Merge heisenberg.transvirtual.com:/tmp/linus-2.5

into heisenberg.transvirtual.com:/tmp/fbdev-2.5

drivers/video/Config.in

@@ -265,7 +265,7 @@ if [ "$CONFIG_FB" = "y" ]; then
       if [ "$CONFIG_FB_ACORN" = "y" -o "$CONFIG_FB_ATARI" = "y" -o \
 	   "$CONFIG_FB_ATY" = "y" -o "$CONFIG_FB_MAC" = "y" -o \
 	   "$CONFIG_FB_OF" = "y" -o "$CONFIG_FB_TGA" = "y" -o \
-	   "$CONFIG_FB_VESA" = "y" -o "$CONFIG_FB_VIRTUAL" = "y" -o \
+	   "$CONFIG_FB_NEOMAGIC" = "y" -o "$CONFIG_FB_VIRTUAL" = "y" -o \
 	   "$CONFIG_FB_TCX" = "y" -o "$CONFIG_FB_CGTHREE" = "y" -o \
 	   "$CONFIG_FB_CONTROL" = "y" -o "$CONFIG_FB_CLGEN" = "y" -o \
 	   "$CONFIG_FB_CGFOURTEEN" = "y" -o "$CONFIG_FB_G364" = "y" -o \
@@ -279,13 +279,13 @@ if [ "$CONFIG_FB" = "y" ]; then
 	   "$CONFIG_FB_SA1100" = "y" -o "$CONFIG_FB_3DFX" = "y" -o \
 	   "$CONFIG_FB_PMAG_BA" = "y" -o "$CONFIG_FB_PMAGB_B" = "y" -o \
 	   "$CONFIG_FB_MAXINE" = "y" -o "$CONFIG_FB_TX3912" = "y" -o \
-	   "$CONFIG_FB_SIS" = "y" -o "$CONFIG_FB_NEOMAGIC" = "y" ]; then
+	   "$CONFIG_FB_SIS" = "y" ]; then
 	 define_tristate CONFIG_FBCON_CFB8 y
       else
 	 if [ "$CONFIG_FB_ACORN" = "m" -o "$CONFIG_FB_ATARI" = "m" -o \
 	      "$CONFIG_FB_ATY" = "m" -o "$CONFIG_FB_MAC" = "m" -o \
 	      "$CONFIG_FB_OF" = "m" -o "$CONFIG_FB_TGA" = "m" -o \
-	      "$CONFIG_FB_VESA" = "m" -o "$CONFIG_FB_VIRTUAL" = "m" -o \
+	      "$CONFIG_FB_NEOMAGIC" = "m" -o "$CONFIG_FB_VIRTUAL" = "m" -o \
 	      "$CONFIG_FB_TCX" = "m" -o "$CONFIG_FB_CGTHREE" = "m" -o \
 	      "$CONFIG_FB_CONTROL" = "m" -o "$CONFIG_FB_CLGEN" = "m" -o \
 	      "$CONFIG_FB_CGFOURTEEN" = "m" -o "$CONFIG_FB_G364" = "m" -o \
@@ -299,12 +299,12 @@ if [ "$CONFIG_FB" = "y" ]; then
 	      "$CONFIG_FB_PMAG_BA" = "m" -o "$CONFIG_FB_PMAGB_B" = "m" -o \
 	      "$CONFIG_FB_MAXINE" = "m" -o "$CONFIG_FB_RADEON" = "m" -o \
 	      "$CONFIG_FB_SA1100" = "m" -o "$CONFIG_FB_SIS" = "m" -o \
-	      "$CONFIG_FB_TX3912" = "m" -o "$CONFIG_FB_NEOMAGIC" = "m" ]; then
+	      "$CONFIG_FB_TX3912" = "m" ]; then
 	    define_tristate CONFIG_FBCON_CFB8 m
 	 fi
       fi
       if [ "$CONFIG_FB_ATARI" = "y" -o "$CONFIG_FB_ATY" = "y" -o \
-	   "$CONFIG_FB_MAC" = "y" -o "$CONFIG_FB_VESA" = "y" -o \
+	   "$CONFIG_FB_MAC" = "y" -o "$CONFIG_FB_NEOMAGIC" = "y" -o \
 	   "$CONFIG_FB_VIRTUAL" = "y" -o "$CONFIG_FB_TBOX" = "y" -o \
 	   "$CONFIG_FB_Q40" = "y" -o "$CONFIG_FB_RADEON" = "y" -o \
 	   "$CONFIG_FB_CONTROL" = "y" -o "$CONFIG_FB_CLGEN" = "y" -o \
@@ -315,12 +315,11 @@ if [ "$CONFIG_FB" = "y" ]; then
 	   "$CONFIG_FB_RIVA" = "y" -o "$CONFIG_FB_ATY128" = "y" -o \
 	   "$CONFIG_FB_CYBER2000" = "y" -o "$CONFIG_FB_3DFX" = "y"  -o \
 	   "$CONFIG_FB_SIS" = "y" -o "$CONFIG_FB_SA1100" = "y" -o \
-	   "$CONFIG_FB_PVR2" = "y" -o "$CONFIG_FB_VOODOO1" = "y" -o \
-	   "$CONFIG_FB_NEOMAGIC" = "y" ]; then
+	   "$CONFIG_FB_PVR2" = "y" -o "$CONFIG_FB_VOODOO1" = "y" ]; then 
 	 define_tristate CONFIG_FBCON_CFB16 y
       else
 	 if [ "$CONFIG_FB_ATARI" = "m" -o "$CONFIG_FB_ATY" = "m" -o \
-	      "$CONFIG_FB_MAC" = "m" -o "$CONFIG_FB_VESA" = "m" -o \
+	      "$CONFIG_FB_MAC" = "m" -o "$CONFIG_FB_NEOMAGIC" = "m" -o \
 	      "$CONFIG_FB_VIRTUAL" = "m" -o "$CONFIG_FB_TBOX" = "m" -o \
 	      "$CONFIG_FB_Q40" = "m" -o "$CONFIG_FB_3DFX" = "m" -o \
 	      "$CONFIG_FB_CONTROL" = "m" -o "$CONFIG_FB_CLGEN" = "m" -o \
@@ -331,8 +330,7 @@ if [ "$CONFIG_FB" = "y" ]; then
 	      "$CONFIG_FB_RIVA" = "m" -o "$CONFIG_FB_ATY128" = "m" -o \
 	      "$CONFIG_FB_CYBER2000" = "m" -o "$CONFIG_FB_SIS" = "m" -o \
 	      "$CONFIG_FB_SA1100" = "m" -o "$CONFIG_FB_RADEON" = "m" -o \
-	      "$CONFIG_FB_PVR2" = "m" -o "$CONFIG_FB_VOODOO1" = "m" -o \
-	      "$CONFIG_FB_NEOMAGIC" = "m" ]; then
+	      "$CONFIG_FB_PVR2" = "m" -o "$CONFIG_FB_VOODOO1" = "m" ]; then 
 	    define_tristate CONFIG_FBCON_CFB16 m
 	 fi
       fi
@@ -354,29 +352,31 @@ if [ "$CONFIG_FB" = "y" ]; then
 	 fi
       fi
       if [ "$CONFIG_FB_ATARI" = "y" -o "$CONFIG_FB_ATY" = "y" -o \
-	   "$CONFIG_FB_VESA" = "y" -o "$CONFIG_FB_VIRTUAL" = "y" -o \
+	   "$CONFIG_FB_VOODOO1" = "y" -o "$CONFIG_FB_VIRTUAL" = "y" -o \
 	   "$CONFIG_FB_CONTROL" = "y" -o "$CONFIG_FB_CLGEN" = "y" -o \
 	   "$CONFIG_FB_TGA" = "y" -o "$CONFIG_FB_PLATINUM" = "y" -o \
 	   "$CONFIG_FB_MATROX" = "y" -o "$CONFIG_FB_PM2" = "y" -o \
 	   "$CONFIG_FB_RIVA" = "y" -o "$CONFIG_FB_ATY128" = "y" -o \
 	   "$CONFIG_FB_FM2" = "y" -o "$CONFIG_FB_SGIVW" = "y" -o \
 	   "$CONFIG_FB_RADEON" = "y" -o "$CONFIG_FB_PVR2" = "y" -o \
-	   "$CONFIG_FB_3DFX" = "y" -o "$CONFIG_FB_SIS" = "y" -o \
-	   "$CONFIG_FB_VOODOO1" = "y" ]; then
+	   "$CONFIG_FB_3DFX" = "y" -o "$CONFIG_FB_SIS" = "y" ]; then 
 	 define_tristate CONFIG_FBCON_CFB32 y
       else
 	 if [ "$CONFIG_FB_ATARI" = "m" -o "$CONFIG_FB_ATY" = "m" -o \
-	      "$CONFIG_FB_VESA" = "m" -o "$CONFIG_FB_VIRTUAL" = "m" -o \
+	      "$CONFIG_FB_VOODOO1" = "m" -o "$CONFIG_FB_VIRTUAL" = "m" -o \
 	      "$CONFIG_FB_CONTROL" = "m" -o "$CONFIG_FB_CLGEN" = "m" -o \
 	      "$CONFIG_FB_TGA" = "m" -o "$CONFIG_FB_PLATINUM" = "m" -o \
 	      "$CONFIG_FB_MATROX" = "m" -o "$CONFIG_FB_PM2" = "m" -o \
 	      "$CONFIG_FB_RIVA" = "m" -o "$CONFIG_FB_ATY128" = "m" -o \
 	      "$CONFIG_FB_3DFX" = "m" -o "$CONFIG_FB_RADEON" = "m" -o \
 	      "$CONFIG_FB_SGIVW" = "m" -o "$CONFIG_FB_SIS" = "m" -o \
-	      "$CONFIG_FB_PVR2" = "m" -o "$CONFIG_FB_VOODOO1" = "m" ]; then
+	      "$CONFIG_FB_PVR2" = "m" ]; then
 	    define_tristate CONFIG_FBCON_CFB32 m
 	 fi
       fi
+      if [ "$CONFIG_FB_VESA" = "y" ]; then
+	 define_tristate CONFIG_FBCON_ACCEL y
+      fi
       if [ "$CONFIG_FB_AMIGA" = "y" ]; then
 	 define_tristate CONFIG_FBCON_AFB y
 	 define_tristate CONFIG_FBCON_ILBM y

drivers/video/Makefile

@@ -69,7 +69,7 @@ obj-$(CONFIG_FB_RETINAZ3)         += retz3fb.o
 obj-$(CONFIG_FB_CLGEN)            += clgenfb.o
 obj-$(CONFIG_FB_S3TRIO)           += S3triofb.o
 obj-$(CONFIG_FB_TGA)              += tgafb.o
-obj-$(CONFIG_FB_VESA)             += vesafb.o 
+obj-$(CONFIG_FB_VESA)             += vesafb.o cfbfillrect.o cfbcopyarea.o cfbimgblt.o 
 obj-$(CONFIG_FB_VGA16)            += vga16fb.o fbcon-vga-planes.o
 obj-$(CONFIG_FB_VIRGE)            += virgefb.o
 obj-$(CONFIG_FB_G364)             += g364fb.o
@@ -138,6 +138,7 @@ obj-$(CONFIG_FBCON_MFB)           += fbcon-mfb.o
 obj-$(CONFIG_FBCON_VGA)           += fbcon-vga.o
 obj-$(CONFIG_FBCON_HGA)           += fbcon-hga.o
 obj-$(CONFIG_FBCON_STI)           += fbcon-sti.o
+obj-$(CONFIG_FBCON_ACCEL)	  += fbcon-accel.o
 
 include $(TOPDIR)/Rules.make
 

drivers/video/cfbcopyarea.c

+/*
+ *  Generic function for frame buffer with packed pixels of any depth.
+ *
+ *      Copyright (C)  June 1999 James Simmons
+ *
+ *  This file is subject to the terms and conditions of the GNU General Public
+ *  License.  See the file COPYING in the main directory of this archive for
+ *  more details.
+ *
+ * NOTES:
+ * 
+ *  This is for cfb packed pixels. Iplan and such are incorporated in the 
+ *  drivers that need them.
+ * 
+ *  FIXME
+ *  The code for 24 bit is horrible. It copies byte by byte size instead of 
+ *  longs like the other sizes. Needs to be optimized. 
+ *
+ *  Also need to add code to deal with cards endians that are different than 
+ *  the native cpu endians. I also need to deal with MSB position in the word.
+ *  
+ */
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/fb.h>
+#include <linux/slab.h>
+#include <asm/types.h>
+#include <asm/io.h>
+#include <video/fbcon.h>
+
+void cfb_copyarea(struct fb_info *p, struct fb_copyarea *area)
+{
+	int x2, y2, lineincr, shift, shift_right, shift_left, old_dx, old_dy;
+	int n, j, linesize = p->fix.line_length, bpl = sizeof(unsigned long);
+	unsigned long start_index, end_index, start_mask, end_mask, last;
+	unsigned long *dst = NULL, *src = NULL;
+	char *src1, *dst1;
+	int tmp, height;
+
+	/* clip the destination */
+	old_dx = area->dx;
+	old_dy = area->dy;
+
+	/*
+	 * We could use hardware clipping but on many cards you get around
+	 * hardware clipping by writing to framebuffer directly.
+	 */
+	x2 = area->dx + area->width;
+	y2 = area->dy + area->height;
+	area->dx = area->dx > 0 ? area->dx : 0;
+	area->dy = area->dy > 0 ? area->dy : 0;
+	x2 = x2 < p->var.xres_virtual ? x2 : p->var.xres_virtual;
+	y2 = y2 < p->var.yres_virtual ? y2 : p->var.yres_virtual;
+	area->width = x2 - area->dx;
+	area->height = y2 - area->dy;
+
+	/* update sx1,sy1 */
+	area->sx += (area->dx - old_dx);
+	area->sy += (area->dy - old_dy);
+
+	height = area->height;
+
+	/* the source must be completely inside the virtual screen */
+	if (area->sx < 0 || area->sy < 0 ||
+	    (area->sx + area->width) > p->var.xres_virtual ||
+	    (area->sy + area->height) > p->var.yres_virtual)
+		return;
+
+	if (area->dy < area->sy
+	    || (area->dy == area->sy && area->dx < area->sx)) {
+		/* start at the top */
+		src1 = p->screen_base + area->sy * linesize +
+		    ((area->sx * p->var.bits_per_pixel) >> 3);
+		dst1 = p->screen_base + area->dy * linesize +
+		    ((area->dx * p->var.bits_per_pixel) >> 3);
+		lineincr = linesize;
+	} else {
+		/* start at the bottom */
+		src1 = p->screen_base + (area->sy + area->height-1) * linesize
+			+ (((area->sx + area->width - 1) * p->var.bits_per_pixel) >> 3);
+		dst1 = p->screen_base + (area->dy + area->height-1) * linesize
+			+ (((area->dx + area->width - 1) * p->var.bits_per_pixel) >> 3);
+		lineincr = -linesize;
+	}
+
+	if ((BITS_PER_LONG % p->var.bits_per_pixel) == 0) {
+		int ppw = BITS_PER_LONG / p->var.bits_per_pixel;
+		int n = ((area->width * p->var.bits_per_pixel) >> 3);
+
+		start_index = ((unsigned long) src1 & (bpl - 1));
+		end_index = ((unsigned long) (src1 + n) & (bpl - 1));
+		shift = ((unsigned long) dst1 & (bpl - 1)) -
+		    	((unsigned long) src1 & (bpl - 1));
+		start_mask = end_mask = 0;
+
+		if (start_index) {
+			start_mask = -1 >> (start_index << 3);
+			n -= (bpl - start_index);
+		}
+
+		if (end_index) {
+			end_mask = -1 << ((bpl - end_index) << 3);
+			n -= end_index;
+		}
+		n = n / bpl;
+
+		if (n <= 0) {
+			if (start_mask) {
+				if (end_mask)
+					end_mask &= start_mask;
+				else
+					end_mask = start_mask;
+				start_mask = 0;
+			}
+			n = 0;
+		}
+
+		if (shift) {
+			if (shift > 0) {
+				/* dest is over to right more */
+				shift_right =
+				    shift * p->var.bits_per_pixel;
+				shift_left =
+				    (ppw - shift) * p->var.bits_per_pixel;
+			} else {
+				/* source is to the right more */
+				shift_right =
+				    (ppw + shift) * p->var.bits_per_pixel;
+				shift_left =
+				    -shift * p->var.bits_per_pixel;
+			}
+			/* general case, positive increment */
+			if (lineincr > 0) {
+				if (shift < 0)
+					n++;
+				do {
+					dst = (unsigned long *) dst1;
+					src = (unsigned long *) src1;
+
+					last = (fb_readl(src) & start_mask);
+
+					if (shift > 0)
+						fb_writel(fb_readl(dst) | (last >> shift_right), dst);
+					for (j = 0; j < n; j++) {
+						dst++;
+						tmp = fb_readl(src);
+						src++;
+						fb_writel((last << shift_left) | (tmp >> shift_right), dst);
+						last = tmp;
+						src++;
+					}
+					fb_writel(fb_readl(dst) | (last << shift_left), dst);
+					src1 += lineincr;
+					dst1 += lineincr;
+				} while (--height);
+			} else {
+				/* general case, negative increment */
+				if (shift > 0)
+					n++;
+				do {
+					dst = (unsigned long *) dst1;
+					src = (unsigned long *) src1;
+
+					last = (fb_readl(src) & end_mask);
+
+					if (shift < 0)
+						fb_writel(fb_readl(dst) | (last >> shift_right), dst);
+					for (j = 0; j < n; j++) {
+						dst--;
+						tmp = fb_readl(src);
+						src--;
+						fb_writel((tmp << shift_left) | (last >> shift_right), dst);
+						last = tmp;
+						src--;
+					}
+					fb_writel(fb_readl(dst) | (last >> shift_right), dst);
+					src1 += lineincr;
+					dst1 += lineincr;
+				} while (--height);
+			}
+		} else {
+			/* no shift needed */
+			if (lineincr > 0) {
+				/* positive increment */
+				do {
+					dst = (unsigned long *) (dst1 - start_index);
+					src = (unsigned long *) (src1 - start_index);
+
+					if (start_mask)
+						fb_writel(fb_readl(src) | start_mask, dst);
+
+					for (j = 0; j < n; j++) {
+						fb_writel(fb_readl(src), dst);
+						dst++;
+						src++;
+					}
+
+					if (end_mask)
+						fb_writel(fb_readl(src) | end_mask, dst);
+					src1 += lineincr;
+					dst1 += lineincr;
+				} while (--height);
+			} else {
+				/* negative increment */
+				do {
+					dst = (unsigned long *) dst1;
+					src = (unsigned long *) src1;
+
+					if (start_mask)
+						fb_writel(fb_readl(src) | start_mask, dst);
+					for (j = 0; j < n; j++) {
+						fb_writel(fb_readl(src), dst);
+						dst--;
+						src--;
+					}
+					src1 += lineincr;
+					dst1 += lineincr;
+				} while (--height);
+			}
+		}
+	}
+}

drivers/video/cfbfillrect.c

+/*
+ *  Generic fillrect for frame buffers with packed pixels of any depth. 
+ *
+ *      Copyright (C)  2000 James Simmons (jsimmons@linux-fbdev.org) 
+ *
+ *  This file is subject to the terms and conditions of the GNU General Public
+ *  License.  See the file COPYING in the main directory of this archive for
+ *  more details.
+ *
+ * NOTES:
+ *
+ *  The code for depths like 24 that don't have integer number of pixels per 
+ *  long is broken and needs to be fixed. For now I turned these types of 
+ *  mode off.
+ *
+ *  Also need to add code to deal with cards endians that are different than
+ *  the native cpu endians. I also need to deal with MSB position in the word.
+ *
+ */
+#include <linux/string.h>
+#include <linux/fb.h>
+#include <asm/types.h>
+#include <video/fbcon.h>
+
+void cfb_fillrect(struct fb_info *p, struct fb_fillrect *rect)
+{
+	unsigned long start_index, end_index, start_mask = 0, end_mask = 0;
+	unsigned long height, ppw, fg, fgcolor;
+	int i, n, x2, y2, linesize = p->fix.line_length;
+	int bpl = sizeof(unsigned long);
+	unsigned long *dst;
+	char *dst1;
+
+	if (!rect->width || !rect->height)
+		return;
+
+	/* We could use hardware clipping but on many cards you get around
+	 * hardware clipping by writing to framebuffer directly. */
+	x2 = rect->dx + rect->width;
+	y2 = rect->dy + rect->height;
+	x2 = x2 < p->var.xres_virtual ? x2 : p->var.xres_virtual;
+	y2 = y2 < p->var.yres_virtual ? y2 : p->var.yres_virtual;
+	rect->width = x2 - rect->dx;
+	height = y2 - rect->dy;
+
+	/* Size of the scanline in bytes */
+	n = (rect->width * (p->var.bits_per_pixel >> 3));
+	ppw = BITS_PER_LONG / p->var.bits_per_pixel;
+
+	dst1 = p->screen_base + (rect->dy * linesize) +
+	    	(rect->dx * (p->var.bits_per_pixel >> 3));
+	start_index = ((unsigned long) dst1 & (bpl - 1));
+	end_index = ((unsigned long) (dst1 + n) & (bpl - 1));
+
+	if (p->fix.visual == FB_VISUAL_TRUECOLOR)
+		fg = fgcolor = ((u32 *) (p->pseudo_palette))[rect->color];
+	else
+		fg = fgcolor = rect->color;
+
+	for (i = 0; i < ppw - 1; i++) {
+		fg <<= p->var.bits_per_pixel;
+		fg |= fgcolor;
+	}
+
+	if (start_index) {
+		start_mask = fg << (start_index << 3);
+		n -= (bpl - start_index);
+	}
+
+	if (end_index) {
+		end_mask = fg >> ((bpl - end_index) << 3);
+		n -= end_index;
+	}
+
+	n = n / bpl;
+
+	if (n <= 0) {
+		if (start_mask) {
+			if (end_mask)
+				end_mask &= start_mask;
+			else
+				end_mask = start_mask;
+			start_mask = 0;
+		}
+		n = 0;
+	}
+
+	if ((BITS_PER_LONG % p->var.bits_per_pixel) == 0) {
+		switch (rect->rop) {
+		case ROP_COPY:
+			do {
+				/* Word align to increases performace :-) */
+				dst = (unsigned long *) (dst1 - start_index);
+
+				if (start_mask) {
+#if BITS_PER_LONG == 32
+					fb_writel(fb_readl(dst) |
+						  start_mask, dst);
+#else
+					fb_writeq(fb_readq(dst) |
+						  start_mask, dst);
+#endif
+					dst++;
+				}
+
+				for (i = 0; i < n; i++) {
+#if BITS_PER_LONG == 32
+					fb_writel(fg, dst);
+#else
+					fb_writeq(fg, dst);
+#endif
+					dst++;
+				}
+
+				if (end_mask)
+#if BITS_PER_LONG == 32
+					fb_writel(fb_readl(dst) | end_mask,
+						  dst);
+#else
+					fb_writeq(fb_readq(dst) | end_mask,
+						  dst);
+#endif
+				dst1 += linesize;
+			} while (--height);
+			break;
+		case ROP_XOR:
+			do {
+				dst = (unsigned long *) (dst1 - start_index);
+
+				if (start_mask) {
+#if BITS_PER_LONG == 32
+					fb_writel(fb_readl(dst) ^
+						  start_mask, dst);
+#else
+					fb_writeq(fb_readq(dst) ^
+						  start_mask, dst);
+#endif
+					dst++;
+				}
+
+				for (i = 0; i < n; i++) {
+#if BITS_PER_LONG == 32
+					fb_writel(fb_readl(dst) ^ fg, dst);
+#else
+					fb_writeq(fb_readq(dst) ^ fg, dst);
+#endif
+					dst++;
+				}
+
+				if (end_mask) {
+#if BITS_PER_LONG == 32
+					fb_writel(fb_readl(dst) ^ end_mask,
+						  dst);
+#else
+					fb_writeq(fb_readq(dst) ^ end_mask,
+						  dst);
+#endif
+				}
+				dst1 += linesize;
+			} while (--height);
+			break;
+		}
+	} else {
+		/* Odd modes like 24 or 80 bits per pixel */
+		start_mask = fg >> (start_index * p->var.bits_per_pixel);
+		end_mask = fg << (end_index * p->var.bits_per_pixel);
+		/* start_mask =& PFILL24(x1,fg);
+		   end_mask_or = end_mask & PFILL24(x1+width-1,fg); */
+
+		n = (rect->width - start_index - end_index) / ppw;
+
+		switch (rect->rop) {
+		case ROP_COPY:
+			do {
+				dst = (unsigned long *) dst1;
+				if (start_mask)
+					*dst |= start_mask;
+				if ((start_index + rect->width) > ppw)
+					dst++;
+
+				/* XXX: slow */
+				for (i = 0; i < n; i++) {
+					*dst++ = fg;
+				}
+				if (end_mask)
+					*dst |= end_mask;
+				dst1 += linesize;
+			} while (--height);
+			break;
+		case ROP_XOR:
+			do {
+				dst = (unsigned long *) dst1;
+				if (start_mask)
+					*dst ^= start_mask;
+				if ((start_mask + rect->width) > ppw)
+					dst++;
+
+				for (i = 0; i < n; i++) {
+					*dst++ ^= fg;	/* PFILL24(fg,x1+i); */
+				}
+				if (end_mask)
+					*dst ^= end_mask;
+				dst1 += linesize;
+			} while (--height);
+			break;
+		}
+	}
+	return;
+}

drivers/video/cfbimgblt.c

+/*
+ *  Generic BitBLT function for frame buffer with packed pixels of any depth.
+ *
+ *      Copyright (C)  June 1999 James Simmons
+ *
+ *  This file is subject to the terms and conditions of the GNU General Public
+ *  License.  See the file COPYING in the main directory of this archive for
+ *  more details.
+ *
+ * NOTES:
+ *
+ *    This function copys a image from system memory to video memory. The
+ *  image can be a bitmap where each 0 represents the background color and
+ *  each 1 represents the foreground color. Great for font handling. It can
+ *  also be a color image. This is determined by image_depth. The color image
+ *  must be laid out exactly in the same format as the framebuffer. Yes I know
+ *  their are cards with hardware that coverts images of various depths to the
+ *  framebuffer depth. But not every card has this. All images must be rounded
+ *  up to the nearest byte. For example a bitmap 12 bits wide must be two 
+ *  bytes width. 
+ *
+ *  FIXME
+ *  The code for 24 bit is horrible. It copies byte by byte size instead of
+ *  longs like the other sizes. Needs to be optimized.
+ *
+ *  Also need to add code to deal with cards endians that are different than
+ *  the native cpu endians. I also need to deal with MSB position in the word.
+ *
+ */
+#include <linux/string.h>
+#include <linux/fb.h>
+#include <asm/types.h>
+
+#include <video/fbcon.h>
+
+#define DEBUG
+
+#ifdef DEBUG
+#define DPRINTK(fmt, args...) printk(KERN_DEBUG "%s: " fmt,__FUNCTION__,## args)
+#else
+#define DPRINTK(fmt, args...)
+#endif
+
+void cfb_imageblit(struct fb_info *p, struct fb_image *image)
+{
+	int pad, ppw, shift, shift_right, shift_left, x2, y2, n, i, j, k, l = 7;
+	unsigned long tmp = ~0 << (BITS_PER_LONG - p->var.bits_per_pixel);
+	unsigned long fgx, bgx, fgcolor, bgcolor, eorx;	
+	unsigned long end_index, end_mask, mask;
+	unsigned long *dst = NULL;
+	u8 *dst1, *src;
+
+	/* 
+	 * We could use hardware clipping but on many cards you get around hardware
+	 * clipping by writing to framebuffer directly like we are doing here. 
+	 */
+	x2 = image->dx + image->width;
+	y2 = image->dy + image->height;
+	image->dx = image->dx > 0 ? image->dx : 0;
+	image->dy = image->dy > 0 ? image->dy : 0;
+	x2 = x2 < p->var.xres_virtual ? x2 : p->var.xres_virtual;
+	y2 = y2 < p->var.yres_virtual ? y2 : p->var.yres_virtual;
+	image->width  = x2 - image->dx;
+	image->height = y2 - image->dy;
+  
+	dst1 = p->screen_base + image->dy * p->fix.line_length + 
+		((image->dx * p->var.bits_per_pixel) >> 3);
+  
+	ppw = BITS_PER_LONG/p->var.bits_per_pixel;
+
+	src = image->data;	
+
+	if (p->fix.visual == FB_VISUAL_TRUECOLOR) {
+		fgx = fgcolor = ((u32 *)(p->pseudo_palette))[image->fg_color];
+		bgx = bgcolor = ((u32 *)(p->pseudo_palette))[image->bg_color];
+	} else {
+		fgx = fgcolor = image->fg_color;
+		bgx = bgcolor = image->bg_color;
+	}	
+ 
+	for (i = 0; i < ppw-1; i++) {
+		fgx <<= p->var.bits_per_pixel;
+		bgx <<= p->var.bits_per_pixel;
+		fgx |= fgcolor;
+		bgx |= bgcolor;
+	}
+	eorx = fgx ^ bgx;
+	n = ((image->width + 7) >> 3);
+	pad = (n << 3) - image->width;
+
+	for (i = 0; i < image->height; i++) {
+		dst = (unsigned long *) dst1;
+		
+		for (j = image->width/ppw; j > 0; j--) {
+			mask = 0;
+		
+			for (k = ppw; k > 0; k--) {	
+				if (test_bit(l, src))
+					mask |= (tmp >> (p->var.bits_per_pixel*(k-1)));
+				l--;
+				if (l < 0) { l = 7; src++; }
+			}
+			fb_writel((mask & eorx)^bgx, dst);
+			dst++;
+		}
+		l =- pad;		
+		dst1 += p->fix.line_length;	
+	}	
+}