Optimize drawing of the mouse cursor in vga planar mode almost as

much as possible, by avoiding null ANDs and ORs to the frame buffer.

Mouse cursors are fairly sparse, especially for their frame.  Pixels
are written in groups of 8 in planar mode and the per-group sparseness
is not as large, but it still averages about 40% with the current
9x13 mouse cursor.  The average drawing time is reduced by about this
amount (from 22 usec constant to 12.5 usec average on Haswell).

This optimization is relatively larger with larger cursors.  Width 10
requires 6 frame buffer accesses per line instead of 4 if not done
sparsely, but rarely more than 4 if done sparsely.

1 files changed, 7 insertions, 4 deletions

diff --git a/sys/dev/syscons/scvgarndr.c b/sys/dev/syscons/scvgarndr.c
index 8450deb74c9c..9e4867b8b7e4 100644
--- a/sys/dev/syscons/scvgarndr.c
+++ b/sys/dev/syscons/scvgarndr.c
@@ -1032,6 +1032,7 @@ draw_pxlmouse_planar(scr_stat *scp, int x, int y)
 	int ymax;
 	u_short m;
 	int i, j, k;
+	uint8_t m1;
 
 	line_width = scp->sc->adp->va_line_width;
 	xoff = (x - scp->xoff*8)%8;
@@ -1046,9 +1047,10 @@ draw_pxlmouse_planar(scr_stat *scp, int x, int y)
 	for (i = y, j = 0; i < ymax; ++i, ++j) {
 		m = ~((mouse_and_mask[j] & ~mouse_or_mask[j]) >> xoff);
 		for (k = 0; k < 2; ++k) {
-			if (x + 8 * k < scp->xpixel) {
+			m1 = m >> (8 * (1 - k));
+			if (m1 != 0xff && x + 8 * k < scp->xpixel) {
 				readb(p + k);
-				writeb(p + k, m >> (8 * (1 - k)));
+				writeb(p + k, m1);
  			}
 		}
 		p += line_width;
@@ -1058,9 +1060,10 @@ draw_pxlmouse_planar(scr_stat *scp, int x, int y)
 	for (i = y, j = 0; i < ymax; ++i, ++j) {
 		m = mouse_or_mask[j] >> xoff;
 		for (k = 0; k < 2; ++k) {
-			if (x + 8 * k < scp->xpixel) {
+			m1 = m >> (8 * (1 - k));
+			if (m1 != 0 && x + 8 * k < scp->xpixel) {
 				readb(p + k);
-				writeb(p + k, m >> (8 * (1 - k)));
+				writeb(p + k, m1);
 			}
 		}
 		p += line_width;