[alsa-devel] sound/core/timer: Deadlock on register_mutex
Takashi Iwai
tiwai at suse.de
Wed Oct 30 22:57:40 CET 2019
On Wed, 30 Oct 2019 16:28:23 +0100,
Kirill A. Shutemov wrote:
>
> On Wed, Oct 30, 2019 at 06:11:37PM +0300, Kirill A. Shutemov wrote:
> > On Wed, Oct 30, 2019 at 04:04:01PM +0100, Takashi Iwai wrote:
> > > On Wed, 30 Oct 2019 15:10:29 +0100,
> > > Kirill A. Shutemov wrote:
> > > >
> > > > Hi,
> > > >
> > > > I've stepped on this after pulling USB sound card:
> > > >
> > > > ============================================
> > > > WARNING: possible recursive locking detected
> > > > 5.4.0-rc4-00090-g95b5dc072cc3-dirty #48 Not tainted
> > > > --------------------------------------------
> > > > xdg-screensaver/1321 is trying to acquire lock:
> > > > ffffffffbaf6b3a0 (register_mutex){+.+.}, at: snd_timer_free.part.0 (/include/linux/compiler.h:199 /include/linux/list.h:268 /sound/core/timer.c:944)
> > > >
> > > > but task is already holding lock:
> > > > ffffffffbaf6b3a0 (register_mutex){+.+.}, at: snd_timer_close (/sound/core/timer.c:416)
> > > >
> > > > other info that might help us debug this:
> > > > Possible unsafe locking scenario:
> > > >
> > > > CPU0
> > > > ----
> > > > lock(register_mutex);
> > > > lock(register_mutex);
> > > >
> > > > *** DEADLOCK ***
> > > >
> > > > May be due to missing lock nesting notation
> > > >
> > > > 2 locks held by xdg-screensaver/1321:
> > > > #0: ffff9f74bbf5ef50 (&tu->ioctl_lock){+.+.}, at: snd_timer_user_release (/sound/core/timer.c:1467)
> > > > #1: ffffffffbaf6b3a0 (register_mutex){+.+.}, at: snd_timer_close (/sound/core/timer.c:416)
> > > >
> > > > stack backtrace:
> > > > CPU: 27 PID: 1321 Comm: xdg-screensaver Not tainted 5.4.0-rc4-00090-g95b5dc072cc3-dirty #48
> > > > Hardware name: Gigabyte Technology Co., Ltd. X299 AORUS Gaming 3 Pro/X299 AORUS Gaming 3 Pro-CF, BIOS F3 12/28/2017
> > > > Call Trace:
> > > > dump_stack (/lib/dump_stack.c:115)
> > > > __lock_acquire.cold (/kernel/locking/lockdep.c:2371 /kernel/locking/lockdep.c:2412 /kernel/locking/lockdep.c:2955 /kernel/locking/lockdep.c:3955)
> > > > ? __lock_acquire (/kernel/locking/lockdep.c:3962)
> > > > lock_acquire (/arch/x86/include/asm/current.h:15 /kernel/locking/lockdep.c:4489)
> > > > ? snd_timer_free.part.0 (/include/linux/compiler.h:199 /include/linux/list.h:268 /sound/core/timer.c:944)
> > > > __mutex_lock (/include/linux/compiler.h:199 /arch/x86/include/asm/atomic64_64.h:22 /include/asm-generic/atomic-instrumented.h:837 /include/asm-generic/atomic-long.h:28 /kernel/locking/mutex.c:111 /kernel/locking/mutex.c:152 /kernel/locking/mutex.c:958 /kernel/locking/mutex.c:1103)
> > > > ? snd_timer_free.part.0 (/include/linux/compiler.h:199 /include/linux/list.h:268 /sound/core/timer.c:944)
> > > > ? __mutex_lock (/include/linux/compiler.h:199 /arch/x86/include/asm/atomic64_64.h:22 /include/asm-generic/atomic-instrumented.h:837 /include/asm-generic/atomic-long.h:28 /kernel/locking/mutex.c:111 /kernel/locking/mutex.c:152 /kernel/locking/mutex.c:958 /kernel/locking/mutex.c:1103)
> > > > ? __mutex_lock (/arch/x86/include/asm/preempt.h:102 /kernel/locking/mutex.c:964 /kernel/locking/mutex.c:1103)
> > > > ? snd_timer_free.part.0 (/include/linux/compiler.h:199 /include/linux/list.h:268 /sound/core/timer.c:944)
> > > > ? snd_timer_free.part.0 (/include/linux/compiler.h:199 /include/linux/list.h:268 /sound/core/timer.c:944)
> > > > ? lockdep_hardirqs_on (/kernel/locking/lockdep.c:3394 /kernel/locking/lockdep.c:3434)
> > > > snd_timer_free.part.0 (/include/linux/compiler.h:199 /include/linux/list.h:268 /sound/core/timer.c:944)
> > > > snd_timer_dev_free (/sound/core/timer.c:967)
> > > > __snd_device_free (/sound/core/device.c:76)
> > > > snd_device_free_all (/sound/core/device.c:228)
> > > > release_card_device (/sound/core/init.c:471 /sound/core/init.c:140)
> > > > device_release (/drivers/base/core.c:1105)
> > > > kobject_put (/lib/kobject.c:697 /lib/kobject.c:722 /include/linux/kref.h:65 /lib/kobject.c:739)
> > > > snd_timer_close_locked (/sound/core/timer.c:398)
> > > > snd_timer_close (/sound/core/timer.c:417)
> > > > snd_timer_user_release (/sound/core/timer.c:1469)
> > > > __fput (/fs/file_table.c:281)
> > > > task_work_run (/kernel/task_work.c:115 (discriminator 1))
> > > > exit_to_usermode_loop (/include/linux/tracehook.h:188 /arch/x86/entry/common.c:163)
> > > > do_syscall_64 (/arch/x86/entry/common.c:194 /arch/x86/entry/common.c:274 /arch/x86/entry/common.c:300)
> > > > entry_SYSCALL_64_after_hwframe (/arch/x86/entry/entry_64.S:177)
> > >
> > > OK, this looks like a deadlock that is via put_device() called at
> > > closing the timer device that is the last open instance while freeing
> > > the card.
> > >
> > > Could you try the patch below?
> >
> > I can, but I'm not sure if I can trigger the issue for the second time.
>
> Yeah, I was able to reproduce it without the patch and cannot with.
>
> Reported-and-tested-by: Kirill A. Shutemov <kirill.shutemov at linux.intel.com>
Great, thanks for quick testing!
FWIW, below is the proper patch with the description I'm going to
queue.
Takashi
-- 8< --
From: Takashi Iwai <tiwai at suse.de>
Subject: [PATCH] ALSA: timer: Fix mutex deadlock at releasing card
When a card is disconnected while in use, the system waits until all
opened files are closed then releases the card. This is done via
put_device() of the card device in each device release code.
The recently reported mutex deadlock bug happens in this code path;
snd_timer_close() for the timer device deals with the global
register_mutex and it calls put_device() there. When this timer
device is the last one, the card gets freed and it eventually calls
snd_timer_free(), which has again the protection with the global
register_mutex -- boom.
Basically put_device() call itself is race-free, so a relative simple
workaround is to move this put_device() call out of the mutex. For
achieving that, in this patch, snd_timer_close_locked() got a new
argument to store the card device pointer in return, and each caller
invokes put_device() with the returned object after the mutex unlock.
Reported-and-tested-by: Kirill A. Shutemov <kirill.shutemov at linux.intel.com>
Cc: <stable at vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai at suse.de>
---
sound/core/timer.c | 24 +++++++++++++++++-------
1 file changed, 17 insertions(+), 7 deletions(-)
diff --git a/sound/core/timer.c b/sound/core/timer.c
index 5c9fbf3f4340..6b724d2ee2de 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -226,7 +226,8 @@ static int snd_timer_check_master(struct snd_timer_instance *master)
return 0;
}
-static int snd_timer_close_locked(struct snd_timer_instance *timeri);
+static int snd_timer_close_locked(struct snd_timer_instance *timeri,
+ struct device **card_devp_to_put);
/*
* open a timer instance
@@ -238,6 +239,7 @@ int snd_timer_open(struct snd_timer_instance **ti,
{
struct snd_timer *timer;
struct snd_timer_instance *timeri = NULL;
+ struct device *card_dev_to_put = NULL;
int err;
mutex_lock(®ister_mutex);
@@ -261,7 +263,7 @@ int snd_timer_open(struct snd_timer_instance **ti,
list_add_tail(&timeri->open_list, &snd_timer_slave_list);
err = snd_timer_check_slave(timeri);
if (err < 0) {
- snd_timer_close_locked(timeri);
+ snd_timer_close_locked(timeri, &card_dev_to_put);
timeri = NULL;
}
goto unlock;
@@ -313,7 +315,7 @@ int snd_timer_open(struct snd_timer_instance **ti,
timeri = NULL;
if (timer->card)
- put_device(&timer->card->card_dev);
+ card_dev_to_put = &timer->card->card_dev;
module_put(timer->module);
goto unlock;
}
@@ -323,12 +325,15 @@ int snd_timer_open(struct snd_timer_instance **ti,
timer->num_instances++;
err = snd_timer_check_master(timeri);
if (err < 0) {
- snd_timer_close_locked(timeri);
+ snd_timer_close_locked(timeri, &card_dev_to_put);
timeri = NULL;
}
unlock:
mutex_unlock(®ister_mutex);
+ /* put_device() is called after unlock for avoiding deadlock */
+ if (card_dev_to_put)
+ put_device(card_dev_to_put);
*ti = timeri;
return err;
}
@@ -338,7 +343,8 @@ EXPORT_SYMBOL(snd_timer_open);
* close a timer instance
* call this with register_mutex down.
*/
-static int snd_timer_close_locked(struct snd_timer_instance *timeri)
+static int snd_timer_close_locked(struct snd_timer_instance *timeri,
+ struct device **card_devp_to_put)
{
struct snd_timer *timer = timeri->timer;
struct snd_timer_instance *slave, *tmp;
@@ -395,7 +401,7 @@ static int snd_timer_close_locked(struct snd_timer_instance *timeri)
timer->hw.close(timer);
/* release a card refcount for safe disconnection */
if (timer->card)
- put_device(&timer->card->card_dev);
+ *card_devp_to_put = &timer->card->card_dev;
module_put(timer->module);
}
@@ -407,14 +413,18 @@ static int snd_timer_close_locked(struct snd_timer_instance *timeri)
*/
int snd_timer_close(struct snd_timer_instance *timeri)
{
+ struct device *card_dev_to_put = NULL;
int err;
if (snd_BUG_ON(!timeri))
return -ENXIO;
mutex_lock(®ister_mutex);
- err = snd_timer_close_locked(timeri);
+ err = snd_timer_close_locked(timeri, &card_dev_to_put);
mutex_unlock(®ister_mutex);
+ /* put_device() is called after unlock for avoiding deadlock */
+ if (card_dev_to_put)
+ put_device(card_dev_to_put);
return err;
}
EXPORT_SYMBOL(snd_timer_close);
--
2.16.4
More information about the Alsa-devel
mailing list