Date:   Fri, 11 Aug 2023 08:15:30 -0700
From:   Ian Rogers <irogers@...gle.com>
To:     John Garry <john.g.garry@...cle.com>
Cc:     Peter Zijlstra <peterz@...radead.org>,
        Ingo Molnar <mingo@...hat.com>,
        Arnaldo Carvalho de Melo <acme@...nel.org>,
        Mark Rutland <mark.rutland@....com>,
        Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
        Jiri Olsa <jolsa@...nel.org>,
        Namhyung Kim <namhyung@...nel.org>,
        Adrian Hunter <adrian.hunter@...el.com>,
        Kan Liang <kan.liang@...ux.intel.com>,
        Ravi Bangoria <ravi.bangoria@....com>,
        Kajol Jain <kjain@...ux.ibm.com>,
        linux-perf-users@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v2 1/3] perf pmus: Sort pmus by name then suffix

On Fri, Aug 11, 2023 at 7:00 AM John Garry <john.g.garry@...cle.com> wrote:
>
> On 10/08/2023 22:49, Ian Rogers wrote:
> > Sort PMUs by name. If two PMUs have the same name but differ by
> > suffix
>
> I think that the wording here can be improved. If they have the same
> name, then they cannot differ. I think that you mean that two PMUs have
> the same name apart from a difference in suffix.

Sure.

> > , sort the suffixes numerically.
>
> I don't know how this will affect some hisi pmus which have special
> naming formats, like hisi_l3c_sscl1_4

Anything not starting with uncore_ is assumed not to have a suffix.

> > For example, "breakpoint" comes
> > before "cpu", "uncore_imc_free_running_0" comes before
> > "uncore_imc_free_running_1".
> >
> > Signed-off-by: Ian Rogers <irogers@...gle.com>
> > ---
> >   tools/perf/util/pmus.c | 48 ++++++++++++++++++++++++++++++++++++++++++
> >   1 file changed, 48 insertions(+)
> >
> > diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c
> > index c58ba9fb6a36..3581710667b0 100644
> > --- a/tools/perf/util/pmus.c
> > +++ b/tools/perf/util/pmus.c
> > @@ -1,8 +1,10 @@
> >   // SPDX-License-Identifier: GPL-2.0
> >   #include <linux/list.h>
> > +#include <linux/list_sort.h>
> >   #include <linux/zalloc.h>
> >   #include <subcmd/pager.h>
> >   #include <sys/types.h>
> > +#include <ctype.h>
> >   #include <dirent.h>
> >   #include <pthread.h>
> >   #include <string.h>
> > @@ -33,6 +35,31 @@ static LIST_HEAD(other_pmus);
> >   static bool read_sysfs_core_pmus;
> >   static bool read_sysfs_all_pmus;
> >
> > +static int pmu_name_len_no_suffix(const char *str, unsigned long *num)
> > +{
> > +     int orig_len, len;
> > +
> > +     orig_len = len = strlen(str);
> > +
> > +     /* Non-uncore PMUs have their full length, for example, i915. */
> > +     if (strncmp(str, "uncore_", 7))
> > +             return len;
> > +
> > +     /*
> > +      * Count trailing digits and '_', if '_{num}' suffix isn't present use
> > +      * the full length.
> > +      */
> > +     while (len > 0 && isdigit(str[len - 1]))
> > +             len--;
> > +
> > +     if (len > 0 && len != orig_len && str[len - 1] == '_') {
> > +             if (num)
> > +                     *num = strtoul(&str[len], NULL, 10);
> > +             return len - 1;
> > +     }
> > +     return orig_len;
> > +}
> > +
> >   void perf_pmus__destroy(void)
> >   {
> >       struct perf_pmu *pmu, *tmp;
> > @@ -122,6 +149,25 @@ static struct perf_pmu *perf_pmu__find2(int dirfd, const char *name)
> >       return perf_pmu__lookup(core_pmu ? &core_pmus : &other_pmus, dirfd, name);
> >   }
> >
> > +static int pmus_cmp(void *priv __maybe_unused,
> > +                 const struct list_head *lhs, const struct list_head *rhs)
> > +{
> > +     unsigned long lhs_num, rhs_num;
> > +     struct perf_pmu *lhs_pmu = container_of(lhs, struct perf_pmu, list);
> > +     struct perf_pmu *rhs_pmu = container_of(rhs, struct perf_pmu, list);
> > +     const char *lhs_pmu_name = lhs_pmu->name ?: "";
> > +     const char *rhs_pmu_name = rhs_pmu->name ?: "";
> > +     int lhs_pmu_name_len = pmu_name_len_no_suffix(lhs_pmu_name, &lhs_num);
> > +     int rhs_pmu_name_len = pmu_name_len_no_suffix(rhs_pmu_name, &rhs_num);
>
>
> This is a bit of a monster... at least it should have a comment on what
> it is doing. Do you consider your own version of strncmp which can
> handle numbers in the suffix as another solution?

Sure, the intention is to be intention revealing getting a left hand
and right hand pmu name, the length of the name part and the suffix
number. I'm not sure a comment can do more than restate what the code
is doing.

> > +     int ret = strncmp(lhs_pmu_name, rhs_pmu_name,
> > +                     lhs_pmu_name_len < rhs_pmu_name_len ? lhs_pmu_name_len : rhs_pmu_name_len);
>
> Could min(lhs_pmu_name_len, rhs_pmu_name_len) be used here?

Right, there is a suitable definition in linux/kernel.h

> > +
> > +     if (lhs_pmu_name_len != rhs_pmu_name_len || ret != 0 || lhs_pmu_name_len == 0)
> > +             return ret;
> > +
> > +     return lhs_num < rhs_num ? -1 : (lhs_num > rhs_num ? 1 : 0);
>
> double ternary operator on same line ain't great - can this be changed
> into multiple return statements and also commented.

The alternative is:
return lhs_num  - rhs_num;
which removes the compares and has a bug around minimum integer
everybody ignores.

Thanks,
Ian

> > +}
> > +
> >   /* Add all pmus in sysfs to pmu list: */
> >   static void pmu_read_sysfs(bool core_only)
> >   {
> > @@ -156,6 +202,8 @@ static void pmu_read_sysfs(bool core_only)
> >               if (!perf_pmu__create_placeholder_core_pmu(&core_pmus))
> >                       pr_err("Failure to set up any core PMUs\n");
> >       }
> > +     list_sort(NULL, &core_pmus, pmus_cmp);
> > +     list_sort(NULL, &other_pmus, pmus_cmp);
> >       if (!list_empty(&core_pmus)) {
> >               read_sysfs_core_pmus = true;
> >               if (!core_only)
>

Powered by blists - more mailing lists