drm/vc4: Use runtime autosuspend to avoid thrashing V3D power state.

commit 3a62234680d86efa0239665ed8a0e908f1aef147 upstream.

The pm_runtime_put() we were using immediately released power on the
device, which meant that we were generally turning the device off and
on once per frame.  In many profiles I've looked at, that added up to
about 1% of CPU time, but this could get worse in the case of frequent
rendering and readback (as may happen in X rendering).  By keeping the
device on until we've been idle for a couple of frames, we drop the
overhead of runtime PM down to sub-.1%.

Signed-off-by: Eric Anholt <eric@anholt.net>
Cc: Amit Pundir <amit.pundir@linaro.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

3 files changed, 12 insertions, 5 deletions

diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index 8703f56b7947..246d1aea87bc 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -61,21 +61,24 @@ static int vc4_get_param_ioctl(struct drm_device *dev, void *data,
                 if (ret < 0)
                         return ret;
                 args->value = V3D_READ(V3D_IDENT0);
-                pm_runtime_put(&vc4->v3d->pdev->dev);
+                pm_runtime_mark_last_busy(&vc4->v3d->pdev->dev);
+                pm_runtime_put_autosuspend(&vc4->v3d->pdev->dev);
                 break;
         case DRM_VC4_PARAM_V3D_IDENT1:
                 ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev);
                 if (ret < 0)
                         return ret;
                 args->value = V3D_READ(V3D_IDENT1);
-                pm_runtime_put(&vc4->v3d->pdev->dev);
+                pm_runtime_mark_last_busy(&vc4->v3d->pdev->dev);
+                pm_runtime_put_autosuspend(&vc4->v3d->pdev->dev);
                 break;
         case DRM_VC4_PARAM_V3D_IDENT2:
                 ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev);
                 if (ret < 0)
                         return ret;
                 args->value = V3D_READ(V3D_IDENT2);
-                pm_runtime_put(&vc4->v3d->pdev->dev);
+                pm_runtime_mark_last_busy(&vc4->v3d->pdev->dev);
+                pm_runtime_put_autosuspend(&vc4->v3d->pdev->dev);
                 break;
         case DRM_VC4_PARAM_SUPPORTS_BRANCHES:
                 args->value = true;
diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index 18e37171e9c8..ab3016982466 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -711,8 +711,10 @@ vc4_complete_exec(struct drm_device *dev, struct vc4_exec_info *exec)
         }
 
         mutex_lock(&vc4->power_lock);
-        if (--vc4->power_refcount == 0)
-                pm_runtime_put(&vc4->v3d->pdev->dev);
+        if (--vc4->power_refcount == 0) {
+                pm_runtime_mark_last_busy(&vc4->v3d->pdev->dev);
+                pm_runtime_put_autosuspend(&vc4->v3d->pdev->dev);
+        }
         mutex_unlock(&vc4->power_lock);
 
         kfree(exec);
diff --git a/drivers/gpu/drm/vc4/vc4_v3d.c b/drivers/gpu/drm/vc4/vc4_v3d.c
index e6d3c6028341..7cc346ad9b0b 100644
--- a/drivers/gpu/drm/vc4/vc4_v3d.c
+++ b/drivers/gpu/drm/vc4/vc4_v3d.c
@@ -222,6 +222,8 @@ static int vc4_v3d_bind(struct device *dev, struct device *master, void *data)
                 return ret;
         }
 
+        pm_runtime_use_autosuspend(dev);
+        pm_runtime_set_autosuspend_delay(dev, 40); /* a little over 2 frames. */
         pm_runtime_enable(dev);
 
         return 0;