diff --git a/scripts/package/Makefile b/scripts/package/Makefile
index a4f31c900fa6..c5d473393816 100644
--- a/scripts/package/Makefile
+++ b/scripts/package/Makefile
@@ -115,7 +115,9 @@ git --git-dir=$(srctree)/.git archive --prefix=$(perf-tar)/         \
 	-o $(perf-tar).tar;                                         \
 mkdir -p $(perf-tar);                                               \
 git --git-dir=$(srctree)/.git rev-parse HEAD > $(perf-tar)/HEAD;    \
-tar rf $(perf-tar).tar $(perf-tar)/HEAD;                            \
+(cd $(srctree)/tools/perf;                                          \
+util/PERF-VERSION-GEN ../../$(perf-tar)/ 2>/dev/null);              \
+tar rf $(perf-tar).tar $(perf-tar)/HEAD $(perf-tar)/PERF-VERSION-FILE; \
 rm -r $(perf-tar);                                                  \
 $(if $(findstring tar-src,$@),,                                     \
 $(if $(findstring bz2,$@),bzip2,                                    \
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 409ceaf3b9b9..6a2508589460 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -106,8 +106,8 @@ static int perf_event__repipe_sample(struct perf_tool *tool,
 				     struct perf_evsel *evsel,
 				     struct machine *machine)
 {
-	if (evsel->handler.func) {
-		inject_handler f = evsel->handler.func;
+	if (evsel->handler) {
+		inject_handler f = evsel->handler;
 		return f(tool, event, sample, evsel, machine);
 	}
 
@@ -383,11 +383,11 @@ static int __cmd_inject(struct perf_inject *inject)
 				if (perf_evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID"))
 					return -EINVAL;
 
-				evsel->handler.func = perf_inject__sched_switch;
+				evsel->handler = perf_inject__sched_switch;
 			} else if (!strcmp(name, "sched:sched_process_exit"))
-				evsel->handler.func = perf_inject__sched_process_exit;
+				evsel->handler = perf_inject__sched_process_exit;
 			else if (!strncmp(name, "sched:sched_stat_", 17))
-				evsel->handler.func = perf_inject__sched_stat;
+				evsel->handler = perf_inject__sched_stat;
 		}
 	}
 
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index a28970f7ddfb..929462aa4943 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -317,8 +317,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 
 	dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid);
 
-	if (evsel->handler.func != NULL) {
-		tracepoint_handler f = evsel->handler.func;
+	if (evsel->handler != NULL) {
+		tracepoint_handler f = evsel->handler;
 		return f(evsel, sample);
 	}
 
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 35f9aaa565cc..c852c7a85d32 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -819,8 +819,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 		return -1;
 	}
 
-	if (evsel->handler.func != NULL) {
-		tracepoint_handler f = evsel->handler.func;
+	if (evsel->handler != NULL) {
+		tracepoint_handler f = evsel->handler;
 		return f(evsel, sample);
 	}
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index ea4c04f7437e..15280b5e5574 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -74,14 +74,8 @@ struct perf_record {
 	bool			no_buildid;
 	bool			no_buildid_cache;
 	long			samples;
-	off_t			post_processing_offset;
 };
 
-static void advance_output(struct perf_record *rec, size_t size)
-{
-	rec->bytes_written += size;
-}
-
 static int write_output(struct perf_record *rec, void *buf, size_t size)
 {
 	struct perf_data_file *file = &rec->file;
@@ -252,13 +246,14 @@ static int process_buildids(struct perf_record *rec)
 {
 	struct perf_data_file *file  = &rec->file;
 	struct perf_session *session = rec->session;
+	u64 start = session->header.data_offset;
 
 	u64 size = lseek(file->fd, 0, SEEK_CUR);
 	if (size == 0)
 		return 0;
 
-	return __perf_session__process_events(session, rec->post_processing_offset,
-					      size - rec->post_processing_offset,
+	return __perf_session__process_events(session, start,
+					      size - start,
 					      size, &build_id__mark_dso_hit_ops);
 }
 
@@ -342,9 +337,28 @@ out:
 	return rc;
 }
 
+static void perf_record__init_features(struct perf_record *rec)
+{
+	struct perf_evlist *evsel_list = rec->evlist;
+	struct perf_session *session = rec->session;
+	int feat;
+
+	for (feat = HEADER_FIRST_FEATURE; feat < HEADER_LAST_FEATURE; feat++)
+		perf_header__set_feat(&session->header, feat);
+
+	if (rec->no_buildid)
+		perf_header__clear_feat(&session->header, HEADER_BUILD_ID);
+
+	if (!have_tracepoints(&evsel_list->entries))
+		perf_header__clear_feat(&session->header, HEADER_TRACING_DATA);
+
+	if (!rec->opts.branch_stack)
+		perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
+}
+
 static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 {
-	int err, feat;
+	int err;
 	unsigned long waking = 0;
 	const bool forks = argc > 0;
 	struct machine *machine;
@@ -371,17 +385,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 
 	rec->session = session;
 
-	for (feat = HEADER_FIRST_FEATURE; feat < HEADER_LAST_FEATURE; feat++)
-		perf_header__set_feat(&session->header, feat);
-
-	if (rec->no_buildid)
-		perf_header__clear_feat(&session->header, HEADER_BUILD_ID);
-
-	if (!have_tracepoints(&evsel_list->entries))
-		perf_header__clear_feat(&session->header, HEADER_TRACING_DATA);
-
-	if (!rec->opts.branch_stack)
-		perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
+	perf_record__init_features(rec);
 
 	if (forks) {
 		err = perf_evlist__prepare_workload(evsel_list, &opts->target,
@@ -425,8 +429,6 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 		goto out_delete_session;
 	}
 
-	rec->post_processing_offset = lseek(file->fd, 0, SEEK_CUR);
-
 	machine = &session->machines.host;
 
 	if (file->is_pipe) {
@@ -452,7 +454,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 				pr_err("Couldn't record tracing data.\n");
 				goto out_delete_session;
 			}
-			advance_output(rec, err);
+			rec->bytes_written += err;
 		}
 	}
 
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index a81ab1828aa5..0f3c65518a2c 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1427,8 +1427,8 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_
 	evsel->hists.stats.total_period += sample->period;
 	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
 
-	if (evsel->handler.func != NULL) {
-		tracepoint_handler f = evsel->handler.func;
+	if (evsel->handler != NULL) {
+		tracepoint_handler f = evsel->handler;
 		err = f(tool, evsel, sample, machine);
 	}
 
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index e11c61d9bda4..41c9bde2fb67 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -483,8 +483,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 	if (sample->cpu > numcpus)
 		numcpus = sample->cpu;
 
-	if (evsel->handler.func != NULL) {
-		tracepoint_handler f = evsel->handler.func;
+	if (evsel->handler != NULL) {
+		tracepoint_handler f = evsel->handler;
 		return f(evsel, sample);
 	}
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index b3e57dc64546..329b7832b5da 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -35,6 +35,189 @@
 # define MADV_UNMERGEABLE	13
 #endif
 
+struct tp_field {
+	int offset;
+	union {
+		u64 (*integer)(struct tp_field *field, struct perf_sample *sample);
+		void *(*pointer)(struct tp_field *field, struct perf_sample *sample);
+	};
+};
+
+#define TP_UINT_FIELD(bits) \
+static u64 tp_field__u##bits(struct tp_field *field, struct perf_sample *sample) \
+{ \
+	return *(u##bits *)(sample->raw_data + field->offset); \
+}
+
+TP_UINT_FIELD(8);
+TP_UINT_FIELD(16);
+TP_UINT_FIELD(32);
+TP_UINT_FIELD(64);
+
+#define TP_UINT_FIELD__SWAPPED(bits) \
+static u64 tp_field__swapped_u##bits(struct tp_field *field, struct perf_sample *sample) \
+{ \
+	u##bits value = *(u##bits *)(sample->raw_data + field->offset); \
+	return bswap_##bits(value);\
+}
+
+TP_UINT_FIELD__SWAPPED(16);
+TP_UINT_FIELD__SWAPPED(32);
+TP_UINT_FIELD__SWAPPED(64);
+
+static int tp_field__init_uint(struct tp_field *field,
+			       struct format_field *format_field,
+			       bool needs_swap)
+{
+	field->offset = format_field->offset;
+
+	switch (format_field->size) {
+	case 1:
+		field->integer = tp_field__u8;
+		break;
+	case 2:
+		field->integer = needs_swap ? tp_field__swapped_u16 : tp_field__u16;
+		break;
+	case 4:
+		field->integer = needs_swap ? tp_field__swapped_u32 : tp_field__u32;
+		break;
+	case 8:
+		field->integer = needs_swap ? tp_field__swapped_u64 : tp_field__u64;
+		break;
+	default:
+		return -1;
+	}
+
+	return 0;
+}
+
+static void *tp_field__ptr(struct tp_field *field, struct perf_sample *sample)
+{
+	return sample->raw_data + field->offset;
+}
+
+static int tp_field__init_ptr(struct tp_field *field, struct format_field *format_field)
+{
+	field->offset = format_field->offset;
+	field->pointer = tp_field__ptr;
+	return 0;
+}
+
+struct syscall_tp {
+	struct tp_field id;
+	union {
+		struct tp_field args, ret;
+	};
+};
+
+static int perf_evsel__init_tp_uint_field(struct perf_evsel *evsel,
+					  struct tp_field *field,
+					  const char *name)
+{
+	struct format_field *format_field = perf_evsel__field(evsel, name);
+
+	if (format_field == NULL)
+		return -1;
+
+	return tp_field__init_uint(field, format_field, evsel->needs_swap);
+}
+
+#define perf_evsel__init_sc_tp_uint_field(evsel, name) \
+	({ struct syscall_tp *sc = evsel->priv;\
+	   perf_evsel__init_tp_uint_field(evsel, &sc->name, #name); })
+
+static int perf_evsel__init_tp_ptr_field(struct perf_evsel *evsel,
+					 struct tp_field *field,
+					 const char *name)
+{
+	struct format_field *format_field = perf_evsel__field(evsel, name);
+
+	if (format_field == NULL)
+		return -1;
+
+	return tp_field__init_ptr(field, format_field);
+}
+
+#define perf_evsel__init_sc_tp_ptr_field(evsel, name) \
+	({ struct syscall_tp *sc = evsel->priv;\
+	   perf_evsel__init_tp_ptr_field(evsel, &sc->name, #name); })
+
+static void perf_evsel__delete_priv(struct perf_evsel *evsel)
+{
+	free(evsel->priv);
+	evsel->priv = NULL;
+	perf_evsel__delete(evsel);
+}
+
+static struct perf_evsel *perf_evsel__syscall_newtp(const char *direction,
+						    void *handler, int idx)
+{
+	struct perf_evsel *evsel = perf_evsel__newtp("raw_syscalls", direction, idx);
+
+	if (evsel) {
+		evsel->priv = malloc(sizeof(struct syscall_tp));
+
+		if (evsel->priv == NULL)
+			goto out_delete;
+
+		if (perf_evsel__init_sc_tp_uint_field(evsel, id))
+			goto out_delete;
+
+		evsel->handler = handler;
+	}
+
+	return evsel;
+
+out_delete:
+	perf_evsel__delete_priv(evsel);
+	return NULL;
+}
+
+#define perf_evsel__sc_tp_uint(evsel, name, sample) \
+	({ struct syscall_tp *fields = evsel->priv; \
+	   fields->name.integer(&fields->name, sample); })
+
+#define perf_evsel__sc_tp_ptr(evsel, name, sample) \
+	({ struct syscall_tp *fields = evsel->priv; \
+	   fields->name.pointer(&fields->name, sample); })
+
+static int perf_evlist__add_syscall_newtp(struct perf_evlist *evlist,
+					  void *sys_enter_handler,
+					  void *sys_exit_handler)
+{
+	int ret = -1;
+	int idx = evlist->nr_entries;
+	struct perf_evsel *sys_enter, *sys_exit;
+
+	sys_enter = perf_evsel__syscall_newtp("sys_enter", sys_enter_handler, idx++);
+	if (sys_enter == NULL)
+		goto out;
+
+	if (perf_evsel__init_sc_tp_ptr_field(sys_enter, args))
+		goto out_delete_sys_enter;
+
+	sys_exit = perf_evsel__syscall_newtp("sys_exit", sys_exit_handler, idx++);
+	if (sys_exit == NULL)
+		goto out_delete_sys_enter;
+
+	if (perf_evsel__init_sc_tp_uint_field(sys_exit, ret))
+		goto out_delete_sys_exit;
+
+	perf_evlist__add(evlist, sys_enter);
+	perf_evlist__add(evlist, sys_exit);
+
+	ret = 0;
+out:
+	return ret;
+
+out_delete_sys_exit:
+	perf_evsel__delete_priv(sys_exit);
+out_delete_sys_enter:
+	perf_evsel__delete_priv(sys_enter);
+	goto out;
+}
+
+
 struct syscall_arg {
 	unsigned long val;
 	struct thread *thread;
@@ -1392,7 +1575,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 	void *args;
 	size_t printed = 0;
 	struct thread *thread;
-	int id = perf_evsel__intval(evsel, sample, "id");
+	int id = perf_evsel__sc_tp_uint(evsel, id, sample);
 	struct syscall *sc = trace__syscall_info(trace, evsel, id);
 	struct thread_trace *ttrace;
 
@@ -1407,12 +1590,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 	if (ttrace == NULL)
 		return -1;
 
-	args = perf_evsel__rawptr(evsel, sample, "args");
-	if (args == NULL) {
-		fprintf(trace->output, "Problems reading syscall arguments\n");
-		return -1;
-	}
-
+	args = perf_evsel__sc_tp_ptr(evsel, args, sample);
 	ttrace = thread->priv;
 
 	if (ttrace->entry_str == NULL) {
@@ -1445,7 +1623,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 	int ret;
 	u64 duration = 0;
 	struct thread *thread;
-	int id = perf_evsel__intval(evsel, sample, "id");
+	int id = perf_evsel__sc_tp_uint(evsel, id, sample);
 	struct syscall *sc = trace__syscall_info(trace, evsel, id);
 	struct thread_trace *ttrace;
 
@@ -1463,7 +1641,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 	if (trace->summary)
 		thread__update_stats(ttrace, id, sample);
 
-	ret = perf_evsel__intval(evsel, sample, "ret");
+	ret = perf_evsel__sc_tp_uint(evsel, ret, sample);
 
 	if (id == trace->audit.open_id && ret >= 0 && trace->last_vfs_getname) {
 		trace__set_fd_pathname(thread, ret, trace->last_vfs_getname);
@@ -1570,7 +1748,7 @@ static int trace__process_sample(struct perf_tool *tool,
 	struct trace *trace = container_of(tool, struct trace, tool);
 	int err = 0;
 
-	tracepoint_handler handler = evsel->handler.func;
+	tracepoint_handler handler = evsel->handler;
 
 	if (skip_sample(trace, sample))
 		return 0;
@@ -1656,7 +1834,7 @@ static void perf_evlist__add_vfs_getname(struct perf_evlist *evlist)
 		return;
 	}
 
-	evsel->handler.func = trace__vfs_getname;
+	evsel->handler = trace__vfs_getname;
 	perf_evlist__add(evlist, evsel);
 }
 
@@ -1675,8 +1853,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 		goto out;
 	}
 
-	if (perf_evlist__add_newtp(evlist, "raw_syscalls", "sys_enter", trace__sys_enter) ||
-		perf_evlist__add_newtp(evlist, "raw_syscalls", "sys_exit", trace__sys_exit))
+	if (perf_evlist__add_syscall_newtp(evlist, trace__sys_enter, trace__sys_exit))
 		goto out_error_tp;
 
 	perf_evlist__add_vfs_getname(evlist);
@@ -1768,7 +1945,7 @@ again:
 				goto next_event;
 			}
 
-			handler = evsel->handler.func;
+			handler = evsel->handler;
 			handler(trace, evsel, &sample);
 next_event:
 			perf_evlist__mmap_consume(evlist, i);
diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN
index ce7a804b2951..39f17507578d 100755
--- a/tools/perf/util/PERF-VERSION-GEN
+++ b/tools/perf/util/PERF-VERSION-GEN
@@ -19,6 +19,9 @@ if test -d ../../.git -o -f ../../.git
 then
 	TAG=$(git describe --abbrev=0 --match "v[0-9].[0-9]*" 2>/dev/null )
 	CID=$(git log -1 --abbrev=4 --pretty=format:"%h" 2>/dev/null) && CID="-g$CID"
+elif test -f ../../PERF-VERSION-FILE
+then
+	TAG=$(cut -d' ' -f3 ../../PERF-VERSION-FILE | sed -e 's/\"//g')
 fi
 if test -z "$TAG"
 then
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 1c173ccb0ef2..b939221efd8d 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -255,7 +255,7 @@ int perf_evlist__add_newtp(struct perf_evlist *evlist,
 	if (evsel == NULL)
 		return -1;
 
-	evsel->handler.func = handler;
+	evsel->handler = handler;
 	perf_evlist__add(evlist, evsel);
 	return 0;
 }
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 5aa68cddc7d9..64ec8e1a7a28 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -74,10 +74,7 @@ struct perf_evsel {
 		off_t		id_offset;
 	};
 	struct cgroup_sel	*cgrp;
-	struct {
-		void		*func;
-		void		*data;
-	} handler;
+	void			*handler;
 	struct cpu_map		*cpus;
 	unsigned int		sample_size;
 	int			id_pos;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 0ce46943d627..f36d24a02445 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1650,9 +1650,9 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session,
 			continue;
 
 		err = -EEXIST;
-		if (evsel->handler.func != NULL)
+		if (evsel->handler != NULL)
 			goto out;
-		evsel->handler.func = assocs[i].handler;
+		evsel->handler = assocs[i].handler;
 	}
 
 	err = 0;
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index f4cc147e0220..43e5ff42a609 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -22,7 +22,6 @@
 #include "parse-events.h"
 
 #include "thread.h"
-#include "sort.h"
 
 extern regex_t parent_regex;
 extern const char *sort_order;