Re: [PATCH] perf evsel: Don't set sample_regs_intr/sample_regs_user for dummy event

[Jin, Yao]

Hi Jiri,

On 7/3/2020 7:00 PM, Jiri Olsa wrote:
> On Fri, Jul 03, 2020 at 08:42:15AM +0800, Jin Yao wrote:
> > Since commit 0a892c1c9472 ("perf record: Add dummy event during system wide synthesis"),
> > a dummy event is added to capture mmaps.
> >
> > But if we run perf-record as,
> >
> >   # perf record -e cycles:p -IXMM0 -a -- sleep 1
> >   Error:
> >   dummy:HG: PMU Hardware doesn't support sampling/overflow-interrupts. Try 'perf stat'
> >
> > The issue is, if we enable the extended regs (-IXMM0), but the
> > pmu->capabilities is not set with PERF_PMU_CAP_EXTENDED_REGS, the kernel
> > will return -EOPNOTSUPP error.
> >
> > See following code pieces.
> >
> > /* in kernel/events/core.c */
> > static int perf_try_init_event(struct pmu *pmu, struct perf_event *event)
> >
> > {
> > 	....
> > 	if (!(pmu->capabilities & PERF_PMU_CAP_EXTENDED_REGS) &&
> > 	    has_extended_regs(event))
> > 		ret = -EOPNOTSUPP;
> > 	....
> > }
> >
> > For software dummy event, the PMU should be not set with
> > PERF_PMU_CAP_EXTENDED_REGS. But unfortunately in current code, the dummy
> > event has possibility to be set with PERF_REG_EXTENDED_MASK bit.
> >
> > In evsel__config, /* tools/perf/util/evsel.c */
> >
> > if (opts->sample_intr_regs) {
> > 	attr->sample_regs_intr = opts->sample_intr_regs;
> > }
> >
> > If we use -IXMM0, the attr>sample_regs_intr will be set with
> > PERF_REG_EXTENDED_MASK bit.
> >
> > It doesn't make sense to set attr->sample_regs_intr for a
> > software dummy event.
> >
> > This patch adds dummy event checking before setting
> > attr->sample_regs_intr.
> >
> > After:
> >    # ./perf record -e cycles:p -IXMM0 -a -- sleep 1
> >    [ perf record: Woken up 1 times to write data ]
> >    [ perf record: Captured and wrote 0.413 MB perf.data (45 samples) ]
>
> LGTM, Adrian (cc-ed) just added another check to the same place,
> but it looks like both of them should be there:
>
>    https://lore.kernel.org/lkml/20200630133935.11150-2-adrian.hunter@xxxxxxxxx/
>
> jirka

Thanks Jiri! Yes, it looks like both of checks should be added here.

So do I post v2 (just rebase) once Adrian's patch gets merged?

Thanks
Jin Yao

> > Fixes: 0a892c1c9472 ("perf record: Add dummy event during system wide synthesis")
> > Signed-off-by: Jin Yao <yao.jin@xxxxxxxxxxxxxxx>
> > ---
> >   tools/perf/util/evsel.c | 4 ++--
> >   1 file changed, 2 insertions(+), 2 deletions(-)
> >
> > diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> > index 96e5171dce41..df3315543e86 100644
> > --- a/tools/perf/util/evsel.c
> > +++ b/tools/perf/util/evsel.c
> > @@ -1020,12 +1020,12 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts,
> >   	if (callchain && callchain->enabled && !evsel->no_aux_samples)
> >   		evsel__config_callchain(evsel, opts, callchain);
> >   
> > -	if (opts->sample_intr_regs) {
> > +	if (opts->sample_intr_regs && !is_dummy_event(evsel)) {
> >   		attr->sample_regs_intr = opts->sample_intr_regs;
> >   		evsel__set_sample_bit(evsel, REGS_INTR);
> >   	}
> >   
> > -	if (opts->sample_user_regs) {
> > +	if (opts->sample_user_regs && !is_dummy_event(evsel)) {
> >   		attr->sample_regs_user |= opts->sample_user_regs;
> >   		evsel__set_sample_bit(evsel, REGS_USER);
> >   	}
> > --
> > 2.17.1