Re: [PATCH 3/6] perf record: Implement basic filtering for off-cpu

[Arnaldo Carvalho de Melo <acme@kernel.org>]

Em Thu, May 19, 2022 at 02:02:28PM -0700, Namhyung Kim escreveu:
> On Wed, May 18, 2022 at 9:02 PM Ian Rogers <irogers@google.com> wrote:
> >
> > On Wed, May 18, 2022 at 3:47 PM Namhyung Kim <namhyung@kernel.org> wrote:
> > >
> > > It should honor cpu and task filtering with -a, -C or -p, -t options.
> > >
> > > Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> > > ---
> > >  tools/perf/builtin-record.c            |  2 +-
> > >  tools/perf/util/bpf_off_cpu.c          | 78 +++++++++++++++++++++++---
> > >  tools/perf/util/bpf_skel/off_cpu.bpf.c | 52 +++++++++++++++--
> > >  tools/perf/util/off_cpu.h              |  6 +-
> > >  4 files changed, 123 insertions(+), 15 deletions(-)
> > >
> > > diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
> > > index 91f88501412e..7f60d2eac0b4 100644
> > > --- a/tools/perf/builtin-record.c
> > > +++ b/tools/perf/builtin-record.c
> > > @@ -907,7 +907,7 @@ static int record__config_text_poke(struct evlist *evlist)
> > >
> > >  static int record__config_off_cpu(struct record *rec)
> > >  {
> > > -       return off_cpu_prepare(rec->evlist);
> > > +       return off_cpu_prepare(rec->evlist, &rec->opts.target);
> > >  }
> > >
> > >  static bool record__kcore_readable(struct machine *machine)
> > > diff --git a/tools/perf/util/bpf_off_cpu.c b/tools/perf/util/bpf_off_cpu.c
> > > index 9ed7aca3f4ac..b5e2d038da50 100644
> > > --- a/tools/perf/util/bpf_off_cpu.c
> > > +++ b/tools/perf/util/bpf_off_cpu.c
> > > @@ -6,6 +6,9 @@
> > >  #include "util/off_cpu.h"
> > >  #include "util/perf-hooks.h"
> > >  #include "util/session.h"
> > > +#include "util/target.h"
> > > +#include "util/cpumap.h"
> > > +#include "util/thread_map.h"
> > >  #include <bpf/bpf.h>
> > >
> > >  #include "bpf_skel/off_cpu.skel.h"
> > > @@ -60,8 +63,23 @@ static int off_cpu_config(struct evlist *evlist)
> > >         return 0;
> > >  }
> > >
> > > -static void off_cpu_start(void *arg __maybe_unused)
> > > +static void off_cpu_start(void *arg)
> > >  {
> > > +       struct evlist *evlist = arg;
> > > +
> > > +       /* update task filter for the given workload */
> > > +       if (!skel->bss->has_cpu && !skel->bss->has_task &&
> > > +           perf_thread_map__pid(evlist->core.threads, 0) != -1) {
> > > +               int fd;
> > > +               u32 pid;
> > > +               u8 val = 1;
> > > +
> > > +               skel->bss->has_task = 1;
> > > +               fd = bpf_map__fd(skel->maps.task_filter);
> > > +               pid = perf_thread_map__pid(evlist->core.threads, 0);
> > > +               bpf_map_update_elem(fd, &pid, &val, BPF_ANY);
> > > +       }
> > > +
> > >         skel->bss->enabled = 1;
> > >  }
> > >
> > > @@ -71,31 +89,75 @@ static void off_cpu_finish(void *arg __maybe_unused)
> > >         off_cpu_bpf__destroy(skel);
> > >  }
> > >
> > > -int off_cpu_prepare(struct evlist *evlist)
> > > +int off_cpu_prepare(struct evlist *evlist, struct target *target)
> > >  {
> > > -       int err;
> > > +       int err, fd, i;
> > > +       int ncpus = 1, ntasks = 1;
> > >
> > >         if (off_cpu_config(evlist) < 0) {
> > >                 pr_err("Failed to config off-cpu BPF event\n");
> > >                 return -1;
> > >         }
> > >
> > > -       set_max_rlimit();
> > > -
> > > -       skel = off_cpu_bpf__open_and_load();
> > > +       skel = off_cpu_bpf__open();
> > >         if (!skel) {
> > >                 pr_err("Failed to open off-cpu BPF skeleton\n");
> > >                 return -1;
> > >         }
> > >
> > > +       /* don't need to set cpu filter for system-wide mode */
> > > +       if (target->cpu_list) {
> > > +               ncpus = perf_cpu_map__nr(evlist->core.user_requested_cpus);
> > > +               bpf_map__set_max_entries(skel->maps.cpu_filter, ncpus);
> > > +       }
> > > +
> > > +       if (target__has_task(target)) {
> > > +               ntasks = perf_thread_map__nr(evlist->core.threads);
> > > +               bpf_map__set_max_entries(skel->maps.task_filter, ntasks);
> > > +       }
> > > +
> > > +       set_max_rlimit();
> > > +
> > > +       err = off_cpu_bpf__load(skel);
> > > +       if (err) {
> > > +               pr_err("Failed to load off-cpu skeleton\n");
> > > +               goto out;
> > > +       }
> > > +
> > > +       if (target->cpu_list) {
> > > +               u32 cpu;
> > > +               u8 val = 1;
> > > +
> > > +               skel->bss->has_cpu = 1;
> > > +               fd = bpf_map__fd(skel->maps.cpu_filter);
> > > +
> > > +               for (i = 0; i < ncpus; i++) {
> > > +                       cpu = perf_cpu_map__cpu(evlist->core.user_requested_cpus, i).cpu;
> > > +                       bpf_map_update_elem(fd, &cpu, &val, BPF_ANY);
> >
> > Perhaps more concise with a for_each:
> >
> > perf_cpu_map__for_each_cpu(cpu, idx, evlist->core.user_requested_cpus)
> >   bpf_map_update_elem(fd, &cpu.cpu, &val, BPF_ANY);

So I'll wait for a new version of this patchset.

- Arnaldo