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

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

New features:

  - Introduce PERF_RECORD_SWITCH(_CPU_WIDE) and use it in 'record' to
    ask for context switches, allowing non priviledged tasks to know
    when they are switched in and out, which wasn't possible with
    the other context switch tracepoint and software events, see the
    patch description for a comprehensive justification (Adrian Hunter)

  - Stop collecting /proc/kallsyms in perf.data files, saving about
    4.5MB on a typical x86-64 system, use the the symbol resolution
    routines used in all the other tools (report, top, etc) now that
    we can ask libtraceevent to use perf's symbol resolution code.
    (Arnaldo Carvalho de Melo)

User visible fixes:

  - Expose perf's symbol resolver to libtraceevent, so that its plugins can
    resolve tracepoint fields to kernel functions, like the 'function' field
    in the "timer:hrtimer_start tracepoint" (Arnaldo Carvalho de Melo)

Infrastructure changes:

  - Map propagation of thread and cpu maps improvements, prep work for
    'perf stat' new features (Jiri Olsa)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

21 files changed, 238 insertions, 103 deletions

diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 2fe98bb0e95b..c73276db6d6f 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -137,6 +137,10 @@ struct dso {
 	struct rb_node	 rb_node;	/* rbtree node sorted by long name */
 	struct rb_root	 symbols[MAP__NR_TYPES];
 	struct rb_root	 symbol_names[MAP__NR_TYPES];
+	struct {
+		u64		addr;
+		struct symbol	*symbol;
+	} last_find_result[MAP__NR_TYPES];
 	void		 *a2l;
 	char		 *symsrc_filename;
 	unsigned int	 a2l_fails;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 67a977e5d0ab..7ff61274ed57 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -26,6 +26,8 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_AUX]			= "AUX",
 	[PERF_RECORD_ITRACE_START]		= "ITRACE_START",
 	[PERF_RECORD_LOST_SAMPLES]		= "LOST_SAMPLES",
+	[PERF_RECORD_SWITCH]			= "SWITCH",
+	[PERF_RECORD_SWITCH_CPU_WIDE]		= "SWITCH_CPU_WIDE",
 	[PERF_RECORD_HEADER_ATTR]		= "ATTR",
 	[PERF_RECORD_HEADER_EVENT_TYPE]		= "EVENT_TYPE",
 	[PERF_RECORD_HEADER_TRACING_DATA]	= "TRACING_DATA",
@@ -749,6 +751,14 @@ int perf_event__process_lost_samples(struct perf_tool *tool __maybe_unused,
 	return machine__process_lost_samples_event(machine, event, sample);
 }
 
+int perf_event__process_switch(struct perf_tool *tool __maybe_unused,
+			       union perf_event *event,
+			       struct perf_sample *sample __maybe_unused,
+			       struct machine *machine)
+{
+	return machine__process_switch_event(machine, event);
+}
+
 size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
 {
 	return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %c %s\n",
@@ -827,6 +837,20 @@ size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp)
 		       event->itrace_start.pid, event->itrace_start.tid);
 }
 
+size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp)
+{
+	bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT;
+	const char *in_out = out ? "OUT" : "IN ";
+
+	if (event->header.type == PERF_RECORD_SWITCH)
+		return fprintf(fp, " %s\n", in_out);
+
+	return fprintf(fp, " %s  %s pid/tid: %5u/%-5u\n",
+		       in_out, out ? "next" : "prev",
+		       event->context_switch.next_prev_pid,
+		       event->context_switch.next_prev_tid);
+}
+
 size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 {
 	size_t ret = fprintf(fp, "PERF_RECORD_%s",
@@ -852,6 +876,10 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 	case PERF_RECORD_ITRACE_START:
 		ret += perf_event__fprintf_itrace_start(event, fp);
 		break;
+	case PERF_RECORD_SWITCH:
+	case PERF_RECORD_SWITCH_CPU_WIDE:
+		ret += perf_event__fprintf_switch(event, fp);
+		break;
 	default:
 		ret += fprintf(fp, "\n");
 	}
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index c53f36384b64..4bb2ae894c78 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -348,6 +348,12 @@ struct itrace_start_event {
 	u32 pid, tid;
 };
 
+struct context_switch_event {
+	struct perf_event_header header;
+	u32 next_prev_pid;
+	u32 next_prev_tid;
+};
+
 union perf_event {
 	struct perf_event_header	header;
 	struct mmap_event		mmap;
@@ -369,6 +375,7 @@ union perf_event {
 	struct auxtrace_error_event	auxtrace_error;
 	struct aux_event		aux;
 	struct itrace_start_event	itrace_start;
+	struct context_switch_event	context_switch;
 };
 
 void perf_event__print_totals(void);
@@ -418,6 +425,10 @@ int perf_event__process_itrace_start(struct perf_tool *tool,
 				     union perf_event *event,
 				     struct perf_sample *sample,
 				     struct machine *machine);
+int perf_event__process_switch(struct perf_tool *tool,
+			       union perf_event *event,
+			       struct perf_sample *sample,
+			       struct machine *machine);
 int perf_event__process_mmap(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_sample *sample,
@@ -480,6 +491,7 @@ size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_task(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf(union perf_event *event, FILE *fp);
 
 u64 kallsyms__get_function_start(const char *kallsyms_filename,
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index f7d9c77ee31b..3b9f411a6b46 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1102,7 +1102,7 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 }
 
 static int perf_evlist__propagate_maps(struct perf_evlist *evlist,
-				       struct target *target)
+				       bool has_user_cpus)
 {
 	struct perf_evsel *evsel;
 
@@ -1111,15 +1111,16 @@ static int perf_evlist__propagate_maps(struct perf_evlist *evlist,
 		 * We already have cpus for evsel (via PMU sysfs) so
 		 * keep it, if there's no target cpu list defined.
 		 */
-		if (evsel->cpus && target->cpu_list)
+		if (evsel->cpus && has_user_cpus)
 			cpu_map__put(evsel->cpus);
 
-		if (!evsel->cpus || target->cpu_list)
+		if (!evsel->cpus || has_user_cpus)
 			evsel->cpus = cpu_map__get(evlist->cpus);
 
 		evsel->threads = thread_map__get(evlist->threads);
 
-		if (!evsel->cpus || !evsel->threads)
+		if ((evlist->cpus && !evsel->cpus) ||
+		    (evlist->threads && !evsel->threads))
 			return -ENOMEM;
 	}
 
@@ -1142,7 +1143,7 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 	if (evlist->cpus == NULL)
 		goto out_delete_threads;
 
-	return perf_evlist__propagate_maps(evlist, target);
+	return perf_evlist__propagate_maps(evlist, !!target->cpu_list);
 
 out_delete_threads:
 	thread_map__put(evlist->threads);
@@ -1150,6 +1151,23 @@ out_delete_threads:
 	return -1;
 }
 
+int perf_evlist__set_maps(struct perf_evlist *evlist,
+			  struct cpu_map *cpus,
+			  struct thread_map *threads)
+{
+	if (evlist->cpus)
+		cpu_map__put(evlist->cpus);
+
+	evlist->cpus = cpus;
+
+	if (evlist->threads)
+		thread_map__put(evlist->threads);
+
+	evlist->threads = threads;
+
+	return perf_evlist__propagate_maps(evlist, false);
+}
+
 int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel)
 {
 	struct perf_evsel *evsel;
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 037633c1da9d..a8930b68456b 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -114,6 +114,7 @@ void perf_evlist__close(struct perf_evlist *evlist);
 
 void perf_evlist__set_id_pos(struct perf_evlist *evlist);
 bool perf_can_sample_identifier(void);
+bool perf_can_record_switch_events(void);
 void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts);
 int record_opts__config(struct record_opts *opts);
 
@@ -152,14 +153,9 @@ int perf_evlist__enable_event_idx(struct perf_evlist *evlist,
 void perf_evlist__set_selected(struct perf_evlist *evlist,
 			       struct perf_evsel *evsel);
 
-static inline void perf_evlist__set_maps(struct perf_evlist *evlist,
-					 struct cpu_map *cpus,
-					 struct thread_map *threads)
-{
-	evlist->cpus	= cpus;
-	evlist->threads	= threads;
-}
-
+int perf_evlist__set_maps(struct perf_evlist *evlist,
+			  struct cpu_map *cpus,
+			  struct thread_map *threads);
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target);
 int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 49fb7b5feb09..71f6905c7cb9 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -738,6 +738,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	attr->mmap2 = track && !perf_missing_features.mmap2;
 	attr->comm  = track;
 
+	if (opts->record_switch_events)
+		attr->context_switch = track;
+
 	if (opts->sample_transaction)
 		perf_evsel__set_sample_bit(evsel, TRANSACTION);
 
@@ -1127,6 +1130,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 	PRINT_ATTRf(mmap2, p_unsigned);
 	PRINT_ATTRf(comm_exec, p_unsigned);
 	PRINT_ATTRf(use_clockid, p_unsigned);
+	PRINT_ATTRf(context_switch, p_unsigned);
 
 	PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned);
 	PRINT_ATTRf(bp_type, p_unsigned);
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 03ace57a800c..179b2bdd157d 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -923,17 +923,13 @@ static void print_cmdline(struct perf_header *ph, int fd __maybe_unused,
 			  FILE *fp)
 {
 	int nr, i;
-	char *str;
 
 	nr = ph->env.nr_cmdline;
-	str = ph->env.cmdline;
 
 	fprintf(fp, "# cmdline : ");
 
-	for (i = 0; i < nr; i++) {
-		fprintf(fp, "%s ", str);
-		str += strlen(str) + 1;
-	}
+	for (i = 0; i < nr; i++)
+		fprintf(fp, "%s ", ph->env.cmdline_argv[i]);
 	fputc('\n', fp);
 }
 
@@ -1541,14 +1537,13 @@ process_event_desc(struct perf_file_section *section __maybe_unused,
 	return 0;
 }
 
-static int process_cmdline(struct perf_file_section *section __maybe_unused,
+static int process_cmdline(struct perf_file_section *section,
 			   struct perf_header *ph, int fd,
 			   void *data __maybe_unused)
 {
 	ssize_t ret;
-	char *str;
-	u32 nr, i;
-	struct strbuf sb;
+	char *str, *cmdline = NULL, **argv = NULL;
+	u32 nr, i, len = 0;
 
 	ret = readn(fd, &nr, sizeof(nr));
 	if (ret != sizeof(nr))
@@ -1558,22 +1553,32 @@ static int process_cmdline(struct perf_file_section *section __maybe_unused,
 		nr = bswap_32(nr);
 
 	ph->env.nr_cmdline = nr;
-	strbuf_init(&sb, 128);
+
+	cmdline = zalloc(section->size + nr + 1);
+	if (!cmdline)
+		return -1;
+
+	argv = zalloc(sizeof(char *) * (nr + 1));
+	if (!argv)
+		goto error;
 
 	for (i = 0; i < nr; i++) {
 		str = do_read_string(fd, ph);
 		if (!str)
 			goto error;
 
-		/* include a NULL character at the end */
-		strbuf_add(&sb, str, strlen(str) + 1);
+		argv[i] = cmdline + len;
+		memcpy(argv[i], str, strlen(str) + 1);
+		len += strlen(str) + 1;
 		free(str);
 	}
-	ph->env.cmdline = strbuf_detach(&sb, NULL);
+	ph->env.cmdline = cmdline;
+	ph->env.cmdline_argv = (const char **) argv;
 	return 0;
 
 error:
-	strbuf_release(&sb);
+	free(argv);
+	free(cmdline);
 	return -1;
 }
 
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index d4d57962c591..9b53b6525ce8 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -84,6 +84,7 @@ struct perf_session_env {
 	int			nr_pmu_mappings;
 	int			nr_groups;
 	char			*cmdline;
+	const char		**cmdline_argv;
 	char			*sibling_cores;
 	char			*sibling_threads;
 	char			*numa_nodes;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index d0bf1e590479..be3e00891d22 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -550,6 +550,14 @@ int machine__process_itrace_start_event(struct machine *machine __maybe_unused,
 	return 0;
 }
 
+int machine__process_switch_event(struct machine *machine __maybe_unused,
+				  union perf_event *event)
+{
+	if (dump_trace)
+		perf_event__fprintf_switch(event, stdout);
+	return 0;
+}
+
 struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 					const char *filename)
 {
@@ -1451,6 +1459,9 @@ int machine__process_event(struct machine *machine, union perf_event *event,
 		ret = machine__process_itrace_start_event(machine, event); break;
 	case PERF_RECORD_LOST_SAMPLES:
 		ret = machine__process_lost_samples_event(machine, event, sample); break;
+	case PERF_RECORD_SWITCH:
+	case PERF_RECORD_SWITCH_CPU_WIDE:
+		ret = machine__process_switch_event(machine, event); break;
 	default:
 		ret = -1;
 		break;
@@ -1993,3 +2004,17 @@ struct dso *machine__findnew_dso(struct machine *machine, const char *filename)
 {
 	return dsos__findnew(&machine->dsos, filename);
 }
+
+char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, char **modp)
+{
+	struct machine *machine = vmachine;
+	struct map *map;
+	struct symbol *sym = map_groups__find_symbol(&machine->kmaps, MAP__FUNCTION, *addrp, &map,  NULL);
+
+	if (sym == NULL)
+		return NULL;
+
+	*modp = __map__is_kmodule(map) ? (char *)map->dso->short_name : NULL;
+	*addrp = map->unmap_ip(map, sym->start);
+	return sym->name;
+}
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 887798e511e9..ea5cb4a621db 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -87,6 +87,8 @@ int machine__process_aux_event(struct machine *machine,
 			       union perf_event *event);
 int machine__process_itrace_start_event(struct machine *machine,
 					union perf_event *event);
+int machine__process_switch_event(struct machine *machine __maybe_unused,
+				  union perf_event *event);
 int machine__process_mmap_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample);
 int machine__process_mmap2_event(struct machine *machine, union perf_event *event,
@@ -237,5 +239,9 @@ int machine__synthesize_threads(struct machine *machine, struct target *target,
 pid_t machine__get_current_tid(struct machine *machine, int cpu);
 int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
 			     pid_t tid);
+/*
+ * For use with libtraceevent's pevent_set_function_resolver()
+ */
+char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, char **modp);
 
 #endif /* __PERF_MACHINE_H */
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index b5a5e9c02437..ce37e95bc513 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -224,6 +224,20 @@ struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
 	return map;
 }
 
+/*
+ * Use this and __map__is_kmodule() for map instances that are in
+ * machine->kmaps, and thus have map->groups->machine all properly set, to
+ * disambiguate between the kernel and modules.
+ *
+ * When the need arises, introduce map__is_{kernel,kmodule)() that
+ * checks (map->groups != NULL && map->groups->machine != NULL &&
+ * map->dso->kernel) before calling __map__is_{kernel,kmodule}())
+ */
+bool __map__is_kernel(const struct map *map)
+{
+	return map->groups->machine->vmlinux_maps[map->type] == map;
+}
+
 static void map__exit(struct map *map)
 {
 	BUG_ON(!RB_EMPTY_NODE(&map->rb_node));
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index d73e687b224e..57829e89b78b 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -256,4 +256,11 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 struct map *map_groups__find_by_name(struct map_groups *mg,
 				     enum map_type type, const char *name);
 
+bool __map__is_kernel(const struct map *map);
+
+static inline bool __map__is_kmodule(const struct map *map)
+{
+	return !__map__is_kernel(map);
+}
+
 #endif /* __PERF_MAP_H */
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 1f7becbe5e18..0d228a29526d 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -85,6 +85,11 @@ static void perf_probe_comm_exec(struct perf_evsel *evsel)
 	evsel->attr.comm_exec = 1;
 }
 
+static void perf_probe_context_switch(struct perf_evsel *evsel)
+{
+	evsel->attr.context_switch = 1;
+}
+
 bool perf_can_sample_identifier(void)
 {
 	return perf_probe_api(perf_probe_sample_identifier);
@@ -95,6 +100,11 @@ static bool perf_can_comm_exec(void)
 	return perf_probe_api(perf_probe_comm_exec);
 }
 
+bool perf_can_record_switch_events(void)
+{
+	return perf_probe_api(perf_probe_context_switch);
+}
+
 void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
 {
 	struct perf_evsel *evsel;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index ed9dc2555ec7..2d9574710543 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -180,6 +180,7 @@ static void perf_session_env__delete(struct perf_session_env *env)
 	zfree(&env->cpuid);
 
 	zfree(&env->cmdline);
+	zfree(&env->cmdline_argv);
 	zfree(&env->sibling_cores);
 	zfree(&env->sibling_threads);
 	zfree(&env->numa_nodes);
@@ -332,6 +333,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		tool->aux = perf_event__process_aux;
 	if (tool->itrace_start == NULL)
 		tool->itrace_start = perf_event__process_itrace_start;
+	if (tool->context_switch == NULL)
+		tool->context_switch = perf_event__process_switch;
 	if (tool->read == NULL)
 		tool->read = process_event_sample_stub;
 	if (tool->throttle == NULL)
@@ -470,6 +473,19 @@ static void perf_event__itrace_start_swap(union perf_event *event,
 		swap_sample_id_all(event, &event->itrace_start + 1);
 }
 
+static void perf_event__switch_swap(union perf_event *event, bool sample_id_all)
+{
+	if (event->header.type == PERF_RECORD_SWITCH_CPU_WIDE) {
+		event->context_switch.next_prev_pid =
+				bswap_32(event->context_switch.next_prev_pid);
+		event->context_switch.next_prev_tid =
+				bswap_32(event->context_switch.next_prev_tid);
+	}
+
+	if (sample_id_all)
+		swap_sample_id_all(event, &event->context_switch + 1);
+}
+
 static void perf_event__throttle_swap(union perf_event *event,
 				      bool sample_id_all)
 {
@@ -632,6 +648,8 @@ static perf_event__swap_op perf_event__swap_ops[] = {
 	[PERF_RECORD_AUX]		  = perf_event__aux_swap,
 	[PERF_RECORD_ITRACE_START]	  = perf_event__itrace_start_swap,
 	[PERF_RECORD_LOST_SAMPLES]	  = perf_event__all64_swap,
+	[PERF_RECORD_SWITCH]		  = perf_event__switch_swap,
+	[PERF_RECORD_SWITCH_CPU_WIDE]	  = perf_event__switch_swap,
 	[PERF_RECORD_HEADER_ATTR]	  = perf_event__hdr_attr_swap,
 	[PERF_RECORD_HEADER_EVENT_TYPE]	  = perf_event__event_type_swap,
 	[PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,
@@ -1093,6 +1111,9 @@ static int machines__deliver_event(struct machines *machines,
 		return tool->aux(tool, event, sample, machine);
 	case PERF_RECORD_ITRACE_START:
 		return tool->itrace_start(tool, event, sample, machine);
+	case PERF_RECORD_SWITCH:
+	case PERF_RECORD_SWITCH_CPU_WIDE:
+		return tool->context_switch(tool, event, sample, machine);
 	default:
 		++evlist->stats.nr_unknown_events;
 		return -1;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 45c2e3a8316b..725640fd7cd8 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -444,7 +444,12 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
 struct symbol *dso__find_symbol(struct dso *dso,
 				enum map_type type, u64 addr)
 {
-	return symbols__find(&dso->symbols[type], addr);
+	if (dso->last_find_result[type].addr != addr) {
+		dso->last_find_result[type].addr   = addr;
+		dso->last_find_result[type].symbol = symbols__find(&dso->symbols[type], addr);
+	}
+
+	return dso->last_find_result[type].symbol;
 }
 
 struct symbol *dso__first_symbol(struct dso *dso, enum map_type type)
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index c307dd438286..cab8cc24831b 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -46,6 +46,7 @@ struct perf_tool {
 			lost_samples,
 			aux,
 			itrace_start,
+			context_switch,
 			throttle,
 			unthrottle;
 	event_attr_op	attr;
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index eb72716017ac..22245986e59e 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -341,20 +341,14 @@ out:
 
 static int record_proc_kallsyms(void)
 {
-	unsigned int size;
-	const char *path = "/proc/kallsyms";
-	struct stat st;
-	int ret, err = 0;
-
-	ret = stat(path, &st);
-	if (ret < 0) {
-		/* not found */
-		size = 0;
-		if (write(output_fd, &size, 4) != 4)
-			err = -EIO;
-		return err;
-	}
-	return record_file(path, 4);
+	unsigned long long size = 0;
+	/*
+	 * Just to keep older perf.data file parsers happy, record a zero
+	 * sized kallsyms file, i.e. do the same thing that was done when
+	 * /proc/kallsyms (or something specified via --kallsyms, in a
+	 * different path) couldn't be read.
+	 */
+	return write(output_fd, &size, 4) != 4 ? -EIO : 0;
 }
 
 static int record_ftrace_printk(void)
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index d4957418657e..8ff7d620d942 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -135,36 +135,6 @@ void event_format__print(struct event_format *event,
 	return event_format__fprintf(event, cpu, data, size, stdout);
 }
 
-void parse_proc_kallsyms(struct pevent *pevent,
-			 char *file, unsigned int size __maybe_unused)
-{
-	unsigned long long addr;
-	char *func;
-	char *line;
-	char *next = NULL;
-	char *addr_str;
-	char *mod;
-	char *fmt = NULL;
-
-	line = strtok_r(file, "\n", &next);
-	while (line) {
-		mod = NULL;
-		addr_str = strtok_r(line, " ", &fmt);
-		addr = strtoull(addr_str, NULL, 16);
-		/* skip character */
-		strtok_r(NULL, " ", &fmt);
-		func = strtok_r(NULL, "\t", &fmt);
-		mod = strtok_r(NULL, "]", &fmt);
-		/* truncate the extra '[' */
-		if (mod)
-			mod = mod + 1;
-
-		pevent_register_function(pevent, func, addr, mod);
-
-		line = strtok_r(NULL, "\n", &next);
-	}
-}
-
 void parse_ftrace_printk(struct pevent *pevent,
 			 char *file, unsigned int size __maybe_unused)
 {
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index 54d9e9b548a8..b67a0ccf5ab9 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -162,25 +162,23 @@ out:
 static int read_proc_kallsyms(struct pevent *pevent)
 {
 	unsigned int size;
-	char *buf;
 
 	size = read4(pevent);
 	if (!size)
 		return 0;
-
-	buf = malloc(size + 1);
-	if (buf == NULL)
-		return -1;
-
-	if (do_read(buf, size) < 0) {
-		free(buf);
-		return -1;
-	}
-	buf[size] = '\0';
-
-	parse_proc_kallsyms(pevent, buf, size);
-
-	free(buf);
+	/*
+	 * Just skip it, now that we configure libtraceevent to use the
+	 * tools/perf/ symbol resolver.
+	 *
+	 * We need to skip it so that we can continue parsing old perf.data
+	 * files, that contains this /proc/kallsyms payload.
+	 *
+	 * Newer perf.data files will have just the 4-bytes zeros "kallsyms
+	 * payload", so that older tools can continue reading it and interpret
+	 * it as "no kallsyms payload is present".
+	 */
+	lseek(input_fd, size, SEEK_CUR);
+	trace_data_size += size;
 	return 0;
 }
 
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index 6322d37164c5..667bd109d16f 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -9,6 +9,7 @@
 #include <linux/kernel.h>
 #include <traceevent/event-parse.h>
 #include "trace-event.h"
+#include "machine.h"
 #include "util.h"
 
 /*
@@ -19,6 +20,7 @@
  * there.
  */
 static struct trace_event tevent;
+static bool tevent_initialized;
 
 int trace_event__init(struct trace_event *t)
 {
@@ -32,6 +34,32 @@ int trace_event__init(struct trace_event *t)
 	return pevent ? 0 : -1;
 }
 
+static int trace_event__init2(void)
+{
+	int be = traceevent_host_bigendian();
+	struct pevent *pevent;
+
+	if (trace_event__init(&tevent))
+		return -1;
+
+	pevent = tevent.pevent;
+	pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT);
+	pevent_set_file_bigendian(pevent, be);
+	pevent_set_host_bigendian(pevent, be);
+	tevent_initialized = true;
+	return 0;
+}
+
+int trace_event__register_resolver(struct machine *machine)
+{
+	if (!tevent_initialized && trace_event__init2())
+		return -1;
+
+	return pevent_set_function_resolver(tevent.pevent,
+					    machine__resolve_kernel_addr,
+					    machine);
+}
+
 void trace_event__cleanup(struct trace_event *t)
 {
 	traceevent_unload_plugins(t->plugin_list, t->pevent);
@@ -62,21 +90,8 @@ tp_format(const char *sys, const char *name)
 struct event_format*
 trace_event__tp_format(const char *sys, const char *name)
 {
-	static bool initialized;
-
-	if (!initialized) {
-		int be = traceevent_host_bigendian();
-		struct pevent *pevent;
-
-		if (trace_event__init(&tevent))
-			return NULL;
-
-		pevent = tevent.pevent;
-		pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT);
-		pevent_set_file_bigendian(pevent, be);
-		pevent_set_host_bigendian(pevent, be);
-		initialized = true;
-	}
+	if (!tevent_initialized && trace_event__init2())
+		return NULL;
 
 	return tp_format(sys, name);
 }
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index d5168f0be4ec..568128c3284a 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -18,6 +18,7 @@ struct trace_event {
 
 int trace_event__init(struct trace_event *t);
 void trace_event__cleanup(struct trace_event *t);
+int trace_event__register_resolver(struct machine *machine);
 struct event_format*
 trace_event__tp_format(const char *sys, const char *name);