From b8b1ab133e593f0dbfa47b174a54b852af6f856e Mon Sep 17 00:00:00 2001 From: Allen-KH Cheng Date: Fri, 11 Mar 2022 21:07:29 +0800 Subject: [PATCH 01/49] dt-bindings: timer: Add compatible for Mediatek MT8186 This commit adds dt-binding documentation of timer for Mediatek MT8186 SoC Platform. Signed-off-by: Allen-KH Cheng Acked-by: Rob Herring Link: https://lore.kernel.org/r/20220311130732.22706-2-allen-kh.cheng@mediatek.com Signed-off-by: Daniel Lezcano --- Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt b/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt index fbd76a8e023b..6f1f9dba6e88 100644 --- a/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt +++ b/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt @@ -23,6 +23,7 @@ Required properties: For those SoCs that use SYST * "mediatek,mt8183-timer" for MT8183 compatible timers (SYST) + * "mediatek,mt8186-timer" for MT8186 compatible timers (SYST) * "mediatek,mt8192-timer" for MT8192 compatible timers (SYST) * "mediatek,mt8195-timer" for MT8195 compatible timers (SYST) * "mediatek,mt7629-timer" for MT7629 compatible timers (SYST) From 41929c9f628b9990d33a200c54bb0c919e089aa8 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 6 Apr 2022 22:55:05 +0200 Subject: [PATCH 02/49] clocksource/drivers/ixp4xx: Drop boardfile probe path The boardfiles for IXP4xx have been deleted. Delete all the quirks and code dealing with that boot path and rely solely on device tree boot. Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20220406205505.2332821-1-linus.walleij@linaro.org Signed-off-by: Daniel Lezcano --- drivers/clocksource/Kconfig | 2 +- drivers/clocksource/timer-ixp4xx.c | 25 ---------------------- include/linux/platform_data/timer-ixp4xx.h | 11 ---------- 3 files changed, 1 insertion(+), 37 deletions(-) delete mode 100644 include/linux/platform_data/timer-ixp4xx.h diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index 1589ae7d5abb..8182ff2d12fe 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -80,7 +80,7 @@ config IXP4XX_TIMER bool "Intel XScale IXP4xx timer driver" if COMPILE_TEST depends on HAS_IOMEM select CLKSRC_MMIO - select TIMER_OF if OF + select TIMER_OF help Enables support for the Intel XScale IXP4xx SoC timer. diff --git a/drivers/clocksource/timer-ixp4xx.c b/drivers/clocksource/timer-ixp4xx.c index cbb184953510..720ed70a2964 100644 --- a/drivers/clocksource/timer-ixp4xx.c +++ b/drivers/clocksource/timer-ixp4xx.c @@ -19,8 +19,6 @@ #include #include #include -/* Goes away with OF conversion */ -#include /* * Constants to make it easy to access Timer Control/Status registers @@ -263,28 +261,6 @@ static struct platform_driver ixp4xx_timer_driver = { }; builtin_platform_driver(ixp4xx_timer_driver); -/** - * ixp4xx_timer_setup() - Timer setup function to be called from boardfiles - * @timerbase: physical base of timer block - * @timer_irq: Linux IRQ number for the timer - * @timer_freq: Fixed frequency of the timer - */ -void __init ixp4xx_timer_setup(resource_size_t timerbase, - int timer_irq, - unsigned int timer_freq) -{ - void __iomem *base; - - base = ioremap(timerbase, 0x100); - if (!base) { - pr_crit("IXP4xx: can't remap timer\n"); - return; - } - ixp4xx_timer_register(base, timer_irq, timer_freq); -} -EXPORT_SYMBOL_GPL(ixp4xx_timer_setup); - -#ifdef CONFIG_OF static __init int ixp4xx_of_timer_init(struct device_node *np) { void __iomem *base; @@ -315,4 +291,3 @@ out_unmap: return ret; } TIMER_OF_DECLARE(ixp4xx, "intel,ixp4xx-timer", ixp4xx_of_timer_init); -#endif diff --git a/include/linux/platform_data/timer-ixp4xx.h b/include/linux/platform_data/timer-ixp4xx.h deleted file mode 100644 index ee92ae7edaed..000000000000 --- a/include/linux/platform_data/timer-ixp4xx.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __TIMER_IXP4XX_H -#define __TIMER_IXP4XX_H - -#include - -void __init ixp4xx_timer_setup(resource_size_t timerbase, - int timer_irq, - unsigned int timer_freq); - -#endif From 232ccac1bd9b5bfe73895f527c08623e7fa0752d Mon Sep 17 00:00:00 2001 From: Samuel Holland Date: Sun, 8 May 2022 20:21:21 -0500 Subject: [PATCH 03/49] clocksource/drivers/riscv: Events are stopped during CPU suspend Some implementations of the SBI time extension depend on hart-local state (for example, CSRs) that are lost or hardware that is powered down when a CPU is suspended. To be safe, the clockevents driver cannot assume that timer IRQs will be received during CPU suspend. Fixes: 62b019436814 ("clocksource: new RISC-V SBI timer driver") Signed-off-by: Samuel Holland Reviewed-by: Anup Patel Link: https://lore.kernel.org/r/20220509012121.40031-1-samuel@sholland.org Signed-off-by: Daniel Lezcano --- drivers/clocksource/timer-riscv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clocksource/timer-riscv.c b/drivers/clocksource/timer-riscv.c index 1767f8bf2013..593d5a957b69 100644 --- a/drivers/clocksource/timer-riscv.c +++ b/drivers/clocksource/timer-riscv.c @@ -34,7 +34,7 @@ static int riscv_clock_next_event(unsigned long delta, static unsigned int riscv_clock_event_irq; static DEFINE_PER_CPU(struct clock_event_device, riscv_clock_event) = { .name = "riscv_timer_clockevent", - .features = CLOCK_EVT_FEAT_ONESHOT, + .features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP, .rating = 100, .set_next_event = riscv_clock_next_event, }; From a98399cbc1e05f7b977419f03905501d566cf54e Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Fri, 6 May 2022 17:25:22 +0100 Subject: [PATCH 04/49] clocksource/drivers/sp804: Avoid error on multiple instances When a machine sports more than one SP804 timer instance, we only bring up the first one, since multiple timers of the same kind are not useful to Linux. As this is intentional behaviour, we should not return an error message, as we do today: =============== [ 0.000800] Failed to initialize '/bus@8000000/motherboard-bus@8000000/iofpga-bus@300000000/timer@120000': -22 =============== Replace the -EINVAL return with a debug message and return 0 instead. Also we do not reach the init function anymore if the DT node is disabled (as this is now handled by OF_DECLARE), so remove the explicit check for that case. This fixes a long standing bogus error when booting ARM's fastmodels. Signed-off-by: Andre Przywara Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/20220506162522.3675399-1-andre.przywara@arm.com Signed-off-by: Daniel Lezcano --- drivers/clocksource/timer-sp804.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/clocksource/timer-sp804.c b/drivers/clocksource/timer-sp804.c index 401d592e85f5..e6a87f4af2b5 100644 --- a/drivers/clocksource/timer-sp804.c +++ b/drivers/clocksource/timer-sp804.c @@ -259,6 +259,11 @@ static int __init sp804_of_init(struct device_node *np, struct sp804_timer *time struct clk *clk1, *clk2; const char *name = of_get_property(np, "compatible", NULL); + if (initialized) { + pr_debug("%pOF: skipping further SP804 timer device\n", np); + return 0; + } + base = of_iomap(np, 0); if (!base) return -ENXIO; @@ -270,11 +275,6 @@ static int __init sp804_of_init(struct device_node *np, struct sp804_timer *time writel(0, timer1_base + timer->ctrl); writel(0, timer2_base + timer->ctrl); - if (initialized || !of_device_is_available(np)) { - ret = -EINVAL; - goto err; - } - clk1 = of_clk_get(np, 0); if (IS_ERR(clk1)) clk1 = NULL; From b89e96917dba49d9fda30f2e0c5a8effdf02cca5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 10 May 2022 19:24:37 +0200 Subject: [PATCH 05/49] clocksource/drivers/bcm_kona: Convert to SPDX identifier The license information clearly states GPL version 2 only. The extra text which excludes warranties is a transcript of the corresponding GPLv2 clause 11, which is explicitely referenced for details. So the SPDX identifier covers it completely. Signed-off-by: Thomas Gleixner Cc: Daniel Lezcano Cc: Florian Fainelli Cc: Ray Jui Cc: Scott Branden Cc: Broadcom Kernel Team Cc: linux-spdx@vger.kernel.org Acked-by: Florian Fainelli Link: https://lore.kernel.org/r/20220510171254.404209482@linutronix.de Signed-off-by: Daniel Lezcano --- drivers/clocksource/bcm_kona_timer.c | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) diff --git a/drivers/clocksource/bcm_kona_timer.c b/drivers/clocksource/bcm_kona_timer.c index a50ab5c2154f..39f172d7e29e 100644 --- a/drivers/clocksource/bcm_kona_timer.c +++ b/drivers/clocksource/bcm_kona_timer.c @@ -1,15 +1,5 @@ -/* - * Copyright (C) 2012 Broadcom Corporation - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2012 Broadcom Corporation #include #include From eb988ba4afbf821e8877810221e6bc00af161014 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 10 May 2022 19:24:38 +0200 Subject: [PATCH 06/49] clocksource/drivers/jcore: Convert to SPDX identifier The licensing text references explicitely the COPYING file in the kernel base directory, which is clearly GPL version 2 only. Signed-off-by: Thomas Gleixner Cc: Rich Felker Cc: Daniel Lezcano Link: https://lore.kernel.org/r/20220510171254.467236056@linutronix.de Signed-off-by: Daniel Lezcano --- drivers/clocksource/jcore-pit.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/clocksource/jcore-pit.c b/drivers/clocksource/jcore-pit.c index 5d3d88e0fc8c..a4a991101fa3 100644 --- a/drivers/clocksource/jcore-pit.c +++ b/drivers/clocksource/jcore-pit.c @@ -1,11 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 /* * J-Core SoC PIT/clocksource driver * * Copyright (C) 2015-2016 Smart Energy Instruments, Inc. - * - * 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. */ #include From dcfa47d4720f91e278a81d0f64d2e74e3c59018b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 10 May 2022 19:24:40 +0200 Subject: [PATCH 07/49] clocksource/drivers/mips-gic-timer: Convert to SPDX identifier The licensing text references explicitely the COPYING file in the kernel base directory, which is clearly GPL version 2 only. Signed-off-by: Thomas Gleixner Cc: Thomas Bogendoerfer Cc: Serge Semin Cc: Daniel Lezcano Cc: linux-mips@vger.kernel.org Acked-by: Serge Semin Link: https://lore.kernel.org/r/20220510171254.529249404@linutronix.de Signed-off-by: Daniel Lezcano --- drivers/clocksource/mips-gic-timer.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/drivers/clocksource/mips-gic-timer.c b/drivers/clocksource/mips-gic-timer.c index be4175f415ba..b3ae38f36720 100644 --- a/drivers/clocksource/mips-gic-timer.c +++ b/drivers/clocksource/mips-gic-timer.c @@ -1,10 +1,5 @@ -/* - * 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 MIPS Technologies, Inc. All rights reserved. - */ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2012 MIPS Technologies, Inc. All rights reserved. #define pr_fmt(fmt) "mips-gic-timer: " fmt From 7160d9c4cce94612d5f42a5db392cd606a38737a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 10 May 2022 19:24:41 +0200 Subject: [PATCH 08/49] clocksource/drivers/armada-370-xp: Convert to SPDX identifier The license information clearly states GPL version 2 only. The extra text which excludes warranties is an excerpt of the corresponding GPLv2 clause 11. So the SPDX identifier covers it completely. Signed-off-by: Thomas Gleixner Cc: Gregory Clement Cc: Daniel Lezcano Acked-by: Gregory CLEMENT Link: https://lore.kernel.org/r/20220510171254.592781786@linutronix.de Signed-off-by: Daniel Lezcano --- drivers/clocksource/timer-armada-370-xp.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/clocksource/timer-armada-370-xp.c b/drivers/clocksource/timer-armada-370-xp.c index e3acc3c631b7..6ec565d6939a 100644 --- a/drivers/clocksource/timer-armada-370-xp.c +++ b/drivers/clocksource/timer-armada-370-xp.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Marvell Armada 370/XP SoC timer handling. * @@ -7,10 +8,6 @@ * Gregory CLEMENT * Thomas Petazzoni * - * This file is licensed under the terms of the GNU General Public - * License version 2. This program is licensed "as is" without any - * warranty of any kind, whether express or implied. - * * Timer 0 is used as free-running clocksource, while timer 1 is * used as clock_event_device. * From b3a9ce9d24ffc3e8018dc35a5f4e8f3406cf497f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 10 May 2022 19:24:43 +0200 Subject: [PATCH 09/49] clocksource/drivers/digicolor: Convert to SPDX identifier The license information clearly states GPL version 2 only. The extra text which excludes warranties is an excerpt of the corresponding GPLv2 clause 11. So the SPDX identifier covers it completely. Signed-off-by: Thomas Gleixner Cc: Daniel Lezcano Cc: Baruch Siach Cc: linux-arm-kernel@lists.infradead.org Acked-by: Baruch Siach Link: https://lore.kernel.org/r/20220510171254.655035023@linutronix.de Signed-off-by: Daniel Lezcano --- drivers/clocksource/timer-digicolor.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/clocksource/timer-digicolor.c b/drivers/clocksource/timer-digicolor.c index 1e984a4d8ad0..559aa96089c3 100644 --- a/drivers/clocksource/timer-digicolor.c +++ b/drivers/clocksource/timer-digicolor.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Conexant Digicolor timer driver * @@ -11,10 +12,6 @@ * Copyright (C) 2013 Maxime Ripard * * Maxime Ripard - * - * This file is licensed under the terms of the GNU General Public - * License version 2. This program is licensed "as is" without any - * warranty of any kind, whether express or implied. */ /* From 85c5aafd8e6a2476d27715b57dbcf26805eb3ab7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 10 May 2022 19:24:45 +0200 Subject: [PATCH 10/49] clocksource/drivers/lpc32xx: Convert to SPDX identifier The license information clearly states GPL version 2 only. The extra text which excludes warranties is an excerpt of the corresponding GPLv2 clause 11. So the SPDX identifier covers it completely. Signed-off-by: Thomas Gleixner Cc: Joachim Eastwood Cc: Vladimir Zapolskiy Cc: Daniel Lezcano Cc: linux-arm-kernel@lists.infradead.org Acked-by: Vladimir Zapolskiy Link: https://lore.kernel.org/r/20220510171254.717233312@linutronix.de Signed-off-by: Daniel Lezcano --- drivers/clocksource/timer-lpc32xx.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/clocksource/timer-lpc32xx.c b/drivers/clocksource/timer-lpc32xx.c index d51a62a79ef7..68eae6378bf3 100644 --- a/drivers/clocksource/timer-lpc32xx.c +++ b/drivers/clocksource/timer-lpc32xx.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Clocksource driver for NXP LPC32xx/18xx/43xx timer * @@ -6,11 +7,6 @@ * Based on: * time-efm32 Copyright (C) 2013 Pengutronix * mach-lpc32xx/timer.c Copyright (C) 2009 - 2010 NXP Semiconductors - * - * This file is licensed under the terms of the GNU General Public - * License version 2. This program is licensed "as is" without any - * warranty of any kind, whether express or implied. - * */ #define pr_fmt(fmt) "%s: " fmt, __func__ From 029aede7774c7997f14364ac4aa8c5503e5624e9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 10 May 2022 19:24:46 +0200 Subject: [PATCH 11/49] clocksource/drivers/orion: Convert to SPDX identifier The license information clearly states GPL version 2 only. The extra text which excludes warranties is an excerpt of the corresponding GPLv2 clause 11. So the SPDX identifier covers it completely. Signed-off-by: Thomas Gleixner Cc: Sebastian Hesselbarth Cc: Daniel Lezcano Link: https://lore.kernel.org/r/20220510171254.780389240@linutronix.de Signed-off-by: Daniel Lezcano --- drivers/clocksource/timer-orion.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/clocksource/timer-orion.c b/drivers/clocksource/timer-orion.c index 5101e834d78f..49e86cb70a7a 100644 --- a/drivers/clocksource/timer-orion.c +++ b/drivers/clocksource/timer-orion.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Marvell Orion SoC timer handling. * * Sebastian Hesselbarth * - * This file is licensed under the terms of the GNU General Public - * License version 2. This program is licensed "as is" without any - * warranty of any kind, whether express or implied. - * * Timer 0 is used as free-running clocksource, while timer 1 is * used as clock_event_device. */ From 6bd8643736cb4e9b5ed744f955318037c7fefee8 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 10 May 2022 19:24:48 +0200 Subject: [PATCH 12/49] clocksource/drivers/pistachio: Convert to SPDX identifier The licensing text references explicitely the COPYING file in the kernel base directory, which is clearly GPL version 2 only. Signed-off-by: Thomas Gleixner Cc: Ezequiel Garcia Cc: Daniel Lezcano Link: https://lore.kernel.org/r/20220510171254.843410802@linutronix.de Signed-off-by: Daniel Lezcano --- drivers/clocksource/timer-pistachio.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/clocksource/timer-pistachio.c b/drivers/clocksource/timer-pistachio.c index 69c069e6f0a2..57b2197a0b67 100644 --- a/drivers/clocksource/timer-pistachio.c +++ b/drivers/clocksource/timer-pistachio.c @@ -1,11 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Pistachio clocksource based on general-purpose timers * * Copyright (C) 2015 Imagination Technologies - * - * 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. */ #define pr_fmt(fmt) "%s: " fmt, __func__ From 60bff9f8ef4bdd1eb24769deb66084dcfd3888d2 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 10 May 2022 19:24:49 +0200 Subject: [PATCH 13/49] clocksource/drivers/timer-sun4i: Convert to SPDX identifier The license information clearly states GPL version 2 only. The extra text which excludes warranties is an excerpt of the corresponding GPLv2 clause 11. So the SPDX identifier covers it completely. Signed-off-by: Thomas Gleixner Cc: Daniel Lezcano Cc: Chen-Yu Tsai Cc: Jernej Skrabec Cc: Samuel Holland Cc: linux-sunxi@lists.linux.dev Link: https://lore.kernel.org/r/20220510171254.908144392@linutronix.de Signed-off-by: Daniel Lezcano --- drivers/clocksource/timer-sun4i.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/clocksource/timer-sun4i.c b/drivers/clocksource/timer-sun4i.c index 0ba8155b8287..bb6ea6c19829 100644 --- a/drivers/clocksource/timer-sun4i.c +++ b/drivers/clocksource/timer-sun4i.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Allwinner A1X SoCs timer handling. * @@ -8,10 +9,6 @@ * Based on code from * Allwinner Technology Co., Ltd. * Benn Huang - * - * This file is licensed under the terms of the GNU General Public - * License version 2. This program is licensed "as is" without any - * warranty of any kind, whether express or implied. */ #include From a74dfa434f98a4fedf3ae2cd8dbeae1e08c1765f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 10 May 2022 19:24:51 +0200 Subject: [PATCH 14/49] clocksource/drivers/timer-sun5i: Convert to SPDX identifier The license information clearly states GPL version 2 only. The extra text which excludes warranties is an excerpt of the corresponding GPLv2 clause 11. So the SPDX identifier covers it completely. Signed-off-by: Thomas Gleixner Cc: Daniel Lezcano Cc: Chen-Yu Tsai Cc: Samuel Holland Cc: Philipp Zabel Cc: linux-sunxi@lists.linux.dev Link: https://lore.kernel.org/r/20220510171254.970933294@linutronix.de Signed-off-by: Daniel Lezcano --- drivers/clocksource/timer-sun5i.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/clocksource/timer-sun5i.c b/drivers/clocksource/timer-sun5i.c index 552c5254390c..85900f7fc69f 100644 --- a/drivers/clocksource/timer-sun5i.c +++ b/drivers/clocksource/timer-sun5i.c @@ -1,13 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Allwinner SoCs hstimer driver. * * Copyright (C) 2013 Maxime Ripard * * Maxime Ripard - * - * This file is licensed under the terms of the GNU General Public - * License version 2. This program is licensed "as is" without any - * warranty of any kind, whether express or implied. */ #include From 8c0d9461ab760439b09ae321803ee85df1136e08 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 19 May 2022 16:58:23 +0300 Subject: [PATCH 15/49] clocksource/drivers/timer-ti-dm: Remove unnecessary NULL check The "pdata" pointer cannot be NULL because it's checked at the start of the function. Delete the check. Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/YoZM65RFDQAfqV6J@kili Signed-off-by: Daniel Lezcano --- drivers/clocksource/timer-ti-dm.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/clocksource/timer-ti-dm.c b/drivers/clocksource/timer-ti-dm.c index 3e52c5226c4d..33609be0b304 100644 --- a/drivers/clocksource/timer-ti-dm.c +++ b/drivers/clocksource/timer-ti-dm.c @@ -828,8 +828,7 @@ static int omap_dm_timer_probe(struct platform_device *pdev) cpu_pm_register_notifier(&timer->nb); } - if (pdata) - timer->errata = pdata->timer_errata; + timer->errata = pdata->timer_errata; timer->pdev = pdev; From 9c04a8ff03def4df3f81219ffbe1ec9b44ff5348 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 22 Apr 2022 12:41:01 +0200 Subject: [PATCH 16/49] clocksource/drivers/oxnas-rps: Fix irq_of_parse_and_map() return value The irq_of_parse_and_map() returns 0 on failure, not a negative ERRNO. Fixes: 89355274e1f7 ("clocksource/drivers/oxnas-rps: Add Oxford Semiconductor RPS Dual Timer") Signed-off-by: Krzysztof Kozlowski Reviewed-by: Neil Armstrong Link: https://lore.kernel.org/r/20220422104101.55754-1-krzysztof.kozlowski@linaro.org Signed-off-by: Daniel Lezcano --- drivers/clocksource/timer-oxnas-rps.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clocksource/timer-oxnas-rps.c b/drivers/clocksource/timer-oxnas-rps.c index 56c0cc32d0ac..d514b44e67dd 100644 --- a/drivers/clocksource/timer-oxnas-rps.c +++ b/drivers/clocksource/timer-oxnas-rps.c @@ -236,7 +236,7 @@ static int __init oxnas_rps_timer_init(struct device_node *np) } rps->irq = irq_of_parse_and_map(np, 0); - if (rps->irq < 0) { + if (!rps->irq) { ret = -EINVAL; goto err_iomap; } From 8a33d96bd178d5f49cc5c1898e4cda08e221d2db Mon Sep 17 00:00:00 2001 From: XueBing Chen Date: Wed, 25 May 2022 16:51:01 +0800 Subject: [PATCH 17/49] x86/setup: Use strscpy() to replace deprecated strlcpy() strlcpy() is marked deprecated and should not be used, because it doesn't limit the source length. The preferred interface for when strlcpy()'s return value is not checked (truncation) is strscpy(). [ mingo: Tweaked the changelog ] Signed-off-by: XueBing Chen Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/730f0fef.a33.180fa69880f.Coremail.chenxuebing@jari.cn --- arch/x86/kernel/setup.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 249981bf3d8a..3ebb85327edb 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -903,18 +903,18 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_CMDLINE_BOOL #ifdef CONFIG_CMDLINE_OVERRIDE - strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); + strscpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); #else if (builtin_cmdline[0]) { /* append boot loader cmdline to builtin */ strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE); strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE); - strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); + strscpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); } #endif #endif - strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE); + strscpy(command_line, boot_command_line, COMMAND_LINE_SIZE); *cmdline_p = command_line; /* From 758cd94a0e16ddbc5607428f28170897f67c2964 Mon Sep 17 00:00:00 2001 From: Juerg Haefliger Date: Wed, 25 May 2022 15:32:02 +0200 Subject: [PATCH 18/49] x86/Kconfig: Fix indentation and add endif comments to arch/x86/Kconfig The convention for indentation seems to be a single tab. Help text is further indented by an additional two whitespaces. Fix the lines that violate these rules. While add it, add missing trailing endif comments and squeeze multiple empty lines. Signed-off-by: Juerg Haefliger Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20220525133203.52463-2-juerg.haefliger@canonical.com --- arch/x86/Kconfig | 101 +++++++++++++++++++++++------------------------ 1 file changed, 49 insertions(+), 52 deletions(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 762a0b6ab8b6..4d610ae216ce 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -41,11 +41,11 @@ config FORCE_DYNAMIC_FTRACE depends on FUNCTION_TRACER select DYNAMIC_FTRACE help - We keep the static function tracing (!DYNAMIC_FTRACE) around - in order to test the non static function tracing in the - generic code, as other architectures still use it. But we - only need to keep it around for x86_64. No need to keep it - for x86_32. For x86_32, force DYNAMIC_FTRACE. + We keep the static function tracing (!DYNAMIC_FTRACE) around + in order to test the non static function tracing in the + generic code, as other architectures still use it. But we + only need to keep it around for x86_64. No need to keep it + for x86_32. For x86_32, force DYNAMIC_FTRACE. # # Arch settings # @@ -392,9 +392,9 @@ config CC_HAS_SANE_STACKPROTECTOR default $(success,$(srctree)/scripts/gcc-x86_64-has-stack-protector.sh $(CC)) if 64BIT default $(success,$(srctree)/scripts/gcc-x86_32-has-stack-protector.sh $(CC)) help - We have to make sure stack protector is unconditionally disabled if - the compiler produces broken code or if it does not let us control - the segment on 32-bit kernels. + We have to make sure stack protector is unconditionally disabled if + the compiler produces broken code or if it does not let us control + the segment on 32-bit kernels. menu "Processor type and features" @@ -530,7 +530,7 @@ config X86_EXTENDED_PLATFORM If you have one of these systems, or if you want to build a generic distribution kernel, say Y here - otherwise say N. -endif +endif # X86_32 if X86_64 config X86_EXTENDED_PLATFORM @@ -549,7 +549,7 @@ config X86_EXTENDED_PLATFORM If you have one of these systems, or if you want to build a generic distribution kernel, say Y here - otherwise say N. -endif +endif # X86_64 # This is an alphabetically sorted list of 64 bit extended platforms # Please maintain the alphabetic order if and when there are additions config X86_NUMACHIP @@ -597,9 +597,9 @@ config X86_GOLDFISH bool "Goldfish (Virtual Platform)" depends on X86_EXTENDED_PLATFORM help - Enable support for the Goldfish virtual platform used primarily - for Android development. Unless you are building for the Android - Goldfish emulator say N here. + Enable support for the Goldfish virtual platform used primarily + for Android development. Unless you are building for the Android + Goldfish emulator say N here. config X86_INTEL_CE bool "CE4100 TV platform" @@ -898,7 +898,7 @@ config INTEL_TDX_GUEST memory contents and CPU state. TDX guests are protected from some attacks from the VMM. -endif #HYPERVISOR_GUEST +endif # HYPERVISOR_GUEST source "arch/x86/Kconfig.cpu" @@ -1159,16 +1159,16 @@ config X86_MCE_INTEL prompt "Intel MCE features" depends on X86_MCE && X86_LOCAL_APIC help - Additional support for intel specific MCE features such as - the thermal monitor. + Additional support for intel specific MCE features such as + the thermal monitor. config X86_MCE_AMD def_bool y prompt "AMD MCE features" depends on X86_MCE && X86_LOCAL_APIC && AMD_NB help - Additional support for AMD specific MCE features such as - the DRAM Error Threshold. + Additional support for AMD specific MCE features such as + the DRAM Error Threshold. config X86_ANCIENT_MCE bool "Support for old Pentium 5 / WinChip machine checks" @@ -1246,18 +1246,18 @@ config X86_VSYSCALL_EMULATION default y depends on X86_64 help - This enables emulation of the legacy vsyscall page. Disabling - it is roughly equivalent to booting with vsyscall=none, except - that it will also disable the helpful warning if a program - tries to use a vsyscall. With this option set to N, offending - programs will just segfault, citing addresses of the form - 0xffffffffff600?00. + This enables emulation of the legacy vsyscall page. Disabling + it is roughly equivalent to booting with vsyscall=none, except + that it will also disable the helpful warning if a program + tries to use a vsyscall. With this option set to N, offending + programs will just segfault, citing addresses of the form + 0xffffffffff600?00. - This option is required by many programs built before 2013, and - care should be used even with newer programs if set to N. + This option is required by many programs built before 2013, and + care should be used even with newer programs if set to N. - Disabling this option saves about 7K of kernel size and - possibly 4K of additional runtime pagetable memory. + Disabling this option saves about 7K of kernel size and + possibly 4K of additional runtime pagetable memory. config X86_IOPL_IOPERM bool "IOPERM and IOPL Emulation" @@ -1994,15 +1994,15 @@ config EFI_MIXED bool "EFI mixed-mode support" depends on EFI_STUB && X86_64 help - Enabling this feature allows a 64-bit kernel to be booted - on a 32-bit firmware, provided that your CPU supports 64-bit - mode. + Enabling this feature allows a 64-bit kernel to be booted + on a 32-bit firmware, provided that your CPU supports 64-bit + mode. - Note that it is not possible to boot a mixed-mode enabled - kernel via the EFI boot stub - a bootloader that supports - the EFI handover protocol must be used. + Note that it is not possible to boot a mixed-mode enabled + kernel via the EFI boot stub - a bootloader that supports + the EFI handover protocol must be used. - If unsure, say N. + If unsure, say N. source "kernel/Kconfig.hz" @@ -2227,16 +2227,16 @@ config RANDOMIZE_MEMORY select DYNAMIC_MEMORY_LAYOUT default RANDOMIZE_BASE help - Randomizes the base virtual address of kernel memory sections - (physical memory mapping, vmalloc & vmemmap). This security feature - makes exploits relying on predictable memory locations less reliable. + Randomizes the base virtual address of kernel memory sections + (physical memory mapping, vmalloc & vmemmap). This security feature + makes exploits relying on predictable memory locations less reliable. - The order of allocations remains unchanged. Entropy is generated in - the same way as RANDOMIZE_BASE. Current implementation in the optimal - configuration have in average 30,000 different possible virtual - addresses for each memory section. + The order of allocations remains unchanged. Entropy is generated in + the same way as RANDOMIZE_BASE. Current implementation in the optimal + configuration have in average 30,000 different possible virtual + addresses for each memory section. - If unsure, say Y. + If unsure, say Y. config RANDOMIZE_MEMORY_PHYSICAL_PADDING hex "Physical memory mapping padding" if EXPERT @@ -2246,12 +2246,12 @@ config RANDOMIZE_MEMORY_PHYSICAL_PADDING range 0x1 0x40 if MEMORY_HOTPLUG range 0x0 0x40 help - Define the padding in terabytes added to the existing physical - memory size during kernel memory randomization. It is useful - for memory hotplug support but reduces the entropy available for - address randomization. + Define the padding in terabytes added to the existing physical + memory size during kernel memory randomization. It is useful + for memory hotplug support but reduces the entropy available for + address randomization. - If unsure, leave at the default value. + If unsure, leave at the default value. config HOTPLUG_CPU def_bool y @@ -2598,7 +2598,6 @@ source "drivers/idle/Kconfig" endmenu - menu "Bus options (PCI etc.)" choice @@ -2822,7 +2821,6 @@ config AMD_NB endmenu - menu "Binary Emulations" config IA32_EMULATION @@ -2867,11 +2865,10 @@ config COMPAT_FOR_U64_ALIGNMENT config SYSVIPC_COMPAT def_bool y depends on SYSVIPC -endif +endif # COMPAT endmenu - config HAVE_ATOMIC_IOMAP def_bool y depends on X86_32 From 0ecfacb4c50ae2fd32ee1898562fe55f045b56d2 Mon Sep 17 00:00:00 2001 From: Juerg Haefliger Date: Wed, 25 May 2022 15:32:03 +0200 Subject: [PATCH 19/49] x86/Kconfig: Fix indentation of arch/x86/Kconfig.debug The convention for indentation seems to be a single tab. Help text is further indented by an additional two whitespaces. Fix the lines that violate these rules. Signed-off-by: Juerg Haefliger Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20220525133203.52463-3-juerg.haefliger@canonical.com --- arch/x86/Kconfig.debug | 29 ++++++++++++++--------------- 1 file changed, 14 insertions(+), 15 deletions(-) diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index d872a7522e55..340399f69954 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -73,20 +73,19 @@ config DEBUG_TLBFLUSH bool "Set upper limit of TLB entries to flush one-by-one" depends on DEBUG_KERNEL help + X86-only for now. - X86-only for now. + This option allows the user to tune the amount of TLB entries the + kernel flushes one-by-one instead of doing a full TLB flush. In + certain situations, the former is cheaper. This is controlled by the + tlb_flushall_shift knob under /sys/kernel/debug/x86. If you set it + to -1, the code flushes the whole TLB unconditionally. Otherwise, + for positive values of it, the kernel will use single TLB entry + invalidating instructions according to the following formula: - This option allows the user to tune the amount of TLB entries the - kernel flushes one-by-one instead of doing a full TLB flush. In - certain situations, the former is cheaper. This is controlled by the - tlb_flushall_shift knob under /sys/kernel/debug/x86. If you set it - to -1, the code flushes the whole TLB unconditionally. Otherwise, - for positive values of it, the kernel will use single TLB entry - invalidating instructions according to the following formula: + flush_entries <= active_tlb_entries / 2^tlb_flushall_shift - flush_entries <= active_tlb_entries / 2^tlb_flushall_shift - - If in doubt, say "N". + If in doubt, say "N". config IOMMU_DEBUG bool "Enable IOMMU debugging" @@ -119,10 +118,10 @@ config X86_DECODER_SELFTEST depends on DEBUG_KERNEL && INSTRUCTION_DECODER depends on !COMPILE_TEST help - Perform x86 instruction decoder selftests at build time. - This option is useful for checking the sanity of x86 instruction - decoder code. - If unsure, say "N". + Perform x86 instruction decoder selftests at build time. + This option is useful for checking the sanity of x86 instruction + decoder code. + If unsure, say "N". choice prompt "IO delay type" From 20eb48885b62d5de4ab6be7e08f9f55aa33333fd Mon Sep 17 00:00:00 2001 From: sunliming Date: Wed, 25 May 2022 09:28:27 +0800 Subject: [PATCH 20/49] x86/idt: Remove unused headers Commit: 4b9a8dca0e58 ("x86/idt: Remove the tracing IDT completely") removed the 'tracing IDT' from arch/x86/kernel/tracepoint.c, but left related headers included - remove them. [ mingo: Tweak changelog. ] Signed-off-by: sunliming Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20220525012827.93464-1-sunliming@kylinos.cn --- arch/x86/kernel/tracepoint.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/x86/kernel/tracepoint.c b/arch/x86/kernel/tracepoint.c index fcfc077afe2d..f39aad69fb64 100644 --- a/arch/x86/kernel/tracepoint.c +++ b/arch/x86/kernel/tracepoint.c @@ -8,10 +8,7 @@ #include #include -#include -#include #include -#include DEFINE_STATIC_KEY_FALSE(trace_pagefault_key); From 108ea7eb3e754be735a1c33d2713a19527fb2065 Mon Sep 17 00:00:00 2001 From: Juerg Haefliger Date: Wed, 25 May 2022 15:39:49 +0200 Subject: [PATCH 21/49] perf/x86/Kconfig: Fix indentation in the Kconfig file The convention for indentation seems to be a single tab. Help text is further indented by an additional two whitespaces. Fix the lines that violate these rules. Signed-off-by: Juerg Haefliger Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20220525133949.53730-1-juerg.haefliger@canonical.com --- arch/x86/events/Kconfig | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/x86/events/Kconfig b/arch/x86/events/Kconfig index 09c56965750a..dabdf3d7bf84 100644 --- a/arch/x86/events/Kconfig +++ b/arch/x86/events/Kconfig @@ -6,24 +6,24 @@ config PERF_EVENTS_INTEL_UNCORE depends on PERF_EVENTS && CPU_SUP_INTEL && PCI default y help - Include support for Intel uncore performance events. These are - available on NehalemEX and more modern processors. + Include support for Intel uncore performance events. These are + available on NehalemEX and more modern processors. config PERF_EVENTS_INTEL_RAPL tristate "Intel/AMD rapl performance events" depends on PERF_EVENTS && (CPU_SUP_INTEL || CPU_SUP_AMD) && PCI default y help - Include support for Intel and AMD rapl performance events for power - monitoring on modern processors. + Include support for Intel and AMD rapl performance events for power + monitoring on modern processors. config PERF_EVENTS_INTEL_CSTATE tristate "Intel cstate performance events" depends on PERF_EVENTS && CPU_SUP_INTEL && PCI default y help - Include support for Intel cstate performance events for power - monitoring on modern processors. + Include support for Intel cstate performance events for power + monitoring on modern processors. config PERF_EVENTS_AMD_POWER depends on PERF_EVENTS && CPU_SUP_AMD From 86dca369075b3e310c3c0adb0f81e513c562b5e4 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Wed, 25 May 2022 06:39:52 -0700 Subject: [PATCH 22/49] perf/x86/intel: Fix event constraints for ICL According to the latest event list, the event encoding 0x55 INST_DECODED.DECODERS and 0x56 UOPS_DECODED.DEC0 are only available on the first 4 counters. Add them into the event constraints table. Fixes: 6017608936c1 ("perf/x86/intel: Add Icelake support") Signed-off-by: Kan Liang Signed-off-by: Ingo Molnar Acked-by: Peter Zijlstra Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220525133952.1660658-1-kan.liang@linux.intel.com --- arch/x86/events/intel/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 955ae91c56dc..45024abd929f 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -276,7 +276,7 @@ static struct event_constraint intel_icl_event_constraints[] = { INTEL_EVENT_CONSTRAINT_RANGE(0x03, 0x0a, 0xf), INTEL_EVENT_CONSTRAINT_RANGE(0x1f, 0x28, 0xf), INTEL_EVENT_CONSTRAINT(0x32, 0xf), /* SW_PREFETCH_ACCESS.* */ - INTEL_EVENT_CONSTRAINT_RANGE(0x48, 0x54, 0xf), + INTEL_EVENT_CONSTRAINT_RANGE(0x48, 0x56, 0xf), INTEL_EVENT_CONSTRAINT_RANGE(0x60, 0x8b, 0xf), INTEL_UEVENT_CONSTRAINT(0x04a3, 0xff), /* CYCLE_ACTIVITY.STALLS_TOTAL */ INTEL_UEVENT_CONSTRAINT(0x10a3, 0xff), /* CYCLE_ACTIVITY.CYCLES_MEM_ANY */ From 8b4dd2d8627e88dc3bd71bf29c48aaae2b69572b Mon Sep 17 00:00:00 2001 From: Haowen Bai Date: Fri, 27 May 2022 18:03:54 +0800 Subject: [PATCH 23/49] perf/core: Remove unused local variable Drop LIST_HEAD() where the variable it declares is never used. Compiler probably never warned us, because the LIST_HEAD() initializer is technically 'usage'. [ mingo: Tweak changelog. ] Signed-off-by: Haowen Bai Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/1653645835-29206-1-git-send-email-baihaowen@meizu.com --- kernel/events/core.c | 1 - 1 file changed, 1 deletion(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 950b25c3f210..80782cddb1da 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4257,7 +4257,6 @@ static void perf_event_remove_on_exec(int ctxn) { struct perf_event_context *ctx, *clone_ctx = NULL; struct perf_event *event, *next; - LIST_HEAD(free_list); unsigned long flags; bool modified = false; From f7081834b2d5bbc77d67073d8ab490bfeaf3c13b Mon Sep 17 00:00:00 2001 From: Bo Liu Date: Fri, 27 May 2022 02:14:00 -0400 Subject: [PATCH 24/49] x86: Fix all occurences of the "the the" typo Rather than waiting for the bots to fix these one-by-one, fix all occurences of "the the" throughout arch/x86. Signed-off-by: Bo Liu Signed-off-by: Ingo Molnar Cc: Paolo Bonzini Link: https://lore.kernel.org/r/20220527061400.5694-1-liubo03@inspur.com --- arch/x86/kvm/vmx/vmx.c | 2 +- arch/x86/kvm/x86.c | 2 +- arch/x86/platform/efi/efi_thunk_64.S | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 610355b9ccce..2a67350d93d2 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6221,7 +6221,7 @@ static noinstr void vmx_l1d_flush(struct kvm_vcpu *vcpu) int size = PAGE_SIZE << L1D_CACHE_ORDER; /* - * This code is only executed when the the flush mode is 'cond' or + * This code is only executed when the flush mode is 'cond' or * 'always' */ if (static_branch_likely(&vmx_l1d_flush_cond)) { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4790f0d7d40b..5f11d7bc6ef4 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -11855,7 +11855,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm) if (current->mm == kvm->mm) { /* * Free memory regions allocated on behalf of userspace, - * unless the the memory map has changed due to process exit + * unless the memory map has changed due to process exit * or fd copying. */ mutex_lock(&kvm->slots_lock); diff --git a/arch/x86/platform/efi/efi_thunk_64.S b/arch/x86/platform/efi/efi_thunk_64.S index 854dd81804b7..9ffe2bad27d5 100644 --- a/arch/x86/platform/efi/efi_thunk_64.S +++ b/arch/x86/platform/efi/efi_thunk_64.S @@ -8,7 +8,7 @@ * The below thunking functions are only used after ExitBootServices() * has been called. This simplifies things considerably as compared with * the early EFI thunking because we can leave all the kernel state - * intact (GDT, IDT, etc) and simply invoke the the 32-bit EFI runtime + * intact (GDT, IDT, etc) and simply invoke the 32-bit EFI runtime * services from __KERNEL32_CS. This means we can continue to service * interrupts across an EFI mixed mode call. * From e19d11267f0e6c8aff2d15d2dfed12365b4c9184 Mon Sep 17 00:00:00 2001 From: Fanjun Kong Date: Thu, 26 May 2022 22:20:39 +0800 Subject: [PATCH 25/49] x86/mm: Use PAGE_ALIGNED(x) instead of IS_ALIGNED(x, PAGE_SIZE) The already provides the PAGE_ALIGNED() macro. Let's use this macro instead of IS_ALIGNED() and passing PAGE_SIZE directly. No change in functionality. [ mingo: Tweak changelog. ] Signed-off-by: Fanjun Kong Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20220526142038.1582839-1-bh1scw@gmail.com --- arch/x86/mm/init_64.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 61d0ab154f96..8779d6be6a49 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1240,8 +1240,8 @@ remove_pagetable(unsigned long start, unsigned long end, bool direct, void __ref vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap) { - VM_BUG_ON(!IS_ALIGNED(start, PAGE_SIZE)); - VM_BUG_ON(!IS_ALIGNED(end, PAGE_SIZE)); + VM_BUG_ON(!PAGE_ALIGNED(start)); + VM_BUG_ON(!PAGE_ALIGNED(end)); remove_pagetable(start, end, false, altmap); } @@ -1605,8 +1605,8 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, { int err; - VM_BUG_ON(!IS_ALIGNED(start, PAGE_SIZE)); - VM_BUG_ON(!IS_ALIGNED(end, PAGE_SIZE)); + VM_BUG_ON(!PAGE_ALIGNED(start)); + VM_BUG_ON(!PAGE_ALIGNED(end)); if (end - start < PAGES_PER_SECTION * sizeof(struct page)) err = vmemmap_populate_basepages(start, end, node, NULL); From 5f3da8c08508df82823566c32f753071c8ad36af Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 19 Apr 2022 09:05:09 -0700 Subject: [PATCH 26/49] objtool: Add CONFIG_HAVE_UACCESS_VALIDATION Allow an arch specify that it has objtool uaccess validation with CONFIG_HAVE_UACCESS_VALIDATION. For now, doing so unconditionally selects CONFIG_OBJTOOL. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/d393d5e2fe73aec6e8e41d5c24f4b6fe8583f2d8.1650384225.git.jpoimboe@redhat.com --- arch/Kconfig | 4 ++++ arch/x86/Kconfig | 1 + scripts/Makefile.build | 2 +- scripts/link-vmlinux.sh | 4 +++- 4 files changed, 9 insertions(+), 2 deletions(-) diff --git a/arch/Kconfig b/arch/Kconfig index 904ed51736d4..cb2954027d10 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -1050,6 +1050,10 @@ config HAVE_NOINSTR_HACK config HAVE_NOINSTR_VALIDATION bool +config HAVE_UACCESS_VALIDATION + bool + select OBJTOOL + config HAVE_STACK_VALIDATION bool help diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index cf531fbcd229..5f41f3c3df9a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -258,6 +258,7 @@ config X86 select HAVE_PREEMPT_DYNAMIC_CALL select HAVE_RSEQ select HAVE_SYSCALL_TRACEPOINTS + select HAVE_UACCESS_VALIDATION if HAVE_OBJTOOL select HAVE_UNSTABLE_SCHED_CLOCK select HAVE_USER_RETURN_NOTIFIER select HAVE_GENERIC_VDSO diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 06400504150b..6a663b27b286 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -218,7 +218,7 @@ objtool_args = \ $(if $(CONFIG_SLS), --sls) \ $(if $(CONFIG_STACK_VALIDATION), --stackval) \ $(if $(CONFIG_HAVE_STATIC_CALL_INLINE), --static-call) \ - --uaccess \ + $(if $(CONFIG_HAVE_UACCESS_VALIDATION), --uaccess) \ $(if $(linked-object), --link) \ $(if $(part-of-module), --module) \ $(if $(CONFIG_GCOV_KERNEL), --no-unreachable) diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index a7f6196c7e41..fd578c380919 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -134,7 +134,9 @@ objtool_link() objtoolopt="${objtoolopt} --static-call" fi - objtoolopt="${objtoolopt} --uaccess" + if is_enabled CONFIG_HAVE_UACCESS_VALIDATION; then + objtoolopt="${objtoolopt} --uaccess" + fi fi if is_enabled CONFIG_NOINSTR_VALIDATION; then From 385bd430c011a8cb8278e61c32d602d11e06f414 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 2 May 2022 11:15:14 +0200 Subject: [PATCH 27/49] objtool: Mark __ubsan_handle_builtin_unreachable() as noreturn fs/ntfs3/ntfs3.prelink.o: warning: objtool: ni_read_frame() falls through to next function ni_readpage_cmpr.cold() That is in fact: 000000000000124a : 124a: 44 89 e0 mov %r12d,%eax 124d: 0f b6 55 98 movzbl -0x68(%rbp),%edx 1251: 48 c7 c7 00 00 00 00 mov $0x0,%rdi 1254: R_X86_64_32S .data+0x1380 1258: 48 89 c6 mov %rax,%rsi 125b: e8 00 00 00 00 call 1260 125c: R_X86_64_PLT32 __ubsan_handle_shift_out_of_bounds-0x4 1260: 48 8d 7d cc lea -0x34(%rbp),%rdi 1264: e8 00 00 00 00 call 1269 1265: R_X86_64_PLT32 __tsan_read4-0x4 1269: 8b 45 cc mov -0x34(%rbp),%eax 126c: e9 00 00 00 00 jmp 1271 126d: R_X86_64_PC32 .text+0x19109 1271: 48 8b 75 a0 mov -0x60(%rbp),%rsi 1275: 48 63 d0 movslq %eax,%rdx 1278: 48 c7 c7 00 00 00 00 mov $0x0,%rdi 127b: R_X86_64_32S .data+0x13a0 127f: 89 45 88 mov %eax,-0x78(%rbp) 1282: e8 00 00 00 00 call 1287 1283: R_X86_64_PLT32 __ubsan_handle_shift_out_of_bounds-0x4 1287: 8b 45 88 mov -0x78(%rbp),%eax 128a: e9 00 00 00 00 jmp 128f 128b: R_X86_64_PC32 .text+0x19098 128f: 48 c7 c7 00 00 00 00 mov $0x0,%rdi 1292: R_X86_64_32S .data+0x11f0 1296: e8 00 00 00 00 call 129b 1297: R_X86_64_PLT32 __ubsan_handle_builtin_unreachable-0x4 000000000000129b : Tell objtool that __ubsan_handle_builtin_unreachable() is a noreturn. Reported-by: kernel test robot Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20220502091514.GB479834@worktop.programming.kicks-ass.net --- tools/objtool/check.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 190b2f6e360a..7a187dae2fcf 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -185,7 +185,8 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "do_group_exit", "stop_this_cpu", "__invalid_creds", - "cpu_startup_entry", + "cpu_startup_entry", + "__ubsan_handle_builtin_unreachable", }; if (!func) From a6a5eb269f6f3a2fe392f725a8d9052190c731e2 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 2 May 2022 12:15:23 +0200 Subject: [PATCH 28/49] x86/cpu: Elide KCSAN for cpu_has() and friends As x86 uses the headers, the regular forms of all bitops are instrumented with explicit calls to KASAN and KCSAN checks. As these are explicit calls, these are not suppressed by the noinstr function attribute. This can result in calls to those check functions in noinstr code, which objtool warns about: vmlinux.o: warning: objtool: enter_from_user_mode+0x24: call to __kcsan_check_access() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_enter_from_user_mode+0x28: call to __kcsan_check_access() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_enter_from_user_mode_prepare+0x24: call to __kcsan_check_access() leaves .noinstr.text section vmlinux.o: warning: objtool: irqentry_enter_from_user_mode+0x24: call to __kcsan_check_access() leaves .noinstr.text section Prevent this by using the arch_*() bitops, which are the underlying bitops without explciit instrumentation. [null: Changelog] Reported-by: kernel test robot Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20220502111216.290518605@infradead.org --- arch/x86/include/asm/cpufeature.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 66d3e3b1d24d..ea34cc31b047 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -54,7 +54,7 @@ extern const char * const x86_power_flags[32]; extern const char * const x86_bug_flags[NBUGINTS*32]; #define test_cpu_cap(c, bit) \ - test_bit(bit, (unsigned long *)((c)->x86_capability)) + arch_test_bit(bit, (unsigned long *)((c)->x86_capability)) /* * There are 32 bits/features in each mask word. The high bits From 656d054e0a15ec327bd82801ccd58201e59f6896 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 2 May 2022 12:30:20 +0200 Subject: [PATCH 29/49] jump_label,noinstr: Avoid instrumentation for JUMP_LABEL=n builds When building x86_64 with JUMP_LABEL=n it's possible for instrumentation to sneak into noinstr: vmlinux.o: warning: objtool: exit_to_user_mode+0x14: call to static_key_count.constprop.0() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_exit_to_user_mode+0x2d: call to static_key_count.constprop.0() leaves .noinstr.text section vmlinux.o: warning: objtool: irqentry_exit_to_user_mode+0x1b: call to static_key_count.constprop.0() leaves .noinstr.text section Switch to arch_ prefixed atomic to avoid the explicit instrumentation. Reported-by: kernel test robot Signed-off-by: Peter Zijlstra (Intel) --- include/linux/jump_label.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 107751cc047b..bf1eef337a07 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -256,9 +256,9 @@ extern void static_key_disable_cpuslocked(struct static_key *key); #include #include -static inline int static_key_count(struct static_key *key) +static __always_inline int static_key_count(struct static_key *key) { - return atomic_read(&key->enabled); + return arch_atomic_read(&key->enabled); } static __always_inline void jump_label_init(void) From 1894a4030582472336c2873cb07911ce67e0d14e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Sat, 7 May 2022 13:37:45 +0200 Subject: [PATCH 30/49] x86: Always inline on_thread_stack() and current_top_of_stack() Becaues GCC clearly lost it's marbles again... vmlinux.o: warning: objtool: enter_from_user_mode+0x4e: call to on_thread_stack() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_enter_from_user_mode+0x53: call to on_thread_stack() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_enter_from_user_mode_prepare+0x4e: call to on_thread_stack() leaves .noinstr.text section vmlinux.o: warning: objtool: irqentry_enter_from_user_mode+0x4e: call to on_thread_stack() leaves .noinstr.text section vmlinux.o: warning: objtool: enter_from_user_mode+0x4e: call to current_top_of_stack() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_enter_from_user_mode+0x53: call to current_top_of_stack() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_enter_from_user_mode_prepare+0x4e: call to current_top_of_stack() leaves .noinstr.text section vmlinux.o: warning: objtool: irqentry_enter_from_user_mode+0x4e: call to current_top_of_stack() leaves .noinstr.text section Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20220526105958.071435483@infradead.org --- arch/x86/include/asm/processor.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 91d0f93a00c7..356308c73951 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -559,7 +559,7 @@ static __always_inline void native_swapgs(void) #endif } -static inline unsigned long current_top_of_stack(void) +static __always_inline unsigned long current_top_of_stack(void) { /* * We can't read directly from tss.sp0: sp0 on x86_32 is special in @@ -569,7 +569,7 @@ static inline unsigned long current_top_of_stack(void) return this_cpu_read_stable(cpu_current_top_of_stack); } -static inline bool on_thread_stack(void) +static __always_inline bool on_thread_stack(void) { return (unsigned long)(current_top_of_stack() - current_stack_pointer) < THREAD_SIZE; From 620f8d3bd3d5e82dff8cc591c831827d4beeae2e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Sat, 7 May 2022 13:35:37 +0200 Subject: [PATCH 31/49] context_tracking: Always inline empty stubs Because GCC is seriously challenged.. vmlinux.o: warning: objtool: enter_from_user_mode+0x85: call to context_tracking_enabled() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_enter_from_user_mode+0x8f: call to context_tracking_enabled() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_enter_from_user_mode_prepare+0x85: call to context_tracking_enabled() leaves .noinstr.text section vmlinux.o: warning: objtool: irqentry_enter_from_user_mode+0x85: call to context_tracking_enabled() leaves .noinstr.text section Signed-off-by: Peter Zijlstra (Intel) Acked-by: Mark Rutland Link: https://lkml.kernel.org/r/20220526105958.134113388@infradead.org --- include/linux/context_tracking_state.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index 65a60d3313b0..ae1e63e26947 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -46,10 +46,10 @@ static __always_inline bool context_tracking_in_user(void) return __this_cpu_read(context_tracking.state) == CONTEXT_USER; } #else -static inline bool context_tracking_in_user(void) { return false; } -static inline bool context_tracking_enabled(void) { return false; } -static inline bool context_tracking_enabled_cpu(int cpu) { return false; } -static inline bool context_tracking_enabled_this_cpu(void) { return false; } +static __always_inline bool context_tracking_in_user(void) { return false; } +static __always_inline bool context_tracking_enabled(void) { return false; } +static __always_inline bool context_tracking_enabled_cpu(int cpu) { return false; } +static __always_inline bool context_tracking_enabled_this_cpu(void) { return false; } #endif /* CONFIG_CONTEXT_TRACKING */ #endif From 2028a255f4df3af9e759f01f958d3237f825f256 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Fri, 20 May 2022 21:27:29 +0200 Subject: [PATCH 32/49] x86/extable: Annotate ex_handler_msr_mce() as a dead end Fix vmlinux.o: warning: objtool: fixup_exception+0x2d6: unreachable instruction Signed-off-by: Borislav Petkov Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20220520192729.23969-1-bp@alien8.de --- arch/x86/include/asm/extable.h | 8 ++++++-- tools/objtool/check.c | 1 + 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/extable.h b/arch/x86/include/asm/extable.h index 155c991ba95e..eeed395c3177 100644 --- a/arch/x86/include/asm/extable.h +++ b/arch/x86/include/asm/extable.h @@ -42,9 +42,13 @@ extern int ex_get_fixup_type(unsigned long ip); extern void early_fixup_exception(struct pt_regs *regs, int trapnr); #ifdef CONFIG_X86_MCE -extern void ex_handler_msr_mce(struct pt_regs *regs, bool wrmsr); +extern void __noreturn ex_handler_msr_mce(struct pt_regs *regs, bool wrmsr); #else -static inline void ex_handler_msr_mce(struct pt_regs *regs, bool wrmsr) { } +static inline void __noreturn ex_handler_msr_mce(struct pt_regs *regs, bool wrmsr) +{ + for (;;) + cpu_relax(); +} #endif #if defined(CONFIG_BPF_JIT) && defined(CONFIG_X86_64) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 7a187dae2fcf..864bb9dd3584 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -187,6 +187,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "__invalid_creds", "cpu_startup_entry", "__ubsan_handle_builtin_unreachable", + "ex_handler_msr_mce", }; if (!func) From 82f586f923e3ac6062bc7867717a7f8afc09e0ff Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 30 May 2022 09:45:38 +0200 Subject: [PATCH 33/49] sched/autogroup: Fix sysctl move Ivan reported /proc/sys/kernel/sched_autogroup_enabled went walk-about and using the noautogroup command line parameter would result in a boot error message. Turns out the sysctl move placed the init function wrong. Fixes: c8eaf6ac76f4 ("sched: move autogroup sysctls into its own file") Reported-by: Ivan Kozik Signed-off-by: Peter Zijlstra (Intel) Tested-by: Ivan Kozik Link: https://lkml.kernel.org/r/YpR2IqndgsyMzN00@worktop.programming.kicks-ass.net --- kernel/sched/autogroup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c index 16092b49ff6a..4ebaf97f7bd8 100644 --- a/kernel/sched/autogroup.c +++ b/kernel/sched/autogroup.c @@ -36,6 +36,7 @@ void __init autogroup_init(struct task_struct *init_task) kref_init(&autogroup_default.kref); init_rwsem(&autogroup_default.lock); init_task->signal->autogroup = &autogroup_default; + sched_autogroup_sysctl_init(); } void autogroup_free(struct task_group *tg) @@ -219,7 +220,6 @@ void sched_autogroup_exit(struct signal_struct *sig) static int __init setup_autogroup(char *str) { sysctl_sched_autogroup_enabled = 0; - sched_autogroup_sysctl_init(); return 1; } From 181b6f40e9ea80c76756d4d0cdeed396016c487e Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 25 May 2022 18:12:29 +0200 Subject: [PATCH 34/49] x86/microcode: Rip out the OLD_INTERFACE Everything should be using the early initrd loading by now. Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20220525161232.14924-2-bp@alien8.de --- arch/x86/Kconfig | 12 ---- arch/x86/kernel/cpu/microcode/core.c | 100 --------------------------- 2 files changed, 112 deletions(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 762a0b6ab8b6..f423a2d87b15 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1350,18 +1350,6 @@ config MICROCODE_AMD If you select this option, microcode patch loading support for AMD processors will be enabled. -config MICROCODE_OLD_INTERFACE - bool "Ancient loading interface (DEPRECATED)" - default n - depends on MICROCODE - help - DO NOT USE THIS! This is the ancient /dev/cpu/microcode interface - which was used by userspace tools like iucode_tool and microcode.ctl. - It is inadequate because it runs too late to be able to properly - load microcode on a machine and it needs special tools. Instead, you - should've switched to the early loading method with the initrd or - builtin microcode by now: Documentation/x86/microcode.rst - config X86_MSR tristate "/dev/cpu/*/msr - Model-specific register support" help diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 239ff5fcec6a..b72c4134f289 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -373,98 +373,6 @@ static int apply_microcode_on_target(int cpu) return ret; } -#ifdef CONFIG_MICROCODE_OLD_INTERFACE -static int do_microcode_update(const void __user *buf, size_t size) -{ - int error = 0; - int cpu; - - for_each_online_cpu(cpu) { - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - enum ucode_state ustate; - - if (!uci->valid) - continue; - - ustate = microcode_ops->request_microcode_user(cpu, buf, size); - if (ustate == UCODE_ERROR) { - error = -1; - break; - } else if (ustate == UCODE_NEW) { - apply_microcode_on_target(cpu); - } - } - - return error; -} - -static int microcode_open(struct inode *inode, struct file *file) -{ - return capable(CAP_SYS_RAWIO) ? stream_open(inode, file) : -EPERM; -} - -static ssize_t microcode_write(struct file *file, const char __user *buf, - size_t len, loff_t *ppos) -{ - ssize_t ret = -EINVAL; - unsigned long nr_pages = totalram_pages(); - - if ((len >> PAGE_SHIFT) > nr_pages) { - pr_err("too much data (max %ld pages)\n", nr_pages); - return ret; - } - - cpus_read_lock(); - mutex_lock(µcode_mutex); - - if (do_microcode_update(buf, len) == 0) - ret = (ssize_t)len; - - if (ret > 0) - perf_check_microcode(); - - mutex_unlock(µcode_mutex); - cpus_read_unlock(); - - return ret; -} - -static const struct file_operations microcode_fops = { - .owner = THIS_MODULE, - .write = microcode_write, - .open = microcode_open, - .llseek = no_llseek, -}; - -static struct miscdevice microcode_dev = { - .minor = MICROCODE_MINOR, - .name = "microcode", - .nodename = "cpu/microcode", - .fops = µcode_fops, -}; - -static int __init microcode_dev_init(void) -{ - int error; - - error = misc_register(µcode_dev); - if (error) { - pr_err("can't misc_register on minor=%d\n", MICROCODE_MINOR); - return error; - } - - return 0; -} - -static void __exit microcode_dev_exit(void) -{ - misc_deregister(µcode_dev); -} -#else -#define microcode_dev_init() 0 -#define microcode_dev_exit() do { } while (0) -#endif - /* fake device for request_firmware */ static struct platform_device *microcode_pdev; @@ -856,10 +764,6 @@ static int __init microcode_init(void) goto out_driver; } - error = microcode_dev_init(); - if (error) - goto out_ucode_group; - register_syscore_ops(&mc_syscore_ops); cpuhp_setup_state_nocalls(CPUHP_AP_MICROCODE_LOADER, "x86/microcode:starting", mc_cpu_starting, NULL); @@ -870,10 +774,6 @@ static int __init microcode_init(void) return 0; - out_ucode_group: - sysfs_remove_group(&cpu_subsys.dev_root->kobj, - &cpu_root_microcode_group); - out_driver: cpus_read_lock(); mutex_lock(µcode_mutex); From a77a94f86273ce42a39cb479217dd8d68acfe0ff Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 25 May 2022 18:12:30 +0200 Subject: [PATCH 35/49] x86/microcode: Default-disable late loading It is dangerous and it should not be used anyway - there's a nice early loading already. Requested-by: Peter Zijlstra (Intel) Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20220525161232.14924-3-bp@alien8.de --- arch/x86/Kconfig | 11 +++++++++++ arch/x86/kernel/cpu/common.c | 2 ++ arch/x86/kernel/cpu/microcode/core.c | 7 ++++++- 3 files changed, 19 insertions(+), 1 deletion(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index f423a2d87b15..976309d57a58 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1350,6 +1350,17 @@ config MICROCODE_AMD If you select this option, microcode patch loading support for AMD processors will be enabled. +config MICROCODE_LATE_LOADING + bool "Late microcode loading (DANGEROUS)" + default n + depends on MICROCODE + help + Loading microcode late, when the system is up and executing instructions + is a tricky business and should be avoided if possible. Just the sequence + of synchronizing all cores and SMT threads is one fragile dance which does + not guarantee that cores might not softlock after the loading. Therefore, + use this at your own risk. Late loading taints the kernel too. + config X86_MSR tristate "/dev/cpu/*/msr - Model-specific register support" help diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 2e9142797c99..c296cb1c0113 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -2222,6 +2222,7 @@ void cpu_init_secondary(void) } #endif +#ifdef CONFIG_MICROCODE_LATE_LOADING /* * The microcode loader calls this upon late microcode load to recheck features, * only when microcode has been updated. Caller holds microcode_mutex and CPU @@ -2251,6 +2252,7 @@ void microcode_check(void) pr_warn("x86/CPU: CPU features have changed after loading microcode, but might not take effect.\n"); pr_warn("x86/CPU: Please consider either early loading through initrd/built-in or a potential BIOS update.\n"); } +#endif /* * Invoked from core CPU hotplug code after hotplug operations diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index b72c4134f289..c717db6b6856 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -376,6 +376,7 @@ static int apply_microcode_on_target(int cpu) /* fake device for request_firmware */ static struct platform_device *microcode_pdev; +#ifdef CONFIG_MICROCODE_LATE_LOADING /* * Late loading dance. Why the heavy-handed stomp_machine effort? * @@ -543,6 +544,9 @@ put: return ret; } +static DEVICE_ATTR_WO(reload); +#endif + static ssize_t version_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -559,7 +563,6 @@ static ssize_t pf_show(struct device *dev, return sprintf(buf, "0x%x\n", uci->cpu_sig.pf); } -static DEVICE_ATTR_WO(reload); static DEVICE_ATTR(version, 0444, version_show, NULL); static DEVICE_ATTR(processor_flags, 0444, pf_show, NULL); @@ -712,7 +715,9 @@ static int mc_cpu_down_prep(unsigned int cpu) } static struct attribute *cpu_root_microcode_attrs[] = { +#ifdef CONFIG_MICROCODE_LATE_LOADING &dev_attr_reload.attr, +#endif NULL }; From d23d33ea0fcdc4bbb484990bf53867f99c63ccab Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 25 May 2022 18:12:31 +0200 Subject: [PATCH 36/49] x86/microcode: Taint and warn on late loading Warn before it is attempted and taint the kernel. Late loading microcode can lead to malfunction of the kernel when the microcode update changes behaviour. There is no way for the kernel to determine whether its safe or not. Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20220525161232.14924-4-bp@alien8.de --- arch/x86/kernel/cpu/microcode/core.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index c717db6b6856..801b44ac3851 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -493,6 +493,9 @@ static int microcode_reload_late(void) { int ret; + pr_err("Attempting late microcode loading - it is dangerous and taints the kernel.\n"); + pr_err("You should switch to early loading, if possible.\n"); + atomic_set(&late_cpus_in, 0); atomic_set(&late_cpus_out, 0); @@ -541,6 +544,8 @@ put: if (ret == 0) ret = size; + add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK); + return ret; } From 0c0fe08c76485fe0178ebb0fa1a2052c727abe94 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 25 May 2022 18:12:32 +0200 Subject: [PATCH 37/49] x86/microcode: Remove unnecessary perf callback c93dc84cbe32 ("perf/x86: Add a microcode revision check for SNB-PEBS") checks whether the microcode revision has fixed PEBS issues. This can happen either: 1. At PEBS init time, where the early microcode has been loaded already 2. During late loading, in the microcode_check() callback. So remove the unnecessary call in the microcode loader init routine. Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20220525161232.14924-5-bp@alien8.de --- arch/x86/kernel/cpu/microcode/core.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 801b44ac3851..ad57e0e4d674 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -756,10 +756,7 @@ static int __init microcode_init(void) cpus_read_lock(); mutex_lock(µcode_mutex); - error = subsys_interface_register(&mc_cpu_interface); - if (!error) - perf_check_microcode(); mutex_unlock(µcode_mutex); cpus_read_unlock(); From 662ce1dc9caf493c309200edbe38d186f1ea20d0 Mon Sep 17 00:00:00 2001 From: Yang Yang Date: Wed, 1 Jun 2022 15:55:25 -0700 Subject: [PATCH 38/49] delayacct: track delays from write-protect copy Delay accounting does not track the delay of write-protect copy. When tasks trigger many write-protect copys(include COW and unsharing of anonymous pages[1]), it may spend a amount of time waiting for them. To get the delay of tasks in write-protect copy, could help users to evaluate the impact of using KSM or fork() or GUP. Also update tools/accounting/getdelays.c: / # ./getdelays -dl -p 231 print delayacct stats ON listen forever PID 231 CPU count real total virtual total delay total delay average 6247 1859000000 2154070021 1674255063 0.268ms IO count delay total delay average 0 0 0ms SWAP count delay total delay average 0 0 0ms RECLAIM count delay total delay average 0 0 0ms THRASHING count delay total delay average 0 0 0ms COMPACT count delay total delay average 3 72758 0ms WPCOPY count delay total delay average 3635 271567604 0ms [1] commit 31cc5bc4af70("mm: support GUP-triggered unsharing of anonymous pages") Link: https://lkml.kernel.org/r/20220409014342.2505532-1-yang.yang29@zte.com.cn Signed-off-by: Yang Yang Reviewed-by: David Hildenbrand Reviewed-by: Jiang Xuexin Reviewed-by: Ran Xiaokai Reviewed-by: wangyong Cc: Jonathan Corbet Cc: Balbir Singh Cc: Mike Kravetz Cc: Stephen Rothwell Signed-off-by: Andrew Morton --- Documentation/accounting/delay-accounting.rst | 5 +++- include/linux/delayacct.h | 28 +++++++++++++++++++ include/uapi/linux/taskstats.h | 6 +++- kernel/delayacct.c | 16 +++++++++++ mm/hugetlb.c | 8 ++++++ mm/memory.c | 8 ++++++ tools/accounting/getdelays.c | 8 +++++- 7 files changed, 76 insertions(+), 3 deletions(-) diff --git a/Documentation/accounting/delay-accounting.rst b/Documentation/accounting/delay-accounting.rst index 197fe319cbec..241d1a87f2cd 100644 --- a/Documentation/accounting/delay-accounting.rst +++ b/Documentation/accounting/delay-accounting.rst @@ -15,6 +15,7 @@ c) swapping in pages d) memory reclaim e) thrashing page cache f) direct compact +g) write-protect copy and makes these statistics available to userspace through the taskstats interface. @@ -48,7 +49,7 @@ this structure. See for a description of the fields pertaining to delay accounting. It will generally be in the form of counters returning the cumulative delay seen for cpu, sync block I/O, swapin, memory reclaim, thrash page -cache, direct compact etc. +cache, direct compact, write-protect copy etc. Taking the difference of two successive readings of a given counter (say cpu_delay_total) for a task will give the delay @@ -117,6 +118,8 @@ Get sum of delays, since system boot, for all pids with tgid 5:: 0 0 0ms COMPACT count delay total delay average 0 0 0ms + WPCOPY count delay total delay average + 0 0 0ms Get IO accounting for pid 1, it works only with -p:: diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 6b16a6930a19..58aea2d7385c 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -45,9 +45,13 @@ struct task_delay_info { u64 compact_start; u64 compact_delay; /* wait for memory compact */ + u64 wpcopy_start; + u64 wpcopy_delay; /* wait for write-protect copy */ + u32 freepages_count; /* total count of memory reclaim */ u32 thrashing_count; /* total count of thrash waits */ u32 compact_count; /* total count of memory compact */ + u32 wpcopy_count; /* total count of write-protect copy */ }; #endif @@ -75,6 +79,8 @@ extern void __delayacct_swapin_start(void); extern void __delayacct_swapin_end(void); extern void __delayacct_compact_start(void); extern void __delayacct_compact_end(void); +extern void __delayacct_wpcopy_start(void); +extern void __delayacct_wpcopy_end(void); static inline void delayacct_tsk_init(struct task_struct *tsk) { @@ -191,6 +197,24 @@ static inline void delayacct_compact_end(void) __delayacct_compact_end(); } +static inline void delayacct_wpcopy_start(void) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (current->delays) + __delayacct_wpcopy_start(); +} + +static inline void delayacct_wpcopy_end(void) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (current->delays) + __delayacct_wpcopy_end(); +} + #else static inline void delayacct_init(void) {} @@ -225,6 +249,10 @@ static inline void delayacct_compact_start(void) {} static inline void delayacct_compact_end(void) {} +static inline void delayacct_wpcopy_start(void) +{} +static inline void delayacct_wpcopy_end(void) +{} #endif /* CONFIG_TASK_DELAY_ACCT */ diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h index 736154171489..a7f5b11a8f1b 100644 --- a/include/uapi/linux/taskstats.h +++ b/include/uapi/linux/taskstats.h @@ -34,7 +34,7 @@ */ -#define TASKSTATS_VERSION 12 +#define TASKSTATS_VERSION 13 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -194,6 +194,10 @@ struct taskstats { __u64 ac_exe_dev; /* program binary device ID */ __u64 ac_exe_inode; /* program binary inode number */ /* v12 end */ + + /* v13: Delay waiting for write-protect copy */ + __u64 wpcopy_count; + __u64 wpcopy_delay_total; }; diff --git a/kernel/delayacct.c b/kernel/delayacct.c index 2c1e18f7c5cf..164ed9ef77a3 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -177,11 +177,14 @@ int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) d->thrashing_delay_total = (tmp < d->thrashing_delay_total) ? 0 : tmp; tmp = d->compact_delay_total + tsk->delays->compact_delay; d->compact_delay_total = (tmp < d->compact_delay_total) ? 0 : tmp; + tmp = d->wpcopy_delay_total + tsk->delays->wpcopy_delay; + d->wpcopy_delay_total = (tmp < d->wpcopy_delay_total) ? 0 : tmp; d->blkio_count += tsk->delays->blkio_count; d->swapin_count += tsk->delays->swapin_count; d->freepages_count += tsk->delays->freepages_count; d->thrashing_count += tsk->delays->thrashing_count; d->compact_count += tsk->delays->compact_count; + d->wpcopy_count += tsk->delays->wpcopy_count; raw_spin_unlock_irqrestore(&tsk->delays->lock, flags); return 0; @@ -249,3 +252,16 @@ void __delayacct_compact_end(void) ¤t->delays->compact_delay, ¤t->delays->compact_count); } + +void __delayacct_wpcopy_start(void) +{ + current->delays->wpcopy_start = local_clock(); +} + +void __delayacct_wpcopy_end(void) +{ + delayacct_end(¤t->delays->lock, + ¤t->delays->wpcopy_start, + ¤t->delays->wpcopy_delay, + ¤t->delays->wpcopy_count); +} diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 7c468ac1d069..a57e1be41401 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include @@ -5230,6 +5231,8 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma, pte = huge_ptep_get(ptep); old_page = pte_page(pte); + delayacct_wpcopy_start(); + retry_avoidcopy: /* * If no-one else is actually using this page, we're the exclusive @@ -5240,6 +5243,8 @@ retry_avoidcopy: page_move_anon_rmap(old_page, vma); if (likely(!unshare)) set_huge_ptep_writable(vma, haddr, ptep); + + delayacct_wpcopy_end(); return 0; } VM_BUG_ON_PAGE(PageAnon(old_page) && PageAnonExclusive(old_page), @@ -5309,6 +5314,7 @@ retry_avoidcopy: * race occurs while re-acquiring page table * lock, and our job is done. */ + delayacct_wpcopy_end(); return 0; } @@ -5367,6 +5373,8 @@ out_release_old: put_page(old_page); spin_lock(ptl); /* Caller expects lock to be held */ + + delayacct_wpcopy_end(); return ret; } diff --git a/mm/memory.c b/mm/memory.c index 21dadf03f089..7a089145cad4 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3090,6 +3090,8 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) int page_copied = 0; struct mmu_notifier_range range; + delayacct_wpcopy_start(); + if (unlikely(anon_vma_prepare(vma))) goto oom; @@ -3114,6 +3116,8 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) put_page(new_page); if (old_page) put_page(old_page); + + delayacct_wpcopy_end(); return 0; } } @@ -3220,12 +3224,16 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) free_swap_cache(old_page); put_page(old_page); } + + delayacct_wpcopy_end(); return (page_copied && !unshare) ? VM_FAULT_WRITE : 0; oom_free_new: put_page(new_page); oom: if (old_page) put_page(old_page); + + delayacct_wpcopy_end(); return VM_FAULT_OOM; } diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c index 11e86739456d..e83e6e47a21e 100644 --- a/tools/accounting/getdelays.c +++ b/tools/accounting/getdelays.c @@ -207,6 +207,8 @@ static void print_delayacct(struct taskstats *t) "THRASHING%12s%15s%15s\n" " %15llu%15llu%15llums\n" "COMPACT %12s%15s%15s\n" + " %15llu%15llu%15llums\n" + "WPCOPY %12s%15s%15s\n" " %15llu%15llu%15llums\n", "count", "real total", "virtual total", "delay total", "delay average", @@ -234,7 +236,11 @@ static void print_delayacct(struct taskstats *t) "count", "delay total", "delay average", (unsigned long long)t->compact_count, (unsigned long long)t->compact_delay_total, - average_ms(t->compact_delay_total, t->compact_count)); + average_ms(t->compact_delay_total, t->compact_count), + "count", "delay total", "delay average", + (unsigned long long)t->wpcopy_count, + (unsigned long long)t->wpcopy_delay_total, + average_ms(t->wpcopy_delay_total, t->wpcopy_count)); } static void task_context_switch_counts(struct taskstats *t) From 1ff810c16d651547fd1781a0b8b29cab547152b2 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 27 May 2022 13:18:52 -0700 Subject: [PATCH 39/49] mailmap: update Josh Poimboeuf's email I recently switched to my kernel.org email address. Add aliases for my previous Red Hat and IBM addresses. Link: https://lkml.kernel.org/r/0519dcfbb1ee2cb82cb32b0aff61410a62949aa5.1653682698.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf Suggested-by: Nick Desaulniers Signed-off-by: Andrew Morton --- .mailmap | 2 ++ 1 file changed, 2 insertions(+) diff --git a/.mailmap b/.mailmap index 6d484937f901..5956aa8d442a 100644 --- a/.mailmap +++ b/.mailmap @@ -201,6 +201,8 @@ Jordan Crouse +Josh Poimboeuf +Josh Poimboeuf Juha Yrjola Juha Yrjola Juha Yrjola From 273aea955ece88a14664fa1cbff5542f05ab0a29 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Mon, 30 May 2022 19:45:05 +0800 Subject: [PATCH 40/49] MAINTAINERS: add maintainer information for z3fold Add the maintainer information for the z3fold compressed page allocator. Also Add myself as a reviewer. Link: https://lkml.kernel.org/r/20220530114505.52367-1-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Cc: Vitaly Wool Signed-off-by: Andrew Morton --- MAINTAINERS | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 7dff84d95e5f..42da5322f1a4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -21958,6 +21958,13 @@ L: linux-mm@kvack.org S: Maintained F: mm/zbud.c +Z3FOLD COMPRESSED PAGE ALLOCATOR +M: Vitaly Wool +R: Miaohe Lin +L: linux-mm@kvack.org +S: Maintained +F: mm/z3fold.c + ZD1211RW WIRELESS DRIVER M: Ulrich Kunitz L: linux-wireless@vger.kernel.org From 0111def915b280c64c05f73f01b59ca404255aa3 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Fri, 27 May 2022 16:19:48 +0800 Subject: [PATCH 41/49] mm: hugetlb_vmemmap: fix CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON The following: commit 47010c040dec ("mm: hugetlb_vmemmap: cleanup CONFIG_HUGETLB_PAGE_FREE_VMEMMAP*") forgot to update CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON used in vmemmap_optimize_mode to CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON. The result is we cannot enable hugetlb_optimize_vmemmap at boot time when we configure CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON. Fix it. Link: https://lkml.kernel.org/r/20220527081948.68832-1-songmuchun@bytedance.com Fixes: 47010c040dec ("mm: hugetlb_vmemmap: cleanup CONFIG_HUGETLB_PAGE_FREE_VMEMMAP*") Signed-off-by: Muchun Song Reported-by: Vlastimil Babka Acked-by: Vlastimil Babka Cc: Mike Kravetz Signed-off-by: Andrew Morton --- mm/hugetlb_vmemmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index fcd9f7872064..1089ea8a9c98 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -33,7 +33,7 @@ DEFINE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON, EXPORT_SYMBOL(hugetlb_optimize_vmemmap_key); static enum vmemmap_optimize_mode vmemmap_optimize_mode = - IS_ENABLED(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON); + IS_ENABLED(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON); static void vmemmap_optimize_mode_switch(enum vmemmap_optimize_mode to) { From 547be963c99f1e9ebc1cfabf630f64601a98dd00 Mon Sep 17 00:00:00 2001 From: Zi Yan Date: Mon, 30 May 2022 22:44:50 -0400 Subject: [PATCH 42/49] mm: page_isolation: use compound_nr() correctly in isolate_single_pageblock() When compound_nr(page) was used, page was not guaranteed to be the head of the compound page and it could cause an infinite loop. Fix it by calling it on the head page. Link: https://lkml.kernel.org/r/20220531024450.2498431-1-zi.yan@sent.com Fixes: b2c9e2fbba32 ("mm: make alloc_contig_range work at pageblock granularity") Signed-off-by: Zi Yan Reported-by: Anshuman Khandual Link: https://lore.kernel.org/linux-mm/20220530115027.123341-1-anshuman.khandual@arm.com/ Reviewed-by: Anshuman Khandual Reviewed-by: Miaohe Lin Reviewed-by: Oscar Salvador Acked-by: Muchun Song Cc: David Hildenbrand Cc: Qian Cai Cc: Vlastimil Babka Cc: Mel Gorman Cc: Eric Ren Cc: Mike Rapoport Cc: Christophe Leroy Signed-off-by: Andrew Morton --- mm/page_isolation.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 6021f8444b5a..d200d41ad0d3 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -385,9 +385,9 @@ static int isolate_single_pageblock(unsigned long boundary_pfn, int flags, * above do the rest. If migration is not possible, just fail. */ if (PageCompound(page)) { - unsigned long nr_pages = compound_nr(page); struct page *head = compound_head(page); unsigned long head_pfn = page_to_pfn(head); + unsigned long nr_pages = compound_nr(head); if (head_pfn + nr_pages <= boundary_pfn) { pfn = head_pfn + nr_pages; From a04e1928e2ead144dc2f369768bc0a0f3110af89 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Tue, 31 May 2022 20:26:43 +0800 Subject: [PATCH 43/49] mm/memremap: fix missing call to untrack_pfn() in pagemap_range() We forget to call untrack_pfn() to pair with track_pfn_remap() when range is not allowed to hotplug. Fix it by jump err_kasan. Link: https://lkml.kernel.org/r/20220531122643.25249-1-linmiaohe@huawei.com Fixes: bca3feaa0764 ("mm/memory_hotplug: prevalidate the address range being added with platform") Signed-off-by: Miaohe Lin Reviewed-by: David Hildenbrand Acked-by: Muchun Song Cc: Anshuman Khandual Cc: Oscar Salvador Cc: Signed-off-by: Andrew Morton --- mm/memremap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memremap.c b/mm/memremap.c index 2b92e97cb25b..b870a659eee6 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -214,7 +214,7 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params, if (!mhp_range_allowed(range->start, range_len(range), !is_private)) { error = -EINVAL; - goto err_pfn_remap; + goto err_kasan; } mem_hotplug_begin(); From b3e34a47f98974d0844444c5121aaff123004e57 Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Wed, 23 Feb 2022 19:32:24 +0800 Subject: [PATCH 44/49] x86/kexec: fix memory leak of elf header buffer This is reported by kmemleak detector: unreferenced object 0xffffc900002a9000 (size 4096): comm "kexec", pid 14950, jiffies 4295110793 (age 373.951s) hex dump (first 32 bytes): 7f 45 4c 46 02 01 01 00 00 00 00 00 00 00 00 00 .ELF............ 04 00 3e 00 01 00 00 00 00 00 00 00 00 00 00 00 ..>............. backtrace: [<0000000016a8ef9f>] __vmalloc_node_range+0x101/0x170 [<000000002b66b6c0>] __vmalloc_node+0xb4/0x160 [<00000000ad40107d>] crash_prepare_elf64_headers+0x8e/0xcd0 [<0000000019afff23>] crash_load_segments+0x260/0x470 [<0000000019ebe95c>] bzImage64_load+0x814/0xad0 [<0000000093e16b05>] arch_kexec_kernel_image_load+0x1be/0x2a0 [<000000009ef2fc88>] kimage_file_alloc_init+0x2ec/0x5a0 [<0000000038f5a97a>] __do_sys_kexec_file_load+0x28d/0x530 [<0000000087c19992>] do_syscall_64+0x3b/0x90 [<0000000066e063a4>] entry_SYSCALL_64_after_hwframe+0x44/0xae In crash_prepare_elf64_headers(), a buffer is allocated via vmalloc() to store elf headers. While it's not freed back to system correctly when kdump kernel is reloaded or unloaded. Then memory leak is caused. Fix it by introducing x86 specific function arch_kimage_file_post_load_cleanup(), and freeing the buffer there. And also remove the incorrect elf header buffer freeing code. Before calling arch specific kexec_file loading function, the image instance has been initialized. So 'image->elf_headers' must be NULL. It doesn't make sense to free the elf header buffer in the place. Three different people have reported three bugs about the memory leak on x86_64 inside Redhat. Link: https://lkml.kernel.org/r/20220223113225.63106-2-bhe@redhat.com Signed-off-by: Baoquan He Acked-by: Dave Young Cc: Signed-off-by: Andrew Morton --- arch/x86/kernel/machine_kexec_64.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 566bb8e17149..0611fd83858e 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -376,9 +376,6 @@ void machine_kexec(struct kimage *image) #ifdef CONFIG_KEXEC_FILE void *arch_kexec_kernel_image_load(struct kimage *image) { - vfree(image->elf_headers); - image->elf_headers = NULL; - if (!image->fops || !image->fops->load) return ERR_PTR(-ENOEXEC); @@ -514,6 +511,15 @@ overflow: (int)ELF64_R_TYPE(rel[i].r_info), value); return -ENOEXEC; } + +int arch_kimage_file_post_load_cleanup(struct kimage *image) +{ + vfree(image->elf_headers); + image->elf_headers = NULL; + image->elf_headers_sz = 0; + + return kexec_image_post_load_cleanup_default(image); +} #endif /* CONFIG_KEXEC_FILE */ static int From a19cad0691597eb79c123b8a19a9faba5ab7d90e Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 1 Jun 2022 15:57:16 -0700 Subject: [PATCH 45/49] mm/oom_kill.c: fix vm_oom_kill_table[] ifdeffery arm allnoconfig: mm/oom_kill.c:60:25: warning: 'vm_oom_kill_table' defined but not used [-Wunused-variable] 60 | static struct ctl_table vm_oom_kill_table[] = { | ^~~~~~~~~~~~~~~~~ Cc: Luis Chamberlain Signed-off-by: Andrew Morton --- mm/oom_kill.c | 58 +++++++++++++++++++++++++-------------------------- 1 file changed, 29 insertions(+), 29 deletions(-) diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 8a70bca67c94..3c6cf9e3cd66 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -56,35 +56,6 @@ static int sysctl_panic_on_oom; static int sysctl_oom_kill_allocating_task; static int sysctl_oom_dump_tasks = 1; -#ifdef CONFIG_SYSCTL -static struct ctl_table vm_oom_kill_table[] = { - { - .procname = "panic_on_oom", - .data = &sysctl_panic_on_oom, - .maxlen = sizeof(sysctl_panic_on_oom), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_TWO, - }, - { - .procname = "oom_kill_allocating_task", - .data = &sysctl_oom_kill_allocating_task, - .maxlen = sizeof(sysctl_oom_kill_allocating_task), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "oom_dump_tasks", - .data = &sysctl_oom_dump_tasks, - .maxlen = sizeof(sysctl_oom_dump_tasks), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - {} -}; -#endif - /* * Serializes oom killer invocations (out_of_memory()) from all contexts to * prevent from over eager oom killing (e.g. when the oom killer is invoked @@ -729,6 +700,35 @@ static void queue_oom_reaper(struct task_struct *tsk) add_timer(&tsk->oom_reaper_timer); } +#ifdef CONFIG_SYSCTL +static struct ctl_table vm_oom_kill_table[] = { + { + .procname = "panic_on_oom", + .data = &sysctl_panic_on_oom, + .maxlen = sizeof(sysctl_panic_on_oom), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_TWO, + }, + { + .procname = "oom_kill_allocating_task", + .data = &sysctl_oom_kill_allocating_task, + .maxlen = sizeof(sysctl_oom_kill_allocating_task), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "oom_dump_tasks", + .data = &sysctl_oom_dump_tasks, + .maxlen = sizeof(sysctl_oom_dump_tasks), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + {} +}; +#endif + static int __init oom_init(void) { oom_reaper_th = kthread_run(oom_reaper, NULL, "oom_reaper"); From 0c9782e204d3cc5625b9e8bf4e8625d38dfe0139 Mon Sep 17 00:00:00 2001 From: Kristen Carlson Accardi Date: Fri, 20 May 2022 10:42:47 -0700 Subject: [PATCH 46/49] x86/sgx: Set active memcg prior to shmem allocation When the system runs out of enclave memory, SGX can reclaim EPC pages by swapping to normal RAM. These backing pages are allocated via a per-enclave shared memory area. Since SGX allows unlimited over commit on EPC memory, the reclaimer thread can allocate a large number of backing RAM pages in response to EPC memory pressure. When the shared memory backing RAM allocation occurs during the reclaimer thread context, the shared memory is charged to the root memory control group, and the shmem usage of the enclave is not properly accounted for, making cgroups ineffective at limiting the amount of RAM an enclave can consume. For example, when using a cgroup to launch a set of test enclaves, the kernel does not properly account for 50% - 75% of shmem page allocations on average. In the worst case, when nearly all allocations occur during the reclaimer thread, the kernel accounts less than a percent of the amount of shmem used by the enclave's cgroup to the correct cgroup. SGX stores a list of mm_structs that are associated with an enclave. Pick one of them during reclaim and charge that mm's memcg with the shmem allocation. The one that gets picked is arbitrary, but this list almost always only has one mm. The cases where there is more than one mm with different memcg's are not worth considering. Create a new function - sgx_encl_alloc_backing(). This function is used whenever a new backing storage page needs to be allocated. Previously the same function was used for page allocation as well as retrieving a previously allocated page. Prior to backing page allocation, if there is a mm_struct associated with the enclave that is requesting the allocation, it is set as the active memory control group. [ dhansen: - fix merge conflict with ELDU fixes - check against actual ksgxd_tsk, not ->mm ] Cc: stable@vger.kernel.org Signed-off-by: Kristen Carlson Accardi Signed-off-by: Dave Hansen Reviewed-by: Shakeel Butt Acked-by: Roman Gushchin Link: https://lkml.kernel.org/r/20220520174248.4918-1-kristen@linux.intel.com --- arch/x86/kernel/cpu/sgx/encl.c | 105 ++++++++++++++++++++++++++++++++- arch/x86/kernel/cpu/sgx/encl.h | 7 ++- arch/x86/kernel/cpu/sgx/main.c | 9 ++- 3 files changed, 115 insertions(+), 6 deletions(-) diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index 3c24e6124d95..19876ebfb504 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -152,7 +152,7 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page, page_pcmd_off = sgx_encl_get_backing_page_pcmd_offset(encl, page_index); - ret = sgx_encl_get_backing(encl, page_index, &b); + ret = sgx_encl_lookup_backing(encl, page_index, &b); if (ret) return ret; @@ -718,7 +718,7 @@ static struct page *sgx_encl_get_backing_page(struct sgx_encl *encl, * 0 on success, * -errno otherwise. */ -int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, +static int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, struct sgx_backing *backing) { pgoff_t page_pcmd_off = sgx_encl_get_backing_page_pcmd_offset(encl, page_index); @@ -743,6 +743,107 @@ int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, return 0; } +/* + * When called from ksgxd, returns the mem_cgroup of a struct mm stored + * in the enclave's mm_list. When not called from ksgxd, just returns + * the mem_cgroup of the current task. + */ +static struct mem_cgroup *sgx_encl_get_mem_cgroup(struct sgx_encl *encl) +{ + struct mem_cgroup *memcg = NULL; + struct sgx_encl_mm *encl_mm; + int idx; + + /* + * If called from normal task context, return the mem_cgroup + * of the current task's mm. The remainder of the handling is for + * ksgxd. + */ + if (!current_is_ksgxd()) + return get_mem_cgroup_from_mm(current->mm); + + /* + * Search the enclave's mm_list to find an mm associated with + * this enclave to charge the allocation to. + */ + idx = srcu_read_lock(&encl->srcu); + + list_for_each_entry_rcu(encl_mm, &encl->mm_list, list) { + if (!mmget_not_zero(encl_mm->mm)) + continue; + + memcg = get_mem_cgroup_from_mm(encl_mm->mm); + + mmput_async(encl_mm->mm); + + break; + } + + srcu_read_unlock(&encl->srcu, idx); + + /* + * In the rare case that there isn't an mm associated with + * the enclave, set memcg to the current active mem_cgroup. + * This will be the root mem_cgroup if there is no active + * mem_cgroup. + */ + if (!memcg) + return get_mem_cgroup_from_mm(NULL); + + return memcg; +} + +/** + * sgx_encl_alloc_backing() - allocate a new backing storage page + * @encl: an enclave pointer + * @page_index: enclave page index + * @backing: data for accessing backing storage for the page + * + * When called from ksgxd, sets the active memcg from one of the + * mms in the enclave's mm_list prior to any backing page allocation, + * in order to ensure that shmem page allocations are charged to the + * enclave. + * + * Return: + * 0 on success, + * -errno otherwise. + */ +int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index, + struct sgx_backing *backing) +{ + struct mem_cgroup *encl_memcg = sgx_encl_get_mem_cgroup(encl); + struct mem_cgroup *memcg = set_active_memcg(encl_memcg); + int ret; + + ret = sgx_encl_get_backing(encl, page_index, backing); + + set_active_memcg(memcg); + mem_cgroup_put(encl_memcg); + + return ret; +} + +/** + * sgx_encl_lookup_backing() - retrieve an existing backing storage page + * @encl: an enclave pointer + * @page_index: enclave page index + * @backing: data for accessing backing storage for the page + * + * Retrieve a backing page for loading data back into an EPC page with ELDU. + * It is the caller's responsibility to ensure that it is appropriate to use + * sgx_encl_lookup_backing() rather than sgx_encl_alloc_backing(). If lookup is + * not used correctly, this will cause an allocation which is not accounted for. + * + * Return: + * 0 on success, + * -errno otherwise. + */ +int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index, + struct sgx_backing *backing) +{ + return sgx_encl_get_backing(encl, page_index, backing); +} + /** * sgx_encl_put_backing() - Unpin the backing storage * @backing: data for accessing backing storage for the page diff --git a/arch/x86/kernel/cpu/sgx/encl.h b/arch/x86/kernel/cpu/sgx/encl.h index d44e7372151f..332ef3568267 100644 --- a/arch/x86/kernel/cpu/sgx/encl.h +++ b/arch/x86/kernel/cpu/sgx/encl.h @@ -103,10 +103,13 @@ static inline int sgx_encl_find(struct mm_struct *mm, unsigned long addr, int sgx_encl_may_map(struct sgx_encl *encl, unsigned long start, unsigned long end, unsigned long vm_flags); +bool current_is_ksgxd(void); void sgx_encl_release(struct kref *ref); int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm); -int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, - struct sgx_backing *backing); +int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index, + struct sgx_backing *backing); +int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index, + struct sgx_backing *backing); void sgx_encl_put_backing(struct sgx_backing *backing); int sgx_encl_test_and_clear_young(struct mm_struct *mm, struct sgx_encl_page *page); diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index ab4ec54bbdd9..a78652d43e61 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -313,7 +313,7 @@ static void sgx_reclaimer_write(struct sgx_epc_page *epc_page, sgx_encl_put_backing(backing); if (!encl->secs_child_cnt && test_bit(SGX_ENCL_INITIALIZED, &encl->flags)) { - ret = sgx_encl_get_backing(encl, PFN_DOWN(encl->size), + ret = sgx_encl_alloc_backing(encl, PFN_DOWN(encl->size), &secs_backing); if (ret) goto out; @@ -384,7 +384,7 @@ static void sgx_reclaim_pages(void) page_index = PFN_DOWN(encl_page->desc - encl_page->encl->base); mutex_lock(&encl_page->encl->lock); - ret = sgx_encl_get_backing(encl_page->encl, page_index, &backing[i]); + ret = sgx_encl_alloc_backing(encl_page->encl, page_index, &backing[i]); if (ret) { mutex_unlock(&encl_page->encl->lock); goto skip; @@ -475,6 +475,11 @@ static bool __init sgx_page_reclaimer_init(void) return true; } +bool current_is_ksgxd(void) +{ + return current == ksgxd_tsk; +} + static struct sgx_epc_page *__sgx_alloc_epc_page_from_node(int nid) { struct sgx_numa_node *node = &sgx_numa_nodes[nid]; From 40a1926022d128057376d35167128a7c74e3dca4 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 5 Jun 2022 14:01:42 -0400 Subject: [PATCH 47/49] fix the breakage in close_fd_get_file() calling conventions change It used to grab an extra reference to struct file rather than just transferring to caller the one it had removed from descriptor table. New variant doesn't, and callers need to be adjusted. Reported-and-tested-by: syzbot+47dd250f527cb7bebf24@syzkaller.appspotmail.com Fixes: 6319194ec57b ("Unify the primitives for file descriptor closing") Signed-off-by: Al Viro --- drivers/android/binder.c | 2 ++ fs/file.c | 3 +-- fs/io_uring.c | 5 +---- 3 files changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 27c9b004823a..73beea5dc18c 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -1857,6 +1857,8 @@ static void binder_deferred_fd_close(int fd) init_task_work(&twcb->twork, binder_do_fd_close); twcb->file = close_fd_get_file(fd); if (twcb->file) { + // pin it until binder_do_fd_close(); see comments there + get_file(twcb->file); filp_close(twcb->file, current->files); task_work_add(current, &twcb->twork, TWA_RESUME); } else { diff --git a/fs/file.c b/fs/file.c index dd6692048f4f..3bcc1ecc314a 100644 --- a/fs/file.c +++ b/fs/file.c @@ -800,8 +800,7 @@ struct file *__close_fd_get_file(unsigned int fd) /* * variant of close_fd that gets a ref on the file for later fput. - * The caller must ensure that filp_close() called on the file, and then - * an fput(). + * The caller must ensure that filp_close() called on the file. */ struct file *close_fd_get_file(unsigned int fd) { diff --git a/fs/io_uring.c b/fs/io_uring.c index 7257b0870353..33da5116cc38 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -5110,7 +5110,7 @@ static int io_close(struct io_kiocb *req, unsigned int issue_flags) struct files_struct *files = current->files; struct io_close *close = &req->close; struct fdtable *fdt; - struct file *file = NULL; + struct file *file; int ret = -EBADF; if (req->close.file_slot) { @@ -5127,7 +5127,6 @@ static int io_close(struct io_kiocb *req, unsigned int issue_flags) file = fdt->fd[close->fd]; if (!file || file->f_op == &io_uring_fops) { spin_unlock(&files->file_lock); - file = NULL; goto err; } @@ -5147,8 +5146,6 @@ static int io_close(struct io_kiocb *req, unsigned int issue_flags) err: if (ret < 0) req_set_fail(req); - if (file) - fput(file); __io_req_complete(req, issue_flags, ret, 0); return 0; } From e1cff7002b716bd0b5f5f4afd4273c99aa8644be Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 5 Jun 2022 11:51:48 -0700 Subject: [PATCH 48/49] bluetooth: don't use bitmaps for random flag accesses The bluetooth code uses our bitmap infrastructure for the two bits (!) of connection setup flags, and in the process causes odd problems when it converts between a bitmap and just the regular values of said bits. It's completely pointless to do things like bitmap_to_arr32() to convert a bitmap into a u32. It shoudln't have been a bitmap in the first place. The reason to use bitmaps is if you have arbitrary number of bits you want to manage (not two!), or if you rely on the atomicity guarantees of the bitmap setting and clearing. The code could use an "atomic_t" and use "atomic_or/andnot()" to set and clear the bit values, but considering that it then copies the bitmaps around with "bitmap_to_arr32()" and friends, there clearly cannot be a lot of atomicity requirements. So just use a regular integer. In the process, this avoids the warnings about erroneous use of bitmap_from_u64() which were triggered on 32-bit architectures when conversion from a u64 would access two words (and, surprise, surprise, only one word is needed - and indeed overkill - for a 2-bit bitmap). That was always problematic, but the compiler seems to notice it and warn about the invalid pattern only after commit 0a97953fd221 ("lib: add bitmap_{from,to}_arr64") changed the exact implementation details of 'bitmap_from_u64()', as reported by Sudip Mukherjee and Stephen Rothwell. Fixes: fe92ee6425a2 ("Bluetooth: hci_core: Rework hci_conn_params flags") Link: https://lore.kernel.org/all/YpyJ9qTNHJzz0FHY@debian/ Link: https://lore.kernel.org/all/20220606080631.0c3014f2@canb.auug.org.au/ Link: https://lore.kernel.org/all/20220605162537.1604762-1-yury.norov@gmail.com/ Reported-by: Stephen Rothwell Reported-by: Sudip Mukherjee Reviewed-by: Yury Norov Cc: Luiz Augusto von Dentz Cc: Marcel Holtmann Signed-off-by: Linus Torvalds --- include/net/bluetooth/hci_core.h | 17 ++++++--------- net/bluetooth/hci_core.c | 4 ++-- net/bluetooth/hci_request.c | 2 +- net/bluetooth/hci_sync.c | 6 +++--- net/bluetooth/mgmt.c | 37 ++++++++++++-------------------- 5 files changed, 27 insertions(+), 39 deletions(-) diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 5a52a2018b56..c0ea2a4892b1 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -155,21 +155,18 @@ struct bdaddr_list_with_irk { u8 local_irk[16]; }; +/* Bitmask of connection flags */ enum hci_conn_flags { - HCI_CONN_FLAG_REMOTE_WAKEUP, - HCI_CONN_FLAG_DEVICE_PRIVACY, - - __HCI_CONN_NUM_FLAGS, + HCI_CONN_FLAG_REMOTE_WAKEUP = 1, + HCI_CONN_FLAG_DEVICE_PRIVACY = 2, }; - -/* Make sure number of flags doesn't exceed sizeof(current_flags) */ -static_assert(__HCI_CONN_NUM_FLAGS < 32); +typedef u8 hci_conn_flags_t; struct bdaddr_list_with_flags { struct list_head list; bdaddr_t bdaddr; u8 bdaddr_type; - DECLARE_BITMAP(flags, __HCI_CONN_NUM_FLAGS); + hci_conn_flags_t flags; }; struct bt_uuid { @@ -576,7 +573,7 @@ struct hci_dev { struct rfkill *rfkill; DECLARE_BITMAP(dev_flags, __HCI_NUM_FLAGS); - DECLARE_BITMAP(conn_flags, __HCI_CONN_NUM_FLAGS); + hci_conn_flags_t conn_flags; __s8 adv_tx_power; __u8 adv_data[HCI_MAX_EXT_AD_LENGTH]; @@ -775,7 +772,7 @@ struct hci_conn_params { struct hci_conn *conn; bool explicit_connect; - DECLARE_BITMAP(flags, __HCI_CONN_NUM_FLAGS); + hci_conn_flags_t flags; u8 privacy_mode; }; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 5abb2ca5b129..59a5c1341c26 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2153,7 +2153,7 @@ int hci_bdaddr_list_add_with_flags(struct list_head *list, bdaddr_t *bdaddr, bacpy(&entry->bdaddr, bdaddr); entry->bdaddr_type = type; - bitmap_from_u64(entry->flags, flags); + entry->flags = flags; list_add(&entry->list, list); @@ -2634,7 +2634,7 @@ int hci_register_dev(struct hci_dev *hdev) * callback. */ if (hdev->wakeup) - set_bit(HCI_CONN_FLAG_REMOTE_WAKEUP, hdev->conn_flags); + hdev->conn_flags |= HCI_CONN_FLAG_REMOTE_WAKEUP; hci_sock_dev_event(hdev, HCI_DEV_REG); hci_dev_hold(hdev); diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index 635cc5fb451e..38ecaf9264ee 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -482,7 +482,7 @@ static int add_to_accept_list(struct hci_request *req, /* During suspend, only wakeable devices can be in accept list */ if (hdev->suspended && - !test_bit(HCI_CONN_FLAG_REMOTE_WAKEUP, params->flags)) + !(params->flags & HCI_CONN_FLAG_REMOTE_WAKEUP)) return 0; *num_entries += 1; diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 4d2203c5f1bb..286d6767f017 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -1637,7 +1637,7 @@ static int hci_le_set_privacy_mode_sync(struct hci_dev *hdev, * indicates that LL Privacy has been enabled and * HCI_OP_LE_SET_PRIVACY_MODE is supported. */ - if (!test_bit(HCI_CONN_FLAG_DEVICE_PRIVACY, params->flags)) + if (!(params->flags & HCI_CONN_FLAG_DEVICE_PRIVACY)) return 0; irk = hci_find_irk_by_addr(hdev, ¶ms->addr, params->addr_type); @@ -1666,7 +1666,7 @@ static int hci_le_add_accept_list_sync(struct hci_dev *hdev, /* During suspend, only wakeable devices can be in acceptlist */ if (hdev->suspended && - !test_bit(HCI_CONN_FLAG_REMOTE_WAKEUP, params->flags)) + !(params->flags & HCI_CONN_FLAG_REMOTE_WAKEUP)) return 0; /* Select filter policy to accept all advertising */ @@ -4888,7 +4888,7 @@ static int hci_update_event_filter_sync(struct hci_dev *hdev) hci_clear_event_filter_sync(hdev); list_for_each_entry(b, &hdev->accept_list, list) { - if (!test_bit(HCI_CONN_FLAG_REMOTE_WAKEUP, b->flags)) + if (!(b->flags & HCI_CONN_FLAG_REMOTE_WAKEUP)) continue; bt_dev_dbg(hdev, "Adding event filters for %pMR", &b->bdaddr); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 74937a834648..ae758ab1b558 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -4013,10 +4013,11 @@ static int exp_ll_privacy_feature_changed(bool enabled, struct hci_dev *hdev, memcpy(ev.uuid, rpa_resolution_uuid, 16); ev.flags = cpu_to_le32((enabled ? BIT(0) : 0) | BIT(1)); + // Do we need to be atomic with the conn_flags? if (enabled && privacy_mode_capable(hdev)) - set_bit(HCI_CONN_FLAG_DEVICE_PRIVACY, hdev->conn_flags); + hdev->conn_flags |= HCI_CONN_FLAG_DEVICE_PRIVACY; else - clear_bit(HCI_CONN_FLAG_DEVICE_PRIVACY, hdev->conn_flags); + hdev->conn_flags &= ~HCI_CONN_FLAG_DEVICE_PRIVACY; return mgmt_limited_event(MGMT_EV_EXP_FEATURE_CHANGED, hdev, &ev, sizeof(ev), @@ -4435,8 +4436,7 @@ static int get_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, hci_dev_lock(hdev); - bitmap_to_arr32(&supported_flags, hdev->conn_flags, - __HCI_CONN_NUM_FLAGS); + supported_flags = hdev->conn_flags; memset(&rp, 0, sizeof(rp)); @@ -4447,8 +4447,7 @@ static int get_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, if (!br_params) goto done; - bitmap_to_arr32(¤t_flags, br_params->flags, - __HCI_CONN_NUM_FLAGS); + current_flags = br_params->flags; } else { params = hci_conn_params_lookup(hdev, &cp->addr.bdaddr, le_addr_type(cp->addr.type)); @@ -4456,8 +4455,7 @@ static int get_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, if (!params) goto done; - bitmap_to_arr32(¤t_flags, params->flags, - __HCI_CONN_NUM_FLAGS); + current_flags = params->flags; } bacpy(&rp.addr.bdaddr, &cp->addr.bdaddr); @@ -4502,8 +4500,8 @@ static int set_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, &cp->addr.bdaddr, cp->addr.type, __le32_to_cpu(current_flags)); - bitmap_to_arr32(&supported_flags, hdev->conn_flags, - __HCI_CONN_NUM_FLAGS); + // We should take hci_dev_lock() early, I think.. conn_flags can change + supported_flags = hdev->conn_flags; if ((supported_flags | current_flags) != supported_flags) { bt_dev_warn(hdev, "Bad flag given (0x%x) vs supported (0x%0x)", @@ -4519,7 +4517,7 @@ static int set_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, cp->addr.type); if (br_params) { - bitmap_from_u64(br_params->flags, current_flags); + br_params->flags = current_flags; status = MGMT_STATUS_SUCCESS; } else { bt_dev_warn(hdev, "No such BR/EDR device %pMR (0x%x)", @@ -4529,15 +4527,11 @@ static int set_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, params = hci_conn_params_lookup(hdev, &cp->addr.bdaddr, le_addr_type(cp->addr.type)); if (params) { - DECLARE_BITMAP(flags, __HCI_CONN_NUM_FLAGS); - - bitmap_from_u64(flags, current_flags); - /* Devices using RPAs can only be programmed in the * acceptlist LL Privacy has been enable otherwise they * cannot mark HCI_CONN_FLAG_REMOTE_WAKEUP. */ - if (test_bit(HCI_CONN_FLAG_REMOTE_WAKEUP, flags) && + if ((current_flags & HCI_CONN_FLAG_REMOTE_WAKEUP) && !use_ll_privacy(hdev) && hci_find_irk_by_addr(hdev, ¶ms->addr, params->addr_type)) { @@ -4546,14 +4540,13 @@ static int set_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, goto unlock; } - bitmap_from_u64(params->flags, current_flags); + params->flags = current_flags; status = MGMT_STATUS_SUCCESS; /* Update passive scan if HCI_CONN_FLAG_DEVICE_PRIVACY * has been set. */ - if (test_bit(HCI_CONN_FLAG_DEVICE_PRIVACY, - params->flags)) + if (params->flags & HCI_CONN_FLAG_DEVICE_PRIVACY) hci_update_passive_scan(hdev); } else { bt_dev_warn(hdev, "No such LE device %pMR (0x%x)", @@ -7154,8 +7147,7 @@ static int add_device(struct sock *sk, struct hci_dev *hdev, params = hci_conn_params_lookup(hdev, &cp->addr.bdaddr, addr_type); if (params) - bitmap_to_arr32(¤t_flags, params->flags, - __HCI_CONN_NUM_FLAGS); + current_flags = params->flags; } err = hci_cmd_sync_queue(hdev, add_device_sync, NULL, NULL); @@ -7164,8 +7156,7 @@ static int add_device(struct sock *sk, struct hci_dev *hdev, added: device_added(sk, hdev, &cp->addr.bdaddr, cp->addr.type, cp->action); - bitmap_to_arr32(&supported_flags, hdev->conn_flags, - __HCI_CONN_NUM_FLAGS); + supported_flags = hdev->conn_flags; device_flags_changed(NULL, hdev, &cp->addr.bdaddr, cp->addr.type, supported_flags, current_flags); From f2906aa863381afb0015a9eb7fefad885d4e5a56 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 5 Jun 2022 17:18:54 -0700 Subject: [PATCH 49/49] Linux 5.19-rc1 --- Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Makefile b/Makefile index 7011d43dff35..c43d825a3c4c 100644 --- a/Makefile +++ b/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 -PATCHLEVEL = 18 +PATCHLEVEL = 19 SUBLEVEL = 0 -EXTRAVERSION = +EXTRAVERSION = -rc1 NAME = Superb Owl # *DOCUMENTATION*