summaryrefslogtreecommitdiff
path: root/arch/x86/crypto/sha1_ssse3_glue.c
blob: 7c48e8b20848e5c890825f25db91c63616dce65d (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
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
/*
 * Cryptographic API.
 *
 * Glue code for the SHA1 Secure Hash Algorithm assembler implementation using
 * Supplemental SSE3 instructions.
 *
 * This file is based on sha1_generic.c
 *
 * Copyright (c) Alan Smithee.
 * Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
 * Copyright (c) Jean-Francois Dive <jef@linuxbe.org>
 * Copyright (c) Mathias Krause <minipli@googlemail.com>
 * Copyright (c) Chandramouli Narayanan <mouli@linux.intel.com>
 *
 * 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.
 *
 */

#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt

#include <crypto/internal/hash.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/cryptohash.h>
#include <linux/types.h>
#include <crypto/sha.h>
#include <crypto/sha1_base.h>
#include <asm/fpu/api.h>


asmlinkage void sha1_transform_ssse3(u32 *digest, const char *data,
				     unsigned int rounds);
#ifdef CONFIG_AS_AVX
asmlinkage void sha1_transform_avx(u32 *digest, const char *data,
				   unsigned int rounds);
#endif
#ifdef CONFIG_AS_AVX2
#define SHA1_AVX2_BLOCK_OPTSIZE	4	/* optimal 4*64 bytes of SHA1 blocks */

asmlinkage void sha1_transform_avx2(u32 *digest, const char *data,
				    unsigned int rounds);
#endif

static void (*sha1_transform_asm)(u32 *, const char *, unsigned int);

static int sha1_ssse3_update(struct shash_desc *desc, const u8 *data,
			     unsigned int len)
{
	struct sha1_state *sctx = shash_desc_ctx(desc);

	if (!irq_fpu_usable() ||
	    (sctx->count % SHA1_BLOCK_SIZE) + len < SHA1_BLOCK_SIZE)
		return crypto_sha1_update(desc, data, len);

	/* make sure casting to sha1_block_fn() is safe */
	BUILD_BUG_ON(offsetof(struct sha1_state, state) != 0);

	kernel_fpu_begin();
	sha1_base_do_update(desc, data, len,
			    (sha1_block_fn *)sha1_transform_asm);
	kernel_fpu_end();

	return 0;
}

static int sha1_ssse3_finup(struct shash_desc *desc, const u8 *data,
			      unsigned int len, u8 *out)
{
	if (!irq_fpu_usable())
		return crypto_sha1_finup(desc, data, len, out);

	kernel_fpu_begin();
	if (len)
		sha1_base_do_update(desc, data, len,
				    (sha1_block_fn *)sha1_transform_asm);
	sha1_base_do_finalize(desc, (sha1_block_fn *)sha1_transform_asm);
	kernel_fpu_end();

	return sha1_base_finish(desc, out);
}

/* Add padding and return the message digest. */
static int sha1_ssse3_final(struct shash_desc *desc, u8 *out)
{
	return sha1_ssse3_finup(desc, NULL, 0, out);
}

#ifdef CONFIG_AS_AVX2
static void sha1_apply_transform_avx2(u32 *digest, const char *data,
				unsigned int rounds)
{
	/* Select the optimal transform based on data block size */
	if (rounds >= SHA1_AVX2_BLOCK_OPTSIZE)
		sha1_transform_avx2(digest, data, rounds);
	else
		sha1_transform_avx(digest, data, rounds);
}
#endif

static struct shash_alg alg = {
	.digestsize	=	SHA1_DIGEST_SIZE,
	.init		=	sha1_base_init,
	.update		=	sha1_ssse3_update,
	.final		=	sha1_ssse3_final,
	.finup		=	sha1_ssse3_finup,
	.descsize	=	sizeof(struct sha1_state),
	.base		=	{
		.cra_name	=	"sha1",
		.cra_driver_name=	"sha1-ssse3",
		.cra_priority	=	150,
		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
		.cra_blocksize	=	SHA1_BLOCK_SIZE,
		.cra_module	=	THIS_MODULE,
	}
};

#ifdef CONFIG_AS_AVX
static bool __init avx_usable(void)
{
	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL)) {
		if (cpu_has_avx)
			pr_info("AVX detected but unusable.\n");
		return false;
	}

	return true;
}

#ifdef CONFIG_AS_AVX2
static bool __init avx2_usable(void)
{
	if (avx_usable() && cpu_has_avx2 && boot_cpu_has(X86_FEATURE_BMI1) &&
	    boot_cpu_has(X86_FEATURE_BMI2))
		return true;

	return false;
}
#endif
#endif

static int __init sha1_ssse3_mod_init(void)
{
	char *algo_name;

	/* test for SSSE3 first */
	if (cpu_has_ssse3) {
		sha1_transform_asm = sha1_transform_ssse3;
		algo_name = "SSSE3";
	}

#ifdef CONFIG_AS_AVX
	/* allow AVX to override SSSE3, it's a little faster */
	if (avx_usable()) {
		sha1_transform_asm = sha1_transform_avx;
		algo_name = "AVX";
#ifdef CONFIG_AS_AVX2
		/* allow AVX2 to override AVX, it's a little faster */
		if (avx2_usable()) {
			sha1_transform_asm = sha1_apply_transform_avx2;
			algo_name = "AVX2";
		}
#endif
	}
#endif

	if (sha1_transform_asm) {
		pr_info("Using %s optimized SHA-1 implementation\n", algo_name);
		return crypto_register_shash(&alg);
	}
	pr_info("Neither AVX nor AVX2 nor SSSE3 is available/usable.\n");

	return -ENODEV;
}

static void __exit sha1_ssse3_mod_fini(void)
{
	crypto_unregister_shash(&alg);
}

module_init(sha1_ssse3_mod_init);
module_exit(sha1_ssse3_mod_fini);

MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, Supplemental SSE3 accelerated");

MODULE_ALIAS_CRYPTO("sha1");