[PATCH 2/2] drm/amdgpu: provide socket/die id info in RAS message

[Clements, John]

[AMD Official Use Only - Internal Distribution Only]

Reviewed-by: John Clements<John.Clements at amd.com>

-----Original Message-----
From: Hawking Zhang <Hawking.Zhang at amd.com> 
Sent: Sunday, April 25, 2021 3:10 PM
To: amd-gfx at lists.freedesktop.org; Li, Dennis <Dennis.Li at amd.com>; Clements, John <John.Clements at amd.com>; Deucher, Alexander <Alexander.Deucher at amd.com>
Cc: Zhang, Hawking <Hawking.Zhang at amd.com>
Subject: [PATCH 2/2] drm/amdgpu: provide socket/die id info in RAS message

Add socket/die information in RAS messages for platforms that support query those information

Signed-off-by: Hawking Zhang <Hawking.Zhang at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 29 +++++++++++++++++++++++++++--
 1 file changed, 27 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index f62873f..ae9fb20 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -901,17 +901,42 @@ int amdgpu_ras_query_error_status(struct amdgpu_device *adev,
 	info->ce_count = obj->err_data.ce_count;
 
 	if (err_data.ce_count) {
-		dev_info(adev->dev, "%ld correctable hardware errors "
+		if (adev->smuio.funcs &&
+		    adev->smuio.funcs->get_socket_id &&
+		    adev->smuio.funcs->get_die_id) {
+			dev_info(adev->dev, "socket: %d, die: %d "
+					"%ld correctable hardware errors "
 					"detected in %s block, no user "
 					"action is needed.\n",
+					adev->smuio.funcs->get_socket_id(adev),
+					adev->smuio.funcs->get_die_id(adev),
 					obj->err_data.ce_count,
 					ras_block_str(info->head.block));
+		} else {
+			dev_info(adev->dev, "%ld correctable hardware errors "
+					"detected in %s block, no user "
+					"action is needed.\n",
+					obj->err_data.ce_count,
+					ras_block_str(info->head.block));
+		}
 	}
 	if (err_data.ue_count) {
-		dev_info(adev->dev, "%ld uncorrectable hardware errors "
+		if (adev->smuio.funcs &&
+		    adev->smuio.funcs->get_socket_id &&
+		    adev->smuio.funcs->get_die_id) {
+			dev_info(adev->dev, "socket: %d, die: %d "
+					"%ld uncorrectable hardware errors "
 					"detected in %s block\n",
+					adev->smuio.funcs->get_socket_id(adev),
+					adev->smuio.funcs->get_die_id(adev),
 					obj->err_data.ue_count,
 					ras_block_str(info->head.block));
+		} else {
+			dev_info(adev->dev, "%ld uncorrectable hardware errors "
+					"detected in %s block\n",
+					obj->err_data.ue_count,
+					ras_block_str(info->head.block));
+		}
 	}
 
 	return 0;
--
2.7.4