* [PATCH v21 1/6] locking: Add task::blocked_lock to serialize blocked_on state
2025-08-18 22:12 [PATCH v21 0/6] Donor Migration for Proxy Execution (v21) John Stultz
@ 2025-08-18 22:12 ` John Stultz
2025-08-18 22:12 ` [PATCH v21 2/6] sched/locking: Add blocked_on_state to provide necessary tri-state for proxy return-migration John Stultz
` (4 subsequent siblings)
5 siblings, 0 replies; 7+ messages in thread
From: John Stultz @ 2025-08-18 22:12 UTC (permalink / raw)
To: LKML
Cc: John Stultz, Joel Fernandes, Qais Yousef, Ingo Molnar,
Peter Zijlstra, Juri Lelli, Vincent Guittot, Dietmar Eggemann,
Valentin Schneider, Steven Rostedt, Ben Segall, Zimuzo Ezeozue,
Mel Gorman, Will Deacon, Waiman Long, Boqun Feng,
Paul E. McKenney, Metin Kaya, Xuewen Yan, K Prateek Nayak,
Thomas Gleixner, Daniel Lezcano, Suleiman Souhlal, kuyo chang,
hupu, kernel-team
So far, we have been able to utilize the mutex::wait_lock
for serializing the blocked_on state, but when we move to
proxying across runqueues, we will need to add more state
and a way to serialize changes to this state in contexts
where we don't hold the mutex::wait_lock.
So introduce the task::blocked_lock, which nests under the
mutex::wait_lock in the locking order, and rework the locking
to use it.
Signed-off-by: John Stultz <jstultz@google.com>
---
v15:
* Split back out into later in the series
v16:
* Fixups to mark tasks unblocked before sleeping in
mutex_optimistic_spin()
* Rework to use guard() as suggested by Peter
v19:
* Rework logic for PREEMPT_RT issues reported by
K Prateek Nayak
v21:
* After recently thinking more on ww_mutex code, I
reworked the blocked_lock usage in mutex lock to
avoid having to take nested locks in the ww_mutex
paths, as I was concerned the lock ordering
constraints weren't as strong as I had previously
thought.
Cc: Joel Fernandes <joelagnelf@nvidia.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: Suleiman Souhlal <suleiman@google.com>
Cc: kuyo chang <kuyo.chang@mediatek.com>
Cc: hupu <hupu.gm@gmail.com>
Cc: kernel-team@android.com
---
include/linux/sched.h | 52 +++++++++++++++---------------------
init/init_task.c | 1 +
kernel/fork.c | 1 +
kernel/locking/mutex-debug.c | 4 +--
kernel/locking/mutex.c | 37 +++++++++++++++----------
kernel/locking/ww_mutex.h | 4 +--
kernel/sched/core.c | 4 ++-
7 files changed, 54 insertions(+), 49 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index f8188b8333503..3ec0ef0d91603 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1235,6 +1235,7 @@ struct task_struct {
#endif
struct mutex *blocked_on; /* lock we're blocked on */
+ raw_spinlock_t blocked_lock;
#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
/*
@@ -2143,57 +2144,48 @@ extern int __cond_resched_rwlock_write(rwlock_t *lock);
#ifndef CONFIG_PREEMPT_RT
static inline struct mutex *__get_task_blocked_on(struct task_struct *p)
{
- struct mutex *m = p->blocked_on;
+ lockdep_assert_held_once(&p->blocked_lock);
+ return p->blocked_on;
+}
- if (m)
- lockdep_assert_held_once(&m->wait_lock);
- return m;
+static inline struct mutex *get_task_blocked_on(struct task_struct *p)
+{
+ guard(raw_spinlock_irqsave)(&p->blocked_lock);
+ return __get_task_blocked_on(p);
}
static inline void __set_task_blocked_on(struct task_struct *p, struct mutex *m)
{
- struct mutex *blocked_on = READ_ONCE(p->blocked_on);
-
WARN_ON_ONCE(!m);
/* The task should only be setting itself as blocked */
WARN_ON_ONCE(p != current);
- /* Currently we serialize blocked_on under the mutex::wait_lock */
- lockdep_assert_held_once(&m->wait_lock);
+ /* Currently we serialize blocked_on under the task::blocked_lock */
+ lockdep_assert_held_once(&p->blocked_lock);
/*
* Check ensure we don't overwrite existing mutex value
* with a different mutex. Note, setting it to the same
* lock repeatedly is ok.
*/
- WARN_ON_ONCE(blocked_on && blocked_on != m);
- WRITE_ONCE(p->blocked_on, m);
-}
-
-static inline void set_task_blocked_on(struct task_struct *p, struct mutex *m)
-{
- guard(raw_spinlock_irqsave)(&m->wait_lock);
- __set_task_blocked_on(p, m);
+ WARN_ON_ONCE(p->blocked_on && p->blocked_on != m);
+ p->blocked_on = m;
}
static inline void __clear_task_blocked_on(struct task_struct *p, struct mutex *m)
{
- if (m) {
- struct mutex *blocked_on = READ_ONCE(p->blocked_on);
-
- /* Currently we serialize blocked_on under the mutex::wait_lock */
- lockdep_assert_held_once(&m->wait_lock);
- /*
- * There may be cases where we re-clear already cleared
- * blocked_on relationships, but make sure we are not
- * clearing the relationship with a different lock.
- */
- WARN_ON_ONCE(blocked_on && blocked_on != m);
- }
- WRITE_ONCE(p->blocked_on, NULL);
+ /* Currently we serialize blocked_on under the task::blocked_lock */
+ lockdep_assert_held_once(&p->blocked_lock);
+ /*
+ * There may be cases where we re-clear already cleared
+ * blocked_on relationships, but make sure we are not
+ * clearing the relationship with a different lock.
+ */
+ WARN_ON_ONCE(m && p->blocked_on && p->blocked_on != m);
+ p->blocked_on = NULL;
}
static inline void clear_task_blocked_on(struct task_struct *p, struct mutex *m)
{
- guard(raw_spinlock_irqsave)(&m->wait_lock);
+ guard(raw_spinlock_irqsave)(&p->blocked_lock);
__clear_task_blocked_on(p, m);
}
#else
diff --git a/init/init_task.c b/init/init_task.c
index e557f622bd906..7e29d86153d9f 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -140,6 +140,7 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = {
.journal_info = NULL,
INIT_CPU_TIMERS(init_task)
.pi_lock = __RAW_SPIN_LOCK_UNLOCKED(init_task.pi_lock),
+ .blocked_lock = __RAW_SPIN_LOCK_UNLOCKED(init_task.blocked_lock),
.timer_slack_ns = 50000, /* 50 usec default slack */
.thread_pid = &init_struct_pid,
.thread_node = LIST_HEAD_INIT(init_signals.thread_head),
diff --git a/kernel/fork.c b/kernel/fork.c
index af673856499dc..db6d08946ec11 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2030,6 +2030,7 @@ __latent_entropy struct task_struct *copy_process(
ftrace_graph_init_task(p);
rt_mutex_init_task(p);
+ raw_spin_lock_init(&p->blocked_lock);
lockdep_assert_irqs_enabled();
#ifdef CONFIG_PROVE_LOCKING
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 949103fd8e9b5..1d8cff71f65e1 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -54,13 +54,13 @@ void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
lockdep_assert_held(&lock->wait_lock);
/* Current thread can't be already blocked (since it's executing!) */
- DEBUG_LOCKS_WARN_ON(__get_task_blocked_on(task));
+ DEBUG_LOCKS_WARN_ON(get_task_blocked_on(task));
}
void debug_mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
struct task_struct *task)
{
- struct mutex *blocked_on = __get_task_blocked_on(task);
+ struct mutex *blocked_on = get_task_blocked_on(task);
DEBUG_LOCKS_WARN_ON(list_empty(&waiter->list));
DEBUG_LOCKS_WARN_ON(waiter->task != task);
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index de7d6702cd96c..fac40c456098e 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -640,6 +640,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
goto err_early_kill;
}
+ raw_spin_lock(¤t->blocked_lock);
__set_task_blocked_on(current, lock);
set_current_state(state);
trace_contention_begin(lock, LCB_F_MUTEX);
@@ -653,8 +654,9 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
* the handoff.
*/
if (__mutex_trylock(lock))
- goto acquired;
+ break;
+ raw_spin_unlock(¤t->blocked_lock);
/*
* Check for signals and kill conditions while holding
* wait_lock. This ensures the lock cancellation is ordered
@@ -677,12 +679,14 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
first = __mutex_waiter_is_first(lock, &waiter);
+ raw_spin_lock_irqsave(&lock->wait_lock, flags);
+ raw_spin_lock(¤t->blocked_lock);
/*
* As we likely have been woken up by task
* that has cleared our blocked_on state, re-set
* it to the lock we are trying to acquire.
*/
- set_task_blocked_on(current, lock);
+ __set_task_blocked_on(current, lock);
set_current_state(state);
/*
* Here we order against unlock; we must either see it change
@@ -693,25 +697,30 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
break;
if (first) {
- trace_contention_begin(lock, LCB_F_MUTEX | LCB_F_SPIN);
+ bool opt_acquired;
+
/*
* mutex_optimistic_spin() can call schedule(), so
- * clear blocked on so we don't become unselectable
+ * we need to release these locks before calling it,
+ * and clear blocked on so we don't become unselectable
* to run.
*/
- clear_task_blocked_on(current, lock);
- if (mutex_optimistic_spin(lock, ww_ctx, &waiter))
+ __clear_task_blocked_on(current, lock);
+ raw_spin_unlock(¤t->blocked_lock);
+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
+ trace_contention_begin(lock, LCB_F_MUTEX | LCB_F_SPIN);
+ opt_acquired = mutex_optimistic_spin(lock, ww_ctx, &waiter);
+ raw_spin_lock_irqsave(&lock->wait_lock, flags);
+ raw_spin_lock(¤t->blocked_lock);
+ __set_task_blocked_on(current, lock);
+ if (opt_acquired)
break;
- set_task_blocked_on(current, lock);
trace_contention_begin(lock, LCB_F_MUTEX);
}
-
- raw_spin_lock_irqsave(&lock->wait_lock, flags);
}
- raw_spin_lock_irqsave(&lock->wait_lock, flags);
-acquired:
__clear_task_blocked_on(current, lock);
__set_current_state(TASK_RUNNING);
+ raw_spin_unlock(¤t->blocked_lock);
if (ww_ctx) {
/*
@@ -740,11 +749,11 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
return 0;
err:
- __clear_task_blocked_on(current, lock);
+ clear_task_blocked_on(current, lock);
__set_current_state(TASK_RUNNING);
__mutex_remove_waiter(lock, &waiter);
err_early_kill:
- WARN_ON(__get_task_blocked_on(current));
+ WARN_ON(get_task_blocked_on(current));
trace_contention_end(lock, ret);
raw_spin_unlock_irqrestore_wake(&lock->wait_lock, flags, &wake_q);
debug_mutex_free_waiter(&waiter);
@@ -955,7 +964,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
next = waiter->task;
debug_mutex_wake_waiter(lock, waiter);
- __clear_task_blocked_on(next, lock);
+ clear_task_blocked_on(next, lock);
wake_q_add(&wake_q, next);
}
diff --git a/kernel/locking/ww_mutex.h b/kernel/locking/ww_mutex.h
index 31a785afee6c0..e4a81790ea7dd 100644
--- a/kernel/locking/ww_mutex.h
+++ b/kernel/locking/ww_mutex.h
@@ -289,7 +289,7 @@ __ww_mutex_die(struct MUTEX *lock, struct MUTEX_WAITER *waiter,
* blocked_on pointer. Otherwise we can see circular
* blocked_on relationships that can't resolve.
*/
- __clear_task_blocked_on(waiter->task, lock);
+ clear_task_blocked_on(waiter->task, lock);
wake_q_add(wake_q, waiter->task);
}
@@ -347,7 +347,7 @@ static bool __ww_mutex_wound(struct MUTEX *lock,
* are waking the mutex owner, who may be currently
* blocked on a different mutex.
*/
- __clear_task_blocked_on(owner, NULL);
+ clear_task_blocked_on(owner, NULL);
wake_q_add(wake_q, owner);
}
return true;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index be00629f0ba4c..0180853dd48c5 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6639,6 +6639,7 @@ static struct task_struct *proxy_deactivate(struct rq *rq, struct task_struct *d
* p->pi_lock
* rq->lock
* mutex->wait_lock
+ * p->blocked_lock
*
* Returns the task that is going to be used as execution context (the one
* that is actually going to be run on cpu_of(rq)).
@@ -6662,8 +6663,9 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)
* and ensure @owner sticks around.
*/
guard(raw_spinlock)(&mutex->wait_lock);
+ guard(raw_spinlock)(&p->blocked_lock);
- /* Check again that p is blocked with wait_lock held */
+ /* Check again that p is blocked with blocked_lock held */
if (mutex != __get_task_blocked_on(p)) {
/*
* Something changed in the blocked_on chain and
--
2.51.0.rc1.167.g924127e9c0-goog
^ permalink raw reply related [flat|nested] 7+ messages in thread* [PATCH v21 2/6] sched/locking: Add blocked_on_state to provide necessary tri-state for proxy return-migration
2025-08-18 22:12 [PATCH v21 0/6] Donor Migration for Proxy Execution (v21) John Stultz
2025-08-18 22:12 ` [PATCH v21 1/6] locking: Add task::blocked_lock to serialize blocked_on state John Stultz
@ 2025-08-18 22:12 ` John Stultz
2025-08-18 22:12 ` [PATCH v21 3/6] sched: Add logic to zap balance callbacks if we pick again John Stultz
` (3 subsequent siblings)
5 siblings, 0 replies; 7+ messages in thread
From: John Stultz @ 2025-08-18 22:12 UTC (permalink / raw)
To: LKML
Cc: John Stultz, Joel Fernandes, Qais Yousef, Ingo Molnar,
Peter Zijlstra, Juri Lelli, Vincent Guittot, Dietmar Eggemann,
Valentin Schneider, Steven Rostedt, Ben Segall, Zimuzo Ezeozue,
Mel Gorman, Will Deacon, Waiman Long, Boqun Feng,
Paul E. McKenney, Metin Kaya, Xuewen Yan, K Prateek Nayak,
Thomas Gleixner, Daniel Lezcano, Suleiman Souhlal, kuyo chang,
hupu, kernel-team
As we add functionality to proxy execution, we may migrate a
donor task to a runqueue where it can't run due to cpu affinity.
Thus, we must be careful to ensure we return-migrate the task
back to a cpu in its cpumask when it becomes unblocked.
Thus we need more then just a binary concept of the task being
blocked on a mutex or not.
So add a blocked_on_state value to the task, that allows the
task to move through BO_RUNNING -> BO_BLOCKED -> BO_WAKING
and back to BO_RUNNING. This provides a guard state in
BO_WAKING so we can know the task is no longer blocked
but we don't want to run it until we have potentially
done return migration, back to a usable cpu.
Signed-off-by: John Stultz <jstultz@google.com>
---
v15:
* Split blocked_on_state into its own patch later in the
series, as the tri-state isn't necessary until we deal
with proxy/return migrations
v16:
* Handle case where task in the chain is being set as
BO_WAKING by another cpu (usually via ww_mutex die code).
Make sure we release the rq lock so the wakeup can
complete.
* Rework to use guard() in find_proxy_task() as suggested
by Peter
v18:
* Add initialization of blocked_on_state for init_task
v19:
* PREEMPT_RT build fixups and rework suggested by
K Prateek Nayak
v20:
* Simplify one of the blocked_on_state changes to avoid extra
PREMEPT_RT conditionals
v21:
* Slight reworks due to avoiding nested blocked_lock locking
* Be consistent in use of blocked_on_state helper functions
* Rework calls to proxy_deactivate() to do proper locking
around blocked_on_state changes that we were cheating in
previous versions.
* Minor cleanups, some comment improvements
Cc: Joel Fernandes <joelagnelf@nvidia.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: Suleiman Souhlal <suleiman@google.com>
Cc: kuyo chang <kuyo.chang@mediatek.com>
Cc: hupu <hupu.gm@gmail.com>
Cc: kernel-team@android.com
---
include/linux/sched.h | 80 +++++++++++++++++++++++++++++----------
init/init_task.c | 1 +
kernel/fork.c | 1 +
kernel/locking/mutex.c | 15 ++++----
kernel/locking/ww_mutex.h | 20 ++++------
kernel/sched/core.c | 44 +++++++++++++++++++--
kernel/sched/sched.h | 2 +-
7 files changed, 120 insertions(+), 43 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 3ec0ef0d91603..5801de1a44a79 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -815,6 +815,12 @@ struct kmap_ctrl {
#endif
};
+enum blocked_on_state {
+ BO_RUNNABLE,
+ BO_BLOCKED,
+ BO_WAKING,
+};
+
struct task_struct {
#ifdef CONFIG_THREAD_INFO_IN_TASK
/*
@@ -1234,6 +1240,7 @@ struct task_struct {
struct rt_mutex_waiter *pi_blocked_on;
#endif
+ enum blocked_on_state blocked_on_state;
struct mutex *blocked_on; /* lock we're blocked on */
raw_spinlock_t blocked_lock;
@@ -2141,7 +2148,52 @@ extern int __cond_resched_rwlock_write(rwlock_t *lock);
__cond_resched_rwlock_write(lock); \
})
-#ifndef CONFIG_PREEMPT_RT
+static inline void __force_blocked_on_runnable(struct task_struct *p)
+{
+ lockdep_assert_held(&p->blocked_lock);
+ p->blocked_on_state = BO_RUNNABLE;
+}
+
+static inline void force_blocked_on_runnable(struct task_struct *p)
+{
+ guard(raw_spinlock_irqsave)(&p->blocked_lock);
+ __force_blocked_on_runnable(p);
+}
+
+static inline void __force_blocked_on_blocked(struct task_struct *p)
+{
+ lockdep_assert_held(&p->blocked_lock);
+ p->blocked_on_state = BO_BLOCKED;
+}
+
+static inline void __set_blocked_on_runnable(struct task_struct *p)
+{
+ lockdep_assert_held(&p->blocked_lock);
+ if (p->blocked_on_state == BO_WAKING)
+ p->blocked_on_state = BO_RUNNABLE;
+}
+
+static inline void set_blocked_on_runnable(struct task_struct *p)
+{
+ if (!sched_proxy_exec())
+ return;
+ guard(raw_spinlock_irqsave)(&p->blocked_lock);
+ __set_blocked_on_runnable(p);
+}
+
+static inline void __set_blocked_on_waking(struct task_struct *p)
+{
+ lockdep_assert_held(&p->blocked_lock);
+ if (p->blocked_on_state == BO_BLOCKED)
+ p->blocked_on_state = BO_WAKING;
+}
+
+static inline void set_blocked_on_waking(struct task_struct *p)
+{
+ guard(raw_spinlock_irqsave)(&p->blocked_lock);
+ __set_blocked_on_waking(p);
+}
+
static inline struct mutex *__get_task_blocked_on(struct task_struct *p)
{
lockdep_assert_held_once(&p->blocked_lock);
@@ -2163,24 +2215,23 @@ static inline void __set_task_blocked_on(struct task_struct *p, struct mutex *m)
lockdep_assert_held_once(&p->blocked_lock);
/*
* Check ensure we don't overwrite existing mutex value
- * with a different mutex. Note, setting it to the same
- * lock repeatedly is ok.
+ * with a different mutex.
*/
- WARN_ON_ONCE(p->blocked_on && p->blocked_on != m);
+ WARN_ON_ONCE(p->blocked_on);
p->blocked_on = m;
+ p->blocked_on_state = BO_BLOCKED;
}
static inline void __clear_task_blocked_on(struct task_struct *p, struct mutex *m)
{
+ /* The task should only be clearing itself */
+ WARN_ON_ONCE(p != current);
/* Currently we serialize blocked_on under the task::blocked_lock */
lockdep_assert_held_once(&p->blocked_lock);
- /*
- * There may be cases where we re-clear already cleared
- * blocked_on relationships, but make sure we are not
- * clearing the relationship with a different lock.
- */
- WARN_ON_ONCE(m && p->blocked_on && p->blocked_on != m);
+ /* Make sure we are clearing the relationship with the right lock */
+ WARN_ON_ONCE(m && p->blocked_on != m);
p->blocked_on = NULL;
+ p->blocked_on_state = BO_RUNNABLE;
}
static inline void clear_task_blocked_on(struct task_struct *p, struct mutex *m)
@@ -2188,15 +2239,6 @@ static inline void clear_task_blocked_on(struct task_struct *p, struct mutex *m)
guard(raw_spinlock_irqsave)(&p->blocked_lock);
__clear_task_blocked_on(p, m);
}
-#else
-static inline void __clear_task_blocked_on(struct task_struct *p, struct rt_mutex *m)
-{
-}
-
-static inline void clear_task_blocked_on(struct task_struct *p, struct rt_mutex *m)
-{
-}
-#endif /* !CONFIG_PREEMPT_RT */
static __always_inline bool need_resched(void)
{
diff --git a/init/init_task.c b/init/init_task.c
index 7e29d86153d9f..6d72ec23410a6 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -174,6 +174,7 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = {
.mems_allowed_seq = SEQCNT_SPINLOCK_ZERO(init_task.mems_allowed_seq,
&init_task.alloc_lock),
#endif
+ .blocked_on_state = BO_RUNNABLE,
#ifdef CONFIG_RT_MUTEXES
.pi_waiters = RB_ROOT_CACHED,
.pi_top_task = NULL,
diff --git a/kernel/fork.c b/kernel/fork.c
index db6d08946ec11..4bd0731995e86 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2129,6 +2129,7 @@ __latent_entropy struct task_struct *copy_process(
lockdep_init_task(p);
#endif
+ p->blocked_on_state = BO_RUNNABLE;
p->blocked_on = NULL; /* not blocked yet */
#ifdef CONFIG_BCACHE
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index fac40c456098e..42e4d2e6e4ad4 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -682,11 +682,9 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
raw_spin_lock_irqsave(&lock->wait_lock, flags);
raw_spin_lock(¤t->blocked_lock);
/*
- * As we likely have been woken up by task
- * that has cleared our blocked_on state, re-set
- * it to the lock we are trying to acquire.
+ * Re-set blocked_on_state as unlock path set it to WAKING/RUNNABLE
*/
- __set_task_blocked_on(current, lock);
+ __force_blocked_on_blocked(current);
set_current_state(state);
/*
* Here we order against unlock; we must either see it change
@@ -705,14 +703,14 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
* and clear blocked on so we don't become unselectable
* to run.
*/
- __clear_task_blocked_on(current, lock);
+ __force_blocked_on_runnable(current);
raw_spin_unlock(¤t->blocked_lock);
raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
trace_contention_begin(lock, LCB_F_MUTEX | LCB_F_SPIN);
opt_acquired = mutex_optimistic_spin(lock, ww_ctx, &waiter);
raw_spin_lock_irqsave(&lock->wait_lock, flags);
raw_spin_lock(¤t->blocked_lock);
- __set_task_blocked_on(current, lock);
+ __force_blocked_on_blocked(current);
if (opt_acquired)
break;
trace_contention_begin(lock, LCB_F_MUTEX);
@@ -963,8 +961,11 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
next = waiter->task;
+ raw_spin_lock(&next->blocked_lock);
debug_mutex_wake_waiter(lock, waiter);
- clear_task_blocked_on(next, lock);
+ WARN_ON_ONCE(__get_task_blocked_on(next) != lock);
+ __set_blocked_on_waking(next);
+ raw_spin_unlock(&next->blocked_lock);
wake_q_add(&wake_q, next);
}
diff --git a/kernel/locking/ww_mutex.h b/kernel/locking/ww_mutex.h
index e4a81790ea7dd..f34363615eb34 100644
--- a/kernel/locking/ww_mutex.h
+++ b/kernel/locking/ww_mutex.h
@@ -285,11 +285,11 @@ __ww_mutex_die(struct MUTEX *lock, struct MUTEX_WAITER *waiter,
debug_mutex_wake_waiter(lock, waiter);
#endif
/*
- * When waking up the task to die, be sure to clear the
- * blocked_on pointer. Otherwise we can see circular
- * blocked_on relationships that can't resolve.
+ * When waking up the task to die, be sure to set the
+ * blocked_on_state to BO_WAKING. Otherwise we can see
+ * circular blocked_on relationships that can't resolve.
*/
- clear_task_blocked_on(waiter->task, lock);
+ set_blocked_on_waking(waiter->task);
wake_q_add(wake_q, waiter->task);
}
@@ -339,15 +339,11 @@ static bool __ww_mutex_wound(struct MUTEX *lock,
*/
if (owner != current) {
/*
- * When waking up the task to wound, be sure to clear the
- * blocked_on pointer. Otherwise we can see circular
- * blocked_on relationships that can't resolve.
- *
- * NOTE: We pass NULL here instead of lock, because we
- * are waking the mutex owner, who may be currently
- * blocked on a different mutex.
+ * When waking up the task to wound, be sure to set the
+ * blocked_on_state to BO_WAKING. Otherwise we can see
+ * circular blocked_on relationships that can't resolve.
*/
- clear_task_blocked_on(owner, NULL);
+ set_blocked_on_waking(owner);
wake_q_add(wake_q, owner);
}
return true;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0180853dd48c5..e0007660161fa 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4328,6 +4328,12 @@ int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
ttwu_queue(p, cpu, wake_flags);
}
out:
+ /*
+ * For now, if we've been woken up, set us as BO_RUNNABLE
+ * We will need to be more careful later when handling
+ * proxy migration
+ */
+ set_blocked_on_runnable(p);
if (success)
ttwu_stat(p, task_cpu(p), wake_flags);
@@ -6623,7 +6629,7 @@ static struct task_struct *proxy_deactivate(struct rq *rq, struct task_struct *d
* as unblocked, as we aren't doing proxy-migrations
* yet (more logic will be needed then).
*/
- donor->blocked_on = NULL;
+ force_blocked_on_runnable(donor);
}
return NULL;
}
@@ -6676,20 +6682,41 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)
return NULL;
}
+ /*
+ * If a ww_mutex hits the die/wound case, it marks the task as
+ * BO_WAKING and calls try_to_wake_up(), so that the mutex
+ * cycle can be broken and we avoid a deadlock.
+ *
+ * However, if at that moment, we are here on the cpu which the
+ * die/wounded task is enqueued, we might loop on the cycle as
+ * BO_WAKING still causes task_is_blocked() to return true
+ * (since we want return migration to occur before we run the
+ * task).
+ *
+ * Unfortunately since we hold the rq lock, it will block
+ * try_to_wake_up from completing and doing the return
+ * migration.
+ *
+ * So when we hit a !BO_BLOCKED task briefly schedule idle
+ * so we release the rq and let the wakeup complete.
+ */
+ if (p->blocked_on_state != BO_BLOCKED)
+ return proxy_resched_idle(rq);
+
owner = __mutex_owner(mutex);
if (!owner) {
- __clear_task_blocked_on(p, mutex);
+ __force_blocked_on_runnable(p);
return p;
}
if (!READ_ONCE(owner->on_rq) || owner->se.sched_delayed) {
/* XXX Don't handle blocked owners/delayed dequeue yet */
- return proxy_deactivate(rq, donor);
+ goto deactivate_donor;
}
if (task_cpu(owner) != this_cpu) {
/* XXX Don't handle migrations yet */
- return proxy_deactivate(rq, donor);
+ goto deactivate_donor;
}
if (task_on_rq_migrating(owner)) {
@@ -6749,6 +6776,15 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)
WARN_ON_ONCE(owner && !owner->on_rq);
return owner;
+
+ /*
+ * NOTE: This logic is down here, because we need to call
+ * the functions with the mutex wait_lock and task
+ * blocked_lock released, so we have to get out of the
+ * guard() scope.
+ */
+deactivate_donor:
+ return proxy_deactivate(rq, donor);
}
#else /* SCHED_PROXY_EXEC */
static struct task_struct *
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index be9745d104f75..845454ec81a22 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2264,7 +2264,7 @@ static inline bool task_is_blocked(struct task_struct *p)
if (!sched_proxy_exec())
return false;
- return !!p->blocked_on;
+ return !!p->blocked_on && p->blocked_on_state != BO_RUNNABLE;
}
static inline int task_on_cpu(struct rq *rq, struct task_struct *p)
--
2.51.0.rc1.167.g924127e9c0-goog
^ permalink raw reply related [flat|nested] 7+ messages in thread* [PATCH v21 3/6] sched: Add logic to zap balance callbacks if we pick again
2025-08-18 22:12 [PATCH v21 0/6] Donor Migration for Proxy Execution (v21) John Stultz
2025-08-18 22:12 ` [PATCH v21 1/6] locking: Add task::blocked_lock to serialize blocked_on state John Stultz
2025-08-18 22:12 ` [PATCH v21 2/6] sched/locking: Add blocked_on_state to provide necessary tri-state for proxy return-migration John Stultz
@ 2025-08-18 22:12 ` John Stultz
2025-08-18 22:12 ` [PATCH v21 4/6] sched: Handle blocked-waiter migration (and return migration) John Stultz
` (2 subsequent siblings)
5 siblings, 0 replies; 7+ messages in thread
From: John Stultz @ 2025-08-18 22:12 UTC (permalink / raw)
To: LKML
Cc: John Stultz, Joel Fernandes, Qais Yousef, Ingo Molnar,
Peter Zijlstra, Juri Lelli, Vincent Guittot, Dietmar Eggemann,
Valentin Schneider, Steven Rostedt, Ben Segall, Zimuzo Ezeozue,
Mel Gorman, Will Deacon, Waiman Long, Boqun Feng,
Paul E. McKenney, Metin Kaya, Xuewen Yan, K Prateek Nayak,
Thomas Gleixner, Daniel Lezcano, Suleiman Souhlal, kuyo chang,
hupu, kernel-team
With proxy-exec, a task is selected to run via pick_next_task(),
and then if it is a mutex blocked task, we call find_proxy_task()
to find a runnable owner. If the runnable owner is on another
cpu, we will need to migrate the selected donor task away, after
which we will pick_again can call pick_next_task() to choose
something else.
However, in the first call to pick_next_task(), we may have
had a balance_callback setup by the class scheduler. After we
pick again, its possible pick_next_task_fair() will be called
which calls sched_balance_newidle() and sched_balance_rq().
This will throw a warning:
[ 8.796467] rq->balance_callback && rq->balance_callback != &balance_push_callback
[ 8.796467] WARNING: CPU: 32 PID: 458 at kernel/sched/sched.h:1750 sched_balance_rq+0xe92/0x1250
...
[ 8.796467] Call Trace:
[ 8.796467] <TASK>
[ 8.796467] ? __warn.cold+0xb2/0x14e
[ 8.796467] ? sched_balance_rq+0xe92/0x1250
[ 8.796467] ? report_bug+0x107/0x1a0
[ 8.796467] ? handle_bug+0x54/0x90
[ 8.796467] ? exc_invalid_op+0x17/0x70
[ 8.796467] ? asm_exc_invalid_op+0x1a/0x20
[ 8.796467] ? sched_balance_rq+0xe92/0x1250
[ 8.796467] sched_balance_newidle+0x295/0x820
[ 8.796467] pick_next_task_fair+0x51/0x3f0
[ 8.796467] __schedule+0x23a/0x14b0
[ 8.796467] ? lock_release+0x16d/0x2e0
[ 8.796467] schedule+0x3d/0x150
[ 8.796467] worker_thread+0xb5/0x350
[ 8.796467] ? __pfx_worker_thread+0x10/0x10
[ 8.796467] kthread+0xee/0x120
[ 8.796467] ? __pfx_kthread+0x10/0x10
[ 8.796467] ret_from_fork+0x31/0x50
[ 8.796467] ? __pfx_kthread+0x10/0x10
[ 8.796467] ret_from_fork_asm+0x1a/0x30
[ 8.796467] </TASK>
This is because if a RT task was originally picked, it will
setup the rq->balance_callback with push_rt_tasks() via
set_next_task_rt().
Once the task is migrated away and we pick again, we haven't
processed any balance callbacks, so rq->balance_callback is not
in the same state as it was the first time pick_next_task was
called.
To handle this, add a zap_balance_callbacks() helper function
which cleans up the blance callbacks without running them. This
should be ok, as we are effectively undoing the state set in
the first call to pick_next_task(), and when we pick again,
the new callback can be configured for the donor task actually
selected.
Signed-off-by: John Stultz <jstultz@google.com>
---
v20:
* Tweaked to avoid build issues with different configs
Cc: Joel Fernandes <joelagnelf@nvidia.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: Suleiman Souhlal <suleiman@google.com>
Cc: kuyo chang <kuyo.chang@mediatek.com>
Cc: hupu <hupu.gm@gmail.com>
Cc: kernel-team@android.com
---
kernel/sched/core.c | 39 ++++++++++++++++++++++++++++++++++++++-
1 file changed, 38 insertions(+), 1 deletion(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e0007660161fa..01bf5ef8d9fcc 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5001,6 +5001,40 @@ static inline void finish_task(struct task_struct *prev)
smp_store_release(&prev->on_cpu, 0);
}
+#if defined(CONFIG_SCHED_PROXY_EXEC)
+/*
+ * Only called from __schedule context
+ *
+ * There are some cases where we are going to re-do the action
+ * that added the balance callbacks. We may not be in a state
+ * where we can run them, so just zap them so they can be
+ * properly re-added on the next time around. This is similar
+ * handling to running the callbacks, except we just don't call
+ * them.
+ */
+static void zap_balance_callbacks(struct rq *rq)
+{
+ struct balance_callback *next, *head;
+ bool found = false;
+
+ lockdep_assert_rq_held(rq);
+
+ head = rq->balance_callback;
+ while (head) {
+ if (head == &balance_push_callback)
+ found = true;
+ next = head->next;
+ head->next = NULL;
+ head = next;
+ }
+ rq->balance_callback = found ? &balance_push_callback : NULL;
+}
+#else
+static inline void zap_balance_callbacks(struct rq *rq)
+{
+}
+#endif
+
static void do_balance_callbacks(struct rq *rq, struct balance_callback *head)
{
void (*func)(struct rq *rq);
@@ -6941,8 +6975,11 @@ static void __sched notrace __schedule(int sched_mode)
rq_set_donor(rq, next);
if (unlikely(task_is_blocked(next))) {
next = find_proxy_task(rq, next, &rf);
- if (!next)
+ if (!next) {
+ /* zap the balance_callbacks before picking again */
+ zap_balance_callbacks(rq);
goto pick_again;
+ }
if (next == rq->idle)
goto keep_resched;
}
--
2.51.0.rc1.167.g924127e9c0-goog
^ permalink raw reply related [flat|nested] 7+ messages in thread* [PATCH v21 4/6] sched: Handle blocked-waiter migration (and return migration)
2025-08-18 22:12 [PATCH v21 0/6] Donor Migration for Proxy Execution (v21) John Stultz
` (2 preceding siblings ...)
2025-08-18 22:12 ` [PATCH v21 3/6] sched: Add logic to zap balance callbacks if we pick again John Stultz
@ 2025-08-18 22:12 ` John Stultz
2025-08-18 22:12 ` [PATCH v21 5/6] sched: Add blocked_donor link to task for smarter mutex handoffs John Stultz
2025-08-18 22:12 ` [PATCH v21 6/6] sched: Migrate whole chain in proxy_migrate_task() John Stultz
5 siblings, 0 replies; 7+ messages in thread
From: John Stultz @ 2025-08-18 22:12 UTC (permalink / raw)
To: LKML
Cc: John Stultz, Joel Fernandes, Qais Yousef, Ingo Molnar,
Peter Zijlstra, Juri Lelli, Vincent Guittot, Dietmar Eggemann,
Valentin Schneider, Steven Rostedt, Ben Segall, Zimuzo Ezeozue,
Mel Gorman, Will Deacon, Waiman Long, Boqun Feng,
Paul E. McKenney, Metin Kaya, Xuewen Yan, K Prateek Nayak,
Thomas Gleixner, Daniel Lezcano, Suleiman Souhlal, kuyo chang,
hupu, kernel-team
Add logic to handle migrating a blocked waiter to a remote
cpu where the lock owner is runnable.
Additionally, as the blocked task may not be able to run
on the remote cpu, add logic to handle return migration once
the waiting task is given the mutex.
Because tasks may get migrated to where they cannot run, also
modify the scheduling classes to avoid sched class migrations on
mutex blocked tasks, leaving find_proxy_task() and related logic
to do the migrations and return migrations.
This was split out from the larger proxy patch, and
significantly reworked.
Credits for the original patch go to:
Peter Zijlstra (Intel) <peterz@infradead.org>
Juri Lelli <juri.lelli@redhat.com>
Valentin Schneider <valentin.schneider@arm.com>
Connor O'Brien <connoro@google.com>
Signed-off-by: John Stultz <jstultz@google.com>
---
v6:
* Integrated sched_proxy_exec() check in proxy_return_migration()
* Minor cleanups to diff
* Unpin the rq before calling __balance_callbacks()
* Tweak proxy migrate to migrate deeper task in chain, to avoid
tasks pingponging between rqs
v7:
* Fixup for unused function arguments
* Switch from that_rq -> target_rq, other minor tweaks, and typo
fixes suggested by Metin Kaya
* Switch back to doing return migration in the ttwu path, which
avoids nasty lock juggling and performance issues
* Fixes for UP builds
v8:
* More simplifications from Metin Kaya
* Fixes for null owner case, including doing return migration
* Cleanup proxy_needs_return logic
v9:
* Narrow logic in ttwu that sets BO_RUNNABLE, to avoid missed
return migrations
* Switch to using zap_balance_callbacks rathern then running
them when we are dropping rq locks for proxy_migration.
* Drop task_is_blocked check in sched_submit_work as suggested
by Metin (may re-add later if this causes trouble)
* Do return migration when we're not on wake_cpu. This avoids
bad task placement caused by proxy migrations raised by
Xuewen Yan
* Fix to call set_next_task(rq->curr) prior to dropping rq lock
to avoid rq->curr getting migrated before we have actually
switched from it
* Cleanup to re-use proxy_resched_idle() instead of open coding
it in proxy_migrate_task()
* Fix return migration not to use DEQUEUE_SLEEP, so that we
properly see the task as task_on_rq_migrating() after it is
dequeued but before set_task_cpu() has been called on it
* Fix to broaden find_proxy_task() checks to avoid race where
a task is dequeued off the rq due to return migration, but
set_task_cpu() and the enqueue on another rq happened after
we checked task_cpu(owner). This ensures we don't proxy
using a task that is not actually on our runqueue.
* Cleanup to avoid the locked BO_WAKING->BO_RUNNABLE transition
in try_to_wake_up() if proxy execution isn't enabled.
* Cleanup to improve comment in proxy_migrate_task() explaining
the set_next_task(rq->curr) logic
* Cleanup deadline.c change to stylistically match rt.c change
* Numerous cleanups suggested by Metin
v10:
* Drop WARN_ON(task_is_blocked(p)) in ttwu current case
v11:
* Include proxy_set_task_cpu from later in the series to this
change so we can use it, rather then reworking logic later
in the series.
* Fix problem with return migration, where affinity was changed
and wake_cpu was left outside the affinity mask.
* Avoid reading the owner's cpu twice (as it might change inbetween)
to avoid occasional migration-to-same-cpu edge cases
* Add extra WARN_ON checks for wake_cpu and return migration
edge cases.
* Typo fix from Metin
v13:
* As we set ret, return it, not just NULL (pulling this change
in from later patch)
* Avoid deadlock between try_to_wake_up() and find_proxy_task() when
blocked_on cycle with ww_mutex is trying a mid-chain wakeup.
* Tweaks to use new __set_blocked_on_runnable() helper
* Potential fix for incorrectly updated task->dl_server issues
* Minor comment improvements
* Add logic to handle missed wakeups, in that case doing return
migration from the find_proxy_task() path
* Minor cleanups
v14:
* Improve edge cases where we wouldn't set the task as BO_RUNNABLE
v15:
* Added comment to better describe proxy_needs_return() as suggested
by Qais
* Build fixes for !CONFIG_SMP reported by
Maciej Żenczykowski <maze@google.com>
* Adds fix for re-evaluating proxy_needs_return when
sched_proxy_exec() is disabled, reported and diagnosed by:
kuyo chang <kuyo.chang@mediatek.com>
v16:
* Larger rework of needs_return logic in find_proxy_task, in
order to avoid problems with cpuhotplug
* Rework to use guard() as suggested by Peter
v18:
* Integrate optimization suggested by Suleiman to do the checks
for sleeping owners before checking if the task_cpu is this_cpu,
so that we can avoid needlessly proxy-migrating tasks to only
then dequeue them. Also check if migrating last.
* Improve comments around guard locking
* Include tweak to ttwu_runnable() as suggested by
hupu <hupu.gm@gmail.com>
* Rework the logic releasing the rq->donor reference before letting
go of the rqlock. Just use rq->idle.
* Go back to doing return migration on BO_WAKING owners, as I was
hitting some softlockups caused by running tasks not making
it out of BO_WAKING.
v19:
* Fixed proxy_force_return() logic for !SMP cases
v21:
* Reworked donor deactivation for unhandled sleeping owners
* Commit message tweaks
Cc: Joel Fernandes <joelagnelf@nvidia.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: Suleiman Souhlal <suleiman@google.com>
Cc: kuyo chang <kuyo.chang@mediatek.com>
Cc: hupu <hupu.gm@gmail.com>
Cc: kernel-team@android.com
---
kernel/sched/core.c | 247 +++++++++++++++++++++++++++++++++++++++-----
kernel/sched/fair.c | 3 +-
2 files changed, 222 insertions(+), 28 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 01bf5ef8d9fcc..0f824446c6046 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3157,6 +3157,14 @@ static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
__do_set_cpus_allowed(p, ctx);
+ /*
+ * It might be that the p->wake_cpu is no longer
+ * allowed, so set it to the dest_cpu so return
+ * migration doesn't send it to an invalid cpu
+ */
+ if (!is_cpu_allowed(p, p->wake_cpu))
+ p->wake_cpu = dest_cpu;
+
return affine_move_task(rq, p, rf, dest_cpu, ctx->flags);
out:
@@ -3717,6 +3725,67 @@ static inline void ttwu_do_wakeup(struct task_struct *p)
trace_sched_wakeup(p);
}
+#ifdef CONFIG_SCHED_PROXY_EXEC
+static inline void proxy_set_task_cpu(struct task_struct *p, int cpu)
+{
+ unsigned int wake_cpu;
+
+ /*
+ * Since we are enqueuing a blocked task on a cpu it may
+ * not be able to run on, preserve wake_cpu when we
+ * __set_task_cpu so we can return the task to where it
+ * was previously runnable.
+ */
+ wake_cpu = p->wake_cpu;
+ __set_task_cpu(p, cpu);
+ p->wake_cpu = wake_cpu;
+}
+
+static bool proxy_task_runnable_but_waking(struct task_struct *p)
+{
+ if (!sched_proxy_exec())
+ return false;
+ return (READ_ONCE(p->__state) == TASK_RUNNING &&
+ READ_ONCE(p->blocked_on_state) == BO_WAKING);
+}
+#else /* !CONFIG_SCHED_PROXY_EXEC */
+static bool proxy_task_runnable_but_waking(struct task_struct *p)
+{
+ return false;
+}
+#endif /* CONFIG_SCHED_PROXY_EXEC */
+
+/*
+ * Checks to see if task p has been proxy-migrated to another rq
+ * and needs to be returned. If so, we deactivate the task here
+ * so that it can be properly woken up on the p->wake_cpu
+ * (or whichever cpu select_task_rq() picks at the bottom of
+ * try_to_wake_up()
+ */
+static inline bool proxy_needs_return(struct rq *rq, struct task_struct *p)
+{
+ bool ret = false;
+
+ if (!sched_proxy_exec())
+ return false;
+
+ raw_spin_lock(&p->blocked_lock);
+ if (__get_task_blocked_on(p) && p->blocked_on_state == BO_WAKING) {
+ if (!task_current(rq, p) && (p->wake_cpu != cpu_of(rq))) {
+ if (task_current_donor(rq, p)) {
+ put_prev_task(rq, p);
+ rq_set_donor(rq, rq->idle);
+ }
+ deactivate_task(rq, p, DEQUEUE_NOCLOCK);
+ ret = true;
+ }
+ __set_blocked_on_runnable(p);
+ resched_curr(rq);
+ }
+ raw_spin_unlock(&p->blocked_lock);
+ return ret;
+}
+
static void
ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
struct rq_flags *rf)
@@ -3802,6 +3871,8 @@ static int ttwu_runnable(struct task_struct *p, int wake_flags)
update_rq_clock(rq);
if (p->se.sched_delayed)
enqueue_task(rq, p, ENQUEUE_NOCLOCK | ENQUEUE_DELAYED);
+ if (proxy_needs_return(rq, p))
+ goto out;
if (!task_on_cpu(rq, p)) {
/*
* When on_rq && !on_cpu the task is preempted, see if
@@ -3812,6 +3883,7 @@ static int ttwu_runnable(struct task_struct *p, int wake_flags)
ttwu_do_wakeup(p);
ret = 1;
}
+out:
__task_rq_unlock(rq, &rf);
return ret;
@@ -4199,6 +4271,8 @@ int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
* it disabling IRQs (this allows not taking ->pi_lock).
*/
WARN_ON_ONCE(p->se.sched_delayed);
+ /* If current is waking up, we know we can run here, so set BO_RUNNBLE */
+ set_blocked_on_runnable(p);
if (!ttwu_state_match(p, state, &success))
goto out;
@@ -4215,8 +4289,15 @@ int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
*/
scoped_guard (raw_spinlock_irqsave, &p->pi_lock) {
smp_mb__after_spinlock();
- if (!ttwu_state_match(p, state, &success))
- break;
+ if (!ttwu_state_match(p, state, &success)) {
+ /*
+ * If we're already TASK_RUNNING, and BO_WAKING
+ * continue on to ttwu_runnable check to force
+ * proxy_needs_return evaluation
+ */
+ if (!proxy_task_runnable_but_waking(p))
+ break;
+ }
trace_sched_waking(p);
@@ -4278,6 +4359,7 @@ int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
* enqueue, such as ttwu_queue_wakelist().
*/
WRITE_ONCE(p->__state, TASK_WAKING);
+ set_blocked_on_runnable(p);
/*
* If the owning (remote) CPU is still in the middle of schedule() with
@@ -4328,12 +4410,6 @@ int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
ttwu_queue(p, cpu, wake_flags);
}
out:
- /*
- * For now, if we've been woken up, set us as BO_RUNNABLE
- * We will need to be more careful later when handling
- * proxy migration
- */
- set_blocked_on_runnable(p);
if (success)
ttwu_stat(p, task_cpu(p), wake_flags);
@@ -6635,7 +6711,7 @@ static inline struct task_struct *proxy_resched_idle(struct rq *rq)
return rq->idle;
}
-static bool __proxy_deactivate(struct rq *rq, struct task_struct *donor)
+static bool proxy_deactivate(struct rq *rq, struct task_struct *donor)
{
unsigned long state = READ_ONCE(donor->__state);
@@ -6655,17 +6731,98 @@ static bool __proxy_deactivate(struct rq *rq, struct task_struct *donor)
return try_to_block_task(rq, donor, &state, true);
}
-static struct task_struct *proxy_deactivate(struct rq *rq, struct task_struct *donor)
+/*
+ * If the blocked-on relationship crosses CPUs, migrate @p to the
+ * owner's CPU.
+ *
+ * This is because we must respect the CPU affinity of execution
+ * contexts (owner) but we can ignore affinity for scheduling
+ * contexts (@p). So we have to move scheduling contexts towards
+ * potential execution contexts.
+ *
+ * Note: The owner can disappear, but simply migrate to @target_cpu
+ * and leave that CPU to sort things out.
+ */
+static void proxy_migrate_task(struct rq *rq, struct rq_flags *rf,
+ struct task_struct *p, int target_cpu)
{
- if (!__proxy_deactivate(rq, donor)) {
- /*
- * XXX: For now, if deactivation failed, set donor
- * as unblocked, as we aren't doing proxy-migrations
- * yet (more logic will be needed then).
- */
- force_blocked_on_runnable(donor);
- }
- return NULL;
+ struct rq *target_rq = cpu_rq(target_cpu);
+
+ lockdep_assert_rq_held(rq);
+
+ /*
+ * Since we're going to drop @rq, we have to put(@rq->donor) first,
+ * otherwise we have a reference that no longer belongs to us.
+ *
+ * Additionally, as we put_prev_task(prev) earlier, its possible that
+ * prev will migrate away as soon as we drop the rq lock, however we
+ * still have it marked as rq->curr, as we've not yet switched tasks.
+ *
+ * After the migration, we are going to pick_again in the __schedule
+ * logic, so backtrack a bit before we release the lock:
+ * Put rq->donor, and set rq->curr as rq->donor and set_next_task,
+ * so that we're close to the situation we had entering __schedule
+ * the first time.
+ *
+ * Then when we re-aquire the lock, we will re-put rq->curr then
+ * rq_set_donor(rq->idle) and set_next_task(rq->idle), before
+ * picking again.
+ */
+ /* XXX - Added to address problems with changed dl_server semantics - double check */
+ __put_prev_set_next_dl_server(rq, rq->donor, rq->curr);
+ put_prev_task(rq, rq->donor);
+ rq_set_donor(rq, rq->idle);
+ set_next_task(rq, rq->idle);
+
+ WARN_ON(p == rq->curr);
+
+ deactivate_task(rq, p, 0);
+ proxy_set_task_cpu(p, target_cpu);
+
+ zap_balance_callbacks(rq);
+ rq_unpin_lock(rq, rf);
+ raw_spin_rq_unlock(rq);
+ raw_spin_rq_lock(target_rq);
+
+ activate_task(target_rq, p, 0);
+ wakeup_preempt(target_rq, p, 0);
+
+ raw_spin_rq_unlock(target_rq);
+ raw_spin_rq_lock(rq);
+ rq_repin_lock(rq, rf);
+}
+
+static void proxy_force_return(struct rq *rq, struct rq_flags *rf,
+ struct task_struct *p)
+{
+ lockdep_assert_rq_held(rq);
+
+ put_prev_task(rq, rq->donor);
+ rq_set_donor(rq, rq->idle);
+ set_next_task(rq, rq->idle);
+
+ WARN_ON(p == rq->curr);
+
+ set_blocked_on_waking(p);
+ get_task_struct(p);
+ block_task(rq, p, 0);
+
+ zap_balance_callbacks(rq);
+ rq_unpin_lock(rq, rf);
+ raw_spin_rq_unlock(rq);
+
+ wake_up_process(p);
+ put_task_struct(p);
+
+ raw_spin_rq_lock(rq);
+ rq_repin_lock(rq, rf);
+}
+
+static inline bool proxy_can_run_here(struct rq *rq, struct task_struct *p)
+{
+ if (p == rq->curr || p->wake_cpu == cpu_of(rq))
+ return true;
+ return false;
}
/*
@@ -6688,9 +6845,11 @@ static struct task_struct *
find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)
{
struct task_struct *owner = NULL;
+ bool curr_in_chain = false;
int this_cpu = cpu_of(rq);
struct task_struct *p;
struct mutex *mutex;
+ int owner_cpu;
/* Follow blocked_on chain. */
for (p = donor; task_is_blocked(p); p = owner) {
@@ -6716,6 +6875,10 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)
return NULL;
}
+ /* Double check blocked_on_state now we're holding the lock */
+ if (p->blocked_on_state == BO_RUNNABLE)
+ return p;
+
/*
* If a ww_mutex hits the die/wound case, it marks the task as
* BO_WAKING and calls try_to_wake_up(), so that the mutex
@@ -6731,26 +6894,46 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)
* try_to_wake_up from completing and doing the return
* migration.
*
- * So when we hit a !BO_BLOCKED task briefly schedule idle
- * so we release the rq and let the wakeup complete.
+ * So when we hit a BO_WAKING task try to wake it up ourselves.
*/
- if (p->blocked_on_state != BO_BLOCKED)
- return proxy_resched_idle(rq);
+ if (p->blocked_on_state == BO_WAKING) {
+ if (task_current(rq, p)) {
+ /* If its current just set it runnable */
+ __force_blocked_on_runnable(p);
+ return p;
+ }
+ goto needs_return;
+ }
+
+ if (task_current(rq, p))
+ curr_in_chain = true;
owner = __mutex_owner(mutex);
if (!owner) {
+ /* If the owner is null, we may have some work to do */
+ if (!proxy_can_run_here(rq, p))
+ goto needs_return;
+
__force_blocked_on_runnable(p);
return p;
}
if (!READ_ONCE(owner->on_rq) || owner->se.sched_delayed) {
/* XXX Don't handle blocked owners/delayed dequeue yet */
+ if (curr_in_chain)
+ return proxy_resched_idle(rq);
goto deactivate_donor;
}
- if (task_cpu(owner) != this_cpu) {
- /* XXX Don't handle migrations yet */
- goto deactivate_donor;
+ owner_cpu = task_cpu(owner);
+ if (owner_cpu != this_cpu) {
+ /*
+ * @owner can disappear, simply migrate to @owner_cpu
+ * and leave that CPU to sort things out.
+ */
+ if (curr_in_chain)
+ return proxy_resched_idle(rq);
+ goto migrate;
}
if (task_on_rq_migrating(owner)) {
@@ -6817,8 +7000,18 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)
* blocked_lock released, so we have to get out of the
* guard() scope.
*/
+migrate:
+ proxy_migrate_task(rq, rf, p, owner_cpu);
+ return NULL;
+needs_return:
+ proxy_force_return(rq, rf, p);
+ return NULL;
deactivate_donor:
- return proxy_deactivate(rq, donor);
+ if (!proxy_deactivate(rq, donor)) {
+ p = donor;
+ goto needs_return;
+ }
+ return NULL;
}
#else /* SCHED_PROXY_EXEC */
static struct task_struct *
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b173a059315c2..cc531eb939831 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8781,7 +8781,8 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf
se = &p->se;
#ifdef CONFIG_FAIR_GROUP_SCHED
- if (prev->sched_class != &fair_sched_class)
+ if (prev->sched_class != &fair_sched_class ||
+ rq->curr != rq->donor)
goto simple;
__put_prev_set_next_dl_server(rq, prev, p);
--
2.51.0.rc1.167.g924127e9c0-goog
^ permalink raw reply related [flat|nested] 7+ messages in thread* [PATCH v21 5/6] sched: Add blocked_donor link to task for smarter mutex handoffs
2025-08-18 22:12 [PATCH v21 0/6] Donor Migration for Proxy Execution (v21) John Stultz
` (3 preceding siblings ...)
2025-08-18 22:12 ` [PATCH v21 4/6] sched: Handle blocked-waiter migration (and return migration) John Stultz
@ 2025-08-18 22:12 ` John Stultz
2025-08-18 22:12 ` [PATCH v21 6/6] sched: Migrate whole chain in proxy_migrate_task() John Stultz
5 siblings, 0 replies; 7+ messages in thread
From: John Stultz @ 2025-08-18 22:12 UTC (permalink / raw)
To: LKML
Cc: Peter Zijlstra, Juri Lelli, Valentin Schneider,
Connor O'Brien, John Stultz, Joel Fernandes, Qais Yousef,
Ingo Molnar, Vincent Guittot, Dietmar Eggemann,
Valentin Schneider, Steven Rostedt, Ben Segall, Zimuzo Ezeozue,
Mel Gorman, Will Deacon, Waiman Long, Boqun Feng,
Paul E. McKenney, Metin Kaya, Xuewen Yan, K Prateek Nayak,
Thomas Gleixner, Daniel Lezcano, Suleiman Souhlal, kuyo chang,
hupu, kernel-team
From: Peter Zijlstra <peterz@infradead.org>
Add link to the task this task is proxying for, and use it so
the mutex owner can do an intelligent hand-off of the mutex to
the task that the owner is running on behalf.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Connor O'Brien <connoro@google.com>
[jstultz: This patch was split out from larger proxy patch]
Signed-off-by: John Stultz <jstultz@google.com>
---
v5:
* Split out from larger proxy patch
v6:
* Moved proxied value from earlier patch to this one where it
is actually used
* Rework logic to check sched_proxy_exec() instead of using ifdefs
* Moved comment change to this patch where it makes sense
v7:
* Use more descriptive term then "us" in comments, as suggested
by Metin Kaya.
* Minor typo fixup from Metin Kaya
* Reworked proxied variable to prev_not_proxied to simplify usage
v8:
* Use helper for donor blocked_on_state transition
v9:
* Re-add mutex lock handoff in the unlock path, but only when we
have a blocked donor
* Slight reword of commit message suggested by Metin
v18:
* Add task_init initialization for blocked_donor, suggested by
Suleiman
Cc: Joel Fernandes <joelagnelf@nvidia.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: Suleiman Souhlal <suleiman@google.com>
Cc: kuyo chang <kuyo.chang@mediatek.com>
Cc: hupu <hupu.gm@gmail.com>
Cc: kernel-team@android.com
---
include/linux/sched.h | 1 +
init/init_task.c | 1 +
kernel/fork.c | 1 +
kernel/locking/mutex.c | 41 ++++++++++++++++++++++++++++++++++++++---
kernel/sched/core.c | 18 ++++++++++++++++--
5 files changed, 57 insertions(+), 5 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5801de1a44a79..ab12eb738c440 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1242,6 +1242,7 @@ struct task_struct {
enum blocked_on_state blocked_on_state;
struct mutex *blocked_on; /* lock we're blocked on */
+ struct task_struct *blocked_donor; /* task that is boosting this task */
raw_spinlock_t blocked_lock;
#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
diff --git a/init/init_task.c b/init/init_task.c
index 6d72ec23410a6..627bbd8953e88 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -175,6 +175,7 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = {
&init_task.alloc_lock),
#endif
.blocked_on_state = BO_RUNNABLE,
+ .blocked_donor = NULL,
#ifdef CONFIG_RT_MUTEXES
.pi_waiters = RB_ROOT_CACHED,
.pi_top_task = NULL,
diff --git a/kernel/fork.c b/kernel/fork.c
index 4bd0731995e86..86fe43ee35952 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2131,6 +2131,7 @@ __latent_entropy struct task_struct *copy_process(
p->blocked_on_state = BO_RUNNABLE;
p->blocked_on = NULL; /* not blocked yet */
+ p->blocked_donor = NULL; /* nobody is boosting p yet */
#ifdef CONFIG_BCACHE
p->sequential_io = 0;
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 42e4d2e6e4ad4..76cba3580fce7 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -921,7 +921,7 @@ EXPORT_SYMBOL_GPL(ww_mutex_lock_interruptible);
*/
static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigned long ip)
{
- struct task_struct *next = NULL;
+ struct task_struct *donor, *next = NULL;
DEFINE_WAKE_Q(wake_q);
unsigned long owner;
unsigned long flags;
@@ -940,6 +940,12 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
MUTEX_WARN_ON(__owner_task(owner) != current);
MUTEX_WARN_ON(owner & MUTEX_FLAG_PICKUP);
+ if (sched_proxy_exec() && current->blocked_donor) {
+ /* force handoff if we have a blocked_donor */
+ owner = MUTEX_FLAG_HANDOFF;
+ break;
+ }
+
if (owner & MUTEX_FLAG_HANDOFF)
break;
@@ -953,7 +959,34 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
raw_spin_lock_irqsave(&lock->wait_lock, flags);
debug_mutex_unlock(lock);
- if (!list_empty(&lock->wait_list)) {
+
+ if (sched_proxy_exec()) {
+ raw_spin_lock(¤t->blocked_lock);
+ /*
+ * If we have a task boosting current, and that task was boosting
+ * current through this lock, hand the lock to that task, as that
+ * is the highest waiter, as selected by the scheduling function.
+ */
+ donor = current->blocked_donor;
+ if (donor) {
+ struct mutex *next_lock;
+
+ raw_spin_lock_nested(&donor->blocked_lock, SINGLE_DEPTH_NESTING);
+ next_lock = __get_task_blocked_on(donor);
+ if (next_lock == lock) {
+ next = donor;
+ __set_blocked_on_waking(donor);
+ wake_q_add(&wake_q, donor);
+ current->blocked_donor = NULL;
+ }
+ raw_spin_unlock(&donor->blocked_lock);
+ }
+ }
+
+ /*
+ * Failing that, pick any on the wait list.
+ */
+ if (!next && !list_empty(&lock->wait_list)) {
/* get the first entry from the wait-list: */
struct mutex_waiter *waiter =
list_first_entry(&lock->wait_list,
@@ -961,7 +994,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
next = waiter->task;
- raw_spin_lock(&next->blocked_lock);
+ raw_spin_lock_nested(&next->blocked_lock, SINGLE_DEPTH_NESTING);
debug_mutex_wake_waiter(lock, waiter);
WARN_ON_ONCE(__get_task_blocked_on(next) != lock);
__set_blocked_on_waking(next);
@@ -972,6 +1005,8 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
if (owner & MUTEX_FLAG_HANDOFF)
__mutex_handoff(lock, next);
+ if (sched_proxy_exec())
+ raw_spin_unlock(¤t->blocked_lock);
raw_spin_unlock_irqrestore_wake(&lock->wait_lock, flags, &wake_q);
}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0f824446c6046..cac03f68cbcce 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6829,7 +6829,17 @@ static inline bool proxy_can_run_here(struct rq *rq, struct task_struct *p)
* Find runnable lock owner to proxy for mutex blocked donor
*
* Follow the blocked-on relation:
- * task->blocked_on -> mutex->owner -> task...
+ *
+ * ,-> task
+ * | | blocked-on
+ * | v
+ * blocked_donor | mutex
+ * | | owner
+ * | v
+ * `-- task
+ *
+ * and set the blocked_donor relation, this latter is used by the mutex
+ * code to find which (blocked) task to hand-off to.
*
* Lock order:
*
@@ -6989,6 +6999,7 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)
* rq, therefore holding @rq->lock is sufficient to
* guarantee its existence, as per ttwu_remote().
*/
+ owner->blocked_donor = p;
}
WARN_ON_ONCE(owner && !owner->on_rq);
@@ -7091,6 +7102,7 @@ static void __sched notrace __schedule(int sched_mode)
unsigned long prev_state;
struct rq_flags rf;
struct rq *rq;
+ bool prev_not_proxied;
int cpu;
/* Trace preemptions consistently with task switches */
@@ -7163,9 +7175,11 @@ static void __sched notrace __schedule(int sched_mode)
switch_count = &prev->nvcsw;
}
+ prev_not_proxied = !prev->blocked_donor;
pick_again:
next = pick_next_task(rq, rq->donor, &rf);
rq_set_donor(rq, next);
+ next->blocked_donor = NULL;
if (unlikely(task_is_blocked(next))) {
next = find_proxy_task(rq, next, &rf);
if (!next) {
@@ -7229,7 +7243,7 @@ static void __sched notrace __schedule(int sched_mode)
rq = context_switch(rq, prev, next, &rf);
} else {
/* In case next was already curr but just got blocked_donor */
- if (!task_current_donor(rq, next))
+ if (prev_not_proxied && next->blocked_donor)
proxy_tag_curr(rq, next);
rq_unpin_lock(rq, &rf);
--
2.51.0.rc1.167.g924127e9c0-goog
^ permalink raw reply related [flat|nested] 7+ messages in thread* [PATCH v21 6/6] sched: Migrate whole chain in proxy_migrate_task()
2025-08-18 22:12 [PATCH v21 0/6] Donor Migration for Proxy Execution (v21) John Stultz
` (4 preceding siblings ...)
2025-08-18 22:12 ` [PATCH v21 5/6] sched: Add blocked_donor link to task for smarter mutex handoffs John Stultz
@ 2025-08-18 22:12 ` John Stultz
5 siblings, 0 replies; 7+ messages in thread
From: John Stultz @ 2025-08-18 22:12 UTC (permalink / raw)
To: LKML
Cc: John Stultz, Joel Fernandes, Qais Yousef, Ingo Molnar,
Peter Zijlstra, Juri Lelli, Vincent Guittot, Dietmar Eggemann,
Valentin Schneider, Steven Rostedt, Ben Segall, Zimuzo Ezeozue,
Mel Gorman, Will Deacon, Waiman Long, Boqun Feng,
Paul E. McKenney, Metin Kaya, Xuewen Yan, K Prateek Nayak,
Thomas Gleixner, Daniel Lezcano, Suleiman Souhlal, kuyo chang,
hupu, kernel-team
Instead of migrating one task each time through find_proxy_task(),
we can walk up the blocked_donor ptrs and migrate the entire
current chain in one go.
This was broken out of earlier patches and held back while the
series was being stabilized, but I wanted to re-introduce it.
Signed-off-by: John Stultz <jstultz@google.com>
---
v12:
* Earlier this was re-using blocked_node, but I hit
a race with activating blocked entities, and to
avoid it introduced a new migration_node listhead
v18:
* Add init_task initialization of migration_node as suggested
by Suleiman
Cc: Joel Fernandes <joelagnelf@nvidia.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: Suleiman Souhlal <suleiman@google.com>
Cc: kuyo chang <kuyo.chang@mediatek.com>
Cc: hupu <hupu.gm@gmail.com>
Cc: kernel-team@android.com
---
include/linux/sched.h | 1 +
init/init_task.c | 1 +
kernel/fork.c | 1 +
kernel/sched/core.c | 25 +++++++++++++++++--------
4 files changed, 20 insertions(+), 8 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ab12eb738c440..176ec117f4041 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1243,6 +1243,7 @@ struct task_struct {
enum blocked_on_state blocked_on_state;
struct mutex *blocked_on; /* lock we're blocked on */
struct task_struct *blocked_donor; /* task that is boosting this task */
+ struct list_head migration_node;
raw_spinlock_t blocked_lock;
#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
diff --git a/init/init_task.c b/init/init_task.c
index 627bbd8953e88..65e0f90285966 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -176,6 +176,7 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = {
#endif
.blocked_on_state = BO_RUNNABLE,
.blocked_donor = NULL,
+ .migration_node = LIST_HEAD_INIT(init_task.migration_node),
#ifdef CONFIG_RT_MUTEXES
.pi_waiters = RB_ROOT_CACHED,
.pi_top_task = NULL,
diff --git a/kernel/fork.c b/kernel/fork.c
index 86fe43ee35952..01fd08c463871 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2132,6 +2132,7 @@ __latent_entropy struct task_struct *copy_process(
p->blocked_on_state = BO_RUNNABLE;
p->blocked_on = NULL; /* not blocked yet */
p->blocked_donor = NULL; /* nobody is boosting p yet */
+ INIT_LIST_HEAD(&p->migration_node);
#ifdef CONFIG_BCACHE
p->sequential_io = 0;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index cac03f68cbcce..26f7a11a39e0e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6747,6 +6747,7 @@ static void proxy_migrate_task(struct rq *rq, struct rq_flags *rf,
struct task_struct *p, int target_cpu)
{
struct rq *target_rq = cpu_rq(target_cpu);
+ LIST_HEAD(migrate_list);
lockdep_assert_rq_held(rq);
@@ -6774,19 +6775,27 @@ static void proxy_migrate_task(struct rq *rq, struct rq_flags *rf,
rq_set_donor(rq, rq->idle);
set_next_task(rq, rq->idle);
- WARN_ON(p == rq->curr);
-
- deactivate_task(rq, p, 0);
- proxy_set_task_cpu(p, target_cpu);
-
+ for (; p; p = p->blocked_donor) {
+ WARN_ON(p == rq->curr);
+ deactivate_task(rq, p, 0);
+ proxy_set_task_cpu(p, target_cpu);
+ /*
+ * We can abuse blocked_node to migrate the thing,
+ * because @p was still on the rq.
+ */
+ list_add(&p->migration_node, &migrate_list);
+ }
zap_balance_callbacks(rq);
rq_unpin_lock(rq, rf);
raw_spin_rq_unlock(rq);
raw_spin_rq_lock(target_rq);
+ while (!list_empty(&migrate_list)) {
+ p = list_first_entry(&migrate_list, struct task_struct, migration_node);
+ list_del_init(&p->migration_node);
- activate_task(target_rq, p, 0);
- wakeup_preempt(target_rq, p, 0);
-
+ activate_task(target_rq, p, 0);
+ wakeup_preempt(target_rq, p, 0);
+ }
raw_spin_rq_unlock(target_rq);
raw_spin_rq_lock(rq);
rq_repin_lock(rq, rf);
--
2.51.0.rc1.167.g924127e9c0-goog
^ permalink raw reply related [flat|nested] 7+ messages in thread