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
|
/*
* Copyright (C) the libgit2 contributors. All rights reserved.
*
* This file is part of libgit2, distributed under the GNU GPL v2 with
* a Linking Exception. For full terms see the included COPYING file.
*/
#include "common.h"
#include "hash.h"
#include "hash/hash_generic.h"
#if defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))
/*
* Force usage of rol or ror by selecting the one with the smaller constant.
* It _can_ generate slightly smaller code (a constant of 1 is special), but
* perhaps more importantly it's possibly faster on any uarch that does a
* rotate with a loop.
*/
#define SHA_ASM(op, x, n) ({ unsigned int __res; __asm__(op " %1,%0":"=r" (__res):"i" (n), "0" (x)); __res; })
#define SHA_ROL(x,n) SHA_ASM("rol", x, n)
#define SHA_ROR(x,n) SHA_ASM("ror", x, n)
#else
#define SHA_ROT(X,l,r) (((X) << (l)) | ((X) >> (r)))
#define SHA_ROL(X,n) SHA_ROT(X,n,32-(n))
#define SHA_ROR(X,n) SHA_ROT(X,32-(n),n)
#endif
/*
* If you have 32 registers or more, the compiler can (and should)
* try to change the array[] accesses into registers. However, on
* machines with less than ~25 registers, that won't really work,
* and at least gcc will make an unholy mess of it.
*
* So to avoid that mess which just slows things down, we force
* the stores to memory to actually happen (we might be better off
* with a 'W(t)=(val);asm("":"+m" (W(t))' there instead, as
* suggested by Artur Skawina - that will also make gcc unable to
* try to do the silly "optimize away loads" part because it won't
* see what the value will be).
*
* Ben Herrenschmidt reports that on PPC, the C version comes close
* to the optimized asm with this (ie on PPC you don't want that
* 'volatile', since there are lots of registers).
*
* On ARM we get the best code generation by forcing a full memory barrier
* between each SHA_ROUND, otherwise gcc happily get wild with spilling and
* the stack frame size simply explode and performance goes down the drain.
*/
#if defined(__i386__) || defined(__x86_64__)
#define setW(x, val) (*(volatile unsigned int *)&W(x) = (val))
#elif defined(__GNUC__) && defined(__arm__)
#define setW(x, val) do { W(x) = (val); __asm__("":::"memory"); } while (0)
#else
#define setW(x, val) (W(x) = (val))
#endif
/*
* Performance might be improved if the CPU architecture is OK with
* unaligned 32-bit loads and a fast ntohl() is available.
* Otherwise fall back to byte loads and shifts which is portable,
* and is faster on architectures with memory alignment issues.
*/
#if defined(__i386__) || defined(__x86_64__) || \
defined(_M_IX86) || defined(_M_X64) || \
defined(__ppc__) || defined(__ppc64__) || \
defined(__powerpc__) || defined(__powerpc64__) || \
defined(__s390__) || defined(__s390x__)
#define get_be32(p) ntohl(*(const unsigned int *)(p))
#define put_be32(p, v) do { *(unsigned int *)(p) = htonl(v); } while (0)
#else
#define get_be32(p) ( \
(*((const unsigned char *)(p) + 0) << 24) | \
(*((const unsigned char *)(p) + 1) << 16) | \
(*((const unsigned char *)(p) + 2) << 8) | \
(*((const unsigned char *)(p) + 3) << 0) )
#define put_be32(p, v) do { \
unsigned int __v = (v); \
*((unsigned char *)(p) + 0) = __v >> 24; \
*((unsigned char *)(p) + 1) = __v >> 16; \
*((unsigned char *)(p) + 2) = __v >> 8; \
*((unsigned char *)(p) + 3) = __v >> 0; } while (0)
#endif
/* This "rolls" over the 512-bit array */
#define W(x) (array[(x)&15])
/*
* Where do we get the source from? The first 16 iterations get it from
* the input data, the next mix it from the 512-bit array.
*/
#define SHA_SRC(t) get_be32(data + t)
#define SHA_MIX(t) SHA_ROL(W(t+13) ^ W(t+8) ^ W(t+2) ^ W(t), 1)
#define SHA_ROUND(t, input, fn, constant, A, B, C, D, E) do { \
unsigned int TEMP = input(t); setW(t, TEMP); \
E += TEMP + SHA_ROL(A,5) + (fn) + (constant); \
B = SHA_ROR(B, 2); } while (0)
#define T_0_15(t, A, B, C, D, E) SHA_ROUND(t, SHA_SRC, (((C^D)&B)^D) , 0x5a827999, A, B, C, D, E )
#define T_16_19(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (((C^D)&B)^D) , 0x5a827999, A, B, C, D, E )
#define T_20_39(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (B^C^D) , 0x6ed9eba1, A, B, C, D, E )
#define T_40_59(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, ((B&C)+(D&(B^C))) , 0x8f1bbcdc, A, B, C, D, E )
#define T_60_79(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (B^C^D) , 0xca62c1d6, A, B, C, D, E )
static void hash__block(git_hash_ctx *ctx, const unsigned int *data)
{
unsigned int A,B,C,D,E;
unsigned int array[16];
A = ctx->H[0];
B = ctx->H[1];
C = ctx->H[2];
D = ctx->H[3];
E = ctx->H[4];
/* Round 1 - iterations 0-16 take their input from 'data' */
T_0_15( 0, A, B, C, D, E);
T_0_15( 1, E, A, B, C, D);
T_0_15( 2, D, E, A, B, C);
T_0_15( 3, C, D, E, A, B);
T_0_15( 4, B, C, D, E, A);
T_0_15( 5, A, B, C, D, E);
T_0_15( 6, E, A, B, C, D);
T_0_15( 7, D, E, A, B, C);
T_0_15( 8, C, D, E, A, B);
T_0_15( 9, B, C, D, E, A);
T_0_15(10, A, B, C, D, E);
T_0_15(11, E, A, B, C, D);
T_0_15(12, D, E, A, B, C);
T_0_15(13, C, D, E, A, B);
T_0_15(14, B, C, D, E, A);
T_0_15(15, A, B, C, D, E);
/* Round 1 - tail. Input from 512-bit mixing array */
T_16_19(16, E, A, B, C, D);
T_16_19(17, D, E, A, B, C);
T_16_19(18, C, D, E, A, B);
T_16_19(19, B, C, D, E, A);
/* Round 2 */
T_20_39(20, A, B, C, D, E);
T_20_39(21, E, A, B, C, D);
T_20_39(22, D, E, A, B, C);
T_20_39(23, C, D, E, A, B);
T_20_39(24, B, C, D, E, A);
T_20_39(25, A, B, C, D, E);
T_20_39(26, E, A, B, C, D);
T_20_39(27, D, E, A, B, C);
T_20_39(28, C, D, E, A, B);
T_20_39(29, B, C, D, E, A);
T_20_39(30, A, B, C, D, E);
T_20_39(31, E, A, B, C, D);
T_20_39(32, D, E, A, B, C);
T_20_39(33, C, D, E, A, B);
T_20_39(34, B, C, D, E, A);
T_20_39(35, A, B, C, D, E);
T_20_39(36, E, A, B, C, D);
T_20_39(37, D, E, A, B, C);
T_20_39(38, C, D, E, A, B);
T_20_39(39, B, C, D, E, A);
/* Round 3 */
T_40_59(40, A, B, C, D, E);
T_40_59(41, E, A, B, C, D);
T_40_59(42, D, E, A, B, C);
T_40_59(43, C, D, E, A, B);
T_40_59(44, B, C, D, E, A);
T_40_59(45, A, B, C, D, E);
T_40_59(46, E, A, B, C, D);
T_40_59(47, D, E, A, B, C);
T_40_59(48, C, D, E, A, B);
T_40_59(49, B, C, D, E, A);
T_40_59(50, A, B, C, D, E);
T_40_59(51, E, A, B, C, D);
T_40_59(52, D, E, A, B, C);
T_40_59(53, C, D, E, A, B);
T_40_59(54, B, C, D, E, A);
T_40_59(55, A, B, C, D, E);
T_40_59(56, E, A, B, C, D);
T_40_59(57, D, E, A, B, C);
T_40_59(58, C, D, E, A, B);
T_40_59(59, B, C, D, E, A);
/* Round 4 */
T_60_79(60, A, B, C, D, E);
T_60_79(61, E, A, B, C, D);
T_60_79(62, D, E, A, B, C);
T_60_79(63, C, D, E, A, B);
T_60_79(64, B, C, D, E, A);
T_60_79(65, A, B, C, D, E);
T_60_79(66, E, A, B, C, D);
T_60_79(67, D, E, A, B, C);
T_60_79(68, C, D, E, A, B);
T_60_79(69, B, C, D, E, A);
T_60_79(70, A, B, C, D, E);
T_60_79(71, E, A, B, C, D);
T_60_79(72, D, E, A, B, C);
T_60_79(73, C, D, E, A, B);
T_60_79(74, B, C, D, E, A);
T_60_79(75, A, B, C, D, E);
T_60_79(76, E, A, B, C, D);
T_60_79(77, D, E, A, B, C);
T_60_79(78, C, D, E, A, B);
T_60_79(79, B, C, D, E, A);
ctx->H[0] += A;
ctx->H[1] += B;
ctx->H[2] += C;
ctx->H[3] += D;
ctx->H[4] += E;
}
int git_hash_init(git_hash_ctx *ctx)
{
ctx->size = 0;
/* Initialize H with the magic constants (see FIPS180 for constants) */
ctx->H[0] = 0x67452301;
ctx->H[1] = 0xefcdab89;
ctx->H[2] = 0x98badcfe;
ctx->H[3] = 0x10325476;
ctx->H[4] = 0xc3d2e1f0;
return 0;
}
int git_hash_update(git_hash_ctx *ctx, const void *data, size_t len)
{
unsigned int lenW = ctx->size & 63;
ctx->size += len;
/* Read the data into W and process blocks as they get full */
if (lenW) {
unsigned int left = 64 - lenW;
if (len < left)
left = (unsigned int)len;
memcpy(lenW + (char *)ctx->W, data, left);
lenW = (lenW + left) & 63;
len -= left;
data = ((const char *)data + left);
if (lenW)
return 0;
hash__block(ctx, ctx->W);
}
while (len >= 64) {
hash__block(ctx, data);
data = ((const char *)data + 64);
len -= 64;
}
if (len)
memcpy(ctx->W, data, len);
return 0;
}
int git_hash_final(git_oid *out, git_hash_ctx *ctx)
{
static const unsigned char pad[64] = { 0x80 };
unsigned int padlen[2];
int i;
/* Pad with a binary 1 (ie 0x80), then zeroes, then length */
padlen[0] = htonl((uint32_t)(ctx->size >> 29));
padlen[1] = htonl((uint32_t)(ctx->size << 3));
i = ctx->size & 63;
git_hash_update(ctx, pad, 1+ (63 & (55 - i)));
git_hash_update(ctx, padlen, 8);
/* Output hash */
for (i = 0; i < 5; i++)
put_be32(out->id + i*4, ctx->H[i]);
return 0;
}
|