dpdk 响应icmp请求(Echo or Echo Reply Message)

注：对于"Echo or Echo Reply Message"类型的icmp报文，响应报文的Identiy和Sequence Number的值与请求报文的这两个字段的值要相同。

Identifier（标识符）字段通常由发送方设置，并被用于将ICMP请求与相应的回复相关联。当发送ICMP请求时，发送方会将一个特定的值放入Identifier字段中，在收到对应的回复时可以通过该值进行匹配。

Sequence Number（序列号）字段用于按顺序编号ICMP请求或回复报文。它起到了帮助接收方正确排序和处理报文的作用。

#include <rte_eal.h>
#include <rte_ethdev.h>
#include <rte_mbuf.h>
#include <stdio.h>
#include <arpa/inet.h>


#define NUM_MBUFS (4096-1) // 内存池中 mbuf 的数量
#define BURST_SIZE 32
#define MAKE_IPV4_ADDR(a, b, c, d) (a + (b<<8) + (c<<16) + (d<<24))

static uint32_t gLocalIp = MAKE_IPV4_ADDR(192, 168, 1, 5);//当前ip，网络字节序

static uint8_t gSrcMac[RTE_ETHER_ADDR_LEN];

int gDpdkPortId = 0;

static const struct rte_eth_conf port_conf_default = {
	.rxmode = {.max_rx_pkt_len = RTE_ETHER_MAX_LEN}
};

static void ng_init_port(struct rte_mempool *mbuf_pool) {
	//dpdk绑定的网卡数量
	uint16_t nb_sys_ports = rte_eth_dev_count_avail();
	if (nb_sys_ports == 0) {
		rte_exit(EXIT_FAILURE, "not support eth\n");
	}

	struct rte_eth_dev_info dev_info;
	/*获取以太网设备的配置和状态信息。它通常用于初始化网络设备、
	 *配置网络设备或者获取网络设备的状态信息。
	 *这里的端口号和网卡是一一对应的
	 */
	rte_eth_dev_info_get(gDpdkPortId, &dev_info);

	const int num_rx_queues = 1;	//接收队列个数
	const int num_tx_queues = 1;	//发送队列个数
	struct rte_eth_conf port_conf = port_conf_default;
	
	rte_eth_dev_configure(gDpdkPortId, num_rx_queues, num_tx_queues, &port_conf);
	// 0是0号接收队列
	// 128是队列长度
	if (rte_eth_rx_queue_setup(gDpdkPortId, 0, 128, rte_eth_dev_socket_id(gDpdkPortId), NULL, mbuf_pool) < 0) {
		rte_exit(EXIT_FAILURE, "Could not setup RX queue\n");
	}

	struct rte_eth_txconf txq_conf = dev_info.default_txconf;
	//offloads 成员是一个 64 位无符号整数，每个比特位表示不同的接收功能选项
	txq_conf.offloads = port_conf.rxmode.offloads;
	/* 0是0号发送队列 
	 * 1024是队列长度
	 * 发送队列长度设置太小运行时会报错:Invalid value for nb_tx_desc(=128), should be: <= 4096, >= 512, and a product of 1
	 */
	if (rte_eth_tx_queue_setup(gDpdkPortId, 0, 1024, rte_eth_dev_socket_id(gDpdkPortId), &txq_conf) < 0) {
		rte_exit(EXIT_FAILURE, "Could not setup TX queue\n");
	}

	if (rte_eth_dev_start(gDpdkPortId) < 0) {
		rte_exit(EXIT_FAILURE, "Could not start\n");
	}

}

static uint16_t ng_checksum(uint16_t *addr, int count) {

	register long sum = 0;

	while (count > 1) {

		sum += *(unsigned short*)addr++;
		count -= 2;
	
	}

	if (count > 0) {
		sum += *(unsigned char *)addr;
	}

	while (sum >> 16) {
		sum = (sum & 0xffff) + (sum >> 16);
	}

	return ~sum;
}


static void ng_encode_icmp_pkt(uint8_t *msg, uint8_t *dst_mac, uint32_t sip, uint32_t dip, 
																	uint16_t id, uint16_t seqnb) {

	//设置以太网头
	struct rte_ether_hdr *eth = (struct rte_ether_hdr *)msg;
	rte_memcpy(eth->s_addr.addr_bytes, gSrcMac, RTE_ETHER_ADDR_LEN);
	rte_memcpy(eth->d_addr.addr_bytes, dst_mac, RTE_ETHER_ADDR_LEN);
	eth->ether_type = htons(RTE_ETHER_TYPE_IPV4);

	//设置ipv4头
	struct rte_ipv4_hdr *ip = (struct rte_ipv4_hdr *)(eth + 1);
	ip->version_ihl = 0x45;
	ip->type_of_service = 0;
	ip->total_length = htons(sizeof(struct rte_icmp_hdr) + sizeof(struct rte_ipv4_hdr));
	ip->packet_id = 0;
	ip->fragment_offset = 0;
	ip->time_to_live = 64;
	ip->next_proto_id = IPPROTO_ICMP;
	ip->src_addr = sip;
	ip->dst_addr = dip;
	//计算ip头部校验和时，先把该字段置为0(ip校验和只包括头部)
	ip->hdr_checksum = 0;
	ip->hdr_checksum = rte_ipv4_cksum(ip);

	//设置icmp报文
	struct rte_icmp_hdr *icmp = (struct rte_icmp_hdr *)(ip + 1);
	icmp->icmp_type = RTE_IP_ICMP_ECHO_REPLY;
	icmp->icmp_code = 0;
	icmp->icmp_ident = id;
	icmp->icmp_seq_nb = seqnb;
	icmp->icmp_cksum = 0;
	icmp->icmp_cksum = ng_checksum((uint16_t *)icmp, sizeof(struct rte_icmp_hdr));
	
}

static void ng_send_icmp(struct rte_mempool *mbuf_pool, uint8_t *dst_mac, uint32_t sip, uint32_t dip, 
																			uint16_t id, uint16_t seqnb) {

	const unsigned total_len = sizeof(struct rte_ether_hdr) + sizeof(struct rte_ipv4_hdr) + sizeof(struct rte_icmp_hdr);
	
	//从内存中申请一个mbuf
	struct rte_mbuf *mbuf = rte_pktmbuf_alloc(mbuf_pool);
	if (mbuf == NULL) {
		rte_exit(EXIT_FAILURE, "rte_pktmbuf_alloc\n");
	}
	mbuf->pkt_len = total_len;
	mbuf->data_len = total_len;

	//用于将数据包缓冲区（packet buffer）转换为指定类型的数据指针，也就是mbuf存储数据包的首地址
	uint8_t *pktdata = rte_pktmbuf_mtod(mbuf, uint8_t*);
	ng_encode_icmp_pkt(pktdata, dst_mac, sip, dip, id, seqnb);

	rte_eth_tx_burst(gDpdkPortId, 0, &mbuf, 1);
	rte_pktmbuf_free(mbuf);
}

static void ng_encode_arp_pkt(uint8_t *msg, uint8_t *dst_mac, uint32_t sip, uint32_t dip) {
	//设置以太网头
	struct rte_ether_hdr *eth = (struct rte_ether_hdr *)msg;
	rte_memcpy(eth->s_addr.addr_bytes, &gSrcMac, RTE_ETHER_ADDR_LEN);
	rte_memcpy(eth->d_addr.addr_bytes, dst_mac, RTE_ETHER_ADDR_LEN);
	eth->ether_type = htons(RTE_ETHER_TYPE_ARP);

	//设置arp报文
	struct rte_arp_hdr *arp = (struct rte_arp_hdr *)(eth + 1);
	arp->arp_hardware = htons(1);
	arp->arp_protocol = htons(RTE_ETHER_TYPE_IPV4);
	arp->arp_hlen = RTE_ETHER_ADDR_LEN;
	arp->arp_plen = sizeof(uint32_t);
	arp->arp_opcode = htons(RTE_ARP_OP_REPLY);
	rte_memcpy(arp->arp_data.arp_sha.addr_bytes, &gSrcMac, RTE_ETHER_ADDR_LEN);
	rte_memcpy(arp->arp_data.arp_tha.addr_bytes, dst_mac, RTE_ETHER_ADDR_LEN);
	arp->arp_data.arp_sip = sip;
	arp->arp_data.arp_tip= dip;
}

static void ng_send_arp(struct rte_mempool *mbuf_pool, uint8_t *dst_mac, 
				uint32_t sip, uint32_t dip) {
	const unsigned total_len = sizeof(struct rte_ether_hdr) + sizeof(struct rte_arp_hdr);

	//从内存中申请一个mbuf
	struct rte_mbuf *mbuf = rte_pktmbuf_alloc(mbuf_pool);
	if (mbuf == NULL) {
		rte_exit(EXIT_FAILURE, "rte_pktmbuf_alloc\n");
	}
	mbuf->pkt_len = total_len;
	mbuf->data_len = total_len;
	
	uint8_t *pktdata = rte_pktmbuf_mtod(mbuf, uint8_t*);
	ng_encode_arp_pkt(pktdata, dst_mac, sip, dip);

	rte_eth_tx_burst(gDpdkPortId, 0, &mbuf, 1);
	rte_pktmbuf_free(mbuf);
}



int main(int argc, char *argv[]) {
	/*dpdk初始化资源
	 *用于初始化 Environment Abstraction Layer (EAL)。EAL 是 DPDK 的一个核心组件，
	 *负责抽象和管理硬件和操作系统依赖性，使得上层应用可以在不同的硬件和操作系统上
	 *以统一的方式运行。
	 */
	if (rte_eal_init(argc, argv) < 0) {
		rte_exit(EXIT_FAILURE, "Error with EAL initialization\n");
	}

	//内存池，接收的数据存在该内存池中
	struct rte_mempool *mbuf_pool = rte_pktmbuf_pool_create("mbuf_pool", NUM_MBUFS,
			0, 0, RTE_MBUF_DEFAULT_BUF_SIZE, rte_socket_id());
	if (mbuf_pool == NULL) {
		rte_exit(EXIT_FAILURE, "Could not create mbuf pool\n");
	}

	ng_init_port(mbuf_pool);

	//获取dpdk绑定的网卡源mac
	rte_eth_macaddr_get(gDpdkPortId, (struct rte_ether_addr *)gSrcMac);
	
	while(1) {
		struct rte_mbuf *mbufs[BURST_SIZE] = {0};
		unsigned num_recvd = rte_eth_rx_burst(gDpdkPortId, 0, mbufs, BURST_SIZE);
		if (num_recvd > BURST_SIZE) {
			rte_exit(EXIT_FAILURE, "Error receive from eth\n");
		}

		unsigned int i = 0;
		for (i = 0; i < num_recvd; i++) {
			struct rte_ether_hdr *ehdr = rte_pktmbuf_mtod(mbufs[i], struct rte_ether_hdr*);
			//arp是广播
			if (ehdr->ether_type == rte_cpu_to_be_16(RTE_ETHER_TYPE_ARP)) {
				struct rte_arp_hdr *ahdr = (struct rte_arp_hdr *)(ehdr + 1);
				if (ahdr->arp_data.arp_tip == gLocalIp) {
					ng_send_arp(mbuf_pool, ahdr->arp_data.arp_sha.addr_bytes, 
						ahdr->arp_data.arp_tip, ahdr->arp_data.arp_sip);
				}
				rte_pktmbuf_free(mbufs[i]);
				continue;
			}
		
			if (ehdr->ether_type != rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4)) {
				rte_pktmbuf_free(mbufs[i]);
				continue;
			}
			struct rte_ipv4_hdr *iphdr = rte_pktmbuf_mtod_offset(mbufs[i], struct rte_ipv4_hdr*, sizeof(struct rte_ether_hdr));
			if (iphdr->next_proto_id == IPPROTO_ICMP) {
				struct rte_icmp_hdr *icmphdr = (struct rte_icmp_hdr *)(iphdr + 1);
				if (icmphdr->icmp_type == RTE_IP_ICMP_ECHO_REQUEST) {
					ng_send_icmp(mbuf_pool, ehdr->s_addr.addr_bytes, iphdr->dst_addr, iphdr->src_addr, 
						icmphdr->icmp_ident, icmphdr->icmp_seq_nb);
				}
				
			}
			rte_pktmbuf_free(mbufs[i]);
		}
		
	}
	
	return 0;
}