2 * Copyright (c) 2017 Thomas Pornin <pornin@bolet.org>
4 * Permission is hereby granted, free of charge, to any person obtaining
5 * a copy of this software and associated documentation files (the
6 * "Software"), to deal in the Software without restriction, including
7 * without limitation the rights to use, copy, modify, merge, publish,
8 * distribute, sublicense, and/or sell copies of the Software, and to
9 * permit persons to whom the Software is furnished to do so, subject to
10 * the following conditions:
12 * The above copyright notice and this permission notice shall be
13 * included in all copies or substantial portions of the Software.
15 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
16 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
17 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
18 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
19 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
20 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
21 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
30 #include <wmmintrin.h>
37 /* see bearssl_block.h */
39 br_aes_x86ni_cbcenc_init(br_aes_x86ni_cbcenc_keys
*ctx
,
40 const void *key
, size_t len
)
42 ctx
->vtable
= &br_aes_x86ni_cbcenc_vtable
;
43 ctx
->num_rounds
= br_aes_x86ni_keysched_enc(ctx
->skey
.skni
, key
, len
);
46 /* see bearssl_block.h */
49 br_aes_x86ni_cbcenc_run(const br_aes_x86ni_cbcenc_keys
*ctx
,
50 void *iv
, void *data
, size_t len
)
58 ivx
= _mm_loadu_si128(iv
);
59 num_rounds
= ctx
->num_rounds
;
60 for (u
= 0; u
<= num_rounds
; u
++) {
61 sk
[u
] = _mm_loadu_si128((void *)(ctx
->skey
.skni
+ (u
<< 4)));
66 x
= _mm_xor_si128(_mm_loadu_si128((void *)buf
), ivx
);
67 x
= _mm_xor_si128(x
, sk
[0]);
68 x
= _mm_aesenc_si128(x
, sk
[1]);
69 x
= _mm_aesenc_si128(x
, sk
[2]);
70 x
= _mm_aesenc_si128(x
, sk
[3]);
71 x
= _mm_aesenc_si128(x
, sk
[4]);
72 x
= _mm_aesenc_si128(x
, sk
[5]);
73 x
= _mm_aesenc_si128(x
, sk
[6]);
74 x
= _mm_aesenc_si128(x
, sk
[7]);
75 x
= _mm_aesenc_si128(x
, sk
[8]);
76 x
= _mm_aesenc_si128(x
, sk
[9]);
77 if (num_rounds
== 10) {
78 x
= _mm_aesenclast_si128(x
, sk
[10]);
79 } else if (num_rounds
== 12) {
80 x
= _mm_aesenc_si128(x
, sk
[10]);
81 x
= _mm_aesenc_si128(x
, sk
[11]);
82 x
= _mm_aesenclast_si128(x
, sk
[12]);
84 x
= _mm_aesenc_si128(x
, sk
[10]);
85 x
= _mm_aesenc_si128(x
, sk
[11]);
86 x
= _mm_aesenc_si128(x
, sk
[12]);
87 x
= _mm_aesenc_si128(x
, sk
[13]);
88 x
= _mm_aesenclast_si128(x
, sk
[14]);
91 _mm_storeu_si128((void *)buf
, x
);
95 _mm_storeu_si128(iv
, ivx
);
98 /* see bearssl_block.h */
99 const br_block_cbcenc_class br_aes_x86ni_cbcenc_vtable
= {
100 sizeof(br_aes_x86ni_cbcenc_keys
),
103 (void (*)(const br_block_cbcenc_class
**, const void *, size_t))
104 &br_aes_x86ni_cbcenc_init
,
105 (void (*)(const br_block_cbcenc_class
*const *, void *, void *, size_t))
106 &br_aes_x86ni_cbcenc_run
109 /* see bearssl_block.h */
110 const br_block_cbcenc_class
*
111 br_aes_x86ni_cbcenc_get_vtable(void)
113 return br_aes_x86ni_supported() ? &br_aes_x86ni_cbcenc_vtable
: NULL
;
118 /* see bearssl_block.h */
119 const br_block_cbcenc_class
*
120 br_aes_x86ni_cbcenc_get_vtable(void)