From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754596Ab0DER6F (ORCPT ); Mon, 5 Apr 2010 13:58:05 -0400 Received: from e9.ny.us.ibm.com ([32.97.182.139]:33153 "EHLO e9.ny.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751723Ab0DER55 (ORCPT ); Mon, 5 Apr 2010 13:57:57 -0400 Date: Mon, 5 Apr 2010 10:57:54 -0700 From: "Paul E. McKenney" To: David Howells Cc: Eric Dumazet , Trond.Myklebust@netapp.com, linux-nfs@vger.kernel.org, linux-kernel@vger.kernel.org Subject: Re: [PATCH] NFS: Fix RCU warnings in nfs_inode_return_delegation_noreclaim() [ver #2] Message-ID: <20100405175754.GE2525@linux.vnet.ibm.com> Reply-To: paulmck@linux.vnet.ibm.com References: <25276.1269901350@redhat.com> <26760.1269903543@redhat.com> <20100329232636.GT2569@linux.vnet.ibm.com> <2440.1269967151@redhat.com> <21972.1269993064@redhat.com> <10818.1270044273@redhat.com> <15371.1270057054@redhat.com> <19556.1270076008@redhat.com> <14003.1270122314@redhat.com> <4161.1270133211@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <4161.1270133211@redhat.com> User-Agent: Mutt/1.5.20 (2009-06-14) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu, Apr 01, 2010 at 03:46:51PM +0100, David Howells wrote: > Paul E. McKenney wrote: > > > So you have objected to needless memory barriers. How do you feel > > about possibly needless ACCESS_ONCE() calls? > > That would work here since it shouldn't emit any excess instructions. And here is the corresponding patch. Seem reasonable? Thanx, Paul ------------------------------------------------------------------------ rcupdate.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) commit 61ad1405cd442fe54f87ff97febf52610817903e Author: Paul E. McKenney Date: Mon Apr 5 10:52:53 2010 -0700 rcu: add rcu_dereference_protect to avoid smp_read_barrier_depends overhead This patch adds a variant of rcu_dereference() that handles situations where the RCU-protected data structure cannot change, perhaps due to our holding the update-side lock, or where the RCU-protected pointer is only to be tested, not dereferenced. Suggested-by: David Howells Signed-off-by: Paul E. McKenney diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 872a98e..123b834 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -209,9 +209,28 @@ static inline int rcu_read_lock_sched_held(void) rcu_dereference_raw(p); \ }) +/** + * rcu_dereference_protected - fetch RCU pointer when protected by algorithm + * + * Return the value of the specified RCU-protected pointer, but omit + * the smp_read_barrier_depends() and keep the ACCESS_ONCE(). This + * is useful in cases where update-side locks prevent the value of the + * pointer from changing, and is also useful in cases where the value + * of this pointer is accessed, but the pointer is not dereferenced. + * An example of this latter occurs when testing an RCU-protected + * pointer against NULL. + */ +#define rcu_dereference_protected(p, c) \ + ({ \ + if (debug_lockdep_rcu_enabled() && !(c)) \ + lockdep_rcu_dereference(__FILE__, __LINE__); \ + ACCESS_ONCE(p); \ + }) + #else /* #ifdef CONFIG_PROVE_RCU */ #define rcu_dereference_check(p, c) rcu_dereference_raw(p) +#define rcu_dereference_protected(p, c) ACCESS_ONCE(p) #endif /* #else #ifdef CONFIG_PROVE_RCU */