[PATCH v2 3/3] powerpc/eeh: Escalate error on non-existing PE

[Gavin Shan]

Sometimes, especially in sinario of loading another kernel with kdump,
we got EEH error on non-existing PE. That means the PEEV / PEST in
the corresponding PHB would be messy and we can't handle that case.
The patch escalates the error to fenced PHB so that the PHB could be
rested in order to revoer the errors on non-existing PEs.

Reported-by: Mahesh Salgaonkar <mahesh at linux.vnet.ibm.com>
Signed-off-by: Gavin Shan <shangw at linux.vnet.ibm.com>
Tested-by: Mahesh Salgaonkar <mahesh at linux.vnet.ibm.com>
---
 arch/powerpc/platforms/powernv/eeh-ioda.c |   31 +++++++++++++++++++----------
 1 file changed, 21 insertions(+), 10 deletions(-)

diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index e0b12d0..92aa1f9 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -862,11 +862,7 @@ static int ioda_eeh_get_pe(struct pci_controller *hose,
 	dev.phb = hose;
 	dev.pe_config_addr = pe_no;
 	dev_pe = eeh_pe_get(&dev);
-	if (!dev_pe) {
-		pr_warning("%s: Can't find PE for PHB#%x - PE#%x\n",
-			   __func__, hose->global_number, pe_no);
-		return -EEXIST;
-	}
+	if (!dev_pe) return -EEXIST;
 
 	*pe = dev_pe;
 	return 0;
@@ -980,12 +976,27 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
 
 			break;
 		case OPAL_EEH_PE_ERROR:
-			if (ioda_eeh_get_pe(hose, frozen_pe_no, pe))
-				break;
+			/*
+			 * If we can't find the corresponding PE, the
+			 * PEEV / PEST would be messy. So we force an
+			 * fenced PHB so that it can be recovered.
+			 */
+			if (ioda_eeh_get_pe(hose, frozen_pe_no, pe)) {
+				if (!ioda_eeh_get_phb_pe(hose, pe)) {
+					pr_err("EEH: Escalated fenced PHB#%x "
+					       "detected for PE#%llx\n",
+						hose->global_number,
+						frozen_pe_no);
+					ret = EEH_NEXT_ERR_FENCED_PHB;
+				} else {
+					ret = EEH_NEXT_ERR_NONE;
+				}
+			} else {
+				pr_err("EEH: Frozen PE#%x on PHB#%x detected\n",
+					(*pe)->addr, (*pe)->phb->global_number);
+				ret = EEH_NEXT_ERR_FROZEN_PE;
+			}
 
-			pr_err("EEH: Frozen PE#%x on PHB#%x detected\n",
-				(*pe)->addr, (*pe)->phb->global_number);
-			ret = EEH_NEXT_ERR_FROZEN_PE;
 			break;
 		default:
 			pr_warn("%s: Unexpected error type %d\n",
-- 
1.7.10.4