1459d335d0
includes itself: rte_lpm.h -> rte_lpm_sse.h -> rte_lpm.h includes itself: rte_lpm.h -> rte_lpm_neon.h -> rte_lpm.h Signed-off-by: Congwen Zhang <zhang.congwen@zte.com.cn>
122 lines
3.3 KiB
C
122 lines
3.3 KiB
C
/* SPDX-License-Identifier: BSD-3-Clause
|
|
* Copyright(c) 2010-2014 Intel Corporation
|
|
*/
|
|
|
|
#ifndef _RTE_LPM_SSE_H_
|
|
#define _RTE_LPM_SSE_H_
|
|
|
|
#include <rte_branch_prediction.h>
|
|
#include <rte_byteorder.h>
|
|
#include <rte_common.h>
|
|
#include <rte_vect.h>
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
static inline void
|
|
rte_lpm_lookupx4(const struct rte_lpm *lpm, xmm_t ip, uint32_t hop[4],
|
|
uint32_t defv)
|
|
{
|
|
__m128i i24;
|
|
rte_xmm_t i8;
|
|
uint32_t tbl[4];
|
|
uint64_t idx, pt, pt2;
|
|
const uint32_t *ptbl;
|
|
|
|
const __m128i mask8 =
|
|
_mm_set_epi32(UINT8_MAX, UINT8_MAX, UINT8_MAX, UINT8_MAX);
|
|
|
|
/*
|
|
* RTE_LPM_VALID_EXT_ENTRY_BITMASK for 2 LPM entries
|
|
* as one 64-bit value (0x0300000003000000).
|
|
*/
|
|
const uint64_t mask_xv =
|
|
((uint64_t)RTE_LPM_VALID_EXT_ENTRY_BITMASK |
|
|
(uint64_t)RTE_LPM_VALID_EXT_ENTRY_BITMASK << 32);
|
|
|
|
/*
|
|
* RTE_LPM_LOOKUP_SUCCESS for 2 LPM entries
|
|
* as one 64-bit value (0x0100000001000000).
|
|
*/
|
|
const uint64_t mask_v =
|
|
((uint64_t)RTE_LPM_LOOKUP_SUCCESS |
|
|
(uint64_t)RTE_LPM_LOOKUP_SUCCESS << 32);
|
|
|
|
/* get 4 indexes for tbl24[]. */
|
|
i24 = _mm_srli_epi32(ip, CHAR_BIT);
|
|
|
|
/* extract values from tbl24[] */
|
|
idx = _mm_cvtsi128_si64(i24);
|
|
/* With -O0 option, gcc 4.8 - 5.4 fails to fold sizeof() into a constant */
|
|
i24 = _mm_srli_si128(i24, /* sizeof(uint64_t) */ 8);
|
|
|
|
ptbl = (const uint32_t *)&lpm->tbl24[(uint32_t)idx];
|
|
tbl[0] = *ptbl;
|
|
ptbl = (const uint32_t *)&lpm->tbl24[idx >> 32];
|
|
tbl[1] = *ptbl;
|
|
|
|
idx = _mm_cvtsi128_si64(i24);
|
|
|
|
ptbl = (const uint32_t *)&lpm->tbl24[(uint32_t)idx];
|
|
tbl[2] = *ptbl;
|
|
ptbl = (const uint32_t *)&lpm->tbl24[idx >> 32];
|
|
tbl[3] = *ptbl;
|
|
|
|
/* get 4 indexes for tbl8[]. */
|
|
i8.x = _mm_and_si128(ip, mask8);
|
|
|
|
pt = (uint64_t)tbl[0] |
|
|
(uint64_t)tbl[1] << 32;
|
|
pt2 = (uint64_t)tbl[2] |
|
|
(uint64_t)tbl[3] << 32;
|
|
|
|
/* search successfully finished for all 4 IP addresses. */
|
|
if (likely((pt & mask_xv) == mask_v) &&
|
|
likely((pt2 & mask_xv) == mask_v)) {
|
|
*(uint64_t *)hop = pt & RTE_LPM_MASKX4_RES;
|
|
*(uint64_t *)(hop + 2) = pt2 & RTE_LPM_MASKX4_RES;
|
|
return;
|
|
}
|
|
|
|
if (unlikely((pt & RTE_LPM_VALID_EXT_ENTRY_BITMASK) ==
|
|
RTE_LPM_VALID_EXT_ENTRY_BITMASK)) {
|
|
i8.u32[0] = i8.u32[0] +
|
|
(uint8_t)tbl[0] * RTE_LPM_TBL8_GROUP_NUM_ENTRIES;
|
|
ptbl = (const uint32_t *)&lpm->tbl8[i8.u32[0]];
|
|
tbl[0] = *ptbl;
|
|
}
|
|
if (unlikely((pt >> 32 & RTE_LPM_VALID_EXT_ENTRY_BITMASK) ==
|
|
RTE_LPM_VALID_EXT_ENTRY_BITMASK)) {
|
|
i8.u32[1] = i8.u32[1] +
|
|
(uint8_t)tbl[1] * RTE_LPM_TBL8_GROUP_NUM_ENTRIES;
|
|
ptbl = (const uint32_t *)&lpm->tbl8[i8.u32[1]];
|
|
tbl[1] = *ptbl;
|
|
}
|
|
if (unlikely((pt2 & RTE_LPM_VALID_EXT_ENTRY_BITMASK) ==
|
|
RTE_LPM_VALID_EXT_ENTRY_BITMASK)) {
|
|
i8.u32[2] = i8.u32[2] +
|
|
(uint8_t)tbl[2] * RTE_LPM_TBL8_GROUP_NUM_ENTRIES;
|
|
ptbl = (const uint32_t *)&lpm->tbl8[i8.u32[2]];
|
|
tbl[2] = *ptbl;
|
|
}
|
|
if (unlikely((pt2 >> 32 & RTE_LPM_VALID_EXT_ENTRY_BITMASK) ==
|
|
RTE_LPM_VALID_EXT_ENTRY_BITMASK)) {
|
|
i8.u32[3] = i8.u32[3] +
|
|
(uint8_t)tbl[3] * RTE_LPM_TBL8_GROUP_NUM_ENTRIES;
|
|
ptbl = (const uint32_t *)&lpm->tbl8[i8.u32[3]];
|
|
tbl[3] = *ptbl;
|
|
}
|
|
|
|
hop[0] = (tbl[0] & RTE_LPM_LOOKUP_SUCCESS) ? tbl[0] & 0x00FFFFFF : defv;
|
|
hop[1] = (tbl[1] & RTE_LPM_LOOKUP_SUCCESS) ? tbl[1] & 0x00FFFFFF : defv;
|
|
hop[2] = (tbl[2] & RTE_LPM_LOOKUP_SUCCESS) ? tbl[2] & 0x00FFFFFF : defv;
|
|
hop[3] = (tbl[3] & RTE_LPM_LOOKUP_SUCCESS) ? tbl[3] & 0x00FFFFFF : defv;
|
|
}
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
|
|
#endif /* _RTE_LPM_SSE_H_ */
|