X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=examples%2Fipsec-secgw%2Fipsec-secgw.c;h=d6a495952a8eea4a3cd82d688b1b5098d9ef5314;hb=d04bb1c52647952e191f5ba2c56319c0139afc73;hp=904ee65d987f8e5eed9d9626b68461e5c5be5a9e;hpb=ba66534fc763b30ac4dc17225f18a65ebfe72b33;p=dpdk.git diff --git a/examples/ipsec-secgw/ipsec-secgw.c b/examples/ipsec-secgw/ipsec-secgw.c index 904ee65d98..d6a495952a 100644 --- a/examples/ipsec-secgw/ipsec-secgw.c +++ b/examples/ipsec-secgw/ipsec-secgw.c @@ -2,6 +2,7 @@ * Copyright(c) 2016 Intel Corporation */ +#include #include #include #include @@ -14,14 +15,15 @@ #include #include #include +#include #include #include +#include #include #include #include #include -#include #include #include #include @@ -41,39 +43,35 @@ #include #include #include +#include #include #include +#include +#include +#include "event_helper.h" +#include "flow.h" #include "ipsec.h" +#include "ipsec_worker.h" #include "parser.h" +#include "sad.h" -#define RTE_LOGTYPE_IPSEC RTE_LOGTYPE_USER1 +volatile bool force_quit; #define MAX_JUMBO_PKT_LEN 9600 #define MEMPOOL_CACHE_SIZE 256 -#define NB_MBUF (32000) - #define CDEV_QUEUE_DESC 2048 #define CDEV_MAP_ENTRIES 16384 -#define CDEV_MP_NB_OBJS 1024 #define CDEV_MP_CACHE_SZ 64 +#define CDEV_MP_CACHE_MULTIPLIER 1.5 /* from rte_mempool.c */ #define MAX_QUEUE_PAIRS 1 #define BURST_TX_DRAIN_US 100 /* TX drain every ~100us */ -#define NB_SOCKETS 4 - -/* Configure how many packets ahead to prefetch, when reading packets */ -#define PREFETCH_OFFSET 3 - -#define MAX_RX_QUEUE_PER_LCORE 16 - #define MAX_LCORE_PARAMS 1024 -#define UNPROTECTED_PORT(port) (unprotected_port_mask & (1 << portid)) - /* * Configurable number of RX/TX ring descriptors */ @@ -82,29 +80,6 @@ static uint16_t nb_rxd = IPSEC_SECGW_RX_DESC_DEFAULT; static uint16_t nb_txd = IPSEC_SECGW_TX_DESC_DEFAULT; -#if RTE_BYTE_ORDER != RTE_LITTLE_ENDIAN -#define __BYTES_TO_UINT64(a, b, c, d, e, f, g, h) \ - (((uint64_t)((a) & 0xff) << 56) | \ - ((uint64_t)((b) & 0xff) << 48) | \ - ((uint64_t)((c) & 0xff) << 40) | \ - ((uint64_t)((d) & 0xff) << 32) | \ - ((uint64_t)((e) & 0xff) << 24) | \ - ((uint64_t)((f) & 0xff) << 16) | \ - ((uint64_t)((g) & 0xff) << 8) | \ - ((uint64_t)(h) & 0xff)) -#else -#define __BYTES_TO_UINT64(a, b, c, d, e, f, g, h) \ - (((uint64_t)((h) & 0xff) << 56) | \ - ((uint64_t)((g) & 0xff) << 48) | \ - ((uint64_t)((f) & 0xff) << 40) | \ - ((uint64_t)((e) & 0xff) << 32) | \ - ((uint64_t)((d) & 0xff) << 24) | \ - ((uint64_t)((c) & 0xff) << 16) | \ - ((uint64_t)((b) & 0xff) << 8) | \ - ((uint64_t)(a) & 0xff)) -#endif -#define ETHADDR(a, b, c, d, e, f) (__BYTES_TO_UINT64(a, b, c, d, e, f, 0, 0)) - #define ETHADDR_TO_UINT64(addr) __BYTES_TO_UINT64( \ (addr)->addr_bytes[0], (addr)->addr_bytes[1], \ (addr)->addr_bytes[2], (addr)->addr_bytes[3], \ @@ -112,15 +87,10 @@ static uint16_t nb_txd = IPSEC_SECGW_TX_DESC_DEFAULT; 0, 0) #define FRAG_TBL_BUCKET_ENTRIES 4 -#define FRAG_TTL_MS (10 * MS_PER_S) +#define MAX_FRAG_TTL_NS (10LL * NS_PER_S) #define MTU_TO_FRAMELEN(x) ((x) + RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN) -/* port/source ethernet addr and destination ethernet addr */ -struct ethaddr_info { - uint64_t src, dst; -}; - struct ethaddr_info ethaddr_tbl[RTE_MAX_ETHPORTS] = { { 0, ETHADDR(0x00, 0x16, 0x3e, 0x7e, 0x94, 0x9a) }, { 0, ETHADDR(0x00, 0x16, 0x3e, 0x22, 0xa1, 0xd9) }, @@ -128,13 +98,29 @@ struct ethaddr_info ethaddr_tbl[RTE_MAX_ETHPORTS] = { { 0, ETHADDR(0x00, 0x16, 0x3e, 0x49, 0x9e, 0xdd) } }; +struct flow_info flow_info_tbl[RTE_MAX_ETHPORTS]; + #define CMD_LINE_OPT_CONFIG "config" #define CMD_LINE_OPT_SINGLE_SA "single-sa" #define CMD_LINE_OPT_CRYPTODEV_MASK "cryptodev_mask" +#define CMD_LINE_OPT_TRANSFER_MODE "transfer-mode" +#define CMD_LINE_OPT_SCHEDULE_TYPE "event-schedule-type" #define CMD_LINE_OPT_RX_OFFLOAD "rxoffload" #define CMD_LINE_OPT_TX_OFFLOAD "txoffload" #define CMD_LINE_OPT_REASSEMBLE "reassemble" #define CMD_LINE_OPT_MTU "mtu" +#define CMD_LINE_OPT_FRAG_TTL "frag-ttl" +#define CMD_LINE_OPT_EVENT_VECTOR "event-vector" +#define CMD_LINE_OPT_VECTOR_SIZE "vector-size" +#define CMD_LINE_OPT_VECTOR_TIMEOUT "vector-tmo" +#define CMD_LINE_OPT_VECTOR_POOL_SZ "vector-pool-sz" +#define CMD_LINE_OPT_PER_PORT_POOL "per-port-pool" + +#define CMD_LINE_ARG_EVENT "event" +#define CMD_LINE_ARG_POLL "poll" +#define CMD_LINE_ARG_ORDERED "ordered" +#define CMD_LINE_ARG_ATOMIC "atomic" +#define CMD_LINE_ARG_PARALLEL "parallel" enum { /* long options mapped to a short option */ @@ -146,32 +132,49 @@ enum { CMD_LINE_OPT_CONFIG_NUM, CMD_LINE_OPT_SINGLE_SA_NUM, CMD_LINE_OPT_CRYPTODEV_MASK_NUM, + CMD_LINE_OPT_TRANSFER_MODE_NUM, + CMD_LINE_OPT_SCHEDULE_TYPE_NUM, CMD_LINE_OPT_RX_OFFLOAD_NUM, CMD_LINE_OPT_TX_OFFLOAD_NUM, CMD_LINE_OPT_REASSEMBLE_NUM, CMD_LINE_OPT_MTU_NUM, + CMD_LINE_OPT_FRAG_TTL_NUM, + CMD_LINE_OPT_EVENT_VECTOR_NUM, + CMD_LINE_OPT_VECTOR_SIZE_NUM, + CMD_LINE_OPT_VECTOR_TIMEOUT_NUM, + CMD_LINE_OPT_VECTOR_POOL_SZ_NUM, + CMD_LINE_OPT_PER_PORT_POOL_NUM, }; static const struct option lgopts[] = { {CMD_LINE_OPT_CONFIG, 1, 0, CMD_LINE_OPT_CONFIG_NUM}, {CMD_LINE_OPT_SINGLE_SA, 1, 0, CMD_LINE_OPT_SINGLE_SA_NUM}, {CMD_LINE_OPT_CRYPTODEV_MASK, 1, 0, CMD_LINE_OPT_CRYPTODEV_MASK_NUM}, + {CMD_LINE_OPT_TRANSFER_MODE, 1, 0, CMD_LINE_OPT_TRANSFER_MODE_NUM}, + {CMD_LINE_OPT_SCHEDULE_TYPE, 1, 0, CMD_LINE_OPT_SCHEDULE_TYPE_NUM}, {CMD_LINE_OPT_RX_OFFLOAD, 1, 0, CMD_LINE_OPT_RX_OFFLOAD_NUM}, {CMD_LINE_OPT_TX_OFFLOAD, 1, 0, CMD_LINE_OPT_TX_OFFLOAD_NUM}, {CMD_LINE_OPT_REASSEMBLE, 1, 0, CMD_LINE_OPT_REASSEMBLE_NUM}, {CMD_LINE_OPT_MTU, 1, 0, CMD_LINE_OPT_MTU_NUM}, + {CMD_LINE_OPT_FRAG_TTL, 1, 0, CMD_LINE_OPT_FRAG_TTL_NUM}, + {CMD_LINE_OPT_EVENT_VECTOR, 0, 0, CMD_LINE_OPT_EVENT_VECTOR_NUM}, + {CMD_LINE_OPT_VECTOR_SIZE, 1, 0, CMD_LINE_OPT_VECTOR_SIZE_NUM}, + {CMD_LINE_OPT_VECTOR_TIMEOUT, 1, 0, CMD_LINE_OPT_VECTOR_TIMEOUT_NUM}, + {CMD_LINE_OPT_VECTOR_POOL_SZ, 1, 0, CMD_LINE_OPT_VECTOR_POOL_SZ_NUM}, + {CMD_LINE_OPT_PER_PORT_POOL, 0, 0, CMD_LINE_OPT_PER_PORT_POOL_NUM}, {NULL, 0, 0, 0} }; +uint32_t unprotected_port_mask; +uint32_t single_sa_idx; /* mask of enabled ports */ static uint32_t enabled_port_mask; static uint64_t enabled_cryptodev_mask = UINT64_MAX; -static uint32_t unprotected_port_mask; static int32_t promiscuous_on = 1; static int32_t numa_on = 1; /**< NUMA is enabled by default. */ static uint32_t nb_lcores; static uint32_t single_sa; -static uint32_t single_sa_idx; +uint32_t nb_bufs_in_pool; /* * RX/TX HW offload capabilities to enable/use on ethernet ports. @@ -183,19 +186,20 @@ static uint64_t dev_tx_offload = UINT64_MAX; /* * global values that determine multi-seg policy */ -static uint32_t frag_tbl_sz; +uint32_t frag_tbl_sz; static uint32_t frame_buf_size = RTE_MBUF_DEFAULT_BUF_SIZE; -static uint32_t mtu_size = RTE_ETHER_MTU; +uint32_t mtu_size = RTE_ETHER_MTU; +static uint64_t frag_ttl_ns = MAX_FRAG_TTL_NS; +static uint32_t stats_interval; /* application wide librte_ipsec/SA parameters */ -struct app_sa_prm app_sa_prm = {.enable = 0}; +struct app_sa_prm app_sa_prm = { + .enable = 0, + .cache_sz = SA_CACHE_SZ, + .udp_encap = 0 + }; static const char *cfgfile; -struct lcore_rx_queue { - uint16_t port_id; - uint8_t queue_id; -} __rte_cache_aligned; - struct lcore_params { uint16_t port_id; uint8_t queue_id; @@ -210,55 +214,34 @@ static uint16_t nb_lcore_params; static struct rte_hash *cdev_map_in; static struct rte_hash *cdev_map_out; -struct buffer { - uint16_t len; - struct rte_mbuf *m_table[MAX_PKT_BURST] __rte_aligned(sizeof(void *)); -}; - -struct lcore_conf { - uint16_t nb_rx_queue; - struct lcore_rx_queue rx_queue_list[MAX_RX_QUEUE_PER_LCORE]; - uint16_t tx_queue_id[RTE_MAX_ETHPORTS]; - struct buffer tx_mbufs[RTE_MAX_ETHPORTS]; - struct ipsec_ctx inbound; - struct ipsec_ctx outbound; - struct rt_ctx *rt4_ctx; - struct rt_ctx *rt6_ctx; - struct { - struct rte_ip_frag_tbl *tbl; - struct rte_mempool *pool_dir; - struct rte_mempool *pool_indir; - struct rte_ip_frag_death_row dr; - } frag; -} __rte_cache_aligned; - -static struct lcore_conf lcore_conf[RTE_MAX_LCORE]; +struct lcore_conf lcore_conf[RTE_MAX_LCORE]; static struct rte_eth_conf port_conf = { .rxmode = { - .mq_mode = ETH_MQ_RX_RSS, - .max_rx_pkt_len = RTE_ETHER_MAX_LEN, + .mq_mode = RTE_ETH_MQ_RX_RSS, .split_hdr_size = 0, - .offloads = DEV_RX_OFFLOAD_CHECKSUM, + .offloads = RTE_ETH_RX_OFFLOAD_CHECKSUM, }, .rx_adv_conf = { .rss_conf = { .rss_key = NULL, - .rss_hf = ETH_RSS_IP | ETH_RSS_UDP | - ETH_RSS_TCP | ETH_RSS_SCTP, + .rss_hf = RTE_ETH_RSS_IP | RTE_ETH_RSS_UDP | + RTE_ETH_RSS_TCP | RTE_ETH_RSS_SCTP, }, }, .txmode = { - .mq_mode = ETH_MQ_TX_NONE, + .mq_mode = RTE_ETH_MQ_TX_NONE, }, }; -static struct socket_ctx socket_ctx[NB_SOCKETS]; +struct socket_ctx socket_ctx[NB_SOCKETS]; + +bool per_port_pool; /* * Determine is multi-segment support required: * - either frame buffer size is smaller then mtu - * - or reassmeble support is requested + * - or reassemble support is requested */ static int multi_seg_required(void) @@ -267,344 +250,68 @@ multi_seg_required(void) frame_buf_size || frag_tbl_sz != 0); } -static inline void -adjust_ipv4_pktlen(struct rte_mbuf *m, const struct rte_ipv4_hdr *iph, - uint32_t l2_len) -{ - uint32_t plen, trim; - - plen = rte_be_to_cpu_16(iph->total_length) + l2_len; - if (plen < m->pkt_len) { - trim = m->pkt_len - plen; - rte_pktmbuf_trim(m, trim); - } -} - -static inline void -adjust_ipv6_pktlen(struct rte_mbuf *m, const struct rte_ipv6_hdr *iph, - uint32_t l2_len) -{ - uint32_t plen, trim; - - plen = rte_be_to_cpu_16(iph->payload_len) + sizeof(*iph) + l2_len; - if (plen < m->pkt_len) { - trim = m->pkt_len - plen; - rte_pktmbuf_trim(m, trim); - } -} - -static inline void -prepare_one_packet(struct rte_mbuf *pkt, struct ipsec_traffic *t) -{ - const struct rte_ether_hdr *eth; - const struct rte_ipv4_hdr *iph4; - const struct rte_ipv6_hdr *iph6; - - eth = rte_pktmbuf_mtod(pkt, const struct rte_ether_hdr *); - if (eth->ether_type == rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4)) { - - iph4 = (const struct rte_ipv4_hdr *)rte_pktmbuf_adj(pkt, - RTE_ETHER_HDR_LEN); - adjust_ipv4_pktlen(pkt, iph4, 0); - - if (iph4->next_proto_id == IPPROTO_ESP) - t->ipsec.pkts[(t->ipsec.num)++] = pkt; - else { - t->ip4.data[t->ip4.num] = &iph4->next_proto_id; - t->ip4.pkts[(t->ip4.num)++] = pkt; - } - pkt->l2_len = 0; - pkt->l3_len = sizeof(*iph4); - } else if (eth->ether_type == rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6)) { - int next_proto; - size_t l3len, ext_len; - uint8_t *p; - - /* get protocol type */ - iph6 = (const struct rte_ipv6_hdr *)rte_pktmbuf_adj(pkt, - RTE_ETHER_HDR_LEN); - adjust_ipv6_pktlen(pkt, iph6, 0); - - next_proto = iph6->proto; - - /* determine l3 header size up to ESP extension */ - l3len = sizeof(struct ip6_hdr); - p = rte_pktmbuf_mtod(pkt, uint8_t *); - while (next_proto != IPPROTO_ESP && l3len < pkt->data_len && - (next_proto = rte_ipv6_get_next_ext(p + l3len, - next_proto, &ext_len)) >= 0) - l3len += ext_len; - - /* drop packet when IPv6 header exceeds first segment length */ - if (unlikely(l3len > pkt->data_len)) { - rte_pktmbuf_free(pkt); - return; - } - - if (next_proto == IPPROTO_ESP) - t->ipsec.pkts[(t->ipsec.num)++] = pkt; - else { - t->ip6.data[t->ip6.num] = &iph6->proto; - t->ip6.pkts[(t->ip6.num)++] = pkt; - } - pkt->l2_len = 0; - pkt->l3_len = l3len; - } else { - /* Unknown/Unsupported type, drop the packet */ - RTE_LOG(ERR, IPSEC, "Unsupported packet type 0x%x\n", - rte_be_to_cpu_16(eth->ether_type)); - rte_pktmbuf_free(pkt); - return; - } - - /* Check if the packet has been processed inline. For inline protocol - * processed packets, the metadata in the mbuf can be used to identify - * the security processing done on the packet. The metadata will be - * used to retrieve the application registered userdata associated - * with the security session. - */ - - if (pkt->ol_flags & PKT_RX_SEC_OFFLOAD) { - struct ipsec_sa *sa; - struct ipsec_mbuf_metadata *priv; - struct rte_security_ctx *ctx = (struct rte_security_ctx *) - rte_eth_dev_get_sec_ctx( - pkt->port); - - /* Retrieve the userdata registered. Here, the userdata - * registered is the SA pointer. - */ - - sa = (struct ipsec_sa *) - rte_security_get_userdata(ctx, pkt->udata64); - - if (sa == NULL) { - /* userdata could not be retrieved */ - return; - } - - /* Save SA as priv member in mbuf. This will be used in the - * IPsec selector(SP-SA) check. - */ - - priv = get_priv(pkt); - priv->sa = sa; - } -} - -static inline void -prepare_traffic(struct rte_mbuf **pkts, struct ipsec_traffic *t, - uint16_t nb_pkts) -{ - int32_t i; - - t->ipsec.num = 0; - t->ip4.num = 0; - t->ip6.num = 0; - - for (i = 0; i < (nb_pkts - PREFETCH_OFFSET); i++) { - rte_prefetch0(rte_pktmbuf_mtod(pkts[i + PREFETCH_OFFSET], - void *)); - prepare_one_packet(pkts[i], t); - } - /* Process left packets */ - for (; i < nb_pkts; i++) - prepare_one_packet(pkts[i], t); -} - -static inline void -prepare_tx_pkt(struct rte_mbuf *pkt, uint16_t port, - const struct lcore_conf *qconf) -{ - struct ip *ip; - struct rte_ether_hdr *ethhdr; - - ip = rte_pktmbuf_mtod(pkt, struct ip *); - - ethhdr = (struct rte_ether_hdr *) - rte_pktmbuf_prepend(pkt, RTE_ETHER_HDR_LEN); - - if (ip->ip_v == IPVERSION) { - pkt->ol_flags |= qconf->outbound.ipv4_offloads; - pkt->l3_len = sizeof(struct ip); - pkt->l2_len = RTE_ETHER_HDR_LEN; - - ip->ip_sum = 0; - - /* calculate IPv4 cksum in SW */ - if ((pkt->ol_flags & PKT_TX_IP_CKSUM) == 0) - ip->ip_sum = rte_ipv4_cksum((struct rte_ipv4_hdr *)ip); - - ethhdr->ether_type = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4); - } else { - pkt->ol_flags |= qconf->outbound.ipv6_offloads; - pkt->l3_len = sizeof(struct ip6_hdr); - pkt->l2_len = RTE_ETHER_HDR_LEN; - - ethhdr->ether_type = rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6); - } - - memcpy(ðhdr->s_addr, ðaddr_tbl[port].src, - sizeof(struct rte_ether_addr)); - memcpy(ðhdr->d_addr, ðaddr_tbl[port].dst, - sizeof(struct rte_ether_addr)); -} - -static inline void -prepare_tx_burst(struct rte_mbuf *pkts[], uint16_t nb_pkts, uint16_t port, - const struct lcore_conf *qconf) -{ - int32_t i; - const int32_t prefetch_offset = 2; - - for (i = 0; i < (nb_pkts - prefetch_offset); i++) { - rte_mbuf_prefetch_part2(pkts[i + prefetch_offset]); - prepare_tx_pkt(pkts[i], port, qconf); - } - /* Process left packets */ - for (; i < nb_pkts; i++) - prepare_tx_pkt(pkts[i], port, qconf); -} - -/* Send burst of packets on an output interface */ -static inline int32_t -send_burst(struct lcore_conf *qconf, uint16_t n, uint16_t port) -{ - struct rte_mbuf **m_table; - int32_t ret; - uint16_t queueid; - - queueid = qconf->tx_queue_id[port]; - m_table = (struct rte_mbuf **)qconf->tx_mbufs[port].m_table; - - prepare_tx_burst(m_table, n, port, qconf); - - ret = rte_eth_tx_burst(port, queueid, m_table, n); - if (unlikely(ret < n)) { - do { - rte_pktmbuf_free(m_table[ret]); - } while (++ret < n); - } - - return 0; -} - -/* - * Helper function to fragment and queue for TX one packet. - */ -static inline uint32_t -send_fragment_packet(struct lcore_conf *qconf, struct rte_mbuf *m, - uint16_t port, uint8_t proto) -{ - struct buffer *tbl; - uint32_t len, n; - int32_t rc; - - tbl = qconf->tx_mbufs + port; - len = tbl->len; - - /* free space for new fragments */ - if (len + RTE_LIBRTE_IP_FRAG_MAX_FRAG >= RTE_DIM(tbl->m_table)) { - send_burst(qconf, len, port); - len = 0; - } - - n = RTE_DIM(tbl->m_table) - len; - - if (proto == IPPROTO_IP) - rc = rte_ipv4_fragment_packet(m, tbl->m_table + len, - n, mtu_size, qconf->frag.pool_dir, - qconf->frag.pool_indir); - else - rc = rte_ipv6_fragment_packet(m, tbl->m_table + len, - n, mtu_size, qconf->frag.pool_dir, - qconf->frag.pool_indir); - - if (rc >= 0) - len += rc; - else - RTE_LOG(ERR, IPSEC, - "%s: failed to fragment packet with size %u, " - "error code: %d\n", - __func__, m->pkt_len, rte_errno); - - rte_pktmbuf_free(m); - return len; -} - -/* Enqueue a single packet, and send burst if queue is filled */ -static inline int32_t -send_single_packet(struct rte_mbuf *m, uint16_t port, uint8_t proto) -{ - uint32_t lcore_id; - uint16_t len; - struct lcore_conf *qconf; - - lcore_id = rte_lcore_id(); - - qconf = &lcore_conf[lcore_id]; - len = qconf->tx_mbufs[port].len; - - if (m->pkt_len <= mtu_size) { - qconf->tx_mbufs[port].m_table[len] = m; - len++; - - /* need to fragment the packet */ - } else if (frag_tbl_sz > 0) - len = send_fragment_packet(qconf, m, port, proto); - else - rte_pktmbuf_free(m); - - /* enough pkts to be sent */ - if (unlikely(len == MAX_PKT_BURST)) { - send_burst(qconf, MAX_PKT_BURST, port); - len = 0; - } - qconf->tx_mbufs[port].len = len; - return 0; -} +struct ipsec_core_statistics core_statistics[RTE_MAX_LCORE]; -static inline void -inbound_sp_sa(struct sp_ctx *sp, struct sa_ctx *sa, struct traffic_type *ip, - uint16_t lim) +/* Print out statistics on packet distribution */ +static void +print_stats_cb(__rte_unused void *param) { - struct rte_mbuf *m; - uint32_t i, j, res, sa_idx; + uint64_t total_packets_dropped, total_packets_tx, total_packets_rx; + float burst_percent, rx_per_call, tx_per_call; + unsigned int coreid; - if (ip->num == 0 || sp == NULL) - return; + total_packets_dropped = 0; + total_packets_tx = 0; + total_packets_rx = 0; - rte_acl_classify((struct rte_acl_ctx *)sp, ip->data, ip->res, - ip->num, DEFAULT_MAX_CATEGORIES); + const char clr[] = { 27, '[', '2', 'J', '\0' }; + const char topLeft[] = { 27, '[', '1', ';', '1', 'H', '\0' }; - j = 0; - for (i = 0; i < ip->num; i++) { - m = ip->pkts[i]; - res = ip->res[i]; - if (res == BYPASS) { - ip->pkts[j++] = m; - continue; - } - if (res == DISCARD) { - rte_pktmbuf_free(m); - continue; - } + /* Clear screen and move to top left */ + printf("%s%s", clr, topLeft); - /* Only check SPI match for processed IPSec packets */ - if (i < lim && ((m->ol_flags & PKT_RX_SEC_OFFLOAD) == 0)) { - rte_pktmbuf_free(m); - continue; - } + printf("\nCore statistics ===================================="); - sa_idx = SPI2IDX(res); - if (!inbound_sa_check(sa, m, sa_idx)) { - rte_pktmbuf_free(m); + for (coreid = 0; coreid < RTE_MAX_LCORE; coreid++) { + /* skip disabled cores */ + if (rte_lcore_is_enabled(coreid) == 0) continue; - } - ip->pkts[j++] = m; - } - ip->num = j; + burst_percent = (float)(core_statistics[coreid].burst_rx * 100)/ + core_statistics[coreid].rx; + rx_per_call = (float)(core_statistics[coreid].rx)/ + core_statistics[coreid].rx_call; + tx_per_call = (float)(core_statistics[coreid].tx)/ + core_statistics[coreid].tx_call; + printf("\nStatistics for core %u ------------------------------" + "\nPackets received: %20"PRIu64 + "\nPackets sent: %24"PRIu64 + "\nPackets dropped: %21"PRIu64 + "\nBurst percent: %23.2f" + "\nPackets per Rx call: %17.2f" + "\nPackets per Tx call: %17.2f", + coreid, + core_statistics[coreid].rx, + core_statistics[coreid].tx, + core_statistics[coreid].dropped, + burst_percent, + rx_per_call, + tx_per_call); + + total_packets_dropped += core_statistics[coreid].dropped; + total_packets_tx += core_statistics[coreid].tx; + total_packets_rx += core_statistics[coreid].rx; + } + printf("\nAggregate statistics ===============================" + "\nTotal packets received: %14"PRIu64 + "\nTotal packets sent: %18"PRIu64 + "\nTotal packets dropped: %15"PRIu64, + total_packets_rx, + total_packets_tx, + total_packets_dropped); + printf("\n====================================================\n"); + + rte_eal_alarm_set(stats_interval * US_PER_S, print_stats_cb, NULL); } static void @@ -634,7 +341,7 @@ split46_traffic(struct ipsec_traffic *trf, struct rte_mbuf *mb[], uint32_t num) offsetof(struct ip6_hdr, ip6_nxt)); n6++; } else - rte_pktmbuf_free(m); + free_pkts(&m, 1); } trf->ip4.num = n4; @@ -646,6 +353,7 @@ static inline void process_pkts_inbound(struct ipsec_ctx *ipsec_ctx, struct ipsec_traffic *traffic) { + unsigned int lcoreid = rte_lcore_id(); uint16_t nb_pkts_in, n_ip4, n_ip6; n_ip4 = traffic->ip4.num; @@ -661,16 +369,20 @@ process_pkts_inbound(struct ipsec_ctx *ipsec_ctx, ipsec_process(ipsec_ctx, traffic); } - inbound_sp_sa(ipsec_ctx->sp4_ctx, ipsec_ctx->sa_ctx, &traffic->ip4, - n_ip4); + inbound_sp_sa(ipsec_ctx->sp4_ctx, + ipsec_ctx->sa_ctx, &traffic->ip4, n_ip4, + &core_statistics[lcoreid].inbound.spd4); - inbound_sp_sa(ipsec_ctx->sp6_ctx, ipsec_ctx->sa_ctx, &traffic->ip6, - n_ip6); + inbound_sp_sa(ipsec_ctx->sp6_ctx, + ipsec_ctx->sa_ctx, &traffic->ip6, n_ip6, + &core_statistics[lcoreid].inbound.spd6); } static inline void -outbound_sp(struct sp_ctx *sp, struct traffic_type *ip, - struct traffic_type *ipsec) +outbound_spd_lookup(struct sp_ctx *sp, + struct traffic_type *ip, + struct traffic_type *ipsec, + struct ipsec_spd_stats *stats) { struct rte_mbuf *m; uint32_t i, j, sa_idx; @@ -681,17 +393,23 @@ outbound_sp(struct sp_ctx *sp, struct traffic_type *ip, rte_acl_classify((struct rte_acl_ctx *)sp, ip->data, ip->res, ip->num, DEFAULT_MAX_CATEGORIES); - j = 0; - for (i = 0; i < ip->num; i++) { + for (i = 0, j = 0; i < ip->num; i++) { m = ip->pkts[i]; - sa_idx = SPI2IDX(ip->res[i]); - if (ip->res[i] == DISCARD) - rte_pktmbuf_free(m); - else if (ip->res[i] == BYPASS) + sa_idx = ip->res[i] - 1; + + if (unlikely(ip->res[i] == DISCARD)) { + free_pkts(&m, 1); + + stats->discard++; + } else if (unlikely(ip->res[i] == BYPASS)) { ip->pkts[j++] = m; - else { + + stats->bypass++; + } else { ipsec->res[ipsec->num] = sa_idx; ipsec->pkts[ipsec->num++] = m; + + stats->protect++; } } ip->num = j; @@ -703,16 +421,20 @@ process_pkts_outbound(struct ipsec_ctx *ipsec_ctx, { struct rte_mbuf *m; uint16_t idx, nb_pkts_out, i; + unsigned int lcoreid = rte_lcore_id(); /* Drop any IPsec traffic from protected ports */ - for (i = 0; i < traffic->ipsec.num; i++) - rte_pktmbuf_free(traffic->ipsec.pkts[i]); + free_pkts(traffic->ipsec.pkts, traffic->ipsec.num); traffic->ipsec.num = 0; - outbound_sp(ipsec_ctx->sp4_ctx, &traffic->ip4, &traffic->ipsec); + outbound_spd_lookup(ipsec_ctx->sp4_ctx, + &traffic->ip4, &traffic->ipsec, + &core_statistics[lcoreid].outbound.spd4); - outbound_sp(ipsec_ctx->sp6_ctx, &traffic->ip6, &traffic->ipsec); + outbound_spd_lookup(ipsec_ctx->sp6_ctx, + &traffic->ip6, &traffic->ipsec, + &core_statistics[lcoreid].outbound.spd6); if (app_sa_prm.enable == 0) { @@ -745,18 +467,6 @@ process_pkts_inbound_nosp(struct ipsec_ctx *ipsec_ctx, struct rte_mbuf *m; uint32_t nb_pkts_in, i, idx; - /* Drop any IPv4 traffic from unprotected ports */ - for (i = 0; i < traffic->ip4.num; i++) - rte_pktmbuf_free(traffic->ip4.pkts[i]); - - traffic->ip4.num = 0; - - /* Drop any IPv6 traffic from unprotected ports */ - for (i = 0; i < traffic->ip6.num; i++) - rte_pktmbuf_free(traffic->ip6.pkts[i]); - - traffic->ip6.num = 0; - if (app_sa_prm.enable == 0) { nb_pkts_in = ipsec_inbound(ipsec_ctx, traffic->ipsec.pkts, @@ -789,8 +499,7 @@ process_pkts_outbound_nosp(struct ipsec_ctx *ipsec_ctx, struct ip *ip; /* Drop any IPsec traffic from protected ports */ - for (i = 0; i < traffic->ipsec.num; i++) - rte_pktmbuf_free(traffic->ipsec.pkts[i]); + free_pkts(traffic->ipsec.pkts, traffic->ipsec.num); n = 0; @@ -833,136 +542,6 @@ process_pkts_outbound_nosp(struct ipsec_ctx *ipsec_ctx, } } -static inline int32_t -get_hop_for_offload_pkt(struct rte_mbuf *pkt, int is_ipv6) -{ - struct ipsec_mbuf_metadata *priv; - struct ipsec_sa *sa; - - priv = get_priv(pkt); - - sa = priv->sa; - if (unlikely(sa == NULL)) { - RTE_LOG(ERR, IPSEC, "SA not saved in private data\n"); - goto fail; - } - - if (is_ipv6) - return sa->portid; - - /* else */ - return (sa->portid | RTE_LPM_LOOKUP_SUCCESS); - -fail: - if (is_ipv6) - return -1; - - /* else */ - return 0; -} - -static inline void -route4_pkts(struct rt_ctx *rt_ctx, struct rte_mbuf *pkts[], uint8_t nb_pkts) -{ - uint32_t hop[MAX_PKT_BURST * 2]; - uint32_t dst_ip[MAX_PKT_BURST * 2]; - int32_t pkt_hop = 0; - uint16_t i, offset; - uint16_t lpm_pkts = 0; - - if (nb_pkts == 0) - return; - - /* Need to do an LPM lookup for non-inline packets. Inline packets will - * have port ID in the SA - */ - - for (i = 0; i < nb_pkts; i++) { - if (!(pkts[i]->ol_flags & PKT_TX_SEC_OFFLOAD)) { - /* Security offload not enabled. So an LPM lookup is - * required to get the hop - */ - offset = offsetof(struct ip, ip_dst); - dst_ip[lpm_pkts] = *rte_pktmbuf_mtod_offset(pkts[i], - uint32_t *, offset); - dst_ip[lpm_pkts] = rte_be_to_cpu_32(dst_ip[lpm_pkts]); - lpm_pkts++; - } - } - - rte_lpm_lookup_bulk((struct rte_lpm *)rt_ctx, dst_ip, hop, lpm_pkts); - - lpm_pkts = 0; - - for (i = 0; i < nb_pkts; i++) { - if (pkts[i]->ol_flags & PKT_TX_SEC_OFFLOAD) { - /* Read hop from the SA */ - pkt_hop = get_hop_for_offload_pkt(pkts[i], 0); - } else { - /* Need to use hop returned by lookup */ - pkt_hop = hop[lpm_pkts++]; - } - - if ((pkt_hop & RTE_LPM_LOOKUP_SUCCESS) == 0) { - rte_pktmbuf_free(pkts[i]); - continue; - } - send_single_packet(pkts[i], pkt_hop & 0xff, IPPROTO_IP); - } -} - -static inline void -route6_pkts(struct rt_ctx *rt_ctx, struct rte_mbuf *pkts[], uint8_t nb_pkts) -{ - int32_t hop[MAX_PKT_BURST * 2]; - uint8_t dst_ip[MAX_PKT_BURST * 2][16]; - uint8_t *ip6_dst; - int32_t pkt_hop = 0; - uint16_t i, offset; - uint16_t lpm_pkts = 0; - - if (nb_pkts == 0) - return; - - /* Need to do an LPM lookup for non-inline packets. Inline packets will - * have port ID in the SA - */ - - for (i = 0; i < nb_pkts; i++) { - if (!(pkts[i]->ol_flags & PKT_TX_SEC_OFFLOAD)) { - /* Security offload not enabled. So an LPM lookup is - * required to get the hop - */ - offset = offsetof(struct ip6_hdr, ip6_dst); - ip6_dst = rte_pktmbuf_mtod_offset(pkts[i], uint8_t *, - offset); - memcpy(&dst_ip[lpm_pkts][0], ip6_dst, 16); - lpm_pkts++; - } - } - - rte_lpm6_lookup_bulk_func((struct rte_lpm6 *)rt_ctx, dst_ip, hop, - lpm_pkts); - - lpm_pkts = 0; - - for (i = 0; i < nb_pkts; i++) { - if (pkts[i]->ol_flags & PKT_TX_SEC_OFFLOAD) { - /* Read hop from the SA */ - pkt_hop = get_hop_for_offload_pkt(pkts[i], 1); - } else { - /* Need to use hop returned by lookup */ - pkt_hop = hop[lpm_pkts++]; - } - - if (pkt_hop == -1) { - rte_pktmbuf_free(pkts[i]); - continue; - } - send_single_packet(pkts[i], pkt_hop & 0xff, IPPROTO_IPV6); - } -} - static inline void process_pkts(struct lcore_conf *qconf, struct rte_mbuf **pkts, uint8_t nb_pkts, uint16_t portid) @@ -972,12 +551,12 @@ process_pkts(struct lcore_conf *qconf, struct rte_mbuf **pkts, prepare_traffic(pkts, &traffic, nb_pkts); if (unlikely(single_sa)) { - if (UNPROTECTED_PORT(portid)) + if (is_unprotected_port(portid)) process_pkts_inbound_nosp(&qconf->inbound, &traffic); else process_pkts_outbound_nosp(&qconf->outbound, &traffic); } else { - if (UNPROTECTED_PORT(portid)) + if (is_unprotected_port(portid)) process_pkts_inbound(&qconf->inbound, &traffic); else process_pkts_outbound(&qconf->outbound, &traffic); @@ -987,21 +566,6 @@ process_pkts(struct lcore_conf *qconf, struct rte_mbuf **pkts, route6_pkts(qconf->rt6_ctx, traffic.ip6.pkts, traffic.ip6.num); } -static inline void -drain_tx_buffers(struct lcore_conf *qconf) -{ - struct buffer *buf; - uint32_t portid; - - for (portid = 0; portid < RTE_MAX_ETHPORTS; portid++) { - buf = &qconf->tx_mbufs[portid]; - if (buf->len == 0) - continue; - send_burst(qconf, buf->len, portid); - buf->len = 0; - } -} - static inline void drain_crypto_buffers(struct lcore_conf *qconf) { @@ -1029,6 +593,7 @@ drain_inbound_crypto_queues(const struct lcore_conf *qconf, { uint32_t n; struct ipsec_traffic trf; + unsigned int lcoreid = rte_lcore_id(); if (app_sa_prm.enable == 0) { @@ -1046,13 +611,15 @@ drain_inbound_crypto_queues(const struct lcore_conf *qconf, /* process ipv4 packets */ if (trf.ip4.num != 0) { - inbound_sp_sa(ctx->sp4_ctx, ctx->sa_ctx, &trf.ip4, 0); + inbound_sp_sa(ctx->sp4_ctx, ctx->sa_ctx, &trf.ip4, 0, + &core_statistics[lcoreid].inbound.spd4); route4_pkts(qconf->rt4_ctx, trf.ip4.pkts, trf.ip4.num); } /* process ipv6 packets */ if (trf.ip6.num != 0) { - inbound_sp_sa(ctx->sp6_ctx, ctx->sa_ctx, &trf.ip6, 0); + inbound_sp_sa(ctx->sp6_ctx, ctx->sa_ctx, &trf.ip6, 0, + &core_statistics[lcoreid].inbound.spd6); route6_pkts(qconf->rt6_ctx, trf.ip6.pkts, trf.ip6.num); } } @@ -1088,8 +655,8 @@ drain_outbound_crypto_queues(const struct lcore_conf *qconf, } /* main processing loop */ -static int32_t -main_loop(__attribute__((unused)) void *dummy) +void +ipsec_poll_mode_worker(void) { struct rte_mbuf *pkts[MAX_PKT_BURST]; uint32_t lcore_id; @@ -1098,7 +665,7 @@ main_loop(__attribute__((unused)) void *dummy) uint16_t portid; uint8_t queueid; struct lcore_conf *qconf; - int32_t socket_id; + int32_t rc, socket_id; const uint64_t drain_tsc = (rte_get_tsc_hz() + US_PER_S - 1) / US_PER_S * BURST_TX_DRAIN_US; struct lcore_rx_queue *rxql; @@ -1125,13 +692,20 @@ main_loop(__attribute__((unused)) void *dummy) qconf->outbound.session_pool = socket_ctx[socket_id].session_pool; qconf->outbound.session_priv_pool = socket_ctx[socket_id].session_priv_pool; - qconf->frag.pool_dir = socket_ctx[socket_id].mbuf_pool; qconf->frag.pool_indir = socket_ctx[socket_id].mbuf_pool_indir; + rc = ipsec_sad_lcore_cache_init(app_sa_prm.cache_sz); + if (rc != 0) { + RTE_LOG(ERR, IPSEC, + "SAD cache init on lcore %u, failed with code: %d\n", + lcore_id, rc); + return; + } + if (qconf->nb_rx_queue == 0) { RTE_LOG(DEBUG, IPSEC, "lcore %u has nothing to do\n", lcore_id); - return 0; + return; } RTE_LOG(INFO, IPSEC, "entering main loop on lcore %u\n", lcore_id); @@ -1144,7 +718,7 @@ main_loop(__attribute__((unused)) void *dummy) lcore_id, portid, queueid); } - while (1) { + while (!force_quit) { cur_tsc = rte_rdtsc(); /* TX queue buffer drain */ @@ -1164,11 +738,13 @@ main_loop(__attribute__((unused)) void *dummy) nb_rx = rte_eth_rx_burst(portid, queueid, pkts, MAX_PKT_BURST); - if (nb_rx > 0) + if (nb_rx > 0) { + core_stats_update_rx(nb_rx); process_pkts(qconf, pkts, nb_rx, portid); + } /* dequeue and process completed crypto-ops */ - if (UNPROTECTED_PORT(portid)) + if (is_unprotected_port(portid)) drain_inbound_crypto_queues(qconf, &qconf->inbound); else @@ -1178,14 +754,42 @@ main_loop(__attribute__((unused)) void *dummy) } } +int +check_flow_params(uint16_t fdir_portid, uint8_t fdir_qid) +{ + uint16_t i; + uint16_t portid; + uint8_t queueid; + + for (i = 0; i < nb_lcore_params; ++i) { + portid = lcore_params_array[i].port_id; + if (portid == fdir_portid) { + queueid = lcore_params_array[i].queue_id; + if (queueid == fdir_qid) + break; + } + + if (i == nb_lcore_params - 1) + return -1; + } + + return 1; +} + static int32_t -check_params(void) +check_poll_mode_params(struct eh_conf *eh_conf) { uint8_t lcore; uint16_t portid; uint16_t i; int32_t socket_id; + if (!eh_conf) + return -EINVAL; + + if (eh_conf->mode != EH_PKT_TRANSFER_MODE_POLL) + return 0; + if (lcore_params == NULL) { printf("Error: No port/queue/core mappings\n"); return -1; @@ -1267,14 +871,22 @@ print_usage(const char *prgname) " [-w REPLAY_WINDOW_SIZE]" " [-e]" " [-a]" + " [-c]" + " [-t STATS_INTERVAL]" + " [-s NUMBER_OF_MBUFS_IN_PKT_POOL]" " -f CONFIG_FILE" " --config (port,queue,lcore)[,(port,queue,lcore)]" " [--single-sa SAIDX]" " [--cryptodev_mask MASK]" + " [--transfer-mode MODE]" + " [--event-schedule-type TYPE]" " [--" CMD_LINE_OPT_RX_OFFLOAD " RX_OFFLOAD_MASK]" " [--" CMD_LINE_OPT_TX_OFFLOAD " TX_OFFLOAD_MASK]" " [--" CMD_LINE_OPT_REASSEMBLE " REASSEMBLE_TABLE_SIZE]" " [--" CMD_LINE_OPT_MTU " MTU]" + " [--event-vector]" + " [--vector-size SIZE]" + " [--vector-tmo TIMEOUT in ns]" "\n\n" " -p PORTMASK: Hexadecimal bitmask of ports to configure\n" " -P : Enable promiscuous mode\n" @@ -1286,18 +898,40 @@ print_usage(const char *prgname) " size for each SA\n" " -e enables ESN\n" " -a enables SA SQN atomic behaviour\n" + " -c specifies inbound SAD cache size,\n" + " zero value disables the cache (default value: 128)\n" + " -t specifies statistics screen update interval,\n" + " zero disables statistics screen (default value: 0)\n" + " -s number of mbufs in packet pool, if not specified number\n" + " of mbufs will be calculated based on number of cores,\n" + " ports and crypto queues\n" " -f CONFIG_FILE: Configuration file\n" - " --config (port,queue,lcore): Rx queue configuration\n" - " --single-sa SAIDX: Use single SA index for outbound traffic,\n" - " bypassing the SP\n" + " --config (port,queue,lcore): Rx queue configuration. In poll\n" + " mode determines which queues from\n" + " which ports are mapped to which cores.\n" + " In event mode this option is not used\n" + " as packets are dynamically scheduled\n" + " to cores by HW.\n" + " --single-sa SAIDX: In poll mode use single SA index for\n" + " outbound traffic, bypassing the SP\n" + " In event mode selects driver submode,\n" + " SA index value is ignored\n" " --cryptodev_mask MASK: Hexadecimal bitmask of the crypto\n" " devices to configure\n" + " --transfer-mode MODE\n" + " \"poll\" : Packet transfer via polling (default)\n" + " \"event\" : Packet transfer via event device\n" + " --event-schedule-type TYPE queue schedule type, used only when\n" + " transfer mode is set to event\n" + " \"ordered\" : Ordered (default)\n" + " \"atomic\" : Atomic\n" + " \"parallel\" : Parallel\n" " --" CMD_LINE_OPT_RX_OFFLOAD ": bitmask of the RX HW offload capabilities to enable/use\n" - " (DEV_RX_OFFLOAD_*)\n" + " (RTE_ETH_RX_OFFLOAD_*)\n" " --" CMD_LINE_OPT_TX_OFFLOAD ": bitmask of the TX HW offload capabilities to enable/use\n" - " (DEV_TX_OFFLOAD_*)\n" + " (RTE_ETH_TX_OFFLOAD_*)\n" " --" CMD_LINE_OPT_REASSEMBLE " NUM" ": max number of entries in reassemble(fragment) table\n" " (zero (default value) disables reassembly)\n" @@ -1305,6 +939,16 @@ print_usage(const char *prgname) ": MTU value on all ports (default value: 1500)\n" " outgoing packets with bigger size will be fragmented\n" " incoming packets with bigger size will be discarded\n" + " --" CMD_LINE_OPT_FRAG_TTL " FRAG_TTL_NS" + ": fragments lifetime in nanoseconds, default\n" + " and maximum value is 10.000.000.000 ns (10 s)\n" + " --event-vector enables event vectorization\n" + " --vector-size Max vector size (default value: 16)\n" + " --vector-tmo Max vector timeout in nanoseconds" + " (default value: 102400)\n" + " --" CMD_LINE_OPT_PER_PORT_POOL " Enable per port mbuf pool\n" + " --" CMD_LINE_OPT_VECTOR_POOL_SZ " Vector pool size\n" + " (default value is based on mbuf count)\n" "\n", prgname); } @@ -1330,6 +974,8 @@ parse_portmask(const char *portmask) char *end = NULL; unsigned long pm; + errno = 0; + /* parse hexadecimal string */ pm = strtoul(portmask, &end, 16); if ((portmask[0] == '\0') || (end == NULL) || (*end != '\0')) @@ -1341,14 +987,15 @@ parse_portmask(const char *portmask) return pm; } -static int32_t +static int64_t parse_decimal(const char *str) { char *end = NULL; - unsigned long num; + uint64_t num; - num = strtoul(str, &end, 10); - if ((str[0] == '\0') || (end == NULL) || (*end != '\0')) + num = strtoull(str, &end, 10); + if ((str[0] == '\0') || (end == NULL) || (*end != '\0') + || num > INT64_MAX) return -1; return num; @@ -1416,26 +1063,63 @@ print_app_sa_prm(const struct app_sa_prm *prm) printf("librte_ipsec usage: %s\n", (prm->enable == 0) ? "disabled" : "enabled"); - if (prm->enable == 0) - return; - printf("replay window size: %u\n", prm->window_size); printf("ESN: %s\n", (prm->enable_esn == 0) ? "disabled" : "enabled"); printf("SA flags: %#" PRIx64 "\n", prm->flags); + printf("Frag TTL: %" PRIu64 " ns\n", frag_ttl_ns); +} + +static int +parse_transfer_mode(struct eh_conf *conf, const char *optarg) +{ + if (!strcmp(CMD_LINE_ARG_POLL, optarg)) + conf->mode = EH_PKT_TRANSFER_MODE_POLL; + else if (!strcmp(CMD_LINE_ARG_EVENT, optarg)) + conf->mode = EH_PKT_TRANSFER_MODE_EVENT; + else { + printf("Unsupported packet transfer mode\n"); + return -EINVAL; + } + + return 0; +} + +static int +parse_schedule_type(struct eh_conf *conf, const char *optarg) +{ + struct eventmode_conf *em_conf = NULL; + + /* Get eventmode conf */ + em_conf = conf->mode_params; + + if (!strcmp(CMD_LINE_ARG_ORDERED, optarg)) + em_conf->ext_params.sched_type = RTE_SCHED_TYPE_ORDERED; + else if (!strcmp(CMD_LINE_ARG_ATOMIC, optarg)) + em_conf->ext_params.sched_type = RTE_SCHED_TYPE_ATOMIC; + else if (!strcmp(CMD_LINE_ARG_PARALLEL, optarg)) + em_conf->ext_params.sched_type = RTE_SCHED_TYPE_PARALLEL; + else { + printf("Unsupported queue schedule type\n"); + return -EINVAL; + } + + return 0; } static int32_t -parse_args(int32_t argc, char **argv) +parse_args(int32_t argc, char **argv, struct eh_conf *eh_conf) { - int32_t opt, ret; + int opt; + int64_t ret; char **argvopt; int32_t option_index; char *prgname = argv[0]; int32_t f_present = 0; + struct eventmode_conf *em_conf = NULL; argvopt = argv; - while ((opt = getopt_long(argc, argvopt, "aelp:Pu:f:j:w:", + while ((opt = getopt_long(argc, argvopt, "aelp:Pu:f:j:w:c:t:s:", lgopts, &option_index)) != EOF) { switch (opt) { @@ -1469,6 +1153,19 @@ parse_args(int32_t argc, char **argv) cfgfile = optarg; f_present = 1; break; + + case 's': + ret = parse_decimal(optarg); + if (ret < 0) { + printf("Invalid number of buffers in a pool: " + "%s\n", optarg); + print_usage(prgname); + return -1; + } + + nb_bufs_in_pool = ret; + break; + case 'j': ret = parse_decimal(optarg); if (ret < RTE_MBUF_DEFAULT_BUF_SIZE || @@ -1485,17 +1182,33 @@ parse_args(int32_t argc, char **argv) app_sa_prm.enable = 1; break; case 'w': - app_sa_prm.enable = 1; app_sa_prm.window_size = parse_decimal(optarg); break; case 'e': - app_sa_prm.enable = 1; app_sa_prm.enable_esn = 1; break; case 'a': app_sa_prm.enable = 1; app_sa_prm.flags |= RTE_IPSEC_SAFLAG_SQN_ATOM; break; + case 'c': + ret = parse_decimal(optarg); + if (ret < 0) { + printf("Invalid SA cache size: %s\n", optarg); + print_usage(prgname); + return -1; + } + app_sa_prm.cache_sz = ret; + break; + case 't': + ret = parse_decimal(optarg); + if (ret < 0) { + printf("Invalid interval value: %s\n", optarg); + print_usage(prgname); + return -1; + } + stats_interval = ret; + break; case CMD_LINE_OPT_CONFIG_NUM: ret = parse_config(optarg); if (ret) { @@ -1506,7 +1219,7 @@ parse_args(int32_t argc, char **argv) break; case CMD_LINE_OPT_SINGLE_SA_NUM: ret = parse_decimal(optarg); - if (ret == -1) { + if (ret == -1 || ret > UINT32_MAX) { printf("Invalid argument[sa_idx]\n"); print_usage(prgname); return -1; @@ -1515,6 +1228,7 @@ parse_args(int32_t argc, char **argv) /* else */ single_sa = 1; single_sa_idx = ret; + eh_conf->ipsec_mode = EH_IPSEC_MODE_TYPE_DRIVER; printf("Configured with single SA index %u\n", single_sa_idx); break; @@ -1529,6 +1243,25 @@ parse_args(int32_t argc, char **argv) /* else */ enabled_cryptodev_mask = ret; break; + + case CMD_LINE_OPT_TRANSFER_MODE_NUM: + ret = parse_transfer_mode(eh_conf, optarg); + if (ret < 0) { + printf("Invalid packet transfer mode\n"); + print_usage(prgname); + return -1; + } + break; + + case CMD_LINE_OPT_SCHEDULE_TYPE_NUM: + ret = parse_schedule_type(eh_conf, optarg); + if (ret < 0) { + printf("Invalid queue schedule type\n"); + print_usage(prgname); + return -1; + } + break; + case CMD_LINE_OPT_RX_OFFLOAD_NUM: ret = parse_mask(optarg, &dev_rx_offload); if (ret != 0) { @@ -1549,7 +1282,7 @@ parse_args(int32_t argc, char **argv) break; case CMD_LINE_OPT_REASSEMBLE_NUM: ret = parse_decimal(optarg); - if (ret < 0) { + if (ret < 0 || ret > UINT32_MAX) { printf("Invalid argument for \'%s\': %s\n", CMD_LINE_OPT_REASSEMBLE, optarg); print_usage(prgname); @@ -1567,6 +1300,47 @@ parse_args(int32_t argc, char **argv) } mtu_size = ret; break; + case CMD_LINE_OPT_FRAG_TTL_NUM: + ret = parse_decimal(optarg); + if (ret < 0 || ret > MAX_FRAG_TTL_NS) { + printf("Invalid argument for \'%s\': %s\n", + CMD_LINE_OPT_MTU, optarg); + print_usage(prgname); + return -1; + } + frag_ttl_ns = ret; + break; + case CMD_LINE_OPT_EVENT_VECTOR_NUM: + em_conf = eh_conf->mode_params; + em_conf->ext_params.event_vector = 1; + break; + case CMD_LINE_OPT_VECTOR_SIZE_NUM: + ret = parse_decimal(optarg); + + if (ret > MAX_PKT_BURST) { + printf("Invalid argument for \'%s\': %s\n", + CMD_LINE_OPT_VECTOR_SIZE, optarg); + print_usage(prgname); + return -1; + } + em_conf = eh_conf->mode_params; + em_conf->ext_params.vector_size = ret; + break; + case CMD_LINE_OPT_VECTOR_TIMEOUT_NUM: + ret = parse_decimal(optarg); + + em_conf = eh_conf->mode_params; + em_conf->vector_tmo_ns = ret; + break; + case CMD_LINE_OPT_VECTOR_POOL_SZ_NUM: + ret = parse_decimal(optarg); + + em_conf = eh_conf->mode_params; + em_conf->vector_pool_sz = ret; + break; + case CMD_LINE_OPT_PER_PORT_POOL_NUM: + per_port_pool = 1; + break; default: print_usage(prgname); return -1; @@ -1629,6 +1403,7 @@ check_all_ports_link_status(uint32_t port_mask) uint8_t count, all_ports_up, print_flag = 0; struct rte_eth_link link; int ret; + char link_status_text[RTE_ETH_LINK_MAX_STR_LEN]; printf("\nChecking link status"); fflush(stdout); @@ -1648,18 +1423,14 @@ check_all_ports_link_status(uint32_t port_mask) } /* print link status if flag set */ if (print_flag == 1) { - if (link.link_status) - printf( - "Port%d Link Up - speed %u Mbps -%s\n", - portid, link.link_speed, - (link.link_duplex == ETH_LINK_FULL_DUPLEX) ? - ("full-duplex") : ("half-duplex\n")); - else - printf("Port %d Link Down\n", portid); + rte_eth_link_to_str(link_status_text, + sizeof(link_status_text), &link); + printf("Port %d %s\n", portid, + link_status_text); continue; } /* clear all_ports_up flag if any link down */ - if (link.link_status == ETH_LINK_DOWN) { + if (link.link_status == RTE_ETH_LINK_DOWN) { all_ports_up = 0; break; } @@ -1726,7 +1497,7 @@ add_mapping(struct rte_hash *map, const char *str, uint16_t cdev_id, ret = rte_hash_add_key_data(map, &key, (void *)i); if (ret < 0) { - printf("Faled to insert cdev mapping for (lcore %u, " + printf("Failed to insert cdev mapping for (lcore %u, " "cdev %u, qp %u), errno %d\n", key.lcore_id, ipsec_ctx->tbl[i].id, ipsec_ctx->tbl[i].qp, ret); @@ -1759,7 +1530,7 @@ add_cdev_mapping(struct rte_cryptodev_info *dev_info, uint16_t cdev_id, str = "Inbound"; } - /* Required cryptodevs with operation chainning */ + /* Required cryptodevs with operation chaining */ if (!(dev_info->feature_flags & RTE_CRYPTODEV_FF_SYM_OPERATION_CHAINING)) return ret; @@ -1804,12 +1575,12 @@ check_cryptodev_mask(uint8_t cdev_id) return -1; } -static int32_t -cryptodevs_init(void) +static uint16_t +cryptodevs_init(uint16_t req_queue_num) { struct rte_cryptodev_config dev_conf; struct rte_cryptodev_qp_conf qp_conf; - uint16_t idx, max_nb_qps, qp, i; + uint16_t idx, max_nb_qps, qp, total_nb_qps, i; int16_t cdev_id; struct rte_hash_parameters params = { 0 }; @@ -1837,6 +1608,7 @@ cryptodevs_init(void) printf("lcore/cryptodev/qp mappings:\n"); idx = 0; + total_nb_qps = 0; for (cdev_id = 0; cdev_id < rte_cryptodev_count(); cdev_id++) { struct rte_cryptodev_info cdev_info; @@ -1867,18 +1639,21 @@ cryptodevs_init(void) i++; } + qp = RTE_MIN(max_nb_qps, RTE_MAX(req_queue_num, qp)); if (qp == 0) continue; + total_nb_qps += qp; dev_conf.socket_id = rte_cryptodev_socket_id(cdev_id); dev_conf.nb_queue_pairs = qp; dev_conf.ff_disable = RTE_CRYPTODEV_FF_ASYMMETRIC_CRYPTO; uint32_t dev_max_sess = cdev_info.sym.max_nb_sessions; - if (dev_max_sess != 0 && dev_max_sess < CDEV_MP_NB_OBJS) + if (dev_max_sess != 0 && + dev_max_sess < get_nb_crypto_sessions()) rte_exit(EXIT_FAILURE, "Device does not support at least %u " - "sessions", CDEV_MP_NB_OBJS); + "sessions", get_nb_crypto_sessions()); if (rte_cryptodev_configure(cdev_id, &dev_conf)) rte_panic("Failed to initialize cryptodev %u\n", @@ -1902,13 +1677,153 @@ cryptodevs_init(void) printf("\n"); + return total_nb_qps; +} + +static int +check_ptype(int portid) +{ + int l3_ipv4 = 0, l3_ipv6 = 0, l4_udp = 0, tunnel_esp = 0; + int i, nb_ptypes; + uint32_t mask; + + mask = (RTE_PTYPE_L3_MASK | RTE_PTYPE_L4_MASK | + RTE_PTYPE_TUNNEL_MASK); + + nb_ptypes = rte_eth_dev_get_supported_ptypes(portid, mask, NULL, 0); + if (nb_ptypes <= 0) + return 0; + + uint32_t ptypes[nb_ptypes]; + + nb_ptypes = rte_eth_dev_get_supported_ptypes(portid, mask, ptypes, nb_ptypes); + for (i = 0; i < nb_ptypes; ++i) { + if (RTE_ETH_IS_IPV4_HDR(ptypes[i])) + l3_ipv4 = 1; + if (RTE_ETH_IS_IPV6_HDR(ptypes[i])) + l3_ipv6 = 1; + if ((ptypes[i] & RTE_PTYPE_TUNNEL_MASK) == RTE_PTYPE_TUNNEL_ESP) + tunnel_esp = 1; + if ((ptypes[i] & RTE_PTYPE_L4_MASK) == RTE_PTYPE_L4_UDP) + l4_udp = 1; + } + + if (l3_ipv4 == 0) + printf("port %d cannot parse RTE_PTYPE_L3_IPV4\n", portid); + + if (l3_ipv6 == 0) + printf("port %d cannot parse RTE_PTYPE_L3_IPV6\n", portid); + + if (l4_udp == 0) + printf("port %d cannot parse RTE_PTYPE_L4_UDP\n", portid); + + if (tunnel_esp == 0) + printf("port %d cannot parse RTE_PTYPE_TUNNEL_ESP\n", portid); + + if (l3_ipv4 && l3_ipv6 && l4_udp && tunnel_esp) + return 1; + return 0; + +} + +static inline void +parse_ptype(struct rte_mbuf *m) +{ + uint32_t packet_type = RTE_PTYPE_UNKNOWN; + const struct rte_ipv4_hdr *iph4; + const struct rte_ipv6_hdr *iph6; + const struct rte_ether_hdr *eth; + const struct rte_udp_hdr *udp; + uint16_t nat_port, ether_type; + int next_proto = 0; + size_t ext_len = 0; + const uint8_t *p; + uint32_t l3len; + + eth = rte_pktmbuf_mtod(m, struct rte_ether_hdr *); + ether_type = eth->ether_type; + + if (ether_type == rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4)) { + iph4 = (const struct rte_ipv4_hdr *)(eth + 1); + l3len = ((iph4->version_ihl & RTE_IPV4_HDR_IHL_MASK) * + RTE_IPV4_IHL_MULTIPLIER); + + if (l3len == sizeof(struct rte_ipv4_hdr)) + packet_type |= RTE_PTYPE_L3_IPV4; + else + packet_type |= RTE_PTYPE_L3_IPV4_EXT_UNKNOWN; + + next_proto = iph4->next_proto_id; + p = (const uint8_t *)iph4; + } else if (ether_type == rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6)) { + iph6 = (const struct rte_ipv6_hdr *)(eth + 1); + l3len = sizeof(struct ip6_hdr); + + /* determine l3 header size up to ESP extension */ + next_proto = iph6->proto; + p = (const uint8_t *)iph6; + while (next_proto != IPPROTO_ESP && l3len < m->data_len && + (next_proto = rte_ipv6_get_next_ext(p + l3len, + next_proto, &ext_len)) >= 0) + l3len += ext_len; + + /* Skip IPv6 header exceeds first segment length */ + if (unlikely(l3len + RTE_ETHER_HDR_LEN > m->data_len)) + goto exit; + + if (l3len == sizeof(struct ip6_hdr)) + packet_type |= RTE_PTYPE_L3_IPV6; + else + packet_type |= RTE_PTYPE_L3_IPV6_EXT; + } + + switch (next_proto) { + case IPPROTO_ESP: + packet_type |= RTE_PTYPE_TUNNEL_ESP; + break; + case IPPROTO_UDP: + if (app_sa_prm.udp_encap == 1) { + udp = (const struct rte_udp_hdr *)(p + l3len); + nat_port = rte_cpu_to_be_16(IPSEC_NAT_T_PORT); + if (udp->src_port == nat_port || + udp->dst_port == nat_port) + packet_type |= + MBUF_PTYPE_TUNNEL_ESP_IN_UDP; + } + break; + default: + break; + } +exit: + m->packet_type = packet_type; +} + +static uint16_t +parse_ptype_cb(uint16_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) +{ + uint32_t i; + + if (unlikely(nb_pkts == 0)) + return nb_pkts; + + rte_prefetch0(rte_pktmbuf_mtod(pkts[0], struct ether_hdr *)); + for (i = 0; i < (unsigned int) (nb_pkts - 1); ++i) { + rte_prefetch0(rte_pktmbuf_mtod(pkts[i+1], + struct ether_hdr *)); + parse_ptype(pkts[i]); + } + parse_ptype(pkts[i]); + + return nb_pkts; } static void port_init(uint16_t portid, uint64_t req_rx_offloads, uint64_t req_tx_offloads) { - uint32_t frame_size; struct rte_eth_dev_info dev_info; struct rte_eth_txconf *txconf; uint16_t nb_tx_queue, nb_rx_queue; @@ -1917,6 +1832,7 @@ port_init(uint16_t portid, uint64_t req_rx_offloads, uint64_t req_tx_offloads) struct lcore_conf *qconf; struct rte_ether_addr ethaddr; struct rte_eth_conf local_port_conf = port_conf; + int ptype_supported; ret = rte_eth_dev_info_get(portid, &dev_info); if (ret != 0) @@ -1924,7 +1840,7 @@ port_init(uint16_t portid, uint64_t req_rx_offloads, uint64_t req_tx_offloads) "Error during getting device (port %u) info: %s\n", portid, strerror(-ret)); - /* limit allowed HW offloafs, as user requested */ + /* limit allowed HW offloads, as user requested */ dev_info.rx_offload_capa &= dev_rx_offload; dev_info.tx_offload_capa &= dev_tx_offload; @@ -1956,14 +1872,11 @@ port_init(uint16_t portid, uint64_t req_rx_offloads, uint64_t req_tx_offloads) printf("Creating queues: nb_rx_queue=%d nb_tx_queue=%u...\n", nb_rx_queue, nb_tx_queue); - frame_size = MTU_TO_FRAMELEN(mtu_size); - if (frame_size > local_port_conf.rxmode.max_rx_pkt_len) - local_port_conf.rxmode.offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME; - local_port_conf.rxmode.max_rx_pkt_len = frame_size; + local_port_conf.rxmode.mtu = mtu_size; if (multi_seg_required()) { - local_port_conf.rxmode.offloads |= DEV_RX_OFFLOAD_SCATTER; - local_port_conf.txmode.offloads |= DEV_TX_OFFLOAD_MULTI_SEGS; + local_port_conf.rxmode.offloads |= RTE_ETH_RX_OFFLOAD_SCATTER; + local_port_conf.txmode.offloads |= RTE_ETH_TX_OFFLOAD_MULTI_SEGS; } local_port_conf.rxmode.offloads |= req_rx_offloads; @@ -1974,7 +1887,7 @@ port_init(uint16_t portid, uint64_t req_rx_offloads, uint64_t req_tx_offloads) local_port_conf.rxmode.offloads) rte_exit(EXIT_FAILURE, "Error: port %u required RX offloads: 0x%" PRIx64 - ", avaialbe RX offloads: 0x%" PRIx64 "\n", + ", available RX offloads: 0x%" PRIx64 "\n", portid, local_port_conf.rxmode.offloads, dev_info.rx_offload_capa); @@ -1982,18 +1895,15 @@ port_init(uint16_t portid, uint64_t req_rx_offloads, uint64_t req_tx_offloads) local_port_conf.txmode.offloads) rte_exit(EXIT_FAILURE, "Error: port %u required TX offloads: 0x%" PRIx64 - ", avaialbe TX offloads: 0x%" PRIx64 "\n", + ", available TX offloads: 0x%" PRIx64 "\n", portid, local_port_conf.txmode.offloads, dev_info.tx_offload_capa); - if (dev_info.tx_offload_capa & DEV_TX_OFFLOAD_MBUF_FAST_FREE) + if (dev_info.tx_offload_capa & RTE_ETH_TX_OFFLOAD_MBUF_FAST_FREE) local_port_conf.txmode.offloads |= - DEV_TX_OFFLOAD_MBUF_FAST_FREE; + RTE_ETH_TX_OFFLOAD_MBUF_FAST_FREE; - if (dev_info.tx_offload_capa & DEV_TX_OFFLOAD_IPV4_CKSUM) - local_port_conf.txmode.offloads |= DEV_TX_OFFLOAD_IPV4_CKSUM; - - printf("port %u configurng rx_offloads=0x%" PRIx64 + printf("port %u configuring rx_offloads=0x%" PRIx64 ", tx_offloads=0x%" PRIx64 "\n", portid, local_port_conf.rxmode.offloads, local_port_conf.txmode.offloads); @@ -2020,6 +1930,11 @@ port_init(uint16_t portid, uint64_t req_rx_offloads, uint64_t req_tx_offloads) rte_exit(EXIT_FAILURE, "Cannot adjust number of descriptors: " "err=%d, port=%d\n", ret, portid); + /* Check if required ptypes are supported */ + ptype_supported = check_ptype(portid); + if (!ptype_supported) + printf("Port %d: softly parse packet type info\n", portid); + /* init one TX queue per lcore */ tx_queueid = 0; for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) { @@ -2047,16 +1962,17 @@ port_init(uint16_t portid, uint64_t req_rx_offloads, uint64_t req_tx_offloads) qconf->tx_queue_id[portid] = tx_queueid; /* Pre-populate pkt offloads based on capabilities */ - qconf->outbound.ipv4_offloads = PKT_TX_IPV4; - qconf->outbound.ipv6_offloads = PKT_TX_IPV6; - if (local_port_conf.txmode.offloads & DEV_TX_OFFLOAD_IPV4_CKSUM) - qconf->outbound.ipv4_offloads |= PKT_TX_IP_CKSUM; + qconf->outbound.ipv4_offloads = RTE_MBUF_F_TX_IPV4; + qconf->outbound.ipv6_offloads = RTE_MBUF_F_TX_IPV6; + if (local_port_conf.txmode.offloads & RTE_ETH_TX_OFFLOAD_IPV4_CKSUM) + qconf->outbound.ipv4_offloads |= RTE_MBUF_F_TX_IP_CKSUM; tx_queueid++; /* init RX queues */ for (queue = 0; queue < qconf->nb_rx_queue; ++queue) { struct rte_eth_rxconf rxq_conf; + struct rte_mempool *pool; if (portid != qconf->rx_queue_list[queue].port_id) continue; @@ -2068,13 +1984,28 @@ port_init(uint16_t portid, uint64_t req_rx_offloads, uint64_t req_tx_offloads) rxq_conf = dev_info.default_rxconf; rxq_conf.offloads = local_port_conf.rxmode.offloads; + + if (per_port_pool) + pool = socket_ctx[socket_id].mbuf_pool[portid]; + else + pool = socket_ctx[socket_id].mbuf_pool[0]; + ret = rte_eth_rx_queue_setup(portid, rx_queueid, - nb_rxd, socket_id, &rxq_conf, - socket_ctx[socket_id].mbuf_pool); + nb_rxd, socket_id, &rxq_conf, pool); if (ret < 0) rte_exit(EXIT_FAILURE, "rte_eth_rx_queue_setup: err=%d, " "port=%d\n", ret, portid); + + /* Register Rx callback if ptypes are not supported */ + if (!ptype_supported && + !rte_eth_add_rx_callback(portid, queue, + parse_ptype_cb, NULL)) { + printf("Failed to add rx callback: port=%d, " + "queue=%d\n", portid, queue); + } + + } } printf("\n"); @@ -2130,12 +2061,16 @@ session_pool_init(struct socket_ctx *ctx, int32_t socket_id, size_t sess_sz) { char mp_name[RTE_MEMPOOL_NAMESIZE]; struct rte_mempool *sess_mp; + uint32_t nb_sess; snprintf(mp_name, RTE_MEMPOOL_NAMESIZE, "sess_mp_%u", socket_id); + nb_sess = (get_nb_crypto_sessions() + CDEV_MP_CACHE_SZ * + rte_lcore_count()); + nb_sess = RTE_MAX(nb_sess, CDEV_MP_CACHE_SZ * + CDEV_MP_CACHE_MULTIPLIER); sess_mp = rte_cryptodev_sym_session_pool_create( - mp_name, CDEV_MP_NB_OBJS, - sess_sz, CDEV_MP_CACHE_SZ, 0, + mp_name, nb_sess, sess_sz, CDEV_MP_CACHE_SZ, 0, socket_id); ctx->session_pool = sess_mp; @@ -2152,11 +2087,16 @@ session_priv_pool_init(struct socket_ctx *ctx, int32_t socket_id, { char mp_name[RTE_MEMPOOL_NAMESIZE]; struct rte_mempool *sess_mp; + uint32_t nb_sess; snprintf(mp_name, RTE_MEMPOOL_NAMESIZE, "sess_mp_priv_%u", socket_id); + nb_sess = (get_nb_crypto_sessions() + CDEV_MP_CACHE_SZ * + rte_lcore_count()); + nb_sess = RTE_MAX(nb_sess, CDEV_MP_CACHE_SZ * + CDEV_MP_CACHE_MULTIPLIER); sess_mp = rte_mempool_create(mp_name, - CDEV_MP_NB_OBJS, + nb_sess, sess_sz, CDEV_MP_CACHE_SZ, 0, NULL, NULL, NULL, @@ -2174,28 +2114,37 @@ session_priv_pool_init(struct socket_ctx *ctx, int32_t socket_id, } static void -pool_init(struct socket_ctx *ctx, int32_t socket_id, uint32_t nb_mbuf) +pool_init(struct socket_ctx *ctx, int32_t socket_id, int portid, + uint32_t nb_mbuf) { char s[64]; int32_t ms; - snprintf(s, sizeof(s), "mbuf_pool_%d", socket_id); - ctx->mbuf_pool = rte_pktmbuf_pool_create(s, nb_mbuf, - MEMPOOL_CACHE_SIZE, ipsec_metadata_size(), - frame_buf_size, socket_id); + + /* mbuf_pool is initialised by the pool_init() function*/ + if (socket_ctx[socket_id].mbuf_pool[portid]) + return; + + snprintf(s, sizeof(s), "mbuf_pool_%d_%d", socket_id, portid); + ctx->mbuf_pool[portid] = rte_pktmbuf_pool_create(s, nb_mbuf, + MEMPOOL_CACHE_SIZE, + ipsec_metadata_size(), + frame_buf_size, + socket_id); /* * if multi-segment support is enabled, then create a pool - * for indirect mbufs. + * for indirect mbufs. This is not per-port but global. */ ms = multi_seg_required(); - if (ms != 0) { + if (ms != 0 && !ctx->mbuf_pool_indir) { snprintf(s, sizeof(s), "mbuf_pool_indir_%d", socket_id); ctx->mbuf_pool_indir = rte_pktmbuf_pool_create(s, nb_mbuf, MEMPOOL_CACHE_SIZE, 0, 0, socket_id); } - if (ctx->mbuf_pool == NULL || (ms != 0 && ctx->mbuf_pool_indir == NULL)) + if (ctx->mbuf_pool[portid] == NULL || + (ms != 0 && ctx->mbuf_pool_indir == NULL)) rte_exit(EXIT_FAILURE, "Cannot init mbuf pool on socket %d\n", socket_id); else @@ -2257,6 +2206,17 @@ inline_ipsec_event_callback(uint16_t port_id, enum rte_eth_event_type type, return -1; } +static int +ethdev_reset_event_callback(uint16_t port_id, + enum rte_eth_event_type type, + void *param __rte_unused, void *ret_param __rte_unused) +{ + printf("Reset Event on port id %d type %d\n", port_id, type); + printf("Force quit application"); + force_quit = true; + return 0; +} + static uint16_t rx_callback(__rte_unused uint16_t port, __rte_unused uint16_t queue, struct rte_mbuf *pkt[], uint16_t nb_pkts, @@ -2303,7 +2263,7 @@ rx_callback(__rte_unused uint16_t port, __rte_unused uint16_t queue, rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6)) { struct rte_ipv6_hdr *iph; - struct ipv6_extension_fragment *fh; + struct rte_ipv6_fragment_ext *fh; iph = (struct rte_ipv6_hdr *)(eth + 1); fh = rte_ipv6_frag_get_ipv6_fragment_header(iph); @@ -2344,8 +2304,8 @@ reassemble_lcore_init(struct lcore_conf *lc, uint32_t cid) /* create fragment table */ sid = rte_lcore_to_socket_id(cid); - frag_cycles = (rte_get_tsc_hz() + MS_PER_S - 1) / - MS_PER_S * FRAG_TTL_MS; + frag_cycles = (rte_get_tsc_hz() + NS_PER_S - 1) / + NS_PER_S * frag_ttl_ns; lc->frag.tbl = rte_ip_frag_table_create(frag_tbl_sz, FRAG_TBL_BUCKET_ENTRIES, frag_tbl_sz, frag_cycles, sid); @@ -2391,17 +2351,528 @@ reassemble_init(void) return rc; } +static void +create_default_ipsec_flow(uint16_t port_id, uint64_t rx_offloads) +{ + struct rte_flow_action action[2]; + struct rte_flow_item pattern[2]; + struct rte_flow_attr attr = {0}; + struct rte_flow_error err; + struct rte_flow *flow; + int ret; + + if (!(rx_offloads & RTE_ETH_RX_OFFLOAD_SECURITY)) + return; + + /* Add the default rte_flow to enable SECURITY for all ESP packets */ + + pattern[0].type = RTE_FLOW_ITEM_TYPE_ESP; + pattern[0].spec = NULL; + pattern[0].mask = NULL; + pattern[0].last = NULL; + pattern[1].type = RTE_FLOW_ITEM_TYPE_END; + + action[0].type = RTE_FLOW_ACTION_TYPE_SECURITY; + action[0].conf = NULL; + action[1].type = RTE_FLOW_ACTION_TYPE_END; + action[1].conf = NULL; + + attr.ingress = 1; + + ret = rte_flow_validate(port_id, &attr, pattern, action, &err); + if (ret) + return; + + flow = rte_flow_create(port_id, &attr, pattern, action, &err); + if (flow == NULL) + return; + + flow_info_tbl[port_id].rx_def_flow = flow; + RTE_LOG(INFO, IPSEC, + "Created default flow enabling SECURITY for all ESP traffic on port %d\n", + port_id); +} + +static void +signal_handler(int signum) +{ + if (signum == SIGINT || signum == SIGTERM) { + printf("\n\nSignal %d received, preparing to exit...\n", + signum); + force_quit = true; + } +} + +static void +ev_mode_sess_verify(struct ipsec_sa *sa, int nb_sa) +{ + struct rte_ipsec_session *ips; + int32_t i; + + if (!sa || !nb_sa) + return; + + for (i = 0; i < nb_sa; i++) { + ips = ipsec_get_primary_session(&sa[i]); + if (ips->type != RTE_SECURITY_ACTION_TYPE_INLINE_PROTOCOL) + rte_exit(EXIT_FAILURE, "Event mode supports only " + "inline protocol sessions\n"); + } + +} + +static int32_t +check_event_mode_params(struct eh_conf *eh_conf) +{ + struct eventmode_conf *em_conf = NULL; + struct lcore_params *params; + uint16_t portid; + + if (!eh_conf || !eh_conf->mode_params) + return -EINVAL; + + /* Get eventmode conf */ + em_conf = eh_conf->mode_params; + + if (eh_conf->mode == EH_PKT_TRANSFER_MODE_POLL && + em_conf->ext_params.sched_type != SCHED_TYPE_NOT_SET) { + printf("error: option --event-schedule-type applies only to " + "event mode\n"); + return -EINVAL; + } + + if (eh_conf->mode != EH_PKT_TRANSFER_MODE_EVENT) + return 0; + + /* Set schedule type to ORDERED if it wasn't explicitly set by user */ + if (em_conf->ext_params.sched_type == SCHED_TYPE_NOT_SET) + em_conf->ext_params.sched_type = RTE_SCHED_TYPE_ORDERED; + + /* + * Event mode currently supports only inline protocol sessions. + * If there are other types of sessions configured then exit with + * error. + */ + ev_mode_sess_verify(sa_in, nb_sa_in); + ev_mode_sess_verify(sa_out, nb_sa_out); + + + /* Option --config does not apply to event mode */ + if (nb_lcore_params > 0) { + printf("error: option --config applies only to poll mode\n"); + return -EINVAL; + } + + /* + * In order to use the same port_init routine for both poll and event + * modes initialize lcore_params with one queue for each eth port + */ + lcore_params = lcore_params_array; + RTE_ETH_FOREACH_DEV(portid) { + if ((enabled_port_mask & (1 << portid)) == 0) + continue; + + params = &lcore_params[nb_lcore_params++]; + params->port_id = portid; + params->queue_id = 0; + params->lcore_id = rte_get_next_lcore(0, 0, 1); + } + + return 0; +} + +static void +inline_sessions_free(struct sa_ctx *sa_ctx) +{ + struct rte_ipsec_session *ips; + struct ipsec_sa *sa; + int32_t ret; + uint32_t i; + + if (!sa_ctx) + return; + + for (i = 0; i < sa_ctx->nb_sa; i++) { + + sa = &sa_ctx->sa[i]; + if (!sa->spi) + continue; + + ips = ipsec_get_primary_session(sa); + if (ips->type != RTE_SECURITY_ACTION_TYPE_INLINE_PROTOCOL && + ips->type != RTE_SECURITY_ACTION_TYPE_INLINE_CRYPTO) + continue; + + if (!rte_eth_dev_is_valid_port(sa->portid)) + continue; + + ret = rte_security_session_destroy( + rte_eth_dev_get_sec_ctx(sa->portid), + ips->security.ses); + if (ret) + RTE_LOG(ERR, IPSEC, "Failed to destroy security " + "session type %d, spi %d\n", + ips->type, sa->spi); + } +} + +static uint32_t +calculate_nb_mbufs(uint16_t nb_ports, uint16_t nb_crypto_qp, uint32_t nb_rxq, + uint32_t nb_txq) +{ + return RTE_MAX((nb_rxq * nb_rxd + + nb_ports * nb_lcores * MAX_PKT_BURST + + nb_ports * nb_txq * nb_txd + + nb_lcores * MEMPOOL_CACHE_SIZE + + nb_crypto_qp * CDEV_QUEUE_DESC + + nb_lcores * frag_tbl_sz * + FRAG_TBL_BUCKET_ENTRIES), + 8192U); +} + + +static int +handle_telemetry_cmd_ipsec_secgw_stats(const char *cmd __rte_unused, + const char *params, struct rte_tel_data *data) +{ + uint64_t total_pkts_dropped = 0, total_pkts_tx = 0, total_pkts_rx = 0; + unsigned int coreid; + + rte_tel_data_start_dict(data); + + if (params) { + coreid = (uint32_t)atoi(params); + if (rte_lcore_is_enabled(coreid) == 0) + return -EINVAL; + + total_pkts_dropped = core_statistics[coreid].dropped; + total_pkts_tx = core_statistics[coreid].tx; + total_pkts_rx = core_statistics[coreid].rx; + + } else { + for (coreid = 0; coreid < RTE_MAX_LCORE; coreid++) { + + /* skip disabled cores */ + if (rte_lcore_is_enabled(coreid) == 0) + continue; + + total_pkts_dropped += core_statistics[coreid].dropped; + total_pkts_tx += core_statistics[coreid].tx; + total_pkts_rx += core_statistics[coreid].rx; + } + } + + /* add telemetry key/values pairs */ + rte_tel_data_add_dict_u64(data, "packets received", + total_pkts_rx); + + rte_tel_data_add_dict_u64(data, "packets transmitted", + total_pkts_tx); + + rte_tel_data_add_dict_u64(data, "packets dropped", + total_pkts_dropped); + + + return 0; +} + +static void +update_lcore_statistics(struct ipsec_core_statistics *total, uint32_t coreid) +{ + struct ipsec_core_statistics *lcore_stats; + + /* skip disabled cores */ + if (rte_lcore_is_enabled(coreid) == 0) + return; + + lcore_stats = &core_statistics[coreid]; + + total->rx = lcore_stats->rx; + total->dropped = lcore_stats->dropped; + total->tx = lcore_stats->tx; + + /* outbound stats */ + total->outbound.spd6.protect += lcore_stats->outbound.spd6.protect; + total->outbound.spd6.bypass += lcore_stats->outbound.spd6.bypass; + total->outbound.spd6.discard += lcore_stats->outbound.spd6.discard; + + total->outbound.spd4.protect += lcore_stats->outbound.spd4.protect; + total->outbound.spd4.bypass += lcore_stats->outbound.spd4.bypass; + total->outbound.spd4.discard += lcore_stats->outbound.spd4.discard; + + total->outbound.sad.miss += lcore_stats->outbound.sad.miss; + + /* inbound stats */ + total->inbound.spd6.protect += lcore_stats->inbound.spd6.protect; + total->inbound.spd6.bypass += lcore_stats->inbound.spd6.bypass; + total->inbound.spd6.discard += lcore_stats->inbound.spd6.discard; + + total->inbound.spd4.protect += lcore_stats->inbound.spd4.protect; + total->inbound.spd4.bypass += lcore_stats->inbound.spd4.bypass; + total->inbound.spd4.discard += lcore_stats->inbound.spd4.discard; + + total->inbound.sad.miss += lcore_stats->inbound.sad.miss; + + + /* routing stats */ + total->lpm4.miss += lcore_stats->lpm4.miss; + total->lpm6.miss += lcore_stats->lpm6.miss; +} + +static void +update_statistics(struct ipsec_core_statistics *total, uint32_t coreid) +{ + memset(total, 0, sizeof(*total)); + + if (coreid != UINT32_MAX) { + update_lcore_statistics(total, coreid); + } else { + for (coreid = 0; coreid < RTE_MAX_LCORE; coreid++) + update_lcore_statistics(total, coreid); + } +} + +static int +handle_telemetry_cmd_ipsec_secgw_stats_outbound(const char *cmd __rte_unused, + const char *params, struct rte_tel_data *data) +{ + struct ipsec_core_statistics total_stats; + + struct rte_tel_data *spd4_data = rte_tel_data_alloc(); + struct rte_tel_data *spd6_data = rte_tel_data_alloc(); + struct rte_tel_data *sad_data = rte_tel_data_alloc(); + unsigned int coreid = UINT32_MAX; + int rc = 0; + + /* verify allocated telemetry data structures */ + if (!spd4_data || !spd6_data || !sad_data) { + rc = -ENOMEM; + goto exit; + } + + /* initialize telemetry data structs as dicts */ + rte_tel_data_start_dict(data); + + rte_tel_data_start_dict(spd4_data); + rte_tel_data_start_dict(spd6_data); + rte_tel_data_start_dict(sad_data); + + if (params) { + coreid = (uint32_t)atoi(params); + if (rte_lcore_is_enabled(coreid) == 0) { + rc = -EINVAL; + goto exit; + } + } + + update_statistics(&total_stats, coreid); + + /* add spd 4 telemetry key/values pairs */ + + rte_tel_data_add_dict_u64(spd4_data, "protect", + total_stats.outbound.spd4.protect); + rte_tel_data_add_dict_u64(spd4_data, "bypass", + total_stats.outbound.spd4.bypass); + rte_tel_data_add_dict_u64(spd4_data, "discard", + total_stats.outbound.spd4.discard); + + rte_tel_data_add_dict_container(data, "spd4", spd4_data, 0); + + /* add spd 6 telemetry key/values pairs */ + + rte_tel_data_add_dict_u64(spd6_data, "protect", + total_stats.outbound.spd6.protect); + rte_tel_data_add_dict_u64(spd6_data, "bypass", + total_stats.outbound.spd6.bypass); + rte_tel_data_add_dict_u64(spd6_data, "discard", + total_stats.outbound.spd6.discard); + + rte_tel_data_add_dict_container(data, "spd6", spd6_data, 0); + + /* add sad telemetry key/values pairs */ + + rte_tel_data_add_dict_u64(sad_data, "miss", + total_stats.outbound.sad.miss); + + rte_tel_data_add_dict_container(data, "sad", sad_data, 0); + +exit: + if (rc) { + rte_tel_data_free(spd4_data); + rte_tel_data_free(spd6_data); + rte_tel_data_free(sad_data); + } + return rc; +} + +static int +handle_telemetry_cmd_ipsec_secgw_stats_inbound(const char *cmd __rte_unused, + const char *params, struct rte_tel_data *data) +{ + struct ipsec_core_statistics total_stats; + + struct rte_tel_data *spd4_data = rte_tel_data_alloc(); + struct rte_tel_data *spd6_data = rte_tel_data_alloc(); + struct rte_tel_data *sad_data = rte_tel_data_alloc(); + unsigned int coreid = UINT32_MAX; + int rc = 0; + + /* verify allocated telemetry data structures */ + if (!spd4_data || !spd6_data || !sad_data) { + rc = -ENOMEM; + goto exit; + } + + /* initialize telemetry data structs as dicts */ + rte_tel_data_start_dict(data); + rte_tel_data_start_dict(spd4_data); + rte_tel_data_start_dict(spd6_data); + rte_tel_data_start_dict(sad_data); + + /* add children dicts to parent dict */ + + if (params) { + coreid = (uint32_t)atoi(params); + if (rte_lcore_is_enabled(coreid) == 0) { + rc = -EINVAL; + goto exit; + } + } + + update_statistics(&total_stats, coreid); + + /* add sad telemetry key/values pairs */ + + rte_tel_data_add_dict_u64(sad_data, "miss", + total_stats.inbound.sad.miss); + + rte_tel_data_add_dict_container(data, "sad", sad_data, 0); + + /* add spd 4 telemetry key/values pairs */ + + rte_tel_data_add_dict_u64(spd4_data, "protect", + total_stats.inbound.spd4.protect); + rte_tel_data_add_dict_u64(spd4_data, "bypass", + total_stats.inbound.spd4.bypass); + rte_tel_data_add_dict_u64(spd4_data, "discard", + total_stats.inbound.spd4.discard); + + rte_tel_data_add_dict_container(data, "spd4", spd4_data, 0); + + /* add spd 6 telemetry key/values pairs */ + + rte_tel_data_add_dict_u64(spd6_data, "protect", + total_stats.inbound.spd6.protect); + rte_tel_data_add_dict_u64(spd6_data, "bypass", + total_stats.inbound.spd6.bypass); + rte_tel_data_add_dict_u64(spd6_data, "discard", + total_stats.inbound.spd6.discard); + + rte_tel_data_add_dict_container(data, "spd6", spd6_data, 0); + +exit: + if (rc) { + rte_tel_data_free(spd4_data); + rte_tel_data_free(spd6_data); + rte_tel_data_free(sad_data); + } + return rc; +} + +static int +handle_telemetry_cmd_ipsec_secgw_stats_routing(const char *cmd __rte_unused, + const char *params, struct rte_tel_data *data) +{ + struct ipsec_core_statistics total_stats; + + struct rte_tel_data *lpm4_data = rte_tel_data_alloc(); + struct rte_tel_data *lpm6_data = rte_tel_data_alloc(); + unsigned int coreid = UINT32_MAX; + int rc = 0; + + /* verify allocated telemetry data structures */ + if (!lpm4_data || !lpm6_data) { + rc = -ENOMEM; + goto exit; + } + + /* initialize telemetry data structs as dicts */ + rte_tel_data_start_dict(data); + rte_tel_data_start_dict(lpm4_data); + rte_tel_data_start_dict(lpm6_data); + + + if (params) { + coreid = (uint32_t)atoi(params); + if (rte_lcore_is_enabled(coreid) == 0) { + rc = -EINVAL; + goto exit; + } + } + + update_statistics(&total_stats, coreid); + + /* add lpm 4 telemetry key/values pairs */ + rte_tel_data_add_dict_u64(lpm4_data, "miss", + total_stats.lpm4.miss); + + rte_tel_data_add_dict_container(data, "IPv4 LPM", lpm4_data, 0); + + /* add lpm 6 telemetry key/values pairs */ + rte_tel_data_add_dict_u64(lpm6_data, "miss", + total_stats.lpm6.miss); + + rte_tel_data_add_dict_container(data, "IPv6 LPM", lpm6_data, 0); + +exit: + if (rc) { + rte_tel_data_free(lpm4_data); + rte_tel_data_free(lpm6_data); + } + return rc; +} + +static void +ipsec_secgw_telemetry_init(void) +{ + rte_telemetry_register_cmd("/examples/ipsec-secgw/stats", + handle_telemetry_cmd_ipsec_secgw_stats, + "Returns global stats. " + "Optional Parameters: int "); + + rte_telemetry_register_cmd("/examples/ipsec-secgw/stats/outbound", + handle_telemetry_cmd_ipsec_secgw_stats_outbound, + "Returns outbound global stats. " + "Optional Parameters: int "); + + rte_telemetry_register_cmd("/examples/ipsec-secgw/stats/inbound", + handle_telemetry_cmd_ipsec_secgw_stats_inbound, + "Returns inbound global stats. " + "Optional Parameters: int "); + + rte_telemetry_register_cmd("/examples/ipsec-secgw/stats/routing", + handle_telemetry_cmd_ipsec_secgw_stats_routing, + "Returns routing stats. " + "Optional Parameters: int "); +} + + int32_t main(int32_t argc, char **argv) { int32_t ret; - uint32_t lcore_id; + uint32_t lcore_id, nb_txq, nb_rxq = 0; + uint32_t cdev_id; uint32_t i; uint8_t socket_id; - uint16_t portid; - uint64_t req_rx_offloads, req_tx_offloads; + uint16_t portid, nb_crypto_qp, nb_ports = 0; + uint64_t req_rx_offloads[RTE_MAX_ETHPORTS]; + uint64_t req_tx_offloads[RTE_MAX_ETHPORTS]; + struct eh_conf *eh_conf = NULL; size_t sess_sz; + nb_bufs_in_pool = 0; + /* init EAL */ ret = rte_eal_init(argc, argv); if (ret < 0) @@ -2409,11 +2880,22 @@ main(int32_t argc, char **argv) argc -= ret; argv += ret; + force_quit = false; + signal(SIGINT, signal_handler); + signal(SIGTERM, signal_handler); + + /* initialize event helper configuration */ + eh_conf = eh_conf_init(); + if (eh_conf == NULL) + rte_exit(EXIT_FAILURE, "Failed to init event helper config"); + /* parse application arguments (after the EAL ones) */ - ret = parse_args(argc, argv); + ret = parse_args(argc, argv, eh_conf); if (ret < 0) rte_exit(EXIT_FAILURE, "Invalid parameters\n"); + ipsec_secgw_telemetry_init(); + /* parse configuration file */ if (parse_cfg_file(cfgfile) < 0) { printf("parsing file \"%s\" failed\n", @@ -2427,8 +2909,14 @@ main(int32_t argc, char **argv) rte_exit(EXIT_FAILURE, "Invalid unprotected portmask 0x%x\n", unprotected_port_mask); - if (check_params() < 0) - rte_exit(EXIT_FAILURE, "check_params failed\n"); + if (unprotected_port_mask && !nb_sa_in) + rte_exit(EXIT_FAILURE, "Cannot use unprotected portmask without configured SA inbound\n"); + + if (check_poll_mode_params(eh_conf) < 0) + rte_exit(EXIT_FAILURE, "check_poll_mode_params failed\n"); + + if (check_event_mode_params(eh_conf) < 0) + rte_exit(EXIT_FAILURE, "check_event_mode_params failed\n"); ret = init_lcore_rx_queues(); if (ret < 0) @@ -2438,6 +2926,31 @@ main(int32_t argc, char **argv) sess_sz = max_session_size(); + /* + * In event mode request minimum number of crypto queues + * to be reserved equal to number of ports. + */ + if (eh_conf->mode == EH_PKT_TRANSFER_MODE_EVENT) + nb_crypto_qp = rte_eth_dev_count_avail(); + else + nb_crypto_qp = 0; + + nb_crypto_qp = cryptodevs_init(nb_crypto_qp); + + if (nb_bufs_in_pool == 0) { + RTE_ETH_FOREACH_DEV(portid) { + if ((enabled_port_mask & (1 << portid)) == 0) + continue; + nb_ports++; + nb_rxq += get_port_nb_rx_queues(portid); + } + + nb_txq = nb_lcores; + + nb_bufs_in_pool = calculate_nb_mbufs(nb_ports, nb_crypto_qp, + nb_rxq, nb_txq); + } + for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) { if (rte_lcore_is_enabled(lcore_id) == 0) continue; @@ -2447,40 +2960,63 @@ main(int32_t argc, char **argv) else socket_id = 0; - /* mbuf_pool is initialised by the pool_init() function*/ - if (socket_ctx[socket_id].mbuf_pool) + if (per_port_pool) { + RTE_ETH_FOREACH_DEV(portid) { + if ((enabled_port_mask & (1 << portid)) == 0) + continue; + + pool_init(&socket_ctx[socket_id], socket_id, + portid, nb_bufs_in_pool); + } + } else { + pool_init(&socket_ctx[socket_id], socket_id, 0, + nb_bufs_in_pool); + } + + if (socket_ctx[socket_id].session_pool) continue; - pool_init(&socket_ctx[socket_id], socket_id, NB_MBUF); session_pool_init(&socket_ctx[socket_id], socket_id, sess_sz); session_priv_pool_init(&socket_ctx[socket_id], socket_id, sess_sz); } + printf("Number of mbufs in packet pool %d\n", nb_bufs_in_pool); RTE_ETH_FOREACH_DEV(portid) { if ((enabled_port_mask & (1 << portid)) == 0) continue; - sa_check_offloads(portid, &req_rx_offloads, &req_tx_offloads); - port_init(portid, req_rx_offloads, req_tx_offloads); + sa_check_offloads(portid, &req_rx_offloads[portid], + &req_tx_offloads[portid]); + port_init(portid, req_rx_offloads[portid], + req_tx_offloads[portid]); } - cryptodevs_init(); + /* + * Set the enabled port mask in helper config for use by helper + * sub-system. This will be used while initializing devices using + * helper sub-system. + */ + eh_conf->eth_portmask = enabled_port_mask; + + /* Initialize eventmode components */ + ret = eh_devs_init(eh_conf); + if (ret < 0) + rte_exit(EXIT_FAILURE, "eh_devs_init failed, err=%d\n", ret); /* start ports */ RTE_ETH_FOREACH_DEV(portid) { if ((enabled_port_mask & (1 << portid)) == 0) continue; - /* - * Start device - * note: device must be started before a flow rule - * can be installed. - */ ret = rte_eth_dev_start(portid); if (ret < 0) rte_exit(EXIT_FAILURE, "rte_eth_dev_start: " "err=%d, port=%d\n", ret, portid); + + /* Create flow after starting the device */ + create_default_ipsec_flow(portid, req_rx_offloads[portid]); + /* * If enabled, put device in promiscuous mode. * This allows IO forwarding mode to forward packets @@ -2495,6 +3031,9 @@ main(int32_t argc, char **argv) rte_strerror(-ret), portid); } + rte_eth_dev_callback_register(portid, RTE_ETH_EVENT_INTR_RESET, + ethdev_reset_event_callback, NULL); + rte_eth_dev_callback_register(portid, RTE_ETH_EVENT_IPSEC, inline_ipsec_event_callback, NULL); } @@ -2509,7 +3048,7 @@ main(int32_t argc, char **argv) /* Replicate each context per socket */ for (i = 0; i < NB_SOCKETS && i < rte_socket_count(); i++) { socket_id = rte_socket_id_by_idx(i); - if ((socket_ctx[socket_id].mbuf_pool != NULL) && + if ((socket_ctx[socket_id].session_pool != NULL) && (socket_ctx[socket_id].sa_in == NULL) && (socket_ctx[socket_id].sa_out == NULL)) { sa_init(&socket_ctx[socket_id], socket_id); @@ -2519,14 +3058,73 @@ main(int32_t argc, char **argv) } } + flow_init(); + check_all_ports_link_status(enabled_port_mask); + if (stats_interval > 0) + rte_eal_alarm_set(stats_interval * US_PER_S, + print_stats_cb, NULL); + else + RTE_LOG(INFO, IPSEC, "Stats display disabled\n"); + /* launch per-lcore init on every lcore */ - rte_eal_mp_remote_launch(main_loop, NULL, CALL_MASTER); - RTE_LCORE_FOREACH_SLAVE(lcore_id) { + rte_eal_mp_remote_launch(ipsec_launch_one_lcore, eh_conf, CALL_MAIN); + RTE_LCORE_FOREACH_WORKER(lcore_id) { if (rte_eal_wait_lcore(lcore_id) < 0) return -1; } + /* Uninitialize eventmode components */ + ret = eh_devs_uninit(eh_conf); + if (ret < 0) + rte_exit(EXIT_FAILURE, "eh_devs_uninit failed, err=%d\n", ret); + + /* Free eventmode configuration memory */ + eh_conf_uninit(eh_conf); + + /* Destroy inline inbound and outbound sessions */ + for (i = 0; i < NB_SOCKETS && i < rte_socket_count(); i++) { + socket_id = rte_socket_id_by_idx(i); + inline_sessions_free(socket_ctx[socket_id].sa_in); + inline_sessions_free(socket_ctx[socket_id].sa_out); + } + + for (cdev_id = 0; cdev_id < rte_cryptodev_count(); cdev_id++) { + printf("Closing cryptodev %d...", cdev_id); + rte_cryptodev_stop(cdev_id); + rte_cryptodev_close(cdev_id); + printf(" Done\n"); + } + + RTE_ETH_FOREACH_DEV(portid) { + if ((enabled_port_mask & (1 << portid)) == 0) + continue; + + printf("Closing port %d...", portid); + if (flow_info_tbl[portid].rx_def_flow) { + struct rte_flow_error err; + + ret = rte_flow_destroy(portid, + flow_info_tbl[portid].rx_def_flow, &err); + if (ret) + RTE_LOG(ERR, IPSEC, "Failed to destroy flow " + " for port %u, err msg: %s\n", portid, + err.message); + } + ret = rte_eth_dev_stop(portid); + if (ret != 0) + RTE_LOG(ERR, IPSEC, + "rte_eth_dev_stop: err=%s, port=%u\n", + rte_strerror(-ret), portid); + + rte_eth_dev_close(portid); + printf(" Done\n"); + } + + /* clean up the EAL */ + rte_eal_cleanup(); + printf("Bye...\n"); + return 0; }