drm/vc4: plane: Ensure fetch_count is sufficient for hw in SAND mode

The number of words to fetch for SAND formats on vc6 needs to account
for all pixels requested by width.

If cropping fractional pixels, then the width was being increased, but
fetch_count had already been computed. That led to insufficient words
being fetched, and the HVS locked up solid.

Apply the fixup for fractional pixel source cropping before computing
fetch_count.

Signed-off-by: Dave Stevenson <dave.stevenson@raspberrypi.com>

Author: 6by9

drivers/gpu/drm/vc4/vc4_plane.c

@@ -1895,6 +1895,24 @@ static int vc6_plane_mode_set(struct drm_plane *plane,
 
 	src_x = vc4_state->src_x >> 16;
 
+	/* fetch an extra pixel if we don't actually line up with the left edge. */
+	if ((vc4_state->src_x & 0xffff) && vc4_state->src_x < (state->fb->width << 16))
+		width++;
+
+	/* same for the right side */
+	if (((vc4_state->src_x + vc4_state->src_w[0]) & 0xffff) &&
+	    vc4_state->src_x + vc4_state->src_w[0] < (state->fb->width << 16))
+		width++;
+
+	/* now for the top */
+	if ((vc4_state->src_y & 0xffff) && vc4_state->src_y < (state->fb->height << 16))
+		height++;
+
+	/* and the bottom */
+	if (((vc4_state->src_y + vc4_state->src_h[0]) & 0xffff) &&
+	    vc4_state->src_y + vc4_state->src_h[0] < (state->fb->height << 16))
+		height++;
+
 	switch (base_format_mod) {
 	case DRM_FORMAT_MOD_LINEAR:
 		tiling = SCALER6_CTL0_ADDR_MODE_LINEAR;
@@ -2016,24 +2034,6 @@ static int vc6_plane_mode_set(struct drm_plane *plane,
 		return -EINVAL;
 	}
 
-	/* fetch an extra pixel if we don't actually line up with the left edge. */
-	if ((vc4_state->src_x & 0xffff) && vc4_state->src_x < (state->fb->width << 16))
-		width++;
-
-	/* same for the right side */
-	if (((vc4_state->src_x + vc4_state->src_w[0]) & 0xffff) &&
-	    vc4_state->src_x + vc4_state->src_w[0] < (state->fb->width << 16))
-		width++;
-
-	/* now for the top */
-	if ((vc4_state->src_y & 0xffff) && vc4_state->src_y < (state->fb->height << 16))
-		height++;
-
-	/* and the bottom */
-	if (((vc4_state->src_y + vc4_state->src_h[0]) & 0xffff) &&
-	    vc4_state->src_y + vc4_state->src_h[0] < (state->fb->height << 16))
-		height++;
-
 	/* for YUV444 hardware wants double the width, otherwise it doesn't
 	 * fetch full width of chroma
 	 */