Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759883AbZAIWec (ORCPT ); Fri, 9 Jan 2009 17:34:32 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1759783AbZAIWdb (ORCPT ); Fri, 9 Jan 2009 17:33:31 -0500 Received: from 8bytes.org ([88.198.83.132]:48592 "EHLO 8bytes.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754395AbZAIWd3 (ORCPT ); Fri, 9 Jan 2009 17:33:29 -0500 Date: Fri, 9 Jan 2009 23:33:27 +0100 From: Joerg Roedel To: Michael Chan Cc: Joerg Roedel , "netdev@vger.kernel.org" , "linux-kernel@vger.kernel.org" , "iommu@lists.linux-foundation.org" , "mingo@redhat.com" Subject: Re: [PATCH 0/16] DMA-API debugging facility v2 Message-ID: <20090109223327.GD9466@8bytes.org> References: <1231517970-20288-1-git-send-email-joerg.roedel@amd.com> <1231536264.10384.11.camel@HP1> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1231536264.10384.11.camel@HP1> User-Agent: Mutt/1.5.13 (2006-08-11) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3112 Lines: 65 On Fri, Jan 09, 2009 at 01:24:24PM -0800, Michael Chan wrote: > > On Fri, 2009-01-09 at 08:19 -0800, Joerg Roedel wrote: > > > > With the code these patches introduce driver developers can find several > > bugs of misusing the DMA-API in their drivers. But be aware, it can not > > find all possible bugs. If it finds a problem it prints out messages > > like > > > > ------------[ cut here ]------------ > > WARNING: at /data2/repos/linux.trees.git/lib/dma-debug.c:231 check_unmap+0xab/0x3d9() > > Hardware name: Toonie > > bnx2 0000:01:00.0: DMA-API: device driver tries to free DMA memory it has not allocated [device address=0x00000000011] > > Modules linked in: > > Pid: 0, comm: swapper Not tainted 2.6.28 #174 > > Call Trace: > > [] warn_slowpath+0xd3/0xf2 > > [] ? find_usage_backwards+0xe2/0x116 > > [] ? find_usage_backwards+0xe2/0x116 > > [] ? usb_hcd_link_urb_to_ep+0x94/0xa0 > > [] ? mark_lock+0x1c/0x364 > > [] ? __lock_acquire+0xaec/0xb55 > > [] ? mark_lock+0x1c/0x364 > > [] ? get_hash_bucket+0x28/0x33 > > [] ? _spin_lock_irqsave+0x69/0x75 > > [] ? get_hash_bucket+0x28/0x33 > > [] check_unmap+0xab/0x3d9 > > [] ? trace_hardirqs_on_caller+0x108/0x14a > > [] ? trace_hardirqs_on+0xd/0xf > > [] debug_unmap_single+0x3e/0x40 > > [] dma_unmap_single+0x3d/0x60 > > [] pci_unmap_page+0x1c/0x1e > > [] bnx2_poll_work+0x626/0x8cb > > [] ? __lock_acquire+0xaec/0xb55 > > [] ? run_posix_cpu_timers+0x49c/0x603 > > [] ? run_posix_cpu_timers+0x39c/0x603 > > [] ? mark_lock+0x1c/0x364 > > [] ? __lock_acquire+0xaec/0xb55 > > [] bnx2_poll_msix+0x33/0x81 > > [] net_rx_action+0x8a/0x139 > > [] __do_softirq+0x8b/0x147 > > [] call_softirq+0x1c/0x34 > > [] do_softirq+0x39/0x90 > > [] irq_exit+0x4e/0x98 > > [] do_IRQ+0x11f/0x135 > > [] ret_from_intr+0x0/0xf > > <4>---[ end trace 4339d58302097423 ]--- > > > This was triggered during pci_unmap_page() -> dma_unmap_single() where > check_unmap() did not find the entry. > > The original mapping was done in bnx2 using pci_map_page(). I did not > see how the debug entry was added to the hash during the call to > pci_map_page() -> dma_map_page(). Did I miss something? dma_map_page() results in dma_map_single() -> debug_map_single() call on x86. This way the entry would be added. Maybe the error from a double free? Joerg -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/