fbdev: Fix sys_imageblit() for arbitrary image widths

Commit 6f29e04 ("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: 6f29e04 ("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

Author: tdz

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;
@@ -229,25 +229,31 @@ 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];
 				*dst++ = colortab[(*src >> 0) & bit_mask];
 			}
 			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;
 	}