1 files changed, 102 insertions, 26 deletions

diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 420da61d4ce..6535936bdf2 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -180,6 +180,22 @@ static bool eeh_dev_removed(struct eeh_dev *edev)
 	return false;
 }
 
+static void *eeh_dev_save_state(void *data, void *userdata)
+{
+	struct eeh_dev *edev = data;
+	struct pci_dev *pdev;
+
+	if (!edev)
+		return NULL;
+
+	pdev = eeh_dev_to_pci_dev(edev);
+	if (!pdev)
+		return NULL;
+
+	pci_save_state(pdev);
+	return NULL;
+}
+
 /**
  * eeh_report_error - Report pci error to each device driver
  * @data: eeh device
@@ -303,6 +319,22 @@ static void *eeh_report_reset(void *data, void *userdata)
 	return NULL;
 }
 
+static void *eeh_dev_restore_state(void *data, void *userdata)
+{
+	struct eeh_dev *edev = data;
+	struct pci_dev *pdev;
+
+	if (!edev)
+		return NULL;
+
+	pdev = eeh_dev_to_pci_dev(edev);
+	if (!pdev)
+		return NULL;
+
+	pci_restore_state(pdev);
+	return NULL;
+}
+
 /**
  * eeh_report_resume - Tell device to resume normal operations
  * @data: eeh device
@@ -450,38 +482,82 @@ static void *eeh_pe_detach_dev(void *data, void *userdata)
 static void *__eeh_clear_pe_frozen_state(void *data, void *flag)
 {
 	struct eeh_pe *pe = (struct eeh_pe *)data;
-	int i, rc;
+	bool *clear_sw_state = flag;
+	int i, rc = 1;
 
-	for (i = 0; i < 3; i++) {
-		rc = eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
-		if (rc)
-			continue;
-		rc = eeh_pci_enable(pe, EEH_OPT_THAW_DMA);
-		if (!rc)
-			break;
-	}
+	for (i = 0; rc && i < 3; i++)
+		rc = eeh_unfreeze_pe(pe, clear_sw_state);
 
-	/* The PE has been isolated, clear it */
+	/* Stop immediately on any errors */
 	if (rc) {
-		pr_warn("%s: Can't clear frozen PHB#%x-PE#%x (%d)\n",
-			__func__, pe->phb->global_number, pe->addr, rc);
+		pr_warn("%s: Failure %d unfreezing PHB#%x-PE#%x\n",
+			__func__, rc, pe->phb->global_number, pe->addr);
 		return (void *)pe;
 	}
 
 	return NULL;
 }
 
-static int eeh_clear_pe_frozen_state(struct eeh_pe *pe)
+static int eeh_clear_pe_frozen_state(struct eeh_pe *pe,
+				     bool clear_sw_state)
 {
 	void *rc;
 
-	rc = eeh_pe_traverse(pe, __eeh_clear_pe_frozen_state, NULL);
+	rc = eeh_pe_traverse(pe, __eeh_clear_pe_frozen_state, &clear_sw_state);
 	if (!rc)
 		eeh_pe_state_clear(pe, EEH_PE_ISOLATED);
 
 	return rc ? -EIO : 0;
 }
 
+int eeh_pe_reset_and_recover(struct eeh_pe *pe)
+{
+	int result, ret;
+
+	/* Bail if the PE is being recovered */
+	if (pe->state & EEH_PE_RECOVERING)
+		return 0;
+
+	/* Put the PE into recovery mode */
+	eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
+
+	/* Save states */
+	eeh_pe_dev_traverse(pe, eeh_dev_save_state, NULL);
+
+	/* Report error */
+	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);
+		return ret;
+	}
+	eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
+
+	/* Unfreeze the PE */
+	ret = eeh_clear_pe_frozen_state(pe, true);
+	if (ret) {
+		eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
+		return ret;
+	}
+
+	/* Notify completion of reset */
+	eeh_pe_dev_traverse(pe, eeh_report_reset, &result);
+
+	/* Restore device state */
+	eeh_pe_dev_traverse(pe, eeh_dev_restore_state, NULL);
+
+	/* Resume */
+	eeh_pe_dev_traverse(pe, eeh_report_resume, NULL);
+
+	/* Clear recovery mode */
+	eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
+
+	return 0;
+}
+
 /**
  * eeh_reset_device - Perform actual reset of a pci slot
  * @pe: EEH PE
@@ -525,10 +601,10 @@ 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_RESET);
+	eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
 	rc = eeh_reset_pe(pe);
 	if (rc) {
-		eeh_pe_state_clear(pe, EEH_PE_RESET);
+		eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
 		return rc;
 	}
 
@@ -537,10 +613,10 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 	/* Restore PE */
 	eeh_ops->configure_bridge(pe);
 	eeh_pe_restore_bars(pe);
-	eeh_pe_state_clear(pe, EEH_PE_RESET);
+	eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
 
 	/* Clear frozen state */
-	rc = eeh_clear_pe_frozen_state(pe);
+	rc = eeh_clear_pe_frozen_state(pe, false);
 	if (rc)
 		return rc;
 
@@ -599,7 +675,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
 	pe->freeze_count++;
 	if (pe->freeze_count > EEH_MAX_ALLOWED_FREEZES)
 		goto excess_failures;
-	pr_warning("EEH: This PCI device has failed %d times in the last hour\n",
+	pr_warn("EEH: This PCI device has failed %d times in the last hour\n",
 		pe->freeze_count);
 
 	/* Walk the various device drivers attached to this slot through
@@ -616,7 +692,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
 	 */
 	rc = eeh_ops->wait_state(pe, MAX_WAIT_FOR_RECOVERY*1000);
 	if (rc < 0 || rc == EEH_STATE_NOT_SUPPORT) {
-		pr_warning("EEH: Permanent failure\n");
+		pr_warn("EEH: Permanent failure\n");
 		goto hard_fail;
 	}
 
@@ -635,8 +711,8 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
 		pr_info("EEH: Reset with hotplug activity\n");
 		rc = eeh_reset_device(pe, frozen_bus);
 		if (rc) {
-			pr_warning("%s: Unable to reset, err=%d\n",
-				   __func__, rc);
+			pr_warn("%s: Unable to reset, err=%d\n",
+				__func__, rc);
 			goto hard_fail;
 		}
 	}
@@ -678,7 +754,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
 
 	/* If any device has a hard failure, then shut off everything. */
 	if (result == PCI_ERS_RESULT_DISCONNECT) {
-		pr_warning("EEH: Device driver gave up\n");
+		pr_warn("EEH: Device driver gave up\n");
 		goto hard_fail;
 	}
 
@@ -687,8 +763,8 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
 		pr_info("EEH: Reset without hotplug activity\n");
 		rc = eeh_reset_device(pe, NULL);
 		if (rc) {
-			pr_warning("%s: Cannot reset, err=%d\n",
-				   __func__, rc);
+			pr_warn("%s: Cannot reset, err=%d\n",
+				__func__, rc);
 			goto hard_fail;
 		}
 
@@ -701,7 +777,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
 	/* All devices should claim they have recovered by now. */
 	if ((result != PCI_ERS_RESULT_RECOVERED) &&
 	    (result != PCI_ERS_RESULT_NONE)) {
-		pr_warning("EEH: Not recovered\n");
+		pr_warn("EEH: Not recovered\n");
 		goto hard_fail;
 	}