diff options
| author | Hawking Zhang <Hawking.Zhang@amd.com> | 2021-04-16 12:34:13 +0300 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2021-04-21 04:35:45 +0300 |
| commit | 53ee6609b42e09f89bf2cdd15a340c236694ecd3 (patch) | |
| tree | c7cf82ceedef56a55b750b0cc1f5b9b6bcf58601 /drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c | |
| parent | 9406d39bb6ef11e8525d7bd9acfcba5708db485b (diff) | |
| download | linux-53ee6609b42e09f89bf2cdd15a340c236694ecd3.tar.xz | |
drm/amdgpu: only harvest gcea/mmea error status in arcturus
SDP RdRspStatus/WrRspStatus or first parity error on
RdRsp data can cause system fatal error in arcturus.
GPU will be freezed in such case.
Driver needs to harvest these error information before
reset the GPU. Check error type to avoid harvest normal
gcea/mmea information.
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Stanley Yang <Stanley.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c | 16 |
1 files changed, 11 insertions, 5 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c index 830080ff90d8..b4789dfc2bb9 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c @@ -994,7 +994,7 @@ static int gfx_v9_4_ras_error_inject(struct amdgpu_device *adev, return ret; } -static const struct soc15_reg_entry gfx_v9_4_rdrsp_status_regs = +static const struct soc15_reg_entry gfx_v9_4_ea_err_status_regs = { SOC15_REG_ENTRY(GC, 0, mmGCEA_ERR_STATUS), 0, 1, 32 }; static void gfx_v9_4_query_ras_error_status(struct amdgpu_device *adev) @@ -1007,15 +1007,21 @@ static void gfx_v9_4_query_ras_error_status(struct amdgpu_device *adev) mutex_lock(&adev->grbm_idx_mutex); - for (i = 0; i < gfx_v9_4_rdrsp_status_regs.se_num; i++) { - for (j = 0; j < gfx_v9_4_rdrsp_status_regs.instance; + for (i = 0; i < gfx_v9_4_ea_err_status_regs.se_num; i++) { + for (j = 0; j < gfx_v9_4_ea_err_status_regs.instance; j++) { gfx_v9_4_select_se_sh(adev, i, 0, j); reg_value = RREG32(SOC15_REG_ENTRY_OFFSET( - gfx_v9_4_rdrsp_status_regs)); - if (reg_value) + gfx_v9_4_ea_err_status_regs)); + if (REG_GET_FIELD(reg_value, GCEA_ERR_STATUS, SDP_RDRSP_STATUS) || + REG_GET_FIELD(reg_value, GCEA_ERR_STATUS, SDP_WRRSP_STATUS) || + REG_GET_FIELD(reg_value, GCEA_ERR_STATUS, SDP_RDRSP_DATAPARITY_ERROR)) { + /* SDP read/write error/parity error in FUE_IS_FATAL mode + * can cause system fatal error in arcturas. Harvest the error + * status before GPU reset */ dev_warn(adev->dev, "GCEA err detected at instance: %d, status: 0x%x!\n", j, reg_value); + } } } |