summaryrefslogtreecommitdiff
path: root/lib/librte_eal/common/include/rte_memcpy.h
blob: fd2a296dac8342a6bdb1b9453a22ad78e89686ba (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
/*-
 *   BSD LICENSE
 * 
 *   Copyright(c) 2010-2012 Intel Corporation. All rights reserved.
 *   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.
 * 
 *  version: DPDK.L.1.2.3-3
 */

#ifndef _RTE_MEMCPY_H_
#define _RTE_MEMCPY_H_

/**
 * @file
 *
 * Functions for SSE implementation of memcpy().
 */

#include <stdint.h>
#include <string.h>

#ifdef __cplusplus
extern "C" {
#endif

/**
 * Copy 16 bytes from one location to another using optimised SSE
 * instructions. The locations should not overlap.
 *
 * @param dst
 *   Pointer to the destination of the data.
 * @param src
 *   Pointer to the source data.
 */
static inline void
rte_mov16(uint8_t *dst, const uint8_t *src)
{
	asm volatile ("movdqu (%[src]), %%xmm0\n\t"
		      "movdqu %%xmm0, (%[dst])\n\t"
		      :
		      : [src] "r" (src),
			[dst] "r"(dst)
		      : "xmm0", "memory");
}

/**
 * Copy 32 bytes from one location to another using optimised SSE
 * instructions. The locations should not overlap.
 *
 * @param dst
 *   Pointer to the destination of the data.
 * @param src
 *   Pointer to the source data.
 */
static inline void
rte_mov32(uint8_t *dst, const uint8_t *src)
{
	asm volatile ("movdqu (%[src]), %%xmm0\n\t"
		      "movdqu 16(%[src]), %%xmm1\n\t"
		      "movdqu %%xmm0, (%[dst])\n\t"
		      "movdqu %%xmm1, 16(%[dst])"
		      :
		      : [src] "r" (src),
			[dst] "r"(dst)
		      : "xmm0", "xmm1", "memory");
}

/**
 * Copy 48 bytes from one location to another using optimised SSE
 * instructions. The locations should not overlap.
 *
 * @param dst
 *   Pointer to the destination of the data.
 * @param src
 *   Pointer to the source data.
 */
static inline void
rte_mov48(uint8_t *dst, const uint8_t *src)
{
	asm volatile ("movdqu (%[src]), %%xmm0\n\t"
		      "movdqu 16(%[src]), %%xmm1\n\t"
		      "movdqu 32(%[src]), %%xmm2\n\t"
		      "movdqu %%xmm0, (%[dst])\n\t"
		      "movdqu %%xmm1, 16(%[dst])\n\t"
		      "movdqu %%xmm2, 32(%[dst])"
		      :
		      : [src] "r" (src),
			[dst] "r"(dst)
		      : "xmm0", "xmm1", "memory");
}

/**
 * Copy 64 bytes from one location to another using optimised SSE
 * instructions. The locations should not overlap.
 *
 * @param dst
 *   Pointer to the destination of the data.
 * @param src
 *   Pointer to the source data.
 */
static inline void
rte_mov64(uint8_t *dst, const uint8_t *src)
{
	asm volatile ("movdqu (%[src]), %%xmm0\n\t"
		      "movdqu 16(%[src]), %%xmm1\n\t"
		      "movdqu 32(%[src]), %%xmm2\n\t"
		      "movdqu 48(%[src]), %%xmm3\n\t"
		      "movdqu %%xmm0, (%[dst])\n\t"
		      "movdqu %%xmm1, 16(%[dst])\n\t"
		      "movdqu %%xmm2, 32(%[dst])\n\t"
		      "movdqu %%xmm3, 48(%[dst])"
		      :
		      : [src] "r" (src),
			[dst] "r"(dst)
		      : "xmm0", "xmm1", "xmm2", "xmm3","memory");
}

/**
 * Copy 128 bytes from one location to another using optimised SSE
 * instructions. The locations should not overlap.
 *
 * @param dst
 *   Pointer to the destination of the data.
 * @param src
 *   Pointer to the source data.
 */
static inline void
rte_mov128(uint8_t *dst, const uint8_t *src)
{
	asm volatile ("movdqu (%[src]), %%xmm0\n\t"
		      "movdqu 16(%[src]), %%xmm1\n\t"
		      "movdqu 32(%[src]), %%xmm2\n\t"
		      "movdqu 48(%[src]), %%xmm3\n\t"
		      "movdqu 64(%[src]), %%xmm4\n\t"
		      "movdqu 80(%[src]), %%xmm5\n\t"
		      "movdqu 96(%[src]), %%xmm6\n\t"
		      "movdqu 112(%[src]), %%xmm7\n\t"
		      "movdqu %%xmm0, (%[dst])\n\t"
		      "movdqu %%xmm1, 16(%[dst])\n\t"
		      "movdqu %%xmm2, 32(%[dst])\n\t"
		      "movdqu %%xmm3, 48(%[dst])\n\t"
		      "movdqu %%xmm4, 64(%[dst])\n\t"
		      "movdqu %%xmm5, 80(%[dst])\n\t"
		      "movdqu %%xmm6, 96(%[dst])\n\t"
		      "movdqu %%xmm7, 112(%[dst])"
		      :
		      : [src] "r" (src),
			[dst] "r"(dst)
		      : "xmm0", "xmm1", "xmm2", "xmm3",
			"xmm4", "xmm5", "xmm6", "xmm7", "memory");
}

/**
 * Copy 256 bytes from one location to another using optimised SSE
 * instructions. The locations should not overlap.
 *
 * @param dst
 *   Pointer to the destination of the data.
 * @param src
 *   Pointer to the source data.
 */
static inline void
rte_mov256(uint8_t *dst, const uint8_t *src)
{
	/*
	 * There are 16XMM registers, but this function does not use
	 * them all so that it can still be compiled as 32bit
	 * code. The performance increase was neglible if all 16
	 * registers were used.
	 */
	rte_mov128(dst, src);
	rte_mov128(dst + 128, src + 128);
}

#ifdef RTE_MEMCPY_BUILTIN_CONSTANT_P
/**
 * Choose between compiler built-in implementation of memcpy or DPDK
 * implementation depending if size is a compile-time constant
 */
#define rte_memcpy(dst, src, n) \
	(__builtin_constant_p (n) ? \
	memcpy(dst, src, n) : rte_memcpy_func(dst, src, n))
#else
/**
 * Always use DPDK implementation.
 */
#define rte_memcpy rte_memcpy_func
#endif

/**
 * Copy bytes from one location to another. The locations must not overlap.
 *
 * @param dst
 *   Pointer to the destination of the data.
 * @param src
 *   Pointer to the source data.
 * @param n
 *   Number of bytes to copy.
 * @return
 *   Pointer to the destination data.
 */
static inline void *
rte_memcpy_func(void *dst, const void *src, size_t n)
{
	void *ret = dst;

	/* We can't copy < 16 bytes using XMM registers so do it manually. */
	if (n < 16) {
		if (n & 0x01) {
			*(uint8_t *)dst = *(const uint8_t *)src;
			dst = (uint8_t *)dst + 1;
			src = (const uint8_t *)src + 1;
		}
		if (n & 0x02) {
			*(uint16_t *)dst = *(const uint16_t *)src;
			dst = (uint16_t *)dst + 1;
			src = (const uint16_t *)src + 1;
		}
		if (n & 0x04) {
			/*
			 * NOTE: doing this as a 32bit copy causes "strict
			 * aliasing" compile errors, but worked fine for 64bit
			 * copy below, for unknown reasons.
			 */
			*(uint16_t *)dst = *(const uint16_t *)src;
			*((uint16_t *)dst + 1) = *((const uint16_t *)src + 1);
			dst = (uint32_t *)dst + 1;
			src = (const uint32_t *)src + 1;
		}
		if (n & 0x08) {
			*(uint64_t *)dst = *(const uint64_t *)src;
		}
		return ret;
	}

	/* Special fast cases for <= 128 bytes */
	if (n <= 32) {
		rte_mov16((uint8_t *)dst, (const uint8_t *)src);
		rte_mov16((uint8_t *)dst - 16 + n, (const uint8_t *)src - 16 + n);
		return ret;
	}

	if (n <= 64) {
		rte_mov32((uint8_t *)dst, (const uint8_t *)src);
		rte_mov32((uint8_t *)dst - 32 + n, (const uint8_t *)src - 32 + n);
		return ret;
	}

	if (n <= 128) {
		rte_mov64((uint8_t *)dst, (const uint8_t *)src);
		rte_mov64((uint8_t *)dst - 64 + n, (const uint8_t *)src - 64 + n);
		return ret;
	}

	/*
	 * For large copies > 128 bytes. This combination of 256, 64 and 16 byte
	 * copies was found to be faster than doing 128 and 32 byte copies as
	 * well.
	 */
	for ( ; n >= 256; n -= 256) {
		rte_mov256((uint8_t *)dst, (const uint8_t *)src);
		dst = (uint8_t *)dst + 256;
		src = (const uint8_t *)src + 256;
	}

	/*
	 * We split the remaining bytes (which will be less than 256) into
	 * 64byte (2^6) chunks.
	 * Using incrementing integers in the case labels of a switch statement
	 * enourages the compiler to use a jump table. To get incrementing
	 * integers, we shift the 2 relevant bits to the LSB position to first
	 * get decrementing integers, and then subtract.
	 */
	switch (3 - (n >> 6)) {
	case 0x00:
		rte_mov64((uint8_t *)dst, (const uint8_t *)src);
		n -= 64;
		dst = (uint8_t *)dst + 64;
		src = (const uint8_t *)src + 64;      /* fallthrough */
	case 0x01:
		rte_mov64((uint8_t *)dst, (const uint8_t *)src);
		n -= 64;
		dst = (uint8_t *)dst + 64;
		src = (const uint8_t *)src + 64;      /* fallthrough */
	case 0x02:
		rte_mov64((uint8_t *)dst, (const uint8_t *)src);
		n -= 64;
		dst = (uint8_t *)dst + 64;
		src = (const uint8_t *)src + 64;      /* fallthrough */
	default:
		;
	}

	/*
	 * We split the remaining bytes (which will be less than 64) into
	 * 16byte (2^4) chunks, using the same switch structure as above.
	 */
	switch (3 - (n >> 4)) {
	case 0x00:
		rte_mov16((uint8_t *)dst, (const uint8_t *)src);
		n -= 16;
		dst = (uint8_t *)dst + 16;
		src = (const uint8_t *)src + 16;      /* fallthrough */
	case 0x01:
		rte_mov16((uint8_t *)dst, (const uint8_t *)src);
		n -= 16;
		dst = (uint8_t *)dst + 16;
		src = (const uint8_t *)src + 16;      /* fallthrough */
	case 0x02:
		rte_mov16((uint8_t *)dst, (const uint8_t *)src);
		n -= 16;
		dst = (uint8_t *)dst + 16;
		src = (const uint8_t *)src + 16;      /* fallthrough */
	default:
		;
	}

	/* Copy any remaining bytes, without going beyond end of buffers */
	if (n != 0) {
		rte_mov16((uint8_t *)dst - 16 + n, (const uint8_t *)src - 16 + n);
	}
	return ret;
}

#ifdef __cplusplus
}
#endif

#endif /* _RTE_MEMCPY_H_ */