From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S964800AbXCBFEA (ORCPT ); Fri, 2 Mar 2007 00:04:00 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S964863AbXCBFD7 (ORCPT ); Fri, 2 Mar 2007 00:03:59 -0500 Received: from pentafluge.infradead.org ([213.146.154.40]:48219 "EHLO pentafluge.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S964800AbXCBFD7 (ORCPT ); Fri, 2 Mar 2007 00:03:59 -0500 Date: Fri, 2 Mar 2007 05:03:51 +0000 From: Christoph Hellwig To: Andrew Morton Cc: Christoph Hellwig , support@coraid.com, "Ed L. Cashin" , linux-kernel@vger.kernel.org, Greg KH Subject: Re: PATCH 2.6.21-rc1 aoe: handle zero _count pages in bios Message-ID: <20070302050351.GA24705@infradead.org> Mail-Followup-To: Christoph Hellwig , Andrew Morton , support@coraid.com, "Ed L. Cashin" , linux-kernel@vger.kernel.org, Greg KH References: <20070301231510.GC8524@coraid.com> <20070301174204.a550dd3a.akpm@linux-foundation.org> <20070302022919.GA26285@infradead.org> <20070301192245.bf034385.akpm@linux-foundation.org> <20070302043039.GA18651@infradead.org> <20070301204806.61225e2b.akpm@linux-foundation.org> <20070302044910.GA22209@infradead.org> <20070301210044.d95bcd70.akpm@linux-foundation.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20070301210044.d95bcd70.akpm@linux-foundation.org> User-Agent: Mutt/1.4.2.2i X-SRS-Rewrite: SMTP reverse-path rewritten from by pentafluge.infradead.org See http://www.infradead.org/rpr.html Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Thu, Mar 01, 2007 at 09:00:44PM -0800, Andrew Morton wrote: > I that case we're talking about different things. > > I thought the proposal was to continue to use slab pages, but to take a ref > on them as they're added to the bio, drop that ref in bi_end_io()? That would give you silent memory corruption in case the networking code hold a reference after the memory gets returned to slab and reused. We need to either stop allowing to pass slab memory to the block layer, or document that drivers need to handle it specially and give them a way to find out about them. (Or do the horrible slab refcounting hack I wrote up above)