diff options
author | Stanley.Yang <Stanley.Yang@amd.com> | 2020-09-15 16:15:05 +0800 |
---|---|---|
committer | Alex Deucher <alexander.deucher@amd.com> | 2020-09-22 17:37:38 -0400 |
commit | 3f975d0f71d384825f47c3598d1d5358e40a57f5 (patch) | |
tree | 1daf6289c4aa95790897b0cf2ba2b450708b06a2 /drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c | |
parent | d117413f5e1be245b7b3e0cd6afda402609b2572 (diff) |
drm/amdgpu: update athub interrupt harvesting handle
GCEA/MMHUB EA error should not result to DF freeze, this is
fixed in next generation, but for some reasons the GCEA/MMHUB
EA error will result to DF freeze in previous generation,
diver should avoid to indicate GCEA/MMHUB EA error as hw fatal
error in kernel message by read GCEA/MMHUB err status registers.
Changed from V1:
make query_ras_error_status function more general
make read mmhub er status register more friendly
Changed from V2:
move ras error status query function into do_recovery workqueue
Changed from V3:
remove useless code from V2, print GCEA error status
instance number
Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@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 | 29 |
1 files changed, 29 insertions, 0 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c index bd85aed3523a..bc699d680ce8 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c @@ -992,3 +992,32 @@ int gfx_v9_4_ras_error_inject(struct amdgpu_device *adev, void *inject_if) return ret; } + +static const struct soc15_reg_entry gfx_v9_4_rdrsp_status_regs = + { SOC15_REG_ENTRY(GC, 0, mmGCEA_ERR_STATUS), 0, 1, 32 }; + +void gfx_v9_4_query_ras_error_status(struct amdgpu_device *adev) +{ + uint32_t i, j; + uint32_t reg_value; + + if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX)) + return; + + 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; + 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) + dev_warn(adev->dev, "GCEA err detected at instance: %d, status: 0x%x!\n", + j, reg_value); + } + } + + gfx_v9_4_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); + mutex_unlock(&adev->grbm_idx_mutex); +} |