G2D: Implement an area threshold for using G2D blits.

Due to the overhead of G2D for small screen-to-screen blits, CPU blits
are faster for small areas. This patch introduces are threshold below
which CPU blits are triggered. It is currently set to 1000 for 32bpp
and 2500 for 16bpp based on test results.

Some benchmarks:

1920x1080x16bppx60Hz, ShadowFB disabled:

x11perf -scroll10

Before:
1500000 trep @   0.0239 msec ( 41800.0/sec): Scroll 10x10 pixels
After:
2500000 trep @   0.0110 msec ( 90900.0/sec): Scroll 10x10 pixels

x11perf -copywinwin10

Before:
1200000 trep @   0.0247 msec ( 40500.0/sec): Copy 10x10 from window to window
After:
1800000 trep @   0.0146 msec ( 68600.0/sec): Copy 10x10 from window to window
Signed-off-by: Harm Hanemaaijer <fgenfb@yahoo.com>

src/sunxi_disp.c

@@ -489,6 +489,7 @@ int sunxi_g2d_blt(void               *self,
                   int                 h)
 {
     sunxi_disp_t *disp = (sunxi_disp_t *)self;
+    int blt_size_threshold;
     g2d_blt tmp;
     /*
      * Very minimal validation here. We just assume that if the begginging
@@ -508,6 +509,18 @@ int sunxi_g2d_blt(void               *self,
     if (w <= 0 || h <= 0)
         return 1;
 
+    /*
+     * If the area is smaller than G2D_BLT_SIZE_THRESHOLD, prefer to avoid the
+     * overhead of G2D and do a CPU blit instead. There is a special threshold
+     * for 16bpp to 16bpp copy.
+     */
+    if (src_bpp == 16 && dst_bpp == 16)
+        blt_size_threshold = G2D_BLT_SIZE_THRESHOLD_16BPP;
+    else
+        blt_size_threshold = G2D_BLT_SIZE_THRESHOLD;
+    if (w * h < blt_size_threshold)
+        return 0;
+
     /* Unsupported overlapping type */
     if (src_bits == dst_bits && src_y == dst_y && src_x + 1 < dst_x)
         return 0;

src/sunxi_disp.h

@@ -118,6 +118,15 @@ int sunxi_g2d_blit_a8r8g8b8(sunxi_disp_t *disp,
                             int           w,
                             int           h);
 
+/*
+ * The following constants are used sunxi_disp.c and represent
+ * the area threshold below which the sunxi_g2d_blit function will
+ * return 0, indicating that a software blit is preferred. The
+ * 16BPP constant applies to 16bpp to 16bpp blit.
+ */
+#define G2D_BLT_SIZE_THRESHOLD 1000
+#define G2D_BLT_SIZE_THRESHOLD_16BPP 2500
+
 /* G2D counterpart for pixman_blt with the support for 16bpp and 32bpp */
 int sunxi_g2d_blt(void               *disp,
                   uint32_t           *src_bits,