diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index adf6d9931643..2814ead4adb8 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -215,8 +215,9 @@ struct perf_event_attr {
 				 */
 				precise_ip     :  2, /* skid constraint       */
 				mmap_data      :  1, /* non-exec mmap data    */
+				sample_id_all  :  1, /* sample_type all events */
 
-				__reserved_1   : 46;
+				__reserved_1   : 45;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -327,6 +328,15 @@ struct perf_event_header {
 enum perf_event_type {
 
 	/*
+	 * If perf_event_attr.sample_id_all is set then all event types will
+	 * have the sample_type selected fields related to where/when
+	 * (identity) an event took place (TID, TIME, ID, CPU, STREAM_ID)
+	 * described in PERF_RECORD_SAMPLE below, it will be stashed just after
+	 * the perf_event_header and the fields already present for the existing
+	 * fields, i.e. at the end of the payload. That way a newer perf.data
+	 * file will be supported by older perf tools, with these new optional
+	 * fields being ignored.
+	 *
 	 * The MMAP events record the PROT_EXEC mappings so that we can
 	 * correlate userspace IPs to code. They have the following structure:
 	 *
@@ -759,6 +769,7 @@ struct perf_event {
 
 	struct perf_event_attr		attr;
 	u16				header_size;
+	u16				id_header_size;
 	u16				read_size;
 	struct hw_perf_event		hw;
 
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index aede71245e9f..77ad22c00b9d 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -133,6 +133,28 @@ static void unclone_ctx(struct perf_event_context *ctx)
 	}
 }
 
+static u32 perf_event_pid(struct perf_event *event, struct task_struct *p)
+{
+	/*
+	 * only top level events have the pid namespace they were created in
+	 */
+	if (event->parent)
+		event = event->parent;
+
+	return task_tgid_nr_ns(p, event->ns);
+}
+
+static u32 perf_event_tid(struct perf_event *event, struct task_struct *p)
+{
+	/*
+	 * only top level events have the pid namespace they were created in
+	 */
+	if (event->parent)
+		event = event->parent;
+
+	return task_pid_nr_ns(p, event->ns);
+}
+
 /*
  * If we inherit events we want to return the parent event id
  * to userspace.
@@ -351,15 +373,30 @@ static void perf_event__header_size(struct perf_event *event)
 	if (sample_type & PERF_SAMPLE_IP)
 		size += sizeof(data->ip);
 
+	if (sample_type & PERF_SAMPLE_ADDR)
+		size += sizeof(data->addr);
+
+	if (sample_type & PERF_SAMPLE_PERIOD)
+		size += sizeof(data->period);
+
+	if (sample_type & PERF_SAMPLE_READ)
+		size += event->read_size;
+
+	event->header_size = size;
+}
+
+static void perf_event__id_header_size(struct perf_event *event)
+{
+	struct perf_sample_data *data;
+	u64 sample_type = event->attr.sample_type;
+	u16 size = 0;
+
 	if (sample_type & PERF_SAMPLE_TID)
 		size += sizeof(data->tid_entry);
 
 	if (sample_type & PERF_SAMPLE_TIME)
 		size += sizeof(data->time);
 
-	if (sample_type & PERF_SAMPLE_ADDR)
-		size += sizeof(data->addr);
-
 	if (sample_type & PERF_SAMPLE_ID)
 		size += sizeof(data->id);
 
@@ -369,13 +406,7 @@ static void perf_event__header_size(struct perf_event *event)
 	if (sample_type & PERF_SAMPLE_CPU)
 		size += sizeof(data->cpu_entry);
 
-	if (sample_type & PERF_SAMPLE_PERIOD)
-		size += sizeof(data->period);
-
-	if (sample_type & PERF_SAMPLE_READ)
-		size += event->read_size;
-
-	event->header_size = size;
+	event->id_header_size = size;
 }
 
 static void perf_group_attach(struct perf_event *event)
@@ -3357,6 +3388,73 @@ __always_inline void perf_output_copy(struct perf_output_handle *handle,
 	} while (len);
 }
 
+static void __perf_event_header__init_id(struct perf_event_header *header,
+					 struct perf_sample_data *data,
+					 struct perf_event *event)
+{
+	u64 sample_type = event->attr.sample_type;
+
+	data->type = sample_type;
+	header->size += event->id_header_size;
+
+	if (sample_type & PERF_SAMPLE_TID) {
+		/* namespace issues */
+		data->tid_entry.pid = perf_event_pid(event, current);
+		data->tid_entry.tid = perf_event_tid(event, current);
+	}
+
+	if (sample_type & PERF_SAMPLE_TIME)
+		data->time = perf_clock();
+
+	if (sample_type & PERF_SAMPLE_ID)
+		data->id = primary_event_id(event);
+
+	if (sample_type & PERF_SAMPLE_STREAM_ID)
+		data->stream_id = event->id;
+
+	if (sample_type & PERF_SAMPLE_CPU) {
+		data->cpu_entry.cpu	 = raw_smp_processor_id();
+		data->cpu_entry.reserved = 0;
+	}
+}
+
+static void perf_event_header__init_id(struct perf_event_header *header,
+				       struct perf_sample_data *data,
+				       struct perf_event *event)
+{
+	if (event->attr.sample_id_all)
+		__perf_event_header__init_id(header, data, event);
+}
+
+static void __perf_event__output_id_sample(struct perf_output_handle *handle,
+					   struct perf_sample_data *data)
+{
+	u64 sample_type = data->type;
+
+	if (sample_type & PERF_SAMPLE_TID)
+		perf_output_put(handle, data->tid_entry);
+
+	if (sample_type & PERF_SAMPLE_TIME)
+		perf_output_put(handle, data->time);
+
+	if (sample_type & PERF_SAMPLE_ID)
+		perf_output_put(handle, data->id);
+
+	if (sample_type & PERF_SAMPLE_STREAM_ID)
+		perf_output_put(handle, data->stream_id);
+
+	if (sample_type & PERF_SAMPLE_CPU)
+		perf_output_put(handle, data->cpu_entry);
+}
+
+static void perf_event__output_id_sample(struct perf_event *event,
+					 struct perf_output_handle *handle,
+					 struct perf_sample_data *sample)
+{
+	if (event->attr.sample_id_all)
+		__perf_event__output_id_sample(handle, sample);
+}
+
 int perf_output_begin(struct perf_output_handle *handle,
 		      struct perf_event *event, unsigned int size,
 		      int nmi, int sample)
@@ -3364,6 +3462,7 @@ int perf_output_begin(struct perf_output_handle *handle,
 	struct perf_buffer *buffer;
 	unsigned long tail, offset, head;
 	int have_lost;
+	struct perf_sample_data sample_data;
 	struct {
 		struct perf_event_header header;
 		u64			 id;
@@ -3390,8 +3489,12 @@ int perf_output_begin(struct perf_output_handle *handle,
 		goto out;
 
 	have_lost = local_read(&buffer->lost);
-	if (have_lost)
-		size += sizeof(lost_event);
+	if (have_lost) {
+		lost_event.header.size = sizeof(lost_event);
+		perf_event_header__init_id(&lost_event.header, &sample_data,
+					   event);
+		size += lost_event.header.size;
+	}
 
 	perf_output_get_handle(handle);
 
@@ -3422,11 +3525,11 @@ int perf_output_begin(struct perf_output_handle *handle,
 	if (have_lost) {
 		lost_event.header.type = PERF_RECORD_LOST;
 		lost_event.header.misc = 0;
-		lost_event.header.size = sizeof(lost_event);
 		lost_event.id          = event->id;
 		lost_event.lost        = local_xchg(&buffer->lost, 0);
 
 		perf_output_put(handle, lost_event);
+		perf_event__output_id_sample(event, handle, &sample_data);
 	}
 
 	return 0;
@@ -3459,28 +3562,6 @@ void perf_output_end(struct perf_output_handle *handle)
 	rcu_read_unlock();
 }
 
-static u32 perf_event_pid(struct perf_event *event, struct task_struct *p)
-{
-	/*
-	 * only top level events have the pid namespace they were created in
-	 */
-	if (event->parent)
-		event = event->parent;
-
-	return task_tgid_nr_ns(p, event->ns);
-}
-
-static u32 perf_event_tid(struct perf_event *event, struct task_struct *p)
-{
-	/*
-	 * only top level events have the pid namespace they were created in
-	 */
-	if (event->parent)
-		event = event->parent;
-
-	return task_pid_nr_ns(p, event->ns);
-}
-
 static void perf_output_read_one(struct perf_output_handle *handle,
 				 struct perf_event *event,
 				 u64 enabled, u64 running)
@@ -3655,37 +3736,17 @@ void perf_prepare_sample(struct perf_event_header *header,
 {
 	u64 sample_type = event->attr.sample_type;
 
-	data->type = sample_type;
-
 	header->type = PERF_RECORD_SAMPLE;
 	header->size = sizeof(*header) + event->header_size;
 
 	header->misc = 0;
 	header->misc |= perf_misc_flags(regs);
 
+	__perf_event_header__init_id(header, data, event);
+
 	if (sample_type & PERF_SAMPLE_IP)
 		data->ip = perf_instruction_pointer(regs);
 
-	if (sample_type & PERF_SAMPLE_TID) {
-		/* namespace issues */
-		data->tid_entry.pid = perf_event_pid(event, current);
-		data->tid_entry.tid = perf_event_tid(event, current);
-	}
-
-	if (sample_type & PERF_SAMPLE_TIME)
-		data->time = perf_clock();
-
-	if (sample_type & PERF_SAMPLE_ID)
-		data->id = primary_event_id(event);
-
-	if (sample_type & PERF_SAMPLE_STREAM_ID)
-		data->stream_id = event->id;
-
-	if (sample_type & PERF_SAMPLE_CPU) {
-		data->cpu_entry.cpu		= raw_smp_processor_id();
-		data->cpu_entry.reserved	= 0;
-	}
-
 	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
 		int size = 1;
 
@@ -3749,6 +3810,7 @@ perf_event_read_event(struct perf_event *event,
 			struct task_struct *task)
 {
 	struct perf_output_handle handle;
+	struct perf_sample_data sample;
 	struct perf_read_event read_event = {
 		.header = {
 			.type = PERF_RECORD_READ,
@@ -3760,12 +3822,14 @@ perf_event_read_event(struct perf_event *event,
 	};
 	int ret;
 
+	perf_event_header__init_id(&read_event.header, &sample, event);
 	ret = perf_output_begin(&handle, event, read_event.header.size, 0, 0);
 	if (ret)
 		return;
 
 	perf_output_put(&handle, read_event);
 	perf_output_read(&handle, event);
+	perf_event__output_id_sample(event, &handle, &sample);
 
 	perf_output_end(&handle);
 }
@@ -3795,14 +3859,16 @@ static void perf_event_task_output(struct perf_event *event,
 				     struct perf_task_event *task_event)
 {
 	struct perf_output_handle handle;
+	struct perf_sample_data	sample;
 	struct task_struct *task = task_event->task;
-	int size, ret;
+	int ret, size = task_event->event_id.header.size;
 
-	size  = task_event->event_id.header.size;
-	ret = perf_output_begin(&handle, event, size, 0, 0);
+	perf_event_header__init_id(&task_event->event_id.header, &sample, event);
 
+	ret = perf_output_begin(&handle, event,
+				task_event->event_id.header.size, 0, 0);
 	if (ret)
-		return;
+		goto out;
 
 	task_event->event_id.pid = perf_event_pid(event, task);
 	task_event->event_id.ppid = perf_event_pid(event, current);
@@ -3812,7 +3878,11 @@ static void perf_event_task_output(struct perf_event *event,
 
 	perf_output_put(&handle, task_event->event_id);
 
+	perf_event__output_id_sample(event, &handle, &sample);
+
 	perf_output_end(&handle);
+out:
+	task_event->event_id.header.size = size;
 }
 
 static int perf_event_task_match(struct perf_event *event)
@@ -3925,11 +3995,16 @@ static void perf_event_comm_output(struct perf_event *event,
 				     struct perf_comm_event *comm_event)
 {
 	struct perf_output_handle handle;
+	struct perf_sample_data sample;
 	int size = comm_event->event_id.header.size;
-	int ret = perf_output_begin(&handle, event, size, 0, 0);
+	int ret;
+
+	perf_event_header__init_id(&comm_event->event_id.header, &sample, event);
+	ret = perf_output_begin(&handle, event,
+				comm_event->event_id.header.size, 0, 0);
 
 	if (ret)
-		return;
+		goto out;
 
 	comm_event->event_id.pid = perf_event_pid(event, comm_event->task);
 	comm_event->event_id.tid = perf_event_tid(event, comm_event->task);
@@ -3937,7 +4012,12 @@ static void perf_event_comm_output(struct perf_event *event,
 	perf_output_put(&handle, comm_event->event_id);
 	perf_output_copy(&handle, comm_event->comm,
 				   comm_event->comm_size);
+
+	perf_event__output_id_sample(event, &handle, &sample);
+
 	perf_output_end(&handle);
+out:
+	comm_event->event_id.header.size = size;
 }
 
 static int perf_event_comm_match(struct perf_event *event)
@@ -3982,7 +4062,6 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
 	comm_event->comm_size = size;
 
 	comm_event->event_id.header.size = sizeof(comm_event->event_id) + size;
-
 	rcu_read_lock();
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
 		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
@@ -4061,11 +4140,15 @@ static void perf_event_mmap_output(struct perf_event *event,
 				     struct perf_mmap_event *mmap_event)
 {
 	struct perf_output_handle handle;
+	struct perf_sample_data sample;
 	int size = mmap_event->event_id.header.size;
-	int ret = perf_output_begin(&handle, event, size, 0, 0);
+	int ret;
 
+	perf_event_header__init_id(&mmap_event->event_id.header, &sample, event);
+	ret = perf_output_begin(&handle, event,
+				mmap_event->event_id.header.size, 0, 0);
 	if (ret)
-		return;
+		goto out;
 
 	mmap_event->event_id.pid = perf_event_pid(event, current);
 	mmap_event->event_id.tid = perf_event_tid(event, current);
@@ -4073,7 +4156,12 @@ static void perf_event_mmap_output(struct perf_event *event,
 	perf_output_put(&handle, mmap_event->event_id);
 	perf_output_copy(&handle, mmap_event->file_name,
 				   mmap_event->file_size);
+
+	perf_event__output_id_sample(event, &handle, &sample);
+
 	perf_output_end(&handle);
+out:
+	mmap_event->event_id.header.size = size;
 }
 
 static int perf_event_mmap_match(struct perf_event *event,
@@ -4226,6 +4314,7 @@ void perf_event_mmap(struct vm_area_struct *vma)
 static void perf_log_throttle(struct perf_event *event, int enable)
 {
 	struct perf_output_handle handle;
+	struct perf_sample_data sample;
 	int ret;
 
 	struct {
@@ -4247,11 +4336,15 @@ static void perf_log_throttle(struct perf_event *event, int enable)
 	if (enable)
 		throttle_event.header.type = PERF_RECORD_UNTHROTTLE;
 
-	ret = perf_output_begin(&handle, event, sizeof(throttle_event), 1, 0);
+	perf_event_header__init_id(&throttle_event.header, &sample, event);
+
+	ret = perf_output_begin(&handle, event,
+				throttle_event.header.size, 1, 0);
 	if (ret)
 		return;
 
 	perf_output_put(&handle, throttle_event);
+	perf_event__output_id_sample(event, &handle, &sample);
 	perf_output_end(&handle);
 }
 
@@ -5745,6 +5838,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	 * Precalculate sample_data sizes
 	 */
 	perf_event__header_size(event);
+	perf_event__id_header_size(event);
 
 	/*
 	 * Drop the reference on the group_event after placing the
@@ -6098,6 +6192,12 @@ inherit_event(struct perf_event *parent_event,
 	child_event->ctx = child_ctx;
 	child_event->overflow_handler = parent_event->overflow_handler;
 
+	/*
+	 * Precalculate sample_data sizes
+	 */
+	perf_event__header_size(child_event);
+	perf_event__id_header_size(child_event);
+
 	/*
 	 * Link it up in the child's context:
 	 */
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-annotate.c b/tools/perf/builtin-annotate.c
index 6d5604d8df95..569a2761b90a 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -58,12 +58,12 @@ static int hists__add_entry(struct hists *self, struct addr_location *al)
 	return hist_entry__inc_addr_samples(he, al->addr);
 }
 
-static int process_sample_event(event_t *event, struct perf_session *session)
+static int process_sample_event(event_t *event, struct sample_data *sample,
+				struct perf_session *session)
 {
 	struct addr_location al;
-	struct sample_data data;
 
-	if (event__preprocess_sample(event, session, &al, &data, NULL) < 0) {
+	if (event__preprocess_sample(event, session, &al, sample, NULL) < 0) {
 		pr_warning("problem processing %d event, skipping it.\n",
 			   event->header.type);
 		return -1;
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 221b823bc26f..5e1a043aae03 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -30,12 +30,13 @@ static int hists__add_entry(struct hists *self,
 	return -ENOMEM;
 }
 
-static int diff__process_sample_event(event_t *event, struct perf_session *session)
+static int diff__process_sample_event(event_t *event,
+				      struct sample_data *sample,
+				      struct perf_session *session)
 {
 	struct addr_location al;
-	struct sample_data data = { .period = 1, };
 
-	if (event__preprocess_sample(event, session, &al, &data, NULL) < 0) {
+	if (event__preprocess_sample(event, session, &al, sample, NULL) < 0) {
 		pr_warning("problem processing %d event, skipping it.\n",
 			   event->header.type);
 		return -1;
@@ -44,12 +45,12 @@ static int diff__process_sample_event(event_t *event, struct perf_session *sessi
 	if (al.filtered || al.sym == NULL)
 		return 0;
 
-	if (hists__add_entry(&session->hists, &al, data.period)) {
+	if (hists__add_entry(&session->hists, &al, sample->period)) {
 		pr_warning("problem incrementing symbol period, skipping event\n");
 		return -1;
 	}
 
-	session->hists.stats.total_period += data.period;
+	session->hists.stats.total_period += sample->period;
 	return 0;
 }
 
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 8e3e47b064ce..4b66b8579410 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -16,8 +16,8 @@
 static char		const *input_name = "-";
 static bool		inject_build_ids;
 
-static int event__repipe(event_t *event __used,
-			 struct perf_session *session __used)
+static int event__repipe_synth(event_t *event,
+			       struct perf_session *session __used)
 {
 	uint32_t size;
 	void *buf = event;
@@ -36,22 +36,30 @@ static int event__repipe(event_t *event __used,
 	return 0;
 }
 
-static int event__repipe_mmap(event_t *self, struct perf_session *session)
+static int event__repipe(event_t *event, struct sample_data *sample __used,
+			 struct perf_session *session)
+{
+	return event__repipe_synth(event, session);
+}
+
+static int event__repipe_mmap(event_t *self, struct sample_data *sample,
+			      struct perf_session *session)
 {
 	int err;
 
-	err = event__process_mmap(self, session);
-	event__repipe(self, session);
+	err = event__process_mmap(self, sample, session);
+	event__repipe(self, sample, session);
 
 	return err;
 }
 
-static int event__repipe_task(event_t *self, struct perf_session *session)
+static int event__repipe_task(event_t *self, struct sample_data *sample,
+			      struct perf_session *session)
 {
 	int err;
 
-	err = event__process_task(self, session);
-	event__repipe(self, session);
+	err = event__process_task(self, sample, session);
+	event__repipe(self, sample, session);
 
 	return err;
 }
@@ -61,7 +69,7 @@ static int event__repipe_tracing_data(event_t *self,
 {
 	int err;
 
-	event__repipe(self, session);
+	event__repipe_synth(self, session);
 	err = event__process_tracing_data(self, session);
 
 	return err;
@@ -111,7 +119,8 @@ static int dso__inject_build_id(struct dso *self, struct perf_session *session)
 	return 0;
 }
 
-static int event__inject_buildid(event_t *event, struct perf_session *session)
+static int event__inject_buildid(event_t *event, struct sample_data *sample,
+				 struct perf_session *session)
 {
 	struct addr_location al;
 	struct thread *thread;
@@ -146,7 +155,7 @@ static int event__inject_buildid(event_t *event, struct perf_session *session)
 	}
 
 repipe:
-	event__repipe(event, session);
+	event__repipe(event, sample, session);
 	return 0;
 }
 
@@ -160,10 +169,10 @@ struct perf_event_ops inject_ops = {
 	.read		= event__repipe,
 	.throttle	= event__repipe,
 	.unthrottle	= event__repipe,
-	.attr		= event__repipe,
-	.event_type 	= event__repipe,
-	.tracing_data 	= event__repipe,
-	.build_id 	= event__repipe,
+	.attr		= event__repipe_synth,
+	.event_type 	= event__repipe_synth,
+	.tracing_data 	= event__repipe_synth,
+	.build_id 	= event__repipe_synth,
 };
 
 extern volatile int session_done;
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 31f60a2535e0..c9620ff6496f 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -304,22 +304,11 @@ process_raw_event(event_t *raw_event __used, void *data,
 	}
 }
 
-static int process_sample_event(event_t *event, struct perf_session *session)
+static int process_sample_event(event_t *event, struct sample_data *sample,
+				struct perf_session *session)
 {
-	struct sample_data data;
-	struct thread *thread;
+	struct thread *thread = perf_session__findnew(session, event->ip.pid);
 
-	memset(&data, 0, sizeof(data));
-	data.time = -1;
-	data.cpu = -1;
-	data.period = 1;
-
-	event__parse_sample(event, session->sample_type, &data);
-
-	dump_printf("(IP, %d): %d/%d: %#Lx period: %Ld\n", event->header.misc,
-		    data.pid, data.tid, data.ip, data.period);
-
-	thread = perf_session__findnew(session, event->ip.pid);
 	if (thread == NULL) {
 		pr_debug("problem processing %d event, skipping it.\n",
 			 event->header.type);
@@ -328,8 +317,8 @@ static int process_sample_event(event_t *event, struct perf_session *session)
 
 	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
 
-	process_raw_event(event, data.raw_data, data.cpu,
-			  data.time, thread);
+	process_raw_event(event, sample->raw_data, sample->cpu,
+			  sample->time, thread);
 
 	return 0;
 }
@@ -747,6 +736,9 @@ static int __cmd_record(int argc, const char **argv)
 	rec_argc = ARRAY_SIZE(record_args) + argc - 1;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
+	if (rec_argv == NULL)
+		return -ENOMEM;
+
 	for (i = 0; i < ARRAY_SIZE(record_args); i++)
 		rec_argv[i] = strdup(record_args[i]);
 
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 8452a2ae2191..b41b4492b1cc 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -834,22 +834,18 @@ static void dump_info(void)
 		die("Unknown type of information\n");
 }
 
-static int process_sample_event(event_t *self, struct perf_session *s)
+static int process_sample_event(event_t *self, struct sample_data *sample,
+				struct perf_session *s)
 {
-	struct sample_data data;
-	struct thread *thread;
+	struct thread *thread = perf_session__findnew(s, sample->tid);
 
-	bzero(&data, sizeof(data));
-	event__parse_sample(self, s->sample_type, &data);
-
-	thread = perf_session__findnew(s, data.tid);
 	if (thread == NULL) {
 		pr_debug("problem processing %d event, skipping it.\n",
 			self->header.type);
 		return -1;
 	}
 
-	process_raw_event(data.raw_data, data.cpu, data.time, thread);
+	process_raw_event(sample->raw_data, sample->cpu, sample->time, thread);
 
 	return 0;
 }
@@ -947,6 +943,9 @@ static int __cmd_record(int argc, const char **argv)
 	rec_argc = ARRAY_SIZE(record_args) + argc - 1;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
+	if (rec_argv == NULL)
+		return -ENOMEM;
+
 	for (i = 0; i < ARRAY_SIZE(record_args); i++)
 		rec_argv[i] = strdup(record_args[i]);
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 024e1441d76b..699dd2149c4b 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -36,6 +36,7 @@ static int			*fd[MAX_NR_CPUS][MAX_COUNTERS];
 
 static u64			user_interval			= ULLONG_MAX;
 static u64			default_interval		=      0;
+static u64			sample_type;
 
 static int			nr_cpus				=      0;
 static unsigned int		page_size;
@@ -48,6 +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;
@@ -60,6 +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;
 
@@ -129,6 +132,7 @@ static void write_output(void *buf, size_t size)
 }
 
 static int process_synthesized_event(event_t *event,
+				     struct sample_data *sample __used,
 				     struct perf_session *self __used)
 {
 	write_output(event, event->header.size);
@@ -281,12 +285,18 @@ 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;
 		attr->sample_type	|= PERF_SAMPLE_CPU;
 	}
 
+	if (!sample_type)
+		sample_type = attr->sample_type;
+
 	attr->mmap		= track;
 	attr->comm		= track;
 	attr->inherit		= !no_inherit;
@@ -294,6 +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:
@@ -310,6 +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;
 			}
 
 			/*
@@ -642,6 +660,8 @@ static int __cmd_record(int argc, const char **argv)
 			open_counters(cpumap[i]);
 	}
 
+	perf_session__set_sample_type(session, sample_type);
+
 	if (pipe_output) {
 		err = perf_header__write_pipe(output);
 		if (err < 0)
@@ -654,6 +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,
@@ -834,6 +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-report.c b/tools/perf/builtin-report.c
index 5de405d45230..904519fba434 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -150,13 +150,13 @@ static int add_event_total(struct perf_session *session,
 	return 0;
 }
 
-static int process_sample_event(event_t *event, struct perf_session *session)
+static int process_sample_event(event_t *event, struct sample_data *sample,
+				struct perf_session *session)
 {
-	struct sample_data data = { .period = 1, };
 	struct addr_location al;
 	struct perf_event_attr *attr;
 
-	if (event__preprocess_sample(event, session, &al, &data, NULL) < 0) {
+	if (event__preprocess_sample(event, session, &al, sample, NULL) < 0) {
 		fprintf(stderr, "problem processing %d event, skipping it.\n",
 			event->header.type);
 		return -1;
@@ -165,14 +165,14 @@ static int process_sample_event(event_t *event, struct perf_session *session)
 	if (al.filtered || (hide_unresolved && al.sym == NULL))
 		return 0;
 
-	if (perf_session__add_hist_entry(session, &al, &data)) {
+	if (perf_session__add_hist_entry(session, &al, sample)) {
 		pr_debug("problem incrementing symbol period, skipping event\n");
 		return -1;
 	}
 
-	attr = perf_header__find_attr(data.id, &session->header);
+	attr = perf_header__find_attr(sample->id, &session->header);
 
-	if (add_event_total(session, &data, attr)) {
+	if (add_event_total(session, sample, attr)) {
 		pr_debug("problem adding event period\n");
 		return -1;
 	}
@@ -180,7 +180,8 @@ static int process_sample_event(event_t *event, struct perf_session *session)
 	return 0;
 }
 
-static int process_read_event(event_t *event, struct perf_session *session __used)
+static int process_read_event(event_t *event, struct sample_data *sample __used,
+			      struct perf_session *session __used)
 {
 	struct perf_event_attr *attr;
 
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 26523c939791..c7753940aea0 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1606,25 +1606,15 @@ process_raw_event(event_t *raw_event __used, struct perf_session *session,
 		process_sched_migrate_task_event(data, session, event, cpu, timestamp, thread);
 }
 
-static int process_sample_event(event_t *event, struct perf_session *session)
+static int process_sample_event(event_t *event, struct sample_data *sample,
+				struct perf_session *session)
 {
-	struct sample_data data;
 	struct thread *thread;
 
 	if (!(session->sample_type & PERF_SAMPLE_RAW))
 		return 0;
 
-	memset(&data, 0, sizeof(data));
-	data.time = -1;
-	data.cpu = -1;
-	data.period = -1;
-
-	event__parse_sample(event, session->sample_type, &data);
-
-	dump_printf("(IP, %d): %d/%d: %#Lx period: %Ld\n", event->header.misc,
-		    data.pid, data.tid, data.ip, data.period);
-
-	thread = perf_session__findnew(session, data.pid);
+	thread = perf_session__findnew(session, sample->pid);
 	if (thread == NULL) {
 		pr_debug("problem processing %d event, skipping it.\n",
 			 event->header.type);
@@ -1633,10 +1623,11 @@ static int process_sample_event(event_t *event, struct perf_session *session)
 
 	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
 
-	if (profile_cpu != -1 && profile_cpu != (int)data.cpu)
+	if (profile_cpu != -1 && profile_cpu != (int)sample->cpu)
 		return 0;
 
-	process_raw_event(event, session, data.raw_data, data.cpu, data.time, thread);
+	process_raw_event(event, session, sample->raw_data, sample->cpu,
+			  sample->time, thread);
 
 	return 0;
 }
@@ -1869,6 +1860,9 @@ static int __cmd_record(int argc, const char **argv)
 	rec_argc = ARRAY_SIZE(record_args) + argc - 1;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
+	if (rec_argv)
+		return -ENOMEM;
+
 	for (i = 0; i < ARRAY_SIZE(record_args); i++)
 		rec_argv[i] = strdup(record_args[i]);
 
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 4539551ab40e..54f1ea808db5 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -63,22 +63,11 @@ static int cleanup_scripting(void)
 
 static char const		*input_name = "perf.data";
 
-static int process_sample_event(event_t *event, struct perf_session *session)
+static int process_sample_event(event_t *event, struct sample_data *sample,
+				struct perf_session *session)
 {
-	struct sample_data data;
-	struct thread *thread;
+	struct thread *thread = perf_session__findnew(session, event->ip.pid);
 
-	memset(&data, 0, sizeof(data));
-	data.time = -1;
-	data.cpu = -1;
-	data.period = 1;
-
-	event__parse_sample(event, session->sample_type, &data);
-
-	dump_printf("(IP, %d): %d/%d: %#Lx period: %Ld\n", event->header.misc,
-		    data.pid, data.tid, data.ip, data.period);
-
-	thread = perf_session__findnew(session, event->ip.pid);
 	if (thread == NULL) {
 		pr_debug("problem processing %d event, skipping it.\n",
 			 event->header.type);
@@ -87,13 +76,13 @@ static int process_sample_event(event_t *event, struct perf_session *session)
 
 	if (session->sample_type & PERF_SAMPLE_RAW) {
 		if (debug_mode) {
-			if (data.time < last_timestamp) {
+			if (sample->time < last_timestamp) {
 				pr_err("Samples misordered, previous: %llu "
 					"this: %llu\n", last_timestamp,
-					data.time);
+					sample->time);
 				nr_unordered++;
 			}
-			last_timestamp = data.time;
+			last_timestamp = sample->time;
 			return 0;
 		}
 		/*
@@ -101,18 +90,19 @@ static int process_sample_event(event_t *event, struct perf_session *session)
 		 * field, although it should be the same than this perf
 		 * event pid
 		 */
-		scripting_ops->process_event(data.cpu, data.raw_data,
-					     data.raw_size,
-					     data.time, thread->comm);
+		scripting_ops->process_event(sample->cpu, sample->raw_data,
+					     sample->raw_size,
+					     sample->time, thread->comm);
 	}
 
-	session->hists.stats.total_period += data.period;
+	session->hists.stats.total_period += sample->period;
 	return 0;
 }
 
 static u64 nr_lost;
 
-static int process_lost_event(event_t *event, struct perf_session *session __used)
+static int process_lost_event(event_t *event, struct sample_data *sample __used,
+			      struct perf_session *session __used)
 {
 	nr_lost += event->lost.lost;
 
@@ -397,10 +387,10 @@ static struct script_desc *script_desc__findnew(const char *name)
 	return NULL;
 }
 
-static char *ends_with(char *str, const char *suffix)
+static const char *ends_with(const char *str, const char *suffix)
 {
 	size_t suffix_len = strlen(suffix);
-	char *p = str;
+	const char *p = str;
 
 	if (strlen(str) > suffix_len) {
 		p = str + strlen(str) - suffix_len;
@@ -492,7 +482,7 @@ static int list_available_scripts(const struct option *opt __used,
 
 		for_each_script(lang_path, lang_dir, script_dirent, script_next) {
 			script_root = strdup(script_dirent.d_name);
-			str = ends_with(script_root, REPORT_SUFFIX);
+			str = (char *)ends_with(script_root, REPORT_SUFFIX);
 			if (str) {
 				*str = '\0';
 				desc = script_desc__findnew(script_root);
@@ -540,7 +530,7 @@ static char *get_script_path(const char *script_root, const char *suffix)
 
 		for_each_script(lang_path, lang_dir, script_dirent, script_next) {
 			__script_root = strdup(script_dirent.d_name);
-			str = ends_with(__script_root, suffix);
+			str = (char *)ends_with(__script_root, suffix);
 			if (str) {
 				*str = '\0';
 				if (strcmp(__script_root, script_root))
@@ -560,7 +550,7 @@ static char *get_script_path(const char *script_root, const char *suffix)
 
 static bool is_top_script(const char *script_path)
 {
-	return ends_with((char *)script_path, "top") == NULL ? false : true;
+	return ends_with(script_path, "top") == NULL ? false : true;
 }
 
 static int has_required_arg(char *script_path)
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 9bcc38f0b706..d2fc46103f83 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -272,19 +272,22 @@ static int cpus_cstate_state[MAX_CPUS];
 static u64 cpus_pstate_start_times[MAX_CPUS];
 static u64 cpus_pstate_state[MAX_CPUS];
 
-static int process_comm_event(event_t *event, struct perf_session *session __used)
+static int process_comm_event(event_t *event, struct sample_data *sample __used,
+			      struct perf_session *session __used)
 {
 	pid_set_comm(event->comm.tid, event->comm.comm);
 	return 0;
 }
 
-static int process_fork_event(event_t *event, struct perf_session *session __used)
+static int process_fork_event(event_t *event, struct sample_data *sample __used,
+			      struct perf_session *session __used)
 {
 	pid_fork(event->fork.pid, event->fork.ppid, event->fork.time);
 	return 0;
 }
 
-static int process_exit_event(event_t *event, struct perf_session *session __used)
+static int process_exit_event(event_t *event, struct sample_data *sample __used,
+			      struct perf_session *session __used)
 {
 	pid_exit(event->fork.pid, event->fork.time);
 	return 0;
@@ -470,24 +473,21 @@ static void sched_switch(int cpu, u64 timestamp, struct trace_entry *te)
 }
 
 
-static int process_sample_event(event_t *event, struct perf_session *session)
+static int process_sample_event(event_t *event __used,
+				struct sample_data *sample,
+				struct perf_session *session)
 {
-	struct sample_data data;
 	struct trace_entry *te;
 
-	memset(&data, 0, sizeof(data));
-
-	event__parse_sample(event, session->sample_type, &data);
-
 	if (session->sample_type & PERF_SAMPLE_TIME) {
-		if (!first_time || first_time > data.time)
-			first_time = data.time;
-		if (last_time < data.time)
-			last_time = data.time;
+		if (!first_time || first_time > sample->time)
+			first_time = sample->time;
+		if (last_time < sample->time)
+			last_time = sample->time;
 	}
 
-	te = (void *)data.raw_data;
-	if (session->sample_type & PERF_SAMPLE_RAW && data.raw_size > 0) {
+	te = (void *)sample->raw_data;
+	if (session->sample_type & PERF_SAMPLE_RAW && sample->raw_size > 0) {
 		char *event_str;
 		struct power_entry *pe;
 
@@ -499,19 +499,19 @@ static int process_sample_event(event_t *event, struct perf_session *session)
 			return 0;
 
 		if (strcmp(event_str, "power:power_start") == 0)
-			c_state_start(pe->cpu_id, data.time, pe->value);
+			c_state_start(pe->cpu_id, sample->time, pe->value);
 
 		if (strcmp(event_str, "power:power_end") == 0)
-			c_state_end(pe->cpu_id, data.time);
+			c_state_end(pe->cpu_id, sample->time);
 
 		if (strcmp(event_str, "power:power_frequency") == 0)
-			p_state_change(pe->cpu_id, data.time, pe->value);
+			p_state_change(pe->cpu_id, sample->time, pe->value);
 
 		if (strcmp(event_str, "sched:sched_wakeup") == 0)
-			sched_wakeup(data.cpu, data.time, data.pid, te);
+			sched_wakeup(sample->cpu, sample->time, sample->pid, te);
 
 		if (strcmp(event_str, "sched:sched_switch") == 0)
-			sched_switch(data.cpu, data.time, te);
+			sched_switch(sample->cpu, sample->time, te);
 	}
 	return 0;
 }
@@ -989,6 +989,9 @@ static int __cmd_record(int argc, const char **argv)
 	rec_argc = ARRAY_SIZE(record_args) + argc - 1;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
+	if (rec_argv == NULL)
+		return -ENOMEM;
+
 	for (i = 0; i < ARRAY_SIZE(record_args); i++)
 		rec_argv[i] = strdup(record_args[i]);
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 3d2b47d5121a..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;
 
@@ -1025,7 +1025,7 @@ static void event__process_sample(const event_t *self,
 	if (self->header.misc & PERF_RECORD_MISC_EXACT_IP)
 		exact_samples++;
 
-	if (event__preprocess_sample(self, session, &al, &data,
+	if (event__preprocess_sample(self, session, &al, sample,
 				     symbol_filter) < 0 ||
 	    al.filtered)
 		return;
@@ -1105,6 +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;
 
 	/*
@@ -1152,10 +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, self);
+			event__process(event, &sample, self);
 		old += size;
 	}
 
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index e437edb72417..deffb8c96071 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -14,7 +14,9 @@
 #include <linux/kernel.h>
 #include "debug.h"
 
-static int build_id__mark_dso_hit(event_t *event, struct perf_session *session)
+static int build_id__mark_dso_hit(event_t *event,
+				  struct sample_data *sample __used,
+				  struct perf_session *session)
 {
 	struct addr_location al;
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
@@ -35,7 +37,8 @@ static int build_id__mark_dso_hit(event_t *event, struct perf_session *session)
 	return 0;
 }
 
-static int event__exit_del_thread(event_t *self, struct perf_session *session)
+static int event__exit_del_thread(event_t *self, struct sample_data *sample __used,
+				  struct perf_session *session)
 {
 	struct thread *thread = perf_session__findnew(session, self->fork.tid);
 
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 7260db75b93d..e4cdc1ebe0fb 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -24,11 +24,19 @@ const char *event__name[] = {
 	[PERF_RECORD_HEADER_BUILD_ID]	 = "BUILD_ID",
 };
 
-static pid_t event__synthesize_comm(pid_t pid, int full,
+static struct sample_data synth_sample = {
+	.pid	   = -1,
+	.tid	   = -1,
+	.time	   = -1,
+	.stream_id = -1,
+	.cpu	   = -1,
+	.period	   = 1,
+};
+
+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;
@@ -49,34 +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, session);
-		goto out_fclose;
+		process(event, &synth_sample, session);
+		goto out;
 	}
 
 	snprintf(filename, sizeof(filename), "/proc/%d/task", pid);
@@ -91,22 +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, 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)
 {
@@ -124,29 +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;
@@ -161,19 +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, session);
+			process(event, &synth_sample, session);
 		}
 	}
 
@@ -187,20 +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);
 
@@ -208,39 +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, 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;
@@ -249,10 +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 {
@@ -286,18 +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)) {
@@ -305,10 +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 {
@@ -321,17 +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, session);
+	err = process(event, &synth_sample, session);
+	free(event);
+
+	return err;
 }
 
 static void thread__comm_adjust(struct thread *self, struct hists *hists)
@@ -361,7 +429,8 @@ static int thread__set_comm_adjust(struct thread *self, const char *comm,
 	return 0;
 }
 
-int event__process_comm(event_t *self, struct perf_session *session)
+int event__process_comm(event_t *self, struct sample_data *sample __used,
+			struct perf_session *session)
 {
 	struct thread *thread = perf_session__findnew(session, self->comm.tid);
 
@@ -376,7 +445,8 @@ int event__process_comm(event_t *self, struct perf_session *session)
 	return 0;
 }
 
-int event__process_lost(event_t *self, struct perf_session *session)
+int event__process_lost(event_t *self, struct sample_data *sample __used,
+			struct perf_session *session)
 {
 	dump_printf(": id:%Ld: lost:%Ld\n", self->lost.id, self->lost.lost);
 	session->hists.stats.total_lost += self->lost.lost;
@@ -485,7 +555,8 @@ static int event__process_kernel_mmap(event_t *self,
 	return -1;
 }
 
-int event__process_mmap(event_t *self, struct perf_session *session)
+int event__process_mmap(event_t *self, struct sample_data *sample __used,
+			struct perf_session *session)
 {
 	struct machine *machine;
 	struct thread *thread;
@@ -526,7 +597,8 @@ int event__process_mmap(event_t *self, struct perf_session *session)
 	return 0;
 }
 
-int event__process_task(event_t *self, struct perf_session *session)
+int event__process_task(event_t *self, struct sample_data *sample __used,
+			struct perf_session *session)
 {
 	struct thread *thread = perf_session__findnew(session, self->fork.tid);
 	struct thread *parent = perf_session__findnew(session, self->fork.ptid);
@@ -548,18 +620,19 @@ int event__process_task(event_t *self, struct perf_session *session)
 	return 0;
 }
 
-int event__process(event_t *event, struct perf_session *session)
+int event__process(event_t *event, struct sample_data *sample,
+		   struct perf_session *session)
 {
 	switch (event->header.type) {
 	case PERF_RECORD_COMM:
-		event__process_comm(event, session);
+		event__process_comm(event, sample, session);
 		break;
 	case PERF_RECORD_MMAP:
-		event__process_mmap(event, session);
+		event__process_mmap(event, sample, session);
 		break;
 	case PERF_RECORD_FORK:
 	case PERF_RECORD_EXIT:
-		event__process_task(event, session);
+		event__process_task(event, sample, session);
 		break;
 	default:
 		break;
@@ -674,32 +747,8 @@ int event__preprocess_sample(const event_t *self, struct perf_session *session,
 			     symbol_filter_t filter)
 {
 	u8 cpumode = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-	struct thread *thread;
+	struct thread *thread = perf_session__findnew(session, self->ip.pid);
 
-	event__parse_sample(self, session->sample_type, data);
-
-	dump_printf("(IP, %d): %d/%d: %#Lx period: %Ld cpu:%d\n",
-		    self->header.misc, data->pid, data->tid, data->ip,
-		    data->period, data->cpu);
-
-	if (session->sample_type & PERF_SAMPLE_CALLCHAIN) {
-		unsigned int i;
-
-		dump_printf("... chain: nr:%Lu\n", data->callchain->nr);
-
-		if (!ip_callchain__valid(data->callchain, self)) {
-			pr_debug("call-chain problem with event, "
-				 "skipping it.\n");
-			goto out_filtered;
-		}
-
-		if (dump_trace) {
-			for (i = 0; i < data->callchain->nr; i++)
-				dump_printf("..... %2d: %016Lx\n",
-					    i, data->callchain->ips[i]);
-		}
-	}
-	thread = perf_session__findnew(session, self->ip.pid);
 	if (thread == NULL)
 		return -1;
 
@@ -766,9 +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 8e790dae7026..a95ab18575ce 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -135,12 +135,15 @@ void event__print_totals(void);
 
 struct perf_session;
 
-typedef int (*event__handler_t)(event_t *event, struct perf_session *session);
+typedef int (*event__handler_synth_t)(event_t *event, 
+				      struct perf_session *session);
+typedef int (*event__handler_t)(event_t *event, struct sample_data *sample,
+				struct perf_session *session);
 
 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,
@@ -150,17 +153,23 @@ int event__synthesize_modules(event__handler_t process,
 			      struct perf_session *session,
 			      struct machine *machine);
 
-int event__process_comm(event_t *self, struct perf_session *session);
-int event__process_lost(event_t *self, struct perf_session *session);
-int event__process_mmap(event_t *self, struct perf_session *session);
-int event__process_task(event_t *self, struct perf_session *session);
-int event__process(event_t *event, struct perf_session *session);
+int event__process_comm(event_t *self, struct sample_data *sample,
+			struct perf_session *session);
+int event__process_lost(event_t *self, struct sample_data *sample,
+			struct perf_session *session);
+int event__process_mmap(event_t *self, struct sample_data *sample,
+			struct perf_session *session);
+int event__process_task(event_t *self, struct sample_data *sample,
+			struct perf_session *session);
+int event__process(event_t *event, struct sample_data *sample,
+		   struct perf_session *session);
 
 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 f65d7dc127b6..76e949a59ea4 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)
 {
@@ -987,21 +1005,23 @@ int event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
 
 	ev = malloc(size);
 
+	if (ev == NULL)
+		return -ENOMEM;
+
 	ev->attr.attr = *attr;
 	memcpy(ev->attr.id, id, ids * sizeof(u64));
 
 	ev->attr.header.type = PERF_RECORD_HEADER_ATTR;
 	ev->attr.header.size = size;
 
-	err = process(ev, session);
+	err = process(ev, NULL, session);
 
 	free(ev);
 
 	return err;
 }
 
-int event__synthesize_attrs(struct perf_header *self,
-			    event__handler_t process,
+int event__synthesize_attrs(struct perf_header *self, event__handler_t process,
 			    struct perf_session *session)
 {
 	struct perf_header_attr	*attr;
@@ -1071,7 +1091,7 @@ int event__synthesize_event_type(u64 event_id, char *name,
 	ev.event_type.header.size = sizeof(ev.event_type) -
 		(sizeof(ev.event_type.event_type.name) - size);
 
-	err = process(&ev, session);
+	err = process(&ev, NULL, session);
 
 	return err;
 }
@@ -1126,7 +1146,7 @@ int event__synthesize_tracing_data(int fd, struct perf_event_attr *pattrs,
 	ev.tracing_data.header.size = sizeof(ev.tracing_data);
 	ev.tracing_data.size = aligned_size;
 
-	process(&ev, session);
+	process(&ev, NULL, session);
 
 	err = read_tracing_data(fd, pattrs, nb_events);
 	write_padded(fd, NULL, 0, padding);
@@ -1186,7 +1206,7 @@ int event__synthesize_build_id(struct dso *pos, u16 misc,
 	ev.build_id.header.size = sizeof(ev.build_id) + len;
 	memcpy(&ev.build_id.filename, pos->long_name, pos->long_name_len);
 
-	err = process(&ev, session);
+	err = process(&ev, NULL, session);
 
 	return err;
 }
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/hist.h b/tools/perf/util/hist.h
index 587d375d3430..ee789856a8c9 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -52,8 +52,10 @@ struct sym_priv {
 struct events_stats {
 	u64 total_period;
 	u64 total_lost;
+	u64 total_invalid_chains;
 	u32 nr_events[PERF_RECORD_HEADER_MAX];
 	u32 nr_unknown_events;
+	u32 nr_invalid_chains;
 };
 
 enum hist_column {
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
index c7d72dce54b2..abc31a1dac1a 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/perf/util/parse-options.h
@@ -119,6 +119,10 @@ struct option {
 	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .flags = PARSE_OPT_NOARG }
 #define OPT_CALLBACK_DEFAULT(s, l, v, a, h, f, d) \
 	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d, .flags = PARSE_OPT_LASTARG_DEFAULT }
+#define OPT_CALLBACK_DEFAULT_NOOPT(s, l, v, a, h, f, d) \
+	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l),\
+	.value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\
+	.flags = PARSE_OPT_LASTARG_DEFAULT | PARSE_OPT_NOARG}
 
 /* parse_options() will filter out the processed options and leave the
  * non-option argments in argv[].
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 52672dad1fe9..3074d38897e6 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -65,9 +65,49 @@ static int perf_session__open(struct perf_session *self, bool force)
 	return -1;
 }
 
+static void perf_session__id_header_size(struct perf_session *session)
+{
+       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)
+{
+	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)
@@ -240,7 +280,15 @@ struct map_symbol *perf_session__resolve_callchain(struct perf_session *self,
 	return syms;
 }
 
+static int process_event_synth_stub(event_t *event __used,
+				    struct perf_session *session __used)
+{
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
 static int process_event_stub(event_t *event __used,
+			      struct sample_data *sample __used,
 			      struct perf_session *session __used)
 {
 	dump_printf(": unhandled!\n");
@@ -280,13 +328,13 @@ static void perf_event_ops__fill_defaults(struct perf_event_ops *handler)
 	if (handler->unthrottle == NULL)
 		handler->unthrottle = process_event_stub;
 	if (handler->attr == NULL)
-		handler->attr = process_event_stub;
+		handler->attr = process_event_synth_stub;
 	if (handler->event_type == NULL)
-		handler->event_type = process_event_stub;
+		handler->event_type = process_event_synth_stub;
 	if (handler->tracing_data == NULL)
-		handler->tracing_data = process_event_stub;
+		handler->tracing_data = process_event_synth_stub;
 	if (handler->build_id == NULL)
-		handler->build_id = process_event_stub;
+		handler->build_id = process_event_synth_stub;
 	if (handler->finished_round == NULL) {
 		if (handler->ordered_samples)
 			handler->finished_round = process_finished_round;
@@ -413,12 +461,18 @@ static void perf_session_free_sample_buffers(struct perf_session *session)
 	}
 }
 
+static int perf_session_deliver_event(struct perf_session *session,
+				      event_t *event,
+				      struct sample_data *sample,
+				      struct perf_event_ops *ops);
+
 static void flush_sample_queue(struct perf_session *s,
 			       struct perf_event_ops *ops)
 {
 	struct ordered_samples *os = &s->ordered_samples;
 	struct list_head *head = &os->samples;
 	struct sample_queue *tmp, *iter;
+	struct sample_data sample;
 	u64 limit = os->next_flush;
 	u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL;
 
@@ -429,7 +483,8 @@ static void flush_sample_queue(struct perf_session *s,
 		if (iter->timestamp > limit)
 			break;
 
-		ops->sample(iter->event, s);
+		event__parse_sample(iter->event, s, &sample);
+		perf_session_deliver_event(s, iter->event, &sample, ops);
 
 		os->last_flush = iter->timestamp;
 		list_del(&iter->list);
@@ -494,8 +549,7 @@ static int process_finished_round(event_t *event __used,
 }
 
 /* The queue is ordered by time */
-static void __queue_sample_event(struct sample_queue *new,
-				 struct perf_session *s)
+static void __queue_event(struct sample_queue *new, struct perf_session *s)
 {
 	struct ordered_samples *os = &s->ordered_samples;
 	struct sample_queue *sample = os->last_sample;
@@ -541,14 +595,17 @@ static void __queue_sample_event(struct sample_queue *new,
 
 #define MAX_SAMPLE_BUFFER	(64 * 1024 / sizeof(struct sample_queue))
 
-static int queue_sample_event(event_t *event, struct sample_data *data,
-			      struct perf_session *s)
+static int perf_session_queue_event(struct perf_session *s, event_t *event,
+				    struct sample_data *data)
 {
 	struct ordered_samples *os = &s->ordered_samples;
 	struct list_head *sc = &os->sample_cache;
 	u64 timestamp = data->time;
 	struct sample_queue *new;
 
+	if (!timestamp)
+		return -ETIME;
+
 	if (timestamp < s->ordered_samples.last_flush) {
 		printf("Warning: Timestamp below last timeslice flush\n");
 		return -EINVAL;
@@ -573,79 +630,142 @@ static int queue_sample_event(event_t *event, struct sample_data *data,
 	new->timestamp = timestamp;
 	new->event = event;
 
-	__queue_sample_event(new, s);
+	__queue_event(new, s);
 
 	return 0;
 }
 
-static int perf_session__process_sample(event_t *event, struct perf_session *s,
-					struct perf_event_ops *ops)
+static void callchain__dump(struct sample_data *sample)
 {
-	struct sample_data data;
+	unsigned int i;
 
-	if (!ops->ordered_samples)
-		return ops->sample(event, s);
+	if (!dump_trace)
+		return;
 
-	bzero(&data, sizeof(struct sample_data));
-	event__parse_sample(event, s->sample_type, &data);
+	printf("... chain: nr:%Lu\n", sample->callchain->nr);
 
-	queue_sample_event(event, &data, s);
-
-	return 0;
+	for (i = 0; i < sample->callchain->nr; i++)
+		printf("..... %2d: %016Lx\n", i, sample->callchain->ips[i]);
 }
 
-static int perf_session__process_event(struct perf_session *self,
+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_deliver_event(struct perf_session *session,
+				      event_t *event,
+				      struct sample_data *sample,
+				      struct perf_event_ops *ops)
+{
+	switch (event->header.type) {
+	case PERF_RECORD_SAMPLE:
+		return ops->sample(event, sample, session);
+	case PERF_RECORD_MMAP:
+		return ops->mmap(event, sample, session);
+	case PERF_RECORD_COMM:
+		return ops->comm(event, sample, session);
+	case PERF_RECORD_FORK:
+		return ops->fork(event, sample, session);
+	case PERF_RECORD_EXIT:
+		return ops->exit(event, sample, session);
+	case PERF_RECORD_LOST:
+		return ops->lost(event, sample, session);
+	case PERF_RECORD_READ:
+		return ops->read(event, sample, session);
+	case PERF_RECORD_THROTTLE:
+		return ops->throttle(event, sample, session);
+	case PERF_RECORD_UNTHROTTLE:
+		return ops->unthrottle(event, sample, session);
+	default:
+		++session->hists.stats.nr_unknown_events;
+		return -1;
+	}
+}
+
+static int perf_session__process_event(struct perf_session *session,
 				       event_t *event,
 				       struct perf_event_ops *ops,
 				       u64 file_offset)
 {
+	struct sample_data sample;
+	int ret;
+
 	trace_event(event);
 
+	if (session->header.needs_swap && event__swap_ops[event->header.type])
+		event__swap_ops[event->header.type](event);
+
+	if (event->header.type >= PERF_RECORD_MMAP &&
+	    event->header.type <= PERF_RECORD_SAMPLE) {
+		event__parse_sample(event, session, &sample);
+		if (dump_trace)
+			perf_session__print_tstamp(session, event, &sample);
+	}
+
 	if (event->header.type < PERF_RECORD_HEADER_MAX) {
 		dump_printf("%#Lx [%#x]: PERF_RECORD_%s",
 			    file_offset, event->header.size,
 			    event__name[event->header.type]);
-		hists__inc_nr_events(&self->hists, event->header.type);
+		hists__inc_nr_events(&session->hists, event->header.type);
 	}
 
-	if (self->header.needs_swap && event__swap_ops[event->header.type])
-		event__swap_ops[event->header.type](event);
-
+	/* These events are processed right away */
 	switch (event->header.type) {
 	case PERF_RECORD_SAMPLE:
-		return perf_session__process_sample(event, self, ops);
-	case PERF_RECORD_MMAP:
-		return ops->mmap(event, self);
-	case PERF_RECORD_COMM:
-		return ops->comm(event, self);
-	case PERF_RECORD_FORK:
-		return ops->fork(event, self);
-	case PERF_RECORD_EXIT:
-		return ops->exit(event, self);
-	case PERF_RECORD_LOST:
-		return ops->lost(event, self);
-	case PERF_RECORD_READ:
-		return ops->read(event, self);
-	case PERF_RECORD_THROTTLE:
-		return ops->throttle(event, self);
-	case PERF_RECORD_UNTHROTTLE:
-		return ops->unthrottle(event, self);
+		dump_printf("(IP, %d): %d/%d: %#Lx period: %Ld\n",
+			    event->header.misc,
+			    sample.pid, sample.tid, sample.ip, sample.period);
+
+		if (session->sample_type & PERF_SAMPLE_CALLCHAIN) {
+			if (!ip_callchain__valid(sample.callchain, event)) {
+				pr_debug("call-chain problem with event, "
+					 "skipping it.\n");
+				++session->hists.stats.nr_invalid_chains;
+				session->hists.stats.total_invalid_chains +=
+					sample.period;
+				return 0;
+			}
+
+			callchain__dump(&sample);
+		}
+		break;
+
 	case PERF_RECORD_HEADER_ATTR:
-		return ops->attr(event, self);
+		return ops->attr(event, session);
 	case PERF_RECORD_HEADER_EVENT_TYPE:
-		return ops->event_type(event, self);
+		return ops->event_type(event, session);
 	case PERF_RECORD_HEADER_TRACING_DATA:
 		/* setup for reading amidst mmap */
-		lseek(self->fd, file_offset, SEEK_SET);
-		return ops->tracing_data(event, self);
+		lseek(session->fd, file_offset, SEEK_SET);
+		return ops->tracing_data(event, session);
 	case PERF_RECORD_HEADER_BUILD_ID:
-		return ops->build_id(event, self);
+		return ops->build_id(event, session);
 	case PERF_RECORD_FINISHED_ROUND:
-		return ops->finished_round(event, self, ops);
+		return ops->finished_round(event, session, ops);
 	default:
-		++self->hists.stats.nr_unknown_events;
-		return -1;
+		break;
 	}
+
+	if (ops->ordered_samples) {
+		ret = perf_session_queue_event(session, event, &sample);
+		if (ret != -ETIME)
+			return ret;
+	}
+
+	return perf_session_deliver_event(session, event, &sample, ops);
 }
 
 void perf_event_header__bswap(struct perf_event_header *self)
@@ -894,6 +1014,14 @@ int __perf_session__process_events(struct perf_session *session,
 			    session->hists.stats.nr_unknown_events);
 	}
 
+ 	if (session->hists.stats.nr_invalid_chains != 0) {
+ 		ui__warning("Found invalid callchains!\n\n"
+ 			    "%u out of %u events were discarded for this reason.\n\n"
+ 			    "Consider reporting to linux-kernel@vger.kernel.org.\n\n",
+ 			    session->hists.stats.nr_invalid_chains,
+ 			    session->hists.stats.nr_events[PERF_RECORD_SAMPLE]);
+ 	}
+
 	perf_session_free_sample_buffers(session);
 	return err;
 }
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 5bf6efa3788a..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;
@@ -54,7 +56,9 @@ struct perf_session {
 
 struct perf_event_ops;
 
-typedef int (*event_op)(event_t *self, struct perf_session *session);
+typedef int (*event_op)(event_t *self, struct sample_data *sample,
+			struct perf_session *session);
+typedef int (*event_synth_op)(event_t *self, struct perf_session *session);
 typedef int (*event_op2)(event_t *self, struct perf_session *session,
 			 struct perf_event_ops *ops);
 
@@ -67,8 +71,8 @@ struct perf_event_ops {
 			lost,
 			read,
 			throttle,
-			unthrottle,
-			attr,
+			unthrottle;
+	event_synth_op	attr,
 			event_type,
 			tracing_data,
 			build_id;
@@ -104,6 +108,8 @@ 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);
 
 static inline
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index b62a553cc67d..f44fa541d56e 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -170,7 +170,7 @@ static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf,
 		return repsep_snprintf(bf, size, "%-*s", width, dso_name);
 	}
 
-	return repsep_snprintf(bf, size, "%*Lx", width, self->ip);
+	return repsep_snprintf(bf, size, "%-*s", width, "[unknown]");
 }
 
 /* --sort symbol */
@@ -196,7 +196,7 @@ static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
 
 	if (verbose) {
 		char o = self->ms.map ? dso__symtab_origin(self->ms.map->dso) : '!';
-		ret += repsep_snprintf(bf, size, "%*Lx %c ",
+		ret += repsep_snprintf(bf, size, "%-#*llx %c ",
 				       BITS_PER_LONG / 4, self->ip, o);
 	}
 
@@ -205,7 +205,7 @@ static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
 		ret += repsep_snprintf(bf + ret, size - ret, "%s",
 				       self->ms.sym->name);
 	else
-		ret += repsep_snprintf(bf + ret, size - ret, "%*Lx",
+		ret += repsep_snprintf(bf + ret, size - ret, "%-#*llx",
 				       BITS_PER_LONG / 4, self->ip);
 
 	return ret;