linux/samples/bpf/xdp1_user.c
Daniel Borkmann e00c7b216f bpf: fix multiple issues in selftest suite and samples
1) The test_lru_map and test_lru_dist fails building on my machine since
   the sys/resource.h header is not included.

2) test_verifier fails in one test case where we try to call an invalid
   function, since the verifier log output changed wrt printing function
   names.

3) Current selftest suite code relies on sysconf(_SC_NPROCESSORS_CONF) for
   retrieving the number of possible CPUs. This is broken at least in our
   scenario and really just doesn't work.

   glibc tries a number of things for retrieving _SC_NPROCESSORS_CONF.
   First it tries equivalent of /sys/devices/system/cpu/cpu[0-9]* | wc -l,
   if that fails, depending on the config, it either tries to count CPUs
   in /proc/cpuinfo, or returns the _SC_NPROCESSORS_ONLN value instead.
   If /proc/cpuinfo has some issue, it returns just 1 worst case. This
   oddity is nothing new [1], but semantics/behaviour seems to be settled.
   _SC_NPROCESSORS_ONLN will parse /sys/devices/system/cpu/online, if
   that fails it looks into /proc/stat for cpuX entries, and if also that
   fails for some reason, /proc/cpuinfo is consulted (and returning 1 if
   unlikely all breaks down).

   While that might match num_possible_cpus() from the kernel in some
   cases, it's really not guaranteed with CPU hotplugging, and can result
   in a buffer overflow since the array in user space could have too few
   number of slots, and on perpcu map lookup, the kernel will write beyond
   that memory of the value buffer.

   William Tu reported such mismatches:

     [...] The fact that sysconf(_SC_NPROCESSORS_CONF) != num_possible_cpu()
     happens when CPU hotadd is enabled. For example, in Fusion when
     setting vcpu.hotadd = "TRUE" or in KVM, setting ./qemu-system-x86_64
     -smp 2, maxcpus=4 ... the num_possible_cpu() will be 4 and sysconf()
     will be 2 [2]. [...]

   Documentation/cputopology.txt says /sys/devices/system/cpu/possible
   outputs cpu_possible_mask. That is the same as in num_possible_cpus(),
   so first step would be to fix the _SC_NPROCESSORS_CONF calls with our
   own implementation. Later, we could add support to bpf(2) for passing
   a mask via CPU_SET(3), for example, to just select a subset of CPUs.

   BPF samples code needs this fix as well (at least so that people stop
   copying this). Thus, define bpf_num_possible_cpus() once in selftests
   and import it from there for the sample code to avoid duplicating it.
   The remaining sysconf(_SC_NPROCESSORS_CONF) in samples are unrelated.

After all three issues are fixed, the test suite runs fine again:

  # make run_tests | grep self
  selftests: test_verifier [PASS]
  selftests: test_maps [PASS]
  selftests: test_lru_map [PASS]
  selftests: test_kmod.sh [PASS]

  [1] https://www.sourceware.org/ml/libc-alpha/2011-06/msg00079.html
  [2] https://www.mail-archive.com/netdev@vger.kernel.org/msg121183.html

Fixes: 3059303f59 ("samples/bpf: update tracex[23] examples to use per-cpu maps")
Fixes: 86af8b4191 ("Add sample for adding simple drop program to link")
Fixes: df570f5772 ("samples/bpf: unit test for BPF_MAP_TYPE_PERCPU_ARRAY")
Fixes: e155967179 ("samples/bpf: unit test for BPF_MAP_TYPE_PERCPU_HASH")
Fixes: ebb676daa1 ("bpf: Print function name in addition to function id")
Fixes: 5db58faf98 ("bpf: Add tests for the LRU bpf_htab")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: William Tu <u9012063@gmail.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-27 20:38:47 -05:00

184 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 "bpf_util.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 = bpf_num_possible_cpus();
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;
}