powerpc/eeh: Fix stale cached primary bus

When PE is created, its primary bus is cached to pe->bus. At later
point, the cached primary bus is returned from eeh_pe_bus_get().
However, we could get stale cached primary bus and run into kernel
crash in one case: full hotplug as part of fenced PHB error recovery
releases all PCI busses under the PHB at unplugging time and recreate
them at plugging time. pe->bus is still dereferencing the PCI bus
that was released.

This adds another PE flag (EEH_PE_PRI_BUS) to represent the validity
of pe->bus. pe->bus is updated when its first child EEH device is
online and the flag is set. Before unplugging in full hotplug for
error recovery, the flag is cleared.

Fixes: 8cdb2833 ("powerpc/eeh: Trace PCI bus from PE")
Cc: stable@vger.kernel.org #v3.11+
Reported-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
Reported-by: Pradipta Ghosh <pradghos@in.ibm.com>
Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Tested-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index c5eb86f3d452fbe66d44ae1cce9bbfff91a8b14d..867c39b45df6ce4c1bd5a342ca314a888bb185bf 100644 (file)
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -81,6 +81,7 @@ struct pci_dn;
 #define EEH_PE_KEEP            (1 << 8)        /* Keep PE on hotplug   */
 #define EEH_PE_CFG_RESTRICTED  (1 << 9)        /* Block config on error */
 #define EEH_PE_REMOVED         (1 << 10)       /* Removed permanently  */
+#define EEH_PE_PRI_BUS         (1 << 11)       /* Cached primary bus   */
 
 struct eeh_pe {
        int type;                       /* PE type: PHB/Bus/Device      */

diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 8d14feb40f121129854a7760818e926f7b5b742c..f69ecaa7ce338a0cc2d31ae5555024c5f8257083 100644 (file)
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -564,6 +564,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
         */
        eeh_pe_state_mark(pe, EEH_PE_KEEP);
        if (bus) {
+               eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
                pci_lock_rescan_remove();
                pcibios_remove_pci_devices(bus);
                pci_unlock_rescan_remove();
@@ -803,6 +804,7 @@ perm_error:
         * the their PCI config any more.
         */
        if (frozen_bus) {
+               eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
                eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
 
                pci_lock_rescan_remove();
@@ -886,6 +888,7 @@ static void eeh_handle_special_event(void)
                                        continue;
 
                                /* Notify all devices to be down */
+                               eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
                                bus = eeh_pe_bus_get(phb_pe);
                                eeh_pe_dev_traverse(pe,
                                        eeh_report_failure, NULL);

diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index ca9e5371930ea7ca272913b931e0a5c6ffc8b656..98f81800e00c1030b69c80d79eb8d43edbda9728 100644 (file)
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -928,7 +928,7 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe)
                bus = pe->phb->bus;
        } else if (pe->type & EEH_PE_BUS ||
                   pe->type & EEH_PE_DEVICE) {
-               if (pe->bus) {
+               if (pe->state & EEH_PE_PRI_BUS) {
                        bus = pe->bus;
                        goto out;
                }

diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 5f152b95ca0c8493536d787a51d741ae628adb8a..87f47e55aab65ac234df1d67c926ca17b1517f06 100644 (file)
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -444,9 +444,12 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data)
         * PCI devices of the PE are expected to be removed prior
         * to PE reset.
         */
-       if (!edev->pe->bus)
+       if (!(edev->pe->state & EEH_PE_PRI_BUS)) {
                edev->pe->bus = pci_find_bus(hose->global_number,
                                             pdn->busno);
+               if (edev->pe->bus)
+                       edev->pe->state |= EEH_PE_PRI_BUS;
+       }
 
        /*
         * Enable EEH explicitly so that we will do EEH check