From: Joerg Roedel <joro@8bytes.org>
To: Bjorn Helgaas <bhelgaas@google.com>
Cc: linux-pci@vger.kernel.org, linux-kernel@vger.kernel.org,
Daniel Drake <drake@endlessm.com>,
Alexander Deucher <Alexander.Deucher@amd.com>,
Samuel Sieb <samuel@sieb.net>,
David Woodhouse <dwmw2@infradead.org>,
Joerg Roedel <jroedel@suse.de>
Subject: [PATCH v2] PCI: Add ATS-disable quirk for AMD Stoney GPUs
Date: Fri, 7 Apr 2017 16:32:18 +0200 [thread overview]
Message-ID: <1491575538-22694-1-git-send-email-joro@8bytes.org> (raw)
From: Joerg Roedel <jroedel@suse.de>
ATS is broken on this hardware and causes IOMMU stalls and
system failure. Disable ATS on these devices to make them
usable again with IOMMU enabled.
Note that the commit in the Fixes-tag is not buggy, it
just uncovers the problem in the hardware by increasing
the ATS-flush rate.
Fixes: b1516a14657a ('iommu/amd: Implement flush queue')
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
drivers/pci/quirks.c | 19 +++++++++++++++++++
1 file changed, 19 insertions(+)
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 6736836..7cbe316 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -4634,3 +4634,22 @@ static void quirk_no_aersid(struct pci_dev *pdev)
DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2031, quirk_no_aersid);
DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2032, quirk_no_aersid);
DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2033, quirk_no_aersid);
+
+#ifdef CONFIG_PCI_ATS
+/*
+ * Some devices have a broken ATS implementation causing IOMMU stalls.
+ * Don't use ATS for those devices.
+ */
+static void quirk_disable_ats(struct pci_dev *pdev)
+{
+ /*
+ * Set pdev->ats_cap = 0 to make pci_enable_ats() bail out
+ * early.
+ */
+ dev_info(&pdev->dev, "QUIRK: Disabling ATS");
+ pdev->ats_cap = 0;
+}
+
+/* AMD Stoney platform GPU */
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x98e4, quirk_disable_ats);
+#endif /* CONFIG_PCI_ATS */
--
1.9.1
next reply other threads:[~2017-04-07 14:32 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-04-07 14:32 Joerg Roedel [this message]
2017-04-07 16:46 ` [PATCH v2] PCI: Add ATS-disable quirk for AMD Stoney GPUs Deucher, Alexander
2017-05-04 10:21 ` David Woodhouse
2017-05-04 14:41 ` Deucher, Alexander
2017-05-23 19:54 ` Deucher, Alexander
2017-05-24 8:44 ` Joerg Roedel
2017-05-24 10:38 ` David Woodhouse
2017-05-24 12:56 ` Deucher, Alexander
2017-05-26 6:48 ` Samuel Sieb
2017-05-26 11:57 ` Deucher, Alexander
2017-05-26 12:54 ` David Woodhouse
2017-05-26 15:59 ` Deucher, Alexander
2017-04-08 7:41 ` Lukas Wunner
2017-04-20 12:11 ` Joerg Roedel
2017-06-15 17:12 ` Bjorn Helgaas
2017-06-15 14:04 ` Joerg Roedel
2017-06-15 17:01 ` Samuel Sieb
2017-06-15 18:13 ` Deucher, Alexander
2017-06-15 19:15 ` Bjorn Helgaas
2017-06-16 16:29 ` Joerg Roedel
2017-07-10 16:53 ` Bjorn Helgaas
2017-07-11 11:49 ` Joerg Roedel
2017-07-11 19:08 ` Deucher, Alexander
2017-07-13 2:56 ` Bjorn Helgaas
2017-08-29 20:02 ` Samuel Sieb
2017-08-29 20:49 ` Bjorn Helgaas
2017-08-30 11:44 ` 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=1491575538-22694-1-git-send-email-joro@8bytes.org \
--to=joro@8bytes.org \
--cc=Alexander.Deucher@amd.com \
--cc=bhelgaas@google.com \
--cc=drake@endlessm.com \
--cc=dwmw2@infradead.org \
--cc=jroedel@suse.de \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pci@vger.kernel.org \
--cc=samuel@sieb.net \
/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).