1/*
2 * Copyright (c) 2016 Thomas Pornin <pornin@bolet.org>
3 *
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:
11 *
12 * The above copyright notice and this permission notice shall be
13 * included in all copies or substantial portions of the Software.
14 *
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
22 * SOFTWARE.
23 */
24
25#include "inner.h"
26
27static inline void
28add_round_key(uint32_t *q, const uint32_t *sk)
29{
30	q[0] ^= sk[0];
31	q[1] ^= sk[1];
32	q[2] ^= sk[2];
33	q[3] ^= sk[3];
34	q[4] ^= sk[4];
35	q[5] ^= sk[5];
36	q[6] ^= sk[6];
37	q[7] ^= sk[7];
38}
39
40static inline void
41shift_rows(uint32_t *q)
42{
43	int i;
44
45	for (i = 0; i < 8; i ++) {
46		uint32_t x;
47
48		x = q[i];
49		q[i] = (x & 0x000000FF)
50			| ((x & 0x0000FC00) >> 2) | ((x & 0x00000300) << 6)
51			| ((x & 0x00F00000) >> 4) | ((x & 0x000F0000) << 4)
52			| ((x & 0xC0000000) >> 6) | ((x & 0x3F000000) << 2);
53	}
54}
55
56static inline uint32_t
57rotr16(uint32_t x)
58{
59	return (x << 16) | (x >> 16);
60}
61
62static inline void
63mix_columns(uint32_t *q)
64{
65	uint32_t q0, q1, q2, q3, q4, q5, q6, q7;
66	uint32_t r0, r1, r2, r3, r4, r5, r6, r7;
67
68	q0 = q[0];
69	q1 = q[1];
70	q2 = q[2];
71	q3 = q[3];
72	q4 = q[4];
73	q5 = q[5];
74	q6 = q[6];
75	q7 = q[7];
76	r0 = (q0 >> 8) | (q0 << 24);
77	r1 = (q1 >> 8) | (q1 << 24);
78	r2 = (q2 >> 8) | (q2 << 24);
79	r3 = (q3 >> 8) | (q3 << 24);
80	r4 = (q4 >> 8) | (q4 << 24);
81	r5 = (q5 >> 8) | (q5 << 24);
82	r6 = (q6 >> 8) | (q6 << 24);
83	r7 = (q7 >> 8) | (q7 << 24);
84
85	q[0] = q7 ^ r7 ^ r0 ^ rotr16(q0 ^ r0);
86	q[1] = q0 ^ r0 ^ q7 ^ r7 ^ r1 ^ rotr16(q1 ^ r1);
87	q[2] = q1 ^ r1 ^ r2 ^ rotr16(q2 ^ r2);
88	q[3] = q2 ^ r2 ^ q7 ^ r7 ^ r3 ^ rotr16(q3 ^ r3);
89	q[4] = q3 ^ r3 ^ q7 ^ r7 ^ r4 ^ rotr16(q4 ^ r4);
90	q[5] = q4 ^ r4 ^ r5 ^ rotr16(q5 ^ r5);
91	q[6] = q5 ^ r5 ^ r6 ^ rotr16(q6 ^ r6);
92	q[7] = q6 ^ r6 ^ r7 ^ rotr16(q7 ^ r7);
93}
94
95/* see inner.h */
96void
97br_aes_ct_bitslice_encrypt(unsigned num_rounds,
98	const uint32_t *skey, uint32_t *q)
99{
100	unsigned u;
101
102	add_round_key(q, skey);
103	for (u = 1; u < num_rounds; u ++) {
104		br_aes_ct_bitslice_Sbox(q);
105		shift_rows(q);
106		mix_columns(q);
107		add_round_key(q, skey + (u << 3));
108	}
109	br_aes_ct_bitslice_Sbox(q);
110	shift_rows(q);
111	add_round_key(q, skey + (num_rounds << 3));
112}
113