summaryrefslogtreecommitdiff
path: root/arch/x86/crypto/sha256_ssse3_glue.c
blob: f248546da1caa956014dfd9648814ad37f2ca8d3 (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
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
/*
 * Cryptographic API.
 *
 * Glue code for the SHA256 Secure Hash Algorithm assembler
 * implementation using supplemental SSE3 / AVX / AVX2 instructions.
 *
 * This file is based on sha256_generic.c
 *
 * Copyright (C) 2013 Intel Corporation.
 *
 * Author:
 *     Tim Chen <tim.c.chen@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.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 */


#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 <asm/byteorder.h>
#include <asm/i387.h>
#include <asm/xcr.h>
#include <asm/xsave.h>
#include <linux/string.h>

asmlinkage void sha256_transform_ssse3(const char *data, u32 *digest,
				     u64 rounds);
#ifdef CONFIG_AS_AVX
asmlinkage void sha256_transform_avx(const char *data, u32 *digest,
				     u64 rounds);
#endif
#ifdef CONFIG_AS_AVX2
asmlinkage void sha256_transform_rorx(const char *data, u32 *digest,
				     u64 rounds);
#endif

static asmlinkage void (*sha256_transform_asm)(const char *, u32 *, u64);


static int sha256_ssse3_init(struct shash_desc *desc)
{
	struct sha256_state *sctx = shash_desc_ctx(desc);

	sctx->state[0] = SHA256_H0;
	sctx->state[1] = SHA256_H1;
	sctx->state[2] = SHA256_H2;
	sctx->state[3] = SHA256_H3;
	sctx->state[4] = SHA256_H4;
	sctx->state[5] = SHA256_H5;
	sctx->state[6] = SHA256_H6;
	sctx->state[7] = SHA256_H7;
	sctx->count = 0;

	return 0;
}

static int __sha256_ssse3_update(struct shash_desc *desc, const u8 *data,
			       unsigned int len, unsigned int partial)
{
	struct sha256_state *sctx = shash_desc_ctx(desc);
	unsigned int done = 0;

	sctx->count += len;

	if (partial) {
		done = SHA256_BLOCK_SIZE - partial;
		memcpy(sctx->buf + partial, data, done);
		sha256_transform_asm(sctx->buf, sctx->state, 1);
	}

	if (len - done >= SHA256_BLOCK_SIZE) {
		const unsigned int rounds = (len - done) / SHA256_BLOCK_SIZE;

		sha256_transform_asm(data + done, sctx->state, (u64) rounds);

		done += rounds * SHA256_BLOCK_SIZE;
	}

	memcpy(sctx->buf, data + done, len - done);

	return 0;
}

static int sha256_ssse3_update(struct shash_desc *desc, const u8 *data,
			     unsigned int len)
{
	struct sha256_state *sctx = shash_desc_ctx(desc);
	unsigned int partial = sctx->count % SHA256_BLOCK_SIZE;
	int res;

	/* Handle the fast case right here */
	if (partial + len < SHA256_BLOCK_SIZE) {
		sctx->count += len;
		memcpy(sctx->buf + partial, data, len);

		return 0;
	}

	if (!irq_fpu_usable()) {
		res = crypto_sha256_update(desc, data, len);
	} else {
		kernel_fpu_begin();
		res = __sha256_ssse3_update(desc, data, len, partial);
		kernel_fpu_end();
	}

	return res;
}


/* Add padding and return the message digest. */
static int sha256_ssse3_final(struct shash_desc *desc, u8 *out)
{
	struct sha256_state *sctx = shash_desc_ctx(desc);
	unsigned int i, index, padlen;
	__be32 *dst = (__be32 *)out;
	__be64 bits;
	static const u8 padding[SHA256_BLOCK_SIZE] = { 0x80, };

	bits = cpu_to_be64(sctx->count << 3);

	/* Pad out to 56 mod 64 and append length */
	index = sctx->count % SHA256_BLOCK_SIZE;
	padlen = (index < 56) ? (56 - index) : ((SHA256_BLOCK_SIZE+56)-index);

	if (!irq_fpu_usable()) {
		crypto_sha256_update(desc, padding, padlen);
		crypto_sha256_update(desc, (const u8 *)&bits, sizeof(bits));
	} else {
		kernel_fpu_begin();
		/* We need to fill a whole block for __sha256_ssse3_update() */
		if (padlen <= 56) {
			sctx->count += padlen;
			memcpy(sctx->buf + index, padding, padlen);
		} else {
			__sha256_ssse3_update(desc, padding, padlen, index);
		}
		__sha256_ssse3_update(desc, (const u8 *)&bits,
					sizeof(bits), 56);
		kernel_fpu_end();
	}

	/* Store state in digest */
	for (i = 0; i < 8; i++)
		dst[i] = cpu_to_be32(sctx->state[i]);

	/* Wipe context */
	memset(sctx, 0, sizeof(*sctx));

	return 0;
}

static int sha256_ssse3_export(struct shash_desc *desc, void *out)
{
	struct sha256_state *sctx = shash_desc_ctx(desc);

	memcpy(out, sctx, sizeof(*sctx));

	return 0;
}

static int sha256_ssse3_import(struct shash_desc *desc, const void *in)
{
	struct sha256_state *sctx = shash_desc_ctx(desc);

	memcpy(sctx, in, sizeof(*sctx));

	return 0;
}

static int sha224_ssse3_init(struct shash_desc *desc)
{
	struct sha256_state *sctx = shash_desc_ctx(desc);

	sctx->state[0] = SHA224_H0;
	sctx->state[1] = SHA224_H1;
	sctx->state[2] = SHA224_H2;
	sctx->state[3] = SHA224_H3;
	sctx->state[4] = SHA224_H4;
	sctx->state[5] = SHA224_H5;
	sctx->state[6] = SHA224_H6;
	sctx->state[7] = SHA224_H7;
	sctx->count = 0;

	return 0;
}

static int sha224_ssse3_final(struct shash_desc *desc, u8 *hash)
{
	u8 D[SHA256_DIGEST_SIZE];

	sha256_ssse3_final(desc, D);

	memcpy(hash, D, SHA224_DIGEST_SIZE);
	memset(D, 0, SHA256_DIGEST_SIZE);

	return 0;
}

static struct shash_alg algs[] = { {
	.digestsize	=	SHA256_DIGEST_SIZE,
	.init		=	sha256_ssse3_init,
	.update		=	sha256_ssse3_update,
	.final		=	sha256_ssse3_final,
	.export		=	sha256_ssse3_export,
	.import		=	sha256_ssse3_import,
	.descsize	=	sizeof(struct sha256_state),
	.statesize	=	sizeof(struct sha256_state),
	.base		=	{
		.cra_name	=	"sha256",
		.cra_driver_name =	"sha256-ssse3",
		.cra_priority	=	150,
		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
		.cra_blocksize	=	SHA256_BLOCK_SIZE,
		.cra_module	=	THIS_MODULE,
	}
}, {
	.digestsize	=	SHA224_DIGEST_SIZE,
	.init		=	sha224_ssse3_init,
	.update		=	sha256_ssse3_update,
	.final		=	sha224_ssse3_final,
	.export		=	sha256_ssse3_export,
	.import		=	sha256_ssse3_import,
	.descsize	=	sizeof(struct sha256_state),
	.statesize	=	sizeof(struct sha256_state),
	.base		=	{
		.cra_name	=	"sha224",
		.cra_driver_name =	"sha224-ssse3",
		.cra_priority	=	150,
		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
		.cra_blocksize	=	SHA224_BLOCK_SIZE,
		.cra_module	=	THIS_MODULE,
	}
} };

#ifdef CONFIG_AS_AVX
static bool __init avx_usable(void)
{
	u64 xcr0;

	if (!cpu_has_avx || !cpu_has_osxsave)
		return false;

	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
		pr_info("AVX detected but unusable.\n");

		return false;
	}

	return true;
}
#endif

static int __init sha256_ssse3_mod_init(void)
{
	/* test for SSSE3 first */
	if (cpu_has_ssse3)
		sha256_transform_asm = sha256_transform_ssse3;

#ifdef CONFIG_AS_AVX
	/* allow AVX to override SSSE3, it's a little faster */
	if (avx_usable()) {
#ifdef CONFIG_AS_AVX2
		if (boot_cpu_has(X86_FEATURE_AVX2) && boot_cpu_has(X86_FEATURE_BMI2))
			sha256_transform_asm = sha256_transform_rorx;
		else
#endif
			sha256_transform_asm = sha256_transform_avx;
	}
#endif

	if (sha256_transform_asm) {
#ifdef CONFIG_AS_AVX
		if (sha256_transform_asm == sha256_transform_avx)
			pr_info("Using AVX optimized SHA-256 implementation\n");
#ifdef CONFIG_AS_AVX2
		else if (sha256_transform_asm == sha256_transform_rorx)
			pr_info("Using AVX2 optimized SHA-256 implementation\n");
#endif
		else
#endif
			pr_info("Using SSSE3 optimized SHA-256 implementation\n");
		return crypto_register_shashes(algs, ARRAY_SIZE(algs));
	}
	pr_info("Neither AVX nor SSSE3 is available/usable.\n");

	return -ENODEV;
}

static void __exit sha256_ssse3_mod_fini(void)
{
	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
}

module_init(sha256_ssse3_mod_init);
module_exit(sha256_ssse3_mod_fini);

MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("SHA256 Secure Hash Algorithm, Supplemental SSE3 accelerated");

MODULE_ALIAS("sha256");
MODULE_ALIAS("sha224");