Re: [PATCH] perf env: Find correct branch counter info on hybrid

From: Ian Rogers
Date: Mon Sep 09 2024 - 16:43:16 EST

On Mon, Sep 9, 2024 at 11:41 AM <kan.liang@xxxxxxxxxxxxxxx> wrote:
>
> From: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
>
> No event is printed in the "Branch Counter" column on hybrid machines.
>
> For example,
> $perf record -e "{cpu_core/branch-instructions/pp,cpu_core/branches/}:S"
> -j any,counter
> $perf report --total-cycles
>
> # Branch counter abbr list:
> # cpu_core/branch-instructions/pp = A
> # cpu_core/branches/ = B
> # '-' No event occurs
> # '+' Event occurrences may be lost due to branch counter saturated
> #
> # Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles Branch Counter
> # ............... .............. ........... .......... ..............
> 44.54% 727.1K 0.00% 1 |+ |+ |
> 36.31% 592.7K 0.00% 2 |+ |+ |
> 17.83% 291.1K 0.00% 1 |+ |+ |
>
> The branch counter information (br_cntr_width and br_cntr_nr) in the
> perf_env is retrieved from the CPU_PMU_CAPS. However, the CPU_PMU_CAPS
> is not available on hybrid machines. Without the width information, the
> number of occurrences of an event cannot be calculated.
>
> For a hybrid machine, the caps information should be retrieved from the
> PMU_CAPS, and stored in the perf_env->pmu_caps.
>
> Add a perf_env__find_br_cntr_info() to return the correct branch counter
> information from the corresponding fields.
>
> Fixes: 6f9d8d1de2c6 ("perf script: Add branch counters")
> Signed-off-by: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>

Reviewed-by: Ian Rogers <irogers@xxxxxxxxxx>

Thanks,
Ian

> ---
> tools/perf/builtin-script.c | 5 +++--
> tools/perf/util/annotate.c | 5 +++--
> tools/perf/util/env.c | 15 +++++++++++++++
> tools/perf/util/env.h | 3 +++
> tools/perf/util/session.c | 6 ++++--
> 5 files changed, 28 insertions(+), 6 deletions(-)
>
> diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
> index dbe792b52c5c..a644787fa9e1 100644
> --- a/tools/perf/builtin-script.c
> +++ b/tools/perf/builtin-script.c
> @@ -1241,10 +1241,11 @@ static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en,
> }
>
> if (PRINT_FIELD(BRCNTR)) {
> - unsigned int width = evsel__env(evsel)->br_cntr_width;
> - unsigned int i = 0, j, num, mask = (1L << width) - 1;
> struct evsel *pos = evsel__leader(evsel);
> + unsigned int i = 0, j, num, mask, width;
>
> + perf_env__find_br_cntr_info(evsel__env(evsel), NULL, &width);
> + mask = (1L << width) - 1;
> printed += fprintf(fp, "br_cntr: ");
> evlist__for_each_entry_from(evsel->evlist, pos) {
> if (!(pos->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS))
> diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
> index 4990c70b1794..c6ebde9d40a8 100644
> --- a/tools/perf/util/annotate.c
> +++ b/tools/perf/util/annotate.c
> @@ -333,14 +333,15 @@ static int symbol__account_br_cntr(struct annotated_branch *branch,
> {
> unsigned int br_cntr_nr = evsel__leader(evsel)->br_cntr_nr;
> unsigned int base = evsel__leader(evsel)->br_cntr_idx;
> - unsigned int width = evsel__env(evsel)->br_cntr_width;
> unsigned int off = offset * evsel->evlist->nr_br_cntr;
> - unsigned int i, mask = (1L << width) - 1;
> u64 *branch_br_cntr = branch->br_cntr;
> + unsigned int i, mask, width;
>
> if (!br_cntr || !branch_br_cntr)
> return 0;
>
> + perf_env__find_br_cntr_info(evsel__env(evsel), NULL, &width);
> + mask = (1L << width) - 1;
> for (i = 0; i < br_cntr_nr; i++) {
> u64 cntr = (br_cntr >> i * width) & mask;
>
> diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
> index a459374d0a1a..1edbccfc3281 100644
> --- a/tools/perf/util/env.c
> +++ b/tools/perf/util/env.c
> @@ -624,3 +624,18 @@ char *perf_env__find_pmu_cap(struct perf_env *env, const char *pmu_name,
> free(cap_eq);
> return NULL;
> }
> +
> +void perf_env__find_br_cntr_info(struct perf_env *env,
> + unsigned int *nr,
> + unsigned int *width)
> +{
> + if (nr) {
> + *nr = env->cpu_pmu_caps ? env->br_cntr_nr :
> + env->pmu_caps->br_cntr_nr;
> + }
> +
> + if (width) {
> + *width = env->cpu_pmu_caps ? env->br_cntr_width :
> + env->pmu_caps->br_cntr_width;
> + }
> +}
> diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
> index 2a2c37cc40b7..51b36c36019b 100644
> --- a/tools/perf/util/env.h
> +++ b/tools/perf/util/env.h
> @@ -192,4 +192,7 @@ char *perf_env__find_pmu_cap(struct perf_env *env, const char *pmu_name,
> const char *cap);
>
> bool perf_env__has_pmu_mapping(struct perf_env *env, const char *pmu_name);
> +void perf_env__find_br_cntr_info(struct perf_env *env,
> + unsigned int *nr,
> + unsigned int *width);
> #endif /* __PERF_ENV_H */
> diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
> index b492300ec959..dbaf07bf6c5f 100644
> --- a/tools/perf/util/session.c
> +++ b/tools/perf/util/session.c
> @@ -856,7 +856,6 @@ static void branch_stack__printf(struct perf_sample *sample,
> struct branch_entry *entries = perf_sample__branch_entries(sample);
> bool callstack = evsel__has_branch_callstack(evsel);
> u64 *branch_stack_cntr = sample->branch_stack_cntr;
> - struct perf_env *env = evsel__env(evsel);
> uint64_t i;
>
> if (!callstack) {
> @@ -900,8 +899,11 @@ static void branch_stack__printf(struct perf_sample *sample,
> }
>
> if (branch_stack_cntr) {
> + unsigned int br_cntr_width, br_cntr_nr;
> +
> + perf_env__find_br_cntr_info(evsel__env(evsel), &br_cntr_nr, &br_cntr_width);
> printf("... branch stack counters: nr:%" PRIu64 " (counter width: %u max counter nr:%u)\n",
> - sample->branch_stack->nr, env->br_cntr_width, env->br_cntr_nr);
> + sample->branch_stack->nr, br_cntr_width, br_cntr_nr);
> for (i = 0; i < sample->branch_stack->nr; i++)
> printf("..... %2"PRIu64": %016" PRIx64 "\n", i, branch_stack_cntr[i]);
> }
> --
> 2.38.1
>