1 files changed, 582 insertions, 317 deletions

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index c27e31f289e..21d830bafff 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -8,10 +8,11 @@
 #include "builtin.h"
 
 #include "util/util.h"
+#include "util/cache.h"
 
+#include "util/annotate.h"
 #include "util/color.h"
 #include <linux/list.h>
-#include "util/cache.h"
 #include <linux/rbtree.h>
 #include "util/symbol.h"
 #include "util/callchain.h"
@@ -20,8 +21,11 @@
 
 #include "perf.h"
 #include "util/debug.h"
+#include "util/evlist.h"
+#include "util/evsel.h"
 #include "util/header.h"
 #include "util/session.h"
+#include "util/tool.h"
 
 #include "util/parse-options.h"
 #include "util/parse-events.h"
@@ -29,168 +33,165 @@
 #include "util/thread.h"
 #include "util/sort.h"
 #include "util/hist.h"
+#include "util/data.h"
+#include "arch/common.h"
+
+#include <dlfcn.h>
+#include <linux/bitmap.h>
+
+struct report {
+	struct perf_tool	tool;
+	struct perf_session	*session;
+	bool			force, use_tui, use_gtk, use_stdio;
+	bool			hide_unresolved;
+	bool			dont_use_callchains;
+	bool			show_full_info;
+	bool			show_threads;
+	bool			inverted_callchain;
+	bool			mem_mode;
+	bool			header;
+	bool			header_only;
+	int			max_stack;
+	struct perf_read_values	show_threads_values;
+	const char		*pretty_printing_style;
+	const char		*cpu_list;
+	const char		*symbol_filter_str;
+	float			min_percent;
+	u64			nr_entries;
+	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
+};
 
-static char		const *input_name = "perf.data";
-
-static bool		force, use_tui, use_stdio;
-static bool		hide_unresolved;
-static bool		dont_use_callchains;
-
-static bool		show_threads;
-static struct perf_read_values	show_threads_values;
-
-static const char	default_pretty_printing_style[] = "normal";
-static const char	*pretty_printing_style = default_pretty_printing_style;
-
-static char		callchain_default_opt[] = "fractal,0.5";
-
-static struct hists *perf_session__hists_findnew(struct perf_session *self,
-						 u64 event_stream, u32 type,
-						 u64 config)
+static int report__config(const char *var, const char *value, void *cb)
 {
-	struct rb_node **p = &self->hists_tree.rb_node;
-	struct rb_node *parent = NULL;
-	struct hists *iter, *new;
-
-	while (*p != NULL) {
-		parent = *p;
-		iter = rb_entry(parent, struct hists, rb_node);
-		if (iter->config == config)
-			return iter;
-
-
-		if (config > iter->config)
-			p = &(*p)->rb_right;
-		else
-			p = &(*p)->rb_left;
+	if (!strcmp(var, "report.group")) {
+		symbol_conf.event_group = perf_config_bool(var, value);
+		return 0;
+	}
+	if (!strcmp(var, "report.percent-limit")) {
+		struct report *rep = 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;
 	}
 
-	new = malloc(sizeof(struct hists));
-	if (new == NULL)
-		return NULL;
-	memset(new, 0, sizeof(struct hists));
-	new->event_stream = event_stream;
-	new->config = config;
-	new->type = type;
-	rb_link_node(&new->rb_node, parent, p);
-	rb_insert_color(&new->rb_node, &self->hists_tree);
-	return new;
+	return perf_default_config(var, value, cb);
 }
 
-static int perf_session__add_hist_entry(struct perf_session *self,
-					struct addr_location *al,
-					struct sample_data *data)
+static void report__inc_stats(struct report *rep, struct hist_entry *he)
 {
-	struct map_symbol *syms = NULL;
-	struct symbol *parent = NULL;
-	int err = -ENOMEM;
-	struct hist_entry *he;
-	struct hists *hists;
-	struct perf_event_attr *attr;
-
-	if ((sort__has_parent || symbol_conf.use_callchain) && data->callchain) {
-		syms = perf_session__resolve_callchain(self, al->thread,
-						       data->callchain, &parent);
-		if (syms == NULL)
-			return -ENOMEM;
-	}
-
-	attr = perf_header__find_attr(data->id, &self->header);
-	if (attr)
-		hists = perf_session__hists_findnew(self, data->id, attr->type, attr->config);
-	else
-		hists = perf_session__hists_findnew(self, data->id, 0, 0);
-	if (hists == NULL)
-		goto out_free_syms;
-	he = __hists__add_entry(hists, al, parent, data->period);
-	if (he == NULL)
-		goto out_free_syms;
-	err = 0;
-	if (symbol_conf.use_callchain) {
-		err = callchain_append(he->callchain, data->callchain, syms,
-				       data->period);
-		if (err)
-			goto out_free_syms;
-	}
 	/*
-	 * Only in the newt browser we are doing integrated annotation,
-	 * so we don't allocated the extra space needed because the stdio
-	 * code will not use it.
+	 * 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 (use_browser > 0)
-		err = hist_entry__inc_addr_samples(he, al->addr);
-out_free_syms:
-	free(syms);
-	return err;
+	if (he->stat.nr_events == 1)
+		rep->nr_entries++;
 }
 
-static int add_event_total(struct perf_session *session,
-			   struct sample_data *data,
-			   struct perf_event_attr *attr)
+static int hist_iter__report_callback(struct hist_entry_iter *iter,
+				      struct addr_location *al, bool single,
+				      void *arg)
 {
-	struct hists *hists;
+	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;
 
-	if (attr)
-		hists = perf_session__hists_findnew(session, data->id,
-						    attr->type, attr->config);
-	else
-		hists = perf_session__hists_findnew(session, data->id, 0, 0);
+	report__inc_stats(rep, he);
 
-	if (!hists)
-		return -ENOMEM;
+	if (!ui__has_annotation())
+		return 0;
 
-	hists->stats.total_period += data->period;
-	/*
-	 * FIXME: add_event_total should be moved from here to
-	 * perf_session__process_event so that the proper hist is passed to
-	 * the event_op methods.
-	 */
-	hists__inc_nr_events(hists, PERF_RECORD_SAMPLE);
-	session->hists.stats.total_period += data->period;
-	return 0;
+	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 = addr_map_symbol__inc_samples(&bi->to, evsel->idx);
+
+	} 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__inc_addr_samples(he, evsel->idx, al->addr);
+
+	} 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);
+	}
+
+out:
+	return err;
 }
 
-static int process_sample_event(event_t *event, struct sample_data *sample,
-				struct perf_session *session)
+static int process_sample_event(struct perf_tool *tool,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct perf_evsel *evsel,
+				struct machine *machine)
 {
+	struct report *rep = container_of(tool, struct report, tool);
 	struct addr_location al;
-	struct perf_event_attr *attr;
-
-	if (event__preprocess_sample(event, session, &al, sample, NULL) < 0) {
-		fprintf(stderr, "problem processing %d event, skipping it.\n",
-			event->header.type);
+	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) {
+		pr_debug("problem processing %d event, skipping it.\n",
+			 event->header.type);
 		return -1;
 	}
 
-	if (al.filtered || (hide_unresolved && al.sym == NULL))
+	if (rep->hide_unresolved && al.sym == NULL)
 		return 0;
 
-	if (perf_session__add_hist_entry(session, &al, sample)) {
-		pr_debug("problem incrementing symbol period, skipping event\n");
-		return -1;
-	}
+	if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
+		return 0;
 
-	attr = perf_header__find_attr(sample->id, &session->header);
+	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 (add_event_total(session, sample, attr)) {
-		pr_debug("problem adding event period\n");
-		return -1;
-	}
+	if (al.map != NULL)
+		al.map->dso->hit = 1;
 
-	return 0;
+	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");
+
+	return ret;
 }
 
-static int process_read_event(event_t *event, struct sample_data *sample __used,
-			      struct perf_session *session __used)
+static int process_read_event(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample __maybe_unused,
+			      struct perf_evsel *evsel,
+			      struct machine *machine __maybe_unused)
 {
-	struct perf_event_attr *attr;
-
-	attr = perf_header__find_attr(event->read.id, &session->header);
+	struct report *rep = container_of(tool, struct report, tool);
 
-	if (show_threads) {
-		const char *name = attr ? __event_name(attr->type, attr->config)
-				   : "unknown";
-		perf_read_values_add_value(&show_threads_values,
+	if (rep->show_threads) {
+		const char *name = evsel ? perf_evsel__name(evsel) : "unknown";
+		perf_read_values_add_value(&rep->show_threads_values,
 					   event->read.pid, event->read.tid,
 					   event->read.id,
 					   name,
@@ -198,245 +199,392 @@ static int process_read_event(event_t *event, struct sample_data *sample __used,
 	}
 
 	dump_printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid,
-		    attr ? __event_name(attr->type, attr->config) : "FAIL",
+		    evsel ? perf_evsel__name(evsel) : "FAIL",
 		    event->read.value);
 
 	return 0;
 }
 
-static int perf_session__setup_sample_type(struct perf_session *self)
+/* For pipe mode, sample_type is not currently set */
+static int report__setup_sample_type(struct report *rep)
 {
-	if (!(self->sample_type & PERF_SAMPLE_CALLCHAIN)) {
+	struct perf_session *session = rep->session;
+	u64 sample_type = perf_evlist__combined_sample_type(session->evlist);
+	bool is_pipe = perf_data_file__is_pipe(session->file);
+
+	if (!is_pipe && !(sample_type & PERF_SAMPLE_CALLCHAIN)) {
 		if (sort__has_parent) {
-			fprintf(stderr, "selected --sort parent, but no"
-					" callchain data. Did you call"
-					" perf record without -g?\n");
+			ui__error("Selected --sort parent, but no "
+				    "callchain data. Did you call "
+				    "'perf record' without -g?\n");
 			return -EINVAL;
 		}
 		if (symbol_conf.use_callchain) {
-			fprintf(stderr, "selected -g but no callchain data."
-					" Did you call perf record without"
-					" -g?\n");
+			ui__error("Selected -g but no callchain data. Did "
+				    "you call 'perf record' without -g?\n");
 			return -1;
 		}
-	} else if (!dont_use_callchains && callchain_param.mode != CHAIN_NONE &&
+	} else if (!rep->dont_use_callchains &&
+		   callchain_param.mode != CHAIN_NONE &&
 		   !symbol_conf.use_callchain) {
 			symbol_conf.use_callchain = true;
-			if (register_callchain_param(&callchain_param) < 0) {
-				fprintf(stderr, "Can't register callchain"
-						" params\n");
+			if (callchain_register_param(&callchain_param) < 0) {
+				ui__error("Can't register callchain params.\n");
 				return -EINVAL;
 			}
 	}
 
-	return 0;
-}
+	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();
+		}
+	}
 
-static struct perf_event_ops event_ops = {
-	.sample	= process_sample_event,
-	.mmap	= event__process_mmap,
-	.comm	= event__process_comm,
-	.exit	= event__process_task,
-	.fork	= event__process_task,
-	.lost	= event__process_lost,
-	.read	= process_read_event,
-	.attr	= event__process_attr,
-	.event_type = event__process_event_type,
-	.tracing_data = event__process_tracing_data,
-	.build_id = event__process_build_id,
-	.ordered_samples = true,
-	.ordering_requires_timestamps = true,
-};
+	if (sort__mode == SORT_MODE__BRANCH) {
+		if (!is_pipe &&
+		    !(sample_type & PERF_SAMPLE_BRANCH_STACK)) {
+			ui__error("Selected -b but no branch data. "
+				  "Did you call perf record without -b?\n");
+			return -1;
+		}
+	}
 
-extern volatile int session_done;
+	return 0;
+}
 
-static void sig_handler(int sig __used)
+static void sig_handler(int sig __maybe_unused)
 {
 	session_done = 1;
 }
 
-static size_t hists__fprintf_nr_sample_events(struct hists *self,
+static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report *rep,
 					      const char *evname, FILE *fp)
 {
 	size_t ret;
 	char unit;
-	unsigned long nr_events = self->stats.nr_events[PERF_RECORD_SAMPLE];
+	unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
+	u64 nr_events = hists->stats.total_period;
+	struct perf_evsel *evsel = hists_to_evsel(hists);
+	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;
+	}
 
-	nr_events = convert_unit(nr_events, &unit);
-	ret = fprintf(fp, "# Events: %lu%c", nr_events, unit);
+	if (perf_evsel__is_group_event(evsel)) {
+		struct perf_evsel *pos;
+
+		perf_evsel__group_desc(evsel, buf, size);
+		evname = buf;
+
+		for_each_group_member(pos, evsel) {
+			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;
+			}
+		}
+	}
+
+	nr_samples = convert_unit(nr_samples, &unit);
+	ret = fprintf(fp, "# Samples: %lu%c", nr_samples, unit);
 	if (evname != NULL)
-		ret += fprintf(fp, " %s", evname);
+		ret += fprintf(fp, " of event '%s'", evname);
+
+	if (rep->mem_mode) {
+		ret += fprintf(fp, "\n# Total weight : %" PRIu64, nr_events);
+		ret += fprintf(fp, "\n# Sort order   : %s", sort_order);
+	} else
+		ret += fprintf(fp, "\n# Event count (approx.): %" PRIu64, nr_events);
 	return ret + fprintf(fp, "\n#\n");
 }
 
-static int hists__tty_browse_tree(struct rb_root *tree, const char *help)
+static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
+					 struct report *rep,
+					 const char *help)
 {
-	struct rb_node *next = rb_first(tree);
+	struct perf_evsel *pos;
 
-	while (next) {
-		struct hists *hists = rb_entry(next, struct hists, rb_node);
-		const char *evname = NULL;
+	evlist__for_each(evlist, pos) {
+		struct hists *hists = &pos->hists;
+		const char *evname = perf_evsel__name(pos);
 
-		if (rb_first(&hists->entries) != rb_last(&hists->entries))
-			evname = __event_name(hists->type, hists->config);
+		if (symbol_conf.event_group &&
+		    !perf_evsel__is_group_leader(pos))
+			continue;
 
-		hists__fprintf_nr_sample_events(hists, evname, stdout);
-		hists__fprintf(hists, NULL, false, stdout);
+		hists__fprintf_nr_sample_events(hists, rep, evname, stdout);
+		hists__fprintf(hists, true, 0, 0, rep->min_percent, stdout);
 		fprintf(stdout, "\n\n");
-		next = rb_next(&hists->rb_node);
 	}
 
 	if (sort_order == default_sort_order &&
 	    parent_pattern == default_parent_pattern) {
 		fprintf(stdout, "#\n# (%s)\n#\n", help);
 
-		if (show_threads) {
-			bool style = !strcmp(pretty_printing_style, "raw");
-			perf_read_values_display(stdout, &show_threads_values,
+		if (rep->show_threads) {
+			bool style = !strcmp(rep->pretty_printing_style, "raw");
+			perf_read_values_display(stdout, &rep->show_threads_values,
 						 style);
-			perf_read_values_destroy(&show_threads_values);
+			perf_read_values_destroy(&rep->show_threads_values);
 		}
 	}
 
 	return 0;
 }
 
-static int __cmd_report(void)
+static void report__warn_kptr_restrict(const struct report *rep)
 {
-	int ret = -EINVAL;
-	struct perf_session *session;
-	struct rb_node *next;
+	struct map *kernel_map = rep->session->machines.host.vmlinux_maps[MAP__FUNCTION];
+	struct kmap *kernel_kmap = map__kmap(kernel_map);
+
+	if (kernel_map == NULL ||
+	    (kernel_map->dso->hit &&
+	     (kernel_kmap->ref_reloc_sym == NULL ||
+	      kernel_kmap->ref_reloc_sym->addr == 0))) {
+		const char *desc =
+		    "As no suitable kallsyms nor vmlinux was found, kernel samples\n"
+		    "can't be resolved.";
+
+		if (kernel_map) {
+			const struct dso *kdso = kernel_map->dso;
+			if (!RB_EMPTY_ROOT(&kdso->symbols[MAP__FUNCTION])) {
+				desc = "If some relocation was applied (e.g. "
+				       "kexec) symbols may be misresolved.";
+			}
+		}
+
+		ui__warning(
+"Kernel address maps (/proc/{kallsyms,modules}) were restricted.\n\n"
+"Check /proc/sys/kernel/kptr_restrict before running 'perf record'.\n\n%s\n\n"
+"Samples in kernel modules can't be resolved as well.\n\n",
+		desc);
+	}
+}
+
+static int report__gtk_browse_hists(struct report *rep, const char *help)
+{
+	int (*hist_browser)(struct perf_evlist *evlist, const char *help,
+			    struct hist_browser_timer *timer, float min_pcnt);
+
+	hist_browser = dlsym(perf_gtk_handle, "perf_evlist__gtk_browse_hists");
+
+	if (hist_browser == NULL) {
+		ui__error("GTK browser not found!\n");
+		return -1;
+	}
+
+	return hist_browser(rep->session->evlist, help, NULL, rep->min_percent);
+}
+
+static int report__browse_hists(struct report *rep)
+{
+	int ret;
+	struct perf_session *session = rep->session;
+	struct perf_evlist *evlist = session->evlist;
 	const char *help = "For a higher level overview, try: perf report --sort comm,dso";
 
+	switch (use_browser) {
+	case 1:
+		ret = perf_evlist__tui_browse_hists(evlist, help, NULL,
+						    rep->min_percent,
+						    &session->header.env);
+		/*
+		 * Usually "ret" is the last pressed key, and we only
+		 * care if the key notifies us to switch data file.
+		 */
+		if (ret != K_SWITCH_INPUT_DATA)
+			ret = 0;
+		break;
+	case 2:
+		ret = report__gtk_browse_hists(rep, help);
+		break;
+	default:
+		ret = perf_evlist__tty_browse_hists(evlist, rep, help);
+		break;
+	}
+
+	return ret;
+}
+
+static void report__collapse_hists(struct report *rep)
+{
+	struct ui_progress prog;
+	struct perf_evsel *pos;
+
+	ui_progress__init(&prog, rep->nr_entries, "Merging related events...");
+
+	evlist__for_each(rep->session->evlist, pos) {
+		struct hists *hists = &pos->hists;
+
+		if (pos->idx == 0)
+			hists->symbol_filter_str = rep->symbol_filter_str;
+
+		hists__collapse_resort(hists, &prog);
+
+		/* Non-group events are considered as leader */
+		if (symbol_conf.event_group &&
+		    !perf_evsel__is_group_leader(pos)) {
+			struct hists *leader_hists = &pos->leader->hists;
+
+			hists__match(leader_hists, hists);
+			hists__link(leader_hists, hists);
+		}
+	}
+
+	ui_progress__finish();
+}
+
+static int __cmd_report(struct report *rep)
+{
+	int ret;
+	struct perf_session *session = rep->session;
+	struct perf_evsel *pos;
+	struct perf_data_file *file = session->file;
+
 	signal(SIGINT, sig_handler);
 
-	session = perf_session__new(input_name, O_RDONLY, force, false, &event_ops);
-	if (session == NULL)
-		return -ENOMEM;
+	if (rep->cpu_list) {
+		ret = perf_session__cpu_bitmap(session, rep->cpu_list,
+					       rep->cpu_bitmap);
+		if (ret)
+			return ret;
+	}
 
-	if (show_threads)
-		perf_read_values_init(&show_threads_values);
+	if (rep->show_threads)
+		perf_read_values_init(&rep->show_threads_values);
 
-	ret = perf_session__setup_sample_type(session);
+	ret = report__setup_sample_type(rep);
 	if (ret)
-		goto out_delete;
+		return ret;
 
-	ret = perf_session__process_events(session, &event_ops);
+	ret = perf_session__process_events(session, &rep->tool);
 	if (ret)
-		goto out_delete;
+		return ret;
 
-	if (dump_trace) {
-		perf_session__fprintf_nr_events(session, stdout);
-		goto out_delete;
-	}
+	report__warn_kptr_restrict(rep);
 
-	if (verbose > 3)
-		perf_session__fprintf(session, stdout);
+	if (use_browser == 0) {
+		if (verbose > 3)
+			perf_session__fprintf(session, stdout);
 
-	if (verbose > 2)
-		perf_session__fprintf_dsos(session, stdout);
+		if (verbose > 2)
+			perf_session__fprintf_dsos(session, stdout);
 
-	next = rb_first(&session->hists_tree);
-	while (next) {
-		struct hists *hists;
+		if (dump_trace) {
+			perf_session__fprintf_nr_events(session, stdout);
+			return 0;
+		}
+	}
+
+	report__collapse_hists(rep);
 
-		hists = rb_entry(next, struct hists, rb_node);
-		hists__collapse_resort(hists);
-		hists__output_resort(hists);
-		next = rb_next(&hists->rb_node);
+	if (session_done())
+		return 0;
+
+	if (rep->nr_entries == 0) {
+		ui__error("The %s file has no samples!\n", file->path);
+		return 0;
 	}
 
-	if (use_browser > 0)
-		hists__tui_browse_tree(&session->hists_tree, help);
-	else
-		hists__tty_browse_tree(&session->hists_tree, help);
+	evlist__for_each(session->evlist, pos)
+		hists__output_resort(&pos->hists);
 
-out_delete:
-	/*
-	 * Speed up the exit process, for large files this can
-	 * take quite a while.
-	 *
-	 * XXX Enable this when using valgrind or if we ever
-	 * librarize this command.
-	 *
-	 * Also experiment with obstacks to see how much speed
-	 * up we'll get here.
-	 *
- 	 * perf_session__delete(session);
- 	 */
-	return ret;
+	return report__browse_hists(rep);
 }
 
 static int
-parse_callchain_opt(const struct option *opt __used, const char *arg,
-		    int unset)
+report_parse_callchain_opt(const struct option *opt, const char *arg, int unset)
 {
-	char *tok, *tok2;
-	char *endptr;
+	struct report *rep = (struct report *)opt->value;
 
 	/*
 	 * --no-call-graph
 	 */
 	if (unset) {
-		dont_use_callchains = true;
+		rep->dont_use_callchains = true;
 		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 parse_callchain_report_opt(arg);
+}
 
-		return 0;
+int
+report_parse_ignore_callees_opt(const struct option *opt __maybe_unused,
+				const char *arg, int unset __maybe_unused)
+{
+	if (arg) {
+		int err = regcomp(&ignore_callees_regex, arg, REG_EXTENDED);
+		if (err) {
+			char buf[BUFSIZ];
+			regerror(err, &ignore_callees_regex, buf, sizeof(buf));
+			pr_err("Invalid --ignore-callees regex: %s\n%s", arg, buf);
+			return -1;
+		}
+		have_ignore_callees = 1;
 	}
 
-	else
-		return -1;
-
-	/* get the min percentage */
-	tok = strtok(NULL, ",");
-	if (!tok)
-		goto setup;
+	return 0;
+}
 
-	tok2 = strtok(NULL, ",");
-	callchain_param.min_percent = strtod(tok, &endptr);
-	if (tok == endptr)
-		return -1;
+static int
+parse_branch_mode(const struct option *opt __maybe_unused,
+		  const char *str __maybe_unused, int unset)
+{
+	int *branch_mode = opt->value;
 
-	if (tok2)
-		callchain_param.print_limit = strtod(tok2, &endptr);
-setup:
-	if (register_callchain_param(&callchain_param) < 0) {
-		fprintf(stderr, "Can't register callchain params\n");
-		return -1;
-	}
+	*branch_mode = !unset;
 	return 0;
 }
 
-static const char * const report_usage[] = {
-	"perf report [<options>] <command>",
-	NULL
-};
+static int
+parse_percent_limit(const struct option *opt, const char *str,
+		    int unset __maybe_unused)
+{
+	struct report *rep = opt->value;
 
-static const struct option options[] = {
+	rep->min_percent = strtof(str, NULL);
+	return 0;
+}
+
+int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+	struct perf_session *session;
+	struct stat st;
+	bool has_br_stack = false;
+	int branch_mode = -1;
+	int ret = -1;
+	char callchain_default_opt[] = "fractal,0.5,callee";
+	const char * const report_usage[] = {
+		"perf report [<options>]",
+		NULL
+	};
+	struct report report = {
+		.tool = {
+			.sample		 = process_sample_event,
+			.mmap		 = perf_event__process_mmap,
+			.mmap2		 = perf_event__process_mmap2,
+			.comm		 = perf_event__process_comm,
+			.exit		 = perf_event__process_exit,
+			.fork		 = perf_event__process_fork,
+			.lost		 = perf_event__process_lost,
+			.read		 = process_read_event,
+			.attr		 = perf_event__process_attr,
+			.tracing_data	 = perf_event__process_tracing_data,
+			.build_id	 = perf_event__process_build_id,
+			.ordered_samples = true,
+			.ordering_requires_timestamps = true,
+		},
+		.max_stack		 = PERF_MAX_STACK_DEPTH,
+		.pretty_printing_style	 = "normal",
+	};
+	const struct option options[] = {
 	OPT_STRING('i', "input", &input_name, "file",
 		    "input file name"),
 	OPT_INCR('v', "verbose", &verbose,
@@ -447,67 +595,181 @@ static const struct option options[] = {
 		   "file", "vmlinux pathname"),
 	OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name,
 		   "file", "kallsyms pathname"),
-	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
+	OPT_BOOLEAN('f', "force", &report.force, "don't complain, do it"),
 	OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules,
 		    "load module symbols - WARNING: use only with -k and LIVE kernel"),
 	OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
 		    "Show a column with the number of samples"),
-	OPT_BOOLEAN('T', "threads", &show_threads,
+	OPT_BOOLEAN('T', "threads", &report.show_threads,
 		    "Show per-thread event counters"),
-	OPT_STRING(0, "pretty", &pretty_printing_style, "key",
+	OPT_STRING(0, "pretty", &report.pretty_printing_style, "key",
 		   "pretty printing style key: normal raw"),
-	OPT_BOOLEAN(0, "tui", &use_tui, "Use the TUI interface"),
-	OPT_BOOLEAN(0, "stdio", &use_stdio, "Use the stdio interface"),
+	OPT_BOOLEAN(0, "tui", &report.use_tui, "Use the TUI interface"),
+	OPT_BOOLEAN(0, "gtk", &report.use_gtk, "Use the GTK2 interface"),
+	OPT_BOOLEAN(0, "stdio", &report.use_stdio,
+		    "Use the stdio interface"),
+	OPT_BOOLEAN(0, "header", &report.header, "Show data header."),
+	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"),
+		   "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",
 		   "regex filter to identify parent, see: '--sort parent'"),
 	OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other,
 		    "Only display entries with parent-match"),
-	OPT_CALLBACK_DEFAULT('g', "call-graph", NULL, "output_type,min_percent",
-		     "Display callchains using output_type (graph, flat, fractal, or none) and min percent threshold. "
-		     "Default: fractal,0.5", &parse_callchain_opt, callchain_default_opt),
+	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", &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. "
+		    "Default: " __stringify(PERF_MAX_STACK_DEPTH)),
+	OPT_BOOLEAN('G', "inverted", &report.inverted_callchain,
+		    "alias for inverted call graph"),
+	OPT_CALLBACK(0, "ignore-callees", NULL, "regex",
+		   "ignore callees of these functions in call graphs",
+		   report_parse_ignore_callees_opt),
 	OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
 		   "only consider symbols in these dsos"),
-	OPT_STRING('C', "comms", &symbol_conf.comm_list_str, "comm[,comm...]",
+	OPT_STRING('c', "comms", &symbol_conf.comm_list_str, "comm[,comm...]",
 		   "only consider symbols in these comms"),
 	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
 		   "only consider these symbols"),
+	OPT_STRING(0, "symbol-filter", &report.symbol_filter_str, "filter",
+		   "only show symbols that (partially) match with this filter"),
 	OPT_STRING('w', "column-widths", &symbol_conf.col_width_list_str,
 		   "width[,width...]",
 		   "don't try to adjust column width, use these fixed values"),
 	OPT_STRING('t', "field-separator", &symbol_conf.field_sep, "separator",
 		   "separator for columns, no spaces will be added between "
 		   "columns '.' is reserved."),
-	OPT_BOOLEAN('U', "hide-unresolved", &hide_unresolved,
+	OPT_BOOLEAN('U', "hide-unresolved", &report.hide_unresolved,
 		    "Only display entries resolved to a symbol"),
 	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
 		    "Look for files with symbols relative to this directory"),
+	OPT_STRING('C', "cpu", &report.cpu_list, "cpu",
+		   "list of cpus to profile"),
+	OPT_BOOLEAN('I', "show-info", &report.show_full_info,
+		    "Display extended information about perf.data file"),
+	OPT_BOOLEAN(0, "source", &symbol_conf.annotate_src,
+		    "Interleave source code with assembly code (default)"),
+	OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw,
+		    "Display raw encoding of assembly instructions (default)"),
+	OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
+		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
+	OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
+		    "Show a column with the sum of periods"),
+	OPT_BOOLEAN(0, "group", &symbol_conf.event_group,
+		    "Show event group information together"),
+	OPT_CALLBACK_NOOPT('b', "branch-stack", &branch_mode, "",
+		    "use branch records for histogram filling", parse_branch_mode),
+	OPT_STRING(0, "objdump", &objdump_path, "path",
+		   "objdump binary to use for disassembly and annotations"),
+	OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
+		    "Disable symbol demangling"),
+	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 = {
+		.mode  = PERF_DATA_MODE_READ,
+	};
+
+	perf_config(report__config, &report);
 
-int cmd_report(int argc, const char **argv, const char *prefix __used)
-{
 	argc = parse_options(argc, argv, options, report_usage, 0);
 
-	if (use_stdio)
+	if (report.use_stdio)
 		use_browser = 0;
-	else if (use_tui)
+	else if (report.use_tui)
 		use_browser = 1;
+	else if (report.use_gtk)
+		use_browser = 2;
+
+	if (report.inverted_callchain)
+		callchain_param.order = ORDER_CALLER;
+
+	if (!input_name || !strlen(input_name)) {
+		if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode))
+			input_name = "-";
+		else
+			input_name = "perf.data";
+	}
+
+	file.path  = input_name;
+	file.force = report.force;
+
+repeat:
+	session = perf_session__new(&file, false, &report.tool);
+	if (session == NULL)
+		return -ENOMEM;
+
+	report.session = session;
+
+	has_br_stack = perf_header__has_feat(&session->header,
+					     HEADER_BRANCH_STACK);
+
+	if (branch_mode == -1 && has_br_stack) {
+		sort__mode = SORT_MODE__BRANCH;
+		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;
+		symbol_conf.cumulate_callchain = false;
+	}
+
+	if (setup_sorting() < 0) {
+		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;
+	}
+
+	/* Force tty output for header output. */
+	if (report.header || report.header_only)
+		use_browser = 0;
 
 	if (strcmp(input_name, "-") != 0)
-		setup_browser();
+		setup_browser(true);
 	else
 		use_browser = 0;
+
+	if (report.header || report.header_only) {
+		perf_session__fprintf_info(session, stdout,
+					   report.show_full_info);
+		if (report.header_only)
+			return 0;
+	} else if (use_browser == 0) {
+		fputs("# To display the perf.data header info, please use --header/--header-only options.\n#\n",
+		      stdout);
+	}
+
 	/*
-	 * Only in the newt browser we are doing integrated annotation,
+	 * Only in the TUI browser we are doing integrated annotation,
 	 * so don't allocate extra space that won't be used in the stdio
 	 * implementation.
 	 */
-	if (use_browser > 0) {
-		symbol_conf.priv_size = sizeof(struct sym_priv);
+	if (ui__has_annotation()) {
+		symbol_conf.priv_size = sizeof(struct annotation);
+		machines__set_symbol_filter(&session->machines,
+					    symbol__annotate_init);
 		/*
  		 * For searching by name on the "Browse map details".
  		 * providing it only in verbose mode not to bloat too
@@ -526,26 +788,29 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 	}
 
 	if (symbol__init() < 0)
-		return -1;
+		goto error;
 
-	setup_sorting(report_usage, options);
+	if (argc) {
+		/*
+		 * Special case: if there's an argument left then assume that
+		 * it's a symbol filter:
+		 */
+		if (argc > 1)
+			usage_with_options(report_usage, options);
 
-	if (parent_pattern != default_parent_pattern) {
-		if (sort_dimension__add("parent") < 0)
-			return -1;
-		sort_parent.elide = 1;
-	} else
-		symbol_conf.exclude_other = false;
+		report.symbol_filter_str = argv[0];
+	}
 
-	/*
-	 * Any (unrecognized) arguments left?
-	 */
-	if (argc)
-		usage_with_options(report_usage, options);
+	sort__setup_elide(stdout);
 
-	sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", stdout);
-	sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list, "comm", stdout);
-	sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", stdout);
+	ret = __cmd_report(&report);
+	if (ret == K_SWITCH_INPUT_DATA) {
+		perf_session__delete(session);
+		goto repeat;
+	} else
+		ret = 0;
 
-	return __cmd_report();
+error:
+	perf_session__delete(session);
+	return ret;
 }