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