Re: [PATCHv4 bpf-next 0/5] bpf: Speed up symbol resolving in kprobe multi link

[Jiri Olsa <olsajiri@gmail.com>]

On Fri, Apr 29, 2022 at 07:28:11AM -0700, Andrii Nakryiko wrote:
> On Thu, Apr 28, 2022 at 1:12 PM Jiri Olsa <jolsa@kernel.org> wrote:
> >
> > hi,
> > sending additional fix for symbol resolving in kprobe multi link
> > requested by Alexei and Andrii [1].
> >
> > This speeds up bpftrace kprobe attachment, when using pure symbols
> > (3344 symbols) to attach:
> >
> > Before:
> >
> >   # perf stat -r 5 -e cycles ./src/bpftrace -e 'kprobe:x* {  } i:ms:1 { exit(); }'
> >   ...
> >   6.5681 +- 0.0225 seconds time elapsed  ( +-  0.34% )
> >
> > After:
> >
> >   # perf stat -r 5 -e cycles ./src/bpftrace -e 'kprobe:x* {  } i:ms:1 { exit(); }'
> >   ...
> >   0.5661 +- 0.0275 seconds time elapsed  ( +-  4.85% )
> >
> > v4 changes:
> >   - fix compile issue [kernel test robot]
> >   - added acks [Andrii]
> >
> > v3 changes:
> >   - renamed kallsyms_lookup_names to ftrace_lookup_symbols
> >     and moved it to ftrace.c [Masami]
> >   - added ack [Andrii]
> >   - couple small test fixes [Andrii]
> >
> > v2 changes (first version [2]):
> >   - removed the 2 seconds check [Alexei]
> >   - moving/forcing symbols sorting out of kallsyms_lookup_names function [Alexei]
> >   - skipping one array allocation and copy_from_user [Andrii]
> >   - several small fixes [Masami,Andrii]
> >   - build fix [kernel test robot]
> >
> > thanks,
> > jirka
> >
> >
> > [1] https://lore.kernel.org/bpf/CAEf4BzZtQaiUxQ-sm_hH2qKPRaqGHyOfEsW96DxtBHRaKLoL3Q@mail.gmail.com/
> > [2] https://lore.kernel.org/bpf/20220407125224.310255-1-jolsa@kernel.org/
> > ---
> > Jiri Olsa (5):
> >       kallsyms: Fully export kallsyms_on_each_symbol function
> >       ftrace: Add ftrace_lookup_symbols function
> >       fprobe: Resolve symbols with ftrace_lookup_symbols
> >       bpf: Resolve symbols with ftrace_lookup_symbols for kprobe multi link
> >       selftests/bpf: Add attach bench test
> >
> 
> Please check [0], it reports rcu_read_unlock() misuse
> 
>   [0] https://github.com/kernel-patches/bpf/runs/6223167405?check_suite_focus=true

hm, first I though it might be related to the bench test
attaching to 'bad' function, but the the warning showed
before that

will try to reproduce  with the CI .config

jirka


> 
> >  include/linux/ftrace.h                                     |   6 ++++++
> >  include/linux/kallsyms.h                                   |   7 ++++++-
> >  kernel/kallsyms.c                                          |   3 +--
> >  kernel/trace/bpf_trace.c                                   | 112 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----------------------------------------------
> >  kernel/trace/fprobe.c                                      |  32 ++++++++++++--------------------
> >  kernel/trace/ftrace.c                                      |  62 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
> >  tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c | 133 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
> >  tools/testing/selftests/bpf/progs/kprobe_multi_empty.c     |  12 ++++++++++++
> >  8 files changed, 298 insertions(+), 69 deletions(-)
> >  create mode 100644 tools/testing/selftests/bpf/progs/kprobe_multi_empty.c