From 69cd9eba38867a493a043bb13eb9b33cad5f1a9a Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 8 Apr 2014 15:30:07 -0700 Subject: futex: avoid race between requeue and wake Jan Stancek reported: "pthread_cond_broadcast/4-1.c testcase from openposix testsuite (LTP) occasionally fails, because some threads fail to wake up. Testcase creates 5 threads, which are all waiting on same condition. Main thread then calls pthread_cond_broadcast() without holding mutex, which calls: futex(uaddr1, FUTEX_CMP_REQUEUE_PRIVATE, 1, 2147483647, uaddr2, ..) This immediately wakes up single thread A, which unlocks mutex and tries to wake up another thread: futex(uaddr2, FUTEX_WAKE_PRIVATE, 1) If thread A manages to call futex_wake() before any waiters are requeued for uaddr2, no other thread is woken up" The ordering constraints for the hash bucket waiter counting are that the waiter counts have to be incremented _before_ getting the spinlock (because the spinlock acts as part of the memory barrier), but the "requeue" operation didn't honor those rules, and nobody had even thought about that case. This fairly simple patch just increments the waiter count for the target hash bucket (hb2) when requeing a futex before taking the locks. It then decrements them again after releasing the lock - the code that actually moves the futex(es) between hash buckets will do the additional required waiter count housekeeping. Reported-and-tested-by: Jan Stancek Acked-by: Davidlohr Bueso Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: stable@vger.kernel.org # 3.14 Signed-off-by: Linus Torvalds --- kernel/futex.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'kernel') diff --git a/kernel/futex.c b/kernel/futex.c index 67dacaf93e56..6801b3751a95 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1452,6 +1452,7 @@ retry: hb2 = hash_futex(&key2); retry_private: + hb_waiters_inc(hb2); double_lock_hb(hb1, hb2); if (likely(cmpval != NULL)) { @@ -1461,6 +1462,7 @@ retry_private: if (unlikely(ret)) { double_unlock_hb(hb1, hb2); + hb_waiters_dec(hb2); ret = get_user(curval, uaddr1); if (ret) @@ -1510,6 +1512,7 @@ retry_private: break; case -EFAULT: double_unlock_hb(hb1, hb2); + hb_waiters_dec(hb2); put_futex_key(&key2); put_futex_key(&key1); ret = fault_in_user_writeable(uaddr2); @@ -1519,6 +1522,7 @@ retry_private: case -EAGAIN: /* The owner was exiting, try again. */ double_unlock_hb(hb1, hb2); + hb_waiters_dec(hb2); put_futex_key(&key2); put_futex_key(&key1); cond_resched(); @@ -1594,6 +1598,7 @@ retry_private: out_unlock: double_unlock_hb(hb1, hb2); + hb_waiters_dec(hb2); /* * drop_futex_key_refs() must be called outside the spinlocks. During -- cgit v1.2.3