diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c
index cd57747286f2..9635897458a0 100644
--- a/drivers/dma-buf/udmabuf.c
+++ b/drivers/dma-buf/udmabuf.c
@@ -77,6 +77,7 @@ static void unmap_udmabuf(struct dma_buf_attachment *at,
 			  struct sg_table *sg,
 			  enum dma_data_direction direction)
 {
+	dma_unmap_sg(at->dev, sg->sgl, sg->nents, direction);
 	sg_free_table(sg);
 	kfree(sg);
 }
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index bcb1a93c0b4c..ab7c5c3004ee 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -4232,8 +4232,7 @@ static void dm_plane_atomic_async_update(struct drm_plane *plane,
 	struct drm_plane_state *old_state =
 		drm_atomic_get_old_plane_state(new_state->state, plane);
 
-	if (plane->state->fb != new_state->fb)
-		drm_atomic_set_fb_for_plane(plane->state, new_state->fb);
+	swap(plane->state->fb, new_state->fb);
 
 	plane->state->src_x = new_state->src_x;
 	plane->state->src_y = new_state->src_y;
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 2e0cb4246cbd..22a5c617f670 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -1607,15 +1607,6 @@ int drm_atomic_helper_async_check(struct drm_device *dev,
 	    old_plane_state->crtc != new_plane_state->crtc)
 		return -EINVAL;
 
-	/*
-	 * FIXME: Since prepare_fb and cleanup_fb are always called on
-	 * the new_plane_state for async updates we need to block framebuffer
-	 * changes. This prevents use of a fb that's been cleaned up and
-	 * double cleanups from occuring.
-	 */
-	if (old_plane_state->fb != new_plane_state->fb)
-		return -EINVAL;
-
 	funcs = plane->helper_private;
 	if (!funcs->atomic_async_update)
 		return -EINVAL;
@@ -1646,6 +1637,8 @@ EXPORT_SYMBOL(drm_atomic_helper_async_check);
  * drm_atomic_async_check() succeeds. Async commits are not supposed to swap
  * the states like normal sync commits, but just do in-place changes on the
  * current state.
+ *
+ * TODO: Implement full swap instead of doing in-place changes.
  */
 void drm_atomic_helper_async_commit(struct drm_device *dev,
 				    struct drm_atomic_state *state)
@@ -1656,6 +1649,9 @@ void drm_atomic_helper_async_commit(struct drm_device *dev,
 	int i;
 
 	for_each_new_plane_in_state(state, plane, plane_state, i) {
+		struct drm_framebuffer *new_fb = plane_state->fb;
+		struct drm_framebuffer *old_fb = plane->state->fb;
+
 		funcs = plane->helper_private;
 		funcs->atomic_async_update(plane, plane_state);
 
@@ -1664,11 +1660,17 @@ void drm_atomic_helper_async_commit(struct drm_device *dev,
 		 * plane->state in-place, make sure at least common
 		 * properties have been properly updated.
 		 */
-		WARN_ON_ONCE(plane->state->fb != plane_state->fb);
+		WARN_ON_ONCE(plane->state->fb != new_fb);
 		WARN_ON_ONCE(plane->state->crtc_x != plane_state->crtc_x);
 		WARN_ON_ONCE(plane->state->crtc_y != plane_state->crtc_y);
 		WARN_ON_ONCE(plane->state->src_x != plane_state->src_x);
 		WARN_ON_ONCE(plane->state->src_y != plane_state->src_y);
+
+		/*
+		 * Make sure the FBs have been swapped so that cleanups in the
+		 * new_state performs a cleanup in the old FB.
+		 */
+		WARN_ON_ONCE(plane_state->fb != old_fb);
 	}
 }
 EXPORT_SYMBOL(drm_atomic_helper_async_commit);
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c
index be13140967b4..b854f471e9e5 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c
@@ -502,6 +502,8 @@ static int mdp5_plane_atomic_async_check(struct drm_plane *plane,
 static void mdp5_plane_atomic_async_update(struct drm_plane *plane,
 					   struct drm_plane_state *new_state)
 {
+	struct drm_framebuffer *old_fb = plane->state->fb;
+
 	plane->state->src_x = new_state->src_x;
 	plane->state->src_y = new_state->src_y;
 	plane->state->crtc_x = new_state->crtc_x;
@@ -524,6 +526,8 @@ static void mdp5_plane_atomic_async_update(struct drm_plane *plane,
 
 	*to_mdp5_plane_state(plane->state) =
 		*to_mdp5_plane_state(new_state);
+
+	new_state->fb = old_fb;
 }
 
 static const struct drm_plane_helper_funcs mdp5_plane_helper_funcs = {
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index 20a9c296d027..3bb242f7d32f 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -924,29 +924,17 @@ static void vop_plane_atomic_async_update(struct drm_plane *plane,
 					  struct drm_plane_state *new_state)
 {
 	struct vop *vop = to_vop(plane->state->crtc);
-	struct drm_plane_state *plane_state;
+	struct drm_framebuffer *old_fb = plane->state->fb;
 
-	plane_state = plane->funcs->atomic_duplicate_state(plane);
-	plane_state->crtc_x = new_state->crtc_x;
-	plane_state->crtc_y = new_state->crtc_y;
-	plane_state->crtc_h = new_state->crtc_h;
-	plane_state->crtc_w = new_state->crtc_w;
-	plane_state->src_x = new_state->src_x;
-	plane_state->src_y = new_state->src_y;
-	plane_state->src_h = new_state->src_h;
-	plane_state->src_w = new_state->src_w;
-
-	if (plane_state->fb != new_state->fb)
-		drm_atomic_set_fb_for_plane(plane_state, new_state->fb);
-
-	swap(plane_state, plane->state);
-
-	if (plane->state->fb && plane->state->fb != new_state->fb) {
-		drm_framebuffer_get(plane->state->fb);
-		WARN_ON(drm_crtc_vblank_get(plane->state->crtc) != 0);
-		drm_flip_work_queue(&vop->fb_unref_work, plane->state->fb);
-		set_bit(VOP_PENDING_FB_UNREF, &vop->pending);
-	}
+	plane->state->crtc_x = new_state->crtc_x;
+	plane->state->crtc_y = new_state->crtc_y;
+	plane->state->crtc_h = new_state->crtc_h;
+	plane->state->crtc_w = new_state->crtc_w;
+	plane->state->src_x = new_state->src_x;
+	plane->state->src_y = new_state->src_y;
+	plane->state->src_h = new_state->src_h;
+	plane->state->src_w = new_state->src_w;
+	swap(plane->state->fb, new_state->fb);
 
 	if (vop->is_enabled) {
 		rockchip_drm_psr_inhibit_get_state(new_state->state);
@@ -955,9 +943,22 @@ static void vop_plane_atomic_async_update(struct drm_plane *plane,
 		vop_cfg_done(vop);
 		spin_unlock(&vop->reg_lock);
 		rockchip_drm_psr_inhibit_put_state(new_state->state);
-	}
 
-	plane->funcs->atomic_destroy_state(plane, plane_state);
+		/*
+		 * A scanout can still be occurring, so we can't drop the
+		 * reference to the old framebuffer. To solve this we get a
+		 * reference to old_fb and set a worker to release it later.
+		 * FIXME: if we perform 500 async_update calls before the
+		 * vblank, then we can have 500 different framebuffers waiting
+		 * to be released.
+		 */
+		if (old_fb && plane->state->fb != old_fb) {
+			drm_framebuffer_get(old_fb);
+			WARN_ON(drm_crtc_vblank_get(plane->state->crtc) != 0);
+			drm_flip_work_queue(&vop->fb_unref_work, old_fb);
+			set_bit(VOP_PENDING_FB_UNREF, &vop->pending);
+		}
+	}
 }
 
 static const struct drm_plane_helper_funcs plane_helper_funcs = {
diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index 4d918d3e4858..afc80b245ea3 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -1025,7 +1025,7 @@ static void vc4_plane_atomic_async_update(struct drm_plane *plane,
 {
 	struct vc4_plane_state *vc4_state, *new_vc4_state;
 
-	drm_atomic_set_fb_for_plane(plane->state, state->fb);
+	swap(plane->state->fb, state->fb);
 	plane->state->crtc_x = state->crtc_x;
 	plane->state->crtc_y = state->crtc_y;
 	plane->state->crtc_w = state->crtc_w;
diff --git a/include/drm/drm_modeset_helper_vtables.h b/include/drm/drm_modeset_helper_vtables.h
index f9c94c2a1364..f7bbd0b0ecd1 100644
--- a/include/drm/drm_modeset_helper_vtables.h
+++ b/include/drm/drm_modeset_helper_vtables.h
@@ -1185,6 +1185,14 @@ struct drm_plane_helper_funcs {
 	 * current one with the new plane configurations in the new
 	 * plane_state.
 	 *
+	 * Drivers should also swap the framebuffers between current plane
+	 * state (&drm_plane.state) and new_state.
+	 * This is required since cleanup for async commits is performed on
+	 * the new state, rather than old state like for traditional commits.
+	 * Since we want to give up the reference on the current (old) fb
+	 * instead of our brand new one, swap them in the driver during the
+	 * async commit.
+	 *
 	 * FIXME:
 	 *  - It only works for single plane updates
 	 *  - Async Pageflips are not supported yet