powerpc/powernv: Clear PAPR error injection registers

The frozen state on one specific PE is probably caused by error
injection, which is done with help of PAPR error injection registers.
According to the hardware spec, those registers should be cleared
automatically after one-shot frozen PE. However, that's not always
true, at least on P7IOC of Firebird-L. So we have to clear them
before doing PE reset to avoid recursive EEH errors at recovery
stage.

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

1 files changed, 25 insertions, 0 deletions

diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index 22609f23f455..d6fb90b32525 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -682,6 +682,31 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option)
 	if (pe->type & EEH_PE_PHB) {
 		ret = ioda_eeh_phb_reset(hose, option);
 	} else {
+		struct pnv_phb *phb;
+		s64 rc;
+
+		/*
+		 * The frozen PE might be caused by PAPR error injection
+		 * registers, which are expected to be cleared after hitting
+		 * frozen PE as stated in the hardware spec. Unfortunately,
+		 * that's not true on P7IOC. So we have to clear it manually
+		 * to avoid recursive EEH errors during recovery.
+		 */
+		phb = hose->private_data;
+		if (phb->model == PNV_PHB_MODEL_P7IOC &&
+		    (option == EEH_RESET_HOT ||
+		    option == EEH_RESET_FUNDAMENTAL)) {
+			rc = opal_pci_reset(phb->opal_id,
+					    OPAL_PHB_ERROR,
+					    OPAL_ASSERT_RESET);
+			if (rc != OPAL_SUCCESS) {
+				pr_warn("%s: Failure %lld clearing "
+					"error injection registers\n",
+					__func__, rc);
+				return -EIO;
+			}
+		}
+
 		bus = eeh_pe_bus_get(pe);
 		if (pci_is_root_bus(bus) ||
 		    pci_is_root_bus(bus->parent))