DPDK and XDP

#!/usr/bin/python
#
# xdp_drop_count.py Drop incoming packets on XDP layer and count for which
#                   protocol type
#
# Copyright (c) 2016 PLUMgrid
# Copyright (c) 2016 Jan Ruth
# Licensed under the Apache License, Version 2.0 (the "License")

from bcc import BPF
import pyroute2
import time
import sys

flags = 0
def usage():
    print("Usage: {0} [-S] <ifdev>".format(sys.argv[0]))
    print("       -S: use skb mode\n")
    print("e.g.: {0} eth0\n".format(sys.argv[0]))
    exit(1)

if len(sys.argv) < 2 or len(sys.argv) > 3:
    usage()

if len(sys.argv) == 2:
    device = sys.argv[1]

if len(sys.argv) == 3:
    if "-S" in sys.argv:
        # XDP_FLAGS_SKB_MODE
        flags |= 2 << 0

    if "-S" == sys.argv[1]:
        device = sys.argv[2]
    else:
        device = sys.argv[1]

mode = BPF.XDP
ctxtype = "xdp_md"

# load BPF program
b = BPF(text = """
#define KBUILD_MODNAME "foo"
#include <uapi/linux/bpf.h>
#include <linux/in.h>
#include <linux/if_ether.h>
#include <linux/if_packet.h>
#include <linux/if_vlan.h>
#include <linux/ip.h>
#include <linux/ipv6.h>

// how to determin ddos
#define MAX_NB_PACKETS 1000
#define LEGAL_DIFF_TIMESTAMP_PACKETS 1000000

// store data, data can be accessd in kernel and user namespace
BPF_HASH(rcv_packets);
BPF_TABLE("percpu_array", uint32_t, long, dropcnt, 256);

static inline int parse_ipv4(void *data, u64 nh_off, void *data_end) {
    struct iphdr *iph = data + nh_off;
    if ((void*)&iph[1] > data_end)
        return 0;
    return iph->protocol;
}
static inline int parse_ipv6(void *data, u64 nh_off, void *data_end) {
    struct ipv6hdr *ip6h = data + nh_off;
    if ((void*)&ip6h[1] > data_end)
        return 0;
    return ip6h->nexthdr;
}

// determine ddos
static inline int detect_ddos(){
    // Used to count number of received packets
    u64 rcv_packets_nb_index = 0, rcv_packets_nb_inter=1, *rcv_packets_nb_ptr;
    // Used to measure elapsed time between 2 successive received packets
    u64 rcv_packets_ts_index = 1, rcv_packets_ts_inter=0, *rcv_packets_ts_ptr;
    int ret = 0;
    
    rcv_packets_nb_ptr = rcv_packets.lookup(&rcv_packets_nb_index);
    rcv_packets_ts_ptr = rcv_packets.lookup(&rcv_packets_ts_index);
    if(rcv_packets_nb_ptr != 0 && rcv_packets_ts_ptr != 0){
        rcv_packets_nb_inter = *rcv_packets_nb_ptr;
        rcv_packets_ts_inter = bpf_ktime_get_ns() - *rcv_packets_ts_ptr;
        if(rcv_packets_ts_inter < LEGAL_DIFF_TIMESTAMP_PACKETS){
            rcv_packets_nb_inter++;
        } else {
            rcv_packets_nb_inter = 0;
        }
        if(rcv_packets_nb_inter > MAX_NB_PACKETS){
            ret = 1;
        }
    }
    rcv_packets_ts_inter = bpf_ktime_get_ns();
    rcv_packets.update(&rcv_packets_nb_index, &rcv_packets_nb_inter);
    rcv_packets.update(&rcv_packets_ts_index, &rcv_packets_ts_inter);
    return ret;
}

// determine and recode by proto
int xdp_prog1(struct CTXTYPE *ctx) {
    void* data_end = (void*)(long)ctx->data_end;
    void* data = (void*)(long)ctx->data;
    struct ethhdr *eth = data;
    // drop packets
    int rc = XDP_PASS; // let pass XDP_PASS or redirect to tx via XDP_TX
    long *value;
    uint16_t h_proto;
    uint64_t nh_off = 0;
    uint32_t index;
    nh_off = sizeof(*eth);
    if (data + nh_off  > data_end)
        return rc;
    h_proto = eth->h_proto;
    // parse double vlans
    if (detect_ddos() == 0){
        return rc;
    }
    rc = XDP_DROP;
    #pragma unroll
    for (int i=0; i<2; i++) {
        if (h_proto == htons(ETH_P_8021Q) || h_proto == htons(ETH_P_8021AD)) {
            struct vlan_hdr *vhdr;
            vhdr = data + nh_off;
            nh_off += sizeof(struct vlan_hdr);
            if (data + nh_off > data_end)
                return rc;
                h_proto = vhdr->h_vlan_encapsulated_proto;
        }
    }
    if (h_proto == htons(ETH_P_IP))
        index = parse_ipv4(data, nh_off, data_end);
    else if (h_proto == htons(ETH_P_IPV6))
       index = parse_ipv6(data, nh_off, data_end);
    else
        index = 0;
    value = dropcnt.lookup(&index);
    if (value)
        *value += 1;
    return rc;
}
""", cflags=["-w", "-DCTXTYPE=%s" % ctxtype])

fn = b.load_func("xdp_prog1", mode)
b.attach_xdp(device, fn, flags)


dropcnt = b.get_table("dropcnt")
prev = [0] * 256
print("Printing drops per IP protocol-number, hit CTRL+C to stop")
while 1:
    try:
        for k in dropcnt.keys():
            val = dropcnt.sum(k).value
            i = k.value
            if val:
                delta = val - prev[i]
                prev[i] = val
                print("{}: {} pkt/s".format(i, delta))
        time.sleep(1)
    except KeyboardInterrupt:
        print("Removing filter from device")
        break;

b.remove_xdp(device, flags)

# 运行 ddos_firewall
/usr/local/share/bcc/examples/networking/xdp/ddos_firewall.py -S lo

# 在另一个窗口用ab测试；本地80有一个正在运行的nginx
ab -n 1000 -c 10 "http://127.0.0.1/"

# 发现有部分请求被判定成了ddos, 平均耗时3.3ms (不开防火墙耗时约1ms)
6: 28 pkt/s
6: 27 pkt/s
6: 26 pkt/s

# 使用hping3测试更准确
# 使用 --fast测试正常，并无drop
hping3 -c 10000 -d 120 -S -w 64 -p 80 --fast --rand-source localhost

# 使用 --faster测试，出现大量drop
hping3 -c 10000 -d 120 -S -w 64 -p 80 --faster --rand-source localhost