aboutsummaryrefslogtreecommitdiffstats
path: root/lib/librte_net/net_crc_sse.h
blob: 7eae14791287a5af0655d06d0e67b7df650de12e (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
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
/*-
 *   BSD LICENSE
 *
 *   Copyright(c) 2017 Intel Corporation.
 *   All rights reserved.
 *
 *   Redistribution and use in source and binary forms, with or without
 *   modification, are permitted provided that the following conditions
 *   are met:
 *
 *     * Redistributions of source code must retain the above copyright
 *       notice, this list of conditions and the following disclaimer.
 *     * Redistributions in binary form must reproduce the above copyright
 *       notice, this list of conditions and the following disclaimer in
 *       the documentation and/or other materials provided with the
 *       distribution.
 *     * Neither the name of Intel Corporation nor the names of its
 *       contributors may be used to endorse or promote products derived
 *       from this software without specific prior written permission.
 *
 *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
 *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
 *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */

#ifndef _RTE_NET_CRC_SSE_H_
#define _RTE_NET_CRC_SSE_H_

#include <rte_branch_prediction.h>

#include <x86intrin.h>
#include <cpuid.h>

#ifdef __cplusplus
extern "C" {
#endif

/** PCLMULQDQ CRC computation context structure */
struct crc_pclmulqdq_ctx {
	__m128i rk1_rk2;
	__m128i rk5_rk6;
	__m128i rk7_rk8;
};

struct crc_pclmulqdq_ctx crc32_eth_pclmulqdq __rte_aligned(16);
struct crc_pclmulqdq_ctx crc16_ccitt_pclmulqdq __rte_aligned(16);
/**
 * @brief Performs one folding round
 *
 * Logically function operates as follows:
 *     DATA = READ_NEXT_16BYTES();
 *     F1 = LSB8(FOLD)
 *     F2 = MSB8(FOLD)
 *     T1 = CLMUL(F1, RK1)
 *     T2 = CLMUL(F2, RK2)
 *     FOLD = XOR(T1, T2, DATA)
 *
 * @param data_block
 *   16 byte data block
 * @param precomp
 *   Precomputed rk1 constant
 * @param fold
 *   Current16 byte folded data
 *
 * @return
 *   New 16 byte folded data
 */
static __rte_always_inline __m128i
crcr32_folding_round(__m128i data_block,
		__m128i precomp,
		__m128i fold)
{
	__m128i tmp0 = _mm_clmulepi64_si128(fold, precomp, 0x01);
	__m128i tmp1 = _mm_clmulepi64_si128(fold, precomp, 0x10);

	return _mm_xor_si128(tmp1, _mm_xor_si128(data_block, tmp0));
}

/**
 * Performs reduction from 128 bits to 64 bits
 *
 * @param data128
 *   128 bits data to be reduced
 * @param precomp
 *   precomputed constants rk5, rk6
 *
 * @return
 *  64 bits reduced data
 */

static __rte_always_inline __m128i
crcr32_reduce_128_to_64(__m128i data128, __m128i precomp)
{
	__m128i tmp0, tmp1, tmp2;

	/* 64b fold */
	tmp0 = _mm_clmulepi64_si128(data128, precomp, 0x00);
	tmp1 = _mm_srli_si128(data128, 8);
	tmp0 = _mm_xor_si128(tmp0, tmp1);

	/* 32b fold */
	tmp2 = _mm_slli_si128(tmp0, 4);
	tmp1 = _mm_clmulepi64_si128(tmp2, precomp, 0x10);

	return _mm_xor_si128(tmp1, tmp0);
}

/**
 * Performs Barret's reduction from 64 bits to 32 bits
 *
 * @param data64
 *   64 bits data to be reduced
 * @param precomp
 *   rk7 precomputed constant
 *
 * @return
 *   reduced 32 bits data
 */

static __rte_always_inline uint32_t
crcr32_reduce_64_to_32(__m128i data64, __m128i precomp)
{
	static const uint32_t mask1[4] __rte_aligned(16) = {
		0xffffffff, 0xffffffff, 0x00000000, 0x00000000
	};

	static const uint32_t mask2[4] __rte_aligned(16) = {
		0x00000000, 0xffffffff, 0xffffffff, 0xffffffff
	};
	__m128i tmp0, tmp1, tmp2;

	tmp0 = _mm_and_si128(data64, _mm_load_si128((const __m128i *)mask2));

	tmp1 = _mm_clmulepi64_si128(tmp0, precomp, 0x00);
	tmp1 = _mm_xor_si128(tmp1, tmp0);
	tmp1 = _mm_and_si128(tmp1, _mm_load_si128((const __m128i *)mask1));

	tmp2 = _mm_clmulepi64_si128(tmp1, precomp, 0x10);
	tmp2 = _mm_xor_si128(tmp2, tmp1);
	tmp2 = _mm_xor_si128(tmp2, tmp0);

	return _mm_extract_epi32(tmp2, 2);
}

static const uint8_t crc_xmm_shift_tab[48] __rte_aligned(16) = {
	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
	0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
	0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
};

/**
 * Shifts left 128 bit register by specified number of bytes
 *
 * @param reg
 *   128 bit value
 * @param num
 *   number of bytes to shift left reg by (0-16)
 *
 * @return
 *   reg << (num * 8)
 */

static __rte_always_inline __m128i
xmm_shift_left(__m128i reg, const unsigned int num)
{
	const __m128i *p = (const __m128i *)(crc_xmm_shift_tab + 16 - num);

	return _mm_shuffle_epi8(reg, _mm_loadu_si128(p));
}

static __rte_always_inline uint32_t
crc32_eth_calc_pclmulqdq(
	const uint8_t *data,
	uint32_t data_len,
	uint32_t crc,
	const struct crc_pclmulqdq_ctx *params)
{
	__m128i temp, fold, k;
	uint32_t n;

	/* Get CRC init value */
	temp = _mm_insert_epi32(_mm_setzero_si128(), crc, 0);

	/**
	 * Folding all data into single 16 byte data block
	 * Assumes: fold holds first 16 bytes of data
	 */

	if (unlikely(data_len < 32)) {
		if (unlikely(data_len == 16)) {
			/* 16 bytes */
			fold = _mm_loadu_si128((const __m128i *)data);
			fold = _mm_xor_si128(fold, temp);
			goto reduction_128_64;
		}

		if (unlikely(data_len < 16)) {
			/* 0 to 15 bytes */
			uint8_t buffer[16] __rte_aligned(16);

			memset(buffer, 0, sizeof(buffer));
			memcpy(buffer, data, data_len);

			fold = _mm_load_si128((const __m128i *)buffer);
			fold = _mm_xor_si128(fold, temp);
			if (unlikely(data_len < 4)) {
				fold = xmm_shift_left(fold, 8 - data_len);
				goto barret_reduction;
			}
			fold = xmm_shift_left(fold, 16 - data_len);
			goto reduction_128_64;
		}
		/* 17 to 31 bytes */
		fold = _mm_loadu_si128((const __m128i *)data);
		fold = _mm_xor_si128(fold, temp);
		n = 16;
		k = params->rk1_rk2;
		goto partial_bytes;
	}

	/** At least 32 bytes in the buffer */
	/** Apply CRC initial value */
	fold = _mm_loadu_si128((const __m128i *)data);
	fold = _mm_xor_si128(fold, temp);

	/** Main folding loop - the last 16 bytes is processed separately */
	k = params->rk1_rk2;
	for (n = 16; (n + 16) <= data_len; n += 16) {
		temp = _mm_loadu_si128((const __m128i *)&data[n]);
		fold = crcr32_folding_round(temp, k, fold);
	}

partial_bytes:
	if (likely(n < data_len)) {

		const uint32_t mask3[4] __rte_aligned(16) = {
			0x80808080, 0x80808080, 0x80808080, 0x80808080
		};

		const uint8_t shf_table[32] __rte_aligned(16) = {
			0x00, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
			0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
			0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
			0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f
		};

		__m128i last16, a, b;

		last16 = _mm_loadu_si128((const __m128i *)&data[data_len - 16]);

		temp = _mm_loadu_si128((const __m128i *)
			&shf_table[data_len & 15]);
		a = _mm_shuffle_epi8(fold, temp);

		temp = _mm_xor_si128(temp,
			_mm_load_si128((const __m128i *)mask3));
		b = _mm_shuffle_epi8(fold, temp);
		b = _mm_blendv_epi8(b, last16, temp);

		/* k = rk1 & rk2 */
		temp = _mm_clmulepi64_si128(a, k, 0x01);
		fold = _mm_clmulepi64_si128(a, k, 0x10);

		fold = _mm_xor_si128(fold, temp);
		fold = _mm_xor_si128(fold, b);
	}

	/** Reduction 128 -> 32 Assumes: fold holds 128bit folded data */
reduction_128_64:
	k = params->rk5_rk6;
	fold = crcr32_reduce_128_to_64(fold, k);

barret_reduction:
	k = params->rk7_rk8;
	n = crcr32_reduce_64_to_32(fold, k);

	return n;
}


static inline void
rte_net_crc_sse42_init(void)
{
	uint64_t k1, k2, k5, k6;
	uint64_t p = 0, q = 0;

	/** Initialize CRC16 data */
	k1 = 0x189aeLLU;
	k2 = 0x8e10LLU;
	k5 = 0x189aeLLU;
	k6 = 0x114aaLLU;
	q =  0x11c581910LLU;
	p =  0x10811LLU;

	/** Save the params in context structure */
	crc16_ccitt_pclmulqdq.rk1_rk2 =
		_mm_setr_epi64(_mm_cvtsi64_m64(k1), _mm_cvtsi64_m64(k2));
	crc16_ccitt_pclmulqdq.rk5_rk6 =
		_mm_setr_epi64(_mm_cvtsi64_m64(k5), _mm_cvtsi64_m64(k6));
	crc16_ccitt_pclmulqdq.rk7_rk8 =
		_mm_setr_epi64(_mm_cvtsi64_m64(q), _mm_cvtsi64_m64(p));

	/** Initialize CRC32 data */
	k1 = 0xccaa009eLLU;
	k2 = 0x1751997d0LLU;
	k5 = 0xccaa009eLLU;
	k6 = 0x163cd6124LLU;
	q =  0x1f7011640LLU;
	p =  0x1db710641LLU;

	/** Save the params in context structure */
	crc32_eth_pclmulqdq.rk1_rk2 =
		_mm_setr_epi64(_mm_cvtsi64_m64(k1), _mm_cvtsi64_m64(k2));
	crc32_eth_pclmulqdq.rk5_rk6 =
		_mm_setr_epi64(_mm_cvtsi64_m64(k5), _mm_cvtsi64_m64(k6));
	crc32_eth_pclmulqdq.rk7_rk8 =
		_mm_setr_epi64(_mm_cvtsi64_m64(q), _mm_cvtsi64_m64(p));

	/**
	 * Reset the register as following calculation may
	 * use other data types such as float, double, etc.
	 */
	_mm_empty();

}

static inline uint32_t
rte_crc16_ccitt_sse42_handler(const uint8_t *data,
	uint32_t data_len)
{
	/** return 16-bit CRC value */
	return (uint16_t)~crc32_eth_calc_pclmulqdq(data,
		data_len,
		0xffff,
		&crc16_ccitt_pclmulqdq);
}

static inline uint32_t
rte_crc32_eth_sse42_handler(const uint8_t *data,
	uint32_t data_len)
{
	return ~crc32_eth_calc_pclmulqdq(data,
		data_len,
		0xffffffffUL,
		&crc32_eth_pclmulqdq);
}

#ifdef __cplusplus
}
#endif

#endif /* _RTE_NET_CRC_SSE_H_ */