Re: [PATCH v2 10/13] perf record: Lazy load kernel symbols

From: Ian Rogers <irogers@google.com>
To: Adrian Hunter <adrian.hunter@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	 Arnaldo Carvalho de Melo <acme@kernel.org>,
	Mark Rutland <mark.rutland@arm.com>,
	 Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Jiri Olsa <jolsa@kernel.org>,  Namhyung Kim <namhyung@kernel.org>,
	Nick Terrell <terrelln@fb.com>,
	 Kan Liang <kan.liang@linux.intel.com>,
	Song Liu <song@kernel.org>,  Sandipan Das <sandipan.das@amd.com>,
	Anshuman Khandual <anshuman.khandual@arm.com>,
	 James Clark <james.clark@arm.com>,
	Liam Howlett <liam.howlett@oracle.com>,
	 Miguel Ojeda <ojeda@kernel.org>, Leo Yan <leo.yan@linaro.org>,
	 German Gomez <german.gomez@arm.com>,
	Ravi Bangoria <ravi.bangoria@amd.com>,
	 Artem Savkov <asavkov@redhat.com>,
	Athira Rajeev <atrajeev@linux.vnet.ibm.com>,
	 Andi Kleen <ak@linux.intel.com>,
	linux-kernel@vger.kernel.org,  linux-perf-users@vger.kernel.org,
	bpf@vger.kernel.org
Subject: Re: [PATCH v2 10/13] perf record: Lazy load kernel symbols
Date: Tue, 24 Oct 2023 11:42:33 -0700	[thread overview]
Message-ID: <CAP-5=fXcQwBk=JBof=MMB7LDoutXEvAkB2FbF46jo2xk3tS6QQ@mail.gmail.com> (raw)
In-Reply-To: <f184e872-4673-419d-9ea8-2d449d9cfd5b@intel.com>

On Thu, Oct 19, 2023 at 4:02 AM Adrian Hunter <adrian.hunter@intel.com> wrote:
>
> On 12/10/23 09:23, Ian Rogers wrote:
> > Commit 5b7ba82a7591 ("perf symbols: Load kernel maps before using")
> > changed it so that loading a kernel dso would cause the symbols for
> > the dso to be eagerly loaded. For perf record this is overhead as the
> > symbols won't be used. Add a symbol_conf to control the behavior and
> > disable it for perf record and perf inject.
> >
> > Signed-off-by: Ian Rogers <irogers@google.com>
> > ---
> >  tools/perf/builtin-inject.c   | 4 ++++
> >  tools/perf/builtin-record.c   | 2 ++
> >  tools/perf/util/event.c       | 4 ++--
> >  tools/perf/util/symbol_conf.h | 3 ++-
> >  4 files changed, 10 insertions(+), 3 deletions(-)
> >
> > diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
> > index c8cf2fdd9cff..1539fb18c749 100644
> > --- a/tools/perf/builtin-inject.c
> > +++ b/tools/perf/builtin-inject.c
> > @@ -2265,6 +2265,10 @@ int cmd_inject(int argc, const char **argv)
> >               "perf inject [<options>]",
> >               NULL
> >       };
> > +
> > +     /* Disable eager loading of kernel symbols that adds overhead to perf inject. */
> > +     symbol_conf.lazy_load_kernel_maps = true;
>
> Possibly not for itrace kernel decoding, so:
>
>         if (!inject->itrace_synth_opts.set)
>                 symbol_conf.lazy_load_kernel_maps = true;

Thanks, added to v3.

Ian

> > +
> >  #ifndef HAVE_JITDUMP
> >       set_option_nobuild(options, 'j', "jit", "NO_LIBELF=1", true);
> >  #endif
> > diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
> > index dcf288a4fb9a..8ec818568662 100644
> > --- a/tools/perf/builtin-record.c
> > +++ b/tools/perf/builtin-record.c
> > @@ -3989,6 +3989,8 @@ int cmd_record(int argc, const char **argv)
> >  # undef set_nobuild
> >  #endif
> >
> > +     /* Disable eager loading of kernel symbols that adds overhead to perf record. */
> > +     symbol_conf.lazy_load_kernel_maps = true;
> >       rec->opts.affinity = PERF_AFFINITY_SYS;
> >
> >       rec->evlist = evlist__new();
> > diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
> > index 923c0fb15122..68f45e9e63b6 100644
> > --- a/tools/perf/util/event.c
> > +++ b/tools/perf/util/event.c
> > @@ -617,13 +617,13 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr,
> >       if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) {
> >               al->level = 'k';
> >               maps = machine__kernel_maps(machine);
> > -             load_map = true;
> > +             load_map = !symbol_conf.lazy_load_kernel_maps;
> >       } else if (cpumode == PERF_RECORD_MISC_USER && perf_host) {
> >               al->level = '.';
> >       } else if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) {
> >               al->level = 'g';
> >               maps = machine__kernel_maps(machine);
> > -             load_map = true;
> > +             load_map = !symbol_conf.lazy_load_kernel_maps;
> >       } else if (cpumode == PERF_RECORD_MISC_GUEST_USER && perf_guest) {
> >               al->level = 'u';
> >       } else {
> > diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h
> > index 0b589570d1d0..2b2fb9e224b0 100644
> > --- a/tools/perf/util/symbol_conf.h
> > +++ b/tools/perf/util/symbol_conf.h
> > @@ -42,7 +42,8 @@ struct symbol_conf {
> >                       inline_name,
> >                       disable_add2line_warn,
> >                       buildid_mmap2,
> > -                     guest_code;
> > +                     guest_code,
> > +                     lazy_load_kernel_maps;
> >       const char      *vmlinux_name,
> >                       *kallsyms_name,
> >                       *source_prefix,
>