These changes are a raw update to a vanilla kernel 4.1.10, with the

[kvmfornfv.git] / kernel / arch / powerpc / kernel / eeh.c

diff --git a/kernel/arch/powerpc/kernel/eeh.c b/kernel/arch/powerpc/kernel/eeh.c
index 9ee61d1..cb565ad 100644 (file)
--- a/kernel/arch/powerpc/kernel/eeh.c
+++ b/kernel/arch/powerpc/kernel/eeh.c
@@ -310,11 +310,26 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity)
        if (!(pe->type & EEH_PE_PHB)) {
                if (eeh_has_flag(EEH_ENABLE_IO_FOR_LOG))
                        eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
+
+               /*
+                * The config space of some PCI devices can't be accessed
+                * when their PEs are in frozen state. Otherwise, fenced
+                * PHB might be seen. Those PEs are identified with flag
+                * EEH_PE_CFG_RESTRICTED, indicating EEH_PE_CFG_BLOCKED
+                * is set automatically when the PE is put to EEH_PE_ISOLATED.
+                *
+                * Restoring BARs possibly triggers PCI config access in
+                * (OPAL) firmware and then causes fenced PHB. If the
+                * PCI config is blocked with flag EEH_PE_CFG_BLOCKED, it's
+                * pointless to restore BARs and dump config space.
+                */
                eeh_ops->configure_bridge(pe);
-               eeh_pe_restore_bars(pe);
+               if (!(pe->state & EEH_PE_CFG_BLOCKED)) {
+                       eeh_pe_restore_bars(pe);
 
-               pci_regs_buf[0] = 0;
-               eeh_pe_traverse(pe, eeh_dump_pe_log, &loglen);
+                       pci_regs_buf[0] = 0;
+                       eeh_pe_traverse(pe, eeh_dump_pe_log, &loglen);
+               }
        }
 
        eeh_ops->get_log(pe, severity, pci_regs_buf, loglen);
@@ -1118,9 +1133,6 @@ void eeh_add_device_late(struct pci_dev *dev)
                return;
        }
 
-       if (eeh_has_flag(EEH_PROBE_MODE_DEV))
-               eeh_ops->probe(pdn, NULL);
-
        /*
         * The EEH cache might not be removed correctly because of
         * unbalanced kref to the device during unplug time, which
@@ -1144,6 +1156,9 @@ void eeh_add_device_late(struct pci_dev *dev)
                dev->dev.archdata.edev = NULL;
        }
 
+       if (eeh_has_flag(EEH_PROBE_MODE_DEV))
+               eeh_ops->probe(pdn, NULL);
+
        edev->pdev = dev;
        dev->dev.archdata.edev = edev;