From: Juri Lelli <juri.lelli@redhat.com>
mutex::wait_lock might be nested under rq->lock.
Make it irq safe then.
Cc: Joel Fernandes <joelaf@google.com>
Cc: Qais Yousef <qyousef@layalina.io>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Valentin Schneider <vschneid@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Segall <bsegall@google.com>
Cc: Zimuzo Ezeozue <zezeozue@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Will Deacon <will@kernel.org>
Cc: Waiman Long <longman@redhat.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Metin Kaya <Metin.Kaya@arm.com>
Cc: Xuewen Yan <xuewen.yan94@gmail.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: kernel-team@android.com
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: Metin Kaya <metin.kaya@arm.com>
Reviewed-by: Metin Kaya <metin.kaya@arm.com>
Reviewed-by: Valentin Schneider <vschneid@redhat.com>
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
[rebase & fix {un,}lock_wait_lock helpers in ww_mutex.h]
Signed-off-by: Connor O'Brien <connoro@google.com>
Signed-off-by: John Stultz <jstultz@google.com>
---
v3:
* Re-added this patch after it was dropped in v2 which
caused lockdep warnings to trip.
v7:
* Fix function definition for PREEMPT_RT case, as pointed out
by Metin Kaya.
* Fix incorrect flags handling in PREEMPT_RT case as found by
Metin Kaya
---
kernel/locking/mutex.c | 18 ++++++++++--------
kernel/locking/ww_mutex.h | 21 +++++++++++----------
2 files changed, 21 insertions(+), 18 deletions(-)
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 6c94da061ec2..cd248d1767eb 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -578,6 +578,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
DEFINE_WAKE_Q(wake_q);
struct mutex_waiter waiter;
struct ww_mutex *ww;
+ unsigned long flags;
int ret;
if (!use_ww_ctx)
@@ -620,7 +621,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
return 0;
}
- raw_spin_lock(&lock->wait_lock);
+ raw_spin_lock_irqsave(&lock->wait_lock, flags);
/*
* After waiting to acquire the wait_lock, try again.
*/
@@ -681,7 +682,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
goto err;
}
- raw_spin_unlock(&lock->wait_lock);
+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
/* Make sure we do wakeups before calling schedule */
wake_up_q(&wake_q);
wake_q_init(&wake_q);
@@ -706,9 +707,9 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
trace_contention_begin(lock, LCB_F_MUTEX);
}
- raw_spin_lock(&lock->wait_lock);
+ raw_spin_lock_irqsave(&lock->wait_lock, flags);
}
- raw_spin_lock(&lock->wait_lock);
+ raw_spin_lock_irqsave(&lock->wait_lock, flags);
acquired:
__set_current_state(TASK_RUNNING);
@@ -734,7 +735,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
if (ww_ctx)
ww_mutex_lock_acquired(ww, ww_ctx);
- raw_spin_unlock(&lock->wait_lock);
+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
wake_up_q(&wake_q);
preempt_enable();
return 0;
@@ -744,7 +745,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
__mutex_remove_waiter(lock, &waiter);
err_early_kill:
trace_contention_end(lock, ret);
- raw_spin_unlock(&lock->wait_lock);
+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
debug_mutex_free_waiter(&waiter);
mutex_release(&lock->dep_map, ip);
wake_up_q(&wake_q);
@@ -915,6 +916,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
struct task_struct *next = NULL;
DEFINE_WAKE_Q(wake_q);
unsigned long owner;
+ unsigned long flags;
mutex_release(&lock->dep_map, ip);
@@ -941,7 +943,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
}
}
- raw_spin_lock(&lock->wait_lock);
+ raw_spin_lock_irqsave(&lock->wait_lock, flags);
debug_mutex_unlock(lock);
if (!list_empty(&lock->wait_list)) {
/* get the first entry from the wait-list: */
@@ -959,7 +961,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
__mutex_handoff(lock, next);
preempt_disable();
- raw_spin_unlock(&lock->wait_lock);
+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
wake_up_q(&wake_q);
preempt_enable();
}
diff --git a/kernel/locking/ww_mutex.h b/kernel/locking/ww_mutex.h
index a54bd16d0f17..37f025a096c9 100644
--- a/kernel/locking/ww_mutex.h
+++ b/kernel/locking/ww_mutex.h
@@ -70,14 +70,14 @@ __ww_mutex_has_waiters(struct mutex *lock)
return atomic_long_read(&lock->owner) & MUTEX_FLAG_WAITERS;
}
-static inline void lock_wait_lock(struct mutex *lock)
+static inline void lock_wait_lock(struct mutex *lock, unsigned long *flags)
{
- raw_spin_lock(&lock->wait_lock);
+ raw_spin_lock_irqsave(&lock->wait_lock, *flags);
}
-static inline void unlock_wait_lock(struct mutex *lock)
+static inline void unlock_wait_lock(struct mutex *lock, unsigned long *flags)
{
- raw_spin_unlock(&lock->wait_lock);
+ raw_spin_unlock_irqrestore(&lock->wait_lock, *flags);
}
static inline void lockdep_assert_wait_lock_held(struct mutex *lock)
@@ -144,14 +144,14 @@ __ww_mutex_has_waiters(struct rt_mutex *lock)
return rt_mutex_has_waiters(&lock->rtmutex);
}
-static inline void lock_wait_lock(struct rt_mutex *lock)
+static inline void lock_wait_lock(struct rt_mutex *lock, unsigned long *flags)
{
- raw_spin_lock(&lock->rtmutex.wait_lock);
+ raw_spin_lock_irqsave(&lock->rtmutex.wait_lock, *flags);
}
-static inline void unlock_wait_lock(struct rt_mutex *lock)
+static inline void unlock_wait_lock(struct rt_mutex *lock, unsigned long *flags)
{
- raw_spin_unlock(&lock->rtmutex.wait_lock);
+ raw_spin_unlock_irqrestore(&lock->rtmutex.wait_lock, *flags);
}
static inline void lockdep_assert_wait_lock_held(struct rt_mutex *lock)
@@ -380,6 +380,7 @@ static __always_inline void
ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
{
DEFINE_WAKE_Q(wake_q);
+ unsigned long flags;
ww_mutex_lock_acquired(lock, ctx);
@@ -408,10 +409,10 @@ ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
* Uh oh, we raced in fastpath, check if any of the waiters need to
* die or wound us.
*/
- lock_wait_lock(&lock->base);
+ lock_wait_lock(&lock->base, &flags);
__ww_mutex_check_waiters(&lock->base, ctx, &wake_q);
preempt_disable();
- unlock_wait_lock(&lock->base);
+ unlock_wait_lock(&lock->base, &flags);
wake_up_q(&wake_q);
preempt_enable();
}
--
2.47.0.rc0.187.ge670bccf7e-googOn Wed, 9 Oct 2024 16:53:35 -0700 John Stultz <jstultz@google.com> wrote: > From: Juri Lelli <juri.lelli@redhat.com> > > mutex::wait_lock might be nested under rq->lock. > > Make it irq safe then. Can you expand on this please? If the mutex:wait_lock might be taken under an rq->lock, doesn't that mean a mutex was taken under rq->lock? Or is it something internal? This change log needs to be more explicit. -- Steve
On Thu, Oct 10, 2024 at 7:00 AM Steven Rostedt <rostedt@goodmis.org> wrote: > On Wed, 9 Oct 2024 16:53:35 -0700 > John Stultz <jstultz@google.com> wrote: > > > From: Juri Lelli <juri.lelli@redhat.com> > > > > mutex::wait_lock might be nested under rq->lock. > > > > Make it irq safe then. > > Can you expand on this please? > > If the mutex:wait_lock might be taken under an rq->lock, doesn't that mean > a mutex was taken under rq->lock? Or is it something internal? > > This change log needs to be more explicit. Sure! Would the following work for you? "With the proxy-execution series, we traverse the task->mutex->task blocked_on/owner chain in the scheduler core. We do this while holding the rq::lock to keep the structures in place while taking and releasing the alternating lock types. Since the mutex::wait_lock is one of the locks we will take in this way under the rq::lock in the scheduler core, we need to make sure that its usage elsewhere is irq safe." ? Thanks for the feedback! -john
On Thu, 10 Oct 2024 19:26:24 -0700 John Stultz <jstultz@google.com> wrote: > On Thu, Oct 10, 2024 at 7:00 AM Steven Rostedt <rostedt@goodmis.org> wrote: > > On Wed, 9 Oct 2024 16:53:35 -0700 > > John Stultz <jstultz@google.com> wrote: > > > > > From: Juri Lelli <juri.lelli@redhat.com> > > > > > > mutex::wait_lock might be nested under rq->lock. > > > > > > Make it irq safe then. > > > > Can you expand on this please? > > > > If the mutex:wait_lock might be taken under an rq->lock, doesn't that mean > > a mutex was taken under rq->lock? Or is it something internal? > > > > This change log needs to be more explicit. > > Sure! Would the following work for you? > > "With the proxy-execution series, we traverse the task->mutex->task > blocked_on/owner chain in the scheduler core. We do this while holding > the rq::lock to keep the structures in place while taking and > releasing the alternating lock types. > > Since the mutex::wait_lock is one of the locks we will take in this > way under the rq::lock in the scheduler core, we need to make sure > that its usage elsewhere is irq safe." > > ? Yes, that explains things much better. ;-) Thanks! -- Steve
On Thu, Oct 10, 2024 at 10:00:45AM -0400, Steven Rostedt wrote: > On Wed, 9 Oct 2024 16:53:35 -0700 > John Stultz <jstultz@google.com> wrote: > > > From: Juri Lelli <juri.lelli@redhat.com> > > > > mutex::wait_lock might be nested under rq->lock. > > > > Make it irq safe then. > > Can you expand on this please? > > If the mutex:wait_lock might be taken under an rq->lock, doesn't that mean > a mutex was taken under rq->lock? Or is it something internal? Very similar to what we do for rt_mutex during PI; we'll want to look at mutex_owner during the block chain walk, and holding wait_lock ensures objects persistence.
The following commit has been merged into the sched/core branch of tip:
Commit-ID: 5ec58525a1f1bd6ca8ea778e9df55cd82bc02e11
Gitweb: https://git.kernel.org/tip/5ec58525a1f1bd6ca8ea778e9df55cd82bc02e11
Author: Juri Lelli <juri.lelli@redhat.com>
AuthorDate: Wed, 09 Oct 2024 16:53:35 -07:00
Committer: Peter Zijlstra <peterz@infradead.org>
CommitterDate: Mon, 14 Oct 2024 12:52:40 +02:00
locking/mutex: Make mutex::wait_lock irq safe
With the proxy-execution series, we traverse the task->mutex->task
blocked_on/owner chain in the scheduler core. We do this while holding
the rq::lock to keep the structures in place while taking and
releasing the alternating lock types.
Since the mutex::wait_lock is one of the locks we will take in this
way under the rq::lock in the scheduler core, we need to make sure
that its usage elsewhere is irq safe.
[rebase & fix {un,}lock_wait_lock helpers in ww_mutex.h]
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Connor O'Brien <connoro@google.com>
Signed-off-by: John Stultz <jstultz@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Metin Kaya <metin.kaya@arm.com>
Reviewed-by: Valentin Schneider <vschneid@redhat.com>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: Metin Kaya <metin.kaya@arm.com>
Link: https://lore.kernel.org/r/20241009235352.1614323-3-jstultz@google.com
---
kernel/locking/mutex.c | 18 ++++++++++--------
kernel/locking/ww_mutex.h | 21 +++++++++++----------
2 files changed, 21 insertions(+), 18 deletions(-)
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 6c94da0..cd248d1 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -578,6 +578,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
DEFINE_WAKE_Q(wake_q);
struct mutex_waiter waiter;
struct ww_mutex *ww;
+ unsigned long flags;
int ret;
if (!use_ww_ctx)
@@ -620,7 +621,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
return 0;
}
- raw_spin_lock(&lock->wait_lock);
+ raw_spin_lock_irqsave(&lock->wait_lock, flags);
/*
* After waiting to acquire the wait_lock, try again.
*/
@@ -681,7 +682,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
goto err;
}
- raw_spin_unlock(&lock->wait_lock);
+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
/* Make sure we do wakeups before calling schedule */
wake_up_q(&wake_q);
wake_q_init(&wake_q);
@@ -706,9 +707,9 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
trace_contention_begin(lock, LCB_F_MUTEX);
}
- raw_spin_lock(&lock->wait_lock);
+ raw_spin_lock_irqsave(&lock->wait_lock, flags);
}
- raw_spin_lock(&lock->wait_lock);
+ raw_spin_lock_irqsave(&lock->wait_lock, flags);
acquired:
__set_current_state(TASK_RUNNING);
@@ -734,7 +735,7 @@ skip_wait:
if (ww_ctx)
ww_mutex_lock_acquired(ww, ww_ctx);
- raw_spin_unlock(&lock->wait_lock);
+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
wake_up_q(&wake_q);
preempt_enable();
return 0;
@@ -744,7 +745,7 @@ err:
__mutex_remove_waiter(lock, &waiter);
err_early_kill:
trace_contention_end(lock, ret);
- raw_spin_unlock(&lock->wait_lock);
+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
debug_mutex_free_waiter(&waiter);
mutex_release(&lock->dep_map, ip);
wake_up_q(&wake_q);
@@ -915,6 +916,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
struct task_struct *next = NULL;
DEFINE_WAKE_Q(wake_q);
unsigned long owner;
+ unsigned long flags;
mutex_release(&lock->dep_map, ip);
@@ -941,7 +943,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
}
}
- raw_spin_lock(&lock->wait_lock);
+ raw_spin_lock_irqsave(&lock->wait_lock, flags);
debug_mutex_unlock(lock);
if (!list_empty(&lock->wait_list)) {
/* get the first entry from the wait-list: */
@@ -959,7 +961,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
__mutex_handoff(lock, next);
preempt_disable();
- raw_spin_unlock(&lock->wait_lock);
+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
wake_up_q(&wake_q);
preempt_enable();
}
diff --git a/kernel/locking/ww_mutex.h b/kernel/locking/ww_mutex.h
index a54bd16..37f025a 100644
--- a/kernel/locking/ww_mutex.h
+++ b/kernel/locking/ww_mutex.h
@@ -70,14 +70,14 @@ __ww_mutex_has_waiters(struct mutex *lock)
return atomic_long_read(&lock->owner) & MUTEX_FLAG_WAITERS;
}
-static inline void lock_wait_lock(struct mutex *lock)
+static inline void lock_wait_lock(struct mutex *lock, unsigned long *flags)
{
- raw_spin_lock(&lock->wait_lock);
+ raw_spin_lock_irqsave(&lock->wait_lock, *flags);
}
-static inline void unlock_wait_lock(struct mutex *lock)
+static inline void unlock_wait_lock(struct mutex *lock, unsigned long *flags)
{
- raw_spin_unlock(&lock->wait_lock);
+ raw_spin_unlock_irqrestore(&lock->wait_lock, *flags);
}
static inline void lockdep_assert_wait_lock_held(struct mutex *lock)
@@ -144,14 +144,14 @@ __ww_mutex_has_waiters(struct rt_mutex *lock)
return rt_mutex_has_waiters(&lock->rtmutex);
}
-static inline void lock_wait_lock(struct rt_mutex *lock)
+static inline void lock_wait_lock(struct rt_mutex *lock, unsigned long *flags)
{
- raw_spin_lock(&lock->rtmutex.wait_lock);
+ raw_spin_lock_irqsave(&lock->rtmutex.wait_lock, *flags);
}
-static inline void unlock_wait_lock(struct rt_mutex *lock)
+static inline void unlock_wait_lock(struct rt_mutex *lock, unsigned long *flags)
{
- raw_spin_unlock(&lock->rtmutex.wait_lock);
+ raw_spin_unlock_irqrestore(&lock->rtmutex.wait_lock, *flags);
}
static inline void lockdep_assert_wait_lock_held(struct rt_mutex *lock)
@@ -380,6 +380,7 @@ static __always_inline void
ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
{
DEFINE_WAKE_Q(wake_q);
+ unsigned long flags;
ww_mutex_lock_acquired(lock, ctx);
@@ -408,10 +409,10 @@ ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
* Uh oh, we raced in fastpath, check if any of the waiters need to
* die or wound us.
*/
- lock_wait_lock(&lock->base);
+ lock_wait_lock(&lock->base, &flags);
__ww_mutex_check_waiters(&lock->base, ctx, &wake_q);
preempt_disable();
- unlock_wait_lock(&lock->base);
+ unlock_wait_lock(&lock->base, &flags);
wake_up_q(&wake_q);
preempt_enable();
}© 2016 - 2024 Red Hat, Inc.