Messages in this thread Patch in this message | | | From | Jan Stancek <> | Subject | [PATCH] futex: avoid race between requeue and wake | Date | Tue, 8 Apr 2014 10:47:15 +0200 |
| |
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.
This patch is re-introducing check removed by: commit 11d4616bd07f38d496bd489ed8fad1dc4d928823 futex: revert back to the explicit waiter counting code
Taking hb->lock in this situation will ensure that thread A needs to wait in futex_wake() until main thread finishes requeue operation.
Signed-off-by: Jan Stancek <jstancek@redhat.com> --- kernel/futex.c | 5 ++++- 1 files changed, 4 insertions(+), 1 deletions(-)
diff --git a/kernel/futex.c b/kernel/futex.c index 67dacaf..5163899 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -284,7 +284,10 @@ static inline void hb_waiters_dec(struct futex_hash_bucket *hb) static inline int hb_waiters_pending(struct futex_hash_bucket *hb) { #ifdef CONFIG_SMP - return atomic_read(&hb->waiters); + if (spin_is_locked(&hb->lock)) + return 1; + else + return atomic_read(&hb->waiters); #else return 1; #endif -- 1.7.1
| |