perf env: Find correct branch counter info on hybrid

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.

Committer notes:

While testing I couldn't s ee those "Branch counter" columns enabled by
pressing 'B' on the TUI, after reporting it to the list Kan explained
the situation:

<quote Kan Liang>
For a hybrid client, the "Branch Counter" feature is only supported
starting from the just released Lunar Lake. Perf falls back to only
"ANY" on your Raptor Lake.

The "The branch counter is not available" message is expected.

Here is the 'perf evlist' result from my Lunar Lake machine,

  # perf evlist -v
  cpu_core/branch-instructions/pp: type: 4 (cpu_core), size: 136, config: 0xc4 (branch-instructions), { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|READ|PERIOD|BRANCH_STACK|IDENTIFIER, read_format: ID|GROUP|LOST, disabled: 1, freq: 1, enable_on_exec: 1, precise_ip: 2, sample_id_all: 1, exclude_guest: 1, branch_sample_type: ANY|COUNTERS
  #
</quote>

Fixes: 6f9d8d1de2 ("perf script: Add branch counters")
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20240909184201.553519-1-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

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))

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;
 

tools/perf/util/env.c

@@ -624,3 +624,18 @@ out:
 	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;
+	}
+}

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 */

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]);
 	}