locking/mutex: Rework task_struct::blocked_on

Track the blocked-on relation for mutexes, to allow following this
relation at schedule time.

   task
     | blocked-on
     v
   mutex
     | owner
     v
   task

This all will be used for tracking blocked-task/mutex chains
with the prox-execution patch in a similar fashion to how
priority inheritance is done with rt_mutexes.

For serialization, blocked-on is only set by the task itself
(current). And both when setting or clearing (potentially by
others), is done while holding the mutex::wait_lock.

[minor changes while rebasing]
[jstultz: Fix blocked_on tracking in __mutex_lock_common in error paths]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Connor O'Brien <connoro@google.com>
Signed-off-by: John Stultz <jstultz@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Link: https://lkml.kernel.org/r/20250712033407.2383110-3-jstultz@google.com

include/linux/sched.h

@@ -1230,10 +1230,7 @@ struct task_struct {
 	struct rt_mutex_waiter		*pi_blocked_on;
 #endif
 
-#ifdef CONFIG_DEBUG_MUTEXES
-	/* Mutex deadlock detection: */
-	struct mutex_waiter		*blocked_on;
-#endif
+	struct mutex			*blocked_on;	/* lock we're blocked on */
 
 #ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
 	/*

kernel/fork.c

@@ -2123,9 +2123,8 @@ __latent_entropy struct task_struct *copy_process(
 	lockdep_init_task(p);
 #endif
 
-#ifdef CONFIG_DEBUG_MUTEXES
 	p->blocked_on = NULL; /* not blocked yet */
-#endif
+
 #ifdef CONFIG_BCACHE
 	p->sequential_io	= 0;
 	p->sequential_io_avg	= 0;

kernel/locking/mutex-debug.c

@@ -53,17 +53,18 @@ void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
 {
 	lockdep_assert_held(&lock->wait_lock);
 
-	/* Mark the current thread as blocked on the lock: */
-	task->blocked_on = waiter;
+	/* Current thread can't be already blocked (since it's executing!) */
+	DEBUG_LOCKS_WARN_ON(task->blocked_on);
 }
 
 void debug_mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
 			 struct task_struct *task)
 {
+	struct mutex *blocked_on = READ_ONCE(task->blocked_on);
+
 	DEBUG_LOCKS_WARN_ON(list_empty(&waiter->list));
 	DEBUG_LOCKS_WARN_ON(waiter->task != task);
-	DEBUG_LOCKS_WARN_ON(task->blocked_on != waiter);
-	task->blocked_on = NULL;
+	DEBUG_LOCKS_WARN_ON(blocked_on && blocked_on != lock);
 
 	INIT_LIST_HEAD(&waiter->list);
 	waiter->task = NULL;

kernel/locking/mutex.c

@@ -644,6 +644,8 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 			goto err_early_kill;
 	}
 
+	WARN_ON(current->blocked_on);
+	current->blocked_on = lock;
 	set_current_state(state);
 	trace_contention_begin(lock, LCB_F_MUTEX);
 	for (;;) {
@@ -680,6 +682,12 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 
 		first = __mutex_waiter_is_first(lock, &waiter);
 
+		/*
+		 * 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 aquire.
+		 */
+		current->blocked_on = lock;
 		set_current_state(state);
 		/*
 		 * Here we order against unlock; we must either see it change
@@ -691,8 +699,11 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 
 		if (first) {
 			trace_contention_begin(lock, LCB_F_MUTEX | LCB_F_SPIN);
+			/* clear blocked_on as mutex_optimistic_spin may schedule() */
+			current->blocked_on = NULL;
 			if (mutex_optimistic_spin(lock, ww_ctx, &waiter))
 				break;
+			current->blocked_on = lock;
 			trace_contention_begin(lock, LCB_F_MUTEX);
 		}
 
@@ -700,6 +711,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 	}
 	raw_spin_lock_irqsave(&lock->wait_lock, flags);
 acquired:
+	current->blocked_on = NULL;
 	__set_current_state(TASK_RUNNING);
 
 	if (ww_ctx) {
@@ -729,9 +741,11 @@ skip_wait:
 	return 0;
 
 err:
+	current->blocked_on = NULL;
 	__set_current_state(TASK_RUNNING);
 	__mutex_remove_waiter(lock, &waiter);
 err_early_kill:
+	WARN_ON(current->blocked_on);
 	trace_contention_end(lock, ret);
 	raw_spin_unlock_irqrestore_wake(&lock->wait_lock, flags, &wake_q);
 	debug_mutex_free_waiter(&waiter);
@@ -942,6 +956,14 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
 		next = waiter->task;
 
 		debug_mutex_wake_waiter(lock, waiter);
+		/*
+		 * Unlock wakeups can be happening in parallel
+		 * (when optimistic spinners steal and release
+		 * the lock), so blocked_on may already be
+		 * cleared here.
+		 */
+		WARN_ON(next->blocked_on && next->blocked_on != lock);
+		next->blocked_on = NULL;
 		wake_q_add(&wake_q, next);
 	}
 

kernel/locking/ww_mutex.h

@@ -283,7 +283,15 @@ __ww_mutex_die(struct MUTEX *lock, struct MUTEX_WAITER *waiter,
 	if (waiter->ww_ctx->acquired > 0 && __ww_ctx_less(waiter->ww_ctx, ww_ctx)) {
 #ifndef WW_RT
 		debug_mutex_wake_waiter(lock, waiter);
+		/*
+		 * 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.
+		 */
+		WARN_ON(waiter->task->blocked_on &&
+			waiter->task->blocked_on != lock);
 #endif
+		waiter->task->blocked_on = NULL;
 		wake_q_add(wake_q, waiter->task);
 	}
 
@@ -331,9 +339,15 @@ static bool __ww_mutex_wound(struct MUTEX *lock,
 		 * it's wounded in __ww_mutex_check_kill() or has a
 		 * wakeup pending to re-read the wounded state.
 		 */
-		if (owner != current)
+		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.
+			 */
+			owner->blocked_on = NULL;
 			wake_q_add(wake_q, owner);
-
+		}
 		return true;
 	}