From 5c7a35e3e25232aef8d7aee484436f8cbe3b9b94 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Wed, 4 Jun 2014 17:31:52 +1000 Subject: [PATCH] powerpc/powernv: Fix killed EEH event On PowerNV platform, EEH errors are reported by IO accessors or poller driven by interrupt. After the PE is isolated, we won't produce EEH event for the PE. The current implementation has possibility of EEH event lost in this way: The interrupt handler queues one "special" event, which drives the poller. EEH thread doesn't pick the special event yet. IO accessors kicks in, the frozen PE is marked as "isolated" and EEH event is queued to the list. EEH thread runs because of special event and purge all existing EEH events. However, we never produce an other EEH event for the frozen PE. Eventually, the PE is marked as "isolated" and we don't have EEH event to recover it. The patch fixes the issue to keep EEH events for PEs that have been marked as "isolated" with the help of additional "force" help to eeh_remove_event(). Reported-by: Rolf Brudeseth Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/eeh_event.h | 2 +- arch/powerpc/kernel/eeh_driver.c | 4 ++-- arch/powerpc/kernel/eeh_event.c | 21 +++++++++++++++------ arch/powerpc/platforms/powernv/eeh-ioda.c | 2 +- 4 files changed, 19 insertions(+), 10 deletions(-) diff --git a/arch/powerpc/include/asm/eeh_event.h b/arch/powerpc/include/asm/eeh_event.h index 89d5670b2eeb..1e551a2d6f82 100644 --- a/arch/powerpc/include/asm/eeh_event.h +++ b/arch/powerpc/include/asm/eeh_event.h @@ -33,7 +33,7 @@ struct eeh_event { int eeh_event_init(void); int eeh_send_failure_event(struct eeh_pe *pe); -void eeh_remove_event(struct eeh_pe *pe); +void eeh_remove_event(struct eeh_pe *pe, bool force); void eeh_handle_event(struct eeh_pe *pe); #endif /* __KERNEL__ */ diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 8bb40e7cdeb6..420da61d4ce0 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -770,7 +770,7 @@ static void eeh_handle_special_event(void) eeh_serialize_lock(&flags); /* Purge all events */ - eeh_remove_event(NULL); + eeh_remove_event(NULL, true); list_for_each_entry(hose, &hose_list, list_node) { phb_pe = eeh_phb_pe_get(hose); @@ -789,7 +789,7 @@ static void eeh_handle_special_event(void) eeh_serialize_lock(&flags); /* Purge all events of the PHB */ - eeh_remove_event(pe); + eeh_remove_event(pe, true); if (rc == EEH_NEXT_ERR_DEAD_PHB) eeh_pe_state_mark(pe, EEH_PE_ISOLATED); diff --git a/arch/powerpc/kernel/eeh_event.c b/arch/powerpc/kernel/eeh_event.c index 72d748b56c86..4eefb6e34dbb 100644 --- a/arch/powerpc/kernel/eeh_event.c +++ b/arch/powerpc/kernel/eeh_event.c @@ -152,24 +152,33 @@ int eeh_send_failure_event(struct eeh_pe *pe) /** * eeh_remove_event - Remove EEH event from the queue * @pe: Event binding to the PE + * @force: Event will be removed unconditionally * * On PowerNV platform, we might have subsequent coming events * is part of the former one. For that case, those subsequent * coming events are totally duplicated and unnecessary, thus * they should be removed. */ -void eeh_remove_event(struct eeh_pe *pe) +void eeh_remove_event(struct eeh_pe *pe, bool force) { unsigned long flags; struct eeh_event *event, *tmp; + /* + * If we have NULL PE passed in, we have dead IOC + * or we're sure we can report all existing errors + * by the caller. + * + * With "force", the event with associated PE that + * have been isolated, the event won't be removed + * to avoid event lost. + */ spin_lock_irqsave(&eeh_eventlist_lock, flags); list_for_each_entry_safe(event, tmp, &eeh_eventlist, list) { - /* - * If we don't have valid PE passed in, that means - * we already have event corresponding to dead IOC - * and all events should be purged. - */ + if (!force && event->pe && + (event->pe->state & EEH_PE_ISOLATED)) + continue; + if (!pe) { list_del(&event->list); kfree(event); diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c index 5711f6f1fda6..9c002099f875 100644 --- a/arch/powerpc/platforms/powernv/eeh-ioda.c +++ b/arch/powerpc/platforms/powernv/eeh-ioda.c @@ -717,7 +717,7 @@ static int ioda_eeh_next_error(struct eeh_pe **pe) * And we should keep the cached OPAL notifier event sychronized * between the kernel and firmware. */ - eeh_remove_event(NULL); + eeh_remove_event(NULL, false); opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul); list_for_each_entry(hose, &hose_list, list_node) { -- 2.20.1