diff options
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_device.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 20 |
1 files changed, 17 insertions, 3 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 905c5ab486a1..d01d7969d47b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4125,8 +4125,23 @@ static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive, amdgpu_fbdev_set_suspend(tmp_adev, 0); - /* must succeed. */ - amdgpu_ras_resume(tmp_adev); + /* + * The GPU enters bad state once faulty pages + * by ECC has reached the threshold, and ras + * recovery is scheduled next. So add one check + * here to break recovery if it indeed exceeds + * bad page threshold, and remind user to + * retire this GPU or setting one bigger + * bad_page_threshold value to fix this once + * probing driver again. + */ + if (!amdgpu_ras_check_err_threshold(tmp_adev)) { + /* must succeed. */ + amdgpu_ras_resume(tmp_adev); + } else { + r = -EINVAL; + goto out; + } /* Update PSP FW topology after reset */ if (hive && tmp_adev->gmc.xgmi.num_physical_nodes > 1) @@ -4134,7 +4149,6 @@ static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive, } } - out: if (!r) { amdgpu_irq_gpu_reset_resume_helper(tmp_adev); |