Skip to contentSkip to conversation

drm/amd/ras: statistic xgmi training error count

PATCH In review Stanley.Yang 2 participants 2 messages Jan 23 – Jan 25

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

PATCH 1/1 drm/amd/ras: statistic xgmi training error count

Report xgmi training error uncorrectable error count.

Change-Id I7f2edf00ed37b5a4f13115ab2f0f914f07fc8519
---
 drivers/gpu/drm/amd/ras/rascore/ras_aca_v1_0.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/gpu/drm/amd/ras/rascore/ras_aca_v1_0.c +1 -1
index 29df98948703..210fbd8851a6 100644
@@ -299,7 +299,7 @@ static int aca_parse_xgmi_bank(struct ras_core_context *ras_core,
 
 	count = ACA_REG_MISC0_ERRCNT(bank->regs[ACA_REG_IDX__MISC0]);
 	if (bank->ecc_type == RAS_ERR_TYPE__UE) {
-		if (ext_error_code != 0 && ext_error_code != 9)
+		if (ext_error_code != 0 && ext_error_code != 1 && ext_error_code != 9)
 			count = 0ULL;
 		ecc->ue_count = count;
 	} else if (bank->ecc_type == RAS_ERR_TYPE__CE) {
Signature · 1 line
2.25.1
Reviewed-by on v1 1/1
#1 lore raw

[AMD Official Use Only - AMD Internal Distribution Only]

Regards,
Hawking
-----Original Message-----
From: amd-gfx <[email protected]> On Behalf Of Stanley.Yang
Sent: Friday, January 23, 2026 20:00
To: [email protected]
Cc: Yang, Stanley <[email protected]>
Subject: [PATCH Review 1/1] drm/amd/ras: statistic xgmi training error count

Report xgmi training error uncorrectable error count.

Change-Id I7f2edf00ed37b5a4f13115ab2f0f914f07fc8519
---
 drivers/gpu/drm/amd/ras/rascore/ras_aca_v1_0.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/gpu/drm/amd/ras/rascore/ras_aca_v1_0.c +1 -1
index 29df98948703..210fbd8851a6 100644
@@ -299,7 +299,7 @@ static int aca_parse_xgmi_bank(struct ras_core_context *ras_core,
 
        count = ACA_REG_MISC0_ERRCNT(bank->regs[ACA_REG_IDX__MISC0]);
        if (bank->ecc_type == RAS_ERR_TYPE__UE) {
-               if (ext_error_code != 0 && ext_error_code != 9)
+               if (ext_error_code != 0 && ext_error_code != 1 && ext_error_code != 9)
                        count = 0ULL;
                ecc->ue_count = count;
        } else if (bank->ecc_type == RAS_ERR_TYPE__CE) {

--
2.25.1