1 /*
2 * Fast C2P (Chunky-to-Planar) Conversion
3 *
4 * Copyright (C) 2003-2008 Geert Uytterhoeven
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
8 * for more details.
9 */
10
11 #include <linux/export.h>
12 #include <linux/module.h>
13 #include <linux/string.h>
14
15 #include <linux/unaligned.h>
16
17 #include "c2p.h"
18 #include "c2p_core.h"
19
20
21 /*
22 * Perform a full C2P step on 16 8-bit pixels, stored in 4 32-bit words
23 * containing
24 * - 16 8-bit chunky pixels on input
25 * - permutated planar data (2 planes per 32-bit word) on output
26 */
27
c2p_16x8(u32 d[4])28 static void c2p_16x8(u32 d[4])
29 {
30 transp4(d, 8, 2);
31 transp4(d, 1, 2);
32 transp4x(d, 16, 2);
33 transp4x(d, 2, 2);
34 transp4(d, 4, 1);
35 }
36
37
38 /*
39 * Array containing the permutation indices of the planar data after c2p
40 */
41
42 static const int perm_c2p_16x8[4] = { 1, 3, 0, 2 };
43
44
45 /*
46 * Store a full block of iplan2 data after c2p conversion
47 */
48
store_iplan2(void * dst,u32 bpp,u32 d[4])49 static inline void store_iplan2(void *dst, u32 bpp, u32 d[4])
50 {
51 int i;
52
53 for (i = 0; i < bpp/2; i++, dst += 4)
54 put_unaligned_be32(d[perm_c2p_16x8[i]], dst);
55 }
56
57
58 /*
59 * Store a partial block of iplan2 data after c2p conversion
60 */
61
store_iplan2_masked(void * dst,u32 bpp,u32 d[4],u32 mask)62 static inline void store_iplan2_masked(void *dst, u32 bpp, u32 d[4], u32 mask)
63 {
64 int i;
65
66 for (i = 0; i < bpp/2; i++, dst += 4)
67 put_unaligned_be32(comp(d[perm_c2p_16x8[i]],
68 get_unaligned_be32(dst), mask),
69 dst);
70 }
71
72
73 /*
74 * c2p_iplan2 - Copy 8-bit chunky image data to an interleaved planar
75 * frame buffer with 2 bytes of interleave
76 * @dst: Starting address of the planar frame buffer
77 * @dx: Horizontal destination offset (in pixels)
78 * @dy: Vertical destination offset (in pixels)
79 * @width: Image width (in pixels)
80 * @height: Image height (in pixels)
81 * @dst_nextline: Frame buffer offset to the next line (in bytes)
82 * @src_nextline: Image offset to the next line (in bytes)
83 * @bpp: Bits per pixel of the planar frame buffer (2, 4, or 8)
84 */
85
c2p_iplan2(void * dst,const void * src,u32 dx,u32 dy,u32 width,u32 height,u32 dst_nextline,u32 src_nextline,u32 bpp)86 void c2p_iplan2(void *dst, const void *src, u32 dx, u32 dy, u32 width,
87 u32 height, u32 dst_nextline, u32 src_nextline, u32 bpp)
88 {
89 union {
90 u8 pixels[16];
91 u32 words[4];
92 } d;
93 u32 dst_idx, first, last, w;
94 const u8 *c;
95 void *p;
96
97 dst += dy*dst_nextline+(dx & ~15)*bpp;
98 dst_idx = dx % 16;
99 first = 0xffffU >> dst_idx;
100 first |= first << 16;
101 last = 0xffffU ^ (0xffffU >> ((dst_idx+width) % 16));
102 last |= last << 16;
103 while (height--) {
104 c = src;
105 p = dst;
106 w = width;
107 if (dst_idx+width <= 16) {
108 /* Single destination word */
109 first &= last;
110 memset(d.pixels, 0, sizeof(d));
111 memcpy(d.pixels+dst_idx, c, width);
112 c += width;
113 c2p_16x8(d.words);
114 store_iplan2_masked(p, bpp, d.words, first);
115 p += bpp*2;
116 } else {
117 /* Multiple destination words */
118 w = width;
119 /* Leading bits */
120 if (dst_idx) {
121 w = 16 - dst_idx;
122 memset(d.pixels, 0, dst_idx);
123 memcpy(d.pixels+dst_idx, c, w);
124 c += w;
125 c2p_16x8(d.words);
126 store_iplan2_masked(p, bpp, d.words, first);
127 p += bpp*2;
128 w = width-w;
129 }
130 /* Main chunk */
131 while (w >= 16) {
132 memcpy(d.pixels, c, 16);
133 c += 16;
134 c2p_16x8(d.words);
135 store_iplan2(p, bpp, d.words);
136 p += bpp*2;
137 w -= 16;
138 }
139 /* Trailing bits */
140 w %= 16;
141 if (w > 0) {
142 memcpy(d.pixels, c, w);
143 memset(d.pixels+w, 0, 16-w);
144 c2p_16x8(d.words);
145 store_iplan2_masked(p, bpp, d.words, last);
146 }
147 }
148 src += src_nextline;
149 dst += dst_nextline;
150 }
151 }
152 EXPORT_SYMBOL_GPL(c2p_iplan2);
153
154 MODULE_LICENSE("GPL");
155