From: Chris Wright <chrisw@sous-sol.org>
To: David Woodhouse <dwmw2@infradead.org>
Cc: Joerg Roedel <joerg.roedel@amd.com>,
fujita.tomonori@lab.ntt.co.jp, netdev@vger.kernel.org,
iommu@lists.linux-foundation.org, mingo@redhat.com,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH 0/16] DMA-API debugging facility v2
Date: Thu, 5 Feb 2009 18:27:59 -0800 [thread overview]
Message-ID: <20090206022759.GF27684@sequoia.sous-sol.org> (raw)
In-Reply-To: <1233874352.8135.12.camel@macbook.infradead.org>
* David Woodhouse (dwmw2@infradead.org) wrote:
> This adds a function to dump the DMA mappings that the debugging code is
> aware of -- either for a single device, or for _all_ devices.
>
> This can be useful for debugging -- sticking a call to it in the DMA
> page fault handler, for example, to see if the faulting address _should_
> be mapped or not, and hence work out whether it's IOMMU bugs we're
> seeing, or driver bugs.
BTW, here's how I hooked it up:
diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index c933980..df593d1 100644
--- a/drivers/pci/intel-iommu.c
+++ b/drivers/pci/intel-iommu.c
@@ -1072,6 +1072,34 @@ void dmar_msi_read(int irq, struct msi_msg *msg)
spin_unlock_irqrestore(&iommu->register_lock, flag);
}
+static struct pci_dev *domain_find_pdev(u8 bus, u8 devfn)
+{
+ unsigned long flags;
+ struct pci_dev *pdev = NULL;
+ struct device_domain_info *info;
+
+ spin_lock_irqsave(&device_domain_lock, flags);
+ list_for_each_entry(info, &device_domain_list, global) {
+ if (info->bus == bus && info->devfn == devfn) {
+ pdev = info->dev;
+ break;
+ }
+ }
+ spin_unlock_irqrestore(&device_domain_lock, flags);
+ return pdev;
+}
+
+static void dump_mappings(u16 source_id)
+{
+ struct pci_dev *pdev;
+ u8 bus = source_id >> 8;
+ u8 devfn = source_id & 0xff;
+
+ pdev = domain_find_pdev(bus, devfn);
+ if (pdev)
+ debug_dma_dump_mappings(&pdev->dev);
+}
+
static int iommu_page_fault_do_one(struct intel_iommu *iommu, int type,
u8 fault_reason, u16 source_id, unsigned long long addr)
{
@@ -1086,6 +1114,8 @@ static int iommu_page_fault_do_one(struct intel_iommu *iommu, int type,
(type ? "DMA Read" : "DMA Write"),
(source_id >> 8), PCI_SLOT(source_id & 0xFF),
PCI_FUNC(source_id & 0xFF), addr, fault_reason, reason);
+
+ dump_mappings(source_id);
return 0;
}
next prev parent reply other threads:[~2009-02-06 2:28 UTC|newest]
Thread overview: 72+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-01-09 16:19 [PATCH 0/16] DMA-API debugging facility v2 Joerg Roedel
2009-01-09 16:19 ` [PATCH 01/16] dma-debug: add Kconfig entry Joerg Roedel
2009-01-09 20:12 ` Randy Dunlap
2009-01-09 16:19 ` [PATCH 02/16] dma-debug: add header file and core data structures Joerg Roedel
2009-01-11 6:25 ` FUJITA Tomonori
2009-01-09 16:19 ` [PATCH 03/16] dma-debug: add hash functions for dma_debug_entries Joerg Roedel
2009-01-09 17:55 ` Evgeniy Polyakov
2009-01-09 18:14 ` Joerg Roedel
2009-01-09 18:23 ` Evgeniy Polyakov
2009-01-09 18:40 ` Joerg Roedel
2009-01-13 8:51 ` Andrew Morton
2009-01-13 8:59 ` David Woodhouse
2009-01-14 11:43 ` Ingo Molnar
2009-01-14 17:39 ` Andrew Morton
2009-01-14 17:43 ` Ingo Molnar
2009-01-14 17:48 ` Ingo Molnar
2009-01-15 3:44 ` FUJITA Tomonori
2009-01-14 17:48 ` David Woodhouse
2009-01-14 17:51 ` Joerg Roedel
2009-01-09 16:19 ` [PATCH 04/16] dma-debug: add allocator code Joerg Roedel
2009-01-10 23:43 ` Ingo Molnar
2009-01-09 16:19 ` [PATCH 05/16] dma-debug: add initialization code Joerg Roedel
2009-01-09 17:58 ` Evgeniy Polyakov
2009-01-09 18:17 ` Joerg Roedel
2009-01-09 16:19 ` [PATCH 06/16] dma-debug: add kernel command line parameters Joerg Roedel
2009-01-09 16:19 ` [PATCH 07/16] dma-debug: add debugfs interface Joerg Roedel
2009-01-10 23:08 ` Ingo Molnar
2009-01-11 7:52 ` Joerg Roedel
2009-01-14 15:22 ` Joerg Roedel
2009-01-10 23:15 ` Ingo Molnar
2009-01-09 16:19 ` [PATCH 08/16] dma-debug: add core checking functions Joerg Roedel
2009-01-10 23:11 ` Ingo Molnar
2009-01-11 7:57 ` Joerg Roedel
2009-01-11 8:34 ` Joerg Roedel
2009-01-14 11:44 ` Joerg Roedel
2009-01-14 11:48 ` Ingo Molnar
2009-01-10 23:12 ` Ingo Molnar
2009-01-11 7:54 ` Joerg Roedel
2009-01-10 23:13 ` Ingo Molnar
2009-01-09 16:19 ` [PATCH 09/16] dma-debug: add checking for map/unmap_single Joerg Roedel
2009-01-09 16:19 ` [PATCH 10/16] dma-debug: add add checking for map/unmap_sg Joerg Roedel
2009-01-09 18:08 ` Evgeniy Polyakov
2009-01-09 18:11 ` Joerg Roedel
2009-01-09 16:19 ` [PATCH 11/16] dma-debug: add checking for [alloc|free]_coherent Joerg Roedel
2009-01-11 6:25 ` FUJITA Tomonori
2009-01-11 6:30 ` FUJITA Tomonori
2009-01-11 7:59 ` Joerg Roedel
2009-01-09 16:19 ` [PATCH 12/16] dma-debug: add checks for sync_single_* Joerg Roedel
2009-01-09 16:19 ` [PATCH 13/16] dma-debug: add checks for sync_single_range_* Joerg Roedel
2009-01-09 16:19 ` [PATCH 14/16] dma-debug: add checks for sync_single_sg_* Joerg Roedel
2009-01-10 23:46 ` Ingo Molnar
2009-01-11 8:00 ` Joerg Roedel
2009-01-09 16:19 ` [PATCH 15/16] dma-debug: x86 architecture bindings Joerg Roedel
2009-01-10 23:04 ` Ingo Molnar
2009-01-10 23:48 ` Ingo Molnar
2009-01-11 6:25 ` FUJITA Tomonori
2009-01-11 8:08 ` Joerg Roedel
2009-01-09 16:19 ` [PATCH 16/16] dma-debug: Documentation update Joerg Roedel
2009-01-09 21:24 ` [PATCH 0/16] DMA-API debugging facility v2 Michael Chan
2009-01-09 22:33 ` Joerg Roedel
2009-01-09 22:37 ` Joerg Roedel
2009-01-11 6:25 ` FUJITA Tomonori
2009-01-10 23:54 ` Ingo Molnar
2009-01-11 8:11 ` Joerg Roedel
2009-02-05 22:52 ` David Woodhouse
2009-02-06 2:05 ` Chris Wright
2009-02-06 7:56 ` David Woodhouse
2009-02-06 16:08 ` Chris Wright
2009-02-06 18:20 ` Chris Wright
2009-02-12 14:48 ` Joerg Roedel
2009-02-06 2:27 ` Chris Wright [this message]
2009-02-12 15:20 ` Joerg Roedel
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20090206022759.GF27684@sequoia.sous-sol.org \
--to=chrisw@sous-sol.org \
--cc=dwmw2@infradead.org \
--cc=fujita.tomonori@lab.ntt.co.jp \
--cc=iommu@lists.linux-foundation.org \
--cc=joerg.roedel@amd.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=netdev@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).