[PATCH EDAC 08/13] ghes_edac: add support for reporting errors via EDAC

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



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: Mauro Carvalho Chehab <mchehab@xxxxxxxxxx>
---
 drivers/edac/ghes_edac.c | 36 +++++++++++++++++++++++++++++++++++-
 include/linux/edac.h     |  1 +
 2 files changed, 36 insertions(+), 1 deletion(-)

diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
index 1badac6..52625b5 100644
--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -9,8 +9,42 @@ static DEFINE_MUTEX(ghes_edac_lock);
 static int ghes_edac_mc_num;
 
 void ghes_edac_report_mem_error(struct ghes *ghes, int sev,
-                               struct cper_sec_mem_err *mem_err)
+			        struct cper_sec_mem_err *mem_err)
 {
+	enum hw_event_mc_err_type type;
+	unsigned long page = 0, offset = 0, grain = 0;
+	char location[80];
+	char *label = "unknown";
+
+	if (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) {
+		page = mem_err->physical_addr >> PAGE_SHIFT;
+		offset = mem_err->physical_addr & ~PAGE_MASK;
+		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(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_raw_mc_handle_error(type, ghes->mci, grain, 1, 0, 0, 0,
+				 page, offset, 0,
+				 "APEI", location, label, "", 0);
 }
 EXPORT_SYMBOL_GPL(ghes_edac_report_mem_error);
 
diff --git a/include/linux/edac.h b/include/linux/edac.h
index 1b7744c..28232a0 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -100,6 +100,7 @@ enum hw_event_mc_err_type {
 	HW_EVENT_ERR_CORRECTED,
 	HW_EVENT_ERR_UNCORRECTED,
 	HW_EVENT_ERR_FATAL,
+	HW_EVENT_ERR_INFO,
 };
 
 /**
-- 
1.8.1.2

--
To unsubscribe from this list: send the line "unsubscribe linux-acpi" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html


[Index of Archives]     [Linux IBM ACPI]     [Linux Power Management]     [Linux Kernel]     [Linux Laptop]     [Kernel Newbies]     [Share Photos]     [Security]     [Netfilter]     [Bugtraq]     [Yosemite News]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Samba]     [Video 4 Linux]     [Device Mapper]     [Linux Resources]

  Powered by Linux