From mboxrd@z Thu Jan 1 00:00:00 1970 From: Johannes Weiner Subject: [PATCH] mutex: set owner only once on acquisition Date: Thu, 15 Jan 2009 09:41:01 +0100 Message-ID: <20090115083951.GA13930@cmpxchg.org> References: <1231774622.4371.96.camel@laptop> <1231859742.442.128.camel@twins> <1231863710.7141.3.camel@twins> <1231864854.7141.8.camel@twins> <1231867314.7141.16.camel@twins> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Linus Torvalds , Ingo Molnar , "Paul E. McKenney" , Gregory Haskins , Matthew Wilcox , Andi Kleen , Chris Mason , Andrew Morton , Linux Kernel Mailing List , linux-fsdevel , linux-btrfs , Thomas Gleixner , Nick Piggin , Peter Morreale , Sven Dietrich , Dmitry Adamushko To: Peter Zijlstra Return-path: Content-Disposition: inline In-Reply-To: <1231867314.7141.16.camel@twins> Sender: linux-kernel-owner@vger.kernel.org List-Id: linux-fsdevel.vger.kernel.org mutex_lock() sets the lock owner, no need to set it upfront in __mutex_lock_common(). Inside __mutex_lock_common() we can cope with the case where the successful acquirer got preempted by us before setting the owner field: there is an explicit check in the spinning code and the sleeping part doesn't rely on it. The debug code does owner checks only on unlock where the field is garuanteed to be set. Signed-off-by: Johannes Weiner --- kernel/mutex.c | 2 -- 1 file changed, 2 deletions(-) Just a small observation. Peter said it wouldn't matter much as the write is to a hot cache line. But otoh, why keep it if it's not necessary. :) --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -195,7 +195,6 @@ __mutex_lock_common(struct mutex *lock, if (atomic_cmpxchg(&lock->count, 1, 0) == 1) { lock_acquired(&lock->dep_map, ip); - mutex_set_owner(lock); preempt_enable(); return 0; } @@ -263,7 +262,6 @@ done: lock_acquired(&lock->dep_map, ip); /* got the lock - rejoice! */ mutex_remove_waiter(lock, &waiter, current_thread_info()); - mutex_set_owner(lock); /* set it to 0 if there are no waiters left: */ if (likely(list_empty(&lock->wait_list)))