[RESEND][PATCH v17 3/8] locking/mutex: Add p->blocked_on wrappers for correctness checks

[John Stultz]

From: Valentin Schneider <valentin.schneider@xxxxxxx>

This lets us assert mutex::wait_lock is held whenever we access
p->blocked_on, as well as warn us for unexpected state changes.

Signed-off-by: Valentin Schneider <valentin.schneider@xxxxxxx>
[fix conflicts, call in more places]
Signed-off-by: Connor O'Brien <connoro@xxxxxxxxxx>
[jstultz: tweaked commit subject, reworked a good bit]
Signed-off-by: John Stultz <jstultz@xxxxxxxxxx>
---
v2:
* Added get_task_blocked_on() accessor
v4:
* Address READ_ONCE usage that was dropped in v2
* Reordered to be a later add on to the main patch series as
  Peter was unhappy with similar wrappers in other patches.
v5:
* Added some extra correctness checking in wrappers
v7:
* Tweaks to reorder this change in the patch series
* Minor cleanup to set_task_blocked_on() suggested by Metin Kaya
v15:
* Split out into its own patch again.
* Further improve assumption checks in helpers.
v16:
* Fix optimistic spin case that can call schedule()
v17:
* Fix typos caught by Metin Kaya
* Add lockdep_assert_held_once and drop the READ_ONCE in
  __get_task_blocked_on(), as suggested by Juri Lelli

Cc: Joel Fernandes <joelagnelf@xxxxxxxxxx>
Cc: Qais Yousef <qyousef@xxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Juri Lelli <juri.lelli@xxxxxxxxxx>
Cc: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
Cc: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>
Cc: Valentin Schneider <vschneid@xxxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Ben Segall <bsegall@xxxxxxxxxx>
Cc: Zimuzo Ezeozue <zezeozue@xxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Cc: Waiman Long <longman@xxxxxxxxxx>
Cc: Boqun Feng <boqun.feng@xxxxxxxxx>
Cc: "Paul E. McKenney" <paulmck@xxxxxxxxxx>
Cc: Metin Kaya <Metin.Kaya@xxxxxxx>
Cc: Xuewen Yan <xuewen.yan94@xxxxxxxxx>
Cc: K Prateek Nayak <kprateek.nayak@xxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Daniel Lezcano <daniel.lezcano@xxxxxxxxxx>
Cc: Suleiman Souhlal <suleiman@xxxxxxxxxx>
Cc: kernel-team@xxxxxxxxxxx
---
 include/linux/sched.h        | 54 ++++++++++++++++++++++++++++++++++--
 kernel/locking/mutex-debug.c |  4 +--
 kernel/locking/mutex.c       | 32 ++++++++++-----------
 kernel/locking/ww_mutex.h    |  6 ++--
 4 files changed, 70 insertions(+), 26 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 10be203ddb7e1..37c081be30ca6 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -34,6 +34,7 @@
 #include <linux/sched/prio.h>
 #include <linux/sched/types.h>
 #include <linux/signal_types.h>
+#include <linux/spinlock.h>
 #include <linux/syscall_user_dispatch_types.h>
 #include <linux/mm_types_task.h>
 #include <linux/netdevice_xmit.h>
@@ -2181,6 +2182,57 @@ extern int __cond_resched_rwlock_write(rwlock_t *lock);
 	__cond_resched_rwlock_write(lock);					\
 })
 
+static inline void __set_task_blocked_on(struct task_struct *p, struct mutex *m)
+{
+	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);
+	/*
+	 * 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(p->blocked_on && p->blocked_on != m);
+	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);
+}
+
+static inline void __clear_task_blocked_on(struct task_struct *p, struct mutex *m)
+{
+	WARN_ON_ONCE(!m);
+	/* 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(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);
+	__clear_task_blocked_on(p, m);
+}
+
+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;
+}
+
 static __always_inline bool need_resched(void)
 {
 	return unlikely(tif_need_resched());
@@ -2220,8 +2272,6 @@ extern bool sched_task_on_rq(struct task_struct *p);
 extern unsigned long get_wchan(struct task_struct *p);
 extern struct task_struct *cpu_curr_snapshot(int cpu);
 
-#include <linux/spinlock.h>
-
 /*
  * In order to reduce various lock holder preemption latencies provide an
  * interface to see if a vCPU is currently running or not.
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 758b7a6792b0c..949103fd8e9b5 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(task->blocked_on);
+	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 = READ_ONCE(task->blocked_on);
+	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 5243e59d75f40..ec39abbaae85a 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -643,8 +643,7 @@ __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_task_blocked_on(current, lock);
 	set_current_state(state);
 	trace_contention_begin(lock, LCB_F_MUTEX);
 	for (;;) {
@@ -684,9 +683,9 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 		/*
 		 * 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.
+		 * it to the lock we are trying to acquire.
 		 */
-		current->blocked_on = lock;
+		set_task_blocked_on(current, lock);
 		set_current_state(state);
 		/*
 		 * Here we order against unlock; we must either see it change
@@ -698,11 +697,15 @@ __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;
+			/*
+			 * mutex_optimistic_spin() can call schedule(), so
+			 * 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))
 				break;
-			current->blocked_on = lock;
+			set_task_blocked_on(current, lock);
 			trace_contention_begin(lock, LCB_F_MUTEX);
 		}
 
@@ -710,7 +713,7 @@ __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;
+	__clear_task_blocked_on(current, lock);
 	__set_current_state(TASK_RUNNING);
 
 	if (ww_ctx) {
@@ -740,11 +743,11 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 	return 0;
 
 err:
-	current->blocked_on = NULL;
+	__clear_task_blocked_on(current, lock);
 	__set_current_state(TASK_RUNNING);
 	__mutex_remove_waiter(lock, &waiter);
 err_early_kill:
-	WARN_ON(current->blocked_on);
+	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);
@@ -954,14 +957,7 @@ 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;
+		__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 00db40946328e..086fd5487ca77 100644
--- a/kernel/locking/ww_mutex.h
+++ b/kernel/locking/ww_mutex.h
@@ -289,9 +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.
 		 */
-		WARN_ON(waiter->task->blocked_on &&
-			waiter->task->blocked_on != lock);
-		waiter->task->blocked_on = NULL;
+		__clear_task_blocked_on(waiter->task, lock);
 		wake_q_add(wake_q, waiter->task);
 	}
 
@@ -345,7 +343,7 @@ static bool __ww_mutex_wound(struct MUTEX *lock,
 			 * blocked_on pointer. Otherwise we can see circular
 			 * blocked_on relationships that can't resolve.
 			 */
-			owner->blocked_on = NULL;
+			__clear_task_blocked_on(owner, lock);
 			wake_q_add(wake_q, owner);
 		}
 		return true;
-- 
2.49.0.1204.g71687c7c1d-goog