fbdev: Improve performance of cfb_imageblit()

Improve the performance of cfb_imageblit() by manually unrolling
the inner blitting loop and moving some invariants out. The compiler
failed to do this automatically. This change keeps cfb_imageblit()
in sync with sys_imagebit().

A microbenchmark measures the average number of CPU cycles
for cfb_imageblit() after a stabilizing period of a few minutes
(i7-4790, FullHD, simpledrm, kernel with debugging).

cfb_imageblit(), new: 15724 cycles
cfb_imageblit(): old: 30566 cycles

In the optimized case, cfb_imageblit() is now ~2x faster than before.

v3:
	* fix commit description (Pekka)

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/20220223193804.18636-5-tzimmermann@suse.de
This commit is contained in:
Thomas Zimmermann 2022-02-23 20:38:03 +01:00
parent 3c54c95bd9
commit 0d03011894

View File

@ -218,23 +218,29 @@ static inline void fast_imageblit(const struct fb_image *image, struct fb_info *
{
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 __iomem *dst;
const u32 *tab = NULL;
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--; ) {
@ -248,15 +254,42 @@ static inline void fast_imageblit(const struct fb_image *image, struct fb_info *
eorx = fgx ^ bgx;
k = image->width/ppw;
for (i = image->height; i--; ) {
dst = (u32 __iomem *) dst1, shift = 8; src = s;
for (i = 0; i < tablen; ++i)
colortab[i] = (tab[i] & eorx) ^ bgx;
for (j = k; j--; ) {
shift -= ppw;
end_mask = tab[(*src >> shift) & bit_mask];
FB_WRITEL((end_mask & eorx)^bgx, dst++);
if (!shift) { shift = 8; src++; }
for (i = image->height; i--; ) {
dst = (u32 __iomem *)dst1;
src = s;
switch (ppw) {
case 4: /* 8 bpp */
for (j = k; j; j -= 2, ++src) {
FB_WRITEL(colortab[(*src >> 4) & bit_mask], dst++);
FB_WRITEL(colortab[(*src >> 0) & bit_mask], dst++);
}
break;
case 2: /* 16 bpp */
for (j = k; j; j -= 4, ++src) {
FB_WRITEL(colortab[(*src >> 6) & bit_mask], dst++);
FB_WRITEL(colortab[(*src >> 4) & bit_mask], dst++);
FB_WRITEL(colortab[(*src >> 2) & bit_mask], dst++);
FB_WRITEL(colortab[(*src >> 0) & bit_mask], dst++);
}
break;
case 1: /* 32 bpp */
for (j = k; j; j -= 8, ++src) {
FB_WRITEL(colortab[(*src >> 7) & bit_mask], dst++);
FB_WRITEL(colortab[(*src >> 6) & bit_mask], dst++);
FB_WRITEL(colortab[(*src >> 5) & bit_mask], dst++);
FB_WRITEL(colortab[(*src >> 4) & bit_mask], dst++);
FB_WRITEL(colortab[(*src >> 3) & bit_mask], dst++);
FB_WRITEL(colortab[(*src >> 2) & bit_mask], dst++);
FB_WRITEL(colortab[(*src >> 1) & bit_mask], dst++);
FB_WRITEL(colortab[(*src >> 0) & bit_mask], dst++);
}
break;
}
dst1 += p->fix.line_length;
s += spitch;
}