X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=examples%2Fl3fwd-power%2Fmain.c;h=2c6da3ffc71a983c9dbbb7cda4d4281c72936d8e;hb=24ac604ef7469eb5773c2504b313dd00257f8df3;hp=12e4fd6b669e58758c9785473f21ee3ca921ad16;hpb=81f7ecd934372fc9f592d1322f8eff86350fa4f5;p=dpdk.git diff --git a/examples/l3fwd-power/main.c b/examples/l3fwd-power/main.c index 12e4fd6b66..2c6da3ffc7 100644 --- a/examples/l3fwd-power/main.c +++ b/examples/l3fwd-power/main.c @@ -1,34 +1,5 @@ -/*- - * BSD LICENSE - * - * Copyright(c) 2010-2014 Intel Corporation. All rights reserved. - * All rights reserved. - * - * 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 Intel 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. +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2010-2018 Intel Corporation */ #include @@ -47,12 +18,10 @@ #include #include #include +#include #include #include -#include -#include #include -#include #include #include #include @@ -61,12 +30,10 @@ #include #include #include -#include #include #include #include #include -#include #include #include #include @@ -75,19 +42,22 @@ #include #include #include +#include +#include +#include "perf_core.h" #include "main.h" #define RTE_LOGTYPE_L3FWD_POWER RTE_LOGTYPE_USER1 #define MAX_PKT_BURST 32 -#define MIN_ZERO_POLL_COUNT 5 +#define MIN_ZERO_POLL_COUNT 10 -/* around 100ms at 2 Ghz */ -#define TIMER_RESOLUTION_CYCLES 200000000ULL /* 100 ms interval */ #define TIMER_NUMBER_PER_SECOND 10 +/* (10ms) */ +#define INTERVALS_PER_SECOND 100 /* 100000 us */ #define SCALING_PERIOD (1000000/TIMER_NUMBER_PER_SECOND) #define SCALING_DOWN_TIME_RATIO_THRESHOLD 0.25 @@ -124,8 +94,6 @@ #define MEMPOOL_CACHE_SIZE 256 -#define MBUF_SIZE (2048 + sizeof(struct rte_mbuf) + RTE_PKTMBUF_HEADROOM) - /* * This expression is used to calculate the number of mbufs needed depending on * user input, taking into account memory for rx and tx hardware rings, cache @@ -134,9 +102,9 @@ */ #define NB_MBUF RTE_MAX ( \ - (nb_ports*nb_rx_queue*RTE_TEST_RX_DESC_DEFAULT + \ + (nb_ports*nb_rx_queue*nb_rxd + \ nb_ports*nb_lcores*MAX_PKT_BURST + \ - nb_ports*n_tx_queue*RTE_TEST_TX_DESC_DEFAULT + \ + nb_ports*n_tx_queue*nb_txd + \ nb_lcores*MEMPOOL_CACHE_SIZE), \ (unsigned)8192) @@ -150,13 +118,27 @@ /* * Configurable number of RX/TX ring descriptors */ -#define RTE_TEST_RX_DESC_DEFAULT 128 -#define RTE_TEST_TX_DESC_DEFAULT 512 +#define RTE_TEST_RX_DESC_DEFAULT 1024 +#define RTE_TEST_TX_DESC_DEFAULT 1024 + +/* + * These two thresholds were decided on by running the training algorithm on + * a 2.5GHz Xeon. These defaults can be overridden by supplying non-zero values + * for the med_threshold and high_threshold parameters on the command line. + */ +#define EMPTY_POLL_MED_THRESHOLD 350000UL +#define EMPTY_POLL_HGH_THRESHOLD 580000UL + + + static uint16_t nb_rxd = RTE_TEST_RX_DESC_DEFAULT; static uint16_t nb_txd = RTE_TEST_TX_DESC_DEFAULT; /* ethernet addresses of ports */ -static struct ether_addr ports_eth_addr[RTE_MAX_ETHPORTS]; +static struct rte_ether_addr ports_eth_addr[RTE_MAX_ETHPORTS]; + +/* ethernet addresses of ports */ +static rte_spinlock_t locks[RTE_MAX_ETHPORTS]; /* mask of enabled ports */ static uint32_t enabled_port_mask = 0; @@ -164,6 +146,16 @@ static uint32_t enabled_port_mask = 0; static int promiscuous_on = 0; /* NUMA is enabled by default. */ static int numa_on = 1; +/* emptypoll is disabled by default. */ +static bool empty_poll_on; +static bool empty_poll_train; +volatile bool empty_poll_stop; +static struct ep_params *ep_params; +static struct ep_policy policy; +static long ep_med_edpi, ep_hgh_edpi; + +static int parse_ptype; /**< Parse packet type using rx callback, and */ + /**< disabled by default */ enum freq_scale_hint_t { @@ -173,13 +165,8 @@ enum freq_scale_hint_t FREQ_HIGHEST = 2 }; -struct mbuf_table { - uint16_t len; - struct rte_mbuf *m_table[MAX_PKT_BURST]; -}; - struct lcore_rx_queue { - uint8_t port_id; + uint16_t port_id; uint8_t queue_id; enum freq_scale_hint_t freq_up_hint; uint32_t zero_rx_packet_count; @@ -190,14 +177,10 @@ struct lcore_rx_queue { #define MAX_TX_QUEUE_PER_PORT RTE_MAX_ETHPORTS #define MAX_RX_QUEUE_PER_PORT 128 -#define MAX_LCORE_PARAMS 1024 -struct lcore_params { - uint8_t port_id; - uint8_t queue_id; - uint8_t lcore_id; -} __rte_cache_aligned; +#define MAX_RX_QUEUE_INTERRUPT_PER_PORT 16 -static struct lcore_params lcore_params_array[MAX_LCORE_PARAMS]; + +struct lcore_params lcore_params_array[MAX_LCORE_PARAMS]; static struct lcore_params lcore_params_array_default[] = { {0, 0, 2}, {0, 1, 2}, @@ -210,29 +193,28 @@ static struct lcore_params lcore_params_array_default[] = { {3, 1, 3}, }; -static struct lcore_params * lcore_params = lcore_params_array_default; -static uint16_t nb_lcore_params = sizeof(lcore_params_array_default) / +struct lcore_params *lcore_params = lcore_params_array_default; +uint16_t nb_lcore_params = sizeof(lcore_params_array_default) / sizeof(lcore_params_array_default[0]); static struct rte_eth_conf port_conf = { .rxmode = { - .mq_mode = ETH_MQ_RX_RSS, - .max_rx_pkt_len = ETHER_MAX_LEN, + .mq_mode = ETH_MQ_RX_RSS, + .max_rx_pkt_len = RTE_ETHER_MAX_LEN, .split_hdr_size = 0, - .header_split = 0, /**< Header Split disabled */ - .hw_ip_checksum = 1, /**< IP checksum offload enabled */ - .hw_vlan_filter = 0, /**< VLAN filtering disabled */ - .jumbo_frame = 0, /**< Jumbo Frame Support disabled */ - .hw_strip_crc = 0, /**< CRC stripped by hardware */ + .offloads = DEV_RX_OFFLOAD_CHECKSUM, }, .rx_adv_conf = { .rss_conf = { .rss_key = NULL, - .rss_hf = ETH_RSS_IP, + .rss_hf = ETH_RSS_UDP, }, }, .txmode = { - .mq_mode = ETH_DCB_NONE, + .mq_mode = ETH_MQ_TX_NONE, + }, + .intr_conf = { + .rxq = 1, }, }; @@ -241,7 +223,7 @@ static struct rte_mempool * pktmbuf_pool[NB_SOCKETS]; #if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH) -#ifdef RTE_MACHINE_CPUFLAG_SSE4_2 +#ifdef RTE_ARCH_X86 #include #define DEFAULT_HASH_FUNC rte_hash_crc #else @@ -276,10 +258,10 @@ struct ipv6_l3fwd_route { }; static struct ipv4_l3fwd_route ipv4_l3fwd_route_array[] = { - {{IPv4(100,10,0,1), IPv4(200,10,0,1), 101, 11, IPPROTO_TCP}, 0}, - {{IPv4(100,20,0,2), IPv4(200,20,0,2), 102, 12, IPPROTO_TCP}, 1}, - {{IPv4(100,30,0,3), IPv4(200,30,0,3), 103, 13, IPPROTO_TCP}, 2}, - {{IPv4(100,40,0,4), IPv4(200,40,0,4), 104, 14, IPPROTO_TCP}, 3}, + {{RTE_IPv4(100,10,0,1), RTE_IPv4(200,10,0,1), 101, 11, IPPROTO_TCP}, 0}, + {{RTE_IPv4(100,20,0,2), RTE_IPv4(200,20,0,2), 102, 12, IPPROTO_TCP}, 1}, + {{RTE_IPv4(100,30,0,3), RTE_IPv4(200,30,0,3), 103, 13, IPPROTO_TCP}, 2}, + {{RTE_IPv4(100,40,0,4), RTE_IPv4(200,40,0,4), 104, 14, IPPROTO_TCP}, 3}, }; static struct ipv6_l3fwd_route ipv6_l3fwd_route_array[] = { @@ -306,8 +288,8 @@ static lookup_struct_t *ipv6_l3fwd_lookup_struct[NB_SOCKETS]; #define IPV6_L3FWD_NUM_ROUTES \ (sizeof(ipv6_l3fwd_route_array) / sizeof(ipv6_l3fwd_route_array[0])) -static uint8_t ipv4_l3fwd_out_if[L3FWD_HASH_ENTRIES] __rte_cache_aligned; -static uint8_t ipv6_l3fwd_out_if[L3FWD_HASH_ENTRIES] __rte_cache_aligned; +static uint16_t ipv4_l3fwd_out_if[L3FWD_HASH_ENTRIES] __rte_cache_aligned; +static uint16_t ipv6_l3fwd_out_if[L3FWD_HASH_ENTRIES] __rte_cache_aligned; #endif #if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM) @@ -318,14 +300,14 @@ struct ipv4_l3fwd_route { }; static struct ipv4_l3fwd_route ipv4_l3fwd_route_array[] = { - {IPv4(1,1,1,0), 24, 0}, - {IPv4(2,1,1,0), 24, 1}, - {IPv4(3,1,1,0), 24, 2}, - {IPv4(4,1,1,0), 24, 3}, - {IPv4(5,1,1,0), 24, 4}, - {IPv4(6,1,1,0), 24, 5}, - {IPv4(7,1,1,0), 24, 6}, - {IPv4(8,1,1,0), 24, 7}, + {RTE_IPv4(1,1,1,0), 24, 0}, + {RTE_IPv4(2,1,1,0), 24, 1}, + {RTE_IPv4(3,1,1,0), 24, 2}, + {RTE_IPv4(4,1,1,0), 24, 3}, + {RTE_IPv4(5,1,1,0), 24, 4}, + {RTE_IPv4(6,1,1,0), 24, 5}, + {RTE_IPv4(7,1,1,0), 24, 6}, + {RTE_IPv4(8,1,1,0), 24, 7}, }; #define IPV4_L3FWD_NUM_ROUTES \ @@ -340,8 +322,10 @@ static lookup_struct_t *ipv4_l3fwd_lookup_struct[NB_SOCKETS]; struct lcore_conf { uint16_t n_rx_queue; struct lcore_rx_queue rx_queue_list[MAX_RX_QUEUE_PER_LCORE]; + uint16_t n_tx_port; + uint16_t tx_port_id[RTE_MAX_ETHPORTS]; uint16_t tx_queue_id[RTE_MAX_ETHPORTS]; - struct mbuf_table tx_mbufs[RTE_MAX_ETHPORTS]; + struct rte_eth_dev_tx_buffer *tx_buffer[RTE_MAX_ETHPORTS]; lookup_struct_t * ipv4_lookup_struct; lookup_struct_t * ipv6_lookup_struct; } __rte_cache_aligned; @@ -366,16 +350,34 @@ static struct rte_timer power_timers[RTE_MAX_LCORE]; static inline uint32_t power_idle_heuristic(uint32_t zero_rx_packet_count); static inline enum freq_scale_hint_t power_freq_scaleup_heuristic( \ - unsigned lcore_id, uint8_t port_id, uint16_t queue_id); + unsigned int lcore_id, uint16_t port_id, uint16_t queue_id); + + +/* + * These defaults are using the max frequency index (1), a medium index (9) + * and a typical low frequency index (14). These can be adjusted to use + * different indexes using the relevant command line parameters. + */ +static uint8_t freq_tlb[] = {14, 9, 1}; + +static int is_done(void) +{ + return empty_poll_stop; +} /* exit signal handler */ static void signal_exit_now(int sigtype) { unsigned lcore_id; + unsigned int portid; int ret; if (sigtype == SIGINT) { + if (empty_poll_on) + empty_poll_stop = true; + + for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) { if (rte_lcore_is_enabled(lcore_id) == 0) continue; @@ -387,9 +389,20 @@ signal_exit_now(int sigtype) "library de-initialization failed on " "core%u\n", lcore_id); } + + if (!empty_poll_on) { + RTE_ETH_FOREACH_DEV(portid) { + if ((enabled_port_mask & (1 << portid)) == 0) + continue; + + rte_eth_dev_stop(portid); + rte_eth_dev_close(portid); + } + } } - rte_exit(EXIT_SUCCESS, "User forced exit\n"); + if (!empty_poll_on) + rte_exit(EXIT_SUCCESS, "User forced exit\n"); } /* Freqency scale down timer callback */ @@ -404,19 +417,22 @@ power_timer_cb(__attribute__((unused)) struct rte_timer *tim, /* accumulate total execution time in us when callback is invoked */ sleep_time_ratio = (float)(stats[lcore_id].sleep_time) / (float)SCALING_PERIOD; - /** * check whether need to scale down frequency a step if it sleep a lot. */ - if (sleep_time_ratio >= SCALING_DOWN_TIME_RATIO_THRESHOLD) - rte_power_freq_down(lcore_id); + if (sleep_time_ratio >= SCALING_DOWN_TIME_RATIO_THRESHOLD) { + if (rte_power_freq_down) + rte_power_freq_down(lcore_id); + } else if ( (unsigned)(stats[lcore_id].nb_rx_processed / - stats[lcore_id].nb_iteration_looped) < MAX_PKT_BURST) + stats[lcore_id].nb_iteration_looped) < MAX_PKT_BURST) { /** * scale down a step if average packet per iteration less * than expectation. */ - rte_power_freq_down(lcore_id); + if (rte_power_freq_down) + rte_power_freq_down(lcore_id); + } /** * initialize another timer according to current frequency to ensure @@ -432,62 +448,32 @@ power_timer_cb(__attribute__((unused)) struct rte_timer *tim, stats[lcore_id].sleep_time = 0; } -/* Send burst of packets on an output interface */ -static inline int -send_burst(struct lcore_conf *qconf, uint16_t n, uint8_t port) -{ - struct rte_mbuf **m_table; - int ret; - uint16_t queueid; - - queueid = qconf->tx_queue_id[port]; - m_table = (struct rte_mbuf **)qconf->tx_mbufs[port].m_table; - - 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; -} - /* Enqueue a single packet, and send burst if queue is filled */ static inline int -send_single_packet(struct rte_mbuf *m, uint8_t port) +send_single_packet(struct rte_mbuf *m, uint16_t port) { 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; - qconf->tx_mbufs[port].m_table[len] = m; - len++; - - /* 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; + rte_eth_tx_buffer(port, qconf->tx_queue_id[port], + qconf->tx_buffer[port], m); + return 0; } #ifdef DO_RFC_1812_CHECKS static inline int -is_valid_ipv4_pkt(struct ipv4_hdr *pkt, uint32_t link_len) +is_valid_ipv4_pkt(struct rte_ipv4_hdr *pkt, uint32_t link_len) { /* From http://www.rfc-editor.org/rfc/rfc1812.txt section 5.2.2 */ /* * 1. The packet length reported by the Link Layer must be large * enough to hold the minimum length legal IP datagram (20 bytes). */ - if (link_len < sizeof(struct ipv4_hdr)) + if (link_len < sizeof(struct rte_ipv4_hdr)) return -1; /* 2. The IP checksum must be correct. */ @@ -512,7 +498,7 @@ is_valid_ipv4_pkt(struct ipv4_hdr *pkt, uint32_t link_len) * datagram header, whose length is specified in the IP header length * field. */ - if (rte_cpu_to_be_16(pkt->total_length) < sizeof(struct ipv4_hdr)) + if (rte_cpu_to_be_16(pkt->total_length) < sizeof(struct rte_ipv4_hdr)) return -5; return 0; @@ -536,8 +522,8 @@ print_ipv6_key(struct ipv6_5tuple key) key.port_dst, key.port_src, key.proto); } -static inline uint8_t -get_ipv4_dst_port(struct ipv4_hdr *ipv4_hdr, uint8_t portid, +static inline uint16_t +get_ipv4_dst_port(struct rte_ipv4_hdr *ipv4_hdr, uint16_t portid, lookup_struct_t * ipv4_l3fwd_lookup_struct) { struct ipv4_5tuple key; @@ -552,14 +538,14 @@ get_ipv4_dst_port(struct ipv4_hdr *ipv4_hdr, uint8_t portid, switch (ipv4_hdr->next_proto_id) { case IPPROTO_TCP: tcp = (struct tcp_hdr *)((unsigned char *)ipv4_hdr + - sizeof(struct ipv4_hdr)); + sizeof(struct rte_ipv4_hdr)); key.port_dst = rte_be_to_cpu_16(tcp->dst_port); key.port_src = rte_be_to_cpu_16(tcp->src_port); break; case IPPROTO_UDP: udp = (struct udp_hdr *)((unsigned char *)ipv4_hdr + - sizeof(struct ipv4_hdr)); + sizeof(struct rte_ipv4_hdr)); key.port_dst = rte_be_to_cpu_16(udp->dst_port); key.port_src = rte_be_to_cpu_16(udp->src_port); break; @@ -572,11 +558,11 @@ get_ipv4_dst_port(struct ipv4_hdr *ipv4_hdr, uint8_t portid, /* Find destination port */ ret = rte_hash_lookup(ipv4_l3fwd_lookup_struct, (const void *)&key); - return (uint8_t)((ret < 0)? portid : ipv4_l3fwd_out_if[ret]); + return ((ret < 0) ? portid : ipv4_l3fwd_out_if[ret]); } -static inline uint8_t -get_ipv6_dst_port(struct ipv6_hdr *ipv6_hdr, uint8_t portid, +static inline uint16_t +get_ipv6_dst_port(struct rte_ipv6_hdr *ipv6_hdr, uint16_t portid, lookup_struct_t *ipv6_l3fwd_lookup_struct) { struct ipv6_5tuple key; @@ -592,14 +578,14 @@ get_ipv6_dst_port(struct ipv6_hdr *ipv6_hdr, uint8_t portid, switch (ipv6_hdr->proto) { case IPPROTO_TCP: tcp = (struct tcp_hdr *)((unsigned char *) ipv6_hdr + - sizeof(struct ipv6_hdr)); + sizeof(struct rte_ipv6_hdr)); key.port_dst = rte_be_to_cpu_16(tcp->dst_port); key.port_src = rte_be_to_cpu_16(tcp->src_port); break; case IPPROTO_UDP: udp = (struct udp_hdr *)((unsigned char *) ipv6_hdr + - sizeof(struct ipv6_hdr)); + sizeof(struct rte_ipv6_hdr)); key.port_dst = rte_be_to_cpu_16(udp->dst_port); key.port_src = rte_be_to_cpu_16(udp->src_port); break; @@ -612,39 +598,81 @@ get_ipv6_dst_port(struct ipv6_hdr *ipv6_hdr, uint8_t portid, /* Find destination port */ ret = rte_hash_lookup(ipv6_l3fwd_lookup_struct, (const void *)&key); - return (uint8_t)((ret < 0)? portid : ipv6_l3fwd_out_if[ret]); + return ((ret < 0) ? portid : ipv6_l3fwd_out_if[ret]); } #endif #if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM) -static inline uint8_t -get_ipv4_dst_port(struct ipv4_hdr *ipv4_hdr, uint8_t portid, +static inline uint16_t +get_ipv4_dst_port(struct rte_ipv4_hdr *ipv4_hdr, uint16_t portid, lookup_struct_t *ipv4_l3fwd_lookup_struct) { - uint8_t next_hop; + uint32_t next_hop; - return (uint8_t) ((rte_lpm_lookup(ipv4_l3fwd_lookup_struct, + return ((rte_lpm_lookup(ipv4_l3fwd_lookup_struct, rte_be_to_cpu_32(ipv4_hdr->dst_addr), &next_hop) == 0)? next_hop : portid); } #endif static inline void -l3fwd_simple_forward(struct rte_mbuf *m, uint8_t portid, +parse_ptype_one(struct rte_mbuf *m) +{ + struct rte_ether_hdr *eth_hdr; + uint32_t packet_type = RTE_PTYPE_UNKNOWN; + uint16_t ether_type; + + eth_hdr = rte_pktmbuf_mtod(m, struct rte_ether_hdr *); + ether_type = eth_hdr->ether_type; + if (ether_type == rte_cpu_to_be_16(RTE_ETHER_TYPE_IPv4)) + packet_type |= RTE_PTYPE_L3_IPV4_EXT_UNKNOWN; + else if (ether_type == rte_cpu_to_be_16(RTE_ETHER_TYPE_IPv6)) + packet_type |= RTE_PTYPE_L3_IPV6_EXT_UNKNOWN; + + m->packet_type = packet_type; +} + +static uint16_t +cb_parse_ptype(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) +{ + unsigned int i; + + for (i = 0; i < nb_pkts; ++i) + parse_ptype_one(pkts[i]); + + return nb_pkts; +} + +static int +add_cb_parse_ptype(uint16_t portid, uint16_t queueid) +{ + printf("Port %d: softly parse packet type info\n", portid); + if (rte_eth_add_rx_callback(portid, queueid, cb_parse_ptype, NULL)) + return 0; + + printf("Failed to add rx callback: port=%d\n", portid); + return -1; +} + +static inline void +l3fwd_simple_forward(struct rte_mbuf *m, uint16_t portid, struct lcore_conf *qconf) { - struct ether_hdr *eth_hdr; - struct ipv4_hdr *ipv4_hdr; + struct rte_ether_hdr *eth_hdr; + struct rte_ipv4_hdr *ipv4_hdr; void *d_addr_bytes; - uint8_t dst_port; + uint16_t dst_port; - eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *); + eth_hdr = rte_pktmbuf_mtod(m, struct rte_ether_hdr *); - if (m->ol_flags & PKT_RX_IPV4_HDR) { + if (RTE_ETH_IS_IPV4_HDR(m->packet_type)) { /* Handle IPv4 headers.*/ ipv4_hdr = - (struct ipv4_hdr *)(rte_pktmbuf_mtod(m, unsigned char*) - + sizeof(struct ether_hdr)); + rte_pktmbuf_mtod_offset(m, struct rte_ipv4_hdr *, + sizeof(struct rte_ether_hdr)); #ifdef DO_RFC_1812_CHECKS /* Check to make sure the packet is valid (RFC1812) */ @@ -672,18 +700,18 @@ l3fwd_simple_forward(struct rte_mbuf *m, uint8_t portid, #endif /* src addr */ - ether_addr_copy(&ports_eth_addr[dst_port], ð_hdr->s_addr); + rte_ether_addr_copy(&ports_eth_addr[dst_port], + ð_hdr->s_addr); send_single_packet(m, dst_port); - } - else { + } else if (RTE_ETH_IS_IPV6_HDR(m->packet_type)) { /* Handle IPv6 headers.*/ #if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH) - struct ipv6_hdr *ipv6_hdr; + struct rte_ipv6_hdr *ipv6_hdr; ipv6_hdr = - (struct ipv6_hdr *)(rte_pktmbuf_mtod(m, unsigned char*) - + sizeof(struct ether_hdr)); + rte_pktmbuf_mtod_offset(m, struct rte_ipv6_hdr *, + sizeof(struct rte_ether_hdr)); dst_port = get_ipv6_dst_port(ipv6_hdr, portid, qconf->ipv6_lookup_struct); @@ -698,42 +726,41 @@ l3fwd_simple_forward(struct rte_mbuf *m, uint8_t portid, 0x000000000002 + ((uint64_t)dst_port << 40); /* src addr */ - ether_addr_copy(&ports_eth_addr[dst_port], ð_hdr->s_addr); + rte_ether_addr_copy(&ports_eth_addr[dst_port], + ð_hdr->s_addr); send_single_packet(m, dst_port); #else /* We don't currently handle IPv6 packets in LPM mode. */ rte_pktmbuf_free(m); #endif - } + } else + rte_pktmbuf_free(m); } -#define SLEEP_GEAR1_THRESHOLD 100 -#define SLEEP_GEAR2_THRESHOLD 1000 +#define MINIMUM_SLEEP_TIME 1 +#define SUSPEND_THRESHOLD 300 static inline uint32_t power_idle_heuristic(uint32_t zero_rx_packet_count) { - /* If zero count is less than 100, use it as the sleep time in us */ - if (zero_rx_packet_count < SLEEP_GEAR1_THRESHOLD) - return zero_rx_packet_count; - /* If zero count is less than 1000, sleep time should be 100 us */ - else if ((zero_rx_packet_count >= SLEEP_GEAR1_THRESHOLD) && - (zero_rx_packet_count < SLEEP_GEAR2_THRESHOLD)) - return SLEEP_GEAR1_THRESHOLD; - /* If zero count is greater than 1000, sleep time should be 1000 us */ - else if (zero_rx_packet_count >= SLEEP_GEAR2_THRESHOLD) - return SLEEP_GEAR2_THRESHOLD; - - return 0; + /* If zero count is less than 100, sleep 1us */ + if (zero_rx_packet_count < SUSPEND_THRESHOLD) + return MINIMUM_SLEEP_TIME; + /* If zero count is less than 1000, sleep 100 us which is the + minimum latency switching from C3/C6 to C0 + */ + else + return SUSPEND_THRESHOLD; } static inline enum freq_scale_hint_t power_freq_scaleup_heuristic(unsigned lcore_id, - uint8_t port_id, + uint16_t port_id, uint16_t queue_id) { + uint32_t rxq_count = rte_eth_rx_queue_count(port_id, queue_id); /** * HW Rx queue size is 128 by default, Rx burst read at maximum 32 entries * per iteration @@ -745,15 +772,12 @@ power_freq_scaleup_heuristic(unsigned lcore_id, #define FREQ_UP_TREND2_ACC 100 #define FREQ_UP_THRESHOLD 10000 - if (likely(rte_eth_rx_descriptor_done(port_id, queue_id, - FREQ_GEAR3_RX_PACKET_THRESHOLD) > 0)) { + if (likely(rxq_count > FREQ_GEAR3_RX_PACKET_THRESHOLD)) { stats[lcore_id].trend = 0; return FREQ_HIGHEST; - } else if (likely(rte_eth_rx_descriptor_done(port_id, queue_id, - FREQ_GEAR2_RX_PACKET_THRESHOLD) > 0)) + } else if (likely(rxq_count > FREQ_GEAR2_RX_PACKET_THRESHOLD)) stats[lcore_id].trend += FREQ_UP_TREND2_ACC; - else if (likely(rte_eth_rx_descriptor_done(port_id, queue_id, - FREQ_GEAR1_RX_PACKET_THRESHOLD) > 0)) + else if (likely(rxq_count > FREQ_GEAR1_RX_PACKET_THRESHOLD)) stats[lcore_id].trend += FREQ_UP_TREND1_ACC; if (likely(stats[lcore_id].trend > FREQ_UP_THRESHOLD)) { @@ -764,26 +788,214 @@ power_freq_scaleup_heuristic(unsigned lcore_id, return FREQ_CURRENT; } +/** + * force polling thread sleep until one-shot rx interrupt triggers + * @param port_id + * Port id. + * @param queue_id + * Rx queue id. + * @return + * 0 on success + */ +static int +sleep_until_rx_interrupt(int num) +{ + struct rte_epoll_event event[num]; + int n, i; + uint16_t port_id; + uint8_t queue_id; + void *data; + + RTE_LOG(INFO, L3FWD_POWER, + "lcore %u sleeps until interrupt triggers\n", + rte_lcore_id()); + + n = rte_epoll_wait(RTE_EPOLL_PER_THREAD, event, num, -1); + for (i = 0; i < n; i++) { + data = event[i].epdata.data; + port_id = ((uintptr_t)data) >> CHAR_BIT; + queue_id = ((uintptr_t)data) & + RTE_LEN2MASK(CHAR_BIT, uint8_t); + rte_eth_dev_rx_intr_disable(port_id, queue_id); + RTE_LOG(INFO, L3FWD_POWER, + "lcore %u is waked up from rx interrupt on" + " port %d queue %d\n", + rte_lcore_id(), port_id, queue_id); + } + + return 0; +} + +static void turn_on_intr(struct lcore_conf *qconf) +{ + int i; + struct lcore_rx_queue *rx_queue; + uint8_t queue_id; + uint16_t port_id; + + for (i = 0; i < qconf->n_rx_queue; ++i) { + rx_queue = &(qconf->rx_queue_list[i]); + port_id = rx_queue->port_id; + queue_id = rx_queue->queue_id; + + rte_spinlock_lock(&(locks[port_id])); + rte_eth_dev_rx_intr_enable(port_id, queue_id); + rte_spinlock_unlock(&(locks[port_id])); + } +} + +static int event_register(struct lcore_conf *qconf) +{ + struct lcore_rx_queue *rx_queue; + uint8_t queueid; + uint16_t portid; + uint32_t data; + int ret; + int i; + + for (i = 0; i < qconf->n_rx_queue; ++i) { + rx_queue = &(qconf->rx_queue_list[i]); + portid = rx_queue->port_id; + queueid = rx_queue->queue_id; + data = portid << CHAR_BIT | queueid; + + ret = rte_eth_dev_rx_intr_ctl_q(portid, queueid, + RTE_EPOLL_PER_THREAD, + RTE_INTR_EVENT_ADD, + (void *)((uintptr_t)data)); + if (ret) + return ret; + } + + return 0; +} +/* main processing loop */ +static int +main_empty_poll_loop(__attribute__((unused)) void *dummy) +{ + struct rte_mbuf *pkts_burst[MAX_PKT_BURST]; + unsigned int lcore_id; + uint64_t prev_tsc, diff_tsc, cur_tsc; + int i, j, nb_rx; + uint8_t queueid; + uint16_t portid; + struct lcore_conf *qconf; + struct lcore_rx_queue *rx_queue; + + const uint64_t drain_tsc = + (rte_get_tsc_hz() + US_PER_S - 1) / + US_PER_S * BURST_TX_DRAIN_US; + + prev_tsc = 0; + + lcore_id = rte_lcore_id(); + qconf = &lcore_conf[lcore_id]; + + if (qconf->n_rx_queue == 0) { + RTE_LOG(INFO, L3FWD_POWER, "lcore %u has nothing to do\n", + lcore_id); + return 0; + } + + for (i = 0; i < qconf->n_rx_queue; i++) { + portid = qconf->rx_queue_list[i].port_id; + queueid = qconf->rx_queue_list[i].queue_id; + RTE_LOG(INFO, L3FWD_POWER, " -- lcoreid=%u portid=%u " + "rxqueueid=%hhu\n", lcore_id, portid, queueid); + } + + while (!is_done()) { + stats[lcore_id].nb_iteration_looped++; + + cur_tsc = rte_rdtsc(); + /* + * TX burst queue drain + */ + diff_tsc = cur_tsc - prev_tsc; + if (unlikely(diff_tsc > drain_tsc)) { + for (i = 0; i < qconf->n_tx_port; ++i) { + portid = qconf->tx_port_id[i]; + rte_eth_tx_buffer_flush(portid, + qconf->tx_queue_id[portid], + qconf->tx_buffer[portid]); + } + prev_tsc = cur_tsc; + } + + /* + * Read packet from RX queues + */ + for (i = 0; i < qconf->n_rx_queue; ++i) { + rx_queue = &(qconf->rx_queue_list[i]); + rx_queue->idle_hint = 0; + portid = rx_queue->port_id; + queueid = rx_queue->queue_id; + + nb_rx = rte_eth_rx_burst(portid, queueid, pkts_burst, + MAX_PKT_BURST); + + stats[lcore_id].nb_rx_processed += nb_rx; + + if (nb_rx == 0) { + + rte_power_empty_poll_stat_update(lcore_id); + + continue; + } else { + rte_power_poll_stat_update(lcore_id, nb_rx); + } + + + /* Prefetch first packets */ + for (j = 0; j < PREFETCH_OFFSET && j < nb_rx; j++) { + rte_prefetch0(rte_pktmbuf_mtod( + pkts_burst[j], void *)); + } + + /* Prefetch and forward already prefetched packets */ + for (j = 0; j < (nb_rx - PREFETCH_OFFSET); j++) { + rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[ + j + PREFETCH_OFFSET], + void *)); + l3fwd_simple_forward(pkts_burst[j], portid, + qconf); + } + + /* Forward remaining prefetched packets */ + for (; j < nb_rx; j++) { + l3fwd_simple_forward(pkts_burst[j], portid, + qconf); + } + + } + + } + + return 0; +} /* main processing loop */ static int main_loop(__attribute__((unused)) void *dummy) { struct rte_mbuf *pkts_burst[MAX_PKT_BURST]; unsigned lcore_id; - uint64_t prev_tsc, diff_tsc, cur_tsc; + uint64_t prev_tsc, diff_tsc, cur_tsc, tim_res_tsc, hz; uint64_t prev_tsc_power = 0, cur_tsc_power, diff_tsc_power; int i, j, nb_rx; - uint8_t portid, queueid; + uint8_t queueid; + uint16_t portid; struct lcore_conf *qconf; struct lcore_rx_queue *rx_queue; enum freq_scale_hint_t lcore_scaleup_hint; - uint32_t lcore_rx_idle_count = 0; uint32_t lcore_idle_hint = 0; + int intr_en = 0; const uint64_t drain_tsc = (rte_get_tsc_hz() + US_PER_S - 1) / US_PER_S * BURST_TX_DRAIN_US; prev_tsc = 0; + hz = rte_get_timer_hz(); + tim_res_tsc = hz/TIMER_NUMBER_PER_SECOND; lcore_id = rte_lcore_id(); qconf = &lcore_conf[lcore_id]; @@ -796,13 +1008,18 @@ main_loop(__attribute__((unused)) void *dummy) RTE_LOG(INFO, L3FWD_POWER, "entering main loop on lcore %u\n", lcore_id); for (i = 0; i < qconf->n_rx_queue; i++) { - portid = qconf->rx_queue_list[i].port_id; queueid = qconf->rx_queue_list[i].queue_id; - RTE_LOG(INFO, L3FWD_POWER, " -- lcoreid=%u portid=%hhu " + RTE_LOG(INFO, L3FWD_POWER, " -- lcoreid=%u portid=%u " "rxqueueid=%hhu\n", lcore_id, portid, queueid); } + /* add into event wait list */ + if (event_register(qconf) == 0) + intr_en = 1; + else + RTE_LOG(INFO, L3FWD_POWER, "RX interrupt won't enable.\n"); + while (1) { stats[lcore_id].nb_iteration_looped++; @@ -814,29 +1031,22 @@ main_loop(__attribute__((unused)) void *dummy) */ diff_tsc = cur_tsc - prev_tsc; if (unlikely(diff_tsc > drain_tsc)) { - - /* - * This could be optimized (use queueid instead of - * portid), but it is not called so often - */ - for (portid = 0; portid < RTE_MAX_ETHPORTS; portid++) { - if (qconf->tx_mbufs[portid].len == 0) - continue; - send_burst(&lcore_conf[lcore_id], - qconf->tx_mbufs[portid].len, - portid); - qconf->tx_mbufs[portid].len = 0; + for (i = 0; i < qconf->n_tx_port; ++i) { + portid = qconf->tx_port_id[i]; + rte_eth_tx_buffer_flush(portid, + qconf->tx_queue_id[portid], + qconf->tx_buffer[portid]); } - prev_tsc = cur_tsc; } diff_tsc_power = cur_tsc_power - prev_tsc_power; - if (diff_tsc_power > TIMER_RESOLUTION_CYCLES) { + if (diff_tsc_power > tim_res_tsc) { rte_timer_manage(); prev_tsc_power = cur_tsc_power; } +start_rx: /* * Read packet from RX queues */ @@ -850,6 +1060,7 @@ main_loop(__attribute__((unused)) void *dummy) nb_rx = rte_eth_rx_burst(portid, queueid, pkts_burst, MAX_PKT_BURST); + stats[lcore_id].nb_rx_processed += nb_rx; if (unlikely(nb_rx == 0)) { /** @@ -878,7 +1089,7 @@ main_loop(__attribute__((unused)) void *dummy) rx_queue->freq_up_hint = power_freq_scaleup_heuristic(lcore_id, portid, queueid); - } + } /* Prefetch first packets */ for (j = 0; j < PREFETCH_OFFSET && j < nb_rx; j++) { @@ -912,16 +1123,19 @@ main_loop(__attribute__((unused)) void *dummy) rx_queue->freq_up_hint; } - if (lcore_scaleup_hint == FREQ_HIGHEST) - rte_power_freq_max(lcore_id); - else if (lcore_scaleup_hint == FREQ_HIGHER) - rte_power_freq_up(lcore_id); + if (lcore_scaleup_hint == FREQ_HIGHEST) { + if (rte_power_freq_max) + rte_power_freq_max(lcore_id); + } else if (lcore_scaleup_hint == FREQ_HIGHER) { + if (rte_power_freq_up) + rte_power_freq_up(lcore_id); + } } else { /** * All Rx queues empty in recent consecutive polls, * sleep in a conservative manner, meaning sleep as - * less as possible. - */ + * less as possible. + */ for (i = 1, lcore_idle_hint = qconf->rx_queue_list[0].idle_hint; i < qconf->n_rx_queue; ++i) { @@ -930,16 +1144,25 @@ main_loop(__attribute__((unused)) void *dummy) lcore_idle_hint = rx_queue->idle_hint; } - if ( lcore_idle_hint < SLEEP_GEAR1_THRESHOLD) + if (lcore_idle_hint < SUSPEND_THRESHOLD) /** * execute "pause" instruction to avoid context - * switch for short sleep. - */ + * switch which generally take hundred of + * microseconds for short sleep. + */ rte_delay_us(lcore_idle_hint); - else - /* long sleep force runing thread to suspend */ - usleep(lcore_idle_hint); - + else { + /* suspend until rx interrupt trigges */ + if (intr_en) { + turn_on_intr(qconf); + sleep_until_rx_interrupt( + qconf->n_rx_queue); + /** + * start receiving packets immediately + */ + goto start_rx; + } + } stats[lcore_id].sleep_time += lcore_idle_hint; } } @@ -974,7 +1197,7 @@ check_lcore_params(void) } static int -check_port_config(const unsigned nb_ports) +check_port_config(void) { unsigned portid; uint16_t i; @@ -986,7 +1209,7 @@ check_port_config(const unsigned nb_ports) portid); return -1; } - if (portid >= nb_ports) { + if (!rte_eth_dev_is_valid_port(portid)) { printf("port %u is not present on the board\n", portid); return -1; @@ -996,7 +1219,7 @@ check_port_config(const unsigned nb_ports) } static uint8_t -get_port_n_rx_queues(const uint8_t port) +get_port_n_rx_queues(const uint16_t port) { int queue = -1; uint16_t i; @@ -1039,13 +1262,21 @@ print_usage(const char *prgname) { printf ("%s [EAL options] -- -p PORTMASK -P" " [--config (port,queue,lcore)[,(port,queue,lcore]]" + " [--high-perf-cores CORELIST" + " [--perf-config (port,queue,hi_perf,lcore_index)[,(port,queue,hi_perf,lcore_index]]" " [--enable-jumbo [--max-pkt-len PKTLEN]]\n" " -p PORTMASK: hexadecimal bitmask of ports to configure\n" " -P : enable promiscuous mode\n" " --config (port,queue,lcore): rx queues configuration\n" + " --high-perf-cores CORELIST: list of high performance cores\n" + " --perf-config: similar as config, cores specified as indices" + " for bins containing high or regular performance cores\n" " --no-numa: optional, disable numa awareness\n" " --enable-jumbo: enable jumbo frame" - " which max packet len is PKTLEN in decimal (64-9600)\n", + " which max packet len is PKTLEN in decimal (64-9600)\n" + " --parse-ptype: parse packet type by software\n" + " --empty-poll: enable empty poll detection" + " follow (training_flag, high_threshold, med_threshold)\n", prgname); } @@ -1138,6 +1369,56 @@ parse_config(const char *q_arg) return 0; } +static int +parse_ep_config(const char *q_arg) +{ + char s[256]; + const char *p = q_arg; + char *end; + int num_arg; + + char *str_fld[3]; + + int training_flag; + int med_edpi; + int hgh_edpi; + + ep_med_edpi = EMPTY_POLL_MED_THRESHOLD; + ep_hgh_edpi = EMPTY_POLL_MED_THRESHOLD; + + strlcpy(s, p, sizeof(s)); + + num_arg = rte_strsplit(s, sizeof(s), str_fld, 3, ','); + + empty_poll_train = false; + + if (num_arg == 0) + return 0; + + if (num_arg == 3) { + + training_flag = strtoul(str_fld[0], &end, 0); + med_edpi = strtoul(str_fld[1], &end, 0); + hgh_edpi = strtoul(str_fld[2], &end, 0); + + if (training_flag == 1) + empty_poll_train = true; + + if (med_edpi > 0) + ep_med_edpi = med_edpi; + + if (med_edpi > 0) + ep_hgh_edpi = hgh_edpi; + + } else { + + return -1; + } + + return 0; + +} +#define CMD_LINE_OPT_PARSE_PTYPE "parse-ptype" /* Parse the argument given in the command line of the application */ static int @@ -1146,17 +1427,22 @@ parse_args(int argc, char **argv) int opt, ret; char **argvopt; int option_index; + uint32_t limit; char *prgname = argv[0]; static struct option lgopts[] = { {"config", 1, 0, 0}, + {"perf-config", 1, 0, 0}, + {"high-perf-cores", 1, 0, 0}, {"no-numa", 0, 0, 0}, {"enable-jumbo", 0, 0, 0}, + {"empty-poll", 1, 0, 0}, + {CMD_LINE_OPT_PARSE_PTYPE, 0, 0, 0}, {NULL, 0, 0, 0} }; argvopt = argv; - while ((opt = getopt_long(argc, argvopt, "p:P", + while ((opt = getopt_long(argc, argvopt, "p:l:m:h:P", lgopts, &option_index)) != EOF) { switch (opt) { @@ -1173,7 +1459,18 @@ parse_args(int argc, char **argv) printf("Promiscuous mode selected\n"); promiscuous_on = 1; break; - + case 'l': + limit = parse_max_pkt_len(optarg); + freq_tlb[LOW] = limit; + break; + case 'm': + limit = parse_max_pkt_len(optarg); + freq_tlb[MED] = limit; + break; + case 'h': + limit = parse_max_pkt_len(optarg); + freq_tlb[HGH] = limit; + break; /* long options */ case 0: if (!strncmp(lgopts[option_index].name, "config", 6)) { @@ -1185,12 +1482,46 @@ parse_args(int argc, char **argv) } } + if (!strncmp(lgopts[option_index].name, + "perf-config", 11)) { + ret = parse_perf_config(optarg); + if (ret) { + printf("invalid perf-config\n"); + print_usage(prgname); + return -1; + } + } + + if (!strncmp(lgopts[option_index].name, + "high-perf-cores", 15)) { + ret = parse_perf_core_list(optarg); + if (ret) { + printf("invalid high-perf-cores\n"); + print_usage(prgname); + return -1; + } + } + if (!strncmp(lgopts[option_index].name, "no-numa", 7)) { printf("numa is disabled \n"); numa_on = 0; } + if (!strncmp(lgopts[option_index].name, + "empty-poll", 10)) { + printf("empty-poll is enabled\n"); + empty_poll_on = true; + ret = parse_ep_config(optarg); + + if (ret) { + printf("invalid empty poll config\n"); + print_usage(prgname); + return -1; + } + + } + if (!strncmp(lgopts[option_index].name, "enable-jumbo", 12)) { struct option lenopts = @@ -1198,11 +1529,14 @@ parse_args(int argc, char **argv) 0, 0}; printf("jumbo frame is enabled \n"); - port_conf.rxmode.jumbo_frame = 1; + port_conf.rxmode.offloads |= + DEV_RX_OFFLOAD_JUMBO_FRAME; + port_conf.txmode.offloads |= + DEV_TX_OFFLOAD_MULTI_SEGS; /** * if no max-pkt-len set, use the default value - * ETHER_MAX_LEN + * RTE_ETHER_MAX_LEN */ if (0 == getopt_long(argc, argvopt, "", &lenopts, &option_index)) { @@ -1221,6 +1555,13 @@ parse_args(int argc, char **argv) (unsigned int)port_conf.rxmode.max_rx_pkt_len); } + if (!strncmp(lgopts[option_index].name, + CMD_LINE_OPT_PARSE_PTYPE, + sizeof(CMD_LINE_OPT_PARSE_PTYPE))) { + printf("soft parse-ptype is enabled\n"); + parse_ptype = 1; + } + break; default: @@ -1233,20 +1574,16 @@ parse_args(int argc, char **argv) argv[optind-1] = prgname; ret = optind-1; - optind = 0; /* reset getopt lib */ + optind = 1; /* reset getopt lib */ return ret; } static void -print_ethaddr(const char *name, const struct ether_addr *eth_addr) +print_ethaddr(const char *name, const struct rte_ether_addr *eth_addr) { - printf ("%s%02X:%02X:%02X:%02X:%02X:%02X", name, - eth_addr->addr_bytes[0], - eth_addr->addr_bytes[1], - eth_addr->addr_bytes[2], - eth_addr->addr_bytes[3], - eth_addr->addr_bytes[4], - eth_addr->addr_bytes[5]); + char buf[RTE_ETHER_ADDR_FMT_SIZE]; + rte_ether_format_addr(buf, RTE_ETHER_ADDR_FMT_SIZE, eth_addr); + printf("%s%s", name, buf); } #if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH) @@ -1256,7 +1593,6 @@ setup_hash(int socketid) struct rte_hash_parameters ipv4_l3fwd_hash_params = { .name = NULL, .entries = L3FWD_HASH_ENTRIES, - .bucket_entries = 4, .key_len = sizeof(struct ipv4_5tuple), .hash_func = DEFAULT_HASH_FUNC, .hash_func_init_val = 0, @@ -1265,7 +1601,6 @@ setup_hash(int socketid) struct rte_hash_parameters ipv6_l3fwd_hash_params = { .name = NULL, .entries = L3FWD_HASH_ENTRIES, - .bucket_entries = 4, .key_len = sizeof(struct ipv6_5tuple), .hash_func = DEFAULT_HASH_FUNC, .hash_func_init_val = 0, @@ -1333,9 +1668,15 @@ setup_lpm(int socketid) char s[64]; /* create the LPM table */ + struct rte_lpm_config lpm_ipv4_config; + + lpm_ipv4_config.max_rules = IPV4_L3FWD_LPM_MAX_RULES; + lpm_ipv4_config.number_tbl8s = 256; + lpm_ipv4_config.flags = 0; + snprintf(s, sizeof(s), "IPV4_L3FWD_LPM_%d", socketid); - ipv4_l3fwd_lookup_struct[socketid] = rte_lpm_create(s, socketid, - IPV4_L3FWD_LPM_MAX_RULES, 0); + ipv4_l3fwd_lookup_struct[socketid] = + rte_lpm_create(s, socketid, &lpm_ipv4_config); if (ipv4_l3fwd_lookup_struct[socketid] == NULL) rte_exit(EXIT_FAILURE, "Unable to create the l3fwd LPM table" " on socket %d\n", socketid); @@ -1386,12 +1727,10 @@ init_mem(unsigned nb_mbuf) if (pktmbuf_pool[socketid] == NULL) { snprintf(s, sizeof(s), "mbuf_pool_%d", socketid); pktmbuf_pool[socketid] = - rte_mempool_create(s, nb_mbuf, - MBUF_SIZE, MEMPOOL_CACHE_SIZE, - sizeof(struct rte_pktmbuf_pool_private), - rte_pktmbuf_pool_init, NULL, - rte_pktmbuf_init, NULL, - socketid, 0); + rte_pktmbuf_pool_create(s, nb_mbuf, + MEMPOOL_CACHE_SIZE, 0, + RTE_MBUF_DEFAULT_BUF_SIZE, + socketid); if (pktmbuf_pool[socketid] == NULL) rte_exit(EXIT_FAILURE, "Cannot init mbuf pool on socket %d\n", @@ -1417,18 +1756,19 @@ init_mem(unsigned nb_mbuf) /* Check the link status of all ports in up to 9s, and print them finally */ static void -check_all_ports_link_status(uint8_t port_num, uint32_t port_mask) +check_all_ports_link_status(uint32_t port_mask) { #define CHECK_INTERVAL 100 /* 100ms */ #define MAX_CHECK_TIME 90 /* 9s (90 * 100ms) in total */ - uint8_t portid, count, all_ports_up, print_flag = 0; + uint8_t count, all_ports_up, print_flag = 0; + uint16_t portid; struct rte_eth_link link; printf("\nChecking link status"); fflush(stdout); for (count = 0; count <= MAX_CHECK_TIME; count++) { all_ports_up = 1; - for (portid = 0; portid < port_num; portid++) { + RTE_ETH_FOREACH_DEV(portid) { if ((port_mask & (1 << portid)) == 0) continue; memset(&link, 0, sizeof(link)); @@ -1447,7 +1787,7 @@ check_all_ports_link_status(uint8_t port_num, uint32_t port_mask) continue; } /* clear all_ports_up flag if any link down */ - if (link.link_status == 0) { + if (link.link_status == ETH_LINK_DOWN) { all_ports_up = 0; break; } @@ -1470,19 +1810,135 @@ check_all_ports_link_status(uint8_t port_num, uint32_t port_mask) } } +static int check_ptype(uint16_t portid) +{ + int i, ret; + int ptype_l3_ipv4 = 0; +#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH) + int ptype_l3_ipv6 = 0; +#endif + uint32_t ptype_mask = RTE_PTYPE_L3_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) { + if (ptypes[i] & RTE_PTYPE_L3_IPV4) + ptype_l3_ipv4 = 1; +#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH) + if (ptypes[i] & RTE_PTYPE_L3_IPV6) + ptype_l3_ipv6 = 1; +#endif + } + + if (ptype_l3_ipv4 == 0) + printf("port %d cannot parse RTE_PTYPE_L3_IPV4\n", portid); + +#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH) + if (ptype_l3_ipv6 == 0) + printf("port %d cannot parse RTE_PTYPE_L3_IPV6\n", portid); +#endif + +#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM) + if (ptype_l3_ipv4) +#else /* APP_LOOKUP_EXACT_MATCH */ + if (ptype_l3_ipv4 && ptype_l3_ipv6) +#endif + return 1; + + return 0; + +} + +static int +init_power_library(void) +{ + int ret = 0, lcore_id; + for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) { + if (rte_lcore_is_enabled(lcore_id)) { + /* init power management library */ + ret = rte_power_init(lcore_id); + if (ret) + RTE_LOG(ERR, POWER, + "Library initialization failed on core %u\n", + lcore_id); + } + } + return ret; +} +static void +empty_poll_setup_timer(void) +{ + int lcore_id = rte_lcore_id(); + uint64_t hz = rte_get_timer_hz(); + + struct ep_params *ep_ptr = ep_params; + + ep_ptr->interval_ticks = hz / INTERVALS_PER_SECOND; + + rte_timer_reset_sync(&ep_ptr->timer0, + ep_ptr->interval_ticks, + PERIODICAL, + lcore_id, + rte_empty_poll_detection, + (void *)ep_ptr); + +} +static int +launch_timer(unsigned int lcore_id) +{ + int64_t prev_tsc = 0, cur_tsc, diff_tsc, cycles_10ms; + + RTE_SET_USED(lcore_id); + + + if (rte_get_master_lcore() != lcore_id) { + rte_panic("timer on lcore:%d which is not master core:%d\n", + lcore_id, + rte_get_master_lcore()); + } + + RTE_LOG(INFO, POWER, "Bring up the Timer\n"); + + empty_poll_setup_timer(); + + cycles_10ms = rte_get_timer_hz() / 100; + + while (!is_done()) { + cur_tsc = rte_rdtsc(); + diff_tsc = cur_tsc - prev_tsc; + if (diff_tsc > cycles_10ms) { + rte_timer_manage(); + prev_tsc = cur_tsc; + cycles_10ms = rte_get_timer_hz() / 100; + } + } + + RTE_LOG(INFO, POWER, "Timer_subsystem is done\n"); + + return 0; +} + + int -MAIN(int argc, char **argv) +main(int argc, char **argv) { struct lcore_conf *qconf; struct rte_eth_dev_info dev_info; struct rte_eth_txconf *txconf; int ret; - unsigned nb_ports; + uint16_t nb_ports; uint16_t queueid; unsigned lcore_id; uint64_t hz; uint32_t n_tx_queue, nb_lcores; - uint8_t portid, nb_rx_queue, queue, socketid; + uint32_t dev_rxq_num, dev_txq_num; + uint8_t nb_rx_queue, queue, socketid; + uint16_t portid; /* catch SIGINT and restore cpufreq governor to ondemand */ signal(SIGINT, signal_exit_now); @@ -1502,6 +1958,12 @@ MAIN(int argc, char **argv) if (ret < 0) rte_exit(EXIT_FAILURE, "Invalid L3FWD parameters\n"); + if (init_power_library()) + RTE_LOG(ERR, L3FWD_POWER, "init_power_library failed\n"); + + if (update_lcore_params() < 0) + rte_exit(EXIT_FAILURE, "update_lcore_params failed\n"); + if (check_lcore_params() < 0) rte_exit(EXIT_FAILURE, "check_lcore_params failed\n"); @@ -1509,18 +1971,17 @@ MAIN(int argc, char **argv) if (ret < 0) rte_exit(EXIT_FAILURE, "init_lcore_rx_queues failed\n"); + nb_ports = rte_eth_dev_count_avail(); - nb_ports = rte_eth_dev_count(); - if (nb_ports > RTE_MAX_ETHPORTS) - nb_ports = RTE_MAX_ETHPORTS; - - if (check_port_config(nb_ports) < 0) + if (check_port_config() < 0) rte_exit(EXIT_FAILURE, "check_port_config failed\n"); nb_lcores = rte_lcore_count(); /* initialize all ports */ - for (portid = 0; portid < nb_ports; portid++) { + RTE_ETH_FOREACH_DEV(portid) { + struct rte_eth_conf local_port_conf = port_conf; + /* skip ports that are not enabled */ if ((enabled_port_mask & (1 << portid)) == 0) { printf("\nSkipping disabled port %d\n", portid); @@ -1531,18 +1992,53 @@ MAIN(int argc, char **argv) printf("Initializing port %d ... ", portid ); fflush(stdout); + rte_eth_dev_info_get(portid, &dev_info); + dev_rxq_num = dev_info.max_rx_queues; + dev_txq_num = dev_info.max_tx_queues; + nb_rx_queue = get_port_n_rx_queues(portid); + if (nb_rx_queue > dev_rxq_num) + rte_exit(EXIT_FAILURE, + "Cannot configure not existed rxq: " + "port=%d\n", portid); + n_tx_queue = nb_lcores; - if (n_tx_queue > MAX_TX_QUEUE_PER_PORT) - n_tx_queue = MAX_TX_QUEUE_PER_PORT; + if (n_tx_queue > dev_txq_num) + n_tx_queue = dev_txq_num; printf("Creating queues: nb_rxq=%d nb_txq=%u... ", nb_rx_queue, (unsigned)n_tx_queue ); + /* If number of Rx queue is 0, no need to enable Rx interrupt */ + if (nb_rx_queue == 0) + local_port_conf.intr_conf.rxq = 0; + rte_eth_dev_info_get(portid, &dev_info); + if (dev_info.tx_offload_capa & DEV_TX_OFFLOAD_MBUF_FAST_FREE) + local_port_conf.txmode.offloads |= + DEV_TX_OFFLOAD_MBUF_FAST_FREE; + + local_port_conf.rx_adv_conf.rss_conf.rss_hf &= + dev_info.flow_type_rss_offloads; + if (local_port_conf.rx_adv_conf.rss_conf.rss_hf != + port_conf.rx_adv_conf.rss_conf.rss_hf) { + printf("Port %u modified RSS hash function based on hardware support," + "requested:%#"PRIx64" configured:%#"PRIx64"\n", + portid, + port_conf.rx_adv_conf.rss_conf.rss_hf, + local_port_conf.rx_adv_conf.rss_conf.rss_hf); + } + ret = rte_eth_dev_configure(portid, nb_rx_queue, - (uint16_t)n_tx_queue, &port_conf); + (uint16_t)n_tx_queue, &local_port_conf); if (ret < 0) rte_exit(EXIT_FAILURE, "Cannot configure device: " "err=%d, port=%d\n", ret, portid); + ret = rte_eth_dev_adjust_nb_rx_tx_desc(portid, &nb_rxd, + &nb_txd); + if (ret < 0) + rte_exit(EXIT_FAILURE, + "Cannot adjust number of descriptors: err=%d, port=%d\n", + ret, portid); + rte_eth_macaddr_get(portid, &ports_eth_addr[portid]); print_ethaddr(" Address:", &ports_eth_addr[portid]); printf(", "); @@ -1552,12 +2048,31 @@ MAIN(int argc, char **argv) if (ret < 0) rte_exit(EXIT_FAILURE, "init_mem failed\n"); + for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) { + if (rte_lcore_is_enabled(lcore_id) == 0) + continue; + + /* Initialize TX buffers */ + qconf = &lcore_conf[lcore_id]; + qconf->tx_buffer[portid] = rte_zmalloc_socket("tx_buffer", + RTE_ETH_TX_BUFFER_SIZE(MAX_PKT_BURST), 0, + rte_eth_dev_socket_id(portid)); + if (qconf->tx_buffer[portid] == NULL) + rte_exit(EXIT_FAILURE, "Can't allocate tx buffer for port %u\n", + portid); + + rte_eth_tx_buffer_init(qconf->tx_buffer[portid], MAX_PKT_BURST); + } + /* init one TX queue per couple (lcore,port) */ queueid = 0; for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) { if (rte_lcore_is_enabled(lcore_id) == 0) continue; + if (queueid >= dev_txq_num) + continue; + if (numa_on) socketid = \ (uint8_t)rte_lcore_to_socket_id(lcore_id); @@ -1567,10 +2082,8 @@ MAIN(int argc, char **argv) printf("txq=%u,%d,%d ", lcore_id, queueid, socketid); fflush(stdout); - rte_eth_dev_info_get(portid, &dev_info); txconf = &dev_info.default_txconf; - if (port_conf.rxmode.jumbo_frame) - txconf->txq_flags = 0; + txconf->offloads = local_port_conf.txmode.offloads; ret = rte_eth_tx_queue_setup(portid, queueid, nb_txd, socketid, txconf); if (ret < 0) @@ -1581,6 +2094,9 @@ MAIN(int argc, char **argv) qconf = &lcore_conf[lcore_id]; qconf->tx_queue_id[portid] = queueid; queueid++; + + qconf->tx_port_id[qconf->n_tx_port] = portid; + qconf->n_tx_port++; } printf("\n"); } @@ -1589,26 +2105,28 @@ MAIN(int argc, char **argv) if (rte_lcore_is_enabled(lcore_id) == 0) continue; - /* init power management library */ - ret = rte_power_init(lcore_id); - if (ret) - rte_exit(EXIT_FAILURE, "Power management library " - "initialization failed on core%u\n", lcore_id); - - /* init timer structures for each enabled lcore */ - rte_timer_init(&power_timers[lcore_id]); - hz = rte_get_timer_hz(); - rte_timer_reset(&power_timers[lcore_id], - hz/TIMER_NUMBER_PER_SECOND, SINGLE, lcore_id, - power_timer_cb, NULL); - + if (empty_poll_on == false) { + /* init timer structures for each enabled lcore */ + rte_timer_init(&power_timers[lcore_id]); + hz = rte_get_timer_hz(); + rte_timer_reset(&power_timers[lcore_id], + hz/TIMER_NUMBER_PER_SECOND, + SINGLE, lcore_id, + power_timer_cb, NULL); + } qconf = &lcore_conf[lcore_id]; printf("\nInitializing rx queues on lcore %u ... ", lcore_id ); fflush(stdout); /* init RX queues */ for(queue = 0; queue < qconf->n_rx_queue; ++queue) { + struct rte_eth_rxconf rxq_conf; + struct rte_eth_dev *dev; + struct rte_eth_conf *conf; + portid = qconf->rx_queue_list[queue].port_id; queueid = qconf->rx_queue_list[queue].queue_id; + dev = &rte_eth_devices[portid]; + conf = &dev->data->dev_conf; if (numa_on) socketid = \ @@ -1619,20 +2137,31 @@ MAIN(int argc, char **argv) printf("rxq=%d,%d,%d ", portid, queueid, socketid); fflush(stdout); + rte_eth_dev_info_get(portid, &dev_info); + rxq_conf = dev_info.default_rxconf; + rxq_conf.offloads = conf->rxmode.offloads; ret = rte_eth_rx_queue_setup(portid, queueid, nb_rxd, - socketid, NULL, + socketid, &rxq_conf, pktmbuf_pool[socketid]); if (ret < 0) rte_exit(EXIT_FAILURE, "rte_eth_rx_queue_setup: err=%d, " "port=%d\n", ret, portid); + + if (parse_ptype) { + if (add_cb_parse_ptype(portid, queueid) < 0) + rte_exit(EXIT_FAILURE, + "Fail to add ptype cb\n"); + } else if (!check_ptype(portid)) + rte_exit(EXIT_FAILURE, + "PMD can not provide needed ptypes\n"); } } printf("\n"); /* start ports */ - for (portid = 0; portid < nb_ports; portid++) { + RTE_ETH_FOREACH_DEV(portid) { if ((enabled_port_mask & (1 << portid)) == 0) { continue; } @@ -1641,7 +2170,6 @@ MAIN(int argc, char **argv) if (ret < 0) rte_exit(EXIT_FAILURE, "rte_eth_dev_start: err=%d, " "port=%d\n", ret, portid); - /* * If enabled, put device in promiscuous mode. * This allows IO forwarding mode to forward packets @@ -1650,16 +2178,49 @@ MAIN(int argc, char **argv) */ if (promiscuous_on) rte_eth_promiscuous_enable(portid); + /* initialize spinlock for each port */ + rte_spinlock_init(&(locks[portid])); + } + + check_all_ports_link_status(enabled_port_mask); + + if (empty_poll_on == true) { + + if (empty_poll_train) { + policy.state = TRAINING; + } else { + policy.state = MED_NORMAL; + policy.med_base_edpi = ep_med_edpi; + policy.hgh_base_edpi = ep_hgh_edpi; + } + + ret = rte_power_empty_poll_stat_init(&ep_params, + freq_tlb, + &policy); + if (ret < 0) + rte_exit(EXIT_FAILURE, "empty poll init failed"); } - check_all_ports_link_status((uint8_t)nb_ports, enabled_port_mask); /* launch per-lcore init on every lcore */ - rte_eal_mp_remote_launch(main_loop, NULL, CALL_MASTER); + if (empty_poll_on == false) { + rte_eal_mp_remote_launch(main_loop, NULL, CALL_MASTER); + } else { + empty_poll_stop = false; + rte_eal_mp_remote_launch(main_empty_poll_loop, NULL, + SKIP_MASTER); + } + + if (empty_poll_on == true) + launch_timer(rte_lcore_id()); + RTE_LCORE_FOREACH_SLAVE(lcore_id) { if (rte_eal_wait_lcore(lcore_id) < 0) return -1; } + if (empty_poll_on) + rte_power_empty_poll_stat_free(); + return 0; }