From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755492AbbAFPXw (ORCPT ); Tue, 6 Jan 2015 10:23:52 -0500 Received: from mail-qg0-f44.google.com ([209.85.192.44]:33322 "EHLO mail-qg0-f44.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754126AbbAFPXu (ORCPT ); Tue, 6 Jan 2015 10:23:50 -0500 Date: Tue, 6 Jan 2015 10:23:47 -0500 From: Tejun Heo To: Kent Overstreet , Christoph Lameter , linux-kernel@vger.kernel.org Subject: [PATCH 1/2 percpu/for-3.20] percpu_ref: remove unnecessary ACCESS_ONCE() in percpu_ref_tryget_live() Message-ID: <20150106152347.GD3077@htj.dyndns.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.5.23 (2014-03-12) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org __ref_is_percpu() needs the implied ACCESS_ONCE() in lockless_dereference() on @ref->percpu_count_ptr because the value is tested for !__PERCPU_REF_ATOMIC, which may be set asynchronously, and then used as a pointer. If the compiler generates a separate fetch when using it as a pointer, __PERCPU_REF_ATOMIC may be set in between contaminating the pointer value. percpu_ref_tryget_live() also uses ACCESS_ONCE() to test __PERCPU_REF_DEAD; however, there's no reason for this. I just copied ACCESS_ONCE() usage blindly from __ref_is_percpu(). All it does is confusing people trying to understand what's going on. This patch removes the unnecessary ACCESS_ONCE() usage from percpu_ref_tryget_live() and adds a comment explaining why __ref_is_percpu() needs it. Signed-off-by: Tejun Heo Cc: Kent Overstreet --- include/linux/percpu-refcount.h | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -128,8 +128,22 @@ static inline void percpu_ref_kill(struc static inline bool __ref_is_percpu(struct percpu_ref *ref, unsigned long __percpu **percpu_countp) { - /* paired with smp_store_release() in percpu_ref_reinit() */ - unsigned long percpu_ptr = lockless_dereference(ref->percpu_count_ptr); + unsigned long percpu_ptr; + + /* + * The value of @ref->percpu_count_ptr is tested for + * !__PERCPU_REF_ATOMIC, which may be set asynchronously, and then + * used as a pointer. If the compiler generates a separate fetch + * when using it as a pointer, __PERCPU_REF_ATOMIC may be set in + * between contaminating the pointer value, meaning that + * ACCESS_ONCE() is required when fetching it. + * + * Also, we need a data dependency barrier to be paired with + * smp_store_release() in __percpu_ref_switch_to_percpu(). + * + * Use lockless deref which contains both. + */ + percpu_ptr = lockless_dereference(ref->percpu_count_ptr); /* * Theoretically, the following could test just ATOMIC; however, @@ -233,7 +247,7 @@ static inline bool percpu_ref_tryget_liv if (__ref_is_percpu(ref, &percpu_count)) { this_cpu_inc(*percpu_count); ret = true; - } else if (!(ACCESS_ONCE(ref->percpu_count_ptr) & __PERCPU_REF_DEAD)) { + } else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) { ret = atomic_long_inc_not_zero(&ref->count); }