@@ -254,6 +254,7 @@ void *eeh_pe_traverse(struct eeh_pe *root,
void *eeh_pe_dev_traverse(struct eeh_pe *root,
eeh_traverse_func fn, void *flag);
void eeh_pe_restore_bars(struct eeh_pe *pe);
+const char *eeh_pe_loc_get(struct eeh_pe *pe);
struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe);
void *eeh_dev_init(struct device_node *dn, void *data);
@@ -330,8 +330,8 @@ static int eeh_phb_check_failure(struct eeh_pe *pe)
eeh_pe_state_mark(phb_pe, EEH_PE_ISOLATED);
eeh_serialize_unlock(flags);
- pr_err("EEH: PHB#%x failure detected\n",
- phb_pe->phb->global_number);
+ pr_err("EEH: PHB#%x failure detected, location: %s\n",
+ phb_pe->phb->global_number, eeh_pe_loc_get(phb_pe));
dump_stack();
eeh_send_failure_event(phb_pe);
@@ -362,7 +362,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev)
unsigned long flags;
struct device_node *dn;
struct pci_dev *dev;
- struct eeh_pe *pe, *parent_pe;
+ struct eeh_pe *pe, *parent_pe, *phb_pe;
int rc = 0;
const char *location;
@@ -481,8 +481,11 @@ int eeh_dev_check_failure(struct eeh_dev *edev)
* a stack trace will help the device-driver authors figure
* out what happened. So print that out.
*/
- pr_err("EEH: Frozen PE#%x detected on PHB#%x\n",
- pe->addr, pe->phb->global_number);
+ phb_pe = eeh_phb_pe_get(pe->phb);
+ pr_err("EEH: Frozen PHB#%x-PE#%x detected\n",
+ pe->phb->global_number, pe->addr);
+ pr_err("EEH: PE location: %s, PHB location: %s\n",
+ eeh_pe_loc_get(pe), eeh_pe_loc_get(phb_pe));
dump_stack();
eeh_send_failure_event(pe);
@@ -792,6 +792,66 @@ void eeh_pe_restore_bars(struct eeh_pe *pe)
}
/**
+ * eeh_pe_loc_get - Retrieve location code binding to the given PE
+ * @pe: EEH PE
+ *
+ * Retrieve the location code of the given PE. If the primary PE bus
+ * is root bus, we will grab location code from PHB device tree node
+ * or root port. Otherwise, the upstream bridge's device tree node
+ * of the primary PE bus will be checked for the location code.
+ */
+const char *eeh_pe_loc_get(struct eeh_pe *pe)
+{
+ struct pci_controller *hose;
+ struct pci_bus *bus = eeh_pe_bus_get(pe);
+ struct pci_dev *pdev;
+ struct device_node *dn;
+ const char *loc;
+
+ if (!bus)
+ return "N/A";
+
+ /* PHB PE or root PE ? */
+ if (pci_is_root_bus(bus)) {
+ hose = pci_bus_to_host(bus);
+ loc = of_get_property(hose->dn,
+ "ibm,loc-code", NULL);
+ if (loc)
+ return loc;
+ loc = of_get_property(hose->dn,
+ "ibm,io-base-loc-code", NULL);
+ if (loc)
+ return loc;
+
+ pdev = pci_get_slot(bus, 0x0);
+ } else {
+ pdev = bus->self;
+ }
+
+ if (!pdev) {
+ loc = "N/A";
+ goto out;
+ }
+
+ dn = pci_device_to_OF_node(pdev);
+ if (!dn) {
+ loc = "N/A";
+ goto out;
+ }
+
+ loc = of_get_property(dn, "ibm,loc-code", NULL);
+ if (!loc)
+ loc = of_get_property(dn, "ibm,slot-location-code", NULL);
+ if (!loc)
+ loc = "N/A";
+
+out:
+ if (pci_is_root_bus(bus) && pdev)
+ pci_dev_put(pdev);
+ return loc;
+}
+
+/**
* eeh_pe_bus_get - Retrieve PCI bus according to the given PE
* @pe: EEH PE
*
@@ -774,19 +774,24 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
case OPAL_EEH_PHB_ERROR:
if (be16_to_cpu(severity) == OPAL_EEH_SEV_PHB_DEAD) {
*pe = phb_pe;
- pr_err("EEH: dead PHB#%x detected\n",
- hose->global_number);
+ pr_err("EEH: dead PHB#%x detected, "
+ "location: %s\n",
+ hose->global_number,
+ eeh_pe_loc_get(phb_pe));
ret = EEH_NEXT_ERR_DEAD_PHB;
} else if (be16_to_cpu(severity) ==
OPAL_EEH_SEV_PHB_FENCED) {
*pe = phb_pe;
- pr_err("EEH: fenced PHB#%x detected\n",
- hose->global_number);
+ pr_err("EEH: Fenced PHB#%x detected, "
+ "location: %s\n",
+ hose->global_number,
+ eeh_pe_loc_get(phb_pe));
ret = EEH_NEXT_ERR_FENCED_PHB;
} else if (be16_to_cpu(severity) == OPAL_EEH_SEV_INF) {
pr_info("EEH: PHB#%x informative error "
- "detected\n",
- hose->global_number);
+ "detected, location: %s\n",
+ hose->global_number,
+ eeh_pe_loc_get(phb_pe));
ioda_eeh_phb_diag(hose);
ret = EEH_NEXT_ERR_NONE;
}
@@ -802,6 +807,8 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
/* Try best to clear it */
pr_info("EEH: Clear non-existing PHB#%x-PE#%llx\n",
hose->global_number, frozen_pe_no);
+ pr_info("EEH: PHB location: %s\n",
+ eeh_pe_loc_get(phb_pe));
opal_pci_eeh_freeze_clear(phb->opal_id, frozen_pe_no,
OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
ret = EEH_NEXT_ERR_NONE;
@@ -810,6 +817,8 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
} else {
pr_err("EEH: Frozen PE#%x on PHB#%x detected\n",
(*pe)->addr, (*pe)->phb->global_number);
+ pr_err("EEH: PE location: %s, PHB location: %s\n",
+ eeh_pe_loc_get(*pe), eeh_pe_loc_get(phb_pe));
ret = EEH_NEXT_ERR_FROZEN_PE;
}
As Ben suggested, it's meaningful to dump PE's location code for site engineers when hitting EEH errors. The patch introduces function eeh_pe_loc_get() to retireve the location code from dev-tree so that we can output it when hitting EEH errors. If primary PE bus is root bus, the PHB's dev-node would be tried prior to root port's dev-node. Otherwise, the upstream bridge's dev-node of the primary PE bus will be check for the location code directly. Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com> --- arch/powerpc/include/asm/eeh.h | 1 + arch/powerpc/kernel/eeh.c | 13 ++++--- arch/powerpc/kernel/eeh_pe.c | 60 +++++++++++++++++++++++++++++++ arch/powerpc/platforms/powernv/eeh-ioda.c | 21 +++++++---- 4 files changed, 84 insertions(+), 11 deletions(-)