Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754167Ab3COKyu (ORCPT ); Fri, 15 Mar 2013 06:54:50 -0400 Received: from mail-pb0-f42.google.com ([209.85.160.42]:61652 "EHLO mail-pb0-f42.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753956Ab3COKyr (ORCPT ); Fri, 15 Mar 2013 06:54:47 -0400 From: Michel Lespinasse To: Alex Shi , Ingo Molnar , David Howells , Peter Zijlstra , Thomas Gleixner , Yuanhan Liu , Rik van Riel , Peter Hurley , Dave Chinner Cc: Andrew Morton , linux-kernel@vger.kernel.org Subject: [PATCH v2 09/13] rwsem: skip initial trylock in rwsem_down_write_failed Date: Fri, 15 Mar 2013 03:54:25 -0700 Message-Id: <1363344869-15732-10-git-send-email-walken@google.com> X-Mailer: git-send-email 1.8.1.3 In-Reply-To: <1363344869-15732-1-git-send-email-walken@google.com> References: <1363344869-15732-1-git-send-email-walken@google.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1756 Lines: 52 We can skip the initial trylock in rwsem_down_write_failed() if there are known active lockers already, thus saving one likely-to-fail cmpxchg. Signed-off-by: Michel Lespinasse --- lib/rwsem.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/lib/rwsem.c b/lib/rwsem.c index edf3d9ca670e..0d50e46d5b0c 100644 --- a/lib/rwsem.c +++ b/lib/rwsem.c @@ -216,14 +216,15 @@ struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem) /* wait until we successfully acquire the lock */ set_task_state(tsk, TASK_UNINTERRUPTIBLE); while (true) { - - /* Try acquiring the write lock. */ - count = RWSEM_ACTIVE_WRITE_BIAS; - if (!list_is_singular(&sem->wait_list)) - count += RWSEM_WAITING_BIAS; - if (cmpxchg(&sem->count, RWSEM_WAITING_BIAS, count) == + if (!(count & RWSEM_ACTIVE_MASK)) { + /* Try acquiring the write lock. */ + count = RWSEM_ACTIVE_WRITE_BIAS; + if (!list_is_singular(&sem->wait_list)) + count += RWSEM_WAITING_BIAS; + if (cmpxchg(&sem->count, RWSEM_WAITING_BIAS, count) == RWSEM_WAITING_BIAS) - break; + break; + } raw_spin_unlock_irq(&sem->wait_lock); @@ -231,7 +232,7 @@ struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem) do { schedule(); set_task_state(tsk, TASK_UNINTERRUPTIBLE); - } while (sem->count & RWSEM_ACTIVE_MASK); + } while ((count = sem->count) & RWSEM_ACTIVE_MASK); raw_spin_lock_irq(&sem->wait_lock); } -- 1.8.1.3 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/