powerpc/eeh: Remove EEH PE for normal PCI hotplug

Function eeh_rmv_from_parent_pe() could be called by the path of
either normal PCI hotplug, or EEH recovery. For the former case,
we need purge the corresponding PE on removal of the associated
PE bus.

The patch tries to cover that by passing more information to function
pcibios_remove_pci_devices() so that we know if the corresponding PE
needs to be purged or be marked as "invalid".

Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

4 files changed, 61 insertions, 26 deletions

diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
index 18c168b..43f6ed4 100644
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -817,6 +817,7 @@ EXPORT_SYMBOL_GPL(eeh_add_device_tree_late);
 /**
  * eeh_remove_device - Undo EEH setup for the indicated pci device
  * @dev: pci device to be removed
+ * @purge_pe: remove the PE or not
  *
  * This routine should be called when a device is removed from
  * a running system (e.g. by hotplug or dlpar).  It unregisters
@@ -824,7 +825,7 @@ EXPORT_SYMBOL_GPL(eeh_add_device_tree_late);
  * this device will no longer be detected after this call; thus,
  * i/o errors affecting this slot may leave this device unusable.
  */
-static void eeh_remove_device(struct pci_dev *dev)
+static void eeh_remove_device(struct pci_dev *dev, int purge_pe)
 {
 	struct eeh_dev *edev;
 
@@ -843,7 +844,7 @@ static void eeh_remove_device(struct pci_dev *dev)
 	dev->dev.archdata.edev = NULL;
 	pci_dev_put(dev);
 
-	eeh_rmv_from_parent_pe(edev);
+	eeh_rmv_from_parent_pe(edev, purge_pe);
 	eeh_addr_cache_rmv_dev(dev);
 	eeh_sysfs_remove_device(dev);
 }
@@ -851,21 +852,22 @@ static void eeh_remove_device(struct pci_dev *dev)
 /**
  * eeh_remove_bus_device - Undo EEH setup for the indicated PCI device
  * @dev: PCI device
+ * @purge_pe: remove the corresponding PE or not
  *
  * This routine must be called when a device is removed from the
  * running system through hotplug or dlpar. The corresponding
  * PCI address cache will be removed.
  */
-void eeh_remove_bus_device(struct pci_dev *dev)
+void eeh_remove_bus_device(struct pci_dev *dev, int purge_pe)
 {
 	struct pci_bus *bus = dev->subordinate;
 	struct pci_dev *child, *tmp;
 
-	eeh_remove_device(dev);
+	eeh_remove_device(dev, purge_pe);
 
 	if (bus && dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
 		list_for_each_entry_safe(child, tmp, &bus->devices, bus_list)
-			 eeh_remove_bus_device(child);
+			 eeh_remove_bus_device(child, purge_pe);
 	}
 }
 EXPORT_SYMBOL_GPL(eeh_remove_bus_device);
diff --git a/arch/powerpc/platforms/pseries/eeh_driver.c b/arch/powerpc/platforms/pseries/eeh_driver.c
index 8370ce7..37c2cf7 100644
--- a/arch/powerpc/platforms/pseries/eeh_driver.c
+++ b/arch/powerpc/platforms/pseries/eeh_driver.c
@@ -305,8 +305,14 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 	/* pcibios will clear the counter; save the value */
 	cnt = pe->freeze_count;
 
+	/*
+	 * We don't remove the corresponding PE instances because
+	 * we need the information afterwords. The attached EEH
+	 * devices are expected to be attached soon when calling
+	 * into pcibios_add_pci_devices().
+	 */
 	if (bus)
-		pcibios_remove_pci_devices(bus);
+		__pcibios_remove_pci_devices(bus, 0);
 
 	/* Reset the pci controller. (Asserts RST#; resets config space).
 	 * Reconfigure bridges and devices. Don't try to bring the system
diff --git a/arch/powerpc/platforms/pseries/eeh_pe.c b/arch/powerpc/platforms/pseries/eeh_pe.c
index 51fc56a..30b8d96 100644
--- a/arch/powerpc/platforms/pseries/eeh_pe.c
+++ b/arch/powerpc/platforms/pseries/eeh_pe.c
@@ -395,13 +395,14 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev)
 /**
  * eeh_rmv_from_parent_pe - Remove one EEH device from the associated PE
  * @edev: EEH device
+ * @purge_pe: remove PE or not
  *
  * The PE hierarchy tree might be changed when doing PCI hotplug.
  * Also, the PCI devices or buses could be removed from the system
  * during EEH recovery. So we have to call the function remove the
  * corresponding PE accordingly if necessary.
  */
-int eeh_rmv_from_parent_pe(struct eeh_dev *edev)
+int eeh_rmv_from_parent_pe(struct eeh_dev *edev, int purge_pe)
 {
 	struct eeh_pe *pe, *parent, *child;
 	int cnt;
@@ -428,19 +429,29 @@ int eeh_rmv_from_parent_pe(struct eeh_dev *edev)
 		if (pe->type & EEH_PE_PHB)
 			break;
 
-		if (list_empty(&pe->edevs)) {
-			cnt = 0;
-			list_for_each_entry(child, &pe->child_list, child) {
-				if (!(pe->type & EEH_PE_INVALID)) {
-					cnt++;
-					break;
-				}
+		if (purge_pe) {
+			if (list_empty(&pe->edevs) &&
+			    list_empty(&pe->child_list)) {
+				list_del(&pe->child);
+				kfree(pe);
+			} else {
+				break;
 			}
+		} else {
+			if (list_empty(&pe->edevs)) {
+				cnt = 0;
+				list_for_each_entry(child, &pe->child_list, child) {
+					if (!(pe->type & EEH_PE_INVALID)) {
+						cnt++;
+						break;
+					}
+				}
 
-			if (!cnt)
-				pe->type |= EEH_PE_INVALID;
-			else
-				break;
+				if (!cnt)
+					pe->type |= EEH_PE_INVALID;
+				else
+					break;
+			}
 		}
 
 		pe = parent;
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index 3ccebc8..261a577 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -65,27 +65,43 @@ pcibios_find_pci_bus(struct device_node *dn)
 EXPORT_SYMBOL_GPL(pcibios_find_pci_bus);
 
 /**
- * pcibios_remove_pci_devices - remove all devices under this bus
+ * __pcibios_remove_pci_devices - remove all devices under this bus
+ * @bus: the indicated PCI bus
+ * @purge_pe: destroy the PE on removal of PCI devices
  *
  * Remove all of the PCI devices under this bus both from the
  * linux pci device tree, and from the powerpc EEH address cache.
+ * By default, the corresponding PE will be destroied during the
+ * normal PCI hotplug path. For PCI hotplug during EEH recovery,
+ * the corresponding PE won't be destroied and deallocated.
  */
-void pcibios_remove_pci_devices(struct pci_bus *bus)
+void __pcibios_remove_pci_devices(struct pci_bus *bus, int purge_pe)
 {
- 	struct pci_dev *dev, *tmp;
+	struct pci_dev *dev, *tmp;
 	struct pci_bus *child_bus;
 
 	/* First go down child busses */
 	list_for_each_entry(child_bus, &bus->children, node)
-		pcibios_remove_pci_devices(child_bus);
+		__pcibios_remove_pci_devices(child_bus, purge_pe);
 
 	pr_debug("PCI: Removing devices on bus %04x:%02x\n",
-		 pci_domain_nr(bus),  bus->number);
+		pci_domain_nr(bus),  bus->number);
 	list_for_each_entry_safe(dev, tmp, &bus->devices, bus_list) {
 		pr_debug("     * Removing %s...\n", pci_name(dev));
-		eeh_remove_bus_device(dev);
- 		pci_stop_and_remove_bus_device(dev);
- 	}
+		eeh_remove_bus_device(dev, purge_pe);
+		pci_stop_and_remove_bus_device(dev);
+	}
+}
+
+/**
+ * pcibios_remove_pci_devices - remove all devices under this bus
+ *
+ * Remove all of the PCI devices under this bus both from the
+ * linux pci device tree, and from the powerpc EEH address cache.
+ */
+void pcibios_remove_pci_devices(struct pci_bus *bus)
+{
+	__pcibios_remove_pci_devices(bus, 1);
 }
 EXPORT_SYMBOL_GPL(pcibios_remove_pci_devices);