1/*-
2 * Copyright (c) 2021 The FreeBSD Foundation
3 *
4 * This software was developed by Andrew Turner under sponsorship from
5 * the FreeBSD Foundation.
6 *
7 * Redistribution and use in source and binary forms, with or without
8 * modification, are permitted provided that the following conditions
9 * are met:
10 * 1. Redistributions of source code must retain the above copyright
11 *    notice, this list of conditions and the following disclaimer.
12 * 2. Redistributions in binary form must reproduce the above copyright
13 *    notice, this list of conditions and the following disclaimer in the
14 *    documentation and/or other materials provided with the distribution.
15 *
16 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
17 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
18 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
19 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
20 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
21 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
22 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
23 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
24 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
25 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
26 * SUCH DAMAGE.
27 */
28
29#include <sys/types.h>
30
31#include <arm_neon.h>
32
33#include "sha256c_impl.h"
34
35void __hidden
36SHA256_Transform_arm64_impl(uint32_t * state, const unsigned char block[64],
37    const uint32_t K[64])
38{
39	uint32x4_t W[4];
40	uint32x4_t S[2];
41	uint32x4_t S_start[2];
42	uint32x4_t K_tmp, S_tmp;
43	int i;
44
45#define	A64_LOAD_W(x)							\
46    W[x] = vld1q_u32((const uint32_t *)(&block[(x) * 16]));		\
47    W[x] = vreinterpretq_u32_u8(vrev32q_u8(vreinterpretq_u8_u32(W[x])))
48
49	/* 1. Prepare the first part of the message schedule W. */
50	A64_LOAD_W(0);
51	A64_LOAD_W(1);
52	A64_LOAD_W(2);
53	A64_LOAD_W(3);
54
55	/* 2. Initialize working variables. */
56	S[0] = vld1q_u32(&state[0]);
57	S[1] = vld1q_u32(&state[4]);
58
59	S_start[0] = S[0];
60	S_start[1] = S[1];
61
62	/* 3. Mix. */
63	for (i = 0; i < 64; i += 16) {
64#define	A64_RNDr(i, ii)							\
65    K_tmp = vaddq_u32(W[i], vld1q_u32(&K[ii + i * 4]));			\
66    S_tmp = vsha256hq_u32(S[0], S[1], K_tmp);				\
67    S[1] = vsha256h2q_u32(S[1], S[0], K_tmp);				\
68    S[0] = S_tmp
69
70		A64_RNDr(0, i);
71		A64_RNDr(1, i);
72		A64_RNDr(2, i);
73		A64_RNDr(3, i);
74
75		if (i == 48)
76			break;
77
78#define	A64_MSCH(x)							\
79    W[x] = vsha256su0q_u32(W[x], W[(x + 1) % 4]);			\
80    W[x] = vsha256su1q_u32(W[x], W[(x + 2) % 4], W[(x + 3) % 4])
81
82		A64_MSCH(0);
83		A64_MSCH(1);
84		A64_MSCH(2);
85		A64_MSCH(3);
86	}
87
88	/* 4. Mix local working variables into global state */
89	S[0] = vaddq_u32(S[0], S_start[0]);
90	S[1] = vaddq_u32(S[1], S_start[1]);
91
92	vst1q_u32(&state[0], S[0]);
93	vst1q_u32(&state[4], S[1]);
94}
95