From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754563AbZANRtL (ORCPT ); Wed, 14 Jan 2009 12:49:11 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753820AbZANRsb (ORCPT ); Wed, 14 Jan 2009 12:48:31 -0500 Received: from casper.infradead.org ([85.118.1.10]:40298 "EHLO casper.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752921AbZANRs3 (ORCPT ); Wed, 14 Jan 2009 12:48:29 -0500 Subject: Re: [PATCH 03/16] dma-debug: add hash functions for dma_debug_entries From: David Woodhouse To: Andrew Morton Cc: Ingo Molnar , Joerg Roedel , linux-kernel@vger.kernel.org, mingo@redhat.com, fujita.tomonori@lab.ntt.co.jp, netdev@vger.kernel.org, iommu@lists.linux-foundation.org In-Reply-To: <20090114093918.e7b0ae46.akpm@linux-foundation.org> References: <1231517970-20288-1-git-send-email-joerg.roedel@amd.com> <1231517970-20288-4-git-send-email-joerg.roedel@amd.com> <20090113005118.82f5037b.akpm@linux-foundation.org> <20090114114347.GG8625@elte.hu> <20090114093918.e7b0ae46.akpm@linux-foundation.org> Content-Type: text/plain Date: Wed, 14 Jan 2009 17:48:15 +0000 Message-Id: <1231955295.25018.5631.camel@macbook.infradead.org> Mime-Version: 1.0 X-Mailer: Evolution 2.24.2 (2.24.2-2.fc10) Content-Transfer-Encoding: 7bit X-SRS-Rewrite: SMTP reverse-path rewritten from by casper.infradead.org See http://www.infradead.org/rpr.html Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, 2009-01-14 at 09:39 -0800, Andrew Morton wrote: > > this code checks the DMA usage of ~1 million lines of kernel code - all > > the DMA using drivers. I think Joerg's feature is hugely relevant as DMA > > scribbles are one of the hardest to debug kernel bugs: they can end up in > > permanent data corruption or other hard to find bugs. In fact i think his > > patchset is rather simple and even having 10 times as much debug code > > would pay for its existence in the long run. > > > > Have we previously found bugs by other means which this facility would > have detected? I don't recall any... Yes. We've found network driver bugs which only showed up when an IOMMU has been active -- and were painful to diagnose because they involved DMA going wrong. It happens when drivers make mistakes with the DMA mapping APIs. With this debug facility, we can find such problems on _any_ hardware, and get a sane report about what's wrong. -- David Woodhouse Open Source Technology Centre David.Woodhouse@intel.com Intel Corporation