1 files changed, 392 insertions, 370 deletions

diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 0c0b66fc5bfb..9446248eb6b8 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -35,22 +35,86 @@
 #include <asm/rtas.h>
 
 struct eeh_rmv_data {
-	struct list_head edev_list;
-	int removed;
+	struct list_head removed_vf_list;
+	int removed_dev_count;
 };
 
-/**
- * eeh_pcid_name - Retrieve name of PCI device driver
- * @pdev: PCI device
- *
- * This routine is used to retrieve the name of PCI device driver
- * if that's valid.
- */
-static inline const char *eeh_pcid_name(struct pci_dev *pdev)
+static int eeh_result_priority(enum pci_ers_result result)
 {
-	if (pdev && pdev->dev.driver)
-		return pdev->dev.driver->name;
-	return "";
+	switch (result) {
+	case PCI_ERS_RESULT_NONE:
+		return 1;
+	case PCI_ERS_RESULT_NO_AER_DRIVER:
+		return 2;
+	case PCI_ERS_RESULT_RECOVERED:
+		return 3;
+	case PCI_ERS_RESULT_CAN_RECOVER:
+		return 4;
+	case PCI_ERS_RESULT_DISCONNECT:
+		return 5;
+	case PCI_ERS_RESULT_NEED_RESET:
+		return 6;
+	default:
+		WARN_ONCE(1, "Unknown pci_ers_result value: %d\n", (int)result);
+		return 0;
+	}
+};
+
+const char *pci_ers_result_name(enum pci_ers_result result)
+{
+	switch (result) {
+	case PCI_ERS_RESULT_NONE:
+		return "none";
+	case PCI_ERS_RESULT_CAN_RECOVER:
+		return "can recover";
+	case PCI_ERS_RESULT_NEED_RESET:
+		return "need reset";
+	case PCI_ERS_RESULT_DISCONNECT:
+		return "disconnect";
+	case PCI_ERS_RESULT_RECOVERED:
+		return "recovered";
+	case PCI_ERS_RESULT_NO_AER_DRIVER:
+		return "no AER driver";
+	default:
+		WARN_ONCE(1, "Unknown result type: %d\n", (int)result);
+		return "unknown";
+	}
+};
+
+static __printf(2, 3) void eeh_edev_info(const struct eeh_dev *edev,
+					 const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	printk(KERN_INFO "EEH: PE#%x (PCI %s): %pV\n", edev->pe_config_addr,
+	       edev->pdev ? dev_name(&edev->pdev->dev) : "none", &vaf);
+
+	va_end(args);
+}
+
+static enum pci_ers_result pci_ers_merge_result(enum pci_ers_result old,
+						enum pci_ers_result new)
+{
+	if (eeh_result_priority(new) > eeh_result_priority(old))
+		return new;
+	return old;
+}
+
+static bool eeh_dev_removed(struct eeh_dev *edev)
+{
+	return !edev || (edev->mode & EEH_DEV_REMOVED);
+}
+
+static bool eeh_edev_actionable(struct eeh_dev *edev)
+{
+	return (edev->pdev && !eeh_dev_removed(edev) &&
+		!eeh_pe_passed(edev->pe));
 }
 
 /**
@@ -98,22 +162,20 @@ static inline void eeh_pcid_put(struct pci_dev *pdev)
  * do real work because EEH should freeze DMA transfers for those PCI
  * devices encountering EEH errors, which includes MSI or MSI-X.
  */
-static void eeh_disable_irq(struct pci_dev *dev)
+static void eeh_disable_irq(struct eeh_dev *edev)
 {
-	struct eeh_dev *edev = pci_dev_to_eeh_dev(dev);
-
 	/* Don't disable MSI and MSI-X interrupts. They are
 	 * effectively disabled by the DMA Stopped state
 	 * when an EEH error occurs.
 	 */
-	if (dev->msi_enabled || dev->msix_enabled)
+	if (edev->pdev->msi_enabled || edev->pdev->msix_enabled)
 		return;
 
-	if (!irq_has_action(dev->irq))
+	if (!irq_has_action(edev->pdev->irq))
 		return;
 
 	edev->mode |= EEH_DEV_IRQ_DISABLED;
-	disable_irq_nosync(dev->irq);
+	disable_irq_nosync(edev->pdev->irq);
 }
 
 /**
@@ -123,10 +185,8 @@ static void eeh_disable_irq(struct pci_dev *dev)
  * This routine must be called to enable interrupt while failed
  * device could be resumed.
  */
-static void eeh_enable_irq(struct pci_dev *dev)
+static void eeh_enable_irq(struct eeh_dev *edev)
 {
-	struct eeh_dev *edev = pci_dev_to_eeh_dev(dev);
-
 	if ((edev->mode) & EEH_DEV_IRQ_DISABLED) {
 		edev->mode &= ~EEH_DEV_IRQ_DISABLED;
 		/*
@@ -149,23 +209,13 @@ static void eeh_enable_irq(struct pci_dev *dev)
 		 *
 		 *	tglx
 		 */
-		if (irqd_irq_disabled(irq_get_irq_data(dev->irq)))
-			enable_irq(dev->irq);
+		if (irqd_irq_disabled(irq_get_irq_data(edev->pdev->irq)))
+			enable_irq(edev->pdev->irq);
 	}
 }
 
-static bool eeh_dev_removed(struct eeh_dev *edev)
-{
-	/* EEH device removed ? */
-	if (!edev || (edev->mode & EEH_DEV_REMOVED))
-		return true;
-
-	return false;
-}
-
-static void *eeh_dev_save_state(void *data, void *userdata)
+static void *eeh_dev_save_state(struct eeh_dev *edev, void *userdata)
 {
-	struct eeh_dev *edev = data;
 	struct pci_dev *pdev;
 
 	if (!edev)
@@ -189,135 +239,159 @@ static void *eeh_dev_save_state(void *data, void *userdata)
 	return NULL;
 }
 
-/**
- * eeh_report_error - Report pci error to each device driver
- * @data: eeh device
- * @userdata: return value
- *
- * Report an EEH error to each device driver, collect up and
- * merge the device driver responses. Cumulative response
- * passed back in "userdata".
- */
-static void *eeh_report_error(void *data, void *userdata)
+static void eeh_set_channel_state(struct eeh_pe *root, enum pci_channel_state s)
 {
-	struct eeh_dev *edev = (struct eeh_dev *)data;
-	struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
-	enum pci_ers_result rc, *res = userdata;
-	struct pci_driver *driver;
+	struct eeh_pe *pe;
+	struct eeh_dev *edev, *tmp;
 
-	if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe))
-		return NULL;
-	dev->error_state = pci_channel_io_frozen;
+	eeh_for_each_pe(root, pe)
+		eeh_pe_for_each_dev(pe, edev, tmp)
+			if (eeh_edev_actionable(edev))
+				edev->pdev->error_state = s;
+}
 
-	driver = eeh_pcid_get(dev);
-	if (!driver) return NULL;
+static void eeh_set_irq_state(struct eeh_pe *root, bool enable)
+{
+	struct eeh_pe *pe;
+	struct eeh_dev *edev, *tmp;
 
-	eeh_disable_irq(dev);
+	eeh_for_each_pe(root, pe) {
+		eeh_pe_for_each_dev(pe, edev, tmp) {
+			if (!eeh_edev_actionable(edev))
+				continue;
 
-	if (!driver->err_handler ||
-	    !driver->err_handler->error_detected) {
-		eeh_pcid_put(dev);
-		return NULL;
+			if (!eeh_pcid_get(edev->pdev))
+				continue;
+
+			if (enable)
+				eeh_enable_irq(edev);
+			else
+				eeh_disable_irq(edev);
+
+			eeh_pcid_put(edev->pdev);
+		}
 	}
+}
 
-	rc = driver->err_handler->error_detected(dev, pci_channel_io_frozen);
+typedef enum pci_ers_result (*eeh_report_fn)(struct eeh_dev *,
+					     struct pci_driver *);
+static void eeh_pe_report_edev(struct eeh_dev *edev, eeh_report_fn fn,
+			       enum pci_ers_result *result)
+{
+	struct pci_driver *driver;
+	enum pci_ers_result new_result;
 
-	/* A driver that needs a reset trumps all others */
-	if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
-	if (*res == PCI_ERS_RESULT_NONE) *res = rc;
+	if (!edev->pdev) {
+		eeh_edev_info(edev, "no device");
+		return;
+	}
+	device_lock(&edev->pdev->dev);
+	if (eeh_edev_actionable(edev)) {
+		driver = eeh_pcid_get(edev->pdev);
+
+		if (!driver)
+			eeh_edev_info(edev, "no driver");
+		else if (!driver->err_handler)
+			eeh_edev_info(edev, "driver not EEH aware");
+		else if (edev->mode & EEH_DEV_NO_HANDLER)
+			eeh_edev_info(edev, "driver bound too late");
+		else {
+			new_result = fn(edev, driver);
+			eeh_edev_info(edev, "%s driver reports: '%s'",
+				      driver->name,
+				      pci_ers_result_name(new_result));
+			if (result)
+				*result = pci_ers_merge_result(*result,
+							       new_result);
+		}
+		if (driver)
+			eeh_pcid_put(edev->pdev);
+	} else {
+		eeh_edev_info(edev, "not actionable (%d,%d,%d)", !!edev->pdev,
+			      !eeh_dev_removed(edev), !eeh_pe_passed(edev->pe));
+	}
+	device_unlock(&edev->pdev->dev);
+}
 
-	edev->in_error = true;
-	eeh_pcid_put(dev);
-	pci_uevent_ers(dev, PCI_ERS_RESULT_NONE);
-	return NULL;
+static void eeh_pe_report(const char *name, struct eeh_pe *root,
+			  eeh_report_fn fn, enum pci_ers_result *result)
+{
+	struct eeh_pe *pe;
+	struct eeh_dev *edev, *tmp;
+
+	pr_info("EEH: Beginning: '%s'\n", name);
+	eeh_for_each_pe(root, pe) eeh_pe_for_each_dev(pe, edev, tmp)
+		eeh_pe_report_edev(edev, fn, result);
+	if (result)
+		pr_info("EEH: Finished:'%s' with aggregate recovery state:'%s'\n",
+			name, pci_ers_result_name(*result));
+	else
+		pr_info("EEH: Finished:'%s'", name);
 }
 
 /**
- * eeh_report_mmio_enabled - Tell drivers that MMIO has been enabled
- * @data: eeh device
- * @userdata: return value
+ * eeh_report_error - Report pci error to each device driver
+ * @edev: eeh device
+ * @driver: device's PCI driver
  *
- * Tells each device driver that IO ports, MMIO and config space I/O
- * are now enabled. Collects up and merges the device driver responses.
- * Cumulative response passed back in "userdata".
+ * Report an EEH error to each device driver.
  */
-static void *eeh_report_mmio_enabled(void *data, void *userdata)
+static enum pci_ers_result eeh_report_error(struct eeh_dev *edev,
+					    struct pci_driver *driver)
 {
-	struct eeh_dev *edev = (struct eeh_dev *)data;
-	struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
-	enum pci_ers_result rc, *res = userdata;
-	struct pci_driver *driver;
-
-	if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe))
-		return NULL;
-
-	driver = eeh_pcid_get(dev);
-	if (!driver) return NULL;
+	enum pci_ers_result rc;
+	struct pci_dev *dev = edev->pdev;
 
-	if (!driver->err_handler ||
-	    !driver->err_handler->mmio_enabled ||
-	    (edev->mode & EEH_DEV_NO_HANDLER)) {
-		eeh_pcid_put(dev);
-		return NULL;
-	}
+	if (!driver->err_handler->error_detected)
+		return PCI_ERS_RESULT_NONE;
 
-	rc = driver->err_handler->mmio_enabled(dev);
+	eeh_edev_info(edev, "Invoking %s->error_detected(IO frozen)",
+		      driver->name);
+	rc = driver->err_handler->error_detected(dev, pci_channel_io_frozen);
 
-	/* A driver that needs a reset trumps all others */
-	if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
-	if (*res == PCI_ERS_RESULT_NONE) *res = rc;
+	edev->in_error = true;
+	pci_uevent_ers(dev, PCI_ERS_RESULT_NONE);
+	return rc;
+}
 
-	eeh_pcid_put(dev);
-	return NULL;
+/**
+ * eeh_report_mmio_enabled - Tell drivers that MMIO has been enabled
+ * @edev: eeh device
+ * @driver: device's PCI driver
+ *
+ * Tells each device driver that IO ports, MMIO and config space I/O
+ * are now enabled.
+ */
+static enum pci_ers_result eeh_report_mmio_enabled(struct eeh_dev *edev,
+						   struct pci_driver *driver)
+{
+	if (!driver->err_handler->mmio_enabled)
+		return PCI_ERS_RESULT_NONE;
+	eeh_edev_info(edev, "Invoking %s->mmio_enabled()", driver->name);
+	return driver->err_handler->mmio_enabled(edev->pdev);
 }
 
 /**
  * eeh_report_reset - Tell device that slot has been reset
- * @data: eeh device
- * @userdata: return value
+ * @edev: eeh device
+ * @driver: device's PCI driver
  *
  * This routine must be called while EEH tries to reset particular
  * PCI device so that the associated PCI device driver could take
  * some actions, usually to save data the driver needs so that the
  * driver can work again while the device is recovered.
  */
-static void *eeh_report_reset(void *data, void *userdata)
+static enum pci_ers_result eeh_report_reset(struct eeh_dev *edev,
+					    struct pci_driver *driver)
 {
-	struct eeh_dev *edev = (struct eeh_dev *)data;
-	struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
-	enum pci_ers_result rc, *res = userdata;
-	struct pci_driver *driver;
-
-	if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe))
-		return NULL;
-	dev->error_state = pci_channel_io_normal;
-
-	driver = eeh_pcid_get(dev);
-	if (!driver) return NULL;
-
-	eeh_enable_irq(dev);
-
-	if (!driver->err_handler ||
-	    !driver->err_handler->slot_reset ||
-	    (edev->mode & EEH_DEV_NO_HANDLER) ||
-	    (!edev->in_error)) {
-		eeh_pcid_put(dev);
-		return NULL;
-	}
-
-	rc = driver->err_handler->slot_reset(dev);
-	if ((*res == PCI_ERS_RESULT_NONE) ||
-	    (*res == PCI_ERS_RESULT_RECOVERED)) *res = rc;
-	if (*res == PCI_ERS_RESULT_DISCONNECT &&
-	     rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
-
-	eeh_pcid_put(dev);
-	return NULL;
+	if (!driver->err_handler->slot_reset || !edev->in_error)
+		return PCI_ERS_RESULT_NONE;
+	eeh_edev_info(edev, "Invoking %s->slot_reset()", driver->name);
+	return driver->err_handler->slot_reset(edev->pdev);
 }
 
-static void *eeh_dev_restore_state(void *data, void *userdata)
+static void *eeh_dev_restore_state(struct eeh_dev *edev, void *userdata)
 {
-	struct eeh_dev *edev = data;
 	struct pci_dev *pdev;
 
 	if (!edev)
@@ -330,7 +404,7 @@ static void *eeh_dev_restore_state(void *data, void *userdata)
 	 * EEH device is created.
 	 */
 	if (edev->pe && (edev->pe->state & EEH_PE_CFG_RESTRICTED)) {
-		if (list_is_last(&edev->list, &edev->pe->edevs))
+		if (list_is_last(&edev->entry, &edev->pe->edevs))
 			eeh_pe_restore_bars(edev->pe);
 
 		return NULL;
@@ -346,90 +420,58 @@ static void *eeh_dev_restore_state(void *data, void *userdata)
 
 /**
  * eeh_report_resume - Tell device to resume normal operations
- * @data: eeh device
- * @userdata: return value
+ * @edev: eeh device
+ * @driver: device's PCI driver
  *
  * This routine must be called to notify the device driver that it
  * could resume so that the device driver can do some initialization
  * to make the recovered device work again.
  */
-static void *eeh_report_resume(void *data, void *userdata)
+static enum pci_ers_result eeh_report_resume(struct eeh_dev *edev,
+					     struct pci_driver *driver)
 {
-	struct eeh_dev *edev = (struct eeh_dev *)data;
-	struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
-	bool was_in_error;
-	struct pci_driver *driver;
-
-	if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe))
-		return NULL;
-	dev->error_state = pci_channel_io_normal;
-
-	driver = eeh_pcid_get(dev);
-	if (!driver) return NULL;
-
-	was_in_error = edev->in_error;
-	edev->in_error = false;
-	eeh_enable_irq(dev);
+	if (!driver->err_handler->resume || !edev->in_error)
+		return PCI_ERS_RESULT_NONE;
 
-	if (!driver->err_handler ||
-	    !driver->err_handler->resume ||
-	    (edev->mode & EEH_DEV_NO_HANDLER) || !was_in_error) {
-		edev->mode &= ~EEH_DEV_NO_HANDLER;
-		eeh_pcid_put(dev);
-		return NULL;
-	}
-
-	driver->err_handler->resume(dev);
+	eeh_edev_info(edev, "Invoking %s->resume()", driver->name);
+	driver->err_handler->resume(edev->pdev);
 
-	eeh_pcid_put(dev);
-	pci_uevent_ers(dev, PCI_ERS_RESULT_RECOVERED);
+	pci_uevent_ers(edev->pdev, PCI_ERS_RESULT_RECOVERED);
 #ifdef CONFIG_PCI_IOV
 	if (eeh_ops->notify_resume && eeh_dev_to_pdn(edev))
 		eeh_ops->notify_resume(eeh_dev_to_pdn(edev));
 #endif
-	return NULL;
+	return PCI_ERS_RESULT_NONE;
 }
 
 /**
  * eeh_report_failure - Tell device driver that device is dead.
- * @data: eeh device
- * @userdata: return value
+ * @edev: eeh device
+ * @driver: device's PCI driver
  *
  * This informs the device driver that the device is permanently
  * dead, and that no further recovery attempts will be made on it.
  */
-static void *eeh_report_failure(void *data, void *userdata)
+static enum pci_ers_result eeh_report_failure(struct eeh_dev *edev,
+					      struct pci_driver *driver)
 {
-	struct eeh_dev *edev = (struct eeh_dev *)data;
-	struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
-	struct pci_driver *driver;
+	enum pci_ers_result rc;
 
-	if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe))
-		return NULL;
-	dev->error_state = pci_channel_io_perm_failure;
-
-	driver = eeh_pcid_get(dev);
-	if (!driver) return NULL;
-
-	eeh_disable_irq(dev);
-
-	if (!driver->err_handler ||
-	    !driver->err_handler->error_detected) {
-		eeh_pcid_put(dev);
-		return NULL;
-	}
+	if (!driver->err_handler->error_detected)
+		return PCI_ERS_RESULT_NONE;
 
-	driver->err_handler->error_detected(dev, pci_channel_io_perm_failure);
+	eeh_edev_info(edev, "Invoking %s->error_detected(permanent failure)",
+		      driver->name);
+	rc = driver->err_handler->error_detected(edev->pdev,
+						 pci_channel_io_perm_failure);
 
-	eeh_pcid_put(dev);
-	pci_uevent_ers(dev, PCI_ERS_RESULT_DISCONNECT);
-	return NULL;
+	pci_uevent_ers(edev->pdev, PCI_ERS_RESULT_DISCONNECT);
+	return rc;
 }
 
-static void *eeh_add_virt_device(void *data, void *userdata)
+static void *eeh_add_virt_device(struct eeh_dev *edev)
 {
 	struct pci_driver *driver;
-	struct eeh_dev *edev = (struct eeh_dev *)data;
 	struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
 	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 
@@ -442,9 +484,11 @@ static void *eeh_add_virt_device(void *data, void *userdata)
 
 	driver = eeh_pcid_get(dev);
 	if (driver) {
-		eeh_pcid_put(dev);
-		if (driver->err_handler)
+		if (driver->err_handler) {
+			eeh_pcid_put(dev);
 			return NULL;
+		}
+		eeh_pcid_put(dev);
 	}
 
 #ifdef CONFIG_PCI_IOV
@@ -453,13 +497,11 @@ static void *eeh_add_virt_device(void *data, void *userdata)
 	return NULL;
 }
 
-static void *eeh_rmv_device(void *data, void *userdata)
+static void *eeh_rmv_device(struct eeh_dev *edev, void *userdata)
 {
 	struct pci_driver *driver;
-	struct eeh_dev *edev = (struct eeh_dev *)data;
 	struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
 	struct eeh_rmv_data *rmv_data = (struct eeh_rmv_data *)userdata;
-	int *removed = rmv_data ? &rmv_data->removed : NULL;
 
 	/*
 	 * Actually, we should remove the PCI bridges as well.
@@ -481,26 +523,27 @@ static void *eeh_rmv_device(void *data, void *userdata)
 	if (eeh_dev_removed(edev))
 		return NULL;
 
-	driver = eeh_pcid_get(dev);
-	if (driver) {
-		eeh_pcid_put(dev);
-		if (removed &&
-		    eeh_pe_passed(edev->pe))
-			return NULL;
-		if (removed &&
-		    driver->err_handler &&
-		    driver->err_handler->error_detected &&
-		    driver->err_handler->slot_reset)
+	if (rmv_data) {
+		if (eeh_pe_passed(edev->pe))
 			return NULL;
+		driver = eeh_pcid_get(dev);
+		if (driver) {
+			if (driver->err_handler &&
+			    driver->err_handler->error_detected &&
+			    driver->err_handler->slot_reset) {
+				eeh_pcid_put(dev);
+				return NULL;
+			}
+			eeh_pcid_put(dev);
+		}
 	}
 
 	/* Remove it from PCI subsystem */
 	pr_debug("EEH: Removing %s without EEH sensitive driver\n",
 		 pci_name(dev));
-	edev->bus = dev->bus;
 	edev->mode |= EEH_DEV_DISCONNECTED;
-	if (removed)
-		(*removed)++;
+	if (rmv_data)
+		rmv_data->removed_dev_count++;
 
 	if (edev->physfn) {
 #ifdef CONFIG_PCI_IOV
@@ -516,7 +559,7 @@ static void *eeh_rmv_device(void *data, void *userdata)
 		pdn->pe_number = IODA_INVALID_PE;
 #endif
 		if (rmv_data)
-			list_add(&edev->rmv_list, &rmv_data->edev_list);
+			list_add(&edev->rmv_entry, &rmv_data->removed_vf_list);
 	} else {
 		pci_lock_rescan_remove();
 		pci_stop_and_remove_bus_device(dev);
@@ -526,9 +569,8 @@ static void *eeh_rmv_device(void *data, void *userdata)
 	return NULL;
 }
 
-static void *eeh_pe_detach_dev(void *data, void *userdata)
+static void *eeh_pe_detach_dev(struct eeh_pe *pe, void *userdata)
 {
-	struct eeh_pe *pe = (struct eeh_pe *)data;
 	struct eeh_dev *edev, *tmp;
 
 	eeh_pe_for_each_dev(pe, edev, tmp) {
@@ -549,9 +591,8 @@ static void *eeh_pe_detach_dev(void *data, void *userdata)
  * PE reset (for 3 times), we try to clear the frozen state
  * for 3 times as well.
  */
-static void *__eeh_clear_pe_frozen_state(void *data, void *flag)
+static void *__eeh_clear_pe_frozen_state(struct eeh_pe *pe, void *flag)
 {
-	struct eeh_pe *pe = (struct eeh_pe *)data;
 	bool clear_sw_state = *(bool *)flag;
 	int i, rc = 1;
 
@@ -619,17 +660,19 @@ int eeh_pe_reset_and_recover(struct eeh_pe *pe)
 
 /**
  * eeh_reset_device - Perform actual reset of a pci slot
+ * @driver_eeh_aware: Does the device's driver provide EEH support?
  * @pe: EEH PE
  * @bus: PCI bus corresponding to the isolcated slot
+ * @rmv_data: Optional, list to record removed devices
  *
  * This routine must be called to do reset on the indicated PE.
  * During the reset, udev might be invoked because those affected
  * PCI devices will be removed and then added.
  */
 static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
-				struct eeh_rmv_data *rmv_data)
+			    struct eeh_rmv_data *rmv_data,
+			    bool driver_eeh_aware)
 {
-	struct pci_bus *frozen_bus = eeh_pe_bus_get(pe);
 	time64_t tstamp;
 	int cnt, rc;
 	struct eeh_dev *edev;
@@ -645,16 +688,12 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
 	 * into pci_hp_add_devices().
 	 */
 	eeh_pe_state_mark(pe, EEH_PE_KEEP);
-	if (bus) {
-		if (pe->type & EEH_PE_VF) {
-			eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL);
-		} else {
-			pci_lock_rescan_remove();
-			pci_hp_remove_devices(bus);
-			pci_unlock_rescan_remove();
-		}
-	} else if (frozen_bus) {
+	if (driver_eeh_aware || (pe->type & EEH_PE_VF)) {
 		eeh_pe_dev_traverse(pe, eeh_rmv_device, rmv_data);
+	} else {
+		pci_lock_rescan_remove();
+		pci_hp_remove_devices(bus);
+		pci_unlock_rescan_remove();
 	}
 
 	/*
@@ -689,8 +728,9 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
 	 * the device up before the scripts have taken it down,
 	 * potentially weird things happen.
 	 */
-	if (bus) {
-		pr_info("EEH: Sleep 5s ahead of complete hotplug\n");
+	if (!driver_eeh_aware || rmv_data->removed_dev_count) {
+		pr_info("EEH: Sleep 5s ahead of %s hotplug\n",
+			(driver_eeh_aware ? "partial" : "complete"));
 		ssleep(5);
 
 		/*
@@ -698,24 +738,15 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
 		 * PE. We should disconnect it so the binding can be
 		 * rebuilt when adding PCI devices.
 		 */
-		edev = list_first_entry(&pe->edevs, struct eeh_dev, list);
+		edev = list_first_entry(&pe->edevs, struct eeh_dev, entry);
 		eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL);
 		if (pe->type & EEH_PE_VF) {
-			eeh_add_virt_device(edev, NULL);
+			eeh_add_virt_device(edev);
 		} else {
-			eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
+			if (!driver_eeh_aware)
+				eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
 			pci_hp_add_devices(bus);
 		}
-	} else if (frozen_bus && rmv_data->removed) {
-		pr_info("EEH: Sleep 5s ahead of partial hotplug\n");
-		ssleep(5);
-
-		edev = list_first_entry(&pe->edevs, struct eeh_dev, list);
-		eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL);
-		if (pe->type & EEH_PE_VF)
-			eeh_add_virt_device(edev, NULL);
-		else
-			pci_hp_add_devices(frozen_bus);
 	}
 	eeh_pe_state_clear(pe, EEH_PE_KEEP);
 
@@ -733,39 +764,52 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
 
 /**
  * eeh_handle_normal_event - Handle EEH events on a specific PE
- * @pe: EEH PE
+ * @pe: EEH PE - which should not be used after we return, as it may
+ * have been invalidated.
  *
  * Attempts to recover the given PE.  If recovery fails or the PE has failed
  * too many times, remove the PE.
  *
- * Returns true if @pe should no longer be used, else false.
+ * While PHB detects address or data parity errors on particular PCI
+ * slot, the associated PE will be frozen. Besides, DMA's occurring
+ * to wild addresses (which usually happen due to bugs in device
+ * drivers or in PCI adapter firmware) can cause EEH error. #SERR,
+ * #PERR or other misc PCI-related errors also can trigger EEH errors.
+ *
+ * Recovery process consists of unplugging the device driver (which
+ * generated hotplug events to userspace), then issuing a PCI #RST to
+ * the device, then reconfiguring the PCI config space for all bridges
+ * & devices under this slot, and then finally restarting the device
+ * drivers (which cause a second set of hotplug events to go out to
+ * userspace).
  */
-static bool eeh_handle_normal_event(struct eeh_pe *pe)
+void eeh_handle_normal_event(struct eeh_pe *pe)
 {
-	struct pci_bus *frozen_bus;
+	struct pci_bus *bus;
 	struct eeh_dev *edev, *tmp;
+	struct eeh_pe *tmp_pe;
 	int rc = 0;
 	enum pci_ers_result result = PCI_ERS_RESULT_NONE;
-	struct eeh_rmv_data rmv_data = {LIST_HEAD_INIT(rmv_data.edev_list), 0};
+	struct eeh_rmv_data rmv_data =
+		{LIST_HEAD_INIT(rmv_data.removed_vf_list), 0};
 
-	frozen_bus = eeh_pe_bus_get(pe);
-	if (!frozen_bus) {
+	bus = eeh_pe_bus_get(pe);
+	if (!bus) {
 		pr_err("%s: Cannot find PCI bus for PHB#%x-PE#%x\n",
 			__func__, pe->phb->global_number, pe->addr);
-		return false;
+		return;
 	}
 
+	eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
+
 	eeh_pe_update_time_stamp(pe);
 	pe->freeze_count++;
 	if (pe->freeze_count > eeh_max_freezes) {
-		pr_err("EEH: PHB#%x-PE#%x has failed %d times in the\n"
-		       "last hour and has been permanently disabled.\n",
+		pr_err("EEH: PHB#%x-PE#%x has failed %d times in the last hour and has been permanently disabled.\n",
 		       pe->phb->global_number, pe->addr,
 		       pe->freeze_count);
-		goto hard_fail;
+		result = PCI_ERS_RESULT_DISCONNECT;
 	}
-	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
 	 * a reset sequence, giving each an opportunity to do what it needs
@@ -777,28 +821,39 @@ static bool eeh_handle_normal_event(struct eeh_pe *pe)
 	 * the error. Override the result if necessary to have partially
 	 * hotplug for this case.
 	 */
-	pr_info("EEH: Notify device drivers to shutdown\n");
-	eeh_pe_dev_traverse(pe, eeh_report_error, &result);
-	if ((pe->type & EEH_PE_PHB) &&
-	    result != PCI_ERS_RESULT_NONE &&
-	    result != PCI_ERS_RESULT_NEED_RESET)
-		result = PCI_ERS_RESULT_NEED_RESET;
+	if (result != PCI_ERS_RESULT_DISCONNECT) {
+		pr_warn("EEH: This PCI device has failed %d times in the last hour and will be permanently disabled after %d failures.\n",
+			pe->freeze_count, eeh_max_freezes);
+		pr_info("EEH: Notify device drivers to shutdown\n");
+		eeh_set_channel_state(pe, pci_channel_io_frozen);
+		eeh_set_irq_state(pe, false);
+		eeh_pe_report("error_detected(IO frozen)", pe,
+			      eeh_report_error, &result);
+		if ((pe->type & EEH_PE_PHB) &&
+		    result != PCI_ERS_RESULT_NONE &&
+		    result != PCI_ERS_RESULT_NEED_RESET)
+			result = PCI_ERS_RESULT_NEED_RESET;
+	}
 
 	/* Get the current PCI slot state. This can take a long time,
 	 * sometimes over 300 seconds for certain systems.
 	 */
-	rc = eeh_ops->wait_state(pe, MAX_WAIT_FOR_RECOVERY*1000);
-	if (rc < 0 || rc == EEH_STATE_NOT_SUPPORT) {
-		pr_warn("EEH: Permanent failure\n");
-		goto hard_fail;
+	if (result != PCI_ERS_RESULT_DISCONNECT) {
+		rc = eeh_wait_state(pe, MAX_WAIT_FOR_RECOVERY*1000);
+		if (rc < 0 || rc == EEH_STATE_NOT_SUPPORT) {
+			pr_warn("EEH: Permanent failure\n");
+			result = PCI_ERS_RESULT_DISCONNECT;
+		}
 	}
 
 	/* Since rtas may enable MMIO when posting the error log,
 	 * don't post the error log until after all dev drivers
 	 * have been informed.
 	 */
-	pr_info("EEH: Collect temporary log\n");
-	eeh_slot_error_detail(pe, EEH_LOG_TEMP);
+	if (result != PCI_ERS_RESULT_DISCONNECT) {
+		pr_info("EEH: Collect temporary log\n");
+		eeh_slot_error_detail(pe, EEH_LOG_TEMP);
+	}
 
 	/* If all device drivers were EEH-unaware, then shut
 	 * down all of the device drivers, and hope they
@@ -806,11 +861,11 @@ static bool eeh_handle_normal_event(struct eeh_pe *pe)
 	 */
 	if (result == PCI_ERS_RESULT_NONE) {
 		pr_info("EEH: Reset with hotplug activity\n");
-		rc = eeh_reset_device(pe, frozen_bus, NULL);
+		rc = eeh_reset_device(pe, bus, NULL, false);
 		if (rc) {
 			pr_warn("%s: Unable to reset, err=%d\n",
 				__func__, rc);
-			goto hard_fail;
+			result = PCI_ERS_RESULT_DISCONNECT;
 		}
 	}
 
@@ -819,13 +874,14 @@ static bool eeh_handle_normal_event(struct eeh_pe *pe)
 		pr_info("EEH: Enable I/O for affected devices\n");
 		rc = eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
 
-		if (rc < 0)
-			goto hard_fail;
-		if (rc) {
+		if (rc < 0) {
+			result = PCI_ERS_RESULT_DISCONNECT;
+		} else if (rc) {
 			result = PCI_ERS_RESULT_NEED_RESET;
 		} else {
 			pr_info("EEH: Notify device drivers to resume I/O\n");
-			eeh_pe_dev_traverse(pe, eeh_report_mmio_enabled, &result);
+			eeh_pe_report("mmio_enabled", pe,
+				      eeh_report_mmio_enabled, &result);
 		}
 	}
 
@@ -834,9 +890,9 @@ static bool eeh_handle_normal_event(struct eeh_pe *pe)
 		pr_info("EEH: Enabled DMA for affected devices\n");
 		rc = eeh_pci_enable(pe, EEH_OPT_THAW_DMA);
 
-		if (rc < 0)
-			goto hard_fail;
-		if (rc) {
+		if (rc < 0) {
+			result = PCI_ERS_RESULT_DISCONNECT;
+		} else if (rc) {
 			result = PCI_ERS_RESULT_NEED_RESET;
 		} else {
 			/*
@@ -849,74 +905,74 @@ static bool 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_warn("EEH: Device driver gave up\n");
-		goto hard_fail;
-	}
-
 	/* If any device called out for a reset, then reset the slot */
 	if (result == PCI_ERS_RESULT_NEED_RESET) {
 		pr_info("EEH: Reset without hotplug activity\n");
-		rc = eeh_reset_device(pe, NULL, &rmv_data);
+		rc = eeh_reset_device(pe, bus, &rmv_data, true);
 		if (rc) {
 			pr_warn("%s: Cannot reset, err=%d\n",
 				__func__, rc);
-			goto hard_fail;
+			result = PCI_ERS_RESULT_DISCONNECT;
+		} else {
+			result = PCI_ERS_RESULT_NONE;
+			eeh_set_channel_state(pe, pci_channel_io_normal);
+			eeh_set_irq_state(pe, true);
+			eeh_pe_report("slot_reset", pe, eeh_report_reset,
+				      &result);
 		}
-
-		pr_info("EEH: Notify device drivers "
-			"the completion of reset\n");
-		result = PCI_ERS_RESULT_NONE;
-		eeh_pe_dev_traverse(pe, eeh_report_reset, &result);
-	}
-
-	/* All devices should claim they have recovered by now. */
-	if ((result != PCI_ERS_RESULT_RECOVERED) &&
-	    (result != PCI_ERS_RESULT_NONE)) {
-		pr_warn("EEH: Not recovered\n");
-		goto hard_fail;
-	}
-
-	/*
-	 * For those hot removed VFs, we should add back them after PF get
-	 * recovered properly.
-	 */
-	list_for_each_entry_safe(edev, tmp, &rmv_data.edev_list, rmv_list) {
-		eeh_add_virt_device(edev, NULL);
-		list_del(&edev->rmv_list);
 	}
 
-	/* Tell all device drivers that they can resume operations */
-	pr_info("EEH: Notify device driver to resume\n");
-	eeh_pe_dev_traverse(pe, eeh_report_resume, NULL);
+	if ((result == PCI_ERS_RESULT_RECOVERED) ||
+	    (result == PCI_ERS_RESULT_NONE)) {
+		/*
+		 * For those hot removed VFs, we should add back them after PF
+		 * get recovered properly.
+		 */
+		list_for_each_entry_safe(edev, tmp, &rmv_data.removed_vf_list,
+					 rmv_entry) {
+			eeh_add_virt_device(edev);
+			list_del(&edev->rmv_entry);
+		}
 
-	return false;
+		/* Tell all device drivers that they can resume operations */
+		pr_info("EEH: Notify device driver to resume\n");
+		eeh_set_channel_state(pe, pci_channel_io_normal);
+		eeh_set_irq_state(pe, true);
+		eeh_pe_report("resume", pe, eeh_report_resume, NULL);
+		eeh_for_each_pe(pe, tmp_pe) {
+			eeh_pe_for_each_dev(tmp_pe, edev, tmp) {
+				edev->mode &= ~EEH_DEV_NO_HANDLER;
+				edev->in_error = false;
+			}
+		}
 
-hard_fail:
-	/*
-	 * About 90% of all real-life EEH failures in the field
-	 * are due to poorly seated PCI cards. Only 10% or so are
-	 * due to actual, failed cards.
-	 */
-	pr_err("EEH: Unable to recover from failure from PHB#%x-PE#%x.\n"
-	       "Please try reseating or replacing it\n",
-		pe->phb->global_number, pe->addr);
+		pr_info("EEH: Recovery successful.\n");
+	} else  {
+		/*
+		 * About 90% of all real-life EEH failures in the field
+		 * are due to poorly seated PCI cards. Only 10% or so are
+		 * due to actual, failed cards.
+		 */
+		pr_err("EEH: Unable to recover from failure from PHB#%x-PE#%x.\n"
+		       "Please try reseating or replacing it\n",
+			pe->phb->global_number, pe->addr);
 
-	eeh_slot_error_detail(pe, EEH_LOG_PERM);
+		eeh_slot_error_detail(pe, EEH_LOG_PERM);
 
-	/* Notify all devices that they're about to go down. */
-	eeh_pe_dev_traverse(pe, eeh_report_failure, NULL);
+		/* Notify all devices that they're about to go down. */
+		eeh_set_channel_state(pe, pci_channel_io_perm_failure);
+		eeh_set_irq_state(pe, false);
+		eeh_pe_report("error_detected(permanent failure)", pe,
+			      eeh_report_failure, NULL);
 
-	/* Mark the PE to be removed permanently */
-	eeh_pe_state_mark(pe, EEH_PE_REMOVED);
+		/* Mark the PE to be removed permanently */
+		eeh_pe_state_mark(pe, EEH_PE_REMOVED);
 
-	/*
-	 * Shut down the device drivers for good. We mark
-	 * all removed devices correctly to avoid access
-	 * the their PCI config any more.
-	 */
-	if (frozen_bus) {
+		/*
+		 * Shut down the device drivers for good. We mark
+		 * all removed devices correctly to avoid access
+		 * the their PCI config any more.
+		 */
 		if (pe->type & EEH_PE_VF) {
 			eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL);
 			eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
@@ -925,14 +981,13 @@ hard_fail:
 			eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
 
 			pci_lock_rescan_remove();
-			pci_hp_remove_devices(frozen_bus);
+			pci_hp_remove_devices(bus);
 			pci_unlock_rescan_remove();
-
 			/* The passed PE should no longer be used */
-			return true;
+			return;
 		}
 	}
-	return false;
+	eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
 }
 
 /**
@@ -942,7 +997,7 @@ hard_fail:
  * specific PE.  Iterates through possible failures and handles them as
  * necessary.
  */
-static void eeh_handle_special_event(void)
+void eeh_handle_special_event(void)
 {
 	struct eeh_pe *pe, *phb_pe;
 	struct pci_bus *bus;
@@ -966,7 +1021,7 @@ static void eeh_handle_special_event(void)
 				phb_pe = eeh_phb_pe_get(hose);
 				if (!phb_pe) continue;
 
-				eeh_pe_state_mark(phb_pe, EEH_PE_ISOLATED);
+				eeh_pe_mark_isolated(phb_pe);
 			}
 
 			eeh_serialize_unlock(flags);
@@ -981,11 +1036,9 @@ static void eeh_handle_special_event(void)
 			/* Purge all events of the PHB */
 			eeh_remove_event(pe, true);
 
-			if (rc == EEH_NEXT_ERR_DEAD_PHB)
-				eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
-			else
-				eeh_pe_state_mark(pe,
-					EEH_PE_ISOLATED | EEH_PE_RECOVERING);
+			if (rc != EEH_NEXT_ERR_DEAD_PHB)
+				eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
+			eeh_pe_mark_isolated(pe);
 
 			eeh_serialize_unlock(flags);
 
@@ -1005,15 +1058,7 @@ static void eeh_handle_special_event(void)
 		 */
 		if (rc == EEH_NEXT_ERR_FROZEN_PE ||
 		    rc == EEH_NEXT_ERR_FENCED_PHB) {
-			/*
-			 * eeh_handle_normal_event() can make the PE stale if it
-			 * determines that the PE cannot possibly be recovered.
-			 * Don't modify the PE state if that's the case.
-			 */
-			if (eeh_handle_normal_event(pe))
-				continue;
-
-			eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
+			eeh_handle_normal_event(pe);
 		} else {
 			pci_lock_rescan_remove();
 			list_for_each_entry(hose, &hose_list, list_node) {
@@ -1025,7 +1070,9 @@ static void eeh_handle_special_event(void)
 
 				/* Notify all devices to be down */
 				eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
-				eeh_pe_dev_traverse(pe,
+				eeh_set_channel_state(pe, pci_channel_io_perm_failure);
+				eeh_pe_report(
+					"error_detected(permanent failure)", pe,
 					eeh_report_failure, NULL);
 				bus = eeh_pe_bus_get(phb_pe);
 				if (!bus) {
@@ -1049,28 +1096,3 @@ static void eeh_handle_special_event(void)
 			break;
 	} while (rc != EEH_NEXT_ERR_NONE);
 }
-
-/**
- * eeh_handle_event - Reset a PCI device after hard lockup.
- * @pe: EEH PE
- *
- * While PHB detects address or data parity errors on particular PCI
- * slot, the associated PE will be frozen. Besides, DMA's occurring
- * to wild addresses (which usually happen due to bugs in device
- * drivers or in PCI adapter firmware) can cause EEH error. #SERR,
- * #PERR or other misc PCI-related errors also can trigger EEH errors.
- *
- * Recovery process consists of unplugging the device driver (which
- * generated hotplug events to userspace), then issuing a PCI #RST to
- * the device, then reconfiguring the PCI config space for all bridges
- * & devices under this slot, and then finally restarting the device
- * drivers (which cause a second set of hotplug events to go out to
- * userspace).
- */
-void eeh_handle_event(struct eeh_pe *pe)
-{
-	if (pe)
-		eeh_handle_normal_event(pe);
-	else
-		eeh_handle_special_event();
-}