powerpc/eeh: Use partial hotplug for EEH unaware drivers

When EEH error happens to one specific PE, some devices with drivers
supporting EEH won't except hotplug on the device. However, there
might have other deivces without driver, or with driver without EEH
support. For the case, we need do partial hotplug in order to make
sure that the PE becomes absolutely quite during reset. Otherise,
the PE reset might fail and leads to failure of error recovery.

The current code doesn't handle that 'mixed' case properly, it either
uses the error callbacks to the drivers, or tries hotplug, but doesn't
handle a PE (EEH domain) composed of a combination of the two.

The patch intends to support so-called "partial" hotplug for EEH:
Before we do reset, we stop and remove those PCI devices without
EEH sensitive driver. The corresponding EEH devices are not detached
from its PE, but with special flag. After the reset is done, those
EEH devices with the special flag will be scanned one by one.

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

1 files changed, 7 insertions, 13 deletions

diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index c8b815e45c8f..2aa955ae01a1 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -149,8 +149,8 @@ static struct eeh_pe *eeh_pe_next(struct eeh_pe *pe,
  * callback returns something other than NULL, or no more PEs
  * to be traversed.
  */
-static void *eeh_pe_traverse(struct eeh_pe *root,
-			eeh_traverse_func fn, void *flag)
+void *eeh_pe_traverse(struct eeh_pe *root,
+		      eeh_traverse_func fn, void *flag)
 {
 	struct eeh_pe *pe;
 	void *ret;
@@ -409,8 +409,8 @@ int eeh_rmv_from_parent_pe(struct eeh_dev *edev)
 	int cnt;
 
 	if (!edev->pe) {
-		pr_warning("%s: No PE found for EEH device %s\n",
-			__func__, edev->dn->full_name);
+		pr_debug("%s: No PE found for EEH device %s\n",
+			 __func__, edev->dn->full_name);
 		return -EEXIST;
 	}
 
@@ -728,18 +728,12 @@ static void eeh_restore_device_bars(struct eeh_dev *edev,
  */
 static void *eeh_restore_one_device_bars(void *data, void *flag)
 {
-	struct pci_dev *pdev = NULL;
 	struct eeh_dev *edev = (struct eeh_dev *)data;
+	struct pci_dev *pdev = eeh_dev_to_pci_dev(edev);
 	struct device_node *dn = eeh_dev_to_of_node(edev);
 
-	/* Trace the PCI bridge */
-	if (eeh_probe_mode_dev()) {
-		pdev = eeh_dev_to_pci_dev(edev);
-		if (pdev->hdr_type != PCI_HEADER_TYPE_BRIDGE)
-                        pdev = NULL;
-        }
-
-	if (pdev)
+	/* Do special restore for bridges */
+	if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
 		eeh_restore_bridge_bars(pdev, edev, dn);
 	else
 		eeh_restore_device_bars(edev, dn);