iommu/vt-d: add quirk for broken interrupt remapping on 55XX chipsets

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>

5 files changed, 40 insertions, 0 deletions

diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index 95fd3527f632..aca6aa2088b2 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -28,6 +28,7 @@
 
 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);
@@ -54,6 +55,7 @@ void irq_remap_modify_chip_defaults(struct irq_chip *chip);
 
 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 3755ef494390..94ab6b90dd3f 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 f3b8f23b5d8f..5b19b2d6ec2d 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -524,6 +524,16 @@ 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 d56f8c17c5fe..3c11043bdee5 100644
--- a/drivers/iommu/irq_remapping.c
+++ b/drivers/iommu/irq_remapping.c
@@ -19,6 +19,7 @@
 int irq_remapping_enabled;
 
 int disable_irq_remap;
+int irq_remap_broken;
 int disable_sourceid_checking;
 int no_x2apic_optout;
 
@@ -211,6 +212,11 @@ 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 ecb637670405..90c4dae5a46b 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;
 extern int irq_remapping_enabled;
@@ -89,6 +90,7 @@ 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 */