Skip to contentSkip to conversation

FAILED: patch "[PATCH] locking/rtmutex: Make sure we wake anything on the wake_q" failed to apply to 6.12-stable tree

PATCH New [email protected] 2 participants 2 messages Jul 2 – Jul 6

Subsystems (2)
lore
Share & tools
lore

[email protected]

author maintainer
#0 lore raw

The patch below does not apply to the 6.12-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 <[email protected]>.

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-6.12.y
git checkout FETCH_HEAD
git cherry-pick -x 4a077914578183ec397ad09f7156a357e00e5d72
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<[email protected]>' --in-reply-to '2026070211-activist-immorally-4371@gregkh' --subject-prefix 'PATCH 6.12.y' 'HEAD^..'

Possible dependencies:

thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From 4a077914578183ec397ad09f7156a357e00e5d72 Mon Sep 17 00:00:00 2001
From: John Stultz <[email protected]>
Date: Thu, 12 Dec 2024 14:21:33 -0800
Subject: [PATCH] locking/rtmutex: Make sure we wake anything on the wake_q
when we release the lock->wait_lock

Bert reported seeing occasional boot hangs when running with PREEPT_RT and bisected it down to commit 894d1b3db41c ("locking/mutex: Remove wakeups from under mutex::wait_lock").

It looks like I missed a few spots where we drop the wait_lock and potentially call into schedule without waking up the tasks on the wake_q structure. Since the tasks being woken are ww_mutex tasks they need to be able to run to release the mutex and unblock the task that currently is planning to wake them. Thus we can deadlock.

So make sure we wake the wake_q tasks when we unlock the wait_lock.

kernel/locking/rtmutex.c +16 -2
index e858de203eb6..697a56d3d949 100644
@@ -1292,7 +1292,13 @@ static int __sched task_blocks_on_rt_mutex(struct rt_mutex_base *lock,
 	 */
 	get_task_struct(owner);
 
+	preempt_disable();
 	raw_spin_unlock_irq(&lock->wait_lock);
+	/* wake up any tasks on the wake_q before calling rt_mutex_adjust_prio_chain */
+	wake_up_q(wake_q);
+	wake_q_init(wake_q);
+	preempt_enable();
+
 
 	res = rt_mutex_adjust_prio_chain(owner, chwalk, lock,
 					 next_lock, waiter, task);
@@ -1596,6 +1602,7 @@ static void __sched remove_waiter(struct rt_mutex_base *lock,
  *			 or TASK_UNINTERRUPTIBLE)
  * @timeout:		 the pre-initialized and started timer, or NULL for none
  * @waiter:		 the pre-initialized rt_mutex_waiter
+ * @wake_q:		 wake_q of tasks to wake when we drop the lock->wait_lock
  *
  * Must be called with lock->wait_lock held and interrupts disabled
  */
@@ -1603,7 +1610,8 @@ static int __sched rt_mutex_slowlock_block(struct rt_mutex_base *lock,
 					   struct ww_acquire_ctx *ww_ctx,
 					   unsigned int state,
 					   struct hrtimer_sleeper *timeout,
-					   struct rt_mutex_waiter *waiter)
+					   struct rt_mutex_waiter *waiter,
+					   struct wake_q_head *wake_q)
 	__releases(&lock->wait_lock) __acquires(&lock->wait_lock)
 {
 	struct rt_mutex *rtm = container_of(lock, struct rt_mutex, rtmutex);
@@ -1634,7 +1642,13 @@ static int __sched rt_mutex_slowlock_block(struct rt_mutex_base *lock,
 			owner = rt_mutex_owner(lock);
 		else
 			owner = NULL;
+		preempt_disable();
 		raw_spin_unlock_irq(&lock->wait_lock);
+		if (wake_q) {
+			wake_up_q(wake_q);
+			wake_q_init(wake_q);
+		}
+		preempt_enable();
 
 		if (!owner || !rtmutex_spin_on_owner(lock, waiter, owner))
 			rt_mutex_schedule();
@@ -1708,7 +1722,7 @@ static int __sched __rt_mutex_slowlock(struct rt_mutex_base *lock,
 
 	ret = task_blocks_on_rt_mutex(lock, waiter, current, ww_ctx, chwalk, wake_q);
 	if (likely(!ret))
-		ret = rt_mutex_slowlock_block(lock, ww_ctx, state, NULL, waiter);
+		ret = rt_mutex_slowlock_block(lock, ww_ctx, state, NULL, waiter, wake_q);
 
 	if (likely(!ret)) {
 		/* acquired the lock */
kernel/locking/rtmutex_api.c +1 -1
index 33ea31d6a7b3..191e4720e546 100644
@@ -383,7 +383,7 @@ int __sched rt_mutex_wait_proxy_lock(struct rt_mutex_base *lock,
 	raw_spin_lock_irq(&lock->wait_lock);
 	/* sleep on the mutex */
 	set_current_state(TASK_INTERRUPTIBLE);
-	ret = rt_mutex_slowlock_block(lock, NULL, TASK_INTERRUPTIBLE, to, waiter);
+	ret = rt_mutex_slowlock_block(lock, NULL, TASK_INTERRUPTIBLE, to, waiter, NULL);
 	/*
 	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
 	 * have to fix that up.
maintainer
#1 lore raw

PATCH 1/1 locking/rtmutex: Make sure we wake anything on the wake_q when we release the lock->wait_lock

From: John Stultz <[email protected]>

[ Upstream commit 4a077914578183ec397ad09f7156a357e00e5d72 ]

Bert reported seeing occasional boot hangs when running with PREEPT_RT and bisected it down to commit 894d1b3db41c ("locking/mutex: Remove wakeups from under mutex::wait_lock").

It looks like I missed a few spots where we drop the wait_lock and potentially call into schedule without waking up the tasks on the wake_q structure. Since the tasks being woken are ww_mutex tasks they need to be able to run to release the mutex and unblock the task that currently is planning to wake them. Thus we can deadlock.

So make sure we wake the wake_q tasks when we unlock the wait_lock.

---
 kernel/locking/rtmutex.c     | 18 ++++++++++++++++--
 kernel/locking/rtmutex_api.c |  2 +-
 2 files changed, 17 insertions(+), 3 deletions(-)
kernel/locking/rtmutex.c +16 -2
index 9b4bd06dd9acd8..9e99b9548e0a68 100644
@@ -1292,7 +1292,13 @@ static int __sched task_blocks_on_rt_mutex(struct rt_mutex_base *lock,
 	 */
 	get_task_struct(owner);
 
+	preempt_disable();
 	raw_spin_unlock_irq(&lock->wait_lock);
+	/* wake up any tasks on the wake_q before calling rt_mutex_adjust_prio_chain */
+	wake_up_q(wake_q);
+	wake_q_init(wake_q);
+	preempt_enable();
+
 
 	res = rt_mutex_adjust_prio_chain(owner, chwalk, lock,
 					 next_lock, waiter, task);
@@ -1602,6 +1608,7 @@ static void __sched remove_waiter(struct rt_mutex_base *lock,
  *			 or TASK_UNINTERRUPTIBLE)
  * @timeout:		 the pre-initialized and started timer, or NULL for none
  * @waiter:		 the pre-initialized rt_mutex_waiter
+ * @wake_q:		 wake_q of tasks to wake when we drop the lock->wait_lock
  *
  * Must be called with lock->wait_lock held and interrupts disabled
  */
@@ -1609,7 +1616,8 @@ static int __sched rt_mutex_slowlock_block(struct rt_mutex_base *lock,
 					   struct ww_acquire_ctx *ww_ctx,
 					   unsigned int state,
 					   struct hrtimer_sleeper *timeout,
-					   struct rt_mutex_waiter *waiter)
+					   struct rt_mutex_waiter *waiter,
+					   struct wake_q_head *wake_q)
 {
 	struct rt_mutex *rtm = container_of(lock, struct rt_mutex, rtmutex);
 	struct task_struct *owner;
@@ -1639,7 +1647,13 @@ static int __sched rt_mutex_slowlock_block(struct rt_mutex_base *lock,
 			owner = rt_mutex_owner(lock);
 		else
 			owner = NULL;
+		preempt_disable();
 		raw_spin_unlock_irq(&lock->wait_lock);
+		if (wake_q) {
+			wake_up_q(wake_q);
+			wake_q_init(wake_q);
+		}
+		preempt_enable();
 
 		if (!owner || !rtmutex_spin_on_owner(lock, waiter, owner))
 			rt_mutex_schedule();
@@ -1713,7 +1727,7 @@ static int __sched __rt_mutex_slowlock(struct rt_mutex_base *lock,
 
 	ret = task_blocks_on_rt_mutex(lock, waiter, current, ww_ctx, chwalk, wake_q);
 	if (likely(!ret))
-		ret = rt_mutex_slowlock_block(lock, ww_ctx, state, NULL, waiter);
+		ret = rt_mutex_slowlock_block(lock, ww_ctx, state, NULL, waiter, wake_q);
 
 	if (likely(!ret)) {
 		/* acquired the lock */
kernel/locking/rtmutex_api.c +1 -1
index 091b109acdc5ee..5b438aa71f8729 100644
@@ -383,7 +383,7 @@ int __sched rt_mutex_wait_proxy_lock(struct rt_mutex_base *lock,
 	raw_spin_lock_irq(&lock->wait_lock);
 	/* sleep on the mutex */
 	set_current_state(TASK_INTERRUPTIBLE);
-	ret = rt_mutex_slowlock_block(lock, NULL, TASK_INTERRUPTIBLE, to, waiter);
+	ret = rt_mutex_slowlock_block(lock, NULL, TASK_INTERRUPTIBLE, to, waiter, NULL);
 	/*
 	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
 	 * have to fix that up.
Signature · 1 line
2.53.0