PCI: Workaround for Intel MPS errata

Intel 5000 and 5100 series memory controllers have a known issue if read
completion coalescing is enabled and the PCI-E Maximum Payload Size is
set to 256B.  To work around this issue, disable read completion
coalescing in the memory controller and root complexes.  Unfortunately,
it must always be disabled, even if no 256B MPS devices are present, due
to the possibility of one being hotplugged.

Links to erratas:
http://www.intel.com/content/dam/doc/specification-update/5000-chipset-memory-controller-hub-specification-update.pdf
http://www.intel.com/content/dam/doc/specification-update/5100-memory-controller-hub-chipset-specification-update.pdf

Thanks to Jesse Brandeburg and Ben Hutchings for providing insight into
the problem.

Tested-and-Reported-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Jon Mason <mason@myri.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>

diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index e5aadf3..dca58b9 100644 (file)
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -2836,6 +2836,75 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SOLARFLARE,
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SOLARFLARE,
                         PCI_DEVICE_ID_SOLARFLARE_SFC4000B, fixup_mpss_256);
 
+/* Intel 5000 and 5100 Memory controllers have an errata with read completion
+ * coalescing (which is enabled by default on some BIOSes) and MPS of 256B.
+ * Since there is no way of knowing what the PCIE MPS on each fabric will be
+ * until all of the devices are discovered and buses walked, read completion
+ * coalescing must be disabled.  Unfortunately, it cannot be re-enabled because
+ * it is possible to hotplug a device with MPS of 256B.
+ */
+static void __devinit quirk_intel_mc_errata(struct pci_dev *dev)
+{
+       int err;
+       u16 rcc;
+
+       if (pcie_bus_config == PCIE_BUS_TUNE_OFF)
+               return;
+
+       /* Intel errata specifies bits to change but does not say what they are.
+        * Keeping them magical until such time as the registers and values can
+        * be explained.
+        */
+       err = pci_read_config_word(dev, 0x48, &rcc);
+       if (err) {
+               dev_err(&dev->dev, "Error attempting to read the read "
+                       "completion coalescing register.\n");
+               return;
+       }
+
+       if (!(rcc & (1 << 10)))
+               return;
+
+       rcc &= ~(1 << 10);
+
+       err = pci_write_config_word(dev, 0x48, rcc);
+       if (err) {
+               dev_err(&dev->dev, "Error attempting to write the read "
+                       "completion coalescing register.\n");
+               return;
+       }
+
+       pr_info_once("Read completion coalescing disabled due to hardware "
+                    "errata relating to 256B MPS.\n");
+}
+/* Intel 5000 series memory controllers and ports 2-7 */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25c0, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25d0, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25d4, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25d8, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25e2, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25e3, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25e4, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25e5, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25e6, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25e7, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25f7, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25f8, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25f9, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25fa, quirk_intel_mc_errata);
+/* Intel 5100 series memory controllers and ports 2-7 */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x65c0, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x65e2, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x65e3, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x65e4, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x65e5, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x65e6, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x65e7, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x65f7, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x65f8, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x65f9, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x65fa, quirk_intel_mc_errata);
+
 static void pci_do_fixups(struct pci_dev *dev, struct pci_fixup *f,
                          struct pci_fixup *end)
 {