Re: [PATCH] samples/bpf: Add xdp_sample_pkts example

[Song Liu <liu.song.a23@gmail.com>]

On Wed, May 30, 2018 at 9:45 AM, Toke Høiland-Jørgensen <toke@toke.dk> wrote:
> This adds an example program showing how to sample packets from XDP using
> the perf event buffer. The example userspace program just prints the
> ethernet header for every packet sampled.
>
> Most of the userspace code is borrowed from other examples, most notably
> trace_output.
>
> Note that the example only works when everything runs on CPU0; so
> suitable smp_affinity needs to be set on the device. Some drivers seem
> to reset smp_affinity when loading an XDP program, so it may be
> necessary to change it after starting the example userspace program.

Why does this only works when everything runs on CPU0? Is this something
we can improve?

Thanks,
Song

>
> Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk>
> ---
>  samples/bpf/Makefile               |   4 +
>  samples/bpf/xdp_sample_pkts_kern.c |  48 ++++++++++++
>  samples/bpf/xdp_sample_pkts_user.c | 147 +++++++++++++++++++++++++++++++++++++
>  3 files changed, 199 insertions(+)
>  create mode 100644 samples/bpf/xdp_sample_pkts_kern.c
>  create mode 100644 samples/bpf/xdp_sample_pkts_user.c
>
> diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
> index 1303af1..6f0c6d2 100644
> --- a/samples/bpf/Makefile
> +++ b/samples/bpf/Makefile
> @@ -52,6 +52,7 @@ hostprogs-y += xdp_adjust_tail
>  hostprogs-y += xdpsock
>  hostprogs-y += xdp_fwd
>  hostprogs-y += task_fd_query
> +hostprogs-y += xdp_sample_pkts
>
>  # Libbpf dependencies
>  LIBBPF = $(TOOLS_PATH)/lib/bpf/libbpf.a
> @@ -107,6 +108,7 @@ xdp_adjust_tail-objs := xdp_adjust_tail_user.o
>  xdpsock-objs := bpf_load.o xdpsock_user.o
>  xdp_fwd-objs := bpf_load.o xdp_fwd_user.o
>  task_fd_query-objs := bpf_load.o task_fd_query_user.o $(TRACE_HELPERS)
> +xdp_sample_pkts-objs := bpf_load.o xdp_sample_pkts_user.o $(TRACE_HELPERS)
>
>  # Tell kbuild to always build the programs
>  always := $(hostprogs-y)
> @@ -163,6 +165,7 @@ always += xdp_adjust_tail_kern.o
>  always += xdpsock_kern.o
>  always += xdp_fwd_kern.o
>  always += task_fd_query_kern.o
> +always += xdp_sample_pkts_kern.o
>
>  HOSTCFLAGS += -I$(objtree)/usr/include
>  HOSTCFLAGS += -I$(srctree)/tools/lib/
> @@ -179,6 +182,7 @@ HOSTCFLAGS_spintest_user.o += -I$(srctree)/tools/lib/bpf/
>  HOSTCFLAGS_trace_event_user.o += -I$(srctree)/tools/lib/bpf/
>  HOSTCFLAGS_sampleip_user.o += -I$(srctree)/tools/lib/bpf/
>  HOSTCFLAGS_task_fd_query_user.o += -I$(srctree)/tools/lib/bpf/
> +HOSTCFLAGS_xdp_sample_pkts_user.o += -I$(srctree)/tools/lib/bpf/
>
>  HOST_LOADLIBES         += $(LIBBPF) -lelf
>  HOSTLOADLIBES_tracex4          += -lrt
> diff --git a/samples/bpf/xdp_sample_pkts_kern.c b/samples/bpf/xdp_sample_pkts_kern.c
> new file mode 100644
> index 0000000..c58183a
> --- /dev/null
> +++ b/samples/bpf/xdp_sample_pkts_kern.c
> @@ -0,0 +1,48 @@
> +#include <linux/ptrace.h>
> +#include <linux/version.h>
> +#include <uapi/linux/bpf.h>
> +#include "bpf_helpers.h"
> +
> +#define SAMPLE_SIZE 64ul
> +
> +struct bpf_map_def SEC("maps") my_map = {
> +       .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
> +       .key_size = sizeof(int),
> +       .value_size = sizeof(u32),
> +       .max_entries = 2,
> +};
> +
> +SEC("xdp_sample")
> +int xdp_sample_prog(struct xdp_md *ctx)
> +{
> +       void *data_end = (void *)(long)ctx->data_end;
> +       void *data = (void *)(long)ctx->data;
> +
> +        /* Metadata will be in the perf event before the packet data. */
> +       struct S {
> +               u16 cookie;
> +               u16 pkt_len;
> +       } __attribute__((packed)) metadata;
> +
> +       if (data + SAMPLE_SIZE < data_end) {
> +               /* The XDP perf_event_output handler will use the upper 32 bits
> +                * of the flags argument as a number of bytes to include of the
> +                * packet payload in the event data. If the size is too big, the
> +                * call to bpf_perf_event_output will fail and return -EFAULT.
> +                *
> +                * See bpf_xdp_event_output in net/core/filter.c.
> +                */
> +               u64 flags = SAMPLE_SIZE << 32;
> +
> +               metadata.cookie = 0xdead;
> +               metadata.pkt_len = (u16)(data_end - data);
> +
> +               bpf_perf_event_output(ctx, &my_map, flags,
> +                                     &metadata, sizeof(metadata));
> +       }
> +
> +       return XDP_PASS;
> +}
> +
> +char _license[] SEC("license") = "GPL";
> +u32 _version SEC("version") = LINUX_VERSION_CODE;
> diff --git a/samples/bpf/xdp_sample_pkts_user.c b/samples/bpf/xdp_sample_pkts_user.c
> new file mode 100644
> index 0000000..f996917
> --- /dev/null
> +++ b/samples/bpf/xdp_sample_pkts_user.c
> @@ -0,0 +1,147 @@
> +/* 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 <stdio.h>
> +#include <unistd.h>
> +#include <stdlib.h>
> +#include <stdbool.h>
> +#include <string.h>
> +#include <fcntl.h>
> +#include <poll.h>
> +#include <linux/perf_event.h>
> +#include <linux/bpf.h>
> +#include <net/if.h>
> +#include <errno.h>
> +#include <assert.h>
> +#include <sys/syscall.h>
> +#include <sys/ioctl.h>
> +#include <sys/mman.h>
> +#include <time.h>
> +#include <signal.h>
> +#include <libbpf.h>
> +#include "bpf_load.h"
> +#include "bpf_util.h"
> +#include <bpf/bpf.h>
> +
> +#include "perf-sys.h"
> +#include "trace_helpers.h"
> +
> +static int pmu_fd, if_idx = 0;
> +static char *if_name;
> +
> +static int do_attach(int idx, int fd, const char *name)
> +{
> +       int err;
> +
> +       err = bpf_set_link_xdp_fd(idx, fd, 0);
> +       if (err < 0)
> +               printf("ERROR: failed to attach program to %s\n", name);
> +
> +       return err;
> +}
> +
> +static int do_detach(int idx, const char *name)
> +{
> +       int err;
> +
> +       err = bpf_set_link_xdp_fd(idx, -1, 0);
> +       if (err < 0)
> +               printf("ERROR: failed to detach program from %s\n", name);
> +
> +       return err;
> +}
> +
> +#define SAMPLE_SIZE 64
> +
> +static int print_bpf_output(void *data, int size)
> +{
> +       struct {
> +               __u16 cookie;
> +               __u16 pkt_len;
> +               __u8  pkt_data[SAMPLE_SIZE];
> +       } __attribute__((packed)) *e = data;
> +       int i;
> +
> +       if (e->cookie != 0xdead) {
> +               printf("BUG cookie %x sized %d\n",
> +                      e->cookie, size);
> +               return LIBBPF_PERF_EVENT_ERROR;
> +       }
> +
> +       printf("Pkt len: %-5d bytes. Ethernet hdr: ", e->pkt_len);
> +       for (i = 0; i < 14 && i < e->pkt_len; i++)
> +               printf("%02x ", e->pkt_data[i]);
> +       printf("\n");
> +
> +       return LIBBPF_PERF_EVENT_CONT;
> +}
> +
> +static void test_bpf_perf_event(void)
> +{
> +       struct perf_event_attr attr = {
> +               .sample_type = PERF_SAMPLE_RAW,
> +               .type = PERF_TYPE_SOFTWARE,
> +               .config = PERF_COUNT_SW_BPF_OUTPUT,
> +       };
> +       int key = 0;
> +
> +       pmu_fd = sys_perf_event_open(&attr, -1/*pid*/, 0/*cpu*/, -1/*group_fd*/, 0);
> +
> +       assert(pmu_fd >= 0);
> +       assert(bpf_map_update_elem(map_fd[0], &key, &pmu_fd, BPF_ANY) == 0);
> +       ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
> +}
> +
> +static void sig_handler(int signo)
> +{
> +       do_detach(if_idx, if_name);
> +       exit(0);
> +}
> +
> +int main(int argc, char **argv)
> +{
> +       char filename[256];
> +       int ret, err;
> +
> +       if (argc < 2) {
> +               printf("Usage: %s <ifname>\n", argv[0]);
> +               return 1;
> +       }
> +
> +       snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
> +
> +       if (load_bpf_file(filename)) {
> +               printf("%s", bpf_log_buf);
> +               return 1;
> +       }
> +
> +       if_idx = if_nametoindex(argv[1]);
> +       if (!if_idx)
> +               if_idx = strtoul(argv[1], NULL, 0);
> +
> +       if (!if_idx) {
> +               fprintf(stderr, "Invalid ifname\n");
> +               return 1;
> +       }
> +       if_name = argv[1];
> +       err = do_attach(if_idx, prog_fd[0], argv[1]);
> +       if (err)
> +               return err;
> +
> +       if (signal(SIGINT, sig_handler) ||
> +           signal(SIGHUP, sig_handler) ||
> +           signal(SIGTERM, sig_handler)) {
> +               perror("signal");
> +               return 1;
> +       }
> +
> +       test_bpf_perf_event();
> +
> +       if (perf_event_mmap(pmu_fd) < 0)
> +               return 1;
> +
> +       ret = perf_event_poller(pmu_fd, print_bpf_output);
> +       kill(0, SIGINT);
> +       return ret;
> +}
> --
> 2.7.4
>