Re: [RFC bpf-next 4/4] selftests/bpf: Add attach bench test

[Andrii Nakryiko]

On Thu, Apr 7, 2022 at 5:53 AM Jiri Olsa <jolsa@xxxxxxxxxx> wrote:
>
> Adding test that reads all functions from ftrace available_filter_functions
> file and attach them all through kprobe_multi API.
>
> It checks that the attach and detach times is under 2 seconds
> and printf stats info with -v option, like on my setup:
>
>   test_bench_attach: found 48712 functions
>   test_bench_attach: attached in   1.069s
>   test_bench_attach: detached in   0.373s
>
> Signed-off-by: Jiri Olsa <jolsa@xxxxxxxxxx>
> ---
>  .../bpf/prog_tests/kprobe_multi_test.c        | 141 ++++++++++++++++++
>  .../selftests/bpf/progs/kprobe_multi_empty.c  |  12 ++
>  2 files changed, 153 insertions(+)
>  create mode 100644 tools/testing/selftests/bpf/progs/kprobe_multi_empty.c
>
> diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
> index b9876b55fc0c..6798b54416de 100644
> --- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
> +++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
> @@ -2,6 +2,9 @@
>  #include <test_progs.h>
>  #include "kprobe_multi.skel.h"
>  #include "trace_helpers.h"
> +#include "kprobe_multi_empty.skel.h"
> +#include "bpf/libbpf_internal.h"
> +#include "bpf/hashmap.h"
>
>  static void kprobe_multi_test_run(struct kprobe_multi *skel, bool test_return)
>  {
> @@ -301,6 +304,142 @@ static void test_attach_api_fails(void)
>         kprobe_multi__destroy(skel);
>  }
>
> +static inline __u64 get_time_ns(void)
> +{
> +       struct timespec t;
> +
> +       clock_gettime(CLOCK_MONOTONIC, &t);
> +       return (__u64) t.tv_sec * 1000000000 + t.tv_nsec;
> +}
> +
> +static size_t symbol_hash(const void *key, void *ctx __maybe_unused)
> +{
> +       return str_hash((const char *) key);
> +}
> +
> +static bool symbol_equal(const void *key1, const void *key2, void *ctx __maybe_unused)
> +{
> +       return strcmp((const char *) key1, (const char *) key2) == 0;
> +}
> +
> +#define DEBUGFS "/sys/kernel/debug/tracing/"
> +
> +static int get_syms(char ***symsp, size_t *cntp)
> +{
> +       size_t cap = 0, cnt = 0, i;
> +       char *name, **syms = NULL;
> +       struct hashmap *map;
> +       char buf[256];
> +       FILE *f;
> +       int err;
> +
> +       /*
> +        * The available_filter_functions contains many duplicates,
> +        * but other than that all symbols are usable in kprobe multi
> +        * interface.
> +        * Filtering out duplicates by using hashmap__add, which won't
> +        * add existing entry.
> +        */
> +       f = fopen(DEBUGFS "available_filter_functions", "r");

I'm really curious how did you manage to attach to everything in
available_filter_functions because when I'm trying to do that I fail.
available_filter_functions has a bunch of functions that should not be
attachable (e.g., notrace functions). Look just at __bpf_tramp_exit:

  void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr);

So first, curious what I am doing wrong or rather why it succeeds in
your case ;)

But second, just wanted to plea to "fix" available_filter_functions to
not list stuff that should not be attachable. Can you please take a
look and checks what's going on there and why do we have notrace
functions (and what else should *NOT* be there)?


> +       if (!f)
> +               return -EINVAL;
> +
> +       map = hashmap__new(symbol_hash, symbol_equal, NULL);
> +       err = libbpf_get_error(map);
> +       if (err)
> +               goto error;
> +

[...]

> +
> +       attach_delta_ns = (attach_end_ns - attach_start_ns) / 1000000000.0;
> +       detach_delta_ns = (detach_end_ns - detach_start_ns) / 1000000000.0;
> +
> +       fprintf(stderr, "%s: found %lu functions\n", __func__, cnt);
> +       fprintf(stderr, "%s: attached in %7.3lfs\n", __func__, attach_delta_ns);
> +       fprintf(stderr, "%s: detached in %7.3lfs\n", __func__, detach_delta_ns);
> +
> +       if (attach_delta_ns > 2.0)
> +               PRINT_FAIL("attach time above 2 seconds\n");
> +       if (detach_delta_ns > 2.0)
> +               PRINT_FAIL("detach time above 2 seconds\n");

see my reply on the cover letter, any such "2 second" assumption are
guaranteed to bite us. We've dealt with a lot of timing issues due to
CI being slower and more unpredictable in terms of performance, I'd
like to avoid dealing with one more case like that.


> +
> +cleanup:
> +       kprobe_multi_empty__destroy(skel);
> +       if (syms) {
> +               for (i = 0; i < cnt; i++)
> +                       free(syms[i]);
> +               free(syms);
> +       }
> +}
> +
>  void test_kprobe_multi_test(void)
>  {
>         if (!ASSERT_OK(load_kallsyms(), "load_kallsyms"))
> @@ -320,4 +459,6 @@ void test_kprobe_multi_test(void)
>                 test_attach_api_syms();
>         if (test__start_subtest("attach_api_fails"))
>                 test_attach_api_fails();
> +       if (test__start_subtest("bench_attach"))
> +               test_bench_attach();
>  }
> diff --git a/tools/testing/selftests/bpf/progs/kprobe_multi_empty.c b/tools/testing/selftests/bpf/progs/kprobe_multi_empty.c
> new file mode 100644
> index 000000000000..be9e3d891d46
> --- /dev/null
> +++ b/tools/testing/selftests/bpf/progs/kprobe_multi_empty.c
> @@ -0,0 +1,12 @@
> +// SPDX-License-Identifier: GPL-2.0
> +#include <linux/bpf.h>
> +#include <bpf/bpf_helpers.h>
> +#include <bpf/bpf_tracing.h>
> +
> +char _license[] SEC("license") = "GPL";
> +
> +SEC("kprobe.multi/*")
> +int test_kprobe_empty(struct pt_regs *ctx)
> +{
> +       return 0;
> +}
> --
> 2.35.1
>