summaryrefslogtreecommitdiffstats
path: root/drivers/video/cfbcopyarea.c
blob: 1c67885a1f4f2da9eaa8487ab5136182c8a965a4 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
/*
 *  Generic function for frame buffer with packed pixels of any depth.
 *
 *      Copyright (C)  1999-2005 James Simmons <jsimmons@www.infradead.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:
 *
 *  This is for cfb packed pixels. Iplan and such are incorporated in the
 *  drivers that need them.
 *
 *  FIXME
 *
 *  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.
 *
 *  The two functions or copying forward and backward could be split up like
 *  the ones for filling, i.e. in aligned and unaligned versions. This would
 *  help moving some redundant computations and branches out of the loop, too.
 */

#include <linux/module.h>
#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 "fb_draw.h"

#if BITS_PER_LONG == 32
#  define FB_WRITEL fb_writel
#  define FB_READL  fb_readl
#else
#  define FB_WRITEL fb_writeq
#  define FB_READL  fb_readq
#endif

    /*
     *  Generic bitwise copy algorithm
     */

static void
bitcpy(unsigned long __iomem *dst, int dst_idx, const unsigned long __iomem *src,
	int src_idx, int bits, unsigned n, u32 bswapmask)
{
	unsigned long first, last;
	int const shift = dst_idx-src_idx;
	int left, right;

	first = fb_shifted_pixels_mask_long(dst_idx, bswapmask);
	last = ~fb_shifted_pixels_mask_long((dst_idx+n) % bits, bswapmask);

	if (!shift) {
		// Same alignment for source and dest

		if (dst_idx+n <= bits) {
			// Single word
			if (last)
				first &= last;
			FB_WRITEL( comp( FB_READL(src), FB_READL(dst), first), dst);
		} else {
			// Multiple destination words

			// Leading bits
			if (first != ~0UL) {
				FB_WRITEL( comp( FB_READL(src), FB_READL(dst), first), dst);
				dst++;
				src++;
				n -= bits - dst_idx;
			}

			// Main chunk
			n /= bits;
			while (n >= 8) {
				FB_WRITEL(FB_READL(src++), dst++);
				FB_WRITEL(FB_READL(src++), dst++);
				FB_WRITEL(FB_READL(src++), dst++);
				FB_WRITEL(FB_READL(src++), dst++);
				FB_WRITEL(FB_READL(src++), dst++);
				FB_WRITEL(FB_READL(src++), dst++);
				FB_WRITEL(FB_READL(src++), dst++);
				FB_WRITEL(FB_READL(src++), dst++);
				n -= 8;
			}
			while (n--)
				FB_WRITEL(FB_READL(src++), dst++);

			// Trailing bits
			if (last)
				FB_WRITEL( comp( FB_READL(src), FB_READL(dst), last), dst);
		}
	} else {
		unsigned long d0, d1;
		int m;
		// Different alignment for source and dest

		right = shift & (bits - 1);
		left = -shift & (bits - 1);

		if (dst_idx+n <= bits) {
			// Single destination word
			if (last)
				first &= last;
			if (shift > 0) {
				// Single source word
				FB_WRITEL( comp( FB_READL(src) >> right, FB_READL(dst), first), dst);
			} else if (src_idx+n <= bits) {
				// Single source word
				FB_WRITEL( comp(FB_READL(src) << left, FB_READL(dst), first), dst);
			} else {
				// 2 source words
				d0 = FB_READL(src++);
				d1 = FB_READL(src);
				FB_WRITEL( comp(d0<<left | d1>>right, FB_READL(dst), first), dst);
			}
		} else {
			// Multiple destination words
			/** We must always remember the last value read, because in case
			SRC and DST overlap bitwise (e.g. when moving just one pixel in
			1bpp), we always collect one full long for DST and that might
			overlap with the current long from SRC. We store this value in
			'd0'. */
			d0 = FB_READL(src++);
			// Leading bits
			if (shift > 0) {
				// Single source word
				FB_WRITEL( comp(d0 >> right, FB_READL(dst), first), dst);
				dst++;
				n -= bits - dst_idx;
			} else {
				// 2 source words
				d1 = FB_READL(src++);
				FB_WRITEL( comp(d0<<left | d1>>right, FB_READL(dst), first), dst);
				d0 = d1;
				dst++;
				n -= bits - dst_idx;
			}

			// Main chunk
			m = n % bits;
			n /= bits;
			while (n >= 4) {
				d1 = FB_READL(src++);
				FB_WRITEL(d0 << left | d1 >> right, dst++);
				d0 = d1;
				d1 = FB_READL(src++);
				FB_WRITEL(d0 << left | d1 >> right, dst++);
				d0 = d1;
				d1 = FB_READL(src++);
				FB_WRITEL(d0 << left | d1 >> right, dst++);
				d0 = d1;
				d1 = FB_READL(src++);
				FB_WRITEL(d0 << left | d1 >> right, dst++);
				d0 = d1;
				n -= 4;
			}
			while (n--) {
				d1 = FB_READL(src++);
				FB_WRITEL(d0 << left | d1 >> right, dst++);
				d0 = d1;
			}

			// Trailing bits
			if (last) {
				if (m <= right) {
					// Single source word
					FB_WRITEL( comp(d0 << left, FB_READL(dst), last), dst);
				} else {
					// 2 source words
					d1 = FB_READL(src);
					FB_WRITEL( comp(d0<<left | d1>>right, FB_READL(dst), last), dst);
				}
			}
		}
	}
}

    /*
     *  Generic bitwise copy algorithm, operating backward
     */

static void
bitcpy_rev(unsigned long __iomem *dst, int dst_idx, const unsigned long __iomem *src,
		int src_idx, int bits, unsigned n, u32 bswapmask)
{
	unsigned long first, last;
	int shift;

	dst += (n-1)/bits;
	src += (n-1)/bits;
	if ((n-1) % bits) {
		dst_idx += (n-1) % bits;
		dst += dst_idx >> (ffs(bits) - 1);
		dst_idx &= bits - 1;
		src_idx += (n-1) % bits;
		src += src_idx >> (ffs(bits) - 1);
		src_idx &= bits - 1;
	}

	shift = dst_idx-src_idx;

	first = fb_shifted_pixels_mask_long(bits - 1 - dst_idx, bswapmask);
	last = ~fb_shifted_pixels_mask_long(bits - 1 - ((dst_idx-n) % bits), bswapmask);

	if (!shift) {
		// Same alignment for source and dest

		if ((unsigned long)dst_idx+1 >= n) {
			// Single word
			if (last)
				first &= last;
			FB_WRITEL( comp( FB_READL(src), FB_READL(dst), first), dst);
		} else {
			// Multiple destination words

			// Leading bits
			if (first != ~0UL) {
				FB_WRITEL( comp( FB_READL(src), FB_READL(dst), first), dst);
				dst--;
				src--;
				n -= dst_idx+1;
			}

			// Main chunk
			n /= bits;
			while (n >= 8) {
				FB_WRITEL(FB_READL(src--), dst--);
				FB_WRITEL(FB_READL(src--), dst--);
				FB_WRITEL(FB_READL(src--), dst--);
				FB_WRITEL(FB_READL(src--), dst--);
				FB_WRITEL(FB_READL(src--), dst--);
				FB_WRITEL(FB_READL(src--), dst--);
				FB_WRITEL(FB_READL(src--), dst--);
				FB_WRITEL(FB_READL(src--), dst--);
				n -= 8;
			}
			while (n--)
				FB_WRITEL(FB_READL(src--), dst--);

			// Trailing bits
			if (last)
				FB_WRITEL( comp( FB_READL(src), FB_READL(dst), last), dst);
		}
	} else {
		// Different alignment for source and dest

		int const left = -shift & (bits-1);
		int const right = shift & (bits-1);

		if ((unsigned long)dst_idx+1 >= n) {
			// Single destination word
			if (last)
				first &= last;
			if (shift < 0) {
				// Single source word
				FB_WRITEL( comp( FB_READL(src)<<left, FB_READL(dst), first), dst);
			} else if (1+(unsigned long)src_idx >= n) {
				// Single source word
				FB_WRITEL( comp( FB_READL(src)>>right, FB_READL(dst), first), dst);
			} else {
				// 2 source words
				FB_WRITEL( comp( (FB_READL(src)>>right | FB_READL(src-1)<<left), FB_READL(dst), first), dst);
			}
		} else {
			// Multiple destination words
			/** We must always remember the last value read, because in case
			SRC and DST overlap bitwise (e.g. when moving just one pixel in
			1bpp), we always collect one full long for DST and that might
			overlap with the current long from SRC. We store this value in
			'd0'. */
			unsigned long d0, d1;
			int m;

			d0 = FB_READL(src--);
			// Leading bits
			if (shift < 0) {
				// Single source word
				FB_WRITEL( comp( (d0 << left), FB_READL(dst), first), dst);
			} else {
				// 2 source words
				d1 = FB_READL(src--);
				FB_WRITEL( comp( (d0>>right | d1<<left), FB_READL(dst), first), dst);
				d0 = d1;
			}
			dst--;
			n -= dst_idx+1;

			// Main chunk
			m = n % bits;
			n /= bits;
			while (n >= 4) {
				d1 = FB_READL(src--);
				FB_WRITEL(d0 >> right | d1 << left, dst--);
				d0 = d1;
				d1 = FB_READL(src--);
				FB_WRITEL(d0 >> right | d1 << left, dst--);
				d0 = d1;
				d1 = FB_READL(src--);
				FB_WRITEL(d0 >> right | d1 << left, dst--);
				d0 = d1;
				d1 = FB_READL(src--);
				FB_WRITEL(d0 >> right | d1 << left, dst--);
				d0 = d1;
				n -= 4;
			}
			while (n--) {
				d1 = FB_READL(src--);
				FB_WRITEL(d0 >> right | d1 << left, dst--);
				d0 = d1;
			}

			// Trailing bits
			if (last) {
				if (m <= left) {
					// Single source word
					FB_WRITEL( comp(d0 >> right, FB_READL(dst), last), dst);
				} else {
					// 2 source words
					d1 = FB_READL(src);
					FB_WRITEL( comp(d0>>right | d1<<left, FB_READL(dst), last), dst);
				}
			}
		}
	}
}

void cfb_copyarea(struct fb_info *p, const struct fb_copyarea *area)
{
	u32 dx = area->dx, dy = area->dy, sx = area->sx, sy = area->sy;
	u32 height = area->height, width = area->width;
	unsigned long const bits_per_line = p->fix.line_length*8u;
	unsigned long __iomem *dst = NULL, *src = NULL;
	int bits = BITS_PER_LONG, bytes = bits >> 3;
	int dst_idx = 0, src_idx = 0, rev_copy = 0;
	u32 bswapmask = fb_compute_bswapmask(p);

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

	/* if the beginning of the target area might overlap with the end of
	the source area, be have to copy the area reverse. */
	if ((dy == sy && dx > sx) || (dy > sy)) {
		dy += height;
		sy += height;
		rev_copy = 1;
	}

	// split the base of the framebuffer into a long-aligned address and the
	// index of the first bit
	dst = src = (unsigned long __iomem *)((unsigned long)p->screen_base & ~(bytes-1));
	dst_idx = src_idx = 8*((unsigned long)p->screen_base & (bytes-1));
	// add offset of source and target area
	dst_idx += dy*bits_per_line + dx*p->var.bits_per_pixel;
	src_idx += sy*bits_per_line + sx*p->var.bits_per_pixel;

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

	if (rev_copy) {
		while (height--) {
			dst_idx -= bits_per_line;
			src_idx -= bits_per_line;
			dst += dst_idx >> (ffs(bits) - 1);
			dst_idx &= (bytes - 1);
			src += src_idx >> (ffs(bits) - 1);
			src_idx &= (bytes - 1);
			bitcpy_rev(dst, dst_idx, src, src_idx, bits,
				width*p->var.bits_per_pixel, bswapmask);
		}
	} else {
		while (height--) {
			dst += dst_idx >> (ffs(bits) - 1);
			dst_idx &= (bytes - 1);
			src += src_idx >> (ffs(bits) - 1);
			src_idx &= (bytes - 1);
			bitcpy(dst, dst_idx, src, src_idx, bits,
				width*p->var.bits_per_pixel, bswapmask);
			dst_idx += bits_per_line;
			src_idx += bits_per_line;
		}
	}
}

EXPORT_SYMBOL(cfb_copyarea);

MODULE_AUTHOR("James Simmons <jsimmons@users.sf.net>");
MODULE_DESCRIPTION("Generic software accelerated copyarea");
MODULE_LICENSE("GPL");