From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753394AbaJFSdb (ORCPT ); Mon, 6 Oct 2014 14:33:31 -0400 Received: from mail-wg0-f47.google.com ([74.125.82.47]:48664 "EHLO mail-wg0-f47.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753335AbaJFSd3 (ORCPT ); Mon, 6 Oct 2014 14:33:29 -0400 From: Manfred Spraul To: Andrew Morton Cc: LKML , Davidlohr Bueso , Michael Kerrisk , Rafael Aquini , Rik van Riel , 1vier1@web.de, Manfred Spraul Subject: [PATCH 1/3] ipc/sem.c: Chance memory barrier in sem_lock() to smp_rmb() Date: Mon, 6 Oct 2014 20:32:41 +0200 Message-Id: <1412620363-2759-2-git-send-email-manfred@colorfullife.com> X-Mailer: git-send-email 1.9.3 In-Reply-To: <1412620363-2759-1-git-send-email-manfred@colorfullife.com> References: <1412620363-2759-1-git-send-email-manfred@colorfullife.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org When I fixed bugs in the sem_lock() logic, I was more conservative than necessary. Therefore it is safe to replace the smp_mb() with smp_rmb(). And: With smp_rmb(), semop() syscalls are up to 10% faster. The race we must protect against is: sem->lock is free sma->complex_count = 0 sma->sem_perm.lock held by thread B thread A: A: spin_lock(&sem->lock) B: sma->complex_count++; (now 1) B: spin_unlock(&sma->sem_perm.lock); A: spin_is_locked(&sma->sem_perm.lock); A: XXXXX memory barrier A: if (sma->complex_count == 0) Thread A must read the increased complex_count value, i.e. the read must not be reordered with the read of sem_perm.lock done by spin_is_locked(). Since it's about ordering of reads, smp_rmb() is sufficient. Signed-off-by: Manfred Spraul --- ipc/sem.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/ipc/sem.c b/ipc/sem.c index 454f6c6..ffc71de 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -326,10 +326,16 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops, /* Then check that the global lock is free */ if (!spin_is_locked(&sma->sem_perm.lock)) { - /* spin_is_locked() is not a memory barrier */ - smp_mb(); + /* + * The next test must happen after the test for + * sem_perm.lock, otherwise we can race with another + * thread that does + * complex_count++;spin_unlock(sem_perm.lock); + */ + smp_rmb(); - /* Now repeat the test of complex_count: + /* + * Now repeat the test of complex_count: * It can't change anymore until we drop sem->lock. * Thus: if is now 0, then it will stay 0. */ -- 1.9.3