[PATCH 1/3] powerpc/eeh: Refactor eeh_reset_pe()

[PATCH 1/3] powerpc/eeh: Refactor eeh_reset_pe()

[Gavin Shan]

The patch refactors eeh_reset_pe() in order for:

   * Varied return values for different failure cases.
   * Replace pr_err() with pr_warn() and print function name.
   * Coding style cleanup.

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
---
 arch/powerpc/kernel/eeh.c | 29 ++++++++++++++++++-----------
 1 file changed, 18 insertions(+), 11 deletions(-)

diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 2248a19..967e4a0 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -758,30 +758,37 @@ static void eeh_reset_pe_once(struct eeh_pe *pe)
 int eeh_reset_pe(struct eeh_pe *pe)
 {
 	int flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
-	int i, rc;
+	int i, state, ret;
 
 	/* Take three shots at resetting the bus */
-	for (i=0; i<3; i++) {
+	for (i = 0; i < 3; i++) {
 		eeh_reset_pe_once(pe);
 
 		/*
 		 * EEH_PE_ISOLATED is expected to be removed after
 		 * BAR restore.
 		 */
-		rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
-		if ((rc & flags) == flags)
-			return 0;
+		state = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
+		if ((state & flags) == flags) {
+			ret = 0;
+			goto out;
+		}
 
-		if (rc < 0) {
-			pr_err("%s: Unrecoverable slot failure on PHB#%d-PE#%x",
+		if (state < 0) {
+			pr_warn("%s: Unrecoverable slot failure on PHB#%d-PE#%x",
 				__func__, pe->phb->global_number, pe->addr);
-			return -1;
+			ret = -ENOTRECOVERABLE;
+			goto out;
 		}
-		pr_err("EEH: bus reset %d failed on PHB#%d-PE#%x, rc=%d\n",
-			i+1, pe->phb->global_number, pe->addr, rc);
+
+		/* We might run out of credits */
+		ret = -EIO;
+		pr_warn("%s: Failure %d resetting PHB#%x-PE#%x\n (%d)\n",
+			__func__, state, pe->phb->global_number, pe->addr, (i + 1));
 	}
 
-	return -1;
+out:
+	return ret;
 }
 
 /**
-- 
1.8.3.2

[PATCH 2/3] powerpc/eeh: Set EEH_PE_RESET on PE reset

[Gavin Shan]

The patch introduces additional flag EEH_PE_RESET to indicate the
corresponding PE is under reset. In turn, the PE retrieval bakcend
on PowerNV platform can return unfrozen state for the EEH core to
moving forward. Flag EEH_PE_CFG_BLOCKED isn't the correct one for
the purpose.

In PCI passthrou case, the problem is more worse: Guest doesn't
recover 6th EEH error. The PE is left in isolated (frozen) and
config blocked state on Broadcom adapters. We can't retrieve the
PE's state correctly any more, even from the host side via sysfs
/sys/bus/pci/devices/xxx/eeh_pe_state.

Reported-by: Rajeshkumar Subramanian <rajeshkumars@in.ibm.com>
Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/eeh.h            |  1 +
 arch/powerpc/kernel/eeh.c                 |  4 ++++
 arch/powerpc/kernel/eeh_driver.c          | 10 ++--------
 arch/powerpc/platforms/powernv/eeh-ioda.c |  2 +-
 4 files changed, 8 insertions(+), 9 deletions(-)

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index ca07f9c..2e633b4 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -72,6 +72,7 @@ struct device_node;
 #define EEH_PE_ISOLATED		(1 << 0)	/* Isolated PE		*/
 #define EEH_PE_RECOVERING	(1 << 1)	/* Recovering PE	*/
 #define EEH_PE_CFG_BLOCKED	(1 << 2)	/* Block config access	*/
+#define EEH_PE_RESET		(1 << 3)	/* PE reset in progress */
 
 #define EEH_PE_KEEP		(1 << 8)	/* Keep PE on hotplug	*/
 #define EEH_PE_CFG_RESTRICTED	(1 << 9)	/* Block config on error */
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 967e4a0..b372bfd 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -760,6 +760,9 @@ int eeh_reset_pe(struct eeh_pe *pe)
 	int flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
 	int i, state, ret;
 
+	/* Mark as reset and block config space */
+	eeh_pe_state_mark(pe, EEH_PE_RESET | EEH_PE_CFG_BLOCKED);
+
 	/* Take three shots at resetting the bus */
 	for (i = 0; i < 3; i++) {
 		eeh_reset_pe_once(pe);
@@ -788,6 +791,7 @@ int eeh_reset_pe(struct eeh_pe *pe)
 	}
 
 out:
+	eeh_pe_state_clear(pe, EEH_PE_RESET | EEH_PE_CFG_BLOCKED);
 	return ret;
 }
 
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 6535936..b17e793 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -528,13 +528,11 @@ int eeh_pe_reset_and_recover(struct eeh_pe *pe)
 	eeh_pe_dev_traverse(pe, eeh_report_error, &result);
 
 	/* Issue reset */
-	eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
 	ret = eeh_reset_pe(pe);
 	if (ret) {
-		eeh_pe_state_clear(pe, EEH_PE_RECOVERING | EEH_PE_CFG_BLOCKED);
+		eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
 		return ret;
 	}
-	eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
 
 	/* Unfreeze the PE */
 	ret = eeh_clear_pe_frozen_state(pe, true);
@@ -601,19 +599,15 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 	 * config accesses. So we prefer to block them. However, controlled
 	 * PCI config accesses initiated from EEH itself are allowed.
 	 */
-	eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
 	rc = eeh_reset_pe(pe);
-	if (rc) {
-		eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
+	if (rc)
 		return rc;
-	}
 
 	pci_lock_rescan_remove();
 
 	/* Restore PE */
 	eeh_ops->configure_bridge(pe);
 	eeh_pe_restore_bars(pe);
-	eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
 
 	/* Clear frozen state */
 	rc = eeh_clear_pe_frozen_state(pe, false);
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index eba9cb1..426814a 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -373,7 +373,7 @@ static int ioda_eeh_get_pe_state(struct eeh_pe *pe)
 	 * moving forward, we have to return operational
 	 * state during PE reset.
 	 */
-	if (pe->state & EEH_PE_CFG_BLOCKED) {
+	if (pe->state & EEH_PE_RESET) {
 		result = (EEH_STATE_MMIO_ACTIVE  |
 			  EEH_STATE_DMA_ACTIVE   |
 			  EEH_STATE_MMIO_ENABLED |
-- 
1.8.3.2

[PATCH 3/3] powerpc/eeh: Recover EEH error on ownership change for BCM5719

[Gavin Shan]

In PCI passthrou scenario, we need simulate EEH recovery for Emulex
adapters when their ownership changes, as we did in commit 5cfb20b96
("powerpc/eeh: Emulate EEH recovery for VFIO devices"). Broadcom
BCM5719 adpaters are facing same problem and needs same cure.

Reported-by: Rajeshkumar Subramanian <rajeshkumars@in.ibm.com>
Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
---
 arch/powerpc/kernel/eeh.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index b372bfd..f1c6b11 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -1220,6 +1220,7 @@ int eeh_unfreeze_pe(struct eeh_pe *pe, bool sw_state)
 static struct pci_device_id eeh_reset_ids[] = {
 	{ PCI_DEVICE(0x19a2, 0x0710) },	/* Emulex, BE     */
 	{ PCI_DEVICE(0x10df, 0xe220) },	/* Emulex, Lancer */
+	{ PCI_DEVICE(0x14e4, 0x1657) }, /* Broadcom BCM5719 */
 	{ 0 }
 };
 
-- 
1.8.3.2