diff options
author | Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> | 2013-07-10 14:57:01 +0530 |
---|---|---|
committer | Tony Luck <tony.luck@intel.com> | 2013-07-10 11:35:02 -0700 |
commit | cf870c70a194443f8fc654ddc9d6cfd02c58003b (patch) | |
tree | 73553a1960478b454dbcb99c0db0c8acf381e58b /drivers/acpi/apei/ghes.c | |
parent | 9ad95879cd1b22ed016c804f8d686ff83a41a9d4 (diff) | |
download | linux-cf870c70a194443f8fc654ddc9d6cfd02c58003b.tar.bz2 |
mce: acpi/apei: Soft-offline a page on firmware GHES notification
If the firmware indicates in GHES error data entry that the error threshold
has exceeded for a corrected error event, then we try to soft-offline the
page. This could be called in interrupt context, so we queue this up similar
to how we handle memory failure scenarios.
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Diffstat (limited to 'drivers/acpi/apei/ghes.c')
-rw-r--r-- | drivers/acpi/apei/ghes.c | 38 |
1 files changed, 29 insertions, 9 deletions
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index fcd7d91cec34..a8f362acc8ec 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -409,6 +409,34 @@ static void ghes_clear_estatus(struct ghes *ghes) ghes->flags &= ~GHES_TO_CLEAR; } +static void ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, int sev) +{ +#ifdef CONFIG_ACPI_APEI_MEMORY_FAILURE + unsigned long pfn; + int sec_sev = ghes_severity(gdata->error_severity); + struct cper_sec_mem_err *mem_err; + mem_err = (struct cper_sec_mem_err *)(gdata + 1); + + if (sec_sev == GHES_SEV_CORRECTED && + (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED) && + (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS)) { + pfn = mem_err->physical_addr >> PAGE_SHIFT; + if (pfn_valid(pfn)) + memory_failure_queue(pfn, 0, MF_SOFT_OFFLINE); + else if (printk_ratelimit()) + pr_warn(FW_WARN GHES_PFX + "Invalid address in generic error data: %#llx\n", + mem_err->physical_addr); + } + if (sev == GHES_SEV_RECOVERABLE && + sec_sev == GHES_SEV_RECOVERABLE && + mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) { + pfn = mem_err->physical_addr >> PAGE_SHIFT; + memory_failure_queue(pfn, 0, 0); + } +#endif +} + static void ghes_do_proc(struct ghes *ghes, const struct acpi_hest_generic_status *estatus) { @@ -428,15 +456,7 @@ static void ghes_do_proc(struct ghes *ghes, apei_mce_report_mem_error(sev == GHES_SEV_CORRECTED, mem_err); #endif -#ifdef CONFIG_ACPI_APEI_MEMORY_FAILURE - if (sev == GHES_SEV_RECOVERABLE && - sec_sev == GHES_SEV_RECOVERABLE && - mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) { - unsigned long pfn; - pfn = mem_err->physical_addr >> PAGE_SHIFT; - memory_failure_queue(pfn, 0, 0); - } -#endif + ghes_handle_memory_failure(gdata, sev); } #ifdef CONFIG_ACPI_APEI_PCIEAER else if (!uuid_le_cmp(*(uuid_le *)gdata->section_type, |