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
|
/*
* Copyright (c) 2012-2013 Vincent Hanquez <vincent@snarc.org>
*
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. Neither the name of the author nor the names of his contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHORS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*/
void SIZED(cryptonite_aesni_encrypt_block)(aes_block *out, aes_key *key, aes_block *in)
{
__m128i *k = (__m128i *) key->data;
PRELOAD_ENC(k);
__m128i m = _mm_loadu_si128((__m128i *) in);
DO_ENC_BLOCK(m);
_mm_storeu_si128((__m128i *) out, m);
}
void SIZED(cryptonite_aesni_decrypt_block)(aes_block *out, aes_key *key, aes_block *in)
{
__m128i *k = (__m128i *) key->data;
PRELOAD_DEC(k);
__m128i m = _mm_loadu_si128((__m128i *) in);
DO_DEC_BLOCK(m);
_mm_storeu_si128((__m128i *) out, m);
}
void SIZED(cryptonite_aesni_encrypt_ecb)(aes_block *out, aes_key *key, aes_block *in, uint32_t blocks)
{
__m128i *k = (__m128i *) key->data;
PRELOAD_ENC(k);
for (; blocks-- > 0; in += 1, out += 1) {
__m128i m = _mm_loadu_si128((__m128i *) in);
DO_ENC_BLOCK(m);
_mm_storeu_si128((__m128i *) out, m);
}
}
void SIZED(cryptonite_aesni_decrypt_ecb)(aes_block *out, aes_key *key, aes_block *in, uint32_t blocks)
{
__m128i *k = (__m128i *) key->data;
PRELOAD_DEC(k);
for (; blocks-- > 0; in += 1, out += 1) {
__m128i m = _mm_loadu_si128((__m128i *) in);
DO_DEC_BLOCK(m);
_mm_storeu_si128((__m128i *) out, m);
}
}
void SIZED(cryptonite_aesni_encrypt_cbc)(aes_block *out, aes_key *key, aes_block *_iv, aes_block *in, uint32_t blocks)
{
__m128i *k = (__m128i *) key->data;
__m128i iv = _mm_loadu_si128((__m128i *) _iv);
PRELOAD_ENC(k);
for (; blocks-- > 0; in += 1, out += 1) {
__m128i m = _mm_loadu_si128((__m128i *) in);
m = _mm_xor_si128(m, iv);
DO_ENC_BLOCK(m);
iv = m;
_mm_storeu_si128((__m128i *) out, m);
}
}
void SIZED(cryptonite_aesni_decrypt_cbc)(aes_block *out, aes_key *key, aes_block *_iv, aes_block *in, uint32_t blocks)
{
__m128i *k = (__m128i *) key->data;
__m128i iv = _mm_loadu_si128((__m128i *) _iv);
PRELOAD_DEC(k);
for (; blocks-- > 0; in += 1, out += 1) {
__m128i m = _mm_loadu_si128((__m128i *) in);
__m128i ivnext = m;
DO_DEC_BLOCK(m);
m = _mm_xor_si128(m, iv);
_mm_storeu_si128((__m128i *) out, m);
iv = ivnext;
}
}
void SIZED(cryptonite_aesni_encrypt_ctr)(uint8_t *output, aes_key *key, aes_block *_iv, uint8_t *input, uint32_t len)
{
__m128i *k = (__m128i *) key->data;
__m128i bswap_mask = _mm_setr_epi8(7,6,5,4,3,2,1,0,15,14,13,12,11,10,9,8);
__m128i one = _mm_set_epi32(0,1,0,0);
uint32_t nb_blocks = len / 16;
uint32_t part_block_len = len % 16;
/* get the IV in little endian format */
__m128i iv = _mm_loadu_si128((__m128i *) _iv);
iv = _mm_shuffle_epi8(iv, bswap_mask);
PRELOAD_ENC(k);
for (; nb_blocks-- > 0; output += 16, input += 16) {
/* put back the iv in big endian mode,
* encrypt it and and xor it the input block
*/
__m128i tmp = _mm_shuffle_epi8(iv, bswap_mask);
DO_ENC_BLOCK(tmp);
__m128i m = _mm_loadu_si128((__m128i *) input);
m = _mm_xor_si128(m, tmp);
_mm_storeu_si128((__m128i *) output, m);
/* iv += 1 */
iv = _mm_add_epi64(iv, one);
}
if (part_block_len != 0) {
aes_block block;
memset(&block.b, 0, 16);
memcpy(&block.b, input, part_block_len);
__m128i m = _mm_loadu_si128((__m128i *) &block);
__m128i tmp = _mm_shuffle_epi8(iv, bswap_mask);
DO_ENC_BLOCK(tmp);
m = _mm_xor_si128(m, tmp);
_mm_storeu_si128((__m128i *) &block.b, m);
memcpy(output, &block.b, part_block_len);
}
return ;
}
void SIZED(cryptonite_aesni_encrypt_xts)(aes_block *out, aes_key *key1, aes_key *key2,
aes_block *_tweak, uint32_t spoint, aes_block *in, uint32_t blocks)
{
__m128i tweak = _mm_loadu_si128((__m128i *) _tweak);
do {
__m128i *k2 = (__m128i *) key2->data;
PRELOAD_ENC(k2);
DO_ENC_BLOCK(tweak);
while (spoint-- > 0)
tweak = gfmulx(tweak);
} while (0) ;
do {
__m128i *k1 = (__m128i *) key1->data;
PRELOAD_ENC(k1);
for ( ; blocks-- > 0; in += 1, out += 1, tweak = gfmulx(tweak)) {
__m128i m = _mm_loadu_si128((__m128i *) in);
m = _mm_xor_si128(m, tweak);
DO_ENC_BLOCK(m);
m = _mm_xor_si128(m, tweak);
_mm_storeu_si128((__m128i *) out, m);
}
} while (0);
}
void SIZED(cryptonite_aesni_gcm_encrypt)(uint8_t *output, aes_gcm *gcm, aes_key *key, uint8_t *input, uint32_t length)
{
__m128i *k = (__m128i *) key->data;
__m128i bswap_mask = _mm_setr_epi8(7,6,5,4,3,2,1,0,15,14,13,12,11,10,9,8);
__m128i one = _mm_set_epi32(0,1,0,0);
uint32_t nb_blocks = length / 16;
uint32_t part_block_len = length % 16;
gcm->length_input += length;
__m128i h = _mm_loadu_si128((__m128i *) &gcm->h);
__m128i tag = _mm_loadu_si128((__m128i *) &gcm->tag);
__m128i iv = _mm_loadu_si128((__m128i *) &gcm->civ);
iv = _mm_shuffle_epi8(iv, bswap_mask);
PRELOAD_ENC(k);
for (; nb_blocks-- > 0; output += 16, input += 16) {
/* iv += 1 */
iv = _mm_add_epi64(iv, one);
/* put back iv in big endian, encrypt it,
* and xor it to input */
__m128i tmp = _mm_shuffle_epi8(iv, bswap_mask);
DO_ENC_BLOCK(tmp);
__m128i m = _mm_loadu_si128((__m128i *) input);
m = _mm_xor_si128(m, tmp);
tag = ghash_add(tag, h, m);
/* store it out */
_mm_storeu_si128((__m128i *) output, m);
}
if (part_block_len > 0) {
__m128i mask;
aes_block block;
/* FIXME could do something a bit more clever (slli & sub & and maybe) ... */
switch (part_block_len) {
case 1: mask = _mm_setr_epi8(0,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80); break;
case 2: mask = _mm_setr_epi8(0,1,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80); break;
case 3: mask = _mm_setr_epi8(0,1,2,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80); break;
case 4: mask = _mm_setr_epi8(0,1,2,3,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80); break;
case 5: mask = _mm_setr_epi8(0,1,2,3,4,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80); break;
case 6: mask = _mm_setr_epi8(0,1,2,3,4,5,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80); break;
case 7: mask = _mm_setr_epi8(0,1,2,3,4,5,6,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80); break;
case 8: mask = _mm_setr_epi8(0,1,2,3,4,5,6,7,0x80,0x80,0x80,0x80,0x80,0x80,0x80,0x80); break;
case 9: mask = _mm_setr_epi8(0,1,2,3,4,5,6,7,8,0x80,0x80,0x80,0x80,0x80,0x80,0x80); break;
case 10: mask = _mm_setr_epi8(0,1,2,3,4,5,6,7,8,9,0x80,0x80,0x80,0x80,0x80,0x80); break;
case 11: mask = _mm_setr_epi8(0,1,2,3,4,5,6,7,8,9,10,0x80,0x80,0x80,0x80,0x80); break;
case 12: mask = _mm_setr_epi8(0,1,2,3,4,5,6,7,8,9,10,11,0x80,0x80,0x80,0x80); break;
case 13: mask = _mm_setr_epi8(0,1,2,3,4,5,6,7,8,9,10,11,12,0x80,0x80,0x80); break;
case 14: mask = _mm_setr_epi8(0,1,2,3,4,5,6,7,8,9,10,11,12,13,0x80,0x80); break;
case 15: mask = _mm_setr_epi8(0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,0x80); break;
default: mask = _mm_setr_epi8(0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15); break;
}
block128_zero(&block);
block128_copy_bytes(&block, input, part_block_len);
/* iv += 1 */
iv = _mm_add_epi64(iv, one);
/* put back iv in big endian mode, encrypt it and xor it with input */
__m128i tmp = _mm_shuffle_epi8(iv, bswap_mask);
DO_ENC_BLOCK(tmp);
__m128i m = _mm_loadu_si128((__m128i *) &block);
m = _mm_xor_si128(m, tmp);
m = _mm_shuffle_epi8(m, mask);
tag = ghash_add(tag, h, m);
/* make output */
_mm_storeu_si128((__m128i *) &block.b, m);
memcpy(output, &block.b, part_block_len);
}
/* store back IV & tag */
__m128i tmp = _mm_shuffle_epi8(iv, bswap_mask);
_mm_storeu_si128((__m128i *) &gcm->civ, tmp);
_mm_storeu_si128((__m128i *) &gcm->tag, tag);
}
|
