}
/* ------------------------------------------------------- */
-/** eeh_report_error - report an EEH error to each device,
- * collect up and merge the device responses.
+/**
+ * eeh_report_error - report pci error to each device driver
+ *
+ * Report an EEH error to each device driver, collect up and
+ * merge the device driver responses. Cumulative response
+ * passed back in "userdata".
*/
static void eeh_report_error(struct pci_dev *dev, void *userdata)
rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
}
-/** eeh_report_reset -- tell this device that the pci slot
- * has been reset.
+/**
+ * eeh_report_reset - tell device that slot has been reset
*/
static void eeh_report_reset(struct pci_dev *dev, void *userdata)
driver->err_handler->slot_reset(dev);
}
+/**
+ * eeh_report_resume - tell device to resume normal operations
+ */
+
static void eeh_report_resume(struct pci_dev *dev, void *userdata)
{
struct pci_driver *driver = dev->driver;
driver->err_handler->resume(dev);
}
+/**
+ * eeh_report_failure - tell device driver that device is dead.
+ *
+ * This informs the device driver that the device is permanently
+ * dead, and that no further recovery attempts will be made on it.
+ */
+
static void eeh_report_failure(struct pci_dev *dev, void *userdata)
{
struct pci_driver *driver = dev->driver;
*
* pSeries systems will isolate a PCI slot if the PCI-Host
* bridge detects address or data parity errors, DMA's
- * occuring to wild addresses (which usually happen due to
+ * occurring to wild addresses (which usually happen due to
* bugs in device drivers or in PCI adapter firmware).
* Slot isolations also occur if #SERR, #PERR or other misc
* PCI-related errors are detected.
/**
* eeh_reset_device() -- perform actual reset of a pci slot
- * Args: bus: pointer to the pci bus structure corresponding
+ * @bus: pointer to the pci bus structure corresponding
* to the isolated slot. A non-null value will
* cause all devices under the bus to be removed
* and then re-added.
- * pe_dn: pointer to a "Partionable Endpoint" device node.
+ * @pe_dn: pointer to a "Partionable Endpoint" device node.
* This is the top-level structure on which pci
* bus resets can be performed.
*/
static int eeh_reset_device (struct pci_dn *pe_dn, struct pci_bus *bus)
{
- int rc;
+ int cnt, rc;
+
+ /* pcibios will clear the counter; save the value */
+ cnt = pe_dn->eeh_freeze_count;
+
if (bus)
pcibios_remove_pci_devices(bus);
ssleep (5);
pcibios_add_pci_devices(bus);
}
+ pe_dn->eeh_freeze_count = cnt;
return 0;
}
struct pci_bus *frozen_bus;
int rc = 0;
enum pci_ers_result result = PCI_ERS_RESULT_NONE;
- const char *pci_str, *drv_str;
+ const char *location, *pci_str, *drv_str;
frozen_dn = find_device_pe(event->dn);
frozen_bus = pcibios_find_pci_bus(frozen_dn);
if (!frozen_dn) {
- printk(KERN_ERR "EEH: Error: Cannot find partition endpoint for %s\n",
- pci_name(event->dev));
+
+ location = get_property(event->dn, "ibm,loc-code", NULL);
+ location = location ? location : "unknown";
+ printk(KERN_ERR "EEH: Error: Cannot find partition endpoint "
+ "for location=%s pci addr=%s\n",
+ location, pci_name(event->dev));
return NULL;
}
+ location = get_property(frozen_dn, "ibm,loc-code", NULL);
+ location = location ? location : "unknown";
/* There are two different styles for coming up with the PE.
* In the old style, it was the highest EEH-capable device
frozen_bus = pcibios_find_pci_bus (frozen_dn->parent);
if (!frozen_bus) {
- printk(KERN_ERR "EEH: Cannot find PCI bus for %s\n",
- frozen_dn->full_name);
+ printk(KERN_ERR "EEH: Cannot find PCI bus "
+ "for location=%s dn=%s\n",
+ location, frozen_dn->full_name);
return NULL;
}
eeh_slot_error_detail(frozen_pdn, 1 /* Temporary Error */);
printk(KERN_WARNING
- "EEH: This PCI device has failed %d times since last reboot: %s - %s\n",
- frozen_pdn->eeh_freeze_count, drv_str, pci_str);
+ "EEH: This PCI device has failed %d times since last reboot: "
+ "location=%s driver=%s pci addr=%s\n",
+ frozen_pdn->eeh_freeze_count, location, drv_str, pci_str);
/* Walk the various device drivers attached to this slot through
* a reset sequence, giving each an opportunity to do what it needs
* due to actual, failed cards.
*/
printk(KERN_ERR
- "EEH: PCI device %s - %s has failed %d times \n"
- "and has been permanently disabled. Please try reseating\n"
- "this device or replacing it.\n",
- drv_str, pci_str, frozen_pdn->eeh_freeze_count);
+ "EEH: PCI device at location=%s driver=%s pci addr=%s \n"
+ "has failed %d times and has been permanently disabled. \n"
+ "Please try reseating this device or replacing it.\n",
+ location, drv_str, pci_str, frozen_pdn->eeh_freeze_count);
goto perm_error;
hard_fail:
printk(KERN_ERR
- "EEH: Unable to recover from failure of PCI device %s - %s\n"
+ "EEH: Unable to recover from failure of PCI device "
+ "at location=%s driver=%s pci addr=%s \n"
"Please try reseating this device or replacing it.\n",
- drv_str, pci_str);
+ location, drv_str, pci_str);
perm_error:
eeh_slot_error_detail(frozen_pdn, 2 /* Permanent Error */);
projects / linux-2.6 / blobdiff