aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/video/fbdev/core/sysimgblt.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/video/fbdev/core/sysimgblt.c')
-rw-r--r--drivers/video/fbdev/core/sysimgblt.c64
1 files changed, 56 insertions, 8 deletions
diff --git a/drivers/video/fbdev/core/sysimgblt.c b/drivers/video/fbdev/core/sysimgblt.c
index a4d05b1b17d7..665ef7a0a249 100644
--- a/drivers/video/fbdev/core/sysimgblt.c
+++ b/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;
- const char *s = image->data, *src;
+ u32 bit_mask, eorx, shift;
+ const u8 *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--; ) {
@@ -218,20 +224,62 @@ 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--; ) {
+ /*
+ * Manually unroll the per-line copying loop for better
+ * performance. This works until we processed the last
+ * completely filled source byte (inclusive).
+ */
+ switch (ppw) {
+ case 4: /* 8 bpp */
+ for (j = k; j >= 2; j -= 2, ++src) {
+ *dst++ = colortab[(*src >> 4) & bit_mask];
+ *dst++ = colortab[(*src >> 0) & bit_mask];
+ }
+ break;
+ case 2: /* 16 bpp */
+ for (j = k; j >= 4; 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 >= 8; 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;
+ }
+
+ /*
+ * For image widths that are not a multiple of 8, there
+ * are trailing pixels left on the current line. Print
+ * them as well.
+ */
+ for (; j--; ) {
shift -= ppw;
- end_mask = tab[(*src >> shift) & bit_mask];
- *dst++ = (end_mask & eorx) ^ bgx;
+ *dst++ = colortab[(*src >> shift) & bit_mask];
if (!shift) {
shift = 8;
- src++;
+ ++src;
}
}
+
dst1 += p->fix.line_length;
s += spitch;
}