Commit f04c62a7 authored by Mauro Carvalho Chehab's avatar Mauro Carvalho Chehab
Browse files

ghes_edac: add support for reporting errors via EDAC 



Now that the EDAC core is capable of just forward the errors via
the userspace API, add a report mechanism for the GHES errors.

Signed-off-by: default avatarMauro Carvalho Chehab <mchehab@redhat.com>
parent 77c5f5d2

drivers/edac/ghes_edac.c

+54 −2
Original line number Diff line number Diff line
@@ -29,6 +29,58 @@ static int ghes_edac_mc_num; 
void ghes_edac_report_mem_error(struct ghes *ghes, int sev,

				struct cper_sec_mem_err *mem_err)

{

	enum hw_event_mc_err_type type;

	struct edac_raw_error_desc *e;

	struct mem_ctl_info *mci;

	struct ghes_edac_pvt *pvt = NULL;



	list_for_each_entry(pvt, &ghes_reglist, list) {

		if (ghes == pvt->ghes)

			break;

	}

	if (!pvt) {

		pr_err("Internal error: Can't find EDAC structure\n");

		return;

	}

	mci = pvt->mci;

	e = &mci->error_desc;



	/* Cleans the error report buffer */

	memset(e, 0, sizeof (*e));

	e->error_count = 1;

	e->msg = "APEI";

	strcpy(e->label, "unknown");

	e->other_detail = "";



	if (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) {

		e->page_frame_number = mem_err->physical_addr >> PAGE_SHIFT;

		e->offset_in_page = mem_err->physical_addr & ~PAGE_MASK;

		e->grain = ~(mem_err->physical_addr_mask & ~PAGE_MASK);

	}



	switch (sev) {

	case GHES_SEV_CORRECTED:

		type = HW_EVENT_ERR_CORRECTED;

		break;

	case GHES_SEV_RECOVERABLE:

		type = HW_EVENT_ERR_UNCORRECTED;

		break;

	case GHES_SEV_PANIC:

		type = HW_EVENT_ERR_FATAL;

		break;

	default:

	case GHES_SEV_NO:

		type = HW_EVENT_ERR_INFO;

	}



	sprintf(e->location,

		"node:%d card:%d module:%d bank:%d device:%d row: %d column:%d bit_pos:%d",

		mem_err->node, mem_err->card, mem_err->module,

		mem_err->bank, mem_err->device, mem_err->row, mem_err->column,

		mem_err->bit_pos);

	edac_dbg(3, "error at location %s\n", e->location);



	edac_raw_mc_handle_error(type, mci, e);

}

EXPORT_SYMBOL_GPL(ghes_edac_report_mem_error);