drm/amdgpu: Fix tdr3 could hang with slow compute issue

When index is 1, need to set compute ring timeout for sriov and passthrough.

Signed-off-by: Emily Deng <Emily.Deng@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index f25275abf4081efc401861ba45f3acaa11d93827..75a0db394e2100710886175c281c9394b6620f5c 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2622,8 +2622,11 @@ static int amdgpu_device_get_job_timeout_settings(struct amdgpu_device *adev)
                 * There is only one value specified and
                 * it should apply to all non-compute jobs.
                 */
-               if (index == 1)
+               if (index == 1) {
                        adev->sdma_timeout = adev->video_timeout = adev->gfx_timeout;
+                       if (amdgpu_sriov_vf(adev) || amdgpu_passthrough(adev))
+                               adev->compute_timeout = adev->gfx_timeout;
+               }
        }
 
        return ret;

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 0473329548aa328c521a3e2400a9056b609ece84..62256fe70abd1ef9a27d6ff38dba8fb1f89baf8f 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -249,9 +249,11 @@ module_param_named(msi, amdgpu_msi, int, 0444);
  * By default(with no lockup_timeout settings), the timeout for all non-compute(GFX, SDMA and Video)
  * jobs is 10000. And there is no timeout enforced on compute jobs.
  */
-MODULE_PARM_DESC(lockup_timeout, "GPU lockup timeout in ms (default: 10000 for non-compute jobs and infinity timeout for compute jobs."
+MODULE_PARM_DESC(lockup_timeout, "GPU lockup timeout in ms (default: for bare metal 10000 for non-compute jobs and infinity timeout for compute jobs; "
+               "for passthrough or sriov, 10000 for all jobs."
                " 0: keep default value. negative: infinity timeout), "
-               "format is [Non-Compute] or [GFX,Compute,SDMA,Video]");
+               "format: for bare metal [Non-Compute] or [GFX,Compute,SDMA,Video]; "
+               "for passthrough or sriov [all jobs] or [GFX,Compute,SDMA,Video].");
 module_param_string(lockup_timeout, amdgpu_lockup_timeout, sizeof(amdgpu_lockup_timeout), 0444);
 
 /**