diff options
| author | Hawking Zhang <Hawking.Zhang@amd.com> | 2020-03-02 07:14:20 +0300 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2020-03-05 08:32:40 +0300 |
| commit | fe5211f19a746c6573e1eae87a95b6b3313fe785 (patch) | |
| tree | e4c476fb095a84ce617467f4b079f06f050b8069 /drivers/gpu/drm/amd/amdgpu | |
| parent | 86153f1be26901598599c190b458dd26dce0fd50 (diff) | |
| download | linux-fe5211f19a746c6573e1eae87a95b6b3313fe785.tar.xz | |
drm/amdgpu: add reset_ras_error_count function for MMHUB
MMHUB ras error counters are dirty ones after cold reboot
Read operation is needed to reset them to 0
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h | 1 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 3 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c | 12 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c | 12 |
4 files changed, 28 insertions, 0 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h index 1cd78940cf82..e89fb35fec71 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h @@ -26,6 +26,7 @@ struct amdgpu_mmhub_funcs { int (*ras_late_init)(struct amdgpu_device *adev); void (*query_ras_error_count)(struct amdgpu_device *adev, void *ras_error_status); + void (*reset_ras_error_count)(struct amdgpu_device *adev); }; struct amdgpu_mmhub { diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 10171acbf3e1..6ceaab553130 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -948,6 +948,9 @@ static int gmc_v9_0_late_init(void *handle) } } + if (adev->mmhub.funcs && adev->mmhub.funcs->reset_ras_error_count) + adev->mmhub.funcs->reset_ras_error_count(adev); + r = amdgpu_gmc_ras_late_init(adev); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c index 49a3a56ec017..396c2a624de0 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c @@ -747,7 +747,19 @@ static void mmhub_v1_0_query_ras_error_count(struct amdgpu_device *adev, err_data->ue_count += ded_count; } +static void mmhub_v1_0_reset_ras_error_count(struct amdgpu_device *adev) +{ + uint32_t i; + + /* read back edc counter registers to reset the counters to 0 */ + if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__MMHUB)) { + for (i = 0; i < ARRAY_SIZE(mmhub_v1_0_edc_cnt_regs); i++) + RREG32(SOC15_REG_ENTRY_OFFSET(mmhub_v1_0_edc_cnt_regs[i])); + } +} + const struct amdgpu_mmhub_funcs mmhub_v1_0_funcs = { .ras_late_init = amdgpu_mmhub_ras_late_init, .query_ras_error_count = mmhub_v1_0_query_ras_error_count, + .reset_ras_error_count = mmhub_v1_0_reset_ras_error_count, }; diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c index a5281df8d84f..0d413fabd015 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c @@ -1596,7 +1596,19 @@ static void mmhub_v9_4_query_ras_error_count(struct amdgpu_device *adev, err_data->ue_count += ded_count; } +static void mmhub_v9_4_reset_ras_error_count(struct amdgpu_device *adev) +{ + uint32_t i; + + /* read back edc counter registers to reset the counters to 0 */ + if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__MMHUB)) { + for (i = 0; i < ARRAY_SIZE(mmhub_v9_4_edc_cnt_regs); i++) + RREG32(SOC15_REG_ENTRY_OFFSET(mmhub_v9_4_edc_cnt_regs[i])); + } +} + const struct amdgpu_mmhub_funcs mmhub_v9_4_funcs = { .ras_late_init = amdgpu_mmhub_ras_late_init, .query_ras_error_count = mmhub_v9_4_query_ras_error_count, + .reset_ras_error_count = mmhub_v9_4_reset_ras_error_count, }; |