From c1e2f0eaf015fb7076d51a339011f2383e6dd389 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 8 Dec 2017 13:49:39 +0100 Subject: futex: Avoid violating the 10th rule of futex Julia reported futex state corruption in the following scenario: waiter waker stealer (prio > waiter) futex(WAIT_REQUEUE_PI, uaddr, uaddr2, timeout=[N ms]) futex_wait_requeue_pi() futex_wait_queue_me() freezable_schedule() futex(LOCK_PI, uaddr2) futex(CMP_REQUEUE_PI, uaddr, uaddr2, 1, 0) /* requeues waiter to uaddr2 */ futex(UNLOCK_PI, uaddr2) wake_futex_pi() cmp_futex_value_locked(uaddr2, waiter) wake_up_q() task> futex(LOCK_PI, uaddr2) __rt_mutex_start_proxy_lock() try_to_take_rt_mutex() /* steals lock */ rt_mutex_set_owner(lock, stealer) rt_mutex_wait_proxy_lock() __rt_mutex_slowlock() try_to_take_rt_mutex() /* fails, lock held by stealer */ if (timeout && !timeout->task) return -ETIMEDOUT; fixup_owner() /* lock wasn't acquired, so, fixup_pi_state_owner skipped */ return -ETIMEDOUT; /* At this point, we've returned -ETIMEDOUT to userspace, but the * futex word shows waiter to be the owner, and the pi_mutex has * stealer as the owner */ futex_lock(LOCK_PI, uaddr2) -> bails with EDEADLK, futex word says we're owner. And suggested that what commit: 73d786bd043e ("futex: Rework inconsistent rt_mutex/futex_q state") removes from fixup_owner() looks to be just what is needed. And indeed it is -- I completely missed that requeue_pi could also result in this case. So we need to restore that, except that subsequent patches, like commit: 16ffa12d7425 ("futex: Pull rt_mutex_futex_unlock() out from under hb->lock") changed all the locking rules. Even without that, the sequence: - if (rt_mutex_futex_trylock(&q->pi_state->pi_mutex)) { - locked = 1; - goto out; - } - raw_spin_lock_irq(&q->pi_state->pi_mutex.wait_lock); - owner = rt_mutex_owner(&q->pi_state->pi_mutex); - if (!owner) - owner = rt_mutex_next_owner(&q->pi_state->pi_mutex); - raw_spin_unlock_irq(&q->pi_state->pi_mutex.wait_lock); - ret = fixup_pi_state_owner(uaddr, q, owner); already suggests there were races; otherwise we'd never have to look at next_owner. So instead of doing 3 consecutive wait_lock sections with who knows what races, we do it all in a single section. Additionally, the usage of pi_state->owner in fixup_owner() was only safe because only the rt_mutex owner would modify it, which this additional case wrecks. Luckily the values can only change away and not to the value we're testing, this means we can do a speculative test and double check once we have the wait_lock. Fixes: 73d786bd043e ("futex: Rework inconsistent rt_mutex/futex_q state") Reported-by: Julia Cartwright Reported-by: Gratian Crisan Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Tested-by: Julia Cartwright Tested-by: Gratian Crisan Cc: Darren Hart Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20171208124939.7livp7no2ov65rrc@hirez.programming.kicks-ass.net --- kernel/locking/rtmutex.c | 26 +++++++++++++++++++------- 1 file changed, 19 insertions(+), 7 deletions(-) (limited to 'kernel/locking/rtmutex.c') diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 6f3dba6e4e9e..65cc0cb984e6 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1290,6 +1290,19 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, return ret; } +static inline int __rt_mutex_slowtrylock(struct rt_mutex *lock) +{ + int ret = try_to_take_rt_mutex(lock, current, NULL); + + /* + * try_to_take_rt_mutex() sets the lock waiters bit + * unconditionally. Clean this up. + */ + fixup_rt_mutex_waiters(lock); + + return ret; +} + /* * Slow path try-lock function: */ @@ -1312,13 +1325,7 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock) */ raw_spin_lock_irqsave(&lock->wait_lock, flags); - ret = try_to_take_rt_mutex(lock, current, NULL); - - /* - * try_to_take_rt_mutex() sets the lock waiters bit - * unconditionally. Clean this up. - */ - fixup_rt_mutex_waiters(lock); + ret = __rt_mutex_slowtrylock(lock); raw_spin_unlock_irqrestore(&lock->wait_lock, flags); @@ -1505,6 +1512,11 @@ int __sched rt_mutex_futex_trylock(struct rt_mutex *lock) return rt_mutex_slowtrylock(lock); } +int __sched __rt_mutex_futex_trylock(struct rt_mutex *lock) +{ + return __rt_mutex_slowtrylock(lock); +} + /** * rt_mutex_timed_lock - lock a rt_mutex interruptible * the timeout structure is provided -- cgit v1.2.3