编译dpdk
meson build
ninja -C build
mkdir -p /dev/hugepages
mountpoint -q /dev/hugepages || mount -t hugetlbfs nodev /dev/hugepages
echo 64 > /sys/devices/system/node/node0/hugepages/hugepages-2048kB/nr_hugepages
ninja app/dpdk-testpmd
环境搭建
1.先通过./usertools/dpdk-devbind.py -s获取网卡的总线地址
2.用ifconfig ens34 down 命令将eth接口down掉
3.modprobe uio.ko
4.下载dpdk-kmods源码,并进入目录编译生成igb_uio.ko模块
5.insmod igb_uio.ko
6.dpdk-devbind.py --bind=igb_uio xxxx:xx:xx.x 绑定网卡总线地址
7.运行./app/dpdk-testpmd – -i --forward-mode=icmpecho
8.set verbose 2
testpmd> show port info all
********************* Infos for port 0 *********************
MAC address: 00:0C:29:A8:09:8A
Device name: 0000:02:06.0
Driver name: net_e1000_em
Firmware-version: not available
Connect to socket: 0
memory allocation on the socket: 0
Link status: up
Link speed: 1 Gbps
Link duplex: full-duplex
Autoneg status: On
MTU: 1500
Promiscuous mode: enabled
Allmulticast mode: disabled
Maximum number of MAC addresses: 15
Maximum number of MAC addresses of hash filtering: 0
VLAN offload:
strip off, filter off, extend off, qinq strip off
No RSS offload flow type is supported.
Minimum size of RX buffer: 256
Maximum configurable length of RX packet: 16128
Maximum configurable size of LRO aggregated packet: 0
Current number of RX queues: 1
Max possible RX queues: 1
Max possible number of RXDs per queue: 4096
Min possible number of RXDs per queue: 32
RXDs number alignment: 8
Current number of TX queues: 1
Max possible TX queues: 1
Max possible number of TXDs per queue: 4096
Min possible number of TXDs per queue: 32
TXDs number alignment: 8
Max segment number per packet: 255
Max segment number per MTU/TSO: 255
Device capabilities: 0x0( )
8.获取MAC地址调用命令绑定arp表 arp -s 192.168.139.133 00:0C:29:A8:09:8A 并ping 192.168.139.133地址
9.打印信息
testpmd> start
icmpecho packet forwarding - ports=1 - cores=1 - streams=1 - NUMA support enabled, MP allocation mode: native
Logical Core 1 (socket 0) forwards packets on 1 streams:
RX P=0/Q=0 (socket 0) -> TX P=0/Q=0 (socket 0) peer=02:00:00:00:00:00
icmpecho packet forwarding packets/burst=32
nb forwarding cores=1 - nb forwarding ports=1
port 0: RX queue number: 1 Tx queue number: 1
Rx offloads=0x0 Tx offloads=0x0
RX queue: 0
RX desc=256 - RX free threshold=0
RX threshold registers: pthresh=0 hthresh=0 wthresh=0
RX Offloads=0x0
TX queue: 0
TX desc=256 - TX free threshold=32
TX threshold registers: pthresh=0 hthresh=0 wthresh=0
TX offloads=0x0 - TX RS bit threshold=32
testpmd>
tanjun hello world Port 0 pkt-len=247 nb-segs=1
ETH: src=00:0C:29:A8:09:94 dst=FF:FF:FF:FF:FF:FF type=0x0800
IPV4: src=192.168.139.131 dst=192.168.139.255 proto=17 (UDP)
tanjun hello world Port 0 pkt-len=247 nb-segs=1
ETH: src=00:0C:29:A8:09:94 dst=FF:FF:FF:FF:FF:FF type=0x0800
IPV4: src=192.168.139.131 dst=192.168.139.255 proto=17 (UDP)
tanjun hello world Port 0 pkt-len=247 nb-segs=1
ETH: src=00:0C:29:A8:09:94 dst=FF:FF:FF:FF:FF:FF type=0x0800
IPV4: src=192.168.139.131 dst=192.168.139.255 proto=17 (UDP)
代码解析
reply_to_icmp_echo_rqsts(struct fwd_stream *fs)
{
struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
struct rte_mbuf *pkt;
struct rte_ether_hdr *eth_h;
struct rte_vlan_hdr *vlan_h;
struct rte_arp_hdr *arp_h;
struct rte_ipv4_hdr *ip_h;
struct rte_icmp_hdr *icmp_h;
struct rte_ether_addr eth_addr;
uint32_t retry;
uint32_t ip_addr;
uint16_t nb_rx;
uint16_t nb_tx;
uint16_t nb_replies;
uint16_t eth_type;
uint16_t vlan_id;
uint16_t arp_op;
uint16_t arp_pro;
uint32_t cksum;
uint8_t i;
int l2_len;
uint64_t start_tsc = 0;
get_start_cycles(&start_tsc);
int tanjun_test=verbose_level;
verbose_level=1;
/*
* First, receive a burst of packets.
*/
nb_rx = rte_eth_rx_burst(fs->rx_port, fs->rx_queue, pkts_burst,
nb_pkt_per_burst);
inc_rx_burst_stats(fs, nb_rx);
if (unlikely(nb_rx == 0))
return;
fs->rx_packets += nb_rx;
nb_replies = 0;
for (i = 0; i < nb_rx; i++) {
if (likely(i < nb_rx - 1))
rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[i + 1],
void *));
pkt = pkts_burst[i];
eth_h = rte_pktmbuf_mtod(pkt, struct rte_ether_hdr *);
eth_type = RTE_BE_TO_CPU_16(eth_h->ether_type);
l2_len = sizeof(struct rte_ether_hdr);
if (verbose_level > 0) {
printf("\ntanjun hello world Port %d pkt-len=%u nb-segs=%u\n",
fs->rx_port, pkt->pkt_len, pkt->nb_segs);
ether_addr_dump(" ETH: src=", ð_h->src_addr);
ether_addr_dump(" dst=", ð_h->dst_addr);
}
if (eth_type == RTE_ETHER_TYPE_VLAN) {
vlan_h = (struct rte_vlan_hdr *)
((char *)eth_h + sizeof(struct rte_ether_hdr));
l2_len += sizeof(struct rte_vlan_hdr);
eth_type = rte_be_to_cpu_16(vlan_h->eth_proto);
if (verbose_level > 0) {
vlan_id = rte_be_to_cpu_16(vlan_h->vlan_tci)
& 0xFFF;
printf(" [vlan id=%u]", vlan_id);
}
}
if (verbose_level > 0) {
printf(" type=0x%04x\n", eth_type);
}
/* Reply to ARP requests */
if (eth_type == RTE_ETHER_TYPE_ARP) {
arp_h = (struct rte_arp_hdr *) ((char *)eth_h + l2_len);
arp_op = RTE_BE_TO_CPU_16(arp_h->arp_opcode);
arp_pro = RTE_BE_TO_CPU_16(arp_h->arp_protocol);
if (verbose_level > 0) {
printf(" ARP: hrd=%d proto=0x%04x hln=%d "
"pln=%d op=%u (%s)\n",
RTE_BE_TO_CPU_16(arp_h->arp_hardware),
arp_pro, arp_h->arp_hlen,
arp_h->arp_plen, arp_op,
arp_op_name(arp_op));
}
if ((RTE_BE_TO_CPU_16(arp_h->arp_hardware) !=
RTE_ARP_HRD_ETHER) ||
(arp_pro != RTE_ETHER_TYPE_IPV4) ||
(arp_h->arp_hlen != 6) ||
(arp_h->arp_plen != 4)
) {
rte_pktmbuf_free(pkt);
if (verbose_level > 0)
printf("\n");
continue;
}
if (verbose_level > 0) {
rte_ether_addr_copy(&arp_h->arp_data.arp_sha,
ð_addr);
ether_addr_dump(" sha=", ð_addr);
ip_addr = arp_h->arp_data.arp_sip;
ipv4_addr_dump(" sip=", ip_addr);
printf("\n");
rte_ether_addr_copy(&arp_h->arp_data.arp_tha,
ð_addr);
ether_addr_dump(" tha=", ð_addr);
ip_addr = arp_h->arp_data.arp_tip;
ipv4_addr_dump(" tip=", ip_addr);
printf("\n");
}
if (arp_op != RTE_ARP_OP_REQUEST) {
rte_pktmbuf_free(pkt);
continue;
}
/*
* Build ARP reply.
*/
/* Use source MAC address as destination MAC address. */
rte_ether_addr_copy(ð_h->src_addr, ð_h->dst_addr);
/* Set source MAC address with MAC address of TX port */
rte_ether_addr_copy(&ports[fs->tx_port].eth_addr,
ð_h->src_addr);
arp_h->arp_opcode = rte_cpu_to_be_16(RTE_ARP_OP_REPLY);
rte_ether_addr_copy(&arp_h->arp_data.arp_tha,
ð_addr);
rte_ether_addr_copy(&arp_h->arp_data.arp_sha,
&arp_h->arp_data.arp_tha);
rte_ether_addr_copy(ð_h->src_addr,
&arp_h->arp_data.arp_sha);
/* Swap IP addresses in ARP payload */
ip_addr = arp_h->arp_data.arp_sip;
arp_h->arp_data.arp_sip = arp_h->arp_data.arp_tip;
arp_h->arp_data.arp_tip = ip_addr;
pkts_burst[nb_replies++] = pkt;
continue;
}
if (eth_type != RTE_ETHER_TYPE_IPV4) {
rte_pktmbuf_free(pkt);
continue;
}
ip_h = (struct rte_ipv4_hdr *) ((char *)eth_h + l2_len);
if (verbose_level > 0) {
ipv4_addr_dump(" IPV4: src=", ip_h->src_addr);
ipv4_addr_dump(" dst=", ip_h->dst_addr);
printf(" proto=%d (%s)\n",
ip_h->next_proto_id,
ip_proto_name(ip_h->next_proto_id));
}
/*
* Check if packet is a ICMP echo request.
*/
icmp_h = (struct rte_icmp_hdr *) ((char *)ip_h +
sizeof(struct rte_ipv4_hdr));
if (! ((ip_h->next_proto_id == IPPROTO_ICMP) &&
(icmp_h->icmp_type == RTE_IP_ICMP_ECHO_REQUEST) &&
(icmp_h->icmp_code == 0))) {
rte_pktmbuf_free(pkt);
continue;
}
if (verbose_level > 0)
printf(" ICMP: echo request seq id=%d\n",
rte_be_to_cpu_16(icmp_h->icmp_seq_nb));
/*
* Prepare ICMP echo reply to be sent back.
* - switch ethernet source and destinations addresses,
* - use the request IP source address as the reply IP
* destination address,
* - if the request IP destination address is a multicast
* address:
* - choose a reply IP source address different from the
* request IP source address,
* - re-compute the IP header checksum.
* Otherwise:
* - switch the request IP source and destination
* addresses in the reply IP header,
* - keep the IP header checksum unchanged.
* - set RTE_IP_ICMP_ECHO_REPLY in ICMP header.
* ICMP checksum is computed by assuming it is valid in the
* echo request and not verified.
*/
rte_ether_addr_copy(ð_h->src_addr, ð_addr);
rte_ether_addr_copy(ð_h->dst_addr, ð_h->src_addr);
rte_ether_addr_copy(ð_addr, ð_h->dst_addr);
ip_addr = ip_h->src_addr;
if (is_multicast_ipv4_addr(ip_h->dst_addr)) {
uint32_t ip_src;
ip_src = rte_be_to_cpu_32(ip_addr);
if ((ip_src & 0x00000003) == 1)
ip_src = (ip_src & 0xFFFFFFFC) | 0x00000002;
else
ip_src = (ip_src & 0xFFFFFFFC) | 0x00000001;
ip_h->src_addr = rte_cpu_to_be_32(ip_src);
ip_h->dst_addr = ip_addr;
ip_h->hdr_checksum = ipv4_hdr_cksum(ip_h);
} else {
ip_h->src_addr = ip_h->dst_addr;
ip_h->dst_addr = ip_addr;
}
icmp_h->icmp_type = RTE_IP_ICMP_ECHO_REPLY;
cksum = ~icmp_h->icmp_cksum & 0xffff;
cksum += ~RTE_BE16(RTE_IP_ICMP_ECHO_REQUEST << 8) & 0xffff;
cksum += RTE_BE16(RTE_IP_ICMP_ECHO_REPLY << 8);
cksum = (cksum & 0xffff) + (cksum >> 16);
cksum = (cksum & 0xffff) + (cksum >> 16);
icmp_h->icmp_cksum = ~cksum;
pkts_burst[nb_replies++] = pkt;
}
/* Send back ICMP echo replies, if any. */
if (nb_replies > 0) {
nb_tx = rte_eth_tx_burst(fs->tx_port, fs->tx_queue, pkts_burst,
nb_replies);
/*
* Retry if necessary
*/
if (unlikely(nb_tx < nb_replies) && fs->retry_enabled) {
retry = 0;
while (nb_tx < nb_replies &&
retry++ < burst_tx_retry_num) {
rte_delay_us(burst_tx_delay_time);
nb_tx += rte_eth_tx_burst(fs->tx_port,
fs->tx_queue,
&pkts_burst[nb_tx],
nb_replies - nb_tx);
}
}
fs->tx_packets += nb_tx;
inc_tx_burst_stats(fs, nb_tx);
if (unlikely(nb_tx < nb_replies)) {
fs->fwd_dropped += (nb_replies - nb_tx);
do {
rte_pktmbuf_free(pkts_burst[nb_tx]);
} while (++nb_tx < nb_replies);
}
}
verbose_level=tanjun_test;
get_end_cycles(fs, start_tsc);
}
verbose_level变量为控制打印信息的开关
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
