locking: Fix __clear_task_blocked_on() warning from __ww_mutex_wound() path

The __clear_task_blocked_on() helper added a number of sanity
checks ensuring we hold the mutex wait lock and that the task
we are clearing blocked_on pointer (if set) matches the mutex.

However, there is an edge case in the _ww_mutex_wound() logic
where we need to clear the blocked_on pointer for the task that
owns the mutex, not the task that is waiting on the mutex.

For this case the sanity checks aren't valid, so handle this
by allowing a NULL lock to skip the additional checks.

K Prateek Nayak and Maarten Lankhorst also pointed out that in
this case where we don't hold the owner's mutex wait_lock, we
need to be a bit more careful using READ_ONCE/WRITE_ONCE in both
the __clear_task_blocked_on() and __set_task_blocked_on()
implementations to avoid accidentally tripping WARN_ONs if two
instances race. So do that here as well.

This issue was easier to miss, I realized, as the test-ww_mutex
driver only exercises the wait-die class of ww_mutexes. I've
sent a patch[1] to address this so the logic will be easier to
test.

[1]: https://lore.kernel.org/lkml/20250801023358.562525-2-jstultz@google.com/

Fixes: a4f0b6fef4b0 ("locking/mutex: Add p->blocked_on wrappers for correctness checks")
Closes: https://lore.kernel.org/lkml/68894443.a00a0220.26d0e1.0015.GAE@google.com/
Reported-by: syzbot+602c4720aed62576cd79@syzkaller.appspotmail.com
Reported-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: John Stultz <jstultz@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: K Prateek Nayak <kprateek.nayak@amd.com>
Acked-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Link: https://lore.kernel.org/r/20250805001026.2247040-1-jstultz@google.com

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 40d2fa90df425ad3a0d9be8d50b461703718aaa7..62103dd6a48e08626264f0b4b0964fc6725d3c7e 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2144,6 +2144,8 @@ static inline struct mutex *__get_task_blocked_on(struct task_struct *p)
 
 static inline void __set_task_blocked_on(struct task_struct *p, struct mutex *m)
 {
+       struct mutex *blocked_on = READ_ONCE(p->blocked_on);
+
        WARN_ON_ONCE(!m);
        /* The task should only be setting itself as blocked */
        WARN_ON_ONCE(p != current);
@@ -2154,8 +2156,8 @@ static inline void __set_task_blocked_on(struct task_struct *p, struct mutex *m)
         * 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;
+       WARN_ON_ONCE(blocked_on && blocked_on != m);
+       WRITE_ONCE(p->blocked_on, m);
 }
 
 static inline void set_task_blocked_on(struct task_struct *p, struct mutex *m)
@@ -2166,16 +2168,19 @@ static inline void set_task_blocked_on(struct task_struct *p, struct mutex *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;
+       if (m) {
+               struct mutex *blocked_on = READ_ONCE(p->blocked_on);
+
+               /* 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(blocked_on && blocked_on != m);
+       }
+       WRITE_ONCE(p->blocked_on, NULL);
 }
 
 static inline void clear_task_blocked_on(struct task_struct *p, struct mutex *m)

diff --git a/kernel/locking/ww_mutex.h b/kernel/locking/ww_mutex.h
index 086fd5487ca770a36ffbbf439e5c9cfef3180cea..31a785afee6c0ebfa36a2ceecc76e8fd27c9a739 100644 (file)
--- a/kernel/locking/ww_mutex.h
+++ b/kernel/locking/ww_mutex.h
@@ -342,8 +342,12 @@ static bool __ww_mutex_wound(struct MUTEX *lock,
                         * 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.
+                        *
+                        * NOTE: We pass NULL here instead of lock, because we
+                        * are waking the mutex owner, who may be currently
+                        * blocked on a different mutex.
                         */
-                       __clear_task_blocked_on(owner, lock);
+                       __clear_task_blocked_on(owner, NULL);
                        wake_q_add(wake_q, owner);
                }
                return true;