drm/amdgpu: Report generic instead of unknown boot time errors

Change the DMESG reporting of unknown errors to "Boot Controller
Generic Error" to align with the RAS SPEC and provide more clarity
to customers.

Signed-off-by: Xiang Liu <xiang.liu@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Xiang Liu 2025-02-26 14:27:27 +08:00 committed by Alex Deucher
parent b965e42530
commit d4bd7a50ca
2 changed files with 3 additions and 3 deletions

View File

@ -5138,9 +5138,9 @@ static void amdgpu_ras_boot_time_error_reporting(struct amdgpu_device *adev,
"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))
if (AMDGPU_RAS_GPU_ERR_GENERIC(boot_error))
dev_info(adev->dev,
"socket: %d, aid: %d, fw_status: 0x%x, unknown boot time errors\n",
"socket: %d, aid: %d, fw_status: 0x%x, Boot Controller Generic Error\n",
socket_id, aid_id, fw_status);
}

View File

@ -47,7 +47,7 @@ struct amdgpu_iv_entry;
#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_GPU_ERR_GENERIC(x) AMDGPU_GET_REG_FIELD(x, 30, 30)
#define AMDGPU_RAS_BOOT_STATUS_POLLING_LIMIT 100
#define AMDGPU_RAS_BOOT_STEADY_STATUS 0xBA