From c700f013adb0ec57518a7fe0163e3117659ce249 Mon Sep 17 00:00:00 2001 From: "Chen, Gong" Date: Fri, 6 Dec 2013 01:17:08 -0500 Subject: EDAC: Add an edac_report parameter to EDAC This new parameter is used to control how to report HW error reporting, especially for newer Intel platform, like Ivybridge-EX, which contains an enhanced error decoding functionality in the firmware, i.e. eMCA. Signed-off-by: Chen, Gong Acked-by: Tony Luck Link: http://lkml.kernel.org/r/1386310630-12529-2-git-send-email-gong.chen@linux.intel.com [ Boris: massage commit message. ] Signed-off-by: Borislav Petkov --- drivers/edac/edac_stub.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'drivers') diff --git a/drivers/edac/edac_stub.c b/drivers/edac/edac_stub.c index 351945fa2ecd..9d9e18aefaaa 100644 --- a/drivers/edac/edac_stub.c +++ b/drivers/edac/edac_stub.c @@ -29,6 +29,25 @@ EXPORT_SYMBOL_GPL(edac_err_assert); static atomic_t edac_subsys_valid = ATOMIC_INIT(0); +int edac_report_status = EDAC_REPORTING_ENABLED; +EXPORT_SYMBOL_GPL(edac_report_status); + +static int __init edac_report_setup(char *str) +{ + if (!str) + return -EINVAL; + + if (!strncmp(str, "on", 2)) + set_edac_report_status(EDAC_REPORTING_ENABLED); + else if (!strncmp(str, "off", 3)) + set_edac_report_status(EDAC_REPORTING_DISABLED); + else if (!strncmp(str, "force", 5)) + set_edac_report_status(EDAC_REPORTING_FORCE); + + return 0; +} +__setup("edac_report=", edac_report_setup); + /* * called to determine if there is an EDAC driver interested in * knowing an event (such as NMI) occurred -- cgit v1.2.3 From fd521039666529a4674b9822f1cc873672f57ee6 Mon Sep 17 00:00:00 2001 From: "Chen, Gong" Date: Fri, 6 Dec 2013 01:17:09 -0500 Subject: EDAC, sb_edac: Modify H/W event reporting policy Newer Intel platforms support more than one method to report H/W event. On this kind of platform, H/W event report can adopt new method and traditional EDAC method should be disabled. Moreover, if EDAC event report method is set to *force*, it means event must be reported via EDAC interface. IOW, it overrides the default event report policy. Signed-off-by: Chen, Gong Acked-by: Tony Luck Link: http://lkml.kernel.org/r/1386310630-12529-3-git-send-email-gong.chen@linux.intel.com [ Boris: massage commit and error messages ] Signed-off-by: Borislav Petkov --- drivers/edac/sb_edac.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index 8472405c5586..e2e2cb365764 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -1829,6 +1829,9 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val, struct mem_ctl_info *mci; struct sbridge_pvt *pvt; + if (get_edac_report_status() == EDAC_REPORTING_DISABLED) + return NOTIFY_DONE; + mci = get_mci_for_node_id(mce->socketid); if (!mci) return NOTIFY_BAD; @@ -2142,9 +2145,10 @@ static int __init sbridge_init(void) opstate_init(); pci_rc = pci_register_driver(&sbridge_driver); - if (pci_rc >= 0) { mce_register_decode_chain(&sbridge_mce_dec); + if (get_edac_report_status() == EDAC_REPORTING_DISABLED) + sbridge_printk(KERN_WARNING, "Loading driver, error reporting disabled.\n"); return 0; } -- cgit v1.2.3 From 42139eb356e3384759ca143ae04d82376346eb4c Mon Sep 17 00:00:00 2001 From: "Chen, Gong" Date: Fri, 6 Dec 2013 01:17:10 -0500 Subject: ACPI, eMCA: Combine eMCA/EDAC event reporting priority eMCA has higher H/W event reporting priority. Once it is loaded, EDAC event reporting should be disabled, unless EDAC overrides eMCA priority via command line parameter "edac_report=force". Signed-off-by: Chen, Gong Acked-by: Tony Luck Link: http://lkml.kernel.org/r/1386310630-12529-4-git-send-email-gong.chen@linux.intel.com [ Boris: massage printk message. ] Signed-off-by: Borislav Petkov --- drivers/acpi/acpi_extlog.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) (limited to 'drivers') diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c index a6869e110ce5..5d33c5415405 100644 --- a/drivers/acpi/acpi_extlog.c +++ b/drivers/acpi/acpi_extlog.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include @@ -43,6 +44,8 @@ struct extlog_l1_head { u8 rev1[12]; }; +static int old_edac_report_status; + static u8 extlog_dsm_uuid[] = "663E35AF-CC10-41A4-88EA-5470AF055295"; /* L1 table related physical address */ @@ -150,7 +153,7 @@ static int extlog_print(struct notifier_block *nb, unsigned long val, rc = print_extlog_rcd(NULL, (struct acpi_generic_status *)elog_buf, cpu); - return NOTIFY_DONE; + return NOTIFY_STOP; } static int extlog_get_dsm(acpi_handle handle, int rev, int func, u64 *ret) @@ -231,8 +234,12 @@ static int __init extlog_init(void) u64 cap; int rc; - rc = -ENODEV; + if (get_edac_report_status() == EDAC_REPORTING_FORCE) { + pr_warn("Not loading eMCA, error reporting force-enabled through EDAC.\n"); + return -EPERM; + } + rc = -ENODEV; rdmsrl(MSR_IA32_MCG_CAP, cap); if (!(cap & MCG_ELOG_P)) return rc; @@ -287,6 +294,12 @@ static int __init extlog_init(void) if (elog_buf == NULL) goto err_release_elog; + /* + * eMCA event report method has higher priority than EDAC method, + * unless EDAC event report method is mandatory. + */ + old_edac_report_status = get_edac_report_status(); + set_edac_report_status(EDAC_REPORTING_DISABLED); mce_register_decode_chain(&extlog_mce_dec); /* enable OS to be involved to take over management from BIOS */ ((struct extlog_l1_head *)extlog_l1_addr)->flags |= FLAG_OS_OPTIN; @@ -308,6 +321,7 @@ err: static void __exit extlog_exit(void) { + set_edac_report_status(old_edac_report_status); mce_unregister_decode_chain(&extlog_mce_dec); ((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN; if (extlog_l1_addr) -- cgit v1.2.3