mirror of https://gitee.com/openkylin/linux.git
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>
This commit is contained in:
parent
86153f1be2
commit
fe5211f19a
|
@ -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 {
|
||||
|
|
|
@ -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;
|
||||
|
|
|
@ -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,
|
||||
};
|
||||
|
|
|
@ -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,
|
||||
};
|
||||
|
|
Loading…
Reference in New Issue