perf diff: Support hot streams comparison

This patch enables perf-diff with "--stream" option.

"--stream": Enable hot streams comparison

Now let's see example.

perf record -b ... Generate perf.data.old with branch data
perf record -b ... Generate perf.data with branch data
perf diff --stream

[ Matched hot streams ]

hot chain pair 1:
cycles: 1, hits: 27.77% cycles: 1, hits: 9.24%
--------------------------- --------------------------
main div.c:39 main div.c:39
main div.c:44 main div.c:44

hot chain pair 2:
cycles: 34, hits: 20.06% cycles: 27, hits: 16.98%
--------------------------- --------------------------
__random_r random_r.c:360 __random_r random_r.c:360
__random_r random_r.c:388 __random_r random_r.c:388
__random_r random_r.c:388 __random_r random_r.c:388
__random_r random_r.c:380 __random_r random_r.c:380
__random_r random_r.c:357 __random_r random_r.c:357
__random random.c:293 __random random.c:293
__random random.c:293 __random random.c:293
__random random.c:291 __random random.c:291
__random random.c:291 __random random.c:291
__random random.c:291 __random random.c:291
__random random.c:288 __random random.c:288
rand rand.c:27 rand rand.c:27
rand rand.c:26 rand rand.c:26
rand@plt rand@plt
rand@plt rand@plt
compute_flag div.c:25 compute_flag div.c:25
compute_flag div.c:22 compute_flag div.c:22
main div.c:40 main div.c:40
main div.c:40 main div.c:40
main div.c:39 main div.c:39

hot chain pair 3:
cycles: 9, hits: 4.48% cycles: 6, hits: 4.51%
--------------------------- --------------------------
__random_r random_r.c:360 __random_r random_r.c:360
__random_r random_r.c:388 __random_r random_r.c:388
__random_r random_r.c:388 __random_r random_r.c:388
__random_r random_r.c:380 __random_r random_r.c:380

[ Hot streams in old perf data only ]

hot chain 1:
cycles: 18, hits: 6.75%
--------------------------
__random_r random_r.c:360
__random_r random_r.c:388
__random_r random_r.c:388
__random_r random_r.c:380
__random_r random_r.c:357
__random random.c:293
__random random.c:293
__random random.c:291
__random random.c:291
__random random.c:291
__random random.c:288
rand rand.c:27
rand rand.c:26
rand@plt
rand@plt
compute_flag div.c:25
compute_flag div.c:22
main div.c:40

hot chain 2:
cycles: 29, hits: 2.78%
--------------------------
compute_flag div.c:22
main div.c:40
main div.c:40
main div.c:39

[ Hot streams in new perf data only ]

hot chain 1:
cycles: 4, hits: 4.54%
--------------------------
main div.c:42
compute_flag div.c:28

hot chain 2:
cycles: 5, hits: 3.51%
--------------------------
main div.c:39
main div.c:44
main div.c:42
compute_flag div.c:28

Signed-off-by: Jin Yao <[e-mail]>
Acked-by: Jiri Olsa <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>

tools/perf/Documentation/perf-diff.txt

···
 --tid=::
 	Only diff samples for given thread ID (comma separated list).
 
+--stream::
+	Enable hot streams comparison. Stream can be a callchain which is
+	aggregated by the branch records from samples.
+
 COMPARISON
 ----------
 The comparison is governed by the baseline file. The baseline perf.data

tools/perf/builtin-diff.c

···
 #include "util/map.h"
 #include "util/spark.h"
 #include "util/block-info.h"
+#include "util/stream.h"
 #include <linux/err.h>
 #include <linux/zalloc.h>
 #include <subcmd/pager.h>
···
 	int				 range_size;
 	int				 range_num;
 	bool				 has_br_stack;
+	bool				 stream;
 };
 
 /* Diff command specific HPP columns. */
···
 	struct perf_data	 data;
 	int			 idx;
 	struct hists		*hists;
+	struct evlist_streams	*evlist_streams;
 	struct diff_hpp_fmt	 fmt[PERF_HPP_DIFF__MAX_INDEX];
 };
 
···
 	COMPUTE_DELTA_ABS,
 	COMPUTE_CYCLES,
 	COMPUTE_MAX,
+	COMPUTE_STREAM,	/* After COMPUTE_MAX to avoid use current compute arrays */
 };
 
 const char *compute_names[COMPUTE_MAX] = {
···
 	struct perf_diff *pdiff = container_of(tool, struct perf_diff, tool);
 	struct addr_location al;
 	struct hists *hists = evsel__hists(evsel);
+	struct hist_entry_iter iter = {
+		.evsel	= evsel,
+		.sample	= sample,
+		.ops	= &hist_iter_normal,
+	};
 	int ret = -1;
 
 	if (perf_time__ranges_skip_sample(pdiff->ptime_range, pdiff->range_num,
···
 		goto out_put;
 	}
 
-	if (compute != COMPUTE_CYCLES) {
-		if (!hists__add_entry(hists, &al, NULL, NULL, NULL, sample,
-				      true)) {
-			pr_warning("problem incrementing symbol period, "
-				   "skipping event\n");
-			goto out_put;
-		}
-	} else {
+	switch (compute) {
+	case COMPUTE_CYCLES:
 		if (!hists__add_entry_ops(hists, &block_hist_ops, &al, NULL,
 					  NULL, NULL, sample, true)) {
 			pr_warning("problem incrementing symbol period, "
···
 
 		hist__account_cycles(sample->branch_stack, &al, sample, false,
 				     NULL);
+		break;
+
+	case COMPUTE_STREAM:
+		if (hist_entry_iter__add(&iter, &al, PERF_MAX_STACK_DEPTH,
+					 NULL)) {
+			pr_debug("problem adding hist entry, skipping event\n");
+			goto out_put;
+		}
+		break;
+
+	default:
+		if (!hists__add_entry(hists, &al, NULL, NULL, NULL, sample,
+				      true)) {
+			pr_warning("problem incrementing symbol period, "
+				   "skipping event\n");
+			goto out_put;
+		}
 	}
 
 	/*
···
 	}
 }
 
+static int process_base_stream(struct data__file *data_base,
+			       struct data__file *data_pair,
+			       const char *title __maybe_unused)
+{
+	struct evlist *evlist_base = data_base->session->evlist;
+	struct evlist *evlist_pair = data_pair->session->evlist;
+	struct evsel *evsel_base, *evsel_pair;
+	struct evsel_streams *es_base, *es_pair;
+
+	evlist__for_each_entry(evlist_base, evsel_base) {
+		evsel_pair = evsel_match(evsel_base, evlist_pair);
+		if (!evsel_pair)
+			continue;
+
+		es_base = evsel_streams__entry(data_base->evlist_streams,
+					       evsel_base->idx);
+		if (!es_base)
+			return -1;
+
+		es_pair = evsel_streams__entry(data_pair->evlist_streams,
+					       evsel_pair->idx);
+		if (!es_pair)
+			return -1;
+
+		evsel_streams__match(es_base, es_pair);
+		evsel_streams__report(es_base, es_pair);
+	}
+
+	return 0;
+}
+
+static void stream_process(void)
+{
+	/*
+	 * Stream comparison only supports two data files.
+	 * perf.data.old and perf.data. data__files[0] is perf.data.old,
+	 * data__files[1] is perf.data.
+	 */
+	process_base_stream(&data__files[0], &data__files[1],
+			    "# Output based on old perf data:\n#\n");
+}
+
 static void data__free(struct data__file *d)
 {
 	int col;
+
+	if (d->evlist_streams)
+		evlist_streams__delete(d->evlist_streams);
 
 	for (col = 0; col < PERF_HPP_DIFF__MAX_INDEX; col++) {
 		struct diff_hpp_fmt *fmt = &d->fmt[col];
···
 
 		if (pdiff.ptime_range)
 			zfree(&pdiff.ptime_range);
+
+		if (compute == COMPUTE_STREAM) {
+			d->evlist_streams = evlist__create_streams(
+						d->session->evlist, 5);
+			if (!d->evlist_streams)
+				goto out_delete;
+		}
 	}
 
-	data_process();
+	if (compute == COMPUTE_STREAM)
+		stream_process();
+	else
+		data_process();
 
  out_delete:
 	data__for_each_file(i, d) {
···
 		   "only consider symbols in these pids"),
 	OPT_STRING(0, "tid", &symbol_conf.tid_list_str, "tid[,tid...]",
 		   "only consider symbols in these tids"),
+	OPT_BOOLEAN(0, "stream", &pdiff.stream,
+		    "Enable hot streams comparison."),
 	OPT_END()
 };
 
···
 	if (cycles_hist && (compute != COMPUTE_CYCLES))
 		usage_with_options(diff_usage, options);
 
+	if (pdiff.stream)
+		compute = COMPUTE_STREAM;
+
 	symbol__annotation_init();
 
 	if (symbol__init(NULL) < 0)
···
 	if (check_file_brstack() < 0)
 		return -1;
 
-	if (compute == COMPUTE_CYCLES && !pdiff.has_br_stack)
+	if ((compute == COMPUTE_CYCLES || compute == COMPUTE_STREAM)
+	    && !pdiff.has_br_stack) {
 		return -1;
+	}
 
-	if (ui_init() < 0)
-		return -1;
+	if (compute == COMPUTE_STREAM) {
+		symbol_conf.show_branchflag_count = true;
+		symbol_conf.disable_add2line_warn = true;
+		callchain_param.mode = CHAIN_FLAT;
+		callchain_param.key = CCKEY_SRCLINE;
+		callchain_param.branch_callstack = 1;
+		symbol_conf.use_callchain = true;
+		callchain_register_param(&callchain_param);
+		sort_order = "srcline,symbol,dso";
+	} else {
+		if (ui_init() < 0)
+			return -1;
 
-	sort__mode = SORT_MODE__DIFF;
+		sort__mode = SORT_MODE__DIFF;
+	}
 
 	if (setup_sorting(NULL) < 0)
 		usage_with_options(diff_usage, options);