sched: Add blocked_donor link to task for smarter mutex handoffs

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.

[jstultz: This patch was split out from larger proxy patch]
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>
Signed-off-by: John Stultz <jstultz@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20260512025635.2840817-8-jstultz@google.com

Author: Peter Zijlstra

include/linux/sched.h

@@ -1250,6 +1250,13 @@ struct task_struct {
 	struct mutex			*blocked_on;	/* lock we're blocked on */
 	raw_spinlock_t			blocked_lock;
 
+	/*
+	 * The task that is boosting this task; a back link for the current
+	 * donor stack. Set in schedule() -> find_proxy_task() and only stable
+	 * under preempt_disable().
+	 */
+	struct task_struct		*blocked_donor;
+
 #ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
 	/*
 	 * Encoded lock address causing task block (lower 2 bits = type from

init/init_task.c

@@ -200,6 +200,7 @@ 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_donor = NULL,
 #ifdef CONFIG_RT_MUTEXES
 	.pi_waiters	= RB_ROOT_CACHED,
 	.pi_top_task	= NULL,

kernel/fork.c

@@ -2224,6 +2224,7 @@ __latent_entropy struct task_struct *copy_process(
 	lockdep_init_task(p);
 
 	p->blocked_on = NULL; /* not blocked yet */
+	p->blocked_donor = NULL; /* nobody is boosting p yet */
 
 #ifdef CONFIG_BCACHE
 	p->sequential_io	= 0;

kernel/locking/mutex.c

@@ -981,15 +981,22 @@ EXPORT_SYMBOL_GPL(ww_mutex_lock_interruptible);
 static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigned long ip)
 	__releases(lock)
 {
-	struct task_struct *next = NULL;
+	struct task_struct *donor, *next = NULL;
 	struct mutex_waiter *waiter;
-	DEFINE_WAKE_Q(wake_q);
 	unsigned long owner;
 	unsigned long flags;
 
 	mutex_release(&lock->dep_map, ip);
 	__release(lock);
 
+	/*
+	 * Ensures the proxy donor stack is stable across unlock and handoff.
+	 * Specifically, it avoids the case where current->blocked_donor is
+	 * NULL when it is inspected while doing the unlock, but a preemption
+	 * before taking the wake_lock would make it set and a hand-off is
+	 * missed.
+	 */
+	guard(preempt)();
 	/*
 	 * Release the lock before (potentially) taking the spinlock such that
 	 * other contenders can get on with things ASAP.
@@ -1002,6 +1009,12 @@ 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;
 
@@ -1014,20 +1027,53 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
 	}
 
 	raw_spin_lock_irqsave(&lock->wait_lock, flags);
+	raw_spin_lock(&current->blocked_lock);
 	debug_mutex_unlock(lock);
+
+	if (sched_proxy_exec()) {
+		/*
+		 * 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 = get_task_struct(donor);
+				__set_task_blocked_on_waking(donor, next_lock);
+				current->blocked_donor = NULL;
+			}
+			raw_spin_unlock(&donor->blocked_lock);
+		}
+	}
+
+	/*
+	 * Failing that, pick first on the wait list.
+	 */
 	waiter = lock->first_waiter;
-	if (waiter) {
-		next = waiter->task;
+	if (!next && waiter) {
+		next = get_task_struct(waiter->task);
 
+		raw_spin_lock_nested(&next->blocked_lock, SINGLE_DEPTH_NESTING);
 		debug_mutex_wake_waiter(lock, waiter);
-		set_task_blocked_on_waking(next, lock);
-		wake_q_add(&wake_q, next);
+		__set_task_blocked_on_waking(next, lock);
+		raw_spin_unlock(&next->blocked_lock);
+
 	}
 
 	if (owner & MUTEX_FLAG_HANDOFF)
 		__mutex_handoff(lock, next);
 
-	raw_spin_unlock_irqrestore_wake(&lock->wait_lock, flags, &wake_q);
+	raw_spin_unlock(&current->blocked_lock);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
+	if (next) {
+		wake_up_process(next);
+		put_task_struct(next);
+	}
 }
 
 #ifndef CONFIG_DEBUG_LOCK_ALLOC

kernel/sched/core.c

@@ -6827,7 +6827,17 @@ static void proxy_migrate_task(struct rq *rq, struct rq_flags *rf,
  * 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:
  *
@@ -6969,6 +6979,7 @@ 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);
 	return owner;
@@ -7125,6 +7136,7 @@ static void __sched notrace __schedule(int sched_mode)
 			clear_task_blocked_on(prev, NULL);
 
 		rq_set_donor(rq, next);
+		next->blocked_donor = NULL;
 		if (unlikely(next->is_blocked && next->blocked_on)) {
 			next = find_proxy_task(rq, next, &rf);
 			if (!next) {