From 912edebe8501a36c6bedcef03bd238ab90a7e060 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 1 Sep 2026 15:54:51 +0200 Subject: [PATCH] futex: Provide rt_mutex_.*_schedule() equivalents for futex scheduling There is rt_mutex_{pre|post}_schedule() around rt_mutex_wait_proxy_lock() to ensure that sched_submit_work()/ sched_update_worker() is invoked before we schedule out and block on rt_mutex while waiting for it become available. The reason is that blocking on rt_mutex assigns a pi_waiter for the PI chain and sched_submit_work() will also assign a pi_waiter if it blocks on lock but a this point we already have a waiter assigned. We can't skip sched_submit_work() entirely because I/O relies on the fact that I/O queue is flushed while it blocks on a sleeping lock. Therefore sched_submit_work() is moved before we block on the lock. Sleeping lock in this context means mutex or rw_semaphore not spinlock_t on PREEMPT_RT. Because the mutex abstraction on PREEMPT_RT uses the same abstraction as the futex proxy lock, the futex code ended up using rt_mutex_{pre|post}_schedule(), too. Using it is/ was just to keep the task_struct::sched_rt_mutex assertion happy. Futex proxy lock is used only in the syscall context of a task. At this point it never got any I/O that needs to be flushed and it can't be a workqueue that needs to notify that it will be scheduled out. Therefore sched_submit_work() does nothing here. By mistake futex_wait_requeue_pi() -> rt_mutex_wait_proxy_lock() did not get the rt_mutex_{pre|post}_schedule() annotation. This was not noticed because in this callchain the lock is (usually) not contended and so rt_mutex_slowlock_block() does not schedule, triggering the assert. Adding rt_mutex_pre_schedule() here looks wrong (as noted by PeterZ) because at this point there is a pi_waiter recorded and invoking sched_submit_work() with a possible lock contention would be wrong. Add rt_mutex_futex_{pre|post}_schedule() which toggles the sched_rt_mutex assert and does not involve sched_submit_work(). Add asserts here to ensure that sched_submit_work() would do nothing. Use it only in futex proxy lock case which is rt_mutex_wait_proxy_lock(). Remove it from futex_lock_pi(). Fixes: d14f9e930b90 ("locking/rtmutex: Use rt_mutex specific scheduler helpers") Reported-by: Yao Kai Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260901135453.3121948-2-bigeasy@linutronix.de Closes: https://lore.kernel.org/all/20260717084922.4153317-2-yaokai34@huawei.com --- include/linux/sched/rt.h | 2 ++ kernel/futex/pi.c | 16 +++------------- kernel/locking/rtmutex_api.c | 2 ++ kernel/sched/core.c | 16 ++++++++++++++++ 4 files changed, 23 insertions(+), 13 deletions(-) diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h index 4e3338103654..922935cc3383 100644 --- a/include/linux/sched/rt.h +++ b/include/linux/sched/rt.h @@ -52,8 +52,10 @@ static inline bool rt_or_dl_task_policy(struct task_struct *tsk) #ifdef CONFIG_RT_MUTEXES extern void rt_mutex_pre_schedule(void); +extern void rt_mutex_futex_pre_schedule(void); extern void rt_mutex_schedule(void); extern void rt_mutex_post_schedule(void); +extern void rt_mutex_futex_post_schedule(void); /* * Must hold either p->pi_lock or task_rq(p)->lock. diff --git a/kernel/futex/pi.c b/kernel/futex/pi.c index 88788e584ec8..98f1b962e59a 100644 --- a/kernel/futex/pi.c +++ b/kernel/futex/pi.c @@ -1070,17 +1070,11 @@ int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int tryl * Caution; releasing @hb in-scope. The hb->lock is still locked * while the reference is dropped. The reference can not be dropped * after the unlock because if a user initiated resize is in progress - * then we might need to wake him. This can not be done after the - * rt_mutex_pre_schedule() invocation. The hb will remain valid because - * the thread, performing resize, will block on hb->lock during - * the requeue. + * then we might need to wake him. The hb will remain valid + * because the thread, performing resize, will block on + * hb->lock during the requeue. */ futex_private_hash_put(no_free_ptr(hbr.fph)); - /* - * Must be done before we enqueue the waiter, here is unfortunately - * under the hb lock, but that *should* work because it does nothing. - */ - rt_mutex_pre_schedule(); rt_mutex_init_waiter(&rt_waiter); @@ -1146,10 +1140,6 @@ int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int tryl * the */ futex_q_lockptr_lock(&q); - /* - * Waiter is unqueued. - */ - rt_mutex_post_schedule(); no_block: /* * Fixup the pi_state owner and possibly acquire the lock if we diff --git a/kernel/locking/rtmutex_api.c b/kernel/locking/rtmutex_api.c index 5d48d64725b1..eb18b094473c 100644 --- a/kernel/locking/rtmutex_api.c +++ b/kernel/locking/rtmutex_api.c @@ -423,6 +423,7 @@ int __sched rt_mutex_wait_proxy_lock(struct rt_mutex_base *lock, { int ret; + rt_mutex_futex_pre_schedule(); raw_spin_lock_irq(&lock->wait_lock); /* sleep on the mutex */ set_current_state(TASK_INTERRUPTIBLE); @@ -433,6 +434,7 @@ int __sched rt_mutex_wait_proxy_lock(struct rt_mutex_base *lock, */ fixup_rt_mutex_waiters(lock, true); raw_spin_unlock_irq(&lock->wait_lock); + rt_mutex_futex_post_schedule(); return ret; } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f78275192036..449ccd871be8 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7637,6 +7637,17 @@ void rt_mutex_pre_schedule(void) sched_submit_work(current); } +/* + * Used within the futex syscall context, skips sched_submit_work() because none + * its work will be done. Asserts ensure that it is indeed the case. + */ +void rt_mutex_futex_pre_schedule(void) +{ + lockdep_assert(!(current->flags & (PF_WQ_WORKER | PF_IO_WORKER))); + lockdep_assert(!current->plug); + lockdep_assert(!fetch_and_set(current->sched_rt_mutex, 1)); +} + void rt_mutex_schedule(void) { lockdep_assert(current->sched_rt_mutex); @@ -7649,6 +7660,11 @@ void rt_mutex_post_schedule(void) lockdep_assert(fetch_and_set(current->sched_rt_mutex, 0)); } +void rt_mutex_futex_post_schedule(void) +{ + lockdep_assert(fetch_and_set(current->sched_rt_mutex, 0)); +} + /* * rt_mutex_setprio - set the current priority of a task * @p: task to boost