[PATCH v5 07/13] drm/xe/xe_ras: Report device memory errors using SIGID

[Badal Nilawar <badal.nilawar@intel.com>]

Use xe_log_comp_info helper to report device memory errors using the
corresponding SIGID.

Example:
	xe 0000:03:00.0: [drm] SIGID=202 (020100020008002000300000)
DEVICE_MEMORY: Double-bit ECC error detected at sw address 0x63000

Reviewed-by: Mallesh Koujalagi <mallesh.koujalagi@intel.com>
Signed-off-by: Badal Nilawar <badal.nilawar@intel.com>
Cc: Riana Tauro <riana.tauro@intel.com>
---
v5:
  - Log unknown memory errors
  - Add example log in commit message (Raag)
---
 drivers/gpu/drm/xe/xe_ras.c | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_ras.c b/drivers/gpu/drm/xe/xe_ras.c
index 95e87c635b04..5ebfc6e8dfc7 100644
--- a/drivers/gpu/drm/xe/xe_ras.c
+++ b/drivers/gpu/drm/xe/xe_ras.c
@@ -643,6 +643,7 @@ static u8 handle_soc_internal_errors(struct xe_device *xe, struct xe_ras_error_a
 static u8 handle_device_memory_errors(struct xe_device *xe, struct xe_ras_error_array *arr)
 {
 	struct xe_ras_memory_error *info = (void *)arr->details;
+	u8 cper_sev = ras_sev_to_cper_sev(arr->counter.common.severity);
 	int ret;
 
 	/*
@@ -654,17 +655,30 @@ static u8 handle_device_memory_errors(struct xe_device *xe, struct xe_ras_error_
 	 */
 	switch (info->category) {
 	case XE_RAS_MEMORY_POISON:
-		xe_info(xe, "[RAS]: Poison error detected\n");
+		xe_log_comp_info(xe, DEVICE_MEMORY, &arr->counter, sizeof(arr->counter),
+				 "Poison error detected\n");
 		break;
 	case XE_RAS_MEMORY_DATA_PARITY:
-		xe_info(xe, "[RAS]: Data parity error detected\n");
+		xe_log_comp_info(xe, DEVICE_MEMORY, &arr->counter, sizeof(arr->counter),
+				 "Data parity error detected\n");
 		break;
 	case XE_RAS_MEMORY_DB_ECC:
 		ret = handle_page_offline(xe, info->sw_address, true);
-		if (ret)
+		if (ret) {
+			xe_log_comp(xe, cper_sev, DEVICE_MEMORY,
+				    &arr->counter, sizeof(arr->counter),
+				    "Failed to recover double-bit ECC error at sw address 0x%llx\n",
+				    info->sw_address);
 			return XE_RAS_RECOVERY_ACTION_RESET;
+		}
+
+		xe_log_comp_info(xe, DEVICE_MEMORY, &arr->counter, sizeof(arr->counter),
+				 "Double-bit ECC error at sw address 0x%llx\n",
+				 info->sw_address);
 		break;
 	default:
+		xe_log_comp(xe, cper_sev, DEVICE_MEMORY, &arr->counter, sizeof(arr->counter),
+			    "Unknown error detected\n");
 		return XE_RAS_RECOVERY_ACTION_RESET;
 	}
 
-- 
2.54.0