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
|
/*
* ChaCha and HChaCha functions (ARM64 optimized)
*
* Copyright (C) 2016 - 2017 Linaro, Ltd. <ard.biesheuvel@linaro.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* Based on:
* ChaCha20 256-bit cipher algorithm, RFC7539, SIMD glue code
*
* Copyright (C) 2015 Martin Willi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*/
#include <crypto/chacha.h>
#include <crypto/internal/simd.h>
#include <linux/jump_label.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <asm/hwcap.h>
#include <asm/neon.h>
#include <asm/simd.h>
asmlinkage void chacha_block_xor_neon(const struct chacha_state *state,
u8 *dst, const u8 *src, int nrounds);
asmlinkage void chacha_4block_xor_neon(const struct chacha_state *state,
u8 *dst, const u8 *src,
int nrounds, int bytes);
asmlinkage void hchacha_block_neon(const struct chacha_state *state,
u32 out[HCHACHA_OUT_WORDS], int nrounds);
static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
static void chacha_doneon(struct chacha_state *state, u8 *dst, const u8 *src,
int bytes, int nrounds)
{
while (bytes > 0) {
int l = min(bytes, CHACHA_BLOCK_SIZE * 5);
if (l <= CHACHA_BLOCK_SIZE) {
u8 buf[CHACHA_BLOCK_SIZE];
memcpy(buf, src, l);
chacha_block_xor_neon(state, buf, buf, nrounds);
memcpy(dst, buf, l);
state->x[12] += 1;
break;
}
chacha_4block_xor_neon(state, dst, src, nrounds, l);
bytes -= l;
src += l;
dst += l;
state->x[12] += DIV_ROUND_UP(l, CHACHA_BLOCK_SIZE);
}
}
void hchacha_block_arch(const struct chacha_state *state,
u32 out[HCHACHA_OUT_WORDS], int nrounds)
{
if (!static_branch_likely(&have_neon) || !crypto_simd_usable()) {
hchacha_block_generic(state, out, nrounds);
} else {
kernel_neon_begin();
hchacha_block_neon(state, out, nrounds);
kernel_neon_end();
}
}
EXPORT_SYMBOL(hchacha_block_arch);
void chacha_crypt_arch(struct chacha_state *state, u8 *dst, const u8 *src,
unsigned int bytes, int nrounds)
{
if (!static_branch_likely(&have_neon) || bytes <= CHACHA_BLOCK_SIZE ||
!crypto_simd_usable())
return chacha_crypt_generic(state, dst, src, bytes, nrounds);
do {
unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
kernel_neon_begin();
chacha_doneon(state, dst, src, todo, nrounds);
kernel_neon_end();
bytes -= todo;
src += todo;
dst += todo;
} while (bytes);
}
EXPORT_SYMBOL(chacha_crypt_arch);
bool chacha_is_arch_optimized(void)
{
return static_key_enabled(&have_neon);
}
EXPORT_SYMBOL(chacha_is_arch_optimized);
static int __init chacha_simd_mod_init(void)
{
if (cpu_have_named_feature(ASIMD))
static_branch_enable(&have_neon);
return 0;
}
subsys_initcall(chacha_simd_mod_init);
static void __exit chacha_simd_mod_exit(void)
{
}
module_exit(chacha_simd_mod_exit);
MODULE_DESCRIPTION("ChaCha and HChaCha functions (ARM64 optimized)");
MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
MODULE_LICENSE("GPL v2");
|
