perf tools: Add branch counter knob

Add a new branch filter, "counter", for the branch counter option. It is
used to mark the events which should be logged in the branch. If it is
applied with the -j option, the counters of all the events should be
logged in the branch. If the legacy kernel doesn't support the new
branch sample type, switching off the branch counter filter.

The stored counter values in each branch are displayed right after the
regular branch stack information via perf report -D.

Usage examples:

# perf record -e "{branch-instructions,branch-misses}:S" -j any,counter

Only the first event, branch-instructions, collect the LBR. Both
branch-instructions and branch-misses are marked as logged events. The
occurrences information of them can be found in the branch stack
extension space of each branch.

# perf record -e "{cpu/branch-instructions,branch_type=any/,cpu/branch-misses,branch_type=counter/}"

Only the first event, branch-instructions, collect the LBR. Only the
branch-misses event is marked as a logged event.

Committer notes:

I noticed 'perf test "Sample parsing"' failing, reported to the list and
Kan provided a patch that checks if the evsel has a leader and that
evsel->evlist is set, the comment in the source code further explains
it.

Reviewed-by: Ian Rogers <[e-mail]>
Signed-off-by: Kan Liang <[e-mail]>
Cc: Adrian Hunter <[e-mail]>
Cc: Alexander Shishkin <[e-mail]>
Cc: Alexey Bayduraev <[e-mail]>
Cc: Andi Kleen <[e-mail]>
Cc: Ingo Molnar <[e-mail]>
Cc: Jiri Olsa <[e-mail]>
Cc: Mark Rutland <[e-mail]>
Cc: Namhyung Kim <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Stephane Eranian <[e-mail]>
Cc: Tinghao Zhang <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>

tools/perf/Documentation/perf-record.txt

···
 		     4th-Gen Xeon+ server), the save branch type is unconditionally enabled
 		     when the taken branch stack sampling is enabled.
 	- priv: save privilege state during sampling in case binary is not available later
+	- counter: save occurrences of the event since the last branch entry. Currently, the
+		   feature is only supported by a newer CPU, e.g., Intel Sierra Forest and
+		   later platforms. An error out is expected if it's used on the unsupported
+		   kernel or CPUs.
 
 +
 The option requires at least one branch type among any, any_call, any_ret, ind_call, cond.

tools/perf/util/evsel.c

···
 
 static void evsel__disable_missing_features(struct evsel *evsel)
 {
+	if (perf_missing_features.branch_counters)
+		evsel->core.attr.branch_sample_type &= ~PERF_SAMPLE_BRANCH_COUNTERS;
 	if (perf_missing_features.read_lost)
 		evsel->core.attr.read_format &= ~PERF_FORMAT_LOST;
 	if (perf_missing_features.weight_struct) {
···
 	 * Must probe features in the order they were added to the
 	 * perf_event_attr interface.
 	 */
-	if (!perf_missing_features.read_lost &&
+	if (!perf_missing_features.branch_counters &&
+	    (evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS)) {
+		perf_missing_features.branch_counters = true;
+		pr_debug2("switching off branch counters support\n");
+		return true;
+	} else if (!perf_missing_features.read_lost &&
 	    (evsel->core.attr.read_format & PERF_FORMAT_LOST)) {
 		perf_missing_features.read_lost = true;
 		pr_debug2("switching off PERF_FORMAT_LOST support\n");
···
 	return new_val;
 }
 
+static inline bool evsel__has_branch_counters(const struct evsel *evsel)
+{
+	struct evsel *cur, *leader = evsel__leader(evsel);
+
+	/* The branch counters feature only supports group */
+	if (!leader || !evsel->evlist)
+		return false;
+
+	evlist__for_each_entry(evsel->evlist, cur) {
+		if ((leader == evsel__leader(cur)) &&
+		    (cur->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS))
+			return true;
+	}
+	return false;
+}
+
 int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 			struct perf_sample *data)
 {
···
 
 		OVERFLOW_CHECK(array, sz, max_size);
 		array = (void *)array + sz;
+
+		if (evsel__has_branch_counters(evsel)) {
+			OVERFLOW_CHECK_u64(array);
+
+			data->branch_stack_cntr = (u64 *)array;
+			sz = data->branch_stack->nr * sizeof(u64);
+
+			OVERFLOW_CHECK(array, sz, max_size);
+			array = (void *)array + sz;
+		}
 	}
 
 	if (type & PERF_SAMPLE_REGS_USER) {

tools/perf/util/evsel.h

···
 	bool code_page_size;
 	bool weight_struct;
 	bool read_lost;
+	bool branch_counters;
 };
 
 extern struct perf_missing_features perf_missing_features;

tools/perf/util/parse-branch-options.c

···
 	BRANCH_OPT("stack", PERF_SAMPLE_BRANCH_CALL_STACK),
 	BRANCH_OPT("hw_index", PERF_SAMPLE_BRANCH_HW_INDEX),
 	BRANCH_OPT("priv", PERF_SAMPLE_BRANCH_PRIV_SAVE),
+	BRANCH_OPT("counter", PERF_SAMPLE_BRANCH_COUNTERS),
 	BRANCH_END
 };
 

tools/perf/util/perf_event_attr_fprintf.c

···
 		bit_name(COND), bit_name(CALL_STACK), bit_name(IND_JUMP),
 		bit_name(CALL), bit_name(NO_FLAGS), bit_name(NO_CYCLES),
 		bit_name(TYPE_SAVE), bit_name(HW_INDEX), bit_name(PRIV_SAVE),
+		bit_name(COUNTERS),
 		{ .name = NULL, }
 	};
 #undef bit_name

tools/perf/util/sample.h

···
 	void *raw_data;
 	struct ip_callchain *callchain;
 	struct branch_stack *branch_stack;
+	u64 *branch_stack_cntr;
 	struct regs_dump  user_regs;
 	struct regs_dump  intr_regs;
 	struct stack_dump user_stack;

tools/perf/util/session.c

···
 		       i, callchain->ips[i]);
 }
 
-static void branch_stack__printf(struct perf_sample *sample, bool callstack)
+static void branch_stack__printf(struct perf_sample *sample,
+				 struct evsel *evsel)
 {
 	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) {
···
 				printf("..... %2"PRIu64": %016" PRIx64 "\n", i+1, e->from);
 			}
 		}
+	}
+
+	if (branch_stack_cntr) {
+		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);
+		for (i = 0; i < sample->branch_stack->nr; i++)
+			printf("..... %2"PRIu64": %016" PRIx64 "\n", i, branch_stack_cntr[i]);
 	}
 }
 
···
 		callchain__printf(evsel, sample);
 
 	if (evsel__has_br_stack(evsel))
-		branch_stack__printf(sample, evsel__has_branch_callstack(evsel));
+		branch_stack__printf(sample, evsel);
 
 	if (sample_type & PERF_SAMPLE_REGS_USER)
 		regs_user__printf(sample, arch);