Patchwork [089/145] iommu/vt-d: add quirk for broken interrupt remapping on 55XX chipsets

login
register
mail settings
Submitter Kamal Mostafa
Date July 17, 2013, 10:47 p.m.
Message ID <1374101277-7915-90-git-send-email-kamal@canonical.com>
Download mbox | patch
Permalink /patch/259935/
State Not Applicable
Headers show

Comments

Kamal Mostafa - July 17, 2013, 10:47 p.m.
3.8.13.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Neil Horman <nhorman@tuxdriver.com>

commit 03bbcb2e7e292838bb0244f5a7816d194c911d62 upstream.

A few years back intel published a spec update:
http://www.intel.com/content/dam/doc/specification-update/5520-and-5500-chipset-ioh-specification-update.pdf

For the 5520 and 5500 chipsets which contained an errata (specificially errata
53), which noted that these chipsets can't properly do interrupt remapping, and
as a result the recommend that interrupt remapping be disabled in bios.  While
many vendors have a bios update to do exactly that, not all do, and of course
not all users update their bios to a level that corrects the problem.  As a
result, occasionally interrupts can arrive at a cpu even after affinity for that
interrupt has be moved, leading to lost or spurrious interrupts (usually
characterized by the message:
kernel: do_IRQ: 7.71 No irq handler for vector (irq -1)

There have been several incidents recently of people seeing this error, and
investigation has shown that they have system for which their BIOS level is such
that this feature was not properly turned off.  As such, it would be good to
give them a reminder that their systems are vulnurable to this problem.  For
details of those that reported the problem, please see:
https://bugzilla.redhat.com/show_bug.cgi?id=887006

[ Joerg: Removed CONFIG_IRQ_REMAP ifdef from early-quirks.c ]

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
CC: Prarit Bhargava <prarit@redhat.com>
CC: Don Zickus <dzickus@redhat.com>
CC: Don Dutile <ddutile@redhat.com>
CC: Bjorn Helgaas <bhelgaas@google.com>
CC: Asit Mallick <asit.k.mallick@intel.com>
CC: David Woodhouse <dwmw2@infradead.org>
CC: linux-pci@vger.kernel.org
CC: Joerg Roedel <joro@8bytes.org>
CC: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
CC: Arkadiusz Miśkiewicz <arekm@maven.pl>
Signed-off-by: Joerg Roedel <joro@8bytes.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 arch/x86/include/asm/irq_remapping.h |  2 ++
 arch/x86/kernel/early-quirks.c       | 20 ++++++++++++++++++++
 drivers/iommu/intel_irq_remapping.c  | 10 ++++++++++
 drivers/iommu/irq_remapping.c        |  6 ++++++
 drivers/iommu/irq_remapping.h        |  2 ++
 5 files changed, 40 insertions(+)
Thomas Backlund - July 18, 2013, 8:02 a.m.
18.07.2013 01:47, Kamal Mostafa skrev:
> 3.8.13.5 -stable review patch.  If anyone has any objections, please let me know.
>
> ------------------
>
> From: Neil Horman <nhorman@tuxdriver.com>
>
> commit 03bbcb2e7e292838bb0244f5a7816d194c911d62 upstream.
>
> A few years back intel published a spec update:
> http://www.intel.com/content/dam/doc/specification-update/5520-and-5500-chipset-ioh-specification-update.pdf
>
> For the 5520 and 5500 chipsets which contained an errata (specificially errata
> 53), which noted that these chipsets can't properly do interrupt remapping, and
> as a result the recommend that interrupt remapping be disabled in bios.  While
> many vendors have a bios update to do exactly that, not all do, and of course
> not all users update their bios to a level that corrects the problem.  As a
> result, occasionally interrupts can arrive at a cpu even after affinity for that
> interrupt has be moved, leading to lost or spurrious interrupts (usually
> characterized by the message:
> kernel: do_IRQ: 7.71 No irq handler for vector (irq -1)
>
> There have been several incidents recently of people seeing this error, and
> investigation has shown that they have system for which their BIOS level is such
> that this feature was not properly turned off.  As such, it would be good to
> give them a reminder that their systems are vulnurable to this problem.  For
> details of those that reported the problem, please see:
> https://bugzilla.redhat.com/show_bug.cgi?id=887006
>
> [ Joerg: Removed CONFIG_IRQ_REMAP ifdef from early-quirks.c ]
>
> Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
> CC: Prarit Bhargava <prarit@redhat.com>
> CC: Don Zickus <dzickus@redhat.com>
> CC: Don Dutile <ddutile@redhat.com>
> CC: Bjorn Helgaas <bhelgaas@google.com>
> CC: Asit Mallick <asit.k.mallick@intel.com>
> CC: David Woodhouse <dwmw2@infradead.org>
> CC: linux-pci@vger.kernel.org
> CC: Joerg Roedel <joro@8bytes.org>
> CC: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
> CC: Arkadiusz Miśkiewicz <arekm@maven.pl>
> Signed-off-by: Joerg Roedel <joro@8bytes.org>
> Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
> ---
>   arch/x86/include/asm/irq_remapping.h |  2 ++
>   arch/x86/kernel/early-quirks.c       | 20 ++++++++++++++++++++
>   drivers/iommu/intel_irq_remapping.c  | 10 ++++++++++
>   drivers/iommu/irq_remapping.c        |  6 ++++++
>   drivers/iommu/irq_remapping.h        |  2 ++
>   5 files changed, 40 insertions(+)
>

This patch introduces this warning on 3.8 series kernels:

In file included from arch/x86/kernel/early-quirks.c:21:0:
/kernel/linux-3.8.13.5/arch/x86/include/asm/irq_remapping.h:46:10: 
varning: ”struct irq_data” deklarerad inuti parameterlista [aktiverat 
som standard]
/kernel/linux-3.8.13.5/arch/x86/include/asm/irq_remapping.h:46:10: 
varning: dess scope-område är endast denna definition eller deklaration, 
vilket troligen inte är vad du vill. [aktiverat som standard]
/kernel/linux-3.8.13.5/arch/x86/include/asm/irq_remapping.h:50:17: 
varning: ”struct msi_msg” deklarerad inuti parameterlista [aktiverat som 
standard]


You need to add this upstream fix too:

commit 35d3d814cbd46a85bed97cd74ba97fbbb51e0ccd
Author: Joerg Roedel <joro@8bytes.org>
Date:   Fri Apr 19 20:34:55 2013 +0200

     iommu: Fix compile warnings with forward declarations


--

Thomas

--
To unsubscribe from this list: send the line "unsubscribe linux-pci" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Neil Horman - July 18, 2013, 10:37 a.m.
On Thu, Jul 18, 2013 at 11:02:00AM +0300, Thomas Backlund wrote:
> 18.07.2013 01:47, Kamal Mostafa skrev:
> >3.8.13.5 -stable review patch.  If anyone has any objections, please let me know.
> >
> >------------------
> >
> >From: Neil Horman <nhorman@tuxdriver.com>
> >
> >commit 03bbcb2e7e292838bb0244f5a7816d194c911d62 upstream.
> >
> >A few years back intel published a spec update:
> >http://www.intel.com/content/dam/doc/specification-update/5520-and-5500-chipset-ioh-specification-update.pdf
> >
> >For the 5520 and 5500 chipsets which contained an errata (specificially errata
> >53), which noted that these chipsets can't properly do interrupt remapping, and
> >as a result the recommend that interrupt remapping be disabled in bios.  While
> >many vendors have a bios update to do exactly that, not all do, and of course
> >not all users update their bios to a level that corrects the problem.  As a
> >result, occasionally interrupts can arrive at a cpu even after affinity for that
> >interrupt has be moved, leading to lost or spurrious interrupts (usually
> >characterized by the message:
> >kernel: do_IRQ: 7.71 No irq handler for vector (irq -1)
> >
> >There have been several incidents recently of people seeing this error, and
> >investigation has shown that they have system for which their BIOS level is such
> >that this feature was not properly turned off.  As such, it would be good to
> >give them a reminder that their systems are vulnurable to this problem.  For
> >details of those that reported the problem, please see:
> >https://bugzilla.redhat.com/show_bug.cgi?id=887006
> >
> >[ Joerg: Removed CONFIG_IRQ_REMAP ifdef from early-quirks.c ]
> >
> >Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
> >CC: Prarit Bhargava <prarit@redhat.com>
> >CC: Don Zickus <dzickus@redhat.com>
> >CC: Don Dutile <ddutile@redhat.com>
> >CC: Bjorn Helgaas <bhelgaas@google.com>
> >CC: Asit Mallick <asit.k.mallick@intel.com>
> >CC: David Woodhouse <dwmw2@infradead.org>
> >CC: linux-pci@vger.kernel.org
> >CC: Joerg Roedel <joro@8bytes.org>
> >CC: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
> >CC: Arkadiusz Miśkiewicz <arekm@maven.pl>
> >Signed-off-by: Joerg Roedel <joro@8bytes.org>
> >Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
> >---
> >  arch/x86/include/asm/irq_remapping.h |  2 ++
> >  arch/x86/kernel/early-quirks.c       | 20 ++++++++++++++++++++
> >  drivers/iommu/intel_irq_remapping.c  | 10 ++++++++++
> >  drivers/iommu/irq_remapping.c        |  6 ++++++
> >  drivers/iommu/irq_remapping.h        |  2 ++
> >  5 files changed, 40 insertions(+)
> >
> 
> This patch introduces this warning on 3.8 series kernels:
> 
> In file included from arch/x86/kernel/early-quirks.c:21:0:
> /kernel/linux-3.8.13.5/arch/x86/include/asm/irq_remapping.h:46:10:
> varning: ”struct irq_data” deklarerad inuti parameterlista
> [aktiverat som standard]
> /kernel/linux-3.8.13.5/arch/x86/include/asm/irq_remapping.h:46:10:
> varning: dess scope-område är endast denna definition eller
> deklaration, vilket troligen inte är vad du vill. [aktiverat som
> standard]
> /kernel/linux-3.8.13.5/arch/x86/include/asm/irq_remapping.h:50:17:
> varning: ”struct msi_msg” deklarerad inuti parameterlista [aktiverat
> som standard]
> 
> 
> You need to add this upstream fix too:
> 
> commit 35d3d814cbd46a85bed97cd74ba97fbbb51e0ccd
> Author: Joerg Roedel <joro@8bytes.org>
> Date:   Fri Apr 19 20:34:55 2013 +0200
> 
>     iommu: Fix compile warnings with forward declarations
> 
I submited a 3.9 backport that included that fix to -stable over a week ago, you
should just be able to use that if you want.
Neil

> 
> --
> 
> Thomas
> 
> 
--
To unsubscribe from this list: send the line "unsubscribe linux-pci" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Thomas Backlund - July 18, 2013, 1:45 p.m.
18.07.2013 13:37, Neil Horman skrev:
> On Thu, Jul 18, 2013 at 11:02:00AM +0300, Thomas Backlund wrote:
>> 18.07.2013 01:47, Kamal Mostafa skrev:
>>> 3.8.13.5 -stable review patch.  If anyone has any objections, please let me know.
>>>
>>> ------------------
>>>
>>> From: Neil Horman <nhorman@tuxdriver.com>
>>>
>>> commit 03bbcb2e7e292838bb0244f5a7816d194c911d62 upstream.
>>>
>>> A few years back intel published a spec update:
>>> http://www.intel.com/content/dam/doc/specification-update/5520-and-5500-chipset-ioh-specification-update.pdf
>>>
>>> For the 5520 and 5500 chipsets which contained an errata (specificially errata
>>> 53), which noted that these chipsets can't properly do interrupt remapping, and
>>> as a result the recommend that interrupt remapping be disabled in bios.  While
>>> many vendors have a bios update to do exactly that, not all do, and of course
>>> not all users update their bios to a level that corrects the problem.  As a
>>> result, occasionally interrupts can arrive at a cpu even after affinity for that
>>> interrupt has be moved, leading to lost or spurrious interrupts (usually
>>> characterized by the message:
>>> kernel: do_IRQ: 7.71 No irq handler for vector (irq -1)
>>>
>>> There have been several incidents recently of people seeing this error, and
>>> investigation has shown that they have system for which their BIOS level is such
>>> that this feature was not properly turned off.  As such, it would be good to
>>> give them a reminder that their systems are vulnurable to this problem.  For
>>> details of those that reported the problem, please see:
>>> https://bugzilla.redhat.com/show_bug.cgi?id=887006
>>>
>>> [ Joerg: Removed CONFIG_IRQ_REMAP ifdef from early-quirks.c ]
>>>
>>> Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
>>> CC: Prarit Bhargava <prarit@redhat.com>
>>> CC: Don Zickus <dzickus@redhat.com>
>>> CC: Don Dutile <ddutile@redhat.com>
>>> CC: Bjorn Helgaas <bhelgaas@google.com>
>>> CC: Asit Mallick <asit.k.mallick@intel.com>
>>> CC: David Woodhouse <dwmw2@infradead.org>
>>> CC: linux-pci@vger.kernel.org
>>> CC: Joerg Roedel <joro@8bytes.org>
>>> CC: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
>>> CC: Arkadiusz Miśkiewicz <arekm@maven.pl>
>>> Signed-off-by: Joerg Roedel <joro@8bytes.org>
>>> Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
>>> ---
>>>   arch/x86/include/asm/irq_remapping.h |  2 ++
>>>   arch/x86/kernel/early-quirks.c       | 20 ++++++++++++++++++++
>>>   drivers/iommu/intel_irq_remapping.c  | 10 ++++++++++
>>>   drivers/iommu/irq_remapping.c        |  6 ++++++
>>>   drivers/iommu/irq_remapping.h        |  2 ++
>>>   5 files changed, 40 insertions(+)
>>>
>>
>> This patch introduces this warning on 3.8 series kernels:
>>
>> In file included from arch/x86/kernel/early-quirks.c:21:0:
>> /kernel/linux-3.8.13.5/arch/x86/include/asm/irq_remapping.h:46:10:
>> varning: ”struct irq_data” deklarerad inuti parameterlista
>> [aktiverat som standard]
>> /kernel/linux-3.8.13.5/arch/x86/include/asm/irq_remapping.h:46:10:
>> varning: dess scope-område är endast denna definition eller
>> deklaration, vilket troligen inte är vad du vill. [aktiverat som
>> standard]
>> /kernel/linux-3.8.13.5/arch/x86/include/asm/irq_remapping.h:50:17:
>> varning: ”struct msi_msg” deklarerad inuti parameterlista [aktiverat
>> som standard]
>>
>>
>> You need to add this upstream fix too:
>>
>> commit 35d3d814cbd46a85bed97cd74ba97fbbb51e0ccd
>> Author: Joerg Roedel <joro@8bytes.org>
>> Date:   Fri Apr 19 20:34:55 2013 +0200
>>
>>      iommu: Fix compile warnings with forward declarations
>>
> I submited a 3.9 backport that included that fix to -stable over a week ago, you
> should just be able to use that if you want.
> Neil

Almost, but not enough...

The patch you refer to was:
[3.9 stable PATCH] iommu/vt-d: add quirk for broken interrupt remapping 
on 55XX chipsets

and got merged in 3.9.9.

And that added a missing: "#include <linux/irq.h>" in
arch/x86/include/asm/irq_remapping.h

But using that patch it still spits out:

kernel/linux-3.8.13.5/arch/x86/include/asm/irq_remapping.h:50:17:
 >> varning: ”struct msi_msg” deklarerad inuti parameterlista [aktiverat
 >> som standard]


which is why the additional patch is still needed...

--

Thomas


--
To unsubscribe from this list: send the line "unsubscribe linux-pci" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Kamal Mostafa - July 18, 2013, 6:30 p.m.
On Thu, 2013-07-18 at 16:45 +0300, Thomas Backlund wrote:
> 18.07.2013 13:37, Neil Horman skrev:
> > On Thu, Jul 18, 2013 at 11:02:00AM +0300, Thomas Backlund wrote:
> >> 18.07.2013 01:47, Kamal Mostafa skrev:
> >>> 3.8.13.5 -stable review patch.  If anyone has any objections, please let me know.
> >>>
> >>> ------------------
> >>>
> >>> From: Neil Horman <nhorman@tuxdriver.com>
> >>>
> >>> commit 03bbcb2e7e292838bb0244f5a7816d194c911d62 upstream.
> >>>
> >>> A few years back intel published a spec update:
> >>> http://www.intel.com/content/dam/doc/specification-update/5520-and-5500-chipset-ioh-specification-update.pdf
> >>>
> >>> For the 5520 and 5500 chipsets which contained an errata (specificially errata
> >>> 53), which noted that these chipsets can't properly do interrupt remapping, and
> >>> as a result the recommend that interrupt remapping be disabled in bios.  While
> >>> many vendors have a bios update to do exactly that, not all do, and of course
> >>> not all users update their bios to a level that corrects the problem.  As a
> >>> result, occasionally interrupts can arrive at a cpu even after affinity for that
> >>> interrupt has be moved, leading to lost or spurrious interrupts (usually
> >>> characterized by the message:
> >>> kernel: do_IRQ: 7.71 No irq handler for vector (irq -1)
> >>>
> >>> There have been several incidents recently of people seeing this error, and
> >>> investigation has shown that they have system for which their BIOS level is such
> >>> that this feature was not properly turned off.  As such, it would be good to
> >>> give them a reminder that their systems are vulnurable to this problem.  For
> >>> details of those that reported the problem, please see:
> >>> https://bugzilla.redhat.com/show_bug.cgi?id=887006
> >>>
> >>> [ Joerg: Removed CONFIG_IRQ_REMAP ifdef from early-quirks.c ]
> >>>
> >>> Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
> >>> CC: Prarit Bhargava <prarit@redhat.com>
> >>> CC: Don Zickus <dzickus@redhat.com>
> >>> CC: Don Dutile <ddutile@redhat.com>
> >>> CC: Bjorn Helgaas <bhelgaas@google.com>
> >>> CC: Asit Mallick <asit.k.mallick@intel.com>
> >>> CC: David Woodhouse <dwmw2@infradead.org>
> >>> CC: linux-pci@vger.kernel.org
> >>> CC: Joerg Roedel <joro@8bytes.org>
> >>> CC: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
> >>> CC: Arkadiusz Miśkiewicz <arekm@maven.pl>
> >>> Signed-off-by: Joerg Roedel <joro@8bytes.org>
> >>> Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
> >>> ---
> >>>   arch/x86/include/asm/irq_remapping.h |  2 ++
> >>>   arch/x86/kernel/early-quirks.c       | 20 ++++++++++++++++++++
> >>>   drivers/iommu/intel_irq_remapping.c  | 10 ++++++++++
> >>>   drivers/iommu/irq_remapping.c        |  6 ++++++
> >>>   drivers/iommu/irq_remapping.h        |  2 ++
> >>>   5 files changed, 40 insertions(+)
> >>>
> >>
> >> This patch introduces this warning on 3.8 series kernels:
> >>
> >> In file included from arch/x86/kernel/early-quirks.c:21:0:
> >> /kernel/linux-3.8.13.5/arch/x86/include/asm/irq_remapping.h:46:10:
> >> varning: ”struct irq_data” deklarerad inuti parameterlista
> >> [aktiverat som standard]
> >> /kernel/linux-3.8.13.5/arch/x86/include/asm/irq_remapping.h:46:10:
> >> varning: dess scope-område är endast denna definition eller
> >> deklaration, vilket troligen inte är vad du vill. [aktiverat som
> >> standard]
> >> /kernel/linux-3.8.13.5/arch/x86/include/asm/irq_remapping.h:50:17:
> >> varning: ”struct msi_msg” deklarerad inuti parameterlista [aktiverat
> >> som standard]
> >>
> >>
> >> You need to add this upstream fix too:
> >>
> >> commit 35d3d814cbd46a85bed97cd74ba97fbbb51e0ccd
> >> Author: Joerg Roedel <joro@8bytes.org>
> >> Date:   Fri Apr 19 20:34:55 2013 +0200
> >>
> >>      iommu: Fix compile warnings with forward declarations
> >>
> > I submited a 3.9 backport that included that fix to -stable over a week ago, you
> > should just be able to use that if you want.
> > Neil
> 
> Almost, but not enough...
> 
> The patch you refer to was:
> [3.9 stable PATCH] iommu/vt-d: add quirk for broken interrupt remapping 
> on 55XX chipsets
> 
> and got merged in 3.9.9.
> 
> And that added a missing: "#include <linux/irq.h>" in
> arch/x86/include/asm/irq_remapping.h
> 
> But using that patch it still spits out:
> 
> kernel/linux-3.8.13.5/arch/x86/include/asm/irq_remapping.h:50:17:
>  >> varning: ”struct msi_msg” deklarerad inuti parameterlista [aktiverat
>  >> som standard]
> 
> 
> which is why the additional patch is still needed...
> 
> --
> 
> Thomas


Ok, I have replaced the queued patch in linux-3.8.y-review[0] with
Neil's backport[1], and added Joerg's patch[2].  These are (still)
queued up for 3.8.13.5 -stable.

Thanks very much for the heads-up folks.

 -Kamal

[0] http://kernel.ubuntu.com/git?p=ubuntu/linux.git;h=linux-3.8.y-review;a=shortlog
[1] http://kernel.ubuntu.com/git?p=ubuntu/linux.git;a=commitdiff;h=af4e6e26bde03f5203c9e366673623f4a3797639
[2] http://kernel.ubuntu.com/git?p=ubuntu/linux.git;a=commitdiff;h=3668f1f9e97d4ab0007f357e06fc67ce152c3998

Patch

diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index 5fb9bbb..38477e6 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -30,6 +30,7 @@  extern int irq_remapping_enabled;
 
 extern void setup_irq_remapping_ops(void);
 extern int irq_remapping_supported(void);
+extern void set_irq_remapping_broken(void);
 extern int irq_remapping_prepare(void);
 extern int irq_remapping_enable(void);
 extern void irq_remapping_disable(void);
@@ -58,6 +59,7 @@  extern int setup_hpet_msi_remapped(unsigned int irq, unsigned int id);
 
 static inline void setup_irq_remapping_ops(void) { }
 static inline int irq_remapping_supported(void) { return 0; }
+static inline void set_irq_remapping_broken(void) { }
 static inline int irq_remapping_prepare(void) { return -ENODEV; }
 static inline int irq_remapping_enable(void) { return -ENODEV; }
 static inline void irq_remapping_disable(void) { }
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 3755ef4..94ab6b9 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -18,6 +18,7 @@ 
 #include <asm/apic.h>
 #include <asm/iommu.h>
 #include <asm/gart.h>
+#include <asm/irq_remapping.h>
 
 static void __init fix_hypertransport_config(int num, int slot, int func)
 {
@@ -192,6 +193,21 @@  static void __init ati_bugs_contd(int num, int slot, int func)
 }
 #endif
 
+static void __init intel_remapping_check(int num, int slot, int func)
+{
+	u8 revision;
+
+	revision = read_pci_config_byte(num, slot, func, PCI_REVISION_ID);
+
+	/*
+	 * Revision 0x13 of this chipset supports irq remapping
+	 * but has an erratum that breaks its behavior, flag it as such
+	 */
+	if (revision == 0x13)
+		set_irq_remapping_broken();
+
+}
+
 #define QFLAG_APPLY_ONCE 	0x1
 #define QFLAG_APPLIED		0x2
 #define QFLAG_DONE		(QFLAG_APPLY_ONCE|QFLAG_APPLIED)
@@ -221,6 +237,10 @@  static struct chipset early_qrk[] __initdata = {
 	  PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs },
 	{ PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS,
 	  PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs_contd },
+	{ PCI_VENDOR_ID_INTEL, 0x3403, PCI_CLASS_BRIDGE_HOST,
+	  PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check },
+	{ PCI_VENDOR_ID_INTEL, 0x3406, PCI_CLASS_BRIDGE_HOST,
+	  PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check },
 	{}
 };
 
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index af8904d..4c9379c 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -509,6 +509,16 @@  static int __init intel_irq_remapping_supported(void)
 
 	if (disable_irq_remap)
 		return 0;
+	if (irq_remap_broken) {
+		WARN_TAINT(1, TAINT_FIRMWARE_WORKAROUND,
+			   "This system BIOS has enabled interrupt remapping\n"
+			   "on a chipset that contains an erratum making that\n"
+			   "feature unstable.  To maintain system stability\n"
+			   "interrupt remapping is being disabled.  Please\n"
+			   "contact your BIOS vendor for an update\n");
+		disable_irq_remap = 1;
+		return 0;
+	}
 
 	if (!dmar_ir_support())
 		return 0;
diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c
index faf85d6..018382c 100644
--- a/drivers/iommu/irq_remapping.c
+++ b/drivers/iommu/irq_remapping.c
@@ -12,6 +12,7 @@ 
 int irq_remapping_enabled;
 
 int disable_irq_remap;
+int irq_remap_broken;
 int disable_sourceid_checking;
 int no_x2apic_optout;
 
@@ -58,6 +59,11 @@  void __init setup_irq_remapping_ops(void)
 #endif
 }
 
+void set_irq_remapping_broken(void)
+{
+	irq_remap_broken = 1;
+}
+
 int irq_remapping_supported(void)
 {
 	if (disable_irq_remap)
diff --git a/drivers/iommu/irq_remapping.h b/drivers/iommu/irq_remapping.h
index 95363ac..23bdea1 100644
--- a/drivers/iommu/irq_remapping.h
+++ b/drivers/iommu/irq_remapping.h
@@ -32,6 +32,7 @@  struct pci_dev;
 struct msi_msg;
 
 extern int disable_irq_remap;
+extern int irq_remap_broken;
 extern int disable_sourceid_checking;
 extern int no_x2apic_optout;
 
@@ -88,6 +89,7 @@  extern struct irq_remap_ops amd_iommu_irq_ops;
 
 #define irq_remapping_enabled 0
 #define disable_irq_remap     1
+#define irq_remap_broken      0
 
 #endif /* CONFIG_IRQ_REMAP */