MIME-Version: 1.0
References: <20230219061329.1001079-1-namhyung@kernel.org> <20230219061329.1001079-3-namhyung@kernel.org>
 <Y/IEpW77gNpQbpK2@kernel.org> <CAM9d7chrbQ+79HRJF=e3DLA7rDL-LdNw2fVW3enjJjY+E-ESsQ@mail.gmail.com>
In-Reply-To: <CAM9d7chrbQ+79HRJF=e3DLA7rDL-LdNw2fVW3enjJjY+E-ESsQ@mail.gmail.com>
From:   Namhyung Kim <namhyung@kernel.org>
Date:   Wed, 22 Feb 2023 11:48:43 -0800
Message-ID: <CAM9d7cg_bnLuYN+SnS_m6gV2qto8hVGF1oYE7gSko=TuY-dpOQ@mail.gmail.com>
Subject: Re: [PATCH 2/8] perf bpf filter: Implement event sample filtering
To:     Arnaldo Carvalho de Melo <acme@kernel.org>
Cc:     Jiri Olsa <jolsa@kernel.org>,
        Peter Zijlstra <peterz@infradead.org>,
        Ingo Molnar <mingo@kernel.org>,
        Ian Rogers <irogers@google.com>,
        Adrian Hunter <adrian.hunter@intel.com>,
        Andi Kleen <ak@linux.intel.com>,
        Kan Liang <kan.liang@linux.intel.com>,
        Song Liu <song@kernel.org>,
        Stephane Eranian <eranian@google.com>,
        Ravi Bangoria <ravi.bangoria@amd.com>,
        Leo Yan <leo.yan@linaro.org>,
        James Clark <james.clark@arm.com>, Hao Luo <haoluo@google.com>,
        LKML <linux-kernel@vger.kernel.org>,
        linux-perf-users@vger.kernel.org, bpf@vger.kernel.org
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

On Sun, Feb 19, 2023 at 8:48 AM Namhyung Kim <namhyung@kernel.org> wrote:
>
> On Sun, Feb 19, 2023 at 3:14 AM Arnaldo Carvalho de Melo
> <acme@kernel.org> wrote:
> >
> > Em Sat, Feb 18, 2023 at 10:13:23PM -0800, Namhyung Kim escreveu:
> > > The BPF program will be attached to a perf_event and be triggered when
> > > it overflows.  It'd iterate the filters map and compare the sample
> > > value according to the expression.  If any of them fails, the sample
> > > would be dropped.
> > >
> > > Also it needs to have the corresponding sample data for the expression
> > > so it compares data->sample_flags with the given value.  To access the
> > > sample data, it uses the bpf_cast_to_kern_ctx() kfunc which was added
> > > in v6.2 kernel.
> >
> >   CLANG   /tmp/build/perf/util/bpf_skel/.tmp/sample_filter.bpf.o
> > util/bpf_skel/sample_filter.bpf.c:26:19: error: no member named 'sample_flags' in 'struct perf_sample_data'
> >         if ((kctx->data->sample_flags & entry->flags) == 0)
> >              ~~~~~~~~~~  ^
> > 1 error generated.
> > make[2]: *** [Makefile.perf:1078: /tmp/build/perf/util/bpf_skel/.tmp/sample_filter.bpf.o] Error 1
> > make[1]: *** [Makefile.perf:236: sub-make] Error 2
> > make: *** [Makefile:113: install-bin] Error 2
> > make: Leaving directory '/var/home/acme/git/perf/tools/perf'
> >
> >  Performance counter stats for 'make -k BUILD_BPF_SKEL=1 CORESIGHT=1 O=/tmp/build/perf -C tools/perf install-bin':
>
> Hmm.. strange.  In the include/linux/perf_event.h, the
> perf_sample_data has sample_flags, but vmlinux.h doesn't.

It looks like the vmlinux.h came from the old kernel image (before v6.1).
Please try again after building the kernel.  I'll add a check to prevent
such a build error in v3.

Thanks,
Namhyung