1 files changed, 105 insertions, 267 deletions
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index c8f21137dfd..21d830bafff 100644
--- a/tools/perf/builtin-report.c
+++ b/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);
 };
 
@@ -71,150 +72,69 @@ static int report__config(const char *var, const char *value, void *cb)
 		rep->min_percent = strtof(value, NULL);
 		return 0;
 	}
+	if (!strcmp(var, "report.children")) {
+		symbol_conf.cumulate_callchain = perf_config_bool(var, value);
+		return 0;
+	}
 
 	return perf_default_config(var, value, cb);
 }
 
-static int report__add_mem_hist_entry(struct report *rep, struct addr_location *al,
-				      struct perf_sample *sample, struct perf_evsel *evsel)
+static void report__inc_stats(struct report *rep, struct hist_entry *he)
 {
-	struct symbol *parent = NULL;
-	struct hist_entry *he;
-	struct mem_info *mi, *mx;
-	uint64_t cost;
-	int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack);
-
-	if (err)
-		return err;
-
-	mi = sample__resolve_mem(sample, al);
-	if (!mi)
-		return -ENOMEM;
-
-	if (rep->hide_unresolved && !al->sym)
-		return 0;
-
-	cost = sample->weight;
-	if (!cost)
-		cost = 1;
-
 	/*
-	 * must pass period=weight in order to get the correct
-	 * sorting from hists__collapse_resort() which is solely
-	 * based on periods. We want sorting be done on nr_events * weight
-	 * and this is indirectly achieved by passing period=weight here
-	 * and the he_stat__add_period() function.
+	 * 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.
 	 */
-	he = __hists__add_entry(&evsel->hists, al, parent, NULL, mi,
-				cost, cost, 0);
-	if (!he)
-		return -ENOMEM;
-
-	if (ui__has_annotation()) {
-		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-		if (err)
-			goto out;
-
-		mx = he->mem_info;
-		err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx);
-		if (err)
-			goto out;
-	}
-
-	evsel->hists.stats.total_period += cost;
-	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
-	err = hist_entry__append_callchain(he, sample);
-out:
-	return err;
+	if (he->stat.nr_events == 1)
+		rep->nr_entries++;
 }
 
-static int report__add_branch_hist_entry(struct report *rep, struct addr_location *al,
-					 struct perf_sample *sample, struct perf_evsel *evsel)
+static int hist_iter__report_callback(struct hist_entry_iter *iter,
+				      struct addr_location *al, bool single,
+				      void *arg)
 {
-	struct symbol *parent = NULL;
-	unsigned i;
-	struct hist_entry *he;
-	struct branch_info *bi, *bx;
-	int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack);
-
-	if (err)
-		return err;
-
-	bi = sample__resolve_bstack(sample, al);
-	if (!bi)
-		return -ENOMEM;
-
-	for (i = 0; i < sample->branch_stack->nr; i++) {
-		if (rep->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym))
-			continue;
+	int err = 0;
+	struct report *rep = arg;
+	struct hist_entry *he = iter->he;
+	struct perf_evsel *evsel = iter->evsel;
+	struct mem_info *mi;
+	struct branch_info *bi;
 
-		err = -ENOMEM;
+	report__inc_stats(rep, he);
 
-		/* overwrite the 'al' to branch-to info */
-		al->map = bi[i].to.map;
-		al->sym = bi[i].to.sym;
-		al->addr = bi[i].to.addr;
-		/*
-		 * The report shows the percentage of total branches captured
-		 * and not events sampled. Thus we use a pseudo period of 1.
-		 */
-		he = __hists__add_entry(&evsel->hists, al, parent, &bi[i], NULL,
-					1, 1, 0);
-		if (he) {
-			if (ui__has_annotation()) {
-				bx = he->branch_info;
-				err = addr_map_symbol__inc_samples(&bx->from,
-								   evsel->idx);
-				if (err)
-					goto out;
-
-				err = addr_map_symbol__inc_samples(&bx->to,
-								   evsel->idx);
-				if (err)
-					goto out;
-			}
+	if (!ui__has_annotation())
+		return 0;
 
-			evsel->hists.stats.total_period += 1;
-			hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
-		} else
+	if (sort__mode == SORT_MODE__BRANCH) {
+		bi = he->branch_info;
+		err = addr_map_symbol__inc_samples(&bi->from, evsel->idx);
+		if (err)
 			goto out;
-	}
-	err = 0;
-out:
-	free(bi);
-	return err;
-}
 
-static int report__add_hist_entry(struct report *rep, struct perf_evsel *evsel,
-				  struct addr_location *al, struct perf_sample *sample)
-{
-	struct symbol *parent = NULL;
-	struct hist_entry *he;
-	int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack);
-
-	if (err)
-		return err;
+		err = addr_map_symbol__inc_samples(&bi->to, evsel->idx);
 
-	he = __hists__add_entry(&evsel->hists, al, parent, NULL, NULL,
-				sample->period, sample->weight,
-				sample->transaction);
-	if (he == NULL)
-		return -ENOMEM;
+	} else if (rep->mem_mode) {
+		mi = he->mem_info;
+		err = addr_map_symbol__inc_samples(&mi->daddr, evsel->idx);
+		if (err)
+			goto out;
 
-	err = hist_entry__append_callchain(he, sample);
-	if (err)
-		goto out;
+		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
 
-	if (ui__has_annotation())
+	} else if (symbol_conf.cumulate_callchain) {
+		if (single)
+			err = hist_entry__inc_addr_samples(he, evsel->idx,
+							   al->addr);
+	} else {
 		err = 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);
 out:
 	return err;
 }
 
-
 static int process_sample_event(struct perf_tool *tool,
 				union perf_event *event,
 				struct perf_sample *sample,
@@ -223,6 +143,10 @@ static int process_sample_event(struct perf_tool *tool,
 {
 	struct report *rep = container_of(tool, struct report, tool);
 	struct addr_location al;
+	struct hist_entry_iter iter = {
+		.hide_unresolved = rep->hide_unresolved,
+		.add_entry_cb = hist_iter__report_callback,
+	};
 	int ret;
 
 	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
@@ -237,22 +161,23 @@ static int process_sample_event(struct perf_tool *tool,
 	if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
 		return 0;
 
-	if (sort__mode == SORT_MODE__BRANCH) {
-		ret = report__add_branch_hist_entry(rep, &al, sample, evsel);
-		if (ret < 0)
-			pr_debug("problem adding lbr entry, skipping event\n");
-	} else if (rep->mem_mode == 1) {
-		ret = report__add_mem_hist_entry(rep, &al, sample, evsel);
-		if (ret < 0)
-			pr_debug("problem adding mem entry, skipping event\n");
-	} else {
-		if (al.map != NULL)
-			al.map->dso->hit = 1;
+	if (sort__mode == SORT_MODE__BRANCH)
+		iter.ops = &hist_iter_branch;
+	else if (rep->mem_mode)
+		iter.ops = &hist_iter_mem;
+	else if (symbol_conf.cumulate_callchain)
+		iter.ops = &hist_iter_cumulative;
+	else
+		iter.ops = &hist_iter_normal;
+
+	if (al.map != NULL)
+		al.map->dso->hit = 1;
+
+	ret = hist_entry_iter__add(&iter, &al, evsel, sample, rep->max_stack,
+				   rep);
+	if (ret < 0)
+		pr_debug("problem adding hist entry, skipping event\n");
 
-		ret = report__add_hist_entry(rep, evsel, &al, sample);
-		if (ret < 0)
-			pr_debug("problem incrementing symbol period, skipping event\n");
-	}
 	return ret;
 }
 
@@ -309,6 +234,14 @@ static int report__setup_sample_type(struct report *rep)
 			}
 	}
 
+	if (symbol_conf.cumulate_callchain) {
+		/* Silently ignore if callchain is missing */
+		if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) {
+			symbol_conf.cumulate_callchain = false;
+			perf_hpp__cancel_cumulate();
+		}
+	}
+
 	if (sort__mode == SORT_MODE__BRANCH) {
 		if (!is_pipe &&
 		    !(sample_type & PERF_SAMPLE_BRANCH_STACK)) {
@@ -337,6 +270,11 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report
 	char buf[512];
 	size_t size = sizeof(buf);
 
+	if (symbol_conf.filter_relative) {
+		nr_samples = hists->stats.nr_non_filtered_samples;
+		nr_events = hists->stats.total_non_filtered_period;
+	}
+
 	if (perf_evsel__is_group_event(evsel)) {
 		struct perf_evsel *pos;
 
@@ -344,8 +282,13 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report
 		evname = buf;
 
 		for_each_group_member(pos, evsel) {
-			nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE];
-			nr_events += pos->hists.stats.total_period;
+			if (symbol_conf.filter_relative) {
+				nr_samples += pos->hists.stats.nr_non_filtered_samples;
+				nr_events += pos->hists.stats.total_non_filtered_period;
+			} else {
+				nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE];
+				nr_events += pos->hists.stats.total_period;
+			}
 		}
 	}
 
@@ -470,24 +413,12 @@ 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;
@@ -496,7 +427,6 @@ 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 &&
@@ -509,14 +439,11 @@ 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;
@@ -556,12 +483,12 @@ 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;
 	}
@@ -573,11 +500,9 @@ static int __cmd_report(struct report *rep)
 }
 
 static int
-parse_callchain_opt(const struct option *opt, const char *arg, int unset)
+report_parse_callchain_opt(const struct option *opt, const char *arg, int unset)
 {
 	struct report *rep = (struct report *)opt->value;
-	char *tok, *tok2;
-	char *endptr;
 
 	/*
 	 * --no-call-graph
@@ -587,80 +512,7 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset)
 		return 0;
 	}
 
-	symbol_conf.use_callchain = true;
-
-	if (!arg)
-		return 0;
-
-	tok = strtok((char *)arg, ",");
-	if (!tok)
-		return -1;
-
-	/* get the output mode */
-	if (!strncmp(tok, "graph", strlen(arg)))
-		callchain_param.mode = CHAIN_GRAPH_ABS;
-
-	else if (!strncmp(tok, "flat", strlen(arg)))
-		callchain_param.mode = CHAIN_FLAT;
-
-	else if (!strncmp(tok, "fractal", strlen(arg)))
-		callchain_param.mode = CHAIN_GRAPH_REL;
-
-	else if (!strncmp(tok, "none", strlen(arg))) {
-		callchain_param.mode = CHAIN_NONE;
-		symbol_conf.use_callchain = false;
-
-		return 0;
-	}
-
-	else
-		return -1;
-
-	/* get the min percentage */
-	tok = strtok(NULL, ",");
-	if (!tok)
-		goto setup;
-
-	callchain_param.min_percent = strtod(tok, &endptr);
-	if (tok == endptr)
-		return -1;
-
-	/* get the print limit */
-	tok2 = strtok(NULL, ",");
-	if (!tok2)
-		goto setup;
-
-	if (tok2[0] != 'c') {
-		callchain_param.print_limit = strtoul(tok2, &endptr, 0);
-		tok2 = strtok(NULL, ",");
-		if (!tok2)
-			goto setup;
-	}
-
-	/* get the call chain order */
-	if (!strncmp(tok2, "caller", strlen("caller")))
-		callchain_param.order = ORDER_CALLER;
-	else if (!strncmp(tok2, "callee", strlen("callee")))
-		callchain_param.order = ORDER_CALLEE;
-	else
-		return -1;
-
-	/* Get the sort key */
-	tok2 = strtok(NULL, ",");
-	if (!tok2)
-		goto setup;
-	if (!strncmp(tok2, "function", strlen("function")))
-		callchain_param.key = CCKEY_FUNCTION;
-	else if (!strncmp(tok2, "address", strlen("address")))
-		callchain_param.key = CCKEY_ADDRESS;
-	else
-		return -1;
-setup:
-	if (callchain_register_param(&callchain_param) < 0) {
-		pr_err("Can't register callchain params\n");
-		return -1;
-	}
-	return 0;
+	return parse_callchain_report_opt(arg);
 }
 
 int
@@ -760,10 +612,10 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN(0, "header-only", &report.header_only,
 		    "Show only data header."),
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
-		   "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline,"
-		   " dso_to, dso_from, symbol_to, symbol_from, mispredict,"
-		   " weight, local_weight, mem, symbol_daddr, dso_daddr, tlb, "
-		   "snoop, locked, abort, in_tx, transaction"),
+		   "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline, ..."
+		   " Please refer the man page for the complete list."),
+	OPT_STRING('F', "fields", &field_order, "key[,keys...]",
+		   "output field(s): overhead, period, sample plus all of sort keys"),
 	OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
 		    "Show sample percentage for different cpu modes"),
 	OPT_STRING('p', "parent", &parent_pattern, "regex",
@@ -772,7 +624,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Only display entries with parent-match"),
 	OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order",
 		     "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address). "
-		     "Default: fractal,0.5,callee,function", &parse_callchain_opt, callchain_default_opt),
+		     "Default: fractal,0.5,callee,function", &report_parse_callchain_opt, callchain_default_opt),
+	OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain,
+		    "Accumulate callchains of children and show total overhead as well"),
 	OPT_INTEGER(0, "max-stack", &report.max_stack,
 		    "Set the maximum stack depth when parsing the callchain, "
 		    "anything beyond the specified depth will be ignored. "
@@ -823,6 +677,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"),
 	OPT_CALLBACK(0, "percent-limit", &report, "percent",
 		     "Don't show entries under that percent", parse_percent_limit),
+	OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
+		     "how to display percentage of filtered entries", parse_filter_percentage),
 	OPT_END()
 	};
 	struct perf_data_file file = {
@@ -863,55 +719,37 @@ repeat:
 	has_br_stack = perf_header__has_feat(&session->header,
 					     HEADER_BRANCH_STACK);
 
-	if (branch_mode == -1 && has_br_stack)
+	if (branch_mode == -1 && has_br_stack) {
 		sort__mode = SORT_MODE__BRANCH;
-
-	/* sort__mode could be NORMAL if --no-branch-stack */
-	if (sort__mode == SORT_MODE__BRANCH) {
-		/*
-		 * if no sort_order is provided, then specify
-		 * branch-mode specific order
-		 */
-		if (sort_order == default_sort_order)
-			sort_order = "comm,dso_from,symbol_from,"
-				     "dso_to,symbol_to";
-
+		symbol_conf.cumulate_callchain = false;
 	}
+
 	if (report.mem_mode) {
 		if (sort__mode == SORT_MODE__BRANCH) {
 			pr_err("branch and mem mode incompatible\n");
 			goto error;
 		}
 		sort__mode = SORT_MODE__MEMORY;
-
-		/*
-		 * if no sort_order is provided, then specify
-		 * branch-mode specific order
-		 */
-		if (sort_order == default_sort_order)
-			sort_order = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked";
+		symbol_conf.cumulate_callchain = false;
 	}
 
 	if (setup_sorting() < 0) {
-		parse_options_usage(report_usage, options, "s", 1);
+		if (sort_order)
+			parse_options_usage(report_usage, options, "s", 1);
+		if (field_order)
+			parse_options_usage(sort_order ? NULL : report_usage,
+					    options, "F", 1);
 		goto error;
 	}
 
-	if (parent_pattern != default_parent_pattern) {
-		if (sort_dimension__add("parent") < 0)
-			goto error;
-	}
-
 	/* Force tty output for header output. */
 	if (report.header || report.header_only)
 		use_browser = 0;
 
 	if (strcmp(input_name, "-") != 0)
 		setup_browser(true);
-	else {
+	else
 		use_browser = 0;
-		perf_hpp__init();
-	}
 
 	if (report.header || report.header_only) {
 		perf_session__fprintf_info(session, stdout,