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>

include/uapi/linux/perf_event.h

@@ -330,7 +330,8 @@ struct perf_event_attr {
 				mmap2          :  1, /* include mmap with inode data     */
 				comm_exec      :  1, /* flag comm events that are due to an exec */
 				use_clockid    :  1, /* use @clockid for time fields */
-				__reserved_1   : 38;
+				context_switch :  1, /* context switch data */
+				__reserved_1   : 37;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -572,9 +573,11 @@ struct perf_event_mmap_page {
 /*
  * PERF_RECORD_MISC_MMAP_DATA and PERF_RECORD_MISC_COMM_EXEC are used on
  * different events so can reuse the same bit position.
+ * Ditto PERF_RECORD_MISC_SWITCH_OUT.
  */
 #define PERF_RECORD_MISC_MMAP_DATA		(1 << 13)
 #define PERF_RECORD_MISC_COMM_EXEC		(1 << 13)
+#define PERF_RECORD_MISC_SWITCH_OUT		(1 << 13)
 /*
  * Indicates that the content of PERF_SAMPLE_IP points to
  * the actual instruction that triggered the event. See also
@@ -818,6 +821,32 @@ enum perf_event_type {
 	 */
 	PERF_RECORD_LOST_SAMPLES		= 13,
 
+	/*
+	 * Records a context switch in or out (flagged by
+	 * PERF_RECORD_MISC_SWITCH_OUT). See also
+	 * PERF_RECORD_SWITCH_CPU_WIDE.
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_SWITCH			= 14,
+
+	/*
+	 * CPU-wide version of PERF_RECORD_SWITCH with next_prev_pid and
+	 * next_prev_tid that are the next (switching out) or previous
+	 * (switching in) pid/tid.
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				next_prev_pid;
+	 *	u32				next_prev_tid;
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_SWITCH_CPU_WIDE		= 15,
+
 	PERF_RECORD_MAX,			/* non-ABI */
 };
 

kernel/events/core.c

@@ -163,6 +163,7 @@ static atomic_t nr_mmap_events __read_mostly;
 static atomic_t nr_comm_events __read_mostly;
 static atomic_t nr_task_events __read_mostly;
 static atomic_t nr_freq_events __read_mostly;
+static atomic_t nr_switch_events __read_mostly;
 
 static LIST_HEAD(pmus);
 static DEFINE_MUTEX(pmus_lock);
@@ -2619,6 +2620,9 @@ static void perf_pmu_sched_task(struct task_struct *prev,
 	local_irq_restore(flags);
 }
 
+static void perf_event_switch(struct task_struct *task,
+			      struct task_struct *next_prev, bool sched_in);
+
 #define for_each_task_context_nr(ctxn)					\
 	for ((ctxn) = 0; (ctxn) < perf_nr_task_contexts; (ctxn)++)
 
@@ -2641,6 +2645,9 @@ void __perf_event_task_sched_out(struct task_struct *task,
 	if (__this_cpu_read(perf_sched_cb_usages))
 		perf_pmu_sched_task(task, next, false);
 
+	if (atomic_read(&nr_switch_events))
+		perf_event_switch(task, next, false);
+
 	for_each_task_context_nr(ctxn)
 		perf_event_context_sched_out(task, ctxn, next);
 
@@ -2831,6 +2838,9 @@ void __perf_event_task_sched_in(struct task_struct *prev,
 	if (atomic_read(this_cpu_ptr(&perf_cgroup_events)))
 		perf_cgroup_sched_in(prev, task);
 
+	if (atomic_read(&nr_switch_events))
+		perf_event_switch(task, prev, true);
+
 	if (__this_cpu_read(perf_sched_cb_usages))
 		perf_pmu_sched_task(prev, task, true);
 }
@@ -3454,6 +3464,10 @@ static void unaccount_event(struct perf_event *event)
 		atomic_dec(&nr_task_events);
 	if (event->attr.freq)
 		atomic_dec(&nr_freq_events);
+	if (event->attr.context_switch) {
+		static_key_slow_dec_deferred(&perf_sched_events);
+		atomic_dec(&nr_switch_events);
+	}
 	if (is_cgroup_event(event))
 		static_key_slow_dec_deferred(&perf_sched_events);
 	if (has_branch_stack(event))
@@ -5981,6 +5995,91 @@ void perf_log_lost_samples(struct perf_event *event, u64 lost)
 	perf_output_end(&handle);
 }
 
+/*
+ * context_switch tracking
+ */
+
+struct perf_switch_event {
+	struct task_struct	*task;
+	struct task_struct	*next_prev;
+
+	struct {
+		struct perf_event_header	header;
+		u32				next_prev_pid;
+		u32				next_prev_tid;
+	} event_id;
+};
+
+static int perf_event_switch_match(struct perf_event *event)
+{
+	return event->attr.context_switch;
+}
+
+static void perf_event_switch_output(struct perf_event *event, void *data)
+{
+	struct perf_switch_event *se = data;
+	struct perf_output_handle handle;
+	struct perf_sample_data sample;
+	int ret;
+
+	if (!perf_event_switch_match(event))
+		return;
+
+	/* Only CPU-wide events are allowed to see next/prev pid/tid */
+	if (event->ctx->task) {
+		se->event_id.header.type = PERF_RECORD_SWITCH;
+		se->event_id.header.size = sizeof(se->event_id.header);
+	} else {
+		se->event_id.header.type = PERF_RECORD_SWITCH_CPU_WIDE;
+		se->event_id.header.size = sizeof(se->event_id);
+		se->event_id.next_prev_pid =
+					perf_event_pid(event, se->next_prev);
+		se->event_id.next_prev_tid =
+					perf_event_tid(event, se->next_prev);
+	}
+
+	perf_event_header__init_id(&se->event_id.header, &sample, event);
+
+	ret = perf_output_begin(&handle, event, se->event_id.header.size);
+	if (ret)
+		return;
+
+	if (event->ctx->task)
+		perf_output_put(&handle, se->event_id.header);
+	else
+		perf_output_put(&handle, se->event_id);
+
+	perf_event__output_id_sample(event, &handle, &sample);
+
+	perf_output_end(&handle);
+}
+
+static void perf_event_switch(struct task_struct *task,
+			      struct task_struct *next_prev, bool sched_in)
+{
+	struct perf_switch_event switch_event;
+
+	/* N.B. caller checks nr_switch_events != 0 */
+
+	switch_event = (struct perf_switch_event){
+		.task		= task,
+		.next_prev	= next_prev,
+		.event_id	= {
+			.header = {
+				/* .type */
+				.misc = sched_in ? 0 : PERF_RECORD_MISC_SWITCH_OUT,
+				/* .size */
+			},
+			/* .next_prev_pid */
+			/* .next_prev_tid */
+		},
+	};
+
+	perf_event_aux(perf_event_switch_output,
+		       &switch_event,
+		       NULL);
+}
+
 /*
  * IRQ throttle logging
  */
@@ -7479,6 +7578,10 @@ static void account_event(struct perf_event *event)
 		if (atomic_inc_return(&nr_freq_events) == 1)
 			tick_nohz_full_kick_all();
 	}
+	if (event->attr.context_switch) {
+		atomic_inc(&nr_switch_events);
+		static_key_slow_inc(&perf_sched_events.key);
+	}
 	if (has_branch_stack(event))
 		static_key_slow_inc(&perf_sched_events.key);
 	if (is_cgroup_event(event))

tools/lib/traceevent/event-parse.c

@@ -418,7 +418,7 @@ static int func_map_init(struct pevent *pevent)
 }
 
 static struct func_map *
-find_func(struct pevent *pevent, unsigned long long addr)
+__find_func(struct pevent *pevent, unsigned long long addr)
 {
 	struct func_map *func;
 	struct func_map key;
@@ -434,6 +434,71 @@ find_func(struct pevent *pevent, unsigned long long addr)
 	return func;
 }
 
+struct func_resolver {
+	pevent_func_resolver_t *func;
+	void		       *priv;
+	struct func_map	       map;
+};
+
+/**
+ * pevent_set_function_resolver - set an alternative function resolver
+ * @pevent: handle for the pevent
+ * @resolver: function to be used
+ * @priv: resolver function private state.
+ *
+ * Some tools may have already a way to resolve kernel functions, allow them to
+ * keep using it instead of duplicating all the entries inside
+ * pevent->funclist.
+ */
+int pevent_set_function_resolver(struct pevent *pevent,
+				 pevent_func_resolver_t *func, void *priv)
+{
+	struct func_resolver *resolver = malloc(sizeof(*resolver));
+
+	if (resolver == NULL)
+		return -1;
+
+	resolver->func = func;
+	resolver->priv = priv;
+
+	free(pevent->func_resolver);
+	pevent->func_resolver = resolver;
+
+	return 0;
+}
+
+/**
+ * pevent_reset_function_resolver - reset alternative function resolver
+ * @pevent: handle for the pevent
+ *
+ * Stop using whatever alternative resolver was set, use the default
+ * one instead.
+ */
+void pevent_reset_function_resolver(struct pevent *pevent)
+{
+	free(pevent->func_resolver);
+	pevent->func_resolver = NULL;
+}
+
+static struct func_map *
+find_func(struct pevent *pevent, unsigned long long addr)
+{
+	struct func_map *map;
+
+	if (!pevent->func_resolver)
+		return __find_func(pevent, addr);
+
+	map = &pevent->func_resolver->map;
+	map->mod  = NULL;
+	map->addr = addr;
+	map->func = pevent->func_resolver->func(pevent->func_resolver->priv,
+						&map->addr, &map->mod);
+	if (map->func == NULL)
+		return NULL;
+
+	return map;
+}
+
 /**
  * pevent_find_function - find a function by a given address
  * @pevent: handle for the pevent
@@ -6564,6 +6629,7 @@ void pevent_free(struct pevent *pevent)
 	free(pevent->trace_clock);
 	free(pevent->events);
 	free(pevent->sort_events);
+	free(pevent->func_resolver);
 
 	free(pevent);
 }

tools/lib/traceevent/event-parse.h

@@ -453,6 +453,10 @@ struct cmdline_list;
 struct func_map;
 struct func_list;
 struct event_handler;
+struct func_resolver;
+
+typedef char *(pevent_func_resolver_t)(void *priv,
+				       unsigned long long *addrp, char **modp);
 
 struct pevent {
 	int ref_count;
@@ -481,6 +485,7 @@ struct pevent {
 	int cmdline_count;
 
 	struct func_map *func_map;
+	struct func_resolver *func_resolver;
 	struct func_list *funclist;
 	unsigned int func_count;
 
@@ -611,6 +616,9 @@ enum trace_flag_type {
 	TRACE_FLAG_SOFTIRQ		= 0x10,
 };
 
+int pevent_set_function_resolver(struct pevent *pevent,
+				 pevent_func_resolver_t *func, void *priv);
+void pevent_reset_function_resolver(struct pevent *pevent);
 int pevent_register_comm(struct pevent *pevent, const char *comm, int pid);
 int pevent_register_trace_clock(struct pevent *pevent, const char *trace_clock);
 int pevent_register_function(struct pevent *pevent, char *name,

tools/perf/Documentation/perf-record.txt

@@ -293,6 +293,10 @@ When processing pre-existing threads /proc/XXX/mmap, it may take a long time,
 because the file may be huge. A time out is needed in such cases.
 This option sets the time out limit. The default value is 500 ms.
 
+--switch-events::
+Record context switch events i.e. events of type PERF_RECORD_SWITCH or
+PERF_RECORD_SWITCH_CPU_WIDE.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]

tools/perf/Documentation/perf-script.txt

@@ -222,6 +222,10 @@ OPTIONS
 --show-mmap-events
 	Display mmap related events (e.g. MMAP, MMAP2).
 
+--show-switch-events
+	Display context switch events i.e. events of type PERF_RECORD_SWITCH or
+	PERF_RECORD_SWITCH_CPU_WIDE.
+
 --header
 	Show perf.data header.
 

tools/perf/builtin-inject.c

@@ -561,6 +561,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 			.lost		= perf_event__repipe,
 			.aux		= perf_event__repipe,
 			.itrace_start	= perf_event__repipe,
+			.context_switch	= perf_event__repipe,
 			.read		= perf_event__repipe_sample,
 			.throttle	= perf_event__repipe,
 			.unthrottle	= perf_event__repipe,

tools/perf/builtin-record.c

@@ -1075,6 +1075,8 @@ struct option __record_options[] = {
 			  "opts", "AUX area tracing Snapshot Mode", ""),
 	OPT_UINTEGER(0, "proc-map-timeout", &record.opts.proc_map_timeout,
 			"per thread proc mmap processing timeout in ms"),
+	OPT_BOOLEAN(0, "switch-events", &record.opts.record_switch_events,
+		    "Record context switch events"),
 	OPT_END()
 };
 
@@ -1102,6 +1104,11 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 			  " system-wide mode\n");
 		usage_with_options(record_usage, record_options);
 	}
+	if (rec->opts.record_switch_events &&
+	    !perf_can_record_switch_events()) {
+		ui__error("kernel does not support recording context switch events (--switch-events option)\n");
+		usage_with_options(record_usage, record_options);
+	}
 
 	if (!rec->itr) {
 		rec->itr = auxtrace_record__init(rec->evlist, &err);

tools/perf/builtin-script.c

@@ -623,6 +623,7 @@ struct perf_script {
 	struct perf_session	*session;
 	bool			show_task_events;
 	bool			show_mmap_events;
+	bool			show_switch_events;
 };
 
 static int process_attr(struct perf_tool *tool, union perf_event *event,
@@ -661,7 +662,7 @@ static int process_comm_event(struct perf_tool *tool,
 	struct thread *thread;
 	struct perf_script *script = container_of(tool, struct perf_script, tool);
 	struct perf_session *session = script->session;
-	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+	struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
 	int ret = -1;
 
 	thread = machine__findnew_thread(machine, event->comm.pid, event->comm.tid);
@@ -695,7 +696,7 @@ static int process_fork_event(struct perf_tool *tool,
 	struct thread *thread;
 	struct perf_script *script = container_of(tool, struct perf_script, tool);
 	struct perf_session *session = script->session;
-	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+	struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
 
 	if (perf_event__process_fork(tool, event, sample, machine) < 0)
 		return -1;
@@ -727,7 +728,7 @@ static int process_exit_event(struct perf_tool *tool,
 	struct thread *thread;
 	struct perf_script *script = container_of(tool, struct perf_script, tool);
 	struct perf_session *session = script->session;
-	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+	struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
 
 	thread = machine__findnew_thread(machine, event->fork.pid, event->fork.tid);
 	if (thread == NULL) {
@@ -759,7 +760,7 @@ static int process_mmap_event(struct perf_tool *tool,
 	struct thread *thread;
 	struct perf_script *script = container_of(tool, struct perf_script, tool);
 	struct perf_session *session = script->session;
-	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+	struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
 
 	if (perf_event__process_mmap(tool, event, sample, machine) < 0)
 		return -1;
@@ -790,7 +791,7 @@ static int process_mmap2_event(struct perf_tool *tool,
 	struct thread *thread;
 	struct perf_script *script = container_of(tool, struct perf_script, tool);
 	struct perf_session *session = script->session;
-	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+	struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
 
 	if (perf_event__process_mmap2(tool, event, sample, machine) < 0)
 		return -1;
@@ -813,6 +814,32 @@ static int process_mmap2_event(struct perf_tool *tool,
 	return 0;
 }
 
+static int process_switch_event(struct perf_tool *tool,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct machine *machine)
+{
+	struct thread *thread;
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+	struct perf_session *session = script->session;
+	struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
+
+	if (perf_event__process_switch(tool, event, sample, machine) < 0)
+		return -1;
+
+	thread = machine__findnew_thread(machine, sample->pid,
+					 sample->tid);
+	if (thread == NULL) {
+		pr_debug("problem processing SWITCH event, skipping it.\n");
+		return -1;
+	}
+
+	print_sample_start(sample, thread, evsel);
+	perf_event__fprintf(event, stdout);
+	thread__put(thread);
+	return 0;
+}
+
 static void sig_handler(int sig __maybe_unused)
 {
 	session_done = 1;
@@ -834,6 +861,8 @@ static int __cmd_script(struct perf_script *script)
 		script->tool.mmap = process_mmap_event;
 		script->tool.mmap2 = process_mmap2_event;
 	}
+	if (script->show_switch_events)
+		script->tool.context_switch = process_switch_event;
 
 	ret = perf_session__process_events(script->session);
 
@@ -1618,6 +1647,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Show the fork/comm/exit events"),
 	OPT_BOOLEAN('\0', "show-mmap-events", &script.show_mmap_events,
 		    "Show the mmap events"),
+	OPT_BOOLEAN('\0', "show-switch-events", &script.show_switch_events,
+		    "Show context switch events (if recorded)"),
 	OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
 	OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
 			    "Instruction Tracing options",
@@ -1830,6 +1861,13 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 	else
 		symbol_conf.use_callchain = false;
 
+	if (pevent_set_function_resolver(session->tevent.pevent,
+					 machine__resolve_kernel_addr,
+					 &session->machines.host) < 0) {
+		pr_err("%s: failed to set libtraceevent function resolver\n", __func__);
+		return -1;
+	}
+
 	if (generate_script_lang) {
 		struct stat perf_stat;
 		int input;

tools/perf/builtin-trace.c

@@ -1489,6 +1489,9 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
 	if (trace->host == NULL)
 		return -ENOMEM;
 
+	if (trace_event__register_resolver(trace->host) < 0)
+		return -errno;
+
 	err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,
 					    evlist->threads, trace__tool_process, false,
 					    trace->opts.proc_map_timeout);

tools/perf/perf.h

@@ -57,6 +57,7 @@ struct record_opts {
 	bool	     running_time;
 	bool	     full_auxtrace;
 	bool	     auxtrace_snapshot_mode;
+	bool	     record_switch_events;
 	unsigned int freq;
 	unsigned int mmap_pages;
 	unsigned int auxtrace_mmap_pages;

tools/perf/tests/thread-map.c

@@ -20,6 +20,8 @@ int test__thread_map(void)
 	TEST_ASSERT_VAL("wrong comm",
 			thread_map__comm(map, 0) &&
 			!strcmp(thread_map__comm(map, 0), "perf"));
+	TEST_ASSERT_VAL("wrong refcnt",
+			atomic_read(&map->refcnt) == 1);
 	thread_map__put(map);
 
 	/* test dummy pid */
@@ -33,6 +35,8 @@ int test__thread_map(void)
 	TEST_ASSERT_VAL("wrong comm",
 			thread_map__comm(map, 0) &&
 			!strcmp(thread_map__comm(map, 0), "dummy"));
+	TEST_ASSERT_VAL("wrong refcnt",
+			atomic_read(&map->refcnt) == 1);
 	thread_map__put(map);
 	return 0;
 }

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;

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");
 	}

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,

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;

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);
 

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);

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;
 }
 

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;