From 7629254054820bead6e18f8c3ae65c2bb01a5ae2 Mon Sep 17 00:00:00 2001 From: Raag Jadav Date: Thu, 5 Aug 2021 00:54:46 +0530 Subject: [PATCH 001/587] dt-bindings: at24: add ON Semi CAT24C04 and CAT24C05 Add bindings for ON Semi CAT24C04 and CAT24C05 eeproms, which are compatible with Atmel AT24C04. Signed-off-by: Raag Jadav Signed-off-by: Bartosz Golaszewski --- Documentation/devicetree/bindings/eeprom/at24.yaml | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/Documentation/devicetree/bindings/eeprom/at24.yaml b/Documentation/devicetree/bindings/eeprom/at24.yaml index 914a423ec449..4c5396a9744f 100644 --- a/Documentation/devicetree/bindings/eeprom/at24.yaml +++ b/Documentation/devicetree/bindings/eeprom/at24.yaml @@ -97,6 +97,12 @@ properties: - items: - const: nxp,se97b - const: atmel,24c02 + - items: + - const: onnn,cat24c04 + - const: atmel,24c04 + - items: + - const: onnn,cat24c05 + - const: atmel,24c04 - items: - const: renesas,r1ex24002 - const: atmel,24c02 From 3ea046564039b7f20b3974adbea9271af64a4295 Mon Sep 17 00:00:00 2001 From: Johan Jonker Date: Sat, 28 Aug 2021 14:10:07 +0200 Subject: [PATCH 002/587] dt-bindings: gpio: add gpio-line-names to rockchip,gpio-bank.yaml Some people and companies may want to add more description to there gpio pins. Add a gpio-line-names property to the rockchip,gpio-bank.yaml file to reduce the notifications from the existing mainline DT. Signed-off-by: Johan Jonker Acked-by: Rob Herring Signed-off-by: Bartosz Golaszewski --- Documentation/devicetree/bindings/gpio/rockchip,gpio-bank.yaml | 2 ++ 1 file changed, 2 insertions(+) diff --git a/Documentation/devicetree/bindings/gpio/rockchip,gpio-bank.yaml b/Documentation/devicetree/bindings/gpio/rockchip,gpio-bank.yaml index 0d62c28fb58d..d4e42c2b995b 100644 --- a/Documentation/devicetree/bindings/gpio/rockchip,gpio-bank.yaml +++ b/Documentation/devicetree/bindings/gpio/rockchip,gpio-bank.yaml @@ -29,6 +29,8 @@ properties: gpio-controller: true + gpio-line-names: true + "#gpio-cells": const: 2 From c119e7d00c916881913011e6f4c6ac349a41e4e2 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Mon, 23 Aug 2021 23:41:40 +0200 Subject: [PATCH 003/587] i2c: xiic: Fix broken locking on tx_msg The tx_msg is set from multiple places, sometimes without locking, which fall apart on any SMP system. Only ever access tx_msg inside the driver mutex. Signed-off-by: Marek Vasut Acked-by: Michal Simek Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-xiic.c | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) diff --git a/drivers/i2c/busses/i2c-xiic.c b/drivers/i2c/busses/i2c-xiic.c index bb93db98404e..50320dd32eea 100644 --- a/drivers/i2c/busses/i2c-xiic.c +++ b/drivers/i2c/busses/i2c-xiic.c @@ -170,7 +170,7 @@ struct xiic_i2c { #define xiic_tx_space(i2c) ((i2c)->tx_msg->len - (i2c)->tx_pos) #define xiic_rx_space(i2c) ((i2c)->rx_msg->len - (i2c)->rx_pos) -static int xiic_start_xfer(struct xiic_i2c *i2c); +static int xiic_start_xfer(struct xiic_i2c *i2c, struct i2c_msg *msgs, int num); static void __xiic_start_xfer(struct xiic_i2c *i2c); /* @@ -684,15 +684,25 @@ static void __xiic_start_xfer(struct xiic_i2c *i2c) } -static int xiic_start_xfer(struct xiic_i2c *i2c) +static int xiic_start_xfer(struct xiic_i2c *i2c, struct i2c_msg *msgs, int num) { int ret; + mutex_lock(&i2c->lock); + ret = xiic_busy(i2c); + if (ret) + goto out; + + i2c->tx_msg = msgs; + i2c->rx_msg = NULL; + i2c->nmsgs = num; + ret = xiic_reinit(i2c); if (!ret) __xiic_start_xfer(i2c); +out: mutex_unlock(&i2c->lock); return ret; @@ -710,14 +720,7 @@ static int xiic_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) if (err < 0) return err; - err = xiic_busy(i2c); - if (err) - goto out; - - i2c->tx_msg = msgs; - i2c->nmsgs = num; - - err = xiic_start_xfer(i2c); + err = xiic_start_xfer(i2c, msgs, num); if (err < 0) { dev_err(adap->dev.parent, "Error xiic_start_xfer\n"); goto out; @@ -725,9 +728,11 @@ static int xiic_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) if (wait_event_timeout(i2c->wait, (i2c->state == STATE_ERROR) || (i2c->state == STATE_DONE), HZ)) { + mutex_lock(&i2c->lock); err = (i2c->state == STATE_DONE) ? num : -EIO; goto out; } else { + mutex_lock(&i2c->lock); i2c->tx_msg = NULL; i2c->rx_msg = NULL; i2c->nmsgs = 0; @@ -735,6 +740,7 @@ static int xiic_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) goto out; } out: + mutex_unlock(&i2c->lock); pm_runtime_mark_last_busy(i2c->dev); pm_runtime_put_autosuspend(i2c->dev); return err; From 861dcffe1b9e986d254ea0d7e9f0a542bfc5ab11 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Mon, 23 Aug 2021 23:41:41 +0200 Subject: [PATCH 004/587] i2c: xiic: Drop broken interrupt handler The interrupt handler is missing locking when reading out registers and is racing with other threads which might access the driver. Drop it altogether, so that the threaded interrupt is always executed, as that one is already serialized by the driver mutex. This also allows dropping local_irq_save()/local_irq_restore() in xiic_start_recv(). Signed-off-by: Marek Vasut Acked-by: Michal Simek Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-xiic.c | 25 +------------------------ 1 file changed, 1 insertion(+), 24 deletions(-) diff --git a/drivers/i2c/busses/i2c-xiic.c b/drivers/i2c/busses/i2c-xiic.c index 50320dd32eea..b13166e94d89 100644 --- a/drivers/i2c/busses/i2c-xiic.c +++ b/drivers/i2c/busses/i2c-xiic.c @@ -554,7 +554,6 @@ static void xiic_start_recv(struct xiic_i2c *i2c) { u8 rx_watermark; struct i2c_msg *msg = i2c->rx_msg = i2c->tx_msg; - unsigned long flags; /* Clear and enable Rx full interrupt. */ xiic_irq_clr_en(i2c, XIIC_INTR_RX_FULL_MASK | XIIC_INTR_TX_ERROR_MASK); @@ -570,7 +569,6 @@ static void xiic_start_recv(struct xiic_i2c *i2c) rx_watermark = IIC_RX_FIFO_DEPTH; xiic_setreg8(i2c, XIIC_RFD_REG_OFFSET, rx_watermark - 1); - local_irq_save(flags); if (!(msg->flags & I2C_M_NOSTART)) /* write the address */ xiic_setreg16(i2c, XIIC_DTR_REG_OFFSET, @@ -580,7 +578,6 @@ static void xiic_start_recv(struct xiic_i2c *i2c) xiic_setreg16(i2c, XIIC_DTR_REG_OFFSET, msg->len | ((i2c->nmsgs == 1) ? XIIC_TX_DYN_STOP_MASK : 0)); - local_irq_restore(flags); if (i2c->nmsgs == 1) /* very last, enable bus not busy as well */ @@ -620,26 +617,6 @@ static void xiic_start_send(struct xiic_i2c *i2c) XIIC_INTR_BNB_MASK); } -static irqreturn_t xiic_isr(int irq, void *dev_id) -{ - struct xiic_i2c *i2c = dev_id; - u32 pend, isr, ier; - irqreturn_t ret = IRQ_NONE; - /* Do not processes a devices interrupts if the device has no - * interrupts pending - */ - - dev_dbg(i2c->adap.dev.parent, "%s entry\n", __func__); - - isr = xiic_getreg32(i2c, XIIC_IISR_OFFSET); - ier = xiic_getreg32(i2c, XIIC_IIER_OFFSET); - pend = isr & ier; - if (pend) - ret = IRQ_WAKE_THREAD; - - return ret; -} - static void __xiic_start_xfer(struct xiic_i2c *i2c) { int first = 1; @@ -818,7 +795,7 @@ static int xiic_i2c_probe(struct platform_device *pdev) pm_runtime_use_autosuspend(i2c->dev); pm_runtime_set_active(i2c->dev); pm_runtime_enable(i2c->dev); - ret = devm_request_threaded_irq(&pdev->dev, irq, xiic_isr, + ret = devm_request_threaded_irq(&pdev->dev, irq, NULL, xiic_process, IRQF_ONESHOT, pdev->name, i2c); From 743e227a895923c37a333eb2ebf3e391f00c406d Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Mon, 23 Aug 2021 23:41:42 +0200 Subject: [PATCH 005/587] i2c: xiic: Defer xiic_wakeup() and __xiic_start_xfer() in xiic_process() The __xiic_start_xfer() manipulates the interrupt flags, xiic_wakeup() may result in return from xiic_xfer() early. Defer both to the end of the xiic_process() interrupt thread, so that they are executed after all the other interrupt bits handling completed and once it completely safe to perform changes to the interrupt bits in the hardware. Signed-off-by: Marek Vasut Acked-by: Michal Simek Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-xiic.c | 37 ++++++++++++++++++++++++----------- 1 file changed, 26 insertions(+), 11 deletions(-) diff --git a/drivers/i2c/busses/i2c-xiic.c b/drivers/i2c/busses/i2c-xiic.c index b13166e94d89..aecdeec57997 100644 --- a/drivers/i2c/busses/i2c-xiic.c +++ b/drivers/i2c/busses/i2c-xiic.c @@ -375,6 +375,9 @@ static irqreturn_t xiic_process(int irq, void *dev_id) struct xiic_i2c *i2c = dev_id; u32 pend, isr, ier; u32 clr = 0; + int xfer_more = 0; + int wakeup_req = 0; + int wakeup_code = 0; /* Get the interrupt Status from the IPIF. There is no clearing of * interrupts in the IPIF. Interrupts must be cleared at the source. @@ -411,10 +414,14 @@ static irqreturn_t xiic_process(int irq, void *dev_id) */ xiic_reinit(i2c); - if (i2c->rx_msg) - xiic_wakeup(i2c, STATE_ERROR); - if (i2c->tx_msg) - xiic_wakeup(i2c, STATE_ERROR); + if (i2c->rx_msg) { + wakeup_req = 1; + wakeup_code = STATE_ERROR; + } + if (i2c->tx_msg) { + wakeup_req = 1; + wakeup_code = STATE_ERROR; + } } if (pend & XIIC_INTR_RX_FULL_MASK) { /* Receive register/FIFO is full */ @@ -448,8 +455,7 @@ static irqreturn_t xiic_process(int irq, void *dev_id) i2c->tx_msg++; dev_dbg(i2c->adap.dev.parent, "%s will start next...\n", __func__); - - __xiic_start_xfer(i2c); + xfer_more = 1; } } } @@ -463,11 +469,13 @@ static irqreturn_t xiic_process(int irq, void *dev_id) if (!i2c->tx_msg) goto out; - if ((i2c->nmsgs == 1) && !i2c->rx_msg && - xiic_tx_space(i2c) == 0) - xiic_wakeup(i2c, STATE_DONE); + wakeup_req = 1; + + if (i2c->nmsgs == 1 && !i2c->rx_msg && + xiic_tx_space(i2c) == 0) + wakeup_code = STATE_DONE; else - xiic_wakeup(i2c, STATE_ERROR); + wakeup_code = STATE_ERROR; } if (pend & (XIIC_INTR_TX_EMPTY_MASK | XIIC_INTR_TX_HALF_MASK)) { /* Transmit register/FIFO is empty or ½ empty */ @@ -491,7 +499,7 @@ static irqreturn_t xiic_process(int irq, void *dev_id) if (i2c->nmsgs > 1) { i2c->nmsgs--; i2c->tx_msg++; - __xiic_start_xfer(i2c); + xfer_more = 1; } else { xiic_irq_dis(i2c, XIIC_INTR_TX_HALF_MASK); @@ -509,6 +517,13 @@ out: dev_dbg(i2c->adap.dev.parent, "%s clr: 0x%x\n", __func__, clr); xiic_setreg32(i2c, XIIC_IISR_OFFSET, clr); + if (xfer_more) + __xiic_start_xfer(i2c); + if (wakeup_req) + xiic_wakeup(i2c, wakeup_code); + + WARN_ON(xfer_more && wakeup_req); + mutex_unlock(&i2c->lock); return IRQ_HANDLED; } From fdacc3c7405d1fc33c1f2771699a4fc24551e480 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Mon, 23 Aug 2021 23:41:43 +0200 Subject: [PATCH 006/587] i2c: xiic: Switch from waitqueue to completion There will never be threads queueing up in the xiic_xmit(), use completion synchronization primitive to wait for the interrupt handler thread to complete instead as it is much better fit and there is no need to overload it for this purpose. Signed-off-by: Marek Vasut Acked-by: Michal Simek Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-xiic.c | 33 ++++++++++++++++++--------------- 1 file changed, 18 insertions(+), 15 deletions(-) diff --git a/drivers/i2c/busses/i2c-xiic.c b/drivers/i2c/busses/i2c-xiic.c index aecdeec57997..f7277629923f 100644 --- a/drivers/i2c/busses/i2c-xiic.c +++ b/drivers/i2c/busses/i2c-xiic.c @@ -23,7 +23,7 @@ #include #include #include -#include +#include #include #include #include @@ -48,7 +48,7 @@ enum xiic_endian { * struct xiic_i2c - Internal representation of the XIIC I2C bus * @dev: Pointer to device structure * @base: Memory base of the HW registers - * @wait: Wait queue for callers + * @completion: Completion for callers * @adap: Kernel adapter representation * @tx_msg: Messages from above to be sent * @lock: Mutual exclusion @@ -64,7 +64,7 @@ enum xiic_endian { struct xiic_i2c { struct device *dev; void __iomem *base; - wait_queue_head_t wait; + struct completion completion; struct i2c_adapter adap; struct i2c_msg *tx_msg; struct mutex lock; @@ -160,6 +160,9 @@ struct xiic_i2c { #define XIIC_PM_TIMEOUT 1000 /* ms */ /* timeout waiting for the controller to respond */ #define XIIC_I2C_TIMEOUT (msecs_to_jiffies(1000)) +/* timeout waiting for the controller finish transfers */ +#define XIIC_XFER_TIMEOUT (msecs_to_jiffies(10000)) + /* * The following constant is used for the device global interrupt enable * register, to enable all interrupts for the device, this is the only bit @@ -367,7 +370,7 @@ static void xiic_wakeup(struct xiic_i2c *i2c, int code) i2c->rx_msg = NULL; i2c->nmsgs = 0; i2c->state = code; - wake_up(&i2c->wait); + complete(&i2c->completion); } static irqreturn_t xiic_process(int irq, void *dev_id) @@ -689,6 +692,7 @@ static int xiic_start_xfer(struct xiic_i2c *i2c, struct i2c_msg *msgs, int num) i2c->tx_msg = msgs; i2c->rx_msg = NULL; i2c->nmsgs = num; + init_completion(&i2c->completion); ret = xiic_reinit(i2c); if (!ret) @@ -715,23 +719,23 @@ static int xiic_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) err = xiic_start_xfer(i2c, msgs, num); if (err < 0) { dev_err(adap->dev.parent, "Error xiic_start_xfer\n"); - goto out; + return err; } - if (wait_event_timeout(i2c->wait, (i2c->state == STATE_ERROR) || - (i2c->state == STATE_DONE), HZ)) { - mutex_lock(&i2c->lock); - err = (i2c->state == STATE_DONE) ? num : -EIO; - goto out; - } else { - mutex_lock(&i2c->lock); + err = wait_for_completion_timeout(&i2c->completion, XIIC_XFER_TIMEOUT); + mutex_lock(&i2c->lock); + if (err == 0) { /* Timeout */ i2c->tx_msg = NULL; i2c->rx_msg = NULL; i2c->nmsgs = 0; err = -ETIMEDOUT; - goto out; + } else if (err < 0) { /* Completion error */ + i2c->tx_msg = NULL; + i2c->rx_msg = NULL; + i2c->nmsgs = 0; + } else { + err = (i2c->state == STATE_DONE) ? num : -EIO; } -out: mutex_unlock(&i2c->lock); pm_runtime_mark_last_busy(i2c->dev); pm_runtime_put_autosuspend(i2c->dev); @@ -793,7 +797,6 @@ static int xiic_i2c_probe(struct platform_device *pdev) i2c->adap.dev.of_node = pdev->dev.of_node; mutex_init(&i2c->lock); - init_waitqueue_head(&i2c->wait); i2c->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(i2c->clk)) From d12e4bbb190b9edb47b31511e624f2a90f35f443 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Mon, 23 Aug 2021 23:41:44 +0200 Subject: [PATCH 007/587] i2c: xiic: Only ever transfer single message Transferring multiple messages via XIIC suffers from strange interaction between the interrupt status/enable register flags. These flags are being reused in the hardware to indicate different things for read and write transfer, and doing multiple transactions becomes horribly complex. Just send a single transaction and reload the controller with another message once the transaction is done in the interrupt handler thread. Signed-off-by: Marek Vasut Acked-by: Michal Simek Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-xiic.c | 44 ++++++++--------------------------- 1 file changed, 10 insertions(+), 34 deletions(-) diff --git a/drivers/i2c/busses/i2c-xiic.c b/drivers/i2c/busses/i2c-xiic.c index f7277629923f..6cd7830fe489 100644 --- a/drivers/i2c/busses/i2c-xiic.c +++ b/drivers/i2c/busses/i2c-xiic.c @@ -609,8 +609,6 @@ static void xiic_start_send(struct xiic_i2c *i2c) { struct i2c_msg *msg = i2c->tx_msg; - xiic_irq_clr(i2c, XIIC_INTR_TX_ERROR_MASK); - dev_dbg(i2c->adap.dev.parent, "%s entry, msg: %p, len: %d", __func__, msg, msg->len); dev_dbg(i2c->adap.dev.parent, "%s entry, ISR: 0x%x, CR: 0x%x\n", @@ -628,16 +626,17 @@ static void xiic_start_send(struct xiic_i2c *i2c) xiic_setreg16(i2c, XIIC_DTR_REG_OFFSET, data); } - xiic_fill_tx_fifo(i2c); - /* Clear any pending Tx empty, Tx Error and then enable them. */ xiic_irq_clr_en(i2c, XIIC_INTR_TX_EMPTY_MASK | XIIC_INTR_TX_ERROR_MASK | - XIIC_INTR_BNB_MASK); + XIIC_INTR_BNB_MASK | + ((i2c->nmsgs > 1 || xiic_tx_space(i2c)) ? + XIIC_INTR_TX_HALF_MASK : 0)); + + xiic_fill_tx_fifo(i2c); } static void __xiic_start_xfer(struct xiic_i2c *i2c) { - int first = 1; int fifo_space = xiic_tx_fifo_space(i2c); dev_dbg(i2c->adap.dev.parent, "%s entry, msg: %p, fifos space: %d\n", __func__, i2c->tx_msg, fifo_space); @@ -648,35 +647,12 @@ static void __xiic_start_xfer(struct xiic_i2c *i2c) i2c->rx_pos = 0; i2c->tx_pos = 0; i2c->state = STATE_START; - while ((fifo_space >= 2) && (first || (i2c->nmsgs > 1))) { - if (!first) { - i2c->nmsgs--; - i2c->tx_msg++; - i2c->tx_pos = 0; - } else - first = 0; - - if (i2c->tx_msg->flags & I2C_M_RD) { - /* we dont date putting several reads in the FIFO */ - xiic_start_recv(i2c); - return; - } else { - xiic_start_send(i2c); - if (xiic_tx_space(i2c) != 0) { - /* the message could not be completely sent */ - break; - } - } - - fifo_space = xiic_tx_fifo_space(i2c); + if (i2c->tx_msg->flags & I2C_M_RD) { + /* we dont date putting several reads in the FIFO */ + xiic_start_recv(i2c); + } else { + xiic_start_send(i2c); } - - /* there are more messages or the current one could not be completely - * put into the FIFO, also enable the half empty interrupt - */ - if (i2c->nmsgs > 1 || xiic_tx_space(i2c)) - xiic_irq_clr_en(i2c, XIIC_INTR_TX_HALF_MASK); - } static int xiic_start_xfer(struct xiic_i2c *i2c, struct i2c_msg *msgs, int num) From 294b29f15469e90893c2b72a738a962ee02a12eb Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Mon, 23 Aug 2021 23:41:45 +0200 Subject: [PATCH 008/587] i2c: xiic: Fix RX IRQ busy check In case the XIIC does TX/RX transfer, make sure no other kernel thread can start another TX transfer at the same time. This could happen since the driver only checks tx_msg for being non-NULL and returns -EBUSY in that case, however it is necessary to check also rx_msg for the same. Signed-off-by: Marek Vasut Acked-by: Michal Simek Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-xiic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-xiic.c b/drivers/i2c/busses/i2c-xiic.c index 6cd7830fe489..eb789cfb9973 100644 --- a/drivers/i2c/busses/i2c-xiic.c +++ b/drivers/i2c/busses/i2c-xiic.c @@ -543,7 +543,7 @@ static int xiic_busy(struct xiic_i2c *i2c) int tries = 3; int err; - if (i2c->tx_msg) + if (i2c->tx_msg || i2c->rx_msg) return -EBUSY; /* In single master mode bus can only be busy, when in use by this From a2aec2c86ef0cad0fd6be718cfeb5cf5eefbfca9 Mon Sep 17 00:00:00 2001 From: "GONG, Ruiqi" Date: Mon, 30 Aug 2021 16:33:56 +0800 Subject: [PATCH 009/587] mtd: Remove obsolete macros only used by the old nand_ecclayout struct All uses of MTD_MAX_{OOBFREE,ECCPOS}_ENTRIES_LARGE have been removed as commit ef5eeea6e911 ("mtd: nand: brcm: switch to mtd_ooblayout_ops") and commit aab616e31d1c ("mtd: kill the nand_ecclayout struct") replaced struct nand_ecclayout by the new mtd_ooblayout_ops interface. Remove these two macros therefore. Reported-by: Yi Yang Signed-off-by: GONG, Ruiqi Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210830083356.31702-1-gongruiqi1@huawei.com --- include/linux/mtd/mtd.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 88227044fc86..f5e7dfc2e4e9 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -72,8 +72,6 @@ struct mtd_oob_ops { uint8_t *oobbuf; }; -#define MTD_MAX_OOBFREE_ENTRIES_LARGE 32 -#define MTD_MAX_ECCPOS_ENTRIES_LARGE 640 /** * struct mtd_oob_region - oob region definition * @offset: region offset From c606d4f77c8a637c0563a206b080c5663f72b61a Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Wed, 1 Sep 2021 15:40:30 +0800 Subject: [PATCH 010/587] mtd: rawnand: atmel: Make use of the helper function devm_platform_ioremap_resource() Use the devm_platform_ioremap_resource() helper instead of calling platform_get_resource() and devm_ioremap_resource() separately Signed-off-by: Cai Huoqing Reviewed-by: Nicolas Ferre Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210901074031.8883-1-caihuoqing@baidu.com --- drivers/mtd/nand/raw/atmel/pmecc.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/mtd/nand/raw/atmel/pmecc.c b/drivers/mtd/nand/raw/atmel/pmecc.c index cbb023bf00f7..498e41ccabbd 100644 --- a/drivers/mtd/nand/raw/atmel/pmecc.c +++ b/drivers/mtd/nand/raw/atmel/pmecc.c @@ -834,7 +834,6 @@ static struct atmel_pmecc *atmel_pmecc_create(struct platform_device *pdev, { struct device *dev = &pdev->dev; struct atmel_pmecc *pmecc; - struct resource *res; pmecc = devm_kzalloc(dev, sizeof(*pmecc), GFP_KERNEL); if (!pmecc) @@ -844,13 +843,11 @@ static struct atmel_pmecc *atmel_pmecc_create(struct platform_device *pdev, pmecc->dev = dev; mutex_init(&pmecc->lock); - res = platform_get_resource(pdev, IORESOURCE_MEM, pmecc_res_idx); - pmecc->regs.base = devm_ioremap_resource(dev, res); + pmecc->regs.base = devm_platform_ioremap_resource(pdev, pmecc_res_idx); if (IS_ERR(pmecc->regs.base)) return ERR_CAST(pmecc->regs.base); - res = platform_get_resource(pdev, IORESOURCE_MEM, errloc_res_idx); - pmecc->regs.errloc = devm_ioremap_resource(dev, res); + pmecc->regs.errloc = devm_platform_ioremap_resource(pdev, errloc_res_idx); if (IS_ERR(pmecc->regs.errloc)) return ERR_CAST(pmecc->regs.errloc); From df9e5170bc4d2d96a0c5dcfd3960c3e248a37218 Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Wed, 1 Sep 2021 15:40:38 +0800 Subject: [PATCH 011/587] mtd: rawnand: bcm6368: Make use of the helper function devm_platform_ioremap_resource_byname() Use the devm_platform_ioremap_resource_byname() helper instead of calling platform_get_resource_byname() and devm_ioremap_resource() separately Signed-off-by: Cai Huoqing Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210901074108.8933-1-caihuoqing@baidu.com --- drivers/mtd/nand/raw/brcmnand/bcm6368_nand.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/mtd/nand/raw/brcmnand/bcm6368_nand.c b/drivers/mtd/nand/raw/brcmnand/bcm6368_nand.c index 7c17ec4ce8b6..a06cd87f839a 100644 --- a/drivers/mtd/nand/raw/brcmnand/bcm6368_nand.c +++ b/drivers/mtd/nand/raw/brcmnand/bcm6368_nand.c @@ -88,16 +88,13 @@ static int bcm6368_nand_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct bcm6368_nand_soc *priv; struct brcmnand_soc *soc; - struct resource *res; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; soc = &priv->soc; - res = platform_get_resource_byname(pdev, - IORESOURCE_MEM, "nand-int-base"); - priv->base = devm_ioremap_resource(dev, res); + priv->base = devm_platform_ioremap_resource_byname(pdev, "nand-int-base"); if (IS_ERR(priv->base)) return PTR_ERR(priv->base); From 5f14a8ca1b493a3c633ff549fb7d494887d7804a Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Wed, 1 Sep 2021 15:41:15 +0800 Subject: [PATCH 012/587] mtd: rawnand: denali: Make use of the helper function devm_platform_ioremap_resource_byname() Use the devm_platform_ioremap_resource_byname() helper instead of calling platform_get_resource_byname() and devm_ioremap_resource() separately Signed-off-by: Cai Huoqing Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210901074116.8983-1-caihuoqing@baidu.com --- drivers/mtd/nand/raw/denali_dt.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/mtd/nand/raw/denali_dt.c b/drivers/mtd/nand/raw/denali_dt.c index f08740ae282b..8513bb9fcfcc 100644 --- a/drivers/mtd/nand/raw/denali_dt.c +++ b/drivers/mtd/nand/raw/denali_dt.c @@ -113,7 +113,6 @@ static int denali_dt_chip_init(struct denali_controller *denali, static int denali_dt_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct resource *res; struct denali_dt *dt; const struct denali_dt_data *data; struct denali_controller *denali; @@ -139,13 +138,11 @@ static int denali_dt_probe(struct platform_device *pdev) if (denali->irq < 0) return denali->irq; - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "denali_reg"); - denali->reg = devm_ioremap_resource(dev, res); + denali->reg = devm_platform_ioremap_resource_byname(pdev, "denali_reg"); if (IS_ERR(denali->reg)) return PTR_ERR(denali->reg); - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nand_data"); - denali->host = devm_ioremap_resource(dev, res); + denali->host = devm_platform_ioremap_resource_byname(pdev, "nand_data"); if (IS_ERR(denali->host)) return PTR_ERR(denali->host); From 557de1cfabd6ea5476e5364a00d23d26bdfa3d4d Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Wed, 1 Sep 2021 15:41:22 +0800 Subject: [PATCH 013/587] mtd: rawnand: gpio: Make use of the helper function devm_platform_ioremap_resource() Use the devm_platform_ioremap_resource() helper instead of calling platform_get_resource() and devm_ioremap_resource() separately Signed-off-by: Cai Huoqing Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210901074123.9033-1-caihuoqing@baidu.com --- drivers/mtd/nand/raw/gpio.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/mtd/nand/raw/gpio.c b/drivers/mtd/nand/raw/gpio.c index fb7a086de35e..8901c4aa0c21 100644 --- a/drivers/mtd/nand/raw/gpio.c +++ b/drivers/mtd/nand/raw/gpio.c @@ -303,8 +303,7 @@ static int gpio_nand_probe(struct platform_device *pdev) chip = &gpiomtd->nand_chip; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - gpiomtd->io = devm_ioremap_resource(dev, res); + gpiomtd->io = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(gpiomtd->io)) return PTR_ERR(gpiomtd->io); From fe6b7a9f9159a3a55f5227e03c97f65b4d81dc71 Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Wed, 1 Sep 2021 15:41:30 +0800 Subject: [PATCH 014/587] mtd: rawnand: gpmi: Make use of the helper function devm_platform_ioremap_resource_byname() Use the devm_platform_ioremap_resource_byname() helper instead of calling platform_get_resource_byname() and devm_ioremap_resource() separately Signed-off-by: Cai Huoqing Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210901074130.9083-1-caihuoqing@baidu.com --- drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c index 4d08e4ab5c1b..10cc71829dcb 100644 --- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c +++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c @@ -951,11 +951,9 @@ static int acquire_register_block(struct gpmi_nand_data *this, { struct platform_device *pdev = this->pdev; struct resources *res = &this->resources; - struct resource *r; void __iomem *p; - r = platform_get_resource_byname(pdev, IORESOURCE_MEM, res_name); - p = devm_ioremap_resource(&pdev->dev, r); + p = devm_platform_ioremap_resource_byname(pdev, res_name); if (IS_ERR(p)) return PTR_ERR(p); From 1cda2633999a9431bc00d7881e2ea96cff5da22f Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Wed, 1 Sep 2021 15:41:37 +0800 Subject: [PATCH 015/587] mtd: rawnand: hisi504: Make use of the helper function devm_platform_ioremap_resource() Use the devm_platform_ioremap_resource() helper instead of calling platform_get_resource() and devm_ioremap_resource() separately Signed-off-by: Cai Huoqing Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210901074138.9133-1-caihuoqing@baidu.com --- drivers/mtd/nand/raw/hisi504_nand.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/mtd/nand/raw/hisi504_nand.c b/drivers/mtd/nand/raw/hisi504_nand.c index 78c4e05434e2..c74f6b2192fc 100644 --- a/drivers/mtd/nand/raw/hisi504_nand.c +++ b/drivers/mtd/nand/raw/hisi504_nand.c @@ -738,7 +738,6 @@ static int hisi_nfc_probe(struct platform_device *pdev) struct hinfc_host *host; struct nand_chip *chip; struct mtd_info *mtd; - struct resource *res; struct device_node *np = dev->of_node; host = devm_kzalloc(dev, sizeof(*host), GFP_KERNEL); @@ -754,13 +753,11 @@ static int hisi_nfc_probe(struct platform_device *pdev) if (irq < 0) return -ENXIO; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - host->iobase = devm_ioremap_resource(dev, res); + host->iobase = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(host->iobase)) return PTR_ERR(host->iobase); - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - host->mmio = devm_ioremap_resource(dev, res); + host->mmio = devm_platform_ioremap_resource(pdev, 1); if (IS_ERR(host->mmio)) return PTR_ERR(host->mmio); From 5da7bb27a582b8f232c09dd1067eb7a254c4d4ee Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Wed, 1 Sep 2021 15:41:44 +0800 Subject: [PATCH 016/587] mtd: rawnand: mtk: Make use of the helper function devm_platform_ioremap_resource() Use the devm_platform_ioremap_resource() helper instead of calling platform_get_resource() and devm_ioremap_resource() separately Signed-off-by: Cai Huoqing Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210901074145.9183-1-caihuoqing@baidu.com --- drivers/mtd/nand/raw/mtk_nand.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/mtk_nand.c b/drivers/mtd/nand/raw/mtk_nand.c index 5c5c92132287..66f04c693c87 100644 --- a/drivers/mtd/nand/raw/mtk_nand.c +++ b/drivers/mtd/nand/raw/mtk_nand.c @@ -1520,7 +1520,6 @@ static int mtk_nfc_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct device_node *np = dev->of_node; struct mtk_nfc *nfc; - struct resource *res; int ret, irq; nfc = devm_kzalloc(dev, sizeof(*nfc), GFP_KERNEL); @@ -1541,8 +1540,7 @@ static int mtk_nfc_probe(struct platform_device *pdev) nfc->caps = of_device_get_match_data(dev); nfc->dev = dev; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - nfc->regs = devm_ioremap_resource(dev, res); + nfc->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(nfc->regs)) { ret = PTR_ERR(nfc->regs); goto release_ecc; From 8826e1107236d8668cfbcf8b31caea3ac943de1e Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Wed, 1 Sep 2021 15:41:52 +0800 Subject: [PATCH 017/587] mtd: rawnand: mtk_ecc: Make use of the helper function devm_platform_ioremap_resource() Use the devm_platform_ioremap_resource() helper instead of calling platform_get_resource() and devm_ioremap_resource() separately Signed-off-by: Cai Huoqing Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210901074153.9233-1-caihuoqing@baidu.com --- drivers/mtd/nand/raw/mtk_ecc.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/mtk_ecc.c b/drivers/mtd/nand/raw/mtk_ecc.c index c437d97debb8..1b47964cb6da 100644 --- a/drivers/mtd/nand/raw/mtk_ecc.c +++ b/drivers/mtd/nand/raw/mtk_ecc.c @@ -495,7 +495,6 @@ static int mtk_ecc_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct mtk_ecc *ecc; - struct resource *res; u32 max_eccdata_size; int irq, ret; @@ -513,8 +512,7 @@ static int mtk_ecc_probe(struct platform_device *pdev) if (!ecc->eccdata) return -ENOMEM; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ecc->regs = devm_ioremap_resource(dev, res); + ecc->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(ecc->regs)) return PTR_ERR(ecc->regs); From 7b7be21861819afcc0b82cd6f0fe5baef40374cd Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Wed, 1 Sep 2021 15:41:59 +0800 Subject: [PATCH 018/587] mtd: rawnand: omap_elm: Make use of the helper function devm_platform_ioremap_resource() Use the devm_platform_ioremap_resource() helper instead of calling platform_get_resource() and devm_ioremap_resource() separately Signed-off-by: Cai Huoqing Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210901074200.9283-1-caihuoqing@baidu.com --- drivers/mtd/nand/raw/omap_elm.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/omap_elm.c b/drivers/mtd/nand/raw/omap_elm.c index 2b21ce04b3ec..8bab753211e9 100644 --- a/drivers/mtd/nand/raw/omap_elm.c +++ b/drivers/mtd/nand/raw/omap_elm.c @@ -384,7 +384,7 @@ static irqreturn_t elm_isr(int this_irq, void *dev_id) static int elm_probe(struct platform_device *pdev) { int ret = 0; - struct resource *res, *irq; + struct resource *irq; struct elm_info *info; info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL); @@ -399,8 +399,7 @@ static int elm_probe(struct platform_device *pdev) return -ENODEV; } - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - info->elm_base = devm_ioremap_resource(&pdev->dev, res); + info->elm_base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(info->elm_base)) return PTR_ERR(info->elm_base); From f47dca43c51f6d1fa0cc1574badc748724d9286c Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Wed, 1 Sep 2021 15:42:07 +0800 Subject: [PATCH 019/587] mtd: rawnand: oxnas: Make use of the helper function devm_platform_ioremap_resource() Use the devm_platform_ioremap_resource() helper instead of calling platform_get_resource() and devm_ioremap_resource() separately Signed-off-by: Cai Huoqing Reviewed-by: Neil Armstrong Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210901074207.9333-1-caihuoqing@baidu.com --- drivers/mtd/nand/raw/oxnas_nand.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/oxnas_nand.c b/drivers/mtd/nand/raw/oxnas_nand.c index f44947043e5a..cd112d45e0b5 100644 --- a/drivers/mtd/nand/raw/oxnas_nand.c +++ b/drivers/mtd/nand/raw/oxnas_nand.c @@ -79,7 +79,6 @@ static int oxnas_nand_probe(struct platform_device *pdev) struct oxnas_nand_ctrl *oxnas; struct nand_chip *chip; struct mtd_info *mtd; - struct resource *res; int count = 0; int err = 0; int i; @@ -92,8 +91,7 @@ static int oxnas_nand_probe(struct platform_device *pdev) nand_controller_init(&oxnas->base); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - oxnas->io_base = devm_ioremap_resource(&pdev->dev, res); + oxnas->io_base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(oxnas->io_base)) return PTR_ERR(oxnas->io_base); From 7e2561430dff0a1bb9ab794e70fcaa56852e10f9 Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Wed, 1 Sep 2021 15:42:14 +0800 Subject: [PATCH 020/587] mtd: rawnand: plat_nand: Make use of the helper function devm_platform_ioremap_resource() Use the devm_platform_ioremap_resource() helper instead of calling platform_get_resource() and devm_ioremap_resource() separately Signed-off-by: Cai Huoqing Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210901074215.9383-1-caihuoqing@baidu.com --- drivers/mtd/nand/raw/plat_nand.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/plat_nand.c b/drivers/mtd/nand/raw/plat_nand.c index 7711e1020c21..c1b2072cb507 100644 --- a/drivers/mtd/nand/raw/plat_nand.c +++ b/drivers/mtd/nand/raw/plat_nand.c @@ -41,7 +41,6 @@ static int plat_nand_probe(struct platform_device *pdev) struct platform_nand_data *pdata = dev_get_platdata(&pdev->dev); struct plat_nand_data *data; struct mtd_info *mtd; - struct resource *res; const char **part_types; int err = 0; @@ -65,8 +64,7 @@ static int plat_nand_probe(struct platform_device *pdev) nand_controller_init(&data->controller); data->chip.controller = &data->controller; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - data->io_base = devm_ioremap_resource(&pdev->dev, res); + data->io_base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(data->io_base)) return PTR_ERR(data->io_base); From 8d77c55f090def05f450df8aa6ee16ec6f4d01ba Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Wed, 1 Sep 2021 15:42:22 +0800 Subject: [PATCH 021/587] mtd: rawnand: stm32_fmc2: Make use of the helper function devm_platform_ioremap_resource() Use the devm_platform_ioremap_resource() helper instead of calling platform_get_resource() and devm_ioremap_resource() separately Signed-off-by: Cai Huoqing Reviewed-by: Christophe Kerello Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210901074222.9433-1-caihuoqing@baidu.com --- drivers/mtd/nand/raw/stm32_fmc2_nand.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/mtd/nand/raw/stm32_fmc2_nand.c b/drivers/mtd/nand/raw/stm32_fmc2_nand.c index 1c277fbb91f2..97b4e02e43e4 100644 --- a/drivers/mtd/nand/raw/stm32_fmc2_nand.c +++ b/drivers/mtd/nand/raw/stm32_fmc2_nand.c @@ -1899,15 +1899,11 @@ static int stm32_fmc2_nfc_probe(struct platform_device *pdev) nfc->data_phys_addr[chip_cs] = res->start; - res = platform_get_resource(pdev, IORESOURCE_MEM, - mem_region + 1); - nfc->cmd_base[chip_cs] = devm_ioremap_resource(dev, res); + nfc->cmd_base[chip_cs] = devm_platform_ioremap_resource(pdev, mem_region + 1); if (IS_ERR(nfc->cmd_base[chip_cs])) return PTR_ERR(nfc->cmd_base[chip_cs]); - res = platform_get_resource(pdev, IORESOURCE_MEM, - mem_region + 2); - nfc->addr_base[chip_cs] = devm_ioremap_resource(dev, res); + nfc->addr_base[chip_cs] = devm_platform_ioremap_resource(pdev, mem_region + 2); if (IS_ERR(nfc->addr_base[chip_cs])) return PTR_ERR(nfc->addr_base[chip_cs]); } From 2f597bc45e47e245e30265de8494423c3a1a7900 Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Wed, 1 Sep 2021 15:42:29 +0800 Subject: [PATCH 022/587] mtd: rawnand: tegra: Make use of the helper function devm_platform_ioremap_resource() Use the devm_platform_ioremap_resource() helper instead of calling platform_get_resource() and devm_ioremap_resource() separately Signed-off-by: Cai Huoqing Acked-by: Stefan Agner Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210901074230.9483-1-caihuoqing@baidu.com --- drivers/mtd/nand/raw/tegra_nand.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/tegra_nand.c b/drivers/mtd/nand/raw/tegra_nand.c index fbf67722a049..32431bbe69b8 100644 --- a/drivers/mtd/nand/raw/tegra_nand.c +++ b/drivers/mtd/nand/raw/tegra_nand.c @@ -1144,7 +1144,6 @@ static int tegra_nand_probe(struct platform_device *pdev) { struct reset_control *rst; struct tegra_nand_controller *ctrl; - struct resource *res; int err = 0; ctrl = devm_kzalloc(&pdev->dev, sizeof(*ctrl), GFP_KERNEL); @@ -1155,8 +1154,7 @@ static int tegra_nand_probe(struct platform_device *pdev) nand_controller_init(&ctrl->controller); ctrl->controller.ops = &tegra_nand_controller_ops; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ctrl->regs = devm_ioremap_resource(&pdev->dev, res); + ctrl->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(ctrl->regs)) return PTR_ERR(ctrl->regs); From 524bd02a6ff8c25a88077747020c1d0a7a94594b Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Wed, 1 Sep 2021 15:42:37 +0800 Subject: [PATCH 023/587] mtd: rawnand: txx9ndfm: Make use of the helper function devm_platform_ioremap_resource() Use the devm_platform_ioremap_resource() helper instead of calling platform_get_resource() and devm_ioremap_resource() separately Signed-off-by: Cai Huoqing Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210901074237.9533-1-caihuoqing@baidu.com --- drivers/mtd/nand/raw/txx9ndfmc.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/txx9ndfmc.c b/drivers/mtd/nand/raw/txx9ndfmc.c index b8894ac27073..b42d61b30c0b 100644 --- a/drivers/mtd/nand/raw/txx9ndfmc.c +++ b/drivers/mtd/nand/raw/txx9ndfmc.c @@ -284,13 +284,11 @@ static int __init txx9ndfmc_probe(struct platform_device *dev) int i; struct txx9ndfmc_drvdata *drvdata; unsigned long gbusclk = plat->gbus_clock; - struct resource *res; drvdata = devm_kzalloc(&dev->dev, sizeof(*drvdata), GFP_KERNEL); if (!drvdata) return -ENOMEM; - res = platform_get_resource(dev, IORESOURCE_MEM, 0); - drvdata->base = devm_ioremap_resource(&dev->dev, res); + drvdata->base = devm_platform_ioremap_resource(dev, 0); if (IS_ERR(drvdata->base)) return PTR_ERR(drvdata->base); From 2d77b08eaf0b2f269512c200c441bb1cda59d978 Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Wed, 1 Sep 2021 15:42:44 +0800 Subject: [PATCH 024/587] mtd: rawnand: vf610: Make use of the helper function devm_platform_ioremap_resource() Use the devm_platform_ioremap_resource() helper instead of calling platform_get_resource() and devm_ioremap_resource() separately Signed-off-by: Cai Huoqing Acked-by: Stefan Agner Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210901074245.9583-1-caihuoqing@baidu.com --- drivers/mtd/nand/raw/vf610_nfc.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/vf610_nfc.c b/drivers/mtd/nand/raw/vf610_nfc.c index 40d70f991d89..a2b89b75073f 100644 --- a/drivers/mtd/nand/raw/vf610_nfc.c +++ b/drivers/mtd/nand/raw/vf610_nfc.c @@ -807,7 +807,6 @@ static const struct nand_controller_ops vf610_nfc_controller_ops = { static int vf610_nfc_probe(struct platform_device *pdev) { struct vf610_nfc *nfc; - struct resource *res; struct mtd_info *mtd; struct nand_chip *chip; struct device_node *child; @@ -831,8 +830,7 @@ static int vf610_nfc_probe(struct platform_device *pdev) if (irq <= 0) return -EINVAL; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - nfc->regs = devm_ioremap_resource(nfc->dev, res); + nfc->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(nfc->regs)) return PTR_ERR(nfc->regs); From abac656349cb9f081bc3b0a4c75d98486ade77f0 Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Wed, 1 Sep 2021 15:42:51 +0800 Subject: [PATCH 025/587] mtd: rawnand: xway: Make use of the helper function devm_platform_ioremap_resource() Use the devm_platform_ioremap_resource() helper instead of calling platform_get_resource() and devm_ioremap_resource() separately Signed-off-by: Cai Huoqing Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210901074252.9633-1-caihuoqing@baidu.com --- drivers/mtd/nand/raw/xway_nand.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/xway_nand.c b/drivers/mtd/nand/raw/xway_nand.c index 26751976e502..92067bd55384 100644 --- a/drivers/mtd/nand/raw/xway_nand.c +++ b/drivers/mtd/nand/raw/xway_nand.c @@ -167,7 +167,6 @@ static int xway_nand_probe(struct platform_device *pdev) { struct xway_nand_data *data; struct mtd_info *mtd; - struct resource *res; int err; u32 cs; u32 cs_flag = 0; @@ -178,8 +177,7 @@ static int xway_nand_probe(struct platform_device *pdev) if (!data) return -ENOMEM; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - data->nandaddr = devm_ioremap_resource(&pdev->dev, res); + data->nandaddr = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(data->nandaddr)) return PTR_ERR(data->nandaddr); From 46a0dc10fb32bec3e765e51bf71fbc070dc77ca3 Mon Sep 17 00:00:00 2001 From: Evgeny Novikov Date: Fri, 3 Sep 2021 11:26:53 +0300 Subject: [PATCH 026/587] mtd: rawnand: intel: Fix potential buffer overflow in probe ebu_nand_probe() read the value of u32 variable "cs" from the device firmware description and used it as the index for array ebu_host->cs that can contain MAX_CS (2) elements at most. That could result in a buffer overflow and various bad consequences later. Fix the potential buffer overflow by restricting values of "cs" with MAX_CS in probe. Found by Linux Driver Verification project (linuxtesting.org). Fixes: 0b1039f016e8 ("mtd: rawnand: Add NAND controller support on Intel LGM SoC") Signed-off-by: Evgeny Novikov Co-developed-by: Kirill Shilimanov Signed-off-by: Kirill Shilimanov Co-developed-by: Anton Vasilyev Signed-off-by: Anton Vasilyev Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210903082653.16441-1-novikov@ispras.ru --- drivers/mtd/nand/raw/intel-nand-controller.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/mtd/nand/raw/intel-nand-controller.c b/drivers/mtd/nand/raw/intel-nand-controller.c index b9784f3da7a1..7c1c80dae826 100644 --- a/drivers/mtd/nand/raw/intel-nand-controller.c +++ b/drivers/mtd/nand/raw/intel-nand-controller.c @@ -609,6 +609,11 @@ static int ebu_nand_probe(struct platform_device *pdev) dev_err(dev, "failed to get chip select: %d\n", ret); return ret; } + if (cs >= MAX_CS) { + dev_err(dev, "got invalid chip select: %d\n", cs); + return -EINVAL; + } + ebu_host->cs_num = cs; resname = devm_kasprintf(dev, GFP_KERNEL, "nand_cs%d", cs); From b72841e4dcd54de486fca2e4ffa00b8defc1eecc Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 10 Sep 2021 13:00:23 +0100 Subject: [PATCH 027/587] mtd: mtdswap: Remove redundant assignment of pointer eb The pointer eb is being assigned a value that is never read, it is being updated later on. The assignment is redundant and can be removed. Addresses-Coverity: ("Unused value") Signed-off-by: Colin Ian King Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210910120023.46308-1-colin.king@canonical.com --- drivers/mtd/mtdswap.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mtd/mtdswap.c b/drivers/mtd/mtdswap.c index 7e309270ddd4..e86b04bc1d6b 100644 --- a/drivers/mtd/mtdswap.c +++ b/drivers/mtd/mtdswap.c @@ -716,7 +716,6 @@ retry: return ret; } - eb = d->eb_data + *newblock / d->pages_per_eblk; d->page_data[page] = *newblock; d->revmap[oldblock] = PAGE_UNDEF; eb = d->eb_data + oldblock / d->pages_per_eblk; From 3149733584c8f0ab828eada539df7aa488c023a9 Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Sat, 11 Sep 2021 10:08:54 +0530 Subject: [PATCH 028/587] perf annotate: Add fusion logic for AMD microarchs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit AMD family 15h and above microarchs fuse a subset of cmp/test/ALU instructions with branch instructions[1][2]. Add perf annotate fused instruction support for these microarchs. Before: │ testb $0x80,0x51(%rax) │ ┌──jne 5b3 0.78 │ │ mov %r13,%rdi │ │→ callq mark_page_accessed 1.08 │5b3:└─→mov 0x8(%r13),%rax After: │ ┌──testb $0x80,0x51(%rax) │ ├──jne 5b3 0.78 │ │ mov %r13,%rdi │ │→ callq mark_page_accessed 1.08 │5b3:└─→mov 0x8(%r13),%rax [1] https://bugzilla.kernel.org/attachment.cgi?id=298553 [2] https://bugzilla.kernel.org/attachment.cgi?id=298555 Committer testing: On a: $ grep -m1 "model name" /proc/cpuinfo model name : AMD Ryzen 9 3900X 12-Core Processor $ Samples: 44K of event 'cycles', 4000 Hz, Event count (approx.): 7533249650 _int_malloc /usr/lib64/libc-2.33.so [Percent: local period] Percent│ ┌──test %eax,%eax │ ├──jne 884 │ │↓ jmpq 943 │ │ nop │878:│ add $0x10,%rdx 0.64 │ │ add %eax,%eax 0.57 │ │↓ je cc9 0.77 │884:└─→test %esi,%eax │ ↑ je 878 │ mov 0x18(%rdx),%r15 Reported-by: Kim Phillips Signed-off-by: Ravi Bangoria Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Jin Yao Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Link: https //lore.kernel.org/r/20210911043854.8373-2-ravi.bangoria@amd.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/x86/annotate/instructions.c | 28 ++++++++++++++++++++- tools/perf/util/annotate.c | 1 - 2 files changed, 27 insertions(+), 2 deletions(-) diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c index 24ea12ec7e02..305872692bfd 100644 --- a/tools/perf/arch/x86/annotate/instructions.c +++ b/tools/perf/arch/x86/annotate/instructions.c @@ -144,8 +144,31 @@ static struct ins x86__instructions[] = { { .name = "xorps", .ops = &mov_ops, }, }; -static bool x86__ins_is_fused(struct arch *arch, const char *ins1, +static bool amd__ins_is_fused(struct arch *arch, const char *ins1, const char *ins2) +{ + if (strstr(ins2, "jmp")) + return false; + + /* Family >= 15h supports cmp/test + branch fusion */ + if (arch->family >= 0x15 && (strstarts(ins1, "test") || + (strstarts(ins1, "cmp") && !strstr(ins1, "xchg")))) { + return true; + } + + /* Family >= 19h supports some ALU + branch fusion */ + if (arch->family >= 0x19 && (strstarts(ins1, "add") || + strstarts(ins1, "sub") || strstarts(ins1, "and") || + strstarts(ins1, "inc") || strstarts(ins1, "dec") || + strstarts(ins1, "or") || strstarts(ins1, "xor"))) { + return true; + } + + return false; +} + +static bool intel__ins_is_fused(struct arch *arch, const char *ins1, + const char *ins2) { if (arch->family != 6 || arch->model < 0x1e || strstr(ins2, "jmp")) return false; @@ -184,6 +207,9 @@ static int x86__cpuid_parse(struct arch *arch, char *cpuid) if (ret == 3) { arch->family = family; arch->model = model; + arch->ins_is_fused = strstarts(cpuid, "AuthenticAMD") ? + amd__ins_is_fused : + intel__ins_is_fused; return 0; } diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 0bae061b2d6d..b55f35485e43 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -183,7 +183,6 @@ static struct arch architectures[] = { .init = x86__annotate_init, .instructions = x86__instructions, .nr_instructions = ARRAY_SIZE(x86__instructions), - .ins_is_fused = x86__ins_is_fused, .objdump = { .comment_char = '#', }, From ddf0d4dee4cbcabdf5161da3fe744b6cb149db88 Mon Sep 17 00:00:00 2001 From: Muhammad Falak R Wani Date: Sun, 15 Aug 2021 16:06:10 +0530 Subject: [PATCH 029/587] perf bpf: Deprecate bpf_map__resize() in favor of bpf_map_set_max_entries() As a part of libbpf 1.0 plan[0], this patch deprecates use of bpf_map__resize in favour of bpf_map__set_max_entries. Reference: https://github.com/libbpf/libbpf/issues/304 [0]: https://github.com/libbpf/libbpf/wiki/Libbpf:-the-road-to-v1.0#libbpfh-high-level-apis Signed-off-by: Muhammad Falak R Wani Acked-by: Andrii Nakryiko Cc: Alexander Shishkin Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Jiri Olsa Cc: John Fastabend Cc: KP Singh Cc: Mark Rutland Cc: Martin KaFai Lau Cc: Muhammad Falak R Wani Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Quentin Monnet Cc: Song Liu Cc: Yu Kuai Link: http //lore.kernel.org/lkml/20210815103610.27887-1-falakreyaz@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf_counter.c | 8 ++++---- tools/perf/util/bpf_counter_cgroup.c | 8 ++++---- 2 files changed, 8 insertions(+), 8 deletions(-) diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c index ba0f20853651..ced2dac31dcf 100644 --- a/tools/perf/util/bpf_counter.c +++ b/tools/perf/util/bpf_counter.c @@ -127,9 +127,9 @@ static int bpf_program_profiler_load_one(struct evsel *evsel, u32 prog_id) skel->rodata->num_cpu = evsel__nr_cpus(evsel); - bpf_map__resize(skel->maps.events, evsel__nr_cpus(evsel)); - bpf_map__resize(skel->maps.fentry_readings, 1); - bpf_map__resize(skel->maps.accum_readings, 1); + bpf_map__set_max_entries(skel->maps.events, evsel__nr_cpus(evsel)); + bpf_map__set_max_entries(skel->maps.fentry_readings, 1); + bpf_map__set_max_entries(skel->maps.accum_readings, 1); prog_name = bpf_target_prog_name(prog_fd); if (!prog_name) { @@ -399,7 +399,7 @@ static int bperf_reload_leader_program(struct evsel *evsel, int attr_map_fd, return -1; } - bpf_map__resize(skel->maps.events, libbpf_num_possible_cpus()); + bpf_map__set_max_entries(skel->maps.events, libbpf_num_possible_cpus()); err = bperf_leader_bpf__load(skel); if (err) { pr_err("Failed to load leader skeleton\n"); diff --git a/tools/perf/util/bpf_counter_cgroup.c b/tools/perf/util/bpf_counter_cgroup.c index 89aa5e71db1a..cbc6c2bca488 100644 --- a/tools/perf/util/bpf_counter_cgroup.c +++ b/tools/perf/util/bpf_counter_cgroup.c @@ -65,14 +65,14 @@ static int bperf_load_program(struct evlist *evlist) /* we need one copy of events per cpu for reading */ map_size = total_cpus * evlist->core.nr_entries / nr_cgroups; - bpf_map__resize(skel->maps.events, map_size); - bpf_map__resize(skel->maps.cgrp_idx, nr_cgroups); + bpf_map__set_max_entries(skel->maps.events, map_size); + bpf_map__set_max_entries(skel->maps.cgrp_idx, nr_cgroups); /* previous result is saved in a per-cpu array */ map_size = evlist->core.nr_entries / nr_cgroups; - bpf_map__resize(skel->maps.prev_readings, map_size); + bpf_map__set_max_entries(skel->maps.prev_readings, map_size); /* cgroup result needs all events (per-cpu) */ map_size = evlist->core.nr_entries; - bpf_map__resize(skel->maps.cgrp_readings, map_size); + bpf_map__set_max_entries(skel->maps.cgrp_readings, map_size); set_max_rlimit(); From 00e0ca3721cf2ddcb38cf676a3de61933640d31d Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 14 Sep 2021 10:00:04 -0700 Subject: [PATCH 030/587] perf bpf: Ignore deprecation warning when using libbpf's btf__get_from_id() Perf code re-implements libbpf's btf__load_from_kernel_by_id() API as a weak function, presumably to dynamically link against old version of libbpf shared library. Unfortunately this causes compilation warning when perf is compiled against libbpf v0.6+. For now, just ignore deprecation warning, but there might be a better solution, depending on perf's needs. Signed-off-by: Andrii Nakryiko Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: kernel-team@fb.com LPU-Reference: 20210914170004.4185659-1-andrii@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf-event.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index 683f6d63560e..1a7112a87736 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -24,7 +24,10 @@ struct btf * __weak btf__load_from_kernel_by_id(__u32 id) { struct btf *btf; +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" int err = btf__get_from_id(id, &btf); +#pragma GCC diagnostic pop return err ? ERR_PTR(err) : btf; } From 8228e9361e2a7447eaed87499123e85871c8bc18 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 15 Sep 2021 14:14:28 -0700 Subject: [PATCH 031/587] perf parse-events: Avoid enum forward declaration. Enum forward declarations aren't allowed as the size can't be implied. Switch to just using an int. This fixes a clang warning: In file included from tools/perf/bench/evlist-open-close.c:13: tools/perf/bench/../util/parse-events.h:185:6: error: redeclaration of already-defined enum 'perf_tool_event' is a GNU extension [-Werror,-Wgnu-redeclared-enum] enum perf_tool_event; ^ tools/perf/bench/../util/evsel.h:28:6: note: previous definition is here enum perf_tool_event { ^ Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20210915211428.1773567-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 2 +- tools/perf/util/parse-events.h | 3 +-- 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 51a2219df601..5d1346aa0627 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1471,7 +1471,7 @@ out_free_terms: int parse_events_add_tool(struct parse_events_state *parse_state, struct list_head *list, - enum perf_tool_event tool_event) + int tool_event) { return add_event_tool(list, &parse_state->idx, tool_event); } diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index bf6e41aa9b6a..b32ed3064c49 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -182,10 +182,9 @@ int parse_events_add_numeric(struct parse_events_state *parse_state, struct list_head *list, u32 type, u64 config, struct list_head *head_config); -enum perf_tool_event; int parse_events_add_tool(struct parse_events_state *parse_state, struct list_head *list, - enum perf_tool_event tool_event); + int tool_event); int parse_events_add_cache(struct list_head *list, int *idx, char *type, char *op_result1, char *op_result2, struct parse_events_error *error, From 84111b9c950ec9a8b31166973e79aa77ddcee7e3 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 10 Aug 2021 21:46:57 -0700 Subject: [PATCH 032/587] perf tools: Allow controlling synthesizing PERF_RECORD_ metadata events during record Depending on the use case, it might require some kind of synthesizing and some not. Make it controllable to turn off heavy operations like MMAP for all tasks. Currently all users are converted to enable all the synthesis by default. It'll be updated in the later patch. Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: Ian Rogers Cc: Ingo Molnar Cc: Jin Yao Cc: Peter Zijlstra Cc: Stephane Eranian Link: https //lore.kernel.org/r/20210811044658.1313391-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/bench/synthesize.c | 4 +-- tools/perf/builtin-kvm.c | 2 +- tools/perf/builtin-record.c | 6 ++-- tools/perf/builtin-top.c | 2 +- tools/perf/builtin-trace.c | 4 +-- tools/perf/tests/code-reading.c | 3 +- tools/perf/tests/mmap-thread-lookup.c | 4 +-- tools/perf/util/synthetic-events.c | 45 ++++++++++++++++----------- tools/perf/util/synthetic-events.h | 8 ++--- 9 files changed, 44 insertions(+), 34 deletions(-) diff --git a/tools/perf/bench/synthesize.c b/tools/perf/bench/synthesize.c index 05f7c923c745..7401ebbac100 100644 --- a/tools/perf/bench/synthesize.c +++ b/tools/perf/bench/synthesize.c @@ -80,7 +80,7 @@ static int do_run_single_threaded(struct perf_session *session, NULL, target, threads, process_synthesized_event, - data_mmap, + true, data_mmap, nr_threads_synthesize); if (err) return err; @@ -171,7 +171,7 @@ static int do_run_multi_threaded(struct target *target, NULL, target, NULL, process_synthesized_event, - false, + true, false, nr_threads_synthesize); if (err) { perf_session__delete(session); diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index aa1b127ffb5b..c6f352ee57e6 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -1456,7 +1456,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm, perf_session__set_id_hdr_size(kvm->session); ordered_events__set_copy_on_queue(&kvm->session->ordered_events, true); machine__synthesize_threads(&kvm->session->machines.host, &kvm->opts.target, - kvm->evlist->core.threads, false, 1); + kvm->evlist->core.threads, true, false, 1); err = kvm_live_open_events(kvm); if (err) goto out; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index b3509d9d20cc..0263e383332f 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1266,6 +1266,7 @@ static int record__synthesize_workload(struct record *rec, bool tail) err = perf_event__synthesize_thread_map(&rec->tool, thread_map, process_synthesized_event, &rec->session->machines.host, + true, rec->opts.sample_address); perf_thread_map__put(thread_map); return err; @@ -1480,8 +1481,9 @@ static int record__synthesize(struct record *rec, bool tail) f = process_locked_synthesized_event; } - err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->core.threads, - f, opts->sample_address, + err = __machine__synthesize_threads(machine, tool, &opts->target, + rec->evlist->core.threads, + f, true, opts->sample_address, rec->opts.nr_threads_synthesize); if (rec->opts.nr_threads_synthesize > 1) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index a3ae9176a83e..020c4f110c10 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1271,7 +1271,7 @@ static int __cmd_top(struct perf_top *top) pr_debug("Couldn't synthesize cgroup events.\n"); machine__synthesize_threads(&top->session->machines.host, &opts->target, - top->evlist->core.threads, false, + top->evlist->core.threads, true, false, top->nr_threads_synthesize); if (top->nr_threads_synthesize > 1) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 2bf21194c7b3..2f1d20553a0a 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1628,8 +1628,8 @@ static int trace__symbols_init(struct trace *trace, struct evlist *evlist) goto out; err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target, - evlist->core.threads, trace__tool_process, false, - 1); + evlist->core.threads, trace__tool_process, + true, false, 1); out: if (err) symbol__exit(); diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 9866cddebf23..3a4d932e7ffc 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -606,7 +606,8 @@ static int do_test_code_reading(bool try_kcore) } ret = perf_event__synthesize_thread_map(NULL, threads, - perf_event__process, machine, false); + perf_event__process, machine, + true, false); if (ret < 0) { pr_debug("perf_event__synthesize_thread_map failed\n"); goto out_err; diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c index 8d9d4cbff76d..6f2da7a72f67 100644 --- a/tools/perf/tests/mmap-thread-lookup.c +++ b/tools/perf/tests/mmap-thread-lookup.c @@ -135,7 +135,7 @@ static int synth_all(struct machine *machine) { return perf_event__synthesize_threads(NULL, perf_event__process, - machine, 0, 1); + machine, 1, 0, 1); } static int synth_process(struct machine *machine) @@ -147,7 +147,7 @@ static int synth_process(struct machine *machine) err = perf_event__synthesize_thread_map(NULL, map, perf_event__process, - machine, 0); + machine, 1, 0); perf_thread_map__put(map); return err; diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index a7e981b2d7de..a7a2825356d6 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -715,7 +715,8 @@ static int __event__synthesize_thread(union perf_event *comm_event, union perf_event *fork_event, union perf_event *namespaces_event, pid_t pid, int full, perf_event__handler_t process, - struct perf_tool *tool, struct machine *machine, bool mmap_data) + struct perf_tool *tool, struct machine *machine, + bool needs_mmap, bool mmap_data) { char filename[PATH_MAX]; struct dirent **dirent; @@ -739,7 +740,7 @@ static int __event__synthesize_thread(union perf_event *comm_event, * send mmap only for thread group leader * see thread__init_maps() */ - if (pid == tgid && + if (pid == tgid && needs_mmap && perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, process, machine, mmap_data)) return -1; @@ -786,7 +787,7 @@ static int __event__synthesize_thread(union perf_event *comm_event, break; rc = 0; - if (_pid == pid && !kernel_thread) { + if (_pid == pid && !kernel_thread && needs_mmap) { /* process the parent's maps too */ rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, process, machine, mmap_data); @@ -806,7 +807,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine, - bool mmap_data) + bool needs_mmap, bool mmap_data) { union perf_event *comm_event, *mmap_event, *fork_event; union perf_event *namespaces_event; @@ -836,7 +837,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, fork_event, namespaces_event, perf_thread_map__pid(threads, thread), 0, process, tool, machine, - mmap_data)) { + needs_mmap, mmap_data)) { err = -1; break; } @@ -862,7 +863,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, fork_event, namespaces_event, comm_event->comm.pid, 0, process, tool, machine, - mmap_data)) { + needs_mmap, mmap_data)) { err = -1; break; } @@ -882,6 +883,7 @@ out: static int __perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, + bool needs_mmap, bool mmap_data, struct dirent **dirent, int start, @@ -926,7 +928,7 @@ static int __perf_event__synthesize_threads(struct perf_tool *tool, */ __event__synthesize_thread(comm_event, mmap_event, fork_event, namespaces_event, pid, 1, process, - tool, machine, mmap_data); + tool, machine, needs_mmap, mmap_data); } err = 0; @@ -945,6 +947,7 @@ struct synthesize_threads_arg { struct perf_tool *tool; perf_event__handler_t process; struct machine *machine; + bool needs_mmap; bool mmap_data; struct dirent **dirent; int num; @@ -956,7 +959,8 @@ static void *synthesize_threads_worker(void *arg) struct synthesize_threads_arg *args = arg; __perf_event__synthesize_threads(args->tool, args->process, - args->machine, args->mmap_data, + args->machine, + args->needs_mmap, args->mmap_data, args->dirent, args->start, args->num); return NULL; @@ -965,7 +969,7 @@ static void *synthesize_threads_worker(void *arg) int perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, - bool mmap_data, + bool needs_mmap, bool mmap_data, unsigned int nr_threads_synthesize) { struct synthesize_threads_arg *args = NULL; @@ -994,7 +998,8 @@ int perf_event__synthesize_threads(struct perf_tool *tool, if (thread_nr <= 1) { err = __perf_event__synthesize_threads(tool, process, - machine, mmap_data, + machine, + needs_mmap, mmap_data, dirent, base, n); goto free_dirent; } @@ -1015,6 +1020,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool, args[i].tool = tool; args[i].process = process; args[i].machine = machine; + args[i].needs_mmap = needs_mmap; args[i].mmap_data = mmap_data; args[i].dirent = dirent; } @@ -1775,26 +1781,27 @@ out_err: int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool, struct target *target, struct perf_thread_map *threads, - perf_event__handler_t process, bool data_mmap, - unsigned int nr_threads_synthesize) + perf_event__handler_t process, bool needs_mmap, + bool data_mmap, unsigned int nr_threads_synthesize) { if (target__has_task(target)) - return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap); + return perf_event__synthesize_thread_map(tool, threads, process, machine, + needs_mmap, data_mmap); else if (target__has_cpu(target)) - return perf_event__synthesize_threads(tool, process, - machine, data_mmap, + return perf_event__synthesize_threads(tool, process, machine, + needs_mmap, data_mmap, nr_threads_synthesize); /* command specified */ return 0; } int machine__synthesize_threads(struct machine *machine, struct target *target, - struct perf_thread_map *threads, bool data_mmap, - unsigned int nr_threads_synthesize) + struct perf_thread_map *threads, bool needs_mmap, + bool data_mmap, unsigned int nr_threads_synthesize) { return __machine__synthesize_threads(machine, NULL, target, threads, - perf_event__process, data_mmap, - nr_threads_synthesize); + perf_event__process, needs_mmap, + data_mmap, nr_threads_synthesize); } static struct perf_record_event_update *event_update_event__new(size_t size, u64 type, u64 id) diff --git a/tools/perf/util/synthetic-events.h b/tools/perf/util/synthetic-events.h index c845e2b9b444..44f72d56ca4d 100644 --- a/tools/perf/util/synthetic-events.h +++ b/tools/perf/util/synthetic-events.h @@ -53,8 +53,8 @@ int perf_event__synthesize_stat_events(struct perf_stat_config *config, struct p int perf_event__synthesize_stat_round(struct perf_tool *tool, u64 time, u64 type, perf_event__handler_t process, struct machine *machine); int perf_event__synthesize_stat(struct perf_tool *tool, u32 cpu, u32 thread, u64 id, struct perf_counts_values *count, perf_event__handler_t process, struct machine *machine); int perf_event__synthesize_thread_map2(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine); -int perf_event__synthesize_thread_map(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine, bool mmap_data); -int perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, bool mmap_data, unsigned int nr_threads_synthesize); +int perf_event__synthesize_thread_map(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine, bool needs_mmap, bool mmap_data); +int perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, bool needs_mmap, bool mmap_data, unsigned int nr_threads_synthesize); int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, struct evlist *evlist, perf_event__handler_t process); int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc, struct perf_tool *tool, perf_event__handler_t process, struct machine *machine); pid_t perf_event__synthesize_comm(struct perf_tool *tool, union perf_event *event, pid_t pid, perf_event__handler_t process, struct machine *machine); @@ -65,10 +65,10 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool, struct target *target, struct perf_thread_map *threads, - perf_event__handler_t process, bool data_mmap, + perf_event__handler_t process, bool needs_mmap, bool data_mmap, unsigned int nr_threads_synthesize); int machine__synthesize_threads(struct machine *machine, struct target *target, - struct perf_thread_map *threads, bool data_mmap, + struct perf_thread_map *threads, bool needs_mmap, bool data_mmap, unsigned int nr_threads_synthesize); #ifdef HAVE_AUXTRACE_SUPPORT From 41b740b6e8a994e5830daa5e15785522874f7456 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 10 Aug 2021 21:46:58 -0700 Subject: [PATCH 033/587] perf record: Add --synth option Add an option to control the synthesizing behavior. --synth Fine-tune event synthesis: default=all This can be useful when we know it doesn't need some synthesis like in a specific usecase and/or when using pipe: $ perf record -a --all-cgroups --synth cgroup -o- sleep 1 | \ > perf report -i- -s cgroup Committer notes: Added a clarification to the man page entry for --synth that this is about pre-existing threads. Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: Ian Rogers Cc: Ingo Molnar Cc: Jin Yao Cc: Peter Zijlstra Cc: Stephane Eranian Link: https //lore.kernel.org/r/20210811044658.1313391-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-record.txt | 16 ++++++++ tools/perf/builtin-record.c | 48 +++++++++++++++++++----- tools/perf/util/record.h | 1 + tools/perf/util/synthetic-events.c | 28 ++++++++++++++ tools/perf/util/synthetic-events.h | 12 ++++++ 5 files changed, 96 insertions(+), 9 deletions(-) diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index f1079ee7f2ec..2d7df8703cf2 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -596,6 +596,22 @@ options. 'perf record --dry-run -e' can act as a BPF script compiler if llvm.dump-obj in config file is set to true. +--synth=TYPE:: +Collect and synthesize given type of events (comma separated). Note that +this option controls the synthesis from the /proc filesystem which represent +task status for pre-existing threads. + +Kernel (and some other) events are recorded regardless of the +choice in this option. For example, --synth=no would have MMAP events for +kernel and modules. + +Available types are: + 'task' - synthesize FORK and COMM events for each task + 'mmap' - synthesize MMAP events for each process (implies 'task') + 'cgroup' - synthesize CGROUP events for each cgroup + 'all' - synthesize all events (default) + 'no' - do not synthesize any of the above events + --tail-synthesize:: Instead of collecting non-sample events (for example, fork, comm, mmap) at the beginning of record, collect them during finalizing an output file. diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 0263e383332f..41bb884f5a74 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1255,6 +1255,7 @@ static int record__synthesize_workload(struct record *rec, bool tail) { int err; struct perf_thread_map *thread_map; + bool needs_mmap = rec->opts.synth & PERF_SYNTH_MMAP; if (rec->opts.tail_synthesize != tail) return 0; @@ -1266,7 +1267,7 @@ static int record__synthesize_workload(struct record *rec, bool tail) err = perf_event__synthesize_thread_map(&rec->tool, thread_map, process_synthesized_event, &rec->session->machines.host, - true, + needs_mmap, rec->opts.sample_address); perf_thread_map__put(thread_map); return err; @@ -1471,20 +1472,26 @@ static int record__synthesize(struct record *rec, bool tail) if (err < 0) pr_warning("Couldn't synthesize bpf events.\n"); - err = perf_event__synthesize_cgroups(tool, process_synthesized_event, - machine); - if (err < 0) - pr_warning("Couldn't synthesize cgroup events.\n"); + if (rec->opts.synth & PERF_SYNTH_CGROUP) { + err = perf_event__synthesize_cgroups(tool, process_synthesized_event, + machine); + if (err < 0) + pr_warning("Couldn't synthesize cgroup events.\n"); + } if (rec->opts.nr_threads_synthesize > 1) { perf_set_multithreaded(); f = process_locked_synthesized_event; } - err = __machine__synthesize_threads(machine, tool, &opts->target, - rec->evlist->core.threads, - f, true, opts->sample_address, - rec->opts.nr_threads_synthesize); + if (rec->opts.synth & PERF_SYNTH_TASK) { + bool needs_mmap = rec->opts.synth & PERF_SYNTH_MMAP; + + err = __machine__synthesize_threads(machine, tool, &opts->target, + rec->evlist->core.threads, + f, needs_mmap, opts->sample_address, + rec->opts.nr_threads_synthesize); + } if (rec->opts.nr_threads_synthesize > 1) perf_set_singlethreaded(); @@ -2393,6 +2400,26 @@ static int process_timestamp_boundary(struct perf_tool *tool, return 0; } +static int parse_record_synth_option(const struct option *opt, + const char *str, + int unset __maybe_unused) +{ + struct record_opts *opts = opt->value; + char *p = strdup(str); + + if (p == NULL) + return -1; + + opts->synth = parse_synth_opt(p); + free(p); + + if (opts->synth < 0) { + pr_err("Invalid synth option: %s\n", str); + return -1; + } + return 0; +} + /* * XXX Ideally would be local to cmd_record() and passed to a record__new * because we need to have access to it in record__exit, that is called @@ -2418,6 +2445,7 @@ static struct record record = { .nr_threads_synthesize = 1, .ctl_fd = -1, .ctl_fd_ack = -1, + .synth = PERF_SYNTH_ALL, }, .tool = { .sample = process_sample_event, @@ -2633,6 +2661,8 @@ static struct option __record_options[] = { "\t\t\t Optionally send control command completion ('ack\\n') to ack-fd descriptor.\n" "\t\t\t Alternatively, ctl-fifo / ack-fifo will be opened and used as ctl-fd / ack-fd.", parse_control_option), + OPT_CALLBACK(0, "synth", &record.opts, "no|all|task|mmap|cgroup", + "Fine-tune event synthesis: default=all", parse_record_synth_option), OPT_END() }; diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h index 68f471d9a88b..ef6c2715fdd9 100644 --- a/tools/perf/util/record.h +++ b/tools/perf/util/record.h @@ -77,6 +77,7 @@ struct record_opts { int ctl_fd; int ctl_fd_ack; bool ctl_fd_close; + int synth; }; extern const char * const *record_usage; diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index a7a2825356d6..198982109f0f 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -2237,3 +2237,31 @@ int perf_event__synthesize_for_pipe(struct perf_tool *tool, return ret; } + +int parse_synth_opt(char *synth) +{ + char *p, *q; + int ret = 0; + + if (synth == NULL) + return -1; + + for (q = synth; (p = strsep(&q, ",")); p = q) { + if (!strcasecmp(p, "no") || !strcasecmp(p, "none")) + return 0; + + if (!strcasecmp(p, "all")) + return PERF_SYNTH_ALL; + + if (!strcasecmp(p, "task")) + ret |= PERF_SYNTH_TASK; + else if (!strcasecmp(p, "mmap")) + ret |= PERF_SYNTH_TASK | PERF_SYNTH_MMAP; + else if (!strcasecmp(p, "cgroup")) + ret |= PERF_SYNTH_CGROUP; + else + return -1; + } + + return ret; +} diff --git a/tools/perf/util/synthetic-events.h b/tools/perf/util/synthetic-events.h index 44f72d56ca4d..c931433bacbf 100644 --- a/tools/perf/util/synthetic-events.h +++ b/tools/perf/util/synthetic-events.h @@ -27,6 +27,18 @@ struct target; union perf_event; +enum perf_record_synth { + PERF_SYNTH_TASK = 1 << 0, + PERF_SYNTH_MMAP = 1 << 1, + PERF_SYNTH_CGROUP = 1 << 2, + + /* last element */ + PERF_SYNTH_MAX = 1 << 3, +}; +#define PERF_SYNTH_ALL (PERF_SYNTH_MAX - 1) + +int parse_synth_opt(char *str); + typedef int (*perf_event__handler_t)(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); From 3a19407913e8e43d6b799a59bc0f6cae889b5446 Mon Sep 17 00:00:00 2001 From: Wang Lu Date: Thu, 9 Sep 2021 11:25:28 +0800 Subject: [PATCH 034/587] PCI/P2PDMA: Apply bus offset correctly in DMA address calculation The bus offset is bus address - physical address, so the calculation in __pci_p2pdma_map_sg should be: bus address = physical address + bus offset. Correct the dma_address computation in __pci_p2pdma_map_sg(). Link: https://lore.kernel.org/r/20210909032528.24517-1-wanglu@dapustor.com Signed-off-by: Wang Lu Signed-off-by: Bjorn Helgaas Reviewed-by: Logan Gunthorpe --- drivers/pci/p2pdma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c index 50cdde3e9a8b..327882638b30 100644 --- a/drivers/pci/p2pdma.c +++ b/drivers/pci/p2pdma.c @@ -874,7 +874,7 @@ static int __pci_p2pdma_map_sg(struct pci_p2pdma_pagemap *p2p_pgmap, int i; for_each_sg(sg, s, nents, i) { - s->dma_address = sg_phys(s) - p2p_pgmap->bus_offset; + s->dma_address = sg_phys(s) + p2p_pgmap->bus_offset; sg_dma_len(s) = s->length; } From e3f4bd3462f6f796594ecc0dda7144ed2d1e5a26 Mon Sep 17 00:00:00 2001 From: Ingmar Klein Date: Fri, 9 Apr 2021 11:26:33 +0200 Subject: [PATCH 035/587] PCI: Mark Atheros QCA6174 to avoid bus reset MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When passing the Atheros QCA6174 through to a virtual machine, the VM hangs at the point where the ath10k driver loads. Add a quirk to avoid bus resets on this device, which avoids the hang. [bhelgaas: commit log] Link: https://lore.kernel.org/r/08982e05-b6e8-5a8d-24ab-da1488ee50a8@web.de Signed-off-by: Ingmar Klein Signed-off-by: Bjorn Helgaas Reviewed-by: Pali Rohár Cc: stable@vger.kernel.org --- drivers/pci/quirks.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 4537d1ea14fd..6c957124f84d 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -3612,6 +3612,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATHEROS, 0x0032, quirk_no_bus_reset); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATHEROS, 0x003c, quirk_no_bus_reset); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATHEROS, 0x0033, quirk_no_bus_reset); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATHEROS, 0x0034, quirk_no_bus_reset); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATHEROS, 0x003e, quirk_no_bus_reset); /* * Root port on some Cavium CN8xxx chips do not successfully complete a bus From 0e8ae5a6ff5952253cd7cc0260df838ab4c21009 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Mon, 30 Aug 2021 10:08:10 +0200 Subject: [PATCH 036/587] PCI/portdrv: Do not setup up IRQs if there are no users Avoid registering service IRQs if there is no service that offers them or no driver to register a handler against them. This saves IRQ vectors when they are limited (e.g. on x86) and also avoids that spurious events could hit a missing handler. Such spurious events need to be generated by the Jailhouse hypervisor for active MSI vectors when enabling or disabling itself. Link: https://lore.kernel.org/r/8f9a13ac-8ab1-15ac-06cb-c131b488a36f@siemens.com Signed-off-by: Jan Kiszka Signed-off-by: Bjorn Helgaas --- drivers/pci/pcie/portdrv_core.c | 47 +++++++++++++++++++++------------ 1 file changed, 30 insertions(+), 17 deletions(-) diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c index 3ee63968deaa..bf5440c3ca8a 100644 --- a/drivers/pci/pcie/portdrv_core.c +++ b/drivers/pci/pcie/portdrv_core.c @@ -166,9 +166,6 @@ static int pcie_init_service_irqs(struct pci_dev *dev, int *irqs, int mask) { int ret, i; - for (i = 0; i < PCIE_PORT_DEVICE_MAXSERVICES; i++) - irqs[i] = -1; - /* * If we support PME but can't use MSI/MSI-X for it, we have to * fall back to INTx or other interrupts, e.g., a system shared @@ -317,8 +314,10 @@ static int pcie_device_init(struct pci_dev *pdev, int service, int irq) */ int pcie_port_device_register(struct pci_dev *dev) { - int status, capabilities, i, nr_service; - int irqs[PCIE_PORT_DEVICE_MAXSERVICES]; + int status, capabilities, irq_services, i, nr_service; + int irqs[PCIE_PORT_DEVICE_MAXSERVICES] = { + [0 ... PCIE_PORT_DEVICE_MAXSERVICES-1] = -1 + }; /* Enable PCI Express port device */ status = pci_enable_device(dev); @@ -331,18 +330,32 @@ int pcie_port_device_register(struct pci_dev *dev) return 0; pci_set_master(dev); - /* - * Initialize service irqs. Don't use service devices that - * require interrupts if there is no way to generate them. - * However, some drivers may have a polling mode (e.g. pciehp_poll_mode) - * that can be used in the absence of irqs. Allow them to determine - * if that is to be used. - */ - status = pcie_init_service_irqs(dev, irqs, capabilities); - if (status) { - capabilities &= PCIE_PORT_SERVICE_HP; - if (!capabilities) - goto error_disable; + + irq_services = 0; + if (IS_ENABLED(CONFIG_PCIE_PME)) + irq_services |= PCIE_PORT_SERVICE_PME; + if (IS_ENABLED(CONFIG_PCIEAER)) + irq_services |= PCIE_PORT_SERVICE_AER; + if (IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE)) + irq_services |= PCIE_PORT_SERVICE_HP; + if (IS_ENABLED(CONFIG_PCIE_DPC)) + irq_services |= PCIE_PORT_SERVICE_DPC; + irq_services &= capabilities; + + if (irq_services) { + /* + * Initialize service IRQs. Don't use service devices that + * require interrupts if there is no way to generate them. + * However, some drivers may have a polling mode (e.g. + * pciehp_poll_mode) that can be used in the absence of IRQs. + * Allow them to determine if that is to be used. + */ + status = pcie_init_service_irqs(dev, irqs, irq_services); + if (status) { + irq_services &= PCIE_PORT_SERVICE_HP; + if (!irq_services) + goto error_disable; + } } /* Allocate child services if any */ From b28e5e439109fe6fd9fa047654ae99d0b7bc5ccc Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 16 Jun 2021 22:55:54 -0700 Subject: [PATCH 037/587] perf daemon: Avoid msan warnings on send_cmd As a full union is always sent, ensure all bytes of the union are initialized with memset to avoid msan warnings of use of uninitialized memory. An example warning from the daemon test: Uninitialized bytes in __interceptor_write at offset 71 inside [0x7ffd98da6280, 72) ==11602==WARNING: MemorySanitizer: use-of-uninitialized-value #0 0x5597edccdbe4 in ion tools/lib/perf/lib.c:18:6 #1 0x5597edccdbe4 in writen tools/lib/perf/lib.c:47:9 #2 0x5597ed221d30 in send_cmd tools/perf/builtin-daemon.c:1376:22 #3 0x5597ed21b48c in cmd_daemon tools/perf/builtin-daemon.c #4 0x5597ed1d6b67 in run_builtin tools/perf/perf.c:313:11 #5 0x5597ed1d6036 in handle_internal_command tools/perf/perf.c:365:8 #6 0x5597ed1d6036 in run_argv tools/perf/perf.c:409:2 #7 0x5597ed1d6036 in main tools/perf/perf.c:539:3 SUMMARY: MemorySanitizer: use-of-uninitialized-value tools/lib/perf/lib.c:18:6 in ion Exiting Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20210617055554.1917997-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-daemon.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/tools/perf/builtin-daemon.c b/tools/perf/builtin-daemon.c index 61929f63a047..c13201fb09c3 100644 --- a/tools/perf/builtin-daemon.c +++ b/tools/perf/builtin-daemon.c @@ -1403,8 +1403,10 @@ out: static int send_cmd_list(struct daemon *daemon) { - union cmd cmd = { .cmd = CMD_LIST, }; + union cmd cmd; + memset(&cmd, 0, sizeof(cmd)); + cmd.list.cmd = CMD_LIST; cmd.list.verbose = verbose; cmd.list.csv_sep = daemon->csv_sep ? *daemon->csv_sep : 0; @@ -1432,6 +1434,7 @@ static int __cmd_signal(struct daemon *daemon, struct option parent_options[], return -1; } + memset(&cmd, 0, sizeof(cmd)); cmd.signal.cmd = CMD_SIGNAL, cmd.signal.sig = SIGUSR2; strncpy(cmd.signal.name, name, sizeof(cmd.signal.name) - 1); @@ -1446,7 +1449,7 @@ static int __cmd_stop(struct daemon *daemon, struct option parent_options[], OPT_PARENT(parent_options), OPT_END() }; - union cmd cmd = { .cmd = CMD_STOP, }; + union cmd cmd; argc = parse_options(argc, argv, start_options, daemon_usage, 0); if (argc) @@ -1457,6 +1460,8 @@ static int __cmd_stop(struct daemon *daemon, struct option parent_options[], return -1; } + memset(&cmd, 0, sizeof(cmd)); + cmd.cmd = CMD_STOP; return send_cmd(daemon, &cmd); } @@ -1470,7 +1475,7 @@ static int __cmd_ping(struct daemon *daemon, struct option parent_options[], OPT_PARENT(parent_options), OPT_END() }; - union cmd cmd = { .cmd = CMD_PING, }; + union cmd cmd; argc = parse_options(argc, argv, ping_options, daemon_usage, 0); if (argc) @@ -1481,6 +1486,8 @@ static int __cmd_ping(struct daemon *daemon, struct option parent_options[], return -1; } + memset(&cmd, 0, sizeof(cmd)); + cmd.cmd = CMD_PING; scnprintf(cmd.ping.name, sizeof(cmd.ping.name), "%s", name); return send_cmd(daemon, &cmd); } From 06dc660e6eb8817c4c379d2ca290ae0b3f77c69f Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Tue, 14 Sep 2021 01:27:08 +1000 Subject: [PATCH 038/587] PCI: Rename pcibios_add_device() to pcibios_device_add() The general convention for pcibios_* hooks is that they're named after the corresponding pci_* function they provide a hook for. The exception is pcibios_add_device() which provides a hook for pci_device_add(). Rename pcibios_add_device() to pcibios_device_add() so it matches pci_device_add(). Also, remove the export of the microblaze version. The only caller must be compiled as a built-in so there's no reason for the export. Link: https://lore.kernel.org/r/20210913152709.48013-1-oohall@gmail.com Signed-off-by: Oliver O'Halloran Signed-off-by: Bjorn Helgaas Acked-by: Niklas Schnelle # s390 --- arch/microblaze/pci/pci-common.c | 3 +-- arch/powerpc/kernel/pci-common.c | 2 +- arch/powerpc/platforms/powernv/pci-sriov.c | 2 +- arch/s390/pci/pci.c | 2 +- arch/sparc/kernel/pci.c | 2 +- arch/x86/pci/common.c | 2 +- drivers/pci/pci.c | 4 ++-- drivers/pci/probe.c | 4 ++-- include/linux/pci.h | 2 +- 9 files changed, 11 insertions(+), 12 deletions(-) diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c index 557585f1be41..622a4867f9e9 100644 --- a/arch/microblaze/pci/pci-common.c +++ b/arch/microblaze/pci/pci-common.c @@ -587,13 +587,12 @@ static void pcibios_fixup_resources(struct pci_dev *dev) } DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pcibios_fixup_resources); -int pcibios_add_device(struct pci_dev *dev) +int pcibios_device_add(struct pci_dev *dev) { dev->irq = of_irq_parse_and_map_pci(dev, 0, 0); return 0; } -EXPORT_SYMBOL(pcibios_add_device); /* * Reparent resource children of pr that conflict with res diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index c3573430919d..6749905932f4 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -1059,7 +1059,7 @@ void pcibios_bus_add_device(struct pci_dev *dev) ppc_md.pcibios_bus_add_device(dev); } -int pcibios_add_device(struct pci_dev *dev) +int pcibios_device_add(struct pci_dev *dev) { struct irq_domain *d; diff --git a/arch/powerpc/platforms/powernv/pci-sriov.c b/arch/powerpc/platforms/powernv/pci-sriov.c index 28aac933a439..486c2937b159 100644 --- a/arch/powerpc/platforms/powernv/pci-sriov.c +++ b/arch/powerpc/platforms/powernv/pci-sriov.c @@ -54,7 +54,7 @@ * to "new_size", calculated above. Implementing this is a convoluted process * which requires several hooks in the PCI core: * - * 1. In pcibios_add_device() we call pnv_pci_ioda_fixup_iov(). + * 1. In pcibios_device_add() we call pnv_pci_ioda_fixup_iov(). * * At this point the device has been probed and the device's BARs are sized, * but no resource allocations have been done. The SR-IOV BARs are sized diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index e7e6788d75a8..ded3321b7208 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -561,7 +561,7 @@ static void zpci_cleanup_bus_resources(struct zpci_dev *zdev) zdev->has_resources = 0; } -int pcibios_add_device(struct pci_dev *pdev) +int pcibios_device_add(struct pci_dev *pdev) { struct zpci_dev *zdev = to_zpci(pdev); struct resource *res; diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c index 9c2b720bfd20..31b0c1983286 100644 --- a/arch/sparc/kernel/pci.c +++ b/arch/sparc/kernel/pci.c @@ -1010,7 +1010,7 @@ void pcibios_set_master(struct pci_dev *dev) } #ifdef CONFIG_PCI_IOV -int pcibios_add_device(struct pci_dev *dev) +int pcibios_device_add(struct pci_dev *dev) { struct pci_dev *pdev; diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 3507f456fcd0..9e1e6b8d8876 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -632,7 +632,7 @@ static void set_dev_domain_options(struct pci_dev *pdev) pdev->hotplug_user_indicators = 1; } -int pcibios_add_device(struct pci_dev *dev) +int pcibios_device_add(struct pci_dev *dev) { struct pci_setup_rom *rom; struct irq_domain *msidom; diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index ce2ab62b64cf..c63598c1cdd8 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -2091,14 +2091,14 @@ void pcim_pin_device(struct pci_dev *pdev) EXPORT_SYMBOL(pcim_pin_device); /* - * pcibios_add_device - provide arch specific hooks when adding device dev + * pcibios_device_add - provide arch specific hooks when adding device dev * @dev: the PCI device being added * * Permits the platform to provide architecture specific functionality when * devices are added. This is the default implementation. Architecture * implementations can override this. */ -int __weak pcibios_add_device(struct pci_dev *dev) +int __weak pcibios_device_add(struct pci_dev *dev) { return 0; } diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index d9fc02a71baa..2ba43b6adf31 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2450,7 +2450,7 @@ static struct irq_domain *pci_dev_msi_domain(struct pci_dev *dev) struct irq_domain *d; /* - * If a domain has been set through the pcibios_add_device() + * If a domain has been set through the pcibios_device_add() * callback, then this is the one (platform code knows best). */ d = dev_get_msi_domain(&dev->dev); @@ -2518,7 +2518,7 @@ void pci_device_add(struct pci_dev *dev, struct pci_bus *bus) list_add_tail(&dev->bus_list, &bus->devices); up_write(&pci_bus_sem); - ret = pcibios_add_device(dev); + ret = pcibios_device_add(dev); WARN_ON(ret < 0); /* Set up MSI IRQ domain */ diff --git a/include/linux/pci.h b/include/linux/pci.h index cd8aa6fce204..7e0ce3a4d5a1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2126,7 +2126,7 @@ void pcibios_disable_device(struct pci_dev *dev); void pcibios_set_master(struct pci_dev *dev); int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state state); -int pcibios_add_device(struct pci_dev *dev); +int pcibios_device_add(struct pci_dev *dev); void pcibios_release_device(struct pci_dev *dev); #ifdef CONFIG_PCI void pcibios_penalize_isa_irq(int irq, int active); From d1c6e08e7503649e4a4f3f9e700e2c05300b6379 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 8 Sep 2021 22:11:37 -0700 Subject: [PATCH 039/587] libnvdimm/labels: Add uuid helpers In preparation for CXL labels that move the uuid to a different offset in the label, add nsl_{ref,get,validate}_uuid(). These helpers use the proper uuid_t type. That type definition predated the libnvdimm subsystem, so now is as a good a time as any to convert all the uuid handling in the subsystem to uuid_t to match the helpers. Note that the uuid fields in the label data and superblocks is not replaced per Andy's expectation that uuid_t is a kernel internal type not to appear in external ABI interfaces. So, in those case {import,export}_uuid() is used to go between the 2 types. Also note that this rework uncovered some unnecessary copies for label comparisons, those are cleaned up with nsl_uuid_equal(). As for the whitespace changes, all new code is clang-format compliant. Reported-by: Andy Shevchenko Reviewed-by: Andy Shevchenko Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/163116429748.2460985.15659993454313919977.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/nvdimm/btt.c | 11 ++-- drivers/nvdimm/btt_devs.c | 14 ++--- drivers/nvdimm/core.c | 40 ++------------- drivers/nvdimm/label.c | 34 +++++-------- drivers/nvdimm/namespace_devs.c | 90 ++++++++++++++++++--------------- drivers/nvdimm/nd-core.h | 5 +- drivers/nvdimm/nd.h | 40 +++++++++++++-- drivers/nvdimm/pfn_devs.c | 2 +- include/linux/nd.h | 4 +- 9 files changed, 124 insertions(+), 116 deletions(-) diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c index 92dec4952297..52de60b7adee 100644 --- a/drivers/nvdimm/btt.c +++ b/drivers/nvdimm/btt.c @@ -973,7 +973,7 @@ static int btt_arena_write_layout(struct arena_info *arena) u64 sum; struct btt_sb *super; struct nd_btt *nd_btt = arena->nd_btt; - const u8 *parent_uuid = nd_dev_to_uuid(&nd_btt->ndns->dev); + const uuid_t *parent_uuid = nd_dev_to_uuid(&nd_btt->ndns->dev); ret = btt_map_init(arena); if (ret) @@ -988,8 +988,8 @@ static int btt_arena_write_layout(struct arena_info *arena) return -ENOMEM; strncpy(super->signature, BTT_SIG, BTT_SIG_LEN); - memcpy(super->uuid, nd_btt->uuid, 16); - memcpy(super->parent_uuid, parent_uuid, 16); + export_uuid(super->uuid, nd_btt->uuid); + export_uuid(super->parent_uuid, parent_uuid); super->flags = cpu_to_le32(arena->flags); super->version_major = cpu_to_le16(arena->version_major); super->version_minor = cpu_to_le16(arena->version_minor); @@ -1575,7 +1575,8 @@ static void btt_blk_cleanup(struct btt *btt) * Pointer to a new struct btt on success, NULL on failure. */ static struct btt *btt_init(struct nd_btt *nd_btt, unsigned long long rawsize, - u32 lbasize, u8 *uuid, struct nd_region *nd_region) + u32 lbasize, uuid_t *uuid, + struct nd_region *nd_region) { int ret; struct btt *btt; @@ -1694,7 +1695,7 @@ int nvdimm_namespace_attach_btt(struct nd_namespace_common *ndns) } nd_region = to_nd_region(nd_btt->dev.parent); btt = btt_init(nd_btt, rawsize, nd_btt->lbasize, nd_btt->uuid, - nd_region); + nd_region); if (!btt) return -ENOMEM; nd_btt->btt = btt; diff --git a/drivers/nvdimm/btt_devs.c b/drivers/nvdimm/btt_devs.c index 05feb97e11ce..8b52e5144f08 100644 --- a/drivers/nvdimm/btt_devs.c +++ b/drivers/nvdimm/btt_devs.c @@ -180,8 +180,8 @@ bool is_nd_btt(struct device *dev) EXPORT_SYMBOL(is_nd_btt); static struct device *__nd_btt_create(struct nd_region *nd_region, - unsigned long lbasize, u8 *uuid, - struct nd_namespace_common *ndns) + unsigned long lbasize, uuid_t *uuid, + struct nd_namespace_common *ndns) { struct nd_btt *nd_btt; struct device *dev; @@ -244,14 +244,16 @@ struct device *nd_btt_create(struct nd_region *nd_region) */ bool nd_btt_arena_is_valid(struct nd_btt *nd_btt, struct btt_sb *super) { - const u8 *parent_uuid = nd_dev_to_uuid(&nd_btt->ndns->dev); + const uuid_t *ns_uuid = nd_dev_to_uuid(&nd_btt->ndns->dev); + uuid_t parent_uuid; u64 checksum; if (memcmp(super->signature, BTT_SIG, BTT_SIG_LEN) != 0) return false; - if (!guid_is_null((guid_t *)&super->parent_uuid)) - if (memcmp(super->parent_uuid, parent_uuid, 16) != 0) + import_uuid(&parent_uuid, super->parent_uuid); + if (!uuid_is_null(&parent_uuid)) + if (!uuid_equal(&parent_uuid, ns_uuid)) return false; checksum = le64_to_cpu(super->checksum); @@ -319,7 +321,7 @@ static int __nd_btt_probe(struct nd_btt *nd_btt, return rc; nd_btt->lbasize = le32_to_cpu(btt_sb->external_lbasize); - nd_btt->uuid = kmemdup(btt_sb->uuid, 16, GFP_KERNEL); + nd_btt->uuid = kmemdup(&btt_sb->uuid, sizeof(uuid_t), GFP_KERNEL); if (!nd_btt->uuid) return -ENOMEM; diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c index 7de592d7eff4..690152d62bf0 100644 --- a/drivers/nvdimm/core.c +++ b/drivers/nvdimm/core.c @@ -206,38 +206,6 @@ struct device *to_nvdimm_bus_dev(struct nvdimm_bus *nvdimm_bus) } EXPORT_SYMBOL_GPL(to_nvdimm_bus_dev); -static bool is_uuid_sep(char sep) -{ - if (sep == '\n' || sep == '-' || sep == ':' || sep == '\0') - return true; - return false; -} - -static int nd_uuid_parse(struct device *dev, u8 *uuid_out, const char *buf, - size_t len) -{ - const char *str = buf; - u8 uuid[16]; - int i; - - for (i = 0; i < 16; i++) { - if (!isxdigit(str[0]) || !isxdigit(str[1])) { - dev_dbg(dev, "pos: %d buf[%zd]: %c buf[%zd]: %c\n", - i, str - buf, str[0], - str + 1 - buf, str[1]); - return -EINVAL; - } - - uuid[i] = (hex_to_bin(str[0]) << 4) | hex_to_bin(str[1]); - str += 2; - if (is_uuid_sep(*str)) - str++; - } - - memcpy(uuid_out, uuid, sizeof(uuid)); - return 0; -} - /** * nd_uuid_store: common implementation for writing 'uuid' sysfs attributes * @dev: container device for the uuid property @@ -248,21 +216,21 @@ static int nd_uuid_parse(struct device *dev, u8 *uuid_out, const char *buf, * (driver detached) * LOCKING: expects nd_device_lock() is held on entry */ -int nd_uuid_store(struct device *dev, u8 **uuid_out, const char *buf, +int nd_uuid_store(struct device *dev, uuid_t **uuid_out, const char *buf, size_t len) { - u8 uuid[16]; + uuid_t uuid; int rc; if (dev->driver) return -EBUSY; - rc = nd_uuid_parse(dev, uuid, buf, len); + rc = uuid_parse(buf, &uuid); if (rc) return rc; kfree(*uuid_out); - *uuid_out = kmemdup(uuid, sizeof(uuid), GFP_KERNEL); + *uuid_out = kmemdup(&uuid, sizeof(uuid), GFP_KERNEL); if (!(*uuid_out)) return -ENOMEM; diff --git a/drivers/nvdimm/label.c b/drivers/nvdimm/label.c index 7f473f9db300..e7fdb718ebf0 100644 --- a/drivers/nvdimm/label.c +++ b/drivers/nvdimm/label.c @@ -321,7 +321,8 @@ static bool preamble_index(struct nvdimm_drvdata *ndd, int idx, return true; } -char *nd_label_gen_id(struct nd_label_id *label_id, u8 *uuid, u32 flags) +char *nd_label_gen_id(struct nd_label_id *label_id, const uuid_t *uuid, + u32 flags) { if (!label_id || !uuid) return NULL; @@ -400,9 +401,9 @@ int nd_label_reserve_dpa(struct nvdimm_drvdata *ndd) struct nvdimm *nvdimm = to_nvdimm(ndd->dev); struct nd_namespace_label *nd_label; struct nd_region *nd_region = NULL; - u8 label_uuid[NSLABEL_UUID_LEN]; struct nd_label_id label_id; struct resource *res; + uuid_t label_uuid; u32 flags; nd_label = to_label(ndd, slot); @@ -410,11 +411,11 @@ int nd_label_reserve_dpa(struct nvdimm_drvdata *ndd) if (!slot_valid(ndd, nd_label, slot)) continue; - memcpy(label_uuid, nd_label->uuid, NSLABEL_UUID_LEN); + nsl_get_uuid(ndd, nd_label, &label_uuid); flags = nsl_get_flags(ndd, nd_label); if (test_bit(NDD_NOBLK, &nvdimm->flags)) flags &= ~NSLABEL_FLAG_LOCAL; - nd_label_gen_id(&label_id, label_uuid, flags); + nd_label_gen_id(&label_id, &label_uuid, flags); res = nvdimm_allocate_dpa(ndd, &label_id, nsl_get_dpa(ndd, nd_label), nsl_get_rawsize(ndd, nd_label)); @@ -851,7 +852,7 @@ static int __pmem_label_update(struct nd_region *nd_region, nd_label = to_label(ndd, slot); memset(nd_label, 0, sizeof_namespace_label(ndd)); - memcpy(nd_label->uuid, nspm->uuid, NSLABEL_UUID_LEN); + nsl_set_uuid(ndd, nd_label, nspm->uuid); nsl_set_name(ndd, nd_label, nspm->alt_name); nsl_set_flags(ndd, nd_label, flags); nsl_set_nlabel(ndd, nd_label, nd_region->ndr_mappings); @@ -878,9 +879,8 @@ static int __pmem_label_update(struct nd_region *nd_region, list_for_each_entry(label_ent, &nd_mapping->labels, list) { if (!label_ent->label) continue; - if (test_and_clear_bit(ND_LABEL_REAP, &label_ent->flags) - || memcmp(nspm->uuid, label_ent->label->uuid, - NSLABEL_UUID_LEN) == 0) + if (test_and_clear_bit(ND_LABEL_REAP, &label_ent->flags) || + nsl_uuid_equal(ndd, label_ent->label, nspm->uuid)) reap_victim(nd_mapping, label_ent); } @@ -1005,7 +1005,6 @@ static int __blk_label_update(struct nd_region *nd_region, unsigned long *free, *victim_map = NULL; struct resource *res, **old_res_list; struct nd_label_id label_id; - u8 uuid[NSLABEL_UUID_LEN]; int min_dpa_idx = 0; LIST_HEAD(list); u32 nslot, slot; @@ -1043,8 +1042,7 @@ static int __blk_label_update(struct nd_region *nd_region, /* mark unused labels for garbage collection */ for_each_clear_bit_le(slot, free, nslot) { nd_label = to_label(ndd, slot); - memcpy(uuid, nd_label->uuid, NSLABEL_UUID_LEN); - if (memcmp(uuid, nsblk->uuid, NSLABEL_UUID_LEN) != 0) + if (!nsl_uuid_equal(ndd, nd_label, nsblk->uuid)) continue; res = to_resource(ndd, nd_label); if (res && is_old_resource(res, old_res_list, @@ -1113,7 +1111,7 @@ static int __blk_label_update(struct nd_region *nd_region, nd_label = to_label(ndd, slot); memset(nd_label, 0, sizeof_namespace_label(ndd)); - memcpy(nd_label->uuid, nsblk->uuid, NSLABEL_UUID_LEN); + nsl_set_uuid(ndd, nd_label, nsblk->uuid); nsl_set_name(ndd, nd_label, nsblk->alt_name); nsl_set_flags(ndd, nd_label, NSLABEL_FLAG_LOCAL); @@ -1161,8 +1159,7 @@ static int __blk_label_update(struct nd_region *nd_region, if (!nd_label) continue; nlabel++; - memcpy(uuid, nd_label->uuid, NSLABEL_UUID_LEN); - if (memcmp(uuid, nsblk->uuid, NSLABEL_UUID_LEN) != 0) + if (!nsl_uuid_equal(ndd, nd_label, nsblk->uuid)) continue; nlabel--; list_move(&label_ent->list, &list); @@ -1192,8 +1189,7 @@ static int __blk_label_update(struct nd_region *nd_region, } for_each_clear_bit_le(slot, free, nslot) { nd_label = to_label(ndd, slot); - memcpy(uuid, nd_label->uuid, NSLABEL_UUID_LEN); - if (memcmp(uuid, nsblk->uuid, NSLABEL_UUID_LEN) != 0) + if (!nsl_uuid_equal(ndd, nd_label, nsblk->uuid)) continue; res = to_resource(ndd, nd_label); res->flags &= ~DPA_RESOURCE_ADJUSTED; @@ -1273,12 +1269,11 @@ static int init_labels(struct nd_mapping *nd_mapping, int num_labels) return max(num_labels, old_num_labels); } -static int del_labels(struct nd_mapping *nd_mapping, u8 *uuid) +static int del_labels(struct nd_mapping *nd_mapping, uuid_t *uuid) { struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); struct nd_label_ent *label_ent, *e; struct nd_namespace_index *nsindex; - u8 label_uuid[NSLABEL_UUID_LEN]; unsigned long *free; LIST_HEAD(list); u32 nslot, slot; @@ -1298,8 +1293,7 @@ static int del_labels(struct nd_mapping *nd_mapping, u8 *uuid) if (!nd_label) continue; active++; - memcpy(label_uuid, nd_label->uuid, NSLABEL_UUID_LEN); - if (memcmp(label_uuid, uuid, NSLABEL_UUID_LEN) != 0) + if (!nsl_uuid_equal(ndd, nd_label, uuid)) continue; active--; slot = to_slot(ndd, nd_label); diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index 4cec171c934d..1415d543c3e3 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -51,7 +51,7 @@ static bool is_namespace_io(const struct device *dev); static int is_uuid_busy(struct device *dev, void *data) { - u8 *uuid1 = data, *uuid2 = NULL; + uuid_t *uuid1 = data, *uuid2 = NULL; if (is_namespace_pmem(dev)) { struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); @@ -71,7 +71,7 @@ static int is_uuid_busy(struct device *dev, void *data) uuid2 = nd_pfn->uuid; } - if (uuid2 && memcmp(uuid1, uuid2, NSLABEL_UUID_LEN) == 0) + if (uuid2 && uuid_equal(uuid1, uuid2)) return -EBUSY; return 0; @@ -89,7 +89,7 @@ static int is_namespace_uuid_busy(struct device *dev, void *data) * @dev: any device on a nvdimm_bus * @uuid: uuid to check */ -bool nd_is_uuid_unique(struct device *dev, u8 *uuid) +bool nd_is_uuid_unique(struct device *dev, uuid_t *uuid) { struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev); @@ -192,12 +192,10 @@ const char *nvdimm_namespace_disk_name(struct nd_namespace_common *ndns, } EXPORT_SYMBOL(nvdimm_namespace_disk_name); -const u8 *nd_dev_to_uuid(struct device *dev) +const uuid_t *nd_dev_to_uuid(struct device *dev) { - static const u8 null_uuid[16]; - if (!dev) - return null_uuid; + return &uuid_null; if (is_namespace_pmem(dev)) { struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); @@ -208,7 +206,7 @@ const u8 *nd_dev_to_uuid(struct device *dev) return nsblk->uuid; } else - return null_uuid; + return &uuid_null; } EXPORT_SYMBOL(nd_dev_to_uuid); @@ -938,7 +936,8 @@ static void nd_namespace_pmem_set_resource(struct nd_region *nd_region, res->end = res->start + size - 1; } -static bool uuid_not_set(const u8 *uuid, struct device *dev, const char *where) +static bool uuid_not_set(const uuid_t *uuid, struct device *dev, + const char *where) { if (!uuid) { dev_dbg(dev, "%s: uuid not set\n", where); @@ -957,7 +956,7 @@ static ssize_t __size_store(struct device *dev, unsigned long long val) struct nd_label_id label_id; u32 flags = 0, remainder; int rc, i, id = -1; - u8 *uuid = NULL; + uuid_t *uuid = NULL; if (dev->driver || ndns->claim) return -EBUSY; @@ -1050,7 +1049,7 @@ static ssize_t size_store(struct device *dev, { struct nd_region *nd_region = to_nd_region(dev->parent); unsigned long long val; - u8 **uuid = NULL; + uuid_t **uuid = NULL; int rc; rc = kstrtoull(buf, 0, &val); @@ -1147,7 +1146,7 @@ static ssize_t size_show(struct device *dev, } static DEVICE_ATTR(size, 0444, size_show, size_store); -static u8 *namespace_to_uuid(struct device *dev) +static uuid_t *namespace_to_uuid(struct device *dev) { if (is_namespace_pmem(dev)) { struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); @@ -1161,10 +1160,10 @@ static u8 *namespace_to_uuid(struct device *dev) return ERR_PTR(-ENXIO); } -static ssize_t uuid_show(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t uuid_show(struct device *dev, struct device_attribute *attr, + char *buf) { - u8 *uuid = namespace_to_uuid(dev); + uuid_t *uuid = namespace_to_uuid(dev); if (IS_ERR(uuid)) return PTR_ERR(uuid); @@ -1181,7 +1180,8 @@ static ssize_t uuid_show(struct device *dev, * @old_uuid: reference to the uuid storage location in the namespace object */ static int namespace_update_uuid(struct nd_region *nd_region, - struct device *dev, u8 *new_uuid, u8 **old_uuid) + struct device *dev, uuid_t *new_uuid, + uuid_t **old_uuid) { u32 flags = is_namespace_blk(dev) ? NSLABEL_FLAG_LOCAL : 0; struct nd_label_id old_label_id; @@ -1231,10 +1231,12 @@ static int namespace_update_uuid(struct nd_region *nd_region, list_for_each_entry(label_ent, &nd_mapping->labels, list) { struct nd_namespace_label *nd_label = label_ent->label; struct nd_label_id label_id; + uuid_t uuid; if (!nd_label) continue; - nd_label_gen_id(&label_id, nd_label->uuid, + nsl_get_uuid(ndd, nd_label, &uuid); + nd_label_gen_id(&label_id, &uuid, nsl_get_flags(ndd, nd_label)); if (strcmp(old_label_id.id, label_id.id) == 0) set_bit(ND_LABEL_REAP, &label_ent->flags); @@ -1251,9 +1253,9 @@ static ssize_t uuid_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct nd_region *nd_region = to_nd_region(dev->parent); - u8 *uuid = NULL; + uuid_t *uuid = NULL; + uuid_t **ns_uuid; ssize_t rc = 0; - u8 **ns_uuid; if (is_namespace_pmem(dev)) { struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); @@ -1378,8 +1380,8 @@ static ssize_t dpa_extents_show(struct device *dev, { struct nd_region *nd_region = to_nd_region(dev->parent); struct nd_label_id label_id; + uuid_t *uuid = NULL; int count = 0, i; - u8 *uuid = NULL; u32 flags = 0; nvdimm_bus_lock(dev); @@ -1831,8 +1833,8 @@ static struct device **create_namespace_io(struct nd_region *nd_region) return devs; } -static bool has_uuid_at_pos(struct nd_region *nd_region, u8 *uuid, - u64 cookie, u16 pos) +static bool has_uuid_at_pos(struct nd_region *nd_region, const uuid_t *uuid, + u64 cookie, u16 pos) { struct nd_namespace_label *found = NULL; int i; @@ -1856,7 +1858,7 @@ static bool has_uuid_at_pos(struct nd_region *nd_region, u8 *uuid, if (!nsl_validate_isetcookie(ndd, nd_label, cookie)) continue; - if (memcmp(nd_label->uuid, uuid, NSLABEL_UUID_LEN) != 0) + if (!nsl_uuid_equal(ndd, nd_label, uuid)) continue; if (!nsl_validate_type_guid(ndd, nd_label, @@ -1881,7 +1883,7 @@ static bool has_uuid_at_pos(struct nd_region *nd_region, u8 *uuid, return found != NULL; } -static int select_pmem_id(struct nd_region *nd_region, u8 *pmem_id) +static int select_pmem_id(struct nd_region *nd_region, const uuid_t *pmem_id) { int i; @@ -1900,7 +1902,7 @@ static int select_pmem_id(struct nd_region *nd_region, u8 *pmem_id) nd_label = label_ent->label; if (!nd_label) continue; - if (memcmp(nd_label->uuid, pmem_id, NSLABEL_UUID_LEN) == 0) + if (nsl_uuid_equal(ndd, nd_label, pmem_id)) break; nd_label = NULL; } @@ -1923,7 +1925,8 @@ static int select_pmem_id(struct nd_region *nd_region, u8 *pmem_id) /* pass */; else { dev_dbg(&nd_region->dev, "%s invalid label for %pUb\n", - dev_name(ndd->dev), nd_label->uuid); + dev_name(ndd->dev), + nsl_uuid_raw(ndd, nd_label)); return -EINVAL; } @@ -1953,6 +1956,7 @@ static struct device *create_namespace_pmem(struct nd_region *nd_region, resource_size_t size = 0; struct resource *res; struct device *dev; + uuid_t uuid; int rc = 0; u16 i; @@ -1963,12 +1967,12 @@ static struct device *create_namespace_pmem(struct nd_region *nd_region, if (!nsl_validate_isetcookie(ndd, nd_label, cookie)) { dev_dbg(&nd_region->dev, "invalid cookie in label: %pUb\n", - nd_label->uuid); + nsl_uuid_raw(ndd, nd_label)); if (!nsl_validate_isetcookie(ndd, nd_label, altcookie)) return ERR_PTR(-EAGAIN); dev_dbg(&nd_region->dev, "valid altcookie in label: %pUb\n", - nd_label->uuid); + nsl_uuid_raw(ndd, nd_label)); } nspm = kzalloc(sizeof(*nspm), GFP_KERNEL); @@ -1984,9 +1988,12 @@ static struct device *create_namespace_pmem(struct nd_region *nd_region, res->flags = IORESOURCE_MEM; for (i = 0; i < nd_region->ndr_mappings; i++) { - if (has_uuid_at_pos(nd_region, nd_label->uuid, cookie, i)) + uuid_t uuid; + + nsl_get_uuid(ndd, nd_label, &uuid); + if (has_uuid_at_pos(nd_region, &uuid, cookie, i)) continue; - if (has_uuid_at_pos(nd_region, nd_label->uuid, altcookie, i)) + if (has_uuid_at_pos(nd_region, &uuid, altcookie, i)) continue; break; } @@ -2000,7 +2007,7 @@ static struct device *create_namespace_pmem(struct nd_region *nd_region, * find a dimm with two instances of the same uuid. */ dev_err(&nd_region->dev, "%s missing label for %pUb\n", - nvdimm_name(nvdimm), nd_label->uuid); + nvdimm_name(nvdimm), nsl_uuid_raw(ndd, nd_label)); rc = -EINVAL; goto err; } @@ -2013,7 +2020,8 @@ static struct device *create_namespace_pmem(struct nd_region *nd_region, * the dimm being enabled (i.e. nd_label_reserve_dpa() * succeeded). */ - rc = select_pmem_id(nd_region, nd_label->uuid); + nsl_get_uuid(ndd, nd_label, &uuid); + rc = select_pmem_id(nd_region, &uuid); if (rc) goto err; @@ -2039,8 +2047,8 @@ static struct device *create_namespace_pmem(struct nd_region *nd_region, WARN_ON(nspm->alt_name || nspm->uuid); nspm->alt_name = kmemdup(nsl_ref_name(ndd, label0), NSLABEL_NAME_LEN, GFP_KERNEL); - nspm->uuid = kmemdup((void __force *) label0->uuid, - NSLABEL_UUID_LEN, GFP_KERNEL); + nsl_get_uuid(ndd, label0, &uuid); + nspm->uuid = kmemdup(&uuid, sizeof(uuid_t), GFP_KERNEL); nspm->lbasize = nsl_get_lbasize(ndd, label0); nspm->nsio.common.claim_class = nsl_get_claim_class(ndd, label0); @@ -2217,15 +2225,15 @@ static int add_namespace_resource(struct nd_region *nd_region, int i; for (i = 0; i < count; i++) { - u8 *uuid = namespace_to_uuid(devs[i]); + uuid_t *uuid = namespace_to_uuid(devs[i]); struct resource *res; - if (IS_ERR_OR_NULL(uuid)) { + if (IS_ERR(uuid)) { WARN_ON(1); continue; } - if (memcmp(uuid, nd_label->uuid, NSLABEL_UUID_LEN) != 0) + if (!nsl_uuid_equal(ndd, nd_label, uuid)) continue; if (is_namespace_blk(devs[i])) { res = nsblk_add_resource(nd_region, ndd, @@ -2236,8 +2244,8 @@ static int add_namespace_resource(struct nd_region *nd_region, nd_dbg_dpa(nd_region, ndd, res, "%d assign\n", count); } else { dev_err(&nd_region->dev, - "error: conflicting extents for uuid: %pUb\n", - nd_label->uuid); + "error: conflicting extents for uuid: %pUb\n", + uuid); return -ENXIO; } break; @@ -2257,6 +2265,7 @@ static struct device *create_namespace_blk(struct nd_region *nd_region, char name[NSLABEL_NAME_LEN]; struct device *dev = NULL; struct resource *res; + uuid_t uuid; if (!nsl_validate_type_guid(ndd, nd_label, &nd_set->type_guid)) return ERR_PTR(-EAGAIN); @@ -2271,7 +2280,8 @@ static struct device *create_namespace_blk(struct nd_region *nd_region, dev->parent = &nd_region->dev; nsblk->id = -1; nsblk->lbasize = nsl_get_lbasize(ndd, nd_label); - nsblk->uuid = kmemdup(nd_label->uuid, NSLABEL_UUID_LEN, GFP_KERNEL); + nsl_get_uuid(ndd, nd_label, &uuid); + nsblk->uuid = kmemdup(&uuid, sizeof(uuid_t), GFP_KERNEL); nsblk->common.claim_class = nsl_get_claim_class(ndd, nd_label); if (!nsblk->uuid) goto blk_err; diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h index 564faa36a3ca..a11850dd475d 100644 --- a/drivers/nvdimm/nd-core.h +++ b/drivers/nvdimm/nd-core.h @@ -126,8 +126,9 @@ void nvdimm_bus_destroy_ndctl(struct nvdimm_bus *nvdimm_bus); void nd_synchronize(void); void __nd_device_register(struct device *dev); struct nd_label_id; -char *nd_label_gen_id(struct nd_label_id *label_id, u8 *uuid, u32 flags); -bool nd_is_uuid_unique(struct device *dev, u8 *uuid); +char *nd_label_gen_id(struct nd_label_id *label_id, const uuid_t *uuid, + u32 flags); +bool nd_is_uuid_unique(struct device *dev, uuid_t *uuid); struct nd_region; struct nvdimm_drvdata; struct nd_mapping; diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index 5467ebbb4a6b..ec3c9aad7f50 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -177,6 +177,38 @@ static inline void nsl_set_lbasize(struct nvdimm_drvdata *ndd, nd_label->lbasize = __cpu_to_le64(lbasize); } +static inline const uuid_t *nsl_get_uuid(struct nvdimm_drvdata *ndd, + struct nd_namespace_label *nd_label, + uuid_t *uuid) +{ + import_uuid(uuid, nd_label->uuid); + return uuid; +} + +static inline const uuid_t *nsl_set_uuid(struct nvdimm_drvdata *ndd, + struct nd_namespace_label *nd_label, + const uuid_t *uuid) +{ + export_uuid(nd_label->uuid, uuid); + return uuid; +} + +static inline bool nsl_uuid_equal(struct nvdimm_drvdata *ndd, + struct nd_namespace_label *nd_label, + const uuid_t *uuid) +{ + uuid_t tmp; + + import_uuid(&tmp, nd_label->uuid); + return uuid_equal(&tmp, uuid); +} + +static inline const u8 *nsl_uuid_raw(struct nvdimm_drvdata *ndd, + struct nd_namespace_label *nd_label) +{ + return nd_label->uuid; +} + bool nsl_validate_blk_isetcookie(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label, u64 isetcookie); @@ -335,7 +367,7 @@ struct nd_btt { struct btt *btt; unsigned long lbasize; u64 size; - u8 *uuid; + uuid_t *uuid; int id; int initial_offset; u16 version_major; @@ -350,7 +382,7 @@ enum nd_pfn_mode { struct nd_pfn { int id; - u8 *uuid; + uuid_t *uuid; struct device dev; unsigned long align; unsigned long npfns; @@ -378,7 +410,7 @@ void wait_nvdimm_bus_probe_idle(struct device *dev); void nd_device_register(struct device *dev); void nd_device_unregister(struct device *dev, enum nd_async_mode mode); void nd_device_notify(struct device *dev, enum nvdimm_event event); -int nd_uuid_store(struct device *dev, u8 **uuid_out, const char *buf, +int nd_uuid_store(struct device *dev, uuid_t **uuid_out, const char *buf, size_t len); ssize_t nd_size_select_show(unsigned long current_size, const unsigned long *supported, char *buf); @@ -561,6 +593,6 @@ static inline bool is_bad_pmem(struct badblocks *bb, sector_t sector, return false; } resource_size_t nd_namespace_blk_validate(struct nd_namespace_blk *nsblk); -const u8 *nd_dev_to_uuid(struct device *dev); +const uuid_t *nd_dev_to_uuid(struct device *dev); bool pmem_should_map_pages(struct device *dev); #endif /* __ND_H__ */ diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c index b499df630d4d..58eda16f5c53 100644 --- a/drivers/nvdimm/pfn_devs.c +++ b/drivers/nvdimm/pfn_devs.c @@ -452,7 +452,7 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig) unsigned long align, start_pad; struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb; struct nd_namespace_common *ndns = nd_pfn->ndns; - const u8 *parent_uuid = nd_dev_to_uuid(&ndns->dev); + const uuid_t *parent_uuid = nd_dev_to_uuid(&ndns->dev); if (!pfn_sb || !ndns) return -ENODEV; diff --git a/include/linux/nd.h b/include/linux/nd.h index ee9ad76afbba..8a8c63edb1b2 100644 --- a/include/linux/nd.h +++ b/include/linux/nd.h @@ -88,7 +88,7 @@ struct nd_namespace_pmem { struct nd_namespace_io nsio; unsigned long lbasize; char *alt_name; - u8 *uuid; + uuid_t *uuid; int id; }; @@ -105,7 +105,7 @@ struct nd_namespace_pmem { struct nd_namespace_blk { struct nd_namespace_common common; char *alt_name; - u8 *uuid; + uuid_t *uuid; int id; unsigned long lbasize; resource_size_t size; From 8172db92527c936c638b52274fbd06a0a624a56b Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 8 Sep 2021 22:11:42 -0700 Subject: [PATCH 040/587] libnvdimm/label: Add a helper for nlabel validation In the CXL namespace label there is no need for nlabel since that is inferred from the region. Add a helper that moves nsl_get_label() behind a helper that validates the number of labels relative to the region. Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/163116430293.2460985.12693942353621355232.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/nvdimm/namespace_devs.c | 5 ++--- drivers/nvdimm/nd.h | 7 +++++++ 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index 1415d543c3e3..b57a2d36c517 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -1848,12 +1848,11 @@ static bool has_uuid_at_pos(struct nd_region *nd_region, const uuid_t *uuid, list_for_each_entry(label_ent, &nd_mapping->labels, list) { struct nd_namespace_label *nd_label = label_ent->label; - u16 position, nlabel; + u16 position; if (!nd_label) continue; position = nsl_get_position(ndd, nd_label); - nlabel = nsl_get_nlabel(ndd, nd_label); if (!nsl_validate_isetcookie(ndd, nd_label, cookie)) continue; @@ -1870,7 +1869,7 @@ static bool has_uuid_at_pos(struct nd_region *nd_region, const uuid_t *uuid, return false; } found_uuid = true; - if (nlabel != nd_region->ndr_mappings) + if (!nsl_validate_nlabel(nd_region, ndd, nd_label)) continue; if (position != pos) continue; diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index ec3c9aad7f50..036638bdb7e3 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -342,6 +342,13 @@ struct nd_region { struct nd_mapping mapping[]; }; +static inline bool nsl_validate_nlabel(struct nd_region *nd_region, + struct nvdimm_drvdata *ndd, + struct nd_namespace_label *nd_label) +{ + return nsl_get_nlabel(ndd, nd_label) == nd_region->ndr_mappings; +} + struct nd_blk_region { int (*enable)(struct nvdimm_bus *nvdimm_bus, struct device *dev); int (*do_io)(struct nd_blk_region *ndbr, resource_size_t dpa, From 42e192aa9891f196bc1adaaeab9a23d975618e5e Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 8 Sep 2021 22:11:48 -0700 Subject: [PATCH 041/587] libnvdimm/labels: Introduce the concept of multi-range namespace labels The CXL specification defines a mechanism for namespaces to be comprised of multiple dis-contiguous ranges. Introduce that concept to the legacy NVDIMM namespace implementation with a new nsl_set_nrange() helper, that sets the number of ranges to 1. Once the NVDIMM subsystem supports CXL labels and updates its namespace capacity provisioning for dis-contiguous support nsl_set_nrange() can be updated, but in the meantime CXL label validation requires nrange be non-zero. Reported-by: Jonathan Cameron Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/163116430804.2460985.5482188351381597529.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/nvdimm/label.c | 1 + drivers/nvdimm/nd.h | 13 +++++++++++++ 2 files changed, 14 insertions(+) diff --git a/drivers/nvdimm/label.c b/drivers/nvdimm/label.c index e7fdb718ebf0..7832b190efd7 100644 --- a/drivers/nvdimm/label.c +++ b/drivers/nvdimm/label.c @@ -856,6 +856,7 @@ static int __pmem_label_update(struct nd_region *nd_region, nsl_set_name(ndd, nd_label, nspm->alt_name); nsl_set_flags(ndd, nd_label, flags); nsl_set_nlabel(ndd, nd_label, nd_region->ndr_mappings); + nsl_set_nrange(ndd, nd_label, 1); nsl_set_position(ndd, nd_label, pos); nsl_set_isetcookie(ndd, nd_label, cookie); nsl_set_rawsize(ndd, nd_label, resource_size(res)); diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index 036638bdb7e3..d57f95a48fe1 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -164,6 +164,19 @@ static inline void nsl_set_nlabel(struct nvdimm_drvdata *ndd, nd_label->nlabel = __cpu_to_le16(nlabel); } +static inline u16 nsl_get_nrange(struct nvdimm_drvdata *ndd, + struct nd_namespace_label *nd_label) +{ + /* EFI labels do not have an nrange field */ + return 1; +} + +static inline void nsl_set_nrange(struct nvdimm_drvdata *ndd, + struct nd_namespace_label *nd_label, + u16 nrange) +{ +} + static inline u64 nsl_get_lbasize(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label) { From 999c993a85f1cab8c37752db71b1f841a5d2c190 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 8 Sep 2021 22:11:53 -0700 Subject: [PATCH 042/587] libnvdimm/labels: Fix kernel-doc for label.h Clean up existing kernel-doc warnings before adding new CXL label data structures. drivers/nvdimm/label.h:66: warning: Function parameter or member 'labelsize' not described in 'nd_namespace_index' drivers/nvdimm/label.h:66: warning: Function parameter or member 'free' not described in 'nd_namespace_index' drivers/nvdimm/label.h:103: warning: Function parameter or member 'align' not described in 'nd_namespace_label' drivers/nvdimm/label.h:103: warning: Function parameter or member 'reserved' not described in 'nd_namespace_label' drivers/nvdimm/label.h:103: warning: Function parameter or member 'type_guid' not described in 'nd_namespace_label' drivers/nvdimm/label.h:103: warning: Function parameter or member 'abstraction_guid' not described in 'nd_namespace_label' drivers/nvdimm/label.h:103: warning: Function parameter or member 'reserved2' not described in 'nd_namespace_label' drivers/nvdimm/label.h:103: warning: Function parameter or member 'checksum' not described in 'nd_namespace_label' Reported-by: Jonathan Cameron Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/163116431381.2460985.6990754901097922099.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/nvdimm/label.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/nvdimm/label.h b/drivers/nvdimm/label.h index 31f94fad7b92..7fa757d47846 100644 --- a/drivers/nvdimm/label.h +++ b/drivers/nvdimm/label.h @@ -34,6 +34,7 @@ enum { * struct nd_namespace_index - label set superblock * @sig: NAMESPACE_INDEX\0 * @flags: placeholder + * @labelsize: log2 size (v1 labels 128 bytes v2 labels 256 bytes) * @seq: sequence number for this index * @myoff: offset of this index in label area * @mysize: size of this index struct @@ -43,7 +44,7 @@ enum { * @major: label area major version * @minor: label area minor version * @checksum: fletcher64 of all fields - * @free[0]: bitmap, nlabel bits + * @free: bitmap, nlabel bits * * The size of free[] is rounded up so the total struct size is a * multiple of NSINDEX_ALIGN bytes. Any bits this allocates beyond @@ -77,7 +78,12 @@ struct nd_namespace_index { * @dpa: DPA of NVM range on this DIMM * @rawsize: size of namespace * @slot: slot of this label in label area - * @unused: must be zero + * @align: physical address alignment of the namespace + * @reserved: reserved + * @type_guid: copy of struct acpi_nfit_system_address.range_guid + * @abstraction_guid: personality id (btt, btt2, fsdax, devdax....) + * @reserved2: reserved + * @checksum: fletcher64 sum of this object */ struct nd_namespace_label { u8 uuid[NSLABEL_UUID_LEN]; From 540ccaa2e4dd6d44dcd9305a007078fda597af02 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 8 Sep 2021 22:11:58 -0700 Subject: [PATCH 043/587] libnvdimm/label: Define CXL region labels Add a definition of the CXL 2.0 region label format. Note this is done as a separate patch to make the next patch that adds namespace label support easier to read. Reported-by: Jonathan Cameron Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/163116431893.2460985.4003511000574373922.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/nvdimm/label.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) diff --git a/drivers/nvdimm/label.h b/drivers/nvdimm/label.h index 7fa757d47846..0519aacc2926 100644 --- a/drivers/nvdimm/label.h +++ b/drivers/nvdimm/label.h @@ -66,6 +66,38 @@ struct nd_namespace_index { u8 free[]; }; +/** + * struct cxl_region_label - CXL 2.0 Table 211 + * @type: uuid identifying this label format (region) + * @uuid: uuid for the region this label describes + * @flags: NSLABEL_FLAG_UPDATING (all other flags reserved) + * @nlabel: 1 per interleave-way in the region + * @position: this label's position in the set + * @dpa: start address in device-local capacity for this label + * @rawsize: size of this label's contribution to region + * @hpa: mandatory system physical address to map this region + * @slot: slot id of this label in label area + * @ig: interleave granularity (1 << @ig) * 256 bytes + * @align: alignment in SZ_256M blocks + * @reserved: reserved + * @checksum: fletcher64 sum of this label + */ +struct cxl_region_label { + u8 type[NSLABEL_UUID_LEN]; + u8 uuid[NSLABEL_UUID_LEN]; + __le32 flags; + __le16 nlabel; + __le16 position; + __le64 dpa; + __le64 rawsize; + __le64 hpa; + __le32 slot; + __le32 ig; + __le32 align; + u8 reserved[0xac]; + __le64 checksum; +}; + /** * struct nd_namespace_label - namespace superblock * @uuid: UUID per RFC 4122 From 5af96835e4dafd21a766fd7a8e583ec7abbfe98c Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 8 Sep 2021 22:12:04 -0700 Subject: [PATCH 044/587] libnvdimm/labels: Introduce CXL labels Now that all of use sites of label data have been converted to nsl_* helpers, introduce the CXL label format. The ->cxl flag in nvdimm_drvdata indicates the label format the device expects. A follow-on patch allows a bus provider to select the label style. Note that the EFI definition of the labels represents the Linux "claim class" with a GUID. The CXL definition of the labels stores the same identifier in UUID byte order. Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/163116432405.2460985.5547867384570123403.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/nvdimm/label.c | 104 +++++++++++++++++++++++++------ drivers/nvdimm/label.h | 52 +++++++++++++++- drivers/nvdimm/nd.h | 135 ++++++++++++++++++++++++++++++++--------- 3 files changed, 241 insertions(+), 50 deletions(-) diff --git a/drivers/nvdimm/label.c b/drivers/nvdimm/label.c index 7832b190efd7..5ec9a4023df9 100644 --- a/drivers/nvdimm/label.c +++ b/drivers/nvdimm/label.c @@ -17,6 +17,14 @@ static guid_t nvdimm_btt2_guid; static guid_t nvdimm_pfn_guid; static guid_t nvdimm_dax_guid; +static uuid_t nvdimm_btt_uuid; +static uuid_t nvdimm_btt2_uuid; +static uuid_t nvdimm_pfn_uuid; +static uuid_t nvdimm_dax_uuid; + +static uuid_t cxl_region_uuid; +static uuid_t cxl_namespace_uuid; + static const char NSINDEX_SIGNATURE[] = "NAMESPACE_INDEX\0"; static u32 best_seq(u32 a, u32 b) @@ -352,7 +360,7 @@ static bool nsl_validate_checksum(struct nvdimm_drvdata *ndd, { u64 sum, sum_save; - if (!namespace_label_has(ndd, checksum)) + if (!ndd->cxl && !efi_namespace_label_has(ndd, checksum)) return true; sum_save = nsl_get_checksum(ndd, nd_label); @@ -367,7 +375,7 @@ static void nsl_calculate_checksum(struct nvdimm_drvdata *ndd, { u64 sum; - if (!namespace_label_has(ndd, checksum)) + if (!ndd->cxl && !efi_namespace_label_has(ndd, checksum)) return; nsl_set_checksum(ndd, nd_label, 0); sum = nd_fletcher64(nd_label, sizeof_namespace_label(ndd), 1); @@ -725,7 +733,7 @@ static unsigned long nd_label_offset(struct nvdimm_drvdata *ndd, - (unsigned long) to_namespace_index(ndd, 0); } -static enum nvdimm_claim_class to_nvdimm_cclass(guid_t *guid) +static enum nvdimm_claim_class guid_to_nvdimm_cclass(guid_t *guid) { if (guid_equal(guid, &nvdimm_btt_guid)) return NVDIMM_CCLASS_BTT; @@ -741,6 +749,23 @@ static enum nvdimm_claim_class to_nvdimm_cclass(guid_t *guid) return NVDIMM_CCLASS_UNKNOWN; } +/* CXL labels store UUIDs instead of GUIDs for the same data */ +static enum nvdimm_claim_class uuid_to_nvdimm_cclass(uuid_t *uuid) +{ + if (uuid_equal(uuid, &nvdimm_btt_uuid)) + return NVDIMM_CCLASS_BTT; + else if (uuid_equal(uuid, &nvdimm_btt2_uuid)) + return NVDIMM_CCLASS_BTT2; + else if (uuid_equal(uuid, &nvdimm_pfn_uuid)) + return NVDIMM_CCLASS_PFN; + else if (uuid_equal(uuid, &nvdimm_dax_uuid)) + return NVDIMM_CCLASS_DAX; + else if (uuid_equal(uuid, &uuid_null)) + return NVDIMM_CCLASS_NONE; + + return NVDIMM_CCLASS_UNKNOWN; +} + static const guid_t *to_abstraction_guid(enum nvdimm_claim_class claim_class, guid_t *target) { @@ -762,6 +787,28 @@ static const guid_t *to_abstraction_guid(enum nvdimm_claim_class claim_class, return &guid_null; } +/* CXL labels store UUIDs instead of GUIDs for the same data */ +static const uuid_t *to_abstraction_uuid(enum nvdimm_claim_class claim_class, + uuid_t *target) +{ + if (claim_class == NVDIMM_CCLASS_BTT) + return &nvdimm_btt_uuid; + else if (claim_class == NVDIMM_CCLASS_BTT2) + return &nvdimm_btt2_uuid; + else if (claim_class == NVDIMM_CCLASS_PFN) + return &nvdimm_pfn_uuid; + else if (claim_class == NVDIMM_CCLASS_DAX) + return &nvdimm_dax_uuid; + else if (claim_class == NVDIMM_CCLASS_UNKNOWN) { + /* + * If we're modifying a namespace for which we don't + * know the claim_class, don't touch the existing uuid. + */ + return target; + } else + return &uuid_null; +} + static void reap_victim(struct nd_mapping *nd_mapping, struct nd_label_ent *victim) { @@ -776,18 +823,18 @@ static void reap_victim(struct nd_mapping *nd_mapping, static void nsl_set_type_guid(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label, guid_t *guid) { - if (namespace_label_has(ndd, type_guid)) - guid_copy(&nd_label->type_guid, guid); + if (efi_namespace_label_has(ndd, type_guid)) + guid_copy(&nd_label->efi.type_guid, guid); } bool nsl_validate_type_guid(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label, guid_t *guid) { - if (!namespace_label_has(ndd, type_guid)) + if (ndd->cxl || !efi_namespace_label_has(ndd, type_guid)) return true; - if (!guid_equal(&nd_label->type_guid, guid)) { + if (!guid_equal(&nd_label->efi.type_guid, guid)) { dev_dbg(ndd->dev, "expect type_guid %pUb got %pUb\n", guid, - &nd_label->type_guid); + &nd_label->efi.type_guid); return false; } return true; @@ -797,19 +844,34 @@ static void nsl_set_claim_class(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label, enum nvdimm_claim_class claim_class) { - if (!namespace_label_has(ndd, abstraction_guid)) + if (ndd->cxl) { + uuid_t uuid; + + import_uuid(&uuid, nd_label->cxl.abstraction_uuid); + export_uuid(nd_label->cxl.abstraction_uuid, + to_abstraction_uuid(claim_class, &uuid)); return; - guid_copy(&nd_label->abstraction_guid, + } + + if (!efi_namespace_label_has(ndd, abstraction_guid)) + return; + guid_copy(&nd_label->efi.abstraction_guid, to_abstraction_guid(claim_class, - &nd_label->abstraction_guid)); + &nd_label->efi.abstraction_guid)); } enum nvdimm_claim_class nsl_get_claim_class(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label) { - if (!namespace_label_has(ndd, abstraction_guid)) + if (ndd->cxl) { + uuid_t uuid; + + import_uuid(&uuid, nd_label->cxl.abstraction_uuid); + return uuid_to_nvdimm_cclass(&uuid); + } + if (!efi_namespace_label_has(ndd, abstraction_guid)) return NVDIMM_CCLASS_NONE; - return to_nvdimm_cclass(&nd_label->abstraction_guid); + return guid_to_nvdimm_cclass(&nd_label->efi.abstraction_guid); } static int __pmem_label_update(struct nd_region *nd_region, @@ -942,7 +1004,7 @@ static void nsl_set_blk_isetcookie(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label, u64 isetcookie) { - if (namespace_label_has(ndd, type_guid)) { + if (efi_namespace_label_has(ndd, type_guid)) { nsl_set_isetcookie(ndd, nd_label, isetcookie); return; } @@ -953,7 +1015,7 @@ bool nsl_validate_blk_isetcookie(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label, u64 isetcookie) { - if (!namespace_label_has(ndd, type_guid)) + if (!efi_namespace_label_has(ndd, type_guid)) return true; if (nsl_get_isetcookie(ndd, nd_label) != isetcookie) { @@ -969,7 +1031,7 @@ static void nsl_set_blk_nlabel(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label, int nlabel, bool first) { - if (!namespace_label_has(ndd, type_guid)) { + if (!efi_namespace_label_has(ndd, type_guid)) { nsl_set_nlabel(ndd, nd_label, 0); /* N/A */ return; } @@ -980,7 +1042,7 @@ static void nsl_set_blk_position(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label, bool first) { - if (!namespace_label_has(ndd, type_guid)) { + if (!efi_namespace_label_has(ndd, type_guid)) { nsl_set_position(ndd, nd_label, 0); return; } @@ -1390,5 +1452,13 @@ int __init nd_label_init(void) WARN_ON(guid_parse(NVDIMM_PFN_GUID, &nvdimm_pfn_guid)); WARN_ON(guid_parse(NVDIMM_DAX_GUID, &nvdimm_dax_guid)); + WARN_ON(uuid_parse(NVDIMM_BTT_GUID, &nvdimm_btt_uuid)); + WARN_ON(uuid_parse(NVDIMM_BTT2_GUID, &nvdimm_btt2_uuid)); + WARN_ON(uuid_parse(NVDIMM_PFN_GUID, &nvdimm_pfn_uuid)); + WARN_ON(uuid_parse(NVDIMM_DAX_GUID, &nvdimm_dax_uuid)); + + WARN_ON(uuid_parse(CXL_REGION_UUID, &cxl_region_uuid)); + WARN_ON(uuid_parse(CXL_NAMESPACE_UUID, &cxl_namespace_uuid)); + return 0; } diff --git a/drivers/nvdimm/label.h b/drivers/nvdimm/label.h index 0519aacc2926..8ee248fc214f 100644 --- a/drivers/nvdimm/label.h +++ b/drivers/nvdimm/label.h @@ -99,7 +99,7 @@ struct cxl_region_label { }; /** - * struct nd_namespace_label - namespace superblock + * struct nvdimm_efi_label - namespace superblock * @uuid: UUID per RFC 4122 * @name: optional name (NULL-terminated) * @flags: see NSLABEL_FLAG_* @@ -117,7 +117,7 @@ struct cxl_region_label { * @reserved2: reserved * @checksum: fletcher64 sum of this object */ -struct nd_namespace_label { +struct nvdimm_efi_label { u8 uuid[NSLABEL_UUID_LEN]; u8 name[NSLABEL_NAME_LEN]; __le32 flags; @@ -130,7 +130,7 @@ struct nd_namespace_label { __le32 slot; /* * Accessing fields past this point should be gated by a - * namespace_label_has() check. + * efi_namespace_label_has() check. */ u8 align; u8 reserved[3]; @@ -140,11 +140,57 @@ struct nd_namespace_label { __le64 checksum; }; +/** + * struct nvdimm_cxl_label - CXL 2.0 Table 212 + * @type: uuid identifying this label format (namespace) + * @uuid: uuid for the namespace this label describes + * @name: friendly name for the namespace + * @flags: NSLABEL_FLAG_UPDATING (all other flags reserved) + * @nrange: discontiguous namespace support + * @position: this label's position in the set + * @dpa: start address in device-local capacity for this label + * @rawsize: size of this label's contribution to namespace + * @slot: slot id of this label in label area + * @align: alignment in SZ_256M blocks + * @region_uuid: host interleave set identifier + * @abstraction_uuid: personality driver for this namespace + * @lbasize: address geometry for disk-like personalities + * @reserved: reserved + * @checksum: fletcher64 sum of this label + */ +struct nvdimm_cxl_label { + u8 type[NSLABEL_UUID_LEN]; + u8 uuid[NSLABEL_UUID_LEN]; + u8 name[NSLABEL_NAME_LEN]; + __le32 flags; + __le16 nrange; + __le16 position; + __le64 dpa; + __le64 rawsize; + __le32 slot; + __le32 align; + u8 region_uuid[16]; + u8 abstraction_uuid[16]; + __le16 lbasize; + u8 reserved[0x56]; + __le64 checksum; +}; + +struct nd_namespace_label { + union { + struct nvdimm_cxl_label cxl; + struct nvdimm_efi_label efi; + }; +}; + #define NVDIMM_BTT_GUID "8aed63a2-29a2-4c66-8b12-f05d15d3922a" #define NVDIMM_BTT2_GUID "18633bfc-1735-4217-8ac9-17239282d3f8" #define NVDIMM_PFN_GUID "266400ba-fb9f-4677-bcb0-968f11d0d225" #define NVDIMM_DAX_GUID "97a86d9c-3cdd-4eda-986f-5068b4f80088" +#define CXL_REGION_UUID "529d7c61-da07-47c4-a93f-ecdf2c06f444" +#define CXL_NAMESPACE_UUID "68bb2c0a-5a77-4937-9f85-3caf41a0f93c" + /** * struct nd_label_id - identifier string for dpa allocation * @id: "{blk|pmem}-" diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index d57f95a48fe1..6f8ce114032d 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -30,6 +30,7 @@ struct nvdimm_drvdata { int nslabel_size; struct nd_cmd_get_config_size nsarea; void *data; + bool cxl; int ns_current, ns_next; struct resource dpa; struct kref kref; @@ -38,13 +39,17 @@ struct nvdimm_drvdata { static inline const u8 *nsl_ref_name(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label) { - return nd_label->name; + if (ndd->cxl) + return nd_label->cxl.name; + return nd_label->efi.name; } static inline u8 *nsl_get_name(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label, u8 *name) { - return memcpy(name, nd_label->name, NSLABEL_NAME_LEN); + if (ndd->cxl) + return memcpy(name, nd_label->cxl.name, NSLABEL_NAME_LEN); + return memcpy(name, nd_label->efi.name, NSLABEL_NAME_LEN); } static inline u8 *nsl_set_name(struct nvdimm_drvdata *ndd, @@ -52,122 +57,168 @@ static inline u8 *nsl_set_name(struct nvdimm_drvdata *ndd, { if (!name) return NULL; - return memcpy(nd_label->name, name, NSLABEL_NAME_LEN); + if (ndd->cxl) + return memcpy(nd_label->cxl.name, name, NSLABEL_NAME_LEN); + return memcpy(nd_label->efi.name, name, NSLABEL_NAME_LEN); } static inline u32 nsl_get_slot(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label) { - return __le32_to_cpu(nd_label->slot); + if (ndd->cxl) + return __le32_to_cpu(nd_label->cxl.slot); + return __le32_to_cpu(nd_label->efi.slot); } static inline void nsl_set_slot(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label, u32 slot) { - nd_label->slot = __cpu_to_le32(slot); + if (ndd->cxl) + nd_label->cxl.slot = __cpu_to_le32(slot); + else + nd_label->efi.slot = __cpu_to_le32(slot); } static inline u64 nsl_get_checksum(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label) { - return __le64_to_cpu(nd_label->checksum); + if (ndd->cxl) + return __le64_to_cpu(nd_label->cxl.checksum); + return __le64_to_cpu(nd_label->efi.checksum); } static inline void nsl_set_checksum(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label, u64 checksum) { - nd_label->checksum = __cpu_to_le64(checksum); + if (ndd->cxl) + nd_label->cxl.checksum = __cpu_to_le64(checksum); + else + nd_label->efi.checksum = __cpu_to_le64(checksum); } static inline u32 nsl_get_flags(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label) { - return __le32_to_cpu(nd_label->flags); + if (ndd->cxl) + return __le32_to_cpu(nd_label->cxl.flags); + return __le32_to_cpu(nd_label->efi.flags); } static inline void nsl_set_flags(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label, u32 flags) { - nd_label->flags = __cpu_to_le32(flags); + if (ndd->cxl) + nd_label->cxl.flags = __cpu_to_le32(flags); + else + nd_label->efi.flags = __cpu_to_le32(flags); } static inline u64 nsl_get_dpa(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label) { - return __le64_to_cpu(nd_label->dpa); + if (ndd->cxl) + return __le64_to_cpu(nd_label->cxl.dpa); + return __le64_to_cpu(nd_label->efi.dpa); } static inline void nsl_set_dpa(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label, u64 dpa) { - nd_label->dpa = __cpu_to_le64(dpa); + if (ndd->cxl) + nd_label->cxl.dpa = __cpu_to_le64(dpa); + else + nd_label->efi.dpa = __cpu_to_le64(dpa); } static inline u64 nsl_get_rawsize(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label) { - return __le64_to_cpu(nd_label->rawsize); + if (ndd->cxl) + return __le64_to_cpu(nd_label->cxl.rawsize); + return __le64_to_cpu(nd_label->efi.rawsize); } static inline void nsl_set_rawsize(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label, u64 rawsize) { - nd_label->rawsize = __cpu_to_le64(rawsize); + if (ndd->cxl) + nd_label->cxl.rawsize = __cpu_to_le64(rawsize); + else + nd_label->efi.rawsize = __cpu_to_le64(rawsize); } static inline u64 nsl_get_isetcookie(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label) { - return __le64_to_cpu(nd_label->isetcookie); + /* WARN future refactor attempts that break this assumption */ + if (dev_WARN_ONCE(ndd->dev, ndd->cxl, + "CXL labels do not use the isetcookie concept\n")) + return 0; + return __le64_to_cpu(nd_label->efi.isetcookie); } static inline void nsl_set_isetcookie(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label, u64 isetcookie) { - nd_label->isetcookie = __cpu_to_le64(isetcookie); + if (!ndd->cxl) + nd_label->efi.isetcookie = __cpu_to_le64(isetcookie); } static inline bool nsl_validate_isetcookie(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label, u64 cookie) { - return cookie == __le64_to_cpu(nd_label->isetcookie); + /* + * Let the EFI and CXL validation comingle, where fields that + * don't matter to CXL always validate. + */ + if (ndd->cxl) + return true; + return cookie == __le64_to_cpu(nd_label->efi.isetcookie); } static inline u16 nsl_get_position(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label) { - return __le16_to_cpu(nd_label->position); + if (ndd->cxl) + return __le16_to_cpu(nd_label->cxl.position); + return __le16_to_cpu(nd_label->efi.position); } static inline void nsl_set_position(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label, u16 position) { - nd_label->position = __cpu_to_le16(position); + if (ndd->cxl) + nd_label->cxl.position = __cpu_to_le16(position); + else + nd_label->efi.position = __cpu_to_le16(position); } - static inline u16 nsl_get_nlabel(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label) { - return __le16_to_cpu(nd_label->nlabel); + if (ndd->cxl) + return 0; + return __le16_to_cpu(nd_label->efi.nlabel); } static inline void nsl_set_nlabel(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label, u16 nlabel) { - nd_label->nlabel = __cpu_to_le16(nlabel); + if (!ndd->cxl) + nd_label->efi.nlabel = __cpu_to_le16(nlabel); } static inline u16 nsl_get_nrange(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label) { - /* EFI labels do not have an nrange field */ + if (ndd->cxl) + return __le16_to_cpu(nd_label->cxl.nrange); return 1; } @@ -175,26 +226,40 @@ static inline void nsl_set_nrange(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label, u16 nrange) { + if (ndd->cxl) + nd_label->cxl.nrange = __cpu_to_le16(nrange); } static inline u64 nsl_get_lbasize(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label) { - return __le64_to_cpu(nd_label->lbasize); + /* + * Yes, for some reason the EFI labels convey a massive 64-bit + * lbasize, that got fixed for CXL. + */ + if (ndd->cxl) + return __le16_to_cpu(nd_label->cxl.lbasize); + return __le64_to_cpu(nd_label->efi.lbasize); } static inline void nsl_set_lbasize(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label, u64 lbasize) { - nd_label->lbasize = __cpu_to_le64(lbasize); + if (ndd->cxl) + nd_label->cxl.lbasize = __cpu_to_le16(lbasize); + else + nd_label->efi.lbasize = __cpu_to_le64(lbasize); } static inline const uuid_t *nsl_get_uuid(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label, uuid_t *uuid) { - import_uuid(uuid, nd_label->uuid); + if (ndd->cxl) + import_uuid(uuid, nd_label->cxl.uuid); + else + import_uuid(uuid, nd_label->efi.uuid); return uuid; } @@ -202,7 +267,10 @@ static inline const uuid_t *nsl_set_uuid(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label, const uuid_t *uuid) { - export_uuid(nd_label->uuid, uuid); + if (ndd->cxl) + export_uuid(nd_label->cxl.uuid, uuid); + else + export_uuid(nd_label->efi.uuid, uuid); return uuid; } @@ -212,14 +280,19 @@ static inline bool nsl_uuid_equal(struct nvdimm_drvdata *ndd, { uuid_t tmp; - import_uuid(&tmp, nd_label->uuid); + if (ndd->cxl) + import_uuid(&tmp, nd_label->cxl.uuid); + else + import_uuid(&tmp, nd_label->efi.uuid); return uuid_equal(&tmp, uuid); } static inline const u8 *nsl_uuid_raw(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label) { - return nd_label->uuid; + if (ndd->cxl) + return nd_label->cxl.uuid; + return nd_label->efi.uuid; } bool nsl_validate_blk_isetcookie(struct nvdimm_drvdata *ndd, @@ -278,8 +351,8 @@ static inline struct nd_namespace_index *to_next_namespace_index( unsigned sizeof_namespace_label(struct nvdimm_drvdata *ndd); -#define namespace_label_has(ndd, field) \ - (offsetof(struct nd_namespace_label, field) \ +#define efi_namespace_label_has(ndd, field) \ + (!ndd->cxl && offsetof(struct nvdimm_efi_label, field) \ < sizeof_namespace_label(ndd)) #define nd_dbg_dpa(r, d, res, fmt, arg...) \ @@ -359,6 +432,8 @@ static inline bool nsl_validate_nlabel(struct nd_region *nd_region, struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label) { + if (ndd->cxl) + return true; return nsl_get_nlabel(ndd, nd_label) == nd_region->ndr_mappings; } From 99e222a5f1b67dd17c2c780f4eb9a694707d3bf7 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 8 Sep 2021 22:12:09 -0700 Subject: [PATCH 045/587] cxl/pci: Make 'struct cxl_mem' device type generic In preparation for adding a unit test provider of a cxl_memdev, convert the 'struct cxl_mem' driver context to carry a generic device rather than a pci device. Note, some dev_dbg() lines needed extra reformatting per clang-format. This conversion also allows the cxl_mem_create() and devm_cxl_add_memdev() calling conventions to be simplified. The "host" for a cxl_memdev, must be the same device for the driver that allocated @cxlm. Acked-by: Ben Widawsky Reviewed-by: Jonathan Cameron Reviewed-by: Ben Widawsky Link: https://lore.kernel.org/r/163116432973.2460985.7553504957932024222.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/cxl/core/memdev.c | 7 ++-- drivers/cxl/cxlmem.h | 6 ++-- drivers/cxl/pci.c | 75 ++++++++++++++++++--------------------- 3 files changed, 41 insertions(+), 47 deletions(-) diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index a9c317e32010..331ef7d6c598 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -149,7 +149,6 @@ static void cxl_memdev_unregister(void *_cxlmd) static struct cxl_memdev *cxl_memdev_alloc(struct cxl_mem *cxlm, const struct file_operations *fops) { - struct pci_dev *pdev = cxlm->pdev; struct cxl_memdev *cxlmd; struct device *dev; struct cdev *cdev; @@ -166,7 +165,7 @@ static struct cxl_memdev *cxl_memdev_alloc(struct cxl_mem *cxlm, dev = &cxlmd->dev; device_initialize(dev); - dev->parent = &pdev->dev; + dev->parent = cxlm->dev; dev->bus = &cxl_bus_type; dev->devt = MKDEV(cxl_mem_major, cxlmd->id); dev->type = &cxl_memdev_type; @@ -182,7 +181,7 @@ err: } struct cxl_memdev * -devm_cxl_add_memdev(struct device *host, struct cxl_mem *cxlm, +devm_cxl_add_memdev(struct cxl_mem *cxlm, const struct cdevm_file_operations *cdevm_fops) { struct cxl_memdev *cxlmd; @@ -210,7 +209,7 @@ devm_cxl_add_memdev(struct device *host, struct cxl_mem *cxlm, if (rc) goto err; - rc = devm_add_action_or_reset(host, cxl_memdev_unregister, cxlmd); + rc = devm_add_action_or_reset(cxlm->dev, cxl_memdev_unregister, cxlmd); if (rc) return ERR_PTR(rc); return cxlmd; diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index 6c0b1e2ea97c..d5334df83fb2 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -63,12 +63,12 @@ static inline struct cxl_memdev *to_cxl_memdev(struct device *dev) } struct cxl_memdev * -devm_cxl_add_memdev(struct device *host, struct cxl_mem *cxlm, +devm_cxl_add_memdev(struct cxl_mem *cxlm, const struct cdevm_file_operations *cdevm_fops); /** * struct cxl_mem - A CXL memory device - * @pdev: The PCI device associated with this CXL device. + * @dev: The device associated with this CXL device. * @cxlmd: Logical memory device chardev / interface * @regs: Parsed register blocks * @payload_size: Size of space for payload @@ -82,7 +82,7 @@ devm_cxl_add_memdev(struct device *host, struct cxl_mem *cxlm, * @ram_range: Volatile memory capacity information. */ struct cxl_mem { - struct pci_dev *pdev; + struct device *dev; struct cxl_memdev *cxlmd; struct cxl_regs regs; diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 8e45aa07d662..c1e1d12e24b6 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -250,7 +250,7 @@ static int cxl_mem_wait_for_doorbell(struct cxl_mem *cxlm) cpu_relax(); } - dev_dbg(&cxlm->pdev->dev, "Doorbell wait took %dms", + dev_dbg(cxlm->dev, "Doorbell wait took %dms", jiffies_to_msecs(end) - jiffies_to_msecs(start)); return 0; } @@ -268,7 +268,7 @@ static bool cxl_is_security_command(u16 opcode) static void cxl_mem_mbox_timeout(struct cxl_mem *cxlm, struct mbox_cmd *mbox_cmd) { - struct device *dev = &cxlm->pdev->dev; + struct device *dev = cxlm->dev; dev_dbg(dev, "Mailbox command (opcode: %#x size: %zub) timed out\n", mbox_cmd->opcode, mbox_cmd->size_in); @@ -300,6 +300,7 @@ static int __cxl_mem_mbox_send_cmd(struct cxl_mem *cxlm, struct mbox_cmd *mbox_cmd) { void __iomem *payload = cxlm->regs.mbox + CXLDEV_MBOX_PAYLOAD_OFFSET; + struct device *dev = cxlm->dev; u64 cmd_reg, status_reg; size_t out_len; int rc; @@ -325,8 +326,7 @@ static int __cxl_mem_mbox_send_cmd(struct cxl_mem *cxlm, /* #1 */ if (cxl_doorbell_busy(cxlm)) { - dev_err_ratelimited(&cxlm->pdev->dev, - "Mailbox re-busy after acquiring\n"); + dev_err_ratelimited(dev, "Mailbox re-busy after acquiring\n"); return -EBUSY; } @@ -345,7 +345,7 @@ static int __cxl_mem_mbox_send_cmd(struct cxl_mem *cxlm, writeq(cmd_reg, cxlm->regs.mbox + CXLDEV_MBOX_CMD_OFFSET); /* #4 */ - dev_dbg(&cxlm->pdev->dev, "Sending command\n"); + dev_dbg(dev, "Sending command\n"); writel(CXLDEV_MBOX_CTRL_DOORBELL, cxlm->regs.mbox + CXLDEV_MBOX_CTRL_OFFSET); @@ -362,7 +362,7 @@ static int __cxl_mem_mbox_send_cmd(struct cxl_mem *cxlm, FIELD_GET(CXLDEV_MBOX_STATUS_RET_CODE_MASK, status_reg); if (mbox_cmd->return_code != 0) { - dev_dbg(&cxlm->pdev->dev, "Mailbox operation had an error\n"); + dev_dbg(dev, "Mailbox operation had an error\n"); return 0; } @@ -399,7 +399,7 @@ static int __cxl_mem_mbox_send_cmd(struct cxl_mem *cxlm, */ static int cxl_mem_mbox_get(struct cxl_mem *cxlm) { - struct device *dev = &cxlm->pdev->dev; + struct device *dev = cxlm->dev; u64 md_status; int rc; @@ -502,7 +502,7 @@ static int handle_mailbox_cmd_from_user(struct cxl_mem *cxlm, u64 in_payload, u64 out_payload, s32 *size_out, u32 *retval) { - struct device *dev = &cxlm->pdev->dev; + struct device *dev = cxlm->dev; struct mbox_cmd mbox_cmd = { .opcode = cmd->opcode, .size_in = cmd->info.size_in, @@ -925,20 +925,19 @@ static int cxl_mem_setup_mailbox(struct cxl_mem *cxlm) */ cxlm->payload_size = min_t(size_t, cxlm->payload_size, SZ_1M); if (cxlm->payload_size < 256) { - dev_err(&cxlm->pdev->dev, "Mailbox is too small (%zub)", + dev_err(cxlm->dev, "Mailbox is too small (%zub)", cxlm->payload_size); return -ENXIO; } - dev_dbg(&cxlm->pdev->dev, "Mailbox payload sized %zu", + dev_dbg(cxlm->dev, "Mailbox payload sized %zu", cxlm->payload_size); return 0; } -static struct cxl_mem *cxl_mem_create(struct pci_dev *pdev) +static struct cxl_mem *cxl_mem_create(struct device *dev) { - struct device *dev = &pdev->dev; struct cxl_mem *cxlm; cxlm = devm_kzalloc(dev, sizeof(*cxlm), GFP_KERNEL); @@ -948,7 +947,7 @@ static struct cxl_mem *cxl_mem_create(struct pci_dev *pdev) } mutex_init(&cxlm->mbox_mutex); - cxlm->pdev = pdev; + cxlm->dev = dev; cxlm->enabled_cmds = devm_kmalloc_array(dev, BITS_TO_LONGS(cxl_cmd_count), sizeof(unsigned long), @@ -964,9 +963,9 @@ static struct cxl_mem *cxl_mem_create(struct pci_dev *pdev) static void __iomem *cxl_mem_map_regblock(struct cxl_mem *cxlm, u8 bar, u64 offset) { - struct pci_dev *pdev = cxlm->pdev; - struct device *dev = &pdev->dev; void __iomem *addr; + struct device *dev = cxlm->dev; + struct pci_dev *pdev = to_pci_dev(dev); /* Basic sanity check that BAR is big enough */ if (pci_resource_len(pdev, bar) < offset) { @@ -989,7 +988,7 @@ static void __iomem *cxl_mem_map_regblock(struct cxl_mem *cxlm, static void cxl_mem_unmap_regblock(struct cxl_mem *cxlm, void __iomem *base) { - pci_iounmap(cxlm->pdev, base); + pci_iounmap(to_pci_dev(cxlm->dev), base); } static int cxl_mem_dvsec(struct pci_dev *pdev, int dvsec) @@ -1018,10 +1017,9 @@ static int cxl_mem_dvsec(struct pci_dev *pdev, int dvsec) static int cxl_probe_regs(struct cxl_mem *cxlm, void __iomem *base, struct cxl_register_map *map) { - struct pci_dev *pdev = cxlm->pdev; - struct device *dev = &pdev->dev; struct cxl_component_reg_map *comp_map; struct cxl_device_reg_map *dev_map; + struct device *dev = cxlm->dev; switch (map->reg_type) { case CXL_REGLOC_RBI_COMPONENT: @@ -1057,8 +1055,8 @@ static int cxl_probe_regs(struct cxl_mem *cxlm, void __iomem *base, static int cxl_map_regs(struct cxl_mem *cxlm, struct cxl_register_map *map) { - struct pci_dev *pdev = cxlm->pdev; - struct device *dev = &pdev->dev; + struct device *dev = cxlm->dev; + struct pci_dev *pdev = to_pci_dev(dev); switch (map->reg_type) { case CXL_REGLOC_RBI_COMPONENT: @@ -1096,13 +1094,12 @@ static void cxl_decode_register_block(u32 reg_lo, u32 reg_hi, */ static int cxl_mem_setup_regs(struct cxl_mem *cxlm) { - struct pci_dev *pdev = cxlm->pdev; - struct device *dev = &pdev->dev; - u32 regloc_size, regblocks; void __iomem *base; - int regloc, i, n_maps; + u32 regloc_size, regblocks; + int regloc, i, n_maps, ret = 0; + struct device *dev = cxlm->dev; + struct pci_dev *pdev = to_pci_dev(dev); struct cxl_register_map *map, maps[CXL_REGLOC_RBI_TYPES]; - int ret = 0; regloc = cxl_mem_dvsec(pdev, PCI_DVSEC_ID_CXL_REGLOC_DVSEC_ID); if (!regloc) { @@ -1226,7 +1223,7 @@ static void cxl_walk_cel(struct cxl_mem *cxlm, size_t size, u8 *cel) struct cxl_mem_command *cmd = cxl_mem_find_command(opcode); if (!cmd) { - dev_dbg(&cxlm->pdev->dev, + dev_dbg(cxlm->dev, "Opcode 0x%04x unsupported by driver", opcode); continue; } @@ -1323,7 +1320,7 @@ static int cxl_mem_get_partition_info(struct cxl_mem *cxlm, static int cxl_mem_enumerate_cmds(struct cxl_mem *cxlm) { struct cxl_mbox_get_supported_logs *gsl; - struct device *dev = &cxlm->pdev->dev; + struct device *dev = cxlm->dev; struct cxl_mem_command *cmd; int i, rc; @@ -1418,15 +1415,14 @@ static int cxl_mem_identify(struct cxl_mem *cxlm) cxlm->partition_align_bytes = le64_to_cpu(id.partition_align); cxlm->partition_align_bytes *= CXL_CAPACITY_MULTIPLIER; - dev_dbg(&cxlm->pdev->dev, "Identify Memory Device\n" + dev_dbg(cxlm->dev, + "Identify Memory Device\n" " total_bytes = %#llx\n" " volatile_only_bytes = %#llx\n" " persistent_only_bytes = %#llx\n" " partition_align_bytes = %#llx\n", - cxlm->total_bytes, - cxlm->volatile_only_bytes, - cxlm->persistent_only_bytes, - cxlm->partition_align_bytes); + cxlm->total_bytes, cxlm->volatile_only_bytes, + cxlm->persistent_only_bytes, cxlm->partition_align_bytes); cxlm->lsa_size = le32_to_cpu(id.lsa_size); memcpy(cxlm->firmware_version, id.fw_revision, sizeof(id.fw_revision)); @@ -1453,19 +1449,18 @@ static int cxl_mem_create_range_info(struct cxl_mem *cxlm) &cxlm->next_volatile_bytes, &cxlm->next_persistent_bytes); if (rc < 0) { - dev_err(&cxlm->pdev->dev, "Failed to query partition information\n"); + dev_err(cxlm->dev, "Failed to query partition information\n"); return rc; } - dev_dbg(&cxlm->pdev->dev, "Get Partition Info\n" + dev_dbg(cxlm->dev, + "Get Partition Info\n" " active_volatile_bytes = %#llx\n" " active_persistent_bytes = %#llx\n" " next_volatile_bytes = %#llx\n" " next_persistent_bytes = %#llx\n", - cxlm->active_volatile_bytes, - cxlm->active_persistent_bytes, - cxlm->next_volatile_bytes, - cxlm->next_persistent_bytes); + cxlm->active_volatile_bytes, cxlm->active_persistent_bytes, + cxlm->next_volatile_bytes, cxlm->next_persistent_bytes); cxlm->ram_range.start = 0; cxlm->ram_range.end = cxlm->active_volatile_bytes - 1; @@ -1487,7 +1482,7 @@ static int cxl_mem_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (rc) return rc; - cxlm = cxl_mem_create(pdev); + cxlm = cxl_mem_create(&pdev->dev); if (IS_ERR(cxlm)) return PTR_ERR(cxlm); @@ -1511,7 +1506,7 @@ static int cxl_mem_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (rc) return rc; - cxlmd = devm_cxl_add_memdev(&pdev->dev, cxlm, &cxl_memdev_fops); + cxlmd = devm_cxl_add_memdev(cxlm, &cxl_memdev_fops); if (IS_ERR(cxlmd)) return PTR_ERR(cxlmd); From 13e7749d06b335774bbb341c65a0232484beb457 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 13 Sep 2021 15:24:32 -0700 Subject: [PATCH 046/587] cxl/pci: Clean up cxl_mem_get_partition_info() Commit 0b9159d0ff21 ("cxl/pci: Store memory capacity values") missed updating the kernel-doc for 'struct cxl_mem' leading to the following warnings: ./scripts/kernel-doc -v drivers/cxl/cxlmem.h 2>&1 | grep warn drivers/cxl/cxlmem.h:107: warning: Function parameter or member 'total_bytes' not described in 'cxl_mem' drivers/cxl/cxlmem.h:107: warning: Function parameter or member 'volatile_only_bytes' not described in 'cxl_mem' drivers/cxl/cxlmem.h:107: warning: Function parameter or member 'persistent_only_bytes' not described in 'cxl_mem' drivers/cxl/cxlmem.h:107: warning: Function parameter or member 'partition_align_bytes' not described in 'cxl_mem' drivers/cxl/cxlmem.h:107: warning: Function parameter or member 'active_volatile_bytes' not described in 'cxl_mem' drivers/cxl/cxlmem.h:107: warning: Function parameter or member 'active_persistent_bytes' not described in 'cxl_mem' drivers/cxl/cxlmem.h:107: warning: Function parameter or member 'next_volatile_bytes' not described in 'cxl_mem' drivers/cxl/cxlmem.h:107: warning: Function parameter or member 'next_persistent_bytes' not described in 'cxl_mem' Also, it is redundant to describe those same parameters in the kernel-doc for cxl_mem_get_partition_info(). Given the only user of that routine updates the values in @cxlm, just do that implicitly internal to the helper. Cc: Ira Weiny Reported-by: Ben Widawsky Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/163157174216.2653013.1277706528753990974.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/cxl/cxlmem.h | 15 +++++++++++++-- drivers/cxl/pci.c | 35 +++++++++++------------------------ 2 files changed, 24 insertions(+), 26 deletions(-) diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index d5334df83fb2..e14bcd7a1ba1 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -78,8 +78,19 @@ devm_cxl_add_memdev(struct cxl_mem *cxlm, * @mbox_mutex: Mutex to synchronize mailbox access. * @firmware_version: Firmware version for the memory device. * @enabled_cmds: Hardware commands found enabled in CEL. - * @pmem_range: Persistent memory capacity information. - * @ram_range: Volatile memory capacity information. + * @pmem_range: Active Persistent memory capacity configuration + * @ram_range: Active Volatile memory capacity configuration + * @total_bytes: sum of all possible capacities + * @volatile_only_bytes: hard volatile capacity + * @persistent_only_bytes: hard persistent capacity + * @partition_align_bytes: alignment size for partition-able capacity + * @active_volatile_bytes: sum of hard + soft volatile + * @active_persistent_bytes: sum of hard + soft persistent + * @next_volatile_bytes: volatile capacity change pending device reset + * @next_persistent_bytes: persistent capacity change pending device reset + * + * See section 8.2.9.5.2 Capacity Configuration and Label Storage for + * details on capacity parameters. */ struct cxl_mem { struct device *dev; diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index c1e1d12e24b6..8077d907e7d3 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -1262,11 +1262,7 @@ static struct cxl_mbox_get_supported_logs *cxl_get_gsl(struct cxl_mem *cxlm) /** * cxl_mem_get_partition_info - Get partition info - * @cxlm: The device to act on - * @active_volatile_bytes: returned active volatile capacity - * @active_persistent_bytes: returned active persistent capacity - * @next_volatile_bytes: return next volatile capacity - * @next_persistent_bytes: return next persistent capacity + * @cxlm: cxl_mem instance to update partition info * * Retrieve the current partition info for the device specified. If not 0, the * 'next' values are pending and take affect on next cold reset. @@ -1275,11 +1271,7 @@ static struct cxl_mbox_get_supported_logs *cxl_get_gsl(struct cxl_mem *cxlm) * * See CXL @8.2.9.5.2.1 Get Partition Info */ -static int cxl_mem_get_partition_info(struct cxl_mem *cxlm, - u64 *active_volatile_bytes, - u64 *active_persistent_bytes, - u64 *next_volatile_bytes, - u64 *next_persistent_bytes) +static int cxl_mem_get_partition_info(struct cxl_mem *cxlm) { struct cxl_mbox_get_partition_info { __le64 active_volatile_cap; @@ -1294,15 +1286,14 @@ static int cxl_mem_get_partition_info(struct cxl_mem *cxlm, if (rc) return rc; - *active_volatile_bytes = le64_to_cpu(pi.active_volatile_cap); - *active_persistent_bytes = le64_to_cpu(pi.active_persistent_cap); - *next_volatile_bytes = le64_to_cpu(pi.next_volatile_cap); - *next_persistent_bytes = le64_to_cpu(pi.next_volatile_cap); - - *active_volatile_bytes *= CXL_CAPACITY_MULTIPLIER; - *active_persistent_bytes *= CXL_CAPACITY_MULTIPLIER; - *next_volatile_bytes *= CXL_CAPACITY_MULTIPLIER; - *next_persistent_bytes *= CXL_CAPACITY_MULTIPLIER; + cxlm->active_volatile_bytes = + le64_to_cpu(pi.active_volatile_cap) * CXL_CAPACITY_MULTIPLIER; + cxlm->active_persistent_bytes = + le64_to_cpu(pi.active_persistent_cap) * CXL_CAPACITY_MULTIPLIER; + cxlm->next_volatile_bytes = + le64_to_cpu(pi.next_volatile_cap) * CXL_CAPACITY_MULTIPLIER; + cxlm->next_persistent_bytes = + le64_to_cpu(pi.next_volatile_cap) * CXL_CAPACITY_MULTIPLIER; return 0; } @@ -1443,11 +1434,7 @@ static int cxl_mem_create_range_info(struct cxl_mem *cxlm) return 0; } - rc = cxl_mem_get_partition_info(cxlm, - &cxlm->active_volatile_bytes, - &cxlm->active_persistent_bytes, - &cxlm->next_volatile_bytes, - &cxlm->next_persistent_bytes); + rc = cxl_mem_get_partition_info(cxlm); if (rc < 0) { dev_err(cxlm->dev, "Failed to query partition information\n"); return rc; From b64955a92929346f16df058ad2bb53630eb80466 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 8 Sep 2021 22:12:21 -0700 Subject: [PATCH 047/587] cxl/mbox: Introduce the mbox_send operation In preparation for implementing a unit test backend transport for ioctl operations, and making the mailbox available to the cxl/pmem infrastructure, move the existing PCI specific portion of mailbox handling to an "mbox_send" operation. With this split all the PCI-specific transport details are comprehended by a single operation and the rest of the mailbox infrastructure is 'struct cxl_mem' and 'struct cxl_memdev' generic. Acked-by: Ben Widawsky Reviewed-by: Jonathan Cameron Reviewed-by: Ben Widawsky Link: https://lore.kernel.org/r/163116434098.2460985.9004760022659400540.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/cxl/cxlmem.h | 42 ++++++++++++++++++++++++ drivers/cxl/pci.c | 76 ++++++++++++-------------------------------- 2 files changed, 63 insertions(+), 55 deletions(-) diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index e14bcd7a1ba1..c142532db8cb 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -66,6 +66,45 @@ struct cxl_memdev * devm_cxl_add_memdev(struct cxl_mem *cxlm, const struct cdevm_file_operations *cdevm_fops); +/** + * struct cxl_mbox_cmd - A command to be submitted to hardware. + * @opcode: (input) The command set and command submitted to hardware. + * @payload_in: (input) Pointer to the input payload. + * @payload_out: (output) Pointer to the output payload. Must be allocated by + * the caller. + * @size_in: (input) Number of bytes to load from @payload_in. + * @size_out: (input) Max number of bytes loaded into @payload_out. + * (output) Number of bytes generated by the device. For fixed size + * outputs commands this is always expected to be deterministic. For + * variable sized output commands, it tells the exact number of bytes + * written. + * @return_code: (output) Error code returned from hardware. + * + * This is the primary mechanism used to send commands to the hardware. + * All the fields except @payload_* correspond exactly to the fields described in + * Command Register section of the CXL 2.0 8.2.8.4.5. @payload_in and + * @payload_out are written to, and read from the Command Payload Registers + * defined in CXL 2.0 8.2.8.4.8. + */ +struct cxl_mbox_cmd { + u16 opcode; + void *payload_in; + void *payload_out; + size_t size_in; + size_t size_out; + u16 return_code; +#define CXL_MBOX_SUCCESS 0 +}; + +/* + * CXL 2.0 - Memory capacity multiplier + * See Section 8.2.9.5 + * + * Volatile, Persistent, and Partition capacities are specified to be in + * multiples of 256MB - define a multiplier to convert to/from bytes. + */ +#define CXL_CAPACITY_MULTIPLIER SZ_256M + /** * struct cxl_mem - A CXL memory device * @dev: The device associated with this CXL device. @@ -88,6 +127,7 @@ devm_cxl_add_memdev(struct cxl_mem *cxlm, * @active_persistent_bytes: sum of hard + soft persistent * @next_volatile_bytes: volatile capacity change pending device reset * @next_persistent_bytes: persistent capacity change pending device reset + * @mbox_send: @dev specific transport for transmitting mailbox commands * * See section 8.2.9.5.2 Capacity Configuration and Label Storage for * details on capacity parameters. @@ -115,5 +155,7 @@ struct cxl_mem { u64 active_persistent_bytes; u64 next_volatile_bytes; u64 next_persistent_bytes; + + int (*mbox_send)(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd); }; #endif /* __CXL_MEM_H__ */ diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 8077d907e7d3..e2f27671c6b2 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -64,45 +64,6 @@ enum opcode { CXL_MBOX_OP_MAX = 0x10000 }; -/* - * CXL 2.0 - Memory capacity multiplier - * See Section 8.2.9.5 - * - * Volatile, Persistent, and Partition capacities are specified to be in - * multiples of 256MB - define a multiplier to convert to/from bytes. - */ -#define CXL_CAPACITY_MULTIPLIER SZ_256M - -/** - * struct mbox_cmd - A command to be submitted to hardware. - * @opcode: (input) The command set and command submitted to hardware. - * @payload_in: (input) Pointer to the input payload. - * @payload_out: (output) Pointer to the output payload. Must be allocated by - * the caller. - * @size_in: (input) Number of bytes to load from @payload_in. - * @size_out: (input) Max number of bytes loaded into @payload_out. - * (output) Number of bytes generated by the device. For fixed size - * outputs commands this is always expected to be deterministic. For - * variable sized output commands, it tells the exact number of bytes - * written. - * @return_code: (output) Error code returned from hardware. - * - * This is the primary mechanism used to send commands to the hardware. - * All the fields except @payload_* correspond exactly to the fields described in - * Command Register section of the CXL 2.0 8.2.8.4.5. @payload_in and - * @payload_out are written to, and read from the Command Payload Registers - * defined in CXL 2.0 8.2.8.4.8. - */ -struct mbox_cmd { - u16 opcode; - void *payload_in; - void *payload_out; - size_t size_in; - size_t size_out; - u16 return_code; -#define CXL_MBOX_SUCCESS 0 -}; - static DECLARE_RWSEM(cxl_memdev_rwsem); static struct dentry *cxl_debugfs; static bool cxl_raw_allow_all; @@ -266,7 +227,7 @@ static bool cxl_is_security_command(u16 opcode) } static void cxl_mem_mbox_timeout(struct cxl_mem *cxlm, - struct mbox_cmd *mbox_cmd) + struct cxl_mbox_cmd *mbox_cmd) { struct device *dev = cxlm->dev; @@ -297,7 +258,7 @@ static void cxl_mem_mbox_timeout(struct cxl_mem *cxlm, * mailbox. */ static int __cxl_mem_mbox_send_cmd(struct cxl_mem *cxlm, - struct mbox_cmd *mbox_cmd) + struct cxl_mbox_cmd *mbox_cmd) { void __iomem *payload = cxlm->regs.mbox + CXLDEV_MBOX_PAYLOAD_OFFSET; struct device *dev = cxlm->dev; @@ -472,6 +433,20 @@ static void cxl_mem_mbox_put(struct cxl_mem *cxlm) mutex_unlock(&cxlm->mbox_mutex); } +static int cxl_pci_mbox_send(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd) +{ + int rc; + + rc = cxl_mem_mbox_get(cxlm); + if (rc) + return rc; + + rc = __cxl_mem_mbox_send_cmd(cxlm, cmd); + cxl_mem_mbox_put(cxlm); + + return rc; +} + /** * handle_mailbox_cmd_from_user() - Dispatch a mailbox command for userspace. * @cxlm: The CXL memory device to communicate with. @@ -503,7 +478,7 @@ static int handle_mailbox_cmd_from_user(struct cxl_mem *cxlm, s32 *size_out, u32 *retval) { struct device *dev = cxlm->dev; - struct mbox_cmd mbox_cmd = { + struct cxl_mbox_cmd mbox_cmd = { .opcode = cmd->opcode, .size_in = cmd->info.size_in, .size_out = cmd->info.size_out, @@ -525,10 +500,6 @@ static int handle_mailbox_cmd_from_user(struct cxl_mem *cxlm, } } - rc = cxl_mem_mbox_get(cxlm); - if (rc) - goto out; - dev_dbg(dev, "Submitting %s command for user\n" "\topcode: %x\n" @@ -539,8 +510,7 @@ static int handle_mailbox_cmd_from_user(struct cxl_mem *cxlm, dev_WARN_ONCE(dev, cmd->info.id == CXL_MEM_COMMAND_ID_RAW, "raw command path used\n"); - rc = __cxl_mem_mbox_send_cmd(cxlm, &mbox_cmd); - cxl_mem_mbox_put(cxlm); + rc = cxlm->mbox_send(cxlm, &mbox_cmd); if (rc) goto out; @@ -874,7 +844,7 @@ static int cxl_mem_mbox_send_cmd(struct cxl_mem *cxlm, u16 opcode, void *out, size_t out_size) { const struct cxl_mem_command *cmd = cxl_mem_find_command(opcode); - struct mbox_cmd mbox_cmd = { + struct cxl_mbox_cmd mbox_cmd = { .opcode = opcode, .payload_in = in, .size_in = in_size, @@ -886,12 +856,7 @@ static int cxl_mem_mbox_send_cmd(struct cxl_mem *cxlm, u16 opcode, if (out_size > cxlm->payload_size) return -E2BIG; - rc = cxl_mem_mbox_get(cxlm); - if (rc) - return rc; - - rc = __cxl_mem_mbox_send_cmd(cxlm, &mbox_cmd); - cxl_mem_mbox_put(cxlm); + rc = cxlm->mbox_send(cxlm, &mbox_cmd); if (rc) return rc; @@ -913,6 +878,7 @@ static int cxl_mem_setup_mailbox(struct cxl_mem *cxlm) { const int cap = readl(cxlm->regs.mbox + CXLDEV_MBOX_CAPS_OFFSET); + cxlm->mbox_send = cxl_pci_mbox_send; cxlm->payload_size = 1 << FIELD_GET(CXLDEV_MBOX_CAP_PAYLOAD_SIZE_MASK, cap); From 4cb35f1ca05a42acbc4a3c8cf7de1029a06558d0 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 8 Sep 2021 22:12:26 -0700 Subject: [PATCH 048/587] cxl/pci: Drop idr.h Commit 3d135db51024 ("cxl/core: Move memdev management to core") left this straggling include for cxl_memdev setup. Clean it up. Cc: Ben Widawsky Reported-by: Jonathan Cameron Reviewed-by: Jonathan Cameron Reviewed-by: Ben Widawsky Link: https://lore.kernel.org/r/163116434668.2460985.12264757586266849616.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/cxl/pci.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index e2f27671c6b2..9d8050fdd69c 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -8,7 +8,6 @@ #include #include #include -#include #include #include #include From 4faf31b43468c58e2c8c91cc5fa26f08a6b733be Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 8 Sep 2021 22:12:32 -0700 Subject: [PATCH 049/587] cxl/mbox: Move mailbox and other non-PCI specific infrastructure to the core Now that the internals of mailbox operations are abstracted from the PCI specifics a bulk of infrastructure can move to the core. The CXL_PMEM driver intends to proxy LIBNVDIMM UAPI and driver requests to the equivalent functionality provided by the CXL hardware mailbox interface. In support of that intent move the mailbox implementation to a shared location for the CXL_PCI driver native IOCTL path and CXL_PMEM nvdimm command proxy path to share. A unit test framework seeks to implement a unit test backend transport for mailbox commands to communicate mocked up payloads. It can reuse all of the mailbox infrastructure minus the PCI specifics, so that also gets moved to the core. Finally with the mailbox infrastructure and ioctl handling being transport generic there is no longer any need to pass file file_operations to devm_cxl_add_memdev(). That allows all the ioctl boilerplate to move into the core for unit test reuse. No functional change intended, just code movement. Acked-by: Ben Widawsky Reported-by: kernel test robot Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/163116435233.2460985.16197340449713287180.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- .../driver-api/cxl/memory-devices.rst | 3 + drivers/cxl/core/Makefile | 1 + drivers/cxl/core/bus.c | 4 + drivers/cxl/core/core.h | 8 + drivers/cxl/core/mbox.c | 825 ++++++++++++++++ drivers/cxl/core/memdev.c | 81 +- drivers/cxl/cxlmem.h | 78 +- drivers/cxl/pci.c | 924 +----------------- 8 files changed, 975 insertions(+), 949 deletions(-) create mode 100644 drivers/cxl/core/mbox.c diff --git a/Documentation/driver-api/cxl/memory-devices.rst b/Documentation/driver-api/cxl/memory-devices.rst index 50ebcda17ad0..4624951b5c38 100644 --- a/Documentation/driver-api/cxl/memory-devices.rst +++ b/Documentation/driver-api/cxl/memory-devices.rst @@ -45,6 +45,9 @@ CXL Core .. kernel-doc:: drivers/cxl/core/regs.c :doc: cxl registers +.. kernel-doc:: drivers/cxl/core/mbox.c + :doc: cxl mbox + External Interfaces =================== diff --git a/drivers/cxl/core/Makefile b/drivers/cxl/core/Makefile index 0fdbf3c6ac1a..07eb8e1fb8a6 100644 --- a/drivers/cxl/core/Makefile +++ b/drivers/cxl/core/Makefile @@ -6,3 +6,4 @@ cxl_core-y := bus.o cxl_core-y += pmem.o cxl_core-y += regs.o cxl_core-y += memdev.o +cxl_core-y += mbox.o diff --git a/drivers/cxl/core/bus.c b/drivers/cxl/core/bus.c index 267d8042bec2..9a8fa88b634c 100644 --- a/drivers/cxl/core/bus.c +++ b/drivers/cxl/core/bus.c @@ -635,6 +635,8 @@ static __init int cxl_core_init(void) { int rc; + cxl_mbox_init(); + rc = cxl_memdev_init(); if (rc) return rc; @@ -646,6 +648,7 @@ static __init int cxl_core_init(void) err: cxl_memdev_exit(); + cxl_mbox_exit(); return rc; } @@ -653,6 +656,7 @@ static void cxl_core_exit(void) { bus_unregister(&cxl_bus_type); cxl_memdev_exit(); + cxl_mbox_exit(); } module_init(cxl_core_init); diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h index 036a3c8106b4..c85b7fbad02d 100644 --- a/drivers/cxl/core/core.h +++ b/drivers/cxl/core/core.h @@ -14,7 +14,15 @@ static inline void unregister_cxl_dev(void *dev) device_unregister(dev); } +struct cxl_send_command; +struct cxl_mem_query_commands; +int cxl_query_cmd(struct cxl_memdev *cxlmd, + struct cxl_mem_query_commands __user *q); +int cxl_send_cmd(struct cxl_memdev *cxlmd, struct cxl_send_command __user *s); + int cxl_memdev_init(void); void cxl_memdev_exit(void); +void cxl_mbox_init(void); +void cxl_mbox_exit(void); #endif /* __CXL_CORE_H__ */ diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c new file mode 100644 index 000000000000..31e183991726 --- /dev/null +++ b/drivers/cxl/core/mbox.c @@ -0,0 +1,825 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright(c) 2020 Intel Corporation. All rights reserved. */ +#include +#include +#include +#include +#include +#include + +#include "core.h" + +static bool cxl_raw_allow_all; + +/** + * DOC: cxl mbox + * + * Core implementation of the CXL 2.0 Type-3 Memory Device Mailbox. The + * implementation is used by the cxl_pci driver to initialize the device + * and implement the cxl_mem.h IOCTL UAPI. It also implements the + * backend of the cxl_pmem_ctl() transport for LIBNVDIMM. + */ + +#define cxl_for_each_cmd(cmd) \ + for ((cmd) = &cxl_mem_commands[0]; \ + ((cmd) - cxl_mem_commands) < ARRAY_SIZE(cxl_mem_commands); (cmd)++) + +#define CXL_CMD(_id, sin, sout, _flags) \ + [CXL_MEM_COMMAND_ID_##_id] = { \ + .info = { \ + .id = CXL_MEM_COMMAND_ID_##_id, \ + .size_in = sin, \ + .size_out = sout, \ + }, \ + .opcode = CXL_MBOX_OP_##_id, \ + .flags = _flags, \ + } + +/* + * This table defines the supported mailbox commands for the driver. This table + * is made up of a UAPI structure. Non-negative values as parameters in the + * table will be validated against the user's input. For example, if size_in is + * 0, and the user passed in 1, it is an error. + */ +static struct cxl_mem_command cxl_mem_commands[CXL_MEM_COMMAND_ID_MAX] = { + CXL_CMD(IDENTIFY, 0, 0x43, CXL_CMD_FLAG_FORCE_ENABLE), +#ifdef CONFIG_CXL_MEM_RAW_COMMANDS + CXL_CMD(RAW, ~0, ~0, 0), +#endif + CXL_CMD(GET_SUPPORTED_LOGS, 0, ~0, CXL_CMD_FLAG_FORCE_ENABLE), + CXL_CMD(GET_FW_INFO, 0, 0x50, 0), + CXL_CMD(GET_PARTITION_INFO, 0, 0x20, 0), + CXL_CMD(GET_LSA, 0x8, ~0, 0), + CXL_CMD(GET_HEALTH_INFO, 0, 0x12, 0), + CXL_CMD(GET_LOG, 0x18, ~0, CXL_CMD_FLAG_FORCE_ENABLE), + CXL_CMD(SET_PARTITION_INFO, 0x0a, 0, 0), + CXL_CMD(SET_LSA, ~0, 0, 0), + CXL_CMD(GET_ALERT_CONFIG, 0, 0x10, 0), + CXL_CMD(SET_ALERT_CONFIG, 0xc, 0, 0), + CXL_CMD(GET_SHUTDOWN_STATE, 0, 0x1, 0), + CXL_CMD(SET_SHUTDOWN_STATE, 0x1, 0, 0), + CXL_CMD(GET_POISON, 0x10, ~0, 0), + CXL_CMD(INJECT_POISON, 0x8, 0, 0), + CXL_CMD(CLEAR_POISON, 0x48, 0, 0), + CXL_CMD(GET_SCAN_MEDIA_CAPS, 0x10, 0x4, 0), + CXL_CMD(SCAN_MEDIA, 0x11, 0, 0), + CXL_CMD(GET_SCAN_MEDIA, 0, ~0, 0), +}; + +/* + * Commands that RAW doesn't permit. The rationale for each: + * + * CXL_MBOX_OP_ACTIVATE_FW: Firmware activation requires adjustment / + * coordination of transaction timeout values at the root bridge level. + * + * CXL_MBOX_OP_SET_PARTITION_INFO: The device memory map may change live + * and needs to be coordinated with HDM updates. + * + * CXL_MBOX_OP_SET_LSA: The label storage area may be cached by the + * driver and any writes from userspace invalidates those contents. + * + * CXL_MBOX_OP_SET_SHUTDOWN_STATE: Set shutdown state assumes no writes + * to the device after it is marked clean, userspace can not make that + * assertion. + * + * CXL_MBOX_OP_[GET_]SCAN_MEDIA: The kernel provides a native error list that + * is kept up to date with patrol notifications and error management. + */ +static u16 cxl_disabled_raw_commands[] = { + CXL_MBOX_OP_ACTIVATE_FW, + CXL_MBOX_OP_SET_PARTITION_INFO, + CXL_MBOX_OP_SET_LSA, + CXL_MBOX_OP_SET_SHUTDOWN_STATE, + CXL_MBOX_OP_SCAN_MEDIA, + CXL_MBOX_OP_GET_SCAN_MEDIA, +}; + +/* + * Command sets that RAW doesn't permit. All opcodes in this set are + * disabled because they pass plain text security payloads over the + * user/kernel boundary. This functionality is intended to be wrapped + * behind the keys ABI which allows for encrypted payloads in the UAPI + */ +static u8 security_command_sets[] = { + 0x44, /* Sanitize */ + 0x45, /* Persistent Memory Data-at-rest Security */ + 0x46, /* Security Passthrough */ +}; + +static bool cxl_is_security_command(u16 opcode) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(security_command_sets); i++) + if (security_command_sets[i] == (opcode >> 8)) + return true; + return false; +} + +static struct cxl_mem_command *cxl_mem_find_command(u16 opcode) +{ + struct cxl_mem_command *c; + + cxl_for_each_cmd(c) + if (c->opcode == opcode) + return c; + + return NULL; +} + +/** + * cxl_mem_mbox_send_cmd() - Send a mailbox command to a memory device. + * @cxlm: The CXL memory device to communicate with. + * @opcode: Opcode for the mailbox command. + * @in: The input payload for the mailbox command. + * @in_size: The length of the input payload + * @out: Caller allocated buffer for the output. + * @out_size: Expected size of output. + * + * Context: Any context. Will acquire and release mbox_mutex. + * Return: + * * %>=0 - Number of bytes returned in @out. + * * %-E2BIG - Payload is too large for hardware. + * * %-EBUSY - Couldn't acquire exclusive mailbox access. + * * %-EFAULT - Hardware error occurred. + * * %-ENXIO - Command completed, but device reported an error. + * * %-EIO - Unexpected output size. + * + * Mailbox commands may execute successfully yet the device itself reported an + * error. While this distinction can be useful for commands from userspace, the + * kernel will only be able to use results when both are successful. + * + * See __cxl_mem_mbox_send_cmd() + */ +int cxl_mem_mbox_send_cmd(struct cxl_mem *cxlm, u16 opcode, void *in, + size_t in_size, void *out, size_t out_size) +{ + const struct cxl_mem_command *cmd = cxl_mem_find_command(opcode); + struct cxl_mbox_cmd mbox_cmd = { + .opcode = opcode, + .payload_in = in, + .size_in = in_size, + .size_out = out_size, + .payload_out = out, + }; + int rc; + + if (out_size > cxlm->payload_size) + return -E2BIG; + + rc = cxlm->mbox_send(cxlm, &mbox_cmd); + if (rc) + return rc; + + /* TODO: Map return code to proper kernel style errno */ + if (mbox_cmd.return_code != CXL_MBOX_SUCCESS) + return -ENXIO; + + /* + * Variable sized commands can't be validated and so it's up to the + * caller to do that if they wish. + */ + if (cmd->info.size_out >= 0 && mbox_cmd.size_out != out_size) + return -EIO; + + return 0; +} +EXPORT_SYMBOL_GPL(cxl_mem_mbox_send_cmd); + +static bool cxl_mem_raw_command_allowed(u16 opcode) +{ + int i; + + if (!IS_ENABLED(CONFIG_CXL_MEM_RAW_COMMANDS)) + return false; + + if (security_locked_down(LOCKDOWN_PCI_ACCESS)) + return false; + + if (cxl_raw_allow_all) + return true; + + if (cxl_is_security_command(opcode)) + return false; + + for (i = 0; i < ARRAY_SIZE(cxl_disabled_raw_commands); i++) + if (cxl_disabled_raw_commands[i] == opcode) + return false; + + return true; +} + +/** + * cxl_validate_cmd_from_user() - Check fields for CXL_MEM_SEND_COMMAND. + * @cxlm: &struct cxl_mem device whose mailbox will be used. + * @send_cmd: &struct cxl_send_command copied in from userspace. + * @out_cmd: Sanitized and populated &struct cxl_mem_command. + * + * Return: + * * %0 - @out_cmd is ready to send. + * * %-ENOTTY - Invalid command specified. + * * %-EINVAL - Reserved fields or invalid values were used. + * * %-ENOMEM - Input or output buffer wasn't sized properly. + * * %-EPERM - Attempted to use a protected command. + * + * The result of this command is a fully validated command in @out_cmd that is + * safe to send to the hardware. + * + * See handle_mailbox_cmd_from_user() + */ +static int cxl_validate_cmd_from_user(struct cxl_mem *cxlm, + const struct cxl_send_command *send_cmd, + struct cxl_mem_command *out_cmd) +{ + const struct cxl_command_info *info; + struct cxl_mem_command *c; + + if (send_cmd->id == 0 || send_cmd->id >= CXL_MEM_COMMAND_ID_MAX) + return -ENOTTY; + + /* + * The user can never specify an input payload larger than what hardware + * supports, but output can be arbitrarily large (simply write out as + * much data as the hardware provides). + */ + if (send_cmd->in.size > cxlm->payload_size) + return -EINVAL; + + /* + * Checks are bypassed for raw commands but a WARN/taint will occur + * later in the callchain + */ + if (send_cmd->id == CXL_MEM_COMMAND_ID_RAW) { + const struct cxl_mem_command temp = { + .info = { + .id = CXL_MEM_COMMAND_ID_RAW, + .flags = 0, + .size_in = send_cmd->in.size, + .size_out = send_cmd->out.size, + }, + .opcode = send_cmd->raw.opcode + }; + + if (send_cmd->raw.rsvd) + return -EINVAL; + + /* + * Unlike supported commands, the output size of RAW commands + * gets passed along without further checking, so it must be + * validated here. + */ + if (send_cmd->out.size > cxlm->payload_size) + return -EINVAL; + + if (!cxl_mem_raw_command_allowed(send_cmd->raw.opcode)) + return -EPERM; + + memcpy(out_cmd, &temp, sizeof(temp)); + + return 0; + } + + if (send_cmd->flags & ~CXL_MEM_COMMAND_FLAG_MASK) + return -EINVAL; + + if (send_cmd->rsvd) + return -EINVAL; + + if (send_cmd->in.rsvd || send_cmd->out.rsvd) + return -EINVAL; + + /* Convert user's command into the internal representation */ + c = &cxl_mem_commands[send_cmd->id]; + info = &c->info; + + /* Check that the command is enabled for hardware */ + if (!test_bit(info->id, cxlm->enabled_cmds)) + return -ENOTTY; + + /* Check the input buffer is the expected size */ + if (info->size_in >= 0 && info->size_in != send_cmd->in.size) + return -ENOMEM; + + /* Check the output buffer is at least large enough */ + if (info->size_out >= 0 && send_cmd->out.size < info->size_out) + return -ENOMEM; + + memcpy(out_cmd, c, sizeof(*c)); + out_cmd->info.size_in = send_cmd->in.size; + /* + * XXX: out_cmd->info.size_out will be controlled by the driver, and the + * specified number of bytes @send_cmd->out.size will be copied back out + * to userspace. + */ + + return 0; +} + +#define cxl_cmd_count ARRAY_SIZE(cxl_mem_commands) + +int cxl_query_cmd(struct cxl_memdev *cxlmd, + struct cxl_mem_query_commands __user *q) +{ + struct device *dev = &cxlmd->dev; + struct cxl_mem_command *cmd; + u32 n_commands; + int j = 0; + + dev_dbg(dev, "Query IOCTL\n"); + + if (get_user(n_commands, &q->n_commands)) + return -EFAULT; + + /* returns the total number if 0 elements are requested. */ + if (n_commands == 0) + return put_user(cxl_cmd_count, &q->n_commands); + + /* + * otherwise, return max(n_commands, total commands) cxl_command_info + * structures. + */ + cxl_for_each_cmd(cmd) { + const struct cxl_command_info *info = &cmd->info; + + if (copy_to_user(&q->commands[j++], info, sizeof(*info))) + return -EFAULT; + + if (j == n_commands) + break; + } + + return 0; +} + +/** + * handle_mailbox_cmd_from_user() - Dispatch a mailbox command for userspace. + * @cxlm: The CXL memory device to communicate with. + * @cmd: The validated command. + * @in_payload: Pointer to userspace's input payload. + * @out_payload: Pointer to userspace's output payload. + * @size_out: (Input) Max payload size to copy out. + * (Output) Payload size hardware generated. + * @retval: Hardware generated return code from the operation. + * + * Return: + * * %0 - Mailbox transaction succeeded. This implies the mailbox + * protocol completed successfully not that the operation itself + * was successful. + * * %-ENOMEM - Couldn't allocate a bounce buffer. + * * %-EFAULT - Something happened with copy_to/from_user. + * * %-EINTR - Mailbox acquisition interrupted. + * * %-EXXX - Transaction level failures. + * + * Creates the appropriate mailbox command and dispatches it on behalf of a + * userspace request. The input and output payloads are copied between + * userspace. + * + * See cxl_send_cmd(). + */ +static int handle_mailbox_cmd_from_user(struct cxl_mem *cxlm, + const struct cxl_mem_command *cmd, + u64 in_payload, u64 out_payload, + s32 *size_out, u32 *retval) +{ + struct device *dev = cxlm->dev; + struct cxl_mbox_cmd mbox_cmd = { + .opcode = cmd->opcode, + .size_in = cmd->info.size_in, + .size_out = cmd->info.size_out, + }; + int rc; + + if (cmd->info.size_out) { + mbox_cmd.payload_out = kvzalloc(cmd->info.size_out, GFP_KERNEL); + if (!mbox_cmd.payload_out) + return -ENOMEM; + } + + if (cmd->info.size_in) { + mbox_cmd.payload_in = vmemdup_user(u64_to_user_ptr(in_payload), + cmd->info.size_in); + if (IS_ERR(mbox_cmd.payload_in)) { + kvfree(mbox_cmd.payload_out); + return PTR_ERR(mbox_cmd.payload_in); + } + } + + dev_dbg(dev, + "Submitting %s command for user\n" + "\topcode: %x\n" + "\tsize: %ub\n", + cxl_command_names[cmd->info.id].name, mbox_cmd.opcode, + cmd->info.size_in); + + dev_WARN_ONCE(dev, cmd->info.id == CXL_MEM_COMMAND_ID_RAW, + "raw command path used\n"); + + rc = cxlm->mbox_send(cxlm, &mbox_cmd); + if (rc) + goto out; + + /* + * @size_out contains the max size that's allowed to be written back out + * to userspace. While the payload may have written more output than + * this it will have to be ignored. + */ + if (mbox_cmd.size_out) { + dev_WARN_ONCE(dev, mbox_cmd.size_out > *size_out, + "Invalid return size\n"); + if (copy_to_user(u64_to_user_ptr(out_payload), + mbox_cmd.payload_out, mbox_cmd.size_out)) { + rc = -EFAULT; + goto out; + } + } + + *size_out = mbox_cmd.size_out; + *retval = mbox_cmd.return_code; + +out: + kvfree(mbox_cmd.payload_in); + kvfree(mbox_cmd.payload_out); + return rc; +} + +int cxl_send_cmd(struct cxl_memdev *cxlmd, struct cxl_send_command __user *s) +{ + struct cxl_mem *cxlm = cxlmd->cxlm; + struct device *dev = &cxlmd->dev; + struct cxl_send_command send; + struct cxl_mem_command c; + int rc; + + dev_dbg(dev, "Send IOCTL\n"); + + if (copy_from_user(&send, s, sizeof(send))) + return -EFAULT; + + rc = cxl_validate_cmd_from_user(cxlmd->cxlm, &send, &c); + if (rc) + return rc; + + /* Prepare to handle a full payload for variable sized output */ + if (c.info.size_out < 0) + c.info.size_out = cxlm->payload_size; + + rc = handle_mailbox_cmd_from_user(cxlm, &c, send.in.payload, + send.out.payload, &send.out.size, + &send.retval); + if (rc) + return rc; + + if (copy_to_user(s, &send, sizeof(send))) + return -EFAULT; + + return 0; +} + +static int cxl_xfer_log(struct cxl_mem *cxlm, uuid_t *uuid, u32 size, u8 *out) +{ + u32 remaining = size; + u32 offset = 0; + + while (remaining) { + u32 xfer_size = min_t(u32, remaining, cxlm->payload_size); + struct cxl_mbox_get_log { + uuid_t uuid; + __le32 offset; + __le32 length; + } __packed log = { + .uuid = *uuid, + .offset = cpu_to_le32(offset), + .length = cpu_to_le32(xfer_size) + }; + int rc; + + rc = cxl_mem_mbox_send_cmd(cxlm, CXL_MBOX_OP_GET_LOG, &log, + sizeof(log), out, xfer_size); + if (rc < 0) + return rc; + + out += xfer_size; + remaining -= xfer_size; + offset += xfer_size; + } + + return 0; +} + +/** + * cxl_walk_cel() - Walk through the Command Effects Log. + * @cxlm: Device. + * @size: Length of the Command Effects Log. + * @cel: CEL + * + * Iterate over each entry in the CEL and determine if the driver supports the + * command. If so, the command is enabled for the device and can be used later. + */ +static void cxl_walk_cel(struct cxl_mem *cxlm, size_t size, u8 *cel) +{ + struct cel_entry { + __le16 opcode; + __le16 effect; + } __packed * cel_entry; + const int cel_entries = size / sizeof(*cel_entry); + int i; + + cel_entry = (struct cel_entry *)cel; + + for (i = 0; i < cel_entries; i++) { + u16 opcode = le16_to_cpu(cel_entry[i].opcode); + struct cxl_mem_command *cmd = cxl_mem_find_command(opcode); + + if (!cmd) { + dev_dbg(cxlm->dev, + "Opcode 0x%04x unsupported by driver", opcode); + continue; + } + + set_bit(cmd->info.id, cxlm->enabled_cmds); + } +} + +struct cxl_mbox_get_supported_logs { + __le16 entries; + u8 rsvd[6]; + struct gsl_entry { + uuid_t uuid; + __le32 size; + } __packed entry[]; +} __packed; + +static struct cxl_mbox_get_supported_logs *cxl_get_gsl(struct cxl_mem *cxlm) +{ + struct cxl_mbox_get_supported_logs *ret; + int rc; + + ret = kvmalloc(cxlm->payload_size, GFP_KERNEL); + if (!ret) + return ERR_PTR(-ENOMEM); + + rc = cxl_mem_mbox_send_cmd(cxlm, CXL_MBOX_OP_GET_SUPPORTED_LOGS, NULL, + 0, ret, cxlm->payload_size); + if (rc < 0) { + kvfree(ret); + return ERR_PTR(rc); + } + + return ret; +} + +enum { + CEL_UUID, + VENDOR_DEBUG_UUID, +}; + +/* See CXL 2.0 Table 170. Get Log Input Payload */ +static const uuid_t log_uuid[] = { + [CEL_UUID] = UUID_INIT(0xda9c0b5, 0xbf41, 0x4b78, 0x8f, 0x79, 0x96, + 0xb1, 0x62, 0x3b, 0x3f, 0x17), + [VENDOR_DEBUG_UUID] = UUID_INIT(0xe1819d9, 0x11a9, 0x400c, 0x81, 0x1f, + 0xd6, 0x07, 0x19, 0x40, 0x3d, 0x86), +}; + +/** + * cxl_mem_enumerate_cmds() - Enumerate commands for a device. + * @cxlm: The device. + * + * Returns 0 if enumerate completed successfully. + * + * CXL devices have optional support for certain commands. This function will + * determine the set of supported commands for the hardware and update the + * enabled_cmds bitmap in the @cxlm. + */ +int cxl_mem_enumerate_cmds(struct cxl_mem *cxlm) +{ + struct cxl_mbox_get_supported_logs *gsl; + struct device *dev = cxlm->dev; + struct cxl_mem_command *cmd; + int i, rc; + + gsl = cxl_get_gsl(cxlm); + if (IS_ERR(gsl)) + return PTR_ERR(gsl); + + rc = -ENOENT; + for (i = 0; i < le16_to_cpu(gsl->entries); i++) { + u32 size = le32_to_cpu(gsl->entry[i].size); + uuid_t uuid = gsl->entry[i].uuid; + u8 *log; + + dev_dbg(dev, "Found LOG type %pU of size %d", &uuid, size); + + if (!uuid_equal(&uuid, &log_uuid[CEL_UUID])) + continue; + + log = kvmalloc(size, GFP_KERNEL); + if (!log) { + rc = -ENOMEM; + goto out; + } + + rc = cxl_xfer_log(cxlm, &uuid, size, log); + if (rc) { + kvfree(log); + goto out; + } + + cxl_walk_cel(cxlm, size, log); + kvfree(log); + + /* In case CEL was bogus, enable some default commands. */ + cxl_for_each_cmd(cmd) + if (cmd->flags & CXL_CMD_FLAG_FORCE_ENABLE) + set_bit(cmd->info.id, cxlm->enabled_cmds); + + /* Found the required CEL */ + rc = 0; + } + +out: + kvfree(gsl); + return rc; +} +EXPORT_SYMBOL_GPL(cxl_mem_enumerate_cmds); + +/** + * cxl_mem_get_partition_info - Get partition info + * @cxlm: cxl_mem instance to update partition info + * + * Retrieve the current partition info for the device specified. The active + * values are the current capacity in bytes. If not 0, the 'next' values are + * the pending values, in bytes, which take affect on next cold reset. + * + * Return: 0 if no error: or the result of the mailbox command. + * + * See CXL @8.2.9.5.2.1 Get Partition Info + */ +static int cxl_mem_get_partition_info(struct cxl_mem *cxlm) +{ + struct cxl_mbox_get_partition_info { + __le64 active_volatile_cap; + __le64 active_persistent_cap; + __le64 next_volatile_cap; + __le64 next_persistent_cap; + } __packed pi; + int rc; + + rc = cxl_mem_mbox_send_cmd(cxlm, CXL_MBOX_OP_GET_PARTITION_INFO, + NULL, 0, &pi, sizeof(pi)); + + if (rc) + return rc; + + cxlm->active_volatile_bytes = + le64_to_cpu(pi.active_volatile_cap) * CXL_CAPACITY_MULTIPLIER; + cxlm->active_persistent_bytes = + le64_to_cpu(pi.active_persistent_cap) * CXL_CAPACITY_MULTIPLIER; + cxlm->next_volatile_bytes = + le64_to_cpu(pi.next_volatile_cap) * CXL_CAPACITY_MULTIPLIER; + cxlm->next_persistent_bytes = + le64_to_cpu(pi.next_volatile_cap) * CXL_CAPACITY_MULTIPLIER; + + return 0; +} + +/** + * cxl_mem_identify() - Send the IDENTIFY command to the device. + * @cxlm: The device to identify. + * + * Return: 0 if identify was executed successfully. + * + * This will dispatch the identify command to the device and on success populate + * structures to be exported to sysfs. + */ +int cxl_mem_identify(struct cxl_mem *cxlm) +{ + /* See CXL 2.0 Table 175 Identify Memory Device Output Payload */ + struct cxl_mbox_identify { + char fw_revision[0x10]; + __le64 total_capacity; + __le64 volatile_capacity; + __le64 persistent_capacity; + __le64 partition_align; + __le16 info_event_log_size; + __le16 warning_event_log_size; + __le16 failure_event_log_size; + __le16 fatal_event_log_size; + __le32 lsa_size; + u8 poison_list_max_mer[3]; + __le16 inject_poison_limit; + u8 poison_caps; + u8 qos_telemetry_caps; + } __packed id; + int rc; + + rc = cxl_mem_mbox_send_cmd(cxlm, CXL_MBOX_OP_IDENTIFY, NULL, 0, &id, + sizeof(id)); + if (rc < 0) + return rc; + + cxlm->total_bytes = + le64_to_cpu(id.total_capacity) * CXL_CAPACITY_MULTIPLIER; + cxlm->volatile_only_bytes = + le64_to_cpu(id.volatile_capacity) * CXL_CAPACITY_MULTIPLIER; + cxlm->persistent_only_bytes = + le64_to_cpu(id.persistent_capacity) * CXL_CAPACITY_MULTIPLIER; + cxlm->partition_align_bytes = + le64_to_cpu(id.partition_align) * CXL_CAPACITY_MULTIPLIER; + + dev_dbg(cxlm->dev, + "Identify Memory Device\n" + " total_bytes = %#llx\n" + " volatile_only_bytes = %#llx\n" + " persistent_only_bytes = %#llx\n" + " partition_align_bytes = %#llx\n", + cxlm->total_bytes, cxlm->volatile_only_bytes, + cxlm->persistent_only_bytes, cxlm->partition_align_bytes); + + cxlm->lsa_size = le32_to_cpu(id.lsa_size); + memcpy(cxlm->firmware_version, id.fw_revision, sizeof(id.fw_revision)); + + return 0; +} +EXPORT_SYMBOL_GPL(cxl_mem_identify); + +int cxl_mem_create_range_info(struct cxl_mem *cxlm) +{ + int rc; + + if (cxlm->partition_align_bytes == 0) { + cxlm->ram_range.start = 0; + cxlm->ram_range.end = cxlm->volatile_only_bytes - 1; + cxlm->pmem_range.start = cxlm->volatile_only_bytes; + cxlm->pmem_range.end = cxlm->volatile_only_bytes + + cxlm->persistent_only_bytes - 1; + return 0; + } + + rc = cxl_mem_get_partition_info(cxlm); + if (rc) { + dev_err(cxlm->dev, "Failed to query partition information\n"); + return rc; + } + + dev_dbg(cxlm->dev, + "Get Partition Info\n" + " active_volatile_bytes = %#llx\n" + " active_persistent_bytes = %#llx\n" + " next_volatile_bytes = %#llx\n" + " next_persistent_bytes = %#llx\n", + cxlm->active_volatile_bytes, cxlm->active_persistent_bytes, + cxlm->next_volatile_bytes, cxlm->next_persistent_bytes); + + cxlm->ram_range.start = 0; + cxlm->ram_range.end = cxlm->active_volatile_bytes - 1; + + cxlm->pmem_range.start = cxlm->active_volatile_bytes; + cxlm->pmem_range.end = + cxlm->active_volatile_bytes + cxlm->active_persistent_bytes - 1; + + return 0; +} +EXPORT_SYMBOL_GPL(cxl_mem_create_range_info); + +struct cxl_mem *cxl_mem_create(struct device *dev) +{ + struct cxl_mem *cxlm; + + cxlm = devm_kzalloc(dev, sizeof(*cxlm), GFP_KERNEL); + if (!cxlm) { + dev_err(dev, "No memory available\n"); + return ERR_PTR(-ENOMEM); + } + + mutex_init(&cxlm->mbox_mutex); + cxlm->dev = dev; + cxlm->enabled_cmds = + devm_kmalloc_array(dev, BITS_TO_LONGS(cxl_cmd_count), + sizeof(unsigned long), + GFP_KERNEL | __GFP_ZERO); + if (!cxlm->enabled_cmds) { + dev_err(dev, "No memory available for bitmap\n"); + return ERR_PTR(-ENOMEM); + } + + return cxlm; +} +EXPORT_SYMBOL_GPL(cxl_mem_create); + +static struct dentry *cxl_debugfs; + +void __init cxl_mbox_init(void) +{ + struct dentry *mbox_debugfs; + + cxl_debugfs = debugfs_create_dir("cxl", NULL); + mbox_debugfs = debugfs_create_dir("mbox", cxl_debugfs); + debugfs_create_bool("raw_allow_all", 0600, mbox_debugfs, + &cxl_raw_allow_all); +} + +void cxl_mbox_exit(void) +{ + debugfs_remove_recursive(cxl_debugfs); +} diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index 331ef7d6c598..df2ba87238c2 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -8,6 +8,8 @@ #include #include "core.h" +static DECLARE_RWSEM(cxl_memdev_rwsem); + /* * An entire PCI topology full of devices should be enough for any * config @@ -132,16 +134,21 @@ static const struct device_type cxl_memdev_type = { .groups = cxl_memdev_attribute_groups, }; +static void cxl_memdev_shutdown(struct device *dev) +{ + struct cxl_memdev *cxlmd = to_cxl_memdev(dev); + + down_write(&cxl_memdev_rwsem); + cxlmd->cxlm = NULL; + up_write(&cxl_memdev_rwsem); +} + static void cxl_memdev_unregister(void *_cxlmd) { struct cxl_memdev *cxlmd = _cxlmd; struct device *dev = &cxlmd->dev; - struct cdev *cdev = &cxlmd->cdev; - const struct cdevm_file_operations *cdevm_fops; - - cdevm_fops = container_of(cdev->ops, typeof(*cdevm_fops), fops); - cdevm_fops->shutdown(dev); + cxl_memdev_shutdown(dev); cdev_device_del(&cxlmd->cdev, dev); put_device(dev); } @@ -180,16 +187,72 @@ err: return ERR_PTR(rc); } +static long __cxl_memdev_ioctl(struct cxl_memdev *cxlmd, unsigned int cmd, + unsigned long arg) +{ + switch (cmd) { + case CXL_MEM_QUERY_COMMANDS: + return cxl_query_cmd(cxlmd, (void __user *)arg); + case CXL_MEM_SEND_COMMAND: + return cxl_send_cmd(cxlmd, (void __user *)arg); + default: + return -ENOTTY; + } +} + +static long cxl_memdev_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + struct cxl_memdev *cxlmd = file->private_data; + int rc = -ENXIO; + + down_read(&cxl_memdev_rwsem); + if (cxlmd->cxlm) + rc = __cxl_memdev_ioctl(cxlmd, cmd, arg); + up_read(&cxl_memdev_rwsem); + + return rc; +} + +static int cxl_memdev_open(struct inode *inode, struct file *file) +{ + struct cxl_memdev *cxlmd = + container_of(inode->i_cdev, typeof(*cxlmd), cdev); + + get_device(&cxlmd->dev); + file->private_data = cxlmd; + + return 0; +} + +static int cxl_memdev_release_file(struct inode *inode, struct file *file) +{ + struct cxl_memdev *cxlmd = + container_of(inode->i_cdev, typeof(*cxlmd), cdev); + + put_device(&cxlmd->dev); + + return 0; +} + +static const struct file_operations cxl_memdev_fops = { + .owner = THIS_MODULE, + .unlocked_ioctl = cxl_memdev_ioctl, + .open = cxl_memdev_open, + .release = cxl_memdev_release_file, + .compat_ioctl = compat_ptr_ioctl, + .llseek = noop_llseek, +}; + struct cxl_memdev * -devm_cxl_add_memdev(struct cxl_mem *cxlm, - const struct cdevm_file_operations *cdevm_fops) +devm_cxl_add_memdev(struct cxl_mem *cxlm) { struct cxl_memdev *cxlmd; struct device *dev; struct cdev *cdev; int rc; - cxlmd = cxl_memdev_alloc(cxlm, &cdevm_fops->fops); + cxlmd = cxl_memdev_alloc(cxlm, &cxl_memdev_fops); if (IS_ERR(cxlmd)) return cxlmd; @@ -219,7 +282,7 @@ err: * The cdev was briefly live, shutdown any ioctl operations that * saw that state. */ - cdevm_fops->shutdown(dev); + cxl_memdev_shutdown(dev); put_device(dev); return ERR_PTR(rc); } diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index c142532db8cb..f5d3326a1d0b 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -2,6 +2,7 @@ /* Copyright(c) 2020-2021 Intel Corporation. */ #ifndef __CXL_MEM_H__ #define __CXL_MEM_H__ +#include #include #include "cxl.h" @@ -28,21 +29,6 @@ (FIELD_GET(CXLMDEV_RESET_NEEDED_MASK, status) != \ CXLMDEV_RESET_NEEDED_NOT) -/** - * struct cdevm_file_operations - devm coordinated cdev file operations - * @fops: file operations that are synchronized against @shutdown - * @shutdown: disconnect driver data - * - * @shutdown is invoked in the devres release path to disconnect any - * driver instance data from @dev. It assumes synchronization with any - * fops operation that requires driver data. After @shutdown an - * operation may only reference @device data. - */ -struct cdevm_file_operations { - struct file_operations fops; - void (*shutdown)(struct device *dev); -}; - /** * struct cxl_memdev - CXL bus object representing a Type-3 Memory Device * @dev: driver core device object @@ -62,9 +48,7 @@ static inline struct cxl_memdev *to_cxl_memdev(struct device *dev) return container_of(dev, struct cxl_memdev, dev); } -struct cxl_memdev * -devm_cxl_add_memdev(struct cxl_mem *cxlm, - const struct cdevm_file_operations *cdevm_fops); +struct cxl_memdev *devm_cxl_add_memdev(struct cxl_mem *cxlm); /** * struct cxl_mbox_cmd - A command to be submitted to hardware. @@ -158,4 +142,62 @@ struct cxl_mem { int (*mbox_send)(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd); }; + +enum cxl_opcode { + CXL_MBOX_OP_INVALID = 0x0000, + CXL_MBOX_OP_RAW = CXL_MBOX_OP_INVALID, + CXL_MBOX_OP_GET_FW_INFO = 0x0200, + CXL_MBOX_OP_ACTIVATE_FW = 0x0202, + CXL_MBOX_OP_GET_SUPPORTED_LOGS = 0x0400, + CXL_MBOX_OP_GET_LOG = 0x0401, + CXL_MBOX_OP_IDENTIFY = 0x4000, + CXL_MBOX_OP_GET_PARTITION_INFO = 0x4100, + CXL_MBOX_OP_SET_PARTITION_INFO = 0x4101, + CXL_MBOX_OP_GET_LSA = 0x4102, + CXL_MBOX_OP_SET_LSA = 0x4103, + CXL_MBOX_OP_GET_HEALTH_INFO = 0x4200, + CXL_MBOX_OP_GET_ALERT_CONFIG = 0x4201, + CXL_MBOX_OP_SET_ALERT_CONFIG = 0x4202, + CXL_MBOX_OP_GET_SHUTDOWN_STATE = 0x4203, + CXL_MBOX_OP_SET_SHUTDOWN_STATE = 0x4204, + CXL_MBOX_OP_GET_POISON = 0x4300, + CXL_MBOX_OP_INJECT_POISON = 0x4301, + CXL_MBOX_OP_CLEAR_POISON = 0x4302, + CXL_MBOX_OP_GET_SCAN_MEDIA_CAPS = 0x4303, + CXL_MBOX_OP_SCAN_MEDIA = 0x4304, + CXL_MBOX_OP_GET_SCAN_MEDIA = 0x4305, + CXL_MBOX_OP_MAX = 0x10000 +}; + +/** + * struct cxl_mem_command - Driver representation of a memory device command + * @info: Command information as it exists for the UAPI + * @opcode: The actual bits used for the mailbox protocol + * @flags: Set of flags effecting driver behavior. + * + * * %CXL_CMD_FLAG_FORCE_ENABLE: In cases of error, commands with this flag + * will be enabled by the driver regardless of what hardware may have + * advertised. + * + * The cxl_mem_command is the driver's internal representation of commands that + * are supported by the driver. Some of these commands may not be supported by + * the hardware. The driver will use @info to validate the fields passed in by + * the user then submit the @opcode to the hardware. + * + * See struct cxl_command_info. + */ +struct cxl_mem_command { + struct cxl_command_info info; + enum cxl_opcode opcode; + u32 flags; +#define CXL_CMD_FLAG_NONE 0 +#define CXL_CMD_FLAG_FORCE_ENABLE BIT(0) +}; + +int cxl_mem_mbox_send_cmd(struct cxl_mem *cxlm, u16 opcode, void *in, + size_t in_size, void *out, size_t out_size); +int cxl_mem_identify(struct cxl_mem *cxlm); +int cxl_mem_enumerate_cmds(struct cxl_mem *cxlm); +int cxl_mem_create_range_info(struct cxl_mem *cxlm); +struct cxl_mem *cxl_mem_create(struct device *dev); #endif /* __CXL_MEM_H__ */ diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 9d8050fdd69c..c9f2ac134f4d 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -1,16 +1,12 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright(c) 2020 Intel Corporation. All rights reserved. */ -#include -#include -#include +#include #include #include #include #include -#include #include #include -#include #include "cxlmem.h" #include "pci.h" #include "cxl.h" @@ -37,162 +33,6 @@ /* CXL 2.0 - 8.2.8.4 */ #define CXL_MAILBOX_TIMEOUT_MS (2 * HZ) -enum opcode { - CXL_MBOX_OP_INVALID = 0x0000, - CXL_MBOX_OP_RAW = CXL_MBOX_OP_INVALID, - CXL_MBOX_OP_GET_FW_INFO = 0x0200, - CXL_MBOX_OP_ACTIVATE_FW = 0x0202, - CXL_MBOX_OP_GET_SUPPORTED_LOGS = 0x0400, - CXL_MBOX_OP_GET_LOG = 0x0401, - CXL_MBOX_OP_IDENTIFY = 0x4000, - CXL_MBOX_OP_GET_PARTITION_INFO = 0x4100, - CXL_MBOX_OP_SET_PARTITION_INFO = 0x4101, - CXL_MBOX_OP_GET_LSA = 0x4102, - CXL_MBOX_OP_SET_LSA = 0x4103, - CXL_MBOX_OP_GET_HEALTH_INFO = 0x4200, - CXL_MBOX_OP_GET_ALERT_CONFIG = 0x4201, - CXL_MBOX_OP_SET_ALERT_CONFIG = 0x4202, - CXL_MBOX_OP_GET_SHUTDOWN_STATE = 0x4203, - CXL_MBOX_OP_SET_SHUTDOWN_STATE = 0x4204, - CXL_MBOX_OP_GET_POISON = 0x4300, - CXL_MBOX_OP_INJECT_POISON = 0x4301, - CXL_MBOX_OP_CLEAR_POISON = 0x4302, - CXL_MBOX_OP_GET_SCAN_MEDIA_CAPS = 0x4303, - CXL_MBOX_OP_SCAN_MEDIA = 0x4304, - CXL_MBOX_OP_GET_SCAN_MEDIA = 0x4305, - CXL_MBOX_OP_MAX = 0x10000 -}; - -static DECLARE_RWSEM(cxl_memdev_rwsem); -static struct dentry *cxl_debugfs; -static bool cxl_raw_allow_all; - -enum { - CEL_UUID, - VENDOR_DEBUG_UUID, -}; - -/* See CXL 2.0 Table 170. Get Log Input Payload */ -static const uuid_t log_uuid[] = { - [CEL_UUID] = UUID_INIT(0xda9c0b5, 0xbf41, 0x4b78, 0x8f, 0x79, 0x96, - 0xb1, 0x62, 0x3b, 0x3f, 0x17), - [VENDOR_DEBUG_UUID] = UUID_INIT(0xe1819d9, 0x11a9, 0x400c, 0x81, 0x1f, - 0xd6, 0x07, 0x19, 0x40, 0x3d, 0x86), -}; - -/** - * struct cxl_mem_command - Driver representation of a memory device command - * @info: Command information as it exists for the UAPI - * @opcode: The actual bits used for the mailbox protocol - * @flags: Set of flags effecting driver behavior. - * - * * %CXL_CMD_FLAG_FORCE_ENABLE: In cases of error, commands with this flag - * will be enabled by the driver regardless of what hardware may have - * advertised. - * - * The cxl_mem_command is the driver's internal representation of commands that - * are supported by the driver. Some of these commands may not be supported by - * the hardware. The driver will use @info to validate the fields passed in by - * the user then submit the @opcode to the hardware. - * - * See struct cxl_command_info. - */ -struct cxl_mem_command { - struct cxl_command_info info; - enum opcode opcode; - u32 flags; -#define CXL_CMD_FLAG_NONE 0 -#define CXL_CMD_FLAG_FORCE_ENABLE BIT(0) -}; - -#define CXL_CMD(_id, sin, sout, _flags) \ - [CXL_MEM_COMMAND_ID_##_id] = { \ - .info = { \ - .id = CXL_MEM_COMMAND_ID_##_id, \ - .size_in = sin, \ - .size_out = sout, \ - }, \ - .opcode = CXL_MBOX_OP_##_id, \ - .flags = _flags, \ - } - -/* - * This table defines the supported mailbox commands for the driver. This table - * is made up of a UAPI structure. Non-negative values as parameters in the - * table will be validated against the user's input. For example, if size_in is - * 0, and the user passed in 1, it is an error. - */ -static struct cxl_mem_command mem_commands[CXL_MEM_COMMAND_ID_MAX] = { - CXL_CMD(IDENTIFY, 0, 0x43, CXL_CMD_FLAG_FORCE_ENABLE), -#ifdef CONFIG_CXL_MEM_RAW_COMMANDS - CXL_CMD(RAW, ~0, ~0, 0), -#endif - CXL_CMD(GET_SUPPORTED_LOGS, 0, ~0, CXL_CMD_FLAG_FORCE_ENABLE), - CXL_CMD(GET_FW_INFO, 0, 0x50, 0), - CXL_CMD(GET_PARTITION_INFO, 0, 0x20, 0), - CXL_CMD(GET_LSA, 0x8, ~0, 0), - CXL_CMD(GET_HEALTH_INFO, 0, 0x12, 0), - CXL_CMD(GET_LOG, 0x18, ~0, CXL_CMD_FLAG_FORCE_ENABLE), - CXL_CMD(SET_PARTITION_INFO, 0x0a, 0, 0), - CXL_CMD(SET_LSA, ~0, 0, 0), - CXL_CMD(GET_ALERT_CONFIG, 0, 0x10, 0), - CXL_CMD(SET_ALERT_CONFIG, 0xc, 0, 0), - CXL_CMD(GET_SHUTDOWN_STATE, 0, 0x1, 0), - CXL_CMD(SET_SHUTDOWN_STATE, 0x1, 0, 0), - CXL_CMD(GET_POISON, 0x10, ~0, 0), - CXL_CMD(INJECT_POISON, 0x8, 0, 0), - CXL_CMD(CLEAR_POISON, 0x48, 0, 0), - CXL_CMD(GET_SCAN_MEDIA_CAPS, 0x10, 0x4, 0), - CXL_CMD(SCAN_MEDIA, 0x11, 0, 0), - CXL_CMD(GET_SCAN_MEDIA, 0, ~0, 0), -}; - -/* - * Commands that RAW doesn't permit. The rationale for each: - * - * CXL_MBOX_OP_ACTIVATE_FW: Firmware activation requires adjustment / - * coordination of transaction timeout values at the root bridge level. - * - * CXL_MBOX_OP_SET_PARTITION_INFO: The device memory map may change live - * and needs to be coordinated with HDM updates. - * - * CXL_MBOX_OP_SET_LSA: The label storage area may be cached by the - * driver and any writes from userspace invalidates those contents. - * - * CXL_MBOX_OP_SET_SHUTDOWN_STATE: Set shutdown state assumes no writes - * to the device after it is marked clean, userspace can not make that - * assertion. - * - * CXL_MBOX_OP_[GET_]SCAN_MEDIA: The kernel provides a native error list that - * is kept up to date with patrol notifications and error management. - */ -static u16 cxl_disabled_raw_commands[] = { - CXL_MBOX_OP_ACTIVATE_FW, - CXL_MBOX_OP_SET_PARTITION_INFO, - CXL_MBOX_OP_SET_LSA, - CXL_MBOX_OP_SET_SHUTDOWN_STATE, - CXL_MBOX_OP_SCAN_MEDIA, - CXL_MBOX_OP_GET_SCAN_MEDIA, -}; - -/* - * Command sets that RAW doesn't permit. All opcodes in this set are - * disabled because they pass plain text security payloads over the - * user/kernel boundary. This functionality is intended to be wrapped - * behind the keys ABI which allows for encrypted payloads in the UAPI - */ -static u8 security_command_sets[] = { - 0x44, /* Sanitize */ - 0x45, /* Persistent Memory Data-at-rest Security */ - 0x46, /* Security Passthrough */ -}; - -#define cxl_for_each_cmd(cmd) \ - for ((cmd) = &mem_commands[0]; \ - ((cmd) - mem_commands) < ARRAY_SIZE(mem_commands); (cmd)++) - -#define cxl_cmd_count ARRAY_SIZE(mem_commands) - static int cxl_mem_wait_for_doorbell(struct cxl_mem *cxlm) { const unsigned long start = jiffies; @@ -215,16 +55,6 @@ static int cxl_mem_wait_for_doorbell(struct cxl_mem *cxlm) return 0; } -static bool cxl_is_security_command(u16 opcode) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(security_command_sets); i++) - if (security_command_sets[i] == (opcode >> 8)) - return true; - return false; -} - static void cxl_mem_mbox_timeout(struct cxl_mem *cxlm, struct cxl_mbox_cmd *mbox_cmd) { @@ -446,433 +276,6 @@ static int cxl_pci_mbox_send(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd) return rc; } -/** - * handle_mailbox_cmd_from_user() - Dispatch a mailbox command for userspace. - * @cxlm: The CXL memory device to communicate with. - * @cmd: The validated command. - * @in_payload: Pointer to userspace's input payload. - * @out_payload: Pointer to userspace's output payload. - * @size_out: (Input) Max payload size to copy out. - * (Output) Payload size hardware generated. - * @retval: Hardware generated return code from the operation. - * - * Return: - * * %0 - Mailbox transaction succeeded. This implies the mailbox - * protocol completed successfully not that the operation itself - * was successful. - * * %-ENOMEM - Couldn't allocate a bounce buffer. - * * %-EFAULT - Something happened with copy_to/from_user. - * * %-EINTR - Mailbox acquisition interrupted. - * * %-EXXX - Transaction level failures. - * - * Creates the appropriate mailbox command and dispatches it on behalf of a - * userspace request. The input and output payloads are copied between - * userspace. - * - * See cxl_send_cmd(). - */ -static int handle_mailbox_cmd_from_user(struct cxl_mem *cxlm, - const struct cxl_mem_command *cmd, - u64 in_payload, u64 out_payload, - s32 *size_out, u32 *retval) -{ - struct device *dev = cxlm->dev; - struct cxl_mbox_cmd mbox_cmd = { - .opcode = cmd->opcode, - .size_in = cmd->info.size_in, - .size_out = cmd->info.size_out, - }; - int rc; - - if (cmd->info.size_out) { - mbox_cmd.payload_out = kvzalloc(cmd->info.size_out, GFP_KERNEL); - if (!mbox_cmd.payload_out) - return -ENOMEM; - } - - if (cmd->info.size_in) { - mbox_cmd.payload_in = vmemdup_user(u64_to_user_ptr(in_payload), - cmd->info.size_in); - if (IS_ERR(mbox_cmd.payload_in)) { - kvfree(mbox_cmd.payload_out); - return PTR_ERR(mbox_cmd.payload_in); - } - } - - dev_dbg(dev, - "Submitting %s command for user\n" - "\topcode: %x\n" - "\tsize: %ub\n", - cxl_command_names[cmd->info.id].name, mbox_cmd.opcode, - cmd->info.size_in); - - dev_WARN_ONCE(dev, cmd->info.id == CXL_MEM_COMMAND_ID_RAW, - "raw command path used\n"); - - rc = cxlm->mbox_send(cxlm, &mbox_cmd); - if (rc) - goto out; - - /* - * @size_out contains the max size that's allowed to be written back out - * to userspace. While the payload may have written more output than - * this it will have to be ignored. - */ - if (mbox_cmd.size_out) { - dev_WARN_ONCE(dev, mbox_cmd.size_out > *size_out, - "Invalid return size\n"); - if (copy_to_user(u64_to_user_ptr(out_payload), - mbox_cmd.payload_out, mbox_cmd.size_out)) { - rc = -EFAULT; - goto out; - } - } - - *size_out = mbox_cmd.size_out; - *retval = mbox_cmd.return_code; - -out: - kvfree(mbox_cmd.payload_in); - kvfree(mbox_cmd.payload_out); - return rc; -} - -static bool cxl_mem_raw_command_allowed(u16 opcode) -{ - int i; - - if (!IS_ENABLED(CONFIG_CXL_MEM_RAW_COMMANDS)) - return false; - - if (security_locked_down(LOCKDOWN_PCI_ACCESS)) - return false; - - if (cxl_raw_allow_all) - return true; - - if (cxl_is_security_command(opcode)) - return false; - - for (i = 0; i < ARRAY_SIZE(cxl_disabled_raw_commands); i++) - if (cxl_disabled_raw_commands[i] == opcode) - return false; - - return true; -} - -/** - * cxl_validate_cmd_from_user() - Check fields for CXL_MEM_SEND_COMMAND. - * @cxlm: &struct cxl_mem device whose mailbox will be used. - * @send_cmd: &struct cxl_send_command copied in from userspace. - * @out_cmd: Sanitized and populated &struct cxl_mem_command. - * - * Return: - * * %0 - @out_cmd is ready to send. - * * %-ENOTTY - Invalid command specified. - * * %-EINVAL - Reserved fields or invalid values were used. - * * %-ENOMEM - Input or output buffer wasn't sized properly. - * * %-EPERM - Attempted to use a protected command. - * - * The result of this command is a fully validated command in @out_cmd that is - * safe to send to the hardware. - * - * See handle_mailbox_cmd_from_user() - */ -static int cxl_validate_cmd_from_user(struct cxl_mem *cxlm, - const struct cxl_send_command *send_cmd, - struct cxl_mem_command *out_cmd) -{ - const struct cxl_command_info *info; - struct cxl_mem_command *c; - - if (send_cmd->id == 0 || send_cmd->id >= CXL_MEM_COMMAND_ID_MAX) - return -ENOTTY; - - /* - * The user can never specify an input payload larger than what hardware - * supports, but output can be arbitrarily large (simply write out as - * much data as the hardware provides). - */ - if (send_cmd->in.size > cxlm->payload_size) - return -EINVAL; - - /* - * Checks are bypassed for raw commands but a WARN/taint will occur - * later in the callchain - */ - if (send_cmd->id == CXL_MEM_COMMAND_ID_RAW) { - const struct cxl_mem_command temp = { - .info = { - .id = CXL_MEM_COMMAND_ID_RAW, - .flags = 0, - .size_in = send_cmd->in.size, - .size_out = send_cmd->out.size, - }, - .opcode = send_cmd->raw.opcode - }; - - if (send_cmd->raw.rsvd) - return -EINVAL; - - /* - * Unlike supported commands, the output size of RAW commands - * gets passed along without further checking, so it must be - * validated here. - */ - if (send_cmd->out.size > cxlm->payload_size) - return -EINVAL; - - if (!cxl_mem_raw_command_allowed(send_cmd->raw.opcode)) - return -EPERM; - - memcpy(out_cmd, &temp, sizeof(temp)); - - return 0; - } - - if (send_cmd->flags & ~CXL_MEM_COMMAND_FLAG_MASK) - return -EINVAL; - - if (send_cmd->rsvd) - return -EINVAL; - - if (send_cmd->in.rsvd || send_cmd->out.rsvd) - return -EINVAL; - - /* Convert user's command into the internal representation */ - c = &mem_commands[send_cmd->id]; - info = &c->info; - - /* Check that the command is enabled for hardware */ - if (!test_bit(info->id, cxlm->enabled_cmds)) - return -ENOTTY; - - /* Check the input buffer is the expected size */ - if (info->size_in >= 0 && info->size_in != send_cmd->in.size) - return -ENOMEM; - - /* Check the output buffer is at least large enough */ - if (info->size_out >= 0 && send_cmd->out.size < info->size_out) - return -ENOMEM; - - memcpy(out_cmd, c, sizeof(*c)); - out_cmd->info.size_in = send_cmd->in.size; - /* - * XXX: out_cmd->info.size_out will be controlled by the driver, and the - * specified number of bytes @send_cmd->out.size will be copied back out - * to userspace. - */ - - return 0; -} - -static int cxl_query_cmd(struct cxl_memdev *cxlmd, - struct cxl_mem_query_commands __user *q) -{ - struct device *dev = &cxlmd->dev; - struct cxl_mem_command *cmd; - u32 n_commands; - int j = 0; - - dev_dbg(dev, "Query IOCTL\n"); - - if (get_user(n_commands, &q->n_commands)) - return -EFAULT; - - /* returns the total number if 0 elements are requested. */ - if (n_commands == 0) - return put_user(cxl_cmd_count, &q->n_commands); - - /* - * otherwise, return max(n_commands, total commands) cxl_command_info - * structures. - */ - cxl_for_each_cmd(cmd) { - const struct cxl_command_info *info = &cmd->info; - - if (copy_to_user(&q->commands[j++], info, sizeof(*info))) - return -EFAULT; - - if (j == n_commands) - break; - } - - return 0; -} - -static int cxl_send_cmd(struct cxl_memdev *cxlmd, - struct cxl_send_command __user *s) -{ - struct cxl_mem *cxlm = cxlmd->cxlm; - struct device *dev = &cxlmd->dev; - struct cxl_send_command send; - struct cxl_mem_command c; - int rc; - - dev_dbg(dev, "Send IOCTL\n"); - - if (copy_from_user(&send, s, sizeof(send))) - return -EFAULT; - - rc = cxl_validate_cmd_from_user(cxlmd->cxlm, &send, &c); - if (rc) - return rc; - - /* Prepare to handle a full payload for variable sized output */ - if (c.info.size_out < 0) - c.info.size_out = cxlm->payload_size; - - rc = handle_mailbox_cmd_from_user(cxlm, &c, send.in.payload, - send.out.payload, &send.out.size, - &send.retval); - if (rc) - return rc; - - if (copy_to_user(s, &send, sizeof(send))) - return -EFAULT; - - return 0; -} - -static long __cxl_memdev_ioctl(struct cxl_memdev *cxlmd, unsigned int cmd, - unsigned long arg) -{ - switch (cmd) { - case CXL_MEM_QUERY_COMMANDS: - return cxl_query_cmd(cxlmd, (void __user *)arg); - case CXL_MEM_SEND_COMMAND: - return cxl_send_cmd(cxlmd, (void __user *)arg); - default: - return -ENOTTY; - } -} - -static long cxl_memdev_ioctl(struct file *file, unsigned int cmd, - unsigned long arg) -{ - struct cxl_memdev *cxlmd = file->private_data; - int rc = -ENXIO; - - down_read(&cxl_memdev_rwsem); - if (cxlmd->cxlm) - rc = __cxl_memdev_ioctl(cxlmd, cmd, arg); - up_read(&cxl_memdev_rwsem); - - return rc; -} - -static int cxl_memdev_open(struct inode *inode, struct file *file) -{ - struct cxl_memdev *cxlmd = - container_of(inode->i_cdev, typeof(*cxlmd), cdev); - - get_device(&cxlmd->dev); - file->private_data = cxlmd; - - return 0; -} - -static int cxl_memdev_release_file(struct inode *inode, struct file *file) -{ - struct cxl_memdev *cxlmd = - container_of(inode->i_cdev, typeof(*cxlmd), cdev); - - put_device(&cxlmd->dev); - - return 0; -} - -static void cxl_memdev_shutdown(struct device *dev) -{ - struct cxl_memdev *cxlmd = to_cxl_memdev(dev); - - down_write(&cxl_memdev_rwsem); - cxlmd->cxlm = NULL; - up_write(&cxl_memdev_rwsem); -} - -static const struct cdevm_file_operations cxl_memdev_fops = { - .fops = { - .owner = THIS_MODULE, - .unlocked_ioctl = cxl_memdev_ioctl, - .open = cxl_memdev_open, - .release = cxl_memdev_release_file, - .compat_ioctl = compat_ptr_ioctl, - .llseek = noop_llseek, - }, - .shutdown = cxl_memdev_shutdown, -}; - -static inline struct cxl_mem_command *cxl_mem_find_command(u16 opcode) -{ - struct cxl_mem_command *c; - - cxl_for_each_cmd(c) - if (c->opcode == opcode) - return c; - - return NULL; -} - -/** - * cxl_mem_mbox_send_cmd() - Send a mailbox command to a memory device. - * @cxlm: The CXL memory device to communicate with. - * @opcode: Opcode for the mailbox command. - * @in: The input payload for the mailbox command. - * @in_size: The length of the input payload - * @out: Caller allocated buffer for the output. - * @out_size: Expected size of output. - * - * Context: Any context. Will acquire and release mbox_mutex. - * Return: - * * %>=0 - Number of bytes returned in @out. - * * %-E2BIG - Payload is too large for hardware. - * * %-EBUSY - Couldn't acquire exclusive mailbox access. - * * %-EFAULT - Hardware error occurred. - * * %-ENXIO - Command completed, but device reported an error. - * * %-EIO - Unexpected output size. - * - * Mailbox commands may execute successfully yet the device itself reported an - * error. While this distinction can be useful for commands from userspace, the - * kernel will only be able to use results when both are successful. - * - * See __cxl_mem_mbox_send_cmd() - */ -static int cxl_mem_mbox_send_cmd(struct cxl_mem *cxlm, u16 opcode, - void *in, size_t in_size, - void *out, size_t out_size) -{ - const struct cxl_mem_command *cmd = cxl_mem_find_command(opcode); - struct cxl_mbox_cmd mbox_cmd = { - .opcode = opcode, - .payload_in = in, - .size_in = in_size, - .size_out = out_size, - .payload_out = out, - }; - int rc; - - if (out_size > cxlm->payload_size) - return -E2BIG; - - rc = cxlm->mbox_send(cxlm, &mbox_cmd); - if (rc) - return rc; - - /* TODO: Map return code to proper kernel style errno */ - if (mbox_cmd.return_code != CXL_MBOX_SUCCESS) - return -ENXIO; - - /* - * Variable sized commands can't be validated and so it's up to the - * caller to do that if they wish. - */ - if (cmd->info.size_out >= 0 && mbox_cmd.size_out != out_size) - return -EIO; - - return 0; -} - static int cxl_mem_setup_mailbox(struct cxl_mem *cxlm) { const int cap = readl(cxlm->regs.mbox + CXLDEV_MBOX_CAPS_OFFSET); @@ -901,30 +304,6 @@ static int cxl_mem_setup_mailbox(struct cxl_mem *cxlm) return 0; } -static struct cxl_mem *cxl_mem_create(struct device *dev) -{ - struct cxl_mem *cxlm; - - cxlm = devm_kzalloc(dev, sizeof(*cxlm), GFP_KERNEL); - if (!cxlm) { - dev_err(dev, "No memory available\n"); - return ERR_PTR(-ENOMEM); - } - - mutex_init(&cxlm->mbox_mutex); - cxlm->dev = dev; - cxlm->enabled_cmds = - devm_kmalloc_array(dev, BITS_TO_LONGS(cxl_cmd_count), - sizeof(unsigned long), - GFP_KERNEL | __GFP_ZERO); - if (!cxlm->enabled_cmds) { - dev_err(dev, "No memory available for bitmap\n"); - return ERR_PTR(-ENOMEM); - } - - return cxlm; -} - static void __iomem *cxl_mem_map_regblock(struct cxl_mem *cxlm, u8 bar, u64 offset) { @@ -1132,298 +511,6 @@ static int cxl_mem_setup_regs(struct cxl_mem *cxlm) return ret; } -static int cxl_xfer_log(struct cxl_mem *cxlm, uuid_t *uuid, u32 size, u8 *out) -{ - u32 remaining = size; - u32 offset = 0; - - while (remaining) { - u32 xfer_size = min_t(u32, remaining, cxlm->payload_size); - struct cxl_mbox_get_log { - uuid_t uuid; - __le32 offset; - __le32 length; - } __packed log = { - .uuid = *uuid, - .offset = cpu_to_le32(offset), - .length = cpu_to_le32(xfer_size) - }; - int rc; - - rc = cxl_mem_mbox_send_cmd(cxlm, CXL_MBOX_OP_GET_LOG, &log, - sizeof(log), out, xfer_size); - if (rc < 0) - return rc; - - out += xfer_size; - remaining -= xfer_size; - offset += xfer_size; - } - - return 0; -} - -/** - * cxl_walk_cel() - Walk through the Command Effects Log. - * @cxlm: Device. - * @size: Length of the Command Effects Log. - * @cel: CEL - * - * Iterate over each entry in the CEL and determine if the driver supports the - * command. If so, the command is enabled for the device and can be used later. - */ -static void cxl_walk_cel(struct cxl_mem *cxlm, size_t size, u8 *cel) -{ - struct cel_entry { - __le16 opcode; - __le16 effect; - } __packed * cel_entry; - const int cel_entries = size / sizeof(*cel_entry); - int i; - - cel_entry = (struct cel_entry *)cel; - - for (i = 0; i < cel_entries; i++) { - u16 opcode = le16_to_cpu(cel_entry[i].opcode); - struct cxl_mem_command *cmd = cxl_mem_find_command(opcode); - - if (!cmd) { - dev_dbg(cxlm->dev, - "Opcode 0x%04x unsupported by driver", opcode); - continue; - } - - set_bit(cmd->info.id, cxlm->enabled_cmds); - } -} - -struct cxl_mbox_get_supported_logs { - __le16 entries; - u8 rsvd[6]; - struct gsl_entry { - uuid_t uuid; - __le32 size; - } __packed entry[]; -} __packed; - -static struct cxl_mbox_get_supported_logs *cxl_get_gsl(struct cxl_mem *cxlm) -{ - struct cxl_mbox_get_supported_logs *ret; - int rc; - - ret = kvmalloc(cxlm->payload_size, GFP_KERNEL); - if (!ret) - return ERR_PTR(-ENOMEM); - - rc = cxl_mem_mbox_send_cmd(cxlm, CXL_MBOX_OP_GET_SUPPORTED_LOGS, NULL, - 0, ret, cxlm->payload_size); - if (rc < 0) { - kvfree(ret); - return ERR_PTR(rc); - } - - return ret; -} - -/** - * cxl_mem_get_partition_info - Get partition info - * @cxlm: cxl_mem instance to update partition info - * - * Retrieve the current partition info for the device specified. If not 0, the - * 'next' values are pending and take affect on next cold reset. - * - * Return: 0 if no error: or the result of the mailbox command. - * - * See CXL @8.2.9.5.2.1 Get Partition Info - */ -static int cxl_mem_get_partition_info(struct cxl_mem *cxlm) -{ - struct cxl_mbox_get_partition_info { - __le64 active_volatile_cap; - __le64 active_persistent_cap; - __le64 next_volatile_cap; - __le64 next_persistent_cap; - } __packed pi; - int rc; - - rc = cxl_mem_mbox_send_cmd(cxlm, CXL_MBOX_OP_GET_PARTITION_INFO, - NULL, 0, &pi, sizeof(pi)); - if (rc) - return rc; - - cxlm->active_volatile_bytes = - le64_to_cpu(pi.active_volatile_cap) * CXL_CAPACITY_MULTIPLIER; - cxlm->active_persistent_bytes = - le64_to_cpu(pi.active_persistent_cap) * CXL_CAPACITY_MULTIPLIER; - cxlm->next_volatile_bytes = - le64_to_cpu(pi.next_volatile_cap) * CXL_CAPACITY_MULTIPLIER; - cxlm->next_persistent_bytes = - le64_to_cpu(pi.next_volatile_cap) * CXL_CAPACITY_MULTIPLIER; - - return 0; -} - -/** - * cxl_mem_enumerate_cmds() - Enumerate commands for a device. - * @cxlm: The device. - * - * Returns 0 if enumerate completed successfully. - * - * CXL devices have optional support for certain commands. This function will - * determine the set of supported commands for the hardware and update the - * enabled_cmds bitmap in the @cxlm. - */ -static int cxl_mem_enumerate_cmds(struct cxl_mem *cxlm) -{ - struct cxl_mbox_get_supported_logs *gsl; - struct device *dev = cxlm->dev; - struct cxl_mem_command *cmd; - int i, rc; - - gsl = cxl_get_gsl(cxlm); - if (IS_ERR(gsl)) - return PTR_ERR(gsl); - - rc = -ENOENT; - for (i = 0; i < le16_to_cpu(gsl->entries); i++) { - u32 size = le32_to_cpu(gsl->entry[i].size); - uuid_t uuid = gsl->entry[i].uuid; - u8 *log; - - dev_dbg(dev, "Found LOG type %pU of size %d", &uuid, size); - - if (!uuid_equal(&uuid, &log_uuid[CEL_UUID])) - continue; - - log = kvmalloc(size, GFP_KERNEL); - if (!log) { - rc = -ENOMEM; - goto out; - } - - rc = cxl_xfer_log(cxlm, &uuid, size, log); - if (rc) { - kvfree(log); - goto out; - } - - cxl_walk_cel(cxlm, size, log); - kvfree(log); - - /* In case CEL was bogus, enable some default commands. */ - cxl_for_each_cmd(cmd) - if (cmd->flags & CXL_CMD_FLAG_FORCE_ENABLE) - set_bit(cmd->info.id, cxlm->enabled_cmds); - - /* Found the required CEL */ - rc = 0; - } - -out: - kvfree(gsl); - return rc; -} - -/** - * cxl_mem_identify() - Send the IDENTIFY command to the device. - * @cxlm: The device to identify. - * - * Return: 0 if identify was executed successfully. - * - * This will dispatch the identify command to the device and on success populate - * structures to be exported to sysfs. - */ -static int cxl_mem_identify(struct cxl_mem *cxlm) -{ - /* See CXL 2.0 Table 175 Identify Memory Device Output Payload */ - struct cxl_mbox_identify { - char fw_revision[0x10]; - __le64 total_capacity; - __le64 volatile_capacity; - __le64 persistent_capacity; - __le64 partition_align; - __le16 info_event_log_size; - __le16 warning_event_log_size; - __le16 failure_event_log_size; - __le16 fatal_event_log_size; - __le32 lsa_size; - u8 poison_list_max_mer[3]; - __le16 inject_poison_limit; - u8 poison_caps; - u8 qos_telemetry_caps; - } __packed id; - int rc; - - rc = cxl_mem_mbox_send_cmd(cxlm, CXL_MBOX_OP_IDENTIFY, NULL, 0, &id, - sizeof(id)); - if (rc < 0) - return rc; - - cxlm->total_bytes = le64_to_cpu(id.total_capacity); - cxlm->total_bytes *= CXL_CAPACITY_MULTIPLIER; - - cxlm->volatile_only_bytes = le64_to_cpu(id.volatile_capacity); - cxlm->volatile_only_bytes *= CXL_CAPACITY_MULTIPLIER; - - cxlm->persistent_only_bytes = le64_to_cpu(id.persistent_capacity); - cxlm->persistent_only_bytes *= CXL_CAPACITY_MULTIPLIER; - - cxlm->partition_align_bytes = le64_to_cpu(id.partition_align); - cxlm->partition_align_bytes *= CXL_CAPACITY_MULTIPLIER; - - dev_dbg(cxlm->dev, - "Identify Memory Device\n" - " total_bytes = %#llx\n" - " volatile_only_bytes = %#llx\n" - " persistent_only_bytes = %#llx\n" - " partition_align_bytes = %#llx\n", - cxlm->total_bytes, cxlm->volatile_only_bytes, - cxlm->persistent_only_bytes, cxlm->partition_align_bytes); - - cxlm->lsa_size = le32_to_cpu(id.lsa_size); - memcpy(cxlm->firmware_version, id.fw_revision, sizeof(id.fw_revision)); - - return 0; -} - -static int cxl_mem_create_range_info(struct cxl_mem *cxlm) -{ - int rc; - - if (cxlm->partition_align_bytes == 0) { - cxlm->ram_range.start = 0; - cxlm->ram_range.end = cxlm->volatile_only_bytes - 1; - cxlm->pmem_range.start = cxlm->volatile_only_bytes; - cxlm->pmem_range.end = cxlm->volatile_only_bytes + - cxlm->persistent_only_bytes - 1; - return 0; - } - - rc = cxl_mem_get_partition_info(cxlm); - if (rc < 0) { - dev_err(cxlm->dev, "Failed to query partition information\n"); - return rc; - } - - dev_dbg(cxlm->dev, - "Get Partition Info\n" - " active_volatile_bytes = %#llx\n" - " active_persistent_bytes = %#llx\n" - " next_volatile_bytes = %#llx\n" - " next_persistent_bytes = %#llx\n", - cxlm->active_volatile_bytes, cxlm->active_persistent_bytes, - cxlm->next_volatile_bytes, cxlm->next_persistent_bytes); - - cxlm->ram_range.start = 0; - cxlm->ram_range.end = cxlm->active_volatile_bytes - 1; - - cxlm->pmem_range.start = cxlm->active_volatile_bytes; - cxlm->pmem_range.end = cxlm->active_volatile_bytes + - cxlm->active_persistent_bytes - 1; - - return 0; -} - static int cxl_mem_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct cxl_memdev *cxlmd; @@ -1458,7 +545,7 @@ static int cxl_mem_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (rc) return rc; - cxlmd = devm_cxl_add_memdev(cxlm, &cxl_memdev_fops); + cxlmd = devm_cxl_add_memdev(cxlm); if (IS_ERR(cxlmd)) return PTR_ERR(cxlmd); @@ -1486,7 +573,6 @@ static struct pci_driver cxl_mem_driver = { static __init int cxl_mem_init(void) { - struct dentry *mbox_debugfs; int rc; /* Double check the anonymous union trickery in struct cxl_regs */ @@ -1497,17 +583,11 @@ static __init int cxl_mem_init(void) if (rc) return rc; - cxl_debugfs = debugfs_create_dir("cxl", NULL); - mbox_debugfs = debugfs_create_dir("mbox", cxl_debugfs); - debugfs_create_bool("raw_allow_all", 0600, mbox_debugfs, - &cxl_raw_allow_all); - return 0; } static __exit void cxl_mem_exit(void) { - debugfs_remove_recursive(cxl_debugfs); pci_unregister_driver(&cxl_mem_driver); } From 5a2328f4e872a5bcbb2ff790497f000e8f79b152 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 8 Sep 2021 22:12:38 -0700 Subject: [PATCH 050/587] cxl/pci: Use module_pci_driver Now that cxl_mem_{init,exit} no longer need to manage debugfs, switch back to the smaller form of the boiler plate. Acked-by: Ben Widawsky Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/163116435825.2460985.7201322215431441130.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/cxl/pci.c | 30 ++++++++---------------------- 1 file changed, 8 insertions(+), 22 deletions(-) diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index c9f2ac134f4d..27f75b5a2ee2 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -517,6 +517,13 @@ static int cxl_mem_probe(struct pci_dev *pdev, const struct pci_device_id *id) struct cxl_mem *cxlm; int rc; + /* + * Double check the anonymous union trickery in struct cxl_regs + * FIXME switch to struct_group() + */ + BUILD_BUG_ON(offsetof(struct cxl_regs, memdev) != + offsetof(struct cxl_regs, device_regs.memdev)); + rc = pcim_enable_device(pdev); if (rc) return rc; @@ -571,27 +578,6 @@ static struct pci_driver cxl_mem_driver = { }, }; -static __init int cxl_mem_init(void) -{ - int rc; - - /* Double check the anonymous union trickery in struct cxl_regs */ - BUILD_BUG_ON(offsetof(struct cxl_regs, memdev) != - offsetof(struct cxl_regs, device_regs.memdev)); - - rc = pci_register_driver(&cxl_mem_driver); - if (rc) - return rc; - - return 0; -} - -static __exit void cxl_mem_exit(void) -{ - pci_unregister_driver(&cxl_mem_driver); -} - MODULE_LICENSE("GPL v2"); -module_init(cxl_mem_init); -module_exit(cxl_mem_exit); +module_pci_driver(cxl_mem_driver); MODULE_IMPORT_NS(CXL); From ff56ab9e164d71c4a6ae33fc61ae856faec265a1 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 8 Sep 2021 22:12:44 -0700 Subject: [PATCH 051/587] cxl/mbox: Convert 'enabled_cmds' to DECLARE_BITMAP Define enabled_cmds as an embedded member of 'struct cxl_mem' rather than a pointer to another dynamic allocation. As this leaves only one user of cxl_cmd_count, just open code it and delete the helper. Acked-by: Ben Widawsky Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/163116436415.2460985.10101824045493194813.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/cxl/core/mbox.c | 12 +----------- drivers/cxl/cxlmem.h | 2 +- 2 files changed, 2 insertions(+), 12 deletions(-) diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 31e183991726..422999740649 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -315,8 +315,6 @@ static int cxl_validate_cmd_from_user(struct cxl_mem *cxlm, return 0; } -#define cxl_cmd_count ARRAY_SIZE(cxl_mem_commands) - int cxl_query_cmd(struct cxl_memdev *cxlmd, struct cxl_mem_query_commands __user *q) { @@ -332,7 +330,7 @@ int cxl_query_cmd(struct cxl_memdev *cxlmd, /* returns the total number if 0 elements are requested. */ if (n_commands == 0) - return put_user(cxl_cmd_count, &q->n_commands); + return put_user(ARRAY_SIZE(cxl_mem_commands), &q->n_commands); /* * otherwise, return max(n_commands, total commands) cxl_command_info @@ -794,14 +792,6 @@ struct cxl_mem *cxl_mem_create(struct device *dev) mutex_init(&cxlm->mbox_mutex); cxlm->dev = dev; - cxlm->enabled_cmds = - devm_kmalloc_array(dev, BITS_TO_LONGS(cxl_cmd_count), - sizeof(unsigned long), - GFP_KERNEL | __GFP_ZERO); - if (!cxlm->enabled_cmds) { - dev_err(dev, "No memory available for bitmap\n"); - return ERR_PTR(-ENOMEM); - } return cxlm; } diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index f5d3326a1d0b..8f59a89a0aab 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -126,7 +126,7 @@ struct cxl_mem { size_t lsa_size; struct mutex mbox_mutex; /* Protects device mailbox and firmware */ char firmware_version[0x10]; - unsigned long *enabled_cmds; + DECLARE_BITMAP(enabled_cmds, CXL_MEM_COMMAND_ID_MAX); struct range pmem_range; struct range ram_range; From 12f3856ad42d6ce0dbd4266e105c04ae999f908c Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 14 Sep 2021 12:03:04 -0700 Subject: [PATCH 052/587] cxl/mbox: Add exclusive kernel command support The CXL_PMEM driver expects exclusive control of the label storage area space. Similar to the LIBNVDIMM expectation that the label storage area is only writable from userspace when the corresponding memory device is not active in any region, the expectation is the native CXL_PCI UAPI path is disabled while the cxl_nvdimm for a given cxl_memdev device is active in LIBNVDIMM. Add the ability to toggle the availability of a given command for the UAPI path. Use that new capability to shutdown changes to partitions and the label storage area while the cxl_nvdimm device is actively proxying commands for LIBNVDIMM. Reviewed-by: Ben Widawsky Link: https://lore.kernel.org/r/163164579468.2830966.6980053377428474263.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/cxl/core/mbox.c | 5 +++++ drivers/cxl/core/memdev.c | 32 ++++++++++++++++++++++++++++++++ drivers/cxl/cxlmem.h | 4 ++++ drivers/cxl/pmem.c | 29 ++++++++++++++++++++++++++--- 4 files changed, 67 insertions(+), 3 deletions(-) diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 422999740649..82e79da195fa 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -221,6 +221,7 @@ static bool cxl_mem_raw_command_allowed(u16 opcode) * * %-EINVAL - Reserved fields or invalid values were used. * * %-ENOMEM - Input or output buffer wasn't sized properly. * * %-EPERM - Attempted to use a protected command. + * * %-EBUSY - Kernel has claimed exclusive access to this opcode * * The result of this command is a fully validated command in @out_cmd that is * safe to send to the hardware. @@ -296,6 +297,10 @@ static int cxl_validate_cmd_from_user(struct cxl_mem *cxlm, if (!test_bit(info->id, cxlm->enabled_cmds)) return -ENOTTY; + /* Check that the command is not claimed for exclusive kernel use */ + if (test_bit(info->id, cxlm->exclusive_cmds)) + return -EBUSY; + /* Check the input buffer is the expected size */ if (info->size_in >= 0 && info->size_in != send_cmd->in.size) return -ENOMEM; diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index df2ba87238c2..bf1b04d00ff4 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -134,6 +134,38 @@ static const struct device_type cxl_memdev_type = { .groups = cxl_memdev_attribute_groups, }; +/** + * set_exclusive_cxl_commands() - atomically disable user cxl commands + * @cxlm: cxl_mem instance to modify + * @cmds: bitmap of commands to mark exclusive + * + * Grab the cxl_memdev_rwsem in write mode to flush in-flight + * invocations of the ioctl path and then disable future execution of + * commands with the command ids set in @cmds. + */ +void set_exclusive_cxl_commands(struct cxl_mem *cxlm, unsigned long *cmds) +{ + down_write(&cxl_memdev_rwsem); + bitmap_or(cxlm->exclusive_cmds, cxlm->exclusive_cmds, cmds, + CXL_MEM_COMMAND_ID_MAX); + up_write(&cxl_memdev_rwsem); +} +EXPORT_SYMBOL_GPL(set_exclusive_cxl_commands); + +/** + * clear_exclusive_cxl_commands() - atomically enable user cxl commands + * @cxlm: cxl_mem instance to modify + * @cmds: bitmap of commands to mark available for userspace + */ +void clear_exclusive_cxl_commands(struct cxl_mem *cxlm, unsigned long *cmds) +{ + down_write(&cxl_memdev_rwsem); + bitmap_andnot(cxlm->exclusive_cmds, cxlm->exclusive_cmds, cmds, + CXL_MEM_COMMAND_ID_MAX); + up_write(&cxl_memdev_rwsem); +} +EXPORT_SYMBOL_GPL(clear_exclusive_cxl_commands); + static void cxl_memdev_shutdown(struct device *dev) { struct cxl_memdev *cxlmd = to_cxl_memdev(dev); diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index 8f59a89a0aab..373add570ef6 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -101,6 +101,7 @@ struct cxl_mbox_cmd { * @mbox_mutex: Mutex to synchronize mailbox access. * @firmware_version: Firmware version for the memory device. * @enabled_cmds: Hardware commands found enabled in CEL. + * @exclusive_cmds: Commands that are kernel-internal only * @pmem_range: Active Persistent memory capacity configuration * @ram_range: Active Volatile memory capacity configuration * @total_bytes: sum of all possible capacities @@ -127,6 +128,7 @@ struct cxl_mem { struct mutex mbox_mutex; /* Protects device mailbox and firmware */ char firmware_version[0x10]; DECLARE_BITMAP(enabled_cmds, CXL_MEM_COMMAND_ID_MAX); + DECLARE_BITMAP(exclusive_cmds, CXL_MEM_COMMAND_ID_MAX); struct range pmem_range; struct range ram_range; @@ -200,4 +202,6 @@ int cxl_mem_identify(struct cxl_mem *cxlm); int cxl_mem_enumerate_cmds(struct cxl_mem *cxlm); int cxl_mem_create_range_info(struct cxl_mem *cxlm); struct cxl_mem *cxl_mem_create(struct device *dev); +void set_exclusive_cxl_commands(struct cxl_mem *cxlm, unsigned long *cmds); +void clear_exclusive_cxl_commands(struct cxl_mem *cxlm, unsigned long *cmds); #endif /* __CXL_MEM_H__ */ diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c index 9652c3ee41e7..5629289939af 100644 --- a/drivers/cxl/pmem.c +++ b/drivers/cxl/pmem.c @@ -16,6 +16,13 @@ */ static struct workqueue_struct *cxl_pmem_wq; +static __read_mostly DECLARE_BITMAP(exclusive_cmds, CXL_MEM_COMMAND_ID_MAX); + +static void clear_exclusive(void *cxlm) +{ + clear_exclusive_cxl_commands(cxlm, exclusive_cmds); +} + static void unregister_nvdimm(void *nvdimm) { nvdimm_delete(nvdimm); @@ -39,25 +46,37 @@ static struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(void) static int cxl_nvdimm_probe(struct device *dev) { struct cxl_nvdimm *cxl_nvd = to_cxl_nvdimm(dev); + struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; + struct cxl_mem *cxlm = cxlmd->cxlm; struct cxl_nvdimm_bridge *cxl_nvb; unsigned long flags = 0; struct nvdimm *nvdimm; - int rc = -ENXIO; + int rc; cxl_nvb = cxl_find_nvdimm_bridge(); if (!cxl_nvb) return -ENXIO; device_lock(&cxl_nvb->dev); - if (!cxl_nvb->nvdimm_bus) + if (!cxl_nvb->nvdimm_bus) { + rc = -ENXIO; + goto out; + } + + set_exclusive_cxl_commands(cxlm, exclusive_cmds); + rc = devm_add_action_or_reset(dev, clear_exclusive, cxlm); + if (rc) goto out; set_bit(NDD_LABELING, &flags); nvdimm = nvdimm_create(cxl_nvb->nvdimm_bus, cxl_nvd, NULL, flags, 0, 0, NULL); - if (!nvdimm) + if (!nvdimm) { + rc = -ENOMEM; goto out; + } + dev_set_drvdata(dev, nvdimm); rc = devm_add_action_or_reset(dev, unregister_nvdimm, nvdimm); out: device_unlock(&cxl_nvb->dev); @@ -194,6 +213,10 @@ static __init int cxl_pmem_init(void) { int rc; + set_bit(CXL_MEM_COMMAND_ID_SET_PARTITION_INFO, exclusive_cmds); + set_bit(CXL_MEM_COMMAND_ID_SET_SHUTDOWN_STATE, exclusive_cmds); + set_bit(CXL_MEM_COMMAND_ID_SET_LSA, exclusive_cmds); + cxl_pmem_wq = alloc_ordered_workqueue("cxl_pmem", 0); if (!cxl_pmem_wq) return -ENXIO; From 60b8f17215de1e6551fec4e942494c3832c3e98b Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 9 Sep 2021 15:08:15 -0700 Subject: [PATCH 053/587] cxl/pmem: Translate NVDIMM label commands to CXL label commands The LIBNVDIMM IOCTL UAPI calls back to the nvdimm-bus-provider to translate the Linux command payload to the device native command format. The LIBNVDIMM commands get-config-size, get-config-data, and set-config-data, map to the CXL memory device commands device-identify, get-lsa, and set-lsa. Recall that the label-storage-area (LSA) on an NVDIMM device arranges for the provisioning of namespaces. Additionally for CXL the LSA is used for provisioning regions as well. The data from device-identify is already cached in the 'struct cxl_mem' instance associated with @cxl_nvd, so that payload return is simply crafted and no CXL command is issued. The conversion for get-lsa is straightforward, but the conversion for set-lsa requires an allocation to append the set-lsa header in front of the payload. Reviewed-by: Ben Widawsky Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/163122524923.2534512.9431316965424264864.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/cxl/pmem.c | 128 +++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 124 insertions(+), 4 deletions(-) diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c index 5629289939af..bc1466b0e999 100644 --- a/drivers/cxl/pmem.c +++ b/drivers/cxl/pmem.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright(c) 2021 Intel Corporation. All rights reserved. */ #include +#include #include #include #include @@ -47,9 +48,9 @@ static int cxl_nvdimm_probe(struct device *dev) { struct cxl_nvdimm *cxl_nvd = to_cxl_nvdimm(dev); struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; + unsigned long flags = 0, cmd_mask = 0; struct cxl_mem *cxlm = cxlmd->cxlm; struct cxl_nvdimm_bridge *cxl_nvb; - unsigned long flags = 0; struct nvdimm *nvdimm; int rc; @@ -69,8 +70,11 @@ static int cxl_nvdimm_probe(struct device *dev) goto out; set_bit(NDD_LABELING, &flags); - nvdimm = nvdimm_create(cxl_nvb->nvdimm_bus, cxl_nvd, NULL, flags, 0, 0, - NULL); + set_bit(ND_CMD_GET_CONFIG_SIZE, &cmd_mask); + set_bit(ND_CMD_GET_CONFIG_DATA, &cmd_mask); + set_bit(ND_CMD_SET_CONFIG_DATA, &cmd_mask); + nvdimm = nvdimm_create(cxl_nvb->nvdimm_bus, cxl_nvd, NULL, flags, + cmd_mask, 0, NULL); if (!nvdimm) { rc = -ENOMEM; goto out; @@ -91,11 +95,127 @@ static struct cxl_driver cxl_nvdimm_driver = { .id = CXL_DEVICE_NVDIMM, }; +static int cxl_pmem_get_config_size(struct cxl_mem *cxlm, + struct nd_cmd_get_config_size *cmd, + unsigned int buf_len) +{ + if (sizeof(*cmd) > buf_len) + return -EINVAL; + + *cmd = (struct nd_cmd_get_config_size) { + .config_size = cxlm->lsa_size, + .max_xfer = cxlm->payload_size, + }; + + return 0; +} + +static int cxl_pmem_get_config_data(struct cxl_mem *cxlm, + struct nd_cmd_get_config_data_hdr *cmd, + unsigned int buf_len) +{ + struct cxl_mbox_get_lsa { + u32 offset; + u32 length; + } get_lsa; + int rc; + + if (sizeof(*cmd) > buf_len) + return -EINVAL; + if (struct_size(cmd, out_buf, cmd->in_length) > buf_len) + return -EINVAL; + + get_lsa = (struct cxl_mbox_get_lsa) { + .offset = cmd->in_offset, + .length = cmd->in_length, + }; + + rc = cxl_mem_mbox_send_cmd(cxlm, CXL_MBOX_OP_GET_LSA, &get_lsa, + sizeof(get_lsa), cmd->out_buf, + cmd->in_length); + cmd->status = 0; + + return rc; +} + +static int cxl_pmem_set_config_data(struct cxl_mem *cxlm, + struct nd_cmd_set_config_hdr *cmd, + unsigned int buf_len) +{ + struct cxl_mbox_set_lsa { + u32 offset; + u32 reserved; + u8 data[]; + } *set_lsa; + int rc; + + if (sizeof(*cmd) > buf_len) + return -EINVAL; + + /* 4-byte status follows the input data in the payload */ + if (struct_size(cmd, in_buf, cmd->in_length) + 4 > buf_len) + return -EINVAL; + + set_lsa = + kvzalloc(struct_size(set_lsa, data, cmd->in_length), GFP_KERNEL); + if (!set_lsa) + return -ENOMEM; + + *set_lsa = (struct cxl_mbox_set_lsa) { + .offset = cmd->in_offset, + }; + memcpy(set_lsa->data, cmd->in_buf, cmd->in_length); + + rc = cxl_mem_mbox_send_cmd(cxlm, CXL_MBOX_OP_SET_LSA, set_lsa, + struct_size(set_lsa, data, cmd->in_length), + NULL, 0); + + /* + * Set "firmware" status (4-packed bytes at the end of the input + * payload. + */ + put_unaligned(0, (u32 *) &cmd->in_buf[cmd->in_length]); + kvfree(set_lsa); + + return rc; +} + +static int cxl_pmem_nvdimm_ctl(struct nvdimm *nvdimm, unsigned int cmd, + void *buf, unsigned int buf_len) +{ + struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); + unsigned long cmd_mask = nvdimm_cmd_mask(nvdimm); + struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; + struct cxl_mem *cxlm = cxlmd->cxlm; + + if (!test_bit(cmd, &cmd_mask)) + return -ENOTTY; + + switch (cmd) { + case ND_CMD_GET_CONFIG_SIZE: + return cxl_pmem_get_config_size(cxlm, buf, buf_len); + case ND_CMD_GET_CONFIG_DATA: + return cxl_pmem_get_config_data(cxlm, buf, buf_len); + case ND_CMD_SET_CONFIG_DATA: + return cxl_pmem_set_config_data(cxlm, buf, buf_len); + default: + return -ENOTTY; + } +} + static int cxl_pmem_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, unsigned int cmd, void *buf, unsigned int buf_len, int *cmd_rc) { - return -ENOTTY; + /* + * No firmware response to translate, let the transport error + * code take precedence. + */ + *cmd_rc = 0; + + if (!nvdimm) + return -ENOTTY; + return cxl_pmem_nvdimm_ctl(nvdimm, cmd, buf, buf_len); } static bool online_nvdimm_bus(struct cxl_nvdimm_bridge *cxl_nvb) From 2e52b6256b9af23c5a881f56b5b5e7f5cb9b8b4b Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 14 Sep 2021 12:08:40 -0700 Subject: [PATCH 054/587] cxl/pmem: Add support for multiple nvdimm-bridge objects In preparation for a mocked unit test environment for CXL objects, allow for multiple unique nvdimm-bridge objects. For now, just allow multiple bridges to be registered. Later, when there are multiple present, further updates are needed to cxl_find_nvdimm_bridge() to identify which bridge is associated with which CXL hierarchy for nvdimm registration. Note that this does change the kernel device-name for the bridge object. User space should not have any attachment to the device name at this point as it is still early days in the CXL driver development. Acked-by: Ben Widawsky Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/163164647007.2831228.2150246954620721526.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/cxl/core/pmem.c | 32 +++++++++++++++++++++++++++++++- drivers/cxl/cxl.h | 2 ++ drivers/cxl/pmem.c | 15 --------------- 3 files changed, 33 insertions(+), 16 deletions(-) diff --git a/drivers/cxl/core/pmem.c b/drivers/cxl/core/pmem.c index d24570f5b8ba..9e56be3994f1 100644 --- a/drivers/cxl/core/pmem.c +++ b/drivers/cxl/core/pmem.c @@ -2,6 +2,7 @@ /* Copyright(c) 2020 Intel Corporation. */ #include #include +#include #include #include #include "core.h" @@ -20,10 +21,13 @@ * operations, for example, namespace label access commands. */ +static DEFINE_IDA(cxl_nvdimm_bridge_ida); + static void cxl_nvdimm_bridge_release(struct device *dev) { struct cxl_nvdimm_bridge *cxl_nvb = to_cxl_nvdimm_bridge(dev); + ida_free(&cxl_nvdimm_bridge_ida, cxl_nvb->id); kfree(cxl_nvb); } @@ -47,16 +51,38 @@ struct cxl_nvdimm_bridge *to_cxl_nvdimm_bridge(struct device *dev) } EXPORT_SYMBOL_GPL(to_cxl_nvdimm_bridge); +static int match_nvdimm_bridge(struct device *dev, const void *data) +{ + return dev->type == &cxl_nvdimm_bridge_type; +} + +struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(void) +{ + struct device *dev; + + dev = bus_find_device(&cxl_bus_type, NULL, NULL, match_nvdimm_bridge); + if (!dev) + return NULL; + return to_cxl_nvdimm_bridge(dev); +} +EXPORT_SYMBOL_GPL(cxl_find_nvdimm_bridge); + static struct cxl_nvdimm_bridge * cxl_nvdimm_bridge_alloc(struct cxl_port *port) { struct cxl_nvdimm_bridge *cxl_nvb; struct device *dev; + int rc; cxl_nvb = kzalloc(sizeof(*cxl_nvb), GFP_KERNEL); if (!cxl_nvb) return ERR_PTR(-ENOMEM); + rc = ida_alloc(&cxl_nvdimm_bridge_ida, GFP_KERNEL); + if (rc < 0) + goto err; + cxl_nvb->id = rc; + dev = &cxl_nvb->dev; cxl_nvb->port = port; cxl_nvb->state = CXL_NVB_NEW; @@ -67,6 +93,10 @@ cxl_nvdimm_bridge_alloc(struct cxl_port *port) dev->type = &cxl_nvdimm_bridge_type; return cxl_nvb; + +err: + kfree(cxl_nvb); + return ERR_PTR(rc); } static void unregister_nvb(void *_cxl_nvb) @@ -119,7 +149,7 @@ struct cxl_nvdimm_bridge *devm_cxl_add_nvdimm_bridge(struct device *host, return cxl_nvb; dev = &cxl_nvb->dev; - rc = dev_set_name(dev, "nvdimm-bridge"); + rc = dev_set_name(dev, "nvdimm-bridge%d", cxl_nvb->id); if (rc) goto err; diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index 53927f9fa77e..1b2e816e061e 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -211,6 +211,7 @@ enum cxl_nvdimm_brige_state { }; struct cxl_nvdimm_bridge { + int id; struct device dev; struct cxl_port *port; struct nvdimm_bus *nvdimm_bus; @@ -323,4 +324,5 @@ struct cxl_nvdimm_bridge *devm_cxl_add_nvdimm_bridge(struct device *host, struct cxl_nvdimm *to_cxl_nvdimm(struct device *dev); bool is_cxl_nvdimm(struct device *dev); int devm_cxl_add_nvdimm(struct device *host, struct cxl_memdev *cxlmd); +struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(void); #endif /* __CXL_H__ */ diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c index bc1466b0e999..5ccf9aa6b3ae 100644 --- a/drivers/cxl/pmem.c +++ b/drivers/cxl/pmem.c @@ -29,21 +29,6 @@ static void unregister_nvdimm(void *nvdimm) nvdimm_delete(nvdimm); } -static int match_nvdimm_bridge(struct device *dev, const void *data) -{ - return strcmp(dev_name(dev), "nvdimm-bridge") == 0; -} - -static struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(void) -{ - struct device *dev; - - dev = bus_find_device(&cxl_bus_type, NULL, NULL, match_nvdimm_bridge); - if (!dev) - return NULL; - return to_cxl_nvdimm_bridge(dev); -} - static int cxl_nvdimm_probe(struct device *dev) { struct cxl_nvdimm *cxl_nvd = to_cxl_nvdimm(dev); From 67dcdd4d3b832ace448f454c47426f657d648fc5 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 14 Sep 2021 12:14:22 -0700 Subject: [PATCH 055/587] tools/testing/cxl: Introduce a mocked-up CXL port hierarchy Create an environment for CXL plumbing unit tests. Especially when it comes to an algorithm for HDM Decoder (Host-managed Device Memory Decoder) programming, the availability of an in-kernel-tree emulation environment for CXL configuration complexity and corner cases speeds development and deters regressions. The approach taken mirrors what was done for tools/testing/nvdimm/. I.e. an external module, cxl_test.ko built out of the tools/testing/cxl/ directory, provides mock implementations of kernel APIs and kernel objects to simulate a real world device hierarchy. One feedback for the tools/testing/nvdimm/ proposal was "why not do this in QEMU?". In fact, the CXL development community has developed a QEMU model for CXL [1]. However, there are a few blocking issues that keep QEMU from being a tight fit for topology + provisioning unit tests: 1/ The QEMU community has yet to show interest in merging any of this support that has had patches on the list since November 2020. So, testing CXL to date involves building custom QEMU with out-of-tree patches. 2/ CXL mechanisms like cross-host-bridge interleave do not have a clear path to be emulated by QEMU without major infrastructure work. This is easier to achieve with the alloc_mock_res() approach taken in this patch to shortcut-define emulated system physical address ranges with interleave behavior. The QEMU enabling has been critical to get the driver off the ground, and may still move forward, but it does not address the ongoing needs of a regression testing environment and test driven development. This patch adds an ACPI CXL Platform definition with emulated CXL multi-ported host-bridges. A follow on patch adds emulated memory expander devices. Acked-by: Ben Widawsky Reported-by: Vishal Verma Link: https://lore.kernel.org/r/20210202005948.241655-1-ben.widawsky@intel.com [1] Link: https://lore.kernel.org/r/163164680798.2831381.838684634806668012.stgit@dwillia2-desk3.amr.corp.intel.com Reviewed-by: Jonathan Cameron Signed-off-by: Dan Williams --- drivers/cxl/acpi.c | 36 ++- drivers/cxl/cxl.h | 16 + tools/testing/cxl/Kbuild | 36 +++ tools/testing/cxl/config_check.c | 13 + tools/testing/cxl/mock_acpi.c | 109 +++++++ tools/testing/cxl/test/Kbuild | 6 + tools/testing/cxl/test/cxl.c | 509 +++++++++++++++++++++++++++++++ tools/testing/cxl/test/mock.c | 171 +++++++++++ tools/testing/cxl/test/mock.h | 27 ++ 9 files changed, 908 insertions(+), 15 deletions(-) create mode 100644 tools/testing/cxl/Kbuild create mode 100644 tools/testing/cxl/config_check.c create mode 100644 tools/testing/cxl/mock_acpi.c create mode 100644 tools/testing/cxl/test/Kbuild create mode 100644 tools/testing/cxl/test/cxl.c create mode 100644 tools/testing/cxl/test/mock.c create mode 100644 tools/testing/cxl/test/mock.h diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c index 54e9d4d2cf5f..32775d1ac4b3 100644 --- a/drivers/cxl/acpi.c +++ b/drivers/cxl/acpi.c @@ -182,15 +182,7 @@ static resource_size_t get_chbcr(struct acpi_cedt_chbs *chbs) return IS_ERR(chbs) ? CXL_RESOURCE_NONE : chbs->base; } -struct cxl_walk_context { - struct device *dev; - struct pci_bus *root; - struct cxl_port *port; - int error; - int count; -}; - -static int match_add_root_ports(struct pci_dev *pdev, void *data) +__mock int match_add_root_ports(struct pci_dev *pdev, void *data) { struct cxl_walk_context *ctx = data; struct pci_bus *root_bus = ctx->root; @@ -239,7 +231,8 @@ static struct cxl_dport *find_dport_by_dev(struct cxl_port *port, struct device return NULL; } -static struct acpi_device *to_cxl_host_bridge(struct device *dev) +__mock struct acpi_device *to_cxl_host_bridge(struct device *host, + struct device *dev) { struct acpi_device *adev = to_acpi_device(dev); @@ -257,9 +250,9 @@ static struct acpi_device *to_cxl_host_bridge(struct device *dev) */ static int add_host_bridge_uport(struct device *match, void *arg) { - struct acpi_device *bridge = to_cxl_host_bridge(match); struct cxl_port *root_port = arg; struct device *host = root_port->dev.parent; + struct acpi_device *bridge = to_cxl_host_bridge(host, match); struct acpi_pci_root *pci_root; struct cxl_walk_context ctx; struct cxl_decoder *cxld; @@ -323,7 +316,7 @@ static int add_host_bridge_dport(struct device *match, void *arg) struct acpi_cedt_chbs *chbs; struct cxl_port *root_port = arg; struct device *host = root_port->dev.parent; - struct acpi_device *bridge = to_cxl_host_bridge(match); + struct acpi_device *bridge = to_cxl_host_bridge(host, match); if (!bridge) return 0; @@ -375,6 +368,17 @@ static int add_root_nvdimm_bridge(struct device *match, void *data) return 1; } +static u32 cedt_instance(struct platform_device *pdev) +{ + const bool *native_acpi0017 = acpi_device_get_match_data(&pdev->dev); + + if (native_acpi0017 && *native_acpi0017) + return 0; + + /* for cxl_test request a non-canonical instance */ + return U32_MAX; +} + static int cxl_acpi_probe(struct platform_device *pdev) { int rc; @@ -388,7 +392,7 @@ static int cxl_acpi_probe(struct platform_device *pdev) return PTR_ERR(root_port); dev_dbg(host, "add: %s\n", dev_name(&root_port->dev)); - status = acpi_get_table(ACPI_SIG_CEDT, 0, &acpi_cedt); + status = acpi_get_table(ACPI_SIG_CEDT, cedt_instance(pdev), &acpi_cedt); if (ACPI_FAILURE(status)) return -ENXIO; @@ -419,9 +423,11 @@ out: return 0; } +static bool native_acpi0017 = true; + static const struct acpi_device_id cxl_acpi_ids[] = { - { "ACPI0017", 0 }, - { "", 0 }, + { "ACPI0017", (unsigned long) &native_acpi0017 }, + { }, }; MODULE_DEVICE_TABLE(acpi, cxl_acpi_ids); diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index 1b2e816e061e..c5152718267e 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -226,6 +226,14 @@ struct cxl_nvdimm { struct nvdimm *nvdimm; }; +struct cxl_walk_context { + struct device *dev; + struct pci_bus *root; + struct cxl_port *port; + int error; + int count; +}; + /** * struct cxl_port - logical collection of upstream port devices and * downstream port devices to construct a CXL memory @@ -325,4 +333,12 @@ struct cxl_nvdimm *to_cxl_nvdimm(struct device *dev); bool is_cxl_nvdimm(struct device *dev); int devm_cxl_add_nvdimm(struct device *host, struct cxl_memdev *cxlmd); struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(void); + +/* + * Unit test builds overrides this to __weak, find the 'strong' version + * of these symbols in tools/testing/cxl/. + */ +#ifndef __mock +#define __mock static +#endif #endif /* __CXL_H__ */ diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild new file mode 100644 index 000000000000..63a4a07e71c4 --- /dev/null +++ b/tools/testing/cxl/Kbuild @@ -0,0 +1,36 @@ +# SPDX-License-Identifier: GPL-2.0 +ldflags-y += --wrap=is_acpi_device_node +ldflags-y += --wrap=acpi_get_table +ldflags-y += --wrap=acpi_put_table +ldflags-y += --wrap=acpi_evaluate_integer +ldflags-y += --wrap=acpi_pci_find_root +ldflags-y += --wrap=pci_walk_bus +ldflags-y += --wrap=nvdimm_bus_register + +DRIVERS := ../../../drivers +CXL_SRC := $(DRIVERS)/cxl +CXL_CORE_SRC := $(DRIVERS)/cxl/core +ccflags-y := -I$(srctree)/drivers/cxl/ +ccflags-y += -D__mock=__weak + +obj-m += cxl_acpi.o + +cxl_acpi-y := $(CXL_SRC)/acpi.o +cxl_acpi-y += mock_acpi.o +cxl_acpi-y += config_check.o + +obj-m += cxl_pmem.o + +cxl_pmem-y := $(CXL_SRC)/pmem.o +cxl_pmem-y += config_check.o + +obj-m += cxl_core.o + +cxl_core-y := $(CXL_CORE_SRC)/bus.o +cxl_core-y += $(CXL_CORE_SRC)/pmem.o +cxl_core-y += $(CXL_CORE_SRC)/regs.o +cxl_core-y += $(CXL_CORE_SRC)/memdev.o +cxl_core-y += $(CXL_CORE_SRC)/mbox.o +cxl_core-y += config_check.o + +obj-m += test/ diff --git a/tools/testing/cxl/config_check.c b/tools/testing/cxl/config_check.c new file mode 100644 index 000000000000..de5e5b3652fd --- /dev/null +++ b/tools/testing/cxl/config_check.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +#include + +void check(void) +{ + /* + * These kconfig symbols must be set to "m" for cxl_test to load + * and operate. + */ + BUILD_BUG_ON(!IS_MODULE(CONFIG_CXL_BUS)); + BUILD_BUG_ON(!IS_MODULE(CONFIG_CXL_ACPI)); + BUILD_BUG_ON(!IS_MODULE(CONFIG_CXL_PMEM)); +} diff --git a/tools/testing/cxl/mock_acpi.c b/tools/testing/cxl/mock_acpi.c new file mode 100644 index 000000000000..4c8a493ace56 --- /dev/null +++ b/tools/testing/cxl/mock_acpi.c @@ -0,0 +1,109 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright(c) 2021 Intel Corporation. All rights reserved. */ + +#include +#include +#include +#include +#include +#include "test/mock.h" + +struct acpi_device *to_cxl_host_bridge(struct device *host, struct device *dev) +{ + int index; + struct acpi_device *adev, *found = NULL; + struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); + + if (ops && ops->is_mock_bridge(dev)) { + found = ACPI_COMPANION(dev); + goto out; + } + + if (dev->bus == &platform_bus_type) + goto out; + + adev = to_acpi_device(dev); + if (!acpi_pci_find_root(adev->handle)) + goto out; + + if (strcmp(acpi_device_hid(adev), "ACPI0016") == 0) { + found = adev; + dev_dbg(host, "found host bridge %s\n", dev_name(&adev->dev)); + } +out: + put_cxl_mock_ops(index); + return found; +} + +static int match_add_root_port(struct pci_dev *pdev, void *data) +{ + struct cxl_walk_context *ctx = data; + struct pci_bus *root_bus = ctx->root; + struct cxl_port *port = ctx->port; + int type = pci_pcie_type(pdev); + struct device *dev = ctx->dev; + u32 lnkcap, port_num; + int rc; + + if (pdev->bus != root_bus) + return 0; + if (!pci_is_pcie(pdev)) + return 0; + if (type != PCI_EXP_TYPE_ROOT_PORT) + return 0; + if (pci_read_config_dword(pdev, pci_pcie_cap(pdev) + PCI_EXP_LNKCAP, + &lnkcap) != PCIBIOS_SUCCESSFUL) + return 0; + + /* TODO walk DVSEC to find component register base */ + port_num = FIELD_GET(PCI_EXP_LNKCAP_PN, lnkcap); + rc = cxl_add_dport(port, &pdev->dev, port_num, CXL_RESOURCE_NONE); + if (rc) { + dev_err(dev, "failed to add dport: %s (%d)\n", + dev_name(&pdev->dev), rc); + ctx->error = rc; + return rc; + } + ctx->count++; + + dev_dbg(dev, "add dport%d: %s\n", port_num, dev_name(&pdev->dev)); + + return 0; +} + +static int mock_add_root_port(struct platform_device *pdev, void *data) +{ + struct cxl_walk_context *ctx = data; + struct cxl_port *port = ctx->port; + struct device *dev = ctx->dev; + int rc; + + rc = cxl_add_dport(port, &pdev->dev, pdev->id, CXL_RESOURCE_NONE); + if (rc) { + dev_err(dev, "failed to add dport: %s (%d)\n", + dev_name(&pdev->dev), rc); + ctx->error = rc; + return rc; + } + ctx->count++; + + dev_dbg(dev, "add dport%d: %s\n", pdev->id, dev_name(&pdev->dev)); + + return 0; +} + +int match_add_root_ports(struct pci_dev *dev, void *data) +{ + int index, rc; + struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); + struct platform_device *pdev = (struct platform_device *) dev; + + if (ops && ops->is_mock_port(pdev)) + rc = mock_add_root_port(pdev, data); + else + rc = match_add_root_port(dev, data); + + put_cxl_mock_ops(index); + + return rc; +} diff --git a/tools/testing/cxl/test/Kbuild b/tools/testing/cxl/test/Kbuild new file mode 100644 index 000000000000..7de4ddecfd21 --- /dev/null +++ b/tools/testing/cxl/test/Kbuild @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-m += cxl_test.o +obj-m += cxl_mock.o + +cxl_test-y := cxl.o +cxl_mock-y := mock.o diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c new file mode 100644 index 000000000000..1c47b34244a4 --- /dev/null +++ b/tools/testing/cxl/test/cxl.c @@ -0,0 +1,509 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright(c) 2021 Intel Corporation. All rights reserved. + +#include +#include +#include +#include +#include +#include +#include +#include "mock.h" + +#define NR_CXL_HOST_BRIDGES 4 +#define NR_CXL_ROOT_PORTS 2 + +static struct platform_device *cxl_acpi; +static struct platform_device *cxl_host_bridge[NR_CXL_HOST_BRIDGES]; +static struct platform_device + *cxl_root_port[NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS]; + +static struct acpi_device acpi0017_mock; +static struct acpi_device host_bridge[NR_CXL_HOST_BRIDGES] = { + [0] = { + .handle = &host_bridge[0], + }, + [1] = { + .handle = &host_bridge[1], + }, + [2] = { + .handle = &host_bridge[2], + }, + [3] = { + .handle = &host_bridge[3], + }, +}; + +static bool is_mock_dev(struct device *dev) +{ + if (dev == &cxl_acpi->dev) + return true; + return false; +} + +static bool is_mock_adev(struct acpi_device *adev) +{ + int i; + + if (adev == &acpi0017_mock) + return true; + + for (i = 0; i < ARRAY_SIZE(host_bridge); i++) + if (adev == &host_bridge[i]) + return true; + + return false; +} + +static struct { + struct acpi_table_cedt cedt; + struct acpi_cedt_chbs chbs[NR_CXL_HOST_BRIDGES]; + struct { + struct acpi_cedt_cfmws cfmws; + u32 target[1]; + } cfmws0; + struct { + struct acpi_cedt_cfmws cfmws; + u32 target[4]; + } cfmws1; + struct { + struct acpi_cedt_cfmws cfmws; + u32 target[1]; + } cfmws2; + struct { + struct acpi_cedt_cfmws cfmws; + u32 target[4]; + } cfmws3; +} __packed mock_cedt = { + .cedt = { + .header = { + .signature = "CEDT", + .length = sizeof(mock_cedt), + .revision = 1, + }, + }, + .chbs[0] = { + .header = { + .type = ACPI_CEDT_TYPE_CHBS, + .length = sizeof(mock_cedt.chbs[0]), + }, + .uid = 0, + .cxl_version = ACPI_CEDT_CHBS_VERSION_CXL20, + }, + .chbs[1] = { + .header = { + .type = ACPI_CEDT_TYPE_CHBS, + .length = sizeof(mock_cedt.chbs[0]), + }, + .uid = 1, + .cxl_version = ACPI_CEDT_CHBS_VERSION_CXL20, + }, + .chbs[2] = { + .header = { + .type = ACPI_CEDT_TYPE_CHBS, + .length = sizeof(mock_cedt.chbs[0]), + }, + .uid = 2, + .cxl_version = ACPI_CEDT_CHBS_VERSION_CXL20, + }, + .chbs[3] = { + .header = { + .type = ACPI_CEDT_TYPE_CHBS, + .length = sizeof(mock_cedt.chbs[0]), + }, + .uid = 3, + .cxl_version = ACPI_CEDT_CHBS_VERSION_CXL20, + }, + .cfmws0 = { + .cfmws = { + .header = { + .type = ACPI_CEDT_TYPE_CFMWS, + .length = sizeof(mock_cedt.cfmws0), + }, + .interleave_ways = 0, + .granularity = 4, + .restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 | + ACPI_CEDT_CFMWS_RESTRICT_VOLATILE, + .qtg_id = 0, + .window_size = SZ_256M, + }, + .target = { 0 }, + }, + .cfmws1 = { + .cfmws = { + .header = { + .type = ACPI_CEDT_TYPE_CFMWS, + .length = sizeof(mock_cedt.cfmws1), + }, + .interleave_ways = 2, + .granularity = 4, + .restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 | + ACPI_CEDT_CFMWS_RESTRICT_VOLATILE, + .qtg_id = 1, + .window_size = SZ_256M * 4, + }, + .target = { 0, 1, 2, 3 }, + }, + .cfmws2 = { + .cfmws = { + .header = { + .type = ACPI_CEDT_TYPE_CFMWS, + .length = sizeof(mock_cedt.cfmws2), + }, + .interleave_ways = 0, + .granularity = 4, + .restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 | + ACPI_CEDT_CFMWS_RESTRICT_PMEM, + .qtg_id = 2, + .window_size = SZ_256M, + }, + .target = { 0 }, + }, + .cfmws3 = { + .cfmws = { + .header = { + .type = ACPI_CEDT_TYPE_CFMWS, + .length = sizeof(mock_cedt.cfmws3), + }, + .interleave_ways = 2, + .granularity = 4, + .restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 | + ACPI_CEDT_CFMWS_RESTRICT_PMEM, + .qtg_id = 3, + .window_size = SZ_256M * 4, + }, + .target = { 0, 1, 2, 3 }, + }, +}; + +struct cxl_mock_res { + struct list_head list; + struct range range; +}; + +static LIST_HEAD(mock_res); +static DEFINE_MUTEX(mock_res_lock); +static struct gen_pool *cxl_mock_pool; + +static void depopulate_all_mock_resources(void) +{ + struct cxl_mock_res *res, *_res; + + mutex_lock(&mock_res_lock); + list_for_each_entry_safe(res, _res, &mock_res, list) { + gen_pool_free(cxl_mock_pool, res->range.start, + range_len(&res->range)); + list_del(&res->list); + kfree(res); + } + mutex_unlock(&mock_res_lock); +} + +static struct cxl_mock_res *alloc_mock_res(resource_size_t size) +{ + struct cxl_mock_res *res = kzalloc(sizeof(*res), GFP_KERNEL); + struct genpool_data_align data = { + .align = SZ_256M, + }; + unsigned long phys; + + INIT_LIST_HEAD(&res->list); + phys = gen_pool_alloc_algo(cxl_mock_pool, size, + gen_pool_first_fit_align, &data); + if (!phys) + return NULL; + + res->range = (struct range) { + .start = phys, + .end = phys + size - 1, + }; + mutex_lock(&mock_res_lock); + list_add(&res->list, &mock_res); + mutex_unlock(&mock_res_lock); + + return res; +} + +static int populate_cedt(void) +{ + struct acpi_cedt_cfmws *cfmws[4] = { + [0] = &mock_cedt.cfmws0.cfmws, + [1] = &mock_cedt.cfmws1.cfmws, + [2] = &mock_cedt.cfmws2.cfmws, + [3] = &mock_cedt.cfmws3.cfmws, + }; + struct cxl_mock_res *res; + int i; + + for (i = 0; i < ARRAY_SIZE(mock_cedt.chbs); i++) { + struct acpi_cedt_chbs *chbs = &mock_cedt.chbs[i]; + resource_size_t size; + + if (chbs->cxl_version == ACPI_CEDT_CHBS_VERSION_CXL20) + size = ACPI_CEDT_CHBS_LENGTH_CXL20; + else + size = ACPI_CEDT_CHBS_LENGTH_CXL11; + + res = alloc_mock_res(size); + if (!res) + return -ENOMEM; + chbs->base = res->range.start; + chbs->length = size; + } + + for (i = 0; i < ARRAY_SIZE(cfmws); i++) { + struct acpi_cedt_cfmws *window = cfmws[i]; + + res = alloc_mock_res(window->window_size); + if (!res) + return -ENOMEM; + window->base_hpa = res->range.start; + } + + return 0; +} + +static acpi_status mock_acpi_get_table(char *signature, u32 instance, + struct acpi_table_header **out_table) +{ + if (instance < U32_MAX || strcmp(signature, ACPI_SIG_CEDT) != 0) + return acpi_get_table(signature, instance, out_table); + + *out_table = (struct acpi_table_header *) &mock_cedt; + return AE_OK; +} + +static void mock_acpi_put_table(struct acpi_table_header *table) +{ + if (table == (struct acpi_table_header *) &mock_cedt) + return; + acpi_put_table(table); +} + +static bool is_mock_bridge(struct device *dev) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(cxl_host_bridge); i++) + if (dev == &cxl_host_bridge[i]->dev) + return true; + + return false; +} + +static int host_bridge_index(struct acpi_device *adev) +{ + return adev - host_bridge; +} + +static struct acpi_device *find_host_bridge(acpi_handle handle) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(host_bridge); i++) + if (handle == host_bridge[i].handle) + return &host_bridge[i]; + return NULL; +} + +static acpi_status +mock_acpi_evaluate_integer(acpi_handle handle, acpi_string pathname, + struct acpi_object_list *arguments, + unsigned long long *data) +{ + struct acpi_device *adev = find_host_bridge(handle); + + if (!adev || strcmp(pathname, METHOD_NAME__UID) != 0) + return acpi_evaluate_integer(handle, pathname, arguments, data); + + *data = host_bridge_index(adev); + return AE_OK; +} + +static struct pci_bus mock_pci_bus[NR_CXL_HOST_BRIDGES]; +static struct acpi_pci_root mock_pci_root[NR_CXL_HOST_BRIDGES] = { + [0] = { + .bus = &mock_pci_bus[0], + }, + [1] = { + .bus = &mock_pci_bus[1], + }, + [2] = { + .bus = &mock_pci_bus[2], + }, + [3] = { + .bus = &mock_pci_bus[3], + }, +}; + +static struct platform_device *mock_cxl_root_port(struct pci_bus *bus, int index) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(mock_pci_bus); i++) + if (bus == &mock_pci_bus[i]) + return cxl_root_port[index + i * NR_CXL_ROOT_PORTS]; + return NULL; +} + +static bool is_mock_port(struct platform_device *pdev) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(cxl_root_port); i++) + if (pdev == cxl_root_port[i]) + return true; + return false; +} + +static bool is_mock_bus(struct pci_bus *bus) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(mock_pci_bus); i++) + if (bus == &mock_pci_bus[i]) + return true; + return false; +} + +static struct acpi_pci_root *mock_acpi_pci_find_root(acpi_handle handle) +{ + struct acpi_device *adev = find_host_bridge(handle); + + if (!adev) + return acpi_pci_find_root(handle); + return &mock_pci_root[host_bridge_index(adev)]; +} + +static struct cxl_mock_ops cxl_mock_ops = { + .is_mock_adev = is_mock_adev, + .is_mock_bridge = is_mock_bridge, + .is_mock_bus = is_mock_bus, + .is_mock_port = is_mock_port, + .is_mock_dev = is_mock_dev, + .mock_port = mock_cxl_root_port, + .acpi_get_table = mock_acpi_get_table, + .acpi_put_table = mock_acpi_put_table, + .acpi_evaluate_integer = mock_acpi_evaluate_integer, + .acpi_pci_find_root = mock_acpi_pci_find_root, + .list = LIST_HEAD_INIT(cxl_mock_ops.list), +}; + +static void mock_companion(struct acpi_device *adev, struct device *dev) +{ + device_initialize(&adev->dev); + fwnode_init(&adev->fwnode, NULL); + dev->fwnode = &adev->fwnode; + adev->fwnode.dev = dev; +} + +#ifndef SZ_64G +#define SZ_64G (SZ_32G * 2) +#endif + +#ifndef SZ_512G +#define SZ_512G (SZ_64G * 8) +#endif + +static __init int cxl_test_init(void) +{ + int rc, i; + + register_cxl_mock_ops(&cxl_mock_ops); + + cxl_mock_pool = gen_pool_create(ilog2(SZ_2M), NUMA_NO_NODE); + if (!cxl_mock_pool) { + rc = -ENOMEM; + goto err_gen_pool_create; + } + + rc = gen_pool_add(cxl_mock_pool, SZ_512G, SZ_64G, NUMA_NO_NODE); + if (rc) + goto err_gen_pool_add; + + rc = populate_cedt(); + if (rc) + goto err_populate; + + for (i = 0; i < ARRAY_SIZE(cxl_host_bridge); i++) { + struct acpi_device *adev = &host_bridge[i]; + struct platform_device *pdev; + + pdev = platform_device_alloc("cxl_host_bridge", i); + if (!pdev) + goto err_bridge; + + mock_companion(adev, &pdev->dev); + rc = platform_device_add(pdev); + if (rc) { + platform_device_put(pdev); + goto err_bridge; + } + cxl_host_bridge[i] = pdev; + } + + for (i = 0; i < ARRAY_SIZE(cxl_root_port); i++) { + struct platform_device *bridge = + cxl_host_bridge[i / NR_CXL_ROOT_PORTS]; + struct platform_device *pdev; + + pdev = platform_device_alloc("cxl_root_port", i); + if (!pdev) + goto err_port; + pdev->dev.parent = &bridge->dev; + + rc = platform_device_add(pdev); + if (rc) { + platform_device_put(pdev); + goto err_port; + } + cxl_root_port[i] = pdev; + } + + cxl_acpi = platform_device_alloc("cxl_acpi", 0); + if (!cxl_acpi) + goto err_port; + + mock_companion(&acpi0017_mock, &cxl_acpi->dev); + acpi0017_mock.dev.bus = &platform_bus_type; + + rc = platform_device_add(cxl_acpi); + if (rc) + goto err_add; + + return 0; + +err_add: + platform_device_put(cxl_acpi); +err_port: + for (i = ARRAY_SIZE(cxl_root_port) - 1; i >= 0; i--) + platform_device_unregister(cxl_root_port[i]); +err_bridge: + for (i = ARRAY_SIZE(cxl_host_bridge) - 1; i >= 0; i--) + platform_device_unregister(cxl_host_bridge[i]); +err_populate: + depopulate_all_mock_resources(); +err_gen_pool_add: + gen_pool_destroy(cxl_mock_pool); +err_gen_pool_create: + unregister_cxl_mock_ops(&cxl_mock_ops); + return rc; +} + +static __exit void cxl_test_exit(void) +{ + int i; + + platform_device_unregister(cxl_acpi); + for (i = ARRAY_SIZE(cxl_root_port) - 1; i >= 0; i--) + platform_device_unregister(cxl_root_port[i]); + for (i = ARRAY_SIZE(cxl_host_bridge) - 1; i >= 0; i--) + platform_device_unregister(cxl_host_bridge[i]); + depopulate_all_mock_resources(); + gen_pool_destroy(cxl_mock_pool); + unregister_cxl_mock_ops(&cxl_mock_ops); +} + +module_init(cxl_test_init); +module_exit(cxl_test_exit); +MODULE_LICENSE("GPL v2"); diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c new file mode 100644 index 000000000000..b8c108abcf07 --- /dev/null +++ b/tools/testing/cxl/test/mock.c @@ -0,0 +1,171 @@ +// SPDX-License-Identifier: GPL-2.0-only +//Copyright(c) 2021 Intel Corporation. All rights reserved. + +#include +#include +#include +#include +#include +#include +#include "mock.h" + +static LIST_HEAD(mock); + +void register_cxl_mock_ops(struct cxl_mock_ops *ops) +{ + list_add_rcu(&ops->list, &mock); +} +EXPORT_SYMBOL_GPL(register_cxl_mock_ops); + +static DEFINE_SRCU(cxl_mock_srcu); + +void unregister_cxl_mock_ops(struct cxl_mock_ops *ops) +{ + list_del_rcu(&ops->list); + synchronize_srcu(&cxl_mock_srcu); +} +EXPORT_SYMBOL_GPL(unregister_cxl_mock_ops); + +struct cxl_mock_ops *get_cxl_mock_ops(int *index) +{ + *index = srcu_read_lock(&cxl_mock_srcu); + return list_first_or_null_rcu(&mock, struct cxl_mock_ops, list); +} +EXPORT_SYMBOL_GPL(get_cxl_mock_ops); + +void put_cxl_mock_ops(int index) +{ + srcu_read_unlock(&cxl_mock_srcu, index); +} +EXPORT_SYMBOL_GPL(put_cxl_mock_ops); + +bool __wrap_is_acpi_device_node(const struct fwnode_handle *fwnode) +{ + struct acpi_device *adev = + container_of(fwnode, struct acpi_device, fwnode); + int index; + struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); + bool retval = false; + + if (ops) + retval = ops->is_mock_adev(adev); + + if (!retval) + retval = is_acpi_device_node(fwnode); + + put_cxl_mock_ops(index); + return retval; +} +EXPORT_SYMBOL(__wrap_is_acpi_device_node); + +acpi_status __wrap_acpi_get_table(char *signature, u32 instance, + struct acpi_table_header **out_table) +{ + int index; + struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); + acpi_status status; + + if (ops) + status = ops->acpi_get_table(signature, instance, out_table); + else + status = acpi_get_table(signature, instance, out_table); + + put_cxl_mock_ops(index); + + return status; +} +EXPORT_SYMBOL(__wrap_acpi_get_table); + +void __wrap_acpi_put_table(struct acpi_table_header *table) +{ + int index; + struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); + + if (ops) + ops->acpi_put_table(table); + else + acpi_put_table(table); + put_cxl_mock_ops(index); +} +EXPORT_SYMBOL(__wrap_acpi_put_table); + +acpi_status __wrap_acpi_evaluate_integer(acpi_handle handle, + acpi_string pathname, + struct acpi_object_list *arguments, + unsigned long long *data) +{ + int index; + struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); + acpi_status status; + + if (ops) + status = ops->acpi_evaluate_integer(handle, pathname, arguments, + data); + else + status = acpi_evaluate_integer(handle, pathname, arguments, + data); + put_cxl_mock_ops(index); + + return status; +} +EXPORT_SYMBOL(__wrap_acpi_evaluate_integer); + +struct acpi_pci_root *__wrap_acpi_pci_find_root(acpi_handle handle) +{ + int index; + struct acpi_pci_root *root; + struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); + + if (ops) + root = ops->acpi_pci_find_root(handle); + else + root = acpi_pci_find_root(handle); + + put_cxl_mock_ops(index); + + return root; +} +EXPORT_SYMBOL_GPL(__wrap_acpi_pci_find_root); + +void __wrap_pci_walk_bus(struct pci_bus *bus, + int (*cb)(struct pci_dev *, void *), void *userdata) +{ + int index; + struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); + + if (ops && ops->is_mock_bus(bus)) { + int rc, i; + + /* + * Simulate 2 root ports per host-bridge and no + * depth recursion. + */ + for (i = 0; i < 2; i++) { + rc = cb((struct pci_dev *) ops->mock_port(bus, i), + userdata); + if (rc) + break; + } + } else + pci_walk_bus(bus, cb, userdata); + + put_cxl_mock_ops(index); +} +EXPORT_SYMBOL_GPL(__wrap_pci_walk_bus); + +struct nvdimm_bus * +__wrap_nvdimm_bus_register(struct device *dev, + struct nvdimm_bus_descriptor *nd_desc) +{ + int index; + struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); + + if (ops && ops->is_mock_dev(dev->parent->parent)) + nd_desc->provider_name = "cxl_test"; + put_cxl_mock_ops(index); + + return nvdimm_bus_register(dev, nd_desc); +} +EXPORT_SYMBOL_GPL(__wrap_nvdimm_bus_register); + +MODULE_LICENSE("GPL v2"); diff --git a/tools/testing/cxl/test/mock.h b/tools/testing/cxl/test/mock.h new file mode 100644 index 000000000000..805a94cb3fbe --- /dev/null +++ b/tools/testing/cxl/test/mock.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include +#include + +struct cxl_mock_ops { + struct list_head list; + bool (*is_mock_adev)(struct acpi_device *dev); + acpi_status (*acpi_get_table)(char *signature, u32 instance, + struct acpi_table_header **out_table); + void (*acpi_put_table)(struct acpi_table_header *table); + bool (*is_mock_bridge)(struct device *dev); + acpi_status (*acpi_evaluate_integer)(acpi_handle handle, + acpi_string pathname, + struct acpi_object_list *arguments, + unsigned long long *data); + struct acpi_pci_root *(*acpi_pci_find_root)(acpi_handle handle); + struct platform_device *(*mock_port)(struct pci_bus *bus, int index); + bool (*is_mock_bus)(struct pci_bus *bus); + bool (*is_mock_port)(struct platform_device *pdev); + bool (*is_mock_dev)(struct device *dev); +}; + +void register_cxl_mock_ops(struct cxl_mock_ops *ops); +void unregister_cxl_mock_ops(struct cxl_mock_ops *ops); +struct cxl_mock_ops *get_cxl_mock_ops(int *index); +void put_cxl_mock_ops(int index); From a5c25802168993c67a03a6e04142761dfb4a3bf5 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 8 Sep 2021 22:13:10 -0700 Subject: [PATCH 056/587] cxl/bus: Populate the target list at decoder create As found by cxl_test, the implementation populated the target_list for the single dport exceptional case, it missed populating the target_list for the typical multi-dport case. Root decoders always know their target list at the beginning of time, and even switch-level decoders should have a target list of one or more zeros by default, depending on the interleave-ways setting. Walk the hosting port's dport list and populate based on the passed in map. Move devm_cxl_add_passthrough_decoder() out of line now that it does the work of generating a target_map. Before: $ cat /sys/bus/cxl/devices/root2/decoder*/target_list 0 0 After: $ cat /sys/bus/cxl/devices/root2/decoder*/target_list 0 0,1,2,3 0 0,1,2,3 Where root2 is a CXL topology root object generated by 'cxl_test'. Acked-by: Ben Widawsky Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/163116439000.2460985.11713777051267946018.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/cxl/acpi.c | 13 ++++++- drivers/cxl/core/bus.c | 80 ++++++++++++++++++++++++++++++++++++------ drivers/cxl/cxl.h | 25 ++++++------- 3 files changed, 91 insertions(+), 27 deletions(-) diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c index 32775d1ac4b3..d39cc797a64e 100644 --- a/drivers/cxl/acpi.c +++ b/drivers/cxl/acpi.c @@ -52,6 +52,12 @@ static int cxl_acpi_cfmws_verify(struct device *dev, return -EINVAL; } + if (CFMWS_INTERLEAVE_WAYS(cfmws) > CXL_DECODER_MAX_INTERLEAVE) { + dev_err(dev, "CFMWS Interleave Ways (%d) too large\n", + CFMWS_INTERLEAVE_WAYS(cfmws)); + return -EINVAL; + } + expected_len = struct_size((cfmws), interleave_targets, CFMWS_INTERLEAVE_WAYS(cfmws)); @@ -71,6 +77,7 @@ static int cxl_acpi_cfmws_verify(struct device *dev, static void cxl_add_cfmws_decoders(struct device *dev, struct cxl_port *root_port) { + int target_map[CXL_DECODER_MAX_INTERLEAVE]; struct acpi_cedt_cfmws *cfmws; struct cxl_decoder *cxld; acpi_size len, cur = 0; @@ -83,6 +90,7 @@ static void cxl_add_cfmws_decoders(struct device *dev, while (cur < len) { struct acpi_cedt_header *c = cedt_subtable + cur; + int i; if (c->type != ACPI_CEDT_TYPE_CFMWS) { cur += c->length; @@ -108,6 +116,9 @@ static void cxl_add_cfmws_decoders(struct device *dev, continue; } + for (i = 0; i < CFMWS_INTERLEAVE_WAYS(cfmws); i++) + target_map[i] = cfmws->interleave_targets[i]; + flags = cfmws_to_decoder_flags(cfmws->restrictions); cxld = devm_cxl_add_decoder(dev, root_port, CFMWS_INTERLEAVE_WAYS(cfmws), @@ -115,7 +126,7 @@ static void cxl_add_cfmws_decoders(struct device *dev, CFMWS_INTERLEAVE_WAYS(cfmws), CFMWS_INTERLEAVE_GRANULARITY(cfmws), CXL_DECODER_EXPANDER, - flags); + flags, target_map); if (IS_ERR(cxld)) { dev_err(dev, "Failed to add decoder for %#llx-%#llx\n", diff --git a/drivers/cxl/core/bus.c b/drivers/cxl/core/bus.c index 9a8fa88b634c..6dfdeaf999f0 100644 --- a/drivers/cxl/core/bus.c +++ b/drivers/cxl/core/bus.c @@ -453,11 +453,38 @@ err: } EXPORT_SYMBOL_GPL(cxl_add_dport); +static int decoder_populate_targets(struct device *host, + struct cxl_decoder *cxld, + struct cxl_port *port, int *target_map, + int nr_targets) +{ + int rc = 0, i; + + if (!target_map) + return 0; + + device_lock(&port->dev); + for (i = 0; i < nr_targets; i++) { + struct cxl_dport *dport = find_dport(port, target_map[i]); + + if (!dport) { + rc = -ENXIO; + break; + } + dev_dbg(host, "%s: target: %d\n", dev_name(dport->dport), i); + cxld->target[i] = dport; + } + device_unlock(&port->dev); + + return rc; +} + static struct cxl_decoder * -cxl_decoder_alloc(struct cxl_port *port, int nr_targets, resource_size_t base, - resource_size_t len, int interleave_ways, - int interleave_granularity, enum cxl_decoder_type type, - unsigned long flags) +cxl_decoder_alloc(struct device *host, struct cxl_port *port, int nr_targets, + resource_size_t base, resource_size_t len, + int interleave_ways, int interleave_granularity, + enum cxl_decoder_type type, unsigned long flags, + int *target_map) { struct cxl_decoder *cxld; struct device *dev; @@ -493,10 +520,10 @@ cxl_decoder_alloc(struct cxl_port *port, int nr_targets, resource_size_t base, .target_type = type, }; - /* handle implied target_list */ - if (interleave_ways == 1) - cxld->target[0] = - list_first_entry(&port->dports, struct cxl_dport, list); + rc = decoder_populate_targets(host, cxld, port, target_map, nr_targets); + if (rc) + goto err; + dev = &cxld->dev; device_initialize(dev); device_set_pm_not_required(dev); @@ -519,14 +546,19 @@ struct cxl_decoder * devm_cxl_add_decoder(struct device *host, struct cxl_port *port, int nr_targets, resource_size_t base, resource_size_t len, int interleave_ways, int interleave_granularity, - enum cxl_decoder_type type, unsigned long flags) + enum cxl_decoder_type type, unsigned long flags, + int *target_map) { struct cxl_decoder *cxld; struct device *dev; int rc; - cxld = cxl_decoder_alloc(port, nr_targets, base, len, interleave_ways, - interleave_granularity, type, flags); + if (nr_targets > CXL_DECODER_MAX_INTERLEAVE) + return ERR_PTR(-EINVAL); + + cxld = cxl_decoder_alloc(host, port, nr_targets, base, len, + interleave_ways, interleave_granularity, type, + flags, target_map); if (IS_ERR(cxld)) return cxld; @@ -550,6 +582,32 @@ err: } EXPORT_SYMBOL_GPL(devm_cxl_add_decoder); +/* + * Per the CXL specification (8.2.5.12 CXL HDM Decoder Capability Structure) + * single ported host-bridges need not publish a decoder capability when a + * passthrough decode can be assumed, i.e. all transactions that the uport sees + * are claimed and passed to the single dport. Default the range a 0-base + * 0-length until the first CXL region is activated. + */ +struct cxl_decoder *devm_cxl_add_passthrough_decoder(struct device *host, + struct cxl_port *port) +{ + struct cxl_dport *dport; + int target_map[1]; + + device_lock(&port->dev); + dport = list_first_entry_or_null(&port->dports, typeof(*dport), list); + device_unlock(&port->dev); + + if (!dport) + return ERR_PTR(-ENXIO); + + target_map[0] = dport->port_id; + return devm_cxl_add_decoder(host, port, 1, 0, 0, 1, PAGE_SIZE, + CXL_DECODER_EXPANDER, 0, target_map); +} +EXPORT_SYMBOL_GPL(devm_cxl_add_passthrough_decoder); + /** * __cxl_driver_register - register a driver for the cxl bus * @cxl_drv: cxl driver structure to attach diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index c5152718267e..84b8836c1f91 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -180,6 +180,12 @@ enum cxl_decoder_type { CXL_DECODER_EXPANDER = 3, }; +/* + * Current specification goes up to 8, double that seems a reasonable + * software max for the foreseeable future + */ +#define CXL_DECODER_MAX_INTERLEAVE 16 + /** * struct cxl_decoder - CXL address range decode configuration * @dev: this decoder's device @@ -284,22 +290,11 @@ struct cxl_decoder * devm_cxl_add_decoder(struct device *host, struct cxl_port *port, int nr_targets, resource_size_t base, resource_size_t len, int interleave_ways, int interleave_granularity, - enum cxl_decoder_type type, unsigned long flags); - -/* - * Per the CXL specification (8.2.5.12 CXL HDM Decoder Capability Structure) - * single ported host-bridges need not publish a decoder capability when a - * passthrough decode can be assumed, i.e. all transactions that the uport sees - * are claimed and passed to the single dport. Default the range a 0-base - * 0-length until the first CXL region is activated. - */ -static inline struct cxl_decoder * -devm_cxl_add_passthrough_decoder(struct device *host, struct cxl_port *port) -{ - return devm_cxl_add_decoder(host, port, 1, 0, 0, 1, PAGE_SIZE, - CXL_DECODER_EXPANDER, 0); -} + enum cxl_decoder_type type, unsigned long flags, + int *target_map); +struct cxl_decoder *devm_cxl_add_passthrough_decoder(struct device *host, + struct cxl_port *port); extern struct bus_type cxl_bus_type; struct cxl_driver { From 49be6dd807511db31809000a7b9d430b18d5e780 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 8 Sep 2021 22:13:15 -0700 Subject: [PATCH 057/587] cxl/mbox: Move command definitions to common location In preparation for cxl_test to mock responses to mailbox command requests, move some definitions from core/mbox.c to cxlmem.h. No functional changes intended. Acked-by: Ben Widawsky Acked-by: Jonathan Cameron Link: https://lore.kernel.org/r/163116439547.2460985.10457111177103589574.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/cxl/core/mbox.c | 45 +++++--------------------------- drivers/cxl/cxlmem.h | 57 +++++++++++++++++++++++++++++++++++++++++ drivers/cxl/pmem.c | 11 ++------ 3 files changed, 65 insertions(+), 48 deletions(-) diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 82e79da195fa..576796a5d9f3 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -485,11 +485,7 @@ static int cxl_xfer_log(struct cxl_mem *cxlm, uuid_t *uuid, u32 size, u8 *out) while (remaining) { u32 xfer_size = min_t(u32, remaining, cxlm->payload_size); - struct cxl_mbox_get_log { - uuid_t uuid; - __le32 offset; - __le32 length; - } __packed log = { + struct cxl_mbox_get_log log = { .uuid = *uuid, .offset = cpu_to_le32(offset), .length = cpu_to_le32(xfer_size) @@ -520,14 +516,11 @@ static int cxl_xfer_log(struct cxl_mem *cxlm, uuid_t *uuid, u32 size, u8 *out) */ static void cxl_walk_cel(struct cxl_mem *cxlm, size_t size, u8 *cel) { - struct cel_entry { - __le16 opcode; - __le16 effect; - } __packed * cel_entry; + struct cxl_cel_entry *cel_entry; const int cel_entries = size / sizeof(*cel_entry); int i; - cel_entry = (struct cel_entry *)cel; + cel_entry = (struct cxl_cel_entry *) cel; for (i = 0; i < cel_entries; i++) { u16 opcode = le16_to_cpu(cel_entry[i].opcode); @@ -543,15 +536,6 @@ static void cxl_walk_cel(struct cxl_mem *cxlm, size_t size, u8 *cel) } } -struct cxl_mbox_get_supported_logs { - __le16 entries; - u8 rsvd[6]; - struct gsl_entry { - uuid_t uuid; - __le32 size; - } __packed entry[]; -} __packed; - static struct cxl_mbox_get_supported_logs *cxl_get_gsl(struct cxl_mem *cxlm) { struct cxl_mbox_get_supported_logs *ret; @@ -578,10 +562,8 @@ enum { /* See CXL 2.0 Table 170. Get Log Input Payload */ static const uuid_t log_uuid[] = { - [CEL_UUID] = UUID_INIT(0xda9c0b5, 0xbf41, 0x4b78, 0x8f, 0x79, 0x96, - 0xb1, 0x62, 0x3b, 0x3f, 0x17), - [VENDOR_DEBUG_UUID] = UUID_INIT(0xe1819d9, 0x11a9, 0x400c, 0x81, 0x1f, - 0xd6, 0x07, 0x19, 0x40, 0x3d, 0x86), + [CEL_UUID] = DEFINE_CXL_CEL_UUID, + [VENDOR_DEBUG_UUID] = DEFINE_CXL_VENDOR_DEBUG_UUID, }; /** @@ -698,22 +680,7 @@ static int cxl_mem_get_partition_info(struct cxl_mem *cxlm) int cxl_mem_identify(struct cxl_mem *cxlm) { /* See CXL 2.0 Table 175 Identify Memory Device Output Payload */ - struct cxl_mbox_identify { - char fw_revision[0x10]; - __le64 total_capacity; - __le64 volatile_capacity; - __le64 persistent_capacity; - __le64 partition_align; - __le16 info_event_log_size; - __le16 warning_event_log_size; - __le16 failure_event_log_size; - __le16 fatal_event_log_size; - __le32 lsa_size; - u8 poison_list_max_mer[3]; - __le16 inject_poison_limit; - u8 poison_caps; - u8 qos_telemetry_caps; - } __packed id; + struct cxl_mbox_identify id; int rc; rc = cxl_mem_mbox_send_cmd(cxlm, CXL_MBOX_OP_IDENTIFY, NULL, 0, &id, diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index 373add570ef6..c4f450ad434d 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -171,6 +171,63 @@ enum cxl_opcode { CXL_MBOX_OP_MAX = 0x10000 }; +#define DEFINE_CXL_CEL_UUID \ + UUID_INIT(0xda9c0b5, 0xbf41, 0x4b78, 0x8f, 0x79, 0x96, 0xb1, 0x62, \ + 0x3b, 0x3f, 0x17) + +#define DEFINE_CXL_VENDOR_DEBUG_UUID \ + UUID_INIT(0xe1819d9, 0x11a9, 0x400c, 0x81, 0x1f, 0xd6, 0x07, 0x19, \ + 0x40, 0x3d, 0x86) + +struct cxl_mbox_get_supported_logs { + __le16 entries; + u8 rsvd[6]; + struct cxl_gsl_entry { + uuid_t uuid; + __le32 size; + } __packed entry[]; +} __packed; + +struct cxl_cel_entry { + __le16 opcode; + __le16 effect; +} __packed; + +struct cxl_mbox_get_log { + uuid_t uuid; + __le32 offset; + __le32 length; +} __packed; + +/* See CXL 2.0 Table 175 Identify Memory Device Output Payload */ +struct cxl_mbox_identify { + char fw_revision[0x10]; + __le64 total_capacity; + __le64 volatile_capacity; + __le64 persistent_capacity; + __le64 partition_align; + __le16 info_event_log_size; + __le16 warning_event_log_size; + __le16 failure_event_log_size; + __le16 fatal_event_log_size; + __le32 lsa_size; + u8 poison_list_max_mer[3]; + __le16 inject_poison_limit; + u8 poison_caps; + u8 qos_telemetry_caps; +} __packed; + +struct cxl_mbox_get_lsa { + u32 offset; + u32 length; +} __packed; + +struct cxl_mbox_set_lsa { + u32 offset; + u32 reserved; + u8 data[]; +} __packed; + /** * struct cxl_mem_command - Driver representation of a memory device command * @info: Command information as it exists for the UAPI diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c index 5ccf9aa6b3ae..d7b5548551e9 100644 --- a/drivers/cxl/pmem.c +++ b/drivers/cxl/pmem.c @@ -99,10 +99,7 @@ static int cxl_pmem_get_config_data(struct cxl_mem *cxlm, struct nd_cmd_get_config_data_hdr *cmd, unsigned int buf_len) { - struct cxl_mbox_get_lsa { - u32 offset; - u32 length; - } get_lsa; + struct cxl_mbox_get_lsa get_lsa; int rc; if (sizeof(*cmd) > buf_len) @@ -127,11 +124,7 @@ static int cxl_pmem_set_config_data(struct cxl_mem *cxlm, struct nd_cmd_set_config_hdr *cmd, unsigned int buf_len) { - struct cxl_mbox_set_lsa { - u32 offset; - u32 reserved; - u8 data[]; - } *set_lsa; + struct cxl_mbox_set_lsa *set_lsa; int rc; if (sizeof(*cmd) > buf_len) From 7d3eb23c4ccf457b52cafdca1a7b20cddf29e021 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 8 Sep 2021 22:13:21 -0700 Subject: [PATCH 058/587] tools/testing/cxl: Introduce a mock memory device + driver Introduce an emulated device-set plus driver to register CXL memory devices, 'struct cxl_memdev' instances, in the mock cxl_test topology. This enables the development of HDM Decoder (Host-managed Device Memory Decoder) programming flow (region provisioning) in an environment that can be updated alongside the kernel as it gains more functionality. Whereas the cxl_pci module looks for CXL memory expanders on the 'pci' bus, the cxl_mock_mem module attaches to CXL expanders on the platform bus emitted by cxl_test. Acked-by: Ben Widawsky Reported-by: kernel test robot Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/163116440099.2460985.10692549614409346604.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/cxl/core/pmem.c | 6 +- drivers/cxl/cxl.h | 2 +- drivers/cxl/pmem.c | 2 +- tools/testing/cxl/Kbuild | 2 + tools/testing/cxl/mock_pmem.c | 24 ++++ tools/testing/cxl/test/Kbuild | 4 + tools/testing/cxl/test/cxl.c | 69 ++++++++- tools/testing/cxl/test/mem.c | 256 ++++++++++++++++++++++++++++++++++ 8 files changed, 359 insertions(+), 6 deletions(-) create mode 100644 tools/testing/cxl/mock_pmem.c create mode 100644 tools/testing/cxl/test/mem.c diff --git a/drivers/cxl/core/pmem.c b/drivers/cxl/core/pmem.c index 9e56be3994f1..74be5132df1c 100644 --- a/drivers/cxl/core/pmem.c +++ b/drivers/cxl/core/pmem.c @@ -51,16 +51,16 @@ struct cxl_nvdimm_bridge *to_cxl_nvdimm_bridge(struct device *dev) } EXPORT_SYMBOL_GPL(to_cxl_nvdimm_bridge); -static int match_nvdimm_bridge(struct device *dev, const void *data) +__mock int match_nvdimm_bridge(struct device *dev, const void *data) { return dev->type == &cxl_nvdimm_bridge_type; } -struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(void) +struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct cxl_nvdimm *cxl_nvd) { struct device *dev; - dev = bus_find_device(&cxl_bus_type, NULL, NULL, match_nvdimm_bridge); + dev = bus_find_device(&cxl_bus_type, NULL, cxl_nvd, match_nvdimm_bridge); if (!dev) return NULL; return to_cxl_nvdimm_bridge(dev); diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index 84b8836c1f91..9af5745ba2c0 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -327,7 +327,7 @@ struct cxl_nvdimm_bridge *devm_cxl_add_nvdimm_bridge(struct device *host, struct cxl_nvdimm *to_cxl_nvdimm(struct device *dev); bool is_cxl_nvdimm(struct device *dev); int devm_cxl_add_nvdimm(struct device *host, struct cxl_memdev *cxlmd); -struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(void); +struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct cxl_nvdimm *cxl_nvd); /* * Unit test builds overrides this to __weak, find the 'strong' version diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c index d7b5548551e9..ceb2115981e5 100644 --- a/drivers/cxl/pmem.c +++ b/drivers/cxl/pmem.c @@ -39,7 +39,7 @@ static int cxl_nvdimm_probe(struct device *dev) struct nvdimm *nvdimm; int rc; - cxl_nvb = cxl_find_nvdimm_bridge(); + cxl_nvb = cxl_find_nvdimm_bridge(cxl_nvd); if (!cxl_nvb) return -ENXIO; diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild index 63a4a07e71c4..86deba8308a1 100644 --- a/tools/testing/cxl/Kbuild +++ b/tools/testing/cxl/Kbuild @@ -33,4 +33,6 @@ cxl_core-y += $(CXL_CORE_SRC)/memdev.o cxl_core-y += $(CXL_CORE_SRC)/mbox.o cxl_core-y += config_check.o +cxl_core-y += mock_pmem.o + obj-m += test/ diff --git a/tools/testing/cxl/mock_pmem.c b/tools/testing/cxl/mock_pmem.c new file mode 100644 index 000000000000..f7315e6f52c0 --- /dev/null +++ b/tools/testing/cxl/mock_pmem.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright(c) 2021 Intel Corporation. All rights reserved. */ +#include +#include "test/mock.h" +#include + +int match_nvdimm_bridge(struct device *dev, const void *data) +{ + int index, rc = 0; + struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); + const struct cxl_nvdimm *cxl_nvd = data; + + if (ops) { + if (dev->type == &cxl_nvdimm_bridge_type && + (ops->is_mock_dev(dev->parent->parent) == + ops->is_mock_dev(cxl_nvd->dev.parent->parent))) + rc = 1; + } else + rc = dev->type == &cxl_nvdimm_bridge_type; + + put_cxl_mock_ops(index); + + return rc; +} diff --git a/tools/testing/cxl/test/Kbuild b/tools/testing/cxl/test/Kbuild index 7de4ddecfd21..4e59e2c911f6 100644 --- a/tools/testing/cxl/test/Kbuild +++ b/tools/testing/cxl/test/Kbuild @@ -1,6 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 +ccflags-y := -I$(srctree)/drivers/cxl/ + obj-m += cxl_test.o obj-m += cxl_mock.o +obj-m += cxl_mock_mem.o cxl_test-y := cxl.o cxl_mock-y := mock.o +cxl_mock_mem-y := mem.o diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c index 1c47b34244a4..cb32f9e27d5d 100644 --- a/tools/testing/cxl/test/cxl.c +++ b/tools/testing/cxl/test/cxl.c @@ -17,6 +17,7 @@ static struct platform_device *cxl_acpi; static struct platform_device *cxl_host_bridge[NR_CXL_HOST_BRIDGES]; static struct platform_device *cxl_root_port[NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS]; +struct platform_device *cxl_mem[NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS]; static struct acpi_device acpi0017_mock; static struct acpi_device host_bridge[NR_CXL_HOST_BRIDGES] = { @@ -36,6 +37,11 @@ static struct acpi_device host_bridge[NR_CXL_HOST_BRIDGES] = { static bool is_mock_dev(struct device *dev) { + int i; + + for (i = 0; i < ARRAY_SIZE(cxl_mem); i++) + if (dev == &cxl_mem[i]->dev) + return true; if (dev == &cxl_acpi->dev) return true; return false; @@ -405,6 +411,44 @@ static void mock_companion(struct acpi_device *adev, struct device *dev) #define SZ_512G (SZ_64G * 8) #endif +static struct platform_device *alloc_memdev(int id) +{ + struct resource res[] = { + [0] = { + .flags = IORESOURCE_MEM, + }, + [1] = { + .flags = IORESOURCE_MEM, + .desc = IORES_DESC_PERSISTENT_MEMORY, + }, + }; + struct platform_device *pdev; + int i, rc; + + for (i = 0; i < ARRAY_SIZE(res); i++) { + struct cxl_mock_res *r = alloc_mock_res(SZ_256M); + + if (!r) + return NULL; + res[i].start = r->range.start; + res[i].end = r->range.end; + } + + pdev = platform_device_alloc("cxl_mem", id); + if (!pdev) + return NULL; + + rc = platform_device_add_resources(pdev, res, ARRAY_SIZE(res)); + if (rc) + goto err; + + return pdev; + +err: + platform_device_put(pdev); + return NULL; +} + static __init int cxl_test_init(void) { int rc, i; @@ -460,9 +504,27 @@ static __init int cxl_test_init(void) cxl_root_port[i] = pdev; } + BUILD_BUG_ON(ARRAY_SIZE(cxl_mem) != ARRAY_SIZE(cxl_root_port)); + for (i = 0; i < ARRAY_SIZE(cxl_mem); i++) { + struct platform_device *port = cxl_root_port[i]; + struct platform_device *pdev; + + pdev = alloc_memdev(i); + if (!pdev) + goto err_mem; + pdev->dev.parent = &port->dev; + + rc = platform_device_add(pdev); + if (rc) { + platform_device_put(pdev); + goto err_mem; + } + cxl_mem[i] = pdev; + } + cxl_acpi = platform_device_alloc("cxl_acpi", 0); if (!cxl_acpi) - goto err_port; + goto err_mem; mock_companion(&acpi0017_mock, &cxl_acpi->dev); acpi0017_mock.dev.bus = &platform_bus_type; @@ -475,6 +537,9 @@ static __init int cxl_test_init(void) err_add: platform_device_put(cxl_acpi); +err_mem: + for (i = ARRAY_SIZE(cxl_mem) - 1; i >= 0; i--) + platform_device_unregister(cxl_mem[i]); err_port: for (i = ARRAY_SIZE(cxl_root_port) - 1; i >= 0; i--) platform_device_unregister(cxl_root_port[i]); @@ -495,6 +560,8 @@ static __exit void cxl_test_exit(void) int i; platform_device_unregister(cxl_acpi); + for (i = ARRAY_SIZE(cxl_mem) - 1; i >= 0; i--) + platform_device_unregister(cxl_mem[i]); for (i = ARRAY_SIZE(cxl_root_port) - 1; i >= 0; i--) platform_device_unregister(cxl_root_port[i]); for (i = ARRAY_SIZE(cxl_host_bridge) - 1; i >= 0; i--) diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c new file mode 100644 index 000000000000..12a8437a9ca0 --- /dev/null +++ b/tools/testing/cxl/test/mem.c @@ -0,0 +1,256 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright(c) 2021 Intel Corporation. All rights reserved. + +#include +#include +#include +#include +#include +#include + +#define LSA_SIZE SZ_128K +#define EFFECT(x) (1U << x) + +static struct cxl_cel_entry mock_cel[] = { + { + .opcode = cpu_to_le16(CXL_MBOX_OP_GET_SUPPORTED_LOGS), + .effect = cpu_to_le16(0), + }, + { + .opcode = cpu_to_le16(CXL_MBOX_OP_IDENTIFY), + .effect = cpu_to_le16(0), + }, + { + .opcode = cpu_to_le16(CXL_MBOX_OP_GET_LSA), + .effect = cpu_to_le16(0), + }, + { + .opcode = cpu_to_le16(CXL_MBOX_OP_SET_LSA), + .effect = cpu_to_le16(EFFECT(1) | EFFECT(2)), + }, +}; + +static struct { + struct cxl_mbox_get_supported_logs gsl; + struct cxl_gsl_entry entry; +} mock_gsl_payload = { + .gsl = { + .entries = cpu_to_le16(1), + }, + .entry = { + .uuid = DEFINE_CXL_CEL_UUID, + .size = cpu_to_le32(sizeof(mock_cel)), + }, +}; + +static int mock_gsl(struct cxl_mbox_cmd *cmd) +{ + if (cmd->size_out < sizeof(mock_gsl_payload)) + return -EINVAL; + + memcpy(cmd->payload_out, &mock_gsl_payload, sizeof(mock_gsl_payload)); + cmd->size_out = sizeof(mock_gsl_payload); + + return 0; +} + +static int mock_get_log(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd) +{ + struct cxl_mbox_get_log *gl = cmd->payload_in; + u32 offset = le32_to_cpu(gl->offset); + u32 length = le32_to_cpu(gl->length); + uuid_t uuid = DEFINE_CXL_CEL_UUID; + void *data = &mock_cel; + + if (cmd->size_in < sizeof(*gl)) + return -EINVAL; + if (length > cxlm->payload_size) + return -EINVAL; + if (offset + length > sizeof(mock_cel)) + return -EINVAL; + if (!uuid_equal(&gl->uuid, &uuid)) + return -EINVAL; + if (length > cmd->size_out) + return -EINVAL; + + memcpy(cmd->payload_out, data + offset, length); + + return 0; +} + +static int mock_id(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd) +{ + struct platform_device *pdev = to_platform_device(cxlm->dev); + struct cxl_mbox_identify id = { + .fw_revision = { "mock fw v1 " }, + .lsa_size = cpu_to_le32(LSA_SIZE), + /* FIXME: Add partition support */ + .partition_align = cpu_to_le64(0), + }; + u64 capacity = 0; + int i; + + if (cmd->size_out < sizeof(id)) + return -EINVAL; + + for (i = 0; i < 2; i++) { + struct resource *res; + + res = platform_get_resource(pdev, IORESOURCE_MEM, i); + if (!res) + break; + + capacity += resource_size(res) / CXL_CAPACITY_MULTIPLIER; + + if (le64_to_cpu(id.partition_align)) + continue; + + if (res->desc == IORES_DESC_PERSISTENT_MEMORY) + id.persistent_capacity = cpu_to_le64( + resource_size(res) / CXL_CAPACITY_MULTIPLIER); + else + id.volatile_capacity = cpu_to_le64( + resource_size(res) / CXL_CAPACITY_MULTIPLIER); + } + + id.total_capacity = cpu_to_le64(capacity); + + memcpy(cmd->payload_out, &id, sizeof(id)); + + return 0; +} + +static int mock_get_lsa(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd) +{ + struct cxl_mbox_get_lsa *get_lsa = cmd->payload_in; + void *lsa = dev_get_drvdata(cxlm->dev); + u32 offset, length; + + if (sizeof(*get_lsa) > cmd->size_in) + return -EINVAL; + offset = le32_to_cpu(get_lsa->offset); + length = le32_to_cpu(get_lsa->length); + if (offset + length > LSA_SIZE) + return -EINVAL; + if (length > cmd->size_out) + return -EINVAL; + + memcpy(cmd->payload_out, lsa + offset, length); + return 0; +} + +static int mock_set_lsa(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd) +{ + struct cxl_mbox_set_lsa *set_lsa = cmd->payload_in; + void *lsa = dev_get_drvdata(cxlm->dev); + u32 offset, length; + + if (sizeof(*set_lsa) > cmd->size_in) + return -EINVAL; + offset = le32_to_cpu(set_lsa->offset); + length = cmd->size_in - sizeof(*set_lsa); + if (offset + length > LSA_SIZE) + return -EINVAL; + + memcpy(lsa + offset, &set_lsa->data[0], length); + return 0; +} + +static int cxl_mock_mbox_send(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd) +{ + struct device *dev = cxlm->dev; + int rc = -EIO; + + switch (cmd->opcode) { + case CXL_MBOX_OP_GET_SUPPORTED_LOGS: + rc = mock_gsl(cmd); + break; + case CXL_MBOX_OP_GET_LOG: + rc = mock_get_log(cxlm, cmd); + break; + case CXL_MBOX_OP_IDENTIFY: + rc = mock_id(cxlm, cmd); + break; + case CXL_MBOX_OP_GET_LSA: + rc = mock_get_lsa(cxlm, cmd); + break; + case CXL_MBOX_OP_SET_LSA: + rc = mock_set_lsa(cxlm, cmd); + break; + default: + break; + } + + dev_dbg(dev, "opcode: %#x sz_in: %zd sz_out: %zd rc: %d\n", cmd->opcode, + cmd->size_in, cmd->size_out, rc); + + return rc; +} + +static void label_area_release(void *lsa) +{ + vfree(lsa); +} + +static int cxl_mock_mem_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct cxl_memdev *cxlmd; + struct cxl_mem *cxlm; + void *lsa; + int rc; + + lsa = vmalloc(LSA_SIZE); + if (!lsa) + return -ENOMEM; + rc = devm_add_action_or_reset(dev, label_area_release, lsa); + if (rc) + return rc; + dev_set_drvdata(dev, lsa); + + cxlm = cxl_mem_create(dev); + if (IS_ERR(cxlm)) + return PTR_ERR(cxlm); + + cxlm->mbox_send = cxl_mock_mbox_send; + cxlm->payload_size = SZ_4K; + + rc = cxl_mem_enumerate_cmds(cxlm); + if (rc) + return rc; + + rc = cxl_mem_identify(cxlm); + if (rc) + return rc; + + rc = cxl_mem_create_range_info(cxlm); + if (rc) + return rc; + + cxlmd = devm_cxl_add_memdev(cxlm); + if (IS_ERR(cxlmd)) + return PTR_ERR(cxlmd); + + if (range_len(&cxlm->pmem_range) && IS_ENABLED(CONFIG_CXL_PMEM)) + rc = devm_cxl_add_nvdimm(dev, cxlmd); + + return 0; +} + +static const struct platform_device_id cxl_mock_mem_ids[] = { + { .name = "cxl_mem", }, + { }, +}; +MODULE_DEVICE_TABLE(platform, cxl_mock_mem_ids); + +static struct platform_driver cxl_mock_mem_driver = { + .probe = cxl_mock_mem_probe, + .id_table = cxl_mock_mem_ids, + .driver = { + .name = KBUILD_MODNAME, + }, +}; + +module_platform_driver(cxl_mock_mem_driver); +MODULE_LICENSE("GPL v2"); +MODULE_IMPORT_NS(CXL); From 48667f676189eccfe9b7ac3a31772d55d6da40e5 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 21 Sep 2021 12:22:16 -0700 Subject: [PATCH 059/587] cxl/core: Split decoder setup into alloc + add The kbuild robot reports: drivers/cxl/core/bus.c:516:1: warning: stack frame size (1032) exceeds limit (1024) in function 'devm_cxl_add_decoder' It is also the case the devm_cxl_add_decoder() is unwieldy to use for all the different decoder types. Fix the stack usage by splitting the creation into alloc and add steps. This also allows for context specific construction before adding. With the split the caller is responsible for registering a devm callback to trigger device_unregister() for the decoder rather than it being implicit in the decoder registration. I.e. the routine that calls alloc is responsible for calling put_device() if the "add" operation fails. Reported-by: kernel test robot Reported-by: Nathan Chancellor Reported-by: Dan Carpenter Reviewed-by: Ben Widawsky Link: https://lore.kernel.org/r/163225205828.3038145.6831131648369404859.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/cxl/acpi.c | 82 ++++++++++++++++++------- drivers/cxl/core/bus.c | 133 +++++++++++++--------------------------- drivers/cxl/core/core.h | 5 -- drivers/cxl/core/pmem.c | 7 ++- drivers/cxl/cxl.h | 13 ++-- 5 files changed, 114 insertions(+), 126 deletions(-) diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c index d39cc797a64e..af1c6c1875ac 100644 --- a/drivers/cxl/acpi.c +++ b/drivers/cxl/acpi.c @@ -82,7 +82,6 @@ static void cxl_add_cfmws_decoders(struct device *dev, struct cxl_decoder *cxld; acpi_size len, cur = 0; void *cedt_subtable; - unsigned long flags; int rc; len = acpi_cedt->length - sizeof(*acpi_cedt); @@ -119,24 +118,36 @@ static void cxl_add_cfmws_decoders(struct device *dev, for (i = 0; i < CFMWS_INTERLEAVE_WAYS(cfmws); i++) target_map[i] = cfmws->interleave_targets[i]; - flags = cfmws_to_decoder_flags(cfmws->restrictions); - cxld = devm_cxl_add_decoder(dev, root_port, - CFMWS_INTERLEAVE_WAYS(cfmws), - cfmws->base_hpa, cfmws->window_size, - CFMWS_INTERLEAVE_WAYS(cfmws), - CFMWS_INTERLEAVE_GRANULARITY(cfmws), - CXL_DECODER_EXPANDER, - flags, target_map); + cxld = cxl_decoder_alloc(root_port, + CFMWS_INTERLEAVE_WAYS(cfmws)); + if (IS_ERR(cxld)) + goto next; - if (IS_ERR(cxld)) { + cxld->flags = cfmws_to_decoder_flags(cfmws->restrictions); + cxld->target_type = CXL_DECODER_EXPANDER; + cxld->range = (struct range) { + .start = cfmws->base_hpa, + .end = cfmws->base_hpa + cfmws->window_size - 1, + }; + cxld->interleave_ways = CFMWS_INTERLEAVE_WAYS(cfmws); + cxld->interleave_granularity = + CFMWS_INTERLEAVE_GRANULARITY(cfmws); + + rc = cxl_decoder_add(cxld, target_map); + if (rc) + put_device(&cxld->dev); + else + rc = cxl_decoder_autoremove(dev, cxld); + if (rc) { dev_err(dev, "Failed to add decoder for %#llx-%#llx\n", cfmws->base_hpa, cfmws->base_hpa + cfmws->window_size - 1); - } else { - dev_dbg(dev, "add: %s range %#llx-%#llx\n", - dev_name(&cxld->dev), cfmws->base_hpa, - cfmws->base_hpa + cfmws->window_size - 1); + goto next; } + dev_dbg(dev, "add: %s range %#llx-%#llx\n", + dev_name(&cxld->dev), cfmws->base_hpa, + cfmws->base_hpa + cfmws->window_size - 1); +next: cur += c->length; } } @@ -266,6 +277,7 @@ static int add_host_bridge_uport(struct device *match, void *arg) struct acpi_device *bridge = to_cxl_host_bridge(host, match); struct acpi_pci_root *pci_root; struct cxl_walk_context ctx; + int single_port_map[1], rc; struct cxl_decoder *cxld; struct cxl_dport *dport; struct cxl_port *port; @@ -301,22 +313,46 @@ static int add_host_bridge_uport(struct device *match, void *arg) return -ENODEV; if (ctx.error) return ctx.error; + if (ctx.count > 1) + return 0; /* TODO: Scan CHBCR for HDM Decoder resources */ /* - * In the single-port host-bridge case there are no HDM decoders - * in the CHBCR and a 1:1 passthrough decode is implied. + * Per the CXL specification (8.2.5.12 CXL HDM Decoder Capability + * Structure) single ported host-bridges need not publish a decoder + * capability when a passthrough decode can be assumed, i.e. all + * transactions that the uport sees are claimed and passed to the single + * dport. Disable the range until the first CXL region is enumerated / + * activated. */ - if (ctx.count == 1) { - cxld = devm_cxl_add_passthrough_decoder(host, port); - if (IS_ERR(cxld)) - return PTR_ERR(cxld); + cxld = cxl_decoder_alloc(port, 1); + if (IS_ERR(cxld)) + return PTR_ERR(cxld); + cxld->interleave_ways = 1; + cxld->interleave_granularity = PAGE_SIZE; + cxld->target_type = CXL_DECODER_EXPANDER; + cxld->range = (struct range) { + .start = 0, + .end = -1, + }; + + device_lock(&port->dev); + dport = list_first_entry(&port->dports, typeof(*dport), list); + device_unlock(&port->dev); + + single_port_map[0] = dport->port_id; + + rc = cxl_decoder_add(cxld, single_port_map); + if (rc) + put_device(&cxld->dev); + else + rc = cxl_decoder_autoremove(host, cxld); + + if (rc == 0) dev_dbg(host, "add: %s\n", dev_name(&cxld->dev)); - } - - return 0; + return rc; } static int add_host_bridge_dport(struct device *match, void *arg) diff --git a/drivers/cxl/core/bus.c b/drivers/cxl/core/bus.c index 6dfdeaf999f0..ebd061d03950 100644 --- a/drivers/cxl/core/bus.c +++ b/drivers/cxl/core/bus.c @@ -453,10 +453,8 @@ err: } EXPORT_SYMBOL_GPL(cxl_add_dport); -static int decoder_populate_targets(struct device *host, - struct cxl_decoder *cxld, - struct cxl_port *port, int *target_map, - int nr_targets) +static int decoder_populate_targets(struct cxl_decoder *cxld, + struct cxl_port *port, int *target_map) { int rc = 0, i; @@ -464,66 +462,48 @@ static int decoder_populate_targets(struct device *host, return 0; device_lock(&port->dev); - for (i = 0; i < nr_targets; i++) { + if (list_empty(&port->dports)) { + rc = -EINVAL; + goto out_unlock; + } + + for (i = 0; i < cxld->nr_targets; i++) { struct cxl_dport *dport = find_dport(port, target_map[i]); if (!dport) { rc = -ENXIO; - break; + goto out_unlock; } - dev_dbg(host, "%s: target: %d\n", dev_name(dport->dport), i); cxld->target[i] = dport; } + +out_unlock: device_unlock(&port->dev); return rc; } -static struct cxl_decoder * -cxl_decoder_alloc(struct device *host, struct cxl_port *port, int nr_targets, - resource_size_t base, resource_size_t len, - int interleave_ways, int interleave_granularity, - enum cxl_decoder_type type, unsigned long flags, - int *target_map) +struct cxl_decoder *cxl_decoder_alloc(struct cxl_port *port, int nr_targets) { - struct cxl_decoder *cxld; + struct cxl_decoder *cxld, cxld_const_init = { + .nr_targets = nr_targets, + }; struct device *dev; int rc = 0; - if (interleave_ways < 1) + if (nr_targets > CXL_DECODER_MAX_INTERLEAVE || nr_targets < 1) return ERR_PTR(-EINVAL); - device_lock(&port->dev); - if (list_empty(&port->dports)) - rc = -EINVAL; - device_unlock(&port->dev); - if (rc) - return ERR_PTR(rc); - cxld = kzalloc(struct_size(cxld, target, nr_targets), GFP_KERNEL); if (!cxld) return ERR_PTR(-ENOMEM); + memcpy(cxld, &cxld_const_init, sizeof(cxld_const_init)); rc = ida_alloc(&port->decoder_ida, GFP_KERNEL); if (rc < 0) goto err; - *cxld = (struct cxl_decoder) { - .id = rc, - .range = { - .start = base, - .end = base + len - 1, - }, - .flags = flags, - .interleave_ways = interleave_ways, - .interleave_granularity = interleave_granularity, - .target_type = type, - }; - - rc = decoder_populate_targets(host, cxld, port, target_map, nr_targets); - if (rc) - goto err; - + cxld->id = rc; dev = &cxld->dev; device_initialize(dev); device_set_pm_not_required(dev); @@ -541,72 +521,47 @@ err: kfree(cxld); return ERR_PTR(rc); } +EXPORT_SYMBOL_GPL(cxl_decoder_alloc); -struct cxl_decoder * -devm_cxl_add_decoder(struct device *host, struct cxl_port *port, int nr_targets, - resource_size_t base, resource_size_t len, - int interleave_ways, int interleave_granularity, - enum cxl_decoder_type type, unsigned long flags, - int *target_map) +int cxl_decoder_add(struct cxl_decoder *cxld, int *target_map) { - struct cxl_decoder *cxld; + struct cxl_port *port; struct device *dev; int rc; - if (nr_targets > CXL_DECODER_MAX_INTERLEAVE) - return ERR_PTR(-EINVAL); + if (WARN_ON_ONCE(!cxld)) + return -EINVAL; - cxld = cxl_decoder_alloc(host, port, nr_targets, base, len, - interleave_ways, interleave_granularity, type, - flags, target_map); - if (IS_ERR(cxld)) - return cxld; + if (WARN_ON_ONCE(IS_ERR(cxld))) + return PTR_ERR(cxld); + + if (cxld->interleave_ways < 1) + return -EINVAL; + + port = to_cxl_port(cxld->dev.parent); + rc = decoder_populate_targets(cxld, port, target_map); + if (rc) + return rc; dev = &cxld->dev; rc = dev_set_name(dev, "decoder%d.%d", port->id, cxld->id); if (rc) - goto err; + return rc; - rc = device_add(dev); - if (rc) - goto err; - - rc = devm_add_action_or_reset(host, unregister_cxl_dev, dev); - if (rc) - return ERR_PTR(rc); - return cxld; - -err: - put_device(dev); - return ERR_PTR(rc); + return device_add(dev); } -EXPORT_SYMBOL_GPL(devm_cxl_add_decoder); +EXPORT_SYMBOL_GPL(cxl_decoder_add); -/* - * Per the CXL specification (8.2.5.12 CXL HDM Decoder Capability Structure) - * single ported host-bridges need not publish a decoder capability when a - * passthrough decode can be assumed, i.e. all transactions that the uport sees - * are claimed and passed to the single dport. Default the range a 0-base - * 0-length until the first CXL region is activated. - */ -struct cxl_decoder *devm_cxl_add_passthrough_decoder(struct device *host, - struct cxl_port *port) +static void cxld_unregister(void *dev) { - struct cxl_dport *dport; - int target_map[1]; - - device_lock(&port->dev); - dport = list_first_entry_or_null(&port->dports, typeof(*dport), list); - device_unlock(&port->dev); - - if (!dport) - return ERR_PTR(-ENXIO); - - target_map[0] = dport->port_id; - return devm_cxl_add_decoder(host, port, 1, 0, 0, 1, PAGE_SIZE, - CXL_DECODER_EXPANDER, 0, target_map); + device_unregister(dev); } -EXPORT_SYMBOL_GPL(devm_cxl_add_passthrough_decoder); + +int cxl_decoder_autoremove(struct device *host, struct cxl_decoder *cxld) +{ + return devm_add_action_or_reset(host, cxld_unregister, &cxld->dev); +} +EXPORT_SYMBOL_GPL(cxl_decoder_autoremove); /** * __cxl_driver_register - register a driver for the cxl bus diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h index c85b7fbad02d..e0c9aacc4e9c 100644 --- a/drivers/cxl/core/core.h +++ b/drivers/cxl/core/core.h @@ -9,11 +9,6 @@ extern const struct device_type cxl_nvdimm_type; extern struct attribute_group cxl_base_attribute_group; -static inline void unregister_cxl_dev(void *dev) -{ - device_unregister(dev); -} - struct cxl_send_command; struct cxl_mem_query_commands; int cxl_query_cmd(struct cxl_memdev *cxlmd, diff --git a/drivers/cxl/core/pmem.c b/drivers/cxl/core/pmem.c index 74be5132df1c..5032f4c1c69d 100644 --- a/drivers/cxl/core/pmem.c +++ b/drivers/cxl/core/pmem.c @@ -222,6 +222,11 @@ static struct cxl_nvdimm *cxl_nvdimm_alloc(struct cxl_memdev *cxlmd) return cxl_nvd; } +static void cxl_nvd_unregister(void *dev) +{ + device_unregister(dev); +} + /** * devm_cxl_add_nvdimm() - add a bridge between a cxl_memdev and an nvdimm * @host: same host as @cxlmd @@ -251,7 +256,7 @@ int devm_cxl_add_nvdimm(struct device *host, struct cxl_memdev *cxlmd) dev_dbg(host, "%s: register %s\n", dev_name(dev->parent), dev_name(dev)); - return devm_add_action_or_reset(host, unregister_cxl_dev, dev); + return devm_add_action_or_reset(host, cxl_nvd_unregister, dev); err: put_device(dev); diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index 9af5745ba2c0..a6687e7fd598 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -195,6 +195,7 @@ enum cxl_decoder_type { * @interleave_granularity: data stride per dport * @target_type: accelerator vs expander (type2 vs type3) selector * @flags: memory type capabilities and locking + * @nr_targets: number of elements in @target * @target: active ordered target list in current decoder configuration */ struct cxl_decoder { @@ -205,6 +206,7 @@ struct cxl_decoder { int interleave_granularity; enum cxl_decoder_type target_type; unsigned long flags; + const int nr_targets; struct cxl_dport *target[]; }; @@ -286,15 +288,10 @@ int cxl_add_dport(struct cxl_port *port, struct device *dport, int port_id, struct cxl_decoder *to_cxl_decoder(struct device *dev); bool is_root_decoder(struct device *dev); -struct cxl_decoder * -devm_cxl_add_decoder(struct device *host, struct cxl_port *port, int nr_targets, - resource_size_t base, resource_size_t len, - int interleave_ways, int interleave_granularity, - enum cxl_decoder_type type, unsigned long flags, - int *target_map); +struct cxl_decoder *cxl_decoder_alloc(struct cxl_port *port, int nr_targets); +int cxl_decoder_add(struct cxl_decoder *cxld, int *target_map); +int cxl_decoder_autoremove(struct device *host, struct cxl_decoder *cxld); -struct cxl_decoder *devm_cxl_add_passthrough_decoder(struct device *host, - struct cxl_port *port); extern struct bus_type cxl_bus_type; struct cxl_driver { From fa9a7d2db6134c737e7d6da3b0902766d92f06be Mon Sep 17 00:00:00 2001 From: Ben Widawsky Date: Mon, 13 Sep 2021 09:33:22 -0700 Subject: [PATCH 060/587] Documentation/cxl: Add bus internal docs Kernel docs are already present in this file, but nothing is instructed to generate them. Address that. Acked-by: Jonathan Cameron Signed-off-by: Ben Widawsky Link: https://lore.kernel.org/r/20210913163324.1008564-2-ben.widawsky@intel.com Signed-off-by: Dan Williams --- Documentation/driver-api/cxl/memory-devices.rst | 3 +++ 1 file changed, 3 insertions(+) diff --git a/Documentation/driver-api/cxl/memory-devices.rst b/Documentation/driver-api/cxl/memory-devices.rst index 4624951b5c38..3b8f41395f6b 100644 --- a/Documentation/driver-api/cxl/memory-devices.rst +++ b/Documentation/driver-api/cxl/memory-devices.rst @@ -39,6 +39,9 @@ CXL Core .. kernel-doc:: drivers/cxl/core/bus.c :doc: cxl core +.. kernel-doc:: drivers/cxl/core/bus.c + :identifiers: + .. kernel-doc:: drivers/cxl/core/pmem.c :doc: cxl pmem From ed97afb53365cd03dde266c9644334a558fe5a16 Mon Sep 17 00:00:00 2001 From: Ben Widawsky Date: Mon, 13 Sep 2021 09:33:24 -0700 Subject: [PATCH 061/587] cxl/pci: Disambiguate cxl_pci further from cxl_mem Commit 21e9f76733a8 ("cxl: Rename mem to pci") introduced the cxl_pci driver which had formerly been named cxl_mem. At the time, the goal was to be as light touch as possible because there were other patches in flight. Since things have settled now, and a new cxl_mem driver will be introduced shortly, spend the LOC now to clean up the existing names. While here, fix the kernel docs to explain the situation better after the core rework that has already landed. Reviewed-by: Jonathan Cameron Signed-off-by: Ben Widawsky Link: https://lore.kernel.org/r/20210913163324.1008564-4-ben.widawsky@intel.com Signed-off-by: Dan Williams --- drivers/cxl/pci.c | 68 ++++++++++++++++++++++++----------------------- 1 file changed, 35 insertions(+), 33 deletions(-) diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 27f75b5a2ee2..64180f46c895 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -16,14 +16,16 @@ * * This implements the PCI exclusive functionality for a CXL device as it is * defined by the Compute Express Link specification. CXL devices may surface - * certain functionality even if it isn't CXL enabled. + * certain functionality even if it isn't CXL enabled. While this driver is + * focused around the PCI specific aspects of a CXL device, it binds to the + * specific CXL memory device class code, and therefore the implementation of + * cxl_pci is focused around CXL memory devices. * * The driver has several responsibilities, mainly: * - Create the memX device and register on the CXL bus. * - Enumerate device's register interface and map them. - * - Probe the device attributes to establish sysfs interface. - * - Provide an IOCTL interface to userspace to communicate with the device for - * things like firmware update. + * - Registers nvdimm bridge device with cxl_core. + * - Registers a CXL mailbox with cxl_core. */ #define cxl_doorbell_busy(cxlm) \ @@ -33,7 +35,7 @@ /* CXL 2.0 - 8.2.8.4 */ #define CXL_MAILBOX_TIMEOUT_MS (2 * HZ) -static int cxl_mem_wait_for_doorbell(struct cxl_mem *cxlm) +static int cxl_pci_mbox_wait_for_doorbell(struct cxl_mem *cxlm) { const unsigned long start = jiffies; unsigned long end = start; @@ -55,7 +57,7 @@ static int cxl_mem_wait_for_doorbell(struct cxl_mem *cxlm) return 0; } -static void cxl_mem_mbox_timeout(struct cxl_mem *cxlm, +static void cxl_pci_mbox_timeout(struct cxl_mem *cxlm, struct cxl_mbox_cmd *mbox_cmd) { struct device *dev = cxlm->dev; @@ -65,7 +67,7 @@ static void cxl_mem_mbox_timeout(struct cxl_mem *cxlm, } /** - * __cxl_mem_mbox_send_cmd() - Execute a mailbox command + * __cxl_pci_mbox_send_cmd() - Execute a mailbox command * @cxlm: The CXL memory device to communicate with. * @mbox_cmd: Command to send to the memory device. * @@ -86,7 +88,7 @@ static void cxl_mem_mbox_timeout(struct cxl_mem *cxlm, * not need to coordinate with each other. The driver only uses the primary * mailbox. */ -static int __cxl_mem_mbox_send_cmd(struct cxl_mem *cxlm, +static int __cxl_pci_mbox_send_cmd(struct cxl_mem *cxlm, struct cxl_mbox_cmd *mbox_cmd) { void __iomem *payload = cxlm->regs.mbox + CXLDEV_MBOX_PAYLOAD_OFFSET; @@ -140,9 +142,9 @@ static int __cxl_mem_mbox_send_cmd(struct cxl_mem *cxlm, cxlm->regs.mbox + CXLDEV_MBOX_CTRL_OFFSET); /* #5 */ - rc = cxl_mem_wait_for_doorbell(cxlm); + rc = cxl_pci_mbox_wait_for_doorbell(cxlm); if (rc == -ETIMEDOUT) { - cxl_mem_mbox_timeout(cxlm, mbox_cmd); + cxl_pci_mbox_timeout(cxlm, mbox_cmd); return rc; } @@ -181,13 +183,13 @@ static int __cxl_mem_mbox_send_cmd(struct cxl_mem *cxlm, } /** - * cxl_mem_mbox_get() - Acquire exclusive access to the mailbox. + * cxl_pci_mbox_get() - Acquire exclusive access to the mailbox. * @cxlm: The memory device to gain access to. * * Context: Any context. Takes the mbox_mutex. * Return: 0 if exclusive access was acquired. */ -static int cxl_mem_mbox_get(struct cxl_mem *cxlm) +static int cxl_pci_mbox_get(struct cxl_mem *cxlm) { struct device *dev = cxlm->dev; u64 md_status; @@ -212,7 +214,7 @@ static int cxl_mem_mbox_get(struct cxl_mem *cxlm) * Mailbox Interface Ready bit. Therefore, waiting for the doorbell * to be ready is sufficient. */ - rc = cxl_mem_wait_for_doorbell(cxlm); + rc = cxl_pci_mbox_wait_for_doorbell(cxlm); if (rc) { dev_warn(dev, "Mailbox interface not ready\n"); goto out; @@ -252,12 +254,12 @@ out: } /** - * cxl_mem_mbox_put() - Release exclusive access to the mailbox. + * cxl_pci_mbox_put() - Release exclusive access to the mailbox. * @cxlm: The CXL memory device to communicate with. * * Context: Any context. Expects mbox_mutex to be held. */ -static void cxl_mem_mbox_put(struct cxl_mem *cxlm) +static void cxl_pci_mbox_put(struct cxl_mem *cxlm) { mutex_unlock(&cxlm->mbox_mutex); } @@ -266,17 +268,17 @@ static int cxl_pci_mbox_send(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd) { int rc; - rc = cxl_mem_mbox_get(cxlm); + rc = cxl_pci_mbox_get(cxlm); if (rc) return rc; - rc = __cxl_mem_mbox_send_cmd(cxlm, cmd); - cxl_mem_mbox_put(cxlm); + rc = __cxl_pci_mbox_send_cmd(cxlm, cmd); + cxl_pci_mbox_put(cxlm); return rc; } -static int cxl_mem_setup_mailbox(struct cxl_mem *cxlm) +static int cxl_pci_setup_mailbox(struct cxl_mem *cxlm) { const int cap = readl(cxlm->regs.mbox + CXLDEV_MBOX_CAPS_OFFSET); @@ -304,7 +306,7 @@ static int cxl_mem_setup_mailbox(struct cxl_mem *cxlm) return 0; } -static void __iomem *cxl_mem_map_regblock(struct cxl_mem *cxlm, +static void __iomem *cxl_pci_map_regblock(struct cxl_mem *cxlm, u8 bar, u64 offset) { void __iomem *addr; @@ -330,12 +332,12 @@ static void __iomem *cxl_mem_map_regblock(struct cxl_mem *cxlm, return addr; } -static void cxl_mem_unmap_regblock(struct cxl_mem *cxlm, void __iomem *base) +static void cxl_pci_unmap_regblock(struct cxl_mem *cxlm, void __iomem *base) { pci_iounmap(to_pci_dev(cxlm->dev), base); } -static int cxl_mem_dvsec(struct pci_dev *pdev, int dvsec) +static int cxl_pci_dvsec(struct pci_dev *pdev, int dvsec) { int pos; @@ -427,7 +429,7 @@ static void cxl_decode_register_block(u32 reg_lo, u32 reg_hi, } /** - * cxl_mem_setup_regs() - Setup necessary MMIO. + * cxl_pci_setup_regs() - Setup necessary MMIO. * @cxlm: The CXL memory device to communicate with. * * Return: 0 if all necessary registers mapped. @@ -436,7 +438,7 @@ static void cxl_decode_register_block(u32 reg_lo, u32 reg_hi, * regions. The purpose of this function is to enumerate and map those * registers. */ -static int cxl_mem_setup_regs(struct cxl_mem *cxlm) +static int cxl_pci_setup_regs(struct cxl_mem *cxlm) { void __iomem *base; u32 regloc_size, regblocks; @@ -445,7 +447,7 @@ static int cxl_mem_setup_regs(struct cxl_mem *cxlm) struct pci_dev *pdev = to_pci_dev(dev); struct cxl_register_map *map, maps[CXL_REGLOC_RBI_TYPES]; - regloc = cxl_mem_dvsec(pdev, PCI_DVSEC_ID_CXL_REGLOC_DVSEC_ID); + regloc = cxl_pci_dvsec(pdev, PCI_DVSEC_ID_CXL_REGLOC_DVSEC_ID); if (!regloc) { dev_err(dev, "register location dvsec not found\n"); return -ENXIO; @@ -480,7 +482,7 @@ static int cxl_mem_setup_regs(struct cxl_mem *cxlm) if (reg_type > CXL_REGLOC_RBI_MEMDEV) continue; - base = cxl_mem_map_regblock(cxlm, bar, offset); + base = cxl_pci_map_regblock(cxlm, bar, offset); if (!base) return -ENOMEM; @@ -492,7 +494,7 @@ static int cxl_mem_setup_regs(struct cxl_mem *cxlm) ret = cxl_probe_regs(cxlm, base + offset, map); /* Always unmap the regblock regardless of probe success */ - cxl_mem_unmap_regblock(cxlm, base); + cxl_pci_unmap_regblock(cxlm, base); if (ret) return ret; @@ -511,7 +513,7 @@ static int cxl_mem_setup_regs(struct cxl_mem *cxlm) return ret; } -static int cxl_mem_probe(struct pci_dev *pdev, const struct pci_device_id *id) +static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct cxl_memdev *cxlmd; struct cxl_mem *cxlm; @@ -532,11 +534,11 @@ static int cxl_mem_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (IS_ERR(cxlm)) return PTR_ERR(cxlm); - rc = cxl_mem_setup_regs(cxlm); + rc = cxl_pci_setup_regs(cxlm); if (rc) return rc; - rc = cxl_mem_setup_mailbox(cxlm); + rc = cxl_pci_setup_mailbox(cxlm); if (rc) return rc; @@ -569,15 +571,15 @@ static const struct pci_device_id cxl_mem_pci_tbl[] = { }; MODULE_DEVICE_TABLE(pci, cxl_mem_pci_tbl); -static struct pci_driver cxl_mem_driver = { +static struct pci_driver cxl_pci_driver = { .name = KBUILD_MODNAME, .id_table = cxl_mem_pci_tbl, - .probe = cxl_mem_probe, + .probe = cxl_pci_probe, .driver = { .probe_type = PROBE_PREFER_ASYNCHRONOUS, }, }; MODULE_LICENSE("GPL v2"); -module_pci_driver(cxl_mem_driver); +module_pci_driver(cxl_pci_driver); MODULE_IMPORT_NS(CXL); From cb7bfb1da6f609bf954d5f164733ff35b1cb4d4e Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 27 Jan 2021 10:46:29 -0800 Subject: [PATCH 062/587] perf parse-events: Remove unnecessary #includes Minor cleanup motivated by trying to separately fuzz test parse-events. Signed-off-by: Ian Rogers Acked-by: Namhyung Kim Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jin Yao Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lore.kernel.org/lkml/20210127184629.516169-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 2 -- tools/perf/util/parse-events.l | 1 - 2 files changed, 3 deletions(-) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 5d1346aa0627..85d3d77d3c6a 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -19,8 +19,6 @@ #include #include "string2.h" #include "strlist.h" -#include "symbol.h" -#include "header.h" #include "bpf-loader.h" #include "debug.h" #include diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 923849024b15..47da7a0c5df4 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -12,7 +12,6 @@ #include #include #include -#include "../perf.h" #include "parse-events.h" #include "parse-events-bison.h" #include "evsel.h" From 89b4db61c76197b899f9dc3dc06ea7c3a60729b8 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 29 Jul 2021 23:07:06 +0900 Subject: [PATCH 063/587] nios2: move the install rule to arch/nios2/Makefile Currently, the install target in arch/nios2/Makefile descends into arch/nios2/boot/Makefile to invoke the shell script, but it is no good reason to do so. arch/nios2/Makefile can run the shell script directly. Signed-off-by: Masahiro Yamada --- arch/nios2/Makefile | 3 ++- arch/nios2/boot/Makefile | 3 --- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/arch/nios2/Makefile b/arch/nios2/Makefile index 52c03e60b114..72e8ff065cf7 100644 --- a/arch/nios2/Makefile +++ b/arch/nios2/Makefile @@ -60,7 +60,8 @@ $(BOOT_TARGETS): vmlinux $(Q)$(MAKE) $(build)=$(nios2-boot) $(nios2-boot)/$@ install: - $(Q)$(MAKE) $(build)=$(nios2-boot) BOOTIMAGE=$(KBUILD_IMAGE) install + sh $(srctree)/$(nios2-boot)/install.sh $(KERNELRELEASE) \ + $(KBUILD_IMAGE) System.map "$(INSTALL_PATH)" define archhelp echo '* vmImage - Kernel-only image for U-Boot ($(KBUILD_IMAGE))' diff --git a/arch/nios2/boot/Makefile b/arch/nios2/boot/Makefile index 37dfc7e584bc..8c3ad76602f3 100644 --- a/arch/nios2/boot/Makefile +++ b/arch/nios2/boot/Makefile @@ -30,6 +30,3 @@ $(obj)/zImage: $(obj)/compressed/vmlinux FORCE $(obj)/compressed/vmlinux: $(obj)/vmlinux.gz FORCE $(Q)$(MAKE) $(build)=$(obj)/compressed $@ - -install: - sh $(srctree)/$(src)/install.sh $(KERNELRELEASE) $(BOOTIMAGE) System.map "$(INSTALL_PATH)" From 04e85bbf71c9072dcf0ad9a7150495d72461105c Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 2 Aug 2021 23:43:15 +0300 Subject: [PATCH 064/587] isystem: delete global -isystem compile option Further isolate kernel from userspace, prevent accidental inclusion of undesireable headers, mainly float.h and stdatomic.h. nds32 keeps -isystem globally due to intrinsics used in entrenched header. -isystem is selectively reenabled for some files, again, for intrinsics. Compile tested on: hexagon-defconfig hexagon-allmodconfig alpha-allmodconfig alpha-allnoconfig alpha-defconfig arm64-allmodconfig arm64-allnoconfig arm64-defconfig arm-am200epdkit arm-aspeed_g4 arm-aspeed_g5 arm-assabet arm-at91_dt arm-axm55xx arm-badge4 arm-bcm2835 arm-cerfcube arm-clps711x arm-cm_x300 arm-cns3420vb arm-colibri_pxa270 arm-colibri_pxa300 arm-collie arm-corgi arm-davinci_all arm-dove arm-ep93xx arm-eseries_pxa arm-exynos arm-ezx arm-footbridge arm-gemini arm-h3600 arm-h5000 arm-hackkit arm-hisi arm-imote2 arm-imx_v4_v5 arm-imx_v6_v7 arm-integrator arm-iop32x arm-ixp4xx arm-jornada720 arm-keystone arm-lart arm-lpc18xx arm-lpc32xx arm-lpd270 arm-lubbock arm-magician arm-mainstone arm-milbeaut_m10v arm-mini2440 arm-mmp2 arm-moxart arm-mps2 arm-multi_v4t arm-multi_v5 arm-multi_v7 arm-mv78xx0 arm-mvebu_v5 arm-mvebu_v7 arm-mxs arm-neponset arm-netwinder arm-nhk8815 arm-omap1 arm-omap2plus arm-orion5x arm-oxnas_v6 arm-palmz72 arm-pcm027 arm-pleb arm-pxa arm-pxa168 arm-pxa255-idp arm-pxa3xx arm-pxa910 arm-qcom arm-realview arm-rpc arm-s3c2410 arm-s3c6400 arm-s5pv210 arm-sama5 arm-shannon arm-shmobile arm-simpad arm-socfpga arm-spear13xx arm-spear3xx arm-spear6xx arm-spitz arm-stm32 arm-sunxi arm-tct_hammer arm-tegra arm-trizeps4 arm-u8500 arm-versatile arm-vexpress arm-vf610m4 arm-viper arm-vt8500_v6_v7 arm-xcep arm-zeus csky-allmodconfig csky-allnoconfig csky-defconfig h8300-edosk2674 h8300-h8300h-sim h8300-h8s-sim i386-allmodconfig i386-allnoconfig i386-defconfig ia64-allmodconfig ia64-allnoconfig ia64-bigsur ia64-generic ia64-gensparse ia64-tiger ia64-zx1 m68k-amcore m68k-amiga m68k-apollo m68k-atari m68k-bvme6000 m68k-hp300 m68k-m5208evb m68k-m5249evb m68k-m5272c3 m68k-m5275evb m68k-m5307c3 m68k-m5407c3 m68k-m5475evb m68k-mac m68k-multi m68k-mvme147 m68k-mvme16x m68k-q40 m68k-stmark2 m68k-sun3 m68k-sun3x microblaze-allmodconfig microblaze-allnoconfig microblaze-mmu mips-ar7 mips-ath25 mips-ath79 mips-bcm47xx mips-bcm63xx mips-bigsur mips-bmips_be mips-bmips_stb mips-capcella mips-cavium_octeon mips-ci20 mips-cobalt mips-cu1000-neo mips-cu1830-neo mips-db1xxx mips-decstation mips-decstation_64 mips-decstation_r4k mips-e55 mips-fuloong2e mips-gcw0 mips-generic mips-gpr mips-ip22 mips-ip27 mips-ip28 mips-ip32 mips-jazz mips-jmr3927 mips-lemote2f mips-loongson1b mips-loongson1c mips-loongson2k mips-loongson3 mips-malta mips-maltaaprp mips-malta_kvm mips-malta_qemu_32r6 mips-maltasmvp mips-maltasmvp_eva mips-maltaup mips-maltaup_xpa mips-mpc30x mips-mtx1 mips-nlm_xlp mips-nlm_xlr mips-omega2p mips-pic32mzda mips-pistachio mips-qi_lb60 mips-rb532 mips-rbtx49xx mips-rm200 mips-rs90 mips-rt305x mips-sb1250_swarm mips-tb0219 mips-tb0226 mips-tb0287 mips-vocore2 mips-workpad mips-xway nds32-allmodconfig nds32-allnoconfig nds32-defconfig nios2-10m50 nios2-3c120 nios2-allmodconfig nios2-allnoconfig openrisc-allmodconfig openrisc-allnoconfig openrisc-or1klitex openrisc-or1ksim openrisc-simple_smp parisc-allnoconfig parisc-generic-32bit parisc-generic-64bit powerpc-acadia powerpc-adder875 powerpc-akebono powerpc-amigaone powerpc-arches powerpc-asp8347 powerpc-bamboo powerpc-bluestone powerpc-canyonlands powerpc-cell powerpc-chrp32 powerpc-cm5200 powerpc-currituck powerpc-ebony powerpc-eiger powerpc-ep8248e powerpc-ep88xc powerpc-fsp2 powerpc-g5 powerpc-gamecube powerpc-ge_imp3a powerpc-holly powerpc-icon powerpc-iss476-smp powerpc-katmai powerpc-kilauea powerpc-klondike powerpc-kmeter1 powerpc-ksi8560 powerpc-linkstation powerpc-lite5200b powerpc-makalu powerpc-maple powerpc-mgcoge powerpc-microwatt powerpc-motionpro powerpc-mpc512x powerpc-mpc5200 powerpc-mpc7448_hpc2 powerpc-mpc8272_ads powerpc-mpc8313_rdb powerpc-mpc8315_rdb powerpc-mpc832x_mds powerpc-mpc832x_rdb powerpc-mpc834x_itx powerpc-mpc834x_itxgp powerpc-mpc834x_mds powerpc-mpc836x_mds powerpc-mpc836x_rdk powerpc-mpc837x_mds powerpc-mpc837x_rdb powerpc-mpc83xx powerpc-mpc8540_ads powerpc-mpc8560_ads powerpc-mpc85xx_cds powerpc-mpc866_ads powerpc-mpc885_ads powerpc-mvme5100 powerpc-obs600 powerpc-pasemi powerpc-pcm030 powerpc-pmac32 powerpc-powernv powerpc-ppa8548 powerpc-ppc40x powerpc-ppc44x powerpc-ppc64 powerpc-ppc64e powerpc-ppc6xx powerpc-pq2fads powerpc-ps3 powerpc-pseries powerpc-rainier powerpc-redwood powerpc-sam440ep powerpc-sbc8548 powerpc-sequoia powerpc-skiroot powerpc-socrates powerpc-storcenter powerpc-stx_gp3 powerpc-taishan powerpc-tqm5200 powerpc-tqm8540 powerpc-tqm8541 powerpc-tqm8548 powerpc-tqm8555 powerpc-tqm8560 powerpc-tqm8xx powerpc-walnut powerpc-warp powerpc-wii powerpc-xes_mpc85xx riscv-allmodconfig riscv-allnoconfig riscv-nommu_k210 riscv-nommu_k210_sdcard riscv-nommu_virt riscv-rv32 s390-allmodconfig s390-allnoconfig s390-debug s390-zfcpdump sh-ap325rxa sh-apsh4a3a sh-apsh4ad0a sh-dreamcast sh-ecovec24 sh-ecovec24-romimage sh-edosk7705 sh-edosk7760 sh-espt sh-hp6xx sh-j2 sh-kfr2r09 sh-kfr2r09-romimage sh-landisk sh-lboxre2 sh-magicpanelr2 sh-microdev sh-migor sh-polaris sh-r7780mp sh-r7785rp sh-rsk7201 sh-rsk7203 sh-rsk7264 sh-rsk7269 sh-rts7751r2d1 sh-rts7751r2dplus sh-sdk7780 sh-sdk7786 sh-se7206 sh-se7343 sh-se7619 sh-se7705 sh-se7712 sh-se7721 sh-se7722 sh-se7724 sh-se7750 sh-se7751 sh-se7780 sh-secureedge5410 sh-sh03 sh-sh2007 sh-sh7710voipgw sh-sh7724_generic sh-sh7757lcr sh-sh7763rdp sh-sh7770_generic sh-sh7785lcr sh-sh7785lcr_32bit sh-shmin sh-shx3 sh-titan sh-ul2 sh-urquell sparc-allmodconfig sparc-allnoconfig sparc-sparc32 sparc-sparc64 um-i386-allmodconfig um-i386-allnoconfig um-i386-defconfig um-x86_64-allmodconfig um-x86_64-allnoconfig x86_64-allmodconfig x86_64-allnoconfig x86_64-defconfig xtensa-allmodconfig xtensa-allnoconfig xtensa-audio_kc705 xtensa-cadence_csp xtensa-common xtensa-generic_kc705 xtensa-iss xtensa-nommu_kc705 xtensa-smp_lx200 xtensa-virt xtensa-xip_kc705 Tested-by: Nathan Chancellor # build (hexagon) Signed-off-by: Alexey Dobriyan Acked-by: Ard Biesheuvel Signed-off-by: Masahiro Yamada --- Makefile | 2 +- arch/arm64/lib/Makefile | 2 ++ arch/nds32/Makefile | 2 ++ arch/powerpc/lib/Makefile | 2 ++ crypto/Makefile | 2 ++ lib/raid6/Makefile | 4 ++++ 6 files changed, 13 insertions(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 5e7c1d854441..ee5896261d2f 100644 --- a/Makefile +++ b/Makefile @@ -981,7 +981,7 @@ KBUILD_CFLAGS += -falign-functions=64 endif # arch Makefile may override CC so keep this after arch Makefile is included -NOSTDINC_FLAGS += -nostdinc -isystem $(shell $(CC) -print-file-name=include) +NOSTDINC_FLAGS += -nostdinc # warn about C99 declaration after statement KBUILD_CFLAGS += -Wdeclaration-after-statement diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile index 0941180a86d3..29490be2546b 100644 --- a/arch/arm64/lib/Makefile +++ b/arch/arm64/lib/Makefile @@ -9,6 +9,8 @@ ifeq ($(CONFIG_KERNEL_MODE_NEON), y) obj-$(CONFIG_XOR_BLOCKS) += xor-neon.o CFLAGS_REMOVE_xor-neon.o += -mgeneral-regs-only CFLAGS_xor-neon.o += -ffreestanding +# Enable +CFLAGS_xor-neon.o += -isystem $(shell $(CC) -print-file-name=include) endif lib-$(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) += uaccess_flushcache.o diff --git a/arch/nds32/Makefile b/arch/nds32/Makefile index ccdca7142020..c17fc3a755c3 100644 --- a/arch/nds32/Makefile +++ b/arch/nds32/Makefile @@ -9,6 +9,8 @@ endif # Avoid generating FPU instructions arch-y += -mno-ext-fpu-sp -mno-ext-fpu-dp -mfloat-abi=soft +# Enable +KBUILD_CFLAGS += -isystem $(shell $(CC) -print-file-name=include) KBUILD_CFLAGS += $(call cc-option, -mno-sched-prolog-epilog) KBUILD_CFLAGS += -mcmodel=large diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 99a7c9132422..9e5d0f413b71 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -65,5 +65,7 @@ obj-$(CONFIG_FTR_FIXUP_SELFTEST) += feature-fixups-test.o obj-$(CONFIG_ALTIVEC) += xor_vmx.o xor_vmx_glue.o CFLAGS_xor_vmx.o += -maltivec $(call cc-option,-mabi=altivec) +# Enable +CFLAGS_xor_vmx.o += -isystem $(shell $(CC) -print-file-name=include) obj-$(CONFIG_PPC64) += $(obj64-y) diff --git a/crypto/Makefile b/crypto/Makefile index c633f15a0481..429c4d57458c 100644 --- a/crypto/Makefile +++ b/crypto/Makefile @@ -119,6 +119,8 @@ CFLAGS_aegis128-neon-inner.o += $(aegis128-cflags-y) CFLAGS_REMOVE_aegis128-neon-inner.o += -mgeneral-regs-only aegis128-$(CONFIG_CRYPTO_AEGIS128_SIMD) += aegis128-neon.o aegis128-neon-inner.o endif +# Enable +CFLAGS_aegis128-neon-inner.o += -isystem $(shell $(CC) -print-file-name=include) obj-$(CONFIG_CRYPTO_PCRYPT) += pcrypt.o obj-$(CONFIG_CRYPTO_CRYPTD) += cryptd.o diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile index c770570bfe4f..45e17619422b 100644 --- a/lib/raid6/Makefile +++ b/lib/raid6/Makefile @@ -14,6 +14,8 @@ hostprogs += mktables ifeq ($(CONFIG_ALTIVEC),y) altivec_flags := -maltivec $(call cc-option,-mabi=altivec) +# Enable +altivec_flags += -isystem $(shell $(CC) -print-file-name=include) ifdef CONFIG_CC_IS_CLANG # clang ppc port does not yet support -maltivec when -msoft-float is @@ -34,6 +36,8 @@ endif # ARM/NEON intrinsics in a non C99-compliant environment (such as the kernel) ifeq ($(CONFIG_KERNEL_MODE_NEON),y) NEON_FLAGS := -ffreestanding +# Enable +NEON_FLAGS += -isystem $(shell $(CC) -print-file-name=include) ifeq ($(ARCH),arm) NEON_FLAGS += -march=armv7-a -mfloat-abi=softfp -mfpu=neon endif From 8f0c32c788fffa8e88f995372415864039347c8a Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 31 Aug 2021 16:39:52 +0900 Subject: [PATCH 065/587] kbuild: move objtool_args back to scripts/Makefile.build Commit b1a1a1a09b46 ("kbuild: lto: postpone objtool") moved objtool_args to Makefile.lib, so the arguments can be used in Makefile.modfinal as well as Makefile.build. With commit 850ded46c642 ("kbuild: Fix TRIM_UNUSED_KSYMS with LTO_CLANG"), module LTO linking came back to scripts/Makefile.build again. So, there is no more reason to keep objtool_args in a separate file. Get it back to the original place, close to the objtool command. Remove the stale comment too. Signed-off-by: Masahiro Yamada Reviewed-by: Kees Cook Acked-by: Josh Poimboeuf --- scripts/Makefile.build | 10 ++++++++++ scripts/Makefile.lib | 11 ----------- 2 files changed, 10 insertions(+), 11 deletions(-) diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 3efc984d4c69..17508c0e4358 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -224,6 +224,16 @@ cmd_record_mcount = $(if $(findstring $(strip $(CC_FLAGS_FTRACE)),$(_c_flags)), endif # CONFIG_FTRACE_MCOUNT_USE_RECORDMCOUNT ifdef CONFIG_STACK_VALIDATION + +objtool_args = \ + $(if $(CONFIG_UNWINDER_ORC),orc generate,check) \ + $(if $(part-of-module), --module) \ + $(if $(CONFIG_FRAME_POINTER),, --no-fp) \ + $(if $(CONFIG_GCOV_KERNEL)$(CONFIG_LTO_CLANG), --no-unreachable)\ + $(if $(CONFIG_RETPOLINE), --retpoline) \ + $(if $(CONFIG_X86_SMAP), --uaccess) \ + $(if $(CONFIG_FTRACE_MCOUNT_USE_OBJTOOL), --mcount) + ifndef CONFIG_LTO_CLANG __objtool_obj := $(objtree)/tools/objtool/objtool diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 54582673fc1a..0a8a4689c3eb 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -232,17 +232,6 @@ ifeq ($(CONFIG_LTO_CLANG),y) mod-prelink-ext := .lto endif -# Objtool arguments are also needed for modfinal with LTO, so we define -# then here to avoid duplication. -objtool_args = \ - $(if $(CONFIG_UNWINDER_ORC),orc generate,check) \ - $(if $(part-of-module), --module) \ - $(if $(CONFIG_FRAME_POINTER),, --no-fp) \ - $(if $(CONFIG_GCOV_KERNEL)$(CONFIG_LTO_CLANG), --no-unreachable)\ - $(if $(CONFIG_RETPOLINE), --retpoline) \ - $(if $(CONFIG_X86_SMAP), --uaccess) \ - $(if $(CONFIG_FTRACE_MCOUNT_USE_OBJTOOL), --mcount) - # Useful for describing the dependency of composite objects # Usage: # $(call multi_depend, multi_used_targets, suffix_to_remove, suffix_to_add) From 5c4859e77aa11f9a8d9533962389893d199df70e Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 31 Aug 2021 16:39:53 +0900 Subject: [PATCH 066/587] kbuild: rename __objtool_obj and reuse it for cmd_cc_lto_link_modules Rename __objtool_obj to objtool, and move it out of the 'ifndef CONFIG_LTO_CLANG' conditional, so it can be used for cmd_cc_lto_link_modules as well. Signed-off-by: Masahiro Yamada Reviewed-by: Nick Desaulniers Reviewed-by: Kees Cook Acked-by: Josh Poimboeuf --- scripts/Makefile.build | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 17508c0e4358..e78096cd396b 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -225,6 +225,8 @@ endif # CONFIG_FTRACE_MCOUNT_USE_RECORDMCOUNT ifdef CONFIG_STACK_VALIDATION +objtool := $(objtree)/tools/objtool/objtool + objtool_args = \ $(if $(CONFIG_UNWINDER_ORC),orc generate,check) \ $(if $(part-of-module), --module) \ @@ -236,17 +238,15 @@ objtool_args = \ ifndef CONFIG_LTO_CLANG -__objtool_obj := $(objtree)/tools/objtool/objtool - # 'OBJECT_FILES_NON_STANDARD := y': skip objtool checking for a directory # 'OBJECT_FILES_NON_STANDARD_foo.o := 'y': skip objtool checking for a file # 'OBJECT_FILES_NON_STANDARD_foo.o := 'n': override directory skip for a file cmd_objtool = $(if $(patsubst y%,, \ $(OBJECT_FILES_NON_STANDARD_$(basetarget).o)$(OBJECT_FILES_NON_STANDARD)n), \ - $(__objtool_obj) $(objtool_args) $@) + $(objtool) $(objtool_args) $@) objtool_obj = $(if $(patsubst y%,, \ $(OBJECT_FILES_NON_STANDARD_$(basetarget).o)$(OBJECT_FILES_NON_STANDARD)n), \ - $(__objtool_obj)) + $(objtool)) endif # CONFIG_LTO_CLANG endif # CONFIG_STACK_VALIDATION @@ -300,8 +300,7 @@ cmd_cc_lto_link_modules = \ ifdef CONFIG_STACK_VALIDATION # objtool was skipped for LLVM bitcode, run it now that we have compiled # modules into native code -cmd_cc_lto_link_modules += ; \ - $(objtree)/tools/objtool/objtool $(objtool_args) --module $@ +cmd_cc_lto_link_modules += ; $(objtool) $(objtool_args) --module $@ endif $(obj)/%.lto.o: $(obj)/%.o FORCE From 92594d569b6d377168fa74c6bb27c5696af02a9d Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 31 Aug 2021 16:39:54 +0900 Subject: [PATCH 067/587] kbuild: store the objtool command in *.cmd files objtool_dep includes include/config/{ORC_UNWINDER,STACK_VALIDATION} so that all the objects are rebuilt when CONFIG_ORC_UNWINDER or CONFIG_STACK_VALIDATION is toggled. BTW, the correct option name is not CONFIG_ORC_UNWINDER, but CONFIG_UNWINDER_ORC. Commit 11af847446ed ("x86/unwind: Rename unwinder config options to 'CONFIG_UNWINDER_*'") missed to adjust this part. So, this dependency has been broken for a long time. As you can see in 'objtool_args', there are more CONFIG options that affect the objtool command line. Adding more and more include/config/* is ugly and unmaintainable. Another issue is that non-standard objects are needlessly rebuilt. Objects specified as OBJECT_FILES_NON_STANDARD is not processed by objtool, but they are rebuilt anyway when CONFIG_STACK_VALIDATION is toggled. This is not a big deal, but better to fix. A cleaner and more precise fix is to include the objtool command in *.cmd files so any command change is naturally detected by if_change. Signed-off-by: Masahiro Yamada Reviewed-by: Nick Desaulniers Reviewed-by: Kees Cook Acked-by: Josh Poimboeuf --- scripts/Makefile.build | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) diff --git a/scripts/Makefile.build b/scripts/Makefile.build index e78096cd396b..021ae0146913 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -155,7 +155,7 @@ $(obj)/%.ll: $(src)/%.c FORCE # (See cmd_cc_o_c + relevant part of rule_cc_o_c) quiet_cmd_cc_o_c = CC $(quiet_modtag) $@ - cmd_cc_o_c = $(CC) $(c_flags) -c -o $@ $< + cmd_cc_o_c = $(CC) $(c_flags) -c -o $@ $< $(cmd_objtool) ifdef CONFIG_MODVERSIONS # When module versioning is enabled the following steps are executed: @@ -243,7 +243,7 @@ ifndef CONFIG_LTO_CLANG # 'OBJECT_FILES_NON_STANDARD_foo.o := 'n': override directory skip for a file cmd_objtool = $(if $(patsubst y%,, \ $(OBJECT_FILES_NON_STANDARD_$(basetarget).o)$(OBJECT_FILES_NON_STANDARD)n), \ - $(objtool) $(objtool_args) $@) + ; $(objtool) $(objtool_args) $@) objtool_obj = $(if $(patsubst y%,, \ $(OBJECT_FILES_NON_STANDARD_$(basetarget).o)$(OBJECT_FILES_NON_STANDARD)n), \ $(objtool)) @@ -251,10 +251,8 @@ objtool_obj = $(if $(patsubst y%,, \ endif # CONFIG_LTO_CLANG endif # CONFIG_STACK_VALIDATION -# Rebuild all objects when objtool changes, or is enabled/disabled. -objtool_dep = $(objtool_obj) \ - $(wildcard include/config/ORC_UNWINDER \ - include/config/STACK_VALIDATION) +# Rebuild all objects when objtool changes +objtool_dep = $(objtool_obj) ifdef CONFIG_TRIM_UNUSED_KSYMS cmd_gen_ksymdeps = \ @@ -269,7 +267,6 @@ define rule_cc_o_c $(call cmd,gen_ksymdeps) $(call cmd,checksrc) $(call cmd,checkdoc) - $(call cmd,objtool) $(call cmd,modversions_c) $(call cmd,record_mcount) endef @@ -277,7 +274,6 @@ endef define rule_as_o_S $(call cmd_and_fixdep,as_o_S) $(call cmd,gen_ksymdeps) - $(call cmd,objtool) $(call cmd,modversions_S) endef @@ -365,7 +361,7 @@ $(obj)/%.s: $(src)/%.S FORCE $(call if_changed_dep,cpp_s_S) quiet_cmd_as_o_S = AS $(quiet_modtag) $@ - cmd_as_o_S = $(CC) $(a_flags) -c -o $@ $< + cmd_as_o_S = $(CC) $(a_flags) -c -o $@ $< $(cmd_objtool) ifdef CONFIG_ASM_MODVERSIONS From 918a6b7f68468ab80ec5e7ab7f3d2ef88905c20b Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 31 Aug 2021 16:39:55 +0900 Subject: [PATCH 068/587] kbuild: factor out OBJECT_FILES_NON_STANDARD check into a macro The OBJECT_FILES_NON_STANDARD check is quite long. Factor it out into a new macro, objtool-enabled, to not repeat it. Signed-off-by: Masahiro Yamada Reviewed-by: Nick Desaulniers Reviewed-by: Kees Cook Acked-by: Josh Poimboeuf --- scripts/Makefile.build | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 021ae0146913..720a86642f48 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -241,12 +241,12 @@ ifndef CONFIG_LTO_CLANG # 'OBJECT_FILES_NON_STANDARD := y': skip objtool checking for a directory # 'OBJECT_FILES_NON_STANDARD_foo.o := 'y': skip objtool checking for a file # 'OBJECT_FILES_NON_STANDARD_foo.o := 'n': override directory skip for a file -cmd_objtool = $(if $(patsubst y%,, \ - $(OBJECT_FILES_NON_STANDARD_$(basetarget).o)$(OBJECT_FILES_NON_STANDARD)n), \ - ; $(objtool) $(objtool_args) $@) -objtool_obj = $(if $(patsubst y%,, \ - $(OBJECT_FILES_NON_STANDARD_$(basetarget).o)$(OBJECT_FILES_NON_STANDARD)n), \ - $(objtool)) + +objtool-enabled = $(if $(filter-out y%, \ + $(OBJECT_FILES_NON_STANDARD_$(basetarget).o)$(OBJECT_FILES_NON_STANDARD)n),y) + +cmd_objtool = $(if $(objtool-enabled), ; $(objtool) $(objtool_args) $@) +objtool_obj = $(if $(objtool-enabled), $(objtool)) endif # CONFIG_LTO_CLANG endif # CONFIG_STACK_VALIDATION From ef62588c2c8611c196b780561610921b7b864bb2 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 31 Aug 2021 16:39:56 +0900 Subject: [PATCH 069/587] kbuild: detect objtool update without using .SECONDEXPANSION Redo commit 8852c5524029 ("kbuild: Fix objtool dependency for 'OBJECT_FILES_NON_STANDARD_ := n'") to add the objtool dependency in a cleaner way. Using .SECONDEXPANSION ends up with unreadable code due to escaped dollars. Also, it is not efficient because the second half of Makefile.build is parsed twice every time. Append the objtool dependency to the *.cmd files at the build time. This is what fixdep and gen_ksymdeps.sh already do. So, following the same pattern seems a natural solution. This allows us to drop $$(objtool_dep) entirely. Signed-off-by: Masahiro Yamada Reviewed-by: Kees Cook Reviewed-by: Nick Desaulniers Acked-by: Josh Poimboeuf --- scripts/Makefile.build | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 720a86642f48..21b55f37a23f 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -246,14 +246,11 @@ objtool-enabled = $(if $(filter-out y%, \ $(OBJECT_FILES_NON_STANDARD_$(basetarget).o)$(OBJECT_FILES_NON_STANDARD)n),y) cmd_objtool = $(if $(objtool-enabled), ; $(objtool) $(objtool_args) $@) -objtool_obj = $(if $(objtool-enabled), $(objtool)) +cmd_gen_objtooldep = $(if $(objtool-enabled), { echo ; echo '$@: $$(wildcard $(objtool))' ; } >> $(dot-target).cmd) endif # CONFIG_LTO_CLANG endif # CONFIG_STACK_VALIDATION -# Rebuild all objects when objtool changes -objtool_dep = $(objtool_obj) - ifdef CONFIG_TRIM_UNUSED_KSYMS cmd_gen_ksymdeps = \ $(CONFIG_SHELL) $(srctree)/scripts/gen_ksymdeps.sh $@ >> $(dot-target).cmd @@ -267,6 +264,7 @@ define rule_cc_o_c $(call cmd,gen_ksymdeps) $(call cmd,checksrc) $(call cmd,checkdoc) + $(call cmd,gen_objtooldep) $(call cmd,modversions_c) $(call cmd,record_mcount) endef @@ -274,12 +272,12 @@ endef define rule_as_o_S $(call cmd_and_fixdep,as_o_S) $(call cmd,gen_ksymdeps) + $(call cmd,gen_objtooldep) $(call cmd,modversions_S) endef # Built-in and composite module parts -.SECONDEXPANSION: -$(obj)/%.o: $(src)/%.c $(recordmcount_source) $$(objtool_dep) FORCE +$(obj)/%.o: $(src)/%.c $(recordmcount_source) FORCE $(call if_changed_rule,cc_o_c) $(call cmd,force_checksrc) @@ -380,7 +378,7 @@ cmd_modversions_S = \ fi endif -$(obj)/%.o: $(src)/%.S $$(objtool_dep) FORCE +$(obj)/%.o: $(src)/%.S FORCE $(call if_changed_rule,as_o_S) targets += $(filter-out $(subdir-builtin), $(real-obj-y)) From 90a353491e9f95516fcfd33ae7331d638557416c Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 31 Aug 2021 16:39:57 +0900 Subject: [PATCH 070/587] kbuild: reuse $(cmd_objtool) for cmd_cc_lto_link_modules For CONFIG_LTO_CLANG=y, the objtool processing is not possible at the compilation, hence postponed by the link time. Reuse $(cmd_objtool) for CONFIG_LTO_CLANG=y by defining objtool-enabled properly. For CONFIG_LTO_CLANG=y: objtool-enabled is off for %.o compilation objtool-enabled is on for %.lto link For CONFIG_LTO_CLANG=n: objtool-enabled is on for %.o compilation (but, it depends on OBJECT_FILE_NON_STANDARD) Set part-of-module := y for %.lto.o to avoid repeating --module. Signed-off-by: Masahiro Yamada Reviewed-by: Kees Cook Acked-by: Josh Poimboeuf --- scripts/Makefile.build | 28 +++++++++++++++++----------- 1 file changed, 17 insertions(+), 11 deletions(-) diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 21b55f37a23f..78656b527fe5 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -236,20 +236,26 @@ objtool_args = \ $(if $(CONFIG_X86_SMAP), --uaccess) \ $(if $(CONFIG_FTRACE_MCOUNT_USE_OBJTOOL), --mcount) -ifndef CONFIG_LTO_CLANG +cmd_objtool = $(if $(objtool-enabled), ; $(objtool) $(objtool_args) $@) +cmd_gen_objtooldep = $(if $(objtool-enabled), { echo ; echo '$@: $$(wildcard $(objtool))' ; } >> $(dot-target).cmd) + +endif # CONFIG_STACK_VALIDATION + +ifdef CONFIG_LTO_CLANG + +# Skip objtool for LLVM bitcode +$(obj)/%.o: objtool-enabled := + +else # 'OBJECT_FILES_NON_STANDARD := y': skip objtool checking for a directory # 'OBJECT_FILES_NON_STANDARD_foo.o := 'y': skip objtool checking for a file # 'OBJECT_FILES_NON_STANDARD_foo.o := 'n': override directory skip for a file -objtool-enabled = $(if $(filter-out y%, \ +$(obj)/%.o: objtool-enabled = $(if $(filter-out y%, \ $(OBJECT_FILES_NON_STANDARD_$(basetarget).o)$(OBJECT_FILES_NON_STANDARD)n),y) -cmd_objtool = $(if $(objtool-enabled), ; $(objtool) $(objtool_args) $@) -cmd_gen_objtooldep = $(if $(objtool-enabled), { echo ; echo '$@: $$(wildcard $(objtool))' ; } >> $(dot-target).cmd) - -endif # CONFIG_LTO_CLANG -endif # CONFIG_STACK_VALIDATION +endif ifdef CONFIG_TRIM_UNUSED_KSYMS cmd_gen_ksymdeps = \ @@ -289,13 +295,13 @@ cmd_cc_lto_link_modules = \ $(LD) $(ld_flags) -r -o $@ \ $(shell [ -s $(@:.lto.o=.o.symversions) ] && \ echo -T $(@:.lto.o=.o.symversions)) \ - --whole-archive $(filter-out FORCE,$^) + --whole-archive $(filter-out FORCE,$^) \ + $(cmd_objtool) -ifdef CONFIG_STACK_VALIDATION # objtool was skipped for LLVM bitcode, run it now that we have compiled # modules into native code -cmd_cc_lto_link_modules += ; $(objtool) $(objtool_args) --module $@ -endif +$(obj)/%.lto.o: objtool-enabled = y +$(obj)/%.lto.o: part-of-module := y $(obj)/%.lto.o: $(obj)/%.o FORCE $(call if_changed,cc_lto_link_modules) From e1db0f55976f796d1e75aa48c06658488d407709 Mon Sep 17 00:00:00 2001 From: Kunihiko Hayashi Date: Thu, 16 Sep 2021 20:19:36 +0900 Subject: [PATCH 071/587] gpio: uniphier: Use helper function to get IRQ hardware number Use helper function to get IRQ hardware number instead of direct access. No functional changes intended. Signed-off-by: Kunihiko Hayashi Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-uniphier.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/gpio/gpio-uniphier.c b/drivers/gpio/gpio-uniphier.c index f99f3c10bed0..954f2b537a75 100644 --- a/drivers/gpio/gpio-uniphier.c +++ b/drivers/gpio/gpio-uniphier.c @@ -180,7 +180,7 @@ static int uniphier_gpio_to_irq(struct gpio_chip *chip, unsigned int offset) static void uniphier_gpio_irq_mask(struct irq_data *data) { struct uniphier_gpio_priv *priv = data->chip_data; - u32 mask = BIT(data->hwirq); + u32 mask = BIT(irqd_to_hwirq(data)); uniphier_gpio_reg_update(priv, UNIPHIER_GPIO_IRQ_EN, mask, 0); @@ -190,7 +190,7 @@ static void uniphier_gpio_irq_mask(struct irq_data *data) static void uniphier_gpio_irq_unmask(struct irq_data *data) { struct uniphier_gpio_priv *priv = data->chip_data; - u32 mask = BIT(data->hwirq); + u32 mask = BIT(irqd_to_hwirq(data)); uniphier_gpio_reg_update(priv, UNIPHIER_GPIO_IRQ_EN, mask, mask); @@ -200,7 +200,7 @@ static void uniphier_gpio_irq_unmask(struct irq_data *data) static int uniphier_gpio_irq_set_type(struct irq_data *data, unsigned int type) { struct uniphier_gpio_priv *priv = data->chip_data; - u32 mask = BIT(data->hwirq); + u32 mask = BIT(irqd_to_hwirq(data)); u32 val = 0; if (type == IRQ_TYPE_EDGE_BOTH) { @@ -297,7 +297,8 @@ static int uniphier_gpio_irq_domain_activate(struct irq_domain *domain, struct uniphier_gpio_priv *priv = domain->host_data; struct gpio_chip *chip = &priv->chip; - return gpiochip_lock_as_irq(chip, data->hwirq + UNIPHIER_GPIO_IRQ_OFFSET); + return gpiochip_lock_as_irq(chip, + irqd_to_hwirq(data) + UNIPHIER_GPIO_IRQ_OFFSET); } static void uniphier_gpio_irq_domain_deactivate(struct irq_domain *domain, @@ -306,7 +307,8 @@ static void uniphier_gpio_irq_domain_deactivate(struct irq_domain *domain, struct uniphier_gpio_priv *priv = domain->host_data; struct gpio_chip *chip = &priv->chip; - gpiochip_unlock_as_irq(chip, data->hwirq + UNIPHIER_GPIO_IRQ_OFFSET); + gpiochip_unlock_as_irq(chip, + irqd_to_hwirq(data) + UNIPHIER_GPIO_IRQ_OFFSET); } static const struct irq_domain_ops uniphier_gpio_irq_domain_ops = { From dcfd2a2975f3eaa29c5a96d150a9364f51a5302c Mon Sep 17 00:00:00 2001 From: Kunihiko Hayashi Date: Thu, 16 Sep 2021 20:19:37 +0900 Subject: [PATCH 072/587] gpio: uniphier: Use helper functions to get private data from IRQ data Use helper functions to get private data from IRQ data instead of direct access. No functional changes intended. Signed-off-by: Kunihiko Hayashi Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-uniphier.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpio/gpio-uniphier.c b/drivers/gpio/gpio-uniphier.c index 954f2b537a75..9c677a0e7025 100644 --- a/drivers/gpio/gpio-uniphier.c +++ b/drivers/gpio/gpio-uniphier.c @@ -179,7 +179,7 @@ static int uniphier_gpio_to_irq(struct gpio_chip *chip, unsigned int offset) static void uniphier_gpio_irq_mask(struct irq_data *data) { - struct uniphier_gpio_priv *priv = data->chip_data; + struct uniphier_gpio_priv *priv = irq_data_get_irq_chip_data(data); u32 mask = BIT(irqd_to_hwirq(data)); uniphier_gpio_reg_update(priv, UNIPHIER_GPIO_IRQ_EN, mask, 0); @@ -189,7 +189,7 @@ static void uniphier_gpio_irq_mask(struct irq_data *data) static void uniphier_gpio_irq_unmask(struct irq_data *data) { - struct uniphier_gpio_priv *priv = data->chip_data; + struct uniphier_gpio_priv *priv = irq_data_get_irq_chip_data(data); u32 mask = BIT(irqd_to_hwirq(data)); uniphier_gpio_reg_update(priv, UNIPHIER_GPIO_IRQ_EN, mask, mask); @@ -199,7 +199,7 @@ static void uniphier_gpio_irq_unmask(struct irq_data *data) static int uniphier_gpio_irq_set_type(struct irq_data *data, unsigned int type) { - struct uniphier_gpio_priv *priv = data->chip_data; + struct uniphier_gpio_priv *priv = irq_data_get_irq_chip_data(data); u32 mask = BIT(irqd_to_hwirq(data)); u32 val = 0; From ca038748068f454d20ad1bb120cbe36599f81db6 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 17 Sep 2021 12:54:11 +0200 Subject: [PATCH 073/587] gpio: tegra186: Force one interrupt per bank Newer chips support up to 8 interrupts per bank, which can be useful to balance the load and decrease latency. However, it also required a very complicated interrupt routing to be set up. To keep things simple for now, ensure that a single interrupt per bank is enforced, even if all possible interrupts are described in device tree. Signed-off-by: Thierry Reding Reviewed-by: Linus Walleij Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-tegra186.c | 68 ++++++++++++++++++++++++++++++++---- 1 file changed, 62 insertions(+), 6 deletions(-) diff --git a/drivers/gpio/gpio-tegra186.c b/drivers/gpio/gpio-tegra186.c index c99858f40a27..1bc4152e0275 100644 --- a/drivers/gpio/gpio-tegra186.c +++ b/drivers/gpio/gpio-tegra186.c @@ -81,6 +81,8 @@ struct tegra_gpio { unsigned int *irq; const struct tegra_gpio_soc *soc; + unsigned int num_irqs_per_bank; + unsigned int num_banks; void __iomem *secure; void __iomem *base; @@ -594,6 +596,28 @@ static void tegra186_gpio_init_route_mapping(struct tegra_gpio *gpio) } } +static unsigned int tegra186_gpio_irqs_per_bank(struct tegra_gpio *gpio) +{ + struct device *dev = gpio->gpio.parent; + + if (gpio->num_irq > gpio->num_banks) { + if (gpio->num_irq % gpio->num_banks != 0) + goto error; + } + + if (gpio->num_irq < gpio->num_banks) + goto error; + + gpio->num_irqs_per_bank = gpio->num_irq / gpio->num_banks; + + return 0; + +error: + dev_err(dev, "invalid number of interrupts (%u) for %u banks\n", + gpio->num_irq, gpio->num_banks); + return -EINVAL; +} + static int tegra186_gpio_probe(struct platform_device *pdev) { unsigned int i, j, offset; @@ -608,7 +632,17 @@ static int tegra186_gpio_probe(struct platform_device *pdev) return -ENOMEM; gpio->soc = device_get_match_data(&pdev->dev); + gpio->gpio.label = gpio->soc->name; + gpio->gpio.parent = &pdev->dev; + /* count the number of banks in the controller */ + for (i = 0; i < gpio->soc->num_ports; i++) + if (gpio->soc->ports[i].bank > gpio->num_banks) + gpio->num_banks = gpio->soc->ports[i].bank; + + gpio->num_banks++; + + /* get register apertures */ gpio->secure = devm_platform_ioremap_resource_byname(pdev, "security"); if (IS_ERR(gpio->secure)) { gpio->secure = devm_platform_ioremap_resource(pdev, 0); @@ -629,6 +663,10 @@ static int tegra186_gpio_probe(struct platform_device *pdev) gpio->num_irq = err; + err = tegra186_gpio_irqs_per_bank(gpio); + if (err < 0) + return err; + gpio->irq = devm_kcalloc(&pdev->dev, gpio->num_irq, sizeof(*gpio->irq), GFP_KERNEL); if (!gpio->irq) @@ -642,9 +680,6 @@ static int tegra186_gpio_probe(struct platform_device *pdev) gpio->irq[i] = err; } - gpio->gpio.label = gpio->soc->name; - gpio->gpio.parent = &pdev->dev; - gpio->gpio.request = gpiochip_generic_request; gpio->gpio.free = gpiochip_generic_free; gpio->gpio.get_direction = tegra186_gpio_get_direction; @@ -708,7 +743,30 @@ static int tegra186_gpio_probe(struct platform_device *pdev) irq->parent_handler = tegra186_gpio_irq; irq->parent_handler_data = gpio; irq->num_parents = gpio->num_irq; - irq->parents = gpio->irq; + + /* + * To simplify things, use a single interrupt per bank for now. Some + * chips support up to 8 interrupts per bank, which can be useful to + * distribute the load and decrease the processing latency for GPIOs + * but it also requires a more complicated interrupt routing than we + * currently program. + */ + if (gpio->num_irqs_per_bank > 1) { + irq->parents = devm_kcalloc(&pdev->dev, gpio->num_banks, + sizeof(*irq->parents), GFP_KERNEL); + if (!irq->parents) + return -ENOMEM; + + for (i = 0; i < gpio->num_banks; i++) + irq->parents[i] = gpio->irq[i * gpio->num_irqs_per_bank]; + + irq->num_parents = gpio->num_banks; + } else { + irq->num_parents = gpio->num_irq; + irq->parents = gpio->irq; + } + + tegra186_gpio_init_route_mapping(gpio); np = of_find_matching_node(NULL, tegra186_pmc_of_match); if (np) { @@ -719,8 +777,6 @@ static int tegra186_gpio_probe(struct platform_device *pdev) return -EPROBE_DEFER; } - tegra186_gpio_init_route_mapping(gpio); - irq->map = devm_kcalloc(&pdev->dev, gpio->gpio.ngpio, sizeof(*irq->map), GFP_KERNEL); if (!irq->map) From 2103868047456e5f3e431ebb253d87e1fb806c76 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 17 Sep 2021 12:54:12 +0200 Subject: [PATCH 074/587] gpio: tegra186: Support multiple interrupts per bank Tegra194 and later support more than a single interrupt per bank. This is primarily useful for virtualization but can also be helpful for more fine-grained CPU affinity control. To keep things simple for now, route all pins to the first interrupt. For backwards-compatibility, support old device trees that specify only one interrupt per bank by counting the interrupts at probe time. Signed-off-by: Thierry Reding Reviewed-by: Linus Walleij Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-tegra186.c | 48 ++++++++++++++++++++++++++++++------ 1 file changed, 41 insertions(+), 7 deletions(-) diff --git a/drivers/gpio/gpio-tegra186.c b/drivers/gpio/gpio-tegra186.c index 1bc4152e0275..c026e7141e4e 100644 --- a/drivers/gpio/gpio-tegra186.c +++ b/drivers/gpio/gpio-tegra186.c @@ -69,6 +69,8 @@ struct tegra_gpio_soc { const char *name; unsigned int instance; + unsigned int num_irqs_per_bank; + const struct tegra186_pin_range *pin_ranges; unsigned int num_pin_ranges; const char *pinmux; @@ -452,7 +454,7 @@ static void tegra186_gpio_irq(struct irq_desc *desc) struct irq_domain *domain = gpio->gpio.irq.domain; struct irq_chip *chip = irq_desc_get_chip(desc); unsigned int parent = irq_desc_get_irq(desc); - unsigned int i, offset = 0; + unsigned int i, j, offset = 0; chained_irq_enter(chip, desc); @@ -465,7 +467,12 @@ static void tegra186_gpio_irq(struct irq_desc *desc) base = gpio->base + port->bank * 0x1000 + port->port * 0x200; /* skip ports that are not associated with this bank */ - if (parent != gpio->irq[port->bank]) + for (j = 0; j < gpio->num_irqs_per_bank; j++) { + if (parent == gpio->irq[port->bank * gpio->num_irqs_per_bank + j]) + break; + } + + if (j == gpio->num_irqs_per_bank) goto skip; value = readl(base + TEGRA186_GPIO_INTERRUPT_STATUS(1)); @@ -567,6 +574,7 @@ static const struct of_device_id tegra186_pmc_of_match[] = { static void tegra186_gpio_init_route_mapping(struct tegra_gpio *gpio) { + struct device *dev = gpio->gpio.parent; unsigned int i, j; u32 value; @@ -585,12 +593,30 @@ static void tegra186_gpio_init_route_mapping(struct tegra_gpio *gpio) */ if ((value & TEGRA186_GPIO_CTL_SCR_SEC_REN) == 0 && (value & TEGRA186_GPIO_CTL_SCR_SEC_WEN) == 0) { - for (j = 0; j < 8; j++) { + /* + * On Tegra194 and later, each pin can be routed to one or more + * interrupts. + */ + for (j = 0; j < gpio->num_irqs_per_bank; j++) { + dev_dbg(dev, "programming default interrupt routing for port %s\n", + port->name); + offset = TEGRA186_GPIO_INT_ROUTE_MAPPING(p, j); - value = readl(base + offset); - value = BIT(port->pins) - 1; - writel(value, base + offset); + /* + * By default we only want to route GPIO pins to IRQ 0. This works + * only under the assumption that we're running as the host kernel + * and hence all GPIO pins are owned by Linux. + * + * For cases where Linux is the guest OS, the hypervisor will have + * to configure the interrupt routing and pass only the valid + * interrupts via device tree. + */ + if (j == 0) { + value = readl(base + offset); + value = BIT(port->pins) - 1; + writel(value, base + offset); + } } } } @@ -610,6 +636,9 @@ static unsigned int tegra186_gpio_irqs_per_bank(struct tegra_gpio *gpio) gpio->num_irqs_per_bank = gpio->num_irq / gpio->num_banks; + if (gpio->num_irqs_per_bank > gpio->soc->num_irqs_per_bank) + goto error; + return 0; error: @@ -766,7 +795,8 @@ static int tegra186_gpio_probe(struct platform_device *pdev) irq->parents = gpio->irq; } - tegra186_gpio_init_route_mapping(gpio); + if (gpio->soc->num_irqs_per_bank > 1) + tegra186_gpio_init_route_mapping(gpio); np = of_find_matching_node(NULL, tegra186_pmc_of_match); if (np) { @@ -833,6 +863,7 @@ static const struct tegra_gpio_soc tegra186_main_soc = { .ports = tegra186_main_ports, .name = "tegra186-gpio", .instance = 0, + .num_irqs_per_bank = 1, }; #define TEGRA186_AON_GPIO_PORT(_name, _bank, _port, _pins) \ @@ -859,6 +890,7 @@ static const struct tegra_gpio_soc tegra186_aon_soc = { .ports = tegra186_aon_ports, .name = "tegra186-gpio-aon", .instance = 1, + .num_irqs_per_bank = 1, }; #define TEGRA194_MAIN_GPIO_PORT(_name, _bank, _port, _pins) \ @@ -910,6 +942,7 @@ static const struct tegra_gpio_soc tegra194_main_soc = { .ports = tegra194_main_ports, .name = "tegra194-gpio", .instance = 0, + .num_irqs_per_bank = 8, .num_pin_ranges = ARRAY_SIZE(tegra194_main_pin_ranges), .pin_ranges = tegra194_main_pin_ranges, .pinmux = "nvidia,tegra194-pinmux", @@ -936,6 +969,7 @@ static const struct tegra_gpio_soc tegra194_aon_soc = { .ports = tegra194_aon_ports, .name = "tegra194-gpio-aon", .instance = 1, + .num_irqs_per_bank = 8, }; static const struct of_device_id tegra186_gpio_of_match[] = { From e24b9fc109280a2420aabe352d38fad722f4ea37 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Mon, 20 Sep 2021 11:05:15 +0200 Subject: [PATCH 075/587] gpio: xilinx: simplify getting .driver_data We should get 'driver_data' from 'struct device' directly. Going via platform_device is an unneeded step back and forth. Signed-off-by: Wolfram Sang Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-xilinx.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/gpio/gpio-xilinx.c b/drivers/gpio/gpio-xilinx.c index a1b66338d077..b6d3a57e27ed 100644 --- a/drivers/gpio/gpio-xilinx.c +++ b/drivers/gpio/gpio-xilinx.c @@ -371,8 +371,7 @@ static int __maybe_unused xgpio_resume(struct device *dev) static int __maybe_unused xgpio_runtime_suspend(struct device *dev) { - struct platform_device *pdev = to_platform_device(dev); - struct xgpio_instance *gpio = platform_get_drvdata(pdev); + struct xgpio_instance *gpio = dev_get_drvdata(dev); clk_disable(gpio->clk); @@ -381,8 +380,7 @@ static int __maybe_unused xgpio_runtime_suspend(struct device *dev) static int __maybe_unused xgpio_runtime_resume(struct device *dev) { - struct platform_device *pdev = to_platform_device(dev); - struct xgpio_instance *gpio = platform_get_drvdata(pdev); + struct xgpio_instance *gpio = dev_get_drvdata(dev); return clk_enable(gpio->clk); } From 3846a3607738ccbc763afe7af75b5bd25009b037 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 16 Sep 2021 18:46:40 +0200 Subject: [PATCH 076/587] gpio: max77620: drop unneeded MODULE_ALIAS The MODULE_DEVICE_TABLE already creates proper alias for platform driver. Having another MODULE_ALIAS causes the alias to be duplicated. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-max77620.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpio/gpio-max77620.c b/drivers/gpio/gpio-max77620.c index 82b3a913005d..ebf9dea6546b 100644 --- a/drivers/gpio/gpio-max77620.c +++ b/drivers/gpio/gpio-max77620.c @@ -365,5 +365,4 @@ module_platform_driver(max77620_gpio_driver); MODULE_DESCRIPTION("GPIO interface for MAX77620 and MAX20024 PMIC"); MODULE_AUTHOR("Laxman Dewangan "); MODULE_AUTHOR("Chaitanya Bandi "); -MODULE_ALIAS("platform:max77620-gpio"); MODULE_LICENSE("GPL v2"); From 03e2080defd2494bd2790d2ac1df9d7432671e85 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 16 Sep 2021 18:46:41 +0200 Subject: [PATCH 077/587] gpio: tps65218: drop unneeded MODULE_ALIAS The MODULE_DEVICE_TABLE already creates proper alias for platform driver. Having another MODULE_ALIAS causes the alias to be duplicated. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-tps65218.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpio/gpio-tps65218.c b/drivers/gpio/gpio-tps65218.c index 3517debe2b0b..912382be48e1 100644 --- a/drivers/gpio/gpio-tps65218.c +++ b/drivers/gpio/gpio-tps65218.c @@ -230,4 +230,3 @@ module_platform_driver(tps65218_gpio_driver); MODULE_AUTHOR("Nicolas Saenz Julienne "); MODULE_DESCRIPTION("GPO interface for TPS65218 PMICs"); MODULE_LICENSE("GPL v2"); -MODULE_ALIAS("platform:tps65218-gpio"); From 23c64d7618a7e76e46db99444d184ef75498fb71 Mon Sep 17 00:00:00 2001 From: Piyush Mehta Date: Wed, 22 Sep 2021 19:23:17 +0530 Subject: [PATCH 078/587] firmware: zynqmp: Add MMIO read and write support for PS_MODE pin Add Xilinx ZynqMP firmware MMIO APIs support to set and get PS_MODE pins value and status. These APIs create an interface path between mode pin controller driver and low-level API to access GPIO pins. Signed-off-by: Piyush Mehta Acked-by: Michal Simek Acked-by: Linus Walleij Signed-off-by: Bartosz Golaszewski --- drivers/firmware/xilinx/zynqmp.c | 46 ++++++++++++++++++++++++++++ include/linux/firmware/xlnx-zynqmp.h | 14 +++++++++ 2 files changed, 60 insertions(+) diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c index a3cadbaf3cba..7feba125b883 100644 --- a/drivers/firmware/xilinx/zynqmp.c +++ b/drivers/firmware/xilinx/zynqmp.c @@ -28,6 +28,13 @@ /* Max HashMap Order for PM API feature check (1<<7 = 128) */ #define PM_API_FEATURE_CHECK_MAX_ORDER 7 +/* CRL registers and bitfields */ +#define CRL_APB_BASE 0xFF5E0000U +/* BOOT_PIN_CTRL- Used to control the mode pins after boot */ +#define CRL_APB_BOOT_PIN_CTRL (CRL_APB_BASE + (0x250U)) +/* BOOT_PIN_CTRL_MASK- out_val[11:8], out_en[3:0] */ +#define CRL_APB_BOOTPIN_CTRL_MASK 0xF0FU + static bool feature_check_enabled; static DEFINE_HASHTABLE(pm_api_features_map, PM_API_FEATURE_CHECK_MAX_ORDER); @@ -925,6 +932,45 @@ int zynqmp_pm_pinctrl_set_config(const u32 pin, const u32 param, } EXPORT_SYMBOL_GPL(zynqmp_pm_pinctrl_set_config); +/** + * zynqmp_pm_bootmode_read() - PM Config API for read bootpin status + * @ps_mode: Returned output value of ps_mode + * + * This API function is to be used for notify the power management controller + * to read bootpin status. + * + * Return: status, either success or error+reason + */ +unsigned int zynqmp_pm_bootmode_read(u32 *ps_mode) +{ + unsigned int ret; + u32 ret_payload[PAYLOAD_ARG_CNT]; + + ret = zynqmp_pm_invoke_fn(PM_MMIO_READ, CRL_APB_BOOT_PIN_CTRL, 0, + 0, 0, ret_payload); + + *ps_mode = ret_payload[1]; + + return ret; +} +EXPORT_SYMBOL_GPL(zynqmp_pm_bootmode_read); + +/** + * zynqmp_pm_bootmode_write() - PM Config API for Configure bootpin + * @ps_mode: Value to be written to the bootpin ctrl register + * + * This API function is to be used for notify the power management controller + * to configure bootpin. + * + * Return: Returns status, either success or error+reason + */ +int zynqmp_pm_bootmode_write(u32 ps_mode) +{ + return zynqmp_pm_invoke_fn(PM_MMIO_WRITE, CRL_APB_BOOT_PIN_CTRL, + CRL_APB_BOOTPIN_CTRL_MASK, ps_mode, 0, NULL); +} +EXPORT_SYMBOL_GPL(zynqmp_pm_bootmode_write); + /** * zynqmp_pm_init_finalize() - PM call to inform firmware that the caller * master has initialized its own power management diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 56b426fe020c..3917f89b2b3c 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -72,6 +72,8 @@ enum pm_api_id { PM_SET_REQUIREMENT = 15, PM_RESET_ASSERT = 17, PM_RESET_GET_STATUS = 18, + PM_MMIO_WRITE = 19, + PM_MMIO_READ = 20, PM_PM_INIT_FINALIZE = 21, PM_FPGA_LOAD = 22, PM_FPGA_GET_STATUS = 23, @@ -390,6 +392,8 @@ int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type); int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset, const enum zynqmp_pm_reset_action assert_flag); int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset, u32 *status); +unsigned int zynqmp_pm_bootmode_read(u32 *ps_mode); +int zynqmp_pm_bootmode_write(u32 ps_mode); int zynqmp_pm_init_finalize(void); int zynqmp_pm_set_suspend_mode(u32 mode); int zynqmp_pm_request_node(const u32 node, const u32 capabilities, @@ -520,6 +524,16 @@ static inline int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset, return -ENODEV; } +static inline unsigned int zynqmp_pm_bootmode_read(u32 *ps_mode) +{ + return -ENODEV; +} + +static inline int zynqmp_pm_bootmode_write(u32 ps_mode) +{ + return -ENODEV; +} + static inline int zynqmp_pm_init_finalize(void) { return -ENODEV; From d7f4a65cdf4f671296fab1e5b331fd3f5ab776e5 Mon Sep 17 00:00:00 2001 From: Piyush Mehta Date: Wed, 22 Sep 2021 19:23:18 +0530 Subject: [PATCH 079/587] dt-bindings: gpio: zynqmp: Add binding documentation for modepin This patch adds DT binding document for zynqmp modepin GPIO controller. Modepin GPIO controller has four GPIO pins which can be configurable as input or output. Modepin driver is a bridge between the peripheral driver and GPIO pins. It has set and get APIs for accessing GPIO pins, based on the device-tree entry of reset-gpio property in the peripheral driver, every pin can be configured as input/output and trigger GPIO pin. For more information please refer zynqMp TRM link: Link: https://www.xilinx.com/support/documentation/user_guides/ug1085-zynq-ultrascale-trm.pdf Chapter 2: Signals, Interfaces, and Pins Table 2-2: Clock, Reset, and Configuration Pins - PS_MODE Signed-off-by: Piyush Mehta Acked-by: Michal Simek Reviewed-by: Rob Herring Signed-off-by: Bartosz Golaszewski --- .../gpio/xlnx,zynqmp-gpio-modepin.yaml | 43 +++++++++++++++++++ 1 file changed, 43 insertions(+) create mode 100644 Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml diff --git a/Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml b/Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml new file mode 100644 index 000000000000..31c0fc345903 --- /dev/null +++ b/Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml @@ -0,0 +1,43 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: "http://devicetree.org/schemas/gpio/xlnx,zynqmp-gpio-modepin.yaml#" +$schema: "http://devicetree.org/meta-schemas/core.yaml#" + +title: ZynqMP Mode Pin GPIO controller + +description: + PS_MODE is 4-bits boot mode pins sampled on POR deassertion. Mode Pin + GPIO controller with configurable from numbers of pins (from 0 to 3 per + PS_MODE). Every pin can be configured as input/output. + +maintainers: + - Piyush Mehta + +properties: + compatible: + const: xlnx,zynqmp-gpio-modepin + + gpio-controller: true + + "#gpio-cells": + const: 2 + +required: + - compatible + - gpio-controller + - "#gpio-cells" + +additionalProperties: false + +examples: + - | + zynqmp-firmware { + gpio { + compatible = "xlnx,zynqmp-gpio-modepin"; + gpio-controller; + #gpio-cells = <2>; + }; + }; + +... From 7687a5b0ee9358c96d85db58bad2a3aebee562b7 Mon Sep 17 00:00:00 2001 From: Piyush Mehta Date: Wed, 22 Sep 2021 19:23:19 +0530 Subject: [PATCH 080/587] gpio: modepin: Add driver support for modepin GPIO controller This patch adds driver support for the zynqmp modepin GPIO controller. GPIO modepin driver set and get the value and status of the PS_MODE pin, based on device-tree pin configuration. These four mode pins are configurable as input/output. The mode pin has a control register, which have lower four-bits [0:3] are configurable as input/output, next four-bits can be used for reading the data as input[4:7], and next setting the output pin state output[8:11]. By default value of mode pin register is 0. Signed-off-by: Piyush Mehta Acked-by: Michal Simek Reviewed-by: Linus Walleij Signed-off-by: Bartosz Golaszewski --- drivers/gpio/Kconfig | 12 +++ drivers/gpio/Makefile | 1 + drivers/gpio/gpio-zynqmp-modepin.c | 162 +++++++++++++++++++++++++++++ 3 files changed, 175 insertions(+) create mode 100644 drivers/gpio/gpio-zynqmp-modepin.c diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index fae5141251e5..37a6f77c86fe 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -763,6 +763,18 @@ config GPIO_ZYNQ help Say yes here to support Xilinx Zynq GPIO controller. +config GPIO_ZYNQMP_MODEPIN + tristate "ZynqMP ps-mode pin gpio configuration driver" + depends on ZYNQMP_FIRMWARE + default ZYNQMP_FIRMWARE + help + Say yes here to support the ZynqMP ps-mode pin gpio configuration + driver. + + This ps-mode pin gpio driver is based on GPIO framework, PS_MODE + is 4-bits boot mode pins. It sets and gets the status of + the ps-mode pin. Every pin can be configured as input/output. + config GPIO_LOONGSON1 tristate "Loongson1 GPIO support" depends on MACH_LOONGSON32 diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile index fbcda637d5e1..71ee9fc2ff83 100644 --- a/drivers/gpio/Makefile +++ b/drivers/gpio/Makefile @@ -184,3 +184,4 @@ obj-$(CONFIG_GPIO_XRA1403) += gpio-xra1403.o obj-$(CONFIG_GPIO_XTENSA) += gpio-xtensa.o obj-$(CONFIG_GPIO_ZEVIO) += gpio-zevio.o obj-$(CONFIG_GPIO_ZYNQ) += gpio-zynq.o +obj-$(CONFIG_GPIO_ZYNQMP_MODEPIN) += gpio-zynqmp-modepin.o diff --git a/drivers/gpio/gpio-zynqmp-modepin.c b/drivers/gpio/gpio-zynqmp-modepin.c new file mode 100644 index 000000000000..a0d69387c153 --- /dev/null +++ b/drivers/gpio/gpio-zynqmp-modepin.c @@ -0,0 +1,162 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Driver for the ps-mode pin configuration. + * + * Copyright (c) 2021 Xilinx, Inc. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* 4-bit boot mode pins */ +#define MODE_PINS 4 + +/** + * modepin_gpio_get_value - Get the state of the specified pin of GPIO device + * @chip: gpio_chip instance to be worked on + * @pin: gpio pin number within the device + * + * This function reads the state of the specified pin of the GPIO device. + * + * Return: 0 if the pin is low, 1 if pin is high, -EINVAL wrong pin configured + * or error value. + */ +static int modepin_gpio_get_value(struct gpio_chip *chip, unsigned int pin) +{ + u32 regval = 0; + int ret; + + ret = zynqmp_pm_bootmode_read(®val); + if (ret) + return ret; + + /* When [0:3] corresponding bit is set, then read output bit [8:11], + * if the bit is clear then read input bit [4:7] for status or value. + */ + if (regval & BIT(pin)) + return !!(regval & BIT(pin + 8)); + else + return !!(regval & BIT(pin + 4)); +} + +/** + * modepin_gpio_set_value - Modify the state of the pin with specified value + * @chip: gpio_chip instance to be worked on + * @pin: gpio pin number within the device + * @state: value used to modify the state of the specified pin + * + * This function reads the state of the specified pin of the GPIO device, mask + * with the capture state of GPIO pin, and update pin of GPIO device. + * + * Return: None. + */ +static void modepin_gpio_set_value(struct gpio_chip *chip, unsigned int pin, + int state) +{ + u32 bootpin_val = 0; + int ret; + + zynqmp_pm_bootmode_read(&bootpin_val); + + /* Configure pin as an output by set bit [0:3] */ + bootpin_val |= BIT(pin); + + if (state) + bootpin_val |= BIT(pin + 8); + else + bootpin_val &= ~BIT(pin + 8); + + /* Configure bootpin value */ + ret = zynqmp_pm_bootmode_write(bootpin_val); + if (ret) + pr_err("modepin: set value error %d for pin %d\n", ret, pin); +} + +/** + * modepin_gpio_dir_in - Set the direction of the specified GPIO pin as input + * @chip: gpio_chip instance to be worked on + * @pin: gpio pin number within the device + * + * Return: 0 always + */ +static int modepin_gpio_dir_in(struct gpio_chip *chip, unsigned int pin) +{ + return 0; +} + +/** + * modepin_gpio_dir_out - Set the direction of the specified GPIO pin as output + * @chip: gpio_chip instance to be worked on + * @pin: gpio pin number within the device + * @state: value to be written to specified pin + * + * Return: 0 always + */ +static int modepin_gpio_dir_out(struct gpio_chip *chip, unsigned int pin, + int state) +{ + return 0; +} + +/** + * modepin_gpio_probe - Initialization method for modepin_gpio + * @pdev: platform device instance + * + * Return: 0 on success, negative error otherwise. + */ +static int modepin_gpio_probe(struct platform_device *pdev) +{ + struct gpio_chip *chip; + int status; + + chip = devm_kzalloc(&pdev->dev, sizeof(*chip), GFP_KERNEL); + if (!chip) + return -ENOMEM; + + platform_set_drvdata(pdev, chip); + + /* configure the gpio chip */ + chip->base = -1; + chip->ngpio = MODE_PINS; + chip->owner = THIS_MODULE; + chip->parent = &pdev->dev; + chip->get = modepin_gpio_get_value; + chip->set = modepin_gpio_set_value; + chip->direction_input = modepin_gpio_dir_in; + chip->direction_output = modepin_gpio_dir_out; + chip->label = dev_name(&pdev->dev); + + /* modepin gpio registration */ + status = devm_gpiochip_add_data(&pdev->dev, chip, chip); + if (status) + return dev_err_probe(&pdev->dev, status, + "Failed to add GPIO chip\n"); + + return status; +} + +static const struct of_device_id modepin_platform_id[] = { + { .compatible = "xlnx,zynqmp-gpio-modepin", }, + { } +}; + +static struct platform_driver modepin_platform_driver = { + .driver = { + .name = "modepin-gpio", + .of_match_table = modepin_platform_id, + }, + .probe = modepin_gpio_probe, +}; + +module_platform_driver(modepin_platform_driver); + +MODULE_AUTHOR("Piyush Mehta "); +MODULE_DESCRIPTION("ZynqMP Boot PS_MODE Configuration"); +MODULE_LICENSE("GPL v2"); From 6c93f39f2f435d822c2f765650f405acebdc49fc Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Thu, 9 Sep 2021 14:18:44 +0800 Subject: [PATCH 081/587] perf list: Display pmu prefix for partially supported hybrid cache events Part of hardware cache events are only available on one CPU PMU. For example, 'L1-dcache-load-misses' is only available on cpu_core. perf list should clearly report this info. root@otcpl-adl-s-2:~# ./perf list Before: L1-dcache-load-misses [Hardware cache event] L1-dcache-loads [Hardware cache event] L1-dcache-stores [Hardware cache event] L1-icache-load-misses [Hardware cache event] L1-icache-loads [Hardware cache event] LLC-load-misses [Hardware cache event] LLC-loads [Hardware cache event] LLC-store-misses [Hardware cache event] LLC-stores [Hardware cache event] branch-load-misses [Hardware cache event] branch-loads [Hardware cache event] dTLB-load-misses [Hardware cache event] dTLB-loads [Hardware cache event] dTLB-store-misses [Hardware cache event] dTLB-stores [Hardware cache event] iTLB-load-misses [Hardware cache event] node-load-misses [Hardware cache event] node-loads [Hardware cache event] node-store-misses [Hardware cache event] node-stores [Hardware cache event] After: L1-dcache-loads [Hardware cache event] L1-dcache-stores [Hardware cache event] L1-icache-load-misses [Hardware cache event] LLC-load-misses [Hardware cache event] LLC-loads [Hardware cache event] LLC-store-misses [Hardware cache event] LLC-stores [Hardware cache event] branch-load-misses [Hardware cache event] branch-loads [Hardware cache event] cpu_atom/L1-icache-loads/ [Hardware cache event] cpu_core/L1-dcache-load-misses/ [Hardware cache event] cpu_core/node-load-misses/ [Hardware cache event] cpu_core/node-loads/ [Hardware cache event] dTLB-load-misses [Hardware cache event] dTLB-loads [Hardware cache event] dTLB-store-misses [Hardware cache event] dTLB-stores [Hardware cache event] iTLB-load-misses [Hardware cache event] Now we can clearly see 'L1-dcache-load-misses' is only available on cpu_core. If without pmu prefix, it indicates the event is available on both cpu_core and cpu_atom. Signed-off-by: Jin Yao Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jin Yao Cc: Jiri Olsa Cc: Kan Liang Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20210909061844.10221-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 76 ++++++++++++++++++++++++++++++---- 1 file changed, 68 insertions(+), 8 deletions(-) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 85d3d77d3c6a..067f830dea4b 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -2701,7 +2701,7 @@ next: return 0; } -static bool is_event_supported(u8 type, unsigned config) +static bool is_event_supported(u8 type, u64 config) { bool ret = true; int open_return; @@ -2821,10 +2821,18 @@ void print_sdt_events(const char *subsys_glob, const char *event_glob, int print_hwcache_events(const char *event_glob, bool name_only) { - unsigned int type, op, i, evt_i = 0, evt_num = 0; - char name[64]; - char **evt_list = NULL; + unsigned int type, op, i, evt_i = 0, evt_num = 0, npmus = 0; + char name[64], new_name[128]; + char **evt_list = NULL, **evt_pmus = NULL; bool evt_num_known = false; + struct perf_pmu *pmu = NULL; + + if (perf_pmu__has_hybrid()) { + npmus = perf_pmu__hybrid_pmu_num(); + evt_pmus = zalloc(sizeof(char *) * npmus); + if (!evt_pmus) + goto out_enomem; + } restart: if (evt_num_known) { @@ -2840,20 +2848,61 @@ restart: continue; for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) { + unsigned int hybrid_supported = 0, j; + bool supported; + __evsel__hw_cache_type_op_res_name(type, op, i, name, sizeof(name)); if (event_glob != NULL && !strglobmatch(name, event_glob)) continue; - if (!is_event_supported(PERF_TYPE_HW_CACHE, - type | (op << 8) | (i << 16))) - continue; + if (!perf_pmu__has_hybrid()) { + if (!is_event_supported(PERF_TYPE_HW_CACHE, + type | (op << 8) | (i << 16))) { + continue; + } + } else { + perf_pmu__for_each_hybrid_pmu(pmu) { + if (!evt_num_known) { + evt_num++; + continue; + } + + supported = is_event_supported( + PERF_TYPE_HW_CACHE, + type | (op << 8) | (i << 16) | + ((__u64)pmu->type << PERF_PMU_TYPE_SHIFT)); + if (supported) { + snprintf(new_name, sizeof(new_name), "%s/%s/", + pmu->name, name); + evt_pmus[hybrid_supported] = strdup(new_name); + hybrid_supported++; + } + } + + if (hybrid_supported == 0) + continue; + } if (!evt_num_known) { evt_num++; continue; } - evt_list[evt_i] = strdup(name); + if ((hybrid_supported == 0) || + (hybrid_supported == npmus)) { + evt_list[evt_i] = strdup(name); + if (npmus > 0) { + for (j = 0; j < npmus; j++) + zfree(&evt_pmus[j]); + } + } else { + for (j = 0; j < hybrid_supported; j++) { + evt_list[evt_i++] = evt_pmus[j]; + evt_pmus[j] = NULL; + } + continue; + } + if (evt_list[evt_i] == NULL) goto out_enomem; evt_i++; @@ -2865,6 +2914,13 @@ restart: evt_num_known = true; goto restart; } + + for (evt_i = 0; evt_i < evt_num; evt_i++) { + if (!evt_list[evt_i]) + break; + } + + evt_num = evt_i; qsort(evt_list, evt_num, sizeof(char *), cmp_string); evt_i = 0; while (evt_i < evt_num) { @@ -2883,6 +2939,10 @@ out_free: for (evt_i = 0; evt_i < evt_num; evt_i++) zfree(&evt_list[evt_i]); zfree(&evt_list); + + for (evt_i = 0; evt_i < npmus; evt_i++) + zfree(&evt_pmus[evt_i]); + zfree(&evt_pmus); return evt_num; out_enomem: From d05377e184fc88e965e20606da93387b8fadf493 Mon Sep 17 00:00:00 2001 From: Ariel Marcovitch Date: Mon, 13 Sep 2021 19:45:14 +0300 Subject: [PATCH 082/587] kconfig: Create links to main menu items in search When one searches for a main menu item, links aren't created for it like with the rest of the symbols. This happens because we trace the item until we get to the rootmenu, but we don't include it in the path of the item. The rationale was probably that we don't want to show the main menu in the path of all items, because it is redundant. However, when an item has only the rootmenu in its path it should be included, because this way the user can jump to its location. Add a 'Main menu' entry in the 'Location:' section for the kconfig items. This makes the 'if (i > 0)' superfluous because each item with prompt will have at least one menu in its path. Signed-off-by: Ariel Marcovitch Signed-off-by: Masahiro Yamada --- scripts/kconfig/menu.c | 33 ++++++++++++++++++--------------- 1 file changed, 18 insertions(+), 15 deletions(-) diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c index 606ba8a63c24..3d6f7cba8846 100644 --- a/scripts/kconfig/menu.c +++ b/scripts/kconfig/menu.c @@ -728,7 +728,7 @@ static void get_prompt_str(struct gstr *r, struct property *prop, get_dep_str(r, prop->visible.expr, " Visible if: "); menu = prop->menu->parent; - for (i = 0; menu != &rootmenu && i < 8; menu = menu->parent) { + for (i = 0; menu && i < 8; menu = menu->parent) { bool accessible = menu_is_visible(menu); submenu[i++] = menu; @@ -758,21 +758,24 @@ static void get_prompt_str(struct gstr *r, struct property *prop, list_add_tail(&jump->entries, head); } - if (i > 0) { - str_printf(r, " Location:\n"); - for (j = 4; --i >= 0; j += 2) { - menu = submenu[i]; - if (jump && menu == location) - jump->offset = strlen(r->s); - str_printf(r, "%*c-> %s", j, ' ', - menu_get_prompt(menu)); - if (menu->sym) { - str_printf(r, " (%s [=%s])", menu->sym->name ? - menu->sym->name : "", - sym_get_string_value(menu->sym)); - } - str_append(r, "\n"); + str_printf(r, " Location:\n"); + for (j = 4; --i >= 0; j += 2) { + menu = submenu[i]; + if (jump && menu == location) + jump->offset = strlen(r->s); + + if (menu == &rootmenu) + /* The real rootmenu prompt is ugly */ + str_printf(r, "%*cMain menu", j, ' '); + else + str_printf(r, "%*c-> %s", j, ' ', menu_get_prompt(menu)); + + if (menu->sym) { + str_printf(r, " (%s [=%s])", menu->sym->name ? + menu->sym->name : "", + sym_get_string_value(menu->sym)); } + str_append(r, "\n"); } } From 0ba37e05c240c7b38e5a327a96f404798a8698ff Mon Sep 17 00:00:00 2001 From: William Cohen Date: Sun, 26 Sep 2021 20:51:15 -0400 Subject: [PATCH 083/587] perf annotate: Add riscv64 support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds basic arch initialization and instruction associate support for the riscv64 CPU architecture. Example output: $ perf annotate --stdio2 Samples: 122K of event 'task-clock:u', 4000 Hz, Event count (approx.): 30637250000, [percent: local period] strcmp() /usr/lib64/libc-2.32.so Percent Disassembly of section .text: 0000000000069a30 : __GI_strcmp(): const unsigned char *s2 = (const unsigned char *) p2; unsigned char c1, c2; do { c1 = (unsigned char) *s1++; 37.30 lbu a5,0(a0) c2 = (unsigned char) *s2++; 1.23 addi a1,a1,1 c1 = (unsigned char) *s1++; 18.68 addi a0,a0,1 c2 = (unsigned char) *s2++; 1.37 lbu a4,-1(a1) if (c1 == '\0') 18.71 ↓ beqz a5,18 return c1 - c2; } Signed-off-by: William Cohen Cc: Albert Ou Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Peter Zijlstra Cc: linux-riscv@lists.infradead.org Link: http://lore.kernel.org/lkml/20210927005115.610264-1-wcohen@redhat.com Signed-off-by: Arnaldo Carvalho de Melo --- .../perf/arch/riscv64/annotate/instructions.c | 34 +++++++++++++++++++ tools/perf/util/annotate.c | 5 +++ 2 files changed, 39 insertions(+) create mode 100644 tools/perf/arch/riscv64/annotate/instructions.c diff --git a/tools/perf/arch/riscv64/annotate/instructions.c b/tools/perf/arch/riscv64/annotate/instructions.c new file mode 100644 index 000000000000..869a0eb28953 --- /dev/null +++ b/tools/perf/arch/riscv64/annotate/instructions.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0 + +static +struct ins_ops *riscv64__associate_ins_ops(struct arch *arch, const char *name) +{ + struct ins_ops *ops = NULL; + + if (!strncmp(name, "jal", 3) || + !strncmp(name, "jr", 2) || + !strncmp(name, "call", 4)) + ops = &call_ops; + else if (!strncmp(name, "ret", 3)) + ops = &ret_ops; + else if (name[0] == 'j' || name[0] == 'b') + ops = &jump_ops; + else + return NULL; + + arch__associate_ins_ops(arch, name, ops); + + return ops; +} + +static +int riscv64__annotate_init(struct arch *arch, char *cpuid __maybe_unused) +{ + if (!arch->initialized) { + arch->associate_instruction_ops = riscv64__associate_ins_ops; + arch->initialized = true; + arch->objdump.comment_char = '#'; + } + + return 0; +} diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index b55f35485e43..4bab2273303a 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -151,6 +151,7 @@ static int arch__associate_ins_ops(struct arch* arch, const char *name, struct i #include "arch/mips/annotate/instructions.c" #include "arch/x86/annotate/instructions.c" #include "arch/powerpc/annotate/instructions.c" +#include "arch/riscv64/annotate/instructions.c" #include "arch/s390/annotate/instructions.c" #include "arch/sparc/annotate/instructions.c" @@ -191,6 +192,10 @@ static struct arch architectures[] = { .name = "powerpc", .init = powerpc__annotate_init, }, + { + .name = "riscv64", + .init = riscv64__annotate_init, + }, { .name = "s390", .init = s390__annotate_init, From 0e46c8307574a8e2dac8d7ba97e0f6f4bbee67a5 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 28 Sep 2021 14:15:01 -0300 Subject: [PATCH 084/587] perf jevents: Add __maybe_unused attribute to unused function arg The tools/perf/pmu-events/jevents.c file isn't being compiled with -Werror and -Wextra, which will be the case soon, so before we turn those compiler flags on, fix what it would flag. Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Like Xu Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Signed-off-by: Arnaldo Carvalho de Melo To: John Garry --- tools/perf/pmu-events/jevents.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index 6731b3cf0c2f..323e1dfe2436 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -45,6 +45,7 @@ #include /* getrlimit */ #include #include +#include #include #include "jsmn.h" #include "json.h" @@ -470,7 +471,7 @@ static void free_arch_std_events(void) } } -static int save_arch_std_events(void *data, struct json_event *je) +static int save_arch_std_events(void *data __maybe_unused, struct json_event *je) { struct event_struct *es; From 9a0a1417d3bb91dba9f95fef9771954ff72ede19 Mon Sep 17 00:00:00 2001 From: Pranay Sanghai Date: Sat, 18 Sep 2021 13:18:02 -0700 Subject: [PATCH 085/587] PCI: Tidy comments Make comments follow multi-line comment conventions. No functional change intended. Link: https://lore.kernel.org/r/YUZJenW2UCA4Qu0O@pranay-desktop Signed-off-by: Pranay Sanghai Signed-off-by: Bjorn Helgaas --- drivers/pci/setup-irq.c | 26 ++++++++++++++------------ 1 file changed, 14 insertions(+), 12 deletions(-) diff --git a/drivers/pci/setup-irq.c b/drivers/pci/setup-irq.c index 7129494754dd..cc7d26b015f3 100644 --- a/drivers/pci/setup-irq.c +++ b/drivers/pci/setup-irq.c @@ -8,7 +8,6 @@ * David Miller (davem@redhat.com) */ - #include #include #include @@ -28,25 +27,26 @@ void pci_assign_irq(struct pci_dev *dev) return; } - /* If this device is not on the primary bus, we need to figure out - which interrupt pin it will come in on. We know which slot it - will come in on 'cos that slot is where the bridge is. Each - time the interrupt line passes through a PCI-PCI bridge we must - apply the swizzle function. */ - + /* + * If this device is not on the primary bus, we need to figure out + * which interrupt pin it will come in on. We know which slot it + * will come in on because that slot is where the bridge is. Each + * time the interrupt line passes through a PCI-PCI bridge we must + * apply the swizzle function. + */ pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin); /* Cope with illegal. */ if (pin > 4) pin = 1; if (pin) { - /* Follow the chain of bridges, swizzling as we go. */ + /* Follow the chain of bridges, swizzling as we go. */ if (hbrg->swizzle_irq) slot = (*(hbrg->swizzle_irq))(dev, &pin); /* - * If a swizzling function is not used map_irq must - * ignore slot + * If a swizzling function is not used, map_irq() must + * ignore slot. */ irq = (*(hbrg->map_irq))(dev, slot, pin); if (irq == -1) @@ -56,7 +56,9 @@ void pci_assign_irq(struct pci_dev *dev) pci_dbg(dev, "assign IRQ: got %d\n", dev->irq); - /* Always tell the device, so the driver knows what is - the real IRQ to use; the device does not use it. */ + /* + * Always tell the device, so the driver knows what is the real IRQ + * to use; the device does not use it. + */ pci_write_config_byte(dev, PCI_INTERRUPT_LINE, irq); } From 4a87dea9e60fe10079f01e06a58c4f9dfb667940 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 17 Sep 2021 11:42:39 -0700 Subject: [PATCH 086/587] perf test: Workload test of metric and metricgroups Test every metric and metricgroup with 'true' as a workload. For metrics, check that we see the metric printed or get unsupported. If the 'true' workload executes too quickly retry with 'perf bench internals synthesize'. v3. Fix test condition (thanks to Paul A. Clarke ). Add a fallback case of a larger workload so that we don't ignore "". v2. Switched the workload to something faster. Signed-off-by: Ian Rogers Reviewed-by: John Garry Cc: Alexander Shishkin Cc: Jin Yao Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Paul Clarke Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lore.kernel.org/lkml/20210917184240.2181186-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../perf/tests/shell/stat_all_metricgroups.sh | 12 ++++++++++ tools/perf/tests/shell/stat_all_metrics.sh | 22 +++++++++++++++++++ 2 files changed, 34 insertions(+) create mode 100755 tools/perf/tests/shell/stat_all_metricgroups.sh create mode 100755 tools/perf/tests/shell/stat_all_metrics.sh diff --git a/tools/perf/tests/shell/stat_all_metricgroups.sh b/tools/perf/tests/shell/stat_all_metricgroups.sh new file mode 100755 index 000000000000..de24d374ce24 --- /dev/null +++ b/tools/perf/tests/shell/stat_all_metricgroups.sh @@ -0,0 +1,12 @@ +#!/bin/sh +# perf all metricgroups test +# SPDX-License-Identifier: GPL-2.0 + +set -e + +for m in $(perf list --raw-dump metricgroups); do + echo "Testing $m" + perf stat -M "$m" true +done + +exit 0 diff --git a/tools/perf/tests/shell/stat_all_metrics.sh b/tools/perf/tests/shell/stat_all_metrics.sh new file mode 100755 index 000000000000..7f4ba3cad632 --- /dev/null +++ b/tools/perf/tests/shell/stat_all_metrics.sh @@ -0,0 +1,22 @@ +#!/bin/sh +# perf all metrics test +# SPDX-License-Identifier: GPL-2.0 + +set -e + +for m in $(perf list --raw-dump metrics); do + echo "Testing $m" + result=$(perf stat -M "$m" true 2>&1) + if [[ ! "$result" =~ "$m" ]] && [[ ! "$result" =~ "" ]]; then + # We failed to see the metric and the events are support. Possibly the + # workload was too small so retry with something longer. + result=$(perf stat -M "$m" perf bench internals synthesize 2>&1) + if [[ ! "$result" =~ "$m" ]]; then + echo "Metric '$m' not printed in:" + echo "$result" + exit 1 + fi + fi +done + +exit 0 From 3d5ac9effcc640d5d66bc6d833e1dcc9faa279aa Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 17 Sep 2021 11:42:40 -0700 Subject: [PATCH 087/587] perf test: Workload test of all PMUs Iterate over the list of PMUs and run the 'true' workload on them. If the event isn't printed then run the large 'perf bench internals synthesize' workload and check the event is counted. On a Skylake this test takes 1m15s mainly running the 'true' workload. Suggested-by: John Garry Signed-off-by: Ian Rogers Reviewed-by: John Garry Cc: Alexander Shishkin Cc: Jin Yao Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Paul Clarke Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lore.kernel.org/lkml/20210917184240.2181186-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/stat_all_pmu.sh | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) create mode 100755 tools/perf/tests/shell/stat_all_pmu.sh diff --git a/tools/perf/tests/shell/stat_all_pmu.sh b/tools/perf/tests/shell/stat_all_pmu.sh new file mode 100755 index 000000000000..2de7fd0394fd --- /dev/null +++ b/tools/perf/tests/shell/stat_all_pmu.sh @@ -0,0 +1,22 @@ +#!/bin/sh +# perf all PMU test +# SPDX-License-Identifier: GPL-2.0 + +set -e + +for p in $(perf list --raw-dump pmu); do + echo "Testing $p" + result=$(perf stat -e "$p" true 2>&1) + if [[ ! "$result" =~ "$p" ]] && [[ ! "$result" =~ "" ]]; then + # We failed to see the event and it is supported. Possibly the workload was + # too small so retry with something longer. + result=$(perf stat -e "$p" perf bench internals synthesize 2>&1) + if [[ ! "$result" =~ "$p" ]]; then + echo "Event '$p' not printed in:" + echo "$result" + exit 1 + fi + fi +done + +exit 0 From b758a61b391fb5ed749f4848f444d8223ae0a324 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 22 Sep 2021 17:10:21 -0700 Subject: [PATCH 088/587] perf tools: Enable libtracefs dynamic linking Currently libtracefs isn't used by perf, but there are potential improvements by using it as identified Steven Rostedt's e-mail: https://lore.kernel.org/lkml/20210610154759.1ef958f0@oasis.local.home/ This change is modelled on the dynamic libtraceevent patch by Michael Petlan: https://lore.kernel.org/linux-perf-users/20210428092023.4009-1-mpetlan@redhat.com/ v3. Adds file missed in v1 and v2 spotted by Jiri Olsa. Signed-off-by: Ian Rogers Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Steven Rostedt (VMware) Cc: Tzvetomir Stoyanov (VMware) Cc: linux-trace-devel@vger.kernel.org Link: http://lore.kernel.org/lkml/20210923001024.550263-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/build/Makefile.feature | 1 + tools/build/feature/Makefile | 4 ++++ tools/build/feature/test-libtracefs.c | 10 ++++++++++ tools/perf/Makefile.config | 9 +++++++++ tools/perf/Makefile.perf | 2 ++ 5 files changed, 26 insertions(+) create mode 100644 tools/build/feature/test-libtracefs.c diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 3dd2f68366f9..45a9a59828c3 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -52,6 +52,7 @@ FEATURE_TESTS_BASIC := \ libslang \ libslang-include-subdir \ libtraceevent \ + libtracefs \ libcrypto \ libunwind \ pthread-attr-setaffinity-np \ diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index eff55d287db1..d024b5204ba0 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -36,6 +36,7 @@ FILES= \ test-libslang.bin \ test-libslang-include-subdir.bin \ test-libtraceevent.bin \ + test-libtracefs.bin \ test-libcrypto.bin \ test-libunwind.bin \ test-libunwind-debug-frame.bin \ @@ -199,6 +200,9 @@ $(OUTPUT)test-libslang-include-subdir.bin: $(OUTPUT)test-libtraceevent.bin: $(BUILD) -ltraceevent +$(OUTPUT)test-libtracefs.bin: + $(BUILD) -ltracefs + $(OUTPUT)test-libcrypto.bin: $(BUILD) -lcrypto diff --git a/tools/build/feature/test-libtracefs.c b/tools/build/feature/test-libtracefs.c new file mode 100644 index 000000000000..8eff16c0c10b --- /dev/null +++ b/tools/build/feature/test-libtracefs.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 +#include + +int main(void) +{ + struct tracefs_instance *inst = tracefs_instance_create("dummy"); + + tracefs_instance_destroy(inst); + return 0; +} diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 446180401e26..00ec900ddbca 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -1098,6 +1098,15 @@ ifdef LIBTRACEEVENT_DYNAMIC endif endif +ifdef LIBTRACEFS_DYNAMIC + $(call feature_check,libtracefs) + ifeq ($(feature-libtracefs), 1) + EXTLIBS += -ltracefs + else + dummy := $(error Error: No libtracefs devel library found, please install libtracefs-dev); + endif +endif + # Among the variables below, these: # perfexecdir # perf_include_dir diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index e04313c4d840..7df13e74450c 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -130,6 +130,8 @@ include ../scripts/utilities.mak # # Define LIBTRACEEVENT_DYNAMIC to enable libtraceevent dynamic linking # +# Define LIBTRACEFS_DYNAMIC to enable libtracefs dynamic linking +# # As per kernel Makefile, avoid funny character set dependencies unexport LC_ALL From 569715164ba2125cf5014aa6de7154ebdb95fef4 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 22 Sep 2021 17:10:22 -0700 Subject: [PATCH 089/587] perf tools: Add define for libtraceevent version The definition is derived from pkg-config as discussed in: https://lore.kernel.org/lkml/20210610155915.20a252d3@oasis.local.home/ The definition is computed using expr rather than passed to be computed in C code, this avoids complications with quote in the variable expansions. For example see the target python/perf.so in Makefile.perf. Signed-off-by: Ian Rogers Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Steven Rostedt (VMware) Cc: Tzvetomir Stoyanov (VMware) Cc: linux-trace-devel@vger.kernel.org Link: http://lore.kernel.org/lkml/20210923001024.550263-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 00ec900ddbca..2001c315f0db 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -1093,6 +1093,12 @@ ifdef LIBTRACEEVENT_DYNAMIC $(call feature_check,libtraceevent) ifeq ($(feature-libtraceevent), 1) EXTLIBS += -ltraceevent + LIBTRACEEVENT_VERSION := $(shell $(PKG_CONFIG) --modversion libtraceevent) + LIBTRACEEVENT_VERSION_1 := $(word 1, $(subst ., ,$(LIBTRACEEVENT_VERSION))) + LIBTRACEEVENT_VERSION_2 := $(word 2, $(subst ., ,$(LIBTRACEEVENT_VERSION))) + LIBTRACEEVENT_VERSION_3 := $(word 3, $(subst ., ,$(LIBTRACEEVENT_VERSION))) + LIBTRACEEVENT_VERSION_CPP := $(shell expr $(LIBTRACEEVENT_VERSION_1) \* 255 \* 255 + $(LIBTRACEEVENT_VERSION_2) \* 255 + $(LIBTRACEEVENT_VERSION_3)) + CFLAGS += -DLIBTRACEEVENT_VERSION=$(LIBTRACEEVENT_VERSION_CPP) else dummy := $(error Error: No libtraceevent devel library found, please install libtraceevent-devel); endif From 359cad09e40bedf927ea6046d27ccf977c83b71a Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 22 Sep 2021 17:10:23 -0700 Subject: [PATCH 090/587] perf tools: Add define for libtracefs version This will allow version specific support of libtracefs. Signed-off-by: Ian Rogers Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Steven Rostedt (VMware) Cc: Tzvetomir Stoyanov (VMware) Cc: linux-trace-devel@vger.kernel.org Link: http://lore.kernel.org/lkml/20210923001024.550263-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 2001c315f0db..0ae2e3d8b832 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -1108,6 +1108,12 @@ ifdef LIBTRACEFS_DYNAMIC $(call feature_check,libtracefs) ifeq ($(feature-libtracefs), 1) EXTLIBS += -ltracefs + LIBTRACEFS_VERSION := $(shell $(PKG_CONFIG) --modversion libtracefs) + LIBTRACEFS_VERSION_1 := $(word 1, $(subst ., ,$(LIBTRACEFS_VERSION))) + LIBTRACEFS_VERSION_2 := $(word 2, $(subst ., ,$(LIBTRACEFS_VERSION))) + LIBTRACEFS_VERSION_3 := $(word 3, $(subst ., ,$(LIBTRACEFS_VERSION))) + LIBTRACEFS_VERSION_CPP := $(shell expr $(LIBTRACEFS_VERSION_1) \* 255 \* 255 + $(LIBTRACEFS_VERSION_2) \* 255 + $(LIBTRACEFS_VERSION_3)) + CFLAGS += -DLIBTRACEFS_VERSION=$(LIBTRACEFS_VERSION_CPP) else dummy := $(error Error: No libtracefs devel library found, please install libtracefs-dev); endif From 08efcb4a638d260ef7fcbae64ecf7ceceb3f1841 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 22 Sep 2021 17:10:24 -0700 Subject: [PATCH 091/587] libtraceevent: Increase libtraceevent logging when verbose libtraceevent has added more levels of debug printout and with changes like: https://lore.kernel.org/linux-trace-devel/20210507095022.1079364-3-tz.stoyanov@gmail.com previously generated output like "registering plugin" is no longer displayed. This change makes it so that if perf's verbose debug output is enabled then the debug and info libtraceevent messages can be displayed. The code is conditionally enabled based on the libtraceevent version as discussed in the RFC: https://lore.kernel.org/lkml/20210610060643.595673-1-irogers@google.com/ v2. Is a rebase and handles the case of building without LIBTRACEEVENT_DYNAMIC. Signed-off-by: Ian Rogers Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Steven Rostedt (VMware) Cc: Tzvetomir Stoyanov (VMware) Cc: linux-trace-devel@vger.kernel.org Link: http://lore.kernel.org/lkml/20210923001024.550263-4-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/debug.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 2c06abf6dcd2..c7a9fa0ffae9 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -24,6 +24,16 @@ #include "util/parse-sublevel-options.h" #include +#include + +#define MAKE_LIBTRACEEVENT_VERSION(a, b, c) ((a)*255*255+(b)*255+(c)) +#ifndef LIBTRACEEVENT_VERSION +/* + * If LIBTRACEEVENT_VERSION wasn't computed then set to version 1.1.0 that ships + * with the Linux kernel tools. + */ +#define LIBTRACEEVENT_VERSION MAKE_LIBTRACEEVENT_VERSION(1, 1, 0) +#endif int verbose; int debug_peo_args; @@ -228,6 +238,15 @@ int perf_debug_option(const char *str) /* Allow only verbose value in range (0, 10), otherwise set 0. */ verbose = (verbose < 0) || (verbose > 10) ? 0 : verbose; +#if MAKE_LIBTRACEEVENT_VERSION(1, 3, 0) <= LIBTRACEEVENT_VERSION + if (verbose == 1) + tep_set_loglevel(TEP_LOG_INFO); + else if (verbose == 2) + tep_set_loglevel(TEP_LOG_DEBUG); + else if (verbose >= 3) + tep_set_loglevel(TEP_LOG_ALL); +#endif + return 0; } From 4f9d4f8aa7328068a2f25cfb3d1d04c1b6fa54ac Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 16 Sep 2021 20:34:21 +0800 Subject: [PATCH 092/587] perf parse-events: Set numeric term config For numeric terms, the config field may be NULL as it is not set from the l+y parsing. Fix by setting the term config from the term type name. Also fix up the pmu-events test to set the alias strings to set the period term properly, and fix up parse-events test to check the term config string. Signed-off-by: John Garry Acked-by: Ian Rogers Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Mathieu Poirier Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Shaokun Zhang Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Cc: linuxarm@huawei.com Cc: liuqi115@huawei.com Link: https://lore.kernel.org/r/1631795665-240946-2-git-send-email-john.garry@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/parse-events.c | 8 ++++---- tools/perf/tests/pmu-events.c | 6 +++--- tools/perf/util/parse-events.c | 2 +- 3 files changed, 8 insertions(+), 8 deletions(-) diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index fd3556cc9ad4..8875e388563e 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -605,7 +605,7 @@ static int test__checkterms_simple(struct list_head *terms) TEST_ASSERT_VAL("wrong type val", term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); TEST_ASSERT_VAL("wrong val", term->val.num == 10); - TEST_ASSERT_VAL("wrong config", !term->config); + TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "config")); /* config1 */ term = list_entry(term->list.next, struct parse_events_term, list); @@ -614,7 +614,7 @@ static int test__checkterms_simple(struct list_head *terms) TEST_ASSERT_VAL("wrong type val", term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); TEST_ASSERT_VAL("wrong val", term->val.num == 1); - TEST_ASSERT_VAL("wrong config", !term->config); + TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "config1")); /* config2=3 */ term = list_entry(term->list.next, struct parse_events_term, list); @@ -623,7 +623,7 @@ static int test__checkterms_simple(struct list_head *terms) TEST_ASSERT_VAL("wrong type val", term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); TEST_ASSERT_VAL("wrong val", term->val.num == 3); - TEST_ASSERT_VAL("wrong config", !term->config); + TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "config2")); /* umask=1*/ term = list_entry(term->list.next, struct parse_events_term, list); @@ -661,7 +661,7 @@ static int test__checkterms_simple(struct list_head *terms) TEST_ASSERT_VAL("wrong type val", term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); TEST_ASSERT_VAL("wrong val", term->val.num == 0xead); - TEST_ASSERT_VAL("wrong config", !term->config); + TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "config")); return 0; } diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index 43743cf719ef..8c5a6ba1cb14 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -67,7 +67,7 @@ static const struct perf_pmu_test_event segment_reg_loads_any = { .desc = "Number of segment register loads", .topic = "other", }, - .alias_str = "umask=0x80,(null)=0x30d40,event=0x6", + .alias_str = "umask=0x80,period=0x30d40,event=0x6", .alias_long_desc = "Number of segment register loads", }; @@ -78,7 +78,7 @@ static const struct perf_pmu_test_event dispatch_blocked_any = { .desc = "Memory cluster signals to block micro-op dispatch for any reason", .topic = "other", }, - .alias_str = "umask=0x20,(null)=0x30d40,event=0x9", + .alias_str = "umask=0x20,period=0x30d40,event=0x9", .alias_long_desc = "Memory cluster signals to block micro-op dispatch for any reason", }; @@ -89,7 +89,7 @@ static const struct perf_pmu_test_event eist_trans = { .desc = "Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions", .topic = "other", }, - .alias_str = "umask=0,(null)=0x30d40,event=0x3a", + .alias_str = "umask=0,period=0x30d40,event=0x3a", .alias_long_desc = "Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions", }; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 067f830dea4b..1acac3e13b32 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -3141,7 +3141,7 @@ int parse_events_term__num(struct parse_events_term **term, struct parse_events_term temp = { .type_val = PARSE_EVENTS__TERM_TYPE_NUM, .type_term = type_term, - .config = config, + .config = config ? : strdup(config_term_names[type_term]), .no_value = no_value, .err_term = loc_term ? loc_term->first_column : 0, .err_val = loc_val ? loc_val->first_column : 0, From d60bad10c4ae42ef96b5b7dfd5924c54f3f257a6 Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 16 Sep 2021 20:34:22 +0800 Subject: [PATCH 093/587] perf jevents: Support ConfigCode Some PMUs use "config=XXX" for eventcodes, like: more /sys/bus/event_source/devices/hisi_sccl1_ddrc3/events/act_cmd config=0x5 However jevents would give an alias with .event field "event=0x5" for this event. This is handled without issue by the parse events code, but the pmu alias code gets a bit confused, as it warns about assigning "event=0x5" over "config=0x5" in perf_pmu_assign_str() when merging aliases: ./perf stat -v -e act_cmd ... alias act_cmd differs in field 'value' ... To make things a bit more straightforward, allow jevents to support "config=XXX" as well, by supporting a "ConfigCode" field. Signed-off-by: John Garry Acked-by: Ian Rogers Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Mathieu Poirier Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Shaokun Zhang Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Cc: linuxarm@huawei.com Cc: liuqi115@huawei.com Link: https://lore.kernel.org/r/1631795665-240946-3-git-send-email-john.garry@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/jevents.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index 323e1dfe2436..19497e4f8a86 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -576,10 +576,12 @@ static int json_events(const char *fn, struct json_event je = {}; char *arch_std = NULL; unsigned long long eventcode = 0; + unsigned long long configcode = 0; struct msrmap *msr = NULL; jsmntok_t *msrval = NULL; jsmntok_t *precise = NULL; jsmntok_t *obj = tok++; + bool configcode_present = false; EXPECT(obj->type == JSMN_OBJECT, obj, "expected object"); for (j = 0; j < obj->size; j += 2) { @@ -602,6 +604,12 @@ static int json_events(const char *fn, addfield(map, &code, "", "", val); eventcode |= strtoul(code, NULL, 0); free(code); + } else if (json_streq(map, field, "ConfigCode")) { + char *code = NULL; + addfield(map, &code, "", "", val); + configcode |= strtoul(code, NULL, 0); + free(code); + configcode_present = true; } else if (json_streq(map, field, "ExtSel")) { char *code = NULL; addfield(map, &code, "", "", val); @@ -683,7 +691,10 @@ static int json_events(const char *fn, addfield(map, &extra_desc, " ", "(Precise event)", NULL); } - snprintf(buf, sizeof buf, "event=%#llx", eventcode); + if (configcode_present) + snprintf(buf, sizeof buf, "config=%#llx", configcode); + else + snprintf(buf, sizeof buf, "event=%#llx", eventcode); addfield(map, &event, ",", buf, NULL); if (je.desc && extra_desc) addfield(map, &je.desc, " ", extra_desc, NULL); From 56be05103a408b7f56c5e75717b2b23a5adf1ddb Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 16 Sep 2021 20:34:23 +0800 Subject: [PATCH 094/587] perf test: Verify more event members in pmu-events test Function compare_pmu_events() does not compare all struct pmu-events members, so add tests for missing members "name", "event", "aggr_mod", "event", "metric_constraint", and "metric_group", and re-order the tests to match current struct pmu-events member ordering. Also fix uncore_hisi_l3c_rd_hit_cpipe.event member, now that we're actually testing it. Signed-off-by: John Garry Acked-by: Ian Rogers Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Mathieu Poirier Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Shaokun Zhang Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Cc: linuxarm@huawei.com Cc: liuqi115@huawei.com Link: https://lore.kernel.org/r/1631795665-240946-4-git-send-email-john.garry@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/pmu-events.c | 50 ++++++++++++++++++++++++++++------- 1 file changed, 40 insertions(+), 10 deletions(-) diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index 8c5a6ba1cb14..adfc17f51c7b 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -146,7 +146,7 @@ static const struct perf_pmu_test_event unc_cbo_xsnp_response_miss_eviction = { static const struct perf_pmu_test_event uncore_hisi_l3c_rd_hit_cpipe = { .event = { .name = "uncore_hisi_l3c.rd_hit_cpipe", - .event = "event=0x2", + .event = "event=0x7", .desc = "Total read hits. Unit: hisi_sccl,l3c ", .topic = "uncore", .long_desc = "Total read hits", @@ -255,6 +255,24 @@ static struct pmu_event *__test_pmu_get_sys_events_table(void) static int compare_pmu_events(struct pmu_event *e1, const struct pmu_event *e2) { + if (!is_same(e1->name, e2->name)) { + pr_debug2("testing event e1 %s: mismatched name string, %s vs %s\n", + e1->name, e1->name, e2->name); + return -1; + } + + if (!is_same(e1->compat, e2->compat)) { + pr_debug2("testing event e1 %s: mismatched compat string, %s vs %s\n", + e1->name, e1->compat, e2->compat); + return -1; + } + + if (!is_same(e1->event, e2->event)) { + pr_debug2("testing event e1 %s: mismatched event, %s vs %s\n", + e1->name, e1->event, e2->event); + return -1; + } + if (!is_same(e1->desc, e2->desc)) { pr_debug2("testing event e1 %s: mismatched desc, %s vs %s\n", e1->name, e1->desc, e2->desc); @@ -273,6 +291,12 @@ static int compare_pmu_events(struct pmu_event *e1, const struct pmu_event *e2) return -1; } + if (!is_same(e1->pmu, e2->pmu)) { + pr_debug2("testing event e1 %s: mismatched pmu string, %s vs %s\n", + e1->name, e1->pmu, e2->pmu); + return -1; + } + if (!is_same(e1->unit, e2->unit)) { pr_debug2("testing event e1 %s: mismatched unit, %s vs %s\n", e1->name, e1->unit, e2->unit); @@ -285,6 +309,12 @@ static int compare_pmu_events(struct pmu_event *e1, const struct pmu_event *e2) return -1; } + if (!is_same(e1->aggr_mode, e2->aggr_mode)) { + pr_debug2("testing event e1 %s: mismatched aggr_mode, %s vs %s\n", + e1->name, e1->aggr_mode, e2->aggr_mode); + return -1; + } + if (!is_same(e1->metric_expr, e2->metric_expr)) { pr_debug2("testing event e1 %s: mismatched metric_expr, %s vs %s\n", e1->name, e1->metric_expr, e2->metric_expr); @@ -297,21 +327,21 @@ static int compare_pmu_events(struct pmu_event *e1, const struct pmu_event *e2) return -1; } + if (!is_same(e1->metric_group, e2->metric_group)) { + pr_debug2("testing event e1 %s: mismatched metric_group, %s vs %s\n", + e1->name, e1->metric_group, e2->metric_group); + return -1; + } + if (!is_same(e1->deprecated, e2->deprecated)) { pr_debug2("testing event e1 %s: mismatched deprecated, %s vs %s\n", e1->name, e1->deprecated, e2->deprecated); return -1; } - if (!is_same(e1->pmu, e2->pmu)) { - pr_debug2("testing event e1 %s: mismatched pmu string, %s vs %s\n", - e1->name, e1->pmu, e2->pmu); - return -1; - } - - if (!is_same(e1->compat, e2->compat)) { - pr_debug2("testing event e1 %s: mismatched compat string, %s vs %s\n", - e1->name, e1->compat, e2->compat); + if (!is_same(e1->metric_constraint, e2->metric_constraint)) { + pr_debug2("testing event e1 %s: mismatched metric_constant, %s vs %s\n", + e1->name, e1->metric_constraint, e2->metric_constraint); return -1; } From b8b350afaa4bd007261c1ce367123444f6953a42 Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 16 Sep 2021 20:34:24 +0800 Subject: [PATCH 095/587] perf test: Add pmu-event test for event described as "config=" Add a new test event for a system event whose event member is in form "config=". Signed-off-by: John Garry Acked-by: Ian Rogers Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Mathieu Poirier Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Shaokun Zhang Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Cc: linuxarm@huawei.com Cc: liuqi115@huawei.com Link: https://lore.kernel.org/r/1631795665-240946-5-git-send-email-john.garry@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/test/test_soc/sys/uncore.json | 7 ++++++ tools/perf/tests/pmu-events.c | 25 +++++++++++++++++++ 2 files changed, 32 insertions(+) diff --git a/tools/perf/pmu-events/arch/test/test_soc/sys/uncore.json b/tools/perf/pmu-events/arch/test/test_soc/sys/uncore.json index 0f681a6e10ea..c7e7528db315 100644 --- a/tools/perf/pmu-events/arch/test/test_soc/sys/uncore.json +++ b/tools/perf/pmu-events/arch/test/test_soc/sys/uncore.json @@ -6,4 +6,11 @@ "Unit": "sys_ddr_pmu", "Compat": "v8" }, + { + "BriefDescription": "ccn read-cycles event", + "ConfigCode": "0x2c", + "EventName": "sys_ccn_pmu.read_cycles", + "Unit": "sys_ccn_pmu", + "Compat": "0x01" + } ] diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index adfc17f51c7b..f14266a4c513 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -208,8 +208,23 @@ static const struct perf_pmu_test_event sys_ddr_pmu_write_cycles = { .matching_pmu = "uncore_sys_ddr_pmu", }; +static const struct perf_pmu_test_event sys_ccn_pmu_read_cycles = { + .event = { + .name = "sys_ccn_pmu.read_cycles", + .event = "config=0x2c", + .desc = "ccn read-cycles event. Unit: uncore_sys_ccn_pmu ", + .topic = "uncore", + .pmu = "uncore_sys_ccn_pmu", + .compat = "0x01", + }, + .alias_str = "config=0x2c", + .alias_long_desc = "ccn read-cycles event. Unit: uncore_sys_ccn_pmu ", + .matching_pmu = "uncore_sys_ccn_pmu", +}; + static const struct perf_pmu_test_event *sys_events[] = { &sys_ddr_pmu_write_cycles, + &sys_ccn_pmu_read_cycles, NULL }; @@ -677,6 +692,16 @@ static struct perf_pmu_test_pmu test_pmus[] = { &sys_ddr_pmu_write_cycles, }, }, + { + .pmu = { + .name = (char *)"uncore_sys_ccn_pmu4", + .is_uncore = 1, + .id = (char *)"0x01", + }, + .aliases = { + &sys_ccn_pmu_read_cycles, + }, + }, }; /* Test that aliases generated are as expected */ From c801612875909cbce823dfc276c58c7155f95b01 Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 16 Sep 2021 20:34:25 +0800 Subject: [PATCH 096/587] perf vendor events arm64: Revise hip08 uncore events To improve alias matching, remove the PMU name prefix from the EventName. This will mean that the pmu code will merge aliases, such that we no longer get a huge list of per-PMU events - see perf_pmu_merge_alias(). Also make the following associated changes: - Use "ConfigCode" rather than "EventCode", so the pmu code is not so disagreeable about inconsistent event codes - Add undocumented HHA event codes to allow alias merging (for those events) Signed-off-by: John Garry Acked-by: Ian Rogers Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Mathieu Poirier Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Shaokun Zhang Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Cc: linuxarm@huawei.com Cc: liuqi115@huawei.com Link: https://lore.kernel.org/r/1631795665-240946-6-git-send-email-john.garry@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arm64/hisilicon/hip08/uncore-ddrc.json | 32 ++--- .../arm64/hisilicon/hip08/uncore-hha.json | 120 +++++++++++++++--- .../arm64/hisilicon/hip08/uncore-l3c.json | 52 ++++---- 3 files changed, 142 insertions(+), 62 deletions(-) diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json index 61514d38601b..2b3cb55df288 100644 --- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json +++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json @@ -1,56 +1,56 @@ [ { - "EventCode": "0x00", - "EventName": "uncore_hisi_ddrc.flux_wr", + "ConfigCode": "0x00", + "EventName": "flux_wr", "BriefDescription": "DDRC total write operations", "PublicDescription": "DDRC total write operations", "Unit": "hisi_sccl,ddrc" }, { - "EventCode": "0x01", - "EventName": "uncore_hisi_ddrc.flux_rd", + "ConfigCode": "0x01", + "EventName": "flux_rd", "BriefDescription": "DDRC total read operations", "PublicDescription": "DDRC total read operations", "Unit": "hisi_sccl,ddrc" }, { - "EventCode": "0x02", - "EventName": "uncore_hisi_ddrc.flux_wcmd", + "ConfigCode": "0x02", + "EventName": "flux_wcmd", "BriefDescription": "DDRC write commands", "PublicDescription": "DDRC write commands", "Unit": "hisi_sccl,ddrc" }, { - "EventCode": "0x03", - "EventName": "uncore_hisi_ddrc.flux_rcmd", + "ConfigCode": "0x03", + "EventName": "flux_rcmd", "BriefDescription": "DDRC read commands", "PublicDescription": "DDRC read commands", "Unit": "hisi_sccl,ddrc" }, { - "EventCode": "0x04", - "EventName": "uncore_hisi_ddrc.pre_cmd", + "ConfigCode": "0x04", + "EventName": "pre_cmd", "BriefDescription": "DDRC precharge commands", "PublicDescription": "DDRC precharge commands", "Unit": "hisi_sccl,ddrc" }, { - "EventCode": "0x05", - "EventName": "uncore_hisi_ddrc.act_cmd", + "ConfigCode": "0x05", + "EventName": "act_cmd", "BriefDescription": "DDRC active commands", "PublicDescription": "DDRC active commands", "Unit": "hisi_sccl,ddrc" }, { - "EventCode": "0x06", - "EventName": "uncore_hisi_ddrc.rnk_chg", + "ConfigCode": "0x06", + "EventName": "rnk_chg", "BriefDescription": "DDRC rank commands", "PublicDescription": "DDRC rank commands", "Unit": "hisi_sccl,ddrc" }, { - "EventCode": "0x07", - "EventName": "uncore_hisi_ddrc.rw_chg", + "ConfigCode": "0x07", + "EventName": "rw_chg", "BriefDescription": "DDRC read and write changes", "PublicDescription": "DDRC read and write changes", "Unit": "hisi_sccl,ddrc" diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json index ada86782933f..9a7ec7af2060 100644 --- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json +++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json @@ -1,72 +1,152 @@ [ { - "EventCode": "0x00", - "EventName": "uncore_hisi_hha.rx_ops_num", + "ConfigCode": "0x00", + "EventName": "rx_ops_num", "BriefDescription": "The number of all operations received by the HHA", "PublicDescription": "The number of all operations received by the HHA", "Unit": "hisi_sccl,hha" }, { - "EventCode": "0x01", - "EventName": "uncore_hisi_hha.rx_outer", + "ConfigCode": "0x01", + "EventName": "rx_outer", "BriefDescription": "The number of all operations received by the HHA from another socket", "PublicDescription": "The number of all operations received by the HHA from another socket", "Unit": "hisi_sccl,hha" }, { - "EventCode": "0x02", - "EventName": "uncore_hisi_hha.rx_sccl", + "ConfigCode": "0x02", + "EventName": "rx_sccl", "BriefDescription": "The number of all operations received by the HHA from another SCCL in this socket", "PublicDescription": "The number of all operations received by the HHA from another SCCL in this socket", "Unit": "hisi_sccl,hha" }, { - "EventCode": "0x03", - "EventName": "uncore_hisi_hha.rx_ccix", + "ConfigCode": "0x03", + "EventName": "rx_ccix", "BriefDescription": "Count of the number of operations that HHA has received from CCIX", "PublicDescription": "Count of the number of operations that HHA has received from CCIX", "Unit": "hisi_sccl,hha" }, { - "EventCode": "0x1c", - "EventName": "uncore_hisi_hha.rd_ddr_64b", + "ConfigCode": "0x4", + "EventName": "rx_wbi", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x5", + "EventName": "rx_wbip", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x11", + "EventName": "rx_wtistash", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x1c", + "EventName": "rd_ddr_64b", "BriefDescription": "The number of read operations sent by HHA to DDRC which size is 64 bytes", "PublicDescription": "The number of read operations sent by HHA to DDRC which size is 64bytes", "Unit": "hisi_sccl,hha" }, { - "EventCode": "0x1d", - "EventName": "uncore_hisi_hha.wr_ddr_64b", + "ConfigCode": "0x1d", + "EventName": "wr_ddr_64b", "BriefDescription": "The number of write operations sent by HHA to DDRC which size is 64 bytes", "PublicDescription": "The number of write operations sent by HHA to DDRC which size is 64 bytes", "Unit": "hisi_sccl,hha" }, { - "EventCode": "0x1e", - "EventName": "uncore_hisi_hha.rd_ddr_128b", + "ConfigCode": "0x1e", + "EventName": "rd_ddr_128b", "BriefDescription": "The number of read operations sent by HHA to DDRC which size is 128 bytes", "PublicDescription": "The number of read operations sent by HHA to DDRC which size is 128 bytes", "Unit": "hisi_sccl,hha" }, { - "EventCode": "0x1f", - "EventName": "uncore_hisi_hha.wr_ddr_128b", + "ConfigCode": "0x1f", + "EventName": "wr_ddr_128b", "BriefDescription": "The number of write operations sent by HHA to DDRC which size is 128 bytes", "PublicDescription": "The number of write operations sent by HHA to DDRC which size is 128 bytes", "Unit": "hisi_sccl,hha" }, { - "EventCode": "0x20", - "EventName": "uncore_hisi_hha.spill_num", + "ConfigCode": "0x20", + "EventName": "spill_num", "BriefDescription": "Count of the number of spill operations that the HHA has sent", "PublicDescription": "Count of the number of spill operations that the HHA has sent", "Unit": "hisi_sccl,hha" }, { - "EventCode": "0x21", - "EventName": "uncore_hisi_hha.spill_success", + "ConfigCode": "0x21", + "EventName": "spill_success", "BriefDescription": "Count of the number of successful spill operations that the HHA has sent", "PublicDescription": "Count of the number of successful spill operations that the HHA has sent", "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x23", + "EventName": "bi_num", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x32", + "EventName": "mediated_num", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x33", + "EventName": "tx_snp_num", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x34", + "EventName": "tx_snp_outer", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x35", + "EventName": "tx_snp_ccix", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x38", + "EventName": "rx_snprspdata", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x3c", + "EventName": "rx_snprsp_outer", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x40", + "EventName": "sdir-lookup", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x41", + "EventName": "edir-lookup", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x42", + "EventName": "sdir-hit", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x43", + "EventName": "edir-hit", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x4c", + "EventName": "sdir-home-migrate", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x4d", + "EventName": "edir-home-migrate", + "Unit": "hisi_sccl,hha" } ] diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json index 67ab19e8cf3a..e3479b65be9a 100644 --- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json +++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json @@ -1,91 +1,91 @@ [ { - "EventCode": "0x00", - "EventName": "uncore_hisi_l3c.rd_cpipe", + "ConfigCode": "0x00", + "EventName": "rd_cpipe", "BriefDescription": "Total read accesses", "PublicDescription": "Total read accesses", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x01", - "EventName": "uncore_hisi_l3c.wr_cpipe", + "ConfigCode": "0x01", + "EventName": "wr_cpipe", "BriefDescription": "Total write accesses", "PublicDescription": "Total write accesses", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x02", - "EventName": "uncore_hisi_l3c.rd_hit_cpipe", + "ConfigCode": "0x02", + "EventName": "rd_hit_cpipe", "BriefDescription": "Total read hits", "PublicDescription": "Total read hits", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x03", - "EventName": "uncore_hisi_l3c.wr_hit_cpipe", + "ConfigCode": "0x03", + "EventName": "wr_hit_cpipe", "BriefDescription": "Total write hits", "PublicDescription": "Total write hits", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x04", - "EventName": "uncore_hisi_l3c.victim_num", + "ConfigCode": "0x04", + "EventName": "victim_num", "BriefDescription": "l3c precharge commands", "PublicDescription": "l3c precharge commands", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x20", - "EventName": "uncore_hisi_l3c.rd_spipe", + "ConfigCode": "0x20", + "EventName": "rd_spipe", "BriefDescription": "Count of the number of read lines that come from this cluster of CPU core in spipe", "PublicDescription": "Count of the number of read lines that come from this cluster of CPU core in spipe", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x21", - "EventName": "uncore_hisi_l3c.wr_spipe", + "ConfigCode": "0x21", + "EventName": "wr_spipe", "BriefDescription": "Count of the number of write lines that come from this cluster of CPU core in spipe", "PublicDescription": "Count of the number of write lines that come from this cluster of CPU core in spipe", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x22", - "EventName": "uncore_hisi_l3c.rd_hit_spipe", + "ConfigCode": "0x22", + "EventName": "rd_hit_spipe", "BriefDescription": "Count of the number of read lines that hits in spipe of this L3C", "PublicDescription": "Count of the number of read lines that hits in spipe of this L3C", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x23", - "EventName": "uncore_hisi_l3c.wr_hit_spipe", + "ConfigCode": "0x23", + "EventName": "wr_hit_spipe", "BriefDescription": "Count of the number of write lines that hits in spipe of this L3C", "PublicDescription": "Count of the number of write lines that hits in spipe of this L3C", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x29", - "EventName": "uncore_hisi_l3c.back_invalid", + "ConfigCode": "0x29", + "EventName": "back_invalid", "BriefDescription": "Count of the number of L3C back invalid operations", "PublicDescription": "Count of the number of L3C back invalid operations", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x40", - "EventName": "uncore_hisi_l3c.retry_cpu", + "ConfigCode": "0x40", + "EventName": "retry_cpu", "BriefDescription": "Count of the number of retry that L3C suppresses the CPU operations", "PublicDescription": "Count of the number of retry that L3C suppresses the CPU operations", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x41", - "EventName": "uncore_hisi_l3c.retry_ring", + "ConfigCode": "0x41", + "EventName": "retry_ring", "BriefDescription": "Count of the number of retry that L3C suppresses the ring operations", "PublicDescription": "Count of the number of retry that L3C suppresses the ring operations", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x42", - "EventName": "uncore_hisi_l3c.prefetch_drop", + "ConfigCode": "0x42", + "EventName": "prefetch_drop", "BriefDescription": "Count of the number of prefetch drops from this L3C", "PublicDescription": "Count of the number of prefetch drops from this L3C", "Unit": "hisi_sccl,l3c" From af9d82626c8f8547910e3e22c76ced3f5d5f5286 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 24 Aug 2021 14:20:51 +0200 Subject: [PATCH 097/587] PCI/ACPI: Remove OSC_PCI_SUPPORT_MASKS and OSC_PCI_CONTROL_MASKS These masks are only used internally in the PCI Host Bridge _OSC negotiation code, which already makes sure nothing outside of these masks is set. Remove the masks and simplify the code. Suggested-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20210824122054.29481-2-joro@8bytes.org Signed-off-by: Joerg Roedel Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki --- drivers/acpi/pci_root.c | 9 +++------ include/linux/acpi.h | 2 -- 2 files changed, 3 insertions(+), 8 deletions(-) diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c index d7deedf3548e..0c3030a58219 100644 --- a/drivers/acpi/pci_root.c +++ b/drivers/acpi/pci_root.c @@ -199,18 +199,15 @@ static acpi_status acpi_pci_query_osc(struct acpi_pci_root *root, acpi_status status; u32 result, capbuf[3]; - support &= OSC_PCI_SUPPORT_MASKS; support |= root->osc_support_set; capbuf[OSC_QUERY_DWORD] = OSC_QUERY_ENABLE; capbuf[OSC_SUPPORT_DWORD] = support; - if (control) { - *control &= OSC_PCI_CONTROL_MASKS; + if (control) capbuf[OSC_CONTROL_DWORD] = *control | root->osc_control_set; - } else { + else /* Run _OSC query only with existing controls. */ capbuf[OSC_CONTROL_DWORD] = root->osc_control_set; - } status = acpi_pci_run_osc(root->device->handle, capbuf, &result); if (ACPI_SUCCESS(status)) { @@ -357,7 +354,7 @@ static acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 *mask, u32 r if (!mask) return AE_BAD_PARAMETER; - ctrl = *mask & OSC_PCI_CONTROL_MASKS; + ctrl = *mask; if ((ctrl & req) != req) return AE_TYPE; diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 974d497a897d..eb59fd3052c0 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -577,7 +577,6 @@ extern u32 osc_sb_native_usb4_control; #define OSC_PCI_MSI_SUPPORT 0x00000010 #define OSC_PCI_EDR_SUPPORT 0x00000080 #define OSC_PCI_HPX_TYPE_3_SUPPORT 0x00000100 -#define OSC_PCI_SUPPORT_MASKS 0x0000019f /* PCI Host Bridge _OSC: Capabilities DWORD 3: Control Field */ #define OSC_PCI_EXPRESS_NATIVE_HP_CONTROL 0x00000001 @@ -587,7 +586,6 @@ extern u32 osc_sb_native_usb4_control; #define OSC_PCI_EXPRESS_CAPABILITY_CONTROL 0x00000010 #define OSC_PCI_EXPRESS_LTR_CONTROL 0x00000020 #define OSC_PCI_EXPRESS_DPC_CONTROL 0x00000080 -#define OSC_PCI_CONTROL_MASKS 0x000000bf #define ACPI_GSB_ACCESS_ATTRIB_QUICK 0x00000002 #define ACPI_GSB_ACCESS_ATTRIB_SEND_RCV 0x00000004 From 4c6f6060b7c4fe058981d17784684429c5491243 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 24 Aug 2021 14:20:52 +0200 Subject: [PATCH 098/587] PCI/ACPI: Move supported and control calculations to separate functions Move the calculations of supported and controlled _OSC features out of negotiate_os_control() into separate functions. Link: https://lore.kernel.org/r/20210824122054.29481-3-joro@8bytes.org Signed-off-by: Joerg Roedel Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki --- drivers/acpi/pci_root.c | 93 ++++++++++++++++++++++++----------------- 1 file changed, 55 insertions(+), 38 deletions(-) diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c index 0c3030a58219..ed4e6b55e9bc 100644 --- a/drivers/acpi/pci_root.c +++ b/drivers/acpi/pci_root.c @@ -396,6 +396,59 @@ static acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 *mask, u32 r return AE_OK; } +static u32 calculate_support(void) +{ + u32 support; + + /* + * All supported architectures that use ACPI have support for + * PCI domains, so we indicate this in _OSC support capabilities. + */ + support = OSC_PCI_SEGMENT_GROUPS_SUPPORT; + support |= OSC_PCI_HPX_TYPE_3_SUPPORT; + if (pci_ext_cfg_avail()) + support |= OSC_PCI_EXT_CONFIG_SUPPORT; + if (pcie_aspm_support_enabled()) + support |= OSC_PCI_ASPM_SUPPORT | OSC_PCI_CLOCK_PM_SUPPORT; + if (pci_msi_enabled()) + support |= OSC_PCI_MSI_SUPPORT; + if (IS_ENABLED(CONFIG_PCIE_EDR)) + support |= OSC_PCI_EDR_SUPPORT; + + return support; +} + +static u32 calculate_control(void) +{ + u32 control; + + control = OSC_PCI_EXPRESS_CAPABILITY_CONTROL + | OSC_PCI_EXPRESS_PME_CONTROL; + + if (IS_ENABLED(CONFIG_PCIEASPM)) + control |= OSC_PCI_EXPRESS_LTR_CONTROL; + + if (IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE)) + control |= OSC_PCI_EXPRESS_NATIVE_HP_CONTROL; + + if (IS_ENABLED(CONFIG_HOTPLUG_PCI_SHPC)) + control |= OSC_PCI_SHPC_NATIVE_HP_CONTROL; + + if (pci_aer_available()) + control |= OSC_PCI_EXPRESS_AER_CONTROL; + + /* + * Per the Downstream Port Containment Related Enhancements ECN to + * the PCI Firmware Spec, r3.2, sec 4.5.1, table 4-5, + * OSC_PCI_EXPRESS_DPC_CONTROL indicates the OS supports both DPC + * and EDR. + */ + if (IS_ENABLED(CONFIG_PCIE_DPC) && IS_ENABLED(CONFIG_PCIE_EDR)) + control |= OSC_PCI_EXPRESS_DPC_CONTROL; + + return control; +} + static void negotiate_os_control(struct acpi_pci_root *root, int *no_aspm, bool is_pcie) { @@ -416,20 +469,7 @@ static void negotiate_os_control(struct acpi_pci_root *root, int *no_aspm, return; } - /* - * All supported architectures that use ACPI have support for - * PCI domains, so we indicate this in _OSC support capabilities. - */ - support = OSC_PCI_SEGMENT_GROUPS_SUPPORT; - support |= OSC_PCI_HPX_TYPE_3_SUPPORT; - if (pci_ext_cfg_avail()) - support |= OSC_PCI_EXT_CONFIG_SUPPORT; - if (pcie_aspm_support_enabled()) - support |= OSC_PCI_ASPM_SUPPORT | OSC_PCI_CLOCK_PM_SUPPORT; - if (pci_msi_enabled()) - support |= OSC_PCI_MSI_SUPPORT; - if (IS_ENABLED(CONFIG_PCIE_EDR)) - support |= OSC_PCI_EDR_SUPPORT; + support = calculate_support(); decode_osc_support(root, "OS supports", support); status = acpi_pci_osc_support(root, support); @@ -456,31 +496,8 @@ static void negotiate_os_control(struct acpi_pci_root *root, int *no_aspm, return; } - control = OSC_PCI_EXPRESS_CAPABILITY_CONTROL - | OSC_PCI_EXPRESS_PME_CONTROL; + requested = control = calculate_control(); - if (IS_ENABLED(CONFIG_PCIEASPM)) - control |= OSC_PCI_EXPRESS_LTR_CONTROL; - - if (IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE)) - control |= OSC_PCI_EXPRESS_NATIVE_HP_CONTROL; - - if (IS_ENABLED(CONFIG_HOTPLUG_PCI_SHPC)) - control |= OSC_PCI_SHPC_NATIVE_HP_CONTROL; - - if (pci_aer_available()) - control |= OSC_PCI_EXPRESS_AER_CONTROL; - - /* - * Per the Downstream Port Containment Related Enhancements ECN to - * the PCI Firmware Spec, r3.2, sec 4.5.1, table 4-5, - * OSC_PCI_EXPRESS_DPC_CONTROL indicates the OS supports both DPC - * and EDR. - */ - if (IS_ENABLED(CONFIG_PCIE_DPC) && IS_ENABLED(CONFIG_PCIE_EDR)) - control |= OSC_PCI_EXPRESS_DPC_CONTROL; - - requested = control; status = acpi_pci_osc_control_set(handle, &control, OSC_PCI_EXPRESS_CAPABILITY_CONTROL); if (ACPI_SUCCESS(status)) { From 87f1f87a16818c36431391ea8c30ea926cab917f Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 24 Aug 2021 14:20:53 +0200 Subject: [PATCH 099/587] PCI/ACPI: Move _OSC query checks to separate function Move the checks about whether the _OSC controls are requested from the firmware to a separate function. Link: https://lore.kernel.org/r/20210824122054.29481-4-joro@8bytes.org Signed-off-by: Joerg Roedel Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki --- drivers/acpi/pci_root.c | 28 +++++++++++++++++++--------- 1 file changed, 19 insertions(+), 9 deletions(-) diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c index ed4e6b55e9bc..f12e512bcddc 100644 --- a/drivers/acpi/pci_root.c +++ b/drivers/acpi/pci_root.c @@ -449,6 +449,24 @@ static u32 calculate_control(void) return control; } +static bool os_control_query_checks(struct acpi_pci_root *root, u32 support) +{ + struct acpi_device *device = root->device; + + if (pcie_ports_disabled) { + dev_info(&device->dev, "PCIe port services disabled; not requesting _OSC control\n"); + return false; + } + + if ((support & ACPI_PCIE_REQ_SUPPORT) != ACPI_PCIE_REQ_SUPPORT) { + decode_osc_support(root, "not requesting OS control; OS requires", + ACPI_PCIE_REQ_SUPPORT); + return false; + } + + return true; +} + static void negotiate_os_control(struct acpi_pci_root *root, int *no_aspm, bool is_pcie) { @@ -485,16 +503,8 @@ static void negotiate_os_control(struct acpi_pci_root *root, int *no_aspm, return; } - if (pcie_ports_disabled) { - dev_info(&device->dev, "PCIe port services disabled; not requesting _OSC control\n"); + if (!os_control_query_checks(root, support)) return; - } - - if ((support & ACPI_PCIE_REQ_SUPPORT) != ACPI_PCIE_REQ_SUPPORT) { - decode_osc_support(root, "not requesting OS control; OS requires", - ACPI_PCIE_REQ_SUPPORT); - return; - } requested = control = calculate_control(); From 6bc779ee05d4fa66c99096dbf88ff61acbb8a887 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 24 Aug 2021 14:20:54 +0200 Subject: [PATCH 100/587] PCI/ACPI: Check for _OSC support in acpi_pci_osc_control_set() Get rid of acpi_pci_osc_support() and check for _OSC supported features directly in acpi_pci_osc_control_set(). There is no point in doing an unconditional _OSC query with control=0 even when the kernel later wants to take control over more features. This saves one _OSC query and simplifies the code by getting rid of the acpi_pci_osc_support() function. As a side effect, the !control checks in acpi_pci_query_osc() can also be removed. Link: https://lore.kernel.org/r/20210824122054.29481-5-joro@8bytes.org Signed-off-by: Joerg Roedel Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki --- drivers/acpi/pci_root.c | 81 ++++++++++++++++------------------------- 1 file changed, 32 insertions(+), 49 deletions(-) diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c index f12e512bcddc..ab2f7dfb0c44 100644 --- a/drivers/acpi/pci_root.c +++ b/drivers/acpi/pci_root.c @@ -203,26 +203,16 @@ static acpi_status acpi_pci_query_osc(struct acpi_pci_root *root, capbuf[OSC_QUERY_DWORD] = OSC_QUERY_ENABLE; capbuf[OSC_SUPPORT_DWORD] = support; - if (control) - capbuf[OSC_CONTROL_DWORD] = *control | root->osc_control_set; - else - /* Run _OSC query only with existing controls. */ - capbuf[OSC_CONTROL_DWORD] = root->osc_control_set; + capbuf[OSC_CONTROL_DWORD] = *control | root->osc_control_set; status = acpi_pci_run_osc(root->device->handle, capbuf, &result); if (ACPI_SUCCESS(status)) { root->osc_support_set = support; - if (control) - *control = result; + *control = result; } return status; } -static acpi_status acpi_pci_osc_support(struct acpi_pci_root *root, u32 flags) -{ - return acpi_pci_query_osc(root, flags, NULL); -} - struct acpi_pci_root *acpi_pci_find_root(acpi_handle handle) { struct acpi_pci_root *root; @@ -345,8 +335,9 @@ EXPORT_SYMBOL_GPL(acpi_get_pci_dev); * _OSC bits the BIOS has granted control of, but its contents are meaningless * on failure. **/ -static acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 *mask, u32 req) +static acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 *mask, u32 support) { + u32 req = OSC_PCI_EXPRESS_CAPABILITY_CONTROL; struct acpi_pci_root *root; acpi_status status; u32 ctrl, capbuf[3]; @@ -354,22 +345,16 @@ static acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 *mask, u32 r if (!mask) return AE_BAD_PARAMETER; - ctrl = *mask; - if ((ctrl & req) != req) - return AE_TYPE; - root = acpi_pci_find_root(handle); if (!root) return AE_NOT_EXIST; - *mask = ctrl | root->osc_control_set; - /* No need to evaluate _OSC if the control was already granted. */ - if ((root->osc_control_set & ctrl) == ctrl) - return AE_OK; + ctrl = *mask; + *mask |= root->osc_control_set; /* Need to check the available controls bits before requesting them. */ - while (*mask) { - status = acpi_pci_query_osc(root, root->osc_support_set, mask); + do { + status = acpi_pci_query_osc(root, support, mask); if (ACPI_FAILURE(status)) return status; if (ctrl == *mask) @@ -377,7 +362,11 @@ static acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 *mask, u32 r decode_osc_control(root, "platform does not support", ctrl & ~(*mask)); ctrl = *mask; - } + } while (*mask); + + /* No need to request _OSC if the control was already granted. */ + if ((root->osc_control_set & ctrl) == ctrl) + return AE_OK; if ((ctrl & req) != req) { decode_osc_control(root, "not requesting control; platform does not support", @@ -470,7 +459,7 @@ static bool os_control_query_checks(struct acpi_pci_root *root, u32 support) static void negotiate_os_control(struct acpi_pci_root *root, int *no_aspm, bool is_pcie) { - u32 support, control, requested; + u32 support, control = 0, requested = 0; acpi_status status; struct acpi_device *device = root->device; acpi_handle handle = device->handle; @@ -490,28 +479,15 @@ static void negotiate_os_control(struct acpi_pci_root *root, int *no_aspm, support = calculate_support(); decode_osc_support(root, "OS supports", support); - status = acpi_pci_osc_support(root, support); - if (ACPI_FAILURE(status)) { - *no_aspm = 1; - /* _OSC is optional for PCI host bridges */ - if ((status == AE_NOT_FOUND) && !is_pcie) - return; + if (os_control_query_checks(root, support)) + requested = control = calculate_control(); - dev_info(&device->dev, "_OSC: platform retains control of PCIe features (%s)\n", - acpi_format_exception(status)); - return; - } - - if (!os_control_query_checks(root, support)) - return; - - requested = control = calculate_control(); - - status = acpi_pci_osc_control_set(handle, &control, - OSC_PCI_EXPRESS_CAPABILITY_CONTROL); + status = acpi_pci_osc_control_set(handle, &control, support); if (ACPI_SUCCESS(status)) { - decode_osc_control(root, "OS now controls", control); + if (control) + decode_osc_control(root, "OS now controls", control); + if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_ASPM) { /* * We have ASPM control, but the FADT indicates that @@ -522,11 +498,6 @@ static void negotiate_os_control(struct acpi_pci_root *root, int *no_aspm, *no_aspm = 1; } } else { - decode_osc_control(root, "OS requested", requested); - decode_osc_control(root, "platform willing to grant", control); - dev_info(&device->dev, "_OSC: platform retains control of PCIe features (%s)\n", - acpi_format_exception(status)); - /* * We want to disable ASPM here, but aspm_disabled * needs to remain in its state from boot so that we @@ -535,6 +506,18 @@ static void negotiate_os_control(struct acpi_pci_root *root, int *no_aspm, * root scan. */ *no_aspm = 1; + + /* _OSC is optional for PCI host bridges */ + if ((status == AE_NOT_FOUND) && !is_pcie) + return; + + if (control) { + decode_osc_control(root, "OS requested", requested); + decode_osc_control(root, "platform willing to grant", control); + } + + dev_info(&device->dev, "_OSC: platform retains control of PCIe features (%s)\n", + acpi_format_exception(status)); } } From c2606ddcf5ad1969ceffe3c98d427b272243e150 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 24 Sep 2021 15:32:23 +0200 Subject: [PATCH 101/587] mtd: onenand: samsung: drop Exynos4 and describe driver in KConfig None of supported Samsung Exynos4 SoCs (Exynos4210, Exynos4412) seem to use OneNAND driver so drop it. Describe better which driver applies to which SoC, to make configuring kernel for Samsung SoC easier. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210924133223.111930-1-krzysztof.kozlowski@canonical.com --- drivers/mtd/nand/onenand/Kconfig | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/mtd/nand/onenand/Kconfig b/drivers/mtd/nand/onenand/Kconfig index 1a0e65bc246e..34d9a7a82ad4 100644 --- a/drivers/mtd/nand/onenand/Kconfig +++ b/drivers/mtd/nand/onenand/Kconfig @@ -33,11 +33,12 @@ config MTD_ONENAND_OMAP2 config MTD_ONENAND_SAMSUNG tristate "OneNAND on Samsung SOC controller support" - depends on ARCH_S3C64XX || ARCH_S5PV210 || ARCH_EXYNOS4 || COMPILE_TEST + depends on ARCH_S3C64XX || ARCH_S5PV210 || COMPILE_TEST help - Support for a OneNAND flash device connected to an Samsung SOC. - S3C64XX uses command mapping method. - S5PC110/S5PC210 use generic OneNAND method. + Support for a OneNAND flash device connected to Samsung S3C64XX + (using command mapping method) and S5PC110/S5PC210 (using generic + OneNAND method) SoCs. + Choose Y here only if you build for such Samsung SoC. config MTD_ONENAND_OTP bool "OneNAND OTP Support" From 95e83e219d68956ba4fed9326683e4d2bd3e39a9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Krzysztof=20Wilczy=C5=84ski?= Date: Wed, 15 Sep 2021 23:01:25 +0000 Subject: [PATCH 102/587] PCI/sysfs: Check CAP_SYS_ADMIN before parsing user input MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Check if the "CAP_SYS_ADMIN" capability flag is set before parsing user input as it makes more sense to first check whether the current user actually has the right permissions before accepting any input from such user. This will also make order in which enable_store() and msi_bus_store() perform the "CAP_SYS_ADMIN" capability check consistent with other PCI-related sysfs objects that first verify whether user has this capability set. Link: https://lore.kernel.org/r/20210915230127.2495723-1-kw@linux.com Signed-off-by: Krzysztof Wilczyński Signed-off-by: Bjorn Helgaas --- drivers/pci/pci-sysfs.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 7fb5cd17cc98..6832e161be1c 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -273,15 +273,16 @@ static ssize_t enable_store(struct device *dev, struct device_attribute *attr, { struct pci_dev *pdev = to_pci_dev(dev); unsigned long val; - ssize_t result = kstrtoul(buf, 0, &val); - - if (result < 0) - return result; + ssize_t result; /* this can crash the machine when done on the "wrong" device */ if (!capable(CAP_SYS_ADMIN)) return -EPERM; + result = kstrtoul(buf, 0, &val); + if (result < 0) + return result; + device_lock(dev); if (dev->driver) result = -EBUSY; @@ -378,12 +379,12 @@ static ssize_t msi_bus_store(struct device *dev, struct device_attribute *attr, struct pci_bus *subordinate = pdev->subordinate; unsigned long val; - if (kstrtoul(buf, 0, &val) < 0) - return -EINVAL; - if (!capable(CAP_SYS_ADMIN)) return -EPERM; + if (kstrtoul(buf, 0, &val) < 0) + return -EINVAL; + /* * "no_msi" and "bus_flags" only affect what happens when a driver * requests MSI or MSI-X. They don't affect any drivers that have From 36f354ec7bf92f8aaf09eaf3b261ea06c25ec337 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Krzysztof=20Wilczy=C5=84ski?= Date: Wed, 15 Sep 2021 23:01:26 +0000 Subject: [PATCH 103/587] PCI/sysfs: Return -EINVAL consistently from "store" functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Most of the "store" functions that handle userspace input via sysfs return -EINVAL should the value fail validation and/or type conversion. This error code is a clear message to userspace that the value is not a valid input. However, some of the "show" functions return input parsing error codes as-is, which may be either -EINVAL or -ERANGE. The former would often be from kstrtobool(), and the latter typically from other kstr*() functions such as kstrtou8(), kstrtou32(), kstrtoint(), etc. -EINVAL is commonly returned as the error code to indicate that the value provided is invalid, but -ERANGE is not very useful in userspace. Therefore, normalize the return error code to be -EINVAL for when the validation and/or type conversion fails. Link: https://lore.kernel.org/r/20210915230127.2495723-2-kw@linux.com Signed-off-by: Krzysztof Wilczyński Signed-off-by: Bjorn Helgaas --- drivers/pci/endpoint/functions/pci-epf-ntb.c | 18 ++++------ drivers/pci/endpoint/pci-ep-cfs.c | 35 +++++++------------- drivers/pci/iov.c | 14 ++++---- drivers/pci/pci-sysfs.c | 20 +++++------ 4 files changed, 33 insertions(+), 54 deletions(-) diff --git a/drivers/pci/endpoint/functions/pci-epf-ntb.c b/drivers/pci/endpoint/functions/pci-epf-ntb.c index 8b4756159f15..e67489144349 100644 --- a/drivers/pci/endpoint/functions/pci-epf-ntb.c +++ b/drivers/pci/endpoint/functions/pci-epf-ntb.c @@ -1947,11 +1947,9 @@ static ssize_t epf_ntb_##_name##_store(struct config_item *item, \ struct config_group *group = to_config_group(item); \ struct epf_ntb *ntb = to_epf_ntb(group); \ u32 val; \ - int ret; \ \ - ret = kstrtou32(page, 0, &val); \ - if (ret) \ - return ret; \ + if (kstrtou32(page, 0, &val) < 0) \ + return -EINVAL; \ \ ntb->_name = val; \ \ @@ -1980,11 +1978,9 @@ static ssize_t epf_ntb_##_name##_store(struct config_item *item, \ struct device *dev = &ntb->epf->dev; \ int win_no; \ u64 val; \ - int ret; \ \ - ret = kstrtou64(page, 0, &val); \ - if (ret) \ - return ret; \ + if (kstrtou64(page, 0, &val) < 0) \ + return -EINVAL; \ \ if (sscanf(#_name, "mw%d", &win_no) != 1) \ return -EINVAL; \ @@ -2005,11 +2001,9 @@ static ssize_t epf_ntb_num_mws_store(struct config_item *item, struct config_group *group = to_config_group(item); struct epf_ntb *ntb = to_epf_ntb(group); u32 val; - int ret; - ret = kstrtou32(page, 0, &val); - if (ret) - return ret; + if (kstrtou32(page, 0, &val) < 0) + return -EINVAL; if (val > MAX_MW) return -EINVAL; diff --git a/drivers/pci/endpoint/pci-ep-cfs.c b/drivers/pci/endpoint/pci-ep-cfs.c index 999911801877..19bc0e828c0c 100644 --- a/drivers/pci/endpoint/pci-ep-cfs.c +++ b/drivers/pci/endpoint/pci-ep-cfs.c @@ -175,9 +175,8 @@ static ssize_t pci_epc_start_store(struct config_item *item, const char *page, epc = epc_group->epc; - ret = kstrtobool(page, &start); - if (ret) - return ret; + if (kstrtobool(page, &start) < 0) + return -EINVAL; if (!start) { pci_epc_stop(epc); @@ -329,13 +328,11 @@ static ssize_t pci_epf_##_name##_store(struct config_item *item, \ const char *page, size_t len) \ { \ u32 val; \ - int ret; \ struct pci_epf *epf = to_pci_epf_group(item)->epf; \ if (WARN_ON_ONCE(!epf->header)) \ return -EINVAL; \ - ret = kstrtou32(page, 0, &val); \ - if (ret) \ - return ret; \ + if (kstrtou32(page, 0, &val) < 0) \ + return -EINVAL; \ epf->header->_name = val; \ return len; \ } @@ -345,13 +342,11 @@ static ssize_t pci_epf_##_name##_store(struct config_item *item, \ const char *page, size_t len) \ { \ u16 val; \ - int ret; \ struct pci_epf *epf = to_pci_epf_group(item)->epf; \ if (WARN_ON_ONCE(!epf->header)) \ return -EINVAL; \ - ret = kstrtou16(page, 0, &val); \ - if (ret) \ - return ret; \ + if (kstrtou16(page, 0, &val) < 0) \ + return -EINVAL; \ epf->header->_name = val; \ return len; \ } @@ -361,13 +356,11 @@ static ssize_t pci_epf_##_name##_store(struct config_item *item, \ const char *page, size_t len) \ { \ u8 val; \ - int ret; \ struct pci_epf *epf = to_pci_epf_group(item)->epf; \ if (WARN_ON_ONCE(!epf->header)) \ return -EINVAL; \ - ret = kstrtou8(page, 0, &val); \ - if (ret) \ - return ret; \ + if (kstrtou8(page, 0, &val) < 0) \ + return -EINVAL; \ epf->header->_name = val; \ return len; \ } @@ -376,11 +369,9 @@ static ssize_t pci_epf_msi_interrupts_store(struct config_item *item, const char *page, size_t len) { u8 val; - int ret; - ret = kstrtou8(page, 0, &val); - if (ret) - return ret; + if (kstrtou8(page, 0, &val) < 0) + return -EINVAL; to_pci_epf_group(item)->epf->msi_interrupts = val; @@ -398,11 +389,9 @@ static ssize_t pci_epf_msix_interrupts_store(struct config_item *item, const char *page, size_t len) { u16 val; - int ret; - ret = kstrtou16(page, 0, &val); - if (ret) - return ret; + if (kstrtou16(page, 0, &val) < 0) + return -EINVAL; to_pci_epf_group(item)->epf->msix_interrupts = val; diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index dafdc652fcd0..0267977c9f17 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -183,11 +183,10 @@ static ssize_t sriov_vf_msix_count_store(struct device *dev, { struct pci_dev *vf_dev = to_pci_dev(dev); struct pci_dev *pdev = pci_physfn(vf_dev); - int val, ret; + int val, ret = 0; - ret = kstrtoint(buf, 0, &val); - if (ret) - return ret; + if (kstrtoint(buf, 0, &val) < 0) + return -EINVAL; if (val < 0) return -EINVAL; @@ -376,12 +375,11 @@ static ssize_t sriov_numvfs_store(struct device *dev, const char *buf, size_t count) { struct pci_dev *pdev = to_pci_dev(dev); - int ret; + int ret = 0; u16 num_vfs; - ret = kstrtou16(buf, 0, &num_vfs); - if (ret < 0) - return ret; + if (kstrtou16(buf, 0, &num_vfs) < 0) + return -EINVAL; if (num_vfs > pci_sriov_get_totalvfs(pdev)) return -ERANGE; diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 6832e161be1c..a092fc0c665d 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -273,15 +273,14 @@ static ssize_t enable_store(struct device *dev, struct device_attribute *attr, { struct pci_dev *pdev = to_pci_dev(dev); unsigned long val; - ssize_t result; + ssize_t result = 0; /* this can crash the machine when done on the "wrong" device */ if (!capable(CAP_SYS_ADMIN)) return -EPERM; - result = kstrtoul(buf, 0, &val); - if (result < 0) - return result; + if (kstrtoul(buf, 0, &val) < 0) + return -EINVAL; device_lock(dev); if (dev->driver) @@ -313,14 +312,13 @@ static ssize_t numa_node_store(struct device *dev, size_t count) { struct pci_dev *pdev = to_pci_dev(dev); - int node, ret; + int node; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - ret = kstrtoint(buf, 0, &node); - if (ret) - return ret; + if (kstrtoint(buf, 0, &node) < 0) + return -EINVAL; if ((node < 0 && node != NUMA_NO_NODE) || node >= MAX_NUMNODES) return -EINVAL; @@ -1340,10 +1338,10 @@ static ssize_t reset_store(struct device *dev, struct device_attribute *attr, { struct pci_dev *pdev = to_pci_dev(dev); unsigned long val; - ssize_t result = kstrtoul(buf, 0, &val); + ssize_t result; - if (result < 0) - return result; + if (kstrtoul(buf, 0, &val) < 0) + return -EINVAL; if (val != 1) return -EINVAL; From e0f7b19223582c302f5736e93927aafde9458d48 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Krzysztof=20Wilczy=C5=84ski?= Date: Wed, 15 Sep 2021 23:01:27 +0000 Subject: [PATCH 104/587] PCI: Use kstrtobool() directly, sans strtobool() wrapper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit strtobool() is a wrapper around kstrtobool() that has been added for backward compatibility. There is no reason to use the old API, so use kstrtobool() directly. Related: ef951599074b ("lib: move strtobool() to kstrtobool()") Link: https://lore.kernel.org/r/20210915230127.2495723-3-kw@linux.com Signed-off-by: Krzysztof Wilczyński Signed-off-by: Bjorn Helgaas --- drivers/pci/p2pdma.c | 6 +++--- drivers/pci/pcie/aspm.c | 4 ++-- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c index 50cdde3e9a8b..4fccdcf9186f 100644 --- a/drivers/pci/p2pdma.c +++ b/drivers/pci/p2pdma.c @@ -943,7 +943,7 @@ EXPORT_SYMBOL_GPL(pci_p2pdma_unmap_sg_attrs); * * Parses an attribute value to decide whether to enable p2pdma. * The value can select a PCI device (using its full BDF device - * name) or a boolean (in any format strtobool() accepts). A false + * name) or a boolean (in any format kstrtobool() accepts). A false * value disables p2pdma, a true value expects the caller * to automatically find a compatible device and specifying a PCI device * expects the caller to use the specific provider. @@ -975,11 +975,11 @@ int pci_p2pdma_enable_store(const char *page, struct pci_dev **p2p_dev, } else if ((page[0] == '0' || page[0] == '1') && !iscntrl(page[1])) { /* * If the user enters a PCI device that doesn't exist - * like "0000:01:00.1", we don't want strtobool to think + * like "0000:01:00.1", we don't want kstrtobool to think * it's a '0' when it's clearly not what the user wanted. * So we require 0's and 1's to be exactly one character. */ - } else if (!strtobool(page, use_p2pdma)) { + } else if (!kstrtobool(page, use_p2pdma)) { return 0; } diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index 013a47f587ce..52c74682601a 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -1219,7 +1219,7 @@ static ssize_t aspm_attr_store_common(struct device *dev, struct pcie_link_state *link = pcie_aspm_get_link(pdev); bool state_enable; - if (strtobool(buf, &state_enable) < 0) + if (kstrtobool(buf, &state_enable) < 0) return -EINVAL; down_read(&pci_bus_sem); @@ -1276,7 +1276,7 @@ static ssize_t clkpm_store(struct device *dev, struct pcie_link_state *link = pcie_aspm_get_link(pdev); bool state_enable; - if (strtobool(buf, &state_enable) < 0) + if (kstrtobool(buf, &state_enable) < 0) return -EINVAL; down_read(&pci_bus_sem); From cb94a02e7494c001fa8b5a4c5e16693fafd98530 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 23 Sep 2021 00:46:04 -0700 Subject: [PATCH 105/587] perf metric: Restructure struct expr_parse_ctx. A later change to parsing the ids out (in expr__find_other) will potentially drop hashmaps and so it is more convenient to move expr_parse_ctx to have a hashmap pointer rather than a struct value. As this pointer must be freed, rather than just going out of scope, add expr__ctx_new and expr__ctx_free to manage expr_parse_ctx memory. Adjust use of struct expr_parse_ctx accordingly. Reviewed-by: Andi Kleen Signed-off-by: Ian Rogers Tested-by: John Garry Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jin Yao Cc: Kajol Jain Cc: Mark Rutland Cc: Namhyung Kim Cc: Paul Clarke Cc: Peter Zijlstra Cc: Sandeep Dasgupta Cc: Stephane Eranian Link: https://lore.kernel.org/r/20210923074616.674826-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/expr.c | 81 ++++++++++++++++++----------------- tools/perf/tests/pmu-events.c | 47 ++++++++++++-------- tools/perf/util/expr.c | 39 +++++++++++++---- tools/perf/util/expr.h | 5 ++- tools/perf/util/metricgroup.c | 44 ++++++++++--------- tools/perf/util/stat-shadow.c | 50 +++++++++++++-------- 6 files changed, 159 insertions(+), 107 deletions(-) diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index 4d01051951cd..b0a3b5fd0c00 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -22,67 +22,70 @@ int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused) const char *p; double val; int ret; - struct expr_parse_ctx ctx; + struct expr_parse_ctx *ctx; - expr__ctx_init(&ctx); - expr__add_id_val(&ctx, strdup("FOO"), 1); - expr__add_id_val(&ctx, strdup("BAR"), 2); + ctx = expr__ctx_new(); + TEST_ASSERT_VAL("expr__ctx_new", ctx); + expr__add_id_val(ctx, strdup("FOO"), 1); + expr__add_id_val(ctx, strdup("BAR"), 2); - ret = test(&ctx, "1+1", 2); - ret |= test(&ctx, "FOO+BAR", 3); - ret |= test(&ctx, "(BAR/2)%2", 1); - ret |= test(&ctx, "1 - -4", 5); - ret |= test(&ctx, "(FOO-1)*2 + (BAR/2)%2 - -4", 5); - ret |= test(&ctx, "1-1 | 1", 1); - ret |= test(&ctx, "1-1 & 1", 0); - ret |= test(&ctx, "min(1,2) + 1", 2); - ret |= test(&ctx, "max(1,2) + 1", 3); - ret |= test(&ctx, "1+1 if 3*4 else 0", 2); - ret |= test(&ctx, "1.1 + 2.1", 3.2); - ret |= test(&ctx, ".1 + 2.", 2.1); - ret |= test(&ctx, "d_ratio(1, 2)", 0.5); - ret |= test(&ctx, "d_ratio(2.5, 0)", 0); - ret |= test(&ctx, "1.1 < 2.2", 1); - ret |= test(&ctx, "2.2 > 1.1", 1); - ret |= test(&ctx, "1.1 < 1.1", 0); - ret |= test(&ctx, "2.2 > 2.2", 0); - ret |= test(&ctx, "2.2 < 1.1", 0); - ret |= test(&ctx, "1.1 > 2.2", 0); + ret = test(ctx, "1+1", 2); + ret |= test(ctx, "FOO+BAR", 3); + ret |= test(ctx, "(BAR/2)%2", 1); + ret |= test(ctx, "1 - -4", 5); + ret |= test(ctx, "(FOO-1)*2 + (BAR/2)%2 - -4", 5); + ret |= test(ctx, "1-1 | 1", 1); + ret |= test(ctx, "1-1 & 1", 0); + ret |= test(ctx, "min(1,2) + 1", 2); + ret |= test(ctx, "max(1,2) + 1", 3); + ret |= test(ctx, "1+1 if 3*4 else 0", 2); + ret |= test(ctx, "1.1 + 2.1", 3.2); + ret |= test(ctx, ".1 + 2.", 2.1); + ret |= test(ctx, "d_ratio(1, 2)", 0.5); + ret |= test(ctx, "d_ratio(2.5, 0)", 0); + ret |= test(ctx, "1.1 < 2.2", 1); + ret |= test(ctx, "2.2 > 1.1", 1); + ret |= test(ctx, "1.1 < 1.1", 0); + ret |= test(ctx, "2.2 > 2.2", 0); + ret |= test(ctx, "2.2 < 1.1", 0); + ret |= test(ctx, "1.1 > 2.2", 0); - if (ret) + if (ret) { + expr__ctx_free(ctx); return ret; + } p = "FOO/0"; - ret = expr__parse(&val, &ctx, p, 1); + ret = expr__parse(&val, ctx, p, 1); TEST_ASSERT_VAL("division by zero", ret == -1); p = "BAR/"; - ret = expr__parse(&val, &ctx, p, 1); + ret = expr__parse(&val, ctx, p, 1); TEST_ASSERT_VAL("missing operand", ret == -1); - expr__ctx_clear(&ctx); + expr__ctx_clear(ctx); TEST_ASSERT_VAL("find other", expr__find_other("FOO + BAR + BAZ + BOZO", "FOO", - &ctx, 1) == 0); - TEST_ASSERT_VAL("find other", hashmap__size(&ctx.ids) == 3); - TEST_ASSERT_VAL("find other", hashmap__find(&ctx.ids, "BAR", + ctx, 1) == 0); + TEST_ASSERT_VAL("find other", hashmap__size(ctx->ids) == 3); + TEST_ASSERT_VAL("find other", hashmap__find(ctx->ids, "BAR", (void **)&val_ptr)); - TEST_ASSERT_VAL("find other", hashmap__find(&ctx.ids, "BAZ", + TEST_ASSERT_VAL("find other", hashmap__find(ctx->ids, "BAZ", (void **)&val_ptr)); - TEST_ASSERT_VAL("find other", hashmap__find(&ctx.ids, "BOZO", + TEST_ASSERT_VAL("find other", hashmap__find(ctx->ids, "BOZO", (void **)&val_ptr)); - expr__ctx_clear(&ctx); + expr__ctx_clear(ctx); TEST_ASSERT_VAL("find other", expr__find_other("EVENT1\\,param\\=?@ + EVENT2\\,param\\=?@", - NULL, &ctx, 3) == 0); - TEST_ASSERT_VAL("find other", hashmap__size(&ctx.ids) == 2); - TEST_ASSERT_VAL("find other", hashmap__find(&ctx.ids, "EVENT1,param=3/", + NULL, ctx, 3) == 0); + TEST_ASSERT_VAL("find other", hashmap__size(ctx->ids) == 2); + TEST_ASSERT_VAL("find other", hashmap__find(ctx->ids, "EVENT1,param=3/", (void **)&val_ptr)); - TEST_ASSERT_VAL("find other", hashmap__find(&ctx.ids, "EVENT2,param=3/", + TEST_ASSERT_VAL("find other", hashmap__find(ctx->ids, "EVENT2,param=3/", (void **)&val_ptr)); - expr__ctx_clear(&ctx); + expr__ctx_free(ctx); return 0; } diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index f14266a4c513..91076ab0514b 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -836,7 +836,7 @@ static int resolve_metric_simple(struct expr_parse_ctx *pctx, do { all = true; - hashmap__for_each_entry_safe((&pctx->ids), cur, cur_tmp, bkt) { + hashmap__for_each_entry_safe(pctx->ids, cur, cur_tmp, bkt) { struct metric_ref *ref; struct pmu_event *pe; @@ -890,9 +890,14 @@ static int test_parsing(void) struct pmu_event *pe; int i, j, k; int ret = 0; - struct expr_parse_ctx ctx; + struct expr_parse_ctx *ctx; double result; + ctx = expr__ctx_new(); + if (!ctx) { + pr_debug("expr__ctx_new failed"); + return TEST_FAIL; + } i = 0; for (;;) { map = &pmu_events_map[i++]; @@ -910,15 +915,15 @@ static int test_parsing(void) break; if (!pe->metric_expr) continue; - expr__ctx_init(&ctx); - if (expr__find_other(pe->metric_expr, NULL, &ctx, 0) + expr__ctx_clear(ctx); + if (expr__find_other(pe->metric_expr, NULL, ctx, 0) < 0) { expr_failure("Parse other failed", map, pe); ret++; continue; } - if (resolve_metric_simple(&ctx, &compound_list, map, + if (resolve_metric_simple(ctx, &compound_list, map, pe->metric_name)) { expr_failure("Could not resolve metrics", map, pe); ret++; @@ -931,27 +936,27 @@ static int test_parsing(void) * make them unique. */ k = 1; - hashmap__for_each_entry((&ctx.ids), cur, bkt) - expr__add_id_val(&ctx, strdup(cur->key), k++); + hashmap__for_each_entry(ctx->ids, cur, bkt) + expr__add_id_val(ctx, strdup(cur->key), k++); - hashmap__for_each_entry((&ctx.ids), cur, bkt) { + hashmap__for_each_entry(ctx->ids, cur, bkt) { if (check_parse_cpu(cur->key, map == cpus_map, pe)) ret++; } list_for_each_entry_safe(metric, tmp, &compound_list, list) { - expr__add_ref(&ctx, &metric->metric_ref); + expr__add_ref(ctx, &metric->metric_ref); free(metric); } - if (expr__parse(&result, &ctx, pe->metric_expr, 0)) { + if (expr__parse(&result, ctx, pe->metric_expr, 0)) { expr_failure("Parse failed", map, pe); ret++; } - expr__ctx_clear(&ctx); } } + expr__ctx_free(ctx); /* TODO: fail when not ok */ exit: return ret == 0 ? TEST_OK : TEST_SKIP; @@ -971,7 +976,7 @@ static struct test_metric metrics[] = { static int metric_parse_fake(const char *str) { - struct expr_parse_ctx ctx; + struct expr_parse_ctx *ctx; struct hashmap_entry *cur; double result; int ret = -1; @@ -980,8 +985,12 @@ static int metric_parse_fake(const char *str) pr_debug("parsing '%s'\n", str); - expr__ctx_init(&ctx); - if (expr__find_other(str, NULL, &ctx, 0) < 0) { + ctx = expr__ctx_new(); + if (!ctx) { + pr_debug("expr__ctx_new failed"); + return TEST_FAIL; + } + if (expr__find_other(str, NULL, ctx, 0) < 0) { pr_err("expr__find_other failed\n"); return -1; } @@ -992,23 +1001,23 @@ static int metric_parse_fake(const char *str) * make them unique. */ i = 1; - hashmap__for_each_entry((&ctx.ids), cur, bkt) - expr__add_id_val(&ctx, strdup(cur->key), i++); + hashmap__for_each_entry(ctx->ids, cur, bkt) + expr__add_id_val(ctx, strdup(cur->key), i++); - hashmap__for_each_entry((&ctx.ids), cur, bkt) { + hashmap__for_each_entry(ctx->ids, cur, bkt) { if (check_parse_fake(cur->key)) { pr_err("check_parse_fake failed\n"); goto out; } } - if (expr__parse(&result, &ctx, str, 0)) + if (expr__parse(&result, ctx, str, 0)) pr_err("expr__parse failed\n"); else ret = 0; out: - expr__ctx_clear(&ctx); + expr__ctx_free(ctx); return ret; } diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c index a850fd0be3ee..7b1c06772a49 100644 --- a/tools/perf/util/expr.c +++ b/tools/perf/util/expr.c @@ -73,7 +73,7 @@ int expr__add_id(struct expr_parse_ctx *ctx, const char *id) data_ptr->parent = ctx->parent; data_ptr->kind = EXPR_ID_DATA__PARENT; - ret = hashmap__set(&ctx->ids, id, data_ptr, + ret = hashmap__set(ctx->ids, id, data_ptr, (const void **)&old_key, (void **)&old_data); if (ret) free(data_ptr); @@ -95,7 +95,7 @@ int expr__add_id_val(struct expr_parse_ctx *ctx, const char *id, double val) data_ptr->val = val; data_ptr->kind = EXPR_ID_DATA__VALUE; - ret = hashmap__set(&ctx->ids, id, data_ptr, + ret = hashmap__set(ctx->ids, id, data_ptr, (const void **)&old_key, (void **)&old_data); if (ret) free(data_ptr); @@ -140,7 +140,7 @@ int expr__add_ref(struct expr_parse_ctx *ctx, struct metric_ref *ref) data_ptr->ref.metric_expr = ref->metric_expr; data_ptr->kind = EXPR_ID_DATA__REF; - ret = hashmap__set(&ctx->ids, name, data_ptr, + ret = hashmap__set(ctx->ids, name, data_ptr, (const void **)&old_key, (void **)&old_data); if (ret) free(data_ptr); @@ -156,7 +156,7 @@ int expr__add_ref(struct expr_parse_ctx *ctx, struct metric_ref *ref) int expr__get_id(struct expr_parse_ctx *ctx, const char *id, struct expr_id_data **data) { - return hashmap__find(&ctx->ids, id, (void **)data) ? 0 : -1; + return hashmap__find(ctx->ids, id, (void **)data) ? 0 : -1; } int expr__resolve_id(struct expr_parse_ctx *ctx, const char *id, @@ -205,15 +205,23 @@ void expr__del_id(struct expr_parse_ctx *ctx, const char *id) struct expr_id_data *old_val = NULL; char *old_key = NULL; - hashmap__delete(&ctx->ids, id, + hashmap__delete(ctx->ids, id, (const void **)&old_key, (void **)&old_val); free(old_key); free(old_val); } -void expr__ctx_init(struct expr_parse_ctx *ctx) +struct expr_parse_ctx *expr__ctx_new(void) { - hashmap__init(&ctx->ids, key_hash, key_equal, NULL); + struct expr_parse_ctx *ctx; + + ctx = malloc(sizeof(struct expr_parse_ctx)); + if (!ctx) + return NULL; + + ctx->ids = hashmap__new(key_hash, key_equal, NULL); + ctx->parent = NULL; + return ctx; } void expr__ctx_clear(struct expr_parse_ctx *ctx) @@ -221,11 +229,24 @@ void expr__ctx_clear(struct expr_parse_ctx *ctx) struct hashmap_entry *cur; size_t bkt; - hashmap__for_each_entry((&ctx->ids), cur, bkt) { + hashmap__for_each_entry(ctx->ids, cur, bkt) { free((char *)cur->key); free(cur->value); } - hashmap__clear(&ctx->ids); + hashmap__clear(ctx->ids); +} + +void expr__ctx_free(struct expr_parse_ctx *ctx) +{ + struct hashmap_entry *cur; + size_t bkt; + + hashmap__for_each_entry(ctx->ids, cur, bkt) { + free((char *)cur->key); + free(cur->value); + } + hashmap__free(ctx->ids); + free(ctx); } static int diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h index 85df3e4771e4..5fa394f10418 100644 --- a/tools/perf/util/expr.h +++ b/tools/perf/util/expr.h @@ -19,7 +19,7 @@ struct expr_id { }; struct expr_parse_ctx { - struct hashmap ids; + struct hashmap *ids; struct expr_id *parent; }; @@ -30,8 +30,9 @@ struct expr_scanner_ctx { int runtime; }; -void expr__ctx_init(struct expr_parse_ctx *ctx); +struct expr_parse_ctx *expr__ctx_new(void); void expr__ctx_clear(struct expr_parse_ctx *ctx); +void expr__ctx_free(struct expr_parse_ctx *ctx); void expr__del_id(struct expr_parse_ctx *ctx, const char *id); int expr__add_id(struct expr_parse_ctx *ctx, const char *id); int expr__add_id_val(struct expr_parse_ctx *ctx, const char *id, double val); diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 29b747ac31c1..b7924a2f1f45 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -118,7 +118,7 @@ struct metric_ref_node { struct metric { struct list_head nd; - struct expr_parse_ctx pctx; + struct expr_parse_ctx *pctx; const char *metric_name; const char *metric_expr; const char *metric_unit; @@ -198,7 +198,7 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, struct evsel *ev, *current_leader = NULL; struct expr_id_data *val_ptr; int i = 0, matched_events = 0, events_to_match; - const int idnum = (int)hashmap__size(&pctx->ids); + const int idnum = (int)hashmap__size(pctx->ids); /* * duration_time is always grouped separately, when events are grouped @@ -206,7 +206,7 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, * add it to metric_events at the end. */ if (!has_constraint && - hashmap__find(&pctx->ids, "duration_time", (void **)&val_ptr)) + hashmap__find(pctx->ids, "duration_time", (void **)&val_ptr)) events_to_match = idnum - 1; else events_to_match = idnum; @@ -242,7 +242,7 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, if (contains_event(metric_events, matched_events, ev->name)) continue; /* Does this event belong to the parse context? */ - if (hashmap__find(&pctx->ids, ev->name, (void **)&val_ptr)) + if (hashmap__find(pctx->ids, ev->name, (void **)&val_ptr)) metric_events[matched_events++] = ev; if (matched_events == events_to_match) @@ -322,12 +322,12 @@ static int metricgroup__setup_events(struct list_head *groups, struct metric_ref *metric_refs = NULL; metric_events = calloc(sizeof(void *), - hashmap__size(&m->pctx.ids) + 1); + hashmap__size(m->pctx->ids) + 1); if (!metric_events) { ret = -ENOMEM; break; } - evsel = find_evsel_group(perf_evlist, &m->pctx, + evsel = find_evsel_group(perf_evlist, m->pctx, metric_no_merge, m->has_constraint, metric_events, evlist_used); @@ -693,7 +693,7 @@ static void metricgroup__add_metric_weak_group(struct strbuf *events, size_t bkt; bool no_group = true, has_duration = false; - hashmap__for_each_entry((&ctx->ids), cur, bkt) { + hashmap__for_each_entry(ctx->ids, cur, bkt) { pr_debug("found event %s\n", (const char *)cur->key); /* * Duration time maps to a software event and can make @@ -724,7 +724,7 @@ static void metricgroup__add_metric_non_group(struct strbuf *events, size_t bkt; bool first = true; - hashmap__for_each_entry((&ctx->ids), cur, bkt) { + hashmap__for_each_entry(ctx->ids, cur, bkt) { if (!first) strbuf_addf(events, ","); strbuf_addf(events, "%s", (const char *)cur->key); @@ -799,7 +799,11 @@ static int __add_metric(struct list_head *metric_list, if (!m) return -ENOMEM; - expr__ctx_init(&m->pctx); + m->pctx = expr__ctx_new(); + if (!m->pctx) { + free(m); + return -ENOMEM; + } m->metric_name = pe->metric_name; m->metric_expr = pe->metric_expr; m->metric_unit = pe->unit; @@ -847,15 +851,15 @@ static int __add_metric(struct list_head *metric_list, /* Force all found IDs in metric to have us as parent ID. */ WARN_ON_ONCE(!parent); - m->pctx.parent = parent; + m->pctx->parent = parent; /* * For both the parent and referenced metrics, we parse * all the metric's IDs and add it to the parent context. */ - if (expr__find_other(pe->metric_expr, NULL, &m->pctx, runtime) < 0) { + if (expr__find_other(pe->metric_expr, NULL, m->pctx, runtime) < 0) { if (m->metric_refs_cnt == 0) { - expr__ctx_clear(&m->pctx); + expr__ctx_free(m->pctx); free(m); *mp = NULL; } @@ -878,8 +882,8 @@ static int __add_metric(struct list_head *metric_list, list_for_each_prev(pos, metric_list) { struct metric *old = list_entry(pos, struct metric, nd); - if (hashmap__size(&m->pctx.ids) <= - hashmap__size(&old->pctx.ids)) + if (hashmap__size(m->pctx->ids) <= + hashmap__size(old->pctx->ids)) break; } list_add(&m->nd, pos); @@ -927,7 +931,7 @@ static int recursion_check(struct metric *m, const char *id, struct expr_id **pa * if we already processed 'id', if we did, it's recursion * and we fail. */ - ret = expr__get_id(&m->pctx, id, &data); + ret = expr__get_id(m->pctx, id, &data); if (ret) return ret; @@ -982,7 +986,7 @@ static int __resolve_metric(struct metric *m, */ do { all = true; - hashmap__for_each_entry((&m->pctx.ids), cur, bkt) { + hashmap__for_each_entry(m->pctx->ids, cur, bkt) { struct expr_id *parent; struct pmu_event *pe; @@ -996,7 +1000,7 @@ static int __resolve_metric(struct metric *m, all = false; /* The metric key itself needs to go out.. */ - expr__del_id(&m->pctx, cur->key); + expr__del_id(m->pctx, cur->key); /* ... and it gets resolved to the parent context. */ ret = add_metric(metric_list, pe, metric_no_group, &m, parent, ids); @@ -1144,10 +1148,10 @@ static int metricgroup__add_metric(const char *metric, bool metric_no_group, if (m->has_constraint) { metricgroup__add_metric_non_group(events, - &m->pctx); + m->pctx); } else { metricgroup__add_metric_weak_group(events, - &m->pctx); + m->pctx); } } @@ -1210,7 +1214,7 @@ static void metricgroup__free_metrics(struct list_head *metric_list) list_for_each_entry_safe (m, tmp, metric_list, nd) { metric__free_refs(m); - expr__ctx_clear(&m->pctx); + expr__ctx_free(m->pctx); list_del_init(&m->nd); free(m); } diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 34a7f5c1fff7..c9fa07e49e72 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -1,8 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 +#include #include #include "evsel.h" #include "stat.h" #include "color.h" +#include "debug.h" #include "pmu.h" #include "rblist.h" #include "evlist.h" @@ -370,12 +372,16 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list) { struct evsel *counter, *leader, **metric_events, *oc; bool found; - struct expr_parse_ctx ctx; + struct expr_parse_ctx *ctx; struct hashmap_entry *cur; size_t bkt; int i; - expr__ctx_init(&ctx); + ctx = expr__ctx_new(); + if (!ctx) { + pr_debug("expr__ctx_new failed"); + return; + } evlist__for_each_entry(evsel_list, counter) { bool invalid = false; @@ -383,25 +389,25 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list) if (!counter->metric_expr) continue; - expr__ctx_clear(&ctx); + expr__ctx_clear(ctx); metric_events = counter->metric_events; if (!metric_events) { if (expr__find_other(counter->metric_expr, counter->name, - &ctx, 1) < 0) + ctx, 1) < 0) continue; metric_events = calloc(sizeof(struct evsel *), - hashmap__size(&ctx.ids) + 1); + hashmap__size(ctx->ids) + 1); if (!metric_events) { - expr__ctx_clear(&ctx); + expr__ctx_free(ctx); return; } counter->metric_events = metric_events; } i = 0; - hashmap__for_each_entry((&ctx.ids), cur, bkt) { + hashmap__for_each_entry(ctx->ids, cur, bkt) { const char *metric_name = (const char *)cur->key; found = false; @@ -453,7 +459,7 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list) counter->metric_expr = NULL; } } - expr__ctx_clear(&ctx); + expr__ctx_free(ctx); } static double runtime_stat_avg(struct runtime_stat *st, @@ -818,7 +824,6 @@ static int prepare_metric(struct evsel **metric_events, char *n, *pn; int i, j, ret; - expr__ctx_init(pctx); for (i = 0; metric_events[i]; i++) { struct saved_value *v; struct stats *stats; @@ -880,17 +885,22 @@ static void generic_metric(struct perf_stat_config *config, struct runtime_stat *st) { print_metric_t print_metric = out->print_metric; - struct expr_parse_ctx pctx; + struct expr_parse_ctx *pctx; double ratio, scale; int i; void *ctxp = out->ctx; - i = prepare_metric(metric_events, metric_refs, &pctx, cpu, st); - if (i < 0) + pctx = expr__ctx_new(); + if (!pctx) return; + i = prepare_metric(metric_events, metric_refs, pctx, cpu, st); + if (i < 0) { + expr__ctx_free(pctx); + return; + } if (!metric_events[i]) { - if (expr__parse(&ratio, &pctx, metric_expr, runtime) == 0) { + if (expr__parse(&ratio, pctx, metric_expr, runtime) == 0) { char *unit; char metric_bf[64]; @@ -926,22 +936,26 @@ static void generic_metric(struct perf_stat_config *config, (metric_name ? metric_name : name) : "", 0); } - expr__ctx_clear(&pctx); + expr__ctx_free(pctx); } double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_stat *st) { - struct expr_parse_ctx pctx; + struct expr_parse_ctx *pctx; double ratio = 0.0; - if (prepare_metric(mexp->metric_events, mexp->metric_refs, &pctx, cpu, st) < 0) + pctx = expr__ctx_new(); + if (!pctx) + return NAN; + + if (prepare_metric(mexp->metric_events, mexp->metric_refs, pctx, cpu, st) < 0) goto out; - if (expr__parse(&ratio, &pctx, mexp->metric_expr, 1)) + if (expr__parse(&ratio, pctx, mexp->metric_expr, 1)) ratio = 0.0; out: - expr__ctx_clear(&pctx); + expr__ctx_free(pctx); return ratio; } From edfe7f554ab8f083556c718ecbcefda509c46851 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 23 Sep 2021 00:46:05 -0700 Subject: [PATCH 106/587] perf metric: Use NAN for missing event IDs. If during computing a metric an event (id) is missing the parsing aborts. A later patch will make it so that events that aren't used in the output are deliberately omitted, in which case we don't want the abort. Modify the missing ID case to report NAN for these cases. Reviewed-by: Andi Kleen Signed-off-by: Ian Rogers Tested-by: John Garry Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jin Yao Cc: Kajol Jain Cc: Mark Rutland Cc: Namhyung Kim Cc: Paul Clarke Cc: Peter Zijlstra Cc: Sandeep Dasgupta Cc: Stephane Eranian Link: https://lore.kernel.org/r/20210923074616.674826-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/expr.y | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index b2ada8f8309a..41c9cd4efadd 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -1,6 +1,7 @@ /* Simple expression parser */ %{ #define YYDEBUG 1 +#include #include #include "util.h" #include "util/debug.h" @@ -88,12 +89,10 @@ expr: NUMBER | ID { struct expr_id_data *data; - if (expr__resolve_id(ctx, $1, &data)) { - free($1); - YYABORT; - } + $$ = NAN; + if (expr__resolve_id(ctx, $1, &data) == 0) + $$ = expr_id_data__value(data); - $$ = expr_id_data__value(data); free($1); } | expr '|' expr { $$ = (long)$1 | (long)$3; } From 7f8fdcbbbefb2d95259aa76a362689affafa4e4b Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 23 Sep 2021 00:46:06 -0700 Subject: [PATCH 107/587] perf expr: Remove unused headers and inline d_ratio No functional change. Inlining d_ratio makes it easier to special case for constants in a later patch. Signed-off-by: Ian Rogers Tested-by: John Garry Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ingo Molnar Cc: Kajol Jain Cc: Jin Yao Cc: Mark Rutland Cc: Namhyung Kim Cc: Paul Clarke Cc: Peter Zijlstra Cc: Sandeep Dasgupta Cc: Stephane Eranian Link: https://lore.kernel.org/r/20210923074616.674826-4-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/expr.y | 22 +++++++--------------- 1 file changed, 7 insertions(+), 15 deletions(-) diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index 41c9cd4efadd..e6005450feae 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -2,23 +2,10 @@ %{ #define YYDEBUG 1 #include -#include -#include "util.h" #include "util/debug.h" -#include // strtod() +#include "smt.h" #define IN_EXPR_Y 1 #include "expr.h" -#include "smt.h" -#include - -static double d_ratio(double val0, double val1) -{ - if (val1 == 0) { - return 0; - } - return val0 / val1; -} - %} %define api.pure full @@ -120,7 +107,12 @@ expr: NUMBER | MIN '(' expr ',' expr ')' { $$ = $3 < $5 ? $3 : $5; } | MAX '(' expr ',' expr ')' { $$ = $3 > $5 ? $3 : $5; } | SMT_ON { $$ = smt_on() > 0; } - | D_RATIO '(' expr ',' expr ')' { $$ = d_ratio($3,$5); } + | D_RATIO '(' expr ',' expr ')' { if ($5 == 0) { + $$ = 0; + } else { + $$ = $3 / $5; + } + } ; %% From aed0d6f8c6edab48be649a071e18d28efb1a203a Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 23 Sep 2021 00:46:07 -0700 Subject: [PATCH 108/587] perf expr: Separate token declataion from type No functional change, so the type of expr remains . A later patch will change the computation to be an aggregate type and making this change makes that later change smaller. Signed-off-by: Ian Rogers Tested-by: John Garry Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ingo Molnar Cc: Jin Yao Cc: Kajol Jain Cc: Mark Rutland Cc: Namhyung Kim Cc: Paul Clarke Cc: Peter Zijlstra Cc: Sandeep Dasgupta Cc: Stephane Eranian Link: https://lore.kernel.org/r/20210923074616.674826-5-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/expr.y | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index e6005450feae..68b122e59b3f 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -20,11 +20,7 @@ char *str; } -%token EXPR_PARSE EXPR_OTHER EXPR_ERROR -%token NUMBER -%token ID -%destructor { free ($$); } -%token MIN MAX IF ELSE SMT_ON D_RATIO +%token ID NUMBER MIN MAX IF ELSE SMT_ON D_RATIO EXPR_ERROR EXPR_PARSE EXPR_OTHER %left MIN MAX IF %left '|' %left '^' @@ -33,6 +29,9 @@ %left '-' '+' %left '*' '/' '%' %left NEG NOT +%type NUMBER +%type ID +%destructor { free ($$); } %type expr if_expr %{ From e87576c5ac14e038ac96145d289bf0134eb08506 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 23 Sep 2021 00:46:08 -0700 Subject: [PATCH 109/587] perf expr: Use macros for operators No functional change, switch the operators to use macros so that additional complexity for constants can be added in a later change. Signed-off-by: Ian Rogers Tested-by: John Garry Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ingo Molnar Cc: Jin Yao Cc: Kajol Jain Cc: Mark Rutland Cc: Namhyung Kim Cc: Paul Clarke Cc: Peter Zijlstra Cc: Sandeep Dasgupta Cc: Stephane Eranian Link: https://lore.kernel.org/r/20210923074616.674826-6-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/expr.y | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index 68b122e59b3f..5535badeef0a 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -43,6 +43,12 @@ static void expr_error(double *final_val __maybe_unused, pr_debug("%s\n", s); } +#define BINARY_LONG_OP(RESULT, OP, LHS, RHS) \ + RESULT = (long)LHS OP (long)RHS; + +#define BINARY_OP(RESULT, OP, LHS, RHS) \ + RESULT = LHS OP RHS; + %} %% @@ -81,14 +87,14 @@ expr: NUMBER free($1); } - | expr '|' expr { $$ = (long)$1 | (long)$3; } - | expr '&' expr { $$ = (long)$1 & (long)$3; } - | expr '^' expr { $$ = (long)$1 ^ (long)$3; } - | expr '<' expr { $$ = $1 < $3; } - | expr '>' expr { $$ = $1 > $3; } - | expr '+' expr { $$ = $1 + $3; } - | expr '-' expr { $$ = $1 - $3; } - | expr '*' expr { $$ = $1 * $3; } + | expr '|' expr { BINARY_LONG_OP($$, |, $1, $3); } + | expr '&' expr { BINARY_LONG_OP($$, &, $1, $3); } + | expr '^' expr { BINARY_LONG_OP($$, ^, $1, $3); } + | expr '<' expr { BINARY_OP($$, <, $1, $3); } + | expr '>' expr { BINARY_OP($$, >, $1, $3); } + | expr '+' expr { BINARY_OP($$, +, $1, $3); } + | expr '-' expr { BINARY_OP($$, -, $1, $3); } + | expr '*' expr { BINARY_OP($$, *, $1, $3); } | expr '/' expr { if ($3 == 0) { pr_debug("division by zero\n"); YYABORT; From c924e0cc0576b4e45b9c495174cd785aa41d51ad Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 23 Sep 2021 00:46:09 -0700 Subject: [PATCH 110/587] perf expr: Move actions to the left. No functional change, just modifying whitespace. This creates additional space for adding logic to actions in later changes. Signed-off-by: Ian Rogers Tested-by: John Garry Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ingo Molnar Cc: Jin Yao Cc: Kajol Jain Cc: Mark Rutland Cc: Namhyung Kim Cc: Paul Clarke Cc: Peter Zijlstra Cc: Sandeep Dasgupta Cc: Stephane Eranian Link: https://lore.kernel.org/r/20210923074616.674826-7-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/expr.y | 116 +++++++++++++++++++++++++---------------- 1 file changed, 71 insertions(+), 45 deletions(-) diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index 5535badeef0a..78cbe377eb0e 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -70,54 +70,80 @@ MIN | MAX | IF | ELSE | SMT_ON | NUMBER | '|' | '^' | '&' | '-' | '+' | '*' | '/ '<' | '>' | D_RATIO all_expr: if_expr { *final_val = $1; } - ; -if_expr: - expr IF expr ELSE expr { $$ = $3 ? $1 : $5; } - | expr - ; +if_expr: expr IF expr ELSE expr +{ + $$ = $3 ? $1 : $5; +} +| expr +; -expr: NUMBER - | ID { - struct expr_id_data *data; +expr: NUMBER +{ + $$ = $1; +} +| ID +{ + struct expr_id_data *data; - $$ = NAN; - if (expr__resolve_id(ctx, $1, &data) == 0) - $$ = expr_id_data__value(data); + $$ = NAN; + if (expr__resolve_id(ctx, $1, &data) == 0) + $$ = expr_id_data__value(data); - free($1); - } - | expr '|' expr { BINARY_LONG_OP($$, |, $1, $3); } - | expr '&' expr { BINARY_LONG_OP($$, &, $1, $3); } - | expr '^' expr { BINARY_LONG_OP($$, ^, $1, $3); } - | expr '<' expr { BINARY_OP($$, <, $1, $3); } - | expr '>' expr { BINARY_OP($$, >, $1, $3); } - | expr '+' expr { BINARY_OP($$, +, $1, $3); } - | expr '-' expr { BINARY_OP($$, -, $1, $3); } - | expr '*' expr { BINARY_OP($$, *, $1, $3); } - | expr '/' expr { if ($3 == 0) { - pr_debug("division by zero\n"); - YYABORT; - } - $$ = $1 / $3; - } - | expr '%' expr { if ((long)$3 == 0) { - pr_debug("division by zero\n"); - YYABORT; - } - $$ = (long)$1 % (long)$3; - } - | '-' expr %prec NEG { $$ = -$2; } - | '(' if_expr ')' { $$ = $2; } - | MIN '(' expr ',' expr ')' { $$ = $3 < $5 ? $3 : $5; } - | MAX '(' expr ',' expr ')' { $$ = $3 > $5 ? $3 : $5; } - | SMT_ON { $$ = smt_on() > 0; } - | D_RATIO '(' expr ',' expr ')' { if ($5 == 0) { - $$ = 0; - } else { - $$ = $3 / $5; - } - } - ; + free($1); +} +| expr '|' expr { BINARY_LONG_OP($$, |, $1, $3); } +| expr '&' expr { BINARY_LONG_OP($$, &, $1, $3); } +| expr '^' expr { BINARY_LONG_OP($$, ^, $1, $3); } +| expr '<' expr { BINARY_OP($$, <, $1, $3); } +| expr '>' expr { BINARY_OP($$, >, $1, $3); } +| expr '+' expr { BINARY_OP($$, +, $1, $3); } +| expr '-' expr { BINARY_OP($$, -, $1, $3); } +| expr '*' expr { BINARY_OP($$, *, $1, $3); } +| expr '/' expr +{ + if ($3 == 0) { + pr_debug("division by zero\n"); + YYABORT; + } + $$ = $1 / $3; +} +| expr '%' expr +{ + if ((long)$3 == 0) { + pr_debug("division by zero\n"); + YYABORT; + } + $$ = (long)$1 % (long)$3; +} +| D_RATIO '(' expr ',' expr ')' +{ + if ($5 == 0) { + $$ = 0; + } else { + $$ = $3 / $5; + } +} +| '-' expr %prec NEG +{ + $$ = -$2; +} +| '(' if_expr ')' +{ + $$ = $2; +} +| MIN '(' expr ',' expr ')' +{ + $$ = $3 < $5 ? $3 : $5; +} +| MAX '(' expr ',' expr ')' +{ + $$ = $3 > $5 ? $3 : $5; +} +| SMT_ON +{ + $$ = smt_on() > 0 ? 1.0 : 0.0; +} +; %% From 7e06a5e30a0c5155291efab8cf866ffea052f829 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 23 Sep 2021 00:46:10 -0700 Subject: [PATCH 111/587] perf metric: Rename expr__find_other. A later change will remove the notion of other, rename the function to expr__find_ids as this is what it populates. Signed-off-by: Ian Rogers Tested-by: John Garry Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ingo Molnar Cc: Jin Yao Cc: Kajol Jain Cc: Mark Rutland Cc: Namhyung Kim Cc: Paul Clarke Cc: Peter Zijlstra Cc: Sandeep Dasgupta Cc: Stephane Eranian Link: https://lore.kernel.org/r/20210923074616.674826-8-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/expr.c | 26 +++++++++++++------------- tools/perf/tests/pmu-events.c | 11 +++++------ tools/perf/util/expr.c | 4 ++-- tools/perf/util/expr.h | 2 +- tools/perf/util/metricgroup.c | 2 +- tools/perf/util/stat-shadow.c | 6 +++--- 6 files changed, 25 insertions(+), 26 deletions(-) diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index b0a3b5fd0c00..7ccb97c73347 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -64,25 +64,25 @@ int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused) TEST_ASSERT_VAL("missing operand", ret == -1); expr__ctx_clear(ctx); - TEST_ASSERT_VAL("find other", - expr__find_other("FOO + BAR + BAZ + BOZO", "FOO", - ctx, 1) == 0); - TEST_ASSERT_VAL("find other", hashmap__size(ctx->ids) == 3); - TEST_ASSERT_VAL("find other", hashmap__find(ctx->ids, "BAR", + TEST_ASSERT_VAL("find ids", + expr__find_ids("FOO + BAR + BAZ + BOZO", "FOO", + ctx, 1) == 0); + TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 3); + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BAR", (void **)&val_ptr)); - TEST_ASSERT_VAL("find other", hashmap__find(ctx->ids, "BAZ", + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BAZ", (void **)&val_ptr)); - TEST_ASSERT_VAL("find other", hashmap__find(ctx->ids, "BOZO", + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BOZO", (void **)&val_ptr)); expr__ctx_clear(ctx); - TEST_ASSERT_VAL("find other", - expr__find_other("EVENT1\\,param\\=?@ + EVENT2\\,param\\=?@", - NULL, ctx, 3) == 0); - TEST_ASSERT_VAL("find other", hashmap__size(ctx->ids) == 2); - TEST_ASSERT_VAL("find other", hashmap__find(ctx->ids, "EVENT1,param=3/", + TEST_ASSERT_VAL("find ids", + expr__find_ids("EVENT1\\,param\\=?@ + EVENT2\\,param\\=?@", + NULL, ctx, 3) == 0); + TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 2); + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "EVENT1,param=3/", (void **)&val_ptr)); - TEST_ASSERT_VAL("find other", hashmap__find(ctx->ids, "EVENT2,param=3/", + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "EVENT2,param=3/", (void **)&val_ptr)); expr__ctx_free(ctx); diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index 91076ab0514b..d3534960ed25 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -866,7 +866,7 @@ static int resolve_metric_simple(struct expr_parse_ctx *pctx, ref->metric_expr = pe->metric_expr; list_add_tail(&metric->list, compound_list); - rc = expr__find_other(pe->metric_expr, NULL, pctx, 0); + rc = expr__find_ids(pe->metric_expr, NULL, pctx, 0); if (rc) goto out_err; break; /* The hashmap has been modified, so restart */ @@ -916,9 +916,8 @@ static int test_parsing(void) if (!pe->metric_expr) continue; expr__ctx_clear(ctx); - if (expr__find_other(pe->metric_expr, NULL, ctx, 0) - < 0) { - expr_failure("Parse other failed", map, pe); + if (expr__find_ids(pe->metric_expr, NULL, ctx, 0) < 0) { + expr_failure("Parse find ids failed", map, pe); ret++; continue; } @@ -990,8 +989,8 @@ static int metric_parse_fake(const char *str) pr_debug("expr__ctx_new failed"); return TEST_FAIL; } - if (expr__find_other(str, NULL, ctx, 0) < 0) { - pr_err("expr__find_other failed\n"); + if (expr__find_ids(str, NULL, ctx, 0) < 0) { + pr_err("expr__find_ids failed\n"); return -1; } diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c index 7b1c06772a49..adf16bb7571a 100644 --- a/tools/perf/util/expr.c +++ b/tools/perf/util/expr.c @@ -288,8 +288,8 @@ int expr__parse(double *final_val, struct expr_parse_ctx *ctx, return __expr__parse(final_val, ctx, expr, EXPR_PARSE, runtime) ? -1 : 0; } -int expr__find_other(const char *expr, const char *one, - struct expr_parse_ctx *ctx, int runtime) +int expr__find_ids(const char *expr, const char *one, + struct expr_parse_ctx *ctx, int runtime) { int ret = __expr__parse(NULL, ctx, expr, EXPR_OTHER, runtime); diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h index 5fa394f10418..de109c2ab917 100644 --- a/tools/perf/util/expr.h +++ b/tools/perf/util/expr.h @@ -43,7 +43,7 @@ int expr__resolve_id(struct expr_parse_ctx *ctx, const char *id, struct expr_id_data **datap); int expr__parse(double *final_val, struct expr_parse_ctx *ctx, const char *expr, int runtime); -int expr__find_other(const char *expr, const char *one, +int expr__find_ids(const char *expr, const char *one, struct expr_parse_ctx *ids, int runtime); double expr_id_data__value(const struct expr_id_data *data); diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index b7924a2f1f45..046fb3fe1700 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -857,7 +857,7 @@ static int __add_metric(struct list_head *metric_list, * For both the parent and referenced metrics, we parse * all the metric's IDs and add it to the parent context. */ - if (expr__find_other(pe->metric_expr, NULL, m->pctx, runtime) < 0) { + if (expr__find_ids(pe->metric_expr, NULL, m->pctx, runtime) < 0) { if (m->metric_refs_cnt == 0) { expr__ctx_free(m->pctx); free(m); diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index c9fa07e49e72..9bc841e09a0c 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -392,9 +392,9 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list) expr__ctx_clear(ctx); metric_events = counter->metric_events; if (!metric_events) { - if (expr__find_other(counter->metric_expr, - counter->name, - ctx, 1) < 0) + if (expr__find_ids(counter->metric_expr, + counter->name, + ctx, 1) < 0) continue; metric_events = calloc(sizeof(struct evsel *), From 114a9d6e396eeb061fa532803ff9a6fd3a966ad8 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 23 Sep 2021 00:46:11 -0700 Subject: [PATCH 112/587] perf metric: Add utilities to work on ids map. Add utilities to new/free an ids hashmap, as well as to union. Add testing of the union. Unioning hashmaps will be used when parsing the metric, if a value is known then the hashmap is unnecessary, otherwise we need to union together all the event ids to compute their values for reporting. Signed-off-by: Ian Rogers Tested-by: John Garry Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ingo Molnar Cc: Jin Yao Cc: Kajol Jain Cc: Mark Rutland Cc: Namhyung Kim Cc: Paul Clarke Cc: Peter Zijlstra Cc: Sandeep Dasgupta Cc: Stephane Eranian Link: https://lore.kernel.org/r/20210923074616.674826-9-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/expr.c | 47 +++++++++++++++++++++++++++ tools/perf/util/expr.c | 71 ++++++++++++++++++++++++++++++++++++++--- tools/perf/util/expr.h | 12 +++++++ 3 files changed, 126 insertions(+), 4 deletions(-) diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index 7ccb97c73347..1c881bea7fca 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -6,6 +6,51 @@ #include #include +static int test_ids_union(void) +{ + struct hashmap *ids1, *ids2; + + /* Empty union. */ + ids1 = ids__new(); + TEST_ASSERT_VAL("ids__new", ids1); + ids2 = ids__new(); + TEST_ASSERT_VAL("ids__new", ids2); + + ids1 = ids__union(ids1, ids2); + TEST_ASSERT_EQUAL("union", (int)hashmap__size(ids1), 0); + + /* Union {foo, bar} against {}. */ + ids2 = ids__new(); + TEST_ASSERT_VAL("ids__new", ids2); + + TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids1, strdup("foo"), NULL), 0); + TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids1, strdup("bar"), NULL), 0); + + ids1 = ids__union(ids1, ids2); + TEST_ASSERT_EQUAL("union", (int)hashmap__size(ids1), 2); + + /* Union {foo, bar} against {foo}. */ + ids2 = ids__new(); + TEST_ASSERT_VAL("ids__new", ids2); + TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids2, strdup("foo"), NULL), 0); + + ids1 = ids__union(ids1, ids2); + TEST_ASSERT_EQUAL("union", (int)hashmap__size(ids1), 2); + + /* Union {foo, bar} against {bar,baz}. */ + ids2 = ids__new(); + TEST_ASSERT_VAL("ids__new", ids2); + TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids2, strdup("bar"), NULL), 0); + TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids2, strdup("baz"), NULL), 0); + + ids1 = ids__union(ids1, ids2); + TEST_ASSERT_EQUAL("union", (int)hashmap__size(ids1), 3); + + ids__free(ids1); + + return 0; +} + static int test(struct expr_parse_ctx *ctx, const char *e, double val2) { double val; @@ -24,6 +69,8 @@ int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused) int ret; struct expr_parse_ctx *ctx; + TEST_ASSERT_EQUAL("ids_union", test_ids_union(), 0); + ctx = expr__ctx_new(); TEST_ASSERT_VAL("expr__ctx_new", ctx); expr__add_id_val(ctx, strdup("FOO"), 1); diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c index adf16bb7571a..81101be51044 100644 --- a/tools/perf/util/expr.c +++ b/tools/perf/util/expr.c @@ -59,8 +59,29 @@ static bool key_equal(const void *key1, const void *key2, return !strcmp((const char *)key1, (const char *)key2); } -/* Caller must make sure id is allocated */ -int expr__add_id(struct expr_parse_ctx *ctx, const char *id) +struct hashmap *ids__new(void) +{ + return hashmap__new(key_hash, key_equal, NULL); +} + +void ids__free(struct hashmap *ids) +{ + struct hashmap_entry *cur; + size_t bkt; + + if (ids == NULL) + return; + + hashmap__for_each_entry(ids, cur, bkt) { + free((char *)cur->key); + free(cur->value); + } + + hashmap__free(ids); +} + +int ids__insert(struct hashmap *ids, const char *id, + struct expr_id *parent) { struct expr_id_data *data_ptr = NULL, *old_data = NULL; char *old_key = NULL; @@ -70,10 +91,10 @@ int expr__add_id(struct expr_parse_ctx *ctx, const char *id) if (!data_ptr) return -ENOMEM; - data_ptr->parent = ctx->parent; + data_ptr->parent = parent; data_ptr->kind = EXPR_ID_DATA__PARENT; - ret = hashmap__set(ctx->ids, id, data_ptr, + ret = hashmap__set(ids, id, data_ptr, (const void **)&old_key, (void **)&old_data); if (ret) free(data_ptr); @@ -82,6 +103,48 @@ int expr__add_id(struct expr_parse_ctx *ctx, const char *id) return ret; } +struct hashmap *ids__union(struct hashmap *ids1, struct hashmap *ids2) +{ + size_t bkt; + struct hashmap_entry *cur; + int ret; + struct expr_id_data *old_data = NULL; + char *old_key = NULL; + + if (!ids1) + return ids2; + + if (!ids2) + return ids1; + + if (hashmap__size(ids1) < hashmap__size(ids2)) { + struct hashmap *tmp = ids1; + + ids1 = ids2; + ids2 = tmp; + } + hashmap__for_each_entry(ids2, cur, bkt) { + ret = hashmap__set(ids1, cur->key, cur->value, + (const void **)&old_key, (void **)&old_data); + free(old_key); + free(old_data); + + if (ret) { + hashmap__free(ids1); + hashmap__free(ids2); + return NULL; + } + } + hashmap__free(ids2); + return ids1; +} + +/* Caller must make sure id is allocated */ +int expr__add_id(struct expr_parse_ctx *ctx, const char *id) +{ + return ids__insert(ctx->ids, id, ctx->parent); +} + /* Caller must make sure id is allocated */ int expr__add_id_val(struct expr_parse_ctx *ctx, const char *id, double val) { diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h index de109c2ab917..4ed186bd1f13 100644 --- a/tools/perf/util/expr.h +++ b/tools/perf/util/expr.h @@ -30,9 +30,19 @@ struct expr_scanner_ctx { int runtime; }; +struct hashmap *ids__new(void); +void ids__free(struct hashmap *ids); +int ids__insert(struct hashmap *ids, const char *id, struct expr_id *parent); +/* + * Union two sets of ids (hashmaps) and construct a third, freeing ids1 and + * ids2. + */ +struct hashmap *ids__union(struct hashmap *ids1, struct hashmap *ids2); + struct expr_parse_ctx *expr__ctx_new(void); void expr__ctx_clear(struct expr_parse_ctx *ctx); void expr__ctx_free(struct expr_parse_ctx *ctx); + void expr__del_id(struct expr_parse_ctx *ctx, const char *id); int expr__add_id(struct expr_parse_ctx *ctx, const char *id); int expr__add_id_val(struct expr_parse_ctx *ctx, const char *id, double val); @@ -41,8 +51,10 @@ int expr__get_id(struct expr_parse_ctx *ctx, const char *id, struct expr_id_data **data); int expr__resolve_id(struct expr_parse_ctx *ctx, const char *id, struct expr_id_data **datap); + int expr__parse(double *final_val, struct expr_parse_ctx *ctx, const char *expr, int runtime); + int expr__find_ids(const char *expr, const char *one, struct expr_parse_ctx *ids, int runtime); From 762a05c561bcc36ccde6a25e268888383e6adb83 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 23 Sep 2021 00:46:12 -0700 Subject: [PATCH 113/587] perf metric: Allow metrics with no events A metric may be a constant value, for example, some SMT metrics are constant 0 if #smt_on is 0. If we eliminate all the events then there is no printing. Fix this by forcing metrics like this to have a duration_time tool event, previously the metric would fail when parsing the events with a parse error. Signed-off-by: Ian Rogers Tested-by: John Garry Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ingo Molnar Cc: Jin Yao Cc: Kajol Jain Cc: Mark Rutland Cc: Namhyung Kim Cc: Paul Clarke Cc: Peter Zijlstra Cc: Sandeep Dasgupta Cc: Stephane Eranian Link: https://lore.kernel.org/r/20210923074616.674826-10-irogers@google.com [ Reflow one __parse_events() call so that a ternary operation gets in a single line ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/metricgroup.c | 106 ++++++++++++++++++---------------- 1 file changed, 56 insertions(+), 50 deletions(-) diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 046fb3fe1700..8ba5370f5f64 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -198,65 +198,69 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, struct evsel *ev, *current_leader = NULL; struct expr_id_data *val_ptr; int i = 0, matched_events = 0, events_to_match; - const int idnum = (int)hashmap__size(pctx->ids); + int idnum = (int)hashmap__size(pctx->ids); - /* - * duration_time is always grouped separately, when events are grouped - * (ie has_constraint is false) then ignore it in the matching loop and - * add it to metric_events at the end. - */ - if (!has_constraint && - hashmap__find(pctx->ids, "duration_time", (void **)&val_ptr)) - events_to_match = idnum - 1; - else + if (idnum != 0) { + /* + * duration_time is always grouped separately, when events are + * grouped (ie has_constraint is false) then ignore it in the + * matching loop and add it to metric_events at the end. + */ events_to_match = idnum; + if (!has_constraint && hashmap__find(pctx->ids, "duration_time", (void **)&val_ptr)) + events_to_match--; - evlist__for_each_entry (perf_evlist, ev) { - /* - * Events with a constraint aren't grouped and match the first - * events available. - */ - if (has_constraint && ev->weak_group) - continue; - /* Ignore event if already used and merging is disabled. */ - if (metric_no_merge && test_bit(ev->core.idx, evlist_used)) - continue; - if (!has_constraint && !evsel__has_leader(ev, current_leader)) { + evlist__for_each_entry(perf_evlist, ev) { /* - * Start of a new group, discard the whole match and - * start again. + * Events with a constraint aren't grouped and match the + * first events available. */ - matched_events = 0; - memset(metric_events, 0, - sizeof(struct evsel *) * idnum); - current_leader = evsel__leader(ev); + if (has_constraint && ev->weak_group) + continue; + /* Ignore event if already used and merging is disabled. */ + if (metric_no_merge && test_bit(ev->core.idx, evlist_used)) + continue; + if (!has_constraint && !evsel__has_leader(ev, current_leader)) { + /* + * Start of a new group, discard the whole match + * and start again. + */ + matched_events = 0; + memset(metric_events, 0, sizeof(struct evsel *) * idnum); + current_leader = evsel__leader(ev); + } + /* + * Check for duplicate events with the same name. For + * example, uncore_imc/cas_count_read/ will turn into 6 + * events per socket on skylakex. Only the first such + * event is placed in metric_events. If events aren't + * grouped then this also ensures that the same event in + * different sibling groups aren't both added to + * metric_events. + */ + if (contains_event(metric_events, matched_events, ev->name)) + continue; + /* Does this event belong to the parse context? */ + if (hashmap__find(pctx->ids, ev->name, (void **)&val_ptr)) + metric_events[matched_events++] = ev; + + if (matched_events == events_to_match) + break; } + } else { /* - * Check for duplicate events with the same name. For example, - * uncore_imc/cas_count_read/ will turn into 6 events per socket - * on skylakex. Only the first such event is placed in - * metric_events. If events aren't grouped then this also - * ensures that the same event in different sibling groups - * aren't both added to metric_events. + * There are no events to match, but we need to associate the + * metric with an event for printing. A duration_time event was + * parsed for this. */ - if (contains_event(metric_events, matched_events, ev->name)) - continue; - /* Does this event belong to the parse context? */ - if (hashmap__find(pctx->ids, ev->name, (void **)&val_ptr)) - metric_events[matched_events++] = ev; - - if (matched_events == events_to_match) - break; + idnum = 1; + events_to_match = 0; } - if (events_to_match != idnum) { /* Add the first duration_time. */ - evlist__for_each_entry(perf_evlist, ev) { - if (!strcmp(ev->name, "duration_time")) { - metric_events[matched_events++] = ev; - break; - } - } + ev = evlist__find_evsel_by_str(perf_evlist, "duration_time"); + if (ev) + metric_events[matched_events++] = ev; } if (matched_events != idnum) { @@ -320,9 +324,10 @@ static int metricgroup__setup_events(struct list_head *groups, list_for_each_entry (m, groups, nd) { struct evsel **metric_events; struct metric_ref *metric_refs = NULL; + const size_t ids_size = hashmap__size(m->pctx->ids); metric_events = calloc(sizeof(void *), - hashmap__size(m->pctx->ids) + 1); + ids_size == 0 ? 2 : ids_size + 1); if (!metric_events) { ret = -ENOMEM; break; @@ -1240,7 +1245,8 @@ static int parse_groups(struct evlist *perf_evlist, const char *str, goto out; pr_debug("adding %s\n", extra_events.buf); bzero(&parse_error, sizeof(parse_error)); - ret = __parse_events(perf_evlist, extra_events.buf, &parse_error, fake_pmu); + ret = __parse_events(perf_evlist, extra_events.len > 0 ? extra_events.buf : "duration_time", + &parse_error, fake_pmu); if (ret) { parse_events_print_error(&parse_error, extra_events.buf); goto out; From 3f965a7df09d7eebde0020cefe427219afe7df4a Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 23 Sep 2021 00:46:13 -0700 Subject: [PATCH 114/587] perf expr: Merge find_ids and regular parsing Add a new option to parsing that the set of IDs being used should be computed, this means every action needs to handle the compute_ids and regular case. This means actions yield a new ids type is a set of ids or the value being computed. Use the compute_ids case to replace find IDs parsing. Signed-off-by: Ian Rogers Tested-by: John Garry Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ingo Molnar Cc: Jin Yao Cc: Kajol Jain Cc: Mark Rutland Cc: Namhyung Kim Cc: Paul Clarke Cc: Peter Zijlstra Cc: Sandeep Dasgupta Cc: Stephane Eranian Link: https://lore.kernel.org/r/20210923074616.674826-11-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/expr.c | 9 +-- tools/perf/util/expr.h | 1 - tools/perf/util/expr.l | 9 --- tools/perf/util/expr.y | 172 +++++++++++++++++++++++++++++++---------- 4 files changed, 134 insertions(+), 57 deletions(-) diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c index 81101be51044..db2445677c8c 100644 --- a/tools/perf/util/expr.c +++ b/tools/perf/util/expr.c @@ -314,10 +314,9 @@ void expr__ctx_free(struct expr_parse_ctx *ctx) static int __expr__parse(double *val, struct expr_parse_ctx *ctx, const char *expr, - int start, int runtime) + bool compute_ids, int runtime) { struct expr_scanner_ctx scanner_ctx = { - .start_token = start, .runtime = runtime, }; YY_BUFFER_STATE buffer; @@ -337,7 +336,7 @@ __expr__parse(double *val, struct expr_parse_ctx *ctx, const char *expr, expr_set_debug(1, scanner); #endif - ret = expr_parse(val, ctx, scanner); + ret = expr_parse(val, ctx, compute_ids, scanner); expr__flush_buffer(buffer, scanner); expr__delete_buffer(buffer, scanner); @@ -348,13 +347,13 @@ __expr__parse(double *val, struct expr_parse_ctx *ctx, const char *expr, int expr__parse(double *final_val, struct expr_parse_ctx *ctx, const char *expr, int runtime) { - return __expr__parse(final_val, ctx, expr, EXPR_PARSE, runtime) ? -1 : 0; + return __expr__parse(final_val, ctx, expr, /*compute_ids=*/false, runtime) ? -1 : 0; } int expr__find_ids(const char *expr, const char *one, struct expr_parse_ctx *ctx, int runtime) { - int ret = __expr__parse(NULL, ctx, expr, EXPR_OTHER, runtime); + int ret = __expr__parse(NULL, ctx, expr, /*compute_ids=*/true, runtime); if (one) expr__del_id(ctx, one); diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h index 4ed186bd1f13..b20513f0ae59 100644 --- a/tools/perf/util/expr.h +++ b/tools/perf/util/expr.h @@ -26,7 +26,6 @@ struct expr_parse_ctx { struct expr_id_data; struct expr_scanner_ctx { - int start_token; int runtime; }; diff --git a/tools/perf/util/expr.l b/tools/perf/util/expr.l index 13e5e3c75f56..702fdf6456ca 100644 --- a/tools/perf/util/expr.l +++ b/tools/perf/util/expr.l @@ -91,15 +91,6 @@ symbol ({spec}|{sym})+ %% struct expr_scanner_ctx *sctx = expr_get_extra(yyscanner); - { - int start_token = sctx->start_token; - - if (sctx->start_token) { - sctx->start_token = 0; - return start_token; - } - } - d_ratio { return D_RATIO; } max { return MAX; } min { return MIN; } diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index 78cbe377eb0e..6aeead54760a 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -1,6 +1,7 @@ /* Simple expression parser */ %{ #define YYDEBUG 1 +#include #include #include "util/debug.h" #include "smt.h" @@ -12,15 +13,31 @@ %parse-param { double *final_val } %parse-param { struct expr_parse_ctx *ctx } +%parse-param { bool compute_ids } %parse-param {void *scanner} %lex-param {void* scanner} %union { double num; char *str; + struct ids { + /* + * When creating ids, holds the working set of event ids. NULL + * implies the set is empty. + */ + struct hashmap *ids; + /* + * The metric value. When not creating ids this is the value + * read from a counter, a constant or some computed value. When + * creating ids the value is either a constant or BOTTOM. NAN is + * used as the special BOTTOM value, representing a "set of all + * values" case. + */ + double val; + } ids; } -%token ID NUMBER MIN MAX IF ELSE SMT_ON D_RATIO EXPR_ERROR EXPR_PARSE EXPR_OTHER +%token ID NUMBER MIN MAX IF ELSE SMT_ON D_RATIO EXPR_ERROR %left MIN MAX IF %left '|' %left '^' @@ -32,65 +49,109 @@ %type NUMBER %type ID %destructor { free ($$); } -%type expr if_expr +%type expr if_expr +%destructor { ids__free($$.ids); } %{ static void expr_error(double *final_val __maybe_unused, struct expr_parse_ctx *ctx __maybe_unused, + bool compute_ids __maybe_unused, void *scanner, const char *s) { pr_debug("%s\n", s); } +/* + * During compute ids, the special "bottom" value uses NAN to represent the set + * of all values. NAN is selected as it isn't a useful constant value. + */ +#define BOTTOM NAN + +static struct ids union_expr(struct ids ids1, struct ids ids2) +{ + struct ids result = { + .val = BOTTOM, + .ids = ids__union(ids1.ids, ids2.ids), + }; + return result; +} + #define BINARY_LONG_OP(RESULT, OP, LHS, RHS) \ - RESULT = (long)LHS OP (long)RHS; + if (!compute_ids) { \ + RESULT.val = (long)LHS.val OP (long)RHS.val; \ + RESULT.ids = NULL; \ + } else { \ + RESULT = union_expr(LHS, RHS); \ + } #define BINARY_OP(RESULT, OP, LHS, RHS) \ - RESULT = LHS OP RHS; + if (!compute_ids) { \ + RESULT.val = LHS.val OP RHS.val; \ + RESULT.ids = NULL; \ + } else { \ + RESULT = union_expr(LHS, RHS); \ + } %} %% -start: -EXPR_PARSE all_expr -| -EXPR_OTHER all_other - -all_other: all_other other -| - -other: ID +start: if_expr { - expr__add_id(ctx, $1); -} -| -MIN | MAX | IF | ELSE | SMT_ON | NUMBER | '|' | '^' | '&' | '-' | '+' | '*' | '/' | '%' | '(' | ')' | ',' -| -'<' | '>' | D_RATIO + if (compute_ids) + ctx->ids = ids__union($1.ids, ctx->ids); -all_expr: if_expr { *final_val = $1; } + if (final_val) + *final_val = $1.val; +} +; if_expr: expr IF expr ELSE expr { - $$ = $3 ? $1 : $5; + if (!compute_ids) { + $$.ids = NULL; + if (fpclassify($3.val) == FP_ZERO) { + $$.val = $5.val; + } else { + $$.val = $1.val; + } + } else { + $$ = union_expr($1, union_expr($3, $5)); + } } | expr ; expr: NUMBER { - $$ = $1; + $$.val = $1; + $$.ids = NULL; } | ID { - struct expr_id_data *data; + if (!compute_ids) { + /* + * Compute the event's value from ID. If the ID isn't known then + * it isn't used to compute the formula so set to NAN. + */ + struct expr_id_data *data; - $$ = NAN; - if (expr__resolve_id(ctx, $1, &data) == 0) - $$ = expr_id_data__value(data); + $$.val = NAN; + if (expr__resolve_id(ctx, $1, &data) == 0) + $$.val = expr_id_data__value(data); - free($1); + $$.ids = NULL; + free($1); + } else { + /* + * Set the value to BOTTOM to show that any value is possible + * when the event is computed. Create a set of just the ID. + */ + $$.val = BOTTOM; + $$.ids = ids__new(); + if (!$$.ids || ids__insert($$.ids, $1, ctx->parent)) + YYABORT; + } } | expr '|' expr { BINARY_LONG_OP($$, |, $1, $3); } | expr '&' expr { BINARY_LONG_OP($$, &, $1, $3); } @@ -102,31 +163,47 @@ expr: NUMBER | expr '*' expr { BINARY_OP($$, *, $1, $3); } | expr '/' expr { - if ($3 == 0) { - pr_debug("division by zero\n"); - YYABORT; + if (!compute_ids) { + if (fpclassify($3.val) == FP_ZERO) { + pr_debug("division by zero\n"); + YYABORT; + } + $$.val = $1.val / $3.val; + $$.ids = NULL; + } else { + $$ = union_expr($1, $3); } - $$ = $1 / $3; } | expr '%' expr { - if ((long)$3 == 0) { - pr_debug("division by zero\n"); - YYABORT; + if (!compute_ids) { + if (fpclassify($3.val) == FP_ZERO) { + pr_debug("division by zero\n"); + YYABORT; + } + $$.val = (long)$1.val % (long)$3.val; + $$.ids = NULL; + } else { + $$ = union_expr($1, $3); } - $$ = (long)$1 % (long)$3; } | D_RATIO '(' expr ',' expr ')' { - if ($5 == 0) { - $$ = 0; + if (!compute_ids) { + $$.ids = NULL; + if (fpclassify($5.val) == FP_ZERO) { + $$.val = 0.0; + } else { + $$.val = $3.val / $5.val; + } } else { - $$ = $3 / $5; + $$ = union_expr($3, $5); } } | '-' expr %prec NEG { - $$ = -$2; + $$.val = -$2.val; + $$.ids = $2.ids; } | '(' if_expr ')' { @@ -134,15 +211,26 @@ expr: NUMBER } | MIN '(' expr ',' expr ')' { - $$ = $3 < $5 ? $3 : $5; + if (!compute_ids) { + $$.val = $3.val < $5.val ? $3.val : $5.val; + $$.ids = NULL; + } else { + $$ = union_expr($3, $5); + } } | MAX '(' expr ',' expr ')' { - $$ = $3 > $5 ? $3 : $5; + if (!compute_ids) { + $$.val = $3.val > $5.val ? $3.val : $5.val; + $$.ids = NULL; + } else { + $$ = union_expr($3, $5); + } } | SMT_ON { - $$ = smt_on() > 0 ? 1.0 : 0.0; + $$.val = smt_on() > 0 ? 1.0 : 0.0; + $$.ids = NULL; } ; From 970f7afe55ee3e9d6d1c73cd138c5f023bb0beba Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 23 Sep 2021 00:46:14 -0700 Subject: [PATCH 115/587] perf expr: Propagate constants for binary operations When we're computing ID values, if we have constant values then compute the constant result. For example: 1 + 2 Previously .val would be set to BOTTOM by union_expr, meaning that all values are possible. With this change .val is set to 3. Later changes will use the constant values to hopefully eliminate ID values that don't need to be computed. Signed-off-by: Ian Rogers Tested-by: John Garry Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ingo Molnar Cc: Jin Yao Cc: Kajol Jain Cc: Mark Rutland Cc: Namhyung Kim Cc: Paul Clarke Cc: Peter Zijlstra Cc: Sandeep Dasgupta Cc: Stephane Eranian Link: https://lore.kernel.org/r/20210923074616.674826-12-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/expr.y | 63 ++++++++++++++++++++++++++++++------------ 1 file changed, 45 insertions(+), 18 deletions(-) diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index 6aeead54760a..5a295e385914 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -68,6 +68,12 @@ static void expr_error(double *final_val __maybe_unused, */ #define BOTTOM NAN +/* During computing ids, does val represent a constant (non-BOTTOM) value? */ +static bool is_const(double val) +{ + return isfinite(val); +} + static struct ids union_expr(struct ids ids1, struct ids ids2) { struct ids result = { @@ -77,8 +83,15 @@ static struct ids union_expr(struct ids ids1, struct ids ids2) return result; } +/* + * If we're not computing ids or $1 and $3 are constants, compute the new + * constant value using OP. Its invariant that there are no ids. If computing + * ids for non-constants union the set of IDs that must be computed. + */ #define BINARY_LONG_OP(RESULT, OP, LHS, RHS) \ - if (!compute_ids) { \ + if (!compute_ids || (is_const(LHS.val) && is_const(RHS.val))) { \ + assert(LHS.ids == NULL); \ + assert(RHS.ids == NULL); \ RESULT.val = (long)LHS.val OP (long)RHS.val; \ RESULT.ids = NULL; \ } else { \ @@ -86,7 +99,9 @@ static struct ids union_expr(struct ids ids1, struct ids ids2) } #define BINARY_OP(RESULT, OP, LHS, RHS) \ - if (!compute_ids) { \ + if (!compute_ids || (is_const(LHS.val) && is_const(RHS.val))) { \ + assert(LHS.ids == NULL); \ + assert(RHS.ids == NULL); \ RESULT.val = LHS.val OP RHS.val; \ RESULT.ids = NULL; \ } else { \ @@ -163,40 +178,52 @@ expr: NUMBER | expr '*' expr { BINARY_OP($$, *, $1, $3); } | expr '/' expr { - if (!compute_ids) { - if (fpclassify($3.val) == FP_ZERO) { - pr_debug("division by zero\n"); - YYABORT; - } + if (fpclassify($3.val) == FP_ZERO) { + pr_debug("division by zero\n"); + YYABORT; + } else if (!compute_ids || (is_const($1.val) && is_const($3.val))) { + assert($1.ids == NULL); + assert($3.ids == NULL); $$.val = $1.val / $3.val; $$.ids = NULL; } else { + /* LHS and/or RHS need computing from event IDs so union. */ $$ = union_expr($1, $3); } } | expr '%' expr { - if (!compute_ids) { - if (fpclassify($3.val) == FP_ZERO) { - pr_debug("division by zero\n"); - YYABORT; - } + if (fpclassify($3.val) == FP_ZERO) { + pr_debug("division by zero\n"); + YYABORT; + } else if (!compute_ids || (is_const($1.val) && is_const($3.val))) { + assert($1.ids == NULL); + assert($3.ids == NULL); $$.val = (long)$1.val % (long)$3.val; $$.ids = NULL; } else { + /* LHS and/or RHS need computing from event IDs so union. */ $$ = union_expr($1, $3); } } | D_RATIO '(' expr ',' expr ')' { - if (!compute_ids) { + if (fpclassify($5.val) == FP_ZERO) { + /* + * Division by constant zero always yields zero and no events + * are necessary. + */ + assert($5.ids == NULL); + $$.val = 0.0; + $$.ids = NULL; + ids__free($3.ids); + } else if (!compute_ids || (is_const($3.val) && is_const($5.val))) { + assert($3.ids == NULL); + assert($5.ids == NULL); + $$.val = $3.val / $5.val; $$.ids = NULL; - if (fpclassify($5.val) == FP_ZERO) { - $$.val = 0.0; - } else { - $$.val = $3.val / $5.val; - } } else { + /* LHS and/or RHS need computing from event IDs so union. */ $$ = union_expr($3, $5); } } From a8e4e880834b5dc53ff6b4cfc9f4268e61399976 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 23 Sep 2021 00:46:15 -0700 Subject: [PATCH 116/587] perf metric: Don't compute unused events For a metric like: EVENT1 if #smt_on else EVENT2 currently EVENT1 and EVENT2 will be measured and then when the metric is reported EVENT1 or EVENT2 will be printed depending on the value from smt_on() during the expr parsing. Computing both events is unnecessary and can lead to multiplexing as discussed in this thread: https://lore.kernel.org/lkml/20201110100346.2527031-1-irogers@google.com/ If the input is constant to certain operators like: IDS1 if CONST else IDS2 then the result will be either IDS1 or IDS2 depending on CONST (which may be evaluated from an entire expression), and so IDS1 or IDS2 may be discarded avoiding events from being programmed. Signed-off-by: Ian Rogers Tested-by: John Garry Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ingo Molnar Cc: Jin Yao Cc: Kajol Jain Cc: Mark Rutland Cc: Namhyung Kim Cc: Paul Clarke Cc: Peter Zijlstra Cc: Sandeep Dasgupta Cc: Stephane Eranian Link: https://lore.kernel.org/r/20210923074616.674826-13-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/expr.c | 11 +++++++++++ tools/perf/util/expr.y | 30 +++++++++++++++++++++++------- 2 files changed, 34 insertions(+), 7 deletions(-) diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index 1c881bea7fca..287989321d2a 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include "util/debug.h" #include "util/expr.h" +#include "util/smt.h" #include "tests.h" #include #include @@ -132,6 +133,16 @@ int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused) TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "EVENT2,param=3/", (void **)&val_ptr)); + /* Only EVENT1 or EVENT2 need be measured depending on the value of smt_on. */ + expr__ctx_clear(ctx); + TEST_ASSERT_VAL("find ids", + expr__find_ids("EVENT1 if #smt_on else EVENT2", + NULL, ctx, 0) == 0); + TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 1); + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, + smt_on() ? "EVENT1" : "EVENT2", + (void **)&val_ptr)); + expr__ctx_free(ctx); return 0; diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index 5a295e385914..5b878f044f22 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -123,14 +123,30 @@ start: if_expr if_expr: expr IF expr ELSE expr { - if (!compute_ids) { - $$.ids = NULL; - if (fpclassify($3.val) == FP_ZERO) { - $$.val = $5.val; - } else { - $$.val = $1.val; - } + if (fpclassify($3.val) == FP_ZERO) { + /* + * The IF expression evaluated to 0 so treat as false, take the + * ELSE and discard everything else. + */ + $$.val = $5.val; + $$.ids = $5.ids; + ids__free($1.ids); + ids__free($3.ids); + } else if (!compute_ids || is_const($3.val)) { + /* + * If ids aren't computed then treat the expression as true. If + * ids are being computed and the IF expr is a non-zero + * constant, then also evaluate the true case. + */ + $$.val = $1.val; + $$.ids = $1.ids; + ids__free($3.ids); + ids__free($5.ids); } else { + /* + * Value is either the LHS or RHS and we need the IF expression + * to compute it. + */ $$ = union_expr($1, union_expr($3, $5)); } } From 94886961e324d5b6bae8e206b227c6eeb0f22c2c Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 23 Sep 2021 00:46:16 -0700 Subject: [PATCH 117/587] perf metric: Avoid events for an 'if' constant result For a metric like: CONST if expr else CONST if the values of CONST are identical then expr doesn't need evaluating, and events, in order to compute a result. Signed-off-by: Ian Rogers Tested-by: John Garry Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ingo Molnar Cc: Jin Yao Cc: Kajol Jain Cc: Mark Rutland Cc: Namhyung Kim Cc: Paul Clarke Cc: Peter Zijlstra Cc: Sandeep Dasgupta Cc: Stephane Eranian Link: https://lore.kernel.org/r/20210923074616.674826-14-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/expr.c | 7 +++++++ tools/perf/util/expr.y | 10 ++++++++++ 2 files changed, 17 insertions(+) diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index 287989321d2a..f1d8411fce12 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -143,6 +143,13 @@ int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused) smt_on() ? "EVENT1" : "EVENT2", (void **)&val_ptr)); + /* The expression is a constant 1.0 without needing to evaluate EVENT1. */ + expr__ctx_clear(ctx); + TEST_ASSERT_VAL("find ids", + expr__find_ids("1.0 if EVENT1 > 100.0 else 1.0", + NULL, ctx, 0) == 0); + TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 0); + expr__ctx_free(ctx); return 0; diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index 5b878f044f22..ba7d3b667fcb 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -142,6 +142,16 @@ if_expr: expr IF expr ELSE expr $$.ids = $1.ids; ids__free($3.ids); ids__free($5.ids); + } else if ($1.val == $5.val) { + /* + * LHS == RHS, so both are an identical constant. No need to + * evaluate any events. + */ + $$.val = $1.val; + $$.ids = NULL; + ids__free($1.ids); + ids__free($3.ids); + ids__free($5.ids); } else { /* * Value is either the LHS or RHS and we need the IF expression From 65017d8381e2425a1b4cdc4681fadc179635c000 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 27 Sep 2021 21:54:36 +0900 Subject: [PATCH 118/587] kconfig: narrow the scope of variables in the lexer The variables, "ts" and "i", are used locally in the action of the [ \t]+ pattern in the start state. Define them where they are used. Signed-off-by: Masahiro Yamada --- scripts/kconfig/lexer.l | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/scripts/kconfig/lexer.l b/scripts/kconfig/lexer.l index 312cbad2d34d..efe487859308 100644 --- a/scripts/kconfig/lexer.l +++ b/scripts/kconfig/lexer.l @@ -85,7 +85,6 @@ n [A-Za-z0-9_-] %% int str = 0; - int ts, i; #.* /* ignore comment */ [ \t]* /* whitespaces */ @@ -196,6 +195,8 @@ n [A-Za-z0-9_-] { [ \t]+ { + int ts, i; + ts = 0; for (i = 0; i < yyleng; i++) { if (yytext[i] == '\t') From 6988f70cf105e70b4ea424d320521a9ed452fe46 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 27 Sep 2021 21:54:37 +0900 Subject: [PATCH 119/587] kconfig: rename a variable in the lexer to a clearer name In Kconfig, like Python, you can enclose a string by double-quotes or single-quotes. So, both "foo" and 'foo' are allowed. The variable, "str", is used to remember whether the string started with a double-quote or a single-quote because open/closing quotation marks must match. The name "str" is too generic to understand the intent. Rename it to "open_quote", which is easier to understand. The type should be 'char'. Signed-off-by: Masahiro Yamada Reviewed-by: Boris Kolpackov --- scripts/kconfig/lexer.l | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/scripts/kconfig/lexer.l b/scripts/kconfig/lexer.l index efe487859308..cc386e443683 100644 --- a/scripts/kconfig/lexer.l +++ b/scripts/kconfig/lexer.l @@ -84,7 +84,7 @@ static void warn_ignored_character(char chr) n [A-Za-z0-9_-] %% - int str = 0; + char open_quote = 0; #.* /* ignore comment */ [ \t]* /* whitespaces */ @@ -133,7 +133,7 @@ n [A-Za-z0-9_-] ":=" return T_COLON_EQUAL; "+=" return T_PLUS_EQUAL; \"|\' { - str = yytext[0]; + open_quote = yytext[0]; new_string(); BEGIN(STRING); } @@ -170,7 +170,7 @@ n [A-Za-z0-9_-] append_string(yytext + 1, yyleng - 1); } \'|\" { - if (str == yytext[0]) { + if (open_quote == yytext[0]) { BEGIN(INITIAL); yylval.string = text; return T_WORD_QUOTE; From 2b775152bbe838c9de0055eb5bdb530c2c88235b Mon Sep 17 00:00:00 2001 From: Michael Petlan Date: Wed, 22 Sep 2021 17:27:06 +0200 Subject: [PATCH 120/587] perf tests vmlinux-kallsyms: Ignore hidden symbols Certain kernel symbols are purposely hidden from kallsyms. The function is_ignored_symbol() from scripts/kallsyms.c decides if a symbol should be hidden or not. The perf test "vmlinux symtab matches kallsyms" fails in case perf finds some of the hidden symbols in its machine image and can't match them to kallsyms. Let's add a filter to check if a symbol not found isn't one of these before failing the test. The function is_ignored_symbol() has been copied from scripts/kallsyms.c and needs to be updated along with the original. Signed-off-by: Michael Petlan Acked-by: Ian Rogers Cc: Jiri Olsa LPU-Reference: 20210922152706.23655-1-mpetlan@redhat.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/vmlinux-kallsyms.c | 102 ++++++++++++++++++++++++++++ 1 file changed, 102 insertions(+) diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index 193b7c91b4e2..4f884aabc7f4 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -3,6 +3,7 @@ #include #include #include +#include #include #include "dso.h" #include "map.h" @@ -14,6 +15,102 @@ #define UM(x) kallsyms_map->unmap_ip(kallsyms_map, (x)) +static bool is_ignored_symbol(const char *name, char type) +{ + /* Symbol names that exactly match to the following are ignored.*/ + static const char * const ignored_symbols[] = { + /* + * Symbols which vary between passes. Passes 1 and 2 must have + * identical symbol lists. The kallsyms_* symbols below are + * only added after pass 1, they would be included in pass 2 + * when --all-symbols is specified so exclude them to get a + * stable symbol list. + */ + "kallsyms_addresses", + "kallsyms_offsets", + "kallsyms_relative_base", + "kallsyms_num_syms", + "kallsyms_names", + "kallsyms_markers", + "kallsyms_token_table", + "kallsyms_token_index", + /* Exclude linker generated symbols which vary between passes */ + "_SDA_BASE_", /* ppc */ + "_SDA2_BASE_", /* ppc */ + NULL + }; + + /* Symbol names that begin with the following are ignored.*/ + static const char * const ignored_prefixes[] = { + "$", /* local symbols for ARM, MIPS, etc. */ + ".LASANPC", /* s390 kasan local symbols */ + "__crc_", /* modversions */ + "__efistub_", /* arm64 EFI stub namespace */ + "__kvm_nvhe_", /* arm64 non-VHE KVM namespace */ + "__AArch64ADRPThunk_", /* arm64 lld */ + "__ARMV5PILongThunk_", /* arm lld */ + "__ARMV7PILongThunk_", + "__ThumbV7PILongThunk_", + "__LA25Thunk_", /* mips lld */ + "__microLA25Thunk_", + NULL + }; + + /* Symbol names that end with the following are ignored.*/ + static const char * const ignored_suffixes[] = { + "_from_arm", /* arm */ + "_from_thumb", /* arm */ + "_veneer", /* arm */ + NULL + }; + + /* Symbol names that contain the following are ignored.*/ + static const char * const ignored_matches[] = { + ".long_branch.", /* ppc stub */ + ".plt_branch.", /* ppc stub */ + NULL + }; + + const char * const *p; + + for (p = ignored_symbols; *p; p++) + if (!strcmp(name, *p)) + return true; + + for (p = ignored_prefixes; *p; p++) + if (!strncmp(name, *p, strlen(*p))) + return true; + + for (p = ignored_suffixes; *p; p++) { + int l = strlen(name) - strlen(*p); + + if (l >= 0 && !strcmp(name + l, *p)) + return true; + } + + for (p = ignored_matches; *p; p++) { + if (strstr(name, *p)) + return true; + } + + if (type == 'U' || type == 'u') + return true; + /* exclude debugging symbols */ + if (type == 'N' || type == 'n') + return true; + + if (toupper(type) == 'A') { + /* Keep these useful absolute symbols */ + if (strcmp(name, "__kernel_syscall_via_break") && + strcmp(name, "__kernel_syscall_via_epc") && + strcmp(name, "__kernel_sigtramp") && + strcmp(name, "__gp")) + return true; + } + + return false; +} + int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest __maybe_unused) { int err = -1; @@ -169,6 +266,11 @@ next_pair: * such as __indirect_thunk_end. */ continue; + } else if (is_ignored_symbol(sym->name, sym->type)) { + /* + * Ignore hidden symbols, see scripts/kallsyms.c for the details + */ + continue; } else { pr_debug("ERR : %#" PRIx64 ": %s not on kallsyms\n", mem_start, sym->name); From 2b3db4db660f9cc04878d81c2517f840763e6733 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 6 Aug 2021 23:15:15 +0200 Subject: [PATCH 121/587] i2c: i801: Improve is_dell_system_with_lis3lv02d Replace the ugly cast of the return_value pointer with proper usage. In addition use dmi_match() instead of open-coding it. Signed-off-by: Heiner Kallweit Reviewed-by: Jean Delvare Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-i801.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 89ae78ef1a1c..f56060fcf5ac 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -1192,7 +1192,7 @@ static acpi_status check_acpi_smo88xx_device(acpi_handle obj_handle, kfree(info); - *((bool *)return_value) = true; + *return_value = NULL; return AE_CTRL_TERMINATE; smo88xx_not_found: @@ -1202,11 +1202,9 @@ smo88xx_not_found: static bool is_dell_system_with_lis3lv02d(void) { - bool found; - const char *vendor; + void *err = ERR_PTR(-ENOENT); - vendor = dmi_get_system_info(DMI_SYS_VENDOR); - if (!vendor || strcmp(vendor, "Dell Inc.")) + if (!dmi_match(DMI_SYS_VENDOR, "Dell Inc.")) return false; /* @@ -1217,11 +1215,9 @@ static bool is_dell_system_with_lis3lv02d(void) * accelerometer but unfortunately ACPI does not provide any other * information (like I2C address). */ - found = false; - acpi_get_devices(NULL, check_acpi_smo88xx_device, NULL, - (void **)&found); + acpi_get_devices(NULL, check_acpi_smo88xx_device, NULL, &err); - return found; + return !IS_ERR(err); } /* From e462aa7e39b5b6f70bc993d5ce50f7cc2e71182a Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 6 Aug 2021 23:15:51 +0200 Subject: [PATCH 122/587] i2c: i801: Remove not needed check for PCI_COMMAND_INTX_DISABLE do_pci_enable_device() takes care that PCI_COMMAND_INTX_DISABLE is cleared if a legacy interrupt is used. Signed-off-by: Heiner Kallweit Reviewed-by: Andy Shevchenko Reviewed-by: Jean Delvare Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-i801.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index f56060fcf5ac..7fa06b85fa97 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -1827,19 +1827,12 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) priv->features &= ~FEATURE_IRQ; if (priv->features & FEATURE_IRQ) { - u16 pcictl, pcists; + u16 pcists; /* Complain if an interrupt is already pending */ pci_read_config_word(priv->pci_dev, PCI_STATUS, &pcists); if (pcists & PCI_STATUS_INTERRUPT) dev_warn(&dev->dev, "An interrupt is pending!\n"); - - /* Check if interrupts have been disabled */ - pci_read_config_word(priv->pci_dev, PCI_COMMAND, &pcictl); - if (pcictl & PCI_COMMAND_INTX_DISABLE) { - dev_info(&dev->dev, "Interrupts are disabled\n"); - priv->features &= ~FEATURE_IRQ; - } } if (priv->features & FEATURE_IRQ) { From 4811a411a92913e5327e4b32d4bb783823348537 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 6 Aug 2021 23:16:33 +0200 Subject: [PATCH 123/587] i2c: i801: Improve i801_acpi_probe/remove functions By using ACPI_HANDLE() the handler argument can be retrieved directly. Both address space handler functions check the handler argument and return an error if it's NULL. This allows to further simplify the code. Reviewed-by: Jean Delvare Tested-by: Jean Delvare Reviewed-by: Mika Westerberg Signed-off-by: Heiner Kallweit Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-i801.c | 23 +++++++---------------- 1 file changed, 7 insertions(+), 16 deletions(-) diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 7fa06b85fa97..bd1db0f0aa19 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -1635,31 +1635,22 @@ i801_acpi_io_handler(u32 function, acpi_physical_address address, u32 bits, static int i801_acpi_probe(struct i801_priv *priv) { - struct acpi_device *adev; + acpi_handle ah = ACPI_HANDLE(&priv->pci_dev->dev); acpi_status status; - adev = ACPI_COMPANION(&priv->pci_dev->dev); - if (adev) { - status = acpi_install_address_space_handler(adev->handle, - ACPI_ADR_SPACE_SYSTEM_IO, i801_acpi_io_handler, - NULL, priv); - if (ACPI_SUCCESS(status)) - return 0; - } + status = acpi_install_address_space_handler(ah, ACPI_ADR_SPACE_SYSTEM_IO, + i801_acpi_io_handler, NULL, priv); + if (ACPI_SUCCESS(status)) + return 0; return acpi_check_resource_conflict(&priv->pci_dev->resource[SMBBAR]); } static void i801_acpi_remove(struct i801_priv *priv) { - struct acpi_device *adev; + acpi_handle ah = ACPI_HANDLE(&priv->pci_dev->dev); - adev = ACPI_COMPANION(&priv->pci_dev->dev); - if (!adev) - return; - - acpi_remove_address_space_handler(adev->handle, - ACPI_ADR_SPACE_SYSTEM_IO, i801_acpi_io_handler); + acpi_remove_address_space_handler(ah, ACPI_ADR_SPACE_SYSTEM_IO, i801_acpi_io_handler); } #else static inline int i801_acpi_probe(struct i801_priv *priv) { return 0; } From 4c5910631cc1a9c3b8d34ebb0048727eded9148c Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 6 Aug 2021 23:17:10 +0200 Subject: [PATCH 124/587] i2c: i801: Improve i801_add_mux The return value of i801_add_mux() isn't used, so let's change it to void. In addition remove the not needed cast to struct gpiod_lookup. GPIO_LOOKUP() uses GPIO_LOOKUP_IDX() that includes this cast. Reviewed-by: Jean Delvare Tested-by: Jean Delvare Signed-off-by: Heiner Kallweit Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-i801.c | 18 +++++++----------- 1 file changed, 7 insertions(+), 11 deletions(-) diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index bd1db0f0aa19..6e9aca81b7f0 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -1391,7 +1391,7 @@ static const struct dmi_system_id mux_dmi_table[] = { }; /* Setup multiplexing if needed */ -static int i801_add_mux(struct i801_priv *priv) +static void i801_add_mux(struct i801_priv *priv) { struct device *dev = &priv->adapter.dev; const struct i801_mux_config *mux_config; @@ -1400,7 +1400,7 @@ static int i801_add_mux(struct i801_priv *priv) int i; if (!priv->mux_drvdata) - return 0; + return; mux_config = priv->mux_drvdata; /* Prepare the platform data */ @@ -1416,13 +1416,11 @@ static int i801_add_mux(struct i801_priv *priv) struct_size(lookup, table, mux_config->n_gpios + 1), GFP_KERNEL); if (!lookup) - return -ENOMEM; + return; lookup->dev_id = "i2c-mux-gpio"; - for (i = 0; i < mux_config->n_gpios; i++) { - lookup->table[i] = (struct gpiod_lookup) - GPIO_LOOKUP(mux_config->gpio_chip, - mux_config->gpios[i], "mux", 0); - } + for (i = 0; i < mux_config->n_gpios; i++) + lookup->table[i] = GPIO_LOOKUP(mux_config->gpio_chip, + mux_config->gpios[i], "mux", 0); gpiod_add_lookup_table(lookup); priv->lookup = lookup; @@ -1440,8 +1438,6 @@ static int i801_add_mux(struct i801_priv *priv) gpiod_remove_lookup_table(lookup); dev_err(dev, "Failed to register i2c-mux-gpio device\n"); } - - return PTR_ERR_OR_ZERO(priv->mux_pdev); } static void i801_del_mux(struct i801_priv *priv) @@ -1471,7 +1467,7 @@ static unsigned int i801_get_adapter_class(struct i801_priv *priv) return class; } #else -static inline int i801_add_mux(struct i801_priv *priv) { return 0; } +static inline void i801_add_mux(struct i801_priv *priv) { } static inline void i801_del_mux(struct i801_priv *priv) { } static inline unsigned int i801_get_adapter_class(struct i801_priv *priv) From 7d6b61c394a42b8385858bb9e306d48a0112823c Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sun, 5 Sep 2021 17:59:42 +0200 Subject: [PATCH 125/587] i2c: i801: Use PCI bus rescan mutex to protect P2SB access As pointed out by Andy in [0] using a local mutex here isn't strictly wrong but not sufficient. We should hold the PCI rescan lock for P2SB operations. [0] https://www.spinics.net/lists/linux-i2c/msg52717.html Fixes: 1a987c69ce2c ("i2c: i801: make p2sb_spinlock a mutex") Reported-by: Andy Shevchenko Signed-off-by: Heiner Kallweit Reviewed-by: Andy Shevchenko Reviewed-by: Jean Delvare Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-i801.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 6e9aca81b7f0..260fc41b5ca7 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -1485,7 +1485,6 @@ static struct platform_device * i801_add_tco_spt(struct i801_priv *priv, struct pci_dev *pci_dev, struct resource *tco_res) { - static DEFINE_MUTEX(p2sb_mutex); struct resource *res; unsigned int devfn; u64 base64_addr; @@ -1498,7 +1497,7 @@ i801_add_tco_spt(struct i801_priv *priv, struct pci_dev *pci_dev, * enumerated by the PCI subsystem, so we need to unhide/hide it * to lookup the P2SB BAR. */ - mutex_lock(&p2sb_mutex); + pci_lock_rescan_remove(); devfn = PCI_DEVFN(PCI_SLOT(pci_dev->devfn), 1); @@ -1516,7 +1515,7 @@ i801_add_tco_spt(struct i801_priv *priv, struct pci_dev *pci_dev, /* Hide the P2SB device, if it was hidden before */ if (hidden) pci_bus_write_config_byte(pci_dev->bus, devfn, 0xe1, hidden); - mutex_unlock(&p2sb_mutex); + pci_unlock_rescan_remove(); res = &tco_res[1]; if (pci_dev->device == PCI_DEVICE_ID_INTEL_DNV_SMBUS) From c073b25dad0c2668b73ae9e8652bc3b8012e762b Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Tue, 7 Sep 2021 22:33:02 +0200 Subject: [PATCH 126/587] i2c: i801: Stop using pm_runtime_set_autosuspend_delay(-1) The original change works as intended, but Andy pointed in [0] that now userspace could re-enable RPM via sysfs, even though we explicitly want to disable it. So effectively revert the original patch, just with small improvements: - Calls to pm_runtime_allow()/pm_runtime_forbid() don't have to be balanced, so we can remove the call to pm_runtime_forbid() in i801_remove(). - priv->acpi_reserved is accessed after i801_acpi_remove(), and according to Robert [1] the custom handler can't run any longer. Therefore we don't have to take priv->acpi_lock. [0] https://www.spinics.net/lists/linux-i2c/msg52730.html [1] https://lore.kernel.org/linux-acpi/BYAPR11MB32561D19A0FD9AB93E2B1E5287D39@BYAPR11MB3256.namprd11.prod.outlook.com/T/#t Fixes: 4e60d5dd10cd ("i2c: i801: Improve disabling runtime pm") Reported-by: Andy Shevchenko Signed-off-by: Heiner Kallweit Acked-by: Rafael J. Wysocki Reviewed-by: Jean Delvare Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-i801.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 260fc41b5ca7..115660dce722 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -1615,7 +1615,7 @@ i801_acpi_io_handler(u32 function, acpi_physical_address address, u32 bits, * BIOS is accessing the host controller so prevent it from * suspending automatically from now on. */ - pm_runtime_set_autosuspend_delay(&pdev->dev, -1); + pm_runtime_get_sync(&pdev->dev); } if ((function & ACPI_IO_MASK) == ACPI_READ) @@ -1866,9 +1866,6 @@ static void i801_remove(struct pci_dev *dev) { struct i801_priv *priv = pci_get_drvdata(dev); - pm_runtime_forbid(&dev->dev); - pm_runtime_get_noresume(&dev->dev); - i801_disable_host_notify(priv); i801_del_mux(priv); i2c_del_adapter(&priv->adapter); @@ -1877,6 +1874,10 @@ static void i801_remove(struct pci_dev *dev) platform_device_unregister(priv->tco_pdev); + /* if acpi_reserved is set then usage_count is incremented already */ + if (!priv->acpi_reserved) + pm_runtime_get_noresume(&dev->dev); + /* * do not call pci_disable_device(dev) since it can cause hard hangs on * some systems during power-off (eg. Fujitsu-Siemens Lifebook E8010) From e7f4264821a4ee07775f3775f8530cfa9a6d4b5d Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Wed, 15 Sep 2021 15:48:27 +0200 Subject: [PATCH 127/587] i2c: rcar: enable interrupts before starting transfer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We want to enable the interrupts _before_ starting the transfer because it is good programming style and also the proposed order in the R-Car manual. There is no difference in practice because it doesn't matter in which order both conditions appear if we wait for both to happen. Signed-off-by: Ryo Kataoka Signed-off-by: Wolfram Sang Reviewed-by: Niklas Söderlund Reviewed-by: Ulrich Hecht Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-rcar.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c index bff9913c37b8..fc13511f4562 100644 --- a/drivers/i2c/busses/i2c-rcar.c +++ b/drivers/i2c/busses/i2c-rcar.c @@ -339,6 +339,9 @@ static void rcar_i2c_prepare_msg(struct rcar_i2c_priv *priv) priv->flags |= ID_LAST_MSG; rcar_i2c_write(priv, ICMAR, i2c_8bit_addr_from_msg(priv->msg)); + if (!priv->atomic_xfer) + rcar_i2c_write(priv, ICMIER, read ? RCAR_IRQ_RECV : RCAR_IRQ_SEND); + /* * We don't have a test case but the HW engineers say that the write order * of ICMSR and ICMCR depends on whether we issue START or REP_START. Since @@ -354,9 +357,6 @@ static void rcar_i2c_prepare_msg(struct rcar_i2c_priv *priv) rcar_i2c_write(priv, ICMCR, RCAR_BUS_PHASE_START); rcar_i2c_write(priv, ICMSR, 0); } - - if (!priv->atomic_xfer) - rcar_i2c_write(priv, ICMIER, read ? RCAR_IRQ_RECV : RCAR_IRQ_SEND); } static void rcar_i2c_next_msg(struct rcar_i2c_priv *priv) From ed2f85115a8e3423b68d8ac39aa7751c0779ce30 Mon Sep 17 00:00:00 2001 From: zhaoxiao Date: Mon, 6 Sep 2021 13:27:30 +0800 Subject: [PATCH 128/587] i2c: bcm-kona: Fix return value in probe() When call function devm_platform_ioremap_resource(), we should use IS_ERR() to check the return value and return PTR_ERR() if failed. Signed-off-by: zhaoxiao Acked-by: Florian Fainelli Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-bcm-kona.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-bcm-kona.c b/drivers/i2c/busses/i2c-bcm-kona.c index ed5e1275ae46..8e350f20cde0 100644 --- a/drivers/i2c/busses/i2c-bcm-kona.c +++ b/drivers/i2c/busses/i2c-bcm-kona.c @@ -763,7 +763,7 @@ static int bcm_kona_i2c_probe(struct platform_device *pdev) /* Map hardware registers */ dev->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(dev->base)) - return -ENOMEM; + return PTR_ERR(dev->base); /* Get and enable external clock */ dev->external_clk = devm_clk_get(dev->device, NULL); From 647d908816a78d604d47ea925c934fd88375b4fd Mon Sep 17 00:00:00 2001 From: Michael Brunner Date: Tue, 31 Aug 2021 10:29:36 +0000 Subject: [PATCH 129/587] i2c: kempld: deprecate class based instantiation Warn users that class based instantiation is going away soon in favour of more robust probing and faster bootup times. Class based instantiation has already been removed for other controllers and it makes absolutely sense to do it for this one too. Signed-off-by: Michael Brunner Acked-by: Ingmar Klein Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-kempld.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-kempld.c b/drivers/i2c/busses/i2c-kempld.c index 2d60be086b1a..5bbb7f0d7852 100644 --- a/drivers/i2c/busses/i2c-kempld.c +++ b/drivers/i2c/busses/i2c-kempld.c @@ -283,7 +283,8 @@ static const struct i2c_algorithm kempld_i2c_algorithm = { static const struct i2c_adapter kempld_i2c_adapter = { .owner = THIS_MODULE, .name = "i2c-kempld", - .class = I2C_CLASS_HWMON | I2C_CLASS_SPD, + .class = I2C_CLASS_HWMON | I2C_CLASS_SPD | + I2C_CLASS_DEPRECATED, .algo = &kempld_i2c_algorithm, }; From 7c3855c423b17f6ca211858afb0cef20569914c7 Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Tue, 13 Jul 2021 20:50:07 +0800 Subject: [PATCH 130/587] PCI: Coalesce host bridge contiguous apertures Built-in graphics at 07:00.0 on HP EliteDesk 805 G6 doesn't work because graphics can't get the BAR it needs. The BIOS configuration is correct: BARs 0 and 2 both fit in the 00:08.1 bridge window. But that 00:08.1 window covers two host bridge apertures from _CRS. Previously we assumed this was illegal, so we clipped the window to fit into one aperture (see 0f7e7aee2f37 ("PCI: Add pci_bus_clip_resource() to clip to fit upstream window")). pci_bus 0000:00: root bus resource [mem 0x10020200000-0x100303fffff window] pci_bus 0000:00: root bus resource [mem 0x10030400000-0x100401fffff window] pci 0000:00:08.1: bridge window [mem 0x10030000000-0x100401fffff 64bit pref] pci 0000:07:00.0: reg 0x10: [mem 0x10030000000-0x1003fffffff 64bit pref] pci 0000:07:00.0: reg 0x18: [mem 0x10040000000-0x100401fffff 64bit pref] pci 0000:00:08.1: can't claim BAR 15 [mem 0x10030000000-0x100401fffff 64bit pref]: no compatible bridge window pci 0000:00:08.1: [mem 0x10030000000-0x100401fffff 64bit pref] clipped to [mem 0x10030000000-0x100303fffff 64bit pref] pci 0000:00:08.1: bridge window [mem 0x10030000000-0x100303fffff 64bit pref] pci 0000:07:00.0: can't claim BAR 0 [mem 0x10030000000-0x1003fffffff 64bit pref]: no compatible bridge window pci 0000:07:00.0: can't claim BAR 2 [mem 0x10040000000-0x100401fffff 64bit pref]: no compatible bridge window However, the host bridge apertures are contiguous, so there's no need to clip in this case. Coalesce contiguous apertures so we can allocate from the entire contiguous region. Previous commit 65db04053efe ("PCI: Coalesce host bridge contiguous apertures") was similar but sorted the apertures, and Guenter Roeck reported a regression in ppc:sam460ex qemu emulation from nvme; see https://lore.kernel.org/all/20210709231529.GA3270116@roeck-us.net/ [bhelgaas: commit log] Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=212013 Suggested-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20210713125007.1260304-1-kai.heng.feng@canonical.com Signed-off-by: Kai-Heng Feng Signed-off-by: Bjorn Helgaas Cc: Guenter Roeck --- drivers/pci/probe.c | 33 ++++++++++++++++++++++++++++----- 1 file changed, 28 insertions(+), 5 deletions(-) diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index d9fc02a71baa..3459f460dbd8 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -883,11 +883,11 @@ static void pci_set_bus_msi_domain(struct pci_bus *bus) static int pci_register_host_bridge(struct pci_host_bridge *bridge) { struct device *parent = bridge->dev.parent; - struct resource_entry *window, *n; + struct resource_entry *window, *next, *n; struct pci_bus *bus, *b; - resource_size_t offset; + resource_size_t offset, next_offset; LIST_HEAD(resources); - struct resource *res; + struct resource *res, *next_res; char addr[64], *fmt; const char *name; int err; @@ -970,11 +970,34 @@ static int pci_register_host_bridge(struct pci_host_bridge *bridge) if (nr_node_ids > 1 && pcibus_to_node(bus) == NUMA_NO_NODE) dev_warn(&bus->dev, "Unknown NUMA node; performance will be reduced\n"); - /* Add initial resources to the bus */ + /* Coalesce contiguous windows */ resource_list_for_each_entry_safe(window, n, &resources) { - list_move_tail(&window->node, &bridge->windows); + if (list_is_last(&window->node, &resources)) + break; + + next = list_next_entry(window, node); offset = window->offset; res = window->res; + next_offset = next->offset; + next_res = next->res; + + if (res->flags != next_res->flags || offset != next_offset) + continue; + + if (res->end + 1 == next_res->start) { + next_res->start = res->start; + res->flags = res->start = res->end = 0; + } + } + + /* Add initial resources to the bus */ + resource_list_for_each_entry_safe(window, n, &resources) { + offset = window->offset; + res = window->res; + if (!res->end) + continue; + + list_move_tail(&window->node, &bridge->windows); if (res->flags & IORESOURCE_BUS) pci_bus_insert_busn_res(bus, bus->number, res->end); From 3a7fb86758c96cc255ecc820ac47168047fe3dfa Mon Sep 17 00:00:00 2001 From: Luca Ceresoli Date: Mon, 31 May 2021 10:59:31 +0200 Subject: [PATCH 131/587] PCI: dwc: Export more symbols to allow modular drivers These symbols are used by the pci-dra7xx driver. Export them to allow building pci-dra7xx as a module. Link: https://lore.kernel.org/r/20210531085934.2662457-2-luca@lucaceresoli.net Signed-off-by: Luca Ceresoli Signed-off-by: Lorenzo Pieralisi Acked-by: Kishon Vijay Abraham I --- drivers/pci/controller/dwc/pcie-designware-ep.c | 1 + drivers/pci/controller/dwc/pcie-designware.c | 1 + 2 files changed, 2 insertions(+) diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c index 998b698f4085..27e4735f577e 100644 --- a/drivers/pci/controller/dwc/pcie-designware-ep.c +++ b/drivers/pci/controller/dwc/pcie-designware-ep.c @@ -83,6 +83,7 @@ void dw_pcie_ep_reset_bar(struct dw_pcie *pci, enum pci_barno bar) for (func_no = 0; func_no < funcs; func_no++) __dw_pcie_ep_reset_bar(pci, func_no, bar, 0); } +EXPORT_SYMBOL_GPL(dw_pcie_ep_reset_bar); static u8 __dw_pcie_ep_find_next_cap(struct dw_pcie_ep *ep, u8 func_no, u8 cap_ptr, u8 cap) diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c index a945f0c0e73d..850b4533f4ef 100644 --- a/drivers/pci/controller/dwc/pcie-designware.c +++ b/drivers/pci/controller/dwc/pcie-designware.c @@ -538,6 +538,7 @@ int dw_pcie_link_up(struct dw_pcie *pci) return ((val & PCIE_PORT_DEBUG1_LINK_UP) && (!(val & PCIE_PORT_DEBUG1_LINK_IN_TRAINING))); } +EXPORT_SYMBOL_GPL(dw_pcie_link_up); void dw_pcie_upconfig_setup(struct dw_pcie *pci) { From 3b868d150efd3c586762cee4410cfc75f46d2a07 Mon Sep 17 00:00:00 2001 From: Luca Ceresoli Date: Mon, 31 May 2021 10:59:32 +0200 Subject: [PATCH 132/587] PCI: dra7xx: Make it a kernel module Enable building the driver as a loadable kernel module. Link: https://lore.kernel.org/r/20210531085934.2662457-3-luca@lucaceresoli.net Signed-off-by: Luca Ceresoli Signed-off-by: Lorenzo Pieralisi Acked-by: Kishon Vijay Abraham I --- drivers/pci/controller/dwc/Kconfig | 6 +++--- drivers/pci/controller/dwc/pci-dra7xx.c | 8 +++++++- 2 files changed, 10 insertions(+), 4 deletions(-) diff --git a/drivers/pci/controller/dwc/Kconfig b/drivers/pci/controller/dwc/Kconfig index 76c0a63a3f64..9892a1135678 100644 --- a/drivers/pci/controller/dwc/Kconfig +++ b/drivers/pci/controller/dwc/Kconfig @@ -17,10 +17,10 @@ config PCIE_DW_EP select PCIE_DW config PCI_DRA7XX - bool + tristate config PCI_DRA7XX_HOST - bool "TI DRA7xx PCIe controller Host Mode" + tristate "TI DRA7xx PCIe controller Host Mode" depends on SOC_DRA7XX || COMPILE_TEST depends on PCI_MSI_IRQ_DOMAIN depends on OF && HAS_IOMEM && TI_PIPE3 @@ -36,7 +36,7 @@ config PCI_DRA7XX_HOST This uses the DesignWare core. config PCI_DRA7XX_EP - bool "TI DRA7xx PCIe controller Endpoint Mode" + tristate "TI DRA7xx PCIe controller Endpoint Mode" depends on SOC_DRA7XX || COMPILE_TEST depends on PCI_ENDPOINT depends on OF && HAS_IOMEM && TI_PIPE3 diff --git a/drivers/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c index fbbb78f6885e..e8418446039d 100644 --- a/drivers/pci/controller/dwc/pci-dra7xx.c +++ b/drivers/pci/controller/dwc/pci-dra7xx.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -607,6 +608,7 @@ static const struct of_device_id of_dra7xx_pcie_match[] = { }, {}, }; +MODULE_DEVICE_TABLE(of, of_dra7xx_pcie_match); /* * dra7xx_pcie_unaligned_memaccess: workaround for AM572x/AM571x Errata i870 @@ -943,4 +945,8 @@ static struct platform_driver dra7xx_pcie_driver = { }, .shutdown = dra7xx_pcie_shutdown, }; -builtin_platform_driver(dra7xx_pcie_driver); +module_platform_driver(dra7xx_pcie_driver); + +MODULE_AUTHOR("Kishon Vijay Abraham I "); +MODULE_DESCRIPTION("PCIe controller driver for TI DRA7xx SoCs"); +MODULE_LICENSE("GPL v2"); From b9a6943dc891f7c4aec41f07e6b60ca2b31a3b2e Mon Sep 17 00:00:00 2001 From: Luca Ceresoli Date: Mon, 31 May 2021 10:59:33 +0200 Subject: [PATCH 133/587] PCI: dra7xx: Remove unused include Unused since commit e259c2926c01 ("PCI: pci-dra7xx: Prepare for deferred probe with module_platform_driver"). Link: https://lore.kernel.org/r/20210531085934.2662457-4-luca@lucaceresoli.net Signed-off-by: Luca Ceresoli Signed-off-by: Lorenzo Pieralisi Acked-by: Kishon Vijay Abraham I --- drivers/pci/controller/dwc/pci-dra7xx.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c index e8418446039d..f8b1221030b4 100644 --- a/drivers/pci/controller/dwc/pci-dra7xx.c +++ b/drivers/pci/controller/dwc/pci-dra7xx.c @@ -14,7 +14,6 @@ #include #include #include -#include #include #include #include From 5af9405397bfb90d6adab61d58f4d94c78166698 Mon Sep 17 00:00:00 2001 From: Luca Ceresoli Date: Mon, 31 May 2021 10:59:34 +0200 Subject: [PATCH 134/587] PCI: dra7xx: Get an optional clock If the clock is provided externally we need to make sure it is enabled before starting PCI scan. Link: https://lore.kernel.org/r/20210531085934.2662457-5-luca@lucaceresoli.net Signed-off-by: Luca Ceresoli Signed-off-by: Lorenzo Pieralisi Acked-by: Kishon Vijay Abraham I --- drivers/pci/controller/dwc/pci-dra7xx.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c index f8b1221030b4..a4221f6f3629 100644 --- a/drivers/pci/controller/dwc/pci-dra7xx.c +++ b/drivers/pci/controller/dwc/pci-dra7xx.c @@ -7,6 +7,7 @@ * Authors: Kishon Vijay Abraham I */ +#include #include #include #include @@ -90,6 +91,7 @@ struct dra7xx_pcie { int phy_count; /* DT phy-names count */ struct phy **phy; struct irq_domain *irq_domain; + struct clk *clk; enum dw_pcie_device_mode mode; }; @@ -741,6 +743,15 @@ static int dra7xx_pcie_probe(struct platform_device *pdev) if (!link) return -ENOMEM; + dra7xx->clk = devm_clk_get_optional(dev, NULL); + if (IS_ERR(dra7xx->clk)) + return dev_err_probe(dev, PTR_ERR(dra7xx->clk), + "clock request failed"); + + ret = clk_prepare_enable(dra7xx->clk); + if (ret) + return ret; + for (i = 0; i < phy_count; i++) { snprintf(name, sizeof(name), "pcie-phy%d", i); phy[i] = devm_phy_get(dev, name); @@ -926,6 +937,8 @@ static void dra7xx_pcie_shutdown(struct platform_device *pdev) pm_runtime_disable(dev); dra7xx_pcie_disable_phy(dra7xx); + + clk_disable_unprepare(dra7xx->clk); } static const struct dev_pm_ops dra7xx_pcie_pm_ops = { From 894682f0a9b34dcb6e8d2ee2d5f6380b24a5b2d9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Mon, 27 Sep 2021 15:43:56 +0200 Subject: [PATCH 135/587] PCI: xgene: Use PCI_VENDOR_ID_AMCC macro MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Header file linux/pci_ids.h defines AMCC vendor id (0x10e8) macro named PCI_VENDOR_ID_AMCC. So use this macro instead of driver custom macro. Link: https://lore.kernel.org/r/20210927134356.11799-1-pali@kernel.org Signed-off-by: Pali Rohár Signed-off-by: Lorenzo Pieralisi Reviewed-by: Krzysztof Wilczyński --- drivers/pci/controller/pci-xgene.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/pci/controller/pci-xgene.c b/drivers/pci/controller/pci-xgene.c index e64536047b65..56d0d50338c8 100644 --- a/drivers/pci/controller/pci-xgene.c +++ b/drivers/pci/controller/pci-xgene.c @@ -48,7 +48,6 @@ #define EN_COHERENCY 0xF0000000 #define EN_REG 0x00000001 #define OB_LO_IO 0x00000002 -#define XGENE_PCIE_VENDORID 0x10E8 #define XGENE_PCIE_DEVICEID 0xE004 #define SZ_1T (SZ_1G*1024ULL) #define PIPE_PHY_RATE_RD(src) ((0xc000 & (u32)(src)) >> 0xe) @@ -560,7 +559,7 @@ static int xgene_pcie_setup(struct xgene_pcie_port *port) xgene_pcie_clear_config(port); /* setup the vendor and device IDs correctly */ - val = (XGENE_PCIE_DEVICEID << 16) | XGENE_PCIE_VENDORID; + val = (XGENE_PCIE_DEVICEID << 16) | PCI_VENDOR_ID_AMCC; xgene_pcie_writel(port, BRIDGE_CFG_0, val); ret = xgene_pcie_map_ranges(port); From a2258831d12d7845946f9c98f08d65aad9aa1121 Mon Sep 17 00:00:00 2001 From: Kunihiko Hayashi Date: Wed, 1 Sep 2021 14:09:17 +0900 Subject: [PATCH 136/587] PCI: endpoint: Use sysfs_emit() in "show" functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Convert sprintf() in sysfs "show" functions to sysfs_emit() in order to check for buffer overruns in sysfs outputs. Link: https://lore.kernel.org/r/1630472957-26857-1-git-send-email-hayashi.kunihiko@socionext.com Signed-off-by: Kunihiko Hayashi Signed-off-by: Lorenzo Pieralisi Reviewed-by: Krzysztof Wilczyński --- drivers/pci/endpoint/functions/pci-epf-ntb.c | 4 ++-- drivers/pci/endpoint/pci-ep-cfs.c | 13 ++++++------- 2 files changed, 8 insertions(+), 9 deletions(-) diff --git a/drivers/pci/endpoint/functions/pci-epf-ntb.c b/drivers/pci/endpoint/functions/pci-epf-ntb.c index 8b4756159f15..99266f05739a 100644 --- a/drivers/pci/endpoint/functions/pci-epf-ntb.c +++ b/drivers/pci/endpoint/functions/pci-epf-ntb.c @@ -1937,7 +1937,7 @@ static ssize_t epf_ntb_##_name##_show(struct config_item *item, \ struct config_group *group = to_config_group(item); \ struct epf_ntb *ntb = to_epf_ntb(group); \ \ - return sprintf(page, "%d\n", ntb->_name); \ + return sysfs_emit(page, "%d\n", ntb->_name); \ } #define EPF_NTB_W(_name) \ @@ -1968,7 +1968,7 @@ static ssize_t epf_ntb_##_name##_show(struct config_item *item, \ \ sscanf(#_name, "mw%d", &win_no); \ \ - return sprintf(page, "%lld\n", ntb->mws_size[win_no - 1]); \ + return sysfs_emit(page, "%lld\n", ntb->mws_size[win_no - 1]); \ } #define EPF_NTB_MW_W(_name) \ diff --git a/drivers/pci/endpoint/pci-ep-cfs.c b/drivers/pci/endpoint/pci-ep-cfs.c index 999911801877..5a0394a38675 100644 --- a/drivers/pci/endpoint/pci-ep-cfs.c +++ b/drivers/pci/endpoint/pci-ep-cfs.c @@ -198,8 +198,7 @@ static ssize_t pci_epc_start_store(struct config_item *item, const char *page, static ssize_t pci_epc_start_show(struct config_item *item, char *page) { - return sprintf(page, "%d\n", - to_pci_epc_group(item)->start); + return sysfs_emit(page, "%d\n", to_pci_epc_group(item)->start); } CONFIGFS_ATTR(pci_epc_, start); @@ -321,7 +320,7 @@ static ssize_t pci_epf_##_name##_show(struct config_item *item, char *page) \ struct pci_epf *epf = to_pci_epf_group(item)->epf; \ if (WARN_ON_ONCE(!epf->header)) \ return -EINVAL; \ - return sprintf(page, "0x%04x\n", epf->header->_name); \ + return sysfs_emit(page, "0x%04x\n", epf->header->_name); \ } #define PCI_EPF_HEADER_W_u32(_name) \ @@ -390,8 +389,8 @@ static ssize_t pci_epf_msi_interrupts_store(struct config_item *item, static ssize_t pci_epf_msi_interrupts_show(struct config_item *item, char *page) { - return sprintf(page, "%d\n", - to_pci_epf_group(item)->epf->msi_interrupts); + return sysfs_emit(page, "%d\n", + to_pci_epf_group(item)->epf->msi_interrupts); } static ssize_t pci_epf_msix_interrupts_store(struct config_item *item, @@ -412,8 +411,8 @@ static ssize_t pci_epf_msix_interrupts_store(struct config_item *item, static ssize_t pci_epf_msix_interrupts_show(struct config_item *item, char *page) { - return sprintf(page, "%d\n", - to_pci_epf_group(item)->epf->msix_interrupts); + return sysfs_emit(page, "%d\n", + to_pci_epf_group(item)->epf->msix_interrupts); } PCI_EPF_HEADER_R(vendorid) From 229d0cfae5b21bfc42525cf43b0b4279243acc4e Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 1 Oct 2021 14:32:44 +0900 Subject: [PATCH 137/587] kconfig: remove 'const' from the return type of sym_escape_string_value() sym_escape_string_value() returns a malloc'ed memory, but as (const char *). So, it must be casted to (void *) when it is free'd. This is odd. The return type of sym_escape_string_value() should be (char *). I exploited that free(NULL) has no effect. Signed-off-by: Masahiro Yamada --- scripts/kconfig/conf.c | 15 +++++++-------- scripts/kconfig/confdata.c | 27 ++++++++++++++------------- scripts/kconfig/lkc_proto.h | 2 +- scripts/kconfig/symbol.c | 3 ++- 4 files changed, 24 insertions(+), 23 deletions(-) diff --git a/scripts/kconfig/conf.c b/scripts/kconfig/conf.c index 5d84b44a2a2a..310fdd408793 100644 --- a/scripts/kconfig/conf.c +++ b/scripts/kconfig/conf.c @@ -647,17 +647,16 @@ static void check_conf(struct menu *menu) switch (input_mode) { case listnewconfig: if (sym->name) { - const char *str; + const char *val = sym_get_string_value(sym); + char *escaped = NULL; if (sym->type == S_STRING) { - str = sym_get_string_value(sym); - str = sym_escape_string_value(str); - printf("%s%s=%s\n", CONFIG_, sym->name, str); - free((void *)str); - } else { - str = sym_get_string_value(sym); - printf("%s%s=%s\n", CONFIG_, sym->name, str); + escaped = sym_escape_string_value(val); + val = escaped; } + + printf("%s%s=%s\n", CONFIG_, sym->name, val); + free(escaped); } break; case helpnewconfig: diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c index cf72680cd769..9b2271eb43d6 100644 --- a/scripts/kconfig/confdata.c +++ b/scripts/kconfig/confdata.c @@ -728,21 +728,22 @@ static struct conf_printer header_printer_cb = static void conf_write_symbol(FILE *fp, struct symbol *sym, struct conf_printer *printer, void *printer_arg) { - const char *str; + const char *val; + char *escaped = NULL; - switch (sym->type) { - case S_UNKNOWN: - break; - case S_STRING: - str = sym_get_string_value(sym); - str = sym_escape_string_value(str); - printer->print_symbol(fp, sym, str, printer_arg); - free((void *)str); - break; - default: - str = sym_get_string_value(sym); - printer->print_symbol(fp, sym, str, printer_arg); + if (sym->type == S_UNKNOWN) + return; + + val = sym_get_string_value(sym); + + if (sym->type == S_STRING) { + escaped = sym_escape_string_value(val); + val = escaped; } + + printer->print_symbol(fp, sym, val, printer_arg); + + free(escaped); } static void diff --git a/scripts/kconfig/lkc_proto.h b/scripts/kconfig/lkc_proto.h index a11626bdc421..e6955df49973 100644 --- a/scripts/kconfig/lkc_proto.h +++ b/scripts/kconfig/lkc_proto.h @@ -18,7 +18,7 @@ extern struct symbol * symbol_hash[SYMBOL_HASHSIZE]; struct symbol * sym_lookup(const char *name, int flags); struct symbol * sym_find(const char *name); -const char * sym_escape_string_value(const char *in); +char *sym_escape_string_value(const char *in); struct symbol ** sym_re_search(const char *pattern); const char * sym_type_name(enum symbol_type type); void sym_calc_value(struct symbol *sym); diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c index 5844d636d38f..6bf8665a6a0f 100644 --- a/scripts/kconfig/symbol.c +++ b/scripts/kconfig/symbol.c @@ -871,7 +871,8 @@ struct symbol *sym_find(const char *name) return symbol; } -const char *sym_escape_string_value(const char *in) +/* The returned pointer must be freed on the caller side */ +char *sym_escape_string_value(const char *in) { const char *p; size_t reslen; From b8228aea5a19d5111a7bf44f7de6749d1f5d487a Mon Sep 17 00:00:00 2001 From: Kewei Xu Date: Fri, 17 Sep 2021 18:14:10 +0800 Subject: [PATCH 138/587] i2c: mediatek: fixing the incorrect register offset The reason for the modification here is that the previous offset information is incorrect, OFFSET_DEBUGSTAT = 0xE4 is the correct value. Fixes: 25708278f810 ("i2c: mediatek: Add i2c support for MediaTek MT8183") Signed-off-by: Kewei Xu Reviewed-by: Chen-Yu Tsai Reviewed-by: Qii Wang Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-mt65xx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-mt65xx.c b/drivers/i2c/busses/i2c-mt65xx.c index 477480d1de6b..32518081b5a4 100644 --- a/drivers/i2c/busses/i2c-mt65xx.c +++ b/drivers/i2c/busses/i2c-mt65xx.c @@ -193,7 +193,7 @@ static const u16 mt_i2c_regs_v2[] = { [OFFSET_CLOCK_DIV] = 0x48, [OFFSET_SOFTRESET] = 0x50, [OFFSET_SCL_MIS_COMP_POINT] = 0x90, - [OFFSET_DEBUGSTAT] = 0xe0, + [OFFSET_DEBUGSTAT] = 0xe4, [OFFSET_DEBUGCTRL] = 0xe8, [OFFSET_FIFO_STAT] = 0xf4, [OFFSET_FIFO_THRESH] = 0xf8, From 511899ec34b605af5f8577f0f53866a8a60939f6 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 16 Sep 2021 19:05:17 +0200 Subject: [PATCH 139/587] i2c: pxa: drop unneeded MODULE_ALIAS The MODULE_DEVICE_TABLE already creates proper alias for platform driver. Having another MODULE_ALIAS causes the alias to be duplicated. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-pxa.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-pxa.c b/drivers/i2c/busses/i2c-pxa.c index a636ea0eb50a..690188a9ffff 100644 --- a/drivers/i2c/busses/i2c-pxa.c +++ b/drivers/i2c/busses/i2c-pxa.c @@ -1547,7 +1547,6 @@ static void __exit i2c_adap_pxa_exit(void) } MODULE_LICENSE("GPL"); -MODULE_ALIAS("platform:pxa2xx-i2c"); subsys_initcall(i2c_adap_pxa_init); module_exit(i2c_adap_pxa_exit); From cf9ae42c435c4a434b7c3d248f010699d43d684e Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 24 Sep 2021 15:35:49 +0200 Subject: [PATCH 140/587] i2c: exynos: describe drivers in KConfig Describe better which driver applies to which SoC, to make configuring kernel for Samsung SoC easier. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Wolfram Sang --- drivers/i2c/busses/Kconfig | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index e17790fe35a7..1df19ccc310b 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -615,7 +615,10 @@ config I2C_EXYNOS5 depends on ARCH_EXYNOS || COMPILE_TEST default y if ARCH_EXYNOS help - High-speed I2C controller on Exynos5 and newer Samsung SoCs. + High-speed I2C controller on Samsung Exynos5 and newer Samsung SoCs: + Exynos5250, Exynos5260, Exynos5410, Exynos542x, Exynos5800, + Exynos5433 and Exynos7. + Choose Y here only if you build for such Samsung SoC. config I2C_GPIO tristate "GPIO-based bitbanging I2C" From d56baf6efaf14e2910610216c581ca71d6940012 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 22 Aug 2021 21:38:12 +0200 Subject: [PATCH 141/587] i2c: switch from 'pci_' to 'dma_' API The wrappers in include/linux/pci-dma-compat.h should go away. The patch has been generated with the coccinelle script below. It has been hand modified to use 'dma_set_mask_and_coherent()' instead of 'pci_set_dma_mask()/pci_set_consistent_dma_mask()' when applicable. This is less verbose. While at it a 'dev_err()' message has been slightly simplified. It has been compile tested. @@ @@ - PCI_DMA_BIDIRECTIONAL + DMA_BIDIRECTIONAL @@ @@ - PCI_DMA_TODEVICE + DMA_TO_DEVICE @@ @@ - PCI_DMA_FROMDEVICE + DMA_FROM_DEVICE @@ @@ - PCI_DMA_NONE + DMA_NONE @@ expression e1, e2, e3; @@ - pci_alloc_consistent(e1, e2, e3) + dma_alloc_coherent(&e1->dev, e2, e3, GFP_) @@ expression e1, e2, e3; @@ - pci_zalloc_consistent(e1, e2, e3) + dma_alloc_coherent(&e1->dev, e2, e3, GFP_) @@ expression e1, e2, e3, e4; @@ - pci_free_consistent(e1, e2, e3, e4) + dma_free_coherent(&e1->dev, e2, e3, e4) @@ expression e1, e2, e3, e4; @@ - pci_map_single(e1, e2, e3, e4) + dma_map_single(&e1->dev, e2, e3, e4) @@ expression e1, e2, e3, e4; @@ - pci_unmap_single(e1, e2, e3, e4) + dma_unmap_single(&e1->dev, e2, e3, e4) @@ expression e1, e2, e3, e4, e5; @@ - pci_map_page(e1, e2, e3, e4, e5) + dma_map_page(&e1->dev, e2, e3, e4, e5) @@ expression e1, e2, e3, e4; @@ - pci_unmap_page(e1, e2, e3, e4) + dma_unmap_page(&e1->dev, e2, e3, e4) @@ expression e1, e2, e3, e4; @@ - pci_map_sg(e1, e2, e3, e4) + dma_map_sg(&e1->dev, e2, e3, e4) @@ expression e1, e2, e3, e4; @@ - pci_unmap_sg(e1, e2, e3, e4) + dma_unmap_sg(&e1->dev, e2, e3, e4) @@ expression e1, e2, e3, e4; @@ - pci_dma_sync_single_for_cpu(e1, e2, e3, e4) + dma_sync_single_for_cpu(&e1->dev, e2, e3, e4) @@ expression e1, e2, e3, e4; @@ - pci_dma_sync_single_for_device(e1, e2, e3, e4) + dma_sync_single_for_device(&e1->dev, e2, e3, e4) @@ expression e1, e2, e3, e4; @@ - pci_dma_sync_sg_for_cpu(e1, e2, e3, e4) + dma_sync_sg_for_cpu(&e1->dev, e2, e3, e4) @@ expression e1, e2, e3, e4; @@ - pci_dma_sync_sg_for_device(e1, e2, e3, e4) + dma_sync_sg_for_device(&e1->dev, e2, e3, e4) @@ expression e1, e2; @@ - pci_dma_mapping_error(e1, e2) + dma_mapping_error(&e1->dev, e2) @@ expression e1, e2; @@ - pci_set_dma_mask(e1, e2) + dma_set_mask(&e1->dev, e2) @@ expression e1, e2; @@ - pci_set_consistent_dma_mask(e1, e2) + dma_set_coherent_mask(&e1->dev, e2) Signed-off-by: Christophe JAILLET Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-amd-mp2-pci.c | 4 ++-- drivers/i2c/busses/i2c-ismt.c | 12 +++++------- 2 files changed, 7 insertions(+), 9 deletions(-) diff --git a/drivers/i2c/busses/i2c-amd-mp2-pci.c b/drivers/i2c/busses/i2c-amd-mp2-pci.c index ce130a821ea5..adf0e8c1ec01 100644 --- a/drivers/i2c/busses/i2c-amd-mp2-pci.c +++ b/drivers/i2c/busses/i2c-amd-mp2-pci.c @@ -307,9 +307,9 @@ static int amd_mp2_pci_init(struct amd_mp2_dev *privdata, pci_set_master(pci_dev); - rc = pci_set_dma_mask(pci_dev, DMA_BIT_MASK(64)); + rc = dma_set_mask(&pci_dev->dev, DMA_BIT_MASK(64)); if (rc) { - rc = pci_set_dma_mask(pci_dev, DMA_BIT_MASK(32)); + rc = dma_set_mask(&pci_dev->dev, DMA_BIT_MASK(32)); if (rc) goto err_dma_mask; } diff --git a/drivers/i2c/busses/i2c-ismt.c b/drivers/i2c/busses/i2c-ismt.c index a6187cbec2c9..f4820fd3dc13 100644 --- a/drivers/i2c/busses/i2c-ismt.c +++ b/drivers/i2c/busses/i2c-ismt.c @@ -918,13 +918,11 @@ ismt_probe(struct pci_dev *pdev, const struct pci_device_id *id) return -ENODEV; } - if ((pci_set_dma_mask(pdev, DMA_BIT_MASK(64)) != 0) || - (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)) != 0)) { - if ((pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) != 0) || - (pci_set_consistent_dma_mask(pdev, - DMA_BIT_MASK(32)) != 0)) { - dev_err(&pdev->dev, "pci_set_dma_mask fail %p\n", - pdev); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (err) { + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (err) { + dev_err(&pdev->dev, "dma_set_mask fail\n"); return -ENODEV; } } From 72698a8789268cb11da21c018041b45233b82cbb Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 30 Sep 2021 19:11:01 -0700 Subject: [PATCH 142/587] openrisc: time: don't mark comment as kernel-doc Fix a kernel-doc warning by unmarking the comment as being in kernel-doc notation. Fixes this warning: arch/openrisc/kernel/time.c:137: warning: expecting prototype for Clocksource(). Prototype was for openrisc_timer_read() instead Fixes: b731fbbd246e ("OpenRISC: Timekeeping") Signed-off-by: Randy Dunlap Reported-by: kernel test robot Cc: Jonas Bonn Cc: Stefan Kristiansson Cc: Stafford Horne Cc: openrisc@lists.librecores.org Signed-off-by: Stafford Horne --- arch/openrisc/kernel/time.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/openrisc/kernel/time.c b/arch/openrisc/kernel/time.c index b82866061958..a6e69386f82a 100644 --- a/arch/openrisc/kernel/time.c +++ b/arch/openrisc/kernel/time.c @@ -127,7 +127,7 @@ irqreturn_t __irq_entry timer_interrupt(struct pt_regs *regs) return IRQ_HANDLED; } -/** +/* * Clocksource: Based on OpenRISC timer/counter * * This sets up the OpenRISC Tick Timer as a clock source. The tick timer From b860b9346e2d5667fbae2cefc571bdb6ce665b53 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 13 Sep 2021 16:08:33 +0200 Subject: [PATCH 143/587] s390/ftrace: remove dead code ftrace_shared_hotpatch_trampoline() never returns NULL, therefore quite a bit of code can be removed. Acked-by: Ilya Leoshkevich Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/ftrace.c | 86 +++------------------------------------ 1 file changed, 6 insertions(+), 80 deletions(-) diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 1d94ffdf347b..5d0c45c13b5f 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -80,17 +80,6 @@ asm( #ifdef CONFIG_MODULES static char *ftrace_plt; - -asm( - " .data\n" - "ftrace_plt_template:\n" - " basr %r1,%r0\n" - " lg %r1,0f-.(%r1)\n" - " br %r1\n" - "0: .quad ftrace_caller\n" - "ftrace_plt_template_end:\n" - " .previous\n" -); #endif /* CONFIG_MODULES */ static const char *ftrace_shared_hotpatch_trampoline(const char **end) @@ -116,7 +105,7 @@ static const char *ftrace_shared_hotpatch_trampoline(const char **end) bool ftrace_need_init_nop(void) { - return ftrace_shared_hotpatch_trampoline(NULL); + return true; } int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) @@ -175,28 +164,6 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, return 0; } -static void ftrace_generate_nop_insn(struct ftrace_insn *insn) -{ - /* brcl 0,0 */ - insn->opc = 0xc004; - insn->disp = 0; -} - -static void ftrace_generate_call_insn(struct ftrace_insn *insn, - unsigned long ip) -{ - unsigned long target; - - /* brasl r0,ftrace_caller */ - target = FTRACE_ADDR; -#ifdef CONFIG_MODULES - if (is_module_addr((void *)ip)) - target = (unsigned long)ftrace_plt; -#endif /* CONFIG_MODULES */ - insn->opc = 0xc005; - insn->disp = (target - ip) / 2; -} - static void brcl_disable(void *brcl) { u8 op = 0x04; /* set mask field to zero */ @@ -207,23 +174,7 @@ static void brcl_disable(void *brcl) int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { - struct ftrace_insn orig, new, old; - - if (ftrace_shared_hotpatch_trampoline(NULL)) { - brcl_disable((void *)rec->ip); - return 0; - } - - if (copy_from_kernel_nofault(&old, (void *) rec->ip, sizeof(old))) - return -EFAULT; - /* Replace ftrace call with a nop. */ - ftrace_generate_call_insn(&orig, rec->ip); - ftrace_generate_nop_insn(&new); - - /* Verify that the to be replaced code matches what we expect. */ - if (memcmp(&orig, &old, sizeof(old))) - return -EINVAL; - s390_kernel_write((void *) rec->ip, &new, sizeof(new)); + brcl_disable((void *)rec->ip); return 0; } @@ -236,23 +187,7 @@ static void brcl_enable(void *brcl) int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { - struct ftrace_insn orig, new, old; - - if (ftrace_shared_hotpatch_trampoline(NULL)) { - brcl_enable((void *)rec->ip); - return 0; - } - - if (copy_from_kernel_nofault(&old, (void *) rec->ip, sizeof(old))) - return -EFAULT; - /* Replace nop with an ftrace call. */ - ftrace_generate_nop_insn(&orig); - ftrace_generate_call_insn(&new, rec->ip); - - /* Verify that the to be replaced code matches what we expect. */ - if (memcmp(&orig, &old, sizeof(old))) - return -EINVAL; - s390_kernel_write((void *) rec->ip, &new, sizeof(new)); + brcl_enable((void *)rec->ip); return 0; } @@ -269,10 +204,7 @@ int __init ftrace_dyn_arch_init(void) void arch_ftrace_update_code(int command) { - if (ftrace_shared_hotpatch_trampoline(NULL)) - ftrace_modify_all_code(command); - else - ftrace_run_stop_machine(command); + ftrace_modify_all_code(command); } static void __ftrace_sync(void *dummy) @@ -281,10 +213,8 @@ static void __ftrace_sync(void *dummy) int ftrace_arch_code_modify_post_process(void) { - if (ftrace_shared_hotpatch_trampoline(NULL)) { - /* Send SIGP to the other CPUs, so they see the new code. */ - smp_call_function(__ftrace_sync, NULL, 1); - } + /* Send SIGP to the other CPUs, so they see the new code. */ + smp_call_function(__ftrace_sync, NULL, 1); return 0; } @@ -299,10 +229,6 @@ static int __init ftrace_plt_init(void) panic("cannot allocate ftrace plt\n"); start = ftrace_shared_hotpatch_trampoline(&end); - if (!start) { - start = ftrace_plt_template; - end = ftrace_plt_template_end; - } memcpy(ftrace_plt, start, end - start); set_memory_ro((unsigned long)ftrace_plt, 1); return 0; From 4df898dc06da83052c73a2ce9a6a4df5640a0905 Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Mon, 6 Sep 2021 11:25:38 +0200 Subject: [PATCH 144/587] s390/kprobes: add sanity check Check whether the specified address points to the start of an instruction to prevent users from setting a kprobe in the mid of an instruction which would crash the kernel. Signed-off-by: Sven Schnelle Reviewed-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/kprobes.c | 48 +++++++++++++++++++++++++++++++++++++- 1 file changed, 47 insertions(+), 1 deletion(-) diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index 52d056a5f89f..0093c326a239 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -120,9 +120,55 @@ static void s390_free_insn_slot(struct kprobe *p) } NOKPROBE_SYMBOL(s390_free_insn_slot); +/* Check if paddr is at an instruction boundary */ +static bool can_probe(unsigned long paddr) +{ + unsigned long addr, offset = 0; + kprobe_opcode_t insn; + struct kprobe *kp; + + if (paddr & 0x01) + return false; + + if (!kallsyms_lookup_size_offset(paddr, NULL, &offset)) + return false; + + /* Decode instructions */ + addr = paddr - offset; + while (addr < paddr) { + if (copy_from_kernel_nofault(&insn, (void *)addr, sizeof(insn))) + return false; + + if (insn >> 8 == 0) { + if (insn != BREAKPOINT_INSTRUCTION) { + /* + * Note that QEMU inserts opcode 0x0000 to implement + * software breakpoints for guests. Since the size of + * the original instruction is unknown, stop following + * instructions and prevent setting a kprobe. + */ + return false; + } + /* + * Check if the instruction has been modified by another + * kprobe, in which case the original instruction is + * decoded. + */ + kp = get_kprobe((void *)addr); + if (!kp) { + /* not a kprobe */ + return false; + } + insn = kp->opcode; + } + addr += insn_length(insn >> 8); + } + return addr == paddr; +} + int arch_prepare_kprobe(struct kprobe *p) { - if ((unsigned long) p->addr & 0x01) + if (!can_probe((unsigned long)p->addr)) return -EINVAL; /* Make sure the probe isn't going on a difficult instruction */ if (probe_is_prohibited_opcode(p->addr)) From 1c8174fdc798489159a79466fca782daa231219a Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Tue, 7 Sep 2021 16:43:29 +0200 Subject: [PATCH 145/587] s390/pci: tolerate inconsistent handle in recover Since commit 8256adda1f44 ("s390/pci: handle FH state mismatch only on disable") zpci_disable_device() returns -EINVAL when the platform detects an attempt to disable a PCI function that it sees as already disabled. In most situations we want to abort whenever this happens and abort is possible since it either means that the device vanished but we haven't gotten an availability event yet, or the FH got out of sync which should not happen. Unfortunately there is an inconsistency between the LPAR and z/VM hypervisors on whether error events for PCI functions contain an an enabled or a general handle. So under z/VM it can happen that our most up to date function handle is enabled but trying to disable the function results in the aforementioned error. Since recover is designed to be used to recover functions from the error state let's make it robust to this inconsistency by explicitly treating it as a successful disable. Acked-by: Pierre Morel Signed-off-by: Niklas Schnelle Signed-off-by: Vasily Gorbik --- arch/s390/pci/pci_sysfs.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c index 335c281811c7..cae280e5c047 100644 --- a/arch/s390/pci/pci_sysfs.c +++ b/arch/s390/pci/pci_sysfs.c @@ -90,6 +90,14 @@ static ssize_t recover_store(struct device *dev, struct device_attribute *attr, if (zdev_enabled(zdev)) { ret = zpci_disable_device(zdev); + /* + * Due to a z/VM vs LPAR inconsistency in the error + * state the FH may indicate an enabled device but + * disable says the device is already disabled don't + * treat it as an error here. + */ + if (ret == -EINVAL) + ret = 0; if (ret) goto out; } From fa172f043f5bc21c357c54a6ca2e9c8acd18c3db Mon Sep 17 00:00:00 2001 From: Vineeth Vijayan Date: Wed, 15 Sep 2021 13:39:16 +0200 Subject: [PATCH 146/587] s390/cio: unregister the subchannel while purging The cio_ignore list is used to create and maintain the list of devices which is to be ignored by Linux. During boot-time, this list is adjusted and accommodate all the devices which are configured on the HMC interface. Once these devices are accessible, they are then available to Linux and set online. cio_ignore purge function should align with this functionality. But currently, the subchannel associated with the offline-devices are not unregistered during purge. Add an explicit subchannel-unregister function in the purge_fn callback. Signed-off-by: Vineeth Vijayan Reviewed-by: Peter Oberparleiter Signed-off-by: Vasily Gorbik --- drivers/s390/cio/device.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index 8d14569823d7..07a17613fab5 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -1322,6 +1322,7 @@ static int purge_fn(struct device *dev, void *data) { struct ccw_device *cdev = to_ccwdev(dev); struct ccw_dev_id *id = &cdev->private->dev_id; + struct subchannel *sch = to_subchannel(cdev->dev.parent); spin_lock_irq(cdev->ccwlock); if (is_blacklisted(id->ssid, id->devno) && @@ -1330,6 +1331,7 @@ static int purge_fn(struct device *dev, void *data) CIO_MSG_EVENT(3, "ccw: purging 0.%x.%04x\n", id->ssid, id->devno); ccw_device_sched_todo(cdev, CDEV_TODO_UNREG); + css_sched_sch_todo(sch, SCH_TODO_UNREG); atomic_set(&cdev->private->onoff, 0); } spin_unlock_irq(cdev->ccwlock); From 6526a597a2e856df9ae94512f9903caccd5196d6 Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Wed, 15 Sep 2021 17:08:44 +0200 Subject: [PATCH 147/587] s390/pci: add simpler s390dbf traces for events We often need to figure out what operations were performed in response to an error or availability event. The operations are easily accessible in s390dbf/pci_msg but the events have to be correlated with these from either the kernel log or s390dbf/pci_err. Improve this situation by logging the most important data from error and availability events that is the FID, PEC and FH together with the operations. Reviewed-by: Matthew Rosato Signed-off-by: Niklas Schnelle Signed-off-by: Vasily Gorbik --- arch/s390/pci/pci_event.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index c856f80cb21b..461bfb12a3a3 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -52,6 +52,8 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf) struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid); struct pci_dev *pdev = NULL; + zpci_dbg(3, "err fid:%x, fh:%x, pec:%x\n", + ccdf->fid, ccdf->fh, ccdf->pec); zpci_err("error CCDF:\n"); zpci_err_hex(ccdf, sizeof(*ccdf)); @@ -96,6 +98,8 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid); enum zpci_state state; + zpci_dbg(3, "avl fid:%x, fh:%x, pec:%x\n", + ccdf->fid, ccdf->fh, ccdf->pec); zpci_err("avail CCDF:\n"); zpci_err_hex(ccdf, sizeof(*ccdf)); From 0c3812c347bfb0dc213556a195e79850c55702f5 Mon Sep 17 00:00:00 2001 From: Vineeth Vijayan Date: Fri, 17 Sep 2021 15:04:01 +0200 Subject: [PATCH 148/587] s390/cio: derive cdev information only for IO-subchannels cdev->online for the purge function must not be checked for the non-IO subchannel type. Make sure that we are deriving the cdev only from sch-type SUBCHANNEL_TYPE_IO. Signed-off-by: Vineeth Vijayan Reviewed-by: Peter Oberparleiter Signed-off-by: Vasily Gorbik --- drivers/s390/cio/css.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index 44461928aab8..2bc55ccf3f23 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -792,10 +792,13 @@ static int __unset_online(struct device *dev, void *data) { struct idset *set = data; struct subchannel *sch = to_subchannel(dev); - struct ccw_device *cdev = sch_get_cdev(sch); + struct ccw_device *cdev; - if (cdev && cdev->online) - idset_sch_del(set, sch->schid); + if (sch->st == SUBCHANNEL_TYPE_IO) { + cdev = sch_get_cdev(sch); + if (cdev && cdev->online) + idset_sch_del(set, sch->schid); + } return 0; } From 54235d5cfea05f2891dca71d51d7ab097b53d22b Mon Sep 17 00:00:00 2001 From: Peter Oberparleiter Date: Thu, 23 Sep 2021 12:42:02 +0200 Subject: [PATCH 149/587] s390/sclp_sd: fix warnings about missing parameter description Fix these warnings that are reported when compiling with W=1: drivers/s390/char/sclp_sd.c:132: warning: Function parameter or member 'listener' not described in 'sclp_sd_listener_init' drivers/s390/char/sclp_sd.c:408: warning: Function parameter or member 'cookie' not described in 'sclp_sd_file_update_async' drivers/s390/char/sclp_sd.c:422: warning: Function parameter or member 'attr' not described in 'reload_store' drivers/s390/char/sclp_sd.c:422: warning: Function parameter or member 'buf' not described in 'reload_store' drivers/s390/char/sclp_sd.c:422: warning: Function parameter or member 'count' not described in 'reload_store' drivers/s390/char/sclp_sd.c:457: warning: Function parameter or member 'file' not described in 'data_read' drivers/s390/char/sclp_sd.c:457: warning: Function parameter or member 'attr' not described in 'data_read' Signed-off-by: Peter Oberparleiter Signed-off-by: Vasily Gorbik --- drivers/s390/char/sclp_sd.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/s390/char/sclp_sd.c b/drivers/s390/char/sclp_sd.c index 1e244f78f192..a5dd4e9f5b1b 100644 --- a/drivers/s390/char/sclp_sd.c +++ b/drivers/s390/char/sclp_sd.c @@ -122,6 +122,7 @@ static void sclp_sd_listener_remove(struct sclp_sd_listener *listener) /** * sclp_sd_listener_init() - Initialize a Store Data response listener + * @listener: Response listener to initialize * @id: Event ID to listen for * * Initialize a listener for asynchronous Store Data responses. This listener @@ -403,6 +404,7 @@ static int sclp_sd_file_update(struct sclp_sd_file *sd_file) /** * sclp_sd_file_update_async() - Wrapper for asynchronous update call * @data: Object to update + * @cookie: Unused */ static void sclp_sd_file_update_async(void *data, async_cookie_t cookie) { @@ -414,6 +416,9 @@ static void sclp_sd_file_update_async(void *data, async_cookie_t cookie) /** * reload_store() - Store function for "reload" sysfs attribute * @kobj: Kobject of sclp_sd_file object + * @attr: Reload attribute + * @buf: Data written to sysfs attribute + * @count: Count of bytes written * * Initiate a reload of the data associated with an sclp_sd_file object. */ @@ -441,8 +446,10 @@ static struct kobj_type sclp_sd_file_ktype = { }; /** - * data_read() - Read function for "read" sysfs attribute + * data_read() - Read function for "data" sysfs attribute + * @file: Open file pointer * @kobj: Kobject of sclp_sd_file object + * @attr: Data attribute * @buffer: Target buffer * @off: Requested file offset * @size: Requested number of bytes From f768a20c0a6e5f2396b9ab99bbbfd39d91228df9 Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Fri, 24 Sep 2021 15:03:07 +0200 Subject: [PATCH 150/587] s390/ftrace: add FTRACE_GEN_NOP_ASM macro FTRACE_GEN_NOP_ASM(name) can be used to generate assembly functions with the required information added to allow tracing via kprobes/ftrace. It adds the nop instruction which will be patched by ftrace later. If the compiler supports -mnop-mcount it will also add an entry to the __mcount_loc section. Signed-off-by: Sven Schnelle Acked-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/ftrace.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h index e8b460f39c58..d1841f4176be 100644 --- a/arch/s390/include/asm/ftrace.h +++ b/arch/s390/include/asm/ftrace.h @@ -68,4 +68,32 @@ static inline bool arch_syscall_match_sym_name(const char *sym, } #endif /* __ASSEMBLY__ */ + +#ifdef CONFIG_FUNCTION_TRACER + +#define FTRACE_NOP_INSN .word 0xc004, 0x0000, 0x0000 /* brcl 0,0 */ + +#ifndef CC_USING_HOTPATCH + +#define FTRACE_GEN_MCOUNT_RECORD(name) \ + .section __mcount_loc, "a", @progbits; \ + .quad name; \ + .previous; + +#else /* !CC_USING_HOTPATCH */ + +#define FTRACE_GEN_MCOUNT_RECORD(name) + +#endif /* !CC_USING_HOTPATCH */ + +#define FTRACE_GEN_NOP_ASM(name) \ + FTRACE_GEN_MCOUNT_RECORD(name) \ + FTRACE_NOP_INSN + +#else /* CONFIG_FUNCTION_TRACER */ + +#define FTRACE_GEN_NOP_ASM(name) + +#endif /* CONFIG_FUNCTION_TRACER */ + #endif /* _ASM_S390_FTRACE_H */ From d340d28a968ec479d0ed3c38ab716ed821d82ad8 Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Thu, 9 Sep 2021 20:59:17 +0200 Subject: [PATCH 151/587] kprobes: add testcases for s390 Add a few testcases to make sure that it's not possible to place a kprobe in the mid of an instruction on s390. Signed-off-by: Sven Schnelle Acked-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/Kconfig | 12 +++++ arch/s390/configs/debug_defconfig | 1 + arch/s390/lib/Makefile | 2 + arch/s390/lib/test_kprobes.c | 75 +++++++++++++++++++++++++++++++ arch/s390/lib/test_kprobes.h | 10 +++++ arch/s390/lib/test_kprobes_asm.S | 45 +++++++++++++++++++ 6 files changed, 145 insertions(+) create mode 100644 arch/s390/lib/test_kprobes.c create mode 100644 arch/s390/lib/test_kprobes.h create mode 100644 arch/s390/lib/test_kprobes_asm.S diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index b86de61b8caa..4d63662a919d 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -946,4 +946,16 @@ config S390_UNWIND_SELFTEST Say N if you are unsure. +config S390_KPROBES_SANITY_TEST + def_tristate n + prompt "Enable s390 specific kprobes tests" + depends on KPROBES + depends on KUNIT + help + This option enables an s390 specific kprobes test module. This option + is not useful for distributions or general kernels, but only for kernel + developers working on architecture code. + + Say N if you are unsure. + endmenu diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 6aad18ee131d..1818d67c2c1c 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -62,6 +62,7 @@ CONFIG_CMM=m CONFIG_APPLDATA_BASE=y CONFIG_KVM=m CONFIG_S390_UNWIND_SELFTEST=y +CONFIG_S390_KPROBES_SANITY_TEST=y CONFIG_KPROBES=y CONFIG_JUMP_LABEL=y CONFIG_STATIC_KEYS_SELFTEST=y diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile index 678333936f78..707cd4622c13 100644 --- a/arch/s390/lib/Makefile +++ b/arch/s390/lib/Makefile @@ -7,6 +7,8 @@ lib-y += delay.o string.o uaccess.o find.o spinlock.o obj-y += mem.o xor.o lib-$(CONFIG_KPROBES) += probes.o lib-$(CONFIG_UPROBES) += probes.o +obj-$(CONFIG_S390_KPROBES_SANITY_TEST) += test_kprobes_s390.o +test_kprobes_s390-objs += test_kprobes_asm.o test_kprobes.o # Instrumenting memory accesses to __user data (in different address space) # produce false positives diff --git a/arch/s390/lib/test_kprobes.c b/arch/s390/lib/test_kprobes.c new file mode 100644 index 000000000000..9e62d62812e5 --- /dev/null +++ b/arch/s390/lib/test_kprobes.c @@ -0,0 +1,75 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include +#include +#include +#include +#include "test_kprobes.h" + +static struct kprobe kp; + +static void setup_kprobe(struct kunit *test, struct kprobe *kp, + const char *symbol, int offset) +{ + kp->offset = offset; + kp->addr = NULL; + kp->symbol_name = symbol; +} + +static void test_kprobe_offset(struct kunit *test, struct kprobe *kp, + const char *target, int offset) +{ + int ret; + + setup_kprobe(test, kp, target, 0); + ret = register_kprobe(kp); + if (!ret) + unregister_kprobe(kp); + KUNIT_EXPECT_EQ(test, 0, ret); + setup_kprobe(test, kp, target, offset); + ret = register_kprobe(kp); + KUNIT_EXPECT_EQ(test, -EINVAL, ret); + if (!ret) + unregister_kprobe(kp); +} + +static void test_kprobe_odd(struct kunit *test) +{ + test_kprobe_offset(test, &kp, "kprobes_target_odd", + kprobes_target_odd_offs); +} + +static void test_kprobe_in_insn4(struct kunit *test) +{ + test_kprobe_offset(test, &kp, "kprobes_target_in_insn4", + kprobes_target_in_insn4_offs); +} + +static void test_kprobe_in_insn6_lo(struct kunit *test) +{ + test_kprobe_offset(test, &kp, "kprobes_target_in_insn6_lo", + kprobes_target_in_insn6_lo_offs); +} + +static void test_kprobe_in_insn6_hi(struct kunit *test) +{ + test_kprobe_offset(test, &kp, "kprobes_target_in_insn6_hi", + kprobes_target_in_insn6_hi_offs); +} + +static struct kunit_case kprobes_testcases[] = { + KUNIT_CASE(test_kprobe_odd), + KUNIT_CASE(test_kprobe_in_insn4), + KUNIT_CASE(test_kprobe_in_insn6_lo), + KUNIT_CASE(test_kprobe_in_insn6_hi), + {} +}; + +static struct kunit_suite kprobes_test_suite = { + .name = "kprobes_test_s390", + .test_cases = kprobes_testcases, +}; + +kunit_test_suites(&kprobes_test_suite); + +MODULE_LICENSE("GPL"); diff --git a/arch/s390/lib/test_kprobes.h b/arch/s390/lib/test_kprobes.h new file mode 100644 index 000000000000..2b4c9bc337f1 --- /dev/null +++ b/arch/s390/lib/test_kprobes.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +#ifndef TEST_KPROBES_H +#define TEST_KPROBES_H + +extern unsigned long kprobes_target_odd_offs; +extern unsigned long kprobes_target_in_insn4_offs; +extern unsigned long kprobes_target_in_insn6_lo_offs; +extern unsigned long kprobes_target_in_insn6_hi_offs; + +#endif diff --git a/arch/s390/lib/test_kprobes_asm.S b/arch/s390/lib/test_kprobes_asm.S new file mode 100644 index 000000000000..ade7a3042334 --- /dev/null +++ b/arch/s390/lib/test_kprobes_asm.S @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#include +#include + +#define KPROBES_TARGET_START(name) \ + SYM_FUNC_START(name); \ + FTRACE_GEN_NOP_ASM(name) + +#define KPROBES_TARGET_END(name) \ + SYM_FUNC_END(name); \ + SYM_DATA(name##_offs, .quad 1b - name) + +KPROBES_TARGET_START(kprobes_target_in_insn4) + .word 0x4700 // bc 0,0 +1: .word 0x0000 + br %r14 +KPROBES_TARGET_END(kprobes_target_in_insn4) + +KPROBES_TARGET_START(kprobes_target_in_insn6_lo) + .word 0xe310 // ly 1,0 +1: .word 0x0000 + .word 0x0058 + br %r14 +KPROBES_TARGET_END(kprobes_target_in_insn6_lo) + +KPROBES_TARGET_START(kprobes_target_in_insn6_hi) + .word 0xe310 // ly 1,0 + .word 0x0000 +1: .word 0x0058 + br %r14 +KPROBES_TARGET_END(kprobes_target_in_insn6_hi) + +KPROBES_TARGET_START(kprobes_target_bp) + nop + .word 0x0000 + nop +1: br %r14 +KPROBES_TARGET_END(kprobes_target_bp) + +KPROBES_TARGET_START(kprobes_target_odd) + .byte 0x07 +1: .byte 0x07 + br %r14 +KPROBES_TARGET_END(kprobes_target_odd) From bca2d0428e3d83b1a39ec46033e69fba8624280f Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 27 Sep 2021 14:56:47 -0700 Subject: [PATCH 152/587] s390/sclp_vt220: fix unused function warning When CONFIG_SCLP_VT220_TTY=y and CONFIG_SCLP_VT220_CONSOLE is not set: ../drivers/s390/char/sclp_vt220.c:771:13: warning: '__sclp_vt220_flush_buffer' defined but not used [-Wunused-function] 771 | static void __sclp_vt220_flush_buffer(void) so move this function inside the #ifdef block where it is used. Signed-off-by: Randy Dunlap Cc: Vasily Gorbik Cc: Christian Borntraeger Link: https://lore.kernel.org/r/20210927215647.11506-1-rdunlap@infradead.org Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- drivers/s390/char/sclp_vt220.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/s390/char/sclp_vt220.c b/drivers/s390/char/sclp_vt220.c index 29a6a0099f83..7bc4e4a10937 100644 --- a/drivers/s390/char/sclp_vt220.c +++ b/drivers/s390/char/sclp_vt220.c @@ -768,6 +768,8 @@ out_driver: } __initcall(sclp_vt220_tty_init); +#ifdef CONFIG_SCLP_VT220_CONSOLE + static void __sclp_vt220_flush_buffer(void) { unsigned long flags; @@ -784,8 +786,6 @@ static void __sclp_vt220_flush_buffer(void) spin_unlock_irqrestore(&sclp_vt220_lock, flags); } -#ifdef CONFIG_SCLP_VT220_CONSOLE - static void sclp_vt220_con_write(struct console *con, const char *buf, unsigned int count) { From 584315ed87a7dce663ef3f07956b5f363f83c7bd Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Tue, 3 Aug 2021 19:42:32 +0200 Subject: [PATCH 153/587] s390/boot: initialize control registers in decompressor Partially revert commit 4555b9f34296 ("s390/boot: move dma sections from decompressor to decompressed kernel"). This is a prerequisite to allow initialization of virtual memory in decompressor and avoid overwriting of ASCEs in the decompressed kernel otherwise. Since the control registers 2, 5 and 15 are reinitialized in the decompressed kernel again, this change does not prevent relocating of amode31 section in any way. Reviewed-by: Heiko Carstens Signed-off-by: Alexander Gordeev Signed-off-by: Vasily Gorbik --- arch/s390/boot/head.S | 17 +++++++++++++++++ arch/s390/kernel/head64.S | 18 ------------------ 2 files changed, 17 insertions(+), 18 deletions(-) diff --git a/arch/s390/boot/head.S b/arch/s390/boot/head.S index 40f4cff538b8..7e843d8e794e 100644 --- a/arch/s390/boot/head.S +++ b/arch/s390/boot/head.S @@ -317,6 +317,7 @@ SYM_CODE_START_LOCAL(startup_normal) xc 0x300(256),0x300 xc 0xe00(256),0xe00 xc 0xf00(256),0xf00 + lctlg %c0,%c15,.Lctl-.LPG0(%r13) # load control registers stcke __LC_BOOT_CLOCK mvc __LC_LAST_UPDATE_CLOCK(8),__LC_BOOT_CLOCK+1 spt 6f-.LPG0(%r13) @@ -335,6 +336,22 @@ SYM_CODE_END(startup_normal) .quad 0x0000000180000000,startup_pgm_check_handler .Lio_new_psw: .quad 0x0002000180000000,0x1f0 # disabled wait +.Lctl: .quad 0x04040000 # cr0: AFP registers & secondary space + .quad 0 # cr1: primary space segment table + .quad 0 # cr2: dispatchable unit control table + .quad 0 # cr3: instruction authorization + .quad 0xffff # cr4: instruction authorization + .quad 0 # cr5: primary-aste origin + .quad 0 # cr6: I/O interrupts + .quad 0 # cr7: secondary space segment table + .quad 0x0000000000008000 # cr8: access registers translation + .quad 0 # cr9: tracing off + .quad 0 # cr10: tracing off + .quad 0 # cr11: tracing off + .quad 0 # cr12: tracing off + .quad 0 # cr13: home space segment table + .quad 0xc0000000 # cr14: machine check handling off + .quad 0 # cr15: linkage stack operations #include "head_kdump.S" diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index 114b5490ad8e..42f9a325a257 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -20,8 +20,6 @@ __HEAD ENTRY(startup_continue) larl %r1,tod_clock_base mvc 0(16,%r1),__LC_BOOT_CLOCK - larl %r13,.LPG1 # get base - lctlg %c0,%c15,.Lctl-.LPG1(%r13) # load control registers # # Setup stack # @@ -42,19 +40,3 @@ ENTRY(startup_continue) .align 16 .LPG1: .Ldw: .quad 0x0002000180000000,0x0000000000000000 -.Lctl: .quad 0x04040000 # cr0: AFP registers & secondary space - .quad 0 # cr1: primary space segment table - .quad 0 # cr2: dispatchable unit control table - .quad 0 # cr3: instruction authorization - .quad 0xffff # cr4: instruction authorization - .quad 0 # cr5: primary-aste origin - .quad 0 # cr6: I/O interrupts - .quad 0 # cr7: secondary space segment table - .quad 0x0000000000008000 # cr8: access registers translation - .quad 0 # cr9: tracing off - .quad 0 # cr10: tracing off - .quad 0 # cr11: tracing off - .quad 0 # cr12: tracing off - .quad 0 # cr13: home space segment table - .quad 0xc0000000 # cr14: machine check handling off - .quad 0 # cr15: linkage stack operations From e3ec8e0f5711d73f7e5d5c3cffdf4fad4f1487b9 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Mon, 27 Sep 2021 14:18:26 +0200 Subject: [PATCH 154/587] s390/boot: allocate amode31 section in decompressor The memory for amode31 section is allocated from the decompressed kernel. Instead, allocate that memory from the decompressor. This is a prerequisite to allow initialization of the virtual memory before the decompressed kernel takes over. Reviewed-by: Heiko Carstens Signed-off-by: Alexander Gordeev Signed-off-by: Vasily Gorbik --- arch/s390/boot/compressed/decompressor.h | 1 + arch/s390/boot/startup.c | 8 ++++++++ arch/s390/kernel/entry.h | 1 + arch/s390/kernel/setup.c | 22 +++++++++------------- arch/s390/kernel/vmlinux.lds.S | 1 + 5 files changed, 20 insertions(+), 13 deletions(-) diff --git a/arch/s390/boot/compressed/decompressor.h b/arch/s390/boot/compressed/decompressor.h index a59f75c5b049..f75cc31a77dd 100644 --- a/arch/s390/boot/compressed/decompressor.h +++ b/arch/s390/boot/compressed/decompressor.h @@ -24,6 +24,7 @@ struct vmlinux_info { unsigned long dynsym_start; unsigned long rela_dyn_start; unsigned long rela_dyn_end; + unsigned long amode31_size; }; /* Symbols defined by linker scripts */ diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index 6dc8d0a53864..7571dee72a0c 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -15,6 +15,7 @@ #include "uv.h" unsigned long __bootdata_preserved(__kaslr_offset); +unsigned long __bootdata(__amode31_base); unsigned long __bootdata_preserved(VMALLOC_START); unsigned long __bootdata_preserved(VMALLOC_END); struct page *__bootdata_preserved(vmemmap); @@ -259,6 +260,12 @@ static void offset_vmlinux_info(unsigned long offset) vmlinux.dynsym_start += offset; } +static unsigned long reserve_amode31(unsigned long safe_addr) +{ + __amode31_base = PAGE_ALIGN(safe_addr); + return safe_addr + vmlinux.amode31_size; +} + void startup_kernel(void) { unsigned long random_lma; @@ -273,6 +280,7 @@ void startup_kernel(void) setup_lpp(); store_ipl_parmblock(); safe_addr = mem_safe_offset(); + safe_addr = reserve_amode31(safe_addr); safe_addr = read_ipl_report(safe_addr); uv_query_info(); rescue_initrd(safe_addr); diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index 7f2696e8d511..6083090be1f4 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -70,5 +70,6 @@ extern struct exception_table_entry _stop_amode31_ex_table[]; #define __amode31_data __section(".amode31.data") #define __amode31_ref __section(".amode31.refs") extern long _start_amode31_refs[], _end_amode31_refs[]; +extern unsigned long __amode31_base; #endif /* _ENTRY_H */ diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 67e5fff96ee0..191fc96a41b2 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -95,10 +95,10 @@ EXPORT_SYMBOL(console_irq); * relocated above 2 GB, because it has to use 31 bit addresses. * Such code and data is part of the .amode31 section. */ -unsigned long __amode31_ref __samode31 = __pa(&_samode31); -unsigned long __amode31_ref __eamode31 = __pa(&_eamode31); -unsigned long __amode31_ref __stext_amode31 = __pa(&_stext_amode31); -unsigned long __amode31_ref __etext_amode31 = __pa(&_etext_amode31); +unsigned long __amode31_ref __samode31 = (unsigned long)&_samode31; +unsigned long __amode31_ref __eamode31 = (unsigned long)&_eamode31; +unsigned long __amode31_ref __stext_amode31 = (unsigned long)&_stext_amode31; +unsigned long __amode31_ref __etext_amode31 = (unsigned long)&_etext_amode31; struct exception_table_entry __amode31_ref *__start_amode31_ex_table = _start_amode31_ex_table; struct exception_table_entry __amode31_ref *__stop_amode31_ex_table = _stop_amode31_ex_table; @@ -149,6 +149,7 @@ struct mem_detect_info __bootdata(mem_detect); struct initrd_data __bootdata(initrd_data); unsigned long __bootdata_preserved(__kaslr_offset); +unsigned long __bootdata(__amode31_base); unsigned int __bootdata_preserved(zlib_dfltcc_support); EXPORT_SYMBOL(zlib_dfltcc_support); u64 __bootdata_preserved(stfle_fac_list[16]); @@ -808,6 +809,7 @@ static void __init reserve_kernel(void) memblock_reserve(0, STARTUP_NORMAL_OFFSET); memblock_reserve((unsigned long)sclp_early_sccb, EXT_SCCB_READ_SCP); + memblock_reserve(__amode31_base, __eamode31 - __samode31); memblock_reserve((unsigned long)_stext, PFN_PHYS(start_pfn) - (unsigned long)_stext); } @@ -831,20 +833,14 @@ static void __init setup_memory(void) static void __init relocate_amode31_section(void) { - unsigned long amode31_addr, amode31_size; - long amode31_offset; + unsigned long amode31_size = __eamode31 - __samode31; + long amode31_offset = __amode31_base - __samode31; long *ptr; - /* Allocate a new AMODE31 capable memory region */ - amode31_size = __eamode31 - __samode31; pr_info("Relocating AMODE31 section of size 0x%08lx\n", amode31_size); - amode31_addr = (unsigned long)memblock_alloc_low(amode31_size, PAGE_SIZE); - if (!amode31_addr) - panic("Failed to allocate memory for AMODE31 section\n"); - amode31_offset = amode31_addr - __samode31; /* Move original AMODE31 section to the new one */ - memmove((void *)amode31_addr, (void *)__samode31, amode31_size); + memmove((void *)__amode31_base, (void *)__samode31, amode31_size); /* Zero out the old AMODE31 section to catch invalid accesses within it */ memset((void *)__samode31, 0, amode31_size); diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 63bdb9e1bfc1..42c43521878f 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -212,6 +212,7 @@ SECTIONS QUAD(__dynsym_start) /* dynsym_start */ QUAD(__rela_dyn_start) /* rela_dyn_start */ QUAD(__rela_dyn_end) /* rela_dyn_end */ + QUAD(_eamode31 - _samode31) /* amode31_size */ } :NONE /* Debugging sections. */ From 11dfe199eb31079a6f2517a59c380ad55f156696 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Mon, 27 Sep 2021 15:02:30 -0700 Subject: [PATCH 155/587] s390/block/dasd_genhd: add error handling support for add_disk() We never checked for errors on add_disk() as this function returned void. Now that this is fixed, use the shiny new error handling. Be sure to call dasd_gendisk_free() on error. Signed-off-by: Luis Chamberlain Link: https://lore.kernel.org/r/20210927220232.1071926-5-mcgrof@kernel.org Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- drivers/s390/block/dasd_genhd.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c index fa966e0db6ca..80673dbfb1f9 100644 --- a/drivers/s390/block/dasd_genhd.c +++ b/drivers/s390/block/dasd_genhd.c @@ -33,7 +33,7 @@ int dasd_gendisk_alloc(struct dasd_block *block) { struct gendisk *gdp; struct dasd_device *base; - int len; + int len, rc; /* Make sure the minor for this device exists. */ base = block->base; @@ -79,7 +79,13 @@ int dasd_gendisk_alloc(struct dasd_block *block) dasd_add_link_to_gendisk(gdp, base); block->gdp = gdp; set_capacity(block->gdp, 0); - device_add_disk(&base->cdev->dev, block->gdp, NULL); + + rc = device_add_disk(&base->cdev->dev, block->gdp, NULL); + if (rc) { + dasd_gendisk_free(block); + return rc; + } + return 0; } From 1a5db707c859a4f63c1066c5b88864d3f1c21c12 Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Mon, 27 Sep 2021 15:02:31 -0700 Subject: [PATCH 156/587] s390/block/dcssblk: add error handling support for add_disk() We never checked for errors on add_disk() as this function returned void. Now that this is fixed, use the shiny new error handling. Signed-off-by: Luis Chamberlain Signed-off-by: Gerald Schaefer Link: https://lore.kernel.org/r/20210927220232.1071926-6-mcgrof@kernel.org Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- drivers/s390/block/dcssblk.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index 5be3d1c39a78..0741a9321712 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -696,7 +696,9 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char } get_device(&dev_info->dev); - device_add_disk(&dev_info->dev, dev_info->gd, NULL); + rc = device_add_disk(&dev_info->dev, dev_info->gd, NULL); + if (rc) + goto out_dax; switch (dev_info->segment_type) { case SEG_TYPE_SR: @@ -712,6 +714,10 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char rc = count; goto out; +out_dax: + put_device(&dev_info->dev); + kill_dax(dev_info->dax_dev); + put_dax(dev_info->dax_dev); put_dev: list_del(&dev_info->lh); blk_cleanup_disk(dev_info->gd); From f367c7d9fb326996862f6b5cf2aff7a2df64692d Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Mon, 27 Sep 2021 15:02:32 -0700 Subject: [PATCH 157/587] s390/block/scm_blk: add error handling support for add_disk() We never checked for errors on add_disk() as this function returned void. Now that this is fixed, use the shiny new error handling. Acked-by: Heiko Carstens Signed-off-by: Luis Chamberlain Link: https://lore.kernel.org/r/20210927220232.1071926-7-mcgrof@kernel.org Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- drivers/s390/block/scm_blk.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/s390/block/scm_blk.c b/drivers/s390/block/scm_blk.c index 88cba6212ee2..61ecdcb2cc6a 100644 --- a/drivers/s390/block/scm_blk.c +++ b/drivers/s390/block/scm_blk.c @@ -495,9 +495,14 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev) /* 512 byte sectors */ set_capacity(bdev->gendisk, scmdev->size >> 9); - device_add_disk(&scmdev->dev, bdev->gendisk, NULL); + ret = device_add_disk(&scmdev->dev, bdev->gendisk, NULL); + if (ret) + goto out_cleanup_disk; + return 0; +out_cleanup_disk: + blk_cleanup_disk(bdev->gendisk); out_tag: blk_mq_free_tag_set(&bdev->tag_set); out: From be8ecc57f180415e8a7c1cc5620c5236be2a7e56 Mon Sep 17 00:00:00 2001 From: Tony Garnock-Jones Date: Thu, 16 Sep 2021 14:09:39 +0200 Subject: [PATCH 158/587] perf srcline: Use long-running addr2line per DSO Invoking addr2line in a separate subprocess, one for each required lookup, takes a terribly long time. This patch introduces a long-running addr2line process for each DSO, *DRAMATICALLY* speeding up runs of perf. What used to take tens of minutes now takes tens of seconds. Debian bug report about this issue: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=911815 Signed-off-by: Tony Garnock-Jones Tested-by: Ian Rogers Cc: Ingo Molnar Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20210916120939.453536-1-tonyg@leastfixedpoint.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/srcline.c | 354 +++++++++++++++++++++++++++----------- 1 file changed, 258 insertions(+), 96 deletions(-) diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index 5b7d6c16d33f..af468e3bb6fa 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -1,8 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include #include #include #include +#include #include #include @@ -15,6 +17,7 @@ #include "srcline.h" #include "string2.h" #include "symbol.h" +#include "subcmd/run-command.h" bool srcline_full_filename; @@ -119,6 +122,8 @@ static struct symbol *new_inline_sym(struct dso *dso, return inline_sym; } +#define MAX_INLINE_NEST 1024 + #ifdef HAVE_LIBBFD_SUPPORT /* @@ -273,8 +278,6 @@ static void addr2line_cleanup(struct a2l_data *a2l) free(a2l); } -#define MAX_INLINE_NEST 1024 - static int inline_list__append_dso_a2l(struct dso *dso, struct inline_node *node, struct symbol *sym) @@ -361,26 +364,14 @@ void dso__free_a2l(struct dso *dso) dso->a2l = NULL; } -static struct inline_node *addr2inlines(const char *dso_name, u64 addr, - struct dso *dso, struct symbol *sym) -{ - struct inline_node *node; - - node = zalloc(sizeof(*node)); - if (node == NULL) { - perror("not enough memory for the inline node"); - return NULL; - } - - INIT_LIST_HEAD(&node->val); - node->addr = addr; - - addr2line(dso_name, addr, NULL, NULL, dso, true, node, sym); - return node; -} - #else /* HAVE_LIBBFD_SUPPORT */ +struct a2l_subprocess { + struct child_process addr2line; + FILE *to_child; + FILE *from_child; +}; + static int filename_split(char *filename, unsigned int *line_nr) { char *sep; @@ -402,114 +393,285 @@ static int filename_split(char *filename, unsigned int *line_nr) return 0; } -static int addr2line(const char *dso_name, u64 addr, - char **file, unsigned int *line_nr, - struct dso *dso __maybe_unused, - bool unwind_inlines __maybe_unused, - struct inline_node *node __maybe_unused, - struct symbol *sym __maybe_unused) +static void addr2line_subprocess_cleanup(struct a2l_subprocess *a2l) { - FILE *fp; - char cmd[PATH_MAX]; - char *filename = NULL; - size_t len; - int ret = 0; - - scnprintf(cmd, sizeof(cmd), "addr2line -e %s %016"PRIx64, - dso_name, addr); - - fp = popen(cmd, "r"); - if (fp == NULL) { - pr_warning("popen failed for %s\n", dso_name); - return 0; + if (a2l->addr2line.pid != -1) { + kill(a2l->addr2line.pid, SIGKILL); + finish_command(&a2l->addr2line); /* ignore result, we don't care */ + a2l->addr2line.pid = -1; } - if (getline(&filename, &len, fp) < 0 || !len) { - pr_warning("addr2line has no output for %s\n", dso_name); + if (a2l->to_child != NULL) { + fclose(a2l->to_child); + a2l->to_child = NULL; + } + + if (a2l->from_child != NULL) { + fclose(a2l->from_child); + a2l->from_child = NULL; + } + + free(a2l); +} + +static struct a2l_subprocess *addr2line_subprocess_init(const char *path) +{ + const char *argv[] = { "addr2line", "-e", path, "-i", "-f", NULL }; + struct a2l_subprocess *a2l = zalloc(sizeof(*a2l)); + int start_command_status = 0; + + if (a2l == NULL) + goto out; + + a2l->to_child = NULL; + a2l->from_child = NULL; + + a2l->addr2line.pid = -1; + a2l->addr2line.in = -1; + a2l->addr2line.out = -1; + a2l->addr2line.no_stderr = 1; + + a2l->addr2line.argv = argv; + start_command_status = start_command(&a2l->addr2line); + a2l->addr2line.argv = NULL; /* it's not used after start_command; avoid dangling pointers */ + + if (start_command_status != 0) { + pr_warning("could not start addr2line for %s: start_command return code %d\n", + path, + start_command_status); goto out; } - ret = filename_split(filename, line_nr); - if (ret != 1) { - free(filename); + a2l->to_child = fdopen(a2l->addr2line.in, "w"); + if (a2l->to_child == NULL) { + pr_warning("could not open write-stream to addr2line of %s\n", path); goto out; } - *file = filename; + a2l->from_child = fdopen(a2l->addr2line.out, "r"); + if (a2l->from_child == NULL) { + pr_warning("could not open read-stream from addr2line of %s\n", path); + goto out; + } + + return a2l; out: - pclose(fp); + if (a2l) + addr2line_subprocess_cleanup(a2l); + + return NULL; +} + +static int read_addr2line_record(struct a2l_subprocess *a2l, + char **function, + char **filename, + unsigned int *line_nr) +{ + /* + * Returns: + * -1 ==> error + * 0 ==> sentinel (or other ill-formed) record read + * 1 ==> a genuine record read + */ + char *line = NULL; + size_t line_len = 0; + unsigned int dummy_line_nr = 0; + int ret = -1; + + if (function != NULL) + zfree(function); + + if (filename != NULL) + zfree(filename); + + if (line_nr != NULL) + *line_nr = 0; + + if (getline(&line, &line_len, a2l->from_child) < 0 || !line_len) + goto error; + + if (function != NULL) + *function = strdup(strim(line)); + + zfree(&line); + line_len = 0; + + if (getline(&line, &line_len, a2l->from_child) < 0 || !line_len) + goto error; + + if (filename_split(line, line_nr == NULL ? &dummy_line_nr : line_nr) == 0) { + ret = 0; + goto error; + } + + if (filename != NULL) + *filename = strdup(line); + + zfree(&line); + line_len = 0; + + return 1; + +error: + free(line); + if (function != NULL) + zfree(function); + if (filename != NULL) + zfree(filename); return ret; } -void dso__free_a2l(struct dso *dso __maybe_unused) +static int inline_list__append_record(struct dso *dso, + struct inline_node *node, + struct symbol *sym, + const char *function, + const char *filename, + unsigned int line_nr) { + struct symbol *inline_sym = new_inline_sym(dso, sym, function); + + return inline_list__append(inline_sym, srcline_from_fileline(filename, line_nr), node); } -static struct inline_node *addr2inlines(const char *dso_name, u64 addr, - struct dso *dso __maybe_unused, - struct symbol *sym) +static int addr2line(const char *dso_name, u64 addr, + char **file, unsigned int *line_nr, + struct dso *dso, + bool unwind_inlines, + struct inline_node *node, + struct symbol *sym __maybe_unused) { - FILE *fp; - char cmd[PATH_MAX]; - struct inline_node *node; - char *filename = NULL; - char *funcname = NULL; - size_t filelen, funclen; - unsigned int line_nr = 0; + struct a2l_subprocess *a2l = dso->a2l; + char *record_function = NULL; + char *record_filename = NULL; + unsigned int record_line_nr = 0; + int record_status = -1; + int ret = 0; + size_t inline_count = 0; - scnprintf(cmd, sizeof(cmd), "addr2line -e %s -i -f %016"PRIx64, - dso_name, addr); - - fp = popen(cmd, "r"); - if (fp == NULL) { - pr_err("popen failed for %s\n", dso_name); - return NULL; + if (!a2l) { + dso->a2l = addr2line_subprocess_init(dso_name); + a2l = dso->a2l; } + if (a2l == NULL) { + if (!symbol_conf.disable_add2line_warn) + pr_warning("%s %s: addr2line_subprocess_init failed\n", __func__, dso_name); + goto out; + } + + /* + * Send our request and then *deliberately* send something that can't be interpreted as + * a valid address to ask addr2line about (namely, ","). This causes addr2line to first + * write out the answer to our request, in an unbounded/unknown number of records, and + * then to write out the lines "??" and "??:0", so that we can detect when it has + * finished giving us anything useful. We have to be careful about the first record, + * though, because it may be genuinely unknown, in which case we'll get two sets of + * "??"/"??:0" lines. + */ + if (fprintf(a2l->to_child, "%016"PRIx64"\n,\n", addr) < 0 || fflush(a2l->to_child) != 0) { + pr_warning("%s %s: could not send request\n", __func__, dso_name); + goto out; + } + + switch (read_addr2line_record(a2l, &record_function, &record_filename, &record_line_nr)) { + case -1: + pr_warning("%s %s: could not read first record\n", __func__, dso_name); + goto out; + case 0: + /* + * The first record was invalid, so return failure, but first read another + * record, since we asked a junk question and have to clear the answer out. + */ + switch (read_addr2line_record(a2l, NULL, NULL, NULL)) { + case -1: + pr_warning("%s %s: could not read delimiter record\n", __func__, dso_name); + break; + case 0: + /* As expected. */ + break; + default: + pr_warning("%s %s: unexpected record instead of sentinel", + __func__, dso_name); + break; + } + goto out; + default: + break; + } + + if (file) { + *file = strdup(record_filename); + ret = 1; + } + if (line_nr) + *line_nr = record_line_nr; + + if (unwind_inlines) { + if (node && inline_list__append_record(dso, node, sym, + record_function, + record_filename, + record_line_nr)) { + ret = 0; + goto out; + } + } + + /* We have to read the records even if we don't care about the inline info. */ + while ((record_status = read_addr2line_record(a2l, + &record_function, + &record_filename, + &record_line_nr)) == 1) { + if (unwind_inlines && node && inline_count++ < MAX_INLINE_NEST) { + if (inline_list__append_record(dso, node, sym, + record_function, + record_filename, + record_line_nr)) { + ret = 0; + goto out; + } + ret = 1; /* found at least one inline frame */ + } + } + +out: + free(record_function); + free(record_filename); + return ret; +} + +void dso__free_a2l(struct dso *dso) +{ + struct a2l_subprocess *a2l = dso->a2l; + + if (!a2l) + return; + + addr2line_subprocess_cleanup(a2l); + + dso->a2l = NULL; +} + +#endif /* HAVE_LIBBFD_SUPPORT */ + +static struct inline_node *addr2inlines(const char *dso_name, u64 addr, + struct dso *dso, struct symbol *sym) +{ + struct inline_node *node; + node = zalloc(sizeof(*node)); if (node == NULL) { perror("not enough memory for the inline node"); - goto out; + return NULL; } INIT_LIST_HEAD(&node->val); node->addr = addr; - /* addr2line -f generates two lines for each inlined functions */ - while (getline(&funcname, &funclen, fp) != -1) { - char *srcline; - struct symbol *inline_sym; - - strim(funcname); - - if (getline(&filename, &filelen, fp) == -1) - goto out; - - if (filename_split(filename, &line_nr) != 1) - goto out; - - srcline = srcline_from_fileline(filename, line_nr); - inline_sym = new_inline_sym(dso, sym, funcname); - - if (inline_list__append(inline_sym, srcline, node) != 0) { - free(srcline); - if (inline_sym && inline_sym->inlined) - symbol__delete(inline_sym); - goto out; - } - } - -out: - pclose(fp); - free(filename); - free(funcname); - + addr2line(dso_name, addr, NULL, NULL, dso, true, node, sym); return node; } -#endif /* HAVE_LIBBFD_SUPPORT */ - /* * Number of addr2line failures (without success) before disabling it for that * dso. From 669b2e4aa1a869def4dc207ea084fdd77366d646 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Mon, 23 Aug 2021 17:45:03 +0300 Subject: [PATCH 159/587] i2c: mlxcpld: Reduce polling time for performance improvement Decrease polling time 'MLXCPLD_I2C_POLL_TIME' from 400 usec to 200 usec. It improves performance of I2C transactions. Reliability of setting polling time to 200 usec has been validated across all the supported systems. Signed-off-by: Vadim Pasternak Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-mlxcpld.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-mlxcpld.c b/drivers/i2c/busses/i2c-mlxcpld.c index 4e0b7c2882ce..520db32ad467 100644 --- a/drivers/i2c/busses/i2c-mlxcpld.c +++ b/drivers/i2c/busses/i2c-mlxcpld.c @@ -27,7 +27,7 @@ #define MLXCPLD_I2C_MAX_ADDR_LEN 4 #define MLXCPLD_I2C_RETR_NUM 2 #define MLXCPLD_I2C_XFER_TO 500000 /* usec */ -#define MLXCPLD_I2C_POLL_TIME 400 /* usec */ +#define MLXCPLD_I2C_POLL_TIME 200 /* usec */ /* LPC I2C registers */ #define MLXCPLD_LPCI2C_CPBLTY_REG 0x0 From 65315ec52c9bd518e22fde1c9ce1e787b9122b4a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Krzysztof=20Wilczy=C5=84ski?= Date: Sun, 3 Oct 2021 02:54:39 +0000 Subject: [PATCH 160/587] PCI: imx6: Remove unused assignment to variable ret MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Previously, the maximum link speed was set following an "fsl,max-link-speed" property read, and should the read failed, then the PCIe generation was manually set to PCIe Gen1 and thus limiting the link speed to 2.5 GT/s. Code refactoring completed in the commit 39bc5006501c ("PCI: dwc: Centralize link gen setting") changed to the logic that was previously used to limit the maximum link speed leaving behind an unused assignment to a variable "ret". Since the value returned from the of_property_read_u32() and stored in the variable "ret" is never used in any meaningful way, and it's also immediately reassigned in the code that follows, the assignment can be removed. Link: https://lore.kernel.org/r/20211003025439.84783-1-kw@linux.com Signed-off-by: Krzysztof Wilczyński Signed-off-by: Lorenzo Pieralisi --- drivers/pci/controller/dwc/pci-imx6.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c index 80fc98acf097..26f49f797b0f 100644 --- a/drivers/pci/controller/dwc/pci-imx6.c +++ b/drivers/pci/controller/dwc/pci-imx6.c @@ -1132,7 +1132,7 @@ static int imx6_pcie_probe(struct platform_device *pdev) /* Limit link speed */ pci->link_gen = 1; - ret = of_property_read_u32(node, "fsl,max-link-speed", &pci->link_gen); + of_property_read_u32(node, "fsl,max-link-speed", &pci->link_gen); imx6_pcie->vpcie = devm_regulator_get_optional(&pdev->dev, "vpcie"); if (IS_ERR(imx6_pcie->vpcie)) { From 3f491d11d8cbc3e4b4ff67bfc7f065e1cb56bcef Mon Sep 17 00:00:00 2001 From: Pratyush Yadav Date: Fri, 24 Sep 2021 00:40:26 +0530 Subject: [PATCH 161/587] MAINTAINERS: Add spi-nor device tree binding under SPI NOR maintainers The binding is for the SPI NOR subsystem so the patches should be sent to its maintainers. Currently the patches get sent to Rob Herring and MTD maintainers who might not always have the full picture. Signed-off-by: Pratyush Yadav Signed-off-by: Tudor Ambarus Link: https://lore.kernel.org/r/20210923191026.19184-1-p.yadav@ti.com --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index abdcbcfef73d..3913d1114324 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17652,6 +17652,7 @@ W: http://www.linux-mtd.infradead.org/ Q: http://patchwork.ozlabs.org/project/linux-mtd/list/ C: irc://irc.oftc.net/mtd T: git git://git.kernel.org/pub/scm/linux/kernel/git/mtd/linux.git spi-nor/next +F: Documentation/devicetree/bindings/mtd/jedec,spi-nor.yaml F: drivers/mtd/spi-nor/ F: include/linux/mtd/spi-nor.h From 460275f124fb072dca218a6b43b6370eebbab20d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Tue, 5 Oct 2021 20:09:40 +0200 Subject: [PATCH 162/587] PCI: Add PCI_EXP_DEVCTL_PAYLOAD_* macros MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Define a macro PCI_EXP_DEVCTL_PAYLOAD_* for every possible Max Payload Size in linux/pci_regs.h, in the same style as PCI_EXP_DEVCTL_READRQ_*. Link: https://lore.kernel.org/r/20211005180952.6812-2-kabel@kernel.org Signed-off-by: Pali Rohár Signed-off-by: Marek Behún Signed-off-by: Lorenzo Pieralisi Reviewed-by: Marek Behún Reviewed-by: Bjorn Helgaas --- include/uapi/linux/pci_regs.h | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index e709ae8235e7..ff6ccbc6efe9 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -504,6 +504,12 @@ #define PCI_EXP_DEVCTL_URRE 0x0008 /* Unsupported Request Reporting En. */ #define PCI_EXP_DEVCTL_RELAX_EN 0x0010 /* Enable relaxed ordering */ #define PCI_EXP_DEVCTL_PAYLOAD 0x00e0 /* Max_Payload_Size */ +#define PCI_EXP_DEVCTL_PAYLOAD_128B 0x0000 /* 128 Bytes */ +#define PCI_EXP_DEVCTL_PAYLOAD_256B 0x0020 /* 256 Bytes */ +#define PCI_EXP_DEVCTL_PAYLOAD_512B 0x0040 /* 512 Bytes */ +#define PCI_EXP_DEVCTL_PAYLOAD_1024B 0x0060 /* 1024 Bytes */ +#define PCI_EXP_DEVCTL_PAYLOAD_2048B 0x0080 /* 2048 Bytes */ +#define PCI_EXP_DEVCTL_PAYLOAD_4096B 0x00a0 /* 4096 Bytes */ #define PCI_EXP_DEVCTL_EXT_TAG 0x0100 /* Extended Tag Field Enable */ #define PCI_EXP_DEVCTL_PHANTOM 0x0200 /* Phantom Functions Enable */ #define PCI_EXP_DEVCTL_AUX_PME 0x0400 /* Auxiliary Power PM Enable */ From a4e17d65dafdd3513042d8f00404c9b6068a825c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Tue, 5 Oct 2021 20:09:41 +0200 Subject: [PATCH 163/587] PCI: aardvark: Fix PCIe Max Payload Size setting MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Change PCIe Max Payload Size setting in PCIe Device Control register to 512 bytes to align with PCIe Link Initialization sequence as defined in Marvell Armada 3700 Functional Specification. According to the specification, maximal Max Payload Size supported by this device is 512 bytes. Without this kernel prints suspicious line: pci 0000:01:00.0: Upstream bridge's Max Payload Size set to 256 (was 16384, max 512) With this change it changes to: pci 0000:01:00.0: Upstream bridge's Max Payload Size set to 256 (was 512, max 512) Link: https://lore.kernel.org/r/20211005180952.6812-3-kabel@kernel.org Fixes: 8c39d710363c ("PCI: aardvark: Add Aardvark PCI host controller driver") Signed-off-by: Pali Rohár Signed-off-by: Marek Behún Signed-off-by: Lorenzo Pieralisi Reviewed-by: Marek Behún Cc: stable@vger.kernel.org --- drivers/pci/controller/pci-aardvark.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index 596ebcfcc82d..884510630bae 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -488,8 +488,9 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie) reg = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_DEVCTL); reg &= ~PCI_EXP_DEVCTL_RELAX_EN; reg &= ~PCI_EXP_DEVCTL_NOSNOOP_EN; + reg &= ~PCI_EXP_DEVCTL_PAYLOAD; reg &= ~PCI_EXP_DEVCTL_READRQ; - reg |= PCI_EXP_DEVCTL_PAYLOAD; /* Set max payload size */ + reg |= PCI_EXP_DEVCTL_PAYLOAD_512B; reg |= PCI_EXP_DEVCTL_READRQ_512B; advk_writel(pcie, reg, PCIE_CORE_PCIEXP_CAP + PCI_EXP_DEVCTL); From 464de7e7fff767e87429cd7be09c4f2cb50a6ccb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Tue, 5 Oct 2021 20:09:42 +0200 Subject: [PATCH 164/587] PCI: aardvark: Don't spam about PIO Response Status MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use dev_dbg() instead of dev_err() in advk_pcie_check_pio_status(). For example CRS is not an error status, it just says that the request should be retried. Link: https://lore.kernel.org/r/20211005180952.6812-4-kabel@kernel.org Fixes: 8c39d710363c1 ("PCI: aardvark: Add Aardvark PCI host controller driver") Signed-off-by: Marek Behún Signed-off-by: Lorenzo Pieralisi --- drivers/pci/controller/pci-aardvark.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index 884510630bae..a7903c531aa3 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -683,7 +683,7 @@ static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_crs, u3 else str_posted = "Posted"; - dev_err(dev, "%s PIO Response Status: %s, %#x @ %#x\n", + dev_dbg(dev, "%s PIO Response Status: %s, %#x @ %#x\n", str_posted, strcomp_status, reg, advk_readl(pcie, PIO_ADDR_LS)); return -EFAULT; From d419052bc6c60fa4ab2b5a51d5f1e55a66e2b4ff Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Tue, 5 Oct 2021 20:09:43 +0200 Subject: [PATCH 165/587] PCI: aardvark: Fix preserving PCI_EXP_RTCTL_CRSSVE flag on emulated bridge MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 43f5c77bcbd2 ("PCI: aardvark: Fix reporting CRS value") started using CRSSVE flag for handling CRS responses. PCI_EXP_RTCTL_CRSSVE flag is stored only in emulated config space buffer and there is handler for PCI_EXP_RTCTL register. So every read operation from config space automatically clears CRSSVE flag as it is not defined in PCI_EXP_RTCTL read handler. Fix this by reading current CRSSVE bit flag from emulated space buffer and appending it to PCI_EXP_RTCTL read response. Link: https://lore.kernel.org/r/20211005180952.6812-5-kabel@kernel.org Fixes: 43f5c77bcbd2 ("PCI: aardvark: Fix reporting CRS value") Signed-off-by: Pali Rohár Signed-off-by: Marek Behún Signed-off-by: Lorenzo Pieralisi Reviewed-by: Marek Behún --- drivers/pci/controller/pci-aardvark.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index a7903c531aa3..bb57ca6aed35 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -724,6 +724,7 @@ advk_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge, case PCI_EXP_RTCTL: { u32 val = advk_readl(pcie, PCIE_ISR0_MASK_REG); *value = (val & PCIE_MSG_PM_PME_MASK) ? 0 : PCI_EXP_RTCTL_PMEIE; + *value |= le16_to_cpu(bridge->pcie_conf.rootctl) & PCI_EXP_RTCTL_CRSSVE; *value |= PCI_EXP_RTCAP_CRSVIS << 16; return PCI_BRIDGE_EMUL_HANDLED; } From 46ef6090dbf590711cb12680b6eafde5fa21fe87 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Tue, 5 Oct 2021 20:09:44 +0200 Subject: [PATCH 166/587] PCI: aardvark: Fix configuring Reference clock MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 366697018c9a ("PCI: aardvark: Add PHY support") introduced configuration of PCIe Reference clock via PCIE_CORE_REF_CLK_REG register, but did it incorrectly. PCIe Reference clock differential pair is routed from system board to endpoint card, so on CPU side it has output direction. Therefore it is required to enable transmitting and disable receiving. Default configuration according to Armada 3700 Functional Specifications is enabled receiver part and disabled transmitter. We need this change because otherwise PCIe Reference clock is configured to some undefined state when differential pair is used for both transmitting and receiving. Fix this by disabling receiver part. Link: https://lore.kernel.org/r/20211005180952.6812-6-kabel@kernel.org Fixes: 366697018c9a ("PCI: aardvark: Add PHY support") Signed-off-by: Pali Rohár Signed-off-by: Marek Behún Signed-off-by: Lorenzo Pieralisi Reviewed-by: Marek Behún Cc: stable@vger.kernel.org --- drivers/pci/controller/pci-aardvark.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index bb57ca6aed35..d5d6f92e5143 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -99,6 +99,7 @@ #define PCIE_CORE_CTRL2_MSI_ENABLE BIT(10) #define PCIE_CORE_REF_CLK_REG (CONTROL_BASE_ADDR + 0x14) #define PCIE_CORE_REF_CLK_TX_ENABLE BIT(1) +#define PCIE_CORE_REF_CLK_RX_ENABLE BIT(2) #define PCIE_MSG_LOG_REG (CONTROL_BASE_ADDR + 0x30) #define PCIE_ISR0_REG (CONTROL_BASE_ADDR + 0x40) #define PCIE_MSG_PM_PME_MASK BIT(7) @@ -451,9 +452,15 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie) u32 reg; int i; - /* Enable TX */ + /* + * Configure PCIe Reference clock. Direction is from the PCIe + * controller to the endpoint card, so enable transmitting of + * Reference clock differential signal off-chip and disable + * receiving off-chip differential signal. + */ reg = advk_readl(pcie, PCIE_CORE_REF_CLK_REG); reg |= PCIE_CORE_REF_CLK_TX_ENABLE; + reg &= ~PCIE_CORE_REF_CLK_RX_ENABLE; advk_writel(pcie, reg, PCIE_CORE_REF_CLK_REG); /* Set to Direct mode */ From a7ca6d7fa3c02c032db5440ff392d96c04684c21 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Tue, 5 Oct 2021 20:09:45 +0200 Subject: [PATCH 167/587] PCI: aardvark: Do not clear status bits of masked interrupts MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The PCIE_ISR1_REG says which interrupts are currently set / active, including those which are masked. The driver currently reads this register and looks if some unmasked interrupts are active, and if not, it clears status bits of _all_ interrupts, including the masked ones. This is incorrect, since, for example, some drivers may poll these bits. Remove this clearing, and also remove this early return statement completely, since it does not change functionality in any way. Link: https://lore.kernel.org/r/20211005180952.6812-7-kabel@kernel.org Fixes: 8c39d710363c ("PCI: aardvark: Add Aardvark PCI host controller driver") Signed-off-by: Pali Rohár Signed-off-by: Marek Behún Signed-off-by: Lorenzo Pieralisi Reviewed-by: Marek Behún Cc: stable@vger.kernel.org --- drivers/pci/controller/pci-aardvark.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index d5d6f92e5143..f7eebf453e83 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -1295,12 +1295,6 @@ static void advk_pcie_handle_int(struct advk_pcie *pcie) isr1_mask = advk_readl(pcie, PCIE_ISR1_MASK_REG); isr1_status = isr1_val & ((~isr1_mask) & PCIE_ISR1_ALL_MASK); - if (!isr0_status && !isr1_status) { - advk_writel(pcie, isr0_val, PCIE_ISR0_REG); - advk_writel(pcie, isr1_val, PCIE_ISR1_REG); - return; - } - /* Process MSI interrupts */ if (isr0_status & PCIE_ISR0_MSI_INT_PENDING) advk_pcie_handle_msi(pcie); From 1fb95d7d3c7a926b002fe8a6bd27a1cb428b46dc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Tue, 5 Oct 2021 20:09:46 +0200 Subject: [PATCH 168/587] PCI: aardvark: Do not unmask unused interrupts MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are lot of undocumented interrupt bits. To prevent unwanted spurious interrupts, fix all *_ALL_MASK macros to define all interrupt bits, so that driver can properly mask all interrupts, including those which are undocumented. Link: https://lore.kernel.org/r/20211005180952.6812-8-kabel@kernel.org Fixes: 8c39d710363c ("PCI: aardvark: Add Aardvark PCI host controller driver") Signed-off-by: Pali Rohár Signed-off-by: Marek Behún Signed-off-by: Lorenzo Pieralisi Reviewed-by: Marek Behún Cc: stable@vger.kernel.org --- drivers/pci/controller/pci-aardvark.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index f7eebf453e83..3448a8c446d4 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -107,13 +107,13 @@ #define PCIE_ISR0_MSI_INT_PENDING BIT(24) #define PCIE_ISR0_INTX_ASSERT(val) BIT(16 + (val)) #define PCIE_ISR0_INTX_DEASSERT(val) BIT(20 + (val)) -#define PCIE_ISR0_ALL_MASK GENMASK(26, 0) +#define PCIE_ISR0_ALL_MASK GENMASK(31, 0) #define PCIE_ISR1_REG (CONTROL_BASE_ADDR + 0x48) #define PCIE_ISR1_MASK_REG (CONTROL_BASE_ADDR + 0x4C) #define PCIE_ISR1_POWER_STATE_CHANGE BIT(4) #define PCIE_ISR1_FLUSH BIT(5) #define PCIE_ISR1_INTX_ASSERT(val) BIT(8 + (val)) -#define PCIE_ISR1_ALL_MASK GENMASK(11, 4) +#define PCIE_ISR1_ALL_MASK GENMASK(31, 0) #define PCIE_MSI_ADDR_LOW_REG (CONTROL_BASE_ADDR + 0x50) #define PCIE_MSI_ADDR_HIGH_REG (CONTROL_BASE_ADDR + 0x54) #define PCIE_MSI_STATUS_REG (CONTROL_BASE_ADDR + 0x58) @@ -199,7 +199,7 @@ #define PCIE_IRQ_MSI_INT2_DET BIT(21) #define PCIE_IRQ_RC_DBELL_DET BIT(22) #define PCIE_IRQ_EP_STATUS BIT(23) -#define PCIE_IRQ_ALL_MASK 0xfff0fb +#define PCIE_IRQ_ALL_MASK GENMASK(31, 0) #define PCIE_IRQ_ENABLE_INTS_MASK PCIE_IRQ_CORE_INT /* Transaction types */ From 67cb2a4c93499c2c22704998fd1fd2bc35194d8e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Tue, 5 Oct 2021 20:09:47 +0200 Subject: [PATCH 169/587] PCI: aardvark: Deduplicate code in advk_pcie_rd_conf() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Avoid code repetition in advk_pcie_rd_conf() by handling errors with goto jump, as is customary in kernel. Link: https://lore.kernel.org/r/20211005180952.6812-9-kabel@kernel.org Fixes: 43f5c77bcbd2 ("PCI: aardvark: Fix reporting CRS value") Signed-off-by: Marek Behún Signed-off-by: Lorenzo Pieralisi --- drivers/pci/controller/pci-aardvark.c | 48 +++++++++++---------------- 1 file changed, 20 insertions(+), 28 deletions(-) diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index 3448a8c446d4..cd5be284789e 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -920,18 +920,8 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn, (le16_to_cpu(pcie->bridge.pcie_conf.rootctl) & PCI_EXP_RTCTL_CRSSVE); - if (advk_pcie_pio_is_running(pcie)) { - /* - * If it is possible return Completion Retry Status so caller - * tries to issue the request again instead of failing. - */ - if (allow_crs) { - *val = CFG_RD_CRS_VAL; - return PCIBIOS_SUCCESSFUL; - } - *val = 0xffffffff; - return PCIBIOS_SET_FAILED; - } + if (advk_pcie_pio_is_running(pcie)) + goto try_crs; /* Program the control register */ reg = advk_readl(pcie, PIO_CTRL); @@ -955,25 +945,13 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn, advk_writel(pcie, 1, PIO_START); ret = advk_pcie_wait_pio(pcie); - if (ret < 0) { - /* - * If it is possible return Completion Retry Status so caller - * tries to issue the request again instead of failing. - */ - if (allow_crs) { - *val = CFG_RD_CRS_VAL; - return PCIBIOS_SUCCESSFUL; - } - *val = 0xffffffff; - return PCIBIOS_SET_FAILED; - } + if (ret < 0) + goto try_crs; /* Check PIO status and get the read result */ ret = advk_pcie_check_pio_status(pcie, allow_crs, val); - if (ret < 0) { - *val = 0xffffffff; - return PCIBIOS_SET_FAILED; - } + if (ret < 0) + goto fail; if (size == 1) *val = (*val >> (8 * (where & 3))) & 0xff; @@ -981,6 +959,20 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn, *val = (*val >> (8 * (where & 3))) & 0xffff; return PCIBIOS_SUCCESSFUL; + +try_crs: + /* + * If it is possible, return Completion Retry Status so that caller + * tries to issue the request again instead of failing. + */ + if (allow_crs) { + *val = CFG_RD_CRS_VAL; + return PCIBIOS_SUCCESSFUL; + } + +fail: + *val = 0xffffffff; + return PCIBIOS_SET_FAILED; } static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn, From 223dec14a05337a4155f1deed46d2becce4d00fd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Tue, 5 Oct 2021 20:09:48 +0200 Subject: [PATCH 170/587] PCI: aardvark: Implement re-issuing config requests on CRS response MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 43f5c77bcbd2 ("PCI: aardvark: Fix reporting CRS value") fixed handling of CRS response and when CRSSVE flag was not enabled it marked CRS response as failed transaction (due to simplicity). But pci-aardvark.c driver is already waiting up to the PIO_RETRY_CNT count for PIO config response and so we can with a small change implement re-issuing of config requests as described in PCIe base specification. This change implements re-issuing of config requests when response is CRS. Set upper bound of wait cycles to around PIO_RETRY_CNT, afterwards the transaction is marked as failed and an all-ones value is returned as before. We do this by returning appropriate error codes from function advk_pcie_check_pio_status(). On CRS we return -EAGAIN and caller then reissues transaction. Link: https://lore.kernel.org/r/20211005180952.6812-10-kabel@kernel.org Signed-off-by: Pali Rohár Signed-off-by: Marek Behún Signed-off-by: Lorenzo Pieralisi Reviewed-by: Marek Behún --- drivers/pci/controller/pci-aardvark.c | 67 +++++++++++++++++---------- 1 file changed, 43 insertions(+), 24 deletions(-) diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index cd5be284789e..efe8b5f7bf8c 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -603,6 +603,7 @@ static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_crs, u3 u32 reg; unsigned int status; char *strcomp_status, *str_posted; + int ret; reg = advk_readl(pcie, PIO_STAT); status = (reg & PIO_COMPLETION_STATUS_MASK) >> @@ -627,6 +628,7 @@ static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_crs, u3 case PIO_COMPLETION_STATUS_OK: if (reg & PIO_ERR_STATUS) { strcomp_status = "COMP_ERR"; + ret = -EFAULT; break; } /* Get the read result */ @@ -634,9 +636,11 @@ static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_crs, u3 *val = advk_readl(pcie, PIO_RD_DATA); /* No error */ strcomp_status = NULL; + ret = 0; break; case PIO_COMPLETION_STATUS_UR: strcomp_status = "UR"; + ret = -EOPNOTSUPP; break; case PIO_COMPLETION_STATUS_CRS: if (allow_crs && val) { @@ -654,6 +658,7 @@ static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_crs, u3 */ *val = CFG_RD_CRS_VAL; strcomp_status = NULL; + ret = 0; break; } /* PCIe r4.0, sec 2.3.2, says: @@ -669,21 +674,24 @@ static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_crs, u3 * Request and taking appropriate action, e.g., complete the * Request to the host as a failed transaction. * - * To simplify implementation do not re-issue the Configuration - * Request and complete the Request as a failed transaction. + * So return -EAGAIN and caller (pci-aardvark.c driver) will + * re-issue request again up to the PIO_RETRY_CNT retries. */ strcomp_status = "CRS"; + ret = -EAGAIN; break; case PIO_COMPLETION_STATUS_CA: strcomp_status = "CA"; + ret = -ECANCELED; break; default: strcomp_status = "Unknown"; + ret = -EINVAL; break; } if (!strcomp_status) - return 0; + return ret; if (reg & PIO_NON_POSTED_REQ) str_posted = "Non-posted"; @@ -693,7 +701,7 @@ static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_crs, u3 dev_dbg(dev, "%s PIO Response Status: %s, %#x @ %#x\n", str_posted, strcomp_status, reg, advk_readl(pcie, PIO_ADDR_LS)); - return -EFAULT; + return ret; } static int advk_pcie_wait_pio(struct advk_pcie *pcie) @@ -701,13 +709,13 @@ static int advk_pcie_wait_pio(struct advk_pcie *pcie) struct device *dev = &pcie->pdev->dev; int i; - for (i = 0; i < PIO_RETRY_CNT; i++) { + for (i = 1; i <= PIO_RETRY_CNT; i++) { u32 start, isr; start = advk_readl(pcie, PIO_START); isr = advk_readl(pcie, PIO_ISR); if (!start && isr) - return 0; + return i; udelay(PIO_RETRY_DELAY); } @@ -898,6 +906,7 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn, int where, int size, u32 *val) { struct advk_pcie *pcie = bus->sysdata; + int retry_count; bool allow_crs; u32 reg; int ret; @@ -940,16 +949,22 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn, /* Program the data strobe */ advk_writel(pcie, 0xf, PIO_WR_DATA_STRB); - /* Clear PIO DONE ISR and start the transfer */ - advk_writel(pcie, 1, PIO_ISR); - advk_writel(pcie, 1, PIO_START); + retry_count = 0; + do { + /* Clear PIO DONE ISR and start the transfer */ + advk_writel(pcie, 1, PIO_ISR); + advk_writel(pcie, 1, PIO_START); - ret = advk_pcie_wait_pio(pcie); - if (ret < 0) - goto try_crs; + ret = advk_pcie_wait_pio(pcie); + if (ret < 0) + goto try_crs; + + retry_count += ret; + + /* Check PIO status and get the read result */ + ret = advk_pcie_check_pio_status(pcie, allow_crs, val); + } while (ret == -EAGAIN && retry_count < PIO_RETRY_CNT); - /* Check PIO status and get the read result */ - ret = advk_pcie_check_pio_status(pcie, allow_crs, val); if (ret < 0) goto fail; @@ -981,6 +996,7 @@ static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn, struct advk_pcie *pcie = bus->sysdata; u32 reg; u32 data_strobe = 0x0; + int retry_count; int offset; int ret; @@ -1022,19 +1038,22 @@ static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn, /* Program the data strobe */ advk_writel(pcie, data_strobe, PIO_WR_DATA_STRB); - /* Clear PIO DONE ISR and start the transfer */ - advk_writel(pcie, 1, PIO_ISR); - advk_writel(pcie, 1, PIO_START); + retry_count = 0; + do { + /* Clear PIO DONE ISR and start the transfer */ + advk_writel(pcie, 1, PIO_ISR); + advk_writel(pcie, 1, PIO_START); - ret = advk_pcie_wait_pio(pcie); - if (ret < 0) - return PCIBIOS_SET_FAILED; + ret = advk_pcie_wait_pio(pcie); + if (ret < 0) + return PCIBIOS_SET_FAILED; - ret = advk_pcie_check_pio_status(pcie, false, NULL); - if (ret < 0) - return PCIBIOS_SET_FAILED; + retry_count += ret; - return PCIBIOS_SUCCESSFUL; + ret = advk_pcie_check_pio_status(pcie, false, NULL); + } while (ret == -EAGAIN && retry_count < PIO_RETRY_CNT); + + return ret < 0 ? PCIBIOS_SET_FAILED : PCIBIOS_SUCCESSFUL; } static struct pci_ops advk_pcie_ops = { From 454c53271fc11f3aa5e44e41fd99ca181bd32c62 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Tue, 5 Oct 2021 20:09:49 +0200 Subject: [PATCH 171/587] PCI: aardvark: Simplify initialization of rootcap on virtual bridge MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit PCIe config space can be initialized also before pci_bridge_emul_init() call, so move rootcap initialization after PCI config space initialization. This simplifies the function a little since it removes one if (ret < 0) check. Link: https://lore.kernel.org/r/20211005180952.6812-11-kabel@kernel.org Signed-off-by: Pali Rohár Signed-off-by: Marek Behún Signed-off-by: Lorenzo Pieralisi Reviewed-by: Marek Behún --- drivers/pci/controller/pci-aardvark.c | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index efe8b5f7bf8c..9c509d5a9afa 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -822,7 +822,6 @@ static struct pci_bridge_emul_ops advk_pci_bridge_emul_ops = { static int advk_sw_pci_bridge_init(struct advk_pcie *pcie) { struct pci_bridge_emul *bridge = &pcie->bridge; - int ret; bridge->conf.vendor = cpu_to_le16(advk_readl(pcie, PCIE_CORE_DEV_ID_REG) & 0xffff); @@ -842,19 +841,14 @@ static int advk_sw_pci_bridge_init(struct advk_pcie *pcie) /* Support interrupt A for MSI feature */ bridge->conf.intpin = PCIE_CORE_INT_A_ASSERT_ENABLE; + /* Indicates supports for Completion Retry Status */ + bridge->pcie_conf.rootcap = cpu_to_le16(PCI_EXP_RTCAP_CRSVIS); + bridge->has_pcie = true; bridge->data = pcie; bridge->ops = &advk_pci_bridge_emul_ops; - /* PCIe config space can be initialized after pci_bridge_emul_init() */ - ret = pci_bridge_emul_init(bridge, 0); - if (ret < 0) - return ret; - - /* Indicates supports for Completion Retry Status */ - bridge->pcie_conf.rootcap = cpu_to_le16(PCI_EXP_RTCAP_CRSVIS); - - return 0; + return pci_bridge_emul_init(bridge, 0); } static bool advk_pcie_valid_device(struct advk_pcie *pcie, struct pci_bus *bus, From f76b36d40beee0a13aa8f6aa011df0d7cbbb8a7f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Tue, 5 Oct 2021 20:09:50 +0200 Subject: [PATCH 172/587] PCI: aardvark: Fix link training MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix multiple link training issues in aardvark driver. The main reason of these issues was misunderstanding of what certain registers do, since their names and comments were misleading: before commit 96be36dbffac ("PCI: aardvark: Replace custom macros by standard linux/pci_regs.h macros"), the pci-aardvark.c driver used custom macros for accessing standard PCIe Root Bridge registers, and misleading comments did not help to understand what the code was really doing. After doing more tests and experiments I've come to the conclusion that the SPEED_GEN register in aardvark sets the PCIe revision / generation compliance and forces maximal link speed. Both GEN3 and GEN2 values set the read-only PCI_EXP_FLAGS_VERS bits (PCIe capabilities version of Root Bridge) to value 2, while GEN1 value sets PCI_EXP_FLAGS_VERS to 1, which matches with PCI Express specifications revisions 3, 2 and 1 respectively. Changing SPEED_GEN also sets the read-only bits PCI_EXP_LNKCAP_SLS and PCI_EXP_LNKCAP2_SLS to corresponding speed. (Note that PCI Express rev 1 specification does not define PCI_EXP_LNKCAP2 and PCI_EXP_LNKCTL2 registers and when SPEED_GEN is set to GEN1 (which also sets PCI_EXP_FLAGS_VERS set to 1), lspci cannot access PCI_EXP_LNKCAP2 and PCI_EXP_LNKCTL2 registers.) Changing PCIe link speed can be done via PCI_EXP_LNKCTL2_TLS bits of PCI_EXP_LNKCTL2 register. Armada 3700 Functional Specifications says that the default value of PCI_EXP_LNKCTL2_TLS is based on SPEED_GEN value, but tests showed that the default value is always 8.0 GT/s, independently of speed set by SPEED_GEN. So after setting SPEED_GEN, we must also set value in PCI_EXP_LNKCTL2 register via PCI_EXP_LNKCTL2_TLS bits. Triggering PCI_EXP_LNKCTL_RL bit immediately after setting LINK_TRAINING_EN bit actually doesn't do anything. Tests have shown that a delay is needed after enabling LINK_TRAINING_EN bit. As triggering PCI_EXP_LNKCTL_RL currently does nothing, remove it. Commit 43fc679ced18 ("PCI: aardvark: Improve link training") introduced code which sets SPEED_GEN register based on negotiated link speed from PCI_EXP_LNKSTA_CLS bits of PCI_EXP_LNKSTA register. This code was added to fix detection of Compex WLE900VX (Atheros QCA9880) WiFi GEN1 PCIe cards, as otherwise these cards were "invisible" on PCIe bus (probably because they crashed). But apparently more people reported the same issues with these cards also with other PCIe controllers [1] and I was able to reproduce this issue also with other "noname" WiFi cards based on Atheros QCA9890 chip (with the same PCI vendor/device ids as Atheros QCA9880). So this is not an issue in aardvark but rather an issue in Atheros QCA98xx chips. Also, this issue only exists if the kernel is compiled with PCIe ASPM support, and a generic workaround for this is to change PCIe Bridge to 2.5 GT/s link speed via PCI_EXP_LNKCTL2_TLS_2_5GT bits in PCI_EXP_LNKCTL2 register [2], before triggering PCI_EXP_LNKCTL_RL bit. This workaround also works when SPEED_GEN is set to value GEN2 (5 GT/s). So remove this hack completely in the aardvark driver and always set SPEED_GEN to value from 'max-link-speed' DT property. Fix for Atheros QCA98xx chips is handled separately by patch [2]. These two things (code for triggering PCI_EXP_LNKCTL_RL bit and changing SPEED_GEN value) also explain why commit 6964494582f5 ("PCI: aardvark: Train link immediately after enabling training") somehow fixed detection of those problematic Compex cards with Atheros chips: if triggering link retraining (via PCI_EXP_LNKCTL_RL bit) was done immediately after enabling link training (via LINK_TRAINING_EN), it did nothing. If there was a specific delay, aardvark HW already initialized PCIe link and therefore triggering link retraining caused the above issue. Compex cards triggered link down event and disappeared from the PCIe bus. Commit f4c7d053d7f7 ("PCI: aardvark: Wait for endpoint to be ready before training link") added 100ms sleep before calling 'Start link training' command and explained that it is a requirement of PCI Express specification. But the code after this 100ms sleep was not doing 'Start link training', rather it triggered PCI_EXP_LNKCTL_RL bit via PCIe Root Bridge to put link into Recovery state. The required delay after fundamental reset is already done in function advk_pcie_wait_for_link() which also checks whether PCIe link is up. So after removing the code which triggers PCI_EXP_LNKCTL_RL bit on PCIe Root Bridge, there is no need to wait 100ms again. Remove the extra msleep() call and update comment about the delay required by the PCI Express specification. According to Marvell Armada 3700 Functional Specifications, Link training should be enabled via aardvark register LINK_TRAINING_EN after selecting PCIe generation and x1 lane. There is no need to disable it prior resetting card via PERST# signal. This disabling code was introduced in commit 5169a9851daa ("PCI: aardvark: Issue PERST via GPIO") as a workaround for some Atheros cards. It turns out that this also is Atheros specific issue and affects any PCIe controller, not only aardvark. Moreover this Atheros issue was triggered by juggling with PCI_EXP_LNKCTL_RL, LINK_TRAINING_EN and SPEED_GEN bits interleaved with sleeps. Now, after removing triggering PCI_EXP_LNKCTL_RL, there is no need to explicitly disable LINK_TRAINING_EN bit. So remove this code too. The problematic Compex cards described in previous git commits are correctly detected in advk_pcie_train_link() function even after applying all these changes. Note that with this patch, and also prior this patch, some NVMe disks which support PCIe GEN3 with 8 GT/s speed are negotiated only at the lowest link speed 2.5 GT/s, independently of SPEED_GEN value. After manually triggering PCI_EXP_LNKCTL_RL bit (e.g. from userspace via setpci), these NVMe disks change link speed to 5 GT/s when SPEED_GEN was configured to GEN2. This issue first needs to be properly investigated. I will send a fix in the future. On the other hand, some other GEN2 PCIe cards with 5 GT/s speed are autonomously by HW autonegotiated at full 5 GT/s speed without need of any software interaction. Armada 3700 Functional Specifications describes the following steps for link training: set SPEED_GEN to GEN2, enable LINK_TRAINING_EN, poll until link training is complete, trigger PCI_EXP_LNKCTL_RL, poll until signal rate is 5 GT/s, poll until link training is complete, enable ASPM L0s. The requirement for triggering PCI_EXP_LNKCTL_RL can be explained by the need to achieve 5 GT/s speed (as changing link speed is done by throw to recovery state entered by PCI_EXP_LNKCTL_RL) or maybe as a part of enabling ASPM L0s (but in this case ASPM L0s should have been enabled prior PCI_EXP_LNKCTL_RL). It is unknown why the original pci-aardvark.c driver was triggering PCI_EXP_LNKCTL_RL bit before waiting for the link to be up. This does not align with neither PCIe base specifications nor with Armada 3700 Functional Specification. (Note that in older versions of aardvark, this bit was called incorrectly PCIE_CORE_LINK_TRAINING, so this may be the reason.) It is also unknown why Armada 3700 Functional Specification says that it is needed to trigger PCI_EXP_LNKCTL_RL for GEN2 mode, as according to PCIe base specification 5 GT/s speed negotiation is supposed to be entirely autonomous, even if initial speed is 2.5 GT/s. [1] - https://lore.kernel.org/linux-pci/87h7l8axqp.fsf@toke.dk/ [2] - https://lore.kernel.org/linux-pci/20210326124326.21163-1-pali@kernel.org/ Link: https://lore.kernel.org/r/20211005180952.6812-12-kabel@kernel.org Signed-off-by: Pali Rohár Signed-off-by: Marek Behún Signed-off-by: Lorenzo Pieralisi Reviewed-by: Marek Behún --- drivers/pci/controller/pci-aardvark.c | 117 ++++++++------------------ 1 file changed, 34 insertions(+), 83 deletions(-) diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index 9c509d5a9afa..2c66cdbb8dd6 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -258,11 +258,6 @@ static inline u32 advk_readl(struct advk_pcie *pcie, u64 reg) return readl(pcie->base + reg); } -static inline u16 advk_read16(struct advk_pcie *pcie, u64 reg) -{ - return advk_readl(pcie, (reg & ~0x3)) >> ((reg & 0x3) * 8); -} - static int advk_pcie_link_up(struct advk_pcie *pcie) { u32 val, ltssm_state; @@ -300,23 +295,9 @@ static void advk_pcie_wait_for_retrain(struct advk_pcie *pcie) static void advk_pcie_issue_perst(struct advk_pcie *pcie) { - u32 reg; - if (!pcie->reset_gpio) return; - /* - * As required by PCI Express spec (PCI Express Base Specification, REV. - * 4.0 PCI Express, February 19 2014, 6.6.1 Conventional Reset) a delay - * for at least 100ms after de-asserting PERST# signal is needed before - * link training is enabled. So ensure that link training is disabled - * prior de-asserting PERST# signal to fulfill that PCI Express spec - * requirement. - */ - reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG); - reg &= ~LINK_TRAINING_EN; - advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG); - /* 10ms delay is needed for some cards */ dev_info(&pcie->pdev->dev, "issuing PERST via reset GPIO for 10ms\n"); gpiod_set_value_cansleep(pcie->reset_gpio, 1); @@ -324,53 +305,46 @@ static void advk_pcie_issue_perst(struct advk_pcie *pcie) gpiod_set_value_cansleep(pcie->reset_gpio, 0); } -static int advk_pcie_train_at_gen(struct advk_pcie *pcie, int gen) +static void advk_pcie_train_link(struct advk_pcie *pcie) { - int ret, neg_gen; + struct device *dev = &pcie->pdev->dev; u32 reg; + int ret; - /* Setup link speed */ + /* + * Setup PCIe rev / gen compliance based on device tree property + * 'max-link-speed' which also forces maximal link speed. + */ reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG); reg &= ~PCIE_GEN_SEL_MSK; - if (gen == 3) + if (pcie->link_gen == 3) reg |= SPEED_GEN_3; - else if (gen == 2) + else if (pcie->link_gen == 2) reg |= SPEED_GEN_2; else reg |= SPEED_GEN_1; advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG); /* - * Enable link training. This is not needed in every call to this - * function, just once suffices, but it does not break anything either. + * Set maximal link speed value also into PCIe Link Control 2 register. + * Armada 3700 Functional Specification says that default value is based + * on SPEED_GEN but tests showed that default value is always 8.0 GT/s. */ + reg = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL2); + reg &= ~PCI_EXP_LNKCTL2_TLS; + if (pcie->link_gen == 3) + reg |= PCI_EXP_LNKCTL2_TLS_8_0GT; + else if (pcie->link_gen == 2) + reg |= PCI_EXP_LNKCTL2_TLS_5_0GT; + else + reg |= PCI_EXP_LNKCTL2_TLS_2_5GT; + advk_writel(pcie, reg, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL2); + + /* Enable link training after selecting PCIe generation */ reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG); reg |= LINK_TRAINING_EN; advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG); - /* - * Start link training immediately after enabling it. - * This solves problems for some buggy cards. - */ - reg = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL); - reg |= PCI_EXP_LNKCTL_RL; - advk_writel(pcie, reg, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL); - - ret = advk_pcie_wait_for_link(pcie); - if (ret) - return ret; - - reg = advk_read16(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKSTA); - neg_gen = reg & PCI_EXP_LNKSTA_CLS; - - return neg_gen; -} - -static void advk_pcie_train_link(struct advk_pcie *pcie) -{ - struct device *dev = &pcie->pdev->dev; - int neg_gen = -1, gen; - /* * Reset PCIe card via PERST# signal. Some cards are not detected * during link training when they are in some non-initial state. @@ -381,41 +355,18 @@ static void advk_pcie_train_link(struct advk_pcie *pcie) * PERST# signal could have been asserted by pinctrl subsystem before * probe() callback has been called or issued explicitly by reset gpio * function advk_pcie_issue_perst(), making the endpoint going into - * fundamental reset. As required by PCI Express spec a delay for at - * least 100ms after such a reset before link training is needed. + * fundamental reset. As required by PCI Express spec (PCI Express + * Base Specification, REV. 4.0 PCI Express, February 19 2014, 6.6.1 + * Conventional Reset) a delay for at least 100ms after such a reset + * before sending a Configuration Request to the device is needed. + * So wait until PCIe link is up. Function advk_pcie_wait_for_link() + * waits for link at least 900ms. */ - msleep(PCI_PM_D3COLD_WAIT); - - /* - * Try link training at link gen specified by device tree property - * 'max-link-speed'. If this fails, iteratively train at lower gen. - */ - for (gen = pcie->link_gen; gen > 0; --gen) { - neg_gen = advk_pcie_train_at_gen(pcie, gen); - if (neg_gen > 0) - break; - } - - if (neg_gen < 0) - goto err; - - /* - * After successful training if negotiated gen is lower than requested, - * train again on negotiated gen. This solves some stability issues for - * some buggy gen1 cards. - */ - if (neg_gen < gen) { - gen = neg_gen; - neg_gen = advk_pcie_train_at_gen(pcie, gen); - } - - if (neg_gen == gen) { - dev_info(dev, "link up at gen %i\n", gen); - return; - } - -err: - dev_err(dev, "link never came up\n"); + ret = advk_pcie_wait_for_link(pcie); + if (ret < 0) + dev_err(dev, "link never came up\n"); + else + dev_info(dev, "link up\n"); } /* From 661c399a651c11aaf83c45cbfe0b4a1fb7bc3179 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Tue, 5 Oct 2021 20:09:51 +0200 Subject: [PATCH 173/587] PCI: aardvark: Fix checking for link up via LTSSM state MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Current implementation of advk_pcie_link_up() is wrong as it marks also link disabled or hot reset states as link up. Fix it by marking link up only to those states which are defined in PCIe Base specification 3.0, Table 4-14: Link Status Mapped to the LTSSM. To simplify implementation, Define macros for every LTSSM state which aardvark hardware can return in CFG_REG register. Fix also checking for link training according to the same Table 4-14. Define a new function advk_pcie_link_training() for this purpose. Link: https://lore.kernel.org/r/20211005180952.6812-13-kabel@kernel.org Fixes: 8c39d710363c ("PCI: aardvark: Add Aardvark PCI host controller driver") Signed-off-by: Pali Rohár Signed-off-by: Marek Behún Signed-off-by: Lorenzo Pieralisi Reviewed-by: Marek Behún Cc: stable@vger.kernel.org Cc: Remi Pommarel --- drivers/pci/controller/pci-aardvark.c | 76 ++++++++++++++++++++++++--- 1 file changed, 70 insertions(+), 6 deletions(-) diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index 2c66cdbb8dd6..f831f7d197bd 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -165,8 +165,50 @@ #define CFG_REG (LMI_BASE_ADDR + 0x0) #define LTSSM_SHIFT 24 #define LTSSM_MASK 0x3f -#define LTSSM_L0 0x10 #define RC_BAR_CONFIG 0x300 + +/* LTSSM values in CFG_REG */ +enum { + LTSSM_DETECT_QUIET = 0x0, + LTSSM_DETECT_ACTIVE = 0x1, + LTSSM_POLLING_ACTIVE = 0x2, + LTSSM_POLLING_COMPLIANCE = 0x3, + LTSSM_POLLING_CONFIGURATION = 0x4, + LTSSM_CONFIG_LINKWIDTH_START = 0x5, + LTSSM_CONFIG_LINKWIDTH_ACCEPT = 0x6, + LTSSM_CONFIG_LANENUM_ACCEPT = 0x7, + LTSSM_CONFIG_LANENUM_WAIT = 0x8, + LTSSM_CONFIG_COMPLETE = 0x9, + LTSSM_CONFIG_IDLE = 0xa, + LTSSM_RECOVERY_RCVR_LOCK = 0xb, + LTSSM_RECOVERY_SPEED = 0xc, + LTSSM_RECOVERY_RCVR_CFG = 0xd, + LTSSM_RECOVERY_IDLE = 0xe, + LTSSM_L0 = 0x10, + LTSSM_RX_L0S_ENTRY = 0x11, + LTSSM_RX_L0S_IDLE = 0x12, + LTSSM_RX_L0S_FTS = 0x13, + LTSSM_TX_L0S_ENTRY = 0x14, + LTSSM_TX_L0S_IDLE = 0x15, + LTSSM_TX_L0S_FTS = 0x16, + LTSSM_L1_ENTRY = 0x17, + LTSSM_L1_IDLE = 0x18, + LTSSM_L2_IDLE = 0x19, + LTSSM_L2_TRANSMIT_WAKE = 0x1a, + LTSSM_DISABLED = 0x20, + LTSSM_LOOPBACK_ENTRY_MASTER = 0x21, + LTSSM_LOOPBACK_ACTIVE_MASTER = 0x22, + LTSSM_LOOPBACK_EXIT_MASTER = 0x23, + LTSSM_LOOPBACK_ENTRY_SLAVE = 0x24, + LTSSM_LOOPBACK_ACTIVE_SLAVE = 0x25, + LTSSM_LOOPBACK_EXIT_SLAVE = 0x26, + LTSSM_HOT_RESET = 0x27, + LTSSM_RECOVERY_EQUALIZATION_PHASE0 = 0x28, + LTSSM_RECOVERY_EQUALIZATION_PHASE1 = 0x29, + LTSSM_RECOVERY_EQUALIZATION_PHASE2 = 0x2a, + LTSSM_RECOVERY_EQUALIZATION_PHASE3 = 0x2b, +}; + #define VENDOR_ID_REG (LMI_BASE_ADDR + 0x44) /* PCIe core controller registers */ @@ -258,13 +300,35 @@ static inline u32 advk_readl(struct advk_pcie *pcie, u64 reg) return readl(pcie->base + reg); } -static int advk_pcie_link_up(struct advk_pcie *pcie) +static u8 advk_pcie_ltssm_state(struct advk_pcie *pcie) { - u32 val, ltssm_state; + u32 val; + u8 ltssm_state; val = advk_readl(pcie, CFG_REG); ltssm_state = (val >> LTSSM_SHIFT) & LTSSM_MASK; - return ltssm_state >= LTSSM_L0; + return ltssm_state; +} + +static inline bool advk_pcie_link_up(struct advk_pcie *pcie) +{ + /* check if LTSSM is in normal operation - some L* state */ + u8 ltssm_state = advk_pcie_ltssm_state(pcie); + return ltssm_state >= LTSSM_L0 && ltssm_state < LTSSM_DISABLED; +} + +static inline bool advk_pcie_link_training(struct advk_pcie *pcie) +{ + /* + * According to PCIe Base specification 3.0, Table 4-14: Link + * Status Mapped to the LTSSM is Link Training mapped to LTSSM + * Configuration and Recovery states. + */ + u8 ltssm_state = advk_pcie_ltssm_state(pcie); + return ((ltssm_state >= LTSSM_CONFIG_LINKWIDTH_START && + ltssm_state < LTSSM_L0) || + (ltssm_state >= LTSSM_RECOVERY_EQUALIZATION_PHASE0 && + ltssm_state <= LTSSM_RECOVERY_EQUALIZATION_PHASE3)); } static int advk_pcie_wait_for_link(struct advk_pcie *pcie) @@ -287,7 +351,7 @@ static void advk_pcie_wait_for_retrain(struct advk_pcie *pcie) size_t retries; for (retries = 0; retries < RETRAIN_WAIT_MAX_RETRIES; ++retries) { - if (!advk_pcie_link_up(pcie)) + if (advk_pcie_link_training(pcie)) break; udelay(RETRAIN_WAIT_USLEEP_US); } @@ -706,7 +770,7 @@ advk_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge, /* u32 contains both PCI_EXP_LNKCTL and PCI_EXP_LNKSTA */ u32 val = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + reg) & ~(PCI_EXP_LNKSTA_LT << 16); - if (!advk_pcie_link_up(pcie)) + if (advk_pcie_link_training(pcie)) val |= (PCI_EXP_LNKSTA_LT << 16); *value = val; return PCI_BRIDGE_EMUL_HANDLED; From 2b650b7ff20eb7ea8ef9031d20fb657286ab90cc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Tue, 5 Oct 2021 20:09:52 +0200 Subject: [PATCH 174/587] PCI: aardvark: Fix reporting Data Link Layer Link Active MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add support for reporting PCI_EXP_LNKSTA_DLLLA bit in Link Control register on emulated bridge via current LTSSM state. Also correctly indicate DLLLA capability via PCI_EXP_LNKCAP_DLLLARC bit in Link Control Capability register. Link: https://lore.kernel.org/r/20211005180952.6812-14-kabel@kernel.org Fixes: 8a3ebd8de328 ("PCI: aardvark: Implement emulated root PCI bridge config space") Signed-off-by: Pali Rohár Signed-off-by: Marek Behún Signed-off-by: Lorenzo Pieralisi Reviewed-by: Marek Behún Cc: stable@vger.kernel.org --- drivers/pci/controller/pci-aardvark.c | 29 ++++++++++++++++++++++++++- 1 file changed, 28 insertions(+), 1 deletion(-) diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index f831f7d197bd..10476c00b312 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -317,6 +317,20 @@ static inline bool advk_pcie_link_up(struct advk_pcie *pcie) return ltssm_state >= LTSSM_L0 && ltssm_state < LTSSM_DISABLED; } +static inline bool advk_pcie_link_active(struct advk_pcie *pcie) +{ + /* + * According to PCIe Base specification 3.0, Table 4-14: Link + * Status Mapped to the LTSSM, and 4.2.6.3.6 Configuration.Idle + * is Link Up mapped to LTSSM Configuration.Idle, Recovery, L0, + * L0s, L1 and L2 states. And according to 3.2.1. Data Link + * Control and Management State Machine Rules is DL Up status + * reported in DL Active state. + */ + u8 ltssm_state = advk_pcie_ltssm_state(pcie); + return ltssm_state >= LTSSM_CONFIG_IDLE && ltssm_state < LTSSM_DISABLED; +} + static inline bool advk_pcie_link_training(struct advk_pcie *pcie) { /* @@ -766,12 +780,26 @@ advk_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge, return PCI_BRIDGE_EMUL_HANDLED; } + case PCI_EXP_LNKCAP: { + u32 val = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + reg); + /* + * PCI_EXP_LNKCAP_DLLLARC bit is hardwired in aardvark HW to 0. + * But support for PCI_EXP_LNKSTA_DLLLA is emulated via ltssm + * state so explicitly enable PCI_EXP_LNKCAP_DLLLARC flag. + */ + val |= PCI_EXP_LNKCAP_DLLLARC; + *value = val; + return PCI_BRIDGE_EMUL_HANDLED; + } + case PCI_EXP_LNKCTL: { /* u32 contains both PCI_EXP_LNKCTL and PCI_EXP_LNKSTA */ u32 val = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + reg) & ~(PCI_EXP_LNKSTA_LT << 16); if (advk_pcie_link_training(pcie)) val |= (PCI_EXP_LNKSTA_LT << 16); + if (advk_pcie_link_active(pcie)) + val |= (PCI_EXP_LNKSTA_DLLLA << 16); *value = val; return PCI_BRIDGE_EMUL_HANDLED; } @@ -779,7 +807,6 @@ advk_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge, case PCI_CAP_LIST_ID: case PCI_EXP_DEVCAP: case PCI_EXP_DEVCTL: - case PCI_EXP_LNKCAP: *value = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + reg); return PCI_BRIDGE_EMUL_HANDLED; default: From 2908a0d81f5b24081e95219b8bdc5b93a310f537 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 23 Jun 2021 17:01:02 +0300 Subject: [PATCH 175/587] PCI: dwc: Clean up Kconfig dependencies (PCIE_DW_HOST) The "depends on" Kconfig construct is a no-op in options that are selected and therefore has no effect. Remove it. Furthermore, there is no need to repeat menu dependencies (PCI). Clean up the users of PCIE_DW_HOST and introduce idiom depends on PCI_MSI_IRQ_DOMAIN select PCIE_DW_HOST for all of them. Link: https://lore.kernel.org/r/20210623140103.47818-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Signed-off-by: Lorenzo Pieralisi --- drivers/pci/controller/dwc/Kconfig | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/pci/controller/dwc/Kconfig b/drivers/pci/controller/dwc/Kconfig index 9892a1135678..8c2028e2eca6 100644 --- a/drivers/pci/controller/dwc/Kconfig +++ b/drivers/pci/controller/dwc/Kconfig @@ -8,7 +8,6 @@ config PCIE_DW config PCIE_DW_HOST bool - depends on PCI_MSI_IRQ_DOMAIN select PCIE_DW config PCIE_DW_EP @@ -22,8 +21,8 @@ config PCI_DRA7XX config PCI_DRA7XX_HOST tristate "TI DRA7xx PCIe controller Host Mode" depends on SOC_DRA7XX || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN depends on OF && HAS_IOMEM && TI_PIPE3 + depends on PCI_MSI_IRQ_DOMAIN select PCIE_DW_HOST select PCI_DRA7XX default y if SOC_DRA7XX @@ -55,7 +54,7 @@ config PCIE_DW_PLAT config PCIE_DW_PLAT_HOST bool "Platform bus based DesignWare PCIe Controller - Host mode" - depends on PCI && PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI_IRQ_DOMAIN select PCIE_DW_HOST select PCIE_DW_PLAT help @@ -138,8 +137,8 @@ config PCI_LAYERSCAPE bool "Freescale Layerscape PCIe controller - Host mode" depends on OF && (ARM || ARCH_LAYERSCAPE || COMPILE_TEST) depends on PCI_MSI_IRQ_DOMAIN - select MFD_SYSCON select PCIE_DW_HOST + select MFD_SYSCON help Say Y here if you want to enable PCIe controller support on Layerscape SoCs to work in Host mode. @@ -283,8 +282,8 @@ config PCIE_HISI_STB config PCI_MESON tristate "MESON PCIe controller" - depends on PCI_MSI_IRQ_DOMAIN default m if ARCH_MESON + depends on PCI_MSI_IRQ_DOMAIN select PCIE_DW_HOST help Say Y here if you want to enable PCI controller support on Amlogic From 8faa1d2defb795806cc46c21d16ad01bb37d23c4 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 23 Jun 2021 17:01:03 +0300 Subject: [PATCH 176/587] PCI: dwc: Clean up Kconfig dependencies (PCIE_DW_EP) The "depends on" Kconfig construct is a no-op in options that are selected and therefore has no effect. Remove it. Clean up the users of PCIE_DW_EP and introduce idiom depends on PCI_ENDPOINT select PCIE_DW_EP for all of them. Link: https://lore.kernel.org/r/20210623140103.47818-2-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Signed-off-by: Lorenzo Pieralisi --- drivers/pci/controller/dwc/Kconfig | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/pci/controller/dwc/Kconfig b/drivers/pci/controller/dwc/Kconfig index 8c2028e2eca6..6c4ee84053b5 100644 --- a/drivers/pci/controller/dwc/Kconfig +++ b/drivers/pci/controller/dwc/Kconfig @@ -12,7 +12,6 @@ config PCIE_DW_HOST config PCIE_DW_EP bool - depends on PCI_ENDPOINT select PCIE_DW config PCI_DRA7XX @@ -37,8 +36,8 @@ config PCI_DRA7XX_HOST config PCI_DRA7XX_EP tristate "TI DRA7xx PCIe controller Endpoint Mode" depends on SOC_DRA7XX || COMPILE_TEST - depends on PCI_ENDPOINT depends on OF && HAS_IOMEM && TI_PIPE3 + depends on PCI_ENDPOINT select PCIE_DW_EP select PCI_DRA7XX help From 5b8402562e553983fc941bb955e2c14d1a69215f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Krzysztof=20Wilczy=C5=84ski?= Date: Thu, 7 Oct 2021 12:28:48 +0000 Subject: [PATCH 177/587] PCI: visconti: Remove surplus dev_err() when using platform_get_irq_byname() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is no need to call the dev_err() function directly to print a custom message when handling an error from either the platform_get_irq() or platform_get_irq_byname() functions as both are going to display an appropriate error message in case of a failure. This change is as per suggestions from Coccinelle, e.g., drivers/pci/controller/dwc/pcie-visconti.c:286:2-9: line 286 is redundant because platform_get_irq() already prints an error Related: https://lore.kernel.org/all/20210310131913.2802385-1-kw@linux.com/ https://lore.kernel.org/all/20200802142601.1635926-1-kw@linux.com/ Link: https://lore.kernel.org/r/20211007122848.3366-1-kw@linux.com Signed-off-by: Krzysztof Wilczyński Signed-off-by: Lorenzo Pieralisi --- drivers/pci/controller/dwc/pcie-visconti.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-visconti.c b/drivers/pci/controller/dwc/pcie-visconti.c index a88eab6829bb..50f80f07e4db 100644 --- a/drivers/pci/controller/dwc/pcie-visconti.c +++ b/drivers/pci/controller/dwc/pcie-visconti.c @@ -279,13 +279,10 @@ static int visconti_add_pcie_port(struct visconti_pcie *pcie, { struct dw_pcie *pci = &pcie->pci; struct pcie_port *pp = &pci->pp; - struct device *dev = &pdev->dev; pp->irq = platform_get_irq_byname(pdev, "intr"); - if (pp->irq < 0) { - dev_err(dev, "Interrupt intr is missing"); + if (pp->irq < 0) return pp->irq; - } pp->ops = &visconti_pcie_host_ops; From 42da7911b83a462373c2d093a587d052f02211b0 Mon Sep 17 00:00:00 2001 From: Chunguang Xu Date: Fri, 17 Sep 2021 21:13:24 +0800 Subject: [PATCH 178/587] PCI: vmd: Assign a number to each VMD controller MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If the system has multiple VMD controllers, the driver does not assign a number to each controller, so when analyzing the interrupt through /proc/interrupts, the names of all controllers are the same, which is not very convenient for problem analysis. Here, try to assign a number to each VMD controller. Link: https://lore.kernel.org/r/1631884404-24141-1-git-send-email-brookxu.cn@gmail.com Signed-off-by: Chunguang Xu Signed-off-by: Lorenzo Pieralisi Reviewed-by: Jon Derrick Reviewed-by: Krzysztof Wilczyński --- drivers/pci/controller/vmd.c | 41 +++++++++++++++++++++++++++++------- 1 file changed, 33 insertions(+), 8 deletions(-) diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c index a5987e52700e..1b3e94a96414 100644 --- a/drivers/pci/controller/vmd.c +++ b/drivers/pci/controller/vmd.c @@ -70,6 +70,8 @@ enum vmd_features { VMD_FEAT_CAN_BYPASS_MSI_REMAP = (1 << 4), }; +static DEFINE_IDA(vmd_instance_ida); + /* * Lock for manipulating VMD IRQ lists. */ @@ -120,6 +122,8 @@ struct vmd_dev { struct pci_bus *bus; u8 busn_start; u8 first_vec; + char *name; + int instance; }; static inline struct vmd_dev *vmd_from_bus(struct pci_bus *bus) @@ -650,7 +654,7 @@ static int vmd_alloc_irqs(struct vmd_dev *vmd) INIT_LIST_HEAD(&vmd->irqs[i].irq_list); err = devm_request_irq(&dev->dev, pci_irq_vector(dev, i), vmd_irq, IRQF_NO_THREAD, - "vmd", &vmd->irqs[i]); + vmd->name, &vmd->irqs[i]); if (err) return err; } @@ -834,18 +838,32 @@ static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id) return -ENOMEM; vmd->dev = dev; + vmd->instance = ida_simple_get(&vmd_instance_ida, 0, 0, GFP_KERNEL); + if (vmd->instance < 0) + return vmd->instance; + + vmd->name = kasprintf(GFP_KERNEL, "vmd%d", vmd->instance); + if (!vmd->name) { + err = -ENOMEM; + goto out_release_instance; + } + err = pcim_enable_device(dev); if (err < 0) - return err; + goto out_release_instance; vmd->cfgbar = pcim_iomap(dev, VMD_CFGBAR, 0); - if (!vmd->cfgbar) - return -ENOMEM; + if (!vmd->cfgbar) { + err = -ENOMEM; + goto out_release_instance; + } pci_set_master(dev); if (dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(64)) && - dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(32))) - return -ENODEV; + dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(32))) { + err = -ENODEV; + goto out_release_instance; + } if (features & VMD_FEAT_OFFSET_FIRST_VECTOR) vmd->first_vec = 1; @@ -854,11 +872,16 @@ static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id) pci_set_drvdata(dev, vmd); err = vmd_enable_domain(vmd, features); if (err) - return err; + goto out_release_instance; dev_info(&vmd->dev->dev, "Bound to PCI domain %04x\n", vmd->sysdata.domain); return 0; + + out_release_instance: + ida_simple_remove(&vmd_instance_ida, vmd->instance); + kfree(vmd->name); + return err; } static void vmd_cleanup_srcu(struct vmd_dev *vmd) @@ -879,6 +902,8 @@ static void vmd_remove(struct pci_dev *dev) vmd_cleanup_srcu(vmd); vmd_detach_resources(vmd); vmd_remove_irq_domain(vmd); + ida_simple_remove(&vmd_instance_ida, vmd->instance); + kfree(vmd->name); } #ifdef CONFIG_PM_SLEEP @@ -903,7 +928,7 @@ static int vmd_resume(struct device *dev) for (i = 0; i < vmd->msix_count; i++) { err = devm_request_irq(dev, pci_irq_vector(pdev, i), vmd_irq, IRQF_NO_THREAD, - "vmd", &vmd->irqs[i]); + vmd->name, &vmd->irqs[i]); if (err) return err; } From 91a45b12d49e2b43d86caba25ed59fae43344ab8 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Thu, 7 Oct 2021 14:34:26 -0700 Subject: [PATCH 179/587] cxl/acpi: Do not fail cxl_acpi_probe() based on a missing CHBS When an ACPI0016 Host Bridge device is present yet no corresponding CEDT Host Bridge Structure (CHBS) exists, the ACPI probe method fails. Rather than fail, emit this warning and continue: cxl_acpi ACPI0017:00: No CHBS found for Host Bridge: ACPI0016:02 This error may occur on systems that are not compliant with the ACPI specification. Compliant systems include a CHBS entry for every CXL host bridge that is present at boot. Suggested-by: Ira Weiny Signed-off-by: Alison Schofield Tested-by: Vishal Verma Reviewed-by: Ira Weiny Link: https://lore.kernel.org/r/20211007213426.392644-1-alison.schofield@intel.com Signed-off-by: Dan Williams --- drivers/cxl/acpi.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c index af1c6c1875ac..dadc7f64b9ff 100644 --- a/drivers/cxl/acpi.c +++ b/drivers/cxl/acpi.c @@ -288,7 +288,7 @@ static int add_host_bridge_uport(struct device *match, void *arg) dport = find_dport_by_dev(root_port, match); if (!dport) { dev_dbg(host, "host bridge expected and not found\n"); - return -ENODEV; + return 0; } port = devm_cxl_add_port(host, match, dport->component_reg_phys, @@ -377,9 +377,11 @@ static int add_host_bridge_dport(struct device *match, void *arg) } chbs = cxl_acpi_match_chbs(host, uid); - if (IS_ERR(chbs)) - dev_dbg(host, "No CHBS found for Host Bridge: %s\n", - dev_name(match)); + if (IS_ERR(chbs)) { + dev_warn(host, "No CHBS found for Host Bridge: %s\n", + dev_name(match)); + return 0; + } rc = cxl_add_dport(root_port, match, uid, get_chbcr(chbs)); if (rc) { From 73e40c9bd44ce91fd0fcee6f0a3480dcd97963b6 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Sat, 21 Aug 2021 11:19:07 +0200 Subject: [PATCH 180/587] libperf cpumap: Use binary search in perf_cpu_map__idx() as array are sorted Since 7074674e7338863e ("perf cpumap: Maintain cpumaps ordered and without dups") perf_cpu_map elements are sorted in ascending order. This patch improves perf_cpu_map__idx() by using a binary search. Signed-off-by: Riccardo Mancini Cc: Andi Kleen Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/f1543c15797169c21e8b205a4a6751159180580d.1629490974.git.rickyman7@gmail.com [ Removed 'else' after if + return, declared variables where needed ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/perf/cpumap.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c index 6d8e521c59e1..adaad3dddf6e 100644 --- a/tools/lib/perf/cpumap.c +++ b/tools/lib/perf/cpumap.c @@ -270,11 +270,19 @@ bool perf_cpu_map__empty(const struct perf_cpu_map *map) int perf_cpu_map__idx(struct perf_cpu_map *cpus, int cpu) { - int i; + int low = 0, high = cpus->nr; - for (i = 0; i < cpus->nr; ++i) { - if (cpus->map[i] == cpu) - return i; + while (low < high) { + int idx = (low + high) / 2, + cpu_at_idx = cpus->map[idx]; + + if (cpu_at_idx == cpu) + return idx; + + if (cpu_at_idx > cpu) + high = idx; + else + low = idx + 1; } return -1; From c65bd90dc93e1b2f8e776f619ffbb0335a7a16ec Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 1 Oct 2021 14:16:09 +0200 Subject: [PATCH 181/587] PCI: rcar-ep: Remove unneeded includes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Remove includes that are not needed, to speed up (re)compilation. Include , which is needed, and was included implicitly through before. Most of these are relics from splitting the driver in a host and a common part and adding endpoint support. [bhelgaas: use driver tag consistent with cadence-ep, designware-ep] Link: https://lore.kernel.org/r/7c708841a2bf84f85b14a963271c3e99c8ba38a5.1633090444.git.geert+renesas@glider.be Signed-off-by: Geert Uytterhoeven Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas Reviewed-by: Niklas Söderlund --- drivers/pci/controller/pcie-rcar-ep.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/pci/controller/pcie-rcar-ep.c b/drivers/pci/controller/pcie-rcar-ep.c index aa1cf24a5a72..f9682df1da61 100644 --- a/drivers/pci/controller/pcie-rcar-ep.c +++ b/drivers/pci/controller/pcie-rcar-ep.c @@ -6,16 +6,13 @@ * Author: Lad Prabhakar */ -#include #include #include -#include -#include #include #include #include -#include #include +#include #include "pcie-rcar.h" From 6bd006c6eb7fdadbe36de84377af4447da4ffabb Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Sat, 21 Aug 2021 11:19:10 +0200 Subject: [PATCH 182/587] perf mmap: Introduce mmap_cpu_mask__duplicate() This patch adds a new function in util/mmap.c to duplicate a mmap_cpu_mask. This new function will be used in patches in the workqueue patchkit. Signed-off-by: Riccardo Mancini Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/8943a548ef7a3dd3e015095afad7e9a8b2154c05.1629490974.git.rickyman7@gmail.com [ bitmap_alloc() was renamed to bitmap_zalloc() ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/mmap.c | 11 +++++++++++ tools/perf/util/mmap.h | 3 +++ 2 files changed, 14 insertions(+) diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index 512dc8b9c168..23ecdba9e670 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -350,3 +350,14 @@ int perf_mmap__push(struct mmap *md, void *to, out: return rc; } + +int mmap_cpu_mask__duplicate(struct mmap_cpu_mask *original, struct mmap_cpu_mask *clone) +{ + clone->nbits = original->nbits; + clone->bits = bitmap_zalloc(original->nbits); + if (!clone->bits) + return -ENOMEM; + + memcpy(clone->bits, original->bits, MMAP_CPU_MASK_BYTES(original)); + return 0; +} diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h index af33118354dd..8e259b9610f8 100644 --- a/tools/perf/util/mmap.h +++ b/tools/perf/util/mmap.h @@ -64,4 +64,7 @@ size_t mmap__mmap_len(struct mmap *map); void mmap_cpu_mask__scnprintf(struct mmap_cpu_mask *mask, const char *tag); +int mmap_cpu_mask__duplicate(struct mmap_cpu_mask *original, + struct mmap_cpu_mask *clone); + #endif /*__PERF_MMAP_H */ From 861e133ba268bef4765ea62c9602d4116b9c63ec Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 1 Oct 2021 14:16:43 +0200 Subject: [PATCH 183/587] PCI: rcar-host: Remove unneeded includes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Remove includes that are not needed, to speed up (re)compilation. Most of these are relics from splitting the driver in a host and a common part. [bhelgaas: use driver tag analogous to rcar-ep] Link: https://lore.kernel.org/r/54bed9a0e6991490ddb2b07e5abfaf40a7a62928.1633090577.git.geert+renesas@glider.be Signed-off-by: Geert Uytterhoeven Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas Reviewed-by: Niklas Söderlund --- drivers/pci/controller/pcie-rcar-host.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/pci/controller/pcie-rcar-host.c b/drivers/pci/controller/pcie-rcar-host.c index 8f3131844e77..e12c2d8be05a 100644 --- a/drivers/pci/controller/pcie-rcar-host.c +++ b/drivers/pci/controller/pcie-rcar-host.c @@ -24,13 +24,11 @@ #include #include #include -#include #include #include #include #include #include -#include #include "pcie-rcar.h" From c2d4fab01f5e69adbe697c82f35cc31cf200bf93 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Sat, 21 Aug 2021 11:19:42 +0200 Subject: [PATCH 184/587] perf test evlist-open-close: Use inline func to convert timeval to usec This patch introduces a new inline function to convert a timeval to usec. This function will be used also in the next patch. Signed-off-by: Riccardo Mancini Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/b95035ec4a125355be8ea843f7275c4580da6398.1629490974.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/bench/evlist-open-close.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/tools/perf/bench/evlist-open-close.c b/tools/perf/bench/evlist-open-close.c index 83e9897c64a1..75a53919126b 100644 --- a/tools/perf/bench/evlist-open-close.c +++ b/tools/perf/bench/evlist-open-close.c @@ -25,6 +25,11 @@ static int iterations = 100; static int nr_events = 1; static const char *event_string = "dummy"; +static inline u64 timeval2usec(struct timeval *tv) +{ + return tv->tv_sec * USEC_PER_SEC + tv->tv_usec; +} + static struct record_opts opts = { .sample_time = true, .mmap_pages = UINT_MAX, @@ -167,7 +172,7 @@ static int bench_evlist_open_close__run(char *evstr) gettimeofday(&end, NULL); timersub(&end, &start, &diff); - runtime_us = diff.tv_sec * USEC_PER_SEC + diff.tv_usec; + runtime_us = timeval2usec(&diff); update_stats(&time_stats, runtime_us); evlist__delete(evlist); From 31c9ef00258075df2f1fe5ef812cd7e9b6a1dc55 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Mon, 20 Sep 2021 12:29:44 +0530 Subject: [PATCH 185/587] dt-bindings: PCI: Add Qualcomm PCIe Endpoint controller Add devicetree binding for Qualcomm PCIe Endpoint controller used in platforms like SDX55. The Endpoint controller is based on the DesignWare core with Qualcomm-specific wrappers. Link: https://lore.kernel.org/r/20210920065946.15090-2-manivannan.sadhasivam@linaro.org Signed-off-by: Manivannan Sadhasivam Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas Reviewed-by: Rob Herring --- .../devicetree/bindings/pci/qcom,pcie-ep.yaml | 158 ++++++++++++++++++ 1 file changed, 158 insertions(+) create mode 100644 Documentation/devicetree/bindings/pci/qcom,pcie-ep.yaml diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie-ep.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie-ep.yaml new file mode 100644 index 000000000000..3d23599e5e91 --- /dev/null +++ b/Documentation/devicetree/bindings/pci/qcom,pcie-ep.yaml @@ -0,0 +1,158 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/pci/qcom,pcie-ep.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm PCIe Endpoint Controller binding + +maintainers: + - Manivannan Sadhasivam + +allOf: + - $ref: "pci-ep.yaml#" + +properties: + compatible: + const: qcom,sdx55-pcie-ep + + reg: + items: + - description: Qualcomm-specific PARF configuration registers + - description: DesignWare PCIe registers + - description: External local bus interface registers + - description: Address Translation Unit (ATU) registers + - description: Memory region used to map remote RC address space + - description: BAR memory region + + reg-names: + items: + - const: parf + - const: dbi + - const: elbi + - const: atu + - const: addr_space + - const: mmio + + clocks: + items: + - description: PCIe Auxiliary clock + - description: PCIe CFG AHB clock + - description: PCIe Master AXI clock + - description: PCIe Slave AXI clock + - description: PCIe Slave Q2A AXI clock + - description: PCIe Sleep clock + - description: PCIe Reference clock + + clock-names: + items: + - const: aux + - const: cfg + - const: bus_master + - const: bus_slave + - const: slave_q2a + - const: sleep + - const: ref + + qcom,perst-regs: + description: Reference to a syscon representing TCSR followed by the two + offsets within syscon for Perst enable and Perst separation + enable registers + $ref: "/schemas/types.yaml#/definitions/phandle-array" + items: + minItems: 3 + maxItems: 3 + + interrupts: + items: + - description: PCIe Global interrupt + - description: PCIe Doorbell interrupt + + interrupt-names: + items: + - const: global + - const: doorbell + + reset-gpios: + description: GPIO used as PERST# input signal + maxItems: 1 + + wake-gpios: + description: GPIO used as WAKE# output signal + maxItems: 1 + + resets: + maxItems: 1 + + reset-names: + const: core + + power-domains: + maxItems: 1 + + phys: + maxItems: 1 + + phy-names: + const: pciephy + + num-lanes: + default: 2 + +required: + - compatible + - reg + - reg-names + - clocks + - clock-names + - qcom,perst-regs + - interrupts + - interrupt-names + - reset-gpios + - resets + - reset-names + - power-domains + +unevaluatedProperties: false + +examples: + - | + #include + #include + #include + pcie_ep: pcie-ep@40000000 { + compatible = "qcom,sdx55-pcie-ep"; + reg = <0x01c00000 0x3000>, + <0x40000000 0xf1d>, + <0x40000f20 0xc8>, + <0x40001000 0x1000>, + <0x40002000 0x1000>, + <0x01c03000 0x3000>; + reg-names = "parf", "dbi", "elbi", "atu", "addr_space", + "mmio"; + + clocks = <&gcc GCC_PCIE_AUX_CLK>, + <&gcc GCC_PCIE_CFG_AHB_CLK>, + <&gcc GCC_PCIE_MSTR_AXI_CLK>, + <&gcc GCC_PCIE_SLV_AXI_CLK>, + <&gcc GCC_PCIE_SLV_Q2A_AXI_CLK>, + <&gcc GCC_PCIE_SLEEP_CLK>, + <&gcc GCC_PCIE_0_CLKREF_CLK>; + clock-names = "aux", "cfg", "bus_master", "bus_slave", + "slave_q2a", "sleep", "ref"; + + qcom,perst-regs = <&tcsr 0xb258 0xb270>; + + interrupts = , + ; + interrupt-names = "global", "doorbell"; + reset-gpios = <&tlmm 57 GPIO_ACTIVE_LOW>; + wake-gpios = <&tlmm 53 GPIO_ACTIVE_LOW>; + resets = <&gcc GCC_PCIE_BCR>; + reset-names = "core"; + power-domains = <&gcc PCIE_GDSC>; + phys = <&pcie0_lane>; + phy-names = "pciephy"; + max-link-speed = <3>; + num-lanes = <2>; + }; From c6c00900c751c2fab9e34ee27f5e883fc1a20fc6 Mon Sep 17 00:00:00 2001 From: Guo Zhengkui Date: Wed, 6 Oct 2021 14:22:34 +0800 Subject: [PATCH 186/587] perf daemon: Remove duplicate sys/file.h include There is a "#include " in line 10, so remove a duplicate one in line 1124. Signed-off-by: Guo Zhengkui Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20211006062235.6364-1-guozhengkui@vivo.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-daemon.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/tools/perf/builtin-daemon.c b/tools/perf/builtin-daemon.c index c13201fb09c3..6cb3f6cc36d0 100644 --- a/tools/perf/builtin-daemon.c +++ b/tools/perf/builtin-daemon.c @@ -1121,8 +1121,6 @@ static int setup_config(struct daemon *daemon) #ifndef F_TLOCK #define F_TLOCK 2 -#include - static int lockf(int fd, int cmd, off_t len) { if (cmd != F_TLOCK || len != 0) From 08f3e0873ac203449465c2b8473d684e2f9f41d1 Mon Sep 17 00:00:00 2001 From: James Clark Date: Thu, 7 Oct 2021 12:05:40 +0100 Subject: [PATCH 187/587] perf vendor-events: Fix all remaining invalid JSON files Remove trailing commas. A later commit will make the parser more strict and these will not be valid anymore. Reviewed-by: Andi Kleen Reviewed-by: John Garry Reviewed-by: Kajol Jain Signed-off-by: James Clark Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andrew.Kilroy@arm.com Cc: Leo Yan Cc: Mark Rutland Cc: Mathieu Poirier Cc: Namhyung Kim Cc: Nick.Forrington@arm.com Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20211007110543.564963-2-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/arm64/ampere/emag/bus.json | 2 +- .../arch/arm64/ampere/emag/cache.json | 20 +++++++++---------- .../arch/arm64/ampere/emag/clock.json | 2 +- .../arch/arm64/ampere/emag/exception.json | 4 ++-- .../arch/arm64/ampere/emag/instruction.json | 10 +++++----- .../arch/arm64/ampere/emag/memory.json | 4 ++-- .../arch/arm64/hisilicon/hip08/metrics.json | 2 +- .../pmu-events/arch/nds32/n13/atcpmu.json | 2 +- .../pmu-events/arch/s390/cf_z10/basic.json | 2 +- .../pmu-events/arch/s390/cf_z10/crypto.json | 2 +- .../pmu-events/arch/s390/cf_z10/extended.json | 2 +- .../pmu-events/arch/s390/cf_z13/basic.json | 2 +- .../pmu-events/arch/s390/cf_z13/crypto.json | 2 +- .../pmu-events/arch/s390/cf_z13/extended.json | 2 +- .../pmu-events/arch/s390/cf_z14/basic.json | 2 +- .../pmu-events/arch/s390/cf_z14/crypto.json | 2 +- .../pmu-events/arch/s390/cf_z14/extended.json | 2 +- .../pmu-events/arch/s390/cf_z15/basic.json | 2 +- .../pmu-events/arch/s390/cf_z15/crypto.json | 2 +- .../pmu-events/arch/s390/cf_z15/crypto6.json | 2 +- .../pmu-events/arch/s390/cf_z15/extended.json | 2 +- .../pmu-events/arch/s390/cf_z196/basic.json | 2 +- .../pmu-events/arch/s390/cf_z196/crypto.json | 2 +- .../arch/s390/cf_z196/extended.json | 2 +- .../pmu-events/arch/s390/cf_zec12/basic.json | 2 +- .../pmu-events/arch/s390/cf_zec12/crypto.json | 2 +- .../arch/s390/cf_zec12/extended.json | 2 +- .../arch/test/test_soc/cpu/uncore.json | 2 +- .../arch/x86/icelakex/icx-metrics.json | 2 +- 29 files changed, 44 insertions(+), 44 deletions(-) diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json index 9bea1ba1c4d2..cf48d0dfc759 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json @@ -18,6 +18,6 @@ "ArchStdEvent": "BUS_ACCESS_PERIPH" }, { - "ArchStdEvent": "BUS_ACCESS", + "ArchStdEvent": "BUS_ACCESS" } ] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json index 1e25f2ae4ae0..4cc50b7da526 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json @@ -39,31 +39,31 @@ "ArchStdEvent": "L2D_CACHE_INVAL" }, { - "ArchStdEvent": "L1I_CACHE_REFILL", + "ArchStdEvent": "L1I_CACHE_REFILL" }, { - "ArchStdEvent": "L1I_TLB_REFILL", + "ArchStdEvent": "L1I_TLB_REFILL" }, { - "ArchStdEvent": "L1D_CACHE_REFILL", + "ArchStdEvent": "L1D_CACHE_REFILL" }, { - "ArchStdEvent": "L1D_CACHE", + "ArchStdEvent": "L1D_CACHE" }, { - "ArchStdEvent": "L1D_TLB_REFILL", + "ArchStdEvent": "L1D_TLB_REFILL" }, { - "ArchStdEvent": "L1I_CACHE", + "ArchStdEvent": "L1I_CACHE" }, { - "ArchStdEvent": "L2D_CACHE", + "ArchStdEvent": "L2D_CACHE" }, { - "ArchStdEvent": "L2D_CACHE_REFILL", + "ArchStdEvent": "L2D_CACHE_REFILL" }, { - "ArchStdEvent": "L2D_CACHE_WB", + "ArchStdEvent": "L2D_CACHE_WB" }, { "PublicDescription": "This event counts any load or store operation which accesses the data L1 TLB", @@ -72,7 +72,7 @@ }, { "PublicDescription": "This event counts any instruction fetch which accesses the instruction L1 TLB", - "ArchStdEvent": "L1I_TLB", + "ArchStdEvent": "L1I_TLB" }, { "PublicDescription": "Level 2 access to data TLB that caused a page table walk. This event counts on any data access which causes L2D_TLB_REFILL to count", diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json index 9076ca2daf9e..927a6f629a03 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json @@ -1,7 +1,7 @@ [ { "PublicDescription": "The number of core clock cycles", - "ArchStdEvent": "CPU_CYCLES", + "ArchStdEvent": "CPU_CYCLES" }, { "PublicDescription": "FSU clocking gated off cycle", diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json index 9761433ad329..ada052e19632 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json @@ -36,9 +36,9 @@ "ArchStdEvent": "EXC_TRAP_FIQ" }, { - "ArchStdEvent": "EXC_TAKEN", + "ArchStdEvent": "EXC_TAKEN" }, { - "ArchStdEvent": "EXC_RETURN", + "ArchStdEvent": "EXC_RETURN" } ] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json index 482aa3f19e58..62f6276e3016 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json @@ -44,25 +44,25 @@ "BriefDescription": "Software increment" }, { - "ArchStdEvent": "INST_RETIRED", + "ArchStdEvent": "INST_RETIRED" }, { "ArchStdEvent": "CID_WRITE_RETIRED", "BriefDescription": "Write to CONTEXTIDR" }, { - "ArchStdEvent": "INST_SPEC", + "ArchStdEvent": "INST_SPEC" }, { - "ArchStdEvent": "TTBR_WRITE_RETIRED", + "ArchStdEvent": "TTBR_WRITE_RETIRED" }, { "PublicDescription": "This event counts all branches, taken or not. This excludes exception entries, debug entries and CCFAIL branches", - "ArchStdEvent": "BR_RETIRED", + "ArchStdEvent": "BR_RETIRED" }, { "PublicDescription": "This event counts any branch counted by BR_RETIRED which is not correctly predicted and causes a pipeline flush", - "ArchStdEvent": "BR_MIS_PRED_RETIRED", + "ArchStdEvent": "BR_MIS_PRED_RETIRED" }, { "PublicDescription": "Operation speculatively executed, NOP", diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json index 2e7555696caf..50157e8c2005 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json @@ -15,10 +15,10 @@ "ArchStdEvent": "UNALIGNED_LDST_SPEC" }, { - "ArchStdEvent": "MEM_ACCESS", + "ArchStdEvent": "MEM_ACCESS" }, { "PublicDescription": "This event counts any correctable or uncorrectable memory error (ECC or parity) in the protected core RAMs", - "ArchStdEvent": "MEMORY_ERROR", + "ArchStdEvent": "MEMORY_ERROR" } ] diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json index dda8e59149d2..6970203cb247 100644 --- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json +++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json @@ -229,5 +229,5 @@ "BriefDescription": "Store bound L3 topdown metric", "MetricGroup": "TopDownL3", "MetricName": "store_bound" - }, + } ] diff --git a/tools/perf/pmu-events/arch/nds32/n13/atcpmu.json b/tools/perf/pmu-events/arch/nds32/n13/atcpmu.json index 5347350c360c..3e7ac409d894 100644 --- a/tools/perf/pmu-events/arch/nds32/n13/atcpmu.json +++ b/tools/perf/pmu-events/arch/nds32/n13/atcpmu.json @@ -286,5 +286,5 @@ "EventCode": "0x21e", "EventName": "pop25_inst", "BriefDescription": "V3 POP25 instructions" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/basic.json b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json index 2dd8dafff2ef..783de7f1aeaa 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z10/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json @@ -82,5 +82,5 @@ "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES", "BriefDescription": "Problem-State L1D Penalty Cycles", "PublicDescription": "Problem-State Level-1 D-Cache Penalty Cycle Count" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json index db286f19e7b6..3f28007d3892 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json @@ -110,5 +110,5 @@ "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the AES functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/extended.json b/tools/perf/pmu-events/arch/s390/cf_z10/extended.json index b6b7f29ca831..86bd8ba9391d 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z10/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z10/extended.json @@ -124,5 +124,5 @@ "EventName": "L2C_STORES_SENT", "BriefDescription": "L2C Stores Sent", "PublicDescription": "Incremented by one for every store sent to Level-2 (L1.5) cache" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/basic.json b/tools/perf/pmu-events/arch/s390/cf_z13/basic.json index 2dd8dafff2ef..783de7f1aeaa 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z13/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_z13/basic.json @@ -82,5 +82,5 @@ "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES", "BriefDescription": "Problem-State L1D Penalty Cycles", "PublicDescription": "Problem-State Level-1 D-Cache Penalty Cycle Count" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json index db286f19e7b6..3f28007d3892 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json @@ -110,5 +110,5 @@ "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the AES functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json index 5da8296b667e..1a5e4f89c57e 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json @@ -390,5 +390,5 @@ "EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE", "BriefDescription": "Cycle count with two threads active", "PublicDescription": "Cycle count with two threads active" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/basic.json b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json index 17fb5241928b..fc762e9f1d6e 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z14/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json @@ -54,5 +54,5 @@ "EventName": "PROBLEM_STATE_INSTRUCTIONS", "BriefDescription": "Problem-State Instructions", "PublicDescription": "Problem-State Instruction Count" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json index db286f19e7b6..3f28007d3892 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json @@ -110,5 +110,5 @@ "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the AES functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json index 89e070727e1b..4942b20a1ea1 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json @@ -369,5 +369,5 @@ "EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE", "BriefDescription": "Cycle count with two threads active", "PublicDescription": "Cycle count with two threads active" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/basic.json b/tools/perf/pmu-events/arch/s390/cf_z15/basic.json index 17fb5241928b..fc762e9f1d6e 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z15/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_z15/basic.json @@ -54,5 +54,5 @@ "EventName": "PROBLEM_STATE_INSTRUCTIONS", "BriefDescription": "Problem-State Instructions", "PublicDescription": "Problem-State Instruction Count" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z15/crypto.json index db286f19e7b6..3f28007d3892 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z15/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_z15/crypto.json @@ -110,5 +110,5 @@ "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the AES functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json b/tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json index c998e4f1d1d2..ad79189050a0 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json +++ b/tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json @@ -26,5 +26,5 @@ "EventName": "ECC_BLOCKED_CYCLES_COUNT", "BriefDescription": "ECC Blocked Cycles Count", "PublicDescription": "This counter counts the total number of CPU cycles blocked for the elliptic-curve cryptography (ECC) functions issued by the CPU because the ECC coprocessor is busy performing a function issued by another CPU." - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/extended.json b/tools/perf/pmu-events/arch/s390/cf_z15/extended.json index 24c4ba2a9ae5..8ac61f8f286b 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z15/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z15/extended.json @@ -397,5 +397,5 @@ "EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE", "BriefDescription": "Cycle count with two threads active", "PublicDescription": "Cycle count with two threads active" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/basic.json b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json index 2dd8dafff2ef..783de7f1aeaa 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z196/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json @@ -82,5 +82,5 @@ "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES", "BriefDescription": "Problem-State L1D Penalty Cycles", "PublicDescription": "Problem-State Level-1 D-Cache Penalty Cycle Count" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json index db286f19e7b6..3f28007d3892 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json @@ -110,5 +110,5 @@ "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the AES functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/extended.json b/tools/perf/pmu-events/arch/s390/cf_z196/extended.json index b7b42a870bb0..86b29fd181cf 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z196/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z196/extended.json @@ -166,5 +166,5 @@ "EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1I Off-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json b/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json index 2dd8dafff2ef..783de7f1aeaa 100644 --- a/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json @@ -82,5 +82,5 @@ "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES", "BriefDescription": "Problem-State L1D Penalty Cycles", "PublicDescription": "Problem-State Level-1 D-Cache Penalty Cycle Count" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json b/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json index db286f19e7b6..3f28007d3892 100644 --- a/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json @@ -110,5 +110,5 @@ "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the AES functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json b/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json index 162251037219..f40cbed89418 100644 --- a/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json @@ -243,5 +243,5 @@ "EventName": "TX_C_TABORT_SPECIAL", "BriefDescription": "Aborted transactions in constrained TX mode using special completion logic", "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete" - }, + } ] diff --git a/tools/perf/pmu-events/arch/test/test_soc/cpu/uncore.json b/tools/perf/pmu-events/arch/test/test_soc/cpu/uncore.json index 788766f45dbc..73089c682f80 100644 --- a/tools/perf/pmu-events/arch/test/test_soc/cpu/uncore.json +++ b/tools/perf/pmu-events/arch/test/test_soc/cpu/uncore.json @@ -38,5 +38,5 @@ "BriefDescription": "Total cache hits", "PublicDescription": "Total cache hits", "Unit": "imc" - }, + } ] diff --git a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json index 57ddbb9f9b31..14b9a8ab15b9 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json @@ -311,5 +311,5 @@ "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency" - }, + } ] From 21813684e46df1c979f714b20b369b3474f5e933 Mon Sep 17 00:00:00 2001 From: James Clark Date: Thu, 7 Oct 2021 12:05:41 +0100 Subject: [PATCH 188/587] perf tools: Make the JSON parser more conformant when in strict mode Return an error when a trailing comma is found or a new item is encountered before a comma or an opening brace. This ensures that the perf JSON files conform more closely to the spec at https://www.json.org Reviewed-by: Andi Kleen Reviewed-by: Kajol Jain Signed-off-by: James Clark Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andrew.Kilroy@arm.com Cc: John Garry Cc: Leo Yan Cc: Mark Rutland Cc: Mathieu Poirier Cc: Namhyung Kim Cc: Nick.Forrington@arm.com Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20211007110543.564963-3-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/jsmn.c | 42 ++++++++++++++++++++++++++++++++++-- 1 file changed, 40 insertions(+), 2 deletions(-) diff --git a/tools/perf/pmu-events/jsmn.c b/tools/perf/pmu-events/jsmn.c index 11d1fa18bfa5..8124d2d3ff0c 100644 --- a/tools/perf/pmu-events/jsmn.c +++ b/tools/perf/pmu-events/jsmn.c @@ -176,6 +176,14 @@ jsmnerr_t jsmn_parse(jsmn_parser *parser, const char *js, size_t len, jsmnerr_t r; int i; jsmntok_t *token; +#ifdef JSMN_STRICT + /* + * Keeps track of whether a new object/list/primitive is expected. New items are only + * allowed after an opening brace, comma or colon. A closing brace after a comma is not + * valid JSON. + */ + int expecting_item = 1; +#endif for (; parser->pos < len; parser->pos++) { char c; @@ -185,6 +193,10 @@ jsmnerr_t jsmn_parse(jsmn_parser *parser, const char *js, size_t len, switch (c) { case '{': case '[': +#ifdef JSMN_STRICT + if (!expecting_item) + return JSMN_ERROR_INVAL; +#endif token = jsmn_alloc_token(parser, tokens, num_tokens); if (token == NULL) return JSMN_ERROR_NOMEM; @@ -196,6 +208,10 @@ jsmnerr_t jsmn_parse(jsmn_parser *parser, const char *js, size_t len, break; case '}': case ']': +#ifdef JSMN_STRICT + if (expecting_item) + return JSMN_ERROR_INVAL; +#endif type = (c == '}' ? JSMN_OBJECT : JSMN_ARRAY); for (i = parser->toknext - 1; i >= 0; i--) { token = &tokens[i]; @@ -219,6 +235,11 @@ jsmnerr_t jsmn_parse(jsmn_parser *parser, const char *js, size_t len, } break; case '\"': +#ifdef JSMN_STRICT + if (!expecting_item) + return JSMN_ERROR_INVAL; + expecting_item = 0; +#endif r = jsmn_parse_string(parser, js, len, tokens, num_tokens); if (r < 0) @@ -229,11 +250,15 @@ jsmnerr_t jsmn_parse(jsmn_parser *parser, const char *js, size_t len, case '\t': case '\r': case '\n': - case ':': - case ',': case ' ': break; #ifdef JSMN_STRICT + case ':': + case ',': + if (expecting_item) + return JSMN_ERROR_INVAL; + expecting_item = 1; + break; /* * In strict mode primitives are: * numbers and booleans. @@ -253,6 +278,9 @@ jsmnerr_t jsmn_parse(jsmn_parser *parser, const char *js, size_t len, case 'f': case 'n': #else + case ':': + case ',': + break; /* * In non-strict mode every unquoted value * is a primitive. @@ -260,6 +288,12 @@ jsmnerr_t jsmn_parse(jsmn_parser *parser, const char *js, size_t len, /*FALL THROUGH */ default: #endif + +#ifdef JSMN_STRICT + if (!expecting_item) + return JSMN_ERROR_INVAL; + expecting_item = 0; +#endif r = jsmn_parse_primitive(parser, js, len, tokens, num_tokens); if (r < 0) @@ -282,7 +316,11 @@ jsmnerr_t jsmn_parse(jsmn_parser *parser, const char *js, size_t len, return JSMN_ERROR_PART; } +#ifdef JSMN_STRICT + return expecting_item ? JSMN_ERROR_INVAL : JSMN_SUCCESS; +#else return JSMN_SUCCESS; +#endif } /* From eda1a84cb4e9375984563c23a950377f915e7e1b Mon Sep 17 00:00:00 2001 From: James Clark Date: Thu, 7 Oct 2021 12:05:42 +0100 Subject: [PATCH 189/587] perf tools: Enable strict JSON parsing This is to ensure that the PMU event files can always be parsed by other tools. Testing ======= * There are no errors when parsing files for all architectures: # pmu-events/jevents nds32 pmu-events/arch/ test # pmu-events/jevents s390 pmu-events/arch/ test # pmu-events/jevents powerpc pmu-events/arch/ test # pmu-events/jevents arm64 pmu-events/arch/ test # pmu-events/jevents test pmu-events/arch/ test # pmu-events/jevents x86 pmu-events/arch/ test * Trailing and leading commas now cause a parse error * Double commas now cause a parse error * Compilation and parsing works with strict mode disabled and enabled * A diff of the output files shows no changes Reviewed-by: Andi Kleen Reviewed-by: Kajol Jain Signed-off-by: James Clark Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andrew.Kilroy@arm.com Cc: John Garry Cc: Leo Yan Cc: Mark Rutland Cc: Mathieu Poirier Cc: Namhyung Kim Cc: Nick.Forrington@arm.com Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20211007110543.564963-4-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/jsmn.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/pmu-events/jsmn.c b/tools/perf/pmu-events/jsmn.c index 8124d2d3ff0c..831dc44c4558 100644 --- a/tools/perf/pmu-events/jsmn.c +++ b/tools/perf/pmu-events/jsmn.c @@ -24,6 +24,7 @@ #include #include "jsmn.h" +#define JSMN_STRICT /* * Allocates a fresh unused token from the token pool. From f792cf8a094eac29e1d4e3d588dffbe68c7741a6 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 22 Sep 2021 14:20:31 -0700 Subject: [PATCH 190/587] perf kmem: Improve man page for record options Since: https://lore.kernel.org/lkml/20200708183919.4141023-1-irogers@google.com/ The output option works for 'perf kmem', however, it must appear after 'record'. This is different to 'stat' where '-i' for the input must appear before. Try to capture this complication in the man page. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lore.kernel.org/lkml/20210922212031.485950-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-kmem.txt | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/tools/perf/Documentation/perf-kmem.txt b/tools/perf/Documentation/perf-kmem.txt index 85b8ac695c87..f378ac59353d 100644 --- a/tools/perf/Documentation/perf-kmem.txt +++ b/tools/perf/Documentation/perf-kmem.txt @@ -8,22 +8,25 @@ perf-kmem - Tool to trace/measure kernel memory properties SYNOPSIS -------- [verse] -'perf kmem' {record|stat} [] +'perf kmem' [] {record|stat} DESCRIPTION ----------- There are two variants of perf kmem: - 'perf kmem record ' to record the kmem events - of an arbitrary workload. + 'perf kmem [] record [] ' to + record the kmem events of an arbitrary workload. Additional 'perf + record' options may be specified after record, such as '-o' to + change the output file name. - 'perf kmem stat' to report kernel memory statistics. + 'perf kmem [] stat' to report kernel memory statistics. OPTIONS ------- -i :: --input=:: - Select the input file (default: perf.data unless stdin is a fifo) + For stat, select the input file (default: perf.data unless stdin is a + fifo) -f:: --force:: From b2105b9f39b57ac80fb909b7ae4da3d343af9f7d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Krzysztof=20Wilczy=C5=84ski?= Date: Wed, 6 Oct 2021 23:38:27 +0000 Subject: [PATCH 191/587] PCI: Correct misspelled and remove duplicated words MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Correct a number of misspelled words and remove any words that were duplicated in the PCI tree. No change to functionality intended. Link: https://lore.kernel.org/r/20211006233827.147328-1-kw@linux.com Signed-off-by: Krzysztof Wilczyński Signed-off-by: Bjorn Helgaas --- drivers/pci/controller/pci-xgene-msi.c | 2 +- drivers/pci/controller/pcie-brcmstb.c | 2 +- drivers/pci/controller/pcie-iproc.c | 2 +- drivers/pci/endpoint/pci-epc-core.c | 2 +- drivers/pci/endpoint/pci-epf-core.c | 4 ++-- drivers/pci/hotplug/acpiphp_glue.c | 2 +- drivers/pci/hotplug/cpqphp_ctrl.c | 4 ++-- drivers/pci/hotplug/ibmphp.h | 4 ++-- drivers/pci/hotplug/shpchp_hpc.c | 2 +- drivers/pci/pci-driver.c | 2 +- drivers/pci/pcie/aer.c | 2 +- drivers/pci/quirks.c | 2 +- 12 files changed, 15 insertions(+), 15 deletions(-) diff --git a/drivers/pci/controller/pci-xgene-msi.c b/drivers/pci/controller/pci-xgene-msi.c index b7a8e062fcc5..c50ff279903c 100644 --- a/drivers/pci/controller/pci-xgene-msi.c +++ b/drivers/pci/controller/pci-xgene-msi.c @@ -302,7 +302,7 @@ static void xgene_msi_isr(struct irq_desc *desc) /* * MSIINTn (n is 0..F) indicates if there is a pending MSI interrupt - * If bit x of this register is set (x is 0..7), one or more interupts + * If bit x of this register is set (x is 0..7), one or more interrupts * corresponding to MSInIRx is set. */ grp_select = xgene_msi_int_read(xgene_msi, msi_grp); diff --git a/drivers/pci/controller/pcie-brcmstb.c b/drivers/pci/controller/pcie-brcmstb.c index cc30215f5a43..1fc7bd49a7ad 100644 --- a/drivers/pci/controller/pcie-brcmstb.c +++ b/drivers/pci/controller/pcie-brcmstb.c @@ -145,7 +145,7 @@ #define BRCM_INT_PCI_MSI_LEGACY_NR 8 #define BRCM_INT_PCI_MSI_SHIFT 0 -/* MSI target adresses */ +/* MSI target addresses */ #define BRCM_MSI_TARGET_ADDR_LT_4GB 0x0fffffffcULL #define BRCM_MSI_TARGET_ADDR_GT_4GB 0xffffffffcULL diff --git a/drivers/pci/controller/pcie-iproc.c b/drivers/pci/controller/pcie-iproc.c index 30ac5fbefbbf..36b9d2c46cfa 100644 --- a/drivers/pci/controller/pcie-iproc.c +++ b/drivers/pci/controller/pcie-iproc.c @@ -249,7 +249,7 @@ enum iproc_pcie_reg { /* * To hold the address of the register where the MSI writes are - * programed. When ARM GICv3 ITS is used, this should be programmed + * programmed. When ARM GICv3 ITS is used, this should be programmed * with the address of the GITS_TRANSLATER register. */ IPROC_PCIE_MSI_ADDR_LO, diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c index ecbb0fb3b653..38621558d397 100644 --- a/drivers/pci/endpoint/pci-epc-core.c +++ b/drivers/pci/endpoint/pci-epc-core.c @@ -700,7 +700,7 @@ EXPORT_SYMBOL_GPL(pci_epc_linkup); /** * pci_epc_init_notify() - Notify the EPF device that EPC device's core * initialization is completed. - * @epc: the EPC device whose core initialization is completeds + * @epc: the EPC device whose core initialization is completed * * Invoke to Notify the EPF device that the EPC device's initialization * is completed. diff --git a/drivers/pci/endpoint/pci-epf-core.c b/drivers/pci/endpoint/pci-epf-core.c index 8aea16380870..9ed556936f48 100644 --- a/drivers/pci/endpoint/pci-epf-core.c +++ b/drivers/pci/endpoint/pci-epf-core.c @@ -224,7 +224,7 @@ EXPORT_SYMBOL_GPL(pci_epf_add_vepf); * be removed * @epf_vf: the virtual EP function to be removed * - * Invoke to remove a virtual endpoint function from the physcial endpoint + * Invoke to remove a virtual endpoint function from the physical endpoint * function. */ void pci_epf_remove_vepf(struct pci_epf *epf_pf, struct pci_epf *epf_vf) @@ -432,7 +432,7 @@ EXPORT_SYMBOL_GPL(pci_epf_destroy); /** * pci_epf_create() - create a new PCI EPF device * @name: the name of the PCI EPF device. This name will be used to bind the - * the EPF device to a EPF driver + * EPF device to a EPF driver * * Invoke to create a new PCI EPF device by providing the name of the function * device. diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index f031302ad401..12f4b351be67 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -22,7 +22,7 @@ * when the bridge is scanned and it loses a refcount when the bridge * is removed. * - When a P2P bridge is present, we elevate the refcount on the subordinate - * bus. It loses the refcount when the the driver unloads. + * bus. It loses the refcount when the driver unloads. */ #define pr_fmt(fmt) "acpiphp_glue: " fmt diff --git a/drivers/pci/hotplug/cpqphp_ctrl.c b/drivers/pci/hotplug/cpqphp_ctrl.c index 1b26ca0b3701..ed7b58eb64d2 100644 --- a/drivers/pci/hotplug/cpqphp_ctrl.c +++ b/drivers/pci/hotplug/cpqphp_ctrl.c @@ -519,7 +519,7 @@ error: * @head: list to search * @size: size of node to find, must be a power of two. * - * Description: This function sorts the resource list by size and then returns + * Description: This function sorts the resource list by size and then * returns the first node of "size" length that is not in the ISA aliasing * window. If it finds a node larger than "size" it will split it up. */ @@ -1202,7 +1202,7 @@ static u8 set_controller_speed(struct controller *ctrl, u8 adapter_speed, u8 hp_ mdelay(5); - /* Reenable interrupts */ + /* Re-enable interrupts */ writel(0, ctrl->hpc_reg + INT_MASK); pci_write_config_byte(ctrl->pci_dev, 0x41, reg); diff --git a/drivers/pci/hotplug/ibmphp.h b/drivers/pci/hotplug/ibmphp.h index e90a4ebf6550..0399c60d2ec1 100644 --- a/drivers/pci/hotplug/ibmphp.h +++ b/drivers/pci/hotplug/ibmphp.h @@ -352,7 +352,7 @@ struct resource_node { u32 len; int type; /* MEM, IO, PFMEM */ u8 fromMem; /* this is to indicate that the range is from - * from the Memory bucket rather than from PFMem */ + * the Memory bucket rather than from PFMem */ struct resource_node *next; struct resource_node *nextRange; /* for the other mem range on bus */ }; @@ -736,7 +736,7 @@ struct controller { int ibmphp_init_devno(struct slot **); /* This function is called from EBDA, so we need it not be static */ int ibmphp_do_disable_slot(struct slot *slot_cur); -int ibmphp_update_slot_info(struct slot *); /* This function is called from HPC, so we need it to not be be static */ +int ibmphp_update_slot_info(struct slot *); /* This function is called from HPC, so we need it to not be static */ int ibmphp_configure_card(struct pci_func *, u8); int ibmphp_unconfigure_card(struct slot **, int); extern const struct hotplug_slot_ops ibmphp_hotplug_slot_ops; diff --git a/drivers/pci/hotplug/shpchp_hpc.c b/drivers/pci/hotplug/shpchp_hpc.c index 9e3b27744305..bd7557ca4910 100644 --- a/drivers/pci/hotplug/shpchp_hpc.c +++ b/drivers/pci/hotplug/shpchp_hpc.c @@ -295,7 +295,7 @@ static int shpc_write_cmd(struct slot *slot, u8 t_slot, u8 cmd) mutex_lock(&slot->ctrl->cmd_lock); if (!shpc_poll_ctrl_busy(ctrl)) { - /* After 1 sec and and the controller is still busy */ + /* After 1 sec and the controller is still busy */ ctrl_err(ctrl, "Controller is still busy after 1 sec\n"); retval = -EBUSY; goto out; diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 2761ab86490d..df3bd7b40542 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -576,7 +576,7 @@ static int pci_pm_reenable_device(struct pci_dev *pci_dev) { int retval; - /* if the device was enabled before suspend, reenable */ + /* if the device was enabled before suspend, re-enable */ retval = pci_reenable_device(pci_dev); /* * if the device was busmaster before the suspend, make it busmaster diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index 9784fdcf3006..9fa1f97e5b27 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -57,7 +57,7 @@ struct aer_stats { * "as seen by this device". Note that this may mean that if an * end point is causing problems, the AER counters may increment * at its link partner (e.g. root port) because the errors will be - * "seen" by the link partner and not the the problematic end point + * "seen" by the link partner and not the problematic end point * itself (which may report all counters as 0 as it never saw any * problems). */ diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 4537d1ea14fd..881c5d7c3d02 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -2700,7 +2700,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, * then the device can't use INTx interrupts. Tegra's PCIe root ports don't * generate MSI interrupts for PME and AER events instead only INTx interrupts * are generated. Though Tegra's PCIe root ports can generate MSI interrupts - * for other events, since PCIe specificiation doesn't support using a mix of + * for other events, since PCIe specification doesn't support using a mix of * INTx and MSI/MSI-X, it is required to disable MSI interrupts to avoid port * service drivers registering their respective ISRs for MSIs. */ From 9bf3d20331295b1ecb81f4ed9ef358c51699a050 Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Fri, 8 Oct 2021 17:38:20 +0800 Subject: [PATCH 192/587] quota: check block number when reading the block in quota file The block number in the quota tree on disk should be smaller than the v2_disk_dqinfo.dqi_blocks. If the quota file was corrupted, we may be allocating an 'allocated' block and that would lead to a loop in a tree, which will probably trigger oops later. This patch adds a check for the block number in the quota tree to prevent such potential issue. Link: https://lore.kernel.org/r/20211008093821.1001186-2-yi.zhang@huawei.com Signed-off-by: Zhang Yi Cc: stable@kernel.org Signed-off-by: Jan Kara --- fs/quota/quota_tree.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/fs/quota/quota_tree.c b/fs/quota/quota_tree.c index d3e995e1046f..583b7f7715f9 100644 --- a/fs/quota/quota_tree.c +++ b/fs/quota/quota_tree.c @@ -479,6 +479,13 @@ static int remove_tree(struct qtree_mem_dqinfo *info, struct dquot *dquot, goto out_buf; } newblk = le32_to_cpu(ref[get_index(info, dquot->dq_id, depth)]); + if (newblk < QT_TREEOFF || newblk >= info->dqi_blocks) { + quota_error(dquot->dq_sb, "Getting block too big (%u >= %u)", + newblk, info->dqi_blocks); + ret = -EUCLEAN; + goto out_buf; + } + if (depth == info->dqi_qtree_depth - 1) { ret = free_dqentry(info, dquot, newblk); newblk = 0; @@ -578,6 +585,13 @@ static loff_t find_tree_dqentry(struct qtree_mem_dqinfo *info, blk = le32_to_cpu(ref[get_index(info, dquot->dq_id, depth)]); if (!blk) /* No reference? */ goto out_buf; + if (blk < QT_TREEOFF || blk >= info->dqi_blocks) { + quota_error(dquot->dq_sb, "Getting block too big (%u >= %u)", + blk, info->dqi_blocks); + ret = -EUCLEAN; + goto out_buf; + } + if (depth < info->dqi_qtree_depth - 1) ret = find_tree_dqentry(info, dquot, blk, depth+1); else From d0e36a62bd4c60c09acc40e06ba4831a4d0bc75b Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Fri, 8 Oct 2021 17:38:21 +0800 Subject: [PATCH 193/587] quota: correct error number in free_dqentry() Fix the error path in free_dqentry(), pass out the error number if the block to free is not correct. Fixes: 1ccd14b9c271 ("quota: Split off quota tree handling into a separate file") Link: https://lore.kernel.org/r/20211008093821.1001186-3-yi.zhang@huawei.com Signed-off-by: Zhang Yi Cc: stable@kernel.org Signed-off-by: Jan Kara --- fs/quota/quota_tree.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/quota/quota_tree.c b/fs/quota/quota_tree.c index 583b7f7715f9..5f2405994280 100644 --- a/fs/quota/quota_tree.c +++ b/fs/quota/quota_tree.c @@ -414,6 +414,7 @@ static int free_dqentry(struct qtree_mem_dqinfo *info, struct dquot *dquot, quota_error(dquot->dq_sb, "Quota structure has offset to " "other block (%u) than it should (%u)", blk, (uint)(dquot->dq_off >> info->dqi_blocksize_bits)); + ret = -EIO; goto out_buf; } ret = read_blk(info, blk, buf); From df7c4a8c1b47dc250d5525e68e785d9e65705e10 Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Fri, 8 Oct 2021 18:35:22 +0200 Subject: [PATCH 194/587] dt-bindings: i2c: Add Apple I2C controller bindings The Apple I2C controller is based on the PASemi I2C controller. It is present on Apple SoCs such as the M1. Reviewed-by: Arnd Bergmann Reviewed-by: Rob Herring Signed-off-by: Sven Peter Acked-by: Olof Johansson Tested-by: Christian Zigotzky Signed-off-by: Wolfram Sang --- .../devicetree/bindings/i2c/apple,i2c.yaml | 61 +++++++++++++++++++ 1 file changed, 61 insertions(+) create mode 100644 Documentation/devicetree/bindings/i2c/apple,i2c.yaml diff --git a/Documentation/devicetree/bindings/i2c/apple,i2c.yaml b/Documentation/devicetree/bindings/i2c/apple,i2c.yaml new file mode 100644 index 000000000000..22fc8483256f --- /dev/null +++ b/Documentation/devicetree/bindings/i2c/apple,i2c.yaml @@ -0,0 +1,61 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: "http://devicetree.org/schemas/i2c/apple,i2c.yaml#" +$schema: "http://devicetree.org/meta-schemas/core.yaml#" + +title: Apple/PASemi I2C controller + +maintainers: + - Sven Peter + +description: | + Apple SoCs such as the M1 come with a I2C controller based on the one found + in machines with P. A. Semi's PWRficient processors. + The bus is used to communicate with e.g. USB PD chips or the speaker + amp. + +allOf: + - $ref: /schemas/i2c/i2c-controller.yaml# + +properties: + compatible: + enum: + - apple,t8103-i2c + - apple,i2c + + reg: + maxItems: 1 + + clocks: + items: + - description: I2C bus reference clock + + interrupts: + maxItems: 1 + + clock-frequency: + description: | + Desired I2C bus clock frequency in Hz. If not specified, 100 kHz will be + used. This frequency is generated by dividing the reference clock. + Allowed values are between ref_clk/(16*4) and ref_clk/(16*255). + +required: + - compatible + - reg + - clocks + - interrupts + +unevaluatedProperties: false + +examples: + - | + i2c@35010000 { + compatible = "apple,t8103-i2c"; + reg = <0x35010000 0x4000>; + interrupt-parent = <&aic>; + interrupts = <0 627 4>; + clocks = <&ref_clk>; + #address-cells = <1>; + #size-cells = <0>; + }; From 3a7442ac1d1bfbe17f7c6cbc69756c529d7dda14 Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Fri, 8 Oct 2021 18:35:23 +0200 Subject: [PATCH 195/587] i2c: pasemi: Use io{read,write}32 In preparation for splitting this driver up into a platform_driver and a pci_driver, replace outl/inl usage with pci_iomap and ioread32/iowrite32. Reviewed-by: Arnd Bergmann Signed-off-by: Sven Peter Acked-by: Olof Johansson Tested-by: Christian Zigotzky Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-pasemi.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/drivers/i2c/busses/i2c-pasemi.c b/drivers/i2c/busses/i2c-pasemi.c index 20f2772c0e79..39fcc584264a 100644 --- a/drivers/i2c/busses/i2c-pasemi.c +++ b/drivers/i2c/busses/i2c-pasemi.c @@ -20,6 +20,7 @@ static struct pci_driver pasemi_smb_driver; struct pasemi_smbus { struct pci_dev *dev; struct i2c_adapter adapter; + void __iomem *ioaddr; unsigned long base; int size; }; @@ -53,13 +54,13 @@ static inline void reg_write(struct pasemi_smbus *smbus, int reg, int val) { dev_dbg(&smbus->dev->dev, "smbus write reg %lx val %08x\n", smbus->base + reg, val); - outl(val, smbus->base + reg); + iowrite32(val, smbus->ioaddr + reg); } static inline int reg_read(struct pasemi_smbus *smbus, int reg) { int ret; - ret = inl(smbus->base + reg); + ret = ioread32(smbus->ioaddr + reg); dev_dbg(&smbus->dev->dev, "smbus read reg %lx val %08x\n", smbus->base + reg, ret); return ret; @@ -351,6 +352,12 @@ static int pasemi_smb_probe(struct pci_dev *dev, goto out_kfree; } + smbus->ioaddr = pci_iomap(dev, 0, 0); + if (!smbus->ioaddr) { + error = -EBUSY; + goto out_release_region; + } + smbus->adapter.owner = THIS_MODULE; snprintf(smbus->adapter.name, sizeof(smbus->adapter.name), "PA Semi SMBus adapter at 0x%lx", smbus->base); @@ -366,12 +373,14 @@ static int pasemi_smb_probe(struct pci_dev *dev, error = i2c_add_adapter(&smbus->adapter); if (error) - goto out_release_region; + goto out_ioport_unmap; pci_set_drvdata(dev, smbus); return 0; + out_ioport_unmap: + pci_iounmap(dev, smbus->ioaddr); out_release_region: release_region(smbus->base, smbus->size); out_kfree: @@ -384,6 +393,7 @@ static void pasemi_smb_remove(struct pci_dev *dev) struct pasemi_smbus *smbus = pci_get_drvdata(dev); i2c_del_adapter(&smbus->adapter); + pci_iounmap(dev, smbus->ioaddr); release_region(smbus->base, smbus->size); kfree(smbus); } From 07e820d4fcb000d5dd72218f4334f2a210f75a81 Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Fri, 8 Oct 2021 18:35:24 +0200 Subject: [PATCH 196/587] i2c: pasemi: Use dev_name instead of port number Right now the i2c adapter name includes the port number which can indirectly be used to identify the device. Replace that with dev_name to directly identify the device and to also allow this to work correctly once we add platform support. Signed-off-by: Sven Peter Acked-by: Olof Johansson Tested-by: Christian Zigotzky Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-pasemi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-pasemi.c b/drivers/i2c/busses/i2c-pasemi.c index 39fcc584264a..ca5a86cf53f1 100644 --- a/drivers/i2c/busses/i2c-pasemi.c +++ b/drivers/i2c/busses/i2c-pasemi.c @@ -360,7 +360,7 @@ static int pasemi_smb_probe(struct pci_dev *dev, smbus->adapter.owner = THIS_MODULE; snprintf(smbus->adapter.name, sizeof(smbus->adapter.name), - "PA Semi SMBus adapter at 0x%lx", smbus->base); + "PA Semi SMBus adapter (%s)", dev_name(smbus->dev)); smbus->adapter.class = I2C_CLASS_HWMON | I2C_CLASS_SPD; smbus->adapter.algo = &smbus_algorithm; smbus->adapter.algo_data = smbus; From c06f50ed36cc0aeaf124bee0d676a21315aea5e7 Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Fri, 8 Oct 2021 18:35:25 +0200 Subject: [PATCH 197/587] i2c: pasemi: Remove usage of pci_dev Prepare to create a platform driver by removing all usages of pci_dev we can. Reviewed-by: Arnd Bergmann Signed-off-by: Sven Peter Acked-by: Olof Johansson Tested-by: Christian Zigotzky Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-pasemi.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/i2c/busses/i2c-pasemi.c b/drivers/i2c/busses/i2c-pasemi.c index ca5a86cf53f1..a018e9376023 100644 --- a/drivers/i2c/busses/i2c-pasemi.c +++ b/drivers/i2c/busses/i2c-pasemi.c @@ -18,7 +18,7 @@ static struct pci_driver pasemi_smb_driver; struct pasemi_smbus { - struct pci_dev *dev; + struct device *dev; struct i2c_adapter adapter; void __iomem *ioaddr; unsigned long base; @@ -52,7 +52,7 @@ struct pasemi_smbus { static inline void reg_write(struct pasemi_smbus *smbus, int reg, int val) { - dev_dbg(&smbus->dev->dev, "smbus write reg %lx val %08x\n", + dev_dbg(smbus->dev, "smbus write reg %lx val %08x\n", smbus->base + reg, val); iowrite32(val, smbus->ioaddr + reg); } @@ -61,7 +61,7 @@ static inline int reg_read(struct pasemi_smbus *smbus, int reg) { int ret; ret = ioread32(smbus->ioaddr + reg); - dev_dbg(&smbus->dev->dev, "smbus read reg %lx val %08x\n", + dev_dbg(smbus->dev, "smbus read reg %lx val %08x\n", smbus->base + reg, ret); return ret; } @@ -94,7 +94,7 @@ static int pasemi_smb_waitready(struct pasemi_smbus *smbus) return -ENXIO; if (timeout < 0) { - dev_warn(&smbus->dev->dev, "Timeout, status 0x%08x\n", status); + dev_warn(smbus->dev, "Timeout, status 0x%08x\n", status); reg_write(smbus, REG_SMSTA, status); return -ETIME; } @@ -342,7 +342,7 @@ static int pasemi_smb_probe(struct pci_dev *dev, if (!smbus) return -ENOMEM; - smbus->dev = dev; + smbus->dev = &dev->dev; smbus->base = pci_resource_start(dev, 0); smbus->size = pci_resource_len(dev, 0); @@ -366,7 +366,7 @@ static int pasemi_smb_probe(struct pci_dev *dev, smbus->adapter.algo_data = smbus; /* set up the sysfs linkage to our parent device */ - smbus->adapter.dev.parent = &dev->dev; + smbus->adapter.dev.parent = smbus->dev; reg_write(smbus, REG_CTL, (CTL_MTR | CTL_MRR | (CLK_100K_DIV & CTL_CLK_M))); From 6adb00c7f0edc081f21e0abd4d7eebe99589a287 Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Fri, 8 Oct 2021 18:35:26 +0200 Subject: [PATCH 198/587] i2c: pasemi: Split off common probing code Split off common probing code that will be used by both the PCI and the platform device. Reviewed-by: Arnd Bergmann Signed-off-by: Sven Peter Acked-by: Olof Johansson Tested-by: Christian Zigotzky Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-pasemi.c | 39 +++++++++++++++++++++------------ 1 file changed, 25 insertions(+), 14 deletions(-) diff --git a/drivers/i2c/busses/i2c-pasemi.c b/drivers/i2c/busses/i2c-pasemi.c index a018e9376023..baf338149673 100644 --- a/drivers/i2c/busses/i2c-pasemi.c +++ b/drivers/i2c/busses/i2c-pasemi.c @@ -329,6 +329,30 @@ static const struct i2c_algorithm smbus_algorithm = { .functionality = pasemi_smb_func, }; +static int pasemi_i2c_common_probe(struct pasemi_smbus *smbus) +{ + int error; + + smbus->adapter.owner = THIS_MODULE; + snprintf(smbus->adapter.name, sizeof(smbus->adapter.name), + "PA Semi SMBus adapter (%s)", dev_name(smbus->dev)); + smbus->adapter.class = I2C_CLASS_HWMON | I2C_CLASS_SPD; + smbus->adapter.algo = &smbus_algorithm; + smbus->adapter.algo_data = smbus; + + /* set up the sysfs linkage to our parent device */ + smbus->adapter.dev.parent = smbus->dev; + + reg_write(smbus, REG_CTL, (CTL_MTR | CTL_MRR | + (CLK_100K_DIV & CTL_CLK_M))); + + error = i2c_add_adapter(&smbus->adapter); + if (error) + return error; + + return 0; +} + static int pasemi_smb_probe(struct pci_dev *dev, const struct pci_device_id *id) { @@ -358,20 +382,7 @@ static int pasemi_smb_probe(struct pci_dev *dev, goto out_release_region; } - smbus->adapter.owner = THIS_MODULE; - snprintf(smbus->adapter.name, sizeof(smbus->adapter.name), - "PA Semi SMBus adapter (%s)", dev_name(smbus->dev)); - smbus->adapter.class = I2C_CLASS_HWMON | I2C_CLASS_SPD; - smbus->adapter.algo = &smbus_algorithm; - smbus->adapter.algo_data = smbus; - - /* set up the sysfs linkage to our parent device */ - smbus->adapter.dev.parent = smbus->dev; - - reg_write(smbus, REG_CTL, (CTL_MTR | CTL_MRR | - (CLK_100K_DIV & CTL_CLK_M))); - - error = i2c_add_adapter(&smbus->adapter); + int error = pasemi_i2c_common_probe(smbus); if (error) goto out_ioport_unmap; From 9bc5f4f660ff3e37113847d749d43fafbadec629 Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Fri, 8 Oct 2021 18:35:27 +0200 Subject: [PATCH 199/587] i2c: pasemi: Split pci driver to its own file Split off the PCI driver so that we can reuse common code for the platform driver. Reviewed-by: Arnd Bergmann Signed-off-by: Sven Peter Acked-by: Olof Johansson Tested-by: Christian Zigotzky Signed-off-by: Wolfram Sang --- drivers/i2c/busses/Makefile | 1 + .../{i2c-pasemi.c => i2c-pasemi-core.c} | 88 +---------------- drivers/i2c/busses/i2c-pasemi-core.h | 19 ++++ drivers/i2c/busses/i2c-pasemi-pci.c | 96 +++++++++++++++++++ 4 files changed, 118 insertions(+), 86 deletions(-) rename drivers/i2c/busses/{i2c-pasemi.c => i2c-pasemi-core.c} (81%) create mode 100644 drivers/i2c/busses/i2c-pasemi-core.h create mode 100644 drivers/i2c/busses/i2c-pasemi-pci.c diff --git a/drivers/i2c/busses/Makefile b/drivers/i2c/busses/Makefile index 1336b04f40e2..0ab1b4cb2228 100644 --- a/drivers/i2c/busses/Makefile +++ b/drivers/i2c/busses/Makefile @@ -84,6 +84,7 @@ obj-$(CONFIG_I2C_NPCM7XX) += i2c-npcm7xx.o obj-$(CONFIG_I2C_OCORES) += i2c-ocores.o obj-$(CONFIG_I2C_OMAP) += i2c-omap.o obj-$(CONFIG_I2C_OWL) += i2c-owl.o +i2c-pasemi-objs := i2c-pasemi-core.o i2c-pasemi-pci.o obj-$(CONFIG_I2C_PASEMI) += i2c-pasemi.o obj-$(CONFIG_I2C_PCA_PLATFORM) += i2c-pca-platform.o obj-$(CONFIG_I2C_PNX) += i2c-pnx.o diff --git a/drivers/i2c/busses/i2c-pasemi.c b/drivers/i2c/busses/i2c-pasemi-core.c similarity index 81% rename from drivers/i2c/busses/i2c-pasemi.c rename to drivers/i2c/busses/i2c-pasemi-core.c index baf338149673..d1cab11a4d50 100644 --- a/drivers/i2c/busses/i2c-pasemi.c +++ b/drivers/i2c/busses/i2c-pasemi-core.c @@ -15,15 +15,7 @@ #include #include -static struct pci_driver pasemi_smb_driver; - -struct pasemi_smbus { - struct device *dev; - struct i2c_adapter adapter; - void __iomem *ioaddr; - unsigned long base; - int size; -}; +#include "i2c-pasemi-core.h" /* Register offsets */ #define REG_MTXFIFO 0x00 @@ -329,7 +321,7 @@ static const struct i2c_algorithm smbus_algorithm = { .functionality = pasemi_smb_func, }; -static int pasemi_i2c_common_probe(struct pasemi_smbus *smbus) +int pasemi_i2c_common_probe(struct pasemi_smbus *smbus) { int error; @@ -352,79 +344,3 @@ static int pasemi_i2c_common_probe(struct pasemi_smbus *smbus) return 0; } - -static int pasemi_smb_probe(struct pci_dev *dev, - const struct pci_device_id *id) -{ - struct pasemi_smbus *smbus; - int error; - - if (!(pci_resource_flags(dev, 0) & IORESOURCE_IO)) - return -ENODEV; - - smbus = kzalloc(sizeof(struct pasemi_smbus), GFP_KERNEL); - if (!smbus) - return -ENOMEM; - - smbus->dev = &dev->dev; - smbus->base = pci_resource_start(dev, 0); - smbus->size = pci_resource_len(dev, 0); - - if (!request_region(smbus->base, smbus->size, - pasemi_smb_driver.name)) { - error = -EBUSY; - goto out_kfree; - } - - smbus->ioaddr = pci_iomap(dev, 0, 0); - if (!smbus->ioaddr) { - error = -EBUSY; - goto out_release_region; - } - - int error = pasemi_i2c_common_probe(smbus); - if (error) - goto out_ioport_unmap; - - pci_set_drvdata(dev, smbus); - - return 0; - - out_ioport_unmap: - pci_iounmap(dev, smbus->ioaddr); - out_release_region: - release_region(smbus->base, smbus->size); - out_kfree: - kfree(smbus); - return error; -} - -static void pasemi_smb_remove(struct pci_dev *dev) -{ - struct pasemi_smbus *smbus = pci_get_drvdata(dev); - - i2c_del_adapter(&smbus->adapter); - pci_iounmap(dev, smbus->ioaddr); - release_region(smbus->base, smbus->size); - kfree(smbus); -} - -static const struct pci_device_id pasemi_smb_ids[] = { - { PCI_DEVICE(0x1959, 0xa003) }, - { 0, } -}; - -MODULE_DEVICE_TABLE(pci, pasemi_smb_ids); - -static struct pci_driver pasemi_smb_driver = { - .name = "i2c-pasemi", - .id_table = pasemi_smb_ids, - .probe = pasemi_smb_probe, - .remove = pasemi_smb_remove, -}; - -module_pci_driver(pasemi_smb_driver); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR ("Olof Johansson "); -MODULE_DESCRIPTION("PA Semi PWRficient SMBus driver"); diff --git a/drivers/i2c/busses/i2c-pasemi-core.h b/drivers/i2c/busses/i2c-pasemi-core.h new file mode 100644 index 000000000000..7acc33de6ce1 --- /dev/null +++ b/drivers/i2c/busses/i2c-pasemi-core.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include +#include +#include +#include +#include +#include +#include +#include + +struct pasemi_smbus { + struct device *dev; + struct i2c_adapter adapter; + void __iomem *ioaddr; + unsigned long base; + int size; +}; + +int pasemi_i2c_common_probe(struct pasemi_smbus *smbus); diff --git a/drivers/i2c/busses/i2c-pasemi-pci.c b/drivers/i2c/busses/i2c-pasemi-pci.c new file mode 100644 index 000000000000..644656e28012 --- /dev/null +++ b/drivers/i2c/busses/i2c-pasemi-pci.c @@ -0,0 +1,96 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2006-2007 PA Semi, Inc + * + * SMBus host driver for PA Semi PWRficient + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "i2c-pasemi-core.h" + +static struct pci_driver pasemi_smb_pci_driver; + +static int pasemi_smb_pci_probe(struct pci_dev *dev, + const struct pci_device_id *id) +{ + struct pasemi_smbus *smbus; + int error; + + if (!(pci_resource_flags(dev, 0) & IORESOURCE_IO)) + return -ENODEV; + + smbus = kzalloc(sizeof(struct pasemi_smbus), GFP_KERNEL); + if (!smbus) + return -ENOMEM; + + smbus->dev = &dev->dev; + smbus->base = pci_resource_start(dev, 0); + smbus->size = pci_resource_len(dev, 0); + + if (!request_region(smbus->base, smbus->size, + pasemi_smb_pci_driver.name)) { + error = -EBUSY; + goto out_kfree; + } + + smbus->ioaddr = pci_iomap(dev, 0, 0); + if (!smbus->ioaddr) { + error = -EBUSY; + goto out_release_region; + } + + error = pasemi_i2c_common_probe(smbus); + if (error) + goto out_ioport_unmap; + + pci_set_drvdata(dev, smbus); + + return 0; + + out_ioport_unmap: + pci_iounmap(dev, smbus->ioaddr); + out_release_region: + release_region(smbus->base, smbus->size); + out_kfree: + kfree(smbus); + return error; +} + +static void pasemi_smb_pci_remove(struct pci_dev *dev) +{ + struct pasemi_smbus *smbus = pci_get_drvdata(dev); + + i2c_del_adapter(&smbus->adapter); + pci_iounmap(dev, smbus->ioaddr); + release_region(smbus->base, smbus->size); + kfree(smbus); +} + +static const struct pci_device_id pasemi_smb_pci_ids[] = { + { PCI_DEVICE(0x1959, 0xa003) }, + { 0, } +}; + +MODULE_DEVICE_TABLE(pci, pasemi_smb_pci_ids); + +static struct pci_driver pasemi_smb_pci_driver = { + .name = "i2c-pasemi", + .id_table = pasemi_smb_pci_ids, + .probe = pasemi_smb_pci_probe, + .remove = pasemi_smb_pci_remove, +}; + +module_pci_driver(pasemi_smb_pci_driver); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Olof Johansson "); +MODULE_DESCRIPTION("PA Semi PWRficient SMBus driver"); From 1a62668cefdb0f8930e5ac47196abe51365ad76f Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Fri, 8 Oct 2021 18:35:28 +0200 Subject: [PATCH 200/587] i2c: pasemi: Move common reset code to own function Split out common reset call to its own function so that we can later add support for selecting the clock frequency and an additional enable bit found in newer revisions. Reviewed-by: Arnd Bergmann Signed-off-by: Sven Peter Acked-by: Olof Johansson Tested-by: Christian Zigotzky Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-pasemi-core.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/i2c/busses/i2c-pasemi-core.c b/drivers/i2c/busses/i2c-pasemi-core.c index d1cab11a4d50..232587c70a38 100644 --- a/drivers/i2c/busses/i2c-pasemi-core.c +++ b/drivers/i2c/busses/i2c-pasemi-core.c @@ -61,6 +61,12 @@ static inline int reg_read(struct pasemi_smbus *smbus, int reg) #define TXFIFO_WR(smbus, reg) reg_write((smbus), REG_MTXFIFO, (reg)) #define RXFIFO_RD(smbus) reg_read((smbus), REG_MRXFIFO) +static void pasemi_reset(struct pasemi_smbus *smbus) +{ + reg_write(smbus, REG_CTL, (CTL_MTR | CTL_MRR | + (CLK_100K_DIV & CTL_CLK_M))); +} + static void pasemi_smb_clear(struct pasemi_smbus *smbus) { unsigned int status; @@ -135,8 +141,7 @@ static int pasemi_i2c_xfer_msg(struct i2c_adapter *adapter, return 0; reset_out: - reg_write(smbus, REG_CTL, (CTL_MTR | CTL_MRR | - (CLK_100K_DIV & CTL_CLK_M))); + pasemi_reset(smbus); return err; } @@ -302,8 +307,7 @@ static int pasemi_smb_xfer(struct i2c_adapter *adapter, return 0; reset_out: - reg_write(smbus, REG_CTL, (CTL_MTR | CTL_MRR | - (CLK_100K_DIV & CTL_CLK_M))); + pasemi_reset(smbus); return err; } @@ -335,8 +339,7 @@ int pasemi_i2c_common_probe(struct pasemi_smbus *smbus) /* set up the sysfs linkage to our parent device */ smbus->adapter.dev.parent = smbus->dev; - reg_write(smbus, REG_CTL, (CTL_MTR | CTL_MRR | - (CLK_100K_DIV & CTL_CLK_M))); + pasemi_reset(smbus); error = i2c_add_adapter(&smbus->adapter); if (error) From fd664ab2319fb89cba5a522995e806eb26748af6 Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Fri, 8 Oct 2021 18:35:29 +0200 Subject: [PATCH 201/587] i2c: pasemi: Allow to configure bus frequency Right now the bus frequency has always been hardcoded as 100 KHz with the specific reference clock used in the PASemi PCI controllers. Make this configurable to prepare for the platform driver. Reviewed-by: Arnd Bergmann Signed-off-by: Sven Peter Acked-by: Olof Johansson Tested-by: Christian Zigotzky Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-pasemi-core.c | 8 +++----- drivers/i2c/busses/i2c-pasemi-core.h | 1 + drivers/i2c/busses/i2c-pasemi-pci.c | 4 ++++ 3 files changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/i2c/busses/i2c-pasemi-core.c b/drivers/i2c/busses/i2c-pasemi-core.c index 232587c70a38..9fb8fac53f2b 100644 --- a/drivers/i2c/busses/i2c-pasemi-core.c +++ b/drivers/i2c/busses/i2c-pasemi-core.c @@ -39,9 +39,6 @@ #define CTL_MTR 0x00000200 #define CTL_CLK_M 0x000000ff -#define CLK_100K_DIV 84 -#define CLK_400K_DIV 21 - static inline void reg_write(struct pasemi_smbus *smbus, int reg, int val) { dev_dbg(smbus->dev, "smbus write reg %lx val %08x\n", @@ -63,8 +60,9 @@ static inline int reg_read(struct pasemi_smbus *smbus, int reg) static void pasemi_reset(struct pasemi_smbus *smbus) { - reg_write(smbus, REG_CTL, (CTL_MTR | CTL_MRR | - (CLK_100K_DIV & CTL_CLK_M))); + u32 val = (CTL_MTR | CTL_MRR | (smbus->clk_div & CTL_CLK_M)); + + reg_write(smbus, REG_CTL, val); } static void pasemi_smb_clear(struct pasemi_smbus *smbus) diff --git a/drivers/i2c/busses/i2c-pasemi-core.h b/drivers/i2c/busses/i2c-pasemi-core.h index 7acc33de6ce1..30a7990825ef 100644 --- a/drivers/i2c/busses/i2c-pasemi-core.h +++ b/drivers/i2c/busses/i2c-pasemi-core.h @@ -14,6 +14,7 @@ struct pasemi_smbus { void __iomem *ioaddr; unsigned long base; int size; + unsigned int clk_div; }; int pasemi_i2c_common_probe(struct pasemi_smbus *smbus); diff --git a/drivers/i2c/busses/i2c-pasemi-pci.c b/drivers/i2c/busses/i2c-pasemi-pci.c index 644656e28012..96585bbf8c24 100644 --- a/drivers/i2c/busses/i2c-pasemi-pci.c +++ b/drivers/i2c/busses/i2c-pasemi-pci.c @@ -17,6 +17,9 @@ #include "i2c-pasemi-core.h" +#define CLK_100K_DIV 84 +#define CLK_400K_DIV 21 + static struct pci_driver pasemi_smb_pci_driver; static int pasemi_smb_pci_probe(struct pci_dev *dev, @@ -35,6 +38,7 @@ static int pasemi_smb_pci_probe(struct pci_dev *dev, smbus->dev = &dev->dev; smbus->base = pci_resource_start(dev, 0); smbus->size = pci_resource_len(dev, 0); + smbus->clk_div = CLK_100K_DIV; if (!request_region(smbus->base, smbus->size, pasemi_smb_pci_driver.name)) { From a2c34bfd2c580f1732fc60e2af4aa439dde285be Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Fri, 8 Oct 2021 18:35:30 +0200 Subject: [PATCH 202/587] i2c: pasemi: Refactor _probe to use devm_* Using managed device resources means there's nothing left to be done in pasemi_smb_pci_remove and also allows to remove base and size from struct pasemi_smbus. Reviewed-by: Arnd Bergmann Signed-off-by: Sven Peter Acked-by: Olof Johansson Tested-by: Christian Zigotzky Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-pasemi-core.c | 8 ++--- drivers/i2c/busses/i2c-pasemi-core.h | 2 -- drivers/i2c/busses/i2c-pasemi-pci.c | 45 ++++++++-------------------- 3 files changed, 15 insertions(+), 40 deletions(-) diff --git a/drivers/i2c/busses/i2c-pasemi-core.c b/drivers/i2c/busses/i2c-pasemi-core.c index 9fb8fac53f2b..3d87b64dd9f7 100644 --- a/drivers/i2c/busses/i2c-pasemi-core.c +++ b/drivers/i2c/busses/i2c-pasemi-core.c @@ -41,8 +41,7 @@ static inline void reg_write(struct pasemi_smbus *smbus, int reg, int val) { - dev_dbg(smbus->dev, "smbus write reg %lx val %08x\n", - smbus->base + reg, val); + dev_dbg(smbus->dev, "smbus write reg %x val %08x\n", reg, val); iowrite32(val, smbus->ioaddr + reg); } @@ -50,8 +49,7 @@ static inline int reg_read(struct pasemi_smbus *smbus, int reg) { int ret; ret = ioread32(smbus->ioaddr + reg); - dev_dbg(smbus->dev, "smbus read reg %lx val %08x\n", - smbus->base + reg, ret); + dev_dbg(smbus->dev, "smbus read reg %x val %08x\n", reg, ret); return ret; } @@ -339,7 +337,7 @@ int pasemi_i2c_common_probe(struct pasemi_smbus *smbus) pasemi_reset(smbus); - error = i2c_add_adapter(&smbus->adapter); + error = devm_i2c_add_adapter(smbus->dev, &smbus->adapter); if (error) return error; diff --git a/drivers/i2c/busses/i2c-pasemi-core.h b/drivers/i2c/busses/i2c-pasemi-core.h index 30a7990825ef..aca4e2da9089 100644 --- a/drivers/i2c/busses/i2c-pasemi-core.h +++ b/drivers/i2c/busses/i2c-pasemi-core.h @@ -12,8 +12,6 @@ struct pasemi_smbus { struct device *dev; struct i2c_adapter adapter; void __iomem *ioaddr; - unsigned long base; - int size; unsigned int clk_div; }; diff --git a/drivers/i2c/busses/i2c-pasemi-pci.c b/drivers/i2c/busses/i2c-pasemi-pci.c index 96585bbf8c24..4251e7b9f177 100644 --- a/drivers/i2c/busses/i2c-pasemi-pci.c +++ b/drivers/i2c/busses/i2c-pasemi-pci.c @@ -26,57 +26,37 @@ static int pasemi_smb_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) { struct pasemi_smbus *smbus; + unsigned long base; + int size; int error; if (!(pci_resource_flags(dev, 0) & IORESOURCE_IO)) return -ENODEV; - smbus = kzalloc(sizeof(struct pasemi_smbus), GFP_KERNEL); + smbus = devm_kzalloc(&dev->dev, sizeof(*smbus), GFP_KERNEL); if (!smbus) return -ENOMEM; smbus->dev = &dev->dev; - smbus->base = pci_resource_start(dev, 0); - smbus->size = pci_resource_len(dev, 0); + base = pci_resource_start(dev, 0); + size = pci_resource_len(dev, 0); smbus->clk_div = CLK_100K_DIV; - if (!request_region(smbus->base, smbus->size, - pasemi_smb_pci_driver.name)) { - error = -EBUSY; - goto out_kfree; - } + if (!devm_request_region(&dev->dev, base, size, + pasemi_smb_pci_driver.name)) + return -EBUSY; - smbus->ioaddr = pci_iomap(dev, 0, 0); - if (!smbus->ioaddr) { - error = -EBUSY; - goto out_release_region; - } + smbus->ioaddr = pcim_iomap(dev, 0, 0); + if (!smbus->ioaddr) + return -EBUSY; error = pasemi_i2c_common_probe(smbus); if (error) - goto out_ioport_unmap; + return error; pci_set_drvdata(dev, smbus); return 0; - - out_ioport_unmap: - pci_iounmap(dev, smbus->ioaddr); - out_release_region: - release_region(smbus->base, smbus->size); - out_kfree: - kfree(smbus); - return error; -} - -static void pasemi_smb_pci_remove(struct pci_dev *dev) -{ - struct pasemi_smbus *smbus = pci_get_drvdata(dev); - - i2c_del_adapter(&smbus->adapter); - pci_iounmap(dev, smbus->ioaddr); - release_region(smbus->base, smbus->size); - kfree(smbus); } static const struct pci_device_id pasemi_smb_pci_ids[] = { @@ -90,7 +70,6 @@ static struct pci_driver pasemi_smb_pci_driver = { .name = "i2c-pasemi", .id_table = pasemi_smb_pci_ids, .probe = pasemi_smb_pci_probe, - .remove = pasemi_smb_pci_remove, }; module_pci_driver(pasemi_smb_pci_driver); From d88ae2932df0e670610cb741fec442ad12466c03 Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Fri, 8 Oct 2021 18:35:31 +0200 Subject: [PATCH 203/587] i2c: pasemi: Add Apple platform driver With all the previous preparations we can now finally add the platform driver to support the PASemi-based controllers in Apple SoCs. This does not work on the M1 yet but should work on the early iPhones already. Reviewed-by: Arnd Bergmann Signed-off-by: Sven Peter Acked-by: Olof Johansson Tested-by: Christian Zigotzky Signed-off-by: Wolfram Sang --- drivers/i2c/busses/Kconfig | 11 ++ drivers/i2c/busses/Makefile | 2 + drivers/i2c/busses/i2c-pasemi-platform.c | 122 +++++++++++++++++++++++ 3 files changed, 135 insertions(+) create mode 100644 drivers/i2c/busses/i2c-pasemi-platform.c diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index 1df19ccc310b..dce392839017 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -859,6 +859,17 @@ config I2C_PASEMI help Supports the PA Semi PWRficient on-chip SMBus interfaces. +config I2C_APPLE + tristate "Apple SMBus platform driver" + depends on ARCH_APPLE || COMPILE_TEST + default ARCH_APPLE + help + Say Y here if you want to use the I2C controller present on Apple + Silicon chips such as the M1. + + This driver can also be built as a module. If so, the module + will be called i2c-apple. + config I2C_PCA_PLATFORM tristate "PCA9564/PCA9665 as platform device" select I2C_ALGOPCA diff --git a/drivers/i2c/busses/Makefile b/drivers/i2c/busses/Makefile index 0ab1b4cb2228..d85899fef8c7 100644 --- a/drivers/i2c/busses/Makefile +++ b/drivers/i2c/busses/Makefile @@ -86,6 +86,8 @@ obj-$(CONFIG_I2C_OMAP) += i2c-omap.o obj-$(CONFIG_I2C_OWL) += i2c-owl.o i2c-pasemi-objs := i2c-pasemi-core.o i2c-pasemi-pci.o obj-$(CONFIG_I2C_PASEMI) += i2c-pasemi.o +i2c-apple-objs := i2c-pasemi-core.o i2c-pasemi-platform.o +obj-$(CONFIG_I2C_APPLE) += i2c-apple.o obj-$(CONFIG_I2C_PCA_PLATFORM) += i2c-pca-platform.o obj-$(CONFIG_I2C_PNX) += i2c-pnx.o obj-$(CONFIG_I2C_PXA) += i2c-pxa.o diff --git a/drivers/i2c/busses/i2c-pasemi-platform.c b/drivers/i2c/busses/i2c-pasemi-platform.c new file mode 100644 index 000000000000..88a54aaf7e3c --- /dev/null +++ b/drivers/i2c/busses/i2c-pasemi-platform.c @@ -0,0 +1,122 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2021 The Asahi Linux Contributors + * + * PA Semi PWRficient SMBus host driver for Apple SoCs + */ + +#include +#include +#include +#include +#include +#include +#include + +#include "i2c-pasemi-core.h" + +struct pasemi_platform_i2c_data { + struct pasemi_smbus smbus; + struct clk *clk_ref; +}; + +static int +pasemi_platform_i2c_calc_clk_div(struct pasemi_platform_i2c_data *data, + u32 frequency) +{ + unsigned long clk_rate = clk_get_rate(data->clk_ref); + + if (!clk_rate) + return -EINVAL; + + data->smbus.clk_div = DIV_ROUND_UP(clk_rate, 16 * frequency); + if (data->smbus.clk_div < 4) + return dev_err_probe(data->smbus.dev, -EINVAL, + "Bus frequency %d is too fast.\n", + frequency); + if (data->smbus.clk_div > 0xff) + return dev_err_probe(data->smbus.dev, -EINVAL, + "Bus frequency %d is too slow.\n", + frequency); + + return 0; +} + +static int pasemi_platform_i2c_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct pasemi_platform_i2c_data *data; + struct pasemi_smbus *smbus; + u32 frequency; + int error; + + data = devm_kzalloc(dev, sizeof(struct pasemi_platform_i2c_data), + GFP_KERNEL); + if (!data) + return -ENOMEM; + + smbus = &data->smbus; + smbus->dev = dev; + + smbus->ioaddr = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(smbus->ioaddr)) + return PTR_ERR(smbus->ioaddr); + + if (of_property_read_u32(dev->of_node, "clock-frequency", &frequency)) + frequency = I2C_MAX_STANDARD_MODE_FREQ; + + data->clk_ref = devm_clk_get(dev, NULL); + if (IS_ERR(data->clk_ref)) + return PTR_ERR(data->clk_ref); + + error = clk_prepare_enable(data->clk_ref); + if (error) + return error; + + error = pasemi_platform_i2c_calc_clk_div(data, frequency); + if (error) + goto out_clk_disable; + + smbus->adapter.dev.of_node = pdev->dev.of_node; + error = pasemi_i2c_common_probe(smbus); + if (error) + goto out_clk_disable; + + platform_set_drvdata(pdev, data); + + return 0; + +out_clk_disable: + clk_disable_unprepare(data->clk_ref); + + return error; +} + +static int pasemi_platform_i2c_remove(struct platform_device *pdev) +{ + struct pasemi_platform_i2c_data *data = platform_get_drvdata(pdev); + + clk_disable_unprepare(data->clk_ref); + return 0; +} + +static const struct of_device_id pasemi_platform_i2c_of_match[] = { + { .compatible = "apple,t8103-i2c" }, + { .compatible = "apple,i2c" }, + {}, +}; +MODULE_DEVICE_TABLE(of, pasemi_platform_i2c_of_match); + +static struct platform_driver pasemi_platform_i2c_driver = { + .driver = { + .name = "i2c-apple", + .of_match_table = pasemi_platform_i2c_of_match, + }, + .probe = pasemi_platform_i2c_probe, + .remove = pasemi_platform_i2c_remove, +}; +module_platform_driver(pasemi_platform_i2c_driver); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Sven Peter "); +MODULE_DESCRIPTION("Apple/PASemi SMBus platform driver"); From 3abdc89b5e309c63fa631de38cbec0755e5b2ee7 Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Fri, 8 Oct 2021 18:35:32 +0200 Subject: [PATCH 204/587] i2c: pasemi: Set enable bit for Apple variant Some later revisions after the original PASemi I2C controller introduce what likely is an enable bit to the CTL register. Without setting it the actual i2c transmission is never started. Reviewed-by: Arnd Bergmann Signed-off-by: Sven Peter Acked-by: Olof Johansson Tested-by: Christian Zigotzky Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-pasemi-core.c | 8 ++++++++ drivers/i2c/busses/i2c-pasemi-core.h | 3 +++ drivers/i2c/busses/i2c-pasemi-pci.c | 6 ++++++ 3 files changed, 17 insertions(+) diff --git a/drivers/i2c/busses/i2c-pasemi-core.c b/drivers/i2c/busses/i2c-pasemi-core.c index 3d87b64dd9f7..4e161a4089d8 100644 --- a/drivers/i2c/busses/i2c-pasemi-core.c +++ b/drivers/i2c/busses/i2c-pasemi-core.c @@ -22,6 +22,7 @@ #define REG_MRXFIFO 0x04 #define REG_SMSTA 0x14 #define REG_CTL 0x1c +#define REG_REV 0x28 /* Register defs */ #define MTXFIFO_READ 0x00000400 @@ -37,6 +38,7 @@ #define CTL_MRR 0x00000400 #define CTL_MTR 0x00000200 +#define CTL_EN 0x00000800 #define CTL_CLK_M 0x000000ff static inline void reg_write(struct pasemi_smbus *smbus, int reg, int val) @@ -60,6 +62,9 @@ static void pasemi_reset(struct pasemi_smbus *smbus) { u32 val = (CTL_MTR | CTL_MRR | (smbus->clk_div & CTL_CLK_M)); + if (smbus->hw_rev >= 6) + val |= CTL_EN; + reg_write(smbus, REG_CTL, val); } @@ -335,6 +340,9 @@ int pasemi_i2c_common_probe(struct pasemi_smbus *smbus) /* set up the sysfs linkage to our parent device */ smbus->adapter.dev.parent = smbus->dev; + if (smbus->hw_rev != PASEMI_HW_REV_PCI) + smbus->hw_rev = reg_read(smbus, REG_REV); + pasemi_reset(smbus); error = devm_i2c_add_adapter(smbus->dev, &smbus->adapter); diff --git a/drivers/i2c/busses/i2c-pasemi-core.h b/drivers/i2c/busses/i2c-pasemi-core.h index aca4e2da9089..4655124a37f3 100644 --- a/drivers/i2c/busses/i2c-pasemi-core.h +++ b/drivers/i2c/busses/i2c-pasemi-core.h @@ -8,11 +8,14 @@ #include #include +#define PASEMI_HW_REV_PCI -1 + struct pasemi_smbus { struct device *dev; struct i2c_adapter adapter; void __iomem *ioaddr; unsigned int clk_div; + int hw_rev; }; int pasemi_i2c_common_probe(struct pasemi_smbus *smbus); diff --git a/drivers/i2c/busses/i2c-pasemi-pci.c b/drivers/i2c/busses/i2c-pasemi-pci.c index 4251e7b9f177..1ab1f28744fb 100644 --- a/drivers/i2c/busses/i2c-pasemi-pci.c +++ b/drivers/i2c/busses/i2c-pasemi-pci.c @@ -42,6 +42,12 @@ static int pasemi_smb_pci_probe(struct pci_dev *dev, size = pci_resource_len(dev, 0); smbus->clk_div = CLK_100K_DIV; + /* + * The original PASemi PCI controllers don't have a register for + * their HW revision. + */ + smbus->hw_rev = PASEMI_HW_REV_PCI; + if (!devm_request_region(&dev->dev, base, size, pasemi_smb_pci_driver.name)) return -EBUSY; From 712d6617d0a29dc4d4da361247720cdf156ae7bb Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Mon, 23 Aug 2021 17:45:04 +0300 Subject: [PATCH 205/587] i2c: mlxcpld: Allow flexible polling time setting for I2C transactions Allow polling time setting according to I2C frequency supported across the system. For base frequency 400 KHz and 1 MHz set polling time is set four times less than for system with base frequency 100KHz. Signed-off-by: Vadim Pasternak Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-mlxcpld.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/drivers/i2c/busses/i2c-mlxcpld.c b/drivers/i2c/busses/i2c-mlxcpld.c index 615f0a98640e..56aa424fd71d 100644 --- a/drivers/i2c/busses/i2c-mlxcpld.c +++ b/drivers/i2c/busses/i2c-mlxcpld.c @@ -73,6 +73,7 @@ struct mlxcpld_i2c_priv { struct mlxcpld_i2c_curr_xfer xfer; struct device *dev; bool smbus_block; + int polling_time; }; static void mlxcpld_i2c_lpc_write_buf(u8 *data, u8 len, u32 addr) @@ -267,8 +268,8 @@ static int mlxcpld_i2c_wait_for_free(struct mlxcpld_i2c_priv *priv) do { if (!mlxcpld_i2c_check_busy(priv)) break; - usleep_range(MLXCPLD_I2C_POLL_TIME / 2, MLXCPLD_I2C_POLL_TIME); - timeout += MLXCPLD_I2C_POLL_TIME; + usleep_range(priv->polling_time / 2, priv->polling_time); + timeout += priv->polling_time; } while (timeout <= MLXCPLD_I2C_XFER_TO); if (timeout > MLXCPLD_I2C_XFER_TO) @@ -288,10 +289,10 @@ static int mlxcpld_i2c_wait_for_tc(struct mlxcpld_i2c_priv *priv) u8 datalen, val; do { - usleep_range(MLXCPLD_I2C_POLL_TIME / 2, MLXCPLD_I2C_POLL_TIME); + usleep_range(priv->polling_time / 2, priv->polling_time); if (!mlxcpld_i2c_check_status(priv, &status)) break; - timeout += MLXCPLD_I2C_POLL_TIME; + timeout += priv->polling_time; } while (status == 0 && timeout < MLXCPLD_I2C_XFER_TO); switch (status) { @@ -498,9 +499,11 @@ mlxcpld_i2c_set_frequency(struct mlxcpld_i2c_priv *priv, switch ((regval & data->mask) >> data->bit) { case MLXCPLD_I2C_FREQ_1000KHZ: freq = MLXCPLD_I2C_FREQ_1000KHZ_SET; + priv->polling_time /= 4; break; case MLXCPLD_I2C_FREQ_400KHZ: freq = MLXCPLD_I2C_FREQ_400KHZ_SET; + priv->polling_time /= 4; break; default: return 0; @@ -527,6 +530,7 @@ static int mlxcpld_i2c_probe(struct platform_device *pdev) priv->dev = &pdev->dev; priv->base_addr = MLXPLAT_CPLD_LPC_I2C_BASE_ADDR; + priv->polling_time = MLXCPLD_I2C_POLL_TIME; /* Set I2C bus frequency if platform data provides this info. */ pdata = dev_get_platdata(&pdev->dev); From e3e4949e637d39321cc379ff73a60c26df6410bc Mon Sep 17 00:00:00 2001 From: Kewei Xu Date: Sun, 10 Oct 2021 15:05:12 +0800 Subject: [PATCH 206/587] i2c: mediatek: Reset the handshake signal between i2c and dma Due to changes in the hardware design of the handshaking signal between i2c and dma, it is necessary to reset the handshaking signal before each transfer to ensure that the multi-msgs can be transferred correctly. Signed-off-by: Kewei Xu Reviewed-by: Qii Wang Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-mt65xx.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/drivers/i2c/busses/i2c-mt65xx.c b/drivers/i2c/busses/i2c-mt65xx.c index 72acda59eb39..c06dbbf73f93 100644 --- a/drivers/i2c/busses/i2c-mt65xx.c +++ b/drivers/i2c/busses/i2c-mt65xx.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -49,6 +50,8 @@ #define I2C_RD_TRANAC_VALUE 0x0001 #define I2C_SCL_MIS_COMP_VALUE 0x0000 #define I2C_CHN_CLR_FLAG 0x0000 +#define I2C_RELIABILITY 0x0010 +#define I2C_DMAACK_ENABLE 0x0008 #define I2C_DMA_CON_TX 0x0000 #define I2C_DMA_CON_RX 0x0001 @@ -851,6 +854,7 @@ static int mtk_i2c_do_transfer(struct mtk_i2c *i2c, struct i2c_msg *msgs, u16 restart_flag = 0; u16 dma_sync = 0; u32 reg_4g_mode; + u32 reg_dma_reset; u8 *dma_rd_buf = NULL; u8 *dma_wr_buf = NULL; dma_addr_t rpaddr = 0; @@ -864,6 +868,28 @@ static int mtk_i2c_do_transfer(struct mtk_i2c *i2c, struct i2c_msg *msgs, reinit_completion(&i2c->msg_complete); + if (i2c->dev_comp->apdma_sync && + i2c->op != I2C_MASTER_WRRD && num > 1) { + mtk_i2c_writew(i2c, 0x00, OFFSET_DEBUGCTRL); + writel(I2C_DMA_HANDSHAKE_RST | I2C_DMA_WARM_RST, + i2c->pdmabase + OFFSET_RST); + + ret = readw_poll_timeout(i2c->pdmabase + OFFSET_RST, + reg_dma_reset, + !(reg_dma_reset & I2C_DMA_WARM_RST), + 0, 100); + if (ret) { + dev_err(i2c->dev, "DMA warm reset timeout\n"); + return -ETIMEDOUT; + } + + writel(I2C_DMA_CLR_FLAG, i2c->pdmabase + OFFSET_RST); + mtk_i2c_writew(i2c, I2C_HANDSHAKE_RST, OFFSET_SOFTRESET); + mtk_i2c_writew(i2c, I2C_CHN_CLR_FLAG, OFFSET_SOFTRESET); + mtk_i2c_writew(i2c, I2C_RELIABILITY | I2C_DMAACK_ENABLE, + OFFSET_DEBUGCTRL); + } + control_reg = mtk_i2c_readw(i2c, OFFSET_CONTROL) & ~(I2C_CONTROL_DIR_CHANGE | I2C_CONTROL_RS); if ((i2c->speed_hz > I2C_MAX_FAST_MODE_PLUS_FREQ) || (left_num >= 1)) From cc28e578f515f068cd8ee280706b8d8e31c472f9 Mon Sep 17 00:00:00 2001 From: Kewei Xu Date: Sun, 10 Oct 2021 15:05:13 +0800 Subject: [PATCH 207/587] i2c: mediatek: Dump i2c/dma register when a timeout occurs When a timeout error occurs in i2c transter, it is usually related to the i2c/dma IP hardware configuration. Therefore, the purpose of this patch is to dump the key register values of i2c/dma when a timeout occurs in i2c for debugging. Signed-off-by: Kewei Xu Reviewed-by: Qii Wang Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-mt65xx.c | 54 +++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) diff --git a/drivers/i2c/busses/i2c-mt65xx.c b/drivers/i2c/busses/i2c-mt65xx.c index c06dbbf73f93..9ea427f53083 100644 --- a/drivers/i2c/busses/i2c-mt65xx.c +++ b/drivers/i2c/busses/i2c-mt65xx.c @@ -130,6 +130,7 @@ enum I2C_REGS_OFFSET { OFFSET_HS, OFFSET_SOFTRESET, OFFSET_DCM_EN, + OFFSET_MULTI_DMA, OFFSET_PATH_DIR, OFFSET_DEBUGSTAT, OFFSET_DEBUGCTRL, @@ -197,6 +198,7 @@ static const u16 mt_i2c_regs_v2[] = { [OFFSET_TRANSFER_LEN_AUX] = 0x44, [OFFSET_CLOCK_DIV] = 0x48, [OFFSET_SOFTRESET] = 0x50, + [OFFSET_MULTI_DMA] = 0x8c, [OFFSET_SCL_MIS_COMP_POINT] = 0x90, [OFFSET_DEBUGSTAT] = 0xe4, [OFFSET_DEBUGCTRL] = 0xe8, @@ -845,6 +847,57 @@ static int mtk_i2c_set_speed(struct mtk_i2c *i2c, unsigned int parent_clk) return 0; } +static void i2c_dump_register(struct mtk_i2c *i2c) +{ + dev_dbg(i2c->dev, "SLAVE_ADDR: 0x%x, INTR_MASK: 0x%x\n", + mtk_i2c_readw(i2c, OFFSET_SLAVE_ADDR), + mtk_i2c_readw(i2c, OFFSET_INTR_MASK)); + dev_dbg(i2c->dev, "INTR_STAT: 0x%x, CONTROL: 0x%x\n", + mtk_i2c_readw(i2c, OFFSET_INTR_STAT), + mtk_i2c_readw(i2c, OFFSET_CONTROL)); + dev_dbg(i2c->dev, "TRANSFER_LEN: 0x%x, TRANSAC_LEN: 0x%x\n", + mtk_i2c_readw(i2c, OFFSET_TRANSFER_LEN), + mtk_i2c_readw(i2c, OFFSET_TRANSAC_LEN)); + dev_dbg(i2c->dev, "DELAY_LEN: 0x%x, HTIMING: 0x%x\n", + mtk_i2c_readw(i2c, OFFSET_DELAY_LEN), + mtk_i2c_readw(i2c, OFFSET_TIMING)); + dev_dbg(i2c->dev, "START: 0x%x, EXT_CONF: 0x%x\n", + mtk_i2c_readw(i2c, OFFSET_START), + mtk_i2c_readw(i2c, OFFSET_EXT_CONF)); + dev_dbg(i2c->dev, "HS: 0x%x, IO_CONFIG: 0x%x\n", + mtk_i2c_readw(i2c, OFFSET_HS), + mtk_i2c_readw(i2c, OFFSET_IO_CONFIG)); + dev_dbg(i2c->dev, "DCM_EN: 0x%x, TRANSFER_LEN_AUX: 0x%x\n", + mtk_i2c_readw(i2c, OFFSET_DCM_EN), + mtk_i2c_readw(i2c, OFFSET_TRANSFER_LEN_AUX)); + dev_dbg(i2c->dev, "CLOCK_DIV: 0x%x, FIFO_STAT: 0x%x\n", + mtk_i2c_readw(i2c, OFFSET_CLOCK_DIV), + mtk_i2c_readw(i2c, OFFSET_FIFO_STAT)); + dev_dbg(i2c->dev, "DEBUGCTRL : 0x%x, DEBUGSTAT: 0x%x\n", + mtk_i2c_readw(i2c, OFFSET_DEBUGCTRL), + mtk_i2c_readw(i2c, OFFSET_DEBUGSTAT)); + if (i2c->dev_comp->regs == mt_i2c_regs_v2) { + dev_dbg(i2c->dev, "LTIMING: 0x%x, MULTI_DMA: 0x%x\n", + mtk_i2c_readw(i2c, OFFSET_LTIMING), + mtk_i2c_readw(i2c, OFFSET_MULTI_DMA)); + } + dev_dbg(i2c->dev, "\nDMA_INT_FLAG: 0x%x, DMA_INT_EN: 0x%x\n", + readl(i2c->pdmabase + OFFSET_INT_FLAG), + readl(i2c->pdmabase + OFFSET_INT_EN)); + dev_dbg(i2c->dev, "DMA_EN: 0x%x, DMA_CON: 0x%x\n", + readl(i2c->pdmabase + OFFSET_EN), + readl(i2c->pdmabase + OFFSET_CON)); + dev_dbg(i2c->dev, "DMA_TX_MEM_ADDR: 0x%x, DMA_RX_MEM_ADDR: 0x%x\n", + readl(i2c->pdmabase + OFFSET_TX_MEM_ADDR), + readl(i2c->pdmabase + OFFSET_RX_MEM_ADDR)); + dev_dbg(i2c->dev, "DMA_TX_LEN: 0x%x, DMA_RX_LEN: 0x%x\n", + readl(i2c->pdmabase + OFFSET_TX_LEN), + readl(i2c->pdmabase + OFFSET_RX_LEN)); + dev_dbg(i2c->dev, "DMA_TX_4G_MODE: 0x%x, DMA_RX_4G_MODE: 0x%x", + readl(i2c->pdmabase + OFFSET_TX_4G_MODE), + readl(i2c->pdmabase + OFFSET_RX_4G_MODE)); +} + static int mtk_i2c_do_transfer(struct mtk_i2c *i2c, struct i2c_msg *msgs, int num, int left_num) { @@ -1075,6 +1128,7 @@ static int mtk_i2c_do_transfer(struct mtk_i2c *i2c, struct i2c_msg *msgs, if (ret == 0) { dev_dbg(i2c->dev, "addr: %x, transfer timeout\n", msgs->addr); + i2c_dump_register(i2c); mtk_i2c_init_hw(i2c); return -ETIMEDOUT; } From ca51b26b4a25b05c9b438ed85c4750bfb6f2d9ab Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 1 Oct 2021 14:32:45 +0900 Subject: [PATCH 208/587] kconfig: refactor conf_write_heading() All the call sites of conf_write_heading() pass NULL to the third argument, and it is not used in the function. Also, the print_comment hooks are doing much more complex than needed. Rewrite the code. Signed-off-by: Masahiro Yamada --- scripts/kconfig/confdata.c | 95 +++++++++++++------------------------- 1 file changed, 33 insertions(+), 62 deletions(-) diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c index 9b2271eb43d6..83e324b9b5e5 100644 --- a/scripts/kconfig/confdata.c +++ b/scripts/kconfig/confdata.c @@ -161,7 +161,6 @@ static int conf_touch_dep(const char *name) struct conf_printer { void (*print_symbol)(FILE *, struct symbol *, const char *, void *); - void (*print_comment)(FILE *, const char *, void *); }; static void conf_warning(const char *fmt, ...) @@ -594,6 +593,36 @@ int conf_read(const char *name) return 0; } +struct comment_style { + const char *decoration; + const char *prefix; + const char *postfix; +}; + +static const struct comment_style comment_style_pound = { + .decoration = "#", + .prefix = "#", + .postfix = "#", +}; + +static const struct comment_style comment_style_c = { + .decoration = " *", + .prefix = "/*", + .postfix = " */", +}; + +static void conf_write_heading(FILE *fp, const struct comment_style *cs) +{ + fprintf(fp, "%s\n", cs->prefix); + + fprintf(fp, "%s Automatically generated file; DO NOT EDIT.\n", + cs->decoration); + + fprintf(fp, "%s %s\n", cs->decoration, rootmenu.prompt->text); + + fprintf(fp, "%s\n", cs->postfix); +} + /* * Kconfig configuration printer * @@ -625,30 +654,9 @@ kconfig_print_symbol(FILE *fp, struct symbol *sym, const char *value, void *arg) fprintf(fp, "%s%s=%s\n", CONFIG_, sym->name, value); } -static void -kconfig_print_comment(FILE *fp, const char *value, void *arg) -{ - const char *p = value; - size_t l; - - for (;;) { - l = strcspn(p, "\n"); - fprintf(fp, "#"); - if (l) { - fprintf(fp, " "); - xfwrite(p, l, 1, fp); - p += l; - } - fprintf(fp, "\n"); - if (*p++ == '\0') - break; - } -} - static struct conf_printer kconfig_printer_cb = { .print_symbol = kconfig_print_symbol, - .print_comment = kconfig_print_comment, }; /* @@ -697,32 +705,9 @@ header_print_symbol(FILE *fp, struct symbol *sym, const char *value, void *arg) } -static void -header_print_comment(FILE *fp, const char *value, void *arg) -{ - const char *p = value; - size_t l; - - fprintf(fp, "/*\n"); - for (;;) { - l = strcspn(p, "\n"); - fprintf(fp, " *"); - if (l) { - fprintf(fp, " "); - xfwrite(p, l, 1, fp); - p += l; - } - fprintf(fp, "\n"); - if (*p++ == '\0') - break; - } - fprintf(fp, " */\n"); -} - static struct conf_printer header_printer_cb = { .print_symbol = header_print_symbol, - .print_comment = header_print_comment, }; static void conf_write_symbol(FILE *fp, struct symbol *sym, @@ -746,20 +731,6 @@ static void conf_write_symbol(FILE *fp, struct symbol *sym, free(escaped); } -static void -conf_write_heading(FILE *fp, struct conf_printer *printer, void *printer_arg) -{ - char buf[256]; - - snprintf(buf, sizeof(buf), - "\n" - "Automatically generated file; DO NOT EDIT.\n" - "%s\n", - rootmenu.prompt->text); - - printer->print_comment(fp, buf, printer_arg); -} - /* * Write out a minimal config. * All values that has default values are skipped as this is redundant. @@ -876,7 +847,7 @@ int conf_write(const char *name) if (!out) return 1; - conf_write_heading(out, &kconfig_printer_cb, NULL); + conf_write_heading(out, &comment_style_pound); if (!conf_get_changed()) sym_clear_all_valid(); @@ -1080,8 +1051,8 @@ int conf_write_autoconf(int overwrite) return 1; } - conf_write_heading(out, &kconfig_printer_cb, NULL); - conf_write_heading(out_h, &header_printer_cb, NULL); + conf_write_heading(out, &comment_style_pound); + conf_write_heading(out_h, &comment_style_c); for_all_symbols(i, sym) { sym_calc_value(sym); From 6ce45a91a9826532dde7c89cd2d6388c0bcb0cf7 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 1 Oct 2021 14:32:46 +0900 Subject: [PATCH 209/587] kconfig: refactor conf_write_symbol() I do not think 'struct conf_printer' is so useful. Add simple functions, print_symbol_for_*() to write out one symbol. Signed-off-by: Masahiro Yamada --- scripts/kconfig/confdata.c | 160 ++++++++++++++++--------------------- 1 file changed, 69 insertions(+), 91 deletions(-) diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c index 83e324b9b5e5..4e3fd194231b 100644 --- a/scripts/kconfig/confdata.c +++ b/scripts/kconfig/confdata.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -159,10 +160,6 @@ static int conf_touch_dep(const char *name) return 0; } -struct conf_printer { - void (*print_symbol)(FILE *, struct symbol *, const char *, void *); -}; - static void conf_warning(const char *fmt, ...) __attribute__ ((format (printf, 1, 2))); @@ -629,89 +626,11 @@ static void conf_write_heading(FILE *fp, const struct comment_style *cs) * This printer is used when generating the resulting configuration after * kconfig invocation and `defconfig' files. Unset symbol might be omitted by * passing a non-NULL argument to the printer. - * */ -static void -kconfig_print_symbol(FILE *fp, struct symbol *sym, const char *value, void *arg) -{ +enum output_n { OUTPUT_N, OUTPUT_N_AS_UNSET, OUTPUT_N_NONE }; - switch (sym->type) { - case S_BOOLEAN: - case S_TRISTATE: - if (*value == 'n') { - bool skip_unset = (arg != NULL); - - if (!skip_unset) - fprintf(fp, "# %s%s is not set\n", - CONFIG_, sym->name); - return; - } - break; - default: - break; - } - - fprintf(fp, "%s%s=%s\n", CONFIG_, sym->name, value); -} - -static struct conf_printer kconfig_printer_cb = -{ - .print_symbol = kconfig_print_symbol, -}; - -/* - * Header printer - * - * This printer is used when generating the `include/generated/autoconf.h' file. - */ -static void -header_print_symbol(FILE *fp, struct symbol *sym, const char *value, void *arg) -{ - - switch (sym->type) { - case S_BOOLEAN: - case S_TRISTATE: { - const char *suffix = ""; - - switch (*value) { - case 'n': - break; - case 'm': - suffix = "_MODULE"; - /* fall through */ - default: - fprintf(fp, "#define %s%s%s 1\n", - CONFIG_, sym->name, suffix); - } - break; - } - case S_HEX: { - const char *prefix = ""; - - if (value[0] != '0' || (value[1] != 'x' && value[1] != 'X')) - prefix = "0x"; - fprintf(fp, "#define %s%s %s%s\n", - CONFIG_, sym->name, prefix, value); - break; - } - case S_STRING: - case S_INT: - fprintf(fp, "#define %s%s %s\n", - CONFIG_, sym->name, value); - break; - default: - break; - } - -} - -static struct conf_printer header_printer_cb = -{ - .print_symbol = header_print_symbol, -}; - -static void conf_write_symbol(FILE *fp, struct symbol *sym, - struct conf_printer *printer, void *printer_arg) +static void __print_symbol(FILE *fp, struct symbol *sym, enum output_n output_n, + bool escape_string) { const char *val; char *escaped = NULL; @@ -721,12 +640,71 @@ static void conf_write_symbol(FILE *fp, struct symbol *sym, val = sym_get_string_value(sym); - if (sym->type == S_STRING) { + if ((sym->type == S_BOOLEAN || sym->type == S_TRISTATE) && + output_n != OUTPUT_N && *val == 'n') { + if (output_n == OUTPUT_N_AS_UNSET) + fprintf(fp, "# %s%s is not set\n", CONFIG_, sym->name); + return; + } + + if (sym->type == S_STRING && escape_string) { escaped = sym_escape_string_value(val); val = escaped; } - printer->print_symbol(fp, sym, val, printer_arg); + fprintf(fp, "%s%s=%s\n", CONFIG_, sym->name, val); + + free(escaped); +} + +static void print_symbol_for_dotconfig(FILE *fp, struct symbol *sym) +{ + __print_symbol(fp, sym, OUTPUT_N_AS_UNSET, true); +} + +static void print_symbol_for_autoconf(FILE *fp, struct symbol *sym) +{ + __print_symbol(fp, sym, OUTPUT_N_NONE, true); +} + +static void print_symbol_for_c(FILE *fp, struct symbol *sym) +{ + const char *val; + const char *sym_suffix = ""; + const char *val_prefix = ""; + char *escaped = NULL; + + if (sym->type == S_UNKNOWN) + return; + + val = sym_get_string_value(sym); + + switch (sym->type) { + case S_BOOLEAN: + case S_TRISTATE: + switch (*val) { + case 'n': + return; + case 'm': + sym_suffix = "_MODULE"; + /* fall through */ + default: + val = "1"; + } + break; + case S_HEX: + if (val[0] != '0' || (val[1] != 'x' && val[1] != 'X')) + val_prefix = "0x"; + break; + case S_STRING: + escaped = sym_escape_string_value(val); + val = escaped; + default: + break; + } + + fprintf(fp, "#define %s%s%s %s%s\n", CONFIG_, sym->name, sym_suffix, + val_prefix, val); free(escaped); } @@ -787,7 +765,7 @@ int conf_write_defconfig(const char *filename) goto next_menu; } } - conf_write_symbol(out, sym, &kconfig_printer_cb, NULL); + print_symbol_for_dotconfig(out, sym); } next_menu: if (menu->list != NULL) { @@ -874,7 +852,7 @@ int conf_write(const char *name) need_newline = false; } sym->flags |= SYMBOL_WRITTEN; - conf_write_symbol(out, sym, &kconfig_printer_cb, NULL); + print_symbol_for_dotconfig(out, sym); } next: @@ -1060,8 +1038,8 @@ int conf_write_autoconf(int overwrite) continue; /* write symbols to auto.conf and autoconf.h */ - conf_write_symbol(out, sym, &kconfig_printer_cb, (void *)1); - conf_write_symbol(out_h, sym, &header_printer_cb, NULL); + print_symbol_for_autoconf(out, sym); + print_symbol_for_c(out_h, sym); } fclose(out); fclose(out_h); From 51d792cb5de87fa8777b4769a33c302e4ad0580a Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 1 Oct 2021 14:32:47 +0900 Subject: [PATCH 210/587] kconfig: refactor listnewconfig code We can reuse __print_symbol() helper to print symbols for listnewconfig. Only the difference is the format for "n" symbols. This prints "CONFIG_FOO=n" instead of "# CONFIG_FOO is not set". Signed-off-by: Masahiro Yamada --- scripts/kconfig/conf.c | 14 ++------------ scripts/kconfig/confdata.c | 5 +++++ scripts/kconfig/lkc_proto.h | 1 + 3 files changed, 8 insertions(+), 12 deletions(-) diff --git a/scripts/kconfig/conf.c b/scripts/kconfig/conf.c index 310fdd408793..971da3598fe4 100644 --- a/scripts/kconfig/conf.c +++ b/scripts/kconfig/conf.c @@ -646,18 +646,8 @@ static void check_conf(struct menu *menu) switch (input_mode) { case listnewconfig: - if (sym->name) { - const char *val = sym_get_string_value(sym); - char *escaped = NULL; - - if (sym->type == S_STRING) { - escaped = sym_escape_string_value(val); - val = escaped; - } - - printf("%s%s=%s\n", CONFIG_, sym->name, val); - free(escaped); - } + if (sym->name) + print_symbol_for_listconfig(sym); break; case helpnewconfig: printf("-----\n"); diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c index 4e3fd194231b..f17a2a9562ee 100644 --- a/scripts/kconfig/confdata.c +++ b/scripts/kconfig/confdata.c @@ -667,6 +667,11 @@ static void print_symbol_for_autoconf(FILE *fp, struct symbol *sym) __print_symbol(fp, sym, OUTPUT_N_NONE, true); } +void print_symbol_for_listconfig(struct symbol *sym) +{ + __print_symbol(stdout, sym, OUTPUT_N, true); +} + static void print_symbol_for_c(FILE *fp, struct symbol *sym) { const char *val; diff --git a/scripts/kconfig/lkc_proto.h b/scripts/kconfig/lkc_proto.h index e6955df49973..ec4a01bb60ce 100644 --- a/scripts/kconfig/lkc_proto.h +++ b/scripts/kconfig/lkc_proto.h @@ -19,6 +19,7 @@ extern struct symbol * symbol_hash[SYMBOL_HASHSIZE]; struct symbol * sym_lookup(const char *name, int flags); struct symbol * sym_find(const char *name); char *sym_escape_string_value(const char *in); +void print_symbol_for_listconfig(struct symbol *sym); struct symbol ** sym_re_search(const char *pattern); const char * sym_type_name(enum symbol_type type); void sym_calc_value(struct symbol *sym); From 80f7bc7737630fb1b2c4f440fc7627337bd2f605 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 1 Oct 2021 14:32:48 +0900 Subject: [PATCH 211/587] kconfig: move sym_escape_string_value() to confdata.c Now that sym_escape_string_value() is only used in confdata.c it can be a 'static' function. Rename it escape_string_value() because it is agnostic about (struct sym *). Signed-off-by: Masahiro Yamada --- scripts/kconfig/confdata.c | 47 +++++++++++++++++++++++++++++++++++-- scripts/kconfig/lkc_proto.h | 1 - scripts/kconfig/symbol.c | 44 ---------------------------------- 3 files changed, 45 insertions(+), 47 deletions(-) diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c index f17a2a9562ee..26b39d34e2be 100644 --- a/scripts/kconfig/confdata.c +++ b/scripts/kconfig/confdata.c @@ -620,6 +620,49 @@ static void conf_write_heading(FILE *fp, const struct comment_style *cs) fprintf(fp, "%s\n", cs->postfix); } +/* The returned pointer must be freed on the caller side */ +static char *escape_string_value(const char *in) +{ + const char *p; + char *out; + size_t len; + + len = strlen(in) + strlen("\"\"") + 1; + + p = in; + while (1) { + p += strcspn(p, "\"\\"); + + if (p[0] == '\0') + break; + + len++; + p++; + } + + out = xmalloc(len); + out[0] = '\0'; + + strcat(out, "\""); + + p = in; + while (1) { + len = strcspn(p, "\"\\"); + strncat(out, p, len); + p += len; + + if (p[0] == '\0') + break; + + strcat(out, "\\"); + strncat(out, p++, 1); + } + + strcat(out, "\""); + + return out; +} + /* * Kconfig configuration printer * @@ -648,7 +691,7 @@ static void __print_symbol(FILE *fp, struct symbol *sym, enum output_n output_n, } if (sym->type == S_STRING && escape_string) { - escaped = sym_escape_string_value(val); + escaped = escape_string_value(val); val = escaped; } @@ -702,7 +745,7 @@ static void print_symbol_for_c(FILE *fp, struct symbol *sym) val_prefix = "0x"; break; case S_STRING: - escaped = sym_escape_string_value(val); + escaped = escape_string_value(val); val = escaped; default: break; diff --git a/scripts/kconfig/lkc_proto.h b/scripts/kconfig/lkc_proto.h index ec4a01bb60ce..edd1e617b25c 100644 --- a/scripts/kconfig/lkc_proto.h +++ b/scripts/kconfig/lkc_proto.h @@ -18,7 +18,6 @@ extern struct symbol * symbol_hash[SYMBOL_HASHSIZE]; struct symbol * sym_lookup(const char *name, int flags); struct symbol * sym_find(const char *name); -char *sym_escape_string_value(const char *in); void print_symbol_for_listconfig(struct symbol *sym); struct symbol ** sym_re_search(const char *pattern); const char * sym_type_name(enum symbol_type type); diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c index 6bf8665a6a0f..0572330bf8a7 100644 --- a/scripts/kconfig/symbol.c +++ b/scripts/kconfig/symbol.c @@ -871,50 +871,6 @@ struct symbol *sym_find(const char *name) return symbol; } -/* The returned pointer must be freed on the caller side */ -char *sym_escape_string_value(const char *in) -{ - const char *p; - size_t reslen; - char *res; - size_t l; - - reslen = strlen(in) + strlen("\"\"") + 1; - - p = in; - for (;;) { - l = strcspn(p, "\"\\"); - p += l; - - if (p[0] == '\0') - break; - - reslen++; - p++; - } - - res = xmalloc(reslen); - res[0] = '\0'; - - strcat(res, "\""); - - p = in; - for (;;) { - l = strcspn(p, "\"\\"); - strncat(res, p, l); - p += l; - - if (p[0] == '\0') - break; - - strcat(res, "\\"); - strncat(res, p++, 1); - } - - strcat(res, "\""); - return res; -} - struct sym_match { struct symbol *sym; off_t so, eo; From 8499f2dd57ef099290fa5411c4498bccc9c407d9 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 1 Oct 2021 14:32:49 +0900 Subject: [PATCH 212/587] kconfig: add conf_get_autoheader_name() For consistency with conf_get_autoconfig_name() Signed-off-by: Masahiro Yamada --- scripts/kconfig/confdata.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c index 26b39d34e2be..acf3d5a2973e 100644 --- a/scripts/kconfig/confdata.c +++ b/scripts/kconfig/confdata.c @@ -223,6 +223,13 @@ static const char *conf_get_autoconfig_name(void) return name ? name : "include/config/auto.conf"; } +static const char *conf_get_autoheader_name(void) +{ + char *name = getenv("KCONFIG_AUTOHEADER"); + + return name ? name : "include/generated/autoconf.h"; +} + static int conf_set_sym_val(struct symbol *sym, int def, int def_flags, char *p) { char *p2; @@ -1092,9 +1099,7 @@ int conf_write_autoconf(int overwrite) fclose(out); fclose(out_h); - name = getenv("KCONFIG_AUTOHEADER"); - if (!name) - name = "include/generated/autoconf.h"; + name = conf_get_autoheader_name(); if (make_parent_dir(name)) return 1; if (rename(".tmpconfig.h", name)) From 57ddd07c456053dfdabebc6a2d030c57cd3fb75b Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 1 Oct 2021 14:32:50 +0900 Subject: [PATCH 213/587] kconfig: refactor conf_write_autoconf() This function does similar for auto.conf and autoconf.h Create __conf_write_autoconf() helper to factor out the common code. Signed-off-by: Masahiro Yamada --- scripts/kconfig/confdata.c | 94 +++++++++++++++++++++++--------------- 1 file changed, 57 insertions(+), 37 deletions(-) diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c index acf3d5a2973e..7301f4b2f4d5 100644 --- a/scripts/kconfig/confdata.c +++ b/scripts/kconfig/confdata.c @@ -1058,13 +1058,53 @@ static int conf_touch_deps(void) return 0; } +static int __conf_write_autoconf(const char *filename, + void (*print_symbol)(FILE *, struct symbol *), + const struct comment_style *comment_style) +{ + char tmp[PATH_MAX]; + FILE *file; + struct symbol *sym; + int ret, i; + + if (make_parent_dir(filename)) + return -1; + + ret = snprintf(tmp, sizeof(tmp), "%s.tmp", filename); + if (ret >= sizeof(tmp)) /* check truncation */ + return -1; + + file = fopen(tmp, "w"); + if (!file) { + perror("fopen"); + return -1; + } + + conf_write_heading(file, comment_style); + + for_all_symbols(i, sym) + if ((sym->flags & SYMBOL_WRITE) && sym->name) + print_symbol(file, sym); + + /* check possible errors in conf_write_heading() and print_symbol() */ + if (ferror(file)) + return -1; + + fclose(file); + + if (rename(tmp, filename)) { + perror("rename"); + return -1; + } + + return 0; +} + int conf_write_autoconf(int overwrite) { struct symbol *sym; - const char *name; const char *autoconf_name = conf_get_autoconfig_name(); - FILE *out, *out_h; - int i; + int ret, i; if (!overwrite && is_present(autoconf_name)) return 0; @@ -1074,45 +1114,25 @@ int conf_write_autoconf(int overwrite) if (conf_touch_deps()) return 1; - out = fopen(".tmpconfig", "w"); - if (!out) - return 1; - - out_h = fopen(".tmpconfig.h", "w"); - if (!out_h) { - fclose(out); - return 1; - } - - conf_write_heading(out, &comment_style_pound); - conf_write_heading(out_h, &comment_style_c); - - for_all_symbols(i, sym) { + for_all_symbols(i, sym) sym_calc_value(sym); - if (!(sym->flags & SYMBOL_WRITE) || !sym->name) - continue; - /* write symbols to auto.conf and autoconf.h */ - print_symbol_for_autoconf(out, sym); - print_symbol_for_c(out_h, sym); - } - fclose(out); - fclose(out_h); + ret = __conf_write_autoconf(conf_get_autoheader_name(), + print_symbol_for_c, + &comment_style_c); + if (ret) + return ret; - name = conf_get_autoheader_name(); - if (make_parent_dir(name)) - return 1; - if (rename(".tmpconfig.h", name)) - return 1; - - if (make_parent_dir(autoconf_name)) - return 1; /* - * This must be the last step, kbuild has a dependency on auto.conf - * and this marks the successful completion of the previous steps. + * Create include/config/auto.conf. This must be the last step because + * Kbuild has a dependency on auto.conf and this marks the successful + * completion of the previous steps. */ - if (rename(".tmpconfig", autoconf_name)) - return 1; + ret = __conf_write_autoconf(conf_get_autoconfig_name(), + print_symbol_for_autoconf, + &comment_style_pound); + if (ret) + return ret; return 0; } From 00d674cb35362dd30df7ff1e0003ad6d6c3ebf3a Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 1 Oct 2021 14:32:51 +0900 Subject: [PATCH 214/587] kconfig: refactor conf_write_dep() The if ... else inside the for-loop is unneeded because one empty line is placed after printing the last element of deps_config. Currently, all errors in conf_write_dep() are ignored. Add proper error checks. Rename it to conf_write_autoconf_cmd(), which is more intuitive. Signed-off-by: Masahiro Yamada --- scripts/kconfig/confdata.c | 62 +++++++++++++++++++++++++------------- 1 file changed, 41 insertions(+), 21 deletions(-) diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c index 7301f4b2f4d5..6ac53bf7aa64 100644 --- a/scripts/kconfig/confdata.c +++ b/scripts/kconfig/confdata.c @@ -957,32 +957,50 @@ next: } /* write a dependency file as used by kbuild to track dependencies */ -static int conf_write_dep(const char *name) +static int conf_write_autoconf_cmd(const char *autoconf_name) { + char name[PATH_MAX], tmp[PATH_MAX]; struct file *file; FILE *out; + int ret; - out = fopen("..config.tmp", "w"); - if (!out) - return 1; - fprintf(out, "deps_config := \\\n"); - for (file = file_list; file; file = file->next) { - if (file->next) - fprintf(out, "\t%s \\\n", file->name); - else - fprintf(out, "\t%s\n", file->name); - } - fprintf(out, "\n%s: \\\n" - "\t$(deps_config)\n\n", conf_get_autoconfig_name()); - - env_write_dep(out, conf_get_autoconfig_name()); - - fprintf(out, "\n$(deps_config): ;\n"); - fclose(out); + ret = snprintf(name, sizeof(name), "%s.cmd", autoconf_name); + if (ret >= sizeof(name)) /* check truncation */ + return -1; if (make_parent_dir(name)) - return 1; - rename("..config.tmp", name); + return -1; + + ret = snprintf(tmp, sizeof(tmp), "%s.cmd.tmp", autoconf_name); + if (ret >= sizeof(tmp)) /* check truncation */ + return -1; + + out = fopen(tmp, "w"); + if (!out) { + perror("fopen"); + return -1; + } + + fprintf(out, "deps_config := \\\n"); + for (file = file_list; file; file = file->next) + fprintf(out, "\t%s \\\n", file->name); + + fprintf(out, "\n%s: $(deps_config)\n\n", autoconf_name); + + env_write_dep(out, autoconf_name); + + fprintf(out, "\n$(deps_config): ;\n"); + + if (ferror(out)) /* error check for all fprintf() calls */ + return -1; + + fclose(out); + + if (rename(tmp, name)) { + perror("rename"); + return -1; + } + return 0; } @@ -1109,7 +1127,9 @@ int conf_write_autoconf(int overwrite) if (!overwrite && is_present(autoconf_name)) return 0; - conf_write_dep("include/config/auto.conf.cmd"); + ret = conf_write_autoconf_cmd(autoconf_name); + if (ret) + return -1; if (conf_touch_deps()) return 1; From fee762d69ad5968dfd0ecbc300810f185ee5c5b8 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 1 Oct 2021 14:32:52 +0900 Subject: [PATCH 215/587] kconfig: refactor conf_touch_dep() If this function fails to touch a dummy header due to missing parent directory, then it creates it and touches the file again. This was needed because CONFIG_FOO_BAR was previously tracked by include/config/foo/bar.h. (include/config/foo/ may not exist here) This is no longer the case since commit 0e0345b77ac4 ("kbuild: redo fake deps at include/config/*.h"); now all the fake headers are placed right under include/config/, like include/config/FOO_BAR. Do not try to create parent directory, include/config/, which already exists. Signed-off-by: Masahiro Yamada --- scripts/kconfig/confdata.c | 22 ++++------------------ 1 file changed, 4 insertions(+), 18 deletions(-) diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c index 6ac53bf7aa64..42bc56ee238c 100644 --- a/scripts/kconfig/confdata.c +++ b/scripts/kconfig/confdata.c @@ -130,31 +130,17 @@ static size_t depfile_prefix_len; /* touch depfile for symbol 'name' */ static int conf_touch_dep(const char *name) { - int fd, ret; - char *d; + int fd; /* check overflow: prefix + name + '\0' must fit in buffer. */ if (depfile_prefix_len + strlen(name) + 1 > sizeof(depfile_path)) return -1; - d = depfile_path + depfile_prefix_len; - strcpy(d, name); + strcpy(depfile_path + depfile_prefix_len, name); - /* Assume directory path already exists. */ fd = open(depfile_path, O_WRONLY | O_CREAT | O_TRUNC, 0644); - if (fd == -1) { - if (errno != ENOENT) - return -1; - - ret = make_parent_dir(depfile_path); - if (ret) - return ret; - - /* Try it again. */ - fd = open(depfile_path, O_WRONLY | O_CREAT | O_TRUNC, 0644); - if (fd == -1) - return -1; - } + if (fd == -1) + return -1; close(fd); return 0; From a3c7ca2b141b9735eb383246e966a4f4322e3e65 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 23 Sep 2021 14:54:18 -0700 Subject: [PATCH 216/587] sparc: Add missing "FORCE" target when using if_changed Fix observed warning: /builds/linux/arch/sparc/boot/Makefile:35: FORCE prerequisite is missing Fixes: e1f86d7b4b2a ("kbuild: warn if FORCE is missing for if_changed(_dep,_rule) and filechk") Signed-off-by: Kees Cook Acked-by: Nicolas Schier Signed-off-by: Masahiro Yamada --- arch/sparc/boot/Makefile | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/sparc/boot/Makefile b/arch/sparc/boot/Makefile index 849236d4eca4..45e5c76d449e 100644 --- a/arch/sparc/boot/Makefile +++ b/arch/sparc/boot/Makefile @@ -22,7 +22,7 @@ ifeq ($(CONFIG_SPARC64),y) # Actual linking -$(obj)/zImage: $(obj)/image +$(obj)/zImage: $(obj)/image FORCE $(call if_changed,gzip) @echo ' kernel: $@ is ready' @@ -31,7 +31,7 @@ $(obj)/vmlinux.aout: vmlinux FORCE @echo ' kernel: $@ is ready' else -$(obj)/zImage: $(obj)/image +$(obj)/zImage: $(obj)/image FORCE $(call if_changed,strip) @echo ' kernel: $@ is ready' @@ -44,7 +44,7 @@ OBJCOPYFLAGS_image.bin := -S -O binary -R .note -R .comment $(obj)/image.bin: $(obj)/image FORCE $(call if_changed,objcopy) -$(obj)/image.gz: $(obj)/image.bin +$(obj)/image.gz: $(obj)/image.bin FORCE $(call if_changed,gzip) UIMAGE_LOADADDR = $(CONFIG_UBOOT_LOAD_ADDR) @@ -56,7 +56,7 @@ quiet_cmd_uimage.o = UIMAGE.O $@ -r -b binary $@ -o $@.o targets += uImage -$(obj)/uImage: $(obj)/image.gz +$(obj)/uImage: $(obj)/image.gz FORCE $(call if_changed,uimage) $(call if_changed,uimage.o) @echo ' Image $@ is ready' From 4a667ba873088d23c4a6d7564239160c9af11783 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 4 Oct 2021 22:16:57 -0700 Subject: [PATCH 217/587] s390/debug: fix kernel-doc warnings Fix kernel-doc warning due to incorrect parameter name in kernel-doc function notation: ../arch/s390/include/asm/debug.h:484: warning: Function parameter or member 'pages' not described in 'DEFINE_STATIC_DEBUG_INFO' ../arch/s390/include/asm/debug.h:484: warning: Excess function parameter 'pages_per_area' description in 'DEFINE_STATIC_DEBUG_INFO' Fixes: d72541f94512 ("s390/debug: add early tracing support") Signed-off-by: Randy Dunlap Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: linux-s390@vger.kernel.org Cc: Peter Oberparleiter Link: https://lore.kernel.org/r/20211005051657.16714-1-rdunlap@infradead.org Signed-off-by: Christian Borntraeger Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/debug.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h index 19a55e1e3a0c..77f24262c25c 100644 --- a/arch/s390/include/asm/debug.h +++ b/arch/s390/include/asm/debug.h @@ -462,7 +462,7 @@ arch_initcall(VNAME(var, reg)) * * @var: Name of debug_info_t variable * @name: Name of debug log (e.g. used for debugfs entry) - * @pages_per_area: Number of pages per area + * @pages: Number of pages per area * @nr_areas: Number of debug areas * @buf_size: Size of data area in each debug entry * @view: Pointer to debug view struct From 25d36a85c61b576401f69e0e205071e6b1befce8 Mon Sep 17 00:00:00 2001 From: Mete Durlu Date: Fri, 1 Oct 2021 15:52:00 +0200 Subject: [PATCH 218/587] s390/test_unwind: convert to KUnit Modified stack unwinder self tests to use kunit framework. The functionality stayed the same but the output format is now in tap13 format. Reviewed-by: Vasily Gorbik Signed-off-by: Mete Durlu Signed-off-by: Vasily Gorbik --- arch/s390/Kconfig | 2 + arch/s390/lib/test_unwind.c | 169 ++++++++++++++++++++---------------- 2 files changed, 98 insertions(+), 73 deletions(-) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 4d63662a919d..8ce2ee8ac88e 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -938,6 +938,8 @@ menu "Selftests" config S390_UNWIND_SELFTEST def_tristate n + depends on KUNIT + default KUNIT_ALL_TESTS prompt "Test unwind functions" help This option enables s390 specific stack unwinder testing kernel diff --git a/arch/s390/lib/test_unwind.c b/arch/s390/lib/test_unwind.c index ecf327d743a0..cfc5f5557c06 100644 --- a/arch/s390/lib/test_unwind.c +++ b/arch/s390/lib/test_unwind.c @@ -3,7 +3,7 @@ * Test module for unwind_for_each_frame */ -#define pr_fmt(fmt) "test_unwind: " fmt +#include #include #include #include @@ -16,6 +16,8 @@ #include #include +struct kunit *current_test; + #define BT_BUF_SIZE (PAGE_SIZE * 4) /* @@ -29,7 +31,7 @@ static void print_backtrace(char *bt) p = strsep(&bt, "\n"); if (!p) break; - pr_err("%s\n", p); + kunit_err(current_test, "%s\n", p); } } @@ -49,7 +51,7 @@ static noinline int test_unwind(struct task_struct *task, struct pt_regs *regs, bt = kmalloc(BT_BUF_SIZE, GFP_ATOMIC); if (!bt) { - pr_err("failed to allocate backtrace buffer\n"); + kunit_err(current_test, "failed to allocate backtrace buffer\n"); return -ENOMEM; } /* Unwind. */ @@ -63,7 +65,7 @@ static noinline int test_unwind(struct task_struct *task, struct pt_regs *regs, if (frame_count++ == max_frames) break; if (state.reliable && !addr) { - pr_err("unwind state reliable but addr is 0\n"); + kunit_err(current_test, "unwind state reliable but addr is 0\n"); ret = -EINVAL; break; } @@ -75,7 +77,7 @@ static noinline int test_unwind(struct task_struct *task, struct pt_regs *regs, stack_type_name(state.stack_info.type), (void *)state.sp, (void *)state.ip); if (bt_pos >= BT_BUF_SIZE) - pr_err("backtrace buffer is too small\n"); + kunit_err(current_test, "backtrace buffer is too small\n"); } frame_count += 1; if (prev_is_func2 && str_has_prefix(sym, "unwindme_func1")) @@ -85,15 +87,15 @@ static noinline int test_unwind(struct task_struct *task, struct pt_regs *regs, /* Check the results. */ if (unwind_error(&state)) { - pr_err("unwind error\n"); + kunit_err(current_test, "unwind error\n"); ret = -EINVAL; } if (!seen_func2_func1) { - pr_err("unwindme_func2 and unwindme_func1 not found\n"); + kunit_err(current_test, "unwindme_func2 and unwindme_func1 not found\n"); ret = -EINVAL; } if (frame_count == max_frames) { - pr_err("Maximum number of frames exceeded\n"); + kunit_err(current_test, "Maximum number of frames exceeded\n"); ret = -EINVAL; } if (ret) @@ -166,7 +168,7 @@ static noinline int unwindme_func4(struct unwindme *u) kp.pre_handler = pgm_pre_handler; ret = register_kprobe(&kp); if (ret < 0) { - pr_err("register_kprobe failed %d\n", ret); + kunit_err(current_test, "register_kprobe failed %d\n", ret); return -EINVAL; } @@ -252,7 +254,7 @@ static int test_unwind_irq(struct unwindme *u) } /* Spawns a task and passes it to test_unwind(). */ -static int test_unwind_task(struct unwindme *u) +static int test_unwind_task(struct kunit *test, struct unwindme *u) { struct task_struct *task; int ret; @@ -267,7 +269,7 @@ static int test_unwind_task(struct unwindme *u) */ task = kthread_run(unwindme_func1, u, "%s", __func__); if (IS_ERR(task)) { - pr_err("kthread_run() failed\n"); + kunit_err(test, "kthread_run() failed\n"); return PTR_ERR(task); } /* @@ -282,77 +284,98 @@ static int test_unwind_task(struct unwindme *u) return ret; } -static int test_unwind_flags(int flags) +struct test_params { + int flags; + char *name; +}; + +/* + * Create required parameter list for tests + */ +static const struct test_params param_list[] = { + {.flags = UWM_DEFAULT, .name = "UWM_DEFAULT"}, + {.flags = UWM_SP, .name = "UWM_SP"}, + {.flags = UWM_REGS, .name = "UWM_REGS"}, + {.flags = UWM_SWITCH_STACK, + .name = "UWM_SWITCH_STACK"}, + {.flags = UWM_SP | UWM_REGS, + .name = "UWM_SP | UWM_REGS"}, + {.flags = UWM_CALLER | UWM_SP, + .name = "WM_CALLER | UWM_SP"}, + {.flags = UWM_CALLER | UWM_SP | UWM_REGS, + .name = "UWM_CALLER | UWM_SP | UWM_REGS"}, + {.flags = UWM_CALLER | UWM_SP | UWM_REGS | UWM_SWITCH_STACK, + .name = "UWM_CALLER | UWM_SP | UWM_REGS | UWM_SWITCH_STACK"}, + {.flags = UWM_THREAD, .name = "UWM_THREAD"}, + {.flags = UWM_THREAD | UWM_SP, + .name = "UWM_THREAD | UWM_SP"}, + {.flags = UWM_THREAD | UWM_CALLER | UWM_SP, + .name = "UWM_THREAD | UWM_CALLER | UWM_SP"}, + {.flags = UWM_IRQ, .name = "UWM_IRQ"}, + {.flags = UWM_IRQ | UWM_SWITCH_STACK, + .name = "UWM_IRQ | UWM_SWITCH_STACK"}, + {.flags = UWM_IRQ | UWM_SP, + .name = "UWM_IRQ | UWM_SP"}, + {.flags = UWM_IRQ | UWM_REGS, + .name = "UWM_IRQ | UWM_REGS"}, + {.flags = UWM_IRQ | UWM_SP | UWM_REGS, + .name = "UWM_IRQ | UWM_SP | UWM_REGS"}, + {.flags = UWM_IRQ | UWM_CALLER | UWM_SP, + .name = "UWM_IRQ | UWM_CALLER | UWM_SP"}, + {.flags = UWM_IRQ | UWM_CALLER | UWM_SP | UWM_REGS, + .name = "UWM_IRQ | UWM_CALLER | UWM_SP | UWM_REGS"}, + {.flags = UWM_IRQ | UWM_CALLER | UWM_SP | UWM_REGS | UWM_SWITCH_STACK, + .name = "UWM_IRQ | UWM_CALLER | UWM_SP | UWM_REGS | UWM_SWITCH_STACK"}, + #ifdef CONFIG_KPROBES + {.flags = UWM_PGM, .name = "UWM_PGM"}, + {.flags = UWM_PGM | UWM_SP, + .name = "UWM_PGM | UWM_SP"}, + {.flags = UWM_PGM | UWM_REGS, + .name = "UWM_PGM | UWM_REGS"}, + {.flags = UWM_PGM | UWM_SP | UWM_REGS, + .name = "UWM_PGM | UWM_SP | UWM_REGS"}, + #endif +}; + +/* + * Parameter description generator: required for KUNIT_ARRAY_PARAM() + */ +static void get_desc(const struct test_params *params, char *desc) +{ + strscpy(desc, params->name, KUNIT_PARAM_DESC_SIZE); +} + +/* + * Create test_unwind_gen_params + */ +KUNIT_ARRAY_PARAM(test_unwind, param_list, get_desc); + +static void test_unwind_flags(struct kunit *test) { struct unwindme u; + const struct test_params *params; - u.flags = flags; + current_test = test; + params = (const struct test_params *)test->param_value; + u.flags = params->flags; if (u.flags & UWM_THREAD) - return test_unwind_task(&u); + KUNIT_EXPECT_EQ(test, 0, test_unwind_task(test, &u)); else if (u.flags & UWM_IRQ) - return test_unwind_irq(&u); + KUNIT_EXPECT_EQ(test, 0, test_unwind_irq(&u)); else - return unwindme_func1(&u); + KUNIT_EXPECT_EQ(test, 0, unwindme_func1(&u)); } -static int test_unwind_init(void) -{ - int failed = 0; - int total = 0; +static struct kunit_case unwind_test_cases[] = { + KUNIT_CASE_PARAM(test_unwind_flags, test_unwind_gen_params), + {} +}; -#define TEST(flags) \ -do { \ - pr_info("[ RUN ] " #flags "\n"); \ - total++; \ - if (!test_unwind_flags((flags))) { \ - pr_info("[ OK ] " #flags "\n"); \ - } else { \ - pr_err("[ FAILED ] " #flags "\n"); \ - failed++; \ - } \ -} while (0) +static struct kunit_suite test_unwind_suite = { + .name = "test_unwind", + .test_cases = unwind_test_cases, +}; - pr_info("running stack unwinder tests"); - TEST(UWM_DEFAULT); - TEST(UWM_SP); - TEST(UWM_REGS); - TEST(UWM_SWITCH_STACK); - TEST(UWM_SP | UWM_REGS); - TEST(UWM_CALLER | UWM_SP); - TEST(UWM_CALLER | UWM_SP | UWM_REGS); - TEST(UWM_CALLER | UWM_SP | UWM_REGS | UWM_SWITCH_STACK); - TEST(UWM_THREAD); - TEST(UWM_THREAD | UWM_SP); - TEST(UWM_THREAD | UWM_CALLER | UWM_SP); - TEST(UWM_IRQ); - TEST(UWM_IRQ | UWM_SWITCH_STACK); - TEST(UWM_IRQ | UWM_SP); - TEST(UWM_IRQ | UWM_REGS); - TEST(UWM_IRQ | UWM_SP | UWM_REGS); - TEST(UWM_IRQ | UWM_CALLER | UWM_SP); - TEST(UWM_IRQ | UWM_CALLER | UWM_SP | UWM_REGS); - TEST(UWM_IRQ | UWM_CALLER | UWM_SP | UWM_REGS | UWM_SWITCH_STACK); -#ifdef CONFIG_KPROBES - TEST(UWM_PGM); - TEST(UWM_PGM | UWM_SP); - TEST(UWM_PGM | UWM_REGS); - TEST(UWM_PGM | UWM_SP | UWM_REGS); -#endif -#undef TEST - if (failed) { - pr_err("%d of %d stack unwinder tests failed", failed, total); - WARN(1, "%d of %d stack unwinder tests failed", failed, total); - } else { - pr_info("all %d stack unwinder tests passed", total); - } +kunit_test_suites(&test_unwind_suite); - return failed ? -EINVAL : 0; -} - -static void test_unwind_exit(void) -{ -} - -module_init(test_unwind_init); -module_exit(test_unwind_exit); MODULE_LICENSE("GPL"); From fbbd140737121637b98aef53440c7a2676e412cf Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 1 Oct 2021 12:56:55 +0200 Subject: [PATCH 219/587] s390/barrier: factor out bcr_serialize() Factor out bcr_serialize() inline assembly function which describes what the bcr instruction is used for. Use bcr_serialize() like before in mb(), but also in upcoming changes. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/barrier.h | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h index f9eddbca79d2..2c057e1f3200 100644 --- a/arch/s390/include/asm/barrier.h +++ b/arch/s390/include/asm/barrier.h @@ -16,20 +16,24 @@ #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES /* Fast-BCR without checkpoint synchronization */ -#define __ASM_BARRIER "bcr 14,0\n" +#define __ASM_BCR_SERIALIZE "bcr 14,0\n" #else -#define __ASM_BARRIER "bcr 15,0\n" +#define __ASM_BCR_SERIALIZE "bcr 15,0\n" #endif -#define mb() do { asm volatile(__ASM_BARRIER : : : "memory"); } while (0) +static __always_inline void bcr_serialize(void) +{ + asm volatile(__ASM_BCR_SERIALIZE : : : "memory"); +} -#define rmb() barrier() -#define wmb() barrier() -#define dma_rmb() mb() -#define dma_wmb() mb() -#define __smp_mb() mb() -#define __smp_rmb() rmb() -#define __smp_wmb() wmb() +#define mb() bcr_serialize() +#define rmb() barrier() +#define wmb() barrier() +#define dma_rmb() mb() +#define dma_wmb() mb() +#define __smp_mb() mb() +#define __smp_rmb() rmb() +#define __smp_wmb() wmb() #define __smp_store_release(p, v) \ do { \ From e16d02ee3f348900a0a2cf41931b204e2042f5e3 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 1 Oct 2021 12:47:01 +0200 Subject: [PATCH 220/587] s390: introduce text_poke_sync() Introduce a text_poke_sync() similar to what x86 has. This can be used to execute a serializing instruction on all CPUs (including the current one). Note: according to the Principles of Operation an IPI (= interrupt) will already serialize a CPU, however it is better to be explicit. In addition on_each_cpu() makes sure that also the current CPU get serialized - just to make sure that possible preemption can prevent some theoretical case where a CPU will not be serialized. Therefore text_poke_sync() has to be used whenever code got modified, just to avoid to rely on implicit serialization. Also introduce text_poke_sync_lock() which will also disable CPU hotplug, to prevent that any CPU is just going online with a prefetched old version of a modified instruction. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/text-patching.h | 16 ++++++++++++++++ arch/s390/kernel/alternative.c | 20 ++++++++++++++++++++ 2 files changed, 36 insertions(+) create mode 100644 arch/s390/include/asm/text-patching.h diff --git a/arch/s390/include/asm/text-patching.h b/arch/s390/include/asm/text-patching.h new file mode 100644 index 000000000000..b219056a8817 --- /dev/null +++ b/arch/s390/include/asm/text-patching.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_S390_TEXT_PATCHING_H +#define _ASM_S390_TEXT_PATCHING_H + +#include + +static __always_inline void sync_core(void) +{ + bcr_serialize(); +} + +void text_poke_sync(void); +void text_poke_sync_lock(void); + +#endif /* _ASM_S390_TEXT_PATCHING_H */ diff --git a/arch/s390/kernel/alternative.c b/arch/s390/kernel/alternative.c index c22ea1c3ef84..cce0ddee2d02 100644 --- a/arch/s390/kernel/alternative.c +++ b/arch/s390/kernel/alternative.c @@ -1,5 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include +#include +#include #include #include #include @@ -110,3 +113,20 @@ void __init apply_alternative_instructions(void) { apply_alternatives(__alt_instructions, __alt_instructions_end); } + +static void do_sync_core(void *info) +{ + sync_core(); +} + +void text_poke_sync(void) +{ + on_each_cpu(do_sync_core, NULL, 1); +} + +void text_poke_sync_lock(void) +{ + cpus_read_lock(); + text_poke_sync(); + cpus_read_unlock(); +} From 1c27dfb24e3b2a026488aa51e9991e27a1d94164 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 1 Oct 2021 14:15:56 +0200 Subject: [PATCH 221/587] s390/jump_label: use text_poke_sync() Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/jump_label.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/arch/s390/kernel/jump_label.c b/arch/s390/kernel/jump_label.c index 9156653b56f6..1e245da82197 100644 --- a/arch/s390/kernel/jump_label.c +++ b/arch/s390/kernel/jump_label.c @@ -6,8 +6,8 @@ * Author(s): Jan Glauber */ #include -#include #include +#include #include struct insn { @@ -72,15 +72,11 @@ static void __jump_label_transform(struct jump_entry *entry, s390_kernel_write(code, &new, sizeof(new)); } -static void __jump_label_sync(void *dummy) -{ -} - void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type) { __jump_label_transform(entry, type, 0); - smp_call_function(__jump_label_sync, NULL, 1); + text_poke_sync(); } void arch_jump_label_transform_static(struct jump_entry *entry, From ae2b9a11b494a9ec59d7dc11d42654d659f859c6 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 1 Oct 2021 14:21:43 +0200 Subject: [PATCH 222/587] s390/ftrace: use text_poke_sync_lock() Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/ftrace.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 5d0c45c13b5f..04a3e88c58d7 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -207,14 +208,13 @@ void arch_ftrace_update_code(int command) ftrace_modify_all_code(command); } -static void __ftrace_sync(void *dummy) -{ -} - int ftrace_arch_code_modify_post_process(void) { - /* Send SIGP to the other CPUs, so they see the new code. */ - smp_call_function(__ftrace_sync, NULL, 1); + /* + * Flush any pre-fetched instructions on all + * CPUs to make the new code visible. + */ + text_poke_sync_lock(); return 0; } From e5873d6f7a7aa5f9de73ca829034fcaaf7b1d25e Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 1 Oct 2021 14:24:42 +0200 Subject: [PATCH 223/587] s390/ftrace: add missing serialization for graph caller patching CPUs must be serialized also when ftrace_graph_caller gets patched. This is missing since ftrace function graph support was added on s390. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/ftrace.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 04a3e88c58d7..e416aaaaf524 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -268,12 +268,14 @@ NOKPROBE_SYMBOL(prepare_ftrace_return); int ftrace_enable_ftrace_graph_caller(void) { brcl_disable(ftrace_graph_caller); + text_poke_sync_lock(); return 0; } int ftrace_disable_ftrace_graph_caller(void) { brcl_enable(ftrace_graph_caller); + text_poke_sync_lock(); return 0; } From 4e0502b8b31032abbc0424cff222139288a3891a Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 4 Oct 2021 12:02:35 +0200 Subject: [PATCH 224/587] s390/jump_label: make use of HAVE_JUMP_LABEL_BATCH Specify HAVE_JUMP_LABEL_BATCH in header file. This allows to make use of the arch_jump_label_transform_queue()/arch_jump_label_transform_apply() mechanism. However unlike on x86, which currently is the only user of this mechanism, the to be patched instructions are still directly modified. The only difference to before is that serialization is only done after all instructions have been modified. This way the number of serialization/synchronization events is reduced. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/jump_label.h | 2 ++ arch/s390/kernel/jump_label.c | 13 +++++++++++++ 2 files changed, 15 insertions(+) diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h index dcb1bba4f406..916cfcb36d8a 100644 --- a/arch/s390/include/asm/jump_label.h +++ b/arch/s390/include/asm/jump_label.h @@ -2,6 +2,8 @@ #ifndef _ASM_S390_JUMP_LABEL_H #define _ASM_S390_JUMP_LABEL_H +#define HAVE_JUMP_LABEL_BATCH + #ifndef __ASSEMBLY__ #include diff --git a/arch/s390/kernel/jump_label.c b/arch/s390/kernel/jump_label.c index 1e245da82197..edefb40f172b 100644 --- a/arch/s390/kernel/jump_label.c +++ b/arch/s390/kernel/jump_label.c @@ -79,8 +79,21 @@ void arch_jump_label_transform(struct jump_entry *entry, text_poke_sync(); } +bool arch_jump_label_transform_queue(struct jump_entry *entry, + enum jump_label_type type) +{ + __jump_label_transform(entry, type, 0); + return true; +} + +void arch_jump_label_transform_apply(void) +{ + text_poke_sync(); +} + void arch_jump_label_transform_static(struct jump_entry *entry, enum jump_label_type type) { __jump_label_transform(entry, type, 1); + text_poke_sync(); } From acd6c9afc63cbb571d5312e7f7583bf266e61f69 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 4 Oct 2021 12:03:42 +0200 Subject: [PATCH 225/587] s390/jump_label: rename __jump_label_transform() Trivial patch just to get rid of the leading underscores. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/jump_label.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/s390/kernel/jump_label.c b/arch/s390/kernel/jump_label.c index edefb40f172b..0546c67da99b 100644 --- a/arch/s390/kernel/jump_label.c +++ b/arch/s390/kernel/jump_label.c @@ -48,9 +48,9 @@ static struct insn orignop = { .offset = JUMP_LABEL_NOP_OFFSET >> 1, }; -static void __jump_label_transform(struct jump_entry *entry, - enum jump_label_type type, - int init) +static void jump_label_transform(struct jump_entry *entry, + enum jump_label_type type, + int init) { void *code = (void *)jump_entry_code(entry); struct insn old, new; @@ -75,14 +75,14 @@ static void __jump_label_transform(struct jump_entry *entry, void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type) { - __jump_label_transform(entry, type, 0); + jump_label_transform(entry, type, 0); text_poke_sync(); } bool arch_jump_label_transform_queue(struct jump_entry *entry, enum jump_label_type type) { - __jump_label_transform(entry, type, 0); + jump_label_transform(entry, type, 0); return true; } @@ -94,6 +94,6 @@ void arch_jump_label_transform_apply(void) void arch_jump_label_transform_static(struct jump_entry *entry, enum jump_label_type type) { - __jump_label_transform(entry, type, 1); + jump_label_transform(entry, type, 1); text_poke_sync(); } From 0c14c037952c0e29c3c66ccad6301648e02e11e1 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 4 Oct 2021 12:07:35 +0200 Subject: [PATCH 226/587] s390/jump_label: add __init_or_module annotation Add missing __init_or_module to arch_jump_label_transform_static(). Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/jump_label.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/s390/kernel/jump_label.c b/arch/s390/kernel/jump_label.c index 0546c67da99b..6bec000c6c1c 100644 --- a/arch/s390/kernel/jump_label.c +++ b/arch/s390/kernel/jump_label.c @@ -7,6 +7,7 @@ */ #include #include +#include #include #include @@ -91,8 +92,8 @@ void arch_jump_label_transform_apply(void) text_poke_sync(); } -void arch_jump_label_transform_static(struct jump_entry *entry, - enum jump_label_type type) +void __init_or_module arch_jump_label_transform_static(struct jump_entry *entry, + enum jump_label_type type) { jump_label_transform(entry, type, 1); text_poke_sync(); From 5740a7c71ab6721863f7dcfc8ab96be00b0a4b58 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 4 Oct 2021 16:10:24 +0200 Subject: [PATCH 227/587] s390/ftrace: add HAVE_DYNAMIC_FTRACE_WITH_ARGS support Add HAVE_DYNAMIC_FTRACE_WITH_ARGS support similar to commit 02a474ca266a ("ftrace/x86: Allow for arguments to be passed in to ftrace_regs by default"). s390's ftrace implementation always provides all registers with pt_regs, therefore this is trivial. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/Kconfig | 1 + arch/s390/include/asm/ftrace.h | 9 +++++++++ 2 files changed, 10 insertions(+) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 8ce2ee8ac88e..03eb3ec08b07 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -153,6 +153,7 @@ config S390 select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE + select HAVE_DYNAMIC_FTRACE_WITH_ARGS select HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_EBPF_JIT if PACK_STACK && HAVE_MARCH_Z196_FEATURES select HAVE_EFFICIENT_UNALIGNED_ACCESS diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h index d1841f4176be..98c066cb347f 100644 --- a/arch/s390/include/asm/ftrace.h +++ b/arch/s390/include/asm/ftrace.h @@ -42,6 +42,15 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr) return addr; } +struct ftrace_regs { + struct pt_regs regs; +}; + +static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs *fregs) +{ + return &fregs->regs; +} + /* * Even though the system call numbers are identical for s390/s390x a * different system call table is used for compat tasks. This may lead From 176510ebecd1ca201a8808dbbee9991eca005207 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 4 Oct 2021 16:16:45 +0200 Subject: [PATCH 228/587] s390/ftrace: add ftrace_instruction_pointer_set() helper function Add ftrace_instruction_pointer_set() helper function to match x86. See commit 2860cd8a2353 ("livepatch: Use the default ftrace_ops instead of REGS when ARGS is available"). Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/ftrace.h | 8 ++++++++ arch/s390/include/asm/livepatch.h | 4 +--- 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h index 98c066cb347f..3baceb4a7d3c 100644 --- a/arch/s390/include/asm/ftrace.h +++ b/arch/s390/include/asm/ftrace.h @@ -51,6 +51,14 @@ static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs * return &fregs->regs; } +static __always_inline void ftrace_instruction_pointer_set(struct ftrace_regs *fregs, + unsigned long ip) +{ + struct pt_regs *regs = arch_ftrace_get_regs(fregs); + + regs->psw.addr = ip; +} + /* * Even though the system call numbers are identical for s390/s390x a * different system call table is used for compat tasks. This may lead diff --git a/arch/s390/include/asm/livepatch.h b/arch/s390/include/asm/livepatch.h index d578a8c76676..5209f223331a 100644 --- a/arch/s390/include/asm/livepatch.h +++ b/arch/s390/include/asm/livepatch.h @@ -16,9 +16,7 @@ static inline void klp_arch_set_pc(struct ftrace_regs *fregs, unsigned long ip) { - struct pt_regs *regs = ftrace_get_regs(fregs); - - regs->psw.addr = ip; + ftrace_instruction_pointer_set(fregs, ip); } #endif From 894979689d3ac4780601b4506a03b4722398caf5 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 4 Oct 2021 20:24:12 +0200 Subject: [PATCH 229/587] s390/ftrace: provide separate ftrace_caller/ftrace_regs_caller implementations ftrace_regs_caller is an alias to ftrace_caller - making ftrace_caller quite heavyweight. Split the function and provide an ftrace_caller implementation which comes with fewer instructions. Especially getting rid of 'stosm' on each function entry should help here, e.g. to have less performance impact on live patched functions. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/ftrace.h | 1 - arch/s390/kernel/mcount.S | 41 ++++++++++++++++++++++++---------- 2 files changed, 29 insertions(+), 13 deletions(-) diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h index 3baceb4a7d3c..4a721b44d4f4 100644 --- a/arch/s390/include/asm/ftrace.h +++ b/arch/s390/include/asm/ftrace.h @@ -17,7 +17,6 @@ void ftrace_caller(void); -extern char ftrace_graph_caller_end; extern void *ftrace_func; struct dyn_arch_ftrace { }; diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index 6b13797143a7..cc25fbd75ea9 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -33,13 +33,15 @@ ENDPROC(ftrace_stub) #define TRACED_FUNC_FRAME_SIZE STACK_FRAME_OVERHEAD #endif -ENTRY(ftrace_caller) - .globl ftrace_regs_caller - .set ftrace_regs_caller,ftrace_caller + .macro ftrace_regs_entry, allregs=0 stg %r14,(__SF_GPRS+8*8)(%r15) # save traced function caller + + .if \allregs == 1 lghi %r14,0 # save condition code ipm %r14 # don't put any instructions sllg %r14,%r14,16 # clobbering CC before this point + .endif + lgr %r1,%r15 # allocate stack frame for ftrace_caller to contain traced function aghi %r15,-TRACED_FUNC_FRAME_SIZE @@ -49,13 +51,30 @@ ENTRY(ftrace_caller) # allocate pt_regs and stack frame for ftrace_trace_function aghi %r15,-STACK_FRAME_SIZE stg %r1,(STACK_PTREGS_GPRS+15*8)(%r15) + + .if \allregs == 1 stg %r14,(STACK_PTREGS_PSW)(%r15) - lg %r14,(__SF_GPRS+8*8)(%r1) # restore original return address stosm (STACK_PTREGS_PSW)(%r15),0 + .endif + + lg %r14,(__SF_GPRS+8*8)(%r1) # restore original return address aghi %r1,-TRACED_FUNC_FRAME_SIZE stg %r1,__SF_BACKCHAIN(%r15) stg %r0,(STACK_PTREGS_PSW+8)(%r15) stmg %r2,%r14,(STACK_PTREGS_GPRS+2*8)(%r15) + .endm + +SYM_CODE_START(ftrace_regs_caller) + ftrace_regs_entry 1 + j ftrace_common +SYM_CODE_END(ftrace_regs_caller) + +SYM_CODE_START(ftrace_caller) + ftrace_regs_entry 0 + j ftrace_common +SYM_CODE_END(ftrace_caller) + +SYM_CODE_START(ftrace_common) #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES aghik %r2,%r0,-MCOUNT_INSN_SIZE lgrl %r4,function_trace_op @@ -74,24 +93,22 @@ ENTRY(ftrace_caller) #ifdef CONFIG_FUNCTION_GRAPH_TRACER # The j instruction gets runtime patched to a nop instruction. # See ftrace_enable_ftrace_graph_caller. - .globl ftrace_graph_caller -ftrace_graph_caller: - j ftrace_graph_caller_end +SYM_INNER_LABEL(ftrace_graph_caller, SYM_L_GLOBAL) + j .Lftrace_graph_caller_end lmg %r2,%r3,(STACK_PTREGS_GPRS+14*8)(%r15) lg %r4,(STACK_PTREGS_PSW+8)(%r15) brasl %r14,prepare_ftrace_return stg %r2,(STACK_PTREGS_GPRS+14*8)(%r15) -ftrace_graph_caller_end: - .globl ftrace_graph_caller_end +.Lftrace_graph_caller_end: #endif lg %r1,(STACK_PTREGS_PSW+8)(%r15) lmg %r2,%r15,(STACK_PTREGS_GPRS+2*8)(%r15) BR_EX %r1 -ENDPROC(ftrace_caller) +SYM_CODE_END(ftrace_common) #ifdef CONFIG_FUNCTION_GRAPH_TRACER -ENTRY(return_to_handler) +SYM_FUNC_START(return_to_handler) stmg %r2,%r5,32(%r15) lgr %r1,%r15 aghi %r15,-STACK_FRAME_OVERHEAD @@ -101,6 +118,6 @@ ENTRY(return_to_handler) lgr %r14,%r2 lmg %r2,%r5,32(%r15) BR_EX %r14 -ENDPROC(return_to_handler) +SYM_FUNC_END(return_to_handler) #endif From 885359c42942566c91bbc93eb1acfaea86d95bcf Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 7 Oct 2021 18:12:50 +0200 Subject: [PATCH 230/587] s390/ptrace: fix coding style Reported-by: Steffen Maier Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/ptrace.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index 61b22aa990e7..662ee212ba51 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -76,8 +76,7 @@ enum { * The pt_regs struct defines the way the registers are stored on * the stack during a system call. */ -struct pt_regs -{ +struct pt_regs { union { user_pt_regs user_regs; struct { From 3990b5baf225a3a96e70a784747d31002686c300 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 6 Oct 2021 14:38:14 +0200 Subject: [PATCH 231/587] selftests/ftrace: add s390 support for kprobe args tests This is the s390 variant of commit 9855c4626c67 ("selftests/ftrace: Add ppc support for kprobe args tests"). Acked-by: Ilya Leoshkevich Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- .../selftests/ftrace/test.d/kprobe/kprobe_args_string.tc | 3 +++ .../selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc | 4 ++++ 2 files changed, 7 insertions(+) diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc index 84285a6f60b0..dc7ade196798 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc @@ -22,6 +22,9 @@ ppc64*) ppc*) ARG1=%r3 ;; +s390*) + ARG1=%r2 +;; *) echo "Please implement other architecture here" exit_untested diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc index 474ca1a9a088..47d84b5cb6ca 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc @@ -32,6 +32,10 @@ ppc*) GOODREG=%r3 BADREG=%msr ;; +s390*) + GOODREG=%r2 + BADREG=%s2 +;; *) echo "Please implement other architecture here" exit_untested From a30b5b03047602be56c5b8ffc3a0e4cfed17561c Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 6 Oct 2021 11:59:29 +0200 Subject: [PATCH 232/587] s390/ptrace: add function argument access API Add regs_get_kernel_argument() which returns Nth argument of a function call. This enables ftrace kprobe events to access kernel function arguments via $argN syntax. This is the s390 variant of commit a823c35ff2ed ("arm64: ptrace: Add function argument access API"). Acked-by: Ilya Leoshkevich Reviewed-by: Steffen Maier Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/Kconfig | 1 + arch/s390/include/asm/ptrace.h | 19 +++++++++++++++++++ 2 files changed, 20 insertions(+) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 03eb3ec08b07..c35c98e515a2 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -160,6 +160,7 @@ config S390 select HAVE_FAST_GUP select HAVE_FENTRY select HAVE_FTRACE_MCOUNT_RECORD + select HAVE_FUNCTION_ARG_ACCESS_API select HAVE_FUNCTION_ERROR_INJECTION select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index 662ee212ba51..82fc11907451 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -196,6 +196,25 @@ const char *regs_query_register_name(unsigned int offset); unsigned long regs_get_register(struct pt_regs *regs, unsigned int offset); unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n); +/** + * regs_get_kernel_argument() - get Nth function argument in kernel + * @regs: pt_regs of that context + * @n: function argument number (start from 0) + * + * regs_get_kernel_argument() returns @n th argument of the function call. + */ +static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, + unsigned int n) +{ + unsigned int argoffset = STACK_FRAME_OVERHEAD / sizeof(long); + +#define NR_REG_ARGUMENTS 5 + if (n < NR_REG_ARGUMENTS) + return regs_get_register(regs, 2 + n); + n -= NR_REG_ARGUMENTS; + return regs_get_kernel_stack_nth(regs, argoffset + n); +} + static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) { return regs->gprs[15]; From b2f583937aad0e43cdf18186070e5502983f60fd Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 1 Oct 2021 16:02:01 +0300 Subject: [PATCH 233/587] s390/cmm: use string_upper() instead of open coded variant Use string_upper() from string helper module instead of open coded variant. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20211001130201.72545-1-andriy.shevchenko@linux.intel.com [hca@linux.ibm.com: removed hunk which converts extmem.c] Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/mm/cmm.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index 1141c8d5c0d0..2203164b39da 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -14,8 +14,8 @@ #include #include #include +#include #include -#include #include #include #include @@ -394,13 +394,10 @@ static int __init cmm_init(void) goto out_sysctl; #ifdef CONFIG_CMM_IUCV /* convert sender to uppercase characters */ - if (sender) { - int len = strlen(sender); - while (len--) - sender[len] = toupper(sender[len]); - } else { + if (sender) + string_upper(sender, sender); + else sender = cmm_default_sender; - } rc = smsg_register_callback(SMSG_PREFIX, cmm_smsg_target); if (rc < 0) From bf2928c7a284e31f9f91a004b5dca09c522157c0 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 10 Sep 2021 08:22:06 +0200 Subject: [PATCH 234/587] PCI/VPD: Add pci_read/write_vpd_any() In certain cases we need a variant of pci_read_vpd()/pci_write_vpd() that does not check against dev->vpd.len. Such cases are: - Reading VPD if dev->vpd.len isn't set yet (in pci_vpd_size()) - Devices that map non-VPD information to arbitrary places in VPD address space (example: Chelsio T3 EEPROM write-protect flag) Therefore add pci_read_vpd_any() and pci_write_vpd_any() that check against PCI_VPD_MAX_SIZE only. Link: https://lore.kernel.org/r/93ecce28-a158-f02a-d134-8afcaced8efe@gmail.com Signed-off-by: Heiner Kallweit Signed-off-by: Bjorn Helgaas Acked-by: Jakub Kicinski --- drivers/pci/vpd.c | 72 +++++++++++++++++++++++++++++++-------------- include/linux/pci.h | 2 ++ 2 files changed, 52 insertions(+), 22 deletions(-) diff --git a/drivers/pci/vpd.c b/drivers/pci/vpd.c index 4be24890132e..0a804715d98e 100644 --- a/drivers/pci/vpd.c +++ b/drivers/pci/vpd.c @@ -156,9 +156,10 @@ static int pci_vpd_wait(struct pci_dev *dev, bool set) } static ssize_t pci_vpd_read(struct pci_dev *dev, loff_t pos, size_t count, - void *arg) + void *arg, bool check_size) { struct pci_vpd *vpd = &dev->vpd; + unsigned int max_len = check_size ? vpd->len : PCI_VPD_MAX_SIZE; int ret = 0; loff_t end = pos + count; u8 *buf = arg; @@ -169,11 +170,11 @@ static ssize_t pci_vpd_read(struct pci_dev *dev, loff_t pos, size_t count, if (pos < 0) return -EINVAL; - if (pos > vpd->len) + if (pos >= max_len) return 0; - if (end > vpd->len) { - end = vpd->len; + if (end > max_len) { + end = max_len; count = end - pos; } @@ -217,9 +218,10 @@ static ssize_t pci_vpd_read(struct pci_dev *dev, loff_t pos, size_t count, } static ssize_t pci_vpd_write(struct pci_dev *dev, loff_t pos, size_t count, - const void *arg) + const void *arg, bool check_size) { struct pci_vpd *vpd = &dev->vpd; + unsigned int max_len = check_size ? vpd->len : PCI_VPD_MAX_SIZE; const u8 *buf = arg; loff_t end = pos + count; int ret = 0; @@ -230,7 +232,7 @@ static ssize_t pci_vpd_write(struct pci_dev *dev, loff_t pos, size_t count, if (pos < 0 || (pos & 3) || (count & 3)) return -EINVAL; - if (end > vpd->len) + if (end > max_len) return -EINVAL; if (mutex_lock_killable(&vpd->lock)) @@ -381,6 +383,24 @@ static int pci_vpd_find_info_keyword(const u8 *buf, unsigned int off, return -ENOENT; } +static ssize_t __pci_read_vpd(struct pci_dev *dev, loff_t pos, size_t count, void *buf, + bool check_size) +{ + ssize_t ret; + + if (dev->dev_flags & PCI_DEV_FLAGS_VPD_REF_F0) { + dev = pci_get_func0_dev(dev); + if (!dev) + return -ENODEV; + + ret = pci_vpd_read(dev, pos, count, buf, check_size); + pci_dev_put(dev); + return ret; + } + + return pci_vpd_read(dev, pos, count, buf, check_size); +} + /** * pci_read_vpd - Read one entry from Vital Product Data * @dev: PCI device struct @@ -389,6 +409,20 @@ static int pci_vpd_find_info_keyword(const u8 *buf, unsigned int off, * @buf: pointer to where to store result */ ssize_t pci_read_vpd(struct pci_dev *dev, loff_t pos, size_t count, void *buf) +{ + return __pci_read_vpd(dev, pos, count, buf, true); +} +EXPORT_SYMBOL(pci_read_vpd); + +/* Same, but allow to access any address */ +ssize_t pci_read_vpd_any(struct pci_dev *dev, loff_t pos, size_t count, void *buf) +{ + return __pci_read_vpd(dev, pos, count, buf, false); +} +EXPORT_SYMBOL(pci_read_vpd_any); + +static ssize_t __pci_write_vpd(struct pci_dev *dev, loff_t pos, size_t count, + const void *buf, bool check_size) { ssize_t ret; @@ -397,14 +431,13 @@ ssize_t pci_read_vpd(struct pci_dev *dev, loff_t pos, size_t count, void *buf) if (!dev) return -ENODEV; - ret = pci_vpd_read(dev, pos, count, buf); + ret = pci_vpd_write(dev, pos, count, buf, check_size); pci_dev_put(dev); return ret; } - return pci_vpd_read(dev, pos, count, buf); + return pci_vpd_write(dev, pos, count, buf, check_size); } -EXPORT_SYMBOL(pci_read_vpd); /** * pci_write_vpd - Write entry to Vital Product Data @@ -415,22 +448,17 @@ EXPORT_SYMBOL(pci_read_vpd); */ ssize_t pci_write_vpd(struct pci_dev *dev, loff_t pos, size_t count, const void *buf) { - ssize_t ret; - - if (dev->dev_flags & PCI_DEV_FLAGS_VPD_REF_F0) { - dev = pci_get_func0_dev(dev); - if (!dev) - return -ENODEV; - - ret = pci_vpd_write(dev, pos, count, buf); - pci_dev_put(dev); - return ret; - } - - return pci_vpd_write(dev, pos, count, buf); + return __pci_write_vpd(dev, pos, count, buf, true); } EXPORT_SYMBOL(pci_write_vpd); +/* Same, but allow to access any address */ +ssize_t pci_write_vpd_any(struct pci_dev *dev, loff_t pos, size_t count, const void *buf) +{ + return __pci_write_vpd(dev, pos, count, buf, false); +} +EXPORT_SYMBOL(pci_write_vpd_any); + int pci_vpd_find_ro_info_keyword(const void *buf, unsigned int len, const char *kw, unsigned int *size) { diff --git a/include/linux/pci.h b/include/linux/pci.h index cd8aa6fce204..9649bd9e468d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1350,6 +1350,8 @@ void pci_unlock_rescan_remove(void); /* Vital Product Data routines */ ssize_t pci_read_vpd(struct pci_dev *dev, loff_t pos, size_t count, void *buf); ssize_t pci_write_vpd(struct pci_dev *dev, loff_t pos, size_t count, const void *buf); +ssize_t pci_read_vpd_any(struct pci_dev *dev, loff_t pos, size_t count, void *buf); +ssize_t pci_write_vpd_any(struct pci_dev *dev, loff_t pos, size_t count, const void *buf); /* Helper functions for low-level code (drivers/pci/setup-[bus,res].c) */ resource_size_t pcibios_retrieve_fw_addr(struct pci_dev *dev, int idx); From f55fee56a631032969480e4b0ee5d79734fe3c69 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Mon, 20 Sep 2021 12:29:45 +0530 Subject: [PATCH 235/587] PCI: qcom-ep: Add Qualcomm PCIe Endpoint controller driver Add driver for Qualcomm PCIe Endpoint controller based on the DesignWare core with added Qualcomm-specific wrapper around the core. The driver support is very basic such that it supports only enumeration, PCIe read/write, and MSI. There is no ASPM and PM support for now but these will be added later. The driver is capable of using the PERST# and WAKE# side-band GPIOs for operation and written on top of the DWC PCI framework. [bhelgaas: wrap a few long lines] Co-developed-by: Siddartha Mohanadoss [mani: restructured the driver and fixed several bugs for upstream] Link: https://lore.kernel.org/r/20210920065946.15090-3-manivannan.sadhasivam@linaro.org Signed-off-by: Siddartha Mohanadoss Signed-off-by: Manivannan Sadhasivam Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas Reviewed-by: Rob Herring --- drivers/pci/controller/dwc/Kconfig | 10 + drivers/pci/controller/dwc/Makefile | 1 + .../pci/controller/dwc/pcie-designware-ep.c | 3 + drivers/pci/controller/dwc/pcie-qcom-ep.c | 721 ++++++++++++++++++ 4 files changed, 735 insertions(+) create mode 100644 drivers/pci/controller/dwc/pcie-qcom-ep.c diff --git a/drivers/pci/controller/dwc/Kconfig b/drivers/pci/controller/dwc/Kconfig index 76c0a63a3f64..49bcbe18a575 100644 --- a/drivers/pci/controller/dwc/Kconfig +++ b/drivers/pci/controller/dwc/Kconfig @@ -180,6 +180,16 @@ config PCIE_QCOM PCIe controller uses the DesignWare core plus Qualcomm-specific hardware wrappers. +config PCIE_QCOM_EP + tristate "Qualcomm PCIe controller - Endpoint mode" + depends on OF && (ARCH_QCOM || COMPILE_TEST) + depends on PCI_ENDPOINT + select PCIE_DW_EP + help + Say Y here to enable support for the PCIe controllers on Qualcomm SoCs + to work in endpoint mode. The PCIe controller uses the DesignWare core + plus Qualcomm-specific hardware wrappers. + config PCIE_ARMADA_8K bool "Marvell Armada-8K PCIe controller" depends on ARCH_MVEBU || COMPILE_TEST diff --git a/drivers/pci/controller/dwc/Makefile b/drivers/pci/controller/dwc/Makefile index 73244409792c..8ba7b67f5e50 100644 --- a/drivers/pci/controller/dwc/Makefile +++ b/drivers/pci/controller/dwc/Makefile @@ -12,6 +12,7 @@ obj-$(CONFIG_PCI_KEYSTONE) += pci-keystone.o obj-$(CONFIG_PCI_LAYERSCAPE) += pci-layerscape.o obj-$(CONFIG_PCI_LAYERSCAPE_EP) += pci-layerscape-ep.o obj-$(CONFIG_PCIE_QCOM) += pcie-qcom.o +obj-$(CONFIG_PCIE_QCOM_EP) += pcie-qcom-ep.o obj-$(CONFIG_PCIE_ARMADA_8K) += pcie-armada8k.o obj-$(CONFIG_PCIE_ARTPEC6) += pcie-artpec6.o obj-$(CONFIG_PCIE_ROCKCHIP_DW_HOST) += pcie-dw-rockchip.o diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c index 998b698f4085..0eda8236c125 100644 --- a/drivers/pci/controller/dwc/pcie-designware-ep.c +++ b/drivers/pci/controller/dwc/pcie-designware-ep.c @@ -83,6 +83,7 @@ void dw_pcie_ep_reset_bar(struct dw_pcie *pci, enum pci_barno bar) for (func_no = 0; func_no < funcs; func_no++) __dw_pcie_ep_reset_bar(pci, func_no, bar, 0); } +EXPORT_SYMBOL_GPL(dw_pcie_ep_reset_bar); static u8 __dw_pcie_ep_find_next_cap(struct dw_pcie_ep *ep, u8 func_no, u8 cap_ptr, u8 cap) @@ -485,6 +486,7 @@ int dw_pcie_ep_raise_legacy_irq(struct dw_pcie_ep *ep, u8 func_no) return -EINVAL; } +EXPORT_SYMBOL_GPL(dw_pcie_ep_raise_legacy_irq); int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no, u8 interrupt_num) @@ -536,6 +538,7 @@ int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no, return 0; } +EXPORT_SYMBOL_GPL(dw_pcie_ep_raise_msi_irq); int dw_pcie_ep_raise_msix_irq_doorbell(struct dw_pcie_ep *ep, u8 func_no, u16 interrupt_num) diff --git a/drivers/pci/controller/dwc/pcie-qcom-ep.c b/drivers/pci/controller/dwc/pcie-qcom-ep.c new file mode 100644 index 000000000000..7b17da2f9b3f --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-qcom-ep.c @@ -0,0 +1,721 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Qualcomm PCIe Endpoint controller driver + * + * Copyright (c) 2020, The Linux Foundation. All rights reserved. + * Author: Siddartha Mohanadoss +#include +#include +#include +#include +#include +#include +#include +#include + +#include "pcie-designware.h" + +/* PARF registers */ +#define PARF_SYS_CTRL 0x00 +#define PARF_DB_CTRL 0x10 +#define PARF_PM_CTRL 0x20 +#define PARF_MHI_BASE_ADDR_LOWER 0x178 +#define PARF_MHI_BASE_ADDR_UPPER 0x17c +#define PARF_DEBUG_INT_EN 0x190 +#define PARF_AXI_MSTR_RD_HALT_NO_WRITES 0x1a4 +#define PARF_AXI_MSTR_WR_ADDR_HALT 0x1a8 +#define PARF_Q2A_FLUSH 0x1ac +#define PARF_LTSSM 0x1b0 +#define PARF_CFG_BITS 0x210 +#define PARF_INT_ALL_STATUS 0x224 +#define PARF_INT_ALL_CLEAR 0x228 +#define PARF_INT_ALL_MASK 0x22c +#define PARF_SLV_ADDR_MSB_CTRL 0x2c0 +#define PARF_DBI_BASE_ADDR 0x350 +#define PARF_DBI_BASE_ADDR_HI 0x354 +#define PARF_SLV_ADDR_SPACE_SIZE 0x358 +#define PARF_SLV_ADDR_SPACE_SIZE_HI 0x35c +#define PARF_ATU_BASE_ADDR 0x634 +#define PARF_ATU_BASE_ADDR_HI 0x638 +#define PARF_SRIS_MODE 0x644 +#define PARF_DEVICE_TYPE 0x1000 +#define PARF_BDF_TO_SID_CFG 0x2c00 + +/* PARF_INT_ALL_{STATUS/CLEAR/MASK} register fields */ +#define PARF_INT_ALL_LINK_DOWN BIT(1) +#define PARF_INT_ALL_BME BIT(2) +#define PARF_INT_ALL_PM_TURNOFF BIT(3) +#define PARF_INT_ALL_DEBUG BIT(4) +#define PARF_INT_ALL_LTR BIT(5) +#define PARF_INT_ALL_MHI_Q6 BIT(6) +#define PARF_INT_ALL_MHI_A7 BIT(7) +#define PARF_INT_ALL_DSTATE_CHANGE BIT(8) +#define PARF_INT_ALL_L1SUB_TIMEOUT BIT(9) +#define PARF_INT_ALL_MMIO_WRITE BIT(10) +#define PARF_INT_ALL_CFG_WRITE BIT(11) +#define PARF_INT_ALL_BRIDGE_FLUSH_N BIT(12) +#define PARF_INT_ALL_LINK_UP BIT(13) +#define PARF_INT_ALL_AER_LEGACY BIT(14) +#define PARF_INT_ALL_PLS_ERR BIT(15) +#define PARF_INT_ALL_PME_LEGACY BIT(16) +#define PARF_INT_ALL_PLS_PME BIT(17) + +/* PARF_BDF_TO_SID_CFG register fields */ +#define PARF_BDF_TO_SID_BYPASS BIT(0) + +/* PARF_DEBUG_INT_EN register fields */ +#define PARF_DEBUG_INT_PM_DSTATE_CHANGE BIT(1) +#define PARF_DEBUG_INT_CFG_BUS_MASTER_EN BIT(2) +#define PARF_DEBUG_INT_RADM_PM_TURNOFF BIT(3) + +/* PARF_DEVICE_TYPE register fields */ +#define PARF_DEVICE_TYPE_EP 0x0 + +/* PARF_PM_CTRL register fields */ +#define PARF_PM_CTRL_REQ_EXIT_L1 BIT(1) +#define PARF_PM_CTRL_READY_ENTR_L23 BIT(2) +#define PARF_PM_CTRL_REQ_NOT_ENTR_L1 BIT(5) + +/* PARF_AXI_MSTR_RD_HALT_NO_WRITES register fields */ +#define PARF_AXI_MSTR_RD_HALT_NO_WRITE_EN BIT(0) + +/* PARF_AXI_MSTR_WR_ADDR_HALT register fields */ +#define PARF_AXI_MSTR_WR_ADDR_HALT_EN BIT(31) + +/* PARF_Q2A_FLUSH register fields */ +#define PARF_Q2A_FLUSH_EN BIT(16) + +/* PARF_SYS_CTRL register fields */ +#define PARF_SYS_CTRL_AUX_PWR_DET BIT(4) +#define PARF_SYS_CTRL_CORE_CLK_CGC_DIS BIT(6) +#define PARF_SYS_CTRL_SLV_DBI_WAKE_DISABLE BIT(11) + +/* PARF_DB_CTRL register fields */ +#define PARF_DB_CTRL_INSR_DBNCR_BLOCK BIT(0) +#define PARF_DB_CTRL_RMVL_DBNCR_BLOCK BIT(1) +#define PARF_DB_CTRL_DBI_WKP_BLOCK BIT(4) +#define PARF_DB_CTRL_SLV_WKP_BLOCK BIT(5) +#define PARF_DB_CTRL_MST_WKP_BLOCK BIT(6) + +/* PARF_CFG_BITS register fields */ +#define PARF_CFG_BITS_REQ_EXIT_L1SS_MSI_LTR_EN BIT(1) + +/* ELBI registers */ +#define ELBI_SYS_STTS 0x08 + +/* DBI registers */ +#define DBI_CON_STATUS 0x44 + +/* DBI register fields */ +#define DBI_CON_STATUS_POWER_STATE_MASK GENMASK(1, 0) + +#define XMLH_LINK_UP 0x400 +#define CORE_RESET_TIME_US_MIN 1000 +#define CORE_RESET_TIME_US_MAX 1005 +#define WAKE_DELAY_US 2000 /* 2 ms */ + +#define to_pcie_ep(x) dev_get_drvdata((x)->dev) + +enum qcom_pcie_ep_link_status { + QCOM_PCIE_EP_LINK_DISABLED, + QCOM_PCIE_EP_LINK_ENABLED, + QCOM_PCIE_EP_LINK_UP, + QCOM_PCIE_EP_LINK_DOWN, +}; + +static struct clk_bulk_data qcom_pcie_ep_clks[] = { + { .id = "cfg" }, + { .id = "aux" }, + { .id = "bus_master" }, + { .id = "bus_slave" }, + { .id = "ref" }, + { .id = "sleep" }, + { .id = "slave_q2a" }, +}; + +struct qcom_pcie_ep { + struct dw_pcie pci; + + void __iomem *parf; + void __iomem *elbi; + struct regmap *perst_map; + struct resource *mmio_res; + + struct reset_control *core_reset; + struct gpio_desc *reset; + struct gpio_desc *wake; + struct phy *phy; + + u32 perst_en; + u32 perst_sep_en; + + enum qcom_pcie_ep_link_status link_status; + int global_irq; + int perst_irq; +}; + +static int qcom_pcie_ep_core_reset(struct qcom_pcie_ep *pcie_ep) +{ + struct dw_pcie *pci = &pcie_ep->pci; + struct device *dev = pci->dev; + int ret; + + ret = reset_control_assert(pcie_ep->core_reset); + if (ret) { + dev_err(dev, "Cannot assert core reset\n"); + return ret; + } + + usleep_range(CORE_RESET_TIME_US_MIN, CORE_RESET_TIME_US_MAX); + + ret = reset_control_deassert(pcie_ep->core_reset); + if (ret) { + dev_err(dev, "Cannot de-assert core reset\n"); + return ret; + } + + usleep_range(CORE_RESET_TIME_US_MIN, CORE_RESET_TIME_US_MAX); + + return 0; +} + +/* + * Delatch PERST_EN and PERST_SEPARATION_ENABLE with TCSR to avoid + * device reset during host reboot and hibernation. The driver is + * expected to handle this situation. + */ +static void qcom_pcie_ep_configure_tcsr(struct qcom_pcie_ep *pcie_ep) +{ + regmap_write(pcie_ep->perst_map, pcie_ep->perst_en, 0); + regmap_write(pcie_ep->perst_map, pcie_ep->perst_sep_en, 0); +} + +static int qcom_pcie_dw_link_up(struct dw_pcie *pci) +{ + struct qcom_pcie_ep *pcie_ep = to_pcie_ep(pci); + u32 reg; + + reg = readl_relaxed(pcie_ep->elbi + ELBI_SYS_STTS); + + return reg & XMLH_LINK_UP; +} + +static int qcom_pcie_dw_start_link(struct dw_pcie *pci) +{ + struct qcom_pcie_ep *pcie_ep = to_pcie_ep(pci); + + enable_irq(pcie_ep->perst_irq); + + return 0; +} + +static void qcom_pcie_dw_stop_link(struct dw_pcie *pci) +{ + struct qcom_pcie_ep *pcie_ep = to_pcie_ep(pci); + + disable_irq(pcie_ep->perst_irq); +} + +static int qcom_pcie_perst_deassert(struct dw_pcie *pci) +{ + struct qcom_pcie_ep *pcie_ep = to_pcie_ep(pci); + struct device *dev = pci->dev; + u32 val, offset; + int ret; + + ret = clk_bulk_prepare_enable(ARRAY_SIZE(qcom_pcie_ep_clks), + qcom_pcie_ep_clks); + if (ret) + return ret; + + ret = qcom_pcie_ep_core_reset(pcie_ep); + if (ret) + goto err_disable_clk; + + ret = phy_init(pcie_ep->phy); + if (ret) + goto err_disable_clk; + + ret = phy_power_on(pcie_ep->phy); + if (ret) + goto err_phy_exit; + + /* Assert WAKE# to RC to indicate device is ready */ + gpiod_set_value_cansleep(pcie_ep->wake, 1); + usleep_range(WAKE_DELAY_US, WAKE_DELAY_US + 500); + gpiod_set_value_cansleep(pcie_ep->wake, 0); + + qcom_pcie_ep_configure_tcsr(pcie_ep); + + /* Disable BDF to SID mapping */ + val = readl_relaxed(pcie_ep->parf + PARF_BDF_TO_SID_CFG); + val |= PARF_BDF_TO_SID_BYPASS; + writel_relaxed(val, pcie_ep->parf + PARF_BDF_TO_SID_CFG); + + /* Enable debug IRQ */ + val = readl_relaxed(pcie_ep->parf + PARF_DEBUG_INT_EN); + val |= PARF_DEBUG_INT_RADM_PM_TURNOFF | + PARF_DEBUG_INT_CFG_BUS_MASTER_EN | + PARF_DEBUG_INT_PM_DSTATE_CHANGE; + writel_relaxed(val, pcie_ep->parf + PARF_DEBUG_INT_EN); + + /* Configure PCIe to endpoint mode */ + writel_relaxed(PARF_DEVICE_TYPE_EP, pcie_ep->parf + PARF_DEVICE_TYPE); + + /* Allow entering L1 state */ + val = readl_relaxed(pcie_ep->parf + PARF_PM_CTRL); + val &= ~PARF_PM_CTRL_REQ_NOT_ENTR_L1; + writel_relaxed(val, pcie_ep->parf + PARF_PM_CTRL); + + /* Read halts write */ + val = readl_relaxed(pcie_ep->parf + PARF_AXI_MSTR_RD_HALT_NO_WRITES); + val &= ~PARF_AXI_MSTR_RD_HALT_NO_WRITE_EN; + writel_relaxed(val, pcie_ep->parf + PARF_AXI_MSTR_RD_HALT_NO_WRITES); + + /* Write after write halt */ + val = readl_relaxed(pcie_ep->parf + PARF_AXI_MSTR_WR_ADDR_HALT); + val |= PARF_AXI_MSTR_WR_ADDR_HALT_EN; + writel_relaxed(val, pcie_ep->parf + PARF_AXI_MSTR_WR_ADDR_HALT); + + /* Q2A flush disable */ + val = readl_relaxed(pcie_ep->parf + PARF_Q2A_FLUSH); + val &= ~PARF_Q2A_FLUSH_EN; + writel_relaxed(val, pcie_ep->parf + PARF_Q2A_FLUSH); + + /* Disable DBI Wakeup, core clock CGC and enable AUX power */ + val = readl_relaxed(pcie_ep->parf + PARF_SYS_CTRL); + val |= PARF_SYS_CTRL_SLV_DBI_WAKE_DISABLE | + PARF_SYS_CTRL_CORE_CLK_CGC_DIS | + PARF_SYS_CTRL_AUX_PWR_DET; + writel_relaxed(val, pcie_ep->parf + PARF_SYS_CTRL); + + /* Disable the debouncers */ + val = readl_relaxed(pcie_ep->parf + PARF_DB_CTRL); + val |= PARF_DB_CTRL_INSR_DBNCR_BLOCK | PARF_DB_CTRL_RMVL_DBNCR_BLOCK | + PARF_DB_CTRL_DBI_WKP_BLOCK | PARF_DB_CTRL_SLV_WKP_BLOCK | + PARF_DB_CTRL_MST_WKP_BLOCK; + writel_relaxed(val, pcie_ep->parf + PARF_DB_CTRL); + + /* Request to exit from L1SS for MSI and LTR MSG */ + val = readl_relaxed(pcie_ep->parf + PARF_CFG_BITS); + val |= PARF_CFG_BITS_REQ_EXIT_L1SS_MSI_LTR_EN; + writel_relaxed(val, pcie_ep->parf + PARF_CFG_BITS); + + dw_pcie_dbi_ro_wr_en(pci); + + /* Set the L0s Exit Latency to 2us-4us = 0x6 */ + offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + val = dw_pcie_readl_dbi(pci, offset + PCI_EXP_LNKCAP); + val &= ~PCI_EXP_LNKCAP_L0SEL; + val |= FIELD_PREP(PCI_EXP_LNKCAP_L0SEL, 0x6); + dw_pcie_writel_dbi(pci, offset + PCI_EXP_LNKCAP, val); + + /* Set the L1 Exit Latency to be 32us-64 us = 0x6 */ + offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + val = dw_pcie_readl_dbi(pci, offset + PCI_EXP_LNKCAP); + val &= ~PCI_EXP_LNKCAP_L1EL; + val |= FIELD_PREP(PCI_EXP_LNKCAP_L1EL, 0x6); + dw_pcie_writel_dbi(pci, offset + PCI_EXP_LNKCAP, val); + + dw_pcie_dbi_ro_wr_dis(pci); + + writel_relaxed(0, pcie_ep->parf + PARF_INT_ALL_MASK); + val = PARF_INT_ALL_LINK_DOWN | PARF_INT_ALL_BME | + PARF_INT_ALL_PM_TURNOFF | PARF_INT_ALL_DSTATE_CHANGE | + PARF_INT_ALL_LINK_UP; + writel_relaxed(val, pcie_ep->parf + PARF_INT_ALL_MASK); + + ret = dw_pcie_ep_init_complete(&pcie_ep->pci.ep); + if (ret) { + dev_err(dev, "Failed to complete initialization: %d\n", ret); + goto err_phy_power_off; + } + + /* + * The physical address of the MMIO region which is exposed as the BAR + * should be written to MHI BASE registers. + */ + writel_relaxed(pcie_ep->mmio_res->start, + pcie_ep->parf + PARF_MHI_BASE_ADDR_LOWER); + writel_relaxed(0, pcie_ep->parf + PARF_MHI_BASE_ADDR_UPPER); + + dw_pcie_ep_init_notify(&pcie_ep->pci.ep); + + /* Enable LTSSM */ + val = readl_relaxed(pcie_ep->parf + PARF_LTSSM); + val |= BIT(8); + writel_relaxed(val, pcie_ep->parf + PARF_LTSSM); + + return 0; + +err_phy_power_off: + phy_power_off(pcie_ep->phy); +err_phy_exit: + phy_exit(pcie_ep->phy); +err_disable_clk: + clk_bulk_disable_unprepare(ARRAY_SIZE(qcom_pcie_ep_clks), + qcom_pcie_ep_clks); + + return ret; +} + +static void qcom_pcie_perst_assert(struct dw_pcie *pci) +{ + struct qcom_pcie_ep *pcie_ep = to_pcie_ep(pci); + struct device *dev = pci->dev; + + if (pcie_ep->link_status == QCOM_PCIE_EP_LINK_DISABLED) { + dev_dbg(dev, "Link is already disabled\n"); + return; + } + + phy_power_off(pcie_ep->phy); + phy_exit(pcie_ep->phy); + clk_bulk_disable_unprepare(ARRAY_SIZE(qcom_pcie_ep_clks), + qcom_pcie_ep_clks); + pcie_ep->link_status = QCOM_PCIE_EP_LINK_DISABLED; +} + +/* Common DWC controller ops */ +static const struct dw_pcie_ops pci_ops = { + .link_up = qcom_pcie_dw_link_up, + .start_link = qcom_pcie_dw_start_link, + .stop_link = qcom_pcie_dw_stop_link, +}; + +static int qcom_pcie_ep_get_io_resources(struct platform_device *pdev, + struct qcom_pcie_ep *pcie_ep) +{ + struct device *dev = &pdev->dev; + struct dw_pcie *pci = &pcie_ep->pci; + struct device_node *syscon; + struct resource *res; + int ret; + + pcie_ep->parf = devm_platform_ioremap_resource_byname(pdev, "parf"); + if (IS_ERR(pcie_ep->parf)) + return PTR_ERR(pcie_ep->parf); + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi"); + pci->dbi_base = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(pci->dbi_base)) + return PTR_ERR(pci->dbi_base); + pci->dbi_base2 = pci->dbi_base; + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "elbi"); + pcie_ep->elbi = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(pcie_ep->elbi)) + return PTR_ERR(pcie_ep->elbi); + + pcie_ep->mmio_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, + "mmio"); + + syscon = of_parse_phandle(dev->of_node, "qcom,perst-regs", 0); + if (!syscon) { + dev_err(dev, "Failed to parse qcom,perst-regs\n"); + return -EINVAL; + } + + pcie_ep->perst_map = syscon_node_to_regmap(syscon); + of_node_put(syscon); + if (IS_ERR(pcie_ep->perst_map)) + return PTR_ERR(pcie_ep->perst_map); + + ret = of_property_read_u32_index(dev->of_node, "qcom,perst-regs", + 1, &pcie_ep->perst_en); + if (ret < 0) { + dev_err(dev, "No Perst Enable offset in syscon\n"); + return ret; + } + + ret = of_property_read_u32_index(dev->of_node, "qcom,perst-regs", + 2, &pcie_ep->perst_sep_en); + if (ret < 0) { + dev_err(dev, "No Perst Separation Enable offset in syscon\n"); + return ret; + } + + return 0; +} + +static int qcom_pcie_ep_get_resources(struct platform_device *pdev, + struct qcom_pcie_ep *pcie_ep) +{ + struct device *dev = &pdev->dev; + int ret; + + ret = qcom_pcie_ep_get_io_resources(pdev, pcie_ep); + if (ret) { + dev_err(&pdev->dev, "Failed to get io resources %d\n", ret); + return ret; + } + + ret = devm_clk_bulk_get(dev, ARRAY_SIZE(qcom_pcie_ep_clks), + qcom_pcie_ep_clks); + if (ret) + return ret; + + pcie_ep->core_reset = devm_reset_control_get_exclusive(dev, "core"); + if (IS_ERR(pcie_ep->core_reset)) + return PTR_ERR(pcie_ep->core_reset); + + pcie_ep->reset = devm_gpiod_get(dev, "reset", GPIOD_IN); + if (IS_ERR(pcie_ep->reset)) + return PTR_ERR(pcie_ep->reset); + + pcie_ep->wake = devm_gpiod_get_optional(dev, "wake", GPIOD_OUT_LOW); + if (IS_ERR(pcie_ep->wake)) + return PTR_ERR(pcie_ep->wake); + + pcie_ep->phy = devm_phy_optional_get(&pdev->dev, "pciephy"); + if (IS_ERR(pcie_ep->phy)) + ret = PTR_ERR(pcie_ep->phy); + + return ret; +} + +/* TODO: Notify clients about PCIe state change */ +static irqreturn_t qcom_pcie_ep_global_irq_thread(int irq, void *data) +{ + struct qcom_pcie_ep *pcie_ep = data; + struct dw_pcie *pci = &pcie_ep->pci; + struct device *dev = pci->dev; + u32 status = readl_relaxed(pcie_ep->parf + PARF_INT_ALL_STATUS); + u32 mask = readl_relaxed(pcie_ep->parf + PARF_INT_ALL_MASK); + u32 dstate, val; + + writel_relaxed(status, pcie_ep->parf + PARF_INT_ALL_CLEAR); + status &= mask; + + if (FIELD_GET(PARF_INT_ALL_LINK_DOWN, status)) { + dev_dbg(dev, "Received Linkdown event\n"); + pcie_ep->link_status = QCOM_PCIE_EP_LINK_DOWN; + } else if (FIELD_GET(PARF_INT_ALL_BME, status)) { + dev_dbg(dev, "Received BME event. Link is enabled!\n"); + pcie_ep->link_status = QCOM_PCIE_EP_LINK_ENABLED; + } else if (FIELD_GET(PARF_INT_ALL_PM_TURNOFF, status)) { + dev_dbg(dev, "Received PM Turn-off event! Entering L23\n"); + val = readl_relaxed(pcie_ep->parf + PARF_PM_CTRL); + val |= PARF_PM_CTRL_READY_ENTR_L23; + writel_relaxed(val, pcie_ep->parf + PARF_PM_CTRL); + } else if (FIELD_GET(PARF_INT_ALL_DSTATE_CHANGE, status)) { + dstate = dw_pcie_readl_dbi(pci, DBI_CON_STATUS) & + DBI_CON_STATUS_POWER_STATE_MASK; + dev_dbg(dev, "Received D%d state event\n", dstate); + if (dstate == 3) { + val = readl_relaxed(pcie_ep->parf + PARF_PM_CTRL); + val |= PARF_PM_CTRL_REQ_EXIT_L1; + writel_relaxed(val, pcie_ep->parf + PARF_PM_CTRL); + } + } else if (FIELD_GET(PARF_INT_ALL_LINK_UP, status)) { + dev_dbg(dev, "Received Linkup event. Enumeration complete!\n"); + dw_pcie_ep_linkup(&pci->ep); + pcie_ep->link_status = QCOM_PCIE_EP_LINK_UP; + } else { + dev_dbg(dev, "Received unknown event: %d\n", status); + } + + return IRQ_HANDLED; +} + +static irqreturn_t qcom_pcie_ep_perst_irq_thread(int irq, void *data) +{ + struct qcom_pcie_ep *pcie_ep = data; + struct dw_pcie *pci = &pcie_ep->pci; + struct device *dev = pci->dev; + u32 perst; + + perst = gpiod_get_value(pcie_ep->reset); + if (perst) { + dev_dbg(dev, "PERST asserted by host. Shutting down the PCIe link!\n"); + qcom_pcie_perst_assert(pci); + } else { + dev_dbg(dev, "PERST de-asserted by host. Starting link training!\n"); + qcom_pcie_perst_deassert(pci); + } + + irq_set_irq_type(gpiod_to_irq(pcie_ep->reset), + (perst ? IRQF_TRIGGER_HIGH : IRQF_TRIGGER_LOW)); + + return IRQ_HANDLED; +} + +static int qcom_pcie_ep_enable_irq_resources(struct platform_device *pdev, + struct qcom_pcie_ep *pcie_ep) +{ + int irq, ret; + + irq = platform_get_irq_byname(pdev, "global"); + if (irq < 0) { + dev_err(&pdev->dev, "Failed to get Global IRQ\n"); + return irq; + } + + ret = devm_request_threaded_irq(&pdev->dev, irq, NULL, + qcom_pcie_ep_global_irq_thread, + IRQF_ONESHOT, + "global_irq", pcie_ep); + if (ret) { + dev_err(&pdev->dev, "Failed to request Global IRQ\n"); + return ret; + } + + pcie_ep->perst_irq = gpiod_to_irq(pcie_ep->reset); + irq_set_status_flags(pcie_ep->perst_irq, IRQ_NOAUTOEN); + ret = devm_request_threaded_irq(&pdev->dev, pcie_ep->perst_irq, NULL, + qcom_pcie_ep_perst_irq_thread, + IRQF_TRIGGER_HIGH | IRQF_ONESHOT, + "perst_irq", pcie_ep); + if (ret) { + dev_err(&pdev->dev, "Failed to request PERST IRQ\n"); + disable_irq(irq); + return ret; + } + + return 0; +} + +static int qcom_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no, + enum pci_epc_irq_type type, u16 interrupt_num) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + + switch (type) { + case PCI_EPC_IRQ_LEGACY: + return dw_pcie_ep_raise_legacy_irq(ep, func_no); + case PCI_EPC_IRQ_MSI: + return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num); + default: + dev_err(pci->dev, "Unknown IRQ type\n"); + return -EINVAL; + } +} + +static const struct pci_epc_features qcom_pcie_epc_features = { + .linkup_notifier = true, + .core_init_notifier = true, + .msi_capable = true, + .msix_capable = false, +}; + +static const struct pci_epc_features * +qcom_pcie_epc_get_features(struct dw_pcie_ep *pci_ep) +{ + return &qcom_pcie_epc_features; +} + +static void qcom_pcie_ep_init(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + enum pci_barno bar; + + for (bar = BAR_0; bar <= BAR_5; bar++) + dw_pcie_ep_reset_bar(pci, bar); +} + +static struct dw_pcie_ep_ops pci_ep_ops = { + .ep_init = qcom_pcie_ep_init, + .raise_irq = qcom_pcie_ep_raise_irq, + .get_features = qcom_pcie_epc_get_features, +}; + +static int qcom_pcie_ep_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct qcom_pcie_ep *pcie_ep; + int ret; + + pcie_ep = devm_kzalloc(dev, sizeof(*pcie_ep), GFP_KERNEL); + if (!pcie_ep) + return -ENOMEM; + + pcie_ep->pci.dev = dev; + pcie_ep->pci.ops = &pci_ops; + pcie_ep->pci.ep.ops = &pci_ep_ops; + platform_set_drvdata(pdev, pcie_ep); + + ret = qcom_pcie_ep_get_resources(pdev, pcie_ep); + if (ret) + return ret; + + ret = clk_bulk_prepare_enable(ARRAY_SIZE(qcom_pcie_ep_clks), + qcom_pcie_ep_clks); + if (ret) + return ret; + + ret = qcom_pcie_ep_core_reset(pcie_ep); + if (ret) + goto err_disable_clk; + + ret = phy_init(pcie_ep->phy); + if (ret) + goto err_disable_clk; + + /* PHY needs to be powered on for dw_pcie_ep_init() */ + ret = phy_power_on(pcie_ep->phy); + if (ret) + goto err_phy_exit; + + ret = dw_pcie_ep_init(&pcie_ep->pci.ep); + if (ret) { + dev_err(dev, "Failed to initialize endpoint: %d\n", ret); + goto err_phy_power_off; + } + + ret = qcom_pcie_ep_enable_irq_resources(pdev, pcie_ep); + if (ret) + goto err_phy_power_off; + + return 0; + +err_phy_power_off: + phy_power_off(pcie_ep->phy); +err_phy_exit: + phy_exit(pcie_ep->phy); +err_disable_clk: + clk_bulk_disable_unprepare(ARRAY_SIZE(qcom_pcie_ep_clks), + qcom_pcie_ep_clks); + + return ret; +} + +static int qcom_pcie_ep_remove(struct platform_device *pdev) +{ + struct qcom_pcie_ep *pcie_ep = platform_get_drvdata(pdev); + + if (pcie_ep->link_status == QCOM_PCIE_EP_LINK_DISABLED) + return 0; + + phy_power_off(pcie_ep->phy); + phy_exit(pcie_ep->phy); + clk_bulk_disable_unprepare(ARRAY_SIZE(qcom_pcie_ep_clks), + qcom_pcie_ep_clks); + + return 0; +} + +static const struct of_device_id qcom_pcie_ep_match[] = { + { .compatible = "qcom,sdx55-pcie-ep", }, + { } +}; + +static struct platform_driver qcom_pcie_ep_driver = { + .probe = qcom_pcie_ep_probe, + .remove = qcom_pcie_ep_remove, + .driver = { + .name = "qcom-pcie-ep", + .of_match_table = qcom_pcie_ep_match, + }, +}; +builtin_platform_driver(qcom_pcie_ep_driver); + +MODULE_AUTHOR("Siddartha Mohanadoss "); +MODULE_AUTHOR("Manivannan Sadhasivam "); +MODULE_DESCRIPTION("Qualcomm PCIe Endpoint controller driver"); +MODULE_LICENSE("GPL v2"); From 79352928a6666a5093dda37db4c909b6a37edf98 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Mon, 20 Sep 2021 12:29:46 +0530 Subject: [PATCH 236/587] MAINTAINERS: Add entry for Qualcomm PCIe Endpoint driver and binding Add MAINTAINERS entry for Qualcomm PCIe Endpoint driver and its devicetree binding. Also fix the PCIe RC entry to cover only the RC driver. Link: https://lore.kernel.org/r/20210920065946.15090-4-manivannan.sadhasivam@linaro.org Signed-off-by: Manivannan Sadhasivam Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas --- MAINTAINERS | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index ca6d6fde85cf..4b3ca1155908 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14596,7 +14596,15 @@ M: Stanimir Varbanov L: linux-pci@vger.kernel.org L: linux-arm-msm@vger.kernel.org S: Maintained -F: drivers/pci/controller/dwc/*qcom* +F: drivers/pci/controller/dwc/pcie-qcom.c + +PCIE ENDPOINT DRIVER FOR QUALCOMM +M: Manivannan Sadhasivam +L: linux-pci@vger.kernel.org +L: linux-arm-msm@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/pci/qcom,pcie-ep.yaml +F: drivers/pci/controller/dwc/pcie-qcom-ep.c PCIE DRIVER FOR ROCKCHIP M: Shawn Lin From 2216cf68cf56808323bff44d43083422a1c4e2f9 Mon Sep 17 00:00:00 2001 From: Hui Su Date: Fri, 8 Oct 2021 19:24:38 +0800 Subject: [PATCH 237/587] scripts: update the comments of kallsyms support update the comments of kallsyms support. Fixes: af73d78bd384 ("kbuild: Remove debug info from kallsyms linking") Signed-off-by: Hui Su Signed-off-by: Masahiro Yamada --- scripts/link-vmlinux.sh | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index d74cee5c4326..a98c4f045302 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -369,14 +369,14 @@ if [ -n "${CONFIG_KALLSYMS}" ]; then # kallsyms support # Generate section listing all symbols and add it into vmlinux # It's a three step process: - # 1) Link .tmp_vmlinux1 so it has all symbols and sections, + # 1) Link .tmp_vmlinux.kallsyms1 so it has all symbols and sections, # but __kallsyms is empty. # Running kallsyms on that gives us .tmp_kallsyms1.o with # the right size - # 2) Link .tmp_vmlinux2 so it now has a __kallsyms section of + # 2) Link .tmp_vmlinux.kallsyms2 so it now has a __kallsyms section of # the right size, but due to the added section, some # addresses have shifted. - # From here, we generate a correct .tmp_kallsyms2.o + # From here, we generate a correct .tmp_vmlinux.kallsyms2.o # 3) That link may have expanded the kernel image enough that # more linker branch stubs / trampolines had to be added, which # introduces new names, which further expands kallsyms. Do another From 88f5e1e66253fc4acd3f68eb4d356fa4653a7bf9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pawe=C5=82=20Jasiak?= Date: Fri, 8 Oct 2021 13:37:59 +0200 Subject: [PATCH 238/587] kbuild: Add make tarzst-pkg build option MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add tarzst-pkg and perf-tarzst-src-pkg targets to build zstd compressed tarballs. Signed-off-by: Paweł Jasiak Signed-off-by: Masahiro Yamada --- scripts/Makefile.package | 10 +++++++--- scripts/package/buildtar | 4 ++++ 2 files changed, 11 insertions(+), 3 deletions(-) diff --git a/scripts/Makefile.package b/scripts/Makefile.package index b74c65284fb2..77b612183c08 100644 --- a/scripts/Makefile.package +++ b/scripts/Makefile.package @@ -103,7 +103,7 @@ snap-pkg: # tarball targets # --------------------------------------------------------------------------- -tar-pkgs := dir-pkg tar-pkg targz-pkg tarbz2-pkg tarxz-pkg +tar-pkgs := dir-pkg tar-pkg targz-pkg tarbz2-pkg tarxz-pkg tarzst-pkg PHONY += $(tar-pkgs) $(tar-pkgs): $(MAKE) -f $(srctree)/Makefile @@ -130,10 +130,12 @@ $(if $(findstring tar-src,$@),, \ $(if $(findstring bz2,$@),$(KBZIP2), \ $(if $(findstring gz,$@),$(KGZIP), \ $(if $(findstring xz,$@),$(XZ), \ -$(error unknown target $@)))) \ +$(if $(findstring zst,$@),$(ZSTD), \ +$(error unknown target $@))))) \ -f -9 $(perf-tar).tar) -perf-tar-pkgs := perf-tar-src-pkg perf-targz-src-pkg perf-tarbz2-src-pkg perf-tarxz-src-pkg +perf-tar-pkgs := perf-tar-src-pkg perf-targz-src-pkg perf-tarbz2-src-pkg \ + perf-tarxz-src-pkg perf-tarzst-src-pkg PHONY += $(perf-tar-pkgs) $(perf-tar-pkgs): $(call cmd,perf_tar) @@ -153,9 +155,11 @@ help: @echo ' targz-pkg - Build the kernel as a gzip compressed tarball' @echo ' tarbz2-pkg - Build the kernel as a bzip2 compressed tarball' @echo ' tarxz-pkg - Build the kernel as a xz compressed tarball' + @echo ' tarzst-pkg - Build the kernel as a zstd compressed tarball' @echo ' perf-tar-src-pkg - Build $(perf-tar).tar source tarball' @echo ' perf-targz-src-pkg - Build $(perf-tar).tar.gz source tarball' @echo ' perf-tarbz2-src-pkg - Build $(perf-tar).tar.bz2 source tarball' @echo ' perf-tarxz-src-pkg - Build $(perf-tar).tar.xz source tarball' + @echo ' perf-tarzst-src-pkg - Build $(perf-tar).tar.zst source tarball' .PHONY: $(PHONY) diff --git a/scripts/package/buildtar b/scripts/package/buildtar index 221aa7df008d..cb54c7f1aa80 100755 --- a/scripts/package/buildtar +++ b/scripts/package/buildtar @@ -39,6 +39,10 @@ case "${1}" in opts="-I ${XZ}" tarball=${tarball}.xz ;; + tarzst-pkg) + opts="-I ${ZSTD}" + tarball=${tarball}.zst + ;; *) echo "Unknown tarball target \"${1}\" requested, please add it to ${0}." >&2 exit 1 From 7e919677bb392c765e0f86fda63191e517c0bd1f Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Mon, 23 Aug 2021 08:49:57 -0700 Subject: [PATCH 239/587] PCI: dwc: Perform host_init() before registering msi On the Qualcomm sc8180x platform the bootloader does something related to PCI that leaves a pending "msi" interrupt, which with the current ordering often fires before init has a chance to enable the clocks that are necessary for the interrupt handler to access the hardware. Move the host_init() call before the registration of the "msi" interrupt handler to ensure the host driver has a chance to enable the clocks. The assignment of the bridge's ops and child_ops is moved along, because at least the TI Keystone driver overwrites these in its host_init callback. Link: https://lore.kernel.org/r/20210823154958.305677-1-bjorn.andersson@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Lorenzo Pieralisi Reviewed-by: Rob Herring --- .../pci/controller/dwc/pcie-designware-host.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c index d1d9b8344ec9..f4755f3a03be 100644 --- a/drivers/pci/controller/dwc/pcie-designware-host.c +++ b/drivers/pci/controller/dwc/pcie-designware-host.c @@ -335,6 +335,16 @@ int dw_pcie_host_init(struct pcie_port *pp) if (pci->link_gen < 1) pci->link_gen = of_pci_get_max_link_speed(np); + /* Set default bus ops */ + bridge->ops = &dw_pcie_ops; + bridge->child_ops = &dw_child_pcie_ops; + + if (pp->ops->host_init) { + ret = pp->ops->host_init(pp); + if (ret) + return ret; + } + if (pci_msi_enabled()) { pp->has_msi_ctrl = !(pp->ops->msi_host_init || of_property_read_bool(np, "msi-parent") || @@ -388,15 +398,6 @@ int dw_pcie_host_init(struct pcie_port *pp) } } - /* Set default bus ops */ - bridge->ops = &dw_pcie_ops; - bridge->child_ops = &dw_child_pcie_ops; - - if (pp->ops->host_init) { - ret = pp->ops->host_init(pp); - if (ret) - goto err_free_msi; - } dw_pcie_iatu_detect(pci); dw_pcie_setup_rc(pp); From 2565e5b69c44b4e42469afea3cc5a97e74d1ed45 Mon Sep 17 00:00:00 2001 From: Adrian Huang Date: Wed, 1 Sep 2021 20:40:47 +0800 Subject: [PATCH 240/587] PCI: vmd: Do not disable MSI-X remapping if interrupt remapping is enabled by IOMMU When enabling VMD in BIOS setup (Ice Lake Processor: Whitley platform), the host OS cannot boot successfully with the following error message: nvme nvme0: I/O 12 QID 0 timeout, completion polled nvme nvme0: Shutdown timeout set to 6 seconds DMAR: DRHD: handling fault status reg 2 DMAR: [INTR-REMAP] Request device [0x00:0x00.5] fault index 0xa00 [fault reason 0x25] Blocked a compatibility format interrupt request The request device is the VMD controller: # lspci -s 0000:00.5 -nn 0000:00:00.5 RAID bus controller [0104]: Intel Corporation Volume Management Device NVMe RAID Controller [8086:28c0] (rev 04) `git bisect` points to this offending commit ee81ee84f873 ("PCI: vmd: Disable MSI-X remapping when possible"), which disables VMD MSI remapping. The IOMMU hardware blocks the compatibility format interrupt request because Interrupt Remapping Enable Status (IRES) and Extended Interrupt Mode Enable (EIME) are enabled. Please refer to section "5.1.4 Interrupt-Remapping Hardware Operation" in Intel VT-d spec. To fix the issue, VMD driver still enables the interrupt remapping irrespective of VMD_FEAT_CAN_BYPASS_MSI_REMAP if the IOMMU subsystem enables the interrupt remapping. Test configuration is shown as follows: * Two VMD controllers 1. 8086:28c0 (Whitley's VMD) 2. 8086:201d (Purley's VMD: The issue does not appear in this controller. Just make sure if any side effect occurs.) * w/wo intremap=off Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=214219 Link: https://lore.kernel.org/r/20210901124047.1615-1-adrianhuang0701@gmail.com Signed-off-by: Adrian Huang Signed-off-by: Lorenzo Pieralisi Reviewed-by: Jon Derrick Cc: Jon Derrick Cc: Nirmal Patel Cc: Joerg Roedel --- drivers/pci/controller/vmd.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c index 1b3e94a96414..1979fc5eac27 100644 --- a/drivers/pci/controller/vmd.c +++ b/drivers/pci/controller/vmd.c @@ -6,6 +6,7 @@ #include #include +#include #include #include #include @@ -765,7 +766,8 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features) * acceptable because the guest is usually CPU-limited and MSI * remapping doesn't become a performance bottleneck. */ - if (!(features & VMD_FEAT_CAN_BYPASS_MSI_REMAP) || + if (iommu_capable(vmd->dev->dev.bus, IOMMU_CAP_INTR_REMAP) || + !(features & VMD_FEAT_CAN_BYPASS_MSI_REMAP) || offset[0] || offset[1]) { ret = vmd_alloc_irqs(vmd); if (ret) From f18312084300598544529510bcfab5f3e795e36a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Krzysztof=20Wilczy=C5=84ski?= Date: Fri, 8 Oct 2021 22:27:30 +0000 Subject: [PATCH 241/587] PCI: hv: Remove unnecessary use of %hx MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit "dom_req" is a u16 but varargs automatically promotes it to int, so there's no point in using the %h modifier. Drop it. See cbacb5ab0aa0 ("docs: printk-formats: Stop encouraging use of unnecessary %h[xudi] and %hh[xudi]") and 70eb2275ff8e ("checkpatch: add warning for unnecessary use of %h[xudi] and %hh[xudi]"). Link: https://lore.kernel.org/r/20211008222732.2868493-1-kw@linux.com Signed-off-by: Krzysztof Wilczyński Signed-off-by: Bjorn Helgaas --- drivers/pci/controller/pci-hyperv.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index eaec915ffe62..8459f857ad9e 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -3126,14 +3126,14 @@ static int hv_pci_probe(struct hv_device *hdev, if (dom == HVPCI_DOM_INVALID) { dev_err(&hdev->device, - "Unable to use dom# 0x%hx or other numbers", dom_req); + "Unable to use dom# 0x%x or other numbers", dom_req); ret = -EINVAL; goto free_bus; } if (dom != dom_req) dev_info(&hdev->device, - "PCI dom# 0x%hx has collision, using 0x%hx", + "PCI dom# 0x%x has collision, using 0x%x", dom_req, dom); hbus->bridge->domain_nr = dom; From 357df2fc00661e0993e0e40d1a56bdd967f45c17 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Krzysztof=20Wilczy=C5=84ski?= Date: Fri, 8 Oct 2021 22:27:32 +0000 Subject: [PATCH 242/587] PCI: Use unsigned to match sscanf("%x") in pci_dev_str_match_path() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Cppcheck warns that pci_dev_str_match_path() passes pointers to signed ints to sscanf("%x"), which expects pointers to *unsigned* ints: invalidScanfArgType_int drivers/pci/pci.c:312 %x in format string (no. 2) requires 'unsigned int *' but the argument type is 'signed int *'. Declare the variables as unsigned to avoid this issue. [bhelgaas: commit log] Link: https://lore.kernel.org/r/20211008222732.2868493-3-kw@linux.com Signed-off-by: Krzysztof Wilczyński Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index ce2ab62b64cf..7998b65e9ae5 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -269,7 +269,7 @@ static int pci_dev_str_match_path(struct pci_dev *dev, const char *path, const char **endptr) { int ret; - int seg, bus, slot, func; + unsigned int seg, bus, slot, func; char *wpath, *p; char end; From 8e9028b3790ddb02c407e1a4da0ab7cf82790e7e Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 12 Oct 2021 15:42:59 -0500 Subject: [PATCH 243/587] PCI: Return NULL for to_pci_driver(NULL) to_pci_driver() takes a pointer to a struct device_driver and uses container_of() to find the struct pci_driver that contains it. If given a NULL pointer to a struct device_driver, return a NULL pci_driver pointer instead of applying container_of() to NULL. This simplifies callers that would otherwise have to check for a NULL pointer first. Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/include/linux/pci.h b/include/linux/pci.h index cd8aa6fce204..a2d62165a7f7 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -900,7 +900,10 @@ struct pci_driver { struct pci_dynids dynids; }; -#define to_pci_driver(drv) container_of(drv, struct pci_driver, driver) +static inline struct pci_driver *to_pci_driver(struct device_driver *drv) +{ + return drv ? container_of(drv, struct pci_driver, driver) : NULL; +} /** * PCI_DEVICE - macro used to describe a specific PCI device From 097d9d414433315122f759ee6c2d8a7417a8ff0f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 4 Oct 2021 14:59:25 +0200 Subject: [PATCH 244/587] PCI: Drop pci_device_remove() test of pci_dev->driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When the driver core calls pci_device_remove(), there is a driver bound to the device, so pci_dev->driver is never NULL. Remove the unnecessary test of pci_dev->driver. Link: https://lore.kernel.org/r/20211004125935.2300113-2-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König Signed-off-by: Bjorn Helgaas Reviewed-by: Christoph Hellwig --- drivers/pci/pci-driver.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 2761ab86490d..8fb6418c93e8 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -459,16 +459,14 @@ static void pci_device_remove(struct device *dev) struct pci_dev *pci_dev = to_pci_dev(dev); struct pci_driver *drv = pci_dev->driver; - if (drv) { - if (drv->remove) { - pm_runtime_get_sync(dev); - drv->remove(pci_dev); - pm_runtime_put_noidle(dev); - } - pcibios_free_irq(pci_dev); - pci_dev->driver = NULL; - pci_iov_remove(pci_dev); + if (drv->remove) { + pm_runtime_get_sync(dev); + drv->remove(pci_dev); + pm_runtime_put_noidle(dev); } + pcibios_free_irq(pci_dev); + pci_dev->driver = NULL; + pci_iov_remove(pci_dev); /* Undo the runtime PM settings in local_pci_probe() */ pm_runtime_put_sync(dev); From ae232f0970ea0c1d2b1e95922000afbe58af039f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 4 Oct 2021 14:59:26 +0200 Subject: [PATCH 245/587] PCI: Drop pci_device_probe() test of !pci_dev->driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When the device core calls the .probe() callback for a device, the device is never bound, so pci_dev->driver is always NULL. Remove the unnecessary test of !pci_dev->driver. Link: https://lore.kernel.org/r/20211004125935.2300113-3-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König Signed-off-by: Bjorn Helgaas Reviewed-by: Christoph Hellwig --- drivers/pci/pci-driver.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 8fb6418c93e8..50449ec622a3 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -397,7 +397,7 @@ static int __pci_device_probe(struct pci_driver *drv, struct pci_dev *pci_dev) const struct pci_device_id *id; int error = 0; - if (!pci_dev->driver && drv->probe) { + if (drv->probe) { error = -ENODEV; id = pci_match_device(drv, pci_dev); From 171d149ce8d11f7fafbd4f338f14d472a153c3d4 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 12 Oct 2021 17:20:06 -0500 Subject: [PATCH 246/587] PCI/ERR: Factor out common dev->driver expressions Save the struct pci_driver pointer from pdev->driver instead of repeating it several times. No functional change. Signed-off-by: Bjorn Helgaas --- drivers/pci/pcie/err.c | 40 ++++++++++++++++++++++++---------------- 1 file changed, 24 insertions(+), 16 deletions(-) diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c index b576aa890c76..0c5a143025af 100644 --- a/drivers/pci/pcie/err.c +++ b/drivers/pci/pcie/err.c @@ -49,14 +49,16 @@ static int report_error_detected(struct pci_dev *dev, pci_channel_state_t state, enum pci_ers_result *result) { + struct pci_driver *pdrv; pci_ers_result_t vote; const struct pci_error_handlers *err_handler; device_lock(&dev->dev); + pdrv = dev->driver; if (!pci_dev_set_io_state(dev, state) || - !dev->driver || - !dev->driver->err_handler || - !dev->driver->err_handler->error_detected) { + !pdrv || + !pdrv->err_handler || + !pdrv->err_handler->error_detected) { /* * If any device in the subtree does not have an error_detected * callback, PCI_ERS_RESULT_NO_AER_DRIVER prevents subsequent @@ -70,7 +72,7 @@ static int report_error_detected(struct pci_dev *dev, vote = PCI_ERS_RESULT_NONE; } } else { - err_handler = dev->driver->err_handler; + err_handler = pdrv->err_handler; vote = err_handler->error_detected(dev, state); } pci_uevent_ers(dev, vote); @@ -91,16 +93,18 @@ static int report_normal_detected(struct pci_dev *dev, void *data) static int report_mmio_enabled(struct pci_dev *dev, void *data) { + struct pci_driver *pdrv; pci_ers_result_t vote, *result = data; const struct pci_error_handlers *err_handler; device_lock(&dev->dev); - if (!dev->driver || - !dev->driver->err_handler || - !dev->driver->err_handler->mmio_enabled) + pdrv = dev->driver; + if (!pdrv || + !pdrv->err_handler || + !pdrv->err_handler->mmio_enabled) goto out; - err_handler = dev->driver->err_handler; + err_handler = pdrv->err_handler; vote = err_handler->mmio_enabled(dev); *result = merge_result(*result, vote); out: @@ -110,16 +114,18 @@ out: static int report_slot_reset(struct pci_dev *dev, void *data) { + struct pci_driver *pdrv; pci_ers_result_t vote, *result = data; const struct pci_error_handlers *err_handler; device_lock(&dev->dev); - if (!dev->driver || - !dev->driver->err_handler || - !dev->driver->err_handler->slot_reset) + pdrv = dev->driver; + if (!pdrv || + !pdrv->err_handler || + !pdrv->err_handler->slot_reset) goto out; - err_handler = dev->driver->err_handler; + err_handler = pdrv->err_handler; vote = err_handler->slot_reset(dev); *result = merge_result(*result, vote); out: @@ -129,16 +135,18 @@ out: static int report_resume(struct pci_dev *dev, void *data) { + struct pci_driver *pdrv; const struct pci_error_handlers *err_handler; device_lock(&dev->dev); + pdrv = dev->driver; if (!pci_dev_set_io_state(dev, pci_channel_io_normal) || - !dev->driver || - !dev->driver->err_handler || - !dev->driver->err_handler->resume) + !pdrv || + !pdrv->err_handler || + !pdrv->err_handler->resume) goto out; - err_handler = dev->driver->err_handler; + err_handler = pdrv->err_handler; err_handler->resume(dev); out: pci_uevent_ers(dev, PCI_ERS_RESULT_RECOVERED); From a534ff3f4d6082f5ac228194accb7b414f0d6f0b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 4 Oct 2021 14:59:32 +0200 Subject: [PATCH 247/587] scsi: message: fusion: Remove unused mpt_pci driver .probe() 'id' parameter MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The only two drivers don't make use of the id parameter, so drop it. This is a step toward removing pci_dev->driver. Link: https://lore.kernel.org/r/20211004125935.2300113-9-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König Signed-off-by: Bjorn Helgaas Reviewed-by: Christoph Hellwig Acked-by: Martin K. Petersen --- drivers/message/fusion/mptbase.c | 7 ++----- drivers/message/fusion/mptbase.h | 2 +- drivers/message/fusion/mptctl.c | 4 ++-- drivers/message/fusion/mptlan.c | 2 +- 4 files changed, 6 insertions(+), 9 deletions(-) diff --git a/drivers/message/fusion/mptbase.c b/drivers/message/fusion/mptbase.c index 7f7abc9069f7..b94d5e4fdc23 100644 --- a/drivers/message/fusion/mptbase.c +++ b/drivers/message/fusion/mptbase.c @@ -829,7 +829,6 @@ int mpt_device_driver_register(struct mpt_pci_driver * dd_cbfunc, u8 cb_idx) { MPT_ADAPTER *ioc; - const struct pci_device_id *id; if (!cb_idx || cb_idx >= MPT_MAX_PROTOCOL_DRIVERS) return -EINVAL; @@ -838,10 +837,8 @@ mpt_device_driver_register(struct mpt_pci_driver * dd_cbfunc, u8 cb_idx) /* call per pci device probe entry point */ list_for_each_entry(ioc, &ioc_list, list) { - id = ioc->pcidev->driver ? - ioc->pcidev->driver->id_table : NULL; if (dd_cbfunc->probe) - dd_cbfunc->probe(ioc->pcidev, id); + dd_cbfunc->probe(ioc->pcidev); } return 0; @@ -2032,7 +2029,7 @@ mpt_attach(struct pci_dev *pdev, const struct pci_device_id *id) for(cb_idx = 0; cb_idx < MPT_MAX_PROTOCOL_DRIVERS; cb_idx++) { if(MptDeviceDriverHandlers[cb_idx] && MptDeviceDriverHandlers[cb_idx]->probe) { - MptDeviceDriverHandlers[cb_idx]->probe(pdev,id); + MptDeviceDriverHandlers[cb_idx]->probe(pdev); } } diff --git a/drivers/message/fusion/mptbase.h b/drivers/message/fusion/mptbase.h index b9e0376be723..4bd0682c65d3 100644 --- a/drivers/message/fusion/mptbase.h +++ b/drivers/message/fusion/mptbase.h @@ -257,7 +257,7 @@ typedef enum { } MPT_DRIVER_CLASS; struct mpt_pci_driver{ - int (*probe) (struct pci_dev *dev, const struct pci_device_id *id); + int (*probe) (struct pci_dev *dev); void (*remove) (struct pci_dev *dev); }; diff --git a/drivers/message/fusion/mptctl.c b/drivers/message/fusion/mptctl.c index 72025996cd70..ae433c150b37 100644 --- a/drivers/message/fusion/mptctl.c +++ b/drivers/message/fusion/mptctl.c @@ -114,7 +114,7 @@ static int mptctl_do_reset(MPT_ADAPTER *iocp, unsigned long arg); static int mptctl_hp_hostinfo(MPT_ADAPTER *iocp, unsigned long arg, unsigned int cmd); static int mptctl_hp_targetinfo(MPT_ADAPTER *iocp, unsigned long arg); -static int mptctl_probe(struct pci_dev *, const struct pci_device_id *); +static int mptctl_probe(struct pci_dev *); static void mptctl_remove(struct pci_dev *); #ifdef CONFIG_COMPAT @@ -2838,7 +2838,7 @@ static long compat_mpctl_ioctl(struct file *f, unsigned int cmd, unsigned long a */ static int -mptctl_probe(struct pci_dev *pdev, const struct pci_device_id *id) +mptctl_probe(struct pci_dev *pdev) { MPT_ADAPTER *ioc = pci_get_drvdata(pdev); diff --git a/drivers/message/fusion/mptlan.c b/drivers/message/fusion/mptlan.c index 3261cac762de..7c1af5e6eb0b 100644 --- a/drivers/message/fusion/mptlan.c +++ b/drivers/message/fusion/mptlan.c @@ -1377,7 +1377,7 @@ mpt_register_lan_device (MPT_ADAPTER *mpt_dev, int pnum) } static int -mptlan_probe(struct pci_dev *pdev, const struct pci_device_id *id) +mptlan_probe(struct pci_dev *pdev) { MPT_ADAPTER *ioc = pci_get_drvdata(pdev); struct net_device *dev; From 8f5c335e34b5ae2dda6db2af300381fc9fb53fe7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 4 Oct 2021 14:59:33 +0200 Subject: [PATCH 248/587] crypto: qat - simplify adf_enable_aer() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A struct pci_driver is shared across all device instances, so assigning pci_driver.err_handler once per device isn't really sensible. Set adf_driver.err_handler statically instead of in adf_enable_aer(). This removes a use of pci_dev->driver, which is a step toward removing pci_dev->driver altogether. Since adf_enable_aer() returns zero unconditionally, make it a void function. Link: https://lore.kernel.org/r/20211004125935.2300113-10-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König Signed-off-by: Bjorn Helgaas --- drivers/crypto/qat/qat_4xxx/adf_drv.c | 7 ++----- drivers/crypto/qat/qat_c3xxx/adf_drv.c | 7 ++----- drivers/crypto/qat/qat_c62x/adf_drv.c | 7 ++----- drivers/crypto/qat/qat_common/adf_aer.c | 10 +++------- drivers/crypto/qat/qat_common/adf_common_drv.h | 3 ++- drivers/crypto/qat/qat_dh895xcc/adf_drv.c | 7 ++----- 6 files changed, 13 insertions(+), 28 deletions(-) diff --git a/drivers/crypto/qat/qat_4xxx/adf_drv.c b/drivers/crypto/qat/qat_4xxx/adf_drv.c index 359fb7989dfb..71ef065914b2 100644 --- a/drivers/crypto/qat/qat_4xxx/adf_drv.c +++ b/drivers/crypto/qat/qat_4xxx/adf_drv.c @@ -247,11 +247,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_master(pdev); - if (adf_enable_aer(accel_dev)) { - dev_err(&pdev->dev, "Failed to enable aer.\n"); - ret = -EFAULT; - goto out_err; - } + adf_enable_aer(accel_dev); if (pci_save_state(pdev)) { dev_err(&pdev->dev, "Failed to save pci state.\n"); @@ -304,6 +300,7 @@ static struct pci_driver adf_driver = { .probe = adf_probe, .remove = adf_remove, .sriov_configure = adf_sriov_configure, + .err_handler = &adf_err_handler, }; module_pci_driver(adf_driver); diff --git a/drivers/crypto/qat/qat_c3xxx/adf_drv.c b/drivers/crypto/qat/qat_c3xxx/adf_drv.c index cc6e75dc60de..2aef0bb791df 100644 --- a/drivers/crypto/qat/qat_c3xxx/adf_drv.c +++ b/drivers/crypto/qat/qat_c3xxx/adf_drv.c @@ -33,6 +33,7 @@ static struct pci_driver adf_driver = { .probe = adf_probe, .remove = adf_remove, .sriov_configure = adf_sriov_configure, + .err_handler = &adf_err_handler, }; static void adf_cleanup_pci_dev(struct adf_accel_dev *accel_dev) @@ -192,11 +193,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) } pci_set_master(pdev); - if (adf_enable_aer(accel_dev)) { - dev_err(&pdev->dev, "Failed to enable aer\n"); - ret = -EFAULT; - goto out_err_free_reg; - } + adf_enable_aer(accel_dev); if (pci_save_state(pdev)) { dev_err(&pdev->dev, "Failed to save pci state\n"); diff --git a/drivers/crypto/qat/qat_c62x/adf_drv.c b/drivers/crypto/qat/qat_c62x/adf_drv.c index bf251dfe74b3..56163083f161 100644 --- a/drivers/crypto/qat/qat_c62x/adf_drv.c +++ b/drivers/crypto/qat/qat_c62x/adf_drv.c @@ -33,6 +33,7 @@ static struct pci_driver adf_driver = { .probe = adf_probe, .remove = adf_remove, .sriov_configure = adf_sriov_configure, + .err_handler = &adf_err_handler, }; static void adf_cleanup_pci_dev(struct adf_accel_dev *accel_dev) @@ -192,11 +193,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) } pci_set_master(pdev); - if (adf_enable_aer(accel_dev)) { - dev_err(&pdev->dev, "Failed to enable aer\n"); - ret = -EFAULT; - goto out_err_free_reg; - } + adf_enable_aer(accel_dev); if (pci_save_state(pdev)) { dev_err(&pdev->dev, "Failed to save pci state\n"); diff --git a/drivers/crypto/qat/qat_common/adf_aer.c b/drivers/crypto/qat/qat_common/adf_aer.c index ed3e40bc56eb..fe9bb2f3536a 100644 --- a/drivers/crypto/qat/qat_common/adf_aer.c +++ b/drivers/crypto/qat/qat_common/adf_aer.c @@ -166,11 +166,12 @@ static void adf_resume(struct pci_dev *pdev) dev_info(&pdev->dev, "Device is up and running\n"); } -static const struct pci_error_handlers adf_err_handler = { +const struct pci_error_handlers adf_err_handler = { .error_detected = adf_error_detected, .slot_reset = adf_slot_reset, .resume = adf_resume, }; +EXPORT_SYMBOL_GPL(adf_err_handler); /** * adf_enable_aer() - Enable Advance Error Reporting for acceleration device @@ -179,17 +180,12 @@ static const struct pci_error_handlers adf_err_handler = { * Function enables PCI Advance Error Reporting for the * QAT acceleration device accel_dev. * To be used by QAT device specific drivers. - * - * Return: 0 on success, error code otherwise. */ -int adf_enable_aer(struct adf_accel_dev *accel_dev) +void adf_enable_aer(struct adf_accel_dev *accel_dev) { struct pci_dev *pdev = accel_to_pci_dev(accel_dev); - struct pci_driver *pdrv = pdev->driver; - pdrv->err_handler = &adf_err_handler; pci_enable_pcie_error_reporting(pdev); - return 0; } EXPORT_SYMBOL_GPL(adf_enable_aer); diff --git a/drivers/crypto/qat/qat_common/adf_common_drv.h b/drivers/crypto/qat/qat_common/adf_common_drv.h index 4261749fae8d..e4c24be212ff 100644 --- a/drivers/crypto/qat/qat_common/adf_common_drv.h +++ b/drivers/crypto/qat/qat_common/adf_common_drv.h @@ -95,7 +95,8 @@ void adf_ae_fw_release(struct adf_accel_dev *accel_dev); int adf_ae_start(struct adf_accel_dev *accel_dev); int adf_ae_stop(struct adf_accel_dev *accel_dev); -int adf_enable_aer(struct adf_accel_dev *accel_dev); +extern const struct pci_error_handlers adf_err_handler; +void adf_enable_aer(struct adf_accel_dev *accel_dev); void adf_disable_aer(struct adf_accel_dev *accel_dev); void adf_reset_sbr(struct adf_accel_dev *accel_dev); void adf_reset_flr(struct adf_accel_dev *accel_dev); diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_drv.c b/drivers/crypto/qat/qat_dh895xcc/adf_drv.c index 3976a81bd99b..acca56752aa0 100644 --- a/drivers/crypto/qat/qat_dh895xcc/adf_drv.c +++ b/drivers/crypto/qat/qat_dh895xcc/adf_drv.c @@ -33,6 +33,7 @@ static struct pci_driver adf_driver = { .probe = adf_probe, .remove = adf_remove, .sriov_configure = adf_sriov_configure, + .err_handler = &adf_err_handler, }; static void adf_cleanup_pci_dev(struct adf_accel_dev *accel_dev) @@ -192,11 +193,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) } pci_set_master(pdev); - if (adf_enable_aer(accel_dev)) { - dev_err(&pdev->dev, "Failed to enable aer\n"); - ret = -EFAULT; - goto out_err_free_reg; - } + adf_enable_aer(accel_dev); if (pci_save_state(pdev)) { dev_err(&pdev->dev, "Failed to save pci state\n"); From 823c523eb2e4f2fe37f898861c28b3d8ef22f5ff Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 4 Oct 2021 14:59:28 +0200 Subject: [PATCH 249/587] bcma: simplify reference to driver name MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When bcma_host_pci_probe() is called, the PCI driver core has already assigned the device's driver in local_pci_probe(). So dev->driver is always true, and here it points to bcma_pci_bridge_driver, which has .name set to "bcma-pci-bridge". Simplify accordingly. Link: https://lore.kernel.org/r/20211004125935.2300113-5-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König Signed-off-by: Bjorn Helgaas --- drivers/bcma/host_pci.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/bcma/host_pci.c b/drivers/bcma/host_pci.c index 69c10a7b7c61..960632197b05 100644 --- a/drivers/bcma/host_pci.c +++ b/drivers/bcma/host_pci.c @@ -162,7 +162,6 @@ static int bcma_host_pci_probe(struct pci_dev *dev, { struct bcma_bus *bus; int err = -ENOMEM; - const char *name; u32 val; /* Alloc */ @@ -175,10 +174,7 @@ static int bcma_host_pci_probe(struct pci_dev *dev, if (err) goto err_kfree_bus; - name = dev_name(&dev->dev); - if (dev->driver && dev->driver->name) - name = dev->driver->name; - err = pci_request_regions(dev, name); + err = pci_request_regions(dev, "bcma-pci-bridge"); if (err) goto err_pci_disable; pci_set_master(dev); From 7c3b2c933a916e32e9c8b56074a47c1b3f3e7cbe Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 4 Oct 2021 14:59:30 +0200 Subject: [PATCH 250/587] ssb: Use dev_driver_string() instead of pci_dev->driver->name MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit All drivers that use ssb_pcihost_probe(), i.e., b43_pci_bridge_driver and b44_pci_driver, set the pci_driver.name, and __pci_register_driver() sets the struct driver.name member to the same value. Replace dev->driver_name() by dev_driver_string() for the corresponding struct device. This is a step toward removing pci_dev->driver. Link: https://lore.kernel.org/r/20211004125935.2300113-7-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König Signed-off-by: Bjorn Helgaas Acked-by: Michael Büsch --- drivers/ssb/pcihost_wrapper.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/ssb/pcihost_wrapper.c b/drivers/ssb/pcihost_wrapper.c index 410215c16920..dd70fd41c77d 100644 --- a/drivers/ssb/pcihost_wrapper.c +++ b/drivers/ssb/pcihost_wrapper.c @@ -69,7 +69,6 @@ static int ssb_pcihost_probe(struct pci_dev *dev, { struct ssb_bus *ssb; int err = -ENOMEM; - const char *name; u32 val; ssb = kzalloc(sizeof(*ssb), GFP_KERNEL); @@ -78,10 +77,7 @@ static int ssb_pcihost_probe(struct pci_dev *dev, err = pci_enable_device(dev); if (err) goto err_kfree_ssb; - name = dev_name(&dev->dev); - if (dev->driver && dev->driver->name) - name = dev->driver->name; - err = pci_request_regions(dev, name); + err = pci_request_regions(dev, dev_driver_string(&dev->dev)); if (err) goto err_pci_disable; pci_set_master(dev); From 5a72431ec318ed38b02a413b1e4ab934e5d3451e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 4 Oct 2021 14:59:29 +0200 Subject: [PATCH 251/587] powerpc/eeh: Use dev_driver_string() instead of struct pci_dev->driver->name MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Replace pdev->driver->name by dev_driver_string() for the corresponding struct device. This is a step toward removing pci_dev->driver. Move the function nearer its only user and instead of the ?: operator use a normal "if" which is more readable. Link: https://lore.kernel.org/r/20211004125935.2300113-6-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König Signed-off-by: Bjorn Helgaas --- arch/powerpc/include/asm/ppc-pci.h | 5 ----- arch/powerpc/kernel/eeh.c | 8 ++++++++ 2 files changed, 8 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h index 2b9edbf6e929..f6cf0159024e 100644 --- a/arch/powerpc/include/asm/ppc-pci.h +++ b/arch/powerpc/include/asm/ppc-pci.h @@ -55,11 +55,6 @@ void eeh_pe_dev_mode_mark(struct eeh_pe *pe, int mode); void eeh_sysfs_add_device(struct pci_dev *pdev); void eeh_sysfs_remove_device(struct pci_dev *pdev); -static inline const char *eeh_driver_name(struct pci_dev *pdev) -{ - return (pdev && pdev->driver) ? pdev->driver->name : ""; -} - #endif /* CONFIG_EEH */ #define PCI_BUSNO(bdfn) ((bdfn >> 8) & 0xff) diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index e9b597ed423c..4b08881c4a1e 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -399,6 +399,14 @@ out: return ret; } +static inline const char *eeh_driver_name(struct pci_dev *pdev) +{ + if (pdev) + return dev_driver_string(&pdev->dev); + + return ""; +} + /** * eeh_dev_check_failure - Check if all 1's data is due to EEH slot freeze * @edev: eeh device From 1fbbcffd0ee1f9fc0a10be311e078c4f37f6c733 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 12 Oct 2021 17:51:53 -0500 Subject: [PATCH 252/587] crypto: hisilicon - use dev_driver_string() instead of pci_dev->driver->name MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Replace dev->driver_name() by dev_driver_string() for the corresponding struct device. This is a step toward removing pci_dev->driver. [bhelgaas: split to separate patch] Link: https://lore.kernel.org/r/20211004125935.2300113-8-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König Signed-off-by: Bjorn Helgaas --- drivers/crypto/hisilicon/qm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index 369562d34d66..8f361e54e524 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -3085,7 +3085,7 @@ static int qm_alloc_uacce(struct hisi_qm *qm) }; int ret; - ret = strscpy(interface.name, pdev->driver->name, + ret = strscpy(interface.name, dev_driver_string(&pdev->dev), sizeof(interface.name)); if (ret < 0) return -ENAMETOOLONG; From e519d9ea62e821659d68c2f1f4d8a5c33ea70db5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 12 Oct 2021 17:52:59 -0500 Subject: [PATCH 253/587] net: hns3: use dev_driver_string() instead of pci_dev->driver->name MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Replace dev->driver_name() by dev_driver_string() for the corresponding struct device. This is a step toward removing pci_dev->driver. [bhelgaas: split to separate patch] Link: https://lore.kernel.org/r/20211004125935.2300113-8-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König Signed-off-by: Bjorn Helgaas --- drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index 7ea511d59e91..f279edfce3f1 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -606,7 +606,7 @@ static void hns3_get_drvinfo(struct net_device *netdev, return; } - strncpy(drvinfo->driver, h->pdev->driver->name, + strncpy(drvinfo->driver, dev_driver_string(&h->pdev->dev), sizeof(drvinfo->driver)); drvinfo->driver[sizeof(drvinfo->driver) - 1] = '\0'; From e14dc26013141d5e962c31c8ddfc488ef09c3c69 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 12 Oct 2021 17:53:45 -0500 Subject: [PATCH 254/587] net: marvell: prestera: use dev_driver_string() instead of pci_dev->driver->name MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Replace dev->driver_name() by dev_driver_string() for the corresponding struct device. This is a step toward removing pci_dev->driver. [bhelgaas: split to separate patch] Link: https://lore.kernel.org/r/20211004125935.2300113-8-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König Signed-off-by: Bjorn Helgaas --- drivers/net/ethernet/marvell/prestera/prestera_pci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/prestera/prestera_pci.c b/drivers/net/ethernet/marvell/prestera/prestera_pci.c index a250d394da38..a8f007f6dad2 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_pci.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_pci.c @@ -720,7 +720,7 @@ out_release: static int prestera_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { - const char *driver_name = pdev->driver->name; + const char *driver_name = dev_driver_string(&pdev->dev); struct prestera_fw *fw; int err; From 40dbd5ffc27843582f98d2bc498409da0ba02359 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 12 Oct 2021 17:54:37 -0500 Subject: [PATCH 255/587] mlxsw: pci: Use dev_driver_string() instead of pci_dev->driver->name MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Replace dev->driver_name() by dev_driver_string() for the corresponding struct device. This is a step toward removing pci_dev->driver. [bhelgaas: split to separate patch] Link: https://lore.kernel.org/r/20211004125935.2300113-8-u.kleine-koenig@pengutronix.de Tested-by: Ido Schimmel Signed-off-by: Uwe Kleine-König Signed-off-by: Bjorn Helgaas Reviewed-by: Ido Schimmel --- drivers/net/ethernet/mellanox/mlxsw/pci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index 13b0259f7ea6..8f306364f7bf 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -1876,7 +1876,7 @@ static void mlxsw_pci_cmd_fini(struct mlxsw_pci *mlxsw_pci) static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { - const char *driver_name = pdev->driver->name; + const char *driver_name = dev_driver_string(&pdev->dev); struct mlxsw_pci *mlxsw_pci; int err; From 230b1e54bd1476578e4ae336b7ac3bca13d81459 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 12 Oct 2021 17:55:03 -0500 Subject: [PATCH 256/587] nfp: use dev_driver_string() instead of pci_dev->driver->name MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Replace dev->driver_name() by dev_driver_string() for the corresponding struct device. This is a step toward removing pci_dev->driver. [bhelgaas: split to separate patch] Link: https://lore.kernel.org/r/20211004125935.2300113-8-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König Signed-off-by: Bjorn Helgaas Acked-by: Simon Horman --- drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index 0685ece1f155..1de076f55740 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -202,7 +202,8 @@ nfp_get_drvinfo(struct nfp_app *app, struct pci_dev *pdev, { char nsp_version[ETHTOOL_FWVERS_LEN] = {}; - strlcpy(drvinfo->driver, pdev->driver->name, sizeof(drvinfo->driver)); + strlcpy(drvinfo->driver, dev_driver_string(&pdev->dev), + sizeof(drvinfo->driver)); nfp_net_get_nspinfo(app, nsp_version); snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%s %s %s %s", vnic_version, nsp_version, From e98754233c58bfe7cad67ed4b7f3980d7e0d731d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Krzysztof=20Wilczy=C5=84ski?= Date: Wed, 13 Oct 2021 01:14:12 +0000 Subject: [PATCH 257/587] PCI: cpqphp: Format if-statement code block correctly MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The code block related to the if-statement in cpqhp_set_irq() is somewhat awkwardly formatted making the code hard to read. Make it readable. No change to functionality intended. Link: https://lore.kernel.org/r/20211013011412.1110829-1-kw@linux.com Signed-off-by: Krzysztof Wilczyński Signed-off-by: Bjorn Helgaas --- drivers/pci/hotplug/cpqphp_pci.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/pci/hotplug/cpqphp_pci.c b/drivers/pci/hotplug/cpqphp_pci.c index 1b2b3f3b648b..9038039ad6db 100644 --- a/drivers/pci/hotplug/cpqphp_pci.c +++ b/drivers/pci/hotplug/cpqphp_pci.c @@ -189,8 +189,10 @@ int cpqhp_set_irq(u8 bus_num, u8 dev_num, u8 int_pin, u8 irq_num) /* This should only be for x86 as it sets the Edge Level * Control Register */ - outb((u8) (temp_word & 0xFF), 0x4d0); outb((u8) ((temp_word & - 0xFF00) >> 8), 0x4d1); rc = 0; } + outb((u8)(temp_word & 0xFF), 0x4d0); + outb((u8)((temp_word & 0xFF00) >> 8), 0x4d1); + rc = 0; + } return rc; } From 3510c5cf4276c3d7bafeb20eae64f1a7a6da8fdf Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 12 Oct 2021 11:55:14 +0900 Subject: [PATCH 258/587] gen_init_cpio: add static const qualifiers Add 'const' to constant arrays. I also added missing 'static'. Signed-off-by: Masahiro Yamada Reviewed-by: Nicolas Schier --- usr/gen_init_cpio.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/usr/gen_init_cpio.c b/usr/gen_init_cpio.c index 03b21189d58b..bf5b98c6cf8d 100644 --- a/usr/gen_init_cpio.c +++ b/usr/gen_init_cpio.c @@ -188,7 +188,7 @@ struct generic_type { mode_t mode; }; -static struct generic_type generic_type_table[] = { +static const struct generic_type generic_type_table[] = { [GT_DIR] = { .type = "dir", .mode = S_IFDIR @@ -491,7 +491,7 @@ static void usage(const char *prog) prog); } -struct file_handler file_handler_table[] = { +static const struct file_handler file_handler_table[] = { { .type = "file", .handler = cpio_mkfile_line, From af7cda832f8a16c5fd4dffdff4ca43790f94d4e8 Mon Sep 17 00:00:00 2001 From: Simon Xue Date: Wed, 18 Aug 2021 17:34:06 +0800 Subject: [PATCH 259/587] dt-bindings: rockchip: Add DesignWare based PCIe controller Document DT bindings for PCIe controller found on Rockchip SoC. Link: https://lore.kernel.org/r/20210818093406.157788-1-xxm@rock-chips.com Signed-off-by: Simon Xue Signed-off-by: Lorenzo Pieralisi Reviewed-by: Rob Herring Reviewed-by: Kever Yang --- .../bindings/pci/rockchip-dw-pcie.yaml | 141 ++++++++++++++++++ 1 file changed, 141 insertions(+) create mode 100644 Documentation/devicetree/bindings/pci/rockchip-dw-pcie.yaml diff --git a/Documentation/devicetree/bindings/pci/rockchip-dw-pcie.yaml b/Documentation/devicetree/bindings/pci/rockchip-dw-pcie.yaml new file mode 100644 index 000000000000..142bbe577763 --- /dev/null +++ b/Documentation/devicetree/bindings/pci/rockchip-dw-pcie.yaml @@ -0,0 +1,141 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/pci/rockchip-dw-pcie.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: DesignWare based PCIe controller on Rockchip SoCs + +maintainers: + - Shawn Lin + - Simon Xue + - Heiko Stuebner + +description: |+ + RK3568 SoC PCIe host controller is based on the Synopsys DesignWare + PCIe IP and thus inherits all the common properties defined in + designware-pcie.txt. + +allOf: + - $ref: /schemas/pci/pci-bus.yaml# + +# We need a select here so we don't match all nodes with 'snps,dw-pcie' +select: + properties: + compatible: + contains: + const: rockchip,rk3568-pcie + required: + - compatible + +properties: + compatible: + items: + - const: rockchip,rk3568-pcie + - const: snps,dw-pcie + + reg: + items: + - description: Data Bus Interface (DBI) registers + - description: Rockchip designed configuration registers + - description: Config registers + + reg-names: + items: + - const: dbi + - const: apb + - const: config + + clocks: + items: + - description: AHB clock for PCIe master + - description: AHB clock for PCIe slave + - description: AHB clock for PCIe dbi + - description: APB clock for PCIe + - description: Auxiliary clock for PCIe + + clock-names: + items: + - const: aclk_mst + - const: aclk_slv + - const: aclk_dbi + - const: pclk + - const: aux + + msi-map: true + + num-lanes: true + + phys: + maxItems: 1 + + phy-names: + const: pcie-phy + + power-domains: + maxItems: 1 + + ranges: + maxItems: 2 + + resets: + maxItems: 1 + + reset-names: + const: pipe + + vpcie3v3-supply: true + +required: + - compatible + - reg + - reg-names + - clocks + - clock-names + - msi-map + - num-lanes + - phys + - phy-names + - power-domains + - resets + - reset-names + +unevaluatedProperties: false + +examples: + - | + + bus { + #address-cells = <2>; + #size-cells = <2>; + + pcie3x2: pcie@fe280000 { + compatible = "rockchip,rk3568-pcie", "snps,dw-pcie"; + reg = <0x3 0xc0800000 0x0 0x390000>, + <0x0 0xfe280000 0x0 0x10000>, + <0x3 0x80000000 0x0 0x100000>; + reg-names = "dbi", "apb", "config"; + bus-range = <0x20 0x2f>; + clocks = <&cru 143>, <&cru 144>, + <&cru 145>, <&cru 146>, + <&cru 147>; + clock-names = "aclk_mst", "aclk_slv", + "aclk_dbi", "pclk", + "aux"; + device_type = "pci"; + linux,pci-domain = <2>; + max-link-speed = <2>; + msi-map = <0x2000 &its 0x2000 0x1000>; + num-lanes = <2>; + phys = <&pcie30phy>; + phy-names = "pcie-phy"; + power-domains = <&power 15>; + ranges = <0x81000000 0x0 0x80800000 0x3 0x80800000 0x0 0x100000>, + <0x83000000 0x0 0x80900000 0x3 0x80900000 0x0 0x3f700000>; + resets = <&cru 193>; + reset-names = "pipe"; + #address-cells = <3>; + #size-cells = <2>; + }; + }; +... From 42cf2a633d5dc2b5abc440d61b6c1c5fb7dddbbb Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 11 Aug 2021 16:25:30 +0200 Subject: [PATCH 260/587] PCI: vmd: depend on !UML With UML having enabled (simulated) PCI on UML, VMD breaks allyesconfig/allmodconfig compilation because it assumes it's running on X86_64 bare metal, and has hardcoded API use of ARCH=x86. Make it depend on !UML to fix this. Link: https://lore.kernel.org/r/20210811162530.affe26231bc3.I131b3c1e67e3d2ead6e98addd256c835fbef9a3e@changeid Signed-off-by: Johannes Berg Signed-off-by: Lorenzo Pieralisi Reviewed-by: Jon Derrick Acked-by: Randy Dunlap # build-tested --- drivers/pci/controller/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig index 326f7d13024f..9ae1ff198e57 100644 --- a/drivers/pci/controller/Kconfig +++ b/drivers/pci/controller/Kconfig @@ -254,7 +254,7 @@ config PCIE_MEDIATEK_GEN3 MediaTek SoCs. config VMD - depends on PCI_MSI && X86_64 && SRCU + depends on PCI_MSI && X86_64 && SRCU && !UML tristate "Intel Volume Management Device Driver" help Adds support for the Intel Volume Management Device (VMD). VMD is a From aa4858eb8264358e9c18c3ad79d6ab4fdc71e0c2 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 4 Oct 2021 14:45:45 +0200 Subject: [PATCH 261/587] gpio: aggregator: Wrap access to gpiochip_fwd.tmp[] The tmp[] member of the gpiochip_fwd structure is used to store both the temporary values bitmap and the desc pointers for operations on multiple GPIOs. As both are arrays with sizes unknown at compile-time, accessing them requires offset calculations, which are currently duplicated in gpio_fwd_get_multiple() and gpio_fwd_set_multiple(). Introduce (a) accessors for both arrays and (b) a macro to calculate the needed storage size. This confines the layout of the tmp[] member into a single spot, to ease maintenance. Signed-off-by: Geert Uytterhoeven Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-aggregator.c | 25 +++++++++++-------------- 1 file changed, 11 insertions(+), 14 deletions(-) diff --git a/drivers/gpio/gpio-aggregator.c b/drivers/gpio/gpio-aggregator.c index 34e35b64dcdc..e9671d1660ef 100644 --- a/drivers/gpio/gpio-aggregator.c +++ b/drivers/gpio/gpio-aggregator.c @@ -247,6 +247,11 @@ struct gpiochip_fwd { unsigned long tmp[]; /* values and descs for multiple ops */ }; +#define fwd_tmp_values(fwd) &(fwd)->tmp[0] +#define fwd_tmp_descs(fwd) (void *)&(fwd)->tmp[BITS_TO_LONGS((fwd)->chip.ngpio)] + +#define fwd_tmp_size(ngpios) (BITS_TO_LONGS((ngpios)) + (ngpios)) + static int gpio_fwd_get_direction(struct gpio_chip *chip, unsigned int offset) { struct gpiochip_fwd *fwd = gpiochip_get_data(chip); @@ -279,15 +284,11 @@ static int gpio_fwd_get(struct gpio_chip *chip, unsigned int offset) static int gpio_fwd_get_multiple(struct gpiochip_fwd *fwd, unsigned long *mask, unsigned long *bits) { - struct gpio_desc **descs; - unsigned long *values; + struct gpio_desc **descs = fwd_tmp_descs(fwd); + unsigned long *values = fwd_tmp_values(fwd); unsigned int i, j = 0; int error; - /* Both values bitmap and desc pointers are stored in tmp[] */ - values = &fwd->tmp[0]; - descs = (void *)&fwd->tmp[BITS_TO_LONGS(fwd->chip.ngpio)]; - bitmap_clear(values, 0, fwd->chip.ngpio); for_each_set_bit(i, mask, fwd->chip.ngpio) descs[j++] = fwd->descs[i]; @@ -333,14 +334,10 @@ static void gpio_fwd_set(struct gpio_chip *chip, unsigned int offset, int value) static void gpio_fwd_set_multiple(struct gpiochip_fwd *fwd, unsigned long *mask, unsigned long *bits) { - struct gpio_desc **descs; - unsigned long *values; + struct gpio_desc **descs = fwd_tmp_descs(fwd); + unsigned long *values = fwd_tmp_values(fwd); unsigned int i, j = 0; - /* Both values bitmap and desc pointers are stored in tmp[] */ - values = &fwd->tmp[0]; - descs = (void *)&fwd->tmp[BITS_TO_LONGS(fwd->chip.ngpio)]; - for_each_set_bit(i, mask, fwd->chip.ngpio) { __assign_bit(j, values, test_bit(i, bits)); descs[j++] = fwd->descs[i]; @@ -398,8 +395,8 @@ static struct gpiochip_fwd *gpiochip_fwd_create(struct device *dev, unsigned int i; int error; - fwd = devm_kzalloc(dev, struct_size(fwd, tmp, - BITS_TO_LONGS(ngpios) + ngpios), GFP_KERNEL); + fwd = devm_kzalloc(dev, struct_size(fwd, tmp, fwd_tmp_size(ngpios)), + GFP_KERNEL); if (!fwd) return ERR_PTR(-ENOMEM); From 06de2cd788bfa3b51137e9bd471d68029ab68103 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 12 Oct 2021 17:39:27 +0200 Subject: [PATCH 262/587] gpio: max730x: Make __max730x_remove() return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit An spi or i2c remove callback is only called for devices that probed successfully. In this case this implies that __max730x_probe() set a non-NULL driver data. So the check ts == NULL is never true. With this check dropped, __max730x_remove() returns zero unconditionally. Make it return void instead which makes it easier to see in the callers that there is no error to handle. Also the return value of i2c and spi remove callbacks is ignored anyway. Signed-off-by: Uwe Kleine-König Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-max7300.c | 4 +++- drivers/gpio/gpio-max7301.c | 4 +++- drivers/gpio/gpio-max730x.c | 6 +----- include/linux/spi/max7301.h | 2 +- 4 files changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/gpio/gpio-max7300.c b/drivers/gpio/gpio-max7300.c index 19cc2ed6a3f5..b2b547dd6e84 100644 --- a/drivers/gpio/gpio-max7300.c +++ b/drivers/gpio/gpio-max7300.c @@ -50,7 +50,9 @@ static int max7300_probe(struct i2c_client *client, static int max7300_remove(struct i2c_client *client) { - return __max730x_remove(&client->dev); + __max730x_remove(&client->dev); + + return 0; } static const struct i2c_device_id max7300_id[] = { diff --git a/drivers/gpio/gpio-max7301.c b/drivers/gpio/gpio-max7301.c index 1307c243b4e9..5862d73bf325 100644 --- a/drivers/gpio/gpio-max7301.c +++ b/drivers/gpio/gpio-max7301.c @@ -66,7 +66,9 @@ static int max7301_probe(struct spi_device *spi) static int max7301_remove(struct spi_device *spi) { - return __max730x_remove(&spi->dev); + __max730x_remove(&spi->dev); + + return 0; } static const struct spi_device_id max7301_id[] = { diff --git a/drivers/gpio/gpio-max730x.c b/drivers/gpio/gpio-max730x.c index b8c1fe20f49a..bb5cf14ae4c8 100644 --- a/drivers/gpio/gpio-max730x.c +++ b/drivers/gpio/gpio-max730x.c @@ -220,18 +220,14 @@ exit_destroy: } EXPORT_SYMBOL_GPL(__max730x_probe); -int __max730x_remove(struct device *dev) +void __max730x_remove(struct device *dev) { struct max7301 *ts = dev_get_drvdata(dev); - if (ts == NULL) - return -ENODEV; - /* Power down the chip and disable IRQ output */ ts->write(dev, 0x04, 0x00); gpiochip_remove(&ts->chip); mutex_destroy(&ts->lock); - return 0; } EXPORT_SYMBOL_GPL(__max730x_remove); diff --git a/include/linux/spi/max7301.h b/include/linux/spi/max7301.h index 21449067aedb..e392c53758bc 100644 --- a/include/linux/spi/max7301.h +++ b/include/linux/spi/max7301.h @@ -31,6 +31,6 @@ struct max7301_platform_data { u32 input_pullup_active; }; -extern int __max730x_remove(struct device *dev); +extern void __max730x_remove(struct device *dev); extern int __max730x_probe(struct max7301 *ts); #endif From f4a20dfac88c06c9b529a41ff4cf9acba8f3fdff Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 12 Oct 2021 17:39:28 +0200 Subject: [PATCH 263/587] gpio: mc33880: Drop if with an always false condition MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit An spi remove callback is only called for devices that probed successfully. In this case this implies that mc33880_probe() set a non-NULL driver data. So the check for mc being NULL is never true and the check can be dropped. Also the return value ofspi remove callbacks is ignored anyway. Signed-off-by: Uwe Kleine-König Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-mc33880.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/gpio/gpio-mc33880.c b/drivers/gpio/gpio-mc33880.c index f8194f7c6186..31d2be1bebc8 100644 --- a/drivers/gpio/gpio-mc33880.c +++ b/drivers/gpio/gpio-mc33880.c @@ -139,8 +139,6 @@ static int mc33880_remove(struct spi_device *spi) struct mc33880 *mc; mc = spi_get_drvdata(spi); - if (!mc) - return -ENODEV; gpiochip_remove(&mc->chip); mutex_destroy(&mc->lock); From 1a323bd071dd81c9c136c06fad9e02c403b48aca Mon Sep 17 00:00:00 2001 From: Kelvin Cao Date: Thu, 14 Oct 2021 14:18:55 +0000 Subject: [PATCH 264/587] PCI/switchtec: Error out MRPC execution when MMIO reads fail A firmware hard reset may be initiated by various mechanisms including a UART interface, TWI sideband interface from BMC, MRPC command from userspace, etc. The switchtec management driver is unaware of these resets. The reset clears PCI state including the BARs and Memory Space Enable bits, so the device no longer responds to the MMIO accesses the driver uses to operate it. MMIO reads to the device will fail with a PCIe error. When the root complex handles that error, it typically fabricates ~0 data to complete the CPU read. Check for this sort of error by reading the device ID from MMIO space. This ID can never be ~0, so if we see that value, it probably means the PCIe Memory Read failed and we should return an error indication to the application using the switchtec driver. Link: https://lore.kernel.org/r/20211014141859.11444-2-kelvin.cao@microchip.com Signed-off-by: Kelvin Cao Signed-off-by: Bjorn Helgaas --- drivers/pci/switch/switchtec.c | 67 ++++++++++++++++++++++++++++++---- 1 file changed, 60 insertions(+), 7 deletions(-) diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index 0b301f8be9ed..e5bb2ac0e7bb 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -45,6 +45,7 @@ enum mrpc_state { MRPC_QUEUED, MRPC_RUNNING, MRPC_DONE, + MRPC_IO_ERROR, }; struct switchtec_user { @@ -66,6 +67,19 @@ struct switchtec_user { int event_cnt; }; +/* + * The MMIO reads to the device_id register should always return the device ID + * of the device, otherwise the firmware is probably stuck or unreachable + * due to a firmware reset which clears PCI state including the BARs and Memory + * Space Enable bits. + */ +static int is_firmware_running(struct switchtec_dev *stdev) +{ + u32 device = ioread32(&stdev->mmio_sys_info->device_id); + + return stdev->pdev->device == device; +} + static struct switchtec_user *stuser_create(struct switchtec_dev *stdev) { struct switchtec_user *stuser; @@ -113,6 +127,7 @@ static void stuser_set_state(struct switchtec_user *stuser, [MRPC_QUEUED] = "QUEUED", [MRPC_RUNNING] = "RUNNING", [MRPC_DONE] = "DONE", + [MRPC_IO_ERROR] = "IO_ERROR", }; stuser->state = state; @@ -184,9 +199,26 @@ static int mrpc_queue_cmd(struct switchtec_user *stuser) return 0; } +static void mrpc_cleanup_cmd(struct switchtec_dev *stdev) +{ + /* requires the mrpc_mutex to already be held when called */ + + struct switchtec_user *stuser = list_entry(stdev->mrpc_queue.next, + struct switchtec_user, list); + + stuser->cmd_done = true; + wake_up_interruptible(&stuser->cmd_comp); + list_del_init(&stuser->list); + stuser_put(stuser); + stdev->mrpc_busy = 0; + + mrpc_cmd_submit(stdev); +} + static void mrpc_complete_cmd(struct switchtec_dev *stdev) { /* requires the mrpc_mutex to already be held when called */ + struct switchtec_user *stuser; if (list_empty(&stdev->mrpc_queue)) @@ -223,13 +255,7 @@ static void mrpc_complete_cmd(struct switchtec_dev *stdev) memcpy_fromio(stuser->data, &stdev->mmio_mrpc->output_data, stuser->read_len); out: - stuser->cmd_done = true; - wake_up_interruptible(&stuser->cmd_comp); - list_del_init(&stuser->list); - stuser_put(stuser); - stdev->mrpc_busy = 0; - - mrpc_cmd_submit(stdev); + mrpc_cleanup_cmd(stdev); } static void mrpc_event_work(struct work_struct *work) @@ -246,6 +272,23 @@ static void mrpc_event_work(struct work_struct *work) mutex_unlock(&stdev->mrpc_mutex); } +static void mrpc_error_complete_cmd(struct switchtec_dev *stdev) +{ + /* requires the mrpc_mutex to already be held when called */ + + struct switchtec_user *stuser; + + if (list_empty(&stdev->mrpc_queue)) + return; + + stuser = list_entry(stdev->mrpc_queue.next, + struct switchtec_user, list); + + stuser_set_state(stuser, MRPC_IO_ERROR); + + mrpc_cleanup_cmd(stdev); +} + static void mrpc_timeout_work(struct work_struct *work) { struct switchtec_dev *stdev; @@ -257,6 +300,11 @@ static void mrpc_timeout_work(struct work_struct *work) mutex_lock(&stdev->mrpc_mutex); + if (!is_firmware_running(stdev)) { + mrpc_error_complete_cmd(stdev); + goto out; + } + if (stdev->dma_mrpc) status = stdev->dma_mrpc->status; else @@ -544,6 +592,11 @@ static ssize_t switchtec_dev_read(struct file *filp, char __user *data, if (rc) return rc; + if (stuser->state == MRPC_IO_ERROR) { + mutex_unlock(&stdev->mrpc_mutex); + return -EIO; + } + if (stuser->state != MRPC_DONE) { mutex_unlock(&stdev->mrpc_mutex); return -EBADE; From 551ec658b69807318aeef5506da886cf9587b251 Mon Sep 17 00:00:00 2001 From: Kelvin Cao Date: Thu, 14 Oct 2021 14:18:56 +0000 Subject: [PATCH 265/587] PCI/switchtec: Fix a MRPC error status handling issue If an error is encountered when executing a MRPC command, the firmware will set the status register to SWITCHTEC_MRPC_STATUS_ERROR and return the error code in the return value register. Add handling of SWITCHTEC_MRPC_STATUS_ERROR on status register when completing a MRPC command. Link: https://lore.kernel.org/r/20211014141859.11444-3-kelvin.cao@microchip.com Signed-off-by: Kelvin Cao Signed-off-by: Bjorn Helgaas --- drivers/pci/switch/switchtec.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index e5bb2ac0e7bb..5c300ff3921d 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -238,7 +238,8 @@ static void mrpc_complete_cmd(struct switchtec_dev *stdev) stuser_set_state(stuser, MRPC_DONE); stuser->return_code = 0; - if (stuser->status != SWITCHTEC_MRPC_STATUS_DONE) + if (stuser->status != SWITCHTEC_MRPC_STATUS_DONE && + stuser->status != SWITCHTEC_MRPC_STATUS_ERROR) goto out; if (stdev->dma_mrpc) @@ -622,7 +623,8 @@ static ssize_t switchtec_dev_read(struct file *filp, char __user *data, out: mutex_unlock(&stdev->mrpc_mutex); - if (stuser->status == SWITCHTEC_MRPC_STATUS_DONE) + if (stuser->status == SWITCHTEC_MRPC_STATUS_DONE || + stuser->status == SWITCHTEC_MRPC_STATUS_ERROR) return size; else if (stuser->status == SWITCHTEC_MRPC_STATUS_INTERRUPTED) return -ENXIO; From 1420ac218abcc1df809eedfb0f7351941b01c785 Mon Sep 17 00:00:00 2001 From: Kelvin Cao Date: Thu, 14 Oct 2021 14:18:57 +0000 Subject: [PATCH 266/587] PCI/switchtec: Update the way of getting management VEP instance ID Gen4 firmware adds DMA VEP and NVMe VEP support in VEP (virtual EP) instance ID register in addtion to management EP, update the way of getting management VEP instance ID. Link: https://lore.kernel.org/r/20211014141859.11444-4-kelvin.cao@microchip.com Signed-off-by: Kelvin Cao Signed-off-by: Bjorn Helgaas --- drivers/pci/switch/switchtec.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index 5c300ff3921d..97a93c9b4629 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -1133,7 +1133,7 @@ static int ioctl_pff_to_port(struct switchtec_dev *stdev, break; } - reg = ioread32(&pcfg->vep_pff_inst_id); + reg = ioread32(&pcfg->vep_pff_inst_id) & 0xFF; if (reg == p.pff) { p.port = SWITCHTEC_IOCTL_PFF_VEP; break; @@ -1179,7 +1179,7 @@ static int ioctl_port_to_pff(struct switchtec_dev *stdev, p.pff = ioread32(&pcfg->usp_pff_inst_id); break; case SWITCHTEC_IOCTL_PFF_VEP: - p.pff = ioread32(&pcfg->vep_pff_inst_id); + p.pff = ioread32(&pcfg->vep_pff_inst_id) & 0xFF; break; default: if (p.port > ARRAY_SIZE(pcfg->dsp_pff_inst_id)) @@ -1553,7 +1553,7 @@ static void init_pff(struct switchtec_dev *stdev) if (reg < stdev->pff_csr_count) stdev->pff_local[reg] = 1; - reg = ioread32(&pcfg->vep_pff_inst_id); + reg = ioread32(&pcfg->vep_pff_inst_id) & 0xFF; if (reg < stdev->pff_csr_count) stdev->pff_local[reg] = 1; From 67116444cf55e1d070ee2060ffe4d1c72917ec31 Mon Sep 17 00:00:00 2001 From: Kelvin Cao Date: Thu, 14 Oct 2021 14:18:58 +0000 Subject: [PATCH 267/587] PCI/switchtec: Replace ENOTSUPP with EOPNOTSUPP ENOTSUPP is not a SUSV4 error code, and the following checkpatch.pl warning will be given for new patches which still use ENOTSUPP. WARNING: ENOTSUPP is not a SUSV4 error code, prefer EOPNOTSUPP See the link below for the discussion. https://lore.kernel.org/netdev/20200511165319.2251678-1-kuba@kernel.org/ Replace ENOTSUPP with EOPNOTSUPP to align with future patches which will be using EOPNOTSUPP. Link: https://lore.kernel.org/r/20211014141859.11444-5-kelvin.cao@microchip.com Signed-off-by: Kelvin Cao Signed-off-by: Bjorn Helgaas --- drivers/pci/switch/switchtec.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index 97a93c9b4629..236cb40cc7c5 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -376,7 +376,7 @@ static ssize_t field ## _show(struct device *dev, \ return io_string_show(buf, &si->gen4.field, \ sizeof(si->gen4.field)); \ else \ - return -ENOTSUPP; \ + return -EOPNOTSUPP; \ } \ \ static DEVICE_ATTR_RO(field) @@ -668,7 +668,7 @@ static int ioctl_flash_info(struct switchtec_dev *stdev, info.flash_length = ioread32(&fi->gen4.flash_length); info.num_partitions = SWITCHTEC_NUM_PARTITIONS_GEN4; } else { - return -ENOTSUPP; + return -EOPNOTSUPP; } if (copy_to_user(uinfo, &info, sizeof(info))) @@ -876,7 +876,7 @@ static int ioctl_flash_part_info(struct switchtec_dev *stdev, if (ret) return ret; } else { - return -ENOTSUPP; + return -EOPNOTSUPP; } if (copy_to_user(uinfo, &info, sizeof(info))) @@ -1611,7 +1611,7 @@ static int switchtec_init_pci(struct switchtec_dev *stdev, else if (stdev->gen == SWITCHTEC_GEN4) part_id = &stdev->mmio_sys_info->gen4.partition_id; else - return -ENOTSUPP; + return -EOPNOTSUPP; stdev->partition = ioread8(part_id); stdev->partition_count = ioread8(&stdev->mmio_ntb->partition_count); From 9f37ab0412eba537377c38b1dde1a04fbd7b5264 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Thu, 14 Oct 2021 14:18:59 +0000 Subject: [PATCH 268/587] PCI/switchtec: Add check of event support Not all events are supported by every gen/variant of the Switchtec firmware. To solve this, since Gen4, a new bit in each event header is introduced to indicate if an event is supported by the firmware. Link: https://lore.kernel.org/r/20211014141859.11444-6-kelvin.cao@microchip.com Signed-off-by: Logan Gunthorpe Signed-off-by: Kelvin Cao Signed-off-by: Bjorn Helgaas --- drivers/pci/switch/switchtec.c | 8 +++++++- include/linux/switchtec.h | 1 + 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index 236cb40cc7c5..38c2b036fb8e 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -1024,6 +1024,9 @@ static int event_ctl(struct switchtec_dev *stdev, return PTR_ERR(reg); hdr = ioread32(reg); + if (hdr & SWITCHTEC_EVENT_NOT_SUPP) + return -EOPNOTSUPP; + for (i = 0; i < ARRAY_SIZE(ctl->data); i++) ctl->data[i] = ioread32(®[i + 1]); @@ -1096,7 +1099,7 @@ static int ioctl_event_ctl(struct switchtec_dev *stdev, for (ctl.index = 0; ctl.index < nr_idxs; ctl.index++) { ctl.flags = event_flags; ret = event_ctl(stdev, &ctl); - if (ret < 0) + if (ret < 0 && ret != -EOPNOTSUPP) return ret; } } else { @@ -1403,6 +1406,9 @@ static int mask_event(struct switchtec_dev *stdev, int eid, int idx) hdr_reg = event_regs[eid].map_reg(stdev, off, idx); hdr = ioread32(hdr_reg); + if (hdr & SWITCHTEC_EVENT_NOT_SUPP) + return 0; + if (!(hdr & SWITCHTEC_EVENT_OCCURRED && hdr & SWITCHTEC_EVENT_EN_IRQ)) return 0; diff --git a/include/linux/switchtec.h b/include/linux/switchtec.h index 082f1d51957a..be24056ac00f 100644 --- a/include/linux/switchtec.h +++ b/include/linux/switchtec.h @@ -19,6 +19,7 @@ #define SWITCHTEC_EVENT_EN_CLI BIT(2) #define SWITCHTEC_EVENT_EN_IRQ BIT(3) #define SWITCHTEC_EVENT_FATAL BIT(4) +#define SWITCHTEC_EVENT_NOT_SUPP BIT(31) #define SWITCHTEC_DMA_MRPC_EN BIT(0) From b89ff410253d7468f84720d2d5c2bb0bafedf3bd Mon Sep 17 00:00:00 2001 From: Prasad Malisetty Date: Thu, 7 Oct 2021 23:18:42 +0530 Subject: [PATCH 269/587] PCI: qcom: Replace ops with struct pcie_cfg in pcie match data Add struct qcom_pcie_cfg as match data for all platforms. Assign appropriate platform ops into struct qcom_pcie_cfg and read using of_device_get_match_data() in qcom_pcie_probe(). Link: https://lore.kernel.org/r/1633628923-25047-5-git-send-email-pmaliset@codeaurora.org Signed-off-by: Prasad Malisetty Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas Reviewed-by: Stephen Boyd --- drivers/pci/controller/dwc/pcie-qcom.c | 66 +++++++++++++++++++++----- 1 file changed, 55 insertions(+), 11 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index 8a7a300163e5..1c3c01ccb831 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -189,6 +189,10 @@ struct qcom_pcie_ops { int (*config_sid)(struct qcom_pcie *pcie); }; +struct qcom_pcie_cfg { + const struct qcom_pcie_ops *ops; +}; + struct qcom_pcie { struct dw_pcie *pci; void __iomem *parf; /* DT parf */ @@ -1456,6 +1460,38 @@ static const struct qcom_pcie_ops ops_1_9_0 = { .config_sid = qcom_pcie_config_sid_sm8250, }; +static const struct qcom_pcie_cfg apq8084_cfg = { + .ops = &ops_1_0_0, +}; + +static const struct qcom_pcie_cfg ipq8064_cfg = { + .ops = &ops_2_1_0, +}; + +static const struct qcom_pcie_cfg msm8996_cfg = { + .ops = &ops_2_3_2, +}; + +static const struct qcom_pcie_cfg ipq8074_cfg = { + .ops = &ops_2_3_3, +}; + +static const struct qcom_pcie_cfg ipq4019_cfg = { + .ops = &ops_2_4_0, +}; + +static const struct qcom_pcie_cfg sdm845_cfg = { + .ops = &ops_2_7_0, +}; + +static const struct qcom_pcie_cfg sm8250_cfg = { + .ops = &ops_1_9_0, +}; + +static const struct qcom_pcie_cfg sc7280_cfg = { + .ops = &ops_1_9_0, +}; + static const struct dw_pcie_ops dw_pcie_ops = { .link_up = qcom_pcie_link_up, .start_link = qcom_pcie_start_link, @@ -1467,6 +1503,7 @@ static int qcom_pcie_probe(struct platform_device *pdev) struct pcie_port *pp; struct dw_pcie *pci; struct qcom_pcie *pcie; + const struct qcom_pcie_cfg *pcie_cfg; int ret; pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); @@ -1488,7 +1525,13 @@ static int qcom_pcie_probe(struct platform_device *pdev) pcie->pci = pci; - pcie->ops = of_device_get_match_data(dev); + pcie_cfg = of_device_get_match_data(dev); + if (!pcie_cfg || !pcie_cfg->ops) { + dev_err(dev, "Invalid platform data\n"); + return -EINVAL; + } + + pcie->ops = pcie_cfg->ops; pcie->reset = devm_gpiod_get_optional(dev, "perst", GPIOD_OUT_HIGH); if (IS_ERR(pcie->reset)) { @@ -1545,16 +1588,17 @@ err_pm_runtime_put: } static const struct of_device_id qcom_pcie_match[] = { - { .compatible = "qcom,pcie-apq8084", .data = &ops_1_0_0 }, - { .compatible = "qcom,pcie-ipq8064", .data = &ops_2_1_0 }, - { .compatible = "qcom,pcie-ipq8064-v2", .data = &ops_2_1_0 }, - { .compatible = "qcom,pcie-apq8064", .data = &ops_2_1_0 }, - { .compatible = "qcom,pcie-msm8996", .data = &ops_2_3_2 }, - { .compatible = "qcom,pcie-ipq8074", .data = &ops_2_3_3 }, - { .compatible = "qcom,pcie-ipq4019", .data = &ops_2_4_0 }, - { .compatible = "qcom,pcie-qcs404", .data = &ops_2_4_0 }, - { .compatible = "qcom,pcie-sdm845", .data = &ops_2_7_0 }, - { .compatible = "qcom,pcie-sm8250", .data = &ops_1_9_0 }, + { .compatible = "qcom,pcie-apq8084", .data = &apq8084_cfg }, + { .compatible = "qcom,pcie-ipq8064", .data = &ipq8064_cfg }, + { .compatible = "qcom,pcie-ipq8064-v2", .data = &ipq8064_cfg }, + { .compatible = "qcom,pcie-apq8064", .data = &ipq8064_cfg }, + { .compatible = "qcom,pcie-msm8996", .data = &msm8996_cfg }, + { .compatible = "qcom,pcie-ipq8074", .data = &ipq8074_cfg }, + { .compatible = "qcom,pcie-ipq4019", .data = &ipq4019_cfg }, + { .compatible = "qcom,pcie-qcs404", .data = &ipq4019_cfg }, + { .compatible = "qcom,pcie-sdm845", .data = &sdm845_cfg }, + { .compatible = "qcom,pcie-sm8250", .data = &sm8250_cfg }, + { .compatible = "qcom,pcie-sc7280", .data = &sc7280_cfg }, { } }; From aa9c0df98c2920f7176b001737546c6595f594a4 Mon Sep 17 00:00:00 2001 From: Prasad Malisetty Date: Thu, 7 Oct 2021 23:18:43 +0530 Subject: [PATCH 270/587] PCI: qcom: Switch pcie_1_pipe_clk_src after PHY init in SC7280 On the SC7280, the clock source for gcc_pcie_1_pipe_clk_src must be the TCXO while gdsc is enabled. After PHY init successful clock source should switch to pipe clock for gcc_pcie_1_pipe_clk_src. Link: https://lore.kernel.org/r/1633628923-25047-6-git-send-email-pmaliset@codeaurora.org Signed-off-by: Prasad Malisetty Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas Reviewed-by: Stephen Boyd --- drivers/pci/controller/dwc/pcie-qcom.c | 29 ++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index 1c3c01ccb831..c4ff996dc443 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -166,6 +166,9 @@ struct qcom_pcie_resources_2_7_0 { struct regulator_bulk_data supplies[2]; struct reset_control *pci_reset; struct clk *pipe_clk; + struct clk *pipe_clk_src; + struct clk *phy_pipe_clk; + struct clk *ref_clk_src; }; union qcom_pcie_resources { @@ -191,6 +194,7 @@ struct qcom_pcie_ops { struct qcom_pcie_cfg { const struct qcom_pcie_ops *ops; + unsigned int pipe_clk_need_muxing:1; }; struct qcom_pcie { @@ -201,6 +205,7 @@ struct qcom_pcie { struct phy *phy; struct gpio_desc *reset; const struct qcom_pcie_ops *ops; + unsigned int pipe_clk_need_muxing:1; }; #define to_qcom_pcie(x) dev_get_drvdata((x)->dev) @@ -1171,6 +1176,20 @@ static int qcom_pcie_get_resources_2_7_0(struct qcom_pcie *pcie) if (ret < 0) return ret; + if (pcie->pipe_clk_need_muxing) { + res->pipe_clk_src = devm_clk_get(dev, "pipe_mux"); + if (IS_ERR(res->pipe_clk_src)) + return PTR_ERR(res->pipe_clk_src); + + res->phy_pipe_clk = devm_clk_get(dev, "phy_pipe"); + if (IS_ERR(res->phy_pipe_clk)) + return PTR_ERR(res->phy_pipe_clk); + + res->ref_clk_src = devm_clk_get(dev, "ref"); + if (IS_ERR(res->ref_clk_src)) + return PTR_ERR(res->ref_clk_src); + } + res->pipe_clk = devm_clk_get(dev, "pipe"); return PTR_ERR_OR_ZERO(res->pipe_clk); } @@ -1189,6 +1208,10 @@ static int qcom_pcie_init_2_7_0(struct qcom_pcie *pcie) return ret; } + /* Set TCXO as clock source for pcie_pipe_clk_src */ + if (pcie->pipe_clk_need_muxing) + clk_set_parent(res->pipe_clk_src, res->ref_clk_src); + ret = clk_bulk_prepare_enable(res->num_clks, res->clks); if (ret < 0) goto err_disable_regulators; @@ -1260,6 +1283,10 @@ static int qcom_pcie_post_init_2_7_0(struct qcom_pcie *pcie) { struct qcom_pcie_resources_2_7_0 *res = &pcie->res.v2_7_0; + /* Set pipe clock as clock source for pcie_pipe_clk_src */ + if (pcie->pipe_clk_need_muxing) + clk_set_parent(res->pipe_clk_src, res->phy_pipe_clk); + return clk_prepare_enable(res->pipe_clk); } @@ -1490,6 +1517,7 @@ static const struct qcom_pcie_cfg sm8250_cfg = { static const struct qcom_pcie_cfg sc7280_cfg = { .ops = &ops_1_9_0, + .pipe_clk_need_muxing = true, }; static const struct dw_pcie_ops dw_pcie_ops = { @@ -1532,6 +1560,7 @@ static int qcom_pcie_probe(struct platform_device *pdev) } pcie->ops = pcie_cfg->ops; + pcie->pipe_clk_need_muxing = pcie_cfg->pipe_clk_need_muxing; pcie->reset = devm_gpiod_get_optional(dev, "perst", GPIOD_OUT_HIGH); if (IS_ERR(pcie->reset)) { From 15b02050baeebcf1a1a1d3146ddea8f37ae00f96 Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Mon, 28 Jun 2021 14:17:29 -0700 Subject: [PATCH 271/587] mtd: spi-nor: Enable locking for n25q128a13 As 4bit block protection patchset for some micron models are merged, n25q128a13 also uses 4 bit Block Protection scheme, so enable locking for it. Tested it on n25q128a13, the locking functions work well. Signed-off-by: Jonathan Lemon Signed-off-by: Tudor Ambarus Reviewed-by: Michael Walle Link: https://lore.kernel.org/r/20210628211729.3625017-1-jonathan.lemon@gmail.com --- drivers/mtd/spi-nor/micron-st.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/spi-nor/micron-st.c b/drivers/mtd/spi-nor/micron-st.c index c224e59820a1..f3d19b716b7b 100644 --- a/drivers/mtd/spi-nor/micron-st.c +++ b/drivers/mtd/spi-nor/micron-st.c @@ -146,7 +146,9 @@ static const struct flash_info st_parts[] = { SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB | SPI_NOR_4BIT_BP | SPI_NOR_BP3_SR_BIT6) }, { "n25q128a13", INFO(0x20ba18, 0, 64 * 1024, 256, - SECT_4K | USE_FSR | SPI_NOR_QUAD_READ) }, + SECT_4K | USE_FSR | SPI_NOR_QUAD_READ | + SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB | + SPI_NOR_4BIT_BP | SPI_NOR_BP3_SR_BIT6) }, { "mt25ql256a", INFO6(0x20ba19, 0x104400, 64 * 1024, 512, SECT_4K | USE_FSR | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ | SPI_NOR_4B_OPCODES) }, From 78e4d342187625585932bb437ec26e1060f7fc6f Mon Sep 17 00:00:00 2001 From: Evgeny Novikov Date: Fri, 9 Jul 2021 17:45:29 +0300 Subject: [PATCH 272/587] mtd: spi-nor: hisi-sfc: Remove excessive clk_disable_unprepare() hisi_spi_nor_probe() invokes clk_disable_unprepare() on all paths after successful call of clk_prepare_enable(). Besides, the clock is enabled by hispi_spi_nor_prep() and disabled by hispi_spi_nor_unprep(). So at remove time it is not possible to have the clock enabled. The patch removes excessive clk_disable_unprepare() from hisi_spi_nor_remove(). Found by Linux Driver Verification project (linuxtesting.org). Fixes: e523f11141bd ("mtd: spi-nor: add hisilicon spi-nor flash controller driver") Signed-off-by: Evgeny Novikov Signed-off-by: Tudor Ambarus Reviewed-by: Pratyush Yadav Link: https://lore.kernel.org/r/20210709144529.31379-1-novikov@ispras.ru --- drivers/mtd/spi-nor/controllers/hisi-sfc.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mtd/spi-nor/controllers/hisi-sfc.c b/drivers/mtd/spi-nor/controllers/hisi-sfc.c index 47fbf1d1e557..516e50269478 100644 --- a/drivers/mtd/spi-nor/controllers/hisi-sfc.c +++ b/drivers/mtd/spi-nor/controllers/hisi-sfc.c @@ -477,7 +477,6 @@ static int hisi_spi_nor_remove(struct platform_device *pdev) hisi_spi_nor_unregister_all(host); mutex_destroy(&host->lock); - clk_disable_unprepare(host->clk); return 0; } From a10ed4c42533362a825be2adb2e5272d3644553e Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Wed, 1 Sep 2021 15:42:59 +0800 Subject: [PATCH 273/587] mtd: spi-nor: hisi-sfc: Make use of the helper function devm_platform_ioremap_resource_byname() Use the devm_platform_ioremap_resource_byname() helper instead of calling platform_get_resource_byname() and devm_ioremap_resource() separately Signed-off-by: Cai Huoqing Signed-off-by: Tudor Ambarus Acked-by: Pratyush Yadav Link: https://lore.kernel.org/r/20210901074259.9683-1-caihuoqing@baidu.com --- drivers/mtd/spi-nor/controllers/hisi-sfc.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/mtd/spi-nor/controllers/hisi-sfc.c b/drivers/mtd/spi-nor/controllers/hisi-sfc.c index 516e50269478..94a969185ceb 100644 --- a/drivers/mtd/spi-nor/controllers/hisi-sfc.c +++ b/drivers/mtd/spi-nor/controllers/hisi-sfc.c @@ -421,7 +421,6 @@ fail: static int hisi_spi_nor_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct resource *res; struct hifmc_host *host; int ret; @@ -432,13 +431,11 @@ static int hisi_spi_nor_probe(struct platform_device *pdev) platform_set_drvdata(pdev, host); host->dev = dev; - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "control"); - host->regbase = devm_ioremap_resource(dev, res); + host->regbase = devm_platform_ioremap_resource_byname(pdev, "control"); if (IS_ERR(host->regbase)) return PTR_ERR(host->regbase); - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "memory"); - host->iobase = devm_ioremap_resource(dev, res); + host->iobase = devm_platform_ioremap_resource_byname(pdev, "memory"); if (IS_ERR(host->iobase)) return PTR_ERR(host->iobase); From df872ab1ffe4bd865dfb5956cae4901429004ab6 Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Wed, 1 Sep 2021 15:43:06 +0800 Subject: [PATCH 274/587] mtd: spi-nor: nxp-spifi: Make use of the helper function devm_platform_ioremap_resource_byname() Use the devm_platform_ioremap_resource_byname() helper instead of calling platform_get_resource_byname() and devm_ioremap_resource() separately Signed-off-by: Cai Huoqing Signed-off-by: Tudor Ambarus Acked-by: Pratyush Yadav Link: https://lore.kernel.org/r/20210901074307.9733-1-caihuoqing@baidu.com --- drivers/mtd/spi-nor/controllers/nxp-spifi.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/mtd/spi-nor/controllers/nxp-spifi.c b/drivers/mtd/spi-nor/controllers/nxp-spifi.c index 2635c80231bb..9032b9ab2eaf 100644 --- a/drivers/mtd/spi-nor/controllers/nxp-spifi.c +++ b/drivers/mtd/spi-nor/controllers/nxp-spifi.c @@ -381,20 +381,17 @@ static int nxp_spifi_probe(struct platform_device *pdev) { struct device_node *flash_np; struct nxp_spifi *spifi; - struct resource *res; int ret; spifi = devm_kzalloc(&pdev->dev, sizeof(*spifi), GFP_KERNEL); if (!spifi) return -ENOMEM; - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "spifi"); - spifi->io_base = devm_ioremap_resource(&pdev->dev, res); + spifi->io_base = devm_platform_ioremap_resource_byname(pdev, "spifi"); if (IS_ERR(spifi->io_base)) return PTR_ERR(spifi->io_base); - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "flash"); - spifi->flash_base = devm_ioremap_resource(&pdev->dev, res); + spifi->flash_base = devm_platform_ioremap_resource_byname(pdev, "flash"); if (IS_ERR(spifi->flash_base)) return PTR_ERR(spifi->flash_base); From 45a3ec891370bba7984bb4cf57299a6f5744b91e Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Mon, 23 Aug 2021 08:49:58 -0700 Subject: [PATCH 275/587] PCI: qcom: Add sc8180x compatible The SC8180x platform comes with 4 PCIe controllers, typically used for things such as NVME storage or connecting a SDX55 5G modem. Add a compatible for this, that just reuses the 1.9.0 ops. Link: https://lore.kernel.org/linux-arm-msm/20210725040038.3966348-4-bjorn.andersson@linaro.org/ Link: https://lore.kernel.org/r/20210823154958.305677-2-bjorn.andersson@linaro.org Signed-off-by: Bjorn Andersson [lorenzo.pieralisi@arm.com: updated match data structure] Signed-off-by: Lorenzo Pieralisi Reviewed-by: Rob Herring --- Documentation/devicetree/bindings/pci/qcom,pcie.txt | 5 +++-- drivers/pci/controller/dwc/pcie-qcom.c | 1 + 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie.txt b/Documentation/devicetree/bindings/pci/qcom,pcie.txt index 3f646875f8c2..a0ae024c2d0c 100644 --- a/Documentation/devicetree/bindings/pci/qcom,pcie.txt +++ b/Documentation/devicetree/bindings/pci/qcom,pcie.txt @@ -12,6 +12,7 @@ - "qcom,pcie-ipq4019" for ipq4019 - "qcom,pcie-ipq8074" for ipq8074 - "qcom,pcie-qcs404" for qcs404 + - "qcom,pcie-sc8180x" for sc8180x - "qcom,pcie-sdm845" for sdm845 - "qcom,pcie-sm8250" for sm8250 - "qcom,pcie-ipq6018" for ipq6018 @@ -156,7 +157,7 @@ - "pipe" PIPE clock - clock-names: - Usage: required for sm8250 + Usage: required for sc8180x and sm8250 Value type: Definition: Should contain the following entries - "aux" Auxiliary clock @@ -245,7 +246,7 @@ - "ahb" AHB reset - reset-names: - Usage: required for sdm845 and sm8250 + Usage: required for sc8180x, sdm845 and sm8250 Value type: Definition: Should contain the following entries - "pci" PCIe core reset diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index c4ff996dc443..1c3d1116bb60 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -1627,6 +1627,7 @@ static const struct of_device_id qcom_pcie_match[] = { { .compatible = "qcom,pcie-qcs404", .data = &ipq4019_cfg }, { .compatible = "qcom,pcie-sdm845", .data = &sdm845_cfg }, { .compatible = "qcom,pcie-sm8250", .data = &sm8250_cfg }, + { .compatible = "qcom,pcie-sc8180x", .data = &sm8250_cfg }, { .compatible = "qcom,pcie-sc7280", .data = &sc7280_cfg }, { } }; From 4caab28a6215da5f3c1b505ff08810bc6acfe365 Mon Sep 17 00:00:00 2001 From: Kunihiko Hayashi Date: Sat, 18 Sep 2021 09:22:59 +0900 Subject: [PATCH 276/587] PCI: uniphier: Serialize INTx masking/unmasking and fix the bit operation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The condition register PCI_RCV_INTX is used in irq_mask() and irq_unmask() callbacks. Accesses to register can occur at the same time without a lock. Add a lock into each callback to prevent the issue. And INTX mask and unmask fields in PCL_RCV_INTX register should only be set/reset for each bit. Clearing by PCL_RCV_INTX_ALL_MASK should be removed. INTX status fields in PCL_RCV_INTX register only indicates each INTX interrupt status, so the handler can't clear by writing 1 to the field. The status is expected to be cleared by the interrupt origin. The ack function has no meaning, so should remove it. Suggested-by: Pali Rohár Link: https://lore.kernel.org/r/1631924579-24567-1-git-send-email-hayashi.kunihiko@socionext.com Fixes: 7e6d5cd88a6f ("PCI: uniphier: Add UniPhier PCIe host controller support") Signed-off-by: Kunihiko Hayashi Signed-off-by: Lorenzo Pieralisi Acked-by: Pali Rohár Acked-by: Marc Zyngier --- drivers/pci/controller/dwc/pcie-uniphier.c | 26 +++++++++------------- 1 file changed, 10 insertions(+), 16 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-uniphier.c b/drivers/pci/controller/dwc/pcie-uniphier.c index d842fd018129..d05be942956e 100644 --- a/drivers/pci/controller/dwc/pcie-uniphier.c +++ b/drivers/pci/controller/dwc/pcie-uniphier.c @@ -168,30 +168,21 @@ static void uniphier_pcie_irq_enable(struct uniphier_pcie_priv *priv) writel(PCL_RCV_INTX_ALL_ENABLE, priv->base + PCL_RCV_INTX); } -static void uniphier_pcie_irq_ack(struct irq_data *d) -{ - struct pcie_port *pp = irq_data_get_irq_chip_data(d); - struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci); - u32 val; - - val = readl(priv->base + PCL_RCV_INTX); - val &= ~PCL_RCV_INTX_ALL_STATUS; - val |= BIT(irqd_to_hwirq(d) + PCL_RCV_INTX_STATUS_SHIFT); - writel(val, priv->base + PCL_RCV_INTX); -} - static void uniphier_pcie_irq_mask(struct irq_data *d) { struct pcie_port *pp = irq_data_get_irq_chip_data(d); struct dw_pcie *pci = to_dw_pcie_from_pp(pp); struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci); + unsigned long flags; u32 val; + raw_spin_lock_irqsave(&pp->lock, flags); + val = readl(priv->base + PCL_RCV_INTX); - val &= ~PCL_RCV_INTX_ALL_MASK; val |= BIT(irqd_to_hwirq(d) + PCL_RCV_INTX_MASK_SHIFT); writel(val, priv->base + PCL_RCV_INTX); + + raw_spin_unlock_irqrestore(&pp->lock, flags); } static void uniphier_pcie_irq_unmask(struct irq_data *d) @@ -199,17 +190,20 @@ static void uniphier_pcie_irq_unmask(struct irq_data *d) struct pcie_port *pp = irq_data_get_irq_chip_data(d); struct dw_pcie *pci = to_dw_pcie_from_pp(pp); struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci); + unsigned long flags; u32 val; + raw_spin_lock_irqsave(&pp->lock, flags); + val = readl(priv->base + PCL_RCV_INTX); - val &= ~PCL_RCV_INTX_ALL_MASK; val &= ~BIT(irqd_to_hwirq(d) + PCL_RCV_INTX_MASK_SHIFT); writel(val, priv->base + PCL_RCV_INTX); + + raw_spin_unlock_irqrestore(&pp->lock, flags); } static struct irq_chip uniphier_pcie_irq_chip = { .name = "PCI", - .irq_ack = uniphier_pcie_irq_ack, .irq_mask = uniphier_pcie_irq_mask, .irq_unmask = uniphier_pcie_irq_unmask, }; From 9be1446ece291a1f08164bd056bed3d698681f8b Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 29 Sep 2021 00:15:00 +0200 Subject: [PATCH 277/587] mtd: rawnand: fsmc: Fix use of SM ORDER The introduction of the generic ECC engine API lead to a number of changes in various drivers which broke some of them. Here is a typical example: I expected the SM_ORDER option to be handled by the Hamming ECC engine internals. Problem: the fsmc driver does not instantiate (yet) a real ECC engine object so we had to use a 'bare' ECC helper instead of the shiny rawnand functions. However, when not intializing this engine properly and using the bare helpers, we do not get the SM ORDER feature handled automatically. It looks like this was lost in the process so let's ensure we use the right SM ORDER now. Fixes: ad9ffdce4539 ("mtd: rawnand: fsmc: Fix external use of SW Hamming ECC helper") Cc: stable@vger.kernel.org Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210928221507.199198-2-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/fsmc_nand.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c index a3e66155ae40..658f0cbe7ce8 100644 --- a/drivers/mtd/nand/raw/fsmc_nand.c +++ b/drivers/mtd/nand/raw/fsmc_nand.c @@ -438,8 +438,10 @@ static int fsmc_correct_ecc1(struct nand_chip *chip, unsigned char *read_ecc, unsigned char *calc_ecc) { + bool sm_order = chip->ecc.options & NAND_ECC_SOFT_HAMMING_SM_ORDER; + return ecc_sw_hamming_correct(buf, read_ecc, calc_ecc, - chip->ecc.size, false); + chip->ecc.size, sm_order); } /* Count the number of 0's in buff upto a max of max_bits */ From d8467112d645ec56760c78928e1e5a3f6faa9b74 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 29 Sep 2021 00:15:01 +0200 Subject: [PATCH 278/587] mtd: rawnand: Let callers use the bare Hamming helpers Before the introduction of the ECC framework infrastructure, many drivers used the ->calculate/correct() Hamming helpers directly. The point of this framework was to avoid this kind of hackish calls and use a proper and generic API but it is true that in certain cases, drivers still need to use these helpers in order to do ECC computations on behalf of their limited hardware. Right after the introduction of the ECC engine core introduction, it was spotted that it was not possible to use the shiny rawnand software ECC helpers so easily because an ECC engine object should have been allocated and initialized first. While this works well in most cases, for these drivers just leveraging the power of a single helper in conjunction with some pretty old and limited hardware, it did not fit. The idea back then was to declare intermediate helpers which would make use of the exported software ECC engine bare functions while keeping the rawnand layer compatibility. As there was already functions with the rawnand_sw_hamming_ prefix it was decided to declare new local helpers for this purpose in each driver needing one. Besides being far from optimal, this design choice was blamed by Linus when he pulled the "fixes" pull request [1] so that is why now it is time to clean this mess up. Enhancing the implementation of the rawnand_ecc_sw_* helpers to support both cases, when the ECC object is instantiated and when it is not is a quite elegant way to solve this situation. This way, we can still use the existing and exported rawnand helpers while avoiding the need for each driver to declare its own helper. Following this change, most of the fixes sent in [2] can now be safely reverted. Only the fsmc fix will need to be kept because there is actually something specific to the driver to do in its ->correct() helper. [1] https://lore.kernel.org/lkml/CAHk-=wh_ZHF685Fni8V9is17mj=pFisUaZ_0=gq6nbK+ZcyQmg@mail.gmail.com/ [2] https://lore.kernel.org/linux-mtd/20210413161840.345208-1-miquel.raynal@bootlin.com/ Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210928221507.199198-3-miquel.raynal@bootlin.com --- drivers/mtd/nand/ecc-sw-hamming.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/mtd/nand/ecc-sw-hamming.c b/drivers/mtd/nand/ecc-sw-hamming.c index a7655b668f32..254db2e7f8bb 100644 --- a/drivers/mtd/nand/ecc-sw-hamming.c +++ b/drivers/mtd/nand/ecc-sw-hamming.c @@ -364,9 +364,9 @@ int nand_ecc_sw_hamming_calculate(struct nand_device *nand, { struct nand_ecc_sw_hamming_conf *engine_conf = nand->ecc.ctx.priv; unsigned int step_size = nand->ecc.ctx.conf.step_size; + bool sm_order = engine_conf ? engine_conf->sm_order : false; - return ecc_sw_hamming_calculate(buf, step_size, code, - engine_conf->sm_order); + return ecc_sw_hamming_calculate(buf, step_size, code, sm_order); } EXPORT_SYMBOL(nand_ecc_sw_hamming_calculate); @@ -457,9 +457,10 @@ int nand_ecc_sw_hamming_correct(struct nand_device *nand, unsigned char *buf, { struct nand_ecc_sw_hamming_conf *engine_conf = nand->ecc.ctx.priv; unsigned int step_size = nand->ecc.ctx.conf.step_size; + bool sm_order = engine_conf ? engine_conf->sm_order : false; return ecc_sw_hamming_correct(buf, read_ecc, calc_ecc, step_size, - engine_conf->sm_order); + sm_order); } EXPORT_SYMBOL(nand_ecc_sw_hamming_correct); From e7f466c51ce9179a7b5105f93fdb3e85ef6b61ce Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 29 Sep 2021 00:15:02 +0200 Subject: [PATCH 279/587] Revert "mtd: rawnand: txx9ndfmc: Fix external use of SW Hamming ECC helper" This reverts commit 3d227a0b0ce319edbff6fd0d8af4d66689e477cc. Before the introduction of the ECC framework infrastructure, many drivers used the ->calculate/correct() Hamming helpers directly. The point of this framework was to avoid this kind of hackish calls and use a proper and generic API but it is true that in certain cases, drivers still need to use these helpers in order to do ECC computations on behalf of their limited hardware. Right after the introduction of the ECC engine core introduction, it was spotted that it was not possible to use the shiny rawnand software ECC helpers so easily because an ECC engine object should have been allocated and initialized first. While this works well in most cases, for these drivers just leveraging the power of a single helper in conjunction with some pretty old and limited hardware, it did not fit. The idea back then was to declare intermediate helpers which would make use of the exported software ECC engine bare functions while keeping the rawnand layer compatibility. As there was already functions with the rawnand_sw_hamming_ prefix it was decided to declare new local helpers for this purpose in each driver needing one. Besides being far from optimal, this design choice was blamed by Linus when he pulled the "fixes" pull request [1] so that is why now it is time to clean this mess up. The implementation of the rawnand_ecc_sw_* helpers has now been enhanced to support both cases, when the ECC object is instantiated and when it is not. This way, we can still use the existing and exported rawnand helpers while avoiding the need for each driver to declare its own helper, thus this fix from [2] can now be safely reverted. [1] https://lore.kernel.org/lkml/CAHk-=wh_ZHF685Fni8V9is17mj=pFisUaZ_0=gq6nbK+ZcyQmg@mail.gmail.com/ [2] https://lore.kernel.org/linux-mtd/20210413161840.345208-1-miquel.raynal@bootlin.com Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210928221507.199198-4-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/txx9ndfmc.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/txx9ndfmc.c b/drivers/mtd/nand/raw/txx9ndfmc.c index b42d61b30c0b..eddcc0728a67 100644 --- a/drivers/mtd/nand/raw/txx9ndfmc.c +++ b/drivers/mtd/nand/raw/txx9ndfmc.c @@ -13,7 +13,6 @@ #include #include #include -#include #include #include #include @@ -194,8 +193,8 @@ static int txx9ndfmc_correct_data(struct nand_chip *chip, unsigned char *buf, int stat; for (eccsize = chip->ecc.size; eccsize > 0; eccsize -= 256) { - stat = ecc_sw_hamming_correct(buf, read_ecc, calc_ecc, - chip->ecc.size, false); + stat = rawnand_sw_hamming_correct(chip, buf, read_ecc, + calc_ecc); if (stat < 0) return stat; corrected += stat; From 048fbdd599101074285d605936a70a21632da9a4 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 29 Sep 2021 00:15:03 +0200 Subject: [PATCH 280/587] Revert "mtd: rawnand: tmio: Fix external use of SW Hamming ECC helper" This reverts commit 6a4c5ada577467a5f79e06f2c5e69c09983c22fb. Before the introduction of the ECC framework infrastructure, many drivers used the ->calculate/correct() Hamming helpers directly. The point of this framework was to avoid this kind of hackish calls and use a proper and generic API but it is true that in certain cases, drivers still need to use these helpers in order to do ECC computations on behalf of their limited hardware. Right after the introduction of the ECC engine core introduction, it was spotted that it was not possible to use the shiny rawnand software ECC helpers so easily because an ECC engine object should have been allocated and initialized first. While this works well in most cases, for these drivers just leveraging the power of a single helper in conjunction with some pretty old and limited hardware, it did not fit. The idea back then was to declare intermediate helpers which would make use of the exported software ECC engine bare functions while keeping the rawnand layer compatibility. As there was already functions with the rawnand_sw_hamming_ prefix it was decided to declare new local helpers for this purpose in each driver needing one. Besides being far from optimal, this design choice was blamed by Linus when he pulled the "fixes" pull request [1] so that is why now it is time to clean this mess up. The implementation of the rawnand_ecc_sw_* helpers has now been enhanced to support both cases, when the ECC object is instantiated and when it is not. This way, we can still use the existing and exported rawnand helpers while avoiding the need for each driver to declare its own helper, thus this fix from [2] can now be safely reverted. [1] https://lore.kernel.org/lkml/CAHk-=wh_ZHF685Fni8V9is17mj=pFisUaZ_0=gq6nbK+ZcyQmg@mail.gmail.com/ [2] https://lore.kernel.org/linux-mtd/20210413161840.345208-1-miquel.raynal@bootlin.com Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210928221507.199198-5-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/tmio_nand.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/mtd/nand/raw/tmio_nand.c b/drivers/mtd/nand/raw/tmio_nand.c index 6d93dd31969b..de8e919d0ebe 100644 --- a/drivers/mtd/nand/raw/tmio_nand.c +++ b/drivers/mtd/nand/raw/tmio_nand.c @@ -34,7 +34,6 @@ #include #include #include -#include #include #include #include @@ -293,12 +292,11 @@ static int tmio_nand_correct_data(struct nand_chip *chip, unsigned char *buf, int r0, r1; /* assume ecc.size = 512 and ecc.bytes = 6 */ - r0 = ecc_sw_hamming_correct(buf, read_ecc, calc_ecc, - chip->ecc.size, false); + r0 = rawnand_sw_hamming_correct(chip, buf, read_ecc, calc_ecc); if (r0 < 0) return r0; - r1 = ecc_sw_hamming_correct(buf + 256, read_ecc + 3, calc_ecc + 3, - chip->ecc.size, false); + r1 = rawnand_sw_hamming_correct(chip, buf + 256, read_ecc + 3, + calc_ecc + 3); if (r1 < 0) return r1; return r0 + r1; From 1d5f55634c92f3b4f01ed6b390ca2ffe3461250c Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 29 Sep 2021 00:15:04 +0200 Subject: [PATCH 281/587] Revert "mtd: rawnand: sharpsl: Fix external use of SW Hamming ECC helper" This reverts commit 46fcb57e6b7283533ebf8ba17a6bd30fa88bdc9f. Before the introduction of the ECC framework infrastructure, many drivers used the ->calculate/correct() Hamming helpers directly. The point of this framework was to avoid this kind of hackish calls and use a proper and generic API but it is true that in certain cases, drivers still need to use these helpers in order to do ECC computations on behalf of their limited hardware. Right after the introduction of the ECC engine core introduction, it was spotted that it was not possible to use the shiny rawnand software ECC helpers so easily because an ECC engine object should have been allocated and initialized first. While this works well in most cases, for these drivers just leveraging the power of a single helper in conjunction with some pretty old and limited hardware, it did not fit. The idea back then was to declare intermediate helpers which would make use of the exported software ECC engine bare functions while keeping the rawnand layer compatibility. As there was already functions with the rawnand_sw_hamming_ prefix it was decided to declare new local helpers for this purpose in each driver needing one. Besides being far from optimal, this design choice was blamed by Linus when he pulled the "fixes" pull request [1] so that is why now it is time to clean this mess up. The implementation of the rawnand_ecc_sw_* helpers has now been enhanced to support both cases, when the ECC object is instantiated and when it is not. This way, we can still use the existing and exported rawnand helpers while avoiding the need for each driver to declare its own helper, thus this fix from [2] can now be safely reverted. [1] https://lore.kernel.org/lkml/CAHk-=wh_ZHF685Fni8V9is17mj=pFisUaZ_0=gq6nbK+ZcyQmg@mail.gmail.com/ [2] https://lore.kernel.org/linux-mtd/20210413161840.345208-1-miquel.raynal@bootlin.com Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210928221507.199198-6-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/sharpsl.c | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) diff --git a/drivers/mtd/nand/raw/sharpsl.c b/drivers/mtd/nand/raw/sharpsl.c index 2f1fe464e663..5612ee628425 100644 --- a/drivers/mtd/nand/raw/sharpsl.c +++ b/drivers/mtd/nand/raw/sharpsl.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include @@ -97,15 +96,6 @@ static int sharpsl_nand_calculate_ecc(struct nand_chip *chip, return readb(sharpsl->io + ECCCNTR) != 0; } -static int sharpsl_nand_correct_ecc(struct nand_chip *chip, - unsigned char *buf, - unsigned char *read_ecc, - unsigned char *calc_ecc) -{ - return ecc_sw_hamming_correct(buf, read_ecc, calc_ecc, - chip->ecc.size, false); -} - static int sharpsl_attach_chip(struct nand_chip *chip) { if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST) @@ -116,7 +106,7 @@ static int sharpsl_attach_chip(struct nand_chip *chip) chip->ecc.strength = 1; chip->ecc.hwctl = sharpsl_nand_enable_hwecc; chip->ecc.calculate = sharpsl_nand_calculate_ecc; - chip->ecc.correct = sharpsl_nand_correct_ecc; + chip->ecc.correct = rawnand_sw_hamming_correct; return 0; } From 8d1e4218a63e96acd593395d6a8a4cf6095d7457 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 29 Sep 2021 00:15:05 +0200 Subject: [PATCH 282/587] Revert "mtd: rawnand: ndfc: Fix external use of SW Hamming ECC helper" This reverts commit 3e09c0252501829b14b10f14e1982aaab77d0b80. Before the introduction of the ECC framework infrastructure, many drivers used the ->calculate/correct() Hamming helpers directly. The point of this framework was to avoid this kind of hackish calls and use a proper and generic API but it is true that in certain cases, drivers still need to use these helpers in order to do ECC computations on behalf of their limited hardware. Right after the introduction of the ECC engine core introduction, it was spotted that it was not possible to use the shiny rawnand software ECC helpers so easily because an ECC engine object should have been allocated and initialized first. While this works well in most cases, for these drivers just leveraging the power of a single helper in conjunction with some pretty old and limited hardware, it did not fit. The idea back then was to declare intermediate helpers which would make use of the exported software ECC engine bare functions while keeping the rawnand layer compatibility. As there was already functions with the rawnand_sw_hamming_ prefix it was decided to declare new local helpers for this purpose in each driver needing one. Besides being far from optimal, this design choice was blamed by Linus when he pulled the "fixes" pull request [1] so that is why now it is time to clean this mess up. The implementation of the rawnand_ecc_sw_* helpers has now been enhanced to support both cases, when the ECC object is instantiated and when it is not. This way, we can still use the existing and exported rawnand helpers while avoiding the need for each driver to declare its own helper, thus this fix from [2] can now be safely reverted. [1] https://lore.kernel.org/lkml/CAHk-=wh_ZHF685Fni8V9is17mj=pFisUaZ_0=gq6nbK+ZcyQmg@mail.gmail.com/ [2] https://lore.kernel.org/linux-mtd/20210413161840.345208-1-miquel.raynal@bootlin.com Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210928221507.199198-7-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/ndfc.c | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) diff --git a/drivers/mtd/nand/raw/ndfc.c b/drivers/mtd/nand/raw/ndfc.c index 98d5a94c3a24..338d6b1a189e 100644 --- a/drivers/mtd/nand/raw/ndfc.c +++ b/drivers/mtd/nand/raw/ndfc.c @@ -22,7 +22,6 @@ #include #include #include -#include #include #include #include @@ -101,15 +100,6 @@ static int ndfc_calculate_ecc(struct nand_chip *chip, return 0; } -static int ndfc_correct_ecc(struct nand_chip *chip, - unsigned char *buf, - unsigned char *read_ecc, - unsigned char *calc_ecc) -{ - return ecc_sw_hamming_correct(buf, read_ecc, calc_ecc, - chip->ecc.size, false); -} - /* * Speedups for buffer read/write/verify * @@ -155,7 +145,7 @@ static int ndfc_chip_init(struct ndfc_controller *ndfc, chip->controller = &ndfc->ndfc_control; chip->legacy.read_buf = ndfc_read_buf; chip->legacy.write_buf = ndfc_write_buf; - chip->ecc.correct = ndfc_correct_ecc; + chip->ecc.correct = rawnand_sw_hamming_correct; chip->ecc.hwctl = ndfc_enable_hwecc; chip->ecc.calculate = ndfc_calculate_ecc; chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; From fe972c458fc561113671dde6bd10198cc7719910 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 29 Sep 2021 00:15:06 +0200 Subject: [PATCH 283/587] Revert "mtd: rawnand: lpc32xx_slc: Fix external use of SW Hamming ECC helper" This reverts commit c4b7d7c480d607e4f52d310d9d16b194868d0917. Before the introduction of the ECC framework infrastructure, many drivers used the ->calculate/correct() Hamming helpers directly. The point of this framework was to avoid this kind of hackish calls and use a proper and generic API but it is true that in certain cases, drivers still need to use these helpers in order to do ECC computations on behalf of their limited hardware. Right after the introduction of the ECC engine core introduction, it was spotted that it was not possible to use the shiny rawnand software ECC helpers so easily because an ECC engine object should have been allocated and initialized first. While this works well in most cases, for these drivers just leveraging the power of a single helper in conjunction with some pretty old and limited hardware, it did not fit. The idea back then was to declare intermediate helpers which would make use of the exported software ECC engine bare functions while keeping the rawnand layer compatibility. As there was already functions with the rawnand_sw_hamming_ prefix it was decided to declare new local helpers for this purpose in each driver needing one. Besides being far from optimal, this design choice was blamed by Linus when he pulled the "fixes" pull request [1] so that is why now it is time to clean this mess up. The implementation of the rawnand_ecc_sw_* helpers has now been enhanced to support both cases, when the ECC object is instantiated and when it is not. This way, we can still use the existing and exported rawnand helpers while avoiding the need for each driver to declare its own helper, thus this fix from [2] can now be safely reverted. [1] https://lore.kernel.org/lkml/CAHk-=wh_ZHF685Fni8V9is17mj=pFisUaZ_0=gq6nbK+ZcyQmg@mail.gmail.com/ [2] https://lore.kernel.org/linux-mtd/20210413161840.345208-1-miquel.raynal@bootlin.com Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210928221507.199198-8-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/lpc32xx_slc.c | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) diff --git a/drivers/mtd/nand/raw/lpc32xx_slc.c b/drivers/mtd/nand/raw/lpc32xx_slc.c index d7dfc6fd85ca..6b7269cfb7d8 100644 --- a/drivers/mtd/nand/raw/lpc32xx_slc.c +++ b/drivers/mtd/nand/raw/lpc32xx_slc.c @@ -27,7 +27,6 @@ #include #include #include -#include #define LPC32XX_MODNAME "lpc32xx-nand" @@ -345,18 +344,6 @@ static int lpc32xx_nand_ecc_calculate(struct nand_chip *chip, return 0; } -/* - * Corrects the data - */ -static int lpc32xx_nand_ecc_correct(struct nand_chip *chip, - unsigned char *buf, - unsigned char *read_ecc, - unsigned char *calc_ecc) -{ - return ecc_sw_hamming_correct(buf, read_ecc, calc_ecc, - chip->ecc.size, false); -} - /* * Read a single byte from NAND device */ @@ -815,7 +802,7 @@ static int lpc32xx_nand_attach_chip(struct nand_chip *chip) chip->ecc.write_oob = lpc32xx_nand_write_oob_syndrome; chip->ecc.read_oob = lpc32xx_nand_read_oob_syndrome; chip->ecc.calculate = lpc32xx_nand_ecc_calculate; - chip->ecc.correct = lpc32xx_nand_ecc_correct; + chip->ecc.correct = rawnand_sw_hamming_correct; chip->ecc.hwctl = lpc32xx_nand_ecc_enable; /* From c625823ad8c095afb9601e06ea9fba07c865f378 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 29 Sep 2021 00:15:07 +0200 Subject: [PATCH 284/587] Revert "mtd: rawnand: cs553x: Fix external use of SW Hamming ECC helper" This reverts commit 56a8d3fd1f342d10ee7b27e9ac0f4d00b5fbb91c. Before the introduction of the ECC framework infrastructure, many drivers used the ->calculate/correct() Hamming helpers directly. The point of this framework was to avoid this kind of hackish calls and use a proper and generic API but it is true that in certain cases, drivers still need to use these helpers in order to do ECC computations on behalf of their limited hardware. Right after the introduction of the ECC engine core introduction, it was spotted that it was not possible to use the shiny rawnand software ECC helpers so easily because an ECC engine object should have been allocated and initialized first. While this works well in most cases, for these drivers just leveraging the power of a single helper in conjunction with some pretty old and limited hardware, it did not fit. The idea back then was to declare intermediate helpers which would make use of the exported software ECC engine bare functions while keeping the rawnand layer compatibility. As there was already functions with the rawnand_sw_hamming_ prefix it was decided to declare new local helpers for this purpose in each driver needing one. Besides being far from optimal, this design choice was blamed by Linus when he pulled the "fixes" pull request [1] so that is why now it is time to clean this mess up. The implementation of the rawnand_ecc_sw_* helpers has now been enhanced to support both cases, when the ECC object is instantiated and when it is not. This way, we can still use the existing and exported rawnand helpers while avoiding the need for each driver to declare its own helper, thus this fix from [2] can now be safely reverted. [1] https://lore.kernel.org/lkml/CAHk-=wh_ZHF685Fni8V9is17mj=pFisUaZ_0=gq6nbK+ZcyQmg@mail.gmail.com/ [2] https://lore.kernel.org/linux-mtd/20210413161840.345208-1-miquel.raynal@bootlin.com Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210928221507.199198-9-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/cs553x_nand.c | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) diff --git a/drivers/mtd/nand/raw/cs553x_nand.c b/drivers/mtd/nand/raw/cs553x_nand.c index df40927e5678..6edf78c16fc8 100644 --- a/drivers/mtd/nand/raw/cs553x_nand.c +++ b/drivers/mtd/nand/raw/cs553x_nand.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include @@ -241,15 +240,6 @@ static int cs_calculate_ecc(struct nand_chip *this, const u_char *dat, return 0; } -static int cs553x_ecc_correct(struct nand_chip *chip, - unsigned char *buf, - unsigned char *read_ecc, - unsigned char *calc_ecc) -{ - return ecc_sw_hamming_correct(buf, read_ecc, calc_ecc, - chip->ecc.size, false); -} - static struct cs553x_nand_controller *controllers[4]; static int cs553x_attach_chip(struct nand_chip *chip) @@ -261,7 +251,7 @@ static int cs553x_attach_chip(struct nand_chip *chip) chip->ecc.bytes = 3; chip->ecc.hwctl = cs_enable_hwecc; chip->ecc.calculate = cs_calculate_ecc; - chip->ecc.correct = cs553x_ecc_correct; + chip->ecc.correct = rawnand_sw_hamming_correct; chip->ecc.strength = 1; return 0; From d707bb74daae07879e0fc1b4b960f8f2d0a5fe5d Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 29 Sep 2021 00:22:40 +0200 Subject: [PATCH 285/587] mtd: rawnand: ams-delta: Keep the driver compatible with on-die ECC engines Following the introduction of the generic ECC engine infrastructure, it was necessary to reorganize the code and move the ECC configuration in the ->attach_chip() hook. Failing to do that properly lead to a first series of fixes supposed to stabilize the situation. Unfortunately, this only fixed the use of software ECC engines, preventing any other kind of engine to be used, including on-die ones. It is now time to (finally) fix the situation by ensuring that we still provide a default (eg. software ECC) but will still support different ECC engines such as on-die ECC engines if properly described in the device tree. There are no changes needed on the core side in order to do this, but we just need to leverage the logic there which allows: 1- a subsystem default (set to Host engines in the raw NAND world) 2- a driver specific default (here set to software ECC engines) 3- any type of engine requested by the user (ie. described in the DT) As the raw NAND subsystem has not yet been fully converted to the ECC engine infrastructure, in order to provide a default ECC engine for this driver we need to set chip->ecc.engine_type *before* calling nand_scan(). During the initialization step, the core will consider this entry as the default engine for this driver. This value may of course be overloaded by the user if the usual DT properties are provided. Fixes: 59d93473323a ("mtd: rawnand: ams-delta: Move the ECC initialization to ->attach_chip()") Cc: stable@vger.kernel.org Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210928222258.199726-2-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/ams-delta.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/ams-delta.c b/drivers/mtd/nand/raw/ams-delta.c index ff1697f899ba..13de39aa3288 100644 --- a/drivers/mtd/nand/raw/ams-delta.c +++ b/drivers/mtd/nand/raw/ams-delta.c @@ -217,9 +217,8 @@ static int gpio_nand_setup_interface(struct nand_chip *this, int csline, static int gpio_nand_attach_chip(struct nand_chip *chip) { - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - - if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) + if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_SOFT && + chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) chip->ecc.algo = NAND_ECC_ALGO_HAMMING; return 0; @@ -370,6 +369,13 @@ static int gpio_nand_probe(struct platform_device *pdev) /* Release write protection */ gpiod_set_value(priv->gpiod_nwp, 0); + /* + * This driver assumes that the default ECC engine should be TYPE_SOFT. + * Set ->engine_type before registering the NAND devices in order to + * provide a driver specific default value. + */ + this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + /* Scan to find existence of the device */ err = nand_scan(this, 1); if (err) From 7e3cdba176ba59eaf4d463d273da0718e3626140 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 29 Sep 2021 00:22:41 +0200 Subject: [PATCH 286/587] mtd: rawnand: au1550nd: Keep the driver compatible with on-die ECC engines Following the introduction of the generic ECC engine infrastructure, it was necessary to reorganize the code and move the ECC configuration in the ->attach_chip() hook. Failing to do that properly lead to a first series of fixes supposed to stabilize the situation. Unfortunately, this only fixed the use of software ECC engines, preventing any other kind of engine to be used, including on-die ones. It is now time to (finally) fix the situation by ensuring that we still provide a default (eg. software ECC) but will still support different ECC engines such as on-die ECC engines if properly described in the device tree. There are no changes needed on the core side in order to do this, but we just need to leverage the logic there which allows: 1- a subsystem default (set to Host engines in the raw NAND world) 2- a driver specific default (here set to software ECC engines) 3- any type of engine requested by the user (ie. described in the DT) As the raw NAND subsystem has not yet been fully converted to the ECC engine infrastructure, in order to provide a default ECC engine for this driver we need to set chip->ecc.engine_type *before* calling nand_scan(). During the initialization step, the core will consider this entry as the default engine for this driver. This value may of course be overloaded by the user if the usual DT properties are provided. Fixes: dbffc8ccdf3a ("mtd: rawnand: au1550: Move the ECC initialization to ->attach_chip()") Cc: stable@vger.kernel.org Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210928222258.199726-3-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/au1550nd.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/au1550nd.c b/drivers/mtd/nand/raw/au1550nd.c index 99116896cfd6..5aa3a06d740c 100644 --- a/drivers/mtd/nand/raw/au1550nd.c +++ b/drivers/mtd/nand/raw/au1550nd.c @@ -239,9 +239,8 @@ static int au1550nd_exec_op(struct nand_chip *this, static int au1550nd_attach_chip(struct nand_chip *chip) { - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - - if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) + if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_SOFT && + chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) chip->ecc.algo = NAND_ECC_ALGO_HAMMING; return 0; @@ -310,6 +309,13 @@ static int au1550nd_probe(struct platform_device *pdev) if (pd->devwidth) this->options |= NAND_BUSWIDTH_16; + /* + * This driver assumes that the default ECC engine should be TYPE_SOFT. + * Set ->engine_type before registering the NAND devices in order to + * provide a driver specific default value. + */ + this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + ret = nand_scan(this, 1); if (ret) { dev_err(&pdev->dev, "NAND scan failed with %d\n", ret); From b5b5b4dc6fcd8194b9dd38c8acdc5ab71adf44f8 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 29 Sep 2021 00:22:42 +0200 Subject: [PATCH 287/587] mtd: rawnand: gpio: Keep the driver compatible with on-die ECC engines Following the introduction of the generic ECC engine infrastructure, it was necessary to reorganize the code and move the ECC configuration in the ->attach_chip() hook. Failing to do that properly lead to a first series of fixes supposed to stabilize the situation. Unfortunately, this only fixed the use of software ECC engines, preventing any other kind of engine to be used, including on-die ones. It is now time to (finally) fix the situation by ensuring that we still provide a default (eg. software ECC) but will still support different ECC engines such as on-die ECC engines if properly described in the device tree. There are no changes needed on the core side in order to do this, but we just need to leverage the logic there which allows: 1- a subsystem default (set to Host engines in the raw NAND world) 2- a driver specific default (here set to software ECC engines) 3- any type of engine requested by the user (ie. described in the DT) As the raw NAND subsystem has not yet been fully converted to the ECC engine infrastructure, in order to provide a default ECC engine for this driver we need to set chip->ecc.engine_type *before* calling nand_scan(). During the initialization step, the core will consider this entry as the default engine for this driver. This value may of course be overloaded by the user if the usual DT properties are provided. Fixes: f6341f6448e0 ("mtd: rawnand: gpio: Move the ECC initialization to ->attach_chip()") Cc: stable@vger.kernel.org Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210928222258.199726-4-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/gpio.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/gpio.c b/drivers/mtd/nand/raw/gpio.c index 8901c4aa0c21..dcf28cff760d 100644 --- a/drivers/mtd/nand/raw/gpio.c +++ b/drivers/mtd/nand/raw/gpio.c @@ -163,9 +163,8 @@ static int gpio_nand_exec_op(struct nand_chip *chip, static int gpio_nand_attach_chip(struct nand_chip *chip) { - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - - if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) + if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_SOFT && + chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) chip->ecc.algo = NAND_ECC_ALGO_HAMMING; return 0; @@ -364,6 +363,13 @@ static int gpio_nand_probe(struct platform_device *pdev) if (gpiomtd->nwp && !IS_ERR(gpiomtd->nwp)) gpiod_direction_output(gpiomtd->nwp, 1); + /* + * This driver assumes that the default ECC engine should be TYPE_SOFT. + * Set ->engine_type before registering the NAND devices in order to + * provide a driver specific default value. + */ + chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + ret = nand_scan(chip, 1); if (ret) goto err_wp; From f9d8570b7fd6f4f08528ce2f5e39787a8a260cd6 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 29 Sep 2021 00:22:43 +0200 Subject: [PATCH 288/587] mtd: rawnand: mpc5121: Keep the driver compatible with on-die ECC engines Following the introduction of the generic ECC engine infrastructure, it was necessary to reorganize the code and move the ECC configuration in the ->attach_chip() hook. Failing to do that properly lead to a first series of fixes supposed to stabilize the situation. Unfortunately, this only fixed the use of software ECC engines, preventing any other kind of engine to be used, including on-die ones. It is now time to (finally) fix the situation by ensuring that we still provide a default (eg. software ECC) but will still support different ECC engines such as on-die ECC engines if properly described in the device tree. There are no changes needed on the core side in order to do this, but we just need to leverage the logic there which allows: 1- a subsystem default (set to Host engines in the raw NAND world) 2- a driver specific default (here set to software ECC engines) 3- any type of engine requested by the user (ie. described in the DT) As the raw NAND subsystem has not yet been fully converted to the ECC engine infrastructure, in order to provide a default ECC engine for this driver we need to set chip->ecc.engine_type *before* calling nand_scan(). During the initialization step, the core will consider this entry as the default engine for this driver. This value may of course be overloaded by the user if the usual DT properties are provided. Fixes: 6dd09f775b72 ("mtd: rawnand: mpc5121: Move the ECC initialization to ->attach_chip()") Cc: stable@vger.kernel.org Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210928222258.199726-5-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/mpc5121_nfc.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/mpc5121_nfc.c b/drivers/mtd/nand/raw/mpc5121_nfc.c index bcd4a556c959..cb293c50acb8 100644 --- a/drivers/mtd/nand/raw/mpc5121_nfc.c +++ b/drivers/mtd/nand/raw/mpc5121_nfc.c @@ -605,9 +605,8 @@ static void mpc5121_nfc_free(struct device *dev, struct mtd_info *mtd) static int mpc5121_nfc_attach_chip(struct nand_chip *chip) { - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - - if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) + if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_SOFT && + chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) chip->ecc.algo = NAND_ECC_ALGO_HAMMING; return 0; @@ -772,6 +771,13 @@ static int mpc5121_nfc_probe(struct platform_device *op) goto error; } + /* + * This driver assumes that the default ECC engine should be TYPE_SOFT. + * Set ->engine_type before registering the NAND devices in order to + * provide a driver specific default value. + */ + chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + /* Detect NAND chips */ retval = nand_scan(chip, be32_to_cpup(chips_no)); if (retval) { From 194ac63de6ff56d30c48e3ac19c8a412f9c1408e Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 29 Sep 2021 00:22:44 +0200 Subject: [PATCH 289/587] mtd: rawnand: orion: Keep the driver compatible with on-die ECC engines Following the introduction of the generic ECC engine infrastructure, it was necessary to reorganize the code and move the ECC configuration in the ->attach_chip() hook. Failing to do that properly lead to a first series of fixes supposed to stabilize the situation. Unfortunately, this only fixed the use of software ECC engines, preventing any other kind of engine to be used, including on-die ones. It is now time to (finally) fix the situation by ensuring that we still provide a default (eg. software ECC) but will still support different ECC engines such as on-die ECC engines if properly described in the device tree. There are no changes needed on the core side in order to do this, but we just need to leverage the logic there which allows: 1- a subsystem default (set to Host engines in the raw NAND world) 2- a driver specific default (here set to software ECC engines) 3- any type of engine requested by the user (ie. described in the DT) As the raw NAND subsystem has not yet been fully converted to the ECC engine infrastructure, in order to provide a default ECC engine for this driver we need to set chip->ecc.engine_type *before* calling nand_scan(). During the initialization step, the core will consider this entry as the default engine for this driver. This value may of course be overloaded by the user if the usual DT properties are provided. Fixes: 553508cec2e8 ("mtd: rawnand: orion: Move the ECC initialization to ->attach_chip()") Cc: stable@vger.kernel.org Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210928222258.199726-6-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/orion_nand.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/orion_nand.c b/drivers/mtd/nand/raw/orion_nand.c index 66211c9311d2..2c87c7d89205 100644 --- a/drivers/mtd/nand/raw/orion_nand.c +++ b/drivers/mtd/nand/raw/orion_nand.c @@ -85,9 +85,8 @@ static void orion_nand_read_buf(struct nand_chip *chip, uint8_t *buf, int len) static int orion_nand_attach_chip(struct nand_chip *chip) { - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - - if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) + if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_SOFT && + chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) chip->ecc.algo = NAND_ECC_ALGO_HAMMING; return 0; @@ -190,6 +189,13 @@ static int __init orion_nand_probe(struct platform_device *pdev) return ret; } + /* + * This driver assumes that the default ECC engine should be TYPE_SOFT. + * Set ->engine_type before registering the NAND devices in order to + * provide a driver specific default value. + */ + nc->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + ret = nand_scan(nc, 1); if (ret) goto no_dev; From f16b7d2a5e810fcf4b15d096246d0d445da9cc88 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 29 Sep 2021 00:22:45 +0200 Subject: [PATCH 290/587] mtd: rawnand: pasemi: Keep the driver compatible with on-die ECC engines Following the introduction of the generic ECC engine infrastructure, it was necessary to reorganize the code and move the ECC configuration in the ->attach_chip() hook. Failing to do that properly lead to a first series of fixes supposed to stabilize the situation. Unfortunately, this only fixed the use of software ECC engines, preventing any other kind of engine to be used, including on-die ones. It is now time to (finally) fix the situation by ensuring that we still provide a default (eg. software ECC) but will still support different ECC engines such as on-die ECC engines if properly described in the device tree. There are no changes needed on the core side in order to do this, but we just need to leverage the logic there which allows: 1- a subsystem default (set to Host engines in the raw NAND world) 2- a driver specific default (here set to software ECC engines) 3- any type of engine requested by the user (ie. described in the DT) As the raw NAND subsystem has not yet been fully converted to the ECC engine infrastructure, in order to provide a default ECC engine for this driver we need to set chip->ecc.engine_type *before* calling nand_scan(). During the initialization step, the core will consider this entry as the default engine for this driver. This value may of course be overloaded by the user if the usual DT properties are provided. Fixes: 8fc6f1f042b2 ("mtd: rawnand: pasemi: Move the ECC initialization to ->attach_chip()") Cc: stable@vger.kernel.org Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210928222258.199726-7-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/pasemi_nand.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/pasemi_nand.c b/drivers/mtd/nand/raw/pasemi_nand.c index 789f33312c15..c176036453ed 100644 --- a/drivers/mtd/nand/raw/pasemi_nand.c +++ b/drivers/mtd/nand/raw/pasemi_nand.c @@ -75,9 +75,8 @@ static int pasemi_device_ready(struct nand_chip *chip) static int pasemi_attach_chip(struct nand_chip *chip) { - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - - if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) + if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_SOFT && + chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) chip->ecc.algo = NAND_ECC_ALGO_HAMMING; return 0; @@ -154,6 +153,13 @@ static int pasemi_nand_probe(struct platform_device *ofdev) /* Enable the following for a flash based bad block table */ chip->bbt_options = NAND_BBT_USE_FLASH; + /* + * This driver assumes that the default ECC engine should be TYPE_SOFT. + * Set ->engine_type before registering the NAND devices in order to + * provide a driver specific default value. + */ + chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + /* Scan to find existence of the device */ err = nand_scan(chip, 1); if (err) From 325fd539fc84f0aaa0ceb9d7d3b8718582473dc5 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 29 Sep 2021 00:22:46 +0200 Subject: [PATCH 291/587] mtd: rawnand: plat_nand: Keep the driver compatible with on-die ECC engines Following the introduction of the generic ECC engine infrastructure, it was necessary to reorganize the code and move the ECC configuration in the ->attach_chip() hook. Failing to do that properly lead to a first series of fixes supposed to stabilize the situation. Unfortunately, this only fixed the use of software ECC engines, preventing any other kind of engine to be used, including on-die ones. It is now time to (finally) fix the situation by ensuring that we still provide a default (eg. software ECC) but will still support different ECC engines such as on-die ECC engines if properly described in the device tree. There are no changes needed on the core side in order to do this, but we just need to leverage the logic there which allows: 1- a subsystem default (set to Host engines in the raw NAND world) 2- a driver specific default (here set to software ECC engines) 3- any type of engine requested by the user (ie. described in the DT) As the raw NAND subsystem has not yet been fully converted to the ECC engine infrastructure, in order to provide a default ECC engine for this driver we need to set chip->ecc.engine_type *before* calling nand_scan(). During the initialization step, the core will consider this entry as the default engine for this driver. This value may of course be overloaded by the user if the usual DT properties are provided. Fixes: 612e048e6aab ("mtd: rawnand: plat_nand: Move the ECC initialization to ->attach_chip()") Cc: stable@vger.kernel.org Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210928222258.199726-8-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/plat_nand.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/plat_nand.c b/drivers/mtd/nand/raw/plat_nand.c index c1b2072cb507..7e0d0a8dfd1e 100644 --- a/drivers/mtd/nand/raw/plat_nand.c +++ b/drivers/mtd/nand/raw/plat_nand.c @@ -21,9 +21,8 @@ struct plat_nand_data { static int plat_nand_attach_chip(struct nand_chip *chip) { - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - - if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) + if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_SOFT && + chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) chip->ecc.algo = NAND_ECC_ALGO_HAMMING; return 0; @@ -92,6 +91,13 @@ static int plat_nand_probe(struct platform_device *pdev) goto out; } + /* + * This driver assumes that the default ECC engine should be TYPE_SOFT. + * Set ->engine_type before registering the NAND devices in order to + * provide a driver specific default value. + */ + data->chip.ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + /* Scan to find existence of the device */ err = nand_scan(&data->chip, pdata->chip.nr_chips); if (err) From b4ebddd6540d78a7f977b3fea0261bd575c6ffe2 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 29 Sep 2021 00:22:47 +0200 Subject: [PATCH 292/587] mtd: rawnand: socrates: Keep the driver compatible with on-die ECC engines Following the introduction of the generic ECC engine infrastructure, it was necessary to reorganize the code and move the ECC configuration in the ->attach_chip() hook. Failing to do that properly lead to a first series of fixes supposed to stabilize the situation. Unfortunately, this only fixed the use of software ECC engines, preventing any other kind of engine to be used, including on-die ones. It is now time to (finally) fix the situation by ensuring that we still provide a default (eg. software ECC) but will still support different ECC engines such as on-die ECC engines if properly described in the device tree. There are no changes needed on the core side in order to do this, but we just need to leverage the logic there which allows: 1- a subsystem default (set to Host engines in the raw NAND world) 2- a driver specific default (here set to software ECC engines) 3- any type of engine requested by the user (ie. described in the DT) As the raw NAND subsystem has not yet been fully converted to the ECC engine infrastructure, in order to provide a default ECC engine for this driver we need to set chip->ecc.engine_type *before* calling nand_scan(). During the initialization step, the core will consider this entry as the default engine for this driver. This value may of course be overloaded by the user if the usual DT properties are provided. Fixes: b36bf0a0fe5d ("mtd: rawnand: socrates: Move the ECC initialization to ->attach_chip()") Cc: stable@vger.kernel.org Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210928222258.199726-9-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/socrates_nand.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/socrates_nand.c b/drivers/mtd/nand/raw/socrates_nand.c index 70f8305c9b6e..fb39cc7ebce0 100644 --- a/drivers/mtd/nand/raw/socrates_nand.c +++ b/drivers/mtd/nand/raw/socrates_nand.c @@ -119,9 +119,8 @@ static int socrates_nand_device_ready(struct nand_chip *nand_chip) static int socrates_attach_chip(struct nand_chip *chip) { - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - - if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) + if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_SOFT && + chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) chip->ecc.algo = NAND_ECC_ALGO_HAMMING; return 0; @@ -175,6 +174,13 @@ static int socrates_nand_probe(struct platform_device *ofdev) /* TODO: I have no idea what real delay is. */ nand_chip->legacy.chip_delay = 20; /* 20us command delay time */ + /* + * This driver assumes that the default ECC engine should be TYPE_SOFT. + * Set ->engine_type before registering the NAND devices in order to + * provide a driver specific default value. + */ + nand_chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + dev_set_drvdata(&ofdev->dev, host); res = nand_scan(nand_chip, 1); From 6bcd2960af1b7bacb2f1e710ab0c0b802d900501 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 29 Sep 2021 00:22:48 +0200 Subject: [PATCH 293/587] mtd: rawnand: xway: Keep the driver compatible with on-die ECC engines Following the introduction of the generic ECC engine infrastructure, it was necessary to reorganize the code and move the ECC configuration in the ->attach_chip() hook. Failing to do that properly lead to a first series of fixes supposed to stabilize the situation. Unfortunately, this only fixed the use of software ECC engines, preventing any other kind of engine to be used, including on-die ones. It is now time to (finally) fix the situation by ensuring that we still provide a default (eg. software ECC) but will still support different ECC engines such as on-die ECC engines if properly described in the device tree. There are no changes needed on the core side in order to do this, but we just need to leverage the logic there which allows: 1- a subsystem default (set to Host engines in the raw NAND world) 2- a driver specific default (here set to software ECC engines) 3- any type of engine requested by the user (ie. described in the DT) As the raw NAND subsystem has not yet been fully converted to the ECC engine infrastructure, in order to provide a default ECC engine for this driver we need to set chip->ecc.engine_type *before* calling nand_scan(). During the initialization step, the core will consider this entry as the default engine for this driver. This value may of course be overloaded by the user if the usual DT properties are provided. Fixes: d525914b5bd8 ("mtd: rawnand: xway: Move the ECC initialization to ->attach_chip()") Cc: stable@vger.kernel.org Cc: Jan Hoffmann Cc: Kestrel seventyfour Signed-off-by: Miquel Raynal Tested-by: Jan Hoffmann Link: https://lore.kernel.org/linux-mtd/20210928222258.199726-10-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/xway_nand.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/xway_nand.c b/drivers/mtd/nand/raw/xway_nand.c index 92067bd55384..035b82aa2f4a 100644 --- a/drivers/mtd/nand/raw/xway_nand.c +++ b/drivers/mtd/nand/raw/xway_nand.c @@ -148,9 +148,8 @@ static void xway_write_buf(struct nand_chip *chip, const u_char *buf, int len) static int xway_attach_chip(struct nand_chip *chip) { - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - - if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) + if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_SOFT && + chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) chip->ecc.algo = NAND_ECC_ALGO_HAMMING; return 0; @@ -217,6 +216,13 @@ static int xway_nand_probe(struct platform_device *pdev) | NAND_CON_SE_P | NAND_CON_WP_P | NAND_CON_PRE_P | cs_flag, EBU_NAND_CON); + /* + * This driver assumes that the default ECC engine should be TYPE_SOFT. + * Set ->engine_type before registering the NAND devices in order to + * provide a driver specific default value. + */ + data->chip.ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + /* Scan to find existence of the device */ err = nand_scan(&data->chip, 1); if (err) From eec417fd317a95a79257c20b3a1d66d4027549df Mon Sep 17 00:00:00 2001 From: Chris Morgan Date: Thu, 30 Sep 2021 11:24:02 -0500 Subject: [PATCH 294/587] mtd: rawnand: hynix: Add support for H27UCG8T2ETR-BC MLC NAND Add support for the H27UCG8T2ETR-BC MLC NAND. The NAND is used widely in the NTC CHIP, is an MLC type NAND, and is 8GB in size. Neither JEDEC nor ONFI detection identifies it correctly, so the ID is added to the nand_ids.c file. Additionally, per the datasheet this NAND appears to use the same paired pages scheme as the Toshiba TC58TEG5DCLTA00 (dist3), so add support for that to enable use in SLC emulation mode. Tested on a NTC CHIP the device is able to write to a ubifs formatted partition, and then have U-Boot (with proposed patches) boot from a kernel located on that ubifs formatted partition. Signed-off-by: Chris Morgan Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210930162402.344-1-macroalpha82@gmail.com --- drivers/mtd/nand/raw/nand_hynix.c | 14 ++++++++++++++ drivers/mtd/nand/raw/nand_ids.c | 4 ++++ 2 files changed, 18 insertions(+) diff --git a/drivers/mtd/nand/raw/nand_hynix.c b/drivers/mtd/nand/raw/nand_hynix.c index a9f50c9af109..0d4d4bbfdece 100644 --- a/drivers/mtd/nand/raw/nand_hynix.c +++ b/drivers/mtd/nand/raw/nand_hynix.c @@ -686,6 +686,16 @@ h27ucg8t2atrbc_choose_interface_config(struct nand_chip *chip, return nand_choose_best_sdr_timings(chip, iface, NULL); } +static int h27ucg8t2etrbc_init(struct nand_chip *chip) +{ + struct mtd_info *mtd = nand_to_mtd(chip); + + chip->options |= NAND_NEED_SCRAMBLING; + mtd_set_pairing_scheme(mtd, &dist3_pairing_scheme); + + return 0; +} + static int hynix_nand_init(struct nand_chip *chip) { struct hynix_nand *hynix; @@ -707,6 +717,10 @@ static int hynix_nand_init(struct nand_chip *chip) chip->ops.choose_interface_config = h27ucg8t2atrbc_choose_interface_config; + if (!strncmp("H27UCG8T2ETR-BC", chip->parameters.model, + sizeof("H27UCG8T2ETR-BC") - 1)) + h27ucg8t2etrbc_init(chip); + ret = hynix_nand_rr_init(chip); if (ret) hynix_nand_cleanup(chip); diff --git a/drivers/mtd/nand/raw/nand_ids.c b/drivers/mtd/nand/raw/nand_ids.c index b9945791a9d7..6e41902be35f 100644 --- a/drivers/mtd/nand/raw/nand_ids.c +++ b/drivers/mtd/nand/raw/nand_ids.c @@ -51,6 +51,10 @@ struct nand_flash_dev nand_flash_ids[] = { { .id = {0xad, 0xde, 0x94, 0xda, 0x74, 0xc4} }, SZ_8K, SZ_8K, SZ_2M, NAND_NEED_SCRAMBLING, 6, 640, NAND_ECC_INFO(40, SZ_1K) }, + {"H27UCG8T2ETR-BC 64G 3.3V 8-bit", + { .id = {0xad, 0xde, 0x14, 0xa7, 0x42, 0x4a} }, + SZ_16K, SZ_8K, SZ_4M, NAND_NEED_SCRAMBLING, 6, 1664, + NAND_ECC_INFO(40, SZ_1K) }, {"TH58NVG2S3HBAI4 4G 3.3V 8-bit", { .id = {0x98, 0xdc, 0x91, 0x15, 0x76} }, SZ_2K, SZ_512, SZ_128K, 0, 5, 128, NAND_ECC_INFO(8, SZ_512) }, From 73e197df1949347bbc1902605b6c7fe8e3b04249 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Mon, 4 Oct 2021 18:09:26 +0530 Subject: [PATCH 295/587] MAINTAINERS: Add entry for Qualcomm NAND controller driver Since I maintain the dt-binding for this controller, I'm stepping forward to maintain the driver also. Signed-off-by: Manivannan Sadhasivam Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20211004123926.53462-1-manivannan.sadhasivam@linaro.org --- MAINTAINERS | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index eeb4c70b3d5b..f4c590b22636 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15572,6 +15572,14 @@ S: Maintained F: Documentation/devicetree/bindings/regulator/vqmmc-ipq4019-regulator.yaml F: drivers/regulator/vqmmc-ipq4019-regulator.c +QUALCOMM NAND CONTROLLER DRIVER +M: Manivannan Sadhasivam +L: linux-mtd@lists.infradead.org +L: linux-arm-msm@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/mtd/qcom,nandc.yaml +F: drivers/mtd/nand/raw/qcom_nandc.c + QUALCOMM RMNET DRIVER M: Subash Abhinov Kasiviswanathan M: Sean Tranchetti From fc9e18f9e987ad46722dad53adab1c12148c213c Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 8 Oct 2021 18:36:40 +0200 Subject: [PATCH 296/587] mtd: rawnand: arasan: Prevent an unsupported configuration Under the following conditions: * after rounding up by 4 the number of bytes to transfer (this is related to the controller's internal constraints), * if this (rounded) amount of data is situated beyond the end of the device, * and only in NV-DDR mode, the Arasan NAND controller timeouts. This currently can happen in a particular helper used when picking software ECC algorithms. Let's prevent this situation by refusing to use the NV-DDR interface with software engines. Fixes: 4edde6031458 ("mtd: rawnand: arasan: Support NV-DDR interface") Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20211008163640.1753821-1-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/arasan-nand-controller.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/mtd/nand/raw/arasan-nand-controller.c b/drivers/mtd/nand/raw/arasan-nand-controller.c index 9cbcc698c64d..53bd10738418 100644 --- a/drivers/mtd/nand/raw/arasan-nand-controller.c +++ b/drivers/mtd/nand/raw/arasan-nand-controller.c @@ -973,6 +973,21 @@ static int anfc_setup_interface(struct nand_chip *chip, int target, nvddr = nand_get_nvddr_timings(conf); if (IS_ERR(nvddr)) return PTR_ERR(nvddr); + + /* + * The controller only supports data payload requests which are + * a multiple of 4. In practice, most data accesses are 4-byte + * aligned and this is not an issue. However, rounding up will + * simply be refused by the controller if we reached the end of + * the device *and* we are using the NV-DDR interface(!). In + * this situation, unaligned data requests ending at the device + * boundary will confuse the controller and cannot be performed. + * + * This is something that happens in nand_read_subpage() when + * selecting software ECC support and must be avoided. + */ + if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_SOFT) + return -ENOTSUPP; } else { sdr = nand_get_sdr_timings(conf); if (IS_ERR(sdr)) From 603362b4a58393061dcfed1c7f0d0fd4aba61126 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 27 Sep 2021 16:10:37 +0200 Subject: [PATCH 297/587] mtd: fixup CFI on ixp4xx drivers/mtd/maps/ixp4xx.c requires MTD_CFI_BE_BYTE_SWAP to be set in order to compile. drivers/mtd/maps/ixp4xx.c:57:4: error: #error CONFIG_MTD_CFI_BE_BYTE_SWAP required This patch avoids the #error output by enforcing the policy in Kconfig. Not sure if this is the right approach, but it helps doing randconfig builds. Signed-off-by: Arnd Bergmann Acked-by: Linus Walleij Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210927141045.1597593-1-arnd@kernel.org --- drivers/mtd/chips/Kconfig | 2 ++ drivers/mtd/maps/Kconfig | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/chips/Kconfig b/drivers/mtd/chips/Kconfig index aef14990e5f7..19726ebd973d 100644 --- a/drivers/mtd/chips/Kconfig +++ b/drivers/mtd/chips/Kconfig @@ -55,12 +55,14 @@ choice LITTLE_ENDIAN_BYTE, if the bytes are reversed. config MTD_CFI_NOSWAP + depends on !ARCH_IXP4XX || CPU_BIG_ENDIAN bool "NO" config MTD_CFI_BE_BYTE_SWAP bool "BIG_ENDIAN_BYTE" config MTD_CFI_LE_BYTE_SWAP + depends on !ARCH_IXP4XX bool "LITTLE_ENDIAN_BYTE" endchoice diff --git a/drivers/mtd/maps/Kconfig b/drivers/mtd/maps/Kconfig index aaa164b977fe..4945caa88345 100644 --- a/drivers/mtd/maps/Kconfig +++ b/drivers/mtd/maps/Kconfig @@ -302,7 +302,7 @@ config MTD_DC21285 config MTD_IXP4XX tristate "CFI Flash device mapped on Intel IXP4xx based systems" - depends on MTD_CFI && MTD_COMPLEX_MAPPINGS && ARCH_IXP4XX + depends on MTD_CFI && MTD_COMPLEX_MAPPINGS && ARCH_IXP4XX && MTD_CFI_ADV_OPTIONS help This enables MTD access to flash devices on platforms based on Intel's IXP4xx family of network processors such as the From a04e96537cc64b63fbeb300df2503167bb54f2a1 Mon Sep 17 00:00:00 2001 From: Joachim Wiberg Date: Sat, 9 Oct 2021 08:09:54 +0200 Subject: [PATCH 298/587] mtd: block2mtd: minor refactor to avoid hard coded constant Signed-off-by: Joachim Wiberg Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20211009060955.552636-2-troglobit@gmail.com --- drivers/mtd/devices/block2mtd.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/devices/block2mtd.c b/drivers/mtd/devices/block2mtd.c index c08721b11642..6c2871788d59 100644 --- a/drivers/mtd/devices/block2mtd.c +++ b/drivers/mtd/devices/block2mtd.c @@ -31,6 +31,9 @@ #include #include +/* Maximum number of comma-separated items in the 'block2mtd=' parameter */ +#define BLOCK2MTD_PARAM_MAX_COUNT 2 + /* Info for the block device */ struct block2mtd_dev { struct list_head list; @@ -381,7 +384,7 @@ static int block2mtd_setup2(const char *val) /* 80 for device, 12 for erase size, 80 for name, 8 for timeout */ char buf[80 + 12 + 80 + 8]; char *str = buf; - char *token[2]; + char *token[BLOCK2MTD_PARAM_MAX_COUNT]; char *name; size_t erase_size = PAGE_SIZE; unsigned long timeout = MTD_DEFAULT_TIMEOUT; @@ -395,7 +398,7 @@ static int block2mtd_setup2(const char *val) strcpy(str, val); kill_final_newline(str); - for (i = 0; i < 2; i++) + for (i = 0; i < BLOCK2MTD_PARAM_MAX_COUNT; i++) token[i] = strsep(&str, ","); if (str) { From 7b09acdcb944a9be6acc38ab1aa8a0ffd08871c1 Mon Sep 17 00:00:00 2001 From: Joachim Wiberg Date: Sat, 9 Oct 2021 08:09:55 +0200 Subject: [PATCH 299/587] mtd: block2mtd: add support for an optional custom MTD label This patch adds support for an optional MTD label for mtd2block emulated MTD devices. Useful when, e.g., testing device images using Qemu. The following line in /etc/fstab can then be used to mount a file system regardless if running on an embedded system, or emulated with block2mtd: mtd:Config /mnt jffs2 noatime,nodiratime 0 0 Kernel command line syntax in the emulated case: block2mtd.block2mtd=/dev/sda,,Config Notice the ',,' it is the optional erase_size, which like before this patch, defaults to PAGE_SIZE when omitted. Hence the strlen() check. Signed-off-by: Joachim Wiberg Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20211009060955.552636-3-troglobit@gmail.com --- drivers/mtd/devices/block2mtd.c | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) diff --git a/drivers/mtd/devices/block2mtd.c b/drivers/mtd/devices/block2mtd.c index 6c2871788d59..40d7211485da 100644 --- a/drivers/mtd/devices/block2mtd.c +++ b/drivers/mtd/devices/block2mtd.c @@ -32,7 +32,7 @@ #include /* Maximum number of comma-separated items in the 'block2mtd=' parameter */ -#define BLOCK2MTD_PARAM_MAX_COUNT 2 +#define BLOCK2MTD_PARAM_MAX_COUNT 3 /* Info for the block device */ struct block2mtd_dev { @@ -217,7 +217,7 @@ static void block2mtd_free_device(struct block2mtd_dev *dev) static struct block2mtd_dev *add_device(char *devname, int erase_size, - int timeout) + char *label, int timeout) { #ifndef MODULE int i; @@ -281,7 +281,10 @@ static struct block2mtd_dev *add_device(char *devname, int erase_size, /* Setup the MTD structure */ /* make the name contain the block device in */ - name = kasprintf(GFP_KERNEL, "block2mtd: %s", devname); + if (!label) + name = kasprintf(GFP_KERNEL, "block2mtd: %s", devname); + else + name = kstrdup(label, GFP_KERNEL); if (!name) goto err_destroy_mutex; @@ -308,7 +311,7 @@ static struct block2mtd_dev *add_device(char *devname, int erase_size, list_add(&dev->list, &blkmtd_device_list); pr_info("mtd%d: [%s] erase_size = %dKiB [%d]\n", dev->mtd.index, - dev->mtd.name + strlen("block2mtd: "), + label ? label : dev->mtd.name + strlen("block2mtd: "), dev->mtd.erasesize >> 10, dev->mtd.erasesize); return dev; @@ -386,6 +389,7 @@ static int block2mtd_setup2(const char *val) char *str = buf; char *token[BLOCK2MTD_PARAM_MAX_COUNT]; char *name; + char *label = NULL; size_t erase_size = PAGE_SIZE; unsigned long timeout = MTD_DEFAULT_TIMEOUT; int i, ret; @@ -417,7 +421,8 @@ static int block2mtd_setup2(const char *val) return 0; } - if (token[1]) { + /* Optional argument when custom label is used */ + if (token[1] && strlen(token[1])) { ret = parse_num(&erase_size, token[1]); if (ret) { pr_err("illegal erase size\n"); @@ -425,7 +430,12 @@ static int block2mtd_setup2(const char *val) } } - add_device(name, erase_size, timeout); + if (token[2]) { + label = token[2]; + pr_info("Using custom MTD label '%s' for dev %s\n", label, name); + } + + add_device(name, erase_size, label, timeout); return 0; } @@ -459,7 +469,7 @@ static int block2mtd_setup(const char *val, const struct kernel_param *kp) module_param_call(block2mtd, block2mtd_setup, NULL, NULL, 0200); -MODULE_PARM_DESC(block2mtd, "Device to use. \"block2mtd=[,]\""); +MODULE_PARM_DESC(block2mtd, "Device to use. \"block2mtd=[,[][,