From 74e144274af39935b0f410c0ee4d2b91c3730414 Mon Sep 17 00:00:00 2001 From: Ji'an Zhou Date: Tue, 2 Jun 2026 09:12:04 +0000 Subject: futex/requeue: Prevent NULL pointer dereference in remove_waiter() on self-deadlock When FUTEX_CMP_REQUEUE_PI requeues a non-top waiter that already owns the target PI futex, task_blocks_on_rt_mutex() returns -EDEADLK before setting waiter->task. The subsequent remove_waiter() in rt_mutex_start_proxy_lock() dereferences the NULL waiter->task, causing a kernel crash. Add a self-deadlock check for non-top waiters before calling rt_mutex_start_proxy_lock(), analogous to the top-waiter check in futex_lock_pi_atomic(). Fixes: 3bfdc63936dd4773109b7b8c280c0f3b5ae7d349 ("rtmutex: Use waiter::task instead of current in remove_waiter()") Signed-off-by: Ji'an Zhou Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org --- kernel/futex/requeue.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/kernel/futex/requeue.c b/kernel/futex/requeue.c index b597cb3d17fc..1d99a84dc9ad 100644 --- a/kernel/futex/requeue.c +++ b/kernel/futex/requeue.c @@ -643,6 +643,12 @@ retry_private: continue; } + /* Self-deadlock: non-top waiter already owns the PI futex. */ + if (rt_mutex_owner(&pi_state->pi_mutex) == this->task) { + ret = -EDEADLK; + break; + } + ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex, this->rt_waiter, this->task); -- cgit v1.2.3 From 40a25d59e85b3c8709ac2424d44f65610467871e Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Thu, 7 May 2026 04:29:13 -0700 Subject: locking/rtmutex: Skip remove_waiter() when waiter is not enqueued syzbot triggered the following splat in remove_waiter() via FUTEX_CMP_REQUEUE_PI: KASAN: null-ptr-deref in range [0x0000000000000a88-0x0000000000000a8f] class_raw_spinlock_constructor remove_waiter+0x159/0x1200 kernel/locking/rtmutex.c:1561 rt_mutex_start_proxy_lock+0x103/0x120 futex_requeue+0x10e4/0x20d0 __x64_sys_futex+0x34f/0x4d0 task_blocks_on_rt_mutex() does not arm the waiter upon deadlock detection, leaving waiter->task nil, where 3bfdc63936dd ("rtmutex: Use waiter::task instead of current in remove_waiter()") made this fatal. Furthermore, rt_mutex_start_proxy_lock() should not be calling into remove_waiter() upon a successfully grabbing the rtmutex. 1a1fb985f2e2 ("futex: Handle early deadlock return correctly"), moved the remove_waiter() out of __rt_mutex_start_proxy_lock() (where 'ret' was only ever 0 or < 0) into the wrapper. Tighten this check to account for try_to_take_rt_mutex(). Fixes: 3bfdc63936dd ("rtmutex: Use waiter::task instead of current in remove_waiter()") Reported-by: syzbot+78147abe6c524f183ee9@syzkaller.appspotmail.com Signed-off-by: Davidlohr Bueso Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Closes: https://lore.kernel.org/all/69f114ac.050a0220.ac8b.0003.GAE@google.com/ Link: https://patch.msgid.link/20260507112913.1019537-1-dave@stgolabs.net --- kernel/locking/rtmutex.c | 3 +++ kernel/locking/rtmutex_api.c | 2 +- 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 4f386ea6c792..daeeeef973e2 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1558,6 +1558,9 @@ static void __sched remove_waiter(struct rt_mutex_base *lock, lockdep_assert_held(&lock->wait_lock); + if (!waiter_task) /* never enqueued */ + return; + scoped_guard(raw_spinlock, &waiter_task->pi_lock) { rt_mutex_dequeue(lock, waiter); waiter_task->pi_blocked_on = NULL; diff --git a/kernel/locking/rtmutex_api.c b/kernel/locking/rtmutex_api.c index 124219aea46e..514fce7a4e0a 100644 --- a/kernel/locking/rtmutex_api.c +++ b/kernel/locking/rtmutex_api.c @@ -365,7 +365,7 @@ int __sched rt_mutex_start_proxy_lock(struct rt_mutex_base *lock, raw_spin_lock_irq(&lock->wait_lock); ret = __rt_mutex_start_proxy_lock(lock, waiter, task, &wake_q); - if (unlikely(ret)) + if (unlikely(ret < 0)) remove_waiter(lock, waiter); preempt_disable(); raw_spin_unlock_irq(&lock->wait_lock); -- cgit v1.2.3