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

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

 * Tidy up sample parsing validation, from Adrian Hunter.

 * Make events stream always parsable by adding a new sample_type bit:
   PERF_SAMPLE_IDENTIFIER, that when requested will be always aat a fixed
   position in all PERF_RECORD_ records, from Adrian Hunter.

 * Add a sample parsing test, from Adrian Hunter.

 * Add option to 'perf trace' to analyze events in a file versus live,
   so that one can do:

   [root@zoo ~]# perf record -a -e raw_syscalls:* sleep 1
   [ perf record: Woken up 0 times to write data ]
   [ perf record: Captured and wrote 25.150 MB perf.data (~1098836 samples) ]
   [root@zoo ~]# perf trace -i perf.data -e futex --duration 1
      17.799 ( 1.020 ms): 7127 futex(uaddr: 0x7fff3f6c6674, op: 393, val: 1, utime: 0x7fff3f6c6470, ua
     113.344 (95.429 ms): 7127 futex(uaddr: 0x7fff3f6c6674, op: 393, val: 1, utime: 0x7fff3f6c6470, uaddr2: 0x7fff3f6c6648, val3: 4294967
     133.778 ( 1.042 ms): 18004 futex(uaddr: 0x7fff3f6c6674, op: 393, val: 1, utime: 0x7fff3f6c6470, uaddr2: 0x7fff3f6c6648, val3: 429496
   [root@zoo ~]#

   From David Ahern.

 * Honor target pid / tid options in 'perf trace' when analyzing a file,
   from David Ahern.

 * Handle missing HUGEPAGE defines in the mmap beautifier in 'perf trace',
   from David Ahern.

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

33 files changed, 1193 insertions, 195 deletions

diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 62c25a25291c..42cb7b62ca59 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -134,8 +134,9 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_STACK_USER			= 1U << 13,
 	PERF_SAMPLE_WEIGHT			= 1U << 14,
 	PERF_SAMPLE_DATA_SRC			= 1U << 15,
+	PERF_SAMPLE_IDENTIFIER			= 1U << 16,
 
-	PERF_SAMPLE_MAX = 1U << 16,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 17,		/* non-ABI */
 };
 
 /*
@@ -492,12 +493,12 @@ 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.
+	 * (identity) an event took place (TID, TIME, ID, STREAM_ID, CPU,
+	 * IDENTIFIER) 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.
 	 *
 	 * struct sample_id {
 	 * 	{ u32			pid, tid; } && PERF_SAMPLE_TID
@@ -505,7 +506,12 @@ enum perf_event_type {
 	 * 	{ u64			id;       } && PERF_SAMPLE_ID
 	 * 	{ u64			stream_id;} && PERF_SAMPLE_STREAM_ID
 	 * 	{ u32			cpu, res; } && PERF_SAMPLE_CPU
+	 *	{ u64			id;	  } && PERF_SAMPLE_IDENTIFIER
 	 * } && perf_event_attr::sample_id_all
+	 *
+	 * Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID.  The
+	 * advantage of PERF_SAMPLE_IDENTIFIER is that its position is fixed
+	 * relative to header.size.
 	 */
 
 	/*
@@ -594,6 +600,13 @@ enum perf_event_type {
 	 * struct {
 	 *	struct perf_event_header	header;
 	 *
+	 *	#
+	 *	# Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID.
+	 *	# The advantage of PERF_SAMPLE_IDENTIFIER is that its position
+	 *	# is fixed relative to header.
+	 *	#
+	 *
+	 *	{ u64			id;	  } && PERF_SAMPLE_IDENTIFIER
 	 *	{ u64			ip;	  } && PERF_SAMPLE_IP
 	 *	{ u32			pid, tid; } && PERF_SAMPLE_TID
 	 *	{ u64			time;     } && PERF_SAMPLE_TIME
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 928fae7ca8c7..15d0f2418e54 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1213,6 +1213,9 @@ static void perf_event__id_header_size(struct perf_event *event)
 	if (sample_type & PERF_SAMPLE_TIME)
 		size += sizeof(data->time);
 
+	if (sample_type & PERF_SAMPLE_IDENTIFIER)
+		size += sizeof(data->id);
+
 	if (sample_type & PERF_SAMPLE_ID)
 		size += sizeof(data->id);
 
@@ -4280,7 +4283,7 @@ static void __perf_event_header__init_id(struct perf_event_header *header,
 	if (sample_type & PERF_SAMPLE_TIME)
 		data->time = perf_clock();
 
-	if (sample_type & PERF_SAMPLE_ID)
+	if (sample_type & (PERF_SAMPLE_ID | PERF_SAMPLE_IDENTIFIER))
 		data->id = primary_event_id(event);
 
 	if (sample_type & PERF_SAMPLE_STREAM_ID)
@@ -4319,6 +4322,9 @@ static void __perf_event__output_id_sample(struct perf_output_handle *handle,
 
 	if (sample_type & PERF_SAMPLE_CPU)
 		perf_output_put(handle, data->cpu_entry);
+
+	if (sample_type & PERF_SAMPLE_IDENTIFIER)
+		perf_output_put(handle, data->id);
 }
 
 void perf_event__output_id_sample(struct perf_event *event,
@@ -4432,6 +4438,9 @@ void perf_output_sample(struct perf_output_handle *handle,
 
 	perf_output_put(handle, *header);
 
+	if (sample_type & PERF_SAMPLE_IDENTIFIER)
+		perf_output_put(handle, data->id);
+
 	if (sample_type & PERF_SAMPLE_IP)
 		perf_output_put(handle, data->ip);
 
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index fe19811faf90..daccd2c0a48f 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -74,6 +74,10 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 --sched:
 	Accrue thread runtime and provide a summary at the end of the session.
 
+-i
+--input
+	Process events from a given perf data file.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script[1]
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 7d30a7ddcc88..ecebfd00295e 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -360,6 +360,7 @@ LIB_OBJS += $(OUTPUT)util/rblist.o
 LIB_OBJS += $(OUTPUT)util/intlist.o
 LIB_OBJS += $(OUTPUT)util/vdso.o
 LIB_OBJS += $(OUTPUT)util/stat.o
+LIB_OBJS += $(OUTPUT)util/record.o
 
 LIB_OBJS += $(OUTPUT)ui/setup.o
 LIB_OBJS += $(OUTPUT)ui/helpline.o
@@ -438,6 +439,7 @@ PERFLIBS = $(LIB_FILE) $(LIBLK) $(LIBTRACEEVENT)
 ifneq ($(OUTPUT),)
   CFLAGS += -I$(OUTPUT)
 endif
+LIB_OBJS += $(OUTPUT)tests/sample-parsing.o
 
 ifdef NO_LIBELF
 EXTLIBS := $(filter-out -lelf,$(EXTLIBS))
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 1d8de2e4a407..9b336fdb6f71 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -198,7 +198,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool,
 
 	cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
-	thread = machine__findnew_thread(machine, event->ip.pid);
+	thread = machine__findnew_thread(machine, sample->pid, sample->pid);
 	if (thread == NULL) {
 		pr_err("problem processing %d event, skipping it.\n",
 		       event->header.type);
@@ -206,7 +206,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool,
 	}
 
 	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-			      event->ip.ip, &al);
+			      sample->ip, &al);
 
 	if (al.map != NULL) {
 		if (!al.map->dso->hit) {
@@ -301,7 +301,9 @@ found:
 	sample_sw.period = sample->period;
 	sample_sw.time	 = sample->time;
 	perf_event__synthesize_sample(event_sw, evsel->attr.sample_type,
-				      &sample_sw, false);
+				      evsel->attr.sample_regs_user,
+				      evsel->attr.read_format, &sample_sw,
+				      false);
 	build_id__mark_dso_hit(tool, event_sw, &sample_sw, evsel, machine);
 	return perf_event__repipe(tool, event_sw, &sample_sw, machine);
 }
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index b49f5c58e152..c2dff9cb1f2c 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -305,7 +305,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				struct perf_evsel *evsel,
 				struct machine *machine)
 {
-	struct thread *thread = machine__findnew_thread(machine, event->ip.pid);
+	struct thread *thread = machine__findnew_thread(machine, sample->pid,
+							sample->pid);
 
 	if (thread == NULL) {
 		pr_debug("problem processing %d event, skipping it.\n",
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 6cd4de59be21..47b35407c2f2 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -815,7 +815,7 @@ static int process_sample_event(struct perf_tool *tool,
 	if (skip_sample(kvm, sample))
 		return 0;
 
-	thread = machine__findnew_thread(machine, sample->tid);
+	thread = machine__findnew_thread(machine, sample->pid, sample->tid);
 	if (thread == NULL) {
 		pr_debug("problem processing %d event, skipping it.\n",
 			event->header.type);
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 76543a4a7a30..ee33ba2f05dd 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -805,7 +805,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				struct perf_evsel *evsel,
 				struct machine *machine)
 {
-	struct thread *thread = machine__findnew_thread(machine, sample->tid);
+	struct thread *thread = machine__findnew_thread(machine, sample->pid,
+							sample->tid);
 
 	if (thread == NULL) {
 		pr_debug("problem processing %d event, skipping it.\n",
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 706a1faa9559..791b432df847 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -94,7 +94,7 @@ dump_raw_samples(struct perf_tool *tool,
 		symbol_conf.field_sep,
 		sample->tid,
 		symbol_conf.field_sep,
-		event->ip.ip,
+		sample->ip,
 		symbol_conf.field_sep,
 		sample->addr,
 		symbol_conf.field_sep,
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 958a56a0e39e..9725aa375414 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -365,7 +365,7 @@ static int process_read_event(struct perf_tool *tool,
 static int perf_report__setup_sample_type(struct perf_report *rep)
 {
 	struct perf_session *self = rep->session;
-	u64 sample_type = perf_evlist__sample_type(self->evlist);
+	u64 sample_type = perf_evlist__combined_sample_type(self->evlist);
 
 	if (!self->fd_pipe && !(sample_type & PERF_SAMPLE_CALLCHAIN)) {
 		if (sort__has_parent) {
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index f809cc7fb7d9..d8c51b2f263f 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -724,8 +724,10 @@ static int replay_fork_event(struct perf_sched *sched,
 {
 	struct thread *child, *parent;
 
-	child = machine__findnew_thread(machine, event->fork.tid);
-	parent = machine__findnew_thread(machine, event->fork.ptid);
+	child = machine__findnew_thread(machine, event->fork.pid,
+					event->fork.tid);
+	parent = machine__findnew_thread(machine, event->fork.ppid,
+					 event->fork.ptid);
 
 	if (child == NULL || parent == NULL) {
 		pr_debug("thread does not exist on fork event: child %p, parent %p\n",
@@ -934,8 +936,8 @@ static int latency_switch_event(struct perf_sched *sched,
 		return -1;
 	}
 
-	sched_out = machine__findnew_thread(machine, prev_pid);
-	sched_in = machine__findnew_thread(machine, next_pid);
+	sched_out = machine__findnew_thread(machine, 0, prev_pid);
+	sched_in = machine__findnew_thread(machine, 0, next_pid);
 
 	out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid);
 	if (!out_events) {
@@ -978,7 +980,7 @@ static int latency_runtime_event(struct perf_sched *sched,
 {
 	const u32 pid	   = perf_evsel__intval(evsel, sample, "pid");
 	const u64 runtime  = perf_evsel__intval(evsel, sample, "runtime");
-	struct thread *thread = machine__findnew_thread(machine, pid);
+	struct thread *thread = machine__findnew_thread(machine, 0, pid);
 	struct work_atoms *atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid);
 	u64 timestamp = sample->time;
 	int cpu = sample->cpu;
@@ -1016,7 +1018,7 @@ static int latency_wakeup_event(struct perf_sched *sched,
 	if (!success)
 		return 0;
 
-	wakee = machine__findnew_thread(machine, pid);
+	wakee = machine__findnew_thread(machine, 0, pid);
 	atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid);
 	if (!atoms) {
 		if (thread_atoms_insert(sched, wakee))
@@ -1070,7 +1072,7 @@ static int latency_migrate_task_event(struct perf_sched *sched,
 	if (sched->profile_cpu == -1)
 		return 0;
 
-	migrant = machine__findnew_thread(machine, pid);
+	migrant = machine__findnew_thread(machine, 0, pid);
 	atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid);
 	if (!atoms) {
 		if (thread_atoms_insert(sched, migrant))
@@ -1289,8 +1291,8 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 		return -1;
 	}
 
-	sched_out = machine__findnew_thread(machine, prev_pid);
-	sched_in = machine__findnew_thread(machine, next_pid);
+	sched_out = machine__findnew_thread(machine, 0, prev_pid);
+	sched_in = machine__findnew_thread(machine, 0, next_pid);
 
 	sched->curr_thread[this_cpu] = sched_in;
 
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 2ad9d5b6fb3c..93a34cef9676 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -501,7 +501,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				struct machine *machine)
 {
 	struct addr_location al;
-	struct thread *thread = machine__findnew_thread(machine, event->ip.tid);
+	struct thread *thread = machine__findnew_thread(machine, sample->pid,
+							sample->tid);
 
 	if (thread == NULL) {
 		pr_debug("problem processing %d event, skipping it.\n",
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index e37521fc715a..212214162bb2 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -689,7 +689,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 {
 	struct perf_top *top = container_of(tool, struct perf_top, tool);
 	struct symbol *parent = NULL;
-	u64 ip = event->ip.ip;
+	u64 ip = sample->ip;
 	struct addr_location al;
 	int err;
 
@@ -699,10 +699,10 @@ static void perf_event__process_sample(struct perf_tool *tool,
 		if (!seen)
 			seen = intlist__new(NULL);
 
-		if (!intlist__has_entry(seen, event->ip.pid)) {
+		if (!intlist__has_entry(seen, sample->pid)) {
 			pr_err("Can't find guest [%d]'s kernel information\n",
-				event->ip.pid);
-			intlist__add(seen, event->ip.pid);
+				sample->pid);
+			intlist__add(seen, sample->pid);
 		}
 		return;
 	}
@@ -836,7 +836,8 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 			break;
 		case PERF_RECORD_MISC_GUEST_KERNEL:
 			++top->guest_kernel_samples;
-			machine = perf_session__find_machine(session, event->ip.pid);
+			machine = perf_session__find_machine(session,
+							     sample.pid);
 			break;
 		case PERF_RECORD_MISC_GUEST_USER:
 			++top->guest_us_samples;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index b72afc73f9a7..69a065e51135 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -4,9 +4,11 @@
 #include "util/debug.h"
 #include "util/evlist.h"
 #include "util/machine.h"
+#include "util/session.h"
 #include "util/thread.h"
 #include "util/parse-options.h"
 #include "util/strlist.h"
+#include "util/intlist.h"
 #include "util/thread_map.h"
 
 #include <libaudit.h>
@@ -69,7 +71,9 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size, unsigned
 	P_MMAP_FLAG(FILE);
 	P_MMAP_FLAG(FIXED);
 	P_MMAP_FLAG(GROWSDOWN);
+#ifdef MAP_HUGETLB
 	P_MMAP_FLAG(HUGETLB);
+#endif
 	P_MMAP_FLAG(LOCKED);
 	P_MMAP_FLAG(NONBLOCK);
 	P_MMAP_FLAG(NORESERVE);
@@ -108,8 +112,12 @@ static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size, uns
 #endif
 	P_MADV_BHV(MERGEABLE);
 	P_MADV_BHV(UNMERGEABLE);
+#ifdef MADV_HUGEPAGE
 	P_MADV_BHV(HUGEPAGE);
+#endif
+#ifdef MADV_NOHUGEPAGE
 	P_MADV_BHV(NOHUGEPAGE);
+#endif
 #ifdef MADV_DONTDUMP
 	P_MADV_BHV(DONTDUMP);
 #endif
@@ -258,6 +266,8 @@ struct trace {
 	unsigned long		nr_events;
 	struct strlist		*ev_qualifier;
 	bool			not_ev_qualifier;
+	struct intlist		*tid_list;
+	struct intlist		*pid_list;
 	bool			sched;
 	bool			multiple_threads;
 	double			duration_filter;
@@ -521,7 +531,8 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 	if (sc->filtered)
 		return 0;
 
-	thread = machine__findnew_thread(&trace->host, sample->tid);
+	thread = machine__findnew_thread(&trace->host, sample->pid,
+					 sample->tid);
 	ttrace = thread__trace(thread, trace->output);
 	if (ttrace == NULL)
 		return -1;
@@ -572,7 +583,8 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 	if (sc->filtered)
 		return 0;
 
-	thread = machine__findnew_thread(&trace->host, sample->tid);
+	thread = machine__findnew_thread(&trace->host, sample->pid,
+					 sample->tid);
 	ttrace = thread__trace(thread, trace->output);
 	if (ttrace == NULL)
 		return -1;
@@ -628,7 +640,9 @@ static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evs
 {
         u64 runtime = perf_evsel__intval(evsel, sample, "runtime");
 	double runtime_ms = (double)runtime / NSEC_PER_MSEC;
-	struct thread *thread = machine__findnew_thread(&trace->host, sample->tid);
+	struct thread *thread = machine__findnew_thread(&trace->host,
+							sample->pid,
+							sample->tid);
 	struct thread_trace *ttrace = thread__trace(thread, trace->output);
 
 	if (ttrace == NULL)
@@ -648,6 +662,72 @@ out_dump:
 	return 0;
 }
 
+static bool skip_sample(struct trace *trace, struct perf_sample *sample)
+{
+	if ((trace->pid_list && intlist__find(trace->pid_list, sample->pid)) ||
+	    (trace->tid_list && intlist__find(trace->tid_list, sample->tid)))
+		return false;
+
+	if (trace->pid_list || trace->tid_list)
+		return true;
+
+	return false;
+}
+
+static int trace__process_sample(struct perf_tool *tool,
+				 union perf_event *event __maybe_unused,
+				 struct perf_sample *sample,
+				 struct perf_evsel *evsel,
+				 struct machine *machine __maybe_unused)
+{
+	struct trace *trace = container_of(tool, struct trace, tool);
+	int err = 0;
+
+	tracepoint_handler handler = evsel->handler.func;
+
+	if (skip_sample(trace, sample))
+		return 0;
+
+	if (trace->base_time == 0)
+		trace->base_time = sample->time;
+
+	if (handler)
+		handler(trace, evsel, sample);
+
+	return err;
+}
+
+static bool
+perf_session__has_tp(struct perf_session *session, const char *name)
+{
+	struct perf_evsel *evsel;
+
+	evsel = perf_evlist__find_tracepoint_by_name(session->evlist, name);
+
+	return evsel != NULL;
+}
+
+static int parse_target_str(struct trace *trace)
+{
+	if (trace->opts.target.pid) {
+		trace->pid_list = intlist__new(trace->opts.target.pid);
+		if (trace->pid_list == NULL) {
+			pr_err("Error parsing process id string\n");
+			return -EINVAL;
+		}
+	}
+
+	if (trace->opts.target.tid) {
+		trace->tid_list = intlist__new(trace->opts.target.tid);
+		if (trace->tid_list == NULL) {
+			pr_err("Error parsing thread id string\n");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
 static int trace__run(struct trace *trace, int argc, const char **argv)
 {
 	struct perf_evlist *evlist = perf_evlist__new();
@@ -787,6 +867,69 @@ out:
 	return err;
 }
 
+static int trace__replay(struct trace *trace)
+{
+	const struct perf_evsel_str_handler handlers[] = {
+		{ "raw_syscalls:sys_enter",  trace__sys_enter, },
+		{ "raw_syscalls:sys_exit",   trace__sys_exit, },
+	};
+
+	struct perf_session *session;
+	int err = -1;
+
+	trace->tool.sample	  = trace__process_sample;
+	trace->tool.mmap	  = perf_event__process_mmap;
+	trace->tool.comm	  = perf_event__process_comm;
+	trace->tool.exit	  = perf_event__process_exit;
+	trace->tool.fork	  = perf_event__process_fork;
+	trace->tool.attr	  = perf_event__process_attr;
+	trace->tool.tracing_data = perf_event__process_tracing_data;
+	trace->tool.build_id	  = perf_event__process_build_id;
+
+	trace->tool.ordered_samples = true;
+	trace->tool.ordering_requires_timestamps = true;
+
+	/* add tid to output */
+	trace->multiple_threads = true;
+
+	if (symbol__init() < 0)
+		return -1;
+
+	session = perf_session__new(input_name, O_RDONLY, 0, false,
+				    &trace->tool);
+	if (session == NULL)
+		return -ENOMEM;
+
+	err = perf_session__set_tracepoints_handlers(session, handlers);
+	if (err)
+		goto out;
+
+	if (!perf_session__has_tp(session, "raw_syscalls:sys_enter")) {
+		pr_err("Data file does not have raw_syscalls:sys_enter events\n");
+		goto out;
+	}
+
+	if (!perf_session__has_tp(session, "raw_syscalls:sys_exit")) {
+		pr_err("Data file does not have raw_syscalls:sys_exit events\n");
+		goto out;
+	}
+
+	err = parse_target_str(trace);
+	if (err != 0)
+		goto out;
+
+	setup_pager();
+
+	err = perf_session__process_events(session, &trace->tool);
+	if (err)
+		pr_err("Failed to process events, error %d", err);
+
+out:
+	perf_session__delete(session);
+
+	return err;
+}
+
 static size_t trace__fprintf_threads_header(FILE *fp)
 {
 	size_t printed;
@@ -888,6 +1031,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_STRING('e', "expr", &ev_qualifier_str, "expr",
 		    "list of events to trace"),
 	OPT_STRING('o', "output", &output_name, "file", "output file name"),
+	OPT_STRING('i', "input", &input_name, "file", "Analyze events in file"),
 	OPT_STRING('p', "pid", &trace.opts.target.pid, "pid",
 		    "trace events on existing process id"),
 	OPT_STRING('t', "tid", &trace.opts.target.tid, "tid",
@@ -896,7 +1040,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "system-wide collection from all CPUs"),
 	OPT_STRING('C', "cpu", &trace.opts.target.cpu_list, "cpu",
 		    "list of cpus to monitor"),
-	OPT_BOOLEAN('i', "no-inherit", &trace.opts.no_inherit,
+	OPT_BOOLEAN(0, "no-inherit", &trace.opts.no_inherit,
 		    "child tasks do not inherit counters"),
 	OPT_UINTEGER('m', "mmap-pages", &trace.opts.mmap_pages,
 		     "number of mmap data pages"),
@@ -954,7 +1098,10 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (!argc && perf_target__none(&trace.opts.target))
 		trace.opts.target.system_wide = true;
 
-	err = trace__run(&trace, argc, argv);
+	if (input_name)
+		err = trace__replay(&trace);
+	else
+		err = trace__run(&trace, argc, argv);
 
 	if (trace.sched && !err)
 		trace__fprintf_thread_summary(&trace, trace.output);
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index f5af19244a05..8ad9415dd847 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -104,6 +104,10 @@ static struct test {
 		.func = test__code_reading,
 	},
 	{
+		.desc = "Test sample parsing",
+		.func = test__sample_parsing,
+	},
+	{
 		.func = NULL,
 	},
 };
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index df9afd9cab4c..6fb781d5586c 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -257,7 +257,7 @@ static int process_sample_event(struct machine *machine,
 		return -1;
 	}
 
-	thread = machine__findnew_thread(machine, sample.pid);
+	thread = machine__findnew_thread(machine, sample.pid, sample.pid);
 	if (!thread) {
 		pr_debug("machine__findnew_thread failed\n");
 		return -1;
@@ -446,7 +446,7 @@ static int do_test_code_reading(bool try_kcore)
 		goto out_err;
 	}
 
-	thread = machine__findnew_thread(machine, pid);
+	thread = machine__findnew_thread(machine, pid, pid);
 	if (!thread) {
 		pr_debug("machine__findnew_thread failed\n");
 		goto out_err;
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 50bfb01183ea..4228ffc0d968 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -88,7 +88,8 @@ static struct machine *setup_fake_machine(struct machines *machines)
 	for (i = 0; i < ARRAY_SIZE(fake_threads); i++) {
 		struct thread *thread;
 
-		thread = machine__findnew_thread(machine, fake_threads[i].pid);
+		thread = machine__findnew_thread(machine, fake_threads[i].pid,
+						 fake_threads[i].pid);
 		if (thread == NULL)
 			goto out;
 
@@ -210,15 +211,13 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 	list_for_each_entry(evsel, &evlist->entries, node) {
 		for (k = 0; k < ARRAY_SIZE(fake_common_samples); k++) {
 			const union perf_event event = {
-				.ip = {
-					.header = {
-						.misc = PERF_RECORD_MISC_USER,
-					},
-					.pid = fake_common_samples[k].pid,
-					.ip  = fake_common_samples[k].ip,
+				.header = {
+					.misc = PERF_RECORD_MISC_USER,
 				},
 			};
 
+			sample.pid = fake_common_samples[k].pid;
+			sample.ip = fake_common_samples[k].ip;
 			if (perf_event__preprocess_sample(&event, machine, &al,
 							  &sample) < 0)
 				goto out;
@@ -234,15 +233,13 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 
 		for (k = 0; k < ARRAY_SIZE(fake_samples[i]); k++) {
 			const union perf_event event = {
-				.ip = {
-					.header = {
-						.misc = PERF_RECORD_MISC_USER,
-					},
-					.pid = fake_samples[i][k].pid,
-					.ip  = fake_samples[i][k].ip,
+				.header = {
+					.misc = PERF_RECORD_MISC_USER,
 				},
 			};
 
+			sample.pid = fake_samples[i][k].pid;
+			sample.ip = fake_samples[i][k].ip;
 			if (perf_event__preprocess_sample(&event, machine, &al,
 							  &sample) < 0)
 				goto out;
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 5b1b5aba722b..c4185b9aeb80 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -72,7 +72,7 @@ int test__basic_mmap(void)
 		}
 
 		evsels[i]->attr.wakeup_events = 1;
-		perf_evsel__set_sample_id(evsels[i]);
+		perf_evsel__set_sample_id(evsels[i], false);
 
 		perf_evlist__add(evlist, evsels[i]);
 
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
new file mode 100644
index 000000000000..77f598dbd97a
--- /dev/null
+++ b/tools/perf/tests/sample-parsing.c
@@ -0,0 +1,316 @@
+#include <stdbool.h>
+#include <inttypes.h>
+
+#include "util.h"
+#include "event.h"
+#include "evsel.h"
+
+#include "tests.h"
+
+#define COMP(m) do {					\
+	if (s1->m != s2->m) {				\
+		pr_debug("Samples differ at '"#m"'\n");	\
+		return false;				\
+	}						\
+} while (0)
+
+#define MCOMP(m) do {					\
+	if (memcmp(&s1->m, &s2->m, sizeof(s1->m))) {	\
+		pr_debug("Samples differ at '"#m"'\n");	\
+		return false;				\
+	}						\
+} while (0)
+
+static bool samples_same(const struct perf_sample *s1,
+			 const struct perf_sample *s2, u64 type, u64 regs_user,
+			 u64 read_format)
+{
+	size_t i;
+
+	if (type & PERF_SAMPLE_IDENTIFIER)
+		COMP(id);
+
+	if (type & PERF_SAMPLE_IP)
+		COMP(ip);
+
+	if (type & PERF_SAMPLE_TID) {
+		COMP(pid);
+		COMP(tid);
+	}
+
+	if (type & PERF_SAMPLE_TIME)
+		COMP(time);
+
+	if (type & PERF_SAMPLE_ADDR)
+		COMP(addr);
+
+	if (type & PERF_SAMPLE_ID)
+		COMP(id);
+
+	if (type & PERF_SAMPLE_STREAM_ID)
+		COMP(stream_id);
+
+	if (type & PERF_SAMPLE_CPU)
+		COMP(cpu);
+
+	if (type & PERF_SAMPLE_PERIOD)
+		COMP(period);
+
+	if (type & PERF_SAMPLE_READ) {
+		if (read_format & PERF_FORMAT_GROUP)
+			COMP(read.group.nr);
+		else
+			COMP(read.one.value);
+		if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+			COMP(read.time_enabled);
+		if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+			COMP(read.time_running);
+		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
+		if (read_format & PERF_FORMAT_GROUP) {
+			for (i = 0; i < s1->read.group.nr; i++)
+				MCOMP(read.group.values[i]);
+		} else {
+			COMP(read.one.id);
+		}
+	}
+
+	if (type & PERF_SAMPLE_CALLCHAIN) {
+		COMP(callchain->nr);
+		for (i = 0; i < s1->callchain->nr; i++)
+			COMP(callchain->ips[i]);
+	}
+
+	if (type & PERF_SAMPLE_RAW) {
+		COMP(raw_size);
+		if (memcmp(s1->raw_data, s2->raw_data, s1->raw_size)) {
+			pr_debug("Samples differ at 'raw_data'\n");
+			return false;
+		}
+	}
+
+	if (type & PERF_SAMPLE_BRANCH_STACK) {
+		COMP(branch_stack->nr);
+		for (i = 0; i < s1->branch_stack->nr; i++)
+			MCOMP(branch_stack->entries[i]);
+	}
+
+	if (type & PERF_SAMPLE_REGS_USER) {
+		size_t sz = hweight_long(regs_user) * sizeof(u64);
+
+		COMP(user_regs.abi);
+		if (s1->user_regs.abi &&
+		    (!s1->user_regs.regs || !s2->user_regs.regs ||
+		     memcmp(s1->user_regs.regs, s2->user_regs.regs, sz))) {
+			pr_debug("Samples differ at 'user_regs'\n");
+			return false;
+		}
+	}
+
+	if (type & PERF_SAMPLE_STACK_USER) {
+		COMP(user_stack.size);
+		if (memcmp(s1->user_stack.data, s1->user_stack.data,
+			   s1->user_stack.size)) {
+			pr_debug("Samples differ at 'user_stack'\n");
+			return false;
+		}
+	}
+
+	if (type & PERF_SAMPLE_WEIGHT)
+		COMP(weight);
+
+	if (type & PERF_SAMPLE_DATA_SRC)
+		COMP(data_src);
+
+	return true;
+}
+
+static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format)
+{
+	struct perf_evsel evsel = {
+		.needs_swap = false,
+		.attr = {
+			.sample_type = sample_type,
+			.sample_regs_user = sample_regs_user,
+			.read_format = read_format,
+		},
+	};
+	union perf_event *event;
+	union {
+		struct ip_callchain callchain;
+		u64 data[64];
+	} callchain = {
+		/* 3 ips */
+		.data = {3, 201, 202, 203},
+	};
+	union {
+		struct branch_stack branch_stack;
+		u64 data[64];
+	} branch_stack = {
+		/* 1 branch_entry */
+		.data = {1, 211, 212, 213},
+	};
+	u64 user_regs[64];
+	const u64 raw_data[] = {0x123456780a0b0c0dULL, 0x1102030405060708ULL};
+	const u64 data[] = {0x2211443366558877ULL, 0, 0xaabbccddeeff4321ULL};
+	struct perf_sample sample = {
+		.ip		= 101,
+		.pid		= 102,
+		.tid		= 103,
+		.time		= 104,
+		.addr		= 105,
+		.id		= 106,
+		.stream_id	= 107,
+		.period		= 108,
+		.weight		= 109,
+		.cpu		= 110,
+		.raw_size	= sizeof(raw_data),
+		.data_src	= 111,
+		.raw_data	= (void *)raw_data,
+		.callchain	= &callchain.callchain,
+		.branch_stack	= &branch_stack.branch_stack,
+		.user_regs	= {
+			.abi	= PERF_SAMPLE_REGS_ABI_64,
+			.regs	= user_regs,
+		},
+		.user_stack	= {
+			.size	= sizeof(data),
+			.data	= (void *)data,
+		},
+		.read		= {
+			.time_enabled = 0x030a59d664fca7deULL,
+			.time_running = 0x011b6ae553eb98edULL,
+		},
+	};
+	struct sample_read_value values[] = {{1, 5}, {9, 3}, {2, 7}, {6, 4},};
+	struct perf_sample sample_out;
+	size_t i, sz, bufsz;
+	int err, ret = -1;
+
+	for (i = 0; i < sizeof(user_regs); i++)
+		*(i + (u8 *)user_regs) = i & 0xfe;
+
+	if (read_format & PERF_FORMAT_GROUP) {
+		sample.read.group.nr     = 4;
+		sample.read.group.values = values;
+	} else {
+		sample.read.one.value = 0x08789faeb786aa87ULL;
+		sample.read.one.id    = 99;
+	}
+
+	sz = perf_event__sample_event_size(&sample, sample_type,
+					   sample_regs_user, read_format);
+	bufsz = sz + 4096; /* Add a bit for overrun checking */
+	event = malloc(bufsz);
+	if (!event) {
+		pr_debug("malloc failed\n");
+		return -1;
+	}
+
+	memset(event, 0xff, bufsz);
+	event->header.type = PERF_RECORD_SAMPLE;
+	event->header.misc = 0;
+	event->header.size = sz;
+
+	err = perf_event__synthesize_sample(event, sample_type,
+					    sample_regs_user, read_format,
+					    &sample, false);
+	if (err) {
+		pr_debug("%s failed for sample_type %#"PRIx64", error %d\n",
+			 "perf_event__synthesize_sample", sample_type, err);
+		goto out_free;
+	}
+
+	/* The data does not contain 0xff so we use that to check the size */
+	for (i = bufsz; i > 0; i--) {
+		if (*(i - 1 + (u8 *)event) != 0xff)
+			break;
+	}
+	if (i != sz) {
+		pr_debug("Event size mismatch: actual %zu vs expected %zu\n",
+			 i, sz);
+		goto out_free;
+	}
+
+	evsel.sample_size = __perf_evsel__sample_size(sample_type);
+
+	err = perf_evsel__parse_sample(&evsel, event, &sample_out);
+	if (err) {
+		pr_debug("%s failed for sample_type %#"PRIx64", error %d\n",
+			 "perf_evsel__parse_sample", sample_type, err);
+		goto out_free;
+	}
+
+	if (!samples_same(&sample, &sample_out, sample_type,
+			  sample_regs_user, read_format)) {
+		pr_debug("parsing failed for sample_type %#"PRIx64"\n",
+			 sample_type);
+		goto out_free;
+	}
+
+	ret = 0;
+out_free:
+	free(event);
+	if (ret && read_format)
+		pr_debug("read_format %#"PRIx64"\n", read_format);
+	return ret;
+}
+
+/**
+ * test__sample_parsing - test sample parsing.
+ *
+ * This function implements a test that synthesizes a sample event, parses it
+ * and then checks that the parsed sample matches the original sample.  The test
+ * checks sample format bits separately and together.  If the test passes %0 is
+ * returned, otherwise %-1 is returned.
+ */
+int test__sample_parsing(void)
+{
+	const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15};
+	u64 sample_type;
+	u64 sample_regs_user;
+	size_t i;
+	int err;
+
+	/*
+	 * Fail the test if it has not been updated when new sample format bits
+	 * were added.
+	 */
+	if (PERF_SAMPLE_MAX > PERF_SAMPLE_IDENTIFIER << 1) {
+		pr_debug("sample format has changed - test needs updating\n");
+		return -1;
+	}
+
+	/* Test each sample format bit separately */
+	for (sample_type = 1; sample_type != PERF_SAMPLE_MAX;
+	     sample_type <<= 1) {
+		/* Test read_format variations */
+		if (sample_type == PERF_SAMPLE_READ) {
+			for (i = 0; i < ARRAY_SIZE(rf); i++) {
+				err = do_test(sample_type, 0, rf[i]);
+				if (err)
+					return err;
+			}
+			continue;
+		}
+
+		if (sample_type == PERF_SAMPLE_REGS_USER)
+			sample_regs_user = 0x3fff;
+		else
+			sample_regs_user = 0;
+
+		err = do_test(sample_type, sample_regs_user, 0);
+		if (err)
+			return err;
+	}
+
+	/* Test all sample format bits together */
+	sample_type = PERF_SAMPLE_MAX - 1;
+	sample_regs_user = 0x3fff;
+	for (i = 0; i < ARRAY_SIZE(rf); i++) {
+		err = do_test(sample_type, sample_regs_user, rf[i]);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index c748f532b20f..83d5b71a3ce4 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -37,5 +37,6 @@ int test__task_exit(void);
 int test__sw_clock_freq(void);
 int test__perf_time_to_tsc(void);
 int test__code_reading(void);
+int test__sample_parsing(void);
 
 #endif /* TESTS_H */
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 5295625c0c00..fb584092eb88 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -18,13 +18,14 @@
 
 int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
 			   union perf_event *event,
-			   struct perf_sample *sample __maybe_unused,
+			   struct perf_sample *sample,
 			   struct perf_evsel *evsel __maybe_unused,
 			   struct machine *machine)
 {
 	struct addr_location al;
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-	struct thread *thread = machine__findnew_thread(machine, event->ip.pid);
+	struct thread *thread = machine__findnew_thread(machine, sample->pid,
+							sample->pid);
 
 	if (thread == NULL) {
 		pr_err("problem processing %d event, skipping it.\n",
@@ -33,7 +34,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
 	}
 
 	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-			      event->ip.ip, &al);
+			      sample->ip, &al);
 
 	if (al.map != NULL)
 		al.map->dso->hit = 1;
@@ -47,7 +48,9 @@ static int perf_event__exit_del_thread(struct perf_tool *tool __maybe_unused,
 				       __maybe_unused,
 				       struct machine *machine)
 {
-	struct thread *thread = machine__findnew_thread(machine, event->fork.tid);
+	struct thread *thread = machine__findnew_thread(machine,
+							event->fork.pid,
+							event->fork.tid);
 
 	dump_printf("(%d:%d):(%d:%d)\n", event->fork.pid, event->fork.tid,
 		    event->fork.ppid, event->fork.ptid);
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 4fee33b229b0..482f68081cd8 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -21,14 +21,6 @@
 
 __thread struct callchain_cursor callchain_cursor;
 
-bool ip_callchain__valid(struct ip_callchain *chain,
-			 const union perf_event *event)
-{
-	unsigned int chain_size = event->header.size;
-	chain_size -= (unsigned long)&event->ip.__more_data - (unsigned long)event;
-	return chain->nr * sizeof(u64) <= chain_size;
-}
-
 #define chain_for_each_child(child, parent)	\
 	list_for_each_entry(child, &parent->children, siblings)
 
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 812d5a0ff2bc..2b585bc308cf 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -109,11 +109,6 @@ int callchain_append(struct callchain_root *root,
 int callchain_merge(struct callchain_cursor *cursor,
 		    struct callchain_root *dst, struct callchain_root *src);
 
-struct ip_callchain;
-union perf_event;
-
-bool ip_callchain__valid(struct ip_callchain *chain,
-			 const union perf_event *event);
 /*
  * Initialize a cursor before adding entries inside, but keep
  * the previously allocated entries as a cache.
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 49713ae46551..8d51f21107aa 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -686,7 +686,8 @@ int perf_event__preprocess_sample(const union perf_event *event,
 				  struct perf_sample *sample)
 {
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-	struct thread *thread = machine__findnew_thread(machine, event->ip.pid);
+	struct thread *thread = machine__findnew_thread(machine, sample->pid,
+							sample->pid);
 
 	if (thread == NULL)
 		return -1;
@@ -708,7 +709,7 @@ int perf_event__preprocess_sample(const union perf_event *event,
 		machine__create_kernel_maps(machine);
 
 	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-			      event->ip.ip, al);
+			      sample->ip, al);
 	dump_printf(" ...... dso: %s\n",
 		    al->map ? al->map->dso->long_name :
 			al->level == 'H' ? "[hypervisor]" : "<not found>");
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 15db071d96b5..93130d856bf0 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -8,16 +8,6 @@
 #include "map.h"
 #include "build-id.h"
 
-/*
- * PERF_SAMPLE_IP | PERF_SAMPLE_TID | *
- */
-struct ip_event {
-	struct perf_event_header header;
-	u64 ip;
-	u32 pid, tid;
-	unsigned char __more_data[];
-};
-
 struct mmap_event {
 	struct perf_event_header header;
 	u32 pid, tid;
@@ -63,7 +53,8 @@ struct read_event {
 	(PERF_SAMPLE_IP | PERF_SAMPLE_TID |		\
 	 PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR |		\
 	PERF_SAMPLE_ID | PERF_SAMPLE_STREAM_ID |	\
-	 PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD)
+	 PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD |		\
+	 PERF_SAMPLE_IDENTIFIER)
 
 struct sample_event {
 	struct perf_event_header        header;
@@ -71,6 +62,7 @@ struct sample_event {
 };
 
 struct regs_dump {
+	u64 abi;
 	u64 *regs;
 };
 
@@ -166,7 +158,6 @@ struct tracing_data_event {
 
 union perf_event {
 	struct perf_event_header	header;
-	struct ip_event			ip;
 	struct mmap_event		mmap;
 	struct comm_event		comm;
 	struct fork_event		fork;
@@ -238,7 +229,10 @@ int perf_event__preprocess_sample(const union perf_event *self,
 
 const char *perf_event__name(unsigned int id);
 
+size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
+				     u64 sample_regs_user, u64 read_format);
 int perf_event__synthesize_sample(union perf_event *event, u64 type,
+				  u64 sample_regs_user, u64 read_format,
 				  const struct perf_sample *sample,
 				  bool swapped);
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 1f5105ac5c85..5df4ca91bed3 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -49,26 +49,19 @@ struct perf_evlist *perf_evlist__new(void)
 	return evlist;
 }
 
-void perf_evlist__config(struct perf_evlist *evlist,
-			struct perf_record_opts *opts)
+/**
+ * perf_evlist__set_id_pos - set the positions of event ids.
+ * @evlist: selected event list
+ *
+ * Events with compatible sample types all have the same id_pos
+ * and is_pos.  For convenience, put a copy on evlist.
+ */
+void perf_evlist__set_id_pos(struct perf_evlist *evlist)
 {
-	struct perf_evsel *evsel;
-	/*
-	 * Set the evsel leader links before we configure attributes,
-	 * since some might depend on this info.
-	 */
-	if (opts->group)
-		perf_evlist__set_leader(evlist);
-
-	if (evlist->cpus->map[0] < 0)
-		opts->no_inherit = true;
-
-	list_for_each_entry(evsel, &evlist->entries, node) {
-		perf_evsel__config(evsel, opts);
+	struct perf_evsel *first = perf_evlist__first(evlist);
 
-		if (evlist->nr_entries > 1)
-			perf_evsel__set_sample_id(evsel);
-	}
+	evlist->id_pos = first->id_pos;
+	evlist->is_pos = first->is_pos;
 }
 
 static void perf_evlist__purge(struct perf_evlist *evlist)
@@ -101,15 +94,20 @@ void perf_evlist__delete(struct perf_evlist *evlist)
 void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry)
 {
 	list_add_tail(&entry->node, &evlist->entries);
-	++evlist->nr_entries;
+	if (!evlist->nr_entries++)
+		perf_evlist__set_id_pos(evlist);
 }
 
 void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
 				   struct list_head *list,
 				   int nr_entries)
 {
+	bool set_id_pos = !evlist->nr_entries;
+
 	list_splice_tail(list, &evlist->entries);
 	evlist->nr_entries += nr_entries;
+	if (set_id_pos)
+		perf_evlist__set_id_pos(evlist);
 }
 
 void __perf_evlist__set_leader(struct list_head *list)
@@ -210,6 +208,21 @@ perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id)
 	return NULL;
 }
 
+struct perf_evsel *
+perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist,
+				     const char *name)
+{
+	struct perf_evsel *evsel;
+
+	list_for_each_entry(evsel, &evlist->entries, node) {
+		if ((evsel->attr.type == PERF_TYPE_TRACEPOINT) &&
+		    (strcmp(evsel->name, name) == 0))
+			return evsel;
+	}
+
+	return NULL;
+}
+
 int perf_evlist__add_newtp(struct perf_evlist *evlist,
 			   const char *sys, const char *name, void *handler)
 {
@@ -371,6 +384,55 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id)
 	return NULL;
 }
 
+static int perf_evlist__event2id(struct perf_evlist *evlist,
+				 union perf_event *event, u64 *id)
+{
+	const u64 *array = event->sample.array;
+	ssize_t n;
+
+	n = (event->header.size - sizeof(event->header)) >> 3;
+
+	if (event->header.type == PERF_RECORD_SAMPLE) {
+		if (evlist->id_pos >= n)
+			return -1;
+		*id = array[evlist->id_pos];
+	} else {
+		if (evlist->is_pos > n)
+			return -1;
+		n -= evlist->is_pos;
+		*id = array[n];
+	}
+	return 0;
+}
+
+static struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
+						   union perf_event *event)
+{
+	struct hlist_head *head;
+	struct perf_sample_id *sid;
+	int hash;
+	u64 id;
+
+	if (evlist->nr_entries == 1)
+		return perf_evlist__first(evlist);
+
+	if (perf_evlist__event2id(evlist, event, &id))
+		return NULL;
+
+	/* Synthesized events have an id of zero */
+	if (!id)
+		return perf_evlist__first(evlist);
+
+	hash = hash_64(id, PERF_EVLIST__HLIST_BITS);
+	head = &evlist->heads[hash];
+
+	hlist_for_each_entry(sid, head, node) {
+		if (sid->id == id)
+			return sid->evsel;
+	}
+	return NULL;
+}
+
 union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 {
 	struct perf_mmap *md = &evlist->mmap[idx];
@@ -681,20 +743,40 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter)
 
 bool perf_evlist__valid_sample_type(struct perf_evlist *evlist)
 {
-	struct perf_evsel *first = perf_evlist__first(evlist), *pos = first;
+	struct perf_evsel *pos;
 
-	list_for_each_entry_continue(pos, &evlist->entries, node) {
-		if (first->attr.sample_type != pos->attr.sample_type)
+	if (evlist->nr_entries == 1)
+		return true;
+
+	if (evlist->id_pos < 0 || evlist->is_pos < 0)
+		return false;
+
+	list_for_each_entry(pos, &evlist->entries, node) {
+		if (pos->id_pos != evlist->id_pos ||
+		    pos->is_pos != evlist->is_pos)
 			return false;
 	}
 
 	return true;
 }
 
-u64 perf_evlist__sample_type(struct perf_evlist *evlist)
+u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist)
 {
-	struct perf_evsel *first = perf_evlist__first(evlist);
-	return first->attr.sample_type;
+	struct perf_evsel *evsel;
+
+	if (evlist->combined_sample_type)
+		return evlist->combined_sample_type;
+
+	list_for_each_entry(evsel, &evlist->entries, node)
+		evlist->combined_sample_type |= evsel->attr.sample_type;
+
+	return evlist->combined_sample_type;
+}
+
+u64 perf_evlist__combined_sample_type(struct perf_evlist *evlist)
+{
+	evlist->combined_sample_type = 0;
+	return __perf_evlist__combined_sample_type(evlist);
 }
 
 bool perf_evlist__valid_read_format(struct perf_evlist *evlist)
@@ -749,6 +831,9 @@ u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist)
 
 	if (sample_type & PERF_SAMPLE_CPU)
 		size += sizeof(data->cpu) * 2;
+
+	if (sample_type & PERF_SAMPLE_IDENTIFIER)
+		size += sizeof(data->id);
 out:
 	return size;
 }
@@ -907,7 +992,10 @@ int perf_evlist__start_workload(struct perf_evlist *evlist)
 int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event,
 			      struct perf_sample *sample)
 {
-	struct perf_evsel *evsel = perf_evlist__first(evlist);
+	struct perf_evsel *evsel = perf_evlist__event2evsel(evlist, event);
+
+	if (!evsel)
+		return -EFAULT;
 	return perf_evsel__parse_sample(evsel, event, sample);
 }
 
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 327ababa67b6..841a39405f6a 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -32,6 +32,9 @@ struct perf_evlist {
 	int		 nr_fds;
 	int		 nr_mmaps;
 	int		 mmap_len;
+	int		 id_pos;
+	int		 is_pos;
+	u64		 combined_sample_type;
 	struct {
 		int	cork_fd;
 		pid_t	pid;
@@ -71,6 +74,10 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter);
 struct perf_evsel *
 perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id);
 
+struct perf_evsel *
+perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist,
+				     const char *name);
+
 void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
 			 int cpu, int thread, u64 id);
 
@@ -85,6 +92,8 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx);
 int perf_evlist__open(struct perf_evlist *evlist);
 void perf_evlist__close(struct perf_evlist *evlist);
 
+void perf_evlist__set_id_pos(struct perf_evlist *evlist);
+bool perf_can_sample_identifier(void);
 void perf_evlist__config(struct perf_evlist *evlist,
 			 struct perf_record_opts *opts);
 
@@ -121,7 +130,8 @@ void __perf_evlist__set_leader(struct list_head *list);
 void perf_evlist__set_leader(struct perf_evlist *evlist);
 
 u64 perf_evlist__read_format(struct perf_evlist *evlist);
-u64 perf_evlist__sample_type(struct perf_evlist *evlist);
+u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist);
+u64 perf_evlist__combined_sample_type(struct perf_evlist *evlist);
 bool perf_evlist__sample_id_all(struct perf_evlist *evlist);
 u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 47cbe1e58b73..e8745fb635a7 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -31,7 +31,7 @@ static struct {
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 
-static int __perf_evsel__sample_size(u64 sample_type)
+int __perf_evsel__sample_size(u64 sample_type)
 {
 	u64 mask = sample_type & PERF_SAMPLE_MASK;
 	int size = 0;
@@ -47,6 +47,72 @@ static int __perf_evsel__sample_size(u64 sample_type)
 	return size;
 }
 
+/**
+ * __perf_evsel__calc_id_pos - calculate id_pos.
+ * @sample_type: sample type
+ *
+ * This function returns the position of the event id (PERF_SAMPLE_ID or
+ * PERF_SAMPLE_IDENTIFIER) in a sample event i.e. in the array of struct
+ * sample_event.
+ */
+static int __perf_evsel__calc_id_pos(u64 sample_type)
+{
+	int idx = 0;
+
+	if (sample_type & PERF_SAMPLE_IDENTIFIER)
+		return 0;
+
+	if (!(sample_type & PERF_SAMPLE_ID))
+		return -1;
+
+	if (sample_type & PERF_SAMPLE_IP)
+		idx += 1;
+
+	if (sample_type & PERF_SAMPLE_TID)
+		idx += 1;
+
+	if (sample_type & PERF_SAMPLE_TIME)
+		idx += 1;
+
+	if (sample_type & PERF_SAMPLE_ADDR)
+		idx += 1;
+
+	return idx;
+}
+
+/**
+ * __perf_evsel__calc_is_pos - calculate is_pos.
+ * @sample_type: sample type
+ *
+ * This function returns the position (counting backwards) of the event id
+ * (PERF_SAMPLE_ID or PERF_SAMPLE_IDENTIFIER) in a non-sample event i.e. if
+ * sample_id_all is used there is an id sample appended to non-sample events.
+ */
+static int __perf_evsel__calc_is_pos(u64 sample_type)
+{
+	int idx = 1;
+
+	if (sample_type & PERF_SAMPLE_IDENTIFIER)
+		return 1;
+
+	if (!(sample_type & PERF_SAMPLE_ID))
+		return -1;
+
+	if (sample_type & PERF_SAMPLE_CPU)
+		idx += 1;
+
+	if (sample_type & PERF_SAMPLE_STREAM_ID)
+		idx += 1;
+
+	return idx;
+}
+
+void perf_evsel__calc_id_pos(struct perf_evsel *evsel)
+{
+	evsel->id_pos = __perf_evsel__calc_id_pos(evsel->attr.sample_type);
+	evsel->is_pos = __perf_evsel__calc_is_pos(evsel->attr.sample_type);
+}
+
 void hists__init(struct hists *hists)
 {
 	memset(hists, 0, sizeof(*hists));
@@ -63,6 +129,7 @@ void __perf_evsel__set_sample_bit(struct perf_evsel *evsel,
 	if (!(evsel->attr.sample_type & bit)) {
 		evsel->attr.sample_type |= bit;
 		evsel->sample_size += sizeof(u64);
+		perf_evsel__calc_id_pos(evsel);
 	}
 }
 
@@ -72,12 +139,19 @@ void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel,
 	if (evsel->attr.sample_type & bit) {
 		evsel->attr.sample_type &= ~bit;
 		evsel->sample_size -= sizeof(u64);
+		perf_evsel__calc_id_pos(evsel);
 	}
 }
 
-void perf_evsel__set_sample_id(struct perf_evsel *evsel)
+void perf_evsel__set_sample_id(struct perf_evsel *evsel,
+			       bool can_sample_identifier)
 {
-	perf_evsel__set_sample_bit(evsel, ID);
+	if (can_sample_identifier) {
+		perf_evsel__reset_sample_bit(evsel, ID);
+		perf_evsel__set_sample_bit(evsel, IDENTIFIER);
+	} else {
+		perf_evsel__set_sample_bit(evsel, ID);
+	}
 	evsel->attr.read_format |= PERF_FORMAT_ID;
 }
 
@@ -90,6 +164,7 @@ void perf_evsel__init(struct perf_evsel *evsel,
 	INIT_LIST_HEAD(&evsel->node);
 	hists__init(&evsel->hists);
 	evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
+	perf_evsel__calc_id_pos(evsel);
 }
 
 struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx)
@@ -509,7 +584,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
 		 * We need ID even in case of single event, because
 		 * PERF_SAMPLE_READ process ID specific data.
 		 */
-		perf_evsel__set_sample_id(evsel);
+		perf_evsel__set_sample_id(evsel, false);
 
 		/*
 		 * Apply group format only if we belong to group
@@ -1088,6 +1163,11 @@ static int perf_evsel__parse_id_sample(const struct perf_evsel *evsel,
 	array += ((event->header.size -
 		   sizeof(event->header)) / sizeof(u64)) - 1;
 
+	if (type & PERF_SAMPLE_IDENTIFIER) {
+		sample->id = *array;
+		array--;
+	}
+
 	if (type & PERF_SAMPLE_CPU) {
 		u.val64 = *array;
 		if (swapped) {
@@ -1131,24 +1211,30 @@ static int perf_evsel__parse_id_sample(const struct perf_evsel *evsel,
 	return 0;
 }
 
-static bool sample_overlap(const union perf_event *event,
-			   const void *offset, u64 size)
+static inline bool overflow(const void *endp, u16 max_size, const void *offset,
+			    u64 size)
 {
-	const void *base = event;
+	return size > max_size || offset + size > endp;
+}
 
-	if (offset + size > base + event->header.size)
-		return true;
+#define OVERFLOW_CHECK(offset, size, max_size)				\
+	do {								\
+		if (overflow(endp, (max_size), (offset), (size)))	\
+			return -EFAULT;					\
+	} while (0)
 
-	return false;
-}
+#define OVERFLOW_CHECK_u64(offset) \
+	OVERFLOW_CHECK(offset, sizeof(u64), sizeof(u64))
 
 int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 			     struct perf_sample *data)
 {
 	u64 type = evsel->attr.sample_type;
-	u64 regs_user = evsel->attr.sample_regs_user;
 	bool swapped = evsel->needs_swap;
 	const u64 *array;
+	u16 max_size = event->header.size;
+	const void *endp = (void *)event + max_size;
+	u64 sz;
 
 	/*
 	 * used for cross-endian analysis. See git commit 65014ab3
@@ -1170,11 +1256,22 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 
 	array = event->sample.array;
 
+	/*
+	 * The evsel's sample_size is based on PERF_SAMPLE_MASK which includes
+	 * up to PERF_SAMPLE_PERIOD.  After that overflow() must be used to
+	 * check the format does not go past the end of the event.
+	 */
 	if (evsel->sample_size + sizeof(event->header) > event->header.size)
 		return -EFAULT;
 
+	data->id = -1ULL;
+	if (type & PERF_SAMPLE_IDENTIFIER) {
+		data->id = *array;
+		array++;
+	}
+
 	if (type & PERF_SAMPLE_IP) {
-		data->ip = event->ip.ip;
+		data->ip = *array;
 		array++;
 	}
 
@@ -1203,7 +1300,6 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 		array++;
 	}
 
-	data->id = -1ULL;
 	if (type & PERF_SAMPLE_ID) {
 		data->id = *array;
 		array++;
@@ -1235,6 +1331,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 	if (type & PERF_SAMPLE_READ) {
 		u64 read_format = evsel->attr.read_format;
 
+		OVERFLOW_CHECK_u64(array);
 		if (read_format & PERF_FORMAT_GROUP)
 			data->read.group.nr = *array;
 		else
@@ -1243,41 +1340,51 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 		array++;
 
 		if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
+			OVERFLOW_CHECK_u64(array);
 			data->read.time_enabled = *array;
 			array++;
 		}
 
 		if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
+			OVERFLOW_CHECK_u64(array);
 			data->read.time_running = *array;
 			array++;
 		}
 
 		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
 		if (read_format & PERF_FORMAT_GROUP) {
-			data->read.group.values = (struct sample_read_value *) array;
-			array = (void *) array + data->read.group.nr *
-				sizeof(struct sample_read_value);
+			const u64 max_group_nr = UINT64_MAX /
+					sizeof(struct sample_read_value);
+
+			if (data->read.group.nr > max_group_nr)
+				return -EFAULT;
+			sz = data->read.group.nr *
+			     sizeof(struct sample_read_value);
+			OVERFLOW_CHECK(array, sz, max_size);
+			data->read.group.values =
+					(struct sample_read_value *)array;
+			array = (void *)array + sz;
 		} else {
+			OVERFLOW_CHECK_u64(array);
 			data->read.one.id = *array;
 			array++;
 		}
 	}
 
 	if (type & PERF_SAMPLE_CALLCHAIN) {
-		if (sample_overlap(event, array, sizeof(data->callchain->nr)))
-			return -EFAULT;
-
-		data->callchain = (struct ip_callchain *)array;
+		const u64 max_callchain_nr = UINT64_MAX / sizeof(u64);
 
-		if (sample_overlap(event, array, data->callchain->nr))
+		OVERFLOW_CHECK_u64(array);
+		data->callchain = (struct ip_callchain *)array++;
+		if (data->callchain->nr > max_callchain_nr)
 			return -EFAULT;
-
-		array += 1 + data->callchain->nr;
+		sz = data->callchain->nr * sizeof(u64);
+		OVERFLOW_CHECK(array, sz, max_size);
+		array = (void *)array + sz;
 	}
 
 	if (type & PERF_SAMPLE_RAW) {
-		const u64 *pdata;
-
+		OVERFLOW_CHECK_u64(array);
 		u.val64 = *array;
 		if (WARN_ONCE(swapped,
 			      "Endianness of raw data not corrected!\n")) {
@@ -1286,65 +1393,71 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 			u.val32[0] = bswap_32(u.val32[0]);
 			u.val32[1] = bswap_32(u.val32[1]);
 		}
-
-		if (sample_overlap(event, array, sizeof(u32)))
-			return -EFAULT;
-
 		data->raw_size = u.val32[0];
-		pdata = (void *) array + sizeof(u32);
-
-		if (sample_overlap(event, pdata, data->raw_size))
-			return -EFAULT;
-
-		data->raw_data = (void *) pdata;
+		array = (void *)array + sizeof(u32);
 
-		array = (void *)array + data->raw_size + sizeof(u32);
+		OVERFLOW_CHECK(array, data->raw_size, max_size);
+		data->raw_data = (void *)array;
+		array = (void *)array + data->raw_size;
 	}
 
 	if (type & PERF_SAMPLE_BRANCH_STACK) {
-		u64 sz;
+		const u64 max_branch_nr = UINT64_MAX /
+					  sizeof(struct branch_entry);
 
-		data->branch_stack = (struct branch_stack *)array;
-		array++; /* nr */
+		OVERFLOW_CHECK_u64(array);
+		data->branch_stack = (struct branch_stack *)array++;
 
+		if (data->branch_stack->nr > max_branch_nr)
+			return -EFAULT;
 		sz = data->branch_stack->nr * sizeof(struct branch_entry);
-		sz /= sizeof(u64);
-		array += sz;
+		OVERFLOW_CHECK(array, sz, max_size);
+		array = (void *)array + sz;
 	}
 
 	if (type & PERF_SAMPLE_REGS_USER) {
-		/* First u64 tells us if we have any regs in sample. */
-		u64 avail = *array++;
+		OVERFLOW_CHECK_u64(array);
+		data->user_regs.abi = *array;
+		array++;
+
+		if (data->user_regs.abi) {
+			u64 regs_user = evsel->attr.sample_regs_user;
 
-		if (avail) {
+			sz = hweight_long(regs_user) * sizeof(u64);
+			OVERFLOW_CHECK(array, sz, max_size);
 			data->user_regs.regs = (u64 *)array;
-			array += hweight_long(regs_user);
+			array = (void *)array + sz;
 		}
 	}
 
 	if (type & PERF_SAMPLE_STACK_USER) {
-		u64 size = *array++;
+		OVERFLOW_CHECK_u64(array);
+		sz = *array++;
 
 		data->user_stack.offset = ((char *)(array - 1)
 					  - (char *) event);
 
-		if (!size) {
+		if (!sz) {
 			data->user_stack.size = 0;
 		} else {
+			OVERFLOW_CHECK(array, sz, max_size);
 			data->user_stack.data = (char *)array;
-			array += size / sizeof(*array);
+			array = (void *)array + sz;
+			OVERFLOW_CHECK_u64(array);
 			data->user_stack.size = *array++;
 		}
 	}
 
 	data->weight = 0;
 	if (type & PERF_SAMPLE_WEIGHT) {
+		OVERFLOW_CHECK_u64(array);
 		data->weight = *array;
 		array++;
 	}
 
 	data->data_src = PERF_MEM_DATA_SRC_NONE;
 	if (type & PERF_SAMPLE_DATA_SRC) {
+		OVERFLOW_CHECK_u64(array);
 		data->data_src = *array;
 		array++;
 	}
@@ -1352,12 +1465,105 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 	return 0;
 }
 
+size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
+				     u64 sample_regs_user, u64 read_format)
+{
+	size_t sz, result = sizeof(struct sample_event);
+
+	if (type & PERF_SAMPLE_IDENTIFIER)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_IP)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_TID)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_TIME)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_ADDR)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_ID)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_STREAM_ID)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_CPU)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_PERIOD)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_READ) {
+		result += sizeof(u64);
+		if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+			result += sizeof(u64);
+		if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+			result += sizeof(u64);
+		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
+		if (read_format & PERF_FORMAT_GROUP) {
+			sz = sample->read.group.nr *
+			     sizeof(struct sample_read_value);
+			result += sz;
+		} else {
+			result += sizeof(u64);
+		}
+	}
+
+	if (type & PERF_SAMPLE_CALLCHAIN) {
+		sz = (sample->callchain->nr + 1) * sizeof(u64);
+		result += sz;
+	}
+
+	if (type & PERF_SAMPLE_RAW) {
+		result += sizeof(u32);
+		result += sample->raw_size;
+	}
+
+	if (type & PERF_SAMPLE_BRANCH_STACK) {
+		sz = sample->branch_stack->nr * sizeof(struct branch_entry);
+		sz += sizeof(u64);
+		result += sz;
+	}
+
+	if (type & PERF_SAMPLE_REGS_USER) {
+		if (sample->user_regs.abi) {
+			result += sizeof(u64);
+			sz = hweight_long(sample_regs_user) * sizeof(u64);
+			result += sz;
+		} else {
+			result += sizeof(u64);
+		}
+	}
+
+	if (type & PERF_SAMPLE_STACK_USER) {
+		sz = sample->user_stack.size;
+		result += sizeof(u64);
+		if (sz) {
+			result += sz;
+			result += sizeof(u64);
+		}
+	}
+
+	if (type & PERF_SAMPLE_WEIGHT)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_DATA_SRC)
+		result += sizeof(u64);
+
+	return result;
+}
+
 int perf_event__synthesize_sample(union perf_event *event, u64 type,
+				  u64 sample_regs_user, u64 read_format,
 				  const struct perf_sample *sample,
 				  bool swapped)
 {
 	u64 *array;
-
+	size_t sz;
 	/*
 	 * used for cross-endian analysis. See git commit 65014ab3
 	 * for why this goofiness is needed.
@@ -1366,8 +1572,13 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 
 	array = event->sample.array;
 
+	if (type & PERF_SAMPLE_IDENTIFIER) {
+		*array = sample->id;
+		array++;
+	}
+
 	if (type & PERF_SAMPLE_IP) {
-		event->ip.ip = sample->ip;
+		*array = sample->ip;
 		array++;
 	}
 
@@ -1425,6 +1636,97 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 		array++;
 	}
 
+	if (type & PERF_SAMPLE_READ) {
+		if (read_format & PERF_FORMAT_GROUP)
+			*array = sample->read.group.nr;
+		else
+			*array = sample->read.one.value;
+		array++;
+
+		if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
+			*array = sample->read.time_enabled;
+			array++;
+		}
+
+		if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
+			*array = sample->read.time_running;
+			array++;
+		}
+
+		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
+		if (read_format & PERF_FORMAT_GROUP) {
+			sz = sample->read.group.nr *
+			     sizeof(struct sample_read_value);
+			memcpy(array, sample->read.group.values, sz);
+			array = (void *)array + sz;
+		} else {
+			*array = sample->read.one.id;
+			array++;
+		}
+	}
+
+	if (type & PERF_SAMPLE_CALLCHAIN) {
+		sz = (sample->callchain->nr + 1) * sizeof(u64);
+		memcpy(array, sample->callchain, sz);
+		array = (void *)array + sz;
+	}
+
+	if (type & PERF_SAMPLE_RAW) {
+		u.val32[0] = sample->raw_size;
+		if (WARN_ONCE(swapped,
+			      "Endianness of raw data not corrected!\n")) {
+			/*
+			 * Inverse of what is done in perf_evsel__parse_sample
+			 */
+			u.val32[0] = bswap_32(u.val32[0]);
+			u.val32[1] = bswap_32(u.val32[1]);
+			u.val64 = bswap_64(u.val64);
+		}
+		*array = u.val64;
+		array = (void *)array + sizeof(u32);
+
+		memcpy(array, sample->raw_data, sample->raw_size);
+		array = (void *)array + sample->raw_size;
+	}
+
+	if (type & PERF_SAMPLE_BRANCH_STACK) {
+		sz = sample->branch_stack->nr * sizeof(struct branch_entry);
+		sz += sizeof(u64);
+		memcpy(array, sample->branch_stack, sz);
+		array = (void *)array + sz;
+	}
+
+	if (type & PERF_SAMPLE_REGS_USER) {
+		if (sample->user_regs.abi) {
+			*array++ = sample->user_regs.abi;
+			sz = hweight_long(sample_regs_user) * sizeof(u64);
+			memcpy(array, sample->user_regs.regs, sz);
+			array = (void *)array + sz;
+		} else {
+			*array++ = 0;
+		}
+	}
+
+	if (type & PERF_SAMPLE_STACK_USER) {
+		sz = sample->user_stack.size;
+		*array++ = sz;
+		if (sz) {
+			memcpy(array, sample->user_stack.data, sz);
+			array = (void *)array + sz;
+			*array++ = sz;
+		}
+	}
+
+	if (type & PERF_SAMPLE_WEIGHT) {
+		*array = sample->weight;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_DATA_SRC) {
+		*array = sample->data_src;
+		array++;
+	}
+
 	return 0;
 }
 
@@ -1554,6 +1856,7 @@ static int sample_type__fprintf(FILE *fp, bool *first, u64 value)
 		bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU),
 		bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW),
 		bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
+		bit_name(IDENTIFIER),
 		{ .name = NULL, }
 	};
 #undef bit_name
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 532a5f925da0..4a7bdc713bab 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -48,6 +48,12 @@ struct perf_sample_id {
  * @name - Can be set to retain the original event name passed by the user,
  *         so that when showing results in tools such as 'perf stat', we
  *         show the name used, not some alias.
+ * @id_pos: the position of the event id (PERF_SAMPLE_ID or
+ *          PERF_SAMPLE_IDENTIFIER) in a sample event i.e. in the array of
+ *          struct sample_event
+ * @is_pos: the position (counting backwards) of the event id (PERF_SAMPLE_ID or
+ *          PERF_SAMPLE_IDENTIFIER) in a non-sample event i.e. if sample_id_all
+ *          is used there is an id sample appended to non-sample events
  */
 struct perf_evsel {
 	struct list_head	node;
@@ -74,6 +80,8 @@ struct perf_evsel {
 	} handler;
 	struct cpu_map		*cpus;
 	unsigned int		sample_size;
+	int			id_pos;
+	int			is_pos;
 	bool 			supported;
 	bool 			needs_swap;
 	/* parse modifier helper */
@@ -104,6 +112,9 @@ void perf_evsel__delete(struct perf_evsel *evsel);
 void perf_evsel__config(struct perf_evsel *evsel,
 			struct perf_record_opts *opts);
 
+int __perf_evsel__sample_size(u64 sample_type);
+void perf_evsel__calc_id_pos(struct perf_evsel *evsel);
+
 bool perf_evsel__is_cache_op_valid(u8 type, u8 op);
 
 #define PERF_EVSEL__MAX_ALIASES 8
@@ -142,7 +153,8 @@ void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel,
 #define perf_evsel__reset_sample_bit(evsel, bit) \
 	__perf_evsel__reset_sample_bit(evsel, PERF_SAMPLE_##bit)
 
-void perf_evsel__set_sample_id(struct perf_evsel *evsel);
+void perf_evsel__set_sample_id(struct perf_evsel *evsel,
+			       bool use_sample_identifier);
 
 int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads,
 			   const char *filter);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 59486c180626..1dca61f0512d 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -32,7 +32,8 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 		return -ENOMEM;
 
 	if (pid != HOST_KERNEL_ID) {
-		struct thread *thread = machine__findnew_thread(machine, pid);
+		struct thread *thread = machine__findnew_thread(machine, 0,
+								pid);
 		char comm[64];
 
 		if (thread == NULL)
@@ -302,9 +303,10 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
 	return th;
 }
 
-struct thread *machine__findnew_thread(struct machine *machine, pid_t tid)
+struct thread *machine__findnew_thread(struct machine *machine, pid_t pid,
+				       pid_t tid)
 {
-	return __machine__findnew_thread(machine, 0, tid, true);
+	return __machine__findnew_thread(machine, pid, tid, true);
 }
 
 struct thread *machine__find_thread(struct machine *machine, pid_t tid)
@@ -314,7 +316,9 @@ struct thread *machine__find_thread(struct machine *machine, pid_t tid)
 
 int machine__process_comm_event(struct machine *machine, union perf_event *event)
 {
-	struct thread *thread = machine__findnew_thread(machine, event->comm.tid);
+	struct thread *thread = machine__findnew_thread(machine,
+							event->comm.pid,
+							event->comm.tid);
 
 	if (dump_trace)
 		perf_event__fprintf_comm(event, stdout);
@@ -1012,7 +1016,8 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 		return 0;
 	}
 
-	thread = machine__findnew_thread(machine, event->mmap.pid);
+	thread = machine__findnew_thread(machine, event->mmap.pid,
+					 event->mmap.pid);
 	if (thread == NULL)
 		goto out_problem;
 
@@ -1051,13 +1056,16 @@ static void machine__remove_thread(struct machine *machine, struct thread *th)
 int machine__process_fork_event(struct machine *machine, union perf_event *event)
 {
 	struct thread *thread = machine__find_thread(machine, event->fork.tid);
-	struct thread *parent = machine__findnew_thread(machine, event->fork.ptid);
+	struct thread *parent = machine__findnew_thread(machine,
+							event->fork.ppid,
+							event->fork.ptid);
 
 	/* if a thread currently exists for the thread id remove it */
 	if (thread != NULL)
 		machine__remove_thread(machine, thread);
 
-	thread = machine__findnew_thread(machine, event->fork.tid);
+	thread = machine__findnew_thread(machine, event->fork.pid,
+					 event->fork.tid);
 	if (dump_trace)
 		perf_event__fprintf_task(event, stdout);
 
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 603ffba999d9..0df925ba6a44 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -106,7 +106,8 @@ static inline bool machine__is_host(struct machine *machine)
 	return machine ? machine->pid == HOST_KERNEL_ID : false;
 }
 
-struct thread *machine__findnew_thread(struct machine *machine, pid_t tid);
+struct thread *machine__findnew_thread(struct machine *machine, pid_t pid,
+				       pid_t tid);
 
 size_t machine__fprintf(struct machine *machine, FILE *fp);
 
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
new file mode 100644
index 000000000000..18d73aa2f0f8
--- /dev/null
+++ b/tools/perf/util/record.c
@@ -0,0 +1,108 @@
+#include "evlist.h"
+#include "evsel.h"
+#include "cpumap.h"
+#include "parse-events.h"
+
+typedef void (*setup_probe_fn_t)(struct perf_evsel *evsel);
+
+static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
+{
+	struct perf_evlist *evlist;
+	struct perf_evsel *evsel;
+	int err = -EAGAIN, fd;
+
+	evlist = perf_evlist__new();
+	if (!evlist)
+		return -ENOMEM;
+
+	if (parse_events(evlist, str))
+		goto out_delete;
+
+	evsel = perf_evlist__first(evlist);
+
+	fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0);
+	if (fd < 0)
+		goto out_delete;
+	close(fd);
+
+	fn(evsel);
+
+	fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0);
+	if (fd < 0) {
+		if (errno == EINVAL)
+			err = -EINVAL;
+		goto out_delete;
+	}
+	close(fd);
+	err = 0;
+
+out_delete:
+	perf_evlist__delete(evlist);
+	return err;
+}
+
+static bool perf_probe_api(setup_probe_fn_t fn)
+{
+	const char *try[] = {"cycles:u", "instructions:u", "cpu-clock", NULL};
+	struct cpu_map *cpus;
+	int cpu, ret, i = 0;
+
+	cpus = cpu_map__new(NULL);
+	if (!cpus)
+		return false;
+	cpu = cpus->map[0];
+	cpu_map__delete(cpus);
+
+	do {
+		ret = perf_do_probe_api(fn, cpu, try[i++]);
+		if (!ret)
+			return true;
+	} while (ret == -EAGAIN && try[i]);
+
+	return false;
+}
+
+static void perf_probe_sample_identifier(struct perf_evsel *evsel)
+{
+	evsel->attr.sample_type |= PERF_SAMPLE_IDENTIFIER;
+}
+
+bool perf_can_sample_identifier(void)
+{
+	return perf_probe_api(perf_probe_sample_identifier);
+}
+
+void perf_evlist__config(struct perf_evlist *evlist,
+			struct perf_record_opts *opts)
+{
+	struct perf_evsel *evsel;
+	bool use_sample_identifier = false;
+
+	/*
+	 * Set the evsel leader links before we configure attributes,
+	 * since some might depend on this info.
+	 */
+	if (opts->group)
+		perf_evlist__set_leader(evlist);
+
+	if (evlist->cpus->map[0] < 0)
+		opts->no_inherit = true;
+
+	list_for_each_entry(evsel, &evlist->entries, node)
+		perf_evsel__config(evsel, opts);
+
+	if (evlist->nr_entries > 1) {
+		struct perf_evsel *first = perf_evlist__first(evlist);
+
+		list_for_each_entry(evsel, &evlist->entries, node) {
+			if (evsel->attr.sample_type == first->attr.sample_type)
+				continue;
+			use_sample_identifier = perf_can_sample_identifier();
+			break;
+		}
+		list_for_each_entry(evsel, &evlist->entries, node)
+			perf_evsel__set_sample_id(evsel, use_sample_identifier);
+	}
+
+	perf_evlist__set_id_pos(evlist);
+}
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index de16a7736859..07642a7b9346 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -739,7 +739,7 @@ static void perf_session__print_tstamp(struct perf_session *session,
 				       union perf_event *event,
 				       struct perf_sample *sample)
 {
-	u64 sample_type = perf_evlist__sample_type(session->evlist);
+	u64 sample_type = __perf_evlist__combined_sample_type(session->evlist);
 
 	if (event->header.type != PERF_RECORD_SAMPLE &&
 	    !perf_evlist__sample_id_all(session->evlist)) {
@@ -840,7 +840,8 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
 
 static struct machine *
 	perf_session__find_machine_for_cpumode(struct perf_session *session,
-					       union perf_event *event)
+					       union perf_event *event,
+					       struct perf_sample *sample)
 {
 	const u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
@@ -852,7 +853,7 @@ static struct machine *
 		if (event->header.type == PERF_RECORD_MMAP)
 			pid = event->mmap.pid;
 		else
-			pid = event->ip.pid;
+			pid = sample->pid;
 
 		return perf_session__findnew_machine(session, pid);
 	}
@@ -958,7 +959,8 @@ static int perf_session_deliver_event(struct perf_session *session,
 		hists__inc_nr_events(&evsel->hists, event->header.type);
 	}
 
-	machine = perf_session__find_machine_for_cpumode(session, event);
+	machine = perf_session__find_machine_for_cpumode(session, event,
+							 sample);
 
 	switch (event->header.type) {
 	case PERF_RECORD_SAMPLE:
@@ -997,22 +999,6 @@ static int perf_session_deliver_event(struct perf_session *session,
 	}
 }
 
-static int perf_session__preprocess_sample(struct perf_session *session,
-					   union perf_event *event, struct perf_sample *sample)
-{
-	if (event->header.type != PERF_RECORD_SAMPLE ||
-	    !(perf_evlist__sample_type(session->evlist) & PERF_SAMPLE_CALLCHAIN))
-		return 0;
-
-	if (!ip_callchain__valid(sample->callchain, event)) {
-		pr_debug("call-chain problem with event, skipping it.\n");
-		++session->stats.nr_invalid_chains;
-		session->stats.total_invalid_chains += sample->period;
-		return -EINVAL;
-	}
-	return 0;
-}
-
 static int perf_session__process_user_event(struct perf_session *session, union perf_event *event,
 					    struct perf_tool *tool, u64 file_offset)
 {
@@ -1075,10 +1061,6 @@ static int perf_session__process_event(struct perf_session *session,
 	if (ret)
 		return ret;
 
-	/* Preprocess sample records - precheck callchains */
-	if (perf_session__preprocess_sample(session, event, &sample))
-		return 0;
-
 	if (tool->ordered_samples) {
 		ret = perf_session_queue_event(session, event, &sample,
 					       file_offset);
@@ -1099,7 +1081,7 @@ void perf_event_header__bswap(struct perf_event_header *self)
 
 struct thread *perf_session__findnew(struct perf_session *session, pid_t pid)
 {
-	return machine__findnew_thread(&session->machines.host, pid);
+	return machine__findnew_thread(&session->machines.host, 0, pid);
 }
 
 static struct thread *perf_session__register_idle_thread(struct perf_session *self)