Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/jolsa/perf into perf/core

Pull perf/core improvements and fixes from Jiri Olsa:

  * Factor hists statistics counts processing which in turn also
    fixes several bugs in TUI report command (Namhyung Kim)

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

tools/perf/builtin-annotate.c

@@ -46,7 +46,7 @@ struct perf_annotate {
 };
 
 static int perf_evsel__add_sample(struct perf_evsel *evsel,
-				  struct perf_sample *sample,
+				  struct perf_sample *sample __maybe_unused,
 				  struct addr_location *al,
 				  struct perf_annotate *ann)
 {
@@ -70,7 +70,6 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
 		return -ENOMEM;
 
 	ret = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-	evsel->hists.stats.total_period += sample->period;
 	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
 	return ret;
 }

tools/perf/builtin-diff.c

@@ -341,11 +341,16 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
 		return -1;
 	}
 
-	if (al.filtered == 0) {
-		evsel->hists.stats.total_non_filtered_period += sample->period;
-		evsel->hists.nr_non_filtered_entries++;
-	}
+	/*
+	 * The total_period is updated here before going to the output
+	 * tree since normally only the baseline hists will call
+	 * hists__output_resort() and precompute needs the total
+	 * period in order to sort entries by percentage delta.
+	 */
 	evsel->hists.stats.total_period += sample->period;
+	if (!al.filtered)
+		evsel->hists.stats.total_non_filtered_period += sample->period;
+
 	return 0;
 }
 
@@ -573,10 +578,7 @@ static void hists__compute_resort(struct hists *hists)
 	hists->entries = RB_ROOT;
 	next = rb_first(root);
 
-	hists->nr_entries = 0;
-	hists->nr_non_filtered_entries = 0;
-	hists->stats.total_period = 0;
-	hists->stats.total_non_filtered_period = 0;
+	hists__reset_stats(hists);
 	hists__reset_col_len(hists);
 
 	while (next != NULL) {
@@ -586,7 +588,10 @@ static void hists__compute_resort(struct hists *hists)
 		next = rb_next(&he->rb_node_in);
 
 		insert_hist_entry_by_compute(&hists->entries, he, compute);
-		hists__inc_nr_entries(hists, he);
+		hists__inc_stats(hists, he);
+
+		if (!he->filtered)
+			hists__calc_col_len(hists, he);
 	}
 }
 

tools/perf/builtin-report.c

@@ -57,6 +57,7 @@ struct report {
 	const char		*cpu_list;
 	const char		*symbol_filter_str;
 	float			min_percent;
+	u64			nr_entries;
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
@@ -75,6 +76,27 @@ static int report__config(const char *var, const char *value, void *cb)
 	return perf_default_config(var, value, cb);
 }
 
+static void report__inc_stats(struct report *rep, struct hist_entry *he)
+{
+	/*
+	 * The @he is either of a newly created one or an existing one
+	 * merging current sample.  We only want to count a new one so
+	 * checking ->nr_events being 1.
+	 */
+	if (he->stat.nr_events == 1)
+		rep->nr_entries++;
+
+	/*
+	 * Only counts number of samples at this stage as it's more
+	 * natural to do it here and non-sample events are also
+	 * counted in perf_session_deliver_event().  The dump_trace
+	 * requires this info is ready before going to the output tree.
+	 */
+	hists__inc_nr_events(he->hists, PERF_RECORD_SAMPLE);
+	if (!he->filtered)
+		he->hists->stats.nr_non_filtered_samples++;
+}
+
 static int report__add_mem_hist_entry(struct report *rep, struct addr_location *al,
 				      struct perf_sample *sample, struct perf_evsel *evsel)
 {
@@ -121,10 +143,8 @@ static int report__add_mem_hist_entry(struct report *rep, struct addr_location *
 			goto out;
 	}
 
-	evsel->hists.stats.total_period += cost;
-	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
-	if (!he->filtered)
-		evsel->hists.stats.nr_non_filtered_samples++;
+	report__inc_stats(rep, he);
+
 	err = hist_entry__append_callchain(he, sample);
 out:
 	return err;
@@ -175,11 +195,7 @@ static int report__add_branch_hist_entry(struct report *rep, struct addr_locatio
 				if (err)
 					goto out;
 			}
-
-			evsel->hists.stats.total_period += 1;
-			hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
-			if (!he->filtered)
-				evsel->hists.stats.nr_non_filtered_samples++;
+			report__inc_stats(rep, he);
 		} else
 			goto out;
 	}
@@ -212,10 +228,8 @@ static int report__add_hist_entry(struct report *rep, struct perf_evsel *evsel,
 	if (ui__has_annotation())
 		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
 
-	evsel->hists.stats.total_period += sample->period;
-	if (!he->filtered)
-		evsel->hists.stats.nr_non_filtered_samples++;
-	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+	report__inc_stats(rep, he);
+
 out:
 	return err;
 }
@@ -486,24 +500,12 @@ static int report__browse_hists(struct report *rep)
 	return ret;
 }
 
-static u64 report__collapse_hists(struct report *rep)
+static void report__collapse_hists(struct report *rep)
 {
 	struct ui_progress prog;
 	struct perf_evsel *pos;
-	u64 nr_samples = 0;
-	/*
- 	 * Count number of histogram entries to use when showing progress,
- 	 * reusing nr_samples variable.
- 	 */
-	evlist__for_each(rep->session->evlist, pos)
-		nr_samples += pos->hists.nr_entries;
 
-	ui_progress__init(&prog, nr_samples, "Merging related events...");
-	/*
-	 * Count total number of samples, will be used to check if this
- 	 * session had any.
- 	 */
-	nr_samples = 0;
+	ui_progress__init(&prog, rep->nr_entries, "Merging related events...");
 
 	evlist__for_each(rep->session->evlist, pos) {
 		struct hists *hists = &pos->hists;
@@ -512,7 +514,6 @@ static u64 report__collapse_hists(struct report *rep)
 			hists->symbol_filter_str = rep->symbol_filter_str;
 
 		hists__collapse_resort(hists, &prog);
-		nr_samples += hists->stats.nr_events[PERF_RECORD_SAMPLE];
 
 		/* Non-group events are considered as leader */
 		if (symbol_conf.event_group &&
@@ -525,14 +526,11 @@ static u64 report__collapse_hists(struct report *rep)
 	}
 
 	ui_progress__finish();
-
-	return nr_samples;
 }
 
 static int __cmd_report(struct report *rep)
 {
 	int ret;
-	u64 nr_samples;
 	struct perf_session *session = rep->session;
 	struct perf_evsel *pos;
 	struct perf_data_file *file = session->file;
@@ -572,12 +570,12 @@ static int __cmd_report(struct report *rep)
 		}
 	}
 
-	nr_samples = report__collapse_hists(rep);
+	report__collapse_hists(rep);
 
 	if (session_done())
 		return 0;
 
-	if (nr_samples == 0) {
+	if (rep->nr_entries == 0) {
 		ui__error("The %s file has no samples!\n", file->path);
 		return 0;
 	}

tools/perf/ui/browsers/hists.c

@@ -26,13 +26,36 @@ struct hist_browser {
 	int		     print_seq;
 	bool		     show_dso;
 	float		     min_pcnt;
-	u64		     nr_pcnt_entries;
+	u64		     nr_non_filtered_entries;
+	u64		     nr_callchain_rows;
 };
 
 extern void hist_browser__init_hpp(void);
 
 static int hists__browser_title(struct hists *hists, char *bf, size_t size,
 				const char *ev_name);
+static void hist_browser__update_nr_entries(struct hist_browser *hb);
+
+static struct rb_node *hists__filter_entries(struct rb_node *nd,
+					     struct hists *hists,
+					     float min_pcnt);
+
+static bool hist_browser__has_filter(struct hist_browser *hb)
+{
+	return hists__has_filter(hb->hists) || hb->min_pcnt;
+}
+
+static u32 hist_browser__nr_entries(struct hist_browser *hb)
+{
+	u32 nr_entries;
+
+	if (hist_browser__has_filter(hb))
+		nr_entries = hb->nr_non_filtered_entries;
+	else
+		nr_entries = hb->hists->nr_entries;
+
+	return nr_entries + hb->nr_callchain_rows;
+}
 
 static void hist_browser__refresh_dimensions(struct hist_browser *browser)
 {
@@ -43,7 +66,14 @@ static void hist_browser__refresh_dimensions(struct hist_browser *browser)
 
 static void hist_browser__reset(struct hist_browser *browser)
 {
-	browser->b.nr_entries = browser->hists->nr_entries;
+	/*
+	 * The hists__remove_entry_filter() already folds non-filtered
+	 * entries so we can assume it has 0 callchain rows.
+	 */
+	browser->nr_callchain_rows = 0;
+
+	hist_browser__update_nr_entries(browser);
+	browser->b.nr_entries = hist_browser__nr_entries(browser);
 	hist_browser__refresh_dimensions(browser);
 	ui_browser__reset_index(&browser->b);
 }
@@ -198,14 +228,16 @@ static bool hist_browser__toggle_fold(struct hist_browser *browser)
 		struct hist_entry *he = browser->he_selection;
 
 		hist_entry__init_have_children(he);
-		browser->hists->nr_entries -= he->nr_rows;
+		browser->b.nr_entries -= he->nr_rows;
+		browser->nr_callchain_rows -= he->nr_rows;
 
 		if (he->ms.unfolded)
 			he->nr_rows = callchain__count_rows(&he->sorted_chain);
 		else
 			he->nr_rows = 0;
-		browser->hists->nr_entries += he->nr_rows;
-		browser->b.nr_entries = browser->hists->nr_entries;
+
+		browser->b.nr_entries += he->nr_rows;
+		browser->nr_callchain_rows += he->nr_rows;
 
 		return true;
 	}
@@ -280,23 +312,27 @@ static void hist_entry__set_folding(struct hist_entry *he, bool unfold)
 		he->nr_rows = 0;
 }
 
-static void hists__set_folding(struct hists *hists, bool unfold)
+static void
+__hist_browser__set_folding(struct hist_browser *browser, bool unfold)
 {
 	struct rb_node *nd;
+	struct hists *hists = browser->hists;
 
-	hists->nr_entries = 0;
-
-	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&hists->entries);
+	     (nd = hists__filter_entries(nd, hists, browser->min_pcnt)) != NULL;
+	     nd = rb_next(nd)) {
 		struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
 		hist_entry__set_folding(he, unfold);
-		hists->nr_entries += 1 + he->nr_rows;
+		browser->nr_callchain_rows += he->nr_rows;
 	}
 }
 
 static void hist_browser__set_folding(struct hist_browser *browser, bool unfold)
 {
-	hists__set_folding(browser->hists, unfold);
-	browser->b.nr_entries = browser->hists->nr_entries;
+	browser->nr_callchain_rows = 0;
+	__hist_browser__set_folding(browser, unfold);
+
+	browser->b.nr_entries = hist_browser__nr_entries(browser);
 	/* Go to the start, we may be way after valid entries after a collapse */
 	ui_browser__reset_index(&browser->b);
 }
@@ -310,8 +346,6 @@ static void ui_browser__warn_lost_events(struct ui_browser *browser)
 		"Or reduce the sampling frequency.");
 }
 
-static void hist_browser__update_pcnt_entries(struct hist_browser *hb);
-
 static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
 			     struct hist_browser_timer *hbt)
 {
@@ -320,9 +354,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
 	int delay_secs = hbt ? hbt->refresh : 0;
 
 	browser->b.entries = &browser->hists->entries;
-	browser->b.nr_entries = browser->hists->nr_entries;
-	if (browser->min_pcnt)
-		browser->b.nr_entries = browser->nr_pcnt_entries;
+	browser->b.nr_entries = hist_browser__nr_entries(browser);
 
 	hist_browser__refresh_dimensions(browser);
 	hists__browser_title(browser->hists, title, sizeof(title), ev_name);
@@ -339,13 +371,10 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
 			u64 nr_entries;
 			hbt->timer(hbt->arg);
 
-			if (browser->min_pcnt) {
-				hist_browser__update_pcnt_entries(browser);
-				nr_entries = browser->nr_pcnt_entries;
-			} else {
-				nr_entries = browser->hists->nr_entries;
-			}
+			if (hist_browser__has_filter(browser))
+				hist_browser__update_nr_entries(browser);
 
+			nr_entries = hist_browser__nr_entries(browser);
 			ui_browser__update_nr_entries(&browser->b, nr_entries);
 
 			if (browser->hists->stats.nr_lost_warned !=
@@ -1343,18 +1372,23 @@ close_file_and_continue:
 	return ret;
 }
 
-static void hist_browser__update_pcnt_entries(struct hist_browser *hb)
+static void hist_browser__update_nr_entries(struct hist_browser *hb)
 {
 	u64 nr_entries = 0;
 	struct rb_node *nd = rb_first(&hb->hists->entries);
 
-	while (nd) {
+	if (hb->min_pcnt == 0) {
+		hb->nr_non_filtered_entries = hb->hists->nr_non_filtered_entries;
+		return;
+	}
+
+	while ((nd = hists__filter_entries(nd, hb->hists,
+					   hb->min_pcnt)) != NULL) {
 		nr_entries++;
-		nd = hists__filter_entries(rb_next(nd), hb->hists,
-					   hb->min_pcnt);
+		nd = rb_next(nd);
 	}
 
-	hb->nr_pcnt_entries = nr_entries;
+	hb->nr_non_filtered_entries = nr_entries;
 }
 
 static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
@@ -1411,7 +1445,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 
 	if (min_pcnt) {
 		browser->min_pcnt = min_pcnt;
-		hist_browser__update_pcnt_entries(browser);
+		hist_browser__update_nr_entries(browser);
 	}
 
 	fstack = pstack__new(2);

tools/perf/util/hist.c

@@ -225,14 +225,18 @@ static void he_stat__decay(struct he_stat *he_stat)
 static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
 {
 	u64 prev_period = he->stat.period;
+	u64 diff;
 
 	if (prev_period == 0)
 		return true;
 
 	he_stat__decay(&he->stat);
 
+	diff = prev_period - he->stat.period;
+
+	hists->stats.total_period -= diff;
 	if (!he->filtered)
-		hists->stats.total_period -= prev_period - he->stat.period;
+		hists->stats.total_non_filtered_period -= diff;
 
 	return he->stat.period == 0;
 }
@@ -259,8 +263,11 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
 			if (sort__need_collapse)
 				rb_erase(&n->rb_node_in, &hists->entries_collapsed);
 
-			hist_entry__free(n);
 			--hists->nr_entries;
+			if (!n->filtered)
+				--hists->nr_non_filtered_entries;
+
+			hist_entry__free(n);
 		}
 	}
 }
@@ -317,17 +324,6 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template)
 	return he;
 }
 
-void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h)
-{
-	if (!h->filtered) {
-		hists__calc_col_len(hists, h);
-		hists->nr_non_filtered_entries++;
-		hists->stats.total_non_filtered_period += h->stat.period;
-	}
-	hists->nr_entries++;
-	hists->stats.total_period += h->stat.period;
-}
-
 static u8 symbol__parent_filter(const struct symbol *parent)
 {
 	if (symbol_conf.exclude_other && parent == NULL)
@@ -393,7 +389,6 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
 	if (!he)
 		return NULL;
 
-	hists->nr_entries++;
 	rb_link_node(&he->rb_node_in, parent, p);
 	rb_insert_color(&he->rb_node_in, hists->entries_in);
 out:
@@ -633,6 +628,35 @@ out:
 	return ret;
 }
 
+static void hists__reset_filter_stats(struct hists *hists)
+{
+	hists->nr_non_filtered_entries = 0;
+	hists->stats.total_non_filtered_period = 0;
+}
+
+void hists__reset_stats(struct hists *hists)
+{
+	hists->nr_entries = 0;
+	hists->stats.total_period = 0;
+
+	hists__reset_filter_stats(hists);
+}
+
+static void hists__inc_filter_stats(struct hists *hists, struct hist_entry *h)
+{
+	hists->nr_non_filtered_entries++;
+	hists->stats.total_non_filtered_period += h->stat.period;
+}
+
+void hists__inc_stats(struct hists *hists, struct hist_entry *h)
+{
+	if (!h->filtered)
+		hists__inc_filter_stats(hists, h);
+
+	hists->nr_entries++;
+	hists->stats.total_period += h->stat.period;
+}
+
 static void __hists__insert_output_entry(struct rb_root *entries,
 					 struct hist_entry *he,
 					 u64 min_callchain_hits)
@@ -676,9 +700,7 @@ void hists__output_resort(struct hists *hists)
 	next = rb_first(root);
 	hists->entries = RB_ROOT;
 
-	hists->nr_non_filtered_entries = 0;
-	hists->stats.total_period = 0;
-	hists->stats.total_non_filtered_period = 0;
+	hists__reset_stats(hists);
 	hists__reset_col_len(hists);
 
 	while (next) {
@@ -686,7 +708,10 @@ void hists__output_resort(struct hists *hists)
 		next = rb_next(&n->rb_node_in);
 
 		__hists__insert_output_entry(&hists->entries, n, min_callchain_hits);
-		hists__inc_nr_entries(hists, n);
+		hists__inc_stats(hists, n);
+
+		if (!n->filtered)
+			hists__calc_col_len(hists, n);
 	}
 }
 
@@ -697,13 +722,13 @@ static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h
 	if (h->filtered)
 		return;
 
-	++hists->nr_non_filtered_entries;
-	if (h->ms.unfolded)
-		hists->nr_non_filtered_entries += h->nr_rows;
+	/* force fold unfiltered entry for simplicity */
+	h->ms.unfolded = false;
 	h->row_offset = 0;
-	hists->stats.total_non_filtered_period += h->stat.period;
+
 	hists->stats.nr_non_filtered_samples += h->stat.nr_events;
 
+	hists__inc_filter_stats(hists, h);
 	hists__calc_col_len(hists, h);
 }
 
@@ -724,9 +749,9 @@ void hists__filter_by_dso(struct hists *hists)
 {
 	struct rb_node *nd;
 
-	hists->nr_non_filtered_entries = 0;
-	hists->stats.total_non_filtered_period = 0;
 	hists->stats.nr_non_filtered_samples = 0;
+
+	hists__reset_filter_stats(hists);
 	hists__reset_col_len(hists);
 
 	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
@@ -758,9 +783,9 @@ void hists__filter_by_thread(struct hists *hists)
 {
 	struct rb_node *nd;
 
-	hists->nr_non_filtered_entries = 0;
-	hists->stats.total_non_filtered_period = 0;
 	hists->stats.nr_non_filtered_samples = 0;
+
+	hists__reset_filter_stats(hists);
 	hists__reset_col_len(hists);
 
 	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
@@ -790,9 +815,9 @@ void hists__filter_by_symbol(struct hists *hists)
 {
 	struct rb_node *nd;
 
-	hists->nr_non_filtered_entries = 0;
-	hists->stats.total_non_filtered_period = 0;
 	hists->stats.nr_non_filtered_samples = 0;
+
+	hists__reset_filter_stats(hists);
 	hists__reset_col_len(hists);
 
 	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
@@ -853,7 +878,7 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
 		he->hists = hists;
 		rb_link_node(&he->rb_node_in, parent, p);
 		rb_insert_color(&he->rb_node_in, root);
-		hists__inc_nr_entries(hists, he);
+		hists__inc_stats(hists, he);
 		he->dummy = true;
 	}
 out:

tools/perf/util/hist.h

@@ -116,7 +116,8 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
 void hists__output_recalc_col_len(struct hists *hists, int max_rows);
 
 u64 hists__total_period(struct hists *hists);
-void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h);
+void hists__reset_stats(struct hists *hists);
+void hists__inc_stats(struct hists *hists, struct hist_entry *h);
 void hists__inc_nr_events(struct hists *hists, u32 type);
 void events_stats__inc(struct events_stats *stats, u32 type);
 size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
@@ -128,6 +129,12 @@ void hists__filter_by_dso(struct hists *hists);
 void hists__filter_by_thread(struct hists *hists);
 void hists__filter_by_symbol(struct hists *hists);
 
+static inline bool hists__has_filter(struct hists *hists)
+{
+	return hists->thread_filter || hists->dso_filter ||
+		hists->symbol_filter_str;
+}
+
 u16 hists__col_len(struct hists *hists, enum hist_column col);
 void hists__set_col_len(struct hists *hists, enum hist_column col, u16 len);
 bool hists__new_col_len(struct hists *hists, enum hist_column col, u16 len);