[linux.git] / 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. 
 *
 *  Tony: 
 *  Incorporate mask tables similar to fbcon-cfb*.c in 2.4 API.  This speeds 
 *  up the code significantly.
 *  
 *  Code for depths not multiples of BITS_PER_LONG is still kludgy, which is
 *  still processed a bit at a time.   
 *
 *  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/module.h>
#include <linux/string.h>
#include <linux/fb.h>
#include <asm/types.h>
#include "fb_draw.h"

#define DEBUG

#ifdef DEBUG
#define DPRINTK(fmt, args...) printk(KERN_DEBUG "%s: " fmt,__func__,## args)
#else
#define DPRINTK(fmt, args...)
#endif

static const u32 cfb_tab8_be[] = {
    0x00000000,0x000000ff,0x0000ff00,0x0000ffff,
    0x00ff0000,0x00ff00ff,0x00ffff00,0x00ffffff,
    0xff000000,0xff0000ff,0xff00ff00,0xff00ffff,
    0xffff0000,0xffff00ff,0xffffff00,0xffffffff
};

static const u32 cfb_tab8_le[] = {
    0x00000000,0xff000000,0x00ff0000,0xffff0000,
    0x0000ff00,0xff00ff00,0x00ffff00,0xffffff00,
    0x000000ff,0xff0000ff,0x00ff00ff,0xffff00ff,
    0x0000ffff,0xff00ffff,0x00ffffff,0xffffffff
};

static const u32 cfb_tab16_be[] = {
    0x00000000, 0x0000ffff, 0xffff0000, 0xffffffff
};

static const u32 cfb_tab16_le[] = {
    0x00000000, 0xffff0000, 0x0000ffff, 0xffffffff
};

static const u32 cfb_tab32[] = {
	0x00000000, 0xffffffff
};

#define FB_WRITEL fb_writel
#define FB_READL  fb_readl

static inline void color_imageblit(const struct fb_image *image, 
				   struct fb_info *p, u8 __iomem *dst1, 
				   u32 start_index,
				   u32 pitch_index)
{
	/* Draw the penguin */
	u32 __iomem *dst, *dst2;
	u32 color = 0, val, shift;
	int i, n, bpp = p->var.bits_per_pixel;
	u32 null_bits = 32 - bpp;
	u32 *palette = (u32 *) p->pseudo_palette;
	const u8 *src = image->data;
	u32 bswapmask = fb_compute_bswapmask(p);

	dst2 = (u32 __iomem *) dst1;
	for (i = image->height; i--; ) {
		n = image->width;
		dst = (u32 __iomem *) dst1;
		shift = 0;
		val = 0;
		
		if (start_index) {
			u32 start_mask = ~fb_shifted_pixels_mask_u32(p,
						start_index, bswapmask);
			val = FB_READL(dst) & start_mask;
			shift = start_index;
		}
		while (n--) {
			if (p->fix.visual == FB_VISUAL_TRUECOLOR ||
			    p->fix.visual == FB_VISUAL_DIRECTCOLOR )
				color = palette[*src];
			else
				color = *src;
			color <<= FB_LEFT_POS(p, bpp);
			val |= FB_SHIFT_HIGH(p, color, shift ^ bswapmask);
			if (shift >= null_bits) {
				FB_WRITEL(val, dst++);
	
				val = (shift == null_bits) ? 0 : 
					FB_SHIFT_LOW(p, color, 32 - shift);
			}
			shift += bpp;
			shift &= (32 - 1);
			src++;
		}
		if (shift) {
			u32 end_mask = fb_shifted_pixels_mask_u32(p, shift,
						bswapmask);

			FB_WRITEL((FB_READL(dst) & end_mask) | val, dst);
		}
		dst1 += p->fix.line_length;
		if (pitch_index) {
			dst2 += p->fix.line_length;
			dst1 = (u8 __iomem *)((long __force)dst2 & ~(sizeof(u32) - 1));

			start_index += pitch_index;
			start_index &= 32 - 1;
		}
	}
}

static inline void slow_imageblit(const struct fb_image *image, struct fb_info *p, 
				  u8 __iomem *dst1, u32 fgcolor,
				  u32 bgcolor, 
				  u32 start_index,
				  u32 pitch_index)
{
	u32 shift, color = 0, bpp = p->var.bits_per_pixel;
	u32 __iomem *dst, *dst2;
	u32 val, pitch = p->fix.line_length;
	u32 null_bits = 32 - bpp;
	u32 spitch = (image->width+7)/8;
	const u8 *src = image->data, *s;
	u32 i, j, l;
	u32 bswapmask = fb_compute_bswapmask(p);

	dst2 = (u32 __iomem *) dst1;
	fgcolor <<= FB_LEFT_POS(p, bpp);
	bgcolor <<= FB_LEFT_POS(p, bpp);

	for (i = image->height; i--; ) {
		shift = val = 0;
		l = 8;
		j = image->width;
		dst = (u32 __iomem *) dst1;
		s = src;

		/* write leading bits */
		if (start_index) {
			u32 start_mask = ~fb_shifted_pixels_mask_u32(p,
						start_index, bswapmask);
			val = FB_READL(dst) & start_mask;
			shift = start_index;
		}

		while (j--) {
			l--;
			color = (*s & (1 << l)) ? fgcolor : bgcolor;
			val |= FB_SHIFT_HIGH(p, color, shift ^ bswapmask);
			
			/* Did the bitshift spill bits to the next long? */
			if (shift >= null_bits) {
				FB_WRITEL(val, dst++);
				val = (shift == null_bits) ? 0 :
					FB_SHIFT_LOW(p, color, 32 - shift);
			}
			shift += bpp;
			shift &= (32 - 1);
			if (!l) { l = 8; s++; };
		}

		/* write trailing bits */
 		if (shift) {
			u32 end_mask = fb_shifted_pixels_mask_u32(p, shift,
						bswapmask);

			FB_WRITEL((FB_READL(dst) & end_mask) | val, dst);
		}
		
		dst1 += pitch;
		src += spitch;	
		if (pitch_index) {
			dst2 += pitch;
			dst1 = (u8 __iomem *)((long __force)dst2 & ~(sizeof(u32) - 1));
			start_index += pitch_index;
			start_index &= 32 - 1;
		}
		
	}
}

/*
 * fast_imageblit - optimized monochrome color expansion
 *
 * Only if:  bits_per_pixel == 8, 16, or 32
 *           image->width is divisible by pixel/dword (ppw);
 *           fix->line_legth is divisible by 4;
 *           beginning and end of a scanline is dword aligned
 */
static inline void fast_imageblit(const struct fb_image *image, struct fb_info *p, 
				  u8 __iomem *dst1, u32 fgcolor, 
				  u32 bgcolor) 
{
	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;
	const char *s = image->data, *src;
	u32 __iomem *dst;
	const u32 *tab = NULL;
	int i, j, k;

	switch (bpp) {
	case 8:
		tab = fb_be_math(p) ? cfb_tab8_be : cfb_tab8_le;
		break;
	case 16:
		tab = fb_be_math(p) ? cfb_tab16_be : cfb_tab16_le;
		break;
	case 32:
	default:
		tab = cfb_tab32;
		break;
	}

	for (i = ppw-1; i--; ) {
		fgx <<= bpp;
		bgx <<= bpp;
		fgx |= fgcolor;
		bgx |= bgcolor;
	}
	
	bit_mask = (1 << ppw) - 1;
	eorx = fgx ^ bgx;
	k = image->width/ppw;

	for (i = image->height; i--; ) {
		dst = (u32 __iomem *) dst1, shift = 8; src = s;
		
		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++; }		
		}
		dst1 += p->fix.line_length;
		s += spitch;
	}
}	
	
void cfb_imageblit(struct fb_info *p, const struct fb_image *image)
{
	u32 fgcolor, bgcolor, start_index, bitstart, pitch_index = 0;
	u32 bpl = sizeof(u32), bpp = p->var.bits_per_pixel;
	u32 width = image->width;
	u32 dx = image->dx, dy = image->dy;
	u8 __iomem *dst1;

	if (p->state != FBINFO_STATE_RUNNING)
		return;

	bitstart = (dy * p->fix.line_length * 8) + (dx * bpp);
	start_index = bitstart & (32 - 1);
	pitch_index = (p->fix.line_length & (bpl - 1)) * 8;

	bitstart /= 8;
	bitstart &= ~(bpl - 1);
	dst1 = p->screen_base + bitstart;

	if (p->fbops->fb_sync)
		p->fbops->fb_sync(p);

	if (image->depth == 1) {
		if (p->fix.visual == FB_VISUAL_TRUECOLOR ||
		    p->fix.visual == FB_VISUAL_DIRECTCOLOR) {
			fgcolor = ((u32*)(p->pseudo_palette))[image->fg_color];
			bgcolor = ((u32*)(p->pseudo_palette))[image->bg_color];
		} else {
			fgcolor = image->fg_color;
			bgcolor = image->bg_color;
		}	
		
		if (32 % bpp == 0 && !start_index && !pitch_index && 
		    ((width & (32/bpp-1)) == 0) &&
		    bpp >= 8 && bpp <= 32) 			
			fast_imageblit(image, p, dst1, fgcolor, bgcolor);
		else 
			slow_imageblit(image, p, dst1, fgcolor, bgcolor,
					start_index, pitch_index);
	} else
		color_imageblit(image, p, dst1, start_index, pitch_index);
}

EXPORT_SYMBOL(cfb_imageblit);

MODULE_AUTHOR("James Simmons <[email protected]>");
MODULE_DESCRIPTION("Generic software accelerated imaging drawing");
MODULE_LICENSE("GPL");
Commit	Line	Data
1da177e4 LT	1	/*
	2	* Generic BitBLT function for frame buffer with packed pixels of any depth.
	3	*
	4	* Copyright (C) June 1999 James Simmons
	5	*
	6	* This file is subject to the terms and conditions of the GNU General Public
	7	* License. See the file COPYING in the main directory of this archive for
	8	* more details.
	9	*
	10	* NOTES:
	11	*
	12	* This function copys a image from system memory to video memory. The
	13	* image can be a bitmap where each 0 represents the background color and
	14	* each 1 represents the foreground color. Great for font handling. It can
	15	* also be a color image. This is determined by image_depth. The color image
	16	* must be laid out exactly in the same format as the framebuffer. Yes I know
	17	* their are cards with hardware that coverts images of various depths to the
	18	* framebuffer depth. But not every card has this. All images must be rounded
	19	* up to the nearest byte. For example a bitmap 12 bits wide must be two
	20	* bytes width.
	21	*
	22	* Tony:
	23	* Incorporate mask tables similar to fbcon-cfb*.c in 2.4 API. This speeds
	24	* up the code significantly.
	25	*
	26	* Code for depths not multiples of BITS_PER_LONG is still kludgy, which is
	27	* still processed a bit at a time.
	28	*
	29	* Also need to add code to deal with cards endians that are different than
	30	* the native cpu endians. I also need to deal with MSB position in the word.
	31	*/
1da177e4 LT	32	#include <linux/module.h>
	33	#include <linux/string.h>
	34	#include <linux/fb.h>
	35	#include <asm/types.h>
779121e9	36	#include "fb_draw.h"
1da177e4 LT	37
	38	#define DEBUG
	39
	40	#ifdef DEBUG
5ae12170	41	#define DPRINTK(fmt, args...) printk(KERN_DEBUG "%s: " fmt,__func__,## args)
1da177e4 LT	42	#else
	43	#define DPRINTK(fmt, args...)
	44	#endif
	45
e4c690e0	46	static const u32 cfb_tab8_be[] = {
1da177e4 LT	47	0x00000000,0x000000ff,0x0000ff00,0x0000ffff,
	48	0x00ff0000,0x00ff00ff,0x00ffff00,0x00ffffff,
	49	0xff000000,0xff0000ff,0xff00ff00,0xff00ffff,
	50	0xffff0000,0xffff00ff,0xffffff00,0xffffffff
e4c690e0 AV	51	};
	52
	53	static const u32 cfb_tab8_le[] = {
1da177e4 LT	54	0x00000000,0xff000000,0x00ff0000,0xffff0000,
	55	0x0000ff00,0xff00ff00,0x00ffff00,0xffffff00,
	56	0x000000ff,0xff0000ff,0x00ff00ff,0xffff00ff,
	57	0x0000ffff,0xff00ffff,0x00ffffff,0xffffffff
1da177e4 LT	58	};
1da177e4 LT	59
e4c690e0	60	static const u32 cfb_tab16_be[] = {
1da177e4	61	0x00000000, 0x0000ffff, 0xffff0000, 0xffffffff
e4c690e0 AV	62	};
	63
	64	static const u32 cfb_tab16_le[] = {
1da177e4	65	0x00000000, 0xffff0000, 0x0000ffff, 0xffffffff
1da177e4 LT	66	};
1da177e4 LT	67
d95159cf	68	static const u32 cfb_tab32[] = {
1da177e4 LT	69	0x00000000, 0xffffffff
	70	};
	71
	72	#define FB_WRITEL fb_writel
	73	#define FB_READL fb_readl
	74
1da177e4 LT	75	static inline void color_imageblit(const struct fb_image *image,
	76	struct fb_info p, u8 __iomem dst1,
	77	u32 start_index,
	78	u32 pitch_index)
	79	{
	80	/* Draw the penguin */
	81	u32 __iomem dst, dst2;
	82	u32 color = 0, val, shift;
	83	int i, n, bpp = p->var.bits_per_pixel;
	84	u32 null_bits = 32 - bpp;
	85	u32 palette = (u32 ) p->pseudo_palette;
	86	const u8 *src = image->data;
779121e9	87	u32 bswapmask = fb_compute_bswapmask(p);
1da177e4 LT	88
	89	dst2 = (u32 __iomem *) dst1;
	90	for (i = image->height; i--; ) {
	91	n = image->width;
	92	dst = (u32 __iomem *) dst1;
	93	shift = 0;
	94	val = 0;
	95
	96	if (start_index) {
e4c690e0 AV	97	u32 start_mask = ~fb_shifted_pixels_mask_u32(p,
e4c690e0 AV	98	start_index, bswapmask);
1da177e4 LT	99	val = FB_READL(dst) & start_mask;
	100	shift = start_index;
	101	}
	102	while (n--) {
	103	if (p->fix.visual == FB_VISUAL_TRUECOLOR \|\|
	104	p->fix.visual == FB_VISUAL_DIRECTCOLOR )
	105	color = palette[*src];
	106	else
	107	color = *src;
e4c690e0 AV	108	color <<= FB_LEFT_POS(p, bpp);
e4c690e0 AV	109	val \|= FB_SHIFT_HIGH(p, color, shift ^ bswapmask);
1da177e4 LT	110	if (shift >= null_bits) {
	111	FB_WRITEL(val, dst++);
	112
	113	val = (shift == null_bits) ? 0 :
e4c690e0	114	FB_SHIFT_LOW(p, color, 32 - shift);
1da177e4 LT	115	}
	116	shift += bpp;
	117	shift &= (32 - 1);
	118	src++;
	119	}
	120	if (shift) {
e4c690e0 AV	121	u32 end_mask = fb_shifted_pixels_mask_u32(p, shift,
e4c690e0 AV	122	bswapmask);
1da177e4 LT	123
	124	FB_WRITEL((FB_READL(dst) & end_mask) \| val, dst);
	125	}
	126	dst1 += p->fix.line_length;
	127	if (pitch_index) {
	128	dst2 += p->fix.line_length;
	129	dst1 = (u8 __iomem *)((long __force)dst2 & ~(sizeof(u32) - 1));
	130
	131	start_index += pitch_index;
	132	start_index &= 32 - 1;
	133	}
	134	}
	135	}
	136
	137	static inline void slow_imageblit(const struct fb_image image, struct fb_info p,
	138	u8 __iomem *dst1, u32 fgcolor,
	139	u32 bgcolor,
	140	u32 start_index,
	141	u32 pitch_index)
	142	{
	143	u32 shift, color = 0, bpp = p->var.bits_per_pixel;
	144	u32 __iomem dst, dst2;
	145	u32 val, pitch = p->fix.line_length;
	146	u32 null_bits = 32 - bpp;
	147	u32 spitch = (image->width+7)/8;
	148	const u8 src = image->data, s;
	149	u32 i, j, l;
779121e9 PP	150	u32 bswapmask = fb_compute_bswapmask(p);
779121e9 PP	151
1da177e4	152	dst2 = (u32 __iomem *) dst1;
e4c690e0 AV	153	fgcolor <<= FB_LEFT_POS(p, bpp);
e4c690e0 AV	154	bgcolor <<= FB_LEFT_POS(p, bpp);
1da177e4 LT	155
	156	for (i = image->height; i--; ) {
	157	shift = val = 0;
	158	l = 8;
	159	j = image->width;
	160	dst = (u32 __iomem *) dst1;
	161	s = src;
	162
	163	/* write leading bits */
	164	if (start_index) {
e4c690e0 AV	165	u32 start_mask = ~fb_shifted_pixels_mask_u32(p,
e4c690e0 AV	166	start_index, bswapmask);
1da177e4 LT	167	val = FB_READL(dst) & start_mask;
	168	shift = start_index;
	169	}
	170
	171	while (j--) {
	172	l--;
a536093a	173	color = (*s & (1 << l)) ? fgcolor : bgcolor;
e4c690e0	174	val \|= FB_SHIFT_HIGH(p, color, shift ^ bswapmask);
1da177e4 LT	175
	176	/* Did the bitshift spill bits to the next long? */
	177	if (shift >= null_bits) {
	178	FB_WRITEL(val, dst++);
	179	val = (shift == null_bits) ? 0 :
e4c690e0	180	FB_SHIFT_LOW(p, color, 32 - shift);
1da177e4 LT	181	}
	182	shift += bpp;
	183	shift &= (32 - 1);
	184	if (!l) { l = 8; s++; };
	185	}
	186
	187	/* write trailing bits */
	188	if (shift) {
e4c690e0 AV	189	u32 end_mask = fb_shifted_pixels_mask_u32(p, shift,
e4c690e0 AV	190	bswapmask);
1da177e4 LT	191
	192	FB_WRITEL((FB_READL(dst) & end_mask) \| val, dst);
	193	}
	194
	195	dst1 += pitch;
	196	src += spitch;
	197	if (pitch_index) {
	198	dst2 += pitch;
	199	dst1 = (u8 __iomem *)((long __force)dst2 & ~(sizeof(u32) - 1));
	200	start_index += pitch_index;
	201	start_index &= 32 - 1;
	202	}
	203
	204	}
	205	}
	206
	207	/*
	208	* fast_imageblit - optimized monochrome color expansion
	209	*
	210	* Only if: bits_per_pixel == 8, 16, or 32
	211	* image->width is divisible by pixel/dword (ppw);
	212	* fix->line_legth is divisible by 4;
	213	* beginning and end of a scanline is dword aligned
	214	*/
	215	static inline void fast_imageblit(const struct fb_image image, struct fb_info p,
	216	u8 __iomem *dst1, u32 fgcolor,
	217	u32 bgcolor)
	218	{
	219	u32 fgx = fgcolor, bgx = bgcolor, bpp = p->var.bits_per_pixel;
	220	u32 ppw = 32/bpp, spitch = (image->width + 7)/8;
	221	u32 bit_mask, end_mask, eorx, shift;
	222	const char s = image->data, src;
	223	u32 __iomem *dst;
d95159cf	224	const u32 *tab = NULL;
1da177e4	225	int i, j, k;
e4c690e0	226
1da177e4 LT	227	switch (bpp) {
1da177e4 LT	228	case 8:
e4c690e0	229	tab = fb_be_math(p) ? cfb_tab8_be : cfb_tab8_le;
1da177e4 LT	230	break;
1da177e4 LT	231	case 16:
e4c690e0	232	tab = fb_be_math(p) ? cfb_tab16_be : cfb_tab16_le;
1da177e4 LT	233	break;
1da177e4 LT	234	case 32:
8126a044	235	default:
1da177e4 LT	236	tab = cfb_tab32;
	237	break;
	238	}
	239
	240	for (i = ppw-1; i--; ) {
	241	fgx <<= bpp;
	242	bgx <<= bpp;
	243	fgx \|= fgcolor;
	244	bgx \|= bgcolor;
	245	}
	246
	247	bit_mask = (1 << ppw) - 1;
	248	eorx = fgx ^ bgx;
	249	k = image->width/ppw;
	250
	251	for (i = image->height; i--; ) {
	252	dst = (u32 __iomem *) dst1, shift = 8; src = s;
	253
	254	for (j = k; j--; ) {
	255	shift -= ppw;
	256	end_mask = tab[(*src >> shift) & bit_mask];
	257	FB_WRITEL((end_mask & eorx)^bgx, dst++);
	258	if (!shift) { shift = 8; src++; }
	259	}
	260	dst1 += p->fix.line_length;
	261	s += spitch;
	262	}
	263	}
	264
	265	void cfb_imageblit(struct fb_info p, const struct fb_image image)
	266	{
	267	u32 fgcolor, bgcolor, start_index, bitstart, pitch_index = 0;
	268	u32 bpl = sizeof(u32), bpp = p->var.bits_per_pixel;
b4d8aea6	269	u32 width = image->width;
1da177e4	270	u32 dx = image->dx, dy = image->dy;
1da177e4 LT	271	u8 __iomem *dst1;
	272
	273	if (p->state != FBINFO_STATE_RUNNING)
	274	return;
	275
1da177e4 LT	276	bitstart = (dy * p->fix.line_length * 8) + (dx * bpp);
	277	start_index = bitstart & (32 - 1);
	278	pitch_index = (p->fix.line_length & (bpl - 1)) * 8;
	279
	280	bitstart /= 8;
	281	bitstart &= ~(bpl - 1);
	282	dst1 = p->screen_base + bitstart;
	283
	284	if (p->fbops->fb_sync)
	285	p->fbops->fb_sync(p);
	286
	287	if (image->depth == 1) {
	288	if (p->fix.visual == FB_VISUAL_TRUECOLOR \|\|
	289	p->fix.visual == FB_VISUAL_DIRECTCOLOR) {
	290	fgcolor = ((u32*)(p->pseudo_palette))[image->fg_color];
	291	bgcolor = ((u32*)(p->pseudo_palette))[image->bg_color];
	292	} else {
	293	fgcolor = image->fg_color;
	294	bgcolor = image->bg_color;
	295	}
	296
	297	if (32 % bpp == 0 && !start_index && !pitch_index &&
	298	((width & (32/bpp-1)) == 0) &&
	299	bpp >= 8 && bpp <= 32)
	300	fast_imageblit(image, p, dst1, fgcolor, bgcolor);
	301	else
	302	slow_imageblit(image, p, dst1, fgcolor, bgcolor,
	303	start_index, pitch_index);
	304	} else
	305	color_imageblit(image, p, dst1, start_index, pitch_index);
	306	}
	307
	308	EXPORT_SYMBOL(cfb_imageblit);
	309
	310	MODULE_AUTHOR("James Simmons <[email protected]>");
	311	MODULE_DESCRIPTION("Generic software accelerated imaging drawing");
	312	MODULE_LICENSE("GPL");
	313