static int pnv_eeh_next_error()

in platforms/powernv/eeh-powernv.c [1406:1601]


static int pnv_eeh_next_error(struct eeh_pe **pe)
{
	struct pci_controller *hose;
	struct pnv_phb *phb;
	struct eeh_pe *phb_pe, *parent_pe;
	__be64 frozen_pe_no;
	__be16 err_type, severity;
	long rc;
	int state, ret = EEH_NEXT_ERR_NONE;

	/*
	 * While running here, it's safe to purge the event queue. The
	 * event should still be masked.
	 */
	eeh_remove_event(NULL, false);

	list_for_each_entry(hose, &hose_list, list_node) {
		/*
		 * If the subordinate PCI buses of the PHB has been
		 * removed or is exactly under error recovery, we
		 * needn't take care of it any more.
		 */
		phb = hose->private_data;
		phb_pe = eeh_phb_pe_get(hose);
		if (!phb_pe || (phb_pe->state & EEH_PE_ISOLATED))
			continue;

		rc = opal_pci_next_error(phb->opal_id,
					 &frozen_pe_no, &err_type, &severity);
		if (rc != OPAL_SUCCESS) {
			pr_devel("%s: Invalid return value on "
				 "PHB#%x (0x%lx) from opal_pci_next_error",
				 __func__, hose->global_number, rc);
			continue;
		}

		/* If the PHB doesn't have error, stop processing */
		if (be16_to_cpu(err_type) == OPAL_EEH_NO_ERROR ||
		    be16_to_cpu(severity) == OPAL_EEH_SEV_NO_ERROR) {
			pr_devel("%s: No error found on PHB#%x\n",
				 __func__, hose->global_number);
			continue;
		}

		/*
		 * Processing the error. We're expecting the error with
		 * highest priority reported upon multiple errors on the
		 * specific PHB.
		 */
		pr_devel("%s: Error (%d, %d, %llu) on PHB#%x\n",
			__func__, be16_to_cpu(err_type),
			be16_to_cpu(severity), be64_to_cpu(frozen_pe_no),
			hose->global_number);
		switch (be16_to_cpu(err_type)) {
		case OPAL_EEH_IOC_ERROR:
			if (be16_to_cpu(severity) == OPAL_EEH_SEV_IOC_DEAD) {
				pr_err("EEH: dead IOC detected\n");
				ret = EEH_NEXT_ERR_DEAD_IOC;
			} else if (be16_to_cpu(severity) == OPAL_EEH_SEV_INF) {
				pr_info("EEH: IOC informative error "
					"detected\n");
				pnv_eeh_get_and_dump_hub_diag(hose);
				ret = EEH_NEXT_ERR_NONE;
			}

			break;
		case OPAL_EEH_PHB_ERROR:
			if (be16_to_cpu(severity) == OPAL_EEH_SEV_PHB_DEAD) {
				*pe = phb_pe;
				pr_err("EEH: dead PHB#%x detected, "
				       "location: %s\n",
					hose->global_number,
					eeh_pe_loc_get(phb_pe));
				ret = EEH_NEXT_ERR_DEAD_PHB;
			} else if (be16_to_cpu(severity) ==
				   OPAL_EEH_SEV_PHB_FENCED) {
				*pe = phb_pe;
				pr_err("EEH: Fenced PHB#%x detected, "
				       "location: %s\n",
					hose->global_number,
					eeh_pe_loc_get(phb_pe));
				ret = EEH_NEXT_ERR_FENCED_PHB;
			} else if (be16_to_cpu(severity) == OPAL_EEH_SEV_INF) {
				pr_info("EEH: PHB#%x informative error "
					"detected, location: %s\n",
					hose->global_number,
					eeh_pe_loc_get(phb_pe));
				pnv_eeh_get_phb_diag(phb_pe);
				pnv_pci_dump_phb_diag_data(hose, phb_pe->data);
				ret = EEH_NEXT_ERR_NONE;
			}

			break;
		case OPAL_EEH_PE_ERROR:
			/*
			 * If we can't find the corresponding PE, we
			 * just try to unfreeze.
			 */
			if (pnv_eeh_get_pe(hose,
				be64_to_cpu(frozen_pe_no), pe)) {
				pr_info("EEH: Clear non-existing PHB#%x-PE#%llx\n",
					hose->global_number, be64_to_cpu(frozen_pe_no));
				pr_info("EEH: PHB location: %s\n",
					eeh_pe_loc_get(phb_pe));

				/* Dump PHB diag-data */
				rc = opal_pci_get_phb_diag_data2(phb->opal_id,
					phb->diag_data, phb->diag_data_size);
				if (rc == OPAL_SUCCESS)
					pnv_pci_dump_phb_diag_data(hose,
							phb->diag_data);

				/* Try best to clear it */
				opal_pci_eeh_freeze_clear(phb->opal_id,
					be64_to_cpu(frozen_pe_no),
					OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
				ret = EEH_NEXT_ERR_NONE;
			} 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",
				       (*pe)->addr,
					(*pe)->phb->global_number);
				pr_err("EEH: PE location: %s, "
				       "PHB location: %s\n",
				       eeh_pe_loc_get(*pe),
				       eeh_pe_loc_get(phb_pe));
				ret = EEH_NEXT_ERR_FROZEN_PE;
			}

			break;
		default:
			pr_warn("%s: Unexpected error type %d\n",
				__func__, be16_to_cpu(err_type));
		}

		/*
		 * EEH core will try recover from fenced PHB or
		 * frozen PE. In the time for frozen PE, EEH core
		 * enable IO path for that before collecting logs,
		 * but it ruins the site. So we have to dump the
		 * log in advance here.
		 */
		if ((ret == EEH_NEXT_ERR_FROZEN_PE  ||
		    ret == EEH_NEXT_ERR_FENCED_PHB) &&
		    !((*pe)->state & EEH_PE_ISOLATED)) {
			eeh_pe_mark_isolated(*pe);
			pnv_eeh_get_phb_diag(*pe);

			if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
				pnv_pci_dump_phb_diag_data((*pe)->phb,
							   (*pe)->data);
		}

		/*
		 * We probably have the frozen parent PE out there and
		 * we need have to handle frozen parent PE firstly.
		 */
		if (ret == EEH_NEXT_ERR_FROZEN_PE) {
			parent_pe = (*pe)->parent;
			while (parent_pe) {
				/* Hit the ceiling ? */
				if (parent_pe->type & EEH_PE_PHB)
					break;

				/* Frozen parent PE ? */
				state = eeh_ops->get_state(parent_pe, NULL);
				if (state > 0 && !eeh_state_active(state))
					*pe = parent_pe;

				/* Next parent level */
				parent_pe = parent_pe->parent;
			}

			/* We possibly migrate to another PE */
			eeh_pe_mark_isolated(*pe);
		}

		/*
		 * If we have no errors on the specific PHB or only
		 * informative error there, we continue poking it.
		 * Otherwise, we need actions to be taken by upper
		 * layer.
		 */
		if (ret > EEH_NEXT_ERR_INF)
			break;
	}

	/* Unmask the event */
	if (ret == EEH_NEXT_ERR_NONE && eeh_enabled())
		enable_irq(eeh_event_irq);

	return ret;
}