Message-ID: <20250722070600.3267819-6-jstultz@google.com>
Date: Tue, 22 Jul 2025 07:05:51 +0000
From: John Stultz <jstultz@...gle.com>
To: LKML <linux-kernel@...r.kernel.org>
Cc: Peter Zijlstra <peterz@...radead.org>, Juri Lelli <juri.lelli@...hat.com>, 
	Valentin Schneider <valentin.schneider@....com>, "Connor O'Brien" <connoro@...gle.com>, 
	John Stultz <jstultz@...gle.com>, Joel Fernandes <joelagnelf@...dia.com>, 
	Qais Yousef <qyousef@...alina.io>, Ingo Molnar <mingo@...hat.com>, 
	Vincent Guittot <vincent.guittot@...aro.org>, Dietmar Eggemann <dietmar.eggemann@....com>, 
	Valentin Schneider <vschneid@...hat.com>, Steven Rostedt <rostedt@...dmis.org>, 
	Ben Segall <bsegall@...gle.com>, Zimuzo Ezeozue <zezeozue@...gle.com>, Mel Gorman <mgorman@...e.de>, 
	Will Deacon <will@...nel.org>, Waiman Long <longman@...hat.com>, Boqun Feng <boqun.feng@...il.com>, 
	"Paul E. McKenney" <paulmck@...nel.org>, Metin Kaya <Metin.Kaya@....com>, 
	Xuewen Yan <xuewen.yan94@...il.com>, K Prateek Nayak <kprateek.nayak@....com>, 
	Thomas Gleixner <tglx@...utronix.de>, Daniel Lezcano <daniel.lezcano@...aro.org>, 
	Suleiman Souhlal <suleiman@...gle.com>, kuyo chang <kuyo.chang@...iatek.com>, hupu <hupu.gm@...il.com>, 
	kernel-team@...roid.com
Subject: [RFC][PATCH v20 5/6] sched: Add blocked_donor link to task for
 smarter mutex handoffs

From: Peter Zijlstra <peterz@...radead.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@...radead.org>
Signed-off-by: Juri Lelli <juri.lelli@...hat.com>
Signed-off-by: Valentin Schneider <valentin.schneider@....com>
Signed-off-by: Connor O'Brien <connoro@...gle.com>
[jstultz: This patch was split out from larger proxy patch]
Signed-off-by: John Stultz <jstultz@...gle.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@...dia.com>
Cc: Qais Yousef <qyousef@...alina.io>
Cc: Ingo Molnar <mingo@...hat.com>
Cc: Peter Zijlstra <peterz@...radead.org>
Cc: Juri Lelli <juri.lelli@...hat.com>
Cc: Vincent Guittot <vincent.guittot@...aro.org>
Cc: Dietmar Eggemann <dietmar.eggemann@....com>
Cc: Valentin Schneider <vschneid@...hat.com>
Cc: Steven Rostedt <rostedt@...dmis.org>
Cc: Ben Segall <bsegall@...gle.com>
Cc: Zimuzo Ezeozue <zezeozue@...gle.com>
Cc: Mel Gorman <mgorman@...e.de>
Cc: Will Deacon <will@...nel.org>
Cc: Waiman Long <longman@...hat.com>
Cc: Boqun Feng <boqun.feng@...il.com>
Cc: "Paul E. McKenney" <paulmck@...nel.org>
Cc: Metin Kaya <Metin.Kaya@....com>
Cc: Xuewen Yan <xuewen.yan94@...il.com>
Cc: K Prateek Nayak <kprateek.nayak@....com>
Cc: Thomas Gleixner <tglx@...utronix.de>
Cc: Daniel Lezcano <daniel.lezcano@...aro.org>
Cc: Suleiman Souhlal <suleiman@...gle.com>
Cc: kuyo chang <kuyo.chang@...iatek.com>
Cc: hupu <hupu.gm@...il.com>
Cc: kernel-team@...roid.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 ced001f889519..675e2f89ec0f8 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1239,6 +1239,7 @@ 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 5eacb25a0c5ab..61a2ac850faf0 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2126,6 +2126,7 @@ __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 b5145ddaec242..da6e964498ad0 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -926,7 +926,7 @@ 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;
@@ -945,6 +945,12 @@ 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;
 
@@ -958,7 +964,34 @@ 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(&current->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,
@@ -966,7 +999,7 @@ 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);
@@ -977,6 +1010,8 @@ 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(&current->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 1c249d1d62f5a..2c3a4b9518927 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6823,7 +6823,17 @@ 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:
  *
@@ -6987,6 +6997,7 @@ 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);
@@ -7083,6 +7094,7 @@ 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_sched_entry_tp(preempt, CALLER_ADDR0);
@@ -7154,9 +7166,11 @@ 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) {
@@ -7220,7 +7234,7 @@ 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);
-- 
2.50.0.727.gbf7dc18ff4-goog

Powered by blists - more mailing lists