summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorNeil Horman <nhorman@tuxdriver.com>2010-09-21 13:54:39 -0400
committerJesse Barnes <jbarnes@virtuousgeek.org>2010-10-15 13:09:50 -0700
commit66db60eaf158aa953651d03e43e931e757e87262 (patch)
treeac095123c1c92b4a646d8e908cbca835b63ac611
parentb22c3d82757109fa107ce17ba9484d45273eed05 (diff)
PCI: add quirk for non-symmetric-mode irq routing to versions 0 and 4 of the MCP55 northbridge
A long time ago I worked on a RHEL5 bug in which kdump hung during boot on a set of systems. The systems hung because they never received timer interrupts during calibrate_delay. These systems also all had Opteron processors on a hypertransport bus, bridged to a pci bus via an Nvidia MCP55 northbridge chip. After much wrangling I managed to learn from Nvidia that they have an undocumented register in some versions of that chip which control how legacy interrupts are send to the cpu complex when the ioapic isn't active. Nvidia defaults this register to only send legacy interrupts to the BSP, so if kdump happens to boot on an AP, we never get timer interrupts and boom. I had initially used this quirk as a workaround, with my intent being to move apic initalization to an earlier point in the boot process, so the setting of the register would be irrelevant. Given the work involved in doing that however, the fragile nature of the apic initalization code, and the fact that, over the 2 years since we found this bug, the MCP55 is the only chip which seems to have this issue, I've figure at this point its likely safer to just carry the quirk around. By setting the referenced bits in this hidden register, interrupts will be broadcast to all cpus when the ioapic isn't active on the above described systems. Acked-by: Simon Horman <horms@verge.net.au> Acked-by: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
-rw-r--r--drivers/pci/quirks.c31
-rw-r--r--include/linux/pci_ids.h2
2 files changed, 33 insertions, 0 deletions
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 857ae01734a..034430690a5 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -2296,6 +2296,37 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA,
PCI_DEVICE_ID_NVIDIA_NVENET_15,
nvenet_msi_disable);
+/*
+ * Some versions of the MCP55 bridge from nvidia have a legacy irq routing
+ * config register. This register controls the routing of legacy interrupts
+ * from devices that route through the MCP55. If this register is misprogramed
+ * interrupts are only sent to the bsp, unlike conventional systems where the
+ * irq is broadxast to all online cpus. Not having this register set
+ * properly prevents kdump from booting up properly, so lets make sure that
+ * we have it set correctly.
+ * Note this is an undocumented register.
+ */
+static void __devinit nvbridge_check_legacy_irq_routing(struct pci_dev *dev)
+{
+ u32 cfg;
+
+ pci_read_config_dword(dev, 0x74, &cfg);
+
+ if (cfg & ((1 << 2) | (1 << 15))) {
+ printk(KERN_INFO "Rewriting irq routing register on MCP55\n");
+ cfg &= ~((1 << 2) | (1 << 15));
+ pci_write_config_dword(dev, 0x74, cfg);
+ }
+}
+
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA,
+ PCI_DEVICE_ID_NVIDIA_MCP55_BRIDGE_V0,
+ nvbridge_check_legacy_irq_routing);
+
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA,
+ PCI_DEVICE_ID_NVIDIA_MCP55_BRIDGE_V4,
+ nvbridge_check_legacy_irq_routing);
+
static int __devinit ht_check_msi_mapping(struct pci_dev *dev)
{
int pos, ttl = 48;
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 570fddeb038..dc2827723c1 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -1249,6 +1249,8 @@
#define PCI_DEVICE_ID_NVIDIA_GEFORCE_FX_GO5700_2 0x0348
#define PCI_DEVICE_ID_NVIDIA_QUADRO_FX_GO1000 0x034C
#define PCI_DEVICE_ID_NVIDIA_QUADRO_FX_1100 0x034E
+#define PCI_DEVICE_ID_NVIDIA_MCP55_BRIDGE_V0 0x0360
+#define PCI_DEVICE_ID_NVIDIA_MCP55_BRIDGE_V4 0x0364
#define PCI_DEVICE_ID_NVIDIA_NVENET_15 0x0373
#define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP61_SATA 0x03E7
#define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP61_SMBUS 0x03EB