powerpc/eeh: Dump PE location code

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>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
This commit is contained in:
Gavin Shan 2014-06-11 18:26:44 +10:00 committed by Benjamin Herrenschmidt
parent d4e58e5928
commit 357b2f3dd9
4 changed files with 84 additions and 11 deletions

View File

@ -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);

View File

@ -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);

View File

@ -791,6 +791,66 @@ void eeh_pe_restore_bars(struct eeh_pe *pe)
eeh_pe_dev_traverse(pe, eeh_restore_one_device_bars, NULL);
}
/**
* 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

View File

@ -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;
}