diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index fab7743c2640d565d5689f1cff06aa3dddbe0aa9..9537d83b83203a358a9229f77de03a774c438272 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -25,6 +25,7 @@ #include #include #include +#include struct pci_dev; struct pci_bus; @@ -84,6 +85,7 @@ struct eeh_pe { int freeze_count; /* Times of froze up */ struct timeval tstamp; /* Time on first-time freeze */ int false_positives; /* Times of reported #ff's */ + atomic_t pass_dev_cnt; /* Count of passed through devs */ struct eeh_pe *parent; /* Parent PE */ struct list_head child_list; /* Link PE to the child list */ struct list_head edevs; /* Link list of EEH devices */ @@ -93,6 +95,11 @@ struct eeh_pe { #define eeh_pe_for_each_dev(pe, edev, tmp) \ list_for_each_entry_safe(edev, tmp, &pe->edevs, list) +static inline bool eeh_pe_passed(struct eeh_pe *pe) +{ + return pe ? !!atomic_read(&pe->pass_dev_cnt) : false; +} + /* * The struct is used to trace EEH state for the associated * PCI device node or PCI device. In future, it might diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 86e25702aaca8894701ff585b87ee08caa017199..c8f1a9d2a67b2e9c1a0e42a21cc40bc572825ffd 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -400,6 +400,14 @@ int eeh_dev_check_failure(struct eeh_dev *edev) if (ret > 0) return ret; + /* + * If the PE isn't owned by us, we shouldn't check the + * state. Instead, let the owner handle it if the PE has + * been frozen. + */ + if (eeh_pe_passed(pe)) + return 0; + /* If we already have a pending isolation event for this * slot, we know it's bad already, we don't need to check. * Do this checking under a lock; as multiple PCI devices diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c index 8ad0c5b891f4e3083e3b554b980f0eae54a51ab7..f6abdb11ee84fb073ee14ff7f09663362cb77594 100644 --- a/arch/powerpc/platforms/powernv/eeh-ioda.c +++ b/arch/powerpc/platforms/powernv/eeh-ioda.c @@ -812,7 +812,8 @@ static int ioda_eeh_next_error(struct eeh_pe **pe) opal_pci_eeh_freeze_clear(phb->opal_id, frozen_pe_no, OPAL_EEH_ACTION_CLEAR_FREEZE_ALL); ret = EEH_NEXT_ERR_NONE; - } else if ((*pe)->state & EEH_PE_ISOLATED) { + } else if ((*pe)->state & EEH_PE_ISOLATED || + eeh_pe_passed(*pe)) { ret = EEH_NEXT_ERR_NONE; } else { pr_err("EEH: Frozen PE#%x on PHB#%x detected\n",