summaryrefslogtreecommitdiffhomepage
path: root/src/crypto/zinc/chacha20/chacha20.c
blob: 1d9168e6c1428a719d21638970382ead299df892 (plain)
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
/* SPDX-License-Identifier: GPL-2.0
 *
 * Copyright (C) 2015-2018 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
 *
 * Implementation of the ChaCha20 stream cipher.
 *
 * Information: https://cr.yp.to/chacha.html
 */

#include <zinc/chacha20.h>

#include <linux/kernel.h>
#include <crypto/algapi.h>

#ifndef HAVE_CHACHA20_ARCH_IMPLEMENTATION
void __init chacha20_fpu_init(void)
{
}
static inline bool chacha20_arch(u8 *out, const u8 *in, const size_t len,
				 const u32 key[8], const u32 counter[4],
				 simd_context_t simd_context)
{
	return false;
}
static inline bool hchacha20_arch(u8 *derived_key, const u8 *nonce,
				  const u8 *key, simd_context_t simd_context)
{
	return false;
}
#endif

#define EXPAND_32_BYTE_K 0x61707865U, 0x3320646eU, 0x79622d32U, 0x6b206574U

#define QUARTER_ROUND(x, a, b, c, d) ( \
	x[a] += x[b], \
	x[d] = rol32((x[d] ^ x[a]), 16), \
	x[c] += x[d], \
	x[b] = rol32((x[b] ^ x[c]), 12), \
	x[a] += x[b], \
	x[d] = rol32((x[d] ^ x[a]), 8), \
	x[c] += x[d], \
	x[b] = rol32((x[b] ^ x[c]), 7) \
)

#define C(i, j) (i * 4 + j)

#define DOUBLE_ROUND(x) ( \
	/* Column Round */ \
	QUARTER_ROUND(x, C(0, 0), C(1, 0), C(2, 0), C(3, 0)), \
	QUARTER_ROUND(x, C(0, 1), C(1, 1), C(2, 1), C(3, 1)), \
	QUARTER_ROUND(x, C(0, 2), C(1, 2), C(2, 2), C(3, 2)), \
	QUARTER_ROUND(x, C(0, 3), C(1, 3), C(2, 3), C(3, 3)), \
	/* Diagonal Round */ \
	QUARTER_ROUND(x, C(0, 0), C(1, 1), C(2, 2), C(3, 3)), \
	QUARTER_ROUND(x, C(0, 1), C(1, 2), C(2, 3), C(3, 0)), \
	QUARTER_ROUND(x, C(0, 2), C(1, 3), C(2, 0), C(3, 1)), \
	QUARTER_ROUND(x, C(0, 3), C(1, 0), C(2, 1), C(3, 2)) \
)

#define TWENTY_ROUNDS(x) ( \
	DOUBLE_ROUND(x), \
	DOUBLE_ROUND(x), \
	DOUBLE_ROUND(x), \
	DOUBLE_ROUND(x), \
	DOUBLE_ROUND(x), \
	DOUBLE_ROUND(x), \
	DOUBLE_ROUND(x), \
	DOUBLE_ROUND(x), \
	DOUBLE_ROUND(x), \
	DOUBLE_ROUND(x) \
)

static void chacha20_block_generic(__le32 *stream, u32 *state)
{
	u32 x[CHACHA20_BLOCK_WORDS];
	int i;

	for (i = 0; i < ARRAY_SIZE(x); ++i)
		x[i] = state[i];

	TWENTY_ROUNDS(x);

	for (i = 0; i < ARRAY_SIZE(x); ++i)
		stream[i] = cpu_to_le32(x[i] + state[i]);

	++state[12];
}

static void chacha20_generic(u8 *out, const u8 *in, u32 len, const u32 key[8],
			     const u32 counter[4])
{
	__le32 buf[CHACHA20_BLOCK_WORDS];
	u32 x[] = {
		EXPAND_32_BYTE_K,
		key[0], key[1], key[2], key[3],
		key[4], key[5], key[6], key[7],
		counter[0], counter[1], counter[2], counter[3]
	};

	if (out != in)
		memmove(out, in, len);

	while (len >= CHACHA20_BLOCK_SIZE) {
		chacha20_block_generic(buf, x);
		crypto_xor(out, (u8 *)buf, CHACHA20_BLOCK_SIZE);
		len -= CHACHA20_BLOCK_SIZE;
		out += CHACHA20_BLOCK_SIZE;
	}
	if (len) {
		chacha20_block_generic(buf, x);
		crypto_xor(out, (u8 *)buf, len);
	}
}

void chacha20(struct chacha20_ctx *state, u8 *dst, const u8 *src, u32 len,
	      simd_context_t simd_context)
{
	if (!chacha20_arch(dst, src, len, state->key, state->counter,
			   simd_context))
		chacha20_generic(dst, src, len, state->key, state->counter);
	state->counter[0] += (len + 63) / 64;
}
EXPORT_SYMBOL(chacha20);

static void hchacha20_generic(u8 derived_key[CHACHA20_KEY_SIZE],
			      const u8 nonce[HCHACHA20_NONCE_SIZE],
			      const u8 key[HCHACHA20_KEY_SIZE])
{
	__le32 *out = (__force __le32 *)derived_key;
	u32 x[] = { EXPAND_32_BYTE_K,
		    get_unaligned_le32(key + 0),
		    get_unaligned_le32(key + 4),
		    get_unaligned_le32(key + 8),
		    get_unaligned_le32(key + 12),
		    get_unaligned_le32(key + 16),
		    get_unaligned_le32(key + 20),
		    get_unaligned_le32(key + 24),
		    get_unaligned_le32(key + 28),
		    get_unaligned_le32(nonce + 0),
		    get_unaligned_le32(nonce + 4),
		    get_unaligned_le32(nonce + 8),
		    get_unaligned_le32(nonce + 12)
	};

	TWENTY_ROUNDS(x);

	out[0] = cpu_to_le32(x[0]);
	out[1] = cpu_to_le32(x[1]);
	out[2] = cpu_to_le32(x[2]);
	out[3] = cpu_to_le32(x[3]);
	out[4] = cpu_to_le32(x[12]);
	out[5] = cpu_to_le32(x[13]);
	out[6] = cpu_to_le32(x[14]);
	out[7] = cpu_to_le32(x[15]);
}

/* Derived key should be 32-bit aligned */
void hchacha20(u8 derived_key[CHACHA20_KEY_SIZE],
	       const u8 nonce[HCHACHA20_NONCE_SIZE],
	       const u8 key[HCHACHA20_KEY_SIZE], simd_context_t simd_context)
{
	if (!hchacha20_arch(derived_key, nonce, key, simd_context))
		hchacha20_generic(derived_key, nonce, key);
}
/* Deliberately not EXPORT_SYMBOL'd, since there are few reasons why somebody
 * should be using this directly, rather than via xchacha20. Revisit only in
 * the unlikely event that somebody has a good reason to export this.
 */