From mboxrd@z Thu Jan 1 00:00:00 1970 From: Joerg Roedel Subject: Re: [PATCH 03/10] x86: add initialization code for DMA-API debugging Date: Fri, 21 Nov 2008 18:10:04 +0100 Message-ID: <20081121171004.GE1386@amd.com> References: <1227284770-19215-1-git-send-email-joerg.roedel@amd.com> <1227284770-19215-4-git-send-email-joerg.roedel@amd.com> <20081121165628.GD733@elte.hu> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Cc: Ingo Molnar , Thomas Gleixner , linux-kernel@vger.kernel.org, netdev@vger.kernel.org, iommu@lists.linux-foundation.org To: Ingo Molnar Return-path: Received: from outbound-wa4.frontbridge.com ([216.32.181.16]:3584 "EHLO WA4EHSOBE005.bigfish.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753187AbYKURKL (ORCPT ); Fri, 21 Nov 2008 12:10:11 -0500 Content-Disposition: inline In-Reply-To: <20081121165628.GD733@elte.hu> Sender: netdev-owner@vger.kernel.org List-ID: On Fri, Nov 21, 2008 at 05:56:28PM +0100, Ingo Molnar wrote: > > + return (entry->dev_addr >> HASH_FN_SHIFT) & HASH_FN_MASK; > > +} > > + > > +static struct dma_debug_entry *dma_entry_alloc(void) > > +{ > > + gfp_t gfp = GFP_KERNEL | __GFP_ZERO; > > + > > + if (in_atomic()) > > + gfp |= GFP_ATOMIC; > > + > > + return kmem_cache_alloc(dma_entry_cache, gfp); > > hm. that slab allocation in the middle of DMA mapping ops makes me a > bit nervous. the DMA mapping ops are generally rather atomic. > > and in_atomic() check there is a bug on !PREEMPT kernels, so it wont > fly. I am not sure I understand this correctly. You say the check for in_atomic() will break on !PREEMPT kernels? > We dont have a gfp flag passed in as all the DMA mapping APIs really > expect all allocations having been done in advance already. Hmm, I can change the code to pre-allocate a certain (configurable?) number of these entries and disble the checking if we run out of it. > Any chance to attach the debug entry to the iotlb entries themselves - > either during build time (for swiotlb) or during iommu init time (for > the hw iommu's) ? Hm, I want to avoid that. This approach has the advantage that is works independent of any dma_ops implementation. So it can be used to find out if a DMA bug originates from the device driver or (in my case) from the IOMMU driver. Joerg -- | AMD Saxony Limited Liability Company & Co. KG Operating | Wilschdorfer Landstr. 101, 01109 Dresden, Germany System | Register Court Dresden: HRA 4896 Research | General Partner authorized to represent: Center | AMD Saxony LLC (Wilmington, Delaware, US) | General Manager of AMD Saxony LLC: Dr. Hans-R. Deppe, Thomas McCoy