From 7cb9d93dc6d4f717218b6fa791be9bcf4e417379 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Thu, 20 Jun 2013 18:13:24 +0800 Subject: [PATCH] powerpc/eeh: Register OPAL notifier for PCI error The patch registers OPAL event notifier and process the PCI errors from firmware. If we have pending PCI errors, special EEH event (without binding PE) will be sent to EEH core for processing. Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/eeh-ioda.c | 41 ++++++++++++++++++++++++++++++- 1 file changed, 40 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c index a3eebd1..2b7689e 100644 --- a/arch/powerpc/platforms/powernv/eeh-ioda.c +++ b/arch/powerpc/platforms/powernv/eeh-ioda.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -42,6 +43,26 @@ #endif static char *hub_diag = NULL; +static int ioda_eeh_nb_init = 0; + +static int ioda_eeh_event(struct notifier_block *nb, + unsigned long events, void *change) +{ + uint64_t changed_evts = (uint64_t)change; + + /* We simply send special EEH event */ + if ((changed_evts & OPAL_EVENT_PCI_ERROR) && + (events & OPAL_EVENT_PCI_ERROR)) + eeh_send_failure_event(NULL); + + return 0; +} + +static struct notifier_block ioda_eeh_nb = { + .notifier_call = ioda_eeh_event, + .next = NULL, + .priority = 0 +}; /** * ioda_eeh_post_init - Chip dependent post initialization @@ -54,6 +75,19 @@ static char *hub_diag = NULL; static int ioda_eeh_post_init(struct pci_controller *hose) { struct pnv_phb *phb = hose->private_data; + int ret; + + /* Register OPAL event notifier */ + if (!ioda_eeh_nb_init) { + ret = opal_notifier_register(&ioda_eeh_nb); + if (ret) { + pr_err("%s: Can't register OPAL event notifier (%d)\n", + __func__, ret); + return ret; + } + + ioda_eeh_nb_init = 1; + } /* FIXME: Enable it for PHB3 later */ if (phb->type == PNV_PHB_IODA1) { @@ -736,8 +770,13 @@ static int ioda_eeh_next_error(struct eeh_pe **pe) long rc; int ret = 1; - /* While running here, it's safe to purge the event queue */ + /* + * While running here, it's safe to purge the event queue. + * And we should keep the cached OPAL notifier event sychronized + * between the kernel and firmware. + */ eeh_remove_event(NULL); + opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul); list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { /* -- 2.7.4