fbdev: Fix cfb_imageblit() for arbitrary image widths

Commit 0d03011 ("fbdev: Improve performance of cfb_imageblit()")
broke cfb_imageblit() for image widths 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: 0d03011 ("fbdev: Improve performance of cfb_imageblit()")
Reported-by: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: Javier Martinez Canillas <javierm@redhat.com>
Cc: Sam Ravnborg <sam@ravnborg.org>
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Tested-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220313192952.12058-3-tzimmermann@suse.de

Author: tdz

drivers/video/fbdev/core/cfbimgblt.c

@@ -218,7 +218,7 @@ 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, eorx;
+	u32 bit_mask, eorx, shift;
 	const char *s = image->data, *src;
 	u32 __iomem *dst;
 	const u32 *tab = NULL;
@@ -259,25 +259,31 @@ static inline void fast_imageblit(const struct fb_image *image, struct fb_info *
 
 	for (i = image->height; i--; ) {
 		dst = (u32 __iomem *)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) {
 				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) {
+			for (j = k; j >= 4; 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) {
+			for (j = k; j >= 8; 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++);
@@ -290,6 +296,20 @@ static inline void fast_imageblit(const struct fb_image *image, struct fb_info *
 			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;
+			FB_WRITEL(colortab[(*src >> shift) & bit_mask], dst++);
+			if (!shift) {
+				shift = 8;
+				++src;
+			}
+		}
+
 		dst1 += p->fix.line_length;
 		s += spitch;
 	}