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
|
///////////////////////////////////////////////////////////////////////////////
//
/// \file sha256.c
/// \brief SHA256
//
// Based on the public domain code found from Wei Dai's Crypto++ library
// version 5.5.1: http://www.cryptopp.com/
// This code has been put into the public domain.
//
/// \todo Crypto++ has x86 ASM optimizations. They use SSE so if they
/// are imported to liblzma, SSE instructions need to be used
/// conditionally to keep the code working on older boxes.
//
// This library is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
//
///////////////////////////////////////////////////////////////////////////////
#include "check.h"
#ifndef WORDS_BIGENDIAN
# include "check_byteswap.h"
#endif
// At least on x86, GCC is able to optimize this to a rotate instruction.
#define rotr_32(num, amount) ((num) >> (amount) | (num) << (32 - (amount)))
#define blk0(i) (W[i] = data[i])
#define blk2(i) (W[i & 15] += s1(W[(i - 2) & 15]) + W[(i - 7) & 15] \
+ s0(W[(i - 15) & 15]))
#define Ch(x, y, z) (z ^ (x & (y ^ z)))
#define Maj(x, y, z) ((x & y) | (z & (x | y)))
#define a(i) T[(0 - i) & 7]
#define b(i) T[(1 - i) & 7]
#define c(i) T[(2 - i) & 7]
#define d(i) T[(3 - i) & 7]
#define e(i) T[(4 - i) & 7]
#define f(i) T[(5 - i) & 7]
#define g(i) T[(6 - i) & 7]
#define h(i) T[(7 - i) & 7]
#define R(i) \
h(i) += S1(e(i)) + Ch(e(i), f(i), g(i)) + SHA256_K[i + j] \
+ (j ? blk2(i) : blk0(i)); \
d(i) += h(i); \
h(i) += S0(a(i)) + Maj(a(i), b(i), c(i))
#define S0(x) (rotr_32(x, 2) ^ rotr_32(x, 13) ^ rotr_32(x, 22))
#define S1(x) (rotr_32(x, 6) ^ rotr_32(x, 11) ^ rotr_32(x, 25))
#define s0(x) (rotr_32(x, 7) ^ rotr_32(x, 18) ^ (x >> 3))
#define s1(x) (rotr_32(x, 17) ^ rotr_32(x, 19) ^ (x >> 10))
static const uint32_t SHA256_K[64] = {
0x428A2F98, 0x71374491, 0xB5C0FBCF, 0xE9B5DBA5,
0x3956C25B, 0x59F111F1, 0x923F82A4, 0xAB1C5ED5,
0xD807AA98, 0x12835B01, 0x243185BE, 0x550C7DC3,
0x72BE5D74, 0x80DEB1FE, 0x9BDC06A7, 0xC19BF174,
0xE49B69C1, 0xEFBE4786, 0x0FC19DC6, 0x240CA1CC,
0x2DE92C6F, 0x4A7484AA, 0x5CB0A9DC, 0x76F988DA,
0x983E5152, 0xA831C66D, 0xB00327C8, 0xBF597FC7,
0xC6E00BF3, 0xD5A79147, 0x06CA6351, 0x14292967,
0x27B70A85, 0x2E1B2138, 0x4D2C6DFC, 0x53380D13,
0x650A7354, 0x766A0ABB, 0x81C2C92E, 0x92722C85,
0xA2BFE8A1, 0xA81A664B, 0xC24B8B70, 0xC76C51A3,
0xD192E819, 0xD6990624, 0xF40E3585, 0x106AA070,
0x19A4C116, 0x1E376C08, 0x2748774C, 0x34B0BCB5,
0x391C0CB3, 0x4ED8AA4A, 0x5B9CCA4F, 0x682E6FF3,
0x748F82EE, 0x78A5636F, 0x84C87814, 0x8CC70208,
0x90BEFFFA, 0xA4506CEB, 0xBEF9A3F7, 0xC67178F2,
};
static void
transform(uint32_t state[static 8], const uint32_t data[static 16])
{
uint32_t W[16];
uint32_t T[8];
// Copy state[] to working vars.
memcpy(T, state, sizeof(T));
// 64 operations, partially loop unrolled
for (unsigned int j = 0; j < 64; j += 16) {
R( 0); R( 1); R( 2); R( 3);
R( 4); R( 5); R( 6); R( 7);
R( 8); R( 9); R(10); R(11);
R(12); R(13); R(14); R(15);
}
// Add the working vars back into state[].
state[0] += a(0);
state[1] += b(0);
state[2] += c(0);
state[3] += d(0);
state[4] += e(0);
state[5] += f(0);
state[6] += g(0);
state[7] += h(0);
}
static void
process(lzma_sha256 *sha256)
{
#ifdef WORDS_BIGENDIAN
transform(sha256->state, (uint32_t *)(sha256->buffer));
#else
uint32_t data[16];
for (size_t i = 0; i < 16; ++i)
data[i] = bswap_32(*((uint32_t*)(sha256->buffer) + i));
transform(sha256->state, data);
#endif
return;
}
extern void
lzma_sha256_init(lzma_sha256 *sha256)
{
static const uint32_t s[8] = {
0x6A09E667, 0xBB67AE85, 0x3C6EF372, 0xA54FF53A,
0x510E527F, 0x9B05688C, 0x1F83D9AB, 0x5BE0CD19,
};
memcpy(sha256->state, s, sizeof(s));
sha256->size = 0;
return;
}
extern void
lzma_sha256_update(const uint8_t *buf, size_t size, lzma_sha256 *sha256)
{
// Copy the input data into a properly aligned temporary buffer.
// This way we can be called with arbitrarily sized buffers
// (no need to be multiple of 64 bytes), and the code works also
// on architectures that don't allow unaligned memory access.
while (size > 0) {
const size_t copy_start = sha256->size & 0x3F;
size_t copy_size = 64 - copy_start;
if (copy_size > size)
copy_size = size;
memcpy(sha256->buffer + copy_start, buf, copy_size);
buf += copy_size;
size -= copy_size;
sha256->size += copy_size;
if ((sha256->size & 0x3F) == 0)
process(sha256);
}
return;
}
extern void
lzma_sha256_finish(lzma_sha256 *sha256)
{
// Add padding as described in RFC 3174 (it describes SHA-1 but
// the same padding style is used for SHA-256 too).
size_t pos = sha256->size & 0x3F;
sha256->buffer[pos++] = 0x80;
while (pos != 64 - 8) {
if (pos == 64) {
process(sha256);
pos = 0;
}
sha256->buffer[pos++] = 0x00;
}
// Convert the message size from bytes to bits.
sha256->size *= 8;
#ifdef WORDS_BIGENDIAN
*(uint64_t *)(sha256->buffer + 64 - 8) = sha256->size;
#else
*(uint64_t *)(sha256->buffer + 64 - 8) = bswap_64(sha256->size);
#endif
process(sha256);
for (size_t i = 0; i < 8; ++i)
#ifdef WORDS_BIGENDIAN
((uint32_t *)(sha256->buffer))[i] = sha256->state[i];
#else
((uint32_t *)(sha256->buffer))[i] = bswap_32(sha256->state[i]);
#endif
return;
}
|
