linux/samples/bpf/xdp1_user.c
Brenden Blanco 86af8b4191 Add sample for adding simple drop program to link
Add a sample program that only drops packets at the BPF_PROG_TYPE_XDP_RX
hook of a link. With the drop-only program, observed single core rate is
~20Mpps.

Other tests were run, for instance without the dropcnt increment or
without reading from the packet header, the packet rate was mostly
unchanged.

$ perf record -a samples/bpf/xdp1 $(</sys/class/net/eth0/ifindex)
proto 17:   20403027 drops/s

./pktgen_sample03_burst_single_flow.sh -i $DEV -d $IP -m $MAC -t 4
Running... ctrl^C to stop
Device: eth4@0
Result: OK: 11791017(c11788327+d2689) usec, 59622913 (60byte,0frags)
  5056638pps 2427Mb/sec (2427186240bps) errors: 0
Device: eth4@1
Result: OK: 11791012(c11787906+d3106) usec, 60526944 (60byte,0frags)
  5133311pps 2463Mb/sec (2463989280bps) errors: 0
Device: eth4@2
Result: OK: 11791019(c11788249+d2769) usec, 59868091 (60byte,0frags)
  5077431pps 2437Mb/sec (2437166880bps) errors: 0
Device: eth4@3
Result: OK: 11795039(c11792403+d2636) usec, 59483181 (60byte,0frags)
  5043067pps 2420Mb/sec (2420672160bps) errors: 0

perf report --no-children:
 26.05%  ksoftirqd/0  [mlx4_en]         [k] mlx4_en_process_rx_cq
 17.84%  ksoftirqd/0  [mlx4_en]         [k] mlx4_en_alloc_frags
  5.52%  ksoftirqd/0  [mlx4_en]         [k] mlx4_en_free_frag
  4.90%  swapper      [kernel.vmlinux]  [k] poll_idle
  4.14%  ksoftirqd/0  [kernel.vmlinux]  [k] get_page_from_freelist
  2.78%  ksoftirqd/0  [kernel.vmlinux]  [k] __free_pages_ok
  2.57%  ksoftirqd/0  [kernel.vmlinux]  [k] bpf_map_lookup_elem
  2.51%  swapper      [mlx4_en]         [k] mlx4_en_process_rx_cq
  1.94%  ksoftirqd/0  [kernel.vmlinux]  [k] percpu_array_map_lookup_elem
  1.45%  swapper      [mlx4_en]         [k] mlx4_en_alloc_frags
  1.35%  ksoftirqd/0  [kernel.vmlinux]  [k] free_one_page
  1.33%  swapper      [kernel.vmlinux]  [k] intel_idle
  1.04%  ksoftirqd/0  [mlx4_en]         [k] 0x000000000001c5c5
  0.96%  ksoftirqd/0  [mlx4_en]         [k] 0x000000000001c58d
  0.93%  ksoftirqd/0  [mlx4_en]         [k] 0x000000000001c6ee
  0.92%  ksoftirqd/0  [mlx4_en]         [k] 0x000000000001c6b9
  0.89%  ksoftirqd/0  [kernel.vmlinux]  [k] __alloc_pages_nodemask
  0.83%  ksoftirqd/0  [mlx4_en]         [k] 0x000000000001c686
  0.83%  ksoftirqd/0  [mlx4_en]         [k] 0x000000000001c5d5
  0.78%  ksoftirqd/0  [mlx4_en]         [k] mlx4_alloc_pages.isra.23
  0.77%  ksoftirqd/0  [mlx4_en]         [k] 0x000000000001c5b4
  0.77%  ksoftirqd/0  [kernel.vmlinux]  [k] net_rx_action

machine specs:
 receiver - Intel E5-1630 v3 @ 3.70GHz
 sender - Intel E5645 @ 2.40GHz
 Mellanox ConnectX-3 @40G

Signed-off-by: Brenden Blanco <bblanco@plumgrid.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-07-19 21:46:32 -07:00

182 lines
3.9 KiB
C

/* Copyright (c) 2016 PLUMgrid
*
* 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 <linux/netlink.h>
#include <linux/rtnetlink.h>
#include <assert.h>
#include <errno.h>
#include <signal.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/socket.h>
#include <unistd.h>
#include "bpf_load.h"
#include "libbpf.h"
static int set_link_xdp_fd(int ifindex, int fd)
{
struct sockaddr_nl sa;
int sock, seq = 0, len, ret = -1;
char buf[4096];
struct nlattr *nla, *nla_xdp;
struct {
struct nlmsghdr nh;
struct ifinfomsg ifinfo;
char attrbuf[64];
} req;
struct nlmsghdr *nh;
struct nlmsgerr *err;
memset(&sa, 0, sizeof(sa));
sa.nl_family = AF_NETLINK;
sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
if (sock < 0) {
printf("open netlink socket: %s\n", strerror(errno));
return -1;
}
if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
printf("bind to netlink: %s\n", strerror(errno));
goto cleanup;
}
memset(&req, 0, sizeof(req));
req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
req.nh.nlmsg_type = RTM_SETLINK;
req.nh.nlmsg_pid = 0;
req.nh.nlmsg_seq = ++seq;
req.ifinfo.ifi_family = AF_UNSPEC;
req.ifinfo.ifi_index = ifindex;
nla = (struct nlattr *)(((char *)&req)
+ NLMSG_ALIGN(req.nh.nlmsg_len));
nla->nla_type = NLA_F_NESTED | 43/*IFLA_XDP*/;
nla_xdp = (struct nlattr *)((char *)nla + NLA_HDRLEN);
nla_xdp->nla_type = 1/*IFLA_XDP_FD*/;
nla_xdp->nla_len = NLA_HDRLEN + sizeof(int);
memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd));
nla->nla_len = NLA_HDRLEN + nla_xdp->nla_len;
req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);
if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
printf("send to netlink: %s\n", strerror(errno));
goto cleanup;
}
len = recv(sock, buf, sizeof(buf), 0);
if (len < 0) {
printf("recv from netlink: %s\n", strerror(errno));
goto cleanup;
}
for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
nh = NLMSG_NEXT(nh, len)) {
if (nh->nlmsg_pid != getpid()) {
printf("Wrong pid %d, expected %d\n",
nh->nlmsg_pid, getpid());
goto cleanup;
}
if (nh->nlmsg_seq != seq) {
printf("Wrong seq %d, expected %d\n",
nh->nlmsg_seq, seq);
goto cleanup;
}
switch (nh->nlmsg_type) {
case NLMSG_ERROR:
err = (struct nlmsgerr *)NLMSG_DATA(nh);
if (!err->error)
continue;
printf("nlmsg error %s\n", strerror(-err->error));
goto cleanup;
case NLMSG_DONE:
break;
}
}
ret = 0;
cleanup:
close(sock);
return ret;
}
static int ifindex;
static void int_exit(int sig)
{
set_link_xdp_fd(ifindex, -1);
exit(0);
}
/* simple per-protocol drop counter
*/
static void poll_stats(int interval)
{
unsigned int nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
const unsigned int nr_keys = 256;
__u64 values[nr_cpus], prev[nr_keys][nr_cpus];
__u32 key;
int i;
memset(prev, 0, sizeof(prev));
while (1) {
sleep(interval);
for (key = 0; key < nr_keys; key++) {
__u64 sum = 0;
assert(bpf_lookup_elem(map_fd[0], &key, values) == 0);
for (i = 0; i < nr_cpus; i++)
sum += (values[i] - prev[key][i]);
if (sum)
printf("proto %u: %10llu pkt/s\n",
key, sum / interval);
memcpy(prev[key], values, sizeof(values));
}
}
}
int main(int ac, char **argv)
{
char filename[256];
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
if (ac != 2) {
printf("usage: %s IFINDEX\n", argv[0]);
return 1;
}
ifindex = strtoul(argv[1], NULL, 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);
if (set_link_xdp_fd(ifindex, prog_fd[0]) < 0) {
printf("link set xdp fd failed\n");
return 1;
}
poll_stats(2);
return 0;
}