| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20230601055846.2349566-5-jstultz@google.com>
Date: Thu, 1 Jun 2023 05:58:07 +0000
From: John Stultz <jstultz@...gle.com>
To: LKML <linux-kernel@...r.kernel.org>
Cc: Peter Zijlstra <peterz@...radead.org>,
Joel Fernandes <joelaf@...gle.com>,
Qais Yousef <qyousef@...gle.com>,
Ingo Molnar <mingo@...hat.com>,
Juri Lelli <juri.lelli@...hat.com>,
Vincent Guittot <vincent.guittot@...aro.org>,
Dietmar Eggemann <dietmar.eggemann@....com>,
Valentin Schneider <vschneid@...hat.com>,
Steven Rostedt <rostedt@...dmis.org>,
Ben Segall <bsegall@...gle.com>,
Zimuzo Ezeozue <zezeozue@...gle.com>,
Youssef Esmat <youssefesmat@...gle.com>,
Mel Gorman <mgorman@...e.de>,
Daniel Bristot de Oliveira <bristot@...hat.com>,
Will Deacon <will@...nel.org>,
Waiman Long <longman@...hat.com>,
Boqun Feng <boqun.feng@...il.com>,
"Paul E . McKenney" <paulmck@...nel.org>, kernel-team@...roid.com,
"Connor O'Brien" <connoro@...gle.com>,
John Stultz <jstultz@...gle.com>
Subject: [PATCH v4 04/13] locking/mutex: Rework task_struct::blocked_on
From: Peter Zijlstra <peterz@...radead.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@...gle.com>
Cc: Qais Yousef <qyousef@...gle.com>
Cc: Ingo Molnar <mingo@...hat.com>
Cc: Peter Zijlstra <peterz@...radead.org>
Cc: Juri Lelli <juri.lelli@...hat.com>
Cc: Vincent Guittot <vincent.guittot@...aro.org>
Cc: Dietmar Eggemann <dietmar.eggemann@....com>
Cc: Valentin Schneider <vschneid@...hat.com>
Cc: Steven Rostedt <rostedt@...dmis.org>
Cc: Ben Segall <bsegall@...gle.com>
Cc: Zimuzo Ezeozue <zezeozue@...gle.com>
Cc: Youssef Esmat <youssefesmat@...gle.com>
Cc: Mel Gorman <mgorman@...e.de>
Cc: Daniel Bristot de Oliveira <bristot@...hat.com>
Cc: Will Deacon <will@...nel.org>
Cc: Waiman Long <longman@...hat.com>
Cc: Boqun Feng <boqun.feng@...il.com>
Cc: "Paul E . McKenney" <paulmck@...nel.org>
Cc: kernel-team@...roid.com
Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
[minor changes while rebasing]
Signed-off-by: Juri Lelli <juri.lelli@...hat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
Signed-off-by: Connor O'Brien <connoro@...gle.com>
[jstultz: Fix blocked_on tracking in __mutex_lock_common in error paths]
Signed-off-by: John Stultz <jstultz@...gle.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.
---
include/linux/sched.h | 5 +----
kernel/fork.c | 3 +--
kernel/locking/mutex-debug.c | 9 +++++----
kernel/locking/mutex.c | 7 +++++++
kernel/locking/ww_mutex.h | 16 ++++++++++++++--
5 files changed, 28 insertions(+), 12 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 37dd571a1246..a312a2ff47bf 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1141,10 +1141,7 @@ 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 ed4e01daccaa..9244c540bb13 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2461,9 +2461,8 @@ __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 a528e7f42caa..d7a202c35ebe 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -646,6 +646,7 @@ __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 (;;) {
@@ -683,6 +684,10 @@ __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
@@ -720,6 +725,7 @@ __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);
@@ -734,6 +740,7 @@ __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:
diff --git a/kernel/locking/ww_mutex.h b/kernel/locking/ww_mutex.h
index 984a4e0bff36..7d623417b496 100644
--- a/kernel/locking/ww_mutex.h
+++ b/kernel/locking/ww_mutex.h
@@ -291,6 +291,12 @@ __ww_mutex_die(struct MUTEX *lock, struct MUTEX_WAITER *waiter,
debug_mutex_wake_waiter(lock, waiter);
#endif
wake_q_add(&ww_ctx->wake_q, waiter->task);
+ /*
+ * 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.
+ */
+ waiter->task->blocked_on = NULL;
}
return true;
@@ -336,9 +342,15 @@ 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) {
wake_q_add(&ww_ctx->wake_q, owner);
-
+ /*
+ * 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;
+ }
return true;
}
--
2.41.0.rc0.172.g3f132b7071-goog
Powered by blists - more mailing lists