From: Gowrishankar Muthukrishnan Date: Thu, 8 Sep 2016 16:48:03 +0000 (+0530) Subject: lpm: add AltiVec for ppc64 X-Git-Tag: spdx-start~6021 X-Git-Url: http://git.droids-corp.org/?a=commitdiff_plain;h=d2cc7959342b5183ab88aed44ea011d660a91021;p=dpdk.git lpm: add AltiVec for ppc64 This patch adds ppc64le port for LPM library in DPDK. Signed-off-by: Gowrishankar Muthukrishnan Acked-by: Chao Zhu --- diff --git a/app/test/test_xmmt_ops.h b/app/test/test_xmmt_ops.h index de9c16fee9..42174d2c92 100644 --- a/app/test/test_xmmt_ops.h +++ b/app/test/test_xmmt_ops.h @@ -62,6 +62,22 @@ vect_set_epi32(int i3, int i2, int i1, int i0) /* sets the 4 signed 32-bit integer values and returns the xmm_t variable */ #define vect_set_epi32(i3, i2, i1, i0) _mm_set_epi32(i3, i2, i1, i0) +#elif defined(RTE_ARCH_PPC_64) + +/* vect_* abstraction implementation using ALTIVEC */ + +/* loads the xmm_t value from address p(does not need to be 16-byte aligned)*/ +#define vect_loadu_sil128(p) vec_ld(0, p) + +/* sets the 4 signed 32-bit integer values and returns the xmm_t variable */ +static inline xmm_t __attribute__((always_inline)) +vect_set_epi32(int i3, int i2, int i1, int i0) +{ + xmm_t data = (xmm_t){i0, i1, i2, i3}; + + return data; +} + #endif #endif /* _TEST_XMMT_OPS_H_ */ diff --git a/config/defconfig_ppc_64-power8-linuxapp-gcc b/config/defconfig_ppc_64-power8-linuxapp-gcc index bef8f49a1b..9ddf3c588b 100644 --- a/config/defconfig_ppc_64-power8-linuxapp-gcc +++ b/config/defconfig_ppc_64-power8-linuxapp-gcc @@ -57,7 +57,6 @@ CONFIG_RTE_LIBRTE_ENIC_PMD=n CONFIG_RTE_LIBRTE_FM10K_PMD=n # This following libraries are not available on Power. So they're turned off. -CONFIG_RTE_LIBRTE_LPM=n CONFIG_RTE_LIBRTE_ACL=n CONFIG_RTE_LIBRTE_SCHED=n CONFIG_RTE_LIBRTE_PORT=n diff --git a/lib/librte_eal/common/include/arch/ppc_64/rte_vect.h b/lib/librte_eal/common/include/arch/ppc_64/rte_vect.h new file mode 100644 index 0000000000..05209e5265 --- /dev/null +++ b/lib/librte_eal/common/include/arch/ppc_64/rte_vect.h @@ -0,0 +1,60 @@ +/* + * BSD LICENSE + * + * Copyright (C) IBM Corporation 2016. + * + * 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 IBM 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_VECT_PPC_64_H_ +#define _RTE_VECT_PPC_64_H_ + +#include + +#ifdef __cplusplus +extern "C" { +#endif + +typedef vector signed int xmm_t; + +#define XMM_SIZE (sizeof(xmm_t)) +#define XMM_MASK (XMM_SIZE - 1) + +typedef union rte_xmm { + xmm_t x; + uint8_t u8[XMM_SIZE / sizeof(uint8_t)]; + uint16_t u16[XMM_SIZE / sizeof(uint16_t)]; + uint32_t u32[XMM_SIZE / sizeof(uint32_t)]; + uint64_t u64[XMM_SIZE / sizeof(uint64_t)]; + double pd[XMM_SIZE / sizeof(double)]; +} __attribute__((aligned(16))) rte_xmm_t; + +#ifdef __cplusplus +} +#endif + +#endif /* _RTE_VECT_PPC_64_H_ */ diff --git a/lib/librte_lpm/Makefile b/lib/librte_lpm/Makefile index 656ade2702..3dc549dcf2 100644 --- a/lib/librte_lpm/Makefile +++ b/lib/librte_lpm/Makefile @@ -51,6 +51,8 @@ ifneq ($(filter y,$(CONFIG_RTE_ARCH_ARM) $(CONFIG_RTE_ARCH_ARM64)),) SYMLINK-$(CONFIG_RTE_LIBRTE_LPM)-include += rte_lpm_neon.h else ifeq ($(CONFIG_RTE_ARCH_X86),y) SYMLINK-$(CONFIG_RTE_LIBRTE_LPM)-include += rte_lpm_sse.h +else ifeq ($(CONFIG_RTE_ARCH_PPC_64),y) +SYMLINK-$(CONFIG_RTE_LIBRTE_LPM)-include += rte_lpm_altivec.h endif # this lib needs eal diff --git a/lib/librte_lpm/rte_lpm.h b/lib/librte_lpm/rte_lpm.h index 2df1d67290..dbe5483c20 100644 --- a/lib/librte_lpm/rte_lpm.h +++ b/lib/librte_lpm/rte_lpm.h @@ -480,6 +480,8 @@ rte_lpm_lookupx4(const struct rte_lpm *lpm, xmm_t ip, uint32_t hop[4], #if defined(RTE_ARCH_ARM) || defined(RTE_ARCH_ARM64) #include "rte_lpm_neon.h" +#elif defined(RTE_ARCH_PPC_64) +#include "rte_lpm_altivec.h" #else #include "rte_lpm_sse.h" #endif diff --git a/lib/librte_lpm/rte_lpm_altivec.h b/lib/librte_lpm/rte_lpm_altivec.h new file mode 100644 index 0000000000..e26e08755a --- /dev/null +++ b/lib/librte_lpm/rte_lpm_altivec.h @@ -0,0 +1,154 @@ +/* + * BSD LICENSE + * + * Copyright (C) IBM Corporation 2016. + * + * 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 IBM 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_LPM_ALTIVEC_H_ +#define _RTE_LPM_ALTIVEC_H_ + +#include +#include +#include +#include + +#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) +{ + vector signed int i24; + rte_xmm_t i8; + uint32_t tbl[4]; + uint64_t idx, pt, pt2; + const uint32_t *ptbl; + + const uint32_t mask = UINT8_MAX; + const vector signed int mask8 = (xmm_t){mask, mask, mask, mask}; + + /* + * 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 = vec_sr((xmm_t) ip, + (vector unsigned int){CHAR_BIT, CHAR_BIT, CHAR_BIT, CHAR_BIT}); + + /* extract values from tbl24[] */ + idx = (uint32_t)i24[0]; + idx = idx < (1<<24) ? idx : (1<<24)-1; + ptbl = (const uint32_t *)&lpm->tbl24[idx]; + tbl[0] = *ptbl; + + idx = (uint32_t) i24[1]; + idx = idx < (1<<24) ? idx : (1<<24)-1; + ptbl = (const uint32_t *)&lpm->tbl24[idx]; + tbl[1] = *ptbl; + + idx = (uint32_t) i24[2]; + idx = idx < (1<<24) ? idx : (1<<24)-1; + ptbl = (const uint32_t *)&lpm->tbl24[idx]; + tbl[2] = *ptbl; + + idx = (uint32_t) i24[3]; + idx = idx < (1<<24) ? idx : (1<<24)-1; + ptbl = (const uint32_t *)&lpm->tbl24[idx]; + tbl[3] = *ptbl; + + /* get 4 indexes for tbl8[]. */ + i8.x = vec_and(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_ALTIVEC_H_ */