Date:   Mon, 20 Mar 2023 23:37:10 +0000
In-Reply-To: <20230320233720.3488453-1-jstultz@google.com>
Mime-Version: 1.0
References: <20230320233720.3488453-1-jstultz@google.com>
Message-ID: <20230320233720.3488453-3-jstultz@google.com>
Subject: [PATCH v2 02/12] 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>,
        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: 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
---
 include/linux/sched.h        | 6 ++----
 kernel/fork.c                | 4 ++--
 kernel/locking/mutex-debug.c | 9 +++++----
 kernel/locking/mutex.c       | 7 +++++++
 4 files changed, 16 insertions(+), 10 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 63d242164b1a..9924d1926bc3 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1139,10 +1139,8 @@ 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 task_struct		*blocked_proxy;	/* task that is boosting us */
+	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 d8cda4c6de6c..ad27fa09fe70 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2223,9 +2223,9 @@ static __latent_entropy struct task_struct *copy_process(
 	lockdep_init_task(p);
 #endif
 
-#ifdef CONFIG_DEBUG_MUTEXES
+	p->blocked_proxy = NULL; /* nobody is boosting us yet */
 	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 1582756914df..f5296aa82255 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -645,6 +645,7 @@ __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 (;;) {
@@ -682,6 +683,10 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 
 		first = __mutex_waiter_is_first(lock, &waiter);
 
+		/*
+		 * Gets reset by ttwu_runnable().
+		 */
+		current->blocked_on = lock;
 		set_current_state(state);
 		/*
 		 * Here we order against unlock; we must either see it change
@@ -719,6 +724,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 	debug_mutex_free_waiter(&waiter);
 
 skip_wait:
+	current->blocked_on = NULL;
 	/* got the lock - cleanup and rejoice! */
 	lock_acquired(&lock->dep_map, ip);
 	trace_contention_end(lock, 0);
@@ -733,6 +739,7 @@ __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:
-- 
2.40.0.rc1.284.g88254d51c5-goog