From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757912Ab0DPJWe (ORCPT ); Fri, 16 Apr 2010 05:22:34 -0400 Received: from cantor.suse.de ([195.135.220.2]:46400 "EHLO mx1.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752098Ab0DPJWc (ORCPT ); Fri, 16 Apr 2010 05:22:32 -0400 Date: Fri, 16 Apr 2010 19:22:24 +1000 From: Nick Piggin To: Benjamin Herrenschmidt Cc: paulmck@linux.vnet.ibm.com, Peter Zijlstra , Andrea Arcangeli , Avi Kivity , Thomas Gleixner , Rik van Riel , Ingo Molnar , akpm@linux-foundation.org, Linus Torvalds , linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org, David Miller , Hugh Dickins , Mel Gorman Subject: Re: [PATCH 01/13] powerpc: Add rcu_read_lock() to gup_fast() implementation Message-ID: <20100416092224.GL5683@laptop> References: <20100408191737.296180458@chello.nl> <20100408192722.643778654@chello.nl> <1271120731.13059.6.camel@pasglop> <20100413034311.GB2772@linux.vnet.ibm.com> <1271400694.13059.183.camel@pasglop> <20100416081859.GK5683@laptop> <1271406542.13059.188.camel@pasglop> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1271406542.13059.188.camel@pasglop> 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 Fri, Apr 16, 2010 at 06:29:02PM +1000, Benjamin Herrenschmidt wrote: > On Fri, 2010-04-16 at 18:18 +1000, Nick Piggin wrote: > > On Fri, Apr 16, 2010 at 04:51:34PM +1000, Benjamin Herrenschmidt wrote: > > > On Mon, 2010-04-12 at 20:43 -0700, Paul E. McKenney wrote: > > > > > So we might have to support the interrupt assumption, at least in > > > > some > > > > > form, with those guys... > > > > > > > > One way to make the interrupt assumption official is to use > > > > synchronize_sched() rather than synchronize_rcu(). > > > > > > Ok, so I'm a bit of a RCU newbie as you may know :-) Right now, we use > > > neither, we use call_rcu and we free the pages from the callback. > > > > BTW. you currently have an interesting page table freeing path where > > you usually free by RCU, but (occasionally) free by IPI. This means > > you need to disable both RCU and interrupts to walk page tables. > > Well, the point is we use interrupts to synchronize. The fact that RCU > used to do the job was an added benefit. I may need to switch to rcu > _sched variants tho to keep that. The IPI case is a slow path in case we > are out of memory and cannot allocate our page of RCU batch. It is the slowpath but it forces all lookup paths to do irq disable too. > > If you change it to always use RCU, then you wouldn't need to disable > > interrupts. Whether this actually matters anywhere in your mm code, I > > don't know (it's probably not terribly important for gup_fast). But > > rcu disable is always preferable for latency and performance. > > Well, the main case is the hash miss and that always runs with IRQs off. Probably not a big deal then.