locking: Add task::blocked_lock to serialize blocked_on state

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>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: K Prateek Nayak <kprateek.nayak@amd.com>
Link: https://patch.msgid.link/20260324191337.1841376-5-jstultz@google.com

include/linux/sched.h

@@ -1238,6 +1238,7 @@ struct task_struct {
 #endif
 
 	struct mutex			*blocked_on;	/* lock we're blocked on */
+	raw_spinlock_t			blocked_lock;
 
 #ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
 	/*
@@ -2181,57 +2182,42 @@ extern int __cond_resched_rwlock_write(rwlock_t *lock) __must_hold(lock);
 #ifndef CONFIG_PREEMPT_RT
 static inline struct mutex *__get_task_blocked_on(struct task_struct *p)
 {
-	struct mutex *m = p->blocked_on;
-
-	if (m)
-		lockdep_assert_held_once(&m->wait_lock);
-	return m;
+	lockdep_assert_held_once(&p->blocked_lock);
+	return p->blocked_on;
 }
 
 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

init/init_task.c

@@ -169,6 +169,7 @@ 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),

kernel/fork.c

@@ -2076,6 +2076,7 @@ __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

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);

kernel/locking/mutex.c

@@ -656,6 +656,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 			goto err_early_kill;
 	}
 
+	raw_spin_lock(&current->blocked_lock);
 	__set_task_blocked_on(current, lock);
 	set_current_state(state);
 	trace_contention_begin(lock, LCB_F_MUTEX);
@@ -669,8 +670,9 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 		 * the handoff.
 		 */
 		if (__mutex_trylock(lock))
-			goto acquired;
+			break;
 
+		raw_spin_unlock(&current->blocked_lock);
 		/*
 		 * Check for signals and kill conditions while holding
 		 * wait_lock. This ensures the lock cancellation is ordered
@@ -693,12 +695,14 @@ __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(&current->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
@@ -709,25 +713,33 @@ __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(&current->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(&current->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(&current->blocked_lock);
 
 	if (ww_ctx) {
 		/*
@@ -756,11 +768,11 @@ skip_wait:
 	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);
@@ -971,7 +983,7 @@ 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);
 	}
 

kernel/locking/mutex.h

@@ -47,6 +47,12 @@ static inline struct task_struct *__mutex_owner(struct mutex *lock)
 	return (struct task_struct *)(atomic_long_read(&lock->owner) & ~MUTEX_FLAGS);
 }
 
+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);
+}
+
 #ifdef CONFIG_DEBUG_MUTEXES
 extern void debug_mutex_lock_common(struct mutex *lock,
 				    struct mutex_waiter *waiter);

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;

kernel/sched/core.c

@@ -6584,6 +6584,7 @@ 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)).
@@ -6603,8 +6604,9 @@ 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