1 files changed, 220 insertions, 154 deletions

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index f2ed2b7e80a3..f5fbd670d619 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -31,6 +31,7 @@
 #include "util/evsel.h"
 #include "util/evswitch.h"
 #include "util/header.h"
+#include "util/mem-info.h"
 #include "util/session.h"
 #include "util/srcline.h"
 #include "util/tool.h"
@@ -59,6 +60,7 @@
 #include <linux/ctype.h>
 #include <signal.h>
 #include <linux/bitmap.h>
+#include <linux/list_sort.h>
 #include <linux/string.h>
 #include <linux/stringify.h>
 #include <linux/time64.h>
@@ -68,7 +70,7 @@
 #include <linux/mman.h>
 
 #ifdef HAVE_LIBTRACEEVENT
-#include <traceevent/event-parse.h>
+#include <event-parse.h>
 #endif
 
 struct report {
@@ -171,7 +173,7 @@ static int hist_iter__report_callback(struct hist_entry_iter *iter,
 	struct mem_info *mi;
 	struct branch_info *bi;
 
-	if (!ui__has_annotation() && !rep->symbol_ipc && !rep->data_type)
+	if (!ui__has_annotation() && !rep->symbol_ipc)
 		return 0;
 
 	if (sort__mode == SORT_MODE__BRANCH) {
@@ -184,7 +186,7 @@ static int hist_iter__report_callback(struct hist_entry_iter *iter,
 
 	} else if (rep->mem_mode) {
 		mi = he->mem_info;
-		err = addr_map_symbol__inc_samples(&mi->daddr, sample, evsel);
+		err = addr_map_symbol__inc_samples(mem_info__daddr(mi), sample, evsel);
 		if (err)
 			goto out;
 
@@ -261,7 +263,7 @@ static int process_feature_event(struct perf_session *session,
 	return 0;
 }
 
-static int process_sample_event(struct perf_tool *tool,
+static int process_sample_event(const struct perf_tool *tool,
 				union perf_event *event,
 				struct perf_sample *sample,
 				struct evsel *evsel,
@@ -321,12 +323,12 @@ static int process_sample_event(struct perf_tool *tool,
 	}
 
 	if (al.map != NULL)
-		map__dso(al.map)->hit = 1;
+		dso__set_hit(map__dso(al.map));
 
 	if (ui__has_annotation() || rep->symbol_ipc || rep->total_cycles_mode) {
 		hist__account_cycles(sample->branch_stack, &al, sample,
 				     rep->nonany_branch_mode,
-				     &rep->total_cycles);
+				     &rep->total_cycles, evsel);
 	}
 
 	ret = hist_entry_iter__add(&iter, &al, rep->max_stack, rep);
@@ -337,7 +339,7 @@ out_put:
 	return ret;
 }
 
-static int process_read_event(struct perf_tool *tool,
+static int process_read_event(const struct perf_tool *tool,
 			      union perf_event *event,
 			      struct perf_sample *sample __maybe_unused,
 			      struct evsel *evsel,
@@ -346,11 +348,9 @@ static int process_read_event(struct perf_tool *tool,
 	struct report *rep = container_of(tool, struct report, tool);
 
 	if (rep->show_threads) {
-		const char *name = evsel__name(evsel);
 		int err = perf_read_values_add_value(&rep->show_threads_values,
 					   event->read.pid, event->read.tid,
-					   evsel->core.idx,
-					   name,
+					   evsel,
 					   event->read.value);
 
 		if (err)
@@ -427,7 +427,7 @@ static int report__setup_sample_type(struct report *rep)
 		 * compatibility, set the bit if it's an old perf data file.
 		 */
 		evlist__for_each_entry(session->evlist, evsel) {
-			if (strstr(evsel->name, "arm_spe") &&
+			if (strstr(evsel__name(evsel), "arm_spe") &&
 				!(sample_type & PERF_SAMPLE_DATA_SRC)) {
 				evsel->core.attr.sample_type |= PERF_SAMPLE_DATA_SRC;
 				sample_type |= PERF_SAMPLE_DATA_SRC;
@@ -453,7 +453,7 @@ static int report__setup_sample_type(struct report *rep)
 	if (!(evlist__combined_branch_type(session->evlist) & PERF_SAMPLE_BRANCH_ANY))
 		rep->nonany_branch_mode = true;
 
-#if !defined(HAVE_LIBUNWIND_SUPPORT) && !defined(HAVE_DWARF_SUPPORT)
+#if !defined(HAVE_LIBUNWIND_SUPPORT) && !defined(HAVE_LIBDW_SUPPORT)
 	if (dwarf_callchain_users) {
 		ui__warning("Please install libunwind or libdw "
 			    "development packages during the perf build.\n");
@@ -563,6 +563,7 @@ static int evlist__tty_browse_hists(struct evlist *evlist, struct report *rep, c
 		struct hists *hists = evsel__hists(pos);
 		const char *evname = evsel__name(pos);
 
+		i++;
 		if (symbol_conf.event_group && !evsel__is_group_leader(pos))
 			continue;
 
@@ -572,7 +573,14 @@ static int evlist__tty_browse_hists(struct evlist *evlist, struct report *rep, c
 		hists__fprintf_nr_sample_events(hists, rep, evname, stdout);
 
 		if (rep->total_cycles_mode) {
-			report__browse_block_hists(&rep->block_reports[i++].hist,
+			char *buf;
+
+			if (!annotation_br_cntr_abbr_list(&buf, pos, true)) {
+				fprintf(stdout, "%s", buf);
+				fprintf(stdout, "#\n");
+				free(buf);
+			}
+			report__browse_block_hists(&rep->block_reports[i - 1].hist,
 						   rep->min_percent, pos, NULL);
 			continue;
 		}
@@ -608,7 +616,7 @@ static void report__warn_kptr_restrict(const struct report *rep)
 		return;
 
 	if (kernel_map == NULL ||
-	     (map__dso(kernel_map)->hit &&
+	    (dso__hit(map__dso(kernel_map)) &&
 	     (kernel_kmap->ref_reloc_sym == NULL ||
 	      kernel_kmap->ref_reloc_sym->addr == 0))) {
 		const char *desc =
@@ -763,7 +771,7 @@ static void report__output_resort(struct report *rep)
 	ui_progress__finish();
 }
 
-static int count_sample_event(struct perf_tool *tool __maybe_unused,
+static int count_sample_event(const struct perf_tool *tool __maybe_unused,
 			      union perf_event *event __maybe_unused,
 			      struct perf_sample *sample __maybe_unused,
 			      struct evsel *evsel,
@@ -775,7 +783,7 @@ static int count_sample_event(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-static int count_lost_samples_event(struct perf_tool *tool,
+static int count_lost_samples_event(const struct perf_tool *tool,
 				    union perf_event *event,
 				    struct perf_sample *sample,
 				    struct machine *machine __maybe_unused)
@@ -785,22 +793,28 @@ static int count_lost_samples_event(struct perf_tool *tool,
 
 	evsel = evlist__id2evsel(rep->session->evlist, sample->id);
 	if (evsel) {
-		hists__inc_nr_lost_samples(evsel__hists(evsel),
-					   event->lost_samples.lost);
+		struct hists *hists = evsel__hists(evsel);
+		u32 count = event->lost_samples.lost;
+
+		if (event->header.misc & PERF_RECORD_MISC_LOST_SAMPLES_BPF)
+			hists__inc_nr_dropped_samples(hists, count);
+		else
+			hists__inc_nr_lost_samples(hists, count);
 	}
 	return 0;
 }
 
-static int process_attr(struct perf_tool *tool __maybe_unused,
+static int process_attr(const struct perf_tool *tool __maybe_unused,
 			union perf_event *event,
 			struct evlist **pevlist);
 
 static void stats_setup(struct report *rep)
 {
-	memset(&rep->tool, 0, sizeof(rep->tool));
+	perf_tool__init(&rep->tool, /*ordered_events=*/false);
 	rep->tool.attr = process_attr;
 	rep->tool.sample = count_sample_event;
 	rep->tool.lost_samples = count_lost_samples_event;
+	rep->tool.event_update = perf_event__process_event_update;
 	rep->tool.no_warn = true;
 }
 
@@ -808,15 +822,14 @@ static int stats_print(struct report *rep)
 {
 	struct perf_session *session = rep->session;
 
-	perf_session__fprintf_nr_events(session, stdout, rep->skip_empty);
-	evlist__fprintf_nr_events(session->evlist, stdout, rep->skip_empty);
+	perf_session__fprintf_nr_events(session, stdout);
+	evlist__fprintf_nr_events(session->evlist, stdout);
 	return 0;
 }
 
 static void tasks_setup(struct report *rep)
 {
-	memset(&rep->tool, 0, sizeof(rep->tool));
-	rep->tool.ordered_events = true;
+	perf_tool__init(&rep->tool, /*ordered_events=*/true);
 	if (rep->mmaps_mode) {
 		rep->tool.mmap = perf_event__process_mmap;
 		rep->tool.mmap2 = perf_event__process_mmap2;
@@ -828,35 +841,6 @@ static void tasks_setup(struct report *rep)
 	rep->tool.no_warn = true;
 }
 
-struct task {
-	struct thread		*thread;
-	struct list_head	 list;
-	struct list_head	 children;
-};
-
-static struct task *tasks_list(struct task *task, struct machine *machine)
-{
-	struct thread *parent_thread, *thread = task->thread;
-	struct task   *parent_task;
-
-	/* Already listed. */
-	if (!list_empty(&task->list))
-		return NULL;
-
-	/* Last one in the chain. */
-	if (thread__ppid(thread) == -1)
-		return task;
-
-	parent_thread = machine__find_thread(machine, -1, thread__ppid(thread));
-	if (!parent_thread)
-		return ERR_PTR(-ENOENT);
-
-	parent_task = thread__priv(parent_thread);
-	thread__put(parent_thread);
-	list_add_tail(&task->list, &parent_task->children);
-	return tasks_list(parent_task, machine);
-}
-
 struct maps__fprintf_task_args {
 	int indent;
 	FILE *fp;
@@ -878,7 +862,7 @@ static int maps__fprintf_task_cb(struct map *map, void *data)
 		prot & PROT_EXEC ? 'x' : '-',
 		map__flags(map) ? 's' : 'p',
 		map__pgoff(map),
-		dso->id.ino, dso->name);
+		dso__id_const(dso)->ino, dso__name(dso));
 
 	if (ret < 0)
 		return ret;
@@ -900,89 +884,156 @@ static size_t maps__fprintf_task(struct maps *maps, int indent, FILE *fp)
 	return args.printed;
 }
 
-static void task__print_level(struct task *task, FILE *fp, int level)
+static int thread_level(struct machine *machine, const struct thread *thread)
 {
-	struct thread *thread = task->thread;
-	struct task *child;
-	int comm_indent = fprintf(fp, "  %8d %8d %8d |%*s",
-				  thread__pid(thread), thread__tid(thread),
-				  thread__ppid(thread), level, "");
+	struct thread *parent_thread;
+	int res;
 
-	fprintf(fp, "%s\n", thread__comm_str(thread));
+	if (thread__tid(thread) <= 0)
+		return 0;
 
-	maps__fprintf_task(thread__maps(thread), comm_indent, fp);
+	if (thread__ppid(thread) <= 0)
+		return 1;
 
-	if (!list_empty(&task->children)) {
-		list_for_each_entry(child, &task->children, list)
-			task__print_level(child, fp, level + 1);
+	parent_thread = machine__find_thread(machine, -1, thread__ppid(thread));
+	if (!parent_thread) {
+		pr_err("Missing parent thread of %d\n", thread__tid(thread));
+		return 0;
 	}
+	res = 1 + thread_level(machine, parent_thread);
+	thread__put(parent_thread);
+	return res;
 }
 
-static int tasks_print(struct report *rep, FILE *fp)
+static void task__print_level(struct machine *machine, struct thread *thread, FILE *fp)
 {
-	struct perf_session *session = rep->session;
-	struct machine      *machine = &session->machines.host;
-	struct task *tasks, *task;
-	unsigned int nr = 0, itask = 0, i;
-	struct rb_node *nd;
-	LIST_HEAD(list);
+	int level = thread_level(machine, thread);
+	int comm_indent = fprintf(fp, "  %8d %8d %8d |%*s",
+				  thread__pid(thread), thread__tid(thread),
+				  thread__ppid(thread), level, "");
 
-	/*
-	 * No locking needed while accessing machine->threads,
-	 * because --tasks is single threaded command.
-	 */
+	fprintf(fp, "%s\n", thread__comm_str(thread));
 
-	/* Count all the threads. */
-	for (i = 0; i < THREADS__TABLE_SIZE; i++)
-		nr += machine->threads[i].nr;
+	maps__fprintf_task(thread__maps(thread), comm_indent, fp);
+}
 
-	tasks = malloc(sizeof(*tasks) * nr);
-	if (!tasks)
-		return -ENOMEM;
+/*
+ * Sort two thread list nodes such that they form a tree. The first node is the
+ * root of the tree, its children are ordered numerically after it. If a child
+ * has children itself then they appear immediately after their parent. For
+ * example, the 4 threads in the order they'd appear in the list:
+ * - init with a TID 1 and a parent of 0
+ * - systemd with a TID 3000 and a parent of init/1
+ * - systemd child thread with TID 4000, the parent is 3000
+ * - NetworkManager is a child of init with a TID of 3500.
+ */
+static int task_list_cmp(void *priv, const struct list_head *la, const struct list_head *lb)
+{
+	struct machine *machine = priv;
+	struct thread_list *task_a = list_entry(la, struct thread_list, list);
+	struct thread_list *task_b = list_entry(lb, struct thread_list, list);
+	struct thread *a = task_a->thread;
+	struct thread *b = task_b->thread;
+	int level_a, level_b, res;
+
+	/* Same thread? */
+	if (thread__tid(a) == thread__tid(b))
+		return 0;
 
-	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
-		struct threads *threads = &machine->threads[i];
+	/* Compare a and b to root. */
+	if (thread__tid(a) == 0)
+		return -1;
 
-		for (nd = rb_first_cached(&threads->entries); nd;
-		     nd = rb_next(nd)) {
-			task = tasks + itask++;
+	if (thread__tid(b) == 0)
+		return 1;
 
-			task->thread = rb_entry(nd, struct thread_rb_node, rb_node)->thread;
-			INIT_LIST_HEAD(&task->children);
-			INIT_LIST_HEAD(&task->list);
-			thread__set_priv(task->thread, task);
-		}
-	}
+	/* If parents match sort by tid. */
+	if (thread__ppid(a) == thread__ppid(b))
+		return thread__tid(a) < thread__tid(b) ? -1 : 1;
 
 	/*
-	 * Iterate every task down to the unprocessed parent
-	 * and link all in task children list. Task with no
-	 * parent is added into 'list'.
+	 * Find a and b such that if they are a child of each other a and b's
+	 * tid's match, otherwise a and b have a common parent and distinct
+	 * tid's to sort by. First make the depths of the threads match.
 	 */
-	for (itask = 0; itask < nr; itask++) {
-		task = tasks + itask;
-
-		if (!list_empty(&task->list))
-			continue;
-
-		task = tasks_list(task, machine);
-		if (IS_ERR(task)) {
-			pr_err("Error: failed to process tasks\n");
-			free(tasks);
-			return PTR_ERR(task);
+	level_a = thread_level(machine, a);
+	level_b = thread_level(machine, b);
+	a = thread__get(a);
+	b = thread__get(b);
+	for (int i = level_a; i > level_b; i--) {
+		struct thread *parent = machine__find_thread(machine, -1, thread__ppid(a));
+
+		thread__put(a);
+		if (!parent) {
+			pr_err("Missing parent thread of %d\n", thread__tid(a));
+			thread__put(b);
+			return -1;
 		}
+		a = parent;
+	}
+	for (int i = level_b; i > level_a; i--) {
+		struct thread *parent = machine__find_thread(machine, -1, thread__ppid(b));
 
-		if (task)
-			list_add_tail(&task->list, &list);
+		thread__put(b);
+		if (!parent) {
+			pr_err("Missing parent thread of %d\n", thread__tid(b));
+			thread__put(a);
+			return 1;
+		}
+		b = parent;
+	}
+	/* Search up to a common parent. */
+	while (thread__ppid(a) != thread__ppid(b)) {
+		struct thread *parent;
+
+		parent = machine__find_thread(machine, -1, thread__ppid(a));
+		thread__put(a);
+		if (!parent)
+			pr_err("Missing parent thread of %d\n", thread__tid(a));
+		a = parent;
+		parent = machine__find_thread(machine, -1, thread__ppid(b));
+		thread__put(b);
+		if (!parent)
+			pr_err("Missing parent thread of %d\n", thread__tid(b));
+		b = parent;
+		if (!a || !b) {
+			/* Handle missing parent (unexpected) with some sanity. */
+			thread__put(a);
+			thread__put(b);
+			return !a && !b ? 0 : (!a ? -1 : 1);
+		}
 	}
+	if (thread__tid(a) == thread__tid(b)) {
+		/* a is a child of b or vice-versa, deeper levels appear later. */
+		res = level_a < level_b ? -1 : (level_a > level_b ? 1 : 0);
+	} else {
+		/* Sort by tid now the parent is the same. */
+		res = thread__tid(a) < thread__tid(b) ? -1 : 1;
+	}
+	thread__put(a);
+	thread__put(b);
+	return res;
+}
 
-	fprintf(fp, "# %8s %8s %8s  %s\n", "pid", "tid", "ppid", "comm");
+static int tasks_print(struct report *rep, FILE *fp)
+{
+	struct machine *machine = &rep->session->machines.host;
+	LIST_HEAD(tasks);
+	int ret;
 
-	list_for_each_entry(task, &list, list)
-		task__print_level(task, fp, 0);
+	ret = machine__thread_list(machine, &tasks);
+	if (!ret) {
+		struct thread_list *task;
 
-	free(tasks);
-	return 0;
+		list_sort(machine, &tasks, task_list_cmp);
+
+		fprintf(fp, "# %8s %8s %8s  %s\n", "pid", "tid", "ppid", "comm");
+
+		list_for_each_entry(task, &tasks, list)
+			task__print_level(machine, task->thread, fp);
+	}
+	thread_list__delete(&tasks);
+	return ret;
 }
 
 static int __cmd_report(struct report *rep)
@@ -1049,10 +1100,7 @@ static int __cmd_report(struct report *rep)
 			perf_session__fprintf_dsos(session, stdout);
 
 		if (dump_trace) {
-			perf_session__fprintf_nr_events(session, stdout,
-							rep->skip_empty);
-			evlist__fprintf_nr_events(session->evlist, stdout,
-						  rep->skip_empty);
+			stats_print(rep);
 			return 0;
 		}
 	}
@@ -1082,18 +1130,23 @@ static int __cmd_report(struct report *rep)
 	report__output_resort(rep);
 
 	if (rep->total_cycles_mode) {
-		int block_hpps[6] = {
+		int nr_hpps = 4;
+		int block_hpps[PERF_HPP_REPORT__BLOCK_MAX_INDEX] = {
 			PERF_HPP_REPORT__BLOCK_TOTAL_CYCLES_PCT,
 			PERF_HPP_REPORT__BLOCK_LBR_CYCLES,
 			PERF_HPP_REPORT__BLOCK_CYCLES_PCT,
 			PERF_HPP_REPORT__BLOCK_AVG_CYCLES,
-			PERF_HPP_REPORT__BLOCK_RANGE,
-			PERF_HPP_REPORT__BLOCK_DSO,
 		};
 
+		if (session->evlist->nr_br_cntr > 0)
+			block_hpps[nr_hpps++] = PERF_HPP_REPORT__BLOCK_BRANCH_COUNTER;
+
+		block_hpps[nr_hpps++] = PERF_HPP_REPORT__BLOCK_RANGE;
+		block_hpps[nr_hpps++] = PERF_HPP_REPORT__BLOCK_DSO;
+
 		rep->block_reports = block_info__create_report(session->evlist,
 							       rep->total_cycles,
-							       block_hpps, 6,
+							       block_hpps, nr_hpps,
 							       &rep->nr_block_reports);
 		if (!rep->block_reports)
 			return -1;
@@ -1196,7 +1249,7 @@ parse_percent_limit(const struct option *opt, const char *str,
 	return 0;
 }
 
-static int process_attr(struct perf_tool *tool __maybe_unused,
+static int process_attr(const struct perf_tool *tool __maybe_unused,
 			union perf_event *event,
 			struct evlist **pevlist)
 {
@@ -1216,6 +1269,10 @@ static int process_attr(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
+#define CALLCHAIN_BRANCH_SORT_ORDER	\
+	"srcline,symbol,dso,callchain_branch_predicted," \
+	"callchain_branch_abort,callchain_branch_cycles"
+
 int cmd_report(int argc, const char **argv)
 {
 	struct perf_session *session;
@@ -1235,37 +1292,13 @@ int cmd_report(int argc, const char **argv)
 		NULL
 	};
 	struct report report = {
-		.tool = {
-			.sample		 = process_sample_event,
-			.mmap		 = perf_event__process_mmap,
-			.mmap2		 = perf_event__process_mmap2,
-			.comm		 = perf_event__process_comm,
-			.namespaces	 = perf_event__process_namespaces,
-			.cgroup		 = perf_event__process_cgroup,
-			.exit		 = perf_event__process_exit,
-			.fork		 = perf_event__process_fork,
-			.lost		 = perf_event__process_lost,
-			.read		 = process_read_event,
-			.attr		 = process_attr,
-#ifdef HAVE_LIBTRACEEVENT
-			.tracing_data	 = perf_event__process_tracing_data,
-#endif
-			.build_id	 = perf_event__process_build_id,
-			.id_index	 = perf_event__process_id_index,
-			.auxtrace_info	 = perf_event__process_auxtrace_info,
-			.auxtrace	 = perf_event__process_auxtrace,
-			.event_update	 = perf_event__process_event_update,
-			.feature	 = process_feature_event,
-			.ordered_events	 = true,
-			.ordering_requires_timestamps = true,
-		},
 		.max_stack		 = PERF_MAX_STACK_DEPTH,
 		.pretty_printing_style	 = "normal",
 		.socket_filter		 = -1,
 		.skip_empty		 = true,
 	};
-	char *sort_order_help = sort_help("sort by key(s):");
-	char *field_order_help = sort_help("output field(s): overhead period sample ");
+	char *sort_order_help = sort_help("sort by key(s):", SORT_MODE__NORMAL);
+	char *field_order_help = sort_help("output field(s):", SORT_MODE__NORMAL);
 	const char *disassembler_style = NULL, *objdump_path = NULL, *addr2line_path = NULL;
 	const struct option options[] = {
 	OPT_STRING('i', "input", &input_name, "file",
@@ -1387,7 +1420,7 @@ int cmd_report(int argc, const char **argv)
 	OPT_STRING(0, "addr2line", &addr2line_path, "path",
 		   "addr2line binary to use for line numbers"),
 	OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
-		    "Disable symbol demangling"),
+		    "Symbol demangling. Enabled by default, use --no-demangle to disable."),
 	OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
 		    "Enable kernel symbol demangling"),
 	OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"),
@@ -1410,7 +1443,7 @@ int cmd_report(int argc, const char **argv)
 		    "only show processor socket that match with this filter"),
 	OPT_BOOLEAN(0, "raw-trace", &symbol_conf.raw_trace,
 		    "Show raw trace event output (do not use print fmt or plugins)"),
-	OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy,
+	OPT_BOOLEAN('H', "hierarchy", &symbol_conf.report_hierarchy,
 		    "Show entries in a hierarchy"),
 	OPT_CALLBACK_DEFAULT(0, "stdio-color", NULL, "mode",
 			     "'always' (default), 'never' or 'auto' only applicable to --stdio mode",
@@ -1440,6 +1473,7 @@ int cmd_report(int argc, const char **argv)
 	};
 	int ret = hists__init();
 	char sort_tmp[128];
+	bool ordered_events = true;
 
 	if (ret < 0)
 		goto exit;
@@ -1494,7 +1528,7 @@ int cmd_report(int argc, const char **argv)
 		report.tasks_mode = true;
 
 	if (dump_trace && report.disable_order)
-		report.tool.ordered_events = false;
+		ordered_events = false;
 
 	if (quiet)
 		perf_quiet_option();
@@ -1522,7 +1556,32 @@ int cmd_report(int argc, const char **argv)
 	data.path  = input_name;
 	data.force = symbol_conf.force;
 
+	symbol_conf.skip_empty = report.skip_empty;
+
 repeat:
+	perf_tool__init(&report.tool, ordered_events);
+	report.tool.sample		 = process_sample_event;
+	report.tool.mmap		 = perf_event__process_mmap;
+	report.tool.mmap2		 = perf_event__process_mmap2;
+	report.tool.comm		 = perf_event__process_comm;
+	report.tool.namespaces		 = perf_event__process_namespaces;
+	report.tool.cgroup		 = perf_event__process_cgroup;
+	report.tool.exit		 = perf_event__process_exit;
+	report.tool.fork		 = perf_event__process_fork;
+	report.tool.lost		 = perf_event__process_lost;
+	report.tool.read		 = process_read_event;
+	report.tool.attr		 = process_attr;
+#ifdef HAVE_LIBTRACEEVENT
+	report.tool.tracing_data	 = perf_event__process_tracing_data;
+#endif
+	report.tool.build_id		 = perf_event__process_build_id;
+	report.tool.id_index		 = perf_event__process_id_index;
+	report.tool.auxtrace_info	 = perf_event__process_auxtrace_info;
+	report.tool.auxtrace		 = perf_event__process_auxtrace;
+	report.tool.event_update	 = perf_event__process_event_update;
+	report.tool.feature		 = process_feature_event;
+	report.tool.ordering_requires_timestamps = true;
+
 	session = perf_session__new(&data, &report.tool);
 	if (IS_ERR(session)) {
 		ret = PTR_ERR(session);
@@ -1582,7 +1641,7 @@ repeat:
 		symbol_conf.use_callchain = true;
 		callchain_register_param(&callchain_param);
 		if (sort_order == NULL)
-			sort_order = "srcline,symbol,dso";
+			sort_order = CALLCHAIN_BRANCH_SORT_ORDER;
 	}
 
 	if (report.mem_mode) {
@@ -1644,7 +1703,7 @@ repeat:
 		report.data_type = true;
 		annotate_opts.annotate_src = false;
 
-#ifndef HAVE_DWARF_GETLOCATIONS_SUPPORT
+#ifndef HAVE_LIBDW_SUPPORT
 		pr_err("Error: Data type profiling is disabled due to missing DWARF support\n");
 		goto error;
 #endif
@@ -1655,6 +1714,11 @@ repeat:
 	else
 		use_browser = 0;
 
+	if (report.data_type && use_browser == 1) {
+		symbol_conf.annotate_data_member = true;
+		symbol_conf.annotate_data_sample = true;
+	}
+
 	if (sort_order && strstr(sort_order, "ipc")) {
 		parse_options_usage(report_usage, options, "s", 1);
 		goto error;
@@ -1766,6 +1830,8 @@ repeat:
 	} else
 		ret = 0;
 
+	if (!use_browser && (verbose > 2 || debug_kmaps))
+		perf_session__dump_kmaps(session);
 error:
 	if (report.ptime_range) {
 		itrace_synth_opts__clear_time_range(&itrace_synth_opts);