X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=examples%2Fl3fwd%2Fl3fwd_em.c;h=53d081bd768192984d9ac761c31d4f6acd6a08ec;hb=cf0fab1d2ca50b48bdca8914f7bdcfc32ca770e8;hp=0adf8f4bfb28b76edeb4db049af72291d1c3d44f;hpb=64d3955de1de4d7879a0930a6d2f501369d3445a;p=dpdk.git diff --git a/examples/l3fwd/l3fwd_em.c b/examples/l3fwd/l3fwd_em.c index 0adf8f4bfb..53d081bd76 100644 --- a/examples/l3fwd/l3fwd_em.c +++ b/examples/l3fwd/l3fwd_em.c @@ -42,11 +42,11 @@ #include #include #include +#include #include #include #include -#include #include #include #include @@ -57,13 +57,17 @@ #include "l3fwd.h" -#ifdef RTE_MACHINE_CPUFLAG_SSE4_2 +#if defined(RTE_ARCH_X86) || defined(RTE_MACHINE_CPUFLAG_CRC32) +#define EM_HASH_CRC 1 +#endif + +#ifdef EM_HASH_CRC #include #define DEFAULT_HASH_FUNC rte_hash_crc #else #include #define DEFAULT_HASH_FUNC rte_jhash -#endif /* RTE_MACHINE_CPUFLAG_SSE4_2 */ +#endif #define IPV6_ADDR_LEN 16 @@ -168,17 +172,17 @@ ipv4_hash_crc(const void *data, __rte_unused uint32_t data_len, t = k->proto; p = (const uint32_t *)&k->port_src; -#ifdef RTE_MACHINE_CPUFLAG_SSE4_2 +#ifdef EM_HASH_CRC init_val = rte_hash_crc_4byte(t, init_val); init_val = rte_hash_crc_4byte(k->ip_src, init_val); init_val = rte_hash_crc_4byte(k->ip_dst, init_val); init_val = rte_hash_crc_4byte(*p, init_val); -#else /* RTE_MACHINE_CPUFLAG_SSE4_2 */ +#else init_val = rte_jhash_1word(t, init_val); init_val = rte_jhash_1word(k->ip_src, init_val); init_val = rte_jhash_1word(k->ip_dst, init_val); init_val = rte_jhash_1word(*p, init_val); -#endif /* RTE_MACHINE_CPUFLAG_SSE4_2 */ +#endif return init_val; } @@ -190,16 +194,16 @@ ipv6_hash_crc(const void *data, __rte_unused uint32_t data_len, const union ipv6_5tuple_host *k; uint32_t t; const uint32_t *p; -#ifdef RTE_MACHINE_CPUFLAG_SSE4_2 +#ifdef EM_HASH_CRC const uint32_t *ip_src0, *ip_src1, *ip_src2, *ip_src3; const uint32_t *ip_dst0, *ip_dst1, *ip_dst2, *ip_dst3; -#endif /* RTE_MACHINE_CPUFLAG_SSE4_2 */ +#endif k = data; t = k->proto; p = (const uint32_t *)&k->port_src; -#ifdef RTE_MACHINE_CPUFLAG_SSE4_2 +#ifdef EM_HASH_CRC ip_src0 = (const uint32_t *) k->ip_src; ip_src1 = (const uint32_t *)(k->ip_src+4); ip_src2 = (const uint32_t *)(k->ip_src+8); @@ -218,14 +222,14 @@ ipv6_hash_crc(const void *data, __rte_unused uint32_t data_len, init_val = rte_hash_crc_4byte(*ip_dst2, init_val); init_val = rte_hash_crc_4byte(*ip_dst3, init_val); init_val = rte_hash_crc_4byte(*p, init_val); -#else /* RTE_MACHINE_CPUFLAG_SSE4_2 */ +#else init_val = rte_jhash_1word(t, init_val); init_val = rte_jhash(k->ip_src, sizeof(uint8_t) * IPV6_ADDR_LEN, init_val); init_val = rte_jhash(k->ip_dst, sizeof(uint8_t) * IPV6_ADDR_LEN, init_val); init_val = rte_jhash_1word(*p, init_val); -#endif /* RTE_MACHINE_CPUFLAG_SSE4_2 */ +#endif return init_val; } @@ -242,7 +246,7 @@ static rte_xmm_t mask0; static rte_xmm_t mask1; static rte_xmm_t mask2; -#if defined(__SSE2__) +#if defined(RTE_MACHINE_CPUFLAG_SSE2) static inline xmm_t em_mask_key(void *key, xmm_t mask) { @@ -250,7 +254,7 @@ em_mask_key(void *key, xmm_t mask) return _mm_and_si128(data, mask); } -#elif defined(__ARM_NEON) +#elif defined(RTE_MACHINE_CPUFLAG_NEON) static inline xmm_t em_mask_key(void *key, xmm_t mask) { @@ -258,6 +262,16 @@ em_mask_key(void *key, xmm_t mask) return vandq_s32(data, mask); } +#elif defined(RTE_MACHINE_CPUFLAG_ALTIVEC) +static inline xmm_t +em_mask_key(void *key, xmm_t mask) +{ + xmm_t data = vec_ld(0, (xmm_t *)(key)); + + return vec_and(data, mask); +} +#else +#error No vector engine (SSE, NEON, ALTIVEC) available, check your toolchain #endif static inline uint8_t @@ -314,16 +328,11 @@ em_get_ipv6_dst_port(void *ipv6_hdr, uint8_t portid, void *lookup_struct) return (uint8_t)((ret < 0) ? portid : ipv6_l3fwd_out_if[ret]); } - -/* - * Include header file if SSE4_1 is enabled for - * buffer optimization i.e. ENABLE_MULTI_BUFFER_OPTIMIZE=1. - */ -#if defined(__SSE4_1__) -#ifndef HASH_MULTI_LOOKUP -#include "l3fwd_em_sse.h" +#if defined RTE_ARCH_X86 || defined RTE_MACHINE_CPUFLAG_NEON +#if defined(NO_HASH_MULTI_LOOKUP) +#include "l3fwd_em_sequential.h" #else -#include "l3fwd_em_hlm_sse.h" +#include "l3fwd_em_hlm.h" #endif #else #include "l3fwd_em.h" @@ -524,6 +533,114 @@ populate_ipv6_many_flow_into_table(const struct rte_hash *h, printf("Hash: Adding 0x%x keys\n", nr_flow); } +/* Requirements: + * 1. IP packets without extension; + * 2. L4 payload should be either TCP or UDP. + */ +int +em_check_ptype(int portid) +{ + int i, ret; + int ptype_l3_ipv4_ext = 0; + int ptype_l3_ipv6_ext = 0; + int ptype_l4_tcp = 0; + int ptype_l4_udp = 0; + uint32_t ptype_mask = RTE_PTYPE_L3_MASK | RTE_PTYPE_L4_MASK; + + ret = rte_eth_dev_get_supported_ptypes(portid, ptype_mask, NULL, 0); + if (ret <= 0) + return 0; + + uint32_t ptypes[ret]; + + ret = rte_eth_dev_get_supported_ptypes(portid, ptype_mask, ptypes, ret); + for (i = 0; i < ret; ++i) { + switch (ptypes[i]) { + case RTE_PTYPE_L3_IPV4_EXT: + ptype_l3_ipv4_ext = 1; + break; + case RTE_PTYPE_L3_IPV6_EXT: + ptype_l3_ipv6_ext = 1; + break; + case RTE_PTYPE_L4_TCP: + ptype_l4_tcp = 1; + break; + case RTE_PTYPE_L4_UDP: + ptype_l4_udp = 1; + break; + } + } + + if (ptype_l3_ipv4_ext == 0) + printf("port %d cannot parse RTE_PTYPE_L3_IPV4_EXT\n", portid); + if (ptype_l3_ipv6_ext == 0) + printf("port %d cannot parse RTE_PTYPE_L3_IPV6_EXT\n", portid); + if (!ptype_l3_ipv4_ext || !ptype_l3_ipv6_ext) + return 0; + + if (ptype_l4_tcp == 0) + printf("port %d cannot parse RTE_PTYPE_L4_TCP\n", portid); + if (ptype_l4_udp == 0) + printf("port %d cannot parse RTE_PTYPE_L4_UDP\n", portid); + if (ptype_l4_tcp && ptype_l4_udp) + return 1; + + return 0; +} + +static inline void +em_parse_ptype(struct rte_mbuf *m) +{ + struct ether_hdr *eth_hdr; + uint32_t packet_type = RTE_PTYPE_UNKNOWN; + uint16_t ether_type; + void *l3; + int hdr_len; + struct ipv4_hdr *ipv4_hdr; + struct ipv6_hdr *ipv6_hdr; + + eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *); + ether_type = eth_hdr->ether_type; + l3 = (uint8_t *)eth_hdr + sizeof(struct ether_hdr); + if (ether_type == rte_cpu_to_be_16(ETHER_TYPE_IPv4)) { + ipv4_hdr = (struct ipv4_hdr *)l3; + hdr_len = (ipv4_hdr->version_ihl & IPV4_HDR_IHL_MASK) * + IPV4_IHL_MULTIPLIER; + if (hdr_len == sizeof(struct ipv4_hdr)) { + packet_type |= RTE_PTYPE_L3_IPV4; + if (ipv4_hdr->next_proto_id == IPPROTO_TCP) + packet_type |= RTE_PTYPE_L4_TCP; + else if (ipv4_hdr->next_proto_id == IPPROTO_UDP) + packet_type |= RTE_PTYPE_L4_UDP; + } else + packet_type |= RTE_PTYPE_L3_IPV4_EXT; + } else if (ether_type == rte_cpu_to_be_16(ETHER_TYPE_IPv6)) { + ipv6_hdr = (struct ipv6_hdr *)l3; + if (ipv6_hdr->proto == IPPROTO_TCP) + packet_type |= RTE_PTYPE_L3_IPV6 | RTE_PTYPE_L4_TCP; + else if (ipv6_hdr->proto == IPPROTO_UDP) + packet_type |= RTE_PTYPE_L3_IPV6 | RTE_PTYPE_L4_UDP; + else + packet_type |= RTE_PTYPE_L3_IPV6_EXT_UNKNOWN; + } + + m->packet_type = packet_type; +} + +uint16_t +em_cb_parse_ptype(uint8_t port __rte_unused, uint16_t queue __rte_unused, + struct rte_mbuf *pkts[], uint16_t nb_pkts, + uint16_t max_pkts __rte_unused, + void *user_param __rte_unused) +{ + unsigned i; + + for (i = 0; i < nb_pkts; ++i) + em_parse_ptype(pkts[i]); + + return nb_pkts; +} + /* main processing loop */ int em_main_loop(__attribute__((unused)) void *dummy) @@ -568,8 +685,8 @@ em_main_loop(__attribute__((unused)) void *dummy) diff_tsc = cur_tsc - prev_tsc; if (unlikely(diff_tsc > drain_tsc)) { - for (i = 0; i < qconf->n_rx_queue; i++) { - portid = qconf->rx_queue_list[i].port_id; + for (i = 0; i < qconf->n_tx_port; ++i) { + portid = qconf->tx_port_id[i]; if (qconf->tx_mbufs[portid].len == 0) continue; send_burst(qconf, @@ -592,17 +709,13 @@ em_main_loop(__attribute__((unused)) void *dummy) if (nb_rx == 0) continue; - /* - * For SSE4_1 use ENABLE_MULTI_BUFFER_OPTIMIZE=1 - * code. - */ -#if defined(__SSE4_1__) +#if defined RTE_ARCH_X86 || defined RTE_MACHINE_CPUFLAG_NEON l3fwd_em_send_packets(nb_rx, pkts_burst, portid, qconf); #else l3fwd_em_no_opt_send_packets(nb_rx, pkts_burst, portid, qconf); -#endif /* __SSE_4_1__ */ +#endif } }