diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 0ad1bc75ab49..52462ae26455 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -108,6 +108,11 @@ OPTIONS
 --data::
 	Sample addresses.
 
+-T::
+--timestamp::
+	Sample timestamps. Use it with 'perf report -D' to see the timestamps,
+	for instance.
+
 -n::
 --no-samples::
 	Don't sample.
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index b34de9291c27..699dd2149c4b 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -49,6 +49,7 @@ static const char		*output_name			= "perf.data";
 static int			group				=      0;
 static int			realtime_prio			=      0;
 static bool			raw_samples			=  false;
+static bool			sample_id_all_avail		=   true;
 static bool			system_wide			=  false;
 static pid_t			target_pid			=     -1;
 static pid_t			target_tid			=     -1;
@@ -61,6 +62,7 @@ static bool			call_graph			=  false;
 static bool			inherit_stat			=  false;
 static bool			no_samples			=  false;
 static bool			sample_address			=  false;
+static bool			sample_time			=  false;
 static bool			no_buildid			=  false;
 static bool			no_buildid_cache		=  false;
 
@@ -283,6 +285,9 @@ static void create_counter(int counter, int cpu)
 	if (system_wide)
 		attr->sample_type	|= PERF_SAMPLE_CPU;
 
+	if (sample_time)
+		attr->sample_type	|= PERF_SAMPLE_TIME;
+
 	if (raw_samples) {
 		attr->sample_type	|= PERF_SAMPLE_TIME;
 		attr->sample_type	|= PERF_SAMPLE_RAW;
@@ -299,6 +304,8 @@ static void create_counter(int counter, int cpu)
 		attr->disabled = 1;
 		attr->enable_on_exec = 1;
 	}
+retry_sample_id:
+	attr->sample_id_all = sample_id_all_avail ? 1 : 0;
 
 	for (thread_index = 0; thread_index < thread_num; thread_index++) {
 try_again:
@@ -315,6 +322,12 @@ static void create_counter(int counter, int cpu)
 			else if (err ==  ENODEV && cpu_list) {
 				die("No such device - did you specify"
 					" an out-of-range profile CPU?\n");
+			} else if (err == EINVAL && sample_id_all_avail) {
+				/*
+				 * Old kernel, no attr->sample_id_type_all field
+				 */
+				sample_id_all_avail = false;
+				goto retry_sample_id;
 			}
 
 			/*
@@ -661,6 +674,8 @@ static int __cmd_record(int argc, const char **argv)
 
 	post_processing_offset = lseek(output, 0, SEEK_CUR);
 
+	perf_session__set_sample_id_all(session, sample_id_all_avail);
+
 	if (pipe_output) {
 		err = event__synthesize_attrs(&session->header,
 					      process_synthesized_event,
@@ -841,6 +856,7 @@ const struct option record_options[] = {
 		    "per thread counts"),
 	OPT_BOOLEAN('d', "data", &sample_address,
 		    "Sample addresses"),
+	OPT_BOOLEAN('T', "timestamp", &sample_time, "Sample timestamps"),
 	OPT_BOOLEAN('n', "no-samples", &no_samples,
 		    "don't sample"),
 	OPT_BOOLEAN('N', "no-buildid-cache", &no_buildid_cache,
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 5aa29e1e855a..0515ce9d3d3e 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -977,12 +977,12 @@ static int symbol_filter(struct map *map, struct symbol *sym)
 }
 
 static void event__process_sample(const event_t *self,
-				 struct perf_session *session, int counter)
+				  struct sample_data *sample,
+				  struct perf_session *session, int counter)
 {
 	u64 ip = self->ip.ip;
 	struct sym_entry *syme;
 	struct addr_location al;
-	struct sample_data data;
 	struct machine *machine;
 	u8 origin = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
@@ -1025,9 +1025,7 @@ static void event__process_sample(const event_t *self,
 	if (self->header.misc & PERF_RECORD_MISC_EXACT_IP)
 		exact_samples++;
 
-	event__parse_sample(self, session->sample_type, &data);
-
-	if (event__preprocess_sample(self, session, &al, &data,
+	if (event__preprocess_sample(self, session, &al, sample,
 				     symbol_filter) < 0 ||
 	    al.filtered)
 		return;
@@ -1107,6 +1105,7 @@ static void perf_session__mmap_read_counter(struct perf_session *self,
 	unsigned int head = mmap_read_head(md);
 	unsigned int old = md->prev;
 	unsigned char *data = md->base + page_size;
+	struct sample_data sample;
 	int diff;
 
 	/*
@@ -1154,10 +1153,11 @@ static void perf_session__mmap_read_counter(struct perf_session *self,
 			event = &event_copy;
 		}
 
+		event__parse_sample(event, self, &sample);
 		if (event->header.type == PERF_RECORD_SAMPLE)
-			event__process_sample(event, self, md->counter);
+			event__process_sample(event, &sample, self, md->counter);
 		else
-			event__process(event, NULL, self);
+			event__process(event, &sample, self);
 		old += size;
 	}
 
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 34510f441975..e4cdc1ebe0fb 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -33,11 +33,10 @@ static struct sample_data synth_sample = {
 	.period	   = 1,
 };
 
-static pid_t event__synthesize_comm(pid_t pid, int full,
+static pid_t event__synthesize_comm(event_t *event, pid_t pid, int full,
 				    event__handler_t process,
 				    struct perf_session *session)
 {
-	event_t ev;
 	char filename[PATH_MAX];
 	char bf[BUFSIZ];
 	FILE *fp;
@@ -58,34 +57,39 @@ static pid_t event__synthesize_comm(pid_t pid, int full,
 		return 0;
 	}
 
-	memset(&ev.comm, 0, sizeof(ev.comm));
-	while (!ev.comm.comm[0] || !ev.comm.pid) {
-		if (fgets(bf, sizeof(bf), fp) == NULL)
-			goto out_failure;
+	memset(&event->comm, 0, sizeof(event->comm));
+
+	while (!event->comm.comm[0] || !event->comm.pid) {
+		if (fgets(bf, sizeof(bf), fp) == NULL) {
+			pr_warning("couldn't get COMM and pgid, malformed %s\n", filename);
+			goto out;
+		}
 
 		if (memcmp(bf, "Name:", 5) == 0) {
 			char *name = bf + 5;
 			while (*name && isspace(*name))
 				++name;
 			size = strlen(name) - 1;
-			memcpy(ev.comm.comm, name, size++);
+			memcpy(event->comm.comm, name, size++);
 		} else if (memcmp(bf, "Tgid:", 5) == 0) {
 			char *tgids = bf + 5;
 			while (*tgids && isspace(*tgids))
 				++tgids;
-			tgid = ev.comm.pid = atoi(tgids);
+			tgid = event->comm.pid = atoi(tgids);
 		}
 	}
 
-	ev.comm.header.type = PERF_RECORD_COMM;
+	event->comm.header.type = PERF_RECORD_COMM;
 	size = ALIGN(size, sizeof(u64));
-	ev.comm.header.size = sizeof(ev.comm) - (sizeof(ev.comm.comm) - size);
-
+	memset(event->comm.comm + size, 0, session->id_hdr_size);
+	event->comm.header.size = (sizeof(event->comm) -
+				(sizeof(event->comm.comm) - size) +
+				session->id_hdr_size);
 	if (!full) {
-		ev.comm.tid = pid;
+		event->comm.tid = pid;
 
-		process(&ev, &synth_sample, session);
-		goto out_fclose;
+		process(event, &synth_sample, session);
+		goto out;
 	}
 
 	snprintf(filename, sizeof(filename), "/proc/%d/task", pid);
@@ -100,22 +104,19 @@ static pid_t event__synthesize_comm(pid_t pid, int full,
 		if (*end)
 			continue;
 
-		ev.comm.tid = pid;
+		event->comm.tid = pid;
 
-		process(&ev, &synth_sample, session);
+		process(event, &synth_sample, session);
 	}
+
 	closedir(tasks);
-
-out_fclose:
+out:
 	fclose(fp);
-	return tgid;
 
-out_failure:
-	pr_warning("couldn't get COMM and pgid, malformed %s\n", filename);
-	return -1;
+	return tgid;
 }
 
-static int event__synthesize_mmap_events(pid_t pid, pid_t tgid,
+static int event__synthesize_mmap_events(event_t *event, pid_t pid, pid_t tgid,
 					 event__handler_t process,
 					 struct perf_session *session)
 {
@@ -133,29 +134,25 @@ static int event__synthesize_mmap_events(pid_t pid, pid_t tgid,
 		return -1;
 	}
 
+	event->header.type = PERF_RECORD_MMAP;
+	/*
+	 * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
+	 */
+	event->header.misc = PERF_RECORD_MISC_USER;
+
 	while (1) {
 		char bf[BUFSIZ], *pbf = bf;
-		event_t ev = {
-			.header = {
-				.type = PERF_RECORD_MMAP,
-				/*
-				 * Just like the kernel, see __perf_event_mmap
-				 * in kernel/perf_event.c
-				 */
-				.misc = PERF_RECORD_MISC_USER,
-			 },
-		};
 		int n;
 		size_t size;
 		if (fgets(bf, sizeof(bf), fp) == NULL)
 			break;
 
 		/* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
-		n = hex2u64(pbf, &ev.mmap.start);
+		n = hex2u64(pbf, &event->mmap.start);
 		if (n < 0)
 			continue;
 		pbf += n + 1;
-		n = hex2u64(pbf, &ev.mmap.len);
+		n = hex2u64(pbf, &event->mmap.len);
 		if (n < 0)
 			continue;
 		pbf += n + 3;
@@ -170,19 +167,21 @@ static int event__synthesize_mmap_events(pid_t pid, pid_t tgid,
 				continue;
 
 			pbf += 3;
-			n = hex2u64(pbf, &ev.mmap.pgoff);
+			n = hex2u64(pbf, &event->mmap.pgoff);
 
 			size = strlen(execname);
 			execname[size - 1] = '\0'; /* Remove \n */
-			memcpy(ev.mmap.filename, execname, size);
+			memcpy(event->mmap.filename, execname, size);
 			size = ALIGN(size, sizeof(u64));
-			ev.mmap.len -= ev.mmap.start;
-			ev.mmap.header.size = (sizeof(ev.mmap) -
-					       (sizeof(ev.mmap.filename) - size));
-			ev.mmap.pid = tgid;
-			ev.mmap.tid = pid;
+			event->mmap.len -= event->mmap.start;
+			event->mmap.header.size = (sizeof(event->mmap) -
+					        (sizeof(event->mmap.filename) - size));
+			memset(event->mmap.filename + size, 0, session->id_hdr_size);
+			event->mmap.header.size += session->id_hdr_size;
+			event->mmap.pid = tgid;
+			event->mmap.tid = pid;
 
-			process(&ev, &synth_sample, session);
+			process(event, &synth_sample, session);
 		}
 	}
 
@@ -196,20 +195,27 @@ int event__synthesize_modules(event__handler_t process,
 {
 	struct rb_node *nd;
 	struct map_groups *kmaps = &machine->kmaps;
-	u16 misc;
+	event_t *event = zalloc(sizeof(event->mmap) + session->id_hdr_size);
+
+	if (event == NULL) {
+		pr_debug("Not enough memory synthesizing mmap event "
+			 "for kernel modules\n");
+		return -1;
+	}
+
+	event->header.type = PERF_RECORD_MMAP;
 
 	/*
 	 * kernel uses 0 for user space maps, see kernel/perf_event.c
 	 * __perf_event_mmap
 	 */
 	if (machine__is_host(machine))
-		misc = PERF_RECORD_MISC_KERNEL;
+		event->header.misc = PERF_RECORD_MISC_KERNEL;
 	else
-		misc = PERF_RECORD_MISC_GUEST_KERNEL;
+		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
 
 	for (nd = rb_first(&kmaps->maps[MAP__FUNCTION]);
 	     nd; nd = rb_next(nd)) {
-		event_t ev;
 		size_t size;
 		struct map *pos = rb_entry(nd, struct map, rb_node);
 
@@ -217,39 +223,78 @@ int event__synthesize_modules(event__handler_t process,
 			continue;
 
 		size = ALIGN(pos->dso->long_name_len + 1, sizeof(u64));
-		memset(&ev, 0, sizeof(ev));
-		ev.mmap.header.misc = misc;
-		ev.mmap.header.type = PERF_RECORD_MMAP;
-		ev.mmap.header.size = (sizeof(ev.mmap) -
-				        (sizeof(ev.mmap.filename) - size));
-		ev.mmap.start = pos->start;
-		ev.mmap.len   = pos->end - pos->start;
-		ev.mmap.pid   = machine->pid;
+		event->mmap.header.type = PERF_RECORD_MMAP;
+		event->mmap.header.size = (sizeof(event->mmap) -
+				        (sizeof(event->mmap.filename) - size));
+		memset(event->mmap.filename + size, 0, session->id_hdr_size);
+		event->mmap.header.size += session->id_hdr_size;
+		event->mmap.start = pos->start;
+		event->mmap.len   = pos->end - pos->start;
+		event->mmap.pid   = machine->pid;
 
-		memcpy(ev.mmap.filename, pos->dso->long_name,
+		memcpy(event->mmap.filename, pos->dso->long_name,
 		       pos->dso->long_name_len + 1);
-		process(&ev, &synth_sample, session);
+		process(event, &synth_sample, session);
 	}
 
+	free(event);
 	return 0;
 }
 
+static int __event__synthesize_thread(event_t *comm_event, event_t *mmap_event,
+				      pid_t pid, event__handler_t process,
+				      struct perf_session *session)
+{
+	pid_t tgid = event__synthesize_comm(comm_event, pid, 1, process,
+					    session);
+	if (tgid == -1)
+		return -1;
+	return event__synthesize_mmap_events(mmap_event, pid, tgid,
+					     process, session);
+}
+
 int event__synthesize_thread(pid_t pid, event__handler_t process,
 			     struct perf_session *session)
 {
-	pid_t tgid = event__synthesize_comm(pid, 1, process, session);
-	if (tgid == -1)
-		return -1;
-	return event__synthesize_mmap_events(pid, tgid, process, session);
+	event_t *comm_event, *mmap_event;
+	int err = -1;
+
+	comm_event = malloc(sizeof(comm_event->comm) + session->id_hdr_size);
+	if (comm_event == NULL)
+		goto out;
+
+	mmap_event = malloc(sizeof(mmap_event->mmap) + session->id_hdr_size);
+	if (mmap_event == NULL)
+		goto out_free_comm;
+
+	err = __event__synthesize_thread(comm_event, mmap_event, pid,
+					 process, session);
+	free(mmap_event);
+out_free_comm:
+	free(comm_event);
+out:
+	return err;
 }
 
-void event__synthesize_threads(event__handler_t process,
-			       struct perf_session *session)
+int event__synthesize_threads(event__handler_t process,
+			      struct perf_session *session)
 {
 	DIR *proc;
 	struct dirent dirent, *next;
+	event_t *comm_event, *mmap_event;
+	int err = -1;
+
+	comm_event = malloc(sizeof(comm_event->comm) + session->id_hdr_size);
+	if (comm_event == NULL)
+		goto out;
+
+	mmap_event = malloc(sizeof(mmap_event->mmap) + session->id_hdr_size);
+	if (mmap_event == NULL)
+		goto out_free_comm;
 
 	proc = opendir("/proc");
+	if (proc == NULL)
+		goto out_free_mmap;
 
 	while (!readdir_r(proc, &dirent, &next) && next) {
 		char *end;
@@ -258,10 +303,18 @@ void event__synthesize_threads(event__handler_t process,
 		if (*end) /* only interested in proper numerical dirents */
 			continue;
 
-		event__synthesize_thread(pid, process, session);
+		__event__synthesize_thread(comm_event, mmap_event, pid,
+					   process, session);
 	}
 
 	closedir(proc);
+	err = 0;
+out_free_mmap:
+	free(mmap_event);
+out_free_comm:
+	free(comm_event);
+out:
+	return err;
 }
 
 struct process_symbol_args {
@@ -295,18 +348,20 @@ int event__synthesize_kernel_mmap(event__handler_t process,
 	char path[PATH_MAX];
 	char name_buff[PATH_MAX];
 	struct map *map;
-
-	event_t ev = {
-		.header = {
-			.type = PERF_RECORD_MMAP,
-		},
-	};
+	int err;
 	/*
 	 * We should get this from /sys/kernel/sections/.text, but till that is
 	 * available use this, and after it is use this as a fallback for older
 	 * kernels.
 	 */
 	struct process_symbol_args args = { .name = symbol_name, };
+	event_t *event = zalloc(sizeof(event->mmap) + session->id_hdr_size);
+
+	if (event == NULL) {
+		pr_debug("Not enough memory synthesizing mmap event "
+			 "for kernel modules\n");
+		return -1;
+	}
 
 	mmap_name = machine__mmap_name(machine, name_buff, sizeof(name_buff));
 	if (machine__is_host(machine)) {
@@ -314,10 +369,10 @@ int event__synthesize_kernel_mmap(event__handler_t process,
 		 * kernel uses PERF_RECORD_MISC_USER for user space maps,
 		 * see kernel/perf_event.c __perf_event_mmap
 		 */
-		ev.header.misc = PERF_RECORD_MISC_KERNEL;
+		event->header.misc = PERF_RECORD_MISC_KERNEL;
 		filename = "/proc/kallsyms";
 	} else {
-		ev.header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
+		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
 		if (machine__is_default_guest(machine))
 			filename = (char *) symbol_conf.default_guest_kallsyms;
 		else {
@@ -330,17 +385,21 @@ int event__synthesize_kernel_mmap(event__handler_t process,
 		return -ENOENT;
 
 	map = machine->vmlinux_maps[MAP__FUNCTION];
-	size = snprintf(ev.mmap.filename, sizeof(ev.mmap.filename),
+	size = snprintf(event->mmap.filename, sizeof(event->mmap.filename),
 			"%s%s", mmap_name, symbol_name) + 1;
 	size = ALIGN(size, sizeof(u64));
-	ev.mmap.header.size = (sizeof(ev.mmap) -
-			(sizeof(ev.mmap.filename) - size));
-	ev.mmap.pgoff = args.start;
-	ev.mmap.start = map->start;
-	ev.mmap.len   = map->end - ev.mmap.start;
-	ev.mmap.pid   = machine->pid;
+	event->mmap.header.type = PERF_RECORD_MMAP;
+	event->mmap.header.size = (sizeof(event->mmap) -
+			(sizeof(event->mmap.filename) - size) + session->id_hdr_size);
+	event->mmap.pgoff = args.start;
+	event->mmap.start = map->start;
+	event->mmap.len   = map->end - event->mmap.start;
+	event->mmap.pid   = machine->pid;
 
-	return process(&ev, &synth_sample, session);
+	err = process(event, &synth_sample, session);
+	free(event);
+
+	return err;
 }
 
 static void thread__comm_adjust(struct thread *self, struct hists *hists)
@@ -756,9 +815,65 @@ int event__preprocess_sample(const event_t *self, struct perf_session *session,
 	return 0;
 }
 
-int event__parse_sample(const event_t *event, u64 type, struct sample_data *data)
+static int event__parse_id_sample(const event_t *event,
+				  struct perf_session *session,
+				  struct sample_data *sample)
 {
-	const u64 *array = event->sample.array;
+	const u64 *array;
+	u64 type;
+
+	sample->cpu = sample->pid = sample->tid = -1;
+	sample->stream_id = sample->id = sample->time = -1ULL;
+
+	if (!session->sample_id_all)
+		return 0;
+
+	array = event->sample.array;
+	array += ((event->header.size -
+		   sizeof(event->header)) / sizeof(u64)) - 1;
+	type = session->sample_type;
+
+	if (type & PERF_SAMPLE_CPU) {
+		u32 *p = (u32 *)array;
+		sample->cpu = *p;
+		array--;
+	}
+
+	if (type & PERF_SAMPLE_STREAM_ID) {
+		sample->stream_id = *array;
+		array--;
+	}
+
+	if (type & PERF_SAMPLE_ID) {
+		sample->id = *array;
+		array--;
+	}
+
+	if (type & PERF_SAMPLE_TIME) {
+		sample->time = *array;
+		array--;
+	}
+
+	if (type & PERF_SAMPLE_TID) {
+		u32 *p = (u32 *)array;
+		sample->pid = p[0];
+		sample->tid = p[1];
+	}
+
+	return 0;
+}
+
+int event__parse_sample(const event_t *event, struct perf_session *session,
+			struct sample_data *data)
+{
+	const u64 *array;
+	u64 type;
+
+	if (event->header.type != PERF_RECORD_SAMPLE)
+		return event__parse_id_sample(event, session, data);
+
+	array = event->sample.array;
+	type = session->sample_type;
 
 	if (type & PERF_SAMPLE_IP) {
 		data->ip = event->ip.ip;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 08c400b83d57..a95ab18575ce 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -142,8 +142,8 @@ typedef int (*event__handler_t)(event_t *event, struct sample_data *sample,
 
 int event__synthesize_thread(pid_t pid, event__handler_t process,
 			     struct perf_session *session);
-void event__synthesize_threads(event__handler_t process,
-			       struct perf_session *session);
+int event__synthesize_threads(event__handler_t process,
+			      struct perf_session *session);
 int event__synthesize_kernel_mmap(event__handler_t process,
 				struct perf_session *session,
 				struct machine *machine,
@@ -168,7 +168,8 @@ struct addr_location;
 int event__preprocess_sample(const event_t *self, struct perf_session *session,
 			     struct addr_location *al, struct sample_data *data,
 			     symbol_filter_t filter);
-int event__parse_sample(const event_t *event, u64 type, struct sample_data *data);
+int event__parse_sample(const event_t *event, struct perf_session *session,
+			struct sample_data *sample);
 
 extern const char *event__name[];
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index fe652f3b0aa7..073f0e1c7123 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -946,6 +946,24 @@ u64 perf_header__sample_type(struct perf_header *header)
 	return type;
 }
 
+bool perf_header__sample_id_all(const struct perf_header *header)
+{
+	bool value = false, first = true;
+	int i;
+
+	for (i = 0; i < header->attrs; i++) {
+		struct perf_header_attr *attr = header->attr[i];
+
+		if (first) {
+			value = attr->attr.sample_id_all;
+			first = false;
+		} else if (value != attr->attr.sample_id_all)
+			die("non matching sample_id_all");
+	}
+
+	return value;
+}
+
 struct perf_event_attr *
 perf_header__find_attr(u64 id, struct perf_header *header)
 {
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index ed550bffd655..6335965e1f93 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -81,6 +81,7 @@ void perf_header_attr__delete(struct perf_header_attr *self);
 int perf_header_attr__add_id(struct perf_header_attr *self, u64 id);
 
 u64 perf_header__sample_type(struct perf_header *header);
+bool perf_header__sample_id_all(const struct perf_header *header);
 struct perf_event_attr *
 perf_header__find_attr(u64 id, struct perf_header *header);
 void perf_header__set_feat(struct perf_header *self, int feat);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 08ec018966a8..5c756609104e 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -65,9 +65,37 @@ static int perf_session__open(struct perf_session *self, bool force)
 	return -1;
 }
 
-void perf_session__update_sample_type(struct perf_session *self)
+static void perf_session__id_header_size(struct perf_session *session)
 {
-	self->sample_type = perf_header__sample_type(&self->header);
+       struct sample_data *data;
+       u64 sample_type = session->sample_type;
+       u16 size = 0;
+
+	if (!session->sample_id_all)
+		goto out;
+
+       if (sample_type & PERF_SAMPLE_TID)
+               size += sizeof(data->tid) * 2;
+
+       if (sample_type & PERF_SAMPLE_TIME)
+               size += sizeof(data->time);
+
+       if (sample_type & PERF_SAMPLE_ID)
+               size += sizeof(data->id);
+
+       if (sample_type & PERF_SAMPLE_STREAM_ID)
+               size += sizeof(data->stream_id);
+
+       if (sample_type & PERF_SAMPLE_CPU)
+               size += sizeof(data->cpu) * 2;
+out:
+       session->id_hdr_size = size;
+}
+
+void perf_session__set_sample_id_all(struct perf_session *session, bool value)
+{
+	session->sample_id_all = value;
+	perf_session__id_header_size(session);
 }
 
 void perf_session__set_sample_type(struct perf_session *session, u64 type)
@@ -75,6 +103,13 @@ void perf_session__set_sample_type(struct perf_session *session, u64 type)
 	session->sample_type = type;
 }
 
+void perf_session__update_sample_type(struct perf_session *self)
+{
+	self->sample_type = perf_header__sample_type(&self->header);
+	self->sample_id_all = perf_header__sample_id_all(&self->header);
+	perf_session__id_header_size(self);
+}
+
 int perf_session__create_kernel_maps(struct perf_session *self)
 {
 	int ret = machine__create_kernel_maps(&self->host_machine);
@@ -443,7 +478,7 @@ static void flush_sample_queue(struct perf_session *s,
 		if (iter->timestamp > limit)
 			break;
 
-		event__parse_sample(iter->event, s->sample_type, &sample);
+		event__parse_sample(iter->event, s, &sample);
 		ops->sample(iter->event, &sample, s);
 
 		os->last_flush = iter->timestamp;
@@ -618,6 +653,23 @@ static void callchain__dump(struct sample_data *sample)
 		printf("..... %2d: %016Lx\n", i, sample->callchain->ips[i]);
 }
 
+static void perf_session__print_tstamp(struct perf_session *session,
+				       event_t *event,
+				       struct sample_data *sample)
+{
+	if (event->header.type != PERF_RECORD_SAMPLE &&
+	    !session->sample_id_all) {
+		fputs("-1 -1 ", stdout);
+		return;
+	}
+
+	if ((session->sample_type & PERF_SAMPLE_CPU))
+		printf("%u ", sample->cpu);
+
+	if (session->sample_type & PERF_SAMPLE_TIME)
+		printf("%Lu ", sample->time);
+}
+
 static int perf_session__process_event(struct perf_session *self,
 				       event_t *event,
 				       struct perf_event_ops *ops,
@@ -630,8 +682,12 @@ static int perf_session__process_event(struct perf_session *self,
 	if (self->header.needs_swap && event__swap_ops[event->header.type])
 		event__swap_ops[event->header.type](event);
 
-	if (event->header.type == PERF_RECORD_SAMPLE)
-		event__parse_sample(event, self->sample_type, &sample);
+	if (event->header.type >= PERF_RECORD_MMAP &&
+	    event->header.type <= PERF_RECORD_SAMPLE) {
+		event__parse_sample(event, self, &sample);
+		if (dump_trace)
+			perf_session__print_tstamp(self, event, &sample);
+	}
 
 	if (event->header.type < PERF_RECORD_HEADER_MAX) {
 		dump_printf("%#Lx [%#x]: PERF_RECORD_%s",
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 4578f86a6209..ac36f99f14af 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -46,6 +46,8 @@ struct perf_session {
 	int			fd;
 	bool			fd_pipe;
 	bool			repipe;
+	bool			sample_id_all;
+	u16			id_hdr_size;
 	int			cwdlen;
 	char			*cwd;
 	struct ordered_samples	ordered_samples;
@@ -106,6 +108,7 @@ int perf_session__create_kernel_maps(struct perf_session *self);
 
 int do_read(int fd, void *buf, size_t size);
 void perf_session__update_sample_type(struct perf_session *self);
+void perf_session__set_sample_id_all(struct perf_session *session, bool value);
 void perf_session__set_sample_type(struct perf_session *session, u64 type);
 void perf_session__remove_thread(struct perf_session *self, struct thread *th);