igt_x86.c 6.3 KB
Newer Older
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
/*
 * Copyright (c) 2013 Intel Corporation
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the "Software"),
 * to deal in the Software without restriction, including without limitation
 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
 * and/or sell copies of the Software, and to permit persons to whom the
 * Software is furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice (including the next
 * paragraph) shall be included in all copies or substantial portions of the
 * Software.
 *
 * 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.
 *
 * Authors:
 *    Chris Wilson <chris@chris-wilson.co.uk>
 *
 */

#include "config.h"

#ifdef HAVE_CPUID_H
#include <cpuid.h>
#else
#define __get_cpuid_max(x, y) 0
#define __cpuid(level, a, b, c, d) a = b = c = d = 0
#define __cpuid_count(level, count, a, b, c, d) a = b = c = d = 0
#endif

#include "igt_x86.h"
39 40 41
#include "igt_aux.h"

#include <stdint.h>
42
#include <stdio.h>
43
#include <string.h>
44

45 46 47 48 49 50 51
/**
 * SECTION:igt_x86
 * @short_description: x86 helper library
 * @title: x86
 * @include: igt_x86.h
 */

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
#define BASIC_CPUID 0x0
#define EXTENDED_CPUID 0x80000000

#ifndef bit_MMX
#define bit_MMX		(1 << 23)
#endif

#ifndef bit_SSE
#define bit_SSE		(1 << 25)
#endif

#ifndef bit_SSE2
#define bit_SSE2	(1 << 26)
#endif

#ifndef bit_SSE3
#define bit_SSE3	(1 << 0)
#endif

#ifndef bit_SSSE3
#define bit_SSSE3	(1 << 9)
#endif

#ifndef bit_SSE4_1
#define bit_SSE4_1	(1 << 19)
#endif

#ifndef bit_SSE4_2
#define bit_SSE4_2	(1 << 20)
#endif

#ifndef bit_OSXSAVE
#define bit_OSXSAVE	(1 << 27)
#endif

#ifndef bit_AVX
#define bit_AVX		(1 << 28)
#endif

#ifndef bit_AVX2
#define bit_AVX2	(1<<5)
#endif

#define xgetbv(index,eax,edx) \
	__asm__ ("xgetbv" : "=a"(eax), "=d"(edx) : "c" (index))

#define has_YMM 0x1

100
#if defined(__x86_64__) || defined(__i386__)
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
unsigned igt_x86_features(void)
{
	unsigned max = __get_cpuid_max(BASIC_CPUID, 0);
	unsigned eax, ebx, ecx, edx;
	unsigned features = 0;
	unsigned extra = 0;

	if (max >= 1) {
		__cpuid(1, eax, ebx, ecx, edx);

		if (ecx & bit_SSE3)
			features |= SSE3;

		if (ecx & bit_SSSE3)
			features |= SSSE3;

		if (ecx & bit_SSE4_1)
			features |= SSE4_1;

		if (ecx & bit_SSE4_2)
			features |= SSE4_2;

		if (ecx & bit_OSXSAVE) {
			unsigned int bv_eax, bv_ecx;
			xgetbv(0, bv_eax, bv_ecx);
			if ((bv_eax & 6) == 6)
				extra |= has_YMM;
		}

		if ((extra & has_YMM) && (ecx & bit_AVX))
			features |= AVX;

		if (edx & bit_MMX)
			features |= MMX;

		if (edx & bit_SSE)
			features |= SSE;

		if (edx & bit_SSE2)
			features |= SSE2;
	}

	if (max >= 7) {
		__cpuid_count(7, 0, eax, ebx, ecx, edx);

		if ((extra & has_YMM) && (ebx & bit_AVX2))
			features |= AVX2;
	}

	return features;
}

char *igt_x86_features_to_string(unsigned features, char *line)
{
	char *ret = line;

#ifdef __x86_64__
	line += sprintf(line, "x86-64");
#else
	line += sprintf(line, "x86");
#endif

	if (features & SSE2)
		line += sprintf(line, ", sse2");
	if (features & SSE3)
		line += sprintf(line, ", sse3");
	if (features & SSSE3)
		line += sprintf(line, ", ssse3");
	if (features & SSE4_1)
		line += sprintf(line, ", sse4.1");
	if (features & SSE4_2)
		line += sprintf(line, ", sse4.2");
	if (features & AVX)
		line += sprintf(line, ", avx");
	if (features & AVX2)
		line += sprintf(line, ", avx2");

178 179
	(void)line;

180 181
	return ret;
}
182
#endif
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

#if defined(__x86_64__) && !defined(__clang__)
#pragma GCC push_options
#pragma GCC target("sse4.1")
#pragma GCC diagnostic ignored "-Wpointer-arith"

#include <smmintrin.h>
static void memcpy_from_wc_sse41(void *dst, const void *src, unsigned long len)
{
	char buf[16];

	/* Flush the internal buffer of potential stale gfx data */
	_mm_mfence();

	if ((uintptr_t)src & 15) {
		__m128i *S = (__m128i *)((uintptr_t)src & ~15);
		unsigned long misalign = (uintptr_t)src & 15;
		unsigned long copy = min(len, 16 - misalign);

		_mm_storeu_si128((__m128i *)buf,
				 _mm_stream_load_si128(S));

		memcpy(dst, buf + misalign, copy);

		dst += copy;
		src += copy;
		len -= copy;
	}

	/* We assume we are doing bulk transfers, so prefer aligned moves */
	if (((uintptr_t)dst & 15) == 0) {
		while (len >= 64) {
			__m128i *S = (__m128i *)src;
			__m128i *D = (__m128i *)dst;
			__m128i tmp[4];

			tmp[0] = _mm_stream_load_si128(S + 0);
			tmp[1] = _mm_stream_load_si128(S + 1);
			tmp[2] = _mm_stream_load_si128(S + 2);
			tmp[3] = _mm_stream_load_si128(S + 3);

			_mm_store_si128(D + 0, tmp[0]);
			_mm_store_si128(D + 1, tmp[1]);
			_mm_store_si128(D + 2, tmp[2]);
			_mm_store_si128(D + 3, tmp[3]);

			src += 64;
			dst += 64;
			len -= 64;
		}
	} else {
		while (len >= 64) {
			__m128i *S = (__m128i *)src;
			__m128i *D = (__m128i *)dst;
			__m128i tmp[4];

			tmp[0] = _mm_stream_load_si128(S + 0);
			tmp[1] = _mm_stream_load_si128(S + 1);
			tmp[2] = _mm_stream_load_si128(S + 2);
			tmp[3] = _mm_stream_load_si128(S + 3);

			_mm_storeu_si128(D + 0, tmp[0]);
			_mm_storeu_si128(D + 1, tmp[1]);
			_mm_storeu_si128(D + 2, tmp[2]);
			_mm_storeu_si128(D + 3, tmp[3]);

			src += 64;
			dst += 64;
			len -= 64;
		}
	}

	while (len >= 16) {
		_mm_storeu_si128((__m128i *)dst,
				 _mm_stream_load_si128((__m128i *)src));

		src += 16;
		dst += 16;
		len -= 16;
	}

	if (len) {
		_mm_storeu_si128((__m128i *)buf,
				 _mm_stream_load_si128((__m128i *)src));
		memcpy(dst, buf, len);
	}
}

#pragma GCC pop_options

static void memcpy_from_wc(void *dst, const void *src, unsigned long len)
{
	memcpy(dst, src, len);
}

static void (*resolve_memcpy_from_wc(void))(void *, const void *, unsigned long)
{
	if (igt_x86_features() & SSE4_1)
		return memcpy_from_wc_sse41;

	return memcpy_from_wc;
}

void igt_memcpy_from_wc(void *dst, const void *src, unsigned long len)
	__attribute__((ifunc("resolve_memcpy_from_wc")));

#else
void igt_memcpy_from_wc(void *dst, const void *src, unsigned long len)
{
	memcpy(dst, src, len);
}
#endif