Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759001Ab3EGNta (ORCPT ); Tue, 7 May 2013 09:49:30 -0400 Received: from mail-pd0-f175.google.com ([209.85.192.175]:44509 "EHLO mail-pd0-f175.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S933440Ab3EGNqO (ORCPT ); Tue, 7 May 2013 09:46:14 -0400 From: Michel Lespinasse To: Linus Torvalds , David Howells , Peter Zijlstra , Ingo Molnar , Rik van Riel , Davidlohr Bueso , Peter Hurley Cc: Alex Shi , Yuanhan Liu , Andrew Morton , linux-kernel@vger.kernel.org Subject: [PATCH v3 04/14] rwsem: simplify rwsem_down_read_failed Date: Tue, 7 May 2013 06:45:52 -0700 Message-Id: <1367934362-10433-5-git-send-email-walken@google.com> X-Mailer: git-send-email 1.8.2.1 In-Reply-To: <1367934362-10433-1-git-send-email-walken@google.com> References: <1367934362-10433-1-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: 2984 Lines: 79 When trying to acquire a read lock, the RWSEM_ACTIVE_READ_BIAS adjustment doesn't cause other readers to block, so we never have to worry about waking them back after canceling this adjustment in rwsem_down_read_failed(). We also never want to steal the lock in rwsem_down_read_failed(), so we don't have to grab the wait_lock either. Signed-off-by: Michel Lespinasse Reviewed-by: Rik van Riel Reviewed-by: Peter Hurley Acked-by: Davidlohr Bueso --- lib/rwsem.c | 22 ++-------------------- 1 file changed, 2 insertions(+), 20 deletions(-) diff --git a/lib/rwsem.c b/lib/rwsem.c index fb658af1c12c..66f307e90761 100644 --- a/lib/rwsem.c +++ b/lib/rwsem.c @@ -182,7 +182,6 @@ try_again_write: */ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem) { - enum rwsem_waiter_type type = RWSEM_WAITING_FOR_READ; signed long adjustment = -RWSEM_ACTIVE_READ_BIAS; struct rwsem_waiter waiter; struct task_struct *tsk = current; @@ -190,7 +189,7 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem) /* set up my own style of waitqueue */ waiter.task = tsk; - waiter.type = type; + waiter.type = RWSEM_WAITING_FOR_READ; get_task_struct(tsk); raw_spin_lock_irq(&sem->wait_lock); @@ -201,17 +200,9 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem) /* we're now waiting on the lock, but no longer actively locking */ count = rwsem_atomic_update(adjustment, sem); - /* If there are no active locks, wake the front queued process(es) up. - * - * Alternatively, if we're called from a failed down_write(), there - * were already threads queued before us and there are no active - * writers, the lock must be read owned; so we try to wake any read - * locks that were queued ahead of us. */ + /* If there are no active locks, wake the front queued process(es). */ if (count == RWSEM_WAITING_BIAS) sem = __rwsem_do_wake(sem, RWSEM_WAKE_NO_ACTIVE); - else if (count > RWSEM_WAITING_BIAS && - adjustment == -RWSEM_ACTIVE_WRITE_BIAS) - sem = __rwsem_do_wake(sem, RWSEM_WAKE_READ_OWNED); raw_spin_unlock_irq(&sem->wait_lock); @@ -220,15 +211,6 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem) set_task_state(tsk, TASK_UNINTERRUPTIBLE); if (!waiter.task) break; - - raw_spin_lock_irq(&sem->wait_lock); - /* Try to get the writer sem, may steal from the head writer: */ - if (type == RWSEM_WAITING_FOR_WRITE) - if (try_get_writer_sem(sem, &waiter)) { - raw_spin_unlock_irq(&sem->wait_lock); - return sem; - } - raw_spin_unlock_irq(&sem->wait_lock); schedule(); } -- 1.8.2.1 -- 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/