X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;ds=inline;f=lib%2Flibrte_eal%2Fcommon%2Finclude%2Farch%2Fx86%2Frte_memcpy.h;h=74c280c2cf2a2456d8e07c647fdd678c136fa8ff;hb=c0e2821041392c17594786d9e46ba5c83de097b5;hp=fb9eba87c87df7cd5120981876dc50db7abc14d3;hpb=60a3df650d523bd2e4bb4f77f9278f25f7f1a65c;p=dpdk.git diff --git a/lib/librte_eal/common/include/arch/x86/rte_memcpy.h b/lib/librte_eal/common/include/arch/x86/rte_memcpy.h index fb9eba87c8..74c280c2cf 100644 --- a/lib/librte_eal/common/include/arch/x86/rte_memcpy.h +++ b/lib/librte_eal/common/include/arch/x86/rte_memcpy.h @@ -34,262 +34,869 @@ #ifndef _RTE_MEMCPY_X86_64_H_ #define _RTE_MEMCPY_X86_64_H_ +/** + * @file + * + * Functions for SSE/AVX/AVX2/AVX512 implementation of memcpy(). + */ + +#include #include #include -#include +#include +#include #ifdef __cplusplus extern "C" { #endif -#include "generic/rte_memcpy.h" +/** + * Copy bytes from one location to another. The locations must not overlap. + * + * @note This is implemented as a macro, so it's address should not be taken + * and care is needed as parameter expressions may be evaluated multiple times. + * + * @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 __rte_always_inline void * +rte_memcpy(void *dst, const void *src, size_t n); -#ifdef __INTEL_COMPILER -#pragma warning(disable:593) /* Stop unused variable warning (reg_a etc). */ -#endif +#ifdef RTE_MACHINE_CPUFLAG_AVX512F + +#define ALIGNMENT_MASK 0x3F + +/** + * AVX512 implementation below + */ +/** + * Copy 16 bytes from one location to another, + * locations should not overlap. + */ static inline void rte_mov16(uint8_t *dst, const uint8_t *src) { - __m128i reg_a; - asm volatile ( - "movdqu (%[src]), %[reg_a]\n\t" - "movdqu %[reg_a], (%[dst])\n\t" - : [reg_a] "=x" (reg_a) - : [src] "r" (src), - [dst] "r"(dst) - : "memory" - ); + __m128i xmm0; + + xmm0 = _mm_loadu_si128((const __m128i *)src); + _mm_storeu_si128((__m128i *)dst, xmm0); } +/** + * Copy 32 bytes from one location to another, + * locations should not overlap. + */ static inline void rte_mov32(uint8_t *dst, const uint8_t *src) { - __m128i reg_a, reg_b; - asm volatile ( - "movdqu (%[src]), %[reg_a]\n\t" - "movdqu 16(%[src]), %[reg_b]\n\t" - "movdqu %[reg_a], (%[dst])\n\t" - "movdqu %[reg_b], 16(%[dst])\n\t" - : [reg_a] "=x" (reg_a), - [reg_b] "=x" (reg_b) - : [src] "r" (src), - [dst] "r"(dst) - : "memory" - ); + __m256i ymm0; + + ymm0 = _mm256_loadu_si256((const __m256i *)src); + _mm256_storeu_si256((__m256i *)dst, ymm0); +} + +/** + * Copy 64 bytes from one location to another, + * locations should not overlap. + */ +static inline void +rte_mov64(uint8_t *dst, const uint8_t *src) +{ + __m512i zmm0; + + zmm0 = _mm512_loadu_si512((const void *)src); + _mm512_storeu_si512((void *)dst, zmm0); +} + +/** + * Copy 128 bytes from one location to another, + * locations should not overlap. + */ +static inline void +rte_mov128(uint8_t *dst, const uint8_t *src) +{ + rte_mov64(dst + 0 * 64, src + 0 * 64); + rte_mov64(dst + 1 * 64, src + 1 * 64); +} + +/** + * Copy 256 bytes from one location to another, + * locations should not overlap. + */ +static inline void +rte_mov256(uint8_t *dst, const uint8_t *src) +{ + rte_mov64(dst + 0 * 64, src + 0 * 64); + rte_mov64(dst + 1 * 64, src + 1 * 64); + rte_mov64(dst + 2 * 64, src + 2 * 64); + rte_mov64(dst + 3 * 64, src + 3 * 64); +} + +/** + * Copy 128-byte blocks from one location to another, + * locations should not overlap. + */ +static inline void +rte_mov128blocks(uint8_t *dst, const uint8_t *src, size_t n) +{ + __m512i zmm0, zmm1; + + while (n >= 128) { + zmm0 = _mm512_loadu_si512((const void *)(src + 0 * 64)); + n -= 128; + zmm1 = _mm512_loadu_si512((const void *)(src + 1 * 64)); + src = src + 128; + _mm512_storeu_si512((void *)(dst + 0 * 64), zmm0); + _mm512_storeu_si512((void *)(dst + 1 * 64), zmm1); + dst = dst + 128; + } +} + +/** + * Copy 512-byte blocks from one location to another, + * locations should not overlap. + */ +static inline void +rte_mov512blocks(uint8_t *dst, const uint8_t *src, size_t n) +{ + __m512i zmm0, zmm1, zmm2, zmm3, zmm4, zmm5, zmm6, zmm7; + + while (n >= 512) { + zmm0 = _mm512_loadu_si512((const void *)(src + 0 * 64)); + n -= 512; + zmm1 = _mm512_loadu_si512((const void *)(src + 1 * 64)); + zmm2 = _mm512_loadu_si512((const void *)(src + 2 * 64)); + zmm3 = _mm512_loadu_si512((const void *)(src + 3 * 64)); + zmm4 = _mm512_loadu_si512((const void *)(src + 4 * 64)); + zmm5 = _mm512_loadu_si512((const void *)(src + 5 * 64)); + zmm6 = _mm512_loadu_si512((const void *)(src + 6 * 64)); + zmm7 = _mm512_loadu_si512((const void *)(src + 7 * 64)); + src = src + 512; + _mm512_storeu_si512((void *)(dst + 0 * 64), zmm0); + _mm512_storeu_si512((void *)(dst + 1 * 64), zmm1); + _mm512_storeu_si512((void *)(dst + 2 * 64), zmm2); + _mm512_storeu_si512((void *)(dst + 3 * 64), zmm3); + _mm512_storeu_si512((void *)(dst + 4 * 64), zmm4); + _mm512_storeu_si512((void *)(dst + 5 * 64), zmm5); + _mm512_storeu_si512((void *)(dst + 6 * 64), zmm6); + _mm512_storeu_si512((void *)(dst + 7 * 64), zmm7); + dst = dst + 512; + } +} + +static inline void * +rte_memcpy_generic(void *dst, const void *src, size_t n) +{ + uintptr_t dstu = (uintptr_t)dst; + uintptr_t srcu = (uintptr_t)src; + void *ret = dst; + size_t dstofss; + size_t bits; + + /** + * Copy less than 16 bytes + */ + if (n < 16) { + if (n & 0x01) { + *(uint8_t *)dstu = *(const uint8_t *)srcu; + srcu = (uintptr_t)((const uint8_t *)srcu + 1); + dstu = (uintptr_t)((uint8_t *)dstu + 1); + } + if (n & 0x02) { + *(uint16_t *)dstu = *(const uint16_t *)srcu; + srcu = (uintptr_t)((const uint16_t *)srcu + 1); + dstu = (uintptr_t)((uint16_t *)dstu + 1); + } + if (n & 0x04) { + *(uint32_t *)dstu = *(const uint32_t *)srcu; + srcu = (uintptr_t)((const uint32_t *)srcu + 1); + dstu = (uintptr_t)((uint32_t *)dstu + 1); + } + if (n & 0x08) + *(uint64_t *)dstu = *(const uint64_t *)srcu; + return ret; + } + + /** + * Fast way when copy size doesn't exceed 512 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 <= 512) { + if (n >= 256) { + n -= 256; + rte_mov256((uint8_t *)dst, (const uint8_t *)src); + src = (const uint8_t *)src + 256; + dst = (uint8_t *)dst + 256; + } + if (n >= 128) { + n -= 128; + rte_mov128((uint8_t *)dst, (const uint8_t *)src); + src = (const uint8_t *)src + 128; + dst = (uint8_t *)dst + 128; + } +COPY_BLOCK_128_BACK63: + if (n > 64) { + rte_mov64((uint8_t *)dst, (const uint8_t *)src); + rte_mov64((uint8_t *)dst - 64 + n, + (const uint8_t *)src - 64 + n); + return ret; + } + if (n > 0) + rte_mov64((uint8_t *)dst - 64 + n, + (const uint8_t *)src - 64 + n); + return ret; + } + + /** + * Make store aligned when copy size exceeds 512 bytes + */ + dstofss = ((uintptr_t)dst & 0x3F); + if (dstofss > 0) { + dstofss = 64 - dstofss; + n -= dstofss; + rte_mov64((uint8_t *)dst, (const uint8_t *)src); + src = (const uint8_t *)src + dstofss; + dst = (uint8_t *)dst + dstofss; + } + + /** + * Copy 512-byte blocks. + * Use copy block function for better instruction order control, + * which is important when load is unaligned. + */ + rte_mov512blocks((uint8_t *)dst, (const uint8_t *)src, n); + bits = n; + n = n & 511; + bits -= n; + src = (const uint8_t *)src + bits; + dst = (uint8_t *)dst + bits; + + /** + * Copy 128-byte blocks. + * Use copy block function for better instruction order control, + * which is important when load is unaligned. + */ + if (n >= 128) { + rte_mov128blocks((uint8_t *)dst, (const uint8_t *)src, n); + bits = n; + n = n & 127; + bits -= n; + src = (const uint8_t *)src + bits; + dst = (uint8_t *)dst + bits; + } + + /** + * Copy whatever left + */ + goto COPY_BLOCK_128_BACK63; +} + +#elif defined RTE_MACHINE_CPUFLAG_AVX2 + +#define ALIGNMENT_MASK 0x1F + +/** + * AVX2 implementation below + */ + +/** + * Copy 16 bytes from one location to another, + * locations should not overlap. + */ +static inline void +rte_mov16(uint8_t *dst, const uint8_t *src) +{ + __m128i xmm0; + + xmm0 = _mm_loadu_si128((const __m128i *)src); + _mm_storeu_si128((__m128i *)dst, xmm0); } +/** + * Copy 32 bytes from one location to another, + * locations should not overlap. + */ static inline void -rte_mov48(uint8_t *dst, const uint8_t *src) +rte_mov32(uint8_t *dst, const uint8_t *src) { - __m128i reg_a, reg_b, reg_c; - asm volatile ( - "movdqu (%[src]), %[reg_a]\n\t" - "movdqu 16(%[src]), %[reg_b]\n\t" - "movdqu 32(%[src]), %[reg_c]\n\t" - "movdqu %[reg_a], (%[dst])\n\t" - "movdqu %[reg_b], 16(%[dst])\n\t" - "movdqu %[reg_c], 32(%[dst])\n\t" - : [reg_a] "=x" (reg_a), - [reg_b] "=x" (reg_b), - [reg_c] "=x" (reg_c) - : [src] "r" (src), - [dst] "r"(dst) - : "memory" - ); + __m256i ymm0; + + ymm0 = _mm256_loadu_si256((const __m256i *)src); + _mm256_storeu_si256((__m256i *)dst, ymm0); } +/** + * Copy 64 bytes from one location to another, + * locations should not overlap. + */ static inline void rte_mov64(uint8_t *dst, const uint8_t *src) { - __m128i reg_a, reg_b, reg_c, reg_d; - asm volatile ( - "movdqu (%[src]), %[reg_a]\n\t" - "movdqu 16(%[src]), %[reg_b]\n\t" - "movdqu 32(%[src]), %[reg_c]\n\t" - "movdqu 48(%[src]), %[reg_d]\n\t" - "movdqu %[reg_a], (%[dst])\n\t" - "movdqu %[reg_b], 16(%[dst])\n\t" - "movdqu %[reg_c], 32(%[dst])\n\t" - "movdqu %[reg_d], 48(%[dst])\n\t" - : [reg_a] "=x" (reg_a), - [reg_b] "=x" (reg_b), - [reg_c] "=x" (reg_c), - [reg_d] "=x" (reg_d) - : [src] "r" (src), - [dst] "r"(dst) - : "memory" - ); + rte_mov32((uint8_t *)dst + 0 * 32, (const uint8_t *)src + 0 * 32); + rte_mov32((uint8_t *)dst + 1 * 32, (const uint8_t *)src + 1 * 32); } +/** + * Copy 128 bytes from one location to another, + * locations should not overlap. + */ static inline void rte_mov128(uint8_t *dst, const uint8_t *src) { - __m128i reg_a, reg_b, reg_c, reg_d, reg_e, reg_f, reg_g, reg_h; - asm volatile ( - "movdqu (%[src]), %[reg_a]\n\t" - "movdqu 16(%[src]), %[reg_b]\n\t" - "movdqu 32(%[src]), %[reg_c]\n\t" - "movdqu 48(%[src]), %[reg_d]\n\t" - "movdqu 64(%[src]), %[reg_e]\n\t" - "movdqu 80(%[src]), %[reg_f]\n\t" - "movdqu 96(%[src]), %[reg_g]\n\t" - "movdqu 112(%[src]), %[reg_h]\n\t" - "movdqu %[reg_a], (%[dst])\n\t" - "movdqu %[reg_b], 16(%[dst])\n\t" - "movdqu %[reg_c], 32(%[dst])\n\t" - "movdqu %[reg_d], 48(%[dst])\n\t" - "movdqu %[reg_e], 64(%[dst])\n\t" - "movdqu %[reg_f], 80(%[dst])\n\t" - "movdqu %[reg_g], 96(%[dst])\n\t" - "movdqu %[reg_h], 112(%[dst])\n\t" - : [reg_a] "=x" (reg_a), - [reg_b] "=x" (reg_b), - [reg_c] "=x" (reg_c), - [reg_d] "=x" (reg_d), - [reg_e] "=x" (reg_e), - [reg_f] "=x" (reg_f), - [reg_g] "=x" (reg_g), - [reg_h] "=x" (reg_h) - : [src] "r" (src), - [dst] "r"(dst) - : "memory" - ); + rte_mov32((uint8_t *)dst + 0 * 32, (const uint8_t *)src + 0 * 32); + rte_mov32((uint8_t *)dst + 1 * 32, (const uint8_t *)src + 1 * 32); + rte_mov32((uint8_t *)dst + 2 * 32, (const uint8_t *)src + 2 * 32); + rte_mov32((uint8_t *)dst + 3 * 32, (const uint8_t *)src + 3 * 32); } -#ifdef __INTEL_COMPILER -#pragma warning(enable:593) -#endif +/** + * Copy 128-byte blocks from one location to another, + * locations should not overlap. + */ +static inline void +rte_mov128blocks(uint8_t *dst, const uint8_t *src, size_t n) +{ + __m256i ymm0, ymm1, ymm2, ymm3; + + while (n >= 128) { + ymm0 = _mm256_loadu_si256((const __m256i *)((const uint8_t *)src + 0 * 32)); + n -= 128; + ymm1 = _mm256_loadu_si256((const __m256i *)((const uint8_t *)src + 1 * 32)); + ymm2 = _mm256_loadu_si256((const __m256i *)((const uint8_t *)src + 2 * 32)); + ymm3 = _mm256_loadu_si256((const __m256i *)((const uint8_t *)src + 3 * 32)); + src = (const uint8_t *)src + 128; + _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 0 * 32), ymm0); + _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 1 * 32), ymm1); + _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 2 * 32), ymm2); + _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 3 * 32), ymm3); + dst = (uint8_t *)dst + 128; + } +} + +static inline void * +rte_memcpy_generic(void *dst, const void *src, size_t n) +{ + uintptr_t dstu = (uintptr_t)dst; + uintptr_t srcu = (uintptr_t)src; + void *ret = dst; + size_t dstofss; + size_t bits; + + /** + * Copy less than 16 bytes + */ + if (n < 16) { + if (n & 0x01) { + *(uint8_t *)dstu = *(const uint8_t *)srcu; + srcu = (uintptr_t)((const uint8_t *)srcu + 1); + dstu = (uintptr_t)((uint8_t *)dstu + 1); + } + if (n & 0x02) { + *(uint16_t *)dstu = *(const uint16_t *)srcu; + srcu = (uintptr_t)((const uint16_t *)srcu + 1); + dstu = (uintptr_t)((uint16_t *)dstu + 1); + } + if (n & 0x04) { + *(uint32_t *)dstu = *(const uint32_t *)srcu; + srcu = (uintptr_t)((const uint32_t *)srcu + 1); + dstu = (uintptr_t)((uint32_t *)dstu + 1); + } + if (n & 0x08) { + *(uint64_t *)dstu = *(const uint64_t *)srcu; + } + return ret; + } + + /** + * Fast way when copy size doesn't exceed 256 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 <= 48) { + rte_mov16((uint8_t *)dst, (const uint8_t *)src); + rte_mov16((uint8_t *)dst + 16, (const uint8_t *)src + 16); + 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 <= 256) { + if (n >= 128) { + n -= 128; + rte_mov128((uint8_t *)dst, (const uint8_t *)src); + src = (const uint8_t *)src + 128; + dst = (uint8_t *)dst + 128; + } +COPY_BLOCK_128_BACK31: + if (n >= 64) { + n -= 64; + rte_mov64((uint8_t *)dst, (const uint8_t *)src); + src = (const uint8_t *)src + 64; + dst = (uint8_t *)dst + 64; + } + if (n > 32) { + 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 > 0) { + rte_mov32((uint8_t *)dst - 32 + n, + (const uint8_t *)src - 32 + n); + } + return ret; + } + + /** + * Make store aligned when copy size exceeds 256 bytes + */ + dstofss = (uintptr_t)dst & 0x1F; + if (dstofss > 0) { + dstofss = 32 - dstofss; + n -= dstofss; + rte_mov32((uint8_t *)dst, (const uint8_t *)src); + src = (const uint8_t *)src + dstofss; + dst = (uint8_t *)dst + dstofss; + } + /** + * Copy 128-byte blocks + */ + rte_mov128blocks((uint8_t *)dst, (const uint8_t *)src, n); + bits = n; + n = n & 127; + bits -= n; + src = (const uint8_t *)src + bits; + dst = (uint8_t *)dst + bits; + + /** + * Copy whatever left + */ + goto COPY_BLOCK_128_BACK31; +} + +#else /* RTE_MACHINE_CPUFLAG */ + +#define ALIGNMENT_MASK 0x0F + +/** + * SSE & AVX implementation below + */ + +/** + * Copy 16 bytes from one location to another, + * locations should not overlap. + */ +static inline void +rte_mov16(uint8_t *dst, const uint8_t *src) +{ + __m128i xmm0; + + xmm0 = _mm_loadu_si128((const __m128i *)(const __m128i *)src); + _mm_storeu_si128((__m128i *)dst, xmm0); +} + +/** + * Copy 32 bytes from one location to another, + * locations should not overlap. + */ +static inline void +rte_mov32(uint8_t *dst, const uint8_t *src) +{ + rte_mov16((uint8_t *)dst + 0 * 16, (const uint8_t *)src + 0 * 16); + rte_mov16((uint8_t *)dst + 1 * 16, (const uint8_t *)src + 1 * 16); +} + +/** + * Copy 64 bytes from one location to another, + * locations should not overlap. + */ +static inline void +rte_mov64(uint8_t *dst, const uint8_t *src) +{ + rte_mov16((uint8_t *)dst + 0 * 16, (const uint8_t *)src + 0 * 16); + rte_mov16((uint8_t *)dst + 1 * 16, (const uint8_t *)src + 1 * 16); + rte_mov16((uint8_t *)dst + 2 * 16, (const uint8_t *)src + 2 * 16); + rte_mov16((uint8_t *)dst + 3 * 16, (const uint8_t *)src + 3 * 16); +} + +/** + * Copy 128 bytes from one location to another, + * locations should not overlap. + */ +static inline void +rte_mov128(uint8_t *dst, const uint8_t *src) +{ + rte_mov16((uint8_t *)dst + 0 * 16, (const uint8_t *)src + 0 * 16); + rte_mov16((uint8_t *)dst + 1 * 16, (const uint8_t *)src + 1 * 16); + rte_mov16((uint8_t *)dst + 2 * 16, (const uint8_t *)src + 2 * 16); + rte_mov16((uint8_t *)dst + 3 * 16, (const uint8_t *)src + 3 * 16); + rte_mov16((uint8_t *)dst + 4 * 16, (const uint8_t *)src + 4 * 16); + rte_mov16((uint8_t *)dst + 5 * 16, (const uint8_t *)src + 5 * 16); + rte_mov16((uint8_t *)dst + 6 * 16, (const uint8_t *)src + 6 * 16); + rte_mov16((uint8_t *)dst + 7 * 16, (const uint8_t *)src + 7 * 16); +} + +/** + * Copy 256 bytes from one location to another, + * locations should not overlap. + */ static inline void rte_mov256(uint8_t *dst, const uint8_t *src) { - rte_mov128(dst, src); - rte_mov128(dst + 128, src + 128); + rte_mov16((uint8_t *)dst + 0 * 16, (const uint8_t *)src + 0 * 16); + rte_mov16((uint8_t *)dst + 1 * 16, (const uint8_t *)src + 1 * 16); + rte_mov16((uint8_t *)dst + 2 * 16, (const uint8_t *)src + 2 * 16); + rte_mov16((uint8_t *)dst + 3 * 16, (const uint8_t *)src + 3 * 16); + rte_mov16((uint8_t *)dst + 4 * 16, (const uint8_t *)src + 4 * 16); + rte_mov16((uint8_t *)dst + 5 * 16, (const uint8_t *)src + 5 * 16); + rte_mov16((uint8_t *)dst + 6 * 16, (const uint8_t *)src + 6 * 16); + rte_mov16((uint8_t *)dst + 7 * 16, (const uint8_t *)src + 7 * 16); + rte_mov16((uint8_t *)dst + 8 * 16, (const uint8_t *)src + 8 * 16); + rte_mov16((uint8_t *)dst + 9 * 16, (const uint8_t *)src + 9 * 16); + rte_mov16((uint8_t *)dst + 10 * 16, (const uint8_t *)src + 10 * 16); + rte_mov16((uint8_t *)dst + 11 * 16, (const uint8_t *)src + 11 * 16); + rte_mov16((uint8_t *)dst + 12 * 16, (const uint8_t *)src + 12 * 16); + rte_mov16((uint8_t *)dst + 13 * 16, (const uint8_t *)src + 13 * 16); + rte_mov16((uint8_t *)dst + 14 * 16, (const uint8_t *)src + 14 * 16); + rte_mov16((uint8_t *)dst + 15 * 16, (const uint8_t *)src + 15 * 16); } -#define rte_memcpy(dst, src, n) \ - ({ (__builtin_constant_p(n)) ? \ - memcpy((dst), (src), (n)) : \ - rte_memcpy_func((dst), (src), (n)); }) +/** + * Macro for copying unaligned block from one location to another with constant load offset, + * 47 bytes leftover maximum, + * locations should not overlap. + * Requirements: + * - Store is aligned + * - Load offset is , which must be immediate value within [1, 15] + * - For , make sure bit backwards & <16 - offset> bit forwards are available for loading + * - , , must be variables + * - __m128i ~ must be pre-defined + */ +#define MOVEUNALIGNED_LEFT47_IMM(dst, src, len, offset) \ +__extension__ ({ \ + int tmp; \ + while (len >= 128 + 16 - offset) { \ + xmm0 = _mm_loadu_si128((const __m128i *)((const uint8_t *)src - offset + 0 * 16)); \ + len -= 128; \ + xmm1 = _mm_loadu_si128((const __m128i *)((const uint8_t *)src - offset + 1 * 16)); \ + xmm2 = _mm_loadu_si128((const __m128i *)((const uint8_t *)src - offset + 2 * 16)); \ + xmm3 = _mm_loadu_si128((const __m128i *)((const uint8_t *)src - offset + 3 * 16)); \ + xmm4 = _mm_loadu_si128((const __m128i *)((const uint8_t *)src - offset + 4 * 16)); \ + xmm5 = _mm_loadu_si128((const __m128i *)((const uint8_t *)src - offset + 5 * 16)); \ + xmm6 = _mm_loadu_si128((const __m128i *)((const uint8_t *)src - offset + 6 * 16)); \ + xmm7 = _mm_loadu_si128((const __m128i *)((const uint8_t *)src - offset + 7 * 16)); \ + xmm8 = _mm_loadu_si128((const __m128i *)((const uint8_t *)src - offset + 8 * 16)); \ + src = (const uint8_t *)src + 128; \ + _mm_storeu_si128((__m128i *)((uint8_t *)dst + 0 * 16), _mm_alignr_epi8(xmm1, xmm0, offset)); \ + _mm_storeu_si128((__m128i *)((uint8_t *)dst + 1 * 16), _mm_alignr_epi8(xmm2, xmm1, offset)); \ + _mm_storeu_si128((__m128i *)((uint8_t *)dst + 2 * 16), _mm_alignr_epi8(xmm3, xmm2, offset)); \ + _mm_storeu_si128((__m128i *)((uint8_t *)dst + 3 * 16), _mm_alignr_epi8(xmm4, xmm3, offset)); \ + _mm_storeu_si128((__m128i *)((uint8_t *)dst + 4 * 16), _mm_alignr_epi8(xmm5, xmm4, offset)); \ + _mm_storeu_si128((__m128i *)((uint8_t *)dst + 5 * 16), _mm_alignr_epi8(xmm6, xmm5, offset)); \ + _mm_storeu_si128((__m128i *)((uint8_t *)dst + 6 * 16), _mm_alignr_epi8(xmm7, xmm6, offset)); \ + _mm_storeu_si128((__m128i *)((uint8_t *)dst + 7 * 16), _mm_alignr_epi8(xmm8, xmm7, offset)); \ + dst = (uint8_t *)dst + 128; \ + } \ + tmp = len; \ + len = ((len - 16 + offset) & 127) + 16 - offset; \ + tmp -= len; \ + src = (const uint8_t *)src + tmp; \ + dst = (uint8_t *)dst + tmp; \ + if (len >= 32 + 16 - offset) { \ + while (len >= 32 + 16 - offset) { \ + xmm0 = _mm_loadu_si128((const __m128i *)((const uint8_t *)src - offset + 0 * 16)); \ + len -= 32; \ + xmm1 = _mm_loadu_si128((const __m128i *)((const uint8_t *)src - offset + 1 * 16)); \ + xmm2 = _mm_loadu_si128((const __m128i *)((const uint8_t *)src - offset + 2 * 16)); \ + src = (const uint8_t *)src + 32; \ + _mm_storeu_si128((__m128i *)((uint8_t *)dst + 0 * 16), _mm_alignr_epi8(xmm1, xmm0, offset)); \ + _mm_storeu_si128((__m128i *)((uint8_t *)dst + 1 * 16), _mm_alignr_epi8(xmm2, xmm1, offset)); \ + dst = (uint8_t *)dst + 32; \ + } \ + tmp = len; \ + len = ((len - 16 + offset) & 31) + 16 - offset; \ + tmp -= len; \ + src = (const uint8_t *)src + tmp; \ + dst = (uint8_t *)dst + tmp; \ + } \ +}) + +/** + * Macro for copying unaligned block from one location to another, + * 47 bytes leftover maximum, + * locations should not overlap. + * Use switch here because the aligning instruction requires immediate value for shift count. + * Requirements: + * - Store is aligned + * - Load offset is , which must be within [1, 15] + * - For , make sure bit backwards & <16 - offset> bit forwards are available for loading + * - , , must be variables + * - __m128i ~ used in MOVEUNALIGNED_LEFT47_IMM must be pre-defined + */ +#define MOVEUNALIGNED_LEFT47(dst, src, len, offset) \ +__extension__ ({ \ + switch (offset) { \ + case 0x01: MOVEUNALIGNED_LEFT47_IMM(dst, src, n, 0x01); break; \ + case 0x02: MOVEUNALIGNED_LEFT47_IMM(dst, src, n, 0x02); break; \ + case 0x03: MOVEUNALIGNED_LEFT47_IMM(dst, src, n, 0x03); break; \ + case 0x04: MOVEUNALIGNED_LEFT47_IMM(dst, src, n, 0x04); break; \ + case 0x05: MOVEUNALIGNED_LEFT47_IMM(dst, src, n, 0x05); break; \ + case 0x06: MOVEUNALIGNED_LEFT47_IMM(dst, src, n, 0x06); break; \ + case 0x07: MOVEUNALIGNED_LEFT47_IMM(dst, src, n, 0x07); break; \ + case 0x08: MOVEUNALIGNED_LEFT47_IMM(dst, src, n, 0x08); break; \ + case 0x09: MOVEUNALIGNED_LEFT47_IMM(dst, src, n, 0x09); break; \ + case 0x0A: MOVEUNALIGNED_LEFT47_IMM(dst, src, n, 0x0A); break; \ + case 0x0B: MOVEUNALIGNED_LEFT47_IMM(dst, src, n, 0x0B); break; \ + case 0x0C: MOVEUNALIGNED_LEFT47_IMM(dst, src, n, 0x0C); break; \ + case 0x0D: MOVEUNALIGNED_LEFT47_IMM(dst, src, n, 0x0D); break; \ + case 0x0E: MOVEUNALIGNED_LEFT47_IMM(dst, src, n, 0x0E); break; \ + case 0x0F: MOVEUNALIGNED_LEFT47_IMM(dst, src, n, 0x0F); break; \ + default:; \ + } \ +}) static inline void * -rte_memcpy_func(void *dst, const void *src, size_t n) +rte_memcpy_generic(void *dst, const void *src, size_t n) { + __m128i xmm0, xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7, xmm8; + uintptr_t dstu = (uintptr_t)dst; + uintptr_t srcu = (uintptr_t)src; void *ret = dst; + size_t dstofss; + size_t srcofs; - /* We can't copy < 16 bytes using XMM registers so do it manually. */ + /** + * Copy less than 16 bytes + */ if (n < 16) { if (n & 0x01) { - *(uint8_t *)dst = *(const uint8_t *)src; - dst = (uint8_t *)dst + 1; - src = (const uint8_t *)src + 1; + *(uint8_t *)dstu = *(const uint8_t *)srcu; + srcu = (uintptr_t)((const uint8_t *)srcu + 1); + dstu = (uintptr_t)((uint8_t *)dstu + 1); } if (n & 0x02) { - *(uint16_t *)dst = *(const uint16_t *)src; - dst = (uint16_t *)dst + 1; - src = (const uint16_t *)src + 1; + *(uint16_t *)dstu = *(const uint16_t *)srcu; + srcu = (uintptr_t)((const uint16_t *)srcu + 1); + dstu = (uintptr_t)((uint16_t *)dstu + 1); } if (n & 0x04) { - *(uint32_t *)dst = *(const uint32_t *)src; - dst = (uint32_t *)dst + 1; - src = (const uint32_t *)src + 1; + *(uint32_t *)dstu = *(const uint32_t *)srcu; + srcu = (uintptr_t)((const uint32_t *)srcu + 1); + dstu = (uintptr_t)((uint32_t *)dstu + 1); } if (n & 0x08) { - *(uint64_t *)dst = *(const uint64_t *)src; + *(uint64_t *)dstu = *(const uint64_t *)srcu; } return ret; } - /* Special fast cases for <= 128 bytes */ + /** + * Fast way when copy size doesn't exceed 512 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 <= 48) { + rte_mov32((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); + rte_mov16((uint8_t *)dst + 32, (const uint8_t *)src + 32); + rte_mov16((uint8_t *)dst - 16 + n, (const uint8_t *)src - 16 + 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); + goto COPY_BLOCK_128_BACK15; + } + if (n <= 512) { + if (n >= 256) { + n -= 256; + rte_mov128((uint8_t *)dst, (const uint8_t *)src); + rte_mov128((uint8_t *)dst + 128, (const uint8_t *)src + 128); + src = (const uint8_t *)src + 256; + dst = (uint8_t *)dst + 256; + } +COPY_BLOCK_255_BACK15: + if (n >= 128) { + n -= 128; + rte_mov128((uint8_t *)dst, (const uint8_t *)src); + src = (const uint8_t *)src + 128; + dst = (uint8_t *)dst + 128; + } +COPY_BLOCK_128_BACK15: + if (n >= 64) { + n -= 64; + rte_mov64((uint8_t *)dst, (const uint8_t *)src); + src = (const uint8_t *)src + 64; + dst = (uint8_t *)dst + 64; + } +COPY_BLOCK_64_BACK15: + if (n >= 32) { + n -= 32; + rte_mov32((uint8_t *)dst, (const uint8_t *)src); + src = (const uint8_t *)src + 32; + dst = (uint8_t *)dst + 32; + } + if (n > 16) { + 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 > 0) { + rte_mov16((uint8_t *)dst - 16 + n, (const uint8_t *)src - 16 + 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. + /** + * Make store aligned when copy size exceeds 512 bytes, + * and make sure the first 15 bytes are copied, because + * unaligned copy functions require up to 15 bytes + * backwards access. */ - 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; + dstofss = (uintptr_t)dst & 0x0F; + if (dstofss > 0) { + dstofss = 16 - dstofss + 16; + n -= dstofss; + rte_mov32((uint8_t *)dst, (const uint8_t *)src); + src = (const uint8_t *)src + dstofss; + dst = (uint8_t *)dst + dstofss; } + srcofs = ((uintptr_t)src & 0x0F); - /* - * 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. + /** + * For aligned copy */ - 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: - ; + if (srcofs == 0) { + /** + * Copy 256-byte blocks + */ + 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; + } + + /** + * Copy whatever left + */ + goto COPY_BLOCK_255_BACK15; } - /* - * We split the remaining bytes (which will be less than 64) into - * 16byte (2^4) chunks, using the same switch structure as above. + /** + * For copy with unaligned load */ - 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: + MOVEUNALIGNED_LEFT47(dst, src, n, srcofs); + + /** + * Copy whatever left + */ + goto COPY_BLOCK_64_BACK15; +} + +#endif /* RTE_MACHINE_CPUFLAG */ + +static inline void * +rte_memcpy_aligned(void *dst, const void *src, size_t n) +{ + void *ret = dst; + + /* Copy size <= 16 bytes */ + if (n < 16) { + if (n & 0x01) { + *(uint8_t *)dst = *(const uint8_t *)src; + src = (const uint8_t *)src + 1; + dst = (uint8_t *)dst + 1; + } + if (n & 0x02) { + *(uint16_t *)dst = *(const uint16_t *)src; + src = (const uint16_t *)src + 1; + dst = (uint16_t *)dst + 1; + } + if (n & 0x04) { + *(uint32_t *)dst = *(const uint32_t *)src; + src = (const uint32_t *)src + 1; + dst = (uint32_t *)dst + 1; + } + if (n & 0x08) + *(uint64_t *)dst = *(const uint64_t *)src; + + return ret; + } + + /* Copy 16 <= size <= 32 bytes */ + if (n <= 32) { rte_mov16((uint8_t *)dst, (const uint8_t *)src); - n -= 16; - dst = (uint8_t *)dst + 16; - src = (const uint8_t *)src + 16; /* fallthrough */ - default: - ; + rte_mov16((uint8_t *)dst - 16 + n, + (const uint8_t *)src - 16 + n); + + return ret; } - /* 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); + /* Copy 32 < size <= 64 bytes */ + 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; } + + /* Copy 64 bytes blocks */ + for (; n >= 64; n -= 64) { + rte_mov64((uint8_t *)dst, (const uint8_t *)src); + dst = (uint8_t *)dst + 64; + src = (const uint8_t *)src + 64; + } + + /* Copy whatever left */ + rte_mov64((uint8_t *)dst - 64 + n, + (const uint8_t *)src - 64 + n); + return ret; } +static inline void * +rte_memcpy(void *dst, const void *src, size_t n) +{ + if (!(((uintptr_t)dst | (uintptr_t)src) & ALIGNMENT_MASK)) + return rte_memcpy_aligned(dst, src, n); + else + return rte_memcpy_generic(dst, src, n); +} + #ifdef __cplusplus } #endif