[PATCH] drm/amd/pm: update XGMI RAS UE criteria for sum v13.0.6

Tao Zhou tao.zhou1 at amd.com
Mon Apr 1 06:24:27 UTC 2024


Add more possible ext error code.

v2: still use ext error code instead of UC bit.

Signed-off-by: Tao Zhou <tao.zhou1 at amd.com>
---
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 443233563a52..7a7c7f4b7de3 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -2694,7 +2694,8 @@ static int mca_pcs_xgmi_mca_get_err_count(const struct mca_ras_info *mca_ras, st
 	ext_error_code = MCA_REG__STATUS__ERRORCODEEXT(entry->regs[MCA_REG_IDX_STATUS]);
 	err_cnt = MCA_REG__MISC0__ERRCNT(entry->regs[MCA_REG_IDX_MISC0]);
 
-	if (type == AMDGPU_MCA_ERROR_TYPE_UE && ext_error_code == 0)
+	if (type == AMDGPU_MCA_ERROR_TYPE_UE &&
+	    (ext_error_code == 0 || ext_error_code == 9))
 		*count = err_cnt;
 	else if (type == AMDGPU_MCA_ERROR_TYPE_CE && ext_error_code == 6)
 		*count = err_cnt;
-- 
2.34.1



More information about the amd-gfx mailing list