, 39 deletions(-)

diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
index cfd36c22b467..5c348ffdc194 100644
--- a/arch/x86/include/asm/kvm_page_track.h
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -33,16 +33,6 @@ struct kvm_page_track_notifier_node {
 	 */
 	void (*track_write)(gpa_t gpa, const u8 *new, int bytes,
 			    struct kvm_page_track_notifier_node *node);
-	/*
-	 * It is called when memory slot is being moved or removed
-	 * users can drop write-protection for the pages in that memory slot
-	 *
-	 * @kvm: the kvm where memory slot being moved or removed
-	 * @slot: the memory slot being moved or removed
-	 * @node: this node
-	 */
-	void (*track_flush_slot)(struct kvm *kvm, struct kvm_memory_slot *slot,
-			    struct kvm_page_track_notifier_node *node);
 
 	/*
 	 * Invoked when a memory region is removed from the guest.  Or in KVM
@@ -85,7 +75,6 @@ kvm_page_track_unregister_notifier(struct kvm *kvm,
 				   struct kvm_page_track_notifier_node *n);
 void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
 			  int bytes);
-void kvm_page_track_flush_slot(struct kvm *kvm, struct kvm_memory_slot *slot);
 void kvm_page_track_delete_slot(struct kvm *kvm, struct kvm_memory_slot *slot);
 
 bool kvm_page_track_has_external_user(struct kvm *kvm);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 28385642eb98..90a528dca883 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -6695,8 +6695,6 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 				   struct kvm_memory_slot *slot)
 {
 	kvm_mmu_zap_all_fast(kvm);
-
-	kvm_page_track_flush_slot(kvm, slot);
 }
 
 void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen)
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index 640e383b5252..98fb96357b84 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -278,32 +278,6 @@ void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
 	kvm_mmu_track_write(vcpu, gpa, new, bytes);
 }
 
-/*
- * Notify the node that memory slot is being removed or moved so that it can
- * drop write-protection for the pages in the memory slot.
- *
- * The node should figure out it has any write-protected pages in this slot
- * by itself.
- */
-void kvm_page_track_flush_slot(struct kvm *kvm, struct kvm_memory_slot *slot)
-{
-	struct kvm_page_track_notifier_head *head;
-	struct kvm_page_track_notifier_node *n;
-	int idx;
-
-	head = &kvm->arch.track_notifier_head;
-
-	if (hlist_empty(&head->track_notifier_list))
-		return;
-
-	idx = srcu_read_lock(&head->track_srcu);
-	hlist_for_each_entry_srcu(n, &head->track_notifier_list, node,
-				  srcu_read_lock_held(&head->track_srcu))
-		if (n->track_flush_slot)
-			n->track_flush_slot(kvm, slot, n);
-	srcu_read_unlock(&head->track_srcu, idx);
-}
-
 /*
  * Notify external page track nodes that a memory region is being removed from
  * the VM, e.g. so that users can free any associated metadata.

From 58ea7cf700cae441fd41d17e6f8092a4f9e2e32b Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:27 -0700
Subject: [PATCH 0877/1189] KVM: x86/mmu: Move KVM-only page-track declarations
 to internal header

Bury the declaration of the page-track helpers that are intended only for
internal KVM use in a "private" header.  In addition to guarding against
unwanted usage of the internal-only helpers, dropping their definitions
avoids exposing other structures that should be KVM-internal, e.g. for
memslots.  This is a baby step toward making kvm_host.h a KVM-internal
header in the very distant future.

Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-22-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_page_track.h | 21 ++---------------
 arch/x86/kvm/mmu/mmu.c                |  3 ++-
 arch/x86/kvm/mmu/page_track.c         |  8 +------
 arch/x86/kvm/mmu/page_track.h         | 33 +++++++++++++++++++++++++++
 arch/x86/kvm/x86.c                    |  1 +
 5 files changed, 39 insertions(+), 27 deletions(-)
 create mode 100644 arch/x86/kvm/mmu/page_track.h

diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
index 5c348ffdc194..76c0070dfe2a 100644
--- a/arch/x86/include/asm/kvm_page_track.h
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -2,6 +2,8 @@
 #ifndef _ASM_X86_KVM_PAGE_TRACK_H
 #define _ASM_X86_KVM_PAGE_TRACK_H
 
+#include <linux/kvm_types.h>
+
 enum kvm_page_track_mode {
 	KVM_PAGE_TRACK_WRITE,
 	KVM_PAGE_TRACK_MAX,
@@ -46,26 +48,12 @@ struct kvm_page_track_notifier_node {
 				    struct kvm_page_track_notifier_node *node);
 };
 
-int kvm_page_track_init(struct kvm *kvm);
-void kvm_page_track_cleanup(struct kvm *kvm);
-
-bool kvm_page_track_write_tracking_enabled(struct kvm *kvm);
-int kvm_page_track_write_tracking_alloc(struct kvm_memory_slot *slot);
-
-void kvm_page_track_free_memslot(struct kvm_memory_slot *slot);
-int kvm_page_track_create_memslot(struct kvm *kvm,
-				  struct kvm_memory_slot *slot,
-				  unsigned long npages);
-
 void kvm_slot_page_track_add_page(struct kvm *kvm,
 				  struct kvm_memory_slot *slot, gfn_t gfn,
 				  enum kvm_page_track_mode mode);
 void kvm_slot_page_track_remove_page(struct kvm *kvm,
 				     struct kvm_memory_slot *slot, gfn_t gfn,
 				     enum kvm_page_track_mode mode);
-bool kvm_slot_page_track_is_active(struct kvm *kvm,
-				   const struct kvm_memory_slot *slot,
-				   gfn_t gfn, enum kvm_page_track_mode mode);
 
 void
 kvm_page_track_register_notifier(struct kvm *kvm,
@@ -73,10 +61,5 @@ kvm_page_track_register_notifier(struct kvm *kvm,
 void
 kvm_page_track_unregister_notifier(struct kvm *kvm,
 				   struct kvm_page_track_notifier_node *n);
-void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
-			  int bytes);
-void kvm_page_track_delete_slot(struct kvm *kvm, struct kvm_memory_slot *slot);
-
-bool kvm_page_track_has_external_user(struct kvm *kvm);
 
 #endif
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 90a528dca883..14b5c74a9247 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -25,6 +25,7 @@
 #include "kvm_cache_regs.h"
 #include "smm.h"
 #include "kvm_emulate.h"
+#include "page_track.h"
 #include "cpuid.h"
 #include "spte.h"
 
@@ -53,7 +54,7 @@
 #include <asm/io.h>
 #include <asm/set_memory.h>
 #include <asm/vmx.h>
-#include <asm/kvm_page_track.h>
+
 #include "trace.h"
 
 extern bool itlb_multihit_kvm_mitigation;
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index 98fb96357b84..ba3261df9b63 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -15,10 +15,9 @@
 #include <linux/kvm_host.h>
 #include <linux/rculist.h>
 
-#include <asm/kvm_page_track.h>
-
 #include "mmu.h"
 #include "mmu_internal.h"
+#include "page_track.h"
 
 bool kvm_page_track_write_tracking_enabled(struct kvm *kvm)
 {
@@ -300,8 +299,3 @@ void kvm_page_track_delete_slot(struct kvm *kvm, struct kvm_memory_slot *slot)
 			n->track_remove_region(slot->base_gfn, slot->npages, n);
 	srcu_read_unlock(&head->track_srcu, idx);
 }
-
-bool kvm_page_track_has_external_user(struct kvm *kvm)
-{
-	return !hlist_empty(&kvm->arch.track_notifier_head.track_notifier_list);
-}
diff --git a/arch/x86/kvm/mmu/page_track.h b/arch/x86/kvm/mmu/page_track.h
new file mode 100644
index 000000000000..cc1c8094bd73
--- /dev/null
+++ b/arch/x86/kvm/mmu/page_track.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __KVM_X86_PAGE_TRACK_H
+#define __KVM_X86_PAGE_TRACK_H
+
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_page_track.h>
+
+int kvm_page_track_init(struct kvm *kvm);
+void kvm_page_track_cleanup(struct kvm *kvm);
+
+bool kvm_page_track_write_tracking_enabled(struct kvm *kvm);
+int kvm_page_track_write_tracking_alloc(struct kvm_memory_slot *slot);
+
+void kvm_page_track_free_memslot(struct kvm_memory_slot *slot);
+int kvm_page_track_create_memslot(struct kvm *kvm,
+				  struct kvm_memory_slot *slot,
+				  unsigned long npages);
+
+bool kvm_slot_page_track_is_active(struct kvm *kvm,
+				   const struct kvm_memory_slot *slot,
+				   gfn_t gfn, enum kvm_page_track_mode mode);
+
+void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
+			  int bytes);
+void kvm_page_track_delete_slot(struct kvm *kvm, struct kvm_memory_slot *slot);
+
+static inline bool kvm_page_track_has_external_user(struct kvm *kvm)
+{
+	return !hlist_empty(&kvm->arch.track_notifier_head.track_notifier_list);
+}
+
+#endif /* __KVM_X86_PAGE_TRACK_H */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 792846447593..6c9c81e82e65 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -25,6 +25,7 @@
 #include "tss.h"
 #include "kvm_cache_regs.h"
 #include "kvm_emulate.h"
+#include "mmu/page_track.h"
 #include "x86.h"
 #include "cpuid.h"
 #include "pmu.h"

From e998fb1a30131fdc7c734bc7422000b41146b631 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:28 -0700
Subject: [PATCH 0878/1189] KVM: x86/mmu: Use page-track notifiers iff there
 are external users

Disable the page-track notifier code at compile time if there are no
external users, i.e. if CONFIG_KVM_EXTERNAL_WRITE_TRACKING=n.  KVM itself
now hooks emulated writes directly instead of relying on the page-track
mechanism.

Provide a stub for "struct kvm_page_track_notifier_node" so that including
headers directly from the command line, e.g. for testing include guards,
doesn't fail due to a struct having an incomplete type.

Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-23-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_host.h       |  2 ++
 arch/x86/include/asm/kvm_page_track.h | 22 +++++++++++++-------
 arch/x86/kvm/mmu/page_track.c         | 10 ++++-----
 arch/x86/kvm/mmu/page_track.h         | 29 +++++++++++++++++++++++----
 4 files changed, 47 insertions(+), 16 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 93fdc42458cc..29ad3f0a126f 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1265,7 +1265,9 @@ struct kvm_arch {
 	 * create an NX huge page (without hanging the guest).
 	 */
 	struct list_head possible_nx_huge_pages;
+#ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING
 	struct kvm_page_track_notifier_head track_notifier_head;
+#endif
 	/*
 	 * Protects marking pages unsync during page faults, as TDP MMU page
 	 * faults only take mmu_lock for read.  For simplicity, the unsync
diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
index 76c0070dfe2a..61adb07b5927 100644
--- a/arch/x86/include/asm/kvm_page_track.h
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -9,6 +9,14 @@ enum kvm_page_track_mode {
 	KVM_PAGE_TRACK_MAX,
 };
 
+void kvm_slot_page_track_add_page(struct kvm *kvm,
+				  struct kvm_memory_slot *slot, gfn_t gfn,
+				  enum kvm_page_track_mode mode);
+void kvm_slot_page_track_remove_page(struct kvm *kvm,
+				     struct kvm_memory_slot *slot, gfn_t gfn,
+				     enum kvm_page_track_mode mode);
+
+#ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING
 /*
  * The notifier represented by @kvm_page_track_notifier_node is linked into
  * the head which will be notified when guest is triggering the track event.
@@ -48,18 +56,18 @@ struct kvm_page_track_notifier_node {
 				    struct kvm_page_track_notifier_node *node);
 };
 
-void kvm_slot_page_track_add_page(struct kvm *kvm,
-				  struct kvm_memory_slot *slot, gfn_t gfn,
-				  enum kvm_page_track_mode mode);
-void kvm_slot_page_track_remove_page(struct kvm *kvm,
-				     struct kvm_memory_slot *slot, gfn_t gfn,
-				     enum kvm_page_track_mode mode);
-
 void
 kvm_page_track_register_notifier(struct kvm *kvm,
 				 struct kvm_page_track_notifier_node *n);
 void
 kvm_page_track_unregister_notifier(struct kvm *kvm,
 				   struct kvm_page_track_notifier_node *n);
+#else
+/*
+ * Allow defining a node in a structure even if page tracking is disabled, e.g.
+ * to play nice with testing headers via direct inclusion from the command line.
+ */
+struct kvm_page_track_notifier_node {};
+#endif /* CONFIG_KVM_EXTERNAL_WRITE_TRACKING */
 
 #endif
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index ba3261df9b63..108075001f5c 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -194,6 +194,7 @@ bool kvm_slot_page_track_is_active(struct kvm *kvm,
 	return !!READ_ONCE(slot->arch.gfn_track[mode][index]);
 }
 
+#ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING
 void kvm_page_track_cleanup(struct kvm *kvm)
 {
 	struct kvm_page_track_notifier_head *head;
@@ -255,14 +256,13 @@ EXPORT_SYMBOL_GPL(kvm_page_track_unregister_notifier);
  * The node should figure out if the written page is the one that node is
  * interested in by itself.
  */
-void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
-			  int bytes)
+void __kvm_page_track_write(struct kvm *kvm, gpa_t gpa, const u8 *new, int bytes)
 {
 	struct kvm_page_track_notifier_head *head;
 	struct kvm_page_track_notifier_node *n;
 	int idx;
 
-	head = &vcpu->kvm->arch.track_notifier_head;
+	head = &kvm->arch.track_notifier_head;
 
 	if (hlist_empty(&head->track_notifier_list))
 		return;
@@ -273,8 +273,6 @@ void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
 		if (n->track_write)
 			n->track_write(gpa, new, bytes, n);
 	srcu_read_unlock(&head->track_srcu, idx);
-
-	kvm_mmu_track_write(vcpu, gpa, new, bytes);
 }
 
 /*
@@ -299,3 +297,5 @@ void kvm_page_track_delete_slot(struct kvm *kvm, struct kvm_memory_slot *slot)
 			n->track_remove_region(slot->base_gfn, slot->npages, n);
 	srcu_read_unlock(&head->track_srcu, idx);
 }
+
+#endif
diff --git a/arch/x86/kvm/mmu/page_track.h b/arch/x86/kvm/mmu/page_track.h
index cc1c8094bd73..ac48c668937a 100644
--- a/arch/x86/kvm/mmu/page_track.h
+++ b/arch/x86/kvm/mmu/page_track.h
@@ -6,8 +6,6 @@
 
 #include <asm/kvm_page_track.h>
 
-int kvm_page_track_init(struct kvm *kvm);
-void kvm_page_track_cleanup(struct kvm *kvm);
 
 bool kvm_page_track_write_tracking_enabled(struct kvm *kvm);
 int kvm_page_track_write_tracking_alloc(struct kvm_memory_slot *slot);
@@ -21,13 +19,36 @@ bool kvm_slot_page_track_is_active(struct kvm *kvm,
 				   const struct kvm_memory_slot *slot,
 				   gfn_t gfn, enum kvm_page_track_mode mode);
 
-void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
-			  int bytes);
+#ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING
+int kvm_page_track_init(struct kvm *kvm);
+void kvm_page_track_cleanup(struct kvm *kvm);
+
+void __kvm_page_track_write(struct kvm *kvm, gpa_t gpa, const u8 *new, int bytes);
 void kvm_page_track_delete_slot(struct kvm *kvm, struct kvm_memory_slot *slot);
 
 static inline bool kvm_page_track_has_external_user(struct kvm *kvm)
 {
 	return !hlist_empty(&kvm->arch.track_notifier_head.track_notifier_list);
 }
+#else
+static inline int kvm_page_track_init(struct kvm *kvm) { return 0; }
+static inline void kvm_page_track_cleanup(struct kvm *kvm) { }
+
+static inline void __kvm_page_track_write(struct kvm *kvm, gpa_t gpa,
+					  const u8 *new, int bytes) { }
+static inline void kvm_page_track_delete_slot(struct kvm *kvm,
+					      struct kvm_memory_slot *slot) { }
+
+static inline bool kvm_page_track_has_external_user(struct kvm *kvm) { return false; }
+
+#endif /* CONFIG_KVM_EXTERNAL_WRITE_TRACKING */
+
+static inline void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa,
+					const u8 *new, int bytes)
+{
+	__kvm_page_track_write(vcpu->kvm, gpa, new, bytes);
+
+	kvm_mmu_track_write(vcpu, gpa, new, bytes);
+}
 
 #endif /* __KVM_X86_PAGE_TRACK_H */

From 338068b5bec4dfa11cf50eb8c1839d1e27749395 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:29 -0700
Subject: [PATCH 0879/1189] KVM: x86/mmu: Drop infrastructure for multiple
 page-track modes

Drop "support" for multiple page-track modes, as there is no evidence
that array-based and refcounted metadata is the optimal solution for
other modes, nor is there any evidence that other use cases, e.g. for
access-tracking, will be a good fit for the page-track machinery in
general.

E.g. one potential use case of access-tracking would be to prevent guest
access to poisoned memory (from the guest's perspective).  In that case,
the number of poisoned pages is likely to be a very small percentage of
the guest memory, and there is no need to reference count the number of
access-tracking users, i.e. expanding gfn_track[] for a new mode would be
grossly inefficient.  And for poisoned memory, host userspace would also
likely want to trap accesses, e.g. to inject #MC into the guest, and that
isn't currently supported by the page-track framework.

A better alternative for that poisoned page use case is likely a
variation of the proposed per-gfn attributes overlay (linked), which
would allow efficiently tracking the sparse set of poisoned pages, and by
default would exit to userspace on access.

Link: https://lore.kernel.org/all/Y2WB48kD0J4VGynX@google.com
Cc: Ben Gardon <bgardon@google.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-24-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_host.h       |  12 +--
 arch/x86/include/asm/kvm_page_track.h |  11 +--
 arch/x86/kvm/mmu/mmu.c                |  14 ++--
 arch/x86/kvm/mmu/page_track.c         | 108 ++++++++------------------
 arch/x86/kvm/mmu/page_track.h         |   3 +-
 drivers/gpu/drm/i915/gvt/kvmgt.c      |   4 +-
 6 files changed, 49 insertions(+), 103 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 29ad3f0a126f..1a4def36d5bb 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -288,13 +288,13 @@ struct kvm_kernel_irq_routing_entry;
  * kvm_mmu_page_role tracks the properties of a shadow page (where shadow page
  * also includes TDP pages) to determine whether or not a page can be used in
  * the given MMU context.  This is a subset of the overall kvm_cpu_role to
- * minimize the size of kvm_memory_slot.arch.gfn_track, i.e. allows allocating
- * 2 bytes per gfn instead of 4 bytes per gfn.
+ * minimize the size of kvm_memory_slot.arch.gfn_write_track, i.e. allows
+ * allocating 2 bytes per gfn instead of 4 bytes per gfn.
  *
  * Upper-level shadow pages having gptes are tracked for write-protection via
- * gfn_track.  As above, gfn_track is a 16 bit counter, so KVM must not create
- * more than 2^16-1 upper-level shadow pages at a single gfn, otherwise
- * gfn_track will overflow and explosions will ensure.
+ * gfn_write_track.  As above, gfn_write_track is a 16 bit counter, so KVM must
+ * not create more than 2^16-1 upper-level shadow pages at a single gfn,
+ * otherwise gfn_write_track will overflow and explosions will ensue.
  *
  * A unique shadow page (SP) for a gfn is created if and only if an existing SP
  * cannot be reused.  The ability to reuse a SP is tracked by its role, which
@@ -1023,7 +1023,7 @@ struct kvm_lpage_info {
 struct kvm_arch_memory_slot {
 	struct kvm_rmap_head *rmap[KVM_NR_PAGE_SIZES];
 	struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1];
-	unsigned short *gfn_track[KVM_PAGE_TRACK_MAX];
+	unsigned short *gfn_write_track;
 };
 
 /*
diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
index 61adb07b5927..9e4ee26d1779 100644
--- a/arch/x86/include/asm/kvm_page_track.h
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -4,17 +4,10 @@
 
 #include <linux/kvm_types.h>
 
-enum kvm_page_track_mode {
-	KVM_PAGE_TRACK_WRITE,
-	KVM_PAGE_TRACK_MAX,
-};
-
 void kvm_slot_page_track_add_page(struct kvm *kvm,
-				  struct kvm_memory_slot *slot, gfn_t gfn,
-				  enum kvm_page_track_mode mode);
+				  struct kvm_memory_slot *slot, gfn_t gfn);
 void kvm_slot_page_track_remove_page(struct kvm *kvm,
-				     struct kvm_memory_slot *slot, gfn_t gfn,
-				     enum kvm_page_track_mode mode);
+				     struct kvm_memory_slot *slot, gfn_t gfn);
 
 #ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING
 /*
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 14b5c74a9247..2d76ead9ddac 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -831,8 +831,7 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 
 	/* the non-leaf shadow pages are keeping readonly. */
 	if (sp->role.level > PG_LEVEL_4K)
-		return kvm_slot_page_track_add_page(kvm, slot, gfn,
-						    KVM_PAGE_TRACK_WRITE);
+		return kvm_slot_page_track_add_page(kvm, slot, gfn);
 
 	kvm_mmu_gfn_disallow_lpage(slot, gfn);
 
@@ -878,8 +877,7 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 	slots = kvm_memslots_for_spte_role(kvm, sp->role);
 	slot = __gfn_to_memslot(slots, gfn);
 	if (sp->role.level > PG_LEVEL_4K)
-		return kvm_slot_page_track_remove_page(kvm, slot, gfn,
-						       KVM_PAGE_TRACK_WRITE);
+		return kvm_slot_page_track_remove_page(kvm, slot, gfn);
 
 	kvm_mmu_gfn_allow_lpage(slot, gfn);
 }
@@ -2809,7 +2807,7 @@ int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot,
 	 * track machinery is used to write-protect upper-level shadow pages,
 	 * i.e. this guards the role.level == 4K assertion below!
 	 */
-	if (kvm_slot_page_track_is_active(kvm, slot, gfn, KVM_PAGE_TRACK_WRITE))
+	if (kvm_slot_page_track_is_active(kvm, slot, gfn))
 		return -EPERM;
 
 	/*
@@ -4203,7 +4201,7 @@ static bool page_fault_handle_page_track(struct kvm_vcpu *vcpu,
 	 * guest is writing the page which is write tracked which can
 	 * not be fixed by page fault handler.
 	 */
-	if (kvm_slot_page_track_is_active(vcpu->kvm, fault->slot, fault->gfn, KVM_PAGE_TRACK_WRITE))
+	if (kvm_slot_page_track_is_active(vcpu->kvm, fault->slot, fault->gfn))
 		return true;
 
 	return false;
@@ -5422,8 +5420,8 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	 * physical address properties) in a single VM would require tracking
 	 * all relevant CPUID information in kvm_mmu_page_role. That is very
 	 * undesirable as it would increase the memory requirements for
-	 * gfn_track (see struct kvm_mmu_page_role comments).  For now that
-	 * problem is swept under the rug; KVM's CPUID API is horrific and
+	 * gfn_write_track (see struct kvm_mmu_page_role comments).  For now
+	 * that problem is swept under the rug; KVM's CPUID API is horrific and
 	 * it's all but impossible to solve it without introducing a new API.
 	 */
 	vcpu->arch.root_mmu.root_role.word = 0;
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index 108075001f5c..9d0b1a50f2fd 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -27,76 +27,50 @@ bool kvm_page_track_write_tracking_enabled(struct kvm *kvm)
 
 void kvm_page_track_free_memslot(struct kvm_memory_slot *slot)
 {
-	int i;
+	kvfree(slot->arch.gfn_write_track);
+	slot->arch.gfn_write_track = NULL;
+}
 
-	for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) {
-		kvfree(slot->arch.gfn_track[i]);
-		slot->arch.gfn_track[i] = NULL;
-	}
+static int __kvm_page_track_write_tracking_alloc(struct kvm_memory_slot *slot,
+						 unsigned long npages)
+{
+	const size_t size = sizeof(*slot->arch.gfn_write_track);
+
+	if (!slot->arch.gfn_write_track)
+		slot->arch.gfn_write_track = __vcalloc(npages, size,
+						       GFP_KERNEL_ACCOUNT);
+
+	return slot->arch.gfn_write_track ? 0 : -ENOMEM;
 }
 
 int kvm_page_track_create_memslot(struct kvm *kvm,
 				  struct kvm_memory_slot *slot,
 				  unsigned long npages)
 {
-	int i;
+	if (!kvm_page_track_write_tracking_enabled(kvm))
+		return 0;
 
-	for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) {
-		if (i == KVM_PAGE_TRACK_WRITE &&
-		    !kvm_page_track_write_tracking_enabled(kvm))
-			continue;
-
-		slot->arch.gfn_track[i] =
-			__vcalloc(npages, sizeof(*slot->arch.gfn_track[i]),
-				  GFP_KERNEL_ACCOUNT);
-		if (!slot->arch.gfn_track[i])
-			goto track_free;
-	}
-
-	return 0;
-
-track_free:
-	kvm_page_track_free_memslot(slot);
-	return -ENOMEM;
-}
-
-static inline bool page_track_mode_is_valid(enum kvm_page_track_mode mode)
-{
-	if (mode < 0 || mode >= KVM_PAGE_TRACK_MAX)
-		return false;
-
-	return true;
+	return __kvm_page_track_write_tracking_alloc(slot, npages);
 }
 
 int kvm_page_track_write_tracking_alloc(struct kvm_memory_slot *slot)
 {
-	unsigned short *gfn_track;
-
-	if (slot->arch.gfn_track[KVM_PAGE_TRACK_WRITE])
-		return 0;
-
-	gfn_track = __vcalloc(slot->npages, sizeof(*gfn_track),
-			      GFP_KERNEL_ACCOUNT);
-	if (gfn_track == NULL)
-		return -ENOMEM;
-
-	slot->arch.gfn_track[KVM_PAGE_TRACK_WRITE] = gfn_track;
-	return 0;
+	return __kvm_page_track_write_tracking_alloc(slot, slot->npages);
 }
 
-static void update_gfn_track(struct kvm_memory_slot *slot, gfn_t gfn,
-			     enum kvm_page_track_mode mode, short count)
+static void update_gfn_write_track(struct kvm_memory_slot *slot, gfn_t gfn,
+				   short count)
 {
 	int index, val;
 
 	index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K);
 
-	val = slot->arch.gfn_track[mode][index];
+	val = slot->arch.gfn_write_track[index];
 
 	if (WARN_ON_ONCE(val + count < 0 || val + count > USHRT_MAX))
 		return;
 
-	slot->arch.gfn_track[mode][index] += count;
+	slot->arch.gfn_write_track[index] += count;
 }
 
 /*
@@ -109,21 +83,14 @@ static void update_gfn_track(struct kvm_memory_slot *slot, gfn_t gfn,
  * @kvm: the guest instance we are interested in.
  * @slot: the @gfn belongs to.
  * @gfn: the guest page.
- * @mode: tracking mode, currently only write track is supported.
  */
 void kvm_slot_page_track_add_page(struct kvm *kvm,
-				  struct kvm_memory_slot *slot, gfn_t gfn,
-				  enum kvm_page_track_mode mode)
+				  struct kvm_memory_slot *slot, gfn_t gfn)
 {
-
-	if (WARN_ON_ONCE(!page_track_mode_is_valid(mode)))
+	if (WARN_ON_ONCE(!kvm_page_track_write_tracking_enabled(kvm)))
 		return;
 
-	if (WARN_ON_ONCE(mode == KVM_PAGE_TRACK_WRITE &&
-			 !kvm_page_track_write_tracking_enabled(kvm)))
-		return;
-
-	update_gfn_track(slot, gfn, mode, 1);
+	update_gfn_write_track(slot, gfn, 1);
 
 	/*
 	 * new track stops large page mapping for the
@@ -131,9 +98,8 @@ void kvm_slot_page_track_add_page(struct kvm *kvm,
 	 */
 	kvm_mmu_gfn_disallow_lpage(slot, gfn);
 
-	if (mode == KVM_PAGE_TRACK_WRITE)
-		if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn, PG_LEVEL_4K))
-			kvm_flush_remote_tlbs(kvm);
+	if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn, PG_LEVEL_4K))
+		kvm_flush_remote_tlbs(kvm);
 }
 EXPORT_SYMBOL_GPL(kvm_slot_page_track_add_page);
 
@@ -148,20 +114,14 @@ EXPORT_SYMBOL_GPL(kvm_slot_page_track_add_page);
  * @kvm: the guest instance we are interested in.
  * @slot: the @gfn belongs to.
  * @gfn: the guest page.
- * @mode: tracking mode, currently only write track is supported.
  */
 void kvm_slot_page_track_remove_page(struct kvm *kvm,
-				     struct kvm_memory_slot *slot, gfn_t gfn,
-				     enum kvm_page_track_mode mode)
+				     struct kvm_memory_slot *slot, gfn_t gfn)
 {
-	if (WARN_ON_ONCE(!page_track_mode_is_valid(mode)))
+	if (WARN_ON_ONCE(!kvm_page_track_write_tracking_enabled(kvm)))
 		return;
 
-	if (WARN_ON_ONCE(mode == KVM_PAGE_TRACK_WRITE &&
-			 !kvm_page_track_write_tracking_enabled(kvm)))
-		return;
-
-	update_gfn_track(slot, gfn, mode, -1);
+	update_gfn_write_track(slot, gfn, -1);
 
 	/*
 	 * allow large page mapping for the tracked page
@@ -176,22 +136,18 @@ EXPORT_SYMBOL_GPL(kvm_slot_page_track_remove_page);
  */
 bool kvm_slot_page_track_is_active(struct kvm *kvm,
 				   const struct kvm_memory_slot *slot,
-				   gfn_t gfn, enum kvm_page_track_mode mode)
+				   gfn_t gfn)
 {
 	int index;
 
-	if (WARN_ON_ONCE(!page_track_mode_is_valid(mode)))
-		return false;
-
 	if (!slot)
 		return false;
 
-	if (mode == KVM_PAGE_TRACK_WRITE &&
-	    !kvm_page_track_write_tracking_enabled(kvm))
+	if (!kvm_page_track_write_tracking_enabled(kvm))
 		return false;
 
 	index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K);
-	return !!READ_ONCE(slot->arch.gfn_track[mode][index]);
+	return !!READ_ONCE(slot->arch.gfn_write_track[index]);
 }
 
 #ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING
diff --git a/arch/x86/kvm/mmu/page_track.h b/arch/x86/kvm/mmu/page_track.h
index ac48c668937a..48a5377395dc 100644
--- a/arch/x86/kvm/mmu/page_track.h
+++ b/arch/x86/kvm/mmu/page_track.h
@@ -16,8 +16,7 @@ int kvm_page_track_create_memslot(struct kvm *kvm,
 				  unsigned long npages);
 
 bool kvm_slot_page_track_is_active(struct kvm *kvm,
-				   const struct kvm_memory_slot *slot,
-				   gfn_t gfn, enum kvm_page_track_mode mode);
+				   const struct kvm_memory_slot *slot, gfn_t gfn);
 
 #ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING
 int kvm_page_track_init(struct kvm *kvm);
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index 3f2327455d85..e71182b8a3f2 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -1564,7 +1564,7 @@ int intel_gvt_page_track_add(struct intel_vgpu *info, u64 gfn)
 	}
 
 	write_lock(&kvm->mmu_lock);
-	kvm_slot_page_track_add_page(kvm, slot, gfn, KVM_PAGE_TRACK_WRITE);
+	kvm_slot_page_track_add_page(kvm, slot, gfn);
 	write_unlock(&kvm->mmu_lock);
 
 	srcu_read_unlock(&kvm->srcu, idx);
@@ -1593,7 +1593,7 @@ int intel_gvt_page_track_remove(struct intel_vgpu *info, u64 gfn)
 	}
 
 	write_lock(&kvm->mmu_lock);
-	kvm_slot_page_track_remove_page(kvm, slot, gfn, KVM_PAGE_TRACK_WRITE);
+	kvm_slot_page_track_remove_page(kvm, slot, gfn);
 	write_unlock(&kvm->mmu_lock);
 	srcu_read_unlock(&kvm->srcu, idx);
 

From 7b574863e71833b5a4907245c1d95e76d507b984 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:30 -0700
Subject: [PATCH 0880/1189] KVM: x86/mmu: Rename page-track APIs to reflect the
 new reality

Rename the page-track APIs to capture that they're all about tracking
writes, now that the facade of supporting multiple modes is gone.

Opportunstically replace "slot" with "gfn" in anticipation of removing
the @slot param from the external APIs.

No functional change intended.

Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-25-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_page_track.h |  8 ++++----
 arch/x86/kvm/mmu/mmu.c                |  8 ++++----
 arch/x86/kvm/mmu/page_track.c         | 20 +++++++++-----------
 arch/x86/kvm/mmu/page_track.h         |  4 ++--
 drivers/gpu/drm/i915/gvt/kvmgt.c      |  4 ++--
 5 files changed, 21 insertions(+), 23 deletions(-)

diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
index 9e4ee26d1779..f5c1db36cdb7 100644
--- a/arch/x86/include/asm/kvm_page_track.h
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -4,10 +4,10 @@
 
 #include <linux/kvm_types.h>
 
-void kvm_slot_page_track_add_page(struct kvm *kvm,
-				  struct kvm_memory_slot *slot, gfn_t gfn);
-void kvm_slot_page_track_remove_page(struct kvm *kvm,
-				     struct kvm_memory_slot *slot, gfn_t gfn);
+void kvm_write_track_add_gfn(struct kvm *kvm,
+			     struct kvm_memory_slot *slot, gfn_t gfn);
+void kvm_write_track_remove_gfn(struct kvm *kvm, struct kvm_memory_slot *slot,
+				gfn_t gfn);
 
 #ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING
 /*
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 2d76ead9ddac..cc9a1e627d7e 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -831,7 +831,7 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 
 	/* the non-leaf shadow pages are keeping readonly. */
 	if (sp->role.level > PG_LEVEL_4K)
-		return kvm_slot_page_track_add_page(kvm, slot, gfn);
+		return kvm_write_track_add_gfn(kvm, slot, gfn);
 
 	kvm_mmu_gfn_disallow_lpage(slot, gfn);
 
@@ -877,7 +877,7 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 	slots = kvm_memslots_for_spte_role(kvm, sp->role);
 	slot = __gfn_to_memslot(slots, gfn);
 	if (sp->role.level > PG_LEVEL_4K)
-		return kvm_slot_page_track_remove_page(kvm, slot, gfn);
+		return kvm_write_track_remove_gfn(kvm, slot, gfn);
 
 	kvm_mmu_gfn_allow_lpage(slot, gfn);
 }
@@ -2807,7 +2807,7 @@ int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot,
 	 * track machinery is used to write-protect upper-level shadow pages,
 	 * i.e. this guards the role.level == 4K assertion below!
 	 */
-	if (kvm_slot_page_track_is_active(kvm, slot, gfn))
+	if (kvm_gfn_is_write_tracked(kvm, slot, gfn))
 		return -EPERM;
 
 	/*
@@ -4201,7 +4201,7 @@ static bool page_fault_handle_page_track(struct kvm_vcpu *vcpu,
 	 * guest is writing the page which is write tracked which can
 	 * not be fixed by page fault handler.
 	 */
-	if (kvm_slot_page_track_is_active(vcpu->kvm, fault->slot, fault->gfn))
+	if (kvm_gfn_is_write_tracked(vcpu->kvm, fault->slot, fault->gfn))
 		return true;
 
 	return false;
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index 9d0b1a50f2fd..dd6765bc385e 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -84,8 +84,8 @@ static void update_gfn_write_track(struct kvm_memory_slot *slot, gfn_t gfn,
  * @slot: the @gfn belongs to.
  * @gfn: the guest page.
  */
-void kvm_slot_page_track_add_page(struct kvm *kvm,
-				  struct kvm_memory_slot *slot, gfn_t gfn)
+void kvm_write_track_add_gfn(struct kvm *kvm, struct kvm_memory_slot *slot,
+			     gfn_t gfn)
 {
 	if (WARN_ON_ONCE(!kvm_page_track_write_tracking_enabled(kvm)))
 		return;
@@ -101,12 +101,11 @@ void kvm_slot_page_track_add_page(struct kvm *kvm,
 	if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn, PG_LEVEL_4K))
 		kvm_flush_remote_tlbs(kvm);
 }
-EXPORT_SYMBOL_GPL(kvm_slot_page_track_add_page);
+EXPORT_SYMBOL_GPL(kvm_write_track_add_gfn);
 
 /*
  * remove the guest page from the tracking pool which stops the interception
- * of corresponding access on that page. It is the opposed operation of
- * kvm_slot_page_track_add_page().
+ * of corresponding access on that page.
  *
  * It should be called under the protection both of mmu-lock and kvm->srcu
  * or kvm->slots_lock.
@@ -115,8 +114,8 @@ EXPORT_SYMBOL_GPL(kvm_slot_page_track_add_page);
  * @slot: the @gfn belongs to.
  * @gfn: the guest page.
  */
-void kvm_slot_page_track_remove_page(struct kvm *kvm,
-				     struct kvm_memory_slot *slot, gfn_t gfn)
+void kvm_write_track_remove_gfn(struct kvm *kvm,
+				struct kvm_memory_slot *slot, gfn_t gfn)
 {
 	if (WARN_ON_ONCE(!kvm_page_track_write_tracking_enabled(kvm)))
 		return;
@@ -129,14 +128,13 @@ void kvm_slot_page_track_remove_page(struct kvm *kvm,
 	 */
 	kvm_mmu_gfn_allow_lpage(slot, gfn);
 }
-EXPORT_SYMBOL_GPL(kvm_slot_page_track_remove_page);
+EXPORT_SYMBOL_GPL(kvm_write_track_remove_gfn);
 
 /*
  * check if the corresponding access on the specified guest page is tracked.
  */
-bool kvm_slot_page_track_is_active(struct kvm *kvm,
-				   const struct kvm_memory_slot *slot,
-				   gfn_t gfn)
+bool kvm_gfn_is_write_tracked(struct kvm *kvm,
+			      const struct kvm_memory_slot *slot, gfn_t gfn)
 {
 	int index;
 
diff --git a/arch/x86/kvm/mmu/page_track.h b/arch/x86/kvm/mmu/page_track.h
index 48a5377395dc..b020f998ee2c 100644
--- a/arch/x86/kvm/mmu/page_track.h
+++ b/arch/x86/kvm/mmu/page_track.h
@@ -15,8 +15,8 @@ int kvm_page_track_create_memslot(struct kvm *kvm,
 				  struct kvm_memory_slot *slot,
 				  unsigned long npages);
 
-bool kvm_slot_page_track_is_active(struct kvm *kvm,
-				   const struct kvm_memory_slot *slot, gfn_t gfn);
+bool kvm_gfn_is_write_tracked(struct kvm *kvm,
+			      const struct kvm_memory_slot *slot, gfn_t gfn);
 
 #ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING
 int kvm_page_track_init(struct kvm *kvm);
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index e71182b8a3f2..05a7e614ead0 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -1564,7 +1564,7 @@ int intel_gvt_page_track_add(struct intel_vgpu *info, u64 gfn)
 	}
 
 	write_lock(&kvm->mmu_lock);
-	kvm_slot_page_track_add_page(kvm, slot, gfn);
+	kvm_write_track_add_gfn(kvm, slot, gfn);
 	write_unlock(&kvm->mmu_lock);
 
 	srcu_read_unlock(&kvm->srcu, idx);
@@ -1593,7 +1593,7 @@ int intel_gvt_page_track_remove(struct intel_vgpu *info, u64 gfn)
 	}
 
 	write_lock(&kvm->mmu_lock);
-	kvm_slot_page_track_remove_page(kvm, slot, gfn);
+	kvm_write_track_remove_gfn(kvm, slot, gfn);
 	write_unlock(&kvm->mmu_lock);
 	srcu_read_unlock(&kvm->srcu, idx);
 

From e18c5429e0c4bf7b550211245dcbfc61e71a7e6f Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:31 -0700
Subject: [PATCH 0881/1189] KVM: x86/mmu: Assert that correct locks are held
 for page write-tracking

When adding/removing gfns to/from write-tracking, assert that mmu_lock
is held for write, and that either slots_lock or kvm->srcu is held.
mmu_lock must be held for write to protect gfn_write_track's refcount,
and SRCU or slots_lock must be held to protect the memslot itself.

Tested-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-26-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/page_track.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index dd6765bc385e..2c6b912072b7 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -12,6 +12,7 @@
  */
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/lockdep.h>
 #include <linux/kvm_host.h>
 #include <linux/rculist.h>
 
@@ -77,9 +78,6 @@ static void update_gfn_write_track(struct kvm_memory_slot *slot, gfn_t gfn,
  * add guest page to the tracking pool so that corresponding access on that
  * page will be intercepted.
  *
- * It should be called under the protection both of mmu-lock and kvm->srcu
- * or kvm->slots_lock.
- *
  * @kvm: the guest instance we are interested in.
  * @slot: the @gfn belongs to.
  * @gfn: the guest page.
@@ -87,6 +85,11 @@ static void update_gfn_write_track(struct kvm_memory_slot *slot, gfn_t gfn,
 void kvm_write_track_add_gfn(struct kvm *kvm, struct kvm_memory_slot *slot,
 			     gfn_t gfn)
 {
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
+	lockdep_assert_once(lockdep_is_held(&kvm->slots_lock) ||
+			    srcu_read_lock_held(&kvm->srcu));
+
 	if (WARN_ON_ONCE(!kvm_page_track_write_tracking_enabled(kvm)))
 		return;
 
@@ -107,9 +110,6 @@ EXPORT_SYMBOL_GPL(kvm_write_track_add_gfn);
  * remove the guest page from the tracking pool which stops the interception
  * of corresponding access on that page.
  *
- * It should be called under the protection both of mmu-lock and kvm->srcu
- * or kvm->slots_lock.
- *
  * @kvm: the guest instance we are interested in.
  * @slot: the @gfn belongs to.
  * @gfn: the guest page.
@@ -117,6 +117,11 @@ EXPORT_SYMBOL_GPL(kvm_write_track_add_gfn);
 void kvm_write_track_remove_gfn(struct kvm *kvm,
 				struct kvm_memory_slot *slot, gfn_t gfn)
 {
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
+	lockdep_assert_once(lockdep_is_held(&kvm->slots_lock) ||
+			    srcu_read_lock_held(&kvm->srcu));
+
 	if (WARN_ON_ONCE(!kvm_page_track_write_tracking_enabled(kvm)))
 		return;
 

From 427c76aed29ec12a57f11546a5036df3cc52855e Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:32 -0700
Subject: [PATCH 0882/1189] KVM: x86/mmu: Bug the VM if write-tracking is used
 but not enabled

Bug the VM if something attempts to write-track a gfn, but write-tracking
isn't enabled.  The VM is doomed (and KVM has an egregious bug) if KVM or
KVMGT wants to shadow guest page tables but can't because write-tracking
isn't enabled.

Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-27-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/page_track.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index 2c6b912072b7..9bf01311ee9c 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -90,7 +90,7 @@ void kvm_write_track_add_gfn(struct kvm *kvm, struct kvm_memory_slot *slot,
 	lockdep_assert_once(lockdep_is_held(&kvm->slots_lock) ||
 			    srcu_read_lock_held(&kvm->srcu));
 
-	if (WARN_ON_ONCE(!kvm_page_track_write_tracking_enabled(kvm)))
+	if (KVM_BUG_ON(!kvm_page_track_write_tracking_enabled(kvm), kvm))
 		return;
 
 	update_gfn_write_track(slot, gfn, 1);
@@ -122,7 +122,7 @@ void kvm_write_track_remove_gfn(struct kvm *kvm,
 	lockdep_assert_once(lockdep_is_held(&kvm->slots_lock) ||
 			    srcu_read_lock_held(&kvm->srcu));
 
-	if (WARN_ON_ONCE(!kvm_page_track_write_tracking_enabled(kvm)))
+	if (KVM_BUG_ON(!kvm_page_track_write_tracking_enabled(kvm), kvm))
 		return;
 
 	update_gfn_write_track(slot, gfn, -1);

From 96316a06700fc93140e7492c9e994045680f7272 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:33 -0700
Subject: [PATCH 0883/1189] KVM: x86/mmu: Drop @slot param from
 exported/external page-track APIs

Refactor KVM's exported/external page-track, a.k.a. write-track, APIs
to take only the gfn and do the required memslot lookup in KVM proper.
Forcing users of the APIs to get the memslot unnecessarily bleeds
KVM internals into KVMGT and complicates usage of the APIs.

No functional change intended.

Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-28-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_page_track.h |  7 +--
 arch/x86/kvm/mmu/mmu.c                |  4 +-
 arch/x86/kvm/mmu/page_track.c         | 85 ++++++++++++++++++++-------
 arch/x86/kvm/mmu/page_track.h         |  5 ++
 drivers/gpu/drm/i915/gvt/kvmgt.c      | 37 +++---------
 5 files changed, 80 insertions(+), 58 deletions(-)

diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
index f5c1db36cdb7..4afab697e21c 100644
--- a/arch/x86/include/asm/kvm_page_track.h
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -4,11 +4,6 @@
 
 #include <linux/kvm_types.h>
 
-void kvm_write_track_add_gfn(struct kvm *kvm,
-			     struct kvm_memory_slot *slot, gfn_t gfn);
-void kvm_write_track_remove_gfn(struct kvm *kvm, struct kvm_memory_slot *slot,
-				gfn_t gfn);
-
 #ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING
 /*
  * The notifier represented by @kvm_page_track_notifier_node is linked into
@@ -55,6 +50,8 @@ kvm_page_track_register_notifier(struct kvm *kvm,
 void
 kvm_page_track_unregister_notifier(struct kvm *kvm,
 				   struct kvm_page_track_notifier_node *n);
+int kvm_write_track_add_gfn(struct kvm *kvm, gfn_t gfn);
+int kvm_write_track_remove_gfn(struct kvm *kvm, gfn_t gfn);
 #else
 /*
  * Allow defining a node in a structure even if page tracking is disabled, e.g.
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index cc9a1e627d7e..060849d6aadf 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -831,7 +831,7 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 
 	/* the non-leaf shadow pages are keeping readonly. */
 	if (sp->role.level > PG_LEVEL_4K)
-		return kvm_write_track_add_gfn(kvm, slot, gfn);
+		return __kvm_write_track_add_gfn(kvm, slot, gfn);
 
 	kvm_mmu_gfn_disallow_lpage(slot, gfn);
 
@@ -877,7 +877,7 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 	slots = kvm_memslots_for_spte_role(kvm, sp->role);
 	slot = __gfn_to_memslot(slots, gfn);
 	if (sp->role.level > PG_LEVEL_4K)
-		return kvm_write_track_remove_gfn(kvm, slot, gfn);
+		return __kvm_write_track_remove_gfn(kvm, slot, gfn);
 
 	kvm_mmu_gfn_allow_lpage(slot, gfn);
 }
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index 9bf01311ee9c..c9ab8b587d25 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -74,16 +74,8 @@ static void update_gfn_write_track(struct kvm_memory_slot *slot, gfn_t gfn,
 	slot->arch.gfn_write_track[index] += count;
 }
 
-/*
- * add guest page to the tracking pool so that corresponding access on that
- * page will be intercepted.
- *
- * @kvm: the guest instance we are interested in.
- * @slot: the @gfn belongs to.
- * @gfn: the guest page.
- */
-void kvm_write_track_add_gfn(struct kvm *kvm, struct kvm_memory_slot *slot,
-			     gfn_t gfn)
+void __kvm_write_track_add_gfn(struct kvm *kvm, struct kvm_memory_slot *slot,
+			       gfn_t gfn)
 {
 	lockdep_assert_held_write(&kvm->mmu_lock);
 
@@ -104,18 +96,9 @@ void kvm_write_track_add_gfn(struct kvm *kvm, struct kvm_memory_slot *slot,
 	if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn, PG_LEVEL_4K))
 		kvm_flush_remote_tlbs(kvm);
 }
-EXPORT_SYMBOL_GPL(kvm_write_track_add_gfn);
 
-/*
- * remove the guest page from the tracking pool which stops the interception
- * of corresponding access on that page.
- *
- * @kvm: the guest instance we are interested in.
- * @slot: the @gfn belongs to.
- * @gfn: the guest page.
- */
-void kvm_write_track_remove_gfn(struct kvm *kvm,
-				struct kvm_memory_slot *slot, gfn_t gfn)
+void __kvm_write_track_remove_gfn(struct kvm *kvm,
+				  struct kvm_memory_slot *slot, gfn_t gfn)
 {
 	lockdep_assert_held_write(&kvm->mmu_lock);
 
@@ -133,7 +116,6 @@ void kvm_write_track_remove_gfn(struct kvm *kvm,
 	 */
 	kvm_mmu_gfn_allow_lpage(slot, gfn);
 }
-EXPORT_SYMBOL_GPL(kvm_write_track_remove_gfn);
 
 /*
  * check if the corresponding access on the specified guest page is tracked.
@@ -257,4 +239,63 @@ void kvm_page_track_delete_slot(struct kvm *kvm, struct kvm_memory_slot *slot)
 	srcu_read_unlock(&head->track_srcu, idx);
 }
 
+/*
+ * add guest page to the tracking pool so that corresponding access on that
+ * page will be intercepted.
+ *
+ * @kvm: the guest instance we are interested in.
+ * @gfn: the guest page.
+ */
+int kvm_write_track_add_gfn(struct kvm *kvm, gfn_t gfn)
+{
+	struct kvm_memory_slot *slot;
+	int idx;
+
+	idx = srcu_read_lock(&kvm->srcu);
+
+	slot = gfn_to_memslot(kvm, gfn);
+	if (!slot) {
+		srcu_read_unlock(&kvm->srcu, idx);
+		return -EINVAL;
+	}
+
+	write_lock(&kvm->mmu_lock);
+	__kvm_write_track_add_gfn(kvm, slot, gfn);
+	write_unlock(&kvm->mmu_lock);
+
+	srcu_read_unlock(&kvm->srcu, idx);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_write_track_add_gfn);
+
+/*
+ * remove the guest page from the tracking pool which stops the interception
+ * of corresponding access on that page.
+ *
+ * @kvm: the guest instance we are interested in.
+ * @gfn: the guest page.
+ */
+int kvm_write_track_remove_gfn(struct kvm *kvm, gfn_t gfn)
+{
+	struct kvm_memory_slot *slot;
+	int idx;
+
+	idx = srcu_read_lock(&kvm->srcu);
+
+	slot = gfn_to_memslot(kvm, gfn);
+	if (!slot) {
+		srcu_read_unlock(&kvm->srcu, idx);
+		return -EINVAL;
+	}
+
+	write_lock(&kvm->mmu_lock);
+	__kvm_write_track_remove_gfn(kvm, slot, gfn);
+	write_unlock(&kvm->mmu_lock);
+
+	srcu_read_unlock(&kvm->srcu, idx);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_write_track_remove_gfn);
 #endif
diff --git a/arch/x86/kvm/mmu/page_track.h b/arch/x86/kvm/mmu/page_track.h
index b020f998ee2c..d4d72ed999b1 100644
--- a/arch/x86/kvm/mmu/page_track.h
+++ b/arch/x86/kvm/mmu/page_track.h
@@ -15,6 +15,11 @@ int kvm_page_track_create_memslot(struct kvm *kvm,
 				  struct kvm_memory_slot *slot,
 				  unsigned long npages);
 
+void __kvm_write_track_add_gfn(struct kvm *kvm, struct kvm_memory_slot *slot,
+			       gfn_t gfn);
+void __kvm_write_track_remove_gfn(struct kvm *kvm,
+				  struct kvm_memory_slot *slot, gfn_t gfn);
+
 bool kvm_gfn_is_write_tracked(struct kvm *kvm,
 			      const struct kvm_memory_slot *slot, gfn_t gfn);
 
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index 05a7e614ead0..21342a93e418 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -1546,9 +1546,7 @@ static struct mdev_driver intel_vgpu_mdev_driver = {
 
 int intel_gvt_page_track_add(struct intel_vgpu *info, u64 gfn)
 {
-	struct kvm *kvm = info->vfio_device.kvm;
-	struct kvm_memory_slot *slot;
-	int idx;
+	int r;
 
 	if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, info->status))
 		return -ESRCH;
@@ -1556,18 +1554,9 @@ int intel_gvt_page_track_add(struct intel_vgpu *info, u64 gfn)
 	if (kvmgt_gfn_is_write_protected(info, gfn))
 		return 0;
 
-	idx = srcu_read_lock(&kvm->srcu);
-	slot = gfn_to_memslot(kvm, gfn);
-	if (!slot) {
-		srcu_read_unlock(&kvm->srcu, idx);
-		return -EINVAL;
-	}
-
-	write_lock(&kvm->mmu_lock);
-	kvm_write_track_add_gfn(kvm, slot, gfn);
-	write_unlock(&kvm->mmu_lock);
-
-	srcu_read_unlock(&kvm->srcu, idx);
+	r = kvm_write_track_add_gfn(info->vfio_device.kvm, gfn);
+	if (r)
+		return r;
 
 	kvmgt_protect_table_add(info, gfn);
 	return 0;
@@ -1575,9 +1564,7 @@ int intel_gvt_page_track_add(struct intel_vgpu *info, u64 gfn)
 
 int intel_gvt_page_track_remove(struct intel_vgpu *info, u64 gfn)
 {
-	struct kvm *kvm = info->vfio_device.kvm;
-	struct kvm_memory_slot *slot;
-	int idx;
+	int r;
 
 	if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, info->status))
 		return -ESRCH;
@@ -1585,17 +1572,9 @@ int intel_gvt_page_track_remove(struct intel_vgpu *info, u64 gfn)
 	if (!kvmgt_gfn_is_write_protected(info, gfn))
 		return 0;
 
-	idx = srcu_read_lock(&kvm->srcu);
-	slot = gfn_to_memslot(kvm, gfn);
-	if (!slot) {
-		srcu_read_unlock(&kvm->srcu, idx);
-		return -EINVAL;
-	}
-
-	write_lock(&kvm->mmu_lock);
-	kvm_write_track_remove_gfn(kvm, slot, gfn);
-	write_unlock(&kvm->mmu_lock);
-	srcu_read_unlock(&kvm->srcu, idx);
+	r = kvm_write_track_remove_gfn(info->vfio_device.kvm, gfn);
+	if (r)
+		return r;
 
 	kvmgt_protect_table_del(info, gfn);
 	return 0;

From f22b1e8500b449fabc33ca271cd8e91749fa63b4 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:34 -0700
Subject: [PATCH 0884/1189] KVM: x86/mmu: Handle KVM bookkeeping in page-track
 APIs, not callers

Get/put references to KVM when a page-track notifier is (un)registered
instead of relying on the caller to do so.  Forcing the caller to do the
bookkeeping is unnecessary and adds one more thing for users to get
wrong, e.g. see commit 9ed1fdee9ee3 ("drm/i915/gvt: Get reference to KVM
iff attachment to VM is successful").

Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-29-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_page_track.h | 11 +++++------
 arch/x86/kvm/mmu/page_track.c         | 18 ++++++++++++------
 drivers/gpu/drm/i915/gvt/kvmgt.c      | 17 +++++++----------
 3 files changed, 24 insertions(+), 22 deletions(-)

diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
index 4afab697e21c..3d040741044b 100644
--- a/arch/x86/include/asm/kvm_page_track.h
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -44,12 +44,11 @@ struct kvm_page_track_notifier_node {
 				    struct kvm_page_track_notifier_node *node);
 };
 
-void
-kvm_page_track_register_notifier(struct kvm *kvm,
-				 struct kvm_page_track_notifier_node *n);
-void
-kvm_page_track_unregister_notifier(struct kvm *kvm,
-				   struct kvm_page_track_notifier_node *n);
+int kvm_page_track_register_notifier(struct kvm *kvm,
+				     struct kvm_page_track_notifier_node *n);
+void kvm_page_track_unregister_notifier(struct kvm *kvm,
+					struct kvm_page_track_notifier_node *n);
+
 int kvm_write_track_add_gfn(struct kvm *kvm, gfn_t gfn);
 int kvm_write_track_remove_gfn(struct kvm *kvm, gfn_t gfn);
 #else
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index c9ab8b587d25..c87da11f3a04 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -157,17 +157,22 @@ int kvm_page_track_init(struct kvm *kvm)
  * register the notifier so that event interception for the tracked guest
  * pages can be received.
  */
-void
-kvm_page_track_register_notifier(struct kvm *kvm,
-				 struct kvm_page_track_notifier_node *n)
+int kvm_page_track_register_notifier(struct kvm *kvm,
+				     struct kvm_page_track_notifier_node *n)
 {
 	struct kvm_page_track_notifier_head *head;
 
+	if (!kvm || kvm->mm != current->mm)
+		return -ESRCH;
+
+	kvm_get_kvm(kvm);
+
 	head = &kvm->arch.track_notifier_head;
 
 	write_lock(&kvm->mmu_lock);
 	hlist_add_head_rcu(&n->node, &head->track_notifier_list);
 	write_unlock(&kvm->mmu_lock);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(kvm_page_track_register_notifier);
 
@@ -175,9 +180,8 @@ EXPORT_SYMBOL_GPL(kvm_page_track_register_notifier);
  * stop receiving the event interception. It is the opposed operation of
  * kvm_page_track_register_notifier().
  */
-void
-kvm_page_track_unregister_notifier(struct kvm *kvm,
-				   struct kvm_page_track_notifier_node *n)
+void kvm_page_track_unregister_notifier(struct kvm *kvm,
+					struct kvm_page_track_notifier_node *n)
 {
 	struct kvm_page_track_notifier_head *head;
 
@@ -187,6 +191,8 @@ kvm_page_track_unregister_notifier(struct kvm *kvm,
 	hlist_del_rcu(&n->node);
 	write_unlock(&kvm->mmu_lock);
 	synchronize_srcu(&head->track_srcu);
+
+	kvm_put_kvm(kvm);
 }
 EXPORT_SYMBOL_GPL(kvm_page_track_unregister_notifier);
 
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index 21342a93e418..eb50997dd369 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -654,21 +654,19 @@ out:
 static int intel_vgpu_open_device(struct vfio_device *vfio_dev)
 {
 	struct intel_vgpu *vgpu = vfio_dev_to_vgpu(vfio_dev);
-
-	if (!vgpu->vfio_device.kvm ||
-	    vgpu->vfio_device.kvm->mm != current->mm) {
-		gvt_vgpu_err("KVM is required to use Intel vGPU\n");
-		return -ESRCH;
-	}
+	int ret;
 
 	if (__kvmgt_vgpu_exist(vgpu))
 		return -EEXIST;
 
 	vgpu->track_node.track_write = kvmgt_page_track_write;
 	vgpu->track_node.track_remove_region = kvmgt_page_track_remove_region;
-	kvm_get_kvm(vgpu->vfio_device.kvm);
-	kvm_page_track_register_notifier(vgpu->vfio_device.kvm,
-					 &vgpu->track_node);
+	ret = kvm_page_track_register_notifier(vgpu->vfio_device.kvm,
+					       &vgpu->track_node);
+	if (ret) {
+		gvt_vgpu_err("KVM is required to use Intel vGPU\n");
+		return ret;
+	}
 
 	set_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status);
 
@@ -703,7 +701,6 @@ static void intel_vgpu_close_device(struct vfio_device *vfio_dev)
 
 	kvm_page_track_unregister_notifier(vgpu->vfio_device.kvm,
 					   &vgpu->track_node);
-	kvm_put_kvm(vgpu->vfio_device.kvm);
 
 	kvmgt_protect_table_destroy(vgpu);
 	gvt_cache_destroy(vgpu);

From 09c8726ffa4a8309af7653988694b6cae6abf723 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:35 -0700
Subject: [PATCH 0885/1189] drm/i915/gvt: Drop final dependencies on KVM
 internal details

Open code gpa_to_gfn() in kvmgt_page_track_write() and drop KVMGT's
dependency on kvm_host.h, i.e. include only kvm_page_track.h.  KVMGT
assumes "gfn == gpa >> PAGE_SHIFT" all over the place, including a few
lines below in the same function with the same gpa, i.e. there's no
reason to use KVM's helper for this one case.

No functional change intended.

Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Reviewed-by: Zhi Wang <zhi.a.wang@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-30-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 drivers/gpu/drm/i915/gvt/gvt.h   | 3 ++-
 drivers/gpu/drm/i915/gvt/kvmgt.c | 2 +-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index 2d65800d8e93..53a0a42a50db 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -34,10 +34,11 @@
 #define _GVT_H_
 
 #include <uapi/linux/pci_regs.h>
-#include <linux/kvm_host.h>
 #include <linux/vfio.h>
 #include <linux/mdev.h>
 
+#include <asm/kvm_page_track.h>
+
 #include "i915_drv.h"
 #include "intel_gvt.h"
 
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index eb50997dd369..aaed3969f204 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -1585,7 +1585,7 @@ static void kvmgt_page_track_write(gpa_t gpa, const u8 *val, int len,
 
 	mutex_lock(&info->vgpu_lock);
 
-	if (kvmgt_gfn_is_write_protected(info, gpa_to_gfn(gpa)))
+	if (kvmgt_gfn_is_write_protected(info, gpa >> PAGE_SHIFT))
 		intel_vgpu_page_track_handler(info, gpa,
 						     (void *)val, len);
 

From c5f2d5645f9b7c12c9546ced9ec1f1a558870747 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:51:56 -0700
Subject: [PATCH 0886/1189] KVM: x86/mmu: Add helper to convert root hpa to
 shadow page

Add a dedicated helper for converting a root hpa to a shadow page in
anticipation of using a "dummy" root to handle the scenario where KVM
needs to load a valid shadow root (from hardware's perspective), but
the guest doesn't have a visible root to shadow.  Similar to PAE roots,
the dummy root won't have an associated kvm_mmu_page and will need special
handling when finding a shadow page given a root.

Opportunistically retrieve the root shadow page in kvm_mmu_sync_roots()
*after* verifying the root is unsync (the dummy root can never be unsync).

Link: https://lore.kernel.org/r/20230729005200.1057358-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c     | 28 +++++++++++++---------------
 arch/x86/kvm/mmu/spte.h    |  9 +++++++++
 arch/x86/kvm/mmu/tdp_mmu.c |  2 +-
 3 files changed, 23 insertions(+), 16 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 060849d6aadf..61b67a7d61e0 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3543,11 +3543,7 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa,
 	if (!VALID_PAGE(*root_hpa))
 		return;
 
-	/*
-	 * The "root" may be a special root, e.g. a PAE entry, treat it as a
-	 * SPTE to ensure any non-PA bits are dropped.
-	 */
-	sp = spte_to_child_sp(*root_hpa);
+	sp = root_to_sp(*root_hpa);
 	if (WARN_ON_ONCE(!sp))
 		return;
 
@@ -3593,7 +3589,7 @@ void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu,
 					   &invalid_list);
 
 	if (free_active_root) {
-		if (to_shadow_page(mmu->root.hpa)) {
+		if (root_to_sp(mmu->root.hpa)) {
 			mmu_free_root_page(kvm, &mmu->root.hpa, &invalid_list);
 		} else if (mmu->pae_root) {
 			for (i = 0; i < 4; ++i) {
@@ -3617,6 +3613,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_free_roots);
 void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu)
 {
 	unsigned long roots_to_free = 0;
+	struct kvm_mmu_page *sp;
 	hpa_t root_hpa;
 	int i;
 
@@ -3631,8 +3628,8 @@ void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu)
 		if (!VALID_PAGE(root_hpa))
 			continue;
 
-		if (!to_shadow_page(root_hpa) ||
-			to_shadow_page(root_hpa)->role.guest_mode)
+		sp = root_to_sp(root_hpa);
+		if (!sp || sp->role.guest_mode)
 			roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i);
 	}
 
@@ -3987,7 +3984,7 @@ static bool is_unsync_root(hpa_t root)
 	 * requirement isn't satisfied.
 	 */
 	smp_rmb();
-	sp = to_shadow_page(root);
+	sp = root_to_sp(root);
 
 	/*
 	 * PAE roots (somewhat arbitrarily) aren't backed by shadow pages, the
@@ -4017,11 +4014,12 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
 
 	if (vcpu->arch.mmu->cpu_role.base.level >= PT64_ROOT_4LEVEL) {
 		hpa_t root = vcpu->arch.mmu->root.hpa;
-		sp = to_shadow_page(root);
 
 		if (!is_unsync_root(root))
 			return;
 
+		sp = root_to_sp(root);
+
 		write_lock(&vcpu->kvm->mmu_lock);
 		mmu_sync_children(vcpu, sp, true);
 		write_unlock(&vcpu->kvm->mmu_lock);
@@ -4351,7 +4349,7 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 static bool is_page_fault_stale(struct kvm_vcpu *vcpu,
 				struct kvm_page_fault *fault)
 {
-	struct kvm_mmu_page *sp = to_shadow_page(vcpu->arch.mmu->root.hpa);
+	struct kvm_mmu_page *sp = root_to_sp(vcpu->arch.mmu->root.hpa);
 
 	/* Special roots, e.g. pae_root, are not backed by shadow pages. */
 	if (sp && is_obsolete_sp(vcpu->kvm, sp))
@@ -4531,7 +4529,7 @@ static inline bool is_root_usable(struct kvm_mmu_root_info *root, gpa_t pgd,
 {
 	return (role.direct || pgd == root->pgd) &&
 	       VALID_PAGE(root->hpa) &&
-	       role.word == to_shadow_page(root->hpa)->role.word;
+	       role.word == root_to_sp(root->hpa)->role.word;
 }
 
 /*
@@ -4605,7 +4603,7 @@ static bool fast_pgd_switch(struct kvm *kvm, struct kvm_mmu *mmu,
 	 * having to deal with PDPTEs. We may add support for 32-bit hosts/VMs
 	 * later if necessary.
 	 */
-	if (VALID_PAGE(mmu->root.hpa) && !to_shadow_page(mmu->root.hpa))
+	if (VALID_PAGE(mmu->root.hpa) && !root_to_sp(mmu->root.hpa))
 		kvm_mmu_free_roots(kvm, mmu, KVM_MMU_ROOT_CURRENT);
 
 	if (VALID_PAGE(mmu->root.hpa))
@@ -4653,7 +4651,7 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd)
 	 */
 	if (!new_role.direct)
 		__clear_sp_write_flooding_count(
-				to_shadow_page(vcpu->arch.mmu->root.hpa));
+				root_to_sp(vcpu->arch.mmu->root.hpa));
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_new_pgd);
 
@@ -5508,7 +5506,7 @@ static bool is_obsolete_root(struct kvm *kvm, hpa_t root_hpa)
 	 *  (c) KVM doesn't track previous roots for PAE paging, and the guest
 	 *      is unlikely to zap an in-use PGD.
 	 */
-	sp = to_shadow_page(root_hpa);
+	sp = root_to_sp(root_hpa);
 	return !sp || is_obsolete_sp(kvm, sp);
 }
 
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index 83e6614f3720..29e0c1c8caa6 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -236,6 +236,15 @@ static inline struct kvm_mmu_page *sptep_to_sp(u64 *sptep)
 	return to_shadow_page(__pa(sptep));
 }
 
+static inline struct kvm_mmu_page *root_to_sp(hpa_t root)
+{
+	/*
+	 * The "root" may be a special root, e.g. a PAE entry, treat it as a
+	 * SPTE to ensure any non-PA bits are dropped.
+	 */
+	return spte_to_child_sp(root);
+}
+
 static inline bool is_mmio_spte(u64 spte)
 {
 	return (spte & shadow_mmio_mask) == shadow_mmio_value &&
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index fda32a72b406..6c63f2d1675f 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -689,7 +689,7 @@ static inline void tdp_mmu_iter_set_spte(struct kvm *kvm, struct tdp_iter *iter,
 		else
 
 #define tdp_mmu_for_each_pte(_iter, _mmu, _start, _end)		\
-	for_each_tdp_pte(_iter, to_shadow_page(_mmu->root.hpa), _start, _end)
+	for_each_tdp_pte(_iter, root_to_sp(_mmu->root.hpa), _start, _end)
 
 /*
  * Yield if the MMU lock is contended or this thread needs to return control

From c30e000e690af74f61a161fa60be140f23948cb1 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:51:57 -0700
Subject: [PATCH 0887/1189] KVM: x86/mmu: Harden new PGD against roots without
 shadow pages

Harden kvm_mmu_new_pgd() against NULL pointer dereference bugs by sanity
checking that the target root has an associated shadow page prior to
dereferencing said shadow page.  The code in question is guaranteed to
only see roots with shadow pages as fast_pgd_switch() explicitly frees the
current root if it doesn't have a shadow page, i.e. is a PAE root, and
that in turn prevents valid roots from being cached, but that's all very
subtle.

Link: https://lore.kernel.org/r/20230729005200.1057358-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c | 25 +++++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 61b67a7d61e0..de73d986a282 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4527,9 +4527,19 @@ static void nonpaging_init_context(struct kvm_mmu *context)
 static inline bool is_root_usable(struct kvm_mmu_root_info *root, gpa_t pgd,
 				  union kvm_mmu_page_role role)
 {
-	return (role.direct || pgd == root->pgd) &&
-	       VALID_PAGE(root->hpa) &&
-	       role.word == root_to_sp(root->hpa)->role.word;
+	struct kvm_mmu_page *sp;
+
+	if (!VALID_PAGE(root->hpa))
+		return false;
+
+	if (!role.direct && pgd != root->pgd)
+		return false;
+
+	sp = root_to_sp(root->hpa);
+	if (WARN_ON_ONCE(!sp))
+		return false;
+
+	return role.word == sp->role.word;
 }
 
 /*
@@ -4649,9 +4659,12 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd)
 	 * If this is a direct root page, it doesn't have a write flooding
 	 * count. Otherwise, clear the write flooding count.
 	 */
-	if (!new_role.direct)
-		__clear_sp_write_flooding_count(
-				root_to_sp(vcpu->arch.mmu->root.hpa));
+	if (!new_role.direct) {
+		struct kvm_mmu_page *sp = root_to_sp(vcpu->arch.mmu->root.hpa);
+
+		if (!WARN_ON_ONCE(!sp))
+			__clear_sp_write_flooding_count(sp);
+	}
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_new_pgd);
 

From 2c6d4c27b92d729a2831df2a873ba6b5f682f435 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:51:58 -0700
Subject: [PATCH 0888/1189] KVM: x86/mmu: Harden TDP MMU iteration against root
 w/o shadow page

Explicitly check that tdp_iter_start() is handed a valid shadow page
to harden KVM against bugs, e.g. if KVM calls into the TDP MMU with an
invalid or shadow MMU root (which would be a fatal KVM bug), the shadow
page pointer will be NULL.

Opportunistically stop the TDP MMU iteration instead of continuing on
with garbage if the incoming root is bogus.  Attempting to walk a garbage
root is more likely to caused major problems than doing nothing.

Cc: Yu Zhang <yu.c.zhang@linux.intel.com>
Link: https://lore.kernel.org/r/20230729005200.1057358-4-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/tdp_iter.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c
index 5bb09f8d9fc6..bd30ebfb2f2c 100644
--- a/arch/x86/kvm/mmu/tdp_iter.c
+++ b/arch/x86/kvm/mmu/tdp_iter.c
@@ -39,13 +39,14 @@ void tdp_iter_restart(struct tdp_iter *iter)
 void tdp_iter_start(struct tdp_iter *iter, struct kvm_mmu_page *root,
 		    int min_level, gfn_t next_last_level_gfn)
 {
-	int root_level = root->role.level;
-
-	WARN_ON_ONCE(root_level < 1);
-	WARN_ON_ONCE(root_level > PT64_ROOT_MAX_LEVEL);
+	if (WARN_ON_ONCE(!root || (root->role.level < 1) ||
+			 (root->role.level > PT64_ROOT_MAX_LEVEL))) {
+		iter->valid = false;
+		return;
+	}
 
 	iter->next_last_level_gfn = next_last_level_gfn;
-	iter->root_level = root_level;
+	iter->root_level = root->role.level;
 	iter->min_level = min_level;
 	iter->pt_path[iter->root_level - 1] = (tdp_ptep_t)root->spt;
 	iter->as_id = kvm_mmu_page_as_id(root);

From b5b359ac30d458cb3e2a7fb953adeec78fae4e35 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:51:59 -0700
Subject: [PATCH 0889/1189] KVM: x86/mmu: Disallow guest from using !visible
 slots for page tables

Explicitly inject a page fault if guest attempts to use a !visible gfn
as a page table.  kvm_vcpu_gfn_to_hva_prot() will naturally handle the
case where there is no memslot, but doesn't catch the scenario where the
gfn points at a KVM-internal memslot.

Letting the guest backdoor its way into accessing KVM-internal memslots
isn't dangerous on its own, e.g. at worst the guest can crash itself, but
disallowing the behavior will simplify fixing how KVM handles !visible
guest root gfns (immediately synthesizing a triple fault when loading the
root is architecturally wrong).

Link: https://lore.kernel.org/r/20230729005200.1057358-5-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/paging_tmpl.h | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index f8d358226ac6..89eb45eb9dd5 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -361,6 +361,7 @@ retry_walk:
 	++walker->level;
 
 	do {
+		struct kvm_memory_slot *slot;
 		unsigned long host_addr;
 
 		pt_access = pte_access;
@@ -391,7 +392,11 @@ retry_walk:
 		if (unlikely(real_gpa == INVALID_GPA))
 			return 0;
 
-		host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, gpa_to_gfn(real_gpa),
+		slot = kvm_vcpu_gfn_to_memslot(vcpu, gpa_to_gfn(real_gpa));
+		if (!kvm_is_visible_memslot(slot))
+			goto error;
+
+		host_addr = gfn_to_hva_memslot_prot(slot, gpa_to_gfn(real_gpa),
 					    &walker->pte_writable[walker->level - 1]);
 		if (unlikely(kvm_is_error_hva(host_addr)))
 			goto error;

From 0e3223d8d00ac05849661f1b8b476d3caca251cf Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:52:00 -0700
Subject: [PATCH 0890/1189] KVM: x86/mmu: Use dummy root, backed by zero page,
 for !visible guest roots

When attempting to allocate a shadow root for a !visible guest root gfn,
e.g. that resides in MMIO space, load a dummy root that is backed by the
zero page instead of immediately synthesizing a triple fault shutdown
(using the zero page ensures any attempt to translate memory will generate
a !PRESENT fault and thus VM-Exit).

Unless the vCPU is racing with memslot activity, KVM will inject a page
fault due to not finding a visible slot in FNAME(walk_addr_generic), i.e.
the end result is mostly same, but critically KVM will inject a fault only
*after* KVM runs the vCPU with the bogus root.

Waiting to inject a fault until after running the vCPU fixes a bug where
KVM would bail from nested VM-Enter if L1 tried to run L2 with TDP enabled
and a !visible root.  Even though a bad root will *probably* lead to
shutdown, (a) it's not guaranteed and (b) the CPU won't read the
underlying memory until after VM-Enter succeeds.  E.g. if L1 runs L2 with
a VMX preemption timer value of '0', then architecturally the preemption
timer VM-Exit is guaranteed to occur before the CPU executes any
instruction, i.e. before the CPU needs to translate a GPA to a HPA (so
long as there are no injected events with higher priority than the
preemption timer).

If KVM manages to get to FNAME(fetch) with a dummy root, e.g. because
userspace created a memslot between installing the dummy root and handling
the page fault, simply unload the MMU to allocate a new root and retry the
instruction.  Use KVM_REQ_MMU_FREE_OBSOLETE_ROOTS to drop the root, as
invoking kvm_mmu_free_roots() while holding mmu_lock would deadlock, and
conceptually the dummy root has indeeed become obsolete.  The only
difference versus existing usage of KVM_REQ_MMU_FREE_OBSOLETE_ROOTS is
that the root has become obsolete due to memslot *creation*, not memslot
deletion or movement.

Reported-by: Reima Ishii <ishiir@g.ecc.u-tokyo.ac.jp>
Cc: Yu Zhang <yu.c.zhang@linux.intel.com>
Link: https://lore.kernel.org/r/20230729005200.1057358-6-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c          | 47 ++++++++++++++++-----------------
 arch/x86/kvm/mmu/mmu_internal.h | 10 +++++++
 arch/x86/kvm/mmu/paging_tmpl.h  | 11 ++++++++
 arch/x86/kvm/mmu/spte.h         |  3 +++
 4 files changed, 47 insertions(+), 24 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index de73d986a282..e1d011c67cc6 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3589,7 +3589,9 @@ void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu,
 					   &invalid_list);
 
 	if (free_active_root) {
-		if (root_to_sp(mmu->root.hpa)) {
+		if (kvm_mmu_is_dummy_root(mmu->root.hpa)) {
+			/* Nothing to cleanup for dummy roots. */
+		} else if (root_to_sp(mmu->root.hpa)) {
 			mmu_free_root_page(kvm, &mmu->root.hpa, &invalid_list);
 		} else if (mmu->pae_root) {
 			for (i = 0; i < 4; ++i) {
@@ -3637,19 +3639,6 @@ void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu)
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_free_guest_mode_roots);
 
-
-static int mmu_check_root(struct kvm_vcpu *vcpu, gfn_t root_gfn)
-{
-	int ret = 0;
-
-	if (!kvm_vcpu_is_visible_gfn(vcpu, root_gfn)) {
-		kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
-		ret = 1;
-	}
-
-	return ret;
-}
-
 static hpa_t mmu_alloc_root(struct kvm_vcpu *vcpu, gfn_t gfn, int quadrant,
 			    u8 level)
 {
@@ -3787,8 +3776,10 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 	root_pgd = kvm_mmu_get_guest_pgd(vcpu, mmu);
 	root_gfn = root_pgd >> PAGE_SHIFT;
 
-	if (mmu_check_root(vcpu, root_gfn))
-		return 1;
+	if (!kvm_vcpu_is_visible_gfn(vcpu, root_gfn)) {
+		mmu->root.hpa = kvm_mmu_get_dummy_root();
+		return 0;
+	}
 
 	/*
 	 * On SVM, reading PDPTRs might access guest memory, which might fault
@@ -3800,8 +3791,8 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 			if (!(pdptrs[i] & PT_PRESENT_MASK))
 				continue;
 
-			if (mmu_check_root(vcpu, pdptrs[i] >> PAGE_SHIFT))
-				return 1;
+			if (!kvm_vcpu_is_visible_gfn(vcpu, pdptrs[i] >> PAGE_SHIFT))
+				pdptrs[i] = 0;
 		}
 	}
 
@@ -3968,7 +3959,7 @@ static bool is_unsync_root(hpa_t root)
 {
 	struct kvm_mmu_page *sp;
 
-	if (!VALID_PAGE(root))
+	if (!VALID_PAGE(root) || kvm_mmu_is_dummy_root(root))
 		return false;
 
 	/*
@@ -4374,6 +4365,10 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 {
 	int r;
 
+	/* Dummy roots are used only for shadowing bad guest roots. */
+	if (WARN_ON_ONCE(kvm_mmu_is_dummy_root(vcpu->arch.mmu->root.hpa)))
+		return RET_PF_RETRY;
+
 	if (page_fault_handle_page_track(vcpu, fault))
 		return RET_PF_EMULATE;
 
@@ -4609,9 +4604,8 @@ static bool fast_pgd_switch(struct kvm *kvm, struct kvm_mmu *mmu,
 			    gpa_t new_pgd, union kvm_mmu_page_role new_role)
 {
 	/*
-	 * For now, limit the caching to 64-bit hosts+VMs in order to avoid
-	 * having to deal with PDPTEs. We may add support for 32-bit hosts/VMs
-	 * later if necessary.
+	 * Limit reuse to 64-bit hosts+VMs without "special" roots in order to
+	 * avoid having to deal with PDPTEs and other complexities.
 	 */
 	if (VALID_PAGE(mmu->root.hpa) && !root_to_sp(mmu->root.hpa))
 		kvm_mmu_free_roots(kvm, mmu, KVM_MMU_ROOT_CURRENT);
@@ -5510,14 +5504,19 @@ static bool is_obsolete_root(struct kvm *kvm, hpa_t root_hpa)
 
 	/*
 	 * When freeing obsolete roots, treat roots as obsolete if they don't
-	 * have an associated shadow page.  This does mean KVM will get false
+	 * have an associated shadow page, as it's impossible to determine if
+	 * such roots are fresh or stale.  This does mean KVM will get false
 	 * positives and free roots that don't strictly need to be freed, but
 	 * such false positives are relatively rare:
 	 *
-	 *  (a) only PAE paging and nested NPT has roots without shadow pages
+	 *  (a) only PAE paging and nested NPT have roots without shadow pages
+	 *      (or any shadow paging flavor with a dummy root, see note below)
 	 *  (b) remote reloads due to a memslot update obsoletes _all_ roots
 	 *  (c) KVM doesn't track previous roots for PAE paging, and the guest
 	 *      is unlikely to zap an in-use PGD.
+	 *
+	 * Note!  Dummy roots are unique in that they are obsoleted by memslot
+	 * _creation_!  See also FNAME(fetch).
 	 */
 	sp = root_to_sp(root_hpa);
 	return !sp || is_obsolete_sp(kvm, sp);
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 95846c40e79e..b102014e2c60 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -36,6 +36,16 @@
 #define INVALID_PAE_ROOT	0
 #define IS_VALID_PAE_ROOT(x)	(!!(x))
 
+static inline hpa_t kvm_mmu_get_dummy_root(void)
+{
+	return my_zero_pfn(0) << PAGE_SHIFT;
+}
+
+static inline bool kvm_mmu_is_dummy_root(hpa_t shadow_page)
+{
+	return is_zero_pfn(shadow_page >> PAGE_SHIFT);
+}
+
 typedef u64 __rcu *tdp_ptep_t;
 
 struct kvm_mmu_page {
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 89eb45eb9dd5..c85255073f67 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -651,6 +651,17 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 	if (WARN_ON_ONCE(!VALID_PAGE(vcpu->arch.mmu->root.hpa)))
 		goto out_gpte_changed;
 
+	/*
+	 * Load a new root and retry the faulting instruction in the extremely
+	 * unlikely scenario that the guest root gfn became visible between
+	 * loading a dummy root and handling the resulting page fault, e.g. if
+	 * userspace create a memslot in the interim.
+	 */
+	if (unlikely(kvm_mmu_is_dummy_root(vcpu->arch.mmu->root.hpa))) {
+		kvm_make_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu);
+		goto out_gpte_changed;
+	}
+
 	for_each_shadow_entry(vcpu, fault->addr, it) {
 		gfn_t table_gfn;
 
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index 29e0c1c8caa6..d4e45de13da0 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -238,6 +238,9 @@ static inline struct kvm_mmu_page *sptep_to_sp(u64 *sptep)
 
 static inline struct kvm_mmu_page *root_to_sp(hpa_t root)
 {
+	if (kvm_mmu_is_dummy_root(root))
+		return NULL;
+
 	/*
 	 * The "root" may be a special root, e.g. a PAE entry, treat it as a
 	 * SPTE to ensure any non-PA bits are dropped.

From d10f3780bc2f80744d291e118c0c8bade54ed3b8 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 8 Aug 2023 15:40:59 -0700
Subject: [PATCH 0891/1189] KVM: x86/mmu: Include mmu.h in spte.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Explicitly include mmu.h in spte.h instead of relying on the "parent" to
include mmu.h.  spte.h references a variety of macros and variables that
are defined/declared in mmu.h, and so including spte.h before (or instead
of) mmu.h will result in build errors, e.g.

  arch/x86/kvm/mmu/spte.h: In function ‘is_mmio_spte’:
  arch/x86/kvm/mmu/spte.h:242:23: error: ‘enable_mmio_caching’ undeclared
    242 |                likely(enable_mmio_caching);
        |                       ^~~~~~~~~~~~~~~~~~~

  arch/x86/kvm/mmu/spte.h: In function ‘is_large_pte’:
  arch/x86/kvm/mmu/spte.h:302:22: error: ‘PT_PAGE_SIZE_MASK’ undeclared
    302 |         return pte & PT_PAGE_SIZE_MASK;
        |                      ^~~~~~~~~~~~~~~~~

  arch/x86/kvm/mmu/spte.h: In function ‘is_dirty_spte’:
  arch/x86/kvm/mmu/spte.h:332:56: error: ‘PT_WRITABLE_MASK’ undeclared
    332 |         return dirty_mask ? spte & dirty_mask : spte & PT_WRITABLE_MASK;
        |                                                        ^~~~~~~~~~~~~~~~

Fixes: 5a9624affe7c ("KVM: mmu: extract spte.h and spte.c")
Link: https://lore.kernel.org/r/20230808224059.2492476-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/spte.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index d4e45de13da0..a129951c9a88 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -3,6 +3,7 @@
 #ifndef KVM_X86_MMU_SPTE_H
 #define KVM_X86_MMU_SPTE_H
 
+#include "mmu.h"
 #include "mmu_internal.h"
 
 /*

From 478c3f5dcd8ca7eb1ef0c7a7022cca80b528325c Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 31 Aug 2023 00:14:19 -0700
Subject: [PATCH 0892/1189] perf list: Don't print Unit for "default_core"

"default_core" was added as a way to demark JSON events whose PMU should
be whatever the default core PMU is, previously this had been assumed to
be "cpu" but that fails on s390 and ARM.

'perf list' displays the PMU in the event description to save storing it
in JSON, but was still comparing against "cpu" and not "default_core",
so update this.

Fixes: d2045f87154bf67a ("perf jevents: Use "default_core" for events with no Unit")
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230831071421.2201358-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-list.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index 1ac47db4d66a..a343823c8ddf 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -148,7 +148,7 @@ static void default_print_event(void *ps, const char *pmu_name, const char *topi
 		char *desc_with_unit = NULL;
 		int desc_len = -1;
 
-		if (pmu_name && strcmp(pmu_name, "cpu")) {
+		if (pmu_name && strcmp(pmu_name, "default_core")) {
 			desc_len = strlen(desc);
 			desc_len = asprintf(&desc_with_unit,
 					    desc[desc_len - 1] != '.'

From 58d3a4cea4a45414a21a712078d95b39dcdda10d Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 31 Aug 2023 00:14:20 -0700
Subject: [PATCH 0893/1189] perf parse-events: Name the two term enums

Name the enums used by 'struct parse_events_term' to
parse_events__term_val_type and parse_events__term_type.

This allows greater compile time error checking.

Fix -Wswitch related issues by explicitly listing all enum values prior
to default.

Add config_term_name to safely look up a parse_events__term_type name,
bounds checking the array access first.

Add documentation to 'struct parse_events_terms' and reorder to save
space.

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230831071421.2201358-3-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.c | 174 ++++++++++++++++++++++++---------
 tools/perf/util/parse-events.h |  60 +++++++++---
 tools/perf/util/parse-events.l |   2 +-
 tools/perf/util/parse-events.y |  18 +++-
 4 files changed, 187 insertions(+), 67 deletions(-)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 0b941b58bdc0..51b73207e9f4 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -153,7 +153,7 @@ const char *event_type(int type)
 	return "unknown";
 }
 
-static char *get_config_str(struct list_head *head_terms, int type_term)
+static char *get_config_str(struct list_head *head_terms, enum parse_events__term_type type_term)
 {
 	struct parse_events_term *term;
 
@@ -722,7 +722,7 @@ int parse_events_add_breakpoint(struct parse_events_state *parse_state,
 
 static int check_type_val(struct parse_events_term *term,
 			  struct parse_events_error *err,
-			  int type)
+			  enum parse_events__term_val_type type)
 {
 	if (type == term->type_val)
 		return 0;
@@ -737,42 +737,49 @@ static int check_type_val(struct parse_events_term *term,
 	return -EINVAL;
 }
 
-/*
- * Update according to parse-events.l
- */
-static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = {
-	[PARSE_EVENTS__TERM_TYPE_USER]			= "<sysfs term>",
-	[PARSE_EVENTS__TERM_TYPE_CONFIG]		= "config",
-	[PARSE_EVENTS__TERM_TYPE_CONFIG1]		= "config1",
-	[PARSE_EVENTS__TERM_TYPE_CONFIG2]		= "config2",
-	[PARSE_EVENTS__TERM_TYPE_CONFIG3]		= "config3",
-	[PARSE_EVENTS__TERM_TYPE_NAME]			= "name",
-	[PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD]		= "period",
-	[PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ]		= "freq",
-	[PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE]	= "branch_type",
-	[PARSE_EVENTS__TERM_TYPE_TIME]			= "time",
-	[PARSE_EVENTS__TERM_TYPE_CALLGRAPH]		= "call-graph",
-	[PARSE_EVENTS__TERM_TYPE_STACKSIZE]		= "stack-size",
-	[PARSE_EVENTS__TERM_TYPE_NOINHERIT]		= "no-inherit",
-	[PARSE_EVENTS__TERM_TYPE_INHERIT]		= "inherit",
-	[PARSE_EVENTS__TERM_TYPE_MAX_STACK]		= "max-stack",
-	[PARSE_EVENTS__TERM_TYPE_MAX_EVENTS]		= "nr",
-	[PARSE_EVENTS__TERM_TYPE_OVERWRITE]		= "overwrite",
-	[PARSE_EVENTS__TERM_TYPE_NOOVERWRITE]		= "no-overwrite",
-	[PARSE_EVENTS__TERM_TYPE_DRV_CFG]		= "driver-config",
-	[PARSE_EVENTS__TERM_TYPE_PERCORE]		= "percore",
-	[PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT]		= "aux-output",
-	[PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE]	= "aux-sample-size",
-	[PARSE_EVENTS__TERM_TYPE_METRIC_ID]		= "metric-id",
-	[PARSE_EVENTS__TERM_TYPE_RAW]                   = "raw",
-	[PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE]          = "legacy-cache",
-	[PARSE_EVENTS__TERM_TYPE_HARDWARE]              = "hardware",
-};
-
 static bool config_term_shrinked;
 
+static const char *config_term_name(enum parse_events__term_type term_type)
+{
+	/*
+	 * Update according to parse-events.l
+	 */
+	static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = {
+		[PARSE_EVENTS__TERM_TYPE_USER]			= "<sysfs term>",
+		[PARSE_EVENTS__TERM_TYPE_CONFIG]		= "config",
+		[PARSE_EVENTS__TERM_TYPE_CONFIG1]		= "config1",
+		[PARSE_EVENTS__TERM_TYPE_CONFIG2]		= "config2",
+		[PARSE_EVENTS__TERM_TYPE_CONFIG3]		= "config3",
+		[PARSE_EVENTS__TERM_TYPE_NAME]			= "name",
+		[PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD]		= "period",
+		[PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ]		= "freq",
+		[PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE]	= "branch_type",
+		[PARSE_EVENTS__TERM_TYPE_TIME]			= "time",
+		[PARSE_EVENTS__TERM_TYPE_CALLGRAPH]		= "call-graph",
+		[PARSE_EVENTS__TERM_TYPE_STACKSIZE]		= "stack-size",
+		[PARSE_EVENTS__TERM_TYPE_NOINHERIT]		= "no-inherit",
+		[PARSE_EVENTS__TERM_TYPE_INHERIT]		= "inherit",
+		[PARSE_EVENTS__TERM_TYPE_MAX_STACK]		= "max-stack",
+		[PARSE_EVENTS__TERM_TYPE_MAX_EVENTS]		= "nr",
+		[PARSE_EVENTS__TERM_TYPE_OVERWRITE]		= "overwrite",
+		[PARSE_EVENTS__TERM_TYPE_NOOVERWRITE]		= "no-overwrite",
+		[PARSE_EVENTS__TERM_TYPE_DRV_CFG]		= "driver-config",
+		[PARSE_EVENTS__TERM_TYPE_PERCORE]		= "percore",
+		[PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT]		= "aux-output",
+		[PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE]	= "aux-sample-size",
+		[PARSE_EVENTS__TERM_TYPE_METRIC_ID]		= "metric-id",
+		[PARSE_EVENTS__TERM_TYPE_RAW]                   = "raw",
+		[PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE]          = "legacy-cache",
+		[PARSE_EVENTS__TERM_TYPE_HARDWARE]              = "hardware",
+	};
+	if ((unsigned int)term_type >= __PARSE_EVENTS__TERM_TYPE_NR)
+		return "unknown term";
+
+	return config_term_names[term_type];
+}
+
 static bool
-config_term_avail(int term_type, struct parse_events_error *err)
+config_term_avail(enum parse_events__term_type term_type, struct parse_events_error *err)
 {
 	char *err_str;
 
@@ -794,13 +801,31 @@ config_term_avail(int term_type, struct parse_events_error *err)
 	case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD:
 	case PARSE_EVENTS__TERM_TYPE_PERCORE:
 		return true;
+	case PARSE_EVENTS__TERM_TYPE_USER:
+	case PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ:
+	case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE:
+	case PARSE_EVENTS__TERM_TYPE_TIME:
+	case PARSE_EVENTS__TERM_TYPE_CALLGRAPH:
+	case PARSE_EVENTS__TERM_TYPE_STACKSIZE:
+	case PARSE_EVENTS__TERM_TYPE_NOINHERIT:
+	case PARSE_EVENTS__TERM_TYPE_INHERIT:
+	case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
+	case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
+	case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE:
+	case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
+	case PARSE_EVENTS__TERM_TYPE_DRV_CFG:
+	case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT:
+	case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE:
+	case PARSE_EVENTS__TERM_TYPE_RAW:
+	case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE:
+	case PARSE_EVENTS__TERM_TYPE_HARDWARE:
 	default:
 		if (!err)
 			return false;
 
 		/* term_type is validated so indexing is safe */
 		if (asprintf(&err_str, "'%s' is not usable in 'perf stat'",
-				config_term_names[term_type]) >= 0)
+			     config_term_name(term_type)) >= 0)
 			parse_events_error__handle(err, -1, err_str, NULL);
 		return false;
 	}
@@ -918,10 +943,14 @@ do {									   \
 			return -EINVAL;
 		}
 		break;
+	case PARSE_EVENTS__TERM_TYPE_DRV_CFG:
+	case PARSE_EVENTS__TERM_TYPE_USER:
+	case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE:
+	case PARSE_EVENTS__TERM_TYPE_HARDWARE:
 	default:
 		parse_events_error__handle(err, term->err_term,
-				strdup("unknown term"),
-				parse_events_formats_error_string(NULL));
+					strdup(config_term_name(term->type_term)),
+					parse_events_formats_error_string(NULL));
 		return -EINVAL;
 	}
 
@@ -1007,10 +1036,26 @@ static int config_term_tracepoint(struct perf_event_attr *attr,
 	case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT:
 	case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE:
 		return config_term_common(attr, term, err);
+	case PARSE_EVENTS__TERM_TYPE_USER:
+	case PARSE_EVENTS__TERM_TYPE_CONFIG:
+	case PARSE_EVENTS__TERM_TYPE_CONFIG1:
+	case PARSE_EVENTS__TERM_TYPE_CONFIG2:
+	case PARSE_EVENTS__TERM_TYPE_CONFIG3:
+	case PARSE_EVENTS__TERM_TYPE_NAME:
+	case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD:
+	case PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ:
+	case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE:
+	case PARSE_EVENTS__TERM_TYPE_TIME:
+	case PARSE_EVENTS__TERM_TYPE_DRV_CFG:
+	case PARSE_EVENTS__TERM_TYPE_PERCORE:
+	case PARSE_EVENTS__TERM_TYPE_METRIC_ID:
+	case PARSE_EVENTS__TERM_TYPE_RAW:
+	case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE:
+	case PARSE_EVENTS__TERM_TYPE_HARDWARE:
 	default:
 		if (err) {
 			parse_events_error__handle(err, term->err_term,
-				strdup("unknown term"),
+						   strdup(config_term_name(term->type_term)),
 				strdup("valid terms: call-graph,stack-size\n"));
 		}
 		return -EINVAL;
@@ -1128,6 +1173,16 @@ do {								\
 			ADD_CONFIG_TERM_VAL(AUX_SAMPLE_SIZE, aux_sample_size,
 					    term->val.num, term->weak);
 			break;
+		case PARSE_EVENTS__TERM_TYPE_USER:
+		case PARSE_EVENTS__TERM_TYPE_CONFIG:
+		case PARSE_EVENTS__TERM_TYPE_CONFIG1:
+		case PARSE_EVENTS__TERM_TYPE_CONFIG2:
+		case PARSE_EVENTS__TERM_TYPE_CONFIG3:
+		case PARSE_EVENTS__TERM_TYPE_NAME:
+		case PARSE_EVENTS__TERM_TYPE_METRIC_ID:
+		case PARSE_EVENTS__TERM_TYPE_RAW:
+		case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE:
+		case PARSE_EVENTS__TERM_TYPE_HARDWARE:
 		default:
 			break;
 		}
@@ -1157,6 +1212,30 @@ static int get_config_chgs(struct perf_pmu *pmu, struct list_head *head_config,
 		case PARSE_EVENTS__TERM_TYPE_CONFIG:
 			bits = ~(u64)0;
 			break;
+		case PARSE_EVENTS__TERM_TYPE_CONFIG1:
+		case PARSE_EVENTS__TERM_TYPE_CONFIG2:
+		case PARSE_EVENTS__TERM_TYPE_CONFIG3:
+		case PARSE_EVENTS__TERM_TYPE_NAME:
+		case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD:
+		case PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ:
+		case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE:
+		case PARSE_EVENTS__TERM_TYPE_TIME:
+		case PARSE_EVENTS__TERM_TYPE_CALLGRAPH:
+		case PARSE_EVENTS__TERM_TYPE_STACKSIZE:
+		case PARSE_EVENTS__TERM_TYPE_NOINHERIT:
+		case PARSE_EVENTS__TERM_TYPE_INHERIT:
+		case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
+		case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
+		case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE:
+		case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
+		case PARSE_EVENTS__TERM_TYPE_DRV_CFG:
+		case PARSE_EVENTS__TERM_TYPE_PERCORE:
+		case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT:
+		case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE:
+		case PARSE_EVENTS__TERM_TYPE_METRIC_ID:
+		case PARSE_EVENTS__TERM_TYPE_RAW:
+		case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE:
+		case PARSE_EVENTS__TERM_TYPE_HARDWARE:
 		default:
 			break;
 		}
@@ -2386,7 +2465,8 @@ static int new_term(struct parse_events_term **_term,
 }
 
 int parse_events_term__num(struct parse_events_term **term,
-			   int type_term, const char *config, u64 num,
+			   enum parse_events__term_type type_term,
+			   const char *config, u64 num,
 			   bool no_value,
 			   void *loc_term_, void *loc_val_)
 {
@@ -2396,7 +2476,7 @@ int parse_events_term__num(struct parse_events_term **term,
 	struct parse_events_term temp = {
 		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
 		.type_term = type_term,
-		.config    = config ? : strdup(config_term_names[type_term]),
+		.config    = config ? : strdup(config_term_name(type_term)),
 		.no_value  = no_value,
 		.err_term  = loc_term ? loc_term->first_column : 0,
 		.err_val   = loc_val  ? loc_val->first_column  : 0,
@@ -2406,7 +2486,8 @@ int parse_events_term__num(struct parse_events_term **term,
 }
 
 int parse_events_term__str(struct parse_events_term **term,
-			   int type_term, char *config, char *str,
+			   enum parse_events__term_type type_term,
+			   char *config, char *str,
 			   void *loc_term_, void *loc_val_)
 {
 	YYLTYPE *loc_term = loc_term_;
@@ -2424,11 +2505,12 @@ int parse_events_term__str(struct parse_events_term **term,
 }
 
 int parse_events_term__term(struct parse_events_term **term,
-			    int term_lhs, int term_rhs,
+			    enum parse_events__term_type term_lhs,
+			    enum parse_events__term_type term_rhs,
 			    void *loc_term, void *loc_val)
 {
 	return parse_events_term__str(term, term_lhs, NULL,
-				      strdup(config_term_names[term_rhs]),
+				      strdup(config_term_name(term_rhs)),
 				      loc_term, loc_val);
 }
 
@@ -2539,7 +2621,7 @@ int parse_events_term__to_strbuf(struct list_head *term_list, struct strbuf *sb)
 				if (ret < 0)
 					return ret;
 			} else if (term->type_term < __PARSE_EVENTS__TERM_TYPE_NR) {
-				ret = strbuf_addf(sb, "%s=", config_term_names[term->type_term]);
+				ret = strbuf_addf(sb, "%s=", config_term_name(term->type_term));
 				if (ret < 0)
 					return ret;
 			}
@@ -2567,7 +2649,7 @@ static void config_terms_list(char *buf, size_t buf_sz)
 
 	buf[0] = '\0';
 	for (i = 0; i < __PARSE_EVENTS__TERM_TYPE_NR; i++) {
-		const char *name = config_term_names[i];
+		const char *name = config_term_name(i);
 
 		if (!config_term_avail(i, NULL))
 			continue;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 20bdc35d6112..855b0725c5d4 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -48,12 +48,12 @@ int parse_events_terms(struct list_head *terms, const char *str, FILE *input);
 int parse_filter(const struct option *opt, const char *str, int unset);
 int exclude_perf(const struct option *opt, const char *arg, int unset);
 
-enum {
+enum parse_events__term_val_type {
 	PARSE_EVENTS__TERM_TYPE_NUM,
 	PARSE_EVENTS__TERM_TYPE_STR,
 };
 
-enum {
+enum parse_events__term_type {
 	PARSE_EVENTS__TERM_TYPE_USER,
 	PARSE_EVENTS__TERM_TYPE_CONFIG,
 	PARSE_EVENTS__TERM_TYPE_CONFIG1,
@@ -80,27 +80,54 @@ enum {
 	PARSE_EVENTS__TERM_TYPE_RAW,
 	PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE,
 	PARSE_EVENTS__TERM_TYPE_HARDWARE,
-	__PARSE_EVENTS__TERM_TYPE_NR,
+#define	__PARSE_EVENTS__TERM_TYPE_NR (PARSE_EVENTS__TERM_TYPE_HARDWARE + 1)
 };
 
 struct parse_events_term {
+	/** @list: The term list the term is a part of. */
+	struct list_head list;
+	/**
+	 * @config: The left-hand side of a term assignment, so the term
+	 * "event=8" would have the config be "event"
+	 */
 	const char *config;
+	/**
+	 * @val: The right-hand side of a term assignment that can either be a
+	 * string or a number depending on type_val.
+	 */
 	union {
 		char *str;
 		u64  num;
 	} val;
-	int type_val;
-	int type_term;
-	struct list_head list;
-	bool used;
-	bool no_value;
-
-	/* error string indexes for within parsed string */
+	/** @type_val: The union variable in val to be used for the term. */
+	enum parse_events__term_val_type type_val;
+	/**
+	 * @type_term: A predefined term type or PARSE_EVENTS__TERM_TYPE_USER
+	 * when not inbuilt.
+	 */
+	enum parse_events__term_type type_term;
+	/**
+	 * @err_term: The column index of the term from parsing, used during
+	 * error output.
+	 */
 	int err_term;
+	/**
+	 * @err_val: The column index of the val from parsing, used during error
+	 * output.
+	 */
 	int err_val;
-
-	/* Coming from implicit alias */
+	/** @used: Was the term used during parameterized-eval. */
+	bool used;
+	/**
+	 * @weak: A term from the sysfs or json encoding of an event that
+	 * shouldn't override terms coming from the command line.
+	 */
 	bool weak;
+	/**
+	 * @no_value: Is there no value. TODO: this should really be part of
+	 * type_val.
+	 */
+	bool no_value;
 };
 
 struct parse_events_error {
@@ -139,14 +166,17 @@ bool parse_events__filter_pmu(const struct parse_events_state *parse_state,
 void parse_events__shrink_config_terms(void);
 int parse_events__is_hardcoded_term(struct parse_events_term *term);
 int parse_events_term__num(struct parse_events_term **term,
-			   int type_term, const char *config, u64 num,
+			   enum parse_events__term_type type_term,
+			   const char *config, u64 num,
 			   bool novalue,
 			   void *loc_term, void *loc_val);
 int parse_events_term__str(struct parse_events_term **term,
-			   int type_term, char *config, char *str,
+			   enum parse_events__term_type type_term,
+			   char *config, char *str,
 			   void *loc_term, void *loc_val);
 int parse_events_term__term(struct parse_events_term **term,
-			    int term_lhs, int term_rhs,
+			    enum parse_events__term_type term_lhs,
+			    enum parse_events__term_type term_rhs,
 			    void *loc_term, void *loc_val);
 int parse_events_term__clone(struct parse_events_term **new,
 			     struct parse_events_term *term);
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 1147084b2c76..4ef4b6f171a0 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -116,7 +116,7 @@ static int tool(yyscan_t scanner, enum perf_tool_event event)
 	return PE_VALUE_SYM_TOOL;
 }
 
-static int term(yyscan_t scanner, int type)
+static int term(yyscan_t scanner, enum parse_events__term_type type)
 {
 	YYSTYPE *yylval = parse_events_get_lval(scanner);
 
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 4a370c36a0d5..534daed91c50 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -777,7 +777,8 @@ PE_TERM_HW
 PE_TERM '=' name_or_legacy
 {
 	struct parse_events_term *term;
-	int err = parse_events_term__str(&term, (int)$1, NULL, $3, &@1, &@3);
+	int err = parse_events_term__str(&term, (enum parse_events__term_type)$1,
+					/*config=*/NULL, $3, &@1, &@3);
 
 	if (err) {
 		free($3);
@@ -789,7 +790,8 @@ PE_TERM '=' name_or_legacy
 PE_TERM '=' PE_TERM_HW
 {
 	struct parse_events_term *term;
-	int err = parse_events_term__str(&term, (int)$1, NULL, $3.str, &@1, &@3);
+	int err = parse_events_term__str(&term, (enum parse_events__term_type)$1,
+					 /*config=*/NULL, $3.str, &@1, &@3);
 
 	if (err) {
 		free($3.str);
@@ -801,7 +803,10 @@ PE_TERM '=' PE_TERM_HW
 PE_TERM '=' PE_TERM
 {
 	struct parse_events_term *term;
-	int err = parse_events_term__term(&term, (int)$1, (int)$3, &@1, &@3);
+	int err = parse_events_term__term(&term,
+					  (enum parse_events__term_type)$1,
+					  (enum parse_events__term_type)$3,
+					  &@1, &@3);
 
 	if (err)
 		PE_ABORT(err);
@@ -812,7 +817,8 @@ PE_TERM '=' PE_TERM
 PE_TERM '=' PE_VALUE
 {
 	struct parse_events_term *term;
-	int err = parse_events_term__num(&term, (int)$1, NULL, $3, false, &@1, &@3);
+	int err = parse_events_term__num(&term, (enum parse_events__term_type)$1,
+					 /*config=*/NULL, $3, /*novalue=*/false, &@1, &@3);
 
 	if (err)
 		PE_ABORT(err);
@@ -823,7 +829,9 @@ PE_TERM '=' PE_VALUE
 PE_TERM
 {
 	struct parse_events_term *term;
-	int err = parse_events_term__num(&term, (int)$1, NULL, 1, true, &@1, NULL);
+	int err = parse_events_term__num(&term, (enum parse_events__term_type)$1,
+					/*config=*/NULL, /*num=*/1, /*novalue=*/true,
+					&@1, /*loc_val=*/NULL);
 
 	if (err)
 		PE_ABORT(err);

From 64199ae4b8a36038dd5b69904a29bd48ef11ca8b Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 31 Aug 2023 00:14:21 -0700
Subject: [PATCH 0894/1189] perf parse-events: Fix propagation of term's
 no_value when cloning

The no_value field in 'struct parse_events_term' indicates that the val
variable isn't used, the case for an event name.

Cloning wasn't propagating this, making cloned event name terms
appearing to have a constant assinged to them.

Working around the bug would check for a value of 1 assigned to value,
but then this meant a user value of 1 couldn't be differentiated causing
the value to be lost in debug printing and perf list.

The change fixes the cloning and updates the "val.num ==/!= 1" tests to
use no_value instead.

To better check the no_value is set appropriately parameter comments are
added for constant values.

This found that no_value wasn't set correctly in parse_events_multi_pmu_add,
which matters now that no_value is used to indicate an event name.

Fixes: 7a6e91644708d514 ("perf parse-events: Make common term list to strbuf helper")
Fixes: 99e7138eb7897aa0 ("perf tools: Fail on using multiple bits long terms without value")
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230831071421.2201358-4-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.c | 29 +++++++++++++----------------
 tools/perf/util/parse-events.y |  9 +++++----
 tools/perf/util/pmu.c          |  2 +-
 3 files changed, 19 insertions(+), 21 deletions(-)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 51b73207e9f4..68fe2c4ff49f 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1510,8 +1510,8 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 
 	if (parse_events_term__num(&term,
 				   PARSE_EVENTS__TERM_TYPE_USER,
-				   config, 1, false, NULL,
-					NULL) < 0) {
+				   config, /*num=*/1, /*novalue=*/true,
+				   loc, /*loc_val=*/NULL) < 0) {
 		zfree(&config);
 		goto out_err;
 	}
@@ -2482,7 +2482,7 @@ int parse_events_term__num(struct parse_events_term **term,
 		.err_val   = loc_val  ? loc_val->first_column  : 0,
 	};
 
-	return new_term(term, &temp, NULL, num);
+	return new_term(term, &temp, /*str=*/NULL, num);
 }
 
 int parse_events_term__str(struct parse_events_term **term,
@@ -2501,7 +2501,7 @@ int parse_events_term__str(struct parse_events_term **term,
 		.err_val   = loc_val  ? loc_val->first_column  : 0,
 	};
 
-	return new_term(term, &temp, str, 0);
+	return new_term(term, &temp, str, /*num=*/0);
 }
 
 int parse_events_term__term(struct parse_events_term **term,
@@ -2518,26 +2518,21 @@ int parse_events_term__clone(struct parse_events_term **new,
 			     struct parse_events_term *term)
 {
 	char *str;
-	struct parse_events_term temp = {
-		.type_val  = term->type_val,
-		.type_term = term->type_term,
-		.config    = NULL,
-		.err_term  = term->err_term,
-		.err_val   = term->err_val,
-	};
+	struct parse_events_term temp = *term;
 
+	temp.used = false;
 	if (term->config) {
 		temp.config = strdup(term->config);
 		if (!temp.config)
 			return -ENOMEM;
 	}
 	if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM)
-		return new_term(new, &temp, NULL, term->val.num);
+		return new_term(new, &temp, /*str=*/NULL, term->val.num);
 
 	str = strdup(term->val.str);
 	if (!str)
 		return -ENOMEM;
-	return new_term(new, &temp, str, 0);
+	return new_term(new, &temp, str, /*num=*/0);
 }
 
 void parse_events_term__delete(struct parse_events_term *term)
@@ -2611,20 +2606,22 @@ int parse_events_term__to_strbuf(struct list_head *term_list, struct strbuf *sb)
 		first = false;
 
 		if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM)
-			if (term->type_term == PARSE_EVENTS__TERM_TYPE_USER && term->val.num == 1)
+			if (term->no_value) {
+				assert(term->type_term == PARSE_EVENTS__TERM_TYPE_USER);
 				ret = strbuf_addf(sb, "%s", term->config);
-			else
+			} else
 				ret = strbuf_addf(sb, "%s=%#"PRIx64, term->config, term->val.num);
 		else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) {
 			if (term->config) {
 				ret = strbuf_addf(sb, "%s=", term->config);
 				if (ret < 0)
 					return ret;
-			} else if (term->type_term < __PARSE_EVENTS__TERM_TYPE_NR) {
+			} else if ((unsigned int)term->type_term < __PARSE_EVENTS__TERM_TYPE_NR) {
 				ret = strbuf_addf(sb, "%s=", config_term_name(term->type_term));
 				if (ret < 0)
 					return ret;
 			}
+			assert(!term->no_value);
 			ret = strbuf_addf(sb, "%s", term->val.str);
 		}
 		if (ret < 0)
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 534daed91c50..4a305df61f74 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -712,7 +712,7 @@ name_or_raw '=' PE_VALUE
 {
 	struct parse_events_term *term;
 	int err = parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					 $1, $3, false, &@1, &@3);
+					 $1, $3, /*novalue=*/false, &@1, &@3);
 
 	if (err) {
 		free($1);
@@ -739,7 +739,7 @@ PE_LEGACY_CACHE
 {
 	struct parse_events_term *term;
 	int err = parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE,
-					 $1, 1, true, &@1, NULL);
+					 $1, /*num=*/1, /*novalue=*/true, &@1, /*loc_val=*/NULL);
 
 	if (err) {
 		free($1);
@@ -752,7 +752,7 @@ PE_NAME
 {
 	struct parse_events_term *term;
 	int err = parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					 $1, 1, true, &@1, NULL);
+					 $1, /*num=*/1, /*novalue=*/true, &@1, /*loc_val=*/NULL);
 
 	if (err) {
 		free($1);
@@ -765,7 +765,8 @@ PE_TERM_HW
 {
 	struct parse_events_term *term;
 	int err = parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_HARDWARE,
-					 $1.str, $1.num & 255, false, &@1, NULL);
+					 $1.str, $1.num & 255, /*novalue=*/false,
+					 &@1, /*loc_val=*/NULL);
 
 	if (err) {
 		free($1.str);
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 152cda84f273..d85602aa4b9f 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1396,7 +1396,7 @@ static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
 		return NULL;
 
 	if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) {
-		if (term->val.num != 1)
+		if (!term->no_value)
 			return NULL;
 		if (pmu_find_format(&pmu->format, term->config))
 			return NULL;

From 6a86b5b5cd76d2734304a0173f5f01aa8aa2025e Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 29 Aug 2023 22:53:52 +0200
Subject: [PATCH 0895/1189] bpf: Annotate bpf_long_memcpy with data_race

syzbot reported a data race splat between two processes trying to
update the same BPF map value via syscall on different CPUs:

  BUG: KCSAN: data-race in bpf_percpu_array_update / bpf_percpu_array_update

  write to 0xffffe8fffe7425d8 of 8 bytes by task 8257 on cpu 1:
   bpf_long_memcpy include/linux/bpf.h:428 [inline]
   bpf_obj_memcpy include/linux/bpf.h:441 [inline]
   copy_map_value_long include/linux/bpf.h:464 [inline]
   bpf_percpu_array_update+0x3bb/0x500 kernel/bpf/arraymap.c:380
   bpf_map_update_value+0x190/0x370 kernel/bpf/syscall.c:175
   generic_map_update_batch+0x3ae/0x4f0 kernel/bpf/syscall.c:1749
   bpf_map_do_batch+0x2df/0x3d0 kernel/bpf/syscall.c:4648
   __sys_bpf+0x28a/0x780
   __do_sys_bpf kernel/bpf/syscall.c:5241 [inline]
   __se_sys_bpf kernel/bpf/syscall.c:5239 [inline]
   __x64_sys_bpf+0x43/0x50 kernel/bpf/syscall.c:5239
   do_syscall_x64 arch/x86/entry/common.c:50 [inline]
   do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80
   entry_SYSCALL_64_after_hwframe+0x63/0xcd

  write to 0xffffe8fffe7425d8 of 8 bytes by task 8268 on cpu 0:
   bpf_long_memcpy include/linux/bpf.h:428 [inline]
   bpf_obj_memcpy include/linux/bpf.h:441 [inline]
   copy_map_value_long include/linux/bpf.h:464 [inline]
   bpf_percpu_array_update+0x3bb/0x500 kernel/bpf/arraymap.c:380
   bpf_map_update_value+0x190/0x370 kernel/bpf/syscall.c:175
   generic_map_update_batch+0x3ae/0x4f0 kernel/bpf/syscall.c:1749
   bpf_map_do_batch+0x2df/0x3d0 kernel/bpf/syscall.c:4648
   __sys_bpf+0x28a/0x780
   __do_sys_bpf kernel/bpf/syscall.c:5241 [inline]
   __se_sys_bpf kernel/bpf/syscall.c:5239 [inline]
   __x64_sys_bpf+0x43/0x50 kernel/bpf/syscall.c:5239
   do_syscall_x64 arch/x86/entry/common.c:50 [inline]
   do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80
   entry_SYSCALL_64_after_hwframe+0x63/0xcd

  value changed: 0x0000000000000000 -> 0xfffffff000002788

The bpf_long_memcpy is used with 8-byte aligned pointers, power-of-8 size
and forced to use long read/writes to try to atomically copy long counters.
It is best-effort only and no barriers are here since it _will_ race with
concurrent updates from BPF programs. The bpf_long_memcpy() is called from
bpf(2) syscall. Marco suggested that the best way to make this known to
KCSAN would be to use data_race() annotation.

Reported-by: syzbot+97522333291430dd277f@syzkaller.appspotmail.com
Suggested-by: Marco Elver <elver@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Marco Elver <elver@google.com>
Link: https://lore.kernel.org/bpf/000000000000d87a7f06040c970c@google.com
Link: https://lore.kernel.org/bpf/57628f7a15e20d502247c3b55fceb1cb2b31f266.1693342186.git.daniel@iogearbox.net
---
 include/linux/bpf.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 12596af59c00..024e8b28c34b 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -438,7 +438,7 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size)
 
 	size /= sizeof(long);
 	while (size--)
-		*ldst++ = *lsrc++;
+		data_race(*ldst++ = *lsrc++);
 }
 
 /* copy everything but bpf_spin_lock, bpf_timer, and kptrs. There could be one of each. */

From be8e754cbfac698d6304bb8382c8d18ac74424d3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= <bjorn@rivosinc.com>
Date: Thu, 31 Aug 2023 18:29:54 +0200
Subject: [PATCH 0896/1189] selftests/bpf: Include build flavors for install
 target
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When using the "install" or targets depending on install, e.g. "gen_tar",
the BPF machine flavors weren't included.

A command like:
  | make ARCH=riscv CROSS_COMPILE=riscv64-linux-gnu- O=/workspace/kbuild \
  |    HOSTCC=gcc FORMAT= SKIP_TARGETS="arm64 ia64 powerpc sparc64 x86 sgx" \
  |    -C tools/testing/selftests gen_tar
would not include bpf/no_alu32, bpf/cpuv4, or bpf/bpf-gcc.

Include the BPF machine flavors for "install" make target.

Signed-off-by: Björn Töpel <bjorn@rivosinc.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20230831162954.111485-1-bjorn@kernel.org
---
 tools/testing/selftests/bpf/Makefile | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index edef49fcd23e..caede9b574cb 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -50,14 +50,17 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test
 	test_cgroup_storage \
 	test_tcpnotify_user test_sysctl \
 	test_progs-no_alu32
+TEST_INST_SUBDIRS := no_alu32
 
 # Also test bpf-gcc, if present
 ifneq ($(BPF_GCC),)
 TEST_GEN_PROGS += test_progs-bpf_gcc
+TEST_INST_SUBDIRS += bpf_gcc
 endif
 
 ifneq ($(CLANG_CPUV4),)
 TEST_GEN_PROGS += test_progs-cpuv4
+TEST_INST_SUBDIRS += cpuv4
 endif
 
 TEST_GEN_FILES = test_lwt_ip_encap.bpf.o test_tc_edt.bpf.o
@@ -714,3 +717,12 @@ EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) $(HOST_SCRATCH_DIR)	\
 
 # Delete partially updated (corrupted) files on error
 .DELETE_ON_ERROR:
+
+DEFAULT_INSTALL_RULE := $(INSTALL_RULE)
+override define INSTALL_RULE
+	$(DEFAULT_INSTALL_RULE)
+	@for DIR in $(TEST_INST_SUBDIRS); do		  \
+		mkdir -p $(INSTALL_PATH)/$$DIR;   \
+		rsync -a $(OUTPUT)/$$DIR/*.bpf.o $(INSTALL_PATH)/$$DIR;\
+	done
+endef

From 44e60b14d5a72f91fd0bdeae8da59ae37a3ca8e5 Mon Sep 17 00:00:00 2001
From: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Date: Tue, 16 May 2023 12:21:19 -0400
Subject: [PATCH 0897/1189] drm/amd/display: Enable Replay for static screen
 use cases

- Setup replay config on device init.
- Enable replay if feature is enabled (prioritize replay over PSR, since
it can be enabled in more usecases)
- Add debug masks to enable replay on supported ASICs

Signed-off-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 22 +++++++++++++++++++
 .../amd/display/amdgpu_dm/amdgpu_dm_crtc.c    |  9 +++++++-
 drivers/gpu/drm/amd/include/amd_shared.h      |  2 ++
 3 files changed, 32 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 268cb99a4c4b..f2b4f1720abd 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -65,6 +65,7 @@
 #include "amdgpu_dm_debugfs.h"
 #endif
 #include "amdgpu_dm_psr.h"
+#include "amdgpu_dm_replay.h"
 
 #include "ivsrcid/ivsrcid_vislands30.h"
 
@@ -4265,6 +4266,7 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 	enum dc_connection_type new_connection_type = dc_connection_none;
 	const struct dc_plane_cap *plane;
 	bool psr_feature_enabled = false;
+	bool replay_feature_enabled = false;
 	int max_overlay = dm->dc->caps.max_slave_planes;
 
 	dm->display_indexes_num = dm->dc->caps.max_streams;
@@ -4374,6 +4376,20 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 		}
 	}
 
+	if (!(amdgpu_dc_debug_mask & DC_DISABLE_REPLAY)) {
+		switch (adev->ip_versions[DCE_HWIP][0]) {
+		case IP_VERSION(3, 1, 4):
+		case IP_VERSION(3, 1, 5):
+		case IP_VERSION(3, 1, 6):
+		case IP_VERSION(3, 2, 0):
+		case IP_VERSION(3, 2, 1):
+			replay_feature_enabled = true;
+			break;
+		default:
+			replay_feature_enabled = amdgpu_dc_feature_mask & DC_REPLAY_MASK;
+			break;
+		}
+	}
 	/* loops over all connectors on the board */
 	for (i = 0; i < link_cnt; i++) {
 		struct dc_link *link = NULL;
@@ -4422,6 +4438,12 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 				amdgpu_dm_update_connector_after_detect(aconnector);
 				setup_backlight_device(dm, aconnector);
 
+				/*
+				 * Disable psr if replay can be enabled
+				 */
+				if (replay_feature_enabled && amdgpu_dm_setup_replay(link, aconnector))
+					psr_feature_enabled = false;
+
 				if (psr_feature_enabled)
 					amdgpu_dm_set_psr_caps(link);
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
index 30d4c6fd95f5..97b7a0b8a1c2 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
@@ -29,6 +29,7 @@
 #include "dc.h"
 #include "amdgpu.h"
 #include "amdgpu_dm_psr.h"
+#include "amdgpu_dm_replay.h"
 #include "amdgpu_dm_crtc.h"
 #include "amdgpu_dm_plane.h"
 #include "amdgpu_dm_trace.h"
@@ -123,7 +124,12 @@ static void vblank_control_worker(struct work_struct *work)
 	 * fill_dc_dirty_rects().
 	 */
 	if (vblank_work->stream && vblank_work->stream->link) {
-		if (vblank_work->enable) {
+		/*
+		 * Prioritize replay, instead of psr
+		 */
+		if (vblank_work->stream->link->replay_settings.replay_feature_enabled)
+			amdgpu_dm_replay_enable(vblank_work->stream, false);
+		else if (vblank_work->enable) {
 			if (vblank_work->stream->link->psr_settings.psr_version < DC_PSR_VERSION_SU_1 &&
 			    vblank_work->stream->link->psr_settings.psr_allow_active)
 				amdgpu_dm_psr_disable(vblank_work->stream);
@@ -132,6 +138,7 @@ static void vblank_control_worker(struct work_struct *work)
 #ifdef CONFIG_DRM_AMD_SECURE_DISPLAY
 			   !amdgpu_dm_crc_window_is_activated(&vblank_work->acrtc->base) &&
 #endif
+			   vblank_work->stream->link->panel_config.psr.disallow_replay &&
 			   vblank_work->acrtc->dm_irq_params.allow_psr_entry) {
 			amdgpu_dm_psr_enable(vblank_work->stream);
 		}
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index abe829bbd54a..67d7b7ee8a2a 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -240,6 +240,7 @@ enum DC_FEATURE_MASK {
 	DC_DISABLE_LTTPR_DP2_0 = (1 << 6), //0x40, disabled by default
 	DC_PSR_ALLOW_SMU_OPT = (1 << 7), //0x80, disabled by default
 	DC_PSR_ALLOW_MULTI_DISP_OPT = (1 << 8), //0x100, disabled by default
+	DC_REPLAY_MASK = (1 << 9), //0x200, disabled by default for dcn < 3.1.4
 };
 
 enum DC_DEBUG_MASK {
@@ -250,6 +251,7 @@ enum DC_DEBUG_MASK {
 	DC_DISABLE_PSR = 0x10,
 	DC_FORCE_SUBVP_MCLK_SWITCH = 0x20,
 	DC_DISABLE_MPO = 0x40,
+	DC_DISABLE_REPLAY = 0x50,
 	DC_ENABLE_DPIA_TRACE = 0x80,
 };
 

From 89df3dbeee40216ff23c1556bdfa8e653f296020 Mon Sep 17 00:00:00 2001
From: Bokun Zhang <bokun.zhang@amd.com>
Date: Mon, 14 Aug 2023 17:06:45 -0400
Subject: [PATCH 0898/1189] drm/amdgpu/pm: Add notification for no DC support

- There is a DPM issue where if DC is not present,
  FCLK will stay at low level.
  We need to send a SMU message to configure the DPM

- Reuse smu_v13_0_notify_display_change() for this purpose

Reviewed-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Bokun Zhang <bokun.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h             | 5 +----
 .../gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_0_ppsmc.h  | 5 ++++-
 drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h              | 3 ++-
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c            | 8 ++------
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c      | 2 ++
 5 files changed, 11 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
index 95eb8a5eb54f..5a52098bcf16 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -1031,10 +1031,7 @@ struct pptable_funcs {
 						   enum smu_feature_mask mask);
 
 	/**
-	 * @notify_display_change: Enable fast memory clock switching.
-	 *
-	 * Allows for fine grained memory clock switching but has more stringent
-	 * timing requirements.
+	 * @notify_display_change: General interface call to let SMU know about DC change
 	 */
 	int (*notify_display_change)(struct smu_context *smu);
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_0_ppsmc.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_0_ppsmc.h
index 10cff75b44d5..e2ee855c7748 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_0_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_0_ppsmc.h
@@ -138,7 +138,10 @@
 #define PPSMC_MSG_SetBadMemoryPagesRetiredFlagsPerChannel 0x4A
 #define PPSMC_MSG_SetPriorityDeltaGain           0x4B
 #define PPSMC_MSG_AllowIHHostInterrupt           0x4C
-#define PPSMC_Message_Count                      0x4D
+
+#define PPSMC_MSG_DALNotPresent                  0x4E
+
+#define PPSMC_Message_Count                      0x4F
 
 //Debug Dump Message
 #define DEBUGSMC_MSG_TestMessage                    0x1
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
index 297b70b9388f..f71fc99447f2 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
@@ -245,7 +245,8 @@
 	__SMU_DUMMY_MAP(AllowGpo),	\
 	__SMU_DUMMY_MAP(Mode2Reset),	\
 	__SMU_DUMMY_MAP(RequestI2cTransaction), \
-	__SMU_DUMMY_MAP(GetMetricsTable),
+	__SMU_DUMMY_MAP(GetMetricsTable), \
+	__SMU_DUMMY_MAP(DALNotPresent),
 
 #undef __SMU_DUMMY_MAP
 #define __SMU_DUMMY_MAP(type)	SMU_MSG_##type
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
index f1282fc4b90a..0232adb95df3 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
@@ -837,12 +837,8 @@ int smu_v13_0_notify_display_change(struct smu_context *smu)
 {
 	int ret = 0;
 
-	if (!smu->pm_enabled)
-		return ret;
-
-	if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_DPM_UCLK_BIT) &&
-	    smu->adev->gmc.vram_type == AMDGPU_VRAM_TYPE_HBM)
-		ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetUclkFastSwitch, 1, NULL);
+	if (!amdgpu_device_has_dc_support(smu->adev))
+		ret = smu_cmn_send_smc_msg(smu, SMU_MSG_DALNotPresent, NULL);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index 8b7403ba89d7..3903a47669e4 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -162,6 +162,7 @@ static struct cmn2asic_msg_mapping smu_v13_0_0_message_map[SMU_MSG_MAX_COUNT] =
 	MSG_MAP(AllowGpo,			PPSMC_MSG_SetGpoAllow,           0),
 	MSG_MAP(AllowIHHostInterrupt,		PPSMC_MSG_AllowIHHostInterrupt,       0),
 	MSG_MAP(ReenableAcDcInterrupt,		PPSMC_MSG_ReenableAcDcInterrupt,       0),
+	MSG_MAP(DALNotPresent,		PPSMC_MSG_DALNotPresent,       0),
 };
 
 static struct cmn2asic_mapping smu_v13_0_0_clk_map[SMU_CLK_COUNT] = {
@@ -2687,6 +2688,7 @@ static const struct pptable_funcs smu_v13_0_0_ppt_funcs = {
 	.send_hbm_bad_channel_flag = smu_v13_0_0_send_bad_mem_channel_flag,
 	.gpo_control = smu_v13_0_gpo_control,
 	.get_ecc_info = smu_v13_0_0_get_ecc_info,
+	.notify_display_change = smu_v13_0_notify_display_change,
 };
 
 void smu_v13_0_0_set_ppt_funcs(struct smu_context *smu)

From fd27af4d5dab9aab591aba3b94bf337df756d3a3 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Wed, 16 Aug 2023 09:07:42 +0530
Subject: [PATCH 0899/1189] Documentation/gpu: Update amdgpu documentation

7957ec80ef97 ("drm/amdgpu: Add FRU sysfs nodes only if needed") moved
the documentation for some of the sysfs nodes to amdgpu_fru_eeprom.c.
Update the documentation accordingly.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 Documentation/gpu/amdgpu/driver-misc.rst | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/Documentation/gpu/amdgpu/driver-misc.rst b/Documentation/gpu/amdgpu/driver-misc.rst
index be131e963d87..4321c38fef21 100644
--- a/Documentation/gpu/amdgpu/driver-misc.rst
+++ b/Documentation/gpu/amdgpu/driver-misc.rst
@@ -11,19 +11,19 @@ via sysfs
 product_name
 ------------
 
-.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c
    :doc: product_name
 
 product_number
 --------------
 
-.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
-   :doc: product_name
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c
+   :doc: product_number
 
 serial_number
 -------------
 
-.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c
    :doc: serial_number
 
 unique_id

From 4b721ed87e63a654fd0eccbf9284c9436ffc0ced Mon Sep 17 00:00:00 2001
From: Candice Li <candice.li@amd.com>
Date: Wed, 16 Aug 2023 21:33:04 +0800
Subject: [PATCH 0900/1189] drm/amdgpu: Only support RAS EEPROM on dGPU
 platform

RAS EEPROM device is only supported on dGPU platform for smu v13_0_6.

Signed-off-by: Candice Li <candice.li@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 4764d2171f92..595d5e535aca 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -158,9 +158,10 @@ static bool __is_ras_eeprom_supported(struct amdgpu_device *adev)
 	case IP_VERSION(11, 0, 7): /* Sienna cichlid */
 	case IP_VERSION(13, 0, 0):
 	case IP_VERSION(13, 0, 2): /* Aldebaran */
-	case IP_VERSION(13, 0, 6):
 	case IP_VERSION(13, 0, 10):
 		return true;
+	case IP_VERSION(13, 0, 6):
+		return (adev->gmc.is_app_apu) ? false : true;
 	default:
 		return false;
 	}

From d4f6425a5615bbeaee1d14663205b23f82dc0313 Mon Sep 17 00:00:00 2001
From: Le Ma <le.ma@amd.com>
Date: Mon, 14 Aug 2023 16:27:59 +0800
Subject: [PATCH 0901/1189] drm/amdgpu: update mall info v2 from discovery

Mall info v2 is introduced in ip discovery

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Shiwu Zhang <shiwu.zhang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c | 5 +++++
 drivers/gpu/drm/amd/include/discovery.h       | 8 +++++++-
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index 74ffe6581c85..d4a7e33653d9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -1478,6 +1478,7 @@ static int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev)
 
 union mall_info {
 	struct mall_info_v1_0 v1;
+	struct mall_info_v2_0 v2;
 };
 
 static int amdgpu_discovery_get_mall_info(struct amdgpu_device *adev)
@@ -1518,6 +1519,10 @@ static int amdgpu_discovery_get_mall_info(struct amdgpu_device *adev)
 		adev->gmc.mall_size = mall_size;
 		adev->gmc.m_half_use = half_use;
 		break;
+	case 2:
+		mall_size_per_umc = le32_to_cpu(mall_info->v2.mall_size_per_umc);
+		adev->gmc.mall_size = mall_size_per_umc * adev->gmc.num_umc;
+		break;
 	default:
 		dev_err(adev->dev,
 			"Unhandled MALL info table %d.%d\n",
diff --git a/drivers/gpu/drm/amd/include/discovery.h b/drivers/gpu/drm/amd/include/discovery.h
index f43e29722ef7..b9884e576f98 100644
--- a/drivers/gpu/drm/amd/include/discovery.h
+++ b/drivers/gpu/drm/amd/include/discovery.h
@@ -30,7 +30,7 @@
 #define GC_TABLE_ID                     0x4347
 #define HARVEST_TABLE_SIGNATURE         0x56524148
 #define VCN_INFO_TABLE_ID               0x004E4356
-#define MALL_INFO_TABLE_ID              0x4D414C4C
+#define MALL_INFO_TABLE_ID              0x4C4C414D
 
 typedef enum
 {
@@ -312,6 +312,12 @@ struct mall_info_v1_0 {
 	uint32_t reserved[5];
 };
 
+struct mall_info_v2_0 {
+	struct mall_info_header header;
+	uint32_t mall_size_per_umc;
+	uint32_t reserved[8];
+};
+
 #define VCN_INFO_TABLE_MAX_NUM_INSTANCES 4
 
 struct vcn_info_header {

From 46b55e25c94af1689636f4be1760fb0d9ddd8ae2 Mon Sep 17 00:00:00 2001
From: Le Ma <le.ma@amd.com>
Date: Mon, 14 Aug 2023 18:37:28 +0800
Subject: [PATCH 0902/1189] drm/amdgpu: update gc_info v2_1 from discovery

Several new fields are exposed in gc_info v2_1

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Shiwu Zhang <shiwu.zhang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c | 10 +++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h       |  3 ++
 drivers/gpu/drm/amd/include/discovery.h       | 30 +++++++++++++++++++
 3 files changed, 43 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index d4a7e33653d9..7d5e7ad28ba8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -1390,6 +1390,7 @@ union gc_info {
 	struct gc_info_v1_1 v1_1;
 	struct gc_info_v1_2 v1_2;
 	struct gc_info_v2_0 v2;
+	struct gc_info_v2_1 v2_1;
 };
 
 static int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev)
@@ -1465,6 +1466,15 @@ static int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev)
 		adev->gfx.config.num_sc_per_sh = le32_to_cpu(gc_info->v2.gc_num_sc_per_se) /
 			le32_to_cpu(gc_info->v2.gc_num_sh_per_se);
 		adev->gfx.config.num_packer_per_sc = le32_to_cpu(gc_info->v2.gc_num_packer_per_sc);
+		if (gc_info->v2.header.version_minor == 1) {
+			adev->gfx.config.gc_num_tcp_per_sa = le32_to_cpu(gc_info->v2_1.gc_num_tcp_per_sh);
+			adev->gfx.config.gc_tcp_size_per_cu = le32_to_cpu(gc_info->v2_1.gc_tcp_size_per_cu);
+			adev->gfx.config.gc_num_sdp_interface = le32_to_cpu(gc_info->v2_1.gc_num_sdp_interface); /* per XCD */
+			adev->gfx.config.gc_num_cu_per_sqc = le32_to_cpu(gc_info->v2_1.gc_num_cu_per_sqc);
+			adev->gfx.config.gc_l1_instruction_cache_size_per_sqc = le32_to_cpu(gc_info->v2_1.gc_instruction_cache_size_per_sqc);
+			adev->gfx.config.gc_l1_data_cache_size_per_sqc = le32_to_cpu(gc_info->v2_1.gc_scalar_data_cache_size_per_sqc);
+			adev->gfx.config.gc_tcc_size = le32_to_cpu(gc_info->v2_1.gc_tcc_size); /* per XCD */
+		}
 		break;
 	default:
 		dev_err(adev->dev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index a4ff515ce896..395c1768b9fc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -241,6 +241,9 @@ struct amdgpu_gfx_config {
 	uint32_t gc_gl1c_per_sa;
 	uint32_t gc_gl1c_size_per_instance;
 	uint32_t gc_gl2c_per_gpu;
+	uint32_t gc_tcp_size_per_cu;
+	uint32_t gc_num_cu_per_sqc;
+	uint32_t gc_tcc_size;
 };
 
 struct amdgpu_cu_info {
diff --git a/drivers/gpu/drm/amd/include/discovery.h b/drivers/gpu/drm/amd/include/discovery.h
index b9884e576f98..7a9d473d0917 100644
--- a/drivers/gpu/drm/amd/include/discovery.h
+++ b/drivers/gpu/drm/amd/include/discovery.h
@@ -280,6 +280,36 @@ struct gc_info_v2_0 {
 	uint32_t gc_num_packer_per_sc;
 };
 
+struct gc_info_v2_1 {
+	struct gpu_info_header header;
+
+	uint32_t gc_num_se;
+	uint32_t gc_num_cu_per_sh;
+	uint32_t gc_num_sh_per_se;
+	uint32_t gc_num_rb_per_se;
+	uint32_t gc_num_tccs;
+	uint32_t gc_num_gprs;
+	uint32_t gc_num_max_gs_thds;
+	uint32_t gc_gs_table_depth;
+	uint32_t gc_gsprim_buff_depth;
+	uint32_t gc_parameter_cache_depth;
+	uint32_t gc_double_offchip_lds_buffer;
+	uint32_t gc_wave_size;
+	uint32_t gc_max_waves_per_simd;
+	uint32_t gc_max_scratch_slots_per_cu;
+	uint32_t gc_lds_size;
+	uint32_t gc_num_sc_per_se;
+	uint32_t gc_num_packer_per_sc;
+	/* new for v2_1 */
+	uint32_t gc_num_tcp_per_sh;
+	uint32_t gc_tcp_size_per_cu;
+	uint32_t gc_num_sdp_interface;
+	uint32_t gc_num_cu_per_sqc;
+	uint32_t gc_instruction_cache_size_per_sqc;
+	uint32_t gc_scalar_data_cache_size_per_sqc;
+	uint32_t gc_tcc_size;
+};
+
 typedef struct harvest_info_header {
 	uint32_t signature; /* Table Signature */
 	uint32_t version;   /* Table Version */

From 85609153102ea402e860657e04df4b839b4212ca Mon Sep 17 00:00:00 2001
From: Asad Kamal <asad.kamal@amd.com>
Date: Sat, 12 Aug 2023 21:42:20 +0800
Subject: [PATCH 0903/1189] drm/amd/pm: Update SMUv13.0.6 PMFW headers

Update PMFW interface headers for updated metrics table and
critical temperature message

Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h  |  4 ++--
 .../amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_ppsmc.h | 16 +++++++++++++++-
 2 files changed, 17 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h
index 252aef190c5c..9be4051c0865 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h
@@ -123,7 +123,7 @@ typedef enum {
   VOLTAGE_GUARDBAND_COUNT
 } GFX_GUARDBAND_e;
 
-#define SMU_METRICS_TABLE_VERSION 0x5
+#define SMU_METRICS_TABLE_VERSION 0x7
 
 typedef struct __attribute__((packed, aligned(4))) {
   uint32_t AccumulationCounter;
@@ -198,7 +198,7 @@ typedef struct __attribute__((packed, aligned(4))) {
   uint32_t SocketThmResidencyAcc;
   uint32_t VrThmResidencyAcc;
   uint32_t HbmThmResidencyAcc;
-  uint32_t spare;
+  uint32_t GfxLockXCDMak;
 
   // New Items at end to maintain driver compatibility
   uint32_t GfxclkFrequency[8];
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_ppsmc.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_ppsmc.h
index ae4f44c4b877..70a4a717fd3f 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_ppsmc.h
@@ -83,13 +83,27 @@
 #define PPSMC_MSG_GetMinGfxDpmFreq                  0x32
 #define PPSMC_MSG_GetMaxGfxDpmFreq                  0x33
 #define PPSMC_MSG_PrepareForDriverUnload            0x34
-#define PPSMC_Message_Count                         0x35
+#define PPSMC_MSG_ReadThrottlerLimit                0x35
+#define PPSMC_MSG_QueryValidMcaCount                0x36
+#define PPSMC_MSG_McaBankDumpDW                     0x37
+#define PPSMC_MSG_GetCTFLimit                       0x38
+#define PPSMC_Message_Count                         0x39
 
 //PPSMC Reset Types for driver msg argument
 #define PPSMC_RESET_TYPE_DRIVER_MODE_1_RESET        0x1
 #define PPSMC_RESET_TYPE_DRIVER_MODE_2_RESET	      0x2
 #define PPSMC_RESET_TYPE_DRIVER_MODE_3_RESET        0x3
 
+//PPSMC Reset Types for driver msg argument
+#define PPSMC_THROTTLING_LIMIT_TYPE_SOCKET          0x1
+#define PPSMC_THROTTLING_LIMIT_TYPE_HBM             0x2
+
+//CTF/Throttle Limit types
+#define PPSMC_AID_THM_TYPE                          0x1
+#define PPSMC_CCD_THM_TYPE                          0x2
+#define PPSMC_XCD_THM_TYPE                          0x3
+#define PPSMC_HBM_THM_TYPE                          0x4
+
 typedef uint32_t PPSMC_Result;
 typedef uint32_t PPSMC_MSG;
 

From 1836bb0a9d09b42ca1e56e90814eb70658aa7c96 Mon Sep 17 00:00:00 2001
From: Asad Kamal <asad.kamal@amd.com>
Date: Sat, 12 Aug 2023 22:22:10 +0800
Subject: [PATCH 0904/1189] drm/amd/pm: Add critical temp for GC v9.4.3

Add critical temperature message support func for smu v13.0.6
and expose critical temperature as part of hw mon attributes
for GC v9.4.3

v2:
Added comment for pmfw version requirement & move the check
to get_thermal_temperature_range function

Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/amdgpu_pm.c            |  8 +--
 drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h  |  1 +
 .../drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c  | 50 +++++++++++++++++++
 3 files changed, 55 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index 5b1d73b00ef7..f03647fa3df6 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -3311,8 +3311,10 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj,
 	    (gc_ver != IP_VERSION(9, 4, 3)) &&
 	    (attr == &sensor_dev_attr_temp2_input.dev_attr.attr ||
 	     attr == &sensor_dev_attr_temp2_label.dev_attr.attr ||
+	     attr == &sensor_dev_attr_temp2_crit.dev_attr.attr ||
 	     attr == &sensor_dev_attr_temp3_input.dev_attr.attr ||
-	     attr == &sensor_dev_attr_temp3_label.dev_attr.attr))
+	     attr == &sensor_dev_attr_temp3_label.dev_attr.attr ||
+	     attr == &sensor_dev_attr_temp3_crit.dev_attr.attr))
 		return 0;
 
 	/* hotspot temperature for gc 9,4,3*/
@@ -3324,9 +3326,7 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj,
 	/* only SOC15 dGPUs support hotspot and mem temperatures */
 	if (((adev->flags & AMD_IS_APU) || gc_ver < IP_VERSION(9, 0, 0) ||
 	    (gc_ver == IP_VERSION(9, 4, 3))) &&
-	    (attr == &sensor_dev_attr_temp2_crit.dev_attr.attr ||
-	     attr == &sensor_dev_attr_temp2_crit_hyst.dev_attr.attr ||
-	     attr == &sensor_dev_attr_temp3_crit.dev_attr.attr ||
+	     (attr == &sensor_dev_attr_temp2_crit_hyst.dev_attr.attr ||
 	     attr == &sensor_dev_attr_temp3_crit_hyst.dev_attr.attr ||
 	     attr == &sensor_dev_attr_temp1_emergency.dev_attr.attr ||
 	     attr == &sensor_dev_attr_temp2_emergency.dev_attr.attr ||
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
index f71fc99447f2..e57265cf637c 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
@@ -84,6 +84,7 @@
        __SMU_DUMMY_MAP(SetTjMax),                     \
        __SMU_DUMMY_MAP(SetFanTemperatureTarget),      \
        __SMU_DUMMY_MAP(PrepareMp1ForUnload),          \
+       __SMU_DUMMY_MAP(GetCTFLimit),                  \
        __SMU_DUMMY_MAP(DramLogSetDramAddrHigh),       \
        __SMU_DUMMY_MAP(DramLogSetDramAddrLow),        \
        __SMU_DUMMY_MAP(DramLogSetDramSize),           \
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 6ed9cd0a1e4e..7d8af9b309b7 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -132,6 +132,7 @@ static const struct cmn2asic_msg_mapping smu_v13_0_6_message_map[SMU_MSG_MAX_COU
 	MSG_MAP(SetSoftMinGfxclk,                    PPSMC_MSG_SetSoftMinGfxClk,                0),
 	MSG_MAP(SetSoftMaxGfxClk,                    PPSMC_MSG_SetSoftMaxGfxClk,                0),
 	MSG_MAP(PrepareMp1ForUnload,                 PPSMC_MSG_PrepareForDriverUnload,          0),
+	MSG_MAP(GetCTFLimit,                         PPSMC_MSG_GetCTFLimit,                     0),
 };
 
 static const struct cmn2asic_mapping smu_v13_0_6_clk_map[SMU_CLK_COUNT] = {
@@ -2081,6 +2082,54 @@ out:
 	return ret;
 }
 
+static int smu_v13_0_6_get_thermal_temperature_range(struct smu_context *smu,
+						     struct smu_temperature_range *range)
+{
+	struct amdgpu_device *adev = smu->adev;
+	u32 aid_temp, xcd_temp;
+	uint32_t smu_version;
+	u32 ccd_temp = 0;
+	int ret;
+
+	if (amdgpu_sriov_vf(smu->adev))
+		return 0;
+
+	if (!range)
+		return -EINVAL;
+
+	/*Check smu version, GetCtfLimit message only supported for smu version 85.69 or higher */
+	smu_cmn_get_smc_version(smu, NULL, &smu_version);
+	if (smu_version < 0x554500)
+		return 0;
+
+	ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GetCTFLimit,
+					      PPSMC_AID_THM_TYPE, &aid_temp);
+	if (ret)
+		goto failed;
+
+	if (adev->flags & AMD_IS_APU) {
+		ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GetCTFLimit,
+						      PPSMC_CCD_THM_TYPE, &ccd_temp);
+		if (ret)
+			goto failed;
+	}
+
+	ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GetCTFLimit,
+					      PPSMC_XCD_THM_TYPE, &xcd_temp);
+	if (ret)
+		goto failed;
+
+	range->hotspot_crit_max = max3(aid_temp, xcd_temp, ccd_temp);
+	ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GetCTFLimit,
+					      PPSMC_HBM_THM_TYPE, &range->mem_crit_max);
+	if (ret)
+		goto failed;
+
+	return 0;
+failed:
+	return ret;
+}
+
 static int smu_v13_0_6_mode1_reset(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
@@ -2177,6 +2226,7 @@ static const struct pptable_funcs smu_v13_0_6_ppt_funcs = {
 	.get_pp_feature_mask = smu_cmn_get_pp_feature_mask,
 	.set_pp_feature_mask = smu_cmn_set_pp_feature_mask,
 	.get_gpu_metrics = smu_v13_0_6_get_gpu_metrics,
+	.get_thermal_temperature_range = smu_v13_0_6_get_thermal_temperature_range,
 	.mode1_reset_is_support = smu_v13_0_6_is_mode1_reset_supported,
 	.mode2_reset_is_support = smu_v13_0_6_is_mode2_reset_supported,
 	.mode1_reset = smu_v13_0_6_mode1_reset,

From bae44a8fcb6e7e244a524b7f3da35b69aa7bb4b3 Mon Sep 17 00:00:00 2001
From: Samir Dhume <samir.dhume@amd.com>
Date: Wed, 16 Aug 2023 15:28:17 -0400
Subject: [PATCH 0905/1189] drm/amdgpu/jpeg - skip change of power-gating state
 for sriov

Powergating is handled in the host driver.

Reviewed-by: Zhigang Luo <zhigang.luo@amd.com>
Signed-off-by: Samir Dhume <samir.dhume@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
index 15612915bb6c..1de79d660285 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
@@ -360,8 +360,10 @@ static int jpeg_v4_0_3_hw_fini(void *handle)
 
 	cancel_delayed_work_sync(&adev->jpeg.idle_work);
 
-	if (adev->jpeg.cur_state != AMD_PG_STATE_GATE)
-		ret = jpeg_v4_0_3_set_powergating_state(adev, AMD_PG_STATE_GATE);
+	if (!amdgpu_sriov_vf(adev)) {
+		if (adev->jpeg.cur_state != AMD_PG_STATE_GATE)
+			ret = jpeg_v4_0_3_set_powergating_state(adev, AMD_PG_STATE_GATE);
+	}
 
 	return ret;
 }

From 3aca8cca606be64c7cd6b61b36c8208bab37d44b Mon Sep 17 00:00:00 2001
From: Alex Sierra <alex.sierra@amd.com>
Date: Tue, 15 Aug 2023 15:42:52 -0500
Subject: [PATCH 0906/1189] drm/amdkfd: retry after EBUSY is returned from
 hmm_ranges_get_pages

if hmm_range_get_pages returns EBUSY error during
svm_range_validate_and_map, within the context of a page fault
interrupt. This should retry through svm_range_restore_pages
callback. Therefore we treat this as EAGAIN error instead, and defer
it to restore pages fallback.

Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index dbbe6559d6bc..49b62c2172cc 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -1686,6 +1686,8 @@ static int svm_range_validate_and_map(struct mm_struct *mm,
 		WRITE_ONCE(p->svms.faulting_task, NULL);
 		if (r) {
 			pr_debug("failed %d to get svm range pages\n", r);
+			if (r == -EBUSY)
+				r = -EAGAIN;
 			goto unreserve_out;
 		}
 

From e81c45568505913a2275c6f60577e348d9786743 Mon Sep 17 00:00:00 2001
From: YiPeng Chai <YiPeng.Chai@amd.com>
Date: Tue, 15 Aug 2023 17:39:30 +0800
Subject: [PATCH 0907/1189] drm/amdgpu: Enable ras for mp0 v13_0_6 sriov

Enable ras for mp0 v13_0_6 sriov

Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com>
Reviewed-by: Stanley.Yang <Stanley.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 7689395e44fd..378478cf9c21 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -2399,6 +2399,7 @@ static bool amdgpu_ras_asic_supported(struct amdgpu_device *adev)
 	if (amdgpu_sriov_vf(adev)) {
 		switch (adev->ip_versions[MP0_HWIP][0]) {
 		case IP_VERSION(13, 0, 2):
+		case IP_VERSION(13, 0, 6):
 			return true;
 		default:
 			return false;

From bab9bec6b6fb6d24f6c9205628cd9c46d768e5c1 Mon Sep 17 00:00:00 2001
From: Ovidiu Bunea <ovidiu.bunea@amd.com>
Date: Wed, 9 Aug 2023 11:55:14 -0400
Subject: [PATCH 0908/1189] drm/amd/display: Roll back unit correction

[why]
This Unit correction exposes a Replay corruption.

[how]
This reverts commit:
commit dbd29029c7b5 ("drm/amd/display: Correct unit conversion for vstartup")

Roll back unit conversion until Replay can fix their corruption.

Fixes: dbd29029c7b5 ("drm/amd/display: Correct unit conversion for vstartup")
Reviewed-by: Reza Amini <reza.amini@amd.com>
Acked-by: Wayne Lin <wayne.lin@amd.com>
Signed-off-by: Ovidiu Bunea <ovidiu.bunea@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../amd/display/dc/dml/dcn314/dcn314_fpu.c    | 25 +------------------
 1 file changed, 1 insertion(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
index 07adb614366e..ed8ddb75b333 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
@@ -31,7 +31,6 @@
 #include "dml/dcn20/dcn20_fpu.h"
 #include "dml/dcn31/dcn31_fpu.h"
 #include "dml/display_mode_vba.h"
-#include "dml/dml_inline_defs.h"
 
 struct _vcs_dpi_ip_params_st dcn3_14_ip = {
 	.VBlankNomDefaultUS = 668,
@@ -274,25 +273,6 @@ static bool is_dual_plane(enum surface_pixel_format format)
 	return format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN || format == SURFACE_PIXEL_FORMAT_GRPH_RGBE_ALPHA;
 }
 
-/*
- * micro_sec_to_vert_lines () - converts time to number of vertical lines for a given timing
- *
- * @param: num_us: number of microseconds
- * @return: number of vertical lines. If exact number of vertical lines is not found then
- *          it will round up to next number of lines to guarantee num_us
- */
-static unsigned int micro_sec_to_vert_lines(unsigned int num_us, struct dc_crtc_timing *timing)
-{
-	unsigned int num_lines = 0;
-	unsigned int lines_time_in_ns = 1000.0 *
-			(((float)timing->h_total * 1000.0) /
-			 ((float)timing->pix_clk_100hz / 10.0));
-
-	num_lines = dml_ceil(1000.0 * num_us / lines_time_in_ns, 1.0);
-
-	return num_lines;
-}
-
 int dcn314_populate_dml_pipes_from_context_fpu(struct dc *dc, struct dc_state *context,
 					       display_e2e_pipe_params_st *pipes,
 					       bool fast_validate)
@@ -309,22 +289,19 @@ int dcn314_populate_dml_pipes_from_context_fpu(struct dc *dc, struct dc_state *c
 
 	for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) {
 		struct dc_crtc_timing *timing;
-		unsigned int num_lines = 0;
 
 		if (!res_ctx->pipe_ctx[i].stream)
 			continue;
 		pipe = &res_ctx->pipe_ctx[i];
 		timing = &pipe->stream->timing;
 
-		num_lines = micro_sec_to_vert_lines(dcn3_14_ip.VBlankNomDefaultUS, timing);
-
 		if (pipe->stream->adjust.v_total_min != 0)
 			pipes[pipe_cnt].pipe.dest.vtotal = pipe->stream->adjust.v_total_min;
 		else
 			pipes[pipe_cnt].pipe.dest.vtotal = timing->v_total;
 
 		pipes[pipe_cnt].pipe.dest.vblank_nom = timing->v_total - pipes[pipe_cnt].pipe.dest.vactive;
-		pipes[pipe_cnt].pipe.dest.vblank_nom = min(pipes[pipe_cnt].pipe.dest.vblank_nom, num_lines);
+		pipes[pipe_cnt].pipe.dest.vblank_nom = min(pipes[pipe_cnt].pipe.dest.vblank_nom, dcn3_14_ip.VBlankNomDefaultUS);
 		pipes[pipe_cnt].pipe.dest.vblank_nom = max(pipes[pipe_cnt].pipe.dest.vblank_nom, timing->v_sync_width);
 		pipes[pipe_cnt].pipe.dest.vblank_nom = min(pipes[pipe_cnt].pipe.dest.vblank_nom, max_allowed_vblank_nom);
 

From 8f31c7be3e89634767686ffab869cd3ebfea188f Mon Sep 17 00:00:00 2001
From: Reza Amini <reza.amini@amd.com>
Date: Fri, 14 Jul 2023 10:43:05 -0400
Subject: [PATCH 0909/1189] drm/amd/display: Correct unit conversion for
 vstartup

[why]
vstartup is calculated to be a large number. it works because
it is within vertical blank, but it reduces region of blank that
can be used for power gating.

[how]
Calculation needs to convert micro seconds to number of
vertical lines.

Reviewed-by: Kazlauskas Nicholas <Nicholas.Kazlauskas@amd.com>
Acked-by: Wayne Lin <wayne.lin@amd.com>
Signed-off-by: Reza Amini <reza.amini@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../amd/display/dc/dml/dcn314/dcn314_fpu.c    | 25 ++++++++++++++++++-
 1 file changed, 24 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
index ed8ddb75b333..07adb614366e 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
@@ -31,6 +31,7 @@
 #include "dml/dcn20/dcn20_fpu.h"
 #include "dml/dcn31/dcn31_fpu.h"
 #include "dml/display_mode_vba.h"
+#include "dml/dml_inline_defs.h"
 
 struct _vcs_dpi_ip_params_st dcn3_14_ip = {
 	.VBlankNomDefaultUS = 668,
@@ -273,6 +274,25 @@ static bool is_dual_plane(enum surface_pixel_format format)
 	return format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN || format == SURFACE_PIXEL_FORMAT_GRPH_RGBE_ALPHA;
 }
 
+/*
+ * micro_sec_to_vert_lines () - converts time to number of vertical lines for a given timing
+ *
+ * @param: num_us: number of microseconds
+ * @return: number of vertical lines. If exact number of vertical lines is not found then
+ *          it will round up to next number of lines to guarantee num_us
+ */
+static unsigned int micro_sec_to_vert_lines(unsigned int num_us, struct dc_crtc_timing *timing)
+{
+	unsigned int num_lines = 0;
+	unsigned int lines_time_in_ns = 1000.0 *
+			(((float)timing->h_total * 1000.0) /
+			 ((float)timing->pix_clk_100hz / 10.0));
+
+	num_lines = dml_ceil(1000.0 * num_us / lines_time_in_ns, 1.0);
+
+	return num_lines;
+}
+
 int dcn314_populate_dml_pipes_from_context_fpu(struct dc *dc, struct dc_state *context,
 					       display_e2e_pipe_params_st *pipes,
 					       bool fast_validate)
@@ -289,19 +309,22 @@ int dcn314_populate_dml_pipes_from_context_fpu(struct dc *dc, struct dc_state *c
 
 	for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) {
 		struct dc_crtc_timing *timing;
+		unsigned int num_lines = 0;
 
 		if (!res_ctx->pipe_ctx[i].stream)
 			continue;
 		pipe = &res_ctx->pipe_ctx[i];
 		timing = &pipe->stream->timing;
 
+		num_lines = micro_sec_to_vert_lines(dcn3_14_ip.VBlankNomDefaultUS, timing);
+
 		if (pipe->stream->adjust.v_total_min != 0)
 			pipes[pipe_cnt].pipe.dest.vtotal = pipe->stream->adjust.v_total_min;
 		else
 			pipes[pipe_cnt].pipe.dest.vtotal = timing->v_total;
 
 		pipes[pipe_cnt].pipe.dest.vblank_nom = timing->v_total - pipes[pipe_cnt].pipe.dest.vactive;
-		pipes[pipe_cnt].pipe.dest.vblank_nom = min(pipes[pipe_cnt].pipe.dest.vblank_nom, dcn3_14_ip.VBlankNomDefaultUS);
+		pipes[pipe_cnt].pipe.dest.vblank_nom = min(pipes[pipe_cnt].pipe.dest.vblank_nom, num_lines);
 		pipes[pipe_cnt].pipe.dest.vblank_nom = max(pipes[pipe_cnt].pipe.dest.vblank_nom, timing->v_sync_width);
 		pipes[pipe_cnt].pipe.dest.vblank_nom = min(pipes[pipe_cnt].pipe.dest.vblank_nom, max_allowed_vblank_nom);
 

From ed6445f5894dc5a952766725b0689451a58fcfd8 Mon Sep 17 00:00:00 2001
From: ChunTao Tso <chuntao.tso@amd.com>
Date: Fri, 4 Aug 2023 14:57:44 +0800
Subject: [PATCH 0910/1189] drm/amd/display: set minimum of VBlank_nom

[Why]
If VBlank_nom is too small, it will cause
VStartUP_Start smaller than VBackPorch + VSync width which is an
invalid case for VStartUP_Start and where to send AS-SDP.

[How]
Setup a minimum value to VBlank_nom

Reviewed-by: Reza Amini <reza.amini@amd.com>
Acked-by: Wayne Lin <wayne.lin@amd.com>
Signed-off-by: ChunTao Tso <chuntao.tso@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../amd/display/dc/dml/dcn314/dcn314_fpu.c    | 21 ++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
index 07adb614366e..fb21572750e8 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
@@ -293,6 +293,17 @@ static unsigned int micro_sec_to_vert_lines(unsigned int num_us, struct dc_crtc_
 	return num_lines;
 }
 
+static unsigned int get_vertical_back_porch(struct dc_crtc_timing *timing)
+{
+	unsigned int v_active = 0, v_blank = 0, v_back_porch = 0;
+
+	v_active = timing->v_border_top + timing->v_addressable + timing->v_border_bottom;
+	v_blank = timing->v_total - v_active;
+	v_back_porch = v_blank - timing->v_front_porch - timing->v_sync_width;
+
+	return v_back_porch;
+}
+
 int dcn314_populate_dml_pipes_from_context_fpu(struct dc *dc, struct dc_state *context,
 					       display_e2e_pipe_params_st *pipes,
 					       bool fast_validate)
@@ -310,6 +321,7 @@ int dcn314_populate_dml_pipes_from_context_fpu(struct dc *dc, struct dc_state *c
 	for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) {
 		struct dc_crtc_timing *timing;
 		unsigned int num_lines = 0;
+		unsigned int v_back_porch = 0;
 
 		if (!res_ctx->pipe_ctx[i].stream)
 			continue;
@@ -323,9 +335,16 @@ int dcn314_populate_dml_pipes_from_context_fpu(struct dc *dc, struct dc_state *c
 		else
 			pipes[pipe_cnt].pipe.dest.vtotal = timing->v_total;
 
+		v_back_porch  = get_vertical_back_porch(timing);
+
 		pipes[pipe_cnt].pipe.dest.vblank_nom = timing->v_total - pipes[pipe_cnt].pipe.dest.vactive;
 		pipes[pipe_cnt].pipe.dest.vblank_nom = min(pipes[pipe_cnt].pipe.dest.vblank_nom, num_lines);
-		pipes[pipe_cnt].pipe.dest.vblank_nom = max(pipes[pipe_cnt].pipe.dest.vblank_nom, timing->v_sync_width);
+		// vblank_nom should not smaller than (VSync (timing->v_sync_width + v_back_porch) + 2)
+		// + 2 is because
+		// 1 -> VStartup_start should be 1 line before VSync
+		// 1 -> always reserve 1 line between start of vblank to vstartup signal
+		pipes[pipe_cnt].pipe.dest.vblank_nom =
+			max(pipes[pipe_cnt].pipe.dest.vblank_nom, timing->v_sync_width + v_back_porch + 2);
 		pipes[pipe_cnt].pipe.dest.vblank_nom = min(pipes[pipe_cnt].pipe.dest.vblank_nom, max_allowed_vblank_nom);
 
 		if (pipe->plane_state &&

From 8f1778939b2f22664737a44aa5acf0308bb6518d Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Fri, 14 Jul 2023 17:02:45 +0530
Subject: [PATCH 0911/1189] drm/amdgpu: Unset baco dummy mode on nbio v7.9

BACO dummy mode could be set under reset conditions and that affects
framebuffer access. Check If baco dummy mode is set, unset it if so.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Tested-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
index 9ea072374cb7..f85eec05d218 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
@@ -437,6 +437,24 @@ static void nbio_v7_9_init_registers(struct amdgpu_device *adev)
 			XCC_DOORBELL_FENCE__SHUB_SLV_MODE_MASK);
 
 	}
+
+	if (!amdgpu_sriov_vf(adev)) {
+		u32 baco_cntl;
+		for_each_inst(i, adev->aid_mask) {
+			baco_cntl = RREG32_SOC15(NBIO, i, regBIF_BX0_BACO_CNTL);
+			if (baco_cntl & (BIF_BX0_BACO_CNTL__BACO_DUMMY_EN_MASK |
+					 BIF_BX0_BACO_CNTL__BACO_EN_MASK)) {
+				baco_cntl &= ~(
+					BIF_BX0_BACO_CNTL__BACO_DUMMY_EN_MASK |
+					BIF_BX0_BACO_CNTL__BACO_EN_MASK);
+				dev_dbg(adev->dev,
+					"Unsetting baco dummy mode %x",
+					baco_cntl);
+				WREG32_SOC15(NBIO, i, regBIF_BX0_BACO_CNTL,
+					     baco_cntl);
+			}
+		}
+	}
 }
 
 static u64 nbio_v7_9_get_pcie_replay_count(struct amdgpu_device *adev)

From 8c97e87c13d9d181c14545864dbf6bbbd83f639b Mon Sep 17 00:00:00 2001
From: Horace Chen <horace.chen@amd.com>
Date: Thu, 17 Aug 2023 17:38:29 +0800
Subject: [PATCH 0912/1189] drm/amdkfd: use correct method to get clock under
 SRIOV

[What]
Current SRIOV still using adev->clock.default_XX which gets from
atomfirmware. But these fields are abandoned in atomfirmware long ago.
Which may cause function to return a 0 value.

[How]
We don't need to check whether SR-IOV. For SR-IOV one-vf-mode,
pm is enabled and VF is able to read dpm clock
from pmfw, so we can use dpm clock interface directly. For
multi-VF mode, VF pm is disabled, so driver can just react as pm
disabled. One-vf-mode is introduced from GFX9 so it shall not have
any backward compatibility issue.

Signed-off-by: Horace Chen <horace.chen@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index df633e9ce920..cdf6087706aa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -442,9 +442,7 @@ void amdgpu_amdkfd_get_local_mem_info(struct amdgpu_device *adev,
 			mem_info->local_mem_size_public,
 			mem_info->local_mem_size_private);
 
-	if (amdgpu_sriov_vf(adev))
-		mem_info->mem_clk_max = adev->clock.default_mclk / 100;
-	else if (adev->pm.dpm_enabled) {
+	if (adev->pm.dpm_enabled) {
 		if (amdgpu_emu_mode == 1)
 			mem_info->mem_clk_max = 0;
 		else
@@ -463,9 +461,7 @@ uint64_t amdgpu_amdkfd_get_gpu_clock_counter(struct amdgpu_device *adev)
 uint32_t amdgpu_amdkfd_get_max_engine_clock_in_mhz(struct amdgpu_device *adev)
 {
 	/* the sclk is in quantas of 10kHz */
-	if (amdgpu_sriov_vf(adev))
-		return adev->clock.default_sclk / 100;
-	else if (adev->pm.dpm_enabled)
+	if (adev->pm.dpm_enabled)
 		return amdgpu_dpm_get_sclk(adev, false) / 100;
 	else
 		return 100;

From 7656168a8a83f8fc6d062d944fd52d18d4da05d7 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Wed, 19 Jul 2023 13:03:25 +0530
Subject: [PATCH 0913/1189] drm/amdgpu: Add bootloader status check

Add a function to wait till bootloader has reached steady state.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Tested-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 17 ++++++++++++++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c    | 11 +++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h    |  3 +++
 3 files changed, 28 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index e77f048c99d8..5586146b8c76 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -885,13 +885,20 @@ static void amdgpu_block_invalid_wreg(struct amdgpu_device *adev,
  */
 static int amdgpu_device_asic_init(struct amdgpu_device *adev)
 {
+	int ret;
+
 	amdgpu_asic_pre_asic_init(adev);
 
 	if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 4, 3) ||
-	    adev->ip_versions[GC_HWIP][0] >= IP_VERSION(11, 0, 0))
-		return amdgpu_atomfirmware_asic_init(adev, true);
-	else
+	    adev->ip_versions[GC_HWIP][0] >= IP_VERSION(11, 0, 0)) {
+		amdgpu_psp_wait_for_bootloader(adev);
+		ret = amdgpu_atomfirmware_asic_init(adev, true);
+		return ret;
+	} else {
 		return amdgpu_atom_asic_init(adev->mode_info.atom_context);
+	}
+
+	return 0;
 }
 
 /**
@@ -4697,6 +4704,9 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev)
 		dev_err(adev->dev, "GPU mode1 reset failed\n");
 
 	amdgpu_device_load_pci_state(adev->pdev);
+	ret = amdgpu_psp_wait_for_bootloader(adev);
+	if (ret)
+		return ret;
 
 	/* wait for asic to come out of reset */
 	for (i = 0; i < adev->usec_timeout; i++) {
@@ -4708,6 +4718,7 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev)
 	}
 
 	amdgpu_atombios_scratch_regs_engine_hung(adev, false);
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 8fdca54bb8a1..429ef212c1f2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -2078,6 +2078,17 @@ int psp_securedisplay_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
 }
 /* SECUREDISPLAY end */
 
+int amdgpu_psp_wait_for_bootloader(struct amdgpu_device *adev)
+{
+	struct psp_context *psp = &adev->psp;
+	int ret = 0;
+
+	if (!amdgpu_sriov_vf(adev) && psp->funcs && psp->funcs->wait_for_bootloader != NULL)
+		ret = psp->funcs->wait_for_bootloader(psp);
+
+	return ret;
+}
+
 static int psp_hw_start(struct psp_context *psp)
 {
 	struct amdgpu_device *adev = psp->adev;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
index 3384eb94fde0..3e67ed63e638 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
@@ -109,6 +109,7 @@ enum psp_reg_prog_id {
 
 struct psp_funcs {
 	int (*init_microcode)(struct psp_context *psp);
+	int (*wait_for_bootloader)(struct psp_context *psp);
 	int (*bootloader_load_kdb)(struct psp_context *psp);
 	int (*bootloader_load_spl)(struct psp_context *psp);
 	int (*bootloader_load_sysdrv)(struct psp_context *psp);
@@ -533,4 +534,6 @@ int psp_spatial_partition(struct psp_context *psp, int mode);
 
 int is_psp_fw_valid(struct psp_bin_desc bin);
 
+int amdgpu_psp_wait_for_bootloader(struct amdgpu_device *adev);
+
 #endif

From 3f16096795dff2ae6c91653338d507fc91905160 Mon Sep 17 00:00:00 2001
From: Mangesh Gadre <Mangesh.Gadre@amd.com>
Date: Wed, 16 Aug 2023 12:57:28 +0800
Subject: [PATCH 0914/1189] drm/amdgpu: Remove SRAM clock gater override by
 driver

rlc firmware does required setting, driver need not do it.

Signed-off-by: Mangesh Gadre <Mangesh.Gadre@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
index 57ed4e5c294c..a60429c3e93c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -2219,15 +2219,6 @@ static void gfx_v9_4_3_xcc_update_sram_fgcg(struct amdgpu_device *adev,
 		WREG32_SOC15(GC, GET_INST(GC, xcc_id),
 			     regRLC_CGTT_MGCG_OVERRIDE, data);
 
-	def = data = RREG32_SOC15(GC, GET_INST(GC, xcc_id), regRLC_CLK_CNTL);
-
-	if (enable)
-		data &= ~RLC_CLK_CNTL__RLC_SRAM_CLK_GATER_OVERRIDE_MASK;
-	else
-		data |= RLC_CLK_CNTL__RLC_SRAM_CLK_GATER_OVERRIDE_MASK;
-
-	if (def != data)
-		WREG32_SOC15(GC, GET_INST(GC, xcc_id), regRLC_CLK_CNTL, data);
 }
 
 static void gfx_v9_4_3_xcc_update_repeater_fgcg(struct amdgpu_device *adev,

From e1c0d2e7066b5675cb62daa2f7cb3899756f789c Mon Sep 17 00:00:00 2001
From: Asad Kamal <asad.kamal@amd.com>
Date: Fri, 18 Aug 2023 18:23:36 +0800
Subject: [PATCH 0915/1189] drm/amd/pm: Fix critical temp unit of SMU v13.0.6

Critical Temperature needs to be reported in
millidegree Celsius.

Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 7d8af9b309b7..d3b578e6bc2a 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -2086,7 +2086,7 @@ static int smu_v13_0_6_get_thermal_temperature_range(struct smu_context *smu,
 						     struct smu_temperature_range *range)
 {
 	struct amdgpu_device *adev = smu->adev;
-	u32 aid_temp, xcd_temp;
+	u32 aid_temp, xcd_temp, mem_temp;
 	uint32_t smu_version;
 	u32 ccd_temp = 0;
 	int ret;
@@ -2119,13 +2119,14 @@ static int smu_v13_0_6_get_thermal_temperature_range(struct smu_context *smu,
 	if (ret)
 		goto failed;
 
-	range->hotspot_crit_max = max3(aid_temp, xcd_temp, ccd_temp);
+	range->hotspot_crit_max = max3(aid_temp, xcd_temp, ccd_temp) *
+				       SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
 	ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GetCTFLimit,
-					      PPSMC_HBM_THM_TYPE, &range->mem_crit_max);
+					      PPSMC_HBM_THM_TYPE, &mem_temp);
 	if (ret)
 		goto failed;
 
-	return 0;
+	range->mem_crit_max = mem_temp * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
 failed:
 	return ret;
 }

From ea7971af7a911a7a388b4c47db2a231a6b8dcc29 Mon Sep 17 00:00:00 2001
From: Hamza Mahfooz <hamza.mahfooz@amd.com>
Date: Fri, 18 Aug 2023 09:11:11 -0400
Subject: [PATCH 0916/1189] drm/amd/display: fix mode scaling (RMX_.*)

As made mention of in commit 4a2df0d1f28e ("drm/amd/display: Fixed
non-native modes not lighting up"), we shouldn't call
drm_mode_set_crtcinfo() once the crtc timings have been decided. Since,
it can cause settings to be unintentionally overwritten. So, since
dm_state is never NULL now, we can use old_stream to determine if we
should call drm_mode_set_crtcinfo() because we only need to set the crtc
timing parameters for entirely new streams.

Cc: Harry Wentland <harry.wentland@amd.com>
Cc: Rodrigo Siqueira <rodrigo.siqueira@amd.com>
Fixes: bd49f19039c1 ("drm/amd/display: Always set crtcinfo from create_stream_for_sink")
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index f2b4f1720abd..88ba8b66de1f 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -6026,7 +6026,7 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 
 	if (recalculate_timing)
 		drm_mode_set_crtcinfo(&saved_mode, 0);
-	else
+	else if (!old_stream)
 		drm_mode_set_crtcinfo(&mode, 0);
 
 	/*

From a9366b944bfdca3c60e463869c8bdb7136b5b6ec Mon Sep 17 00:00:00 2001
From: SungHuai Wang <danny.wang@amd.com>
Date: Fri, 11 Aug 2023 11:15:37 +0800
Subject: [PATCH 0917/1189] drm/amd/display: fix static screen detection
 setting

[WHY]
OTG_STATIC_SCREEN_EVENT_MASK is changed in DCN3,
but we still follow DCN2 to apply setting for
OTG_STATIC_SCREEN_EVENT_MASK.

[How]
Add new function to apply correct settings for DCN3 series.

Reviewed-by: Anthony Koo <anthony.koo@amd.com>
Acked-by: Wayne Lin <wayne.lin@amd.com>
Signed-off-by: SungHuai Wang <danny.wang@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c  | 17 +++++++++++++++++
 .../gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.h  |  2 ++
 .../gpu/drm/amd/display/dc/dcn30/dcn30_init.c   |  2 +-
 .../gpu/drm/amd/display/dc/dcn31/dcn31_init.c   |  2 +-
 .../gpu/drm/amd/display/dc/dcn314/dcn314_init.c |  2 +-
 .../gpu/drm/amd/display/dc/dcn32/dcn32_init.c   |  2 +-
 6 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
index 6cef62d7a2e5..255713ec29bb 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
@@ -987,3 +987,20 @@ void dcn30_prepare_bandwidth(struct dc *dc,
 	}
 }
 
+void dcn30_set_static_screen_control(struct pipe_ctx **pipe_ctx,
+		int num_pipes, const struct dc_static_screen_params *params)
+{
+	unsigned int i;
+	unsigned int triggers = 0;
+
+	if (params->triggers.surface_update)
+		triggers |= 0x100;
+	if (params->triggers.cursor_update)
+		triggers |= 0x8;
+	if (params->triggers.force_trigger)
+		triggers |= 0x1;
+
+	for (i = 0; i < num_pipes; i++)
+		pipe_ctx[i]->stream_res.tg->funcs->set_static_screen_control(pipe_ctx[i]->stream_res.tg,
+					triggers, params->num_frames);
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.h
index a24a8e33a3d2..ce19c54097f8 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.h
@@ -87,5 +87,7 @@ void dcn30_set_hubp_blank(const struct dc *dc,
 void dcn30_prepare_bandwidth(struct dc *dc,
 	struct dc_state *context);
 
+void dcn30_set_static_screen_control(struct pipe_ctx **pipe_ctx,
+		int num_pipes, const struct dc_static_screen_params *params);
 
 #endif /* __DC_HWSS_DCN30_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c
index 3d19acaa12f3..0de8b2783cf6 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c
@@ -64,7 +64,7 @@ static const struct hw_sequencer_funcs dcn30_funcs = {
 	.update_bandwidth = dcn20_update_bandwidth,
 	.set_drr = dcn10_set_drr,
 	.get_position = dcn10_get_position,
-	.set_static_screen_control = dcn10_set_static_screen_control,
+	.set_static_screen_control = dcn30_set_static_screen_control,
 	.setup_stereo = dcn10_setup_stereo,
 	.set_avmute = dcn30_set_avmute,
 	.log_hw_state = dcn10_log_hw_state,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c
index fc25cc300a17..1d7bc1e39afe 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c
@@ -67,7 +67,7 @@ static const struct hw_sequencer_funcs dcn31_funcs = {
 	.update_bandwidth = dcn20_update_bandwidth,
 	.set_drr = dcn10_set_drr,
 	.get_position = dcn10_get_position,
-	.set_static_screen_control = dcn10_set_static_screen_control,
+	.set_static_screen_control = dcn30_set_static_screen_control,
 	.setup_stereo = dcn10_setup_stereo,
 	.set_avmute = dcn30_set_avmute,
 	.log_hw_state = dcn10_log_hw_state,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c
index ca8fe55c33b8..4ef85c3a0688 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c
@@ -69,7 +69,7 @@ static const struct hw_sequencer_funcs dcn314_funcs = {
 	.update_bandwidth = dcn20_update_bandwidth,
 	.set_drr = dcn10_set_drr,
 	.get_position = dcn10_get_position,
-	.set_static_screen_control = dcn10_set_static_screen_control,
+	.set_static_screen_control = dcn30_set_static_screen_control,
 	.setup_stereo = dcn10_setup_stereo,
 	.set_avmute = dcn30_set_avmute,
 	.log_hw_state = dcn10_log_hw_state,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c
index 777b2fac20c4..c7417147dff1 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c
@@ -65,7 +65,7 @@ static const struct hw_sequencer_funcs dcn32_funcs = {
 	.update_bandwidth = dcn20_update_bandwidth,
 	.set_drr = dcn10_set_drr,
 	.get_position = dcn10_get_position,
-	.set_static_screen_control = dcn10_set_static_screen_control,
+	.set_static_screen_control = dcn30_set_static_screen_control,
 	.setup_stereo = dcn10_setup_stereo,
 	.set_avmute = dcn30_set_avmute,
 	.log_hw_state = dcn10_log_hw_state,

From 7d4424373daacf3b0938d6278136678060690096 Mon Sep 17 00:00:00 2001
From: Hawking Zhang <Hawking.Zhang@amd.com>
Date: Sat, 19 Aug 2023 14:15:08 +0800
Subject: [PATCH 0918/1189] drm/amdgpu: Fix the return for gpu mode1_reset

amdgpu_device_mode1_reset will return gpu mode1_reset
succeed (ret = 0) as long as wait_for_bootloader call
succeed, regardless of the status reported by smu or
psp firmware. This results to driver continue executing
recovery even smu or psp fail to perform mode1 reset.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 5586146b8c76..533daba2accb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4701,12 +4701,12 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev)
 	}
 
 	if (ret)
-		dev_err(adev->dev, "GPU mode1 reset failed\n");
+		goto mode1_reset_failed;
 
 	amdgpu_device_load_pci_state(adev->pdev);
 	ret = amdgpu_psp_wait_for_bootloader(adev);
 	if (ret)
-		return ret;
+		goto mode1_reset_failed;
 
 	/* wait for asic to come out of reset */
 	for (i = 0; i < adev->usec_timeout; i++) {
@@ -4717,8 +4717,17 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev)
 		udelay(1);
 	}
 
+	if (i >= adev->usec_timeout) {
+		ret = -ETIMEDOUT;
+		goto mode1_reset_failed;
+	}
+
 	amdgpu_atombios_scratch_regs_engine_hung(adev, false);
 
+	return 0;
+
+mode1_reset_failed:
+	dev_err(adev->dev, "GPU mode1 reset failed\n");
 	return ret;
 }
 

From a7dd9b97fd5b12549721bbdc7977b5671870f4bb Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 18 Aug 2023 15:18:07 -0400
Subject: [PATCH 0919/1189] drm/amd/pm: fix debugfs pm_info output

Print both input and avg power.

Fixes: 47f1724db4fe ("drm/amd: Introduce `AMDGPU_PP_SENSOR_GPU_INPUT_POWER`")
Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/amdgpu_pm.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index f03647fa3df6..41147da54458 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -3471,6 +3471,9 @@ static int amdgpu_debugfs_pm_info_pp(struct seq_file *m, struct amdgpu_device *a
 	size = sizeof(uint32_t);
 	if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_AVG_POWER, (void *)&query, &size))
 		seq_printf(m, "\t%u.%u W (average GPU)\n", query >> 8, query & 0xff);
+	size = sizeof(uint32_t);
+	if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_INPUT_POWER, (void *)&query, &size))
+		seq_printf(m, "\t%u.%u W (current GPU)\n", query >> 8, query & 0xff);
 	size = sizeof(value);
 	seq_printf(m, "\n");
 

From 7b9f62353024fbf69e1df45f2df87d3cfe0806e9 Mon Sep 17 00:00:00 2001
From: Mangesh Gadre <Mangesh.Gadre@amd.com>
Date: Mon, 21 Aug 2023 18:26:24 +0800
Subject: [PATCH 0920/1189] drm/amdgpu: Updated TCP/UTCL1 programming

Update TCP/UTCL1 thrashing control settings

v2: updated rev_id check

Signed-off-by: Mangesh Gadre <Mangesh.Gadre@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
index a60429c3e93c..b4fdb269f856 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -203,6 +203,9 @@ static void gfx_v9_4_3_init_golden_registers(struct amdgpu_device *adev)
 		if (adev->rev_id == 0) {
 			WREG32_FIELD15_PREREG(GC, dev_inst, TCP_UTCL1_CNTL1,
 					      REDUCE_FIFO_DEPTH_BY_2, 2);
+		} else {
+			WREG32_FIELD15_PREREG(GC, dev_inst, TCP_UTCL1_CNTL2,
+						SPARE, 0x1);
 		}
 	}
 }

From 0a611560f53bfd489e33f4a718c915f1a6123d03 Mon Sep 17 00:00:00 2001
From: Hamza Mahfooz <hamza.mahfooz@amd.com>
Date: Tue, 15 Aug 2023 09:13:37 -0400
Subject: [PATCH 0921/1189] drm/amdgpu: register a dirty framebuffer callback
 for fbcon

fbcon requires that we implement &drm_framebuffer_funcs.dirty.
Otherwise, the framebuffer might take a while to flush (which would
manifest as noticeable lag). However, we can't enable this callback for
non-fbcon cases since it may cause too many atomic commits to be made at
once. So, implement amdgpu_dirtyfb() and only enable it for fbcon
framebuffers (we can use the "struct drm_file file" parameter in the
callback to check for this since it is only NULL when called by fbcon,
at least in the mainline kernel) on devices that support atomic KMS.

Cc: Aurabindo Pillai <aurabindo.pillai@amd.com>
Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: stable@vger.kernel.org # 6.1+
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2519
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_display.c | 26 ++++++++++++++++++++-
 1 file changed, 25 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index d20dd3f852fc..363e6a2cad8c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -38,6 +38,8 @@
 #include <linux/pci.h>
 #include <linux/pm_runtime.h>
 #include <drm/drm_crtc_helper.h>
+#include <drm/drm_damage_helper.h>
+#include <drm/drm_drv.h>
 #include <drm/drm_edid.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
@@ -532,11 +534,29 @@ bool amdgpu_display_ddc_probe(struct amdgpu_connector *amdgpu_connector,
 	return true;
 }
 
+static int amdgpu_dirtyfb(struct drm_framebuffer *fb, struct drm_file *file,
+			  unsigned int flags, unsigned int color,
+			  struct drm_clip_rect *clips, unsigned int num_clips)
+{
+
+	if (file)
+		return -ENOSYS;
+
+	return drm_atomic_helper_dirtyfb(fb, file, flags, color, clips,
+					 num_clips);
+}
+
 static const struct drm_framebuffer_funcs amdgpu_fb_funcs = {
 	.destroy = drm_gem_fb_destroy,
 	.create_handle = drm_gem_fb_create_handle,
 };
 
+static const struct drm_framebuffer_funcs amdgpu_fb_funcs_atomic = {
+	.destroy = drm_gem_fb_destroy,
+	.create_handle = drm_gem_fb_create_handle,
+	.dirty = amdgpu_dirtyfb
+};
+
 uint32_t amdgpu_display_supported_domains(struct amdgpu_device *adev,
 					  uint64_t bo_flags)
 {
@@ -1139,7 +1159,11 @@ static int amdgpu_display_gem_fb_verify_and_init(struct drm_device *dev,
 	if (ret)
 		goto err;
 
-	ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs);
+	if (drm_drv_uses_atomic_modeset(dev))
+		ret = drm_framebuffer_init(dev, &rfb->base,
+					   &amdgpu_fb_funcs_atomic);
+	else
+		ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs);
 
 	if (ret)
 		goto err;

From 7c2949c12e6d5c0f054ee884de6e5a6a1794f0a9 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Wed, 19 Jul 2023 13:17:22 +0530
Subject: [PATCH 0922/1189] drm/amdgpu: Add bootloader wait for PSP v13

Implement the wait for bootloader call back for PSP v13.0 ASICs. Only
for ASICs with PSP v13.0.6, it needs an additional check for VBIOS
mailbox status.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Tested-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/psp_v13_0.c | 28 ++++++++++++++++++++++++--
 1 file changed, 26 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
index 10b17bd5aebe..d2a88bc630d2 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
@@ -133,12 +133,35 @@ static bool psp_v13_0_is_sos_alive(struct psp_context *psp)
 	return sol_reg != 0x0;
 }
 
+static int psp_v13_0_wait_for_vmbx_ready(struct psp_context *psp)
+{
+	struct amdgpu_device *adev = psp->adev;
+	int retry_loop, ret;
+
+	for (retry_loop = 0; retry_loop < 70; retry_loop++) {
+		/* Wait for bootloader to signify that is
+		   ready having bit 31 of C2PMSG_33 set to 1 */
+		ret = psp_wait_for(
+			psp, SOC15_REG_OFFSET(MP0, 0, regMP0_SMN_C2PMSG_33),
+			0x80000000, 0xffffffff, false);
+
+		if (ret == 0)
+			break;
+	}
+
+	if (ret)
+		dev_warn(adev->dev, "Bootloader wait timed out");
+
+	return ret;
+}
+
 static int psp_v13_0_wait_for_bootloader(struct psp_context *psp)
 {
 	struct amdgpu_device *adev = psp->adev;
+	int retry_loop, ret;
 
-	int ret;
-	int retry_loop;
+	if (adev->ip_versions[MP0_HWIP][0] == IP_VERSION(13, 0, 6))
+		psp_v13_0_wait_for_vmbx_ready(psp);
 
 	/* Wait for bootloader to signify that it is ready having bit 31 of
 	 * C2PMSG_35 set to 1. All other bits are expected to be cleared.
@@ -714,6 +737,7 @@ static int psp_v13_0_fatal_error_recovery_quirk(struct psp_context *psp)
 
 static const struct psp_funcs psp_v13_0_funcs = {
 	.init_microcode = psp_v13_0_init_microcode,
+	.wait_for_bootloader = psp_v13_0_wait_for_bootloader,
 	.bootloader_load_kdb = psp_v13_0_bootloader_load_kdb,
 	.bootloader_load_spl = psp_v13_0_bootloader_load_spl,
 	.bootloader_load_sysdrv = psp_v13_0_bootloader_load_sysdrv,

From 1611917f39bee1abfc01501238db8ac19649042d Mon Sep 17 00:00:00 2001
From: Hamza Mahfooz <hamza.mahfooz@amd.com>
Date: Tue, 22 Aug 2023 12:31:09 -0400
Subject: [PATCH 0923/1189] drm/amd/display: register edp_backlight_control()
 for DCN301

As made mention of in commit 099303e9a9bd ("drm/amd/display: eDP
intermittent black screen during PnP"), we need to turn off the
display's backlight before powering off an eDP display. Not doing so
will result in undefined behaviour according to the eDP spec. So, set
DCN301's edp_backlight_control() function pointer to
dce110_edp_backlight_control().

Cc: stable@vger.kernel.org
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2765
Fixes: 9c75891feef0 ("drm/amd/display: rework recent update PHY state commit")
Suggested-by: Swapnil Patel <swapnil.patel@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c
index 257df8660b4c..61205cdbe2d5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c
@@ -75,6 +75,7 @@ static const struct hw_sequencer_funcs dcn301_funcs = {
 	.get_hw_state = dcn10_get_hw_state,
 	.clear_status_bits = dcn10_clear_status_bits,
 	.wait_for_mpcc_disconnect = dcn10_wait_for_mpcc_disconnect,
+	.edp_backlight_control = dce110_edp_backlight_control,
 	.edp_power_control = dce110_edp_power_control,
 	.edp_wait_for_hpd_ready = dce110_edp_wait_for_hpd_ready,
 	.set_cursor_position = dcn10_set_cursor_position,

From 39c8b93a105678821cbf1674d56bd58d775b932f Mon Sep 17 00:00:00 2001
From: Wenjing Liu <wenjing.liu@amd.com>
Date: Tue, 8 Aug 2023 18:49:20 -0400
Subject: [PATCH 0924/1189] Partially revert "drm/amd/display: update add plane
 to context logic with a new algorithm"

This partially reverts commit 460ea8980511 ("drm/amd/display: update add
plane to context logic with a new algorithm").

The new secondary pipe allocation logic triggers an issue with a
specific hardware state transition and causes a frame of corruption when
toggling between windowed MPO and ODM desktop only mode. Ideally hwss is
supposed to handle this scenario. We are temporarily reverting the logic
and investigate the root cause why this transition would cause
corruptions.

Fixes: 460ea8980511 ("drm/amd/display: update add plane to context logic with a new algorithm")
Reviewed-by: Martin Leung <martin.leung@amd.com>
Acked-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Wenjing Liu <wenjing.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/dc/dcn32/dcn32_resource.c | 118 +++++++++++++++++-
 1 file changed, 114 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
index 935cd23e6a01..f9d601c8c721 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
@@ -2564,18 +2564,128 @@ static int find_optimal_free_pipe_as_secondary_dpp_pipe(
 	return free_pipe_idx;
 }
 
+static struct pipe_ctx *find_idle_secondary_pipe_check_mpo(
+		struct resource_context *res_ctx,
+		const struct resource_pool *pool,
+		const struct pipe_ctx *primary_pipe)
+{
+	int i;
+	struct pipe_ctx *secondary_pipe = NULL;
+	struct pipe_ctx *next_odm_mpo_pipe = NULL;
+	int primary_index, preferred_pipe_idx;
+	struct pipe_ctx *old_primary_pipe = NULL;
+
+	/*
+	 * Modified from find_idle_secondary_pipe
+	 * With windowed MPO and ODM, we want to avoid the case where we want a
+	 *  free pipe for the left side but the free pipe is being used on the
+	 *  right side.
+	 * Add check on current_state if the primary_pipe is the left side,
+	 *  to check the right side ( primary_pipe->next_odm_pipe ) to see if
+	 *  it is using a pipe for MPO ( primary_pipe->next_odm_pipe->bottom_pipe )
+	 * - If so, then don't use this pipe
+	 * EXCEPTION - 3 plane ( 2 MPO plane ) case
+	 * - in this case, the primary pipe has already gotten a free pipe for the
+	 *  MPO window in the left
+	 * - when it tries to get a free pipe for the MPO window on the right,
+	 *  it will see that it is already assigned to the right side
+	 *  ( primary_pipe->next_odm_pipe ).  But in this case, we want this
+	 *  free pipe, since it will be for the right side.  So add an
+	 *  additional condition, that skipping the free pipe on the right only
+	 *  applies if the primary pipe has no bottom pipe currently assigned
+	 */
+	if (primary_pipe) {
+		primary_index = primary_pipe->pipe_idx;
+		old_primary_pipe = &primary_pipe->stream->ctx->dc->current_state->res_ctx.pipe_ctx[primary_index];
+		if ((old_primary_pipe->next_odm_pipe) && (old_primary_pipe->next_odm_pipe->bottom_pipe)
+			&& (!primary_pipe->bottom_pipe))
+			next_odm_mpo_pipe = old_primary_pipe->next_odm_pipe->bottom_pipe;
+
+		preferred_pipe_idx = (pool->pipe_count - 1) - primary_pipe->pipe_idx;
+		if ((res_ctx->pipe_ctx[preferred_pipe_idx].stream == NULL) &&
+			!(next_odm_mpo_pipe && next_odm_mpo_pipe->pipe_idx == preferred_pipe_idx)) {
+			secondary_pipe = &res_ctx->pipe_ctx[preferred_pipe_idx];
+			secondary_pipe->pipe_idx = preferred_pipe_idx;
+		}
+	}
+
+	/*
+	 * search backwards for the second pipe to keep pipe
+	 * assignment more consistent
+	 */
+	if (!secondary_pipe)
+		for (i = pool->pipe_count - 1; i >= 0; i--) {
+			if ((res_ctx->pipe_ctx[i].stream == NULL) &&
+				!(next_odm_mpo_pipe && next_odm_mpo_pipe->pipe_idx == i)) {
+				secondary_pipe = &res_ctx->pipe_ctx[i];
+				secondary_pipe->pipe_idx = i;
+				break;
+			}
+		}
+
+	return secondary_pipe;
+}
+
+static struct pipe_ctx *dcn32_acquire_idle_pipe_for_head_pipe_in_layer(
+		struct dc_state *state,
+		const struct resource_pool *pool,
+		struct dc_stream_state *stream,
+		const struct pipe_ctx *head_pipe)
+{
+	struct resource_context *res_ctx = &state->res_ctx;
+	struct pipe_ctx *idle_pipe, *pipe;
+	struct resource_context *old_ctx = &stream->ctx->dc->current_state->res_ctx;
+	int head_index;
+
+	if (!head_pipe)
+		ASSERT(0);
+
+	/*
+	 * Modified from dcn20_acquire_idle_pipe_for_layer
+	 * Check if head_pipe in old_context already has bottom_pipe allocated.
+	 * - If so, check if that pipe is available in the current context.
+	 * --  If so, reuse pipe from old_context
+	 */
+	head_index = head_pipe->pipe_idx;
+	pipe = &old_ctx->pipe_ctx[head_index];
+	if (pipe->bottom_pipe && res_ctx->pipe_ctx[pipe->bottom_pipe->pipe_idx].stream == NULL) {
+		idle_pipe = &res_ctx->pipe_ctx[pipe->bottom_pipe->pipe_idx];
+		idle_pipe->pipe_idx = pipe->bottom_pipe->pipe_idx;
+	} else {
+		idle_pipe = find_idle_secondary_pipe_check_mpo(res_ctx, pool, head_pipe);
+		if (!idle_pipe)
+			return NULL;
+	}
+
+	idle_pipe->stream = head_pipe->stream;
+	idle_pipe->stream_res.tg = head_pipe->stream_res.tg;
+	idle_pipe->stream_res.opp = head_pipe->stream_res.opp;
+
+	idle_pipe->plane_res.hubp = pool->hubps[idle_pipe->pipe_idx];
+	idle_pipe->plane_res.ipp = pool->ipps[idle_pipe->pipe_idx];
+	idle_pipe->plane_res.dpp = pool->dpps[idle_pipe->pipe_idx];
+	idle_pipe->plane_res.mpcc_inst = pool->dpps[idle_pipe->pipe_idx]->inst;
+
+	return idle_pipe;
+}
+
 struct pipe_ctx *dcn32_acquire_free_pipe_as_secondary_dpp_pipe(
 		const struct dc_state *cur_ctx,
 		struct dc_state *new_ctx,
 		const struct resource_pool *pool,
 		const struct pipe_ctx *opp_head_pipe)
 {
-	int free_pipe_idx =
-			find_optimal_free_pipe_as_secondary_dpp_pipe(
-					&cur_ctx->res_ctx, &new_ctx->res_ctx,
-					pool, opp_head_pipe);
+
+	int free_pipe_idx;
 	struct pipe_ctx *free_pipe;
 
+	if (!opp_head_pipe->stream->ctx->dc->config.enable_windowed_mpo_odm)
+		return dcn32_acquire_idle_pipe_for_head_pipe_in_layer(
+				new_ctx, pool, opp_head_pipe->stream, opp_head_pipe);
+
+	free_pipe_idx = find_optimal_free_pipe_as_secondary_dpp_pipe(
+					&cur_ctx->res_ctx, &new_ctx->res_ctx,
+					pool, opp_head_pipe);
 	if (free_pipe_idx >= 0) {
 		free_pipe = &new_ctx->res_ctx.pipe_ctx[free_pipe_idx];
 		free_pipe->pipe_idx = free_pipe_idx;

From 05347402d1c1e52924786cd0c0326080c33e00dc Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Wed, 19 Jul 2023 13:31:47 +0530
Subject: [PATCH 0925/1189] drm/amdgpu: Add SMU v13.0.6 default reset methods

For APUs with SMU v13.0.6, mode-2 reset is kept as default and for
others mode-1 is the default reset method.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Tested-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/soc15.c                   | 4 +++-
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c | 3 +--
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index c45721ca916e..f5be40d7ba36 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -559,8 +559,10 @@ soc15_asic_reset_method(struct amdgpu_device *adev)
 		 */
 		if (amdgpu_gpu_recovery == 4 || amdgpu_gpu_recovery == 5)
 			return AMD_RESET_METHOD_MODE2;
+		else if (!(adev->flags & AMD_IS_APU))
+			return AMD_RESET_METHOD_MODE1;
 		else
-			return AMD_RESET_METHOD_NONE;
+			return AMD_RESET_METHOD_MODE2;
 	default:
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index d3b578e6bc2a..199a673b8120 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -2158,8 +2158,7 @@ static int smu_v13_0_6_mode1_reset(struct smu_context *smu)
 
 static bool smu_v13_0_6_is_mode1_reset_supported(struct smu_context *smu)
 {
-	/* TODO: Enable this when FW support is added */
-	return false;
+	return true;
 }
 
 static bool smu_v13_0_6_is_mode2_reset_supported(struct smu_context *smu)

From 72105dcfa3d12b5af49311f857e3490baa225135 Mon Sep 17 00:00:00 2001
From: Fudong Wang <fudong.wang@amd.com>
Date: Fri, 11 Aug 2023 08:24:59 +0800
Subject: [PATCH 0926/1189] drm/amd/display: Add smu write msg id fail retry
 process

A benchmark stress test (12-40 machines x 48hours) found that DCN315 has
cases where DC writes to an indirect register to set the smu clock msg
id, but when we go to read the same indirect register the returned msg
id doesn't match with what we just set it to. So, to fix this retry the
write until the register's value matches with the requested value.

Cc: stable@vger.kernel.org # 6.1+
Fixes: f94903996140 ("drm/amd/display: Add DCN315 CLK_MGR")
Reviewed-by: Charlene Liu <charlene.liu@amd.com>
Acked-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Fudong Wang <fudong.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../display/dc/clk_mgr/dcn315/dcn315_smu.c    | 20 +++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c
index 3e0da873cf4c..1042cf1a3ab0 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c
@@ -32,6 +32,7 @@
 
 #define MAX_INSTANCE                                        6
 #define MAX_SEGMENT                                         6
+#define SMU_REGISTER_WRITE_RETRY_COUNT                      5
 
 struct IP_BASE_INSTANCE {
     unsigned int segment[MAX_SEGMENT];
@@ -132,6 +133,8 @@ static int dcn315_smu_send_msg_with_param(
 		unsigned int msg_id, unsigned int param)
 {
 	uint32_t result;
+	uint32_t i = 0;
+	uint32_t read_back_data;
 
 	result = dcn315_smu_wait_for_response(clk_mgr, 10, 200000);
 
@@ -148,10 +151,19 @@ static int dcn315_smu_send_msg_with_param(
 	/* Set the parameter register for the SMU message, unit is Mhz */
 	REG_WRITE(MP1_SMN_C2PMSG_37, param);
 
-	/* Trigger the message transaction by writing the message ID */
-	generic_write_indirect_reg(CTX,
-		REG_NBIO(RSMU_INDEX), REG_NBIO(RSMU_DATA),
-		mmMP1_C2PMSG_3, msg_id);
+	for (i = 0; i < SMU_REGISTER_WRITE_RETRY_COUNT; i++) {
+		/* Trigger the message transaction by writing the message ID */
+		generic_write_indirect_reg(CTX,
+			REG_NBIO(RSMU_INDEX), REG_NBIO(RSMU_DATA),
+			mmMP1_C2PMSG_3, msg_id);
+		read_back_data = generic_read_indirect_reg(CTX,
+			REG_NBIO(RSMU_INDEX), REG_NBIO(RSMU_DATA),
+			mmMP1_C2PMSG_3);
+		if (read_back_data == msg_id)
+			break;
+		udelay(2);
+		smu_print("SMU msg id write fail %x times. \n", i + 1);
+	}
 
 	result = dcn315_smu_wait_for_response(clk_mgr, 10, 200000);
 

From 1482650bc7ef01ebb24ec2c3a2e4d50e45da4d8c Mon Sep 17 00:00:00 2001
From: Wenjing Liu <wenjing.liu@amd.com>
Date: Mon, 14 Aug 2023 17:11:16 -0400
Subject: [PATCH 0927/1189] drm/amd/display: update blank state on ODM changes

When we are dynamically adding new ODM slices, we didn't update
blank state, if the pipe used by new ODM slice is previously blanked,
we will continue outputting blank pixel data on that slice causing
right half of the screen showing blank image.

The previous fix was a temporary hack to directly update current state
when committing new state. This could potentially cause hw and sw
state synchronization issues and it is not permitted by dc commit
design.

Cc: stable@vger.kernel.org
Fixes: 7fbf451e7639 ("drm/amd/display: Reinit DPG when exiting dynamic ODM")
Reviewed-by: Dillon Varone <dillon.varone@amd.com>
Acked-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Wenjing Liu <wenjing.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/dc/dcn20/dcn20_hwseq.c    | 36 +++++--------------
 1 file changed, 9 insertions(+), 27 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index 65fa9e21ad9c..87c1ac40240b 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -1106,29 +1106,6 @@ void dcn20_blank_pixel_data(
 			v_active,
 			offset);
 
-	if (!blank && dc->debug.enable_single_display_2to1_odm_policy) {
-		/* when exiting dynamic ODM need to reinit DPG state for unused pipes */
-		struct pipe_ctx *old_odm_pipe = dc->current_state->res_ctx.pipe_ctx[pipe_ctx->pipe_idx].next_odm_pipe;
-
-		odm_pipe = pipe_ctx->next_odm_pipe;
-
-		while (old_odm_pipe) {
-			if (!odm_pipe || old_odm_pipe->pipe_idx != odm_pipe->pipe_idx)
-				dc->hwss.set_disp_pattern_generator(dc,
-						old_odm_pipe,
-						CONTROLLER_DP_TEST_PATTERN_VIDEOMODE,
-						CONTROLLER_DP_COLOR_SPACE_UDEFINED,
-						COLOR_DEPTH_888,
-						NULL,
-						0,
-						0,
-						0);
-			old_odm_pipe = old_odm_pipe->next_odm_pipe;
-			if (odm_pipe)
-				odm_pipe = odm_pipe->next_odm_pipe;
-		}
-	}
-
 	if (!blank)
 		if (stream_res->abm) {
 			dc->hwss.set_pipe(pipe_ctx);
@@ -1722,11 +1699,16 @@ static void dcn20_program_pipe(
 		struct dc_state *context)
 {
 	struct dce_hwseq *hws = dc->hwseq;
-	/* Only need to unblank on top pipe */
 
-	if ((pipe_ctx->update_flags.bits.enable || pipe_ctx->stream->update_flags.bits.abm_level)
-			&& !pipe_ctx->top_pipe && !pipe_ctx->prev_odm_pipe)
-		hws->funcs.blank_pixel_data(dc, pipe_ctx, !pipe_ctx->plane_state->visible);
+	/* Only need to unblank on top pipe */
+	if (resource_is_pipe_type(pipe_ctx, OTG_MASTER)) {
+		if (pipe_ctx->update_flags.bits.enable ||
+				pipe_ctx->update_flags.bits.odm ||
+				pipe_ctx->stream->update_flags.bits.abm_level)
+			hws->funcs.blank_pixel_data(dc, pipe_ctx,
+					!pipe_ctx->plane_state ||
+					!pipe_ctx->plane_state->visible);
+	}
 
 	/* Only update TG on top pipe */
 	if (pipe_ctx->update_flags.bits.global_sync && !pipe_ctx->top_pipe

From 5a3ccb1400339268c5e3dc1fa044a7f6c7f59a02 Mon Sep 17 00:00:00 2001
From: Gabe Teeger <gabe.teeger@amd.com>
Date: Mon, 14 Aug 2023 16:06:18 -0400
Subject: [PATCH 0928/1189] drm/amd/display: Remove wait while locked

[Why]
We wait for mpc idle while in a locked state, leading to potential
deadlock.

[What]
Move the wait_for_idle call to outside of HW lock. This and a
call to wait_drr_doublebuffer_pending_clear are moved added to a new
static helper function called wait_for_outstanding_hw_updates, to make
the interface clearer.

Cc: stable@vger.kernel.org
Fixes: 8f0d304d21b3 ("drm/amd/display: Do not commit pipe when updating DRR")
Reviewed-by: Jun Lei <jun.lei@amd.com>
Acked-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Gabe Teeger <gabe.teeger@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/Makefile       |  1 +
 drivers/gpu/drm/amd/display/dc/core/dc.c      | 58 +++++++++++++------
 .../drm/amd/display/dc/dcn20/dcn20_hwseq.c    | 11 ----
 3 files changed, 42 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/Makefile b/drivers/gpu/drm/amd/display/dc/Makefile
index 69ffd4424dc7..1b8c2aef4633 100644
--- a/drivers/gpu/drm/amd/display/dc/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/Makefile
@@ -78,3 +78,4 @@ DC_EDID += dc_edid_parser.o
 AMD_DISPLAY_DMUB = $(addprefix $(AMDDALPATH)/dc/,$(DC_DMUB))
 AMD_DISPLAY_EDID = $(addprefix $(AMDDALPATH)/dc/,$(DC_EDID))
 AMD_DISPLAY_FILES += $(AMD_DISPLAY_DMUB) $(AMD_DISPLAY_EDID)
+
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 566d7045b2de..54da304b38f0 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -3501,6 +3501,45 @@ static void commit_planes_for_stream_fast(struct dc *dc,
 		top_pipe_to_program->stream->update_flags.raw = 0;
 }
 
+static void wait_for_outstanding_hw_updates(struct dc *dc, const struct dc_state *dc_context)
+{
+/*
+ * This function calls HWSS to wait for any potentially double buffered
+ * operations to complete. It should be invoked as a pre-amble prior
+ * to full update programming before asserting any HW locks.
+ */
+	int pipe_idx;
+	int opp_inst;
+	int opp_count = dc->res_pool->pipe_count;
+	struct hubp *hubp;
+	int mpcc_inst;
+	const struct pipe_ctx *pipe_ctx;
+
+	for (pipe_idx = 0; pipe_idx < dc->res_pool->pipe_count; pipe_idx++) {
+		pipe_ctx = &dc_context->res_ctx.pipe_ctx[pipe_idx];
+
+		if (!pipe_ctx->stream)
+			continue;
+
+		if (pipe_ctx->stream_res.tg->funcs->wait_drr_doublebuffer_pending_clear)
+			pipe_ctx->stream_res.tg->funcs->wait_drr_doublebuffer_pending_clear(pipe_ctx->stream_res.tg);
+
+		hubp = pipe_ctx->plane_res.hubp;
+		if (!hubp)
+			continue;
+
+		mpcc_inst = hubp->inst;
+		// MPCC inst is equal to pipe index in practice
+		for (opp_inst = 0; opp_inst < opp_count; opp_inst++) {
+			if (dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst]) {
+				dc->res_pool->mpc->funcs->wait_for_idle(dc->res_pool->mpc, mpcc_inst);
+				dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst] = false;
+				break;
+			}
+		}
+	}
+}
+
 static void commit_planes_for_stream(struct dc *dc,
 		struct dc_surface_update *srf_updates,
 		int surface_count,
@@ -3519,24 +3558,9 @@ static void commit_planes_for_stream(struct dc *dc,
 	// dc->current_state anymore, so we have to cache it before we apply
 	// the new SubVP context
 	subvp_prev_use = false;
-
-
 	dc_z10_restore(dc);
-
-	if (update_type == UPDATE_TYPE_FULL) {
-		/* wait for all double-buffer activity to clear on all pipes */
-		int pipe_idx;
-
-		for (pipe_idx = 0; pipe_idx < dc->res_pool->pipe_count; pipe_idx++) {
-			struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[pipe_idx];
-
-			if (!pipe_ctx->stream)
-				continue;
-
-			if (pipe_ctx->stream_res.tg->funcs->wait_drr_doublebuffer_pending_clear)
-				pipe_ctx->stream_res.tg->funcs->wait_drr_doublebuffer_pending_clear(pipe_ctx->stream_res.tg);
-		}
-	}
+	if (update_type == UPDATE_TYPE_FULL)
+		wait_for_outstanding_hw_updates(dc, context);
 
 	if (update_type == UPDATE_TYPE_FULL) {
 		dc_allow_idle_optimizations(dc, false);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index 87c1ac40240b..e72f15ac0048 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -1561,17 +1561,6 @@ static void dcn20_update_dchubp_dpp(
 			|| plane_state->update_flags.bits.global_alpha_change
 			|| plane_state->update_flags.bits.per_pixel_alpha_change) {
 		// MPCC inst is equal to pipe index in practice
-		int mpcc_inst = hubp->inst;
-		int opp_inst;
-		int opp_count = dc->res_pool->pipe_count;
-
-		for (opp_inst = 0; opp_inst < opp_count; opp_inst++) {
-			if (dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst]) {
-				dc->res_pool->mpc->funcs->wait_for_idle(dc->res_pool->mpc, mpcc_inst);
-				dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst] = false;
-				break;
-			}
-		}
 		hws->funcs.update_mpcc(dc, pipe_ctx);
 	}
 

From 49a30c3d1a2258fc93cfe6eea8e4951dabadc824 Mon Sep 17 00:00:00 2001
From: Wenjing Liu <wenjing.liu@amd.com>
Date: Tue, 15 Aug 2023 10:47:52 -0400
Subject: [PATCH 0929/1189] drm/amd/display: always switch off ODM before
 committing more streams

ODM power optimization is only supported with single stream. When ODM
power optimization is enabled, we might not have enough free pipes for
enabling other stream. So when we are committing more than 1 stream we
should first switch off ODM power optimization to make room for new
stream and then allocating pipe resource for the new stream.

Cc: stable@vger.kernel.org
Fixes: 59de751e3845 ("drm/amd/display: add ODM case when looking for first split pipe")
Reviewed-by: Dillon Varone <dillon.varone@amd.com>
Acked-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Wenjing Liu <wenjing.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 54da304b38f0..3a9077b60029 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -2073,12 +2073,12 @@ enum dc_status dc_commit_streams(struct dc *dc,
 		}
 	}
 
-	/* Check for case where we are going from odm 2:1 to max
-	 *  pipe scenario.  For these cases, we will call
-	 *  commit_minimal_transition_state() to exit out of odm 2:1
-	 *  first before processing new streams
+	/* ODM Combine 2:1 power optimization is only applied for single stream
+	 * scenario, it uses extra pipes than needed to reduce power consumption
+	 * We need to switch off this feature to make room for new streams.
 	 */
-	if (stream_count == dc->res_pool->pipe_count) {
+	if (stream_count > dc->current_state->stream_count &&
+			dc->current_state->stream_count == 1) {
 		for (i = 0; i < dc->res_pool->pipe_count; i++) {
 			pipe = &dc->current_state->res_ctx.pipe_ctx[i];
 			if (pipe->next_odm_pipe)

From 48d02dcba17aae6a1de4f9814aa5cbe4c977abbb Mon Sep 17 00:00:00 2001
From: Hawking Zhang <Hawking.Zhang@amd.com>
Date: Wed, 23 Aug 2023 17:41:44 +0800
Subject: [PATCH 0930/1189] drm/amdgpu: Add umc_info v4_0 structure

To be used by aqua_vanjaram

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Candice Li <candice.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/include/atomfirmware.h | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h
index e68c1e280322..fa7d6ced786f 100644
--- a/drivers/gpu/drm/amd/include/atomfirmware.h
+++ b/drivers/gpu/drm/amd/include/atomfirmware.h
@@ -3117,6 +3117,24 @@ enum atom_umc_config1_def {
 	UMC_CONFIG1__ENABLE_ECC_CAPABLE = 0x00010000,
 };
 
+struct atom_umc_info_v4_0 {
+	struct atom_common_table_header table_header;
+	uint32_t ucode_reserved[5];
+	uint8_t umcip_min_ver;
+	uint8_t umcip_max_ver;
+	uint8_t vram_type;
+	uint8_t umc_config;
+	uint32_t mem_refclk_10khz;
+	uint32_t clk_reserved[4];
+	uint32_t golden_reserved;
+	uint32_t umc_config1;
+	uint32_t reserved[2];
+	uint8_t channel_num;
+	uint8_t channel_width;
+	uint8_t channel_reserve[2];
+	uint8_t umc_info_reserved[16];
+};
+
 /* 
   ***************************************************************************
     Data Table vram_info  structure

From e0c5c387ac608591c1ce60383b43a99b261483de Mon Sep 17 00:00:00 2001
From: Hawking Zhang <Hawking.Zhang@amd.com>
Date: Wed, 23 Aug 2023 17:43:46 +0800
Subject: [PATCH 0931/1189] drm/amdgpu: Support query ecc cap for aqua_vanjaram

Driver queries umc_info v4_0 to identify ecc cap
for aqua_vanjaram

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Candice Li <candice.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c   | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
index 835980e94b9e..fb2681dd6b33 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
@@ -217,6 +217,7 @@ union umc_info {
 	struct atom_umc_info_v3_1 v31;
 	struct atom_umc_info_v3_2 v32;
 	struct atom_umc_info_v3_3 v33;
+	struct atom_umc_info_v4_0 v40;
 };
 
 union vram_info {
@@ -508,9 +509,8 @@ bool amdgpu_atomfirmware_mem_ecc_supported(struct amdgpu_device *adev)
 
 	if (amdgpu_atom_parse_data_header(mode_info->atom_context,
 				index, &size, &frev, &crev, &data_offset)) {
+		umc_info = (union umc_info *)(mode_info->atom_context->bios + data_offset);
 		if (frev == 3) {
-			umc_info = (union umc_info *)
-				(mode_info->atom_context->bios + data_offset);
 			switch (crev) {
 			case 1:
 				umc_config = le32_to_cpu(umc_info->v31.umc_config);
@@ -533,6 +533,20 @@ bool amdgpu_atomfirmware_mem_ecc_supported(struct amdgpu_device *adev)
 				/* unsupported crev */
 				return false;
 			}
+		} else if (frev == 4) {
+			switch (crev) {
+			case 0:
+				umc_config1 = le32_to_cpu(umc_info->v40.umc_config1);
+				ecc_default_enabled =
+					(umc_config1 & UMC_CONFIG1__ENABLE_ECC_CAPABLE) ? true : false;
+				break;
+			default:
+				/* unsupported crev */
+				return false;
+			}
+		} else {
+			/* unsupported frev */
+			return false;
 		}
 	}
 

From 6d1b3455481a2cc1c6cd478770755c31e932130f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Andr=C3=A9=20Almeida?= <andrealmeid@igalia.com>
Date: Thu, 17 Aug 2023 15:20:46 -0300
Subject: [PATCH 0932/1189] drm/amdgpu: Allocate coredump memory in a
 nonblocking way
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

During a GPU reset, a normal memory reclaim could block to reclaim
memory. Giving that coredump is a best effort mechanism, it shouldn't
disturb the reset path. Change its memory allocation flag to a
nonblocking one.

Signed-off-by: André Almeida <andrealmeid@igalia.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 533daba2accb..3f001a50b34a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4869,7 +4869,7 @@ static void amdgpu_reset_capture_coredumpm(struct amdgpu_device *adev)
 	struct drm_device *dev = adev_to_drm(adev);
 
 	ktime_get_ts64(&adev->reset_time);
-	dev_coredumpm(dev->dev, THIS_MODULE, adev, 0, GFP_KERNEL,
+	dev_coredumpm(dev->dev, THIS_MODULE, adev, 0, GFP_NOWAIT,
 		      amdgpu_devcoredump_read, amdgpu_devcoredump_free);
 }
 #endif

From a1fe9e9f73ce42f8cfcd07b5af221c17b850ebdf Mon Sep 17 00:00:00 2001
From: Alex Sierra <alex.sierra@amd.com>
Date: Mon, 28 Aug 2023 09:47:21 -0500
Subject: [PATCH 0933/1189] drm/amdkfd: use mask to get v9 interrupt sq data
 bits correctly

Interrupt sq data bits were not taken properly from contextid0 and contextid1.
Use macro KFD_CONTEXT_ID_GET_SQ_INT_DATA instead.

Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
index f0731a6a5306..830396b1c3b1 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
@@ -384,7 +384,7 @@ static void event_interrupt_wq_v9(struct kfd_node *dev,
 			default:
 				break;
 			}
-			kfd_signal_event_interrupt(pasid, context_id0 & 0xffffff, 24);
+			kfd_signal_event_interrupt(pasid, sq_int_data, 24);
 		} else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE) {
 			kfd_set_dbg_ev_from_interrupt(dev, pasid,
 				KFD_DEBUG_DOORBELL_ID(context_id0),

From e23b10675ac610b26f24a6e8b3eb9bc6d38e5342 Mon Sep 17 00:00:00 2001
From: Tao Zhou <tao.zhou1@amd.com>
Date: Fri, 25 Aug 2023 15:13:57 +0800
Subject: [PATCH 0934/1189] drm/amdgpu: use read-modify-write mode for gfx
 v9_4_3 SQ setting

Instead of using direct update, avoid touching unrelated fields.

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
index b4fdb269f856..f24a5474db35 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -4042,7 +4042,8 @@ static void gfx_v9_4_3_inst_enable_watchdog_timer(struct amdgpu_device *adev,
 	uint32_t i;
 	uint32_t data;
 
-	data = REG_SET_FIELD(0, SQ_TIMEOUT_CONFIG, TIMEOUT_FATAL_DISABLE,
+	data = RREG32_SOC15(GC, GET_INST(GC, 0), regSQ_TIMEOUT_CONFIG);
+	data = REG_SET_FIELD(data, SQ_TIMEOUT_CONFIG, TIMEOUT_FATAL_DISABLE,
 			     amdgpu_watchdog_timer.timeout_fatal_disable ? 1 : 0);
 
 	if (amdgpu_watchdog_timer.timeout_fatal_disable &&

From 2031c46b09843c9f135468fe03a333f9fa0a30a7 Mon Sep 17 00:00:00 2001
From: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Date: Thu, 24 Aug 2023 11:16:40 -0400
Subject: [PATCH 0935/1189] drm/amdgpu: Hide xcp partition sysfs under SRIOV

XCP partitions should not be visible for the VF for GFXIP 9.4.3.

Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
index f24a5474db35..0a26a00074a6 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -863,11 +863,15 @@ static int gfx_v9_4_3_sw_init(void *handle)
 	if (r)
 		return r;
 
-	r = amdgpu_gfx_sysfs_init(adev);
+	r = amdgpu_gfx_ras_sw_init(adev);
 	if (r)
 		return r;
 
-	return amdgpu_gfx_ras_sw_init(adev);
+
+	if (!amdgpu_sriov_vf(adev))
+		r = amdgpu_gfx_sysfs_init(adev);
+
+	return r;
 }
 
 static int gfx_v9_4_3_sw_fini(void *handle)
@@ -888,7 +892,8 @@ static int gfx_v9_4_3_sw_fini(void *handle)
 	gfx_v9_4_3_mec_fini(adev);
 	amdgpu_bo_unref(&adev->gfx.rlc.clear_state_obj);
 	gfx_v9_4_3_free_microcode(adev);
-	amdgpu_gfx_sysfs_fini(adev);
+	if (!amdgpu_sriov_vf(adev))
+		amdgpu_gfx_sysfs_fini(adev);
 
 	return 0;
 }

From 9f051d6ff13fb20b424a86672db42746aa27d963 Mon Sep 17 00:00:00 2001
From: Hawking Zhang <Hawking.Zhang@amd.com>
Date: Tue, 29 Aug 2023 23:20:27 +0800
Subject: [PATCH 0936/1189] drm/amdgpu: Free ras cmd input buffer properly

Do not access the pointer for ras input cmd buffer
if it is even not allocated.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Stanley Yang <Stanley.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 378478cf9c21..3c4600e15b86 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -764,7 +764,7 @@ int amdgpu_ras_feature_enable(struct amdgpu_device *adev,
 {
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 	union ta_ras_cmd_input *info;
-	int ret = 0;
+	int ret;
 
 	if (!con)
 		return -EINVAL;
@@ -773,7 +773,7 @@ int amdgpu_ras_feature_enable(struct amdgpu_device *adev,
 	if (enable &&
 	    head->block != AMDGPU_RAS_BLOCK__GFX &&
 	    !amdgpu_ras_is_feature_allowed(adev, head))
-		goto out;
+		return 0;
 
 	/* Only enable gfx ras feature from host side */
 	if (head->block == AMDGPU_RAS_BLOCK__GFX &&
@@ -801,16 +801,16 @@ int amdgpu_ras_feature_enable(struct amdgpu_device *adev,
 				enable ? "enable":"disable",
 				get_ras_block_str(head),
 				amdgpu_ras_is_poison_mode_supported(adev), ret);
-			goto out;
+			return ret;
 		}
+
+		kfree(info);
 	}
 
 	/* setup the obj */
 	__amdgpu_ras_feature_enable(adev, head, enable);
-out:
-	if (head->block == AMDGPU_RAS_BLOCK__GFX)
-		kfree(info);
-	return ret;
+
+	return 0;
 }
 
 /* Only used in device probe stage and called only once. */

From e9dca969b2426702a73719ab9207e43c6d80b581 Mon Sep 17 00:00:00 2001
From: Jay Cornwall <jay.cornwall@amd.com>
Date: Fri, 25 Aug 2023 12:18:41 -0400
Subject: [PATCH 0937/1189] drm/amdkfd: Add missing gfx11 MQD manager callbacks

mqd_stride function was introduced in commit 2f77b9a242a2
("drm/amdkfd: Update MQD management on multi XCC setup")
but not assigned for gfx11. Fixes a NULL dereference in debugfs.

Signed-off-by: Jay Cornwall <jay.cornwall@amd.com>
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.5.x
---
 drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
index 2319467d2d95..0bbf0edbabd4 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
@@ -457,6 +457,7 @@ struct mqd_manager *mqd_manager_init_v11(enum KFD_MQD_TYPE type,
 		mqd->is_occupied = kfd_is_occupied_cp;
 		mqd->mqd_size = sizeof(struct v11_compute_mqd);
 		mqd->get_wave_state = get_wave_state;
+		mqd->mqd_stride = kfd_mqd_stride;
 #if defined(CONFIG_DEBUG_FS)
 		mqd->debugfs_show_mqd = debugfs_show_mqd;
 #endif
@@ -472,6 +473,7 @@ struct mqd_manager *mqd_manager_init_v11(enum KFD_MQD_TYPE type,
 		mqd->destroy_mqd = destroy_hiq_mqd;
 		mqd->is_occupied = kfd_is_occupied_cp;
 		mqd->mqd_size = sizeof(struct v11_compute_mqd);
+		mqd->mqd_stride = kfd_mqd_stride;
 #if defined(CONFIG_DEBUG_FS)
 		mqd->debugfs_show_mqd = debugfs_show_mqd;
 #endif
@@ -501,6 +503,7 @@ struct mqd_manager *mqd_manager_init_v11(enum KFD_MQD_TYPE type,
 		mqd->destroy_mqd = kfd_destroy_mqd_sdma;
 		mqd->is_occupied = kfd_is_occupied_sdma;
 		mqd->mqd_size = sizeof(struct v11_sdma_mqd);
+		mqd->mqd_stride = kfd_mqd_stride;
 #if defined(CONFIG_DEBUG_FS)
 		mqd->debugfs_show_mqd = debugfs_show_mqd_sdma;
 #endif

From 46528db35561e45ff0a5e9c80d6e6e69a5877150 Mon Sep 17 00:00:00 2001
From: Hamza Mahfooz <hamza.mahfooz@amd.com>
Date: Tue, 29 Aug 2023 07:27:15 -0400
Subject: [PATCH 0938/1189] Revert "Revert "drm/amd/display: Implement zpos
 property""

This reverts commit e2066eb4efe0e7d2d329d6e6765ed637a523ac45.

The problematic IGT test case (i.e. kms_atomic@plane-immutable-zpos) has
been fixed as of commit cb77add45011 ("tests/kms_atomic: remove zpos <
N-planes assert") to the IGT repo. So, reintroduce the reverted code.

Link: https://gitlab.freedesktop.org/drm/igt-gpu-tools/-/commit/cb77add45011b129e21f3cb2a4089a73dde56179
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Melissa Wen <mwen@igalia.com>
Signed-off-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
index 8eeca160d434..2198df96ed6f 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
@@ -1468,6 +1468,15 @@ int amdgpu_dm_plane_init(struct amdgpu_display_manager *dm,
 		drm_plane_create_blend_mode_property(plane, blend_caps);
 	}
 
+	if (plane->type == DRM_PLANE_TYPE_PRIMARY) {
+		drm_plane_create_zpos_immutable_property(plane, 0);
+	} else if (plane->type == DRM_PLANE_TYPE_OVERLAY) {
+		unsigned int zpos = 1 + drm_plane_index(plane);
+		drm_plane_create_zpos_property(plane, zpos, 1, 254);
+	} else if (plane->type == DRM_PLANE_TYPE_CURSOR) {
+		drm_plane_create_zpos_immutable_property(plane, 255);
+	}
+
 	if (plane->type == DRM_PLANE_TYPE_PRIMARY &&
 	    plane_cap &&
 	    (plane_cap->pixel_format_support.nv12 ||

From 35588314e963938dfdcdb792c9170108399377d6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>
Date: Fri, 25 Aug 2023 15:28:00 +0200
Subject: [PATCH 0939/1189] drm/amdgpu: fix amdgpu_cs_p1_user_fence
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The offset is just 32bits here so this can potentially overflow if
somebody specifies a large value. Instead reduce the size to calculate
the last possible offset.

The error handling path incorrectly drops the reference to the user
fence BO resulting in potential reference count underflow.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 18 ++++--------------
 1 file changed, 4 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 49dd9aa8da70..efdb1c48f431 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -127,7 +127,6 @@ static int amdgpu_cs_p1_user_fence(struct amdgpu_cs_parser *p,
 {
 	struct drm_gem_object *gobj;
 	unsigned long size;
-	int r;
 
 	gobj = drm_gem_object_lookup(p->filp, data->handle);
 	if (gobj == NULL)
@@ -137,23 +136,14 @@ static int amdgpu_cs_p1_user_fence(struct amdgpu_cs_parser *p,
 	drm_gem_object_put(gobj);
 
 	size = amdgpu_bo_size(p->uf_bo);
-	if (size != PAGE_SIZE || (data->offset + 8) > size) {
-		r = -EINVAL;
-		goto error_unref;
-	}
+	if (size != PAGE_SIZE || data->offset > (size - 8))
+		return -EINVAL;
 
-	if (amdgpu_ttm_tt_get_usermm(p->uf_bo->tbo.ttm)) {
-		r = -EINVAL;
-		goto error_unref;
-	}
+	if (amdgpu_ttm_tt_get_usermm(p->uf_bo->tbo.ttm))
+		return -EINVAL;
 
 	*offset = data->offset;
-
 	return 0;
-
-error_unref:
-	amdgpu_bo_unref(&p->uf_bo);
-	return r;
 }
 
 static int amdgpu_cs_p1_bo_handles(struct amdgpu_cs_parser *p,

From 82ba0ff7bf0483d962e592017bef659ae022d754 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 31 Aug 2023 08:45:09 +0000
Subject: [PATCH 0940/1189] net/handshake: fix null-ptr-deref in
 handshake_nl_done_doit()

We should not call trace_handshake_cmd_done_err() if socket lookup has failed.

Also we should call trace_handshake_cmd_done_err() before releasing the file,
otherwise dereferencing sock->sk can return garbage.

This also reverts 7afc6d0a107f ("net/handshake: Fix uninitialized local variable")

Unable to handle kernel paging request at virtual address dfff800000000003
KASAN: null-ptr-deref in range [0x0000000000000018-0x000000000000001f]
Mem abort info:
ESR = 0x0000000096000005
EC = 0x25: DABT (current EL), IL = 32 bits
SET = 0, FnV = 0
EA = 0, S1PTW = 0
FSC = 0x05: level 1 translation fault
Data abort info:
ISV = 0, ISS = 0x00000005, ISS2 = 0x00000000
CM = 0, WnR = 0, TnD = 0, TagAccess = 0
GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
[dfff800000000003] address between user and kernel address ranges
Internal error: Oops: 0000000096000005 [#1] PREEMPT SMP
Modules linked in:
CPU: 1 PID: 5986 Comm: syz-executor292 Not tainted 6.5.0-rc7-syzkaller-gfe4469582053 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/26/2023
pstate: 80400005 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : handshake_nl_done_doit+0x198/0x9c8 net/handshake/netlink.c:193
lr : handshake_nl_done_doit+0x180/0x9c8
sp : ffff800096e37180
x29: ffff800096e37200 x28: 1ffff00012dc6e34 x27: dfff800000000000
x26: ffff800096e373d0 x25: 0000000000000000 x24: 00000000ffffffa8
x23: ffff800096e373f0 x22: 1ffff00012dc6e38 x21: 0000000000000000
x20: ffff800096e371c0 x19: 0000000000000018 x18: 0000000000000000
x17: 0000000000000000 x16: ffff800080516cc4 x15: 0000000000000001
x14: 1fffe0001b14aa3b x13: 0000000000000000 x12: 0000000000000000
x11: 0000000000000000 x10: 0000000000000000 x9 : 0000000000000003
x8 : 0000000000000003 x7 : ffff800080afe47c x6 : 0000000000000000
x5 : 0000000000000000 x4 : 0000000000000000 x3 : ffff800080a88078
x2 : 0000000000000001 x1 : 00000000ffffffa8 x0 : 0000000000000000
Call trace:
handshake_nl_done_doit+0x198/0x9c8 net/handshake/netlink.c:193
genl_family_rcv_msg_doit net/netlink/genetlink.c:970 [inline]
genl_family_rcv_msg net/netlink/genetlink.c:1050 [inline]
genl_rcv_msg+0x96c/0xc50 net/netlink/genetlink.c:1067
netlink_rcv_skb+0x214/0x3c4 net/netlink/af_netlink.c:2549
genl_rcv+0x38/0x50 net/netlink/genetlink.c:1078
netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline]
netlink_unicast+0x660/0x8d4 net/netlink/af_netlink.c:1365
netlink_sendmsg+0x834/0xb18 net/netlink/af_netlink.c:1914
sock_sendmsg_nosec net/socket.c:725 [inline]
sock_sendmsg net/socket.c:748 [inline]
____sys_sendmsg+0x56c/0x840 net/socket.c:2494
___sys_sendmsg net/socket.c:2548 [inline]
__sys_sendmsg+0x26c/0x33c net/socket.c:2577
__do_sys_sendmsg net/socket.c:2586 [inline]
__se_sys_sendmsg net/socket.c:2584 [inline]
__arm64_sys_sendmsg+0x80/0x94 net/socket.c:2584
__invoke_syscall arch/arm64/kernel/syscall.c:37 [inline]
invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:51
el0_svc_common+0x130/0x23c arch/arm64/kernel/syscall.c:136
do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:155
el0_svc+0x58/0x16c arch/arm64/kernel/entry-common.c:678
el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:696
el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:591
Code: 12800108 b90043e8 910062b3 d343fe68 (387b6908)

Fixes: 3b3009ea8abb ("net/handshake: Create a NETLINK service for handling handshake requests")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/handshake/netlink.c | 18 ++++++------------
 1 file changed, 6 insertions(+), 12 deletions(-)

diff --git a/net/handshake/netlink.c b/net/handshake/netlink.c
index 1086653e1fad..d0bc1dd8e65a 100644
--- a/net/handshake/netlink.c
+++ b/net/handshake/netlink.c
@@ -157,26 +157,24 @@ out_status:
 int handshake_nl_done_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct net *net = sock_net(skb->sk);
-	struct handshake_req *req = NULL;
-	struct socket *sock = NULL;
+	struct handshake_req *req;
+	struct socket *sock;
 	int fd, status, err;
 
 	if (GENL_REQ_ATTR_CHECK(info, HANDSHAKE_A_DONE_SOCKFD))
 		return -EINVAL;
 	fd = nla_get_u32(info->attrs[HANDSHAKE_A_DONE_SOCKFD]);
 
-	err = 0;
 	sock = sockfd_lookup(fd, &err);
-	if (err) {
-		err = -EBADF;
-		goto out_status;
-	}
+	if (!sock)
+		return err;
 
 	req = handshake_req_hash_lookup(sock->sk);
 	if (!req) {
 		err = -EBUSY;
+		trace_handshake_cmd_done_err(net, req, sock->sk, err);
 		fput(sock->file);
-		goto out_status;
+		return err;
 	}
 
 	trace_handshake_cmd_done(net, req, sock->sk, fd);
@@ -188,10 +186,6 @@ int handshake_nl_done_doit(struct sk_buff *skb, struct genl_info *info)
 	handshake_complete(req, status, info);
 	fput(sock->file);
 	return 0;
-
-out_status:
-	trace_handshake_cmd_done_err(net, req, sock->sk, err);
-	return err;
 }
 
 static unsigned int handshake_net_id;

From 66d58f046c9d3a8f996b7138d02e965fd0617de0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 31 Aug 2023 13:52:08 +0000
Subject: [PATCH 0941/1189] net: use sk_forward_alloc_get() in sk_get_meminfo()

inet_sk_diag_fill() has been changed to use sk_forward_alloc_get(),
but sk_get_meminfo() was forgotten.

Fixes: 292e6077b040 ("net: introduce sk_forward_alloc_get()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index b0dd501dabd6..a61ec97098ad 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3743,7 +3743,7 @@ void sk_get_meminfo(const struct sock *sk, u32 *mem)
 	mem[SK_MEMINFO_RCVBUF] = READ_ONCE(sk->sk_rcvbuf);
 	mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk);
 	mem[SK_MEMINFO_SNDBUF] = READ_ONCE(sk->sk_sndbuf);
-	mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc;
+	mem[SK_MEMINFO_FWD_ALLOC] = sk_forward_alloc_get(sk);
 	mem[SK_MEMINFO_WMEM_QUEUED] = READ_ONCE(sk->sk_wmem_queued);
 	mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
 	mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len);

From 5e6300e7b3a4ab5b72a82079753868e91fbf9efc Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 31 Aug 2023 13:52:09 +0000
Subject: [PATCH 0942/1189] net: annotate data-races around
 sk->sk_forward_alloc

Every time sk->sk_forward_alloc is read locklessly,
add a READ_ONCE().

Add sk_forward_alloc_add() helper to centralize updates,
to reduce number of WRITE_ONCE().

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h    | 12 +++++++++---
 net/core/sock.c       |  8 ++++----
 net/ipv4/tcp_output.c |  2 +-
 net/ipv4/udp.c        |  6 +++---
 net/mptcp/protocol.c  |  6 +++---
 5 files changed, 20 insertions(+), 14 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 11d503417591..f04869ac1d92 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1053,6 +1053,12 @@ static inline void sk_wmem_queued_add(struct sock *sk, int val)
 	WRITE_ONCE(sk->sk_wmem_queued, sk->sk_wmem_queued + val);
 }
 
+static inline void sk_forward_alloc_add(struct sock *sk, int val)
+{
+	/* Paired with lockless reads of sk->sk_forward_alloc */
+	WRITE_ONCE(sk->sk_forward_alloc, sk->sk_forward_alloc + val);
+}
+
 void sk_stream_write_space(struct sock *sk);
 
 /* OOB backlog add */
@@ -1377,7 +1383,7 @@ static inline int sk_forward_alloc_get(const struct sock *sk)
 	if (sk->sk_prot->forward_alloc_get)
 		return sk->sk_prot->forward_alloc_get(sk);
 #endif
-	return sk->sk_forward_alloc;
+	return READ_ONCE(sk->sk_forward_alloc);
 }
 
 static inline bool __sk_stream_memory_free(const struct sock *sk, int wake)
@@ -1673,14 +1679,14 @@ static inline void sk_mem_charge(struct sock *sk, int size)
 {
 	if (!sk_has_account(sk))
 		return;
-	sk->sk_forward_alloc -= size;
+	sk_forward_alloc_add(sk, -size);
 }
 
 static inline void sk_mem_uncharge(struct sock *sk, int size)
 {
 	if (!sk_has_account(sk))
 		return;
-	sk->sk_forward_alloc += size;
+	sk_forward_alloc_add(sk, size);
 	sk_mem_reclaim(sk);
 }
 
diff --git a/net/core/sock.c b/net/core/sock.c
index a61ec97098ad..40e1bda4bde0 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1045,7 +1045,7 @@ static int sock_reserve_memory(struct sock *sk, int bytes)
 		mem_cgroup_uncharge_skmem(sk->sk_memcg, pages);
 		return -ENOMEM;
 	}
-	sk->sk_forward_alloc += pages << PAGE_SHIFT;
+	sk_forward_alloc_add(sk, pages << PAGE_SHIFT);
 
 	WRITE_ONCE(sk->sk_reserved_mem,
 		   sk->sk_reserved_mem + (pages << PAGE_SHIFT));
@@ -3139,10 +3139,10 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind)
 {
 	int ret, amt = sk_mem_pages(size);
 
-	sk->sk_forward_alloc += amt << PAGE_SHIFT;
+	sk_forward_alloc_add(sk, amt << PAGE_SHIFT);
 	ret = __sk_mem_raise_allocated(sk, size, amt, kind);
 	if (!ret)
-		sk->sk_forward_alloc -= amt << PAGE_SHIFT;
+		sk_forward_alloc_add(sk, -(amt << PAGE_SHIFT));
 	return ret;
 }
 EXPORT_SYMBOL(__sk_mem_schedule);
@@ -3174,7 +3174,7 @@ void __sk_mem_reduce_allocated(struct sock *sk, int amount)
 void __sk_mem_reclaim(struct sock *sk, int amount)
 {
 	amount >>= PAGE_SHIFT;
-	sk->sk_forward_alloc -= amount << PAGE_SHIFT;
+	sk_forward_alloc_add(sk, -(amount << PAGE_SHIFT));
 	__sk_mem_reduce_allocated(sk, amount);
 }
 EXPORT_SYMBOL(__sk_mem_reclaim);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e6b4fbd642f7..ccfc8bbf7455 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3474,7 +3474,7 @@ void sk_forced_mem_schedule(struct sock *sk, int size)
 	if (delta <= 0)
 		return;
 	amt = sk_mem_pages(delta);
-	sk->sk_forward_alloc += amt << PAGE_SHIFT;
+	sk_forward_alloc_add(sk, amt << PAGE_SHIFT);
 	sk_memory_allocated_add(sk, amt);
 
 	if (mem_cgroup_sockets_enabled && sk->sk_memcg)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 0794a2c46a56..f39b9c844580 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1414,9 +1414,9 @@ static void udp_rmem_release(struct sock *sk, int size, int partial,
 		spin_lock(&sk_queue->lock);
 
 
-	sk->sk_forward_alloc += size;
+	sk_forward_alloc_add(sk, size);
 	amt = (sk->sk_forward_alloc - partial) & ~(PAGE_SIZE - 1);
-	sk->sk_forward_alloc -= amt;
+	sk_forward_alloc_add(sk, -amt);
 
 	if (amt)
 		__sk_mem_reduce_allocated(sk, amt >> PAGE_SHIFT);
@@ -1527,7 +1527,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
 		goto uncharge_drop;
 	}
 
-	sk->sk_forward_alloc -= size;
+	sk_forward_alloc_add(sk, -size);
 
 	/* no need to setup a destructor, we will explicitly release the
 	 * forward allocated memory on dequeue
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 933b257eee02..625df3a36c46 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1800,7 +1800,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		}
 
 		/* data successfully copied into the write queue */
-		sk->sk_forward_alloc -= total_ts;
+		sk_forward_alloc_add(sk, -total_ts);
 		copied += psize;
 		dfrag->data_len += psize;
 		frag_truesize += psize;
@@ -3257,7 +3257,7 @@ void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags)
 	/* move all the rx fwd alloc into the sk_mem_reclaim_final in
 	 * inet_sock_destruct() will dispose it
 	 */
-	sk->sk_forward_alloc += msk->rmem_fwd_alloc;
+	sk_forward_alloc_add(sk, msk->rmem_fwd_alloc);
 	msk->rmem_fwd_alloc = 0;
 	mptcp_token_destroy(msk);
 	mptcp_pm_free_anno_list(msk);
@@ -3522,7 +3522,7 @@ static void mptcp_shutdown(struct sock *sk, int how)
 
 static int mptcp_forward_alloc_get(const struct sock *sk)
 {
-	return sk->sk_forward_alloc + mptcp_sk(sk)->rmem_fwd_alloc;
+	return READ_ONCE(sk->sk_forward_alloc) + mptcp_sk(sk)->rmem_fwd_alloc;
 }
 
 static int mptcp_ioctl_outq(const struct mptcp_sock *msk, u64 v)

From 9531e4a83febc3fb47ac77e24cfb5ea97e50034d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 31 Aug 2023 13:52:10 +0000
Subject: [PATCH 0943/1189] mptcp: annotate data-races around
 msk->rmem_fwd_alloc

msk->rmem_fwd_alloc can be read locklessly.

Add mptcp_rmem_fwd_alloc_add(), similar to sk_forward_alloc_add(),
and appropriate READ_ONCE()/WRITE_ONCE() annotations.

Fixes: 6511882cdd82 ("mptcp: allocate fwd memory separately on the rx and tx path")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 625df3a36c46..a7fc16f5175d 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -134,9 +134,15 @@ static void mptcp_drop(struct sock *sk, struct sk_buff *skb)
 	__kfree_skb(skb);
 }
 
+static void mptcp_rmem_fwd_alloc_add(struct sock *sk, int size)
+{
+	WRITE_ONCE(mptcp_sk(sk)->rmem_fwd_alloc,
+		   mptcp_sk(sk)->rmem_fwd_alloc + size);
+}
+
 static void mptcp_rmem_charge(struct sock *sk, int size)
 {
-	mptcp_sk(sk)->rmem_fwd_alloc -= size;
+	mptcp_rmem_fwd_alloc_add(sk, -size);
 }
 
 static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to,
@@ -177,7 +183,7 @@ static bool mptcp_ooo_try_coalesce(struct mptcp_sock *msk, struct sk_buff *to,
 static void __mptcp_rmem_reclaim(struct sock *sk, int amount)
 {
 	amount >>= PAGE_SHIFT;
-	mptcp_sk(sk)->rmem_fwd_alloc -= amount << PAGE_SHIFT;
+	mptcp_rmem_charge(sk, amount << PAGE_SHIFT);
 	__sk_mem_reduce_allocated(sk, amount);
 }
 
@@ -186,7 +192,7 @@ static void mptcp_rmem_uncharge(struct sock *sk, int size)
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	int reclaimable;
 
-	msk->rmem_fwd_alloc += size;
+	mptcp_rmem_fwd_alloc_add(sk, size);
 	reclaimable = msk->rmem_fwd_alloc - sk_unused_reserved_mem(sk);
 
 	/* see sk_mem_uncharge() for the rationale behind the following schema */
@@ -341,7 +347,7 @@ static bool mptcp_rmem_schedule(struct sock *sk, struct sock *ssk, int size)
 	if (!__sk_mem_raise_allocated(sk, size, amt, SK_MEM_RECV))
 		return false;
 
-	msk->rmem_fwd_alloc += amount;
+	mptcp_rmem_fwd_alloc_add(sk, amount);
 	return true;
 }
 
@@ -3258,7 +3264,7 @@ void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags)
 	 * inet_sock_destruct() will dispose it
 	 */
 	sk_forward_alloc_add(sk, msk->rmem_fwd_alloc);
-	msk->rmem_fwd_alloc = 0;
+	WRITE_ONCE(msk->rmem_fwd_alloc, 0);
 	mptcp_token_destroy(msk);
 	mptcp_pm_free_anno_list(msk);
 	mptcp_free_local_addr_list(msk);
@@ -3522,7 +3528,8 @@ static void mptcp_shutdown(struct sock *sk, int how)
 
 static int mptcp_forward_alloc_get(const struct sock *sk)
 {
-	return READ_ONCE(sk->sk_forward_alloc) + mptcp_sk(sk)->rmem_fwd_alloc;
+	return READ_ONCE(sk->sk_forward_alloc) +
+	       READ_ONCE(mptcp_sk(sk)->rmem_fwd_alloc);
 }
 
 static int mptcp_ioctl_outq(const struct mptcp_sock *msk, u64 v)

From e3390b30a5dfb112e8e802a59c0f68f947b638b2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 31 Aug 2023 13:52:11 +0000
Subject: [PATCH 0944/1189] net: annotate data-races around sk->sk_tsflags

sk->sk_tsflags can be read locklessly, add corresponding annotations.

Fixes: b9f40e21ef42 ("net-timestamp: move timestamp flags out of sk_flags")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h       |  2 +-
 include/net/sock.h     | 17 ++++++++++-------
 net/can/j1939/socket.c | 10 ++++++----
 net/core/skbuff.c      | 10 ++++++----
 net/core/sock.c        |  4 ++--
 net/ipv4/ip_output.c   |  2 +-
 net/ipv4/ip_sockglue.c |  2 +-
 net/ipv4/tcp.c         |  4 ++--
 net/ipv6/ip6_output.c  |  2 +-
 net/ipv6/ping.c        |  2 +-
 net/ipv6/raw.c         |  2 +-
 net/ipv6/udp.c         |  2 +-
 net/socket.c           | 13 +++++++------
 13 files changed, 40 insertions(+), 32 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index 19adacd5ece0..9276cea775cc 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -94,7 +94,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm,
 	ipcm_init(ipcm);
 
 	ipcm->sockc.mark = READ_ONCE(inet->sk.sk_mark);
-	ipcm->sockc.tsflags = inet->sk.sk_tsflags;
+	ipcm->sockc.tsflags = READ_ONCE(inet->sk.sk_tsflags);
 	ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if);
 	ipcm->addr = inet->inet_saddr;
 	ipcm->protocol = inet->inet_num;
diff --git a/include/net/sock.h b/include/net/sock.h
index f04869ac1d92..b770261fbdaf 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1906,7 +1906,9 @@ struct sockcm_cookie {
 static inline void sockcm_init(struct sockcm_cookie *sockc,
 			       const struct sock *sk)
 {
-	*sockc = (struct sockcm_cookie) { .tsflags = sk->sk_tsflags };
+	*sockc = (struct sockcm_cookie) {
+		.tsflags = READ_ONCE(sk->sk_tsflags)
+	};
 }
 
 int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg,
@@ -2701,9 +2703,9 @@ void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk,
 static inline void
 sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
 {
-	ktime_t kt = skb->tstamp;
 	struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb);
-
+	u32 tsflags = READ_ONCE(sk->sk_tsflags);
+	ktime_t kt = skb->tstamp;
 	/*
 	 * generate control messages if
 	 * - receive time stamping in software requested
@@ -2711,10 +2713,10 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
 	 * - hardware time stamps available and wanted
 	 */
 	if (sock_flag(sk, SOCK_RCVTSTAMP) ||
-	    (sk->sk_tsflags & SOF_TIMESTAMPING_RX_SOFTWARE) ||
-	    (kt && sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) ||
+	    (tsflags & SOF_TIMESTAMPING_RX_SOFTWARE) ||
+	    (kt && tsflags & SOF_TIMESTAMPING_SOFTWARE) ||
 	    (hwtstamps->hwtstamp &&
-	     (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE)))
+	     (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE)))
 		__sock_recv_timestamp(msg, sk, skb);
 	else
 		sock_write_timestamp(sk, kt);
@@ -2736,7 +2738,8 @@ static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk,
 #define TSFLAGS_ANY	  (SOF_TIMESTAMPING_SOFTWARE			| \
 			   SOF_TIMESTAMPING_RAW_HARDWARE)
 
-	if (sk->sk_flags & FLAGS_RECV_CMSGS || sk->sk_tsflags & TSFLAGS_ANY)
+	if (sk->sk_flags & FLAGS_RECV_CMSGS ||
+	    READ_ONCE(sk->sk_tsflags) & TSFLAGS_ANY)
 		__sock_recv_cmsgs(msg, sk, skb);
 	else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP)))
 		sock_write_timestamp(sk, skb->tstamp);
diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c
index feaec4ad6d16..b28c976f52a0 100644
--- a/net/can/j1939/socket.c
+++ b/net/can/j1939/socket.c
@@ -974,6 +974,7 @@ static void __j1939_sk_errqueue(struct j1939_session *session, struct sock *sk,
 	struct sock_exterr_skb *serr;
 	struct sk_buff *skb;
 	char *state = "UNK";
+	u32 tsflags;
 	int err;
 
 	jsk = j1939_sk(sk);
@@ -981,13 +982,14 @@ static void __j1939_sk_errqueue(struct j1939_session *session, struct sock *sk,
 	if (!(jsk->state & J1939_SOCK_ERRQUEUE))
 		return;
 
+	tsflags = READ_ONCE(sk->sk_tsflags);
 	switch (type) {
 	case J1939_ERRQUEUE_TX_ACK:
-		if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_ACK))
+		if (!(tsflags & SOF_TIMESTAMPING_TX_ACK))
 			return;
 		break;
 	case J1939_ERRQUEUE_TX_SCHED:
-		if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_SCHED))
+		if (!(tsflags & SOF_TIMESTAMPING_TX_SCHED))
 			return;
 		break;
 	case J1939_ERRQUEUE_TX_ABORT:
@@ -997,7 +999,7 @@ static void __j1939_sk_errqueue(struct j1939_session *session, struct sock *sk,
 	case J1939_ERRQUEUE_RX_DPO:
 		fallthrough;
 	case J1939_ERRQUEUE_RX_ABORT:
-		if (!(sk->sk_tsflags & SOF_TIMESTAMPING_RX_SOFTWARE))
+		if (!(tsflags & SOF_TIMESTAMPING_RX_SOFTWARE))
 			return;
 		break;
 	default:
@@ -1054,7 +1056,7 @@ static void __j1939_sk_errqueue(struct j1939_session *session, struct sock *sk,
 	}
 
 	serr->opt_stats = true;
-	if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)
+	if (tsflags & SOF_TIMESTAMPING_OPT_ID)
 		serr->ee.ee_data = session->tskey;
 
 	netdev_dbg(session->priv->ndev, "%s: 0x%p tskey: %i, state: %s\n",
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 45707059082f..24f26e816184 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5207,7 +5207,7 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb,
 	serr->ee.ee_info = tstype;
 	serr->opt_stats = opt_stats;
 	serr->header.h4.iif = skb->dev ? skb->dev->ifindex : 0;
-	if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) {
+	if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) {
 		serr->ee.ee_data = skb_shinfo(skb)->tskey;
 		if (sk_is_tcp(sk))
 			serr->ee.ee_data -= atomic_read(&sk->sk_tskey);
@@ -5263,21 +5263,23 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
 {
 	struct sk_buff *skb;
 	bool tsonly, opt_stats = false;
+	u32 tsflags;
 
 	if (!sk)
 		return;
 
-	if (!hwtstamps && !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TX_SWHW) &&
+	tsflags = READ_ONCE(sk->sk_tsflags);
+	if (!hwtstamps && !(tsflags & SOF_TIMESTAMPING_OPT_TX_SWHW) &&
 	    skb_shinfo(orig_skb)->tx_flags & SKBTX_IN_PROGRESS)
 		return;
 
-	tsonly = sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TSONLY;
+	tsonly = tsflags & SOF_TIMESTAMPING_OPT_TSONLY;
 	if (!skb_may_tx_timestamp(sk, tsonly))
 		return;
 
 	if (tsonly) {
 #ifdef CONFIG_INET
-		if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS) &&
+		if ((tsflags & SOF_TIMESTAMPING_OPT_STATS) &&
 		    sk_is_tcp(sk)) {
 			skb = tcp_get_timestamping_opt_stats(sk, orig_skb,
 							     ack_skb);
diff --git a/net/core/sock.c b/net/core/sock.c
index 40e1bda4bde0..d05a290300b6 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -937,7 +937,7 @@ int sock_set_timestamping(struct sock *sk, int optname,
 			return ret;
 	}
 
-	sk->sk_tsflags = val;
+	WRITE_ONCE(sk->sk_tsflags, val);
 	sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW);
 
 	if (val & SOF_TIMESTAMPING_RX_SOFTWARE)
@@ -1719,7 +1719,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 
 	case SO_TIMESTAMPING_OLD:
 		lv = sizeof(v.timestamping);
-		v.timestamping.flags = sk->sk_tsflags;
+		v.timestamping.flags = READ_ONCE(sk->sk_tsflags);
 		v.timestamping.bind_phc = sk->sk_bind_phc;
 		break;
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index b2e0ad312028..4ab877cf6d35 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -981,7 +981,7 @@ static int __ip_append_data(struct sock *sk,
 	paged = !!cork->gso_size;
 
 	if (cork->tx_flags & SKBTX_ANY_TSTAMP &&
-	    sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)
+	    READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID)
 		tskey = atomic_inc_return(&sk->sk_tskey) - 1;
 
 	hh_len = LL_RESERVED_SPACE(rt->dst.dev);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index d1c73660b844..cce9cb25f3b3 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -511,7 +511,7 @@ static bool ipv4_datagram_support_cmsg(const struct sock *sk,
 	 * or without payload (SOF_TIMESTAMPING_OPT_TSONLY).
 	 */
 	info = PKTINFO_SKB_CB(skb);
-	if (!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG) ||
+	if (!(READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_CMSG) ||
 	    !info->ipi_ifindex)
 		return false;
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index cee1e548660c..cc4b250262c1 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2259,14 +2259,14 @@ void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
 			}
 		}
 
-		if (sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE)
+		if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_SOFTWARE)
 			has_timestamping = true;
 		else
 			tss->ts[0] = (struct timespec64) {0};
 	}
 
 	if (tss->ts[2].tv_sec || tss->ts[2].tv_nsec) {
-		if (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE)
+		if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_RAW_HARDWARE)
 			has_timestamping = true;
 		else
 			tss->ts[2] = (struct timespec64) {0};
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 4ab50169a5a9..54fc4c711f2c 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1501,7 +1501,7 @@ static int __ip6_append_data(struct sock *sk,
 	orig_mtu = mtu;
 
 	if (cork->tx_flags & SKBTX_ANY_TSTAMP &&
-	    sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)
+	    READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID)
 		tskey = atomic_inc_return(&sk->sk_tskey) - 1;
 
 	hh_len = LL_RESERVED_SPACE(rt->dst.dev);
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 1b2772834972..5831aaa53d75 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -119,7 +119,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		return -EINVAL;
 
 	ipcm6_init_sk(&ipc6, np);
-	ipc6.sockc.tsflags = sk->sk_tsflags;
+	ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags);
 	ipc6.sockc.mark = READ_ONCE(sk->sk_mark);
 
 	fl6.flowi6_oif = oif;
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 0eae7661a85c..42fcec3ecf5e 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -772,7 +772,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	fl6.flowi6_uid = sk->sk_uid;
 
 	ipcm6_init(&ipc6);
-	ipc6.sockc.tsflags = sk->sk_tsflags;
+	ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags);
 	ipc6.sockc.mark = fl6.flowi6_mark;
 
 	if (sin6) {
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index ebc6ae47cfea..86b5d509a468 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1339,7 +1339,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	ipcm6_init(&ipc6);
 	ipc6.gso_size = READ_ONCE(up->gso_size);
-	ipc6.sockc.tsflags = sk->sk_tsflags;
+	ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags);
 	ipc6.sockc.mark = READ_ONCE(sk->sk_mark);
 
 	/* destination address check */
diff --git a/net/socket.c b/net/socket.c
index 848116d06b51..98ffffab949e 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -825,7 +825,7 @@ static bool skb_is_swtx_tstamp(const struct sk_buff *skb, int false_tstamp)
 
 static ktime_t get_timestamp(struct sock *sk, struct sk_buff *skb, int *if_index)
 {
-	bool cycles = sk->sk_tsflags & SOF_TIMESTAMPING_BIND_PHC;
+	bool cycles = READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_BIND_PHC;
 	struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb);
 	struct net_device *orig_dev;
 	ktime_t hwtstamp;
@@ -877,12 +877,12 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 	int need_software_tstamp = sock_flag(sk, SOCK_RCVTSTAMP);
 	int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW);
 	struct scm_timestamping_internal tss;
-
 	int empty = 1, false_tstamp = 0;
 	struct skb_shared_hwtstamps *shhwtstamps =
 		skb_hwtstamps(skb);
 	int if_index;
 	ktime_t hwtstamp;
+	u32 tsflags;
 
 	/* Race occurred between timestamp enabling and packet
 	   receiving.  Fill in the current time for now. */
@@ -924,11 +924,12 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 	}
 
 	memset(&tss, 0, sizeof(tss));
-	if ((sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) &&
+	tsflags = READ_ONCE(sk->sk_tsflags);
+	if ((tsflags & SOF_TIMESTAMPING_SOFTWARE) &&
 	    ktime_to_timespec64_cond(skb->tstamp, tss.ts + 0))
 		empty = 0;
 	if (shhwtstamps &&
-	    (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) &&
+	    (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) &&
 	    !skb_is_swtx_tstamp(skb, false_tstamp)) {
 		if_index = 0;
 		if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_NETDEV)
@@ -936,14 +937,14 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 		else
 			hwtstamp = shhwtstamps->hwtstamp;
 
-		if (sk->sk_tsflags & SOF_TIMESTAMPING_BIND_PHC)
+		if (tsflags & SOF_TIMESTAMPING_BIND_PHC)
 			hwtstamp = ptp_convert_timestamp(&hwtstamp,
 							 sk->sk_bind_phc);
 
 		if (ktime_to_timespec64_cond(hwtstamp, tss.ts + 2)) {
 			empty = 0;
 
-			if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) &&
+			if ((tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) &&
 			    !skb_is_err_queue(skb))
 				put_ts_pktinfo(msg, skb, if_index);
 		}

From 251cd405a9e6e70b92fe5afbdd17fd5caf9d3266 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 31 Aug 2023 13:52:12 +0000
Subject: [PATCH 0945/1189] net: annotate data-races around sk->sk_bind_phc

sk->sk_bind_phc is read locklessly. Add corresponding annotations.

Fixes: d463126e23f1 ("net: sock: extend SO_TIMESTAMPING for PHC binding")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yangbo Lu <yangbo.lu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 4 ++--
 net/socket.c    | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index d05a290300b6..d3c7b53368d2 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -894,7 +894,7 @@ static int sock_timestamping_bind_phc(struct sock *sk, int phc_index)
 	if (!match)
 		return -EINVAL;
 
-	sk->sk_bind_phc = phc_index;
+	WRITE_ONCE(sk->sk_bind_phc, phc_index);
 
 	return 0;
 }
@@ -1720,7 +1720,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 	case SO_TIMESTAMPING_OLD:
 		lv = sizeof(v.timestamping);
 		v.timestamping.flags = READ_ONCE(sk->sk_tsflags);
-		v.timestamping.bind_phc = sk->sk_bind_phc;
+		v.timestamping.bind_phc = READ_ONCE(sk->sk_bind_phc);
 		break;
 
 	case SO_RCVTIMEO_OLD:
diff --git a/net/socket.c b/net/socket.c
index 98ffffab949e..928b05811cfd 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -939,7 +939,7 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 
 		if (tsflags & SOF_TIMESTAMPING_BIND_PHC)
 			hwtstamp = ptp_convert_timestamp(&hwtstamp,
-							 sk->sk_bind_phc);
+							 READ_ONCE(sk->sk_bind_phc));
 
 		if (ktime_to_timespec64_cond(hwtstamp, tss.ts + 2)) {
 			empty = 0;

From 2ea35288c83b3d501a88bc17f2df8f176b5cc96f Mon Sep 17 00:00:00 2001
From: Mohamed Khalfella <mkhalfella@purestorage.com>
Date: Thu, 31 Aug 2023 02:17:02 -0600
Subject: [PATCH 0946/1189] skbuff: skb_segment, Call zero copy functions
 before using skbuff frags

Commit bf5c25d60861 ("skbuff: in skb_segment, call zerocopy functions
once per nskb") added the call to zero copy functions in skb_segment().
The change introduced a bug in skb_segment() because skb_orphan_frags()
may possibly change the number of fragments or allocate new fragments
altogether leaving nrfrags and frag to point to the old values. This can
cause a panic with stacktrace like the one below.

[  193.894380] BUG: kernel NULL pointer dereference, address: 00000000000000bc
[  193.895273] CPU: 13 PID: 18164 Comm: vh-net-17428 Kdump: loaded Tainted: G           O      5.15.123+ #26
[  193.903919] RIP: 0010:skb_segment+0xb0e/0x12f0
[  194.021892] Call Trace:
[  194.027422]  <TASK>
[  194.072861]  tcp_gso_segment+0x107/0x540
[  194.082031]  inet_gso_segment+0x15c/0x3d0
[  194.090783]  skb_mac_gso_segment+0x9f/0x110
[  194.095016]  __skb_gso_segment+0xc1/0x190
[  194.103131]  netem_enqueue+0x290/0xb10 [sch_netem]
[  194.107071]  dev_qdisc_enqueue+0x16/0x70
[  194.110884]  __dev_queue_xmit+0x63b/0xb30
[  194.121670]  bond_start_xmit+0x159/0x380 [bonding]
[  194.128506]  dev_hard_start_xmit+0xc3/0x1e0
[  194.131787]  __dev_queue_xmit+0x8a0/0xb30
[  194.138225]  macvlan_start_xmit+0x4f/0x100 [macvlan]
[  194.141477]  dev_hard_start_xmit+0xc3/0x1e0
[  194.144622]  sch_direct_xmit+0xe3/0x280
[  194.147748]  __dev_queue_xmit+0x54a/0xb30
[  194.154131]  tap_get_user+0x2a8/0x9c0 [tap]
[  194.157358]  tap_sendmsg+0x52/0x8e0 [tap]
[  194.167049]  handle_tx_zerocopy+0x14e/0x4c0 [vhost_net]
[  194.173631]  handle_tx+0xcd/0xe0 [vhost_net]
[  194.176959]  vhost_worker+0x76/0xb0 [vhost]
[  194.183667]  kthread+0x118/0x140
[  194.190358]  ret_from_fork+0x1f/0x30
[  194.193670]  </TASK>

In this case calling skb_orphan_frags() updated nr_frags leaving nrfrags
local variable in skb_segment() stale. This resulted in the code hitting
i >= nrfrags prematurely and trying to move to next frag_skb using
list_skb pointer, which was NULL, and caused kernel panic. Move the call
to zero copy functions before using frags and nr_frags.

Fixes: bf5c25d60861 ("skbuff: in skb_segment, call zerocopy functions once per nskb")
Signed-off-by: Mohamed Khalfella <mkhalfella@purestorage.com>
Reported-by: Amit Goyal <agoyal@purestorage.com>
Cc: stable@vger.kernel.org
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 34 ++++++++++++++++++++--------------
 1 file changed, 20 insertions(+), 14 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 24f26e816184..17caf4ea67da 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4423,21 +4423,20 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 	struct sk_buff *segs = NULL;
 	struct sk_buff *tail = NULL;
 	struct sk_buff *list_skb = skb_shinfo(head_skb)->frag_list;
-	skb_frag_t *frag = skb_shinfo(head_skb)->frags;
 	unsigned int mss = skb_shinfo(head_skb)->gso_size;
 	unsigned int doffset = head_skb->data - skb_mac_header(head_skb);
-	struct sk_buff *frag_skb = head_skb;
 	unsigned int offset = doffset;
 	unsigned int tnl_hlen = skb_tnl_header_len(head_skb);
 	unsigned int partial_segs = 0;
 	unsigned int headroom;
 	unsigned int len = head_skb->len;
+	struct sk_buff *frag_skb;
+	skb_frag_t *frag;
 	__be16 proto;
 	bool csum, sg;
-	int nfrags = skb_shinfo(head_skb)->nr_frags;
 	int err = -ENOMEM;
 	int i = 0;
-	int pos;
+	int nfrags, pos;
 
 	if ((skb_shinfo(head_skb)->gso_type & SKB_GSO_DODGY) &&
 	    mss != GSO_BY_FRAGS && mss != skb_headlen(head_skb)) {
@@ -4514,6 +4513,13 @@ normal:
 	headroom = skb_headroom(head_skb);
 	pos = skb_headlen(head_skb);
 
+	if (skb_orphan_frags(head_skb, GFP_ATOMIC))
+		return ERR_PTR(-ENOMEM);
+
+	nfrags = skb_shinfo(head_skb)->nr_frags;
+	frag = skb_shinfo(head_skb)->frags;
+	frag_skb = head_skb;
+
 	do {
 		struct sk_buff *nskb;
 		skb_frag_t *nskb_frag;
@@ -4534,6 +4540,10 @@ normal:
 		    (skb_headlen(list_skb) == len || sg)) {
 			BUG_ON(skb_headlen(list_skb) > len);
 
+			nskb = skb_clone(list_skb, GFP_ATOMIC);
+			if (unlikely(!nskb))
+				goto err;
+
 			i = 0;
 			nfrags = skb_shinfo(list_skb)->nr_frags;
 			frag = skb_shinfo(list_skb)->frags;
@@ -4552,12 +4562,8 @@ normal:
 				frag++;
 			}
 
-			nskb = skb_clone(list_skb, GFP_ATOMIC);
 			list_skb = list_skb->next;
 
-			if (unlikely(!nskb))
-				goto err;
-
 			if (unlikely(pskb_trim(nskb, len))) {
 				kfree_skb(nskb);
 				goto err;
@@ -4633,12 +4639,16 @@ normal:
 		skb_shinfo(nskb)->flags |= skb_shinfo(head_skb)->flags &
 					   SKBFL_SHARED_FRAG;
 
-		if (skb_orphan_frags(frag_skb, GFP_ATOMIC) ||
-		    skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC))
+		if (skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC))
 			goto err;
 
 		while (pos < offset + len) {
 			if (i >= nfrags) {
+				if (skb_orphan_frags(list_skb, GFP_ATOMIC) ||
+				    skb_zerocopy_clone(nskb, list_skb,
+						       GFP_ATOMIC))
+					goto err;
+
 				i = 0;
 				nfrags = skb_shinfo(list_skb)->nr_frags;
 				frag = skb_shinfo(list_skb)->frags;
@@ -4652,10 +4662,6 @@ normal:
 					i--;
 					frag--;
 				}
-				if (skb_orphan_frags(frag_skb, GFP_ATOMIC) ||
-				    skb_zerocopy_clone(nskb, frag_skb,
-						       GFP_ATOMIC))
-					goto err;
 
 				list_skb = list_skb->next;
 			}

From 6ac66cb03ae306c2e288a9be18226310529f5b25 Mon Sep 17 00:00:00 2001
From: Sriram Yagnaraman <sriram.yagnaraman@est.tech>
Date: Thu, 31 Aug 2023 10:03:30 +0200
Subject: [PATCH 0947/1189] ipv4: ignore dst hint for multipath routes

Route hints when the nexthop is part of a multipath group causes packets
in the same receive batch to be sent to the same nexthop irrespective of
the multipath hash of the packet. So, do not extract route hint for
packets whose destination is part of a multipath group.

A new SKB flag IPSKB_MULTIPATH is introduced for this purpose, set the
flag when route is looked up in ip_mkroute_input() and use it in
ip_extract_route_hint() to check for the existence of the flag.

Fixes: 02b24941619f ("ipv4: use dst hint for ipv4 list receive")
Signed-off-by: Sriram Yagnaraman <sriram.yagnaraman@est.tech>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h    | 1 +
 net/ipv4/ip_input.c | 3 ++-
 net/ipv4/route.c    | 1 +
 3 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index 9276cea775cc..3489a1cca5e7 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -57,6 +57,7 @@ struct inet_skb_parm {
 #define IPSKB_FRAG_PMTU		BIT(6)
 #define IPSKB_L3SLAVE		BIT(7)
 #define IPSKB_NOPOLICY		BIT(8)
+#define IPSKB_MULTIPATH		BIT(9)
 
 	u16			frag_max_size;
 };
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index fe9ead9ee863..5e9c8156656a 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -584,7 +584,8 @@ static void ip_sublist_rcv_finish(struct list_head *head)
 static struct sk_buff *ip_extract_route_hint(const struct net *net,
 					     struct sk_buff *skb, int rt_type)
 {
-	if (fib4_has_custom_rules(net) || rt_type == RTN_BROADCAST)
+	if (fib4_has_custom_rules(net) || rt_type == RTN_BROADCAST ||
+	    IPCB(skb)->flags & IPSKB_MULTIPATH)
 		return NULL;
 
 	return skb;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index a4e153dd615b..6a3f57a3fa41 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2144,6 +2144,7 @@ static int ip_mkroute_input(struct sk_buff *skb,
 		int h = fib_multipath_hash(res->fi->fib_net, NULL, skb, hkeys);
 
 		fib_select_multipath(res, h);
+		IPCB(skb)->flags |= IPSKB_MULTIPATH;
 	}
 #endif
 

From 8423be8926aa82cd2e28bba5cc96ccb72c7ce6be Mon Sep 17 00:00:00 2001
From: Sriram Yagnaraman <sriram.yagnaraman@est.tech>
Date: Thu, 31 Aug 2023 10:03:31 +0200
Subject: [PATCH 0948/1189] ipv6: ignore dst hint for multipath routes

Route hints when the nexthop is part of a multipath group causes packets
in the same receive batch to be sent to the same nexthop irrespective of
the multipath hash of the packet. So, do not extract route hint for
packets whose destination is part of a multipath group.

A new SKB flag IP6SKB_MULTIPATH is introduced for this purpose, set the
flag when route is looked up in fib6_select_path() and use it in
ip6_can_use_hint() to check for the existence of the flag.

Fixes: 197dbf24e360 ("ipv6: introduce and uses route look hints for list input.")
Signed-off-by: Sriram Yagnaraman <sriram.yagnaraman@est.tech>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h | 1 +
 net/ipv6/ip6_input.c | 3 ++-
 net/ipv6/route.c     | 3 +++
 3 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 5883551b1ee8..af8a771a053c 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -147,6 +147,7 @@ struct inet6_skb_parm {
 #define IP6SKB_JUMBOGRAM      128
 #define IP6SKB_SEG6	      256
 #define IP6SKB_FAKEJUMBO      512
+#define IP6SKB_MULTIPATH      1024
 };
 
 #if defined(CONFIG_NET_L3_MASTER_DEV)
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index d94041bb4287..b8378814532c 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -99,7 +99,8 @@ static bool ip6_can_use_hint(const struct sk_buff *skb,
 static struct sk_buff *ip6_extract_route_hint(const struct net *net,
 					      struct sk_buff *skb)
 {
-	if (fib6_routes_require_src(net) || fib6_has_custom_rules(net))
+	if (fib6_routes_require_src(net) || fib6_has_custom_rules(net) ||
+	    IP6CB(skb)->flags & IP6SKB_MULTIPATH)
 		return NULL;
 
 	return skb;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 846aec8e0093..01d6d352850a 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -423,6 +423,9 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
 	if (match->nh && have_oif_match && res->nh)
 		return;
 
+	if (skb)
+		IP6CB(skb)->flags |= IP6SKB_MULTIPATH;
+
 	/* We might have already computed the hash for ICMPv6 errors. In such
 	 * case it will always be non-zero. Otherwise now is the time to do it.
 	 */

From 8ae9efb859c05a54ac92b3336c6ca0597c9c8cdb Mon Sep 17 00:00:00 2001
From: Sriram Yagnaraman <sriram.yagnaraman@est.tech>
Date: Thu, 31 Aug 2023 10:03:32 +0200
Subject: [PATCH 0949/1189] selftests: fib_tests: Add multipath list receive
 tests

The test uses perf stat to count the number of fib:fib_table_lookup
tracepoint hits for IPv4 and the number of fib6:fib6_table_lookup for
IPv6. The measured count is checked to be within 5% of the total number
of packets sent via veth1.

Signed-off-by: Sriram Yagnaraman <sriram.yagnaraman@est.tech>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/fib_tests.sh | 155 ++++++++++++++++++++++-
 1 file changed, 154 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index d328af4a149c..e7d2a530618a 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -12,7 +12,8 @@ ksft_skip=4
 TESTS="unregister down carrier nexthop suppress ipv6_notify ipv4_notify \
        ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics \
        ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr \
-       ipv6_del_addr ipv4_mangle ipv6_mangle ipv4_bcast_neigh fib6_gc_test"
+       ipv6_del_addr ipv4_mangle ipv6_mangle ipv4_bcast_neigh fib6_gc_test \
+       ipv4_mpath_list ipv6_mpath_list"
 
 VERBOSE=0
 PAUSE_ON_FAIL=no
@@ -2352,6 +2353,156 @@ ipv4_bcast_neigh_test()
 	cleanup
 }
 
+mpath_dep_check()
+{
+	if [ ! -x "$(command -v mausezahn)" ]; then
+		echo "mausezahn command not found. Skipping test"
+		return 1
+	fi
+
+	if [ ! -x "$(command -v jq)" ]; then
+		echo "jq command not found. Skipping test"
+		return 1
+	fi
+
+	if [ ! -x "$(command -v bc)" ]; then
+		echo "bc command not found. Skipping test"
+		return 1
+	fi
+
+	if [ ! -x "$(command -v perf)" ]; then
+		echo "perf command not found. Skipping test"
+		return 1
+	fi
+
+	perf list fib:* | grep -q fib_table_lookup
+	if [ $? -ne 0 ]; then
+		echo "IPv4 FIB tracepoint not found. Skipping test"
+		return 1
+	fi
+
+	perf list fib6:* | grep -q fib6_table_lookup
+	if [ $? -ne 0 ]; then
+		echo "IPv6 FIB tracepoint not found. Skipping test"
+		return 1
+	fi
+
+	return 0
+}
+
+link_stats_get()
+{
+	local ns=$1; shift
+	local dev=$1; shift
+	local dir=$1; shift
+	local stat=$1; shift
+
+	ip -n $ns -j -s link show dev $dev \
+		| jq '.[]["stats64"]["'$dir'"]["'$stat'"]'
+}
+
+list_rcv_eval()
+{
+	local file=$1; shift
+	local expected=$1; shift
+
+	local count=$(tail -n 1 $file | jq '.["counter-value"] | tonumber | floor')
+	local ratio=$(echo "scale=2; $count / $expected" | bc -l)
+	local res=$(echo "$ratio >= 0.95" | bc)
+	[[ $res -eq 1 ]]
+	log_test $? 0 "Multipath route hit ratio ($ratio)"
+}
+
+ipv4_mpath_list_test()
+{
+	echo
+	echo "IPv4 multipath list receive tests"
+
+	mpath_dep_check || return 1
+
+	route_setup
+
+	set -e
+	run_cmd "ip netns exec ns1 ethtool -K veth1 tcp-segmentation-offload off"
+
+	run_cmd "ip netns exec ns2 bash -c \"echo 20000 > /sys/class/net/veth2/gro_flush_timeout\""
+	run_cmd "ip netns exec ns2 bash -c \"echo 1 > /sys/class/net/veth2/napi_defer_hard_irqs\""
+	run_cmd "ip netns exec ns2 ethtool -K veth2 generic-receive-offload on"
+	run_cmd "ip -n ns2 link add name nh1 up type dummy"
+	run_cmd "ip -n ns2 link add name nh2 up type dummy"
+	run_cmd "ip -n ns2 address add 172.16.201.1/24 dev nh1"
+	run_cmd "ip -n ns2 address add 172.16.202.1/24 dev nh2"
+	run_cmd "ip -n ns2 neigh add 172.16.201.2 lladdr 00:11:22:33:44:55 nud perm dev nh1"
+	run_cmd "ip -n ns2 neigh add 172.16.202.2 lladdr 00:aa:bb:cc:dd:ee nud perm dev nh2"
+	run_cmd "ip -n ns2 route add 203.0.113.0/24
+		nexthop via 172.16.201.2 nexthop via 172.16.202.2"
+	run_cmd "ip netns exec ns2 sysctl -qw net.ipv4.fib_multipath_hash_policy=1"
+	set +e
+
+	local dmac=$(ip -n ns2 -j link show dev veth2 | jq -r '.[]["address"]')
+	local tmp_file=$(mktemp)
+	local cmd="ip netns exec ns1 mausezahn veth1 -a own -b $dmac
+		-A 172.16.101.1 -B 203.0.113.1 -t udp 'sp=12345,dp=0-65535' -q"
+
+	# Packets forwarded in a list using a multipath route must not reuse a
+	# cached result so that a flow always hits the same nexthop. In other
+	# words, the FIB lookup tracepoint needs to be triggered for every
+	# packet.
+	local t0_rx_pkts=$(link_stats_get ns2 veth2 rx packets)
+	run_cmd "perf stat -e fib:fib_table_lookup --filter 'err == 0' -j -o $tmp_file -- $cmd"
+	local t1_rx_pkts=$(link_stats_get ns2 veth2 rx packets)
+	local diff=$(echo $t1_rx_pkts - $t0_rx_pkts | bc -l)
+	list_rcv_eval $tmp_file $diff
+
+	rm $tmp_file
+	route_cleanup
+}
+
+ipv6_mpath_list_test()
+{
+	echo
+	echo "IPv6 multipath list receive tests"
+
+	mpath_dep_check || return 1
+
+	route_setup
+
+	set -e
+	run_cmd "ip netns exec ns1 ethtool -K veth1 tcp-segmentation-offload off"
+
+	run_cmd "ip netns exec ns2 bash -c \"echo 20000 > /sys/class/net/veth2/gro_flush_timeout\""
+	run_cmd "ip netns exec ns2 bash -c \"echo 1 > /sys/class/net/veth2/napi_defer_hard_irqs\""
+	run_cmd "ip netns exec ns2 ethtool -K veth2 generic-receive-offload on"
+	run_cmd "ip -n ns2 link add name nh1 up type dummy"
+	run_cmd "ip -n ns2 link add name nh2 up type dummy"
+	run_cmd "ip -n ns2 -6 address add 2001:db8:201::1/64 dev nh1"
+	run_cmd "ip -n ns2 -6 address add 2001:db8:202::1/64 dev nh2"
+	run_cmd "ip -n ns2 -6 neigh add 2001:db8:201::2 lladdr 00:11:22:33:44:55 nud perm dev nh1"
+	run_cmd "ip -n ns2 -6 neigh add 2001:db8:202::2 lladdr 00:aa:bb:cc:dd:ee nud perm dev nh2"
+	run_cmd "ip -n ns2 -6 route add 2001:db8:301::/64
+		nexthop via 2001:db8:201::2 nexthop via 2001:db8:202::2"
+	run_cmd "ip netns exec ns2 sysctl -qw net.ipv6.fib_multipath_hash_policy=1"
+	set +e
+
+	local dmac=$(ip -n ns2 -j link show dev veth2 | jq -r '.[]["address"]')
+	local tmp_file=$(mktemp)
+	local cmd="ip netns exec ns1 mausezahn -6 veth1 -a own -b $dmac
+		-A 2001:db8:101::1 -B 2001:db8:301::1 -t udp 'sp=12345,dp=0-65535' -q"
+
+	# Packets forwarded in a list using a multipath route must not reuse a
+	# cached result so that a flow always hits the same nexthop. In other
+	# words, the FIB lookup tracepoint needs to be triggered for every
+	# packet.
+	local t0_rx_pkts=$(link_stats_get ns2 veth2 rx packets)
+	run_cmd "perf stat -e fib6:fib6_table_lookup --filter 'err == 0' -j -o $tmp_file -- $cmd"
+	local t1_rx_pkts=$(link_stats_get ns2 veth2 rx packets)
+	local diff=$(echo $t1_rx_pkts - $t0_rx_pkts | bc -l)
+	list_rcv_eval $tmp_file $diff
+
+	rm $tmp_file
+	route_cleanup
+}
+
 ################################################################################
 # usage
 
@@ -2433,6 +2584,8 @@ do
 	ipv6_mangle)			ipv6_mangle_test;;
 	ipv4_bcast_neigh)		ipv4_bcast_neigh_test;;
 	fib6_gc_test|ipv6_gc)		fib6_gc_test;;
+	ipv4_mpath_list)		ipv4_mpath_list_test;;
+	ipv6_mpath_list)		ipv6_mpath_list_test;;
 
 	help) echo "Test names: $TESTS"; exit 0;;
 	esac

From ae074e2b2fd410bf54d56509a7e48fb83873af3b Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree.xilinx@gmail.com>
Date: Thu, 31 Aug 2023 17:58:11 +0100
Subject: [PATCH 0950/1189] sfc: check for zero length in EF10 RX prefix

When EF10 RXDP firmware is operating in cut-through mode, packet length
 is not known at the time the RX prefix is generated, so it is left as
 zero and RX event merging is inhibited to ensure that the length is
 available in the RX event.  However, it has been found that in certain
 circumstances the RX events for these packets still get merged,
 meaning the driver cannot read the length from the RX event, and tries
 to use the length from the prefix.
The resulting zero-length SKBs cause crashes in GRO since commit
 1d11fa696733 ("net-gro: remove GRO_DROP"), so add a check to the driver
 to detect these zero-length RX events and discard the packet.

Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/rx.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index 2375cef577e4..f77a2d3ef37e 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -359,26 +359,36 @@ static bool efx_do_xdp(struct efx_nic *efx, struct efx_channel *channel,
 /* Handle a received packet.  Second half: Touches packet payload. */
 void __efx_rx_packet(struct efx_channel *channel)
 {
+	struct efx_rx_queue *rx_queue = efx_channel_get_rx_queue(channel);
 	struct efx_nic *efx = channel->efx;
 	struct efx_rx_buffer *rx_buf =
-		efx_rx_buffer(&channel->rx_queue, channel->rx_pkt_index);
+		efx_rx_buffer(rx_queue, channel->rx_pkt_index);
 	u8 *eh = efx_rx_buf_va(rx_buf);
 
 	/* Read length from the prefix if necessary.  This already
 	 * excludes the length of the prefix itself.
 	 */
-	if (rx_buf->flags & EFX_RX_PKT_PREFIX_LEN)
+	if (rx_buf->flags & EFX_RX_PKT_PREFIX_LEN) {
 		rx_buf->len = le16_to_cpup((__le16 *)
 					   (eh + efx->rx_packet_len_offset));
+		/* A known issue may prevent this being filled in;
+		 * if that happens, just drop the packet.
+		 * Must do that in the driver since passing a zero-length
+		 * packet up to the stack may cause a crash.
+		 */
+		if (unlikely(!rx_buf->len)) {
+			efx_free_rx_buffers(rx_queue, rx_buf,
+					    channel->rx_pkt_n_frags);
+			channel->n_rx_frm_trunc++;
+			goto out;
+		}
+	}
 
 	/* If we're in loopback test, then pass the packet directly to the
 	 * loopback layer, and free the rx_buf here
 	 */
 	if (unlikely(efx->loopback_selftest)) {
-		struct efx_rx_queue *rx_queue;
-
 		efx_loopback_rx_packet(efx, eh, rx_buf->len);
-		rx_queue = efx_channel_get_rx_queue(channel);
 		efx_free_rx_buffers(rx_queue, rx_buf,
 				    channel->rx_pkt_n_frags);
 		goto out;

From c1970e26bdc1209974bb5cf31cc23f2b7ad6ce50 Mon Sep 17 00:00:00 2001
From: Xu Kuohai <xukuohai@huawei.com>
Date: Fri, 1 Sep 2023 11:10:37 +0800
Subject: [PATCH 0951/1189] selftests/bpf: Fix a CI failure caused by vsock
 write

While commit 90f0074cd9f9 ("selftests/bpf: fix a CI failure caused by vsock sockmap test")
fixes a receive failure of vsock sockmap test, there is still a write failure:

Error: #211/79 sockmap_listen/sockmap VSOCK test_vsock_redir
Error: #211/79 sockmap_listen/sockmap VSOCK test_vsock_redir
  ./test_progs:vsock_unix_redir_connectible:1501: egress: write: Transport endpoint is not connected
  vsock_unix_redir_connectible:FAIL:1501
  ./test_progs:vsock_unix_redir_connectible:1501: ingress: write: Transport endpoint is not connected
  vsock_unix_redir_connectible:FAIL:1501
  ./test_progs:vsock_unix_redir_connectible:1501: egress: write: Transport endpoint is not connected
  vsock_unix_redir_connectible:FAIL:1501

The reason is that the vsock connection in the test is set to ESTABLISHED state
by function virtio_transport_recv_pkt, which is executed in a workqueue thread,
so when the user space test thread runs before the workqueue thread, this
problem occurs.

To fix it, before writing the connection, wait for it to be connected.

Fixes: d61bd8c1fd02 ("selftests/bpf: add a test case for vsock sockmap")
Signed-off-by: Xu Kuohai <xukuohai@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20230901031037.3314007-1-xukuohai@huaweicloud.com
---
 .../bpf/prog_tests/sockmap_helpers.h          | 26 +++++++++++++++++++
 .../selftests/bpf/prog_tests/sockmap_listen.c |  7 +++++
 2 files changed, 33 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
index d12665490a90..36d829a65aa4 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
@@ -179,6 +179,32 @@
 		__ret;                                                         \
 	})
 
+static inline int poll_connect(int fd, unsigned int timeout_sec)
+{
+	struct timeval timeout = { .tv_sec = timeout_sec };
+	fd_set wfds;
+	int r, eval;
+	socklen_t esize = sizeof(eval);
+
+	FD_ZERO(&wfds);
+	FD_SET(fd, &wfds);
+
+	r = select(fd + 1, NULL, &wfds, NULL, &timeout);
+	if (r == 0)
+		errno = ETIME;
+	if (r != 1)
+		return -1;
+
+	if (getsockopt(fd, SOL_SOCKET, SO_ERROR, &eval, &esize) < 0)
+		return -1;
+	if (eval != 0) {
+		errno = eval;
+		return -1;
+	}
+
+	return 0;
+}
+
 static inline int poll_read(int fd, unsigned int timeout_sec)
 {
 	struct timeval timeout = { .tv_sec = timeout_sec };
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index 5674a9d0cacf..8df8cbb447f1 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -1452,11 +1452,18 @@ static int vsock_socketpair_connectible(int sotype, int *v0, int *v1)
 	if (p < 0)
 		goto close_cli;
 
+	if (poll_connect(c, IO_TIMEOUT_SEC) < 0) {
+		FAIL_ERRNO("poll_connect");
+		goto close_acc;
+	}
+
 	*v0 = p;
 	*v1 = c;
 
 	return 0;
 
+close_acc:
+	close(p);
 close_cli:
 	close(c);
 close_srv:

From 69d0fd348d31977368defc3c0737c0ecb824732b Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 31 Aug 2023 15:04:56 +0200
Subject: [PATCH 0952/1189] ASoC: dmaengine: Drop unused iov_iter for process
 callback

Passing the iov_iter to the process callback is rather buggy, as the
iterator has been already processed for playback.  Similarly, it makes
the copy for capture buggy after the process callback reading the
iterator out.  Moreover, all existing process callbacks don't refer to
the passed iterator at all.  So, it's better to drop the argument from
the process callback.

Fixes: 9bebd65443c1 ("ASoC: dmaengine: Use iov_iter for process callback, too")
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/CAHk-=wje+VkXjjfVTmK-uJdG_M5=ar14QxAwK+XDiq07k_pzBg@mail.gmail.com
Reviewed-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20230831130457.8180-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/dmaengine_pcm.h         | 2 +-
 sound/soc/atmel/mchp-pdmc.c           | 2 +-
 sound/soc/soc-generic-dmaengine-pcm.c | 4 ++--
 sound/soc/stm/stm32_sai_sub.c         | 2 +-
 4 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/include/sound/dmaengine_pcm.h b/include/sound/dmaengine_pcm.h
index c9a8bce9a785..d70c55f17df7 100644
--- a/include/sound/dmaengine_pcm.h
+++ b/include/sound/dmaengine_pcm.h
@@ -142,7 +142,7 @@ struct snd_dmaengine_pcm_config {
 			struct snd_pcm_substream *substream);
 	int (*process)(struct snd_pcm_substream *substream,
 		       int channel, unsigned long hwoff,
-		       struct iov_iter *buf, unsigned long bytes);
+		       unsigned long bytes);
 	dma_filter_fn compat_filter_fn;
 	struct device *dma_dev;
 	const char *chan_names[SNDRV_PCM_STREAM_LAST + 1];
diff --git a/sound/soc/atmel/mchp-pdmc.c b/sound/soc/atmel/mchp-pdmc.c
index afe213a71212..dcc4e14b3dde 100644
--- a/sound/soc/atmel/mchp-pdmc.c
+++ b/sound/soc/atmel/mchp-pdmc.c
@@ -954,7 +954,7 @@ static int mchp_pdmc_dt_init(struct mchp_pdmc *dd)
 /* used to clean the channel index found on RHR's MSB */
 static int mchp_pdmc_process(struct snd_pcm_substream *substream,
 			     int channel, unsigned long hwoff,
-			     struct iov_iter *buf, unsigned long bytes)
+			     unsigned long bytes)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	u8 *dma_ptr = runtime->dma_area + hwoff +
diff --git a/sound/soc/soc-generic-dmaengine-pcm.c b/sound/soc/soc-generic-dmaengine-pcm.c
index ff2166525dbc..7a07fbf98e2e 100644
--- a/sound/soc/soc-generic-dmaengine-pcm.c
+++ b/sound/soc/soc-generic-dmaengine-pcm.c
@@ -296,7 +296,7 @@ static int dmaengine_copy(struct snd_soc_component *component,
 	struct dmaengine_pcm *pcm = soc_component_to_pcm(component);
 	int (*process)(struct snd_pcm_substream *substream,
 		       int channel, unsigned long hwoff,
-		       struct iov_iter *buf, unsigned long bytes) = pcm->config->process;
+		       unsigned long bytes) = pcm->config->process;
 	bool is_playback = substream->stream == SNDRV_PCM_STREAM_PLAYBACK;
 	void *dma_ptr = runtime->dma_area + hwoff +
 			channel * (runtime->dma_bytes / runtime->channels);
@@ -306,7 +306,7 @@ static int dmaengine_copy(struct snd_soc_component *component,
 			return -EFAULT;
 
 	if (process) {
-		int ret = process(substream, channel, hwoff, buf, bytes);
+		int ret = process(substream, channel, hwoff, bytes);
 		if (ret < 0)
 			return ret;
 	}
diff --git a/sound/soc/stm/stm32_sai_sub.c b/sound/soc/stm/stm32_sai_sub.c
index f9b5d5969155..0acc848c1f00 100644
--- a/sound/soc/stm/stm32_sai_sub.c
+++ b/sound/soc/stm/stm32_sai_sub.c
@@ -1246,7 +1246,7 @@ static const struct snd_soc_dai_ops stm32_sai_pcm_dai_ops2 = {
 
 static int stm32_sai_pcm_process_spdif(struct snd_pcm_substream *substream,
 				       int channel, unsigned long hwoff,
-				       struct iov_iter *buf, unsigned long bytes)
+				       unsigned long bytes)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream);

From ef98a4883298bc2ead30ade6b6a10c4ac4bc07c8 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 31 Aug 2023 15:04:57 +0200
Subject: [PATCH 0953/1189] ASoC: Name iov_iter argument as iterator instead of
 buffer

While transitioning ASoC code for iov_iter usages, I kept the argument
name as "buf" as the original code.  But, iov_iter is an iterator, and
using the name "buf" may be misleading: the crucial difference is that
iov_iter can be proceeded after the operation, hence it can't be
passed twice, while a simple "buffer" sounds as if reusable.

To make the usage clearer, rename the argument from "buf" to "iter".
There is no functional changes, just names.

Fixes: 66201cacc33d ("ASoC: component: Add generic PCM copy ops")
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/CAHk-=wje+VkXjjfVTmK-uJdG_M5=ar14QxAwK+XDiq07k_pzBg@mail.gmail.com
Reviewed-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20230831130457.8180-2-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/soc-component.h         | 4 ++--
 sound/soc/soc-component.c             | 4 ++--
 sound/soc/soc-generic-dmaengine-pcm.c | 6 +++---
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/include/sound/soc-component.h b/include/sound/soc-component.h
index 17bea3144551..ceca69b46a82 100644
--- a/include/sound/soc-component.h
+++ b/include/sound/soc-component.h
@@ -139,7 +139,7 @@ struct snd_soc_component_driver {
 		struct snd_pcm_audio_tstamp_report *audio_tstamp_report);
 	int (*copy)(struct snd_soc_component *component,
 		    struct snd_pcm_substream *substream, int channel,
-		    unsigned long pos, struct iov_iter *buf,
+		    unsigned long pos, struct iov_iter *iter,
 		    unsigned long bytes);
 	struct page *(*page)(struct snd_soc_component *component,
 			     struct snd_pcm_substream *substream,
@@ -511,7 +511,7 @@ int snd_soc_pcm_component_ioctl(struct snd_pcm_substream *substream,
 int snd_soc_pcm_component_sync_stop(struct snd_pcm_substream *substream);
 int snd_soc_pcm_component_copy(struct snd_pcm_substream *substream,
 			       int channel, unsigned long pos,
-			       struct iov_iter *buf, unsigned long bytes);
+			       struct iov_iter *iter, unsigned long bytes);
 struct page *snd_soc_pcm_component_page(struct snd_pcm_substream *substream,
 					unsigned long offset);
 int snd_soc_pcm_component_mmap(struct snd_pcm_substream *substream,
diff --git a/sound/soc/soc-component.c b/sound/soc/soc-component.c
index f18406dfa1e4..ba7c0ae82e00 100644
--- a/sound/soc/soc-component.c
+++ b/sound/soc/soc-component.c
@@ -1054,7 +1054,7 @@ int snd_soc_pcm_component_sync_stop(struct snd_pcm_substream *substream)
 
 int snd_soc_pcm_component_copy(struct snd_pcm_substream *substream,
 			       int channel, unsigned long pos,
-			       struct iov_iter *buf, unsigned long bytes)
+			       struct iov_iter *iter, unsigned long bytes)
 {
 	struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream);
 	struct snd_soc_component *component;
@@ -1065,7 +1065,7 @@ int snd_soc_pcm_component_copy(struct snd_pcm_substream *substream,
 		if (component->driver->copy)
 			return soc_component_ret(component,
 				component->driver->copy(component, substream,
-					channel, pos, buf, bytes));
+					channel, pos, iter, bytes));
 
 	return -EINVAL;
 }
diff --git a/sound/soc/soc-generic-dmaengine-pcm.c b/sound/soc/soc-generic-dmaengine-pcm.c
index 7a07fbf98e2e..d0653d775c87 100644
--- a/sound/soc/soc-generic-dmaengine-pcm.c
+++ b/sound/soc/soc-generic-dmaengine-pcm.c
@@ -290,7 +290,7 @@ static snd_pcm_uframes_t dmaengine_pcm_pointer(
 static int dmaengine_copy(struct snd_soc_component *component,
 			  struct snd_pcm_substream *substream,
 			  int channel, unsigned long hwoff,
-			  struct iov_iter *buf, unsigned long bytes)
+			  struct iov_iter *iter, unsigned long bytes)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct dmaengine_pcm *pcm = soc_component_to_pcm(component);
@@ -302,7 +302,7 @@ static int dmaengine_copy(struct snd_soc_component *component,
 			channel * (runtime->dma_bytes / runtime->channels);
 
 	if (is_playback)
-		if (copy_from_iter(dma_ptr, bytes, buf) != bytes)
+		if (copy_from_iter(dma_ptr, bytes, iter) != bytes)
 			return -EFAULT;
 
 	if (process) {
@@ -312,7 +312,7 @@ static int dmaengine_copy(struct snd_soc_component *component,
 	}
 
 	if (!is_playback)
-		if (copy_to_iter(dma_ptr, bytes, buf) != bytes)
+		if (copy_to_iter(dma_ptr, bytes, iter) != bytes)
 			return -EFAULT;
 
 	return 0;

From f7cf22424665043787a96a66a048ff6b2cfd473c Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Mon, 28 Aug 2023 17:31:42 +0200
Subject: [PATCH 0954/1189] s390/dasd: fix string length handling

Building dasd_eckd.o with latest clang reveals this bug:

    CC      drivers/s390/block/dasd_eckd.o
      drivers/s390/block/dasd_eckd.c:1082:3: warning: 'snprintf' will always be truncated;
      specified size is 1, but format string expands to at least 11 [-Wfortify-source]
       1082 |                 snprintf(print_uid, sizeof(*print_uid),
            |                 ^
      drivers/s390/block/dasd_eckd.c:1087:3: warning: 'snprintf' will always be truncated;
      specified size is 1, but format string expands to at least 10 [-Wfortify-source]
       1087 |                 snprintf(print_uid, sizeof(*print_uid),
            |                 ^

Fix this by moving and using the existing UID_STRLEN for the arrays
that are being written to. Also rename UID_STRLEN to DASD_UID_STRLEN
to clarify its scope.

Fixes: 23596961b437 ("s390/dasd: split up dasd_eckd_read_conf")
Reviewed-by: Peter Oberparleiter <oberpar@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Tested-by: Nick Desaulniers <ndesaulniers@google.com> # build
Reported-by: Nathan Chancellor <nathan@kernel.org>
Closes: https://github.com/ClangBuiltLinux/linux/issues/1923
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Link: https://lore.kernel.org/r/20230828153142.2843753-2-hca@linux.ibm.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/s390/block/dasd_devmap.c |  6 +-----
 drivers/s390/block/dasd_eckd.c   | 10 +++++-----
 drivers/s390/block/dasd_int.h    |  4 ++++
 3 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c
index 620fab01b710..c4e36650c426 100644
--- a/drivers/s390/block/dasd_devmap.c
+++ b/drivers/s390/block/dasd_devmap.c
@@ -1378,16 +1378,12 @@ static ssize_t dasd_vendor_show(struct device *dev,
 
 static DEVICE_ATTR(vendor, 0444, dasd_vendor_show, NULL);
 
-#define UID_STRLEN ( /* vendor */ 3 + 1 + /* serial    */ 14 + 1 +\
-		     /* SSID   */ 4 + 1 + /* unit addr */ 2 + 1 +\
-		     /* vduit */ 32 + 1)
-
 static ssize_t
 dasd_uid_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
+	char uid_string[DASD_UID_STRLEN];
 	struct dasd_device *device;
 	struct dasd_uid uid;
-	char uid_string[UID_STRLEN];
 	char ua_string[3];
 
 	device = dasd_device_from_cdev(to_ccwdev(dev));
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index 8587e423169e..bd89b032968a 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -1079,12 +1079,12 @@ static void dasd_eckd_get_uid_string(struct dasd_conf *conf,
 
 	create_uid(conf, &uid);
 	if (strlen(uid.vduit) > 0)
-		snprintf(print_uid, sizeof(*print_uid),
+		snprintf(print_uid, DASD_UID_STRLEN,
 			 "%s.%s.%04x.%02x.%s",
 			 uid.vendor, uid.serial, uid.ssid,
 			 uid.real_unit_addr, uid.vduit);
 	else
-		snprintf(print_uid, sizeof(*print_uid),
+		snprintf(print_uid, DASD_UID_STRLEN,
 			 "%s.%s.%04x.%02x",
 			 uid.vendor, uid.serial, uid.ssid,
 			 uid.real_unit_addr);
@@ -1093,8 +1093,8 @@ static void dasd_eckd_get_uid_string(struct dasd_conf *conf,
 static int dasd_eckd_check_cabling(struct dasd_device *device,
 				   void *conf_data, __u8 lpm)
 {
+	char print_path_uid[DASD_UID_STRLEN], print_device_uid[DASD_UID_STRLEN];
 	struct dasd_eckd_private *private = device->private;
-	char print_path_uid[60], print_device_uid[60];
 	struct dasd_conf path_conf;
 
 	path_conf.data = conf_data;
@@ -1293,9 +1293,9 @@ static void dasd_eckd_path_available_action(struct dasd_device *device,
 	__u8 path_rcd_buf[DASD_ECKD_RCD_DATA_SIZE];
 	__u8 lpm, opm, npm, ppm, epm, hpfpm, cablepm;
 	struct dasd_conf_data *conf_data;
+	char print_uid[DASD_UID_STRLEN];
 	struct dasd_conf path_conf;
 	unsigned long flags;
-	char print_uid[60];
 	int rc, pos;
 
 	opm = 0;
@@ -5855,8 +5855,8 @@ static void dasd_eckd_dump_sense(struct dasd_device *device,
 static int dasd_eckd_reload_device(struct dasd_device *device)
 {
 	struct dasd_eckd_private *private = device->private;
+	char print_uid[DASD_UID_STRLEN];
 	int rc, old_base;
-	char print_uid[60];
 	struct dasd_uid uid;
 	unsigned long flags;
 
diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h
index 0aa56351da72..8a4dbe9d7741 100644
--- a/drivers/s390/block/dasd_int.h
+++ b/drivers/s390/block/dasd_int.h
@@ -259,6 +259,10 @@ struct dasd_uid {
 	char vduit[33];
 };
 
+#define DASD_UID_STRLEN ( /* vendor */ 3 + 1 + /* serial    */ 14 + 1 +	\
+			  /* SSID   */ 4 + 1 + /* unit addr */ 2 + 1 +	\
+			  /* vduit */ 32 + 1)
+
 /*
  * PPRC Status data
  */

From b484a40dc1f16edb58e5430105a021e1916e6f27 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Fri, 1 Sep 2023 21:49:16 +0800
Subject: [PATCH 0955/1189] io_uring: fix IO hang in io_wq_put_and_exit from
 do_exit()

io_wq_put_and_exit() is called from do_exit(), but all FIXED_FILE requests
in io_wq aren't canceled in io_uring_cancel_generic() called from do_exit().
Meantime io_wq IO code path may share resource with normal iopoll code
path.

So if any HIPRI request is submittd via io_wq, this request may not get resouce
for moving on, given iopoll isn't possible in io_wq_put_and_exit().

The issue can be triggered when terminating 't/io_uring -n4 /dev/nullb0'
with default null_blk parameters.

Fix it by always cancelling all requests in io_wq by adding helper of
io_uring_cancel_wq(), and this way is reasonable because io_wq destroying
follows canceling requests immediately.

Closes: https://lore.kernel.org/linux-block/3893581.1691785261@warthog.procyon.org.uk/
Reported-by: David Howells <dhowells@redhat.com>
Cc: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20230901134916.2415386-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/io_uring.c | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index e7675355048d..c6d9e4677073 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -3290,6 +3290,37 @@ static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked)
 	return percpu_counter_sum(&tctx->inflight);
 }
 
+static void io_uring_cancel_wq(struct io_uring_task *tctx)
+{
+	int ret;
+
+	if (!tctx->io_wq)
+		return;
+
+	/*
+	 * FIXED_FILE request isn't tracked in do_exit(), and these
+	 * requests may be submitted to our io_wq as iopoll, so have to
+	 * cancel them before destroying io_wq for avoiding IO hang
+	 */
+	do {
+		struct io_tctx_node *node;
+		unsigned long index;
+
+		ret = 0;
+		xa_for_each(&tctx->xa, index, node) {
+			struct io_ring_ctx *ctx = node->ctx;
+			struct io_task_cancel cancel = { .task = current, .all = true, };
+			enum io_wq_cancel cret;
+
+			io_iopoll_try_reap_events(ctx);
+			cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_task_cb,
+				       &cancel, true);
+			ret |= (cret != IO_WQ_CANCEL_NOTFOUND);
+			cond_resched();
+		}
+	} while (ret);
+}
+
 /*
  * Find any io_uring ctx that this task has registered or done IO on, and cancel
  * requests. @sqd should be not-null IFF it's an SQPOLL thread cancellation.
@@ -3361,6 +3392,7 @@ end_wait:
 		finish_wait(&tctx->wait, &wait);
 	} while (1);
 
+	io_uring_cancel_wq(tctx);
 	io_uring_clean_tctx(tctx);
 	if (cancel_all) {
 		/*

From 3888fa134eddac467b5a094949a8f0731ef6ffd5 Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Fri, 1 Sep 2023 15:59:35 +0300
Subject: [PATCH 0956/1189] docs/bpf: Fix "file doesn't exist" warnings in
 {llvm_reloc,btf}.rst

scripts/documentation-file-ref-check reports warnings for (valid) cross-links
of form:

  :ref:`Documentation/bpf/btf <BTF_Ext_Section>`

Adding extension to the file name helps to avoid the warning, e.g:

  :ref:`Documentation/bpf/btf.rst <BTF_Ext_Section>`

Fixes: be4033d36070 ("docs/bpf: Add description for CO-RE relocations")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Closes: https://lore.kernel.org/oe-kbuild-all/202309010804.G3MpXo59-lkp@intel.com
Link: https://lore.kernel.org/bpf/20230901125935.487972-1-eddyz87@gmail.com
---
 Documentation/bpf/btf.rst        | 2 +-
 Documentation/bpf/llvm_reloc.rst | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/bpf/btf.rst b/Documentation/bpf/btf.rst
index ffc11afee569..e43c2fdafcd7 100644
--- a/Documentation/bpf/btf.rst
+++ b/Documentation/bpf/btf.rst
@@ -803,7 +803,7 @@ structure when .BTF.ext is generated. All ``bpf_core_relo`` structures
 within a single ``btf_ext_info_sec`` describe relocations applied to
 section named by ``btf_ext_info_sec->sec_name_off``.
 
-See :ref:`Documentation/bpf/llvm_reloc <btf-co-re-relocations>`
+See :ref:`Documentation/bpf/llvm_reloc.rst <btf-co-re-relocations>`
 for more information on CO-RE relocations.
 
 4.2 .BTF_ids section
diff --git a/Documentation/bpf/llvm_reloc.rst b/Documentation/bpf/llvm_reloc.rst
index 73bf805000f2..44188e219d32 100644
--- a/Documentation/bpf/llvm_reloc.rst
+++ b/Documentation/bpf/llvm_reloc.rst
@@ -250,7 +250,7 @@ CO-RE Relocations
 From object file point of view CO-RE mechanism is implemented as a set
 of CO-RE specific relocation records. These relocation records are not
 related to ELF relocations and are encoded in .BTF.ext section.
-See :ref:`Documentation/bpf/btf <BTF_Ext_Section>` for more
+See :ref:`Documentation/bpf/btf.rst <BTF_Ext_Section>` for more
 information on .BTF.ext structure.
 
 CO-RE relocations are applied to BPF instructions to update immediate

From 5a26e45edb4690d58406178b5a9ea4c6dcf2c105 Mon Sep 17 00:00:00 2001
From: Chengming Zhou <zhouchengming@bytedance.com>
Date: Fri, 1 Sep 2023 20:03:06 +0800
Subject: [PATCH 0957/1189] null_blk: fix poll request timeout handling

When doing io_uring benchmark on /dev/nullb0, it's easy to crash the
kernel if poll requests timeout triggered, as reported by David. [1]

BUG: kernel NULL pointer dereference, address: 0000000000000008
Workqueue: kblockd blk_mq_timeout_work
RIP: 0010:null_timeout_rq+0x4e/0x91
Call Trace:
 ? null_timeout_rq+0x4e/0x91
 blk_mq_handle_expired+0x31/0x4b
 bt_iter+0x68/0x84
 ? bt_tags_iter+0x81/0x81
 __sbitmap_for_each_set.constprop.0+0xb0/0xf2
 ? __blk_mq_complete_request_remote+0xf/0xf
 bt_for_each+0x46/0x64
 ? __blk_mq_complete_request_remote+0xf/0xf
 ? percpu_ref_get_many+0xc/0x2a
 blk_mq_queue_tag_busy_iter+0x14d/0x18e
 blk_mq_timeout_work+0x95/0x127
 process_one_work+0x185/0x263
 worker_thread+0x1b5/0x227

This is indeed a race problem between null_timeout_rq() and null_poll().

null_poll()				null_timeout_rq()
  spin_lock(&nq->poll_lock)
  list_splice_init(&nq->poll_list, &list)
  spin_unlock(&nq->poll_lock)

  while (!list_empty(&list))
    req = list_first_entry()
    list_del_init()
    ...
    blk_mq_add_to_batch()
    // req->rq_next = NULL
					spin_lock(&nq->poll_lock)

					// rq->queuelist->next == NULL
					list_del_init(&rq->queuelist)

					spin_unlock(&nq->poll_lock)

Fix these problems by setting requests state to MQ_RQ_COMPLETE under
nq->poll_lock protection, in which null_timeout_rq() can safely detect
this race and early return.

Note this patch just fix the kernel panic when request timeout happen.

[1] https://lore.kernel.org/all/3893581.1691785261@warthog.procyon.org.uk/

Fixes: 0a593fbbc245 ("null_blk: poll queue support")
Reported-by: David Howells <dhowells@redhat.com>
Tested-by: David Howells <dhowells@redhat.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Link: https://lore.kernel.org/r/20230901120306.170520-2-chengming.zhou@linux.dev
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/null_blk/main.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index 864013019d6b..968090935eb2 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -1643,9 +1643,12 @@ static int null_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 	struct nullb_queue *nq = hctx->driver_data;
 	LIST_HEAD(list);
 	int nr = 0;
+	struct request *rq;
 
 	spin_lock(&nq->poll_lock);
 	list_splice_init(&nq->poll_list, &list);
+	list_for_each_entry(rq, &list, queuelist)
+		blk_mq_set_request_complete(rq);
 	spin_unlock(&nq->poll_lock);
 
 	while (!list_empty(&list)) {
@@ -1671,16 +1674,21 @@ static enum blk_eh_timer_return null_timeout_rq(struct request *rq)
 	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
 	struct nullb_cmd *cmd = blk_mq_rq_to_pdu(rq);
 
-	pr_info("rq %p timed out\n", rq);
-
 	if (hctx->type == HCTX_TYPE_POLL) {
 		struct nullb_queue *nq = hctx->driver_data;
 
 		spin_lock(&nq->poll_lock);
+		/* The request may have completed meanwhile. */
+		if (blk_mq_request_completed(rq)) {
+			spin_unlock(&nq->poll_lock);
+			return BLK_EH_DONE;
+		}
 		list_del_init(&rq->queuelist);
 		spin_unlock(&nq->poll_lock);
 	}
 
+	pr_info("rq %p timed out\n", rq);
+
 	/*
 	 * If the device is marked as blocking (i.e. memory backed or zoned
 	 * device), the submission path may be blocked waiting for resources

From 584ea6564bcaead223840cdafe84e4947ba85509 Mon Sep 17 00:00:00 2001
From: Evan Green <evan@rivosinc.com>
Date: Fri, 18 Aug 2023 12:41:35 -0700
Subject: [PATCH 0958/1189] RISC-V: Probe for unaligned access speed

Rather than deferring unaligned access speed determinations to a vendor
function, let's probe them and find out how fast they are. If we
determine that an unaligned word access is faster than N byte accesses,
mark the hardware's unaligned access as "fast". Otherwise, we mark
accesses as slow.

The algorithm itself runs for a fixed amount of jiffies. Within each
iteration it attempts to time a single loop, and then keeps only the best
(fastest) loop it saw. This algorithm was found to have lower variance from
run to run than my first attempt, which counted the total number of
iterations that could be done in that fixed amount of jiffies. By taking
only the best iteration in the loop, assuming at least one loop wasn't
perturbed by an interrupt, we eliminate the effects of interrupts and
other "warm up" factors like branch prediction. The only downside is it
depends on having an rdtime granular and accurate enough to measure a
single copy. If we ever manage to complete a loop in 0 rdtime ticks, we
leave the unaligned setting at UNKNOWN.

There is a slight change in user-visible behavior here. Previously, all
boards except the THead C906 reported misaligned access speed of
UNKNOWN. C906 reported FAST. With this change, since we're now measuring
misaligned access speed on each hart, all RISC-V systems will have this
key set as either FAST or SLOW.

Currently, we don't have a way to confidently measure the difference between
SLOW and EMULATED, so we label anything not fast as SLOW. This will
mislabel some systems that are actually EMULATED as SLOW. When we get
support for delegating misaligned access traps to the kernel (as opposed
to the firmware quietly handling it), we can explicitly test in Linux to
see if unaligned accesses trap. Those systems will start to report
EMULATED, though older (today's) systems without that new SBI mechanism
will continue to report SLOW.

I've updated the documentation for those hwprobe values to reflect
this, specifically: SLOW may or may not be emulated by software, and FAST
represents means being faster than equivalent byte accesses. The change
in documentation is accurate with respect to both the former and current
behavior.

Signed-off-by: Evan Green <evan@rivosinc.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20230818194136.4084400-2-evan@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 Documentation/riscv/hwprobe.rst     |  11 ++-
 arch/riscv/include/asm/cpufeature.h |   2 +
 arch/riscv/kernel/Makefile          |   1 +
 arch/riscv/kernel/copy-unaligned.S  |  71 +++++++++++++++++++
 arch/riscv/kernel/copy-unaligned.h  |  13 ++++
 arch/riscv/kernel/cpufeature.c      | 104 ++++++++++++++++++++++++++++
 arch/riscv/kernel/smpboot.c         |   2 +
 7 files changed, 198 insertions(+), 6 deletions(-)
 create mode 100644 arch/riscv/kernel/copy-unaligned.S
 create mode 100644 arch/riscv/kernel/copy-unaligned.h

diff --git a/Documentation/riscv/hwprobe.rst b/Documentation/riscv/hwprobe.rst
index 19165ebd82ba..f63fd05f1a73 100644
--- a/Documentation/riscv/hwprobe.rst
+++ b/Documentation/riscv/hwprobe.rst
@@ -87,13 +87,12 @@ The following keys are defined:
     emulated via software, either in or below the kernel.  These accesses are
     always extremely slow.
 
-  * :c:macro:`RISCV_HWPROBE_MISALIGNED_SLOW`: Misaligned accesses are supported
-    in hardware, but are slower than the cooresponding aligned accesses
-    sequences.
+  * :c:macro:`RISCV_HWPROBE_MISALIGNED_SLOW`: Misaligned accesses are slower
+    than equivalent byte accesses.  Misaligned accesses may be supported
+    directly in hardware, or trapped and emulated by software.
 
-  * :c:macro:`RISCV_HWPROBE_MISALIGNED_FAST`: Misaligned accesses are supported
-    in hardware and are faster than the cooresponding aligned accesses
-    sequences.
+  * :c:macro:`RISCV_HWPROBE_MISALIGNED_FAST`: Misaligned accesses are faster
+    than equivalent byte accesses.
 
   * :c:macro:`RISCV_HWPROBE_MISALIGNED_UNSUPPORTED`: Misaligned accesses are
     not supported at all and will generate a misaligned address fault.
diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index 23fed53b8815..d0345bd659c9 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -30,4 +30,6 @@ DECLARE_PER_CPU(long, misaligned_access_speed);
 /* Per-cpu ISA extensions. */
 extern struct riscv_isainfo hart_isa[NR_CPUS];
 
+void check_unaligned_access(int cpu);
+
 #endif
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 506cc4a9a45a..7e6c464cdfe9 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -38,6 +38,7 @@ extra-y += vmlinux.lds
 obj-y	+= head.o
 obj-y	+= soc.o
 obj-$(CONFIG_RISCV_ALTERNATIVE) += alternative.o
+obj-y	+= copy-unaligned.o
 obj-y	+= cpu.o
 obj-y	+= cpufeature.o
 obj-y	+= entry.o
diff --git a/arch/riscv/kernel/copy-unaligned.S b/arch/riscv/kernel/copy-unaligned.S
new file mode 100644
index 000000000000..cfdecfbaad62
--- /dev/null
+++ b/arch/riscv/kernel/copy-unaligned.S
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2023 Rivos Inc. */
+
+#include <linux/linkage.h>
+#include <asm/asm.h>
+
+	.text
+
+/* void __riscv_copy_words_unaligned(void *, const void *, size_t) */
+/* Performs a memcpy without aligning buffers, using word loads and stores. */
+/* Note: The size is truncated to a multiple of 8 * SZREG */
+ENTRY(__riscv_copy_words_unaligned)
+	andi  a4, a2, ~((8*SZREG)-1)
+	beqz  a4, 2f
+	add   a3, a1, a4
+1:
+	REG_L a4,       0(a1)
+	REG_L a5,   SZREG(a1)
+	REG_L a6, 2*SZREG(a1)
+	REG_L a7, 3*SZREG(a1)
+	REG_L t0, 4*SZREG(a1)
+	REG_L t1, 5*SZREG(a1)
+	REG_L t2, 6*SZREG(a1)
+	REG_L t3, 7*SZREG(a1)
+	REG_S a4,       0(a0)
+	REG_S a5,   SZREG(a0)
+	REG_S a6, 2*SZREG(a0)
+	REG_S a7, 3*SZREG(a0)
+	REG_S t0, 4*SZREG(a0)
+	REG_S t1, 5*SZREG(a0)
+	REG_S t2, 6*SZREG(a0)
+	REG_S t3, 7*SZREG(a0)
+	addi  a0, a0, 8*SZREG
+	addi  a1, a1, 8*SZREG
+	bltu  a1, a3, 1b
+
+2:
+	ret
+END(__riscv_copy_words_unaligned)
+
+/* void __riscv_copy_bytes_unaligned(void *, const void *, size_t) */
+/* Performs a memcpy without aligning buffers, using only byte accesses. */
+/* Note: The size is truncated to a multiple of 8 */
+ENTRY(__riscv_copy_bytes_unaligned)
+	andi a4, a2, ~(8-1)
+	beqz a4, 2f
+	add  a3, a1, a4
+1:
+	lb   a4, 0(a1)
+	lb   a5, 1(a1)
+	lb   a6, 2(a1)
+	lb   a7, 3(a1)
+	lb   t0, 4(a1)
+	lb   t1, 5(a1)
+	lb   t2, 6(a1)
+	lb   t3, 7(a1)
+	sb   a4, 0(a0)
+	sb   a5, 1(a0)
+	sb   a6, 2(a0)
+	sb   a7, 3(a0)
+	sb   t0, 4(a0)
+	sb   t1, 5(a0)
+	sb   t2, 6(a0)
+	sb   t3, 7(a0)
+	addi a0, a0, 8
+	addi a1, a1, 8
+	bltu a1, a3, 1b
+
+2:
+	ret
+END(__riscv_copy_bytes_unaligned)
diff --git a/arch/riscv/kernel/copy-unaligned.h b/arch/riscv/kernel/copy-unaligned.h
new file mode 100644
index 000000000000..e3d70d35b708
--- /dev/null
+++ b/arch/riscv/kernel/copy-unaligned.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023 Rivos, Inc.
+ */
+#ifndef __RISCV_KERNEL_COPY_UNALIGNED_H
+#define __RISCV_KERNEL_COPY_UNALIGNED_H
+
+#include <linux/types.h>
+
+void __riscv_copy_words_unaligned(void *dst, const void *src, size_t size);
+void __riscv_copy_bytes_unaligned(void *dst, const void *src, size_t size);
+
+#endif /* __RISCV_KERNEL_COPY_UNALIGNED_H */
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index bdcf460ea53d..cc09444352b2 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -19,12 +19,19 @@
 #include <asm/cacheflush.h>
 #include <asm/cpufeature.h>
 #include <asm/hwcap.h>
+#include <asm/hwprobe.h>
 #include <asm/patch.h>
 #include <asm/processor.h>
 #include <asm/vector.h>
 
+#include "copy-unaligned.h"
+
 #define NUM_ALPHA_EXTS ('z' - 'a' + 1)
 
+#define MISALIGNED_ACCESS_JIFFIES_LG2 1
+#define MISALIGNED_BUFFER_SIZE 0x4000
+#define MISALIGNED_COPY_SIZE ((MISALIGNED_BUFFER_SIZE / 2) - 0x80)
+
 unsigned long elf_hwcap __read_mostly;
 
 /* Host ISA bitmap */
@@ -396,6 +403,103 @@ unsigned long riscv_get_elf_hwcap(void)
 	return hwcap;
 }
 
+void check_unaligned_access(int cpu)
+{
+	u64 start_cycles, end_cycles;
+	u64 word_cycles;
+	u64 byte_cycles;
+	int ratio;
+	unsigned long start_jiffies, now;
+	struct page *page;
+	void *dst;
+	void *src;
+	long speed = RISCV_HWPROBE_MISALIGNED_SLOW;
+
+	page = alloc_pages(GFP_NOWAIT, get_order(MISALIGNED_BUFFER_SIZE));
+	if (!page) {
+		pr_warn("Can't alloc pages to measure memcpy performance");
+		return;
+	}
+
+	/* Make an unaligned destination buffer. */
+	dst = (void *)((unsigned long)page_address(page) | 0x1);
+	/* Unalign src as well, but differently (off by 1 + 2 = 3). */
+	src = dst + (MISALIGNED_BUFFER_SIZE / 2);
+	src += 2;
+	word_cycles = -1ULL;
+	/* Do a warmup. */
+	__riscv_copy_words_unaligned(dst, src, MISALIGNED_COPY_SIZE);
+	preempt_disable();
+	start_jiffies = jiffies;
+	while ((now = jiffies) == start_jiffies)
+		cpu_relax();
+
+	/*
+	 * For a fixed amount of time, repeatedly try the function, and take
+	 * the best time in cycles as the measurement.
+	 */
+	while (time_before(jiffies, now + (1 << MISALIGNED_ACCESS_JIFFIES_LG2))) {
+		start_cycles = get_cycles64();
+		/* Ensure the CSR read can't reorder WRT to the copy. */
+		mb();
+		__riscv_copy_words_unaligned(dst, src, MISALIGNED_COPY_SIZE);
+		/* Ensure the copy ends before the end time is snapped. */
+		mb();
+		end_cycles = get_cycles64();
+		if ((end_cycles - start_cycles) < word_cycles)
+			word_cycles = end_cycles - start_cycles;
+	}
+
+	byte_cycles = -1ULL;
+	__riscv_copy_bytes_unaligned(dst, src, MISALIGNED_COPY_SIZE);
+	start_jiffies = jiffies;
+	while ((now = jiffies) == start_jiffies)
+		cpu_relax();
+
+	while (time_before(jiffies, now + (1 << MISALIGNED_ACCESS_JIFFIES_LG2))) {
+		start_cycles = get_cycles64();
+		mb();
+		__riscv_copy_bytes_unaligned(dst, src, MISALIGNED_COPY_SIZE);
+		mb();
+		end_cycles = get_cycles64();
+		if ((end_cycles - start_cycles) < byte_cycles)
+			byte_cycles = end_cycles - start_cycles;
+	}
+
+	preempt_enable();
+
+	/* Don't divide by zero. */
+	if (!word_cycles || !byte_cycles) {
+		pr_warn("cpu%d: rdtime lacks granularity needed to measure unaligned access speed\n",
+			cpu);
+
+		goto out;
+	}
+
+	if (word_cycles < byte_cycles)
+		speed = RISCV_HWPROBE_MISALIGNED_FAST;
+
+	ratio = div_u64((byte_cycles * 100), word_cycles);
+	pr_info("cpu%d: Ratio of byte access time to unaligned word access is %d.%02d, unaligned accesses are %s\n",
+		cpu,
+		ratio / 100,
+		ratio % 100,
+		(speed == RISCV_HWPROBE_MISALIGNED_FAST) ? "fast" : "slow");
+
+	per_cpu(misaligned_access_speed, cpu) = speed;
+
+out:
+	__free_pages(page, get_order(MISALIGNED_BUFFER_SIZE));
+}
+
+static int check_unaligned_access_boot_cpu(void)
+{
+	check_unaligned_access(0);
+	return 0;
+}
+
+arch_initcall(check_unaligned_access_boot_cpu);
+
 #ifdef CONFIG_RISCV_ALTERNATIVE
 /*
  * Alternative patch sites consider 48 bits when determining when to patch
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index f4d6acb38dd0..00ddbd2364dc 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -26,6 +26,7 @@
 #include <linux/sched/task_stack.h>
 #include <linux/sched/mm.h>
 #include <asm/cpu_ops.h>
+#include <asm/cpufeature.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/numa.h>
@@ -245,6 +246,7 @@ asmlinkage __visible void smp_callin(void)
 
 	numa_add_cpu(curr_cpuid);
 	set_cpu_online(curr_cpuid, 1);
+	check_unaligned_access(curr_cpuid);
 	probe_vendor_features(curr_cpuid);
 
 	if (has_vector()) {

From f2d14bc4e437b8ed21e6890ae047a6ec47c030d9 Mon Sep 17 00:00:00 2001
From: Evan Green <evan@rivosinc.com>
Date: Fri, 18 Aug 2023 12:41:36 -0700
Subject: [PATCH 0959/1189] RISC-V: alternative: Remove feature_probe_func

Now that we're testing unaligned memory copy and making that
determination generically, there are no more users of the vendor
feature_probe_func(). While I think it's probably going to need to come
back, there are no users right now, so let's remove it until it's
needed.

Signed-off-by: Evan Green <evan@rivosinc.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20230818194136.4084400-3-evan@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/errata/thead/errata.c     |  8 --------
 arch/riscv/include/asm/alternative.h |  5 -----
 arch/riscv/kernel/alternative.c      | 19 -------------------
 arch/riscv/kernel/smpboot.c          |  1 -
 4 files changed, 33 deletions(-)

diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c
index be84b14f0118..0554ed4bf087 100644
--- a/arch/riscv/errata/thead/errata.c
+++ b/arch/riscv/errata/thead/errata.c
@@ -120,11 +120,3 @@ void thead_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
 	if (stage == RISCV_ALTERNATIVES_EARLY_BOOT)
 		local_flush_icache_all();
 }
-
-void thead_feature_probe_func(unsigned int cpu,
-			      unsigned long archid,
-			      unsigned long impid)
-{
-	if ((archid == 0) && (impid == 0))
-		per_cpu(misaligned_access_speed, cpu) = RISCV_HWPROBE_MISALIGNED_FAST;
-}
diff --git a/arch/riscv/include/asm/alternative.h b/arch/riscv/include/asm/alternative.h
index 6a41537826a7..58ccd2f8cab7 100644
--- a/arch/riscv/include/asm/alternative.h
+++ b/arch/riscv/include/asm/alternative.h
@@ -30,7 +30,6 @@
 #define ALT_OLD_PTR(a)			__ALT_PTR(a, old_offset)
 #define ALT_ALT_PTR(a)			__ALT_PTR(a, alt_offset)
 
-void probe_vendor_features(unsigned int cpu);
 void __init apply_boot_alternatives(void);
 void __init apply_early_boot_alternatives(void);
 void apply_module_alternatives(void *start, size_t length);
@@ -53,15 +52,11 @@ void thead_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
 			     unsigned long archid, unsigned long impid,
 			     unsigned int stage);
 
-void thead_feature_probe_func(unsigned int cpu, unsigned long archid,
-			      unsigned long impid);
-
 void riscv_cpufeature_patch_func(struct alt_entry *begin, struct alt_entry *end,
 				 unsigned int stage);
 
 #else /* CONFIG_RISCV_ALTERNATIVE */
 
-static inline void probe_vendor_features(unsigned int cpu) { }
 static inline void apply_boot_alternatives(void) { }
 static inline void apply_early_boot_alternatives(void) { }
 static inline void apply_module_alternatives(void *start, size_t length) { }
diff --git a/arch/riscv/kernel/alternative.c b/arch/riscv/kernel/alternative.c
index 6b75788c18e6..85056153fa23 100644
--- a/arch/riscv/kernel/alternative.c
+++ b/arch/riscv/kernel/alternative.c
@@ -27,8 +27,6 @@ struct cpu_manufacturer_info_t {
 	void (*patch_func)(struct alt_entry *begin, struct alt_entry *end,
 				  unsigned long archid, unsigned long impid,
 				  unsigned int stage);
-	void (*feature_probe_func)(unsigned int cpu, unsigned long archid,
-				   unsigned long impid);
 };
 
 static void riscv_fill_cpu_mfr_info(struct cpu_manufacturer_info_t *cpu_mfr_info)
@@ -43,7 +41,6 @@ static void riscv_fill_cpu_mfr_info(struct cpu_manufacturer_info_t *cpu_mfr_info
 	cpu_mfr_info->imp_id = sbi_get_mimpid();
 #endif
 
-	cpu_mfr_info->feature_probe_func = NULL;
 	switch (cpu_mfr_info->vendor_id) {
 #ifdef CONFIG_ERRATA_SIFIVE
 	case SIFIVE_VENDOR_ID:
@@ -53,7 +50,6 @@ static void riscv_fill_cpu_mfr_info(struct cpu_manufacturer_info_t *cpu_mfr_info
 #ifdef CONFIG_ERRATA_THEAD
 	case THEAD_VENDOR_ID:
 		cpu_mfr_info->patch_func = thead_errata_patch_func;
-		cpu_mfr_info->feature_probe_func = thead_feature_probe_func;
 		break;
 #endif
 	default:
@@ -143,20 +139,6 @@ void riscv_alternative_fix_offsets(void *alt_ptr, unsigned int len,
 	}
 }
 
-/* Called on each CPU as it starts */
-void probe_vendor_features(unsigned int cpu)
-{
-	struct cpu_manufacturer_info_t cpu_mfr_info;
-
-	riscv_fill_cpu_mfr_info(&cpu_mfr_info);
-	if (!cpu_mfr_info.feature_probe_func)
-		return;
-
-	cpu_mfr_info.feature_probe_func(cpu,
-					cpu_mfr_info.arch_id,
-					cpu_mfr_info.imp_id);
-}
-
 /*
  * This is called very early in the boot process (directly after we run
  * a feature detect on the boot CPU). No need to worry about other CPUs
@@ -211,7 +193,6 @@ void __init apply_boot_alternatives(void)
 	/* If called on non-boot cpu things could go wrong */
 	WARN_ON(smp_processor_id() != 0);
 
-	probe_vendor_features(0);
 	_apply_alternatives((struct alt_entry *)__alt_start,
 			    (struct alt_entry *)__alt_end,
 			    RISCV_ALTERNATIVES_BOOT);
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index 00ddbd2364dc..1b8da4e40a4d 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -247,7 +247,6 @@ asmlinkage __visible void smp_callin(void)
 	numa_add_cpu(curr_cpuid);
 	set_cpu_online(curr_cpuid, 1);
 	check_unaligned_access(curr_cpuid);
-	probe_vendor_features(curr_cpuid);
 
 	if (has_vector()) {
 		if (riscv_v_setup_vsize())

From eb746180132a555da8cfb02d98cb6d0a9d58e870 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 17 Aug 2023 00:23:34 +0100
Subject: [PATCH 0960/1189] riscv: dma-mapping: only invalidate after DMA, not
 flush

No other architecture intentionally writes back dirty cache lines into
a buffer that a device has just finished writing into. If the cache is
clean, this has no effect at all, but if a cacheline in the buffer has
actually been written by the CPU,  there is a driver bug that is likely
made worse by overwriting that buffer.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Acked-by: Palmer Dabbelt <palmer@rivosinc.com>
Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Link: https://lore.kernel.org/r/20230816232336.164413-2-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/mm/dma-noncoherent.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/mm/dma-noncoherent.c b/arch/riscv/mm/dma-noncoherent.c
index d51a75864e53..94614cf61cdd 100644
--- a/arch/riscv/mm/dma-noncoherent.c
+++ b/arch/riscv/mm/dma-noncoherent.c
@@ -42,7 +42,7 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
 		break;
 	case DMA_FROM_DEVICE:
 	case DMA_BIDIRECTIONAL:
-		ALT_CMO_OP(flush, vaddr, size, riscv_cbom_block_size);
+		ALT_CMO_OP(inval, vaddr, size, riscv_cbom_block_size);
 		break;
 	default:
 		break;

From 482069ebdc1d61fba14527055894b9f4f0ced08c Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 17 Aug 2023 00:23:35 +0100
Subject: [PATCH 0961/1189] riscv: dma-mapping: skip invalidation before
 bidirectional DMA

For a DMA_BIDIRECTIONAL transfer, the caches have to be cleaned
first to let the device see data written by the CPU, and invalidated
after the transfer to let the CPU see data written by the device.

riscv also invalidates the caches before the transfer, which does
not appear to serve any purpose.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Acked-by: Palmer Dabbelt <palmer@rivosinc.com>
Acked-by: Guo Ren <guoren@kernel.org>
Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Link: https://lore.kernel.org/r/20230816232336.164413-3-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/mm/dma-noncoherent.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/mm/dma-noncoherent.c b/arch/riscv/mm/dma-noncoherent.c
index 94614cf61cdd..fc6377a64c8d 100644
--- a/arch/riscv/mm/dma-noncoherent.c
+++ b/arch/riscv/mm/dma-noncoherent.c
@@ -25,7 +25,7 @@ void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
 		ALT_CMO_OP(clean, vaddr, size, riscv_cbom_block_size);
 		break;
 	case DMA_BIDIRECTIONAL:
-		ALT_CMO_OP(flush, vaddr, size, riscv_cbom_block_size);
+		ALT_CMO_OP(clean, vaddr, size, riscv_cbom_block_size);
 		break;
 	default:
 		break;

From 935730160738a478dbf4b61cf0cfc29c1442fb4e Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Thu, 17 Aug 2023 00:23:36 +0100
Subject: [PATCH 0962/1189] riscv: dma-mapping: switch over to generic
 implementation

Add helper functions for cache wback/inval/clean and use them
arch_sync_dma_for_device()/arch_sync_dma_for_cpu() functions. The proposed
changes are in preparation for switching over to generic implementation.

Reorganization of the code is based on the patch (Link[0]) from Arnd.
For now I have dropped CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU check as this
will be enabled by default upon selection of RISCV_DMA_NONCOHERENT
and also dropped arch_dma_mark_dcache_clean().

Link[0]: https://lore.kernel.org/all/20230327121317.4081816-22-arnd@kernel.org/
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Link: https://lore.kernel.org/r/20230816232336.164413-4-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/mm/dma-noncoherent.c | 60 ++++++++++++++++++++++++++++-----
 1 file changed, 51 insertions(+), 9 deletions(-)

diff --git a/arch/riscv/mm/dma-noncoherent.c b/arch/riscv/mm/dma-noncoherent.c
index fc6377a64c8d..06b8fea58e20 100644
--- a/arch/riscv/mm/dma-noncoherent.c
+++ b/arch/riscv/mm/dma-noncoherent.c
@@ -12,21 +12,61 @@
 
 static bool noncoherent_supported __ro_after_init;
 
-void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
-			      enum dma_data_direction dir)
+static inline void arch_dma_cache_wback(phys_addr_t paddr, size_t size)
 {
 	void *vaddr = phys_to_virt(paddr);
 
+	ALT_CMO_OP(clean, vaddr, size, riscv_cbom_block_size);
+}
+
+static inline void arch_dma_cache_inv(phys_addr_t paddr, size_t size)
+{
+	void *vaddr = phys_to_virt(paddr);
+
+	ALT_CMO_OP(inval, vaddr, size, riscv_cbom_block_size);
+}
+
+static inline void arch_dma_cache_wback_inv(phys_addr_t paddr, size_t size)
+{
+	void *vaddr = phys_to_virt(paddr);
+
+	ALT_CMO_OP(flush, vaddr, size, riscv_cbom_block_size);
+}
+
+static inline bool arch_sync_dma_clean_before_fromdevice(void)
+{
+	return true;
+}
+
+static inline bool arch_sync_dma_cpu_needs_post_dma_flush(void)
+{
+	return true;
+}
+
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+			      enum dma_data_direction dir)
+{
 	switch (dir) {
 	case DMA_TO_DEVICE:
-		ALT_CMO_OP(clean, vaddr, size, riscv_cbom_block_size);
+		arch_dma_cache_wback(paddr, size);
 		break;
+
 	case DMA_FROM_DEVICE:
-		ALT_CMO_OP(clean, vaddr, size, riscv_cbom_block_size);
-		break;
+		if (!arch_sync_dma_clean_before_fromdevice()) {
+			arch_dma_cache_inv(paddr, size);
+			break;
+		}
+		fallthrough;
+
 	case DMA_BIDIRECTIONAL:
-		ALT_CMO_OP(clean, vaddr, size, riscv_cbom_block_size);
+		/* Skip the invalidate here if it's done later */
+		if (IS_ENABLED(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) &&
+		    arch_sync_dma_cpu_needs_post_dma_flush())
+			arch_dma_cache_wback(paddr, size);
+		else
+			arch_dma_cache_wback_inv(paddr, size);
 		break;
+
 	default:
 		break;
 	}
@@ -35,15 +75,17 @@ void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
 void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
 			   enum dma_data_direction dir)
 {
-	void *vaddr = phys_to_virt(paddr);
-
 	switch (dir) {
 	case DMA_TO_DEVICE:
 		break;
+
 	case DMA_FROM_DEVICE:
 	case DMA_BIDIRECTIONAL:
-		ALT_CMO_OP(inval, vaddr, size, riscv_cbom_block_size);
+		/* FROM_DEVICE invalidate needed if speculative CPU prefetch only */
+		if (arch_sync_dma_cpu_needs_post_dma_flush())
+			arch_dma_cache_inv(paddr, size);
 		break;
+
 	default:
 		break;
 	}

From d6ca3a56f4f3e1d408397f1e309f7c57a6d01c38 Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Fri, 18 Aug 2023 14:57:18 +0100
Subject: [PATCH 0963/1189] riscv: asm: vendorid_list: Add Andes Technology to
 the vendors list

Add Andes Technology to the vendors list.

Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Tested-by: Conor Dooley <conor.dooley@microchip.com> # tyre-kicking on a d1
Link: https://lore.kernel.org/r/20230818135723.80612-2-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/vendorid_list.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/riscv/include/asm/vendorid_list.h b/arch/riscv/include/asm/vendorid_list.h
index cb89af3f0704..e55407ace0c3 100644
--- a/arch/riscv/include/asm/vendorid_list.h
+++ b/arch/riscv/include/asm/vendorid_list.h
@@ -5,6 +5,7 @@
 #ifndef ASM_VENDOR_LIST_H
 #define ASM_VENDOR_LIST_H
 
+#define ANDESTECH_VENDOR_ID	0x31e
 #define SIFIVE_VENDOR_ID	0x489
 #define THEAD_VENDOR_ID		0x5b7
 

From e021ae7f5145d46ab64cb058cbffda31059f37e5 Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Fri, 18 Aug 2023 14:57:19 +0100
Subject: [PATCH 0964/1189] riscv: errata: Add Andes alternative ports

Add required ports of the Alternative scheme for Andes CPU cores.

I/O Coherence Port (IOCP) provides an AXI interface for connecting external
non-caching masters, such as DMA controllers. IOCP is a specification
option and is disabled on the Renesas RZ/Five SoC due to this reason cache
management needs a software workaround.

Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Tested-by: Conor Dooley <conor.dooley@microchip.com> # tyre-kicking on a d1
Link: https://lore.kernel.org/r/20230818135723.80612-3-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig.errata            | 21 +++++++++
 arch/riscv/errata/Makefile           |  1 +
 arch/riscv/errata/andes/Makefile     |  1 +
 arch/riscv/errata/andes/errata.c     | 66 ++++++++++++++++++++++++++++
 arch/riscv/include/asm/alternative.h |  3 ++
 arch/riscv/include/asm/errata_list.h |  5 +++
 arch/riscv/kernel/alternative.c      |  5 +++
 7 files changed, 102 insertions(+)
 create mode 100644 arch/riscv/errata/andes/Makefile
 create mode 100644 arch/riscv/errata/andes/errata.c

diff --git a/arch/riscv/Kconfig.errata b/arch/riscv/Kconfig.errata
index 0c8f4652cd82..92c779764b27 100644
--- a/arch/riscv/Kconfig.errata
+++ b/arch/riscv/Kconfig.errata
@@ -1,5 +1,26 @@
 menu "CPU errata selection"
 
+config ERRATA_ANDES
+	bool "Andes AX45MP errata"
+	depends on RISCV_ALTERNATIVE
+	help
+	  All Andes errata Kconfig depend on this Kconfig. Disabling
+	  this Kconfig will disable all Andes errata. Please say "Y"
+	  here if your platform uses Andes CPU cores.
+
+	  Otherwise, please say "N" here to avoid unnecessary overhead.
+
+config ERRATA_ANDES_CMO
+	bool "Apply Andes cache management errata"
+	depends on ERRATA_ANDES && MMU && ARCH_R9A07G043
+	select RISCV_DMA_NONCOHERENT
+	default y
+	help
+	  This will apply the cache management errata to handle the
+	  non-standard handling on non-coherent operations on Andes cores.
+
+	  If you don't know what to do here, say "Y".
+
 config ERRATA_SIFIVE
 	bool "SiFive errata"
 	depends on RISCV_ALTERNATIVE
diff --git a/arch/riscv/errata/Makefile b/arch/riscv/errata/Makefile
index 7b2637c8c332..8a2739485123 100644
--- a/arch/riscv/errata/Makefile
+++ b/arch/riscv/errata/Makefile
@@ -2,5 +2,6 @@ ifdef CONFIG_RELOCATABLE
 KBUILD_CFLAGS += -fno-pie
 endif
 
+obj-$(CONFIG_ERRATA_ANDES) += andes/
 obj-$(CONFIG_ERRATA_SIFIVE) += sifive/
 obj-$(CONFIG_ERRATA_THEAD) += thead/
diff --git a/arch/riscv/errata/andes/Makefile b/arch/riscv/errata/andes/Makefile
new file mode 100644
index 000000000000..2d644e19caef
--- /dev/null
+++ b/arch/riscv/errata/andes/Makefile
@@ -0,0 +1 @@
+obj-y += errata.o
diff --git a/arch/riscv/errata/andes/errata.c b/arch/riscv/errata/andes/errata.c
new file mode 100644
index 000000000000..197db68cc8da
--- /dev/null
+++ b/arch/riscv/errata/andes/errata.c
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Erratas to be applied for Andes CPU cores
+ *
+ *  Copyright (C) 2023 Renesas Electronics Corporation.
+ *
+ * Author: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
+ */
+
+#include <linux/memory.h>
+#include <linux/module.h>
+
+#include <asm/alternative.h>
+#include <asm/cacheflush.h>
+#include <asm/errata_list.h>
+#include <asm/patch.h>
+#include <asm/processor.h>
+#include <asm/sbi.h>
+#include <asm/vendorid_list.h>
+
+#define ANDESTECH_AX45MP_MARCHID	0x8000000000008a45UL
+#define ANDESTECH_AX45MP_MIMPID		0x500UL
+#define ANDESTECH_SBI_EXT_ANDES		0x0900031E
+
+#define ANDES_SBI_EXT_IOCP_SW_WORKAROUND	1
+
+static long ax45mp_iocp_sw_workaround(void)
+{
+	struct sbiret ret;
+
+	/*
+	 * ANDES_SBI_EXT_IOCP_SW_WORKAROUND SBI EXT checks if the IOCP is missing and
+	 * cache is controllable only then CMO will be applied to the platform.
+	 */
+	ret = sbi_ecall(ANDESTECH_SBI_EXT_ANDES, ANDES_SBI_EXT_IOCP_SW_WORKAROUND,
+			0, 0, 0, 0, 0, 0);
+
+	return ret.error ? 0 : ret.value;
+}
+
+static bool errata_probe_iocp(unsigned int stage, unsigned long arch_id, unsigned long impid)
+{
+	if (!IS_ENABLED(CONFIG_ERRATA_ANDES_CMO))
+		return false;
+
+	if (arch_id != ANDESTECH_AX45MP_MARCHID || impid != ANDESTECH_AX45MP_MIMPID)
+		return false;
+
+	if (!ax45mp_iocp_sw_workaround())
+		return false;
+
+	/* Set this just to make core cbo code happy */
+	riscv_cbom_block_size = 1;
+	riscv_noncoherent_supported();
+
+	return true;
+}
+
+void __init_or_module andes_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
+					      unsigned long archid, unsigned long impid,
+					      unsigned int stage)
+{
+	errata_probe_iocp(stage, archid, impid);
+
+	/* we have nothing to patch here ATM so just return back */
+}
diff --git a/arch/riscv/include/asm/alternative.h b/arch/riscv/include/asm/alternative.h
index 6a41537826a7..f6cfca939c92 100644
--- a/arch/riscv/include/asm/alternative.h
+++ b/arch/riscv/include/asm/alternative.h
@@ -46,6 +46,9 @@ struct alt_entry {
 	u32 patch_id;		/* The patch ID (erratum ID or cpufeature ID) */
 };
 
+void andes_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
+			     unsigned long archid, unsigned long impid,
+			     unsigned int stage);
 void sifive_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
 			      unsigned long archid, unsigned long impid,
 			      unsigned int stage);
diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h
index fb1a810f3d8c..e2ecd01bfac7 100644
--- a/arch/riscv/include/asm/errata_list.h
+++ b/arch/riscv/include/asm/errata_list.h
@@ -11,6 +11,11 @@
 #include <asm/hwcap.h>
 #include <asm/vendorid_list.h>
 
+#ifdef CONFIG_ERRATA_ANDES
+#define ERRATA_ANDESTECH_NO_IOCP	0
+#define ERRATA_ANDESTECH_NUMBER		1
+#endif
+
 #ifdef CONFIG_ERRATA_SIFIVE
 #define	ERRATA_SIFIVE_CIP_453 0
 #define	ERRATA_SIFIVE_CIP_1200 1
diff --git a/arch/riscv/kernel/alternative.c b/arch/riscv/kernel/alternative.c
index 6b75788c18e6..b0345992a35e 100644
--- a/arch/riscv/kernel/alternative.c
+++ b/arch/riscv/kernel/alternative.c
@@ -45,6 +45,11 @@ static void riscv_fill_cpu_mfr_info(struct cpu_manufacturer_info_t *cpu_mfr_info
 
 	cpu_mfr_info->feature_probe_func = NULL;
 	switch (cpu_mfr_info->vendor_id) {
+#ifdef CONFIG_ERRATA_ANDES
+	case ANDESTECH_VENDOR_ID:
+		cpu_mfr_info->patch_func = andes_errata_patch_func;
+		break;
+#endif
 #ifdef CONFIG_ERRATA_SIFIVE
 	case SIFIVE_VENDOR_ID:
 		cpu_mfr_info->patch_func = sifive_errata_patch_func;

From b79f300c1fd4bd83b1f827c7a0e043fca7aad73c Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Fri, 18 Aug 2023 14:57:20 +0100
Subject: [PATCH 0965/1189] riscv: mm: dma-noncoherent: nonstandard cache
 operations support

Introduce support for nonstandard noncoherent systems in the RISC-V
architecture. It enables function pointer support to handle cache
management in such systems.

This patch adds a new configuration option called
"RISCV_NONSTANDARD_CACHE_OPS." This option is a boolean flag that
depends on "RISCV_DMA_NONCOHERENT" and enables the function pointer
support for cache management in nonstandard noncoherent systems.

Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Tested-by: Conor Dooley <conor.dooley@microchip.com> # tyre-kicking on a d1
Reviewed-by: Emil Renner Berthing <emil.renner.berthing@canonical.com>
Tested-by: Emil Renner Berthing <emil.renner.berthing@canonical.com> #
Link: https://lore.kernel.org/r/20230818135723.80612-4-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig                       |  7 ++++
 arch/riscv/include/asm/dma-noncoherent.h | 28 +++++++++++++++
 arch/riscv/mm/dma-noncoherent.c          | 43 ++++++++++++++++++++++++
 arch/riscv/mm/pmem.c                     | 13 +++++++
 4 files changed, 91 insertions(+)
 create mode 100644 arch/riscv/include/asm/dma-noncoherent.h

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 4c07b9189c86..3c2087974ce0 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -269,6 +269,13 @@ config RISCV_DMA_NONCOHERENT
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select DMA_DIRECT_REMAP
 
+config RISCV_NONSTANDARD_CACHE_OPS
+	bool
+	depends on RISCV_DMA_NONCOHERENT
+	help
+	  This enables function pointer support for non-standard noncoherent
+	  systems to handle cache management.
+
 config AS_HAS_INSN
 	def_bool $(as-instr,.insn r 51$(comma) 0$(comma) 0$(comma) t0$(comma) t0$(comma) zero)
 
diff --git a/arch/riscv/include/asm/dma-noncoherent.h b/arch/riscv/include/asm/dma-noncoherent.h
new file mode 100644
index 000000000000..312cfa0858fb
--- /dev/null
+++ b/arch/riscv/include/asm/dma-noncoherent.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023 Renesas Electronics Corp.
+ */
+
+#ifndef __ASM_DMA_NONCOHERENT_H
+#define __ASM_DMA_NONCOHERENT_H
+
+#include <linux/dma-direct.h>
+
+/*
+ * struct riscv_nonstd_cache_ops - Structure for non-standard CMO function pointers
+ *
+ * @wback: Function pointer for cache writeback
+ * @inv: Function pointer for invalidating cache
+ * @wback_inv: Function pointer for flushing the cache (writeback + invalidating)
+ */
+struct riscv_nonstd_cache_ops {
+	void (*wback)(phys_addr_t paddr, size_t size);
+	void (*inv)(phys_addr_t paddr, size_t size);
+	void (*wback_inv)(phys_addr_t paddr, size_t size);
+};
+
+extern struct riscv_nonstd_cache_ops noncoherent_cache_ops;
+
+void riscv_noncoherent_register_cache_ops(const struct riscv_nonstd_cache_ops *ops);
+
+#endif	/* __ASM_DMA_NONCOHERENT_H */
diff --git a/arch/riscv/mm/dma-noncoherent.c b/arch/riscv/mm/dma-noncoherent.c
index 06b8fea58e20..a4f3f37859ae 100644
--- a/arch/riscv/mm/dma-noncoherent.c
+++ b/arch/riscv/mm/dma-noncoherent.c
@@ -9,13 +9,26 @@
 #include <linux/dma-map-ops.h>
 #include <linux/mm.h>
 #include <asm/cacheflush.h>
+#include <asm/dma-noncoherent.h>
 
 static bool noncoherent_supported __ro_after_init;
 
+struct riscv_nonstd_cache_ops noncoherent_cache_ops __ro_after_init = {
+	.wback = NULL,
+	.inv = NULL,
+	.wback_inv = NULL,
+};
+
 static inline void arch_dma_cache_wback(phys_addr_t paddr, size_t size)
 {
 	void *vaddr = phys_to_virt(paddr);
 
+#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS
+	if (unlikely(noncoherent_cache_ops.wback)) {
+		noncoherent_cache_ops.wback(paddr, size);
+		return;
+	}
+#endif
 	ALT_CMO_OP(clean, vaddr, size, riscv_cbom_block_size);
 }
 
@@ -23,6 +36,13 @@ static inline void arch_dma_cache_inv(phys_addr_t paddr, size_t size)
 {
 	void *vaddr = phys_to_virt(paddr);
 
+#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS
+	if (unlikely(noncoherent_cache_ops.inv)) {
+		noncoherent_cache_ops.inv(paddr, size);
+		return;
+	}
+#endif
+
 	ALT_CMO_OP(inval, vaddr, size, riscv_cbom_block_size);
 }
 
@@ -30,6 +50,13 @@ static inline void arch_dma_cache_wback_inv(phys_addr_t paddr, size_t size)
 {
 	void *vaddr = phys_to_virt(paddr);
 
+#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS
+	if (unlikely(noncoherent_cache_ops.wback_inv)) {
+		noncoherent_cache_ops.wback_inv(paddr, size);
+		return;
+	}
+#endif
+
 	ALT_CMO_OP(flush, vaddr, size, riscv_cbom_block_size);
 }
 
@@ -95,6 +122,13 @@ void arch_dma_prep_coherent(struct page *page, size_t size)
 {
 	void *flush_addr = page_address(page);
 
+#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS
+	if (unlikely(noncoherent_cache_ops.wback_inv)) {
+		noncoherent_cache_ops.wback_inv(page_to_phys(page), size);
+		return;
+	}
+#endif
+
 	ALT_CMO_OP(flush, flush_addr, size, riscv_cbom_block_size);
 }
 
@@ -120,3 +154,12 @@ void riscv_noncoherent_supported(void)
 	     "Non-coherent DMA support enabled without a block size\n");
 	noncoherent_supported = true;
 }
+
+void riscv_noncoherent_register_cache_ops(const struct riscv_nonstd_cache_ops *ops)
+{
+	if (!ops)
+		return;
+
+	noncoherent_cache_ops = *ops;
+}
+EXPORT_SYMBOL_GPL(riscv_noncoherent_register_cache_ops);
diff --git a/arch/riscv/mm/pmem.c b/arch/riscv/mm/pmem.c
index 089df92ae876..c5fc5ec96f6d 100644
--- a/arch/riscv/mm/pmem.c
+++ b/arch/riscv/mm/pmem.c
@@ -7,15 +7,28 @@
 #include <linux/libnvdimm.h>
 
 #include <asm/cacheflush.h>
+#include <asm/dma-noncoherent.h>
 
 void arch_wb_cache_pmem(void *addr, size_t size)
 {
+#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS
+	if (unlikely(noncoherent_cache_ops.wback)) {
+		noncoherent_cache_ops.wback(virt_to_phys(addr), size);
+		return;
+	}
+#endif
 	ALT_CMO_OP(clean, addr, size, riscv_cbom_block_size);
 }
 EXPORT_SYMBOL_GPL(arch_wb_cache_pmem);
 
 void arch_invalidate_pmem(void *addr, size_t size)
 {
+#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS
+	if (unlikely(noncoherent_cache_ops.inv)) {
+		noncoherent_cache_ops.inv(virt_to_phys(addr), size);
+		return;
+	}
+#endif
 	ALT_CMO_OP(inval, addr, size, riscv_cbom_block_size);
 }
 EXPORT_SYMBOL_GPL(arch_invalidate_pmem);

From 3e7bf4685e42786dc10a57512c8a767947f25c10 Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Fri, 18 Aug 2023 14:57:21 +0100
Subject: [PATCH 0966/1189] dt-bindings: cache: andestech,ax45mp-cache: Add DT
 binding documentation for L2 cache controller

Add DT binding documentation for L2 cache controller found on RZ/Five SoC.

The Renesas RZ/Five microprocessor includes a RISC-V CPU Core (AX45MP
Single) from Andes. The AX45MP core has an L2 cache controller, this patch
describes the L2 cache block.

Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Tested-by: Conor Dooley <conor.dooley@microchip.com> # tyre-kicking on a d1
Link: https://lore.kernel.org/r/20230818135723.80612-5-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 .../cache/andestech,ax45mp-cache.yaml         | 81 +++++++++++++++++++
 1 file changed, 81 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/cache/andestech,ax45mp-cache.yaml

diff --git a/Documentation/devicetree/bindings/cache/andestech,ax45mp-cache.yaml b/Documentation/devicetree/bindings/cache/andestech,ax45mp-cache.yaml
new file mode 100644
index 000000000000..9ab5f0c435d4
--- /dev/null
+++ b/Documentation/devicetree/bindings/cache/andestech,ax45mp-cache.yaml
@@ -0,0 +1,81 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+# Copyright (C) 2023 Renesas Electronics Corp.
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/cache/andestech,ax45mp-cache.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Andestech AX45MP L2 Cache Controller
+
+maintainers:
+  - Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
+
+description:
+  A level-2 cache (L2C) is used to improve the system performance by providing
+  a large amount of cache line entries and reasonable access delays. The L2C
+  is shared between cores, and a non-inclusive non-exclusive policy is used.
+
+select:
+  properties:
+    compatible:
+      contains:
+        enum:
+          - andestech,ax45mp-cache
+
+  required:
+    - compatible
+
+properties:
+  compatible:
+    items:
+      - const: andestech,ax45mp-cache
+      - const: cache
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  cache-line-size:
+    const: 64
+
+  cache-level:
+    const: 2
+
+  cache-sets:
+    const: 1024
+
+  cache-size:
+    enum: [131072, 262144, 524288, 1048576, 2097152]
+
+  cache-unified: true
+
+  next-level-cache: true
+
+additionalProperties: false
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - cache-line-size
+  - cache-level
+  - cache-sets
+  - cache-size
+  - cache-unified
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+
+    cache-controller@2010000 {
+        compatible = "andestech,ax45mp-cache", "cache";
+        reg = <0x13400000 0x100000>;
+        interrupts = <508 IRQ_TYPE_LEVEL_HIGH>;
+        cache-line-size = <64>;
+        cache-level = <2>;
+        cache-sets = <1024>;
+        cache-size = <262144>;
+        cache-unified;
+    };

From d34599bcd2e4e93a28d5904bf94bc7dafc511f04 Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Fri, 18 Aug 2023 14:57:22 +0100
Subject: [PATCH 0967/1189] cache: Add L2 cache management for Andes AX45MP
 RISC-V core

I/O Coherence Port (IOCP) provides an AXI interface for connecting
external non-caching masters, such as DMA controllers. The accesses
from IOCP are coherent with D-Caches and L2 Cache.

IOCP is a specification option and is disabled on the Renesas RZ/Five
SoC due to this reason IP blocks using DMA will fail.

The Andes AX45MP core has a Programmable Physical Memory Attributes (PMA)
block that allows dynamic adjustment of memory attributes in the runtime.
It contains a configurable amount of PMA entries implemented as CSR
registers to control the attributes of memory locations in interest.
Below are the memory attributes supported:
* Device, Non-bufferable
* Device, bufferable
* Memory, Non-cacheable, Non-bufferable
* Memory, Non-cacheable, Bufferable
* Memory, Write-back, No-allocate
* Memory, Write-back, Read-allocate
* Memory, Write-back, Write-allocate
* Memory, Write-back, Read and Write-allocate

More info about PMA (section 10.3):
Link: http://www.andestech.com/wp-content/uploads/AX45MP-1C-Rev.-5.0.0-Datasheet.pdf

As a workaround for SoCs with IOCP disabled CMO needs to be handled by
software. Firstly OpenSBI configures the memory region as
"Memory, Non-cacheable, Bufferable" and passes this region as a global
shared dma pool as a DT node. With DMA_GLOBAL_POOL enabled all DMA
allocations happen from this region and synchronization callbacks are
implemented to synchronize when doing DMA transactions.

Example PMA region passes as a DT node from OpenSBI:
    reserved-memory {
        #address-cells = <2>;
        #size-cells = <2>;
        ranges;

        pma_resv0@58000000 {
            compatible = "shared-dma-pool";
            reg = <0x0 0x58000000 0x0 0x08000000>;
            no-map;
            linux,dma-default;
        };
    };

Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Tested-by: Conor Dooley <conor.dooley@microchip.com> # tyre-kicking on a d1
Link: https://lore.kernel.org/r/20230818135723.80612-6-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 MAINTAINERS                  |   7 ++
 drivers/Kconfig              |   2 +
 drivers/Makefile             |   1 +
 drivers/cache/Kconfig        |  11 ++
 drivers/cache/Makefile       |   3 +
 drivers/cache/ax45mp_cache.c | 213 +++++++++++++++++++++++++++++++++++
 6 files changed, 237 insertions(+)
 create mode 100644 drivers/cache/Kconfig
 create mode 100644 drivers/cache/Makefile
 create mode 100644 drivers/cache/ax45mp_cache.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 3be1bdfe8ecc..7f3abc958bbc 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -20241,6 +20241,13 @@ S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging.git
 F:	drivers/staging/
 
+STANDALONE CACHE CONTROLLER DRIVERS
+M:	Conor Dooley <conor@kernel.org>
+L:	linux-riscv@lists.infradead.org
+S:	Maintained
+T:	git https://git.kernel.org/pub/scm/linux/kernel/git/conor/linux.git/
+F:	drivers/cache
+
 STARFIRE/DURALAN NETWORK DRIVER
 M:	Ion Badulescu <ionut@badula.org>
 S:	Odd Fixes
diff --git a/drivers/Kconfig b/drivers/Kconfig
index 514ae6b24cb2..2ae1b6707c2c 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -15,6 +15,8 @@ source "drivers/base/Kconfig"
 
 source "drivers/bus/Kconfig"
 
+source "drivers/cache/Kconfig"
+
 source "drivers/connector/Kconfig"
 
 source "drivers/firmware/Kconfig"
diff --git a/drivers/Makefile b/drivers/Makefile
index 7241d80a7b29..23eb201fe18a 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -11,6 +11,7 @@ ifdef building_out_of_srctree
 MAKEFLAGS += --include-dir=$(srctree)
 endif
 
+obj-y				+= cache/
 obj-y				+= irqchip/
 obj-y				+= bus/
 
diff --git a/drivers/cache/Kconfig b/drivers/cache/Kconfig
new file mode 100644
index 000000000000..a57677f908f3
--- /dev/null
+++ b/drivers/cache/Kconfig
@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0
+menu "Cache Drivers"
+
+config AX45MP_L2_CACHE
+	bool "Andes Technology AX45MP L2 Cache controller"
+	depends on RISCV_DMA_NONCOHERENT
+	select RISCV_NONSTANDARD_CACHE_OPS
+	help
+	  Support for the L2 cache controller on Andes Technology AX45MP platforms.
+
+endmenu
diff --git a/drivers/cache/Makefile b/drivers/cache/Makefile
new file mode 100644
index 000000000000..2012e7fb978d
--- /dev/null
+++ b/drivers/cache/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_AX45MP_L2_CACHE) += ax45mp_cache.o
diff --git a/drivers/cache/ax45mp_cache.c b/drivers/cache/ax45mp_cache.c
new file mode 100644
index 000000000000..57186c58dc84
--- /dev/null
+++ b/drivers/cache/ax45mp_cache.c
@@ -0,0 +1,213 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * non-coherent cache functions for Andes AX45MP
+ *
+ * Copyright (C) 2023 Renesas Electronics Corp.
+ */
+
+#include <linux/cacheflush.h>
+#include <linux/cacheinfo.h>
+#include <linux/dma-direction.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+
+#include <asm/dma-noncoherent.h>
+
+/* L2 cache registers */
+#define AX45MP_L2C_REG_CTL_OFFSET		0x8
+
+#define AX45MP_L2C_REG_C0_CMD_OFFSET		0x40
+#define AX45MP_L2C_REG_C0_ACC_OFFSET		0x48
+#define AX45MP_L2C_REG_STATUS_OFFSET		0x80
+
+/* D-cache operation */
+#define AX45MP_CCTL_L1D_VA_INVAL		0 /* Invalidate an L1 cache entry */
+#define AX45MP_CCTL_L1D_VA_WB			1 /* Write-back an L1 cache entry */
+
+/* L2 CCTL status */
+#define AX45MP_CCTL_L2_STATUS_IDLE		0
+
+/* L2 CCTL status cores mask */
+#define AX45MP_CCTL_L2_STATUS_C0_MASK		0xf
+
+/* L2 cache operation */
+#define AX45MP_CCTL_L2_PA_INVAL			0x8 /* Invalidate an L2 cache entry */
+#define AX45MP_CCTL_L2_PA_WB			0x9 /* Write-back an L2 cache entry */
+
+#define AX45MP_L2C_REG_PER_CORE_OFFSET		0x10
+#define AX45MP_CCTL_L2_STATUS_PER_CORE_OFFSET	4
+
+#define AX45MP_L2C_REG_CN_CMD_OFFSET(n)	\
+	(AX45MP_L2C_REG_C0_CMD_OFFSET + ((n) * AX45MP_L2C_REG_PER_CORE_OFFSET))
+#define AX45MP_L2C_REG_CN_ACC_OFFSET(n)	\
+	(AX45MP_L2C_REG_C0_ACC_OFFSET + ((n) * AX45MP_L2C_REG_PER_CORE_OFFSET))
+#define AX45MP_CCTL_L2_STATUS_CN_MASK(n)	\
+	(AX45MP_CCTL_L2_STATUS_C0_MASK << ((n) * AX45MP_CCTL_L2_STATUS_PER_CORE_OFFSET))
+
+#define AX45MP_CCTL_REG_UCCTLBEGINADDR_NUM	0x80b
+#define AX45MP_CCTL_REG_UCCTLCOMMAND_NUM	0x80c
+
+#define AX45MP_CACHE_LINE_SIZE			64
+
+struct ax45mp_priv {
+	void __iomem *l2c_base;
+	u32 ax45mp_cache_line_size;
+};
+
+static struct ax45mp_priv ax45mp_priv;
+
+/* L2 Cache operations */
+static inline uint32_t ax45mp_cpu_l2c_get_cctl_status(void)
+{
+	return readl(ax45mp_priv.l2c_base + AX45MP_L2C_REG_STATUS_OFFSET);
+}
+
+static void ax45mp_cpu_cache_operation(unsigned long start, unsigned long end,
+				       unsigned int l1_op, unsigned int l2_op)
+{
+	unsigned long line_size = ax45mp_priv.ax45mp_cache_line_size;
+	void __iomem *base = ax45mp_priv.l2c_base;
+	int mhartid = smp_processor_id();
+	unsigned long pa;
+
+	while (end > start) {
+		csr_write(AX45MP_CCTL_REG_UCCTLBEGINADDR_NUM, start);
+		csr_write(AX45MP_CCTL_REG_UCCTLCOMMAND_NUM, l1_op);
+
+		pa = virt_to_phys((void *)start);
+		writel(pa, base + AX45MP_L2C_REG_CN_ACC_OFFSET(mhartid));
+		writel(l2_op, base + AX45MP_L2C_REG_CN_CMD_OFFSET(mhartid));
+		while ((ax45mp_cpu_l2c_get_cctl_status() &
+			AX45MP_CCTL_L2_STATUS_CN_MASK(mhartid)) !=
+			AX45MP_CCTL_L2_STATUS_IDLE)
+			;
+
+		start += line_size;
+	}
+}
+
+/* Write-back L1 and L2 cache entry */
+static inline void ax45mp_cpu_dcache_wb_range(unsigned long start, unsigned long end)
+{
+	ax45mp_cpu_cache_operation(start, end, AX45MP_CCTL_L1D_VA_WB,
+				   AX45MP_CCTL_L2_PA_WB);
+}
+
+/* Invalidate the L1 and L2 cache entry */
+static inline void ax45mp_cpu_dcache_inval_range(unsigned long start, unsigned long end)
+{
+	ax45mp_cpu_cache_operation(start, end, AX45MP_CCTL_L1D_VA_INVAL,
+				   AX45MP_CCTL_L2_PA_INVAL);
+}
+
+static void ax45mp_dma_cache_inv(phys_addr_t paddr, size_t size)
+{
+	unsigned long start = (unsigned long)phys_to_virt(paddr);
+	unsigned long end = start + size;
+	unsigned long line_size;
+	unsigned long flags;
+
+	if (unlikely(start == end))
+		return;
+
+	line_size = ax45mp_priv.ax45mp_cache_line_size;
+
+	start = start & (~(line_size - 1));
+	end = ((end + line_size - 1) & (~(line_size - 1)));
+
+	local_irq_save(flags);
+
+	ax45mp_cpu_dcache_inval_range(start, end);
+
+	local_irq_restore(flags);
+}
+
+static void ax45mp_dma_cache_wback(phys_addr_t paddr, size_t size)
+{
+	unsigned long start = (unsigned long)phys_to_virt(paddr);
+	unsigned long end = start + size;
+	unsigned long line_size;
+	unsigned long flags;
+
+	line_size = ax45mp_priv.ax45mp_cache_line_size;
+	start = start & (~(line_size - 1));
+	local_irq_save(flags);
+	ax45mp_cpu_dcache_wb_range(start, end);
+	local_irq_restore(flags);
+}
+
+static void ax45mp_dma_cache_wback_inv(phys_addr_t paddr, size_t size)
+{
+	ax45mp_dma_cache_wback(paddr, size);
+	ax45mp_dma_cache_inv(paddr, size);
+}
+
+static int ax45mp_get_l2_line_size(struct device_node *np)
+{
+	int ret;
+
+	ret = of_property_read_u32(np, "cache-line-size", &ax45mp_priv.ax45mp_cache_line_size);
+	if (ret) {
+		pr_err("Failed to get cache-line-size, defaulting to 64 bytes\n");
+		return ret;
+	}
+
+	if (ax45mp_priv.ax45mp_cache_line_size != AX45MP_CACHE_LINE_SIZE) {
+		pr_err("Expected cache-line-size to be 64 bytes (found:%u)\n",
+		       ax45mp_priv.ax45mp_cache_line_size);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static const struct riscv_nonstd_cache_ops ax45mp_cmo_ops __initdata = {
+	.wback = &ax45mp_dma_cache_wback,
+	.inv = &ax45mp_dma_cache_inv,
+	.wback_inv = &ax45mp_dma_cache_wback_inv,
+};
+
+static const struct of_device_id ax45mp_cache_ids[] = {
+	{ .compatible = "andestech,ax45mp-cache" },
+	{ /* sentinel */ }
+};
+
+static int __init ax45mp_cache_init(void)
+{
+	struct device_node *np;
+	struct resource res;
+	int ret;
+
+	np = of_find_matching_node(NULL, ax45mp_cache_ids);
+	if (!of_device_is_available(np))
+		return -ENODEV;
+
+	ret = of_address_to_resource(np, 0, &res);
+	if (ret)
+		return ret;
+
+	/*
+	 * If IOCP is present on the Andes AX45MP core riscv_cbom_block_size
+	 * will be 0 for sure, so we can definitely rely on it. If
+	 * riscv_cbom_block_size = 0 we don't need to handle CMO using SW any
+	 * more so we just return success here and only if its being set we
+	 * continue further in the probe path.
+	 */
+	if (!riscv_cbom_block_size)
+		return 0;
+
+	ax45mp_priv.l2c_base = ioremap(res.start, resource_size(&res));
+	if (!ax45mp_priv.l2c_base)
+		return -ENOMEM;
+
+	ret = ax45mp_get_l2_line_size(np);
+	if (ret) {
+		iounmap(ax45mp_priv.l2c_base);
+		return ret;
+	}
+
+	riscv_noncoherent_register_cache_ops(&ax45mp_cmo_ops);
+
+	return 0;
+}
+early_initcall(ax45mp_cache_init);

From 484861e09f3ed8fb2e1de290d9e33fee3611b9fc Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Fri, 18 Aug 2023 14:57:23 +0100
Subject: [PATCH 0968/1189] soc: renesas: Kconfig: Select the required configs
 for RZ/Five SoC

Explicitly select the required Cache management and Errata configs
required for the RZ/Five SoC.

Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>
Tested-by: Conor Dooley <conor.dooley@microchip.com> # tyre-kicking on a d1
Link: https://lore.kernel.org/r/20230818135723.80612-7-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 drivers/soc/renesas/Kconfig | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/soc/renesas/Kconfig b/drivers/soc/renesas/Kconfig
index de31589ed054..67604f24973e 100644
--- a/drivers/soc/renesas/Kconfig
+++ b/drivers/soc/renesas/Kconfig
@@ -334,6 +334,10 @@ if RISCV
 config ARCH_R9A07G043
 	bool "RISC-V Platform support for RZ/Five"
 	select ARCH_RZG2L
+	select AX45MP_L2_CACHE
+	select DMA_GLOBAL_POOL
+	select ERRATA_ANDES
+	select ERRATA_ANDES_CMO
 	help
 	  This enables support for the Renesas RZ/Five SoC.
 

From 9300f00439743c4a34d735e1a27118eb68a1504e Mon Sep 17 00:00:00 2001
From: Andy Chiu <andy.chiu@sifive.com>
Date: Fri, 25 Aug 2023 05:02:46 +0000
Subject: [PATCH 0969/1189] RISC-V: Add ptrace support for vectors

This patch add back the ptrace support with the following fix:
 - Define NT_RISCV_CSR and re-number NT_RISCV_VECTOR to prevent
   conflicting with gdb's NT_RISCV_CSR.
 - Use struct __riscv_v_regset_state to handle ptrace requests

Since gdb does not directly include the note description header in
Linux and has already defined NT_RISCV_CSR as 0x900, we decide to
sync with gdb and renumber NT_RISCV_VECTOR to solve and prevent future
conflicts.

Fixes: 0c59922c769a ("riscv: Add ptrace vector support")
Signed-off-by: Andy Chiu <andy.chiu@sifive.com>
Link: https://lore.kernel.org/r/20230825050248.32681-1-andy.chiu@sifive.com
[Palmer: Drop the unused "size" variable in riscv_vr_set().]
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/uapi/asm/ptrace.h | 13 +++--
 arch/riscv/kernel/ptrace.c           | 79 ++++++++++++++++++++++++++++
 include/uapi/linux/elf.h             |  2 +
 3 files changed, 90 insertions(+), 4 deletions(-)

diff --git a/arch/riscv/include/uapi/asm/ptrace.h b/arch/riscv/include/uapi/asm/ptrace.h
index 283800130614..575e95bb1bc3 100644
--- a/arch/riscv/include/uapi/asm/ptrace.h
+++ b/arch/riscv/include/uapi/asm/ptrace.h
@@ -103,13 +103,18 @@ struct __riscv_v_ext_state {
 	 * In signal handler, datap will be set a correct user stack offset
 	 * and vector registers will be copied to the address of datap
 	 * pointer.
-	 *
-	 * In ptrace syscall, datap will be set to zero and the vector
-	 * registers will be copied to the address right after this
-	 * structure.
 	 */
 };
 
+struct __riscv_v_regset_state {
+	unsigned long vstart;
+	unsigned long vl;
+	unsigned long vtype;
+	unsigned long vcsr;
+	unsigned long vlenb;
+	char vreg[];
+};
+
 /*
  * According to spec: The number of bits in a single vector register,
  * VLEN >= ELEN, which must be a power of 2, and must be no greater than
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index 487303e3ef22..2afe460de16a 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -25,6 +25,9 @@ enum riscv_regset {
 #ifdef CONFIG_FPU
 	REGSET_F,
 #endif
+#ifdef CONFIG_RISCV_ISA_V
+	REGSET_V,
+#endif
 };
 
 static int riscv_gpr_get(struct task_struct *target,
@@ -81,6 +84,71 @@ static int riscv_fpr_set(struct task_struct *target,
 }
 #endif
 
+#ifdef CONFIG_RISCV_ISA_V
+static int riscv_vr_get(struct task_struct *target,
+			const struct user_regset *regset,
+			struct membuf to)
+{
+	struct __riscv_v_ext_state *vstate = &target->thread.vstate;
+	struct __riscv_v_regset_state ptrace_vstate;
+
+	if (!riscv_v_vstate_query(task_pt_regs(target)))
+		return -EINVAL;
+
+	/*
+	 * Ensure the vector registers have been saved to the memory before
+	 * copying them to membuf.
+	 */
+	if (target == current)
+		riscv_v_vstate_save(current, task_pt_regs(current));
+
+	ptrace_vstate.vstart = vstate->vstart;
+	ptrace_vstate.vl = vstate->vl;
+	ptrace_vstate.vtype = vstate->vtype;
+	ptrace_vstate.vcsr = vstate->vcsr;
+	ptrace_vstate.vlenb = vstate->vlenb;
+
+	/* Copy vector header from vstate. */
+	membuf_write(&to, &ptrace_vstate, sizeof(struct __riscv_v_regset_state));
+
+	/* Copy all the vector registers from vstate. */
+	return membuf_write(&to, vstate->datap, riscv_v_vsize);
+}
+
+static int riscv_vr_set(struct task_struct *target,
+			const struct user_regset *regset,
+			unsigned int pos, unsigned int count,
+			const void *kbuf, const void __user *ubuf)
+{
+	int ret;
+	struct __riscv_v_ext_state *vstate = &target->thread.vstate;
+	struct __riscv_v_regset_state ptrace_vstate;
+
+	if (!riscv_v_vstate_query(task_pt_regs(target)))
+		return -EINVAL;
+
+	/* Copy rest of the vstate except datap */
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ptrace_vstate, 0,
+				 sizeof(struct __riscv_v_regset_state));
+	if (unlikely(ret))
+		return ret;
+
+	if (vstate->vlenb != ptrace_vstate.vlenb)
+		return -EINVAL;
+
+	vstate->vstart = ptrace_vstate.vstart;
+	vstate->vl = ptrace_vstate.vl;
+	vstate->vtype = ptrace_vstate.vtype;
+	vstate->vcsr = ptrace_vstate.vcsr;
+
+	/* Copy all the vector registers. */
+	pos = 0;
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vstate->datap,
+				 0, riscv_v_vsize);
+	return ret;
+}
+#endif
+
 static const struct user_regset riscv_user_regset[] = {
 	[REGSET_X] = {
 		.core_note_type = NT_PRSTATUS,
@@ -100,6 +168,17 @@ static const struct user_regset riscv_user_regset[] = {
 		.set = riscv_fpr_set,
 	},
 #endif
+#ifdef CONFIG_RISCV_ISA_V
+	[REGSET_V] = {
+		.core_note_type = NT_RISCV_VECTOR,
+		.align = 16,
+		.n = ((32 * RISCV_MAX_VLENB) +
+		      sizeof(struct __riscv_v_regset_state)) / sizeof(__u32),
+		.size = sizeof(__u32),
+		.regset_get = riscv_vr_get,
+		.set = riscv_vr_set,
+	},
+#endif
 };
 
 static const struct user_regset_view riscv_user_native_view = {
diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index e0e159138331..20e285fdbc46 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -443,6 +443,8 @@ typedef struct elf64_shdr {
 #define NT_MIPS_DSP	0x800		/* MIPS DSP ASE registers */
 #define NT_MIPS_FP_MODE	0x801		/* MIPS floating-point mode */
 #define NT_MIPS_MSA	0x802		/* MIPS SIMD registers */
+#define NT_RISCV_CSR	0x900		/* RISC-V Control and Status Registers */
+#define NT_RISCV_VECTOR	0x901		/* RISC-V vector registers */
 #define NT_LOONGARCH_CPUCFG	0xa00	/* LoongArch CPU config registers */
 #define NT_LOONGARCH_CSR	0xa01	/* LoongArch control and status registers */
 #define NT_LOONGARCH_LSX	0xa02	/* LoongArch Loongson SIMD Extension registers */

From 32f5dea040ee6e3cc30ac52d23f1674fd5110d03 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 1 Sep 2023 13:59:19 -0600
Subject: [PATCH 0970/1189] io_uring/fdinfo: only print ->sq_array[] if it's
 there

If a ring is setup with IORING_SETUP_NO_SQARRAY, then we don't have
the SQ array. Don't try to dump info from it through fdinfo if that
is the case.

Reported-by: syzbot+216e2ea6e0bf4a0acdd7@syzkaller.appspotmail.com
Fixes: 2af89abda7d9 ("io_uring: add option to remove SQ indirection")
Reviewed-by: Gabriel Krisman Bertazi <krisman@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/fdinfo.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c
index 300455b4bc12..c53678875416 100644
--- a/io_uring/fdinfo.c
+++ b/io_uring/fdinfo.c
@@ -93,6 +93,8 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f)
 		struct io_uring_sqe *sqe;
 		unsigned int sq_idx;
 
+		if (ctx->flags & IORING_SETUP_NO_SQARRAY)
+			break;
 		sq_idx = READ_ONCE(ctx->sq_array[entry & sq_mask]);
 		if (sq_idx > sq_mask)
 			continue;

From e14ebde5df2ade7164b3adc3b8644d531a78a785 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Sat, 2 Sep 2023 08:10:43 +0200
Subject: [PATCH 0971/1189] ALSA: pcm: Fix error checks of default read/write
 copy ops

copy_from/to_iter() returns the actually copied bytes, and the more
correct check should be to compare with the given bytes, instead of
zero-check.

Fixes: cf393babb37a ("ALSA: pcm: Add copy ops with iov_iter")
Reported-by: Al Viro <viro@zeniv.linux.org.uk>
Closes: https://lore.kernel.org/r/20230902053044.GJ3390869@ZenIV
Link: https://lore.kernel.org/r/20230902061044.19366-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/pcm_lib.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c
index 4859fb1caec9..a11cd7d6295f 100644
--- a/sound/core/pcm_lib.c
+++ b/sound/core/pcm_lib.c
@@ -1992,8 +1992,8 @@ static int default_write_copy(struct snd_pcm_substream *substream,
 			      int channel, unsigned long hwoff,
 			      struct iov_iter *iter, unsigned long bytes)
 {
-	if (!copy_from_iter(get_dma_ptr(substream->runtime, channel, hwoff),
-			    bytes, iter))
+	if (copy_from_iter(get_dma_ptr(substream->runtime, channel, hwoff),
+			   bytes, iter) != bytes)
 		return -EFAULT;
 	return 0;
 }
@@ -2025,8 +2025,8 @@ static int default_read_copy(struct snd_pcm_substream *substream,
 			     int channel, unsigned long hwoff,
 			     struct iov_iter *iter, unsigned long bytes)
 {
-	if (!copy_to_iter(get_dma_ptr(substream->runtime, channel, hwoff),
-			  bytes, iter))
+	if (copy_to_iter(get_dma_ptr(substream->runtime, channel, hwoff),
+			 bytes, iter) != bytes)
 		return -EFAULT;
 	return 0;
 }

From 4cbc7d9cdfbed4c0ab65c3061af901fa8ec971ff Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Sat, 2 Sep 2023 08:10:44 +0200
Subject: [PATCH 0972/1189] ALSA: sb: Fix wrong argument in commented code

While rewriting the code from sockptr_t to iov_iter during the
development, I forgot to replace one place in emu8000-pcm code.  As
it's in the disabled area (with ifdef), it's never built and
overlooked.  Replace with the proper argument NULL.

Fixes: 9d0fdc602de9 ("ALSA: emu8000: Convert to generic PCM copy ops")
Reported-by: Al Viro <viro@zeniv.linux.org.uk>
Closes: https://lore.kernel.org/r/20230902053646.GK3390869@ZenIV
Link: https://lore.kernel.org/r/20230902061044.19366-2-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/isa/sb/emu8000_pcm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/isa/sb/emu8000_pcm.c b/sound/isa/sb/emu8000_pcm.c
index c05935c2edc4..9234d4fe8ada 100644
--- a/sound/isa/sb/emu8000_pcm.c
+++ b/sound/isa/sb/emu8000_pcm.c
@@ -456,7 +456,7 @@ static int emu8k_pcm_silence(struct snd_pcm_substream *subs,
 	/* convert to word unit */
 	pos = (pos << 1) + rec->loop_start[voice];
 	count <<= 1;
-	LOOP_WRITE(rec, pos, USER_SOCKPTR(NULL), count);
+	LOOP_WRITE(rec, pos, NULL, count);
 	return 0;
 }
 

From 9ea150a8d073c2f2987d7e9ea4c35856449c9cb2 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 1 Sep 2023 16:39:44 -0700
Subject: [PATCH 0973/1189] perf parse-events: Fixes relating to no_value terms

A term may have no value in which case it is assumed to have a value
of 1. It doesn't just apply to alias/event terms so change the
parse_events_term__to_strbuf assert.

Commit 99e7138eb7897aa0 ("perf tools: Fail on using multiple bits long
terms without value") made it so that no_value terms could only be for a
single bit. Prior to commit 64199ae4b8a3 ("perf parse-events: Fix
propagation of term's no_value when cloning") this missed a test case
where config1 had no_value.

Fixes: 64199ae4b8a36038 ("perf parse-events: Fix propagation of term's no_value when cloning")
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230901233949.2930562-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/parse-events.c | 2 +-
 tools/perf/util/parse-events.c  | 2 +-
 tools/perf/util/parse-events.h  | 4 ++--
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index d86076d575ed..d47f1f871164 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -2170,7 +2170,7 @@ static const struct evlist_test test__events[] = {
 
 static const struct evlist_test test__events_pmu[] = {
 	{
-		.name  = "cpu/config=10,config1,config2=3,period=1000/u",
+		.name  = "cpu/config=10,config1=1,config2=3,period=1000/u",
 		.valid = test__pmu_cpu_valid,
 		.check = test__checkevent_pmu,
 		/* 0 */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 68fe2c4ff49f..65608a3cba81 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -2607,7 +2607,7 @@ int parse_events_term__to_strbuf(struct list_head *term_list, struct strbuf *sb)
 
 		if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM)
 			if (term->no_value) {
-				assert(term->type_term == PARSE_EVENTS__TERM_TYPE_USER);
+				assert(term->val.num == 1);
 				ret = strbuf_addf(sb, "%s", term->config);
 			} else
 				ret = strbuf_addf(sb, "%s=%#"PRIx64, term->config, term->val.num);
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 855b0725c5d4..594e5d2dc67f 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -124,8 +124,8 @@ struct parse_events_term {
 	 */
 	bool weak;
 	/**
-	 * @no_value: Is there no value. TODO: this should really be part of
-	 * type_val.
+	 * @no_value: Is there no value. If a numeric term has no value then the
+	 * value is assumed to be 1. An event name also has no value.
 	 */
 	bool no_value;
 };

From fa09bc40b21a33937872c4c4cf0f266ec9fa4869 Mon Sep 17 00:00:00 2001
From: Corinna Vinschen <vinschen@redhat.com>
Date: Thu, 31 Aug 2023 14:19:13 +0200
Subject: [PATCH 0974/1189] igb: disable virtualization features on 82580

Disable virtualization features on 82580 just as on i210/i211.
This avoids that virt functions are acidentally called on 82850.

Fixes: 55cac248caa4 ("igb: Add full support for 82580 devices")
Signed-off-by: Corinna Vinschen <vinschen@redhat.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/igb/igb_main.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 1ab787ed254d..13ba9c74bd84 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -3933,8 +3933,9 @@ static void igb_probe_vfs(struct igb_adapter *adapter)
 	struct pci_dev *pdev = adapter->pdev;
 	struct e1000_hw *hw = &adapter->hw;
 
-	/* Virtualization features not supported on i210 family. */
-	if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211))
+	/* Virtualization features not supported on i210 and 82580 family. */
+	if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211) ||
+	    (hw->mac.type == e1000_82580))
 		return;
 
 	/* Of the below we really only want the effect of getting

From f5069159f32c8c943e047f22731317463c8e9b84 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Sun, 3 Sep 2023 11:24:37 -0500
Subject: [PATCH 0975/1189] ksmbd: remove experimental warning

ksmbd has made significant improvements over the past two
years and is regularly tested and used.  Remove the experimental
warning.

Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/Kconfig  | 2 +-
 fs/smb/server/server.c | 2 --
 2 files changed, 1 insertion(+), 3 deletions(-)

diff --git a/fs/smb/server/Kconfig b/fs/smb/server/Kconfig
index 793151ddd60e..cabe6a843c6a 100644
--- a/fs/smb/server/Kconfig
+++ b/fs/smb/server/Kconfig
@@ -1,5 +1,5 @@
 config SMB_SERVER
-	tristate "SMB3 server support (EXPERIMENTAL)"
+	tristate "SMB3 server support"
 	depends on INET
 	depends on MULTIUSER
 	depends on FILE_LOCKING
diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c
index 801cd0929209..5ab2f52f9b35 100644
--- a/fs/smb/server/server.c
+++ b/fs/smb/server/server.c
@@ -590,8 +590,6 @@ static int __init ksmbd_server_init(void)
 	if (ret)
 		goto err_crypto_destroy;
 
-	pr_warn_once("The ksmbd server is experimental\n");
-
 	return 0;
 
 err_crypto_destroy:

From 915d975b2ffa58a14bfcf16fafe00c41315949ff Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 31 Aug 2023 18:37:50 +0000
Subject: [PATCH 0976/1189] net: deal with integer overflows in
 kmalloc_reserve()

Blamed commit changed:
    ptr = kmalloc(size);
    if (ptr)
      size = ksize(ptr);

to:
    size = kmalloc_size_roundup(size);
    ptr = kmalloc(size);

This allowed various crash as reported by syzbot [1]
and Kyle Zeng.

Problem is that if @size is bigger than 0x80000001,
kmalloc_size_roundup(size) returns 2^32.

kmalloc_reserve() uses a 32bit variable (obj_size),
so 2^32 is truncated to 0.

kmalloc(0) returns ZERO_SIZE_PTR which is not handled by
skb allocations.

Following trace can be triggered if a netdev->mtu is set
close to 0x7fffffff

We might in the future limit netdev->mtu to more sensible
limit (like KMALLOC_MAX_SIZE).

This patch is based on a syzbot report, and also a report
and tentative fix from Kyle Zeng.

[1]
BUG: KASAN: user-memory-access in __build_skb_around net/core/skbuff.c:294 [inline]
BUG: KASAN: user-memory-access in __alloc_skb+0x3c4/0x6e8 net/core/skbuff.c:527
Write of size 32 at addr 00000000fffffd10 by task syz-executor.4/22554

CPU: 1 PID: 22554 Comm: syz-executor.4 Not tainted 6.1.39-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/03/2023
Call trace:
dump_backtrace+0x1c8/0x1f4 arch/arm64/kernel/stacktrace.c:279
show_stack+0x2c/0x3c arch/arm64/kernel/stacktrace.c:286
__dump_stack lib/dump_stack.c:88 [inline]
dump_stack_lvl+0x120/0x1a0 lib/dump_stack.c:106
print_report+0xe4/0x4b4 mm/kasan/report.c:398
kasan_report+0x150/0x1ac mm/kasan/report.c:495
kasan_check_range+0x264/0x2a4 mm/kasan/generic.c:189
memset+0x40/0x70 mm/kasan/shadow.c:44
__build_skb_around net/core/skbuff.c:294 [inline]
__alloc_skb+0x3c4/0x6e8 net/core/skbuff.c:527
alloc_skb include/linux/skbuff.h:1316 [inline]
igmpv3_newpack+0x104/0x1088 net/ipv4/igmp.c:359
add_grec+0x81c/0x1124 net/ipv4/igmp.c:534
igmpv3_send_cr net/ipv4/igmp.c:667 [inline]
igmp_ifc_timer_expire+0x1b0/0x1008 net/ipv4/igmp.c:810
call_timer_fn+0x1c0/0x9f0 kernel/time/timer.c:1474
expire_timers kernel/time/timer.c:1519 [inline]
__run_timers+0x54c/0x710 kernel/time/timer.c:1790
run_timer_softirq+0x28/0x4c kernel/time/timer.c:1803
_stext+0x380/0xfbc
____do_softirq+0x14/0x20 arch/arm64/kernel/irq.c:79
call_on_irq_stack+0x24/0x4c arch/arm64/kernel/entry.S:891
do_softirq_own_stack+0x20/0x2c arch/arm64/kernel/irq.c:84
invoke_softirq kernel/softirq.c:437 [inline]
__irq_exit_rcu+0x1c0/0x4cc kernel/softirq.c:683
irq_exit_rcu+0x14/0x78 kernel/softirq.c:695
el0_interrupt+0x7c/0x2e0 arch/arm64/kernel/entry-common.c:717
__el0_irq_handler_common+0x18/0x24 arch/arm64/kernel/entry-common.c:724
el0t_64_irq_handler+0x10/0x1c arch/arm64/kernel/entry-common.c:729
el0t_64_irq+0x1a0/0x1a4 arch/arm64/kernel/entry.S:584

Fixes: 12d6c1d3a2ad ("skbuff: Proactively round up to kmalloc bucket size")
Reported-by: syzbot <syzkaller@googlegroups.com>
Reported-by: Kyle Zeng <zengyhkyle@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 17caf4ea67da..4eaf7ed0d1f4 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -550,7 +550,7 @@ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node,
 			     bool *pfmemalloc)
 {
 	bool ret_pfmemalloc = false;
-	unsigned int obj_size;
+	size_t obj_size;
 	void *obj;
 
 	obj_size = SKB_HEAD_ALIGN(*size);
@@ -567,7 +567,13 @@ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node,
 		obj = kmem_cache_alloc_node(skb_small_head_cache, flags, node);
 		goto out;
 	}
-	*size = obj_size = kmalloc_size_roundup(obj_size);
+
+	obj_size = kmalloc_size_roundup(obj_size);
+	/* The following cast might truncate high-order bits of obj_size, this
+	 * is harmless because kmalloc(obj_size >= 2^32) will fail anyway.
+	 */
+	*size = (unsigned int)obj_size;
+
 	/*
 	 * Try a regular allocation, when that fails and we're not entitled
 	 * to the reserves, fail.

From 817c7cd2043a83a3d8147f40eea1505ac7300b62 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 31 Aug 2023 21:38:12 +0000
Subject: [PATCH 0977/1189] gve: fix frag_list chaining

gve_rx_append_frags() is able to build skbs chained with frag_list,
like GRO engine.

Problem is that shinfo->frag_list should only be used
for the head of the chain.

All other links should use skb->next pointer.

Otherwise, built skbs are not valid and can cause crashes.

Equivalent code in GRO (skb_gro_receive()) is:

    if (NAPI_GRO_CB(p)->last == p)
        skb_shinfo(p)->frag_list = skb;
    else
        NAPI_GRO_CB(p)->last->next = skb;
    NAPI_GRO_CB(p)->last = skb;

Fixes: 9b8dd5e5ea48 ("gve: DQO: Add RX path")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Bailey Forrest <bcf@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Catherine Sullivan <csully@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/google/gve/gve_rx_dqo.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
index ea0e38b4d9e9..f281e42a7ef9 100644
--- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
@@ -570,7 +570,10 @@ static int gve_rx_append_frags(struct napi_struct *napi,
 		if (!skb)
 			return -1;
 
-		skb_shinfo(rx->ctx.skb_tail)->frag_list = skb;
+		if (rx->ctx.skb_tail == rx->ctx.skb_head)
+			skb_shinfo(rx->ctx.skb_head)->frag_list = skb;
+		else
+			rx->ctx.skb_tail->next = skb;
 		rx->ctx.skb_tail = skb;
 		num_frags = 0;
 	}

From 151e887d8ff97e2e42110ffa1fb1e6a2128fb364 Mon Sep 17 00:00:00 2001
From: Liang Chen <liangchen.linux@gmail.com>
Date: Fri, 1 Sep 2023 12:09:21 +0800
Subject: [PATCH 0978/1189] veth: Fixing transmit return status for dropped
 packets

The veth_xmit function returns NETDEV_TX_OK even when packets are dropped.
This behavior leads to incorrect calculations of statistics counts, as
well as things like txq->trans_start updates.

Fixes: e314dbdc1c0d ("[NET]: Virtual ethernet device driver.")
Signed-off-by: Liang Chen <liangchen.linux@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/veth.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index d43e62ebc2fc..9c6f4f83f22b 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -344,6 +344,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
 	struct veth_rq *rq = NULL;
+	int ret = NETDEV_TX_OK;
 	struct net_device *rcv;
 	int length = skb->len;
 	bool use_napi = false;
@@ -378,11 +379,12 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 	} else {
 drop:
 		atomic64_inc(&priv->dropped);
+		ret = NET_XMIT_DROP;
 	}
 
 	rcu_read_unlock();
 
-	return NETDEV_TX_OK;
+	return ret;
 }
 
 static u64 veth_stats_tx(struct net_device *dev, u64 *packets, u64 *bytes)

From f31867d0d9d82af757c1e0178b659438f4c1ea3c Mon Sep 17 00:00:00 2001
From: Alex Henrie <alexhenrie24@gmail.com>
Date: Thu, 31 Aug 2023 22:41:27 -0600
Subject: [PATCH 0979/1189] net: ipv6/addrconf: avoid integer underflow in
 ipv6_create_tempaddr

The existing code incorrectly casted a negative value (the result of a
subtraction) to an unsigned value without checking. For example, if
/proc/sys/net/ipv6/conf/*/temp_prefered_lft was set to 1, the preferred
lifetime would jump to 4 billion seconds. On my machine and network the
shortest lifetime that avoided underflow was 3 seconds.

Fixes: 76506a986dc3 ("IPv6: fix DESYNC_FACTOR")
Signed-off-by: Alex Henrie <alexhenrie24@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 47d1dd8501b7..85cdbc252654 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1378,7 +1378,7 @@ retry:
 	 * idev->desync_factor if it's larger
 	 */
 	cnf_temp_preferred_lft = READ_ONCE(idev->cnf.temp_prefered_lft);
-	max_desync_factor = min_t(__u32,
+	max_desync_factor = min_t(long,
 				  idev->cnf.max_desync_factor,
 				  cnf_temp_preferred_lft - regen_advance);
 

From 719c5e37e99d2fd588d1c994284d17650a66354c Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Fri, 1 Sep 2023 06:53:23 +0200
Subject: [PATCH 0980/1189] net: phy: micrel: Correct bit assignments for
 phy_device flags

Previously, the defines for phy_device flags in the Micrel driver were
ambiguous in their representation. They were intended to be bit masks
but were mistakenly defined as bit positions. This led to the following
issues:

- MICREL_KSZ8_P1_ERRATA, designated for KSZ88xx switches, overlapped
  with MICREL_PHY_FXEN and MICREL_PHY_50MHZ_CLK.
- Due to this overlap, the code path for MICREL_PHY_FXEN, tailored for
  the KSZ8041 PHY, was not executed for KSZ88xx PHYs.
- Similarly, the code associated with MICREL_PHY_50MHZ_CLK wasn't
  triggered for KSZ88xx.

To rectify this, all three flags have now been explicitly converted to
use the `BIT()` macro, ensuring they are defined as bit masks and
preventing potential overlaps in the future.

Fixes: 49011e0c1555 ("net: phy: micrel: ksz886x/ksz8081: add cabletest support")
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/micrel_phy.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h
index 8bef1ab62bba..322d87255984 100644
--- a/include/linux/micrel_phy.h
+++ b/include/linux/micrel_phy.h
@@ -41,9 +41,9 @@
 #define	PHY_ID_KSZ9477		0x00221631
 
 /* struct phy_device dev_flags definitions */
-#define MICREL_PHY_50MHZ_CLK	0x00000001
-#define MICREL_PHY_FXEN		0x00000002
-#define MICREL_KSZ8_P1_ERRATA	0x00000003
+#define MICREL_PHY_50MHZ_CLK	BIT(0)
+#define MICREL_PHY_FXEN		BIT(1)
+#define MICREL_KSZ8_P1_ERRATA	BIT(2)
 
 #define MICREL_KSZ9021_EXTREG_CTRL	0xB
 #define MICREL_KSZ9021_EXTREG_DATA_WRITE	0xC

From a454d84ee20baf7bd7be90721b9821f73c7d23d9 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Fri, 1 Sep 2023 13:21:37 -0700
Subject: [PATCH 0981/1189] bpf, sockmap: Fix skb refcnt race after locking
 changes

There is a race where skb's from the sk_psock_backlog can be referenced
after userspace side has already skb_consumed() the sk_buff and its refcnt
dropped to zer0 causing use after free.

The flow is the following:

  while ((skb = skb_peek(&psock->ingress_skb))
    sk_psock_handle_Skb(psock, skb, ..., ingress)
    if (!ingress) ...
    sk_psock_skb_ingress
       sk_psock_skb_ingress_enqueue(skb)
          msg->skb = skb
          sk_psock_queue_msg(psock, msg)
    skb_dequeue(&psock->ingress_skb)

The sk_psock_queue_msg() puts the msg on the ingress_msg queue. This is
what the application reads when recvmsg() is called. An application can
read this anytime after the msg is placed on the queue. The recvmsg hook
will also read msg->skb and then after user space reads the msg will call
consume_skb(skb) on it effectively free'ing it.

But, the race is in above where backlog queue still has a reference to
the skb and calls skb_dequeue(). If the skb_dequeue happens after the
user reads and free's the skb we have a use after free.

The !ingress case does not suffer from this problem because it uses
sendmsg_*(sk, msg) which does not pass the sk_buff further down the
stack.

The following splat was observed with 'test_progs -t sockmap_listen':

  [ 1022.710250][ T2556] general protection fault, ...
  [...]
  [ 1022.712830][ T2556] Workqueue: events sk_psock_backlog
  [ 1022.713262][ T2556] RIP: 0010:skb_dequeue+0x4c/0x80
  [ 1022.713653][ T2556] Code: ...
  [...]
  [ 1022.720699][ T2556] Call Trace:
  [ 1022.720984][ T2556]  <TASK>
  [ 1022.721254][ T2556]  ? die_addr+0x32/0x80^M
  [ 1022.721589][ T2556]  ? exc_general_protection+0x25a/0x4b0
  [ 1022.722026][ T2556]  ? asm_exc_general_protection+0x22/0x30
  [ 1022.722489][ T2556]  ? skb_dequeue+0x4c/0x80
  [ 1022.722854][ T2556]  sk_psock_backlog+0x27a/0x300
  [ 1022.723243][ T2556]  process_one_work+0x2a7/0x5b0
  [ 1022.723633][ T2556]  worker_thread+0x4f/0x3a0
  [ 1022.723998][ T2556]  ? __pfx_worker_thread+0x10/0x10
  [ 1022.724386][ T2556]  kthread+0xfd/0x130
  [ 1022.724709][ T2556]  ? __pfx_kthread+0x10/0x10
  [ 1022.725066][ T2556]  ret_from_fork+0x2d/0x50
  [ 1022.725409][ T2556]  ? __pfx_kthread+0x10/0x10
  [ 1022.725799][ T2556]  ret_from_fork_asm+0x1b/0x30
  [ 1022.726201][ T2556]  </TASK>

To fix we add an skb_get() before passing the skb to be enqueued in the
engress queue. This bumps the skb->users refcnt so that consume_skb()
and kfree_skb will not immediately free the sk_buff. With this we can
be sure the skb is still around when we do the dequeue. Then we just
need to decrement the refcnt or free the skb in the backlog case which
we do by calling kfree_skb() on the ingress case as well as the sendmsg
case.

Before locking change from fixes tag we had the sock locked so we
couldn't race with user and there was no issue here.

Fixes: 799aa7f98d53e ("skmsg: Avoid lock_sock() in sk_psock_backlog()")
Reported-by: Jiri Olsa  <jolsa@kernel.org>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Xu Kuohai <xukuohai@huawei.com>
Tested-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/bpf/20230901202137.214666-1-john.fastabend@gmail.com
---
 net/core/skmsg.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index a0659fc29bcc..6c31eefbd777 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -612,12 +612,18 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb
 static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb,
 			       u32 off, u32 len, bool ingress)
 {
+	int err = 0;
+
 	if (!ingress) {
 		if (!sock_writeable(psock->sk))
 			return -EAGAIN;
 		return skb_send_sock(psock->sk, skb, off, len);
 	}
-	return sk_psock_skb_ingress(psock, skb, off, len);
+	skb_get(skb);
+	err = sk_psock_skb_ingress(psock, skb, off, len);
+	if (err < 0)
+		kfree_skb(skb);
+	return err;
 }
 
 static void sk_psock_skb_state(struct sk_psock *psock,
@@ -685,9 +691,7 @@ static void sk_psock_backlog(struct work_struct *work)
 		} while (len);
 
 		skb = skb_dequeue(&psock->ingress_skb);
-		if (!ingress) {
-			kfree_skb(skb);
-		}
+		kfree_skb(skb);
 	}
 end:
 	mutex_unlock(&psock->work_mutex);

From ee8ab74aa0c248138c14f74cc6a636e0191c410b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 1 Sep 2023 07:24:05 -0700
Subject: [PATCH 0982/1189] docs: netdev: document patchwork patch states

The patchwork states are largely self-explanatory but small
ambiguities may still come up. Document how we interpret
the states in networking.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/process/maintainer-netdev.rst | 32 ++++++++++++++++++++-
 1 file changed, 31 insertions(+), 1 deletion(-)

diff --git a/Documentation/process/maintainer-netdev.rst b/Documentation/process/maintainer-netdev.rst
index c1c732e9748b..db1b81cfba9b 100644
--- a/Documentation/process/maintainer-netdev.rst
+++ b/Documentation/process/maintainer-netdev.rst
@@ -120,7 +120,37 @@ queue for netdev:
   https://patchwork.kernel.org/project/netdevbpf/list/
 
 The "State" field will tell you exactly where things are at with your
-patch. Patches are indexed by the ``Message-ID`` header of the emails
+patch:
+
+================== =============================================================
+Patch state        Description
+================== =============================================================
+New, Under review  pending review, patch is in the maintainer’s queue for
+                   review; the two states are used interchangeably (depending on
+                   the exact co-maintainer handling patchwork at the time)
+Accepted           patch was applied to the appropriate networking tree, this is
+                   usually set automatically by the pw-bot
+Needs ACK          waiting for an ack from an area expert or testing
+Changes requested  patch has not passed the review, new revision is expected
+                   with appropriate code and commit message changes
+Rejected           patch has been rejected and new revision is not expected
+Not applicable     patch is expected to be applied outside of the networking
+                   subsystem
+Awaiting upstream  patch should be reviewed and handled by appropriate
+                   sub-maintainer, who will send it on to the networking trees;
+                   patches set to ``Awaiting upstream`` in netdev's patchwork
+                   will usually remain in this state, whether the sub-maintainer
+                   requested changes, accepted or rejected the patch
+Deferred           patch needs to be reposted later, usually due to dependency
+                   or because it was posted for a closed tree
+Superseded         new version of the patch was posted, usually set by the
+                   pw-bot
+RFC                not to be applied, usually not in maintainer’s review queue,
+                   pw-bot can automatically set patches to this state based
+                   on subject tags
+================== =============================================================
+
+Patches are indexed by the ``Message-ID`` header of the emails
 which carried them so if you have trouble finding your patch append
 the value of ``Message-ID`` to the URL above.
 

From 5245008738029135af52a2048d9fe9c4dd9be698 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 1 Sep 2023 14:17:18 -0700
Subject: [PATCH 0983/1189] docs: netdev: update the netdev infra URLs

Some corporate proxies block our current NIPA URLs because
they use a free / shady DNS domain. As suggested by Jesse
we got a new DNS entry from Konstantin - netdev.bots.linux.dev,
use it.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/process/maintainer-netdev.rst | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/process/maintainer-netdev.rst b/Documentation/process/maintainer-netdev.rst
index db1b81cfba9b..09dcf6377c27 100644
--- a/Documentation/process/maintainer-netdev.rst
+++ b/Documentation/process/maintainer-netdev.rst
@@ -98,7 +98,7 @@ If you aren't subscribed to netdev and/or are simply unsure if
 repository link above for any new networking-related commits.  You may
 also check the following website for the current status:
 
-  https://patchwork.hopto.org/net-next.html
+  https://netdev.bots.linux.dev/net-next.html
 
 The ``net`` tree continues to collect fixes for the vX.Y content, and is
 fed back to Linus at regular (~weekly) intervals.  Meaning that the
@@ -185,7 +185,7 @@ must match the MAINTAINERS entry) and a handful of senior reviewers.
 
 Bot records its activity here:
 
-  https://patchwork.hopto.org/pw-bot.html
+  https://netdev.bots.linux.dev/pw-bot.html
 
 Review timelines
 ~~~~~~~~~~~~~~~~

From 718e6b51298e0f254baca0d40ab52a00e004e014 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 1 Sep 2023 16:46:04 -0700
Subject: [PATCH 0984/1189] af_unix: Fix msg_controllen test in
 scm_pidfd_recv() for MSG_CMSG_COMPAT.

Heiko Carstens reported that SCM_PIDFD does not work with MSG_CMSG_COMPAT
because scm_pidfd_recv() always checks msg_controllen against sizeof(struct
cmsghdr).

We need to use sizeof(struct compat_cmsghdr) for the compat case.

Fixes: 5e2ff6704a27 ("scm: add SO_PASSPIDFD and SCM_PIDFD")
Reported-by: Heiko Carstens <hca@linux.ibm.com>
Closes: https://lore.kernel.org/netdev/20230901200517.8742-A-hca@linux.ibm.com/
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Tested-by: Heiko Carstens <hca@linux.ibm.com>
Reviewed-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Acked-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/scm.h | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/include/net/scm.h b/include/net/scm.h
index c5bcdf65f55c..e8c76b4be2fe 100644
--- a/include/net/scm.h
+++ b/include/net/scm.h
@@ -9,6 +9,7 @@
 #include <linux/pid.h>
 #include <linux/nsproxy.h>
 #include <linux/sched/signal.h>
+#include <net/compat.h>
 
 /* Well, we should have at least one descriptor open
  * to accept passed FDs 8)
@@ -123,14 +124,17 @@ static inline bool scm_has_secdata(struct socket *sock)
 static __inline__ void scm_pidfd_recv(struct msghdr *msg, struct scm_cookie *scm)
 {
 	struct file *pidfd_file = NULL;
-	int pidfd;
+	int len, pidfd;
 
-	/*
-	 * put_cmsg() doesn't return an error if CMSG is truncated,
+	/* put_cmsg() doesn't return an error if CMSG is truncated,
 	 * that's why we need to opencode these checks here.
 	 */
-	if ((msg->msg_controllen <= sizeof(struct cmsghdr)) ||
-	    (msg->msg_controllen - sizeof(struct cmsghdr)) < sizeof(int)) {
+	if (msg->msg_flags & MSG_CMSG_COMPAT)
+		len = sizeof(struct compat_cmsghdr) + sizeof(int);
+	else
+		len = sizeof(struct cmsghdr) + sizeof(int);
+
+	if (msg->msg_controllen < len) {
 		msg->msg_flags |= MSG_CTRUNC;
 		return;
 	}

From 0bc36c0650b21df36fbec8136add83936eaf0607 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 1 Sep 2023 17:27:05 -0700
Subject: [PATCH 0985/1189] af_unix: Fix data-races around user->unix_inflight.

user->unix_inflight is changed under spin_lock(unix_gc_lock),
but too_many_unix_fds() reads it locklessly.

Let's annotate the write/read accesses to user->unix_inflight.

BUG: KCSAN: data-race in unix_attach_fds / unix_inflight

write to 0xffffffff8546f2d0 of 8 bytes by task 44798 on cpu 1:
 unix_inflight+0x157/0x180 net/unix/scm.c:66
 unix_attach_fds+0x147/0x1e0 net/unix/scm.c:123
 unix_scm_to_skb net/unix/af_unix.c:1827 [inline]
 unix_dgram_sendmsg+0x46a/0x14f0 net/unix/af_unix.c:1950
 unix_seqpacket_sendmsg net/unix/af_unix.c:2308 [inline]
 unix_seqpacket_sendmsg+0xba/0x130 net/unix/af_unix.c:2292
 sock_sendmsg_nosec net/socket.c:725 [inline]
 sock_sendmsg+0x148/0x160 net/socket.c:748
 ____sys_sendmsg+0x4e4/0x610 net/socket.c:2494
 ___sys_sendmsg+0xc6/0x140 net/socket.c:2548
 __sys_sendmsg+0x94/0x140 net/socket.c:2577
 __do_sys_sendmsg net/socket.c:2586 [inline]
 __se_sys_sendmsg net/socket.c:2584 [inline]
 __x64_sys_sendmsg+0x45/0x50 net/socket.c:2584
 do_syscall_x64 arch/x86/entry/common.c:50 [inline]
 do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80
 entry_SYSCALL_64_after_hwframe+0x6e/0xd8

read to 0xffffffff8546f2d0 of 8 bytes by task 44814 on cpu 0:
 too_many_unix_fds net/unix/scm.c:101 [inline]
 unix_attach_fds+0x54/0x1e0 net/unix/scm.c:110
 unix_scm_to_skb net/unix/af_unix.c:1827 [inline]
 unix_dgram_sendmsg+0x46a/0x14f0 net/unix/af_unix.c:1950
 unix_seqpacket_sendmsg net/unix/af_unix.c:2308 [inline]
 unix_seqpacket_sendmsg+0xba/0x130 net/unix/af_unix.c:2292
 sock_sendmsg_nosec net/socket.c:725 [inline]
 sock_sendmsg+0x148/0x160 net/socket.c:748
 ____sys_sendmsg+0x4e4/0x610 net/socket.c:2494
 ___sys_sendmsg+0xc6/0x140 net/socket.c:2548
 __sys_sendmsg+0x94/0x140 net/socket.c:2577
 __do_sys_sendmsg net/socket.c:2586 [inline]
 __se_sys_sendmsg net/socket.c:2584 [inline]
 __x64_sys_sendmsg+0x45/0x50 net/socket.c:2584
 do_syscall_x64 arch/x86/entry/common.c:50 [inline]
 do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80
 entry_SYSCALL_64_after_hwframe+0x6e/0xd8

value changed: 0x000000000000000c -> 0x000000000000000d

Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 44814 Comm: systemd-coredum Not tainted 6.4.0-11989-g6843306689af #6
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014

Fixes: 712f4aad406b ("unix: properly account for FDs passed over unix sockets")
Reported-by: syzkaller <syzkaller@googlegroups.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Acked-by: Willy Tarreau <w@1wt.eu>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/scm.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/unix/scm.c b/net/unix/scm.c
index e9dde7176c8a..6ff628f2349f 100644
--- a/net/unix/scm.c
+++ b/net/unix/scm.c
@@ -64,7 +64,7 @@ void unix_inflight(struct user_struct *user, struct file *fp)
 		/* Paired with READ_ONCE() in wait_for_unix_gc() */
 		WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + 1);
 	}
-	user->unix_inflight++;
+	WRITE_ONCE(user->unix_inflight, user->unix_inflight + 1);
 	spin_unlock(&unix_gc_lock);
 }
 
@@ -85,7 +85,7 @@ void unix_notinflight(struct user_struct *user, struct file *fp)
 		/* Paired with READ_ONCE() in wait_for_unix_gc() */
 		WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - 1);
 	}
-	user->unix_inflight--;
+	WRITE_ONCE(user->unix_inflight, user->unix_inflight - 1);
 	spin_unlock(&unix_gc_lock);
 }
 
@@ -99,7 +99,7 @@ static inline bool too_many_unix_fds(struct task_struct *p)
 {
 	struct user_struct *user = current_user();
 
-	if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE)))
+	if (unlikely(READ_ONCE(user->unix_inflight) > task_rlimit(p, RLIMIT_NOFILE)))
 		return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN);
 	return false;
 }

From ade32bd8a738d7497ffe9743c46728db26740f78 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 1 Sep 2023 17:27:06 -0700
Subject: [PATCH 0986/1189] af_unix: Fix data-race around unix_tot_inflight.

unix_tot_inflight is changed under spin_lock(unix_gc_lock), but
unix_release_sock() reads it locklessly.

Let's use READ_ONCE() for unix_tot_inflight.

Note that the writer side was marked by commit 9d6d7f1cb67c ("af_unix:
annote lockless accesses to unix_tot_inflight & gc_in_progress")

BUG: KCSAN: data-race in unix_inflight / unix_release_sock

write (marked) to 0xffffffff871852b8 of 4 bytes by task 123 on cpu 1:
 unix_inflight+0x130/0x180 net/unix/scm.c:64
 unix_attach_fds+0x137/0x1b0 net/unix/scm.c:123
 unix_scm_to_skb net/unix/af_unix.c:1832 [inline]
 unix_dgram_sendmsg+0x46a/0x14f0 net/unix/af_unix.c:1955
 sock_sendmsg_nosec net/socket.c:724 [inline]
 sock_sendmsg+0x148/0x160 net/socket.c:747
 ____sys_sendmsg+0x4e4/0x610 net/socket.c:2493
 ___sys_sendmsg+0xc6/0x140 net/socket.c:2547
 __sys_sendmsg+0x94/0x140 net/socket.c:2576
 __do_sys_sendmsg net/socket.c:2585 [inline]
 __se_sys_sendmsg net/socket.c:2583 [inline]
 __x64_sys_sendmsg+0x45/0x50 net/socket.c:2583
 do_syscall_x64 arch/x86/entry/common.c:50 [inline]
 do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80
 entry_SYSCALL_64_after_hwframe+0x72/0xdc

read to 0xffffffff871852b8 of 4 bytes by task 4891 on cpu 0:
 unix_release_sock+0x608/0x910 net/unix/af_unix.c:671
 unix_release+0x59/0x80 net/unix/af_unix.c:1058
 __sock_release+0x7d/0x170 net/socket.c:653
 sock_close+0x19/0x30 net/socket.c:1385
 __fput+0x179/0x5e0 fs/file_table.c:321
 ____fput+0x15/0x20 fs/file_table.c:349
 task_work_run+0x116/0x1a0 kernel/task_work.c:179
 resume_user_mode_work include/linux/resume_user_mode.h:49 [inline]
 exit_to_user_mode_loop kernel/entry/common.c:171 [inline]
 exit_to_user_mode_prepare+0x174/0x180 kernel/entry/common.c:204
 __syscall_exit_to_user_mode_work kernel/entry/common.c:286 [inline]
 syscall_exit_to_user_mode+0x1a/0x30 kernel/entry/common.c:297
 do_syscall_64+0x4b/0x90 arch/x86/entry/common.c:86
 entry_SYSCALL_64_after_hwframe+0x72/0xdc

value changed: 0x00000000 -> 0x00000001

Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 4891 Comm: systemd-coredum Not tainted 6.4.0-rc5-01219-gfa0e21fa4443 #5
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014

Fixes: 9305cfa4443d ("[AF_UNIX]: Make unix_tot_inflight counter non-atomic")
Reported-by: syzkaller <syzkaller@googlegroups.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 86930a8ed012..3e8a04a13668 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -680,7 +680,7 @@ static void unix_release_sock(struct sock *sk, int embrion)
 	 *	  What the above comment does talk about? --ANK(980817)
 	 */
 
-	if (unix_tot_inflight)
+	if (READ_ONCE(unix_tot_inflight))
 		unix_gc();		/* Garbage collect fds */
 }
 

From afe8764f76346ba838d4f162883e23d2fcfaa90e Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 1 Sep 2023 17:27:07 -0700
Subject: [PATCH 0987/1189] af_unix: Fix data-races around sk->sk_shutdown.

sk->sk_shutdown is changed under unix_state_lock(sk), but
unix_dgram_sendmsg() calls two functions to read sk_shutdown locklessly.

  sock_alloc_send_pskb
  `- sock_wait_for_wmem

Let's use READ_ONCE() there.

Note that the writer side was marked by commit e1d09c2c2f57 ("af_unix:
Fix data races around sk->sk_shutdown.").

BUG: KCSAN: data-race in sock_alloc_send_pskb / unix_release_sock

write (marked) to 0xffff8880069af12c of 1 bytes by task 1 on cpu 1:
 unix_release_sock+0x75c/0x910 net/unix/af_unix.c:631
 unix_release+0x59/0x80 net/unix/af_unix.c:1053
 __sock_release+0x7d/0x170 net/socket.c:654
 sock_close+0x19/0x30 net/socket.c:1386
 __fput+0x2a3/0x680 fs/file_table.c:384
 ____fput+0x15/0x20 fs/file_table.c:412
 task_work_run+0x116/0x1a0 kernel/task_work.c:179
 resume_user_mode_work include/linux/resume_user_mode.h:49 [inline]
 exit_to_user_mode_loop kernel/entry/common.c:171 [inline]
 exit_to_user_mode_prepare+0x174/0x180 kernel/entry/common.c:204
 __syscall_exit_to_user_mode_work kernel/entry/common.c:286 [inline]
 syscall_exit_to_user_mode+0x1a/0x30 kernel/entry/common.c:297
 do_syscall_64+0x4b/0x90 arch/x86/entry/common.c:86
 entry_SYSCALL_64_after_hwframe+0x6e/0xd8

read to 0xffff8880069af12c of 1 bytes by task 28650 on cpu 0:
 sock_alloc_send_pskb+0xd2/0x620 net/core/sock.c:2767
 unix_dgram_sendmsg+0x2f8/0x14f0 net/unix/af_unix.c:1944
 unix_seqpacket_sendmsg net/unix/af_unix.c:2308 [inline]
 unix_seqpacket_sendmsg+0xba/0x130 net/unix/af_unix.c:2292
 sock_sendmsg_nosec net/socket.c:725 [inline]
 sock_sendmsg+0x148/0x160 net/socket.c:748
 ____sys_sendmsg+0x4e4/0x610 net/socket.c:2494
 ___sys_sendmsg+0xc6/0x140 net/socket.c:2548
 __sys_sendmsg+0x94/0x140 net/socket.c:2577
 __do_sys_sendmsg net/socket.c:2586 [inline]
 __se_sys_sendmsg net/socket.c:2584 [inline]
 __x64_sys_sendmsg+0x45/0x50 net/socket.c:2584
 do_syscall_x64 arch/x86/entry/common.c:50 [inline]
 do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80
 entry_SYSCALL_64_after_hwframe+0x6e/0xd8

value changed: 0x00 -> 0x03

Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 28650 Comm: systemd-coredum Not tainted 6.4.0-11989-g6843306689af #6
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzkaller <syzkaller@googlegroups.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index d3c7b53368d2..e3da7eae9338 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2747,7 +2747,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo)
 		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 		if (refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf))
 			break;
-		if (sk->sk_shutdown & SEND_SHUTDOWN)
+		if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN)
 			break;
 		if (sk->sk_err)
 			break;
@@ -2777,7 +2777,7 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
 			goto failure;
 
 		err = -EPIPE;
-		if (sk->sk_shutdown & SEND_SHUTDOWN)
+		if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN)
 			goto failure;
 
 		if (sk_wmem_alloc_get(sk) < READ_ONCE(sk->sk_sndbuf))

From b192812905e4b134f7b7994b079eb647e9d2d37e Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 1 Sep 2023 17:27:08 -0700
Subject: [PATCH 0988/1189] af_unix: Fix data race around sk->sk_err.

As with sk->sk_shutdown shown in the previous patch, sk->sk_err can be
read locklessly by unix_dgram_sendmsg().

Let's use READ_ONCE() for sk_err as well.

Note that the writer side is marked by commit cc04410af7de ("af_unix:
annotate lockless accesses to sk->sk_err").

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index e3da7eae9338..16584e2dd648 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2749,7 +2749,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo)
 			break;
 		if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN)
 			break;
-		if (sk->sk_err)
+		if (READ_ONCE(sk->sk_err))
 			break;
 		timeo = schedule_timeout(timeo);
 	}

From c87906a7d56e1f26320a6c8f6d8306656e78b353 Mon Sep 17 00:00:00 2001
From: Kevin-Lu <kevin-lu@ti.com>
Date: Mon, 4 Sep 2023 00:14:37 +0800
Subject: [PATCH 0989/1189] MAINTAINERS: Update the MAINTAINERS enties for
 TEXAS INSTRUMENTS ASoC DRIVERS

Update the MAINTAINERS email for TEXAS INSTRUMENTS ASoC DRIVERS.

Signed-off-by: Kevin-Lu <kevin-lu@ti.com>
Link: https://lore.kernel.org/r/20230903161439.85-1-kevin-lu@ti.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 3aaec9532ff9..a4735048b3d4 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -21064,7 +21064,7 @@ F:	sound/soc/ti/
 TEXAS INSTRUMENTS AUDIO (ASoC/HDA) DRIVERS
 M:	Shenghao Ding <shenghao-ding@ti.com>
 M:	Kevin Lu <kevin-lu@ti.com>
-M:	Baojun Xu <x1077012@ti.com>
+M:	Baojun Xu <baojun.xu@ti.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 S:	Maintained
 F:	Documentation/devicetree/bindings/sound/tas2552.txt

From d1cf5d30b43f1a331032ebf3e11d9e366ab0f885 Mon Sep 17 00:00:00 2001
From: Shubh <shubhisroking@gmail.com>
Date: Sat, 2 Sep 2023 20:38:07 +0530
Subject: [PATCH 0990/1189] ASoC: amd: yc: Add DMI entries to support Victus by
 HP Gaming Laptop 15-fb0xxx (8A3E)

This model requires an additional detection quirk to
enable the internal microphone.

Signed-off-by: Shubh <shubhisroking@gmail.com>
Link: https://lore.kernel.org/r/20230902150807.133523-1-shubhisroking@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/yc/acp6x-mach.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index a2fe3bd4f9a1..887188650bd6 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -318,6 +318,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "8A22"),
 		}
 	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "HP"),
+			DMI_MATCH(DMI_BOARD_NAME, "8A3E"),
+		}
+	},
 	{
 		.driver_data = &acp6x_card,
 		.matches = {

From 5366a64033ef46d7fc36db097d4bde12af22c405 Mon Sep 17 00:00:00 2001
From: Brent Lu <brent.lu@intel.com>
Date: Mon, 4 Sep 2023 18:40:46 +0800
Subject: [PATCH 0991/1189] ASoC: rt5645: NULL pointer access when removing
 jack

Machine driver calls snd_soc_component_set_jack() function with NULL
jack and data parameters when removing jack in codec exit function.
Do not access data when jack is NULL.

Signed-off-by: Brent Lu <brent.lu@intel.com>
Link: https://lore.kernel.org/r/20230904104046.4150208-1-brent.lu@intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt5645.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c
index 038d93e20883..1a137ca3f496 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -3269,13 +3269,17 @@ static int rt5645_component_set_jack(struct snd_soc_component *component,
 {
 	struct snd_soc_jack *mic_jack = NULL;
 	struct snd_soc_jack *btn_jack = NULL;
-	int *type = (int *)data;
+	int type;
 
-	if (*type & SND_JACK_MICROPHONE)
-		mic_jack = hs_jack;
-	if (*type & (SND_JACK_BTN_0 | SND_JACK_BTN_1 |
-		SND_JACK_BTN_2 | SND_JACK_BTN_3))
-		btn_jack = hs_jack;
+	if (hs_jack) {
+		type = *(int *)data;
+
+		if (type & SND_JACK_MICROPHONE)
+			mic_jack = hs_jack;
+		if (type & (SND_JACK_BTN_0 | SND_JACK_BTN_1 |
+			SND_JACK_BTN_2 | SND_JACK_BTN_3))
+			btn_jack = hs_jack;
+	}
 
 	return rt5645_set_jack_detect(component, hs_jack, mic_jack, btn_jack);
 }

From 171f8a49f212e87a8b04087568e1b3d132e36a18 Mon Sep 17 00:00:00 2001
From: Tobias Schramm <t.schramm@manjaro.org>
Date: Sun, 27 Aug 2023 17:25:57 +0200
Subject: [PATCH 0992/1189] spi: sun6i: reduce DMA RX transfer width to single
 byte

Through empirical testing it has been determined that sometimes RX SPI
transfers with DMA enabled return corrupted data. This is down to single
or even multiple bytes lost during DMA transfer from SPI peripheral to
memory. It seems the RX FIFO within the SPI peripheral can become
confused when performing bus read accesses wider than a single byte to it
during an active SPI transfer.

This patch reduces the width of individual DMA read accesses to the
RX FIFO to a single byte to mitigate that issue.

Signed-off-by: Tobias Schramm <t.schramm@manjaro.org>
Link: https://lore.kernel.org/r/20230827152558.5368-2-t.schramm@manjaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-sun6i.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/spi/spi-sun6i.c b/drivers/spi/spi-sun6i.c
index 30d541612253..8fcb2696ec09 100644
--- a/drivers/spi/spi-sun6i.c
+++ b/drivers/spi/spi-sun6i.c
@@ -207,7 +207,7 @@ static int sun6i_spi_prepare_dma(struct sun6i_spi *sspi,
 		struct dma_slave_config rxconf = {
 			.direction = DMA_DEV_TO_MEM,
 			.src_addr = sspi->dma_addr_rx,
-			.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES,
+			.src_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE,
 			.src_maxburst = 8,
 		};
 

From 1f11f4202caf5710204d334fe63392052783876d Mon Sep 17 00:00:00 2001
From: Tobias Schramm <t.schramm@manjaro.org>
Date: Sun, 27 Aug 2023 17:25:58 +0200
Subject: [PATCH 0993/1189] spi: sun6i: fix race between DMA RX transfer
 completion and RX FIFO drain

Previously the transfer complete IRQ immediately drained to RX FIFO to
read any data remaining in FIFO to the RX buffer. This behaviour is
correct when dealing with SPI in interrupt mode. However in DMA mode the
transfer complete interrupt still fires as soon as all bytes to be
transferred have been stored in the FIFO. At that point data in the FIFO
still needs to be picked up by the DMA engine. Thus the drain procedure
and DMA engine end up racing to read from RX FIFO, corrupting any data
read. Additionally the RX buffer pointer is never adjusted according to
DMA progress in DMA mode, thus calling the RX FIFO drain procedure in DMA
mode is a bug.
Fix corruptions in DMA RX mode by draining RX FIFO only in interrupt mode.
Also wait for completion of RX DMA when in DMA mode before returning to
ensure all data has been copied to the supplied memory buffer.

Signed-off-by: Tobias Schramm <t.schramm@manjaro.org>
Link: https://lore.kernel.org/r/20230827152558.5368-3-t.schramm@manjaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-sun6i.c | 29 ++++++++++++++++++++++++++++-
 1 file changed, 28 insertions(+), 1 deletion(-)

diff --git a/drivers/spi/spi-sun6i.c b/drivers/spi/spi-sun6i.c
index 8fcb2696ec09..57c828e73c44 100644
--- a/drivers/spi/spi-sun6i.c
+++ b/drivers/spi/spi-sun6i.c
@@ -102,6 +102,7 @@ struct sun6i_spi {
 	struct reset_control	*rstc;
 
 	struct completion	done;
+	struct completion	dma_rx_done;
 
 	const u8		*tx_buf;
 	u8			*rx_buf;
@@ -196,6 +197,13 @@ static size_t sun6i_spi_max_transfer_size(struct spi_device *spi)
 	return SUN6I_MAX_XFER_SIZE - 1;
 }
 
+static void sun6i_spi_dma_rx_cb(void *param)
+{
+	struct sun6i_spi *sspi = param;
+
+	complete(&sspi->dma_rx_done);
+}
+
 static int sun6i_spi_prepare_dma(struct sun6i_spi *sspi,
 				 struct spi_transfer *tfr)
 {
@@ -220,6 +228,8 @@ static int sun6i_spi_prepare_dma(struct sun6i_spi *sspi,
 						 DMA_PREP_INTERRUPT);
 		if (!rxdesc)
 			return -EINVAL;
+		rxdesc->callback_param = sspi;
+		rxdesc->callback = sun6i_spi_dma_rx_cb;
 	}
 
 	txdesc = NULL;
@@ -275,6 +285,7 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 		return -EINVAL;
 
 	reinit_completion(&sspi->done);
+	reinit_completion(&sspi->dma_rx_done);
 	sspi->tx_buf = tfr->tx_buf;
 	sspi->rx_buf = tfr->rx_buf;
 	sspi->len = tfr->len;
@@ -459,6 +470,22 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 	start = jiffies;
 	timeout = wait_for_completion_timeout(&sspi->done,
 					      msecs_to_jiffies(tx_time));
+
+	if (!use_dma) {
+		sun6i_spi_drain_fifo(sspi);
+	} else {
+		if (timeout && rx_len) {
+			/*
+			 * Even though RX on the peripheral side has finished
+			 * RX DMA might still be in flight
+			 */
+			timeout = wait_for_completion_timeout(&sspi->dma_rx_done,
+							      timeout);
+			if (!timeout)
+				dev_warn(&master->dev, "RX DMA timeout\n");
+		}
+	}
+
 	end = jiffies;
 	if (!timeout) {
 		dev_warn(&master->dev,
@@ -486,7 +513,6 @@ static irqreturn_t sun6i_spi_handler(int irq, void *dev_id)
 	/* Transfer complete */
 	if (status & SUN6I_INT_CTL_TC) {
 		sun6i_spi_write(sspi, SUN6I_INT_STA_REG, SUN6I_INT_CTL_TC);
-		sun6i_spi_drain_fifo(sspi);
 		complete(&sspi->done);
 		return IRQ_HANDLED;
 	}
@@ -644,6 +670,7 @@ static int sun6i_spi_probe(struct platform_device *pdev)
 	}
 
 	init_completion(&sspi->done);
+	init_completion(&sspi->dma_rx_done);
 
 	sspi->rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL);
 	if (IS_ERR(sspi->rstc)) {

From 3f874c9b2aae8e30463efc1872bea4baa9ed25dc Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 9 Aug 2023 20:52:20 +0200
Subject: [PATCH 0994/1189] x86/smp: Don't send INIT to non-present and
 non-booted CPUs

Vasant reported that kexec() can hang or reset the machine when it tries to
park CPUs via INIT. This happens when the kernel is using extended APIC,
but the present mask has APIC IDs >= 0x100 enumerated.

As extended APIC can only handle 8 bit of APIC ID sending INIT to APIC ID
0x100 sends INIT to APIC ID 0x0. That's the boot CPU which is special on
x86 and INIT causes the system to hang or resets the machine.

Prevent this by sending INIT only to those CPUs which have been booted
once.

Fixes: 45e34c8af58f ("x86/smp: Put CPUs into INIT on shutdown if possible")
Reported-by: Dheeraj Kumar Srivastava <dheerajkumar.srivastava@amd.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Vasant Hegde <vasant.hegde@amd.com>
Link: https://lore.kernel.org/r/87cyzwjbff.ffs@tglx
---
 arch/x86/kernel/smpboot.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index d7667a29acf3..4e45ff44aa07 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1250,7 +1250,7 @@ bool smp_park_other_cpus_in_init(void)
 	if (this_cpu)
 		return false;
 
-	for_each_present_cpu(cpu) {
+	for_each_cpu_and(cpu, &cpus_booted_once_mask, cpu_present_mask) {
 		if (cpu == this_cpu)
 			continue;
 		apicid = apic->cpu_present_to_apicid(cpu);

From 99bf5b0baac941176a6a3d5cef7705b29808de34 Mon Sep 17 00:00:00 2001
From: Vitaly Rodionov <vitalyr@opensource.cirrus.com>
Date: Mon, 4 Sep 2023 17:00:33 +0100
Subject: [PATCH 0995/1189] ALSA: hda/cirrus: Fix broken audio on hardware with
 two CS42L42 codecs.

Recently in v6.3-rc1 there was a change affecting behaviour of hrtimers
(commit 0c52310f260014d95c1310364379772cb74cf82d) and causing
few issues on platforms with two CS42L42 codecs. Canonical/Dell
has reported an issue with Vostro-3910.
We need to increase this value by 15ms.

Link: https://bugs.launchpad.net/somerville/+bug/2031060
Fixes: 9fb9fa18fb50 ("ALSA: hda/cirrus: Add extra 10 ms delay to allow PLL settle and lock.")
Signed-off-by: Vitaly Rodionov <vitalyr@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20230904160033.908135-1-vitalyr@opensource.cirrus.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_cs8409.c | 2 +-
 sound/pci/hda/patch_cs8409.h | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/sound/pci/hda/patch_cs8409.c b/sound/pci/hda/patch_cs8409.c
index 0ba1fbcbb21e..627899959ffe 100644
--- a/sound/pci/hda/patch_cs8409.c
+++ b/sound/pci/hda/patch_cs8409.c
@@ -888,7 +888,7 @@ static void cs42l42_resume(struct sub_codec *cs42l42)
 
 	/* Initialize CS42L42 companion codec */
 	cs8409_i2c_bulk_write(cs42l42, cs42l42->init_seq, cs42l42->init_seq_num);
-	usleep_range(30000, 35000);
+	msleep(CS42L42_INIT_TIMEOUT_MS);
 
 	/* Clear interrupts, by reading interrupt status registers */
 	cs8409_i2c_bulk_read(cs42l42, irq_regs, ARRAY_SIZE(irq_regs));
diff --git a/sound/pci/hda/patch_cs8409.h b/sound/pci/hda/patch_cs8409.h
index 2a8dfb4ff046..937e9387abdc 100644
--- a/sound/pci/hda/patch_cs8409.h
+++ b/sound/pci/hda/patch_cs8409.h
@@ -229,6 +229,7 @@ enum cs8409_coefficient_index_registers {
 #define CS42L42_I2C_SLEEP_US			(2000)
 #define CS42L42_PDN_TIMEOUT_US			(250000)
 #define CS42L42_PDN_SLEEP_US			(2000)
+#define CS42L42_INIT_TIMEOUT_MS			(45)
 #define CS42L42_FULL_SCALE_VOL_MASK		(2)
 #define CS42L42_FULL_SCALE_VOL_0DB		(1)
 #define CS42L42_FULL_SCALE_VOL_MINUS6DB		(0)

From 8fc134fee27f2263988ae38920bc03da416b03d8 Mon Sep 17 00:00:00 2001
From: valis <sec@valis.email>
Date: Fri, 1 Sep 2023 12:22:37 -0400
Subject: [PATCH 0996/1189] net: sched: sch_qfq: Fix UAF in qfq_dequeue()

When the plug qdisc is used as a class of the qfq qdisc it could trigger a
UAF. This issue can be reproduced with following commands:

  tc qdisc add dev lo root handle 1: qfq
  tc class add dev lo parent 1: classid 1:1 qfq weight 1 maxpkt 512
  tc qdisc add dev lo parent 1:1 handle 2: plug
  tc filter add dev lo parent 1: basic classid 1:1
  ping -c1 127.0.0.1

and boom:

[  285.353793] BUG: KASAN: slab-use-after-free in qfq_dequeue+0xa7/0x7f0
[  285.354910] Read of size 4 at addr ffff8880bad312a8 by task ping/144
[  285.355903]
[  285.356165] CPU: 1 PID: 144 Comm: ping Not tainted 6.5.0-rc3+ #4
[  285.357112] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014
[  285.358376] Call Trace:
[  285.358773]  <IRQ>
[  285.359109]  dump_stack_lvl+0x44/0x60
[  285.359708]  print_address_description.constprop.0+0x2c/0x3c0
[  285.360611]  kasan_report+0x10c/0x120
[  285.361195]  ? qfq_dequeue+0xa7/0x7f0
[  285.361780]  qfq_dequeue+0xa7/0x7f0
[  285.362342]  __qdisc_run+0xf1/0x970
[  285.362903]  net_tx_action+0x28e/0x460
[  285.363502]  __do_softirq+0x11b/0x3de
[  285.364097]  do_softirq.part.0+0x72/0x90
[  285.364721]  </IRQ>
[  285.365072]  <TASK>
[  285.365422]  __local_bh_enable_ip+0x77/0x90
[  285.366079]  __dev_queue_xmit+0x95f/0x1550
[  285.366732]  ? __pfx_csum_and_copy_from_iter+0x10/0x10
[  285.367526]  ? __pfx___dev_queue_xmit+0x10/0x10
[  285.368259]  ? __build_skb_around+0x129/0x190
[  285.368960]  ? ip_generic_getfrag+0x12c/0x170
[  285.369653]  ? __pfx_ip_generic_getfrag+0x10/0x10
[  285.370390]  ? csum_partial+0x8/0x20
[  285.370961]  ? raw_getfrag+0xe5/0x140
[  285.371559]  ip_finish_output2+0x539/0xa40
[  285.372222]  ? __pfx_ip_finish_output2+0x10/0x10
[  285.372954]  ip_output+0x113/0x1e0
[  285.373512]  ? __pfx_ip_output+0x10/0x10
[  285.374130]  ? icmp_out_count+0x49/0x60
[  285.374739]  ? __pfx_ip_finish_output+0x10/0x10
[  285.375457]  ip_push_pending_frames+0xf3/0x100
[  285.376173]  raw_sendmsg+0xef5/0x12d0
[  285.376760]  ? do_syscall_64+0x40/0x90
[  285.377359]  ? __static_call_text_end+0x136578/0x136578
[  285.378173]  ? do_syscall_64+0x40/0x90
[  285.378772]  ? kasan_enable_current+0x11/0x20
[  285.379469]  ? __pfx_raw_sendmsg+0x10/0x10
[  285.380137]  ? __sock_create+0x13e/0x270
[  285.380673]  ? __sys_socket+0xf3/0x180
[  285.381174]  ? __x64_sys_socket+0x3d/0x50
[  285.381725]  ? entry_SYSCALL_64_after_hwframe+0x6e/0xd8
[  285.382425]  ? __rcu_read_unlock+0x48/0x70
[  285.382975]  ? ip4_datagram_release_cb+0xd8/0x380
[  285.383608]  ? __pfx_ip4_datagram_release_cb+0x10/0x10
[  285.384295]  ? preempt_count_sub+0x14/0xc0
[  285.384844]  ? __list_del_entry_valid+0x76/0x140
[  285.385467]  ? _raw_spin_lock_bh+0x87/0xe0
[  285.386014]  ? __pfx__raw_spin_lock_bh+0x10/0x10
[  285.386645]  ? release_sock+0xa0/0xd0
[  285.387148]  ? preempt_count_sub+0x14/0xc0
[  285.387712]  ? freeze_secondary_cpus+0x348/0x3c0
[  285.388341]  ? aa_sk_perm+0x177/0x390
[  285.388856]  ? __pfx_aa_sk_perm+0x10/0x10
[  285.389441]  ? check_stack_object+0x22/0x70
[  285.390032]  ? inet_send_prepare+0x2f/0x120
[  285.390603]  ? __pfx_inet_sendmsg+0x10/0x10
[  285.391172]  sock_sendmsg+0xcc/0xe0
[  285.391667]  __sys_sendto+0x190/0x230
[  285.392168]  ? __pfx___sys_sendto+0x10/0x10
[  285.392727]  ? kvm_clock_get_cycles+0x14/0x30
[  285.393328]  ? set_normalized_timespec64+0x57/0x70
[  285.393980]  ? _raw_spin_unlock_irq+0x1b/0x40
[  285.394578]  ? __x64_sys_clock_gettime+0x11c/0x160
[  285.395225]  ? __pfx___x64_sys_clock_gettime+0x10/0x10
[  285.395908]  ? _copy_to_user+0x3e/0x60
[  285.396432]  ? exit_to_user_mode_prepare+0x1a/0x120
[  285.397086]  ? syscall_exit_to_user_mode+0x22/0x50
[  285.397734]  ? do_syscall_64+0x71/0x90
[  285.398258]  __x64_sys_sendto+0x74/0x90
[  285.398786]  do_syscall_64+0x64/0x90
[  285.399273]  ? exit_to_user_mode_prepare+0x1a/0x120
[  285.399949]  ? syscall_exit_to_user_mode+0x22/0x50
[  285.400605]  ? do_syscall_64+0x71/0x90
[  285.401124]  entry_SYSCALL_64_after_hwframe+0x6e/0xd8
[  285.401807] RIP: 0033:0x495726
[  285.402233] Code: ff ff ff f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b8 0f 1f 00 41 89 ca 64 8b 04 25 18 00 00 00 85 c0 75 11 b8 2c 00 00 00 0f 09
[  285.404683] RSP: 002b:00007ffcc25fb618 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
[  285.405677] RAX: ffffffffffffffda RBX: 0000000000000040 RCX: 0000000000495726
[  285.406628] RDX: 0000000000000040 RSI: 0000000002518750 RDI: 0000000000000000
[  285.407565] RBP: 00000000005205ef R08: 00000000005f8838 R09: 000000000000001c
[  285.408523] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000002517634
[  285.409460] R13: 00007ffcc25fb6f0 R14: 0000000000000003 R15: 0000000000000000
[  285.410403]  </TASK>
[  285.410704]
[  285.410929] Allocated by task 144:
[  285.411402]  kasan_save_stack+0x1e/0x40
[  285.411926]  kasan_set_track+0x21/0x30
[  285.412442]  __kasan_slab_alloc+0x55/0x70
[  285.412973]  kmem_cache_alloc_node+0x187/0x3d0
[  285.413567]  __alloc_skb+0x1b4/0x230
[  285.414060]  __ip_append_data+0x17f7/0x1b60
[  285.414633]  ip_append_data+0x97/0xf0
[  285.415144]  raw_sendmsg+0x5a8/0x12d0
[  285.415640]  sock_sendmsg+0xcc/0xe0
[  285.416117]  __sys_sendto+0x190/0x230
[  285.416626]  __x64_sys_sendto+0x74/0x90
[  285.417145]  do_syscall_64+0x64/0x90
[  285.417624]  entry_SYSCALL_64_after_hwframe+0x6e/0xd8
[  285.418306]
[  285.418531] Freed by task 144:
[  285.418960]  kasan_save_stack+0x1e/0x40
[  285.419469]  kasan_set_track+0x21/0x30
[  285.419988]  kasan_save_free_info+0x27/0x40
[  285.420556]  ____kasan_slab_free+0x109/0x1a0
[  285.421146]  kmem_cache_free+0x1c2/0x450
[  285.421680]  __netif_receive_skb_core+0x2ce/0x1870
[  285.422333]  __netif_receive_skb_one_core+0x97/0x140
[  285.423003]  process_backlog+0x100/0x2f0
[  285.423537]  __napi_poll+0x5c/0x2d0
[  285.424023]  net_rx_action+0x2be/0x560
[  285.424510]  __do_softirq+0x11b/0x3de
[  285.425034]
[  285.425254] The buggy address belongs to the object at ffff8880bad31280
[  285.425254]  which belongs to the cache skbuff_head_cache of size 224
[  285.426993] The buggy address is located 40 bytes inside of
[  285.426993]  freed 224-byte region [ffff8880bad31280, ffff8880bad31360)
[  285.428572]
[  285.428798] The buggy address belongs to the physical page:
[  285.429540] page:00000000f4b77674 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0xbad31
[  285.430758] flags: 0x100000000000200(slab|node=0|zone=1)
[  285.431447] page_type: 0xffffffff()
[  285.431934] raw: 0100000000000200 ffff88810094a8c0 dead000000000122 0000000000000000
[  285.432757] raw: 0000000000000000 00000000800c000c 00000001ffffffff 0000000000000000
[  285.433562] page dumped because: kasan: bad access detected
[  285.434144]
[  285.434320] Memory state around the buggy address:
[  285.434828]  ffff8880bad31180: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[  285.435580]  ffff8880bad31200: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[  285.436264] >ffff8880bad31280: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  285.436777]                                   ^
[  285.437106]  ffff8880bad31300: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc
[  285.437616]  ffff8880bad31380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[  285.438126] ==================================================================
[  285.438662] Disabling lock debugging due to kernel taint

Fix this by:
1. Changing sch_plug's .peek handler to qdisc_peek_dequeued(), a
function compatible with non-work-conserving qdiscs
2. Checking the return value of qdisc_dequeue_peeked() in sch_qfq.

Fixes: 462dbc9101ac ("pkt_sched: QFQ Plus: fair-queueing service at DRR cost")
Reported-by: valis <sec@valis.email>
Signed-off-by: valis <sec@valis.email>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://lore.kernel.org/r/20230901162237.11525-1-jhs@mojatatu.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/sched/sch_plug.c |  2 +-
 net/sched/sch_qfq.c  | 22 +++++++++++++++++-----
 2 files changed, 18 insertions(+), 6 deletions(-)

diff --git a/net/sched/sch_plug.c b/net/sched/sch_plug.c
index ea8c4a7174bb..35f49edf63db 100644
--- a/net/sched/sch_plug.c
+++ b/net/sched/sch_plug.c
@@ -207,7 +207,7 @@ static struct Qdisc_ops plug_qdisc_ops __read_mostly = {
 	.priv_size   =       sizeof(struct plug_sched_data),
 	.enqueue     =       plug_enqueue,
 	.dequeue     =       plug_dequeue,
-	.peek        =       qdisc_peek_head,
+	.peek        =       qdisc_peek_dequeued,
 	.init        =       plug_init,
 	.change      =       plug_change,
 	.reset       =	     qdisc_reset_queue,
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 1a25752f1a9a..546c10adcacd 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -974,10 +974,13 @@ static void qfq_update_eligible(struct qfq_sched *q)
 }
 
 /* Dequeue head packet of the head class in the DRR queue of the aggregate. */
-static void agg_dequeue(struct qfq_aggregate *agg,
-			struct qfq_class *cl, unsigned int len)
+static struct sk_buff *agg_dequeue(struct qfq_aggregate *agg,
+				   struct qfq_class *cl, unsigned int len)
 {
-	qdisc_dequeue_peeked(cl->qdisc);
+	struct sk_buff *skb = qdisc_dequeue_peeked(cl->qdisc);
+
+	if (!skb)
+		return NULL;
 
 	cl->deficit -= (int) len;
 
@@ -987,6 +990,8 @@ static void agg_dequeue(struct qfq_aggregate *agg,
 		cl->deficit += agg->lmax;
 		list_move_tail(&cl->alist, &agg->active);
 	}
+
+	return skb;
 }
 
 static inline struct sk_buff *qfq_peek_skb(struct qfq_aggregate *agg,
@@ -1132,11 +1137,18 @@ static struct sk_buff *qfq_dequeue(struct Qdisc *sch)
 	if (!skb)
 		return NULL;
 
-	qdisc_qstats_backlog_dec(sch, skb);
 	sch->q.qlen--;
+
+	skb = agg_dequeue(in_serv_agg, cl, len);
+
+	if (!skb) {
+		sch->q.qlen++;
+		return NULL;
+	}
+
+	qdisc_qstats_backlog_dec(sch, skb);
 	qdisc_bstats_update(sch, skb);
 
-	agg_dequeue(in_serv_agg, cl, len);
 	/* If lmax is lowered, through qfq_change_class, for a class
 	 * owning pending packets with larger size than the new value
 	 * of lmax, then the following condition may hold.

From b1757fa30ef14f254f4719bf6f7d54a4c8207216 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 5 Sep 2023 07:45:11 +0200
Subject: [PATCH 0997/1189] ALSA: usb-audio: Fix potential memory leaks at
 error path for UMP open

The allocation and initialization errors at alloc_midi_urbs() that is
called at MIDI 2.0 / UMP device are supposed to be handled at the
caller side by invoking free_midi_urbs().  However, free_midi_urbs()
loops only for ep->num_urbs entries, and since ep->num_entries wasn't
updated yet at the allocation / init error in alloc_midi_urbs(), this
entry won't be released.

The intention of free_midi_urbs() is to release the whole elements, so
change the loop size to NUM_URBS to scan over all elements for fixing
the missed releases.

Also, the call of free_midi_urbs() is missing at
snd_usb_midi_v2_open().  Although it'll be released later at
reopen/close or disconnection, it's better to release immediately at
the error path.

Fixes: ff49d1df79ae ("ALSA: usb-audio: USB MIDI 2.0 UMP support")
Reported-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Closes: https://lore.kernel.org/r/fc275ed315b9157952dcf2744ee7bdb78defdb5f.1693746347.git.christophe.jaillet@wanadoo.fr
Link: https://lore.kernel.org/r/20230905054511.20502-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/midi2.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/sound/usb/midi2.c b/sound/usb/midi2.c
index a27e244650c8..1ec177fe284e 100644
--- a/sound/usb/midi2.c
+++ b/sound/usb/midi2.c
@@ -265,7 +265,7 @@ static void free_midi_urbs(struct snd_usb_midi2_endpoint *ep)
 
 	if (!ep)
 		return;
-	for (i = 0; i < ep->num_urbs; ++i) {
+	for (i = 0; i < NUM_URBS; ++i) {
 		ctx = &ep->urbs[i];
 		if (!ctx->urb)
 			break;
@@ -279,6 +279,7 @@ static void free_midi_urbs(struct snd_usb_midi2_endpoint *ep)
 }
 
 /* allocate URBs for an EP */
+/* the callers should handle allocation errors via free_midi_urbs() */
 static int alloc_midi_urbs(struct snd_usb_midi2_endpoint *ep)
 {
 	struct snd_usb_midi2_urb *ctx;
@@ -351,8 +352,10 @@ static int snd_usb_midi_v2_open(struct snd_ump_endpoint *ump, int dir)
 		return -EIO;
 	if (ep->direction == STR_OUT) {
 		err = alloc_midi_urbs(ep);
-		if (err)
+		if (err) {
+			free_midi_urbs(ep);
 			return err;
+		}
 	}
 	return 0;
 }

From 6ad40b36cd3b04209e2d6c89d252c873d8082a59 Mon Sep 17 00:00:00 2001
From: Shigeru Yoshida <syoshida@redhat.com>
Date: Sun, 3 Sep 2023 02:07:08 +0900
Subject: [PATCH 0998/1189] kcm: Destroy mutex in kcm_exit_net()

kcm_exit_net() should call mutex_destroy() on knet->mutex. This is especially
needed if CONFIG_DEBUG_MUTEXES is enabled.

Fixes: ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module")
Signed-off-by: Shigeru Yoshida <syoshida@redhat.com>
Link: https://lore.kernel.org/r/20230902170708.1727999-1-syoshida@redhat.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/kcm/kcmsock.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 393f01b2a7e6..4580f61426bb 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1859,6 +1859,8 @@ static __net_exit void kcm_exit_net(struct net *net)
 	 * that all multiplexors and psocks have been destroyed.
 	 */
 	WARN_ON(!list_empty(&knet->mux_list));
+
+	mutex_destroy(&knet->mutex);
 }
 
 static struct pernet_operations kcm_net_ops = {

From 86496fd4a2fabb7c978fdaca2d4b718207a96d36 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 5 Sep 2023 10:12:10 +0200
Subject: [PATCH 0999/1189] ALSA: seq: Fix snd_seq_expand_var_event() call to
 user-space

The recent fix to clear the padding bytes at
snd_seq_expand_var_event() broke the read to user-space with
in_kernel=0 parameter.  For user-space address, it has to use
clear_user() instead of memset().

Fixes: f80e6d60d677 ("ALSA: seq: Clear padded bytes at expanding events")
Reported-and-tested-by: Ash Holland <ash@sorrel.sh>
Closes: https://lore.kernel.org/r/8a555319-9f31-4ea2-878f-adc338bc40d4@sorrel.sh
Link: https://lore.kernel.org/r/20230905052631.18240-1-tiwai@suse.de
Link: https://lore.kernel.org/r/20230905081210.6731-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/seq/seq_memory.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c
index 174585bf59d2..b603bb93f896 100644
--- a/sound/core/seq/seq_memory.c
+++ b/sound/core/seq/seq_memory.c
@@ -187,8 +187,13 @@ int snd_seq_expand_var_event(const struct snd_seq_event *event, int count, char
 	err = expand_var_event(event, 0, len, buf, in_kernel);
 	if (err < 0)
 		return err;
-	if (len != newlen)
-		memset(buf + len, 0, newlen - len);
+	if (len != newlen) {
+		if (in_kernel)
+			memset(buf + len, 0, newlen - len);
+		else if (clear_user((__force void __user *)buf + len,
+				    newlen - len))
+			return -EFAULT;
+	}
 	return newlen;
 }
 EXPORT_SYMBOL(snd_seq_expand_var_event);

From d3287e4038ca4f81e02067ab72d087af7224c68b Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Mon, 4 Sep 2023 10:56:04 +0200
Subject: [PATCH 1000/1189] Revert "net: macsec: preserve ingress frame
 ordering"

This reverts commit ab046a5d4be4c90a3952a0eae75617b49c0cb01b.

It was trying to work around an issue at the crypto layer by excluding
ASYNC implementations of gcm(aes), because a bug in the AESNI version
caused reordering when some requests bypassed the cryptd queue while
older requests were still pending on the queue.

This was fixed by commit 38b2f68b4264 ("crypto: aesni - Fix cryptd
reordering problem on gcm"), which pre-dates ab046a5d4be4.

Herbert Xu confirmed that all ASYNC implementations are expected to
maintain the ordering of completions wrt requests, so we can use them
in MACsec.

On my test machine, this restores the performance of a single netperf
instance, from 1.4Gbps to 4.4Gbps.

Link: https://lore.kernel.org/netdev/9328d206c5d9f9239cae27e62e74de40b258471d.1692279161.git.sd@queasysnail.net/T/
Link: https://lore.kernel.org/netdev/1b0cec71-d084-8153-2ba4-72ce71abeb65@byu.edu/
Link: https://lore.kernel.org/netdev/d335ddaa-18dc-f9f0-17ee-9783d3b2ca29@mailbox.tu-dresden.de/
Fixes: ab046a5d4be4 ("net: macsec: preserve ingress frame ordering")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://lore.kernel.org/r/11c952469d114db6fb29242e1d9545e61f52f512.1693757159.git.sd@queasysnail.net
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/macsec.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index c3f30663070f..b7e151439c48 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -1330,8 +1330,7 @@ static struct crypto_aead *macsec_alloc_tfm(char *key, int key_len, int icv_len)
 	struct crypto_aead *tfm;
 	int ret;
 
-	/* Pick a sync gcm(aes) cipher to ensure order is preserved. */
-	tfm = crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC);
+	tfm = crypto_alloc_aead("gcm(aes)", 0, 0);
 
 	if (IS_ERR(tfm))
 		return tfm;

From 45fc4628c15ab2cb7b2f53354b21db63f0a41f81 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 4 Sep 2023 20:38:05 -0700
Subject: [PATCH 1001/1189] perf parse-events: Fix driver config term

Inadvertently deleted in commit 30f4ade33d649aa0 ("perf tools: Revert
enable indices setting syntax for BPF map").

Fixes: 30f4ade33d649aa0 ("perf tools: Revert enable indices setting syntax for BPF map")
Reported-by: James Clark <james.clark@arm.com>
Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20230905033805.3094293-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.y | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 4a305df61f74..21bfe7e0d944 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -839,6 +839,23 @@ PE_TERM
 
 	$$ = term;
 }
+|
+PE_DRV_CFG_TERM
+{
+	struct parse_events_term *term;
+	char *config = strdup($1);
+	int err;
+
+	if (!config)
+		YYNOMEM;
+	err = parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_DRV_CFG, config, $1, &@1, NULL);
+	if (err) {
+		free($1);
+		free(config);
+		PE_ABORT(err);
+	}
+	$$ = term;
+}
 
 sep_dc: ':' |
 

From 5f02d16868b9d738d70656d074518cac760d39ab Mon Sep 17 00:00:00 2001
From: Minjie Du <duminjie@vivo.com>
Date: Mon, 17 Jul 2023 15:19:37 +0800
Subject: [PATCH 1002/1189] gfs2: increase usage of folio_next_index() helper

Simplify code pattern of 'folio->index + folio_nr_pages(folio)' by using
the existing helper folio_next_index().

Signed-off-by: Minjie Du <duminjie@vivo.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/aops.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index ae49256b7c8c..5f02542370c4 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -272,8 +272,7 @@ continue_unlock:
 				 * not be suitable for data integrity
 				 * writeout).
 				 */
-				*done_index = folio->index +
-					folio_nr_pages(folio);
+				*done_index = folio_next_index(folio);
 				ret = 1;
 				break;
 			}

From 111c7d27a1b7954954afde46f9db01d5ad24b316 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Wed, 26 Jul 2023 23:17:53 +0200
Subject: [PATCH 1003/1189] gfs2: Use mapping->gfp_mask for metadata inodes

Set mapping->gfp mask to GFP_NOFS for all metadata inodes so that
allocating pages in the address space of those inodes won't call back
into the filesystem.  This allows to switch back from
find_or_create_page() to grab_cache_page() in two places.

Partially reverts commit 220cca2a4f58 ("GFS2: Change truncate page
allocation to be GFP_NOFS").

Thanks to Dan Carpenter <dan.carpenter@linaro.org> for pointing out a
Smatch static checker warning.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/inode.c | 14 ++++++++++----
 fs/gfs2/lops.c  |  7 +++----
 fs/gfs2/quota.c |  2 +-
 3 files changed, 14 insertions(+), 9 deletions(-)

diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 17c994a0c0d0..fadf5c157603 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -276,10 +276,16 @@ struct inode *gfs2_lookup_simple(struct inode *dip, const char *name)
 	 * gfs2_lookup_simple callers expect ENOENT
 	 * and do not check for NULL.
 	 */
-	if (inode == NULL)
-		return ERR_PTR(-ENOENT);
-	else
-		return inode;
+	if (IS_ERR_OR_NULL(inode))
+		return inode ? inode : ERR_PTR(-ENOENT);
+
+	/*
+	 * Must not call back into the filesystem when allocating
+	 * pages in the metadata inode's address space.
+	 */
+	mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
+
+	return inode;
 }
 
 
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 251322b01631..483f69807062 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -456,7 +456,7 @@ static bool gfs2_jhead_pg_srch(struct gfs2_jdesc *jd,
  * Find the folio with 'index' in the journal's mapping. Search the folio for
  * the journal head if requested (cleanup == false). Release refs on the
  * folio so the page cache can reclaim it. We grabbed a
- * reference on this folio twice, first when we did a find_or_create_page()
+ * reference on this folio twice, first when we did a grab_cache_page()
  * to obtain the folio to add it to the bio and second when we do a
  * filemap_get_folio() here to get the folio to wait on while I/O on it is being
  * completed.
@@ -481,7 +481,7 @@ static void gfs2_jhead_process_page(struct gfs2_jdesc *jd, unsigned long index,
 	if (!*done)
 		*done = gfs2_jhead_pg_srch(jd, head, &folio->page);
 
-	/* filemap_get_folio() and the earlier find_or_create_page() */
+	/* filemap_get_folio() and the earlier grab_cache_page() */
 	folio_put_refs(folio, 2);
 }
 
@@ -535,8 +535,7 @@ int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head,
 
 		for (; block < je->lblock + je->blocks; block++, dblock++) {
 			if (!page) {
-				page = find_or_create_page(mapping,
-						block >> shift, GFP_NOFS);
+				page = grab_cache_page(mapping, block >> shift);
 				if (!page) {
 					ret = -ENOMEM;
 					done = true;
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 704192b73605..96d41ee034d7 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -724,7 +724,7 @@ static int gfs2_write_buf_to_page(struct gfs2_inode *ip, unsigned long index,
 	blk = index << (PAGE_SHIFT - sdp->sd_sb.sb_bsize_shift);
 	boff = off % bsize;
 
-	page = find_or_create_page(mapping, index, GFP_NOFS);
+	page = grab_cache_page(mapping, index);
 	if (!page)
 		return -ENOMEM;
 	if (!page_has_buffers(page))

From dc0b9435238c1a68150c798c9c7a1b5d7414cbb9 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Wed, 26 Jul 2023 23:29:11 +0200
Subject: [PATCH 1004/1189] gfs: Don't use GFP_NOFS in gfs2_unstuff_dinode

Revert the rest of commit 220cca2a4f58 ("GFS2: Change truncate page
allocation to be GFP_NOFS"):

In gfs2_unstuff_dinode(), there is no need to carry out the page cache
allocation under GFP_NOFS because inodes on the "regular" filesystem are
never un-inlined under memory pressure, so switch back from
find_or_create_page() to grab_cache_page() here as well.

Inodes on the "metadata" filesystem can theoretically be un-inlined
under memory pressure, but any page cache allocations in that context
would happen in GFP_NOFS context because those inodes have
inode->i_mapping->gfp_mask set to GFP_NOFS (see the previous patch).

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/bmap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 8d611fbcf0bd..c2f0ed76a2b6 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -161,7 +161,7 @@ int gfs2_unstuff_dinode(struct gfs2_inode *ip)
 	int error;
 
 	down_write(&ip->i_rw_mutex);
-	page = find_or_create_page(inode->i_mapping, 0, GFP_NOFS);
+	page = grab_cache_page(inode->i_mapping, 0);
 	error = -ENOMEM;
 	if (!page)
 		goto out;

From de3e7f97aebb7304856c46daf358ef14f0204219 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Tue, 8 Aug 2023 22:46:34 +0200
Subject: [PATCH 1005/1189] gfs2: do_promote cleanup

Change function do_promote to return true on success, and false
otherwise.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/glock.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 1438e7465e30..d0c82b721f90 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -468,10 +468,10 @@ done:
  * do_promote - promote as many requests as possible on the current queue
  * @gl: The glock
  * 
- * Returns: 1 if there is a blocked holder at the head of the list
+ * Returns true on success (i.e., progress was made or there are no waiters).
  */
 
-static int do_promote(struct gfs2_glock *gl)
+static bool do_promote(struct gfs2_glock *gl)
 {
 	struct gfs2_holder *gh, *current_gh;
 
@@ -484,10 +484,10 @@ static int do_promote(struct gfs2_glock *gl)
 			 * If we get here, it means we may not grant this
 			 * holder for some reason. If this holder is at the
 			 * head of the list, it means we have a blocked holder
-			 * at the head, so return 1.
+			 * at the head, so return false.
 			 */
 			if (list_is_first(&gh->gh_list, &gl->gl_holders))
-				return 1;
+				return false;
 			do_error(gl, 0);
 			break;
 		}
@@ -497,7 +497,7 @@ static int do_promote(struct gfs2_glock *gl)
 		if (!current_gh)
 			current_gh = gh;
 	}
-	return 0;
+	return true;
 }
 
 /**
@@ -834,7 +834,7 @@ __acquires(&gl->gl_lockref.lock)
 	} else {
 		if (test_bit(GLF_DEMOTE, &gl->gl_flags))
 			gfs2_demote_wake(gl);
-		if (do_promote(gl) == 0)
+		if (do_promote(gl))
 			goto out_unlock;
 		gh = find_first_waiter(gl);
 		gl->gl_target = gh->gh_state;

From 0b93bac2271e11beb980fca037a34a9819c7dc37 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Tue, 8 Aug 2023 20:27:46 +0200
Subject: [PATCH 1006/1189] gfs2: Remove LM_FLAG_PRIORITY flag

The last user of this flag was removed in commit b77b4a4815a9 ("gfs2:
Rework freeze / thaw logic").

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 Documentation/filesystems/gfs2-glocks.rst |  3 +--
 fs/gfs2/glock.c                           | 23 ++++++-----------------
 fs/gfs2/glock.h                           |  9 ---------
 fs/gfs2/lock_dlm.c                        |  5 -----
 4 files changed, 7 insertions(+), 33 deletions(-)

diff --git a/Documentation/filesystems/gfs2-glocks.rst b/Documentation/filesystems/gfs2-glocks.rst
index d14f230f0b12..93a690b9bcf2 100644
--- a/Documentation/filesystems/gfs2-glocks.rst
+++ b/Documentation/filesystems/gfs2-glocks.rst
@@ -20,8 +20,7 @@ The gl_holders list contains all the queued lock requests (not
 just the holders) associated with the glock. If there are any
 held locks, then they will be contiguous entries at the head
 of the list. Locks are granted in strictly the order that they
-are queued, except for those marked LM_FLAG_PRIORITY which are
-used only during recovery, and even then only for journal locks.
+are queued.
 
 There are three lock states that users of the glock layer can request,
 namely shared (SH), deferred (DF) and exclusive (EX). Those translate
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index d0c82b721f90..72346f3306e4 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -591,8 +591,7 @@ static void finish_xmote(struct gfs2_glock *gl, unsigned int ret)
 		if (gh && !test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags)) {
 			/* move to back of queue and try next entry */
 			if (ret & LM_OUT_CANCELED) {
-				if ((gh->gh_flags & LM_FLAG_PRIORITY) == 0)
-					list_move_tail(&gh->gh_list, &gl->gl_holders);
+				list_move_tail(&gh->gh_list, &gl->gl_holders);
 				gh = find_first_waiter(gl);
 				gl->gl_target = gh->gh_state;
 				goto retry;
@@ -679,8 +678,7 @@ __acquires(&gl->gl_lockref.lock)
 	    gh && !(gh->gh_flags & LM_FLAG_NOEXP))
 		goto skip_inval;
 
-	lck_flags &= (LM_FLAG_TRY | LM_FLAG_TRY_1CB | LM_FLAG_NOEXP |
-		      LM_FLAG_PRIORITY);
+	lck_flags &= (LM_FLAG_TRY | LM_FLAG_TRY_1CB | LM_FLAG_NOEXP);
 	GLOCK_BUG_ON(gl, gl->gl_state == target);
 	GLOCK_BUG_ON(gl, gl->gl_state == gl->gl_target);
 	if ((target == LM_ST_UNLOCKED || target == LM_ST_DEFERRED) &&
@@ -1515,27 +1513,20 @@ fail:
 		}
 		if (test_bit(HIF_HOLDER, &gh2->gh_iflags))
 			continue;
-		if (unlikely((gh->gh_flags & LM_FLAG_PRIORITY) && !insert_pt))
-			insert_pt = &gh2->gh_list;
 	}
 	trace_gfs2_glock_queue(gh, 1);
 	gfs2_glstats_inc(gl, GFS2_LKS_QCOUNT);
 	gfs2_sbstats_inc(gl, GFS2_LKS_QCOUNT);
 	if (likely(insert_pt == NULL)) {
 		list_add_tail(&gh->gh_list, &gl->gl_holders);
-		if (unlikely(gh->gh_flags & LM_FLAG_PRIORITY))
-			goto do_cancel;
 		return;
 	}
 	list_add_tail(&gh->gh_list, insert_pt);
-do_cancel:
 	gh = list_first_entry(&gl->gl_holders, struct gfs2_holder, gh_list);
-	if (!(gh->gh_flags & LM_FLAG_PRIORITY)) {
-		spin_unlock(&gl->gl_lockref.lock);
-		if (sdp->sd_lockstruct.ls_ops->lm_cancel)
-			sdp->sd_lockstruct.ls_ops->lm_cancel(gl);
-		spin_lock(&gl->gl_lockref.lock);
-	}
+	spin_unlock(&gl->gl_lockref.lock);
+	if (sdp->sd_lockstruct.ls_ops->lm_cancel)
+		sdp->sd_lockstruct.ls_ops->lm_cancel(gl);
+	spin_lock(&gl->gl_lockref.lock);
 	return;
 
 trap_recursive:
@@ -2227,8 +2218,6 @@ static const char *hflags2str(char *buf, u16 flags, unsigned long iflags)
 		*p++ = 'e';
 	if (flags & LM_FLAG_ANY)
 		*p++ = 'A';
-	if (flags & LM_FLAG_PRIORITY)
-		*p++ = 'p';
 	if (flags & LM_FLAG_NODE_SCOPE)
 		*p++ = 'n';
 	if (flags & GL_ASYNC)
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
index 1f1ba92c15a8..c8685ca7d2a2 100644
--- a/fs/gfs2/glock.h
+++ b/fs/gfs2/glock.h
@@ -68,14 +68,6 @@ enum {
  * also be granted in SHARED.  The preferred state is whichever is compatible
  * with other granted locks, or the specified state if no other locks exist.
  *
- * LM_FLAG_PRIORITY
- * Override fairness considerations.  Suppose a lock is held in a shared state
- * and there is a pending request for the deferred state.  A shared lock
- * request with the priority flag would be allowed to bypass the deferred
- * request and directly join the other shared lock.  A shared lock request
- * without the priority flag might be forced to wait until the deferred
- * requested had acquired and released the lock.
- *
  * LM_FLAG_NODE_SCOPE
  * This holder agrees to share the lock within this node. In other words,
  * the glock is held in EX mode according to DLM, but local holders on the
@@ -86,7 +78,6 @@ enum {
 #define LM_FLAG_TRY_1CB		0x0002
 #define LM_FLAG_NOEXP		0x0004
 #define LM_FLAG_ANY		0x0008
-#define LM_FLAG_PRIORITY	0x0010
 #define LM_FLAG_NODE_SCOPE	0x0020
 #define GL_ASYNC		0x0040
 #define GL_EXACT		0x0080
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index 54911294687c..59ab18c79889 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -222,11 +222,6 @@ static u32 make_flags(struct gfs2_glock *gl, const unsigned int gfs_flags,
 		lkf |= DLM_LKF_NOQUEUEBAST;
 	}
 
-	if (gfs_flags & LM_FLAG_PRIORITY) {
-		lkf |= DLM_LKF_NOORDER;
-		lkf |= DLM_LKF_HEADQUE;
-	}
-
 	if (gfs_flags & LM_FLAG_ANY) {
 		if (req == DLM_LOCK_PR)
 			lkf |= DLM_LKF_ALTCW;

From 66fa9912ec973796de4ce9b430d0811d401c17bb Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Wed, 26 Jul 2023 12:01:08 -0500
Subject: [PATCH 1007/1189] gfs2: conversion deadlock do_promote bypass

Consider the following case:
1. A glock is held in shared mode.
2. A process requests the glock in exclusive mode (rename).
3. Before the lock is granted, more processes (read / ls) request the
   glock in shared mode again.
4. gfs2 sends a request to dlm for the lock in exclusive mode because
   that holder is at the head of the queue.
5. Somehow the dlm request gets canceled, so dlm sends us back a
   response with state == LM_ST_SHARED and LM_OUT_CANCELED.  So at that
   point, the glock is still held in shared mode.
6. finish_xmote gets called to process the response from dlm. It detects
   that the glock is not in the requested mode and no demote is in
   progress, so it moves the canceled holder to the tail of the queue
   and finds the new holder at the head of the queue.  That holder is
   requesting the glock in shared mode.
7. finish_xmote calls do_xmote to transition the glock into shared mode,
   but the glock is already in shared mode and so do_xmote complains
   about that with:
	GLOCK_BUG_ON(gl, gl->gl_state == gl->gl_target);

Instead, in finish_xmote, after moving the canceled holder to the tail
of the queue, check if any new holders can be granted.  Only call
do_xmote to repeat the dlm request if the holder at the head of the
queue is requesting the glock in a mode that is incompatible with the
mode the glock is currently held in.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/glock.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 72346f3306e4..675bfec77706 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -594,6 +594,8 @@ static void finish_xmote(struct gfs2_glock *gl, unsigned int ret)
 				list_move_tail(&gh->gh_list, &gl->gl_holders);
 				gh = find_first_waiter(gl);
 				gl->gl_target = gh->gh_state;
+				if (do_promote(gl))
+					goto out;
 				goto retry;
 			}
 			/* Some error or failed "try lock" - report it */

From 6df373b09b1dcf2f7d579f515f653f89a896d417 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Thu, 17 Aug 2023 15:46:16 +0200
Subject: [PATCH 1008/1189] gfs2: Switch to wait_event in gfs2_logd

In gfs2_logd(), switch from an open-coded wait loop to
wait_event_interruptible_timeout().

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/log.c | 17 +++++------------
 1 file changed, 5 insertions(+), 12 deletions(-)

diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index aa568796207c..d3da259820e3 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -1301,7 +1301,6 @@ int gfs2_logd(void *data)
 {
 	struct gfs2_sbd *sdp = data;
 	unsigned long t = 1;
-	DEFINE_WAIT(wait);
 
 	while (!kthread_should_stop()) {
 
@@ -1338,17 +1337,11 @@ int gfs2_logd(void *data)
 
 		try_to_freeze();
 
-		do {
-			prepare_to_wait(&sdp->sd_logd_waitq, &wait,
-					TASK_INTERRUPTIBLE);
-			if (!gfs2_ail_flush_reqd(sdp) &&
-			    !gfs2_jrnl_flush_reqd(sdp) &&
-			    !kthread_should_stop())
-				t = schedule_timeout(t);
-		} while(t && !gfs2_ail_flush_reqd(sdp) &&
-			!gfs2_jrnl_flush_reqd(sdp) &&
-			!kthread_should_stop());
-		finish_wait(&sdp->sd_logd_waitq, &wait);
+		t = wait_event_interruptible_timeout(sdp->sd_logd_waitq,
+				gfs2_ail_flush_reqd(sdp) ||
+				gfs2_jrnl_flush_reqd(sdp) ||
+				kthread_should_stop(),
+				t);
 	}
 
 	return 0;

From b74cd55aa9a9d0aca760028a51343ec79812e410 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Thu, 10 Aug 2023 17:15:46 +0200
Subject: [PATCH 1009/1189] gfs2: low-memory forced flush fixes

First, function gfs2_ail_flush_reqd checks the SDF_FORCE_AIL_FLUSH flag
to determine if an AIL flush should be forced in low-memory situations.
However, it also immediately clears the flag, and when called repeatedly
as in function gfs2_logd, the flag will be lost.  Fix that by pulling
the SDF_FORCE_AIL_FLUSH flag check out of gfs2_ail_flush_reqd.

Second, function gfs2_writepages sets the SDF_FORCE_AIL_FLUSH flag
whether or not enough pages were written.  If enough pages could be
written, flushing the AIL is unnecessary, though.

Third, gfs2_writepages doesn't wake up logd after setting the
SDF_FORCE_AIL_FLUSH flag, so it can take a long time for logd to react.
It would be preferable to wake up logd, but that hurts the performance
of some workloads and we don't quite understand why so far, so don't
wake up logd so far.

Fixes: b066a4eebd4f ("gfs2: forcibly flush ail to relieve memory pressure")
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/aops.c | 4 ++--
 fs/gfs2/log.c  | 8 ++++----
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 5f02542370c4..add62aa2df21 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -183,13 +183,13 @@ static int gfs2_writepages(struct address_space *mapping,
 	int ret;
 
 	/*
-	 * Even if we didn't write any pages here, we might still be holding
+	 * Even if we didn't write enough pages here, we might still be holding
 	 * dirty pages in the ail. We forcibly flush the ail because we don't
 	 * want balance_dirty_pages() to loop indefinitely trying to write out
 	 * pages held in the ail that it can't find.
 	 */
 	ret = iomap_writepages(mapping, wbc, &wpc, &gfs2_writeback_ops);
-	if (ret == 0)
+	if (ret == 0 && wbc->nr_to_write > 0)
 		set_bit(SDF_FORCE_AIL_FLUSH, &sdp->sd_flags);
 	return ret;
 }
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index d3da259820e3..aaca22f2aa2d 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -1282,9 +1282,6 @@ static inline int gfs2_ail_flush_reqd(struct gfs2_sbd *sdp)
 {
 	unsigned int used_blocks = sdp->sd_jdesc->jd_blocks - atomic_read(&sdp->sd_log_blks_free);
 
-	if (test_and_clear_bit(SDF_FORCE_AIL_FLUSH, &sdp->sd_flags))
-		return 1;
-
 	return used_blocks + atomic_read(&sdp->sd_log_blks_needed) >=
 		atomic_read(&sdp->sd_log_thresh2);
 }
@@ -1325,7 +1322,9 @@ int gfs2_logd(void *data)
 						  GFS2_LFC_LOGD_JFLUSH_REQD);
 		}
 
-		if (gfs2_ail_flush_reqd(sdp)) {
+		if (test_bit(SDF_FORCE_AIL_FLUSH, &sdp->sd_flags) ||
+		    gfs2_ail_flush_reqd(sdp)) {
+			clear_bit(SDF_FORCE_AIL_FLUSH, &sdp->sd_flags);
 			gfs2_ail1_start(sdp);
 			gfs2_ail1_wait(sdp);
 			gfs2_ail1_empty(sdp, 0);
@@ -1338,6 +1337,7 @@ int gfs2_logd(void *data)
 		try_to_freeze();
 
 		t = wait_event_interruptible_timeout(sdp->sd_logd_waitq,
+				test_bit(SDF_FORCE_AIL_FLUSH, &sdp->sd_flags) ||
 				gfs2_ail_flush_reqd(sdp) ||
 				gfs2_jrnl_flush_reqd(sdp) ||
 				kthread_should_stop(),

From b6b8f72a11b9d0d7badc7b51030f7fecf695fd79 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Thu, 17 Aug 2023 18:36:36 +0200
Subject: [PATCH 1010/1189] gfs2: Fix logd wakeup on I/O error

When quotad detects an I/O error, it sets sd_log_error and then it wakes
up logd to withdraw the filesystem.  However, logd doesn't wake up when
sd_log_error is set.  Fix that.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/log.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index aaca22f2aa2d..abe4397dc59b 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -1340,6 +1340,7 @@ int gfs2_logd(void *data)
 				test_bit(SDF_FORCE_AIL_FLUSH, &sdp->sd_flags) ||
 				gfs2_ail_flush_reqd(sdp) ||
 				gfs2_jrnl_flush_reqd(sdp) ||
+				sdp->sd_log_error ||
 				kthread_should_stop(),
 				t);
 	}

From db77789bae7e33b458220110f189f2381f19362b Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Fri, 11 Aug 2023 16:00:10 +0200
Subject: [PATCH 1011/1189] gfs2: journal flush threshold fixes and cleanup

Commit f07b35202148 ("GFS2: Made logd daemon take into account log
demand") changed gfs2_ail_flush_reqd() and gfs2_jrnl_flush_reqd() to
take sd_log_blks_needed into account, but the checks in
gfs2_log_commit() were not updated correspondingly.

Once that is fixed, gfs2_jrnl_flush_reqd() and gfs2_ail_flush_reqd() can
be used in gfs2_log_commit().  Make those two helpers available to
gfs2_log_commit() by defining them above gfs2_log_commit().

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/log.c | 34 ++++++++++++++++------------------
 1 file changed, 16 insertions(+), 18 deletions(-)

diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index abe4397dc59b..addf4ce0bedd 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -1227,6 +1227,21 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 	gfs2_log_unlock(sdp);
 }
 
+static inline int gfs2_jrnl_flush_reqd(struct gfs2_sbd *sdp)
+{
+	return atomic_read(&sdp->sd_log_pinned) +
+	       atomic_read(&sdp->sd_log_blks_needed) >=
+	       atomic_read(&sdp->sd_log_thresh1);
+}
+
+static inline int gfs2_ail_flush_reqd(struct gfs2_sbd *sdp)
+{
+	return sdp->sd_jdesc->jd_blocks -
+	       atomic_read(&sdp->sd_log_blks_free) +
+	       atomic_read(&sdp->sd_log_blks_needed) >=
+	       atomic_read(&sdp->sd_log_thresh2);
+}
+
 /**
  * gfs2_log_commit - Commit a transaction to the log
  * @sdp: the filesystem
@@ -1246,9 +1261,7 @@ void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 {
 	log_refund(sdp, tr);
 
-	if (atomic_read(&sdp->sd_log_pinned) > atomic_read(&sdp->sd_log_thresh1) ||
-	    ((sdp->sd_jdesc->jd_blocks - atomic_read(&sdp->sd_log_blks_free)) >
-	    atomic_read(&sdp->sd_log_thresh2)))
+	if (gfs2_ail_flush_reqd(sdp) || gfs2_jrnl_flush_reqd(sdp))
 		wake_up(&sdp->sd_logd_waitq);
 }
 
@@ -1271,21 +1284,6 @@ static void gfs2_log_shutdown(struct gfs2_sbd *sdp)
 	gfs2_assert_warn(sdp, list_empty(&sdp->sd_ail2_list));
 }
 
-static inline int gfs2_jrnl_flush_reqd(struct gfs2_sbd *sdp)
-{
-	return (atomic_read(&sdp->sd_log_pinned) +
-		atomic_read(&sdp->sd_log_blks_needed) >=
-		atomic_read(&sdp->sd_log_thresh1));
-}
-
-static inline int gfs2_ail_flush_reqd(struct gfs2_sbd *sdp)
-{
-	unsigned int used_blocks = sdp->sd_jdesc->jd_blocks - atomic_read(&sdp->sd_log_blks_free);
-
-	return used_blocks + atomic_read(&sdp->sd_log_blks_needed) >=
-		atomic_read(&sdp->sd_log_thresh2);
-}
-
 /**
  * gfs2_logd - Update log tail as Active Items get flushed to in-place blocks
  * @data: Pointer to GFS2 superblock

From 481f6e7d734ad9a00b44cf0c000f0ed30843e4d3 Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Fri, 16 Jun 2023 10:46:50 -0500
Subject: [PATCH 1012/1189] gfs2: Use qd_sbd more consequently

Before this patch many of the functions in quota.c got their superblock
pointer, sdp, from the quota_data's glock pointer. That's silly because
the qd already has its own pointer to the superblock (qd_sbd).

This patch changes references to use that instead, eliminating a level
of indirection.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/quota.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 96d41ee034d7..48b9fbffe260 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -119,7 +119,7 @@ static void gfs2_qd_dispose(struct list_head *list)
 
 	while (!list_empty(list)) {
 		qd = list_first_entry(list, struct gfs2_quota_data, qd_lru);
-		sdp = qd->qd_gl->gl_name.ln_sbd;
+		sdp = qd->qd_sbd;
 
 		list_del(&qd->qd_lru);
 
@@ -302,7 +302,7 @@ static int qd_get(struct gfs2_sbd *sdp, struct kqid qid,
 
 static void qd_hold(struct gfs2_quota_data *qd)
 {
-	struct gfs2_sbd *sdp = qd->qd_gl->gl_name.ln_sbd;
+	struct gfs2_sbd *sdp = qd->qd_sbd;
 	gfs2_assert(sdp, !__lockref_is_dead(&qd->qd_lockref));
 	lockref_get(&qd->qd_lockref);
 }
@@ -367,7 +367,7 @@ static void slot_put(struct gfs2_quota_data *qd)
 
 static int bh_get(struct gfs2_quota_data *qd)
 {
-	struct gfs2_sbd *sdp = qd->qd_gl->gl_name.ln_sbd;
+	struct gfs2_sbd *sdp = qd->qd_sbd;
 	struct inode *inode = sdp->sd_qc_inode;
 	struct gfs2_inode *ip = GFS2_I(inode);
 	unsigned int block, offset;
@@ -421,7 +421,7 @@ fail:
 
 static void bh_put(struct gfs2_quota_data *qd)
 {
-	struct gfs2_sbd *sdp = qd->qd_gl->gl_name.ln_sbd;
+	struct gfs2_sbd *sdp = qd->qd_sbd;
 
 	mutex_lock(&sdp->sd_quota_mutex);
 	gfs2_assert(sdp, qd->qd_bh_count);
@@ -489,8 +489,7 @@ static int qd_fish(struct gfs2_sbd *sdp, struct gfs2_quota_data **qdp)
 
 static void qd_unlock(struct gfs2_quota_data *qd)
 {
-	gfs2_assert_warn(qd->qd_gl->gl_name.ln_sbd,
-			 test_bit(QDF_LOCKED, &qd->qd_flags));
+	gfs2_assert_warn(qd->qd_sbd, test_bit(QDF_LOCKED, &qd->qd_flags));
 	clear_bit(QDF_LOCKED, &qd->qd_flags);
 	bh_put(qd);
 	slot_put(qd);
@@ -666,7 +665,7 @@ static int sort_qd(const void *a, const void *b)
 
 static void do_qc(struct gfs2_quota_data *qd, s64 change, int qc_type)
 {
-	struct gfs2_sbd *sdp = qd->qd_gl->gl_name.ln_sbd;
+	struct gfs2_sbd *sdp = qd->qd_sbd;
 	struct gfs2_inode *ip = GFS2_I(sdp->sd_qc_inode);
 	struct gfs2_quota_change *qc = qd->qd_bh_qc;
 	s64 x;
@@ -881,7 +880,7 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
 
 static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda)
 {
-	struct gfs2_sbd *sdp = (*qda)->qd_gl->gl_name.ln_sbd;
+	struct gfs2_sbd *sdp = (*qda)->qd_sbd;
 	struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode);
 	struct gfs2_alloc_parms ap = { .aflags = 0, };
 	unsigned int data_blocks, ind_blocks;
@@ -1009,11 +1008,12 @@ static int update_qd(struct gfs2_sbd *sdp, struct gfs2_quota_data *qd)
 static int do_glock(struct gfs2_quota_data *qd, int force_refresh,
 		    struct gfs2_holder *q_gh)
 {
-	struct gfs2_sbd *sdp = qd->qd_gl->gl_name.ln_sbd;
+	struct gfs2_sbd *sdp = qd->qd_sbd;
 	struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode);
 	struct gfs2_holder i_gh;
 	int error;
 
+	gfs2_assert_warn(sdp, sdp == qd->qd_gl->gl_name.ln_sbd);
 restart:
 	error = gfs2_glock_nq_init(qd->qd_gl, LM_ST_SHARED, 0, q_gh);
 	if (error)
@@ -1091,7 +1091,7 @@ int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
 
 static int need_sync(struct gfs2_quota_data *qd)
 {
-	struct gfs2_sbd *sdp = qd->qd_gl->gl_name.ln_sbd;
+	struct gfs2_sbd *sdp = qd->qd_sbd;
 	struct gfs2_tune *gt = &sdp->sd_tune;
 	s64 value;
 	unsigned int num, den;
@@ -1178,7 +1178,7 @@ void gfs2_quota_unlock(struct gfs2_inode *ip)
 
 static int print_message(struct gfs2_quota_data *qd, char *type)
 {
-	struct gfs2_sbd *sdp = qd->qd_gl->gl_name.ln_sbd;
+	struct gfs2_sbd *sdp = qd->qd_sbd;
 
 	fs_info(sdp, "quota %s for %s %u\n",
 		type,

From 3c69c437bf9832d2201702c5ccc3b8a77a7e0aa3 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Wed, 23 Aug 2023 15:49:58 +0200
Subject: [PATCH 1013/1189] gfs2: Rename sd_{ glock => kill }_wait

Rename sd_glock_wait to sd_kill_wait: we'll use it for other things
related to "killing" a filesystem on unmount soon (kill_sb).

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/glock.c      | 6 +++---
 fs/gfs2/incore.h     | 2 +-
 fs/gfs2/ops_fstype.c | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 675bfec77706..e242745cf40f 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -176,7 +176,7 @@ void gfs2_glock_free(struct gfs2_glock *gl)
 	wake_up_glock(gl);
 	call_rcu(&gl->gl_rcu, gfs2_glock_dealloc);
 	if (atomic_dec_and_test(&sdp->sd_glock_disposal))
-		wake_up(&sdp->sd_glock_wait);
+		wake_up(&sdp->sd_kill_wait);
 }
 
 /**
@@ -1231,7 +1231,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 out_free:
 	gfs2_glock_dealloc(&gl->gl_rcu);
 	if (atomic_dec_and_test(&sdp->sd_glock_disposal))
-		wake_up(&sdp->sd_glock_wait);
+		wake_up(&sdp->sd_kill_wait);
 
 out:
 	return ret;
@@ -2188,7 +2188,7 @@ void gfs2_gl_hash_clear(struct gfs2_sbd *sdp)
 	flush_workqueue(glock_workqueue);
 	glock_hash_walk(clear_glock, sdp);
 	flush_workqueue(glock_workqueue);
-	wait_event_timeout(sdp->sd_glock_wait,
+	wait_event_timeout(sdp->sd_kill_wait,
 			   atomic_read(&sdp->sd_glock_disposal) == 0,
 			   HZ * 600);
 	glock_hash_walk(dump_glock_func, sdp);
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 04f2d78e8658..7abb43bb8df0 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -716,7 +716,7 @@ struct gfs2_sbd {
 	struct gfs2_glock *sd_rename_gl;
 	struct gfs2_glock *sd_freeze_gl;
 	struct work_struct sd_freeze_work;
-	wait_queue_head_t sd_glock_wait;
+	wait_queue_head_t sd_kill_wait;
 	wait_queue_head_t sd_async_glock_wait;
 	atomic_t sd_glock_disposal;
 	struct completion sd_locking_init;
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 8a27957dbfee..19d19491c0d1 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -87,7 +87,7 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
 	set_bit(SDF_NOJOURNALID, &sdp->sd_flags);
 	gfs2_tune_init(&sdp->sd_tune);
 
-	init_waitqueue_head(&sdp->sd_glock_wait);
+	init_waitqueue_head(&sdp->sd_kill_wait);
 	init_waitqueue_head(&sdp->sd_async_glock_wait);
 	atomic_set(&sdp->sd_glock_disposal, 0);
 	init_completion(&sdp->sd_locking_init);

From e7beb8b6de1a6d6956fe0652d85cf356416ce4d9 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Wed, 23 Aug 2023 15:53:13 +0200
Subject: [PATCH 1014/1189] gfs2: Rename SDF_DEACTIVATING to SDF_KILL

Rename the SDF_DEACTIVATING flag to SDF_KILL to make it more obvious
that this relates to the kill_sb filesystem operation.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/glock.c      | 4 ++--
 fs/gfs2/glops.c      | 2 +-
 fs/gfs2/incore.h     | 2 +-
 fs/gfs2/ops_fstype.c | 4 ++--
 fs/gfs2/super.c      | 2 +-
 fs/gfs2/sys.c        | 2 +-
 6 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index e242745cf40f..9cbf8d98489a 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1022,7 +1022,7 @@ static void delete_work_func(struct work_struct *work)
 		 * step entirely.
 		 */
 		if (gfs2_try_evict(gl)) {
-			if (test_bit(SDF_DEACTIVATING, &sdp->sd_flags))
+			if (test_bit(SDF_KILL, &sdp->sd_flags))
 				goto out;
 			if (gfs2_queue_verify_evict(gl))
 				return;
@@ -1035,7 +1035,7 @@ static void delete_work_func(struct work_struct *work)
 					    GFS2_BLKST_UNLINKED);
 		if (IS_ERR(inode)) {
 			if (PTR_ERR(inode) == -EAGAIN &&
-			    !test_bit(SDF_DEACTIVATING, &sdp->sd_flags) &&
+			    !test_bit(SDF_KILL, &sdp->sd_flags) &&
 			    gfs2_queue_verify_evict(gl))
 				return;
 		} else {
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 54319328b16b..7d6cca467fa1 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -637,7 +637,7 @@ static void iopen_go_callback(struct gfs2_glock *gl, bool remote)
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 
 	if (!remote || sb_rdonly(sdp->sd_vfs) ||
-	    test_bit(SDF_DEACTIVATING, &sdp->sd_flags))
+	    test_bit(SDF_KILL, &sdp->sd_flags))
 		return;
 
 	if (gl->gl_demote_state == LM_ST_UNLOCKED &&
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 7abb43bb8df0..ab857431dfa4 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -606,7 +606,7 @@ enum {
 	SDF_REMOTE_WITHDRAW	= 13, /* Performing remote recovery */
 	SDF_WITHDRAW_RECOVERY	= 14, /* Wait for journal recovery when we are
 					 withdrawing */
-	SDF_DEACTIVATING	= 15,
+	SDF_KILL		= 15,
 	SDF_EVICTING		= 16,
 	SDF_FROZEN		= 17,
 };
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 19d19491c0d1..6ea295cee463 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1786,9 +1786,9 @@ static void gfs2_kill_sb(struct super_block *sb)
 	/*
 	 * Flush and then drain the delete workqueue here (via
 	 * destroy_workqueue()) to ensure that any delete work that
-	 * may be running will also see the SDF_DEACTIVATING flag.
+	 * may be running will also see the SDF_KILL flag.
 	 */
-	set_bit(SDF_DEACTIVATING, &sdp->sd_flags);
+	set_bit(SDF_KILL, &sdp->sd_flags);
 	gfs2_flush_delete_work(sdp);
 	destroy_workqueue(sdp->sd_delete_wq);
 
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 9f4d5d6549ee..e0dceef3c9cc 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -546,7 +546,7 @@ void gfs2_make_fs_ro(struct gfs2_sbd *sdp)
 {
 	int log_write_allowed = test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
 
-	if (!test_bit(SDF_DEACTIVATING, &sdp->sd_flags))
+	if (!test_bit(SDF_KILL, &sdp->sd_flags))
 		gfs2_flush_delete_work(sdp);
 
 	if (!log_write_allowed && current == sdp->sd_quotad_process)
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index 2dfbe2f188dd..a85fe7b92911 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -118,7 +118,7 @@ static ssize_t status_show(struct gfs2_sbd *sdp, char *buf)
 		     test_bit(SDF_WITHDRAW_IN_PROG, &f),
 		     test_bit(SDF_REMOTE_WITHDRAW, &f),
 		     test_bit(SDF_WITHDRAW_RECOVERY, &f),
-		     test_bit(SDF_DEACTIVATING, &f),
+		     test_bit(SDF_KILL, &f),
 		     sdp->sd_log_error,
 		     rwsem_is_locked(&sdp->sd_log_flush_lock),
 		     sdp->sd_log_num_revoke,

From 6b0e9a5f1e6d7f2719856b601d5639902fc0ee4f Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Tue, 22 Aug 2023 22:59:27 +0200
Subject: [PATCH 1015/1189] gfs2: Fix wrong quota shrinker return value

Function gfs2_qd_isolate must only return LRU_REMOVED when removing the
item from the lru list; otherwise, the number of items on the list will
go wrong.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/quota.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 48b9fbffe260..f58072efafc9 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -149,18 +149,22 @@ static enum lru_status gfs2_qd_isolate(struct list_head *item,
 		struct list_lru_one *lru, spinlock_t *lru_lock, void *arg)
 {
 	struct list_head *dispose = arg;
-	struct gfs2_quota_data *qd = list_entry(item, struct gfs2_quota_data, qd_lru);
+	struct gfs2_quota_data *qd =
+		list_entry(item, struct gfs2_quota_data, qd_lru);
+	enum lru_status status;
 
 	if (!spin_trylock(&qd->qd_lockref.lock))
 		return LRU_SKIP;
 
+	status = LRU_SKIP;
 	if (qd->qd_lockref.count == 0) {
 		lockref_mark_dead(&qd->qd_lockref);
 		list_lru_isolate_move(lru, &qd->qd_lru, dispose);
+		status = LRU_REMOVED;
 	}
 
 	spin_unlock(&qd->qd_lockref.lock);
-	return LRU_REMOVED;
+	return status;
 }
 
 static unsigned long gfs2_qd_shrink_scan(struct shrinker *shrink,

From 961fe3422e055d251b32a117cd8cd3d27153bc96 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Wed, 23 Aug 2023 21:38:04 +0200
Subject: [PATCH 1016/1189] gfs2: Use gfs2_qd_dispose in gfs2_quota_cleanup

Change gfs2_quota_cleanup() to move the quota data objects to dispose of
on a dispose list and call gfs2_qd_dispose() on that list, like
gfs2_qd_shrink_scan() does, instead of disposing of the quota data
objects directly.

This may look a bit pointless by itself, but it will make more sense in
combination with a fix that follows.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/quota.c | 26 ++++----------------------
 1 file changed, 4 insertions(+), 22 deletions(-)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index f58072efafc9..976bf1097706 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -1459,35 +1459,17 @@ fail:
 
 void gfs2_quota_cleanup(struct gfs2_sbd *sdp)
 {
-	struct list_head *head = &sdp->sd_quota_list;
 	struct gfs2_quota_data *qd;
+	LIST_HEAD(dispose);
 
 	spin_lock(&qd_lock);
-	while (!list_empty(head)) {
-		qd = list_last_entry(head, struct gfs2_quota_data, qd_list);
-
-		list_del(&qd->qd_list);
-
-		/* Also remove if this qd exists in the reclaim list */
+	list_for_each_entry(qd, &sdp->sd_quota_list, qd_list) {
 		list_lru_del(&gfs2_qd_lru, &qd->qd_lru);
-		atomic_dec(&sdp->sd_quota_count);
-		spin_unlock(&qd_lock);
-
-		spin_lock_bucket(qd->qd_hash);
-		hlist_bl_del_rcu(&qd->qd_hlist);
-		spin_unlock_bucket(qd->qd_hash);
-
-		gfs2_assert_warn(sdp, !qd->qd_change);
-		gfs2_assert_warn(sdp, !qd->qd_slot_count);
-		gfs2_assert_warn(sdp, !qd->qd_bh_count);
-
-		gfs2_glock_put(qd->qd_gl);
-		call_rcu(&qd->qd_rcu, gfs2_qd_dealloc);
-
-		spin_lock(&qd_lock);
+		list_add(&qd->qd_lru, &dispose);
 	}
 	spin_unlock(&qd_lock);
 
+	gfs2_qd_dispose(&dispose);
 	gfs2_assert_warn(sdp, !atomic_read(&sdp->sd_quota_count));
 
 	kvfree(sdp->sd_quota_bitmap);

From faada74a90563183cb57af3e4604ed183d71a81c Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Tue, 22 Aug 2023 14:18:21 +0200
Subject: [PATCH 1017/1189] gfs2: Factor out duplicate quota data disposal code

Rename gfs2_qd_dispose() to gfs2_qd_dispose_list().  Move some code
duplicated in gfs2_qd_dispose_list() and gfs2_quota_cleanup() into a
new gfs2_qd_dispose() function.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/quota.c | 47 ++++++++++++++++++++++++-----------------------
 1 file changed, 24 insertions(+), 23 deletions(-)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 976bf1097706..01fae6b030e9 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -112,35 +112,36 @@ static void gfs2_qd_dealloc(struct rcu_head *rcu)
 	kmem_cache_free(gfs2_quotad_cachep, qd);
 }
 
-static void gfs2_qd_dispose(struct list_head *list)
+static void gfs2_qd_dispose(struct gfs2_quota_data *qd)
+{
+	struct gfs2_sbd *sdp = qd->qd_sbd;
+
+	spin_lock(&qd_lock);
+	list_del(&qd->qd_list);
+	spin_unlock(&qd_lock);
+
+	spin_lock_bucket(qd->qd_hash);
+	hlist_bl_del_rcu(&qd->qd_hlist);
+	spin_unlock_bucket(qd->qd_hash);
+
+	gfs2_assert_warn(sdp, !qd->qd_change);
+	gfs2_assert_warn(sdp, !qd->qd_slot_count);
+	gfs2_assert_warn(sdp, !qd->qd_bh_count);
+
+	gfs2_glock_put(qd->qd_gl);
+	call_rcu(&qd->qd_rcu, gfs2_qd_dealloc);
+}
+
+static void gfs2_qd_list_dispose(struct list_head *list)
 {
 	struct gfs2_quota_data *qd;
-	struct gfs2_sbd *sdp;
 
 	while (!list_empty(list)) {
 		qd = list_first_entry(list, struct gfs2_quota_data, qd_lru);
-		sdp = qd->qd_sbd;
-
 		list_del(&qd->qd_lru);
 
-		/* Free from the filesystem-specific list */
-		spin_lock(&qd_lock);
-		list_del(&qd->qd_list);
-		spin_unlock(&qd_lock);
-
-		spin_lock_bucket(qd->qd_hash);
-		hlist_bl_del_rcu(&qd->qd_hlist);
-		spin_unlock_bucket(qd->qd_hash);
-
-		gfs2_assert_warn(sdp, !qd->qd_change);
-		gfs2_assert_warn(sdp, !qd->qd_slot_count);
-		gfs2_assert_warn(sdp, !qd->qd_bh_count);
-
-		gfs2_glock_put(qd->qd_gl);
+		gfs2_qd_dispose(qd);
 		atomic_dec(&sdp->sd_quota_count);
-
-		/* Delete it from the common reclaim list */
-		call_rcu(&qd->qd_rcu, gfs2_qd_dealloc);
 	}
 }
 
@@ -179,7 +180,7 @@ static unsigned long gfs2_qd_shrink_scan(struct shrinker *shrink,
 	freed = list_lru_shrink_walk(&gfs2_qd_lru, sc,
 				     gfs2_qd_isolate, &dispose);
 
-	gfs2_qd_dispose(&dispose);
+	gfs2_qd_list_dispose(&dispose);
 
 	return freed;
 }
@@ -1469,7 +1470,7 @@ void gfs2_quota_cleanup(struct gfs2_sbd *sdp)
 	}
 	spin_unlock(&qd_lock);
 
-	gfs2_qd_dispose(&dispose);
+	gfs2_qd_list_dispose(&dispose);
 	gfs2_assert_warn(sdp, !atomic_read(&sdp->sd_quota_count));
 
 	kvfree(sdp->sd_quota_bitmap);

From fae2e73a5537e40ebae9a00e6548101e5ab2441f Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Thu, 24 Aug 2023 15:08:55 +0200
Subject: [PATCH 1018/1189] gfs2: No more quota complaints after withdraw

Once a filesystem is withdrawn, don't complain about quota changes
that can't be synced to the main quota file anymore.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/quota.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 01fae6b030e9..fccdb22980e8 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -124,9 +124,11 @@ static void gfs2_qd_dispose(struct gfs2_quota_data *qd)
 	hlist_bl_del_rcu(&qd->qd_hlist);
 	spin_unlock_bucket(qd->qd_hash);
 
-	gfs2_assert_warn(sdp, !qd->qd_change);
-	gfs2_assert_warn(sdp, !qd->qd_slot_count);
-	gfs2_assert_warn(sdp, !qd->qd_bh_count);
+	if (!gfs2_withdrawn(sdp)) {
+		gfs2_assert_warn(sdp, !qd->qd_change);
+		gfs2_assert_warn(sdp, !qd->qd_slot_count);
+		gfs2_assert_warn(sdp, !qd->qd_bh_count);
+	}
 
 	gfs2_glock_put(qd->qd_gl);
 	call_rcu(&qd->qd_rcu, gfs2_qd_dealloc);

From bb73ae8ff394f767a8acbc99a1d682b874ba5e74 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Thu, 24 Aug 2023 14:52:29 +0200
Subject: [PATCH 1019/1189] gfs2: Fix initial quota data refcount

Fix the refcount of quota data objects created directly by
gfs2_quota_init(): those are placed into the in-memory quota "database"
for eventual syncing to the main quota file, but they are not actively
held and should thus have an initial refcount of 0.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/quota.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index fccdb22980e8..97fdf64148ba 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -228,7 +228,7 @@ static struct gfs2_quota_data *qd_alloc(unsigned hash, struct gfs2_sbd *sdp, str
 		return NULL;
 
 	qd->qd_sbd = sdp;
-	qd->qd_lockref.count = 1;
+	qd->qd_lockref.count = 0;
 	spin_lock_init(&qd->qd_lockref.lock);
 	qd->qd_id = qid;
 	qd->qd_slot = -1;
@@ -290,6 +290,7 @@ static int qd_get(struct gfs2_sbd *sdp, struct kqid qid,
 	spin_lock_bucket(hash);
 	*qdp = qd = gfs2_qd_search_bucket(hash, sdp, qid);
 	if (qd == NULL) {
+		new_qd->qd_lockref.count++;
 		*qdp = new_qd;
 		list_add(&new_qd->qd_list, &sdp->sd_quota_list);
 		hlist_bl_add_head_rcu(&new_qd->qd_hlist, &qd_hash_table[hash]);

From a475c5dd16e57c570113eccba51955b5df8bb052 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Wed, 23 Aug 2023 17:15:47 +0200
Subject: [PATCH 1020/1189] gfs2: Free quota data objects synchronously

In gfs2_quota_cleanup(), wait for the quota data objects to be freed
before returning.  Otherwise, there is no guarantee that the quota data
objects will be gone when their kmem cache is destroyed.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/quota.c | 37 ++++++++++++++++++++++++++++++++++---
 1 file changed, 34 insertions(+), 3 deletions(-)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 97fdf64148ba..75be0d8e243f 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -109,7 +109,11 @@ static inline void spin_unlock_bucket(unsigned int hash)
 static void gfs2_qd_dealloc(struct rcu_head *rcu)
 {
 	struct gfs2_quota_data *qd = container_of(rcu, struct gfs2_quota_data, qd_rcu);
+	struct gfs2_sbd *sdp = qd->qd_sbd;
+
 	kmem_cache_free(gfs2_quotad_cachep, qd);
+	if (atomic_dec_and_test(&sdp->sd_quota_count))
+		wake_up(&sdp->sd_kill_wait);
 }
 
 static void gfs2_qd_dispose(struct gfs2_quota_data *qd)
@@ -143,7 +147,6 @@ static void gfs2_qd_list_dispose(struct list_head *list)
 		list_del(&qd->qd_lru);
 
 		gfs2_qd_dispose(qd);
-		atomic_dec(&sdp->sd_quota_count);
 	}
 }
 
@@ -317,13 +320,24 @@ static void qd_hold(struct gfs2_quota_data *qd)
 
 static void qd_put(struct gfs2_quota_data *qd)
 {
+	struct gfs2_sbd *sdp;
+
 	if (lockref_put_or_lock(&qd->qd_lockref))
 		return;
 
+	BUG_ON(__lockref_is_dead(&qd->qd_lockref));
+	sdp = qd->qd_sbd;
+	if (unlikely(!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))) {
+		lockref_mark_dead(&qd->qd_lockref);
+		spin_unlock(&qd->qd_lockref.lock);
+
+		gfs2_qd_dispose(qd);
+		return;
+	}
+
 	qd->qd_lockref.count = 0;
 	list_lru_add(&gfs2_qd_lru, &qd->qd_lru);
 	spin_unlock(&qd->qd_lockref.lock);
-
 }
 
 static int slot_get(struct gfs2_quota_data *qd)
@@ -1465,16 +1479,33 @@ void gfs2_quota_cleanup(struct gfs2_sbd *sdp)
 {
 	struct gfs2_quota_data *qd;
 	LIST_HEAD(dispose);
+	int count;
+
+	BUG_ON(test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags));
 
 	spin_lock(&qd_lock);
 	list_for_each_entry(qd, &sdp->sd_quota_list, qd_list) {
+		spin_lock(&qd->qd_lockref.lock);
+		if (qd->qd_lockref.count != 0) {
+			spin_unlock(&qd->qd_lockref.lock);
+			continue;
+		}
+		lockref_mark_dead(&qd->qd_lockref);
+		spin_unlock(&qd->qd_lockref.lock);
+
 		list_lru_del(&gfs2_qd_lru, &qd->qd_lru);
 		list_add(&qd->qd_lru, &dispose);
 	}
 	spin_unlock(&qd_lock);
 
 	gfs2_qd_list_dispose(&dispose);
-	gfs2_assert_warn(sdp, !atomic_read(&sdp->sd_quota_count));
+
+	wait_event_timeout(sdp->sd_kill_wait,
+		(count = atomic_read(&sdp->sd_quota_count)) == 0,
+		HZ * 60);
+
+	if (count != 0)
+		fs_err(sdp, "%d left-over quota data objects\n", count);
 
 	kvfree(sdp->sd_quota_bitmap);
 	sdp->sd_quota_bitmap = NULL;

From f66af88e33212b57ea86da2c5d66c0d9d5c46344 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Mon, 28 Aug 2023 16:39:20 +0200
Subject: [PATCH 1021/1189] gfs2: Stop using gfs2_make_fs_ro for withdraw

[   81.372851][ T5532] CPU: 1 PID: 5532 Comm: syz-executor.0 Not tainted 6.2.0-rc1-syzkaller-dirty #0
[   81.382080][ T5532] Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/12/2023
[   81.392343][ T5532] Call Trace:
[   81.395654][ T5532]  <TASK>
[   81.398603][ T5532]  dump_stack_lvl+0x1b1/0x290
[   81.418421][ T5532]  gfs2_assert_warn_i+0x19a/0x2e0
[   81.423480][ T5532]  gfs2_quota_cleanup+0x4c6/0x6b0
[   81.428611][ T5532]  gfs2_make_fs_ro+0x517/0x610
[   81.457802][ T5532]  gfs2_withdraw+0x609/0x1540
[   81.481452][ T5532]  gfs2_inode_refresh+0xb2d/0xf60
[   81.506658][ T5532]  gfs2_instantiate+0x15e/0x220
[   81.511504][ T5532]  gfs2_glock_wait+0x1d9/0x2a0
[   81.516352][ T5532]  do_sync+0x485/0xc80
[   81.554943][ T5532]  gfs2_quota_sync+0x3da/0x8b0
[   81.559738][ T5532]  gfs2_sync_fs+0x49/0xb0
[   81.564063][ T5532]  sync_filesystem+0xe8/0x220
[   81.568740][ T5532]  generic_shutdown_super+0x6b/0x310
[   81.574112][ T5532]  kill_block_super+0x79/0xd0
[   81.578779][ T5532]  deactivate_locked_super+0xa7/0xf0
[   81.584064][ T5532]  cleanup_mnt+0x494/0x520
[   81.593753][ T5532]  task_work_run+0x243/0x300
[   81.608837][ T5532]  exit_to_user_mode_loop+0x124/0x150
[   81.614232][ T5532]  exit_to_user_mode_prepare+0xb2/0x140
[   81.619820][ T5532]  syscall_exit_to_user_mode+0x26/0x60
[   81.625287][ T5532]  do_syscall_64+0x49/0xb0
[   81.629710][ T5532]  entry_SYSCALL_64_after_hwframe+0x63/0xcd

In this backtrace, gfs2_quota_sync() takes quota data references and
then calls do_sync().  Function do_sync() encounters filesystem
corruption and withdraws the filesystem, which (among other things) calls
gfs2_quota_cleanup().  Function gfs2_quota_cleanup() wrongly assumes
that nobody is holding any quota data references anymore, and destroys
all quota data objects.  When gfs2_quota_sync() then resumes and
dereferences the quota data objects it is holding, those objects are no
longer there.

Function gfs2_quota_cleanup() deals with resource deallocation and can
easily be delayed until gfs2_put_super() in the case of a filesystem
withdraw.  In fact, most of the other work gfs2_make_fs_ro() does is
unnecessary during a withdraw as well, so change signal_our_withdraw()
to skip gfs2_make_fs_ro() and perform the necessary steps directly
instead.

Thanks to Edward Adam Davis <eadavis@sina.com> for the initial patches.

Link: https://lore.kernel.org/all/0000000000002b5e2405f14e860f@google.com
Reported-by: syzbot+3f6a670108ce43356017@syzkaller.appspotmail.com
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/super.c |  9 ++-------
 fs/gfs2/util.c  | 19 ++++++++++++++++++-
 2 files changed, 20 insertions(+), 8 deletions(-)

diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index e0dceef3c9cc..119a5b20eb00 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -580,15 +580,8 @@ void gfs2_make_fs_ro(struct gfs2_sbd *sdp)
 				   gfs2_log_is_empty(sdp),
 				   HZ * 5);
 		gfs2_assert_warn(sdp, gfs2_log_is_empty(sdp));
-	} else {
-		wait_event_timeout(sdp->sd_log_waitq,
-				   gfs2_log_is_empty(sdp),
-				   HZ * 5);
 	}
 	gfs2_quota_cleanup(sdp);
-
-	if (!log_write_allowed)
-		sdp->sd_vfs->s_flags |= SB_RDONLY;
 }
 
 /**
@@ -622,6 +615,8 @@ restart:
 	if (!sb_rdonly(sb)) {
 		gfs2_make_fs_ro(sdp);
 	}
+	if (gfs2_withdrawn(sdp))
+		gfs2_quota_cleanup(sdp);
 	WARN_ON(gfs2_withdrawing(sdp));
 
 	/*  At this point, we're through modifying the disk  */
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index dac22b1c1a2e..b3086a9baf00 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -9,6 +9,7 @@
 #include <linux/spinlock.h>
 #include <linux/completion.h>
 #include <linux/buffer_head.h>
+#include <linux/kthread.h>
 #include <linux/crc32.h>
 #include <linux/gfs2_ondisk.h>
 #include <linux/delay.h>
@@ -150,7 +151,23 @@ static void signal_our_withdraw(struct gfs2_sbd *sdp)
 	if (!sb_rdonly(sdp->sd_vfs)) {
 		bool locked = mutex_trylock(&sdp->sd_freeze_mutex);
 
-		gfs2_make_fs_ro(sdp);
+		if (sdp->sd_quotad_process &&
+		    current != sdp->sd_quotad_process) {
+			kthread_stop(sdp->sd_quotad_process);
+			sdp->sd_quotad_process = NULL;
+		}
+
+		if (sdp->sd_logd_process &&
+		    current != sdp->sd_logd_process) {
+			kthread_stop(sdp->sd_logd_process);
+			sdp->sd_logd_process = NULL;
+		}
+
+		wait_event_timeout(sdp->sd_log_waitq,
+				   gfs2_log_is_empty(sdp),
+				   HZ * 5);
+
+		sdp->sd_vfs->s_flags |= SB_RDONLY;
 
 		if (locked)
 			mutex_unlock(&sdp->sd_freeze_mutex);

From fe4f7940d212440334f06783e06a15d674013bb1 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Mon, 28 Aug 2023 17:14:32 +0200
Subject: [PATCH 1022/1189] gfs2: Fix asynchronous thread destruction

The kernel threads are currently stopped and destroyed synchronously by
gfs2_make_fs_ro() and gfs2_put_super(), and asynchronously by
signal_our_withdraw(), with no synchronization, so the synchronous and
asynchronous contexts can race with each other.

First, when creating the kernel threads, take an extra task struct
reference so that the task struct won't go away immediately when they
terminate.  This allows those kthreads to terminate immediately when
they're done rather than hanging around as zombies until they are reaped
by kthread_stop().  When kthread_stop() is called on a terminated
kthread, it will return immediately.

Second, in signal_our_withdraw(), once the SDF_JOURNAL_LIVE flag has
been cleared, wake up the logd and quotad wait queues instead of
stopping the logd and quotad kthreads.  The kthreads are then expected
to terminate automatically within short time, but if they cannot, they
will not block the withdraw.

For example, if a user process and one of the kthread decide to withdraw
at the same time, only one of them will perform the actual withdraw and
the other will wait for it to be done.  If the kthread ends up being the
one to wait, the withdrawing user process won't be able to stop it.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/ops_fstype.c | 35 +++++++++++++++++++++++++----------
 fs/gfs2/super.c      | 16 ++++------------
 fs/gfs2/super.h      |  1 +
 fs/gfs2/util.c       | 13 ++-----------
 4 files changed, 32 insertions(+), 33 deletions(-)

diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 6ea295cee463..a1a8be56ead5 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1103,29 +1103,49 @@ static int init_threads(struct gfs2_sbd *sdp)
 	struct task_struct *p;
 	int error = 0;
 
-	p = kthread_run(gfs2_logd, sdp, "gfs2_logd");
+	p = kthread_create(gfs2_logd, sdp, "gfs2_logd");
 	if (IS_ERR(p)) {
 		error = PTR_ERR(p);
-		fs_err(sdp, "can't start logd thread: %d\n", error);
+		fs_err(sdp, "can't create logd thread: %d\n", error);
 		return error;
 	}
+	get_task_struct(p);
 	sdp->sd_logd_process = p;
 
-	p = kthread_run(gfs2_quotad, sdp, "gfs2_quotad");
+	p = kthread_create(gfs2_quotad, sdp, "gfs2_quotad");
 	if (IS_ERR(p)) {
 		error = PTR_ERR(p);
-		fs_err(sdp, "can't start quotad thread: %d\n", error);
+		fs_err(sdp, "can't create quotad thread: %d\n", error);
 		goto fail;
 	}
+	get_task_struct(p);
 	sdp->sd_quotad_process = p;
+
+	wake_up_process(sdp->sd_logd_process);
+	wake_up_process(sdp->sd_quotad_process);
 	return 0;
 
 fail:
 	kthread_stop(sdp->sd_logd_process);
+	put_task_struct(sdp->sd_logd_process);
 	sdp->sd_logd_process = NULL;
 	return error;
 }
 
+void gfs2_destroy_threads(struct gfs2_sbd *sdp)
+{
+	if (sdp->sd_logd_process) {
+		kthread_stop(sdp->sd_logd_process);
+		put_task_struct(sdp->sd_logd_process);
+		sdp->sd_logd_process = NULL;
+	}
+	if (sdp->sd_quotad_process) {
+		kthread_stop(sdp->sd_quotad_process);
+		put_task_struct(sdp->sd_quotad_process);
+		sdp->sd_quotad_process = NULL;
+	}
+}
+
 /**
  * gfs2_fill_super - Read in superblock
  * @sb: The VFS superblock
@@ -1276,12 +1296,7 @@ static int gfs2_fill_super(struct super_block *sb, struct fs_context *fc)
 
 	if (error) {
 		gfs2_freeze_unlock(&sdp->sd_freeze_gh);
-		if (sdp->sd_quotad_process)
-			kthread_stop(sdp->sd_quotad_process);
-		sdp->sd_quotad_process = NULL;
-		if (sdp->sd_logd_process)
-			kthread_stop(sdp->sd_logd_process);
-		sdp->sd_logd_process = NULL;
+		gfs2_destroy_threads(sdp);
 		fs_err(sdp, "can't make FS RW: %d\n", error);
 		goto fail_per_node;
 	}
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 119a5b20eb00..be3f69c15edc 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -549,17 +549,7 @@ void gfs2_make_fs_ro(struct gfs2_sbd *sdp)
 	if (!test_bit(SDF_KILL, &sdp->sd_flags))
 		gfs2_flush_delete_work(sdp);
 
-	if (!log_write_allowed && current == sdp->sd_quotad_process)
-		fs_warn(sdp, "The quotad daemon is withdrawing.\n");
-	else if (sdp->sd_quotad_process)
-		kthread_stop(sdp->sd_quotad_process);
-	sdp->sd_quotad_process = NULL;
-
-	if (!log_write_allowed && current == sdp->sd_logd_process)
-		fs_warn(sdp, "The logd daemon is withdrawing.\n");
-	else if (sdp->sd_logd_process)
-		kthread_stop(sdp->sd_logd_process);
-	sdp->sd_logd_process = NULL;
+	gfs2_destroy_threads(sdp);
 
 	if (log_write_allowed) {
 		gfs2_quota_sync(sdp->sd_vfs, 0);
@@ -615,8 +605,10 @@ restart:
 	if (!sb_rdonly(sb)) {
 		gfs2_make_fs_ro(sdp);
 	}
-	if (gfs2_withdrawn(sdp))
+	if (gfs2_withdrawn(sdp)) {
+		gfs2_destroy_threads(sdp);
 		gfs2_quota_cleanup(sdp);
+	}
 	WARN_ON(gfs2_withdrawing(sdp));
 
 	/*  At this point, we're through modifying the disk  */
diff --git a/fs/gfs2/super.h b/fs/gfs2/super.h
index bba58629bc45..ab9c83106932 100644
--- a/fs/gfs2/super.h
+++ b/fs/gfs2/super.h
@@ -36,6 +36,7 @@ extern int gfs2_lookup_in_master_dir(struct gfs2_sbd *sdp, char *filename,
 extern int gfs2_make_fs_rw(struct gfs2_sbd *sdp);
 extern void gfs2_make_fs_ro(struct gfs2_sbd *sdp);
 extern void gfs2_online_uevent(struct gfs2_sbd *sdp);
+extern void gfs2_destroy_threads(struct gfs2_sbd *sdp);
 extern int gfs2_statfs_init(struct gfs2_sbd *sdp);
 extern void gfs2_statfs_change(struct gfs2_sbd *sdp, s64 total, s64 free,
 			       s64 dinodes);
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index b3086a9baf00..65a3c7b1a51e 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -151,17 +151,8 @@ static void signal_our_withdraw(struct gfs2_sbd *sdp)
 	if (!sb_rdonly(sdp->sd_vfs)) {
 		bool locked = mutex_trylock(&sdp->sd_freeze_mutex);
 
-		if (sdp->sd_quotad_process &&
-		    current != sdp->sd_quotad_process) {
-			kthread_stop(sdp->sd_quotad_process);
-			sdp->sd_quotad_process = NULL;
-		}
-
-		if (sdp->sd_logd_process &&
-		    current != sdp->sd_logd_process) {
-			kthread_stop(sdp->sd_logd_process);
-			sdp->sd_logd_process = NULL;
-		}
+		wake_up(&sdp->sd_logd_waitq);
+		wake_up(&sdp->sd_quota_wait);
 
 		wait_event_timeout(sdp->sd_log_waitq,
 				   gfs2_log_is_empty(sdp),

From e4a8b5481c59a3f1252f595330c2d2cd038886b2 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Fri, 25 Aug 2023 11:06:20 +0200
Subject: [PATCH 1023/1189] gfs2: Switch to wait_event in gfs2_quotad

In gfs2_quotad(), switch from an open-coded wait loop to
wait_event_interruptible_timeout().

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/quota.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 75be0d8e243f..5201bb403fc6 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -1557,7 +1557,6 @@ int gfs2_quotad(void *data)
 	unsigned long statfs_timeo = 0;
 	unsigned long quotad_timeo = 0;
 	unsigned long t = 0;
-	DEFINE_WAIT(wait);
 
 	while (!kthread_should_stop()) {
 
@@ -1583,12 +1582,12 @@ int gfs2_quotad(void *data)
 bypass:
 		t = min(quotad_timeo, statfs_timeo);
 
-		prepare_to_wait(&sdp->sd_quota_wait, &wait, TASK_INTERRUPTIBLE);
-		if (!sdp->sd_statfs_force_sync)
-			t -= schedule_timeout(t);
-		else
+		t = wait_event_interruptible_timeout(sdp->sd_quota_wait,
+				sdp->sd_statfs_force_sync,
+				t);
+
+		if (sdp->sd_statfs_force_sync)
 			t = 0;
-		finish_wait(&sdp->sd_quota_wait, &wait);
 	}
 
 	return 0;

From fe0690f0a6f190a9ec0736c01ddeba7a729cf30d Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Fri, 25 Aug 2023 11:18:38 +0200
Subject: [PATCH 1024/1189] gfs2: Sanitize kthread stopping

Immediately stop the logd and quotad kernel threads when a filesystem
withdraw is detected: those threads aren't doing anything useful after a
withdraw.  (Depends on the extra logd and quotad task struct references
held since commit 7a109f383fa3 ("gfs2: Fix asynchronous thread
destruction").)

In addition, check for kthread_should_stop() in the wait condition in
gfs2_quotad() to stop immediately when kthread_stop() is called.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/log.c   | 9 ++++-----
 fs/gfs2/quota.c | 9 +++++----
 2 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index addf4ce0bedd..e5271ae87d1c 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -1298,11 +1298,9 @@ int gfs2_logd(void *data)
 	unsigned long t = 1;
 
 	while (!kthread_should_stop()) {
+		if (gfs2_withdrawn(sdp))
+			break;
 
-		if (gfs2_withdrawn(sdp)) {
-			msleep_interruptible(HZ);
-			continue;
-		}
 		/* Check for errors writing to the journal */
 		if (sdp->sd_log_error) {
 			gfs2_lm(sdp,
@@ -1311,7 +1309,7 @@ int gfs2_logd(void *data)
 				"prevent further damage.\n",
 				sdp->sd_fsname, sdp->sd_log_error);
 			gfs2_withdraw(sdp);
-			continue;
+			break;
 		}
 
 		if (gfs2_jrnl_flush_reqd(sdp) || t == 0) {
@@ -1339,6 +1337,7 @@ int gfs2_logd(void *data)
 				gfs2_ail_flush_reqd(sdp) ||
 				gfs2_jrnl_flush_reqd(sdp) ||
 				sdp->sd_log_error ||
+				gfs2_withdrawn(sdp) ||
 				kthread_should_stop(),
 				t);
 	}
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 5201bb403fc6..3a3189f5104a 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -1559,9 +1559,9 @@ int gfs2_quotad(void *data)
 	unsigned long t = 0;
 
 	while (!kthread_should_stop()) {
-
 		if (gfs2_withdrawn(sdp))
-			goto bypass;
+			break;
+
 		/* Update the master statfs file */
 		if (sdp->sd_statfs_force_sync) {
 			int error = gfs2_statfs_sync(sdp->sd_vfs, 0);
@@ -1579,11 +1579,12 @@ int gfs2_quotad(void *data)
 
 		try_to_freeze();
 
-bypass:
 		t = min(quotad_timeo, statfs_timeo);
 
 		t = wait_event_interruptible_timeout(sdp->sd_quota_wait,
-				sdp->sd_statfs_force_sync,
+				sdp->sd_statfs_force_sync ||
+				gfs2_withdrawn(sdp) ||
+				kthread_should_stop(),
 				t);
 
 		if (sdp->sd_statfs_force_sync)

From e3da6be3d70449a1f14c99f13cc1eb453a2be4ea Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Wed, 30 Aug 2023 22:09:36 +0200
Subject: [PATCH 1025/1189] gfs2: Fix withdraw race

Function gfs2_withdraw() tries to synchronize concurrent callers by
atomically setting the SDF_WITHDRAWN flag in the first caller, setting
the SDF_WITHDRAW_IN_PROG flag to indicate that a withdraw is in
progress, performing the actual withdraw, and clearing the
SDF_WITHDRAW_IN_PROG flag when done.  All other callers wait for the
SDF_WITHDRAW_IN_PROG flag to be cleared before returning.

This leaves a small window in which callers can find the SDF_WITHDRAWN
flag set before the SDF_WITHDRAW_IN_PROG flag has been set, causing them
to return prematurely, before the withdraw has been completed.

Fix that by setting the SDF_WITHDRAWN and SDF_WITHDRAW_IN_PROG flags
atomically.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/util.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index 65a3c7b1a51e..da29fafb6272 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -323,19 +323,19 @@ int gfs2_withdraw(struct gfs2_sbd *sdp)
 	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
 	const struct lm_lockops *lm = ls->ls_ops;
 
-	if (sdp->sd_args.ar_errors == GFS2_ERRORS_WITHDRAW &&
-	    test_and_set_bit(SDF_WITHDRAWN, &sdp->sd_flags)) {
-		if (!test_bit(SDF_WITHDRAW_IN_PROG, &sdp->sd_flags))
-			return -1;
-
-		wait_on_bit(&sdp->sd_flags, SDF_WITHDRAW_IN_PROG,
-			    TASK_UNINTERRUPTIBLE);
-		return -1;
-	}
-
-	set_bit(SDF_WITHDRAW_IN_PROG, &sdp->sd_flags);
-
 	if (sdp->sd_args.ar_errors == GFS2_ERRORS_WITHDRAW) {
+		unsigned long old = READ_ONCE(sdp->sd_flags), new;
+
+		do {
+			if (old & BIT(SDF_WITHDRAWN)) {
+				wait_on_bit(&sdp->sd_flags,
+					    SDF_WITHDRAW_IN_PROG,
+					    TASK_UNINTERRUPTIBLE);
+				return -1;
+			}
+			new = old | BIT(SDF_WITHDRAWN) | BIT(SDF_WITHDRAW_IN_PROG);
+		} while (unlikely(!try_cmpxchg(&sdp->sd_flags, &old, new)));
+
 		fs_err(sdp, "about to withdraw this file system\n");
 		BUG_ON(sdp->sd_args.ar_debug);
 

From 5c0dc371a28e9a1eb4b80093f37c79d28305cc18 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Mon, 28 Aug 2023 18:02:22 +0200
Subject: [PATCH 1026/1189] gfs2: Rename "gfs_recovery" workqueue to
 "gfs2_recovery"

Rename the "gfs_recovery" workqueue to "gfs2_recovery", and
gfs_recovery_wq to gfs2_recovery_wq.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/main.c     | 8 ++++----
 fs/gfs2/recovery.c | 4 ++--
 fs/gfs2/recovery.h | 2 +-
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index afcb32854f14..69bded82f376 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -152,9 +152,9 @@ static int __init init_gfs2_fs(void)
 		goto fail_shrinker;
 
 	error = -ENOMEM;
-	gfs_recovery_wq = alloc_workqueue("gfs_recovery",
+	gfs2_recovery_wq = alloc_workqueue("gfs2_recovery",
 					  WQ_MEM_RECLAIM | WQ_FREEZABLE, 0);
-	if (!gfs_recovery_wq)
+	if (!gfs2_recovery_wq)
 		goto fail_wq1;
 
 	gfs2_control_wq = alloc_workqueue("gfs2_control",
@@ -194,7 +194,7 @@ fail_mempool:
 fail_wq3:
 	destroy_workqueue(gfs2_control_wq);
 fail_wq2:
-	destroy_workqueue(gfs_recovery_wq);
+	destroy_workqueue(gfs2_recovery_wq);
 fail_wq1:
 	unregister_shrinker(&gfs2_qd_shrinker);
 fail_shrinker:
@@ -234,7 +234,7 @@ static void __exit exit_gfs2_fs(void)
 	gfs2_unregister_debugfs();
 	unregister_filesystem(&gfs2_fs_type);
 	unregister_filesystem(&gfs2meta_fs_type);
-	destroy_workqueue(gfs_recovery_wq);
+	destroy_workqueue(gfs2_recovery_wq);
 	destroy_workqueue(gfs2_control_wq);
 	destroy_workqueue(gfs2_freeze_wq);
 	list_lru_destroy(&gfs2_qd_lru);
diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
index 9c7a9f640bad..5aae02669a40 100644
--- a/fs/gfs2/recovery.c
+++ b/fs/gfs2/recovery.c
@@ -27,7 +27,7 @@
 #include "util.h"
 #include "dir.h"
 
-struct workqueue_struct *gfs_recovery_wq;
+struct workqueue_struct *gfs2_recovery_wq;
 
 int gfs2_replay_read_block(struct gfs2_jdesc *jd, unsigned int blk,
 			   struct buffer_head **bh)
@@ -570,7 +570,7 @@ int gfs2_recover_journal(struct gfs2_jdesc *jd, bool wait)
 		return -EBUSY;
 
 	/* we have JDF_RECOVERY, queue should always succeed */
-	rv = queue_work(gfs_recovery_wq, &jd->jd_work);
+	rv = queue_work(gfs2_recovery_wq, &jd->jd_work);
 	BUG_ON(!rv);
 
 	if (wait)
diff --git a/fs/gfs2/recovery.h b/fs/gfs2/recovery.h
index 0d30f8e804f4..7a0c9d0b7503 100644
--- a/fs/gfs2/recovery.h
+++ b/fs/gfs2/recovery.h
@@ -9,7 +9,7 @@
 
 #include "incore.h"
 
-extern struct workqueue_struct *gfs_recovery_wq;
+extern struct workqueue_struct *gfs2_recovery_wq;
 
 static inline void gfs2_replay_incr_blk(struct gfs2_jdesc *jd, u32 *blk)
 {

From ab8eecf5d0a7b8e8b06e282aeb051dc37eecaf21 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Mon, 28 Aug 2023 18:03:30 +0200
Subject: [PATCH 1027/1189] gfs2: Rename "freeze_workqueue" to "gfs2_freeze"

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index 69bded82f376..66eb98b690a2 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -162,7 +162,7 @@ static int __init init_gfs2_fs(void)
 	if (!gfs2_control_wq)
 		goto fail_wq2;
 
-	gfs2_freeze_wq = alloc_workqueue("freeze_workqueue", 0, 0);
+	gfs2_freeze_wq = alloc_workqueue("gfs2_freeze", 0, 0);
 
 	if (!gfs2_freeze_wq)
 		goto fail_wq3;

From 267d1a011ec2345a320e84c16d8b91411f165aa8 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Mon, 28 Aug 2023 18:05:44 +0200
Subject: [PATCH 1028/1189] gfs2: Add device name to gfs2_logd and gfs2_quotad

Add the device name to the names of the gfs2_logd and gfs2_quotad kernel
threads to allow for easier identification.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/ops_fstype.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index a1a8be56ead5..bcbe95229e89 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1103,7 +1103,7 @@ static int init_threads(struct gfs2_sbd *sdp)
 	struct task_struct *p;
 	int error = 0;
 
-	p = kthread_create(gfs2_logd, sdp, "gfs2_logd");
+	p = kthread_create(gfs2_logd, sdp, "gfs2_logd/%s", sdp->sd_fsname);
 	if (IS_ERR(p)) {
 		error = PTR_ERR(p);
 		fs_err(sdp, "can't create logd thread: %d\n", error);
@@ -1112,7 +1112,7 @@ static int init_threads(struct gfs2_sbd *sdp)
 	get_task_struct(p);
 	sdp->sd_logd_process = p;
 
-	p = kthread_create(gfs2_quotad, sdp, "gfs2_quotad");
+	p = kthread_create(gfs2_quotad, sdp, "gfs2_quotad/%s", sdp->sd_fsname);
 	if (IS_ERR(p)) {
 		error = PTR_ERR(p);
 		fs_err(sdp, "can't create quotad thread: %d\n", error);

From eef46ab713f78591fe2cb20f5e90d9a8fdbddd59 Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Wed, 28 Jun 2023 13:52:42 -0500
Subject: [PATCH 1029/1189] gfs2: Introduce new quota=quiet mount option

This patch adds a new mount option quota=quiet which is the same as
quota=on but it suppresses gfs2 quota error messages.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/incore.h     |  1 +
 fs/gfs2/ops_fstype.c |  1 +
 fs/gfs2/quota.c      | 17 +++++++++++------
 fs/gfs2/super.c      |  3 +++
 4 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index ab857431dfa4..7e94cf3562d6 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -537,6 +537,7 @@ struct gfs2_statfs_change_host {
 #define GFS2_QUOTA_OFF		0
 #define GFS2_QUOTA_ACCOUNT	1
 #define GFS2_QUOTA_ON		2
+#define GFS2_QUOTA_QUIET	3 /* on but not complaining */
 
 #define GFS2_DATA_DEFAULT	GFS2_DATA_ORDERED
 #define GFS2_DATA_WRITEBACK	1
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index bcbe95229e89..33ca04733e93 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1396,6 +1396,7 @@ static const struct constant_table gfs2_param_quota[] = {
 	{"off",        GFS2_QUOTA_OFF},
 	{"account",    GFS2_QUOTA_ACCOUNT},
 	{"on",         GFS2_QUOTA_ON},
+	{"quiet",      GFS2_QUOTA_QUIET},
 	{}
 };
 
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 3a3189f5104a..0cc585064eae 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -1083,7 +1083,8 @@ int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
 	u32 x;
 	int error = 0;
 
-	if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
+	if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON &&
+	    sdp->sd_args.ar_quota != GFS2_QUOTA_QUIET)
 		return 0;
 
 	error = gfs2_quota_hold(ip, uid, gid);
@@ -1202,10 +1203,11 @@ static int print_message(struct gfs2_quota_data *qd, char *type)
 {
 	struct gfs2_sbd *sdp = qd->qd_sbd;
 
-	fs_info(sdp, "quota %s for %s %u\n",
-		type,
-		(qd->qd_id.type == USRQUOTA) ? "user" : "group",
-		from_kqid(&init_user_ns, qd->qd_id));
+	if (sdp->sd_args.ar_quota != GFS2_QUOTA_QUIET)
+		fs_info(sdp, "quota %s for %s %u\n",
+			type,
+			(qd->qd_id.type == USRQUOTA) ? "user" : "group",
+			from_kqid(&init_user_ns, qd->qd_id));
 
 	return 0;
 }
@@ -1291,7 +1293,8 @@ void gfs2_quota_change(struct gfs2_inode *ip, s64 change,
 	u32 x;
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 
-	if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON ||
+	if ((sdp->sd_args.ar_quota != GFS2_QUOTA_ON &&
+	    sdp->sd_args.ar_quota != GFS2_QUOTA_QUIET) ||
 	    gfs2_assert_warn(sdp, change))
 		return;
 	if (ip->i_diskflags & GFS2_DIF_SYSTEM)
@@ -1601,6 +1604,8 @@ static int gfs2_quota_get_state(struct super_block *sb, struct qc_state *state)
 	memset(state, 0, sizeof(*state));
 
 	switch (sdp->sd_args.ar_quota) {
+	case GFS2_QUOTA_QUIET:
+		fallthrough;
 	case GFS2_QUOTA_ON:
 		state->s_state[USRQUOTA].flags |= QCI_LIMITS_ENFORCED;
 		state->s_state[GRPQUOTA].flags |= QCI_LIMITS_ENFORCED;
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index be3f69c15edc..18993ecc2f70 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1119,6 +1119,9 @@ static int gfs2_show_options(struct seq_file *s, struct dentry *root)
 		case GFS2_QUOTA_ON:
 			state = "on";
 			break;
+		case GFS2_QUOTA_QUIET:
+			state = "quiet";
+			break;
 		default:
 			state = "unknown";
 			break;

From 768963ab07e5219d7ae84a6e4ec61bc59bc4b81d Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Wed, 31 May 2023 10:08:49 -0500
Subject: [PATCH 1030/1189] gfs2: remove dead code for quota writes

Since patch 845802b112ee function gfs2_write_buf_to_page checks if the
target inode is jdata or ordered. This function only operates on the
system quota file, which is always jdata, so the check for jdata is
useless. This patch removes it.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/quota.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 0cc585064eae..2f311118df9b 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -772,10 +772,7 @@ static int gfs2_write_buf_to_page(struct gfs2_inode *ip, unsigned long index,
 			set_buffer_uptodate(bh);
 		if (bh_read(bh, REQ_META | REQ_PRIO) < 0)
 			goto unlock_out;
-		if (gfs2_is_jdata(ip))
-			gfs2_trans_add_data(ip->i_gl, bh);
-		else
-			gfs2_ordered_add_inode(ip);
+		gfs2_trans_add_data(ip->i_gl, bh);
 
 		/* If we need to write to the next block as well */
 		if (to_write > (bsize - boff)) {

From ee1768e467a9c0f272192da1ce0ea5a9caf98ccc Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Wed, 31 May 2023 10:25:29 -0500
Subject: [PATCH 1031/1189] gfs2: Pass sdp to gfs2_adjust_quota

Before this change function gfs2_adjust_quota's first parameter was an
gfs2_inode pointer. But it always pointed to the quota inode. Here we
switch that to pass the superblock pointer, sdp, so it is easier to read
the code and understand that it's only dealing with the quota inode.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/quota.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 2f311118df9b..3d78026c63c4 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -830,7 +830,7 @@ static int gfs2_write_disk_quota(struct gfs2_inode *ip, struct gfs2_quota *qp,
 
 /**
  * gfs2_adjust_quota - adjust record of current block usage
- * @ip: The quota inode
+ * @sdp: The superblock
  * @loc: Offset of the entry in the quota file
  * @change: The amount of usage change to record
  * @qd: The quota data
@@ -842,12 +842,12 @@ static int gfs2_write_disk_quota(struct gfs2_inode *ip, struct gfs2_quota *qp,
  * Returns: 0 or -ve on error
  */
 
-static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
+static int gfs2_adjust_quota(struct gfs2_sbd *sdp, loff_t loc,
 			     s64 change, struct gfs2_quota_data *qd,
 			     struct qc_dqblk *fdq)
 {
+	struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode);
 	struct inode *inode = &ip->i_inode;
-	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct gfs2_quota q;
 	int err;
 	u64 size;
@@ -971,7 +971,8 @@ static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda)
 	for (x = 0; x < num_qd; x++) {
 		qd = qda[x];
 		offset = qd2offset(qd);
-		error = gfs2_adjust_quota(ip, offset, qd->qd_change_sync, qd, NULL);
+		error = gfs2_adjust_quota(sdp, offset, qd->qd_change_sync, qd,
+							NULL);
 		if (error)
 			goto out_end_trans;
 
@@ -1749,7 +1750,7 @@ static int gfs2_set_dqblk(struct super_block *sb, struct kqid qid,
 		goto out_release;
 
 	/* Apply changes */
-	error = gfs2_adjust_quota(ip, offset, 0, qd, fdq);
+	error = gfs2_adjust_quota(sdp, offset, 0, qd, fdq);
 	if (!error)
 		clear_bit(QDF_QMSG_QUIET, &qd->qd_flags);
 

From adfd2b5e4f87590fcd0abd756c71b0aefe20dbf4 Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Wed, 31 May 2023 10:31:33 -0500
Subject: [PATCH 1032/1189] gfs2: pass sdp in to gfs2_write_disk_quota

Like the previous patch, we now pass the superblock pointer to function
gfs2_write_disk_quota. This makes the code more understandable, since it
only operates on the quota inode.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/quota.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 3d78026c63c4..3dade83bd358 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -798,9 +798,10 @@ unlock_out:
 	return -EIO;
 }
 
-static int gfs2_write_disk_quota(struct gfs2_inode *ip, struct gfs2_quota *qp,
+static int gfs2_write_disk_quota(struct gfs2_sbd *sdp, struct gfs2_quota *qp,
 				 loff_t loc)
 {
+	struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode);
 	unsigned long pg_beg;
 	unsigned pg_off, nbytes, overflow = 0;
 	int pg_oflow = 0, error;
@@ -884,7 +885,7 @@ static int gfs2_adjust_quota(struct gfs2_sbd *sdp, loff_t loc,
 		}
 	}
 
-	err = gfs2_write_disk_quota(ip, &q, loc);
+	err = gfs2_write_disk_quota(sdp, &q, loc);
 	if (!err) {
 		size = loc + sizeof(struct gfs2_quota);
 		if (size > inode->i_size)

From d96dad2715672c8b9f16b54216da46514aaeb453 Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Wed, 31 May 2023 10:39:42 -0500
Subject: [PATCH 1033/1189] gfs2: pass sdp to gfs2_write_buf_to_page

This patch passes the superblock pointer to gfs2_write_buf_to_page so it
becomes more apparent it's dealing with the system quota file.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/quota.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 3dade83bd358..7b79fcc65763 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -729,11 +729,11 @@ static void do_qc(struct gfs2_quota_data *qd, s64 change, int qc_type)
 	mutex_unlock(&sdp->sd_quota_mutex);
 }
 
-static int gfs2_write_buf_to_page(struct gfs2_inode *ip, unsigned long index,
+static int gfs2_write_buf_to_page(struct gfs2_sbd *sdp, unsigned long index,
 				  unsigned off, void *buf, unsigned bytes)
 {
+	struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode);
 	struct inode *inode = &ip->i_inode;
-	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct address_space *mapping = inode->i_mapping;
 	struct page *page;
 	struct buffer_head *bh;
@@ -801,7 +801,6 @@ unlock_out:
 static int gfs2_write_disk_quota(struct gfs2_sbd *sdp, struct gfs2_quota *qp,
 				 loff_t loc)
 {
-	struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode);
 	unsigned long pg_beg;
 	unsigned pg_off, nbytes, overflow = 0;
 	int pg_oflow = 0, error;
@@ -819,11 +818,11 @@ static int gfs2_write_disk_quota(struct gfs2_sbd *sdp, struct gfs2_quota *qp,
 	}
 
 	ptr = qp;
-	error = gfs2_write_buf_to_page(ip, pg_beg, pg_off, ptr,
+	error = gfs2_write_buf_to_page(sdp, pg_beg, pg_off, ptr,
 				       nbytes - overflow);
 	/* If there's an overflow, write the remaining bytes to the next page */
 	if (!error && pg_oflow)
-		error = gfs2_write_buf_to_page(ip, pg_beg + 1, 0,
+		error = gfs2_write_buf_to_page(sdp, pg_beg + 1, 0,
 					       ptr + nbytes - overflow,
 					       overflow);
 	return error;

From f0418e4b568ac4759336e1ff8a53582ec88ea966 Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Wed, 31 May 2023 10:47:17 -0500
Subject: [PATCH 1034/1189] gfs2: remove unneeded variable done

Function gfs2_write_buf_to_page uses variable done to exit its loop, but
it's unnecessary if we just code an infinite loop and exit when we need.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/quota.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 7b79fcc65763..59c6fa01455d 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -740,7 +740,6 @@ static int gfs2_write_buf_to_page(struct gfs2_sbd *sdp, unsigned long index,
 	u64 blk;
 	unsigned bsize = sdp->sd_sb.sb_bsize, bnum = 0, boff = 0;
 	unsigned to_write = bytes, pg_off = off;
-	int done = 0;
 
 	blk = index << (PAGE_SHIFT - sdp->sd_sb.sb_bsize_shift);
 	boff = off % bsize;
@@ -752,7 +751,7 @@ static int gfs2_write_buf_to_page(struct gfs2_sbd *sdp, unsigned long index,
 		create_empty_buffers(page, bsize, 0);
 
 	bh = page_buffers(page);
-	while (!done) {
+	for(;;) {
 		/* Find the beginning block within the page */
 		if (pg_off >= ((bnum * bsize) + bsize)) {
 			bh = bh->b_this_page;
@@ -781,7 +780,7 @@ static int gfs2_write_buf_to_page(struct gfs2_sbd *sdp, unsigned long index,
 			boff = pg_off % bsize;
 			continue;
 		}
-		done = 1;
+		break;
 	}
 
 	/* Write to the page, now that we have setup the buffer(s) */

From e34c16c9c699461e7d3f9eed28069e3b8466d871 Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Wed, 31 May 2023 11:41:16 -0500
Subject: [PATCH 1035/1189] gfs2: remove unneeded pg_oflow variable

Function gfs2_write_disk_quota checks if its write overflows onto
another page, and if so, does a second write. Before this patch it kept
two variables for this, but only one is needed. This patch simplifies
it by eliminating pg_oflow.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/quota.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 59c6fa01455d..678b21cad303 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -802,7 +802,7 @@ static int gfs2_write_disk_quota(struct gfs2_sbd *sdp, struct gfs2_quota *qp,
 {
 	unsigned long pg_beg;
 	unsigned pg_off, nbytes, overflow = 0;
-	int pg_oflow = 0, error;
+	int error;
 	void *ptr;
 
 	nbytes = sizeof(struct gfs2_quota);
@@ -811,16 +811,14 @@ static int gfs2_write_disk_quota(struct gfs2_sbd *sdp, struct gfs2_quota *qp,
 	pg_off = offset_in_page(loc);
 
 	/* If the quota straddles a page boundary, split the write in two */
-	if ((pg_off + nbytes) > PAGE_SIZE) {
-		pg_oflow = 1;
+	if ((pg_off + nbytes) > PAGE_SIZE)
 		overflow = (pg_off + nbytes) - PAGE_SIZE;
-	}
 
 	ptr = qp;
 	error = gfs2_write_buf_to_page(sdp, pg_beg, pg_off, ptr,
 				       nbytes - overflow);
 	/* If there's an overflow, write the remaining bytes to the next page */
-	if (!error && pg_oflow)
+	if (!error && overflow)
 		error = gfs2_write_buf_to_page(sdp, pg_beg + 1, 0,
 					       ptr + nbytes - overflow,
 					       overflow);

From 2a4f651167560adae05e644e41d2666d727c549b Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Wed, 31 May 2023 12:31:52 -0500
Subject: [PATCH 1036/1189] gfs2: Simplify function need_sync

This patch simplifies function need_sync by eliminating a variable in
favor of just returning the appropriate value as soon as we know it.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/quota.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 678b21cad303..fa1d48d5c112 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -1107,16 +1107,15 @@ int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
 	return error;
 }
 
-static int need_sync(struct gfs2_quota_data *qd)
+static bool need_sync(struct gfs2_quota_data *qd)
 {
 	struct gfs2_sbd *sdp = qd->qd_sbd;
 	struct gfs2_tune *gt = &sdp->sd_tune;
 	s64 value;
 	unsigned int num, den;
-	int do_sync = 1;
 
 	if (!qd->qd_qb.qb_limit)
-		return 0;
+		return false;
 
 	spin_lock(&qd_lock);
 	value = qd->qd_change;
@@ -1128,19 +1127,19 @@ static int need_sync(struct gfs2_quota_data *qd)
 	spin_unlock(&gt->gt_spin);
 
 	if (value < 0)
-		do_sync = 0;
+		return false;
 	else if ((s64)be64_to_cpu(qd->qd_qb.qb_value) >=
 		 (s64)be64_to_cpu(qd->qd_qb.qb_limit))
-		do_sync = 0;
+		return false;
 	else {
 		value *= gfs2_jindex_size(sdp) * num;
 		value = div_s64(value, den);
 		value += (s64)be64_to_cpu(qd->qd_qb.qb_value);
 		if (value < (s64)be64_to_cpu(qd->qd_qb.qb_limit))
-			do_sync = 0;
+			return false;
 	}
 
-	return do_sync;
+	return true;
 }
 
 void gfs2_quota_unlock(struct gfs2_inode *ip)
@@ -1156,7 +1155,7 @@ void gfs2_quota_unlock(struct gfs2_inode *ip)
 
 	for (x = 0; x < ip->i_qadata->qa_qd_num; x++) {
 		struct gfs2_quota_data *qd;
-		int sync;
+		bool sync;
 
 		qd = ip->i_qadata->qa_qd[x];
 		sync = need_sync(qd);

From 9f494e9bdcc54eaed94fcc8fe5d4d5a51c36834c Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Wed, 30 Aug 2023 07:57:47 -0500
Subject: [PATCH 1037/1189] gfs2: Don't try to sync non-changes

Function need_sync is supposed to determine if a qd element needs to be
synced. If the "change" (qd_change) is zero, it does not need to be
synced because there's literally no change in the value. Before this
patch need_sync returned false if value < 0. That should be <= 0.
This patch changes the check to <=.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/quota.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index fa1d48d5c112..9be210f3dbd8 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -1126,7 +1126,7 @@ static bool need_sync(struct gfs2_quota_data *qd)
 	den = gt->gt_quota_scale_den;
 	spin_unlock(&gt->gt_spin);
 
-	if (value < 0)
+	if (value <= 0)
 		return false;
 	else if ((s64)be64_to_cpu(qd->qd_qb.qb_value) >=
 		 (s64)be64_to_cpu(qd->qd_qb.qb_limit))

From 03d468f1c0469707086f260d4544a2552c7bfa6e Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Fri, 16 Jun 2023 06:59:02 -0500
Subject: [PATCH 1038/1189] gfs2: improvements to sysfs status

This patch adds some new fields to the gfs2 status file in sysfs to aid
in debugging.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/sys.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index a85fe7b92911..32d5be85382e 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -98,7 +98,10 @@ static ssize_t status_show(struct gfs2_sbd *sdp, char *buf)
 		     "sd_log_flush_head:        %d\n"
 		     "sd_log_flush_tail:        %d\n"
 		     "sd_log_blks_reserved:     %d\n"
-		     "sd_log_revokes_available: %d\n",
+		     "sd_log_revokes_available: %d\n"
+		     "sd_log_pinned:            %d\n"
+		     "sd_log_thresh1:           %d\n"
+		     "sd_log_thresh2:           %d\n",
 		     test_bit(SDF_JOURNAL_CHECKED, &f),
 		     test_bit(SDF_JOURNAL_LIVE, &f),
 		     (sdp->sd_jdesc ? sdp->sd_jdesc->jd_jid : 0),
@@ -128,7 +131,10 @@ static ssize_t status_show(struct gfs2_sbd *sdp, char *buf)
 		     sdp->sd_log_flush_head,
 		     sdp->sd_log_flush_tail,
 		     sdp->sd_log_blks_reserved,
-		     atomic_read(&sdp->sd_log_revokes_available));
+		     atomic_read(&sdp->sd_log_revokes_available),
+		     atomic_read(&sdp->sd_log_pinned),
+		     atomic_read(&sdp->sd_log_thresh1),
+		     atomic_read(&sdp->sd_log_thresh2));
 	return s;
 }
 

From a4d22e337d022d7bb8da25c18629bac2af24ec81 Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Fri, 16 Jun 2023 12:36:51 -0500
Subject: [PATCH 1039/1189] gfs2: move qdsb_put and reduce redundancy

This patch looks more invasive than it is. It simply moves function
qdsb_put before qd_unlock, then changes qd_unlock to call it rather than
open coding it. Again, this reduces redundancy.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/quota.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 9be210f3dbd8..21100feb1db7 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -509,13 +509,18 @@ static int qd_fish(struct gfs2_sbd *sdp, struct gfs2_quota_data **qdp)
 	return 0;
 }
 
+static void qdsb_put(struct gfs2_quota_data *qd)
+{
+	bh_put(qd);
+	slot_put(qd);
+	qd_put(qd);
+}
+
 static void qd_unlock(struct gfs2_quota_data *qd)
 {
 	gfs2_assert_warn(qd->qd_sbd, test_bit(QDF_LOCKED, &qd->qd_flags));
 	clear_bit(QDF_LOCKED, &qd->qd_flags);
-	bh_put(qd);
-	slot_put(qd);
-	qd_put(qd);
+	qdsb_put(qd);
 }
 
 static int qdsb_get(struct gfs2_sbd *sdp, struct kqid qid,
@@ -544,13 +549,6 @@ fail:
 	return error;
 }
 
-static void qdsb_put(struct gfs2_quota_data *qd)
-{
-	bh_put(qd);
-	slot_put(qd);
-	qd_put(qd);
-}
-
 /**
  * gfs2_qa_get - make sure we have a quota allocations data structure,
  *               if necessary

From f511e60a55c5f2c8a9781efb67f1897a3b3aebb1 Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Tue, 20 Jun 2023 13:49:57 -0500
Subject: [PATCH 1040/1189] gfs2: Small gfs2_quota_lock cleanup

No need to set error = 0 since it's set further down.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/quota.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 21100feb1db7..c4da8c01deb7 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -1074,7 +1074,7 @@ int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_quota_data *qd;
 	u32 x;
-	int error = 0;
+	int error;
 
 	if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON &&
 	    sdp->sd_args.ar_quota != GFS2_QUOTA_QUIET)

From dec64ae37bf90c2ae3fba2089f5bd1d025c57995 Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Wed, 21 Jun 2023 12:31:15 -0500
Subject: [PATCH 1041/1189] gfs2: Remove useless err set

Function gfs2_adjust_quota set variable err, then set it again to a
different value. This patch removes the redundant set.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/quota.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index c4da8c01deb7..6824c7497d99 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -859,7 +859,6 @@ static int gfs2_adjust_quota(struct gfs2_sbd *sdp, loff_t loc,
 		return err;
 
 	loc -= sizeof(q); /* gfs2_internal_read would've advanced the loc ptr */
-	err = -EIO;
 	be64_add_cpu(&q.qu_value, change);
 	if (((s64)be64_to_cpu(q.qu_value)) < 0)
 		q.qu_value = 0; /* Never go negative on quota usage */

From fce17cb0eebfb90618f0fcfbdc7f8e0aa207c81a Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Thu, 22 Jun 2023 11:04:45 -0500
Subject: [PATCH 1042/1189] gfs2: Set qd_sync_gen in do_sync

Func do_sync was called in two places: gfs2_quota_unlock and
gfs2_quota_sync. In gfs2_quota_sync it updated qd_sync_gen to the latest
superblock sync gen, if do_sync was successful. In gfs2_quota_unlock it
didn't update the value. That can only lead to extra work, for example,
if the value is synced by gfs2_quota_unlock but still has the old value.

This patch moves the setting of qd_sync_gen inside do_sync so we are
guaranteed consistency.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/quota.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 6824c7497d99..e12d54104485 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -991,6 +991,10 @@ out_dq:
 		       GFS2_LOG_HEAD_FLUSH_NORMAL | GFS2_LFC_DO_SYNC);
 out:
 	gfs2_qa_put(ip);
+	if (!error) {
+		for (x = 0; x < num_qd; x++)
+			qda[x]->qd_sync_gen = sdp->sd_quota_sync_gen;
+	}
 	return error;
 }
 
@@ -1334,10 +1338,6 @@ int gfs2_quota_sync(struct super_block *sb, int type)
 		if (num_qd) {
 			if (!error)
 				error = do_sync(num_qd, qda);
-			if (!error)
-				for (x = 0; x < num_qd; x++)
-					qda[x]->qd_sync_gen =
-						sdp->sd_quota_sync_gen;
 
 			for (x = 0; x < num_qd; x++)
 				qd_unlock(qda[x]);

From c9ff3c65c26b8f89c6b925ce257fac348559d484 Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Thu, 22 Jun 2023 11:37:37 -0500
Subject: [PATCH 1043/1189] gfs2: use constant for array size

Function gfs2_quota_unlock declared an array of 4 qd elements. We have a
constant for that, we should be using it.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/quota.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index e12d54104485..9c7234256ebc 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -1146,7 +1146,7 @@ static bool need_sync(struct gfs2_quota_data *qd)
 void gfs2_quota_unlock(struct gfs2_inode *ip)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	struct gfs2_quota_data *qda[4];
+	struct gfs2_quota_data *qda[2 * GFS2_MAXQUOTAS];
 	unsigned int count = 0;
 	u32 x;
 	int found;

From 3932e5073011567d24ce66cf66575d4d81ea8c94 Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Thu, 22 Jun 2023 12:36:59 -0500
Subject: [PATCH 1044/1189] gfs2: Remove quota allocation info from quota file

Function do_sync called gfs2_qa_get and put for quota allocation data.
But the inode in question is the system master quota file, which is
never subject to quotas. Therefore, a qa structure should be unnecessary
and if anything accesses it, it's probably a bug.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/quota.c | 12 ++----------
 1 file changed, 2 insertions(+), 10 deletions(-)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 9c7234256ebc..ecadbcdad9bf 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -905,18 +905,12 @@ static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda)
 	unsigned int nalloc = 0, blocks;
 	int error;
 
-	error = gfs2_qa_get(ip);
-	if (error)
-		return error;
-
 	gfs2_write_calc_reserv(ip, sizeof(struct gfs2_quota),
 			      &data_blocks, &ind_blocks);
 
 	ghs = kmalloc_array(num_qd, sizeof(struct gfs2_holder), GFP_NOFS);
-	if (!ghs) {
-		error = -ENOMEM;
-		goto out;
-	}
+	if (!ghs)
+		return -ENOMEM;
 
 	sort(qda, num_qd, sizeof(struct gfs2_quota_data *), sort_qd, NULL);
 	inode_lock(&ip->i_inode);
@@ -989,8 +983,6 @@ out_dq:
 	kfree(ghs);
 	gfs2_log_flush(ip->i_gl->gl_name.ln_sbd, ip->i_gl,
 		       GFS2_LOG_HEAD_FLUSH_NORMAL | GFS2_LFC_DO_SYNC);
-out:
-	gfs2_qa_put(ip);
 	if (!error) {
 		for (x = 0; x < num_qd; x++)
 			qda[x]->qd_sync_gen = sdp->sd_quota_sync_gen;

From 7dbc6ae60dd7089d8ed42892b6a66c138f0aa7a0 Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Fri, 23 Jun 2023 08:07:55 -0500
Subject: [PATCH 1045/1189] gfs2: introduce qd_bh_get_or_undo

This patch is an attempt to force some consistency in quota sync
processing. Two functions (qd_fish and gfs2_quota_unlock) called
qd_check_sync, after which they both called bh_get, and if that failed,
they took the same steps to undo the actions of qd_check_sync.

This patch introduces a new function, qd_bh_get_or_undo, which performs
the same steps, reducing code redundancy.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/quota.c | 36 +++++++++++++++++++-----------------
 1 file changed, 19 insertions(+), 17 deletions(-)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index ecadbcdad9bf..aba8d31a9a7f 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -473,6 +473,20 @@ static int qd_check_sync(struct gfs2_sbd *sdp, struct gfs2_quota_data *qd,
 	return 1;
 }
 
+static int qd_bh_get_or_undo(struct gfs2_sbd *sdp, struct gfs2_quota_data *qd)
+{
+	int error;
+
+	error = bh_get(qd);
+	if (!error)
+		return 0;
+
+	clear_bit(QDF_LOCKED, &qd->qd_flags);
+	slot_put(qd);
+	qd_put(qd);
+	return error;
+}
+
 static int qd_fish(struct gfs2_sbd *sdp, struct gfs2_quota_data **qdp)
 {
 	struct gfs2_quota_data *qd = NULL, *iter;
@@ -495,17 +509,12 @@ static int qd_fish(struct gfs2_sbd *sdp, struct gfs2_quota_data **qdp)
 	spin_unlock(&qd_lock);
 
 	if (qd) {
-		error = bh_get(qd);
-		if (error) {
-			clear_bit(QDF_LOCKED, &qd->qd_flags);
-			slot_put(qd);
-			qd_put(qd);
+		error = qd_bh_get_or_undo(sdp, qd);
+		if (error)
 			return error;
-		}
+		*qdp = qd;
 	}
 
-	*qdp = qd;
-
 	return 0;
 }
 
@@ -1164,15 +1173,8 @@ void gfs2_quota_unlock(struct gfs2_inode *ip)
 		if (!found)
 			continue;
 
-		gfs2_assert_warn(sdp, qd->qd_change_sync);
-		if (bh_get(qd)) {
-			clear_bit(QDF_LOCKED, &qd->qd_flags);
-			slot_put(qd);
-			qd_put(qd);
-			continue;
-		}
-
-		qda[count++] = qd;
+		if (!qd_bh_get_or_undo(sdp, qd))
+			qda[count++] = qd;
 	}
 
 	if (count) {

From 8f190c97a4f559bc7e8db739026ebb2d0f53ebed Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Mon, 26 Jun 2023 10:55:52 -0500
Subject: [PATCH 1046/1189] gfs2: Simplify qd2offset

This is a minor cleanup of function qd2offset.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/quota.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index aba8d31a9a7f..d45a3a1ed9fe 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -213,12 +213,7 @@ static u64 qd2index(struct gfs2_quota_data *qd)
 
 static u64 qd2offset(struct gfs2_quota_data *qd)
 {
-	u64 offset;
-
-	offset = qd2index(qd);
-	offset *= sizeof(struct gfs2_quota);
-
-	return offset;
+	return qd2index(qd) * sizeof(struct gfs2_quota);
 }
 
 static struct gfs2_quota_data *qd_alloc(unsigned hash, struct gfs2_sbd *sdp, struct kqid qid)

From 9ab7b78a13aff5bcb3b76380f551ed5cf4125280 Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Wed, 28 Jun 2023 07:40:30 -0500
Subject: [PATCH 1047/1189] gfs2: simplify slot_get

Simplify function slot_get and get rid of the goto that jumps into the
middle of an else branch.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/quota.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index d45a3a1ed9fe..8b6a1c14a03e 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -342,20 +342,19 @@ static int slot_get(struct gfs2_quota_data *qd)
 	int error = 0;
 
 	spin_lock(&sdp->sd_bitmap_lock);
-	if (qd->qd_slot_count != 0)
-		goto out;
-
-	error = -ENOSPC;
-	bit = find_first_zero_bit(sdp->sd_quota_bitmap, sdp->sd_quota_slots);
-	if (bit < sdp->sd_quota_slots) {
+	if (qd->qd_slot_count == 0) {
+		bit = find_first_zero_bit(sdp->sd_quota_bitmap,
+					  sdp->sd_quota_slots);
+		if (bit >= sdp->sd_quota_slots) {
+			error = -ENOSPC;
+			goto out;
+		}
 		set_bit(bit, sdp->sd_quota_bitmap);
 		qd->qd_slot = bit;
-		error = 0;
-out:
-		qd->qd_slot_count++;
 	}
+	qd->qd_slot_count++;
+out:
 	spin_unlock(&sdp->sd_bitmap_lock);
-
 	return error;
 }
 

From 36a740916a94ea0efa0c5c2ddcd9dcdce56c9a40 Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Wed, 28 Jun 2023 08:50:46 -0500
Subject: [PATCH 1048/1189] gfs2: Remove useless assignment

This assignment is unnecessary because if error was not already 0, it
would have branched to an error label already.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/quota.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 8b6a1c14a03e..678d2e749db8 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -971,8 +971,6 @@ static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda)
 		set_bit(QDF_REFRESH, &qd->qd_flags);
 	}
 
-	error = 0;
-
 out_end_trans:
 	gfs2_trans_end(sdp);
 out_ipres:

From 06aa6fd31a5f402b055e12ea53bb7b086359d3c8 Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Thu, 8 Jun 2023 12:30:16 -0500
Subject: [PATCH 1049/1189] gfs2: check for no eligible quota changes

Before this patch, function gfs2_quota_sync would always allocate a page
full of memory and increment its quota sync generation number. This
happened even when the system was completely idle or if no blocks were
allocated or quota changes made. This patch adds function qd_changed
to determine if any changes have been made that qualify for a
quota sync. If not, it avoids the memory allocation and bumping the
generation number, along with all the additional work it would do.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/quota.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 678d2e749db8..6f6e3493b5fa 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -1294,6 +1294,24 @@ void gfs2_quota_change(struct gfs2_inode *ip, s64 change,
 	}
 }
 
+static bool qd_changed(struct gfs2_sbd *sdp)
+{
+	struct gfs2_quota_data *qd;
+	bool changed = false;
+
+	spin_lock(&qd_lock);
+	list_for_each_entry(qd, &sdp->sd_quota_list, qd_list) {
+		if (test_bit(QDF_LOCKED, &qd->qd_flags) ||
+		    !test_bit(QDF_CHANGE, &qd->qd_flags))
+			continue;
+
+		changed = true;
+		break;
+	}
+	spin_unlock(&qd_lock);
+	return changed;
+}
+
 int gfs2_quota_sync(struct super_block *sb, int type)
 {
 	struct gfs2_sbd *sdp = sb->s_fs_info;
@@ -1303,6 +1321,9 @@ int gfs2_quota_sync(struct super_block *sb, int type)
 	unsigned int x;
 	int error = 0;
 
+	if (!qd_changed(sdp))
+		return 0;
+
 	qda = kcalloc(max_qd, sizeof(struct gfs2_quota_data *), GFP_KERNEL);
 	if (!qda)
 		return -ENOMEM;

From 0e072cac92d08c05257432b10fa8cd66d64b3f43 Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Fri, 16 Jun 2023 13:22:04 -0500
Subject: [PATCH 1050/1189] gfs2: change qd_slot_count to qd_slot_ref

Variable qd_slot_count is a reference count, not a count of slots. This
patch renames it to qd_slot_ref to make that more clear.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/incore.h |  2 +-
 fs/gfs2/quota.c  | 16 ++++++++--------
 2 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 7e94cf3562d6..a8c95c5293c6 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -452,7 +452,7 @@ struct gfs2_quota_data {
 	s64 qd_change_sync;
 
 	unsigned int qd_slot;
-	unsigned int qd_slot_count;
+	unsigned int qd_slot_ref;
 
 	struct buffer_head *qd_bh;
 	struct gfs2_quota_change *qd_bh_qc;
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 6f6e3493b5fa..5160e5c36980 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -130,7 +130,7 @@ static void gfs2_qd_dispose(struct gfs2_quota_data *qd)
 
 	if (!gfs2_withdrawn(sdp)) {
 		gfs2_assert_warn(sdp, !qd->qd_change);
-		gfs2_assert_warn(sdp, !qd->qd_slot_count);
+		gfs2_assert_warn(sdp, !qd->qd_slot_ref);
 		gfs2_assert_warn(sdp, !qd->qd_bh_count);
 	}
 
@@ -342,7 +342,7 @@ static int slot_get(struct gfs2_quota_data *qd)
 	int error = 0;
 
 	spin_lock(&sdp->sd_bitmap_lock);
-	if (qd->qd_slot_count == 0) {
+	if (qd->qd_slot_ref == 0) {
 		bit = find_first_zero_bit(sdp->sd_quota_bitmap,
 					  sdp->sd_quota_slots);
 		if (bit >= sdp->sd_quota_slots) {
@@ -352,7 +352,7 @@ static int slot_get(struct gfs2_quota_data *qd)
 		set_bit(bit, sdp->sd_quota_bitmap);
 		qd->qd_slot = bit;
 	}
-	qd->qd_slot_count++;
+	qd->qd_slot_ref++;
 out:
 	spin_unlock(&sdp->sd_bitmap_lock);
 	return error;
@@ -363,8 +363,8 @@ static void slot_hold(struct gfs2_quota_data *qd)
 	struct gfs2_sbd *sdp = qd->qd_sbd;
 
 	spin_lock(&sdp->sd_bitmap_lock);
-	gfs2_assert(sdp, qd->qd_slot_count);
-	qd->qd_slot_count++;
+	gfs2_assert(sdp, qd->qd_slot_ref);
+	qd->qd_slot_ref++;
 	spin_unlock(&sdp->sd_bitmap_lock);
 }
 
@@ -373,8 +373,8 @@ static void slot_put(struct gfs2_quota_data *qd)
 	struct gfs2_sbd *sdp = qd->qd_sbd;
 
 	spin_lock(&sdp->sd_bitmap_lock);
-	gfs2_assert(sdp, qd->qd_slot_count);
-	if (!--qd->qd_slot_count) {
+	gfs2_assert(sdp, qd->qd_slot_ref);
+	if (!--qd->qd_slot_ref) {
 		BUG_ON(!test_and_clear_bit(qd->qd_slot, sdp->sd_quota_bitmap));
 		qd->qd_slot = -1;
 	}
@@ -1446,7 +1446,7 @@ int gfs2_quota_init(struct gfs2_sbd *sdp)
 			set_bit(QDF_CHANGE, &qd->qd_flags);
 			qd->qd_change = qc_change;
 			qd->qd_slot = slot;
-			qd->qd_slot_count = 1;
+			qd->qd_slot_ref = 1;
 
 			spin_lock(&qd_lock);
 			BUG_ON(test_and_set_bit(slot, sdp->sd_quota_bitmap));

From 76d3ccecfa186af3120e206d62f03db1a94a535f Mon Sep 17 00:00:00 2001
From: Matteo Rizzo <matteorizzo@google.com>
Date: Mon, 21 Aug 2023 17:15:52 -0400
Subject: [PATCH 1051/1189] io_uring: add a sysctl to disable io_uring
 system-wide

Introduce a new sysctl (io_uring_disabled) which can be either 0, 1, or
2. When 0 (the default), all processes are allowed to create io_uring
instances, which is the current behavior.  When 1, io_uring creation is
disabled (io_uring_setup() will fail with -EPERM) for unprivileged
processes not in the kernel.io_uring_group group.  When 2, calls to
io_uring_setup() fail with -EPERM regardless of privilege.

Signed-off-by: Matteo Rizzo <matteorizzo@google.com>
[JEM: modified to add io_uring_group]
Signed-off-by: Jeff Moyer <jmoyer@redhat.com>
Link: https://lore.kernel.org/r/x49y1i42j1z.fsf@segfault.boston.devel.redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 Documentation/admin-guide/sysctl/kernel.rst | 29 ++++++++++++
 io_uring/io_uring.c                         | 50 +++++++++++++++++++++
 2 files changed, 79 insertions(+)

diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
index 3800fab1619b..0795d790cc56 100644
--- a/Documentation/admin-guide/sysctl/kernel.rst
+++ b/Documentation/admin-guide/sysctl/kernel.rst
@@ -450,6 +450,35 @@ this allows system administrators to override the
 ``IA64_THREAD_UAC_NOPRINT`` ``prctl`` and avoid logs being flooded.
 
 
+io_uring_disabled
+=================
+
+Prevents all processes from creating new io_uring instances. Enabling this
+shrinks the kernel's attack surface.
+
+= ======================================================================
+0 All processes can create io_uring instances as normal. This is the
+  default setting.
+1 io_uring creation is disabled (io_uring_setup() will fail with
+  -EPERM) for unprivileged processes not in the io_uring_group group.
+  Existing io_uring instances can still be used.  See the
+  documentation for io_uring_group for more information.
+2 io_uring creation is disabled for all processes. io_uring_setup()
+  always fails with -EPERM. Existing io_uring instances can still be
+  used.
+= ======================================================================
+
+
+io_uring_group
+==============
+
+When io_uring_disabled is set to 1, a process must either be
+privileged (CAP_SYS_ADMIN) or be in the io_uring_group group in order
+to create an io_uring instance.  If io_uring_group is set to -1 (the
+default), only processes with the CAP_SYS_ADMIN capability may create
+io_uring instances.
+
+
 kexec_load_disabled
 ===================
 
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index c6d9e4677073..0f0ba31c3850 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -150,6 +150,31 @@ static void io_queue_sqe(struct io_kiocb *req);
 
 struct kmem_cache *req_cachep;
 
+static int __read_mostly sysctl_io_uring_disabled;
+static int __read_mostly sysctl_io_uring_group = -1;
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table kernel_io_uring_disabled_table[] = {
+	{
+		.procname	= "io_uring_disabled",
+		.data		= &sysctl_io_uring_disabled,
+		.maxlen		= sizeof(sysctl_io_uring_disabled),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_TWO,
+	},
+	{
+		.procname	= "io_uring_group",
+		.data		= &sysctl_io_uring_group,
+		.maxlen		= sizeof(gid_t),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{},
+};
+#endif
+
 struct sock *io_uring_get_socket(struct file *file)
 {
 #if defined(CONFIG_UNIX)
@@ -4070,9 +4095,30 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
 	return io_uring_create(entries, &p, params);
 }
 
+static inline bool io_uring_allowed(void)
+{
+	int disabled = READ_ONCE(sysctl_io_uring_disabled);
+	kgid_t io_uring_group;
+
+	if (disabled == 2)
+		return false;
+
+	if (disabled == 0 || capable(CAP_SYS_ADMIN))
+		return true;
+
+	io_uring_group = make_kgid(&init_user_ns, sysctl_io_uring_group);
+	if (!gid_valid(io_uring_group))
+		return false;
+
+	return in_group_p(io_uring_group);
+}
+
 SYSCALL_DEFINE2(io_uring_setup, u32, entries,
 		struct io_uring_params __user *, params)
 {
+	if (!io_uring_allowed())
+		return -EPERM;
+
 	return io_uring_setup(entries, params);
 }
 
@@ -4666,6 +4712,10 @@ static int __init io_uring_init(void)
 				offsetof(struct io_kiocb, cmd.data),
 				sizeof_field(struct io_kiocb, cmd.data), NULL);
 
+#ifdef CONFIG_SYSCTL
+	register_sysctl_init("kernel", kernel_io_uring_disabled_table);
+#endif
+
 	return 0;
 };
 __initcall(io_uring_init);

From 7625df9f4b255eb9d56885e25c564d7e794c6da1 Mon Sep 17 00:00:00 2001
From: Jeongtae Park <jtp.park@samsung.com>
Date: Tue, 5 Sep 2023 21:33:09 +0900
Subject: [PATCH 1052/1189] perf: CXL: fix mismatched number of counters mask

The number of Count Units field is described as 6 bits long
in the CXL 3.0 specification. However, its mask value was
only declared as 5 bits long.

Signed-off-by: Jeongtae Park <jtp.park@samsung.com>
Acked-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/20230905123309.775854-1-jtp.park@samsung.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/perf/cxl_pmu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/perf/cxl_pmu.c b/drivers/perf/cxl_pmu.c
index 0a8f597e695b..365d964b0f6a 100644
--- a/drivers/perf/cxl_pmu.c
+++ b/drivers/perf/cxl_pmu.c
@@ -25,7 +25,7 @@
 #include "../cxl/pmu.h"
 
 #define CXL_PMU_CAP_REG			0x0
-#define   CXL_PMU_CAP_NUM_COUNTERS_MSK			GENMASK_ULL(4, 0)
+#define   CXL_PMU_CAP_NUM_COUNTERS_MSK			GENMASK_ULL(5, 0)
 #define   CXL_PMU_CAP_COUNTER_WIDTH_MSK			GENMASK_ULL(15, 8)
 #define   CXL_PMU_CAP_NUM_EVN_CAP_REG_SUP_MSK		GENMASK_ULL(24, 20)
 #define   CXL_PMU_CAP_FILTERS_SUP_MSK			GENMASK_ULL(39, 32)

From 7b7e3ed78ef78f7e6a4d4f4a4973f6a5d22123ec Mon Sep 17 00:00:00 2001
From: Andrew Price <anprice@redhat.com>
Date: Thu, 31 Aug 2023 10:57:48 +0100
Subject: [PATCH 1053/1189] MAINTAINERS: Update gfs2 mailing list

Signed-off-by: Andrew Price <anprice@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 0f966f05fb0d..6067875f01ae 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8724,7 +8724,7 @@ F:	scripts/get_maintainer.pl
 GFS2 FILE SYSTEM
 M:	Bob Peterson <rpeterso@redhat.com>
 M:	Andreas Gruenbacher <agruenba@redhat.com>
-L:	cluster-devel@redhat.com
+L:	gfs2@lists.linux.dev
 S:	Supported
 B:	https://bugzilla.kernel.org/enter_bug.cgi?product=File%20System&component=gfs2
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2.git

From 2938fd750e8b73a6dac4d9339fb6f7f1cd624a2d Mon Sep 17 00:00:00 2001
From: Andrew Price <anprice@redhat.com>
Date: Thu, 31 Aug 2023 10:57:49 +0100
Subject: [PATCH 1054/1189] MAINTAINERS: Update dlm mailing list

The new gfs2@ list will also be used for dlm development.

Signed-off-by: Andrew Price <anprice@redhat.com>
Acked-by: David Teigland <teigland@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 6067875f01ae..1131d849e1d2 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6092,7 +6092,7 @@ F:	include/video/udlfb.h
 DISTRIBUTED LOCK MANAGER (DLM)
 M:	Christine Caulfield <ccaulfie@redhat.com>
 M:	David Teigland <teigland@redhat.com>
-L:	cluster-devel@redhat.com
+L:	gfs2@lists.linux.dev
 S:	Supported
 W:	http://sources.redhat.com/cluster/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/teigland/linux-dlm.git

From 739c031110da9ba966b0189fa25a2a1c0d42263c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Amadeusz=20S=C5=82awi=C5=84ski?=
 <amadeuszx.slawinski@linux.intel.com>
Date: Tue, 5 Sep 2023 11:31:47 +0200
Subject: [PATCH 1055/1189] ASoC: Intel: avs: Provide support for fallback
 topology
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

HDA and HDMI devices are simple enough that in case of user not having
topology tailored to their device, they can use fallback topology.

Signed-off-by: Amadeusz Sławiński <amadeuszx.slawinski@linux.intel.com>
Link: https://lore.kernel.org/r/20230905093147.1960675-1-amadeuszx.slawinski@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/avs/pcm.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/sound/soc/intel/avs/pcm.c b/sound/soc/intel/avs/pcm.c
index 1fbb2c2fadb5..8565a530706d 100644
--- a/sound/soc/intel/avs/pcm.c
+++ b/sound/soc/intel/avs/pcm.c
@@ -796,6 +796,28 @@ static int avs_component_probe(struct snd_soc_component *component)
 
 	ret = avs_load_topology(component, filename);
 	kfree(filename);
+	if (ret == -ENOENT && !strncmp(mach->tplg_filename, "hda-", 4)) {
+		unsigned int vendor_id;
+
+		if (sscanf(mach->tplg_filename, "hda-%08x-tplg.bin", &vendor_id) != 1)
+			return ret;
+
+		if (((vendor_id >> 16) & 0xFFFF) == 0x8086)
+			mach->tplg_filename = devm_kasprintf(adev->dev, GFP_KERNEL,
+							     "hda-8086-generic-tplg.bin");
+		else
+			mach->tplg_filename = devm_kasprintf(adev->dev, GFP_KERNEL,
+							     "hda-generic-tplg.bin");
+
+		filename = kasprintf(GFP_KERNEL, "%s/%s", component->driver->topology_name_prefix,
+				     mach->tplg_filename);
+		if (!filename)
+			return -ENOMEM;
+
+		dev_info(card->dev, "trying to load fallback topology %s\n", mach->tplg_filename);
+		ret = avs_load_topology(component, filename);
+		kfree(filename);
+	}
 	if (ret < 0)
 		return ret;
 

From c3b704d4a4a265660e665df51b129e8425216ed1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 5 Sep 2023 04:23:38 +0000
Subject: [PATCH 1056/1189] igmp: limit igmpv3_newpack() packet size to
 IP_MAX_MTU

This is a follow up of commit 915d975b2ffa ("net: deal with integer
overflows in kmalloc_reserve()") based on David Laight feedback.

Back in 2010, I failed to realize malicious users could set dev->mtu
to arbitrary values. This mtu has been since limited to 0x7fffffff but
regardless of how big dev->mtu is, it makes no sense for igmpv3_newpack()
to allocate more than IP_MAX_MTU and risk various skb fields overflows.

Fixes: 57e1ab6eaddc ("igmp: refine skb allocations")
Link: https://lore.kernel.org/netdev/d273628df80f45428e739274ab9ecb72@AcuMS.aculab.com/
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: David Laight <David.Laight@ACULAB.COM>
Cc: Kyle Zeng <zengyhkyle@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/igmp.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 0c9e768e5628..418e5fb58fd3 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -353,8 +353,9 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
 	struct flowi4 fl4;
 	int hlen = LL_RESERVED_SPACE(dev);
 	int tlen = dev->needed_tailroom;
-	unsigned int size = mtu;
+	unsigned int size;
 
+	size = min(mtu, IP_MAX_MTU);
 	while (1) {
 		skb = alloc_skb(size + hlen + tlen,
 				GFP_ATOMIC | __GFP_NOWARN);

From 29fe7a1b62717d58f033009874554d99d71f7d37 Mon Sep 17 00:00:00 2001
From: Geetha sowjanya <gakula@marvell.com>
Date: Tue, 5 Sep 2023 12:18:16 +0530
Subject: [PATCH 1057/1189] octeontx2-af: Fix truncation of smq in CN10K NIX AQ
 enqueue mbox handler

The smq value used in the CN10K NIX AQ instruction enqueue mailbox
handler was truncated to 9-bit value from 10-bit value because of
typecasting the CN10K mbox request structure to the CN9K structure.
Though this hasn't caused any problems when programming the NIX SQ
context to the HW because the context structure is the same size.
However, this causes a problem when accessing the structure parameters.
This patch reads the right smq value for each platform.

Fixes: 30077d210c83 ("octeontx2-af: cn10k: Update NIX/NPA context structure")
Signed-off-by: Geetha sowjanya <gakula@marvell.com>
Signed-off-by: Sunil Kovvuri Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/marvell/octeontx2/af/rvu_nix.c   | 21 +++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index c2f68678e947..23c2f2ed2fb8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -846,6 +846,21 @@ static int nix_aq_enqueue_wait(struct rvu *rvu, struct rvu_block *block,
 	return 0;
 }
 
+static void nix_get_aq_req_smq(struct rvu *rvu, struct nix_aq_enq_req *req,
+			       u16 *smq, u16 *smq_mask)
+{
+	struct nix_cn10k_aq_enq_req *aq_req;
+
+	if (!is_rvu_otx2(rvu)) {
+		aq_req = (struct nix_cn10k_aq_enq_req *)req;
+		*smq = aq_req->sq.smq;
+		*smq_mask = aq_req->sq_mask.smq;
+	} else {
+		*smq = req->sq.smq;
+		*smq_mask = req->sq_mask.smq;
+	}
+}
+
 static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw,
 				   struct nix_aq_enq_req *req,
 				   struct nix_aq_enq_rsp *rsp)
@@ -857,6 +872,7 @@ static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw,
 	struct rvu_block *block;
 	struct admin_queue *aq;
 	struct rvu_pfvf *pfvf;
+	u16 smq, smq_mask;
 	void *ctx, *mask;
 	bool ena;
 	u64 cfg;
@@ -928,13 +944,14 @@ static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw,
 	if (rc)
 		return rc;
 
+	nix_get_aq_req_smq(rvu, req, &smq, &smq_mask);
 	/* Check if SQ pointed SMQ belongs to this PF/VF or not */
 	if (req->ctype == NIX_AQ_CTYPE_SQ &&
 	    ((req->op == NIX_AQ_INSTOP_INIT && req->sq.ena) ||
 	     (req->op == NIX_AQ_INSTOP_WRITE &&
-	      req->sq_mask.ena && req->sq_mask.smq && req->sq.ena))) {
+	      req->sq_mask.ena && req->sq.ena && smq_mask))) {
 		if (!is_valid_txschq(rvu, blkaddr, NIX_TXSCH_LVL_SMQ,
-				     pcifunc, req->sq.smq))
+				     pcifunc, smq))
 			return NIX_AF_ERR_AQ_ENQUEUE;
 	}
 

From 26641b3f22abe3f03bd8e078c116cc98de740f43 Mon Sep 17 00:00:00 2001
From: Lizhi Hou <lizhi.hou@amd.com>
Date: Thu, 31 Aug 2023 11:19:07 -0700
Subject: [PATCH 1058/1189] PCI: Fix CONFIG_PCI_DYNAMIC_OF_NODES kconfig
 dependencies

Generating interrupt-map property depends on of_irq_parse_raw() which
is enabled by CONFIG_OF_IRQ. Change CONFIG_PCI_DYNAMIC_OF_NODES
dependency from CONFIG_OF to CONFIG_OF_IRQ.

Closes: https://lore.kernel.org/linux-devicetree/2187619d-55bc-41bb-bbb4-6059399db997@roeck-us.net/
Fixes: 407d1a51921e ("PCI: Create device tree node for bridge")
Link: https://lore.kernel.org/r/1693505947-29786-1-git-send-email-lizhi.hou@amd.com
Reported-by: Guenter Roeck <groeck7@gmail.com>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 49bd09c7dd0a..e9ae66cc4189 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -196,7 +196,7 @@ config PCI_HYPERV
 
 config PCI_DYNAMIC_OF_NODES
 	bool "Create Device tree nodes for PCI devices"
-	depends on OF
+	depends on OF_IRQ
 	select OF_DYNAMIC
 	help
 	  This option enables support for generating device tree nodes for some

From 5aa48279712e1f134aac908acde4df798955a955 Mon Sep 17 00:00:00 2001
From: Olga Zaborska <olga.zaborska@intel.com>
Date: Tue, 25 Jul 2023 10:10:56 +0200
Subject: [PATCH 1059/1189] igc: Change IGC_MIN to allow set rx/tx value
 between 64 and 80

Change the minimum value of RX/TX descriptors to 64 to enable setting the rx/tx
value between 64 and 80. All igc devices can use as low as 64 descriptors.
This change will unify igc with other drivers.
Based on commit 7b1be1987c1e ("e1000e: lower ring minimum size to 64")

Fixes: 0507ef8a0372 ("igc: Add transmit and receive fastpath and interrupt handlers")
Signed-off-by: Olga Zaborska <olga.zaborska@intel.com>
Tested-by: Naama Meir <naamax.meir@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 8ebe6999a528..f48f82d5e274 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -379,11 +379,11 @@ static inline u32 igc_rss_type(const union igc_adv_rx_desc *rx_desc)
 /* TX/RX descriptor defines */
 #define IGC_DEFAULT_TXD		256
 #define IGC_DEFAULT_TX_WORK	128
-#define IGC_MIN_TXD		80
+#define IGC_MIN_TXD		64
 #define IGC_MAX_TXD		4096
 
 #define IGC_DEFAULT_RXD		256
-#define IGC_MIN_RXD		80
+#define IGC_MIN_RXD		64
 #define IGC_MAX_RXD		4096
 
 /* Supported Rx Buffer Sizes */

From 8360717524a24a421c36ef8eb512406dbd42160a Mon Sep 17 00:00:00 2001
From: Olga Zaborska <olga.zaborska@intel.com>
Date: Tue, 25 Jul 2023 10:10:57 +0200
Subject: [PATCH 1060/1189] igbvf: Change IGBVF_MIN to allow set rx/tx value
 between 64 and 80

Change the minimum value of RX/TX descriptors to 64 to enable setting the rx/tx
value between 64 and 80. All igbvf devices can use as low as 64 descriptors.
This change will unify igbvf with other drivers.
Based on commit 7b1be1987c1e ("e1000e: lower ring minimum size to 64")

Fixes: d4e0fe01a38a ("igbvf: add new driver to support 82576 virtual functions")
Signed-off-by: Olga Zaborska <olga.zaborska@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igbvf/igbvf.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/igbvf/igbvf.h b/drivers/net/ethernet/intel/igbvf/igbvf.h
index 57d39ee00b58..7b83678ba83a 100644
--- a/drivers/net/ethernet/intel/igbvf/igbvf.h
+++ b/drivers/net/ethernet/intel/igbvf/igbvf.h
@@ -39,11 +39,11 @@ enum latency_range {
 /* Tx/Rx descriptor defines */
 #define IGBVF_DEFAULT_TXD	256
 #define IGBVF_MAX_TXD		4096
-#define IGBVF_MIN_TXD		80
+#define IGBVF_MIN_TXD		64
 
 #define IGBVF_DEFAULT_RXD	256
 #define IGBVF_MAX_RXD		4096
-#define IGBVF_MIN_RXD		80
+#define IGBVF_MIN_RXD		64
 
 #define IGBVF_MIN_ITR_USECS	10 /* 100000 irq/sec */
 #define IGBVF_MAX_ITR_USECS	10000 /* 100    irq/sec */

From 6319685bdc8ad5310890add907b7c42f89302886 Mon Sep 17 00:00:00 2001
From: Olga Zaborska <olga.zaborska@intel.com>
Date: Tue, 25 Jul 2023 10:10:58 +0200
Subject: [PATCH 1061/1189] igb: Change IGB_MIN to allow set rx/tx value
 between 64 and 80

Change the minimum value of RX/TX descriptors to 64 to enable setting the rx/tx
value between 64 and 80. All igb devices can use as low as 64 descriptors.
This change will unify igb with other drivers.
Based on commit 7b1be1987c1e ("e1000e: lower ring minimum size to 64")

Fixes: 9d5c824399de ("igb: PCI-Express 82575 Gigabit Ethernet driver")
Signed-off-by: Olga Zaborska <olga.zaborska@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igb/igb.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 015b78144114..a2b759531cb7 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -34,11 +34,11 @@ struct igb_adapter;
 /* TX/RX descriptor defines */
 #define IGB_DEFAULT_TXD		256
 #define IGB_DEFAULT_TX_WORK	128
-#define IGB_MIN_TXD		80
+#define IGB_MIN_TXD		64
 #define IGB_MAX_TXD		4096
 
 #define IGB_DEFAULT_RXD		256
-#define IGB_MIN_RXD		80
+#define IGB_MIN_RXD		64
 #define IGB_MAX_RXD		4096
 
 #define IGB_DEFAULT_ITR		3 /* dynamic */

From cf60ce92358da29f3b1e24005f7b748584b82753 Mon Sep 17 00:00:00 2001
From: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Date: Mon, 4 Sep 2023 12:00:02 +0200
Subject: [PATCH 1062/1189] of: overlay: Fix of_overlay_fdt_apply prototype
 when !CONFIG_OF_OVERLAY

The of_overlay_fdt_apply has been changed but when CONFIG_OF_OVERLAY
support is not configured then old stub prototype is declared
by of.h header.

Signed-off-by: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Fixes: 47284862bfc7 ("of: overlay: Extend of_overlay_fdt_apply() to specify the target node")
Acked-by: Marc Kleine-Budde <mkl@pengutronix.de>
Link: https://lore.kernel.org/r/20230904100002.7913-1-pisa@cmp.felk.cvut.cz
Signed-off-by: Rob Herring <robh@kernel.org>
---
 include/linux/of.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/of.h b/include/linux/of.h
index ed679819c279..6a9ddf20e79a 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -1676,8 +1676,8 @@ int of_overlay_notifier_unregister(struct notifier_block *nb);
 
 #else
 
-static inline int of_overlay_fdt_apply(void *overlay_fdt, u32 overlay_fdt_size,
-				       int *ovcs_id)
+static inline int of_overlay_fdt_apply(const void *overlay_fdt, u32 overlay_fdt_size,
+				       int *ovcs_id, struct device_node *target_base)
 {
 	return -ENOTSUPP;
 }

From 08d90f46c7ddff0cbd3fefbddf1d2bd53ce4b477 Mon Sep 17 00:00:00 2001
From: Alexander Gordeev <agordeev@linux.ibm.com>
Date: Fri, 1 Sep 2023 15:12:13 +0200
Subject: [PATCH 1063/1189] s390/mm: fix MAX_DMA_ADDRESS physical vs virtual
 confusion

MAX_DMA_ADDRESS is defined and treated as a physical address,
whereas it should be virtual.

Reviewed-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/include/asm/dma.h | 2 +-
 arch/s390/mm/init.c         | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/s390/include/asm/dma.h b/arch/s390/include/asm/dma.h
index c260adb25997..7fe3e31956d7 100644
--- a/arch/s390/include/asm/dma.h
+++ b/arch/s390/include/asm/dma.h
@@ -9,6 +9,6 @@
  * to DMA. It _is_ used for the s390 memory zone split at 2GB caused
  * by the 31 bit heritage.
  */
-#define MAX_DMA_ADDRESS         0x80000000
+#define MAX_DMA_ADDRESS		__va(0x80000000)
 
 #endif /* _ASM_S390_DMA_H */
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index d1631f8e53b5..8b94d2212d33 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -98,7 +98,7 @@ void __init paging_init(void)
 	sparse_init();
 	zone_dma_bits = 31;
 	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
-	max_zone_pfns[ZONE_DMA] = PFN_DOWN(MAX_DMA_ADDRESS);
+	max_zone_pfns[ZONE_DMA] = virt_to_pfn(MAX_DMA_ADDRESS);
 	max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
 	free_area_init(max_zone_pfns);
 }

From 6252f47b78031979ad919f971dc8468b893488bd Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 31 Aug 2023 13:59:59 +0300
Subject: [PATCH 1064/1189] s390/zcrypt: don't leak memory if dev_set_name()
 fails

When dev_set_name() fails, zcdn_create() doesn't free the newly
allocated resources. Do it.

Fixes: 00fab2350e6b ("s390/zcrypt: multiple zcrypt device nodes support")
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20230831110000.24279-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Harald Freudenberger <freude@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 drivers/s390/crypto/zcrypt_api.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c
index 4b23c9f7f3e5..6b99f7dd0643 100644
--- a/drivers/s390/crypto/zcrypt_api.c
+++ b/drivers/s390/crypto/zcrypt_api.c
@@ -413,6 +413,7 @@ static int zcdn_create(const char *name)
 			 ZCRYPT_NAME "_%d", (int)MINOR(devt));
 	nodename[sizeof(nodename) - 1] = '\0';
 	if (dev_set_name(&zcdndev->device, nodename)) {
+		kfree(zcdndev);
 		rc = -EINVAL;
 		goto unlockout;
 	}

From f59ec04d382d2f2528f439947e215a52703e0094 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 31 Aug 2023 14:00:00 +0300
Subject: [PATCH 1065/1189] s390/zcrypt: utilize dev_set_name() ability to use
 a formatted string

With the dev_set_name() prototype it's not obvious that it takes
a formatted string as a parameter. Use its facility instead of
duplicating the same with strncpy()/snprintf() calls.

With this, also prevent return error code to be shadowed.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20230831110000.24279-2-andriy.shevchenko@linux.intel.com
Signed-off-by: Harald Freudenberger <freude@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 drivers/s390/crypto/zcrypt_api.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c
index 6b99f7dd0643..ce04caa7913f 100644
--- a/drivers/s390/crypto/zcrypt_api.c
+++ b/drivers/s390/crypto/zcrypt_api.c
@@ -366,7 +366,6 @@ static int zcdn_create(const char *name)
 {
 	dev_t devt;
 	int i, rc = 0;
-	char nodename[ZCDN_MAX_NAME];
 	struct zcdn_device *zcdndev;
 
 	if (mutex_lock_interruptible(&ap_perms_mutex))
@@ -407,14 +406,11 @@ static int zcdn_create(const char *name)
 	zcdndev->device.devt = devt;
 	zcdndev->device.groups = zcdn_dev_attr_groups;
 	if (name[0])
-		strncpy(nodename, name, sizeof(nodename));
+		rc = dev_set_name(&zcdndev->device, "%s", name);
 	else
-		snprintf(nodename, sizeof(nodename),
-			 ZCRYPT_NAME "_%d", (int)MINOR(devt));
-	nodename[sizeof(nodename) - 1] = '\0';
-	if (dev_set_name(&zcdndev->device, nodename)) {
+		rc = dev_set_name(&zcdndev->device, ZCRYPT_NAME "_%d", (int)MINOR(devt));
+	if (rc) {
 		kfree(zcdndev);
-		rc = -EINVAL;
 		goto unlockout;
 	}
 	rc = device_register(&zcdndev->device);

From 06fc3b0d2251b550f530a1c42e0f9c5d022476dd Mon Sep 17 00:00:00 2001
From: Alexander Gordeev <agordeev@linux.ibm.com>
Date: Fri, 1 Sep 2023 08:11:14 +0200
Subject: [PATCH 1066/1189] s390/vmem: do not silently ignore mapping limit

The only interface that allows drivers establishing
liner mappings is vmem_add_mapping(). It does check
a requested range against allowed limits and a call
to modify_pagetable() with an invalid mapping range
is impossible.

Hence, an attempt to map an address range outside of
the identity mapping or vmemmap array could only be
kernel bug.

Reviewed-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/mm/vmem.c | 18 +++---------------
 1 file changed, 3 insertions(+), 15 deletions(-)

diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index d734058f28d3..6957d2ed97bf 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -290,14 +290,9 @@ out:
 
 static void try_free_pmd_table(pud_t *pud, unsigned long start)
 {
-	const unsigned long end = start + PUD_SIZE;
 	pmd_t *pmd;
 	int i;
 
-	/* Don't mess with any tables not fully in 1:1 mapping & vmemmap area */
-	if (end > VMALLOC_START)
-		return;
-
 	pmd = pmd_offset(pud, start);
 	for (i = 0; i < PTRS_PER_PMD; i++, pmd++)
 		if (!pmd_none(*pmd))
@@ -362,14 +357,9 @@ out:
 
 static void try_free_pud_table(p4d_t *p4d, unsigned long start)
 {
-	const unsigned long end = start + P4D_SIZE;
 	pud_t *pud;
 	int i;
 
-	/* Don't mess with any tables not fully in 1:1 mapping & vmemmap area */
-	if (end > VMALLOC_START)
-		return;
-
 	pud = pud_offset(p4d, start);
 	for (i = 0; i < PTRS_PER_PUD; i++, pud++) {
 		if (!pud_none(*pud))
@@ -412,14 +402,9 @@ out:
 
 static void try_free_p4d_table(pgd_t *pgd, unsigned long start)
 {
-	const unsigned long end = start + PGDIR_SIZE;
 	p4d_t *p4d;
 	int i;
 
-	/* Don't mess with any tables not fully in 1:1 mapping & vmemmap area */
-	if (end > VMALLOC_START)
-		return;
-
 	p4d = p4d_offset(pgd, start);
 	for (i = 0; i < PTRS_PER_P4D; i++, p4d++) {
 		if (!p4d_none(*p4d))
@@ -439,6 +424,9 @@ static int modify_pagetable(unsigned long start, unsigned long end, bool add,
 
 	if (WARN_ON_ONCE(!PAGE_ALIGNED(start | end)))
 		return -EINVAL;
+	/* Don't mess with any tables not fully in 1:1 mapping & vmemmap area */
+	if (WARN_ON_ONCE(end > VMALLOC_START))
+		return -EINVAL;
 	for (addr = start; addr < end; addr = next) {
 		next = pgd_addr_end(addr, end);
 		pgd = pgd_offset_k(addr);

From 9ffa7b92bc768609243d79fb0c0125b9704c7061 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Wed, 30 Aug 2023 18:11:38 +0200
Subject: [PATCH 1067/1189] thermal: core: Clean up headers of thermal zone
 registration functions

For consistency, add a missing thermal_zone_device_register_with_trips()
stub for the CONFIG_THERMAL unset case, specify argument names in all of
the thermal zone registration and unregistration function headers and
make all of them use white space consistently.

No intentional functional impact.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/thermal.h | 49 +++++++++++++++++++++++++++++------------
 1 file changed, 35 insertions(+), 14 deletions(-)

diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index eb17495c8acc..a30643104f3f 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -300,16 +300,24 @@ int thermal_acpi_critical_trip_temp(struct acpi_device *adev, int *ret_temp);
 #endif
 
 #ifdef CONFIG_THERMAL
-struct thermal_zone_device *thermal_zone_device_register(const char *, int, int,
-		void *, struct thermal_zone_device_ops *,
-		const struct thermal_zone_params *, int, int);
+struct thermal_zone_device *thermal_zone_device_register(
+					const char *type,
+					int num_trips, int mask,
+					void *devdata,
+					struct thermal_zone_device_ops *ops,
+					const struct thermal_zone_params *tzp,
+					int passive_delay, int polling_delay);
 
-void thermal_zone_device_unregister(struct thermal_zone_device *);
+struct thermal_zone_device *thermal_zone_device_register_with_trips(
+					const char *type,
+					struct thermal_trip *trips,
+					int num_trips, int mask,
+					void *devdata,
+					struct thermal_zone_device_ops *ops,
+					const struct thermal_zone_params *tzp,
+					int passive_delay, int polling_delay);
 
-struct thermal_zone_device *
-thermal_zone_device_register_with_trips(const char *, struct thermal_trip *, int, int,
-					void *, struct thermal_zone_device_ops *,
-					const struct thermal_zone_params *, int, int);
+void thermal_zone_device_unregister(struct thermal_zone_device *tz);
 
 void *thermal_zone_device_priv(struct thermal_zone_device *tzd);
 const char *thermal_zone_device_type(struct thermal_zone_device *tzd);
@@ -351,14 +359,27 @@ int thermal_zone_device_disable(struct thermal_zone_device *tz);
 void thermal_zone_device_critical(struct thermal_zone_device *tz);
 #else
 static inline struct thermal_zone_device *thermal_zone_device_register(
-	const char *type, int trips, int mask, void *devdata,
-	struct thermal_zone_device_ops *ops,
-	const struct thermal_zone_params *tzp,
-	int passive_delay, int polling_delay)
+					const char *type,
+					int num_trips, int mask,
+					void *devdata,
+					struct thermal_zone_device_ops *ops,
+					const struct thermal_zone_params *tzp,
+					int passive_delay, int polling_delay)
 { return ERR_PTR(-ENODEV); }
-static inline void thermal_zone_device_unregister(
-	struct thermal_zone_device *tz)
+
+static inline struct thermal_zone_device *thermal_zone_device_register_with_trips(
+					const char *type,
+					struct thermal_trip *trips,
+					int num_trips, int mask,
+					void *devdata,
+					struct thermal_zone_device_ops *ops,
+					const struct thermal_zone_params *tzp,
+					int passive_delay, int polling_delay)
+{ return ERR_PTR(-ENODEV); }
+
+static inline void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 { }
+
 static inline struct thermal_cooling_device *
 thermal_cooling_device_register(const char *type, void *devdata,
 	const struct thermal_cooling_device_ops *ops)

From d332db8fc1a2dfb4738281b1d6d4ed20115dd9d3 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Wed, 30 Aug 2023 18:13:35 +0200
Subject: [PATCH 1068/1189] thermal: core: Add function for registering
 tripless thermal zones

Multiple callers of thermal_zone_device_register() don't pass any trips
to it and they might use a shortened argument list for that, so add
a special function with fewer arguments for this purpose.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/thermal_core.c | 11 +++++++++++
 include/linux/thermal.h        | 13 +++++++++++++
 2 files changed, 24 insertions(+)

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 0bdde1ab5d8b..33ebec043800 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -1400,6 +1400,17 @@ struct thermal_zone_device *thermal_zone_device_register(const char *type, int n
 }
 EXPORT_SYMBOL_GPL(thermal_zone_device_register);
 
+struct thermal_zone_device *thermal_tripless_zone_device_register(
+					const char *type,
+					void *devdata,
+					struct thermal_zone_device_ops *ops,
+					const struct thermal_zone_params *tzp)
+{
+	return thermal_zone_device_register_with_trips(type, NULL, 0, 0, devdata,
+						       ops, tzp, 0, 0);
+}
+EXPORT_SYMBOL_GPL(thermal_tripless_zone_device_register);
+
 void *thermal_zone_device_priv(struct thermal_zone_device *tzd)
 {
 	return tzd->devdata;
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index a30643104f3f..1a1433eb9b59 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -317,6 +317,12 @@ struct thermal_zone_device *thermal_zone_device_register_with_trips(
 					const struct thermal_zone_params *tzp,
 					int passive_delay, int polling_delay);
 
+struct thermal_zone_device *thermal_tripless_zone_device_register(
+					const char *type,
+					void *devdata,
+					struct thermal_zone_device_ops *ops,
+					const struct thermal_zone_params *tzp);
+
 void thermal_zone_device_unregister(struct thermal_zone_device *tz);
 
 void *thermal_zone_device_priv(struct thermal_zone_device *tzd);
@@ -377,6 +383,13 @@ static inline struct thermal_zone_device *thermal_zone_device_register_with_trip
 					int passive_delay, int polling_delay)
 { return ERR_PTR(-ENODEV); }
 
+static inline struct thermal_zone_device *thermal_tripless_zone_device_register(
+					const char *type,
+					void *devdata,
+					struct thermal_zone_device_ops *ops,
+					const struct thermal_zone_params *tzp)
+{ return ERR_PTR(-ENODEV); }
+
 static inline void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 { }
 

From cbcd51e822bf51dfc7715f474c24fbca0ed23fce Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Wed, 30 Aug 2023 18:14:57 +0200
Subject: [PATCH 1069/1189] thermal: Use
 thermal_tripless_zone_device_register()

All of the remaining callers of thermal_zone_device_register()
can use thermal_tripless_zone_device_register(), so make them
do so in order to allow the former to be dropped.

No intentional functional impact.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/power/supply/power_supply_core.c                | 4 ++--
 drivers/thermal/armada_thermal.c                        | 5 +++--
 drivers/thermal/dove_thermal.c                          | 4 ++--
 drivers/thermal/intel/int340x_thermal/int3400_thermal.c | 6 +++---
 drivers/thermal/kirkwood_thermal.c                      | 4 ++--
 drivers/thermal/spear_thermal.c                         | 4 ++--
 6 files changed, 14 insertions(+), 13 deletions(-)

diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c
index 4aa466c945e2..0b69fb7bafd8 100644
--- a/drivers/power/supply/power_supply_core.c
+++ b/drivers/power/supply/power_supply_core.c
@@ -1309,8 +1309,8 @@ static int psy_register_thermal(struct power_supply *psy)
 		struct thermal_zone_params tzp = {
 			.no_hwmon = IS_ENABLED(CONFIG_POWER_SUPPLY_HWMON)
 		};
-		psy->tzd = thermal_zone_device_register(psy->desc->name,
-				0, 0, psy, &psy_tzd_ops, &tzp, 0, 0);
+		psy->tzd = thermal_tripless_zone_device_register(psy->desc->name,
+				psy, &psy_tzd_ops, &tzp);
 		if (IS_ERR(psy->tzd))
 			return PTR_ERR(psy->tzd);
 		ret = thermal_zone_device_enable(psy->tzd);
diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c
index 9f6dc4fc9112..f00765bfc22e 100644
--- a/drivers/thermal/armada_thermal.c
+++ b/drivers/thermal/armada_thermal.c
@@ -876,8 +876,9 @@ static int armada_thermal_probe(struct platform_device *pdev)
 		/* Wait the sensors to be valid */
 		armada_wait_sensor_validity(priv);
 
-		tz = thermal_zone_device_register(priv->zone_name, 0, 0, priv,
-						  &legacy_ops, NULL, 0, 0);
+		tz = thermal_tripless_zone_device_register(priv->zone_name,
+							   priv, &legacy_ops,
+							   NULL);
 		if (IS_ERR(tz)) {
 			dev_err(&pdev->dev,
 				"Failed to register thermal zone device\n");
diff --git a/drivers/thermal/dove_thermal.c b/drivers/thermal/dove_thermal.c
index 9954040d1d2c..7a18cb960bee 100644
--- a/drivers/thermal/dove_thermal.c
+++ b/drivers/thermal/dove_thermal.c
@@ -139,8 +139,8 @@ static int dove_thermal_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	thermal = thermal_zone_device_register("dove_thermal", 0, 0,
-					       priv, &ops, NULL, 0, 0);
+	thermal = thermal_tripless_zone_device_register("dove_thermal", priv,
+							&ops, NULL);
 	if (IS_ERR(thermal)) {
 		dev_err(&pdev->dev,
 			"Failed to register thermal zone device\n");
diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
index ddd600820f68..ffc2871a021c 100644
--- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
+++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
@@ -609,9 +609,9 @@ static int int3400_thermal_probe(struct platform_device *pdev)
 
 	evaluate_odvp(priv);
 
-	priv->thermal = thermal_zone_device_register("INT3400 Thermal", 0, 0,
-						priv, &int3400_thermal_ops,
-						&int3400_thermal_params, 0, 0);
+	priv->thermal = thermal_tripless_zone_device_register("INT3400 Thermal", priv,
+							      &int3400_thermal_ops,
+							      &int3400_thermal_params);
 	if (IS_ERR(priv->thermal)) {
 		result = PTR_ERR(priv->thermal);
 		goto free_art_trt;
diff --git a/drivers/thermal/kirkwood_thermal.c b/drivers/thermal/kirkwood_thermal.c
index 668747bd86ef..acb10d24256d 100644
--- a/drivers/thermal/kirkwood_thermal.c
+++ b/drivers/thermal/kirkwood_thermal.c
@@ -71,8 +71,8 @@ static int kirkwood_thermal_probe(struct platform_device *pdev)
 	if (IS_ERR(priv->sensor))
 		return PTR_ERR(priv->sensor);
 
-	thermal = thermal_zone_device_register("kirkwood_thermal", 0, 0,
-					       priv, &ops, NULL, 0, 0);
+	thermal = thermal_tripless_zone_device_register("kirkwood_thermal",
+							priv, &ops, NULL);
 	if (IS_ERR(thermal)) {
 		dev_err(&pdev->dev,
 			"Failed to register thermal zone device\n");
diff --git a/drivers/thermal/spear_thermal.c b/drivers/thermal/spear_thermal.c
index 6e78616a576e..96d99289799a 100644
--- a/drivers/thermal/spear_thermal.c
+++ b/drivers/thermal/spear_thermal.c
@@ -122,8 +122,8 @@ static int spear_thermal_probe(struct platform_device *pdev)
 	stdev->flags = val;
 	writel_relaxed(stdev->flags, stdev->thermal_base);
 
-	spear_thermal = thermal_zone_device_register("spear_thermal", 0, 0,
-				stdev, &ops, NULL, 0, 0);
+	spear_thermal = thermal_tripless_zone_device_register("spear_thermal",
+							      stdev, &ops, NULL);
 	if (IS_ERR(spear_thermal)) {
 		dev_err(&pdev->dev, "thermal zone device is NULL\n");
 		ret = PTR_ERR(spear_thermal);

From edd220b33f479cf9dcda0bfefb2cb8c5902e9885 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Wed, 30 Aug 2023 18:16:29 +0200
Subject: [PATCH 1070/1189] thermal: core: Drop thermal_zone_device_register()

There are no more users of thermal_zone_device_register(), so drop it
from the core.

Note that thermal_zone_device_register_with_trips() may be renamed to
thermal_zone_device_register() in the future, but only after a grace
period allowing all of the possible work in progress that may be using
the latter to adjust.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/thermal_core.c | 11 -----------
 include/linux/thermal.h        | 17 -----------------
 2 files changed, 28 deletions(-)

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 33ebec043800..8717a3343512 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -1389,17 +1389,6 @@ free_tz:
 }
 EXPORT_SYMBOL_GPL(thermal_zone_device_register_with_trips);
 
-struct thermal_zone_device *thermal_zone_device_register(const char *type, int ntrips, int mask,
-							 void *devdata, struct thermal_zone_device_ops *ops,
-							 const struct thermal_zone_params *tzp, int passive_delay,
-							 int polling_delay)
-{
-	return thermal_zone_device_register_with_trips(type, NULL, ntrips, mask,
-						       devdata, ops, tzp,
-						       passive_delay, polling_delay);
-}
-EXPORT_SYMBOL_GPL(thermal_zone_device_register);
-
 struct thermal_zone_device *thermal_tripless_zone_device_register(
 					const char *type,
 					void *devdata,
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 1a1433eb9b59..c99440aac1a1 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -300,14 +300,6 @@ int thermal_acpi_critical_trip_temp(struct acpi_device *adev, int *ret_temp);
 #endif
 
 #ifdef CONFIG_THERMAL
-struct thermal_zone_device *thermal_zone_device_register(
-					const char *type,
-					int num_trips, int mask,
-					void *devdata,
-					struct thermal_zone_device_ops *ops,
-					const struct thermal_zone_params *tzp,
-					int passive_delay, int polling_delay);
-
 struct thermal_zone_device *thermal_zone_device_register_with_trips(
 					const char *type,
 					struct thermal_trip *trips,
@@ -364,15 +356,6 @@ int thermal_zone_device_enable(struct thermal_zone_device *tz);
 int thermal_zone_device_disable(struct thermal_zone_device *tz);
 void thermal_zone_device_critical(struct thermal_zone_device *tz);
 #else
-static inline struct thermal_zone_device *thermal_zone_device_register(
-					const char *type,
-					int num_trips, int mask,
-					void *devdata,
-					struct thermal_zone_device_ops *ops,
-					const struct thermal_zone_params *tzp,
-					int passive_delay, int polling_delay)
-{ return ERR_PTR(-ENODEV); }
-
 static inline struct thermal_zone_device *thermal_zone_device_register_with_trips(
 					const char *type,
 					struct thermal_trip *trips,

From 6f7f984fa85b305799076a1bcec941b9377587de Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Tue, 5 Sep 2023 06:42:48 -0700
Subject: [PATCH 1071/1189] perf/x86/uncore: Correct the number of CHAs on EMR

Starting from SPR, the basic uncore PMON information is retrieved from
the discovery table (resides in an MMIO space populated by BIOS). It is
called the discovery method. The existing value of the type->num_boxes
is from the discovery table.

On some SPR variants, there is a firmware bug that makes the value from the
discovery table incorrect. We use the value from the
SPR_MSR_UNC_CBO_CONFIG MSR to replace the one from the discovery table:

   38776cc45eb7 ("perf/x86/uncore: Correct the number of CHAs on SPR")

Unfortunately, the SPR_MSR_UNC_CBO_CONFIG isn't available for the EMR
XCC (Always returns 0), but the above firmware bug doesn't impact the
EMR XCC.

Don't let the value from the MSR replace the existing value from the
discovery table.

Fixes: 38776cc45eb7 ("perf/x86/uncore: Correct the number of CHAs on SPR")
Reported-by: Stephane Eranian <eranian@google.com>
Reported-by: Yunying Sun <yunying.sun@intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Yunying Sun <yunying.sun@intel.com>
Link: https://lore.kernel.org/r/20230905134248.496114-1-kan.liang@linux.intel.com
---
 arch/x86/events/intel/uncore_snbep.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 4d349986f76a..8250f0f59c2b 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -6474,8 +6474,18 @@ void spr_uncore_cpu_init(void)
 
 	type = uncore_find_type_by_id(uncore_msr_uncores, UNCORE_SPR_CHA);
 	if (type) {
+		/*
+		 * The value from the discovery table (stored in the type->num_boxes
+		 * of UNCORE_SPR_CHA) is incorrect on some SPR variants because of a
+		 * firmware bug. Using the value from SPR_MSR_UNC_CBO_CONFIG to replace it.
+		 */
 		rdmsrl(SPR_MSR_UNC_CBO_CONFIG, num_cbo);
-		type->num_boxes = num_cbo;
+		/*
+		 * The MSR doesn't work on the EMR XCC, but the firmware bug doesn't impact
+		 * the EMR XCC. Don't let the value from the MSR replace the existing value.
+		 */
+		if (num_cbo)
+			type->num_boxes = num_cbo;
 	}
 	spr_uncore_iio_free_running.num_boxes = uncore_type_max_boxes(uncore_msr_uncores, UNCORE_SPR_IIO);
 }

From ca0e36e3e39a4e8b5a4b647dff8c5938ca6ccbec Mon Sep 17 00:00:00 2001
From: Jerome Neanne <jneanne@baylibre.com>
Date: Tue, 5 Sep 2023 16:07:34 +0200
Subject: [PATCH 1072/1189] regulator: tps6594-regulator: Fix random kernel
 crash

Random kernel crash detected in TI CICD when regulator driver is added.
This is root caused to irq index increment being done twice causing
irq_data being allocated outside of the range.

- Rework tps6594_request_reg_irqs with correct index increment
- Adjust irq_data kmalloc size to the exact size needed for the device

This has been reported on TI mainline. No public bug report associated.

Reported-by: Udit Kumar <u-kumar1@ti.com>
Fixes: f17ccc5deb4d ("regulator: tps6594-regulator: Add driver for TI TPS6594 regulators")
Signed-off-by: Jerome Neanne <jneanne@baylibre.com>
Link: https://lore.kernel.org/r/20230828-tps6594_random_boot_crash_fix-v1-1-f29cbf9ddb37@baylibre.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/tps6594-regulator.c | 31 +++++++++++++--------------
 1 file changed, 15 insertions(+), 16 deletions(-)

diff --git a/drivers/regulator/tps6594-regulator.c b/drivers/regulator/tps6594-regulator.c
index 25ef102c8270..b7f0c8779757 100644
--- a/drivers/regulator/tps6594-regulator.c
+++ b/drivers/regulator/tps6594-regulator.c
@@ -384,21 +384,19 @@ static int tps6594_request_reg_irqs(struct platform_device *pdev,
 		if (irq < 0)
 			return -EINVAL;
 
-		irq_data[*irq_idx + j].dev = tps->dev;
-		irq_data[*irq_idx + j].type = irq_type;
-		irq_data[*irq_idx + j].rdev = rdev;
+		irq_data[*irq_idx].dev = tps->dev;
+		irq_data[*irq_idx].type = irq_type;
+		irq_data[*irq_idx].rdev = rdev;
 
 		error = devm_request_threaded_irq(tps->dev, irq, NULL,
-						  tps6594_regulator_irq_handler,
-						  IRQF_ONESHOT,
-						  irq_type->irq_name,
-						  &irq_data[*irq_idx]);
-		(*irq_idx)++;
+						  tps6594_regulator_irq_handler, IRQF_ONESHOT,
+						  irq_type->irq_name, &irq_data[*irq_idx]);
 		if (error) {
 			dev_err(tps->dev, "tps6594 failed to request %s IRQ %d: %d\n",
 				irq_type->irq_name, irq, error);
 			return error;
 		}
+		(*irq_idx)++;
 	}
 	return 0;
 }
@@ -420,8 +418,8 @@ static int tps6594_regulator_probe(struct platform_device *pdev)
 	int error, i, irq, multi, delta;
 	int irq_idx = 0;
 	int buck_idx = 0;
-	int ext_reg_irq_nb = 2;
-
+	size_t ext_reg_irq_nb = 2;
+	size_t reg_irq_nb;
 	enum {
 		MULTI_BUCK12,
 		MULTI_BUCK123,
@@ -484,15 +482,16 @@ static int tps6594_regulator_probe(struct platform_device *pdev)
 		}
 	}
 
-	if (tps->chip_id == LP8764)
+	if (tps->chip_id == LP8764) {
 		/* There is only 4 buck on LP8764 */
 		buck_configured[4] = 1;
+		reg_irq_nb = size_mul(REGS_INT_NB, (BUCK_NB - 1));
+	} else {
+		reg_irq_nb = size_mul(REGS_INT_NB, (size_add(BUCK_NB, LDO_NB)));
+	}
 
-	irq_data = devm_kmalloc_array(tps->dev,
-				REGS_INT_NB * sizeof(struct tps6594_regulator_irq_data),
-				ARRAY_SIZE(tps6594_bucks_irq_types) +
-				ARRAY_SIZE(tps6594_ldos_irq_types),
-				GFP_KERNEL);
+	irq_data = devm_kmalloc_array(tps->dev, reg_irq_nb,
+				      sizeof(struct tps6594_regulator_irq_data), GFP_KERNEL);
 	if (!irq_data)
 		return -ENOMEM;
 

From 44ade291b77c1cff25f253782c486c0c1e7296eb Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Thu, 17 Aug 2023 15:26:46 -0500
Subject: [PATCH 1073/1189] media: dt-bindings: Merge OV5695 into OV5693
 binding

The OV5695 binding is almost the same as the OV5693 binding. The only
difference is 'clock-names' is defined for OV5695. However, the lack of
clock-names is an omission as the Linux OV5693 driver expects the same
'xvclk' clock name.

'link-frequencies' is required by OV5693, but not OV5695, so make that
conditional. Really, this shouldn't vary by device, but we're stuck with
the existing binding use.

The rockchip-isp1 binding example is missing required properties, so it
has to be updated as well.

Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20230817202647.2179609-1-robh@kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../devicetree/bindings/media/i2c/ov5695.txt  | 41 -------------------
 .../bindings/media/i2c/ovti,ov5693.yaml       | 31 ++++++++++----
 .../bindings/media/rockchip-isp1.yaml         |  1 +
 3 files changed, 25 insertions(+), 48 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/media/i2c/ov5695.txt

diff --git a/Documentation/devicetree/bindings/media/i2c/ov5695.txt b/Documentation/devicetree/bindings/media/i2c/ov5695.txt
deleted file mode 100644
index 640a63717d96..000000000000
--- a/Documentation/devicetree/bindings/media/i2c/ov5695.txt
+++ /dev/null
@@ -1,41 +0,0 @@
-* Omnivision OV5695 MIPI CSI-2 sensor
-
-Required Properties:
-- compatible: shall be "ovti,ov5695"
-- clocks: reference to the xvclk input clock
-- clock-names: shall be "xvclk"
-- avdd-supply: Analog voltage supply, 2.8 volts
-- dovdd-supply: Digital I/O voltage supply, 1.8 volts
-- dvdd-supply: Digital core voltage supply, 1.2 volts
-- reset-gpios: Low active reset gpio
-
-The device node shall contain one 'port' child node with an
-'endpoint' subnode for its digital output video port,
-in accordance with the video interface bindings defined in
-Documentation/devicetree/bindings/media/video-interfaces.txt.
-The endpoint optional property 'data-lanes' shall be "<1 2>".
-
-Example:
-&i2c7 {
-	ov5695: camera-sensor@36 {
-		compatible = "ovti,ov5695";
-		reg = <0x36>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&clk_24m_cam>;
-
-		clocks = <&cru SCLK_TESTCLKOUT1>;
-		clock-names = "xvclk";
-
-		avdd-supply = <&pp2800_cam>;
-		dovdd-supply = <&pp1800>;
-		dvdd-supply = <&pp1250_cam>;
-		reset-gpios = <&gpio2 5 GPIO_ACTIVE_LOW>;
-
-		port {
-			wcam_out: endpoint {
-				remote-endpoint = <&mipi_in_wcam>;
-				data-lanes = <1 2>;
-			};
-		};
-	};
-};
diff --git a/Documentation/devicetree/bindings/media/i2c/ovti,ov5693.yaml b/Documentation/devicetree/bindings/media/i2c/ovti,ov5693.yaml
index 359dc08440a8..6829a4aadd22 100644
--- a/Documentation/devicetree/bindings/media/i2c/ovti,ov5693.yaml
+++ b/Documentation/devicetree/bindings/media/i2c/ovti,ov5693.yaml
@@ -5,26 +5,41 @@
 $id: http://devicetree.org/schemas/media/i2c/ovti,ov5693.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
-title: Omnivision OV5693 CMOS Sensor
+title: Omnivision OV5693/OV5695 CMOS Sensors
 
 maintainers:
   - Tommaso Merciai <tommaso.merciai@amarulasolutions.com>
 
 description: |
-  The Omnivision OV5693 is a high performance, 1/4-inch, 5 megapixel, CMOS
-  image sensor that delivers 2592x1944 at 30fps. It provides full-frame,
+  The Omnivision OV5693/OV5695 are high performance, 1/4-inch, 5 megapixel, CMOS
+  image sensors that deliver 2592x1944 at 30fps. It provides full-frame,
   sub-sampled, and windowed 10-bit MIPI images in various formats via the
   Serial Camera Control Bus (SCCB) interface.
 
-  OV5693 is controlled via I2C and two-wire Serial Camera Control Bus (SCCB).
-  The sensor output is available via CSI-2 serial data output (up to 2-lane).
+  OV5693/OV5695 are controlled via I2C and two-wire Serial Camera Control Bus
+  (SCCB). The sensor output is available via CSI-2 serial data output (up to
+  2-lane).
 
 allOf:
   - $ref: /schemas/media/video-interface-devices.yaml#
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: ovti,ov5693
+    then:
+      properties:
+        port:
+          properties:
+            endpoint:
+              required:
+                - link-frequencies
 
 properties:
   compatible:
-    const: ovti,ov5693
+    enum:
+      - ovti,ov5693
+      - ovti,ov5695
 
   reg:
     maxItems: 1
@@ -34,6 +49,9 @@ properties:
       System input clock (aka XVCLK). From 6 to 27 MHz.
     maxItems: 1
 
+  clock-names:
+    const: xvclk
+
   dovdd-supply:
     description:
       Digital I/O voltage supply, 1.8V.
@@ -72,7 +90,6 @@ properties:
 
         required:
           - data-lanes
-          - link-frequencies
 
 required:
   - compatible
diff --git a/Documentation/devicetree/bindings/media/rockchip-isp1.yaml b/Documentation/devicetree/bindings/media/rockchip-isp1.yaml
index 0bad7e640148..e466dff8286d 100644
--- a/Documentation/devicetree/bindings/media/rockchip-isp1.yaml
+++ b/Documentation/devicetree/bindings/media/rockchip-isp1.yaml
@@ -199,6 +199,7 @@ examples:
             wcam: camera@36 {
                 compatible = "ovti,ov5695";
                 reg = <0x36>;
+                clocks = <&cru SCLK_TESTCLKOUT1>;
 
                 port {
                     wcam_out: endpoint {

From 274e480982e6d1239be6a236bb457aa95460e1f1 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Thu, 17 Aug 2023 15:27:13 -0500
Subject: [PATCH 1074/1189] media: dt-bindings: Convert Omnivision OV7251 to DT
 schema

Convert the OmniVision OV7251 Image Sensor binding to DT schema format.

vddd-supply was listed as required, but the example and actual user
don't have it. Also, the data brief says it has an internal regulator,
so perhaps it is truly optional.

Add missing common "link-frequencies" which is used and required by the
Linux driver.

Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Acked-by: Wolfram Sang <wsa@kernel.org> # for I2C
Link: https://lore.kernel.org/r/20230817202713.2180195-1-robh@kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../devicetree/bindings/i2c/qcom,i2c-cci.yaml |   1 +
 .../devicetree/bindings/media/i2c/ov7251.txt  |  52 ---------
 .../bindings/media/i2c/ovti,ov7251.yaml       | 109 ++++++++++++++++++
 3 files changed, 110 insertions(+), 52 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/media/i2c/ov7251.txt
 create mode 100644 Documentation/devicetree/bindings/media/i2c/ovti,ov7251.yaml

diff --git a/Documentation/devicetree/bindings/i2c/qcom,i2c-cci.yaml b/Documentation/devicetree/bindings/i2c/qcom,i2c-cci.yaml
index ec79b7270437..042d4dc636ee 100644
--- a/Documentation/devicetree/bindings/i2c/qcom,i2c-cci.yaml
+++ b/Documentation/devicetree/bindings/i2c/qcom,i2c-cci.yaml
@@ -269,6 +269,7 @@ examples:
                 port {
                     ov7251_ep: endpoint {
                         data-lanes = <0 1>;
+                        link-frequencies = /bits/ 64 <240000000 319200000>;
                         remote-endpoint = <&csiphy3_ep>;
                     };
                 };
diff --git a/Documentation/devicetree/bindings/media/i2c/ov7251.txt b/Documentation/devicetree/bindings/media/i2c/ov7251.txt
deleted file mode 100644
index 8281151f7493..000000000000
--- a/Documentation/devicetree/bindings/media/i2c/ov7251.txt
+++ /dev/null
@@ -1,52 +0,0 @@
-* Omnivision 1/7.5-Inch B&W VGA CMOS Digital Image Sensor
-
-The Omnivision OV7251 is a 1/7.5-Inch CMOS active pixel digital image sensor
-with an active array size of 640H x 480V. It is programmable through a serial
-I2C interface.
-
-Required Properties:
-- compatible: Value should be "ovti,ov7251".
-- clocks: Reference to the xclk clock.
-- clock-names: Should be "xclk".
-- clock-frequency: Frequency of the xclk clock.
-- enable-gpios: Chip enable GPIO. Polarity is GPIO_ACTIVE_HIGH. This corresponds
-  to the hardware pin XSHUTDOWN which is physically active low.
-- vdddo-supply: Chip digital IO regulator.
-- vdda-supply: Chip analog regulator.
-- vddd-supply: Chip digital core regulator.
-
-The device node shall contain one 'port' child node with a single 'endpoint'
-subnode for its digital output video port, in accordance with the video
-interface bindings defined in
-Documentation/devicetree/bindings/media/video-interfaces.txt.
-
-Example:
-
-	&i2c1 {
-		...
-
-		ov7251: camera-sensor@60 {
-			compatible = "ovti,ov7251";
-			reg = <0x60>;
-
-			enable-gpios = <&gpio1 6 GPIO_ACTIVE_HIGH>;
-			pinctrl-names = "default";
-			pinctrl-0 = <&camera_bw_default>;
-
-			clocks = <&clks 200>;
-			clock-names = "xclk";
-			clock-frequency = <24000000>;
-
-			vdddo-supply = <&camera_dovdd_1v8>;
-			vdda-supply = <&camera_avdd_2v8>;
-			vddd-supply = <&camera_dvdd_1v2>;
-
-			port {
-				ov7251_ep: endpoint {
-					clock-lanes = <1>;
-					data-lanes = <0>;
-					remote-endpoint = <&csi0_ep>;
-				};
-			};
-		};
-	};
diff --git a/Documentation/devicetree/bindings/media/i2c/ovti,ov7251.yaml b/Documentation/devicetree/bindings/media/i2c/ovti,ov7251.yaml
new file mode 100644
index 000000000000..2e5187acbbb8
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/i2c/ovti,ov7251.yaml
@@ -0,0 +1,109 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/media/i2c/ovti,ov7251.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: OmniVision OV7251 Image Sensor
+
+description:
+  The Omnivision OV7251 is a 1/7.5-Inch CMOS active pixel digital image sensor
+  with an active array size of 640H x 480V. It is programmable through a serial
+  I2C interface.
+
+maintainers:
+  - Todor Tomov <todor.too@gmail.com>
+
+properties:
+  compatible:
+    const: ovti,ov7251
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    description: XCLK Input Clock
+
+  clock-names:
+    const: xclk
+
+  clock-frequency:
+    description: Frequency of the xclk clock in Hz.
+
+  vdda-supply:
+    description: Analog voltage supply, 2.8 volts
+
+  vddd-supply:
+    description: Digital core voltage supply, 1.2 volts
+
+  vdddo-supply:
+    description: Digital I/O voltage supply, 1.8 volts
+
+  enable-gpios:
+    maxItems: 1
+    description:
+      Reference to the GPIO connected to the XSHUTDOWN pin, if any. Polarity
+      is GPIO_ACTIVE_HIGH.
+
+  port:
+    description: Digital Output Port
+    $ref: /schemas/graph.yaml#/$defs/port-base
+    additionalProperties: false
+
+    properties:
+      endpoint:
+        $ref: /schemas/media/video-interfaces.yaml#
+        unevaluatedProperties: false
+
+        properties:
+          clock-lanes:
+            maximum: 1
+
+          data-lanes:
+            maxItems: 1
+
+          link-frequencies: true
+
+        required:
+          - data-lanes
+          - link-frequencies
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - vdddo-supply
+  - vdda-supply
+  - port
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        camera@3c {
+            compatible = "ovti,ov7251";
+            reg = <0x3c>;
+            clocks = <&clks 1>;
+            clock-frequency = <24000000>;
+            vdddo-supply = <&ov7251_vdddo_1v8>;
+            vdda-supply = <&ov7251_vdda_2v8>;
+            vddd-supply = <&ov7251_vddd_1v5>;
+            enable-gpios = <&gpio1 19 GPIO_ACTIVE_HIGH>;
+
+            port {
+                ov7251_ep: endpoint {
+                    remote-endpoint = <&csi0_ep>;
+                    clock-lanes = <1>;
+                    data-lanes = <0>;
+                    link-frequencies = /bits/ 64 <240000000 319200000>;
+                };
+            };
+        };
+    };
+...

From 591b00cc4fcfcb4532e4b85b5b2e67bbcf4973a0 Mon Sep 17 00:00:00 2001
From: Raphael Gallais-Pou <rgallaispou@gmail.com>
Date: Tue, 5 Sep 2023 09:27:40 +0200
Subject: [PATCH 1075/1189] dt-bindings: irqchip: convert st,stih407-irq-syscfg
 to DT schema

Convert deprecated format to DT schema format.

Signed-off-by: Raphael Gallais-Pou <rgallaispou@gmail.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20230905072740.23859-1-rgallaispou@gmail.com
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../st,sti-irq-syscfg.txt                     | 30 ---------
 .../st,stih407-irq-syscfg.yaml                | 65 +++++++++++++++++++
 2 files changed, 65 insertions(+), 30 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/interrupt-controller/st,sti-irq-syscfg.txt
 create mode 100644 Documentation/devicetree/bindings/interrupt-controller/st,stih407-irq-syscfg.yaml

diff --git a/Documentation/devicetree/bindings/interrupt-controller/st,sti-irq-syscfg.txt b/Documentation/devicetree/bindings/interrupt-controller/st,sti-irq-syscfg.txt
deleted file mode 100644
index 977d7ed3670e..000000000000
--- a/Documentation/devicetree/bindings/interrupt-controller/st,sti-irq-syscfg.txt
+++ /dev/null
@@ -1,30 +0,0 @@
-STMicroelectronics STi System Configuration Controlled IRQs
------------------------------------------------------------
-
-On STi based systems; External, CTI (Core Sight), PMU (Performance Management),
-and PL310 L2 Cache IRQs are controlled using System Configuration registers.
-This driver is used to unmask them prior to use.
-
-Required properties:
-- compatible	: Should be "st,stih407-irq-syscfg"
-- st,syscfg	: Phandle to Cortex-A9 IRQ system config registers
-- st,irq-device	: Array of IRQs to enable - should be 2 in length
-- st,fiq-device	: Array of FIQs to enable - should be 2 in length
-
-Optional properties:
-- st,invert-ext	: External IRQs can be inverted at will.  This property inverts
-		  these IRQs using bitwise logic.  A number of defines have been
-		  provided for convenience:
-			ST_IRQ_SYSCFG_EXT_1_INV
-			ST_IRQ_SYSCFG_EXT_2_INV
-			ST_IRQ_SYSCFG_EXT_3_INV
-Example:
-
-irq-syscfg {
-	compatible    = "st,stih407-irq-syscfg";
-	st,syscfg     = <&syscfg_cpu>;
-	st,irq-device = <ST_IRQ_SYSCFG_PMU_0>,
-			<ST_IRQ_SYSCFG_PMU_1>;
-	st,fiq-device = <ST_IRQ_SYSCFG_DISABLED>,
-			<ST_IRQ_SYSCFG_DISABLED>;
-};
diff --git a/Documentation/devicetree/bindings/interrupt-controller/st,stih407-irq-syscfg.yaml b/Documentation/devicetree/bindings/interrupt-controller/st,stih407-irq-syscfg.yaml
new file mode 100644
index 000000000000..2b153d7c5421
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/st,stih407-irq-syscfg.yaml
@@ -0,0 +1,65 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/interrupt-controller/st,stih407-irq-syscfg.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: STMicroelectronics STi System Configuration Controlled IRQs
+
+maintainers:
+  - Patrice Chotard <patrice.chotard@foss.st.com>
+
+description:
+  On STi based systems; External, CTI (Core Sight), PMU (Performance
+  Management), and PL310 L2 Cache IRQs are controlled using System
+  Configuration registers.  This device is used to unmask them prior to use.
+
+properties:
+  compatible:
+    const: st,stih407-irq-syscfg
+
+  st,syscfg:
+    description: Phandle to Cortex-A9 IRQ system config registers
+    $ref: /schemas/types.yaml#/definitions/phandle
+
+  st,irq-device:
+    description: Array of IRQs to enable.
+    $ref: /schemas/types.yaml#/definitions/uint32-array
+    items:
+      - description: Enable the IRQ of the channel one.
+      - description: Enable the IRQ of the channel two.
+
+  st,fiq-device:
+    description: Array of FIQs to enable.
+    $ref: /schemas/types.yaml#/definitions/uint32-array
+    items:
+      - description: Enable the IRQ of the channel one.
+      - description: Enable the IRQ of the channel two.
+
+  st,invert-ext:
+    description: External IRQs can be inverted at will. This property inverts
+      these three IRQs using bitwise logic, each one being encoded respectively
+      on the first, second and fourth bit.
+    $ref: /schemas/types.yaml#/definitions/uint32
+    enum: [ 1, 2, 3, 4, 5, 6 ]
+
+required:
+  - compatible
+  - st,syscfg
+  - st,irq-device
+  - st,fiq-device
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq-st.h>
+    irq-syscfg {
+        compatible    = "st,stih407-irq-syscfg";
+        st,syscfg     = <&syscfg_cpu>;
+        st,irq-device = <ST_IRQ_SYSCFG_PMU_0>,
+                        <ST_IRQ_SYSCFG_PMU_1>;
+        st,fiq-device = <ST_IRQ_SYSCFG_DISABLED>,
+                        <ST_IRQ_SYSCFG_DISABLED>;
+    };
+...

From e7716c74e3882405f9eca16faa6cb1bf19995399 Mon Sep 17 00:00:00 2001
From: Philipp Stanner <pstanner@redhat.com>
Date: Mon, 21 Aug 2023 10:21:29 +0200
Subject: [PATCH 1076/1189] xarray: Document necessary flag in alloc functions

Adds a new line to the docstrings of functions wrapping __xa_alloc() and
__xa_alloc_cyclic(), informing about the necessity of flag XA_FLAGS_ALLOC
being set previously.

The documentation so far says that functions wrapping __xa_alloc() and
__xa_alloc_cyclic() are supposed to return either -ENOMEM or -EBUSY in
case of an error. If the xarray has been initialized without the flag
XA_FLAGS_ALLOC, however, they fail with a different, undocumented error
code.

As hinted at in Documentation/core-api/xarray.rst, wrappers around these
functions should only be invoked when the flag has been set. The
functions' documentation should reflect that as well.

Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/linux/xarray.h | 18 ++++++++++++++++++
 lib/xarray.c           |  6 ++++++
 2 files changed, 24 insertions(+)

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 741703b45f61..cb571dfcf4b1 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -856,6 +856,9 @@ static inline int __must_check xa_insert_irq(struct xarray *xa,
  * stores the index into the @id pointer, then stores the entry at
  * that index.  A concurrent lookup will not see an uninitialised @id.
  *
+ * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set
+ * in xa_init_flags().
+ *
  * Context: Any context.  Takes and releases the xa_lock.  May sleep if
  * the @gfp flags permit.
  * Return: 0 on success, -ENOMEM if memory could not be allocated or
@@ -886,6 +889,9 @@ static inline __must_check int xa_alloc(struct xarray *xa, u32 *id,
  * stores the index into the @id pointer, then stores the entry at
  * that index.  A concurrent lookup will not see an uninitialised @id.
  *
+ * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set
+ * in xa_init_flags().
+ *
  * Context: Any context.  Takes and releases the xa_lock while
  * disabling softirqs.  May sleep if the @gfp flags permit.
  * Return: 0 on success, -ENOMEM if memory could not be allocated or
@@ -916,6 +922,9 @@ static inline int __must_check xa_alloc_bh(struct xarray *xa, u32 *id,
  * stores the index into the @id pointer, then stores the entry at
  * that index.  A concurrent lookup will not see an uninitialised @id.
  *
+ * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set
+ * in xa_init_flags().
+ *
  * Context: Process context.  Takes and releases the xa_lock while
  * disabling interrupts.  May sleep if the @gfp flags permit.
  * Return: 0 on success, -ENOMEM if memory could not be allocated or
@@ -949,6 +958,9 @@ static inline int __must_check xa_alloc_irq(struct xarray *xa, u32 *id,
  * The search for an empty entry will start at @next and will wrap
  * around if necessary.
  *
+ * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set
+ * in xa_init_flags().
+ *
  * Context: Any context.  Takes and releases the xa_lock.  May sleep if
  * the @gfp flags permit.
  * Return: 0 if the allocation succeeded without wrapping.  1 if the
@@ -983,6 +995,9 @@ static inline int xa_alloc_cyclic(struct xarray *xa, u32 *id, void *entry,
  * The search for an empty entry will start at @next and will wrap
  * around if necessary.
  *
+ * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set
+ * in xa_init_flags().
+ *
  * Context: Any context.  Takes and releases the xa_lock while
  * disabling softirqs.  May sleep if the @gfp flags permit.
  * Return: 0 if the allocation succeeded without wrapping.  1 if the
@@ -1017,6 +1032,9 @@ static inline int xa_alloc_cyclic_bh(struct xarray *xa, u32 *id, void *entry,
  * The search for an empty entry will start at @next and will wrap
  * around if necessary.
  *
+ * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set
+ * in xa_init_flags().
+ *
  * Context: Process context.  Takes and releases the xa_lock while
  * disabling interrupts.  May sleep if the @gfp flags permit.
  * Return: 0 if the allocation succeeded without wrapping.  1 if the
diff --git a/lib/xarray.c b/lib/xarray.c
index 142e36f9dfda..39f07bfc4dcc 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -1802,6 +1802,9 @@ EXPORT_SYMBOL(xa_get_order);
  * stores the index into the @id pointer, then stores the entry at
  * that index.  A concurrent lookup will not see an uninitialised @id.
  *
+ * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set
+ * in xa_init_flags().
+ *
  * Context: Any context.  Expects xa_lock to be held on entry.  May
  * release and reacquire xa_lock if @gfp flags permit.
  * Return: 0 on success, -ENOMEM if memory could not be allocated or
@@ -1850,6 +1853,9 @@ EXPORT_SYMBOL(__xa_alloc);
  * The search for an empty entry will start at @next and will wrap
  * around if necessary.
  *
+ * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set
+ * in xa_init_flags().
+ *
  * Context: Any context.  Expects xa_lock to be held on entry.  May
  * release and reacquire xa_lock if @gfp flags permit.
  * Return: 0 if the allocation succeeded without wrapping.  1 if the

From 2a15de80dd0f7e04a823291aa9eb49c5294f56af Mon Sep 17 00:00:00 2001
From: Ariel Marcovitch <arielmarcovitch@gmail.com>
Date: Sat, 26 Aug 2023 20:33:17 +0300
Subject: [PATCH 1077/1189] idr: fix param name in idr_alloc_cyclic() doc

The relevant parameter is 'start' and not 'nextid'

Fixes: 460488c58ca8 ("idr: Remove idr_alloc_ext")
Signed-off-by: Ariel Marcovitch <arielmarcovitch@gmail.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 lib/idr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/idr.c b/lib/idr.c
index 7ecdfdb5309e..13f2758c2377 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -100,7 +100,7 @@ EXPORT_SYMBOL_GPL(idr_alloc);
  * @end: The maximum ID (exclusive).
  * @gfp: Memory allocation flags.
  *
- * Allocates an unused ID in the range specified by @nextid and @end.  If
+ * Allocates an unused ID in the range specified by @start and @end.  If
  * @end is <= 0, it is treated as one larger than %INT_MAX.  This allows
  * callers to use @start + N as @end as long as N is within integer range.
  * The search for an unused ID will start at the last ID allocated and will

From 6e13d6528be2f7e801af63c8153b87293f25d736 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Thu, 31 Aug 2023 10:13:24 -0400
Subject: [PATCH 1078/1189] i3c: master: svc: fix probe failure when no i3c
 device exist

I3C masters are expected to support hot-join. This means at initialization
time we might not yet discover any device and this should not be treated
as a fatal error.

During the DAA procedure which happens at probe time, if no device has
joined, all CCC will be NACKed (from a bus perspective). This leads to an
early return with an error code which fails the probe of the master.

Let's avoid this by just telling the core through an I3C_ERROR_M2
return command code that no device was discovered, which is a valid
situation. This way the master will no longer bail out and fail to probe
for a wrong reason.

Cc: stable@vger.kernel.org
Fixes: dd3c52846d59 ("i3c: master: svc: Add Silvaco I3C master driver")
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Acked-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/r/20230831141324.2841525-1-Frank.Li@nxp.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/svc-i3c-master.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c
index 17b4ce12aef3..8f8295acdadb 100644
--- a/drivers/i3c/master/svc-i3c-master.c
+++ b/drivers/i3c/master/svc-i3c-master.c
@@ -790,6 +790,10 @@ static int svc_i3c_master_do_daa_locked(struct svc_i3c_master *master,
 				 */
 				break;
 			} else if (SVC_I3C_MSTATUS_NACKED(reg)) {
+				/* No I3C devices attached */
+				if (dev_nb == 0)
+					break;
+
 				/*
 				 * A slave device nacked the address, this is
 				 * allowed only once, DAA will be stopped and
@@ -1264,11 +1268,17 @@ static int svc_i3c_master_send_ccc_cmd(struct i3c_master_controller *m,
 {
 	struct svc_i3c_master *master = to_svc_i3c_master(m);
 	bool broadcast = cmd->id < 0x80;
+	int ret;
 
 	if (broadcast)
-		return svc_i3c_master_send_bdcast_ccc_cmd(master, cmd);
+		ret = svc_i3c_master_send_bdcast_ccc_cmd(master, cmd);
 	else
-		return svc_i3c_master_send_direct_ccc_cmd(master, cmd);
+		ret = svc_i3c_master_send_direct_ccc_cmd(master, cmd);
+
+	if (ret)
+		cmd->err = I3C_ERROR_M2;
+
+	return ret;
 }
 
 static int svc_i3c_master_priv_xfers(struct i3c_dev_desc *dev,

From 348c11a7d71b0b216f28ea077137e2351ab0dea8 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Mon, 28 Aug 2023 00:15:31 +0200
Subject: [PATCH 1079/1189] rtc: stop warning for invalid alarms when the alarm
 is disabled

When the alarm is not enabled, it may never have been set and so we can't
expect it to be valid. This will prevent the apparition of boot messages
like this one:

rtc rtc0: invalid alarm value: 2023-7-8 45:85:85

Link: https://lore.kernel.org/r/20230827221532.543353-1-alexandre.belloni@bootlin.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/interface.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c
index 499d89150afc..1b63111cdda2 100644
--- a/drivers/rtc/interface.c
+++ b/drivers/rtc/interface.c
@@ -376,7 +376,7 @@ int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
 	err = rtc_valid_tm(&alarm->time);
 
 done:
-	if (err)
+	if (err && alarm->enabled)
 		dev_warn(&rtc->dev, "invalid alarm value: %ptR\n",
 			 &alarm->time);
 

From 94ec1f06d02350860e0579b8058f1ef87506f697 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Mon, 28 Aug 2023 00:16:40 +0200
Subject: [PATCH 1080/1189] rtc: sun6i: remove unnecessary message

The core already print a message once the rtc is successfully registered,
it is not necessary to print an other one.

Acked-by: Jernej Skrabec <jernej.skrabec@gmail.com>
Link: https://lore.kernel.org/r/20230827221643.544259-1-alexandre.belloni@bootlin.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-sun6i.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/rtc/rtc-sun6i.c b/drivers/rtc/rtc-sun6i.c
index 753a2d9c8a17..8e0c66906103 100644
--- a/drivers/rtc/rtc-sun6i.c
+++ b/drivers/rtc/rtc-sun6i.c
@@ -846,8 +846,6 @@ static int sun6i_rtc_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	dev_info(&pdev->dev, "RTC enabled\n");
-
 	return 0;
 }
 

From 8805baceb0aa24757916300667940f12aa002dab Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Mon, 28 Aug 2023 00:16:41 +0200
Subject: [PATCH 1081/1189] rtc: twl: remove unnecessary messages

The RTC core already prints a message when the RTC is registered and when
registering fails, it is not necessary to have more in the driver.

Link: https://lore.kernel.org/r/20230827221643.544259-2-alexandre.belloni@bootlin.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-twl.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/rtc/rtc-twl.c b/drivers/rtc/rtc-twl.c
index f8f0d774a06e..13f8ce08243c 100644
--- a/drivers/rtc/rtc-twl.c
+++ b/drivers/rtc/rtc-twl.c
@@ -555,7 +555,6 @@ static int twl_rtc_probe(struct platform_device *pdev)
 			REG_INT_MSK_STS_A);
 	}
 
-	dev_info(&pdev->dev, "Enabling TWL-RTC\n");
 	ret = twl_rtc_write_u8(twl_rtc, BIT_RTC_CTRL_REG_STOP_RTC_M,
 			       REG_RTC_CTRL_REG);
 	if (ret < 0)
@@ -577,11 +576,8 @@ static int twl_rtc_probe(struct platform_device *pdev)
 
 	twl_rtc->rtc = devm_rtc_device_register(&pdev->dev, pdev->name,
 					&twl_rtc_ops, THIS_MODULE);
-	if (IS_ERR(twl_rtc->rtc)) {
-		dev_err(&pdev->dev, "can't register RTC device, err %ld\n",
-			PTR_ERR(twl_rtc->rtc));
+	if (IS_ERR(twl_rtc->rtc))
 		return PTR_ERR(twl_rtc->rtc);
-	}
 
 	ret = devm_request_threaded_irq(&pdev->dev, irq, NULL,
 					twl_rtc_interrupt,

From d844c64bbc86682f4ac3e92627b8e3b57ddfad6a Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Mon, 28 Aug 2023 00:16:42 +0200
Subject: [PATCH 1082/1189] rtc: wm8350: remove unnecessary messages

The RTC core already prints a message when the RTC is registered and when
registering fails, it is not necessary to have more in the driver.

Acked-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20230827221643.544259-3-alexandre.belloni@bootlin.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-wm8350.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/drivers/rtc/rtc-wm8350.c b/drivers/rtc/rtc-wm8350.c
index 947f8071803f..3c773cff2b39 100644
--- a/drivers/rtc/rtc-wm8350.c
+++ b/drivers/rtc/rtc-wm8350.c
@@ -386,8 +386,6 @@ static int wm8350_rtc_probe(struct platform_device *pdev)
 	/* enable the RTC if it's not already enabled */
 	power5 = wm8350_reg_read(wm8350, WM8350_POWER_MGMT_5);
 	if (!(power5 &  WM8350_RTC_TICK_ENA)) {
-		dev_info(wm8350->dev, "Starting RTC\n");
-
 		wm8350_reg_unlock(wm8350);
 
 		ret = wm8350_set_bits(wm8350, WM8350_POWER_MGMT_5,
@@ -426,11 +424,8 @@ static int wm8350_rtc_probe(struct platform_device *pdev)
 
 	wm_rtc->rtc = devm_rtc_device_register(&pdev->dev, "wm8350",
 					&wm8350_rtc_ops, THIS_MODULE);
-	if (IS_ERR(wm_rtc->rtc)) {
-		ret = PTR_ERR(wm_rtc->rtc);
-		dev_err(&pdev->dev, "failed to register RTC: %d\n", ret);
-		return ret;
-	}
+	if (IS_ERR(wm_rtc->rtc))
+		return PTR_ERR(wm_rtc->rtc);
 
 	ret = wm8350_register_irq(wm8350, WM8350_IRQ_RTC_SEC,
 			    wm8350_rtc_update_handler, 0,

From ce413486c9a0d735d86cc7d88660abeac99c2501 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <festevam@denx.de>
Date: Sat, 2 Sep 2023 10:44:07 -0300
Subject: [PATCH 1083/1189] dt-bindings: rtc: ds3231: Remove text binding

The "maxim,ds3231" compatible is described in the rtc-ds1307.yaml, so
there is no need to keep the text bindings version.

Remove the maxim,ds3231.txt file in favor of the rtc-ds1307.yaml binding.

Signed-off-by: Fabio Estevam <festevam@denx.de>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20230902134407.2589099-1-festevam@gmail.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 .../devicetree/bindings/rtc/maxim,ds3231.txt  | 38 -------------------
 1 file changed, 38 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/rtc/maxim,ds3231.txt

diff --git a/Documentation/devicetree/bindings/rtc/maxim,ds3231.txt b/Documentation/devicetree/bindings/rtc/maxim,ds3231.txt
deleted file mode 100644
index 85be53a42180..000000000000
--- a/Documentation/devicetree/bindings/rtc/maxim,ds3231.txt
+++ /dev/null
@@ -1,38 +0,0 @@
-* Maxim DS3231 Real Time Clock
-
-Required properties:
-- compatible: Should contain "maxim,ds3231".
-- reg: I2C address for chip.
-
-Optional property:
-- #clock-cells: Should be 1.
-- clock-output-names:
-  overwrite the default clock names "ds3231_clk_sqw" and "ds3231_clk_32khz".
-
-Each clock is assigned an identifier and client nodes can use this identifier
-to specify the clock which they consume. Following indices are allowed:
-    - 0: square-wave output on the SQW pin
-    - 1: square-wave output on the 32kHz pin
-
-- interrupts: rtc alarm/event interrupt. When this property is selected,
-  clock on the SQW pin cannot be used.
-
-Example:
-
-ds3231: ds3231@51 {
-	compatible = "maxim,ds3231";
-	reg = <0x68>;
-	#clock-cells = <1>;
-};
-
-device1 {
-...
-	clocks = <&ds3231 0>;
-...
-};
-
-device2 {
-...
-	clocks = <&ds3231 1>;
-...
-};

From 84fe419dc7578b03e721b9bd6eb07947db70fd0e Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Sat, 22 Jul 2023 14:38:46 +0200
Subject: [PATCH 1084/1189] riscv: Introduce virtual kernel mapping KASLR

KASLR implementation relies on a relocatable kernel so that we can move
the kernel mapping.

The seed needed to virtually move the kernel is taken from the device tree,
so we rely on the bootloader to provide a correct seed. Zkr could be used
unconditionnally instead if implemented, but that's for another patch.

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Tested-by: Conor Dooley <conor.dooley@microchip.com>
Tested-by: Song Shuai <songshuaishuai@tinylab.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Tested-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lore.kernel.org/r/20230722123850.634544-2-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig                   | 19 +++++++++++++++
 arch/riscv/include/asm/page.h        |  3 +++
 arch/riscv/kernel/pi/Makefile        |  2 +-
 arch/riscv/kernel/pi/cmdline_early.c | 13 ++++++++++
 arch/riscv/kernel/pi/fdt_early.c     | 30 +++++++++++++++++++++++
 arch/riscv/mm/init.c                 | 36 +++++++++++++++++++++++++++-
 6 files changed, 101 insertions(+), 2 deletions(-)
 create mode 100644 arch/riscv/kernel/pi/fdt_early.c

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 4c07b9189c86..6a606d5b74c6 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -719,6 +719,25 @@ config RELOCATABLE
 
           If unsure, say N.
 
+config RANDOMIZE_BASE
+        bool "Randomize the address of the kernel image"
+        select RELOCATABLE
+        depends on MMU && 64BIT && !XIP_KERNEL
+        help
+          Randomizes the virtual address at which the kernel image is
+          loaded, as a security feature that deters exploit attempts
+          relying on knowledge of the location of kernel internals.
+
+          It is the bootloader's job to provide entropy, by passing a
+          random u64 value in /chosen/kaslr-seed at kernel entry.
+
+          When booting via the UEFI stub, it will invoke the firmware's
+          EFI_RNG_PROTOCOL implementation (if available) to supply entropy
+          to the kernel proper. In addition, it will randomise the physical
+          location of the kernel Image as well.
+
+          If unsure, say N.
+
 endmenu # "Kernel features"
 
 menu "Boot options"
diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h
index b55ba20903ec..5488ecc337b6 100644
--- a/arch/riscv/include/asm/page.h
+++ b/arch/riscv/include/asm/page.h
@@ -106,6 +106,7 @@ typedef struct page *pgtable_t;
 struct kernel_mapping {
 	unsigned long page_offset;
 	unsigned long virt_addr;
+	unsigned long virt_offset;
 	uintptr_t phys_addr;
 	uintptr_t size;
 	/* Offset between linear mapping virtual address and kernel load address */
@@ -185,6 +186,8 @@ extern phys_addr_t __phys_addr_symbol(unsigned long x);
 
 #define sym_to_pfn(x)           __phys_to_pfn(__pa_symbol(x))
 
+unsigned long kaslr_offset(void);
+
 #endif /* __ASSEMBLY__ */
 
 #define virt_addr_valid(vaddr)	({						\
diff --git a/arch/riscv/kernel/pi/Makefile b/arch/riscv/kernel/pi/Makefile
index 7b593d44c712..07915dc9279e 100644
--- a/arch/riscv/kernel/pi/Makefile
+++ b/arch/riscv/kernel/pi/Makefile
@@ -35,5 +35,5 @@ $(obj)/string.o: $(srctree)/lib/string.c FORCE
 $(obj)/ctype.o: $(srctree)/lib/ctype.c FORCE
 	$(call if_changed_rule,cc_o_c)
 
-obj-y		:= cmdline_early.pi.o string.pi.o ctype.pi.o lib-fdt.pi.o lib-fdt_ro.pi.o
+obj-y		:= cmdline_early.pi.o fdt_early.pi.o string.pi.o ctype.pi.o lib-fdt.pi.o lib-fdt_ro.pi.o
 extra-y		:= $(patsubst %.pi.o,%.o,$(obj-y))
diff --git a/arch/riscv/kernel/pi/cmdline_early.c b/arch/riscv/kernel/pi/cmdline_early.c
index 05652d13c746..68e786c84c94 100644
--- a/arch/riscv/kernel/pi/cmdline_early.c
+++ b/arch/riscv/kernel/pi/cmdline_early.c
@@ -14,6 +14,7 @@ static char early_cmdline[COMMAND_LINE_SIZE];
  * LLVM complain because the function is actually unused in this file).
  */
 u64 set_satp_mode_from_cmdline(uintptr_t dtb_pa);
+bool set_nokaslr_from_cmdline(uintptr_t dtb_pa);
 
 static char *get_early_cmdline(uintptr_t dtb_pa)
 {
@@ -60,3 +61,15 @@ u64 set_satp_mode_from_cmdline(uintptr_t dtb_pa)
 
 	return match_noXlvl(cmdline);
 }
+
+static bool match_nokaslr(char *cmdline)
+{
+	return strstr(cmdline, "nokaslr");
+}
+
+bool set_nokaslr_from_cmdline(uintptr_t dtb_pa)
+{
+	char *cmdline = get_early_cmdline(dtb_pa);
+
+	return match_nokaslr(cmdline);
+}
diff --git a/arch/riscv/kernel/pi/fdt_early.c b/arch/riscv/kernel/pi/fdt_early.c
new file mode 100644
index 000000000000..899610e042ab
--- /dev/null
+++ b/arch/riscv/kernel/pi/fdt_early.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/libfdt.h>
+
+/*
+ * Declare the functions that are exported (but prefixed) here so that LLVM
+ * does not complain it lacks the 'static' keyword (which, if added, makes
+ * LLVM complain because the function is actually unused in this file).
+ */
+u64 get_kaslr_seed(uintptr_t dtb_pa);
+
+u64 get_kaslr_seed(uintptr_t dtb_pa)
+{
+	int node, len;
+	fdt64_t *prop;
+	u64 ret;
+
+	node = fdt_path_offset((void *)dtb_pa, "/chosen");
+	if (node < 0)
+		return 0;
+
+	prop = fdt_getprop_w((void *)dtb_pa, node, "kaslr-seed", &len);
+	if (!prop || len != sizeof(u64))
+		return 0;
+
+	ret = fdt64_to_cpu(*prop);
+	*prop = 0;
+	return ret;
+}
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 70fb31960b63..ff926531236e 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -1012,11 +1012,45 @@ static void __init pt_ops_set_late(void)
 #endif
 }
 
+#ifdef CONFIG_RANDOMIZE_BASE
+extern bool __init __pi_set_nokaslr_from_cmdline(uintptr_t dtb_pa);
+extern u64 __init __pi_get_kaslr_seed(uintptr_t dtb_pa);
+
+static int __init print_nokaslr(char *p)
+{
+	pr_info("Disabled KASLR");
+	return 0;
+}
+early_param("nokaslr", print_nokaslr);
+
+unsigned long kaslr_offset(void)
+{
+	return kernel_map.virt_offset;
+}
+#endif
+
 asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 {
 	pmd_t __maybe_unused fix_bmap_spmd, fix_bmap_epmd;
 
-	kernel_map.virt_addr = KERNEL_LINK_ADDR;
+#ifdef CONFIG_RANDOMIZE_BASE
+	if (!__pi_set_nokaslr_from_cmdline(dtb_pa)) {
+		u64 kaslr_seed = __pi_get_kaslr_seed(dtb_pa);
+		u32 kernel_size = (uintptr_t)(&_end) - (uintptr_t)(&_start);
+		u32 nr_pos;
+
+		/*
+		 * Compute the number of positions available: we are limited
+		 * by the early page table that only has one PUD and we must
+		 * be aligned on PMD_SIZE.
+		 */
+		nr_pos = (PUD_SIZE - kernel_size) / PMD_SIZE;
+
+		kernel_map.virt_offset = (kaslr_seed % nr_pos) * PMD_SIZE;
+	}
+#endif
+
+	kernel_map.virt_addr = KERNEL_LINK_ADDR + kernel_map.virt_offset;
 	kernel_map.page_offset = _AC(CONFIG_PAGE_OFFSET, UL);
 
 #ifdef CONFIG_XIP_KERNEL

From 54a519e6aff9a6bc8922149e94f89c4bf4e3e8fb Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Sat, 22 Jul 2023 14:38:47 +0200
Subject: [PATCH 1085/1189] riscv: Dump out kernel offset information on panic

Dump out the KASLR virtual kernel offset when panic to help debug kernel.

Signed-off-by: Zong Li <zong.li@sifive.com>
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Tested-by: Conor Dooley <conor.dooley@microchip.com>
Tested-by: Song Shuai <songshuaishuai@tinylab.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Tested-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lore.kernel.org/r/20230722123850.634544-3-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/setup.c | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 971fe776e2f8..0fb5a26ca4cc 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -21,6 +21,7 @@
 #include <linux/smp.h>
 #include <linux/efi.h>
 #include <linux/crash_dump.h>
+#include <linux/panic_notifier.h>
 
 #include <asm/acpi.h>
 #include <asm/alternative.h>
@@ -341,3 +342,27 @@ void free_initmem(void)
 
 	free_initmem_default(POISON_FREE_INITMEM);
 }
+
+static int dump_kernel_offset(struct notifier_block *self,
+			      unsigned long v, void *p)
+{
+	pr_emerg("Kernel Offset: 0x%lx from 0x%lx\n",
+		 kernel_map.virt_offset,
+		 KERNEL_LINK_ADDR);
+
+	return 0;
+}
+
+static struct notifier_block kernel_offset_notifier = {
+	.notifier_call = dump_kernel_offset
+};
+
+static int __init register_kernel_offset_dumper(void)
+{
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE))
+		atomic_notifier_chain_register(&panic_notifier_list,
+					       &kernel_offset_notifier);
+
+	return 0;
+}
+device_initcall(register_kernel_offset_dumper);

From 6b56beb5f6940f0b77cb520263651328a8378efa Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Sat, 22 Jul 2023 14:38:48 +0200
Subject: [PATCH 1086/1189] arm64: libstub: Move KASLR handling functions to
 kaslr.c
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This prepares for riscv to use the same functions to handle the pĥysical
kernel move when KASLR is enabled.

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Tested-by: Conor Dooley <conor.dooley@microchip.com>
Tested-by: Song Shuai <songshuaishuai@tinylab.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Tested-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lore.kernel.org/r/20230722123850.634544-4-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/arm64/include/asm/efi.h              |   2 +
 drivers/firmware/efi/libstub/Makefile     |   2 +-
 drivers/firmware/efi/libstub/arm64-stub.c | 117 ++--------------
 drivers/firmware/efi/libstub/efistub.h    |   8 ++
 drivers/firmware/efi/libstub/kaslr.c      | 159 ++++++++++++++++++++++
 5 files changed, 183 insertions(+), 105 deletions(-)
 create mode 100644 drivers/firmware/efi/libstub/kaslr.c

diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index 4cf2cb053bc8..46273ee89445 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -168,4 +168,6 @@ static inline void efi_capsule_flush_cache_range(void *addr, int size)
 
 efi_status_t efi_handle_corrupted_x18(efi_status_t s, const char *f);
 
+void efi_icache_sync(unsigned long start, unsigned long end);
+
 #endif /* _ASM_EFI_H */
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index 16d64a34d1e1..11aba8a041ec 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -86,7 +86,7 @@ lib-$(CONFIG_EFI_GENERIC_STUB)	+= efi-stub.o string.o intrinsics.o systable.o \
 				   screen_info.o efi-stub-entry.o
 
 lib-$(CONFIG_ARM)		+= arm32-stub.o
-lib-$(CONFIG_ARM64)		+= arm64.o arm64-stub.o smbios.o
+lib-$(CONFIG_ARM64)		+= kaslr.o arm64.o arm64-stub.o smbios.o
 lib-$(CONFIG_X86)		+= x86-stub.o
 lib-$(CONFIG_RISCV)		+= riscv.o riscv-stub.o
 lib-$(CONFIG_LOONGARCH)		+= loongarch.o loongarch-stub.o
diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c
index 770b8ecb7398..452b7ccd330e 100644
--- a/drivers/firmware/efi/libstub/arm64-stub.c
+++ b/drivers/firmware/efi/libstub/arm64-stub.c
@@ -14,42 +14,6 @@
 
 #include "efistub.h"
 
-/*
- * Distro versions of GRUB may ignore the BSS allocation entirely (i.e., fail
- * to provide space, and fail to zero it). Check for this condition by double
- * checking that the first and the last byte of the image are covered by the
- * same EFI memory map entry.
- */
-static bool check_image_region(u64 base, u64 size)
-{
-	struct efi_boot_memmap *map;
-	efi_status_t status;
-	bool ret = false;
-	int map_offset;
-
-	status = efi_get_memory_map(&map, false);
-	if (status != EFI_SUCCESS)
-		return false;
-
-	for (map_offset = 0; map_offset < map->map_size; map_offset += map->desc_size) {
-		efi_memory_desc_t *md = (void *)map->map + map_offset;
-		u64 end = md->phys_addr + md->num_pages * EFI_PAGE_SIZE;
-
-		/*
-		 * Find the region that covers base, and return whether
-		 * it covers base+size bytes.
-		 */
-		if (base >= md->phys_addr && base < end) {
-			ret = (base + size) <= end;
-			break;
-		}
-	}
-
-	efi_bs_call(free_pool, map);
-
-	return ret;
-}
-
 efi_status_t handle_kernel_image(unsigned long *image_addr,
 				 unsigned long *image_size,
 				 unsigned long *reserve_addr,
@@ -59,31 +23,6 @@ efi_status_t handle_kernel_image(unsigned long *image_addr,
 {
 	efi_status_t status;
 	unsigned long kernel_size, kernel_codesize, kernel_memsize;
-	u32 phys_seed = 0;
-	u64 min_kimg_align = efi_get_kimg_min_align();
-
-	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
-		efi_guid_t li_fixed_proto = LINUX_EFI_LOADED_IMAGE_FIXED_GUID;
-		void *p;
-
-		if (efi_nokaslr) {
-			efi_info("KASLR disabled on kernel command line\n");
-		} else if (efi_bs_call(handle_protocol, image_handle,
-				       &li_fixed_proto, &p) == EFI_SUCCESS) {
-			efi_info("Image placement fixed by loader\n");
-		} else {
-			status = efi_get_random_bytes(sizeof(phys_seed),
-						      (u8 *)&phys_seed);
-			if (status == EFI_NOT_FOUND) {
-				efi_info("EFI_RNG_PROTOCOL unavailable\n");
-				efi_nokaslr = true;
-			} else if (status != EFI_SUCCESS) {
-				efi_err("efi_get_random_bytes() failed (0x%lx)\n",
-					status);
-				efi_nokaslr = true;
-			}
-		}
-	}
 
 	if (image->image_base != _text) {
 		efi_err("FIRMWARE BUG: efi_loaded_image_t::image_base has bogus value\n");
@@ -98,50 +37,15 @@ efi_status_t handle_kernel_image(unsigned long *image_addr,
 	kernel_codesize = __inittext_end - _text;
 	kernel_memsize = kernel_size + (_end - _edata);
 	*reserve_size = kernel_memsize;
+	*image_addr = (unsigned long)_text;
 
-	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && phys_seed != 0) {
-		/*
-		 * If KASLR is enabled, and we have some randomness available,
-		 * locate the kernel at a randomized offset in physical memory.
-		 */
-		status = efi_random_alloc(*reserve_size, min_kimg_align,
-					  reserve_addr, phys_seed,
-					  EFI_LOADER_CODE);
-		if (status != EFI_SUCCESS)
-			efi_warn("efi_random_alloc() failed: 0x%lx\n", status);
-	} else {
-		status = EFI_OUT_OF_RESOURCES;
-	}
-
-	if (status != EFI_SUCCESS) {
-		if (!check_image_region((u64)_text, kernel_memsize)) {
-			efi_err("FIRMWARE BUG: Image BSS overlaps adjacent EFI memory region\n");
-		} else if (IS_ALIGNED((u64)_text, min_kimg_align) &&
-			   (u64)_end < EFI_ALLOC_LIMIT) {
-			/*
-			 * Just execute from wherever we were loaded by the
-			 * UEFI PE/COFF loader if the placement is suitable.
-			 */
-			*image_addr = (u64)_text;
-			*reserve_size = 0;
-			return EFI_SUCCESS;
-		}
-
-		status = efi_allocate_pages_aligned(*reserve_size, reserve_addr,
-						    ULONG_MAX, min_kimg_align,
-						    EFI_LOADER_CODE);
-
-		if (status != EFI_SUCCESS) {
-			efi_err("Failed to relocate kernel\n");
-			*reserve_size = 0;
-			return status;
-		}
-	}
-
-	*image_addr = *reserve_addr;
-	memcpy((void *)*image_addr, _text, kernel_size);
-	caches_clean_inval_pou(*image_addr, *image_addr + kernel_codesize);
-	efi_remap_image(*image_addr, *reserve_size, kernel_codesize);
+	status = efi_kaslr_relocate_kernel(image_addr,
+					   reserve_addr, reserve_size,
+					   kernel_size, kernel_codesize,
+					   kernel_memsize,
+					   efi_kaslr_get_phys_seed(image_handle));
+	if (status != EFI_SUCCESS)
+		return status;
 
 	return EFI_SUCCESS;
 }
@@ -159,3 +63,8 @@ unsigned long primary_entry_offset(void)
 	 */
 	return (char *)primary_entry - _text;
 }
+
+void efi_icache_sync(unsigned long start, unsigned long end)
+{
+	caches_clean_inval_pou(start, end);
+}
diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index 6aa38a1bf126..b1a1037567ba 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -1132,6 +1132,14 @@ const u8 *__efi_get_smbios_string(const struct efi_smbios_record *record,
 
 void efi_remap_image(unsigned long image_base, unsigned alloc_size,
 		     unsigned long code_size);
+efi_status_t efi_kaslr_relocate_kernel(unsigned long *image_addr,
+				       unsigned long *reserve_addr,
+				       unsigned long *reserve_size,
+				       unsigned long kernel_size,
+				       unsigned long kernel_codesize,
+				       unsigned long kernel_memsize,
+				       u32 phys_seed);
+u32 efi_kaslr_get_phys_seed(efi_handle_t image_handle);
 
 asmlinkage efi_status_t __efiapi
 efi_zboot_entry(efi_handle_t handle, efi_system_table_t *systab);
diff --git a/drivers/firmware/efi/libstub/kaslr.c b/drivers/firmware/efi/libstub/kaslr.c
new file mode 100644
index 000000000000..be0c8ab0982a
--- /dev/null
+++ b/drivers/firmware/efi/libstub/kaslr.c
@@ -0,0 +1,159 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Helper functions used by the EFI stub on multiple
+ * architectures to deal with physical address space randomization.
+ */
+#include <linux/efi.h>
+
+#include "efistub.h"
+
+/**
+ * efi_kaslr_get_phys_seed() - Get random seed for physical kernel KASLR
+ * @image_handle:	Handle to the image
+ *
+ * If KASLR is not disabled, obtain a random seed using EFI_RNG_PROTOCOL
+ * that will be used to move the kernel physical mapping.
+ *
+ * Return:	the random seed
+ */
+u32 efi_kaslr_get_phys_seed(efi_handle_t image_handle)
+{
+	efi_status_t status;
+	u32 phys_seed;
+	efi_guid_t li_fixed_proto = LINUX_EFI_LOADED_IMAGE_FIXED_GUID;
+	void *p;
+
+	if (!IS_ENABLED(CONFIG_RANDOMIZE_BASE))
+		return 0;
+
+	if (efi_nokaslr) {
+		efi_info("KASLR disabled on kernel command line\n");
+	} else if (efi_bs_call(handle_protocol, image_handle,
+			       &li_fixed_proto, &p) == EFI_SUCCESS) {
+		efi_info("Image placement fixed by loader\n");
+	} else {
+		status = efi_get_random_bytes(sizeof(phys_seed),
+					      (u8 *)&phys_seed);
+		if (status == EFI_SUCCESS) {
+			return phys_seed;
+		} else if (status == EFI_NOT_FOUND) {
+			efi_info("EFI_RNG_PROTOCOL unavailable\n");
+			efi_nokaslr = true;
+		} else if (status != EFI_SUCCESS) {
+			efi_err("efi_get_random_bytes() failed (0x%lx)\n",
+				status);
+			efi_nokaslr = true;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Distro versions of GRUB may ignore the BSS allocation entirely (i.e., fail
+ * to provide space, and fail to zero it). Check for this condition by double
+ * checking that the first and the last byte of the image are covered by the
+ * same EFI memory map entry.
+ */
+static bool check_image_region(u64 base, u64 size)
+{
+	struct efi_boot_memmap *map;
+	efi_status_t status;
+	bool ret = false;
+	int map_offset;
+
+	status = efi_get_memory_map(&map, false);
+	if (status != EFI_SUCCESS)
+		return false;
+
+	for (map_offset = 0; map_offset < map->map_size; map_offset += map->desc_size) {
+		efi_memory_desc_t *md = (void *)map->map + map_offset;
+		u64 end = md->phys_addr + md->num_pages * EFI_PAGE_SIZE;
+
+		/*
+		 * Find the region that covers base, and return whether
+		 * it covers base+size bytes.
+		 */
+		if (base >= md->phys_addr && base < end) {
+			ret = (base + size) <= end;
+			break;
+		}
+	}
+
+	efi_bs_call(free_pool, map);
+
+	return ret;
+}
+
+/**
+ * efi_kaslr_relocate_kernel() - Relocate the kernel (random if KASLR enabled)
+ * @image_addr: Pointer to the current kernel location
+ * @reserve_addr:	Pointer to the relocated kernel location
+ * @reserve_size:	Size of the relocated kernel
+ * @kernel_size:	Size of the text + data
+ * @kernel_codesize:	Size of the text
+ * @kernel_memsize:	Size of the text + data + bss
+ * @phys_seed:		Random seed used for the relocation
+ *
+ * If KASLR is not enabled, this function relocates the kernel to a fixed
+ * address (or leave it as its current location). If KASLR is enabled, the
+ * kernel physical location is randomized using the seed in parameter.
+ *
+ * Return:	status code, EFI_SUCCESS if relocation is successful
+ */
+efi_status_t efi_kaslr_relocate_kernel(unsigned long *image_addr,
+				       unsigned long *reserve_addr,
+				       unsigned long *reserve_size,
+				       unsigned long kernel_size,
+				       unsigned long kernel_codesize,
+				       unsigned long kernel_memsize,
+				       u32 phys_seed)
+{
+	efi_status_t status;
+	u64 min_kimg_align = efi_get_kimg_min_align();
+
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && phys_seed != 0) {
+		/*
+		 * If KASLR is enabled, and we have some randomness available,
+		 * locate the kernel at a randomized offset in physical memory.
+		 */
+		status = efi_random_alloc(*reserve_size, min_kimg_align,
+					  reserve_addr, phys_seed,
+					  EFI_LOADER_CODE);
+		if (status != EFI_SUCCESS)
+			efi_warn("efi_random_alloc() failed: 0x%lx\n", status);
+	} else {
+		status = EFI_OUT_OF_RESOURCES;
+	}
+
+	if (status != EFI_SUCCESS) {
+		if (!check_image_region(*image_addr, kernel_memsize)) {
+			efi_err("FIRMWARE BUG: Image BSS overlaps adjacent EFI memory region\n");
+		} else if (IS_ALIGNED(*image_addr, min_kimg_align) &&
+			   (u64)_end < EFI_ALLOC_LIMIT) {
+			/*
+			 * Just execute from wherever we were loaded by the
+			 * UEFI PE/COFF loader if the placement is suitable.
+			 */
+			*reserve_size = 0;
+			return EFI_SUCCESS;
+		}
+
+		status = efi_allocate_pages_aligned(*reserve_size, reserve_addr,
+						    ULONG_MAX, min_kimg_align,
+						    EFI_LOADER_CODE);
+
+		if (status != EFI_SUCCESS) {
+			efi_err("Failed to relocate kernel\n");
+			*reserve_size = 0;
+			return status;
+		}
+	}
+
+	memcpy((void *)*reserve_addr, (void *)*image_addr, kernel_size);
+	*image_addr = *reserve_addr;
+	efi_icache_sync(*image_addr, *image_addr + kernel_codesize);
+	efi_remap_image(*image_addr, *reserve_size, kernel_codesize);
+
+	return status;
+}

From 3c35d1a03c8b864f08088d51e121aa7c0067b146 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Sat, 22 Jul 2023 14:38:49 +0200
Subject: [PATCH 1087/1189] libstub: Fix compilation warning for rv32

Fix the following warning which appears when compiled for rv32 by using
unsigned long type instead of u64.

../drivers/firmware/efi/libstub/efi-stub-helper.c: In function 'efi_kaslr_relocate_kernel':
../drivers/firmware/efi/libstub/efi-stub-helper.c:846:28: warning: cast from pointer to integer of different size [-Wpointer-to-int-cast]
  846 |                            (u64)_end < EFI_ALLOC_LIMIT) {

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Tested-by: Conor Dooley <conor.dooley@microchip.com>
Tested-by: Song Shuai <songshuaishuai@tinylab.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Tested-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lore.kernel.org/r/20230722123850.634544-5-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 drivers/firmware/efi/libstub/kaslr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/firmware/efi/libstub/kaslr.c b/drivers/firmware/efi/libstub/kaslr.c
index be0c8ab0982a..afb857329799 100644
--- a/drivers/firmware/efi/libstub/kaslr.c
+++ b/drivers/firmware/efi/libstub/kaslr.c
@@ -130,7 +130,7 @@ efi_status_t efi_kaslr_relocate_kernel(unsigned long *image_addr,
 		if (!check_image_region(*image_addr, kernel_memsize)) {
 			efi_err("FIRMWARE BUG: Image BSS overlaps adjacent EFI memory region\n");
 		} else if (IS_ALIGNED(*image_addr, min_kimg_align) &&
-			   (u64)_end < EFI_ALLOC_LIMIT) {
+			   (unsigned long)_end < EFI_ALLOC_LIMIT) {
 			/*
 			 * Just execute from wherever we were loaded by the
 			 * UEFI PE/COFF loader if the placement is suitable.

From b7ac4b8ee73d4fec0998664c9dd61f089d481044 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Sat, 22 Jul 2023 14:38:50 +0200
Subject: [PATCH 1088/1189] riscv: libstub: Implement KASLR by using generic
 functions

We can now use arm64 functions to handle the move of the kernel physical
mapping: if KASLR is enabled, we will try to get a random seed from the
firmware, if not possible, the kernel will be moved to a location that
suits its alignment constraints.

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Tested-by: Conor Dooley <conor.dooley@microchip.com>
Tested-by: Song Shuai <songshuaishuai@tinylab.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Tested-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lore.kernel.org/r/20230722123850.634544-6-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/efi.h              |  2 ++
 arch/riscv/kernel/image-vars.h            |  1 +
 drivers/firmware/efi/libstub/Makefile     |  2 +-
 drivers/firmware/efi/libstub/riscv-stub.c | 33 +++++++++++------------
 4 files changed, 19 insertions(+), 19 deletions(-)

diff --git a/arch/riscv/include/asm/efi.h b/arch/riscv/include/asm/efi.h
index 29e9a0d84b16..00b24ba55035 100644
--- a/arch/riscv/include/asm/efi.h
+++ b/arch/riscv/include/asm/efi.h
@@ -51,4 +51,6 @@ void efi_virtmap_unload(void);
 
 unsigned long stext_offset(void);
 
+void efi_icache_sync(unsigned long start, unsigned long end);
+
 #endif /* _ASM_EFI_H */
diff --git a/arch/riscv/kernel/image-vars.h b/arch/riscv/kernel/image-vars.h
index 15616155008c..ea1a10355ce9 100644
--- a/arch/riscv/kernel/image-vars.h
+++ b/arch/riscv/kernel/image-vars.h
@@ -27,6 +27,7 @@ __efistub__start		= _start;
 __efistub__start_kernel		= _start_kernel;
 __efistub__end			= _end;
 __efistub__edata		= _edata;
+__efistub___init_text_end	= __init_text_end;
 __efistub_screen_info		= screen_info;
 
 #endif
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index 11aba8a041ec..dc90a31b189f 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -88,7 +88,7 @@ lib-$(CONFIG_EFI_GENERIC_STUB)	+= efi-stub.o string.o intrinsics.o systable.o \
 lib-$(CONFIG_ARM)		+= arm32-stub.o
 lib-$(CONFIG_ARM64)		+= kaslr.o arm64.o arm64-stub.o smbios.o
 lib-$(CONFIG_X86)		+= x86-stub.o
-lib-$(CONFIG_RISCV)		+= riscv.o riscv-stub.o
+lib-$(CONFIG_RISCV)		+= kaslr.o riscv.o riscv-stub.o
 lib-$(CONFIG_LOONGARCH)		+= loongarch.o loongarch-stub.o
 
 CFLAGS_arm32-stub.o		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
diff --git a/drivers/firmware/efi/libstub/riscv-stub.c b/drivers/firmware/efi/libstub/riscv-stub.c
index 145c9f0ba217..c96d6dcee86c 100644
--- a/drivers/firmware/efi/libstub/riscv-stub.c
+++ b/drivers/firmware/efi/libstub/riscv-stub.c
@@ -30,32 +30,29 @@ efi_status_t handle_kernel_image(unsigned long *image_addr,
 				 efi_loaded_image_t *image,
 				 efi_handle_t image_handle)
 {
-	unsigned long kernel_size = 0;
-	unsigned long preferred_addr;
+	unsigned long kernel_size, kernel_codesize, kernel_memsize;
 	efi_status_t status;
 
 	kernel_size = _edata - _start;
+	kernel_codesize = __init_text_end - _start;
+	kernel_memsize = kernel_size + (_end - _edata);
 	*image_addr = (unsigned long)_start;
-	*image_size = kernel_size + (_end - _edata);
-
-	/*
-	 * RISC-V kernel maps PAGE_OFFSET virtual address to the same physical
-	 * address where kernel is booted. That's why kernel should boot from
-	 * as low as possible to avoid wastage of memory. Currently, dram_base
-	 * is occupied by the firmware. So the preferred address for kernel to
-	 * boot is next aligned address. If preferred address is not available,
-	 * relocate_kernel will fall back to efi_low_alloc_above to allocate
-	 * lowest possible memory region as long as the address and size meets
-	 * the alignment constraints.
-	 */
-	preferred_addr = EFI_KIMG_PREFERRED_ADDRESS;
-	status = efi_relocate_kernel(image_addr, kernel_size, *image_size,
-				     preferred_addr, efi_get_kimg_min_align(),
-				     0x0);
+	*image_size = kernel_memsize;
+	*reserve_size = *image_size;
 
+	status = efi_kaslr_relocate_kernel(image_addr,
+					   reserve_addr, reserve_size,
+					   kernel_size, kernel_codesize, kernel_memsize,
+					   efi_kaslr_get_phys_seed(image_handle));
 	if (status != EFI_SUCCESS) {
 		efi_err("Failed to relocate kernel\n");
 		*image_size = 0;
 	}
+
 	return status;
 }
+
+void efi_icache_sync(unsigned long start, unsigned long end)
+{
+	asm volatile ("fence.i" ::: "memory");
+}

From a5e2151ff9d5852d0ababbbcaeebd9646af9c8d9 Mon Sep 17 00:00:00 2001
From: Quan Tian <qtian@vmware.com>
Date: Tue, 5 Sep 2023 10:36:10 +0000
Subject: [PATCH 1089/1189] net/ipv6: SKB symmetric hash should incorporate
 transport ports

__skb_get_hash_symmetric() was added to compute a symmetric hash over
the protocol, addresses and transport ports, by commit eb70db875671
("packet: Use symmetric hash for PACKET_FANOUT_HASH."). It uses
flow_keys_dissector_symmetric_keys as the flow_dissector to incorporate
IPv4 addresses, IPv6 addresses and ports. However, it should not specify
the flag as FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL, which stops further
dissection when an IPv6 flow label is encountered, making transport
ports not being incorporated in such case.

As a consequence, the symmetric hash is based on 5-tuple for IPv4 but
3-tuple for IPv6 when flow label is present. It caused a few problems,
e.g. when nft symhash and openvswitch l4_sym rely on the symmetric hash
to perform load balancing as different L4 flows between two given IPv6
addresses would always get the same symmetric hash, leading to uneven
traffic distribution.

Removing the use of FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL makes sure the
symmetric hash is based on 5-tuple for both IPv4 and IPv6 consistently.

Fixes: eb70db875671 ("packet: Use symmetric hash for PACKET_FANOUT_HASH.")
Reported-by: Lars Ekman <uablrek@gmail.com>
Closes: https://github.com/antrea-io/antrea/issues/5457
Signed-off-by: Quan Tian <qtian@vmware.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/flow_dissector.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 89d15ceaf9af..b3b3af0e7844 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -1831,8 +1831,7 @@ u32 __skb_get_hash_symmetric(const struct sk_buff *skb)
 
 	memset(&keys, 0, sizeof(keys));
 	__skb_flow_dissect(NULL, skb, &flow_keys_dissector_symmetric,
-			   &keys, NULL, 0, 0, 0,
-			   FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
+			   &keys, NULL, 0, 0, 0, 0);
 
 	return __flow_hash_from_keys(&keys, &hashrnd);
 }

From 39285e124edbc752331e98ace37cc141a6a3747a Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Tue, 5 Sep 2023 08:46:10 +0000
Subject: [PATCH 1090/1189] net: team: do not use dynamic lockdep key

team interface has used a dynamic lockdep key to avoid false-positive
lockdep deadlock detection. Virtual interfaces such as team usually
have their own lock for protecting private data.
These interfaces can be nested.
team0
  |
team1

Each interface's lock is actually different(team0->lock and team1->lock).
So,
mutex_lock(&team0->lock);
mutex_lock(&team1->lock);
mutex_unlock(&team1->lock);
mutex_unlock(&team0->lock);
The above case is absolutely safe. But lockdep warns about deadlock.
Because the lockdep understands these two locks are same. This is a
false-positive lockdep warning.

So, in order to avoid this problem, the team interfaces started to use
dynamic lockdep key. The false-positive problem was fixed, but it
introduced a new problem.

When the new team virtual interface is created, it registers a dynamic
lockdep key(creates dynamic lockdep key) and uses it. But there is the
limitation of the number of lockdep keys.
So, If so many team interfaces are created, it consumes all lockdep keys.
Then, the lockdep stops to work and warns about it.

In order to fix this problem, team interfaces use the subclass instead
of the dynamic key. So, when a new team interface is created, it doesn't
register(create) a new lockdep, but uses existed subclass key instead.
It is already used by the bonding interface for a similar case.

As the bonding interface does, the subclass variable is the same as
the 'dev->nested_level'. This variable indicates the depth in the stacked
interface graph.

The 'dev->nested_level' is protected by RTNL and RCU.
So, 'mutex_lock_nested()' for 'team->lock' requires RTNL or RCU.
In the current code, 'team->lock' is usually acquired under RTNL, there is
no problem with using 'dev->nested_level'.

The 'team_nl_team_get()' and The 'lb_stats_refresh()' functions acquire
'team->lock' without RTNL.
But these don't iterate their own ports nested so they don't need nested
lock.

Reproducer:
   for i in {0..1000}
   do
           ip link add team$i type team
           ip link add dummy$i master team$i type dummy
           ip link set dummy$i up
           ip link set team$i up
   done

Splat looks like:
   BUG: MAX_LOCKDEP_ENTRIES too low!
   turning off the locking correctness validator.
   Please attach the output of /proc/lock_stat to the bug report
   CPU: 0 PID: 4104 Comm: ip Not tainted 6.5.0-rc7+ #45
   Call Trace:
    <TASK>
   dump_stack_lvl+0x64/0xb0
   add_lock_to_list+0x30d/0x5e0
   check_prev_add+0x73a/0x23a0
   ...
   sock_def_readable+0xfe/0x4f0
   netlink_broadcast+0x76b/0xac0
   nlmsg_notify+0x69/0x1d0
   dev_open+0xed/0x130
   ...

Reported-by: syzbot+9bbbacfbf1e04d5221f7@syzkaller.appspotmail.com
Fixes: 369f61bee0f5 ("team: fix nested locking lockdep warning")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c                  | 113 +++++++++++------------
 drivers/net/team/team_mode_loadbalance.c |   4 +-
 include/linux/if_team.h                  |  30 +++++-
 3 files changed, 86 insertions(+), 61 deletions(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index e8b94580194e..ad29122a5468 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1135,8 +1135,8 @@ static int team_port_add(struct team *team, struct net_device *port_dev,
 			 struct netlink_ext_ack *extack)
 {
 	struct net_device *dev = team->dev;
-	struct team_port *port;
 	char *portname = port_dev->name;
+	struct team_port *port;
 	int err;
 
 	if (port_dev->flags & IFF_LOOPBACK) {
@@ -1203,13 +1203,6 @@ static int team_port_add(struct team *team, struct net_device *port_dev,
 
 	memcpy(port->orig.dev_addr, port_dev->dev_addr, port_dev->addr_len);
 
-	err = team_port_enter(team, port);
-	if (err) {
-		netdev_err(dev, "Device %s failed to enter team mode\n",
-			   portname);
-		goto err_port_enter;
-	}
-
 	err = dev_open(port_dev, extack);
 	if (err) {
 		netdev_dbg(dev, "Device %s opening failed\n",
@@ -1217,6 +1210,26 @@ static int team_port_add(struct team *team, struct net_device *port_dev,
 		goto err_dev_open;
 	}
 
+	err = team_upper_dev_link(team, port, extack);
+	if (err) {
+		netdev_err(dev, "Device %s failed to set upper link\n",
+			   portname);
+		goto err_set_upper_link;
+	}
+
+	/* lockdep subclass variable(dev->nested_level) was updated by
+	 * team_upper_dev_link().
+	 */
+	team_unlock(team);
+	team_lock(team);
+
+	err = team_port_enter(team, port);
+	if (err) {
+		netdev_err(dev, "Device %s failed to enter team mode\n",
+			   portname);
+		goto err_port_enter;
+	}
+
 	err = vlan_vids_add_by_dev(port_dev, dev);
 	if (err) {
 		netdev_err(dev, "Failed to add vlan ids to device %s\n",
@@ -1242,13 +1255,6 @@ static int team_port_add(struct team *team, struct net_device *port_dev,
 		goto err_handler_register;
 	}
 
-	err = team_upper_dev_link(team, port, extack);
-	if (err) {
-		netdev_err(dev, "Device %s failed to set upper link\n",
-			   portname);
-		goto err_set_upper_link;
-	}
-
 	err = __team_option_inst_add_port(team, port);
 	if (err) {
 		netdev_err(dev, "Device %s failed to add per-port options\n",
@@ -1295,9 +1301,6 @@ err_set_slave_promisc:
 	__team_option_inst_del_port(team, port);
 
 err_option_port_add:
-	team_upper_dev_unlink(team, port);
-
-err_set_upper_link:
 	netdev_rx_handler_unregister(port_dev);
 
 err_handler_register:
@@ -1307,13 +1310,16 @@ err_enable_netpoll:
 	vlan_vids_del_by_dev(port_dev, dev);
 
 err_vids_add:
+	team_port_leave(team, port);
+
+err_port_enter:
+	team_upper_dev_unlink(team, port);
+
+err_set_upper_link:
 	dev_close(port_dev);
 
 err_dev_open:
-	team_port_leave(team, port);
 	team_port_set_orig_dev_addr(port);
-
-err_port_enter:
 	dev_set_mtu(port_dev, port->orig.mtu);
 
 err_set_mtu:
@@ -1616,6 +1622,7 @@ static int team_init(struct net_device *dev)
 	int err;
 
 	team->dev = dev;
+	mutex_init(&team->lock);
 	team_set_no_mode(team);
 	team->notifier_ctx = false;
 
@@ -1643,8 +1650,6 @@ static int team_init(struct net_device *dev)
 		goto err_options_register;
 	netif_carrier_off(dev);
 
-	lockdep_register_key(&team->team_lock_key);
-	__mutex_init(&team->lock, "team->team_lock_key", &team->team_lock_key);
 	netdev_lockdep_set_classes(dev);
 
 	return 0;
@@ -1665,7 +1670,7 @@ static void team_uninit(struct net_device *dev)
 	struct team_port *port;
 	struct team_port *tmp;
 
-	mutex_lock(&team->lock);
+	team_lock(team);
 	list_for_each_entry_safe(port, tmp, &team->port_list, list)
 		team_port_del(team, port->dev);
 
@@ -1674,9 +1679,8 @@ static void team_uninit(struct net_device *dev)
 	team_mcast_rejoin_fini(team);
 	team_notify_peers_fini(team);
 	team_queue_override_fini(team);
-	mutex_unlock(&team->lock);
+	team_unlock(team);
 	netdev_change_features(dev);
-	lockdep_unregister_key(&team->team_lock_key);
 }
 
 static void team_destructor(struct net_device *dev)
@@ -1790,18 +1794,18 @@ static void team_set_rx_mode(struct net_device *dev)
 
 static int team_set_mac_address(struct net_device *dev, void *p)
 {
-	struct sockaddr *addr = p;
 	struct team *team = netdev_priv(dev);
+	struct sockaddr *addr = p;
 	struct team_port *port;
 
 	if (dev->type == ARPHRD_ETHER && !is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 	dev_addr_set(dev, addr->sa_data);
-	mutex_lock(&team->lock);
+	team_lock(team);
 	list_for_each_entry(port, &team->port_list, list)
 		if (team->ops.port_change_dev_addr)
 			team->ops.port_change_dev_addr(team, port);
-	mutex_unlock(&team->lock);
+	team_unlock(team);
 	return 0;
 }
 
@@ -1815,7 +1819,7 @@ static int team_change_mtu(struct net_device *dev, int new_mtu)
 	 * Alhough this is reader, it's guarded by team lock. It's not possible
 	 * to traverse list in reverse under rcu_read_lock
 	 */
-	mutex_lock(&team->lock);
+	team_lock(team);
 	team->port_mtu_change_allowed = true;
 	list_for_each_entry(port, &team->port_list, list) {
 		err = dev_set_mtu(port->dev, new_mtu);
@@ -1826,7 +1830,7 @@ static int team_change_mtu(struct net_device *dev, int new_mtu)
 		}
 	}
 	team->port_mtu_change_allowed = false;
-	mutex_unlock(&team->lock);
+	team_unlock(team);
 
 	dev->mtu = new_mtu;
 
@@ -1836,7 +1840,7 @@ unwind:
 	list_for_each_entry_continue_reverse(port, &team->port_list, list)
 		dev_set_mtu(port->dev, dev->mtu);
 	team->port_mtu_change_allowed = false;
-	mutex_unlock(&team->lock);
+	team_unlock(team);
 
 	return err;
 }
@@ -1890,20 +1894,20 @@ static int team_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid)
 	 * Alhough this is reader, it's guarded by team lock. It's not possible
 	 * to traverse list in reverse under rcu_read_lock
 	 */
-	mutex_lock(&team->lock);
+	team_lock(team);
 	list_for_each_entry(port, &team->port_list, list) {
 		err = vlan_vid_add(port->dev, proto, vid);
 		if (err)
 			goto unwind;
 	}
-	mutex_unlock(&team->lock);
+	team_unlock(team);
 
 	return 0;
 
 unwind:
 	list_for_each_entry_continue_reverse(port, &team->port_list, list)
 		vlan_vid_del(port->dev, proto, vid);
-	mutex_unlock(&team->lock);
+	team_unlock(team);
 
 	return err;
 }
@@ -1913,10 +1917,10 @@ static int team_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid)
 	struct team *team = netdev_priv(dev);
 	struct team_port *port;
 
-	mutex_lock(&team->lock);
+	team_lock(team);
 	list_for_each_entry(port, &team->port_list, list)
 		vlan_vid_del(port->dev, proto, vid);
-	mutex_unlock(&team->lock);
+	team_unlock(team);
 
 	return 0;
 }
@@ -1938,9 +1942,9 @@ static void team_netpoll_cleanup(struct net_device *dev)
 {
 	struct team *team = netdev_priv(dev);
 
-	mutex_lock(&team->lock);
+	team_lock(team);
 	__team_netpoll_cleanup(team);
-	mutex_unlock(&team->lock);
+	team_unlock(team);
 }
 
 static int team_netpoll_setup(struct net_device *dev,
@@ -1950,7 +1954,7 @@ static int team_netpoll_setup(struct net_device *dev,
 	struct team_port *port;
 	int err = 0;
 
-	mutex_lock(&team->lock);
+	team_lock(team);
 	list_for_each_entry(port, &team->port_list, list) {
 		err = __team_port_enable_netpoll(port);
 		if (err) {
@@ -1958,7 +1962,7 @@ static int team_netpoll_setup(struct net_device *dev,
 			break;
 		}
 	}
-	mutex_unlock(&team->lock);
+	team_unlock(team);
 	return err;
 }
 #endif
@@ -1969,9 +1973,9 @@ static int team_add_slave(struct net_device *dev, struct net_device *port_dev,
 	struct team *team = netdev_priv(dev);
 	int err;
 
-	mutex_lock(&team->lock);
+	team_lock(team);
 	err = team_port_add(team, port_dev, extack);
-	mutex_unlock(&team->lock);
+	team_unlock(team);
 
 	if (!err)
 		netdev_change_features(dev);
@@ -1984,19 +1988,12 @@ static int team_del_slave(struct net_device *dev, struct net_device *port_dev)
 	struct team *team = netdev_priv(dev);
 	int err;
 
-	mutex_lock(&team->lock);
+	team_lock(team);
 	err = team_port_del(team, port_dev);
-	mutex_unlock(&team->lock);
+	team_unlock(team);
 
-	if (err)
-		return err;
-
-	if (netif_is_team_master(port_dev)) {
-		lockdep_unregister_key(&team->team_lock_key);
-		lockdep_register_key(&team->team_lock_key);
-		lockdep_set_class(&team->lock, &team->team_lock_key);
-	}
-	netdev_change_features(dev);
+	if (!err)
+		netdev_change_features(dev);
 
 	return err;
 }
@@ -2316,13 +2313,13 @@ static struct team *team_nl_team_get(struct genl_info *info)
 	}
 
 	team = netdev_priv(dev);
-	mutex_lock(&team->lock);
+	__team_lock(team);
 	return team;
 }
 
 static void team_nl_team_put(struct team *team)
 {
-	mutex_unlock(&team->lock);
+	team_unlock(team);
 	dev_put(team->dev);
 }
 
@@ -2984,9 +2981,9 @@ static void team_port_change_check(struct team_port *port, bool linkup)
 {
 	struct team *team = port->team;
 
-	mutex_lock(&team->lock);
+	team_lock(team);
 	__team_port_change_check(port, linkup);
-	mutex_unlock(&team->lock);
+	team_unlock(team);
 }
 
 
diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c
index 00f8989c29c0..7bcc9d37447a 100644
--- a/drivers/net/team/team_mode_loadbalance.c
+++ b/drivers/net/team/team_mode_loadbalance.c
@@ -478,7 +478,7 @@ static void lb_stats_refresh(struct work_struct *work)
 	team = lb_priv_ex->team;
 	lb_priv = get_lb_priv(team);
 
-	if (!mutex_trylock(&team->lock)) {
+	if (!team_trylock(team)) {
 		schedule_delayed_work(&lb_priv_ex->stats.refresh_dw, 0);
 		return;
 	}
@@ -515,7 +515,7 @@ static void lb_stats_refresh(struct work_struct *work)
 	schedule_delayed_work(&lb_priv_ex->stats.refresh_dw,
 			      (lb_priv_ex->stats.refresh_interval * HZ) / 10);
 
-	mutex_unlock(&team->lock);
+	team_unlock(team);
 }
 
 static void lb_stats_refresh_interval_get(struct team *team,
diff --git a/include/linux/if_team.h b/include/linux/if_team.h
index 1b9b15a492fa..12d4447fc8ab 100644
--- a/include/linux/if_team.h
+++ b/include/linux/if_team.h
@@ -221,10 +221,38 @@ struct team {
 		atomic_t count_pending;
 		struct delayed_work dw;
 	} mcast_rejoin;
-	struct lock_class_key team_lock_key;
 	long mode_priv[TEAM_MODE_PRIV_LONGS];
 };
 
+static inline void __team_lock(struct team *team)
+{
+	mutex_lock(&team->lock);
+}
+
+static inline int team_trylock(struct team *team)
+{
+	return mutex_trylock(&team->lock);
+}
+
+#ifdef CONFIG_LOCKDEP
+static inline void team_lock(struct team *team)
+{
+	ASSERT_RTNL();
+	mutex_lock_nested(&team->lock, team->dev->nested_level);
+}
+
+#else
+static inline void team_lock(struct team *team)
+{
+	__team_lock(team);
+}
+#endif
+
+static inline void team_unlock(struct team *team)
+{
+	mutex_unlock(&team->lock);
+}
+
 static inline int team_dev_queue_xmit(struct team *team, struct team_port *port,
 				      struct sk_buff *skb)
 {

From 9b271ebaf9a2c5c566a54bc6cd915962e8241130 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 5 Sep 2023 13:40:46 +0000
Subject: [PATCH 1091/1189] ip_tunnels: use DEV_STATS_INC()

syzbot/KCSAN reported data-races in iptunnel_xmit_stats() [1]

This can run from multiple cpus without mutual exclusion.

Adopt SMP safe DEV_STATS_INC() to update dev->stats fields.

[1]
BUG: KCSAN: data-race in iptunnel_xmit / iptunnel_xmit

read-write to 0xffff8881353df170 of 8 bytes by task 30263 on cpu 1:
iptunnel_xmit_stats include/net/ip_tunnels.h:493 [inline]
iptunnel_xmit+0x432/0x4a0 net/ipv4/ip_tunnel_core.c:87
ip_tunnel_xmit+0x1477/0x1750 net/ipv4/ip_tunnel.c:831
__gre_xmit net/ipv4/ip_gre.c:469 [inline]
ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:662
__netdev_start_xmit include/linux/netdevice.h:4889 [inline]
netdev_start_xmit include/linux/netdevice.h:4903 [inline]
xmit_one net/core/dev.c:3544 [inline]
dev_hard_start_xmit+0x11b/0x3f0 net/core/dev.c:3560
__dev_queue_xmit+0xeee/0x1de0 net/core/dev.c:4340
dev_queue_xmit include/linux/netdevice.h:3082 [inline]
__bpf_tx_skb net/core/filter.c:2129 [inline]
__bpf_redirect_no_mac net/core/filter.c:2159 [inline]
__bpf_redirect+0x723/0x9c0 net/core/filter.c:2182
____bpf_clone_redirect net/core/filter.c:2453 [inline]
bpf_clone_redirect+0x16c/0x1d0 net/core/filter.c:2425
___bpf_prog_run+0xd7d/0x41e0 kernel/bpf/core.c:1954
__bpf_prog_run512+0x74/0xa0 kernel/bpf/core.c:2195
bpf_dispatcher_nop_func include/linux/bpf.h:1181 [inline]
__bpf_prog_run include/linux/filter.h:609 [inline]
bpf_prog_run include/linux/filter.h:616 [inline]
bpf_test_run+0x15d/0x3d0 net/bpf/test_run.c:423
bpf_prog_test_run_skb+0x77b/0xa00 net/bpf/test_run.c:1045
bpf_prog_test_run+0x265/0x3d0 kernel/bpf/syscall.c:3996
__sys_bpf+0x3af/0x780 kernel/bpf/syscall.c:5353
__do_sys_bpf kernel/bpf/syscall.c:5439 [inline]
__se_sys_bpf kernel/bpf/syscall.c:5437 [inline]
__x64_sys_bpf+0x43/0x50 kernel/bpf/syscall.c:5437
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd

read-write to 0xffff8881353df170 of 8 bytes by task 30249 on cpu 0:
iptunnel_xmit_stats include/net/ip_tunnels.h:493 [inline]
iptunnel_xmit+0x432/0x4a0 net/ipv4/ip_tunnel_core.c:87
ip_tunnel_xmit+0x1477/0x1750 net/ipv4/ip_tunnel.c:831
__gre_xmit net/ipv4/ip_gre.c:469 [inline]
ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:662
__netdev_start_xmit include/linux/netdevice.h:4889 [inline]
netdev_start_xmit include/linux/netdevice.h:4903 [inline]
xmit_one net/core/dev.c:3544 [inline]
dev_hard_start_xmit+0x11b/0x3f0 net/core/dev.c:3560
__dev_queue_xmit+0xeee/0x1de0 net/core/dev.c:4340
dev_queue_xmit include/linux/netdevice.h:3082 [inline]
__bpf_tx_skb net/core/filter.c:2129 [inline]
__bpf_redirect_no_mac net/core/filter.c:2159 [inline]
__bpf_redirect+0x723/0x9c0 net/core/filter.c:2182
____bpf_clone_redirect net/core/filter.c:2453 [inline]
bpf_clone_redirect+0x16c/0x1d0 net/core/filter.c:2425
___bpf_prog_run+0xd7d/0x41e0 kernel/bpf/core.c:1954
__bpf_prog_run512+0x74/0xa0 kernel/bpf/core.c:2195
bpf_dispatcher_nop_func include/linux/bpf.h:1181 [inline]
__bpf_prog_run include/linux/filter.h:609 [inline]
bpf_prog_run include/linux/filter.h:616 [inline]
bpf_test_run+0x15d/0x3d0 net/bpf/test_run.c:423
bpf_prog_test_run_skb+0x77b/0xa00 net/bpf/test_run.c:1045
bpf_prog_test_run+0x265/0x3d0 kernel/bpf/syscall.c:3996
__sys_bpf+0x3af/0x780 kernel/bpf/syscall.c:5353
__do_sys_bpf kernel/bpf/syscall.c:5439 [inline]
__se_sys_bpf kernel/bpf/syscall.c:5437 [inline]
__x64_sys_bpf+0x43/0x50 kernel/bpf/syscall.c:5437
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd

value changed: 0x0000000000018830 -> 0x0000000000018831

Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 30249 Comm: syz-executor.4 Not tainted 6.5.0-syzkaller-11704-g3f86ed6ec0b3 #0

Fixes: 039f50629b7f ("ip_tunnel: Move stats update to iptunnel_xmit()")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_tunnels.h | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index e8750b4ef7e1..f346b4efbc30 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -483,15 +483,14 @@ static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len)
 		u64_stats_inc(&tstats->tx_packets);
 		u64_stats_update_end(&tstats->syncp);
 		put_cpu_ptr(tstats);
-	} else {
-		struct net_device_stats *err_stats = &dev->stats;
+		return;
+	}
 
-		if (pkt_len < 0) {
-			err_stats->tx_errors++;
-			err_stats->tx_aborted_errors++;
-		} else {
-			err_stats->tx_dropped++;
-		}
+	if (pkt_len < 0) {
+		DEV_STATS_INC(dev, tx_errors);
+		DEV_STATS_INC(dev, tx_aborted_errors);
+	} else {
+		DEV_STATS_INC(dev, tx_dropped);
 	}
 }
 

From b7558a77529fef60e7992f40fb5353fed8be0cf8 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Tue, 5 Sep 2023 10:48:45 -0700
Subject: [PATCH 1092/1189] net/mlx5e: Clear mirred devices array if the rule
 is split

In the cited commit, the mirred devices are recorded and checked while
parsing the actions. In order to avoid system crash, the duplicate
action in a single rule is not allowed.

But the rule is actually break down into several FTEs in different
tables, for either mirroring, or the specified types of actions which
use post action infrastructure.

It will reject certain action list by mistake, for example:
    actions:enp8s0f0_1,set(ipv4(ttl=63)),enp8s0f0_0,enp8s0f0_1.
Here the rule is split to two FTEs because of pedit action.

To fix this issue, when parsing the rule actions, reset if_count to
clear the mirred devices array if the rule is split to multiple
FTEs, and then the duplicate checking is restarted.

Fixes: 554fe75c1b3f ("net/mlx5e: Avoid duplicating rule destinations")
Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c        | 4 +++-
 drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c    | 1 +
 drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c     | 4 +++-
 .../ethernet/mellanox/mlx5/core/en/tc/act/redirect_ingress.c  | 1 +
 drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c      | 1 +
 .../net/ethernet/mellanox/mlx5/core/en/tc/act/vlan_mangle.c   | 4 +++-
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c               | 1 +
 7 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c
index 92d3952dfa8b..feeb41693c17 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c
@@ -17,8 +17,10 @@ tc_act_parse_ct(struct mlx5e_tc_act_parse_state *parse_state,
 	if (err)
 		return err;
 
-	if (mlx5e_is_eswitch_flow(parse_state->flow))
+	if (mlx5e_is_eswitch_flow(parse_state->flow)) {
 		attr->esw_attr->split_count = attr->esw_attr->out_count;
+		parse_state->if_count = 0;
+	}
 
 	attr->flags |= MLX5_ATTR_FLAG_CT;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c
index 291193f7120d..f63402c48028 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c
@@ -294,6 +294,7 @@ parse_mirred_ovs_master(struct mlx5e_tc_act_parse_state *parse_state,
 	if (err)
 		return err;
 
+	parse_state->if_count = 0;
 	esw_attr->out_count++;
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c
index 3b272bbf4c53..368a95fa77d3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c
@@ -98,8 +98,10 @@ tc_act_parse_pedit(struct mlx5e_tc_act_parse_state *parse_state,
 
 	attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
 
-	if (ns_type == MLX5_FLOW_NAMESPACE_FDB)
+	if (ns_type == MLX5_FLOW_NAMESPACE_FDB) {
 		esw_attr->split_count = esw_attr->out_count;
+		parse_state->if_count = 0;
+	}
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/redirect_ingress.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/redirect_ingress.c
index ad09a8a5f36e..2d1d4a04501b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/redirect_ingress.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/redirect_ingress.c
@@ -66,6 +66,7 @@ tc_act_parse_redirect_ingress(struct mlx5e_tc_act_parse_state *parse_state,
 	if (err)
 		return err;
 
+	parse_state->if_count = 0;
 	esw_attr->out_count++;
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c
index c8a3eaf189f6..a13c5e707b83 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c
@@ -166,6 +166,7 @@ tc_act_parse_vlan(struct mlx5e_tc_act_parse_state *parse_state,
 		return err;
 
 	esw_attr->split_count = esw_attr->out_count;
+	parse_state->if_count = 0;
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan_mangle.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan_mangle.c
index 310b99230760..f17575b09788 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan_mangle.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan_mangle.c
@@ -65,8 +65,10 @@ tc_act_parse_vlan_mangle(struct mlx5e_tc_act_parse_state *parse_state,
 	if (err)
 		return err;
 
-	if (ns_type == MLX5_FLOW_NAMESPACE_FDB)
+	if (ns_type == MLX5_FLOW_NAMESPACE_FDB) {
 		attr->esw_attr->split_count = attr->esw_attr->out_count;
+		parse_state->if_count = 0;
+	}
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 318083690fcd..c24828b688ac 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -3936,6 +3936,7 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state,
 			}
 
 			i_split = i + 1;
+			parse_state->if_count = 0;
 			list_add(&attr->list, &flow->attrs);
 		}
 

From 344134609a564f28b3cc81ca6650319ccd5d8961 Mon Sep 17 00:00:00 2001
From: Bodong Wang <bodong@nvidia.com>
Date: Tue, 5 Sep 2023 10:48:46 -0700
Subject: [PATCH 1093/1189] mlx5/core: E-Switch, Create ACL FT for eswitch
 manager in switchdev mode

ACL flow table is required in switchdev mode when metadata is enabled,
driver creates such table when loading each vport. However, not every
vport is loaded in switchdev mode. Such as ECPF if it's the eswitch manager.
In this case, ACL flow table is still needed.

To make it modularized, create ACL flow table for eswitch manager as
default and skip such operations when loading manager vport.

Also, there is no need to load the eswitch manager vport in switchdev mode.
This means there is no need to load it on regular connect-x HCAs where
the PF is the eswitch manager. This will avoid creating duplicate ACL
flow table for host PF vport.

Fixes: 29bcb6e4fe70 ("net/mlx5e: E-Switch, Use metadata for vport matching in send-to-vport rules")
Fixes: eb8e9fae0a22 ("mlx5/core: E-Switch, Allocate ECPF vport if it's an eswitch manager")
Fixes: 5019833d661f ("net/mlx5: E-switch, Introduce helper function to enable/disable vports")
Signed-off-by: Bodong Wang <bodong@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlx5/core/eswitch.c | 21 ++++++--
 .../mellanox/mlx5/core/eswitch_offloads.c     | 49 +++++++++++++------
 2 files changed, 51 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 6cd7d6497e10..d4cde6555063 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1276,12 +1276,19 @@ int
 mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw,
 				 enum mlx5_eswitch_vport_event enabled_events)
 {
+	bool pf_needed;
 	int ret;
 
+	pf_needed = mlx5_core_is_ecpf_esw_manager(esw->dev) ||
+		    esw->mode == MLX5_ESWITCH_LEGACY;
+
 	/* Enable PF vport */
-	ret = mlx5_eswitch_load_pf_vf_vport(esw, MLX5_VPORT_PF, enabled_events);
-	if (ret)
-		return ret;
+	if (pf_needed) {
+		ret = mlx5_eswitch_load_pf_vf_vport(esw, MLX5_VPORT_PF,
+						    enabled_events);
+		if (ret)
+			return ret;
+	}
 
 	/* Enable external host PF HCA */
 	ret = host_pf_enable_hca(esw->dev);
@@ -1317,7 +1324,8 @@ ec_vf_err:
 ecpf_err:
 	host_pf_disable_hca(esw->dev);
 pf_hca_err:
-	mlx5_eswitch_unload_pf_vf_vport(esw, MLX5_VPORT_PF);
+	if (pf_needed)
+		mlx5_eswitch_unload_pf_vf_vport(esw, MLX5_VPORT_PF);
 	return ret;
 }
 
@@ -1335,7 +1343,10 @@ void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw)
 	}
 
 	host_pf_disable_hca(esw->dev);
-	mlx5_eswitch_unload_pf_vf_vport(esw, MLX5_VPORT_PF);
+
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev) ||
+	    esw->mode == MLX5_ESWITCH_LEGACY)
+		mlx5_eswitch_unload_pf_vf_vport(esw, MLX5_VPORT_PF);
 }
 
 static void mlx5_eswitch_get_devlink_param(struct mlx5_eswitch *esw)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 752fb0dfb111..b296ac52a439 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -3216,26 +3216,47 @@ esw_vport_destroy_offloads_acl_tables(struct mlx5_eswitch *esw,
 	esw_acl_ingress_ofld_cleanup(esw, vport);
 }
 
-static int esw_create_uplink_offloads_acl_tables(struct mlx5_eswitch *esw)
+static int esw_create_offloads_acl_tables(struct mlx5_eswitch *esw)
 {
-	struct mlx5_vport *vport;
+	struct mlx5_vport *uplink, *manager;
+	int ret;
 
-	vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK);
-	if (IS_ERR(vport))
-		return PTR_ERR(vport);
+	uplink = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK);
+	if (IS_ERR(uplink))
+		return PTR_ERR(uplink);
 
-	return esw_vport_create_offloads_acl_tables(esw, vport);
+	ret = esw_vport_create_offloads_acl_tables(esw, uplink);
+	if (ret)
+		return ret;
+
+	manager = mlx5_eswitch_get_vport(esw, esw->manager_vport);
+	if (IS_ERR(manager)) {
+		ret = PTR_ERR(manager);
+		goto err_manager;
+	}
+
+	ret = esw_vport_create_offloads_acl_tables(esw, manager);
+	if (ret)
+		goto err_manager;
+
+	return 0;
+
+err_manager:
+	esw_vport_destroy_offloads_acl_tables(esw, uplink);
+	return ret;
 }
 
-static void esw_destroy_uplink_offloads_acl_tables(struct mlx5_eswitch *esw)
+static void esw_destroy_offloads_acl_tables(struct mlx5_eswitch *esw)
 {
 	struct mlx5_vport *vport;
 
-	vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK);
-	if (IS_ERR(vport))
-		return;
+	vport = mlx5_eswitch_get_vport(esw, esw->manager_vport);
+	if (!IS_ERR(vport))
+		esw_vport_destroy_offloads_acl_tables(esw, vport);
 
-	esw_vport_destroy_offloads_acl_tables(esw, vport);
+	vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK);
+	if (!IS_ERR(vport))
+		esw_vport_destroy_offloads_acl_tables(esw, vport);
 }
 
 int mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw)
@@ -3280,7 +3301,7 @@ static int esw_offloads_steering_init(struct mlx5_eswitch *esw)
 	}
 	esw->fdb_table.offloads.indir = indir;
 
-	err = esw_create_uplink_offloads_acl_tables(esw);
+	err = esw_create_offloads_acl_tables(esw);
 	if (err)
 		goto create_acl_err;
 
@@ -3321,7 +3342,7 @@ create_fdb_err:
 create_restore_err:
 	esw_destroy_offloads_table(esw);
 create_offloads_err:
-	esw_destroy_uplink_offloads_acl_tables(esw);
+	esw_destroy_offloads_acl_tables(esw);
 create_acl_err:
 	mlx5_esw_indir_table_destroy(esw->fdb_table.offloads.indir);
 create_indir_err:
@@ -3337,7 +3358,7 @@ static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw)
 	esw_destroy_offloads_fdb_tables(esw);
 	esw_destroy_restore_table(esw);
 	esw_destroy_offloads_table(esw);
-	esw_destroy_uplink_offloads_acl_tables(esw);
+	esw_destroy_offloads_acl_tables(esw);
 	mlx5_esw_indir_table_destroy(esw->fdb_table.offloads.indir);
 	mutex_destroy(&esw->fdb_table.offloads.vports.lock);
 }

From 954ad9bf13c4f95a4958b5f8433301f2ab99e1f5 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Wed, 6 Sep 2023 00:53:36 +0300
Subject: [PATCH 1094/1189] net: dsa: sja1105: fix bandwidth discrepancy
 between tc-cbs software and offload

More careful measurement of the tc-cbs bandwidth shows that the stream
bandwidth (effectively idleslope) increases, there is a larger and
larger discrepancy between the rate limit obtained by the software
Qdisc, and the rate limit obtained by its offloaded counterpart.

The discrepancy becomes so large, that e.g. at an idleslope of 40000
(40Mbps), the offloaded cbs does not actually rate limit anything, and
traffic will pass at line rate through a 100 Mbps port.

The reason for the discrepancy is that the hardware documentation I've
been following is incorrect. UM11040.pdf (for SJA1105P/Q/R/S) states
about IDLE_SLOPE that it is "the rate (in unit of bytes/sec) at which
the credit counter is increased".

Cross-checking with UM10944.pdf (for SJA1105E/T) and UM11107.pdf
(for SJA1110), the wording is different: "This field specifies the
value, in bytes per second times link speed, by which the credit counter
is increased".

So there's an extra scaling for link speed that the driver is currently
not accounting for, and apparently (empirically), that link speed is
expressed in Kbps.

I've pondered whether to pollute the sja1105_mac_link_up()
implementation with CBS shaper reprogramming, but I don't think it is
worth it. IMO, the UAPI exposed by tc-cbs requires user space to
recalculate the sendslope anyway, since the formula for that depends on
port_transmit_rate (see man tc-cbs), which is not an invariant from tc's
perspective.

So we use the offload->sendslope and offload->idleslope to deduce the
original port_transmit_rate from the CBS formula, and use that value to
scale the offload->sendslope and offload->idleslope to values that the
hardware understands.

Some numerical data points:

 40Mbps stream, max interfering frame size 1500, port speed 100M
 ---------------------------------------------------------------

 tc-cbs parameters:
 idleslope 40000 sendslope -60000 locredit -900 hicredit 600

 which result in hardware values:

 Before (doesn't work)           After (works)
 credit_hi    600                600
 credit_lo    900                900
 send_slope   7500000            75
 idle_slope   5000000            50

 40Mbps stream, max interfering frame size 1500, port speed 1G
 -------------------------------------------------------------

 tc-cbs parameters:
 idleslope 40000 sendslope -960000 locredit -1440 hicredit 60

 which result in hardware values:

 Before (doesn't work)           After (works)
 credit_hi    60                 60
 credit_lo    1440               1440
 send_slope   120000000          120
 idle_slope   5000000            5

 5.12Mbps stream, max interfering frame size 1522, port speed 100M
 -----------------------------------------------------------------

 tc-cbs parameters:
 idleslope 5120 sendslope -94880 locredit -1444 hicredit 77

 which result in hardware values:

 Before (doesn't work)           After (works)
 credit_hi    77                 77
 credit_lo    1444               1444
 send_slope   11860000           118
 idle_slope   640000             6

Tested on SJA1105T, SJA1105S and SJA1110A, at 1Gbps and 100Mbps.

Fixes: 4d7525085a9b ("net: dsa: sja1105: offload the Credit-Based Shaper qdisc")
Reported-by: Yanan Yang <yanan.yang@nxp.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105_main.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 331bb1c6676a..3f17c17ff636 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -2150,6 +2150,7 @@ static int sja1105_setup_tc_cbs(struct dsa_switch *ds, int port,
 {
 	struct sja1105_private *priv = ds->priv;
 	struct sja1105_cbs_entry *cbs;
+	s64 port_transmit_rate_kbps;
 	int index;
 
 	if (!offload->enable)
@@ -2167,9 +2168,17 @@ static int sja1105_setup_tc_cbs(struct dsa_switch *ds, int port,
 	 */
 	cbs->credit_hi = offload->hicredit;
 	cbs->credit_lo = abs(offload->locredit);
-	/* User space is in kbits/sec, hardware in bytes/sec */
-	cbs->idle_slope = offload->idleslope * BYTES_PER_KBIT;
-	cbs->send_slope = abs(offload->sendslope * BYTES_PER_KBIT);
+	/* User space is in kbits/sec, while the hardware in bytes/sec times
+	 * link speed. Since the given offload->sendslope is good only for the
+	 * current link speed anyway, and user space is likely to reprogram it
+	 * when that changes, don't even bother to track the port's link speed,
+	 * but deduce the port transmit rate from idleslope - sendslope.
+	 */
+	port_transmit_rate_kbps = offload->idleslope - offload->sendslope;
+	cbs->idle_slope = div_s64(offload->idleslope * BYTES_PER_KBIT,
+				  port_transmit_rate_kbps);
+	cbs->send_slope = div_s64(abs(offload->sendslope * BYTES_PER_KBIT),
+				  port_transmit_rate_kbps);
 	/* Convert the negative values from 64-bit 2's complement
 	 * to 32-bit 2's complement (for the case of 0x80000000 whose
 	 * negative is still negative).

From 894cafc5c62ccced758077bd4e970dc714c42637 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Wed, 6 Sep 2023 00:53:37 +0300
Subject: [PATCH 1095/1189] net: dsa: sja1105: fix -ENOSPC when replacing the
 same tc-cbs too many times

After running command [2] too many times in a row:

[1] $ tc qdisc add dev sw2p0 root handle 1: mqprio num_tc 8 \
	map 0 1 2 3 4 5 6 7 queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 hw 0
[2] $ tc qdisc replace dev sw2p0 parent 1:1 cbs offload 1 \
	idleslope 120000 sendslope -880000 locredit -1320 hicredit 180

(aka more than priv->info->num_cbs_shapers times)

we start seeing the following error message:

Error: Specified device failed to setup cbs hardware offload.

This comes from the fact that ndo_setup_tc(TC_SETUP_QDISC_CBS) presents
the same API for the qdisc create and replace cases, and the sja1105
driver fails to distinguish between the 2. Thus, it always thinks that
it must allocate the same shaper for a {port, queue} pair, when it may
instead have to replace an existing one.

Fixes: 4d7525085a9b ("net: dsa: sja1105: offload the Credit-Based Shaper qdisc")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105_main.c | 23 ++++++++++++++++++++---
 1 file changed, 20 insertions(+), 3 deletions(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 3f17c17ff636..d7f57f223031 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -2116,6 +2116,18 @@ static void sja1105_bridge_leave(struct dsa_switch *ds, int port,
 
 #define BYTES_PER_KBIT (1000LL / 8)
 
+static int sja1105_find_cbs_shaper(struct sja1105_private *priv,
+				   int port, int prio)
+{
+	int i;
+
+	for (i = 0; i < priv->info->num_cbs_shapers; i++)
+		if (priv->cbs[i].port == port && priv->cbs[i].prio == prio)
+			return i;
+
+	return -1;
+}
+
 static int sja1105_find_unused_cbs_shaper(struct sja1105_private *priv)
 {
 	int i;
@@ -2156,9 +2168,14 @@ static int sja1105_setup_tc_cbs(struct dsa_switch *ds, int port,
 	if (!offload->enable)
 		return sja1105_delete_cbs_shaper(priv, port, offload->queue);
 
-	index = sja1105_find_unused_cbs_shaper(priv);
-	if (index < 0)
-		return -ENOSPC;
+	/* The user may be replacing an existing shaper */
+	index = sja1105_find_cbs_shaper(priv, port, offload->queue);
+	if (index < 0) {
+		/* That isn't the case - see if we can allocate a new one */
+		index = sja1105_find_unused_cbs_shaper(priv);
+		if (index < 0)
+			return -ENOSPC;
+	}
 
 	cbs = &priv->cbs[index];
 	cbs->port = port;

From 180a7419fe4adc8d9c8e0ef0fd17bcdd0cf78acd Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Wed, 6 Sep 2023 00:53:38 +0300
Subject: [PATCH 1096/1189] net: dsa: sja1105: complete tc-cbs offload support
 on SJA1110

The blamed commit left this delta behind:

  struct sja1105_cbs_entry {
 -	u64 port;
 -	u64 prio;
 +	u64 port; /* Not used for SJA1110 */
 +	u64 prio; /* Not used for SJA1110 */
  	u64 credit_hi;
  	u64 credit_lo;
  	u64 send_slope;
  	u64 idle_slope;
  };

but did not actually implement tc-cbs offload fully for the new switch.
The offload is accepted, but it doesn't work.

The difference compared to earlier switch generations is that now, the
table of CBS shapers is sparse, because there are many more shapers, so
the mapping between a {port, prio} and a table index is static, rather
than requiring us to store the port and prio into the sja1105_cbs_entry.

So, the problem is that the code programs the CBS shaper parameters at a
dynamic table index which is incorrect.

All that needs to be done for SJA1110 CBS shapers to work is to bypass
the logic which allocates shapers in a dense manner, as for SJA1105, and
use the fixed mapping instead.

Fixes: 3e77e59bf8cf ("net: dsa: sja1105: add support for the SJA1110 switch family")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105.h      |  2 ++
 drivers/net/dsa/sja1105/sja1105_main.c | 13 +++++++++++++
 drivers/net/dsa/sja1105/sja1105_spi.c  |  4 ++++
 3 files changed, 19 insertions(+)

diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h
index dee35ba924ad..0617d5ccd3ff 100644
--- a/drivers/net/dsa/sja1105/sja1105.h
+++ b/drivers/net/dsa/sja1105/sja1105.h
@@ -132,6 +132,8 @@ struct sja1105_info {
 	int max_frame_mem;
 	int num_ports;
 	bool multiple_cascade_ports;
+	/* Every {port, TXQ} has its own CBS shaper */
+	bool fixed_cbs_mapping;
 	enum dsa_tag_protocol tag_proto;
 	const struct sja1105_dynamic_table_ops *dyn_ops;
 	const struct sja1105_table_ops *static_ops;
diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index d7f57f223031..a23d980d28f5 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -2115,12 +2115,22 @@ static void sja1105_bridge_leave(struct dsa_switch *ds, int port,
 }
 
 #define BYTES_PER_KBIT (1000LL / 8)
+/* Port 0 (the uC port) does not have CBS shapers */
+#define SJA1110_FIXED_CBS(port, prio) ((((port) - 1) * SJA1105_NUM_TC) + (prio))
 
 static int sja1105_find_cbs_shaper(struct sja1105_private *priv,
 				   int port, int prio)
 {
 	int i;
 
+	if (priv->info->fixed_cbs_mapping) {
+		i = SJA1110_FIXED_CBS(port, prio);
+		if (i >= 0 && i < priv->info->num_cbs_shapers)
+			return i;
+
+		return -1;
+	}
+
 	for (i = 0; i < priv->info->num_cbs_shapers; i++)
 		if (priv->cbs[i].port == port && priv->cbs[i].prio == prio)
 			return i;
@@ -2132,6 +2142,9 @@ static int sja1105_find_unused_cbs_shaper(struct sja1105_private *priv)
 {
 	int i;
 
+	if (priv->info->fixed_cbs_mapping)
+		return -1;
+
 	for (i = 0; i < priv->info->num_cbs_shapers; i++)
 		if (!priv->cbs[i].idle_slope && !priv->cbs[i].send_slope)
 			return i;
diff --git a/drivers/net/dsa/sja1105/sja1105_spi.c b/drivers/net/dsa/sja1105/sja1105_spi.c
index 5ce29c8057a4..834b5c1b4db0 100644
--- a/drivers/net/dsa/sja1105/sja1105_spi.c
+++ b/drivers/net/dsa/sja1105/sja1105_spi.c
@@ -781,6 +781,7 @@ const struct sja1105_info sja1110a_info = {
 	.tag_proto		= DSA_TAG_PROTO_SJA1110,
 	.can_limit_mcast_flood	= true,
 	.multiple_cascade_ports	= true,
+	.fixed_cbs_mapping	= true,
 	.ptp_ts_bits		= 32,
 	.ptpegr_ts_bytes	= 8,
 	.max_frame_mem		= SJA1110_MAX_FRAME_MEMORY,
@@ -831,6 +832,7 @@ const struct sja1105_info sja1110b_info = {
 	.tag_proto		= DSA_TAG_PROTO_SJA1110,
 	.can_limit_mcast_flood	= true,
 	.multiple_cascade_ports	= true,
+	.fixed_cbs_mapping	= true,
 	.ptp_ts_bits		= 32,
 	.ptpegr_ts_bytes	= 8,
 	.max_frame_mem		= SJA1110_MAX_FRAME_MEMORY,
@@ -881,6 +883,7 @@ const struct sja1105_info sja1110c_info = {
 	.tag_proto		= DSA_TAG_PROTO_SJA1110,
 	.can_limit_mcast_flood	= true,
 	.multiple_cascade_ports	= true,
+	.fixed_cbs_mapping	= true,
 	.ptp_ts_bits		= 32,
 	.ptpegr_ts_bytes	= 8,
 	.max_frame_mem		= SJA1110_MAX_FRAME_MEMORY,
@@ -931,6 +934,7 @@ const struct sja1105_info sja1110d_info = {
 	.tag_proto		= DSA_TAG_PROTO_SJA1110,
 	.can_limit_mcast_flood	= true,
 	.multiple_cascade_ports	= true,
+	.fixed_cbs_mapping	= true,
 	.ptp_ts_bits		= 32,
 	.ptpegr_ts_bytes	= 8,
 	.max_frame_mem		= SJA1110_MAX_FRAME_MEMORY,

From 1a961e74d5abbea049588a3d74b759955b4ed9d5 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 5 Sep 2023 16:42:02 -0700
Subject: [PATCH 1097/1189] net: phylink: fix sphinx complaint about invalid
 literal

sphinx complains about the use of "%PHYLINK_PCS_NEG_*":

Documentation/networking/kapi:144: ./include/linux/phylink.h:601: WARNING: Inline literal start-string without end-string.
Documentation/networking/kapi:144: ./include/linux/phylink.h:633: WARNING: Inline literal start-string without end-string.

These are not valid symbols so drop the '%' prefix.

Alternatively we could use %PHYLINK_PCS_NEG_\* (escape the *)
or use normal literal ``PHYLINK_PCS_NEG_*`` but there is already
a handful of un-adorned DEFINE_* in this file.

Fixes: f99d471afa03 ("net: phylink: add PCS negotiation mode")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Link: https://lore.kernel.org/all/20230626162908.2f149f98@canb.auug.org.au/
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Bagas Sanjaya <bagasdotme@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/phylink.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index 7d07f8736431..2b886ea654bb 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -600,7 +600,7 @@ void pcs_get_state(struct phylink_pcs *pcs,
  *
  * The %neg_mode argument should be tested via the phylink_mode_*() family of
  * functions, or for PCS that set pcs->neg_mode true, should be tested
- * against the %PHYLINK_PCS_NEG_* definitions.
+ * against the PHYLINK_PCS_NEG_* definitions.
  */
 int pcs_config(struct phylink_pcs *pcs, unsigned int neg_mode,
 	       phy_interface_t interface, const unsigned long *advertising,
@@ -630,7 +630,7 @@ void pcs_an_restart(struct phylink_pcs *pcs);
  *
  * The %mode argument should be tested via the phylink_mode_*() family of
  * functions, or for PCS that set pcs->neg_mode true, should be tested
- * against the %PHYLINK_PCS_NEG_* definitions.
+ * against the PHYLINK_PCS_NEG_* definitions.
  */
 void pcs_link_up(struct phylink_pcs *pcs, unsigned int neg_mode,
 		 phy_interface_t interface, int speed, int duplex);

From 7645629f7dc88cd777f98970134bf1a54c8d77e3 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Wed, 30 Aug 2023 10:04:04 +0200
Subject: [PATCH 1098/1189] bpf: Invoke __bpf_prog_exit_sleepable_recur() on
 recursion in kern_sys_bpf().

If __bpf_prog_enter_sleepable_recur() detects recursion then it returns
0 without undoing rcu_read_lock_trace(), migrate_disable() or
decrementing the recursion counter. This is fine in the JIT case because
the JIT code will jump in the 0 case to the end and invoke the matching
exit trampoline (__bpf_prog_exit_sleepable_recur()).

This is not the case in kern_sys_bpf() which returns directly to the
caller with an error code.

Add __bpf_prog_exit_sleepable_recur() as clean up in the recursion case.

Fixes: b1d18a7574d0d ("bpf: Extend sys_bpf commands for bpf_syscall programs.")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/bpf/20230830080405.251926-2-bigeasy@linutronix.de
---
 kernel/bpf/syscall.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ebeb0695305a..53a0b62464e9 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -5505,6 +5505,7 @@ int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size)
 		run_ctx.saved_run_ctx = NULL;
 		if (!__bpf_prog_enter_sleepable_recur(prog, &run_ctx)) {
 			/* recursion detected */
+			__bpf_prog_exit_sleepable_recur(prog, 0, &run_ctx);
 			bpf_prog_put(prog);
 			return -EBUSY;
 		}

From 6764e767f4af1e35f87f3497e1182d945de37f93 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Wed, 30 Aug 2023 10:04:05 +0200
Subject: [PATCH 1099/1189] bpf: Assign bpf_tramp_run_ctx::saved_run_ctx before
 recursion check.

__bpf_prog_enter_recur() assigns bpf_tramp_run_ctx::saved_run_ctx before
performing the recursion check which means in case of a recursion
__bpf_prog_exit_recur() uses the previously set bpf_tramp_run_ctx::saved_run_ctx
value.

__bpf_prog_enter_sleepable_recur() assigns bpf_tramp_run_ctx::saved_run_ctx
after the recursion check which means in case of a recursion
__bpf_prog_exit_sleepable_recur() uses an uninitialized value. This does not
look right. If I read the entry trampoline code right, then bpf_tramp_run_ctx
isn't initialized upfront.

Align __bpf_prog_enter_sleepable_recur() with __bpf_prog_enter_recur() and
set bpf_tramp_run_ctx::saved_run_ctx before the recursion check is made.
Remove the assignment of saved_run_ctx in kern_sys_bpf() since it happens
a few cycles later.

Fixes: e384c7b7b46d0 ("bpf, x86: Create bpf_tramp_run_ctx on the caller thread's stack")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/bpf/20230830080405.251926-3-bigeasy@linutronix.de
---
 kernel/bpf/syscall.c    | 1 -
 kernel/bpf/trampoline.c | 5 ++---
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 53a0b62464e9..eb01c31ed591 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -5502,7 +5502,6 @@ int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size)
 		}
 
 		run_ctx.bpf_cookie = 0;
-		run_ctx.saved_run_ctx = NULL;
 		if (!__bpf_prog_enter_sleepable_recur(prog, &run_ctx)) {
 			/* recursion detected */
 			__bpf_prog_exit_sleepable_recur(prog, 0, &run_ctx);
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 78acf28d4873..53ff50cac61e 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -926,13 +926,12 @@ u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog,
 	migrate_disable();
 	might_fault();
 
+	run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);
+
 	if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) {
 		bpf_prog_inc_misses_counter(prog);
 		return 0;
 	}
-
-	run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);
-
 	return bpf_prog_start_time();
 }
 

From a192103a11465e9d517975c50f9944dc80e44d61 Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Wed, 6 Sep 2023 02:44:19 +0200
Subject: [PATCH 1100/1189] s390/bpf: Pass through tail call counter in
 trampolines

s390x eBPF programs use the following extension to the s390x calling
convention: tail call counter is passed on stack at offset
STK_OFF_TCCNT, which callees otherwise use as scratch space.

Currently trampoline does not respect this and clobbers tail call
counter. This breaks enforcing tail call limits in eBPF programs, which
have trampolines attached to them.

Fix by forwarding a copy of the tail call counter to the original eBPF
program in the trampoline (for fexit), and by restoring it at the end
of the trampoline (for fentry).

Fixes: 528eb2cb87bc ("s390/bpf: Implement arch_prepare_bpf_trampoline()")
Reported-by: Leon Hwang <hffilwlqm@gmail.com>
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20230906004448.111674-1-iii@linux.ibm.com
---
 arch/s390/net/bpf_jit_comp.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 5e9371fbf3d5..de2fb12120d2 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -2088,6 +2088,7 @@ struct bpf_tramp_jit {
 				 */
 	int r14_off;		/* Offset of saved %r14 */
 	int run_ctx_off;	/* Offset of struct bpf_tramp_run_ctx */
+	int tccnt_off;		/* Offset of saved tailcall counter */
 	int do_fexit;		/* do_fexit: label */
 };
 
@@ -2258,12 +2259,16 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 	tjit->r14_off = alloc_stack(tjit, sizeof(u64));
 	tjit->run_ctx_off = alloc_stack(tjit,
 					sizeof(struct bpf_tramp_run_ctx));
+	tjit->tccnt_off = alloc_stack(tjit, sizeof(u64));
 	/* The caller has already reserved STACK_FRAME_OVERHEAD bytes. */
 	tjit->stack_size -= STACK_FRAME_OVERHEAD;
 	tjit->orig_stack_args_off = tjit->stack_size + STACK_FRAME_OVERHEAD;
 
 	/* aghi %r15,-stack_size */
 	EMIT4_IMM(0xa70b0000, REG_15, -tjit->stack_size);
+	/* mvc tccnt_off(4,%r15),stack_size+STK_OFF_TCCNT(%r15) */
+	_EMIT6(0xd203f000 | tjit->tccnt_off,
+	       0xf000 | (tjit->stack_size + STK_OFF_TCCNT));
 	/* stmg %r2,%rN,fwd_reg_args_off(%r15) */
 	if (nr_reg_args)
 		EMIT6_DISP_LH(0xeb000000, 0x0024, REG_2,
@@ -2400,6 +2405,8 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 				       (nr_stack_args * sizeof(u64) - 1) << 16 |
 				       tjit->stack_args_off,
 			       0xf000 | tjit->orig_stack_args_off);
+		/* mvc STK_OFF_TCCNT(4,%r15),tccnt_off(%r15) */
+		_EMIT6(0xd203f000 | STK_OFF_TCCNT, 0xf000 | tjit->tccnt_off);
 		/* lgr %r1,%r8 */
 		EMIT4(0xb9040000, REG_1, REG_8);
 		/* %r1() */
@@ -2456,6 +2463,9 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 	if (flags & (BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_RET_FENTRY_RET))
 		EMIT6_DISP_LH(0xe3000000, 0x0004, REG_2, REG_0, REG_15,
 			      tjit->retval_off);
+	/* mvc stack_size+STK_OFF_TCCNT(4,%r15),tccnt_off(%r15) */
+	_EMIT6(0xd203f000 | (tjit->stack_size + STK_OFF_TCCNT),
+	       0xf000 | tjit->tccnt_off);
 	/* aghi %r15,stack_size */
 	EMIT4_IMM(0xa70b0000, REG_15, tjit->stack_size);
 	/* Emit an expoline for the following indirect jump. */

From a96a44aba556c42b432929d37d60158aca21ad4c Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <martin.lau@kernel.org>
Date: Fri, 1 Sep 2023 16:11:27 -0700
Subject: [PATCH 1101/1189] bpf: bpf_sk_storage: Fix invalid wait context
 lockdep report

'./test_progs -t test_local_storage' reported a splat:

[   27.137569] =============================
[   27.138122] [ BUG: Invalid wait context ]
[   27.138650] 6.5.0-03980-gd11ae1b16b0a #247 Tainted: G           O
[   27.139542] -----------------------------
[   27.140106] test_progs/1729 is trying to lock:
[   27.140713] ffff8883ef047b88 (stock_lock){-.-.}-{3:3}, at: local_lock_acquire+0x9/0x130
[   27.141834] other info that might help us debug this:
[   27.142437] context-{5:5}
[   27.142856] 2 locks held by test_progs/1729:
[   27.143352]  #0: ffffffff84bcd9c0 (rcu_read_lock){....}-{1:3}, at: rcu_lock_acquire+0x4/0x40
[   27.144492]  #1: ffff888107deb2c0 (&storage->lock){..-.}-{2:2}, at: bpf_local_storage_update+0x39e/0x8e0
[   27.145855] stack backtrace:
[   27.146274] CPU: 0 PID: 1729 Comm: test_progs Tainted: G           O       6.5.0-03980-gd11ae1b16b0a #247
[   27.147550] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014
[   27.149127] Call Trace:
[   27.149490]  <TASK>
[   27.149867]  dump_stack_lvl+0x130/0x1d0
[   27.152609]  dump_stack+0x14/0x20
[   27.153131]  __lock_acquire+0x1657/0x2220
[   27.153677]  lock_acquire+0x1b8/0x510
[   27.157908]  local_lock_acquire+0x29/0x130
[   27.159048]  obj_cgroup_charge+0xf4/0x3c0
[   27.160794]  slab_pre_alloc_hook+0x28e/0x2b0
[   27.161931]  __kmem_cache_alloc_node+0x51/0x210
[   27.163557]  __kmalloc+0xaa/0x210
[   27.164593]  bpf_map_kzalloc+0xbc/0x170
[   27.165147]  bpf_selem_alloc+0x130/0x510
[   27.166295]  bpf_local_storage_update+0x5aa/0x8e0
[   27.167042]  bpf_fd_sk_storage_update_elem+0xdb/0x1a0
[   27.169199]  bpf_map_update_value+0x415/0x4f0
[   27.169871]  map_update_elem+0x413/0x550
[   27.170330]  __sys_bpf+0x5e9/0x640
[   27.174065]  __x64_sys_bpf+0x80/0x90
[   27.174568]  do_syscall_64+0x48/0xa0
[   27.175201]  entry_SYSCALL_64_after_hwframe+0x6e/0xd8
[   27.175932] RIP: 0033:0x7effb40e41ad
[   27.176357] Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d8
[   27.179028] RSP: 002b:00007ffe64c21fc8 EFLAGS: 00000202 ORIG_RAX: 0000000000000141
[   27.180088] RAX: ffffffffffffffda RBX: 00007ffe64c22768 RCX: 00007effb40e41ad
[   27.181082] RDX: 0000000000000020 RSI: 00007ffe64c22008 RDI: 0000000000000002
[   27.182030] RBP: 00007ffe64c21ff0 R08: 0000000000000000 R09: 00007ffe64c22788
[   27.183038] R10: 0000000000000064 R11: 0000000000000202 R12: 0000000000000000
[   27.184006] R13: 00007ffe64c22788 R14: 00007effb42a1000 R15: 0000000000000000
[   27.184958]  </TASK>

It complains about acquiring a local_lock while holding a raw_spin_lock.
It means it should not allocate memory while holding a raw_spin_lock
since it is not safe for RT.

raw_spin_lock is needed because bpf_local_storage supports tracing
context. In particular for task local storage, it is easy to
get a "current" task PTR_TO_BTF_ID in tracing bpf prog.
However, task (and cgroup) local storage has already been moved to
bpf mem allocator which can be used after raw_spin_lock.

The splat is for the sk storage. For sk (and inode) storage,
it has not been moved to bpf mem allocator. Using raw_spin_lock or not,
kzalloc(GFP_ATOMIC) could theoretically be unsafe in tracing context.
However, the local storage helper requires a verifier accepted
sk pointer (PTR_TO_BTF_ID), it is hypothetical if that (mean running
a bpf prog in a kzalloc unsafe context and also able to hold a verifier
accepted sk pointer) could happen.

This patch avoids kzalloc after raw_spin_lock to silent the splat.
There is an existing kzalloc before the raw_spin_lock. At that point,
a kzalloc is very likely required because a lookup has just been done
before. Thus, this patch always does the kzalloc before acquiring
the raw_spin_lock and remove the later kzalloc usage after the
raw_spin_lock. After this change, it will have a charge and then
uncharge during the syscall bpf_map_update_elem() code path.
This patch opts for simplicity and not continue the old
optimization to save one charge and uncharge.

This issue is dated back to the very first commit of bpf_sk_storage
which had been refactored multiple times to create task, inode, and
cgroup storage. This patch uses a Fixes tag with a more recent
commit that should be easier to do backport.

Fixes: b00fa38a9c1c ("bpf: Enable non-atomic allocations in local storage")
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20230901231129.578493-2-martin.lau@linux.dev
---
 kernel/bpf/bpf_local_storage.c | 47 ++++++++++------------------------
 1 file changed, 14 insertions(+), 33 deletions(-)

diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index b5149cfce7d4..37ad47d52dc5 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -553,7 +553,7 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
 			 void *value, u64 map_flags, gfp_t gfp_flags)
 {
 	struct bpf_local_storage_data *old_sdata = NULL;
-	struct bpf_local_storage_elem *selem = NULL;
+	struct bpf_local_storage_elem *alloc_selem, *selem = NULL;
 	struct bpf_local_storage *local_storage;
 	unsigned long flags;
 	int err;
@@ -607,11 +607,12 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
 		}
 	}
 
-	if (gfp_flags == GFP_KERNEL) {
-		selem = bpf_selem_alloc(smap, owner, value, true, gfp_flags);
-		if (!selem)
-			return ERR_PTR(-ENOMEM);
-	}
+	/* A lookup has just been done before and concluded a new selem is
+	 * needed. The chance of an unnecessary alloc is unlikely.
+	 */
+	alloc_selem = selem = bpf_selem_alloc(smap, owner, value, true, gfp_flags);
+	if (!alloc_selem)
+		return ERR_PTR(-ENOMEM);
 
 	raw_spin_lock_irqsave(&local_storage->lock, flags);
 
@@ -623,13 +624,13 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
 		 * simple.
 		 */
 		err = -EAGAIN;
-		goto unlock_err;
+		goto unlock;
 	}
 
 	old_sdata = bpf_local_storage_lookup(local_storage, smap, false);
 	err = check_flags(old_sdata, map_flags);
 	if (err)
-		goto unlock_err;
+		goto unlock;
 
 	if (old_sdata && (map_flags & BPF_F_LOCK)) {
 		copy_map_value_locked(&smap->map, old_sdata->data, value,
@@ -638,23 +639,7 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
 		goto unlock;
 	}
 
-	if (gfp_flags != GFP_KERNEL) {
-		/* local_storage->lock is held.  Hence, we are sure
-		 * we can unlink and uncharge the old_sdata successfully
-		 * later.  Hence, instead of charging the new selem now
-		 * and then uncharge the old selem later (which may cause
-		 * a potential but unnecessary charge failure),  avoid taking
-		 * a charge at all here (the "!old_sdata" check) and the
-		 * old_sdata will not be uncharged later during
-		 * bpf_selem_unlink_storage_nolock().
-		 */
-		selem = bpf_selem_alloc(smap, owner, value, !old_sdata, gfp_flags);
-		if (!selem) {
-			err = -ENOMEM;
-			goto unlock_err;
-		}
-	}
-
+	alloc_selem = NULL;
 	/* First, link the new selem to the map */
 	bpf_selem_link_map(smap, selem);
 
@@ -665,20 +650,16 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
 	if (old_sdata) {
 		bpf_selem_unlink_map(SELEM(old_sdata));
 		bpf_selem_unlink_storage_nolock(local_storage, SELEM(old_sdata),
-						false, false);
+						true, false);
 	}
 
 unlock:
 	raw_spin_unlock_irqrestore(&local_storage->lock, flags);
-	return SDATA(selem);
-
-unlock_err:
-	raw_spin_unlock_irqrestore(&local_storage->lock, flags);
-	if (selem) {
+	if (alloc_selem) {
 		mem_uncharge(smap, owner, smap->elem_size);
-		bpf_selem_free(selem, smap, true);
+		bpf_selem_free(alloc_selem, smap, true);
 	}
-	return ERR_PTR(err);
+	return err ? ERR_PTR(err) : SDATA(selem);
 }
 
 static u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache)

From 55d49f750b1cb1f177fb1b00ae02cba4613bcfb7 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <martin.lau@kernel.org>
Date: Fri, 1 Sep 2023 16:11:28 -0700
Subject: [PATCH 1102/1189] bpf: bpf_sk_storage: Fix the missing uncharge in
 sk_omem_alloc

The commit c83597fa5dc6 ("bpf: Refactor some inode/task/sk storage functions
for reuse"), refactored the bpf_{sk,task,inode}_storage_free() into
bpf_local_storage_unlink_nolock() which then later renamed to
bpf_local_storage_destroy(). The commit accidentally passed the
"bool uncharge_mem = false" argument to bpf_selem_unlink_storage_nolock()
which then stopped the uncharge from happening to the sk->sk_omem_alloc.

This missing uncharge only happens when the sk is going away (during
__sk_destruct).

This patch fixes it by always passing "uncharge_mem = true". It is a
noop to the task/inode/cgroup storage because they do not have the
map_local_storage_(un)charge enabled in the map_ops. A followup patch
will be done in bpf-next to remove the uncharge_mem argument.

A selftest is added in the next patch.

Fixes: c83597fa5dc6 ("bpf: Refactor some inode/task/sk storage functions for reuse")
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20230901231129.578493-3-martin.lau@linux.dev
---
 kernel/bpf/bpf_local_storage.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index 37ad47d52dc5..146824cc9689 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -760,7 +760,7 @@ void bpf_local_storage_destroy(struct bpf_local_storage *local_storage)
 		 * of the loop will set the free_cgroup_storage to true.
 		 */
 		free_storage = bpf_selem_unlink_storage_nolock(
-			local_storage, selem, false, true);
+			local_storage, selem, true, true);
 	}
 	raw_spin_unlock_irqrestore(&local_storage->lock, flags);
 

From a96d1cfb2da040bdf692d22022371b249742abb2 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <martin.lau@kernel.org>
Date: Fri, 1 Sep 2023 16:11:29 -0700
Subject: [PATCH 1103/1189] selftests/bpf: Check bpf_sk_storage has uncharged
 sk_omem_alloc

This patch checks the sk_omem_alloc has been uncharged by bpf_sk_storage
during the __sk_destruct.

Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20230901231129.578493-4-martin.lau@linux.dev
---
 .../bpf/prog_tests/sk_storage_omem_uncharge.c | 56 +++++++++++++++++
 .../selftests/bpf/progs/bpf_tracing_net.h     |  1 +
 .../bpf/progs/sk_storage_omem_uncharge.c      | 61 +++++++++++++++++++
 3 files changed, 118 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/sk_storage_omem_uncharge.c
 create mode 100644 tools/testing/selftests/bpf/progs/sk_storage_omem_uncharge.c

diff --git a/tools/testing/selftests/bpf/prog_tests/sk_storage_omem_uncharge.c b/tools/testing/selftests/bpf/prog_tests/sk_storage_omem_uncharge.c
new file mode 100644
index 000000000000..f35852d245e3
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sk_storage_omem_uncharge.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Facebook */
+#include <test_progs.h>
+#include <bpf/libbpf.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include "sk_storage_omem_uncharge.skel.h"
+
+void test_sk_storage_omem_uncharge(void)
+{
+	struct sk_storage_omem_uncharge *skel;
+	int sk_fd = -1, map_fd, err, value;
+	socklen_t optlen;
+
+	skel = sk_storage_omem_uncharge__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel open_and_load"))
+		return;
+	map_fd = bpf_map__fd(skel->maps.sk_storage);
+
+	/* A standalone socket not binding to addr:port,
+	 * so nentns is not needed.
+	 */
+	sk_fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (!ASSERT_GE(sk_fd, 0, "socket"))
+		goto done;
+
+	optlen = sizeof(skel->bss->cookie);
+	err = getsockopt(sk_fd, SOL_SOCKET, SO_COOKIE, &skel->bss->cookie, &optlen);
+	if (!ASSERT_OK(err, "getsockopt(SO_COOKIE)"))
+		goto done;
+
+	value = 0;
+	err = bpf_map_update_elem(map_fd, &sk_fd, &value, 0);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(value=0)"))
+		goto done;
+
+	value = 0xdeadbeef;
+	err = bpf_map_update_elem(map_fd, &sk_fd, &value, 0);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(value=0xdeadbeef)"))
+		goto done;
+
+	err = sk_storage_omem_uncharge__attach(skel);
+	if (!ASSERT_OK(err, "attach"))
+		goto done;
+
+	close(sk_fd);
+	sk_fd = -1;
+
+	ASSERT_EQ(skel->bss->cookie_found, 2, "cookie_found");
+	ASSERT_EQ(skel->bss->omem, 0, "omem");
+
+done:
+	sk_storage_omem_uncharge__destroy(skel);
+	if (sk_fd != -1)
+		close(sk_fd);
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
index cfed4df490f3..0b793a102791 100644
--- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
+++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
@@ -88,6 +88,7 @@
 #define sk_v6_rcv_saddr		__sk_common.skc_v6_rcv_saddr
 #define sk_flags		__sk_common.skc_flags
 #define sk_reuse		__sk_common.skc_reuse
+#define sk_cookie		__sk_common.skc_cookie
 
 #define s6_addr32		in6_u.u6_addr32
 
diff --git a/tools/testing/selftests/bpf/progs/sk_storage_omem_uncharge.c b/tools/testing/selftests/bpf/progs/sk_storage_omem_uncharge.c
new file mode 100644
index 000000000000..3e745793b27a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/sk_storage_omem_uncharge.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Facebook */
+#include "vmlinux.h"
+#include "bpf_tracing_net.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+
+void *local_storage_ptr = NULL;
+void *sk_ptr = NULL;
+int cookie_found = 0;
+__u64 cookie = 0;
+__u32 omem = 0;
+
+void *bpf_rdonly_cast(void *, __u32) __ksym;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, int);
+} sk_storage SEC(".maps");
+
+SEC("fexit/bpf_local_storage_destroy")
+int BPF_PROG(bpf_local_storage_destroy, struct bpf_local_storage *local_storage)
+{
+	struct sock *sk;
+
+	if (local_storage_ptr != local_storage)
+		return 0;
+
+	sk = bpf_rdonly_cast(sk_ptr, bpf_core_type_id_kernel(struct sock));
+	if (sk->sk_cookie.counter != cookie)
+		return 0;
+
+	cookie_found++;
+	omem = sk->sk_omem_alloc.counter;
+	local_storage_ptr = NULL;
+
+	return 0;
+}
+
+SEC("fentry/inet6_sock_destruct")
+int BPF_PROG(inet6_sock_destruct, struct sock *sk)
+{
+	int *value;
+
+	if (!cookie || sk->sk_cookie.counter != cookie)
+		return 0;
+
+	value = bpf_sk_storage_get(&sk_storage, sk, 0, 0);
+	if (value && *value == 0xdeadbeef) {
+		cookie_found++;
+		sk_ptr = sk;
+		local_storage_ptr = sk->sk_bpf_storage;
+	}
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";

From 20e490adea279d49d57b800475938f5b67926d98 Mon Sep 17 00:00:00 2001
From: Puranjay Mohan <puranjay12@gmail.com>
Date: Thu, 31 Aug 2023 13:12:26 +0000
Subject: [PATCH 1104/1189] bpf: make bpf_prog_pack allocator portable
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The bpf_prog_pack allocator currently uses module_alloc() and
module_memfree() to allocate and free memory. This is not portable
because different architectures use different methods for allocating
memory for BPF programs. Like ARM64 and riscv use vmalloc()/vfree().

Use bpf_jit_alloc_exec() and bpf_jit_free_exec() for memory management
in bpf_prog_pack allocator. Other architectures can override these with
their implementation and will be able to use bpf_prog_pack directly.

On architectures that don't override bpf_jit_alloc/free_exec() this is
basically a NOP.

Signed-off-by: Puranjay Mohan <puranjay12@gmail.com>
Acked-by: Song Liu <song@kernel.org>
Acked-by: Björn Töpel <bjorn@kernel.org>
Tested-by: Björn Töpel <bjorn@rivosinc.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/r/20230831131229.497941-2-puranjay12@gmail.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 kernel/bpf/core.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 0f8f036d8bd1..4e3ce0542e31 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -870,7 +870,7 @@ static struct bpf_prog_pack *alloc_new_pack(bpf_jit_fill_hole_t bpf_fill_ill_ins
 		       GFP_KERNEL);
 	if (!pack)
 		return NULL;
-	pack->ptr = module_alloc(BPF_PROG_PACK_SIZE);
+	pack->ptr = bpf_jit_alloc_exec(BPF_PROG_PACK_SIZE);
 	if (!pack->ptr) {
 		kfree(pack);
 		return NULL;
@@ -894,7 +894,7 @@ void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns)
 	mutex_lock(&pack_mutex);
 	if (size > BPF_PROG_PACK_SIZE) {
 		size = round_up(size, PAGE_SIZE);
-		ptr = module_alloc(size);
+		ptr = bpf_jit_alloc_exec(size);
 		if (ptr) {
 			bpf_fill_ill_insns(ptr, size);
 			set_vm_flush_reset_perms(ptr);
@@ -932,7 +932,7 @@ void bpf_prog_pack_free(struct bpf_binary_header *hdr)
 
 	mutex_lock(&pack_mutex);
 	if (hdr->size > BPF_PROG_PACK_SIZE) {
-		module_memfree(hdr);
+		bpf_jit_free_exec(hdr);
 		goto out;
 	}
 
@@ -956,7 +956,7 @@ void bpf_prog_pack_free(struct bpf_binary_header *hdr)
 	if (bitmap_find_next_zero_area(pack->bitmap, BPF_PROG_CHUNK_COUNT, 0,
 				       BPF_PROG_CHUNK_COUNT, 0) == 0) {
 		list_del(&pack->list);
-		module_memfree(pack->ptr);
+		bpf_jit_free_exec(pack->ptr);
 		kfree(pack);
 	}
 out:

From 9721873c3c023254f04138bbb21d539b4f0f0ad6 Mon Sep 17 00:00:00 2001
From: Puranjay Mohan <puranjay12@gmail.com>
Date: Thu, 31 Aug 2023 13:12:27 +0000
Subject: [PATCH 1105/1189] riscv: extend patch_text_nosync() for multiple
 pages
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The patch_insn_write() function currently doesn't work for multiple pages
of instructions, therefore patch_text_nosync() will fail with a page fault
if called with lengths spanning multiple pages.

This commit extends the patch_insn_write() function to support multiple
pages by copying at max 2 pages at a time in a loop. This implementation
is similar to text_poke_copy() function of x86.

Signed-off-by: Puranjay Mohan <puranjay12@gmail.com>
Reviewed-by: Pu Lehui <pulehui@huawei.com>
Reviewed-by: Björn Töpel <bjorn@rivosinc.com>
Tested-by: Björn Töpel <bjorn@rivosinc.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/r/20230831131229.497941-3-puranjay12@gmail.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/patch.c | 37 ++++++++++++++++++++++++++++++++-----
 1 file changed, 32 insertions(+), 5 deletions(-)

diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c
index 575e71d6c8ae..2c97e246f4dc 100644
--- a/arch/riscv/kernel/patch.c
+++ b/arch/riscv/kernel/patch.c
@@ -53,12 +53,18 @@ static void patch_unmap(int fixmap)
 }
 NOKPROBE_SYMBOL(patch_unmap);
 
-static int patch_insn_write(void *addr, const void *insn, size_t len)
+static int __patch_insn_write(void *addr, const void *insn, size_t len)
 {
 	void *waddr = addr;
 	bool across_pages = (((uintptr_t) addr & ~PAGE_MASK) + len) > PAGE_SIZE;
 	int ret;
 
+	/*
+	 * Only two pages can be mapped at a time for writing.
+	 */
+	if (len + offset_in_page(addr) > 2 * PAGE_SIZE)
+		return -EINVAL;
+
 	/*
 	 * Before reaching here, it was expected to lock the text_mutex
 	 * already, so we don't need to give another lock here and could
@@ -74,7 +80,7 @@ static int patch_insn_write(void *addr, const void *insn, size_t len)
 		lockdep_assert_held(&text_mutex);
 
 	if (across_pages)
-		patch_map(addr + len, FIX_TEXT_POKE1);
+		patch_map(addr + PAGE_SIZE, FIX_TEXT_POKE1);
 
 	waddr = patch_map(addr, FIX_TEXT_POKE0);
 
@@ -87,15 +93,36 @@ static int patch_insn_write(void *addr, const void *insn, size_t len)
 
 	return ret;
 }
-NOKPROBE_SYMBOL(patch_insn_write);
+NOKPROBE_SYMBOL(__patch_insn_write);
 #else
-static int patch_insn_write(void *addr, const void *insn, size_t len)
+static int __patch_insn_write(void *addr, const void *insn, size_t len)
 {
 	return copy_to_kernel_nofault(addr, insn, len);
 }
-NOKPROBE_SYMBOL(patch_insn_write);
+NOKPROBE_SYMBOL(__patch_insn_write);
 #endif /* CONFIG_MMU */
 
+static int patch_insn_write(void *addr, const void *insn, size_t len)
+{
+	size_t patched = 0;
+	size_t size;
+	int ret = 0;
+
+	/*
+	 * Copy the instructions to the destination address, two pages at a time
+	 * because __patch_insn_write() can only handle len <= 2 * PAGE_SIZE.
+	 */
+	while (patched < len && !ret) {
+		size = min_t(size_t, PAGE_SIZE * 2 - offset_in_page(addr + patched), len - patched);
+		ret = __patch_insn_write(addr + patched, insn + patched, size);
+
+		patched += size;
+	}
+
+	return ret;
+}
+NOKPROBE_SYMBOL(patch_insn_write);
+
 int patch_text_nosync(void *addr, const void *insns, size_t len)
 {
 	u32 *tp = addr;

From cad539baa48ff257b598000a90db2b7edd4b2dd5 Mon Sep 17 00:00:00 2001
From: Puranjay Mohan <puranjay12@gmail.com>
Date: Thu, 31 Aug 2023 13:12:28 +0000
Subject: [PATCH 1106/1189] riscv: implement a memset like function for text
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The BPF JIT needs to write invalid instructions to RX regions of memory to
invalidate removed BPF programs. This needs a function like memset() that
can work with RX memory.

Implement patch_text_set_nosync() which is similar to text_poke_set() of
x86.

Signed-off-by: Puranjay Mohan <puranjay12@gmail.com>
Reviewed-by: Pu Lehui <pulehui@huawei.com>
Acked-by: Björn Töpel <bjorn@kernel.org>
Tested-by: Björn Töpel <bjorn@rivosinc.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/r/20230831131229.497941-4-puranjay12@gmail.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/patch.h |  1 +
 arch/riscv/kernel/patch.c      | 77 ++++++++++++++++++++++++++++++++++
 2 files changed, 78 insertions(+)

diff --git a/arch/riscv/include/asm/patch.h b/arch/riscv/include/asm/patch.h
index 63c98833d510..e88b52d39eac 100644
--- a/arch/riscv/include/asm/patch.h
+++ b/arch/riscv/include/asm/patch.h
@@ -7,6 +7,7 @@
 #define _ASM_RISCV_PATCH_H
 
 int patch_text_nosync(void *addr, const void *insns, size_t len);
+int patch_text_set_nosync(void *addr, u8 c, size_t len);
 int patch_text(void *addr, u32 *insns, int ninsns);
 
 extern int riscv_patch_in_stop_machine;
diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c
index 2c97e246f4dc..13ee7bf589a1 100644
--- a/arch/riscv/kernel/patch.c
+++ b/arch/riscv/kernel/patch.c
@@ -6,6 +6,7 @@
 #include <linux/spinlock.h>
 #include <linux/mm.h>
 #include <linux/memory.h>
+#include <linux/string.h>
 #include <linux/uaccess.h>
 #include <linux/stop_machine.h>
 #include <asm/kprobes.h>
@@ -53,6 +54,39 @@ static void patch_unmap(int fixmap)
 }
 NOKPROBE_SYMBOL(patch_unmap);
 
+static int __patch_insn_set(void *addr, u8 c, size_t len)
+{
+	void *waddr = addr;
+	bool across_pages = (((uintptr_t)addr & ~PAGE_MASK) + len) > PAGE_SIZE;
+
+	/*
+	 * Only two pages can be mapped at a time for writing.
+	 */
+	if (len + offset_in_page(addr) > 2 * PAGE_SIZE)
+		return -EINVAL;
+	/*
+	 * Before reaching here, it was expected to lock the text_mutex
+	 * already, so we don't need to give another lock here and could
+	 * ensure that it was safe between each cores.
+	 */
+	lockdep_assert_held(&text_mutex);
+
+	if (across_pages)
+		patch_map(addr + PAGE_SIZE, FIX_TEXT_POKE1);
+
+	waddr = patch_map(addr, FIX_TEXT_POKE0);
+
+	memset(waddr, c, len);
+
+	patch_unmap(FIX_TEXT_POKE0);
+
+	if (across_pages)
+		patch_unmap(FIX_TEXT_POKE1);
+
+	return 0;
+}
+NOKPROBE_SYMBOL(__patch_insn_set);
+
 static int __patch_insn_write(void *addr, const void *insn, size_t len)
 {
 	void *waddr = addr;
@@ -95,6 +129,14 @@ static int __patch_insn_write(void *addr, const void *insn, size_t len)
 }
 NOKPROBE_SYMBOL(__patch_insn_write);
 #else
+static int __patch_insn_set(void *addr, u8 c, size_t len)
+{
+	memset(addr, c, len);
+
+	return 0;
+}
+NOKPROBE_SYMBOL(__patch_insn_set);
+
 static int __patch_insn_write(void *addr, const void *insn, size_t len)
 {
 	return copy_to_kernel_nofault(addr, insn, len);
@@ -102,6 +144,41 @@ static int __patch_insn_write(void *addr, const void *insn, size_t len)
 NOKPROBE_SYMBOL(__patch_insn_write);
 #endif /* CONFIG_MMU */
 
+static int patch_insn_set(void *addr, u8 c, size_t len)
+{
+	size_t patched = 0;
+	size_t size;
+	int ret = 0;
+
+	/*
+	 * __patch_insn_set() can only work on 2 pages at a time so call it in a
+	 * loop with len <= 2 * PAGE_SIZE.
+	 */
+	while (patched < len && !ret) {
+		size = min_t(size_t, PAGE_SIZE * 2 - offset_in_page(addr + patched), len - patched);
+		ret = __patch_insn_set(addr + patched, c, size);
+
+		patched += size;
+	}
+
+	return ret;
+}
+NOKPROBE_SYMBOL(patch_insn_set);
+
+int patch_text_set_nosync(void *addr, u8 c, size_t len)
+{
+	u32 *tp = addr;
+	int ret;
+
+	ret = patch_insn_set(tp, c, len);
+
+	if (!ret)
+		flush_icache_range((uintptr_t)tp, (uintptr_t)tp + len);
+
+	return ret;
+}
+NOKPROBE_SYMBOL(patch_text_set_nosync);
+
 static int patch_insn_write(void *addr, const void *insn, size_t len)
 {
 	size_t patched = 0;

From 48a8f78c50bd6f7f08fd40daa62252fd043f2f18 Mon Sep 17 00:00:00 2001
From: Puranjay Mohan <puranjay12@gmail.com>
Date: Thu, 31 Aug 2023 13:12:29 +0000
Subject: [PATCH 1107/1189] bpf, riscv: use prog pack allocator in the BPF JIT
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use bpf_jit_binary_pack_alloc() for memory management of JIT binaries in
RISCV BPF JIT. The bpf_jit_binary_pack_alloc creates a pair of RW and RX
buffers. The JIT writes the program into the RW buffer. When the JIT is
done, the program is copied to the final RX buffer with
bpf_jit_binary_pack_finalize.

Implement bpf_arch_text_copy() and bpf_arch_text_invalidate() for RISCV
JIT as these functions are required by bpf_jit_binary_pack allocator.

Signed-off-by: Puranjay Mohan <puranjay12@gmail.com>
Reviewed-by: Song Liu <song@kernel.org>
Reviewed-by: Pu Lehui <pulehui@huawei.com>
Acked-by: Björn Töpel <bjorn@kernel.org>
Tested-by: Björn Töpel <bjorn@rivosinc.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/r/20230831131229.497941-5-puranjay12@gmail.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/net/bpf_jit.h        |   3 +
 arch/riscv/net/bpf_jit_comp64.c |  60 ++++++++++++++----
 arch/riscv/net/bpf_jit_core.c   | 106 +++++++++++++++++++++++++++-----
 3 files changed, 141 insertions(+), 28 deletions(-)

diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h
index d21c6c92a683..a5ce1ab76ece 100644
--- a/arch/riscv/net/bpf_jit.h
+++ b/arch/riscv/net/bpf_jit.h
@@ -68,6 +68,7 @@ static inline bool is_creg(u8 reg)
 struct rv_jit_context {
 	struct bpf_prog *prog;
 	u16 *insns;		/* RV insns */
+	u16 *ro_insns;
 	int ninsns;
 	int prologue_len;
 	int epilogue_offset;
@@ -85,7 +86,9 @@ static inline int ninsns_rvoff(int ninsns)
 
 struct rv_jit_data {
 	struct bpf_binary_header *header;
+	struct bpf_binary_header *ro_header;
 	u8 *image;
+	u8 *ro_image;
 	struct rv_jit_context ctx;
 };
 
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 8423f4ddf8f5..ecd3ae6f4116 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -144,7 +144,11 @@ static bool in_auipc_jalr_range(s64 val)
 /* Emit fixed-length instructions for address */
 static int emit_addr(u8 rd, u64 addr, bool extra_pass, struct rv_jit_context *ctx)
 {
-	u64 ip = (u64)(ctx->insns + ctx->ninsns);
+	/*
+	 * Use the ro_insns(RX) to calculate the offset as the BPF program will
+	 * finally run from this memory region.
+	 */
+	u64 ip = (u64)(ctx->ro_insns + ctx->ninsns);
 	s64 off = addr - ip;
 	s64 upper = (off + (1 << 11)) >> 12;
 	s64 lower = off & 0xfff;
@@ -464,8 +468,12 @@ static int emit_call(u64 addr, bool fixed_addr, struct rv_jit_context *ctx)
 	s64 off = 0;
 	u64 ip;
 
-	if (addr && ctx->insns) {
-		ip = (u64)(long)(ctx->insns + ctx->ninsns);
+	if (addr && ctx->insns && ctx->ro_insns) {
+		/*
+		 * Use the ro_insns(RX) to calculate the offset as the BPF
+		 * program will finally run from this memory region.
+		 */
+		ip = (u64)(long)(ctx->ro_insns + ctx->ninsns);
 		off = addr - ip;
 	}
 
@@ -578,9 +586,10 @@ static int add_exception_handler(const struct bpf_insn *insn,
 {
 	struct exception_table_entry *ex;
 	unsigned long pc;
-	off_t offset;
+	off_t ins_offset;
+	off_t fixup_offset;
 
-	if (!ctx->insns || !ctx->prog->aux->extable ||
+	if (!ctx->insns || !ctx->ro_insns || !ctx->prog->aux->extable ||
 	    (BPF_MODE(insn->code) != BPF_PROBE_MEM && BPF_MODE(insn->code) != BPF_PROBE_MEMSX))
 		return 0;
 
@@ -594,12 +603,17 @@ static int add_exception_handler(const struct bpf_insn *insn,
 		return -EINVAL;
 
 	ex = &ctx->prog->aux->extable[ctx->nexentries];
-	pc = (unsigned long)&ctx->insns[ctx->ninsns - insn_len];
+	pc = (unsigned long)&ctx->ro_insns[ctx->ninsns - insn_len];
 
-	offset = pc - (long)&ex->insn;
-	if (WARN_ON_ONCE(offset >= 0 || offset < INT_MIN))
+	/*
+	 * This is the relative offset of the instruction that may fault from
+	 * the exception table itself. This will be written to the exception
+	 * table and if this instruction faults, the destination register will
+	 * be set to '0' and the execution will jump to the next instruction.
+	 */
+	ins_offset = pc - (long)&ex->insn;
+	if (WARN_ON_ONCE(ins_offset >= 0 || ins_offset < INT_MIN))
 		return -ERANGE;
-	ex->insn = offset;
 
 	/*
 	 * Since the extable follows the program, the fixup offset is always
@@ -608,12 +622,25 @@ static int add_exception_handler(const struct bpf_insn *insn,
 	 * bits. We don't need to worry about buildtime or runtime sort
 	 * modifying the upper bits because the table is already sorted, and
 	 * isn't part of the main exception table.
+	 *
+	 * The fixup_offset is set to the next instruction from the instruction
+	 * that may fault. The execution will jump to this after handling the
+	 * fault.
 	 */
-	offset = (long)&ex->fixup - (pc + insn_len * sizeof(u16));
-	if (!FIELD_FIT(BPF_FIXUP_OFFSET_MASK, offset))
+	fixup_offset = (long)&ex->fixup - (pc + insn_len * sizeof(u16));
+	if (!FIELD_FIT(BPF_FIXUP_OFFSET_MASK, fixup_offset))
 		return -ERANGE;
 
-	ex->fixup = FIELD_PREP(BPF_FIXUP_OFFSET_MASK, offset) |
+	/*
+	 * The offsets above have been calculated using the RO buffer but we
+	 * need to use the R/W buffer for writes.
+	 * switch ex to rw buffer for writing.
+	 */
+	ex = (void *)ctx->insns + ((void *)ex - (void *)ctx->ro_insns);
+
+	ex->insn = ins_offset;
+
+	ex->fixup = FIELD_PREP(BPF_FIXUP_OFFSET_MASK, fixup_offset) |
 		FIELD_PREP(BPF_FIXUP_REG_MASK, dst_reg);
 	ex->type = EX_TYPE_BPF;
 
@@ -1007,6 +1034,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
 
 	ctx.ninsns = 0;
 	ctx.insns = NULL;
+	ctx.ro_insns = NULL;
 	ret = __arch_prepare_bpf_trampoline(im, m, tlinks, func_addr, flags, &ctx);
 	if (ret < 0)
 		return ret;
@@ -1015,7 +1043,15 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
 		return -EFBIG;
 
 	ctx.ninsns = 0;
+	/*
+	 * The bpf_int_jit_compile() uses a RW buffer (ctx.insns) to write the
+	 * JITed instructions and later copies it to a RX region (ctx.ro_insns).
+	 * It also uses ctx.ro_insns to calculate offsets for jumps etc. As the
+	 * trampoline image uses the same memory area for writing and execution,
+	 * both ctx.insns and ctx.ro_insns can be set to image.
+	 */
 	ctx.insns = image;
+	ctx.ro_insns = image;
 	ret = __arch_prepare_bpf_trampoline(im, m, tlinks, func_addr, flags, &ctx);
 	if (ret < 0)
 		return ret;
diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c
index 7a26a3e1c73c..7b70ccb7fec3 100644
--- a/arch/riscv/net/bpf_jit_core.c
+++ b/arch/riscv/net/bpf_jit_core.c
@@ -8,6 +8,8 @@
 
 #include <linux/bpf.h>
 #include <linux/filter.h>
+#include <linux/memory.h>
+#include <asm/patch.h>
 #include "bpf_jit.h"
 
 /* Number of iterations to try until offsets converge. */
@@ -117,16 +119,24 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 				sizeof(struct exception_table_entry);
 			prog_size = sizeof(*ctx->insns) * ctx->ninsns;
 
-			jit_data->header =
-				bpf_jit_binary_alloc(prog_size + extable_size,
-						     &jit_data->image,
-						     sizeof(u32),
-						     bpf_fill_ill_insns);
-			if (!jit_data->header) {
+			jit_data->ro_header =
+				bpf_jit_binary_pack_alloc(prog_size + extable_size,
+							  &jit_data->ro_image, sizeof(u32),
+							  &jit_data->header, &jit_data->image,
+							  bpf_fill_ill_insns);
+			if (!jit_data->ro_header) {
 				prog = orig_prog;
 				goto out_offset;
 			}
 
+			/*
+			 * Use the image(RW) for writing the JITed instructions. But also save
+			 * the ro_image(RX) for calculating the offsets in the image. The RW
+			 * image will be later copied to the RX image from where the program
+			 * will run. The bpf_jit_binary_pack_finalize() will do this copy in the
+			 * final step.
+			 */
+			ctx->ro_insns = (u16 *)jit_data->ro_image;
 			ctx->insns = (u16 *)jit_data->image;
 			/*
 			 * Now, when the image is allocated, the image can
@@ -138,14 +148,12 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 
 	if (i == NR_JIT_ITERATIONS) {
 		pr_err("bpf-jit: image did not converge in <%d passes!\n", i);
-		if (jit_data->header)
-			bpf_jit_binary_free(jit_data->header);
 		prog = orig_prog;
-		goto out_offset;
+		goto out_free_hdr;
 	}
 
 	if (extable_size)
-		prog->aux->extable = (void *)ctx->insns + prog_size;
+		prog->aux->extable = (void *)ctx->ro_insns + prog_size;
 
 skip_init_ctx:
 	pass++;
@@ -154,23 +162,33 @@ skip_init_ctx:
 
 	bpf_jit_build_prologue(ctx);
 	if (build_body(ctx, extra_pass, NULL)) {
-		bpf_jit_binary_free(jit_data->header);
 		prog = orig_prog;
-		goto out_offset;
+		goto out_free_hdr;
 	}
 	bpf_jit_build_epilogue(ctx);
 
 	if (bpf_jit_enable > 1)
 		bpf_jit_dump(prog->len, prog_size, pass, ctx->insns);
 
-	prog->bpf_func = (void *)ctx->insns;
+	prog->bpf_func = (void *)ctx->ro_insns;
 	prog->jited = 1;
 	prog->jited_len = prog_size;
 
-	bpf_flush_icache(jit_data->header, ctx->insns + ctx->ninsns);
-
 	if (!prog->is_func || extra_pass) {
-		bpf_jit_binary_lock_ro(jit_data->header);
+		if (WARN_ON(bpf_jit_binary_pack_finalize(prog, jit_data->ro_header,
+							 jit_data->header))) {
+			/* ro_header has been freed */
+			jit_data->ro_header = NULL;
+			prog = orig_prog;
+			goto out_offset;
+		}
+		/*
+		 * The instructions have now been copied to the ROX region from
+		 * where they will execute.
+		 * Write any modified data cache blocks out to memory and
+		 * invalidate the corresponding blocks in the instruction cache.
+		 */
+		bpf_flush_icache(jit_data->ro_header, ctx->ro_insns + ctx->ninsns);
 		for (i = 0; i < prog->len; i++)
 			ctx->offset[i] = ninsns_rvoff(ctx->offset[i]);
 		bpf_prog_fill_jited_linfo(prog, ctx->offset);
@@ -185,6 +203,14 @@ out:
 		bpf_jit_prog_release_other(prog, prog == orig_prog ?
 					   tmp : orig_prog);
 	return prog;
+
+out_free_hdr:
+	if (jit_data->header) {
+		bpf_arch_text_copy(&jit_data->ro_header->size, &jit_data->header->size,
+				   sizeof(jit_data->header->size));
+		bpf_jit_binary_pack_free(jit_data->ro_header, jit_data->header);
+	}
+	goto out_offset;
 }
 
 u64 bpf_jit_alloc_exec_limit(void)
@@ -204,3 +230,51 @@ void bpf_jit_free_exec(void *addr)
 {
 	return vfree(addr);
 }
+
+void *bpf_arch_text_copy(void *dst, void *src, size_t len)
+{
+	int ret;
+
+	mutex_lock(&text_mutex);
+	ret = patch_text_nosync(dst, src, len);
+	mutex_unlock(&text_mutex);
+
+	if (ret)
+		return ERR_PTR(-EINVAL);
+
+	return dst;
+}
+
+int bpf_arch_text_invalidate(void *dst, size_t len)
+{
+	int ret;
+
+	mutex_lock(&text_mutex);
+	ret = patch_text_set_nosync(dst, 0, len);
+	mutex_unlock(&text_mutex);
+
+	return ret;
+}
+
+void bpf_jit_free(struct bpf_prog *prog)
+{
+	if (prog->jited) {
+		struct rv_jit_data *jit_data = prog->aux->jit_data;
+		struct bpf_binary_header *hdr;
+
+		/*
+		 * If we fail the final pass of JIT (from jit_subprogs),
+		 * the program may not be finalized yet. Call finalize here
+		 * before freeing it.
+		 */
+		if (jit_data) {
+			bpf_jit_binary_pack_finalize(prog, jit_data->ro_header, jit_data->header);
+			kfree(jit_data);
+		}
+		hdr = bpf_jit_binary_pack_hdr(prog);
+		bpf_jit_binary_pack_free(hdr, NULL);
+		WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(prog));
+	}
+
+	bpf_prog_unlock_free(prog);
+}

From 5905afc2c7bb713d52c7c7585565feecbb686b44 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 5 Sep 2023 14:47:31 +0200
Subject: [PATCH 1108/1189] block: fix pin count management when merging
 same-page segments

There is no need to unpin the added page when adding it to the bio fails
as that is done by the loop below.  Instead we want to unpin it when adding
a single page to the bio more than once as bio_release_pages will only
unpin it once.

Fixes: d1916c86ccdc ("block: move same page handling from __bio_add_pc_page to the callers")
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Link: https://lore.kernel.org/r/20230905124731.328255-1-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-map.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/block/blk-map.c b/block/blk-map.c
index 44d74a30ddac..8584babf3ea0 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -315,12 +315,11 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
 					n = bytes;
 
 				if (!bio_add_hw_page(rq->q, bio, page, n, offs,
-						     max_sectors, &same_page)) {
-					if (same_page)
-						bio_release_page(bio, page);
+						     max_sectors, &same_page))
 					break;
-				}
 
+				if (same_page)
+					bio_release_page(bio, page);
 				bytes -= n;
 				offs = 0;
 			}

From 4b9c2edaf7282d60e069551b4b28abc2932cd3e3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christoph=20B=C3=B6hmwalder?=
 <christoph.boehmwalder@linbit.com>
Date: Wed, 6 Sep 2023 15:30:34 +0200
Subject: [PATCH 1109/1189] drbd: swap bvec_set_page len and offset
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

bvec_set_page has the following signature:

static inline void bvec_set_page(struct bio_vec *bv, struct page *page,
		unsigned int len, unsigned int offset)

However, the usage in DRBD swaps the len and offset parameters. This
leads to a bvec with length=0 instead of the intended length=4096, which
causes sock_sendmsg to return -EIO.

This leaves DRBD unable to transmit any pages and thus completely
broken.

Swapping the parameters fixes the regression.

Fixes: eeac7405c735 ("drbd: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage()")
Reported-by: Serguei Ivantsov <manowar@gsc-game.com>
Link: https://lore.kernel.org/regressions/CAKH+VT3YLmAn0Y8=q37UTDShqxDLsqPcQ4hBMzY7HPn7zNx+RQ@mail.gmail.com/
Cc: stable@vger.kernel.org
Signed-off-by: Christoph Böhmwalder <christoph.boehmwalder@linbit.com>
Link: https://lore.kernel.org/r/20230906133034.948817-1-christoph.boehmwalder@linbit.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/drbd/drbd_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 79ab532aabaf..6bc86106c7b2 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -1557,7 +1557,7 @@ static int _drbd_send_page(struct drbd_peer_device *peer_device, struct page *pa
 	do {
 		int sent;
 
-		bvec_set_page(&bvec, page, offset, len);
+		bvec_set_page(&bvec, page, len, offset);
 		iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, len);
 
 		sent = sock_sendmsg(socket, &msg);

From 8ff81bb24f68f747ab2f738c3d493b9c2cad52bf Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Wed, 6 Sep 2023 22:53:09 +0800
Subject: [PATCH 1110/1189] LoongArch: Drop unused parse_r and parse_v macros

When building with CONFIG_LTO_CLANG_FULL, there are several errors due
to the way that parse_r is defined with an __asm__ statement in a
header:

  ld.lld: error: ld-temp.o <inline asm>:105:1: macro 'parse_r' is already defined
  .macro  parse_r var r
  ^

This was an issue for arch/mips as well, which was resolved by commit
67512a8cf5a7 ("MIPS: Avoid macro redefinitions").

However, parse_r is unused in arch/loongarch after commit 83d8b38967d2
("LoongArch: Simplify the invtlb wrappers"), so doing the same change
does not make much sense now. Just remove parse_r (and parse_v, which
is also unused) to resolve the redefinition error. If it needs to be
brought back due to an actual use, it should be brought back with the
same changes as the aforementioned arch/mips commit.

Closes: https://github.com/ClangBuiltLinux/linux/issues/1924
Reviewed-by: WANG Xuerui <git@xen0n.name>
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/asmmacro.h  | 107 -------------------------
 arch/loongarch/include/asm/loongarch.h |  43 ----------
 2 files changed, 150 deletions(-)

diff --git a/arch/loongarch/include/asm/asmmacro.h b/arch/loongarch/include/asm/asmmacro.h
index 79e1d53fea89..af542a8d847f 100644
--- a/arch/loongarch/include/asm/asmmacro.h
+++ b/arch/loongarch/include/asm/asmmacro.h
@@ -10,113 +10,6 @@
 #include <asm/fpregdef.h>
 #include <asm/loongarch.h>
 
-	.macro	parse_v var val
-	\var	= \val
-	.endm
-
-	.macro	parse_r var r
-	\var	= -1
-	.ifc	\r, $r0
-	\var	= 0
-	.endif
-	.ifc	\r, $r1
-	\var	= 1
-	.endif
-	.ifc	\r, $r2
-	\var	= 2
-	.endif
-	.ifc	\r, $r3
-	\var	= 3
-	.endif
-	.ifc	\r, $r4
-	\var	= 4
-	.endif
-	.ifc	\r, $r5
-	\var	= 5
-	.endif
-	.ifc	\r, $r6
-	\var	= 6
-	.endif
-	.ifc	\r, $r7
-	\var	= 7
-	.endif
-	.ifc	\r, $r8
-	\var	= 8
-	.endif
-	.ifc	\r, $r9
-	\var	= 9
-	.endif
-	.ifc	\r, $r10
-	\var	= 10
-	.endif
-	.ifc	\r, $r11
-	\var	= 11
-	.endif
-	.ifc	\r, $r12
-	\var	= 12
-	.endif
-	.ifc	\r, $r13
-	\var	= 13
-	.endif
-	.ifc	\r, $r14
-	\var	= 14
-	.endif
-	.ifc	\r, $r15
-	\var	= 15
-	.endif
-	.ifc	\r, $r16
-	\var	= 16
-	.endif
-	.ifc	\r, $r17
-	\var	= 17
-	.endif
-	.ifc	\r, $r18
-	\var	= 18
-	.endif
-	.ifc	\r, $r19
-	\var	= 19
-	.endif
-	.ifc	\r, $r20
-	\var	= 20
-	.endif
-	.ifc	\r, $r21
-	\var	= 21
-	.endif
-	.ifc	\r, $r22
-	\var	= 22
-	.endif
-	.ifc	\r, $r23
-	\var	= 23
-	.endif
-	.ifc	\r, $r24
-	\var	= 24
-	.endif
-	.ifc	\r, $r25
-	\var	= 25
-	.endif
-	.ifc	\r, $r26
-	\var	= 26
-	.endif
-	.ifc	\r, $r27
-	\var	= 27
-	.endif
-	.ifc	\r, $r28
-	\var	= 28
-	.endif
-	.ifc	\r, $r29
-	\var	= 29
-	.endif
-	.ifc	\r, $r30
-	\var	= 30
-	.endif
-	.ifc	\r, $r31
-	\var	= 31
-	.endif
-	.iflt	\var
-	.error	"Unable to parse register name \r"
-	.endif
-	.endm
-
 	.macro	cpu_save_nonscratch thread
 	stptr.d	s0, \thread, THREAD_REG23
 	stptr.d	s1, \thread, THREAD_REG24
diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h
index 10748a20a2ab..a500efe0fd92 100644
--- a/arch/loongarch/include/asm/loongarch.h
+++ b/arch/loongarch/include/asm/loongarch.h
@@ -12,49 +12,6 @@
 #ifndef __ASSEMBLY__
 #include <larchintrin.h>
 
-/*
- * parse_r var, r - Helper assembler macro for parsing register names.
- *
- * This converts the register name in $n form provided in \r to the
- * corresponding register number, which is assigned to the variable \var. It is
- * needed to allow explicit encoding of instructions in inline assembly where
- * registers are chosen by the compiler in $n form, allowing us to avoid using
- * fixed register numbers.
- *
- * It also allows newer instructions (not implemented by the assembler) to be
- * transparently implemented using assembler macros, instead of needing separate
- * cases depending on toolchain support.
- *
- * Simple usage example:
- * __asm__ __volatile__("parse_r addr, %0\n\t"
- *			"#invtlb op, 0, %0\n\t"
- *			".word ((0x6498000) | (addr << 10) | (0 << 5) | op)"
- *			: "=r" (status);
- */
-
-/* Match an individual register number and assign to \var */
-#define _IFC_REG(n)				\
-	".ifc	\\r, $r" #n "\n\t"		\
-	"\\var	= " #n "\n\t"			\
-	".endif\n\t"
-
-__asm__(".macro	parse_r var r\n\t"
-	"\\var	= -1\n\t"
-	_IFC_REG(0)  _IFC_REG(1)  _IFC_REG(2)  _IFC_REG(3)
-	_IFC_REG(4)  _IFC_REG(5)  _IFC_REG(6)  _IFC_REG(7)
-	_IFC_REG(8)  _IFC_REG(9)  _IFC_REG(10) _IFC_REG(11)
-	_IFC_REG(12) _IFC_REG(13) _IFC_REG(14) _IFC_REG(15)
-	_IFC_REG(16) _IFC_REG(17) _IFC_REG(18) _IFC_REG(19)
-	_IFC_REG(20) _IFC_REG(21) _IFC_REG(22) _IFC_REG(23)
-	_IFC_REG(24) _IFC_REG(25) _IFC_REG(26) _IFC_REG(27)
-	_IFC_REG(28) _IFC_REG(29) _IFC_REG(30) _IFC_REG(31)
-	".iflt	\\var\n\t"
-	".error	\"Unable to parse register name \\r\"\n\t"
-	".endif\n\t"
-	".endm");
-
-#undef _IFC_REG
-
 /* CPUCFG */
 #define read_cpucfg(reg) __cpucfg(reg)
 

From 303be4b33562a5b689261ced1616bf16ad49efa7 Mon Sep 17 00:00:00 2001
From: Hongchen Zhang <zhanghongchen@loongson.cn>
Date: Wed, 6 Sep 2023 22:53:09 +0800
Subject: [PATCH 1111/1189] LoongArch: mm: Add p?d_leaf() definitions

When I do LTP test, LTP test case ksm06 caused panic at
	break_ksm_pmd_entry
	  -> pmd_leaf (Huge page table but False)
	  -> pte_present (panic)

The reason is pmd_leaf() is not defined, So like commit 501b81046701
("mips: mm: add p?d_leaf() definitions") add p?d_leaf() definition for
LoongArch.

Fixes: 09cfefb7fa70 ("LoongArch: Add memory management")
Cc: stable@vger.kernel.org
Acked-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Hongchen Zhang <zhanghongchen@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/pgtable.h | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h
index 38afeb7dd58b..0ac6afa4a825 100644
--- a/arch/loongarch/include/asm/pgtable.h
+++ b/arch/loongarch/include/asm/pgtable.h
@@ -593,6 +593,9 @@ static inline long pmd_protnone(pmd_t pmd)
 }
 #endif /* CONFIG_NUMA_BALANCING */
 
+#define pmd_leaf(pmd)		((pmd_val(pmd) & _PAGE_HUGE) != 0)
+#define pud_leaf(pud)		((pud_val(pud) & _PAGE_HUGE) != 0)
+
 /*
  * We provide our own get_unmapped area to cope with the virtual aliasing
  * constraints placed on us by the cache architecture.

From ad3ff105611b9b06e16ae57e97b48916ff93dd46 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Wed, 6 Sep 2023 22:53:09 +0800
Subject: [PATCH 1112/1189] LoongArch: Remove shm_align_mask and use SHMLBA
 instead

Both shm_align_mask and SHMLBA want to avoid cache alias. But they are
inconsistent: shm_align_mask is (PAGE_SIZE - 1) while SHMLBA is SZ_64K,
but PAGE_SIZE is not always equal to SZ_64K.

This may cause problems when shmat() twice. Fix this problem by removing
shm_align_mask and using SHMLBA (strictly SHMLBA - 1) instead.

Reported-by: Jiantao Shan <shanjiantao@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/mm/cache.c |  1 -
 arch/loongarch/mm/mmap.c  | 13 ++++++-------
 2 files changed, 6 insertions(+), 8 deletions(-)

diff --git a/arch/loongarch/mm/cache.c b/arch/loongarch/mm/cache.c
index 72685a48eaf0..6be04d36ca07 100644
--- a/arch/loongarch/mm/cache.c
+++ b/arch/loongarch/mm/cache.c
@@ -156,7 +156,6 @@ void cpu_cache_init(void)
 
 	current_cpu_data.cache_leaves_present = leaf;
 	current_cpu_data.options |= LOONGARCH_CPU_PREFETCH;
-	shm_align_mask = PAGE_SIZE - 1;
 }
 
 static const pgprot_t protection_map[16] = {
diff --git a/arch/loongarch/mm/mmap.c b/arch/loongarch/mm/mmap.c
index fbe1a4856fc4..a9630a81b38a 100644
--- a/arch/loongarch/mm/mmap.c
+++ b/arch/loongarch/mm/mmap.c
@@ -8,12 +8,11 @@
 #include <linux/mm.h>
 #include <linux/mman.h>
 
-unsigned long shm_align_mask = PAGE_SIZE - 1;	/* Sane caches */
-EXPORT_SYMBOL(shm_align_mask);
+#define SHM_ALIGN_MASK	(SHMLBA - 1)
 
-#define COLOUR_ALIGN(addr, pgoff)				\
-	((((addr) + shm_align_mask) & ~shm_align_mask) +	\
-	 (((pgoff) << PAGE_SHIFT) & shm_align_mask))
+#define COLOUR_ALIGN(addr, pgoff)			\
+	((((addr) + SHM_ALIGN_MASK) & ~SHM_ALIGN_MASK)	\
+	 + (((pgoff) << PAGE_SHIFT) & SHM_ALIGN_MASK))
 
 enum mmap_allocation_direction {UP, DOWN};
 
@@ -40,7 +39,7 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp,
 		 * cache aliasing constraints.
 		 */
 		if ((flags & MAP_SHARED) &&
-		    ((addr - (pgoff << PAGE_SHIFT)) & shm_align_mask))
+		    ((addr - (pgoff << PAGE_SHIFT)) & SHM_ALIGN_MASK))
 			return -EINVAL;
 		return addr;
 	}
@@ -63,7 +62,7 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp,
 	}
 
 	info.length = len;
-	info.align_mask = do_color_align ? (PAGE_MASK & shm_align_mask) : 0;
+	info.align_mask = do_color_align ? (PAGE_MASK & SHM_ALIGN_MASK) : 0;
 	info.align_offset = pgoff << PAGE_SHIFT;
 
 	if (dir == DOWN) {

From f33efa905ce4839d9d1f20b559db9c2e8a39e059 Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Wed, 6 Sep 2023 22:53:09 +0800
Subject: [PATCH 1113/1189] LoongArch: Code improvements in function
 pcpu_populate_pte()

Do some code improvements in function pcpu_populate_pte():
1. Add memory allocation failure handling;
2. Replace pgd_populate() with p4d_populate(), it will be useful if
   there are four-level page tables.

Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/numa.c | 28 +++++++++++++++-------------
 1 file changed, 15 insertions(+), 13 deletions(-)

diff --git a/arch/loongarch/kernel/numa.c b/arch/loongarch/kernel/numa.c
index 708665895b47..4844ad2d7712 100644
--- a/arch/loongarch/kernel/numa.c
+++ b/arch/loongarch/kernel/numa.c
@@ -73,32 +73,34 @@ void __init pcpu_populate_pte(unsigned long addr)
 	pmd_t *pmd;
 
 	if (p4d_none(*p4d)) {
-		pud_t *new;
-
-		new = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-		pgd_populate(&init_mm, pgd, new);
+		pud = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+		if (!pud)
+			panic("%s: Failed to allocate memory\n", __func__);
+		p4d_populate(&init_mm, p4d, pud);
 #ifndef __PAGETABLE_PUD_FOLDED
-		pud_init(new);
+		pud_init(pud);
 #endif
 	}
 
 	pud = pud_offset(p4d, addr);
 	if (pud_none(*pud)) {
-		pmd_t *new;
-
-		new = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-		pud_populate(&init_mm, pud, new);
+		pmd = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+		if (!pmd)
+			panic("%s: Failed to allocate memory\n", __func__);
+		pud_populate(&init_mm, pud, pmd);
 #ifndef __PAGETABLE_PMD_FOLDED
-		pmd_init(new);
+		pmd_init(pmd);
 #endif
 	}
 
 	pmd = pmd_offset(pud, addr);
 	if (!pmd_present(*pmd)) {
-		pte_t *new;
+		pte_t *pte;
 
-		new = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-		pmd_populate_kernel(&init_mm, pmd, new);
+		pte = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+		if (!pte)
+			panic("%s: Failed to allocate memory\n", __func__);
+		pmd_populate_kernel(&init_mm, pmd, pte);
 	}
 }
 

From 2bb20d2926a8ea991386315aa8017990ef7beb6a Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Wed, 6 Sep 2023 22:53:09 +0800
Subject: [PATCH 1114/1189] LoongArch: mm: Introduce unified function
 populate_kernel_pte()

Function pcpu_populate_pte() and fixmap_pte() are similar, they populate
one page from kernel address space. And there is confusion between pgd
and p4d in the function fixmap_pte(), such as pgd_none() always returns
zero. This patch introduces a unified function populate_kernel_pte() and
then replaces pcpu_populate_pte() and fixmap_pte().

Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/pgalloc.h |  1 +
 arch/loongarch/kernel/numa.c         | 36 +----------------------
 arch/loongarch/mm/init.c             | 43 ++++++++++++++--------------
 3 files changed, 23 insertions(+), 57 deletions(-)

diff --git a/arch/loongarch/include/asm/pgalloc.h b/arch/loongarch/include/asm/pgalloc.h
index af1d1e4a6965..ca17b573dba6 100644
--- a/arch/loongarch/include/asm/pgalloc.h
+++ b/arch/loongarch/include/asm/pgalloc.h
@@ -91,4 +91,5 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
 
 #endif /* __PAGETABLE_PUD_FOLDED */
 
+extern pte_t * __init populate_kernel_pte(unsigned long addr);
 #endif /* _ASM_PGALLOC_H */
diff --git a/arch/loongarch/kernel/numa.c b/arch/loongarch/kernel/numa.c
index 4844ad2d7712..cb00804826f7 100644
--- a/arch/loongarch/kernel/numa.c
+++ b/arch/loongarch/kernel/numa.c
@@ -67,41 +67,7 @@ static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
 
 void __init pcpu_populate_pte(unsigned long addr)
 {
-	pgd_t *pgd = pgd_offset_k(addr);
-	p4d_t *p4d = p4d_offset(pgd, addr);
-	pud_t *pud;
-	pmd_t *pmd;
-
-	if (p4d_none(*p4d)) {
-		pud = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-		if (!pud)
-			panic("%s: Failed to allocate memory\n", __func__);
-		p4d_populate(&init_mm, p4d, pud);
-#ifndef __PAGETABLE_PUD_FOLDED
-		pud_init(pud);
-#endif
-	}
-
-	pud = pud_offset(p4d, addr);
-	if (pud_none(*pud)) {
-		pmd = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-		if (!pmd)
-			panic("%s: Failed to allocate memory\n", __func__);
-		pud_populate(&init_mm, pud, pmd);
-#ifndef __PAGETABLE_PMD_FOLDED
-		pmd_init(pmd);
-#endif
-	}
-
-	pmd = pmd_offset(pud, addr);
-	if (!pmd_present(*pmd)) {
-		pte_t *pte;
-
-		pte = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-		if (!pte)
-			panic("%s: Failed to allocate memory\n", __func__);
-		pmd_populate_kernel(&init_mm, pmd, pte);
-	}
+	populate_kernel_pte(addr);
 }
 
 void __init setup_per_cpu_areas(void)
diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c
index 3b7d8129570b..0f1dee285da2 100644
--- a/arch/loongarch/mm/init.c
+++ b/arch/loongarch/mm/init.c
@@ -191,43 +191,42 @@ void vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *al
 #endif
 #endif
 
-static pte_t *fixmap_pte(unsigned long addr)
+pte_t * __init populate_kernel_pte(unsigned long addr)
 {
-	pgd_t *pgd;
-	p4d_t *p4d;
+	pgd_t *pgd = pgd_offset_k(addr);
+	p4d_t *p4d = p4d_offset(pgd, addr);
 	pud_t *pud;
 	pmd_t *pmd;
 
-	pgd = pgd_offset_k(addr);
-	p4d = p4d_offset(pgd, addr);
-
-	if (pgd_none(*pgd)) {
-		pud_t *new __maybe_unused;
-
-		new = memblock_alloc_low(PAGE_SIZE, PAGE_SIZE);
-		pgd_populate(&init_mm, pgd, new);
+	if (p4d_none(*p4d)) {
+		pud = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+		if (!pud)
+			panic("%s: Failed to allocate memory\n", __func__);
+		p4d_populate(&init_mm, p4d, pud);
 #ifndef __PAGETABLE_PUD_FOLDED
-		pud_init(new);
+		pud_init(pud);
 #endif
 	}
 
 	pud = pud_offset(p4d, addr);
 	if (pud_none(*pud)) {
-		pmd_t *new __maybe_unused;
-
-		new = memblock_alloc_low(PAGE_SIZE, PAGE_SIZE);
-		pud_populate(&init_mm, pud, new);
+		pmd = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+		if (!pmd)
+			panic("%s: Failed to allocate memory\n", __func__);
+		pud_populate(&init_mm, pud, pmd);
 #ifndef __PAGETABLE_PMD_FOLDED
-		pmd_init(new);
+		pmd_init(pmd);
 #endif
 	}
 
 	pmd = pmd_offset(pud, addr);
-	if (pmd_none(*pmd)) {
-		pte_t *new __maybe_unused;
+	if (!pmd_present(*pmd)) {
+		pte_t *pte;
 
-		new = memblock_alloc_low(PAGE_SIZE, PAGE_SIZE);
-		pmd_populate_kernel(&init_mm, pmd, new);
+		pte = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+		if (!pte)
+			panic("%s: Failed to allocate memory\n", __func__);
+		pmd_populate_kernel(&init_mm, pmd, pte);
 	}
 
 	return pte_offset_kernel(pmd, addr);
@@ -241,7 +240,7 @@ void __init __set_fixmap(enum fixed_addresses idx,
 
 	BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses);
 
-	ptep = fixmap_pte(addr);
+	ptep = populate_kernel_pte(addr);
 	if (!pte_none(*ptep)) {
 		pte_ERROR(*ptep);
 		return;

From 0921af6ccfb37dc2d6aefcf744333c14e7ca739d Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Wed, 6 Sep 2023 22:53:10 +0800
Subject: [PATCH 1115/1189] LoongArch: Use static defined zero page rather than
 allocated

On LoongArch system, there is only one page needed for zero page (no
cache synonyms), and there is no COLOR_ZERO_PAGE, so zero_page_mask is
useless and the macro __HAVE_COLOR_ZERO_PAGE is not necessary.

Like other popular architectures, It is simpler to define the zero page
in kernel BSS code segment rather than dynamically allocate.

Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/mmzone.h  |  2 --
 arch/loongarch/include/asm/pgtable.h |  7 ++-----
 arch/loongarch/kernel/numa.c         |  1 -
 arch/loongarch/mm/init.c             | 28 +---------------------------
 4 files changed, 3 insertions(+), 35 deletions(-)

diff --git a/arch/loongarch/include/asm/mmzone.h b/arch/loongarch/include/asm/mmzone.h
index fe67d0b4b33d..2b9a90727e19 100644
--- a/arch/loongarch/include/asm/mmzone.h
+++ b/arch/loongarch/include/asm/mmzone.h
@@ -13,6 +13,4 @@ extern struct pglist_data *node_data[];
 
 #define NODE_DATA(nid)	(node_data[(nid)])
 
-extern void setup_zero_pages(void);
-
 #endif /* _ASM_MMZONE_H_ */
diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h
index 0ac6afa4a825..7699af049443 100644
--- a/arch/loongarch/include/asm/pgtable.h
+++ b/arch/loongarch/include/asm/pgtable.h
@@ -70,12 +70,9 @@ struct vm_area_struct;
  * for zero-mapped memory areas etc..
  */
 
-extern unsigned long empty_zero_page;
-extern unsigned long zero_page_mask;
+extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 
-#define ZERO_PAGE(vaddr) \
-	(virt_to_page((void *)(empty_zero_page + (((unsigned long)(vaddr)) & zero_page_mask))))
-#define __HAVE_COLOR_ZERO_PAGE
+#define ZERO_PAGE(vaddr)	virt_to_page(empty_zero_page)
 
 /*
  * TLB refill handlers may also map the vmalloc area into xkvrange.
diff --git a/arch/loongarch/kernel/numa.c b/arch/loongarch/kernel/numa.c
index cb00804826f7..c7d33c489e04 100644
--- a/arch/loongarch/kernel/numa.c
+++ b/arch/loongarch/kernel/numa.c
@@ -438,7 +438,6 @@ void __init mem_init(void)
 {
 	high_memory = (void *) __va(get_num_physpages() << PAGE_SHIFT);
 	memblock_free_all();
-	setup_zero_pages();	/* This comes from node 0 */
 }
 
 int pcibus_to_node(struct pci_bus *bus)
diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c
index 0f1dee285da2..f3fe8c06ba4d 100644
--- a/arch/loongarch/mm/init.c
+++ b/arch/loongarch/mm/init.c
@@ -35,33 +35,8 @@
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
 
-/*
- * We have up to 8 empty zeroed pages so we can map one of the right colour
- * when needed.	 Since page is never written to after the initialization we
- * don't have to care about aliases on other CPUs.
- */
-unsigned long empty_zero_page, zero_page_mask;
+unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss;
 EXPORT_SYMBOL(empty_zero_page);
-EXPORT_SYMBOL(zero_page_mask);
-
-void setup_zero_pages(void)
-{
-	unsigned int order, i;
-	struct page *page;
-
-	order = 0;
-
-	empty_zero_page = __get_free_pages(GFP_KERNEL | __GFP_ZERO, order);
-	if (!empty_zero_page)
-		panic("Oh boy, that early out of memory?");
-
-	page = virt_to_page((void *)empty_zero_page);
-	split_page(page, order);
-	for (i = 0; i < (1 << order); i++, page++)
-		mark_page_reserved(page);
-
-	zero_page_mask = ((PAGE_SIZE << order) - 1) & PAGE_MASK;
-}
 
 void copy_user_highpage(struct page *to, struct page *from,
 	unsigned long vaddr, struct vm_area_struct *vma)
@@ -106,7 +81,6 @@ void __init mem_init(void)
 	high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT);
 
 	memblock_free_all();
-	setup_zero_pages();	/* Setup zeroed pages.  */
 }
 #endif /* !CONFIG_NUMA */
 

From 937f65935950a0346292120acc5d98033f90e61c Mon Sep 17 00:00:00 2001
From: Weihao Li <liweihao@loongson.cn>
Date: Wed, 6 Sep 2023 22:53:10 +0800
Subject: [PATCH 1116/1189] LoongArch: Adjust {copy, clear}_user exception
 handler behavior

The {copy, clear}_user function should returns number of bytes that
could not be {copied, cleared}. So, try to {copy, clear} byte by byte
when ld.{d,w,h} and st.{d,w,h} trapped into an exception.

Reviewed-by: WANG Rui <wangrui@loongson.cn>
Signed-off-by: Weihao Li <liweihao@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/lib/clear_user.S |  87 ++++++++---------
 arch/loongarch/lib/copy_user.S  | 161 ++++++++++++++++----------------
 2 files changed, 127 insertions(+), 121 deletions(-)

diff --git a/arch/loongarch/lib/clear_user.S b/arch/loongarch/lib/clear_user.S
index 0790eadce166..be741544e62b 100644
--- a/arch/loongarch/lib/clear_user.S
+++ b/arch/loongarch/lib/clear_user.S
@@ -11,19 +11,6 @@
 #include <asm/cpu.h>
 #include <asm/regdef.h>
 
-.irp to, 0, 1, 2, 3, 4, 5, 6, 7
-.L_fixup_handle_\to\():
-	sub.d	a0, a2, a0
-	addi.d	a0, a0, (\to) * (-8)
-	jr	ra
-.endr
-
-.irp to, 0, 2, 4
-.L_fixup_handle_s\to\():
-	addi.d	a0, a1, -\to
-	jr	ra
-.endr
-
 SYM_FUNC_START(__clear_user)
 	/*
 	 * Some CPUs support hardware unaligned access
@@ -51,7 +38,7 @@ SYM_FUNC_START(__clear_user_generic)
 2:	move	a0, a1
 	jr	ra
 
-	_asm_extable 1b, .L_fixup_handle_s0
+	_asm_extable 1b, 2b
 SYM_FUNC_END(__clear_user_generic)
 
 /*
@@ -173,33 +160,47 @@ SYM_FUNC_START(__clear_user_fast)
 	jr	ra
 
 	/* fixup and ex_table */
-	_asm_extable 0b, .L_fixup_handle_0
-	_asm_extable 1b, .L_fixup_handle_0
-	_asm_extable 2b, .L_fixup_handle_1
-	_asm_extable 3b, .L_fixup_handle_2
-	_asm_extable 4b, .L_fixup_handle_3
-	_asm_extable 5b, .L_fixup_handle_4
-	_asm_extable 6b, .L_fixup_handle_5
-	_asm_extable 7b, .L_fixup_handle_6
-	_asm_extable 8b, .L_fixup_handle_7
-	_asm_extable 9b, .L_fixup_handle_0
-	_asm_extable 10b, .L_fixup_handle_1
-	_asm_extable 11b, .L_fixup_handle_2
-	_asm_extable 12b, .L_fixup_handle_3
-	_asm_extable 13b, .L_fixup_handle_0
-	_asm_extable 14b, .L_fixup_handle_1
-	_asm_extable 15b, .L_fixup_handle_0
-	_asm_extable 16b, .L_fixup_handle_0
-	_asm_extable 17b, .L_fixup_handle_s0
-	_asm_extable 18b, .L_fixup_handle_s0
-	_asm_extable 19b, .L_fixup_handle_s0
-	_asm_extable 20b, .L_fixup_handle_s2
-	_asm_extable 21b, .L_fixup_handle_s0
-	_asm_extable 22b, .L_fixup_handle_s0
-	_asm_extable 23b, .L_fixup_handle_s4
-	_asm_extable 24b, .L_fixup_handle_s0
-	_asm_extable 25b, .L_fixup_handle_s4
-	_asm_extable 26b, .L_fixup_handle_s0
-	_asm_extable 27b, .L_fixup_handle_s4
-	_asm_extable 28b, .L_fixup_handle_s0
+.Llarge_fixup:
+	sub.d	a1, a2, a0
+
+.Lsmall_fixup:
+29:	st.b	zero, a0, 0
+	addi.d	a0, a0, 1
+	addi.d	a1, a1, -1
+	bgt	a1, zero, 29b
+
+.Lexit:
+	move	a0, a1
+	jr	ra
+
+	_asm_extable 0b, .Lsmall_fixup
+	_asm_extable 1b, .Llarge_fixup
+	_asm_extable 2b, .Llarge_fixup
+	_asm_extable 3b, .Llarge_fixup
+	_asm_extable 4b, .Llarge_fixup
+	_asm_extable 5b, .Llarge_fixup
+	_asm_extable 6b, .Llarge_fixup
+	_asm_extable 7b, .Llarge_fixup
+	_asm_extable 8b, .Llarge_fixup
+	_asm_extable 9b, .Llarge_fixup
+	_asm_extable 10b, .Llarge_fixup
+	_asm_extable 11b, .Llarge_fixup
+	_asm_extable 12b, .Llarge_fixup
+	_asm_extable 13b, .Llarge_fixup
+	_asm_extable 14b, .Llarge_fixup
+	_asm_extable 15b, .Llarge_fixup
+	_asm_extable 16b, .Llarge_fixup
+	_asm_extable 17b, .Lexit
+	_asm_extable 18b, .Lsmall_fixup
+	_asm_extable 19b, .Lsmall_fixup
+	_asm_extable 20b, .Lsmall_fixup
+	_asm_extable 21b, .Lsmall_fixup
+	_asm_extable 22b, .Lsmall_fixup
+	_asm_extable 23b, .Lsmall_fixup
+	_asm_extable 24b, .Lsmall_fixup
+	_asm_extable 25b, .Lsmall_fixup
+	_asm_extable 26b, .Lsmall_fixup
+	_asm_extable 27b, .Lsmall_fixup
+	_asm_extable 28b, .Lsmall_fixup
+	_asm_extable 29b, .Lexit
 SYM_FUNC_END(__clear_user_fast)
diff --git a/arch/loongarch/lib/copy_user.S b/arch/loongarch/lib/copy_user.S
index bfe3d2793d00..feec3d362803 100644
--- a/arch/loongarch/lib/copy_user.S
+++ b/arch/loongarch/lib/copy_user.S
@@ -11,19 +11,6 @@
 #include <asm/cpu.h>
 #include <asm/regdef.h>
 
-.irp to, 0, 1, 2, 3, 4, 5, 6, 7
-.L_fixup_handle_\to\():
-	sub.d	a0, a2, a0
-	addi.d	a0, a0, (\to) * (-8)
-	jr	ra
-.endr
-
-.irp to, 0, 2, 4
-.L_fixup_handle_s\to\():
-	addi.d	a0, a2, -\to
-	jr	ra
-.endr
-
 SYM_FUNC_START(__copy_user)
 	/*
 	 * Some CPUs support hardware unaligned access
@@ -54,8 +41,8 @@ SYM_FUNC_START(__copy_user_generic)
 3:	move	a0, a2
 	jr	ra
 
-	_asm_extable 1b, .L_fixup_handle_s0
-	_asm_extable 2b, .L_fixup_handle_s0
+	_asm_extable 1b, 3b
+	_asm_extable 2b, 3b
 SYM_FUNC_END(__copy_user_generic)
 
 /*
@@ -69,10 +56,10 @@ SYM_FUNC_START(__copy_user_fast)
 	sltui	t0, a2, 9
 	bnez	t0, .Lsmall
 
-	add.d	a3, a1, a2
-	add.d	a2, a0, a2
 0:	ld.d	t0, a1, 0
 1:	st.d	t0, a0, 0
+	add.d	a3, a1, a2
+	add.d	a2, a0, a2
 
 	/* align up destination address */
 	andi	t1, a0, 7
@@ -94,7 +81,6 @@ SYM_FUNC_START(__copy_user_fast)
 7:	ld.d	t5, a1, 40
 8:	ld.d	t6, a1, 48
 9:	ld.d	t7, a1, 56
-	addi.d	a1, a1, 64
 10:	st.d	t0, a0, 0
 11:	st.d	t1, a0, 8
 12:	st.d	t2, a0, 16
@@ -103,6 +89,7 @@ SYM_FUNC_START(__copy_user_fast)
 15:	st.d	t5, a0, 40
 16:	st.d	t6, a0, 48
 17:	st.d	t7, a0, 56
+	addi.d	a1, a1, 64
 	addi.d	a0, a0, 64
 	bltu	a1, a4, .Lloop64
 
@@ -114,11 +101,11 @@ SYM_FUNC_START(__copy_user_fast)
 19:	ld.d	t1, a1, 8
 20:	ld.d	t2, a1, 16
 21:	ld.d	t3, a1, 24
-	addi.d	a1, a1, 32
 22:	st.d	t0, a0, 0
 23:	st.d	t1, a0, 8
 24:	st.d	t2, a0, 16
 25:	st.d	t3, a0, 24
+	addi.d	a1, a1, 32
 	addi.d	a0, a0, 32
 
 .Llt32:
@@ -126,9 +113,9 @@ SYM_FUNC_START(__copy_user_fast)
 	bgeu	a1, a4, .Llt16
 26:	ld.d	t0, a1, 0
 27:	ld.d	t1, a1, 8
-	addi.d	a1, a1, 16
 28:	st.d	t0, a0, 0
 29:	st.d	t1, a0, 8
+	addi.d	a1, a1, 16
 	addi.d	a0, a0, 16
 
 .Llt16:
@@ -136,6 +123,7 @@ SYM_FUNC_START(__copy_user_fast)
 	bgeu	a1, a4, .Llt8
 30:	ld.d	t0, a1, 0
 31:	st.d	t0, a0, 0
+	addi.d	a1, a1, 8
 	addi.d	a0, a0, 8
 
 .Llt8:
@@ -214,62 +202,79 @@ SYM_FUNC_START(__copy_user_fast)
 	jr	ra
 
 	/* fixup and ex_table */
-	_asm_extable 0b, .L_fixup_handle_0
-	_asm_extable 1b, .L_fixup_handle_0
-	_asm_extable 2b, .L_fixup_handle_0
-	_asm_extable 3b, .L_fixup_handle_0
-	_asm_extable 4b, .L_fixup_handle_0
-	_asm_extable 5b, .L_fixup_handle_0
-	_asm_extable 6b, .L_fixup_handle_0
-	_asm_extable 7b, .L_fixup_handle_0
-	_asm_extable 8b, .L_fixup_handle_0
-	_asm_extable 9b, .L_fixup_handle_0
-	_asm_extable 10b, .L_fixup_handle_0
-	_asm_extable 11b, .L_fixup_handle_1
-	_asm_extable 12b, .L_fixup_handle_2
-	_asm_extable 13b, .L_fixup_handle_3
-	_asm_extable 14b, .L_fixup_handle_4
-	_asm_extable 15b, .L_fixup_handle_5
-	_asm_extable 16b, .L_fixup_handle_6
-	_asm_extable 17b, .L_fixup_handle_7
-	_asm_extable 18b, .L_fixup_handle_0
-	_asm_extable 19b, .L_fixup_handle_0
-	_asm_extable 20b, .L_fixup_handle_0
-	_asm_extable 21b, .L_fixup_handle_0
-	_asm_extable 22b, .L_fixup_handle_0
-	_asm_extable 23b, .L_fixup_handle_1
-	_asm_extable 24b, .L_fixup_handle_2
-	_asm_extable 25b, .L_fixup_handle_3
-	_asm_extable 26b, .L_fixup_handle_0
-	_asm_extable 27b, .L_fixup_handle_0
-	_asm_extable 28b, .L_fixup_handle_0
-	_asm_extable 29b, .L_fixup_handle_1
-	_asm_extable 30b, .L_fixup_handle_0
-	_asm_extable 31b, .L_fixup_handle_0
-	_asm_extable 32b, .L_fixup_handle_0
-	_asm_extable 33b, .L_fixup_handle_0
-	_asm_extable 34b, .L_fixup_handle_s0
-	_asm_extable 35b, .L_fixup_handle_s0
-	_asm_extable 36b, .L_fixup_handle_s0
-	_asm_extable 37b, .L_fixup_handle_s0
-	_asm_extable 38b, .L_fixup_handle_s0
-	_asm_extable 39b, .L_fixup_handle_s0
-	_asm_extable 40b, .L_fixup_handle_s0
-	_asm_extable 41b, .L_fixup_handle_s2
-	_asm_extable 42b, .L_fixup_handle_s0
-	_asm_extable 43b, .L_fixup_handle_s0
-	_asm_extable 44b, .L_fixup_handle_s0
-	_asm_extable 45b, .L_fixup_handle_s0
-	_asm_extable 46b, .L_fixup_handle_s0
-	_asm_extable 47b, .L_fixup_handle_s4
-	_asm_extable 48b, .L_fixup_handle_s0
-	_asm_extable 49b, .L_fixup_handle_s0
-	_asm_extable 50b, .L_fixup_handle_s0
-	_asm_extable 51b, .L_fixup_handle_s4
-	_asm_extable 52b, .L_fixup_handle_s0
-	_asm_extable 53b, .L_fixup_handle_s0
-	_asm_extable 54b, .L_fixup_handle_s0
-	_asm_extable 55b, .L_fixup_handle_s4
-	_asm_extable 56b, .L_fixup_handle_s0
-	_asm_extable 57b, .L_fixup_handle_s0
+.Llarge_fixup:
+	sub.d	a2, a2, a0
+
+.Lsmall_fixup:
+58:	ld.b	t0, a1, 0
+59:	st.b	t0, a0, 0
+	addi.d	a0, a0, 1
+	addi.d	a1, a1, 1
+	addi.d	a2, a2, -1
+	bgt	a2, zero, 58b
+
+.Lexit:
+	move	a0, a2
+	jr	ra
+
+	_asm_extable 0b, .Lsmall_fixup
+	_asm_extable 1b, .Lsmall_fixup
+	_asm_extable 2b, .Llarge_fixup
+	_asm_extable 3b, .Llarge_fixup
+	_asm_extable 4b, .Llarge_fixup
+	_asm_extable 5b, .Llarge_fixup
+	_asm_extable 6b, .Llarge_fixup
+	_asm_extable 7b, .Llarge_fixup
+	_asm_extable 8b, .Llarge_fixup
+	_asm_extable 9b, .Llarge_fixup
+	_asm_extable 10b, .Llarge_fixup
+	_asm_extable 11b, .Llarge_fixup
+	_asm_extable 12b, .Llarge_fixup
+	_asm_extable 13b, .Llarge_fixup
+	_asm_extable 14b, .Llarge_fixup
+	_asm_extable 15b, .Llarge_fixup
+	_asm_extable 16b, .Llarge_fixup
+	_asm_extable 17b, .Llarge_fixup
+	_asm_extable 18b, .Llarge_fixup
+	_asm_extable 19b, .Llarge_fixup
+	_asm_extable 20b, .Llarge_fixup
+	_asm_extable 21b, .Llarge_fixup
+	_asm_extable 22b, .Llarge_fixup
+	_asm_extable 23b, .Llarge_fixup
+	_asm_extable 24b, .Llarge_fixup
+	_asm_extable 25b, .Llarge_fixup
+	_asm_extable 26b, .Llarge_fixup
+	_asm_extable 27b, .Llarge_fixup
+	_asm_extable 28b, .Llarge_fixup
+	_asm_extable 29b, .Llarge_fixup
+	_asm_extable 30b, .Llarge_fixup
+	_asm_extable 31b, .Llarge_fixup
+	_asm_extable 32b, .Llarge_fixup
+	_asm_extable 33b, .Llarge_fixup
+	_asm_extable 34b, .Lexit
+	_asm_extable 35b, .Lexit
+	_asm_extable 36b, .Lsmall_fixup
+	_asm_extable 37b, .Lsmall_fixup
+	_asm_extable 38b, .Lsmall_fixup
+	_asm_extable 39b, .Lsmall_fixup
+	_asm_extable 40b, .Lsmall_fixup
+	_asm_extable 41b, .Lsmall_fixup
+	_asm_extable 42b, .Lsmall_fixup
+	_asm_extable 43b, .Lsmall_fixup
+	_asm_extable 44b, .Lsmall_fixup
+	_asm_extable 45b, .Lsmall_fixup
+	_asm_extable 46b, .Lsmall_fixup
+	_asm_extable 47b, .Lsmall_fixup
+	_asm_extable 48b, .Lsmall_fixup
+	_asm_extable 49b, .Lsmall_fixup
+	_asm_extable 50b, .Lsmall_fixup
+	_asm_extable 51b, .Lsmall_fixup
+	_asm_extable 52b, .Lsmall_fixup
+	_asm_extable 53b, .Lsmall_fixup
+	_asm_extable 54b, .Lsmall_fixup
+	_asm_extable 55b, .Lsmall_fixup
+	_asm_extable 56b, .Lsmall_fixup
+	_asm_extable 57b, .Lsmall_fixup
+	_asm_extable 58b, .Lexit
+	_asm_extable 59b, .Lexit
 SYM_FUNC_END(__copy_user_fast)

From 8f58c571bf3095278ebda49ce95df5ead27ebb42 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Wed, 6 Sep 2023 22:53:10 +0800
Subject: [PATCH 1117/1189] LoongArch: Define symbol 'fault' as a local label
 in fpu.S

The initial aim is to silence the following objtool warnings:

  arch/loongarch/kernel/fpu.o: warning: objtool: _save_fp_context() falls through to next function fault()
  arch/loongarch/kernel/fpu.o: warning: objtool: _restore_fp_context() falls through to next function fault()
  arch/loongarch/kernel/fpu.o: warning: objtool: _save_lsx_context() falls through to next function fault()
  arch/loongarch/kernel/fpu.o: warning: objtool: _restore_lsx_context() falls through to next function fault()
  arch/loongarch/kernel/fpu.o: warning: objtool: _save_lasx_context() falls through to next function fault()
  arch/loongarch/kernel/fpu.o: warning: objtool: _restore_lasx_context() falls through to next function fault()

Currently, SYM_FUNC_START()/SYM_FUNC_END() defines the symbol 'fault' as
SYM_T_FUNC which is STT_FUNC, the objtool warnings are generated through
the following code:

tools/objtool/include/objtool/check.h:

static inline struct symbol *insn_func(struct instruction *insn)
{
	struct symbol *sym = insn->sym;

	if (sym && sym->type != STT_FUNC)
		sym = NULL;

	return sym;
}

tools/objtool/check.c:

static int validate_branch(struct objtool_file *file, struct symbol *func,
			   struct instruction *insn, struct insn_state state)
{
	...
		if (func && insn_func(insn) && func != insn_func(insn)->pfunc) {
	...
			WARN("%s() falls through to next function %s()",
			     func->name, insn_func(insn)->name);
			return 1;
		}
	...
}

We can see that the fixup can be a local label in the following code:

arch/loongarch/include/asm/asm-extable.h:
	.pushsection	__ex_table, "a";		\
	.balign		4;				\
	.long		((insn) - .);			\
	.long		((fixup) - .);			\
	.short		(type);				\
	.short		(data);				\
	.popsection;

	.macro		_asm_extable, insn, fixup
	__ASM_EXTABLE_RAW(\insn, \fixup, EX_TYPE_FIXUP, 0)
	.endm

Like arch/loongarch/lib/*.S, just define the symbol 'fault' as a local
label in fpu.S.

Before:

$ readelf -s arch/loongarch/kernel/fpu.o | awk -F: /fault/'{print $2}'
 000000000000053c     8 FUNC    GLOBAL DEFAULT    1 fault

After:

$ readelf -s arch/loongarch/kernel/fpu.o | awk -F: /fault/'{print $2}'
 000000000000053c     0 NOTYPE  LOCAL  DEFAULT    1 .L_fpu_fault

Co-developed-by: Youling Tang <tangyouling@loongson.cn>
Signed-off-by: Youling Tang <tangyouling@loongson.cn>
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/fpu.S | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/arch/loongarch/kernel/fpu.S b/arch/loongarch/kernel/fpu.S
index 501094a09f5d..80dccf8e39a7 100644
--- a/arch/loongarch/kernel/fpu.S
+++ b/arch/loongarch/kernel/fpu.S
@@ -22,7 +22,7 @@
 
 	.macro	EX insn, reg, src, offs
 .ex\@:	\insn	\reg, \src, \offs
-	_asm_extable .ex\@, fault
+	_asm_extable .ex\@, .L_fpu_fault
 	.endm
 
 	.macro sc_save_fp base
@@ -514,7 +514,6 @@ SYM_FUNC_START(_restore_lasx_context)
 	jr	ra
 SYM_FUNC_END(_restore_lasx_context)
 
-SYM_FUNC_START(fault)
+.L_fpu_fault:
 	li.w	a0, -EFAULT				# failure
 	jr	ra
-SYM_FUNC_END(fault)

From 2478e4b7593a2a55073a4a6bf23dc885c19befd8 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Wed, 6 Sep 2023 22:53:55 +0800
Subject: [PATCH 1118/1189] LoongArch: Allow usage of LSX/LASX in the kernel

Allow usage of LSX/LASX in the kernel by extending kernel_fpu_begin()
and kernel_fpu_end().

Reviewed-by: WANG Xuerui <git@xen0n.name>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/kfpu.c | 55 +++++++++++++++++++++++++++++++++---
 1 file changed, 51 insertions(+), 4 deletions(-)

diff --git a/arch/loongarch/kernel/kfpu.c b/arch/loongarch/kernel/kfpu.c
index 5c46ae8c6cac..ec5b28e570c9 100644
--- a/arch/loongarch/kernel/kfpu.c
+++ b/arch/loongarch/kernel/kfpu.c
@@ -8,19 +8,40 @@
 #include <asm/fpu.h>
 #include <asm/smp.h>
 
+static unsigned int euen_mask = CSR_EUEN_FPEN;
+
+/*
+ * The critical section between kernel_fpu_begin() and kernel_fpu_end()
+ * is non-reentrant. It is the caller's responsibility to avoid reentrance.
+ * See drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c as an example.
+ */
 static DEFINE_PER_CPU(bool, in_kernel_fpu);
+static DEFINE_PER_CPU(unsigned int, euen_current);
 
 void kernel_fpu_begin(void)
 {
+	unsigned int *euen_curr;
+
 	preempt_disable();
 
 	WARN_ON(this_cpu_read(in_kernel_fpu));
 
 	this_cpu_write(in_kernel_fpu, true);
+	euen_curr = this_cpu_ptr(&euen_current);
 
-	if (!is_fpu_owner())
-		enable_fpu();
+	*euen_curr = csr_xchg32(euen_mask, euen_mask, LOONGARCH_CSR_EUEN);
+
+#ifdef CONFIG_CPU_HAS_LASX
+	if (*euen_curr & CSR_EUEN_LASXEN)
+		_save_lasx(&current->thread.fpu);
 	else
+#endif
+#ifdef CONFIG_CPU_HAS_LSX
+	if (*euen_curr & CSR_EUEN_LSXEN)
+		_save_lsx(&current->thread.fpu);
+	else
+#endif
+	if (*euen_curr & CSR_EUEN_FPEN)
 		_save_fp(&current->thread.fpu);
 
 	write_fcsr(LOONGARCH_FCSR0, 0);
@@ -29,15 +50,41 @@ EXPORT_SYMBOL_GPL(kernel_fpu_begin);
 
 void kernel_fpu_end(void)
 {
+	unsigned int *euen_curr;
+
 	WARN_ON(!this_cpu_read(in_kernel_fpu));
 
-	if (!is_fpu_owner())
-		disable_fpu();
+	euen_curr = this_cpu_ptr(&euen_current);
+
+#ifdef CONFIG_CPU_HAS_LASX
+	if (*euen_curr & CSR_EUEN_LASXEN)
+		_restore_lasx(&current->thread.fpu);
 	else
+#endif
+#ifdef CONFIG_CPU_HAS_LSX
+	if (*euen_curr & CSR_EUEN_LSXEN)
+		_restore_lsx(&current->thread.fpu);
+	else
+#endif
+	if (*euen_curr & CSR_EUEN_FPEN)
 		_restore_fp(&current->thread.fpu);
 
+	*euen_curr = csr_xchg32(*euen_curr, euen_mask, LOONGARCH_CSR_EUEN);
+
 	this_cpu_write(in_kernel_fpu, false);
 
 	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(kernel_fpu_end);
+
+static int __init init_euen_mask(void)
+{
+	if (cpu_has_lsx)
+		euen_mask |= CSR_EUEN_LSXEN;
+
+	if (cpu_has_lasx)
+		euen_mask |= CSR_EUEN_LASXEN;
+
+	return 0;
+}
+arch_initcall(init_euen_mask);

From 75ded18a5e8e51ca2d26d55f010d60ae9aab652c Mon Sep 17 00:00:00 2001
From: WANG Xuerui <git@xen0n.name>
Date: Wed, 6 Sep 2023 22:53:55 +0800
Subject: [PATCH 1119/1189] LoongArch: Add SIMD-optimized XOR routines

Add LSX and LASX implementations of xor operations, operating on 64
bytes (one L1 cache line) at a time, for a balance between memory
utilization and instruction mix. Huacai confirmed that all future
LoongArch implementations by Loongson (that we care) will likely also
feature 64-byte cache lines, and experiments show no throughput
improvement with further unrolling.

Performance numbers measured during system boot on a 3A5000 @ 2.5GHz:

> 8regs           : 12702 MB/sec
> 8regs_prefetch  : 10920 MB/sec
> 32regs          : 12686 MB/sec
> 32regs_prefetch : 10918 MB/sec
> lsx             : 17589 MB/sec
> lasx            : 26116 MB/sec

Acked-by: Song Liu <song@kernel.org>
Signed-off-by: WANG Xuerui <git@xen0n.name>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/xor.h      |  68 ++++++++++++++++
 arch/loongarch/include/asm/xor_simd.h |  34 ++++++++
 arch/loongarch/lib/Makefile           |   2 +
 arch/loongarch/lib/xor_simd.c         |  93 ++++++++++++++++++++++
 arch/loongarch/lib/xor_simd.h         |  38 +++++++++
 arch/loongarch/lib/xor_simd_glue.c    |  72 +++++++++++++++++
 arch/loongarch/lib/xor_template.c     | 110 ++++++++++++++++++++++++++
 7 files changed, 417 insertions(+)
 create mode 100644 arch/loongarch/include/asm/xor.h
 create mode 100644 arch/loongarch/include/asm/xor_simd.h
 create mode 100644 arch/loongarch/lib/xor_simd.c
 create mode 100644 arch/loongarch/lib/xor_simd.h
 create mode 100644 arch/loongarch/lib/xor_simd_glue.c
 create mode 100644 arch/loongarch/lib/xor_template.c

diff --git a/arch/loongarch/include/asm/xor.h b/arch/loongarch/include/asm/xor.h
new file mode 100644
index 000000000000..12467fffee46
--- /dev/null
+++ b/arch/loongarch/include/asm/xor.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2023 WANG Xuerui <git@xen0n.name>
+ */
+#ifndef _ASM_LOONGARCH_XOR_H
+#define _ASM_LOONGARCH_XOR_H
+
+#include <asm/cpu-features.h>
+#include <asm/xor_simd.h>
+
+#ifdef CONFIG_CPU_HAS_LSX
+static struct xor_block_template xor_block_lsx = {
+	.name = "lsx",
+	.do_2 = xor_lsx_2,
+	.do_3 = xor_lsx_3,
+	.do_4 = xor_lsx_4,
+	.do_5 = xor_lsx_5,
+};
+
+#define XOR_SPEED_LSX()					\
+	do {						\
+		if (cpu_has_lsx)			\
+			xor_speed(&xor_block_lsx);	\
+	} while (0)
+#else /* CONFIG_CPU_HAS_LSX */
+#define XOR_SPEED_LSX()
+#endif /* CONFIG_CPU_HAS_LSX */
+
+#ifdef CONFIG_CPU_HAS_LASX
+static struct xor_block_template xor_block_lasx = {
+	.name = "lasx",
+	.do_2 = xor_lasx_2,
+	.do_3 = xor_lasx_3,
+	.do_4 = xor_lasx_4,
+	.do_5 = xor_lasx_5,
+};
+
+#define XOR_SPEED_LASX()					\
+	do {							\
+		if (cpu_has_lasx)				\
+			xor_speed(&xor_block_lasx);		\
+	} while (0)
+#else /* CONFIG_CPU_HAS_LASX */
+#define XOR_SPEED_LASX()
+#endif /* CONFIG_CPU_HAS_LASX */
+
+/*
+ * For grins, also test the generic routines.
+ *
+ * More importantly: it cannot be ruled out at this point of time, that some
+ * future (maybe reduced) models could run the vector algorithms slower than
+ * the scalar ones, maybe for errata or micro-op reasons. It may be
+ * appropriate to revisit this after one or two more uarch generations.
+ */
+#include <asm-generic/xor.h>
+
+#undef XOR_TRY_TEMPLATES
+#define XOR_TRY_TEMPLATES				\
+do {							\
+	xor_speed(&xor_block_8regs);			\
+	xor_speed(&xor_block_8regs_p);			\
+	xor_speed(&xor_block_32regs);			\
+	xor_speed(&xor_block_32regs_p);			\
+	XOR_SPEED_LSX();				\
+	XOR_SPEED_LASX();				\
+} while (0)
+
+#endif /* _ASM_LOONGARCH_XOR_H */
diff --git a/arch/loongarch/include/asm/xor_simd.h b/arch/loongarch/include/asm/xor_simd.h
new file mode 100644
index 000000000000..471b96332f38
--- /dev/null
+++ b/arch/loongarch/include/asm/xor_simd.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2023 WANG Xuerui <git@xen0n.name>
+ */
+#ifndef _ASM_LOONGARCH_XOR_SIMD_H
+#define _ASM_LOONGARCH_XOR_SIMD_H
+
+#ifdef CONFIG_CPU_HAS_LSX
+void xor_lsx_2(unsigned long bytes, unsigned long * __restrict p1,
+	       const unsigned long * __restrict p2);
+void xor_lsx_3(unsigned long bytes, unsigned long * __restrict p1,
+	       const unsigned long * __restrict p2, const unsigned long * __restrict p3);
+void xor_lsx_4(unsigned long bytes, unsigned long * __restrict p1,
+	       const unsigned long * __restrict p2, const unsigned long * __restrict p3,
+	       const unsigned long * __restrict p4);
+void xor_lsx_5(unsigned long bytes, unsigned long * __restrict p1,
+	       const unsigned long * __restrict p2, const unsigned long * __restrict p3,
+	       const unsigned long * __restrict p4, const unsigned long * __restrict p5);
+#endif /* CONFIG_CPU_HAS_LSX */
+
+#ifdef CONFIG_CPU_HAS_LASX
+void xor_lasx_2(unsigned long bytes, unsigned long * __restrict p1,
+	        const unsigned long * __restrict p2);
+void xor_lasx_3(unsigned long bytes, unsigned long * __restrict p1,
+	        const unsigned long * __restrict p2, const unsigned long * __restrict p3);
+void xor_lasx_4(unsigned long bytes, unsigned long * __restrict p1,
+	        const unsigned long * __restrict p2, const unsigned long * __restrict p3,
+	        const unsigned long * __restrict p4);
+void xor_lasx_5(unsigned long bytes, unsigned long * __restrict p1,
+	        const unsigned long * __restrict p2, const unsigned long * __restrict p3,
+	        const unsigned long * __restrict p4, const unsigned long * __restrict p5);
+#endif /* CONFIG_CPU_HAS_LASX */
+
+#endif /* _ASM_LOONGARCH_XOR_SIMD_H */
diff --git a/arch/loongarch/lib/Makefile b/arch/loongarch/lib/Makefile
index d60d4e096cfa..a77bf160bfc4 100644
--- a/arch/loongarch/lib/Makefile
+++ b/arch/loongarch/lib/Makefile
@@ -6,4 +6,6 @@
 lib-y	+= delay.o memset.o memcpy.o memmove.o \
 	   clear_user.o copy_user.o csum.o dump_tlb.o unaligned.o
 
+obj-$(CONFIG_CPU_HAS_LSX) += xor_simd.o xor_simd_glue.o
+
 obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
diff --git a/arch/loongarch/lib/xor_simd.c b/arch/loongarch/lib/xor_simd.c
new file mode 100644
index 000000000000..84cd24b728c4
--- /dev/null
+++ b/arch/loongarch/lib/xor_simd.c
@@ -0,0 +1,93 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * LoongArch SIMD XOR operations
+ *
+ * Copyright (C) 2023 WANG Xuerui <git@xen0n.name>
+ */
+
+#include "xor_simd.h"
+
+/*
+ * Process one cache line (64 bytes) per loop. This is assuming all future
+ * popular LoongArch cores are similar performance-characteristics-wise to the
+ * current models.
+ */
+#define LINE_WIDTH 64
+
+#ifdef CONFIG_CPU_HAS_LSX
+
+#define LD(reg, base, offset)	\
+	"vld $vr" #reg ", %[" #base "], " #offset "\n\t"
+#define ST(reg, base, offset)	\
+	"vst $vr" #reg ", %[" #base "], " #offset "\n\t"
+#define XOR(dj, k)	"vxor.v $vr" #dj ", $vr" #dj ", $vr" #k "\n\t"
+
+#define LD_INOUT_LINE(base)	\
+	LD(0, base, 0)		\
+	LD(1, base, 16)		\
+	LD(2, base, 32)		\
+	LD(3, base, 48)
+
+#define LD_AND_XOR_LINE(base)	\
+	LD(4, base, 0)		\
+	LD(5, base, 16)		\
+	LD(6, base, 32)		\
+	LD(7, base, 48)		\
+	XOR(0, 4)		\
+	XOR(1, 5)		\
+	XOR(2, 6)		\
+	XOR(3, 7)
+
+#define ST_LINE(base)		\
+	ST(0, base, 0)		\
+	ST(1, base, 16)		\
+	ST(2, base, 32)		\
+	ST(3, base, 48)
+
+#define XOR_FUNC_NAME(nr) __xor_lsx_##nr
+#include "xor_template.c"
+
+#undef LD
+#undef ST
+#undef XOR
+#undef LD_INOUT_LINE
+#undef LD_AND_XOR_LINE
+#undef ST_LINE
+#undef XOR_FUNC_NAME
+
+#endif /* CONFIG_CPU_HAS_LSX */
+
+#ifdef CONFIG_CPU_HAS_LASX
+
+#define LD(reg, base, offset)	\
+	"xvld $xr" #reg ", %[" #base "], " #offset "\n\t"
+#define ST(reg, base, offset)	\
+	"xvst $xr" #reg ", %[" #base "], " #offset "\n\t"
+#define XOR(dj, k)	"xvxor.v $xr" #dj ", $xr" #dj ", $xr" #k "\n\t"
+
+#define LD_INOUT_LINE(base)	\
+	LD(0, base, 0)		\
+	LD(1, base, 32)
+
+#define LD_AND_XOR_LINE(base)	\
+	LD(2, base, 0)		\
+	LD(3, base, 32)		\
+	XOR(0, 2)		\
+	XOR(1, 3)
+
+#define ST_LINE(base)		\
+	ST(0, base, 0)		\
+	ST(1, base, 32)
+
+#define XOR_FUNC_NAME(nr) __xor_lasx_##nr
+#include "xor_template.c"
+
+#undef LD
+#undef ST
+#undef XOR
+#undef LD_INOUT_LINE
+#undef LD_AND_XOR_LINE
+#undef ST_LINE
+#undef XOR_FUNC_NAME
+
+#endif /* CONFIG_CPU_HAS_LASX */
diff --git a/arch/loongarch/lib/xor_simd.h b/arch/loongarch/lib/xor_simd.h
new file mode 100644
index 000000000000..f50f32514d80
--- /dev/null
+++ b/arch/loongarch/lib/xor_simd.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Simple interface to link xor_simd.c and xor_simd_glue.c
+ *
+ * Separating these files ensures that no SIMD instructions are run outside of
+ * the kfpu critical section.
+ */
+
+#ifndef __LOONGARCH_LIB_XOR_SIMD_H
+#define __LOONGARCH_LIB_XOR_SIMD_H
+
+#ifdef CONFIG_CPU_HAS_LSX
+void __xor_lsx_2(unsigned long bytes, unsigned long * __restrict p1,
+		 const unsigned long * __restrict p2);
+void __xor_lsx_3(unsigned long bytes, unsigned long * __restrict p1,
+		 const unsigned long * __restrict p2, const unsigned long * __restrict p3);
+void __xor_lsx_4(unsigned long bytes, unsigned long * __restrict p1,
+		 const unsigned long * __restrict p2, const unsigned long * __restrict p3,
+		 const unsigned long * __restrict p4);
+void __xor_lsx_5(unsigned long bytes, unsigned long * __restrict p1,
+		 const unsigned long * __restrict p2, const unsigned long * __restrict p3,
+		 const unsigned long * __restrict p4, const unsigned long * __restrict p5);
+#endif /* CONFIG_CPU_HAS_LSX */
+
+#ifdef CONFIG_CPU_HAS_LASX
+void __xor_lasx_2(unsigned long bytes, unsigned long * __restrict p1,
+		  const unsigned long * __restrict p2);
+void __xor_lasx_3(unsigned long bytes, unsigned long * __restrict p1,
+		  const unsigned long * __restrict p2, const unsigned long * __restrict p3);
+void __xor_lasx_4(unsigned long bytes, unsigned long * __restrict p1,
+		  const unsigned long * __restrict p2, const unsigned long * __restrict p3,
+		  const unsigned long * __restrict p4);
+void __xor_lasx_5(unsigned long bytes, unsigned long * __restrict p1,
+		  const unsigned long * __restrict p2, const unsigned long * __restrict p3,
+		  const unsigned long * __restrict p4, const unsigned long * __restrict p5);
+#endif /* CONFIG_CPU_HAS_LASX */
+
+#endif /* __LOONGARCH_LIB_XOR_SIMD_H */
diff --git a/arch/loongarch/lib/xor_simd_glue.c b/arch/loongarch/lib/xor_simd_glue.c
new file mode 100644
index 000000000000..393f689dbcf6
--- /dev/null
+++ b/arch/loongarch/lib/xor_simd_glue.c
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * LoongArch SIMD XOR operations
+ *
+ * Copyright (C) 2023 WANG Xuerui <git@xen0n.name>
+ */
+
+#include <linux/export.h>
+#include <linux/sched.h>
+#include <asm/fpu.h>
+#include <asm/xor_simd.h>
+#include "xor_simd.h"
+
+#define MAKE_XOR_GLUE_2(flavor)							\
+void xor_##flavor##_2(unsigned long bytes, unsigned long * __restrict p1,	\
+		      const unsigned long * __restrict p2)			\
+{										\
+	kernel_fpu_begin();							\
+	__xor_##flavor##_2(bytes, p1, p2);					\
+	kernel_fpu_end();							\
+}										\
+EXPORT_SYMBOL_GPL(xor_##flavor##_2)
+
+#define MAKE_XOR_GLUE_3(flavor)							\
+void xor_##flavor##_3(unsigned long bytes, unsigned long * __restrict p1,	\
+		      const unsigned long * __restrict p2,			\
+		      const unsigned long * __restrict p3)			\
+{										\
+	kernel_fpu_begin();							\
+	__xor_##flavor##_3(bytes, p1, p2, p3);					\
+	kernel_fpu_end();							\
+}										\
+EXPORT_SYMBOL_GPL(xor_##flavor##_3)
+
+#define MAKE_XOR_GLUE_4(flavor)							\
+void xor_##flavor##_4(unsigned long bytes, unsigned long * __restrict p1,	\
+		      const unsigned long * __restrict p2,			\
+		      const unsigned long * __restrict p3,			\
+		      const unsigned long * __restrict p4)			\
+{										\
+	kernel_fpu_begin();							\
+	__xor_##flavor##_4(bytes, p1, p2, p3, p4);				\
+	kernel_fpu_end();							\
+}										\
+EXPORT_SYMBOL_GPL(xor_##flavor##_4)
+
+#define MAKE_XOR_GLUE_5(flavor)							\
+void xor_##flavor##_5(unsigned long bytes, unsigned long * __restrict p1,	\
+		      const unsigned long * __restrict p2,			\
+		      const unsigned long * __restrict p3,			\
+		      const unsigned long * __restrict p4,			\
+		      const unsigned long * __restrict p5)			\
+{										\
+	kernel_fpu_begin();							\
+	__xor_##flavor##_5(bytes, p1, p2, p3, p4, p5);				\
+	kernel_fpu_end();							\
+}										\
+EXPORT_SYMBOL_GPL(xor_##flavor##_5)
+
+#define MAKE_XOR_GLUES(flavor)		\
+	MAKE_XOR_GLUE_2(flavor);	\
+	MAKE_XOR_GLUE_3(flavor);	\
+	MAKE_XOR_GLUE_4(flavor);	\
+	MAKE_XOR_GLUE_5(flavor)
+
+#ifdef CONFIG_CPU_HAS_LSX
+MAKE_XOR_GLUES(lsx);
+#endif
+
+#ifdef CONFIG_CPU_HAS_LASX
+MAKE_XOR_GLUES(lasx);
+#endif
diff --git a/arch/loongarch/lib/xor_template.c b/arch/loongarch/lib/xor_template.c
new file mode 100644
index 000000000000..0358ced7fe33
--- /dev/null
+++ b/arch/loongarch/lib/xor_template.c
@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2023 WANG Xuerui <git@xen0n.name>
+ *
+ * Template for XOR operations, instantiated in xor_simd.c.
+ *
+ * Expected preprocessor definitions:
+ *
+ * - LINE_WIDTH
+ * - XOR_FUNC_NAME(nr)
+ * - LD_INOUT_LINE(buf)
+ * - LD_AND_XOR_LINE(buf)
+ * - ST_LINE(buf)
+ */
+
+void XOR_FUNC_NAME(2)(unsigned long bytes,
+		      unsigned long * __restrict v1,
+		      const unsigned long * __restrict v2)
+{
+	unsigned long lines = bytes / LINE_WIDTH;
+
+	do {
+		__asm__ __volatile__ (
+			LD_INOUT_LINE(v1)
+			LD_AND_XOR_LINE(v2)
+			ST_LINE(v1)
+		: : [v1] "r"(v1), [v2] "r"(v2) : "memory"
+		);
+
+		v1 += LINE_WIDTH / sizeof(unsigned long);
+		v2 += LINE_WIDTH / sizeof(unsigned long);
+	} while (--lines > 0);
+}
+
+void XOR_FUNC_NAME(3)(unsigned long bytes,
+		      unsigned long * __restrict v1,
+		      const unsigned long * __restrict v2,
+		      const unsigned long * __restrict v3)
+{
+	unsigned long lines = bytes / LINE_WIDTH;
+
+	do {
+		__asm__ __volatile__ (
+			LD_INOUT_LINE(v1)
+			LD_AND_XOR_LINE(v2)
+			LD_AND_XOR_LINE(v3)
+			ST_LINE(v1)
+		: : [v1] "r"(v1), [v2] "r"(v2), [v3] "r"(v3) : "memory"
+		);
+
+		v1 += LINE_WIDTH / sizeof(unsigned long);
+		v2 += LINE_WIDTH / sizeof(unsigned long);
+		v3 += LINE_WIDTH / sizeof(unsigned long);
+	} while (--lines > 0);
+}
+
+void XOR_FUNC_NAME(4)(unsigned long bytes,
+		      unsigned long * __restrict v1,
+		      const unsigned long * __restrict v2,
+		      const unsigned long * __restrict v3,
+		      const unsigned long * __restrict v4)
+{
+	unsigned long lines = bytes / LINE_WIDTH;
+
+	do {
+		__asm__ __volatile__ (
+			LD_INOUT_LINE(v1)
+			LD_AND_XOR_LINE(v2)
+			LD_AND_XOR_LINE(v3)
+			LD_AND_XOR_LINE(v4)
+			ST_LINE(v1)
+		: : [v1] "r"(v1), [v2] "r"(v2), [v3] "r"(v3), [v4] "r"(v4)
+		: "memory"
+		);
+
+		v1 += LINE_WIDTH / sizeof(unsigned long);
+		v2 += LINE_WIDTH / sizeof(unsigned long);
+		v3 += LINE_WIDTH / sizeof(unsigned long);
+		v4 += LINE_WIDTH / sizeof(unsigned long);
+	} while (--lines > 0);
+}
+
+void XOR_FUNC_NAME(5)(unsigned long bytes,
+		      unsigned long * __restrict v1,
+		      const unsigned long * __restrict v2,
+		      const unsigned long * __restrict v3,
+		      const unsigned long * __restrict v4,
+		      const unsigned long * __restrict v5)
+{
+	unsigned long lines = bytes / LINE_WIDTH;
+
+	do {
+		__asm__ __volatile__ (
+			LD_INOUT_LINE(v1)
+			LD_AND_XOR_LINE(v2)
+			LD_AND_XOR_LINE(v3)
+			LD_AND_XOR_LINE(v4)
+			LD_AND_XOR_LINE(v5)
+			ST_LINE(v1)
+		: : [v1] "r"(v1), [v2] "r"(v2), [v3] "r"(v3), [v4] "r"(v4),
+		    [v5] "r"(v5) : "memory"
+		);
+
+		v1 += LINE_WIDTH / sizeof(unsigned long);
+		v2 += LINE_WIDTH / sizeof(unsigned long);
+		v3 += LINE_WIDTH / sizeof(unsigned long);
+		v4 += LINE_WIDTH / sizeof(unsigned long);
+		v5 += LINE_WIDTH / sizeof(unsigned long);
+	} while (--lines > 0);
+}

From 8f3f06dfd6873135068ccf1a0b386308e8c4da38 Mon Sep 17 00:00:00 2001
From: WANG Xuerui <git@xen0n.name>
Date: Wed, 6 Sep 2023 22:53:55 +0800
Subject: [PATCH 1120/1189] raid6: Add LoongArch SIMD syndrome calculation

The algorithms work on 64 bytes at a time, which is the L1 cache line
size of all current and future LoongArch cores (that we care about), as
confirmed by Huacai. The code is based on the generic int.uc algorithm,
unrolled 4 times for LSX and 2 times for LASX. Further unrolling does
not meaningfully improve the performance according to experiments.

Performance numbers measured during system boot on a 3A5000 @ 2.5GHz:

> raid6: lasx     gen() 12726 MB/s
> raid6: lsx      gen() 10001 MB/s
> raid6: int64x8  gen()  2876 MB/s
> raid6: int64x4  gen()  3867 MB/s
> raid6: int64x2  gen()  2531 MB/s
> raid6: int64x1  gen()  1945 MB/s

Comparison of xor() speeds (from different boots but meaningful anyway):

> lasx:    11226 MB/s
> lsx:     6395 MB/s
> int64x4: 2147 MB/s

Performance as measured by raid6test:

> raid6: lasx     gen() 25109 MB/s
> raid6: lsx      gen() 13233 MB/s
> raid6: int64x8  gen()  4164 MB/s
> raid6: int64x4  gen()  6005 MB/s
> raid6: int64x2  gen()  5781 MB/s
> raid6: int64x1  gen()  4119 MB/s
> raid6: using algorithm lasx gen() 25109 MB/s
> raid6: .... xor() 14439 MB/s, rmw enabled

Acked-by: Song Liu <song@kernel.org>
Signed-off-by: WANG Xuerui <git@xen0n.name>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 include/linux/raid/pq.h    |   2 +
 lib/raid6/Makefile         |   1 +
 lib/raid6/algos.c          |   8 +
 lib/raid6/loongarch.h      |  38 ++++
 lib/raid6/loongarch_simd.c | 422 +++++++++++++++++++++++++++++++++++++
 lib/raid6/test/Makefile    |  12 ++
 6 files changed, 483 insertions(+)
 create mode 100644 lib/raid6/loongarch.h
 create mode 100644 lib/raid6/loongarch_simd.c

diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h
index f29aaaf2eb21..874447485848 100644
--- a/include/linux/raid/pq.h
+++ b/include/linux/raid/pq.h
@@ -108,6 +108,8 @@ extern const struct raid6_calls raid6_vpermxor1;
 extern const struct raid6_calls raid6_vpermxor2;
 extern const struct raid6_calls raid6_vpermxor4;
 extern const struct raid6_calls raid6_vpermxor8;
+extern const struct raid6_calls raid6_lsx;
+extern const struct raid6_calls raid6_lasx;
 
 struct raid6_recov_calls {
 	void (*data2)(int, size_t, int, int, void **);
diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile
index 45e17619422b..2b9ebe105480 100644
--- a/lib/raid6/Makefile
+++ b/lib/raid6/Makefile
@@ -9,6 +9,7 @@ raid6_pq-$(CONFIG_ALTIVEC) += altivec1.o altivec2.o altivec4.o altivec8.o \
                               vpermxor1.o vpermxor2.o vpermxor4.o vpermxor8.o
 raid6_pq-$(CONFIG_KERNEL_MODE_NEON) += neon.o neon1.o neon2.o neon4.o neon8.o recov_neon.o recov_neon_inner.o
 raid6_pq-$(CONFIG_S390) += s390vx8.o recov_s390xc.o
+raid6_pq-$(CONFIG_LOONGARCH) += loongarch_simd.o
 
 hostprogs	+= mktables
 
diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c
index a22a05c9af8a..739c7ebcae1a 100644
--- a/lib/raid6/algos.c
+++ b/lib/raid6/algos.c
@@ -73,6 +73,14 @@ const struct raid6_calls * const raid6_algos[] = {
 	&raid6_neonx2,
 	&raid6_neonx1,
 #endif
+#ifdef CONFIG_LOONGARCH
+#ifdef CONFIG_CPU_HAS_LASX
+	&raid6_lasx,
+#endif
+#ifdef CONFIG_CPU_HAS_LSX
+	&raid6_lsx,
+#endif
+#endif
 #if defined(__ia64__)
 	&raid6_intx32,
 	&raid6_intx16,
diff --git a/lib/raid6/loongarch.h b/lib/raid6/loongarch.h
new file mode 100644
index 000000000000..acfc33ce7056
--- /dev/null
+++ b/lib/raid6/loongarch.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2023 WANG Xuerui <git@xen0n.name>
+ *
+ * raid6/loongarch.h
+ *
+ * Definitions common to LoongArch RAID-6 code only
+ */
+
+#ifndef _LIB_RAID6_LOONGARCH_H
+#define _LIB_RAID6_LOONGARCH_H
+
+#ifdef __KERNEL__
+
+#include <asm/cpu-features.h>
+#include <asm/fpu.h>
+
+#else /* for user-space testing */
+
+#include <sys/auxv.h>
+
+/* have to supply these defines for glibc 2.37- and musl */
+#ifndef HWCAP_LOONGARCH_LSX
+#define HWCAP_LOONGARCH_LSX	(1 << 4)
+#endif
+#ifndef HWCAP_LOONGARCH_LASX
+#define HWCAP_LOONGARCH_LASX	(1 << 5)
+#endif
+
+#define kernel_fpu_begin()
+#define kernel_fpu_end()
+
+#define cpu_has_lsx	(getauxval(AT_HWCAP) & HWCAP_LOONGARCH_LSX)
+#define cpu_has_lasx	(getauxval(AT_HWCAP) & HWCAP_LOONGARCH_LASX)
+
+#endif /* __KERNEL__ */
+
+#endif /* _LIB_RAID6_LOONGARCH_H */
diff --git a/lib/raid6/loongarch_simd.c b/lib/raid6/loongarch_simd.c
new file mode 100644
index 000000000000..aa5d9f924ca3
--- /dev/null
+++ b/lib/raid6/loongarch_simd.c
@@ -0,0 +1,422 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * RAID6 syndrome calculations in LoongArch SIMD (LSX & LASX)
+ *
+ * Copyright 2023 WANG Xuerui <git@xen0n.name>
+ *
+ * Based on the generic RAID-6 code (int.uc):
+ *
+ * Copyright 2002-2004 H. Peter Anvin
+ */
+
+#include <linux/raid/pq.h>
+#include "loongarch.h"
+
+/*
+ * The vector algorithms are currently priority 0, which means the generic
+ * scalar algorithms are not being disabled if vector support is present.
+ * This is like the similar LoongArch RAID5 XOR code, with the main reason
+ * repeated here: it cannot be ruled out at this point of time, that some
+ * future (maybe reduced) models could run the vector algorithms slower than
+ * the scalar ones, maybe for errata or micro-op reasons. It may be
+ * appropriate to revisit this after one or two more uarch generations.
+ */
+
+#ifdef CONFIG_CPU_HAS_LSX
+#define NSIZE 16
+
+static int raid6_has_lsx(void)
+{
+	return cpu_has_lsx;
+}
+
+static void raid6_lsx_gen_syndrome(int disks, size_t bytes, void **ptrs)
+{
+	u8 **dptr = (u8 **)ptrs;
+	u8 *p, *q;
+	int d, z, z0;
+
+	z0 = disks - 3;		/* Highest data disk */
+	p = dptr[z0+1];		/* XOR parity */
+	q = dptr[z0+2];		/* RS syndrome */
+
+	kernel_fpu_begin();
+
+	/*
+	 * $vr0, $vr1, $vr2, $vr3: wp
+	 * $vr4, $vr5, $vr6, $vr7: wq
+	 * $vr8, $vr9, $vr10, $vr11: wd
+	 * $vr12, $vr13, $vr14, $vr15: w2
+	 * $vr16, $vr17, $vr18, $vr19: w1
+	 */
+	for (d = 0; d < bytes; d += NSIZE*4) {
+		/* wq$$ = wp$$ = *(unative_t *)&dptr[z0][d+$$*NSIZE]; */
+		asm volatile("vld $vr0, %0" : : "m"(dptr[z0][d+0*NSIZE]));
+		asm volatile("vld $vr1, %0" : : "m"(dptr[z0][d+1*NSIZE]));
+		asm volatile("vld $vr2, %0" : : "m"(dptr[z0][d+2*NSIZE]));
+		asm volatile("vld $vr3, %0" : : "m"(dptr[z0][d+3*NSIZE]));
+		asm volatile("vori.b $vr4, $vr0, 0");
+		asm volatile("vori.b $vr5, $vr1, 0");
+		asm volatile("vori.b $vr6, $vr2, 0");
+		asm volatile("vori.b $vr7, $vr3, 0");
+		for (z = z0-1; z >= 0; z--) {
+			/* wd$$ = *(unative_t *)&dptr[z][d+$$*NSIZE]; */
+			asm volatile("vld $vr8, %0" : : "m"(dptr[z][d+0*NSIZE]));
+			asm volatile("vld $vr9, %0" : : "m"(dptr[z][d+1*NSIZE]));
+			asm volatile("vld $vr10, %0" : : "m"(dptr[z][d+2*NSIZE]));
+			asm volatile("vld $vr11, %0" : : "m"(dptr[z][d+3*NSIZE]));
+			/* wp$$ ^= wd$$; */
+			asm volatile("vxor.v $vr0, $vr0, $vr8");
+			asm volatile("vxor.v $vr1, $vr1, $vr9");
+			asm volatile("vxor.v $vr2, $vr2, $vr10");
+			asm volatile("vxor.v $vr3, $vr3, $vr11");
+			/* w2$$ = MASK(wq$$); */
+			asm volatile("vslti.b $vr12, $vr4, 0");
+			asm volatile("vslti.b $vr13, $vr5, 0");
+			asm volatile("vslti.b $vr14, $vr6, 0");
+			asm volatile("vslti.b $vr15, $vr7, 0");
+			/* w1$$ = SHLBYTE(wq$$); */
+			asm volatile("vslli.b $vr16, $vr4, 1");
+			asm volatile("vslli.b $vr17, $vr5, 1");
+			asm volatile("vslli.b $vr18, $vr6, 1");
+			asm volatile("vslli.b $vr19, $vr7, 1");
+			/* w2$$ &= NBYTES(0x1d); */
+			asm volatile("vandi.b $vr12, $vr12, 0x1d");
+			asm volatile("vandi.b $vr13, $vr13, 0x1d");
+			asm volatile("vandi.b $vr14, $vr14, 0x1d");
+			asm volatile("vandi.b $vr15, $vr15, 0x1d");
+			/* w1$$ ^= w2$$; */
+			asm volatile("vxor.v $vr16, $vr16, $vr12");
+			asm volatile("vxor.v $vr17, $vr17, $vr13");
+			asm volatile("vxor.v $vr18, $vr18, $vr14");
+			asm volatile("vxor.v $vr19, $vr19, $vr15");
+			/* wq$$ = w1$$ ^ wd$$; */
+			asm volatile("vxor.v $vr4, $vr16, $vr8");
+			asm volatile("vxor.v $vr5, $vr17, $vr9");
+			asm volatile("vxor.v $vr6, $vr18, $vr10");
+			asm volatile("vxor.v $vr7, $vr19, $vr11");
+		}
+		/* *(unative_t *)&p[d+NSIZE*$$] = wp$$; */
+		asm volatile("vst $vr0, %0" : "=m"(p[d+NSIZE*0]));
+		asm volatile("vst $vr1, %0" : "=m"(p[d+NSIZE*1]));
+		asm volatile("vst $vr2, %0" : "=m"(p[d+NSIZE*2]));
+		asm volatile("vst $vr3, %0" : "=m"(p[d+NSIZE*3]));
+		/* *(unative_t *)&q[d+NSIZE*$$] = wq$$; */
+		asm volatile("vst $vr4, %0" : "=m"(q[d+NSIZE*0]));
+		asm volatile("vst $vr5, %0" : "=m"(q[d+NSIZE*1]));
+		asm volatile("vst $vr6, %0" : "=m"(q[d+NSIZE*2]));
+		asm volatile("vst $vr7, %0" : "=m"(q[d+NSIZE*3]));
+	}
+
+	kernel_fpu_end();
+}
+
+static void raid6_lsx_xor_syndrome(int disks, int start, int stop,
+				   size_t bytes, void **ptrs)
+{
+	u8 **dptr = (u8 **)ptrs;
+	u8 *p, *q;
+	int d, z, z0;
+
+	z0 = stop;		/* P/Q right side optimization */
+	p = dptr[disks-2];	/* XOR parity */
+	q = dptr[disks-1];	/* RS syndrome */
+
+	kernel_fpu_begin();
+
+	/*
+	 * $vr0, $vr1, $vr2, $vr3: wp
+	 * $vr4, $vr5, $vr6, $vr7: wq
+	 * $vr8, $vr9, $vr10, $vr11: wd
+	 * $vr12, $vr13, $vr14, $vr15: w2
+	 * $vr16, $vr17, $vr18, $vr19: w1
+	 */
+	for (d = 0; d < bytes; d += NSIZE*4) {
+		/* P/Q data pages */
+		/* wq$$ = wp$$ = *(unative_t *)&dptr[z0][d+$$*NSIZE]; */
+		asm volatile("vld $vr0, %0" : : "m"(dptr[z0][d+0*NSIZE]));
+		asm volatile("vld $vr1, %0" : : "m"(dptr[z0][d+1*NSIZE]));
+		asm volatile("vld $vr2, %0" : : "m"(dptr[z0][d+2*NSIZE]));
+		asm volatile("vld $vr3, %0" : : "m"(dptr[z0][d+3*NSIZE]));
+		asm volatile("vori.b $vr4, $vr0, 0");
+		asm volatile("vori.b $vr5, $vr1, 0");
+		asm volatile("vori.b $vr6, $vr2, 0");
+		asm volatile("vori.b $vr7, $vr3, 0");
+		for (z = z0-1; z >= start; z--) {
+			/* wd$$ = *(unative_t *)&dptr[z][d+$$*NSIZE]; */
+			asm volatile("vld $vr8, %0" : : "m"(dptr[z][d+0*NSIZE]));
+			asm volatile("vld $vr9, %0" : : "m"(dptr[z][d+1*NSIZE]));
+			asm volatile("vld $vr10, %0" : : "m"(dptr[z][d+2*NSIZE]));
+			asm volatile("vld $vr11, %0" : : "m"(dptr[z][d+3*NSIZE]));
+			/* wp$$ ^= wd$$; */
+			asm volatile("vxor.v $vr0, $vr0, $vr8");
+			asm volatile("vxor.v $vr1, $vr1, $vr9");
+			asm volatile("vxor.v $vr2, $vr2, $vr10");
+			asm volatile("vxor.v $vr3, $vr3, $vr11");
+			/* w2$$ = MASK(wq$$); */
+			asm volatile("vslti.b $vr12, $vr4, 0");
+			asm volatile("vslti.b $vr13, $vr5, 0");
+			asm volatile("vslti.b $vr14, $vr6, 0");
+			asm volatile("vslti.b $vr15, $vr7, 0");
+			/* w1$$ = SHLBYTE(wq$$); */
+			asm volatile("vslli.b $vr16, $vr4, 1");
+			asm volatile("vslli.b $vr17, $vr5, 1");
+			asm volatile("vslli.b $vr18, $vr6, 1");
+			asm volatile("vslli.b $vr19, $vr7, 1");
+			/* w2$$ &= NBYTES(0x1d); */
+			asm volatile("vandi.b $vr12, $vr12, 0x1d");
+			asm volatile("vandi.b $vr13, $vr13, 0x1d");
+			asm volatile("vandi.b $vr14, $vr14, 0x1d");
+			asm volatile("vandi.b $vr15, $vr15, 0x1d");
+			/* w1$$ ^= w2$$; */
+			asm volatile("vxor.v $vr16, $vr16, $vr12");
+			asm volatile("vxor.v $vr17, $vr17, $vr13");
+			asm volatile("vxor.v $vr18, $vr18, $vr14");
+			asm volatile("vxor.v $vr19, $vr19, $vr15");
+			/* wq$$ = w1$$ ^ wd$$; */
+			asm volatile("vxor.v $vr4, $vr16, $vr8");
+			asm volatile("vxor.v $vr5, $vr17, $vr9");
+			asm volatile("vxor.v $vr6, $vr18, $vr10");
+			asm volatile("vxor.v $vr7, $vr19, $vr11");
+		}
+
+		/* P/Q left side optimization */
+		for (z = start-1; z >= 0; z--) {
+			/* w2$$ = MASK(wq$$); */
+			asm volatile("vslti.b $vr12, $vr4, 0");
+			asm volatile("vslti.b $vr13, $vr5, 0");
+			asm volatile("vslti.b $vr14, $vr6, 0");
+			asm volatile("vslti.b $vr15, $vr7, 0");
+			/* w1$$ = SHLBYTE(wq$$); */
+			asm volatile("vslli.b $vr16, $vr4, 1");
+			asm volatile("vslli.b $vr17, $vr5, 1");
+			asm volatile("vslli.b $vr18, $vr6, 1");
+			asm volatile("vslli.b $vr19, $vr7, 1");
+			/* w2$$ &= NBYTES(0x1d); */
+			asm volatile("vandi.b $vr12, $vr12, 0x1d");
+			asm volatile("vandi.b $vr13, $vr13, 0x1d");
+			asm volatile("vandi.b $vr14, $vr14, 0x1d");
+			asm volatile("vandi.b $vr15, $vr15, 0x1d");
+			/* wq$$ = w1$$ ^ w2$$; */
+			asm volatile("vxor.v $vr4, $vr16, $vr12");
+			asm volatile("vxor.v $vr5, $vr17, $vr13");
+			asm volatile("vxor.v $vr6, $vr18, $vr14");
+			asm volatile("vxor.v $vr7, $vr19, $vr15");
+		}
+		/*
+		 * *(unative_t *)&p[d+NSIZE*$$] ^= wp$$;
+		 * *(unative_t *)&q[d+NSIZE*$$] ^= wq$$;
+		 */
+		asm volatile(
+			"vld $vr20, %0\n\t"
+			"vld $vr21, %1\n\t"
+			"vld $vr22, %2\n\t"
+			"vld $vr23, %3\n\t"
+			"vld $vr24, %4\n\t"
+			"vld $vr25, %5\n\t"
+			"vld $vr26, %6\n\t"
+			"vld $vr27, %7\n\t"
+			"vxor.v $vr20, $vr20, $vr0\n\t"
+			"vxor.v $vr21, $vr21, $vr1\n\t"
+			"vxor.v $vr22, $vr22, $vr2\n\t"
+			"vxor.v $vr23, $vr23, $vr3\n\t"
+			"vxor.v $vr24, $vr24, $vr4\n\t"
+			"vxor.v $vr25, $vr25, $vr5\n\t"
+			"vxor.v $vr26, $vr26, $vr6\n\t"
+			"vxor.v $vr27, $vr27, $vr7\n\t"
+			"vst $vr20, %0\n\t"
+			"vst $vr21, %1\n\t"
+			"vst $vr22, %2\n\t"
+			"vst $vr23, %3\n\t"
+			"vst $vr24, %4\n\t"
+			"vst $vr25, %5\n\t"
+			"vst $vr26, %6\n\t"
+			"vst $vr27, %7\n\t"
+			: "+m"(p[d+NSIZE*0]), "+m"(p[d+NSIZE*1]),
+			  "+m"(p[d+NSIZE*2]), "+m"(p[d+NSIZE*3]),
+			  "+m"(q[d+NSIZE*0]), "+m"(q[d+NSIZE*1]),
+			  "+m"(q[d+NSIZE*2]), "+m"(q[d+NSIZE*3])
+		);
+	}
+
+	kernel_fpu_end();
+}
+
+const struct raid6_calls raid6_lsx = {
+	raid6_lsx_gen_syndrome,
+	raid6_lsx_xor_syndrome,
+	raid6_has_lsx,
+	"lsx",
+	.priority = 0 /* see the comment near the top of the file for reason */
+};
+
+#undef NSIZE
+#endif /* CONFIG_CPU_HAS_LSX */
+
+#ifdef CONFIG_CPU_HAS_LASX
+#define NSIZE 32
+
+static int raid6_has_lasx(void)
+{
+	return cpu_has_lasx;
+}
+
+static void raid6_lasx_gen_syndrome(int disks, size_t bytes, void **ptrs)
+{
+	u8 **dptr = (u8 **)ptrs;
+	u8 *p, *q;
+	int d, z, z0;
+
+	z0 = disks - 3;		/* Highest data disk */
+	p = dptr[z0+1];		/* XOR parity */
+	q = dptr[z0+2];		/* RS syndrome */
+
+	kernel_fpu_begin();
+
+	/*
+	 * $xr0, $xr1: wp
+	 * $xr2, $xr3: wq
+	 * $xr4, $xr5: wd
+	 * $xr6, $xr7: w2
+	 * $xr8, $xr9: w1
+	 */
+	for (d = 0; d < bytes; d += NSIZE*2) {
+		/* wq$$ = wp$$ = *(unative_t *)&dptr[z0][d+$$*NSIZE]; */
+		asm volatile("xvld $xr0, %0" : : "m"(dptr[z0][d+0*NSIZE]));
+		asm volatile("xvld $xr1, %0" : : "m"(dptr[z0][d+1*NSIZE]));
+		asm volatile("xvori.b $xr2, $xr0, 0");
+		asm volatile("xvori.b $xr3, $xr1, 0");
+		for (z = z0-1; z >= 0; z--) {
+			/* wd$$ = *(unative_t *)&dptr[z][d+$$*NSIZE]; */
+			asm volatile("xvld $xr4, %0" : : "m"(dptr[z][d+0*NSIZE]));
+			asm volatile("xvld $xr5, %0" : : "m"(dptr[z][d+1*NSIZE]));
+			/* wp$$ ^= wd$$; */
+			asm volatile("xvxor.v $xr0, $xr0, $xr4");
+			asm volatile("xvxor.v $xr1, $xr1, $xr5");
+			/* w2$$ = MASK(wq$$); */
+			asm volatile("xvslti.b $xr6, $xr2, 0");
+			asm volatile("xvslti.b $xr7, $xr3, 0");
+			/* w1$$ = SHLBYTE(wq$$); */
+			asm volatile("xvslli.b $xr8, $xr2, 1");
+			asm volatile("xvslli.b $xr9, $xr3, 1");
+			/* w2$$ &= NBYTES(0x1d); */
+			asm volatile("xvandi.b $xr6, $xr6, 0x1d");
+			asm volatile("xvandi.b $xr7, $xr7, 0x1d");
+			/* w1$$ ^= w2$$; */
+			asm volatile("xvxor.v $xr8, $xr8, $xr6");
+			asm volatile("xvxor.v $xr9, $xr9, $xr7");
+			/* wq$$ = w1$$ ^ wd$$; */
+			asm volatile("xvxor.v $xr2, $xr8, $xr4");
+			asm volatile("xvxor.v $xr3, $xr9, $xr5");
+		}
+		/* *(unative_t *)&p[d+NSIZE*$$] = wp$$; */
+		asm volatile("xvst $xr0, %0" : "=m"(p[d+NSIZE*0]));
+		asm volatile("xvst $xr1, %0" : "=m"(p[d+NSIZE*1]));
+		/* *(unative_t *)&q[d+NSIZE*$$] = wq$$; */
+		asm volatile("xvst $xr2, %0" : "=m"(q[d+NSIZE*0]));
+		asm volatile("xvst $xr3, %0" : "=m"(q[d+NSIZE*1]));
+	}
+
+	kernel_fpu_end();
+}
+
+static void raid6_lasx_xor_syndrome(int disks, int start, int stop,
+				    size_t bytes, void **ptrs)
+{
+	u8 **dptr = (u8 **)ptrs;
+	u8 *p, *q;
+	int d, z, z0;
+
+	z0 = stop;		/* P/Q right side optimization */
+	p = dptr[disks-2];	/* XOR parity */
+	q = dptr[disks-1];	/* RS syndrome */
+
+	kernel_fpu_begin();
+
+	/*
+	 * $xr0, $xr1: wp
+	 * $xr2, $xr3: wq
+	 * $xr4, $xr5: wd
+	 * $xr6, $xr7: w2
+	 * $xr8, $xr9: w1
+	 */
+	for (d = 0; d < bytes; d += NSIZE*2) {
+		/* P/Q data pages */
+		/* wq$$ = wp$$ = *(unative_t *)&dptr[z0][d+$$*NSIZE]; */
+		asm volatile("xvld $xr0, %0" : : "m"(dptr[z0][d+0*NSIZE]));
+		asm volatile("xvld $xr1, %0" : : "m"(dptr[z0][d+1*NSIZE]));
+		asm volatile("xvori.b $xr2, $xr0, 0");
+		asm volatile("xvori.b $xr3, $xr1, 0");
+		for (z = z0-1; z >= start; z--) {
+			/* wd$$ = *(unative_t *)&dptr[z][d+$$*NSIZE]; */
+			asm volatile("xvld $xr4, %0" : : "m"(dptr[z][d+0*NSIZE]));
+			asm volatile("xvld $xr5, %0" : : "m"(dptr[z][d+1*NSIZE]));
+			/* wp$$ ^= wd$$; */
+			asm volatile("xvxor.v $xr0, $xr0, $xr4");
+			asm volatile("xvxor.v $xr1, $xr1, $xr5");
+			/* w2$$ = MASK(wq$$); */
+			asm volatile("xvslti.b $xr6, $xr2, 0");
+			asm volatile("xvslti.b $xr7, $xr3, 0");
+			/* w1$$ = SHLBYTE(wq$$); */
+			asm volatile("xvslli.b $xr8, $xr2, 1");
+			asm volatile("xvslli.b $xr9, $xr3, 1");
+			/* w2$$ &= NBYTES(0x1d); */
+			asm volatile("xvandi.b $xr6, $xr6, 0x1d");
+			asm volatile("xvandi.b $xr7, $xr7, 0x1d");
+			/* w1$$ ^= w2$$; */
+			asm volatile("xvxor.v $xr8, $xr8, $xr6");
+			asm volatile("xvxor.v $xr9, $xr9, $xr7");
+			/* wq$$ = w1$$ ^ wd$$; */
+			asm volatile("xvxor.v $xr2, $xr8, $xr4");
+			asm volatile("xvxor.v $xr3, $xr9, $xr5");
+		}
+
+		/* P/Q left side optimization */
+		for (z = start-1; z >= 0; z--) {
+			/* w2$$ = MASK(wq$$); */
+			asm volatile("xvslti.b $xr6, $xr2, 0");
+			asm volatile("xvslti.b $xr7, $xr3, 0");
+			/* w1$$ = SHLBYTE(wq$$); */
+			asm volatile("xvslli.b $xr8, $xr2, 1");
+			asm volatile("xvslli.b $xr9, $xr3, 1");
+			/* w2$$ &= NBYTES(0x1d); */
+			asm volatile("xvandi.b $xr6, $xr6, 0x1d");
+			asm volatile("xvandi.b $xr7, $xr7, 0x1d");
+			/* wq$$ = w1$$ ^ w2$$; */
+			asm volatile("xvxor.v $xr2, $xr8, $xr6");
+			asm volatile("xvxor.v $xr3, $xr9, $xr7");
+		}
+		/*
+		 * *(unative_t *)&p[d+NSIZE*$$] ^= wp$$;
+		 * *(unative_t *)&q[d+NSIZE*$$] ^= wq$$;
+		 */
+		asm volatile(
+			"xvld $xr10, %0\n\t"
+			"xvld $xr11, %1\n\t"
+			"xvld $xr12, %2\n\t"
+			"xvld $xr13, %3\n\t"
+			"xvxor.v $xr10, $xr10, $xr0\n\t"
+			"xvxor.v $xr11, $xr11, $xr1\n\t"
+			"xvxor.v $xr12, $xr12, $xr2\n\t"
+			"xvxor.v $xr13, $xr13, $xr3\n\t"
+			"xvst $xr10, %0\n\t"
+			"xvst $xr11, %1\n\t"
+			"xvst $xr12, %2\n\t"
+			"xvst $xr13, %3\n\t"
+			: "+m"(p[d+NSIZE*0]), "+m"(p[d+NSIZE*1]),
+			  "+m"(q[d+NSIZE*0]), "+m"(q[d+NSIZE*1])
+		);
+	}
+
+	kernel_fpu_end();
+}
+
+const struct raid6_calls raid6_lasx = {
+	raid6_lasx_gen_syndrome,
+	raid6_lasx_xor_syndrome,
+	raid6_has_lasx,
+	"lasx",
+	.priority = 0 /* see the comment near the top of the file for reason */
+};
+#undef NSIZE
+#endif /* CONFIG_CPU_HAS_LASX */
diff --git a/lib/raid6/test/Makefile b/lib/raid6/test/Makefile
index 1f693ea3b980..7b244bce32b3 100644
--- a/lib/raid6/test/Makefile
+++ b/lib/raid6/test/Makefile
@@ -41,6 +41,16 @@ ifeq ($(findstring ppc,$(ARCH)),ppc)
                          gcc -c -x c - >/dev/null && rm ./-.o && echo yes)
 endif
 
+ifeq ($(ARCH),loongarch64)
+        CFLAGS += -I../../../arch/loongarch/include -DCONFIG_LOONGARCH=1
+        CFLAGS += $(shell echo 'vld $$vr0, $$zero, 0' |         \
+                    gcc -c -x assembler - >/dev/null 2>&1 &&    \
+                    rm ./-.o && echo -DCONFIG_CPU_HAS_LSX=1)
+        CFLAGS += $(shell echo 'xvld $$xr0, $$zero, 0' |        \
+                    gcc -c -x assembler - >/dev/null 2>&1 &&    \
+                    rm ./-.o && echo -DCONFIG_CPU_HAS_LASX=1)
+endif
+
 ifeq ($(IS_X86),yes)
         OBJS   += mmx.o sse1.o sse2.o avx2.o recov_ssse3.o recov_avx2.o avx512.o recov_avx512.o
         CFLAGS += -DCONFIG_X86
@@ -54,6 +64,8 @@ else ifeq ($(HAS_ALTIVEC),yes)
         CFLAGS += -DCONFIG_ALTIVEC
         OBJS += altivec1.o altivec2.o altivec4.o altivec8.o \
                 vpermxor1.o vpermxor2.o vpermxor4.o vpermxor8.o
+else ifeq ($(ARCH),loongarch64)
+        OBJS += loongarch_simd.o
 endif
 
 .c.o:

From f2091321044d9fbcadb93dfc1c9cf23e563ea40c Mon Sep 17 00:00:00 2001
From: WANG Xuerui <git@xen0n.name>
Date: Wed, 6 Sep 2023 22:53:55 +0800
Subject: [PATCH 1121/1189] raid6: Add LoongArch SIMD recovery implementation

Similar to the syndrome calculation, the recovery algorithms also work
on 64 bytes at a time to align with the L1 cache line size of current
and future LoongArch cores (that we care about). Which means
unrolled-by-4 LSX and unrolled-by-2 LASX code.

The assembly is originally based on the x86 SSSE3/AVX2 ports, but
register allocation has been redone to take advantage of LSX/LASX's 32
vector registers, and instruction sequence has been optimized to suit
(e.g. LoongArch can perform per-byte srl and andi on vectors, but x86
cannot).

Performance numbers measured by instrumenting the raid6test code, on a
3A5000 system clocked at 2.5GHz:

> lasx  2data: 354.987 MiB/s
> lasx  datap: 350.430 MiB/s
> lsx   2data: 340.026 MiB/s
> lsx   datap: 337.318 MiB/s
> intx1 2data: 164.280 MiB/s
> intx1 datap: 187.966 MiB/s

Because recovery algorithms are chosen solely based on priority and
availability, lasx is marked as priority 2 and lsx priority 1. At least
for the current generation of LoongArch micro-architectures, LASX should
always be faster than LSX whenever supported, and have similar power
consumption characteristics (because the only known LASX-capable uarch,
the LA464, always compute the full 256-bit result for vector ops).

Acked-by: Song Liu <song@kernel.org>
Signed-off-by: WANG Xuerui <git@xen0n.name>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 include/linux/raid/pq.h          |   2 +
 lib/raid6/Makefile               |   2 +-
 lib/raid6/algos.c                |   8 +
 lib/raid6/recov_loongarch_simd.c | 513 +++++++++++++++++++++++++++++++
 lib/raid6/test/Makefile          |   2 +-
 5 files changed, 525 insertions(+), 2 deletions(-)
 create mode 100644 lib/raid6/recov_loongarch_simd.c

diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h
index 874447485848..006e18decfad 100644
--- a/include/linux/raid/pq.h
+++ b/include/linux/raid/pq.h
@@ -125,6 +125,8 @@ extern const struct raid6_recov_calls raid6_recov_avx2;
 extern const struct raid6_recov_calls raid6_recov_avx512;
 extern const struct raid6_recov_calls raid6_recov_s390xc;
 extern const struct raid6_recov_calls raid6_recov_neon;
+extern const struct raid6_recov_calls raid6_recov_lsx;
+extern const struct raid6_recov_calls raid6_recov_lasx;
 
 extern const struct raid6_calls raid6_neonx1;
 extern const struct raid6_calls raid6_neonx2;
diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile
index 2b9ebe105480..035b0a4db476 100644
--- a/lib/raid6/Makefile
+++ b/lib/raid6/Makefile
@@ -9,7 +9,7 @@ raid6_pq-$(CONFIG_ALTIVEC) += altivec1.o altivec2.o altivec4.o altivec8.o \
                               vpermxor1.o vpermxor2.o vpermxor4.o vpermxor8.o
 raid6_pq-$(CONFIG_KERNEL_MODE_NEON) += neon.o neon1.o neon2.o neon4.o neon8.o recov_neon.o recov_neon_inner.o
 raid6_pq-$(CONFIG_S390) += s390vx8.o recov_s390xc.o
-raid6_pq-$(CONFIG_LOONGARCH) += loongarch_simd.o
+raid6_pq-$(CONFIG_LOONGARCH) += loongarch_simd.o recov_loongarch_simd.o
 
 hostprogs	+= mktables
 
diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c
index 739c7ebcae1a..0ec534faf019 100644
--- a/lib/raid6/algos.c
+++ b/lib/raid6/algos.c
@@ -111,6 +111,14 @@ const struct raid6_recov_calls *const raid6_recov_algos[] = {
 #endif
 #if defined(CONFIG_KERNEL_MODE_NEON)
 	&raid6_recov_neon,
+#endif
+#ifdef CONFIG_LOONGARCH
+#ifdef CONFIG_CPU_HAS_LASX
+	&raid6_recov_lasx,
+#endif
+#ifdef CONFIG_CPU_HAS_LSX
+	&raid6_recov_lsx,
+#endif
 #endif
 	&raid6_recov_intx1,
 	NULL
diff --git a/lib/raid6/recov_loongarch_simd.c b/lib/raid6/recov_loongarch_simd.c
new file mode 100644
index 000000000000..94aeac85e6f7
--- /dev/null
+++ b/lib/raid6/recov_loongarch_simd.c
@@ -0,0 +1,513 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * RAID6 recovery algorithms in LoongArch SIMD (LSX & LASX)
+ *
+ * Copyright (C) 2023 WANG Xuerui <git@xen0n.name>
+ *
+ * Originally based on recov_avx2.c and recov_ssse3.c:
+ *
+ * Copyright (C) 2012 Intel Corporation
+ * Author: Jim Kukunas <james.t.kukunas@linux.intel.com>
+ */
+
+#include <linux/raid/pq.h>
+#include "loongarch.h"
+
+/*
+ * Unlike with the syndrome calculation algorithms, there's no boot-time
+ * selection of recovery algorithms by benchmarking, so we have to specify
+ * the priorities and hope the future cores will all have decent vector
+ * support (i.e. no LASX slower than LSX, or even scalar code).
+ */
+
+#ifdef CONFIG_CPU_HAS_LSX
+static int raid6_has_lsx(void)
+{
+	return cpu_has_lsx;
+}
+
+static void raid6_2data_recov_lsx(int disks, size_t bytes, int faila,
+				  int failb, void **ptrs)
+{
+	u8 *p, *q, *dp, *dq;
+	const u8 *pbmul;	/* P multiplier table for B data */
+	const u8 *qmul;		/* Q multiplier table (for both) */
+
+	p = (u8 *)ptrs[disks - 2];
+	q = (u8 *)ptrs[disks - 1];
+
+	/*
+	 * Compute syndrome with zero for the missing data pages
+	 * Use the dead data pages as temporary storage for
+	 * delta p and delta q
+	 */
+	dp = (u8 *)ptrs[faila];
+	ptrs[faila] = (void *)raid6_empty_zero_page;
+	ptrs[disks - 2] = dp;
+	dq = (u8 *)ptrs[failb];
+	ptrs[failb] = (void *)raid6_empty_zero_page;
+	ptrs[disks - 1] = dq;
+
+	raid6_call.gen_syndrome(disks, bytes, ptrs);
+
+	/* Restore pointer table */
+	ptrs[faila] = dp;
+	ptrs[failb] = dq;
+	ptrs[disks - 2] = p;
+	ptrs[disks - 1] = q;
+
+	/* Now, pick the proper data tables */
+	pbmul = raid6_vgfmul[raid6_gfexi[failb - faila]];
+	qmul  = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila] ^ raid6_gfexp[failb]]];
+
+	kernel_fpu_begin();
+
+	/*
+	 * vr20, vr21: qmul
+	 * vr22, vr23: pbmul
+	 */
+	asm volatile("vld $vr20, %0" : : "m" (qmul[0]));
+	asm volatile("vld $vr21, %0" : : "m" (qmul[16]));
+	asm volatile("vld $vr22, %0" : : "m" (pbmul[0]));
+	asm volatile("vld $vr23, %0" : : "m" (pbmul[16]));
+
+	while (bytes) {
+		/* vr4 - vr7: Q */
+		asm volatile("vld $vr4, %0" : : "m" (q[0]));
+		asm volatile("vld $vr5, %0" : : "m" (q[16]));
+		asm volatile("vld $vr6, %0" : : "m" (q[32]));
+		asm volatile("vld $vr7, %0" : : "m" (q[48]));
+		/*  vr4 - vr7: Q + Qxy */
+		asm volatile("vld $vr8, %0" : : "m" (dq[0]));
+		asm volatile("vld $vr9, %0" : : "m" (dq[16]));
+		asm volatile("vld $vr10, %0" : : "m" (dq[32]));
+		asm volatile("vld $vr11, %0" : : "m" (dq[48]));
+		asm volatile("vxor.v $vr4, $vr4, $vr8");
+		asm volatile("vxor.v $vr5, $vr5, $vr9");
+		asm volatile("vxor.v $vr6, $vr6, $vr10");
+		asm volatile("vxor.v $vr7, $vr7, $vr11");
+		/* vr0 - vr3: P */
+		asm volatile("vld $vr0, %0" : : "m" (p[0]));
+		asm volatile("vld $vr1, %0" : : "m" (p[16]));
+		asm volatile("vld $vr2, %0" : : "m" (p[32]));
+		asm volatile("vld $vr3, %0" : : "m" (p[48]));
+		/* vr0 - vr3: P + Pxy */
+		asm volatile("vld $vr8, %0" : : "m" (dp[0]));
+		asm volatile("vld $vr9, %0" : : "m" (dp[16]));
+		asm volatile("vld $vr10, %0" : : "m" (dp[32]));
+		asm volatile("vld $vr11, %0" : : "m" (dp[48]));
+		asm volatile("vxor.v $vr0, $vr0, $vr8");
+		asm volatile("vxor.v $vr1, $vr1, $vr9");
+		asm volatile("vxor.v $vr2, $vr2, $vr10");
+		asm volatile("vxor.v $vr3, $vr3, $vr11");
+
+		/* vr8 - vr11: higher 4 bits of each byte of (Q + Qxy) */
+		asm volatile("vsrli.b $vr8, $vr4, 4");
+		asm volatile("vsrli.b $vr9, $vr5, 4");
+		asm volatile("vsrli.b $vr10, $vr6, 4");
+		asm volatile("vsrli.b $vr11, $vr7, 4");
+		/* vr4 - vr7: lower 4 bits of each byte of (Q + Qxy) */
+		asm volatile("vandi.b $vr4, $vr4, 0x0f");
+		asm volatile("vandi.b $vr5, $vr5, 0x0f");
+		asm volatile("vandi.b $vr6, $vr6, 0x0f");
+		asm volatile("vandi.b $vr7, $vr7, 0x0f");
+		/* lookup from qmul[0] */
+		asm volatile("vshuf.b $vr4, $vr20, $vr20, $vr4");
+		asm volatile("vshuf.b $vr5, $vr20, $vr20, $vr5");
+		asm volatile("vshuf.b $vr6, $vr20, $vr20, $vr6");
+		asm volatile("vshuf.b $vr7, $vr20, $vr20, $vr7");
+		/* lookup from qmul[16] */
+		asm volatile("vshuf.b $vr8, $vr21, $vr21, $vr8");
+		asm volatile("vshuf.b $vr9, $vr21, $vr21, $vr9");
+		asm volatile("vshuf.b $vr10, $vr21, $vr21, $vr10");
+		asm volatile("vshuf.b $vr11, $vr21, $vr21, $vr11");
+		/* vr16 - vr19: B(Q + Qxy) */
+		asm volatile("vxor.v $vr16, $vr8, $vr4");
+		asm volatile("vxor.v $vr17, $vr9, $vr5");
+		asm volatile("vxor.v $vr18, $vr10, $vr6");
+		asm volatile("vxor.v $vr19, $vr11, $vr7");
+
+		/* vr4 - vr7: higher 4 bits of each byte of (P + Pxy) */
+		asm volatile("vsrli.b $vr4, $vr0, 4");
+		asm volatile("vsrli.b $vr5, $vr1, 4");
+		asm volatile("vsrli.b $vr6, $vr2, 4");
+		asm volatile("vsrli.b $vr7, $vr3, 4");
+		/* vr12 - vr15: lower 4 bits of each byte of (P + Pxy) */
+		asm volatile("vandi.b $vr12, $vr0, 0x0f");
+		asm volatile("vandi.b $vr13, $vr1, 0x0f");
+		asm volatile("vandi.b $vr14, $vr2, 0x0f");
+		asm volatile("vandi.b $vr15, $vr3, 0x0f");
+		/* lookup from pbmul[0] */
+		asm volatile("vshuf.b $vr12, $vr22, $vr22, $vr12");
+		asm volatile("vshuf.b $vr13, $vr22, $vr22, $vr13");
+		asm volatile("vshuf.b $vr14, $vr22, $vr22, $vr14");
+		asm volatile("vshuf.b $vr15, $vr22, $vr22, $vr15");
+		/* lookup from pbmul[16] */
+		asm volatile("vshuf.b $vr4, $vr23, $vr23, $vr4");
+		asm volatile("vshuf.b $vr5, $vr23, $vr23, $vr5");
+		asm volatile("vshuf.b $vr6, $vr23, $vr23, $vr6");
+		asm volatile("vshuf.b $vr7, $vr23, $vr23, $vr7");
+		/* vr4 - vr7: A(P + Pxy) */
+		asm volatile("vxor.v $vr4, $vr4, $vr12");
+		asm volatile("vxor.v $vr5, $vr5, $vr13");
+		asm volatile("vxor.v $vr6, $vr6, $vr14");
+		asm volatile("vxor.v $vr7, $vr7, $vr15");
+
+		/* vr4 - vr7: A(P + Pxy) + B(Q + Qxy) = Dx */
+		asm volatile("vxor.v $vr4, $vr4, $vr16");
+		asm volatile("vxor.v $vr5, $vr5, $vr17");
+		asm volatile("vxor.v $vr6, $vr6, $vr18");
+		asm volatile("vxor.v $vr7, $vr7, $vr19");
+		asm volatile("vst $vr4, %0" : "=m" (dq[0]));
+		asm volatile("vst $vr5, %0" : "=m" (dq[16]));
+		asm volatile("vst $vr6, %0" : "=m" (dq[32]));
+		asm volatile("vst $vr7, %0" : "=m" (dq[48]));
+
+		/* vr0 - vr3: P + Pxy + Dx = Dy */
+		asm volatile("vxor.v $vr0, $vr0, $vr4");
+		asm volatile("vxor.v $vr1, $vr1, $vr5");
+		asm volatile("vxor.v $vr2, $vr2, $vr6");
+		asm volatile("vxor.v $vr3, $vr3, $vr7");
+		asm volatile("vst $vr0, %0" : "=m" (dp[0]));
+		asm volatile("vst $vr1, %0" : "=m" (dp[16]));
+		asm volatile("vst $vr2, %0" : "=m" (dp[32]));
+		asm volatile("vst $vr3, %0" : "=m" (dp[48]));
+
+		bytes -= 64;
+		p += 64;
+		q += 64;
+		dp += 64;
+		dq += 64;
+	}
+
+	kernel_fpu_end();
+}
+
+static void raid6_datap_recov_lsx(int disks, size_t bytes, int faila,
+				  void **ptrs)
+{
+	u8 *p, *q, *dq;
+	const u8 *qmul;		/* Q multiplier table */
+
+	p = (u8 *)ptrs[disks - 2];
+	q = (u8 *)ptrs[disks - 1];
+
+	/*
+	 * Compute syndrome with zero for the missing data page
+	 * Use the dead data page as temporary storage for delta q
+	 */
+	dq = (u8 *)ptrs[faila];
+	ptrs[faila] = (void *)raid6_empty_zero_page;
+	ptrs[disks - 1] = dq;
+
+	raid6_call.gen_syndrome(disks, bytes, ptrs);
+
+	/* Restore pointer table */
+	ptrs[faila] = dq;
+	ptrs[disks - 1] = q;
+
+	/* Now, pick the proper data tables */
+	qmul  = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila]]];
+
+	kernel_fpu_begin();
+
+	/* vr22, vr23: qmul */
+	asm volatile("vld $vr22, %0" : : "m" (qmul[0]));
+	asm volatile("vld $vr23, %0" : : "m" (qmul[16]));
+
+	while (bytes) {
+		/* vr0 - vr3: P + Dx */
+		asm volatile("vld $vr0, %0" : : "m" (p[0]));
+		asm volatile("vld $vr1, %0" : : "m" (p[16]));
+		asm volatile("vld $vr2, %0" : : "m" (p[32]));
+		asm volatile("vld $vr3, %0" : : "m" (p[48]));
+		/* vr4 - vr7: Qx */
+		asm volatile("vld $vr4, %0" : : "m" (dq[0]));
+		asm volatile("vld $vr5, %0" : : "m" (dq[16]));
+		asm volatile("vld $vr6, %0" : : "m" (dq[32]));
+		asm volatile("vld $vr7, %0" : : "m" (dq[48]));
+		/* vr4 - vr7: Q + Qx */
+		asm volatile("vld $vr8, %0" : : "m" (q[0]));
+		asm volatile("vld $vr9, %0" : : "m" (q[16]));
+		asm volatile("vld $vr10, %0" : : "m" (q[32]));
+		asm volatile("vld $vr11, %0" : : "m" (q[48]));
+		asm volatile("vxor.v $vr4, $vr4, $vr8");
+		asm volatile("vxor.v $vr5, $vr5, $vr9");
+		asm volatile("vxor.v $vr6, $vr6, $vr10");
+		asm volatile("vxor.v $vr7, $vr7, $vr11");
+
+		/* vr8 - vr11: higher 4 bits of each byte of (Q + Qx) */
+		asm volatile("vsrli.b $vr8, $vr4, 4");
+		asm volatile("vsrli.b $vr9, $vr5, 4");
+		asm volatile("vsrli.b $vr10, $vr6, 4");
+		asm volatile("vsrli.b $vr11, $vr7, 4");
+		/* vr4 - vr7: lower 4 bits of each byte of (Q + Qx) */
+		asm volatile("vandi.b $vr4, $vr4, 0x0f");
+		asm volatile("vandi.b $vr5, $vr5, 0x0f");
+		asm volatile("vandi.b $vr6, $vr6, 0x0f");
+		asm volatile("vandi.b $vr7, $vr7, 0x0f");
+		/* lookup from qmul[0] */
+		asm volatile("vshuf.b $vr4, $vr22, $vr22, $vr4");
+		asm volatile("vshuf.b $vr5, $vr22, $vr22, $vr5");
+		asm volatile("vshuf.b $vr6, $vr22, $vr22, $vr6");
+		asm volatile("vshuf.b $vr7, $vr22, $vr22, $vr7");
+		/* lookup from qmul[16] */
+		asm volatile("vshuf.b $vr8, $vr23, $vr23, $vr8");
+		asm volatile("vshuf.b $vr9, $vr23, $vr23, $vr9");
+		asm volatile("vshuf.b $vr10, $vr23, $vr23, $vr10");
+		asm volatile("vshuf.b $vr11, $vr23, $vr23, $vr11");
+		/* vr4 - vr7: qmul(Q + Qx) = Dx */
+		asm volatile("vxor.v $vr4, $vr4, $vr8");
+		asm volatile("vxor.v $vr5, $vr5, $vr9");
+		asm volatile("vxor.v $vr6, $vr6, $vr10");
+		asm volatile("vxor.v $vr7, $vr7, $vr11");
+		asm volatile("vst $vr4, %0" : "=m" (dq[0]));
+		asm volatile("vst $vr5, %0" : "=m" (dq[16]));
+		asm volatile("vst $vr6, %0" : "=m" (dq[32]));
+		asm volatile("vst $vr7, %0" : "=m" (dq[48]));
+
+		/* vr0 - vr3: P + Dx + Dx = P */
+		asm volatile("vxor.v $vr0, $vr0, $vr4");
+		asm volatile("vxor.v $vr1, $vr1, $vr5");
+		asm volatile("vxor.v $vr2, $vr2, $vr6");
+		asm volatile("vxor.v $vr3, $vr3, $vr7");
+		asm volatile("vst $vr0, %0" : "=m" (p[0]));
+		asm volatile("vst $vr1, %0" : "=m" (p[16]));
+		asm volatile("vst $vr2, %0" : "=m" (p[32]));
+		asm volatile("vst $vr3, %0" : "=m" (p[48]));
+
+		bytes -= 64;
+		p += 64;
+		q += 64;
+		dq += 64;
+	}
+
+	kernel_fpu_end();
+}
+
+const struct raid6_recov_calls raid6_recov_lsx = {
+	.data2 = raid6_2data_recov_lsx,
+	.datap = raid6_datap_recov_lsx,
+	.valid = raid6_has_lsx,
+	.name = "lsx",
+	.priority = 1,
+};
+#endif /* CONFIG_CPU_HAS_LSX */
+
+#ifdef CONFIG_CPU_HAS_LASX
+static int raid6_has_lasx(void)
+{
+	return cpu_has_lasx;
+}
+
+static void raid6_2data_recov_lasx(int disks, size_t bytes, int faila,
+				   int failb, void **ptrs)
+{
+	u8 *p, *q, *dp, *dq;
+	const u8 *pbmul;	/* P multiplier table for B data */
+	const u8 *qmul;		/* Q multiplier table (for both) */
+
+	p = (u8 *)ptrs[disks - 2];
+	q = (u8 *)ptrs[disks - 1];
+
+	/*
+	 * Compute syndrome with zero for the missing data pages
+	 * Use the dead data pages as temporary storage for
+	 * delta p and delta q
+	 */
+	dp = (u8 *)ptrs[faila];
+	ptrs[faila] = (void *)raid6_empty_zero_page;
+	ptrs[disks - 2] = dp;
+	dq = (u8 *)ptrs[failb];
+	ptrs[failb] = (void *)raid6_empty_zero_page;
+	ptrs[disks - 1] = dq;
+
+	raid6_call.gen_syndrome(disks, bytes, ptrs);
+
+	/* Restore pointer table */
+	ptrs[faila] = dp;
+	ptrs[failb] = dq;
+	ptrs[disks - 2] = p;
+	ptrs[disks - 1] = q;
+
+	/* Now, pick the proper data tables */
+	pbmul = raid6_vgfmul[raid6_gfexi[failb - faila]];
+	qmul  = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila] ^ raid6_gfexp[failb]]];
+
+	kernel_fpu_begin();
+
+	/*
+	 * xr20, xr21: qmul
+	 * xr22, xr23: pbmul
+	 */
+	asm volatile("vld $vr20, %0" : : "m" (qmul[0]));
+	asm volatile("vld $vr21, %0" : : "m" (qmul[16]));
+	asm volatile("vld $vr22, %0" : : "m" (pbmul[0]));
+	asm volatile("vld $vr23, %0" : : "m" (pbmul[16]));
+	asm volatile("xvreplve0.q $xr20, $xr20");
+	asm volatile("xvreplve0.q $xr21, $xr21");
+	asm volatile("xvreplve0.q $xr22, $xr22");
+	asm volatile("xvreplve0.q $xr23, $xr23");
+
+	while (bytes) {
+		/* xr0, xr1: Q */
+		asm volatile("xvld $xr0, %0" : : "m" (q[0]));
+		asm volatile("xvld $xr1, %0" : : "m" (q[32]));
+		/* xr0, xr1: Q + Qxy */
+		asm volatile("xvld $xr4, %0" : : "m" (dq[0]));
+		asm volatile("xvld $xr5, %0" : : "m" (dq[32]));
+		asm volatile("xvxor.v $xr0, $xr0, $xr4");
+		asm volatile("xvxor.v $xr1, $xr1, $xr5");
+		/* xr2, xr3: P */
+		asm volatile("xvld $xr2, %0" : : "m" (p[0]));
+		asm volatile("xvld $xr3, %0" : : "m" (p[32]));
+		/* xr2, xr3: P + Pxy */
+		asm volatile("xvld $xr4, %0" : : "m" (dp[0]));
+		asm volatile("xvld $xr5, %0" : : "m" (dp[32]));
+		asm volatile("xvxor.v $xr2, $xr2, $xr4");
+		asm volatile("xvxor.v $xr3, $xr3, $xr5");
+
+		/* xr4, xr5: higher 4 bits of each byte of (Q + Qxy) */
+		asm volatile("xvsrli.b $xr4, $xr0, 4");
+		asm volatile("xvsrli.b $xr5, $xr1, 4");
+		/* xr0, xr1: lower 4 bits of each byte of (Q + Qxy) */
+		asm volatile("xvandi.b $xr0, $xr0, 0x0f");
+		asm volatile("xvandi.b $xr1, $xr1, 0x0f");
+		/* lookup from qmul[0] */
+		asm volatile("xvshuf.b $xr0, $xr20, $xr20, $xr0");
+		asm volatile("xvshuf.b $xr1, $xr20, $xr20, $xr1");
+		/* lookup from qmul[16] */
+		asm volatile("xvshuf.b $xr4, $xr21, $xr21, $xr4");
+		asm volatile("xvshuf.b $xr5, $xr21, $xr21, $xr5");
+		/* xr6, xr7: B(Q + Qxy) */
+		asm volatile("xvxor.v $xr6, $xr4, $xr0");
+		asm volatile("xvxor.v $xr7, $xr5, $xr1");
+
+		/* xr4, xr5: higher 4 bits of each byte of (P + Pxy) */
+		asm volatile("xvsrli.b $xr4, $xr2, 4");
+		asm volatile("xvsrli.b $xr5, $xr3, 4");
+		/* xr0, xr1: lower 4 bits of each byte of (P + Pxy) */
+		asm volatile("xvandi.b $xr0, $xr2, 0x0f");
+		asm volatile("xvandi.b $xr1, $xr3, 0x0f");
+		/* lookup from pbmul[0] */
+		asm volatile("xvshuf.b $xr0, $xr22, $xr22, $xr0");
+		asm volatile("xvshuf.b $xr1, $xr22, $xr22, $xr1");
+		/* lookup from pbmul[16] */
+		asm volatile("xvshuf.b $xr4, $xr23, $xr23, $xr4");
+		asm volatile("xvshuf.b $xr5, $xr23, $xr23, $xr5");
+		/* xr0, xr1: A(P + Pxy) */
+		asm volatile("xvxor.v $xr0, $xr0, $xr4");
+		asm volatile("xvxor.v $xr1, $xr1, $xr5");
+
+		/* xr0, xr1: A(P + Pxy) + B(Q + Qxy) = Dx */
+		asm volatile("xvxor.v $xr0, $xr0, $xr6");
+		asm volatile("xvxor.v $xr1, $xr1, $xr7");
+
+		/* xr2, xr3: P + Pxy + Dx = Dy */
+		asm volatile("xvxor.v $xr2, $xr2, $xr0");
+		asm volatile("xvxor.v $xr3, $xr3, $xr1");
+
+		asm volatile("xvst $xr0, %0" : "=m" (dq[0]));
+		asm volatile("xvst $xr1, %0" : "=m" (dq[32]));
+		asm volatile("xvst $xr2, %0" : "=m" (dp[0]));
+		asm volatile("xvst $xr3, %0" : "=m" (dp[32]));
+
+		bytes -= 64;
+		p += 64;
+		q += 64;
+		dp += 64;
+		dq += 64;
+	}
+
+	kernel_fpu_end();
+}
+
+static void raid6_datap_recov_lasx(int disks, size_t bytes, int faila,
+				   void **ptrs)
+{
+	u8 *p, *q, *dq;
+	const u8 *qmul;		/* Q multiplier table */
+
+	p = (u8 *)ptrs[disks - 2];
+	q = (u8 *)ptrs[disks - 1];
+
+	/*
+	 * Compute syndrome with zero for the missing data page
+	 * Use the dead data page as temporary storage for delta q
+	 */
+	dq = (u8 *)ptrs[faila];
+	ptrs[faila] = (void *)raid6_empty_zero_page;
+	ptrs[disks - 1] = dq;
+
+	raid6_call.gen_syndrome(disks, bytes, ptrs);
+
+	/* Restore pointer table */
+	ptrs[faila] = dq;
+	ptrs[disks - 1] = q;
+
+	/* Now, pick the proper data tables */
+	qmul  = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila]]];
+
+	kernel_fpu_begin();
+
+	/* xr22, xr23: qmul */
+	asm volatile("vld $vr22, %0" : : "m" (qmul[0]));
+	asm volatile("xvreplve0.q $xr22, $xr22");
+	asm volatile("vld $vr23, %0" : : "m" (qmul[16]));
+	asm volatile("xvreplve0.q $xr23, $xr23");
+
+	while (bytes) {
+		/* xr0, xr1: P + Dx */
+		asm volatile("xvld $xr0, %0" : : "m" (p[0]));
+		asm volatile("xvld $xr1, %0" : : "m" (p[32]));
+		/* xr2, xr3: Qx */
+		asm volatile("xvld $xr2, %0" : : "m" (dq[0]));
+		asm volatile("xvld $xr3, %0" : : "m" (dq[32]));
+		/* xr2, xr3: Q + Qx */
+		asm volatile("xvld $xr4, %0" : : "m" (q[0]));
+		asm volatile("xvld $xr5, %0" : : "m" (q[32]));
+		asm volatile("xvxor.v $xr2, $xr2, $xr4");
+		asm volatile("xvxor.v $xr3, $xr3, $xr5");
+
+		/* xr4, xr5: higher 4 bits of each byte of (Q + Qx) */
+		asm volatile("xvsrli.b $xr4, $xr2, 4");
+		asm volatile("xvsrli.b $xr5, $xr3, 4");
+		/* xr2, xr3: lower 4 bits of each byte of (Q + Qx) */
+		asm volatile("xvandi.b $xr2, $xr2, 0x0f");
+		asm volatile("xvandi.b $xr3, $xr3, 0x0f");
+		/* lookup from qmul[0] */
+		asm volatile("xvshuf.b $xr2, $xr22, $xr22, $xr2");
+		asm volatile("xvshuf.b $xr3, $xr22, $xr22, $xr3");
+		/* lookup from qmul[16] */
+		asm volatile("xvshuf.b $xr4, $xr23, $xr23, $xr4");
+		asm volatile("xvshuf.b $xr5, $xr23, $xr23, $xr5");
+		/* xr2, xr3: qmul(Q + Qx) = Dx */
+		asm volatile("xvxor.v $xr2, $xr2, $xr4");
+		asm volatile("xvxor.v $xr3, $xr3, $xr5");
+
+		/* xr0, xr1: P + Dx + Dx = P */
+		asm volatile("xvxor.v $xr0, $xr0, $xr2");
+		asm volatile("xvxor.v $xr1, $xr1, $xr3");
+
+		asm volatile("xvst $xr2, %0" : "=m" (dq[0]));
+		asm volatile("xvst $xr3, %0" : "=m" (dq[32]));
+		asm volatile("xvst $xr0, %0" : "=m" (p[0]));
+		asm volatile("xvst $xr1, %0" : "=m" (p[32]));
+
+		bytes -= 64;
+		p += 64;
+		q += 64;
+		dq += 64;
+	}
+
+	kernel_fpu_end();
+}
+
+const struct raid6_recov_calls raid6_recov_lasx = {
+	.data2 = raid6_2data_recov_lasx,
+	.datap = raid6_datap_recov_lasx,
+	.valid = raid6_has_lasx,
+	.name = "lasx",
+	.priority = 2,
+};
+#endif /* CONFIG_CPU_HAS_LASX */
diff --git a/lib/raid6/test/Makefile b/lib/raid6/test/Makefile
index 7b244bce32b3..2abe0076a636 100644
--- a/lib/raid6/test/Makefile
+++ b/lib/raid6/test/Makefile
@@ -65,7 +65,7 @@ else ifeq ($(HAS_ALTIVEC),yes)
         OBJS += altivec1.o altivec2.o altivec4.o altivec8.o \
                 vpermxor1.o vpermxor2.o vpermxor4.o vpermxor8.o
 else ifeq ($(ARCH),loongarch64)
-        OBJS += loongarch_simd.o
+        OBJS += loongarch_simd.o recov_loongarch_simd.o
 endif
 
 .c.o:

From bd3c5798484aa9a08302a844d7a75a2ee3b53d05 Mon Sep 17 00:00:00 2001
From: Qi Hu <huqi@loongson.cn>
Date: Wed, 6 Sep 2023 22:53:55 +0800
Subject: [PATCH 1122/1189] LoongArch: Add Loongson Binary Translation (LBT)
 extension support

Loongson Binary Translation (LBT) is used to accelerate binary translation,
which contains 4 scratch registers (scr0 to scr3), x86/ARM eflags (eflags)
and x87 fpu stack pointer (ftop).

This patch support kernel to save/restore these registers, handle the LBT
exception and maintain sigcontext.

Signed-off-by: Qi Hu <huqi@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/Kconfig                       |  15 ++
 arch/loongarch/include/asm/asm-prototypes.h  |   1 +
 arch/loongarch/include/asm/asmmacro.h        |  51 ++++-
 arch/loongarch/include/asm/lbt.h             | 109 +++++++++++
 arch/loongarch/include/asm/loongarch.h       |   4 +
 arch/loongarch/include/asm/processor.h       |  26 +--
 arch/loongarch/include/asm/switch_to.h       |   2 +
 arch/loongarch/include/asm/thread_info.h     |   4 +
 arch/loongarch/include/uapi/asm/ptrace.h     |   6 +
 arch/loongarch/include/uapi/asm/sigcontext.h |  10 +
 arch/loongarch/kernel/Makefile               |   2 +
 arch/loongarch/kernel/asm-offsets.c          |  18 +-
 arch/loongarch/kernel/cpu-probe.c            |  14 ++
 arch/loongarch/kernel/fpu.S                  |   9 +-
 arch/loongarch/kernel/lbt.S                  | 155 +++++++++++++++
 arch/loongarch/kernel/process.c              |  15 +-
 arch/loongarch/kernel/ptrace.c               |  54 ++++++
 arch/loongarch/kernel/signal.c               | 188 +++++++++++++++++++
 arch/loongarch/kernel/traps.c                |  41 +++-
 19 files changed, 693 insertions(+), 31 deletions(-)
 create mode 100644 arch/loongarch/include/asm/lbt.h
 create mode 100644 arch/loongarch/kernel/lbt.S

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 465759f6b0ed..21cc2e2d1f27 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -254,6 +254,9 @@ config AS_HAS_LSX_EXTENSION
 config AS_HAS_LASX_EXTENSION
 	def_bool $(as-instr,xvld \$xr0$(comma)\$a0$(comma)0)
 
+config AS_HAS_LBT_EXTENSION
+	def_bool $(as-instr,movscr2gr \$a0$(comma)\$scr0)
+
 menu "Kernel type and options"
 
 source "kernel/Kconfig.hz"
@@ -534,6 +537,18 @@ config CPU_HAS_LASX
 
 	  If unsure, say Y.
 
+config CPU_HAS_LBT
+	bool "Support for the Loongson Binary Translation Extension"
+	depends on AS_HAS_LBT_EXTENSION
+	help
+	  Loongson Binary Translation (LBT) introduces 4 scratch registers (SCR0
+	  to SCR3), x86/ARM eflags (eflags) and x87 fpu stack pointer (ftop).
+	  Enabling this option allows the kernel to allocate and switch registers
+	  specific to LBT.
+
+	  If you want to use this feature, such as the Loongson Architecture
+	  Translator (LAT), say Y.
+
 config CPU_HAS_PREFETCH
 	bool
 	default y
diff --git a/arch/loongarch/include/asm/asm-prototypes.h b/arch/loongarch/include/asm/asm-prototypes.h
index ed06d3997420..cf8e1a4e7c19 100644
--- a/arch/loongarch/include/asm/asm-prototypes.h
+++ b/arch/loongarch/include/asm/asm-prototypes.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/uaccess.h>
 #include <asm/fpu.h>
+#include <asm/lbt.h>
 #include <asm/mmu_context.h>
 #include <asm/page.h>
 #include <asm/ftrace.h>
diff --git a/arch/loongarch/include/asm/asmmacro.h b/arch/loongarch/include/asm/asmmacro.h
index af542a8d847f..c9544f358c33 100644
--- a/arch/loongarch/include/asm/asmmacro.h
+++ b/arch/loongarch/include/asm/asmmacro.h
@@ -41,12 +41,51 @@
 
 	.macro fpu_save_csr thread tmp
 	movfcsr2gr	\tmp, fcsr0
-	stptr.w	\tmp, \thread, THREAD_FCSR
+	stptr.w		\tmp, \thread, THREAD_FCSR
+#ifdef CONFIG_CPU_HAS_LBT
+	/* TM bit is always 0 if LBT not supported */
+	andi		\tmp, \tmp, FPU_CSR_TM
+	beqz		\tmp, 1f
+	/* Save FTOP */
+	x86mftop	\tmp
+	stptr.w		\tmp, \thread, THREAD_FTOP
+	/* Turn off TM to ensure the order of FPR in memory independent of TM */
+	x86clrtm
+1:
+#endif
 	.endm
 
-	.macro fpu_restore_csr thread tmp
-	ldptr.w	\tmp, \thread, THREAD_FCSR
-	movgr2fcsr	fcsr0, \tmp
+	.macro fpu_restore_csr thread tmp0 tmp1
+	ldptr.w		\tmp0, \thread, THREAD_FCSR
+	movgr2fcsr	fcsr0, \tmp0
+#ifdef CONFIG_CPU_HAS_LBT
+	/* TM bit is always 0 if LBT not supported */
+	andi		\tmp0, \tmp0, FPU_CSR_TM
+	beqz		\tmp0, 2f
+	/* Restore FTOP */
+	ldptr.w		\tmp0, \thread, THREAD_FTOP
+	andi		\tmp0, \tmp0, 0x7
+	la.pcrel	\tmp1, 1f
+	alsl.d		\tmp1, \tmp0, \tmp1, 3
+	jr		\tmp1
+1:
+	x86mttop	0
+	b	2f
+	x86mttop	1
+	b	2f
+	x86mttop	2
+	b	2f
+	x86mttop	3
+	b	2f
+	x86mttop	4
+	b	2f
+	x86mttop	5
+	b	2f
+	x86mttop	6
+	b	2f
+	x86mttop	7
+2:
+#endif
 	.endm
 
 	.macro fpu_save_cc thread tmp0 tmp1
@@ -246,7 +285,7 @@
 	.macro	lsx_restore_all	thread tmp0 tmp1
 	lsx_restore_data	\thread, \tmp0
 	fpu_restore_cc		\thread, \tmp0, \tmp1
-	fpu_restore_csr		\thread, \tmp0
+	fpu_restore_csr		\thread, \tmp0, \tmp1
 	.endm
 
 	.macro	lsx_save_upper vd base tmp off
@@ -456,7 +495,7 @@
 	.macro	lasx_restore_all thread tmp0 tmp1
 	lasx_restore_data	\thread, \tmp0
 	fpu_restore_cc		\thread, \tmp0, \tmp1
-	fpu_restore_csr		\thread, \tmp0
+	fpu_restore_csr		\thread, \tmp0, \tmp1
 	.endm
 
 	.macro	lasx_save_upper xd base tmp off
diff --git a/arch/loongarch/include/asm/lbt.h b/arch/loongarch/include/asm/lbt.h
new file mode 100644
index 000000000000..e671978bf552
--- /dev/null
+++ b/arch/loongarch/include/asm/lbt.h
@@ -0,0 +1,109 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Author: Qi Hu <huqi@loongson.cn>
+ *         Huacai Chen <chenhuacai@loongson.cn>
+ * Copyright (C) 2020-2023 Loongson Technology Corporation Limited
+ */
+#ifndef _ASM_LBT_H
+#define _ASM_LBT_H
+
+#include <asm/cpu.h>
+#include <asm/current.h>
+#include <asm/loongarch.h>
+#include <asm/processor.h>
+
+extern void _init_lbt(void);
+extern void _save_lbt(struct loongarch_lbt *);
+extern void _restore_lbt(struct loongarch_lbt *);
+
+static inline int is_lbt_enabled(void)
+{
+	if (!cpu_has_lbt)
+		return 0;
+
+	return (csr_read32(LOONGARCH_CSR_EUEN) & CSR_EUEN_LBTEN) ?
+		1 : 0;
+}
+
+static inline int is_lbt_owner(void)
+{
+	return test_thread_flag(TIF_USEDLBT);
+}
+
+#ifdef CONFIG_CPU_HAS_LBT
+
+static inline void enable_lbt(void)
+{
+	if (cpu_has_lbt)
+		csr_xchg32(CSR_EUEN_LBTEN, CSR_EUEN_LBTEN, LOONGARCH_CSR_EUEN);
+}
+
+static inline void disable_lbt(void)
+{
+	if (cpu_has_lbt)
+		csr_xchg32(0, CSR_EUEN_LBTEN, LOONGARCH_CSR_EUEN);
+}
+
+static inline void __own_lbt(void)
+{
+	enable_lbt();
+	set_thread_flag(TIF_USEDLBT);
+	KSTK_EUEN(current) |= CSR_EUEN_LBTEN;
+}
+
+static inline void own_lbt_inatomic(int restore)
+{
+	if (cpu_has_lbt && !is_lbt_owner()) {
+		__own_lbt();
+		if (restore)
+			_restore_lbt(&current->thread.lbt);
+	}
+}
+
+static inline void own_lbt(int restore)
+{
+	preempt_disable();
+	own_lbt_inatomic(restore);
+	preempt_enable();
+}
+
+static inline void lose_lbt_inatomic(int save, struct task_struct *tsk)
+{
+	if (cpu_has_lbt && is_lbt_owner()) {
+		if (save)
+			_save_lbt(&tsk->thread.lbt);
+
+		disable_lbt();
+		clear_tsk_thread_flag(tsk, TIF_USEDLBT);
+	}
+	KSTK_EUEN(tsk) &= ~(CSR_EUEN_LBTEN);
+}
+
+static inline void lose_lbt(int save)
+{
+	preempt_disable();
+	lose_lbt_inatomic(save, current);
+	preempt_enable();
+}
+
+static inline void init_lbt(void)
+{
+	__own_lbt();
+	_init_lbt();
+}
+#else
+static inline void own_lbt_inatomic(int restore) {}
+static inline void lose_lbt_inatomic(int save, struct task_struct *tsk) {}
+static inline void init_lbt(void) {}
+static inline void lose_lbt(int save) {}
+#endif
+
+static inline int thread_lbt_context_live(void)
+{
+	if (!cpu_has_lbt)
+		return 0;
+
+	return test_thread_flag(TIF_LBT_CTX_LIVE);
+}
+
+#endif /* _ASM_LBT_H */
diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h
index a500efe0fd92..33531d432b49 100644
--- a/arch/loongarch/include/asm/loongarch.h
+++ b/arch/loongarch/include/asm/loongarch.h
@@ -1410,6 +1410,10 @@ __BUILD_CSR_OP(tlbidx)
 #define FPU_CSR_RU	0x200	/* towards +Infinity */
 #define FPU_CSR_RD	0x300	/* towards -Infinity */
 
+/* Bit 6 of FPU Status Register specify the LBT TOP simulation mode */
+#define FPU_CSR_TM_SHIFT	0x6
+#define FPU_CSR_TM		(_ULCAST_(1) << FPU_CSR_TM_SHIFT)
+
 #define read_fcsr(source)	\
 ({	\
 	unsigned int __res;	\
diff --git a/arch/loongarch/include/asm/processor.h b/arch/loongarch/include/asm/processor.h
index 636e1c66398c..c3bc44b5f5b3 100644
--- a/arch/loongarch/include/asm/processor.h
+++ b/arch/loongarch/include/asm/processor.h
@@ -80,11 +80,22 @@ BUILD_FPR_ACCESS(32)
 BUILD_FPR_ACCESS(64)
 
 struct loongarch_fpu {
-	unsigned int	fcsr;
 	uint64_t	fcc;	/* 8x8 */
+	uint32_t	fcsr;
+	uint32_t	ftop;
 	union fpureg	fpr[NUM_FPU_REGS];
 };
 
+struct loongarch_lbt {
+	/* Scratch registers */
+	unsigned long scr0;
+	unsigned long scr1;
+	unsigned long scr2;
+	unsigned long scr3;
+	/* Eflags register */
+	unsigned long eflags;
+};
+
 #define INIT_CPUMASK { \
 	{0,} \
 }
@@ -113,15 +124,6 @@ struct thread_struct {
 	unsigned long csr_ecfg;
 	unsigned long csr_badvaddr;	/* Last user fault */
 
-	/* Scratch registers */
-	unsigned long scr0;
-	unsigned long scr1;
-	unsigned long scr2;
-	unsigned long scr3;
-
-	/* Eflags register */
-	unsigned long eflags;
-
 	/* Other stuff associated with the thread. */
 	unsigned long trap_nr;
 	unsigned long error_code;
@@ -133,6 +135,7 @@ struct thread_struct {
 	 * context because they are conditionally copied at fork().
 	 */
 	struct loongarch_fpu fpu FPU_ALIGN;
+	struct loongarch_lbt lbt; /* Also conditionally copied */
 
 	/* Hardware breakpoints pinned to this task. */
 	struct perf_event *hbp_break[LOONGARCH_MAX_BRP];
@@ -174,8 +177,9 @@ struct thread_struct {
 	 * FPU & vector registers				\
 	 */							\
 	.fpu			= {				\
-		.fcsr		= 0,				\
 		.fcc		= 0,				\
+		.fcsr		= 0,				\
+		.ftop		= 0,				\
 		.fpr		= {{{0,},},},			\
 	},							\
 	.hbp_break		= {0},				\
diff --git a/arch/loongarch/include/asm/switch_to.h b/arch/loongarch/include/asm/switch_to.h
index 24e3094bebab..5b225aff3ba2 100644
--- a/arch/loongarch/include/asm/switch_to.h
+++ b/arch/loongarch/include/asm/switch_to.h
@@ -7,6 +7,7 @@
 
 #include <asm/cpu-features.h>
 #include <asm/fpu.h>
+#include <asm/lbt.h>
 
 struct task_struct;
 
@@ -34,6 +35,7 @@ extern asmlinkage struct task_struct *__switch_to(struct task_struct *prev,
 #define switch_to(prev, next, last)						\
 do {										\
 	lose_fpu_inatomic(1, prev);						\
+	lose_lbt_inatomic(1, prev);						\
 	hw_breakpoint_thread_switch(next);					\
 	(last) = __switch_to(prev, next, task_thread_info(next),		\
 		 __builtin_return_address(0), __builtin_frame_address(0));	\
diff --git a/arch/loongarch/include/asm/thread_info.h b/arch/loongarch/include/asm/thread_info.h
index 1a3354ca056e..8cb653d49a54 100644
--- a/arch/loongarch/include/asm/thread_info.h
+++ b/arch/loongarch/include/asm/thread_info.h
@@ -84,6 +84,8 @@ register unsigned long current_stack_pointer __asm__("$sp");
 #define TIF_SINGLESTEP		16	/* Single Step */
 #define TIF_LSX_CTX_LIVE	17	/* LSX context must be preserved */
 #define TIF_LASX_CTX_LIVE	18	/* LASX context must be preserved */
+#define TIF_USEDLBT		19	/* LBT was used by this task this quantum (SMP) */
+#define TIF_LBT_CTX_LIVE	20	/* LBT context must be preserved */
 
 #define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
@@ -101,6 +103,8 @@ register unsigned long current_stack_pointer __asm__("$sp");
 #define _TIF_SINGLESTEP		(1<<TIF_SINGLESTEP)
 #define _TIF_LSX_CTX_LIVE	(1<<TIF_LSX_CTX_LIVE)
 #define _TIF_LASX_CTX_LIVE	(1<<TIF_LASX_CTX_LIVE)
+#define _TIF_USEDLBT		(1<<TIF_USEDLBT)
+#define _TIF_LBT_CTX_LIVE	(1<<TIF_LBT_CTX_LIVE)
 
 #endif /* __KERNEL__ */
 #endif /* _ASM_THREAD_INFO_H */
diff --git a/arch/loongarch/include/uapi/asm/ptrace.h b/arch/loongarch/include/uapi/asm/ptrace.h
index 06e3be52cb04..ac915f841650 100644
--- a/arch/loongarch/include/uapi/asm/ptrace.h
+++ b/arch/loongarch/include/uapi/asm/ptrace.h
@@ -56,6 +56,12 @@ struct user_lasx_state {
 	uint64_t vregs[32*4];
 };
 
+struct user_lbt_state {
+	uint64_t scr[4];
+	uint32_t eflags;
+	uint32_t ftop;
+};
+
 struct user_watch_state {
 	uint64_t dbg_info;
 	struct {
diff --git a/arch/loongarch/include/uapi/asm/sigcontext.h b/arch/loongarch/include/uapi/asm/sigcontext.h
index 4cd7d16f7037..6c22f616b8f1 100644
--- a/arch/loongarch/include/uapi/asm/sigcontext.h
+++ b/arch/loongarch/include/uapi/asm/sigcontext.h
@@ -59,4 +59,14 @@ struct lasx_context {
 	__u32	fcsr;
 };
 
+/* LBT context */
+#define LBT_CTX_MAGIC		0x42540001
+#define LBT_CTX_ALIGN		8
+struct lbt_context {
+	__u64	regs[4];
+	__u32	eflags;
+	__u32	ftop;
+};
+
+
 #endif /* _UAPI_ASM_SIGCONTEXT_H */
diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile
index 8e279f04f9e7..5341dcf15a17 100644
--- a/arch/loongarch/kernel/Makefile
+++ b/arch/loongarch/kernel/Makefile
@@ -15,6 +15,8 @@ obj-$(CONFIG_EFI) 		+= efi.o
 
 obj-$(CONFIG_CPU_HAS_FPU)	+= fpu.o kfpu.o
 
+obj-$(CONFIG_CPU_HAS_LBT)	+= lbt.o
+
 obj-$(CONFIG_ARCH_STRICT_ALIGN)	+= unaligned.o
 
 ifdef CONFIG_FUNCTION_TRACER
diff --git a/arch/loongarch/kernel/asm-offsets.c b/arch/loongarch/kernel/asm-offsets.c
index 505e4bf59603..8da0726777ed 100644
--- a/arch/loongarch/kernel/asm-offsets.c
+++ b/arch/loongarch/kernel/asm-offsets.c
@@ -118,13 +118,6 @@ void output_thread_defines(void)
 	OFFSET(THREAD_CSRECFG, task_struct,
 	       thread.csr_ecfg);
 
-	OFFSET(THREAD_SCR0, task_struct, thread.scr0);
-	OFFSET(THREAD_SCR1, task_struct, thread.scr1);
-	OFFSET(THREAD_SCR2, task_struct, thread.scr2);
-	OFFSET(THREAD_SCR3, task_struct, thread.scr3);
-
-	OFFSET(THREAD_EFLAGS, task_struct, thread.eflags);
-
 	OFFSET(THREAD_FPU, task_struct, thread.fpu);
 
 	OFFSET(THREAD_BVADDR, task_struct, \
@@ -172,6 +165,17 @@ void output_thread_fpu_defines(void)
 
 	OFFSET(THREAD_FCSR, loongarch_fpu, fcsr);
 	OFFSET(THREAD_FCC,  loongarch_fpu, fcc);
+	OFFSET(THREAD_FTOP, loongarch_fpu, ftop);
+	BLANK();
+}
+
+void output_thread_lbt_defines(void)
+{
+	OFFSET(THREAD_SCR0,  loongarch_lbt, scr0);
+	OFFSET(THREAD_SCR1,  loongarch_lbt, scr1);
+	OFFSET(THREAD_SCR2,  loongarch_lbt, scr2);
+	OFFSET(THREAD_SCR3,  loongarch_lbt, scr3);
+	OFFSET(THREAD_EFLAGS, loongarch_lbt, eflags);
 	BLANK();
 }
 
diff --git a/arch/loongarch/kernel/cpu-probe.c b/arch/loongarch/kernel/cpu-probe.c
index e925579c7a71..55320813ee08 100644
--- a/arch/loongarch/kernel/cpu-probe.c
+++ b/arch/loongarch/kernel/cpu-probe.c
@@ -144,6 +144,20 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c)
 		c->options |= LOONGARCH_CPU_LVZ;
 		elf_hwcap |= HWCAP_LOONGARCH_LVZ;
 	}
+#ifdef CONFIG_CPU_HAS_LBT
+	if (config & CPUCFG2_X86BT) {
+		c->options |= LOONGARCH_CPU_LBT_X86;
+		elf_hwcap |= HWCAP_LOONGARCH_LBT_X86;
+	}
+	if (config & CPUCFG2_ARMBT) {
+		c->options |= LOONGARCH_CPU_LBT_ARM;
+		elf_hwcap |= HWCAP_LOONGARCH_LBT_ARM;
+	}
+	if (config & CPUCFG2_MIPSBT) {
+		c->options |= LOONGARCH_CPU_LBT_MIPS;
+		elf_hwcap |= HWCAP_LOONGARCH_LBT_MIPS;
+	}
+#endif
 
 	config = read_cpucfg(LOONGARCH_CPUCFG6);
 	if (config & CPUCFG6_PMP)
diff --git a/arch/loongarch/kernel/fpu.S b/arch/loongarch/kernel/fpu.S
index 80dccf8e39a7..d53ab10f4644 100644
--- a/arch/loongarch/kernel/fpu.S
+++ b/arch/loongarch/kernel/fpu.S
@@ -138,6 +138,13 @@
 	.macro sc_save_fcsr base, tmp0
 	movfcsr2gr	\tmp0, fcsr0
 	EX	st.w	\tmp0, \base, 0
+#if defined(CONFIG_CPU_HAS_LBT)
+	/* TM bit is always 0 if LBT not supported */
+	andi		\tmp0, \tmp0, FPU_CSR_TM
+	beqz		\tmp0, 1f
+	x86clrtm
+1:
+#endif
 	.endm
 
 	.macro sc_restore_fcsr base, tmp0
@@ -309,7 +316,7 @@ EXPORT_SYMBOL(_save_fp)
  */
 SYM_FUNC_START(_restore_fp)
 	fpu_restore_double	a0 t1		# clobbers t1
-	fpu_restore_csr		a0 t1
+	fpu_restore_csr		a0 t1 t2
 	fpu_restore_cc		a0 t1 t2	# clobbers t1, t2
 	jr			ra
 SYM_FUNC_END(_restore_fp)
diff --git a/arch/loongarch/kernel/lbt.S b/arch/loongarch/kernel/lbt.S
new file mode 100644
index 000000000000..9c75120a26d8
--- /dev/null
+++ b/arch/loongarch/kernel/lbt.S
@@ -0,0 +1,155 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Author: Qi Hu <huqi@loongson.cn>
+ *         Huacai Chen <chenhuacai@loongson.cn>
+ *
+ * Copyright (C) 2020-2023 Loongson Technology Corporation Limited
+ */
+#include <asm/asm.h>
+#include <asm/asmmacro.h>
+#include <asm/asm-extable.h>
+#include <asm/asm-offsets.h>
+#include <asm/errno.h>
+#include <asm/regdef.h>
+
+#define SCR_REG_WIDTH 8
+
+	.macro	EX insn, reg, src, offs
+.ex\@:	\insn	\reg, \src, \offs
+	_asm_extable .ex\@, .L_lbt_fault
+	.endm
+
+/*
+ * Save a thread's lbt context.
+ */
+SYM_FUNC_START(_save_lbt)
+	movscr2gr	t1, $scr0		# save scr
+	stptr.d		t1, a0, THREAD_SCR0
+	movscr2gr	t1, $scr1
+	stptr.d		t1, a0, THREAD_SCR1
+	movscr2gr	t1, $scr2
+	stptr.d		t1, a0, THREAD_SCR2
+	movscr2gr	t1, $scr3
+	stptr.d		t1, a0, THREAD_SCR3
+
+	x86mfflag	t1, 0x3f		# save eflags
+	stptr.d		t1, a0, THREAD_EFLAGS
+	jr		ra
+SYM_FUNC_END(_save_lbt)
+EXPORT_SYMBOL(_save_lbt)
+
+/*
+ * Restore a thread's lbt context.
+ */
+SYM_FUNC_START(_restore_lbt)
+	ldptr.d		t1, a0, THREAD_SCR0	# restore scr
+	movgr2scr	$scr0, t1
+	ldptr.d		t1, a0, THREAD_SCR1
+	movgr2scr	$scr1, t1
+	ldptr.d		t1, a0, THREAD_SCR2
+	movgr2scr	$scr2, t1
+	ldptr.d		t1, a0, THREAD_SCR3
+	movgr2scr	$scr3, t1
+
+	ldptr.d		t1, a0, THREAD_EFLAGS	# restore eflags
+	x86mtflag	t1, 0x3f
+	jr		ra
+SYM_FUNC_END(_restore_lbt)
+EXPORT_SYMBOL(_restore_lbt)
+
+/*
+ * Load scr/eflag with zero.
+ */
+SYM_FUNC_START(_init_lbt)
+	movgr2scr	$scr0, zero
+	movgr2scr	$scr1, zero
+	movgr2scr	$scr2, zero
+	movgr2scr	$scr3, zero
+
+	x86mtflag	zero, 0x3f
+	jr		ra
+SYM_FUNC_END(_init_lbt)
+
+/*
+ * a0: scr
+ * a1: eflag
+ */
+SYM_FUNC_START(_save_lbt_context)
+	movscr2gr	t1, $scr0		# save scr
+	EX	st.d	t1, a0, (0 * SCR_REG_WIDTH)
+	movscr2gr	t1, $scr1
+	EX	st.d	t1, a0, (1 * SCR_REG_WIDTH)
+	movscr2gr	t1, $scr2
+	EX	st.d	t1, a0, (2 * SCR_REG_WIDTH)
+	movscr2gr	t1, $scr3
+	EX	st.d	t1, a0, (3 * SCR_REG_WIDTH)
+
+	x86mfflag	t1, 0x3f		# save eflags
+	EX 	st.w	t1, a1, 0
+	li.w		a0, 0			# success
+	jr		ra
+SYM_FUNC_END(_save_lbt_context)
+
+/*
+ * a0: scr
+ * a1: eflag
+ */
+SYM_FUNC_START(_restore_lbt_context)
+	EX	ld.d	t1, a0, (0 * SCR_REG_WIDTH)	# restore scr
+	movgr2scr	$scr0, t1
+	EX	ld.d	t1, a0, (1 * SCR_REG_WIDTH)
+	movgr2scr	$scr1, t1
+	EX	ld.d	t1, a0, (2 * SCR_REG_WIDTH)
+	movgr2scr	$scr2, t1
+	EX	ld.d	t1, a0, (3 * SCR_REG_WIDTH)
+	movgr2scr	$scr3, t1
+
+	EX 	ld.w	t1, a1, 0			# restore eflags
+	x86mtflag	t1, 0x3f
+	li.w		a0, 0			# success
+	jr		ra
+SYM_FUNC_END(_restore_lbt_context)
+
+/*
+ * a0: ftop
+ */
+SYM_FUNC_START(_save_ftop_context)
+	x86mftop	t1
+	st.w		t1, a0, 0
+	li.w		a0, 0			# success
+	jr		ra
+SYM_FUNC_END(_save_ftop_context)
+
+/*
+ * a0: ftop
+ */
+SYM_FUNC_START(_restore_ftop_context)
+	ld.w		t1, a0, 0
+	andi		t1, t1, 0x7
+	la.pcrel	a0, 1f
+	alsl.d		a0, t1, a0, 3
+	jr		a0
+1:
+	x86mttop	0
+	b	2f
+	x86mttop	1
+	b	2f
+	x86mttop	2
+	b	2f
+	x86mttop	3
+	b	2f
+	x86mttop	4
+	b	2f
+	x86mttop	5
+	b	2f
+	x86mttop	6
+	b	2f
+	x86mttop	7
+2:
+	li.w		a0, 0			# success
+	jr		ra
+SYM_FUNC_END(_restore_ftop_context)
+
+.L_lbt_fault:
+	li.w		a0, -EFAULT		# failure
+	jr		ra
diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c
index 4ee1e9d6a65f..91ccedd9db6a 100644
--- a/arch/loongarch/kernel/process.c
+++ b/arch/loongarch/kernel/process.c
@@ -38,6 +38,7 @@
 #include <asm/cpu.h>
 #include <asm/elf.h>
 #include <asm/fpu.h>
+#include <asm/lbt.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/irq_regs.h>
@@ -82,9 +83,11 @@ void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp)
 	euen = regs->csr_euen & ~(CSR_EUEN_FPEN);
 	regs->csr_euen = euen;
 	lose_fpu(0);
+	lose_lbt(0);
 
 	clear_thread_flag(TIF_LSX_CTX_LIVE);
 	clear_thread_flag(TIF_LASX_CTX_LIVE);
+	clear_thread_flag(TIF_LBT_CTX_LIVE);
 	clear_used_math();
 	regs->csr_era = pc;
 	regs->regs[3] = sp;
@@ -121,10 +124,14 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 
 	preempt_enable();
 
-	if (used_math())
-		memcpy(dst, src, sizeof(struct task_struct));
-	else
+	if (!used_math())
 		memcpy(dst, src, offsetof(struct task_struct, thread.fpu.fpr));
+	else
+		memcpy(dst, src, offsetof(struct task_struct, thread.lbt.scr0));
+
+#ifdef CONFIG_CPU_HAS_LBT
+	memcpy(&dst->thread.lbt, &src->thread.lbt, sizeof(struct loongarch_lbt));
+#endif
 
 	return 0;
 }
@@ -189,8 +196,10 @@ out:
 	ptrace_hw_copy_thread(p);
 	clear_tsk_thread_flag(p, TIF_USEDFPU);
 	clear_tsk_thread_flag(p, TIF_USEDSIMD);
+	clear_tsk_thread_flag(p, TIF_USEDLBT);
 	clear_tsk_thread_flag(p, TIF_LSX_CTX_LIVE);
 	clear_tsk_thread_flag(p, TIF_LASX_CTX_LIVE);
+	clear_tsk_thread_flag(p, TIF_LBT_CTX_LIVE);
 
 	return 0;
 }
diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c
index f72adbf530c6..c114c5ef1332 100644
--- a/arch/loongarch/kernel/ptrace.c
+++ b/arch/loongarch/kernel/ptrace.c
@@ -38,6 +38,7 @@
 #include <asm/cpu.h>
 #include <asm/cpu-info.h>
 #include <asm/fpu.h>
+#include <asm/lbt.h>
 #include <asm/loongarch.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
@@ -338,6 +339,46 @@ static int simd_set(struct task_struct *target,
 
 #endif /* CONFIG_CPU_HAS_LSX */
 
+#ifdef CONFIG_CPU_HAS_LBT
+static int lbt_get(struct task_struct *target,
+		   const struct user_regset *regset,
+		   struct membuf to)
+{
+	int r;
+
+	r = membuf_write(&to, &target->thread.lbt.scr0, sizeof(target->thread.lbt.scr0));
+	r = membuf_write(&to, &target->thread.lbt.scr1, sizeof(target->thread.lbt.scr1));
+	r = membuf_write(&to, &target->thread.lbt.scr2, sizeof(target->thread.lbt.scr2));
+	r = membuf_write(&to, &target->thread.lbt.scr3, sizeof(target->thread.lbt.scr3));
+	r = membuf_write(&to, &target->thread.lbt.eflags, sizeof(u32));
+	r = membuf_write(&to, &target->thread.fpu.ftop, sizeof(u32));
+
+	return r;
+}
+
+static int lbt_set(struct task_struct *target,
+		   const struct user_regset *regset,
+		   unsigned int pos, unsigned int count,
+		   const void *kbuf, const void __user *ubuf)
+{
+	int err = 0;
+	const int eflags_start = 4 * sizeof(target->thread.lbt.scr0);
+	const int ftop_start = eflags_start + sizeof(u32);
+
+	err |= user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				  &target->thread.lbt.scr0,
+				  0, 4 * sizeof(target->thread.lbt.scr0));
+	err |= user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				  &target->thread.lbt.eflags,
+				  eflags_start, ftop_start);
+	err |= user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				  &target->thread.fpu.ftop,
+				  ftop_start, ftop_start + sizeof(u32));
+
+	return err;
+}
+#endif /* CONFIG_CPU_HAS_LBT */
+
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 
 /*
@@ -802,6 +843,9 @@ enum loongarch_regset {
 #ifdef CONFIG_CPU_HAS_LASX
 	REGSET_LASX,
 #endif
+#ifdef CONFIG_CPU_HAS_LBT
+	REGSET_LBT,
+#endif
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 	REGSET_HW_BREAK,
 	REGSET_HW_WATCH,
@@ -853,6 +897,16 @@ static const struct user_regset loongarch64_regsets[] = {
 		.set		= simd_set,
 	},
 #endif
+#ifdef CONFIG_CPU_HAS_LBT
+	[REGSET_LBT] = {
+		.core_note_type	= NT_LOONGARCH_LBT,
+		.n		= 5,
+		.size		= sizeof(u64),
+		.align		= sizeof(u64),
+		.regset_get	= lbt_get,
+		.set		= lbt_set,
+	},
+#endif
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 	[REGSET_HW_BREAK] = {
 		.core_note_type = NT_LOONGARCH_HW_BREAK,
diff --git a/arch/loongarch/kernel/signal.c b/arch/loongarch/kernel/signal.c
index ceb899366c0a..504fdfe85203 100644
--- a/arch/loongarch/kernel/signal.c
+++ b/arch/loongarch/kernel/signal.c
@@ -32,6 +32,7 @@
 #include <asm/cacheflush.h>
 #include <asm/cpu-features.h>
 #include <asm/fpu.h>
+#include <asm/lbt.h>
 #include <asm/ucontext.h>
 #include <asm/vdso.h>
 
@@ -44,6 +45,9 @@
 /* Make sure we will not lose FPU ownership */
 #define lock_fpu_owner()	({ preempt_disable(); pagefault_disable(); })
 #define unlock_fpu_owner()	({ pagefault_enable(); preempt_enable(); })
+/* Make sure we will not lose LBT ownership */
+#define lock_lbt_owner()	({ preempt_disable(); pagefault_disable(); })
+#define unlock_lbt_owner()	({ pagefault_enable(); preempt_enable(); })
 
 /* Assembly functions to move context to/from the FPU */
 extern asmlinkage int
@@ -59,6 +63,13 @@ _save_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
 extern asmlinkage int
 _restore_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
 
+#ifdef CONFIG_CPU_HAS_LBT
+extern asmlinkage int _save_lbt_context(void __user *regs, void __user *eflags);
+extern asmlinkage int _restore_lbt_context(void __user *regs, void __user *eflags);
+extern asmlinkage int _save_ftop_context(void __user *ftop);
+extern asmlinkage int _restore_ftop_context(void __user *ftop);
+#endif
+
 struct rt_sigframe {
 	struct siginfo rs_info;
 	struct ucontext rs_uctx;
@@ -75,6 +86,7 @@ struct extctx_layout {
 	struct _ctx_layout fpu;
 	struct _ctx_layout lsx;
 	struct _ctx_layout lasx;
+	struct _ctx_layout lbt;
 	struct _ctx_layout end;
 };
 
@@ -215,6 +227,52 @@ static int copy_lasx_from_sigcontext(struct lasx_context __user *ctx)
 	return err;
 }
 
+#ifdef CONFIG_CPU_HAS_LBT
+static int copy_lbt_to_sigcontext(struct lbt_context __user *ctx)
+{
+	int err = 0;
+	uint64_t __user *regs	= (uint64_t *)&ctx->regs;
+	uint32_t __user *eflags	= (uint32_t *)&ctx->eflags;
+
+	err |= __put_user(current->thread.lbt.scr0, &regs[0]);
+	err |= __put_user(current->thread.lbt.scr1, &regs[1]);
+	err |= __put_user(current->thread.lbt.scr2, &regs[2]);
+	err |= __put_user(current->thread.lbt.scr3, &regs[3]);
+	err |= __put_user(current->thread.lbt.eflags, eflags);
+
+	return err;
+}
+
+static int copy_lbt_from_sigcontext(struct lbt_context __user *ctx)
+{
+	int err = 0;
+	uint64_t __user *regs	= (uint64_t *)&ctx->regs;
+	uint32_t __user *eflags	= (uint32_t *)&ctx->eflags;
+
+	err |= __get_user(current->thread.lbt.scr0, &regs[0]);
+	err |= __get_user(current->thread.lbt.scr1, &regs[1]);
+	err |= __get_user(current->thread.lbt.scr2, &regs[2]);
+	err |= __get_user(current->thread.lbt.scr3, &regs[3]);
+	err |= __get_user(current->thread.lbt.eflags, eflags);
+
+	return err;
+}
+
+static int copy_ftop_to_sigcontext(struct lbt_context __user *ctx)
+{
+	uint32_t  __user *ftop	= &ctx->ftop;
+
+	return __put_user(current->thread.fpu.ftop, ftop);
+}
+
+static int copy_ftop_from_sigcontext(struct lbt_context __user *ctx)
+{
+	uint32_t  __user *ftop	= &ctx->ftop;
+
+	return __get_user(current->thread.fpu.ftop, ftop);
+}
+#endif
+
 /*
  * Wrappers for the assembly _{save,restore}_fp_context functions.
  */
@@ -272,6 +330,41 @@ static int restore_hw_lasx_context(struct lasx_context __user *ctx)
 	return _restore_lasx_context(regs, fcc, fcsr);
 }
 
+/*
+ * Wrappers for the assembly _{save,restore}_lbt_context functions.
+ */
+#ifdef CONFIG_CPU_HAS_LBT
+static int save_hw_lbt_context(struct lbt_context __user *ctx)
+{
+	uint64_t __user *regs	= (uint64_t *)&ctx->regs;
+	uint32_t __user *eflags	= (uint32_t *)&ctx->eflags;
+
+	return _save_lbt_context(regs, eflags);
+}
+
+static int restore_hw_lbt_context(struct lbt_context __user *ctx)
+{
+	uint64_t __user *regs	= (uint64_t *)&ctx->regs;
+	uint32_t __user *eflags	= (uint32_t *)&ctx->eflags;
+
+	return _restore_lbt_context(regs, eflags);
+}
+
+static int save_hw_ftop_context(struct lbt_context __user *ctx)
+{
+	uint32_t __user *ftop	= &ctx->ftop;
+
+	return _save_ftop_context(ftop);
+}
+
+static int restore_hw_ftop_context(struct lbt_context __user *ctx)
+{
+	uint32_t __user *ftop	= &ctx->ftop;
+
+	return _restore_ftop_context(ftop);
+}
+#endif
+
 static int fcsr_pending(unsigned int __user *fcsr)
 {
 	int err, sig = 0;
@@ -519,6 +612,77 @@ static int protected_restore_lasx_context(struct extctx_layout *extctx)
 	return err ?: sig;
 }
 
+#ifdef CONFIG_CPU_HAS_LBT
+static int protected_save_lbt_context(struct extctx_layout *extctx)
+{
+	int err = 0;
+	struct sctx_info __user *info = extctx->lbt.addr;
+	struct lbt_context __user *lbt_ctx =
+		(struct lbt_context *)get_ctx_through_ctxinfo(info);
+	uint64_t __user *regs	= (uint64_t *)&lbt_ctx->regs;
+	uint32_t __user *eflags	= (uint32_t *)&lbt_ctx->eflags;
+
+	while (1) {
+		lock_lbt_owner();
+		if (is_lbt_owner())
+			err |= save_hw_lbt_context(lbt_ctx);
+		else
+			err |= copy_lbt_to_sigcontext(lbt_ctx);
+		if (is_fpu_owner())
+			err |= save_hw_ftop_context(lbt_ctx);
+		else
+			err |= copy_ftop_to_sigcontext(lbt_ctx);
+		unlock_lbt_owner();
+
+		err |= __put_user(LBT_CTX_MAGIC, &info->magic);
+		err |= __put_user(extctx->lbt.size, &info->size);
+
+		if (likely(!err))
+			break;
+		/* Touch the LBT context and try again */
+		err = __put_user(0, &regs[0]) | __put_user(0, eflags);
+
+		if (err)
+			return err;
+	}
+
+	return err;
+}
+
+static int protected_restore_lbt_context(struct extctx_layout *extctx)
+{
+	int err = 0, tmp __maybe_unused;
+	struct sctx_info __user *info = extctx->lbt.addr;
+	struct lbt_context __user *lbt_ctx =
+		(struct lbt_context *)get_ctx_through_ctxinfo(info);
+	uint64_t __user *regs	= (uint64_t *)&lbt_ctx->regs;
+	uint32_t __user *eflags	= (uint32_t *)&lbt_ctx->eflags;
+
+	while (1) {
+		lock_lbt_owner();
+		if (is_lbt_owner())
+			err |= restore_hw_lbt_context(lbt_ctx);
+		else
+			err |= copy_lbt_from_sigcontext(lbt_ctx);
+		if (is_fpu_owner())
+			err |= restore_hw_ftop_context(lbt_ctx);
+		else
+			err |= copy_ftop_from_sigcontext(lbt_ctx);
+		unlock_lbt_owner();
+
+		if (likely(!err))
+			break;
+		/* Touch the LBT context and try again */
+		err = __get_user(tmp, &regs[0]) | __get_user(tmp, eflags);
+
+		if (err)
+			return err;
+	}
+
+	return err;
+}
+#endif
+
 static int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
 			    struct extctx_layout *extctx)
 {
@@ -539,6 +703,11 @@ static int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
 	else if (extctx->fpu.addr)
 		err |= protected_save_fpu_context(extctx);
 
+#ifdef CONFIG_CPU_HAS_LBT
+	if (extctx->lbt.addr)
+		err |= protected_save_lbt_context(extctx);
+#endif
+
 	/* Set the "end" magic */
 	info = (struct sctx_info *)extctx->end.addr;
 	err |= __put_user(0, &info->magic);
@@ -584,6 +753,13 @@ static int parse_extcontext(struct sigcontext __user *sc, struct extctx_layout *
 			extctx->lasx.addr = info;
 			break;
 
+		case LBT_CTX_MAGIC:
+			if (size < (sizeof(struct sctx_info) +
+				    sizeof(struct lbt_context)))
+				goto invalid;
+			extctx->lbt.addr = info;
+			break;
+
 		default:
 			goto invalid;
 		}
@@ -636,6 +812,11 @@ static int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc
 	else if (extctx.fpu.addr)
 		err |= protected_restore_fpu_context(&extctx);
 
+#ifdef CONFIG_CPU_HAS_LBT
+	if (extctx.lbt.addr)
+		err |= protected_restore_lbt_context(&extctx);
+#endif
+
 bad:
 	return err;
 }
@@ -700,6 +881,13 @@ static unsigned long setup_extcontext(struct extctx_layout *extctx, unsigned lon
 			  sizeof(struct fpu_context), FPU_CTX_ALIGN, new_sp);
 	}
 
+#ifdef CONFIG_CPU_HAS_LBT
+	if (cpu_has_lbt && thread_lbt_context_live()) {
+		new_sp = extframe_alloc(extctx, &extctx->lbt,
+			  sizeof(struct lbt_context), LBT_CTX_ALIGN, new_sp);
+	}
+#endif
+
 	return new_sp;
 }
 
diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c
index 89699db45cec..7ed01a7b2542 100644
--- a/arch/loongarch/kernel/traps.c
+++ b/arch/loongarch/kernel/traps.c
@@ -36,6 +36,7 @@
 #include <asm/break.h>
 #include <asm/cpu.h>
 #include <asm/fpu.h>
+#include <asm/lbt.h>
 #include <asm/inst.h>
 #include <asm/loongarch.h>
 #include <asm/mmu_context.h>
@@ -966,13 +967,47 @@ out:
 	irqentry_exit(regs, state);
 }
 
+static void init_restore_lbt(void)
+{
+	if (!thread_lbt_context_live()) {
+		/* First time LBT context user */
+		init_lbt();
+		set_thread_flag(TIF_LBT_CTX_LIVE);
+	} else {
+		if (!is_lbt_owner())
+			own_lbt_inatomic(1);
+	}
+
+	BUG_ON(!is_lbt_enabled());
+}
+
 asmlinkage void noinstr do_lbt(struct pt_regs *regs)
 {
 	irqentry_state_t state = irqentry_enter(regs);
 
-	local_irq_enable();
-	force_sig(SIGILL);
-	local_irq_disable();
+	/*
+	 * BTD (Binary Translation Disable exception) can be triggered
+	 * during FP save/restore if TM (Top Mode) is on, which may
+	 * cause irq_enable during 'switch_to'. To avoid this situation
+	 * (including the user using 'MOVGR2GCSR' to turn on TM, which
+	 * will not trigger the BTE), we need to check PRMD first.
+	 */
+	if (regs->csr_prmd & CSR_PRMD_PIE)
+		local_irq_enable();
+
+	if (!cpu_has_lbt) {
+		force_sig(SIGILL);
+		goto out;
+	}
+	BUG_ON(is_lbt_enabled());
+
+	preempt_disable();
+	init_restore_lbt();
+	preempt_enable();
+
+out:
+	if (regs->csr_prmd & CSR_PRMD_PIE)
+		local_irq_disable();
 
 	irqentry_exit(regs, state);
 }

From e14dd076964ef11e9d6e3b06a2f1c6bb7d034133 Mon Sep 17 00:00:00 2001
From: Qing Zhang <zhangqing@loongson.cn>
Date: Wed, 6 Sep 2023 22:53:55 +0800
Subject: [PATCH 1123/1189] LoongArch: Add basic KGDB & KDB support

KGDB is intended to be used as a source level debugger for the Linux
kernel. It is used along with gdb to debug a Linux kernel. GDB can be
used to "break in" to the kernel to inspect memory, variables and regs
similar to the way an application developer would use GDB to debug an
application. KDB is a frontend of KGDB which is similar to GDB.

By now, in addition to the generic KGDB features, the LoongArch KGDB
implements the following features:
- Hardware breakpoints/watchpoints;
- Software single-step support for KDB.

Signed-off-by: Qing Zhang <zhangqing@loongson.cn>   # Framework & CoreFeature
Signed-off-by: Binbin Zhou <zhoubinbin@loongson.cn> # BreakPoint & SingleStep
Signed-off-by: Hui Li <lihui@loongson.cn>           # Some Minor Improvements
Signed-off-by: Randy Dunlap <rdunlap@infradead.org> # Some Build Error Fixes
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 .../features/debug/kgdb/arch-support.txt      |   2 +-
 arch/loongarch/Kconfig                        |   1 +
 arch/loongarch/include/asm/kgdb.h             |  97 +++
 arch/loongarch/include/asm/stackframe.h       |   4 +
 arch/loongarch/kernel/Makefile                |   1 +
 arch/loongarch/kernel/entry.S                 |   5 +
 arch/loongarch/kernel/kgdb.c                  | 727 ++++++++++++++++++
 arch/loongarch/kernel/traps.c                 |   9 +
 8 files changed, 845 insertions(+), 1 deletion(-)
 create mode 100644 arch/loongarch/include/asm/kgdb.h
 create mode 100644 arch/loongarch/kernel/kgdb.c

diff --git a/Documentation/features/debug/kgdb/arch-support.txt b/Documentation/features/debug/kgdb/arch-support.txt
index 958498f9f2a4..5e91ec78c80b 100644
--- a/Documentation/features/debug/kgdb/arch-support.txt
+++ b/Documentation/features/debug/kgdb/arch-support.txt
@@ -13,7 +13,7 @@
     |        csky: | TODO |
     |     hexagon: |  ok  |
     |        ia64: | TODO |
-    |   loongarch: | TODO |
+    |   loongarch: |  ok  |
     |        m68k: | TODO |
     |  microblaze: |  ok  |
     |        mips: |  ok  |
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 21cc2e2d1f27..b02e399b1cd7 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -91,6 +91,7 @@ config LOONGARCH
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_JUMP_LABEL_RELATIVE
+	select HAVE_ARCH_KGDB if PERF_EVENTS
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
diff --git a/arch/loongarch/include/asm/kgdb.h b/arch/loongarch/include/asm/kgdb.h
new file mode 100644
index 000000000000..2041ae58b161
--- /dev/null
+++ b/arch/loongarch/include/asm/kgdb.h
@@ -0,0 +1,97 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023 Loongson Technology Corporation Limited
+ */
+
+#ifndef _ASM_LOONGARCH_KGDB_H
+#define _ASM_LOONGARCH_KGDB_H
+
+#define GDB_SIZEOF_REG		sizeof(u64)
+
+/* gdb remote procotol expects the following register layout. */
+
+/*
+ * General purpose registers:
+ *     r0-r31: 64 bit
+ *     orig_a0: 64 bit
+ *     pc : 64 bit
+ *     csr_badvaddr: 64 bit
+ */
+#define DBG_PT_REGS_BASE	0
+#define DBG_PT_REGS_NUM		35
+#define DBG_PT_REGS_END		(DBG_PT_REGS_BASE + DBG_PT_REGS_NUM - 1)
+
+/*
+ * Floating point registers:
+ *     f0-f31: 64 bit
+ */
+#define DBG_FPR_BASE		(DBG_PT_REGS_END + 1)
+#define DBG_FPR_NUM		32
+#define DBG_FPR_END		(DBG_FPR_BASE + DBG_FPR_NUM - 1)
+
+/*
+ * Condition Flag registers:
+ *     fcc0-fcc8: 8 bit
+ */
+#define DBG_FCC_BASE		(DBG_FPR_END + 1)
+#define DBG_FCC_NUM		8
+#define DBG_FCC_END		(DBG_FCC_BASE + DBG_FCC_NUM - 1)
+
+/*
+ * Floating-point Control and Status registers:
+ *     fcsr: 32 bit
+ */
+#define DBG_FCSR_NUM		1
+#define DBG_FCSR		(DBG_FCC_END + 1)
+
+#define DBG_MAX_REG_NUM		(DBG_FCSR + 1)
+
+/*
+ * Size of I/O buffer for gdb packet.
+ * considering to hold all register contents, size is set
+ */
+#define BUFMAX			2048
+
+/*
+ * Number of bytes required for gdb_regs buffer.
+ * PT_REGS and FPR: 8 bytes; FCSR: 4 bytes; FCC: 1 bytes.
+ * GDB fails to connect for size beyond this with error
+ * "'g' packet reply is too long"
+ */
+#define NUMREGBYTES		((DBG_PT_REGS_NUM + DBG_FPR_NUM) * GDB_SIZEOF_REG + DBG_FCC_NUM * 1 + DBG_FCSR_NUM * 4)
+
+#define BREAK_INSTR_SIZE	4
+#define CACHE_FLUSH_IS_SAFE	0
+
+/* Register numbers of various important registers. */
+enum dbg_loongarch_regnum {
+	DBG_LOONGARCH_ZERO = 0,
+	DBG_LOONGARCH_RA,
+	DBG_LOONGARCH_TP,
+	DBG_LOONGARCH_SP,
+	DBG_LOONGARCH_A0,
+	DBG_LOONGARCH_FP = 22,
+	DBG_LOONGARCH_S0,
+	DBG_LOONGARCH_S1,
+	DBG_LOONGARCH_S2,
+	DBG_LOONGARCH_S3,
+	DBG_LOONGARCH_S4,
+	DBG_LOONGARCH_S5,
+	DBG_LOONGARCH_S6,
+	DBG_LOONGARCH_S7,
+	DBG_LOONGARCH_S8,
+	DBG_LOONGARCH_ORIG_A0,
+	DBG_LOONGARCH_PC,
+	DBG_LOONGARCH_BADV
+};
+
+void kgdb_breakinst(void);
+void arch_kgdb_breakpoint(void);
+
+#ifdef CONFIG_KGDB
+bool kgdb_breakpoint_handler(struct pt_regs *regs);
+#else /* !CONFIG_KGDB */
+static inline bool kgdb_breakpoint_handler(struct pt_regs *regs) { return false; }
+#endif /* CONFIG_KGDB */
+
+#endif /* __ASM_KGDB_H_ */
diff --git a/arch/loongarch/include/asm/stackframe.h b/arch/loongarch/include/asm/stackframe.h
index 7df80e6ae9d2..4fb1e6408b98 100644
--- a/arch/loongarch/include/asm/stackframe.h
+++ b/arch/loongarch/include/asm/stackframe.h
@@ -158,6 +158,10 @@
 	cfi_st  u0, PT_R21, \docfi
 	csrrd	u0, PERCPU_BASE_KS
 9:
+#ifdef CONFIG_KGDB
+	li.w	t0, CSR_CRMD_WE
+	csrxchg	t0, t0, LOONGARCH_CSR_CRMD
+#endif
 	.endm
 
 	.macro	SAVE_ALL docfi=0
diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile
index 5341dcf15a17..c0b88528cb81 100644
--- a/arch/loongarch/kernel/Makefile
+++ b/arch/loongarch/kernel/Makefile
@@ -56,6 +56,7 @@ obj-$(CONFIG_UNWINDER_PROLOGUE) += unwind_prologue.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o perf_regs.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 
+obj-$(CONFIG_KGDB)		+= kgdb.o
 obj-$(CONFIG_KPROBES)		+= kprobes.o
 obj-$(CONFIG_RETHOOK)		+= rethook.o rethook_trampoline.o
 obj-$(CONFIG_UPROBES)		+= uprobes.o
diff --git a/arch/loongarch/kernel/entry.S b/arch/loongarch/kernel/entry.S
index d737e3cf42d3..65518bb8f472 100644
--- a/arch/loongarch/kernel/entry.S
+++ b/arch/loongarch/kernel/entry.S
@@ -58,6 +58,11 @@ SYM_FUNC_START(handle_syscall)
 
 	SAVE_STATIC
 
+#ifdef CONFIG_KGDB
+	li.w		t1, CSR_CRMD_WE
+	csrxchg		t1, t1, LOONGARCH_CSR_CRMD
+#endif
+
 	move		u0, t0
 	li.d		tp, ~_THREAD_MASK
 	and		tp, tp, sp
diff --git a/arch/loongarch/kernel/kgdb.c b/arch/loongarch/kernel/kgdb.c
new file mode 100644
index 000000000000..445c452d72a7
--- /dev/null
+++ b/arch/loongarch/kernel/kgdb.c
@@ -0,0 +1,727 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * LoongArch KGDB support
+ *
+ * Copyright (C) 2023 Loongson Technology Corporation Limited
+ */
+
+#include <linux/hw_breakpoint.h>
+#include <linux/kdebug.h>
+#include <linux/kgdb.h>
+#include <linux/processor.h>
+#include <linux/ptrace.h>
+#include <linux/sched.h>
+#include <linux/smp.h>
+
+#include <asm/cacheflush.h>
+#include <asm/fpu.h>
+#include <asm/hw_breakpoint.h>
+#include <asm/inst.h>
+#include <asm/irq_regs.h>
+#include <asm/ptrace.h>
+#include <asm/sigcontext.h>
+
+int kgdb_watch_activated;
+static unsigned int stepped_opcode;
+static unsigned long stepped_address;
+
+struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = {
+	{ "r0", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[0]) },
+	{ "r1", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[1]) },
+	{ "r2", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[2]) },
+	{ "r3", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[3]) },
+	{ "r4", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[4]) },
+	{ "r5", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[5]) },
+	{ "r6", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[6]) },
+	{ "r7", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[7]) },
+	{ "r8", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[8]) },
+	{ "r9", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[9]) },
+	{ "r10", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[10]) },
+	{ "r11", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[11]) },
+	{ "r12", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[12]) },
+	{ "r13", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[13]) },
+	{ "r14", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[14]) },
+	{ "r15", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[15]) },
+	{ "r16", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[16]) },
+	{ "r17", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[17]) },
+	{ "r18", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[18]) },
+	{ "r19", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[19]) },
+	{ "r20", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[20]) },
+	{ "r21", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[21]) },
+	{ "r22", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[22]) },
+	{ "r23", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[23]) },
+	{ "r24", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[24]) },
+	{ "r25", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[25]) },
+	{ "r26", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[26]) },
+	{ "r27", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[27]) },
+	{ "r28", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[28]) },
+	{ "r29", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[29]) },
+	{ "r30", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[30]) },
+	{ "r31", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[31]) },
+	{ "orig_a0", GDB_SIZEOF_REG, offsetof(struct pt_regs, orig_a0) },
+	{ "pc", GDB_SIZEOF_REG, offsetof(struct pt_regs, csr_era) },
+	{ "badv", GDB_SIZEOF_REG, offsetof(struct pt_regs, csr_badvaddr) },
+	{ "f0", GDB_SIZEOF_REG, 0 },
+	{ "f1", GDB_SIZEOF_REG, 1 },
+	{ "f2", GDB_SIZEOF_REG, 2 },
+	{ "f3", GDB_SIZEOF_REG, 3 },
+	{ "f4", GDB_SIZEOF_REG, 4 },
+	{ "f5", GDB_SIZEOF_REG, 5 },
+	{ "f6", GDB_SIZEOF_REG, 6 },
+	{ "f7", GDB_SIZEOF_REG, 7 },
+	{ "f8", GDB_SIZEOF_REG, 8 },
+	{ "f9", GDB_SIZEOF_REG, 9 },
+	{ "f10", GDB_SIZEOF_REG, 10 },
+	{ "f11", GDB_SIZEOF_REG, 11 },
+	{ "f12", GDB_SIZEOF_REG, 12 },
+	{ "f13", GDB_SIZEOF_REG, 13 },
+	{ "f14", GDB_SIZEOF_REG, 14 },
+	{ "f15", GDB_SIZEOF_REG, 15 },
+	{ "f16", GDB_SIZEOF_REG, 16 },
+	{ "f17", GDB_SIZEOF_REG, 17 },
+	{ "f18", GDB_SIZEOF_REG, 18 },
+	{ "f19", GDB_SIZEOF_REG, 19 },
+	{ "f20", GDB_SIZEOF_REG, 20 },
+	{ "f21", GDB_SIZEOF_REG, 21 },
+	{ "f22", GDB_SIZEOF_REG, 22 },
+	{ "f23", GDB_SIZEOF_REG, 23 },
+	{ "f24", GDB_SIZEOF_REG, 24 },
+	{ "f25", GDB_SIZEOF_REG, 25 },
+	{ "f26", GDB_SIZEOF_REG, 26 },
+	{ "f27", GDB_SIZEOF_REG, 27 },
+	{ "f28", GDB_SIZEOF_REG, 28 },
+	{ "f29", GDB_SIZEOF_REG, 29 },
+	{ "f30", GDB_SIZEOF_REG, 30 },
+	{ "f31", GDB_SIZEOF_REG, 31 },
+	{ "fcc0", 1, 0 },
+	{ "fcc1", 1, 1 },
+	{ "fcc2", 1, 2 },
+	{ "fcc3", 1, 3 },
+	{ "fcc4", 1, 4 },
+	{ "fcc5", 1, 5 },
+	{ "fcc6", 1, 6 },
+	{ "fcc7", 1, 7 },
+	{ "fcsr", 4, 0 },
+};
+
+char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs)
+{
+	int reg_offset, reg_size;
+
+	if (regno < 0 || regno >= DBG_MAX_REG_NUM)
+		return NULL;
+
+	reg_offset = dbg_reg_def[regno].offset;
+	reg_size = dbg_reg_def[regno].size;
+
+	if (reg_offset == -1)
+		goto out;
+
+	/* Handle general-purpose/orig_a0/pc/badv registers */
+	if (regno <= DBG_PT_REGS_END) {
+		memcpy(mem, (void *)regs + reg_offset, reg_size);
+		goto out;
+	}
+
+	if (!(regs->csr_euen & CSR_EUEN_FPEN))
+		goto out;
+
+	save_fp(current);
+
+	/* Handle FP registers */
+	switch (regno) {
+	case DBG_FCSR:				/* Process the fcsr */
+		memcpy(mem, (void *)&current->thread.fpu.fcsr, reg_size);
+		break;
+	case DBG_FCC_BASE ... DBG_FCC_END:	/* Process the fcc */
+		memcpy(mem, (void *)&current->thread.fpu.fcc + reg_offset, reg_size);
+		break;
+	case DBG_FPR_BASE ... DBG_FPR_END:	/* Process the fpr */
+		memcpy(mem, (void *)&current->thread.fpu.fpr[reg_offset], reg_size);
+		break;
+	default:
+		break;
+	}
+
+out:
+	return dbg_reg_def[regno].name;
+}
+
+int dbg_set_reg(int regno, void *mem, struct pt_regs *regs)
+{
+	int reg_offset, reg_size;
+
+	if (regno < 0 || regno >= DBG_MAX_REG_NUM)
+		return -EINVAL;
+
+	reg_offset = dbg_reg_def[regno].offset;
+	reg_size = dbg_reg_def[regno].size;
+
+	if (reg_offset == -1)
+		return 0;
+
+	/* Handle general-purpose/orig_a0/pc/badv registers */
+	if (regno <= DBG_PT_REGS_END) {
+		memcpy((void *)regs + reg_offset, mem, reg_size);
+		return 0;
+	}
+
+	if (!(regs->csr_euen & CSR_EUEN_FPEN))
+		return 0;
+
+	/* Handle FP registers */
+	switch (regno) {
+	case DBG_FCSR:				/* Process the fcsr */
+		memcpy((void *)&current->thread.fpu.fcsr, mem, reg_size);
+		break;
+	case DBG_FCC_BASE ... DBG_FCC_END:	/* Process the fcc */
+		memcpy((void *)&current->thread.fpu.fcc + reg_offset, mem, reg_size);
+		break;
+	case DBG_FPR_BASE ... DBG_FPR_END:	/* Process the fpr */
+		memcpy((void *)&current->thread.fpu.fpr[reg_offset], mem, reg_size);
+		break;
+	default:
+		break;
+	}
+
+	restore_fp(current);
+
+	return 0;
+}
+
+/*
+ * Similar to regs_to_gdb_regs() except that process is sleeping and so
+ * we may not be able to get all the info.
+ */
+void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p)
+{
+	/* Initialize to zero */
+	memset((char *)gdb_regs, 0, NUMREGBYTES);
+
+	gdb_regs[DBG_LOONGARCH_RA] = p->thread.reg01;
+	gdb_regs[DBG_LOONGARCH_TP] = (long)p;
+	gdb_regs[DBG_LOONGARCH_SP] = p->thread.reg03;
+
+	/* S0 - S8 */
+	gdb_regs[DBG_LOONGARCH_S0] = p->thread.reg23;
+	gdb_regs[DBG_LOONGARCH_S1] = p->thread.reg24;
+	gdb_regs[DBG_LOONGARCH_S2] = p->thread.reg25;
+	gdb_regs[DBG_LOONGARCH_S3] = p->thread.reg26;
+	gdb_regs[DBG_LOONGARCH_S4] = p->thread.reg27;
+	gdb_regs[DBG_LOONGARCH_S5] = p->thread.reg28;
+	gdb_regs[DBG_LOONGARCH_S6] = p->thread.reg29;
+	gdb_regs[DBG_LOONGARCH_S7] = p->thread.reg30;
+	gdb_regs[DBG_LOONGARCH_S8] = p->thread.reg31;
+
+	/*
+	 * PC use return address (RA), i.e. the moment after return from __switch_to()
+	 */
+	gdb_regs[DBG_LOONGARCH_PC] = p->thread.reg01;
+}
+
+void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)
+{
+	regs->csr_era = pc;
+}
+
+void arch_kgdb_breakpoint(void)
+{
+	__asm__ __volatile__ (			\
+		".globl kgdb_breakinst\n\t"	\
+		"nop\n"				\
+		"kgdb_breakinst:\tbreak 2\n\t"); /* BRK_KDB = 2 */
+}
+
+/*
+ * Calls linux_debug_hook before the kernel dies. If KGDB is enabled,
+ * then try to fall into the debugger
+ */
+static int kgdb_loongarch_notify(struct notifier_block *self, unsigned long cmd, void *ptr)
+{
+	struct die_args *args = (struct die_args *)ptr;
+	struct pt_regs *regs = args->regs;
+
+	/* Userspace events, ignore. */
+	if (user_mode(regs))
+		return NOTIFY_DONE;
+
+	if (!kgdb_io_module_registered)
+		return NOTIFY_DONE;
+
+	if (atomic_read(&kgdb_active) != -1)
+		kgdb_nmicallback(smp_processor_id(), regs);
+
+	if (kgdb_handle_exception(args->trapnr, args->signr, cmd, regs))
+		return NOTIFY_DONE;
+
+	if (atomic_read(&kgdb_setting_breakpoint))
+		if (regs->csr_era == (unsigned long)&kgdb_breakinst)
+			regs->csr_era += LOONGARCH_INSN_SIZE;
+
+	return NOTIFY_STOP;
+}
+
+bool kgdb_breakpoint_handler(struct pt_regs *regs)
+{
+	struct die_args args = {
+		.regs	= regs,
+		.str	= "Break",
+		.err	= BRK_KDB,
+		.trapnr = read_csr_excode(),
+		.signr	= SIGTRAP,
+
+	};
+
+	return (kgdb_loongarch_notify(NULL, DIE_TRAP, &args) == NOTIFY_STOP) ? true : false;
+}
+
+static struct notifier_block kgdb_notifier = {
+	.notifier_call = kgdb_loongarch_notify,
+};
+
+static inline void kgdb_arch_update_addr(struct pt_regs *regs,
+					 char *remcom_in_buffer)
+{
+	unsigned long addr;
+	char *ptr;
+
+	ptr = &remcom_in_buffer[1];
+	if (kgdb_hex2long(&ptr, &addr))
+		regs->csr_era = addr;
+}
+
+/* Calculate the new address for after a step */
+static int get_step_address(struct pt_regs *regs, unsigned long *next_addr)
+{
+	char cj_val;
+	unsigned int si, si_l, si_h, rd, rj, cj;
+	unsigned long pc = instruction_pointer(regs);
+	union loongarch_instruction *ip = (union loongarch_instruction *)pc;
+
+	if (pc & 3) {
+		pr_warn("%s: invalid pc 0x%lx\n", __func__, pc);
+		return -EINVAL;
+	}
+
+	*next_addr = pc + LOONGARCH_INSN_SIZE;
+
+	si_h = ip->reg0i26_format.immediate_h;
+	si_l = ip->reg0i26_format.immediate_l;
+	switch (ip->reg0i26_format.opcode) {
+	case b_op:
+		*next_addr = pc + sign_extend64((si_h << 16 | si_l) << 2, 27);
+		return 0;
+	case bl_op:
+		*next_addr = pc + sign_extend64((si_h << 16 | si_l) << 2, 27);
+		regs->regs[1] = pc + LOONGARCH_INSN_SIZE;
+		return 0;
+	}
+
+	rj = ip->reg1i21_format.rj;
+	cj = (rj & 0x07) + DBG_FCC_BASE;
+	si_l = ip->reg1i21_format.immediate_l;
+	si_h = ip->reg1i21_format.immediate_h;
+	dbg_get_reg(cj, &cj_val, regs);
+	switch (ip->reg1i21_format.opcode) {
+	case beqz_op:
+		if (regs->regs[rj] == 0)
+			*next_addr = pc + sign_extend64((si_h << 16 | si_l) << 2, 22);
+		return 0;
+	case bnez_op:
+		if (regs->regs[rj] != 0)
+			*next_addr = pc + sign_extend64((si_h << 16 | si_l) << 2, 22);
+		return 0;
+	case bceqz_op: /* bceqz_op = bcnez_op */
+		if (((rj & 0x18) == 0x00) && !cj_val) /* bceqz */
+			*next_addr = pc + sign_extend64((si_h << 16 | si_l) << 2, 22);
+		if (((rj & 0x18) == 0x08) && cj_val) /* bcnez */
+			*next_addr = pc + sign_extend64((si_h << 16 | si_l) << 2, 22);
+		return 0;
+	}
+
+	rj = ip->reg2i16_format.rj;
+	rd = ip->reg2i16_format.rd;
+	si = ip->reg2i16_format.immediate;
+	switch (ip->reg2i16_format.opcode) {
+	case beq_op:
+		if (regs->regs[rj] == regs->regs[rd])
+			*next_addr = pc + sign_extend64(si << 2, 17);
+		return 0;
+	case bne_op:
+		if (regs->regs[rj] != regs->regs[rd])
+			*next_addr = pc + sign_extend64(si << 2, 17);
+		return 0;
+	case blt_op:
+		if ((long)regs->regs[rj] < (long)regs->regs[rd])
+			*next_addr = pc + sign_extend64(si << 2, 17);
+		return 0;
+	case bge_op:
+		if ((long)regs->regs[rj] >= (long)regs->regs[rd])
+			*next_addr = pc + sign_extend64(si << 2, 17);
+		return 0;
+	case bltu_op:
+		if (regs->regs[rj] < regs->regs[rd])
+			*next_addr = pc + sign_extend64(si << 2, 17);
+		return 0;
+	case bgeu_op:
+		if (regs->regs[rj] >= regs->regs[rd])
+			*next_addr = pc + sign_extend64(si << 2, 17);
+		return 0;
+	case jirl_op:
+		regs->regs[rd] = pc + LOONGARCH_INSN_SIZE;
+		*next_addr = regs->regs[rj] + sign_extend64(si << 2, 17);
+		return 0;
+	}
+
+	return 0;
+}
+
+static int do_single_step(struct pt_regs *regs)
+{
+	int error = 0;
+	unsigned long addr = 0; /* Determine where the target instruction will send us to */
+
+	error = get_step_address(regs, &addr);
+	if (error)
+		return error;
+
+	/* Store the opcode in the stepped address */
+	error = get_kernel_nofault(stepped_opcode, (void *)addr);
+	if (error)
+		return error;
+
+	stepped_address = addr;
+
+	/* Replace the opcode with the break instruction */
+	error = copy_to_kernel_nofault((void *)stepped_address,
+				       arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE);
+	flush_icache_range(addr, addr + BREAK_INSTR_SIZE);
+
+	if (error) {
+		stepped_opcode = 0;
+		stepped_address = 0;
+	} else {
+		kgdb_single_step = 1;
+		atomic_set(&kgdb_cpu_doing_single_step, raw_smp_processor_id());
+	}
+
+	return error;
+}
+
+/* Undo a single step */
+static void undo_single_step(struct pt_regs *regs)
+{
+	if (stepped_opcode) {
+		copy_to_kernel_nofault((void *)stepped_address,
+				       (void *)&stepped_opcode, BREAK_INSTR_SIZE);
+		flush_icache_range(stepped_address, stepped_address + BREAK_INSTR_SIZE);
+	}
+
+	stepped_opcode = 0;
+	stepped_address = 0;
+	kgdb_single_step = 0;
+	atomic_set(&kgdb_cpu_doing_single_step, -1);
+}
+
+int kgdb_arch_handle_exception(int vector, int signo, int err_code,
+			       char *remcom_in_buffer, char *remcom_out_buffer,
+			       struct pt_regs *regs)
+{
+	int ret = 0;
+
+	undo_single_step(regs);
+	regs->csr_prmd |= CSR_PRMD_PWE;
+
+	switch (remcom_in_buffer[0]) {
+	case 'D':
+	case 'k':
+		regs->csr_prmd &= ~CSR_PRMD_PWE;
+		fallthrough;
+	case 'c':
+		kgdb_arch_update_addr(regs, remcom_in_buffer);
+		break;
+	case 's':
+		kgdb_arch_update_addr(regs, remcom_in_buffer);
+		ret = do_single_step(regs);
+		break;
+	default:
+		ret = -1;
+	}
+
+	return ret;
+}
+
+static struct hw_breakpoint {
+	unsigned int		enabled;
+	unsigned long		addr;
+	int			len;
+	int			type;
+	struct perf_event	* __percpu *pev;
+} breakinfo[LOONGARCH_MAX_BRP];
+
+static int hw_break_reserve_slot(int breakno)
+{
+	int cpu, cnt = 0;
+	struct perf_event **pevent;
+
+	for_each_online_cpu(cpu) {
+		cnt++;
+		pevent = per_cpu_ptr(breakinfo[breakno].pev, cpu);
+		if (dbg_reserve_bp_slot(*pevent))
+			goto fail;
+	}
+
+	return 0;
+
+fail:
+	for_each_online_cpu(cpu) {
+		cnt--;
+		if (!cnt)
+			break;
+		pevent = per_cpu_ptr(breakinfo[breakno].pev, cpu);
+		dbg_release_bp_slot(*pevent);
+	}
+
+	return -1;
+}
+
+static int hw_break_release_slot(int breakno)
+{
+	int cpu;
+	struct perf_event **pevent;
+
+	if (dbg_is_early)
+		return 0;
+
+	for_each_online_cpu(cpu) {
+		pevent = per_cpu_ptr(breakinfo[breakno].pev, cpu);
+		if (dbg_release_bp_slot(*pevent))
+			/*
+			 * The debugger is responsible for handing the retry on
+			 * remove failure.
+			 */
+			return -1;
+	}
+
+	return 0;
+}
+
+static int kgdb_set_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype)
+{
+	int i;
+
+	for (i = 0; i < LOONGARCH_MAX_BRP; i++)
+		if (!breakinfo[i].enabled)
+			break;
+
+	if (i == LOONGARCH_MAX_BRP)
+		return -1;
+
+	switch (bptype) {
+	case BP_HARDWARE_BREAKPOINT:
+		breakinfo[i].type = HW_BREAKPOINT_X;
+		break;
+	case BP_READ_WATCHPOINT:
+		breakinfo[i].type = HW_BREAKPOINT_R;
+		break;
+	case BP_WRITE_WATCHPOINT:
+		breakinfo[i].type = HW_BREAKPOINT_W;
+		break;
+	case BP_ACCESS_WATCHPOINT:
+		breakinfo[i].type = HW_BREAKPOINT_RW;
+		break;
+	default:
+		return -1;
+	}
+
+	switch (len) {
+	case 1:
+		breakinfo[i].len = HW_BREAKPOINT_LEN_1;
+		break;
+	case 2:
+		breakinfo[i].len = HW_BREAKPOINT_LEN_2;
+		break;
+	case 4:
+		breakinfo[i].len = HW_BREAKPOINT_LEN_4;
+		break;
+	case 8:
+		breakinfo[i].len = HW_BREAKPOINT_LEN_8;
+		break;
+	default:
+		return -1;
+	}
+
+	breakinfo[i].addr = addr;
+	if (hw_break_reserve_slot(i)) {
+		breakinfo[i].addr = 0;
+		return -1;
+	}
+	breakinfo[i].enabled = 1;
+
+	return 0;
+}
+
+static int kgdb_remove_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype)
+{
+	int i;
+
+	for (i = 0; i < LOONGARCH_MAX_BRP; i++)
+		if (breakinfo[i].addr == addr && breakinfo[i].enabled)
+			break;
+
+	if (i == LOONGARCH_MAX_BRP)
+		return -1;
+
+	if (hw_break_release_slot(i)) {
+		pr_err("Cannot remove hw breakpoint at %lx\n", addr);
+		return -1;
+	}
+	breakinfo[i].enabled = 0;
+
+	return 0;
+}
+
+static void kgdb_disable_hw_break(struct pt_regs *regs)
+{
+	int i;
+	int cpu = raw_smp_processor_id();
+	struct perf_event *bp;
+
+	for (i = 0; i < LOONGARCH_MAX_BRP; i++) {
+		if (!breakinfo[i].enabled)
+			continue;
+
+		bp = *per_cpu_ptr(breakinfo[i].pev, cpu);
+		if (bp->attr.disabled == 1)
+			continue;
+
+		arch_uninstall_hw_breakpoint(bp);
+		bp->attr.disabled = 1;
+	}
+
+	/* Disable hardware debugging while we are in kgdb */
+	csr_xchg32(0, CSR_CRMD_WE, LOONGARCH_CSR_CRMD);
+}
+
+static void kgdb_remove_all_hw_break(void)
+{
+	int i;
+	int cpu = raw_smp_processor_id();
+	struct perf_event *bp;
+
+	for (i = 0; i < LOONGARCH_MAX_BRP; i++) {
+		if (!breakinfo[i].enabled)
+			continue;
+
+		bp = *per_cpu_ptr(breakinfo[i].pev, cpu);
+		if (!bp->attr.disabled) {
+			arch_uninstall_hw_breakpoint(bp);
+			bp->attr.disabled = 1;
+			continue;
+		}
+
+		if (hw_break_release_slot(i))
+			pr_err("KGDB: hw bpt remove failed %lx\n", breakinfo[i].addr);
+		breakinfo[i].enabled = 0;
+	}
+
+	csr_xchg32(0, CSR_CRMD_WE, LOONGARCH_CSR_CRMD);
+	kgdb_watch_activated = 0;
+}
+
+static void kgdb_correct_hw_break(void)
+{
+	int i, activated = 0;
+
+	for (i = 0; i < LOONGARCH_MAX_BRP; i++) {
+		struct perf_event *bp;
+		int val;
+		int cpu = raw_smp_processor_id();
+
+		if (!breakinfo[i].enabled)
+			continue;
+
+		bp = *per_cpu_ptr(breakinfo[i].pev, cpu);
+		if (bp->attr.disabled != 1)
+			continue;
+
+		bp->attr.bp_addr = breakinfo[i].addr;
+		bp->attr.bp_len = breakinfo[i].len;
+		bp->attr.bp_type = breakinfo[i].type;
+
+		val = hw_breakpoint_arch_parse(bp, &bp->attr, counter_arch_bp(bp));
+		if (val)
+			return;
+
+		val = arch_install_hw_breakpoint(bp);
+		if (!val)
+			bp->attr.disabled = 0;
+		activated = 1;
+	}
+
+	csr_xchg32(activated ? CSR_CRMD_WE : 0, CSR_CRMD_WE, LOONGARCH_CSR_CRMD);
+	kgdb_watch_activated = activated;
+}
+
+const struct kgdb_arch arch_kgdb_ops = {
+	.gdb_bpt_instr		= {0x02, 0x00, break_op >> 1, 0x00}, /* BRK_KDB = 2 */
+	.flags			= KGDB_HW_BREAKPOINT,
+	.set_hw_breakpoint	= kgdb_set_hw_break,
+	.remove_hw_breakpoint	= kgdb_remove_hw_break,
+	.disable_hw_break	= kgdb_disable_hw_break,
+	.remove_all_hw_break	= kgdb_remove_all_hw_break,
+	.correct_hw_break	= kgdb_correct_hw_break,
+};
+
+int kgdb_arch_init(void)
+{
+	return register_die_notifier(&kgdb_notifier);
+}
+
+void kgdb_arch_late(void)
+{
+	int i, cpu;
+	struct perf_event_attr attr;
+	struct perf_event **pevent;
+
+	hw_breakpoint_init(&attr);
+
+	attr.bp_addr = (unsigned long)kgdb_arch_init;
+	attr.bp_len = HW_BREAKPOINT_LEN_4;
+	attr.bp_type = HW_BREAKPOINT_W;
+	attr.disabled = 1;
+
+	for (i = 0; i < LOONGARCH_MAX_BRP; i++) {
+		if (breakinfo[i].pev)
+			continue;
+
+		breakinfo[i].pev = register_wide_hw_breakpoint(&attr, NULL, NULL);
+		if (IS_ERR((void * __force)breakinfo[i].pev)) {
+			pr_err("kgdb: Could not allocate hw breakpoints.\n");
+			breakinfo[i].pev = NULL;
+			return;
+		}
+
+		for_each_online_cpu(cpu) {
+			pevent = per_cpu_ptr(breakinfo[i].pev, cpu);
+			if (pevent[0]->destroy) {
+				pevent[0]->destroy = NULL;
+				release_bp_slot(*pevent);
+			}
+		}
+	}
+}
+
+void kgdb_arch_exit(void)
+{
+	int i;
+
+	for (i = 0; i < LOONGARCH_MAX_BRP; i++) {
+		if (breakinfo[i].pev) {
+			unregister_wide_hw_breakpoint(breakinfo[i].pev);
+			breakinfo[i].pev = NULL;
+		}
+	}
+
+	unregister_die_notifier(&kgdb_notifier);
+}
diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c
index 7ed01a7b2542..65214774ef7c 100644
--- a/arch/loongarch/kernel/traps.c
+++ b/arch/loongarch/kernel/traps.c
@@ -38,6 +38,7 @@
 #include <asm/fpu.h>
 #include <asm/lbt.h>
 #include <asm/inst.h>
+#include <asm/kgdb.h>
 #include <asm/loongarch.h>
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
@@ -703,6 +704,11 @@ asmlinkage void noinstr do_bp(struct pt_regs *regs)
 	 * pertain to them.
 	 */
 	switch (bcode) {
+	case BRK_KDB:
+		if (kgdb_breakpoint_handler(regs))
+			goto out;
+		else
+			break;
 	case BRK_KPROBE_BP:
 		if (kprobe_breakpoint_handler(regs))
 			goto out;
@@ -769,6 +775,9 @@ asmlinkage void noinstr do_watch(struct pt_regs *regs)
 #ifndef CONFIG_HAVE_HW_BREAKPOINT
 	pr_warn("Hardware watch point handler not implemented!\n");
 #else
+	if (kgdb_breakpoint_handler(regs))
+		goto out;
+
 	if (test_tsk_thread_flag(current, TIF_SINGLESTEP)) {
 		int llbit = (csr_read32(LOONGARCH_CSR_LLBCTL) & 0x1);
 		unsigned long pc = instruction_pointer(regs);

From b72961f847c0f0df113ae2d6ac9fd6b1e6bdeaf2 Mon Sep 17 00:00:00 2001
From: Feiyang Chen <chenfeiyang@loongson.cn>
Date: Wed, 6 Sep 2023 22:53:55 +0800
Subject: [PATCH 1124/1189] LoongArch: Provide kaslr_offset() to get kernel
 offset

Provide kaslr_offset() to get the kernel offset when KASLR is enabled.

Signed-off-by: Feiyang Chen <chenfeiyang@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/setup.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/arch/loongarch/include/asm/setup.h b/arch/loongarch/include/asm/setup.h
index be05c0e706a2..7c68b4365a4d 100644
--- a/arch/loongarch/include/asm/setup.h
+++ b/arch/loongarch/include/asm/setup.h
@@ -7,6 +7,7 @@
 #define _LOONGARCH_SETUP_H
 
 #include <linux/types.h>
+#include <asm/sections.h>
 #include <uapi/asm/setup.h>
 
 #define VECSIZE 0x200
@@ -37,4 +38,9 @@ extern void * __init relocate_kernel(void);
 
 #endif
 
+static inline unsigned long kaslr_offset(void)
+{
+	return (unsigned long)&_text - VMLINUX_LOAD_ADDRESS;
+}
+
 #endif /* __SETUP_H */

From 2363088eba2ecccfb643725e4864af73c4226a04 Mon Sep 17 00:00:00 2001
From: Feiyang Chen <chenfeiyang@loongson.cn>
Date: Wed, 6 Sep 2023 22:53:55 +0800
Subject: [PATCH 1125/1189] LoongArch: Allow building with kcov coverage

Add ARCH_HAS_KCOV and HAVE_GCC_PLUGINS to the LoongArch Kconfig. And
also disable instrumentation of vdso.

Signed-off-by: Feiyang Chen <chenfeiyang@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 Documentation/features/debug/kcov/arch-support.txt | 2 +-
 arch/loongarch/Kconfig                             | 2 ++
 arch/loongarch/vdso/Makefile                       | 2 ++
 3 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/Documentation/features/debug/kcov/arch-support.txt b/Documentation/features/debug/kcov/arch-support.txt
index ffcc9f2b1d74..de84cefbcdd3 100644
--- a/Documentation/features/debug/kcov/arch-support.txt
+++ b/Documentation/features/debug/kcov/arch-support.txt
@@ -13,7 +13,7 @@
     |        csky: | TODO |
     |     hexagon: | TODO |
     |        ia64: | TODO |
-    |   loongarch: | TODO |
+    |   loongarch: |  ok  |
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: |  ok  |
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index b02e399b1cd7..6cda4843f93b 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -13,6 +13,7 @@ config LOONGARCH
 	select ARCH_HAS_ACPI_TABLE_UPGRADE	if ACPI
 	select ARCH_HAS_CPU_FINALIZE_INIT
 	select ARCH_HAS_FORTIFY_SOURCE
+	select ARCH_HAS_KCOV
 	select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS
 	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PTE_SPECIAL
@@ -116,6 +117,7 @@ config LOONGARCH
 	select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
+	select HAVE_GCC_PLUGINS
 	select HAVE_GENERIC_VDSO
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS
 	select HAVE_IOREMAP_PROT
diff --git a/arch/loongarch/vdso/Makefile b/arch/loongarch/vdso/Makefile
index a50308b6fc25..d8b75f07c869 100644
--- a/arch/loongarch/vdso/Makefile
+++ b/arch/loongarch/vdso/Makefile
@@ -1,6 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 # Objects to go into the VDSO.
 
+KCOV_INSTRUMENT := n
+
 # Include the generic Makefile to check the built vdso.
 include $(srctree)/lib/vdso/Makefile
 

From ec9fee79d48f2f05cb1b95dc901071aa3670f228 Mon Sep 17 00:00:00 2001
From: Enze Li <lienze@kylinos.cn>
Date: Wed, 6 Sep 2023 22:53:55 +0800
Subject: [PATCH 1126/1189] kfence: Defer the assignment of the local variable
 addr

The LoongArch architecture is different from other architectures. It
needs to update __kfence_pool during arch_kfence_init_pool().

This patch modifies the assignment location of the local variable addr
in the kfence_init_pool() function to support the case of updating
__kfence_pool in arch_kfence_init_pool().

Acked-by: Marco Elver <elver@google.com>
Signed-off-by: Enze Li <lienze@kylinos.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 mm/kfence/core.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index dad3c0eb70a0..e124ffff489f 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -566,13 +566,14 @@ static void rcu_guarded_free(struct rcu_head *h)
  */
 static unsigned long kfence_init_pool(void)
 {
-	unsigned long addr = (unsigned long)__kfence_pool;
+	unsigned long addr;
 	struct page *pages;
 	int i;
 
 	if (!arch_kfence_init_pool())
-		return addr;
+		return (unsigned long)__kfence_pool;
 
+	addr = (unsigned long)__kfence_pool;
 	pages = virt_to_page(__kfence_pool);
 
 	/*

From 8b5cb1cbf33292372933e727805e68b506852234 Mon Sep 17 00:00:00 2001
From: Enze Li <lienze@kylinos.cn>
Date: Wed, 6 Sep 2023 22:53:55 +0800
Subject: [PATCH 1127/1189] LoongArch: mm: Add page table mapped mode support
 for virt_to_page()

According to LoongArch documentations, there are two types of address
translation modes: direct mapped address translation mode (DMW mode) and
page table mapped address translation mode (TLB mode).

Currently, virt_to_page() only supports direct mapped mode. This patch
determines which mode is used, and adds corresponding handling functions
for both modes.

For more details on the two modes, see [1].

[1] https://loongson.github.io/LoongArch-Documentation/LoongArch-Vol1-EN.html#virtual-address-space-and-address-translation-mode

Signed-off-by: Enze Li <lienze@kylinos.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/page.h    |  7 ++++++-
 arch/loongarch/include/asm/pgtable.h |  3 +++
 arch/loongarch/mm/pgtable.c          | 12 ++++++++++++
 3 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/arch/loongarch/include/asm/page.h b/arch/loongarch/include/asm/page.h
index 26e8dccb6619..63f137ce82a4 100644
--- a/arch/loongarch/include/asm/page.h
+++ b/arch/loongarch/include/asm/page.h
@@ -84,7 +84,12 @@ typedef struct { unsigned long pgprot; } pgprot_t;
 #define sym_to_pfn(x)		__phys_to_pfn(__pa_symbol(x))
 
 #define virt_to_pfn(kaddr)	PFN_DOWN(PHYSADDR(kaddr))
-#define virt_to_page(kaddr)	pfn_to_page(virt_to_pfn(kaddr))
+
+#define virt_to_page(kaddr)								\
+({											\
+	(likely((unsigned long)kaddr < vm_map_base)) ?					\
+	dmw_virt_to_page((unsigned long)kaddr) : tlb_virt_to_page((unsigned long)kaddr);\
+})
 
 extern int __virt_addr_valid(volatile void *kaddr);
 #define virt_addr_valid(kaddr)	__virt_addr_valid((volatile void *)(kaddr))
diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h
index 7699af049443..338d1b147464 100644
--- a/arch/loongarch/include/asm/pgtable.h
+++ b/arch/loongarch/include/asm/pgtable.h
@@ -353,6 +353,9 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *pt
 extern pgd_t swapper_pg_dir[];
 extern pgd_t invalid_pg_dir[];
 
+struct page *dmw_virt_to_page(unsigned long kaddr);
+struct page *tlb_virt_to_page(unsigned long kaddr);
+
 /*
  * The following only work if pte_present() is true.
  * Undefined behaviour if not..
diff --git a/arch/loongarch/mm/pgtable.c b/arch/loongarch/mm/pgtable.c
index 36a6dc0148ae..482923251824 100644
--- a/arch/loongarch/mm/pgtable.c
+++ b/arch/loongarch/mm/pgtable.c
@@ -9,6 +9,18 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 
+struct page *dmw_virt_to_page(unsigned long kaddr)
+{
+	return pfn_to_page(virt_to_pfn(kaddr));
+}
+EXPORT_SYMBOL_GPL(dmw_virt_to_page);
+
+struct page *tlb_virt_to_page(unsigned long kaddr)
+{
+	return pfn_to_page(pte_pfn(*virt_to_kpte(kaddr)));
+}
+EXPORT_SYMBOL_GPL(tlb_virt_to_page);
+
 pgd_t *pgd_alloc(struct mm_struct *mm)
 {
 	pgd_t *ret, *init;

From 95bb5b617beec0275bcc47b68796b34852fe4ecb Mon Sep 17 00:00:00 2001
From: Enze Li <lienze@kylinos.cn>
Date: Wed, 6 Sep 2023 22:54:16 +0800
Subject: [PATCH 1128/1189] LoongArch: Get partial stack information when
 providing regs parameter

Currently, arch_stack_walk() can only get the full stack information
including NMI.  This is because the implementation of arch_stack_walk()
is forced to ignore the information passed by the regs parameter and use
the current stack information instead.

For some detection systems like KFENCE, only partial stack information
is needed.  In particular, the stack frame where the interrupt occurred.

To support KFENCE, this patch modifies the implementation of the
arch_stack_walk() function so that if this function is called with the
regs argument passed, it retains all the stack information in regs and
uses it to provide accurate information.

Before this patch:
[    1.531195 ] ==================================================================
[    1.531442 ] BUG: KFENCE: out-of-bounds read in stack_trace_save_regs+0x48/0x6c
[    1.531442 ]
[    1.531900 ] Out-of-bounds read at 0xffff800012267fff (1B left of kfence-#12):
[    1.532046 ]  stack_trace_save_regs+0x48/0x6c
[    1.532169 ]  kfence_report_error+0xa4/0x528
[    1.532276 ]  kfence_handle_page_fault+0x124/0x270
[    1.532388 ]  no_context+0x50/0x94
[    1.532453 ]  do_page_fault+0x1a8/0x36c
[    1.532524 ]  tlb_do_page_fault_0+0x118/0x1b4
[    1.532623 ]  test_out_of_bounds_read+0xa0/0x1d8
[    1.532745 ]  kunit_generic_run_threadfn_adapter+0x1c/0x28
[    1.532854 ]  kthread+0x124/0x130
[    1.532922 ]  ret_from_kernel_thread+0xc/0xa4
<snip>

After this patch:
[    1.320220 ] ==================================================================
[    1.320401 ] BUG: KFENCE: out-of-bounds read in test_out_of_bounds_read+0xa8/0x1d8
[    1.320401 ]
[    1.320898 ] Out-of-bounds read at 0xffff800012257fff (1B left of kfence-#10):
[    1.321134 ]  test_out_of_bounds_read+0xa8/0x1d8
[    1.321264 ]  kunit_generic_run_threadfn_adapter+0x1c/0x28
[    1.321392 ]  kthread+0x124/0x130
[    1.321459 ]  ret_from_kernel_thread+0xc/0xa4
<snip>

Suggested-by: Jinyang He <hejinyang@loongson.cn>
Signed-off-by: Enze Li <lienze@kylinos.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/stacktrace.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/arch/loongarch/kernel/stacktrace.c b/arch/loongarch/kernel/stacktrace.c
index 2463d2fea21f..92270f14db94 100644
--- a/arch/loongarch/kernel/stacktrace.c
+++ b/arch/loongarch/kernel/stacktrace.c
@@ -18,17 +18,19 @@ void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
 	struct pt_regs dummyregs;
 	struct unwind_state state;
 
-	regs = &dummyregs;
+	if (!regs) {
+		regs = &dummyregs;
 
-	if (task == current) {
-		regs->regs[3] = (unsigned long)__builtin_frame_address(0);
-		regs->csr_era = (unsigned long)__builtin_return_address(0);
-	} else {
-		regs->regs[3] = thread_saved_fp(task);
-		regs->csr_era = thread_saved_ra(task);
+		if (task == current) {
+			regs->regs[3] = (unsigned long)__builtin_frame_address(0);
+			regs->csr_era = (unsigned long)__builtin_return_address(0);
+		} else {
+			regs->regs[3] = thread_saved_fp(task);
+			regs->csr_era = thread_saved_ra(task);
+		}
+		regs->regs[1] = 0;
 	}
 
-	regs->regs[1] = 0;
 	for (unwind_start(&state, task, regs);
 	     !unwind_done(&state) && !unwind_error(&state); unwind_next_frame(&state)) {
 		addr = unwind_get_return_address(&state);

From 6ad3df56bb199134800933df2afcd7df3b03ef33 Mon Sep 17 00:00:00 2001
From: Enze Li <lienze@kylinos.cn>
Date: Wed, 6 Sep 2023 22:54:16 +0800
Subject: [PATCH 1129/1189] LoongArch: Add KFENCE (Kernel Electric-Fence)
 support

The LoongArch architecture is quite different from other architectures.
When the allocating of KFENCE itself is done, it is mapped to the direct
mapping configuration window [1] by default on LoongArch.  It means that
it is not possible to use the page table mapped mode which required by
the KFENCE system and therefore it should be remapped to the appropriate
region.

This patch adds architecture specific implementation details for KFENCE.
In particular, this implements the required interface in <asm/kfence.h>.

Tested this patch by running the testcases and all passed.

[1] https://loongson.github.io/LoongArch-Documentation/LoongArch-Vol1-EN.html#virtual-address-space-and-address-translation-mode

Signed-off-by: Enze Li <lienze@kylinos.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/Kconfig               |  1 +
 arch/loongarch/include/asm/kfence.h  | 61 ++++++++++++++++++++++++++++
 arch/loongarch/include/asm/pgtable.h | 11 ++++-
 arch/loongarch/mm/fault.c            | 22 ++++++----
 4 files changed, 86 insertions(+), 9 deletions(-)
 create mode 100644 arch/loongarch/include/asm/kfence.h

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 6cda4843f93b..0619ec165424 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -92,6 +92,7 @@ config LOONGARCH
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_JUMP_LABEL_RELATIVE
+	select HAVE_ARCH_KFENCE
 	select HAVE_ARCH_KGDB if PERF_EVENTS
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
 	select HAVE_ARCH_SECCOMP_FILTER
diff --git a/arch/loongarch/include/asm/kfence.h b/arch/loongarch/include/asm/kfence.h
new file mode 100644
index 000000000000..6c82aea1c993
--- /dev/null
+++ b/arch/loongarch/include/asm/kfence.h
@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * KFENCE support for LoongArch.
+ *
+ * Author: Enze Li <lienze@kylinos.cn>
+ * Copyright (C) 2022-2023 KylinSoft Corporation.
+ */
+
+#ifndef _ASM_LOONGARCH_KFENCE_H
+#define _ASM_LOONGARCH_KFENCE_H
+
+#include <linux/kfence.h>
+#include <asm/pgtable.h>
+#include <asm/tlb.h>
+
+static inline bool arch_kfence_init_pool(void)
+{
+	int err;
+	char *kfence_pool = __kfence_pool;
+	struct vm_struct *area;
+
+	area = __get_vm_area_caller(KFENCE_POOL_SIZE, VM_IOREMAP,
+				    KFENCE_AREA_START, KFENCE_AREA_END,
+				    __builtin_return_address(0));
+	if (!area)
+		return false;
+
+	__kfence_pool = (char *)area->addr;
+	err = ioremap_page_range((unsigned long)__kfence_pool,
+				 (unsigned long)__kfence_pool + KFENCE_POOL_SIZE,
+				 virt_to_phys((void *)kfence_pool), PAGE_KERNEL);
+	if (err) {
+		free_vm_area(area);
+		__kfence_pool = kfence_pool;
+		return false;
+	}
+
+	return true;
+}
+
+/* Protect the given page and flush TLB. */
+static inline bool kfence_protect_page(unsigned long addr, bool protect)
+{
+	pte_t *pte = virt_to_kpte(addr);
+
+	if (WARN_ON(!pte) || pte_none(*pte))
+		return false;
+
+	if (protect)
+		set_pte(pte, __pte(pte_val(*pte) & ~(_PAGE_VALID | _PAGE_PRESENT)));
+	else
+		set_pte(pte, __pte(pte_val(*pte) | (_PAGE_VALID | _PAGE_PRESENT)));
+
+	preempt_disable();
+	local_flush_tlb_one(addr);
+	preempt_enable();
+
+	return true;
+}
+
+#endif /* _ASM_LOONGARCH_KFENCE_H */
diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h
index 338d1b147464..7e3708883994 100644
--- a/arch/loongarch/include/asm/pgtable.h
+++ b/arch/loongarch/include/asm/pgtable.h
@@ -82,14 +82,23 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 #define MODULES_VADDR	(vm_map_base + PCI_IOSIZE + (2 * PAGE_SIZE))
 #define MODULES_END	(MODULES_VADDR + SZ_256M)
 
+#ifdef CONFIG_KFENCE
+#define KFENCE_AREA_SIZE	(((CONFIG_KFENCE_NUM_OBJECTS + 1) * 2 + 2) * PAGE_SIZE)
+#else
+#define KFENCE_AREA_SIZE	0
+#endif
+
 #define VMALLOC_START	MODULES_END
 #define VMALLOC_END	\
 	(vm_map_base +	\
-	 min(PTRS_PER_PGD * PTRS_PER_PUD * PTRS_PER_PMD * PTRS_PER_PTE * PAGE_SIZE, (1UL << cpu_vabits)) - PMD_SIZE - VMEMMAP_SIZE)
+	 min(PTRS_PER_PGD * PTRS_PER_PUD * PTRS_PER_PMD * PTRS_PER_PTE * PAGE_SIZE, (1UL << cpu_vabits)) - PMD_SIZE - VMEMMAP_SIZE - KFENCE_AREA_SIZE)
 
 #define vmemmap		((struct page *)((VMALLOC_END + PMD_SIZE) & PMD_MASK))
 #define VMEMMAP_END	((unsigned long)vmemmap + VMEMMAP_SIZE - 1)
 
+#define KFENCE_AREA_START	(VMEMMAP_END + 1)
+#define KFENCE_AREA_END		(KFENCE_AREA_START + KFENCE_AREA_SIZE - 1)
+
 #define pte_ERROR(e) \
 	pr_err("%s:%d: bad pte %016lx.\n", __FILE__, __LINE__, pte_val(e))
 #ifndef __PAGETABLE_PMD_FOLDED
diff --git a/arch/loongarch/mm/fault.c b/arch/loongarch/mm/fault.c
index da5b6d518cdb..e6376e3dce86 100644
--- a/arch/loongarch/mm/fault.c
+++ b/arch/loongarch/mm/fault.c
@@ -23,6 +23,7 @@
 #include <linux/kprobes.h>
 #include <linux/perf_event.h>
 #include <linux/uaccess.h>
+#include <linux/kfence.h>
 
 #include <asm/branch.h>
 #include <asm/mmu_context.h>
@@ -30,7 +31,8 @@
 
 int show_unhandled_signals = 1;
 
-static void __kprobes no_context(struct pt_regs *regs, unsigned long address)
+static void __kprobes no_context(struct pt_regs *regs,
+			unsigned long write, unsigned long address)
 {
 	const int field = sizeof(unsigned long) * 2;
 
@@ -38,6 +40,9 @@ static void __kprobes no_context(struct pt_regs *regs, unsigned long address)
 	if (fixup_exception(regs))
 		return;
 
+	if (kfence_handle_page_fault(address, write, regs))
+		return;
+
 	/*
 	 * Oops. The kernel tried to access some bad page. We'll have to
 	 * terminate things with extreme prejudice.
@@ -51,14 +56,15 @@ static void __kprobes no_context(struct pt_regs *regs, unsigned long address)
 	die("Oops", regs);
 }
 
-static void __kprobes do_out_of_memory(struct pt_regs *regs, unsigned long address)
+static void __kprobes do_out_of_memory(struct pt_regs *regs,
+			unsigned long write, unsigned long address)
 {
 	/*
 	 * We ran out of memory, call the OOM killer, and return the userspace
 	 * (which will retry the fault, or kill us if we got oom-killed).
 	 */
 	if (!user_mode(regs)) {
-		no_context(regs, address);
+		no_context(regs, write, address);
 		return;
 	}
 	pagefault_out_of_memory();
@@ -69,7 +75,7 @@ static void __kprobes do_sigbus(struct pt_regs *regs,
 {
 	/* Kernel mode? Handle exceptions or die */
 	if (!user_mode(regs)) {
-		no_context(regs, address);
+		no_context(regs, write, address);
 		return;
 	}
 
@@ -90,7 +96,7 @@ static void __kprobes do_sigsegv(struct pt_regs *regs,
 
 	/* Kernel mode? Handle exceptions or die */
 	if (!user_mode(regs)) {
-		no_context(regs, address);
+		no_context(regs, write, address);
 		return;
 	}
 
@@ -149,7 +155,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs,
 	 */
 	if (address & __UA_LIMIT) {
 		if (!user_mode(regs))
-			no_context(regs, address);
+			no_context(regs, write, address);
 		else
 			do_sigsegv(regs, write, address, si_code);
 		return;
@@ -211,7 +217,7 @@ good_area:
 
 	if (fault_signal_pending(fault, regs)) {
 		if (!user_mode(regs))
-			no_context(regs, address);
+			no_context(regs, write, address);
 		return;
 	}
 
@@ -232,7 +238,7 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		mmap_read_unlock(mm);
 		if (fault & VM_FAULT_OOM) {
-			do_out_of_memory(regs, address);
+			do_out_of_memory(regs, write, address);
 			return;
 		} else if (fault & VM_FAULT_SIGSEGV) {
 			do_sigsegv(regs, write, address, si_code);

From 9b04c764af18a1dab6d48ca0671f70cdcccf90a2 Mon Sep 17 00:00:00 2001
From: Qing Zhang <zhangqing@loongson.cn>
Date: Wed, 6 Sep 2023 22:54:16 +0800
Subject: [PATCH 1130/1189] kasan: Add __HAVE_ARCH_SHADOW_MAP to support arch
 specific mapping

MIPS, LoongArch and some other architectures have many holes between
different segments and the valid address space (256T available) is
insufficient to map all these segments to kasan shadow memory with the
common formula provided by kasan core. So we need architecture specific
mapping formulas to ensure different segments are mapped individually,
and only limited space lengths of those specific segments are mapped to
shadow.

Therefore, when the incoming address is converted to a shadow, we need
to add a condition to determine whether it is valid.

Reviewed-by: Andrey Konovalov <andreyknvl@gmail.com>
Signed-off-by: Qing Zhang <zhangqing@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 include/linux/kasan.h | 2 ++
 mm/kasan/kasan.h      | 6 ++++++
 2 files changed, 8 insertions(+)

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 819b6bc8ac08..3df5499f7936 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -54,11 +54,13 @@ extern p4d_t kasan_early_shadow_p4d[MAX_PTRS_PER_P4D];
 int kasan_populate_early_shadow(const void *shadow_start,
 				const void *shadow_end);
 
+#ifndef __HAVE_ARCH_SHADOW_MAP
 static inline void *kasan_mem_to_shadow(const void *addr)
 {
 	return (void *)((unsigned long)addr >> KASAN_SHADOW_SCALE_SHIFT)
 		+ KASAN_SHADOW_OFFSET;
 }
+#endif
 
 int kasan_add_zero_shadow(void *start, unsigned long size);
 void kasan_remove_zero_shadow(void *start, unsigned long size);
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index 2e973b36fe07..f70e3d7a602e 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -291,16 +291,22 @@ struct kasan_stack_ring {
 
 #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 
+#ifndef __HAVE_ARCH_SHADOW_MAP
 static inline const void *kasan_shadow_to_mem(const void *shadow_addr)
 {
 	return (void *)(((unsigned long)shadow_addr - KASAN_SHADOW_OFFSET)
 		<< KASAN_SHADOW_SCALE_SHIFT);
 }
+#endif
 
 static __always_inline bool addr_has_metadata(const void *addr)
 {
+#ifdef __HAVE_ARCH_SHADOW_MAP
+	return (kasan_mem_to_shadow((void *)addr) != NULL);
+#else
 	return (kasan_reset_tag(addr) >=
 		kasan_shadow_to_mem((void *)KASAN_SHADOW_START));
+#endif
 }
 
 /**

From fb6d5c1d99ab6958c5e284f7aa5f0cc553f0268c Mon Sep 17 00:00:00 2001
From: Qing Zhang <zhangqing@loongson.cn>
Date: Wed, 6 Sep 2023 22:54:16 +0800
Subject: [PATCH 1131/1189] kasan: Add (pmd|pud)_init for LoongArch
 zero_(pud|p4d)_populate process

LoongArch populates pmd/pud with invalid_pmd_table/invalid_pud_table in
pagetable_init, So pmd_init/pud_init(p) is required, define them as __weak
in mm/kasan/init.c, like mm/sparse-vmemmap.c.

Reviewed-by: Andrey Konovalov <andreyknvl@gmail.com>
Signed-off-by: Qing Zhang <zhangqing@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 mm/kasan/init.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/mm/kasan/init.c b/mm/kasan/init.c
index dcfec277e839..89895f38f722 100644
--- a/mm/kasan/init.c
+++ b/mm/kasan/init.c
@@ -139,6 +139,10 @@ static int __ref zero_pmd_populate(pud_t *pud, unsigned long addr,
 	return 0;
 }
 
+void __weak __meminit pmd_init(void *addr)
+{
+}
+
 static int __ref zero_pud_populate(p4d_t *p4d, unsigned long addr,
 				unsigned long end)
 {
@@ -166,8 +170,9 @@ static int __ref zero_pud_populate(p4d_t *p4d, unsigned long addr,
 				if (!p)
 					return -ENOMEM;
 			} else {
-				pud_populate(&init_mm, pud,
-					early_alloc(PAGE_SIZE, NUMA_NO_NODE));
+				p = early_alloc(PAGE_SIZE, NUMA_NO_NODE);
+				pmd_init(p);
+				pud_populate(&init_mm, pud, p);
 			}
 		}
 		zero_pmd_populate(pud, addr, next);
@@ -176,6 +181,10 @@ static int __ref zero_pud_populate(p4d_t *p4d, unsigned long addr,
 	return 0;
 }
 
+void __weak __meminit pud_init(void *addr)
+{
+}
+
 static int __ref zero_p4d_populate(pgd_t *pgd, unsigned long addr,
 				unsigned long end)
 {
@@ -207,8 +216,9 @@ static int __ref zero_p4d_populate(pgd_t *pgd, unsigned long addr,
 				if (!p)
 					return -ENOMEM;
 			} else {
-				p4d_populate(&init_mm, p4d,
-					early_alloc(PAGE_SIZE, NUMA_NO_NODE));
+				p = early_alloc(PAGE_SIZE, NUMA_NO_NODE);
+				pud_init(p);
+				p4d_populate(&init_mm, p4d, p);
 			}
 		}
 		zero_pud_populate(p4d, addr, next);

From 9fbcc076798ead2af28c854a265d9da83bec8429 Mon Sep 17 00:00:00 2001
From: Qing Zhang <zhangqing@loongson.cn>
Date: Wed, 6 Sep 2023 22:54:16 +0800
Subject: [PATCH 1132/1189] LoongArch: Simplify the processing of jumping new
 kernel for KASLR

Modified relocate_kernel() doesn't return new kernel's entry point but
the random_offset. In this way we share the start_kernel() processing
with the normal kernel, which avoids calling 'jr a0' directly and allows
some other operations (e.g, kasan_early_init) before start_kernel() when
KASLR (CONFIG_RANDOMIZE_BASE) is turned on.

Signed-off-by: Qing Zhang <zhangqing@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/setup.h |  2 +-
 arch/loongarch/kernel/head.S       | 11 ++++++-----
 arch/loongarch/kernel/relocate.c   |  8 ++------
 3 files changed, 9 insertions(+), 12 deletions(-)

diff --git a/arch/loongarch/include/asm/setup.h b/arch/loongarch/include/asm/setup.h
index 7c68b4365a4d..a0bc159ce8bd 100644
--- a/arch/loongarch/include/asm/setup.h
+++ b/arch/loongarch/include/asm/setup.h
@@ -34,7 +34,7 @@ extern long __la_abs_end;
 extern long __rela_dyn_begin;
 extern long __rela_dyn_end;
 
-extern void * __init relocate_kernel(void);
+extern unsigned long __init relocate_kernel(void);
 
 #endif
 
diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S
index 5e828a8bc0a0..5743fef70dfe 100644
--- a/arch/loongarch/kernel/head.S
+++ b/arch/loongarch/kernel/head.S
@@ -95,13 +95,14 @@ SYM_CODE_START(kernel_entry)			# kernel entry point
 	PTR_LI		sp, (_THREAD_SIZE - PT_SIZE)
 	PTR_ADD		sp, sp, tp
 	set_saved_sp	sp, t0, t1
-#endif
 
-	/* relocate_kernel() returns the new kernel entry point */
-	jr		a0
-	ASM_BUG()
+	/* Jump to the new kernel: new_pc = current_pc + random_offset */
+	pcaddi		t0, 0
+	add.d		t0, t0, a0
+	jirl		zero, t0, 0xc
+#endif /* CONFIG_RANDOMIZE_BASE */
 
-#endif
+#endif /* CONFIG_RELOCATABLE */
 
 	bl		start_kernel
 	ASM_BUG()
diff --git a/arch/loongarch/kernel/relocate.c b/arch/loongarch/kernel/relocate.c
index 01f94d1e3edf..6c3eff9af9fb 100644
--- a/arch/loongarch/kernel/relocate.c
+++ b/arch/loongarch/kernel/relocate.c
@@ -157,12 +157,11 @@ static inline void __init update_reloc_offset(unsigned long *addr, long random_o
 	*new_addr = (unsigned long)reloc_offset;
 }
 
-void * __init relocate_kernel(void)
+unsigned long __init relocate_kernel(void)
 {
 	unsigned long kernel_length;
 	unsigned long random_offset = 0;
 	void *location_new = _text; /* Default to original kernel start */
-	void *kernel_entry = start_kernel; /* Default to original kernel entry point */
 	char *cmdline = early_ioremap(fw_arg1, COMMAND_LINE_SIZE); /* Boot command line is passed in fw_arg1 */
 
 	strscpy(boot_command_line, cmdline, COMMAND_LINE_SIZE);
@@ -190,9 +189,6 @@ void * __init relocate_kernel(void)
 
 		reloc_offset += random_offset;
 
-		/* Return the new kernel's entry point */
-		kernel_entry = RELOCATED_KASLR(start_kernel);
-
 		/* The current thread is now within the relocated kernel */
 		__current_thread_info = RELOCATED_KASLR(__current_thread_info);
 
@@ -204,7 +200,7 @@ void * __init relocate_kernel(void)
 
 	relocate_absolute(random_offset);
 
-	return kernel_entry;
+	return random_offset;
 }
 
 /*

From 5aa4ac64e6add3e40d5049e31275b2822daf885d Mon Sep 17 00:00:00 2001
From: Qing Zhang <zhangqing@loongson.cn>
Date: Wed, 6 Sep 2023 22:54:16 +0800
Subject: [PATCH 1133/1189] LoongArch: Add KASAN (Kernel Address Sanitizer)
 support

1/8 of kernel addresses reserved for shadow memory. But for LoongArch,
There are a lot of holes between different segments and valid address
space (256T available) is insufficient to map all these segments to kasan
shadow memory with the common formula provided by kasan core, saying
(addr >> KASAN_SHADOW_SCALE_SHIFT) + KASAN_SHADOW_OFFSET

So LoongArch has a arch-specific mapping formula, different segments are
mapped individually, and only limited space lengths of these specific
segments are mapped to shadow.

At early boot stage the whole shadow region populated with just one
physical page (kasan_early_shadow_page). Later, this page is reused as
readonly zero shadow for some memory that kasan currently don't track.
After mapping the physical memory, pages for shadow memory are allocated
and mapped.

Functions like memset()/memcpy()/memmove() do a lot of memory accesses.
If bad pointer passed to one of these function it is important to be
caught. Compiler's instrumentation cannot do this since these functions
are written in assembly.

KASan replaces memory functions with manually instrumented variants.
Original functions declared as weak symbols so strong definitions in
mm/kasan/kasan.c could replace them. Original functions have aliases
with '__' prefix in names, so we could call non-instrumented variant
if needed.

Signed-off-by: Qing Zhang <zhangqing@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 Documentation/dev-tools/kasan.rst             |   4 +-
 .../features/debug/KASAN/arch-support.txt     |   2 +-
 .../translations/zh_CN/dev-tools/kasan.rst    |   2 +-
 arch/loongarch/Kconfig                        |   7 +
 arch/loongarch/Makefile                       |   3 +
 arch/loongarch/include/asm/kasan.h            | 126 +++++++++
 arch/loongarch/include/asm/pgtable.h          |   7 +
 arch/loongarch/include/asm/string.h           |  20 ++
 arch/loongarch/kernel/Makefile                |   6 +
 arch/loongarch/kernel/head.S                  |   4 +
 arch/loongarch/kernel/setup.c                 |   4 +
 arch/loongarch/lib/memcpy.S                   |   8 +-
 arch/loongarch/lib/memmove.S                  |  20 +-
 arch/loongarch/lib/memset.S                   |   8 +-
 arch/loongarch/mm/Makefile                    |   3 +
 arch/loongarch/mm/kasan_init.c                | 243 ++++++++++++++++++
 arch/loongarch/vdso/Makefile                  |   1 +
 17 files changed, 455 insertions(+), 13 deletions(-)
 create mode 100644 arch/loongarch/include/asm/kasan.h
 create mode 100644 arch/loongarch/mm/kasan_init.c

diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst
index f4acf9c2e90f..382818a7197a 100644
--- a/Documentation/dev-tools/kasan.rst
+++ b/Documentation/dev-tools/kasan.rst
@@ -41,8 +41,8 @@ Support
 Architectures
 ~~~~~~~~~~~~~
 
-Generic KASAN is supported on x86_64, arm, arm64, powerpc, riscv, s390, and
-xtensa, and the tag-based KASAN modes are supported only on arm64.
+Generic KASAN is supported on x86_64, arm, arm64, powerpc, riscv, s390, xtensa,
+and loongarch, and the tag-based KASAN modes are supported only on arm64.
 
 Compilers
 ~~~~~~~~~
diff --git a/Documentation/features/debug/KASAN/arch-support.txt b/Documentation/features/debug/KASAN/arch-support.txt
index bf0124fae643..c4581c2edb28 100644
--- a/Documentation/features/debug/KASAN/arch-support.txt
+++ b/Documentation/features/debug/KASAN/arch-support.txt
@@ -13,7 +13,7 @@
     |        csky: | TODO |
     |     hexagon: | TODO |
     |        ia64: | TODO |
-    |   loongarch: | TODO |
+    |   loongarch: |  ok  |
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: | TODO |
diff --git a/Documentation/translations/zh_CN/dev-tools/kasan.rst b/Documentation/translations/zh_CN/dev-tools/kasan.rst
index 05ef904dbcfb..8fdb20c9665b 100644
--- a/Documentation/translations/zh_CN/dev-tools/kasan.rst
+++ b/Documentation/translations/zh_CN/dev-tools/kasan.rst
@@ -42,7 +42,7 @@ KASAN有三种模式:
 体系架构
 ~~~~~~~~
 
-在x86_64、arm、arm64、powerpc、riscv、s390和xtensa上支持通用KASAN，
+在x86_64、arm、arm64、powerpc、riscv、s390、xtensa和loongarch上支持通用KASAN，
 而基于标签的KASAN模式只在arm64上支持。
 
 编译器
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 0619ec165424..32157188d5b8 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -8,6 +8,7 @@ config LOONGARCH
 	select ACPI_PPTT if ACPI
 	select ACPI_SYSTEM_POWER_STATES_SUPPORT	if ACPI
 	select ARCH_BINFMT_ELF_STATE
+	select ARCH_DISABLE_KASAN_INLINE
 	select ARCH_ENABLE_MEMORY_HOTPLUG
 	select ARCH_ENABLE_MEMORY_HOTREMOVE
 	select ARCH_HAS_ACPI_TABLE_UPGRADE	if ACPI
@@ -92,6 +93,7 @@ config LOONGARCH
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_JUMP_LABEL_RELATIVE
+	select HAVE_ARCH_KASAN
 	select HAVE_ARCH_KFENCE
 	select HAVE_ARCH_KGDB if PERF_EVENTS
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
@@ -669,6 +671,11 @@ config ARCH_MMAP_RND_BITS_MAX
 config ARCH_SUPPORTS_UPROBES
 	def_bool y
 
+config KASAN_SHADOW_OFFSET
+	hex
+	default 0x0
+	depends on KASAN
+
 menu "Power management options"
 
 config ARCH_SUSPEND_POSSIBLE
diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile
index ef87bab46754..fb0fada43197 100644
--- a/arch/loongarch/Makefile
+++ b/arch/loongarch/Makefile
@@ -84,7 +84,10 @@ LDFLAGS_vmlinux			+= -static -pie --no-dynamic-linker -z notext
 endif
 
 cflags-y += $(call cc-option, -mno-check-zero-division)
+
+ifndef CONFIG_KASAN
 cflags-y += -fno-builtin-memcpy -fno-builtin-memmove -fno-builtin-memset
+endif
 
 load-y		= 0x9000000000200000
 bootvars-y	= VMLINUX_LOAD_ADDRESS=$(load-y)
diff --git a/arch/loongarch/include/asm/kasan.h b/arch/loongarch/include/asm/kasan.h
new file mode 100644
index 000000000000..deeff8158f45
--- /dev/null
+++ b/arch/loongarch/include/asm/kasan.h
@@ -0,0 +1,126 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_KASAN_H
+#define __ASM_KASAN_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/linkage.h>
+#include <linux/mmzone.h>
+#include <asm/addrspace.h>
+#include <asm/io.h>
+#include <asm/pgtable.h>
+
+#define __HAVE_ARCH_SHADOW_MAP
+
+#define KASAN_SHADOW_SCALE_SHIFT 3
+#define KASAN_SHADOW_OFFSET	_AC(CONFIG_KASAN_SHADOW_OFFSET, UL)
+
+#define XRANGE_SHIFT (48)
+
+/* Valid address length */
+#define XRANGE_SHADOW_SHIFT	(PGDIR_SHIFT + PAGE_SHIFT - 3)
+/* Used for taking out the valid address */
+#define XRANGE_SHADOW_MASK	GENMASK_ULL(XRANGE_SHADOW_SHIFT - 1, 0)
+/* One segment whole address space size */
+#define XRANGE_SIZE		(XRANGE_SHADOW_MASK + 1)
+
+/* 64-bit segment value. */
+#define XKPRANGE_UC_SEG		(0x8000)
+#define XKPRANGE_CC_SEG		(0x9000)
+#define XKVRANGE_VC_SEG		(0xffff)
+
+/* Cached */
+#define XKPRANGE_CC_START		CACHE_BASE
+#define XKPRANGE_CC_SIZE		XRANGE_SIZE
+#define XKPRANGE_CC_KASAN_OFFSET	(0)
+#define XKPRANGE_CC_SHADOW_SIZE		(XKPRANGE_CC_SIZE >> KASAN_SHADOW_SCALE_SHIFT)
+#define XKPRANGE_CC_SHADOW_END		(XKPRANGE_CC_KASAN_OFFSET + XKPRANGE_CC_SHADOW_SIZE)
+
+/* UnCached */
+#define XKPRANGE_UC_START		UNCACHE_BASE
+#define XKPRANGE_UC_SIZE		XRANGE_SIZE
+#define XKPRANGE_UC_KASAN_OFFSET	XKPRANGE_CC_SHADOW_END
+#define XKPRANGE_UC_SHADOW_SIZE		(XKPRANGE_UC_SIZE >> KASAN_SHADOW_SCALE_SHIFT)
+#define XKPRANGE_UC_SHADOW_END		(XKPRANGE_UC_KASAN_OFFSET + XKPRANGE_UC_SHADOW_SIZE)
+
+/* VMALLOC (Cached or UnCached)  */
+#define XKVRANGE_VC_START		MODULES_VADDR
+#define XKVRANGE_VC_SIZE		round_up(KFENCE_AREA_END - MODULES_VADDR + 1, PGDIR_SIZE)
+#define XKVRANGE_VC_KASAN_OFFSET	XKPRANGE_UC_SHADOW_END
+#define XKVRANGE_VC_SHADOW_SIZE		(XKVRANGE_VC_SIZE >> KASAN_SHADOW_SCALE_SHIFT)
+#define XKVRANGE_VC_SHADOW_END		(XKVRANGE_VC_KASAN_OFFSET + XKVRANGE_VC_SHADOW_SIZE)
+
+/* KAsan shadow memory start right after vmalloc. */
+#define KASAN_SHADOW_START		round_up(KFENCE_AREA_END, PGDIR_SIZE)
+#define KASAN_SHADOW_SIZE		(XKVRANGE_VC_SHADOW_END - XKPRANGE_CC_KASAN_OFFSET)
+#define KASAN_SHADOW_END		round_up(KASAN_SHADOW_START + KASAN_SHADOW_SIZE, PGDIR_SIZE)
+
+#define XKPRANGE_CC_SHADOW_OFFSET	(KASAN_SHADOW_START + XKPRANGE_CC_KASAN_OFFSET)
+#define XKPRANGE_UC_SHADOW_OFFSET	(KASAN_SHADOW_START + XKPRANGE_UC_KASAN_OFFSET)
+#define XKVRANGE_VC_SHADOW_OFFSET	(KASAN_SHADOW_START + XKVRANGE_VC_KASAN_OFFSET)
+
+extern bool kasan_early_stage;
+extern unsigned char kasan_early_shadow_page[PAGE_SIZE];
+
+#define kasan_arch_is_ready kasan_arch_is_ready
+static __always_inline bool kasan_arch_is_ready(void)
+{
+	return !kasan_early_stage;
+}
+
+static inline void *kasan_mem_to_shadow(const void *addr)
+{
+	if (!kasan_arch_is_ready()) {
+		return (void *)(kasan_early_shadow_page);
+	} else {
+		unsigned long maddr = (unsigned long)addr;
+		unsigned long xrange = (maddr >> XRANGE_SHIFT) & 0xffff;
+		unsigned long offset = 0;
+
+		maddr &= XRANGE_SHADOW_MASK;
+		switch (xrange) {
+		case XKPRANGE_CC_SEG:
+			offset = XKPRANGE_CC_SHADOW_OFFSET;
+			break;
+		case XKPRANGE_UC_SEG:
+			offset = XKPRANGE_UC_SHADOW_OFFSET;
+			break;
+		case XKVRANGE_VC_SEG:
+			offset = XKVRANGE_VC_SHADOW_OFFSET;
+			break;
+		default:
+			WARN_ON(1);
+			return NULL;
+		}
+
+		return (void *)((maddr >> KASAN_SHADOW_SCALE_SHIFT) + offset);
+	}
+}
+
+static inline const void *kasan_shadow_to_mem(const void *shadow_addr)
+{
+	unsigned long addr = (unsigned long)shadow_addr;
+
+	if (unlikely(addr > KASAN_SHADOW_END) ||
+		unlikely(addr < KASAN_SHADOW_START)) {
+		WARN_ON(1);
+		return NULL;
+	}
+
+	if (addr >= XKVRANGE_VC_SHADOW_OFFSET)
+		return (void *)(((addr - XKVRANGE_VC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKVRANGE_VC_START);
+	else if (addr >= XKPRANGE_UC_SHADOW_OFFSET)
+		return (void *)(((addr - XKPRANGE_UC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKPRANGE_UC_START);
+	else if (addr >= XKPRANGE_CC_SHADOW_OFFSET)
+		return (void *)(((addr - XKPRANGE_CC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKPRANGE_CC_START);
+	else {
+		WARN_ON(1);
+		return NULL;
+	}
+}
+
+void kasan_init(void);
+asmlinkage void kasan_early_init(void);
+
+#endif
+#endif
diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h
index 7e3708883994..e5675ce0907a 100644
--- a/arch/loongarch/include/asm/pgtable.h
+++ b/arch/loongarch/include/asm/pgtable.h
@@ -89,9 +89,16 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 #endif
 
 #define VMALLOC_START	MODULES_END
+
+#ifndef CONFIG_KASAN
 #define VMALLOC_END	\
 	(vm_map_base +	\
 	 min(PTRS_PER_PGD * PTRS_PER_PUD * PTRS_PER_PMD * PTRS_PER_PTE * PAGE_SIZE, (1UL << cpu_vabits)) - PMD_SIZE - VMEMMAP_SIZE - KFENCE_AREA_SIZE)
+#else
+#define VMALLOC_END	\
+	(vm_map_base +	\
+	 min(PTRS_PER_PGD * PTRS_PER_PUD * PTRS_PER_PMD * PTRS_PER_PTE * PAGE_SIZE, (1UL << cpu_vabits) / 2) - PMD_SIZE - VMEMMAP_SIZE - KFENCE_AREA_SIZE)
+#endif
 
 #define vmemmap		((struct page *)((VMALLOC_END + PMD_SIZE) & PMD_MASK))
 #define VMEMMAP_END	((unsigned long)vmemmap + VMEMMAP_SIZE - 1)
diff --git a/arch/loongarch/include/asm/string.h b/arch/loongarch/include/asm/string.h
index 7b29cc9c70aa..5bb5a90d2681 100644
--- a/arch/loongarch/include/asm/string.h
+++ b/arch/loongarch/include/asm/string.h
@@ -7,11 +7,31 @@
 
 #define __HAVE_ARCH_MEMSET
 extern void *memset(void *__s, int __c, size_t __count);
+extern void *__memset(void *__s, int __c, size_t __count);
 
 #define __HAVE_ARCH_MEMCPY
 extern void *memcpy(void *__to, __const__ void *__from, size_t __n);
+extern void *__memcpy(void *__to, __const__ void *__from, size_t __n);
 
 #define __HAVE_ARCH_MEMMOVE
 extern void *memmove(void *__dest, __const__ void *__src, size_t __n);
+extern void *__memmove(void *__dest, __const__ void *__src, size_t __n);
+
+#if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__)
+
+/*
+ * For files that are not instrumented (e.g. mm/slub.c) we
+ * should use not instrumented version of mem* functions.
+ */
+
+#define memset(s, c, n) __memset(s, c, n)
+#define memcpy(dst, src, len) __memcpy(dst, src, len)
+#define memmove(dst, src, len) __memmove(dst, src, len)
+
+#ifndef __NO_FORTIFY
+#define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */
+#endif
+
+#endif
 
 #endif /* _ASM_STRING_H */
diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile
index c0b88528cb81..c56ea0b75448 100644
--- a/arch/loongarch/kernel/Makefile
+++ b/arch/loongarch/kernel/Makefile
@@ -34,6 +34,12 @@ ifdef CONFIG_FUNCTION_TRACER
   CFLAGS_REMOVE_rethook_trampoline.o = $(CC_FLAGS_FTRACE)
 endif
 
+KASAN_SANITIZE_efi.o := n
+KASAN_SANITIZE_cpu-probe.o := n
+KASAN_SANITIZE_traps.o := n
+KASAN_SANITIZE_smp.o := n
+KASAN_SANITIZE_vdso.o := n
+
 obj-$(CONFIG_MODULES)		+= module.o module-sections.o
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 
diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S
index 5743fef70dfe..53b883db0786 100644
--- a/arch/loongarch/kernel/head.S
+++ b/arch/loongarch/kernel/head.S
@@ -104,6 +104,10 @@ SYM_CODE_START(kernel_entry)			# kernel entry point
 
 #endif /* CONFIG_RELOCATABLE */
 
+#ifdef CONFIG_KASAN
+	bl		kasan_early_init
+#endif
+
 	bl		start_kernel
 	ASM_BUG()
 
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index 9d830ab4e302..7783f0a3d742 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -626,4 +626,8 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 	paging_init();
+
+#ifdef CONFIG_KASAN
+	kasan_init();
+#endif
 }
diff --git a/arch/loongarch/lib/memcpy.S b/arch/loongarch/lib/memcpy.S
index cc30b3b6252f..fa1148878d2b 100644
--- a/arch/loongarch/lib/memcpy.S
+++ b/arch/loongarch/lib/memcpy.S
@@ -10,6 +10,8 @@
 #include <asm/cpu.h>
 #include <asm/regdef.h>
 
+.section .noinstr.text, "ax"
+
 SYM_FUNC_START(memcpy)
 	/*
 	 * Some CPUs support hardware unaligned access
@@ -17,9 +19,13 @@ SYM_FUNC_START(memcpy)
 	ALTERNATIVE	"b __memcpy_generic", \
 			"b __memcpy_fast", CPU_FEATURE_UAL
 SYM_FUNC_END(memcpy)
-_ASM_NOKPROBE(memcpy)
+SYM_FUNC_ALIAS(__memcpy, memcpy)
 
 EXPORT_SYMBOL(memcpy)
+EXPORT_SYMBOL(__memcpy)
+
+_ASM_NOKPROBE(memcpy)
+_ASM_NOKPROBE(__memcpy)
 
 /*
  * void *__memcpy_generic(void *dst, const void *src, size_t n)
diff --git a/arch/loongarch/lib/memmove.S b/arch/loongarch/lib/memmove.S
index 7dc76d1484b6..82dae062fec8 100644
--- a/arch/loongarch/lib/memmove.S
+++ b/arch/loongarch/lib/memmove.S
@@ -10,23 +10,29 @@
 #include <asm/cpu.h>
 #include <asm/regdef.h>
 
+.section .noinstr.text, "ax"
+
 SYM_FUNC_START(memmove)
-	blt	a0, a1, memcpy	/* dst < src, memcpy */
-	blt	a1, a0, rmemcpy	/* src < dst, rmemcpy */
-	jr	ra		/* dst == src, return */
+	blt	a0, a1, __memcpy	/* dst < src, memcpy */
+	blt	a1, a0, __rmemcpy	/* src < dst, rmemcpy */
+	jr	ra			/* dst == src, return */
 SYM_FUNC_END(memmove)
-_ASM_NOKPROBE(memmove)
+SYM_FUNC_ALIAS(__memmove, memmove)
 
 EXPORT_SYMBOL(memmove)
+EXPORT_SYMBOL(__memmove)
 
-SYM_FUNC_START(rmemcpy)
+_ASM_NOKPROBE(memmove)
+_ASM_NOKPROBE(__memmove)
+
+SYM_FUNC_START(__rmemcpy)
 	/*
 	 * Some CPUs support hardware unaligned access
 	 */
 	ALTERNATIVE	"b __rmemcpy_generic", \
 			"b __rmemcpy_fast", CPU_FEATURE_UAL
-SYM_FUNC_END(rmemcpy)
-_ASM_NOKPROBE(rmemcpy)
+SYM_FUNC_END(__rmemcpy)
+_ASM_NOKPROBE(__rmemcpy)
 
 /*
  * void *__rmemcpy_generic(void *dst, const void *src, size_t n)
diff --git a/arch/loongarch/lib/memset.S b/arch/loongarch/lib/memset.S
index 3f20f7996e8e..06d3ca54cbfe 100644
--- a/arch/loongarch/lib/memset.S
+++ b/arch/loongarch/lib/memset.S
@@ -16,6 +16,8 @@
 	bstrins.d \r0, \r0, 63, 32
 .endm
 
+.section .noinstr.text, "ax"
+
 SYM_FUNC_START(memset)
 	/*
 	 * Some CPUs support hardware unaligned access
@@ -23,9 +25,13 @@ SYM_FUNC_START(memset)
 	ALTERNATIVE	"b __memset_generic", \
 			"b __memset_fast", CPU_FEATURE_UAL
 SYM_FUNC_END(memset)
-_ASM_NOKPROBE(memset)
+SYM_FUNC_ALIAS(__memset, memset)
 
 EXPORT_SYMBOL(memset)
+EXPORT_SYMBOL(__memset)
+
+_ASM_NOKPROBE(memset)
+_ASM_NOKPROBE(__memset)
 
 /*
  * void *__memset_generic(void *s, int c, size_t n)
diff --git a/arch/loongarch/mm/Makefile b/arch/loongarch/mm/Makefile
index 8ffc6383f836..e4d1e581dbae 100644
--- a/arch/loongarch/mm/Makefile
+++ b/arch/loongarch/mm/Makefile
@@ -7,3 +7,6 @@ obj-y				+= init.o cache.o tlb.o tlbex.o extable.o \
 				   fault.o ioremap.o maccess.o mmap.o pgtable.o page.o
 
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
+obj-$(CONFIG_KASAN)		+= kasan_init.o
+
+KASAN_SANITIZE_kasan_init.o     := n
diff --git a/arch/loongarch/mm/kasan_init.c b/arch/loongarch/mm/kasan_init.c
new file mode 100644
index 000000000000..da68bc1a4643
--- /dev/null
+++ b/arch/loongarch/mm/kasan_init.c
@@ -0,0 +1,243 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2023 Loongson Technology Corporation Limited
+ */
+#define pr_fmt(fmt) "kasan: " fmt
+#include <linux/kasan.h>
+#include <linux/memblock.h>
+#include <linux/sched/task.h>
+
+#include <asm/tlbflush.h>
+#include <asm/pgalloc.h>
+#include <asm-generic/sections.h>
+
+static pgd_t kasan_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
+
+#ifdef __PAGETABLE_PUD_FOLDED
+#define __p4d_none(early, p4d) (0)
+#else
+#define __p4d_none(early, p4d) (early ? (p4d_val(p4d) == 0) : \
+(__pa(p4d_val(p4d)) == (unsigned long)__pa(kasan_early_shadow_pud)))
+#endif
+
+#ifdef __PAGETABLE_PMD_FOLDED
+#define __pud_none(early, pud) (0)
+#else
+#define __pud_none(early, pud) (early ? (pud_val(pud) == 0) : \
+(__pa(pud_val(pud)) == (unsigned long)__pa(kasan_early_shadow_pmd)))
+#endif
+
+#define __pmd_none(early, pmd) (early ? (pmd_val(pmd) == 0) : \
+(__pa(pmd_val(pmd)) == (unsigned long)__pa(kasan_early_shadow_pte)))
+
+#define __pte_none(early, pte) (early ? pte_none(pte) : \
+((pte_val(pte) & _PFN_MASK) == (unsigned long)__pa(kasan_early_shadow_page)))
+
+bool kasan_early_stage = true;
+
+/*
+ * Alloc memory for shadow memory page table.
+ */
+static phys_addr_t __init kasan_alloc_zeroed_page(int node)
+{
+	void *p = memblock_alloc_try_nid(PAGE_SIZE, PAGE_SIZE,
+					__pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, node);
+	if (!p)
+		panic("%s: Failed to allocate %lu bytes align=0x%lx nid=%d from=%llx\n",
+			__func__, PAGE_SIZE, PAGE_SIZE, node, __pa(MAX_DMA_ADDRESS));
+
+	return __pa(p);
+}
+
+static pte_t *__init kasan_pte_offset(pmd_t *pmdp, unsigned long addr, int node, bool early)
+{
+	if (__pmd_none(early, READ_ONCE(*pmdp))) {
+		phys_addr_t pte_phys = early ?
+				__pa_symbol(kasan_early_shadow_pte) : kasan_alloc_zeroed_page(node);
+		if (!early)
+			memcpy(__va(pte_phys), kasan_early_shadow_pte, sizeof(kasan_early_shadow_pte));
+		pmd_populate_kernel(NULL, pmdp, (pte_t *)__va(pte_phys));
+	}
+
+	return pte_offset_kernel(pmdp, addr);
+}
+
+static pmd_t *__init kasan_pmd_offset(pud_t *pudp, unsigned long addr, int node, bool early)
+{
+	if (__pud_none(early, READ_ONCE(*pudp))) {
+		phys_addr_t pmd_phys = early ?
+				__pa_symbol(kasan_early_shadow_pmd) : kasan_alloc_zeroed_page(node);
+		if (!early)
+			memcpy(__va(pmd_phys), kasan_early_shadow_pmd, sizeof(kasan_early_shadow_pmd));
+		pud_populate(&init_mm, pudp, (pmd_t *)__va(pmd_phys));
+	}
+
+	return pmd_offset(pudp, addr);
+}
+
+static pud_t *__init kasan_pud_offset(p4d_t *p4dp, unsigned long addr, int node, bool early)
+{
+	if (__p4d_none(early, READ_ONCE(*p4dp))) {
+		phys_addr_t pud_phys = early ?
+			__pa_symbol(kasan_early_shadow_pud) : kasan_alloc_zeroed_page(node);
+		if (!early)
+			memcpy(__va(pud_phys), kasan_early_shadow_pud, sizeof(kasan_early_shadow_pud));
+		p4d_populate(&init_mm, p4dp, (pud_t *)__va(pud_phys));
+	}
+
+	return pud_offset(p4dp, addr);
+}
+
+static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr,
+				      unsigned long end, int node, bool early)
+{
+	unsigned long next;
+	pte_t *ptep = kasan_pte_offset(pmdp, addr, node, early);
+
+	do {
+		phys_addr_t page_phys = early ?
+					__pa_symbol(kasan_early_shadow_page)
+					      : kasan_alloc_zeroed_page(node);
+		next = addr + PAGE_SIZE;
+		set_pte(ptep, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL));
+	} while (ptep++, addr = next, addr != end && __pte_none(early, READ_ONCE(*ptep)));
+}
+
+static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr,
+				      unsigned long end, int node, bool early)
+{
+	unsigned long next;
+	pmd_t *pmdp = kasan_pmd_offset(pudp, addr, node, early);
+
+	do {
+		next = pmd_addr_end(addr, end);
+		kasan_pte_populate(pmdp, addr, next, node, early);
+	} while (pmdp++, addr = next, addr != end && __pmd_none(early, READ_ONCE(*pmdp)));
+}
+
+static void __init kasan_pud_populate(p4d_t *p4dp, unsigned long addr,
+					    unsigned long end, int node, bool early)
+{
+	unsigned long next;
+	pud_t *pudp = kasan_pud_offset(p4dp, addr, node, early);
+
+	do {
+		next = pud_addr_end(addr, end);
+		kasan_pmd_populate(pudp, addr, next, node, early);
+	} while (pudp++, addr = next, addr != end);
+}
+
+static void __init kasan_p4d_populate(pgd_t *pgdp, unsigned long addr,
+					    unsigned long end, int node, bool early)
+{
+	unsigned long next;
+	p4d_t *p4dp = p4d_offset(pgdp, addr);
+
+	do {
+		next = p4d_addr_end(addr, end);
+		kasan_pud_populate(p4dp, addr, next, node, early);
+	} while (p4dp++, addr = next, addr != end);
+}
+
+static void __init kasan_pgd_populate(unsigned long addr, unsigned long end,
+				      int node, bool early)
+{
+	unsigned long next;
+	pgd_t *pgdp;
+
+	pgdp = pgd_offset_k(addr);
+
+	do {
+		next = pgd_addr_end(addr, end);
+		kasan_p4d_populate(pgdp, addr, next, node, early);
+	} while (pgdp++, addr = next, addr != end);
+
+}
+
+/* Set up full kasan mappings, ensuring that the mapped pages are zeroed */
+static void __init kasan_map_populate(unsigned long start, unsigned long end,
+				      int node)
+{
+	kasan_pgd_populate(start & PAGE_MASK, PAGE_ALIGN(end), node, false);
+}
+
+asmlinkage void __init kasan_early_init(void)
+{
+	BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_START, PGDIR_SIZE));
+	BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, PGDIR_SIZE));
+}
+
+static inline void kasan_set_pgd(pgd_t *pgdp, pgd_t pgdval)
+{
+	WRITE_ONCE(*pgdp, pgdval);
+}
+
+static void __init clear_pgds(unsigned long start, unsigned long end)
+{
+	/*
+	 * Remove references to kasan page tables from
+	 * swapper_pg_dir. pgd_clear() can't be used
+	 * here because it's nop on 2,3-level pagetable setups
+	 */
+	for (; start < end; start += PGDIR_SIZE)
+		kasan_set_pgd((pgd_t *)pgd_offset_k(start), __pgd(0));
+}
+
+void __init kasan_init(void)
+{
+	u64 i;
+	phys_addr_t pa_start, pa_end;
+
+	/*
+	 * PGD was populated as invalid_pmd_table or invalid_pud_table
+	 * in pagetable_init() which depends on how many levels of page
+	 * table you are using, but we had to clean the gpd of kasan
+	 * shadow memory, as the pgd value is none-zero.
+	 * The assertion pgd_none is going to be false and the formal populate
+	 * afterwards is not going to create any new pgd at all.
+	 */
+	memcpy(kasan_pg_dir, swapper_pg_dir, sizeof(kasan_pg_dir));
+	csr_write64(__pa_symbol(kasan_pg_dir), LOONGARCH_CSR_PGDH);
+	local_flush_tlb_all();
+
+	clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END);
+
+	/* Maps everything to a single page of zeroes */
+	kasan_pgd_populate(KASAN_SHADOW_START, KASAN_SHADOW_END, NUMA_NO_NODE, true);
+
+	kasan_populate_early_shadow(kasan_mem_to_shadow((void *)VMALLOC_START),
+					kasan_mem_to_shadow((void *)KFENCE_AREA_END));
+
+	kasan_early_stage = false;
+
+	/* Populate the linear mapping */
+	for_each_mem_range(i, &pa_start, &pa_end) {
+		void *start = (void *)phys_to_virt(pa_start);
+		void *end   = (void *)phys_to_virt(pa_end);
+
+		if (start >= end)
+			break;
+
+		kasan_map_populate((unsigned long)kasan_mem_to_shadow(start),
+			(unsigned long)kasan_mem_to_shadow(end), NUMA_NO_NODE);
+	}
+
+	/* Populate modules mapping */
+	kasan_map_populate((unsigned long)kasan_mem_to_shadow((void *)MODULES_VADDR),
+		(unsigned long)kasan_mem_to_shadow((void *)MODULES_END), NUMA_NO_NODE);
+	/*
+	 * KAsan may reuse the contents of kasan_early_shadow_pte directly, so we
+	 * should make sure that it maps the zero page read-only.
+	 */
+	for (i = 0; i < PTRS_PER_PTE; i++)
+		set_pte(&kasan_early_shadow_pte[i],
+			pfn_pte(__phys_to_pfn(__pa_symbol(kasan_early_shadow_page)), PAGE_KERNEL_RO));
+
+	memset(kasan_early_shadow_page, 0, PAGE_SIZE);
+	csr_write64(__pa_symbol(swapper_pg_dir), LOONGARCH_CSR_PGDH);
+	local_flush_tlb_all();
+
+	/* At this point kasan is fully initialized. Enable error messages */
+	init_task.kasan_depth = 0;
+	pr_info("KernelAddressSanitizer initialized.\n");
+}
diff --git a/arch/loongarch/vdso/Makefile b/arch/loongarch/vdso/Makefile
index d8b75f07c869..5c97d1463328 100644
--- a/arch/loongarch/vdso/Makefile
+++ b/arch/loongarch/vdso/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 # Objects to go into the VDSO.
 
+KASAN_SANITIZE := n
 KCOV_INSTRUMENT := n
 
 # Include the generic Makefile to check the built vdso.

From 180b10bd160b014448366e5bc86e0558f8acb74f Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Fri, 1 Sep 2023 14:24:24 +0200
Subject: [PATCH 1134/1189] gpio: zynq: restore
 zynq_gpio_irq_reqres/zynq_gpio_irq_relres callbacks

Commit f56914393537 ("gpio: zynq: fix zynqmp_gpio not an immutable chip
warning") ditched the open-coded resource allocation handlers in favor
of the generic ones. These generic handlers don't maintain the PM
runtime anymore, which causes a regression in that level IRQs are no
longer reported.

Restore the original handlers to fix this.

Signed-off-by: Daniel Mack <daniel@zonque.org>
Fixes: f56914393537 ("gpio: zynq: fix zynqmp_gpio not an immutable chip warning")
Cc: stable@kernel.org
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpio-zynq.c | 26 ++++++++++++++++++++++++--
 1 file changed, 24 insertions(+), 2 deletions(-)

diff --git a/drivers/gpio/gpio-zynq.c b/drivers/gpio/gpio-zynq.c
index 0a7264aabe48..324e942c0650 100644
--- a/drivers/gpio/gpio-zynq.c
+++ b/drivers/gpio/gpio-zynq.c
@@ -575,6 +575,26 @@ static int zynq_gpio_set_wake(struct irq_data *data, unsigned int on)
 	return 0;
 }
 
+static int zynq_gpio_irq_reqres(struct irq_data *d)
+{
+	struct gpio_chip *chip = irq_data_get_irq_chip_data(d);
+	int ret;
+
+	ret = pm_runtime_resume_and_get(chip->parent);
+	if (ret < 0)
+		return ret;
+
+	return gpiochip_reqres_irq(chip, d->hwirq);
+}
+
+static void zynq_gpio_irq_relres(struct irq_data *d)
+{
+	struct gpio_chip *chip = irq_data_get_irq_chip_data(d);
+
+	gpiochip_relres_irq(chip, d->hwirq);
+	pm_runtime_put(chip->parent);
+}
+
 /* irq chip descriptor */
 static const struct irq_chip zynq_gpio_level_irqchip = {
 	.name		= DRIVER_NAME,
@@ -584,9 +604,10 @@ static const struct irq_chip zynq_gpio_level_irqchip = {
 	.irq_unmask	= zynq_gpio_irq_unmask,
 	.irq_set_type	= zynq_gpio_set_irq_type,
 	.irq_set_wake	= zynq_gpio_set_wake,
+	.irq_request_resources = zynq_gpio_irq_reqres,
+	.irq_release_resources = zynq_gpio_irq_relres,
 	.flags		= IRQCHIP_EOI_THREADED | IRQCHIP_EOI_IF_HANDLED |
 			  IRQCHIP_MASK_ON_SUSPEND | IRQCHIP_IMMUTABLE,
-	GPIOCHIP_IRQ_RESOURCE_HELPERS,
 };
 
 static const struct irq_chip zynq_gpio_edge_irqchip = {
@@ -597,8 +618,9 @@ static const struct irq_chip zynq_gpio_edge_irqchip = {
 	.irq_unmask	= zynq_gpio_irq_unmask,
 	.irq_set_type	= zynq_gpio_set_irq_type,
 	.irq_set_wake	= zynq_gpio_set_wake,
+	.irq_request_resources = zynq_gpio_irq_reqres,
+	.irq_release_resources = zynq_gpio_irq_relres,
 	.flags		= IRQCHIP_MASK_ON_SUSPEND | IRQCHIP_IMMUTABLE,
-	GPIOCHIP_IRQ_RESOURCE_HELPERS,
 };
 
 static void zynq_gpio_handle_bank_irq(struct zynq_gpio *gpio,

From fd94d9dadee58e09b49075240fe83423eb1dcd36 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 5 Sep 2023 23:13:56 +0200
Subject: [PATCH 1135/1189] netfilter: nftables: exthdr: fix 4-byte stack OOB
 write

If priv->len is a multiple of 4, then dst[len / 4] can write past
the destination array which leads to stack corruption.

This construct is necessary to clean the remainder of the register
in case ->len is NOT a multiple of the register size, so make it
conditional just like nft_payload.c does.

The bug was added in 4.1 cycle and then copied/inherited when
tcp/sctp and ip option support was added.

Bug reported by Zero Day Initiative project (ZDI-CAN-21950,
ZDI-CAN-21951, ZDI-CAN-21961).

Fixes: 49499c3e6e18 ("netfilter: nf_tables: switch registers to 32 bit addressing")
Fixes: 935b7f643018 ("netfilter: nft_exthdr: add TCP option matching")
Fixes: 133dc203d77d ("netfilter: nft_exthdr: Support SCTP chunks")
Fixes: dbb5281a1f84 ("netfilter: nf_tables: add support for matching IPv4 options")
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nft_exthdr.c | 22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index a9844eefedeb..3fbaa7bf41f9 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -35,6 +35,14 @@ static unsigned int optlen(const u8 *opt, unsigned int offset)
 		return opt[offset + 1];
 }
 
+static int nft_skb_copy_to_reg(const struct sk_buff *skb, int offset, u32 *dest, unsigned int len)
+{
+	if (len % NFT_REG32_SIZE)
+		dest[len / NFT_REG32_SIZE] = 0;
+
+	return skb_copy_bits(skb, offset, dest, len);
+}
+
 static void nft_exthdr_ipv6_eval(const struct nft_expr *expr,
 				 struct nft_regs *regs,
 				 const struct nft_pktinfo *pkt)
@@ -56,8 +64,7 @@ static void nft_exthdr_ipv6_eval(const struct nft_expr *expr,
 	}
 	offset += priv->offset;
 
-	dest[priv->len / NFT_REG32_SIZE] = 0;
-	if (skb_copy_bits(pkt->skb, offset, dest, priv->len) < 0)
+	if (nft_skb_copy_to_reg(pkt->skb, offset, dest, priv->len) < 0)
 		goto err;
 	return;
 err:
@@ -153,8 +160,7 @@ static void nft_exthdr_ipv4_eval(const struct nft_expr *expr,
 	}
 	offset += priv->offset;
 
-	dest[priv->len / NFT_REG32_SIZE] = 0;
-	if (skb_copy_bits(pkt->skb, offset, dest, priv->len) < 0)
+	if (nft_skb_copy_to_reg(pkt->skb, offset, dest, priv->len) < 0)
 		goto err;
 	return;
 err:
@@ -210,7 +216,8 @@ static void nft_exthdr_tcp_eval(const struct nft_expr *expr,
 		if (priv->flags & NFT_EXTHDR_F_PRESENT) {
 			*dest = 1;
 		} else {
-			dest[priv->len / NFT_REG32_SIZE] = 0;
+			if (priv->len % NFT_REG32_SIZE)
+				dest[priv->len / NFT_REG32_SIZE] = 0;
 			memcpy(dest, opt + offset, priv->len);
 		}
 
@@ -388,9 +395,8 @@ static void nft_exthdr_sctp_eval(const struct nft_expr *expr,
 			    offset + ntohs(sch->length) > pkt->skb->len)
 				break;
 
-			dest[priv->len / NFT_REG32_SIZE] = 0;
-			if (skb_copy_bits(pkt->skb, offset + priv->offset,
-					  dest, priv->len) < 0)
+			if (nft_skb_copy_to_reg(pkt->skb, offset + priv->offset,
+						dest, priv->len) < 0)
 				break;
 			return;
 		}

From f4f8a7803119005e87b716874bec07c751efafec Mon Sep 17 00:00:00 2001
From: Wander Lairson Costa <wander@redhat.com>
Date: Fri, 1 Sep 2023 10:50:20 -0300
Subject: [PATCH 1136/1189] netfilter: nfnetlink_osf: avoid OOB read

The opt_num field is controlled by user mode and is not currently
validated inside the kernel. An attacker can take advantage of this to
trigger an OOB read and potentially leak information.

BUG: KASAN: slab-out-of-bounds in nf_osf_match_one+0xbed/0xd10 net/netfilter/nfnetlink_osf.c:88
Read of size 2 at addr ffff88804bc64272 by task poc/6431

CPU: 1 PID: 6431 Comm: poc Not tainted 6.0.0-rc4 #1
Call Trace:
 nf_osf_match_one+0xbed/0xd10 net/netfilter/nfnetlink_osf.c:88
 nf_osf_find+0x186/0x2f0 net/netfilter/nfnetlink_osf.c:281
 nft_osf_eval+0x37f/0x590 net/netfilter/nft_osf.c:47
 expr_call_ops_eval net/netfilter/nf_tables_core.c:214
 nft_do_chain+0x2b0/0x1490 net/netfilter/nf_tables_core.c:264
 nft_do_chain_ipv4+0x17c/0x1f0 net/netfilter/nft_chain_filter.c:23
 [..]

Also add validation to genre, subtype and version fields.

Fixes: 11eeef41d5f6 ("netfilter: passive OS fingerprint xtables match")
Reported-by: Lucas Leong <wmliang@infosec.exchange>
Signed-off-by: Wander Lairson Costa <wander@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nfnetlink_osf.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c
index 8f1bfa6ccc2d..50723ba08289 100644
--- a/net/netfilter/nfnetlink_osf.c
+++ b/net/netfilter/nfnetlink_osf.c
@@ -315,6 +315,14 @@ static int nfnl_osf_add_callback(struct sk_buff *skb,
 
 	f = nla_data(osf_attrs[OSF_ATTR_FINGER]);
 
+	if (f->opt_num > ARRAY_SIZE(f->opt))
+		return -EINVAL;
+
+	if (!memchr(f->genre, 0, MAXGENRELEN) ||
+	    !memchr(f->subtype, 0, MAXGENRELEN) ||
+	    !memchr(f->version, 0, MAXGENRELEN))
+		return -EINVAL;
+
 	kf = kmalloc(sizeof(struct nf_osf_finger), GFP_KERNEL);
 	if (!kf)
 		return -ENOMEM;

From fdc04cc2d5fd0bb9c17f36d0a895cf3e151109e6 Mon Sep 17 00:00:00 2001
From: Phil Sutter <phil@nwl.cc>
Date: Fri, 1 Sep 2023 14:15:16 +0200
Subject: [PATCH 1137/1189] netfilter: nf_tables: uapi: Describe
 NFTA_RULE_CHAIN_ID

Add a brief description to the enum's comment.

Fixes: 837830a4b439 ("netfilter: nf_tables: add NFTA_RULE_CHAIN_ID attribute")
Signed-off-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 include/uapi/linux/netfilter/nf_tables.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 8466c2a9938f..ca30232b7bc8 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -263,6 +263,7 @@ enum nft_chain_attributes {
  * @NFTA_RULE_USERDATA: user data (NLA_BINARY, NFT_USERDATA_MAXLEN)
  * @NFTA_RULE_ID: uniquely identifies a rule in a transaction (NLA_U32)
  * @NFTA_RULE_POSITION_ID: transaction unique identifier of the previous rule (NLA_U32)
+ * @NFTA_RULE_CHAIN_ID: add the rule to chain by ID, alternative to @NFTA_RULE_CHAIN (NLA_U32)
  */
 enum nft_rule_attributes {
 	NFTA_RULE_UNSPEC,

From 2ee52ae94baabf7ee09cf2a8d854b990dac5d0e4 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 4 Sep 2023 02:14:36 +0200
Subject: [PATCH 1138/1189] netfilter: nft_set_rbtree: skip sync GC for new
 elements in this transaction

New elements in this transaction might expired before such transaction
ends. Skip sync GC for such elements otherwise commit path might walk
over an already released object. Once transaction is finished, async GC
will collect such expired element.

Fixes: f6c383b8c31a ("netfilter: nf_tables: adapt set backend to use GC transaction API")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nft_set_rbtree.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index c6435e709231..f250b5399344 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -312,6 +312,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 	struct nft_rbtree_elem *rbe, *rbe_le = NULL, *rbe_ge = NULL;
 	struct rb_node *node, *next, *parent, **p, *first = NULL;
 	struct nft_rbtree *priv = nft_set_priv(set);
+	u8 cur_genmask = nft_genmask_cur(net);
 	u8 genmask = nft_genmask_next(net);
 	int d, err;
 
@@ -357,8 +358,11 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 		if (!nft_set_elem_active(&rbe->ext, genmask))
 			continue;
 
-		/* perform garbage collection to avoid bogus overlap reports. */
-		if (nft_set_elem_expired(&rbe->ext)) {
+		/* perform garbage collection to avoid bogus overlap reports
+		 * but skip new elements in this transaction.
+		 */
+		if (nft_set_elem_expired(&rbe->ext) &&
+		    nft_set_elem_active(&rbe->ext, cur_genmask)) {
 			err = nft_rbtree_gc_elem(set, priv, rbe, genmask);
 			if (err < 0)
 				return err;

From 050d91c03b28ca479df13dfb02bcd2c60dd6a878 Mon Sep 17 00:00:00 2001
From: Kyle Zeng <zengyhkyle@gmail.com>
Date: Tue, 5 Sep 2023 15:04:09 -0700
Subject: [PATCH 1139/1189] netfilter: ipset: add the missing
 IP_SET_HASH_WITH_NET0 macro for ip_set_hash_netportnet.c

The missing IP_SET_HASH_WITH_NET0 macro in ip_set_hash_netportnet can
lead to the use of wrong `CIDR_POS(c)` for calculating array offsets,
which can lead to integer underflow. As a result, it leads to slab
out-of-bound access.
This patch adds back the IP_SET_HASH_WITH_NET0 macro to
ip_set_hash_netportnet to address the issue.

Fixes: 886503f34d63 ("netfilter: ipset: actually allow allowable CIDR 0 in hash:net,port,net")
Suggested-by: Jozsef Kadlecsik <kadlec@netfilter.org>
Signed-off-by: Kyle Zeng <zengyhkyle@gmail.com>
Acked-by: Jozsef Kadlecsik <kadlec@netfilter.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/ipset/ip_set_hash_netportnet.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c
index 005a7ce87217..bf4f91b78e1d 100644
--- a/net/netfilter/ipset/ip_set_hash_netportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netportnet.c
@@ -36,6 +36,7 @@ MODULE_ALIAS("ip_set_hash:net,port,net");
 #define IP_SET_HASH_WITH_PROTO
 #define IP_SET_HASH_WITH_NETS
 #define IPSET_NET_COUNT 2
+#define IP_SET_HASH_WITH_NET0
 
 /* IPv4 variant */
 

From 9b5ba5c9c5109bf89dc64a3f4734bd125d1ce52e Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 6 Sep 2023 11:42:02 +0200
Subject: [PATCH 1140/1189] netfilter: nf_tables: Unbreak audit log reset

Deliver audit log from __nf_tables_dump_rules(), table dereference at
the end of the table list loop might point to the list head, leading to
this crash.

[ 4137.407349] BUG: unable to handle page fault for address: 00000000001f3c50
[ 4137.407357] #PF: supervisor read access in kernel mode
[ 4137.407359] #PF: error_code(0x0000) - not-present page
[ 4137.407360] PGD 0 P4D 0
[ 4137.407363] Oops: 0000 [#1] PREEMPT SMP PTI
[ 4137.407365] CPU: 4 PID: 500177 Comm: nft Not tainted 6.5.0+ #277
[ 4137.407369] RIP: 0010:string+0x49/0xd0
[ 4137.407374] Code: ff 77 36 45 89 d1 31 f6 49 01 f9 66 45 85 d2 75 19 eb 1e 49 39 f8 76 02 88 07 48 83 c7 01 83 c6 01 48 83 c2 01 4c 39 cf 74 07 <0f> b6 02 84 c0 75 e2 4c 89 c2 e9 58 e5 ff ff 48 c7 c0 0e b2 ff 81
[ 4137.407377] RSP: 0018:ffff8881179737f0 EFLAGS: 00010286
[ 4137.407379] RAX: 00000000001f2c50 RBX: ffff888117973848 RCX: ffff0a00ffffff04
[ 4137.407380] RDX: 00000000001f3c50 RSI: 0000000000000000 RDI: 0000000000000000
[ 4137.407381] RBP: 0000000000000000 R08: 0000000000000000 R09: 00000000ffffffff
[ 4137.407383] R10: ffffffffffffffff R11: ffff88813584d200 R12: 0000000000000000
[ 4137.407384] R13: ffffffffa15cf709 R14: 0000000000000000 R15: ffffffffa15cf709
[ 4137.407385] FS:  00007fcfc18bb580(0000) GS:ffff88840e700000(0000) knlGS:0000000000000000
[ 4137.407387] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 4137.407388] CR2: 00000000001f3c50 CR3: 00000001055b2001 CR4: 00000000001706e0
[ 4137.407390] Call Trace:
[ 4137.407392]  <TASK>
[ 4137.407393]  ? __die+0x1b/0x60
[ 4137.407397]  ? page_fault_oops+0x6b/0xa0
[ 4137.407399]  ? exc_page_fault+0x60/0x120
[ 4137.407403]  ? asm_exc_page_fault+0x22/0x30
[ 4137.407408]  ? string+0x49/0xd0
[ 4137.407410]  vsnprintf+0x257/0x4f0
[ 4137.407414]  kvasprintf+0x3e/0xb0
[ 4137.407417]  kasprintf+0x3e/0x50
[ 4137.407419]  nf_tables_dump_rules+0x1c0/0x360 [nf_tables]
[ 4137.407439]  ? __alloc_skb+0xc3/0x170
[ 4137.407442]  netlink_dump+0x170/0x330
[ 4137.407447]  __netlink_dump_start+0x227/0x300
[ 4137.407449]  nf_tables_getrule+0x205/0x390 [nf_tables]

Deliver audit log only once at the end of the rule dump+reset for
consistency with the set dump+reset.

Ensure audit reset access to table under rcu read side lock. The table
list iteration holds rcu read lock side, but recent audit code
dereferences table object out of the rcu read lock side.

Fixes: ea078ae9108e ("netfilter: nf_tables: Audit log rule reset")
Fixes: 7e9be1124dbe ("netfilter: nf_tables: Audit log setelem reset")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Acked-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nf_tables_api.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 2c81cee858d6..e429ebba74b3 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -3480,6 +3480,10 @@ cont:
 cont_skip:
 		(*idx)++;
 	}
+
+	if (reset && *idx)
+		audit_log_rule_reset(table, cb->seq, *idx);
+
 	return 0;
 }
 
@@ -3540,9 +3544,6 @@ static int nf_tables_dump_rules(struct sk_buff *skb,
 done:
 	rcu_read_unlock();
 
-	if (reset && idx > cb->args[0])
-		audit_log_rule_reset(table, cb->seq, idx - cb->args[0]);
-
 	cb->args[0] = idx;
 	return skb->len;
 }
@@ -5760,8 +5761,6 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
 	if (!args.iter.err && args.iter.count == cb->args[0])
 		args.iter.err = nft_set_catchall_dump(net, skb, set,
 						      reset, cb->seq);
-	rcu_read_unlock();
-
 	nla_nest_end(skb, nest);
 	nlmsg_end(skb, nlh);
 
@@ -5769,6 +5768,8 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
 		audit_log_nft_set_reset(table, cb->seq,
 					args.iter.count - args.iter.skip);
 
+	rcu_read_unlock();
+
 	if (args.iter.err && args.iter.err != -EMSGSIZE)
 		return args.iter.err;
 	if (args.iter.count == cb->args[0])

From 8ec9c1d5d0a5a4744516adb483b97a238892f9d5 Mon Sep 17 00:00:00 2001
From: Ross Lagerwall <ross.lagerwall@citrix.com>
Date: Wed, 6 Sep 2023 12:08:46 +0100
Subject: [PATCH 1141/1189] PCI: Free released resource after coalescing

release_resource() doesn't actually free the resource or resource list
entry so free the resource list entry to avoid a leak.

Closes: https://lore.kernel.org/r/878r9sga1t.fsf@kernel.org/
Fixes: e54223275ba1 ("PCI: Release resource invalidated by coalescing")
Link: https://lore.kernel.org/r/20230906110846.225369-1-ross.lagerwall@citrix.com
Reported-by: Kalle Valo <kvalo@kernel.org>
Tested-by: Kalle Valo <kvalo@kernel.org>
Signed-off-by: Ross Lagerwall <ross.lagerwall@citrix.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: stable@vger.kernel.org      # v5.16+
---
 drivers/pci/probe.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index ab2a4a3a4c06..795534589b98 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -997,6 +997,7 @@ static int pci_register_host_bridge(struct pci_host_bridge *bridge)
 		res = window->res;
 		if (!res->flags && !res->start && !res->end) {
 			release_resource(res);
+			resource_list_destroy_entry(window);
 			continue;
 		}
 

From ab41a97474c00ceab1b8f44ac78a51079130466a Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Wed, 6 Sep 2023 19:15:37 +0100
Subject: [PATCH 1142/1189] arm64/sysreg: Fix broken strncpy() -> strscpy()
 conversion

Mostafa reports that commit d232606773a0 ("arm64/sysreg: refactor
deprecated strncpy") breaks our early command-line parsing because the
original code is working on space-delimited substrings rather than
NUL-terminated strings.

Rather than simply reverting the broken conversion patch, replace the
strscpy() with a simple memcpy() with an explicit NUL-termination of the
result.

Reported-by: Mostafa Saleh <smostafa@google.com>
Tested-by: Mostafa Saleh <smostafa@google.com>
Fixes: d232606773a0 ("arm64/sysreg: refactor deprecated strncpy")
Signed-off-by: Justin Stitt <justinstitt@google.com>
Link: https://lore.kernel.org/r/20230905-strncpy-arch-arm64-v4-1-bc4b14ddfaef@google.com
Link: https://lore.kernel.org/r/20230831162227.2307863-1-smostafa@google.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/idreg-override.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/kernel/idreg-override.c b/arch/arm64/kernel/idreg-override.c
index aee12c75b738..3addc09f8746 100644
--- a/arch/arm64/kernel/idreg-override.c
+++ b/arch/arm64/kernel/idreg-override.c
@@ -262,9 +262,9 @@ static __init void __parse_cmdline(const char *cmdline, bool parse_aliases)
 		if (!len)
 			return;
 
-		len = strscpy(buf, cmdline, ARRAY_SIZE(buf));
-		if (len == -E2BIG)
-			len = ARRAY_SIZE(buf) - 1;
+		len = min(len, ARRAY_SIZE(buf) - 1);
+		memcpy(buf, cmdline, len);
+		buf[len] = '\0';
 
 		if (strcmp(buf, "--") == 0)
 			return;

From cfff2a7794d23b03a3ddedd318bf1df1876c598f Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Wed, 6 Sep 2023 13:22:57 -0500
Subject: [PATCH 1143/1189] ASoC: amd: yc: Fix a non-functional mic on Lenovo
 82TL

Lenovo 82TL has DMIC connected like 82V2 does.  Also match
82TL.

Reported-by: wildjim@kiwinet.org
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217063
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/r/20230906182257.45736-1-mario.limonciello@amd.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/yc/acp6x-mach.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index 887188650bd6..965d222c2443 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -213,6 +213,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "21J6"),
 		}
 	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "82TL"),
+		}
+	},
 	{
 		.driver_data = &acp6x_card,
 		.matches = {

From 081690e941188acfad41b8dbde2112029a2aa206 Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Wed, 6 Sep 2023 12:08:16 -0700
Subject: [PATCH 1144/1189] powercap: intel_rapl: Fix invalid setting of Power
 Limit 4

System runs at minimum performance, once powercap RAPL package domain
enabled flag is changed from 1 to 0 to 1.

Setting RAPL package domain enabled flag to 0, results in setting of
power limit 4 (PL4) MSR 0x601 to 0. This implies disabling PL4 limit.
The PL4 limit controls the peak power. So setting 0, results in some
undesirable performance, which depends on hardware implementation.

Even worse, when the enabled flag is set to 1 again. This will set PL4
MSR value to 0x01, which means reduce peak power to 0.125W. This will
force system to run at the lowest possible performance on every PL4
supported system.

Setting enabled flag should only affect the "enable" bit, not other
bits. Here it is changing power limit.

This is caused by a change which assumes that there is an enable bit in
the PL4 MSR like other power limits. Although PL4 enable/disable bit is
present with TPMI RAPL interface, it is not present with the MSR
interface.

There is a rapl_primitive_info defined for non existent PL4 enable bit
and then it is used with the commit 9050a9cd5e4c ("powercap: intel_rapl:
Cleanup Power Limits support") to enable PL4. This is wrong, hence remove
this rapl primitive for PL4. Also in the function
rapl_detect_powerlimit(), PL_ENABLE is used to check for the presence of
power limits. Replace PL_ENABLE with PL_LIMIT, as PL_LIMIT must be
present. Without this change, PL4 controls will not be available in the
sysfs once rapl primitive for PL4 is removed.

Fixes: 9050a9cd5e4c ("powercap: intel_rapl: Cleanup Power Limits support")
Suggested-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Tested-by: Sumeet Pawnikar <sumeet.r.pawnikar@intel.com>
Cc: 6.5+ <stable@vger.kernel.org> # 6.5+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/powercap/intel_rapl_common.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c
index 5c2e6d5eea2a..40a2cc649c79 100644
--- a/drivers/powercap/intel_rapl_common.c
+++ b/drivers/powercap/intel_rapl_common.c
@@ -658,8 +658,6 @@ static struct rapl_primitive_info rpi_msr[NR_RAPL_PRIMITIVES] = {
 			    RAPL_DOMAIN_REG_LIMIT, ARBITRARY_UNIT, 0),
 	[PL2_CLAMP] = PRIMITIVE_INFO_INIT(PL2_CLAMP, POWER_LIMIT2_CLAMP, 48,
 			    RAPL_DOMAIN_REG_LIMIT, ARBITRARY_UNIT, 0),
-	[PL4_ENABLE] = PRIMITIVE_INFO_INIT(PL4_ENABLE, POWER_LIMIT4_MASK, 0,
-				RAPL_DOMAIN_REG_PL4, ARBITRARY_UNIT, 0),
 	[TIME_WINDOW1] = PRIMITIVE_INFO_INIT(TIME_WINDOW1, TIME_WINDOW1_MASK, 17,
 			    RAPL_DOMAIN_REG_LIMIT, TIME_UNIT, 0),
 	[TIME_WINDOW2] = PRIMITIVE_INFO_INIT(TIME_WINDOW2, TIME_WINDOW2_MASK, 49,
@@ -1458,7 +1456,7 @@ static void rapl_detect_powerlimit(struct rapl_domain *rd)
 			}
 		}
 
-		if (rapl_read_pl_data(rd, i, PL_ENABLE, false, &val64))
+		if (rapl_read_pl_data(rd, i, PL_LIMIT, false, &val64))
 			rd->rpl[i].name = NULL;
 	}
 }

From 65e710899fd19f435f40268f3a92dfaa11f14470 Mon Sep 17 00:00:00 2001
From: Song Liu <song@kernel.org>
Date: Wed, 6 Sep 2023 10:52:15 -0700
Subject: [PATCH 1145/1189] x86/build: Fix linker fill bytes
 quirk/incompatibility for ld.lld

With ":text =0xcccc", ld.lld fills unused text area with 0xcccc0000.
Example objdump -D output:

	ffffffff82b04203:       00 00                   add    %al,(%rax)
	ffffffff82b04205:       cc                      int3
	ffffffff82b04206:       cc                      int3
	ffffffff82b04207:       00 00                   add    %al,(%rax)
	ffffffff82b04209:       cc                      int3
	ffffffff82b0420a:       cc                      int3

Replace it with ":text =0xcccccccc", so we get the following instead:

	ffffffff82b04203:       cc                      int3
	ffffffff82b04204:       cc                      int3
	ffffffff82b04205:       cc                      int3
	ffffffff82b04206:       cc                      int3
	ffffffff82b04207:       cc                      int3
	ffffffff82b04208:       cc                      int3

gcc/ld doesn't seem to have the same issue. The generated code stays the
same for gcc/ld.

Signed-off-by: Song Liu <song@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Fixes: 7705dc855797 ("x86/vmlinux: Use INT3 instead of NOP for linker fill bytes")
Link: https://lore.kernel.org/r/20230906175215.2236033-1-song@kernel.org
---
 arch/x86/kernel/vmlinux.lds.S | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 83d41c2601d7..f15fb71f280e 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -156,7 +156,7 @@ SECTIONS
 		ALIGN_ENTRY_TEXT_END
 		*(.gnu.warning)
 
-	} :text =0xcccc
+	} :text = 0xcccccccc
 
 	/* End of text section, which should occupy whole number of pages */
 	_etext = .;

From 659df86a7b2fe98feb5f4ec880e694caaebd27ae Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Wed, 6 Sep 2023 18:26:58 +0200
Subject: [PATCH 1146/1189] x86: Remove the arch_calc_vm_prot_bits() macro from
 the UAPI

The arch_calc_vm_prot_bits() macro uses VM_PKEY_BIT0 etc. which are
not part of the UAPI, so the macro is completely useless for userspace.

It is also hidden behind the CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
config switch which we shouldn't expose to userspace. Thus let's move
this macro into a new internal header instead.

Fixes: 8f62c883222c ("x86/mm/pkeys: Add arch-specific VMA protection bits")
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Nicolas Schier <nicolas@fjasle.eu>
Acked-by: Dave Hansen <dave.hansen@intel.com>
Link: https://lore.kernel.org/r/20230906162658.142511-1-thuth@redhat.com
---
 arch/x86/include/asm/mman.h      | 15 +++++++++++++++
 arch/x86/include/uapi/asm/mman.h |  8 --------
 scripts/headers_install.sh       |  1 -
 3 files changed, 15 insertions(+), 9 deletions(-)
 create mode 100644 arch/x86/include/asm/mman.h

diff --git a/arch/x86/include/asm/mman.h b/arch/x86/include/asm/mman.h
new file mode 100644
index 000000000000..12b820259b9f
--- /dev/null
+++ b/arch/x86/include/asm/mman.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_MMAN_H__
+#define __ASM_MMAN_H__
+
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+#define arch_calc_vm_prot_bits(prot, key) (		\
+		((key) & 0x1 ? VM_PKEY_BIT0 : 0) |      \
+		((key) & 0x2 ? VM_PKEY_BIT1 : 0) |      \
+		((key) & 0x4 ? VM_PKEY_BIT2 : 0) |      \
+		((key) & 0x8 ? VM_PKEY_BIT3 : 0))
+#endif
+
+#include <uapi/asm/mman.h>
+
+#endif /* __ASM_MMAN_H__ */
diff --git a/arch/x86/include/uapi/asm/mman.h b/arch/x86/include/uapi/asm/mman.h
index 8148bdddbd2c..46cdc941f958 100644
--- a/arch/x86/include/uapi/asm/mman.h
+++ b/arch/x86/include/uapi/asm/mman.h
@@ -5,14 +5,6 @@
 #define MAP_32BIT	0x40		/* only give out 32bit addresses */
 #define MAP_ABOVE4G	0x80		/* only map above 4GB */
 
-#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
-#define arch_calc_vm_prot_bits(prot, key) (		\
-		((key) & 0x1 ? VM_PKEY_BIT0 : 0) |      \
-		((key) & 0x2 ? VM_PKEY_BIT1 : 0) |      \
-		((key) & 0x4 ? VM_PKEY_BIT2 : 0) |      \
-		((key) & 0x8 ? VM_PKEY_BIT3 : 0))
-#endif
-
 /* Flags for map_shadow_stack(2) */
 #define SHADOW_STACK_SET_TOKEN	(1ULL << 0)	/* Set up a restore token in the shadow stack */
 
diff --git a/scripts/headers_install.sh b/scripts/headers_install.sh
index afdddc82f02b..56d3c338d91d 100755
--- a/scripts/headers_install.sh
+++ b/scripts/headers_install.sh
@@ -81,7 +81,6 @@ arch/nios2/include/uapi/asm/swab.h:CONFIG_NIOS2_CI_SWAB_NO
 arch/nios2/include/uapi/asm/swab.h:CONFIG_NIOS2_CI_SWAB_SUPPORT
 arch/x86/include/uapi/asm/auxvec.h:CONFIG_IA32_EMULATION
 arch/x86/include/uapi/asm/auxvec.h:CONFIG_X86_64
-arch/x86/include/uapi/asm/mman.h:CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
 "
 
 for c in $configs

From 3d7d72a34e05b23e21bafc8bfb861e73c86b31f3 Mon Sep 17 00:00:00 2001
From: Jack Wang <jinpu.wang@ionos.com>
Date: Wed, 6 Sep 2023 15:17:12 +0200
Subject: [PATCH 1147/1189] x86/sgx: Break up long non-preemptible delays in
 sgx_vepc_release()

On large enclaves we hit the softlockup warning with following call trace:

	xa_erase()
	sgx_vepc_release()
	__fput()
	task_work_run()
	do_exit()

The latency issue is similar to the one fixed in:

  8795359e35bc ("x86/sgx: Silence softlockup detection when releasing large enclaves")

The test system has 64GB of enclave memory, and all is assigned to a single VM.
Release of 'vepc' takes a longer time and causes long latencies, which triggers
the softlockup warning.

Add cond_resched() to give other tasks a chance to run and reduce
latencies, which also avoids the softlockup detector.

[ mingo: Rewrote the changelog. ]

Fixes: 540745ddbc70 ("x86/sgx: Introduce virtual EPC for use by KVM guests")
Reported-by: Yu Zhang <yu.zhang@ionos.com>
Signed-off-by: Jack Wang <jinpu.wang@ionos.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Yu Zhang <yu.zhang@ionos.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Reviewed-by: Kai Huang <kai.huang@intel.com>
Acked-by: Haitao Huang <haitao.huang@linux.intel.com>
Cc: stable@vger.kernel.org
---
 arch/x86/kernel/cpu/sgx/virt.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/x86/kernel/cpu/sgx/virt.c b/arch/x86/kernel/cpu/sgx/virt.c
index c3e37eaec8ec..7aaa3652e31d 100644
--- a/arch/x86/kernel/cpu/sgx/virt.c
+++ b/arch/x86/kernel/cpu/sgx/virt.c
@@ -204,6 +204,7 @@ static int sgx_vepc_release(struct inode *inode, struct file *file)
 			continue;
 
 		xa_erase(&vepc->page_array, index);
+		cond_resched();
 	}
 
 	/*
@@ -222,6 +223,7 @@ static int sgx_vepc_release(struct inode *inode, struct file *file)
 			list_add_tail(&epc_page->list, &secs_pages);
 
 		xa_erase(&vepc->page_array, index);
+		cond_resched();
 	}
 
 	/*
@@ -243,6 +245,7 @@ static int sgx_vepc_release(struct inode *inode, struct file *file)
 
 		if (sgx_vepc_free_page(epc_page))
 			list_add_tail(&epc_page->list, &secs_pages);
+		cond_resched();
 	}
 
 	if (!list_empty(&secs_pages))

From a81de4a22bbe3183b7f0d6f13f592b8f5b5a3c18 Mon Sep 17 00:00:00 2001
From: Hamza Mahfooz <hamza.mahfooz@amd.com>
Date: Thu, 31 Aug 2023 15:17:14 -0400
Subject: [PATCH 1148/1189] Revert "drm/amd/display: Remove v_startup
 workaround for dcn3+"

This reverts commit 3a31e8b89b7240d9a17ace8a1ed050bdcb560f9e.

We still need to call dcn20_adjust_freesync_v_startup() for older DCN3+
ASICs. Otherwise, it can cause DP to HDMI 2.1 PCONs to fail to light up.

Cc: stable@vger.kernel.org
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2809
Reviewed-by: Fangzhi Zuo <jerry.zuo@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/dc/dml/dcn20/dcn20_fpu.c  | 24 ++++---------------
 1 file changed, 4 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
index 8afda5ecc0cd..d01bc2dff49b 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
@@ -1099,6 +1099,10 @@ void dcn20_calculate_dlg_params(struct dc *dc,
 		context->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz =
 						pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000;
 		context->res_ctx.pipe_ctx[i].pipe_dlg_param = pipes[pipe_idx].pipe.dest;
+		if (context->res_ctx.pipe_ctx[i].stream->adaptive_sync_infopacket.valid)
+			dcn20_adjust_freesync_v_startup(
+				&context->res_ctx.pipe_ctx[i].stream->timing,
+				&context->res_ctx.pipe_ctx[i].pipe_dlg_param.vstartup_start);
 
 		pipe_idx++;
 	}
@@ -1927,7 +1931,6 @@ static bool dcn20_validate_bandwidth_internal(struct dc *dc, struct dc_state *co
 	int vlevel = 0;
 	int pipe_split_from[MAX_PIPES];
 	int pipe_cnt = 0;
-	int i = 0;
 	display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_ATOMIC);
 	DC_LOGGER_INIT(dc->ctx->logger);
 
@@ -1951,15 +1954,6 @@ static bool dcn20_validate_bandwidth_internal(struct dc *dc, struct dc_state *co
 	dcn20_calculate_wm(dc, context, pipes, &pipe_cnt, pipe_split_from, vlevel, fast_validate);
 	dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel);
 
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		if (!context->res_ctx.pipe_ctx[i].stream)
-			continue;
-		if (context->res_ctx.pipe_ctx[i].stream->adaptive_sync_infopacket.valid)
-			dcn20_adjust_freesync_v_startup(
-				&context->res_ctx.pipe_ctx[i].stream->timing,
-				&context->res_ctx.pipe_ctx[i].pipe_dlg_param.vstartup_start);
-	}
-
 	BW_VAL_TRACE_END_WATERMARKS();
 
 	goto validate_out;
@@ -2232,7 +2226,6 @@ bool dcn21_validate_bandwidth_fp(struct dc *dc,
 	int vlevel = 0;
 	int pipe_split_from[MAX_PIPES];
 	int pipe_cnt = 0;
-	int i = 0;
 	display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_ATOMIC);
 	DC_LOGGER_INIT(dc->ctx->logger);
 
@@ -2261,15 +2254,6 @@ bool dcn21_validate_bandwidth_fp(struct dc *dc,
 	dcn21_calculate_wm(dc, context, pipes, &pipe_cnt, pipe_split_from, vlevel, fast_validate);
 	dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel);
 
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		if (!context->res_ctx.pipe_ctx[i].stream)
-			continue;
-		if (context->res_ctx.pipe_ctx[i].stream->adaptive_sync_infopacket.valid)
-			dcn20_adjust_freesync_v_startup(
-				&context->res_ctx.pipe_ctx[i].stream->timing,
-				&context->res_ctx.pipe_ctx[i].pipe_dlg_param.vstartup_start);
-	}
-
 	BW_VAL_TRACE_END_WATERMARKS();
 
 	goto validate_out;

From 47428f4b638d3b3264a2efa1a567b0bbddbb6107 Mon Sep 17 00:00:00 2001
From: Hamza Mahfooz <hamza.mahfooz@amd.com>
Date: Thu, 31 Aug 2023 15:22:35 -0400
Subject: [PATCH 1149/1189] drm/amd/display: limit the v_startup workaround to
 ASICs older than DCN3.1

Since, calling dcn20_adjust_freesync_v_startup() on DCN3.1+ ASICs
can cause the display to flicker and underflow to occur, we shouldn't
call it for them. So, ensure that the DCN version is less than
DCN_VERSION_3_1 before calling dcn20_adjust_freesync_v_startup().

Cc: stable@vger.kernel.org
Reviewed-by: Fangzhi Zuo <jerry.zuo@amd.com>
Signed-off-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
index d01bc2dff49b..5805fb02af14 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
@@ -1099,7 +1099,8 @@ void dcn20_calculate_dlg_params(struct dc *dc,
 		context->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz =
 						pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000;
 		context->res_ctx.pipe_ctx[i].pipe_dlg_param = pipes[pipe_idx].pipe.dest;
-		if (context->res_ctx.pipe_ctx[i].stream->adaptive_sync_infopacket.valid)
+		if (dc->ctx->dce_version < DCN_VERSION_3_1 &&
+		    context->res_ctx.pipe_ctx[i].stream->adaptive_sync_infopacket.valid)
 			dcn20_adjust_freesync_v_startup(
 				&context->res_ctx.pipe_ctx[i].stream->timing,
 				&context->res_ctx.pipe_ctx[i].pipe_dlg_param.vstartup_start);

From 57a943ebfcdb4a97fbb409640234bdb44bfa1953 Mon Sep 17 00:00:00 2001
From: Melissa Wen <mwen@igalia.com>
Date: Thu, 31 Aug 2023 15:12:28 -0100
Subject: [PATCH 1150/1189] drm/amd/display: enable cursor degamma for DCN3+
 DRM legacy gamma

For DRM legacy gamma, AMD display manager applies implicit sRGB degamma
using a pre-defined sRGB transfer function. It works fine for DCN2
family where degamma ROM and custom curves go to the same color block.
But, on DCN3+, degamma is split into two blocks: degamma ROM for
pre-defined TFs and `gamma correction` for user/custom curves and
degamma ROM settings doesn't apply to cursor plane. To get DRM legacy
gamma working as expected, enable cursor degamma ROM for implict sRGB
degamma on HW with this configuration.

Cc: stable@vger.kernel.org
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2803
Fixes: 96b020e2163f ("drm/amd/display: check attr flag before set cursor degamma on DCN3+")
Signed-off-by: Melissa Wen <mwen@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
index 2198df96ed6f..cc74dd69acf2 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
@@ -1269,6 +1269,13 @@ void amdgpu_dm_plane_handle_cursor_update(struct drm_plane *plane,
 	attributes.rotation_angle    = 0;
 	attributes.attribute_flags.value = 0;
 
+	/* Enable cursor degamma ROM on DCN3+ for implicit sRGB degamma in DRM
+	 * legacy gamma setup.
+	 */
+	if (crtc_state->cm_is_degamma_srgb &&
+	    adev->dm.dc->caps.color.dpp.gamma_corr)
+		attributes.attribute_flags.bits.ENABLE_CURSOR_DEGAMMA = 1;
+
 	attributes.pitch = afb->base.pitches[0] / afb->base.format->cpp[0];
 
 	if (crtc_state->stream) {

From 07e388aab042774f284a2ad75a70a194517cdad4 Mon Sep 17 00:00:00 2001
From: Hamza Mahfooz <hamza.mahfooz@amd.com>
Date: Tue, 5 Sep 2023 13:27:22 -0400
Subject: [PATCH 1151/1189] drm/amd/display: prevent potential division by zero
 errors

There are two places in apply_below_the_range() where it's possible for
a divide by zero error to occur. So, to fix this make sure the divisor
is non-zero before attempting the computation in both cases.

Cc: stable@vger.kernel.org
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2637
Fixes: a463b263032f ("drm/amd/display: Fix frames_to_insert math")
Fixes: ded6119e825a ("drm/amd/display: Reinstate LFC optimization")
Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/modules/freesync/freesync.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
index dbd60811f95d..ef3a67409021 100644
--- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
+++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
@@ -338,7 +338,9 @@ static void apply_below_the_range(struct core_freesync *core_freesync,
 		 *  - Delta for CEIL: delta_from_mid_point_in_us_1
 		 *  - Delta for FLOOR: delta_from_mid_point_in_us_2
 		 */
-		if ((last_render_time_in_us / mid_point_frames_ceil) < in_out_vrr->min_duration_in_us) {
+		if (mid_point_frames_ceil &&
+		    (last_render_time_in_us / mid_point_frames_ceil) <
+		    in_out_vrr->min_duration_in_us) {
 			/* Check for out of range.
 			 * If using CEIL produces a value that is out of range,
 			 * then we are forced to use FLOOR.
@@ -385,8 +387,9 @@ static void apply_below_the_range(struct core_freesync *core_freesync,
 		/* Either we've calculated the number of frames to insert,
 		 * or we need to insert min duration frames
 		 */
-		if (last_render_time_in_us / frames_to_insert <
-				in_out_vrr->min_duration_in_us){
+		if (frames_to_insert &&
+		    (last_render_time_in_us / frames_to_insert) <
+		    in_out_vrr->min_duration_in_us){
 			frames_to_insert -= (frames_to_insert > 1) ?
 					1 : 0;
 		}

From fbe1a9e0c78134db7e7f48322ab7d6a0530f2ee2 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Mon, 4 Sep 2023 18:15:13 +0530
Subject: [PATCH 1152/1189] drm/amdgpu: Restrict bootloader wait to SMUv13.0.6

Restrict the wait for boot loader steady state only to SMUv13.0.6. For
older SOCs, ASIC init has a longer wait period and that takes care.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/psp_v13_0.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
index d2a88bc630d2..469eed084976 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
@@ -160,9 +160,6 @@ static int psp_v13_0_wait_for_bootloader(struct psp_context *psp)
 	struct amdgpu_device *adev = psp->adev;
 	int retry_loop, ret;
 
-	if (adev->ip_versions[MP0_HWIP][0] == IP_VERSION(13, 0, 6))
-		psp_v13_0_wait_for_vmbx_ready(psp);
-
 	/* Wait for bootloader to signify that it is ready having bit 31 of
 	 * C2PMSG_35 set to 1. All other bits are expected to be cleared.
 	 * If there is an error in processing command, bits[7:0] will be set.
@@ -180,6 +177,19 @@ static int psp_v13_0_wait_for_bootloader(struct psp_context *psp)
 	return ret;
 }
 
+static int psp_v13_0_wait_for_bootloader_steady_state(struct psp_context *psp)
+{
+	struct amdgpu_device *adev = psp->adev;
+
+	if (adev->ip_versions[MP0_HWIP][0] == IP_VERSION(13, 0, 6)) {
+		psp_v13_0_wait_for_vmbx_ready(psp);
+
+		return psp_v13_0_wait_for_bootloader(psp);
+	}
+
+	return 0;
+}
+
 static int psp_v13_0_bootloader_load_component(struct psp_context  	*psp,
 					       struct psp_bin_desc 	*bin_desc,
 					       enum psp_bootloader_cmd  bl_cmd)
@@ -737,7 +747,7 @@ static int psp_v13_0_fatal_error_recovery_quirk(struct psp_context *psp)
 
 static const struct psp_funcs psp_v13_0_funcs = {
 	.init_microcode = psp_v13_0_init_microcode,
-	.wait_for_bootloader = psp_v13_0_wait_for_bootloader,
+	.wait_for_bootloader = psp_v13_0_wait_for_bootloader_steady_state,
 	.bootloader_load_kdb = psp_v13_0_bootloader_load_kdb,
 	.bootloader_load_spl = psp_v13_0_bootloader_load_spl,
 	.bootloader_load_sysdrv = psp_v13_0_bootloader_load_sysdrv,

From 08c6d8bae48c2c28f7017d7b61b5d5a1518ceb39 Mon Sep 17 00:00:00 2001
From: Lukasz Majewski <lukma@denx.de>
Date: Tue, 5 Sep 2023 11:33:15 +0200
Subject: [PATCH 1153/1189] net: phy: Provide Module 4 KSZ9477 errata
 (DS80000754C)

The KSZ9477 errata points out (in 'Module 4') the link up/down problems
when EEE (Energy Efficient Ethernet) is enabled in the device to which
the KSZ9477 tries to auto negotiate.

The suggested workaround is to clear advertisement of EEE for PHYs in
this chip driver.

To avoid regressions with other switch ICs the new MICREL_NO_EEE flag
has been introduced.

Moreover, the in-register disablement of MMD_DEVICE_ID_EEE_ADV.MMD_EEE_ADV
MMD register is removed, as this code is both; now executed too late
(after previous rework of the PHY and DSA for KSZ switches) and not
required as setting all members of eee_broken_modes bit field prevents
the KSZ9477 from advertising EEE.

Fixes: 69d3b36ca045 ("net: dsa: microchip: enable EEE support") # for KSZ9477
Signed-off-by: Lukasz Majewski <lukma@denx.de>
Tested-by: Oleksij Rempel <o.rempel@pengutronix.de> # Confirmed disabled EEE with oscilloscope.
Reviewed-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://lore.kernel.org/r/20230905093315.784052-1-lukma@denx.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/microchip/ksz_common.c | 16 +++++++++++++++-
 drivers/net/phy/micrel.c               |  9 ++++++---
 include/linux/micrel_phy.h             |  1 +
 3 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index 6673122266b7..42db7679c360 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -2335,13 +2335,27 @@ static u32 ksz_get_phy_flags(struct dsa_switch *ds, int port)
 {
 	struct ksz_device *dev = ds->priv;
 
-	if (dev->chip_id == KSZ8830_CHIP_ID) {
+	switch (dev->chip_id) {
+	case KSZ8830_CHIP_ID:
 		/* Silicon Errata Sheet (DS80000830A):
 		 * Port 1 does not work with LinkMD Cable-Testing.
 		 * Port 1 does not respond to received PAUSE control frames.
 		 */
 		if (!port)
 			return MICREL_KSZ8_P1_ERRATA;
+		break;
+	case KSZ9477_CHIP_ID:
+		/* KSZ9477 Errata DS80000754C
+		 *
+		 * Module 4: Energy Efficient Ethernet (EEE) feature select must
+		 * be manually disabled
+		 *   The EEE feature is enabled by default, but it is not fully
+		 *   operational. It must be manually disabled through register
+		 *   controls. If not disabled, the PHY ports can auto-negotiate
+		 *   to enable EEE, and this feature can cause link drops when
+		 *   linked to another device supporting EEE.
+		 */
+		return MICREL_NO_EEE;
 	}
 
 	return 0;
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index b6d7981b2d1e..927d3d54658e 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -1800,9 +1800,6 @@ static const struct ksz9477_errata_write ksz9477_errata_writes[] = {
 	/* Transmit waveform amplitude can be improved (1000BASE-T, 100BASE-TX, 10BASE-Te) */
 	{0x1c, 0x04, 0x00d0},
 
-	/* Energy Efficient Ethernet (EEE) feature select must be manually disabled */
-	{0x07, 0x3c, 0x0000},
-
 	/* Register settings are required to meet data sheet supply current specifications */
 	{0x1c, 0x13, 0x6eff},
 	{0x1c, 0x14, 0xe6ff},
@@ -1847,6 +1844,12 @@ static int ksz9477_config_init(struct phy_device *phydev)
 			return err;
 	}
 
+	/* According to KSZ9477 Errata DS80000754C (Module 4) all EEE modes
+	 * in this switch shall be regarded as broken.
+	 */
+	if (phydev->dev_flags & MICREL_NO_EEE)
+		phydev->eee_broken_modes = -1;
+
 	err = genphy_restart_aneg(phydev);
 	if (err)
 		return err;
diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h
index 322d87255984..4e27ca7c49de 100644
--- a/include/linux/micrel_phy.h
+++ b/include/linux/micrel_phy.h
@@ -44,6 +44,7 @@
 #define MICREL_PHY_50MHZ_CLK	BIT(0)
 #define MICREL_PHY_FXEN		BIT(1)
 #define MICREL_KSZ8_P1_ERRATA	BIT(2)
+#define MICREL_NO_EEE		BIT(3)
 
 #define MICREL_KSZ9021_EXTREG_CTRL	0xB
 #define MICREL_KSZ9021_EXTREG_DATA_WRITE	0xC

From 671eae93ae2090d2df01d810d354cab05f6bed8b Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Thu, 7 Sep 2023 12:06:20 +0800
Subject: [PATCH 1154/1189] LoongArch: Update Loongson-3 default config file

1, Enable LSX and LASX.
2, Enable KASLR (CONFIG_RANDOMIZE_BASE).
3, Enable jump label (patching mechanism for static key).
4, Enable LoongArch CRC32(c) Acceleration.
5, Enable Loongson-specific drivers: I2C/RTC/DRM/SOC/CLK/PINCTRL/GPIO/SPI.
6, Enable EXFAT/NTFS3/JFS/GFS2/OCFS2/UBIFS/EROFS/CEPH file systems.
7, Enable WangXun NGBE/TXGBE NIC drivers.
8, Enable some IPVS options.
9, Remove CONFIG_SYSFS_DEPRECATED since it is removed in Kconfig.
10, Remove CONFIG_IP_NF_TARGET_CLUSTERIP since it is removed in Kconfig.
11, Remove CONFIG_NFT_OBJREF since it is removed in Kconfig.
12, Remove CONFIG_R8188EU since it is replaced by CONFIG_RTL8XXXU.

Signed-off-by: Trevor Woerner <twoerner@gmail.com>
Signed-off-by: Xuewen Wang <wangxuewen@kylinos.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/configs/loongson3_defconfig | 74 ++++++++++++++++++++--
 1 file changed, 70 insertions(+), 4 deletions(-)

diff --git a/arch/loongarch/configs/loongson3_defconfig b/arch/loongarch/configs/loongson3_defconfig
index d64849b4cba1..a3b52aaa83b3 100644
--- a/arch/loongarch/configs/loongson3_defconfig
+++ b/arch/loongarch/configs/loongson3_defconfig
@@ -30,7 +30,6 @@ CONFIG_NAMESPACES=y
 CONFIG_USER_NS=y
 CONFIG_CHECKPOINT_RESTORE=y
 CONFIG_SCHED_AUTOGROUP=y
-CONFIG_SYSFS_DEPRECATED=y
 CONFIG_RELAY=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
@@ -47,8 +46,12 @@ CONFIG_SMP=y
 CONFIG_HOTPLUG_CPU=y
 CONFIG_NR_CPUS=64
 CONFIG_NUMA=y
+CONFIG_CPU_HAS_FPU=y
+CONFIG_CPU_HAS_LSX=y
+CONFIG_CPU_HAS_LASX=y
 CONFIG_KEXEC=y
 CONFIG_CRASH_DUMP=y
+CONFIG_RANDOMIZE_BASE=y
 CONFIG_SUSPEND=y
 CONFIG_HIBERNATION=y
 CONFIG_ACPI=y
@@ -63,6 +66,7 @@ CONFIG_EFI_ZBOOT=y
 CONFIG_EFI_GENERIC_STUB_INITRD_CMDLINE_LOADER=y
 CONFIG_EFI_CAPSULE_LOADER=m
 CONFIG_EFI_TEST=m
+CONFIG_JUMP_LABEL=y
 CONFIG_MODULES=y
 CONFIG_MODULE_FORCE_LOAD=y
 CONFIG_MODULE_UNLOAD=y
@@ -108,7 +112,12 @@ CONFIG_IP_PNP_BOOTP=y
 CONFIG_IP_PNP_RARP=y
 CONFIG_NET_IPIP=m
 CONFIG_NET_IPGRE_DEMUX=m
+CONFIG_NET_IPGRE=m
+CONFIG_NET_IPGRE_BROADCAST=y
 CONFIG_IP_MROUTE=y
+CONFIG_IP_MROUTE_MULTIPLE_TABLES=y
+CONFIG_IP_PIMSM_V1=y
+CONFIG_IP_PIMSM_V2=y
 CONFIG_INET_ESP=m
 CONFIG_INET_UDP_DIAG=y
 CONFIG_TCP_CONG_ADVANCED=y
@@ -137,7 +146,6 @@ CONFIG_NFT_MASQ=m
 CONFIG_NFT_REDIR=m
 CONFIG_NFT_NAT=m
 CONFIG_NFT_TUNNEL=m
-CONFIG_NFT_OBJREF=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_QUOTA=m
 CONFIG_NFT_REJECT=m
@@ -208,7 +216,11 @@ CONFIG_IP_VS=m
 CONFIG_IP_VS_IPV6=y
 CONFIG_IP_VS_PROTO_TCP=y
 CONFIG_IP_VS_PROTO_UDP=y
+CONFIG_IP_VS_PROTO_ESP=y
+CONFIG_IP_VS_PROTO_AH=y
+CONFIG_IP_VS_PROTO_SCTP=y
 CONFIG_IP_VS_RR=m
+CONFIG_IP_VS_WRR=m
 CONFIG_IP_VS_NFCT=y
 CONFIG_NF_TABLES_IPV4=y
 CONFIG_NFT_DUP_IPV4=m
@@ -227,7 +239,6 @@ CONFIG_IP_NF_TARGET_MASQUERADE=m
 CONFIG_IP_NF_TARGET_NETMAP=m
 CONFIG_IP_NF_TARGET_REDIRECT=m
 CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_CLUSTERIP=m
 CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IP_NF_RAW=m
@@ -363,6 +374,8 @@ CONFIG_MTD_CFI_AMDSTD=m
 CONFIG_MTD_CFI_STAA=m
 CONFIG_MTD_RAM=m
 CONFIG_MTD_ROM=m
+CONFIG_MTD_UBI=m
+CONFIG_MTD_UBI_BLOCK=y
 CONFIG_PARPORT=y
 CONFIG_PARPORT_PC=y
 CONFIG_PARPORT_SERIAL=y
@@ -370,6 +383,7 @@ CONFIG_PARPORT_PC_FIFO=y
 CONFIG_ZRAM=m
 CONFIG_ZRAM_DEF_COMP_ZSTD=y
 CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=8192
@@ -516,6 +530,8 @@ CONFIG_STMMAC_ETH=y
 # CONFIG_NET_VENDOR_TEHUTI is not set
 # CONFIG_NET_VENDOR_TI is not set
 # CONFIG_NET_VENDOR_VIA is not set
+CONFIG_NGBE=y
+CONFIG_TXGBE=y
 # CONFIG_NET_VENDOR_WIZNET is not set
 # CONFIG_NET_VENDOR_XILINX is not set
 CONFIG_PPP=m
@@ -602,9 +618,15 @@ CONFIG_HW_RANDOM_VIRTIO=m
 CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_PIIX4=y
 CONFIG_I2C_GPIO=y
+CONFIG_I2C_LS2X=y
 CONFIG_SPI=y
+CONFIG_SPI_LOONGSON_PCI=m
+CONFIG_SPI_LOONGSON_PLATFORM=m
+CONFIG_PINCTRL=y
+CONFIG_PINCTRL_LOONGSON2=y
 CONFIG_GPIO_SYSFS=y
 CONFIG_GPIO_LOONGSON=y
+CONFIG_GPIO_LOONGSON_64BIT=y
 CONFIG_POWER_RESET=y
 CONFIG_POWER_RESET_RESTART=y
 CONFIG_POWER_RESET_SYSCON=y
@@ -614,6 +636,7 @@ CONFIG_SENSORS_LM75=m
 CONFIG_SENSORS_LM93=m
 CONFIG_SENSORS_W83795=m
 CONFIG_SENSORS_W83627HF=m
+CONFIG_LOONGSON2_THERMAL=m
 CONFIG_RC_CORE=m
 CONFIG_LIRC=y
 CONFIG_RC_DECODERS=y
@@ -643,6 +666,7 @@ CONFIG_DRM_AMDGPU_USERPTR=y
 CONFIG_DRM_AST=y
 CONFIG_DRM_QXL=m
 CONFIG_DRM_VIRTIO_GPU=m
+CONFIG_DRM_LOONGSON=y
 CONFIG_FB=y
 CONFIG_FB_EFI=y
 CONFIG_FB_RADEON=y
@@ -712,6 +736,7 @@ CONFIG_UCSI_ACPI=m
 CONFIG_INFINIBAND=m
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_EFI=y
+CONFIG_RTC_DRV_LOONGSON=y
 CONFIG_DMADEVICES=y
 CONFIG_UIO=m
 CONFIG_UIO_PDRV_GENIRQ=m
@@ -745,7 +770,9 @@ CONFIG_COMEDI_NI_LABPC_PCI=m
 CONFIG_COMEDI_NI_PCIDIO=m
 CONFIG_COMEDI_NI_PCIMIO=m
 CONFIG_STAGING=y
-CONFIG_R8188EU=m
+CONFIG_COMMON_CLK_LOONGSON2=y
+CONFIG_LOONGSON2_GUTS=y
+CONFIG_LOONGSON2_PM=y
 CONFIG_PM_DEVFREQ=y
 CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND=y
 CONFIG_DEVFREQ_GOV_PERFORMANCE=y
@@ -759,10 +786,17 @@ CONFIG_EXT2_FS_SECURITY=y
 CONFIG_EXT3_FS=y
 CONFIG_EXT3_FS_POSIX_ACL=y
 CONFIG_EXT3_FS_SECURITY=y
+CONFIG_JFS_FS=m
+CONFIG_JFS_POSIX_ACL=y
+CONFIG_JFS_SECURITY=y
 CONFIG_XFS_FS=y
 CONFIG_XFS_QUOTA=y
 CONFIG_XFS_POSIX_ACL=y
+CONFIG_GFS2_FS=m
+CONFIG_GFS2_FS_LOCKING_DLM=y
+CONFIG_OCFS2_FS=m
 CONFIG_BTRFS_FS=y
+CONFIG_BTRFS_FS_POSIX_ACL=y
 CONFIG_FANOTIFY=y
 CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y
 CONFIG_QUOTA=y
@@ -771,11 +805,14 @@ CONFIG_QFMT_V1=m
 CONFIG_QFMT_V2=m
 CONFIG_AUTOFS_FS=y
 CONFIG_FUSE_FS=m
+CONFIG_CUSE=m
+CONFIG_VIRTIO_FS=m
 CONFIG_OVERLAY_FS=y
 CONFIG_OVERLAY_FS_INDEX=y
 CONFIG_OVERLAY_FS_XINO_AUTO=y
 CONFIG_OVERLAY_FS_METACOPY=y
 CONFIG_FSCACHE=y
+CONFIG_CACHEFILES=m
 CONFIG_ISO9660_FS=y
 CONFIG_JOLIET=y
 CONFIG_ZISOFS=y
@@ -784,19 +821,42 @@ CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
 CONFIG_FAT_DEFAULT_CODEPAGE=936
 CONFIG_FAT_DEFAULT_IOCHARSET="gb2312"
+CONFIG_EXFAT_FS=m
+CONFIG_NTFS3_FS=m
+CONFIG_NTFS3_64BIT_CLUSTER=y
+CONFIG_NTFS3_LZX_XPRESS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
 CONFIG_HUGETLBFS=y
 CONFIG_CONFIGFS_FS=y
+CONFIG_ORANGEFS_FS=m
+CONFIG_ECRYPT_FS=m
+CONFIG_ECRYPT_FS_MESSAGING=y
 CONFIG_HFS_FS=m
 CONFIG_HFSPLUS_FS=m
+CONFIG_UBIFS_FS=m
+CONFIG_UBIFS_FS_ADVANCED_COMPR=y
 CONFIG_CRAMFS=m
 CONFIG_SQUASHFS=y
 CONFIG_SQUASHFS_XATTR=y
 CONFIG_SQUASHFS_LZ4=y
 CONFIG_SQUASHFS_LZO=y
 CONFIG_SQUASHFS_XZ=y
+CONFIG_MINIX_FS=m
+CONFIG_ROMFS_FS=m
+CONFIG_PSTORE=m
+CONFIG_PSTORE_LZO_COMPRESS=m
+CONFIG_PSTORE_LZ4_COMPRESS=m
+CONFIG_PSTORE_LZ4HC_COMPRESS=m
+CONFIG_PSTORE_842_COMPRESS=y
+CONFIG_PSTORE_ZSTD_COMPRESS=y
+CONFIG_PSTORE_ZSTD_COMPRESS_DEFAULT=y
+CONFIG_SYSV_FS=m
+CONFIG_UFS_FS=m
+CONFIG_EROFS_FS=m
+CONFIG_EROFS_FS_ZIP_LZMA=y
+CONFIG_EROFS_FS_PCPU_KTHREAD=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3_ACL=y
 CONFIG_NFS_V4=y
@@ -807,6 +867,10 @@ CONFIG_NFSD=y
 CONFIG_NFSD_V3_ACL=y
 CONFIG_NFSD_V4=y
 CONFIG_NFSD_BLOCKLAYOUT=y
+CONFIG_CEPH_FS=m
+CONFIG_CEPH_FSCACHE=y
+CONFIG_CEPH_FS_POSIX_ACL=y
+CONFIG_CEPH_FS_SECURITY_LABEL=y
 CONFIG_CIFS=m
 # CONFIG_CIFS_DEBUG is not set
 CONFIG_9P_FS=y
@@ -814,6 +878,7 @@ CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_CODEPAGE_936=y
 CONFIG_NLS_ASCII=y
 CONFIG_NLS_UTF8=y
+CONFIG_DLM=m
 CONFIG_KEY_DH_OPERATIONS=y
 CONFIG_SECURITY=y
 CONFIG_SECURITY_SELINUX=y
@@ -847,6 +912,7 @@ CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
+CONFIG_CRYPTO_CRC32_LOONGARCH=m
 CONFIG_CRYPTO_DEV_VIRTIO=m
 CONFIG_PRINTK_TIME=y
 CONFIG_STRIP_ASM_SYMS=y

From feeec636b6b1cf3e6129e645411751b205c44976 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Fri, 1 Sep 2023 01:29:17 -0500
Subject: [PATCH 1155/1189] smb3: add trace point for queryfs (statfs)

In debugging a recent performance problem with statfs, it would have
been helpful to be able to trace the smb3 query fs info request
more narrowly.  Add a trace point "smb3_qfs_done"

Which displays:

 stat-68950   [008] .....  1472.360598: smb3_qfs_done: xid=14 sid=0xaa9765e4 tid=0x95a76f54 unc_name=\\localhost\test rc=0

Reviewed-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2ops.c | 1 +
 fs/smb/client/trace.h   | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index e3dd698854d6..d9eda2e958b4 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -2683,6 +2683,7 @@ smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon,
 		smb2_copy_fs_info_to_kstatfs(info, buf);
 
 qfs_exit:
+	trace_smb3_qfs_done(xid, tcon->tid, tcon->ses->Suid, tcon->tree_name, rc);
 	free_rsp_buf(buftype, rsp_iov.iov_base);
 	return rc;
 }
diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h
index e671bd16f00c..a7e4755bed0f 100644
--- a/fs/smb/client/trace.h
+++ b/fs/smb/client/trace.h
@@ -691,7 +691,7 @@ DEFINE_EVENT(smb3_tcon_class, smb3_##name,    \
 	TP_ARGS(xid, tid, sesid, unc_name, rc))
 
 DEFINE_SMB3_TCON_EVENT(tcon);
-
+DEFINE_SMB3_TCON_EVENT(qfs_done);
 
 /*
  * For smb2/smb3 open (including create and mkdir) calls

From 6a50d71d0ffff6791737eb502b27f74fb87d0cae Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Fri, 1 Sep 2023 02:15:14 -0500
Subject: [PATCH 1156/1189] smb3: allow controlling maximum number of cached
 directories

Allow adjusting the maximum number of cached directories per share
(defaults to 16) via mount parm "max_cached_dirs"

Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cached_dir.c |  7 ++++---
 fs/smb/client/cached_dir.h |  2 +-
 fs/smb/client/cifsfs.c     |  2 ++
 fs/smb/client/cifsglob.h   |  1 +
 fs/smb/client/connect.c    |  1 +
 fs/smb/client/fs_context.c | 11 ++++++++++-
 fs/smb/client/fs_context.h |  4 +++-
 7 files changed, 22 insertions(+), 6 deletions(-)

diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c
index 9d84c4a7bd0c..b17f067e4ada 100644
--- a/fs/smb/client/cached_dir.c
+++ b/fs/smb/client/cached_dir.c
@@ -18,7 +18,8 @@ static void smb2_close_cached_fid(struct kref *ref);
 
 static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids,
 						    const char *path,
-						    bool lookup_only)
+						    bool lookup_only,
+						    __u32 max_cached_dirs)
 {
 	struct cached_fid *cfid;
 
@@ -43,7 +44,7 @@ static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids,
 		spin_unlock(&cfids->cfid_list_lock);
 		return NULL;
 	}
-	if (cfids->num_entries >= MAX_CACHED_FIDS) {
+	if (cfids->num_entries >= max_cached_dirs) {
 		spin_unlock(&cfids->cfid_list_lock);
 		return NULL;
 	}
@@ -162,7 +163,7 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon,
 	if (!utf16_path)
 		return -ENOMEM;
 
-	cfid = find_or_create_cached_dir(cfids, path, lookup_only);
+	cfid = find_or_create_cached_dir(cfids, path, lookup_only, tcon->max_cached_dirs);
 	if (cfid == NULL) {
 		kfree(utf16_path);
 		return -ENOENT;
diff --git a/fs/smb/client/cached_dir.h b/fs/smb/client/cached_dir.h
index facc9b154d00..a82ff2cea789 100644
--- a/fs/smb/client/cached_dir.h
+++ b/fs/smb/client/cached_dir.h
@@ -49,7 +49,7 @@ struct cached_fid {
 	struct cached_dirents dirents;
 };
 
-#define MAX_CACHED_FIDS 16
+/* default MAX_CACHED_FIDS is 16 */
 struct cached_fids {
 	/* Must be held when:
 	 * - accessing the cfids->entries list
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index 52612bb52bd7..22869cda1356 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -699,6 +699,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 		seq_printf(s, ",snapshot=%llu", tcon->snapshot_time);
 	if (tcon->handle_timeout)
 		seq_printf(s, ",handletimeout=%u", tcon->handle_timeout);
+	if (tcon->max_cached_dirs != MAX_CACHED_FIDS)
+		seq_printf(s, ",max_cached_dirs=%u", tcon->max_cached_dirs);
 
 	/*
 	 * Display file and directory attribute timeout in seconds.
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 501426ee39e7..032d8716f671 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -1210,6 +1210,7 @@ struct cifs_tcon {
 	__u32 max_chunks;
 	__u32 max_bytes_chunk;
 	__u32 max_bytes_copy;
+	__u32 max_cached_dirs;
 #ifdef CONFIG_CIFS_FSCACHE
 	u64 resource_id;		/* server resource id */
 	struct fscache_volume *fscache;	/* cookie for share */
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index 3bd71f982170..687754791bf0 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -2657,6 +2657,7 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx)
 	tcon->retry = ctx->retry;
 	tcon->nocase = ctx->nocase;
 	tcon->broken_sparse_sup = ctx->no_sparse;
+	tcon->max_cached_dirs = ctx->max_cached_dirs;
 	if (ses->server->capabilities & SMB2_GLOBAL_CAP_DIRECTORY_LEASING)
 		tcon->nohandlecache = ctx->nohandlecache;
 	else
diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c
index 67e16c2ac90e..e45ce31bbda7 100644
--- a/fs/smb/client/fs_context.c
+++ b/fs/smb/client/fs_context.c
@@ -150,6 +150,7 @@ const struct fs_parameter_spec smb3_fs_parameters[] = {
 	fsparam_u32("closetimeo", Opt_closetimeo),
 	fsparam_u32("echo_interval", Opt_echo_interval),
 	fsparam_u32("max_credits", Opt_max_credits),
+	fsparam_u32("max_cached_dirs", Opt_max_cached_dirs),
 	fsparam_u32("handletimeout", Opt_handletimeout),
 	fsparam_u64("snapshot", Opt_snapshot),
 	fsparam_u32("max_channels", Opt_max_channels),
@@ -1165,6 +1166,14 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
 		if (result.uint_32 > 1)
 			ctx->multichannel = true;
 		break;
+	case Opt_max_cached_dirs:
+		if (result.uint_32 < 1) {
+			cifs_errorf(fc, "%s: Invalid max_cached_dirs, needs to be 1 or more\n",
+				    __func__);
+			goto cifs_parse_mount_err;
+		}
+		ctx->max_cached_dirs = result.uint_32;
+		break;
 	case Opt_handletimeout:
 		ctx->handle_timeout = result.uint_32;
 		if (ctx->handle_timeout > SMB3_MAX_HANDLE_TIMEOUT) {
@@ -1592,7 +1601,7 @@ int smb3_init_fs_context(struct fs_context *fc)
 	ctx->acregmax = CIFS_DEF_ACTIMEO;
 	ctx->acdirmax = CIFS_DEF_ACTIMEO;
 	ctx->closetimeo = SMB3_DEF_DCLOSETIMEO;
-
+	ctx->max_cached_dirs = MAX_CACHED_FIDS;
 	/* Most clients set timeout to 0, allows server to use its default */
 	ctx->handle_timeout = 0; /* See MS-SMB2 spec section 2.2.14.2.12 */
 
diff --git a/fs/smb/client/fs_context.h b/fs/smb/client/fs_context.h
index f4eaf8558902..9d8d34af0211 100644
--- a/fs/smb/client/fs_context.h
+++ b/fs/smb/client/fs_context.h
@@ -128,6 +128,7 @@ enum cifs_param {
 	Opt_closetimeo,
 	Opt_echo_interval,
 	Opt_max_credits,
+	Opt_max_cached_dirs,
 	Opt_snapshot,
 	Opt_max_channels,
 	Opt_handletimeout,
@@ -261,6 +262,7 @@ struct smb3_fs_context {
 	__u32 handle_timeout; /* persistent and durable handle timeout in ms */
 	unsigned int max_credits; /* smb3 max_credits 10 < credits < 60000 */
 	unsigned int max_channels;
+	unsigned int max_cached_dirs;
 	__u16 compression; /* compression algorithm 0xFFFF default 0=disabled */
 	bool rootfs:1; /* if it's a SMB root file system */
 	bool witness:1; /* use witness protocol */
@@ -287,7 +289,7 @@ extern void smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb);
  */
 #define SMB3_MAX_DCLOSETIMEO (1 << 30)
 #define SMB3_DEF_DCLOSETIMEO (1 * HZ) /* even 1 sec enough to help eg open/write/close/open/read */
-
+#define MAX_CACHED_FIDS 16
 extern char *cifs_sanitize_prepath(char *prepath, gfp_t gfp);
 
 #endif

From 30bded94dcef8d329eb2575665518aadf90ca344 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Thu, 20 Jul 2023 08:30:32 -0500
Subject: [PATCH 1157/1189] cifs: update internal module version number for
 cifs.ko

From 2.44 to 2.45

Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsfs.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/smb/client/cifsfs.h b/fs/smb/client/cifsfs.h
index 532c38fe07cd..41daebd220ff 100644
--- a/fs/smb/client/cifsfs.h
+++ b/fs/smb/client/cifsfs.h
@@ -152,6 +152,6 @@ extern const struct export_operations cifs_export_ops;
 #endif /* CONFIG_CIFS_NFSD_EXPORT */
 
 /* when changing internal version - update following two lines at same time */
-#define SMB3_PRODUCT_BUILD 44
-#define CIFS_VERSION   "2.44"
+#define SMB3_PRODUCT_BUILD 45
+#define CIFS_VERSION   "2.45"
 #endif				/* _CIFSFS_H */

From e43252db7e207a2e194e6a4883a43a31a776a968 Mon Sep 17 00:00:00 2001
From: Kailang Yang <kailang@realtek.com>
Date: Wed, 6 Sep 2023 16:50:41 +0800
Subject: [PATCH 1158/1189] ALSA: hda/realtek - ALC287 I2S speaker platform
 support

0x17 was only speaker pin, DAC assigned will be 0x03. Headphone
assigned to 0x02.
Playback via headphone will get EQ filter processing. So,it needs to
swap DAC.

Tested-by: Mark Pearson <mpearson@lenovo.com>
Signed-off-by: Kailang Yang <kailang@realtek.com>
Link: https://lore.kernel.org/r/4e4cfa1b3b4c46838aecafc6e8b6f876@realtek.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index a07df6f92960..b7e78bfcffd8 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -7057,6 +7057,27 @@ static void alc295_fixup_dell_inspiron_top_speakers(struct hda_codec *codec,
 	}
 }
 
+/* Forcibly assign NID 0x03 to HP while NID 0x02 to SPK */
+static void alc287_fixup_bind_dacs(struct hda_codec *codec,
+				    const struct hda_fixup *fix, int action)
+{
+	struct alc_spec *spec = codec->spec;
+	static const hda_nid_t conn[] = { 0x02, 0x03 }; /* exclude 0x06 */
+	static const hda_nid_t preferred_pairs[] = {
+		0x17, 0x02, 0x21, 0x03, 0
+	};
+
+	if (action != HDA_FIXUP_ACT_PRE_PROBE)
+		return;
+
+	snd_hda_override_conn_list(codec, 0x17, ARRAY_SIZE(conn), conn);
+	spec->gen.preferred_dacs = preferred_pairs;
+	spec->gen.auto_mute_via_amp = 1;
+	snd_hda_codec_write_cache(codec, 0x14, 0, AC_VERB_SET_PIN_WIDGET_CONTROL,
+			    0x0); /* Make sure 0x14 was disable */
+}
+
+
 enum {
 	ALC269_FIXUP_GPIO2,
 	ALC269_FIXUP_SONY_VAIO,
@@ -7319,6 +7340,7 @@ enum {
 	ALC287_FIXUP_TAS2781_I2C,
 	ALC245_FIXUP_HP_MUTE_LED_COEFBIT,
 	ALC245_FIXUP_HP_X360_MUTE_LEDS,
+	ALC287_FIXUP_THINKPAD_I2S_SPK,
 };
 
 /* A special fixup for Lenovo C940 and Yoga Duet 7;
@@ -9413,6 +9435,10 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC245_FIXUP_HP_GPIO_LED
 	},
+	[ALC287_FIXUP_THINKPAD_I2S_SPK] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc287_fixup_bind_dacs,
+	},
 };
 
 static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -10544,6 +10570,10 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x17, 0x90170111},
 		{0x19, 0x03a11030},
 		{0x21, 0x03211020}),
+	SND_HDA_PIN_QUIRK(0x10ec0287, 0x17aa, "Lenovo", ALC287_FIXUP_THINKPAD_I2S_SPK,
+		{0x17, 0x90170110},
+		{0x19, 0x03a11030},
+		{0x21, 0x03211020}),
 	SND_HDA_PIN_QUIRK(0x10ec0286, 0x1025, "Acer", ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE,
 		{0x12, 0x90a60130},
 		{0x17, 0x90170110},

From 61a1deacc3d4fd3d57d7fda4d935f7f7503e8440 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Wed, 6 Sep 2023 15:20:12 +0800
Subject: [PATCH 1159/1189] net: hns3: fix tx timeout issue

Currently, the driver knocks the ring doorbell before updating
the ring->last_to_use in tx flow. if the hardware transmiting
packet and napi poll scheduling are fast enough, it may get
the old ring->last_to_use in drivers' napi poll.
In this case, the driver will think the tx is not completed, and
return directly without clear the flag __QUEUE_STATE_STACK_XOFF,
which may cause tx timeout.

Fixes: 20d06ca2679c ("net: hns3: optimize the tx clean process")
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Jijie Shao <shaojijie@huawei.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index eac2d0573241..81947c4e5100 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -2103,8 +2103,12 @@ static void hns3_tx_doorbell(struct hns3_enet_ring *ring, int num,
 	 */
 	if (test_bit(HNS3_NIC_STATE_TX_PUSH_ENABLE, &priv->state) && num &&
 	    !ring->pending_buf && num <= HNS3_MAX_PUSH_BD_NUM && doorbell) {
+		/* This smp_store_release() pairs with smp_load_aquire() in
+		 * hns3_nic_reclaim_desc(). Ensure that the BD valid bit
+		 * is updated.
+		 */
+		smp_store_release(&ring->last_to_use, ring->next_to_use);
 		hns3_tx_push_bd(ring, num);
-		WRITE_ONCE(ring->last_to_use, ring->next_to_use);
 		return;
 	}
 
@@ -2115,6 +2119,11 @@ static void hns3_tx_doorbell(struct hns3_enet_ring *ring, int num,
 		return;
 	}
 
+	/* This smp_store_release() pairs with smp_load_aquire() in
+	 * hns3_nic_reclaim_desc(). Ensure that the BD valid bit is updated.
+	 */
+	smp_store_release(&ring->last_to_use, ring->next_to_use);
+
 	if (ring->tqp->mem_base)
 		hns3_tx_mem_doorbell(ring);
 	else
@@ -2122,7 +2131,6 @@ static void hns3_tx_doorbell(struct hns3_enet_ring *ring, int num,
 		       ring->tqp->io_base + HNS3_RING_TX_RING_TAIL_REG);
 
 	ring->pending_buf = 0;
-	WRITE_ONCE(ring->last_to_use, ring->next_to_use);
 }
 
 static void hns3_tsyn(struct net_device *netdev, struct sk_buff *skb,
@@ -3563,9 +3571,8 @@ static void hns3_reuse_buffer(struct hns3_enet_ring *ring, int i)
 static bool hns3_nic_reclaim_desc(struct hns3_enet_ring *ring,
 				  int *bytes, int *pkts, int budget)
 {
-	/* pair with ring->last_to_use update in hns3_tx_doorbell(),
-	 * smp_store_release() is not used in hns3_tx_doorbell() because
-	 * the doorbell operation already have the needed barrier operation.
+	/* This smp_load_acquire() pairs with smp_store_release() in
+	 * hns3_tx_doorbell().
 	 */
 	int ltu = smp_load_acquire(&ring->last_to_use);
 	int ntc = ring->next_to_clean;

From dd2bbc2ef69a920d93801321b0b01ac6c4e5cacd Mon Sep 17 00:00:00 2001
From: Jijie Shao <shaojijie@huawei.com>
Date: Wed, 6 Sep 2023 15:20:13 +0800
Subject: [PATCH 1160/1189] net: hns3: Support query tx timeout threshold by
 debugfs

support query tx timeout threshold by debugfs

Signed-off-by: Jijie Shao <shaojijie@huawei.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index f276b5ecb431..8086722a56c0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -1045,6 +1045,7 @@ hns3_dbg_dev_specs(struct hnae3_handle *h, char *buf, int len, int *pos)
 	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
 	struct hnae3_dev_specs *dev_specs = &ae_dev->dev_specs;
 	struct hnae3_knic_private_info *kinfo = &h->kinfo;
+	struct net_device *dev = kinfo->netdev;
 
 	*pos += scnprintf(buf + *pos, len - *pos, "dev_spec:\n");
 	*pos += scnprintf(buf + *pos, len - *pos, "MAC entry num: %u\n",
@@ -1087,6 +1088,9 @@ hns3_dbg_dev_specs(struct hnae3_handle *h, char *buf, int len, int *pos)
 			  dev_specs->mc_mac_size);
 	*pos += scnprintf(buf + *pos, len - *pos, "MAC statistics number: %u\n",
 			  dev_specs->mac_stats_num);
+	*pos += scnprintf(buf + *pos, len - *pos,
+			  "TX timeout threshold: %d seconds\n",
+			  dev->watchdog_timeo / HZ);
 }
 
 static int hns3_dbg_dev_info(struct hnae3_handle *h, char *buf, int len)

From efccf655e99b6907ca07a466924e91805892e7d3 Mon Sep 17 00:00:00 2001
From: Hao Chen <chenhao418@huawei.com>
Date: Wed, 6 Sep 2023 15:20:14 +0800
Subject: [PATCH 1161/1189] net: hns3: fix byte order conversion issue in
 hclge_dbg_fd_tcam_read()

req1->tcam_data is defined as "u8 tcam_data[8]", and we convert it as
(u32 *) without considerring byte order conversion,
it may result in printing wrong data for tcam_data.

Convert tcam_data to (__le32 *) first to fix it.

Fixes: b5a0b70d77b9 ("net: hns3: refactor dump fd tcam of debugfs")
Signed-off-by: Hao Chen <chenhao418@huawei.com>
Signed-off-by: Jijie Shao <shaojijie@huawei.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index f01a7a9ee02c..ff3f8f424ad9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -1519,7 +1519,7 @@ static int hclge_dbg_fd_tcam_read(struct hclge_dev *hdev, bool sel_x,
 	struct hclge_desc desc[3];
 	int pos = 0;
 	int ret, i;
-	u32 *req;
+	__le32 *req;
 
 	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_FD_TCAM_OP, true);
 	desc[0].flag |= cpu_to_le16(HCLGE_COMM_CMD_FLAG_NEXT);
@@ -1544,22 +1544,22 @@ static int hclge_dbg_fd_tcam_read(struct hclge_dev *hdev, bool sel_x,
 			 tcam_msg.loc);
 
 	/* tcam_data0 ~ tcam_data1 */
-	req = (u32 *)req1->tcam_data;
+	req = (__le32 *)req1->tcam_data;
 	for (i = 0; i < 2; i++)
 		pos += scnprintf(tcam_buf + pos, HCLGE_DBG_TCAM_BUF_SIZE - pos,
-				 "%08x\n", *req++);
+				 "%08x\n", le32_to_cpu(*req++));
 
 	/* tcam_data2 ~ tcam_data7 */
-	req = (u32 *)req2->tcam_data;
+	req = (__le32 *)req2->tcam_data;
 	for (i = 0; i < 6; i++)
 		pos += scnprintf(tcam_buf + pos, HCLGE_DBG_TCAM_BUF_SIZE - pos,
-				 "%08x\n", *req++);
+				 "%08x\n", le32_to_cpu(*req++));
 
 	/* tcam_data8 ~ tcam_data12 */
-	req = (u32 *)req3->tcam_data;
+	req = (__le32 *)req3->tcam_data;
 	for (i = 0; i < 5; i++)
 		pos += scnprintf(tcam_buf + pos, HCLGE_DBG_TCAM_BUF_SIZE - pos,
-				 "%08x\n", *req++);
+				 "%08x\n", le32_to_cpu(*req++));
 
 	return ret;
 }

From c295160b1d95e885f1af4586a221cb221d232d10 Mon Sep 17 00:00:00 2001
From: Hao Chen <chenhao418@huawei.com>
Date: Wed, 6 Sep 2023 15:20:15 +0800
Subject: [PATCH 1162/1189] net: hns3: fix debugfs concurrency issue between
 kfree buffer and read

Now in hns3_dbg_uninit(), there may be concurrency between
kfree buffer and read, it may result in memory error.

Moving debugfs_remove_recursive() in front of kfree buffer to ensure
they don't happen at the same time.

Fixes: 5e69ea7ee2a6 ("net: hns3: refactor the debugfs process")
Signed-off-by: Hao Chen <chenhao418@huawei.com>
Signed-off-by: Jijie Shao <shaojijie@huawei.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 8086722a56c0..b8508533878b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -1415,9 +1415,9 @@ int hns3_dbg_init(struct hnae3_handle *handle)
 	return 0;
 
 out:
-	mutex_destroy(&handle->dbgfs_lock);
 	debugfs_remove_recursive(handle->hnae3_dbgfs);
 	handle->hnae3_dbgfs = NULL;
+	mutex_destroy(&handle->dbgfs_lock);
 	return ret;
 }
 
@@ -1425,6 +1425,9 @@ void hns3_dbg_uninit(struct hnae3_handle *handle)
 {
 	u32 i;
 
+	debugfs_remove_recursive(handle->hnae3_dbgfs);
+	handle->hnae3_dbgfs = NULL;
+
 	for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd); i++)
 		if (handle->dbgfs_buf[i]) {
 			kvfree(handle->dbgfs_buf[i]);
@@ -1432,8 +1435,6 @@ void hns3_dbg_uninit(struct hnae3_handle *handle)
 		}
 
 	mutex_destroy(&handle->dbgfs_lock);
-	debugfs_remove_recursive(handle->hnae3_dbgfs);
-	handle->hnae3_dbgfs = NULL;
 }
 
 void hns3_dbg_register_debugfs(const char *debugfs_dir_name)

From fa5564945f7d15ae2390b00c08b6abaef0165cda Mon Sep 17 00:00:00 2001
From: Jijie Shao <shaojijie@huawei.com>
Date: Wed, 6 Sep 2023 15:20:16 +0800
Subject: [PATCH 1163/1189] net: hns3: fix invalid mutex between tc qdisc and
 dcb ets command issue

We hope that tc qdisc and dcb ets commands can not be used crosswise.
If we want to use any of the commands to configure tc,
We must use the other command to clear the existing configuration.

However, when we configure a single tc with tc qdisc,
we can still configure it with dcb ets.
Because we use mqprio_active as the tag of tc qdisc configuration,
but with dcb ets, we do not check mqprio_active.

This patch fix this issue by check mqprio_active before
executing the dcb ets command. and add dcb_ets_active to
replace HCLGE_FLAG_DCB_ENABLE and HCLGE_FLAG_MQPRIO_ENABLE
at the hclge layer,

Fixes: cacde272dd00 ("net: hns3: Add hclge_dcb module for the support of DCB feature")
Signed-off-by: Jijie Shao <shaojijie@huawei.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.h   |  1 +
 .../hisilicon/hns3/hns3pf/hclge_dcb.c         | 20 +++++--------------
 .../hisilicon/hns3/hns3pf/hclge_main.c        |  5 +++--
 .../hisilicon/hns3/hns3pf/hclge_main.h        |  2 --
 4 files changed, 9 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index a4b43bcd2f0c..aaf1f42624a7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -814,6 +814,7 @@ struct hnae3_tc_info {
 	u8 max_tc; /* Total number of TCs */
 	u8 num_tc; /* Total number of enabled TCs */
 	bool mqprio_active;
+	bool dcb_ets_active;
 };
 
 #define HNAE3_MAX_DSCP			64
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
index fad5a5ff3cda..b98301e205f7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
@@ -259,7 +259,7 @@ static int hclge_ieee_setets(struct hnae3_handle *h, struct ieee_ets *ets)
 	int ret;
 
 	if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE) ||
-	    hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE)
+	    h->kinfo.tc_info.mqprio_active)
 		return -EINVAL;
 
 	ret = hclge_ets_validate(hdev, ets, &num_tc, &map_changed);
@@ -275,10 +275,7 @@ static int hclge_ieee_setets(struct hnae3_handle *h, struct ieee_ets *ets)
 	}
 
 	hclge_tm_schd_info_update(hdev, num_tc);
-	if (num_tc > 1)
-		hdev->flag |= HCLGE_FLAG_DCB_ENABLE;
-	else
-		hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE;
+	h->kinfo.tc_info.dcb_ets_active = num_tc > 1;
 
 	ret = hclge_ieee_ets_to_tm_info(hdev, ets);
 	if (ret)
@@ -487,7 +484,7 @@ static u8 hclge_getdcbx(struct hnae3_handle *h)
 	struct hclge_vport *vport = hclge_get_vport(h);
 	struct hclge_dev *hdev = vport->back;
 
-	if (hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE)
+	if (h->kinfo.tc_info.mqprio_active)
 		return 0;
 
 	return hdev->dcbx_cap;
@@ -611,7 +608,8 @@ static int hclge_setup_tc(struct hnae3_handle *h,
 	if (!test_bit(HCLGE_STATE_NIC_REGISTERED, &hdev->state))
 		return -EBUSY;
 
-	if (hdev->flag & HCLGE_FLAG_DCB_ENABLE)
+	kinfo = &vport->nic.kinfo;
+	if (kinfo->tc_info.dcb_ets_active)
 		return -EINVAL;
 
 	ret = hclge_mqprio_qopt_check(hdev, mqprio_qopt);
@@ -625,7 +623,6 @@ static int hclge_setup_tc(struct hnae3_handle *h,
 	if (ret)
 		return ret;
 
-	kinfo = &vport->nic.kinfo;
 	memcpy(&old_tc_info, &kinfo->tc_info, sizeof(old_tc_info));
 	hclge_sync_mqprio_qopt(&kinfo->tc_info, mqprio_qopt);
 	kinfo->tc_info.mqprio_active = tc > 0;
@@ -634,13 +631,6 @@ static int hclge_setup_tc(struct hnae3_handle *h,
 	if (ret)
 		goto err_out;
 
-	hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE;
-
-	if (tc > 1)
-		hdev->flag |= HCLGE_FLAG_MQPRIO_ENABLE;
-	else
-		hdev->flag &= ~HCLGE_FLAG_MQPRIO_ENABLE;
-
 	return hclge_notify_init_up(hdev);
 
 err_out:
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 0f50dba6cc47..8ca368424436 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -11026,6 +11026,7 @@ static void hclge_get_mdix_mode(struct hnae3_handle *handle,
 
 static void hclge_info_show(struct hclge_dev *hdev)
 {
+	struct hnae3_handle *handle = &hdev->vport->nic;
 	struct device *dev = &hdev->pdev->dev;
 
 	dev_info(dev, "PF info begin:\n");
@@ -11042,9 +11043,9 @@ static void hclge_info_show(struct hclge_dev *hdev)
 	dev_info(dev, "This is %s PF\n",
 		 hdev->flag & HCLGE_FLAG_MAIN ? "main" : "not main");
 	dev_info(dev, "DCB %s\n",
-		 hdev->flag & HCLGE_FLAG_DCB_ENABLE ? "enable" : "disable");
+		 handle->kinfo.tc_info.dcb_ets_active ? "enable" : "disable");
 	dev_info(dev, "MQPRIO %s\n",
-		 hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE ? "enable" : "disable");
+		 handle->kinfo.tc_info.mqprio_active ? "enable" : "disable");
 	dev_info(dev, "Default tx spare buffer size: %u\n",
 		 hdev->tx_spare_buf_size);
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index ec233ec57222..7bc2049b723d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -919,8 +919,6 @@ struct hclge_dev {
 
 #define HCLGE_FLAG_MAIN			BIT(0)
 #define HCLGE_FLAG_DCB_CAPABLE		BIT(1)
-#define HCLGE_FLAG_DCB_ENABLE		BIT(2)
-#define HCLGE_FLAG_MQPRIO_ENABLE	BIT(3)
 	u32 flag;
 
 	u32 pkt_buf_size; /* Total pf buf size for tx/rx */

From 674d9591a32d01df75d6b5fffed4ef942a294376 Mon Sep 17 00:00:00 2001
From: Yisen Zhuang <yisen.zhuang@huawei.com>
Date: Wed, 6 Sep 2023 15:20:17 +0800
Subject: [PATCH 1164/1189] net: hns3: fix the port information display when
 sfp is absent

When sfp is absent or unidentified, the port type should be
displayed as PORT_OTHERS, rather than PORT_FIBRE.

Fixes: 88d10bd6f730 ("net: hns3: add support for multiple media type")
Signed-off-by: Yisen Zhuang <yisen.zhuang@huawei.com>
Signed-off-by: Jijie Shao <shaojijie@huawei.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 36858a72d771..682239f33082 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -773,7 +773,9 @@ static int hns3_get_link_ksettings(struct net_device *netdev,
 		hns3_get_ksettings(h, cmd);
 		break;
 	case HNAE3_MEDIA_TYPE_FIBER:
-		if (module_type == HNAE3_MODULE_TYPE_CR)
+		if (module_type == HNAE3_MODULE_TYPE_UNKNOWN)
+			cmd->base.port = PORT_OTHER;
+		else if (module_type == HNAE3_MODULE_TYPE_CR)
 			cmd->base.port = PORT_DA;
 		else
 			cmd->base.port = PORT_FIBRE;

From 60326634f6c54528778de18bfef1e8a7a93b3771 Mon Sep 17 00:00:00 2001
From: Jie Wang <wangjie125@huawei.com>
Date: Wed, 6 Sep 2023 15:20:18 +0800
Subject: [PATCH 1165/1189] net: hns3: remove GSO partial feature bit

HNS3 NIC does not support GSO partial packets segmentation. Actually tunnel
packets for example NvGRE packets segment offload and checksum offload is
already supported. There is no need to keep gso partial feature bit. So
this patch removes it.

Fixes: 76ad4f0ee747 ("net: hns3: Add support of HNS3 Ethernet Driver for hip08 SoC")
Signed-off-by: Jie Wang <wangjie125@huawei.com>
Signed-off-by: Jijie Shao <shaojijie@huawei.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 81947c4e5100..b4895c7b3efd 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -3316,8 +3316,6 @@ static void hns3_set_default_feature(struct net_device *netdev)
 
 	netdev->priv_flags |= IFF_UNICAST_FLT;
 
-	netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
-
 	netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER |
 		NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
 		NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO |

From 8bd795fedb8450ecbef18eeadbd23ed8fc7630f5 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Thu, 7 Sep 2023 09:54:11 +0100
Subject: [PATCH 1166/1189] arm64: csum: Fix OoB access in IP checksum code for
 negative lengths

Although commit c2c24edb1d9c ("arm64: csum: Fix pathological zero-length
calls") added an early return for zero-length input, syzkaller has
popped up with an example of a _negative_ length which causes an
undefined shift and an out-of-bounds read:

 | BUG: KASAN: slab-out-of-bounds in do_csum+0x44/0x254 arch/arm64/lib/csum.c:39
 | Read of size 4294966928 at addr ffff0000d7ac0170 by task syz-executor412/5975
 |
 | CPU: 0 PID: 5975 Comm: syz-executor412 Not tainted 6.4.0-rc4-syzkaller-g908f31f2a05b #0
 | Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/25/2023
 | Call trace:
 |  dump_backtrace+0x1b8/0x1e4 arch/arm64/kernel/stacktrace.c:233
 |  show_stack+0x2c/0x44 arch/arm64/kernel/stacktrace.c:240
 |  __dump_stack lib/dump_stack.c:88 [inline]
 |  dump_stack_lvl+0xd0/0x124 lib/dump_stack.c:106
 |  print_address_description mm/kasan/report.c:351 [inline]
 |  print_report+0x174/0x514 mm/kasan/report.c:462
 |  kasan_report+0xd4/0x130 mm/kasan/report.c:572
 |  kasan_check_range+0x264/0x2a4 mm/kasan/generic.c:187
 |  __kasan_check_read+0x20/0x30 mm/kasan/shadow.c:31
 |  do_csum+0x44/0x254 arch/arm64/lib/csum.c:39
 |  csum_partial+0x30/0x58 lib/checksum.c:128
 |  gso_make_checksum include/linux/skbuff.h:4928 [inline]
 |  __udp_gso_segment+0xaf4/0x1bc4 net/ipv4/udp_offload.c:332
 |  udp6_ufo_fragment+0x540/0xca0 net/ipv6/udp_offload.c:47
 |  ipv6_gso_segment+0x5cc/0x1760 net/ipv6/ip6_offload.c:119
 |  skb_mac_gso_segment+0x2b4/0x5b0 net/core/gro.c:141
 |  __skb_gso_segment+0x250/0x3d0 net/core/dev.c:3401
 |  skb_gso_segment include/linux/netdevice.h:4859 [inline]
 |  validate_xmit_skb+0x364/0xdbc net/core/dev.c:3659
 |  validate_xmit_skb_list+0x94/0x130 net/core/dev.c:3709
 |  sch_direct_xmit+0xe8/0x548 net/sched/sch_generic.c:327
 |  __dev_xmit_skb net/core/dev.c:3805 [inline]
 |  __dev_queue_xmit+0x147c/0x3318 net/core/dev.c:4210
 |  dev_queue_xmit include/linux/netdevice.h:3085 [inline]
 |  packet_xmit+0x6c/0x318 net/packet/af_packet.c:276
 |  packet_snd net/packet/af_packet.c:3081 [inline]
 |  packet_sendmsg+0x376c/0x4c98 net/packet/af_packet.c:3113
 |  sock_sendmsg_nosec net/socket.c:724 [inline]
 |  sock_sendmsg net/socket.c:747 [inline]
 |  __sys_sendto+0x3b4/0x538 net/socket.c:2144

Extend the early return to reject negative lengths as well, aligning our
implementation with the generic code in lib/checksum.c

Cc: Robin Murphy <robin.murphy@arm.com>
Fixes: 5777eaed566a ("arm64: Implement optimised checksum routine")
Reported-by: syzbot+4a9f9820bd8d302e22f7@syzkaller.appspotmail.com
Link: https://lore.kernel.org/r/000000000000e0e94c0603f8d213@google.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/lib/csum.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/lib/csum.c b/arch/arm64/lib/csum.c
index 78b87a64ca0a..2432683e48a6 100644
--- a/arch/arm64/lib/csum.c
+++ b/arch/arm64/lib/csum.c
@@ -24,7 +24,7 @@ unsigned int __no_sanitize_address do_csum(const unsigned char *buff, int len)
 	const u64 *ptr;
 	u64 data, sum64 = 0;
 
-	if (unlikely(len == 0))
+	if (unlikely(len <= 0))
 		return 0;
 
 	offset = (unsigned long)buff & 7;

From 4952801fc6adb5b50b8ec2bcc5aeef92fcce8730 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 5 Sep 2023 10:19:02 +0200
Subject: [PATCH 1167/1189] Revert "printk: export symbols for debug modules"

This reverts commit 3e00123a13d824d63072b1824c9da59cd78356d9.

No, we never export random symbols for out of tree modules.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/20230905081902.321778-1-hch@lst.de
---
 kernel/printk/printk.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 96fc38cb2e84..7e0b4dd02398 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -538,14 +538,12 @@ char *log_buf_addr_get(void)
 {
 	return log_buf;
 }
-EXPORT_SYMBOL_GPL(log_buf_addr_get);
 
 /* Return log buffer size */
 u32 log_buf_len_get(void)
 {
 	return log_buf_len;
 }
-EXPORT_SYMBOL_GPL(log_buf_len_get);
 
 /*
  * Define how much of the log buffer we could take at maximum. The value

From 45500dc4e01c167ee063f3dcc22f51ced5b2b1e9 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Thu, 7 Sep 2023 13:50:07 +0100
Subject: [PATCH 1168/1189] io_uring: break out of iowq iopoll on teardown

io-wq will retry iopoll even when it failed with -EAGAIN. If that
races with task exit, which sets TIF_NOTIFY_SIGNAL for all its workers,
such workers might potentially infinitely spin retrying iopoll again and
again and each time failing on some allocation / waiting / etc. Don't
keep spinning if io-wq is dying.

Fixes: 561fb04a6a225 ("io_uring: replace workqueue usage with io-wq")
Cc: stable@vger.kernel.org
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/io-wq.c    | 10 ++++++++++
 io_uring/io-wq.h    |  1 +
 io_uring/io_uring.c |  2 ++
 3 files changed, 13 insertions(+)

diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c
index 62f345587df5..1ecc8c748768 100644
--- a/io_uring/io-wq.c
+++ b/io_uring/io-wq.c
@@ -174,6 +174,16 @@ static void io_worker_ref_put(struct io_wq *wq)
 		complete(&wq->worker_done);
 }
 
+bool io_wq_worker_stopped(void)
+{
+	struct io_worker *worker = current->worker_private;
+
+	if (WARN_ON_ONCE(!io_wq_current_is_worker()))
+		return true;
+
+	return test_bit(IO_WQ_BIT_EXIT, &worker->wq->state);
+}
+
 static void io_worker_cancel_cb(struct io_worker *worker)
 {
 	struct io_wq_acct *acct = io_wq_get_acct(worker);
diff --git a/io_uring/io-wq.h b/io_uring/io-wq.h
index 06d9ca90c577..2b2a6406dd8e 100644
--- a/io_uring/io-wq.h
+++ b/io_uring/io-wq.h
@@ -52,6 +52,7 @@ void io_wq_hash_work(struct io_wq_work *work, void *val);
 
 int io_wq_cpu_affinity(struct io_uring_task *tctx, cpumask_var_t mask);
 int io_wq_max_workers(struct io_wq *wq, int *new_count);
+bool io_wq_worker_stopped(void);
 
 static inline bool io_wq_is_hashed(struct io_wq_work *work)
 {
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 0f0ba31c3850..58d8dd34a45f 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1975,6 +1975,8 @@ fail:
 		if (!needs_poll) {
 			if (!(req->ctx->flags & IORING_SETUP_IOPOLL))
 				break;
+			if (io_wq_worker_stopped())
+				break;
 			cond_resched();
 			continue;
 		}

From 27122c079f5b4b4ecf1323b65700edc57e07bf6e Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Thu, 7 Sep 2023 13:50:08 +0100
Subject: [PATCH 1169/1189] io_uring: fix unprotected iopoll overflow

[   71.490669] WARNING: CPU: 3 PID: 17070 at io_uring/io_uring.c:769
io_cqring_event_overflow+0x47b/0x6b0
[   71.498381] Call Trace:
[   71.498590]  <TASK>
[   71.501858]  io_req_cqe_overflow+0x105/0x1e0
[   71.502194]  __io_submit_flush_completions+0x9f9/0x1090
[   71.503537]  io_submit_sqes+0xebd/0x1f00
[   71.503879]  __do_sys_io_uring_enter+0x8c5/0x2380
[   71.507360]  do_syscall_64+0x39/0x80

We decoupled CQ locking from ->task_complete but haven't fixed up places
forcing locking for CQ overflows.

Fixes: ec26c225f06f5 ("io_uring: merge iopoll and normal completion paths")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/io_uring.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 58d8dd34a45f..090913acf1db 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -908,7 +908,7 @@ static void __io_flush_post_cqes(struct io_ring_ctx *ctx)
 		struct io_uring_cqe *cqe = &ctx->completion_cqes[i];
 
 		if (!io_fill_cqe_aux(ctx, cqe->user_data, cqe->res, cqe->flags)) {
-			if (ctx->task_complete) {
+			if (ctx->lockless_cq) {
 				spin_lock(&ctx->completion_lock);
 				io_cqring_event_overflow(ctx, cqe->user_data,
 							cqe->res, cqe->flags, 0, 0);
@@ -1566,7 +1566,7 @@ void __io_submit_flush_completions(struct io_ring_ctx *ctx)
 
 		if (!(req->flags & REQ_F_CQE_SKIP) &&
 		    unlikely(!io_fill_cqe_req(ctx, req))) {
-			if (ctx->task_complete) {
+			if (ctx->lockless_cq) {
 				spin_lock(&ctx->completion_lock);
 				io_req_cqe_overflow(req);
 				spin_unlock(&ctx->completion_lock);

From 023464fe33a53d7e3fa0a1967a2adcb17e5e40e3 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 7 Sep 2023 09:41:49 -0600
Subject: [PATCH 1170/1189] Revert "io_uring: fix IO hang in io_wq_put_and_exit
 from do_exit()"

This reverts commit b484a40dc1f16edb58e5430105a021e1916e6f27.

This commit cancels all requests with io-wq, not just the ones from the
originating task. This breaks use cases that have thread pools, or just
multiple tasks issuing requests on the same ring. The liburing
regression test for this also shows that problem:

$ test/thread-exit.t
cqe->res=-125, Expected 512

where an IO thread gets its request canceled rather than complete
successfully.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/io_uring.c | 32 --------------------------------
 1 file changed, 32 deletions(-)

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 090913acf1db..783ed0fff71b 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -3317,37 +3317,6 @@ static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked)
 	return percpu_counter_sum(&tctx->inflight);
 }
 
-static void io_uring_cancel_wq(struct io_uring_task *tctx)
-{
-	int ret;
-
-	if (!tctx->io_wq)
-		return;
-
-	/*
-	 * FIXED_FILE request isn't tracked in do_exit(), and these
-	 * requests may be submitted to our io_wq as iopoll, so have to
-	 * cancel them before destroying io_wq for avoiding IO hang
-	 */
-	do {
-		struct io_tctx_node *node;
-		unsigned long index;
-
-		ret = 0;
-		xa_for_each(&tctx->xa, index, node) {
-			struct io_ring_ctx *ctx = node->ctx;
-			struct io_task_cancel cancel = { .task = current, .all = true, };
-			enum io_wq_cancel cret;
-
-			io_iopoll_try_reap_events(ctx);
-			cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_task_cb,
-				       &cancel, true);
-			ret |= (cret != IO_WQ_CANCEL_NOTFOUND);
-			cond_resched();
-		}
-	} while (ret);
-}
-
 /*
  * Find any io_uring ctx that this task has registered or done IO on, and cancel
  * requests. @sqd should be not-null IFF it's an SQPOLL thread cancellation.
@@ -3419,7 +3388,6 @@ end_wait:
 		finish_wait(&tctx->wait, &wait);
 	} while (1);
 
-	io_uring_cancel_wq(tctx);
 	io_uring_clean_tctx(tctx);
 	if (cancel_all) {
 		/*

From 9013c51c630ac5a046aa2d51d67e966b6185f1cd Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 3 Sep 2023 13:08:03 -0700
Subject: [PATCH 1171/1189] vfs: mostly undo glibc turning 'fstat()' into
 'fstatat(AT_EMPTY_PATH)'

Mateusz reports that glibc turns 'fstat()' calls into 'fstatat()', and
that seems to have been going on for quite a long time due to glibc
having tried to simplify its stat logic into just one point.

This turns out to cause completely unnecessary overhead, where we then
go off and allocate the kernel side pathname, and actually look up the
empty path.  Sure, our path lookup is quite optimized, but it still
causes a fair bit of allocation overhead and a couple of completely
unnecessary rounds of lockref accesses etc.

This is all hopefully getting fixed in user space, and there is a patch
floating around for just having glibc use the native fstat() system
call.  But even with the current situation we can at least improve on
things by catching the situation and short-circuiting it.

Note that this is still measurably slower than just a plain 'fstat()',
since just checking that the filename is actually empty is somewhat
expensive due to inevitable user space access overhead from the kernel
(ie verifying pointers, and SMAP on x86).  But it's still quite a bit
faster than actually looking up the path for real.

To quote numers from Mateusz:
 "Sapphire Rapids, will-it-scale, ops/s

  stock fstat	5088199
  patched fstat	7625244	(+49%)
  real fstat	8540383	(+67% / +12%)"

where that 'stock fstat' is the glibc translation of fstat into
fstatat() with an empty path, the 'patched fstat' is with this short
circuiting of the path lookup, and the 'real fstat' is the actual native
fstat() system call with none of this overhead.

Link: https://lore.kernel.org/lkml/20230903204858.lv7i3kqvw6eamhgz@f/
Reported-by: Mateusz Guzik <mjguzik@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/stat.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/fs/stat.c b/fs/stat.c
index 136711ae72fb..6822ac77aec2 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -311,6 +311,23 @@ int vfs_fstatat(int dfd, const char __user *filename,
 	int statx_flags = flags | AT_NO_AUTOMOUNT;
 	struct filename *name;
 
+	/*
+	 * Work around glibc turning fstat() into fstatat(AT_EMPTY_PATH)
+	 *
+	 * If AT_EMPTY_PATH is set, we expect the common case to be that
+	 * empty path, and avoid doing all the extra pathname work.
+	 */
+	if (dfd >= 0 && flags == AT_EMPTY_PATH) {
+		char c;
+
+		ret = get_user(c, filename);
+		if (unlikely(ret))
+			return ret;
+
+		if (likely(!c))
+			return vfs_fstat(dfd, stat);
+	}
+
 	name = getname_flags(filename, getname_statx_lookup_flags(statx_flags), NULL);
 	ret = vfs_statx(dfd, name, statx_flags, stat, STATX_BASIC_STATS);
 	putname(name);

From 78a06688a4d40d9bb6138e2b9ad3353d7bf0157a Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Thu, 7 Sep 2023 18:03:40 +0200
Subject: [PATCH 1172/1189] ntfs3: drop inode references in ntfs_put_super()

Recently we moved most cleanup from ntfs_put_super() into
ntfs3_kill_sb() as part of a bigger cleanup.  This accidently also moved
dropping inode references stashed in ntfs3's sb->s_fs_info from
@sb->put_super() to @sb->kill_sb().  But generic_shutdown_super()
verifies that there are no busy inodes past sb->put_super().  Fix this
and disentangle dropping inode references from freeing @sb->s_fs_info.

Fixes: a4f64a300a29 ("ntfs3: free the sbi in ->kill_sb") # mainline only
Reported-by: Guenter Roeck <linux@roeck-us.net>
Tested-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/ntfs3/super.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
index 5fffddea554f..cfec5e0c7f66 100644
--- a/fs/ntfs3/super.c
+++ b/fs/ntfs3/super.c
@@ -571,12 +571,8 @@ static void init_once(void *foo)
 /*
  * Noinline to reduce binary size.
  */
-static noinline void ntfs3_free_sbi(struct ntfs_sb_info *sbi)
+static noinline void ntfs3_put_sbi(struct ntfs_sb_info *sbi)
 {
-	kfree(sbi->new_rec);
-	kvfree(ntfs_put_shared(sbi->upcase));
-	kfree(sbi->def_table);
-
 	wnd_close(&sbi->mft.bitmap);
 	wnd_close(&sbi->used.bitmap);
 
@@ -601,6 +597,13 @@ static noinline void ntfs3_free_sbi(struct ntfs_sb_info *sbi)
 	indx_clear(&sbi->security.index_sdh);
 	indx_clear(&sbi->reparse.index_r);
 	indx_clear(&sbi->objid.index_o);
+}
+
+static void ntfs3_free_sbi(struct ntfs_sb_info *sbi)
+{
+	kfree(sbi->new_rec);
+	kvfree(ntfs_put_shared(sbi->upcase));
+	kfree(sbi->def_table);
 	kfree(sbi->compress.lznt);
 #ifdef CONFIG_NTFS3_LZX_XPRESS
 	xpress_free_decompressor(sbi->compress.xpress);
@@ -625,6 +628,7 @@ static void ntfs_put_super(struct super_block *sb)
 
 	/* Mark rw ntfs as clear, if possible. */
 	ntfs_set_state(sbi, NTFS_DIRTY_CLEAR);
+	ntfs3_put_sbi(sbi);
 }
 
 static int ntfs_statfs(struct dentry *dentry, struct kstatfs *buf)
@@ -1644,8 +1648,10 @@ static void ntfs_fs_free(struct fs_context *fc)
 	struct ntfs_mount_options *opts = fc->fs_private;
 	struct ntfs_sb_info *sbi = fc->s_fs_info;
 
-	if (sbi)
+	if (sbi) {
+		ntfs3_put_sbi(sbi);
 		ntfs3_free_sbi(sbi);
+	}
 
 	if (opts)
 		put_mount_options(opts);

From 6afcf0fb92701487421aa73c692855aa70fbc796 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 7 Sep 2023 11:01:04 -0700
Subject: [PATCH 1173/1189] Revert "net: team: do not use dynamic lockdep key"

This reverts commit 39285e124edbc752331e98ace37cc141a6a3747a.

Looks like the change has unintended consequences in exposing
objects before they are initialized. Let's drop this patch
and try again in net-next.

Reported-by: syzbot+44ae022028805f4600fc@syzkaller.appspotmail.com
Fixes: 39285e124edb ("net: team: do not use dynamic lockdep key")
Link: https://lore.kernel.org/all/20230907103124.6adb7256@kernel.org/
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/team/team.c                  | 113 ++++++++++++-----------
 drivers/net/team/team_mode_loadbalance.c |   4 +-
 include/linux/if_team.h                  |  30 +-----
 3 files changed, 61 insertions(+), 86 deletions(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index ad29122a5468..e8b94580194e 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1135,8 +1135,8 @@ static int team_port_add(struct team *team, struct net_device *port_dev,
 			 struct netlink_ext_ack *extack)
 {
 	struct net_device *dev = team->dev;
-	char *portname = port_dev->name;
 	struct team_port *port;
+	char *portname = port_dev->name;
 	int err;
 
 	if (port_dev->flags & IFF_LOOPBACK) {
@@ -1203,26 +1203,6 @@ static int team_port_add(struct team *team, struct net_device *port_dev,
 
 	memcpy(port->orig.dev_addr, port_dev->dev_addr, port_dev->addr_len);
 
-	err = dev_open(port_dev, extack);
-	if (err) {
-		netdev_dbg(dev, "Device %s opening failed\n",
-			   portname);
-		goto err_dev_open;
-	}
-
-	err = team_upper_dev_link(team, port, extack);
-	if (err) {
-		netdev_err(dev, "Device %s failed to set upper link\n",
-			   portname);
-		goto err_set_upper_link;
-	}
-
-	/* lockdep subclass variable(dev->nested_level) was updated by
-	 * team_upper_dev_link().
-	 */
-	team_unlock(team);
-	team_lock(team);
-
 	err = team_port_enter(team, port);
 	if (err) {
 		netdev_err(dev, "Device %s failed to enter team mode\n",
@@ -1230,6 +1210,13 @@ static int team_port_add(struct team *team, struct net_device *port_dev,
 		goto err_port_enter;
 	}
 
+	err = dev_open(port_dev, extack);
+	if (err) {
+		netdev_dbg(dev, "Device %s opening failed\n",
+			   portname);
+		goto err_dev_open;
+	}
+
 	err = vlan_vids_add_by_dev(port_dev, dev);
 	if (err) {
 		netdev_err(dev, "Failed to add vlan ids to device %s\n",
@@ -1255,6 +1242,13 @@ static int team_port_add(struct team *team, struct net_device *port_dev,
 		goto err_handler_register;
 	}
 
+	err = team_upper_dev_link(team, port, extack);
+	if (err) {
+		netdev_err(dev, "Device %s failed to set upper link\n",
+			   portname);
+		goto err_set_upper_link;
+	}
+
 	err = __team_option_inst_add_port(team, port);
 	if (err) {
 		netdev_err(dev, "Device %s failed to add per-port options\n",
@@ -1301,6 +1295,9 @@ err_set_slave_promisc:
 	__team_option_inst_del_port(team, port);
 
 err_option_port_add:
+	team_upper_dev_unlink(team, port);
+
+err_set_upper_link:
 	netdev_rx_handler_unregister(port_dev);
 
 err_handler_register:
@@ -1310,16 +1307,13 @@ err_enable_netpoll:
 	vlan_vids_del_by_dev(port_dev, dev);
 
 err_vids_add:
-	team_port_leave(team, port);
-
-err_port_enter:
-	team_upper_dev_unlink(team, port);
-
-err_set_upper_link:
 	dev_close(port_dev);
 
 err_dev_open:
+	team_port_leave(team, port);
 	team_port_set_orig_dev_addr(port);
+
+err_port_enter:
 	dev_set_mtu(port_dev, port->orig.mtu);
 
 err_set_mtu:
@@ -1622,7 +1616,6 @@ static int team_init(struct net_device *dev)
 	int err;
 
 	team->dev = dev;
-	mutex_init(&team->lock);
 	team_set_no_mode(team);
 	team->notifier_ctx = false;
 
@@ -1650,6 +1643,8 @@ static int team_init(struct net_device *dev)
 		goto err_options_register;
 	netif_carrier_off(dev);
 
+	lockdep_register_key(&team->team_lock_key);
+	__mutex_init(&team->lock, "team->team_lock_key", &team->team_lock_key);
 	netdev_lockdep_set_classes(dev);
 
 	return 0;
@@ -1670,7 +1665,7 @@ static void team_uninit(struct net_device *dev)
 	struct team_port *port;
 	struct team_port *tmp;
 
-	team_lock(team);
+	mutex_lock(&team->lock);
 	list_for_each_entry_safe(port, tmp, &team->port_list, list)
 		team_port_del(team, port->dev);
 
@@ -1679,8 +1674,9 @@ static void team_uninit(struct net_device *dev)
 	team_mcast_rejoin_fini(team);
 	team_notify_peers_fini(team);
 	team_queue_override_fini(team);
-	team_unlock(team);
+	mutex_unlock(&team->lock);
 	netdev_change_features(dev);
+	lockdep_unregister_key(&team->team_lock_key);
 }
 
 static void team_destructor(struct net_device *dev)
@@ -1794,18 +1790,18 @@ static void team_set_rx_mode(struct net_device *dev)
 
 static int team_set_mac_address(struct net_device *dev, void *p)
 {
-	struct team *team = netdev_priv(dev);
 	struct sockaddr *addr = p;
+	struct team *team = netdev_priv(dev);
 	struct team_port *port;
 
 	if (dev->type == ARPHRD_ETHER && !is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 	dev_addr_set(dev, addr->sa_data);
-	team_lock(team);
+	mutex_lock(&team->lock);
 	list_for_each_entry(port, &team->port_list, list)
 		if (team->ops.port_change_dev_addr)
 			team->ops.port_change_dev_addr(team, port);
-	team_unlock(team);
+	mutex_unlock(&team->lock);
 	return 0;
 }
 
@@ -1819,7 +1815,7 @@ static int team_change_mtu(struct net_device *dev, int new_mtu)
 	 * Alhough this is reader, it's guarded by team lock. It's not possible
 	 * to traverse list in reverse under rcu_read_lock
 	 */
-	team_lock(team);
+	mutex_lock(&team->lock);
 	team->port_mtu_change_allowed = true;
 	list_for_each_entry(port, &team->port_list, list) {
 		err = dev_set_mtu(port->dev, new_mtu);
@@ -1830,7 +1826,7 @@ static int team_change_mtu(struct net_device *dev, int new_mtu)
 		}
 	}
 	team->port_mtu_change_allowed = false;
-	team_unlock(team);
+	mutex_unlock(&team->lock);
 
 	dev->mtu = new_mtu;
 
@@ -1840,7 +1836,7 @@ unwind:
 	list_for_each_entry_continue_reverse(port, &team->port_list, list)
 		dev_set_mtu(port->dev, dev->mtu);
 	team->port_mtu_change_allowed = false;
-	team_unlock(team);
+	mutex_unlock(&team->lock);
 
 	return err;
 }
@@ -1894,20 +1890,20 @@ static int team_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid)
 	 * Alhough this is reader, it's guarded by team lock. It's not possible
 	 * to traverse list in reverse under rcu_read_lock
 	 */
-	team_lock(team);
+	mutex_lock(&team->lock);
 	list_for_each_entry(port, &team->port_list, list) {
 		err = vlan_vid_add(port->dev, proto, vid);
 		if (err)
 			goto unwind;
 	}
-	team_unlock(team);
+	mutex_unlock(&team->lock);
 
 	return 0;
 
 unwind:
 	list_for_each_entry_continue_reverse(port, &team->port_list, list)
 		vlan_vid_del(port->dev, proto, vid);
-	team_unlock(team);
+	mutex_unlock(&team->lock);
 
 	return err;
 }
@@ -1917,10 +1913,10 @@ static int team_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid)
 	struct team *team = netdev_priv(dev);
 	struct team_port *port;
 
-	team_lock(team);
+	mutex_lock(&team->lock);
 	list_for_each_entry(port, &team->port_list, list)
 		vlan_vid_del(port->dev, proto, vid);
-	team_unlock(team);
+	mutex_unlock(&team->lock);
 
 	return 0;
 }
@@ -1942,9 +1938,9 @@ static void team_netpoll_cleanup(struct net_device *dev)
 {
 	struct team *team = netdev_priv(dev);
 
-	team_lock(team);
+	mutex_lock(&team->lock);
 	__team_netpoll_cleanup(team);
-	team_unlock(team);
+	mutex_unlock(&team->lock);
 }
 
 static int team_netpoll_setup(struct net_device *dev,
@@ -1954,7 +1950,7 @@ static int team_netpoll_setup(struct net_device *dev,
 	struct team_port *port;
 	int err = 0;
 
-	team_lock(team);
+	mutex_lock(&team->lock);
 	list_for_each_entry(port, &team->port_list, list) {
 		err = __team_port_enable_netpoll(port);
 		if (err) {
@@ -1962,7 +1958,7 @@ static int team_netpoll_setup(struct net_device *dev,
 			break;
 		}
 	}
-	team_unlock(team);
+	mutex_unlock(&team->lock);
 	return err;
 }
 #endif
@@ -1973,9 +1969,9 @@ static int team_add_slave(struct net_device *dev, struct net_device *port_dev,
 	struct team *team = netdev_priv(dev);
 	int err;
 
-	team_lock(team);
+	mutex_lock(&team->lock);
 	err = team_port_add(team, port_dev, extack);
-	team_unlock(team);
+	mutex_unlock(&team->lock);
 
 	if (!err)
 		netdev_change_features(dev);
@@ -1988,12 +1984,19 @@ static int team_del_slave(struct net_device *dev, struct net_device *port_dev)
 	struct team *team = netdev_priv(dev);
 	int err;
 
-	team_lock(team);
+	mutex_lock(&team->lock);
 	err = team_port_del(team, port_dev);
-	team_unlock(team);
+	mutex_unlock(&team->lock);
 
-	if (!err)
-		netdev_change_features(dev);
+	if (err)
+		return err;
+
+	if (netif_is_team_master(port_dev)) {
+		lockdep_unregister_key(&team->team_lock_key);
+		lockdep_register_key(&team->team_lock_key);
+		lockdep_set_class(&team->lock, &team->team_lock_key);
+	}
+	netdev_change_features(dev);
 
 	return err;
 }
@@ -2313,13 +2316,13 @@ static struct team *team_nl_team_get(struct genl_info *info)
 	}
 
 	team = netdev_priv(dev);
-	__team_lock(team);
+	mutex_lock(&team->lock);
 	return team;
 }
 
 static void team_nl_team_put(struct team *team)
 {
-	team_unlock(team);
+	mutex_unlock(&team->lock);
 	dev_put(team->dev);
 }
 
@@ -2981,9 +2984,9 @@ static void team_port_change_check(struct team_port *port, bool linkup)
 {
 	struct team *team = port->team;
 
-	team_lock(team);
+	mutex_lock(&team->lock);
 	__team_port_change_check(port, linkup);
-	team_unlock(team);
+	mutex_unlock(&team->lock);
 }
 
 
diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c
index 7bcc9d37447a..00f8989c29c0 100644
--- a/drivers/net/team/team_mode_loadbalance.c
+++ b/drivers/net/team/team_mode_loadbalance.c
@@ -478,7 +478,7 @@ static void lb_stats_refresh(struct work_struct *work)
 	team = lb_priv_ex->team;
 	lb_priv = get_lb_priv(team);
 
-	if (!team_trylock(team)) {
+	if (!mutex_trylock(&team->lock)) {
 		schedule_delayed_work(&lb_priv_ex->stats.refresh_dw, 0);
 		return;
 	}
@@ -515,7 +515,7 @@ static void lb_stats_refresh(struct work_struct *work)
 	schedule_delayed_work(&lb_priv_ex->stats.refresh_dw,
 			      (lb_priv_ex->stats.refresh_interval * HZ) / 10);
 
-	team_unlock(team);
+	mutex_unlock(&team->lock);
 }
 
 static void lb_stats_refresh_interval_get(struct team *team,
diff --git a/include/linux/if_team.h b/include/linux/if_team.h
index 12d4447fc8ab..1b9b15a492fa 100644
--- a/include/linux/if_team.h
+++ b/include/linux/if_team.h
@@ -221,38 +221,10 @@ struct team {
 		atomic_t count_pending;
 		struct delayed_work dw;
 	} mcast_rejoin;
+	struct lock_class_key team_lock_key;
 	long mode_priv[TEAM_MODE_PRIV_LONGS];
 };
 
-static inline void __team_lock(struct team *team)
-{
-	mutex_lock(&team->lock);
-}
-
-static inline int team_trylock(struct team *team)
-{
-	return mutex_trylock(&team->lock);
-}
-
-#ifdef CONFIG_LOCKDEP
-static inline void team_lock(struct team *team)
-{
-	ASSERT_RTNL();
-	mutex_lock_nested(&team->lock, team->dev->nested_level);
-}
-
-#else
-static inline void team_lock(struct team *team)
-{
-	__team_lock(team);
-}
-#endif
-
-static inline void team_unlock(struct team *team)
-{
-	mutex_unlock(&team->lock);
-}
-
 static inline int team_dev_queue_xmit(struct team *team, struct team_port *port,
 				      struct sk_buff *skb)
 {

From 1b36955cc048c8ff6ba448dbf4be0e52f59f2963 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Wed, 6 Sep 2023 17:16:09 +0300
Subject: [PATCH 1174/1189] net: enetc: distinguish error from valid pointers
 in enetc_fixup_clear_rss_rfs()

enetc_psi_create() returns an ERR_PTR() or a valid station interface
pointer, but checking for the non-NULL quality of the return code blurs
that difference away. So if enetc_psi_create() fails, we call
enetc_psi_destroy() when we shouldn't. This will likely result in
crashes, since enetc_psi_create() cleans up everything after itself when
it returns an ERR_PTR().

Fixes: f0168042a212 ("net: enetc: reimplement RFS/RSS memory clearing as PCI quirk")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/netdev/582183ef-e03b-402b-8e2d-6d9bb3c83bd9@moroto.mountain/
Suggested-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230906141609.247579-1-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc_pf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index e0a4cb7e3f50..c153dc083aff 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -1402,7 +1402,7 @@ static void enetc_fixup_clear_rss_rfs(struct pci_dev *pdev)
 		return;
 
 	si = enetc_psi_create(pdev);
-	if (si)
+	if (!IS_ERR(si))
 		enetc_psi_destroy(pdev);
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_FREESCALE, ENETC_DEV_ID_PF,

From f875db4f20f4ec2e4fa3b3be0e5081976e0b5dad Mon Sep 17 00:00:00 2001
From: Zhenhua Huang <quic_zhenhuah@quicinc.com>
Date: Thu, 7 Sep 2023 16:03:56 +0800
Subject: [PATCH 1175/1189] Revert "dma-contiguous: check for memory region
 overlap"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reverts commit 3fa6456ebe13adab3ba1817c8e515a5b88f95dce.

The Commit broke the CMA region creation through DT on arm64,
as showed below logs with "memblock=debug":
[    0.000000] memblock_phys_alloc_range: 41943040 bytes align=0x200000
from=0x0000000000000000 max_addr=0x00000000ffffffff
early_init_dt_alloc_reserved_memory_arch+0x34/0xa0
[    0.000000] memblock_reserve: [0x00000000fd600000-0x00000000ffdfffff]
memblock_alloc_range_nid+0xc0/0x19c
[    0.000000] Reserved memory: overlap with other memblock reserved region

>From call flow, region we defined in DT was always reserved before entering
into rmem_cma_setup. Also, rmem_cma_setup has one routine cma_init_reserved_mem
to ensure the region was reserved. Checking the region not reserved here seems
not correct.

early_init_fdt_scan_reserved_mem:
    fdt_scan_reserved_mem
        __reserved_mem_reserve_reg
		early_init_dt_reserve_memory
			memblock_reserve(using “reg” prop case)
        fdt_init_reserved_mem
		__reserved_mem_alloc_size
			*early_init_dt_alloc_reserved_memory_arch*
				memblock_reserve(dynamic alloc case)
        __reserved_mem_init_node
		rmem_cma_setup(region overlap check here should always fail)

Example DT can be used to reproduce issue:

    dump_mem: mem_dump_region {
            compatible = "shared-dma-pool";
            alloc-ranges = <0x0 0x00000000 0x0 0xffffffff>;
            reusable;
            size = <0 0x2800000>;
    };

Signed-off-by: Zhenhua Huang <quic_zhenhuah@quicinc.com>
---
 kernel/dma/contiguous.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 88c595e49e34..f005c66f378c 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -473,11 +473,6 @@ static int __init rmem_cma_setup(struct reserved_mem *rmem)
 		return -EBUSY;
 	}
 
-	if (memblock_is_region_reserved(rmem->base, rmem->size)) {
-		pr_info("Reserved memory: overlap with other memblock reserved region\n");
-		return -EBUSY;
-	}
-
 	if (!of_get_flat_dt_prop(node, "reusable", NULL) ||
 	    of_get_flat_dt_prop(node, "no-map", NULL))
 		return -EINVAL;

From e7ddd00eb3752b109e24eee19cb6b7421059d4db Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Fri, 1 Sep 2023 11:51:11 +0100
Subject: [PATCH 1176/1189] riscv: Kconfig: Select DMA_DIRECT_REMAP only if MMU
 is enabled

kernel/dma/mapping.c has its use of pgprot_dmacoherent() inside
an #ifdef CONFIG_MMU block. kernel/dma/pool.c has its use of
pgprot_dmacoherent() inside an #ifdef CONFIG_DMA_DIRECT_REMAP block.
So select DMA_DIRECT_REMAP only if MMU is enabled for RISCV_DMA_NONCOHERENT
config.

This avoids users to explicitly select MMU.

Suggested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Link: https://lore.kernel.org/r/20230901105111.311200-1-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 712ae0269131..d607ab0f7c6d 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -273,7 +273,7 @@ config RISCV_DMA_NONCOHERENT
 	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select DMA_BOUNCE_UNALIGNED_KMALLOC if SWIOTLB
-	select DMA_DIRECT_REMAP
+	select DMA_DIRECT_REMAP if MMU
 
 config RISCV_NONSTANDARD_CACHE_OPS
 	bool

From 54adc24c9a8f6e602f7e9d716107814d10281f8d Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Fri, 1 Sep 2023 11:58:58 +0100
Subject: [PATCH 1177/1189] riscv: Kconfig.errata: Drop dependency for MMU in
 ERRATA_ANDES_CMO config

Now that RISCV_DMA_NONCOHERENT conditionally selects DMA_DIRECT_REMAP
ie only if MMU is enabled, we no longer need the MMU dependency in
ERRATA_ANDES_CMO config.

Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20230901105858.311745-1-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig.errata | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/Kconfig.errata b/arch/riscv/Kconfig.errata
index 92c779764b27..bee5d838763b 100644
--- a/arch/riscv/Kconfig.errata
+++ b/arch/riscv/Kconfig.errata
@@ -12,7 +12,7 @@ config ERRATA_ANDES
 
 config ERRATA_ANDES_CMO
 	bool "Apply Andes cache management errata"
-	depends on ERRATA_ANDES && MMU && ARCH_R9A07G043
+	depends on ERRATA_ANDES && ARCH_R9A07G043
 	select RISCV_DMA_NONCOHERENT
 	default y
 	help

From 2f73b35d79d06f5354c859c31e5946391efc45c8 Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Fri, 1 Sep 2023 12:03:20 +0100
Subject: [PATCH 1178/1189] riscv: Kconfig.errata: Add dependency for RISCV_SBI
 in ERRATA_ANDES config

Andes errata uses sbi_ecalll() which is only available if RISCV_SBI is
enabled. So add an dependency for RISCV_SBI in ERRATA_ANDES config to
avoid any build failures.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202308311610.ec6bm2G8-lkp@intel.com/
Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://lore.kernel.org/r/20230901110320.312674-1-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig.errata | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/Kconfig.errata b/arch/riscv/Kconfig.errata
index bee5d838763b..566bcefeab50 100644
--- a/arch/riscv/Kconfig.errata
+++ b/arch/riscv/Kconfig.errata
@@ -2,7 +2,7 @@ menu "CPU errata selection"
 
 config ERRATA_ANDES
 	bool "Andes AX45MP errata"
-	depends on RISCV_ALTERNATIVE
+	depends on RISCV_ALTERNATIVE && RISCV_SBI
 	help
 	  All Andes errata Kconfig depend on this Kconfig. Disabling
 	  this Kconfig will disable all Andes errata. Please say "Y"

From c6a906cce61a8015b622707f9c12003f90673399 Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Fri, 1 Sep 2023 12:09:36 +0100
Subject: [PATCH 1179/1189] soc: renesas: Kconfig: For ARCH_R9A07G043 select
 the required configs if dependencies are met

To prevent randconfig build issues when enabling the RZ/Five SoC, consider
selecting specific configurations only when their dependencies are
satisfied.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202308311610.ec6bm2G8-lkp@intel.com/
Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Fixes: 484861e09f3e ("soc: renesas: Kconfig: Select the required configs for RZ/Five SoC")
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20230901110936.313171-1-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 drivers/soc/renesas/Kconfig | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/soc/renesas/Kconfig b/drivers/soc/renesas/Kconfig
index 67604f24973e..5a75ab64d1ed 100644
--- a/drivers/soc/renesas/Kconfig
+++ b/drivers/soc/renesas/Kconfig
@@ -334,10 +334,11 @@ if RISCV
 config ARCH_R9A07G043
 	bool "RISC-V Platform support for RZ/Five"
 	select ARCH_RZG2L
-	select AX45MP_L2_CACHE
+	select AX45MP_L2_CACHE if RISCV_DMA_NONCOHERENT
 	select DMA_GLOBAL_POOL
-	select ERRATA_ANDES
-	select ERRATA_ANDES_CMO
+	select ERRATA_ANDES if RISCV_SBI
+	select ERRATA_ANDES_CMO if ERRATA_ANDES
+
 	help
 	  This enables support for the Renesas RZ/Five SoC.
 

From 5260bd6d36c83c5b269c33baaaf8c78e520908b0 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Fri, 8 Sep 2023 14:55:30 -0500
Subject: [PATCH 1180/1189] Revert "PCI: Mark NVIDIA T4 GPUs to avoid bus
 reset"

This reverts commit d5af729dc2071273f14cbb94abbc60608142fd83.

d5af729dc207 ("PCI: Mark NVIDIA T4 GPUs to avoid bus reset") avoided
Secondary Bus Reset on the T4 because the reset seemed to not work when the
T4 was directly attached to a Root Port.

But NVIDIA thinks the issue is probably related to some issue with the Root
Port, not with the T4.  The T4 provides neither PM nor FLR reset, so
masking bus reset compromises this device for assignment scenarios.

Revert d5af729dc207 as requested by Wu Zongyong.  This will leave SBR
broken in the specific configuration Wu tested, as it was in v6.5, so Wu
will debug that further.

Link: https://lore.kernel.org/r/ZPqMCDWvITlOLHgJ@wuzongyong-alibaba
Link: https://lore.kernel.org/r/20230908201104.GA305023@bhelgaas
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/quirks.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 5de09d2eb014..eeec1d6f9023 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -3726,7 +3726,7 @@ static void quirk_no_bus_reset(struct pci_dev *dev)
  */
 static void quirk_nvidia_no_bus_reset(struct pci_dev *dev)
 {
-	if ((dev->device & 0xffc0) == 0x2340 || dev->device == 0x1eb8)
+	if ((dev->device & 0xffc0) == 0x2340)
 		quirk_no_bus_reset(dev);
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID,

From 702c390bc8cc84a486e677dfd76c3917cd244d30 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Fri, 8 Sep 2023 15:48:57 -0500
Subject: [PATCH 1181/1189] smb3: fix minor typo in SMB2_GLOBAL_CAP_LARGE_MTU

There was a minor typo in the define for SMB2_GLOBAL_CAP_LARGE_MTU
      0X00000004 instead of 0x00000004
make it consistent

Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/common/smb2pdu.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h
index 2680251b9aac..319fb9ffc6a0 100644
--- a/fs/smb/common/smb2pdu.h
+++ b/fs/smb/common/smb2pdu.h
@@ -406,7 +406,7 @@ struct smb2_tree_disconnect_rsp {
 /* Capabilities flags */
 #define SMB2_GLOBAL_CAP_DFS		0x00000001
 #define SMB2_GLOBAL_CAP_LEASING		0x00000002 /* Resp only New to SMB2.1 */
-#define SMB2_GLOBAL_CAP_LARGE_MTU	0X00000004 /* Resp only New to SMB2.1 */
+#define SMB2_GLOBAL_CAP_LARGE_MTU	0x00000004 /* Resp only New to SMB2.1 */
 #define SMB2_GLOBAL_CAP_MULTI_CHANNEL	0x00000008 /* New to SMB3 */
 #define SMB2_GLOBAL_CAP_PERSISTENT_HANDLES 0x00000010 /* New to SMB3 */
 #define SMB2_GLOBAL_CAP_DIRECTORY_LEASING  0x00000020 /* New to SMB3 */

From 86495af1171e1feec79faa9b64c05c89f46e41d1 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Fri, 8 Sep 2023 10:20:36 +0100
Subject: [PATCH 1182/1189] media: dvb: symbol fixup for dvb_attach()

In commit 9011e49d54dc ("modules: only allow symbol_get of
EXPORT_SYMBOL_GPL modules") the use of symbol_get is properly restricted
to GPL-only marked symbols.  This interacts oddly with the DVB logic
which only uses dvb_attach() to load the dvb driver which then uses
symbol_get().

Fix this up by properly marking all of the dvb_attach attach symbols as
EXPORT_SYMBOL_GPL().

Fixes: 9011e49d54dc ("modules: only allow symbol_get of EXPORT_SYMBOL_GPL modules")
Cc: stable <stable@kernel.org>
Reported-by: Stefan Lippers-Hollmann <s.l-h@gmx.de>
Cc: Mauro Carvalho Chehab <mchehab@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: linux-media@vger.kernel.org
Cc: linux-modules@vger.kernel.org
Acked-by: Luis Chamberlain <mcgrof@kernel.org>
Acked-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Link: https://lore.kernel.org/r/20230908092035.3815268-2-gregkh@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/media/dvb-frontends/ascot2e.c             | 2 +-
 drivers/media/dvb-frontends/atbm8830.c            | 2 +-
 drivers/media/dvb-frontends/au8522_dig.c          | 2 +-
 drivers/media/dvb-frontends/bcm3510.c             | 2 +-
 drivers/media/dvb-frontends/cx22700.c             | 2 +-
 drivers/media/dvb-frontends/cx22702.c             | 2 +-
 drivers/media/dvb-frontends/cx24110.c             | 2 +-
 drivers/media/dvb-frontends/cx24113.c             | 2 +-
 drivers/media/dvb-frontends/cx24116.c             | 2 +-
 drivers/media/dvb-frontends/cx24120.c             | 2 +-
 drivers/media/dvb-frontends/cx24123.c             | 2 +-
 drivers/media/dvb-frontends/cxd2820r_core.c       | 2 +-
 drivers/media/dvb-frontends/cxd2841er.c           | 4 ++--
 drivers/media/dvb-frontends/cxd2880/cxd2880_top.c | 2 +-
 drivers/media/dvb-frontends/dib0070.c             | 2 +-
 drivers/media/dvb-frontends/dib0090.c             | 4 ++--
 drivers/media/dvb-frontends/dib3000mb.c           | 2 +-
 drivers/media/dvb-frontends/dib3000mc.c           | 2 +-
 drivers/media/dvb-frontends/dib7000m.c            | 2 +-
 drivers/media/dvb-frontends/dib7000p.c            | 2 +-
 drivers/media/dvb-frontends/dib8000.c             | 2 +-
 drivers/media/dvb-frontends/dib9000.c             | 2 +-
 drivers/media/dvb-frontends/drx39xyj/drxj.c       | 2 +-
 drivers/media/dvb-frontends/drxd_hard.c           | 2 +-
 drivers/media/dvb-frontends/drxk_hard.c           | 2 +-
 drivers/media/dvb-frontends/ds3000.c              | 2 +-
 drivers/media/dvb-frontends/dvb-pll.c             | 2 +-
 drivers/media/dvb-frontends/ec100.c               | 2 +-
 drivers/media/dvb-frontends/helene.c              | 4 ++--
 drivers/media/dvb-frontends/horus3a.c             | 2 +-
 drivers/media/dvb-frontends/isl6405.c             | 2 +-
 drivers/media/dvb-frontends/isl6421.c             | 2 +-
 drivers/media/dvb-frontends/isl6423.c             | 2 +-
 drivers/media/dvb-frontends/itd1000.c             | 2 +-
 drivers/media/dvb-frontends/ix2505v.c             | 2 +-
 drivers/media/dvb-frontends/l64781.c              | 2 +-
 drivers/media/dvb-frontends/lg2160.c              | 2 +-
 drivers/media/dvb-frontends/lgdt3305.c            | 2 +-
 drivers/media/dvb-frontends/lgdt3306a.c           | 2 +-
 drivers/media/dvb-frontends/lgdt330x.c            | 2 +-
 drivers/media/dvb-frontends/lgs8gxx.c             | 2 +-
 drivers/media/dvb-frontends/lnbh25.c              | 2 +-
 drivers/media/dvb-frontends/lnbp21.c              | 4 ++--
 drivers/media/dvb-frontends/lnbp22.c              | 2 +-
 drivers/media/dvb-frontends/m88ds3103.c           | 2 +-
 drivers/media/dvb-frontends/m88rs2000.c           | 2 +-
 drivers/media/dvb-frontends/mb86a16.c             | 2 +-
 drivers/media/dvb-frontends/mb86a20s.c            | 2 +-
 drivers/media/dvb-frontends/mt312.c               | 2 +-
 drivers/media/dvb-frontends/mt352.c               | 2 +-
 drivers/media/dvb-frontends/nxt200x.c             | 2 +-
 drivers/media/dvb-frontends/nxt6000.c             | 2 +-
 drivers/media/dvb-frontends/or51132.c             | 2 +-
 drivers/media/dvb-frontends/or51211.c             | 2 +-
 drivers/media/dvb-frontends/s5h1409.c             | 2 +-
 drivers/media/dvb-frontends/s5h1411.c             | 2 +-
 drivers/media/dvb-frontends/s5h1420.c             | 2 +-
 drivers/media/dvb-frontends/s5h1432.c             | 2 +-
 drivers/media/dvb-frontends/s921.c                | 2 +-
 drivers/media/dvb-frontends/si21xx.c              | 2 +-
 drivers/media/dvb-frontends/sp887x.c              | 2 +-
 drivers/media/dvb-frontends/stb0899_drv.c         | 2 +-
 drivers/media/dvb-frontends/stb6000.c             | 2 +-
 drivers/media/dvb-frontends/stb6100.c             | 2 +-
 drivers/media/dvb-frontends/stv0288.c             | 2 +-
 drivers/media/dvb-frontends/stv0297.c             | 2 +-
 drivers/media/dvb-frontends/stv0299.c             | 2 +-
 drivers/media/dvb-frontends/stv0367.c             | 6 +++---
 drivers/media/dvb-frontends/stv0900_core.c        | 2 +-
 drivers/media/dvb-frontends/stv090x.c             | 2 +-
 drivers/media/dvb-frontends/stv6110.c             | 2 +-
 drivers/media/dvb-frontends/stv6110x.c            | 2 +-
 drivers/media/dvb-frontends/tda10021.c            | 2 +-
 drivers/media/dvb-frontends/tda10023.c            | 2 +-
 drivers/media/dvb-frontends/tda10048.c            | 2 +-
 drivers/media/dvb-frontends/tda1004x.c            | 4 ++--
 drivers/media/dvb-frontends/tda10086.c            | 2 +-
 drivers/media/dvb-frontends/tda665x.c             | 2 +-
 drivers/media/dvb-frontends/tda8083.c             | 2 +-
 drivers/media/dvb-frontends/tda8261.c             | 2 +-
 drivers/media/dvb-frontends/tda826x.c             | 2 +-
 drivers/media/dvb-frontends/ts2020.c              | 2 +-
 drivers/media/dvb-frontends/tua6100.c             | 2 +-
 drivers/media/dvb-frontends/ves1820.c             | 2 +-
 drivers/media/dvb-frontends/ves1x93.c             | 2 +-
 drivers/media/dvb-frontends/zl10036.c             | 2 +-
 drivers/media/dvb-frontends/zl10039.c             | 2 +-
 drivers/media/dvb-frontends/zl10353.c             | 2 +-
 drivers/media/pci/bt8xx/dst.c                     | 2 +-
 drivers/media/pci/bt8xx/dst_ca.c                  | 2 +-
 drivers/media/pci/ddbridge/ddbridge-dummy-fe.c    | 2 +-
 drivers/media/tuners/fc0011.c                     | 2 +-
 drivers/media/tuners/fc0012.c                     | 2 +-
 drivers/media/tuners/fc0013.c                     | 2 +-
 drivers/media/tuners/max2165.c                    | 2 +-
 drivers/media/tuners/mc44s803.c                   | 2 +-
 drivers/media/tuners/mt2060.c                     | 2 +-
 drivers/media/tuners/mt2131.c                     | 2 +-
 drivers/media/tuners/mt2266.c                     | 2 +-
 drivers/media/tuners/mxl5005s.c                   | 2 +-
 drivers/media/tuners/qt1010.c                     | 2 +-
 drivers/media/tuners/tda18218.c                   | 2 +-
 drivers/media/tuners/xc2028.c                     | 2 +-
 drivers/media/tuners/xc4000.c                     | 2 +-
 drivers/media/tuners/xc5000.c                     | 2 +-
 drivers/staging/media/av7110/sp8870.c             | 2 +-
 106 files changed, 113 insertions(+), 113 deletions(-)

diff --git a/drivers/media/dvb-frontends/ascot2e.c b/drivers/media/dvb-frontends/ascot2e.c
index 9b00b56230b6..cf8e5f1bd101 100644
--- a/drivers/media/dvb-frontends/ascot2e.c
+++ b/drivers/media/dvb-frontends/ascot2e.c
@@ -533,7 +533,7 @@ struct dvb_frontend *ascot2e_attach(struct dvb_frontend *fe,
 		priv->i2c_address, priv->i2c);
 	return fe;
 }
-EXPORT_SYMBOL(ascot2e_attach);
+EXPORT_SYMBOL_GPL(ascot2e_attach);
 
 MODULE_DESCRIPTION("Sony ASCOT2E terr/cab tuner driver");
 MODULE_AUTHOR("info@netup.ru");
diff --git a/drivers/media/dvb-frontends/atbm8830.c b/drivers/media/dvb-frontends/atbm8830.c
index bdd16b9c5824..778c865085bf 100644
--- a/drivers/media/dvb-frontends/atbm8830.c
+++ b/drivers/media/dvb-frontends/atbm8830.c
@@ -489,7 +489,7 @@ error_out:
 	return NULL;
 
 }
-EXPORT_SYMBOL(atbm8830_attach);
+EXPORT_SYMBOL_GPL(atbm8830_attach);
 
 MODULE_DESCRIPTION("AltoBeam ATBM8830/8831 GB20600 demodulator driver");
 MODULE_AUTHOR("David T. L. Wong <davidtlwong@gmail.com>");
diff --git a/drivers/media/dvb-frontends/au8522_dig.c b/drivers/media/dvb-frontends/au8522_dig.c
index 78cafdf27961..230436bf6cbd 100644
--- a/drivers/media/dvb-frontends/au8522_dig.c
+++ b/drivers/media/dvb-frontends/au8522_dig.c
@@ -879,7 +879,7 @@ error:
 	au8522_release_state(state);
 	return NULL;
 }
-EXPORT_SYMBOL(au8522_attach);
+EXPORT_SYMBOL_GPL(au8522_attach);
 
 static const struct dvb_frontend_ops au8522_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
diff --git a/drivers/media/dvb-frontends/bcm3510.c b/drivers/media/dvb-frontends/bcm3510.c
index 68b92b4419cf..b3f5c49accaf 100644
--- a/drivers/media/dvb-frontends/bcm3510.c
+++ b/drivers/media/dvb-frontends/bcm3510.c
@@ -835,7 +835,7 @@ error:
 	kfree(state);
 	return NULL;
 }
-EXPORT_SYMBOL(bcm3510_attach);
+EXPORT_SYMBOL_GPL(bcm3510_attach);
 
 static const struct dvb_frontend_ops bcm3510_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
diff --git a/drivers/media/dvb-frontends/cx22700.c b/drivers/media/dvb-frontends/cx22700.c
index b39ff516271b..1d04c0a652b2 100644
--- a/drivers/media/dvb-frontends/cx22700.c
+++ b/drivers/media/dvb-frontends/cx22700.c
@@ -432,4 +432,4 @@ MODULE_DESCRIPTION("Conexant CX22700 DVB-T Demodulator driver");
 MODULE_AUTHOR("Holger Waechtler");
 MODULE_LICENSE("GPL");
 
-EXPORT_SYMBOL(cx22700_attach);
+EXPORT_SYMBOL_GPL(cx22700_attach);
diff --git a/drivers/media/dvb-frontends/cx22702.c b/drivers/media/dvb-frontends/cx22702.c
index cc6acbf6393d..61ad34b7004b 100644
--- a/drivers/media/dvb-frontends/cx22702.c
+++ b/drivers/media/dvb-frontends/cx22702.c
@@ -604,7 +604,7 @@ error:
 	kfree(state);
 	return NULL;
 }
-EXPORT_SYMBOL(cx22702_attach);
+EXPORT_SYMBOL_GPL(cx22702_attach);
 
 static const struct dvb_frontend_ops cx22702_ops = {
 	.delsys = { SYS_DVBT },
diff --git a/drivers/media/dvb-frontends/cx24110.c b/drivers/media/dvb-frontends/cx24110.c
index 6f99d6a27be2..9aeea089756f 100644
--- a/drivers/media/dvb-frontends/cx24110.c
+++ b/drivers/media/dvb-frontends/cx24110.c
@@ -653,4 +653,4 @@ MODULE_DESCRIPTION("Conexant CX24110 DVB-S Demodulator driver");
 MODULE_AUTHOR("Peter Hettkamp");
 MODULE_LICENSE("GPL");
 
-EXPORT_SYMBOL(cx24110_attach);
+EXPORT_SYMBOL_GPL(cx24110_attach);
diff --git a/drivers/media/dvb-frontends/cx24113.c b/drivers/media/dvb-frontends/cx24113.c
index dd55d314bf9a..203cb6b3f941 100644
--- a/drivers/media/dvb-frontends/cx24113.c
+++ b/drivers/media/dvb-frontends/cx24113.c
@@ -590,7 +590,7 @@ error:
 
 	return NULL;
 }
-EXPORT_SYMBOL(cx24113_attach);
+EXPORT_SYMBOL_GPL(cx24113_attach);
 
 module_param(debug, int, 0644);
 MODULE_PARM_DESC(debug, "Activates frontend debugging (default:0)");
diff --git a/drivers/media/dvb-frontends/cx24116.c b/drivers/media/dvb-frontends/cx24116.c
index ea8264ccbb4e..8b978a9f74a4 100644
--- a/drivers/media/dvb-frontends/cx24116.c
+++ b/drivers/media/dvb-frontends/cx24116.c
@@ -1133,7 +1133,7 @@ struct dvb_frontend *cx24116_attach(const struct cx24116_config *config,
 	state->frontend.demodulator_priv = state;
 	return &state->frontend;
 }
-EXPORT_SYMBOL(cx24116_attach);
+EXPORT_SYMBOL_GPL(cx24116_attach);
 
 /*
  * Initialise or wake up device
diff --git a/drivers/media/dvb-frontends/cx24120.c b/drivers/media/dvb-frontends/cx24120.c
index 0f778660c72b..44515fdbe91d 100644
--- a/drivers/media/dvb-frontends/cx24120.c
+++ b/drivers/media/dvb-frontends/cx24120.c
@@ -305,7 +305,7 @@ error:
 	kfree(state);
 	return NULL;
 }
-EXPORT_SYMBOL(cx24120_attach);
+EXPORT_SYMBOL_GPL(cx24120_attach);
 
 static int cx24120_test_rom(struct cx24120_state *state)
 {
diff --git a/drivers/media/dvb-frontends/cx24123.c b/drivers/media/dvb-frontends/cx24123.c
index 3d84ee17e54c..539889e638cc 100644
--- a/drivers/media/dvb-frontends/cx24123.c
+++ b/drivers/media/dvb-frontends/cx24123.c
@@ -1096,7 +1096,7 @@ error:
 
 	return NULL;
 }
-EXPORT_SYMBOL(cx24123_attach);
+EXPORT_SYMBOL_GPL(cx24123_attach);
 
 static const struct dvb_frontend_ops cx24123_ops = {
 	.delsys = { SYS_DVBS },
diff --git a/drivers/media/dvb-frontends/cxd2820r_core.c b/drivers/media/dvb-frontends/cxd2820r_core.c
index d7ee294c6833..7feb08dccfa1 100644
--- a/drivers/media/dvb-frontends/cxd2820r_core.c
+++ b/drivers/media/dvb-frontends/cxd2820r_core.c
@@ -536,7 +536,7 @@ struct dvb_frontend *cxd2820r_attach(const struct cxd2820r_config *config,
 
 	return pdata.get_dvb_frontend(client);
 }
-EXPORT_SYMBOL(cxd2820r_attach);
+EXPORT_SYMBOL_GPL(cxd2820r_attach);
 
 static struct dvb_frontend *cxd2820r_get_dvb_frontend(struct i2c_client *client)
 {
diff --git a/drivers/media/dvb-frontends/cxd2841er.c b/drivers/media/dvb-frontends/cxd2841er.c
index ef403a9fb753..d925ca24183b 100644
--- a/drivers/media/dvb-frontends/cxd2841er.c
+++ b/drivers/media/dvb-frontends/cxd2841er.c
@@ -3930,14 +3930,14 @@ struct dvb_frontend *cxd2841er_attach_s(struct cxd2841er_config *cfg,
 {
 	return cxd2841er_attach(cfg, i2c, SYS_DVBS);
 }
-EXPORT_SYMBOL(cxd2841er_attach_s);
+EXPORT_SYMBOL_GPL(cxd2841er_attach_s);
 
 struct dvb_frontend *cxd2841er_attach_t_c(struct cxd2841er_config *cfg,
 					struct i2c_adapter *i2c)
 {
 	return cxd2841er_attach(cfg, i2c, 0);
 }
-EXPORT_SYMBOL(cxd2841er_attach_t_c);
+EXPORT_SYMBOL_GPL(cxd2841er_attach_t_c);
 
 static const struct dvb_frontend_ops cxd2841er_dvbs_s2_ops = {
 	.delsys = { SYS_DVBS, SYS_DVBS2 },
diff --git a/drivers/media/dvb-frontends/cxd2880/cxd2880_top.c b/drivers/media/dvb-frontends/cxd2880/cxd2880_top.c
index f67b6d24b8d4..a06d8368ca79 100644
--- a/drivers/media/dvb-frontends/cxd2880/cxd2880_top.c
+++ b/drivers/media/dvb-frontends/cxd2880/cxd2880_top.c
@@ -1950,7 +1950,7 @@ struct dvb_frontend *cxd2880_attach(struct dvb_frontend *fe,
 
 	return fe;
 }
-EXPORT_SYMBOL(cxd2880_attach);
+EXPORT_SYMBOL_GPL(cxd2880_attach);
 
 MODULE_DESCRIPTION("Sony CXD2880 DVB-T2/T tuner + demod driver");
 MODULE_AUTHOR("Sony Semiconductor Solutions Corporation");
diff --git a/drivers/media/dvb-frontends/dib0070.c b/drivers/media/dvb-frontends/dib0070.c
index cafb41dba861..9a8e7cdd2a24 100644
--- a/drivers/media/dvb-frontends/dib0070.c
+++ b/drivers/media/dvb-frontends/dib0070.c
@@ -762,7 +762,7 @@ free_mem:
 	fe->tuner_priv = NULL;
 	return NULL;
 }
-EXPORT_SYMBOL(dib0070_attach);
+EXPORT_SYMBOL_GPL(dib0070_attach);
 
 MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@posteo.de>");
 MODULE_DESCRIPTION("Driver for the DiBcom 0070 base-band RF Tuner");
diff --git a/drivers/media/dvb-frontends/dib0090.c b/drivers/media/dvb-frontends/dib0090.c
index 903da33642df..c958bcff026e 100644
--- a/drivers/media/dvb-frontends/dib0090.c
+++ b/drivers/media/dvb-frontends/dib0090.c
@@ -2634,7 +2634,7 @@ struct dvb_frontend *dib0090_register(struct dvb_frontend *fe, struct i2c_adapte
 	return NULL;
 }
 
-EXPORT_SYMBOL(dib0090_register);
+EXPORT_SYMBOL_GPL(dib0090_register);
 
 struct dvb_frontend *dib0090_fw_register(struct dvb_frontend *fe, struct i2c_adapter *i2c, const struct dib0090_config *config)
 {
@@ -2660,7 +2660,7 @@ free_mem:
 	fe->tuner_priv = NULL;
 	return NULL;
 }
-EXPORT_SYMBOL(dib0090_fw_register);
+EXPORT_SYMBOL_GPL(dib0090_fw_register);
 
 MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@posteo.de>");
 MODULE_AUTHOR("Olivier Grenie <olivier.grenie@parrot.com>");
diff --git a/drivers/media/dvb-frontends/dib3000mb.c b/drivers/media/dvb-frontends/dib3000mb.c
index a6c2fc4586eb..c598b2a63325 100644
--- a/drivers/media/dvb-frontends/dib3000mb.c
+++ b/drivers/media/dvb-frontends/dib3000mb.c
@@ -815,4 +815,4 @@ MODULE_AUTHOR(DRIVER_AUTHOR);
 MODULE_DESCRIPTION(DRIVER_DESC);
 MODULE_LICENSE("GPL");
 
-EXPORT_SYMBOL(dib3000mb_attach);
+EXPORT_SYMBOL_GPL(dib3000mb_attach);
diff --git a/drivers/media/dvb-frontends/dib3000mc.c b/drivers/media/dvb-frontends/dib3000mc.c
index 2e11a246aae0..c2fca8289aba 100644
--- a/drivers/media/dvb-frontends/dib3000mc.c
+++ b/drivers/media/dvb-frontends/dib3000mc.c
@@ -935,7 +935,7 @@ error:
 	kfree(st);
 	return NULL;
 }
-EXPORT_SYMBOL(dib3000mc_attach);
+EXPORT_SYMBOL_GPL(dib3000mc_attach);
 
 static const struct dvb_frontend_ops dib3000mc_ops = {
 	.delsys = { SYS_DVBT },
diff --git a/drivers/media/dvb-frontends/dib7000m.c b/drivers/media/dvb-frontends/dib7000m.c
index 97ce97789c9e..fdb22f32e3a1 100644
--- a/drivers/media/dvb-frontends/dib7000m.c
+++ b/drivers/media/dvb-frontends/dib7000m.c
@@ -1434,7 +1434,7 @@ error:
 	kfree(st);
 	return NULL;
 }
-EXPORT_SYMBOL(dib7000m_attach);
+EXPORT_SYMBOL_GPL(dib7000m_attach);
 
 static const struct dvb_frontend_ops dib7000m_ops = {
 	.delsys = { SYS_DVBT },
diff --git a/drivers/media/dvb-frontends/dib7000p.c b/drivers/media/dvb-frontends/dib7000p.c
index 9273758bf140..444fe1c4bf2d 100644
--- a/drivers/media/dvb-frontends/dib7000p.c
+++ b/drivers/media/dvb-frontends/dib7000p.c
@@ -2822,7 +2822,7 @@ void *dib7000p_attach(struct dib7000p_ops *ops)
 
 	return ops;
 }
-EXPORT_SYMBOL(dib7000p_attach);
+EXPORT_SYMBOL_GPL(dib7000p_attach);
 
 static const struct dvb_frontend_ops dib7000p_ops = {
 	.delsys = { SYS_DVBT },
diff --git a/drivers/media/dvb-frontends/dib8000.c b/drivers/media/dvb-frontends/dib8000.c
index 2abda7d1cb6e..2f5165918163 100644
--- a/drivers/media/dvb-frontends/dib8000.c
+++ b/drivers/media/dvb-frontends/dib8000.c
@@ -4527,7 +4527,7 @@ void *dib8000_attach(struct dib8000_ops *ops)
 
 	return ops;
 }
-EXPORT_SYMBOL(dib8000_attach);
+EXPORT_SYMBOL_GPL(dib8000_attach);
 
 MODULE_AUTHOR("Olivier Grenie <Olivier.Grenie@parrot.com, Patrick Boettcher <patrick.boettcher@posteo.de>");
 MODULE_DESCRIPTION("Driver for the DiBcom 8000 ISDB-T demodulator");
diff --git a/drivers/media/dvb-frontends/dib9000.c b/drivers/media/dvb-frontends/dib9000.c
index 1c57587a917a..83cf6eadd49c 100644
--- a/drivers/media/dvb-frontends/dib9000.c
+++ b/drivers/media/dvb-frontends/dib9000.c
@@ -2546,7 +2546,7 @@ error:
 	kfree(st);
 	return NULL;
 }
-EXPORT_SYMBOL(dib9000_attach);
+EXPORT_SYMBOL_GPL(dib9000_attach);
 
 static const struct dvb_frontend_ops dib9000_ops = {
 	.delsys = { SYS_DVBT },
diff --git a/drivers/media/dvb-frontends/drx39xyj/drxj.c b/drivers/media/dvb-frontends/drx39xyj/drxj.c
index 68f4e8b5a0ab..a738573c8cd7 100644
--- a/drivers/media/dvb-frontends/drx39xyj/drxj.c
+++ b/drivers/media/dvb-frontends/drx39xyj/drxj.c
@@ -12372,7 +12372,7 @@ error:
 
 	return NULL;
 }
-EXPORT_SYMBOL(drx39xxj_attach);
+EXPORT_SYMBOL_GPL(drx39xxj_attach);
 
 static const struct dvb_frontend_ops drx39xxj_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
diff --git a/drivers/media/dvb-frontends/drxd_hard.c b/drivers/media/dvb-frontends/drxd_hard.c
index 9860cae65f1c..6a531937f4bb 100644
--- a/drivers/media/dvb-frontends/drxd_hard.c
+++ b/drivers/media/dvb-frontends/drxd_hard.c
@@ -2939,7 +2939,7 @@ error:
 	kfree(state);
 	return NULL;
 }
-EXPORT_SYMBOL(drxd_attach);
+EXPORT_SYMBOL_GPL(drxd_attach);
 
 MODULE_DESCRIPTION("DRXD driver");
 MODULE_AUTHOR("Micronas");
diff --git a/drivers/media/dvb-frontends/drxk_hard.c b/drivers/media/dvb-frontends/drxk_hard.c
index 2770baebbbbc..87f3d4f0eb8c 100644
--- a/drivers/media/dvb-frontends/drxk_hard.c
+++ b/drivers/media/dvb-frontends/drxk_hard.c
@@ -6814,7 +6814,7 @@ error:
 	kfree(state);
 	return NULL;
 }
-EXPORT_SYMBOL(drxk_attach);
+EXPORT_SYMBOL_GPL(drxk_attach);
 
 MODULE_DESCRIPTION("DRX-K driver");
 MODULE_AUTHOR("Ralph Metzler");
diff --git a/drivers/media/dvb-frontends/ds3000.c b/drivers/media/dvb-frontends/ds3000.c
index 20fcf31af165..515aa7c7baf2 100644
--- a/drivers/media/dvb-frontends/ds3000.c
+++ b/drivers/media/dvb-frontends/ds3000.c
@@ -859,7 +859,7 @@ struct dvb_frontend *ds3000_attach(const struct ds3000_config *config,
 	ds3000_set_voltage(&state->frontend, SEC_VOLTAGE_OFF);
 	return &state->frontend;
 }
-EXPORT_SYMBOL(ds3000_attach);
+EXPORT_SYMBOL_GPL(ds3000_attach);
 
 static int ds3000_set_carrier_offset(struct dvb_frontend *fe,
 					s32 carrier_offset_khz)
diff --git a/drivers/media/dvb-frontends/dvb-pll.c b/drivers/media/dvb-frontends/dvb-pll.c
index 90cb41eacf98..ef697ab6bc2e 100644
--- a/drivers/media/dvb-frontends/dvb-pll.c
+++ b/drivers/media/dvb-frontends/dvb-pll.c
@@ -866,7 +866,7 @@ out:
 
 	return NULL;
 }
-EXPORT_SYMBOL(dvb_pll_attach);
+EXPORT_SYMBOL_GPL(dvb_pll_attach);
 
 
 static int
diff --git a/drivers/media/dvb-frontends/ec100.c b/drivers/media/dvb-frontends/ec100.c
index 03bd80666cf8..2ad0a3c2f756 100644
--- a/drivers/media/dvb-frontends/ec100.c
+++ b/drivers/media/dvb-frontends/ec100.c
@@ -299,7 +299,7 @@ error:
 	kfree(state);
 	return NULL;
 }
-EXPORT_SYMBOL(ec100_attach);
+EXPORT_SYMBOL_GPL(ec100_attach);
 
 static const struct dvb_frontend_ops ec100_ops = {
 	.delsys = { SYS_DVBT },
diff --git a/drivers/media/dvb-frontends/helene.c b/drivers/media/dvb-frontends/helene.c
index 68c1a3e0e2ba..f127adee3ebb 100644
--- a/drivers/media/dvb-frontends/helene.c
+++ b/drivers/media/dvb-frontends/helene.c
@@ -1025,7 +1025,7 @@ struct dvb_frontend *helene_attach_s(struct dvb_frontend *fe,
 			priv->i2c_address, priv->i2c);
 	return fe;
 }
-EXPORT_SYMBOL(helene_attach_s);
+EXPORT_SYMBOL_GPL(helene_attach_s);
 
 struct dvb_frontend *helene_attach(struct dvb_frontend *fe,
 		const struct helene_config *config,
@@ -1061,7 +1061,7 @@ struct dvb_frontend *helene_attach(struct dvb_frontend *fe,
 			priv->i2c_address, priv->i2c);
 	return fe;
 }
-EXPORT_SYMBOL(helene_attach);
+EXPORT_SYMBOL_GPL(helene_attach);
 
 static int helene_probe(struct i2c_client *client)
 {
diff --git a/drivers/media/dvb-frontends/horus3a.c b/drivers/media/dvb-frontends/horus3a.c
index 24bf5cbcc184..0330b78a5b3f 100644
--- a/drivers/media/dvb-frontends/horus3a.c
+++ b/drivers/media/dvb-frontends/horus3a.c
@@ -395,7 +395,7 @@ struct dvb_frontend *horus3a_attach(struct dvb_frontend *fe,
 		priv->i2c_address, priv->i2c);
 	return fe;
 }
-EXPORT_SYMBOL(horus3a_attach);
+EXPORT_SYMBOL_GPL(horus3a_attach);
 
 MODULE_DESCRIPTION("Sony HORUS3A satellite tuner driver");
 MODULE_AUTHOR("Sergey Kozlov <serjk@netup.ru>");
diff --git a/drivers/media/dvb-frontends/isl6405.c b/drivers/media/dvb-frontends/isl6405.c
index 2cd69b4ff82c..7d28a743f97e 100644
--- a/drivers/media/dvb-frontends/isl6405.c
+++ b/drivers/media/dvb-frontends/isl6405.c
@@ -141,7 +141,7 @@ struct dvb_frontend *isl6405_attach(struct dvb_frontend *fe, struct i2c_adapter
 
 	return fe;
 }
-EXPORT_SYMBOL(isl6405_attach);
+EXPORT_SYMBOL_GPL(isl6405_attach);
 
 MODULE_DESCRIPTION("Driver for lnb supply and control ic isl6405");
 MODULE_AUTHOR("Hartmut Hackmann & Oliver Endriss");
diff --git a/drivers/media/dvb-frontends/isl6421.c b/drivers/media/dvb-frontends/isl6421.c
index 43b0dfc6f453..2e9f6f12f849 100644
--- a/drivers/media/dvb-frontends/isl6421.c
+++ b/drivers/media/dvb-frontends/isl6421.c
@@ -213,7 +213,7 @@ struct dvb_frontend *isl6421_attach(struct dvb_frontend *fe, struct i2c_adapter
 
 	return fe;
 }
-EXPORT_SYMBOL(isl6421_attach);
+EXPORT_SYMBOL_GPL(isl6421_attach);
 
 MODULE_DESCRIPTION("Driver for lnb supply and control ic isl6421");
 MODULE_AUTHOR("Andrew de Quincey & Oliver Endriss");
diff --git a/drivers/media/dvb-frontends/isl6423.c b/drivers/media/dvb-frontends/isl6423.c
index 8cd1bb88ce6e..a0d0a3834057 100644
--- a/drivers/media/dvb-frontends/isl6423.c
+++ b/drivers/media/dvb-frontends/isl6423.c
@@ -289,7 +289,7 @@ exit:
 	fe->sec_priv = NULL;
 	return NULL;
 }
-EXPORT_SYMBOL(isl6423_attach);
+EXPORT_SYMBOL_GPL(isl6423_attach);
 
 MODULE_DESCRIPTION("ISL6423 SEC");
 MODULE_AUTHOR("Manu Abraham");
diff --git a/drivers/media/dvb-frontends/itd1000.c b/drivers/media/dvb-frontends/itd1000.c
index 1b33478653d1..f8f362f50e78 100644
--- a/drivers/media/dvb-frontends/itd1000.c
+++ b/drivers/media/dvb-frontends/itd1000.c
@@ -389,7 +389,7 @@ struct dvb_frontend *itd1000_attach(struct dvb_frontend *fe, struct i2c_adapter
 
 	return fe;
 }
-EXPORT_SYMBOL(itd1000_attach);
+EXPORT_SYMBOL_GPL(itd1000_attach);
 
 MODULE_AUTHOR("Patrick Boettcher <pb@linuxtv.org>");
 MODULE_DESCRIPTION("Integrant ITD1000 driver");
diff --git a/drivers/media/dvb-frontends/ix2505v.c b/drivers/media/dvb-frontends/ix2505v.c
index 73f27105c139..3212e333d472 100644
--- a/drivers/media/dvb-frontends/ix2505v.c
+++ b/drivers/media/dvb-frontends/ix2505v.c
@@ -302,7 +302,7 @@ error:
 	kfree(state);
 	return NULL;
 }
-EXPORT_SYMBOL(ix2505v_attach);
+EXPORT_SYMBOL_GPL(ix2505v_attach);
 
 module_param_named(debug, ix2505v_debug, int, 0644);
 MODULE_PARM_DESC(debug, "Turn on/off frontend debugging (default:off).");
diff --git a/drivers/media/dvb-frontends/l64781.c b/drivers/media/dvb-frontends/l64781.c
index c5106a1ea1cd..fe5af2453d55 100644
--- a/drivers/media/dvb-frontends/l64781.c
+++ b/drivers/media/dvb-frontends/l64781.c
@@ -593,4 +593,4 @@ MODULE_DESCRIPTION("LSI L64781 DVB-T Demodulator driver");
 MODULE_AUTHOR("Holger Waechtler, Marko Kohtala");
 MODULE_LICENSE("GPL");
 
-EXPORT_SYMBOL(l64781_attach);
+EXPORT_SYMBOL_GPL(l64781_attach);
diff --git a/drivers/media/dvb-frontends/lg2160.c b/drivers/media/dvb-frontends/lg2160.c
index f343066c297e..fe700aa56bff 100644
--- a/drivers/media/dvb-frontends/lg2160.c
+++ b/drivers/media/dvb-frontends/lg2160.c
@@ -1426,7 +1426,7 @@ struct dvb_frontend *lg2160_attach(const struct lg2160_config *config,
 
 	return &state->frontend;
 }
-EXPORT_SYMBOL(lg2160_attach);
+EXPORT_SYMBOL_GPL(lg2160_attach);
 
 MODULE_DESCRIPTION("LG Electronics LG216x ATSC/MH Demodulator Driver");
 MODULE_AUTHOR("Michael Krufky <mkrufky@linuxtv.org>");
diff --git a/drivers/media/dvb-frontends/lgdt3305.c b/drivers/media/dvb-frontends/lgdt3305.c
index c15d3735d34c..bdc8311e1c0b 100644
--- a/drivers/media/dvb-frontends/lgdt3305.c
+++ b/drivers/media/dvb-frontends/lgdt3305.c
@@ -1148,7 +1148,7 @@ fail:
 	kfree(state);
 	return NULL;
 }
-EXPORT_SYMBOL(lgdt3305_attach);
+EXPORT_SYMBOL_GPL(lgdt3305_attach);
 
 static const struct dvb_frontend_ops lgdt3304_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
diff --git a/drivers/media/dvb-frontends/lgdt3306a.c b/drivers/media/dvb-frontends/lgdt3306a.c
index 3c6650f6e9a3..263887592415 100644
--- a/drivers/media/dvb-frontends/lgdt3306a.c
+++ b/drivers/media/dvb-frontends/lgdt3306a.c
@@ -1859,7 +1859,7 @@ fail:
 	kfree(state);
 	return NULL;
 }
-EXPORT_SYMBOL(lgdt3306a_attach);
+EXPORT_SYMBOL_GPL(lgdt3306a_attach);
 
 #ifdef DBG_DUMP
 
diff --git a/drivers/media/dvb-frontends/lgdt330x.c b/drivers/media/dvb-frontends/lgdt330x.c
index 97a10996c7fa..081d6ad3ce72 100644
--- a/drivers/media/dvb-frontends/lgdt330x.c
+++ b/drivers/media/dvb-frontends/lgdt330x.c
@@ -927,7 +927,7 @@ struct dvb_frontend *lgdt330x_attach(const struct lgdt330x_config *_config,
 
 	return lgdt330x_get_dvb_frontend(client);
 }
-EXPORT_SYMBOL(lgdt330x_attach);
+EXPORT_SYMBOL_GPL(lgdt330x_attach);
 
 static const struct dvb_frontend_ops lgdt3302_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
diff --git a/drivers/media/dvb-frontends/lgs8gxx.c b/drivers/media/dvb-frontends/lgs8gxx.c
index 30014979b985..ffaf60e16ecd 100644
--- a/drivers/media/dvb-frontends/lgs8gxx.c
+++ b/drivers/media/dvb-frontends/lgs8gxx.c
@@ -1043,7 +1043,7 @@ error_out:
 	return NULL;
 
 }
-EXPORT_SYMBOL(lgs8gxx_attach);
+EXPORT_SYMBOL_GPL(lgs8gxx_attach);
 
 MODULE_DESCRIPTION("Legend Silicon LGS8913/LGS8GXX DMB-TH demodulator driver");
 MODULE_AUTHOR("David T. L. Wong <davidtlwong@gmail.com>");
diff --git a/drivers/media/dvb-frontends/lnbh25.c b/drivers/media/dvb-frontends/lnbh25.c
index 9ffe06cd787d..41bec050642b 100644
--- a/drivers/media/dvb-frontends/lnbh25.c
+++ b/drivers/media/dvb-frontends/lnbh25.c
@@ -173,7 +173,7 @@ struct dvb_frontend *lnbh25_attach(struct dvb_frontend *fe,
 		__func__, priv->i2c_address);
 	return fe;
 }
-EXPORT_SYMBOL(lnbh25_attach);
+EXPORT_SYMBOL_GPL(lnbh25_attach);
 
 MODULE_DESCRIPTION("ST LNBH25 driver");
 MODULE_AUTHOR("info@netup.ru");
diff --git a/drivers/media/dvb-frontends/lnbp21.c b/drivers/media/dvb-frontends/lnbp21.c
index e564974162d6..32593b1f75a3 100644
--- a/drivers/media/dvb-frontends/lnbp21.c
+++ b/drivers/media/dvb-frontends/lnbp21.c
@@ -155,7 +155,7 @@ struct dvb_frontend *lnbh24_attach(struct dvb_frontend *fe,
 	return lnbx2x_attach(fe, i2c, override_set, override_clear,
 							i2c_addr, LNBH24_TTX);
 }
-EXPORT_SYMBOL(lnbh24_attach);
+EXPORT_SYMBOL_GPL(lnbh24_attach);
 
 struct dvb_frontend *lnbp21_attach(struct dvb_frontend *fe,
 				struct i2c_adapter *i2c, u8 override_set,
@@ -164,7 +164,7 @@ struct dvb_frontend *lnbp21_attach(struct dvb_frontend *fe,
 	return lnbx2x_attach(fe, i2c, override_set, override_clear,
 							0x08, LNBP21_ISEL);
 }
-EXPORT_SYMBOL(lnbp21_attach);
+EXPORT_SYMBOL_GPL(lnbp21_attach);
 
 MODULE_DESCRIPTION("Driver for lnb supply and control ic lnbp21, lnbh24");
 MODULE_AUTHOR("Oliver Endriss, Igor M. Liplianin");
diff --git a/drivers/media/dvb-frontends/lnbp22.c b/drivers/media/dvb-frontends/lnbp22.c
index b8c7145d4cef..cb4ea5d3fad4 100644
--- a/drivers/media/dvb-frontends/lnbp22.c
+++ b/drivers/media/dvb-frontends/lnbp22.c
@@ -125,7 +125,7 @@ struct dvb_frontend *lnbp22_attach(struct dvb_frontend *fe,
 
 	return fe;
 }
-EXPORT_SYMBOL(lnbp22_attach);
+EXPORT_SYMBOL_GPL(lnbp22_attach);
 
 MODULE_DESCRIPTION("Driver for lnb supply and control ic lnbp22");
 MODULE_AUTHOR("Dominik Kuhlen");
diff --git a/drivers/media/dvb-frontends/m88ds3103.c b/drivers/media/dvb-frontends/m88ds3103.c
index cf49ac56a37e..cf037b61b226 100644
--- a/drivers/media/dvb-frontends/m88ds3103.c
+++ b/drivers/media/dvb-frontends/m88ds3103.c
@@ -1695,7 +1695,7 @@ struct dvb_frontend *m88ds3103_attach(const struct m88ds3103_config *cfg,
 	*tuner_i2c_adapter = pdata.get_i2c_adapter(client);
 	return pdata.get_dvb_frontend(client);
 }
-EXPORT_SYMBOL(m88ds3103_attach);
+EXPORT_SYMBOL_GPL(m88ds3103_attach);
 
 static const struct dvb_frontend_ops m88ds3103_ops = {
 	.delsys = {SYS_DVBS, SYS_DVBS2},
diff --git a/drivers/media/dvb-frontends/m88rs2000.c b/drivers/media/dvb-frontends/m88rs2000.c
index b294ba87e934..2aa98203cd65 100644
--- a/drivers/media/dvb-frontends/m88rs2000.c
+++ b/drivers/media/dvb-frontends/m88rs2000.c
@@ -808,7 +808,7 @@ error:
 
 	return NULL;
 }
-EXPORT_SYMBOL(m88rs2000_attach);
+EXPORT_SYMBOL_GPL(m88rs2000_attach);
 
 MODULE_DESCRIPTION("M88RS2000 DVB-S Demodulator driver");
 MODULE_AUTHOR("Malcolm Priestley tvboxspy@gmail.com");
diff --git a/drivers/media/dvb-frontends/mb86a16.c b/drivers/media/dvb-frontends/mb86a16.c
index 3ec2cb4fa504..0fc45896e7b8 100644
--- a/drivers/media/dvb-frontends/mb86a16.c
+++ b/drivers/media/dvb-frontends/mb86a16.c
@@ -1853,6 +1853,6 @@ error:
 	kfree(state);
 	return NULL;
 }
-EXPORT_SYMBOL(mb86a16_attach);
+EXPORT_SYMBOL_GPL(mb86a16_attach);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Manu Abraham");
diff --git a/drivers/media/dvb-frontends/mb86a20s.c b/drivers/media/dvb-frontends/mb86a20s.c
index 125fed4891ba..f8e4bbee5bd5 100644
--- a/drivers/media/dvb-frontends/mb86a20s.c
+++ b/drivers/media/dvb-frontends/mb86a20s.c
@@ -2078,7 +2078,7 @@ struct dvb_frontend *mb86a20s_attach(const struct mb86a20s_config *config,
 	dev_info(&i2c->dev, "Detected a Fujitsu mb86a20s frontend\n");
 	return &state->frontend;
 }
-EXPORT_SYMBOL(mb86a20s_attach);
+EXPORT_SYMBOL_GPL(mb86a20s_attach);
 
 static const struct dvb_frontend_ops mb86a20s_ops = {
 	.delsys = { SYS_ISDBT },
diff --git a/drivers/media/dvb-frontends/mt312.c b/drivers/media/dvb-frontends/mt312.c
index d43a67045dbe..fb867dd8a26b 100644
--- a/drivers/media/dvb-frontends/mt312.c
+++ b/drivers/media/dvb-frontends/mt312.c
@@ -827,7 +827,7 @@ error:
 	kfree(state);
 	return NULL;
 }
-EXPORT_SYMBOL(mt312_attach);
+EXPORT_SYMBOL_GPL(mt312_attach);
 
 module_param(debug, int, 0644);
 MODULE_PARM_DESC(debug, "Turn on/off frontend debugging (default:off).");
diff --git a/drivers/media/dvb-frontends/mt352.c b/drivers/media/dvb-frontends/mt352.c
index 399d5c519027..1b2889f5cf67 100644
--- a/drivers/media/dvb-frontends/mt352.c
+++ b/drivers/media/dvb-frontends/mt352.c
@@ -593,4 +593,4 @@ MODULE_DESCRIPTION("Zarlink MT352 DVB-T Demodulator driver");
 MODULE_AUTHOR("Holger Waechtler, Daniel Mack, Antonio Mancuso");
 MODULE_LICENSE("GPL");
 
-EXPORT_SYMBOL(mt352_attach);
+EXPORT_SYMBOL_GPL(mt352_attach);
diff --git a/drivers/media/dvb-frontends/nxt200x.c b/drivers/media/dvb-frontends/nxt200x.c
index 200b6dbc75f8..1c549ada6ebf 100644
--- a/drivers/media/dvb-frontends/nxt200x.c
+++ b/drivers/media/dvb-frontends/nxt200x.c
@@ -1216,5 +1216,5 @@ MODULE_DESCRIPTION("NXT200X (ATSC 8VSB & ITU-T J.83 AnnexB 64/256 QAM) Demodulat
 MODULE_AUTHOR("Kirk Lapray, Michael Krufky, Jean-Francois Thibert, and Taylor Jacob");
 MODULE_LICENSE("GPL");
 
-EXPORT_SYMBOL(nxt200x_attach);
+EXPORT_SYMBOL_GPL(nxt200x_attach);
 
diff --git a/drivers/media/dvb-frontends/nxt6000.c b/drivers/media/dvb-frontends/nxt6000.c
index 136918f82dda..e8d4940370dd 100644
--- a/drivers/media/dvb-frontends/nxt6000.c
+++ b/drivers/media/dvb-frontends/nxt6000.c
@@ -621,4 +621,4 @@ MODULE_DESCRIPTION("NxtWave NXT6000 DVB-T demodulator driver");
 MODULE_AUTHOR("Florian Schirmer");
 MODULE_LICENSE("GPL");
 
-EXPORT_SYMBOL(nxt6000_attach);
+EXPORT_SYMBOL_GPL(nxt6000_attach);
diff --git a/drivers/media/dvb-frontends/or51132.c b/drivers/media/dvb-frontends/or51132.c
index 355f3598627b..74e04c7cca1e 100644
--- a/drivers/media/dvb-frontends/or51132.c
+++ b/drivers/media/dvb-frontends/or51132.c
@@ -605,4 +605,4 @@ MODULE_AUTHOR("Kirk Lapray");
 MODULE_AUTHOR("Trent Piepho");
 MODULE_LICENSE("GPL");
 
-EXPORT_SYMBOL(or51132_attach);
+EXPORT_SYMBOL_GPL(or51132_attach);
diff --git a/drivers/media/dvb-frontends/or51211.c b/drivers/media/dvb-frontends/or51211.c
index ae732dc5116e..2e8e7071a67a 100644
--- a/drivers/media/dvb-frontends/or51211.c
+++ b/drivers/media/dvb-frontends/or51211.c
@@ -551,5 +551,5 @@ MODULE_DESCRIPTION("Oren OR51211 VSB [pcHDTV HD-2000] Demodulator Driver");
 MODULE_AUTHOR("Kirk Lapray");
 MODULE_LICENSE("GPL");
 
-EXPORT_SYMBOL(or51211_attach);
+EXPORT_SYMBOL_GPL(or51211_attach);
 
diff --git a/drivers/media/dvb-frontends/s5h1409.c b/drivers/media/dvb-frontends/s5h1409.c
index 3089cc174a6f..28b1dca077ea 100644
--- a/drivers/media/dvb-frontends/s5h1409.c
+++ b/drivers/media/dvb-frontends/s5h1409.c
@@ -981,7 +981,7 @@ error:
 	kfree(state);
 	return NULL;
 }
-EXPORT_SYMBOL(s5h1409_attach);
+EXPORT_SYMBOL_GPL(s5h1409_attach);
 
 static const struct dvb_frontend_ops s5h1409_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
diff --git a/drivers/media/dvb-frontends/s5h1411.c b/drivers/media/dvb-frontends/s5h1411.c
index 2563a72e98b7..fc48e659c2d8 100644
--- a/drivers/media/dvb-frontends/s5h1411.c
+++ b/drivers/media/dvb-frontends/s5h1411.c
@@ -900,7 +900,7 @@ error:
 	kfree(state);
 	return NULL;
 }
-EXPORT_SYMBOL(s5h1411_attach);
+EXPORT_SYMBOL_GPL(s5h1411_attach);
 
 static const struct dvb_frontend_ops s5h1411_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
diff --git a/drivers/media/dvb-frontends/s5h1420.c b/drivers/media/dvb-frontends/s5h1420.c
index 6bdec2898bc8..d700de1ea6c2 100644
--- a/drivers/media/dvb-frontends/s5h1420.c
+++ b/drivers/media/dvb-frontends/s5h1420.c
@@ -918,7 +918,7 @@ error:
 	kfree(state);
 	return NULL;
 }
-EXPORT_SYMBOL(s5h1420_attach);
+EXPORT_SYMBOL_GPL(s5h1420_attach);
 
 static const struct dvb_frontend_ops s5h1420_ops = {
 	.delsys = { SYS_DVBS },
diff --git a/drivers/media/dvb-frontends/s5h1432.c b/drivers/media/dvb-frontends/s5h1432.c
index 956e8ee4b388..ff5d3bdf3bc6 100644
--- a/drivers/media/dvb-frontends/s5h1432.c
+++ b/drivers/media/dvb-frontends/s5h1432.c
@@ -355,7 +355,7 @@ struct dvb_frontend *s5h1432_attach(const struct s5h1432_config *config,
 
 	return &state->frontend;
 }
-EXPORT_SYMBOL(s5h1432_attach);
+EXPORT_SYMBOL_GPL(s5h1432_attach);
 
 static const struct dvb_frontend_ops s5h1432_ops = {
 	.delsys = { SYS_DVBT },
diff --git a/drivers/media/dvb-frontends/s921.c b/drivers/media/dvb-frontends/s921.c
index f118d8e64103..7e461ac159fc 100644
--- a/drivers/media/dvb-frontends/s921.c
+++ b/drivers/media/dvb-frontends/s921.c
@@ -495,7 +495,7 @@ struct dvb_frontend *s921_attach(const struct s921_config *config,
 
 	return &state->frontend;
 }
-EXPORT_SYMBOL(s921_attach);
+EXPORT_SYMBOL_GPL(s921_attach);
 
 static const struct dvb_frontend_ops s921_ops = {
 	.delsys = { SYS_ISDBT },
diff --git a/drivers/media/dvb-frontends/si21xx.c b/drivers/media/dvb-frontends/si21xx.c
index 2d29d2c4d434..210ccd356e2b 100644
--- a/drivers/media/dvb-frontends/si21xx.c
+++ b/drivers/media/dvb-frontends/si21xx.c
@@ -937,7 +937,7 @@ error:
 	kfree(state);
 	return NULL;
 }
-EXPORT_SYMBOL(si21xx_attach);
+EXPORT_SYMBOL_GPL(si21xx_attach);
 
 module_param(debug, int, 0644);
 MODULE_PARM_DESC(debug, "Turn on/off frontend debugging (default:off).");
diff --git a/drivers/media/dvb-frontends/sp887x.c b/drivers/media/dvb-frontends/sp887x.c
index 146e7f2dd3c5..f59c0f96416b 100644
--- a/drivers/media/dvb-frontends/sp887x.c
+++ b/drivers/media/dvb-frontends/sp887x.c
@@ -624,4 +624,4 @@ MODULE_PARM_DESC(debug, "Turn on/off frontend debugging (default:off).");
 MODULE_DESCRIPTION("Spase sp887x DVB-T demodulator driver");
 MODULE_LICENSE("GPL");
 
-EXPORT_SYMBOL(sp887x_attach);
+EXPORT_SYMBOL_GPL(sp887x_attach);
diff --git a/drivers/media/dvb-frontends/stb0899_drv.c b/drivers/media/dvb-frontends/stb0899_drv.c
index 4ee6c1e1e9f7..2f4d8fb400cd 100644
--- a/drivers/media/dvb-frontends/stb0899_drv.c
+++ b/drivers/media/dvb-frontends/stb0899_drv.c
@@ -1638,7 +1638,7 @@ error:
 	kfree(state);
 	return NULL;
 }
-EXPORT_SYMBOL(stb0899_attach);
+EXPORT_SYMBOL_GPL(stb0899_attach);
 MODULE_PARM_DESC(verbose, "Set Verbosity level");
 MODULE_AUTHOR("Manu Abraham");
 MODULE_DESCRIPTION("STB0899 Multi-Std frontend");
diff --git a/drivers/media/dvb-frontends/stb6000.c b/drivers/media/dvb-frontends/stb6000.c
index 8c9800d577e0..d74e34677b92 100644
--- a/drivers/media/dvb-frontends/stb6000.c
+++ b/drivers/media/dvb-frontends/stb6000.c
@@ -232,7 +232,7 @@ struct dvb_frontend *stb6000_attach(struct dvb_frontend *fe, int addr,
 
 	return fe;
 }
-EXPORT_SYMBOL(stb6000_attach);
+EXPORT_SYMBOL_GPL(stb6000_attach);
 
 module_param(debug, int, 0644);
 MODULE_PARM_DESC(debug, "Turn on/off frontend debugging (default:off).");
diff --git a/drivers/media/dvb-frontends/stb6100.c b/drivers/media/dvb-frontends/stb6100.c
index 698866c4f15a..c5818a15a0d7 100644
--- a/drivers/media/dvb-frontends/stb6100.c
+++ b/drivers/media/dvb-frontends/stb6100.c
@@ -557,7 +557,7 @@ static void stb6100_release(struct dvb_frontend *fe)
 	kfree(state);
 }
 
-EXPORT_SYMBOL(stb6100_attach);
+EXPORT_SYMBOL_GPL(stb6100_attach);
 MODULE_PARM_DESC(verbose, "Set Verbosity level");
 
 MODULE_AUTHOR("Manu Abraham");
diff --git a/drivers/media/dvb-frontends/stv0288.c b/drivers/media/dvb-frontends/stv0288.c
index 3ae1f3a2f142..a5581bd60f9e 100644
--- a/drivers/media/dvb-frontends/stv0288.c
+++ b/drivers/media/dvb-frontends/stv0288.c
@@ -590,7 +590,7 @@ error:
 
 	return NULL;
 }
-EXPORT_SYMBOL(stv0288_attach);
+EXPORT_SYMBOL_GPL(stv0288_attach);
 
 module_param(debug_legacy_dish_switch, int, 0444);
 MODULE_PARM_DESC(debug_legacy_dish_switch,
diff --git a/drivers/media/dvb-frontends/stv0297.c b/drivers/media/dvb-frontends/stv0297.c
index 6d5962d5697a..9d4dbd99a5a7 100644
--- a/drivers/media/dvb-frontends/stv0297.c
+++ b/drivers/media/dvb-frontends/stv0297.c
@@ -710,4 +710,4 @@ MODULE_DESCRIPTION("ST STV0297 DVB-C Demodulator driver");
 MODULE_AUTHOR("Dennis Noermann and Andrew de Quincey");
 MODULE_LICENSE("GPL");
 
-EXPORT_SYMBOL(stv0297_attach);
+EXPORT_SYMBOL_GPL(stv0297_attach);
diff --git a/drivers/media/dvb-frontends/stv0299.c b/drivers/media/dvb-frontends/stv0299.c
index b5263a0ee5aa..da7ff2c2e8e5 100644
--- a/drivers/media/dvb-frontends/stv0299.c
+++ b/drivers/media/dvb-frontends/stv0299.c
@@ -752,4 +752,4 @@ MODULE_DESCRIPTION("ST STV0299 DVB Demodulator driver");
 MODULE_AUTHOR("Ralph Metzler, Holger Waechtler, Peter Schildmann, Felix Domke, Andreas Oberritter, Andrew de Quincey, Kenneth Aafly");
 MODULE_LICENSE("GPL");
 
-EXPORT_SYMBOL(stv0299_attach);
+EXPORT_SYMBOL_GPL(stv0299_attach);
diff --git a/drivers/media/dvb-frontends/stv0367.c b/drivers/media/dvb-frontends/stv0367.c
index a93f40617469..48326434488c 100644
--- a/drivers/media/dvb-frontends/stv0367.c
+++ b/drivers/media/dvb-frontends/stv0367.c
@@ -1750,7 +1750,7 @@ error:
 	kfree(state);
 	return NULL;
 }
-EXPORT_SYMBOL(stv0367ter_attach);
+EXPORT_SYMBOL_GPL(stv0367ter_attach);
 
 static int stv0367cab_gate_ctrl(struct dvb_frontend *fe, int enable)
 {
@@ -2919,7 +2919,7 @@ error:
 	kfree(state);
 	return NULL;
 }
-EXPORT_SYMBOL(stv0367cab_attach);
+EXPORT_SYMBOL_GPL(stv0367cab_attach);
 
 /*
  * Functions for operation on Digital Devices hardware
@@ -3340,7 +3340,7 @@ error:
 	kfree(state);
 	return NULL;
 }
-EXPORT_SYMBOL(stv0367ddb_attach);
+EXPORT_SYMBOL_GPL(stv0367ddb_attach);
 
 MODULE_PARM_DESC(debug, "Set debug");
 MODULE_PARM_DESC(i2c_debug, "Set i2c debug");
diff --git a/drivers/media/dvb-frontends/stv0900_core.c b/drivers/media/dvb-frontends/stv0900_core.c
index 212312d20ff6..e7b9b9b11d7d 100644
--- a/drivers/media/dvb-frontends/stv0900_core.c
+++ b/drivers/media/dvb-frontends/stv0900_core.c
@@ -1957,7 +1957,7 @@ error:
 	kfree(state);
 	return NULL;
 }
-EXPORT_SYMBOL(stv0900_attach);
+EXPORT_SYMBOL_GPL(stv0900_attach);
 
 MODULE_PARM_DESC(debug, "Set debug");
 
diff --git a/drivers/media/dvb-frontends/stv090x.c b/drivers/media/dvb-frontends/stv090x.c
index a07dc5fdeb3d..cc45139057ba 100644
--- a/drivers/media/dvb-frontends/stv090x.c
+++ b/drivers/media/dvb-frontends/stv090x.c
@@ -5071,7 +5071,7 @@ error:
 	kfree(state);
 	return NULL;
 }
-EXPORT_SYMBOL(stv090x_attach);
+EXPORT_SYMBOL_GPL(stv090x_attach);
 
 static const struct i2c_device_id stv090x_id_table[] = {
 	{"stv090x", 0},
diff --git a/drivers/media/dvb-frontends/stv6110.c b/drivers/media/dvb-frontends/stv6110.c
index 963f6a896102..1cf9c095dbff 100644
--- a/drivers/media/dvb-frontends/stv6110.c
+++ b/drivers/media/dvb-frontends/stv6110.c
@@ -427,7 +427,7 @@ struct dvb_frontend *stv6110_attach(struct dvb_frontend *fe,
 
 	return fe;
 }
-EXPORT_SYMBOL(stv6110_attach);
+EXPORT_SYMBOL_GPL(stv6110_attach);
 
 module_param(debug, int, 0644);
 MODULE_PARM_DESC(debug, "Turn on/off frontend debugging (default:off).");
diff --git a/drivers/media/dvb-frontends/stv6110x.c b/drivers/media/dvb-frontends/stv6110x.c
index 11653f846c12..c678f47d2449 100644
--- a/drivers/media/dvb-frontends/stv6110x.c
+++ b/drivers/media/dvb-frontends/stv6110x.c
@@ -467,7 +467,7 @@ const struct stv6110x_devctl *stv6110x_attach(struct dvb_frontend *fe,
 	dev_info(&stv6110x->i2c->dev, "Attaching STV6110x\n");
 	return stv6110x->devctl;
 }
-EXPORT_SYMBOL(stv6110x_attach);
+EXPORT_SYMBOL_GPL(stv6110x_attach);
 
 static const struct i2c_device_id stv6110x_id_table[] = {
 	{"stv6110x", 0},
diff --git a/drivers/media/dvb-frontends/tda10021.c b/drivers/media/dvb-frontends/tda10021.c
index faa6e54b3372..462e12ab6bd1 100644
--- a/drivers/media/dvb-frontends/tda10021.c
+++ b/drivers/media/dvb-frontends/tda10021.c
@@ -523,4 +523,4 @@ MODULE_DESCRIPTION("Philips TDA10021 DVB-C demodulator driver");
 MODULE_AUTHOR("Ralph Metzler, Holger Waechtler, Markus Schulz");
 MODULE_LICENSE("GPL");
 
-EXPORT_SYMBOL(tda10021_attach);
+EXPORT_SYMBOL_GPL(tda10021_attach);
diff --git a/drivers/media/dvb-frontends/tda10023.c b/drivers/media/dvb-frontends/tda10023.c
index 8f32edf6b700..4c2541ecd743 100644
--- a/drivers/media/dvb-frontends/tda10023.c
+++ b/drivers/media/dvb-frontends/tda10023.c
@@ -594,4 +594,4 @@ MODULE_DESCRIPTION("Philips TDA10023 DVB-C demodulator driver");
 MODULE_AUTHOR("Georg Acher, Hartmut Birr");
 MODULE_LICENSE("GPL");
 
-EXPORT_SYMBOL(tda10023_attach);
+EXPORT_SYMBOL_GPL(tda10023_attach);
diff --git a/drivers/media/dvb-frontends/tda10048.c b/drivers/media/dvb-frontends/tda10048.c
index 3cb4e5270e4f..5d5e4e9e4422 100644
--- a/drivers/media/dvb-frontends/tda10048.c
+++ b/drivers/media/dvb-frontends/tda10048.c
@@ -1138,7 +1138,7 @@ error:
 	kfree(state);
 	return NULL;
 }
-EXPORT_SYMBOL(tda10048_attach);
+EXPORT_SYMBOL_GPL(tda10048_attach);
 
 static const struct dvb_frontend_ops tda10048_ops = {
 	.delsys = { SYS_DVBT },
diff --git a/drivers/media/dvb-frontends/tda1004x.c b/drivers/media/dvb-frontends/tda1004x.c
index 83a798ca9b00..6f306db6c615 100644
--- a/drivers/media/dvb-frontends/tda1004x.c
+++ b/drivers/media/dvb-frontends/tda1004x.c
@@ -1378,5 +1378,5 @@ MODULE_DESCRIPTION("Philips TDA10045H & TDA10046H DVB-T Demodulator");
 MODULE_AUTHOR("Andrew de Quincey & Robert Schlabbach");
 MODULE_LICENSE("GPL");
 
-EXPORT_SYMBOL(tda10045_attach);
-EXPORT_SYMBOL(tda10046_attach);
+EXPORT_SYMBOL_GPL(tda10045_attach);
+EXPORT_SYMBOL_GPL(tda10046_attach);
diff --git a/drivers/media/dvb-frontends/tda10086.c b/drivers/media/dvb-frontends/tda10086.c
index cdcf97664bba..b449514ae585 100644
--- a/drivers/media/dvb-frontends/tda10086.c
+++ b/drivers/media/dvb-frontends/tda10086.c
@@ -764,4 +764,4 @@ MODULE_DESCRIPTION("Philips TDA10086 DVB-S Demodulator");
 MODULE_AUTHOR("Andrew de Quincey");
 MODULE_LICENSE("GPL");
 
-EXPORT_SYMBOL(tda10086_attach);
+EXPORT_SYMBOL_GPL(tda10086_attach);
diff --git a/drivers/media/dvb-frontends/tda665x.c b/drivers/media/dvb-frontends/tda665x.c
index 13e8969da7f8..346be5011fb7 100644
--- a/drivers/media/dvb-frontends/tda665x.c
+++ b/drivers/media/dvb-frontends/tda665x.c
@@ -227,7 +227,7 @@ struct dvb_frontend *tda665x_attach(struct dvb_frontend *fe,
 
 	return fe;
 }
-EXPORT_SYMBOL(tda665x_attach);
+EXPORT_SYMBOL_GPL(tda665x_attach);
 
 MODULE_DESCRIPTION("TDA665x driver");
 MODULE_AUTHOR("Manu Abraham");
diff --git a/drivers/media/dvb-frontends/tda8083.c b/drivers/media/dvb-frontends/tda8083.c
index e3e1c3db2c85..44f53624557b 100644
--- a/drivers/media/dvb-frontends/tda8083.c
+++ b/drivers/media/dvb-frontends/tda8083.c
@@ -481,4 +481,4 @@ MODULE_DESCRIPTION("Philips TDA8083 DVB-S Demodulator");
 MODULE_AUTHOR("Ralph Metzler, Holger Waechtler");
 MODULE_LICENSE("GPL");
 
-EXPORT_SYMBOL(tda8083_attach);
+EXPORT_SYMBOL_GPL(tda8083_attach);
diff --git a/drivers/media/dvb-frontends/tda8261.c b/drivers/media/dvb-frontends/tda8261.c
index 0d576d41c67d..8b06f92745dc 100644
--- a/drivers/media/dvb-frontends/tda8261.c
+++ b/drivers/media/dvb-frontends/tda8261.c
@@ -188,7 +188,7 @@ exit:
 	return NULL;
 }
 
-EXPORT_SYMBOL(tda8261_attach);
+EXPORT_SYMBOL_GPL(tda8261_attach);
 
 MODULE_AUTHOR("Manu Abraham");
 MODULE_DESCRIPTION("TDA8261 8PSK/QPSK Tuner");
diff --git a/drivers/media/dvb-frontends/tda826x.c b/drivers/media/dvb-frontends/tda826x.c
index f9703a1dd758..eafcf5f7da3d 100644
--- a/drivers/media/dvb-frontends/tda826x.c
+++ b/drivers/media/dvb-frontends/tda826x.c
@@ -164,7 +164,7 @@ struct dvb_frontend *tda826x_attach(struct dvb_frontend *fe, int addr, struct i2
 
 	return fe;
 }
-EXPORT_SYMBOL(tda826x_attach);
+EXPORT_SYMBOL_GPL(tda826x_attach);
 
 module_param(debug, int, 0644);
 MODULE_PARM_DESC(debug, "Turn on/off frontend debugging (default:off).");
diff --git a/drivers/media/dvb-frontends/ts2020.c b/drivers/media/dvb-frontends/ts2020.c
index f5b60f827697..a5ebce57f35e 100644
--- a/drivers/media/dvb-frontends/ts2020.c
+++ b/drivers/media/dvb-frontends/ts2020.c
@@ -525,7 +525,7 @@ struct dvb_frontend *ts2020_attach(struct dvb_frontend *fe,
 
 	return fe;
 }
-EXPORT_SYMBOL(ts2020_attach);
+EXPORT_SYMBOL_GPL(ts2020_attach);
 
 /*
  * We implement own regmap locking due to legacy DVB attach which uses frontend
diff --git a/drivers/media/dvb-frontends/tua6100.c b/drivers/media/dvb-frontends/tua6100.c
index 2483f614d0e7..41dd9b6d3190 100644
--- a/drivers/media/dvb-frontends/tua6100.c
+++ b/drivers/media/dvb-frontends/tua6100.c
@@ -186,7 +186,7 @@ struct dvb_frontend *tua6100_attach(struct dvb_frontend *fe, int addr, struct i2
 	fe->tuner_priv = priv;
 	return fe;
 }
-EXPORT_SYMBOL(tua6100_attach);
+EXPORT_SYMBOL_GPL(tua6100_attach);
 
 MODULE_DESCRIPTION("DVB tua6100 driver");
 MODULE_AUTHOR("Andrew de Quincey");
diff --git a/drivers/media/dvb-frontends/ves1820.c b/drivers/media/dvb-frontends/ves1820.c
index 9df14d0be1c1..ee5620e731e9 100644
--- a/drivers/media/dvb-frontends/ves1820.c
+++ b/drivers/media/dvb-frontends/ves1820.c
@@ -434,4 +434,4 @@ MODULE_DESCRIPTION("VLSI VES1820 DVB-C Demodulator driver");
 MODULE_AUTHOR("Ralph Metzler, Holger Waechtler");
 MODULE_LICENSE("GPL");
 
-EXPORT_SYMBOL(ves1820_attach);
+EXPORT_SYMBOL_GPL(ves1820_attach);
diff --git a/drivers/media/dvb-frontends/ves1x93.c b/drivers/media/dvb-frontends/ves1x93.c
index b74727286302..c60e21d26b88 100644
--- a/drivers/media/dvb-frontends/ves1x93.c
+++ b/drivers/media/dvb-frontends/ves1x93.c
@@ -540,4 +540,4 @@ MODULE_DESCRIPTION("VLSI VES1x93 DVB-S Demodulator driver");
 MODULE_AUTHOR("Ralph Metzler");
 MODULE_LICENSE("GPL");
 
-EXPORT_SYMBOL(ves1x93_attach);
+EXPORT_SYMBOL_GPL(ves1x93_attach);
diff --git a/drivers/media/dvb-frontends/zl10036.c b/drivers/media/dvb-frontends/zl10036.c
index d392c7cce2ce..7ba575e9c55f 100644
--- a/drivers/media/dvb-frontends/zl10036.c
+++ b/drivers/media/dvb-frontends/zl10036.c
@@ -496,7 +496,7 @@ error:
 	kfree(state);
 	return NULL;
 }
-EXPORT_SYMBOL(zl10036_attach);
+EXPORT_SYMBOL_GPL(zl10036_attach);
 
 module_param_named(debug, zl10036_debug, int, 0644);
 MODULE_PARM_DESC(debug, "Turn on/off frontend debugging (default:off).");
diff --git a/drivers/media/dvb-frontends/zl10039.c b/drivers/media/dvb-frontends/zl10039.c
index 1335bf78d5b7..a3e4d219400c 100644
--- a/drivers/media/dvb-frontends/zl10039.c
+++ b/drivers/media/dvb-frontends/zl10039.c
@@ -295,7 +295,7 @@ error:
 	kfree(state);
 	return NULL;
 }
-EXPORT_SYMBOL(zl10039_attach);
+EXPORT_SYMBOL_GPL(zl10039_attach);
 
 module_param(debug, int, 0644);
 MODULE_PARM_DESC(debug, "Turn on/off frontend debugging (default:off).");
diff --git a/drivers/media/dvb-frontends/zl10353.c b/drivers/media/dvb-frontends/zl10353.c
index 2a2cf20a73d6..8849d05475c2 100644
--- a/drivers/media/dvb-frontends/zl10353.c
+++ b/drivers/media/dvb-frontends/zl10353.c
@@ -665,4 +665,4 @@ MODULE_DESCRIPTION("Zarlink ZL10353 DVB-T demodulator driver");
 MODULE_AUTHOR("Chris Pascoe");
 MODULE_LICENSE("GPL");
 
-EXPORT_SYMBOL(zl10353_attach);
+EXPORT_SYMBOL_GPL(zl10353_attach);
diff --git a/drivers/media/pci/bt8xx/dst.c b/drivers/media/pci/bt8xx/dst.c
index 3e52a51982d7..110651e47831 100644
--- a/drivers/media/pci/bt8xx/dst.c
+++ b/drivers/media/pci/bt8xx/dst.c
@@ -1722,7 +1722,7 @@ struct dst_state *dst_attach(struct dst_state *state, struct dvb_adapter *dvb_ad
 	return state;				/*	Manu (DST is a card not a frontend)	*/
 }
 
-EXPORT_SYMBOL(dst_attach);
+EXPORT_SYMBOL_GPL(dst_attach);
 
 static const struct dvb_frontend_ops dst_dvbt_ops = {
 	.delsys = { SYS_DVBT },
diff --git a/drivers/media/pci/bt8xx/dst_ca.c b/drivers/media/pci/bt8xx/dst_ca.c
index d234a0f404d6..a9cc6e7a57f9 100644
--- a/drivers/media/pci/bt8xx/dst_ca.c
+++ b/drivers/media/pci/bt8xx/dst_ca.c
@@ -668,7 +668,7 @@ struct dvb_device *dst_ca_attach(struct dst_state *dst, struct dvb_adapter *dvb_
 	return NULL;
 }
 
-EXPORT_SYMBOL(dst_ca_attach);
+EXPORT_SYMBOL_GPL(dst_ca_attach);
 
 MODULE_DESCRIPTION("DST DVB-S/T/C Combo CA driver");
 MODULE_AUTHOR("Manu Abraham");
diff --git a/drivers/media/pci/ddbridge/ddbridge-dummy-fe.c b/drivers/media/pci/ddbridge/ddbridge-dummy-fe.c
index 6868a0c4fc82..520ebd16b0c4 100644
--- a/drivers/media/pci/ddbridge/ddbridge-dummy-fe.c
+++ b/drivers/media/pci/ddbridge/ddbridge-dummy-fe.c
@@ -112,7 +112,7 @@ struct dvb_frontend *ddbridge_dummy_fe_qam_attach(void)
 	state->frontend.demodulator_priv = state;
 	return &state->frontend;
 }
-EXPORT_SYMBOL(ddbridge_dummy_fe_qam_attach);
+EXPORT_SYMBOL_GPL(ddbridge_dummy_fe_qam_attach);
 
 static const struct dvb_frontend_ops ddbridge_dummy_fe_qam_ops = {
 	.delsys = { SYS_DVBC_ANNEX_A },
diff --git a/drivers/media/tuners/fc0011.c b/drivers/media/tuners/fc0011.c
index eaa3bbc903d7..3d3b54be2955 100644
--- a/drivers/media/tuners/fc0011.c
+++ b/drivers/media/tuners/fc0011.c
@@ -499,7 +499,7 @@ struct dvb_frontend *fc0011_attach(struct dvb_frontend *fe,
 
 	return fe;
 }
-EXPORT_SYMBOL(fc0011_attach);
+EXPORT_SYMBOL_GPL(fc0011_attach);
 
 MODULE_DESCRIPTION("Fitipower FC0011 silicon tuner driver");
 MODULE_AUTHOR("Michael Buesch <m@bues.ch>");
diff --git a/drivers/media/tuners/fc0012.c b/drivers/media/tuners/fc0012.c
index 4429d5e8c579..81e65acbdb17 100644
--- a/drivers/media/tuners/fc0012.c
+++ b/drivers/media/tuners/fc0012.c
@@ -495,7 +495,7 @@ err:
 
 	return fe;
 }
-EXPORT_SYMBOL(fc0012_attach);
+EXPORT_SYMBOL_GPL(fc0012_attach);
 
 MODULE_DESCRIPTION("Fitipower FC0012 silicon tuner driver");
 MODULE_AUTHOR("Hans-Frieder Vogt <hfvogt@gmx.net>");
diff --git a/drivers/media/tuners/fc0013.c b/drivers/media/tuners/fc0013.c
index 29dd9b55ff33..1006a2798eef 100644
--- a/drivers/media/tuners/fc0013.c
+++ b/drivers/media/tuners/fc0013.c
@@ -608,7 +608,7 @@ struct dvb_frontend *fc0013_attach(struct dvb_frontend *fe,
 
 	return fe;
 }
-EXPORT_SYMBOL(fc0013_attach);
+EXPORT_SYMBOL_GPL(fc0013_attach);
 
 MODULE_DESCRIPTION("Fitipower FC0013 silicon tuner driver");
 MODULE_AUTHOR("Hans-Frieder Vogt <hfvogt@gmx.net>");
diff --git a/drivers/media/tuners/max2165.c b/drivers/media/tuners/max2165.c
index 1c746bed51fe..1575ab94e1c8 100644
--- a/drivers/media/tuners/max2165.c
+++ b/drivers/media/tuners/max2165.c
@@ -410,7 +410,7 @@ struct dvb_frontend *max2165_attach(struct dvb_frontend *fe,
 
 	return fe;
 }
-EXPORT_SYMBOL(max2165_attach);
+EXPORT_SYMBOL_GPL(max2165_attach);
 
 MODULE_AUTHOR("David T. L. Wong <davidtlwong@gmail.com>");
 MODULE_DESCRIPTION("Maxim MAX2165 silicon tuner driver");
diff --git a/drivers/media/tuners/mc44s803.c b/drivers/media/tuners/mc44s803.c
index 0c9161516abd..ed8bdf7ebd99 100644
--- a/drivers/media/tuners/mc44s803.c
+++ b/drivers/media/tuners/mc44s803.c
@@ -356,7 +356,7 @@ error:
 	kfree(priv);
 	return NULL;
 }
-EXPORT_SYMBOL(mc44s803_attach);
+EXPORT_SYMBOL_GPL(mc44s803_attach);
 
 MODULE_AUTHOR("Jochen Friedrich");
 MODULE_DESCRIPTION("Freescale MC44S803 silicon tuner driver");
diff --git a/drivers/media/tuners/mt2060.c b/drivers/media/tuners/mt2060.c
index 0278a9f0aeef..4205ed4cf467 100644
--- a/drivers/media/tuners/mt2060.c
+++ b/drivers/media/tuners/mt2060.c
@@ -440,7 +440,7 @@ struct dvb_frontend * mt2060_attach(struct dvb_frontend *fe, struct i2c_adapter
 
 	return fe;
 }
-EXPORT_SYMBOL(mt2060_attach);
+EXPORT_SYMBOL_GPL(mt2060_attach);
 
 static int mt2060_probe(struct i2c_client *client)
 {
diff --git a/drivers/media/tuners/mt2131.c b/drivers/media/tuners/mt2131.c
index 37f50ff6c0bd..eebc06088341 100644
--- a/drivers/media/tuners/mt2131.c
+++ b/drivers/media/tuners/mt2131.c
@@ -274,7 +274,7 @@ struct dvb_frontend * mt2131_attach(struct dvb_frontend *fe,
 	fe->tuner_priv = priv;
 	return fe;
 }
-EXPORT_SYMBOL(mt2131_attach);
+EXPORT_SYMBOL_GPL(mt2131_attach);
 
 MODULE_AUTHOR("Steven Toth");
 MODULE_DESCRIPTION("Microtune MT2131 silicon tuner driver");
diff --git a/drivers/media/tuners/mt2266.c b/drivers/media/tuners/mt2266.c
index 6136f20fa9b7..2e92885a6bcb 100644
--- a/drivers/media/tuners/mt2266.c
+++ b/drivers/media/tuners/mt2266.c
@@ -336,7 +336,7 @@ struct dvb_frontend * mt2266_attach(struct dvb_frontend *fe, struct i2c_adapter
 	mt2266_calibrate(priv);
 	return fe;
 }
-EXPORT_SYMBOL(mt2266_attach);
+EXPORT_SYMBOL_GPL(mt2266_attach);
 
 MODULE_AUTHOR("Olivier DANET");
 MODULE_DESCRIPTION("Microtune MT2266 silicon tuner driver");
diff --git a/drivers/media/tuners/mxl5005s.c b/drivers/media/tuners/mxl5005s.c
index 06dfab9fb8cb..d9bfa257a005 100644
--- a/drivers/media/tuners/mxl5005s.c
+++ b/drivers/media/tuners/mxl5005s.c
@@ -4120,7 +4120,7 @@ struct dvb_frontend *mxl5005s_attach(struct dvb_frontend *fe,
 	fe->tuner_priv = state;
 	return fe;
 }
-EXPORT_SYMBOL(mxl5005s_attach);
+EXPORT_SYMBOL_GPL(mxl5005s_attach);
 
 MODULE_DESCRIPTION("MaxLinear MXL5005S silicon tuner driver");
 MODULE_AUTHOR("Steven Toth");
diff --git a/drivers/media/tuners/qt1010.c b/drivers/media/tuners/qt1010.c
index a7b19863f489..48fc79cd4027 100644
--- a/drivers/media/tuners/qt1010.c
+++ b/drivers/media/tuners/qt1010.c
@@ -441,7 +441,7 @@ struct dvb_frontend * qt1010_attach(struct dvb_frontend *fe,
 	fe->tuner_priv = priv;
 	return fe;
 }
-EXPORT_SYMBOL(qt1010_attach);
+EXPORT_SYMBOL_GPL(qt1010_attach);
 
 MODULE_DESCRIPTION("Quantek QT1010 silicon tuner driver");
 MODULE_AUTHOR("Antti Palosaari <crope@iki.fi>");
diff --git a/drivers/media/tuners/tda18218.c b/drivers/media/tuners/tda18218.c
index 4ed94646116f..7d8d84dcb245 100644
--- a/drivers/media/tuners/tda18218.c
+++ b/drivers/media/tuners/tda18218.c
@@ -336,7 +336,7 @@ struct dvb_frontend *tda18218_attach(struct dvb_frontend *fe,
 
 	return fe;
 }
-EXPORT_SYMBOL(tda18218_attach);
+EXPORT_SYMBOL_GPL(tda18218_attach);
 
 MODULE_DESCRIPTION("NXP TDA18218HN silicon tuner driver");
 MODULE_AUTHOR("Antti Palosaari <crope@iki.fi>");
diff --git a/drivers/media/tuners/xc2028.c b/drivers/media/tuners/xc2028.c
index 69c2e1b99bf1..5a967edceca9 100644
--- a/drivers/media/tuners/xc2028.c
+++ b/drivers/media/tuners/xc2028.c
@@ -1512,7 +1512,7 @@ fail:
 	return NULL;
 }
 
-EXPORT_SYMBOL(xc2028_attach);
+EXPORT_SYMBOL_GPL(xc2028_attach);
 
 MODULE_DESCRIPTION("Xceive xc2028/xc3028 tuner driver");
 MODULE_AUTHOR("Michel Ludwig <michel.ludwig@gmail.com>");
diff --git a/drivers/media/tuners/xc4000.c b/drivers/media/tuners/xc4000.c
index d59b4ab77430..57ded9ff3f04 100644
--- a/drivers/media/tuners/xc4000.c
+++ b/drivers/media/tuners/xc4000.c
@@ -1742,7 +1742,7 @@ fail2:
 	xc4000_release(fe);
 	return NULL;
 }
-EXPORT_SYMBOL(xc4000_attach);
+EXPORT_SYMBOL_GPL(xc4000_attach);
 
 MODULE_AUTHOR("Steven Toth, Davide Ferri");
 MODULE_DESCRIPTION("Xceive xc4000 silicon tuner driver");
diff --git a/drivers/media/tuners/xc5000.c b/drivers/media/tuners/xc5000.c
index 7b7d9fe4f945..2182e5b7b606 100644
--- a/drivers/media/tuners/xc5000.c
+++ b/drivers/media/tuners/xc5000.c
@@ -1460,7 +1460,7 @@ fail:
 	xc5000_release(fe);
 	return NULL;
 }
-EXPORT_SYMBOL(xc5000_attach);
+EXPORT_SYMBOL_GPL(xc5000_attach);
 
 MODULE_AUTHOR("Steven Toth");
 MODULE_DESCRIPTION("Xceive xc5000 silicon tuner driver");
diff --git a/drivers/staging/media/av7110/sp8870.c b/drivers/staging/media/av7110/sp8870.c
index 9767159aeb9b..abf5c72607b6 100644
--- a/drivers/staging/media/av7110/sp8870.c
+++ b/drivers/staging/media/av7110/sp8870.c
@@ -606,4 +606,4 @@ MODULE_DESCRIPTION("Spase SP8870 DVB-T Demodulator driver");
 MODULE_AUTHOR("Juergen Peitz");
 MODULE_LICENSE("GPL");
 
-EXPORT_SYMBOL(sp8870_attach);
+EXPORT_SYMBOL_GPL(sp8870_attach);

From 5d153cd128251aaedc8e9657f0a949ec94952055 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Fri, 8 Sep 2023 16:34:59 -0500
Subject: [PATCH 1183/1189] spnego: add missing OID to oid registry

Add missing OID to the registry. Some servers and clients (including
Windows) now request "NEGOEX - SPNEGEO Extended Negotiation Security")

See https://datatracker.ietf.org/doc/html/draft-zhu-negoex-02

Reviewed-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 include/linux/oid_registry.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/linux/oid_registry.h b/include/linux/oid_registry.h
index 0f4a8903922a..f86a08ba0207 100644
--- a/include/linux/oid_registry.h
+++ b/include/linux/oid_registry.h
@@ -67,6 +67,7 @@ enum OID {
 	OID_msOutlookExpress,		/* 1.3.6.1.4.1.311.16.4 */
 
 	OID_ntlmssp,			/* 1.3.6.1.4.1.311.2.2.10 */
+	OID_negoex,			/* 1.3.6.1.4.1.311.2.2.30 */
 
 	OID_spnego,			/* 1.3.6.1.5.5.2 */
 

From fb60211f377b69acffead3147578f86d0092a7a5 Mon Sep 17 00:00:00 2001
From: Petr Tesarik <petr.tesarik.ext@huawei.com>
Date: Mon, 24 Jul 2023 14:07:42 +0200
Subject: [PATCH 1184/1189] sh: boards: Fix CEU buffer size passed to
 dma_declare_coherent_memory()

In all these cases, the last argument to dma_declare_coherent_memory() is
the buffer end address, but the expected value should be the size of the
reserved region.

Fixes: 39fb993038e1 ("media: arch: sh: ap325rxa: Use new renesas-ceu camera driver")
Fixes: c2f9b05fd5c1 ("media: arch: sh: ecovec: Use new renesas-ceu camera driver")
Fixes: f3590dc32974 ("media: arch: sh: kfr2r09: Use new renesas-ceu camera driver")
Fixes: 186c446f4b84 ("media: arch: sh: migor: Use new renesas-ceu camera driver")
Fixes: 1a3c230b4151 ("media: arch: sh: ms7724se: Use new renesas-ceu camera driver")
Signed-off-by: Petr Tesarik <petr.tesarik.ext@huawei.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Jacopo Mondi <jacopo.mondi@ideasonboard.com>
Reviewed-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Reviewed-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Link: https://lore.kernel.org/r/20230724120742.2187-1-petrtesarik@huaweicloud.com
Signed-off-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
---
 arch/sh/boards/mach-ap325rxa/setup.c | 2 +-
 arch/sh/boards/mach-ecovec24/setup.c | 6 ++----
 arch/sh/boards/mach-kfr2r09/setup.c  | 2 +-
 arch/sh/boards/mach-migor/setup.c    | 2 +-
 arch/sh/boards/mach-se/7724/setup.c  | 6 ++----
 5 files changed, 7 insertions(+), 11 deletions(-)

diff --git a/arch/sh/boards/mach-ap325rxa/setup.c b/arch/sh/boards/mach-ap325rxa/setup.c
index 151792162152..645cccf3da88 100644
--- a/arch/sh/boards/mach-ap325rxa/setup.c
+++ b/arch/sh/boards/mach-ap325rxa/setup.c
@@ -531,7 +531,7 @@ static int __init ap325rxa_devices_setup(void)
 	device_initialize(&ap325rxa_ceu_device.dev);
 	dma_declare_coherent_memory(&ap325rxa_ceu_device.dev,
 			ceu_dma_membase, ceu_dma_membase,
-			ceu_dma_membase + CEU_BUFFER_MEMORY_SIZE - 1);
+			CEU_BUFFER_MEMORY_SIZE);
 
 	platform_device_add(&ap325rxa_ceu_device);
 
diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c
index 674da7ebd8b7..7ec03d4a4edf 100644
--- a/arch/sh/boards/mach-ecovec24/setup.c
+++ b/arch/sh/boards/mach-ecovec24/setup.c
@@ -1454,15 +1454,13 @@ static int __init arch_setup(void)
 	device_initialize(&ecovec_ceu_devices[0]->dev);
 	dma_declare_coherent_memory(&ecovec_ceu_devices[0]->dev,
 				    ceu0_dma_membase, ceu0_dma_membase,
-				    ceu0_dma_membase +
-				    CEU_BUFFER_MEMORY_SIZE - 1);
+				    CEU_BUFFER_MEMORY_SIZE);
 	platform_device_add(ecovec_ceu_devices[0]);
 
 	device_initialize(&ecovec_ceu_devices[1]->dev);
 	dma_declare_coherent_memory(&ecovec_ceu_devices[1]->dev,
 				    ceu1_dma_membase, ceu1_dma_membase,
-				    ceu1_dma_membase +
-				    CEU_BUFFER_MEMORY_SIZE - 1);
+				    CEU_BUFFER_MEMORY_SIZE);
 	platform_device_add(ecovec_ceu_devices[1]);
 
 	gpiod_add_lookup_table(&cn12_power_gpiod_table);
diff --git a/arch/sh/boards/mach-kfr2r09/setup.c b/arch/sh/boards/mach-kfr2r09/setup.c
index 20f4db778ed6..c6d556dfbbbe 100644
--- a/arch/sh/boards/mach-kfr2r09/setup.c
+++ b/arch/sh/boards/mach-kfr2r09/setup.c
@@ -603,7 +603,7 @@ static int __init kfr2r09_devices_setup(void)
 	device_initialize(&kfr2r09_ceu_device.dev);
 	dma_declare_coherent_memory(&kfr2r09_ceu_device.dev,
 			ceu_dma_membase, ceu_dma_membase,
-			ceu_dma_membase + CEU_BUFFER_MEMORY_SIZE - 1);
+			CEU_BUFFER_MEMORY_SIZE);
 
 	platform_device_add(&kfr2r09_ceu_device);
 
diff --git a/arch/sh/boards/mach-migor/setup.c b/arch/sh/boards/mach-migor/setup.c
index f60061283c48..773ee767d0c4 100644
--- a/arch/sh/boards/mach-migor/setup.c
+++ b/arch/sh/boards/mach-migor/setup.c
@@ -604,7 +604,7 @@ static int __init migor_devices_setup(void)
 	device_initialize(&migor_ceu_device.dev);
 	dma_declare_coherent_memory(&migor_ceu_device.dev,
 			ceu_dma_membase, ceu_dma_membase,
-			ceu_dma_membase + CEU_BUFFER_MEMORY_SIZE - 1);
+			CEU_BUFFER_MEMORY_SIZE);
 
 	platform_device_add(&migor_ceu_device);
 
diff --git a/arch/sh/boards/mach-se/7724/setup.c b/arch/sh/boards/mach-se/7724/setup.c
index b60a2626e18b..6495f9354065 100644
--- a/arch/sh/boards/mach-se/7724/setup.c
+++ b/arch/sh/boards/mach-se/7724/setup.c
@@ -940,15 +940,13 @@ static int __init devices_setup(void)
 	device_initialize(&ms7724se_ceu_devices[0]->dev);
 	dma_declare_coherent_memory(&ms7724se_ceu_devices[0]->dev,
 				    ceu0_dma_membase, ceu0_dma_membase,
-				    ceu0_dma_membase +
-				    CEU_BUFFER_MEMORY_SIZE - 1);
+				    CEU_BUFFER_MEMORY_SIZE);
 	platform_device_add(ms7724se_ceu_devices[0]);
 
 	device_initialize(&ms7724se_ceu_devices[1]->dev);
 	dma_declare_coherent_memory(&ms7724se_ceu_devices[1]->dev,
 				    ceu1_dma_membase, ceu1_dma_membase,
-				    ceu1_dma_membase +
-				    CEU_BUFFER_MEMORY_SIZE - 1);
+				    CEU_BUFFER_MEMORY_SIZE);
 	platform_device_add(ms7724se_ceu_devices[1]);
 
 	return platform_add_devices(ms7724se_devices,

From 246f80a0b17f8f582b2c0996db02998239057c65 Mon Sep 17 00:00:00 2001
From: Duoming Zhou <duoming@zju.edu.cn>
Date: Wed, 2 Aug 2023 11:37:37 +0800
Subject: [PATCH 1185/1189] sh: push-switch: Reorder cleanup operations to
 avoid use-after-free bug

The original code puts flush_work() before timer_shutdown_sync()
in switch_drv_remove(). Although we use flush_work() to stop
the worker, it could be rescheduled in switch_timer(). As a result,
a use-after-free bug can occur. The details are shown below:

      (cpu 0)                    |      (cpu 1)
switch_drv_remove()              |
 flush_work()                    |
  ...                            |  switch_timer // timer
                                 |   schedule_work(&psw->work)
 timer_shutdown_sync()           |
 ...                             |  switch_work_handler // worker
 kfree(psw) // free              |
                                 |   psw->state = 0 // use

This patch puts timer_shutdown_sync() before flush_work() to
mitigate the bugs. As a result, the worker and timer will be
stopped safely before the deallocate operations.

Fixes: 9f5e8eee5cfe ("sh: generic push-switch framework.")
Signed-off-by: Duoming Zhou <duoming@zju.edu.cn>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Link: https://lore.kernel.org/r/20230802033737.9738-1-duoming@zju.edu.cn
Signed-off-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
---
 arch/sh/drivers/push-switch.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/sh/drivers/push-switch.c b/arch/sh/drivers/push-switch.c
index c95f48ff3f6f..6ecba5f521eb 100644
--- a/arch/sh/drivers/push-switch.c
+++ b/arch/sh/drivers/push-switch.c
@@ -101,8 +101,8 @@ static int switch_drv_remove(struct platform_device *pdev)
 		device_remove_file(&pdev->dev, &dev_attr_switch);
 
 	platform_set_drvdata(pdev, NULL);
-	flush_work(&psw->work);
 	timer_shutdown_sync(&psw->debounce);
+	flush_work(&psw->work);
 	free_irq(irq, pdev);
 
 	kfree(psw);

From f741bd7178c95abd7aeac5a9d933ee542f9a5509 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 8 Sep 2023 17:03:20 +0100
Subject: [PATCH 1186/1189] iov_iter: Fix iov_iter_extract_pages() with
 zero-sized entries

iov_iter_extract_pages() doesn't correctly handle skipping over initial
zero-length entries in ITER_KVEC and ITER_BVEC-type iterators.

The problem is that it accidentally reduces maxsize to 0 when it
skipping and thus runs to the end of the array and returns 0.

Fix this by sticking the calculated size-to-copy in a new variable
rather than back in maxsize.

Fixes: 7d58fe731028 ("iov_iter: Add a function to extract a page list from an iterator")
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: David Hildenbrand <david@redhat.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 lib/iov_iter.c | 30 +++++++++++++++---------------
 1 file changed, 15 insertions(+), 15 deletions(-)

diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index b31597b0ca20..27234a820eeb 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -1654,14 +1654,14 @@ static ssize_t iov_iter_extract_bvec_pages(struct iov_iter *i,
 					   size_t *offset0)
 {
 	struct page **p, *page;
-	size_t skip = i->iov_offset, offset;
+	size_t skip = i->iov_offset, offset, size;
 	int k;
 
 	for (;;) {
 		if (i->nr_segs == 0)
 			return 0;
-		maxsize = min(maxsize, i->bvec->bv_len - skip);
-		if (maxsize)
+		size = min(maxsize, i->bvec->bv_len - skip);
+		if (size)
 			break;
 		i->iov_offset = 0;
 		i->nr_segs--;
@@ -1674,16 +1674,16 @@ static ssize_t iov_iter_extract_bvec_pages(struct iov_iter *i,
 	offset = skip % PAGE_SIZE;
 	*offset0 = offset;
 
-	maxpages = want_pages_array(pages, maxsize, offset, maxpages);
+	maxpages = want_pages_array(pages, size, offset, maxpages);
 	if (!maxpages)
 		return -ENOMEM;
 	p = *pages;
 	for (k = 0; k < maxpages; k++)
 		p[k] = page + k;
 
-	maxsize = min_t(size_t, maxsize, maxpages * PAGE_SIZE - offset);
-	iov_iter_advance(i, maxsize);
-	return maxsize;
+	size = min_t(size_t, size, maxpages * PAGE_SIZE - offset);
+	iov_iter_advance(i, size);
+	return size;
 }
 
 /*
@@ -1698,14 +1698,14 @@ static ssize_t iov_iter_extract_kvec_pages(struct iov_iter *i,
 {
 	struct page **p, *page;
 	const void *kaddr;
-	size_t skip = i->iov_offset, offset, len;
+	size_t skip = i->iov_offset, offset, len, size;
 	int k;
 
 	for (;;) {
 		if (i->nr_segs == 0)
 			return 0;
-		maxsize = min(maxsize, i->kvec->iov_len - skip);
-		if (maxsize)
+		size = min(maxsize, i->kvec->iov_len - skip);
+		if (size)
 			break;
 		i->iov_offset = 0;
 		i->nr_segs--;
@@ -1717,13 +1717,13 @@ static ssize_t iov_iter_extract_kvec_pages(struct iov_iter *i,
 	offset = (unsigned long)kaddr & ~PAGE_MASK;
 	*offset0 = offset;
 
-	maxpages = want_pages_array(pages, maxsize, offset, maxpages);
+	maxpages = want_pages_array(pages, size, offset, maxpages);
 	if (!maxpages)
 		return -ENOMEM;
 	p = *pages;
 
 	kaddr -= offset;
-	len = offset + maxsize;
+	len = offset + size;
 	for (k = 0; k < maxpages; k++) {
 		size_t seg = min_t(size_t, len, PAGE_SIZE);
 
@@ -1737,9 +1737,9 @@ static ssize_t iov_iter_extract_kvec_pages(struct iov_iter *i,
 		kaddr += PAGE_SIZE;
 	}
 
-	maxsize = min_t(size_t, maxsize, maxpages * PAGE_SIZE - offset);
-	iov_iter_advance(i, maxsize);
-	return maxsize;
+	size = min_t(size_t, size, maxpages * PAGE_SIZE - offset);
+	iov_iter_advance(i, size);
+	return size;
 }
 
 /*

From 2d71340ff1d41a5b9fc1b30ded12d638b2e2ae96 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 8 Sep 2023 17:03:21 +0100
Subject: [PATCH 1187/1189] iov_iter: Kunit tests for copying to/from an
 iterator

Add some kunit tests for page extraction for ITER_BVEC, ITER_KVEC and
ITER_XARRAY type iterators.  ITER_UBUF and ITER_IOVEC aren't dealt with
as they require userspace VM interaction.  ITER_DISCARD isn't dealt with
either as that does nothing.

Signed-off-by: David Howells <dhowells@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: David Hildenbrand <david@redhat.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 lib/Kconfig.debug    |  11 +
 lib/Makefile         |   1 +
 lib/kunit_iov_iter.c | 537 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 549 insertions(+)
 create mode 100644 lib/kunit_iov_iter.c

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 319cfbeb0738..fa307f93fa2e 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2237,6 +2237,17 @@ config TEST_DIV64
 
 	  If unsure, say N.
 
+config TEST_IOV_ITER
+	tristate "Test iov_iter operation" if !KUNIT_ALL_TESTS
+	depends on KUNIT
+	default KUNIT_ALL_TESTS
+	help
+	  Enable this to turn on testing of the operation of the I/O iterator
+	  (iov_iter). This test is executed only once during system boot (so
+	  affects only boot time), or at module load time.
+
+	  If unsure, say N.
+
 config KPROBES_SANITY_TEST
 	tristate "Kprobes sanity tests" if !KUNIT_ALL_TESTS
 	depends on DEBUG_KERNEL
diff --git a/lib/Makefile b/lib/Makefile
index 2e08397f6210..740109b6e2c8 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -64,6 +64,7 @@ obj-$(CONFIG_TEST_BITOPS) += test_bitops.o
 CFLAGS_test_bitops.o += -Werror
 obj-$(CONFIG_CPUMASK_KUNIT_TEST) += cpumask_kunit.o
 obj-$(CONFIG_TEST_SYSCTL) += test_sysctl.o
+obj-$(CONFIG_TEST_IOV_ITER) += kunit_iov_iter.o
 obj-$(CONFIG_HASH_KUNIT_TEST) += test_hash.o
 obj-$(CONFIG_TEST_IDA) += test_ida.o
 obj-$(CONFIG_TEST_UBSAN) += test_ubsan.o
diff --git a/lib/kunit_iov_iter.c b/lib/kunit_iov_iter.c
new file mode 100644
index 000000000000..25a910187d17
--- /dev/null
+++ b/lib/kunit_iov_iter.c
@@ -0,0 +1,537 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* I/O iterator tests.  This can only test kernel-backed iterator types.
+ *
+ * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/vmalloc.h>
+#include <linux/mm.h>
+#include <linux/uio.h>
+#include <linux/bvec.h>
+#include <kunit/test.h>
+
+MODULE_DESCRIPTION("iov_iter testing");
+MODULE_AUTHOR("David Howells <dhowells@redhat.com>");
+MODULE_LICENSE("GPL");
+
+struct kvec_test_range {
+	int	from, to;
+};
+
+static const struct kvec_test_range kvec_test_ranges[] = {
+	{ 0x00002, 0x00002 },
+	{ 0x00027, 0x03000 },
+	{ 0x05193, 0x18794 },
+	{ 0x20000, 0x20000 },
+	{ 0x20000, 0x24000 },
+	{ 0x24000, 0x27001 },
+	{ 0x29000, 0xffffb },
+	{ 0xffffd, 0xffffe },
+	{ -1 }
+};
+
+static inline u8 pattern(unsigned long x)
+{
+	return x & 0xff;
+}
+
+static void iov_kunit_unmap(void *data)
+{
+	vunmap(data);
+}
+
+static void *__init iov_kunit_create_buffer(struct kunit *test,
+					    struct page ***ppages,
+					    size_t npages)
+{
+	struct page **pages;
+	unsigned long got;
+	void *buffer;
+
+	pages = kunit_kcalloc(test, npages, sizeof(struct page *), GFP_KERNEL);
+        KUNIT_ASSERT_NOT_ERR_OR_NULL(test, pages);
+	*ppages = pages;
+
+	got = alloc_pages_bulk_array(GFP_KERNEL, npages, pages);
+	if (got != npages) {
+		release_pages(pages, got);
+		KUNIT_ASSERT_EQ(test, got, npages);
+	}
+
+	buffer = vmap(pages, npages, VM_MAP | VM_MAP_PUT_PAGES, PAGE_KERNEL);
+        KUNIT_ASSERT_NOT_ERR_OR_NULL(test, buffer);
+
+	kunit_add_action_or_reset(test, iov_kunit_unmap, buffer);
+	return buffer;
+}
+
+static void __init iov_kunit_load_kvec(struct kunit *test,
+				       struct iov_iter *iter, int dir,
+				       struct kvec *kvec, unsigned int kvmax,
+				       void *buffer, size_t bufsize,
+				       const struct kvec_test_range *pr)
+{
+	size_t size = 0;
+	int i;
+
+	for (i = 0; i < kvmax; i++, pr++) {
+		if (pr->from < 0)
+			break;
+		KUNIT_ASSERT_GE(test, pr->to, pr->from);
+		KUNIT_ASSERT_LE(test, pr->to, bufsize);
+		kvec[i].iov_base = buffer + pr->from;
+		kvec[i].iov_len = pr->to - pr->from;
+		size += pr->to - pr->from;
+	}
+	KUNIT_ASSERT_LE(test, size, bufsize);
+
+	iov_iter_kvec(iter, dir, kvec, i, size);
+}
+
+/*
+ * Test copying to a ITER_KVEC-type iterator.
+ */
+static void __init iov_kunit_copy_to_kvec(struct kunit *test)
+{
+	const struct kvec_test_range *pr;
+	struct iov_iter iter;
+	struct page **spages, **bpages;
+	struct kvec kvec[8];
+	u8 *scratch, *buffer;
+	size_t bufsize, npages, size, copied;
+	int i, patt;
+
+	bufsize = 0x100000;
+	npages = bufsize / PAGE_SIZE;
+
+	scratch = iov_kunit_create_buffer(test, &spages, npages);
+	for (i = 0; i < bufsize; i++)
+		scratch[i] = pattern(i);
+
+	buffer = iov_kunit_create_buffer(test, &bpages, npages);
+	memset(buffer, 0, bufsize);
+
+	iov_kunit_load_kvec(test, &iter, READ, kvec, ARRAY_SIZE(kvec),
+			    buffer, bufsize, kvec_test_ranges);
+	size = iter.count;
+
+	copied = copy_to_iter(scratch, size, &iter);
+
+	KUNIT_EXPECT_EQ(test, copied, size);
+	KUNIT_EXPECT_EQ(test, iter.count, 0);
+	KUNIT_EXPECT_EQ(test, iter.nr_segs, 0);
+
+	/* Build the expected image in the scratch buffer. */
+	patt = 0;
+	memset(scratch, 0, bufsize);
+	for (pr = kvec_test_ranges; pr->from >= 0; pr++)
+		for (i = pr->from; i < pr->to; i++)
+			scratch[i] = pattern(patt++);
+
+	/* Compare the images */
+	for (i = 0; i < bufsize; i++) {
+		KUNIT_EXPECT_EQ_MSG(test, buffer[i], scratch[i], "at i=%x", i);
+		if (buffer[i] != scratch[i])
+			return;
+	}
+
+	KUNIT_SUCCEED();
+}
+
+/*
+ * Test copying from a ITER_KVEC-type iterator.
+ */
+static void __init iov_kunit_copy_from_kvec(struct kunit *test)
+{
+	const struct kvec_test_range *pr;
+	struct iov_iter iter;
+	struct page **spages, **bpages;
+	struct kvec kvec[8];
+	u8 *scratch, *buffer;
+	size_t bufsize, npages, size, copied;
+	int i, j;
+
+	bufsize = 0x100000;
+	npages = bufsize / PAGE_SIZE;
+
+	buffer = iov_kunit_create_buffer(test, &bpages, npages);
+	for (i = 0; i < bufsize; i++)
+		buffer[i] = pattern(i);
+
+	scratch = iov_kunit_create_buffer(test, &spages, npages);
+	memset(scratch, 0, bufsize);
+
+	iov_kunit_load_kvec(test, &iter, WRITE, kvec, ARRAY_SIZE(kvec),
+			    buffer, bufsize, kvec_test_ranges);
+	size = min(iter.count, bufsize);
+
+	copied = copy_from_iter(scratch, size, &iter);
+
+	KUNIT_EXPECT_EQ(test, copied, size);
+	KUNIT_EXPECT_EQ(test, iter.count, 0);
+	KUNIT_EXPECT_EQ(test, iter.nr_segs, 0);
+
+	/* Build the expected image in the main buffer. */
+	i = 0;
+	memset(buffer, 0, bufsize);
+	for (pr = kvec_test_ranges; pr->from >= 0; pr++) {
+		for (j = pr->from; j < pr->to; j++) {
+			buffer[i++] = pattern(j);
+			if (i >= bufsize)
+				goto stop;
+		}
+	}
+stop:
+
+	/* Compare the images */
+	for (i = 0; i < bufsize; i++) {
+		KUNIT_EXPECT_EQ_MSG(test, scratch[i], buffer[i], "at i=%x", i);
+		if (scratch[i] != buffer[i])
+			return;
+	}
+
+	KUNIT_SUCCEED();
+}
+
+struct bvec_test_range {
+	int	page, from, to;
+};
+
+static const struct bvec_test_range bvec_test_ranges[] = {
+	{ 0, 0x0002, 0x0002 },
+	{ 1, 0x0027, 0x0893 },
+	{ 2, 0x0193, 0x0794 },
+	{ 3, 0x0000, 0x1000 },
+	{ 4, 0x0000, 0x1000 },
+	{ 5, 0x0000, 0x1000 },
+	{ 6, 0x0000, 0x0ffb },
+	{ 6, 0x0ffd, 0x0ffe },
+	{ -1, -1, -1 }
+};
+
+static void __init iov_kunit_load_bvec(struct kunit *test,
+				       struct iov_iter *iter, int dir,
+				       struct bio_vec *bvec, unsigned int bvmax,
+				       struct page **pages, size_t npages,
+				       size_t bufsize,
+				       const struct bvec_test_range *pr)
+{
+	struct page *can_merge = NULL, *page;
+	size_t size = 0;
+	int i;
+
+	for (i = 0; i < bvmax; i++, pr++) {
+		if (pr->from < 0)
+			break;
+		KUNIT_ASSERT_LT(test, pr->page, npages);
+		KUNIT_ASSERT_LT(test, pr->page * PAGE_SIZE, bufsize);
+		KUNIT_ASSERT_GE(test, pr->from, 0);
+		KUNIT_ASSERT_GE(test, pr->to, pr->from);
+		KUNIT_ASSERT_LE(test, pr->to, PAGE_SIZE);
+
+		page = pages[pr->page];
+		if (pr->from == 0 && pr->from != pr->to && page == can_merge) {
+			i--;
+			bvec[i].bv_len += pr->to;
+		} else {
+			bvec_set_page(&bvec[i], page, pr->to - pr->from, pr->from);
+		}
+
+		size += pr->to - pr->from;
+		if ((pr->to & ~PAGE_MASK) == 0)
+			can_merge = page + pr->to / PAGE_SIZE;
+		else
+			can_merge = NULL;
+	}
+
+	iov_iter_bvec(iter, dir, bvec, i, size);
+}
+
+/*
+ * Test copying to a ITER_BVEC-type iterator.
+ */
+static void __init iov_kunit_copy_to_bvec(struct kunit *test)
+{
+	const struct bvec_test_range *pr;
+	struct iov_iter iter;
+	struct bio_vec bvec[8];
+	struct page **spages, **bpages;
+	u8 *scratch, *buffer;
+	size_t bufsize, npages, size, copied;
+	int i, b, patt;
+
+	bufsize = 0x100000;
+	npages = bufsize / PAGE_SIZE;
+
+	scratch = iov_kunit_create_buffer(test, &spages, npages);
+	for (i = 0; i < bufsize; i++)
+		scratch[i] = pattern(i);
+
+	buffer = iov_kunit_create_buffer(test, &bpages, npages);
+	memset(buffer, 0, bufsize);
+
+	iov_kunit_load_bvec(test, &iter, READ, bvec, ARRAY_SIZE(bvec),
+			    bpages, npages, bufsize, bvec_test_ranges);
+	size = iter.count;
+
+	copied = copy_to_iter(scratch, size, &iter);
+
+	KUNIT_EXPECT_EQ(test, copied, size);
+	KUNIT_EXPECT_EQ(test, iter.count, 0);
+	KUNIT_EXPECT_EQ(test, iter.nr_segs, 0);
+
+	/* Build the expected image in the scratch buffer. */
+	b = 0;
+	patt = 0;
+	memset(scratch, 0, bufsize);
+	for (pr = bvec_test_ranges; pr->from >= 0; pr++, b++) {
+		u8 *p = scratch + pr->page * PAGE_SIZE;
+
+		for (i = pr->from; i < pr->to; i++)
+			p[i] = pattern(patt++);
+	}
+
+	/* Compare the images */
+	for (i = 0; i < bufsize; i++) {
+		KUNIT_EXPECT_EQ_MSG(test, buffer[i], scratch[i], "at i=%x", i);
+		if (buffer[i] != scratch[i])
+			return;
+	}
+
+	KUNIT_SUCCEED();
+}
+
+/*
+ * Test copying from a ITER_BVEC-type iterator.
+ */
+static void __init iov_kunit_copy_from_bvec(struct kunit *test)
+{
+	const struct bvec_test_range *pr;
+	struct iov_iter iter;
+	struct bio_vec bvec[8];
+	struct page **spages, **bpages;
+	u8 *scratch, *buffer;
+	size_t bufsize, npages, size, copied;
+	int i, j;
+
+	bufsize = 0x100000;
+	npages = bufsize / PAGE_SIZE;
+
+	buffer = iov_kunit_create_buffer(test, &bpages, npages);
+	for (i = 0; i < bufsize; i++)
+		buffer[i] = pattern(i);
+
+	scratch = iov_kunit_create_buffer(test, &spages, npages);
+	memset(scratch, 0, bufsize);
+
+	iov_kunit_load_bvec(test, &iter, WRITE, bvec, ARRAY_SIZE(bvec),
+			    bpages, npages, bufsize, bvec_test_ranges);
+	size = iter.count;
+
+	copied = copy_from_iter(scratch, size, &iter);
+
+	KUNIT_EXPECT_EQ(test, copied, size);
+	KUNIT_EXPECT_EQ(test, iter.count, 0);
+	KUNIT_EXPECT_EQ(test, iter.nr_segs, 0);
+
+	/* Build the expected image in the main buffer. */
+	i = 0;
+	memset(buffer, 0, bufsize);
+	for (pr = bvec_test_ranges; pr->from >= 0; pr++) {
+		size_t patt = pr->page * PAGE_SIZE;
+
+		for (j = pr->from; j < pr->to; j++) {
+			buffer[i++] = pattern(patt + j);
+			if (i >= bufsize)
+				goto stop;
+		}
+	}
+stop:
+
+	/* Compare the images */
+	for (i = 0; i < bufsize; i++) {
+		KUNIT_EXPECT_EQ_MSG(test, scratch[i], buffer[i], "at i=%x", i);
+		if (scratch[i] != buffer[i])
+			return;
+	}
+
+	KUNIT_SUCCEED();
+}
+
+static void iov_kunit_destroy_xarray(void *data)
+{
+	struct xarray *xarray = data;
+
+	xa_destroy(xarray);
+	kfree(xarray);
+}
+
+static void __init iov_kunit_load_xarray(struct kunit *test,
+					 struct iov_iter *iter, int dir,
+					 struct xarray *xarray,
+					 struct page **pages, size_t npages)
+{
+	size_t size = 0;
+	int i;
+
+	for (i = 0; i < npages; i++) {
+		void *x = xa_store(xarray, i, pages[i], GFP_KERNEL);
+
+		KUNIT_ASSERT_FALSE(test, xa_is_err(x));
+		size += PAGE_SIZE;
+	}
+	iov_iter_xarray(iter, dir, xarray, 0, size);
+}
+
+static struct xarray *iov_kunit_create_xarray(struct kunit *test)
+{
+	struct xarray *xarray;
+
+	xarray = kzalloc(sizeof(struct xarray), GFP_KERNEL);
+	xa_init(xarray);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, xarray);
+	kunit_add_action_or_reset(test, iov_kunit_destroy_xarray, xarray);
+	return xarray;
+}
+
+/*
+ * Test copying to a ITER_XARRAY-type iterator.
+ */
+static void __init iov_kunit_copy_to_xarray(struct kunit *test)
+{
+	const struct kvec_test_range *pr;
+	struct iov_iter iter;
+	struct xarray *xarray;
+	struct page **spages, **bpages;
+	u8 *scratch, *buffer;
+	size_t bufsize, npages, size, copied;
+	int i, patt;
+
+	bufsize = 0x100000;
+	npages = bufsize / PAGE_SIZE;
+
+	xarray = iov_kunit_create_xarray(test);
+
+	scratch = iov_kunit_create_buffer(test, &spages, npages);
+	for (i = 0; i < bufsize; i++)
+		scratch[i] = pattern(i);
+
+	buffer = iov_kunit_create_buffer(test, &bpages, npages);
+	memset(buffer, 0, bufsize);
+
+	iov_kunit_load_xarray(test, &iter, READ, xarray, bpages, npages);
+
+	i = 0;
+	for (pr = kvec_test_ranges; pr->from >= 0; pr++) {
+		size = pr->to - pr->from;
+		KUNIT_ASSERT_LE(test, pr->to, bufsize);
+
+		iov_iter_xarray(&iter, READ, xarray, pr->from, size);
+		copied = copy_to_iter(scratch + i, size, &iter);
+
+		KUNIT_EXPECT_EQ(test, copied, size);
+		KUNIT_EXPECT_EQ(test, iter.count, 0);
+		KUNIT_EXPECT_EQ(test, iter.iov_offset, size);
+		i += size;
+	}
+
+	/* Build the expected image in the scratch buffer. */
+	patt = 0;
+	memset(scratch, 0, bufsize);
+	for (pr = kvec_test_ranges; pr->from >= 0; pr++)
+		for (i = pr->from; i < pr->to; i++)
+			scratch[i] = pattern(patt++);
+
+	/* Compare the images */
+	for (i = 0; i < bufsize; i++) {
+		KUNIT_EXPECT_EQ_MSG(test, buffer[i], scratch[i], "at i=%x", i);
+		if (buffer[i] != scratch[i])
+			return;
+	}
+
+	KUNIT_SUCCEED();
+}
+
+/*
+ * Test copying from a ITER_XARRAY-type iterator.
+ */
+static void __init iov_kunit_copy_from_xarray(struct kunit *test)
+{
+	const struct kvec_test_range *pr;
+	struct iov_iter iter;
+	struct xarray *xarray;
+	struct page **spages, **bpages;
+	u8 *scratch, *buffer;
+	size_t bufsize, npages, size, copied;
+	int i, j;
+
+	bufsize = 0x100000;
+	npages = bufsize / PAGE_SIZE;
+
+	xarray = iov_kunit_create_xarray(test);
+
+	buffer = iov_kunit_create_buffer(test, &bpages, npages);
+	for (i = 0; i < bufsize; i++)
+		buffer[i] = pattern(i);
+
+	scratch = iov_kunit_create_buffer(test, &spages, npages);
+	memset(scratch, 0, bufsize);
+
+	iov_kunit_load_xarray(test, &iter, READ, xarray, bpages, npages);
+
+	i = 0;
+	for (pr = kvec_test_ranges; pr->from >= 0; pr++) {
+		size = pr->to - pr->from;
+		KUNIT_ASSERT_LE(test, pr->to, bufsize);
+
+		iov_iter_xarray(&iter, WRITE, xarray, pr->from, size);
+		copied = copy_from_iter(scratch + i, size, &iter);
+
+		KUNIT_EXPECT_EQ(test, copied, size);
+		KUNIT_EXPECT_EQ(test, iter.count, 0);
+		KUNIT_EXPECT_EQ(test, iter.iov_offset, size);
+		i += size;
+	}
+
+	/* Build the expected image in the main buffer. */
+	i = 0;
+	memset(buffer, 0, bufsize);
+	for (pr = kvec_test_ranges; pr->from >= 0; pr++) {
+		for (j = pr->from; j < pr->to; j++) {
+			buffer[i++] = pattern(j);
+			if (i >= bufsize)
+				goto stop;
+		}
+	}
+stop:
+
+	/* Compare the images */
+	for (i = 0; i < bufsize; i++) {
+		KUNIT_EXPECT_EQ_MSG(test, scratch[i], buffer[i], "at i=%x", i);
+		if (scratch[i] != buffer[i])
+			return;
+	}
+
+	KUNIT_SUCCEED();
+}
+
+static struct kunit_case __refdata iov_kunit_cases[] = {
+	KUNIT_CASE(iov_kunit_copy_to_kvec),
+	KUNIT_CASE(iov_kunit_copy_from_kvec),
+	KUNIT_CASE(iov_kunit_copy_to_bvec),
+	KUNIT_CASE(iov_kunit_copy_from_bvec),
+	KUNIT_CASE(iov_kunit_copy_to_xarray),
+	KUNIT_CASE(iov_kunit_copy_from_xarray),
+	{}
+};
+
+static struct kunit_suite iov_kunit_suite = {
+	.name = "iov_iter",
+	.test_cases = iov_kunit_cases,
+};
+
+kunit_test_suites(&iov_kunit_suite);

From a3c57ab79a06e333a869ae340420cb3c6f5921d3 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 8 Sep 2023 17:03:22 +0100
Subject: [PATCH 1188/1189] iov_iter: Kunit tests for page extraction

Add some kunit tests for page extraction for ITER_BVEC, ITER_KVEC and
ITER_XARRAY type iterators.  ITER_UBUF and ITER_IOVEC aren't dealt with
as they require userspace VM interaction.  ITER_DISCARD isn't dealt with
either as that can't be extracted.

Signed-off-by: David Howells <dhowells@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: David Hildenbrand <david@redhat.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 lib/kunit_iov_iter.c | 240 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 240 insertions(+)

diff --git a/lib/kunit_iov_iter.c b/lib/kunit_iov_iter.c
index 25a910187d17..859b67c4d697 100644
--- a/lib/kunit_iov_iter.c
+++ b/lib/kunit_iov_iter.c
@@ -519,6 +519,243 @@ stop:
 	KUNIT_SUCCEED();
 }
 
+/*
+ * Test the extraction of ITER_KVEC-type iterators.
+ */
+static void __init iov_kunit_extract_pages_kvec(struct kunit *test)
+{
+	const struct kvec_test_range *pr;
+	struct iov_iter iter;
+	struct page **bpages, *pagelist[8], **pages = pagelist;
+	struct kvec kvec[8];
+	u8 *buffer;
+	ssize_t len;
+	size_t bufsize, size = 0, npages;
+	int i, from;
+
+	bufsize = 0x100000;
+	npages = bufsize / PAGE_SIZE;
+
+	buffer = iov_kunit_create_buffer(test, &bpages, npages);
+
+	iov_kunit_load_kvec(test, &iter, READ, kvec, ARRAY_SIZE(kvec),
+			    buffer, bufsize, kvec_test_ranges);
+	size = iter.count;
+
+	pr = kvec_test_ranges;
+	from = pr->from;
+	do {
+		size_t offset0 = LONG_MAX;
+
+		for (i = 0; i < ARRAY_SIZE(pagelist); i++)
+			pagelist[i] = (void *)(unsigned long)0xaa55aa55aa55aa55ULL;
+
+		len = iov_iter_extract_pages(&iter, &pages, 100 * 1024,
+					     ARRAY_SIZE(pagelist), 0, &offset0);
+		KUNIT_EXPECT_GE(test, len, 0);
+		if (len < 0)
+			break;
+		KUNIT_EXPECT_GE(test, (ssize_t)offset0, 0);
+		KUNIT_EXPECT_LT(test, offset0, PAGE_SIZE);
+		KUNIT_EXPECT_LE(test, len, size);
+		KUNIT_EXPECT_EQ(test, iter.count, size - len);
+		size -= len;
+
+		if (len == 0)
+			break;
+
+		for (i = 0; i < ARRAY_SIZE(pagelist); i++) {
+			struct page *p;
+			ssize_t part = min_t(ssize_t, len, PAGE_SIZE - offset0);
+			int ix;
+
+			KUNIT_ASSERT_GE(test, part, 0);
+			while (from == pr->to) {
+				pr++;
+				from = pr->from;
+				if (from < 0)
+					goto stop;
+			}
+			ix = from / PAGE_SIZE;
+			KUNIT_ASSERT_LT(test, ix, npages);
+			p = bpages[ix];
+			KUNIT_EXPECT_PTR_EQ(test, pagelist[i], p);
+			KUNIT_EXPECT_EQ(test, offset0, from % PAGE_SIZE);
+			from += part;
+			len -= part;
+			KUNIT_ASSERT_GE(test, len, 0);
+			if (len == 0)
+				break;
+			offset0 = 0;
+		}
+
+		if (test->status == KUNIT_FAILURE)
+			break;
+	} while (iov_iter_count(&iter) > 0);
+
+stop:
+	KUNIT_EXPECT_EQ(test, size, 0);
+	KUNIT_EXPECT_EQ(test, iter.count, 0);
+	KUNIT_SUCCEED();
+}
+
+/*
+ * Test the extraction of ITER_BVEC-type iterators.
+ */
+static void __init iov_kunit_extract_pages_bvec(struct kunit *test)
+{
+	const struct bvec_test_range *pr;
+	struct iov_iter iter;
+	struct page **bpages, *pagelist[8], **pages = pagelist;
+	struct bio_vec bvec[8];
+	ssize_t len;
+	size_t bufsize, size = 0, npages;
+	int i, from;
+
+	bufsize = 0x100000;
+	npages = bufsize / PAGE_SIZE;
+
+	iov_kunit_create_buffer(test, &bpages, npages);
+	iov_kunit_load_bvec(test, &iter, READ, bvec, ARRAY_SIZE(bvec),
+			    bpages, npages, bufsize, bvec_test_ranges);
+	size = iter.count;
+
+	pr = bvec_test_ranges;
+	from = pr->from;
+	do {
+		size_t offset0 = LONG_MAX;
+
+		for (i = 0; i < ARRAY_SIZE(pagelist); i++)
+			pagelist[i] = (void *)(unsigned long)0xaa55aa55aa55aa55ULL;
+
+		len = iov_iter_extract_pages(&iter, &pages, 100 * 1024,
+					     ARRAY_SIZE(pagelist), 0, &offset0);
+		KUNIT_EXPECT_GE(test, len, 0);
+		if (len < 0)
+			break;
+		KUNIT_EXPECT_GE(test, (ssize_t)offset0, 0);
+		KUNIT_EXPECT_LT(test, offset0, PAGE_SIZE);
+		KUNIT_EXPECT_LE(test, len, size);
+		KUNIT_EXPECT_EQ(test, iter.count, size - len);
+		size -= len;
+
+		if (len == 0)
+			break;
+
+		for (i = 0; i < ARRAY_SIZE(pagelist); i++) {
+			struct page *p;
+			ssize_t part = min_t(ssize_t, len, PAGE_SIZE - offset0);
+			int ix;
+
+			KUNIT_ASSERT_GE(test, part, 0);
+			while (from == pr->to) {
+				pr++;
+				from = pr->from;
+				if (from < 0)
+					goto stop;
+			}
+			ix = pr->page + from / PAGE_SIZE;
+			KUNIT_ASSERT_LT(test, ix, npages);
+			p = bpages[ix];
+			KUNIT_EXPECT_PTR_EQ(test, pagelist[i], p);
+			KUNIT_EXPECT_EQ(test, offset0, from % PAGE_SIZE);
+			from += part;
+			len -= part;
+			KUNIT_ASSERT_GE(test, len, 0);
+			if (len == 0)
+				break;
+			offset0 = 0;
+		}
+
+		if (test->status == KUNIT_FAILURE)
+			break;
+	} while (iov_iter_count(&iter) > 0);
+
+stop:
+	KUNIT_EXPECT_EQ(test, size, 0);
+	KUNIT_EXPECT_EQ(test, iter.count, 0);
+	KUNIT_SUCCEED();
+}
+
+/*
+ * Test the extraction of ITER_XARRAY-type iterators.
+ */
+static void __init iov_kunit_extract_pages_xarray(struct kunit *test)
+{
+	const struct kvec_test_range *pr;
+	struct iov_iter iter;
+	struct xarray *xarray;
+	struct page **bpages, *pagelist[8], **pages = pagelist;
+	ssize_t len;
+	size_t bufsize, size = 0, npages;
+	int i, from;
+
+	bufsize = 0x100000;
+	npages = bufsize / PAGE_SIZE;
+
+	xarray = iov_kunit_create_xarray(test);
+
+	iov_kunit_create_buffer(test, &bpages, npages);
+	iov_kunit_load_xarray(test, &iter, READ, xarray, bpages, npages);
+
+	for (pr = kvec_test_ranges; pr->from >= 0; pr++) {
+		from = pr->from;
+		size = pr->to - from;
+		KUNIT_ASSERT_LE(test, pr->to, bufsize);
+
+		iov_iter_xarray(&iter, WRITE, xarray, from, size);
+
+		do {
+			size_t offset0 = LONG_MAX;
+
+			for (i = 0; i < ARRAY_SIZE(pagelist); i++)
+				pagelist[i] = (void *)(unsigned long)0xaa55aa55aa55aa55ULL;
+
+			len = iov_iter_extract_pages(&iter, &pages, 100 * 1024,
+						     ARRAY_SIZE(pagelist), 0, &offset0);
+			KUNIT_EXPECT_GE(test, len, 0);
+			if (len < 0)
+				break;
+			KUNIT_EXPECT_LE(test, len, size);
+			KUNIT_EXPECT_EQ(test, iter.count, size - len);
+			if (len == 0)
+				break;
+			size -= len;
+			KUNIT_EXPECT_GE(test, (ssize_t)offset0, 0);
+			KUNIT_EXPECT_LT(test, offset0, PAGE_SIZE);
+
+			for (i = 0; i < ARRAY_SIZE(pagelist); i++) {
+				struct page *p;
+				ssize_t part = min_t(ssize_t, len, PAGE_SIZE - offset0);
+				int ix;
+
+				KUNIT_ASSERT_GE(test, part, 0);
+				ix = from / PAGE_SIZE;
+				KUNIT_ASSERT_LT(test, ix, npages);
+				p = bpages[ix];
+				KUNIT_EXPECT_PTR_EQ(test, pagelist[i], p);
+				KUNIT_EXPECT_EQ(test, offset0, from % PAGE_SIZE);
+				from += part;
+				len -= part;
+				KUNIT_ASSERT_GE(test, len, 0);
+				if (len == 0)
+					break;
+				offset0 = 0;
+			}
+
+			if (test->status == KUNIT_FAILURE)
+				goto stop;
+		} while (iov_iter_count(&iter) > 0);
+
+		KUNIT_EXPECT_EQ(test, size, 0);
+		KUNIT_EXPECT_EQ(test, iter.count, 0);
+		KUNIT_EXPECT_EQ(test, iter.iov_offset, pr->to - pr->from);
+	}
+
+stop:
+	KUNIT_SUCCEED();
+}
+
 static struct kunit_case __refdata iov_kunit_cases[] = {
 	KUNIT_CASE(iov_kunit_copy_to_kvec),
 	KUNIT_CASE(iov_kunit_copy_from_kvec),
@@ -526,6 +763,9 @@ static struct kunit_case __refdata iov_kunit_cases[] = {
 	KUNIT_CASE(iov_kunit_copy_from_bvec),
 	KUNIT_CASE(iov_kunit_copy_to_xarray),
 	KUNIT_CASE(iov_kunit_copy_from_xarray),
+	KUNIT_CASE(iov_kunit_extract_pages_kvec),
+	KUNIT_CASE(iov_kunit_extract_pages_bvec),
+	KUNIT_CASE(iov_kunit_extract_pages_xarray),
 	{}
 };
 

From 0bb80ecc33a8fb5a682236443c1e740d5c917d1d Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 10 Sep 2023 16:28:41 -0700
Subject: [PATCH 1189/1189] Linux 6.6-rc1

---
 Makefile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Makefile b/Makefile
index 73f23fa0677a..ceb23eed4dce 100644
--- a/Makefile
+++ b/Makefile
@@ -1,8 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 6
-PATCHLEVEL = 5
+PATCHLEVEL = 6
 SUBLEVEL = 0
-EXTRAVERSION =
+EXTRAVERSION = -rc1
 NAME = Hurr durr I'ma ninja sloth
 
 # *DOCUMENTATION*