diff options
| author | Thomas Zimmermann <tzimmermann@suse.de> | 2022-03-13 20:29:51 +0100 |
|---|---|---|
| committer | Dave Airlie <airlied@redhat.com> | 2022-03-25 09:55:52 +1000 |
| commit | 40faaf80c463b2c99a0351d28bd74d75d64ed017 (patch) | |
| tree | ac30af48895176dea45e7beb3475b85d40c50c88 | |
| parent | c73c3576a2227492b448f9be41428ce6a0b5855a (diff) | |
| download | linux-40faaf80c463b2c99a0351d28bd74d75d64ed017.tar.gz | |
fbdev: Fix sys_imageblit() for arbitrary image widths
Commit 6f29e04938bf ("fbdev: Improve performance of sys_imageblit()")
broke sys_imageblit() for image width that are not aligned to 8-bit
boundaries. Fix this by handling the trailing pixels on each line
separately. The performance improvements in the original commit do not
regress by this change.
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Fixes: 6f29e04938bf ("fbdev: Improve performance of sys_imageblit()")
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: Javier Martinez Canillas <javierm@redhat.com>
Cc: Sam Ravnborg <sam@ravnborg.org>
Tested-by: Geert Uytterhoeven <geert@linux-m68k.org>
Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220313192952.12058-2-tzimmermann@suse.de
| -rw-r--r-- | drivers/video/fbdev/core/sysimgblt.c | 29 |
1 files changed, 25 insertions, 4 deletions
diff --git a/drivers/video/fbdev/core/sysimgblt.c b/drivers/video/fbdev/core/sysimgblt.c index 722c327a381bd..335e92b813fc4 100644 --- a/drivers/video/fbdev/core/sysimgblt.c +++ b/drivers/video/fbdev/core/sysimgblt.c @@ -188,7 +188,7 @@ 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, eorx; + u32 bit_mask, eorx, shift; const char *s = image->data, *src; u32 *dst; const u32 *tab; @@ -229,17 +229,23 @@ static void fast_imageblit(const struct fb_image *image, struct fb_info *p, for (i = image->height; i--; ) { dst = dst1; + shift = 8; src = s; + /* + * 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; j -= 2, ++src) { + 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; j -= 4, ++src) { + 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]; @@ -247,7 +253,7 @@ static void fast_imageblit(const struct fb_image *image, struct fb_info *p, } break; case 1: /* 32 bpp */ - for (j = k; j; j -= 8, ++src) { + 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]; @@ -259,6 +265,21 @@ static void fast_imageblit(const struct fb_image *image, struct fb_info *p, } 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; + *dst++ = colortab[(*src >> shift) & bit_mask]; + if (!shift) { + shift = 8; + ++src; + } + } + dst1 += p->fix.line_length; s += spitch; } |