Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:2 as permitted sender) client-ip=2620:137:e000::3:2;
Date:   Mon,  6 Nov 2023 19:34:48 +0000
In-Reply-To: <20231106193524.866104-1-jstultz@google.com>
Mime-Version: 1.0
References: <20231106193524.866104-1-jstultz@google.com>
Message-ID: <20231106193524.866104-6-jstultz@google.com>
Subject: [PATCH v6 05/20] locking/mutex: Rework task_struct::blocked_on
From:   John Stultz <jstultz@google.com>
To:     LKML <linux-kernel@vger.kernel.org>
Cc:     Peter Zijlstra <peterz@infradead.org>,
        Joel Fernandes <joelaf@google.com>,
        Qais Yousef <qyousef@google.com>,
        Ingo Molnar <mingo@redhat.com>,
        Juri Lelli <juri.lelli@redhat.com>,
        Vincent Guittot <vincent.guittot@linaro.org>,
        Dietmar Eggemann <dietmar.eggemann@arm.com>,
        Valentin Schneider <vschneid@redhat.com>,
        Steven Rostedt <rostedt@goodmis.org>,
        Ben Segall <bsegall@google.com>,
        Zimuzo Ezeozue <zezeozue@google.com>,
        Youssef Esmat <youssefesmat@google.com>,
        Mel Gorman <mgorman@suse.de>,
        Daniel Bristot de Oliveira <bristot@redhat.com>,
        Will Deacon <will@kernel.org>,
        Waiman Long <longman@redhat.com>,
        Boqun Feng <boqun.feng@gmail.com>,
        "Paul E . McKenney" <paulmck@kernel.org>, kernel-team@android.com,
        "Connor O'Brien" <connoro@google.com>,
        John Stultz <jstultz@google.com>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

From: Peter Zijlstra <peterz@infradead.org>

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

   task
     | blocked-on
     v
   mutex
     | owner
     v
   task

Cc: Joel Fernandes <joelaf@google.com>
Cc: Qais Yousef <qyousef@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Valentin Schneider <vschneid@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Segall <bsegall@google.com>
Cc: Zimuzo Ezeozue <zezeozue@google.com>
Cc: Youssef Esmat <youssefesmat@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Daniel Bristot de Oliveira <bristot@redhat.com>
Cc: Will Deacon <will@kernel.org>
Cc: Waiman Long <longman@redhat.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: "Paul E . McKenney" <paulmck@kernel.org>
Cc: kernel-team@android.com
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
[minor changes while rebasing]
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Connor O'Brien <connoro@google.com>
[jstultz: Fix blocked_on tracking in __mutex_lock_common in error paths]
Signed-off-by: John Stultz <jstultz@google.com>
---
v2:
* Fixed blocked_on tracking in error paths that was causing crashes
v4:
* Ensure we clear blocked_on when waking ww_mutexes to die or wound.
  This is critical so we don't get ciruclar blocked_on relationships
  that can't be resolved.
v5:
* Fix potential bug where the skip_wait path might clear blocked_on
  when that path never set it
* Slight tweaks to where we set blocked_on to make it consistent,
  along with extra WARN_ON correctness checking
* Minor comment changes
---
 include/linux/sched.h        |  5 +----
 kernel/fork.c                |  3 +--
 kernel/locking/mutex-debug.c |  9 +++++----
 kernel/locking/mutex.c       | 10 ++++++++++
 kernel/locking/ww_mutex.h    | 17 +++++++++++++++--
 5 files changed, 32 insertions(+), 12 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4f5b0710c0f1..22a6ac47d5fb 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1145,10 +1145,7 @@ 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_DEBUG_ATOMIC_SLEEP
 	int				non_block_count;
diff --git a/kernel/fork.c b/kernel/fork.c
index 3b6d20dfb9a8..1c3f7eaa9239 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2455,9 +2455,8 @@ __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;
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index bc8abb8549d2..7228909c3e62 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -52,17 +52,18 @@ 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;
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 2c5d1a9cf767..73064e4865b7 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -622,6 +622,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 			goto err_early_kill;
 	}
 
+	current->blocked_on = lock;
 	set_current_state(state);
 	trace_contention_begin(lock, LCB_F_MUTEX);
 	for (;;) {
@@ -662,6 +663,10 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 
 		first = __mutex_waiter_is_first(lock, &waiter);
 
+		/*
+		 * Gets reset by unlock path().
+		 */
+		current->blocked_on = lock;
 		set_current_state(state);
 		/*
 		 * Here we order against unlock; we must either see it change
@@ -682,6 +687,7 @@ __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) {
@@ -712,9 +718,11 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 	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(&lock->wait_lock, flags);
 	debug_mutex_free_waiter(&waiter);
@@ -926,6 +934,8 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
 		next = waiter->task;
 
 		debug_mutex_wake_waiter(lock, waiter);
+		WARN_ON(next->blocked_on != lock);
+		next->blocked_on = NULL;
 		wake_q_add(&wake_q, next);
 	}
 
diff --git a/kernel/locking/ww_mutex.h b/kernel/locking/ww_mutex.h
index 8b94f4b89e74..8bb334491732 100644
--- a/kernel/locking/ww_mutex.h
+++ b/kernel/locking/ww_mutex.h
@@ -284,6 +284,13 @@ __ww_mutex_die(struct MUTEX *lock, struct MUTEX_WAITER *waiter,
 #ifndef WW_RT
 		debug_mutex_wake_waiter(lock, waiter);
 #endif
+		/*
+		 * 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 != lock);
+		waiter->task->blocked_on = NULL;
 		wake_q_add(wake_q, waiter->task);
 	}
 
@@ -331,9 +338,15 @@ 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;
 	}
 
-- 
2.42.0.869.gea05f2083d-goog