powerpc/eeh: Fix invalid cached PE primary bus

The PE primary bus cannot be got from its child devices when having
full hotplug in error recovery. The PE primary bus is cached, which
is done in commit <05ba75f84864> ("powerpc/eeh: Fix stale cached primary
bus"). In eeh_reset_device(), the flag (EEH_PE_PRI_BUS) is cleared
before the PCI hot remove. eeh_pe_bus_get() then returns NULL as the
PE primary bus in pnv_eeh_reset() and it crashes the kernel eventually.

This fixes the issue by clearing the flag (EEH_PE_PRI_BUS) before the
PCI hot add. With it, the PowerNV EEH reset backend (pnv_eeh_reset())
can get valid PE primary bus through eeh_pe_bus_get().

Fixes: 67086e32b564 ("powerpc/eeh: powerpc/eeh: Support error recovery for VF PE")
Reported-by: Pridhiviraj Paidipeddi <ppaiddipe@in.ibm.com>
Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 2714a3b81d24476ad07d651c64720f42ab96bcec..b5f73cb5eeb6e34b43fd75d5054f867128e792f7 100644 (file)
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -642,7 +642,6 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
                if (pe->type & EEH_PE_VF) {
                        eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL);
                } else {
-                       eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
                        pci_lock_rescan_remove();
                        pci_hp_remove_devices(bus);
                        pci_unlock_rescan_remove();
@@ -692,10 +691,12 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
                 */
                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)
+               if (pe->type & EEH_PE_VF) {
                        eeh_add_virt_device(edev, NULL);
-               else
+               } else {
+                       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);