^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1) // SPDX-License-Identifier: GPL-2.0-only
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 3) * NFIT - Machine Check Handler
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 4) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 5) * Copyright(c) 2013-2016 Intel Corporation. All rights reserved.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 6) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 7) #include <linux/notifier.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 8) #include <linux/acpi.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 9) #include <linux/nd.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 10) #include <asm/mce.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 11) #include "nfit.h"
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 12)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 13) static int nfit_handle_mce(struct notifier_block *nb, unsigned long val,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 14) void *data)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 15) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 16) struct mce *mce = (struct mce *)data;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 17) struct acpi_nfit_desc *acpi_desc;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 18) struct nfit_spa *nfit_spa;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 19)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 20) /* We only care about uncorrectable memory errors */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 21) if (!mce_is_memory_error(mce) || mce_is_correctable(mce))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 22) return NOTIFY_DONE;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 23)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 24) /* Verify the address reported in the MCE is valid. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 25) if (!mce_usable_address(mce))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 26) return NOTIFY_DONE;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 27)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 28) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 29) * mce->addr contains the physical addr accessed that caused the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 30) * machine check. We need to walk through the list of NFITs, and see
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 31) * if any of them matches that address, and only then start a scrub.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 32) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 33) mutex_lock(&acpi_desc_lock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 34) list_for_each_entry(acpi_desc, &acpi_descs, list) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 35) struct device *dev = acpi_desc->dev;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 36) int found_match = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 37)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 38) mutex_lock(&acpi_desc->init_mutex);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 39) list_for_each_entry(nfit_spa, &acpi_desc->spas, list) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 40) struct acpi_nfit_system_address *spa = nfit_spa->spa;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 41)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 42) if (nfit_spa_type(spa) != NFIT_SPA_PM)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 43) continue;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 44) /* find the spa that covers the mce addr */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 45) if (spa->address > mce->addr)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 46) continue;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 47) if ((spa->address + spa->length - 1) < mce->addr)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 48) continue;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 49) found_match = 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 50) dev_dbg(dev, "addr in SPA %d (0x%llx, 0x%llx)\n",
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 51) spa->range_index, spa->address, spa->length);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 52) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 53) * We can break at the first match because we're going
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 54) * to rescan all the SPA ranges. There shouldn't be any
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 55) * aliasing anyway.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 56) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 57) break;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 58) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 59) mutex_unlock(&acpi_desc->init_mutex);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 60)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 61) if (!found_match)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 62) continue;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 63)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 64) /* If this fails due to an -ENOMEM, there is little we can do */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 65) nvdimm_bus_add_badrange(acpi_desc->nvdimm_bus,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 66) ALIGN(mce->addr, L1_CACHE_BYTES),
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 67) L1_CACHE_BYTES);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 68) nvdimm_region_notify(nfit_spa->nd_region,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 69) NVDIMM_REVALIDATE_POISON);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 70)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 71) if (acpi_desc->scrub_mode == HW_ERROR_SCRUB_ON) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 72) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 73) * We can ignore an -EBUSY here because if an ARS is
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 74) * already in progress, just let that be the last
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 75) * authoritative one
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 76) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 77) acpi_nfit_ars_rescan(acpi_desc, 0);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 78) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 79) mce->kflags |= MCE_HANDLED_NFIT;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 80) break;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 81) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 82)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 83) mutex_unlock(&acpi_desc_lock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 84) return NOTIFY_DONE;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 85) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 86)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 87) static struct notifier_block nfit_mce_dec = {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 88) .notifier_call = nfit_handle_mce,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 89) .priority = MCE_PRIO_NFIT,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 90) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 91)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 92) void nfit_mce_register(void)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 93) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 94) mce_register_decode_chain(&nfit_mce_dec);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 95) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 96)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 97) void nfit_mce_unregister(void)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 98) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 99) mce_unregister_decode_chain(&nfit_mce_dec);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 100) }