fbdev: Improve performance of sys_imageblit()

Improve the performance of sys_imageblit() by manually unrolling
the inner blitting loop and moving some invariants out. The compiler
failed to do this automatically. The resulting binary code was even
slower than the cfb_imageblit() helper, which uses the same algorithm,
but operates on I/O memory.

A microbenchmark measures the average number of CPU cycles
for sys_imageblit() after a stabilizing period of a few minutes
(i7-4790, FullHD, simpledrm, kernel with debugging). The value
for CFB is given as a reference.

  sys_imageblit(), new: 25934 cycles
  sys_imageblit(), old: 35944 cycles
  cfb_imageblit():      30566 cycles

In the optimized case, sys_imageblit() is now ~30% faster than before
and ~20% faster than cfb_imageblit().

v2:
	* move switch out of inner loop (Gerd)
	* remove test for alignment of dst1 (Sam)
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Acked-by: Sam Ravnborg <sam@ravnborg.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20220223193804.18636-3-tzimmermann@suse.de

drivers/video/fbdev/core/sysimgblt.c

@@ -188,23 +188,29 @@ static void fast_imageblit(const struct fb_image *image, struct fb_info *p,
 {
 	u32 fgx = fgcolor, bgx = bgcolor, bpp = p->var.bits_per_pixel;
 	u32 ppw = 32/bpp, spitch = (image->width + 7)/8;
-	u32 bit_mask, end_mask, eorx, shift;
+	u32 bit_mask, eorx;
 	const char *s = image->data, *src;
 	u32 *dst;
-	const u32 *tab = NULL;
+	const u32 *tab;
+	size_t tablen;
+	u32 colortab[16];
 	int i, j, k;
 
 	switch (bpp) {
 	case 8:
 		tab = fb_be_math(p) ? cfb_tab8_be : cfb_tab8_le;
+		tablen = 16;
 		break;
 	case 16:
 		tab = fb_be_math(p) ? cfb_tab16_be : cfb_tab16_le;
+		tablen = 4;
 		break;
 	case 32:
-	default:
 		tab = cfb_tab32;
+		tablen = 2;
 		break;
+	default:
+		return;
 	}
 
 	for (i = ppw-1; i--; ) {
@@ -218,19 +224,40 @@ static void fast_imageblit(const struct fb_image *image, struct fb_info *p,
 	eorx = fgx ^ bgx;
 	k = image->width/ppw;
 
+	for (i = 0; i < tablen; ++i)
+		colortab[i] = (tab[i] & eorx) ^ bgx;
+
 	for (i = image->height; i--; ) {
 		dst = dst1;
-		shift = 8;
 		src = s;
 
-		for (j = k; j--; ) {
-			shift -= ppw;
-			end_mask = tab[(*src >> shift) & bit_mask];
-			*dst++ = (end_mask & eorx) ^ bgx;
-			if (!shift) {
-				shift = 8;
-				src++;
+		switch (ppw) {
+		case 4: /* 8 bpp */
+			for (j = k; j; j -= 2, ++src) {
+				*dst++ = colortab[(*src >> 4) & bit_mask];
+				*dst++ = colortab[(*src >> 0) & bit_mask];
+			}
+			break;
+		case 2: /* 16 bpp */
+			for (j = k; j; j -= 4, ++src) {
+				*dst++ = colortab[(*src >> 6) & bit_mask];
+				*dst++ = colortab[(*src >> 4) & bit_mask];
+				*dst++ = colortab[(*src >> 2) & bit_mask];
+				*dst++ = colortab[(*src >> 0) & bit_mask];
+			}
+			break;
+		case 1: /* 32 bpp */
+			for (j = k; j; j -= 8, ++src) {
+				*dst++ = colortab[(*src >> 7) & bit_mask];
+				*dst++ = colortab[(*src >> 6) & bit_mask];
+				*dst++ = colortab[(*src >> 5) & bit_mask];
+				*dst++ = colortab[(*src >> 4) & bit_mask];
+				*dst++ = colortab[(*src >> 3) & bit_mask];
+				*dst++ = colortab[(*src >> 2) & bit_mask];
+				*dst++ = colortab[(*src >> 1) & bit_mask];
+				*dst++ = colortab[(*src >> 0) & bit_mask];
 			}
+			break;
 		}
 		dst1 += p->fix.line_length;
 		s += spitch;