The patch below does not apply to the 6.6-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y
git checkout FETCH_HEAD
git cherry-pick -x 5d2fb074dea289c41f5aaf2c3f68286bee370634
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024120322-subside-manhood-cb29@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 5d2fb074dea289c41f5aaf2c3f68286bee370634 Mon Sep 17 00:00:00 2001
From: Thinh Nguyen <Thinh.Nguyen(a)synopsys.com>
Date: Thu, 14 Nov 2024 01:02:06 +0000
Subject: [PATCH] usb: dwc3: ep0: Don't clear ep0 DWC3_EP_TRANSFER_STARTED
The driver cannot issue the End Transfer command to the SETUP transfer.
Don't clear DWC3_EP_TRANSFER_STARTED flag to make sure that the driver
won't send Start Transfer command again, which can cause no-resource
error. For example this can occur if the host issues a reset to the
device.
Cc: stable(a)vger.kernel.org
Fixes: 76cb323f80ac ("usb: dwc3: ep0: clear all EP0 flags")
Signed-off-by: Thinh Nguyen <Thinh.Nguyen(a)synopsys.com>
Link: https://lore.kernel.org/r/d3d618185fd614bb7426352a9fc1199641d3b5f5.17315457…
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c
index f3d97ad5156e..666ac432f52d 100644
--- a/drivers/usb/dwc3/ep0.c
+++ b/drivers/usb/dwc3/ep0.c
@@ -232,7 +232,7 @@ void dwc3_ep0_stall_and_restart(struct dwc3 *dwc)
/* stall is always issued on EP0 */
dep = dwc->eps[0];
__dwc3_gadget_ep_set_halt(dep, 1, false);
- dep->flags &= DWC3_EP_RESOURCE_ALLOCATED;
+ dep->flags &= DWC3_EP_RESOURCE_ALLOCATED | DWC3_EP_TRANSFER_STARTED;
dep->flags |= DWC3_EP_ENABLED;
dwc->delayed_status = false;
The patch below does not apply to the 5.10-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y
git checkout FETCH_HEAD
git cherry-pick -x 166105c9030a30ba08574a9998afc7b60bc72dd7
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024120304-postnasal-shoptalk-c764@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 166105c9030a30ba08574a9998afc7b60bc72dd7 Mon Sep 17 00:00:00 2001
From: Filip Brozovic <fbrozovic(a)gmail.com>
Date: Sun, 10 Nov 2024 12:17:00 +0100
Subject: [PATCH] serial: 8250_fintek: Add support for F81216E
The F81216E is a LPC/eSPI to 4 UART Super I/O and is mostly compatible with
the F81216H, but does not support RS-485 auto-direction delays on any port.
Signed-off-by: Filip Brozovic <fbrozovic(a)gmail.com>
Cc: stable <stable(a)kernel.org>
Link: https://lore.kernel.org/r/20241110111703.15494-1-fbrozovic@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
diff --git a/drivers/tty/serial/8250/8250_fintek.c b/drivers/tty/serial/8250/8250_fintek.c
index f59c01f48480..b4461a89b8d0 100644
--- a/drivers/tty/serial/8250/8250_fintek.c
+++ b/drivers/tty/serial/8250/8250_fintek.c
@@ -21,6 +21,7 @@
#define CHIP_ID_F81866 0x1010
#define CHIP_ID_F81966 0x0215
#define CHIP_ID_F81216AD 0x1602
+#define CHIP_ID_F81216E 0x1617
#define CHIP_ID_F81216H 0x0501
#define CHIP_ID_F81216 0x0802
#define VENDOR_ID1 0x23
@@ -158,6 +159,7 @@ static int fintek_8250_check_id(struct fintek_8250 *pdata)
case CHIP_ID_F81866:
case CHIP_ID_F81966:
case CHIP_ID_F81216AD:
+ case CHIP_ID_F81216E:
case CHIP_ID_F81216H:
case CHIP_ID_F81216:
break;
@@ -181,6 +183,7 @@ static int fintek_8250_get_ldn_range(struct fintek_8250 *pdata, int *min,
return 0;
case CHIP_ID_F81216AD:
+ case CHIP_ID_F81216E:
case CHIP_ID_F81216H:
case CHIP_ID_F81216:
*min = F81216_LDN_LOW;
@@ -250,6 +253,7 @@ static void fintek_8250_set_irq_mode(struct fintek_8250 *pdata, bool is_level)
break;
case CHIP_ID_F81216AD:
+ case CHIP_ID_F81216E:
case CHIP_ID_F81216H:
case CHIP_ID_F81216:
sio_write_mask_reg(pdata, FINTEK_IRQ_MODE, IRQ_SHARE,
@@ -263,7 +267,8 @@ static void fintek_8250_set_irq_mode(struct fintek_8250 *pdata, bool is_level)
static void fintek_8250_set_max_fifo(struct fintek_8250 *pdata)
{
switch (pdata->pid) {
- case CHIP_ID_F81216H: /* 128Bytes FIFO */
+ case CHIP_ID_F81216E: /* 128Bytes FIFO */
+ case CHIP_ID_F81216H:
case CHIP_ID_F81966:
case CHIP_ID_F81866:
sio_write_mask_reg(pdata, FIFO_CTRL,
@@ -297,6 +302,7 @@ static void fintek_8250_set_termios(struct uart_port *port,
goto exit;
switch (pdata->pid) {
+ case CHIP_ID_F81216E:
case CHIP_ID_F81216H:
reg = RS485;
break;
@@ -346,6 +352,7 @@ static void fintek_8250_set_termios_handler(struct uart_8250_port *uart)
struct fintek_8250 *pdata = uart->port.private_data;
switch (pdata->pid) {
+ case CHIP_ID_F81216E:
case CHIP_ID_F81216H:
case CHIP_ID_F81966:
case CHIP_ID_F81866:
@@ -438,6 +445,11 @@ static void fintek_8250_set_rs485_handler(struct uart_8250_port *uart)
uart->port.rs485_supported = fintek_8250_rs485_supported;
break;
+ case CHIP_ID_F81216E: /* F81216E does not support RS485 delays */
+ uart->port.rs485_config = fintek_8250_rs485_config;
+ uart->port.rs485_supported = fintek_8250_rs485_supported;
+ break;
+
default: /* No RS485 Auto direction functional */
break;
}
The patch below does not apply to the 6.11-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.11.y
git checkout FETCH_HEAD
git cherry-pick -x cb3daa51db819a172e9524e96e2ed96b4237e51a
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024120330-purifier-maturely-c720@gregkh' --subject-prefix 'PATCH 6.11.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From cb3daa51db819a172e9524e96e2ed96b4237e51a Mon Sep 17 00:00:00 2001
From: Herve Codina <herve.codina(a)bootlin.com>
Date: Tue, 5 Nov 2024 15:56:23 +0100
Subject: [PATCH] soc: fsl: cpm1: qmc: Set the ret error code on
platform_get_irq() failure
A kernel test robot detected a missing error code:
qmc.c:1942 qmc_probe() warn: missing error code 'ret'
Indeed, the error returned by platform_get_irq() is checked and the
operation is aborted in case of failure but the ret error code is
not set in that case.
Set the ret error code.
Reported-by: kernel test robot <lkp(a)intel.com>
Reported-by: Dan Carpenter <dan.carpenter(a)linaro.org>
Closes: https://lore.kernel.org/r/202411051350.KNy6ZIWA-lkp@intel.com/
Fixes: 3178d58e0b97 ("soc: fsl: cpm1: Add support for QMC")
Cc: stable(a)vger.kernel.org
Signed-off-by: Herve Codina <herve.codina(a)bootlin.com>
Link: https://lore.kernel.org/r/20241105145623.401528-1-herve.codina@bootlin.com
Signed-off-by: Christophe Leroy <christophe.leroy(a)csgroup.eu>
diff --git a/drivers/soc/fsl/qe/qmc.c b/drivers/soc/fsl/qe/qmc.c
index 3dffebb48b0d..fa7dc7d4abf3 100644
--- a/drivers/soc/fsl/qe/qmc.c
+++ b/drivers/soc/fsl/qe/qmc.c
@@ -2005,8 +2005,10 @@ static int qmc_probe(struct platform_device *pdev)
/* Set the irq handler */
irq = platform_get_irq(pdev, 0);
- if (irq < 0)
+ if (irq < 0) {
+ ret = irq;
goto err_exit_xcc;
+ }
ret = devm_request_irq(qmc->dev, irq, qmc_irq_handler, 0, "qmc", qmc);
if (ret < 0)
goto err_exit_xcc;
The patch below does not apply to the 6.6-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y
git checkout FETCH_HEAD
git cherry-pick -x cb3daa51db819a172e9524e96e2ed96b4237e51a
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024120331-disarm-unfixed-bbec@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From cb3daa51db819a172e9524e96e2ed96b4237e51a Mon Sep 17 00:00:00 2001
From: Herve Codina <herve.codina(a)bootlin.com>
Date: Tue, 5 Nov 2024 15:56:23 +0100
Subject: [PATCH] soc: fsl: cpm1: qmc: Set the ret error code on
platform_get_irq() failure
A kernel test robot detected a missing error code:
qmc.c:1942 qmc_probe() warn: missing error code 'ret'
Indeed, the error returned by platform_get_irq() is checked and the
operation is aborted in case of failure but the ret error code is
not set in that case.
Set the ret error code.
Reported-by: kernel test robot <lkp(a)intel.com>
Reported-by: Dan Carpenter <dan.carpenter(a)linaro.org>
Closes: https://lore.kernel.org/r/202411051350.KNy6ZIWA-lkp@intel.com/
Fixes: 3178d58e0b97 ("soc: fsl: cpm1: Add support for QMC")
Cc: stable(a)vger.kernel.org
Signed-off-by: Herve Codina <herve.codina(a)bootlin.com>
Link: https://lore.kernel.org/r/20241105145623.401528-1-herve.codina@bootlin.com
Signed-off-by: Christophe Leroy <christophe.leroy(a)csgroup.eu>
diff --git a/drivers/soc/fsl/qe/qmc.c b/drivers/soc/fsl/qe/qmc.c
index 3dffebb48b0d..fa7dc7d4abf3 100644
--- a/drivers/soc/fsl/qe/qmc.c
+++ b/drivers/soc/fsl/qe/qmc.c
@@ -2005,8 +2005,10 @@ static int qmc_probe(struct platform_device *pdev)
/* Set the irq handler */
irq = platform_get_irq(pdev, 0);
- if (irq < 0)
+ if (irq < 0) {
+ ret = irq;
goto err_exit_xcc;
+ }
ret = devm_request_irq(qmc->dev, irq, qmc_irq_handler, 0, "qmc", qmc);
if (ret < 0)
goto err_exit_xcc;
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y
git checkout FETCH_HEAD
git cherry-pick -x 6bda857bcbb86fb9d0e54fbef93a093d51172acc
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024120344-onshore-retrain-f7ee@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 6bda857bcbb86fb9d0e54fbef93a093d51172acc Mon Sep 17 00:00:00 2001
From: Muchun Song <muchun.song(a)linux.dev>
Date: Mon, 14 Oct 2024 17:29:33 +0800
Subject: [PATCH] block: fix ordering between checking QUEUE_FLAG_QUIESCED
request adding
Supposing the following scenario.
CPU0 CPU1
blk_mq_insert_request() 1) store
blk_mq_unquiesce_queue()
blk_queue_flag_clear() 3) store
blk_mq_run_hw_queues()
blk_mq_run_hw_queue()
if (!blk_mq_hctx_has_pending()) 4) load
return
blk_mq_run_hw_queue()
if (blk_queue_quiesced()) 2) load
return
blk_mq_sched_dispatch_requests()
The full memory barrier should be inserted between 1) and 2), as well as
between 3) and 4) to make sure that either CPU0 sees QUEUE_FLAG_QUIESCED
is cleared or CPU1 sees dispatch list or setting of bitmap of software
queue. Otherwise, either CPU will not rerun the hardware queue causing
starvation.
So the first solution is to 1) add a pair of memory barrier to fix the
problem, another solution is to 2) use hctx->queue->queue_lock to
synchronize QUEUE_FLAG_QUIESCED. Here, we chose 2) to fix it since
memory barrier is not easy to be maintained.
Fixes: f4560ffe8cec ("blk-mq: use QUEUE_FLAG_QUIESCED to quiesce queue")
Cc: stable(a)vger.kernel.org
Cc: Muchun Song <muchun.song(a)linux.dev>
Signed-off-by: Muchun Song <songmuchun(a)bytedance.com>
Reviewed-by: Ming Lei <ming.lei(a)redhat.com>
Link: https://lore.kernel.org/r/20241014092934.53630-3-songmuchun@bytedance.com
Signed-off-by: Jens Axboe <axboe(a)kernel.dk>
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 5deb9dffca0a..bb4ee2380dce 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2227,6 +2227,24 @@ void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
}
EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
+static inline bool blk_mq_hw_queue_need_run(struct blk_mq_hw_ctx *hctx)
+{
+ bool need_run;
+
+ /*
+ * When queue is quiesced, we may be switching io scheduler, or
+ * updating nr_hw_queues, or other things, and we can't run queue
+ * any more, even blk_mq_hctx_has_pending() can't be called safely.
+ *
+ * And queue will be rerun in blk_mq_unquiesce_queue() if it is
+ * quiesced.
+ */
+ __blk_mq_run_dispatch_ops(hctx->queue, false,
+ need_run = !blk_queue_quiesced(hctx->queue) &&
+ blk_mq_hctx_has_pending(hctx));
+ return need_run;
+}
+
/**
* blk_mq_run_hw_queue - Start to run a hardware queue.
* @hctx: Pointer to the hardware queue to run.
@@ -2247,20 +2265,23 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
might_sleep_if(!async && hctx->flags & BLK_MQ_F_BLOCKING);
- /*
- * When queue is quiesced, we may be switching io scheduler, or
- * updating nr_hw_queues, or other things, and we can't run queue
- * any more, even __blk_mq_hctx_has_pending() can't be called safely.
- *
- * And queue will be rerun in blk_mq_unquiesce_queue() if it is
- * quiesced.
- */
- __blk_mq_run_dispatch_ops(hctx->queue, false,
- need_run = !blk_queue_quiesced(hctx->queue) &&
- blk_mq_hctx_has_pending(hctx));
+ need_run = blk_mq_hw_queue_need_run(hctx);
+ if (!need_run) {
+ unsigned long flags;
- if (!need_run)
- return;
+ /*
+ * Synchronize with blk_mq_unquiesce_queue(), because we check
+ * if hw queue is quiesced locklessly above, we need the use
+ * ->queue_lock to make sure we see the up-to-date status to
+ * not miss rerunning the hw queue.
+ */
+ spin_lock_irqsave(&hctx->queue->queue_lock, flags);
+ need_run = blk_mq_hw_queue_need_run(hctx);
+ spin_unlock_irqrestore(&hctx->queue->queue_lock, flags);
+
+ if (!need_run)
+ return;
+ }
if (async || !cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask)) {
blk_mq_delay_run_hw_queue(hctx, 0);
The patch below does not apply to the 5.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y
git checkout FETCH_HEAD
git cherry-pick -x 6bda857bcbb86fb9d0e54fbef93a093d51172acc
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024120343-express-overbuilt-6478@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 6bda857bcbb86fb9d0e54fbef93a093d51172acc Mon Sep 17 00:00:00 2001
From: Muchun Song <muchun.song(a)linux.dev>
Date: Mon, 14 Oct 2024 17:29:33 +0800
Subject: [PATCH] block: fix ordering between checking QUEUE_FLAG_QUIESCED
request adding
Supposing the following scenario.
CPU0 CPU1
blk_mq_insert_request() 1) store
blk_mq_unquiesce_queue()
blk_queue_flag_clear() 3) store
blk_mq_run_hw_queues()
blk_mq_run_hw_queue()
if (!blk_mq_hctx_has_pending()) 4) load
return
blk_mq_run_hw_queue()
if (blk_queue_quiesced()) 2) load
return
blk_mq_sched_dispatch_requests()
The full memory barrier should be inserted between 1) and 2), as well as
between 3) and 4) to make sure that either CPU0 sees QUEUE_FLAG_QUIESCED
is cleared or CPU1 sees dispatch list or setting of bitmap of software
queue. Otherwise, either CPU will not rerun the hardware queue causing
starvation.
So the first solution is to 1) add a pair of memory barrier to fix the
problem, another solution is to 2) use hctx->queue->queue_lock to
synchronize QUEUE_FLAG_QUIESCED. Here, we chose 2) to fix it since
memory barrier is not easy to be maintained.
Fixes: f4560ffe8cec ("blk-mq: use QUEUE_FLAG_QUIESCED to quiesce queue")
Cc: stable(a)vger.kernel.org
Cc: Muchun Song <muchun.song(a)linux.dev>
Signed-off-by: Muchun Song <songmuchun(a)bytedance.com>
Reviewed-by: Ming Lei <ming.lei(a)redhat.com>
Link: https://lore.kernel.org/r/20241014092934.53630-3-songmuchun@bytedance.com
Signed-off-by: Jens Axboe <axboe(a)kernel.dk>
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 5deb9dffca0a..bb4ee2380dce 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2227,6 +2227,24 @@ void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
}
EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
+static inline bool blk_mq_hw_queue_need_run(struct blk_mq_hw_ctx *hctx)
+{
+ bool need_run;
+
+ /*
+ * When queue is quiesced, we may be switching io scheduler, or
+ * updating nr_hw_queues, or other things, and we can't run queue
+ * any more, even blk_mq_hctx_has_pending() can't be called safely.
+ *
+ * And queue will be rerun in blk_mq_unquiesce_queue() if it is
+ * quiesced.
+ */
+ __blk_mq_run_dispatch_ops(hctx->queue, false,
+ need_run = !blk_queue_quiesced(hctx->queue) &&
+ blk_mq_hctx_has_pending(hctx));
+ return need_run;
+}
+
/**
* blk_mq_run_hw_queue - Start to run a hardware queue.
* @hctx: Pointer to the hardware queue to run.
@@ -2247,20 +2265,23 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
might_sleep_if(!async && hctx->flags & BLK_MQ_F_BLOCKING);
- /*
- * When queue is quiesced, we may be switching io scheduler, or
- * updating nr_hw_queues, or other things, and we can't run queue
- * any more, even __blk_mq_hctx_has_pending() can't be called safely.
- *
- * And queue will be rerun in blk_mq_unquiesce_queue() if it is
- * quiesced.
- */
- __blk_mq_run_dispatch_ops(hctx->queue, false,
- need_run = !blk_queue_quiesced(hctx->queue) &&
- blk_mq_hctx_has_pending(hctx));
+ need_run = blk_mq_hw_queue_need_run(hctx);
+ if (!need_run) {
+ unsigned long flags;
- if (!need_run)
- return;
+ /*
+ * Synchronize with blk_mq_unquiesce_queue(), because we check
+ * if hw queue is quiesced locklessly above, we need the use
+ * ->queue_lock to make sure we see the up-to-date status to
+ * not miss rerunning the hw queue.
+ */
+ spin_lock_irqsave(&hctx->queue->queue_lock, flags);
+ need_run = blk_mq_hw_queue_need_run(hctx);
+ spin_unlock_irqrestore(&hctx->queue->queue_lock, flags);
+
+ if (!need_run)
+ return;
+ }
if (async || !cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask)) {
blk_mq_delay_run_hw_queue(hctx, 0);
The patch below does not apply to the 5.10-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y
git checkout FETCH_HEAD
git cherry-pick -x 6bda857bcbb86fb9d0e54fbef93a093d51172acc
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024120343-livable-euphemism-b28b@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 6bda857bcbb86fb9d0e54fbef93a093d51172acc Mon Sep 17 00:00:00 2001
From: Muchun Song <muchun.song(a)linux.dev>
Date: Mon, 14 Oct 2024 17:29:33 +0800
Subject: [PATCH] block: fix ordering between checking QUEUE_FLAG_QUIESCED
request adding
Supposing the following scenario.
CPU0 CPU1
blk_mq_insert_request() 1) store
blk_mq_unquiesce_queue()
blk_queue_flag_clear() 3) store
blk_mq_run_hw_queues()
blk_mq_run_hw_queue()
if (!blk_mq_hctx_has_pending()) 4) load
return
blk_mq_run_hw_queue()
if (blk_queue_quiesced()) 2) load
return
blk_mq_sched_dispatch_requests()
The full memory barrier should be inserted between 1) and 2), as well as
between 3) and 4) to make sure that either CPU0 sees QUEUE_FLAG_QUIESCED
is cleared or CPU1 sees dispatch list or setting of bitmap of software
queue. Otherwise, either CPU will not rerun the hardware queue causing
starvation.
So the first solution is to 1) add a pair of memory barrier to fix the
problem, another solution is to 2) use hctx->queue->queue_lock to
synchronize QUEUE_FLAG_QUIESCED. Here, we chose 2) to fix it since
memory barrier is not easy to be maintained.
Fixes: f4560ffe8cec ("blk-mq: use QUEUE_FLAG_QUIESCED to quiesce queue")
Cc: stable(a)vger.kernel.org
Cc: Muchun Song <muchun.song(a)linux.dev>
Signed-off-by: Muchun Song <songmuchun(a)bytedance.com>
Reviewed-by: Ming Lei <ming.lei(a)redhat.com>
Link: https://lore.kernel.org/r/20241014092934.53630-3-songmuchun@bytedance.com
Signed-off-by: Jens Axboe <axboe(a)kernel.dk>
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 5deb9dffca0a..bb4ee2380dce 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2227,6 +2227,24 @@ void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
}
EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
+static inline bool blk_mq_hw_queue_need_run(struct blk_mq_hw_ctx *hctx)
+{
+ bool need_run;
+
+ /*
+ * When queue is quiesced, we may be switching io scheduler, or
+ * updating nr_hw_queues, or other things, and we can't run queue
+ * any more, even blk_mq_hctx_has_pending() can't be called safely.
+ *
+ * And queue will be rerun in blk_mq_unquiesce_queue() if it is
+ * quiesced.
+ */
+ __blk_mq_run_dispatch_ops(hctx->queue, false,
+ need_run = !blk_queue_quiesced(hctx->queue) &&
+ blk_mq_hctx_has_pending(hctx));
+ return need_run;
+}
+
/**
* blk_mq_run_hw_queue - Start to run a hardware queue.
* @hctx: Pointer to the hardware queue to run.
@@ -2247,20 +2265,23 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
might_sleep_if(!async && hctx->flags & BLK_MQ_F_BLOCKING);
- /*
- * When queue is quiesced, we may be switching io scheduler, or
- * updating nr_hw_queues, or other things, and we can't run queue
- * any more, even __blk_mq_hctx_has_pending() can't be called safely.
- *
- * And queue will be rerun in blk_mq_unquiesce_queue() if it is
- * quiesced.
- */
- __blk_mq_run_dispatch_ops(hctx->queue, false,
- need_run = !blk_queue_quiesced(hctx->queue) &&
- blk_mq_hctx_has_pending(hctx));
+ need_run = blk_mq_hw_queue_need_run(hctx);
+ if (!need_run) {
+ unsigned long flags;
- if (!need_run)
- return;
+ /*
+ * Synchronize with blk_mq_unquiesce_queue(), because we check
+ * if hw queue is quiesced locklessly above, we need the use
+ * ->queue_lock to make sure we see the up-to-date status to
+ * not miss rerunning the hw queue.
+ */
+ spin_lock_irqsave(&hctx->queue->queue_lock, flags);
+ need_run = blk_mq_hw_queue_need_run(hctx);
+ spin_unlock_irqrestore(&hctx->queue->queue_lock, flags);
+
+ if (!need_run)
+ return;
+ }
if (async || !cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask)) {
blk_mq_delay_run_hw_queue(hctx, 0);