Merge tag 'drm-vc4-next-2015-12-11' of http://github.com/anholt/linux into drm-next

This pull request brings in 3D acceleration support for the VC4 GPU.
While there is still performance work to be done (particularly
surrounding RCL generation), the CL submit ABI should be settled and
done now.

* tag 'drm-vc4-next-2015-12-11' of http://github.com/anholt/linux:
  drm/vc4: Add an interface for capturing the GPU state after a hang.
  drm/vc4: Add support for async pageflips.
  drm/vc4: Add support for drawing 3D frames.
  drm/vc4: Bind and initialize the V3D engine.
  drm/vc4: Fix a typo in a V3D debug register.
  drm/vc4: Add an API for creating GPU shaders in GEM BOs.
  drm/vc4: Add create and map BO ioctls.
  drm/vc4: Add a BO cache.
  drm: Create a driver hook for allocating GEM object structs.

1 files changed, 40 insertions, 0 deletions

diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index f34c422733dc..0addbad15832 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -29,6 +29,14 @@ struct vc4_plane_state {
 	u32 *dlist;
 	u32 dlist_size; /* Number of dwords in allocated for the display list */
 	u32 dlist_count; /* Number of used dwords in the display list. */
+
+	/* Offset in the dlist to pointer word 0. */
+	u32 pw0_offset;
+
+	/* Offset where the plane's dlist was last stored in the
+	   hardware at vc4_crtc_atomic_flush() time.
+	*/
+	u32 *hw_dlist;
 };
 
 static inline struct vc4_plane_state *
@@ -207,6 +215,8 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 	/* Position Word 3: Context.  Written by the HVS. */
 	vc4_dlist_write(vc4_state, 0xc0c0c0c0);
 
+	vc4_state->pw0_offset = vc4_state->dlist_count;
+
 	/* Pointer Word 0: RGB / Y Pointer */
 	vc4_dlist_write(vc4_state, bo->paddr + offset);
 
@@ -258,6 +268,8 @@ u32 vc4_plane_write_dlist(struct drm_plane *plane, u32 __iomem *dlist)
 	struct vc4_plane_state *vc4_state = to_vc4_plane_state(plane->state);
 	int i;
 
+	vc4_state->hw_dlist = dlist;
+
 	/* Can't memcpy_toio() because it needs to be 32-bit writes. */
 	for (i = 0; i < vc4_state->dlist_count; i++)
 		writel(vc4_state->dlist[i], &dlist[i]);
@@ -272,6 +284,34 @@ u32 vc4_plane_dlist_size(struct drm_plane_state *state)
 	return vc4_state->dlist_count;
 }
 
+/* Updates the plane to immediately (well, once the FIFO needs
+ * refilling) scan out from at a new framebuffer.
+ */
+void vc4_plane_async_set_fb(struct drm_plane *plane, struct drm_framebuffer *fb)
+{
+	struct vc4_plane_state *vc4_state = to_vc4_plane_state(plane->state);
+	struct drm_gem_cma_object *bo = drm_fb_cma_get_gem_obj(fb, 0);
+	uint32_t addr;
+
+	/* We're skipping the address adjustment for negative origin,
+	 * because this is only called on the primary plane.
+	 */
+	WARN_ON_ONCE(plane->state->crtc_x < 0 || plane->state->crtc_y < 0);
+	addr = bo->paddr + fb->offsets[0];
+
+	/* Write the new address into the hardware immediately.  The
+	 * scanout will start from this address as soon as the FIFO
+	 * needs to refill with pixels.
+	 */
+	writel(addr, &vc4_state->hw_dlist[vc4_state->pw0_offset]);
+
+	/* Also update the CPU-side dlist copy, so that any later
+	 * atomic updates that don't do a new modeset on our plane
+	 * also use our updated address.
+	 */
+	vc4_state->dlist[vc4_state->pw0_offset] = addr;
+}
+
 static const struct drm_plane_helper_funcs vc4_plane_helper_funcs = {
 	.prepare_fb = NULL,
 	.cleanup_fb = NULL,