1. Patchew
  2. linux
  3. View series

[PATCH] mmc: core: Fix system shutdown hang in mmc_bus_shutdown

Michael Wu posted 1 patch 5 days, 19 hours ago 
drivers/mmc/core/bus.c  |  2 +-
drivers/mmc/core/core.c | 14 ++++++++++++++
drivers/mmc/core/core.h |  1 +
3 files changed, 16 insertions(+), 1 deletion(-)
[PATCH] mmc: core: Fix system shutdown hang in mmc_bus_shutdown
Posted by Michael Wu 5 days, 19 hours ago 
During system shutdown, mmc_bus_shutdown() calls __mmc_stop_host() which
uses cancel_delayed_work_sync(). This can block indefinitely if the work
queue is stuck, causing the system to hang during shutdown.

This patch introduces a new function __mmc_stop_host_no_sync() that skips
the synchronous work cancellation, preventing potential shutdown hangs.
The function is used in mmc_bus_shutdown() where blocking is not
acceptable during system shutdown.

Changes:
- Add __mmc_stop_host_no_sync() function that avoids cancel_delayed_work_sync()
- Update mmc_bus_shutdown() to use the new non-blocking function
- Keep the original __mmc_stop_host() unchanged for normal operation

This ensures graceful system shutdown while maintaining existing
functionality for regular MMC host operations.

stack information when an error occurs:
INFO: task init:1 blocked for more than 720 seconds.
      Tainted: G           OE     5.15.185-android13-8-00043-gd00fb6bce7ed-ab13792018 #1
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
task:init            state:D stack:    0 pid:    1 ppid:     0 flags:0x04000008
Call trace:
 __switch_to+0x234/0x470
 __schedule+0x694/0xb8c
 schedule+0x150/0x254
 schedule_timeout+0x48/0x138
 wait_for_common+0x144/0x308
 __flush_work+0x3d8/0x508
 __cancel_work_timer+0x120/0x2e8
 mmc_bus_shutdown+0x90/0x158
 device_shutdown+0x204/0x434
 kernel_restart+0x54/0x220
 kernel_restart+0x0/0x220
 invoke_syscall+0x60/0x150
 el0_svc_common+0xb8/0xf8
 do_el0_svc+0x28/0x98
 el0_svc+0x24/0x84
 el0t_64_sync_handler+0x88/0xec
 el0t_64_sync+0x1b8/0x1bc
INFO: task kworker/1:1:73 blocked for more than 721 seconds.
      Tainted: G           OE     5.15.185-android13-8-00043-gd00fb6bce7ed-ab13792018 #1
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
task:kworker/1:1     state:D stack:    0 pid:   73 ppid:     2 flags:0x00000008
Workqueue: events_freezable mmc_rescan.cfi_jt
Call trace:
 __switch_to+0x234/0x470
 __schedule+0x694/0xb8c
 schedule+0x150/0x254
 schedule_preempt_disabled+0x2c/0x4c
 __mutex_lock+0x360/0xb00
 __mutex_lock_slowpath+0x18/0x28
 mutex_lock+0x48/0x12c
 device_del+0x48/0x8d0
 mmc_remove_card+0x128/0x158
 mmc_sdio_remove+0x190/0x1ac
 mmc_sdio_detect+0x7c/0x118
 mmc_rescan+0xe8/0x42c
 process_one_work+0x248/0x55c
 worker_thread+0x3b0/0x740
 kthread+0x168/0x1dc
 ret_from_fork+0x10/0x20

Signed-off-by: Michael Wu <michael@allwinnertech.com>
---
 drivers/mmc/core/bus.c  |  2 +-
 drivers/mmc/core/core.c | 14 ++++++++++++++
 drivers/mmc/core/core.h |  1 +
 3 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/mmc/core/bus.c b/drivers/mmc/core/bus.c
index 1cf64e0952fbe..6ff6fcb4c6f27 100644
--- a/drivers/mmc/core/bus.c
+++ b/drivers/mmc/core/bus.c
@@ -149,7 +149,7 @@ static void mmc_bus_shutdown(struct device *dev)
 	if (dev->driver && drv->shutdown)
 		drv->shutdown(card);
 
-	__mmc_stop_host(host);
+	__mmc_stop_host_no_sync(host);
 
 	if (host->bus_ops->shutdown) {
 		ret = host->bus_ops->shutdown(host);
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index a0e2dce704343..2d75ad26f84a9 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -2336,6 +2336,20 @@ void __mmc_stop_host(struct mmc_host *host)
 	cancel_delayed_work_sync(&host->detect);
 }
 
+void __mmc_stop_host_no_sync(struct mmc_host *host)
+{
+	if (host->rescan_disable)
+		return;
+
+	if (host->slot.cd_irq >= 0) {
+		mmc_gpio_set_cd_wake(host, false);
+		disable_irq(host->slot.cd_irq);
+	}
+
+	host->rescan_disable = 1;
+	/* Skip cancel_delayed_work_sync to avoid potential blocking */
+}
+
 void mmc_stop_host(struct mmc_host *host)
 {
 	__mmc_stop_host(host);
diff --git a/drivers/mmc/core/core.h b/drivers/mmc/core/core.h
index 622085cd766f9..eb59a61717357 100644
--- a/drivers/mmc/core/core.h
+++ b/drivers/mmc/core/core.h
@@ -71,6 +71,7 @@ static inline void mmc_delay(unsigned int ms)
 void mmc_rescan(struct work_struct *work);
 void mmc_start_host(struct mmc_host *host);
 void __mmc_stop_host(struct mmc_host *host);
+void __mmc_stop_host_no_sync(struct mmc_host *host);
 void mmc_stop_host(struct mmc_host *host);
 
 void _mmc_detect_change(struct mmc_host *host, unsigned long delay,
-- 
2.29.0
Re: [PATCH] mmc: core: Fix system shutdown hang in mmc_bus_shutdown
Posted by Ulf Hansson 5 days, 9 hours ago 
On Fri, 26 Sept 2025 at 04:49, Michael Wu <michael@allwinnertech.com> wrote:
>
> During system shutdown, mmc_bus_shutdown() calls __mmc_stop_host() which
> uses cancel_delayed_work_sync(). This can block indefinitely if the work
> queue is stuck, causing the system to hang during shutdown.

Why, more exactly, is it stuck?

I looked at the trace below, it looks like we are failing to remove an
SDIO card, why?

>
> This patch introduces a new function __mmc_stop_host_no_sync() that skips
> the synchronous work cancellation, preventing potential shutdown hangs.
> The function is used in mmc_bus_shutdown() where blocking is not
> acceptable during system shutdown.

This isn't the only thing that can block in mmc_bus_shutdown().

With this change, I am worried that we may execute the
power-off-notifications to an eMMC/SD card, when it's not safe to do
so. But perhaps there is no other way?

Kind regards
Uffe

>
> Changes:
> - Add __mmc_stop_host_no_sync() function that avoids cancel_delayed_work_sync()
> - Update mmc_bus_shutdown() to use the new non-blocking function
> - Keep the original __mmc_stop_host() unchanged for normal operation
>
> This ensures graceful system shutdown while maintaining existing
> functionality for regular MMC host operations.
>
> stack information when an error occurs:
> INFO: task init:1 blocked for more than 720 seconds.
>       Tainted: G           OE     5.15.185-android13-8-00043-gd00fb6bce7ed-ab13792018 #1
> "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
> task:init            state:D stack:    0 pid:    1 ppid:     0 flags:0x04000008
> Call trace:
>  __switch_to+0x234/0x470
>  __schedule+0x694/0xb8c
>  schedule+0x150/0x254
>  schedule_timeout+0x48/0x138
>  wait_for_common+0x144/0x308
>  __flush_work+0x3d8/0x508
>  __cancel_work_timer+0x120/0x2e8
>  mmc_bus_shutdown+0x90/0x158
>  device_shutdown+0x204/0x434
>  kernel_restart+0x54/0x220
>  kernel_restart+0x0/0x220
>  invoke_syscall+0x60/0x150
>  el0_svc_common+0xb8/0xf8
>  do_el0_svc+0x28/0x98
>  el0_svc+0x24/0x84
>  el0t_64_sync_handler+0x88/0xec
>  el0t_64_sync+0x1b8/0x1bc
> INFO: task kworker/1:1:73 blocked for more than 721 seconds.
>       Tainted: G           OE     5.15.185-android13-8-00043-gd00fb6bce7ed-ab13792018 #1
> "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
> task:kworker/1:1     state:D stack:    0 pid:   73 ppid:     2 flags:0x00000008
> Workqueue: events_freezable mmc_rescan.cfi_jt
> Call trace:
>  __switch_to+0x234/0x470
>  __schedule+0x694/0xb8c
>  schedule+0x150/0x254
>  schedule_preempt_disabled+0x2c/0x4c
>  __mutex_lock+0x360/0xb00
>  __mutex_lock_slowpath+0x18/0x28
>  mutex_lock+0x48/0x12c
>  device_del+0x48/0x8d0
>  mmc_remove_card+0x128/0x158
>  mmc_sdio_remove+0x190/0x1ac
>  mmc_sdio_detect+0x7c/0x118
>  mmc_rescan+0xe8/0x42c
>  process_one_work+0x248/0x55c
>  worker_thread+0x3b0/0x740
>  kthread+0x168/0x1dc
>  ret_from_fork+0x10/0x20
>
> Signed-off-by: Michael Wu <michael@allwinnertech.com>
> ---
>  drivers/mmc/core/bus.c  |  2 +-
>  drivers/mmc/core/core.c | 14 ++++++++++++++
>  drivers/mmc/core/core.h |  1 +
>  3 files changed, 16 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/mmc/core/bus.c b/drivers/mmc/core/bus.c
> index 1cf64e0952fbe..6ff6fcb4c6f27 100644
> --- a/drivers/mmc/core/bus.c
> +++ b/drivers/mmc/core/bus.c
> @@ -149,7 +149,7 @@ static void mmc_bus_shutdown(struct device *dev)
>         if (dev->driver && drv->shutdown)
>                 drv->shutdown(card);
>
> -       __mmc_stop_host(host);
> +       __mmc_stop_host_no_sync(host);
>
>         if (host->bus_ops->shutdown) {
>                 ret = host->bus_ops->shutdown(host);
> diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
> index a0e2dce704343..2d75ad26f84a9 100644
> --- a/drivers/mmc/core/core.c
> +++ b/drivers/mmc/core/core.c
> @@ -2336,6 +2336,20 @@ void __mmc_stop_host(struct mmc_host *host)
>         cancel_delayed_work_sync(&host->detect);
>  }
>
> +void __mmc_stop_host_no_sync(struct mmc_host *host)
> +{
> +       if (host->rescan_disable)
> +               return;
> +
> +       if (host->slot.cd_irq >= 0) {
> +               mmc_gpio_set_cd_wake(host, false);
> +               disable_irq(host->slot.cd_irq);
> +       }
> +
> +       host->rescan_disable = 1;
> +       /* Skip cancel_delayed_work_sync to avoid potential blocking */
> +}
> +
>  void mmc_stop_host(struct mmc_host *host)
>  {
>         __mmc_stop_host(host);
> diff --git a/drivers/mmc/core/core.h b/drivers/mmc/core/core.h
> index 622085cd766f9..eb59a61717357 100644
> --- a/drivers/mmc/core/core.h
> +++ b/drivers/mmc/core/core.h
> @@ -71,6 +71,7 @@ static inline void mmc_delay(unsigned int ms)
>  void mmc_rescan(struct work_struct *work);
>  void mmc_start_host(struct mmc_host *host);
>  void __mmc_stop_host(struct mmc_host *host);
> +void __mmc_stop_host_no_sync(struct mmc_host *host);
>  void mmc_stop_host(struct mmc_host *host);
>
>  void _mmc_detect_change(struct mmc_host *host, unsigned long delay,
> --
> 2.29.0
>

Patchew 2.1-devel-b67e4c2

© 2016 - 2025 Red Hat, Inc.