2 * Copyright 2013 John-Mark Gurney <jmg@FreeBSD.org>
5 * Redistribution and use in source and binary forms, with or without
6 * modification, are permitted provided that the following conditions
8 * 1. Redistributions of source code must retain the above copyright
9 * notice, this list of conditions and the following disclaimer.
10 * 2. Redistributions in binary form must reproduce the above copyright
11 * notice, this list of conditions and the following disclaimer in the
12 * documentation and/or other materials provided with the distribution.
14 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
15 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
16 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
17 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
18 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
19 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
20 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
21 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
22 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
23 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
30 #include <wmmintrin.h>
33 aesni_enc8(int rounds, const __m128i *keysched, __m128i a,
34 __m128i b, __m128i c, __m128i d, __m128i e, __m128i f, __m128i g,
35 __m128i h, __m128i out[8])
48 for (i = 0; i < rounds; i++) {
49 a = _mm_aesenc_si128(a, keysched[i + 1]);
50 b = _mm_aesenc_si128(b, keysched[i + 1]);
51 c = _mm_aesenc_si128(c, keysched[i + 1]);
52 d = _mm_aesenc_si128(d, keysched[i + 1]);
53 e = _mm_aesenc_si128(e, keysched[i + 1]);
54 f = _mm_aesenc_si128(f, keysched[i + 1]);
55 g = _mm_aesenc_si128(g, keysched[i + 1]);
56 h = _mm_aesenc_si128(h, keysched[i + 1]);
59 out[0] = _mm_aesenclast_si128(a, keysched[i + 1]);
60 out[1] = _mm_aesenclast_si128(b, keysched[i + 1]);
61 out[2] = _mm_aesenclast_si128(c, keysched[i + 1]);
62 out[3] = _mm_aesenclast_si128(d, keysched[i + 1]);
63 out[4] = _mm_aesenclast_si128(e, keysched[i + 1]);
64 out[5] = _mm_aesenclast_si128(f, keysched[i + 1]);
65 out[6] = _mm_aesenclast_si128(g, keysched[i + 1]);
66 out[7] = _mm_aesenclast_si128(h, keysched[i + 1]);
70 aesni_dec8(int rounds, const __m128i *keysched, __m128i a,
71 __m128i b, __m128i c, __m128i d, __m128i e, __m128i f, __m128i g,
72 __m128i h, __m128i out[8])
85 for (i = 0; i < rounds; i++) {
86 a = _mm_aesdec_si128(a, keysched[i + 1]);
87 b = _mm_aesdec_si128(b, keysched[i + 1]);
88 c = _mm_aesdec_si128(c, keysched[i + 1]);
89 d = _mm_aesdec_si128(d, keysched[i + 1]);
90 e = _mm_aesdec_si128(e, keysched[i + 1]);
91 f = _mm_aesdec_si128(f, keysched[i + 1]);
92 g = _mm_aesdec_si128(g, keysched[i + 1]);
93 h = _mm_aesdec_si128(h, keysched[i + 1]);
96 out[0] = _mm_aesdeclast_si128(a, keysched[i + 1]);
97 out[1] = _mm_aesdeclast_si128(b, keysched[i + 1]);
98 out[2] = _mm_aesdeclast_si128(c, keysched[i + 1]);
99 out[3] = _mm_aesdeclast_si128(d, keysched[i + 1]);
100 out[4] = _mm_aesdeclast_si128(e, keysched[i + 1]);
101 out[5] = _mm_aesdeclast_si128(f, keysched[i + 1]);
102 out[6] = _mm_aesdeclast_si128(g, keysched[i + 1]);
103 out[7] = _mm_aesdeclast_si128(h, keysched[i + 1]);
106 static inline __m128i
107 aesni_enc(int rounds, const __m128i *keysched, const __m128i from)
112 tmp = from ^ keysched[0];
114 for (i = 0; i < rounds; i++)
115 tmp = _mm_aesenc_si128(tmp, keysched[i + 1]);
117 return _mm_aesenclast_si128(tmp, keysched[i + 1]);
120 static inline __m128i
121 aesni_dec(int rounds, const __m128i *keysched, const __m128i from)
126 tmp = from ^ keysched[0];
128 for (i = 0; i < rounds; i++)
129 tmp = _mm_aesdec_si128(tmp, keysched[i + 1]);
131 return _mm_aesdeclast_si128(tmp, keysched[i + 1]);