summaryrefslogtreecommitdiff
path: root/samples/bpf/xdp_tx_iptunnel_user.c
diff options
context:
space:
mode:
authorMartin KaFai Lau <kafai@fb.com>2016-12-08 02:53:14 +0300
committerDavid S. Miller <davem@davemloft.net>2016-12-08 22:25:13 +0300
commit12d8bb64e3f65f5287ff17c084d076a28daa8096 (patch)
treee772f55d041956a3e07a487b48b42df8a0b830bf /samples/bpf/xdp_tx_iptunnel_user.c
parentea3349a03519dcd4f32d949cd80ab995623dc5ac (diff)
downloadlinux-12d8bb64e3f65f5287ff17c084d076a28daa8096.tar.xz
bpf: xdp: Add XDP example for head adjustment
The XDP prog checks if the incoming packet matches any VIP:PORT combination in the BPF hashmap. If it is, it will encapsulate the packet with a IPv4/v6 header as instructed by the value of the BPF hashmap and then XDP_TX it out. The VIP:PORT -> IP-Encap-Info can be specified by the cmd args of the user prog. Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'samples/bpf/xdp_tx_iptunnel_user.c')
-rw-r--r--samples/bpf/xdp_tx_iptunnel_user.c256
1 files changed, 256 insertions, 0 deletions
diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c
new file mode 100644
index 000000000000..7a71f5c74684
--- /dev/null
+++ b/samples/bpf/xdp_tx_iptunnel_user.c
@@ -0,0 +1,256 @@
+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <linux/bpf.h>
+#include <assert.h>
+#include <errno.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/resource.h>
+#include <arpa/inet.h>
+#include <netinet/ether.h>
+#include <unistd.h>
+#include <time.h>
+#include "bpf_load.h"
+#include "libbpf.h"
+#include "bpf_util.h"
+#include "xdp_tx_iptunnel_common.h"
+
+#define STATS_INTERVAL_S 2U
+
+static int ifindex = -1;
+
+static void int_exit(int sig)
+{
+ if (ifindex > -1)
+ set_link_xdp_fd(ifindex, -1);
+ exit(0);
+}
+
+/* simple per-protocol drop counter
+ */
+static void poll_stats(unsigned int kill_after_s)
+{
+ const unsigned int nr_protos = 256;
+ unsigned int nr_cpus = bpf_num_possible_cpus();
+ time_t started_at = time(NULL);
+ __u64 values[nr_cpus], prev[nr_protos][nr_cpus];
+ __u32 proto;
+ int i;
+
+ memset(prev, 0, sizeof(prev));
+
+ while (!kill_after_s || time(NULL) - started_at <= kill_after_s) {
+ sleep(STATS_INTERVAL_S);
+
+ for (proto = 0; proto < nr_protos; proto++) {
+ __u64 sum = 0;
+
+ assert(bpf_lookup_elem(map_fd[0], &proto, values) == 0);
+ for (i = 0; i < nr_cpus; i++)
+ sum += (values[i] - prev[proto][i]);
+
+ if (sum)
+ printf("proto %u: sum:%10llu pkts, rate:%10llu pkts/s\n",
+ proto, sum, sum / STATS_INTERVAL_S);
+ memcpy(prev[proto], values, sizeof(values));
+ }
+ }
+}
+
+static void usage(const char *cmd)
+{
+ printf("Start a XDP prog which encapsulates incoming packets\n"
+ "in an IPv4/v6 header and XDP_TX it out. The dst <VIP:PORT>\n"
+ "is used to select packets to encapsulate\n\n");
+ printf("Usage: %s [...]\n", cmd);
+ printf(" -i <ifindex> Interface Index\n");
+ printf(" -a <vip-service-address> IPv4 or IPv6\n");
+ printf(" -p <vip-service-port> A port range (e.g. 433-444) is also allowed\n");
+ printf(" -s <source-ip> Used in the IPTunnel header\n");
+ printf(" -d <dest-ip> Used in the IPTunnel header\n");
+ printf(" -m <dest-MAC> Used in sending the IP Tunneled pkt\n");
+ printf(" -T <stop-after-X-seconds> Default: 0 (forever)\n");
+ printf(" -P <IP-Protocol> Default is TCP\n");
+ printf(" -h Display this help\n");
+}
+
+static int parse_ipstr(const char *ipstr, unsigned int *addr)
+{
+ if (inet_pton(AF_INET6, ipstr, addr) == 1) {
+ return AF_INET6;
+ } else if (inet_pton(AF_INET, ipstr, addr) == 1) {
+ addr[1] = addr[2] = addr[3] = 0;
+ return AF_INET;
+ }
+
+ fprintf(stderr, "%s is an invalid IP\n", ipstr);
+ return AF_UNSPEC;
+}
+
+static int parse_ports(const char *port_str, int *min_port, int *max_port)
+{
+ char *end;
+ long tmp_min_port;
+ long tmp_max_port;
+
+ tmp_min_port = strtol(optarg, &end, 10);
+ if (tmp_min_port < 1 || tmp_min_port > 65535) {
+ fprintf(stderr, "Invalid port(s):%s\n", optarg);
+ return 1;
+ }
+
+ if (*end == '-') {
+ end++;
+ tmp_max_port = strtol(end, NULL, 10);
+ if (tmp_max_port < 1 || tmp_max_port > 65535) {
+ fprintf(stderr, "Invalid port(s):%s\n", optarg);
+ return 1;
+ }
+ } else {
+ tmp_max_port = tmp_min_port;
+ }
+
+ if (tmp_min_port > tmp_max_port) {
+ fprintf(stderr, "Invalid port(s):%s\n", optarg);
+ return 1;
+ }
+
+ if (tmp_max_port - tmp_min_port + 1 > MAX_IPTNL_ENTRIES) {
+ fprintf(stderr, "Port range (%s) is larger than %u\n",
+ port_str, MAX_IPTNL_ENTRIES);
+ return 1;
+ }
+ *min_port = tmp_min_port;
+ *max_port = tmp_max_port;
+
+ return 0;
+}
+
+int main(int argc, char **argv)
+{
+ unsigned char opt_flags[256] = {};
+ unsigned int kill_after_s = 0;
+ const char *optstr = "i:a:p:s:d:m:T:P:h";
+ int min_port = 0, max_port = 0;
+ struct iptnl_info tnl = {};
+ struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+ struct vip vip = {};
+ char filename[256];
+ int opt;
+ int i;
+
+ tnl.family = AF_UNSPEC;
+ vip.protocol = IPPROTO_TCP;
+
+ for (i = 0; i < strlen(optstr); i++)
+ if (optstr[i] != 'h' && 'a' <= optstr[i] && optstr[i] <= 'z')
+ opt_flags[(unsigned char)optstr[i]] = 1;
+
+ while ((opt = getopt(argc, argv, optstr)) != -1) {
+ unsigned short family;
+ unsigned int *v6;
+
+ switch (opt) {
+ case 'i':
+ ifindex = atoi(optarg);
+ break;
+ case 'a':
+ vip.family = parse_ipstr(optarg, vip.daddr.v6);
+ if (vip.family == AF_UNSPEC)
+ return 1;
+ break;
+ case 'p':
+ if (parse_ports(optarg, &min_port, &max_port))
+ return 1;
+ break;
+ case 'P':
+ vip.protocol = atoi(optarg);
+ break;
+ case 's':
+ case 'd':
+ if (opt == 's')
+ v6 = tnl.saddr.v6;
+ else
+ v6 = tnl.daddr.v6;
+
+ family = parse_ipstr(optarg, v6);
+ if (family == AF_UNSPEC)
+ return 1;
+ if (tnl.family == AF_UNSPEC) {
+ tnl.family = family;
+ } else if (tnl.family != family) {
+ fprintf(stderr,
+ "The IP version of the src and dst addresses used in the IP encapsulation does not match\n");
+ return 1;
+ }
+ break;
+ case 'm':
+ if (!ether_aton_r(optarg,
+ (struct ether_addr *)tnl.dmac)) {
+ fprintf(stderr, "Invalid mac address:%s\n",
+ optarg);
+ return 1;
+ }
+ break;
+ case 'T':
+ kill_after_s = atoi(optarg);
+ break;
+ default:
+ usage(argv[0]);
+ return 1;
+ }
+ opt_flags[opt] = 0;
+ }
+
+ for (i = 0; i < strlen(optstr); i++) {
+ if (opt_flags[(unsigned int)optstr[i]]) {
+ fprintf(stderr, "Missing argument -%c\n", optstr[i]);
+ usage(argv[0]);
+ return 1;
+ }
+ }
+
+ if (setrlimit(RLIMIT_MEMLOCK, &r)) {
+ perror("setrlimit(RLIMIT_MEMLOCK, RLIM_INFINITY)");
+ return 1;
+ }
+
+ snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+ if (load_bpf_file(filename)) {
+ printf("%s", bpf_log_buf);
+ return 1;
+ }
+
+ if (!prog_fd[0]) {
+ printf("load_bpf_file: %s\n", strerror(errno));
+ return 1;
+ }
+
+ signal(SIGINT, int_exit);
+
+ while (min_port <= max_port) {
+ vip.dport = htons(min_port++);
+ if (bpf_update_elem(map_fd[1], &vip, &tnl, BPF_NOEXIST)) {
+ perror("bpf_update_elem(&vip2tnl)");
+ return 1;
+ }
+ }
+
+ if (set_link_xdp_fd(ifindex, prog_fd[0]) < 0) {
+ printf("link set xdp fd failed\n");
+ return 1;
+ }
+
+ poll_stats(kill_after_s);
+
+ set_link_xdp_fd(ifindex, -1);
+
+ return 0;
+}