Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-11-10 06:01:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

drm/amdgpu: Add more types for boot time error reporting

Browse Source 
Data abort exception and unknown errors are supported.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Hawking Zhang 2024-08-01 13:45:27 +08:00 committed by Alex Deucher
parent 9192c7613c
commit dfe9d047b1
2 changed files with 12 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
View File

@ -4748,6 +4748,16 @@ static void amdgpu_ras_boot_time_error_reporting(struct amdgpu_device *adev,
dev_info(adev->dev,
"socket: %d, aid: %d, hbm: %d, fw_status: 0x%x, hbm bist test failed\n",
socket_id, aid_id, hbm_id, fw_status);
if (AMDGPU_RAS_GPU_ERR_DATA_ABORT(boot_error))
dev_info(adev->dev,
"socket: %d, aid: %d, fw_status: 0x%x, data abort exception\n",
socket_id, aid_id, fw_status);
if (AMDGPU_RAS_GPU_ERR_UNKNOWN(boot_error))
dev_info(adev->dev,
"socket: %d, aid: %d, fw_status: 0x%x, unknown boot time errors\n",
socket_id, aid_id, fw_status);
}
static bool amdgpu_ras_boot_error_detected(struct amdgpu_device *adev,

2
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
View File

@ -46,6 +46,8 @@ struct amdgpu_iv_entry;
#define AMDGPU_RAS_GPU_ERR_SOCKET_ID(x) AMDGPU_GET_REG_FIELD(x, 10, 8)
#define AMDGPU_RAS_GPU_ERR_AID_ID(x) AMDGPU_GET_REG_FIELD(x, 12, 11)
#define AMDGPU_RAS_GPU_ERR_HBM_ID(x) AMDGPU_GET_REG_FIELD(x, 14, 13)
#define AMDGPU_RAS_GPU_ERR_DATA_ABORT(x) AMDGPU_GET_REG_FIELD(x, 29, 29)
#define AMDGPU_RAS_GPU_ERR_UNKNOWN(x) AMDGPU_GET_REG_FIELD(x, 30, 30)
#define AMDGPU_RAS_BOOT_STATUS_POLLING_LIMIT 100
#define AMDGPU_RAS_BOOT_STEADY_STATUS 0xBA