From: James S. <jsi...@in...> - 2004-04-14 18:45:59
|
Hi folks!!! I have been quite recently because I have been working on fixing cfb_imageblit. It had some nasty bugs. I pounded out all the bugs except for drawinfonts like 12x222 Sun fonts. I haven't fixed the problem yet so if anyone wants to give it a shot here it is. /* * 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/config.h> #include <linux/module.h> #include <linux/string.h> #include <linux/fb.h> #include <asm/byteorder.h> #include <asm/types.h> #define DEBUG #ifdef DEBUG #define DPRINTK(fmt, args...) printk(KERN_DEBUG "%s: " fmt,__FUNCTION__,## args) #else #define DPRINTK(fmt, args...) #endif static u32 cfb_tab8[] = { #if defined(__BIG_ENDIAN) 0x00000000,0x000000ff,0x0000ff00,0x0000ffff, 0x00ff0000,0x00ff00ff,0x00ffff00,0x00ffffff, 0xff000000,0xff0000ff,0xff00ff00,0xff00ffff, 0xffff0000,0xffff00ff,0xffffff00,0xffffffff #elif defined(__LITTLE_ENDIAN) 0x00000000,0xff000000,0x00ff0000,0xffff0000, 0x0000ff00,0xff00ff00,0x00ffff00,0xffffff00, 0x000000ff,0xff0000ff,0x00ff00ff,0xffff00ff, 0x0000ffff,0xff00ffff,0x00ffffff,0xffffffff #else #error FIXME: No endianness?? #endif }; static u32 cfb_tab16[] = { #if defined(__BIG_ENDIAN) 0x00000000, 0x0000ffff, 0xffff0000, 0xffffffff #elif defined(__LITTLE_ENDIAN) 0x00000000, 0xffff0000, 0x0000ffff, 0xffffffff #else #error FIXME: No endianness?? #endif }; static u32 cfb_tab32[] = { 0x00000000, 0xffffffff }; #define FB_WRITEL fb_writel #define FB_READL fb_readl #define SHIFT_HIGH(val, bits) ((val) << (bits)) #define SHIFT_LOW(val, bits) ((val) >> (bits)) static inline void slow_imageblit(const struct fb_image *image, struct fb_info *p, u8 *dst1, u32 start_index, u32 pitch_index) { /* Draw the penguin */ int spitch = (image->width * image->depth + 7) >> 3; int scan_align = p->pixmap.scan_align - 1; u32 *dst, *dst2, color = 0, val, shift; int i, n, bpp = p->var.bits_per_pixel; u32 *palette = (u32 *) p->pseudo_palette; int bits = p->pixmap.access_align << 3; u32 null_bits = bits - bpp; const u32 *src = (const u32 *) image->data; int mask = (1 << image->depth) - 1; u32 l = bits - image->depth; spitch = (spitch + scan_align) & ~scan_align; dst2 = (u32 *) dst1; for (i = image->height; i--; ) { dst = (u32 *) dst1; shift = 0, val = 0; n = image->width; /* write leading bits */ if (start_index) { u32 start_mask = ~(SHIFT_HIGH(~(u32)0, start_index)); val = FB_READL(dst) & start_mask; shift -= start_index; } while (n--) { if (image->depth == 1) color = (be32_to_cpu(*src) & (1 << l)) ? image->fg_color : image->bg_color; else color = (be32_to_cpu(*src) & (mask << l)) >> l; if (p->fix.visual == FB_VISUAL_TRUECOLOR || p->fix.visual == FB_VISUAL_DIRECTCOLOR) color = palette[color]; val |= SHIFT_HIGH(color, shift); /* Did the bitshift spill bits into the next long? */ if (shift >= null_bits) { FB_WRITEL(val, dst++); val = (shift == null_bits) ? 0 : SHIFT_LOW(color, bits - shift); } shift += bpp; shift &= (bits - 1); if (!l) { src++; l = bits; } l -= image->depth; } l -= (8 - (image->width & 7)) * image->depth; /* write trailing bits */ if (shift) { u32 end_mask = SHIFT_HIGH(~(u32)0, shift); FB_WRITEL((FB_READL(dst) & end_mask) | val, dst); } dst1 += p->fix.line_length; if (pitch_index) { dst2 += p->fix.line_length; dst1 = (u8 *)((long)dst2 & ~(p->pixmap.access_align - 1)); start_index += pitch_index; start_index &= bits - 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 *dst1) { u32 fgx, fgcolor, bgx, bgcolor, bpp = p->var.bits_per_pixel; int bit_access = p->pixmap.access_align << 3; int scan_align = p->pixmap.scan_align - 1; int ppw = 32/bpp, spitch = (image->width + 7) >> 3; u32 bit_mask, end_mask, eorx, shift; const char *s = image->data, *src; u32 *dst, *tab = NULL; int i, j, k; spitch = (spitch + scan_align) & ~scan_align; if (p->fix.visual == FB_VISUAL_TRUECOLOR || p->fix.visual == FB_VISUAL_DIRECTCOLOR) { 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; } switch (bpp) { case 8: tab = cfb_tab8; break; case 16: tab = cfb_tab16; break; case 32: 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 * bpp)/bit_access; for (i = image->height; i--; ) { dst = (u32 *) 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 bpl = p->pixmap.access_align, bpp = p->var.bits_per_pixel; u32 width = image->width, height = image->height; u32 start_index, bitstart, pitch_index = 0; int x2, y2, vxres, vyres, bits = bpl << 3; u32 dx = image->dx, dy = image->dy; u8 *dst1; if (p->state != FBINFO_STATE_RUNNING) return; vxres = p->var.xres_virtual; vyres = p->var.yres_virtual; /* * We could use hardware clipping but on many cards you get around * hardware clipping by writing to framebuffer directly like we are * doing here. */ if (image->dx > vxres || image->dy > vyres) return; x2 = image->dx + image->width; y2 = image->dy + image->height; dx = image->dx > 0 ? image->dx : 0; dy = image->dy > 0 ? image->dy : 0; x2 = x2 < vxres ? x2 : vxres; y2 = y2 < vyres ? y2 : vyres; width = x2 - dx; height = y2 - dy; bitstart = ((dy * p->fix.line_length) << 3) + (dx * bpp); start_index = bitstart & (bits - 1); pitch_index = (p->fix.line_length & (bpl - 1)) << 3; bitstart >>= 3; bitstart &= ~(bpl - 1); dst1 = p->screen_base + bitstart; if (p->fbops->fb_sync) p->fbops->fb_sync(p); /* if (bits % bpp == 0 && image->depth == 1 && !start_index && !pitch_index && bpp >= 8 && bpp <= 32 && ((width & (bits/bpp-1)) == 0)) { fast_imageblit(image, p, dst1); } else { if (image->depth <= bpp) */ slow_imageblit(image, p, dst1, start_index, pitch_index); //} } EXPORT_SYMBOL(cfb_imageblit); MODULE_AUTHOR("James Simmons <jsi...@us...>"); MODULE_DESCRIPTION("Generic software accelerated imaging drawing"); MODULE_LICENSE("GPL"); |