diff options
Diffstat (limited to '')
31 files changed, 10444 insertions, 0 deletions
diff --git a/src/seastar/dpdk/examples/l3fwd-acl/Makefile b/src/seastar/dpdk/examples/l3fwd-acl/Makefile new file mode 100644 index 000000000..fc236f129 --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd-acl/Makefile @@ -0,0 +1,61 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2010-2014 Intel Corporation + +# binary name +APP = l3fwd-acl + +# all source are stored in SRCS-y +SRCS-y := main.c + +# Build using pkg-config variables if possible +$(shell pkg-config --exists libdpdk) +ifeq ($(.SHELLSTATUS),0) + +all: shared +.PHONY: shared static +shared: build/$(APP)-shared + ln -sf $(APP)-shared build/$(APP) +static: build/$(APP)-static + ln -sf $(APP)-static build/$(APP) + +PC_FILE := $(shell pkg-config --path libdpdk) +CFLAGS += -O3 $(shell pkg-config --cflags libdpdk) +LDFLAGS_SHARED = $(shell pkg-config --libs libdpdk) +LDFLAGS_STATIC = -Wl,-Bstatic $(shell pkg-config --static --libs libdpdk) + +build/$(APP)-shared: $(SRCS-y) Makefile $(PC_FILE) | build + $(CC) $(CFLAGS) $(SRCS-y) -o $@ $(LDFLAGS) $(LDFLAGS_SHARED) + +build/$(APP)-static: $(SRCS-y) Makefile $(PC_FILE) | build + $(CC) $(CFLAGS) $(SRCS-y) -o $@ $(LDFLAGS) $(LDFLAGS_STATIC) + +build: + @mkdir -p $@ + +.PHONY: clean +clean: + rm -f build/$(APP) build/$(APP)-static build/$(APP)-shared + rmdir --ignore-fail-on-non-empty build + +else # Build using legacy build system + +ifeq ($(RTE_SDK),) +$(error "Please define RTE_SDK environment variable") +endif + +# Default target, detect a build directory, by looking for a path with a .config +RTE_TARGET ?= $(notdir $(abspath $(dir $(firstword $(wildcard $(RTE_SDK)/*/.config))))) + +include $(RTE_SDK)/mk/rte.vars.mk + +CFLAGS += -O3 +CFLAGS += $(WERROR_FLAGS) + +# workaround for a gcc bug with noreturn attribute +# http://gcc.gnu.org/bugzilla/show_bug.cgi?id=12603 +ifeq ($(CONFIG_RTE_TOOLCHAIN_GCC),y) +CFLAGS_main.o += -Wno-return-type +endif + +include $(RTE_SDK)/mk/rte.extapp.mk +endif diff --git a/src/seastar/dpdk/examples/l3fwd-acl/main.c b/src/seastar/dpdk/examples/l3fwd-acl/main.c new file mode 100644 index 000000000..a322ce4f2 --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd-acl/main.c @@ -0,0 +1,2086 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2010-2016 Intel Corporation + */ + +#include <stdio.h> +#include <stdlib.h> +#include <stdint.h> +#include <inttypes.h> +#include <sys/types.h> +#include <string.h> +#include <sys/queue.h> +#include <stdarg.h> +#include <errno.h> +#include <getopt.h> + +#include <rte_common.h> +#include <rte_byteorder.h> +#include <rte_log.h> +#include <rte_memory.h> +#include <rte_memcpy.h> +#include <rte_eal.h> +#include <rte_launch.h> +#include <rte_atomic.h> +#include <rte_cycles.h> +#include <rte_prefetch.h> +#include <rte_lcore.h> +#include <rte_per_lcore.h> +#include <rte_branch_prediction.h> +#include <rte_interrupts.h> +#include <rte_random.h> +#include <rte_debug.h> +#include <rte_ether.h> +#include <rte_ethdev.h> +#include <rte_mempool.h> +#include <rte_mbuf.h> +#include <rte_ip.h> +#include <rte_tcp.h> +#include <rte_udp.h> +#include <rte_string_fns.h> +#include <rte_acl.h> + +#if RTE_LOG_DP_LEVEL >= RTE_LOG_DEBUG +#define L3FWDACL_DEBUG +#endif +#define DO_RFC_1812_CHECKS + +#define RTE_LOGTYPE_L3FWD RTE_LOGTYPE_USER1 + +#define MAX_JUMBO_PKT_LEN 9600 + +#define MEMPOOL_CACHE_SIZE 256 + +/* + * 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 per lcore and mtable per port per lcore. + * RTE_MAX is used to ensure that NB_MBUF never goes below a + * minimum value of 8192 + */ + +#define NB_MBUF RTE_MAX(\ + (nb_ports * nb_rx_queue * nb_rxd + \ + nb_ports * nb_lcores * MAX_PKT_BURST + \ + nb_ports * n_tx_queue * nb_txd + \ + nb_lcores * MEMPOOL_CACHE_SIZE), \ + (unsigned)8192) + +#define MAX_PKT_BURST 32 +#define BURST_TX_DRAIN_US 100 /* TX drain every ~100us */ + +#define NB_SOCKETS 8 + +/* Configure how many packets ahead to prefetch, when reading packets */ +#define PREFETCH_OFFSET 3 + +/* + * Configurable number of RX/TX ring descriptors + */ +#define RTE_TEST_RX_DESC_DEFAULT 1024 +#define RTE_TEST_TX_DESC_DEFAULT 1024 +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]; + +/* mask of enabled ports */ +static uint32_t enabled_port_mask; +static int promiscuous_on; /**< Ports set in promiscuous mode off by default. */ +static int numa_on = 1; /**< NUMA is enabled by default. */ + +struct lcore_rx_queue { + uint16_t port_id; + uint8_t queue_id; +} __rte_cache_aligned; + +#define MAX_RX_QUEUE_PER_LCORE 16 +#define MAX_TX_QUEUE_PER_PORT RTE_MAX_ETHPORTS +#define MAX_RX_QUEUE_PER_PORT 128 + +#define MAX_LCORE_PARAMS 1024 +struct lcore_params { + uint16_t port_id; + uint8_t queue_id; + uint8_t lcore_id; +} __rte_cache_aligned; + +static struct lcore_params lcore_params_array[MAX_LCORE_PARAMS]; +static struct lcore_params lcore_params_array_default[] = { + {0, 0, 2}, + {0, 1, 2}, + {0, 2, 2}, + {1, 0, 2}, + {1, 1, 2}, + {1, 2, 2}, + {2, 0, 2}, + {3, 0, 3}, + {3, 1, 3}, +}; + +static struct lcore_params *lcore_params = lcore_params_array_default; +static 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, + .split_hdr_size = 0, + .offloads = DEV_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, + }, + }, + .txmode = { + .mq_mode = ETH_MQ_TX_NONE, + }, +}; + +static struct rte_mempool *pktmbuf_pool[NB_SOCKETS]; + +/***********************start of ACL part******************************/ +#ifdef DO_RFC_1812_CHECKS +static inline int +is_valid_ipv4_pkt(struct ipv4_hdr *pkt, uint32_t link_len); +#endif +static inline void +send_single_packet(struct rte_mbuf *m, uint16_t port); + +#define MAX_ACL_RULE_NUM 100000 +#define DEFAULT_MAX_CATEGORIES 1 +#define L3FWD_ACL_IPV4_NAME "l3fwd-acl-ipv4" +#define L3FWD_ACL_IPV6_NAME "l3fwd-acl-ipv6" +#define ACL_LEAD_CHAR ('@') +#define ROUTE_LEAD_CHAR ('R') +#define COMMENT_LEAD_CHAR ('#') +#define OPTION_CONFIG "config" +#define OPTION_NONUMA "no-numa" +#define OPTION_ENBJMO "enable-jumbo" +#define OPTION_RULE_IPV4 "rule_ipv4" +#define OPTION_RULE_IPV6 "rule_ipv6" +#define OPTION_SCALAR "scalar" +#define ACL_DENY_SIGNATURE 0xf0000000 +#define RTE_LOGTYPE_L3FWDACL RTE_LOGTYPE_USER3 +#define acl_log(format, ...) RTE_LOG(ERR, L3FWDACL, format, ##__VA_ARGS__) +#define uint32_t_to_char(ip, a, b, c, d) do {\ + *a = (unsigned char)(ip >> 24 & 0xff);\ + *b = (unsigned char)(ip >> 16 & 0xff);\ + *c = (unsigned char)(ip >> 8 & 0xff);\ + *d = (unsigned char)(ip & 0xff);\ + } while (0) +#define OFF_ETHHEAD (sizeof(struct ether_hdr)) +#define OFF_IPV42PROTO (offsetof(struct ipv4_hdr, next_proto_id)) +#define OFF_IPV62PROTO (offsetof(struct ipv6_hdr, proto)) +#define MBUF_IPV4_2PROTO(m) \ + rte_pktmbuf_mtod_offset((m), uint8_t *, OFF_ETHHEAD + OFF_IPV42PROTO) +#define MBUF_IPV6_2PROTO(m) \ + rte_pktmbuf_mtod_offset((m), uint8_t *, OFF_ETHHEAD + OFF_IPV62PROTO) + +#define GET_CB_FIELD(in, fd, base, lim, dlm) do { \ + unsigned long val; \ + char *end; \ + errno = 0; \ + val = strtoul((in), &end, (base)); \ + if (errno != 0 || end[0] != (dlm) || val > (lim)) \ + return -EINVAL; \ + (fd) = (typeof(fd))val; \ + (in) = end + 1; \ +} while (0) + +/* + * ACL rules should have higher priorities than route ones to ensure ACL rule + * always be found when input packets have multi-matches in the database. + * A exception case is performance measure, which can define route rules with + * higher priority and route rules will always be returned in each lookup. + * Reserve range from ACL_RULE_PRIORITY_MAX + 1 to + * RTE_ACL_MAX_PRIORITY for route entries in performance measure + */ +#define ACL_RULE_PRIORITY_MAX 0x10000000 + +/* + * Forward port info save in ACL lib starts from 1 + * since ACL assume 0 is invalid. + * So, need add 1 when saving and minus 1 when forwarding packets. + */ +#define FWD_PORT_SHIFT 1 + +/* + * Rule and trace formats definitions. + */ + +enum { + PROTO_FIELD_IPV4, + SRC_FIELD_IPV4, + DST_FIELD_IPV4, + SRCP_FIELD_IPV4, + DSTP_FIELD_IPV4, + NUM_FIELDS_IPV4 +}; + +/* + * That effectively defines order of IPV4VLAN classifications: + * - PROTO + * - VLAN (TAG and DOMAIN) + * - SRC IP ADDRESS + * - DST IP ADDRESS + * - PORTS (SRC and DST) + */ +enum { + RTE_ACL_IPV4VLAN_PROTO, + RTE_ACL_IPV4VLAN_VLAN, + RTE_ACL_IPV4VLAN_SRC, + RTE_ACL_IPV4VLAN_DST, + RTE_ACL_IPV4VLAN_PORTS, + RTE_ACL_IPV4VLAN_NUM +}; + +struct rte_acl_field_def ipv4_defs[NUM_FIELDS_IPV4] = { + { + .type = RTE_ACL_FIELD_TYPE_BITMASK, + .size = sizeof(uint8_t), + .field_index = PROTO_FIELD_IPV4, + .input_index = RTE_ACL_IPV4VLAN_PROTO, + .offset = 0, + }, + { + .type = RTE_ACL_FIELD_TYPE_MASK, + .size = sizeof(uint32_t), + .field_index = SRC_FIELD_IPV4, + .input_index = RTE_ACL_IPV4VLAN_SRC, + .offset = offsetof(struct ipv4_hdr, src_addr) - + offsetof(struct ipv4_hdr, next_proto_id), + }, + { + .type = RTE_ACL_FIELD_TYPE_MASK, + .size = sizeof(uint32_t), + .field_index = DST_FIELD_IPV4, + .input_index = RTE_ACL_IPV4VLAN_DST, + .offset = offsetof(struct ipv4_hdr, dst_addr) - + offsetof(struct ipv4_hdr, next_proto_id), + }, + { + .type = RTE_ACL_FIELD_TYPE_RANGE, + .size = sizeof(uint16_t), + .field_index = SRCP_FIELD_IPV4, + .input_index = RTE_ACL_IPV4VLAN_PORTS, + .offset = sizeof(struct ipv4_hdr) - + offsetof(struct ipv4_hdr, next_proto_id), + }, + { + .type = RTE_ACL_FIELD_TYPE_RANGE, + .size = sizeof(uint16_t), + .field_index = DSTP_FIELD_IPV4, + .input_index = RTE_ACL_IPV4VLAN_PORTS, + .offset = sizeof(struct ipv4_hdr) - + offsetof(struct ipv4_hdr, next_proto_id) + + sizeof(uint16_t), + }, +}; + +#define IPV6_ADDR_LEN 16 +#define IPV6_ADDR_U16 (IPV6_ADDR_LEN / sizeof(uint16_t)) +#define IPV6_ADDR_U32 (IPV6_ADDR_LEN / sizeof(uint32_t)) + +enum { + PROTO_FIELD_IPV6, + SRC1_FIELD_IPV6, + SRC2_FIELD_IPV6, + SRC3_FIELD_IPV6, + SRC4_FIELD_IPV6, + DST1_FIELD_IPV6, + DST2_FIELD_IPV6, + DST3_FIELD_IPV6, + DST4_FIELD_IPV6, + SRCP_FIELD_IPV6, + DSTP_FIELD_IPV6, + NUM_FIELDS_IPV6 +}; + +struct rte_acl_field_def ipv6_defs[NUM_FIELDS_IPV6] = { + { + .type = RTE_ACL_FIELD_TYPE_BITMASK, + .size = sizeof(uint8_t), + .field_index = PROTO_FIELD_IPV6, + .input_index = PROTO_FIELD_IPV6, + .offset = 0, + }, + { + .type = RTE_ACL_FIELD_TYPE_MASK, + .size = sizeof(uint32_t), + .field_index = SRC1_FIELD_IPV6, + .input_index = SRC1_FIELD_IPV6, + .offset = offsetof(struct ipv6_hdr, src_addr) - + offsetof(struct ipv6_hdr, proto), + }, + { + .type = RTE_ACL_FIELD_TYPE_MASK, + .size = sizeof(uint32_t), + .field_index = SRC2_FIELD_IPV6, + .input_index = SRC2_FIELD_IPV6, + .offset = offsetof(struct ipv6_hdr, src_addr) - + offsetof(struct ipv6_hdr, proto) + sizeof(uint32_t), + }, + { + .type = RTE_ACL_FIELD_TYPE_MASK, + .size = sizeof(uint32_t), + .field_index = SRC3_FIELD_IPV6, + .input_index = SRC3_FIELD_IPV6, + .offset = offsetof(struct ipv6_hdr, src_addr) - + offsetof(struct ipv6_hdr, proto) + 2 * sizeof(uint32_t), + }, + { + .type = RTE_ACL_FIELD_TYPE_MASK, + .size = sizeof(uint32_t), + .field_index = SRC4_FIELD_IPV6, + .input_index = SRC4_FIELD_IPV6, + .offset = offsetof(struct ipv6_hdr, src_addr) - + offsetof(struct ipv6_hdr, proto) + 3 * sizeof(uint32_t), + }, + { + .type = RTE_ACL_FIELD_TYPE_MASK, + .size = sizeof(uint32_t), + .field_index = DST1_FIELD_IPV6, + .input_index = DST1_FIELD_IPV6, + .offset = offsetof(struct ipv6_hdr, dst_addr) + - offsetof(struct ipv6_hdr, proto), + }, + { + .type = RTE_ACL_FIELD_TYPE_MASK, + .size = sizeof(uint32_t), + .field_index = DST2_FIELD_IPV6, + .input_index = DST2_FIELD_IPV6, + .offset = offsetof(struct ipv6_hdr, dst_addr) - + offsetof(struct ipv6_hdr, proto) + sizeof(uint32_t), + }, + { + .type = RTE_ACL_FIELD_TYPE_MASK, + .size = sizeof(uint32_t), + .field_index = DST3_FIELD_IPV6, + .input_index = DST3_FIELD_IPV6, + .offset = offsetof(struct ipv6_hdr, dst_addr) - + offsetof(struct ipv6_hdr, proto) + 2 * sizeof(uint32_t), + }, + { + .type = RTE_ACL_FIELD_TYPE_MASK, + .size = sizeof(uint32_t), + .field_index = DST4_FIELD_IPV6, + .input_index = DST4_FIELD_IPV6, + .offset = offsetof(struct ipv6_hdr, dst_addr) - + offsetof(struct ipv6_hdr, proto) + 3 * sizeof(uint32_t), + }, + { + .type = RTE_ACL_FIELD_TYPE_RANGE, + .size = sizeof(uint16_t), + .field_index = SRCP_FIELD_IPV6, + .input_index = SRCP_FIELD_IPV6, + .offset = sizeof(struct ipv6_hdr) - + offsetof(struct ipv6_hdr, proto), + }, + { + .type = RTE_ACL_FIELD_TYPE_RANGE, + .size = sizeof(uint16_t), + .field_index = DSTP_FIELD_IPV6, + .input_index = SRCP_FIELD_IPV6, + .offset = sizeof(struct ipv6_hdr) - + offsetof(struct ipv6_hdr, proto) + sizeof(uint16_t), + }, +}; + +enum { + CB_FLD_SRC_ADDR, + CB_FLD_DST_ADDR, + CB_FLD_SRC_PORT_LOW, + CB_FLD_SRC_PORT_DLM, + CB_FLD_SRC_PORT_HIGH, + CB_FLD_DST_PORT_LOW, + CB_FLD_DST_PORT_DLM, + CB_FLD_DST_PORT_HIGH, + CB_FLD_PROTO, + CB_FLD_USERDATA, + CB_FLD_NUM, +}; + +RTE_ACL_RULE_DEF(acl4_rule, RTE_DIM(ipv4_defs)); +RTE_ACL_RULE_DEF(acl6_rule, RTE_DIM(ipv6_defs)); + +struct acl_search_t { + const uint8_t *data_ipv4[MAX_PKT_BURST]; + struct rte_mbuf *m_ipv4[MAX_PKT_BURST]; + uint32_t res_ipv4[MAX_PKT_BURST]; + int num_ipv4; + + const uint8_t *data_ipv6[MAX_PKT_BURST]; + struct rte_mbuf *m_ipv6[MAX_PKT_BURST]; + uint32_t res_ipv6[MAX_PKT_BURST]; + int num_ipv6; +}; + +static struct { + char mapped[NB_SOCKETS]; + struct rte_acl_ctx *acx_ipv4[NB_SOCKETS]; + struct rte_acl_ctx *acx_ipv6[NB_SOCKETS]; +#ifdef L3FWDACL_DEBUG + struct acl4_rule *rule_ipv4; + struct acl6_rule *rule_ipv6; +#endif +} acl_config; + +static struct{ + const char *rule_ipv4_name; + const char *rule_ipv6_name; + int scalar; +} parm_config; + +const char cb_port_delim[] = ":"; + +static inline void +print_one_ipv4_rule(struct acl4_rule *rule, int extra) +{ + unsigned char a, b, c, d; + + uint32_t_to_char(rule->field[SRC_FIELD_IPV4].value.u32, + &a, &b, &c, &d); + printf("%hhu.%hhu.%hhu.%hhu/%u ", a, b, c, d, + rule->field[SRC_FIELD_IPV4].mask_range.u32); + uint32_t_to_char(rule->field[DST_FIELD_IPV4].value.u32, + &a, &b, &c, &d); + printf("%hhu.%hhu.%hhu.%hhu/%u ", a, b, c, d, + rule->field[DST_FIELD_IPV4].mask_range.u32); + printf("%hu : %hu %hu : %hu 0x%hhx/0x%hhx ", + rule->field[SRCP_FIELD_IPV4].value.u16, + rule->field[SRCP_FIELD_IPV4].mask_range.u16, + rule->field[DSTP_FIELD_IPV4].value.u16, + rule->field[DSTP_FIELD_IPV4].mask_range.u16, + rule->field[PROTO_FIELD_IPV4].value.u8, + rule->field[PROTO_FIELD_IPV4].mask_range.u8); + if (extra) + printf("0x%x-0x%x-0x%x ", + rule->data.category_mask, + rule->data.priority, + rule->data.userdata); +} + +static inline void +print_one_ipv6_rule(struct acl6_rule *rule, int extra) +{ + unsigned char a, b, c, d; + + uint32_t_to_char(rule->field[SRC1_FIELD_IPV6].value.u32, + &a, &b, &c, &d); + printf("%.2x%.2x:%.2x%.2x", a, b, c, d); + uint32_t_to_char(rule->field[SRC2_FIELD_IPV6].value.u32, + &a, &b, &c, &d); + printf(":%.2x%.2x:%.2x%.2x", a, b, c, d); + uint32_t_to_char(rule->field[SRC3_FIELD_IPV6].value.u32, + &a, &b, &c, &d); + printf(":%.2x%.2x:%.2x%.2x", a, b, c, d); + uint32_t_to_char(rule->field[SRC4_FIELD_IPV6].value.u32, + &a, &b, &c, &d); + printf(":%.2x%.2x:%.2x%.2x/%u ", a, b, c, d, + rule->field[SRC1_FIELD_IPV6].mask_range.u32 + + rule->field[SRC2_FIELD_IPV6].mask_range.u32 + + rule->field[SRC3_FIELD_IPV6].mask_range.u32 + + rule->field[SRC4_FIELD_IPV6].mask_range.u32); + + uint32_t_to_char(rule->field[DST1_FIELD_IPV6].value.u32, + &a, &b, &c, &d); + printf("%.2x%.2x:%.2x%.2x", a, b, c, d); + uint32_t_to_char(rule->field[DST2_FIELD_IPV6].value.u32, + &a, &b, &c, &d); + printf(":%.2x%.2x:%.2x%.2x", a, b, c, d); + uint32_t_to_char(rule->field[DST3_FIELD_IPV6].value.u32, + &a, &b, &c, &d); + printf(":%.2x%.2x:%.2x%.2x", a, b, c, d); + uint32_t_to_char(rule->field[DST4_FIELD_IPV6].value.u32, + &a, &b, &c, &d); + printf(":%.2x%.2x:%.2x%.2x/%u ", a, b, c, d, + rule->field[DST1_FIELD_IPV6].mask_range.u32 + + rule->field[DST2_FIELD_IPV6].mask_range.u32 + + rule->field[DST3_FIELD_IPV6].mask_range.u32 + + rule->field[DST4_FIELD_IPV6].mask_range.u32); + + printf("%hu : %hu %hu : %hu 0x%hhx/0x%hhx ", + rule->field[SRCP_FIELD_IPV6].value.u16, + rule->field[SRCP_FIELD_IPV6].mask_range.u16, + rule->field[DSTP_FIELD_IPV6].value.u16, + rule->field[DSTP_FIELD_IPV6].mask_range.u16, + rule->field[PROTO_FIELD_IPV6].value.u8, + rule->field[PROTO_FIELD_IPV6].mask_range.u8); + if (extra) + printf("0x%x-0x%x-0x%x ", + rule->data.category_mask, + rule->data.priority, + rule->data.userdata); +} + +/* Bypass comment and empty lines */ +static inline int +is_bypass_line(char *buff) +{ + int i = 0; + + /* comment line */ + if (buff[0] == COMMENT_LEAD_CHAR) + return 1; + /* empty line */ + while (buff[i] != '\0') { + if (!isspace(buff[i])) + return 0; + i++; + } + return 1; +} + +#ifdef L3FWDACL_DEBUG +static inline void +dump_acl4_rule(struct rte_mbuf *m, uint32_t sig) +{ + uint32_t offset = sig & ~ACL_DENY_SIGNATURE; + unsigned char a, b, c, d; + struct ipv4_hdr *ipv4_hdr = rte_pktmbuf_mtod_offset(m, + struct ipv4_hdr *, + sizeof(struct ether_hdr)); + + uint32_t_to_char(rte_bswap32(ipv4_hdr->src_addr), &a, &b, &c, &d); + printf("Packet Src:%hhu.%hhu.%hhu.%hhu ", a, b, c, d); + uint32_t_to_char(rte_bswap32(ipv4_hdr->dst_addr), &a, &b, &c, &d); + printf("Dst:%hhu.%hhu.%hhu.%hhu ", a, b, c, d); + + printf("Src port:%hu,Dst port:%hu ", + rte_bswap16(*(uint16_t *)(ipv4_hdr + 1)), + rte_bswap16(*((uint16_t *)(ipv4_hdr + 1) + 1))); + printf("hit ACL %d - ", offset); + + print_one_ipv4_rule(acl_config.rule_ipv4 + offset, 1); + + printf("\n\n"); +} + +static inline void +dump_acl6_rule(struct rte_mbuf *m, uint32_t sig) +{ + unsigned i; + uint32_t offset = sig & ~ACL_DENY_SIGNATURE; + struct ipv6_hdr *ipv6_hdr = rte_pktmbuf_mtod_offset(m, + struct ipv6_hdr *, + sizeof(struct ether_hdr)); + + printf("Packet Src"); + for (i = 0; i < RTE_DIM(ipv6_hdr->src_addr); i += sizeof(uint16_t)) + printf(":%.2x%.2x", + ipv6_hdr->src_addr[i], ipv6_hdr->src_addr[i + 1]); + + printf("\nDst"); + for (i = 0; i < RTE_DIM(ipv6_hdr->dst_addr); i += sizeof(uint16_t)) + printf(":%.2x%.2x", + ipv6_hdr->dst_addr[i], ipv6_hdr->dst_addr[i + 1]); + + printf("\nSrc port:%hu,Dst port:%hu ", + rte_bswap16(*(uint16_t *)(ipv6_hdr + 1)), + rte_bswap16(*((uint16_t *)(ipv6_hdr + 1) + 1))); + printf("hit ACL %d - ", offset); + + print_one_ipv6_rule(acl_config.rule_ipv6 + offset, 1); + + printf("\n\n"); +} +#endif /* L3FWDACL_DEBUG */ + +static inline void +dump_ipv4_rules(struct acl4_rule *rule, int num, int extra) +{ + int i; + + for (i = 0; i < num; i++, rule++) { + printf("\t%d:", i + 1); + print_one_ipv4_rule(rule, extra); + printf("\n"); + } +} + +static inline void +dump_ipv6_rules(struct acl6_rule *rule, int num, int extra) +{ + int i; + + for (i = 0; i < num; i++, rule++) { + printf("\t%d:", i + 1); + print_one_ipv6_rule(rule, extra); + printf("\n"); + } +} + +#ifdef DO_RFC_1812_CHECKS +static inline void +prepare_one_packet(struct rte_mbuf **pkts_in, struct acl_search_t *acl, + int index) +{ + struct ipv4_hdr *ipv4_hdr; + struct rte_mbuf *pkt = pkts_in[index]; + + if (RTE_ETH_IS_IPV4_HDR(pkt->packet_type)) { + ipv4_hdr = rte_pktmbuf_mtod_offset(pkt, struct ipv4_hdr *, + sizeof(struct ether_hdr)); + + /* Check to make sure the packet is valid (RFC1812) */ + if (is_valid_ipv4_pkt(ipv4_hdr, pkt->pkt_len) >= 0) { + + /* Update time to live and header checksum */ + --(ipv4_hdr->time_to_live); + ++(ipv4_hdr->hdr_checksum); + + /* Fill acl structure */ + acl->data_ipv4[acl->num_ipv4] = MBUF_IPV4_2PROTO(pkt); + acl->m_ipv4[(acl->num_ipv4)++] = pkt; + + } else { + /* Not a valid IPv4 packet */ + rte_pktmbuf_free(pkt); + } + } else if (RTE_ETH_IS_IPV6_HDR(pkt->packet_type)) { + /* Fill acl structure */ + acl->data_ipv6[acl->num_ipv6] = MBUF_IPV6_2PROTO(pkt); + acl->m_ipv6[(acl->num_ipv6)++] = pkt; + + } else { + /* Unknown type, drop the packet */ + rte_pktmbuf_free(pkt); + } +} + +#else +static inline void +prepare_one_packet(struct rte_mbuf **pkts_in, struct acl_search_t *acl, + int index) +{ + struct rte_mbuf *pkt = pkts_in[index]; + + if (RTE_ETH_IS_IPV4_HDR(pkt->packet_type)) { + /* Fill acl structure */ + acl->data_ipv4[acl->num_ipv4] = MBUF_IPV4_2PROTO(pkt); + acl->m_ipv4[(acl->num_ipv4)++] = pkt; + + } else if (RTE_ETH_IS_IPV6_HDR(pkt->packet_type)) { + /* Fill acl structure */ + acl->data_ipv6[acl->num_ipv6] = MBUF_IPV6_2PROTO(pkt); + acl->m_ipv6[(acl->num_ipv6)++] = pkt; + } else { + /* Unknown type, drop the packet */ + rte_pktmbuf_free(pkt); + } +} +#endif /* DO_RFC_1812_CHECKS */ + +static inline void +prepare_acl_parameter(struct rte_mbuf **pkts_in, struct acl_search_t *acl, + int nb_rx) +{ + int i; + + acl->num_ipv4 = 0; + acl->num_ipv6 = 0; + + /* Prefetch first packets */ + for (i = 0; i < PREFETCH_OFFSET && i < nb_rx; i++) { + rte_prefetch0(rte_pktmbuf_mtod( + pkts_in[i], void *)); + } + + for (i = 0; i < (nb_rx - PREFETCH_OFFSET); i++) { + rte_prefetch0(rte_pktmbuf_mtod(pkts_in[ + i + PREFETCH_OFFSET], void *)); + prepare_one_packet(pkts_in, acl, i); + } + + /* Process left packets */ + for (; i < nb_rx; i++) + prepare_one_packet(pkts_in, acl, i); +} + +static inline void +send_one_packet(struct rte_mbuf *m, uint32_t res) +{ + if (likely((res & ACL_DENY_SIGNATURE) == 0 && res != 0)) { + /* forward packets */ + send_single_packet(m, + (uint8_t)(res - FWD_PORT_SHIFT)); + } else{ + /* in the ACL list, drop it */ +#ifdef L3FWDACL_DEBUG + if ((res & ACL_DENY_SIGNATURE) != 0) { + if (RTE_ETH_IS_IPV4_HDR(m->packet_type)) + dump_acl4_rule(m, res); + else if (RTE_ETH_IS_IPV6_HDR(m->packet_type)) + dump_acl6_rule(m, res); + } +#endif + rte_pktmbuf_free(m); + } +} + + + +static inline void +send_packets(struct rte_mbuf **m, uint32_t *res, int num) +{ + int i; + + /* Prefetch first packets */ + for (i = 0; i < PREFETCH_OFFSET && i < num; i++) { + rte_prefetch0(rte_pktmbuf_mtod( + m[i], void *)); + } + + for (i = 0; i < (num - PREFETCH_OFFSET); i++) { + rte_prefetch0(rte_pktmbuf_mtod(m[ + i + PREFETCH_OFFSET], void *)); + send_one_packet(m[i], res[i]); + } + + /* Process left packets */ + for (; i < num; i++) + send_one_packet(m[i], res[i]); +} + +/* + * Parses IPV6 address, exepcts the following format: + * XXXX:XXXX:XXXX:XXXX:XXXX:XXXX:XXXX:XXXX (where X - is a hexedecimal digit). + */ +static int +parse_ipv6_addr(const char *in, const char **end, uint32_t v[IPV6_ADDR_U32], + char dlm) +{ + uint32_t addr[IPV6_ADDR_U16]; + + GET_CB_FIELD(in, addr[0], 16, UINT16_MAX, ':'); + GET_CB_FIELD(in, addr[1], 16, UINT16_MAX, ':'); + GET_CB_FIELD(in, addr[2], 16, UINT16_MAX, ':'); + GET_CB_FIELD(in, addr[3], 16, UINT16_MAX, ':'); + GET_CB_FIELD(in, addr[4], 16, UINT16_MAX, ':'); + GET_CB_FIELD(in, addr[5], 16, UINT16_MAX, ':'); + GET_CB_FIELD(in, addr[6], 16, UINT16_MAX, ':'); + GET_CB_FIELD(in, addr[7], 16, UINT16_MAX, dlm); + + *end = in; + + v[0] = (addr[0] << 16) + addr[1]; + v[1] = (addr[2] << 16) + addr[3]; + v[2] = (addr[4] << 16) + addr[5]; + v[3] = (addr[6] << 16) + addr[7]; + + return 0; +} + +static int +parse_ipv6_net(const char *in, struct rte_acl_field field[4]) +{ + int32_t rc; + const char *mp; + uint32_t i, m, v[4]; + const uint32_t nbu32 = sizeof(uint32_t) * CHAR_BIT; + + /* get address. */ + rc = parse_ipv6_addr(in, &mp, v, '/'); + if (rc != 0) + return rc; + + /* get mask. */ + GET_CB_FIELD(mp, m, 0, CHAR_BIT * sizeof(v), 0); + + /* put all together. */ + for (i = 0; i != RTE_DIM(v); i++) { + if (m >= (i + 1) * nbu32) + field[i].mask_range.u32 = nbu32; + else + field[i].mask_range.u32 = m > (i * nbu32) ? + m - (i * 32) : 0; + + field[i].value.u32 = v[i]; + } + + return 0; +} + +static int +parse_cb_ipv6_rule(char *str, struct rte_acl_rule *v, int has_userdata) +{ + int i, rc; + char *s, *sp, *in[CB_FLD_NUM]; + static const char *dlm = " \t\n"; + int dim = has_userdata ? CB_FLD_NUM : CB_FLD_USERDATA; + s = str; + + for (i = 0; i != dim; i++, s = NULL) { + in[i] = strtok_r(s, dlm, &sp); + if (in[i] == NULL) + return -EINVAL; + } + + rc = parse_ipv6_net(in[CB_FLD_SRC_ADDR], v->field + SRC1_FIELD_IPV6); + if (rc != 0) { + acl_log("failed to read source address/mask: %s\n", + in[CB_FLD_SRC_ADDR]); + return rc; + } + + rc = parse_ipv6_net(in[CB_FLD_DST_ADDR], v->field + DST1_FIELD_IPV6); + if (rc != 0) { + acl_log("failed to read destination address/mask: %s\n", + in[CB_FLD_DST_ADDR]); + return rc; + } + + /* source port. */ + GET_CB_FIELD(in[CB_FLD_SRC_PORT_LOW], + v->field[SRCP_FIELD_IPV6].value.u16, + 0, UINT16_MAX, 0); + GET_CB_FIELD(in[CB_FLD_SRC_PORT_HIGH], + v->field[SRCP_FIELD_IPV6].mask_range.u16, + 0, UINT16_MAX, 0); + + if (strncmp(in[CB_FLD_SRC_PORT_DLM], cb_port_delim, + sizeof(cb_port_delim)) != 0) + return -EINVAL; + + /* destination port. */ + GET_CB_FIELD(in[CB_FLD_DST_PORT_LOW], + v->field[DSTP_FIELD_IPV6].value.u16, + 0, UINT16_MAX, 0); + GET_CB_FIELD(in[CB_FLD_DST_PORT_HIGH], + v->field[DSTP_FIELD_IPV6].mask_range.u16, + 0, UINT16_MAX, 0); + + if (strncmp(in[CB_FLD_DST_PORT_DLM], cb_port_delim, + sizeof(cb_port_delim)) != 0) + return -EINVAL; + + if (v->field[SRCP_FIELD_IPV6].mask_range.u16 + < v->field[SRCP_FIELD_IPV6].value.u16 + || v->field[DSTP_FIELD_IPV6].mask_range.u16 + < v->field[DSTP_FIELD_IPV6].value.u16) + return -EINVAL; + + GET_CB_FIELD(in[CB_FLD_PROTO], v->field[PROTO_FIELD_IPV6].value.u8, + 0, UINT8_MAX, '/'); + GET_CB_FIELD(in[CB_FLD_PROTO], v->field[PROTO_FIELD_IPV6].mask_range.u8, + 0, UINT8_MAX, 0); + + if (has_userdata) + GET_CB_FIELD(in[CB_FLD_USERDATA], v->data.userdata, + 0, UINT32_MAX, 0); + + return 0; +} + +/* + * Parse ClassBench rules file. + * Expected format: + * '@'<src_ipv4_addr>'/'<masklen> <space> \ + * <dst_ipv4_addr>'/'<masklen> <space> \ + * <src_port_low> <space> ":" <src_port_high> <space> \ + * <dst_port_low> <space> ":" <dst_port_high> <space> \ + * <proto>'/'<mask> + */ +static int +parse_ipv4_net(const char *in, uint32_t *addr, uint32_t *mask_len) +{ + uint8_t a, b, c, d, m; + + GET_CB_FIELD(in, a, 0, UINT8_MAX, '.'); + GET_CB_FIELD(in, b, 0, UINT8_MAX, '.'); + GET_CB_FIELD(in, c, 0, UINT8_MAX, '.'); + GET_CB_FIELD(in, d, 0, UINT8_MAX, '/'); + GET_CB_FIELD(in, m, 0, sizeof(uint32_t) * CHAR_BIT, 0); + + addr[0] = IPv4(a, b, c, d); + mask_len[0] = m; + + return 0; +} + +static int +parse_cb_ipv4vlan_rule(char *str, struct rte_acl_rule *v, int has_userdata) +{ + int i, rc; + char *s, *sp, *in[CB_FLD_NUM]; + static const char *dlm = " \t\n"; + int dim = has_userdata ? CB_FLD_NUM : CB_FLD_USERDATA; + s = str; + + for (i = 0; i != dim; i++, s = NULL) { + in[i] = strtok_r(s, dlm, &sp); + if (in[i] == NULL) + return -EINVAL; + } + + rc = parse_ipv4_net(in[CB_FLD_SRC_ADDR], + &v->field[SRC_FIELD_IPV4].value.u32, + &v->field[SRC_FIELD_IPV4].mask_range.u32); + if (rc != 0) { + acl_log("failed to read source address/mask: %s\n", + in[CB_FLD_SRC_ADDR]); + return rc; + } + + rc = parse_ipv4_net(in[CB_FLD_DST_ADDR], + &v->field[DST_FIELD_IPV4].value.u32, + &v->field[DST_FIELD_IPV4].mask_range.u32); + if (rc != 0) { + acl_log("failed to read destination address/mask: %s\n", + in[CB_FLD_DST_ADDR]); + return rc; + } + + GET_CB_FIELD(in[CB_FLD_SRC_PORT_LOW], + v->field[SRCP_FIELD_IPV4].value.u16, + 0, UINT16_MAX, 0); + GET_CB_FIELD(in[CB_FLD_SRC_PORT_HIGH], + v->field[SRCP_FIELD_IPV4].mask_range.u16, + 0, UINT16_MAX, 0); + + if (strncmp(in[CB_FLD_SRC_PORT_DLM], cb_port_delim, + sizeof(cb_port_delim)) != 0) + return -EINVAL; + + GET_CB_FIELD(in[CB_FLD_DST_PORT_LOW], + v->field[DSTP_FIELD_IPV4].value.u16, + 0, UINT16_MAX, 0); + GET_CB_FIELD(in[CB_FLD_DST_PORT_HIGH], + v->field[DSTP_FIELD_IPV4].mask_range.u16, + 0, UINT16_MAX, 0); + + if (strncmp(in[CB_FLD_DST_PORT_DLM], cb_port_delim, + sizeof(cb_port_delim)) != 0) + return -EINVAL; + + if (v->field[SRCP_FIELD_IPV4].mask_range.u16 + < v->field[SRCP_FIELD_IPV4].value.u16 + || v->field[DSTP_FIELD_IPV4].mask_range.u16 + < v->field[DSTP_FIELD_IPV4].value.u16) + return -EINVAL; + + GET_CB_FIELD(in[CB_FLD_PROTO], v->field[PROTO_FIELD_IPV4].value.u8, + 0, UINT8_MAX, '/'); + GET_CB_FIELD(in[CB_FLD_PROTO], v->field[PROTO_FIELD_IPV4].mask_range.u8, + 0, UINT8_MAX, 0); + + if (has_userdata) + GET_CB_FIELD(in[CB_FLD_USERDATA], v->data.userdata, 0, + UINT32_MAX, 0); + + return 0; +} + +static int +add_rules(const char *rule_path, + struct rte_acl_rule **proute_base, + unsigned int *proute_num, + struct rte_acl_rule **pacl_base, + unsigned int *pacl_num, uint32_t rule_size, + int (*parser)(char *, struct rte_acl_rule*, int)) +{ + uint8_t *acl_rules, *route_rules; + struct rte_acl_rule *next; + unsigned int acl_num = 0, route_num = 0, total_num = 0; + unsigned int acl_cnt = 0, route_cnt = 0; + char buff[LINE_MAX]; + FILE *fh = fopen(rule_path, "rb"); + unsigned int i = 0; + int val; + + if (fh == NULL) + rte_exit(EXIT_FAILURE, "%s: Open %s failed\n", __func__, + rule_path); + + while ((fgets(buff, LINE_MAX, fh) != NULL)) { + if (buff[0] == ROUTE_LEAD_CHAR) + route_num++; + else if (buff[0] == ACL_LEAD_CHAR) + acl_num++; + } + + if (0 == route_num) + rte_exit(EXIT_FAILURE, "Not find any route entries in %s!\n", + rule_path); + + val = fseek(fh, 0, SEEK_SET); + if (val < 0) { + rte_exit(EXIT_FAILURE, "%s: File seek operation failed\n", + __func__); + } + + acl_rules = calloc(acl_num, rule_size); + + if (NULL == acl_rules) + rte_exit(EXIT_FAILURE, "%s: failed to malloc memory\n", + __func__); + + route_rules = calloc(route_num, rule_size); + + if (NULL == route_rules) + rte_exit(EXIT_FAILURE, "%s: failed to malloc memory\n", + __func__); + + i = 0; + while (fgets(buff, LINE_MAX, fh) != NULL) { + i++; + + if (is_bypass_line(buff)) + continue; + + char s = buff[0]; + + /* Route entry */ + if (s == ROUTE_LEAD_CHAR) + next = (struct rte_acl_rule *)(route_rules + + route_cnt * rule_size); + + /* ACL entry */ + else if (s == ACL_LEAD_CHAR) + next = (struct rte_acl_rule *)(acl_rules + + acl_cnt * rule_size); + + /* Illegal line */ + else + rte_exit(EXIT_FAILURE, + "%s Line %u: should start with leading " + "char %c or %c\n", + rule_path, i, ROUTE_LEAD_CHAR, ACL_LEAD_CHAR); + + if (parser(buff + 1, next, s == ROUTE_LEAD_CHAR) != 0) + rte_exit(EXIT_FAILURE, + "%s Line %u: parse rules error\n", + rule_path, i); + + if (s == ROUTE_LEAD_CHAR) { + /* Check the forwarding port number */ + if ((enabled_port_mask & (1 << next->data.userdata)) == + 0) + rte_exit(EXIT_FAILURE, + "%s Line %u: fwd number illegal:%u\n", + rule_path, i, next->data.userdata); + next->data.userdata += FWD_PORT_SHIFT; + route_cnt++; + } else { + next->data.userdata = ACL_DENY_SIGNATURE + acl_cnt; + acl_cnt++; + } + + next->data.priority = RTE_ACL_MAX_PRIORITY - total_num; + next->data.category_mask = -1; + total_num++; + } + + fclose(fh); + + *pacl_base = (struct rte_acl_rule *)acl_rules; + *pacl_num = acl_num; + *proute_base = (struct rte_acl_rule *)route_rules; + *proute_num = route_cnt; + + return 0; +} + +static void +dump_acl_config(void) +{ + printf("ACL option are:\n"); + printf(OPTION_RULE_IPV4": %s\n", parm_config.rule_ipv4_name); + printf(OPTION_RULE_IPV6": %s\n", parm_config.rule_ipv6_name); + printf(OPTION_SCALAR": %d\n", parm_config.scalar); +} + +static int +check_acl_config(void) +{ + if (parm_config.rule_ipv4_name == NULL) { + acl_log("ACL IPv4 rule file not specified\n"); + return -1; + } else if (parm_config.rule_ipv6_name == NULL) { + acl_log("ACL IPv6 rule file not specified\n"); + return -1; + } + + return 0; +} + +static struct rte_acl_ctx* +setup_acl(struct rte_acl_rule *route_base, + struct rte_acl_rule *acl_base, unsigned int route_num, + unsigned int acl_num, int ipv6, int socketid) +{ + char name[PATH_MAX]; + struct rte_acl_param acl_param; + struct rte_acl_config acl_build_param; + struct rte_acl_ctx *context; + int dim = ipv6 ? RTE_DIM(ipv6_defs) : RTE_DIM(ipv4_defs); + + /* Create ACL contexts */ + snprintf(name, sizeof(name), "%s%d", + ipv6 ? L3FWD_ACL_IPV6_NAME : L3FWD_ACL_IPV4_NAME, + socketid); + + acl_param.name = name; + acl_param.socket_id = socketid; + acl_param.rule_size = RTE_ACL_RULE_SZ(dim); + acl_param.max_rule_num = MAX_ACL_RULE_NUM; + + if ((context = rte_acl_create(&acl_param)) == NULL) + rte_exit(EXIT_FAILURE, "Failed to create ACL context\n"); + + if (parm_config.scalar && rte_acl_set_ctx_classify(context, + RTE_ACL_CLASSIFY_SCALAR) != 0) + rte_exit(EXIT_FAILURE, + "Failed to setup classify method for ACL context\n"); + + if (rte_acl_add_rules(context, route_base, route_num) < 0) + rte_exit(EXIT_FAILURE, "add rules failed\n"); + + if (rte_acl_add_rules(context, acl_base, acl_num) < 0) + rte_exit(EXIT_FAILURE, "add rules failed\n"); + + /* Perform builds */ + memset(&acl_build_param, 0, sizeof(acl_build_param)); + + acl_build_param.num_categories = DEFAULT_MAX_CATEGORIES; + acl_build_param.num_fields = dim; + memcpy(&acl_build_param.defs, ipv6 ? ipv6_defs : ipv4_defs, + ipv6 ? sizeof(ipv6_defs) : sizeof(ipv4_defs)); + + if (rte_acl_build(context, &acl_build_param) != 0) + rte_exit(EXIT_FAILURE, "Failed to build ACL trie\n"); + + rte_acl_dump(context); + + return context; +} + +static int +app_acl_init(void) +{ + unsigned lcore_id; + unsigned int i; + int socketid; + struct rte_acl_rule *acl_base_ipv4, *route_base_ipv4, + *acl_base_ipv6, *route_base_ipv6; + unsigned int acl_num_ipv4 = 0, route_num_ipv4 = 0, + acl_num_ipv6 = 0, route_num_ipv6 = 0; + + if (check_acl_config() != 0) + rte_exit(EXIT_FAILURE, "Failed to get valid ACL options\n"); + + dump_acl_config(); + + /* Load rules from the input file */ + if (add_rules(parm_config.rule_ipv4_name, &route_base_ipv4, + &route_num_ipv4, &acl_base_ipv4, &acl_num_ipv4, + sizeof(struct acl4_rule), &parse_cb_ipv4vlan_rule) < 0) + rte_exit(EXIT_FAILURE, "Failed to add rules\n"); + + acl_log("IPv4 Route entries %u:\n", route_num_ipv4); + dump_ipv4_rules((struct acl4_rule *)route_base_ipv4, route_num_ipv4, 1); + + acl_log("IPv4 ACL entries %u:\n", acl_num_ipv4); + dump_ipv4_rules((struct acl4_rule *)acl_base_ipv4, acl_num_ipv4, 1); + + if (add_rules(parm_config.rule_ipv6_name, &route_base_ipv6, + &route_num_ipv6, + &acl_base_ipv6, &acl_num_ipv6, + sizeof(struct acl6_rule), &parse_cb_ipv6_rule) < 0) + rte_exit(EXIT_FAILURE, "Failed to add rules\n"); + + acl_log("IPv6 Route entries %u:\n", route_num_ipv6); + dump_ipv6_rules((struct acl6_rule *)route_base_ipv6, route_num_ipv6, 1); + + acl_log("IPv6 ACL entries %u:\n", acl_num_ipv6); + dump_ipv6_rules((struct acl6_rule *)acl_base_ipv6, acl_num_ipv6, 1); + + memset(&acl_config, 0, sizeof(acl_config)); + + /* Check sockets a context should be created on */ + if (!numa_on) + acl_config.mapped[0] = 1; + else { + for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) { + if (rte_lcore_is_enabled(lcore_id) == 0) + continue; + + socketid = rte_lcore_to_socket_id(lcore_id); + if (socketid >= NB_SOCKETS) { + acl_log("Socket %d of lcore %u is out " + "of range %d\n", + socketid, lcore_id, NB_SOCKETS); + free(route_base_ipv4); + free(route_base_ipv6); + free(acl_base_ipv4); + free(acl_base_ipv6); + return -1; + } + + acl_config.mapped[socketid] = 1; + } + } + + for (i = 0; i < NB_SOCKETS; i++) { + if (acl_config.mapped[i]) { + acl_config.acx_ipv4[i] = setup_acl(route_base_ipv4, + acl_base_ipv4, route_num_ipv4, acl_num_ipv4, + 0, i); + + acl_config.acx_ipv6[i] = setup_acl(route_base_ipv6, + acl_base_ipv6, route_num_ipv6, acl_num_ipv6, + 1, i); + } + } + + free(route_base_ipv4); + free(route_base_ipv6); + +#ifdef L3FWDACL_DEBUG + acl_config.rule_ipv4 = (struct acl4_rule *)acl_base_ipv4; + acl_config.rule_ipv6 = (struct acl6_rule *)acl_base_ipv6; +#else + free(acl_base_ipv4); + free(acl_base_ipv6); +#endif + + return 0; +} + +/***********************end of ACL part******************************/ + +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 rte_eth_dev_tx_buffer *tx_buffer[RTE_MAX_ETHPORTS]; +} __rte_cache_aligned; + +static struct lcore_conf lcore_conf[RTE_MAX_LCORE]; + +/* Enqueue a single packet, and send burst if queue is filled */ +static inline void +send_single_packet(struct rte_mbuf *m, uint16_t port) +{ + uint32_t lcore_id; + struct lcore_conf *qconf; + + lcore_id = rte_lcore_id(); + + qconf = &lcore_conf[lcore_id]; + rte_eth_tx_buffer(port, qconf->tx_queue_id[port], + qconf->tx_buffer[port], m); +} + +#ifdef DO_RFC_1812_CHECKS +static inline int +is_valid_ipv4_pkt(struct 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)) + return -1; + + /* 2. The IP checksum must be correct. */ + /* this is checked in H/W */ + + /* + * 3. The IP version number must be 4. If the version number is not 4 + * then the packet may be another version of IP, such as IPng or + * ST-II. + */ + if (((pkt->version_ihl) >> 4) != 4) + return -3; + /* + * 4. The IP header length field must be large enough to hold the + * minimum length legal IP datagram (20 bytes = 5 words). + */ + if ((pkt->version_ihl & 0xf) < 5) + return -4; + + /* + * 5. The IP total length field must be large enough to hold the IP + * 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)) + return -5; + + return 0; +} +#endif + +/* 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; + int i, nb_rx; + uint16_t portid; + uint8_t queueid; + struct lcore_conf *qconf; + int socketid; + 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]; + socketid = rte_lcore_to_socket_id(lcore_id); + + if (qconf->n_rx_queue == 0) { + RTE_LOG(INFO, L3FWD, "lcore %u has nothing to do\n", lcore_id); + return 0; + } + + RTE_LOG(INFO, L3FWD, "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, + " -- lcoreid=%u portid=%u rxqueueid=%hhu\n", + lcore_id, portid, queueid); + } + + while (1) { + + 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) { + + portid = qconf->rx_queue_list[i].port_id; + queueid = qconf->rx_queue_list[i].queue_id; + nb_rx = rte_eth_rx_burst(portid, queueid, + pkts_burst, MAX_PKT_BURST); + + if (nb_rx > 0) { + struct acl_search_t acl_search; + + prepare_acl_parameter(pkts_burst, &acl_search, + nb_rx); + + if (acl_search.num_ipv4) { + rte_acl_classify( + acl_config.acx_ipv4[socketid], + acl_search.data_ipv4, + acl_search.res_ipv4, + acl_search.num_ipv4, + DEFAULT_MAX_CATEGORIES); + + send_packets(acl_search.m_ipv4, + acl_search.res_ipv4, + acl_search.num_ipv4); + } + + if (acl_search.num_ipv6) { + rte_acl_classify( + acl_config.acx_ipv6[socketid], + acl_search.data_ipv6, + acl_search.res_ipv6, + acl_search.num_ipv6, + DEFAULT_MAX_CATEGORIES); + + send_packets(acl_search.m_ipv6, + acl_search.res_ipv6, + acl_search.num_ipv6); + } + } + } + } +} + +static int +check_lcore_params(void) +{ + uint8_t queue, lcore; + uint16_t i; + int socketid; + + for (i = 0; i < nb_lcore_params; ++i) { + queue = lcore_params[i].queue_id; + if (queue >= MAX_RX_QUEUE_PER_PORT) { + printf("invalid queue number: %hhu\n", queue); + return -1; + } + lcore = lcore_params[i].lcore_id; + if (!rte_lcore_is_enabled(lcore)) { + printf("error: lcore %hhu is not enabled in " + "lcore mask\n", lcore); + return -1; + } + socketid = rte_lcore_to_socket_id(lcore); + if (socketid != 0 && numa_on == 0) { + printf("warning: lcore %hhu is on socket %d " + "with numa off\n", + lcore, socketid); + } + } + return 0; +} + +static int +check_port_config(void) +{ + unsigned portid; + uint16_t i; + + for (i = 0; i < nb_lcore_params; ++i) { + portid = lcore_params[i].port_id; + + if ((enabled_port_mask & (1 << portid)) == 0) { + printf("port %u is not enabled in port mask\n", portid); + return -1; + } + if (!rte_eth_dev_is_valid_port(portid)) { + printf("port %u is not present on the board\n", portid); + return -1; + } + } + return 0; +} + +static uint8_t +get_port_n_rx_queues(const uint16_t port) +{ + int queue = -1; + uint16_t i; + + for (i = 0; i < nb_lcore_params; ++i) { + if (lcore_params[i].port_id == port && + lcore_params[i].queue_id > queue) + queue = lcore_params[i].queue_id; + } + return (uint8_t)(++queue); +} + +static int +init_lcore_rx_queues(void) +{ + uint16_t i, nb_rx_queue; + uint8_t lcore; + + for (i = 0; i < nb_lcore_params; ++i) { + lcore = lcore_params[i].lcore_id; + nb_rx_queue = lcore_conf[lcore].n_rx_queue; + if (nb_rx_queue >= MAX_RX_QUEUE_PER_LCORE) { + printf("error: too many queues (%u) for lcore: %u\n", + (unsigned)nb_rx_queue + 1, (unsigned)lcore); + return -1; + } else { + lcore_conf[lcore].rx_queue_list[nb_rx_queue].port_id = + lcore_params[i].port_id; + lcore_conf[lcore].rx_queue_list[nb_rx_queue].queue_id = + lcore_params[i].queue_id; + lcore_conf[lcore].n_rx_queue++; + } + } + return 0; +} + +/* display usage */ +static void +print_usage(const char *prgname) +{ + printf("%s [EAL options] -- -p PORTMASK -P" + "--"OPTION_RULE_IPV4"=FILE" + "--"OPTION_RULE_IPV6"=FILE" + " [--"OPTION_CONFIG" (port,queue,lcore)[,(port,queue,lcore]]" + " [--"OPTION_ENBJMO" [--max-pkt-len PKTLEN]]\n" + " -p PORTMASK: hexadecimal bitmask of ports to configure\n" + " -P : enable promiscuous mode\n" + " --"OPTION_CONFIG": (port,queue,lcore): " + "rx queues configuration\n" + " --"OPTION_NONUMA": optional, disable numa awareness\n" + " --"OPTION_ENBJMO": enable jumbo frame" + " which max packet len is PKTLEN in decimal (64-9600)\n" + " --"OPTION_RULE_IPV4"=FILE: specify the ipv4 rules entries " + "file. " + "Each rule occupy one line. " + "2 kinds of rules are supported. " + "One is ACL entry at while line leads with character '%c', " + "another is route entry at while line leads with " + "character '%c'.\n" + " --"OPTION_RULE_IPV6"=FILE: specify the ipv6 rules " + "entries file.\n" + " --"OPTION_SCALAR": Use scalar function to do lookup\n", + prgname, ACL_LEAD_CHAR, ROUTE_LEAD_CHAR); +} + +static int +parse_max_pkt_len(const char *pktlen) +{ + char *end = NULL; + unsigned long len; + + /* parse decimal string */ + len = strtoul(pktlen, &end, 10); + if ((pktlen[0] == '\0') || (end == NULL) || (*end != '\0')) + return -1; + + if (len == 0) + return -1; + + return len; +} + +static int +parse_portmask(const char *portmask) +{ + char *end = NULL; + unsigned long pm; + + /* parse hexadecimal string */ + pm = strtoul(portmask, &end, 16); + if ((portmask[0] == '\0') || (end == NULL) || (*end != '\0')) + return -1; + + if (pm == 0) + return -1; + + return pm; +} + +static int +parse_config(const char *q_arg) +{ + char s[256]; + const char *p, *p0 = q_arg; + char *end; + enum fieldnames { + FLD_PORT = 0, + FLD_QUEUE, + FLD_LCORE, + _NUM_FLD + }; + unsigned long int_fld[_NUM_FLD]; + char *str_fld[_NUM_FLD]; + int i; + unsigned size; + + nb_lcore_params = 0; + + while ((p = strchr(p0, '(')) != NULL) { + ++p; + if ((p0 = strchr(p, ')')) == NULL) + return -1; + + size = p0 - p; + if (size >= sizeof(s)) + return -1; + + snprintf(s, sizeof(s), "%.*s", size, p); + if (rte_strsplit(s, sizeof(s), str_fld, _NUM_FLD, ',') != + _NUM_FLD) + return -1; + for (i = 0; i < _NUM_FLD; i++) { + errno = 0; + int_fld[i] = strtoul(str_fld[i], &end, 0); + if (errno != 0 || end == str_fld[i] || int_fld[i] > 255) + return -1; + } + if (nb_lcore_params >= MAX_LCORE_PARAMS) { + printf("exceeded max number of lcore params: %hu\n", + nb_lcore_params); + return -1; + } + lcore_params_array[nb_lcore_params].port_id = + (uint8_t)int_fld[FLD_PORT]; + lcore_params_array[nb_lcore_params].queue_id = + (uint8_t)int_fld[FLD_QUEUE]; + lcore_params_array[nb_lcore_params].lcore_id = + (uint8_t)int_fld[FLD_LCORE]; + ++nb_lcore_params; + } + lcore_params = lcore_params_array; + return 0; +} + +/* Parse the argument given in the command line of the application */ +static int +parse_args(int argc, char **argv) +{ + int opt, ret; + char **argvopt; + int option_index; + char *prgname = argv[0]; + static struct option lgopts[] = { + {OPTION_CONFIG, 1, 0, 0}, + {OPTION_NONUMA, 0, 0, 0}, + {OPTION_ENBJMO, 0, 0, 0}, + {OPTION_RULE_IPV4, 1, 0, 0}, + {OPTION_RULE_IPV6, 1, 0, 0}, + {OPTION_SCALAR, 0, 0, 0}, + {NULL, 0, 0, 0} + }; + + argvopt = argv; + + while ((opt = getopt_long(argc, argvopt, "p:P", + lgopts, &option_index)) != EOF) { + + switch (opt) { + /* portmask */ + case 'p': + enabled_port_mask = parse_portmask(optarg); + if (enabled_port_mask == 0) { + printf("invalid portmask\n"); + print_usage(prgname); + return -1; + } + break; + case 'P': + printf("Promiscuous mode selected\n"); + promiscuous_on = 1; + break; + + /* long options */ + case 0: + if (!strncmp(lgopts[option_index].name, + OPTION_CONFIG, + sizeof(OPTION_CONFIG))) { + ret = parse_config(optarg); + if (ret) { + printf("invalid config\n"); + print_usage(prgname); + return -1; + } + } + + if (!strncmp(lgopts[option_index].name, + OPTION_NONUMA, + sizeof(OPTION_NONUMA))) { + printf("numa is disabled\n"); + numa_on = 0; + } + + if (!strncmp(lgopts[option_index].name, + OPTION_ENBJMO, sizeof(OPTION_ENBJMO))) { + struct option lenopts = { + "max-pkt-len", + required_argument, + 0, + 0 + }; + + printf("jumbo frame is enabled\n"); + port_conf.rxmode.offloads |= + DEV_RX_OFFLOAD_JUMBO_FRAME; + port_conf.txmode.offloads |= + DEV_TX_OFFLOAD_MULTI_SEGS; + + /* + * if no max-pkt-len set, then use the + * default value ETHER_MAX_LEN + */ + if (0 == getopt_long(argc, argvopt, "", + &lenopts, &option_index)) { + ret = parse_max_pkt_len(optarg); + if ((ret < 64) || + (ret > MAX_JUMBO_PKT_LEN)) { + printf("invalid packet " + "length\n"); + print_usage(prgname); + return -1; + } + port_conf.rxmode.max_rx_pkt_len = ret; + } + printf("set jumbo frame max packet length " + "to %u\n", + (unsigned int) + port_conf.rxmode.max_rx_pkt_len); + } + + if (!strncmp(lgopts[option_index].name, + OPTION_RULE_IPV4, + sizeof(OPTION_RULE_IPV4))) + parm_config.rule_ipv4_name = optarg; + + if (!strncmp(lgopts[option_index].name, + OPTION_RULE_IPV6, + sizeof(OPTION_RULE_IPV6))) { + parm_config.rule_ipv6_name = optarg; + } + + if (!strncmp(lgopts[option_index].name, + OPTION_SCALAR, sizeof(OPTION_SCALAR))) + parm_config.scalar = 1; + + + break; + + default: + print_usage(prgname); + return -1; + } + } + + if (optind >= 0) + argv[optind-1] = prgname; + + ret = optind-1; + optind = 1; /* reset getopt lib */ + return ret; +} + +static void +print_ethaddr(const char *name, const struct ether_addr *eth_addr) +{ + char buf[ETHER_ADDR_FMT_SIZE]; + ether_format_addr(buf, ETHER_ADDR_FMT_SIZE, eth_addr); + printf("%s%s", name, buf); +} + +static int +init_mem(unsigned nb_mbuf) +{ + int socketid; + unsigned lcore_id; + char s[64]; + + for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) { + if (rte_lcore_is_enabled(lcore_id) == 0) + continue; + + if (numa_on) + socketid = rte_lcore_to_socket_id(lcore_id); + else + socketid = 0; + + if (socketid >= NB_SOCKETS) { + rte_exit(EXIT_FAILURE, + "Socket %d of lcore %u is out of range %d\n", + socketid, lcore_id, NB_SOCKETS); + } + if (pktmbuf_pool[socketid] == NULL) { + snprintf(s, sizeof(s), "mbuf_pool_%d", socketid); + pktmbuf_pool[socketid] = + 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", + socketid); + else + printf("Allocated mbuf pool on socket %d\n", + socketid); + } + } + return 0; +} + +/* Check the link status of all ports in up to 9s, and print them finally */ +static void +check_all_ports_link_status(uint32_t port_mask) +{ +#define CHECK_INTERVAL 100 /* 100ms */ +#define MAX_CHECK_TIME 90 /* 9s (90 * 100ms) in total */ + uint16_t portid; + uint8_t count, all_ports_up, print_flag = 0; + struct rte_eth_link link; + + printf("\nChecking link status"); + fflush(stdout); + for (count = 0; count <= MAX_CHECK_TIME; count++) { + all_ports_up = 1; + RTE_ETH_FOREACH_DEV(portid) { + if ((port_mask & (1 << portid)) == 0) + continue; + memset(&link, 0, sizeof(link)); + rte_eth_link_get_nowait(portid, &link); + /* 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); + continue; + } + /* clear all_ports_up flag if any link down */ + if (link.link_status == ETH_LINK_DOWN) { + all_ports_up = 0; + break; + } + } + /* after finally printing all link status, get out */ + if (print_flag == 1) + break; + + if (all_ports_up == 0) { + printf("."); + fflush(stdout); + rte_delay_ms(CHECK_INTERVAL); + } + + /* set the print_flag if all ports up or timeout */ + if (all_ports_up == 1 || count == (MAX_CHECK_TIME - 1)) { + print_flag = 1; + printf("done\n"); + } + } +} + +int +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 queueid; + unsigned lcore_id; + uint32_t n_tx_queue, nb_lcores; + uint16_t portid; + uint8_t nb_rx_queue, queue, socketid; + + /* init EAL */ + ret = rte_eal_init(argc, argv); + if (ret < 0) + rte_exit(EXIT_FAILURE, "Invalid EAL parameters\n"); + argc -= ret; + argv += ret; + + /* parse application arguments (after the EAL ones) */ + ret = parse_args(argc, argv); + if (ret < 0) + rte_exit(EXIT_FAILURE, "Invalid L3FWD parameters\n"); + + if (check_lcore_params() < 0) + rte_exit(EXIT_FAILURE, "check_lcore_params failed\n"); + + ret = init_lcore_rx_queues(); + if (ret < 0) + rte_exit(EXIT_FAILURE, "init_lcore_rx_queues failed\n"); + + nb_ports = rte_eth_dev_count_avail(); + + if (check_port_config() < 0) + rte_exit(EXIT_FAILURE, "check_port_config failed\n"); + + /* Add ACL rules and route entries, build trie */ + if (app_acl_init() < 0) + rte_exit(EXIT_FAILURE, "app_acl_init failed\n"); + + nb_lcores = rte_lcore_count(); + + /* initialize all ports */ + 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); + continue; + } + + /* init port */ + printf("Initializing port %d ... ", portid); + fflush(stdout); + + nb_rx_queue = get_port_n_rx_queues(portid); + n_tx_queue = nb_lcores; + if (n_tx_queue > MAX_TX_QUEUE_PER_PORT) + n_tx_queue = MAX_TX_QUEUE_PER_PORT; + printf("Creating queues: nb_rxq=%d nb_txq=%u... ", + nb_rx_queue, (unsigned)n_tx_queue); + 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, &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, + "rte_eth_dev_adjust_nb_rx_tx_desc: err=%d, port=%d\n", + ret, portid); + + rte_eth_macaddr_get(portid, &ports_eth_addr[portid]); + print_ethaddr(" Address:", &ports_eth_addr[portid]); + printf(", "); + + /* init memory */ + ret = init_mem(NB_MBUF); + 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", + (unsigned) 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 (numa_on) + socketid = (uint8_t) + rte_lcore_to_socket_id(lcore_id); + else + socketid = 0; + + printf("txq=%u,%d,%d ", lcore_id, queueid, socketid); + fflush(stdout); + + rte_eth_dev_info_get(portid, &dev_info); + txconf = &dev_info.default_txconf; + txconf->offloads = local_port_conf.txmode.offloads; + ret = rte_eth_tx_queue_setup(portid, queueid, nb_txd, + socketid, txconf); + if (ret < 0) + rte_exit(EXIT_FAILURE, + "rte_eth_tx_queue_setup: err=%d, " + "port=%d\n", ret, portid); + + 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"); + } + + for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) { + if (rte_lcore_is_enabled(lcore_id) == 0) + continue; + 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_dev *dev; + struct rte_eth_conf *conf; + struct rte_eth_rxconf rxq_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 = (uint8_t) + rte_lcore_to_socket_id(lcore_id); + else + socketid = 0; + + 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, &rxq_conf, + pktmbuf_pool[socketid]); + if (ret < 0) + rte_exit(EXIT_FAILURE, + "rte_eth_rx_queue_setup: err=%d," + "port=%d\n", ret, portid); + } + } + + printf("\n"); + + /* start ports */ + RTE_ETH_FOREACH_DEV(portid) { + if ((enabled_port_mask & (1 << portid)) == 0) + continue; + + /* Start device */ + ret = rte_eth_dev_start(portid); + 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 + * to itself through 2 cross-connected ports of the + * target machine. + */ + if (promiscuous_on) + rte_eth_promiscuous_enable(portid); + } + + check_all_ports_link_status(enabled_port_mask); + + /* launch per-lcore init on every lcore */ + rte_eal_mp_remote_launch(main_loop, NULL, CALL_MASTER); + RTE_LCORE_FOREACH_SLAVE(lcore_id) { + if (rte_eal_wait_lcore(lcore_id) < 0) + return -1; + } + + return 0; +} diff --git a/src/seastar/dpdk/examples/l3fwd-acl/meson.build b/src/seastar/dpdk/examples/l3fwd-acl/meson.build new file mode 100644 index 000000000..7096e00c1 --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd-acl/meson.build @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2017 Intel Corporation + +# meson file, for building this example as part of a main DPDK build. +# +# To build this example as a standalone application with an already-installed +# DPDK instance, use 'make' + +deps += ['acl', 'lpm', 'hash'] +sources = files( + 'main.c' +) diff --git a/src/seastar/dpdk/examples/l3fwd-power/Makefile b/src/seastar/dpdk/examples/l3fwd-power/Makefile new file mode 100644 index 000000000..a106b0404 --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd-power/Makefile @@ -0,0 +1,71 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2010-2018 Intel Corporation + +# binary name +APP = l3fwd-power + +# all source are stored in SRCS-y +SRCS-y := main.c perf_core.c + +# Build using pkg-config variables if possible +$(shell pkg-config --exists libdpdk) +ifeq ($(.SHELLSTATUS),0) + +all: shared +.PHONY: shared static +shared: build/$(APP)-shared + ln -sf $(APP)-shared build/$(APP) +static: build/$(APP)-static + ln -sf $(APP)-static build/$(APP) + +PC_FILE := $(shell pkg-config --path libdpdk) +CFLAGS += -O3 $(shell pkg-config --cflags libdpdk) +LDFLAGS_SHARED = $(shell pkg-config --libs libdpdk) +LDFLAGS_STATIC = -Wl,-Bstatic $(shell pkg-config --static --libs libdpdk) + +CFLAGS += -DALLOW_EXPERIMENTAL_API + +build/$(APP)-shared: $(SRCS-y) Makefile $(PC_FILE) | build + $(CC) $(CFLAGS) $(SRCS-y) -o $@ $(LDFLAGS) $(LDFLAGS_SHARED) + +build/$(APP)-static: $(SRCS-y) Makefile $(PC_FILE) | build + $(CC) $(CFLAGS) $(SRCS-y) -o $@ $(LDFLAGS) $(LDFLAGS_STATIC) + +build: + @mkdir -p $@ + +.PHONY: clean +clean: + rm -f build/$(APP) build/$(APP)-static build/$(APP)-shared + rmdir --ignore-fail-on-non-empty build + +else # Build using legacy build system + +ifeq ($(RTE_SDK),) +$(error "Please define RTE_SDK environment variable") +endif + +# Default target, detect a build directory, by looking for a path with a .config +RTE_TARGET ?= $(notdir $(abspath $(dir $(firstword $(wildcard $(RTE_SDK)/*/.config))))) + +include $(RTE_SDK)/mk/rte.vars.mk + +ifneq ($(CONFIG_RTE_EXEC_ENV_LINUX),y) +$(info This application can only operate in a linux environment, \ +please change the definition of the RTE_TARGET environment variable) +all: +else + +CFLAGS += -DALLOW_EXPERIMENTAL_API +CFLAGS += -O3 +CFLAGS += $(WERROR_FLAGS) + +# workaround for a gcc bug with noreturn attribute +# http://gcc.gnu.org/bugzilla/show_bug.cgi?id=12603 +ifeq ($(CONFIG_RTE_TOOLCHAIN_GCC),y) +CFLAGS_main.o += -Wno-return-type +endif + +include $(RTE_SDK)/mk/rte.extapp.mk +endif +endif diff --git a/src/seastar/dpdk/examples/l3fwd-power/main.c b/src/seastar/dpdk/examples/l3fwd-power/main.c new file mode 100644 index 000000000..3b448acc4 --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd-power/main.c @@ -0,0 +1,2224 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2010-2018 Intel Corporation + */ + +#include <stdio.h> +#include <stdlib.h> +#include <stdint.h> +#include <inttypes.h> +#include <sys/types.h> +#include <string.h> +#include <sys/queue.h> +#include <stdarg.h> +#include <errno.h> +#include <getopt.h> +#include <unistd.h> +#include <signal.h> + +#include <rte_common.h> +#include <rte_byteorder.h> +#include <rte_log.h> +#include <rte_malloc.h> +#include <rte_memory.h> +#include <rte_memcpy.h> +#include <rte_eal.h> +#include <rte_launch.h> +#include <rte_atomic.h> +#include <rte_cycles.h> +#include <rte_prefetch.h> +#include <rte_lcore.h> +#include <rte_per_lcore.h> +#include <rte_branch_prediction.h> +#include <rte_interrupts.h> +#include <rte_random.h> +#include <rte_debug.h> +#include <rte_ether.h> +#include <rte_ethdev.h> +#include <rte_mempool.h> +#include <rte_mbuf.h> +#include <rte_ip.h> +#include <rte_tcp.h> +#include <rte_udp.h> +#include <rte_string_fns.h> +#include <rte_timer.h> +#include <rte_power.h> +#include <rte_spinlock.h> +#include <rte_power_empty_poll.h> + +#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 10 + +/* 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 + +#define APP_LOOKUP_EXACT_MATCH 0 +#define APP_LOOKUP_LPM 1 +#define DO_RFC_1812_CHECKS + +#ifndef APP_LOOKUP_METHOD +#define APP_LOOKUP_METHOD APP_LOOKUP_LPM +#endif + +#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH) +#include <rte_hash.h> +#elif (APP_LOOKUP_METHOD == APP_LOOKUP_LPM) +#include <rte_lpm.h> +#else +#error "APP_LOOKUP_METHOD set to incorrect value" +#endif + +#ifndef IPv6_BYTES +#define IPv6_BYTES_FMT "%02x%02x:%02x%02x:%02x%02x:%02x%02x:"\ + "%02x%02x:%02x%02x:%02x%02x:%02x%02x" +#define IPv6_BYTES(addr) \ + addr[0], addr[1], addr[2], addr[3], \ + addr[4], addr[5], addr[6], addr[7], \ + addr[8], addr[9], addr[10], addr[11],\ + addr[12], addr[13],addr[14], addr[15] +#endif + +#define MAX_JUMBO_PKT_LEN 9600 + +#define IPV6_ADDR_LEN 16 + +#define MEMPOOL_CACHE_SIZE 256 + +/* + * 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 + * per lcore and mtable per port per lcore. RTE_MAX is used to ensure that + * NB_MBUF never goes below a minimum value of 8192. + */ + +#define NB_MBUF RTE_MAX ( \ + (nb_ports*nb_rx_queue*nb_rxd + \ + nb_ports*nb_lcores*MAX_PKT_BURST + \ + nb_ports*n_tx_queue*nb_txd + \ + nb_lcores*MEMPOOL_CACHE_SIZE), \ + (unsigned)8192) + +#define BURST_TX_DRAIN_US 100 /* TX drain every ~100us */ + +#define NB_SOCKETS 8 + +/* Configure how many packets ahead to prefetch, when reading packets */ +#define PREFETCH_OFFSET 3 + +/* + * Configurable number of RX/TX ring descriptors + */ +#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]; + +/* ethernet addresses of ports */ +static rte_spinlock_t locks[RTE_MAX_ETHPORTS]; + +/* mask of enabled ports */ +static uint32_t enabled_port_mask = 0; +/* Ports set in promiscuous mode off by default. */ +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 +{ + FREQ_LOWER = -1, + FREQ_CURRENT = 0, + FREQ_HIGHER = 1, + FREQ_HIGHEST = 2 +}; + +struct lcore_rx_queue { + uint16_t port_id; + uint8_t queue_id; + enum freq_scale_hint_t freq_up_hint; + uint32_t zero_rx_packet_count; + uint32_t idle_hint; +} __rte_cache_aligned; + +#define MAX_RX_QUEUE_PER_LCORE 16 +#define MAX_TX_QUEUE_PER_PORT RTE_MAX_ETHPORTS +#define MAX_RX_QUEUE_PER_PORT 128 + +#define MAX_RX_QUEUE_INTERRUPT_PER_PORT 16 + + +struct lcore_params lcore_params_array[MAX_LCORE_PARAMS]; +static struct lcore_params lcore_params_array_default[] = { + {0, 0, 2}, + {0, 1, 2}, + {0, 2, 2}, + {1, 0, 2}, + {1, 1, 2}, + {1, 2, 2}, + {2, 0, 2}, + {3, 0, 3}, + {3, 1, 3}, +}; + +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, + .split_hdr_size = 0, + .offloads = DEV_RX_OFFLOAD_CHECKSUM, + }, + .rx_adv_conf = { + .rss_conf = { + .rss_key = NULL, + .rss_hf = ETH_RSS_UDP, + }, + }, + .txmode = { + .mq_mode = ETH_MQ_TX_NONE, + }, + .intr_conf = { + .rxq = 1, + }, +}; + +static struct rte_mempool * pktmbuf_pool[NB_SOCKETS]; + + +#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH) + +#ifdef RTE_ARCH_X86 +#include <rte_hash_crc.h> +#define DEFAULT_HASH_FUNC rte_hash_crc +#else +#include <rte_jhash.h> +#define DEFAULT_HASH_FUNC rte_jhash +#endif + +struct ipv4_5tuple { + uint32_t ip_dst; + uint32_t ip_src; + uint16_t port_dst; + uint16_t port_src; + uint8_t proto; +} __attribute__((__packed__)); + +struct ipv6_5tuple { + uint8_t ip_dst[IPV6_ADDR_LEN]; + uint8_t ip_src[IPV6_ADDR_LEN]; + uint16_t port_dst; + uint16_t port_src; + uint8_t proto; +} __attribute__((__packed__)); + +struct ipv4_l3fwd_route { + struct ipv4_5tuple key; + uint8_t if_out; +}; + +struct ipv6_l3fwd_route { + struct ipv6_5tuple key; + uint8_t if_out; +}; + +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}, +}; + +static struct ipv6_l3fwd_route ipv6_l3fwd_route_array[] = { + { + { + {0xfe, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x02, 0x1b, 0x21, 0xff, 0xfe, 0x91, 0x38, 0x05}, + {0xfe, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x02, 0x1e, 0x67, 0xff, 0xfe, 0x0d, 0xb6, 0x0a}, + 1, 10, IPPROTO_UDP + }, 4 + }, +}; + +typedef struct rte_hash lookup_struct_t; +static lookup_struct_t *ipv4_l3fwd_lookup_struct[NB_SOCKETS]; +static lookup_struct_t *ipv6_l3fwd_lookup_struct[NB_SOCKETS]; + +#define L3FWD_HASH_ENTRIES 1024 + +#define IPV4_L3FWD_NUM_ROUTES \ + (sizeof(ipv4_l3fwd_route_array) / sizeof(ipv4_l3fwd_route_array[0])) + +#define IPV6_L3FWD_NUM_ROUTES \ + (sizeof(ipv6_l3fwd_route_array) / sizeof(ipv6_l3fwd_route_array[0])) + +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) +struct ipv4_l3fwd_route { + uint32_t ip; + uint8_t depth; + uint8_t if_out; +}; + +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}, +}; + +#define IPV4_L3FWD_NUM_ROUTES \ + (sizeof(ipv4_l3fwd_route_array) / sizeof(ipv4_l3fwd_route_array[0])) + +#define IPV4_L3FWD_LPM_MAX_RULES 1024 + +typedef struct rte_lpm lookup_struct_t; +static lookup_struct_t *ipv4_l3fwd_lookup_struct[NB_SOCKETS]; +#endif + +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 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; + +struct lcore_stats { + /* total sleep time in ms since last frequency scaling down */ + uint32_t sleep_time; + /* number of long sleep recently */ + uint32_t nb_long_sleep; + /* freq. scaling up trend */ + uint32_t trend; + /* total packet processed recently */ + uint64_t nb_rx_processed; + /* total iterations looped recently */ + uint64_t nb_iteration_looped; + uint32_t padding[9]; +} __rte_cache_aligned; + +static struct lcore_conf lcore_conf[RTE_MAX_LCORE] __rte_cache_aligned; +static struct lcore_stats stats[RTE_MAX_LCORE] __rte_cache_aligned; +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 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; + + /* init power management library */ + ret = rte_power_exit(lcore_id); + if (ret) + rte_exit(EXIT_FAILURE, "Power management " + "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); + } + } + } + + if (!empty_poll_on) + rte_exit(EXIT_SUCCESS, "User forced exit\n"); +} + +/* Freqency scale down timer callback */ +static void +power_timer_cb(__attribute__((unused)) struct rte_timer *tim, + __attribute__((unused)) void *arg) +{ + uint64_t hz; + float sleep_time_ratio; + unsigned lcore_id = rte_lcore_id(); + + /* 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) { + 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) { + /** + * scale down a step if average packet per iteration less + * than expectation. + */ + if (rte_power_freq_down) + rte_power_freq_down(lcore_id); + } + + /** + * initialize another timer according to current frequency to ensure + * timer interval is relatively fixed. + */ + hz = rte_get_timer_hz(); + rte_timer_reset(&power_timers[lcore_id], hz/TIMER_NUMBER_PER_SECOND, + SINGLE, lcore_id, power_timer_cb, NULL); + + stats[lcore_id].nb_rx_processed = 0; + stats[lcore_id].nb_iteration_looped = 0; + + stats[lcore_id].sleep_time = 0; +} + +/* Enqueue a single packet, and send burst if queue is filled */ +static inline int +send_single_packet(struct rte_mbuf *m, uint16_t port) +{ + uint32_t lcore_id; + struct lcore_conf *qconf; + + lcore_id = rte_lcore_id(); + qconf = &lcore_conf[lcore_id]; + + 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) +{ + /* 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)) + return -1; + + /* 2. The IP checksum must be correct. */ + /* this is checked in H/W */ + + /* + * 3. The IP version number must be 4. If the version number is not 4 + * then the packet may be another version of IP, such as IPng or + * ST-II. + */ + if (((pkt->version_ihl) >> 4) != 4) + return -3; + /* + * 4. The IP header length field must be large enough to hold the + * minimum length legal IP datagram (20 bytes = 5 words). + */ + if ((pkt->version_ihl & 0xf) < 5) + return -4; + + /* + * 5. The IP total length field must be large enough to hold the IP + * 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)) + return -5; + + return 0; +} +#endif + +#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH) +static void +print_ipv4_key(struct ipv4_5tuple key) +{ + printf("IP dst = %08x, IP src = %08x, port dst = %d, port src = %d, " + "proto = %d\n", (unsigned)key.ip_dst, (unsigned)key.ip_src, + key.port_dst, key.port_src, key.proto); +} +static void +print_ipv6_key(struct ipv6_5tuple key) +{ + printf( "IP dst = " IPv6_BYTES_FMT ", IP src = " IPv6_BYTES_FMT ", " + "port dst = %d, port src = %d, proto = %d\n", + IPv6_BYTES(key.ip_dst), IPv6_BYTES(key.ip_src), + key.port_dst, key.port_src, key.proto); +} + +static inline uint16_t +get_ipv4_dst_port(struct ipv4_hdr *ipv4_hdr, uint16_t portid, + lookup_struct_t * ipv4_l3fwd_lookup_struct) +{ + struct ipv4_5tuple key; + struct tcp_hdr *tcp; + struct udp_hdr *udp; + int ret = 0; + + key.ip_dst = rte_be_to_cpu_32(ipv4_hdr->dst_addr); + key.ip_src = rte_be_to_cpu_32(ipv4_hdr->src_addr); + key.proto = ipv4_hdr->next_proto_id; + + switch (ipv4_hdr->next_proto_id) { + case IPPROTO_TCP: + tcp = (struct tcp_hdr *)((unsigned char *)ipv4_hdr + + sizeof(struct 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)); + key.port_dst = rte_be_to_cpu_16(udp->dst_port); + key.port_src = rte_be_to_cpu_16(udp->src_port); + break; + + default: + key.port_dst = 0; + key.port_src = 0; + break; + } + + /* Find destination port */ + ret = rte_hash_lookup(ipv4_l3fwd_lookup_struct, (const void *)&key); + return ((ret < 0) ? portid : ipv4_l3fwd_out_if[ret]); +} + +static inline uint16_t +get_ipv6_dst_port(struct ipv6_hdr *ipv6_hdr, uint16_t portid, + lookup_struct_t *ipv6_l3fwd_lookup_struct) +{ + struct ipv6_5tuple key; + struct tcp_hdr *tcp; + struct udp_hdr *udp; + int ret = 0; + + memcpy(key.ip_dst, ipv6_hdr->dst_addr, IPV6_ADDR_LEN); + memcpy(key.ip_src, ipv6_hdr->src_addr, IPV6_ADDR_LEN); + + key.proto = ipv6_hdr->proto; + + switch (ipv6_hdr->proto) { + case IPPROTO_TCP: + tcp = (struct tcp_hdr *)((unsigned char *) ipv6_hdr + + sizeof(struct 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)); + key.port_dst = rte_be_to_cpu_16(udp->dst_port); + key.port_src = rte_be_to_cpu_16(udp->src_port); + break; + + default: + key.port_dst = 0; + key.port_src = 0; + break; + } + + /* Find destination port */ + ret = rte_hash_lookup(ipv6_l3fwd_lookup_struct, (const void *)&key); + return ((ret < 0) ? portid : ipv6_l3fwd_out_if[ret]); +} +#endif + +#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM) +static inline uint16_t +get_ipv4_dst_port(struct ipv4_hdr *ipv4_hdr, uint16_t portid, + lookup_struct_t *ipv4_l3fwd_lookup_struct) +{ + uint32_t next_hop; + + 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 +parse_ptype_one(struct rte_mbuf *m) +{ + struct ether_hdr *eth_hdr; + uint32_t packet_type = RTE_PTYPE_UNKNOWN; + uint16_t ether_type; + + eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *); + ether_type = eth_hdr->ether_type; + if (ether_type == rte_cpu_to_be_16(ETHER_TYPE_IPv4)) + packet_type |= RTE_PTYPE_L3_IPV4_EXT_UNKNOWN; + else if (ether_type == rte_cpu_to_be_16(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; + void *d_addr_bytes; + uint16_t dst_port; + + eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *); + + if (RTE_ETH_IS_IPV4_HDR(m->packet_type)) { + /* Handle IPv4 headers.*/ + ipv4_hdr = + rte_pktmbuf_mtod_offset(m, struct ipv4_hdr *, + sizeof(struct ether_hdr)); + +#ifdef DO_RFC_1812_CHECKS + /* Check to make sure the packet is valid (RFC1812) */ + if (is_valid_ipv4_pkt(ipv4_hdr, m->pkt_len) < 0) { + rte_pktmbuf_free(m); + return; + } +#endif + + dst_port = get_ipv4_dst_port(ipv4_hdr, portid, + qconf->ipv4_lookup_struct); + if (dst_port >= RTE_MAX_ETHPORTS || + (enabled_port_mask & 1 << dst_port) == 0) + dst_port = portid; + + /* 02:00:00:00:00:xx */ + d_addr_bytes = ð_hdr->d_addr.addr_bytes[0]; + *((uint64_t *)d_addr_bytes) = + 0x000000000002 + ((uint64_t)dst_port << 40); + +#ifdef DO_RFC_1812_CHECKS + /* Update time to live and header checksum */ + --(ipv4_hdr->time_to_live); + ++(ipv4_hdr->hdr_checksum); +#endif + + /* src addr */ + ether_addr_copy(&ports_eth_addr[dst_port], ð_hdr->s_addr); + + send_single_packet(m, dst_port); + } 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; + + ipv6_hdr = + rte_pktmbuf_mtod_offset(m, struct ipv6_hdr *, + sizeof(struct ether_hdr)); + + dst_port = get_ipv6_dst_port(ipv6_hdr, portid, + qconf->ipv6_lookup_struct); + + if (dst_port >= RTE_MAX_ETHPORTS || + (enabled_port_mask & 1 << dst_port) == 0) + dst_port = portid; + + /* 02:00:00:00:00:xx */ + d_addr_bytes = ð_hdr->d_addr.addr_bytes[0]; + *((uint64_t *)d_addr_bytes) = + 0x000000000002 + ((uint64_t)dst_port << 40); + + /* src addr */ + 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 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, 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, + 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 + */ +#define FREQ_GEAR1_RX_PACKET_THRESHOLD MAX_PKT_BURST +#define FREQ_GEAR2_RX_PACKET_THRESHOLD (MAX_PKT_BURST*2) +#define FREQ_GEAR3_RX_PACKET_THRESHOLD (MAX_PKT_BURST*3) +#define FREQ_UP_TREND1_ACC 1 +#define FREQ_UP_TREND2_ACC 100 +#define FREQ_UP_THRESHOLD 10000 + + if (likely(rxq_count > FREQ_GEAR3_RX_PACKET_THRESHOLD)) { + stats[lcore_id].trend = 0; + return FREQ_HIGHEST; + } else if (likely(rxq_count > FREQ_GEAR2_RX_PACKET_THRESHOLD)) + stats[lcore_id].trend += FREQ_UP_TREND2_ACC; + 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)) { + stats[lcore_id].trend = 0; + return FREQ_HIGHER; + } + + 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, tim_res_tsc, hz; + uint64_t prev_tsc_power = 0, cur_tsc_power, diff_tsc_power; + int i, j, nb_rx; + 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]; + + if (qconf->n_rx_queue == 0) { + RTE_LOG(INFO, L3FWD_POWER, "lcore %u has nothing to do\n", lcore_id); + return 0; + } + + 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=%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++; + + cur_tsc = rte_rdtsc(); + cur_tsc_power = cur_tsc; + + /* + * 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; + } + + diff_tsc_power = cur_tsc_power - prev_tsc_power; + if (diff_tsc_power > tim_res_tsc) { + rte_timer_manage(); + prev_tsc_power = cur_tsc_power; + } + +start_rx: + /* + * Read packet from RX queues + */ + lcore_scaleup_hint = FREQ_CURRENT; + lcore_rx_idle_count = 0; + 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 (unlikely(nb_rx == 0)) { + /** + * no packet received from rx queue, try to + * sleep for a while forcing CPU enter deeper + * C states. + */ + rx_queue->zero_rx_packet_count++; + + if (rx_queue->zero_rx_packet_count <= + MIN_ZERO_POLL_COUNT) + continue; + + rx_queue->idle_hint = power_idle_heuristic(\ + rx_queue->zero_rx_packet_count); + lcore_rx_idle_count++; + } else { + rx_queue->zero_rx_packet_count = 0; + + /** + * do not scale up frequency immediately as + * user to kernel space communication is costly + * which might impact packet I/O for received + * packets. + */ + 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++) { + 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); + } + } + + if (likely(lcore_rx_idle_count != qconf->n_rx_queue)) { + for (i = 1, lcore_scaleup_hint = + qconf->rx_queue_list[0].freq_up_hint; + i < qconf->n_rx_queue; ++i) { + rx_queue = &(qconf->rx_queue_list[i]); + if (rx_queue->freq_up_hint > + lcore_scaleup_hint) + lcore_scaleup_hint = + rx_queue->freq_up_hint; + } + + 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. + */ + for (i = 1, lcore_idle_hint = + qconf->rx_queue_list[0].idle_hint; + i < qconf->n_rx_queue; ++i) { + rx_queue = &(qconf->rx_queue_list[i]); + if (rx_queue->idle_hint < lcore_idle_hint) + lcore_idle_hint = rx_queue->idle_hint; + } + + if (lcore_idle_hint < SUSPEND_THRESHOLD) + /** + * execute "pause" instruction to avoid context + * switch which generally take hundred of + * microseconds for short sleep. + */ + rte_delay_us(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; + } + } +} + +static int +check_lcore_params(void) +{ + uint8_t queue, lcore; + uint16_t i; + int socketid; + + for (i = 0; i < nb_lcore_params; ++i) { + queue = lcore_params[i].queue_id; + if (queue >= MAX_RX_QUEUE_PER_PORT) { + printf("invalid queue number: %hhu\n", queue); + return -1; + } + lcore = lcore_params[i].lcore_id; + if (!rte_lcore_is_enabled(lcore)) { + printf("error: lcore %hhu is not enabled in lcore " + "mask\n", lcore); + return -1; + } + if ((socketid = rte_lcore_to_socket_id(lcore) != 0) && + (numa_on == 0)) { + printf("warning: lcore %hhu is on socket %d with numa " + "off\n", lcore, socketid); + } + } + return 0; +} + +static int +check_port_config(void) +{ + unsigned portid; + uint16_t i; + + for (i = 0; i < nb_lcore_params; ++i) { + portid = lcore_params[i].port_id; + if ((enabled_port_mask & (1 << portid)) == 0) { + printf("port %u is not enabled in port mask\n", + portid); + return -1; + } + if (!rte_eth_dev_is_valid_port(portid)) { + printf("port %u is not present on the board\n", + portid); + return -1; + } + } + return 0; +} + +static uint8_t +get_port_n_rx_queues(const uint16_t port) +{ + int queue = -1; + uint16_t i; + + for (i = 0; i < nb_lcore_params; ++i) { + if (lcore_params[i].port_id == port && + lcore_params[i].queue_id > queue) + queue = lcore_params[i].queue_id; + } + return (uint8_t)(++queue); +} + +static int +init_lcore_rx_queues(void) +{ + uint16_t i, nb_rx_queue; + uint8_t lcore; + + for (i = 0; i < nb_lcore_params; ++i) { + lcore = lcore_params[i].lcore_id; + nb_rx_queue = lcore_conf[lcore].n_rx_queue; + if (nb_rx_queue >= MAX_RX_QUEUE_PER_LCORE) { + printf("error: too many queues (%u) for lcore: %u\n", + (unsigned)nb_rx_queue + 1, (unsigned)lcore); + return -1; + } else { + lcore_conf[lcore].rx_queue_list[nb_rx_queue].port_id = + lcore_params[i].port_id; + lcore_conf[lcore].rx_queue_list[nb_rx_queue].queue_id = + lcore_params[i].queue_id; + lcore_conf[lcore].n_rx_queue++; + } + } + return 0; +} + +/* display usage */ +static void +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" + " --parse-ptype: parse packet type by software\n" + " --empty-poll: enable empty poll detection" + " follow (training_flag, high_threshold, med_threshold)\n", + prgname); +} + +static int parse_max_pkt_len(const char *pktlen) +{ + char *end = NULL; + unsigned long len; + + /* parse decimal string */ + len = strtoul(pktlen, &end, 10); + if ((pktlen[0] == '\0') || (end == NULL) || (*end != '\0')) + return -1; + + if (len == 0) + return -1; + + return len; +} + +static int +parse_portmask(const char *portmask) +{ + char *end = NULL; + unsigned long pm; + + /* parse hexadecimal string */ + pm = strtoul(portmask, &end, 16); + if ((portmask[0] == '\0') || (end == NULL) || (*end != '\0')) + return -1; + + if (pm == 0) + return -1; + + return pm; +} + +static int +parse_config(const char *q_arg) +{ + char s[256]; + const char *p, *p0 = q_arg; + char *end; + enum fieldnames { + FLD_PORT = 0, + FLD_QUEUE, + FLD_LCORE, + _NUM_FLD + }; + unsigned long int_fld[_NUM_FLD]; + char *str_fld[_NUM_FLD]; + int i; + unsigned size; + + nb_lcore_params = 0; + + while ((p = strchr(p0,'(')) != NULL) { + ++p; + if((p0 = strchr(p,')')) == NULL) + return -1; + + size = p0 - p; + if(size >= sizeof(s)) + return -1; + + snprintf(s, sizeof(s), "%.*s", size, p); + if (rte_strsplit(s, sizeof(s), str_fld, _NUM_FLD, ',') != + _NUM_FLD) + return -1; + for (i = 0; i < _NUM_FLD; i++){ + errno = 0; + int_fld[i] = strtoul(str_fld[i], &end, 0); + if (errno != 0 || end == str_fld[i] || int_fld[i] > + 255) + return -1; + } + if (nb_lcore_params >= MAX_LCORE_PARAMS) { + printf("exceeded max number of lcore params: %hu\n", + nb_lcore_params); + return -1; + } + lcore_params_array[nb_lcore_params].port_id = + (uint8_t)int_fld[FLD_PORT]; + lcore_params_array[nb_lcore_params].queue_id = + (uint8_t)int_fld[FLD_QUEUE]; + lcore_params_array[nb_lcore_params].lcore_id = + (uint8_t)int_fld[FLD_LCORE]; + ++nb_lcore_params; + } + lcore_params = lcore_params_array; + + 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 +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:l:m:h:P", + lgopts, &option_index)) != EOF) { + + switch (opt) { + /* portmask */ + case 'p': + enabled_port_mask = parse_portmask(optarg); + if (enabled_port_mask == 0) { + printf("invalid portmask\n"); + print_usage(prgname); + return -1; + } + break; + case 'P': + 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)) { + ret = parse_config(optarg); + if (ret) { + printf("invalid config\n"); + print_usage(prgname); + return -1; + } + } + + 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 = + {"max-pkt-len", required_argument, \ + 0, 0}; + + printf("jumbo frame is enabled \n"); + 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 + */ + if (0 == getopt_long(argc, argvopt, "", + &lenopts, &option_index)) { + ret = parse_max_pkt_len(optarg); + if ((ret < 64) || + (ret > MAX_JUMBO_PKT_LEN)){ + printf("invalid packet " + "length\n"); + print_usage(prgname); + return -1; + } + port_conf.rxmode.max_rx_pkt_len = ret; + } + printf("set jumbo frame " + "max packet length to %u\n", + (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: + print_usage(prgname); + return -1; + } + } + + if (optind >= 0) + argv[optind-1] = prgname; + + ret = optind-1; + optind = 1; /* reset getopt lib */ + return ret; +} + +static void +print_ethaddr(const char *name, const struct ether_addr *eth_addr) +{ + char buf[ETHER_ADDR_FMT_SIZE]; + ether_format_addr(buf, ETHER_ADDR_FMT_SIZE, eth_addr); + printf("%s%s", name, buf); +} + +#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH) +static void +setup_hash(int socketid) +{ + struct rte_hash_parameters ipv4_l3fwd_hash_params = { + .name = NULL, + .entries = L3FWD_HASH_ENTRIES, + .key_len = sizeof(struct ipv4_5tuple), + .hash_func = DEFAULT_HASH_FUNC, + .hash_func_init_val = 0, + }; + + struct rte_hash_parameters ipv6_l3fwd_hash_params = { + .name = NULL, + .entries = L3FWD_HASH_ENTRIES, + .key_len = sizeof(struct ipv6_5tuple), + .hash_func = DEFAULT_HASH_FUNC, + .hash_func_init_val = 0, + }; + + unsigned i; + int ret; + char s[64]; + + /* create ipv4 hash */ + snprintf(s, sizeof(s), "ipv4_l3fwd_hash_%d", socketid); + ipv4_l3fwd_hash_params.name = s; + ipv4_l3fwd_hash_params.socket_id = socketid; + ipv4_l3fwd_lookup_struct[socketid] = + rte_hash_create(&ipv4_l3fwd_hash_params); + if (ipv4_l3fwd_lookup_struct[socketid] == NULL) + rte_exit(EXIT_FAILURE, "Unable to create the l3fwd hash on " + "socket %d\n", socketid); + + /* create ipv6 hash */ + snprintf(s, sizeof(s), "ipv6_l3fwd_hash_%d", socketid); + ipv6_l3fwd_hash_params.name = s; + ipv6_l3fwd_hash_params.socket_id = socketid; + ipv6_l3fwd_lookup_struct[socketid] = + rte_hash_create(&ipv6_l3fwd_hash_params); + if (ipv6_l3fwd_lookup_struct[socketid] == NULL) + rte_exit(EXIT_FAILURE, "Unable to create the l3fwd hash on " + "socket %d\n", socketid); + + + /* populate the ipv4 hash */ + for (i = 0; i < IPV4_L3FWD_NUM_ROUTES; i++) { + ret = rte_hash_add_key (ipv4_l3fwd_lookup_struct[socketid], + (void *) &ipv4_l3fwd_route_array[i].key); + if (ret < 0) { + rte_exit(EXIT_FAILURE, "Unable to add entry %u to the" + "l3fwd hash on socket %d\n", i, socketid); + } + ipv4_l3fwd_out_if[ret] = ipv4_l3fwd_route_array[i].if_out; + printf("Hash: Adding key\n"); + print_ipv4_key(ipv4_l3fwd_route_array[i].key); + } + + /* populate the ipv6 hash */ + for (i = 0; i < IPV6_L3FWD_NUM_ROUTES; i++) { + ret = rte_hash_add_key (ipv6_l3fwd_lookup_struct[socketid], + (void *) &ipv6_l3fwd_route_array[i].key); + if (ret < 0) { + rte_exit(EXIT_FAILURE, "Unable to add entry %u to the" + "l3fwd hash on socket %d\n", i, socketid); + } + ipv6_l3fwd_out_if[ret] = ipv6_l3fwd_route_array[i].if_out; + printf("Hash: Adding key\n"); + print_ipv6_key(ipv6_l3fwd_route_array[i].key); + } +} +#endif + +#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM) +static void +setup_lpm(int socketid) +{ + unsigned i; + int ret; + 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, &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); + + /* populate the LPM table */ + for (i = 0; i < IPV4_L3FWD_NUM_ROUTES; i++) { + ret = rte_lpm_add(ipv4_l3fwd_lookup_struct[socketid], + ipv4_l3fwd_route_array[i].ip, + ipv4_l3fwd_route_array[i].depth, + ipv4_l3fwd_route_array[i].if_out); + + if (ret < 0) { + rte_exit(EXIT_FAILURE, "Unable to add entry %u to the " + "l3fwd LPM table on socket %d\n", + i, socketid); + } + + printf("LPM: Adding route 0x%08x / %d (%d)\n", + (unsigned)ipv4_l3fwd_route_array[i].ip, + ipv4_l3fwd_route_array[i].depth, + ipv4_l3fwd_route_array[i].if_out); + } +} +#endif + +static int +init_mem(unsigned nb_mbuf) +{ + struct lcore_conf *qconf; + int socketid; + unsigned lcore_id; + char s[64]; + + for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) { + if (rte_lcore_is_enabled(lcore_id) == 0) + continue; + + if (numa_on) + socketid = rte_lcore_to_socket_id(lcore_id); + else + socketid = 0; + + if (socketid >= NB_SOCKETS) { + rte_exit(EXIT_FAILURE, "Socket %d of lcore %u is " + "out of range %d\n", socketid, + lcore_id, NB_SOCKETS); + } + if (pktmbuf_pool[socketid] == NULL) { + snprintf(s, sizeof(s), "mbuf_pool_%d", socketid); + pktmbuf_pool[socketid] = + 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", + socketid); + else + printf("Allocated mbuf pool on socket %d\n", + socketid); + +#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM) + setup_lpm(socketid); +#else + setup_hash(socketid); +#endif + } + qconf = &lcore_conf[lcore_id]; + qconf->ipv4_lookup_struct = ipv4_l3fwd_lookup_struct[socketid]; +#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH) + qconf->ipv6_lookup_struct = ipv6_l3fwd_lookup_struct[socketid]; +#endif + } + return 0; +} + +/* Check the link status of all ports in up to 9s, and print them finally */ +static void +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 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; + RTE_ETH_FOREACH_DEV(portid) { + if ((port_mask & (1 << portid)) == 0) + continue; + memset(&link, 0, sizeof(link)); + rte_eth_link_get_nowait(portid, &link); + /* print link status if flag set */ + if (print_flag == 1) { + if (link.link_status) + printf("Port %d Link Up - speed %u " + "Mbps - %s\n", (uint8_t)portid, + (unsigned)link.link_speed, + (link.link_duplex == ETH_LINK_FULL_DUPLEX) ? + ("full-duplex") : ("half-duplex\n")); + else + printf("Port %d Link Down\n", + (uint8_t)portid); + continue; + } + /* clear all_ports_up flag if any link down */ + if (link.link_status == ETH_LINK_DOWN) { + all_ports_up = 0; + break; + } + } + /* after finally printing all link status, get out */ + if (print_flag == 1) + break; + + if (all_ports_up == 0) { + printf("."); + fflush(stdout); + rte_delay_ms(CHECK_INTERVAL); + } + + /* set the print_flag if all ports up or timeout */ + if (all_ports_up == 1 || count == (MAX_CHECK_TIME - 1)) { + print_flag = 1; + printf("done\n"); + } + } +} + +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) +{ + struct lcore_conf *qconf; + struct rte_eth_dev_info dev_info; + struct rte_eth_txconf *txconf; + int ret; + uint16_t nb_ports; + uint16_t queueid; + unsigned lcore_id; + uint64_t hz; + uint32_t n_tx_queue, nb_lcores; + 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); + + /* init EAL */ + ret = rte_eal_init(argc, argv); + if (ret < 0) + rte_exit(EXIT_FAILURE, "Invalid EAL parameters\n"); + argc -= ret; + argv += ret; + + /* init RTE timer library to be used late */ + rte_timer_subsystem_init(); + + /* parse application arguments (after the EAL ones) */ + ret = parse_args(argc, 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"); + + ret = init_lcore_rx_queues(); + if (ret < 0) + rte_exit(EXIT_FAILURE, "init_lcore_rx_queues failed\n"); + + nb_ports = rte_eth_dev_count_avail(); + + if (check_port_config() < 0) + rte_exit(EXIT_FAILURE, "check_port_config failed\n"); + + nb_lcores = rte_lcore_count(); + + /* initialize all ports */ + 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); + continue; + } + + /* init port */ + 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 > 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, &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(", "); + + /* init memory */ + ret = init_mem(NB_MBUF); + 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); + else + socketid = 0; + + printf("txq=%u,%d,%d ", lcore_id, queueid, socketid); + fflush(stdout); + + txconf = &dev_info.default_txconf; + txconf->offloads = local_port_conf.txmode.offloads; + ret = rte_eth_tx_queue_setup(portid, queueid, nb_txd, + socketid, txconf); + if (ret < 0) + rte_exit(EXIT_FAILURE, + "rte_eth_tx_queue_setup: err=%d, " + "port=%d\n", ret, portid); + + 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"); + } + + for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) { + if (rte_lcore_is_enabled(lcore_id) == 0) + continue; + + 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 = \ + (uint8_t)rte_lcore_to_socket_id(lcore_id); + else + socketid = 0; + + 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, &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 */ + RTE_ETH_FOREACH_DEV(portid) { + if ((enabled_port_mask & (1 << portid)) == 0) { + continue; + } + /* Start device */ + ret = rte_eth_dev_start(portid); + 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 + * to itself through 2 cross-connected ports of the + * target machine. + */ + 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"); + } + + + /* launch per-lcore init on every lcore */ + 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; +} diff --git a/src/seastar/dpdk/examples/l3fwd-power/main.h b/src/seastar/dpdk/examples/l3fwd-power/main.h new file mode 100644 index 000000000..258de98f5 --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd-power/main.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2010-2018 Intel Corporation + */ + +#ifndef _MAIN_H_ +#define _MAIN_H_ + + +#define MAX_LCORE_PARAMS 1024 +struct lcore_params { + uint16_t port_id; + uint8_t queue_id; + uint8_t lcore_id; +} __rte_cache_aligned; + +extern struct lcore_params *lcore_params; +extern uint16_t nb_lcore_params; +extern struct lcore_params lcore_params_array[]; + +#endif /* _MAIN_H_ */ diff --git a/src/seastar/dpdk/examples/l3fwd-power/meson.build b/src/seastar/dpdk/examples/l3fwd-power/meson.build new file mode 100644 index 000000000..2c84123b6 --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd-power/meson.build @@ -0,0 +1,16 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2018 Intel Corporation + +# meson file, for building this example as part of a main DPDK build. +# +# To build this example as a standalone application with an already-installed +# DPDK instance, use 'make' + +if not is_linux + build = false +endif +allow_experimental_apis = true +deps += ['power', 'timer', 'lpm', 'hash'] +sources = files( + 'main.c', 'perf_core.c' +) diff --git a/src/seastar/dpdk/examples/l3fwd-power/perf_core.c b/src/seastar/dpdk/examples/l3fwd-power/perf_core.c new file mode 100644 index 000000000..83948ea21 --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd-power/perf_core.c @@ -0,0 +1,230 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2010-2018 Intel Corporation + */ + +#include <stdio.h> +#include <string.h> + +#include <rte_common.h> +#include <rte_memory.h> +#include <rte_lcore.h> +#include <rte_power.h> +#include <rte_string_fns.h> + +#include "perf_core.h" +#include "main.h" + + +static uint16_t hp_lcores[RTE_MAX_LCORE]; +static uint16_t nb_hp_lcores; + +struct perf_lcore_params { + uint16_t port_id; + uint8_t queue_id; + uint8_t high_perf; + uint8_t lcore_idx; +} __rte_cache_aligned; + +static struct perf_lcore_params prf_lc_prms[MAX_LCORE_PARAMS]; +static uint16_t nb_prf_lc_prms; + +int +update_lcore_params(void) +{ + uint8_t non_perf_lcores[RTE_MAX_LCORE]; + uint16_t nb_non_perf_lcores = 0; + int i, j, ret; + + /* if perf-config option was not used do nothing */ + if (nb_prf_lc_prms == 0) + return 0; + + /* if high-perf-cores option was not used query every available core */ + if (nb_hp_lcores == 0) { + for (i = 0; i < RTE_MAX_LCORE; i++) { + if (rte_lcore_is_enabled(i)) { + struct rte_power_core_capabilities caps; + ret = rte_power_get_capabilities(i, &caps); + if (ret == 0 && caps.turbo) { + hp_lcores[nb_hp_lcores] = i; + nb_hp_lcores++; + } + } + } + } + + /* create a list on non high performance cores*/ + for (i = 0; i < RTE_MAX_LCORE; i++) { + if (rte_lcore_is_enabled(i)) { + int hp = 0; + for (j = 0; j < nb_hp_lcores; j++) { + if (hp_lcores[j] == i) { + hp = 1; + break; + } + } + if (!hp) + non_perf_lcores[nb_non_perf_lcores++] = i; + } + } + + /* update the lcore config */ + for (i = 0; i < nb_prf_lc_prms; i++) { + int lcore = -1; + if (prf_lc_prms[i].high_perf) { + if (prf_lc_prms[i].lcore_idx < nb_hp_lcores) + lcore = hp_lcores[prf_lc_prms[i].lcore_idx]; + } else { + if (prf_lc_prms[i].lcore_idx < nb_non_perf_lcores) + lcore = + non_perf_lcores[prf_lc_prms[i].lcore_idx]; + } + + if (lcore < 0) { + printf("Performance cores configuration error\n"); + return -1; + } + + lcore_params_array[i].lcore_id = lcore; + lcore_params_array[i].queue_id = prf_lc_prms[i].queue_id; + lcore_params_array[i].port_id = prf_lc_prms[i].port_id; + } + + lcore_params = lcore_params_array; + nb_lcore_params = nb_prf_lc_prms; + + printf("Updated performance core configuration\n"); + for (i = 0; i < nb_prf_lc_prms; i++) + printf("\t(%d,%d,%d)\n", lcore_params[i].port_id, + lcore_params[i].queue_id, + lcore_params[i].lcore_id); + + return 0; +} + +int +parse_perf_config(const char *q_arg) +{ + char s[256]; + const char *p, *p0 = q_arg; + char *end; + enum fieldnames { + FLD_PORT = 0, + FLD_QUEUE, + FLD_LCORE_HP, + FLD_LCORE_IDX, + _NUM_FLD + }; + unsigned long int_fld[_NUM_FLD]; + char *str_fld[_NUM_FLD]; + int i; + unsigned int size; + + nb_prf_lc_prms = 0; + + while ((p = strchr(p0, '(')) != NULL) { + ++p; + p0 = strchr(p, ')'); + if (p0 == NULL) + return -1; + + size = p0 - p; + if (size >= sizeof(s)) + return -1; + + snprintf(s, sizeof(s), "%.*s", size, p); + if (rte_strsplit(s, sizeof(s), str_fld, _NUM_FLD, ',') != + _NUM_FLD) + return -1; + for (i = 0; i < _NUM_FLD; i++) { + errno = 0; + int_fld[i] = strtoul(str_fld[i], &end, 0); + if (errno != 0 || end == str_fld[i] || int_fld[i] > 255) + return -1; + } + if (nb_prf_lc_prms >= MAX_LCORE_PARAMS) { + printf("exceeded max number of lcore params: %hu\n", + nb_prf_lc_prms); + return -1; + } + prf_lc_prms[nb_prf_lc_prms].port_id = + (uint8_t)int_fld[FLD_PORT]; + prf_lc_prms[nb_prf_lc_prms].queue_id = + (uint8_t)int_fld[FLD_QUEUE]; + prf_lc_prms[nb_prf_lc_prms].high_perf = + !!(uint8_t)int_fld[FLD_LCORE_HP]; + prf_lc_prms[nb_prf_lc_prms].lcore_idx = + (uint8_t)int_fld[FLD_LCORE_IDX]; + ++nb_prf_lc_prms; + } + + return 0; +} + +int +parse_perf_core_list(const char *corelist) +{ + int i, idx = 0; + unsigned int count = 0; + char *end = NULL; + int min, max; + + if (corelist == NULL) { + printf("invalid core list\n"); + return -1; + } + + + /* Remove all blank characters ahead and after */ + while (isblank(*corelist)) + corelist++; + i = strlen(corelist); + while ((i > 0) && isblank(corelist[i - 1])) + i--; + + /* Get list of cores */ + min = RTE_MAX_LCORE; + do { + while (isblank(*corelist)) + corelist++; + if (*corelist == '\0') + return -1; + errno = 0; + idx = strtoul(corelist, &end, 10); + if (errno || end == NULL) + return -1; + while (isblank(*end)) + end++; + if (*end == '-') { + min = idx; + } else if ((*end == ',') || (*end == '\0')) { + max = idx; + if (min == RTE_MAX_LCORE) + min = idx; + for (idx = min; idx <= max; idx++) { + hp_lcores[count] = idx; + count++; + } + min = RTE_MAX_LCORE; + } else { + printf("invalid core list\n"); + return -1; + } + corelist = end + 1; + } while (*end != '\0'); + + if (count == 0) { + printf("invalid core list\n"); + return -1; + } + + nb_hp_lcores = count; + + printf("Configured %d high performance cores\n", nb_hp_lcores); + for (i = 0; i < nb_hp_lcores; i++) + printf("\tHigh performance core %d %d\n", + i, hp_lcores[i]); + + return 0; +} + diff --git a/src/seastar/dpdk/examples/l3fwd-power/perf_core.h b/src/seastar/dpdk/examples/l3fwd-power/perf_core.h new file mode 100644 index 000000000..7b7b747bb --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd-power/perf_core.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2010-2018 Intel Corporation + */ + +#ifndef _PERF_CORE_H_ +#define _PERF_CORE_H_ + +int parse_perf_config(const char *q_arg); +int parse_perf_core_list(const char *corelist); +int update_lcore_params(void); + +#endif /* _PERF_CORE_H_ */ diff --git a/src/seastar/dpdk/examples/l3fwd-vf/Makefile b/src/seastar/dpdk/examples/l3fwd-vf/Makefile new file mode 100644 index 000000000..cc93603e3 --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd-vf/Makefile @@ -0,0 +1,61 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2010-2014 Intel Corporation + +# binary name +APP = l3fwd-vf + +# all source are stored in SRCS-y +SRCS-y := main.c + +# Build using pkg-config variables if possible +$(shell pkg-config --exists libdpdk) +ifeq ($(.SHELLSTATUS),0) + +all: shared +.PHONY: shared static +shared: build/$(APP)-shared + ln -sf $(APP)-shared build/$(APP) +static: build/$(APP)-static + ln -sf $(APP)-static build/$(APP) + +PC_FILE := $(shell pkg-config --path libdpdk) +CFLAGS += -O3 $(shell pkg-config --cflags libdpdk) +LDFLAGS_SHARED = $(shell pkg-config --libs libdpdk) +LDFLAGS_STATIC = -Wl,-Bstatic $(shell pkg-config --static --libs libdpdk) + +build/$(APP)-shared: $(SRCS-y) Makefile $(PC_FILE) | build + $(CC) $(CFLAGS) $(SRCS-y) -o $@ $(LDFLAGS) $(LDFLAGS_SHARED) + +build/$(APP)-static: $(SRCS-y) Makefile $(PC_FILE) | build + $(CC) $(CFLAGS) $(SRCS-y) -o $@ $(LDFLAGS) $(LDFLAGS_STATIC) + +build: + @mkdir -p $@ + +.PHONY: clean +clean: + rm -f build/$(APP) build/$(APP)-static build/$(APP)-shared + rmdir --ignore-fail-on-non-empty build + +else # Build using legacy build system + +ifeq ($(RTE_SDK),) +$(error "Please define RTE_SDK environment variable") +endif + +# Default target, detect a build directory, by looking for a path with a .config +RTE_TARGET ?= $(notdir $(abspath $(dir $(firstword $(wildcard $(RTE_SDK)/*/.config))))) + +include $(RTE_SDK)/mk/rte.vars.mk + +CFLAGS += -O3 $(USER_FLAGS) +CFLAGS += $(WERROR_FLAGS) + +# workaround for a gcc bug with noreturn attribute +# http://gcc.gnu.org/bugzilla/show_bug.cgi?id=12603 +ifeq ($(CONFIG_RTE_TOOLCHAIN_GCC),y) +CFLAGS_main.o += -Wno-return-type +endif + +include $(RTE_SDK)/mk/rte.extapp.mk +endif diff --git a/src/seastar/dpdk/examples/l3fwd-vf/main.c b/src/seastar/dpdk/examples/l3fwd-vf/main.c new file mode 100644 index 000000000..41137f978 --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd-vf/main.c @@ -0,0 +1,1096 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2010-2014 Intel Corporation + */ + +#include <stdio.h> +#include <stdlib.h> +#include <stdint.h> +#include <inttypes.h> +#include <sys/types.h> +#include <string.h> +#include <sys/queue.h> +#include <stdarg.h> +#include <errno.h> +#include <getopt.h> +#include <signal.h> + +#include <rte_common.h> +#include <rte_byteorder.h> +#include <rte_log.h> +#include <rte_memory.h> +#include <rte_memcpy.h> +#include <rte_eal.h> +#include <rte_launch.h> +#include <rte_atomic.h> +#include <rte_spinlock.h> +#include <rte_cycles.h> +#include <rte_prefetch.h> +#include <rte_lcore.h> +#include <rte_per_lcore.h> +#include <rte_branch_prediction.h> +#include <rte_interrupts.h> +#include <rte_random.h> +#include <rte_debug.h> +#include <rte_ether.h> +#include <rte_ethdev.h> +#include <rte_mempool.h> +#include <rte_mbuf.h> +#include <rte_ip.h> +#include <rte_tcp.h> +#include <rte_udp.h> +#include <rte_string_fns.h> + +#define APP_LOOKUP_EXACT_MATCH 0 +#define APP_LOOKUP_LPM 1 +#define DO_RFC_1812_CHECKS + +//#define APP_LOOKUP_METHOD APP_LOOKUP_EXACT_MATCH +#ifndef APP_LOOKUP_METHOD +#define APP_LOOKUP_METHOD APP_LOOKUP_LPM +#endif + +#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH) +#include <rte_hash.h> +#elif (APP_LOOKUP_METHOD == APP_LOOKUP_LPM) +#include <rte_lpm.h> +#else +#error "APP_LOOKUP_METHOD set to incorrect value" +#endif + +#define RTE_LOGTYPE_L3FWD RTE_LOGTYPE_USER1 + +#define MEMPOOL_CACHE_SIZE 256 + +/* + * 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 per lcore and mtable per port per lcore. + * RTE_MAX is used to ensure that NB_MBUF never goes below a minimum value of 8192 + */ + +#define NB_MBUF RTE_MAX ( \ + (nb_ports*nb_rx_queue*nb_rxd + \ + nb_ports*nb_lcores*MAX_PKT_BURST + \ + nb_ports*n_tx_queue*nb_txd + \ + nb_lcores*MEMPOOL_CACHE_SIZE), \ + (unsigned)8192) + +/* + * RX and TX Prefetch, Host, and Write-back threshold values should be + * carefully set for optimal performance. Consult the network + * controller's datasheet and supporting DPDK documentation for guidance + * on how these parameters should be set. + */ +#define RX_PTHRESH 8 /**< Default values of RX prefetch threshold reg. */ +#define RX_HTHRESH 8 /**< Default values of RX host threshold reg. */ +#define RX_WTHRESH 4 /**< Default values of RX write-back threshold reg. */ + +/* + * These default values are optimized for use with the Intel(R) 82599 10 GbE + * Controller and the DPDK ixgbe PMD. Consider using other values for other + * network controllers and/or network drivers. + */ +#define TX_PTHRESH 36 /**< Default values of TX prefetch threshold reg. */ +#define TX_HTHRESH 0 /**< Default values of TX host threshold reg. */ +#define TX_WTHRESH 0 /**< Default values of TX write-back threshold reg. */ + +#define MAX_PKT_BURST 32 +#define BURST_TX_DRAIN_US 100 /* TX drain every ~100us */ + +#define NB_SOCKETS 8 + +#define SOCKET0 0 + +/* Configure how many packets ahead to prefetch, when reading packets */ +#define PREFETCH_OFFSET 3 + +/* + * Configurable number of RX/TX ring descriptors + */ +#define RTE_TEST_RX_DESC_DEFAULT 1024 +#define RTE_TEST_TX_DESC_DEFAULT 1024 +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]; + +/* mask of enabled ports */ +static uint32_t enabled_port_mask = 0; +static int numa_on = 1; /**< NUMA is enabled by default. */ + +struct mbuf_table { + uint16_t len; + struct rte_mbuf *m_table[MAX_PKT_BURST]; +}; + +struct lcore_rx_queue { + uint16_t port_id; + uint8_t queue_id; +} __rte_cache_aligned; + +#define MAX_RX_QUEUE_PER_LCORE 16 +#define MAX_TX_QUEUE_PER_PORT 1 +#define MAX_RX_QUEUE_PER_PORT 1 + +#define MAX_LCORE_PARAMS 1024 +struct lcore_params { + uint16_t port_id; + uint8_t queue_id; + uint8_t lcore_id; +} __rte_cache_aligned; + +static struct lcore_params lcore_params_array[MAX_LCORE_PARAMS]; +static struct lcore_params lcore_params_array_default[] = { + {0, 0, 2}, + {0, 1, 2}, + {0, 2, 2}, + {1, 0, 2}, + {1, 1, 2}, + {1, 2, 2}, + {2, 0, 2}, + {3, 0, 3}, + {3, 1, 3}, +}; + +static struct lcore_params * lcore_params = lcore_params_array_default; +static 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, + .split_hdr_size = 0, + .offloads = DEV_RX_OFFLOAD_CHECKSUM, + }, + .rx_adv_conf = { + .rss_conf = { + .rss_key = NULL, + .rss_hf = ETH_RSS_IP, + }, + }, + .txmode = { + .mq_mode = ETH_MQ_TX_NONE, + }, +}; + +static struct rte_mempool * pktmbuf_pool[NB_SOCKETS]; + + +#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH) + +#ifdef RTE_ARCH_X86 +#include <rte_hash_crc.h> +#define DEFAULT_HASH_FUNC rte_hash_crc +#else +#include <rte_jhash.h> +#define DEFAULT_HASH_FUNC rte_jhash +#endif + +struct ipv4_5tuple { + uint32_t ip_dst; + uint32_t ip_src; + uint16_t port_dst; + uint16_t port_src; + uint8_t proto; +} __attribute__((__packed__)); + +struct l3fwd_route { + struct ipv4_5tuple key; + uint8_t if_out; +}; + +static struct l3fwd_route 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}, +}; + +typedef struct rte_hash lookup_struct_t; +static lookup_struct_t *l3fwd_lookup_struct[NB_SOCKETS]; + +#define L3FWD_HASH_ENTRIES 1024 +struct rte_hash_parameters l3fwd_hash_params = { + .name = "l3fwd_hash_0", + .entries = L3FWD_HASH_ENTRIES, + .key_len = sizeof(struct ipv4_5tuple), + .hash_func = DEFAULT_HASH_FUNC, + .hash_func_init_val = 0, + .socket_id = SOCKET0, +}; + +#define L3FWD_NUM_ROUTES \ + (sizeof(l3fwd_route_array) / sizeof(l3fwd_route_array[0])) + +static uint8_t l3fwd_out_if[L3FWD_HASH_ENTRIES] __rte_cache_aligned; +#endif + +#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM) +struct l3fwd_route { + uint32_t ip; + uint8_t depth; + uint8_t if_out; +}; + +static struct l3fwd_route 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}, +}; + +#define L3FWD_NUM_ROUTES \ + (sizeof(l3fwd_route_array) / sizeof(l3fwd_route_array[0])) + +#define L3FWD_LPM_MAX_RULES 1024 + +typedef struct rte_lpm lookup_struct_t; +static lookup_struct_t *l3fwd_lookup_struct[NB_SOCKETS]; +#endif + +struct lcore_conf { + uint16_t n_rx_queue; + struct lcore_rx_queue rx_queue_list[MAX_RX_QUEUE_PER_LCORE]; + uint16_t tx_queue_id; + struct mbuf_table tx_mbufs[RTE_MAX_ETHPORTS]; + lookup_struct_t * lookup_struct; +} __rte_cache_aligned; + +static struct lcore_conf lcore_conf[RTE_MAX_LCORE]; +static rte_spinlock_t spinlock_conf[RTE_MAX_ETHPORTS] = {RTE_SPINLOCK_INITIALIZER}; +/* Send burst of packets on an output interface */ +static inline int +send_burst(struct lcore_conf *qconf, uint16_t n, uint16_t port) +{ + struct rte_mbuf **m_table; + int ret; + uint16_t queueid; + + queueid = qconf->tx_queue_id; + m_table = (struct rte_mbuf **)qconf->tx_mbufs[port].m_table; + + rte_spinlock_lock(&spinlock_conf[port]); + ret = rte_eth_tx_burst(port, queueid, m_table, n); + rte_spinlock_unlock(&spinlock_conf[port]); + + 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, 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; + return 0; +} + +#ifdef DO_RFC_1812_CHECKS +static inline int +is_valid_ipv4_pkt(struct 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)) + return -1; + + /* 2. The IP checksum must be correct. */ + /* this is checked in H/W */ + + /* + * 3. The IP version number must be 4. If the version number is not 4 + * then the packet may be another version of IP, such as IPng or + * ST-II. + */ + if (((pkt->version_ihl) >> 4) != 4) + return -3; + /* + * 4. The IP header length field must be large enough to hold the + * minimum length legal IP datagram (20 bytes = 5 words). + */ + if ((pkt->version_ihl & 0xf) < 5) + return -4; + + /* + * 5. The IP total length field must be large enough to hold the IP + * 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)) + return -5; + + return 0; +} +#endif + +#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH) +static void +print_key(struct ipv4_5tuple key) +{ + printf("IP dst = %08x, IP src = %08x, port dst = %d, port src = %d, proto = %d\n", + (unsigned)key.ip_dst, (unsigned)key.ip_src, key.port_dst, key.port_src, key.proto); +} + +static inline uint16_t +get_dst_port(struct ipv4_hdr *ipv4_hdr, uint16_t portid, + lookup_struct_t *l3fwd_lookup_struct) +{ + struct ipv4_5tuple key; + struct tcp_hdr *tcp; + struct udp_hdr *udp; + int ret = 0; + + key.ip_dst = rte_be_to_cpu_32(ipv4_hdr->dst_addr); + key.ip_src = rte_be_to_cpu_32(ipv4_hdr->src_addr); + key.proto = ipv4_hdr->next_proto_id; + + switch (ipv4_hdr->next_proto_id) { + case IPPROTO_TCP: + tcp = (struct tcp_hdr *)((unsigned char *) ipv4_hdr + + sizeof(struct 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)); + key.port_dst = rte_be_to_cpu_16(udp->dst_port); + key.port_src = rte_be_to_cpu_16(udp->src_port); + break; + + default: + key.port_dst = 0; + key.port_src = 0; + } + + /* Find destination port */ + ret = rte_hash_lookup(l3fwd_lookup_struct, (const void *)&key); + return ((ret < 0) ? portid : l3fwd_out_if[ret]); +} +#endif + +#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM) +static inline uint32_t +get_dst_port(struct ipv4_hdr *ipv4_hdr, uint16_t portid, + lookup_struct_t *l3fwd_lookup_struct) +{ + uint32_t next_hop; + + return ((rte_lpm_lookup(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, uint16_t portid, + lookup_struct_t *l3fwd_lookup_struct) +{ + struct ether_hdr *eth_hdr; + struct ipv4_hdr *ipv4_hdr; + void *tmp; + uint16_t dst_port; + + eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *); + + ipv4_hdr = rte_pktmbuf_mtod_offset(m, struct ipv4_hdr *, + sizeof(struct ether_hdr)); + +#ifdef DO_RFC_1812_CHECKS + /* Check to make sure the packet is valid (RFC1812) */ + if (is_valid_ipv4_pkt(ipv4_hdr, m->pkt_len) < 0) { + rte_pktmbuf_free(m); + return; + } +#endif + + dst_port = get_dst_port(ipv4_hdr, portid, l3fwd_lookup_struct); + if (dst_port >= RTE_MAX_ETHPORTS || (enabled_port_mask & 1 << dst_port) == 0) + dst_port = portid; + + /* 02:00:00:00:00:xx */ + tmp = ð_hdr->d_addr.addr_bytes[0]; + *((uint64_t *)tmp) = 0x000000000002 + ((uint64_t)dst_port << 40); + +#ifdef DO_RFC_1812_CHECKS + /* Update time to live and header checksum */ + --(ipv4_hdr->time_to_live); + ++(ipv4_hdr->hdr_checksum); +#endif + + /* src addr */ + ether_addr_copy(&ports_eth_addr[dst_port], ð_hdr->s_addr); + + send_single_packet(m, dst_port); + +} + +/* 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; + int i, j, nb_rx; + uint8_t queueid; + uint16_t portid; + struct lcore_conf *qconf; + 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, "lcore %u has nothing to do\n", lcore_id); + return 0; + } + + RTE_LOG(INFO, L3FWD, "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, " --lcoreid=%u portid=%u rxqueueid=%hhu\n", + lcore_id, portid, queueid); + } + + while (1) { + + cur_tsc = rte_rdtsc(); + + /* + * TX burst queue drain + */ + 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; + } + + prev_tsc = cur_tsc; + } + + /* + * Read packet from RX queues + */ + 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; + nb_rx = rte_eth_rx_burst(portid, queueid, pkts_burst, MAX_PKT_BURST); + + /* 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->lookup_struct); + } + + /* Forward remaining prefetched packets */ + for (; j < nb_rx; j++) { + l3fwd_simple_forward(pkts_burst[j], portid, qconf->lookup_struct); + } + } + } +} + +static int +check_lcore_params(void) +{ + uint8_t queue, lcore; + uint16_t i; + int socketid; + + for (i = 0; i < nb_lcore_params; ++i) { + queue = lcore_params[i].queue_id; + if (queue >= MAX_RX_QUEUE_PER_PORT) { + printf("invalid queue number: %hhu\n", queue); + return -1; + } + lcore = lcore_params[i].lcore_id; + if (!rte_lcore_is_enabled(lcore)) { + printf("error: lcore %hhu is not enabled in lcore mask\n", lcore); + return -1; + } + if ((socketid = rte_lcore_to_socket_id(lcore) != 0) && + (numa_on == 0)) { + printf("warning: lcore %hhu is on socket %d with numa off \n", + lcore, socketid); + } + } + return 0; +} + +static int +check_port_config(void) +{ + unsigned portid; + uint16_t i; + + for (i = 0; i < nb_lcore_params; ++i) { + portid = lcore_params[i].port_id; + if ((enabled_port_mask & (1 << portid)) == 0) { + printf("port %u is not enabled in port mask\n", portid); + return -1; + } + if (!rte_eth_dev_is_valid_port(portid)) { + printf("port %u is not present on the board\n", portid); + return -1; + } + } + return 0; +} + +static uint8_t +get_port_n_rx_queues(const uint16_t port) +{ + int queue = -1; + uint16_t i; + + for (i = 0; i < nb_lcore_params; ++i) { + if (lcore_params[i].port_id == port && lcore_params[i].queue_id > queue) + queue = lcore_params[i].queue_id; + } + return (uint8_t)(++queue); +} + +static int +init_lcore_rx_queues(void) +{ + uint16_t i, nb_rx_queue; + uint8_t lcore; + + for (i = 0; i < nb_lcore_params; ++i) { + lcore = lcore_params[i].lcore_id; + nb_rx_queue = lcore_conf[lcore].n_rx_queue; + if (nb_rx_queue >= MAX_RX_QUEUE_PER_LCORE) { + printf("error: too many queues (%u) for lcore: %u\n", + (unsigned)nb_rx_queue + 1, (unsigned)lcore); + return -1; + } else { + lcore_conf[lcore].rx_queue_list[nb_rx_queue].port_id = + lcore_params[i].port_id; + lcore_conf[lcore].rx_queue_list[nb_rx_queue].queue_id = + lcore_params[i].queue_id; + lcore_conf[lcore].n_rx_queue++; + } + } + return 0; +} + +/* display usage */ +static void +print_usage(const char *prgname) +{ + printf ("%s [EAL options] -- -p PORTMASK" + " [--config (port,queue,lcore)[,(port,queue,lcore]]\n" + " -p PORTMASK: hexadecimal bitmask of ports to configure\n" + " --config (port,queue,lcore): rx queues configuration\n" + " --no-numa: optional, disable numa awareness\n", + prgname); +} + +/* Custom handling of signals to handle process terminal */ +static void +signal_handler(int signum) +{ + uint16_t portid; + + /* When we receive a SIGINT signal */ + if (signum == SIGINT) { + RTE_ETH_FOREACH_DEV(portid) { + /* skip ports that are not enabled */ + if ((enabled_port_mask & (1 << portid)) == 0) + continue; + rte_eth_dev_close(portid); + } + } + rte_exit(EXIT_SUCCESS, "\n User forced exit\n"); +} +static int +parse_portmask(const char *portmask) +{ + char *end = NULL; + unsigned long pm; + + /* parse hexadecimal string */ + pm = strtoul(portmask, &end, 16); + if ((portmask[0] == '\0') || (end == NULL) || (*end != '\0')) + return -1; + + if (pm == 0) + return -1; + + return pm; +} + +static int +parse_config(const char *q_arg) +{ + char s[256]; + const char *p, *p0 = q_arg; + char *end; + enum fieldnames { + FLD_PORT = 0, + FLD_QUEUE, + FLD_LCORE, + _NUM_FLD + }; + unsigned long int_fld[_NUM_FLD]; + char *str_fld[_NUM_FLD]; + int i; + unsigned size; + + nb_lcore_params = 0; + + while ((p = strchr(p0,'(')) != NULL) { + ++p; + if((p0 = strchr(p,')')) == NULL) + return -1; + + size = p0 - p; + if(size >= sizeof(s)) + return -1; + + snprintf(s, sizeof(s), "%.*s", size, p); + if (rte_strsplit(s, sizeof(s), str_fld, _NUM_FLD, ',') != _NUM_FLD) + return -1; + for (i = 0; i < _NUM_FLD; i++){ + errno = 0; + int_fld[i] = strtoul(str_fld[i], &end, 0); + if (errno != 0 || end == str_fld[i] || int_fld[i] > 255) + return -1; + } + if (nb_lcore_params >= MAX_LCORE_PARAMS) { + printf("exceeded max number of lcore params: %hu\n", + nb_lcore_params); + return -1; + } + lcore_params_array[nb_lcore_params].port_id = int_fld[FLD_PORT]; + lcore_params_array[nb_lcore_params].queue_id = (uint8_t)int_fld[FLD_QUEUE]; + lcore_params_array[nb_lcore_params].lcore_id = (uint8_t)int_fld[FLD_LCORE]; + ++nb_lcore_params; + } + lcore_params = lcore_params_array; + return 0; +} + +/* Parse the argument given in the command line of the application */ +static int +parse_args(int argc, char **argv) +{ + int opt, ret; + char **argvopt; + int option_index; + char *prgname = argv[0]; + static struct option lgopts[] = { + {"config", 1, 0, 0}, + {"no-numa", 0, 0, 0}, + {NULL, 0, 0, 0} + }; + + argvopt = argv; + + while ((opt = getopt_long(argc, argvopt, "p:", + lgopts, &option_index)) != EOF) { + + switch (opt) { + /* portmask */ + case 'p': + enabled_port_mask = parse_portmask(optarg); + if (enabled_port_mask == 0) { + printf("invalid portmask\n"); + print_usage(prgname); + return -1; + } + break; + + /* long options */ + case 0: + if (!strcmp(lgopts[option_index].name, "config")) { + ret = parse_config(optarg); + if (ret) { + printf("invalid config\n"); + print_usage(prgname); + return -1; + } + } + + if (!strcmp(lgopts[option_index].name, "no-numa")) { + printf("numa is disabled \n"); + numa_on = 0; + } + break; + + default: + print_usage(prgname); + return -1; + } + } + + if (optind >= 0) + argv[optind-1] = prgname; + + ret = optind-1; + optind = 1; /* reset getopt lib */ + return ret; +} + +static void +print_ethaddr(const char *name, const struct ether_addr *eth_addr) +{ + char buf[ETHER_ADDR_FMT_SIZE]; + ether_format_addr(buf, ETHER_ADDR_FMT_SIZE, eth_addr); + printf("%s%s", name, buf); +} + +#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH) +static void +setup_hash(int socketid) +{ + unsigned i; + int ret; + char s[64]; + + /* create hashes */ + snprintf(s, sizeof(s), "l3fwd_hash_%d", socketid); + l3fwd_hash_params.name = s; + l3fwd_hash_params.socket_id = socketid; + l3fwd_lookup_struct[socketid] = rte_hash_create(&l3fwd_hash_params); + if (l3fwd_lookup_struct[socketid] == NULL) + rte_exit(EXIT_FAILURE, "Unable to create the l3fwd hash on " + "socket %d\n", socketid); + + /* populate the hash */ + for (i = 0; i < L3FWD_NUM_ROUTES; i++) { + ret = rte_hash_add_key (l3fwd_lookup_struct[socketid], + (void *) &l3fwd_route_array[i].key); + if (ret < 0) { + rte_exit(EXIT_FAILURE, "Unable to add entry %u to the" + "l3fwd hash on socket %d\n", i, socketid); + } + l3fwd_out_if[ret] = l3fwd_route_array[i].if_out; + printf("Hash: Adding key\n"); + print_key(l3fwd_route_array[i].key); + } +} +#endif + +#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM) +static void +setup_lpm(int socketid) +{ + unsigned i; + int ret; + char s[64]; + + struct rte_lpm_config lpm_ipv4_config; + + lpm_ipv4_config.max_rules = L3FWD_LPM_MAX_RULES; + lpm_ipv4_config.number_tbl8s = 256; + lpm_ipv4_config.flags = 0; + + /* create the LPM table */ + snprintf(s, sizeof(s), "L3FWD_LPM_%d", socketid); + l3fwd_lookup_struct[socketid] = + rte_lpm_create(s, socketid, &lpm_ipv4_config); + if (l3fwd_lookup_struct[socketid] == NULL) + rte_exit(EXIT_FAILURE, "Unable to create the l3fwd LPM table" + " on socket %d\n", socketid); + + /* populate the LPM table */ + for (i = 0; i < L3FWD_NUM_ROUTES; i++) { + ret = rte_lpm_add(l3fwd_lookup_struct[socketid], + l3fwd_route_array[i].ip, + l3fwd_route_array[i].depth, + l3fwd_route_array[i].if_out); + + if (ret < 0) { + rte_exit(EXIT_FAILURE, "Unable to add entry %u to the " + "l3fwd LPM table on socket %d\n", + i, socketid); + } + + printf("LPM: Adding route 0x%08x / %d (%d)\n", + (unsigned)l3fwd_route_array[i].ip, + l3fwd_route_array[i].depth, + l3fwd_route_array[i].if_out); + } +} +#endif + +static int +init_mem(unsigned nb_mbuf) +{ + struct lcore_conf *qconf; + int socketid; + unsigned lcore_id; + char s[64]; + + for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) { + if (rte_lcore_is_enabled(lcore_id) == 0) + continue; + + if (numa_on) + socketid = rte_lcore_to_socket_id(lcore_id); + else + socketid = 0; + + if (socketid >= NB_SOCKETS) { + rte_exit(EXIT_FAILURE, "Socket %d of lcore %u is out of range %d\n", + socketid, lcore_id, NB_SOCKETS); + } + if (pktmbuf_pool[socketid] == NULL) { + snprintf(s, sizeof(s), "mbuf_pool_%d", socketid); + pktmbuf_pool[socketid] = 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", socketid); + else + printf("Allocated mbuf pool on socket %d\n", socketid); + +#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM) + setup_lpm(socketid); +#else + setup_hash(socketid); +#endif + } + qconf = &lcore_conf[lcore_id]; + qconf->lookup_struct = l3fwd_lookup_struct[socketid]; + } + return 0; +} + +int +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 queueid, portid; + unsigned lcore_id; + uint32_t nb_lcores; + uint16_t n_tx_queue; + uint8_t nb_rx_queue, queue, socketid; + + signal(SIGINT, signal_handler); + /* init EAL */ + ret = rte_eal_init(argc, argv); + if (ret < 0) + rte_exit(EXIT_FAILURE, "Invalid EAL parameters\n"); + argc -= ret; + argv += ret; + + /* parse application arguments (after the EAL ones) */ + ret = parse_args(argc, argv); + if (ret < 0) + rte_exit(EXIT_FAILURE, "Invalid L3FWD-VF parameters\n"); + + if (check_lcore_params() < 0) + rte_exit(EXIT_FAILURE, "check_lcore_params failed\n"); + + ret = init_lcore_rx_queues(); + if (ret < 0) + rte_exit(EXIT_FAILURE, "init_lcore_rx_queues failed\n"); + + nb_ports = rte_eth_dev_count_avail(); + + if (check_port_config() < 0) + rte_exit(EXIT_FAILURE, "check_port_config failed\n"); + + nb_lcores = rte_lcore_count(); + + /* initialize all ports */ + 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); + continue; + } + + /* init port */ + printf("Initializing port %d ... ", portid ); + fflush(stdout); + + /* must always equal(=1) */ + nb_rx_queue = get_port_n_rx_queues(portid); + n_tx_queue = MAX_TX_QUEUE_PER_PORT; + + printf("Creating queues: nb_rxq=%d nb_txq=%u... ", + nb_rx_queue, (unsigned)1 ); + + 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, + 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(", "); + + ret = init_mem(NB_MBUF); + if (ret < 0) + rte_exit(EXIT_FAILURE, "init_mem failed\n"); + + /* init one TX queue */ + socketid = (uint8_t)rte_lcore_to_socket_id(rte_get_master_lcore()); + + printf("txq=%d,%d,%d ", portid, 0, socketid); + fflush(stdout); + + txconf = &dev_info.default_txconf; + txconf->offloads = local_port_conf.txmode.offloads; + ret = rte_eth_tx_queue_setup(portid, 0, nb_txd, + socketid, txconf); + if (ret < 0) + rte_exit(EXIT_FAILURE, "rte_eth_tx_queue_setup: err=%d, " + "port=%d\n", ret, portid); + + printf("\n"); + } + + for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) { + struct rte_eth_rxconf rxq_conf; + + if (rte_lcore_is_enabled(lcore_id) == 0) + continue; + qconf = &lcore_conf[lcore_id]; + qconf->tx_queue_id = 0; + + 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_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 = (uint8_t)rte_lcore_to_socket_id(lcore_id); + else + socketid = 0; + + 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, &rxq_conf, + pktmbuf_pool[socketid]); + if (ret < 0) + rte_exit(EXIT_FAILURE, "rte_eth_rx_queue_setup: err=%d," + "port=%d\n", ret, portid); + } + } + printf("\n"); + + /* start ports */ + RTE_ETH_FOREACH_DEV(portid) { + if ((enabled_port_mask & (1 << portid)) == 0) { + continue; + } + /* Start device */ + ret = rte_eth_dev_start(portid); + if (ret < 0) + rte_exit(EXIT_FAILURE, "rte_eth_dev_start: err=%d, port=%d\n", + ret, portid); + + printf("done: Port %d\n", portid); + + } + + /* launch per-lcore init on every lcore */ + rte_eal_mp_remote_launch(main_loop, NULL, CALL_MASTER); + RTE_LCORE_FOREACH_SLAVE(lcore_id) { + if (rte_eal_wait_lcore(lcore_id) < 0) + return -1; + } + + return 0; +} diff --git a/src/seastar/dpdk/examples/l3fwd-vf/meson.build b/src/seastar/dpdk/examples/l3fwd-vf/meson.build new file mode 100644 index 000000000..226286e74 --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd-vf/meson.build @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2017 Intel Corporation + +# meson file, for building this example as part of a main DPDK build. +# +# To build this example as a standalone application with an already-installed +# DPDK instance, use 'make' + +deps += ['lpm', 'hash'] +sources = files( + 'main.c' +) diff --git a/src/seastar/dpdk/examples/l3fwd/Makefile b/src/seastar/dpdk/examples/l3fwd/Makefile new file mode 100644 index 000000000..8c51c7b96 --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd/Makefile @@ -0,0 +1,56 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2010-2016 Intel Corporation + +# binary name +APP = l3fwd + +# all source are stored in SRCS-y +SRCS-y := main.c l3fwd_lpm.c l3fwd_em.c + +# Build using pkg-config variables if possible +$(shell pkg-config --exists libdpdk) +ifeq ($(.SHELLSTATUS),0) + +all: shared +.PHONY: shared static +shared: build/$(APP)-shared + ln -sf $(APP)-shared build/$(APP) +static: build/$(APP)-static + ln -sf $(APP)-static build/$(APP) + +PC_FILE := $(shell pkg-config --path libdpdk) +CFLAGS += -O3 $(shell pkg-config --cflags libdpdk) +LDFLAGS_SHARED = $(shell pkg-config --libs libdpdk) +LDFLAGS_STATIC = -Wl,-Bstatic $(shell pkg-config --static --libs libdpdk) + +build/$(APP)-shared: $(SRCS-y) Makefile $(PC_FILE) | build + $(CC) $(CFLAGS) $(SRCS-y) -o $@ $(LDFLAGS) $(LDFLAGS_SHARED) + +build/$(APP)-static: $(SRCS-y) Makefile $(PC_FILE) | build + $(CC) $(CFLAGS) $(SRCS-y) -o $@ $(LDFLAGS) $(LDFLAGS_STATIC) + +build: + @mkdir -p $@ + +.PHONY: clean +clean: + rm -f build/$(APP) build/$(APP)-static build/$(APP)-shared + rmdir --ignore-fail-on-non-empty build + +else # Build using legacy build system + +ifeq ($(RTE_SDK),) +$(error "Please define RTE_SDK environment variable") +endif + +# Default target, detect a build directory, by looking for a path with a .config +RTE_TARGET ?= $(notdir $(abspath $(dir $(firstword $(wildcard $(RTE_SDK)/*/.config))))) + +include $(RTE_SDK)/mk/rte.vars.mk + +CFLAGS += -I$(SRCDIR) +CFLAGS += -O3 $(USER_FLAGS) +CFLAGS += $(WERROR_FLAGS) + +include $(RTE_SDK)/mk/rte.extapp.mk +endif diff --git a/src/seastar/dpdk/examples/l3fwd/l3fwd.h b/src/seastar/dpdk/examples/l3fwd/l3fwd.h new file mode 100644 index 000000000..c962deac3 --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd/l3fwd.h @@ -0,0 +1,212 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2010-2016 Intel Corporation + */ + +#ifndef __L3_FWD_H__ +#define __L3_FWD_H__ + +#include <rte_vect.h> + +#define DO_RFC_1812_CHECKS + +#define RTE_LOGTYPE_L3FWD RTE_LOGTYPE_USER1 + +#if !defined(NO_HASH_MULTI_LOOKUP) && defined(RTE_MACHINE_CPUFLAG_NEON) +#define NO_HASH_MULTI_LOOKUP 1 +#endif + +#define MAX_PKT_BURST 32 +#define BURST_TX_DRAIN_US 100 /* TX drain every ~100us */ + +#define MAX_RX_QUEUE_PER_LCORE 16 + +/* + * Try to avoid TX buffering if we have at least MAX_TX_BURST packets to send. + */ +#define MAX_TX_BURST (MAX_PKT_BURST / 2) + +#define NB_SOCKETS 8 + +/* Configure how many packets ahead to prefetch, when reading packets */ +#define PREFETCH_OFFSET 3 + +/* Used to mark destination port as 'invalid'. */ +#define BAD_PORT ((uint16_t)-1) + +#define FWDSTEP 4 + +/* replace first 12B of the ethernet header. */ +#define MASK_ETH 0x3f + +/* Hash parameters. */ +#ifdef RTE_ARCH_64 +/* default to 4 million hash entries (approx) */ +#define L3FWD_HASH_ENTRIES (1024*1024*4) +#else +/* 32-bit has less address-space for hugepage memory, limit to 1M entries */ +#define L3FWD_HASH_ENTRIES (1024*1024*1) +#endif +#define HASH_ENTRY_NUMBER_DEFAULT 4 + +struct mbuf_table { + uint16_t len; + struct rte_mbuf *m_table[MAX_PKT_BURST]; +}; + +struct lcore_rx_queue { + uint16_t port_id; + uint8_t queue_id; +} __rte_cache_aligned; + +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]; + void *ipv4_lookup_struct; + void *ipv6_lookup_struct; +} __rte_cache_aligned; + +extern volatile bool force_quit; + +/* ethernet addresses of ports */ +extern uint64_t dest_eth_addr[RTE_MAX_ETHPORTS]; +extern struct ether_addr ports_eth_addr[RTE_MAX_ETHPORTS]; + +/* mask of enabled ports */ +extern uint32_t enabled_port_mask; + +/* Used only in exact match mode. */ +extern int ipv6; /**< ipv6 is false by default. */ +extern uint32_t hash_entry_number; + +extern xmm_t val_eth[RTE_MAX_ETHPORTS]; + +extern struct lcore_conf lcore_conf[RTE_MAX_LCORE]; + +/* Send burst of packets on an output interface */ +static inline int +send_burst(struct lcore_conf *qconf, uint16_t n, uint16_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 lcore_conf *qconf, + struct rte_mbuf *m, uint16_t port) +{ + uint16_t len; + + 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; + return 0; +} + +#ifdef DO_RFC_1812_CHECKS +static inline int +is_valid_ipv4_pkt(struct 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)) + return -1; + + /* 2. The IP checksum must be correct. */ + /* this is checked in H/W */ + + /* + * 3. The IP version number must be 4. If the version number is not 4 + * then the packet may be another version of IP, such as IPng or + * ST-II. + */ + if (((pkt->version_ihl) >> 4) != 4) + return -3; + /* + * 4. The IP header length field must be large enough to hold the + * minimum length legal IP datagram (20 bytes = 5 words). + */ + if ((pkt->version_ihl & 0xf) < 5) + return -4; + + /* + * 5. The IP total length field must be large enough to hold the IP + * 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)) + return -5; + + return 0; +} +#endif /* DO_RFC_1812_CHECKS */ + +/* Function pointers for LPM or EM functionality. */ +void +setup_lpm(const int socketid); + +void +setup_hash(const int socketid); + +int +em_check_ptype(int portid); + +int +lpm_check_ptype(int portid); + +uint16_t +em_cb_parse_ptype(uint16_t port, uint16_t queue, struct rte_mbuf *pkts[], + uint16_t nb_pkts, uint16_t max_pkts, void *user_param); + +uint16_t +lpm_cb_parse_ptype(uint16_t port, uint16_t queue, struct rte_mbuf *pkts[], + uint16_t nb_pkts, uint16_t max_pkts, void *user_param); + +int +em_main_loop(__attribute__((unused)) void *dummy); + +int +lpm_main_loop(__attribute__((unused)) void *dummy); + +/* Return ipv4/ipv6 fwd lookup struct for LPM or EM. */ +void * +em_get_ipv4_l3fwd_lookup_struct(const int socketid); + +void * +em_get_ipv6_l3fwd_lookup_struct(const int socketid); + +void * +lpm_get_ipv4_l3fwd_lookup_struct(const int socketid); + +void * +lpm_get_ipv6_l3fwd_lookup_struct(const int socketid); + +#endif /* __L3_FWD_H__ */ diff --git a/src/seastar/dpdk/examples/l3fwd/l3fwd_altivec.h b/src/seastar/dpdk/examples/l3fwd/l3fwd_altivec.h new file mode 100644 index 000000000..5ec99f961 --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd/l3fwd_altivec.h @@ -0,0 +1,255 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2016 Intel Corporation. + * Copyright(c) 2017 IBM Corporation. + * All rights reserved. + */ + +#ifndef _L3FWD_ALTIVEC_H_ +#define _L3FWD_ALTIVEC_H_ + +#include "l3fwd.h" +#include "l3fwd_common.h" + +/* + * Update source and destination MAC addresses in the ethernet header. + * Perform RFC1812 checks and updates for IPV4 packets. + */ +static inline void +processx4_step3(struct rte_mbuf *pkt[FWDSTEP], uint16_t dst_port[FWDSTEP]) +{ + vector unsigned int te[FWDSTEP]; + vector unsigned int ve[FWDSTEP]; + vector unsigned int *p[FWDSTEP]; + + p[0] = rte_pktmbuf_mtod(pkt[0], vector unsigned int *); + p[1] = rte_pktmbuf_mtod(pkt[1], vector unsigned int *); + p[2] = rte_pktmbuf_mtod(pkt[2], vector unsigned int *); + p[3] = rte_pktmbuf_mtod(pkt[3], vector unsigned int *); + + ve[0] = (vector unsigned int)val_eth[dst_port[0]]; + te[0] = *p[0]; + + ve[1] = (vector unsigned int)val_eth[dst_port[1]]; + te[1] = *p[1]; + + ve[2] = (vector unsigned int)val_eth[dst_port[2]]; + te[2] = *p[2]; + + ve[3] = (vector unsigned int)val_eth[dst_port[3]]; + te[3] = *p[3]; + + /* Update first 12 bytes, keep rest bytes intact. */ + te[0] = (vector unsigned int)vec_sel( + (vector unsigned short)ve[0], + (vector unsigned short)te[0], + (vector unsigned short) {0, 0, 0, 0, + 0, 0, 0xffff, 0xffff}); + + te[1] = (vector unsigned int)vec_sel( + (vector unsigned short)ve[1], + (vector unsigned short)te[1], + (vector unsigned short) {0, 0, 0, 0, + 0, 0, 0xffff, 0xffff}); + + te[2] = (vector unsigned int)vec_sel( + (vector unsigned short)ve[2], + (vector unsigned short)te[2], + (vector unsigned short) {0, 0, 0, 0, 0, + 0, 0xffff, 0xffff}); + + te[3] = (vector unsigned int)vec_sel( + (vector unsigned short)ve[3], + (vector unsigned short)te[3], + (vector unsigned short) {0, 0, 0, 0, + 0, 0, 0xffff, 0xffff}); + + *p[0] = te[0]; + *p[1] = te[1]; + *p[2] = te[2]; + *p[3] = te[3]; + + rfc1812_process((struct ipv4_hdr *)((struct ether_hdr *)p[0] + 1), + &dst_port[0], pkt[0]->packet_type); + rfc1812_process((struct ipv4_hdr *)((struct ether_hdr *)p[1] + 1), + &dst_port[1], pkt[1]->packet_type); + rfc1812_process((struct ipv4_hdr *)((struct ether_hdr *)p[2] + 1), + &dst_port[2], pkt[2]->packet_type); + rfc1812_process((struct ipv4_hdr *)((struct ether_hdr *)p[3] + 1), + &dst_port[3], pkt[3]->packet_type); +} + +/* + * Group consecutive packets with the same destination port in bursts of 4. + * Suppose we have array of destination ports: + * dst_port[] = {a, b, c, d,, e, ... } + * dp1 should contain: <a, b, c, d>, dp2: <b, c, d, e>. + * We doing 4 comparisons at once and the result is 4 bit mask. + * This mask is used as an index into prebuild array of pnum values. + */ +static inline uint16_t * +port_groupx4(uint16_t pn[FWDSTEP + 1], uint16_t *lp, vector unsigned short dp1, + vector unsigned short dp2) +{ + union { + uint16_t u16[FWDSTEP + 1]; + uint64_t u64; + } *pnum = (void *)pn; + + int32_t v; + + v = vec_any_eq(dp1, dp2); + + + /* update last port counter. */ + lp[0] += gptbl[v].lpv; + + /* if dest port value has changed. */ + if (v != GRPMSK) { + pnum->u64 = gptbl[v].pnum; + pnum->u16[FWDSTEP] = 1; + lp = pnum->u16 + gptbl[v].idx; + } + + return lp; +} + +/** + * Process one packet: + * Update source and destination MAC addresses in the ethernet header. + * Perform RFC1812 checks and updates for IPV4 packets. + */ +static inline void +process_packet(struct rte_mbuf *pkt, uint16_t *dst_port) +{ + struct ether_hdr *eth_hdr; + vector unsigned int te, ve; + + eth_hdr = rte_pktmbuf_mtod(pkt, struct ether_hdr *); + + te = *(vector unsigned int *)eth_hdr; + ve = (vector unsigned int)val_eth[dst_port[0]]; + + rfc1812_process((struct ipv4_hdr *)(eth_hdr + 1), dst_port, + pkt->packet_type); + + /* dynamically vec_sel te and ve for MASK_ETH (0x3f) */ + te = (vector unsigned int)vec_sel( + (vector unsigned short)ve, + (vector unsigned short)te, + (vector unsigned short){0, 0, 0, 0, + 0, 0, 0xffff, 0xffff}); + + *(vector unsigned int *)eth_hdr = te; +} + +/** + * Send packets burst from pkts_burst to the ports in dst_port array + */ +static __rte_always_inline void +send_packets_multi(struct lcore_conf *qconf, struct rte_mbuf **pkts_burst, + uint16_t dst_port[MAX_PKT_BURST], int nb_rx) +{ + int32_t k; + int j = 0; + uint16_t dlp; + uint16_t *lp; + uint16_t pnum[MAX_PKT_BURST + 1]; + + /* + * Finish packet processing and group consecutive + * packets with the same destination port. + */ + k = RTE_ALIGN_FLOOR(nb_rx, FWDSTEP); + if (k != 0) { + vector unsigned short dp1, dp2; + + lp = pnum; + lp[0] = 1; + + processx4_step3(pkts_burst, dst_port); + + /* dp1: <d[0], d[1], d[2], d[3], ... > */ + dp1 = *(vector unsigned short *)dst_port; + + for (j = FWDSTEP; j != k; j += FWDSTEP) { + processx4_step3(&pkts_burst[j], &dst_port[j]); + + /* + * dp2: + * <d[j-3], d[j-2], d[j-1], d[j], ... > + */ + dp2 = *((vector unsigned short *) + &dst_port[j - FWDSTEP + 1]); + lp = port_groupx4(&pnum[j - FWDSTEP], lp, dp1, dp2); + + /* + * dp1: + * <d[j], d[j+1], d[j+2], d[j+3], ... > + */ + dp1 = vec_sro(dp2, (vector unsigned char) { + 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, (FWDSTEP - 1) * sizeof(dst_port[0])}); + } + + /* + * dp2: <d[j-3], d[j-2], d[j-1], d[j-1], ... > + */ + dp2 = vec_perm(dp1, (vector unsigned short){}, + (vector unsigned char){0xf9}); + lp = port_groupx4(&pnum[j - FWDSTEP], lp, dp1, dp2); + + /* + * remove values added by the last repeated + * dst port. + */ + lp[0]--; + dlp = dst_port[j - 1]; + } else { + /* set dlp and lp to the never used values. */ + dlp = BAD_PORT - 1; + lp = pnum + MAX_PKT_BURST; + } + + /* Process up to last 3 packets one by one. */ + switch (nb_rx % FWDSTEP) { + case 3: + process_packet(pkts_burst[j], dst_port + j); + GROUP_PORT_STEP(dlp, dst_port, lp, pnum, j); + j++; + /* fall-through */ + case 2: + process_packet(pkts_burst[j], dst_port + j); + GROUP_PORT_STEP(dlp, dst_port, lp, pnum, j); + j++; + /* fall-through */ + case 1: + process_packet(pkts_burst[j], dst_port + j); + GROUP_PORT_STEP(dlp, dst_port, lp, pnum, j); + j++; + } + + /* + * Send packets out, through destination port. + * Consecutive packets with the same destination port + * are already grouped together. + * If destination port for the packet equals BAD_PORT, + * then free the packet without sending it out. + */ + for (j = 0; j < nb_rx; j += k) { + + int32_t m; + uint16_t pn; + + pn = dst_port[j]; + k = pnum[j]; + + if (likely(pn != BAD_PORT)) + send_packetsx4(qconf, pn, pkts_burst + j, k); + else + for (m = j; m != j + k; m++) + rte_pktmbuf_free(pkts_burst[m]); + + } +} + +#endif /* _L3FWD_ALTIVEC_H_ */ diff --git a/src/seastar/dpdk/examples/l3fwd/l3fwd_common.h b/src/seastar/dpdk/examples/l3fwd/l3fwd_common.h new file mode 100644 index 000000000..0f4fcb427 --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd/l3fwd_common.h @@ -0,0 +1,264 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2016-2018 Intel Corporation. + * Copyright(c) 2017-2018 Linaro Limited. + */ + + +#ifndef _L3FWD_COMMON_H_ +#define _L3FWD_COMMON_H_ + +#ifdef DO_RFC_1812_CHECKS + +#define IPV4_MIN_VER_IHL 0x45 +#define IPV4_MAX_VER_IHL 0x4f +#define IPV4_MAX_VER_IHL_DIFF (IPV4_MAX_VER_IHL - IPV4_MIN_VER_IHL) + +/* Minimum value of IPV4 total length (20B) in network byte order. */ +#define IPV4_MIN_LEN_BE (sizeof(struct ipv4_hdr) << 8) + +/* + * From http://www.rfc-editor.org/rfc/rfc1812.txt section 5.2.2: + * - The IP version number must be 4. + * - The IP header length field must be large enough to hold the + * minimum length legal IP datagram (20 bytes = 5 words). + * - The IP total length field must be large enough to hold the IP + * datagram header, whose length is specified in the IP header length + * field. + * If we encounter invalid IPV4 packet, then set destination port for it + * to BAD_PORT value. + */ +static __rte_always_inline void +rfc1812_process(struct ipv4_hdr *ipv4_hdr, uint16_t *dp, uint32_t ptype) +{ + uint8_t ihl; + + if (RTE_ETH_IS_IPV4_HDR(ptype)) { + ihl = ipv4_hdr->version_ihl - IPV4_MIN_VER_IHL; + + ipv4_hdr->time_to_live--; + ipv4_hdr->hdr_checksum++; + + if (ihl > IPV4_MAX_VER_IHL_DIFF || + ((uint8_t)ipv4_hdr->total_length == 0 && + ipv4_hdr->total_length < IPV4_MIN_LEN_BE)) + dp[0] = BAD_PORT; + + } +} + +#else +#define rfc1812_process(mb, dp, ptype) do { } while (0) +#endif /* DO_RFC_1812_CHECKS */ + +/* + * We group consecutive packets with the same destionation port into one burst. + * To avoid extra latency this is done together with some other packet + * processing, but after we made a final decision about packet's destination. + * To do this we maintain: + * pnum - array of number of consecutive packets with the same dest port for + * each packet in the input burst. + * lp - pointer to the last updated element in the pnum. + * dlp - dest port value lp corresponds to. + */ + +#define GRPSZ (1 << FWDSTEP) +#define GRPMSK (GRPSZ - 1) + +#define GROUP_PORT_STEP(dlp, dcp, lp, pn, idx) do { \ + if (likely((dlp) == (dcp)[(idx)])) { \ + (lp)[0]++; \ + } else { \ + (dlp) = (dcp)[idx]; \ + (lp) = (pn) + (idx); \ + (lp)[0] = 1; \ + } \ +} while (0) + +static const struct { + uint64_t pnum; /* prebuild 4 values for pnum[]. */ + int32_t idx; /* index for new last updated elemnet. */ + uint16_t lpv; /* add value to the last updated element. */ +} gptbl[GRPSZ] = { + { + /* 0: a != b, b != c, c != d, d != e */ + .pnum = UINT64_C(0x0001000100010001), + .idx = 4, + .lpv = 0, + }, + { + /* 1: a == b, b != c, c != d, d != e */ + .pnum = UINT64_C(0x0001000100010002), + .idx = 4, + .lpv = 1, + }, + { + /* 2: a != b, b == c, c != d, d != e */ + .pnum = UINT64_C(0x0001000100020001), + .idx = 4, + .lpv = 0, + }, + { + /* 3: a == b, b == c, c != d, d != e */ + .pnum = UINT64_C(0x0001000100020003), + .idx = 4, + .lpv = 2, + }, + { + /* 4: a != b, b != c, c == d, d != e */ + .pnum = UINT64_C(0x0001000200010001), + .idx = 4, + .lpv = 0, + }, + { + /* 5: a == b, b != c, c == d, d != e */ + .pnum = UINT64_C(0x0001000200010002), + .idx = 4, + .lpv = 1, + }, + { + /* 6: a != b, b == c, c == d, d != e */ + .pnum = UINT64_C(0x0001000200030001), + .idx = 4, + .lpv = 0, + }, + { + /* 7: a == b, b == c, c == d, d != e */ + .pnum = UINT64_C(0x0001000200030004), + .idx = 4, + .lpv = 3, + }, + { + /* 8: a != b, b != c, c != d, d == e */ + .pnum = UINT64_C(0x0002000100010001), + .idx = 3, + .lpv = 0, + }, + { + /* 9: a == b, b != c, c != d, d == e */ + .pnum = UINT64_C(0x0002000100010002), + .idx = 3, + .lpv = 1, + }, + { + /* 0xa: a != b, b == c, c != d, d == e */ + .pnum = UINT64_C(0x0002000100020001), + .idx = 3, + .lpv = 0, + }, + { + /* 0xb: a == b, b == c, c != d, d == e */ + .pnum = UINT64_C(0x0002000100020003), + .idx = 3, + .lpv = 2, + }, + { + /* 0xc: a != b, b != c, c == d, d == e */ + .pnum = UINT64_C(0x0002000300010001), + .idx = 2, + .lpv = 0, + }, + { + /* 0xd: a == b, b != c, c == d, d == e */ + .pnum = UINT64_C(0x0002000300010002), + .idx = 2, + .lpv = 1, + }, + { + /* 0xe: a != b, b == c, c == d, d == e */ + .pnum = UINT64_C(0x0002000300040001), + .idx = 1, + .lpv = 0, + }, + { + /* 0xf: a == b, b == c, c == d, d == e */ + .pnum = UINT64_C(0x0002000300040005), + .idx = 0, + .lpv = 4, + }, +}; + +static __rte_always_inline void +send_packetsx4(struct lcore_conf *qconf, uint16_t port, struct rte_mbuf *m[], + uint32_t num) +{ + uint32_t len, j, n; + + len = qconf->tx_mbufs[port].len; + + /* + * If TX buffer for that queue is empty, and we have enough packets, + * then send them straightway. + */ + if (num >= MAX_TX_BURST && len == 0) { + n = rte_eth_tx_burst(port, qconf->tx_queue_id[port], m, num); + if (unlikely(n < num)) { + do { + rte_pktmbuf_free(m[n]); + } while (++n < num); + } + return; + } + + /* + * Put packets into TX buffer for that queue. + */ + + n = len + num; + n = (n > MAX_PKT_BURST) ? MAX_PKT_BURST - len : num; + + j = 0; + switch (n % FWDSTEP) { + while (j < n) { + case 0: + qconf->tx_mbufs[port].m_table[len + j] = m[j]; + j++; + /* fallthrough */ + case 3: + qconf->tx_mbufs[port].m_table[len + j] = m[j]; + j++; + /* fallthrough */ + case 2: + qconf->tx_mbufs[port].m_table[len + j] = m[j]; + j++; + /* fallthrough */ + case 1: + qconf->tx_mbufs[port].m_table[len + j] = m[j]; + j++; + } + } + + len += n; + + /* enough pkts to be sent */ + if (unlikely(len == MAX_PKT_BURST)) { + + send_burst(qconf, MAX_PKT_BURST, port); + + /* copy rest of the packets into the TX buffer. */ + len = num - n; + j = 0; + switch (len % FWDSTEP) { + while (j < len) { + case 0: + qconf->tx_mbufs[port].m_table[j] = m[n + j]; + j++; + /* fallthrough */ + case 3: + qconf->tx_mbufs[port].m_table[j] = m[n + j]; + j++; + /* fallthrough */ + case 2: + qconf->tx_mbufs[port].m_table[j] = m[n + j]; + j++; + /* fallthrough */ + case 1: + qconf->tx_mbufs[port].m_table[j] = m[n + j]; + j++; + } + } + } + + qconf->tx_mbufs[port].len = len; +} + +#endif /* _L3FWD_COMMON_H_ */ diff --git a/src/seastar/dpdk/examples/l3fwd/l3fwd_em.c b/src/seastar/dpdk/examples/l3fwd/l3fwd_em.c new file mode 100644 index 000000000..fa8f82be6 --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd/l3fwd_em.c @@ -0,0 +1,785 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2010-2016 Intel Corporation + */ + +#include <stdio.h> +#include <stdlib.h> +#include <stdint.h> +#include <inttypes.h> +#include <sys/types.h> +#include <string.h> +#include <sys/queue.h> +#include <stdarg.h> +#include <errno.h> +#include <getopt.h> +#include <stdbool.h> +#include <netinet/in.h> + +#include <rte_debug.h> +#include <rte_ether.h> +#include <rte_ethdev.h> +#include <rte_cycles.h> +#include <rte_mbuf.h> +#include <rte_ip.h> +#include <rte_tcp.h> +#include <rte_udp.h> +#include <rte_hash.h> + +#include "l3fwd.h" + +#if defined(RTE_ARCH_X86) || defined(RTE_MACHINE_CPUFLAG_CRC32) +#define EM_HASH_CRC 1 +#endif + +#ifdef EM_HASH_CRC +#include <rte_hash_crc.h> +#define DEFAULT_HASH_FUNC rte_hash_crc +#else +#include <rte_jhash.h> +#define DEFAULT_HASH_FUNC rte_jhash +#endif + +#define IPV6_ADDR_LEN 16 + +struct ipv4_5tuple { + uint32_t ip_dst; + uint32_t ip_src; + uint16_t port_dst; + uint16_t port_src; + uint8_t proto; +} __attribute__((__packed__)); + +union ipv4_5tuple_host { + struct { + uint8_t pad0; + uint8_t proto; + uint16_t pad1; + uint32_t ip_src; + uint32_t ip_dst; + uint16_t port_src; + uint16_t port_dst; + }; + xmm_t xmm; +}; + +#define XMM_NUM_IN_IPV6_5TUPLE 3 + +struct ipv6_5tuple { + uint8_t ip_dst[IPV6_ADDR_LEN]; + uint8_t ip_src[IPV6_ADDR_LEN]; + uint16_t port_dst; + uint16_t port_src; + uint8_t proto; +} __attribute__((__packed__)); + +union ipv6_5tuple_host { + struct { + uint16_t pad0; + uint8_t proto; + uint8_t pad1; + uint8_t ip_src[IPV6_ADDR_LEN]; + uint8_t ip_dst[IPV6_ADDR_LEN]; + uint16_t port_src; + uint16_t port_dst; + uint64_t reserve; + }; + xmm_t xmm[XMM_NUM_IN_IPV6_5TUPLE]; +}; + + + +struct ipv4_l3fwd_em_route { + struct ipv4_5tuple key; + uint8_t if_out; +}; + +struct ipv6_l3fwd_em_route { + struct ipv6_5tuple key; + uint8_t if_out; +}; + +static struct ipv4_l3fwd_em_route ipv4_l3fwd_em_route_array[] = { + {{IPv4(101, 0, 0, 0), IPv4(100, 10, 0, 1), 101, 11, IPPROTO_TCP}, 0}, + {{IPv4(201, 0, 0, 0), IPv4(200, 20, 0, 1), 102, 12, IPPROTO_TCP}, 1}, + {{IPv4(111, 0, 0, 0), IPv4(100, 30, 0, 1), 101, 11, IPPROTO_TCP}, 2}, + {{IPv4(211, 0, 0, 0), IPv4(200, 40, 0, 1), 102, 12, IPPROTO_TCP}, 3}, +}; + +static struct ipv6_l3fwd_em_route ipv6_l3fwd_em_route_array[] = { + {{ + {0xfe, 0x80, 0, 0, 0, 0, 0, 0, 0x02, 0x1e, 0x67, 0xff, 0xfe, 0, 0, 0}, + {0xfe, 0x80, 0, 0, 0, 0, 0, 0, 0x02, 0x1b, 0x21, 0xff, 0xfe, 0x91, 0x38, 0x05}, + 101, 11, IPPROTO_TCP}, 0}, + + {{ + {0xfe, 0x90, 0, 0, 0, 0, 0, 0, 0x02, 0x1e, 0x67, 0xff, 0xfe, 0, 0, 0}, + {0xfe, 0x90, 0, 0, 0, 0, 0, 0, 0x02, 0x1b, 0x21, 0xff, 0xfe, 0x91, 0x38, 0x05}, + 102, 12, IPPROTO_TCP}, 1}, + + {{ + {0xfe, 0xa0, 0, 0, 0, 0, 0, 0, 0x02, 0x1e, 0x67, 0xff, 0xfe, 0, 0, 0}, + {0xfe, 0xa0, 0, 0, 0, 0, 0, 0, 0x02, 0x1b, 0x21, 0xff, 0xfe, 0x91, 0x38, 0x05}, + 101, 11, IPPROTO_TCP}, 2}, + + {{ + {0xfe, 0xb0, 0, 0, 0, 0, 0, 0, 0x02, 0x1e, 0x67, 0xff, 0xfe, 0, 0, 0}, + {0xfe, 0xb0, 0, 0, 0, 0, 0, 0, 0x02, 0x1b, 0x21, 0xff, 0xfe, 0x91, 0x38, 0x05}, + 102, 12, IPPROTO_TCP}, 3}, +}; + +struct rte_hash *ipv4_l3fwd_em_lookup_struct[NB_SOCKETS]; +struct rte_hash *ipv6_l3fwd_em_lookup_struct[NB_SOCKETS]; + +static inline uint32_t +ipv4_hash_crc(const void *data, __rte_unused uint32_t data_len, + uint32_t init_val) +{ + const union ipv4_5tuple_host *k; + uint32_t t; + const uint32_t *p; + + k = data; + t = k->proto; + p = (const uint32_t *)&k->port_src; + +#ifdef EM_HASH_CRC + init_val = rte_hash_crc_4byte(t, init_val); + init_val = rte_hash_crc_4byte(k->ip_src, init_val); + init_val = rte_hash_crc_4byte(k->ip_dst, init_val); + init_val = rte_hash_crc_4byte(*p, init_val); +#else + init_val = rte_jhash_1word(t, init_val); + init_val = rte_jhash_1word(k->ip_src, init_val); + init_val = rte_jhash_1word(k->ip_dst, init_val); + init_val = rte_jhash_1word(*p, init_val); +#endif + + return init_val; +} + +static inline uint32_t +ipv6_hash_crc(const void *data, __rte_unused uint32_t data_len, + uint32_t init_val) +{ + const union ipv6_5tuple_host *k; + uint32_t t; + const uint32_t *p; +#ifdef EM_HASH_CRC + const uint32_t *ip_src0, *ip_src1, *ip_src2, *ip_src3; + const uint32_t *ip_dst0, *ip_dst1, *ip_dst2, *ip_dst3; +#endif + + k = data; + t = k->proto; + p = (const uint32_t *)&k->port_src; + +#ifdef EM_HASH_CRC + ip_src0 = (const uint32_t *) k->ip_src; + ip_src1 = (const uint32_t *)(k->ip_src+4); + ip_src2 = (const uint32_t *)(k->ip_src+8); + ip_src3 = (const uint32_t *)(k->ip_src+12); + ip_dst0 = (const uint32_t *) k->ip_dst; + ip_dst1 = (const uint32_t *)(k->ip_dst+4); + ip_dst2 = (const uint32_t *)(k->ip_dst+8); + ip_dst3 = (const uint32_t *)(k->ip_dst+12); + init_val = rte_hash_crc_4byte(t, init_val); + init_val = rte_hash_crc_4byte(*ip_src0, init_val); + init_val = rte_hash_crc_4byte(*ip_src1, init_val); + init_val = rte_hash_crc_4byte(*ip_src2, init_val); + init_val = rte_hash_crc_4byte(*ip_src3, init_val); + init_val = rte_hash_crc_4byte(*ip_dst0, init_val); + init_val = rte_hash_crc_4byte(*ip_dst1, init_val); + init_val = rte_hash_crc_4byte(*ip_dst2, init_val); + init_val = rte_hash_crc_4byte(*ip_dst3, init_val); + init_val = rte_hash_crc_4byte(*p, init_val); +#else + init_val = rte_jhash_1word(t, init_val); + init_val = rte_jhash(k->ip_src, + sizeof(uint8_t) * IPV6_ADDR_LEN, init_val); + init_val = rte_jhash(k->ip_dst, + sizeof(uint8_t) * IPV6_ADDR_LEN, init_val); + init_val = rte_jhash_1word(*p, init_val); +#endif + return init_val; +} + +#define IPV4_L3FWD_EM_NUM_ROUTES \ + (sizeof(ipv4_l3fwd_em_route_array) / sizeof(ipv4_l3fwd_em_route_array[0])) + +#define IPV6_L3FWD_EM_NUM_ROUTES \ + (sizeof(ipv6_l3fwd_em_route_array) / sizeof(ipv6_l3fwd_em_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 rte_xmm_t mask0; +static rte_xmm_t mask1; +static rte_xmm_t mask2; + +#if defined(RTE_MACHINE_CPUFLAG_SSE2) +static inline xmm_t +em_mask_key(void *key, xmm_t mask) +{ + __m128i data = _mm_loadu_si128((__m128i *)(key)); + + return _mm_and_si128(data, mask); +} +#elif defined(RTE_MACHINE_CPUFLAG_NEON) +static inline xmm_t +em_mask_key(void *key, xmm_t mask) +{ + int32x4_t data = vld1q_s32((int32_t *)key); + + return vandq_s32(data, mask); +} +#elif defined(RTE_MACHINE_CPUFLAG_ALTIVEC) +static inline xmm_t +em_mask_key(void *key, xmm_t mask) +{ + xmm_t data = vec_ld(0, (xmm_t *)(key)); + + return vec_and(data, mask); +} +#else +#error No vector engine (SSE, NEON, ALTIVEC) available, check your toolchain +#endif + +static inline uint16_t +em_get_ipv4_dst_port(void *ipv4_hdr, uint16_t portid, void *lookup_struct) +{ + int ret = 0; + union ipv4_5tuple_host key; + struct rte_hash *ipv4_l3fwd_lookup_struct = + (struct rte_hash *)lookup_struct; + + ipv4_hdr = (uint8_t *)ipv4_hdr + offsetof(struct ipv4_hdr, time_to_live); + + /* + * Get 5 tuple: dst port, src port, dst IP address, + * src IP address and protocol. + */ + key.xmm = em_mask_key(ipv4_hdr, mask0.x); + + /* Find destination port */ + ret = rte_hash_lookup(ipv4_l3fwd_lookup_struct, (const void *)&key); + return (ret < 0) ? portid : ipv4_l3fwd_out_if[ret]; +} + +static inline uint16_t +em_get_ipv6_dst_port(void *ipv6_hdr, uint16_t portid, void *lookup_struct) +{ + int ret = 0; + union ipv6_5tuple_host key; + struct rte_hash *ipv6_l3fwd_lookup_struct = + (struct rte_hash *)lookup_struct; + + ipv6_hdr = (uint8_t *)ipv6_hdr + offsetof(struct ipv6_hdr, payload_len); + void *data0 = ipv6_hdr; + void *data1 = ((uint8_t *)ipv6_hdr) + sizeof(xmm_t); + void *data2 = ((uint8_t *)ipv6_hdr) + sizeof(xmm_t) + sizeof(xmm_t); + + /* Get part of 5 tuple: src IP address lower 96 bits and protocol */ + key.xmm[0] = em_mask_key(data0, mask1.x); + + /* + * Get part of 5 tuple: dst IP address lower 96 bits + * and src IP address higher 32 bits. + */ + key.xmm[1] = *(xmm_t *)data1; + + /* + * Get part of 5 tuple: dst port and src port + * and dst IP address higher 32 bits. + */ + key.xmm[2] = em_mask_key(data2, mask2.x); + + /* Find destination port */ + ret = rte_hash_lookup(ipv6_l3fwd_lookup_struct, (const void *)&key); + return (ret < 0) ? portid : ipv6_l3fwd_out_if[ret]; +} + +#if defined RTE_ARCH_X86 || defined RTE_MACHINE_CPUFLAG_NEON +#if defined(NO_HASH_MULTI_LOOKUP) +#include "l3fwd_em_sequential.h" +#else +#include "l3fwd_em_hlm.h" +#endif +#else +#include "l3fwd_em.h" +#endif + +static void +convert_ipv4_5tuple(struct ipv4_5tuple *key1, + union ipv4_5tuple_host *key2) +{ + key2->ip_dst = rte_cpu_to_be_32(key1->ip_dst); + key2->ip_src = rte_cpu_to_be_32(key1->ip_src); + key2->port_dst = rte_cpu_to_be_16(key1->port_dst); + key2->port_src = rte_cpu_to_be_16(key1->port_src); + key2->proto = key1->proto; + key2->pad0 = 0; + key2->pad1 = 0; +} + +static void +convert_ipv6_5tuple(struct ipv6_5tuple *key1, + union ipv6_5tuple_host *key2) +{ + uint32_t i; + + for (i = 0; i < 16; i++) { + key2->ip_dst[i] = key1->ip_dst[i]; + key2->ip_src[i] = key1->ip_src[i]; + } + key2->port_dst = rte_cpu_to_be_16(key1->port_dst); + key2->port_src = rte_cpu_to_be_16(key1->port_src); + key2->proto = key1->proto; + key2->pad0 = 0; + key2->pad1 = 0; + key2->reserve = 0; +} + +#define BYTE_VALUE_MAX 256 +#define ALL_32_BITS 0xffffffff +#define BIT_8_TO_15 0x0000ff00 + +static inline void +populate_ipv4_few_flow_into_table(const struct rte_hash *h) +{ + uint32_t i; + int32_t ret; + + mask0 = (rte_xmm_t){.u32 = {BIT_8_TO_15, ALL_32_BITS, + ALL_32_BITS, ALL_32_BITS} }; + + for (i = 0; i < IPV4_L3FWD_EM_NUM_ROUTES; i++) { + struct ipv4_l3fwd_em_route entry; + union ipv4_5tuple_host newkey; + + entry = ipv4_l3fwd_em_route_array[i]; + convert_ipv4_5tuple(&entry.key, &newkey); + ret = rte_hash_add_key(h, (void *) &newkey); + if (ret < 0) { + rte_exit(EXIT_FAILURE, "Unable to add entry %" PRIu32 + " to the l3fwd hash.\n", i); + } + ipv4_l3fwd_out_if[ret] = entry.if_out; + } + printf("Hash: Adding 0x%" PRIx64 " keys\n", + (uint64_t)IPV4_L3FWD_EM_NUM_ROUTES); +} + +#define BIT_16_TO_23 0x00ff0000 +static inline void +populate_ipv6_few_flow_into_table(const struct rte_hash *h) +{ + uint32_t i; + int32_t ret; + + mask1 = (rte_xmm_t){.u32 = {BIT_16_TO_23, ALL_32_BITS, + ALL_32_BITS, ALL_32_BITS} }; + + mask2 = (rte_xmm_t){.u32 = {ALL_32_BITS, ALL_32_BITS, 0, 0} }; + + for (i = 0; i < IPV6_L3FWD_EM_NUM_ROUTES; i++) { + struct ipv6_l3fwd_em_route entry; + union ipv6_5tuple_host newkey; + + entry = ipv6_l3fwd_em_route_array[i]; + convert_ipv6_5tuple(&entry.key, &newkey); + ret = rte_hash_add_key(h, (void *) &newkey); + if (ret < 0) { + rte_exit(EXIT_FAILURE, "Unable to add entry %" PRIu32 + " to the l3fwd hash.\n", i); + } + ipv6_l3fwd_out_if[ret] = entry.if_out; + } + printf("Hash: Adding 0x%" PRIx64 "keys\n", + (uint64_t)IPV6_L3FWD_EM_NUM_ROUTES); +} + +#define NUMBER_PORT_USED 4 +static inline void +populate_ipv4_many_flow_into_table(const struct rte_hash *h, + unsigned int nr_flow) +{ + unsigned i; + + mask0 = (rte_xmm_t){.u32 = {BIT_8_TO_15, ALL_32_BITS, + ALL_32_BITS, ALL_32_BITS} }; + + for (i = 0; i < nr_flow; i++) { + struct ipv4_l3fwd_em_route entry; + union ipv4_5tuple_host newkey; + + uint8_t a = (uint8_t) + ((i/NUMBER_PORT_USED)%BYTE_VALUE_MAX); + uint8_t b = (uint8_t) + (((i/NUMBER_PORT_USED)/BYTE_VALUE_MAX)%BYTE_VALUE_MAX); + uint8_t c = (uint8_t) + ((i/NUMBER_PORT_USED)/(BYTE_VALUE_MAX*BYTE_VALUE_MAX)); + + /* Create the ipv4 exact match flow */ + memset(&entry, 0, sizeof(entry)); + switch (i & (NUMBER_PORT_USED - 1)) { + case 0: + entry = ipv4_l3fwd_em_route_array[0]; + entry.key.ip_dst = IPv4(101, c, b, a); + break; + case 1: + entry = ipv4_l3fwd_em_route_array[1]; + entry.key.ip_dst = IPv4(201, c, b, a); + break; + case 2: + entry = ipv4_l3fwd_em_route_array[2]; + entry.key.ip_dst = IPv4(111, c, b, a); + break; + case 3: + entry = ipv4_l3fwd_em_route_array[3]; + entry.key.ip_dst = IPv4(211, c, b, a); + break; + }; + convert_ipv4_5tuple(&entry.key, &newkey); + int32_t ret = rte_hash_add_key(h, (void *) &newkey); + + if (ret < 0) + rte_exit(EXIT_FAILURE, "Unable to add entry %u\n", i); + + ipv4_l3fwd_out_if[ret] = (uint8_t) entry.if_out; + + } + printf("Hash: Adding 0x%x keys\n", nr_flow); +} + +static inline void +populate_ipv6_many_flow_into_table(const struct rte_hash *h, + unsigned int nr_flow) +{ + unsigned i; + + mask1 = (rte_xmm_t){.u32 = {BIT_16_TO_23, ALL_32_BITS, + ALL_32_BITS, ALL_32_BITS} }; + mask2 = (rte_xmm_t){.u32 = {ALL_32_BITS, ALL_32_BITS, 0, 0} }; + + for (i = 0; i < nr_flow; i++) { + struct ipv6_l3fwd_em_route entry; + union ipv6_5tuple_host newkey; + + uint8_t a = (uint8_t) + ((i/NUMBER_PORT_USED)%BYTE_VALUE_MAX); + uint8_t b = (uint8_t) + (((i/NUMBER_PORT_USED)/BYTE_VALUE_MAX)%BYTE_VALUE_MAX); + uint8_t c = (uint8_t) + ((i/NUMBER_PORT_USED)/(BYTE_VALUE_MAX*BYTE_VALUE_MAX)); + + /* Create the ipv6 exact match flow */ + memset(&entry, 0, sizeof(entry)); + switch (i & (NUMBER_PORT_USED - 1)) { + case 0: + entry = ipv6_l3fwd_em_route_array[0]; + break; + case 1: + entry = ipv6_l3fwd_em_route_array[1]; + break; + case 2: + entry = ipv6_l3fwd_em_route_array[2]; + break; + case 3: + entry = ipv6_l3fwd_em_route_array[3]; + break; + }; + entry.key.ip_dst[13] = c; + entry.key.ip_dst[14] = b; + entry.key.ip_dst[15] = a; + convert_ipv6_5tuple(&entry.key, &newkey); + int32_t ret = rte_hash_add_key(h, (void *) &newkey); + + if (ret < 0) + rte_exit(EXIT_FAILURE, "Unable to add entry %u\n", i); + + ipv6_l3fwd_out_if[ret] = (uint8_t) entry.if_out; + + } + printf("Hash: Adding 0x%x keys\n", nr_flow); +} + +/* Requirements: + * 1. IP packets without extension; + * 2. L4 payload should be either TCP or UDP. + */ +int +em_check_ptype(int portid) +{ + int i, ret; + int ptype_l3_ipv4_ext = 0; + int ptype_l3_ipv6_ext = 0; + int ptype_l4_tcp = 0; + int ptype_l4_udp = 0; + uint32_t ptype_mask = RTE_PTYPE_L3_MASK | RTE_PTYPE_L4_MASK; + + ret = rte_eth_dev_get_supported_ptypes(portid, ptype_mask, NULL, 0); + if (ret <= 0) + return 0; + + uint32_t ptypes[ret]; + + ret = rte_eth_dev_get_supported_ptypes(portid, ptype_mask, ptypes, ret); + for (i = 0; i < ret; ++i) { + switch (ptypes[i]) { + case RTE_PTYPE_L3_IPV4_EXT: + ptype_l3_ipv4_ext = 1; + break; + case RTE_PTYPE_L3_IPV6_EXT: + ptype_l3_ipv6_ext = 1; + break; + case RTE_PTYPE_L4_TCP: + ptype_l4_tcp = 1; + break; + case RTE_PTYPE_L4_UDP: + ptype_l4_udp = 1; + break; + } + } + + if (ptype_l3_ipv4_ext == 0) + printf("port %d cannot parse RTE_PTYPE_L3_IPV4_EXT\n", portid); + if (ptype_l3_ipv6_ext == 0) + printf("port %d cannot parse RTE_PTYPE_L3_IPV6_EXT\n", portid); + if (!ptype_l3_ipv4_ext || !ptype_l3_ipv6_ext) + return 0; + + if (ptype_l4_tcp == 0) + printf("port %d cannot parse RTE_PTYPE_L4_TCP\n", portid); + if (ptype_l4_udp == 0) + printf("port %d cannot parse RTE_PTYPE_L4_UDP\n", portid); + if (ptype_l4_tcp && ptype_l4_udp) + return 1; + + return 0; +} + +static inline void +em_parse_ptype(struct rte_mbuf *m) +{ + struct ether_hdr *eth_hdr; + uint32_t packet_type = RTE_PTYPE_UNKNOWN; + uint16_t ether_type; + void *l3; + int hdr_len; + struct ipv4_hdr *ipv4_hdr; + struct ipv6_hdr *ipv6_hdr; + + eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *); + ether_type = eth_hdr->ether_type; + l3 = (uint8_t *)eth_hdr + sizeof(struct ether_hdr); + if (ether_type == rte_cpu_to_be_16(ETHER_TYPE_IPv4)) { + ipv4_hdr = (struct ipv4_hdr *)l3; + hdr_len = (ipv4_hdr->version_ihl & IPV4_HDR_IHL_MASK) * + IPV4_IHL_MULTIPLIER; + if (hdr_len == sizeof(struct ipv4_hdr)) { + packet_type |= RTE_PTYPE_L3_IPV4; + if (ipv4_hdr->next_proto_id == IPPROTO_TCP) + packet_type |= RTE_PTYPE_L4_TCP; + else if (ipv4_hdr->next_proto_id == IPPROTO_UDP) + packet_type |= RTE_PTYPE_L4_UDP; + } else + packet_type |= RTE_PTYPE_L3_IPV4_EXT; + } else if (ether_type == rte_cpu_to_be_16(ETHER_TYPE_IPv6)) { + ipv6_hdr = (struct ipv6_hdr *)l3; + if (ipv6_hdr->proto == IPPROTO_TCP) + packet_type |= RTE_PTYPE_L3_IPV6 | RTE_PTYPE_L4_TCP; + else if (ipv6_hdr->proto == IPPROTO_UDP) + packet_type |= RTE_PTYPE_L3_IPV6 | RTE_PTYPE_L4_UDP; + else + packet_type |= RTE_PTYPE_L3_IPV6_EXT_UNKNOWN; + } + + m->packet_type = packet_type; +} + +uint16_t +em_cb_parse_ptype(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 i; + + for (i = 0; i < nb_pkts; ++i) + em_parse_ptype(pkts[i]); + + return nb_pkts; +} + +/* main processing loop */ +int +em_main_loop(__attribute__((unused)) void *dummy) +{ + struct rte_mbuf *pkts_burst[MAX_PKT_BURST]; + unsigned lcore_id; + uint64_t prev_tsc, diff_tsc, cur_tsc; + int i, nb_rx; + uint8_t queueid; + uint16_t portid; + struct lcore_conf *qconf; + 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, "lcore %u has nothing to do\n", lcore_id); + return 0; + } + + RTE_LOG(INFO, L3FWD, "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, + " -- lcoreid=%u portid=%u rxqueueid=%hhu\n", + lcore_id, portid, queueid); + } + + while (!force_quit) { + + 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]; + if (qconf->tx_mbufs[portid].len == 0) + continue; + send_burst(qconf, + qconf->tx_mbufs[portid].len, + portid); + qconf->tx_mbufs[portid].len = 0; + } + + prev_tsc = cur_tsc; + } + + /* + * Read packet from RX queues + */ + 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; + nb_rx = rte_eth_rx_burst(portid, queueid, pkts_burst, + MAX_PKT_BURST); + if (nb_rx == 0) + continue; + +#if defined RTE_ARCH_X86 || defined RTE_MACHINE_CPUFLAG_NEON + l3fwd_em_send_packets(nb_rx, pkts_burst, + portid, qconf); +#else + l3fwd_em_no_opt_send_packets(nb_rx, pkts_burst, + portid, qconf); +#endif + } + } + + return 0; +} + +/* + * Initialize exact match (hash) parameters. + */ +void +setup_hash(const int socketid) +{ + struct rte_hash_parameters ipv4_l3fwd_hash_params = { + .name = NULL, + .entries = L3FWD_HASH_ENTRIES, + .key_len = sizeof(union ipv4_5tuple_host), + .hash_func = ipv4_hash_crc, + .hash_func_init_val = 0, + }; + + struct rte_hash_parameters ipv6_l3fwd_hash_params = { + .name = NULL, + .entries = L3FWD_HASH_ENTRIES, + .key_len = sizeof(union ipv6_5tuple_host), + .hash_func = ipv6_hash_crc, + .hash_func_init_val = 0, + }; + + char s[64]; + + /* create ipv4 hash */ + snprintf(s, sizeof(s), "ipv4_l3fwd_hash_%d", socketid); + ipv4_l3fwd_hash_params.name = s; + ipv4_l3fwd_hash_params.socket_id = socketid; + ipv4_l3fwd_em_lookup_struct[socketid] = + rte_hash_create(&ipv4_l3fwd_hash_params); + if (ipv4_l3fwd_em_lookup_struct[socketid] == NULL) + rte_exit(EXIT_FAILURE, + "Unable to create the l3fwd hash on socket %d\n", + socketid); + + /* create ipv6 hash */ + snprintf(s, sizeof(s), "ipv6_l3fwd_hash_%d", socketid); + ipv6_l3fwd_hash_params.name = s; + ipv6_l3fwd_hash_params.socket_id = socketid; + ipv6_l3fwd_em_lookup_struct[socketid] = + rte_hash_create(&ipv6_l3fwd_hash_params); + if (ipv6_l3fwd_em_lookup_struct[socketid] == NULL) + rte_exit(EXIT_FAILURE, + "Unable to create the l3fwd hash on socket %d\n", + socketid); + + if (hash_entry_number != HASH_ENTRY_NUMBER_DEFAULT) { + /* For testing hash matching with a large number of flows we + * generate millions of IP 5-tuples with an incremented dst + * address to initialize the hash table. */ + if (ipv6 == 0) { + /* populate the ipv4 hash */ + populate_ipv4_many_flow_into_table( + ipv4_l3fwd_em_lookup_struct[socketid], + hash_entry_number); + } else { + /* populate the ipv6 hash */ + populate_ipv6_many_flow_into_table( + ipv6_l3fwd_em_lookup_struct[socketid], + hash_entry_number); + } + } else { + /* + * Use data in ipv4/ipv6 l3fwd lookup table + * directly to initialize the hash table. + */ + if (ipv6 == 0) { + /* populate the ipv4 hash */ + populate_ipv4_few_flow_into_table( + ipv4_l3fwd_em_lookup_struct[socketid]); + } else { + /* populate the ipv6 hash */ + populate_ipv6_few_flow_into_table( + ipv6_l3fwd_em_lookup_struct[socketid]); + } + } +} + +/* Return ipv4/ipv6 em fwd lookup struct. */ +void * +em_get_ipv4_l3fwd_lookup_struct(const int socketid) +{ + return ipv4_l3fwd_em_lookup_struct[socketid]; +} + +void * +em_get_ipv6_l3fwd_lookup_struct(const int socketid) +{ + return ipv6_l3fwd_em_lookup_struct[socketid]; +} diff --git a/src/seastar/dpdk/examples/l3fwd/l3fwd_em.h b/src/seastar/dpdk/examples/l3fwd/l3fwd_em.h new file mode 100644 index 000000000..228164e26 --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd/l3fwd_em.h @@ -0,0 +1,109 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2010-2016 Intel Corporation + */ + +#ifndef __L3FWD_EM_H__ +#define __L3FWD_EM_H__ + +static __rte_always_inline void +l3fwd_em_simple_forward(struct rte_mbuf *m, uint16_t portid, + struct lcore_conf *qconf) +{ + struct ether_hdr *eth_hdr; + struct ipv4_hdr *ipv4_hdr; + uint16_t dst_port; + uint32_t tcp_or_udp; + uint32_t l3_ptypes; + + eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *); + tcp_or_udp = m->packet_type & (RTE_PTYPE_L4_TCP | RTE_PTYPE_L4_UDP); + l3_ptypes = m->packet_type & RTE_PTYPE_L3_MASK; + + if (tcp_or_udp && (l3_ptypes == RTE_PTYPE_L3_IPV4)) { + /* Handle IPv4 headers.*/ + ipv4_hdr = rte_pktmbuf_mtod_offset(m, struct ipv4_hdr *, + sizeof(struct ether_hdr)); + +#ifdef DO_RFC_1812_CHECKS + /* Check to make sure the packet is valid (RFC1812) */ + if (is_valid_ipv4_pkt(ipv4_hdr, m->pkt_len) < 0) { + rte_pktmbuf_free(m); + return; + } +#endif + dst_port = em_get_ipv4_dst_port(ipv4_hdr, portid, + qconf->ipv4_lookup_struct); + + if (dst_port >= RTE_MAX_ETHPORTS || + (enabled_port_mask & 1 << dst_port) == 0) + dst_port = portid; + +#ifdef DO_RFC_1812_CHECKS + /* Update time to live and header checksum */ + --(ipv4_hdr->time_to_live); + ++(ipv4_hdr->hdr_checksum); +#endif + /* dst addr */ + *(uint64_t *)ð_hdr->d_addr = dest_eth_addr[dst_port]; + + /* src addr */ + ether_addr_copy(&ports_eth_addr[dst_port], ð_hdr->s_addr); + + send_single_packet(qconf, m, dst_port); + } else if (tcp_or_udp && (l3_ptypes == RTE_PTYPE_L3_IPV6)) { + /* Handle IPv6 headers.*/ + struct ipv6_hdr *ipv6_hdr; + + ipv6_hdr = rte_pktmbuf_mtod_offset(m, struct ipv6_hdr *, + sizeof(struct ether_hdr)); + + dst_port = em_get_ipv6_dst_port(ipv6_hdr, portid, + qconf->ipv6_lookup_struct); + + if (dst_port >= RTE_MAX_ETHPORTS || + (enabled_port_mask & 1 << dst_port) == 0) + dst_port = portid; + + /* dst addr */ + *(uint64_t *)ð_hdr->d_addr = dest_eth_addr[dst_port]; + + /* src addr */ + ether_addr_copy(&ports_eth_addr[dst_port], ð_hdr->s_addr); + + send_single_packet(qconf, m, dst_port); + } else { + /* Free the mbuf that contains non-IPV4/IPV6 packet */ + rte_pktmbuf_free(m); + } +} + +/* + * Buffer non-optimized handling of packets, invoked + * from main_loop. + */ +static inline void +l3fwd_em_no_opt_send_packets(int nb_rx, struct rte_mbuf **pkts_burst, + uint16_t portid, struct lcore_conf *qconf) +{ + int32_t j; + + /* 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_em_simple_forward(pkts_burst[j], portid, qconf); + } + + /* Forward remaining prefetched packets */ + for (; j < nb_rx; j++) + l3fwd_em_simple_forward(pkts_burst[j], portid, qconf); +} + +#endif /* __L3FWD_EM_H__ */ diff --git a/src/seastar/dpdk/examples/l3fwd/l3fwd_em_hlm.h b/src/seastar/dpdk/examples/l3fwd/l3fwd_em_hlm.h new file mode 100644 index 000000000..22c26dce3 --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd/l3fwd_em_hlm.h @@ -0,0 +1,189 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2016-2018 Intel Corporation. + * Copyright(c) 2017-2018 Linaro Limited. + */ + +#ifndef __L3FWD_EM_HLM_H__ +#define __L3FWD_EM_HLM_H__ + +#if defined RTE_ARCH_X86 +#include "l3fwd_sse.h" +#include "l3fwd_em_hlm_sse.h" +#elif defined RTE_MACHINE_CPUFLAG_NEON +#include "l3fwd_neon.h" +#include "l3fwd_em_hlm_neon.h" +#endif + +#ifdef RTE_ARCH_ARM64 +#define EM_HASH_LOOKUP_COUNT 16 +#else +#define EM_HASH_LOOKUP_COUNT 8 +#endif + + +static __rte_always_inline void +em_get_dst_port_ipv4xN(struct lcore_conf *qconf, struct rte_mbuf *m[], + uint16_t portid, uint16_t dst_port[]) +{ + int i; + int32_t ret[EM_HASH_LOOKUP_COUNT]; + union ipv4_5tuple_host key[EM_HASH_LOOKUP_COUNT]; + const void *key_array[EM_HASH_LOOKUP_COUNT]; + + for (i = 0; i < EM_HASH_LOOKUP_COUNT; i++) { + get_ipv4_5tuple(m[i], mask0.x, &key[i]); + key_array[i] = &key[i]; + } + + rte_hash_lookup_bulk(qconf->ipv4_lookup_struct, &key_array[0], + EM_HASH_LOOKUP_COUNT, ret); + + for (i = 0; i < EM_HASH_LOOKUP_COUNT; i++) { + dst_port[i] = ((ret[i] < 0) ? + portid : ipv4_l3fwd_out_if[ret[i]]); + + if (dst_port[i] >= RTE_MAX_ETHPORTS || + (enabled_port_mask & 1 << dst_port[i]) == 0) + dst_port[i] = portid; + } +} + +static __rte_always_inline void +em_get_dst_port_ipv6xN(struct lcore_conf *qconf, struct rte_mbuf *m[], + uint16_t portid, uint16_t dst_port[]) +{ + int i; + int32_t ret[EM_HASH_LOOKUP_COUNT]; + union ipv6_5tuple_host key[EM_HASH_LOOKUP_COUNT]; + const void *key_array[EM_HASH_LOOKUP_COUNT]; + + for (i = 0; i < EM_HASH_LOOKUP_COUNT; i++) { + get_ipv6_5tuple(m[i], mask1.x, mask2.x, &key[i]); + key_array[i] = &key[i]; + } + + rte_hash_lookup_bulk(qconf->ipv6_lookup_struct, &key_array[0], + EM_HASH_LOOKUP_COUNT, ret); + + for (i = 0; i < EM_HASH_LOOKUP_COUNT; i++) { + dst_port[i] = ((ret[i] < 0) ? + portid : ipv6_l3fwd_out_if[ret[i]]); + + if (dst_port[i] >= RTE_MAX_ETHPORTS || + (enabled_port_mask & 1 << dst_port[i]) == 0) + dst_port[i] = portid; + } +} + +static __rte_always_inline uint16_t +em_get_dst_port(const struct lcore_conf *qconf, struct rte_mbuf *pkt, + uint16_t portid) +{ + uint16_t next_hop; + struct ipv4_hdr *ipv4_hdr; + struct ipv6_hdr *ipv6_hdr; + uint32_t tcp_or_udp; + uint32_t l3_ptypes; + + tcp_or_udp = pkt->packet_type & (RTE_PTYPE_L4_TCP | RTE_PTYPE_L4_UDP); + l3_ptypes = pkt->packet_type & RTE_PTYPE_L3_MASK; + + if (tcp_or_udp && (l3_ptypes == RTE_PTYPE_L3_IPV4)) { + + /* Handle IPv4 headers.*/ + ipv4_hdr = rte_pktmbuf_mtod_offset(pkt, struct ipv4_hdr *, + sizeof(struct ether_hdr)); + + next_hop = em_get_ipv4_dst_port(ipv4_hdr, portid, + qconf->ipv4_lookup_struct); + + if (next_hop >= RTE_MAX_ETHPORTS || + (enabled_port_mask & 1 << next_hop) == 0) + next_hop = portid; + + return next_hop; + + } else if (tcp_or_udp && (l3_ptypes == RTE_PTYPE_L3_IPV6)) { + + /* Handle IPv6 headers.*/ + ipv6_hdr = rte_pktmbuf_mtod_offset(pkt, struct ipv6_hdr *, + sizeof(struct ether_hdr)); + + next_hop = em_get_ipv6_dst_port(ipv6_hdr, portid, + qconf->ipv6_lookup_struct); + + if (next_hop >= RTE_MAX_ETHPORTS || + (enabled_port_mask & 1 << next_hop) == 0) + next_hop = portid; + + return next_hop; + + } + + return portid; +} + +/* + * Buffer optimized handling of packets, invoked + * from main_loop. + */ +static inline void +l3fwd_em_send_packets(int nb_rx, struct rte_mbuf **pkts_burst, + uint16_t portid, struct lcore_conf *qconf) +{ + int32_t i, j, pos; + uint16_t dst_port[MAX_PKT_BURST]; + + /* + * Send nb_rx - nb_rx % EM_HASH_LOOKUP_COUNT packets + * in groups of EM_HASH_LOOKUP_COUNT. + */ + int32_t n = RTE_ALIGN_FLOOR(nb_rx, EM_HASH_LOOKUP_COUNT); + + for (j = 0; j < EM_HASH_LOOKUP_COUNT && j < nb_rx; j++) { + rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[j], + struct ether_hdr *) + 1); + } + + for (j = 0; j < n; j += EM_HASH_LOOKUP_COUNT) { + + uint32_t pkt_type = RTE_PTYPE_L3_MASK | + RTE_PTYPE_L4_TCP | RTE_PTYPE_L4_UDP; + uint32_t l3_type, tcp_or_udp; + + for (i = 0; i < EM_HASH_LOOKUP_COUNT; i++) + pkt_type &= pkts_burst[j + i]->packet_type; + + l3_type = pkt_type & RTE_PTYPE_L3_MASK; + tcp_or_udp = pkt_type & (RTE_PTYPE_L4_TCP | RTE_PTYPE_L4_UDP); + + for (i = 0, pos = j + EM_HASH_LOOKUP_COUNT; + i < EM_HASH_LOOKUP_COUNT && pos < nb_rx; i++, pos++) { + rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[pos], + struct ether_hdr *) + 1); + } + + if (tcp_or_udp && (l3_type == RTE_PTYPE_L3_IPV4)) { + + em_get_dst_port_ipv4xN(qconf, &pkts_burst[j], portid, + &dst_port[j]); + + } else if (tcp_or_udp && (l3_type == RTE_PTYPE_L3_IPV6)) { + + em_get_dst_port_ipv6xN(qconf, &pkts_burst[j], portid, + &dst_port[j]); + + } else { + for (i = 0; i < EM_HASH_LOOKUP_COUNT; i++) + dst_port[j + i] = em_get_dst_port(qconf, + pkts_burst[j + i], portid); + } + } + + for (; j < nb_rx; j++) + dst_port[j] = em_get_dst_port(qconf, pkts_burst[j], portid); + + send_packets_multi(qconf, pkts_burst, dst_port, nb_rx); + +} +#endif /* __L3FWD_EM_HLM_H__ */ diff --git a/src/seastar/dpdk/examples/l3fwd/l3fwd_em_hlm_neon.h b/src/seastar/dpdk/examples/l3fwd/l3fwd_em_hlm_neon.h new file mode 100644 index 000000000..16c8b04ac --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd/l3fwd_em_hlm_neon.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2016-2018 Intel Corporation. + * Copyright(c) 2017-2018 Linaro Limited. + */ + +#ifndef __L3FWD_EM_HLM_NEON_H__ +#define __L3FWD_EM_HLM_NEON_H__ + +#include <arm_neon.h> + +static inline void +get_ipv4_5tuple(struct rte_mbuf *m0, int32x4_t mask0, + union ipv4_5tuple_host *key) +{ + int32x4_t tmpdata0 = vld1q_s32(rte_pktmbuf_mtod_offset(m0, int32_t *, + sizeof(struct ether_hdr) + + offsetof(struct ipv4_hdr, time_to_live))); + + key->xmm = vandq_s32(tmpdata0, mask0); +} + +static inline void +get_ipv6_5tuple(struct rte_mbuf *m0, int32x4_t mask0, + int32x4_t mask1, union ipv6_5tuple_host *key) +{ + int32x4_t tmpdata0 = vld1q_s32( + rte_pktmbuf_mtod_offset(m0, int *, + sizeof(struct ether_hdr) + + offsetof(struct ipv6_hdr, payload_len))); + + int32x4_t tmpdata1 = vld1q_s32( + rte_pktmbuf_mtod_offset(m0, int *, + sizeof(struct ether_hdr) + + offsetof(struct ipv6_hdr, payload_len) + 8)); + + int32x4_t tmpdata2 = vld1q_s32( + rte_pktmbuf_mtod_offset(m0, int *, + sizeof(struct ether_hdr) + + offsetof(struct ipv6_hdr, payload_len) + 16)); + + key->xmm[0] = vandq_s32(tmpdata0, mask0); + key->xmm[1] = tmpdata1; + key->xmm[2] = vandq_s32(tmpdata2, mask1); +} +#endif /* __L3FWD_EM_HLM_NEON_H__ */ diff --git a/src/seastar/dpdk/examples/l3fwd/l3fwd_em_hlm_sse.h b/src/seastar/dpdk/examples/l3fwd/l3fwd_em_hlm_sse.h new file mode 100644 index 000000000..41e2be958 --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd/l3fwd_em_hlm_sse.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2016 Intel Corporation + */ + +#ifndef __L3FWD_EM_HLM_SSE_H__ +#define __L3FWD_EM_HLM_SSE_H__ + +#include "l3fwd_sse.h" + +static __rte_always_inline void +get_ipv4_5tuple(struct rte_mbuf *m0, __m128i mask0, + union ipv4_5tuple_host *key) +{ + __m128i tmpdata0 = _mm_loadu_si128( + rte_pktmbuf_mtod_offset(m0, __m128i *, + sizeof(struct ether_hdr) + + offsetof(struct ipv4_hdr, time_to_live))); + + key->xmm = _mm_and_si128(tmpdata0, mask0); +} + +static inline void +get_ipv6_5tuple(struct rte_mbuf *m0, __m128i mask0, + __m128i mask1, union ipv6_5tuple_host *key) +{ + __m128i tmpdata0 = _mm_loadu_si128( + rte_pktmbuf_mtod_offset(m0, __m128i *, + sizeof(struct ether_hdr) + + offsetof(struct ipv6_hdr, payload_len))); + + __m128i tmpdata1 = _mm_loadu_si128( + rte_pktmbuf_mtod_offset(m0, __m128i *, + sizeof(struct ether_hdr) + + offsetof(struct ipv6_hdr, payload_len) + + sizeof(__m128i))); + + __m128i tmpdata2 = _mm_loadu_si128( + rte_pktmbuf_mtod_offset(m0, __m128i *, + sizeof(struct ether_hdr) + + offsetof(struct ipv6_hdr, payload_len) + + sizeof(__m128i) + sizeof(__m128i))); + + key->xmm[0] = _mm_and_si128(tmpdata0, mask0); + key->xmm[1] = tmpdata1; + key->xmm[2] = _mm_and_si128(tmpdata2, mask1); +} +#endif /* __L3FWD_EM_SSE_HLM_H__ */ diff --git a/src/seastar/dpdk/examples/l3fwd/l3fwd_em_sequential.h b/src/seastar/dpdk/examples/l3fwd/l3fwd_em_sequential.h new file mode 100644 index 000000000..35cf5eac0 --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd/l3fwd_em_sequential.h @@ -0,0 +1,97 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2010-2016 Intel Corporation + */ + +#ifndef __L3FWD_EM_SEQUENTIAL_H__ +#define __L3FWD_EM_SEQUENTIAL_H__ + +/** + * @file + * This is an optional implementation of packet classification in Exact-Match + * path using sequential packet classification method. + * While hash lookup multi seems to provide better performance, it's disabled + * by default and can be enabled with NO_HASH_LOOKUP_MULTI global define in + * compilation time. + */ + +#if defined RTE_ARCH_X86 +#include "l3fwd_sse.h" +#elif defined RTE_MACHINE_CPUFLAG_NEON +#include "l3fwd_neon.h" +#endif + +static __rte_always_inline uint16_t +em_get_dst_port(const struct lcore_conf *qconf, struct rte_mbuf *pkt, + uint16_t portid) +{ + uint8_t next_hop; + struct ipv4_hdr *ipv4_hdr; + struct ipv6_hdr *ipv6_hdr; + uint32_t tcp_or_udp; + uint32_t l3_ptypes; + + tcp_or_udp = pkt->packet_type & (RTE_PTYPE_L4_TCP | RTE_PTYPE_L4_UDP); + l3_ptypes = pkt->packet_type & RTE_PTYPE_L3_MASK; + + if (tcp_or_udp && (l3_ptypes == RTE_PTYPE_L3_IPV4)) { + + /* Handle IPv4 headers.*/ + ipv4_hdr = rte_pktmbuf_mtod_offset(pkt, struct ipv4_hdr *, + sizeof(struct ether_hdr)); + + next_hop = em_get_ipv4_dst_port(ipv4_hdr, portid, + qconf->ipv4_lookup_struct); + + if (next_hop >= RTE_MAX_ETHPORTS || + (enabled_port_mask & 1 << next_hop) == 0) + next_hop = portid; + + return next_hop; + + } else if (tcp_or_udp && (l3_ptypes == RTE_PTYPE_L3_IPV6)) { + + /* Handle IPv6 headers.*/ + ipv6_hdr = rte_pktmbuf_mtod_offset(pkt, struct ipv6_hdr *, + sizeof(struct ether_hdr)); + + next_hop = em_get_ipv6_dst_port(ipv6_hdr, portid, + qconf->ipv6_lookup_struct); + + if (next_hop >= RTE_MAX_ETHPORTS || + (enabled_port_mask & 1 << next_hop) == 0) + next_hop = portid; + + return next_hop; + + } + + return portid; +} + +/* + * Buffer optimized handling of packets, invoked + * from main_loop. + */ +static inline void +l3fwd_em_send_packets(int nb_rx, struct rte_mbuf **pkts_burst, + uint16_t portid, struct lcore_conf *qconf) +{ + int32_t i, j; + uint16_t dst_port[MAX_PKT_BURST]; + + if (nb_rx > 0) { + rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[0], + struct ether_hdr *) + 1); + } + + for (i = 1, j = 0; j < nb_rx; i++, j++) { + if (i < nb_rx) { + rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[i], + struct ether_hdr *) + 1); + } + dst_port[j] = em_get_dst_port(qconf, pkts_burst[j], portid); + } + + send_packets_multi(qconf, pkts_burst, dst_port, nb_rx); +} +#endif /* __L3FWD_EM_SEQUENTIAL_H__ */ diff --git a/src/seastar/dpdk/examples/l3fwd/l3fwd_lpm.c b/src/seastar/dpdk/examples/l3fwd/l3fwd_lpm.c new file mode 100644 index 000000000..60a00639e --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd/l3fwd_lpm.c @@ -0,0 +1,422 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2010-2016 Intel Corporation + */ + +#include <stdio.h> +#include <stdlib.h> +#include <stdint.h> +#include <inttypes.h> +#include <sys/types.h> +#include <string.h> +#include <sys/queue.h> +#include <stdarg.h> +#include <errno.h> +#include <getopt.h> +#include <stdbool.h> +#include <sys/socket.h> +#include <arpa/inet.h> + +#include <rte_debug.h> +#include <rte_ether.h> +#include <rte_ethdev.h> +#include <rte_cycles.h> +#include <rte_mbuf.h> +#include <rte_ip.h> +#include <rte_tcp.h> +#include <rte_udp.h> +#include <rte_lpm.h> +#include <rte_lpm6.h> + +#include "l3fwd.h" + +struct ipv4_l3fwd_lpm_route { + uint32_t ip; + uint8_t depth; + uint8_t if_out; +}; + +struct ipv6_l3fwd_lpm_route { + uint8_t ip[16]; + uint8_t depth; + uint8_t if_out; +}; + +/* 192.18.0.0/16 are set aside for RFC2544 benchmarking. */ +static struct ipv4_l3fwd_lpm_route ipv4_l3fwd_lpm_route_array[] = { + {IPv4(192, 18, 0, 0), 24, 0}, + {IPv4(192, 18, 1, 0), 24, 1}, + {IPv4(192, 18, 2, 0), 24, 2}, + {IPv4(192, 18, 3, 0), 24, 3}, + {IPv4(192, 18, 4, 0), 24, 4}, + {IPv4(192, 18, 5, 0), 24, 5}, + {IPv4(192, 18, 6, 0), 24, 6}, + {IPv4(192, 18, 7, 0), 24, 7}, +}; + +/* 2001:0200::/48 is IANA reserved range for IPv6 benchmarking (RFC5180) */ +static struct ipv6_l3fwd_lpm_route ipv6_l3fwd_lpm_route_array[] = { + {{32, 1, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0}, 48, 0}, + {{32, 1, 2, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0}, 48, 1}, + {{32, 1, 2, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0}, 48, 2}, + {{32, 1, 2, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0}, 48, 3}, + {{32, 1, 2, 0, 0, 0, 0, 0, 0, 4, 0, 0, 0, 0, 0, 0}, 48, 4}, + {{32, 1, 2, 0, 0, 0, 0, 0, 0, 5, 0, 0, 0, 0, 0, 0}, 48, 5}, + {{32, 1, 2, 0, 0, 0, 0, 0, 0, 6, 0, 0, 0, 0, 0, 0}, 48, 6}, + {{32, 1, 2, 0, 0, 0, 0, 0, 0, 7, 0, 0, 0, 0, 0, 0}, 48, 7}, +}; + +#define IPV4_L3FWD_LPM_NUM_ROUTES \ + (sizeof(ipv4_l3fwd_lpm_route_array) / sizeof(ipv4_l3fwd_lpm_route_array[0])) +#define IPV6_L3FWD_LPM_NUM_ROUTES \ + (sizeof(ipv6_l3fwd_lpm_route_array) / sizeof(ipv6_l3fwd_lpm_route_array[0])) + +#define IPV4_L3FWD_LPM_MAX_RULES 1024 +#define IPV4_L3FWD_LPM_NUMBER_TBL8S (1 << 8) +#define IPV6_L3FWD_LPM_MAX_RULES 1024 +#define IPV6_L3FWD_LPM_NUMBER_TBL8S (1 << 16) + +struct rte_lpm *ipv4_l3fwd_lpm_lookup_struct[NB_SOCKETS]; +struct rte_lpm6 *ipv6_l3fwd_lpm_lookup_struct[NB_SOCKETS]; + +static inline uint16_t +lpm_get_ipv4_dst_port(void *ipv4_hdr, uint16_t portid, void *lookup_struct) +{ + uint32_t next_hop; + struct rte_lpm *ipv4_l3fwd_lookup_struct = + (struct rte_lpm *)lookup_struct; + + return (uint16_t) ((rte_lpm_lookup(ipv4_l3fwd_lookup_struct, + rte_be_to_cpu_32(((struct ipv4_hdr *)ipv4_hdr)->dst_addr), + &next_hop) == 0) ? next_hop : portid); +} + +static inline uint16_t +lpm_get_ipv6_dst_port(void *ipv6_hdr, uint16_t portid, void *lookup_struct) +{ + uint32_t next_hop; + struct rte_lpm6 *ipv6_l3fwd_lookup_struct = + (struct rte_lpm6 *)lookup_struct; + + return (uint16_t) ((rte_lpm6_lookup(ipv6_l3fwd_lookup_struct, + ((struct ipv6_hdr *)ipv6_hdr)->dst_addr, + &next_hop) == 0) ? next_hop : portid); +} + +static __rte_always_inline uint16_t +lpm_get_dst_port(const struct lcore_conf *qconf, struct rte_mbuf *pkt, + uint16_t portid) +{ + struct ipv6_hdr *ipv6_hdr; + struct ipv4_hdr *ipv4_hdr; + struct ether_hdr *eth_hdr; + + if (RTE_ETH_IS_IPV4_HDR(pkt->packet_type)) { + + eth_hdr = rte_pktmbuf_mtod(pkt, struct ether_hdr *); + ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1); + + return lpm_get_ipv4_dst_port(ipv4_hdr, portid, + qconf->ipv4_lookup_struct); + } else if (RTE_ETH_IS_IPV6_HDR(pkt->packet_type)) { + + eth_hdr = rte_pktmbuf_mtod(pkt, struct ether_hdr *); + ipv6_hdr = (struct ipv6_hdr *)(eth_hdr + 1); + + return lpm_get_ipv6_dst_port(ipv6_hdr, portid, + qconf->ipv6_lookup_struct); + } + + return portid; +} + +/* + * lpm_get_dst_port optimized routine for packets where dst_ipv4 is already + * precalculated. If packet is ipv6 dst_addr is taken directly from packet + * header and dst_ipv4 value is not used. + */ +static __rte_always_inline uint16_t +lpm_get_dst_port_with_ipv4(const struct lcore_conf *qconf, struct rte_mbuf *pkt, + uint32_t dst_ipv4, uint16_t portid) +{ + uint32_t next_hop; + struct ipv6_hdr *ipv6_hdr; + struct ether_hdr *eth_hdr; + + if (RTE_ETH_IS_IPV4_HDR(pkt->packet_type)) { + return (uint16_t) ((rte_lpm_lookup(qconf->ipv4_lookup_struct, + dst_ipv4, &next_hop) == 0) + ? next_hop : portid); + + } else if (RTE_ETH_IS_IPV6_HDR(pkt->packet_type)) { + + eth_hdr = rte_pktmbuf_mtod(pkt, struct ether_hdr *); + ipv6_hdr = (struct ipv6_hdr *)(eth_hdr + 1); + + return (uint16_t) ((rte_lpm6_lookup(qconf->ipv6_lookup_struct, + ipv6_hdr->dst_addr, &next_hop) == 0) + ? next_hop : portid); + + } + + return portid; +} + +#if defined(RTE_ARCH_X86) +#include "l3fwd_lpm_sse.h" +#elif defined RTE_MACHINE_CPUFLAG_NEON +#include "l3fwd_lpm_neon.h" +#elif defined(RTE_ARCH_PPC_64) +#include "l3fwd_lpm_altivec.h" +#else +#include "l3fwd_lpm.h" +#endif + +/* main processing loop */ +int +lpm_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; + int i, nb_rx; + uint16_t portid; + uint8_t queueid; + struct lcore_conf *qconf; + 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, "lcore %u has nothing to do\n", lcore_id); + return 0; + } + + RTE_LOG(INFO, L3FWD, "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, + " -- lcoreid=%u portid=%u rxqueueid=%hhu\n", + lcore_id, portid, queueid); + } + + while (!force_quit) { + + 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]; + if (qconf->tx_mbufs[portid].len == 0) + continue; + send_burst(qconf, + qconf->tx_mbufs[portid].len, + portid); + qconf->tx_mbufs[portid].len = 0; + } + + prev_tsc = cur_tsc; + } + + /* + * Read packet from RX queues + */ + 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; + nb_rx = rte_eth_rx_burst(portid, queueid, pkts_burst, + MAX_PKT_BURST); + if (nb_rx == 0) + continue; + +#if defined RTE_ARCH_X86 || defined RTE_MACHINE_CPUFLAG_NEON \ + || defined RTE_ARCH_PPC_64 + l3fwd_lpm_send_packets(nb_rx, pkts_burst, + portid, qconf); +#else + l3fwd_lpm_no_opt_send_packets(nb_rx, pkts_burst, + portid, qconf); +#endif /* X86 */ + } + } + + return 0; +} + +void +setup_lpm(const int socketid) +{ + struct rte_lpm6_config config; + struct rte_lpm_config config_ipv4; + unsigned i; + int ret; + char s[64]; + char abuf[INET6_ADDRSTRLEN]; + + /* create the LPM table */ + config_ipv4.max_rules = IPV4_L3FWD_LPM_MAX_RULES; + config_ipv4.number_tbl8s = IPV4_L3FWD_LPM_NUMBER_TBL8S; + config_ipv4.flags = 0; + snprintf(s, sizeof(s), "IPV4_L3FWD_LPM_%d", socketid); + ipv4_l3fwd_lpm_lookup_struct[socketid] = + rte_lpm_create(s, socketid, &config_ipv4); + if (ipv4_l3fwd_lpm_lookup_struct[socketid] == NULL) + rte_exit(EXIT_FAILURE, + "Unable to create the l3fwd LPM table on socket %d\n", + socketid); + + /* populate the LPM table */ + for (i = 0; i < IPV4_L3FWD_LPM_NUM_ROUTES; i++) { + struct in_addr in; + + /* skip unused ports */ + if ((1 << ipv4_l3fwd_lpm_route_array[i].if_out & + enabled_port_mask) == 0) + continue; + + ret = rte_lpm_add(ipv4_l3fwd_lpm_lookup_struct[socketid], + ipv4_l3fwd_lpm_route_array[i].ip, + ipv4_l3fwd_lpm_route_array[i].depth, + ipv4_l3fwd_lpm_route_array[i].if_out); + + if (ret < 0) { + rte_exit(EXIT_FAILURE, + "Unable to add entry %u to the l3fwd LPM table on socket %d\n", + i, socketid); + } + + in.s_addr = htonl(ipv4_l3fwd_lpm_route_array[i].ip); + printf("LPM: Adding route %s / %d (%d)\n", + inet_ntop(AF_INET, &in, abuf, sizeof(abuf)), + ipv4_l3fwd_lpm_route_array[i].depth, + ipv4_l3fwd_lpm_route_array[i].if_out); + } + + /* create the LPM6 table */ + snprintf(s, sizeof(s), "IPV6_L3FWD_LPM_%d", socketid); + + config.max_rules = IPV6_L3FWD_LPM_MAX_RULES; + config.number_tbl8s = IPV6_L3FWD_LPM_NUMBER_TBL8S; + config.flags = 0; + ipv6_l3fwd_lpm_lookup_struct[socketid] = rte_lpm6_create(s, socketid, + &config); + if (ipv6_l3fwd_lpm_lookup_struct[socketid] == NULL) + rte_exit(EXIT_FAILURE, + "Unable to create the l3fwd LPM table on socket %d\n", + socketid); + + /* populate the LPM table */ + for (i = 0; i < IPV6_L3FWD_LPM_NUM_ROUTES; i++) { + + /* skip unused ports */ + if ((1 << ipv6_l3fwd_lpm_route_array[i].if_out & + enabled_port_mask) == 0) + continue; + + ret = rte_lpm6_add(ipv6_l3fwd_lpm_lookup_struct[socketid], + ipv6_l3fwd_lpm_route_array[i].ip, + ipv6_l3fwd_lpm_route_array[i].depth, + ipv6_l3fwd_lpm_route_array[i].if_out); + + if (ret < 0) { + rte_exit(EXIT_FAILURE, + "Unable to add entry %u to the l3fwd LPM table on socket %d\n", + i, socketid); + } + + printf("LPM: Adding route %s / %d (%d)\n", + inet_ntop(AF_INET6, ipv6_l3fwd_lpm_route_array[i].ip, + abuf, sizeof(abuf)), + ipv6_l3fwd_lpm_route_array[i].depth, + ipv6_l3fwd_lpm_route_array[i].if_out); + } +} + +int +lpm_check_ptype(int portid) +{ + int i, ret; + int ptype_l3_ipv4 = 0, ptype_l3_ipv6 = 0; + 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 (ptypes[i] & RTE_PTYPE_L3_IPV6) + ptype_l3_ipv6 = 1; + } + + if (ptype_l3_ipv4 == 0) + printf("port %d cannot parse RTE_PTYPE_L3_IPV4\n", portid); + + if (ptype_l3_ipv6 == 0) + printf("port %d cannot parse RTE_PTYPE_L3_IPV6\n", portid); + + if (ptype_l3_ipv4 && ptype_l3_ipv6) + return 1; + + return 0; + +} + +static inline void +lpm_parse_ptype(struct rte_mbuf *m) +{ + struct ether_hdr *eth_hdr; + uint32_t packet_type = RTE_PTYPE_UNKNOWN; + uint16_t ether_type; + + eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *); + ether_type = eth_hdr->ether_type; + if (ether_type == rte_cpu_to_be_16(ETHER_TYPE_IPv4)) + packet_type |= RTE_PTYPE_L3_IPV4_EXT_UNKNOWN; + else if (ether_type == rte_cpu_to_be_16(ETHER_TYPE_IPv6)) + packet_type |= RTE_PTYPE_L3_IPV6_EXT_UNKNOWN; + + m->packet_type = packet_type; +} + +uint16_t +lpm_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 i; + + for (i = 0; i < nb_pkts; ++i) + lpm_parse_ptype(pkts[i]); + + return nb_pkts; +} + +/* Return ipv4/ipv6 lpm fwd lookup struct. */ +void * +lpm_get_ipv4_l3fwd_lookup_struct(const int socketid) +{ + return ipv4_l3fwd_lpm_lookup_struct[socketid]; +} + +void * +lpm_get_ipv6_l3fwd_lookup_struct(const int socketid) +{ + return ipv6_l3fwd_lpm_lookup_struct[socketid]; +} diff --git a/src/seastar/dpdk/examples/l3fwd/l3fwd_lpm.h b/src/seastar/dpdk/examples/l3fwd/l3fwd_lpm.h new file mode 100644 index 000000000..b68868f44 --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd/l3fwd_lpm.h @@ -0,0 +1,98 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2010-2016 Intel Corporation + */ + +#ifndef __L3FWD_LPM_H__ +#define __L3FWD_LPM_H__ + +static __rte_always_inline void +l3fwd_lpm_simple_forward(struct rte_mbuf *m, uint16_t portid, + struct lcore_conf *qconf) +{ + struct ether_hdr *eth_hdr; + struct ipv4_hdr *ipv4_hdr; + uint16_t dst_port; + + eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *); + + if (RTE_ETH_IS_IPV4_HDR(m->packet_type)) { + /* Handle IPv4 headers.*/ + ipv4_hdr = rte_pktmbuf_mtod_offset(m, struct ipv4_hdr *, + sizeof(struct ether_hdr)); + +#ifdef DO_RFC_1812_CHECKS + /* Check to make sure the packet is valid (RFC1812) */ + if (is_valid_ipv4_pkt(ipv4_hdr, m->pkt_len) < 0) { + rte_pktmbuf_free(m); + return; + } +#endif + dst_port = lpm_get_ipv4_dst_port(ipv4_hdr, portid, + qconf->ipv4_lookup_struct); + + if (dst_port >= RTE_MAX_ETHPORTS || + (enabled_port_mask & 1 << dst_port) == 0) + dst_port = portid; + +#ifdef DO_RFC_1812_CHECKS + /* Update time to live and header checksum */ + --(ipv4_hdr->time_to_live); + ++(ipv4_hdr->hdr_checksum); +#endif + /* dst addr */ + *(uint64_t *)ð_hdr->d_addr = dest_eth_addr[dst_port]; + + /* src addr */ + ether_addr_copy(&ports_eth_addr[dst_port], ð_hdr->s_addr); + + send_single_packet(qconf, m, dst_port); + } else if (RTE_ETH_IS_IPV6_HDR(m->packet_type)) { + /* Handle IPv6 headers.*/ + struct ipv6_hdr *ipv6_hdr; + + ipv6_hdr = rte_pktmbuf_mtod_offset(m, struct ipv6_hdr *, + sizeof(struct ether_hdr)); + + dst_port = lpm_get_ipv6_dst_port(ipv6_hdr, portid, + qconf->ipv6_lookup_struct); + + if (dst_port >= RTE_MAX_ETHPORTS || + (enabled_port_mask & 1 << dst_port) == 0) + dst_port = portid; + + /* dst addr */ + *(uint64_t *)ð_hdr->d_addr = dest_eth_addr[dst_port]; + + /* src addr */ + ether_addr_copy(&ports_eth_addr[dst_port], ð_hdr->s_addr); + + send_single_packet(qconf, m, dst_port); + } else { + /* Free the mbuf that contains non-IPV4/IPV6 packet */ + rte_pktmbuf_free(m); + } +} + +static inline void +l3fwd_lpm_no_opt_send_packets(int nb_rx, struct rte_mbuf **pkts_burst, + uint16_t portid, struct lcore_conf *qconf) +{ + int32_t j; + + /* 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_lpm_simple_forward(pkts_burst[j], portid, qconf); + } + + /* Forward remaining prefetched packets */ + for (; j < nb_rx; j++) + l3fwd_lpm_simple_forward(pkts_burst[j], portid, qconf); +} + +#endif /* __L3FWD_LPM_H__ */ diff --git a/src/seastar/dpdk/examples/l3fwd/l3fwd_lpm_altivec.h b/src/seastar/dpdk/examples/l3fwd/l3fwd_lpm_altivec.h new file mode 100644 index 000000000..4c9e2438b --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd/l3fwd_lpm_altivec.h @@ -0,0 +1,136 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2010-2016 Intel Corporation. + * Copyright(c) 2017 IBM Corporation. + * All rights reserved. + */ + +#ifndef __L3FWD_LPM_ALTIVEC_H__ +#define __L3FWD_LPM_ALTIVEC_H__ + +#include "l3fwd_altivec.h" + +/* + * Read packet_type and destination IPV4 addresses from 4 mbufs. + */ +static inline void +processx4_step1(struct rte_mbuf *pkt[FWDSTEP], + vector unsigned int *dip, + uint32_t *ipv4_flag) +{ + struct ipv4_hdr *ipv4_hdr; + struct ether_hdr *eth_hdr; + uint32_t x0, x1, x2, x3; + + eth_hdr = rte_pktmbuf_mtod(pkt[0], struct ether_hdr *); + ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1); + x0 = ipv4_hdr->dst_addr; + ipv4_flag[0] = pkt[0]->packet_type & RTE_PTYPE_L3_IPV4; + + rte_compiler_barrier(); + eth_hdr = rte_pktmbuf_mtod(pkt[1], struct ether_hdr *); + ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1); + x1 = ipv4_hdr->dst_addr; + ipv4_flag[0] &= pkt[1]->packet_type; + + rte_compiler_barrier(); + eth_hdr = rte_pktmbuf_mtod(pkt[2], struct ether_hdr *); + ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1); + x2 = ipv4_hdr->dst_addr; + ipv4_flag[0] &= pkt[2]->packet_type; + + rte_compiler_barrier(); + eth_hdr = rte_pktmbuf_mtod(pkt[3], struct ether_hdr *); + ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1); + x3 = ipv4_hdr->dst_addr; + ipv4_flag[0] &= pkt[3]->packet_type; + + rte_compiler_barrier(); + dip[0] = (vector unsigned int){x0, x1, x2, x3}; +} + +/* + * Lookup into LPM for destination port. + * If lookup fails, use incoming port (portid) as destination port. + */ +static inline void +processx4_step2(const struct lcore_conf *qconf, + vector unsigned int dip, + uint32_t ipv4_flag, + uint8_t portid, + struct rte_mbuf *pkt[FWDSTEP], + uint16_t dprt[FWDSTEP]) +{ + rte_xmm_t dst; + const vector unsigned char bswap_mask = (vector unsigned char){ + 3, 2, 1, 0, + 7, 6, 5, 4, + 11, 10, 9, 8, + 15, 14, 13, 12}; + + /* Byte swap 4 IPV4 addresses. */ + dip = (vector unsigned int)vec_perm(*(vector unsigned char *)&dip, + (vector unsigned char){}, bswap_mask); + + /* if all 4 packets are IPV4. */ + if (likely(ipv4_flag)) { + rte_lpm_lookupx4(qconf->ipv4_lookup_struct, (xmm_t)dip, + (uint32_t *)&dst, portid); + /* get rid of unused upper 16 bit for each dport. */ + dst.x = (xmm_t)vec_packs(dst.x, dst.x); + *(uint64_t *)dprt = dst.u64[0]; + } else { + dst.x = (xmm_t)dip; + dprt[0] = lpm_get_dst_port_with_ipv4(qconf, pkt[0], + dst.u32[0], portid); + dprt[1] = lpm_get_dst_port_with_ipv4(qconf, pkt[1], + dst.u32[1], portid); + dprt[2] = lpm_get_dst_port_with_ipv4(qconf, pkt[2], + dst.u32[2], portid); + dprt[3] = lpm_get_dst_port_with_ipv4(qconf, pkt[3], + dst.u32[3], portid); + } +} + +/* + * Buffer optimized handling of packets, invoked + * from main_loop. + */ +static inline void +l3fwd_lpm_send_packets(int nb_rx, struct rte_mbuf **pkts_burst, + uint8_t portid, struct lcore_conf *qconf) +{ + int32_t j; + uint16_t dst_port[MAX_PKT_BURST]; + vector unsigned int dip[MAX_PKT_BURST / FWDSTEP]; + uint32_t ipv4_flag[MAX_PKT_BURST / FWDSTEP]; + const int32_t k = RTE_ALIGN_FLOOR(nb_rx, FWDSTEP); + + for (j = 0; j != k; j += FWDSTEP) + processx4_step1(&pkts_burst[j], &dip[j / FWDSTEP], + &ipv4_flag[j / FWDSTEP]); + + for (j = 0; j != k; j += FWDSTEP) + processx4_step2(qconf, dip[j / FWDSTEP], + ipv4_flag[j / FWDSTEP], + portid, &pkts_burst[j], &dst_port[j]); + + /* Classify last up to 3 packets one by one */ + switch (nb_rx % FWDSTEP) { + case 3: + dst_port[j] = lpm_get_dst_port(qconf, pkts_burst[j], portid); + j++; + /* fall-through */ + case 2: + dst_port[j] = lpm_get_dst_port(qconf, pkts_burst[j], portid); + j++; + /* fall-through */ + case 1: + dst_port[j] = lpm_get_dst_port(qconf, pkts_burst[j], portid); + j++; + /* fall-through */ + } + + send_packets_multi(qconf, pkts_burst, dst_port, nb_rx); +} + +#endif /* __L3FWD_LPM_ALTIVEC_H__ */ diff --git a/src/seastar/dpdk/examples/l3fwd/l3fwd_lpm_neon.h b/src/seastar/dpdk/examples/l3fwd/l3fwd_lpm_neon.h new file mode 100644 index 000000000..02ec0d802 --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd/l3fwd_lpm_neon.h @@ -0,0 +1,164 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2010-2018 Intel Corporation. + * Copyright(c) 2017-2018 Linaro Limited. + */ + +#ifndef __L3FWD_LPM_NEON_H__ +#define __L3FWD_LPM_NEON_H__ + +#include <arm_neon.h> + +#include "l3fwd_neon.h" + +/* + * Read packet_type and destination IPV4 addresses from 4 mbufs. + */ +static inline void +processx4_step1(struct rte_mbuf *pkt[FWDSTEP], + int32x4_t *dip, + uint32_t *ipv4_flag) +{ + struct ipv4_hdr *ipv4_hdr; + struct ether_hdr *eth_hdr; + int32_t dst[FWDSTEP]; + + eth_hdr = rte_pktmbuf_mtod(pkt[0], struct ether_hdr *); + ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1); + dst[0] = ipv4_hdr->dst_addr; + ipv4_flag[0] = pkt[0]->packet_type & RTE_PTYPE_L3_IPV4; + + eth_hdr = rte_pktmbuf_mtod(pkt[1], struct ether_hdr *); + ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1); + dst[1] = ipv4_hdr->dst_addr; + ipv4_flag[0] &= pkt[1]->packet_type; + + eth_hdr = rte_pktmbuf_mtod(pkt[2], struct ether_hdr *); + ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1); + dst[2] = ipv4_hdr->dst_addr; + ipv4_flag[0] &= pkt[2]->packet_type; + + eth_hdr = rte_pktmbuf_mtod(pkt[3], struct ether_hdr *); + ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1); + dst[3] = ipv4_hdr->dst_addr; + ipv4_flag[0] &= pkt[3]->packet_type; + + dip[0] = vld1q_s32(dst); +} + +/* + * Lookup into LPM for destination port. + * If lookup fails, use incoming port (portid) as destination port. + */ +static inline void +processx4_step2(const struct lcore_conf *qconf, + int32x4_t dip, + uint32_t ipv4_flag, + uint16_t portid, + struct rte_mbuf *pkt[FWDSTEP], + uint16_t dprt[FWDSTEP]) +{ + rte_xmm_t dst; + + dip = vreinterpretq_s32_u8(vrev32q_u8(vreinterpretq_u8_s32(dip))); + + /* if all 4 packets are IPV4. */ + if (likely(ipv4_flag)) { + rte_lpm_lookupx4(qconf->ipv4_lookup_struct, dip, dst.u32, + portid); + /* get rid of unused upper 16 bit for each dport. */ + vst1_s16((int16_t *)dprt, vqmovn_s32(dst.x)); + } else { + dst.x = dip; + dprt[0] = lpm_get_dst_port_with_ipv4(qconf, pkt[0], + dst.u32[0], portid); + dprt[1] = lpm_get_dst_port_with_ipv4(qconf, pkt[1], + dst.u32[1], portid); + dprt[2] = lpm_get_dst_port_with_ipv4(qconf, pkt[2], + dst.u32[2], portid); + dprt[3] = lpm_get_dst_port_with_ipv4(qconf, pkt[3], + dst.u32[3], portid); + } +} + +/* + * Buffer optimized handling of packets, invoked + * from main_loop. + */ +static inline void +l3fwd_lpm_send_packets(int nb_rx, struct rte_mbuf **pkts_burst, + uint16_t portid, struct lcore_conf *qconf) +{ + int32_t i = 0, j = 0; + uint16_t dst_port[MAX_PKT_BURST]; + int32x4_t dip; + uint32_t ipv4_flag; + const int32_t k = RTE_ALIGN_FLOOR(nb_rx, FWDSTEP); + const int32_t m = nb_rx % FWDSTEP; + + if (k) { + for (i = 0; i < FWDSTEP; i++) { + rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[i], + struct ether_hdr *) + 1); + } + + for (j = 0; j != k - FWDSTEP; j += FWDSTEP) { + for (i = 0; i < FWDSTEP; i++) { + rte_prefetch0(rte_pktmbuf_mtod( + pkts_burst[j + i + FWDSTEP], + struct ether_hdr *) + 1); + } + + processx4_step1(&pkts_burst[j], &dip, &ipv4_flag); + processx4_step2(qconf, dip, ipv4_flag, portid, + &pkts_burst[j], &dst_port[j]); + } + + processx4_step1(&pkts_burst[j], &dip, &ipv4_flag); + processx4_step2(qconf, dip, ipv4_flag, portid, &pkts_burst[j], + &dst_port[j]); + + j += FWDSTEP; + } + + if (m) { + /* Prefetch last up to 3 packets one by one */ + switch (m) { + case 3: + rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[j], + struct ether_hdr *) + 1); + j++; + /* fallthrough */ + case 2: + rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[j], + struct ether_hdr *) + 1); + j++; + /* fallthrough */ + case 1: + rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[j], + struct ether_hdr *) + 1); + j++; + } + + j -= m; + /* Classify last up to 3 packets one by one */ + switch (m) { + case 3: + dst_port[j] = lpm_get_dst_port(qconf, pkts_burst[j], + portid); + j++; + /* fallthrough */ + case 2: + dst_port[j] = lpm_get_dst_port(qconf, pkts_burst[j], + portid); + j++; + /* fallthrough */ + case 1: + dst_port[j] = lpm_get_dst_port(qconf, pkts_burst[j], + portid); + } + } + + send_packets_multi(qconf, pkts_burst, dst_port, nb_rx); +} + +#endif /* __L3FWD_LPM_NEON_H__ */ diff --git a/src/seastar/dpdk/examples/l3fwd/l3fwd_lpm_sse.h b/src/seastar/dpdk/examples/l3fwd/l3fwd_lpm_sse.h new file mode 100644 index 000000000..1d1615906 --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd/l3fwd_lpm_sse.h @@ -0,0 +1,120 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2010-2016 Intel Corporation + */ + +#ifndef __L3FWD_LPM_SSE_H__ +#define __L3FWD_LPM_SSE_H__ + +#include "l3fwd_sse.h" + +/* + * Read packet_type and destination IPV4 addresses from 4 mbufs. + */ +static inline void +processx4_step1(struct rte_mbuf *pkt[FWDSTEP], + __m128i *dip, + uint32_t *ipv4_flag) +{ + struct ipv4_hdr *ipv4_hdr; + struct ether_hdr *eth_hdr; + uint32_t x0, x1, x2, x3; + + eth_hdr = rte_pktmbuf_mtod(pkt[0], struct ether_hdr *); + ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1); + x0 = ipv4_hdr->dst_addr; + ipv4_flag[0] = pkt[0]->packet_type & RTE_PTYPE_L3_IPV4; + + eth_hdr = rte_pktmbuf_mtod(pkt[1], struct ether_hdr *); + ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1); + x1 = ipv4_hdr->dst_addr; + ipv4_flag[0] &= pkt[1]->packet_type; + + eth_hdr = rte_pktmbuf_mtod(pkt[2], struct ether_hdr *); + ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1); + x2 = ipv4_hdr->dst_addr; + ipv4_flag[0] &= pkt[2]->packet_type; + + eth_hdr = rte_pktmbuf_mtod(pkt[3], struct ether_hdr *); + ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1); + x3 = ipv4_hdr->dst_addr; + ipv4_flag[0] &= pkt[3]->packet_type; + + dip[0] = _mm_set_epi32(x3, x2, x1, x0); +} + +/* + * Lookup into LPM for destination port. + * If lookup fails, use incoming port (portid) as destination port. + */ +static inline void +processx4_step2(const struct lcore_conf *qconf, + __m128i dip, + uint32_t ipv4_flag, + uint16_t portid, + struct rte_mbuf *pkt[FWDSTEP], + uint16_t dprt[FWDSTEP]) +{ + rte_xmm_t dst; + const __m128i bswap_mask = _mm_set_epi8(12, 13, 14, 15, 8, 9, 10, 11, + 4, 5, 6, 7, 0, 1, 2, 3); + + /* Byte swap 4 IPV4 addresses. */ + dip = _mm_shuffle_epi8(dip, bswap_mask); + + /* if all 4 packets are IPV4. */ + if (likely(ipv4_flag)) { + rte_lpm_lookupx4(qconf->ipv4_lookup_struct, dip, dst.u32, + portid); + /* get rid of unused upper 16 bit for each dport. */ + dst.x = _mm_packs_epi32(dst.x, dst.x); + *(uint64_t *)dprt = dst.u64[0]; + } else { + dst.x = dip; + dprt[0] = lpm_get_dst_port_with_ipv4(qconf, pkt[0], dst.u32[0], portid); + dprt[1] = lpm_get_dst_port_with_ipv4(qconf, pkt[1], dst.u32[1], portid); + dprt[2] = lpm_get_dst_port_with_ipv4(qconf, pkt[2], dst.u32[2], portid); + dprt[3] = lpm_get_dst_port_with_ipv4(qconf, pkt[3], dst.u32[3], portid); + } +} + +/* + * Buffer optimized handling of packets, invoked + * from main_loop. + */ +static inline void +l3fwd_lpm_send_packets(int nb_rx, struct rte_mbuf **pkts_burst, + uint16_t portid, struct lcore_conf *qconf) +{ + int32_t j; + uint16_t dst_port[MAX_PKT_BURST]; + __m128i dip[MAX_PKT_BURST / FWDSTEP]; + uint32_t ipv4_flag[MAX_PKT_BURST / FWDSTEP]; + const int32_t k = RTE_ALIGN_FLOOR(nb_rx, FWDSTEP); + + for (j = 0; j != k; j += FWDSTEP) + processx4_step1(&pkts_burst[j], &dip[j / FWDSTEP], + &ipv4_flag[j / FWDSTEP]); + + for (j = 0; j != k; j += FWDSTEP) + processx4_step2(qconf, dip[j / FWDSTEP], + ipv4_flag[j / FWDSTEP], portid, &pkts_burst[j], &dst_port[j]); + + /* Classify last up to 3 packets one by one */ + switch (nb_rx % FWDSTEP) { + case 3: + dst_port[j] = lpm_get_dst_port(qconf, pkts_burst[j], portid); + j++; + /* fall-through */ + case 2: + dst_port[j] = lpm_get_dst_port(qconf, pkts_burst[j], portid); + j++; + /* fall-through */ + case 1: + dst_port[j] = lpm_get_dst_port(qconf, pkts_burst[j], portid); + j++; + } + + send_packets_multi(qconf, pkts_burst, dst_port, nb_rx); +} + +#endif /* __L3FWD_LPM_SSE_H__ */ diff --git a/src/seastar/dpdk/examples/l3fwd/l3fwd_neon.h b/src/seastar/dpdk/examples/l3fwd/l3fwd_neon.h new file mode 100644 index 000000000..76ccdfa73 --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd/l3fwd_neon.h @@ -0,0 +1,230 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2016-2018 Intel Corporation. + * Copyright(c) 2017-2018 Linaro Limited. + */ + +#ifndef _L3FWD_NEON_H_ +#define _L3FWD_NEON_H_ + +#include "l3fwd.h" +#include "l3fwd_common.h" + +/* + * Update source and destination MAC addresses in the ethernet header. + * Perform RFC1812 checks and updates for IPV4 packets. + */ +static inline void +processx4_step3(struct rte_mbuf *pkt[FWDSTEP], uint16_t dst_port[FWDSTEP]) +{ + uint32x4_t te[FWDSTEP]; + uint32x4_t ve[FWDSTEP]; + uint32_t *p[FWDSTEP]; + + p[0] = rte_pktmbuf_mtod(pkt[0], uint32_t *); + p[1] = rte_pktmbuf_mtod(pkt[1], uint32_t *); + p[2] = rte_pktmbuf_mtod(pkt[2], uint32_t *); + p[3] = rte_pktmbuf_mtod(pkt[3], uint32_t *); + + ve[0] = vreinterpretq_u32_s32(val_eth[dst_port[0]]); + te[0] = vld1q_u32(p[0]); + + ve[1] = vreinterpretq_u32_s32(val_eth[dst_port[1]]); + te[1] = vld1q_u32(p[1]); + + ve[2] = vreinterpretq_u32_s32(val_eth[dst_port[2]]); + te[2] = vld1q_u32(p[2]); + + ve[3] = vreinterpretq_u32_s32(val_eth[dst_port[3]]); + te[3] = vld1q_u32(p[3]); + + /* Update last 4 bytes */ + ve[0] = vsetq_lane_u32(vgetq_lane_u32(te[0], 3), ve[0], 3); + ve[1] = vsetq_lane_u32(vgetq_lane_u32(te[1], 3), ve[1], 3); + ve[2] = vsetq_lane_u32(vgetq_lane_u32(te[2], 3), ve[2], 3); + ve[3] = vsetq_lane_u32(vgetq_lane_u32(te[3], 3), ve[3], 3); + + vst1q_u32(p[0], ve[0]); + vst1q_u32(p[1], ve[1]); + vst1q_u32(p[2], ve[2]); + vst1q_u32(p[3], ve[3]); + + rfc1812_process((struct ipv4_hdr *)((struct ether_hdr *)p[0] + 1), + &dst_port[0], pkt[0]->packet_type); + rfc1812_process((struct ipv4_hdr *)((struct ether_hdr *)p[1] + 1), + &dst_port[1], pkt[1]->packet_type); + rfc1812_process((struct ipv4_hdr *)((struct ether_hdr *)p[2] + 1), + &dst_port[2], pkt[2]->packet_type); + rfc1812_process((struct ipv4_hdr *)((struct ether_hdr *)p[3] + 1), + &dst_port[3], pkt[3]->packet_type); +} + +/* + * Group consecutive packets with the same destination port in bursts of 4. + * Suppose we have array of destionation ports: + * dst_port[] = {a, b, c, d,, e, ... } + * dp1 should contain: <a, b, c, d>, dp2: <b, c, d, e>. + * We doing 4 comparisons at once and the result is 4 bit mask. + * This mask is used as an index into prebuild array of pnum values. + */ +static inline uint16_t * +port_groupx4(uint16_t pn[FWDSTEP + 1], uint16_t *lp, uint16x8_t dp1, + uint16x8_t dp2) +{ + union { + uint16_t u16[FWDSTEP + 1]; + uint64_t u64; + } *pnum = (void *)pn; + + int32_t v; + uint16x8_t mask = {1, 2, 4, 8, 0, 0, 0, 0}; + + dp1 = vceqq_u16(dp1, dp2); + dp1 = vandq_u16(dp1, mask); + v = vaddvq_u16(dp1); + + /* update last port counter. */ + lp[0] += gptbl[v].lpv; + rte_compiler_barrier(); + + /* if dest port value has changed. */ + if (v != GRPMSK) { + pnum->u64 = gptbl[v].pnum; + pnum->u16[FWDSTEP] = 1; + lp = pnum->u16 + gptbl[v].idx; + } + + return lp; +} + +/** + * Process one packet: + * Update source and destination MAC addresses in the ethernet header. + * Perform RFC1812 checks and updates for IPV4 packets. + */ +static inline void +process_packet(struct rte_mbuf *pkt, uint16_t *dst_port) +{ + struct ether_hdr *eth_hdr; + uint32x4_t te, ve; + + eth_hdr = rte_pktmbuf_mtod(pkt, struct ether_hdr *); + + te = vld1q_u32((uint32_t *)eth_hdr); + ve = vreinterpretq_u32_s32(val_eth[dst_port[0]]); + + + rfc1812_process((struct ipv4_hdr *)(eth_hdr + 1), dst_port, + pkt->packet_type); + + ve = vcopyq_laneq_u32(ve, 3, te, 3); + vst1q_u32((uint32_t *)eth_hdr, ve); +} + +/** + * Send packets burst from pkts_burst to the ports in dst_port array + */ +static __rte_always_inline void +send_packets_multi(struct lcore_conf *qconf, struct rte_mbuf **pkts_burst, + uint16_t dst_port[MAX_PKT_BURST], int nb_rx) +{ + int32_t k; + int j = 0; + uint16_t dlp; + uint16_t *lp; + uint16_t pnum[MAX_PKT_BURST + 1]; + + /* + * Finish packet processing and group consecutive + * packets with the same destination port. + */ + k = RTE_ALIGN_FLOOR(nb_rx, FWDSTEP); + if (k != 0) { + uint16x8_t dp1, dp2; + + lp = pnum; + lp[0] = 1; + + processx4_step3(pkts_burst, dst_port); + + /* dp1: <d[0], d[1], d[2], d[3], ... > */ + dp1 = vld1q_u16(dst_port); + + for (j = FWDSTEP; j != k; j += FWDSTEP) { + processx4_step3(&pkts_burst[j], &dst_port[j]); + + /* + * dp2: + * <d[j-3], d[j-2], d[j-1], d[j], ... > + */ + dp2 = vld1q_u16(&dst_port[j - FWDSTEP + 1]); + lp = port_groupx4(&pnum[j - FWDSTEP], lp, dp1, dp2); + + /* + * dp1: + * <d[j], d[j+1], d[j+2], d[j+3], ... > + */ + dp1 = vextq_u16(dp2, dp1, FWDSTEP - 1); + } + + /* + * dp2: <d[j-3], d[j-2], d[j-1], d[j-1], ... > + */ + dp2 = vextq_u16(dp1, dp1, 1); + dp2 = vsetq_lane_u16(vgetq_lane_u16(dp2, 2), dp2, 3); + lp = port_groupx4(&pnum[j - FWDSTEP], lp, dp1, dp2); + + /* + * remove values added by the last repeated + * dst port. + */ + lp[0]--; + dlp = dst_port[j - 1]; + } else { + /* set dlp and lp to the never used values. */ + dlp = BAD_PORT - 1; + lp = pnum + MAX_PKT_BURST; + } + + /* Process up to last 3 packets one by one. */ + switch (nb_rx % FWDSTEP) { + case 3: + process_packet(pkts_burst[j], dst_port + j); + GROUP_PORT_STEP(dlp, dst_port, lp, pnum, j); + j++; + /* fallthrough */ + case 2: + process_packet(pkts_burst[j], dst_port + j); + GROUP_PORT_STEP(dlp, dst_port, lp, pnum, j); + j++; + /* fallthrough */ + case 1: + process_packet(pkts_burst[j], dst_port + j); + GROUP_PORT_STEP(dlp, dst_port, lp, pnum, j); + j++; + } + + /* + * Send packets out, through destination port. + * Consecutive packets with the same destination port + * are already grouped together. + * If destination port for the packet equals BAD_PORT, + * then free the packet without sending it out. + */ + for (j = 0; j < nb_rx; j += k) { + + int32_t m; + uint16_t pn; + + pn = dst_port[j]; + k = pnum[j]; + + if (likely(pn != BAD_PORT)) + send_packetsx4(qconf, pn, pkts_burst + j, k); + else + for (m = j; m != j + k; m++) + rte_pktmbuf_free(pkts_burst[m]); + + } +} + +#endif /* _L3FWD_NEON_H_ */ diff --git a/src/seastar/dpdk/examples/l3fwd/l3fwd_sse.h b/src/seastar/dpdk/examples/l3fwd/l3fwd_sse.h new file mode 100644 index 000000000..ed5267c11 --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd/l3fwd_sse.h @@ -0,0 +1,227 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2016 Intel Corporation + */ + + +#ifndef _L3FWD_SSE_H_ +#define _L3FWD_SSE_H_ + +#include "l3fwd.h" +#include "l3fwd_common.h" + +/* + * Update source and destination MAC addresses in the ethernet header. + * Perform RFC1812 checks and updates for IPV4 packets. + */ +static inline void +processx4_step3(struct rte_mbuf *pkt[FWDSTEP], uint16_t dst_port[FWDSTEP]) +{ + __m128i te[FWDSTEP]; + __m128i ve[FWDSTEP]; + __m128i *p[FWDSTEP]; + + p[0] = rte_pktmbuf_mtod(pkt[0], __m128i *); + p[1] = rte_pktmbuf_mtod(pkt[1], __m128i *); + p[2] = rte_pktmbuf_mtod(pkt[2], __m128i *); + p[3] = rte_pktmbuf_mtod(pkt[3], __m128i *); + + ve[0] = val_eth[dst_port[0]]; + te[0] = _mm_loadu_si128(p[0]); + + ve[1] = val_eth[dst_port[1]]; + te[1] = _mm_loadu_si128(p[1]); + + ve[2] = val_eth[dst_port[2]]; + te[2] = _mm_loadu_si128(p[2]); + + ve[3] = val_eth[dst_port[3]]; + te[3] = _mm_loadu_si128(p[3]); + + /* Update first 12 bytes, keep rest bytes intact. */ + te[0] = _mm_blend_epi16(te[0], ve[0], MASK_ETH); + te[1] = _mm_blend_epi16(te[1], ve[1], MASK_ETH); + te[2] = _mm_blend_epi16(te[2], ve[2], MASK_ETH); + te[3] = _mm_blend_epi16(te[3], ve[3], MASK_ETH); + + _mm_storeu_si128(p[0], te[0]); + _mm_storeu_si128(p[1], te[1]); + _mm_storeu_si128(p[2], te[2]); + _mm_storeu_si128(p[3], te[3]); + + rfc1812_process((struct ipv4_hdr *)((struct ether_hdr *)p[0] + 1), + &dst_port[0], pkt[0]->packet_type); + rfc1812_process((struct ipv4_hdr *)((struct ether_hdr *)p[1] + 1), + &dst_port[1], pkt[1]->packet_type); + rfc1812_process((struct ipv4_hdr *)((struct ether_hdr *)p[2] + 1), + &dst_port[2], pkt[2]->packet_type); + rfc1812_process((struct ipv4_hdr *)((struct ether_hdr *)p[3] + 1), + &dst_port[3], pkt[3]->packet_type); +} + +/* + * Group consecutive packets with the same destination port in bursts of 4. + * Suppose we have array of destionation ports: + * dst_port[] = {a, b, c, d,, e, ... } + * dp1 should contain: <a, b, c, d>, dp2: <b, c, d, e>. + * We doing 4 comparisons at once and the result is 4 bit mask. + * This mask is used as an index into prebuild array of pnum values. + */ +static inline uint16_t * +port_groupx4(uint16_t pn[FWDSTEP + 1], uint16_t *lp, __m128i dp1, __m128i dp2) +{ + union { + uint16_t u16[FWDSTEP + 1]; + uint64_t u64; + } *pnum = (void *)pn; + + int32_t v; + + dp1 = _mm_cmpeq_epi16(dp1, dp2); + dp1 = _mm_unpacklo_epi16(dp1, dp1); + v = _mm_movemask_ps((__m128)dp1); + + /* update last port counter. */ + lp[0] += gptbl[v].lpv; + + /* if dest port value has changed. */ + if (v != GRPMSK) { + pnum->u64 = gptbl[v].pnum; + pnum->u16[FWDSTEP] = 1; + lp = pnum->u16 + gptbl[v].idx; + } + + return lp; +} + +/** + * Process one packet: + * Update source and destination MAC addresses in the ethernet header. + * Perform RFC1812 checks and updates for IPV4 packets. + */ +static inline void +process_packet(struct rte_mbuf *pkt, uint16_t *dst_port) +{ + struct ether_hdr *eth_hdr; + __m128i te, ve; + + eth_hdr = rte_pktmbuf_mtod(pkt, struct ether_hdr *); + + te = _mm_loadu_si128((__m128i *)eth_hdr); + ve = val_eth[dst_port[0]]; + + rfc1812_process((struct ipv4_hdr *)(eth_hdr + 1), dst_port, + pkt->packet_type); + + te = _mm_blend_epi16(te, ve, MASK_ETH); + _mm_storeu_si128((__m128i *)eth_hdr, te); +} + +/** + * Send packets burst from pkts_burst to the ports in dst_port array + */ +static __rte_always_inline void +send_packets_multi(struct lcore_conf *qconf, struct rte_mbuf **pkts_burst, + uint16_t dst_port[MAX_PKT_BURST], int nb_rx) +{ + int32_t k; + int j = 0; + uint16_t dlp; + uint16_t *lp; + uint16_t pnum[MAX_PKT_BURST + 1]; + + /* + * Finish packet processing and group consecutive + * packets with the same destination port. + */ + k = RTE_ALIGN_FLOOR(nb_rx, FWDSTEP); + if (k != 0) { + __m128i dp1, dp2; + + lp = pnum; + lp[0] = 1; + + processx4_step3(pkts_burst, dst_port); + + /* dp1: <d[0], d[1], d[2], d[3], ... > */ + dp1 = _mm_loadu_si128((__m128i *)dst_port); + + for (j = FWDSTEP; j != k; j += FWDSTEP) { + processx4_step3(&pkts_burst[j], &dst_port[j]); + + /* + * dp2: + * <d[j-3], d[j-2], d[j-1], d[j], ... > + */ + dp2 = _mm_loadu_si128((__m128i *) + &dst_port[j - FWDSTEP + 1]); + lp = port_groupx4(&pnum[j - FWDSTEP], lp, dp1, dp2); + + /* + * dp1: + * <d[j], d[j+1], d[j+2], d[j+3], ... > + */ + dp1 = _mm_srli_si128(dp2, (FWDSTEP - 1) * + sizeof(dst_port[0])); + } + + /* + * dp2: <d[j-3], d[j-2], d[j-1], d[j-1], ... > + */ + dp2 = _mm_shufflelo_epi16(dp1, 0xf9); + lp = port_groupx4(&pnum[j - FWDSTEP], lp, dp1, dp2); + + /* + * remove values added by the last repeated + * dst port. + */ + lp[0]--; + dlp = dst_port[j - 1]; + } else { + /* set dlp and lp to the never used values. */ + dlp = BAD_PORT - 1; + lp = pnum + MAX_PKT_BURST; + } + + /* Process up to last 3 packets one by one. */ + switch (nb_rx % FWDSTEP) { + case 3: + process_packet(pkts_burst[j], dst_port + j); + GROUP_PORT_STEP(dlp, dst_port, lp, pnum, j); + j++; + /* fall-through */ + case 2: + process_packet(pkts_burst[j], dst_port + j); + GROUP_PORT_STEP(dlp, dst_port, lp, pnum, j); + j++; + /* fall-through */ + case 1: + process_packet(pkts_burst[j], dst_port + j); + GROUP_PORT_STEP(dlp, dst_port, lp, pnum, j); + j++; + } + + /* + * Send packets out, through destination port. + * Consecutive packets with the same destination port + * are already grouped together. + * If destination port for the packet equals BAD_PORT, + * then free the packet without sending it out. + */ + for (j = 0; j < nb_rx; j += k) { + + int32_t m; + uint16_t pn; + + pn = dst_port[j]; + k = pnum[j]; + + if (likely(pn != BAD_PORT)) + send_packetsx4(qconf, pn, pkts_burst + j, k); + else + for (m = j; m != j + k; m++) + rte_pktmbuf_free(pkts_burst[m]); + + } +} + +#endif /* _L3FWD_SSE_H_ */ diff --git a/src/seastar/dpdk/examples/l3fwd/main.c b/src/seastar/dpdk/examples/l3fwd/main.c new file mode 100644 index 000000000..7b9683187 --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd/main.c @@ -0,0 +1,1075 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2010-2016 Intel Corporation + */ + +#include <stdio.h> +#include <stdlib.h> +#include <stdint.h> +#include <inttypes.h> +#include <sys/types.h> +#include <string.h> +#include <sys/queue.h> +#include <stdarg.h> +#include <errno.h> +#include <getopt.h> +#include <signal.h> +#include <stdbool.h> + +#include <rte_common.h> +#include <rte_vect.h> +#include <rte_byteorder.h> +#include <rte_log.h> +#include <rte_memory.h> +#include <rte_memcpy.h> +#include <rte_eal.h> +#include <rte_launch.h> +#include <rte_atomic.h> +#include <rte_cycles.h> +#include <rte_prefetch.h> +#include <rte_lcore.h> +#include <rte_per_lcore.h> +#include <rte_branch_prediction.h> +#include <rte_interrupts.h> +#include <rte_random.h> +#include <rte_debug.h> +#include <rte_ether.h> +#include <rte_ethdev.h> +#include <rte_mempool.h> +#include <rte_mbuf.h> +#include <rte_ip.h> +#include <rte_tcp.h> +#include <rte_udp.h> +#include <rte_string_fns.h> +#include <rte_cpuflags.h> + +#include <cmdline_parse.h> +#include <cmdline_parse_etheraddr.h> + +#include "l3fwd.h" + +/* + * Configurable number of RX/TX ring descriptors + */ +#define RTE_TEST_RX_DESC_DEFAULT 1024 +#define RTE_TEST_TX_DESC_DEFAULT 1024 + +#define MAX_TX_QUEUE_PER_PORT RTE_MAX_ETHPORTS +#define MAX_RX_QUEUE_PER_PORT 128 + +#define MAX_LCORE_PARAMS 1024 + +/* Static global variables used within this file. */ +static uint16_t nb_rxd = RTE_TEST_RX_DESC_DEFAULT; +static uint16_t nb_txd = RTE_TEST_TX_DESC_DEFAULT; + +/**< Ports set in promiscuous mode off by default. */ +static int promiscuous_on; + +/* Select Longest-Prefix or Exact match. */ +static int l3fwd_lpm_on; +static int l3fwd_em_on; + +/* Global variables. */ + +static int numa_on = 1; /**< NUMA is enabled by default. */ +static int parse_ptype; /**< Parse packet type using rx callback, and */ + /**< disabled by default */ +static int per_port_pool; /**< Use separate buffer pools per port; disabled */ + /**< by default */ + +volatile bool force_quit; + +/* ethernet addresses of ports */ +uint64_t dest_eth_addr[RTE_MAX_ETHPORTS]; +struct ether_addr ports_eth_addr[RTE_MAX_ETHPORTS]; + +xmm_t val_eth[RTE_MAX_ETHPORTS]; + +/* mask of enabled ports */ +uint32_t enabled_port_mask; + +/* Used only in exact match mode. */ +int ipv6; /**< ipv6 is false by default. */ +uint32_t hash_entry_number = HASH_ENTRY_NUMBER_DEFAULT; + +struct lcore_conf lcore_conf[RTE_MAX_LCORE]; + +struct lcore_params { + uint16_t port_id; + uint8_t queue_id; + uint8_t lcore_id; +} __rte_cache_aligned; + +static struct lcore_params lcore_params_array[MAX_LCORE_PARAMS]; +static struct lcore_params lcore_params_array_default[] = { + {0, 0, 2}, + {0, 1, 2}, + {0, 2, 2}, + {1, 0, 2}, + {1, 1, 2}, + {1, 2, 2}, + {2, 0, 2}, + {3, 0, 3}, + {3, 1, 3}, +}; + +static struct lcore_params * lcore_params = lcore_params_array_default; +static 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, + .split_hdr_size = 0, + .offloads = DEV_RX_OFFLOAD_CHECKSUM, + }, + .rx_adv_conf = { + .rss_conf = { + .rss_key = NULL, + .rss_hf = ETH_RSS_IP, + }, + }, + .txmode = { + .mq_mode = ETH_MQ_TX_NONE, + }, +}; + +static struct rte_mempool *pktmbuf_pool[RTE_MAX_ETHPORTS][NB_SOCKETS]; +static uint8_t lkp_per_socket[NB_SOCKETS]; + +struct l3fwd_lkp_mode { + void (*setup)(int); + int (*check_ptype)(int); + rte_rx_callback_fn cb_parse_ptype; + int (*main_loop)(void *); + void* (*get_ipv4_lookup_struct)(int); + void* (*get_ipv6_lookup_struct)(int); +}; + +static struct l3fwd_lkp_mode l3fwd_lkp; + +static struct l3fwd_lkp_mode l3fwd_em_lkp = { + .setup = setup_hash, + .check_ptype = em_check_ptype, + .cb_parse_ptype = em_cb_parse_ptype, + .main_loop = em_main_loop, + .get_ipv4_lookup_struct = em_get_ipv4_l3fwd_lookup_struct, + .get_ipv6_lookup_struct = em_get_ipv6_l3fwd_lookup_struct, +}; + +static struct l3fwd_lkp_mode l3fwd_lpm_lkp = { + .setup = setup_lpm, + .check_ptype = lpm_check_ptype, + .cb_parse_ptype = lpm_cb_parse_ptype, + .main_loop = lpm_main_loop, + .get_ipv4_lookup_struct = lpm_get_ipv4_l3fwd_lookup_struct, + .get_ipv6_lookup_struct = lpm_get_ipv6_l3fwd_lookup_struct, +}; + +/* + * Setup lookup methods for forwarding. + * Currently exact-match and longest-prefix-match + * are supported ones. + */ +static void +setup_l3fwd_lookup_tables(void) +{ + /* Setup HASH lookup functions. */ + if (l3fwd_em_on) + l3fwd_lkp = l3fwd_em_lkp; + /* Setup LPM lookup functions. */ + else + l3fwd_lkp = l3fwd_lpm_lkp; +} + +static int +check_lcore_params(void) +{ + uint8_t queue, lcore; + uint16_t i; + int socketid; + + for (i = 0; i < nb_lcore_params; ++i) { + queue = lcore_params[i].queue_id; + if (queue >= MAX_RX_QUEUE_PER_PORT) { + printf("invalid queue number: %hhu\n", queue); + return -1; + } + lcore = lcore_params[i].lcore_id; + if (!rte_lcore_is_enabled(lcore)) { + printf("error: lcore %hhu is not enabled in lcore mask\n", lcore); + return -1; + } + if ((socketid = rte_lcore_to_socket_id(lcore) != 0) && + (numa_on == 0)) { + printf("warning: lcore %hhu is on socket %d with numa off \n", + lcore, socketid); + } + } + return 0; +} + +static int +check_port_config(void) +{ + uint16_t portid; + uint16_t i; + + for (i = 0; i < nb_lcore_params; ++i) { + portid = lcore_params[i].port_id; + if ((enabled_port_mask & (1 << portid)) == 0) { + printf("port %u is not enabled in port mask\n", portid); + return -1; + } + if (!rte_eth_dev_is_valid_port(portid)) { + printf("port %u is not present on the board\n", portid); + return -1; + } + } + return 0; +} + +static uint8_t +get_port_n_rx_queues(const uint16_t port) +{ + int queue = -1; + uint16_t i; + + for (i = 0; i < nb_lcore_params; ++i) { + if (lcore_params[i].port_id == port) { + if (lcore_params[i].queue_id == queue+1) + queue = lcore_params[i].queue_id; + else + rte_exit(EXIT_FAILURE, "queue ids of the port %d must be" + " in sequence and must start with 0\n", + lcore_params[i].port_id); + } + } + return (uint8_t)(++queue); +} + +static int +init_lcore_rx_queues(void) +{ + uint16_t i, nb_rx_queue; + uint8_t lcore; + + for (i = 0; i < nb_lcore_params; ++i) { + lcore = lcore_params[i].lcore_id; + nb_rx_queue = lcore_conf[lcore].n_rx_queue; + if (nb_rx_queue >= MAX_RX_QUEUE_PER_LCORE) { + printf("error: too many queues (%u) for lcore: %u\n", + (unsigned)nb_rx_queue + 1, (unsigned)lcore); + return -1; + } else { + lcore_conf[lcore].rx_queue_list[nb_rx_queue].port_id = + lcore_params[i].port_id; + lcore_conf[lcore].rx_queue_list[nb_rx_queue].queue_id = + lcore_params[i].queue_id; + lcore_conf[lcore].n_rx_queue++; + } + } + return 0; +} + +/* display usage */ +static void +print_usage(const char *prgname) +{ + fprintf(stderr, "%s [EAL options] --" + " -p PORTMASK" + " [-P]" + " [-E]" + " [-L]" + " --config (port,queue,lcore)[,(port,queue,lcore)]" + " [--eth-dest=X,MM:MM:MM:MM:MM:MM]" + " [--enable-jumbo [--max-pkt-len PKTLEN]]" + " [--no-numa]" + " [--hash-entry-num]" + " [--ipv6]" + " [--parse-ptype]" + " [--per-port-pool]\n\n" + + " -p PORTMASK: Hexadecimal bitmask of ports to configure\n" + " -P : Enable promiscuous mode\n" + " -E : Enable exact match\n" + " -L : Enable longest prefix match (default)\n" + " --config (port,queue,lcore): Rx queue configuration\n" + " --eth-dest=X,MM:MM:MM:MM:MM:MM: Ethernet destination for port X\n" + " --enable-jumbo: Enable jumbo frames\n" + " --max-pkt-len: Under the premise of enabling jumbo,\n" + " maximum packet length in decimal (64-9600)\n" + " --no-numa: Disable numa awareness\n" + " --hash-entry-num: Specify the hash entry number in hexadecimal to be setup\n" + " --ipv6: Set if running ipv6 packets\n" + " --parse-ptype: Set to use software to analyze packet type\n" + " --per-port-pool: Use separate buffer pool per port\n\n", + prgname); +} + +static int +parse_max_pkt_len(const char *pktlen) +{ + char *end = NULL; + unsigned long len; + + /* parse decimal string */ + len = strtoul(pktlen, &end, 10); + if ((pktlen[0] == '\0') || (end == NULL) || (*end != '\0')) + return -1; + + if (len == 0) + return -1; + + return len; +} + +static int +parse_portmask(const char *portmask) +{ + char *end = NULL; + unsigned long pm; + + /* parse hexadecimal string */ + pm = strtoul(portmask, &end, 16); + if ((portmask[0] == '\0') || (end == NULL) || (*end != '\0')) + return -1; + + if (pm == 0) + return -1; + + return pm; +} + +static int +parse_hash_entry_number(const char *hash_entry_num) +{ + char *end = NULL; + unsigned long hash_en; + /* parse hexadecimal string */ + hash_en = strtoul(hash_entry_num, &end, 16); + if ((hash_entry_num[0] == '\0') || (end == NULL) || (*end != '\0')) + return -1; + + if (hash_en == 0) + return -1; + + return hash_en; +} + +static int +parse_config(const char *q_arg) +{ + char s[256]; + const char *p, *p0 = q_arg; + char *end; + enum fieldnames { + FLD_PORT = 0, + FLD_QUEUE, + FLD_LCORE, + _NUM_FLD + }; + unsigned long int_fld[_NUM_FLD]; + char *str_fld[_NUM_FLD]; + int i; + unsigned size; + + nb_lcore_params = 0; + + while ((p = strchr(p0,'(')) != NULL) { + ++p; + if((p0 = strchr(p,')')) == NULL) + return -1; + + size = p0 - p; + if(size >= sizeof(s)) + return -1; + + snprintf(s, sizeof(s), "%.*s", size, p); + if (rte_strsplit(s, sizeof(s), str_fld, _NUM_FLD, ',') != _NUM_FLD) + return -1; + for (i = 0; i < _NUM_FLD; i++){ + errno = 0; + int_fld[i] = strtoul(str_fld[i], &end, 0); + if (errno != 0 || end == str_fld[i] || int_fld[i] > 255) + return -1; + } + if (nb_lcore_params >= MAX_LCORE_PARAMS) { + printf("exceeded max number of lcore params: %hu\n", + nb_lcore_params); + return -1; + } + lcore_params_array[nb_lcore_params].port_id = + (uint8_t)int_fld[FLD_PORT]; + lcore_params_array[nb_lcore_params].queue_id = + (uint8_t)int_fld[FLD_QUEUE]; + lcore_params_array[nb_lcore_params].lcore_id = + (uint8_t)int_fld[FLD_LCORE]; + ++nb_lcore_params; + } + lcore_params = lcore_params_array; + return 0; +} + +static void +parse_eth_dest(const char *optarg) +{ + uint16_t portid; + char *port_end; + uint8_t c, *dest, peer_addr[6]; + + errno = 0; + portid = strtoul(optarg, &port_end, 10); + if (errno != 0 || port_end == optarg || *port_end++ != ',') + rte_exit(EXIT_FAILURE, + "Invalid eth-dest: %s", optarg); + if (portid >= RTE_MAX_ETHPORTS) + rte_exit(EXIT_FAILURE, + "eth-dest: port %d >= RTE_MAX_ETHPORTS(%d)\n", + portid, RTE_MAX_ETHPORTS); + + if (cmdline_parse_etheraddr(NULL, port_end, + &peer_addr, sizeof(peer_addr)) < 0) + rte_exit(EXIT_FAILURE, + "Invalid ethernet address: %s\n", + port_end); + dest = (uint8_t *)&dest_eth_addr[portid]; + for (c = 0; c < 6; c++) + dest[c] = peer_addr[c]; + *(uint64_t *)(val_eth + portid) = dest_eth_addr[portid]; +} + +#define MAX_JUMBO_PKT_LEN 9600 +#define MEMPOOL_CACHE_SIZE 256 + +static const char short_options[] = + "p:" /* portmask */ + "P" /* promiscuous */ + "L" /* enable long prefix match */ + "E" /* enable exact match */ + ; + +#define CMD_LINE_OPT_CONFIG "config" +#define CMD_LINE_OPT_ETH_DEST "eth-dest" +#define CMD_LINE_OPT_NO_NUMA "no-numa" +#define CMD_LINE_OPT_IPV6 "ipv6" +#define CMD_LINE_OPT_ENABLE_JUMBO "enable-jumbo" +#define CMD_LINE_OPT_HASH_ENTRY_NUM "hash-entry-num" +#define CMD_LINE_OPT_PARSE_PTYPE "parse-ptype" +#define CMD_LINE_OPT_PER_PORT_POOL "per-port-pool" +enum { + /* long options mapped to a short option */ + + /* first long only option value must be >= 256, so that we won't + * conflict with short options */ + CMD_LINE_OPT_MIN_NUM = 256, + CMD_LINE_OPT_CONFIG_NUM, + CMD_LINE_OPT_ETH_DEST_NUM, + CMD_LINE_OPT_NO_NUMA_NUM, + CMD_LINE_OPT_IPV6_NUM, + CMD_LINE_OPT_ENABLE_JUMBO_NUM, + CMD_LINE_OPT_HASH_ENTRY_NUM_NUM, + CMD_LINE_OPT_PARSE_PTYPE_NUM, + CMD_LINE_OPT_PARSE_PER_PORT_POOL, +}; + +static const struct option lgopts[] = { + {CMD_LINE_OPT_CONFIG, 1, 0, CMD_LINE_OPT_CONFIG_NUM}, + {CMD_LINE_OPT_ETH_DEST, 1, 0, CMD_LINE_OPT_ETH_DEST_NUM}, + {CMD_LINE_OPT_NO_NUMA, 0, 0, CMD_LINE_OPT_NO_NUMA_NUM}, + {CMD_LINE_OPT_IPV6, 0, 0, CMD_LINE_OPT_IPV6_NUM}, + {CMD_LINE_OPT_ENABLE_JUMBO, 0, 0, CMD_LINE_OPT_ENABLE_JUMBO_NUM}, + {CMD_LINE_OPT_HASH_ENTRY_NUM, 1, 0, CMD_LINE_OPT_HASH_ENTRY_NUM_NUM}, + {CMD_LINE_OPT_PARSE_PTYPE, 0, 0, CMD_LINE_OPT_PARSE_PTYPE_NUM}, + {CMD_LINE_OPT_PER_PORT_POOL, 0, 0, CMD_LINE_OPT_PARSE_PER_PORT_POOL}, + {NULL, 0, 0, 0} +}; + +/* + * 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 per lcore and mtable per port per lcore. + * RTE_MAX is used to ensure that NB_MBUF never goes below a minimum + * value of 8192 + */ +#define NB_MBUF(nports) RTE_MAX( \ + (nports*nb_rx_queue*nb_rxd + \ + nports*nb_lcores*MAX_PKT_BURST + \ + nports*n_tx_queue*nb_txd + \ + nb_lcores*MEMPOOL_CACHE_SIZE), \ + (unsigned)8192) + +/* Parse the argument given in the command line of the application */ +static int +parse_args(int argc, char **argv) +{ + int opt, ret; + char **argvopt; + int option_index; + char *prgname = argv[0]; + + argvopt = argv; + + /* Error or normal output strings. */ + while ((opt = getopt_long(argc, argvopt, short_options, + lgopts, &option_index)) != EOF) { + + switch (opt) { + /* portmask */ + case 'p': + enabled_port_mask = parse_portmask(optarg); + if (enabled_port_mask == 0) { + fprintf(stderr, "Invalid portmask\n"); + print_usage(prgname); + return -1; + } + break; + + case 'P': + promiscuous_on = 1; + break; + + case 'E': + l3fwd_em_on = 1; + break; + + case 'L': + l3fwd_lpm_on = 1; + break; + + /* long options */ + case CMD_LINE_OPT_CONFIG_NUM: + ret = parse_config(optarg); + if (ret) { + fprintf(stderr, "Invalid config\n"); + print_usage(prgname); + return -1; + } + break; + + case CMD_LINE_OPT_ETH_DEST_NUM: + parse_eth_dest(optarg); + break; + + case CMD_LINE_OPT_NO_NUMA_NUM: + numa_on = 0; + break; + + case CMD_LINE_OPT_IPV6_NUM: + ipv6 = 1; + break; + + case CMD_LINE_OPT_ENABLE_JUMBO_NUM: { + const struct option lenopts = { + "max-pkt-len", required_argument, 0, 0 + }; + + 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. + */ + if (getopt_long(argc, argvopt, "", + &lenopts, &option_index) == 0) { + ret = parse_max_pkt_len(optarg); + if (ret < 64 || ret > MAX_JUMBO_PKT_LEN) { + fprintf(stderr, + "invalid maximum packet length\n"); + print_usage(prgname); + return -1; + } + port_conf.rxmode.max_rx_pkt_len = ret; + } + break; + } + + case CMD_LINE_OPT_HASH_ENTRY_NUM_NUM: + ret = parse_hash_entry_number(optarg); + if ((ret > 0) && (ret <= L3FWD_HASH_ENTRIES)) { + hash_entry_number = ret; + } else { + fprintf(stderr, "invalid hash entry number\n"); + print_usage(prgname); + return -1; + } + break; + + case CMD_LINE_OPT_PARSE_PTYPE_NUM: + printf("soft parse-ptype is enabled\n"); + parse_ptype = 1; + break; + + case CMD_LINE_OPT_PARSE_PER_PORT_POOL: + printf("per port buffer pool is enabled\n"); + per_port_pool = 1; + break; + + default: + print_usage(prgname); + return -1; + } + } + + /* If both LPM and EM are selected, return error. */ + if (l3fwd_lpm_on && l3fwd_em_on) { + fprintf(stderr, "LPM and EM are mutually exclusive, select only one\n"); + return -1; + } + + /* + * Nothing is selected, pick longest-prefix match + * as default match. + */ + if (!l3fwd_lpm_on && !l3fwd_em_on) { + fprintf(stderr, "LPM or EM none selected, default LPM on\n"); + l3fwd_lpm_on = 1; + } + + /* + * ipv6 and hash flags are valid only for + * exact macth, reset them to default for + * longest-prefix match. + */ + if (l3fwd_lpm_on) { + ipv6 = 0; + hash_entry_number = HASH_ENTRY_NUMBER_DEFAULT; + } + + if (optind >= 0) + argv[optind-1] = prgname; + + ret = optind-1; + optind = 1; /* reset getopt lib */ + return ret; +} + +static void +print_ethaddr(const char *name, const struct ether_addr *eth_addr) +{ + char buf[ETHER_ADDR_FMT_SIZE]; + ether_format_addr(buf, ETHER_ADDR_FMT_SIZE, eth_addr); + printf("%s%s", name, buf); +} + +static int +init_mem(uint16_t portid, unsigned int nb_mbuf) +{ + struct lcore_conf *qconf; + int socketid; + unsigned lcore_id; + char s[64]; + + for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) { + if (rte_lcore_is_enabled(lcore_id) == 0) + continue; + + if (numa_on) + socketid = rte_lcore_to_socket_id(lcore_id); + else + socketid = 0; + + if (socketid >= NB_SOCKETS) { + rte_exit(EXIT_FAILURE, + "Socket %d of lcore %u is out of range %d\n", + socketid, lcore_id, NB_SOCKETS); + } + + if (pktmbuf_pool[portid][socketid] == NULL) { + snprintf(s, sizeof(s), "mbuf_pool_%d:%d", + portid, socketid); + pktmbuf_pool[portid][socketid] = + rte_pktmbuf_pool_create(s, nb_mbuf, + MEMPOOL_CACHE_SIZE, 0, + RTE_MBUF_DEFAULT_BUF_SIZE, socketid); + if (pktmbuf_pool[portid][socketid] == NULL) + rte_exit(EXIT_FAILURE, + "Cannot init mbuf pool on socket %d\n", + socketid); + else + printf("Allocated mbuf pool on socket %d\n", + socketid); + + /* Setup either LPM or EM(f.e Hash). But, only once per + * available socket. + */ + if (!lkp_per_socket[socketid]) { + l3fwd_lkp.setup(socketid); + lkp_per_socket[socketid] = 1; + } + } + qconf = &lcore_conf[lcore_id]; + qconf->ipv4_lookup_struct = + l3fwd_lkp.get_ipv4_lookup_struct(socketid); + qconf->ipv6_lookup_struct = + l3fwd_lkp.get_ipv6_lookup_struct(socketid); + } + return 0; +} + +/* Check the link status of all ports in up to 9s, and print them finally */ +static void +check_all_ports_link_status(uint32_t port_mask) +{ +#define CHECK_INTERVAL 100 /* 100ms */ +#define MAX_CHECK_TIME 90 /* 9s (90 * 100ms) in total */ + uint16_t portid; + uint8_t count, all_ports_up, print_flag = 0; + struct rte_eth_link link; + + printf("\nChecking link status"); + fflush(stdout); + for (count = 0; count <= MAX_CHECK_TIME; count++) { + if (force_quit) + return; + all_ports_up = 1; + RTE_ETH_FOREACH_DEV(portid) { + if (force_quit) + return; + if ((port_mask & (1 << portid)) == 0) + continue; + memset(&link, 0, sizeof(link)); + rte_eth_link_get_nowait(portid, &link); + /* 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); + continue; + } + /* clear all_ports_up flag if any link down */ + if (link.link_status == ETH_LINK_DOWN) { + all_ports_up = 0; + break; + } + } + /* after finally printing all link status, get out */ + if (print_flag == 1) + break; + + if (all_ports_up == 0) { + printf("."); + fflush(stdout); + rte_delay_ms(CHECK_INTERVAL); + } + + /* set the print_flag if all ports up or timeout */ + if (all_ports_up == 1 || count == (MAX_CHECK_TIME - 1)) { + print_flag = 1; + printf("done\n"); + } + } +} + +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 int +prepare_ptype_parser(uint16_t portid, uint16_t queueid) +{ + if (parse_ptype) { + printf("Port %d: softly parse packet type info\n", portid); + if (rte_eth_add_rx_callback(portid, queueid, + l3fwd_lkp.cb_parse_ptype, + NULL)) + return 1; + + printf("Failed to add rx callback: port=%d\n", portid); + return 0; + } + + if (l3fwd_lkp.check_ptype(portid)) + return 1; + + printf("port %d cannot parse packet type, please add --%s\n", + portid, CMD_LINE_OPT_PARSE_PTYPE); + return 0; +} + +int +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 queueid, portid; + unsigned lcore_id; + uint32_t n_tx_queue, nb_lcores; + uint8_t nb_rx_queue, queue, socketid; + + /* init EAL */ + ret = rte_eal_init(argc, argv); + if (ret < 0) + rte_exit(EXIT_FAILURE, "Invalid EAL parameters\n"); + argc -= ret; + argv += ret; + + force_quit = false; + signal(SIGINT, signal_handler); + signal(SIGTERM, signal_handler); + + /* pre-init dst MACs for all ports to 02:00:00:00:00:xx */ + for (portid = 0; portid < RTE_MAX_ETHPORTS; portid++) { + dest_eth_addr[portid] = + ETHER_LOCAL_ADMIN_ADDR + ((uint64_t)portid << 40); + *(uint64_t *)(val_eth + portid) = dest_eth_addr[portid]; + } + + /* parse application arguments (after the EAL ones) */ + ret = parse_args(argc, argv); + if (ret < 0) + rte_exit(EXIT_FAILURE, "Invalid L3FWD parameters\n"); + + if (check_lcore_params() < 0) + rte_exit(EXIT_FAILURE, "check_lcore_params failed\n"); + + ret = init_lcore_rx_queues(); + if (ret < 0) + rte_exit(EXIT_FAILURE, "init_lcore_rx_queues failed\n"); + + nb_ports = rte_eth_dev_count_avail(); + + if (check_port_config() < 0) + rte_exit(EXIT_FAILURE, "check_port_config failed\n"); + + nb_lcores = rte_lcore_count(); + + /* Setup function pointers for lookup method. */ + setup_l3fwd_lookup_tables(); + + /* initialize all ports */ + 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); + continue; + } + + /* init port */ + printf("Initializing port %d ... ", portid ); + fflush(stdout); + + nb_rx_queue = get_port_n_rx_queues(portid); + n_tx_queue = nb_lcores; + if (n_tx_queue > MAX_TX_QUEUE_PER_PORT) + n_tx_queue = MAX_TX_QUEUE_PER_PORT; + printf("Creating queues: nb_rxq=%d nb_txq=%u... ", + nb_rx_queue, (unsigned)n_tx_queue ); + + 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, &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(", "); + print_ethaddr("Destination:", + (const struct ether_addr *)&dest_eth_addr[portid]); + printf(", "); + + /* + * prepare src MACs for each port. + */ + ether_addr_copy(&ports_eth_addr[portid], + (struct ether_addr *)(val_eth + portid) + 1); + + /* init memory */ + if (!per_port_pool) { + /* portid = 0; this is *not* signifying the first port, + * rather, it signifies that portid is ignored. + */ + ret = init_mem(0, NB_MBUF(nb_ports)); + } else { + ret = init_mem(portid, NB_MBUF(1)); + } + if (ret < 0) + rte_exit(EXIT_FAILURE, "init_mem failed\n"); + + /* 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 (numa_on) + socketid = + (uint8_t)rte_lcore_to_socket_id(lcore_id); + else + socketid = 0; + + printf("txq=%u,%d,%d ", lcore_id, queueid, socketid); + fflush(stdout); + + txconf = &dev_info.default_txconf; + txconf->offloads = local_port_conf.txmode.offloads; + ret = rte_eth_tx_queue_setup(portid, queueid, nb_txd, + socketid, txconf); + if (ret < 0) + rte_exit(EXIT_FAILURE, + "rte_eth_tx_queue_setup: err=%d, " + "port=%d\n", ret, portid); + + 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"); + } + + for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) { + if (rte_lcore_is_enabled(lcore_id) == 0) + continue; + 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_dev *dev; + struct rte_eth_conf *conf; + struct rte_eth_rxconf rxq_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 = + (uint8_t)rte_lcore_to_socket_id(lcore_id); + else + socketid = 0; + + 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; + if (!per_port_pool) + ret = rte_eth_rx_queue_setup(portid, queueid, + nb_rxd, socketid, + &rxq_conf, + pktmbuf_pool[0][socketid]); + else + ret = rte_eth_rx_queue_setup(portid, queueid, + nb_rxd, socketid, + &rxq_conf, + pktmbuf_pool[portid][socketid]); + if (ret < 0) + rte_exit(EXIT_FAILURE, + "rte_eth_rx_queue_setup: err=%d, port=%d\n", + ret, portid); + } + } + + printf("\n"); + + /* start ports */ + RTE_ETH_FOREACH_DEV(portid) { + if ((enabled_port_mask & (1 << portid)) == 0) { + continue; + } + /* Start device */ + ret = rte_eth_dev_start(portid); + 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 + * to itself through 2 cross-connected ports of the + * target machine. + */ + if (promiscuous_on) + rte_eth_promiscuous_enable(portid); + } + + printf("\n"); + + for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) { + if (rte_lcore_is_enabled(lcore_id) == 0) + continue; + qconf = &lcore_conf[lcore_id]; + for (queue = 0; queue < qconf->n_rx_queue; ++queue) { + portid = qconf->rx_queue_list[queue].port_id; + queueid = qconf->rx_queue_list[queue].queue_id; + if (prepare_ptype_parser(portid, queueid) == 0) + rte_exit(EXIT_FAILURE, "ptype check fails\n"); + } + } + + + check_all_ports_link_status(enabled_port_mask); + + ret = 0; + /* launch per-lcore init on every lcore */ + rte_eal_mp_remote_launch(l3fwd_lkp.main_loop, NULL, CALL_MASTER); + RTE_LCORE_FOREACH_SLAVE(lcore_id) { + if (rte_eal_wait_lcore(lcore_id) < 0) { + ret = -1; + break; + } + } + + /* stop ports */ + RTE_ETH_FOREACH_DEV(portid) { + if ((enabled_port_mask & (1 << portid)) == 0) + continue; + printf("Closing port %d...", portid); + rte_eth_dev_stop(portid); + rte_eth_dev_close(portid); + printf(" Done\n"); + } + printf("Bye...\n"); + + return ret; +} diff --git a/src/seastar/dpdk/examples/l3fwd/meson.build b/src/seastar/dpdk/examples/l3fwd/meson.build new file mode 100644 index 000000000..6dd4b9022 --- /dev/null +++ b/src/seastar/dpdk/examples/l3fwd/meson.build @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2017 Intel Corporation + +# meson file, for building this example as part of a main DPDK build. +# +# To build this example as a standalone application with an already-installed +# DPDK instance, use 'make' + +deps += ['hash', 'lpm'] +sources = files( + 'l3fwd_em.c', 'l3fwd_lpm.c', 'main.c' +) |