Commit cf870c70 authored by Naveen N. Rao's avatar Naveen N. Rao Committed by Tony Luck
Browse files

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: default avatarNaveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: default avatarBorislav Petkov <bp@suse.de>
Signed-off-by: default avatarTony Luck <tony.luck@intel.com>
parent 9ad95879

drivers/acpi/apei/ghes.c

+29 −9
Original line number Diff line number Diff line
@@ -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,

include/linux/mm.h

+1 −0
Original line number Diff line number Diff line
@@ -1784,6 +1784,7 @@ enum mf_flags { 
	MF_COUNT_INCREASED = 1 << 0,

	MF_ACTION_REQUIRED = 1 << 1,

	MF_MUST_KILL = 1 << 2,

	MF_SOFT_OFFLINE = 1 << 3,

};

extern int memory_failure(unsigned long pfn, int trapno, int flags);

extern void memory_failure_queue(unsigned long pfn, int trapno, int flags);

mm/memory-failure.c

+4 −1
Original line number Diff line number Diff line
@@ -1286,6 +1286,9 @@ static void memory_failure_work_func(struct work_struct *work) 
		spin_unlock_irqrestore(&mf_cpu->lock, proc_flags);

		if (!gotten)

			break;

		if (entry.flags & MF_SOFT_OFFLINE)

			soft_offline_page(pfn_to_page(entry.pfn), entry.flags);

		else

			memory_failure(entry.pfn, entry.trapno, entry.flags);

	}

}

CRA Git | Maintained and supported by SUSTech CRA and CCSE