Merge tag 'perf-core-for-mingo-3' of...

Merge tag 'perf-core-for-mingo-3' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core callchain fixes and improvements from Arnaldo Carvalho de Melo <acme@redhat.com:

User visible changes:

  - Make --percent-limit apply to callchains also and fix some bugs
    related to --percent-limit (Namhyung Kim)
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: NIngo Molnar <mingo@kernel.org>

tools/perf/builtin-report.c

@@ -75,7 +75,10 @@ static int report__config(const char *var, const char *value, void *cb)
 		return 0;
 	}
 	if (!strcmp(var, "report.percent-limit")) {
-		rep->min_percent = strtof(value, NULL);
+		double pcnt = strtof(value, NULL);
+
+		rep->min_percent = pcnt;
+		callchain_param.min_percent = pcnt;
 		return 0;
 	}
 	if (!strcmp(var, "report.children")) {
@@ -633,8 +636,10 @@ parse_percent_limit(const struct option *opt, const char *str,
 		    int unset __maybe_unused)
 {
 	struct report *rep = opt->value;
+	double pcnt = strtof(str, NULL);
 
-	rep->min_percent = strtof(str, NULL);
+	rep->min_percent = pcnt;
+	callchain_param.min_percent = pcnt;
 	return 0;
 }
 

tools/perf/ui/browsers/hists.c

@@ -657,9 +657,24 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser,
 	return 1;
 }
 
+static bool check_percent_display(struct rb_node *node, u64 parent_total)
+{
+	struct callchain_node *child;
+
+	if (node == NULL)
+		return false;
+
+	if (rb_next(node))
+		return true;
+
+	child = rb_entry(node, struct callchain_node, rb_node);
+	return callchain_cumul_hits(child) != parent_total;
+}
+
 static int hist_browser__show_callchain_flat(struct hist_browser *browser,
 					     struct rb_root *root,
 					     unsigned short row, u64 total,
+					     u64 parent_total,
 					     print_callchain_entry_fn print,
 					     struct callchain_print_arg *arg,
 					     check_output_full_fn is_output_full)
@@ -669,7 +684,7 @@ static int hist_browser__show_callchain_flat(struct hist_browser *browser,
 	bool need_percent;
 
 	node = rb_first(root);
-	need_percent = node && rb_next(node);
+	need_percent = check_percent_display(node, parent_total);
 
 	while (node) {
 		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
@@ -763,6 +778,7 @@ static char *hist_browser__folded_callchain_str(struct hist_browser *browser,
 static int hist_browser__show_callchain_folded(struct hist_browser *browser,
 					       struct rb_root *root,
 					       unsigned short row, u64 total,
+					       u64 parent_total,
 					       print_callchain_entry_fn print,
 					       struct callchain_print_arg *arg,
 					       check_output_full_fn is_output_full)
@@ -772,7 +788,7 @@ static int hist_browser__show_callchain_folded(struct hist_browser *browser,
 	bool need_percent;
 
 	node = rb_first(root);
-	need_percent = node && rb_next(node);
+	need_percent = check_percent_display(node, parent_total);
 
 	while (node) {
 		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
@@ -844,20 +860,24 @@ static int hist_browser__show_callchain_folded(struct hist_browser *browser,
 	return row - first_row;
 }
 
-static int hist_browser__show_callchain(struct hist_browser *browser,
+static int hist_browser__show_callchain_graph(struct hist_browser *browser,
 					struct rb_root *root, int level,
 					unsigned short row, u64 total,
+					u64 parent_total,
 					print_callchain_entry_fn print,
 					struct callchain_print_arg *arg,
 					check_output_full_fn is_output_full)
 {
 	struct rb_node *node;
 	int first_row = row, offset = level * LEVEL_OFFSET_STEP;
-	u64 new_total;
 	bool need_percent;
+	u64 percent_total = total;
+
+	if (callchain_param.mode == CHAIN_GRAPH_REL)
+		percent_total = parent_total;
 
 	node = rb_first(root);
-	need_percent = node && rb_next(node);
+	need_percent = check_percent_display(node, parent_total);
 
 	while (node) {
 		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
@@ -878,7 +898,7 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
 			folded_sign = callchain_list__folded(chain);
 
 			row += hist_browser__show_callchain_list(browser, child,
-							chain, row, total,
+							chain, row, percent_total,
 							was_first && need_percent,
 							offset + extra_offset,
 							print, arg);
@@ -893,13 +913,9 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
 		if (folded_sign == '-') {
 			const int new_level = level + (extra_offset ? 2 : 1);
 
-			if (callchain_param.mode == CHAIN_GRAPH_REL)
-				new_total = child->children_hit;
-			else
-				new_total = total;
-
-			row += hist_browser__show_callchain(browser, &child->rb_root,
-							    new_level, row, new_total,
+			row += hist_browser__show_callchain_graph(browser, &child->rb_root,
+							    new_level, row, total,
+							    child->children_hit,
 							    print, arg, is_output_full);
 		}
 		if (is_output_full(browser, row))
@@ -910,6 +926,45 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
 	return row - first_row;
 }
 
+static int hist_browser__show_callchain(struct hist_browser *browser,
+					struct hist_entry *entry, int level,
+					unsigned short row,
+					print_callchain_entry_fn print,
+					struct callchain_print_arg *arg,
+					check_output_full_fn is_output_full)
+{
+	u64 total = hists__total_period(entry->hists);
+	u64 parent_total;
+	int printed;
+
+	if (symbol_conf.cumulate_callchain)
+		parent_total = entry->stat_acc->period;
+	else
+		parent_total = entry->stat.period;
+
+	if (callchain_param.mode == CHAIN_FLAT) {
+		printed = hist_browser__show_callchain_flat(browser,
+						&entry->sorted_chain, row,
+						total, parent_total, print, arg,
+						is_output_full);
+	} else if (callchain_param.mode == CHAIN_FOLDED) {
+		printed = hist_browser__show_callchain_folded(browser,
+						&entry->sorted_chain, row,
+						total, parent_total, print, arg,
+						is_output_full);
+	} else {
+		printed = hist_browser__show_callchain_graph(browser,
+						&entry->sorted_chain, level, row,
+						total, parent_total, print, arg,
+						is_output_full);
+	}
+
+	if (arg->is_current_entry)
+		browser->he_selection = entry;
+
+	return printed;
+}
+
 struct hpp_arg {
 	struct ui_browser *b;
 	char folded_sign;
@@ -1084,38 +1139,14 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 		--row_offset;
 
 	if (folded_sign == '-' && row != browser->b.rows) {
-		u64 total = hists__total_period(entry->hists);
 		struct callchain_print_arg arg = {
 			.row_offset = row_offset,
 			.is_current_entry = current_entry,
 		};
 
-		if (callchain_param.mode == CHAIN_GRAPH_REL) {
-			if (symbol_conf.cumulate_callchain)
-				total = entry->stat_acc->period;
-			else
-				total = entry->stat.period;
-		}
-
-		if (callchain_param.mode == CHAIN_FLAT) {
-			printed += hist_browser__show_callchain_flat(browser,
-					&entry->sorted_chain, row, total,
-					hist_browser__show_callchain_entry, &arg,
-					hist_browser__check_output_full);
-		} else if (callchain_param.mode == CHAIN_FOLDED) {
-			printed += hist_browser__show_callchain_folded(browser,
-					&entry->sorted_chain, row, total,
-					hist_browser__show_callchain_entry, &arg,
-					hist_browser__check_output_full);
-		} else {
-			printed += hist_browser__show_callchain(browser,
-					&entry->sorted_chain, 1, row, total,
+		printed += hist_browser__show_callchain(browser, entry, 1, row,
 					hist_browser__show_callchain_entry, &arg,
 					hist_browser__check_output_full);
-		}
-
-		if (arg.is_current_entry)
-			browser->he_selection = entry;
 	}
 
 	return printed;
@@ -1380,15 +1411,11 @@ static void ui_browser__hists_seek(struct ui_browser *browser,
 static int hist_browser__fprintf_callchain(struct hist_browser *browser,
 					   struct hist_entry *he, FILE *fp)
 {
-	u64 total = hists__total_period(he->hists);
 	struct callchain_print_arg arg  = {
 		.fp = fp,
 	};
 
-	if (symbol_conf.cumulate_callchain)
-		total = he->stat_acc->period;
-
-	hist_browser__show_callchain(browser, &he->sorted_chain, 1, 0, total,
+	hist_browser__show_callchain(browser, he, 1, 0,
 				     hist_browser__fprintf_callchain_entry, &arg,
 				     hist_browser__check_dump_full);
 	return arg.printed;

tools/perf/ui/stdio/hist.c

@@ -165,8 +165,28 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 	return ret;
 }
 
+/*
+ * If have one single callchain root, don't bother printing
+ * its percentage (100 % in fractal mode and the same percentage
+ * than the hist in graph mode). This also avoid one level of column.
+ *
+ * However when percent-limit applied, it's possible that single callchain
+ * node have different (non-100% in fractal mode) percentage.
+ */
+static bool need_percent_display(struct rb_node *node, u64 parent_samples)
+{
+	struct callchain_node *cnode;
+
+	if (rb_next(node))
+		return true;
+
+	cnode = rb_entry(node, struct callchain_node, rb_node);
+	return callchain_cumul_hits(cnode) != parent_samples;
+}
+
 static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
-				       u64 total_samples, int left_margin)
+				       u64 total_samples, u64 parent_samples,
+				       int left_margin)
 {
 	struct callchain_node *cnode;
 	struct callchain_list *chain;
@@ -177,13 +197,8 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 	int ret = 0;
 	char bf[1024];
 
-	/*
-	 * If have one single callchain root, don't bother printing
-	 * its percentage (100 % in fractal mode and the same percentage
-	 * than the hist in graph mode). This also avoid one level of column.
-	 */
 	node = rb_first(root);
-	if (node && !rb_next(node)) {
+	if (node && !need_percent_display(node, parent_samples)) {
 		cnode = rb_entry(node, struct callchain_node, rb_node);
 		list_for_each_entry(chain, &cnode->val, list) {
 			/*
@@ -213,9 +228,15 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 		root = &cnode->rb_root;
 	}
 
+	if (callchain_param.mode == CHAIN_GRAPH_REL)
+		total_samples = parent_samples;
+
 	ret += __callchain__fprintf_graph(fp, root, total_samples,
 					  1, 1, left_margin);
-	ret += fprintf(fp, "\n");
+	if (ret) {
+		/* do not add a blank line if it printed nothing */
+		ret += fprintf(fp, "\n");
+	}
 
 	return ret;
 }
@@ -323,16 +344,19 @@ static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
 					    u64 total_samples, int left_margin,
 					    FILE *fp)
 {
+	u64 parent_samples = he->stat.period;
+
+	if (symbol_conf.cumulate_callchain)
+		parent_samples = he->stat_acc->period;
+
 	switch (callchain_param.mode) {
 	case CHAIN_GRAPH_REL:
-		return callchain__fprintf_graph(fp, &he->sorted_chain,
-						symbol_conf.cumulate_callchain ?
-						he->stat_acc->period : he->stat.period,
-						left_margin);
+		return callchain__fprintf_graph(fp, &he->sorted_chain, total_samples,
+						parent_samples, left_margin);
 		break;
 	case CHAIN_GRAPH_ABS:
 		return callchain__fprintf_graph(fp, &he->sorted_chain, total_samples,
-						left_margin);
+						parent_samples, left_margin);
 		break;
 	case CHAIN_FLAT:
 		return callchain__fprintf_flat(fp, &he->sorted_chain, total_samples);
@@ -349,30 +373,6 @@ static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
 	return 0;
 }
 
-static size_t hist_entry__callchain_fprintf(struct hist_entry *he,
-					    struct hists *hists,
-					    FILE *fp)
-{
-	int left_margin = 0;
-	u64 total_period = hists->stats.total_period;
-
-	if (field_order == NULL && (sort_order == NULL ||
-				    !prefixcmp(sort_order, "comm"))) {
-		struct perf_hpp_fmt *fmt;
-
-		perf_hpp__for_each_format(fmt) {
-			if (!perf_hpp__is_sort_entry(fmt))
-				continue;
-
-			/* must be 'comm' sort entry */
-			left_margin = fmt->width(fmt, NULL, hists_to_evsel(hists));
-			left_margin -= thread__comm_len(he->thread);
-			break;
-		}
-	}
-	return hist_entry_callchain__fprintf(he, total_period, left_margin, fp);
-}
-
 static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
 {
 	const char *sep = symbol_conf.field_sep;
@@ -418,6 +418,7 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 		.buf		= bf,
 		.size		= size,
 	};
+	u64 total_period = hists->stats.total_period;
 
 	if (size == 0 || size > bfsz)
 		size = hpp.size = bfsz;
@@ -427,7 +428,7 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 	ret = fprintf(fp, "%s\n", bf);
 
 	if (symbol_conf.use_callchain)
-		ret += hist_entry__callchain_fprintf(he, hists, fp);
+		ret += hist_entry_callchain__fprintf(he, total_period, 0, fp);
 
 	return ret;
 }

tools/perf/util/hist.c

@@ -432,8 +432,12 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 		cmp = hist_entry__cmp(he, entry);
 
 		if (!cmp) {
-			if (sample_self)
+			if (sample_self) {
 				he_stat__add_period(&he->stat, period, weight);
+				hists->stats.total_period += period;
+				if (!he->filtered)
+					hists->stats.total_non_filtered_period += period;
+			}
 			if (symbol_conf.cumulate_callchain)
 				he_stat__add_period(he->stat_acc, period, weight);
 
@@ -466,7 +470,10 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 	if (!he)
 		return NULL;
 
-	hists->nr_entries++;
+	if (sample_self)
+		hists__inc_stats(hists, he);
+	else
+		hists->nr_entries++;
 
 	rb_link_node(&he->rb_node_in, parent, p);
 	rb_insert_color(&he->rb_node_in, hists->entries_in);
@@ -1163,9 +1170,18 @@ static void __hists__insert_output_entry(struct rb_root *entries,
 	struct rb_node *parent = NULL;
 	struct hist_entry *iter;
 
-	if (use_callchain)
+	if (use_callchain) {
+		if (callchain_param.mode == CHAIN_GRAPH_REL) {
+			u64 total = he->stat.period;
+
+			if (symbol_conf.cumulate_callchain)
+				total = he->stat_acc->period;
+
+			min_callchain_hits = total * (callchain_param.min_percent / 100);
+		}
 		callchain_param.sort(&he->sorted_chain, he->callchain,
 				      min_callchain_hits, &callchain_param);
+	}
 
 	while (*p != NULL) {
 		parent = *p;
@@ -1195,7 +1211,7 @@ void hists__output_resort(struct hists *hists, struct ui_progress *prog)
 	else
 		use_callchain = symbol_conf.use_callchain;
 
-	min_callchain_hits = hists->stats.total_period * (callchain_param.min_percent / 100);
+	min_callchain_hits = hists__total_period(hists) * (callchain_param.min_percent / 100);
 
 	if (sort__need_collapse)
 		root = &hists->entries_collapsed;