From 56222b212e8edb1cf51f5dd73ff645809b082b40 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 22 Mar 2017 11:36:00 +0100 Subject: futex: Drop hb->lock before enqueueing on the rtmutex When PREEMPT_RT_FULL does the spinlock -> rt_mutex substitution the PI chain code will (falsely) report a deadlock and BUG. The problem is that it hold hb->lock (now an rt_mutex) while doing task_blocks_on_rt_mutex on the futex's pi_state::rtmutex. This, when interleaved just right with futex_unlock_pi() leads it to believe to see an AB-BA deadlock. Task1 (holds rt_mutex, Task2 (does FUTEX_LOCK_PI) does FUTEX_UNLOCK_PI) lock hb->lock lock rt_mutex (as per start_proxy) lock hb->lock Which is a trivial AB-BA. It is not an actual deadlock, because it won't be holding hb->lock by the time it actually blocks on the rt_mutex, but the chainwalk code doesn't know that and it would be a nightmare to handle this gracefully. To avoid this problem, do the same as in futex_unlock_pi() and drop hb->lock after acquiring wait_lock. This still fully serializes against futex_unlock_pi(), since adding to the wait_list does the very same lock dance, and removing it holds both locks. Aside of solving the RT problem this makes the lock and unlock mechanism symetric and reduces the hb->lock held time. Reported-and-tested-by: Sebastian Andrzej Siewior Suggested-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Cc: juri.lelli@arm.com Cc: xlpang@redhat.com Cc: rostedt@goodmis.org Cc: mathieu.desnoyers@efficios.com Cc: jdesfossez@efficios.com Cc: dvhart@infradead.org Cc: bristot@redhat.com Link: http://lkml.kernel.org/r/20170322104152.161341537@infradead.org Signed-off-by: Thomas Gleixner --- kernel/locking/rtmutex.c | 49 +++++++++++++++++++++++------------------ kernel/locking/rtmutex_common.h | 3 +++ 2 files changed, 31 insertions(+), 21 deletions(-) (limited to 'kernel/locking') diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 48418a1733b8..dd103124166b 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1669,31 +1669,14 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock, rt_mutex_set_owner(lock, NULL); } -/** - * rt_mutex_start_proxy_lock() - Start lock acquisition for another task - * @lock: the rt_mutex to take - * @waiter: the pre-initialized rt_mutex_waiter - * @task: the task to prepare - * - * Returns: - * 0 - task blocked on lock - * 1 - acquired the lock for task, caller should wake it up - * <0 - error - * - * Special API call for FUTEX_REQUEUE_PI support. - */ -int rt_mutex_start_proxy_lock(struct rt_mutex *lock, +int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, struct task_struct *task) { int ret; - raw_spin_lock_irq(&lock->wait_lock); - - if (try_to_take_rt_mutex(lock, task, NULL)) { - raw_spin_unlock_irq(&lock->wait_lock); + if (try_to_take_rt_mutex(lock, task, NULL)) return 1; - } /* We enforce deadlock detection for futexes */ ret = task_blocks_on_rt_mutex(lock, waiter, task, @@ -1712,13 +1695,37 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock, if (unlikely(ret)) remove_waiter(lock, waiter); - raw_spin_unlock_irq(&lock->wait_lock); - debug_rt_mutex_print_deadlock(waiter); return ret; } +/** + * rt_mutex_start_proxy_lock() - Start lock acquisition for another task + * @lock: the rt_mutex to take + * @waiter: the pre-initialized rt_mutex_waiter + * @task: the task to prepare + * + * Returns: + * 0 - task blocked on lock + * 1 - acquired the lock for task, caller should wake it up + * <0 - error + * + * Special API call for FUTEX_REQUEUE_PI support. + */ +int rt_mutex_start_proxy_lock(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter, + struct task_struct *task) +{ + int ret; + + raw_spin_lock_irq(&lock->wait_lock); + ret = __rt_mutex_start_proxy_lock(lock, waiter, task); + raw_spin_unlock_irq(&lock->wait_lock); + + return ret; +} + /** * rt_mutex_next_owner - return the next owner of the lock * diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h index 1e93e15a0e45..b1ccfea2effe 100644 --- a/kernel/locking/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h @@ -104,6 +104,9 @@ extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock, extern void rt_mutex_proxy_unlock(struct rt_mutex *lock, struct task_struct *proxy_owner); extern void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter); +extern int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter, + struct task_struct *task); extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, struct task_struct *task); -- cgit v1.2.3