drm/amdgpu: wait for all rings to drain before runtime suspending

Add a safety check to runtime suspend to make sure all outstanding
fences have signaled before we suspend.  Doesn't fix any known issue.

We already do this via the fence driver suspend function, but we
just force completion rather than bailing.  This bails on runtime
suspend so we can try again later once the fences are signaled to
avoid missing any outstanding work.

Reviewed-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 3f6f14ce1511a9bc1ff2741226690c64c1206d4b..d264d9011e03925823e053867822fbf93b5477ed 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1203,13 +1203,23 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev)
        struct pci_dev *pdev = to_pci_dev(dev);
        struct drm_device *drm_dev = pci_get_drvdata(pdev);
        struct amdgpu_device *adev = drm_dev->dev_private;
-       int ret;
+       int ret, i;
 
        if (!adev->runpm) {
                pm_runtime_forbid(dev);
                return -EBUSY;
        }
 
+       /* wait for all rings to drain before suspending */
+       for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
+               struct amdgpu_ring *ring = adev->rings[i];
+               if (ring && ring->sched.ready) {
+                       ret = amdgpu_fence_wait_empty(ring);
+                       if (ret)
+                               return -EBUSY;
+               }
+       }
+
        if (amdgpu_device_supports_boco(drm_dev))
                drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
        drm_kms_helper_poll_disable(drm_dev);