powerpc/eeh: Freeze PE before PE reset

The patch adds one more option (EEH_OPT_FREEZE_PE) to set_option()
method to proactively freeze PE, which will be issued before resetting
pass-throughed PE to drop MMIO access during reset because it's
always contributing to recursive EEH error.

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

4 files changed, 44 insertions, 11 deletions

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index c79869d4a652..59d3e2a4fc42 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -172,6 +172,7 @@ enum {
 #define EEH_OPT_ENABLE		1	/* EEH enable	*/
 #define EEH_OPT_THAW_MMIO	2	/* MMIO enable	*/
 #define EEH_OPT_THAW_DMA	3	/* DMA enable	*/
+#define EEH_OPT_FREEZE_PE	4	/* Freeze PE	*/
 #define EEH_STATE_UNAVAILABLE	(1 << 0)	/* State unavailable	*/
 #define EEH_STATE_NOT_SUPPORT	(1 << 1)	/* EEH not supported	*/
 #define EEH_STATE_RESET_ACTIVE	(1 << 2)	/* Active reset		*/
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index db35c2722201..633f6bf965c3 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -1382,6 +1382,13 @@ int eeh_pe_reset(struct eeh_pe *pe, int option)
 		break;
 	case EEH_RESET_HOT:
 	case EEH_RESET_FUNDAMENTAL:
+		/*
+		 * Proactively freeze the PE to drop all MMIO access
+		 * during reset, which should be banned as it's always
+		 * cause recursive EEH error.
+		 */
+		eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE);
+
 		ret = eeh_ops->reset(pe, option);
 		break;
 	default:
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index df5c2cc55285..1d8f37b93457 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -189,6 +189,7 @@ static int ioda_eeh_set_option(struct eeh_pe *pe, int option)
 {
 	struct pci_controller *hose = pe->phb;
 	struct pnv_phb *phb = hose->private_data;
+	bool freeze_pe = false;
 	int enable, ret = 0;
 	s64 rc;
 
@@ -212,6 +213,10 @@ static int ioda_eeh_set_option(struct eeh_pe *pe, int option)
 	case EEH_OPT_THAW_DMA:
 		enable = OPAL_EEH_ACTION_CLEAR_FREEZE_DMA;
 		break;
+	case EEH_OPT_FREEZE_PE:
+		freeze_pe = true;
+		enable = OPAL_EEH_ACTION_SET_FREEZE_ALL;
+		break;
 	default:
 		pr_warn("%s: Invalid option %d\n",
 			__func__, option);
@@ -219,17 +224,35 @@ static int ioda_eeh_set_option(struct eeh_pe *pe, int option)
 	}
 
 	/* If PHB supports compound PE, to handle it */
-	if (phb->unfreeze_pe) {
-		ret = phb->unfreeze_pe(phb, pe->addr, enable);
+	if (freeze_pe) {
+		if (phb->freeze_pe) {
+			phb->freeze_pe(phb, pe->addr);
+		} else {
+			rc = opal_pci_eeh_freeze_set(phb->opal_id,
+						     pe->addr,
+						     enable);
+			if (rc != OPAL_SUCCESS) {
+				pr_warn("%s: Failure %lld freezing "
+					"PHB#%x-PE#%x\n",
+					__func__, rc,
+					phb->hose->global_number, pe->addr);
+				ret = -EIO;
+			}
+		}
 	} else {
-		rc = opal_pci_eeh_freeze_clear(phb->opal_id,
-					       pe->addr,
-					       enable);
-		if (rc != OPAL_SUCCESS) {
-			pr_warn("%s: Failure %lld enable %d for PHB#%x-PE#%x\n",
-				__func__, rc, option, phb->hose->global_number,
-				pe->addr);
-			ret = -EIO;
+		if (phb->unfreeze_pe) {
+			ret = phb->unfreeze_pe(phb, pe->addr, enable);
+		} else {
+			rc = opal_pci_eeh_freeze_clear(phb->opal_id,
+						       pe->addr,
+						       enable);
+			if (rc != OPAL_SUCCESS) {
+				pr_warn("%s: Failure %lld enable %d "
+					"for PHB#%x-PE#%x\n",
+					__func__, rc, option,
+					phb->hose->global_number, pe->addr);
+				ret = -EIO;
+			}
 		}
 	}
 
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index b08053819d99..b645dc60e000 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -349,7 +349,9 @@ static int pseries_eeh_set_option(struct eeh_pe *pe, int option)
 		if (pe->addr)
 			config_addr = pe->addr;
 		break;
-
+	case EEH_OPT_FREEZE_PE:
+		/* Not support */
+		return 0;
 	default:
 		pr_err("%s: Invalid option %d\n",
 			__func__, option);