Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "The main updates in this cycle were:

   - Lots of perf tooling changes too voluminous to list (big perf trace
     and perf stat improvements, lots of libtraceevent reorganization,
     etc.), so I'll list the authors and refer to the changelog for
     details:

       Benjamin Peterson, Jérémie Galarneau, Kim Phillips, Peter
       Zijlstra, Ravi Bangoria, Sangwon Hong, Sean V Kelley, Steven
       Rostedt, Thomas Gleixner, Ding Xiang, Eduardo Habkost, Thomas
       Richter, Andi Kleen, Sanskriti Sharma, Adrian Hunter, Tzvetomir
       Stoyanov, Arnaldo Carvalho de Melo, Jiri Olsa.

     ... with the bulk of the changes written by Jiri Olsa, Tzvetomir
     Stoyanov and Arnaldo Carvalho de Melo.

   - Continued intel_rdt work with a focus on playing well with perf
     events. This also imported some non-perf RDT work due to
     dependencies. (Reinette Chatre)

   - Implement counter freezing for Arch Perfmon v4 (Skylake and newer).
     This allows to speed up the PMI handler by avoiding unnecessary MSR
     writes and make it more accurate. (Andi Kleen)

   - kprobes cleanups and simplification (Masami Hiramatsu)

   - Intel Goldmont PMU updates (Kan Liang)

   - ... plus misc other fixes and updates"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (155 commits)
  kprobes/x86: Use preempt_enable() in optimized_callback()
  x86/intel_rdt: Prevent pseudo-locking from using stale pointers
  kprobes, x86/ptrace.h: Make regs_get_kernel_stack_nth() not fault on bad stack
  perf/x86/intel: Export mem events only if there's PEBS support
  x86/cpu: Drop pointless static qualifier in punit_dev_state_show()
  x86/intel_rdt: Fix initial allocation to consider CDP
  x86/intel_rdt: CBM overlap should also check for overlap with CDP peer
  x86/intel_rdt: Introduce utility to obtain CDP peer
  tools lib traceevent, perf tools: Move struct tep_handler definition in a local header file
  tools lib traceevent: Separate out tep_strerror() for strerror_r() issues
  perf python: More portable way to make CFLAGS work with clang
  perf python: Make clang_has_option() work on Python 3
  perf tools: Free temporary 'sys' string in read_event_files()
  perf tools: Avoid double free in read_event_file()
  perf tools: Free 'printk' string in parse_ftrace_printk()
  perf tools: Cleanup trace-event-info 'tdata' leak
  perf strbuf: Match va_{add,copy} with va_end
  perf test: S390 does not support watchpoints in test 22
  perf auxtrace: Include missing asm/bitsperlong.h to get BITS_PER_LONG
  tools include: Adopt linux/bits.h
  ...

42 files changed, 2034 insertions, 453 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 7efe15b9618d..ecd9f9ceda77 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -73,6 +73,7 @@ libperf-y += vdso.o
 libperf-y += counts.o
 libperf-y += stat.o
 libperf-y += stat-shadow.o
+libperf-y += stat-display.o
 libperf-y += record.o
 libperf-y += srcline.o
 libperf-y += data.o
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index db1511359c5e..c4617bcfd521 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -906,9 +906,8 @@ out_free:
 	return err;
 }
 
-int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
-				      union perf_event *event,
-				      struct perf_session *session)
+int perf_event__process_auxtrace_info(struct perf_session *session,
+				      union perf_event *event)
 {
 	enum auxtrace_type type = event->auxtrace_info.type;
 
@@ -932,9 +931,8 @@ int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
 	}
 }
 
-s64 perf_event__process_auxtrace(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session)
+s64 perf_event__process_auxtrace(struct perf_session *session,
+				 union perf_event *event)
 {
 	s64 err;
 
@@ -950,7 +948,7 @@ s64 perf_event__process_auxtrace(struct perf_tool *tool,
 	if (!session->auxtrace || event->header.type != PERF_RECORD_AUXTRACE)
 		return -EINVAL;
 
-	err = session->auxtrace->process_auxtrace_event(session, event, tool);
+	err = session->auxtrace->process_auxtrace_event(session, event, session->tool);
 	if (err < 0)
 		return err;
 
@@ -1185,9 +1183,8 @@ void events_stats__auxtrace_error_warn(const struct events_stats *stats)
 	}
 }
 
-int perf_event__process_auxtrace_error(struct perf_tool *tool __maybe_unused,
-				       union perf_event *event,
-				       struct perf_session *session)
+int perf_event__process_auxtrace_error(struct perf_session *session,
+				       union perf_event *event)
 {
 	if (auxtrace__dont_decode(session))
 		return 0;
@@ -1196,11 +1193,12 @@ int perf_event__process_auxtrace_error(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-static int __auxtrace_mmap__read(struct auxtrace_mmap *mm,
+static int __auxtrace_mmap__read(struct perf_mmap *map,
 				 struct auxtrace_record *itr,
 				 struct perf_tool *tool, process_auxtrace_t fn,
 				 bool snapshot, size_t snapshot_size)
 {
+	struct auxtrace_mmap *mm = &map->auxtrace_mmap;
 	u64 head, old = mm->prev, offset, ref;
 	unsigned char *data = mm->base;
 	size_t size, head_off, old_off, len1, len2, padding;
@@ -1287,7 +1285,7 @@ static int __auxtrace_mmap__read(struct auxtrace_mmap *mm,
 	ev.auxtrace.tid = mm->tid;
 	ev.auxtrace.cpu = mm->cpu;
 
-	if (fn(tool, &ev, data1, len1, data2, len2))
+	if (fn(tool, map, &ev, data1, len1, data2, len2))
 		return -1;
 
 	mm->prev = head;
@@ -1306,18 +1304,18 @@ static int __auxtrace_mmap__read(struct auxtrace_mmap *mm,
 	return 1;
 }
 
-int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
+int auxtrace_mmap__read(struct perf_mmap *map, struct auxtrace_record *itr,
 			struct perf_tool *tool, process_auxtrace_t fn)
 {
-	return __auxtrace_mmap__read(mm, itr, tool, fn, false, 0);
+	return __auxtrace_mmap__read(map, itr, tool, fn, false, 0);
 }
 
-int auxtrace_mmap__read_snapshot(struct auxtrace_mmap *mm,
+int auxtrace_mmap__read_snapshot(struct perf_mmap *map,
 				 struct auxtrace_record *itr,
 				 struct perf_tool *tool, process_auxtrace_t fn,
 				 size_t snapshot_size)
 {
-	return __auxtrace_mmap__read(mm, itr, tool, fn, true, snapshot_size);
+	return __auxtrace_mmap__read(map, itr, tool, fn, true, snapshot_size);
 }
 
 /**
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 71fc3bd74299..d88f6e9eb461 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -23,6 +23,7 @@
 #include <linux/list.h>
 #include <linux/perf_event.h>
 #include <linux/types.h>
+#include <asm/bitsperlong.h>
 
 #include "../perf.h"
 #include "event.h"
@@ -33,6 +34,7 @@ union perf_event;
 struct perf_session;
 struct perf_evlist;
 struct perf_tool;
+struct perf_mmap;
 struct option;
 struct record_opts;
 struct auxtrace_info_event;
@@ -434,13 +436,14 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
 				   bool per_cpu);
 
 typedef int (*process_auxtrace_t)(struct perf_tool *tool,
+				  struct perf_mmap *map,
 				  union perf_event *event, void *data1,
 				  size_t len1, void *data2, size_t len2);
 
-int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
+int auxtrace_mmap__read(struct perf_mmap *map, struct auxtrace_record *itr,
 			struct perf_tool *tool, process_auxtrace_t fn);
 
-int auxtrace_mmap__read_snapshot(struct auxtrace_mmap *mm,
+int auxtrace_mmap__read_snapshot(struct perf_mmap *map,
 				 struct auxtrace_record *itr,
 				 struct perf_tool *tool, process_auxtrace_t fn,
 				 size_t snapshot_size);
@@ -517,15 +520,12 @@ int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
 					 struct perf_tool *tool,
 					 struct perf_session *session,
 					 perf_event__handler_t process);
-int perf_event__process_auxtrace_info(struct perf_tool *tool,
-				      union perf_event *event,
-				      struct perf_session *session);
-s64 perf_event__process_auxtrace(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session);
-int perf_event__process_auxtrace_error(struct perf_tool *tool,
-				       union perf_event *event,
-				       struct perf_session *session);
+int perf_event__process_auxtrace_info(struct perf_session *session,
+				      union perf_event *event);
+s64 perf_event__process_auxtrace(struct perf_session *session,
+				 union perf_event *event);
+int perf_event__process_auxtrace_error(struct perf_session *session,
+				       union perf_event *event);
 int itrace_parse_synth_opts(const struct option *opt, const char *str,
 			    int unset);
 void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts);
@@ -577,6 +577,23 @@ static inline void auxtrace__free(struct perf_session *session)
 	return session->auxtrace->free(session);
 }
 
+#define ITRACE_HELP \
+"				i:	    		synthesize instructions events\n"		\
+"				b:	    		synthesize branches events\n"		\
+"				c:	    		synthesize branches events (calls only)\n"	\
+"				r:	    		synthesize branches events (returns only)\n" \
+"				x:	    		synthesize transactions events\n"		\
+"				w:	    		synthesize ptwrite events\n"		\
+"				p:	    		synthesize power events\n"			\
+"				e:	    		synthesize error events\n"			\
+"				d:	    		create a debug log\n"			\
+"				g[len]:     		synthesize a call chain (use with i or x)\n" \
+"				l[len]:     		synthesize last branch entries (use with i or x)\n" \
+"				sNUMBER:    		skip initial number of events\n"		\
+"				PERIOD[ns|us|ms|i|t]:   specify period to sample stream\n" \
+"				concatenate multiple options. Default is ibxwpe or cewp\n"
+
+
 #else
 
 static inline struct auxtrace_record *
@@ -717,6 +734,8 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
 				   struct perf_evlist *evlist, int idx,
 				   bool per_cpu);
 
+#define ITRACE_HELP ""
+
 #endif
 
 #endif
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 47aac41349a2..f9ae1a993806 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -1615,7 +1615,7 @@ struct perf_evsel *bpf__setup_output_event(struct perf_evlist *evlist, const cha
 int bpf__setup_stdout(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel = bpf__setup_output_event(evlist, "__bpf_stdout__");
-	return IS_ERR(evsel) ? PTR_ERR(evsel) : 0;
+	return PTR_ERR_OR_ZERO(evsel);
 }
 
 #define ERRNO_OFFSET(e)		((e) - __BPF_LOADER_ERRNO__START)
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index abd38abf1d91..2a36fab76994 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -182,20 +182,20 @@ err_put_field:
 }
 
 static struct bt_ctf_field_type*
-get_tracepoint_field_type(struct ctf_writer *cw, struct format_field *field)
+get_tracepoint_field_type(struct ctf_writer *cw, struct tep_format_field *field)
 {
 	unsigned long flags = field->flags;
 
-	if (flags & FIELD_IS_STRING)
+	if (flags & TEP_FIELD_IS_STRING)
 		return cw->data.string;
 
-	if (!(flags & FIELD_IS_SIGNED)) {
+	if (!(flags & TEP_FIELD_IS_SIGNED)) {
 		/* unsigned long are mostly pointers */
-		if (flags & FIELD_IS_LONG || flags & FIELD_IS_POINTER)
+		if (flags & TEP_FIELD_IS_LONG || flags & TEP_FIELD_IS_POINTER)
 			return cw->data.u64_hex;
 	}
 
-	if (flags & FIELD_IS_SIGNED) {
+	if (flags & TEP_FIELD_IS_SIGNED) {
 		if (field->size == 8)
 			return cw->data.s64;
 		else
@@ -287,7 +287,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 				      struct bt_ctf_event_class *event_class,
 				      struct bt_ctf_event *event,
 				      struct perf_sample *sample,
-				      struct format_field *fmtf)
+				      struct tep_format_field *fmtf)
 {
 	struct bt_ctf_field_type *type;
 	struct bt_ctf_field *array_field;
@@ -304,10 +304,10 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 	name = fmtf->alias;
 	offset = fmtf->offset;
 	len = fmtf->size;
-	if (flags & FIELD_IS_STRING)
-		flags &= ~FIELD_IS_ARRAY;
+	if (flags & TEP_FIELD_IS_STRING)
+		flags &= ~TEP_FIELD_IS_ARRAY;
 
-	if (flags & FIELD_IS_DYNAMIC) {
+	if (flags & TEP_FIELD_IS_DYNAMIC) {
 		unsigned long long tmp_val;
 
 		tmp_val = tep_read_number(fmtf->event->pevent,
@@ -317,7 +317,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 		offset &= 0xffff;
 	}
 
-	if (flags & FIELD_IS_ARRAY) {
+	if (flags & TEP_FIELD_IS_ARRAY) {
 
 		type = bt_ctf_event_class_get_field_by_name(
 				event_class, name);
@@ -338,7 +338,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 	type = get_tracepoint_field_type(cw, fmtf);
 
 	for (i = 0; i < n_items; i++) {
-		if (flags & FIELD_IS_ARRAY)
+		if (flags & TEP_FIELD_IS_ARRAY)
 			field = bt_ctf_field_array_get_field(array_field, i);
 		else
 			field = bt_ctf_field_create(type);
@@ -348,7 +348,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 			return -1;
 		}
 
-		if (flags & FIELD_IS_STRING)
+		if (flags & TEP_FIELD_IS_STRING)
 			ret = string_set_value(field, data + offset + i * len);
 		else {
 			unsigned long long value_int;
@@ -357,7 +357,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 					fmtf->event->pevent,
 					data + offset + i * len, len);
 
-			if (!(flags & FIELD_IS_SIGNED))
+			if (!(flags & TEP_FIELD_IS_SIGNED))
 				ret = bt_ctf_field_unsigned_integer_set_value(
 						field, value_int);
 			else
@@ -369,7 +369,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 			pr_err("failed to set file value %s\n", name);
 			goto err_put_field;
 		}
-		if (!(flags & FIELD_IS_ARRAY)) {
+		if (!(flags & TEP_FIELD_IS_ARRAY)) {
 			ret = bt_ctf_event_set_payload(event, name, field);
 			if (ret) {
 				pr_err("failed to set payload %s\n", name);
@@ -378,7 +378,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 		}
 		bt_ctf_field_put(field);
 	}
-	if (flags & FIELD_IS_ARRAY) {
+	if (flags & TEP_FIELD_IS_ARRAY) {
 		ret = bt_ctf_event_set_payload(event, name, array_field);
 		if (ret) {
 			pr_err("Failed add payload array %s\n", name);
@@ -396,10 +396,10 @@ err_put_field:
 static int add_tracepoint_fields_values(struct ctf_writer *cw,
 					struct bt_ctf_event_class *event_class,
 					struct bt_ctf_event *event,
-					struct format_field *fields,
+					struct tep_format_field *fields,
 					struct perf_sample *sample)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 	int ret;
 
 	for (field = fields; field; field = field->next) {
@@ -417,8 +417,8 @@ static int add_tracepoint_values(struct ctf_writer *cw,
 				 struct perf_evsel *evsel,
 				 struct perf_sample *sample)
 {
-	struct format_field *common_fields = evsel->tp_format->format.common_fields;
-	struct format_field *fields        = evsel->tp_format->format.fields;
+	struct tep_format_field *common_fields = evsel->tp_format->format.common_fields;
+	struct tep_format_field *fields        = evsel->tp_format->format.fields;
 	int ret;
 
 	ret = add_tracepoint_fields_values(cw, event_class, event,
@@ -970,7 +970,7 @@ out:
 
 static int event_class_add_field(struct bt_ctf_event_class *event_class,
 		struct bt_ctf_field_type *type,
-		struct format_field *field)
+		struct tep_format_field *field)
 {
 	struct bt_ctf_field_type *t = NULL;
 	char *name;
@@ -1009,10 +1009,10 @@ static int event_class_add_field(struct bt_ctf_event_class *event_class,
 }
 
 static int add_tracepoint_fields_types(struct ctf_writer *cw,
-				       struct format_field *fields,
+				       struct tep_format_field *fields,
 				       struct bt_ctf_event_class *event_class)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 	int ret;
 
 	for (field = fields; field; field = field->next) {
@@ -1030,15 +1030,15 @@ static int add_tracepoint_fields_types(struct ctf_writer *cw,
 		 * type and don't care that it is an array. What we don't
 		 * support is an array of strings.
 		 */
-		if (flags & FIELD_IS_STRING)
-			flags &= ~FIELD_IS_ARRAY;
+		if (flags & TEP_FIELD_IS_STRING)
+			flags &= ~TEP_FIELD_IS_ARRAY;
 
-		if (flags & FIELD_IS_ARRAY)
+		if (flags & TEP_FIELD_IS_ARRAY)
 			type = bt_ctf_field_type_array_create(type, field->arraylen);
 
 		ret = event_class_add_field(event_class, type, field);
 
-		if (flags & FIELD_IS_ARRAY)
+		if (flags & TEP_FIELD_IS_ARRAY)
 			bt_ctf_field_type_put(type);
 
 		if (ret) {
@@ -1055,8 +1055,8 @@ static int add_tracepoint_types(struct ctf_writer *cw,
 				struct perf_evsel *evsel,
 				struct bt_ctf_event_class *class)
 {
-	struct format_field *common_fields = evsel->tp_format->format.common_fields;
-	struct format_field *fields        = evsel->tp_format->format.fields;
+	struct tep_format_field *common_fields = evsel->tp_format->format.common_fields;
+	struct tep_format_field *fields        = evsel->tp_format->format.fields;
 	int ret;
 
 	ret = add_tracepoint_fields_types(cw, common_fields, class);
@@ -1578,7 +1578,7 @@ int bt_convert__perf2ctf(const char *input, const char *path,
 {
 	struct perf_session *session;
 	struct perf_data data = {
-		.file.path = input,
+		.file      = { .path = input, .fd = -1 },
 		.mode      = PERF_DATA_MODE_READ,
 		.force     = opts->force,
 	};
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index 7123746edcf4..69fbb0a72d0c 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -463,6 +463,28 @@ int db_export__branch_types(struct db_export *dbe)
 		if (err)
 			break;
 	}
+
+	/* Add trace begin / end variants */
+	for (i = 0; branch_types[i].name ; i++) {
+		const char *name = branch_types[i].name;
+		u32 type = branch_types[i].branch_type;
+		char buf[64];
+
+		if (type == PERF_IP_FLAG_BRANCH ||
+		    (type & (PERF_IP_FLAG_TRACE_BEGIN | PERF_IP_FLAG_TRACE_END)))
+			continue;
+
+		snprintf(buf, sizeof(buf), "trace begin / %s", name);
+		err = db_export__branch_type(dbe, type | PERF_IP_FLAG_TRACE_BEGIN, buf);
+		if (err)
+			break;
+
+		snprintf(buf, sizeof(buf), "%s / trace end", name);
+		err = db_export__branch_type(dbe, type | PERF_IP_FLAG_TRACE_END, buf);
+		if (err)
+			break;
+	}
+
 	return err;
 }
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index e596ae358c4d..29d7b97f66fb 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2685,7 +2685,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 	return 0;
 }
 
-struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name)
+struct tep_format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name)
 {
 	return tep_find_field(evsel->tp_format, name);
 }
@@ -2693,7 +2693,7 @@ struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *nam
 void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample,
 			 const char *name)
 {
-	struct format_field *field = perf_evsel__field(evsel, name);
+	struct tep_format_field *field = perf_evsel__field(evsel, name);
 	int offset;
 
 	if (!field)
@@ -2701,7 +2701,7 @@ void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample,
 
 	offset = field->offset;
 
-	if (field->flags & FIELD_IS_DYNAMIC) {
+	if (field->flags & TEP_FIELD_IS_DYNAMIC) {
 		offset = *(int *)(sample->raw_data + field->offset);
 		offset &= 0xffff;
 	}
@@ -2709,7 +2709,7 @@ void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample,
 	return sample->raw_data + offset;
 }
 
-u64 format_field__intval(struct format_field *field, struct perf_sample *sample,
+u64 format_field__intval(struct tep_format_field *field, struct perf_sample *sample,
 			 bool needs_swap)
 {
 	u64 value;
@@ -2751,7 +2751,7 @@ u64 format_field__intval(struct format_field *field, struct perf_sample *sample,
 u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
 		       const char *name)
 {
-	struct format_field *field = perf_evsel__field(evsel, name);
+	struct tep_format_field *field = perf_evsel__field(evsel, name);
 
 	if (!field)
 		return 0;
@@ -2943,3 +2943,32 @@ struct perf_env *perf_evsel__env(struct perf_evsel *evsel)
 		return evsel->evlist->env;
 	return NULL;
 }
+
+static int store_evsel_ids(struct perf_evsel *evsel, struct perf_evlist *evlist)
+{
+	int cpu, thread;
+
+	for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
+		for (thread = 0; thread < xyarray__max_y(evsel->fd);
+		     thread++) {
+			int fd = FD(evsel, cpu, thread);
+
+			if (perf_evlist__id_add_fd(evlist, evsel,
+						   cpu, thread, fd) < 0)
+				return -1;
+		}
+	}
+
+	return 0;
+}
+
+int perf_evsel__store_ids(struct perf_evsel *evsel, struct perf_evlist *evlist)
+{
+	struct cpu_map *cpus = evsel->cpus;
+	struct thread_map *threads = evsel->threads;
+
+	if (perf_evsel__alloc_id(evsel, cpus->nr, threads->nr))
+		return -ENOMEM;
+
+	return store_evsel_ids(evsel, evlist);
+}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 163c960614d3..4107c39f4a54 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -102,7 +102,7 @@ struct perf_evsel {
 	char			*name;
 	double			scale;
 	const char		*unit;
-	struct event_format	*tp_format;
+	struct tep_event_format	*tp_format;
 	off_t			id_offset;
 	struct perf_stat_evsel  *stats;
 	void			*priv;
@@ -211,7 +211,7 @@ static inline struct perf_evsel *perf_evsel__newtp(const char *sys, const char *
 
 struct perf_evsel *perf_evsel__new_cycles(bool precise);
 
-struct event_format *event_format__new(const char *sys, const char *name);
+struct tep_event_format *event_format__new(const char *sys, const char *name);
 
 void perf_evsel__init(struct perf_evsel *evsel,
 		      struct perf_event_attr *attr, int idx);
@@ -296,11 +296,11 @@ static inline char *perf_evsel__strval(struct perf_evsel *evsel,
 	return perf_evsel__rawptr(evsel, sample, name);
 }
 
-struct format_field;
+struct tep_format_field;
 
-u64 format_field__intval(struct format_field *field, struct perf_sample *sample, bool needs_swap);
+u64 format_field__intval(struct tep_format_field *field, struct perf_sample *sample, bool needs_swap);
 
-struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name);
+struct tep_format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name);
 
 #define perf_evsel__match(evsel, t, c)		\
 	(evsel->attr.type == PERF_TYPE_##t &&	\
@@ -481,4 +481,5 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 
 struct perf_env *perf_evsel__env(struct perf_evsel *evsel);
 
+int perf_evsel__store_ids(struct perf_evsel *evsel, struct perf_evlist *evlist);
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c
index 06dfb027879d..0d0a4c6f368b 100644
--- a/tools/perf/util/evsel_fprintf.c
+++ b/tools/perf/util/evsel_fprintf.c
@@ -73,7 +73,7 @@ int perf_evsel__fprintf(struct perf_evsel *evsel,
 	}
 
 	if (details->trace_fields) {
-		struct format_field *field;
+		struct tep_format_field *field;
 
 		if (evsel->attr.type != PERF_TYPE_TRACEPOINT) {
 			printed += comma_fprintf(fp, &first, " (not a tracepoint)");
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 3cadc252dd89..1ec1d9bc2d63 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -3206,7 +3206,7 @@ static int read_attr(int fd, struct perf_header *ph,
 static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel,
 						struct tep_handle *pevent)
 {
-	struct event_format *event;
+	struct tep_event_format *event;
 	char bf[128];
 
 	/* already prepared */
@@ -3448,10 +3448,10 @@ int perf_event__synthesize_features(struct perf_tool *tool,
 	return ret;
 }
 
-int perf_event__process_feature(struct perf_tool *tool,
-				union perf_event *event,
-				struct perf_session *session __maybe_unused)
+int perf_event__process_feature(struct perf_session *session,
+				union perf_event *event)
 {
+	struct perf_tool *tool = session->tool;
 	struct feat_fd ff = { .fd = 0 };
 	struct feature_event *fe = (struct feature_event *)event;
 	int type = fe->header.type;
@@ -3637,13 +3637,13 @@ size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp)
 }
 
 int perf_event__synthesize_attrs(struct perf_tool *tool,
-				   struct perf_session *session,
-				   perf_event__handler_t process)
+				 struct perf_evlist *evlist,
+				 perf_event__handler_t process)
 {
 	struct perf_evsel *evsel;
 	int err = 0;
 
-	evlist__for_each_entry(session->evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		err = perf_event__synthesize_attr(tool, &evsel->attr, evsel->ids,
 						  evsel->id, process);
 		if (err) {
@@ -3856,9 +3856,8 @@ int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd,
 	return aligned_size;
 }
 
-int perf_event__process_tracing_data(struct perf_tool *tool __maybe_unused,
-				     union perf_event *event,
-				     struct perf_session *session)
+int perf_event__process_tracing_data(struct perf_session *session,
+				     union perf_event *event)
 {
 	ssize_t size_read, padding, size = event->tracing_data.size;
 	int fd = perf_data__fd(session->data);
@@ -3924,9 +3923,8 @@ int perf_event__synthesize_build_id(struct perf_tool *tool,
 	return err;
 }
 
-int perf_event__process_build_id(struct perf_tool *tool __maybe_unused,
-				 union perf_event *event,
-				 struct perf_session *session)
+int perf_event__process_build_id(struct perf_session *session,
+				 union perf_event *event)
 {
 	__event_process_build_id(&event->build_id,
 				 event->build_id.filename,
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 6d7fe44aadc0..e17903caa71d 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -116,15 +116,14 @@ int perf_event__synthesize_extra_attr(struct perf_tool *tool,
 				      perf_event__handler_t process,
 				      bool is_pipe);
 
-int perf_event__process_feature(struct perf_tool *tool,
-				union perf_event *event,
-				struct perf_session *session);
+int perf_event__process_feature(struct perf_session *session,
+				union perf_event *event);
 
 int perf_event__synthesize_attr(struct perf_tool *tool,
 				struct perf_event_attr *attr, u32 ids, u64 *id,
 				perf_event__handler_t process);
 int perf_event__synthesize_attrs(struct perf_tool *tool,
-				 struct perf_session *session,
+				 struct perf_evlist *evlist,
 				 perf_event__handler_t process);
 int perf_event__synthesize_event_update_unit(struct perf_tool *tool,
 					     struct perf_evsel *evsel,
@@ -148,17 +147,15 @@ size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp);
 int perf_event__synthesize_tracing_data(struct perf_tool *tool,
 					int fd, struct perf_evlist *evlist,
 					perf_event__handler_t process);
-int perf_event__process_tracing_data(struct perf_tool *tool,
-				     union perf_event *event,
-				     struct perf_session *session);
+int perf_event__process_tracing_data(struct perf_session *session,
+				     union perf_event *event);
 
 int perf_event__synthesize_build_id(struct perf_tool *tool,
 				    struct dso *pos, u16 misc,
 				    perf_event__handler_t process,
 				    struct machine *machine);
-int perf_event__process_build_id(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session);
+int perf_event__process_build_id(struct perf_session *session,
+				 union perf_event *event);
 bool is_perf_magic(u64 magic);
 
 #define NAME_ALIGN 64
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index d404bed7003a..58f6a9ceb590 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -1165,7 +1165,7 @@ static int intel_pt_walk_tip(struct intel_pt_decoder *decoder)
 		decoder->pge = false;
 		decoder->continuous_period = false;
 		decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
-		decoder->state.to_ip = 0;
+		decoder->state.type |= INTEL_PT_TRACE_END;
 		return 0;
 	}
 	if (err == INTEL_PT_RETURN)
@@ -1179,9 +1179,13 @@ static int intel_pt_walk_tip(struct intel_pt_decoder *decoder)
 			decoder->continuous_period = false;
 			decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
 			decoder->state.from_ip = decoder->ip;
-			decoder->state.to_ip = 0;
-			if (decoder->packet.count != 0)
+			if (decoder->packet.count == 0) {
+				decoder->state.to_ip = 0;
+			} else {
+				decoder->state.to_ip = decoder->last_ip;
 				decoder->ip = decoder->last_ip;
+			}
+			decoder->state.type |= INTEL_PT_TRACE_END;
 		} else {
 			decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
 			decoder->state.from_ip = decoder->ip;
@@ -1208,7 +1212,8 @@ static int intel_pt_walk_tip(struct intel_pt_decoder *decoder)
 			decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
 			decoder->ip = to_ip;
 			decoder->state.from_ip = decoder->ip;
-			decoder->state.to_ip = 0;
+			decoder->state.to_ip = to_ip;
+			decoder->state.type |= INTEL_PT_TRACE_END;
 			return 0;
 		}
 		intel_pt_log_at("ERROR: Conditional branch when expecting indirect branch",
@@ -1640,14 +1645,15 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder)
 
 		case INTEL_PT_TIP_PGD:
 			decoder->state.from_ip = decoder->ip;
-			decoder->state.to_ip = 0;
-			if (decoder->packet.count != 0) {
+			if (decoder->packet.count == 0) {
+				decoder->state.to_ip = 0;
+			} else {
 				intel_pt_set_ip(decoder);
-				intel_pt_log("Omitting PGD ip " x64_fmt "\n",
-					     decoder->ip);
+				decoder->state.to_ip = decoder->ip;
 			}
 			decoder->pge = false;
 			decoder->continuous_period = false;
+			decoder->state.type |= INTEL_PT_TRACE_END;
 			return 0;
 
 		case INTEL_PT_TIP_PGE:
@@ -1661,6 +1667,7 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder)
 				intel_pt_set_ip(decoder);
 				decoder->state.to_ip = decoder->ip;
 			}
+			decoder->state.type |= INTEL_PT_TRACE_BEGIN;
 			return 0;
 
 		case INTEL_PT_TIP:
@@ -1739,6 +1746,7 @@ next:
 			intel_pt_set_ip(decoder);
 			decoder->state.from_ip = 0;
 			decoder->state.to_ip = decoder->ip;
+			decoder->state.type |= INTEL_PT_TRACE_BEGIN;
 			return 0;
 		}
 
@@ -2077,9 +2085,13 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
 			decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD;
 			if (intel_pt_have_ip(decoder))
 				intel_pt_set_ip(decoder);
-			if (decoder->ip)
-				return 0;
-			break;
+			if (!decoder->ip)
+				break;
+			if (decoder->packet.type == INTEL_PT_TIP_PGE)
+				decoder->state.type |= INTEL_PT_TRACE_BEGIN;
+			if (decoder->packet.type == INTEL_PT_TIP_PGD)
+				decoder->state.type |= INTEL_PT_TRACE_END;
+			return 0;
 
 		case INTEL_PT_FUP:
 			if (intel_pt_have_ip(decoder))
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
index 51c18d67f4ca..ed088d4726ba 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
@@ -37,6 +37,8 @@ enum intel_pt_sample_type {
 	INTEL_PT_EX_STOP	= 1 << 6,
 	INTEL_PT_PWR_EXIT	= 1 << 7,
 	INTEL_PT_CBR_CHG	= 1 << 8,
+	INTEL_PT_TRACE_BEGIN	= 1 << 9,
+	INTEL_PT_TRACE_END	= 1 << 10,
 };
 
 enum intel_pt_period_type {
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index aec68908d604..48c1d415c6b0 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -908,6 +908,11 @@ static void intel_pt_sample_flags(struct intel_pt_queue *ptq)
 		ptq->insn_len = ptq->state->insn_len;
 		memcpy(ptq->insn, ptq->state->insn, INTEL_PT_INSN_BUF_SZ);
 	}
+
+	if (ptq->state->type & INTEL_PT_TRACE_BEGIN)
+		ptq->flags |= PERF_IP_FLAG_TRACE_BEGIN;
+	if (ptq->state->type & INTEL_PT_TRACE_END)
+		ptq->flags |= PERF_IP_FLAG_TRACE_END;
 }
 
 static int intel_pt_setup_queue(struct intel_pt *pt,
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 19262f98cd4e..5b0b60f00275 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -19,7 +19,7 @@
 #define CLANG_BPF_CMD_DEFAULT_TEMPLATE				\
 		"$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
 		"-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE "	\
-		"$CLANG_OPTIONS $KERNEL_INC_OPTIONS $PERF_BPF_INC_OPTIONS " \
+		"$CLANG_OPTIONS $PERF_BPF_INC_OPTIONS $KERNEL_INC_OPTIONS " \
 		"-Wno-unused-value -Wno-pointer-sign "		\
 		"-working-directory $WORKING_DIR "		\
 		"-c \"$CLANG_SOURCE\" -target bpf $CLANG_EMIT_LLVM -O2 -o - $LLVM_OPTIONS_PIPE"
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 6a6929f208b4..354e54550d2b 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -320,12 +320,11 @@ int map__load(struct map *map)
 			build_id__sprintf(map->dso->build_id,
 					  sizeof(map->dso->build_id),
 					  sbuild_id);
-			pr_warning("%s with build id %s not found",
-				   name, sbuild_id);
+			pr_debug("%s with build id %s not found", name, sbuild_id);
 		} else
-			pr_warning("Failed to open %s", name);
+			pr_debug("Failed to open %s", name);
 
-		pr_warning(", continuing without symbols\n");
+		pr_debug(", continuing without symbols\n");
 		return -1;
 	} else if (nr == 0) {
 #ifdef HAVE_LIBELF_SUPPORT
@@ -334,12 +333,11 @@ int map__load(struct map *map)
 
 		if (len > sizeof(DSO__DELETED) &&
 		    strcmp(name + real_len + 1, DSO__DELETED) == 0) {
-			pr_warning("%.*s was updated (is prelink enabled?). "
+			pr_debug("%.*s was updated (is prelink enabled?). "
 				"Restart the long running apps that use it!\n",
 				   (int)real_len, name);
 		} else {
-			pr_warning("no symbols found in %s, maybe install "
-				   "a debug package?\n", name);
+			pr_debug("no symbols found in %s, maybe install a debug package?\n", name);
 		}
 #endif
 		return -1;
@@ -712,8 +710,7 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp
 		if (verbose >= 2) {
 
 			if (use_browser) {
-				pr_warning("overlapping maps in %s "
-					   "(disable tui for more info)\n",
+				pr_debug("overlapping maps in %s (disable tui for more info)\n",
 					   map->dso->name);
 			} else {
 				fputs("overlapping maps:\n", fp);
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 215f69f41672..cdb95b3a1213 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -281,7 +281,7 @@ int perf_mmap__read_init(struct perf_mmap *map)
 }
 
 int perf_mmap__push(struct perf_mmap *md, void *to,
-		    int push(void *to, void *buf, size_t size))
+		    int push(struct perf_mmap *map, void *to, void *buf, size_t size))
 {
 	u64 head = perf_mmap__read_head(md);
 	unsigned char *data = md->base + page_size;
@@ -300,7 +300,7 @@ int perf_mmap__push(struct perf_mmap *md, void *to,
 		size = md->mask + 1 - (md->start & md->mask);
 		md->start += size;
 
-		if (push(to, buf, size) < 0) {
+		if (push(md, to, buf, size) < 0) {
 			rc = -1;
 			goto out;
 		}
@@ -310,7 +310,7 @@ int perf_mmap__push(struct perf_mmap *md, void *to,
 	size = md->end - md->start;
 	md->start += size;
 
-	if (push(to, buf, size) < 0) {
+	if (push(md, to, buf, size) < 0) {
 		rc = -1;
 		goto out;
 	}
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index 05a6d47c7956..e603314dc792 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -93,7 +93,7 @@ union perf_event *perf_mmap__read_forward(struct perf_mmap *map);
 union perf_event *perf_mmap__read_event(struct perf_mmap *map);
 
 int perf_mmap__push(struct perf_mmap *md, void *to,
-		    int push(void *to, void *buf, size_t size));
+		    int push(struct perf_mmap *map, void *to, void *buf, size_t size));
 
 size_t perf_mmap__mmap_len(struct perf_mmap *map);
 
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
index bad9e0296e9a..1904e7f6ec84 100644
--- a/tools/perf/util/ordered-events.c
+++ b/tools/perf/util/ordered-events.c
@@ -80,14 +80,20 @@ static union perf_event *dup_event(struct ordered_events *oe,
 	return oe->copy_on_queue ? __dup_event(oe, event) : event;
 }
 
-static void free_dup_event(struct ordered_events *oe, union perf_event *event)
+static void __free_dup_event(struct ordered_events *oe, union perf_event *event)
 {
-	if (event && oe->copy_on_queue) {
+	if (event) {
 		oe->cur_alloc_size -= event->header.size;
 		free(event);
 	}
 }
 
+static void free_dup_event(struct ordered_events *oe, union perf_event *event)
+{
+	if (oe->copy_on_queue)
+		__free_dup_event(oe, event);
+}
+
 #define MAX_SAMPLE_BUFFER	(64 * 1024 / sizeof(struct ordered_event))
 static struct ordered_event *alloc_event(struct ordered_events *oe,
 					 union perf_event *event)
@@ -95,21 +101,49 @@ static struct ordered_event *alloc_event(struct ordered_events *oe,
 	struct list_head *cache = &oe->cache;
 	struct ordered_event *new = NULL;
 	union perf_event *new_event;
+	size_t size;
 
 	new_event = dup_event(oe, event);
 	if (!new_event)
 		return NULL;
 
+	/*
+	 * We maintain the following scheme of buffers for ordered
+	 * event allocation:
+	 *
+	 *   to_free list -> buffer1 (64K)
+	 *                   buffer2 (64K)
+	 *                   ...
+	 *
+	 * Each buffer keeps an array of ordered events objects:
+	 *    buffer -> event[0]
+	 *              event[1]
+	 *              ...
+	 *
+	 * Each allocated ordered event is linked to one of
+	 * following lists:
+	 *   - time ordered list 'events'
+	 *   - list of currently removed events 'cache'
+	 *
+	 * Allocation of the ordered event uses the following order
+	 * to get the memory:
+	 *   - use recently removed object from 'cache' list
+	 *   - use available object in current allocation buffer
+	 *   - allocate new buffer if the current buffer is full
+	 *
+	 * Removal of ordered event object moves it from events to
+	 * the cache list.
+	 */
+	size = sizeof(*oe->buffer) + MAX_SAMPLE_BUFFER * sizeof(*new);
+
 	if (!list_empty(cache)) {
 		new = list_entry(cache->next, struct ordered_event, list);
 		list_del(&new->list);
 	} else if (oe->buffer) {
-		new = oe->buffer + oe->buffer_idx;
+		new = &oe->buffer->event[oe->buffer_idx];
 		if (++oe->buffer_idx == MAX_SAMPLE_BUFFER)
 			oe->buffer = NULL;
-	} else if (oe->cur_alloc_size < oe->max_alloc_size) {
-		size_t size = MAX_SAMPLE_BUFFER * sizeof(*new);
-
+	} else if ((oe->cur_alloc_size + size) < oe->max_alloc_size) {
 		oe->buffer = malloc(size);
 		if (!oe->buffer) {
 			free_dup_event(oe, new_event);
@@ -122,11 +156,11 @@ static struct ordered_event *alloc_event(struct ordered_events *oe,
 		oe->cur_alloc_size += size;
 		list_add(&oe->buffer->list, &oe->to_free);
 
-		/* First entry is abused to maintain the to_free list. */
-		oe->buffer_idx = 2;
-		new = oe->buffer + 1;
+		oe->buffer_idx = 1;
+		new = &oe->buffer->event[0];
 	} else {
 		pr("allocation limit reached %" PRIu64 "B\n", oe->max_alloc_size);
+		return NULL;
 	}
 
 	new->event = new_event;
@@ -300,15 +334,38 @@ void ordered_events__init(struct ordered_events *oe, ordered_events__deliver_t d
 	oe->deliver	   = deliver;
 }
 
+static void
+ordered_events_buffer__free(struct ordered_events_buffer *buffer,
+			    unsigned int max, struct ordered_events *oe)
+{
+	if (oe->copy_on_queue) {
+		unsigned int i;
+
+		for (i = 0; i < max; i++)
+			__free_dup_event(oe, buffer->event[i].event);
+	}
+
+	free(buffer);
+}
+
 void ordered_events__free(struct ordered_events *oe)
 {
-	while (!list_empty(&oe->to_free)) {
-		struct ordered_event *event;
+	struct ordered_events_buffer *buffer, *tmp;
 
-		event = list_entry(oe->to_free.next, struct ordered_event, list);
-		list_del(&event->list);
-		free_dup_event(oe, event->event);
-		free(event);
+	if (list_empty(&oe->to_free))
+		return;
+
+	/*
+	 * Current buffer might not have all the events allocated
+	 * yet, we need to free only allocated ones ...
+	 */
+	list_del(&oe->buffer->list);
+	ordered_events_buffer__free(oe->buffer, oe->buffer_idx, oe);
+
+	/* ... and continue with the rest */
+	list_for_each_entry_safe(buffer, tmp, &oe->to_free, list) {
+		list_del(&buffer->list);
+		ordered_events_buffer__free(buffer, MAX_SAMPLE_BUFFER, oe);
 	}
 }
 
diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h
index 8c7a2948593e..1338d5c345dc 100644
--- a/tools/perf/util/ordered-events.h
+++ b/tools/perf/util/ordered-events.h
@@ -25,23 +25,28 @@ struct ordered_events;
 typedef int (*ordered_events__deliver_t)(struct ordered_events *oe,
 					 struct ordered_event *event);
 
+struct ordered_events_buffer {
+	struct list_head	list;
+	struct ordered_event	event[0];
+};
+
 struct ordered_events {
-	u64			last_flush;
-	u64			next_flush;
-	u64			max_timestamp;
-	u64			max_alloc_size;
-	u64			cur_alloc_size;
-	struct list_head	events;
-	struct list_head	cache;
-	struct list_head	to_free;
-	struct ordered_event	*buffer;
-	struct ordered_event	*last;
-	ordered_events__deliver_t deliver;
-	int			buffer_idx;
-	unsigned int		nr_events;
-	enum oe_flush		last_flush_type;
-	u32			nr_unordered_events;
-	bool                    copy_on_queue;
+	u64				 last_flush;
+	u64				 next_flush;
+	u64				 max_timestamp;
+	u64				 max_alloc_size;
+	u64				 cur_alloc_size;
+	struct list_head		 events;
+	struct list_head		 cache;
+	struct list_head		 to_free;
+	struct ordered_events_buffer	*buffer;
+	struct ordered_event		*last;
+	ordered_events__deliver_t	 deliver;
+	int				 buffer_idx;
+	unsigned int			 nr_events;
+	enum oe_flush			 last_flush_type;
+	u32				 nr_unordered_events;
+	bool				 copy_on_queue;
 };
 
 int ordered_events__queue(struct ordered_events *oe, union perf_event *event,
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index ce501ba14b08..50150dfc0cdf 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -340,7 +340,7 @@ static bool is_tracepoint(struct pyrf_event *pevent)
 }
 
 static PyObject*
-tracepoint_field(struct pyrf_event *pe, struct format_field *field)
+tracepoint_field(struct pyrf_event *pe, struct tep_format_field *field)
 {
 	struct tep_handle *pevent = field->event->pevent;
 	void *data = pe->sample.raw_data;
@@ -348,28 +348,28 @@ tracepoint_field(struct pyrf_event *pe, struct format_field *field)
 	unsigned long long val;
 	unsigned int offset, len;
 
-	if (field->flags & FIELD_IS_ARRAY) {
+	if (field->flags & TEP_FIELD_IS_ARRAY) {
 		offset = field->offset;
 		len    = field->size;
-		if (field->flags & FIELD_IS_DYNAMIC) {
+		if (field->flags & TEP_FIELD_IS_DYNAMIC) {
 			val     = tep_read_number(pevent, data + offset, len);
 			offset  = val;
 			len     = offset >> 16;
 			offset &= 0xffff;
 		}
-		if (field->flags & FIELD_IS_STRING &&
+		if (field->flags & TEP_FIELD_IS_STRING &&
 		    is_printable_array(data + offset, len)) {
 			ret = _PyUnicode_FromString((char *)data + offset);
 		} else {
 			ret = PyByteArray_FromStringAndSize((const char *) data + offset, len);
-			field->flags &= ~FIELD_IS_STRING;
+			field->flags &= ~TEP_FIELD_IS_STRING;
 		}
 	} else {
 		val = tep_read_number(pevent, data + field->offset,
 				      field->size);
-		if (field->flags & FIELD_IS_POINTER)
+		if (field->flags & TEP_FIELD_IS_POINTER)
 			ret = PyLong_FromUnsignedLong((unsigned long) val);
-		else if (field->flags & FIELD_IS_SIGNED)
+		else if (field->flags & TEP_FIELD_IS_SIGNED)
 			ret = PyLong_FromLong((long) val);
 		else
 			ret = PyLong_FromUnsignedLong((unsigned long) val);
@@ -383,10 +383,10 @@ get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name)
 {
 	const char *str = _PyUnicode_AsString(PyObject_Str(attr_name));
 	struct perf_evsel *evsel = pevent->evsel;
-	struct format_field *field;
+	struct tep_format_field *field;
 
 	if (!evsel->tp_format) {
-		struct event_format *tp_format;
+		struct tep_event_format *tp_format;
 
 		tp_format = trace_event__tp_format_id(evsel->attr.config);
 		if (!tp_format)
@@ -1240,7 +1240,7 @@ static struct {
 static PyObject *pyrf__tracepoint(struct pyrf_evsel *pevsel,
 				  PyObject *args, PyObject *kwargs)
 {
-	struct event_format *tp_format;
+	struct tep_event_format *tp_format;
 	static char *kwlist[] = { "sys", "name", NULL };
 	char *sys  = NULL;
 	char *name = NULL;
diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c
index d2c78ffd9fee..a2eeebbfb25f 100644
--- a/tools/perf/util/s390-cpumsf.c
+++ b/tools/perf/util/s390-cpumsf.c
@@ -147,6 +147,9 @@
 #include <linux/bitops.h>
 #include <linux/log2.h>
 
+#include <sys/stat.h>
+#include <sys/types.h>
+
 #include "cpumap.h"
 #include "color.h"
 #include "evsel.h"
@@ -159,6 +162,7 @@
 #include "auxtrace.h"
 #include "s390-cpumsf.h"
 #include "s390-cpumsf-kernel.h"
+#include "config.h"
 
 struct s390_cpumsf {
 	struct auxtrace		auxtrace;
@@ -170,6 +174,8 @@ struct s390_cpumsf {
 	u32			pmu_type;
 	u16			machine_type;
 	bool			data_queued;
+	bool			use_logfile;
+	char			*logdir;
 };
 
 struct s390_cpumsf_queue {
@@ -177,6 +183,7 @@ struct s390_cpumsf_queue {
 	unsigned int		queue_nr;
 	struct auxtrace_buffer	*buffer;
 	int			cpu;
+	FILE			*logfile;
 };
 
 /* Display s390 CPU measurement facility basic-sampling data entry */
@@ -595,6 +602,12 @@ static int s390_cpumsf_run_decoder(struct s390_cpumsf_queue *sfq,
 			buffer->use_size = buffer->size;
 			buffer->use_data = buffer->data;
 		}
+		if (sfq->logfile) {	/* Write into log file */
+			size_t rc = fwrite(buffer->data, buffer->size, 1,
+					   sfq->logfile);
+			if (rc != 1)
+				pr_err("Failed to write auxiliary data\n");
+		}
 	} else
 		buffer = sfq->buffer;
 
@@ -606,6 +619,13 @@ static int s390_cpumsf_run_decoder(struct s390_cpumsf_queue *sfq,
 			return -ENOMEM;
 		buffer->use_size = buffer->size;
 		buffer->use_data = buffer->data;
+
+		if (sfq->logfile) {	/* Write into log file */
+			size_t rc = fwrite(buffer->data, buffer->size, 1,
+					   sfq->logfile);
+			if (rc != 1)
+				pr_err("Failed to write auxiliary data\n");
+		}
 	}
 	pr_debug4("%s queue_nr:%d buffer:%" PRId64 " offset:%#" PRIx64 " size:%#zx rest:%#zx\n",
 		  __func__, sfq->queue_nr, buffer->buffer_nr, buffer->offset,
@@ -640,6 +660,23 @@ s390_cpumsf_alloc_queue(struct s390_cpumsf *sf, unsigned int queue_nr)
 	sfq->sf = sf;
 	sfq->queue_nr = queue_nr;
 	sfq->cpu = -1;
+	if (sf->use_logfile) {
+		char *name;
+		int rc;
+
+		rc = (sf->logdir)
+			? asprintf(&name, "%s/aux.smp.%02x",
+				 sf->logdir, queue_nr)
+			: asprintf(&name, "aux.smp.%02x", queue_nr);
+		if (rc > 0)
+			sfq->logfile = fopen(name, "w");
+		if (sfq->logfile == NULL) {
+			pr_err("Failed to open auxiliary log file %s,"
+			       "continue...\n", name);
+			sf->use_logfile = false;
+		}
+		free(name);
+	}
 	return sfq;
 }
 
@@ -850,8 +887,16 @@ static void s390_cpumsf_free_queues(struct perf_session *session)
 	struct auxtrace_queues *queues = &sf->queues;
 	unsigned int i;
 
-	for (i = 0; i < queues->nr_queues; i++)
+	for (i = 0; i < queues->nr_queues; i++) {
+		struct s390_cpumsf_queue *sfq = (struct s390_cpumsf_queue *)
+						queues->queue_array[i].priv;
+
+		if (sfq != NULL && sfq->logfile) {
+			fclose(sfq->logfile);
+			sfq->logfile = NULL;
+		}
 		zfree(&queues->queue_array[i].priv);
+	}
 	auxtrace_queues__free(queues);
 }
 
@@ -864,6 +909,7 @@ static void s390_cpumsf_free(struct perf_session *session)
 	auxtrace_heap__free(&sf->heap);
 	s390_cpumsf_free_queues(session);
 	session->auxtrace = NULL;
+	free(sf->logdir);
 	free(sf);
 }
 
@@ -877,17 +923,55 @@ static int s390_cpumsf_get_type(const char *cpuid)
 
 /* Check itrace options set on perf report command.
  * Return true, if none are set or all options specified can be
- * handled on s390.
+ * handled on s390 (currently only option 'd' for logging.
  * Return false otherwise.
  */
 static bool check_auxtrace_itrace(struct itrace_synth_opts *itops)
 {
+	bool ison = false;
+
 	if (!itops || !itops->set)
 		return true;
-	pr_err("No --itrace options supported\n");
+	ison = itops->inject || itops->instructions || itops->branches ||
+		itops->transactions || itops->ptwrites ||
+		itops->pwr_events || itops->errors ||
+		itops->dont_decode || itops->calls || itops->returns ||
+		itops->callchain || itops->thread_stack ||
+		itops->last_branch;
+	if (!ison)
+		return true;
+	pr_err("Unsupported --itrace options specified\n");
 	return false;
 }
 
+/* Check for AUXTRACE dump directory if it is needed.
+ * On failure print an error message but continue.
+ * Return 0 on wrong keyword in config file and 1 otherwise.
+ */
+static int s390_cpumsf__config(const char *var, const char *value, void *cb)
+{
+	struct s390_cpumsf *sf = cb;
+	struct stat stbuf;
+	int rc;
+
+	if (strcmp(var, "auxtrace.dumpdir"))
+		return 0;
+	sf->logdir = strdup(value);
+	if (sf->logdir == NULL) {
+		pr_err("Failed to find auxtrace log directory %s,"
+		       " continue with current directory...\n", value);
+		return 1;
+	}
+	rc = stat(sf->logdir, &stbuf);
+	if (rc == -1 || !S_ISDIR(stbuf.st_mode)) {
+		pr_err("Missing auxtrace log directory %s,"
+		       " continue with current directory...\n", value);
+		free(sf->logdir);
+		sf->logdir = NULL;
+	}
+	return 1;
+}
+
 int s390_cpumsf_process_auxtrace_info(union perf_event *event,
 				      struct perf_session *session)
 {
@@ -906,6 +990,9 @@ int s390_cpumsf_process_auxtrace_info(union perf_event *event,
 		err = -EINVAL;
 		goto err_free;
 	}
+	sf->use_logfile = session->itrace_synth_opts->log;
+	if (sf->use_logfile)
+		perf_config(s390_cpumsf__config, sf);
 
 	err = auxtrace_queues__init(&sf->queues);
 	if (err)
@@ -940,6 +1027,7 @@ err_free_queues:
 	auxtrace_queues__free(&sf->queues);
 	session->auxtrace = NULL;
 err_free:
+	free(sf->logdir);
 	free(sf);
 	return err;
 }
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 45484f0f7292..89cb887648f9 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -99,7 +99,7 @@ static void define_symbolic_value(const char *ev_name,
 	LEAVE;
 }
 
-static void define_symbolic_values(struct print_flag_sym *field,
+static void define_symbolic_values(struct tep_print_flag_sym *field,
 				   const char *ev_name,
 				   const char *field_name)
 {
@@ -157,7 +157,7 @@ static void define_flag_value(const char *ev_name,
 	LEAVE;
 }
 
-static void define_flag_values(struct print_flag_sym *field,
+static void define_flag_values(struct tep_print_flag_sym *field,
 			       const char *ev_name,
 			       const char *field_name)
 {
@@ -189,62 +189,62 @@ static void define_flag_field(const char *ev_name,
 	LEAVE;
 }
 
-static void define_event_symbols(struct event_format *event,
+static void define_event_symbols(struct tep_event_format *event,
 				 const char *ev_name,
-				 struct print_arg *args)
+				 struct tep_print_arg *args)
 {
 	if (args == NULL)
 		return;
 
 	switch (args->type) {
-	case PRINT_NULL:
+	case TEP_PRINT_NULL:
 		break;
-	case PRINT_ATOM:
+	case TEP_PRINT_ATOM:
 		define_flag_value(ev_name, cur_field_name, "0",
 				  args->atom.atom);
 		zero_flag_atom = 0;
 		break;
-	case PRINT_FIELD:
+	case TEP_PRINT_FIELD:
 		free(cur_field_name);
 		cur_field_name = strdup(args->field.name);
 		break;
-	case PRINT_FLAGS:
+	case TEP_PRINT_FLAGS:
 		define_event_symbols(event, ev_name, args->flags.field);
 		define_flag_field(ev_name, cur_field_name, args->flags.delim);
 		define_flag_values(args->flags.flags, ev_name, cur_field_name);
 		break;
-	case PRINT_SYMBOL:
+	case TEP_PRINT_SYMBOL:
 		define_event_symbols(event, ev_name, args->symbol.field);
 		define_symbolic_field(ev_name, cur_field_name);
 		define_symbolic_values(args->symbol.symbols, ev_name,
 				       cur_field_name);
 		break;
-	case PRINT_HEX:
-	case PRINT_HEX_STR:
+	case TEP_PRINT_HEX:
+	case TEP_PRINT_HEX_STR:
 		define_event_symbols(event, ev_name, args->hex.field);
 		define_event_symbols(event, ev_name, args->hex.size);
 		break;
-	case PRINT_INT_ARRAY:
+	case TEP_PRINT_INT_ARRAY:
 		define_event_symbols(event, ev_name, args->int_array.field);
 		define_event_symbols(event, ev_name, args->int_array.count);
 		define_event_symbols(event, ev_name, args->int_array.el_size);
 		break;
-	case PRINT_BSTRING:
-	case PRINT_DYNAMIC_ARRAY:
-	case PRINT_DYNAMIC_ARRAY_LEN:
-	case PRINT_STRING:
-	case PRINT_BITMASK:
+	case TEP_PRINT_BSTRING:
+	case TEP_PRINT_DYNAMIC_ARRAY:
+	case TEP_PRINT_DYNAMIC_ARRAY_LEN:
+	case TEP_PRINT_STRING:
+	case TEP_PRINT_BITMASK:
 		break;
-	case PRINT_TYPE:
+	case TEP_PRINT_TYPE:
 		define_event_symbols(event, ev_name, args->typecast.item);
 		break;
-	case PRINT_OP:
+	case TEP_PRINT_OP:
 		if (strcmp(args->op.op, ":") == 0)
 			zero_flag_atom = 1;
 		define_event_symbols(event, ev_name, args->op.left);
 		define_event_symbols(event, ev_name, args->op.right);
 		break;
-	case PRINT_FUNC:
+	case TEP_PRINT_FUNC:
 	default:
 		pr_err("Unsupported print arg type\n");
 		/* we should warn... */
@@ -338,8 +338,8 @@ static void perl_process_tracepoint(struct perf_sample *sample,
 				    struct addr_location *al)
 {
 	struct thread *thread = al->thread;
-	struct event_format *event = evsel->tp_format;
-	struct format_field *field;
+	struct tep_event_format *event = evsel->tp_format;
+	struct tep_format_field *field;
 	static char handler[256];
 	unsigned long long val;
 	unsigned long s, ns;
@@ -388,9 +388,9 @@ static void perl_process_tracepoint(struct perf_sample *sample,
 	/* common fields other than pid can be accessed via xsub fns */
 
 	for (field = event->format.fields; field; field = field->next) {
-		if (field->flags & FIELD_IS_STRING) {
+		if (field->flags & TEP_FIELD_IS_STRING) {
 			int offset;
-			if (field->flags & FIELD_IS_DYNAMIC) {
+			if (field->flags & TEP_FIELD_IS_DYNAMIC) {
 				offset = *(int *)(data + field->offset);
 				offset &= 0xffff;
 			} else
@@ -399,7 +399,7 @@ static void perl_process_tracepoint(struct perf_sample *sample,
 		} else { /* FIELD_IS_NUMERIC */
 			val = read_size(event, data + field->offset,
 					field->size);
-			if (field->flags & FIELD_IS_SIGNED) {
+			if (field->flags & TEP_FIELD_IS_SIGNED) {
 				XPUSHs(sv_2mortal(newSViv(val)));
 			} else {
 				XPUSHs(sv_2mortal(newSVuv(val)));
@@ -537,8 +537,8 @@ static int perl_stop_script(void)
 
 static int perl_generate_script(struct tep_handle *pevent, const char *outfile)
 {
-	struct event_format *event = NULL;
-	struct format_field *f;
+	struct tep_event_format *event = NULL;
+	struct tep_format_field *f;
 	char fname[PATH_MAX];
 	int not_first, count;
 	FILE *ofp;
@@ -646,11 +646,11 @@ sub print_backtrace\n\
 			count++;
 
 			fprintf(ofp, "%s=", f->name);
-			if (f->flags & FIELD_IS_STRING ||
-			    f->flags & FIELD_IS_FLAG ||
-			    f->flags & FIELD_IS_SYMBOLIC)
+			if (f->flags & TEP_FIELD_IS_STRING ||
+			    f->flags & TEP_FIELD_IS_FLAG ||
+			    f->flags & TEP_FIELD_IS_SYMBOLIC)
 				fprintf(ofp, "%%s");
-			else if (f->flags & FIELD_IS_SIGNED)
+			else if (f->flags & TEP_FIELD_IS_SIGNED)
 				fprintf(ofp, "%%d");
 			else
 				fprintf(ofp, "%%u");
@@ -668,7 +668,7 @@ sub print_backtrace\n\
 			if (++count % 5 == 0)
 				fprintf(ofp, "\n\t       ");
 
-			if (f->flags & FIELD_IS_FLAG) {
+			if (f->flags & TEP_FIELD_IS_FLAG) {
 				if ((count - 1) % 5 != 0) {
 					fprintf(ofp, "\n\t       ");
 					count = 4;
@@ -678,7 +678,7 @@ sub print_backtrace\n\
 					event->name);
 				fprintf(ofp, "\"%s\", $%s)", f->name,
 					f->name);
-			} else if (f->flags & FIELD_IS_SYMBOLIC) {
+			} else if (f->flags & TEP_FIELD_IS_SYMBOLIC) {
 				if ((count - 1) % 5 != 0) {
 					fprintf(ofp, "\n\t       ");
 					count = 4;
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index dfc6093f118c..69aa93d4ee99 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -193,7 +193,7 @@ static void try_call_object(const char *handler_name, PyObject *args)
 		call_object(handler, args, handler_name);
 }
 
-static void define_value(enum print_arg_type field_type,
+static void define_value(enum tep_print_arg_type field_type,
 			 const char *ev_name,
 			 const char *field_name,
 			 const char *field_value,
@@ -204,7 +204,7 @@ static void define_value(enum print_arg_type field_type,
 	unsigned long long value;
 	unsigned n = 0;
 
-	if (field_type == PRINT_SYMBOL)
+	if (field_type == TEP_PRINT_SYMBOL)
 		handler_name = "define_symbolic_value";
 
 	t = PyTuple_New(4);
@@ -223,8 +223,8 @@ static void define_value(enum print_arg_type field_type,
 	Py_DECREF(t);
 }
 
-static void define_values(enum print_arg_type field_type,
-			  struct print_flag_sym *field,
+static void define_values(enum tep_print_arg_type field_type,
+			  struct tep_print_flag_sym *field,
 			  const char *ev_name,
 			  const char *field_name)
 {
@@ -235,7 +235,7 @@ static void define_values(enum print_arg_type field_type,
 		define_values(field_type, field->next, ev_name, field_name);
 }
 
-static void define_field(enum print_arg_type field_type,
+static void define_field(enum tep_print_arg_type field_type,
 			 const char *ev_name,
 			 const char *field_name,
 			 const char *delim)
@@ -244,10 +244,10 @@ static void define_field(enum print_arg_type field_type,
 	PyObject *t;
 	unsigned n = 0;
 
-	if (field_type == PRINT_SYMBOL)
+	if (field_type == TEP_PRINT_SYMBOL)
 		handler_name = "define_symbolic_field";
 
-	if (field_type == PRINT_FLAGS)
+	if (field_type == TEP_PRINT_FLAGS)
 		t = PyTuple_New(3);
 	else
 		t = PyTuple_New(2);
@@ -256,7 +256,7 @@ static void define_field(enum print_arg_type field_type,
 
 	PyTuple_SetItem(t, n++, _PyUnicode_FromString(ev_name));
 	PyTuple_SetItem(t, n++, _PyUnicode_FromString(field_name));
-	if (field_type == PRINT_FLAGS)
+	if (field_type == TEP_PRINT_FLAGS)
 		PyTuple_SetItem(t, n++, _PyUnicode_FromString(delim));
 
 	try_call_object(handler_name, t);
@@ -264,54 +264,54 @@ static void define_field(enum print_arg_type field_type,
 	Py_DECREF(t);
 }
 
-static void define_event_symbols(struct event_format *event,
+static void define_event_symbols(struct tep_event_format *event,
 				 const char *ev_name,
-				 struct print_arg *args)
+				 struct tep_print_arg *args)
 {
 	if (args == NULL)
 		return;
 
 	switch (args->type) {
-	case PRINT_NULL:
+	case TEP_PRINT_NULL:
 		break;
-	case PRINT_ATOM:
-		define_value(PRINT_FLAGS, ev_name, cur_field_name, "0",
+	case TEP_PRINT_ATOM:
+		define_value(TEP_PRINT_FLAGS, ev_name, cur_field_name, "0",
 			     args->atom.atom);
 		zero_flag_atom = 0;
 		break;
-	case PRINT_FIELD:
+	case TEP_PRINT_FIELD:
 		free(cur_field_name);
 		cur_field_name = strdup(args->field.name);
 		break;
-	case PRINT_FLAGS:
+	case TEP_PRINT_FLAGS:
 		define_event_symbols(event, ev_name, args->flags.field);
-		define_field(PRINT_FLAGS, ev_name, cur_field_name,
+		define_field(TEP_PRINT_FLAGS, ev_name, cur_field_name,
 			     args->flags.delim);
-		define_values(PRINT_FLAGS, args->flags.flags, ev_name,
+		define_values(TEP_PRINT_FLAGS, args->flags.flags, ev_name,
 			      cur_field_name);
 		break;
-	case PRINT_SYMBOL:
+	case TEP_PRINT_SYMBOL:
 		define_event_symbols(event, ev_name, args->symbol.field);
-		define_field(PRINT_SYMBOL, ev_name, cur_field_name, NULL);
-		define_values(PRINT_SYMBOL, args->symbol.symbols, ev_name,
+		define_field(TEP_PRINT_SYMBOL, ev_name, cur_field_name, NULL);
+		define_values(TEP_PRINT_SYMBOL, args->symbol.symbols, ev_name,
 			      cur_field_name);
 		break;
-	case PRINT_HEX:
-	case PRINT_HEX_STR:
+	case TEP_PRINT_HEX:
+	case TEP_PRINT_HEX_STR:
 		define_event_symbols(event, ev_name, args->hex.field);
 		define_event_symbols(event, ev_name, args->hex.size);
 		break;
-	case PRINT_INT_ARRAY:
+	case TEP_PRINT_INT_ARRAY:
 		define_event_symbols(event, ev_name, args->int_array.field);
 		define_event_symbols(event, ev_name, args->int_array.count);
 		define_event_symbols(event, ev_name, args->int_array.el_size);
 		break;
-	case PRINT_STRING:
+	case TEP_PRINT_STRING:
 		break;
-	case PRINT_TYPE:
+	case TEP_PRINT_TYPE:
 		define_event_symbols(event, ev_name, args->typecast.item);
 		break;
-	case PRINT_OP:
+	case TEP_PRINT_OP:
 		if (strcmp(args->op.op, ":") == 0)
 			zero_flag_atom = 1;
 		define_event_symbols(event, ev_name, args->op.left);
@@ -319,11 +319,11 @@ static void define_event_symbols(struct event_format *event,
 		break;
 	default:
 		/* gcc warns for these? */
-	case PRINT_BSTRING:
-	case PRINT_DYNAMIC_ARRAY:
-	case PRINT_DYNAMIC_ARRAY_LEN:
-	case PRINT_FUNC:
-	case PRINT_BITMASK:
+	case TEP_PRINT_BSTRING:
+	case TEP_PRINT_DYNAMIC_ARRAY:
+	case TEP_PRINT_DYNAMIC_ARRAY_LEN:
+	case TEP_PRINT_FUNC:
+	case TEP_PRINT_BITMASK:
 		/* we should warn... */
 		return;
 	}
@@ -332,10 +332,10 @@ static void define_event_symbols(struct event_format *event,
 		define_event_symbols(event, ev_name, args->next);
 }
 
-static PyObject *get_field_numeric_entry(struct event_format *event,
-		struct format_field *field, void *data)
+static PyObject *get_field_numeric_entry(struct tep_event_format *event,
+		struct tep_format_field *field, void *data)
 {
-	bool is_array = field->flags & FIELD_IS_ARRAY;
+	bool is_array = field->flags & TEP_FIELD_IS_ARRAY;
 	PyObject *obj = NULL, *list = NULL;
 	unsigned long long val;
 	unsigned int item_size, n_items, i;
@@ -353,7 +353,7 @@ static PyObject *get_field_numeric_entry(struct event_format *event,
 
 		val = read_size(event, data + field->offset + i * item_size,
 				item_size);
-		if (field->flags & FIELD_IS_SIGNED) {
+		if (field->flags & TEP_FIELD_IS_SIGNED) {
 			if ((long long)val >= LONG_MIN &&
 					(long long)val <= LONG_MAX)
 				obj = _PyLong_FromLong(val);
@@ -790,11 +790,11 @@ static void python_process_tracepoint(struct perf_sample *sample,
 				      struct perf_evsel *evsel,
 				      struct addr_location *al)
 {
-	struct event_format *event = evsel->tp_format;
+	struct tep_event_format *event = evsel->tp_format;
 	PyObject *handler, *context, *t, *obj = NULL, *callchain;
 	PyObject *dict = NULL, *all_entries_dict = NULL;
 	static char handler_name[256];
-	struct format_field *field;
+	struct tep_format_field *field;
 	unsigned long s, ns;
 	unsigned n = 0;
 	int pid;
@@ -867,22 +867,22 @@ static void python_process_tracepoint(struct perf_sample *sample,
 		unsigned int offset, len;
 		unsigned long long val;
 
-		if (field->flags & FIELD_IS_ARRAY) {
+		if (field->flags & TEP_FIELD_IS_ARRAY) {
 			offset = field->offset;
 			len    = field->size;
-			if (field->flags & FIELD_IS_DYNAMIC) {
+			if (field->flags & TEP_FIELD_IS_DYNAMIC) {
 				val     = tep_read_number(scripting_context->pevent,
 							  data + offset, len);
 				offset  = val;
 				len     = offset >> 16;
 				offset &= 0xffff;
 			}
-			if (field->flags & FIELD_IS_STRING &&
+			if (field->flags & TEP_FIELD_IS_STRING &&
 			    is_printable_array(data + offset, len)) {
 				obj = _PyUnicode_FromString((char *) data + offset);
 			} else {
 				obj = PyByteArray_FromStringAndSize((const char *) data + offset, len);
-				field->flags &= ~FIELD_IS_STRING;
+				field->flags &= ~TEP_FIELD_IS_STRING;
 			}
 		} else { /* FIELD_IS_NUMERIC */
 			obj = get_field_numeric_entry(event, field, data);
@@ -1590,8 +1590,8 @@ static int python_stop_script(void)
 
 static int python_generate_script(struct tep_handle *pevent, const char *outfile)
 {
-	struct event_format *event = NULL;
-	struct format_field *f;
+	struct tep_event_format *event = NULL;
+	struct tep_format_field *f;
 	char fname[PATH_MAX];
 	int not_first, count;
 	FILE *ofp;
@@ -1686,12 +1686,12 @@ static int python_generate_script(struct tep_handle *pevent, const char *outfile
 			count++;
 
 			fprintf(ofp, "%s=", f->name);
-			if (f->flags & FIELD_IS_STRING ||
-			    f->flags & FIELD_IS_FLAG ||
-			    f->flags & FIELD_IS_ARRAY ||
-			    f->flags & FIELD_IS_SYMBOLIC)
+			if (f->flags & TEP_FIELD_IS_STRING ||
+			    f->flags & TEP_FIELD_IS_FLAG ||
+			    f->flags & TEP_FIELD_IS_ARRAY ||
+			    f->flags & TEP_FIELD_IS_SYMBOLIC)
 				fprintf(ofp, "%%s");
-			else if (f->flags & FIELD_IS_SIGNED)
+			else if (f->flags & TEP_FIELD_IS_SIGNED)
 				fprintf(ofp, "%%d");
 			else
 				fprintf(ofp, "%%u");
@@ -1709,7 +1709,7 @@ static int python_generate_script(struct tep_handle *pevent, const char *outfile
 			if (++count % 5 == 0)
 				fprintf(ofp, "\n\t\t");
 
-			if (f->flags & FIELD_IS_FLAG) {
+			if (f->flags & TEP_FIELD_IS_FLAG) {
 				if ((count - 1) % 5 != 0) {
 					fprintf(ofp, "\n\t\t");
 					count = 4;
@@ -1719,7 +1719,7 @@ static int python_generate_script(struct tep_handle *pevent, const char *outfile
 					event->name);
 				fprintf(ofp, "\"%s\", %s)", f->name,
 					f->name);
-			} else if (f->flags & FIELD_IS_SYMBOLIC) {
+			} else if (f->flags & TEP_FIELD_IS_SYMBOLIC) {
 				if ((count - 1) % 5 != 0) {
 					fprintf(ofp, "\n\t\t");
 					count = 4;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 8b9369303561..7d2c8ce6cfad 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -199,12 +199,10 @@ void perf_session__delete(struct perf_session *session)
 	free(session);
 }
 
-static int process_event_synth_tracing_data_stub(struct perf_tool *tool
+static int process_event_synth_tracing_data_stub(struct perf_session *session
 						 __maybe_unused,
 						 union perf_event *event
-						 __maybe_unused,
-						 struct perf_session *session
-						__maybe_unused)
+						 __maybe_unused)
 {
 	dump_printf(": unhandled!\n");
 	return 0;
@@ -277,10 +275,8 @@ static int skipn(int fd, off_t n)
 	return 0;
 }
 
-static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
-				       union perf_event *event,
-				       struct perf_session *session
-				       __maybe_unused)
+static s64 process_event_auxtrace_stub(struct perf_session *session __maybe_unused,
+				       union perf_event *event)
 {
 	dump_printf(": unhandled!\n");
 	if (perf_data__is_pipe(session->data))
@@ -288,9 +284,8 @@ static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
 	return event->auxtrace.size;
 }
 
-static int process_event_op2_stub(struct perf_tool *tool __maybe_unused,
-				  union perf_event *event __maybe_unused,
-				  struct perf_session *session __maybe_unused)
+static int process_event_op2_stub(struct perf_session *session __maybe_unused,
+				  union perf_event *event __maybe_unused)
 {
 	dump_printf(": unhandled!\n");
 	return 0;
@@ -298,9 +293,8 @@ static int process_event_op2_stub(struct perf_tool *tool __maybe_unused,
 
 
 static
-int process_event_thread_map_stub(struct perf_tool *tool __maybe_unused,
-				  union perf_event *event __maybe_unused,
-				  struct perf_session *session __maybe_unused)
+int process_event_thread_map_stub(struct perf_session *session __maybe_unused,
+				  union perf_event *event __maybe_unused)
 {
 	if (dump_trace)
 		perf_event__fprintf_thread_map(event, stdout);
@@ -310,9 +304,8 @@ int process_event_thread_map_stub(struct perf_tool *tool __maybe_unused,
 }
 
 static
-int process_event_cpu_map_stub(struct perf_tool *tool __maybe_unused,
-			       union perf_event *event __maybe_unused,
-			       struct perf_session *session __maybe_unused)
+int process_event_cpu_map_stub(struct perf_session *session __maybe_unused,
+			       union perf_event *event __maybe_unused)
 {
 	if (dump_trace)
 		perf_event__fprintf_cpu_map(event, stdout);
@@ -322,9 +315,8 @@ int process_event_cpu_map_stub(struct perf_tool *tool __maybe_unused,
 }
 
 static
-int process_event_stat_config_stub(struct perf_tool *tool __maybe_unused,
-				   union perf_event *event __maybe_unused,
-				   struct perf_session *session __maybe_unused)
+int process_event_stat_config_stub(struct perf_session *session __maybe_unused,
+				   union perf_event *event __maybe_unused)
 {
 	if (dump_trace)
 		perf_event__fprintf_stat_config(event, stdout);
@@ -333,10 +325,8 @@ int process_event_stat_config_stub(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-static int process_stat_stub(struct perf_tool *tool __maybe_unused,
-			     union perf_event *event __maybe_unused,
-			     struct perf_session *perf_session
-			     __maybe_unused)
+static int process_stat_stub(struct perf_session *perf_session __maybe_unused,
+			     union perf_event *event)
 {
 	if (dump_trace)
 		perf_event__fprintf_stat(event, stdout);
@@ -345,10 +335,8 @@ static int process_stat_stub(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-static int process_stat_round_stub(struct perf_tool *tool __maybe_unused,
-				   union perf_event *event __maybe_unused,
-				   struct perf_session *perf_session
-				   __maybe_unused)
+static int process_stat_round_stub(struct perf_session *perf_session __maybe_unused,
+				   union perf_event *event)
 {
 	if (dump_trace)
 		perf_event__fprintf_stat_round(event, stdout);
@@ -1374,37 +1362,37 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 	case PERF_RECORD_HEADER_TRACING_DATA:
 		/* setup for reading amidst mmap */
 		lseek(fd, file_offset, SEEK_SET);
-		return tool->tracing_data(tool, event, session);
+		return tool->tracing_data(session, event);
 	case PERF_RECORD_HEADER_BUILD_ID:
-		return tool->build_id(tool, event, session);
+		return tool->build_id(session, event);
 	case PERF_RECORD_FINISHED_ROUND:
 		return tool->finished_round(tool, event, oe);
 	case PERF_RECORD_ID_INDEX:
-		return tool->id_index(tool, event, session);
+		return tool->id_index(session, event);
 	case PERF_RECORD_AUXTRACE_INFO:
-		return tool->auxtrace_info(tool, event, session);
+		return tool->auxtrace_info(session, event);
 	case PERF_RECORD_AUXTRACE:
 		/* setup for reading amidst mmap */
 		lseek(fd, file_offset + event->header.size, SEEK_SET);
-		return tool->auxtrace(tool, event, session);
+		return tool->auxtrace(session, event);
 	case PERF_RECORD_AUXTRACE_ERROR:
 		perf_session__auxtrace_error_inc(session, event);
-		return tool->auxtrace_error(tool, event, session);
+		return tool->auxtrace_error(session, event);
 	case PERF_RECORD_THREAD_MAP:
-		return tool->thread_map(tool, event, session);
+		return tool->thread_map(session, event);
 	case PERF_RECORD_CPU_MAP:
-		return tool->cpu_map(tool, event, session);
+		return tool->cpu_map(session, event);
 	case PERF_RECORD_STAT_CONFIG:
-		return tool->stat_config(tool, event, session);
+		return tool->stat_config(session, event);
 	case PERF_RECORD_STAT:
-		return tool->stat(tool, event, session);
+		return tool->stat(session, event);
 	case PERF_RECORD_STAT_ROUND:
-		return tool->stat_round(tool, event, session);
+		return tool->stat_round(session, event);
 	case PERF_RECORD_TIME_CONV:
 		session->time_conv = event->time_conv;
-		return tool->time_conv(tool, event, session);
+		return tool->time_conv(session, event);
 	case PERF_RECORD_HEADER_FEATURE:
-		return tool->feature(tool, event, session);
+		return tool->feature(session, event);
 	default:
 		return -EINVAL;
 	}
@@ -2133,9 +2121,8 @@ out:
 	return err;
 }
 
-int perf_event__process_id_index(struct perf_tool *tool __maybe_unused,
-				 union perf_event *event,
-				 struct perf_session *session)
+int perf_event__process_id_index(struct perf_session *session,
+				 union perf_event *event)
 {
 	struct perf_evlist *evlist = session->evlist;
 	struct id_index_event *ie = &event->id_index;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index da40b4b380ca..d96eccd7d27f 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -120,9 +120,8 @@ int perf_session__deliver_synth_event(struct perf_session *session,
 				      union perf_event *event,
 				      struct perf_sample *sample);
 
-int perf_event__process_id_index(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session);
+int perf_event__process_id_index(struct perf_session *session,
+				 union perf_event *event);
 
 int perf_event__synthesize_id_index(struct perf_tool *tool,
 				    perf_event__handler_t process,
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 1942f6dd24f6..63f758c655d5 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -5,16 +5,18 @@ from subprocess import Popen, PIPE
 from re import sub
 
 def clang_has_option(option):
-    return [o for o in Popen(['clang', option], stderr=PIPE).stderr.readlines() if "unknown argument" in o] == [ ]
+    return [o for o in Popen(['clang', option], stderr=PIPE).stderr.readlines() if b"unknown argument" in o] == [ ]
 
 cc = getenv("CC")
 if cc == "clang":
-    from _sysconfigdata import build_time_vars
-    build_time_vars["CFLAGS"] = sub("-specs=[^ ]+", "", build_time_vars["CFLAGS"])
-    if not clang_has_option("-mcet"):
-        build_time_vars["CFLAGS"] = sub("-mcet", "", build_time_vars["CFLAGS"])
-    if not clang_has_option("-fcf-protection"):
-        build_time_vars["CFLAGS"] = sub("-fcf-protection", "", build_time_vars["CFLAGS"])
+    from distutils.sysconfig import get_config_vars
+    vars = get_config_vars()
+    for var in ('CFLAGS', 'OPT'):
+        vars[var] = sub("-specs=[^ ]+", "", vars[var])
+        if not clang_has_option("-mcet"):
+            vars[var] = sub("-mcet", "", vars[var])
+        if not clang_has_option("-fcf-protection"):
+            vars[var] = sub("-fcf-protection", "", vars[var])
 
 from distutils.core import setup, Extension
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index b284276ec963..f96c005b3c41 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1884,7 +1884,7 @@ static int __sort_dimension__add_hpp_output(struct sort_dimension *sd,
 struct hpp_dynamic_entry {
 	struct perf_hpp_fmt hpp;
 	struct perf_evsel *evsel;
-	struct format_field *field;
+	struct tep_format_field *field;
 	unsigned dynamic_len;
 	bool raw_trace;
 };
@@ -1899,7 +1899,7 @@ static int hde_width(struct hpp_dynamic_entry *hde)
 		if (namelen > len)
 			len = namelen;
 
-		if (!(hde->field->flags & FIELD_IS_STRING)) {
+		if (!(hde->field->flags & TEP_FIELD_IS_STRING)) {
 			/* length for print hex numbers */
 			fieldlen = hde->field->size * 2 + 2;
 		}
@@ -1915,7 +1915,7 @@ static void update_dynamic_len(struct hpp_dynamic_entry *hde,
 			       struct hist_entry *he)
 {
 	char *str, *pos;
-	struct format_field *field = hde->field;
+	struct tep_format_field *field = hde->field;
 	size_t namelen;
 	bool last = false;
 
@@ -2000,7 +2000,7 @@ static int __sort__hde_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	struct hpp_dynamic_entry *hde;
 	size_t len = fmt->user_len;
 	char *str, *pos;
-	struct format_field *field;
+	struct tep_format_field *field;
 	size_t namelen;
 	bool last = false;
 	int ret;
@@ -2060,7 +2060,7 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt,
 			       struct hist_entry *a, struct hist_entry *b)
 {
 	struct hpp_dynamic_entry *hde;
-	struct format_field *field;
+	struct tep_format_field *field;
 	unsigned offset, size;
 
 	hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
@@ -2071,7 +2071,7 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt,
 	}
 
 	field = hde->field;
-	if (field->flags & FIELD_IS_DYNAMIC) {
+	if (field->flags & TEP_FIELD_IS_DYNAMIC) {
 		unsigned long long dyn;
 
 		tep_read_number_field(field, a->raw_data, &dyn);
@@ -2117,7 +2117,7 @@ static void hde_free(struct perf_hpp_fmt *fmt)
 }
 
 static struct hpp_dynamic_entry *
-__alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field,
+__alloc_dynamic_entry(struct perf_evsel *evsel, struct tep_format_field *field,
 		      int level)
 {
 	struct hpp_dynamic_entry *hde;
@@ -2252,7 +2252,7 @@ static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_nam
 }
 
 static int __dynamic_dimension__add(struct perf_evsel *evsel,
-				    struct format_field *field,
+				    struct tep_format_field *field,
 				    bool raw_trace, int level)
 {
 	struct hpp_dynamic_entry *hde;
@@ -2270,7 +2270,7 @@ static int __dynamic_dimension__add(struct perf_evsel *evsel,
 static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace, int level)
 {
 	int ret;
-	struct format_field *field;
+	struct tep_format_field *field;
 
 	field = evsel->tp_format->format.fields;
 	while (field) {
@@ -2305,7 +2305,7 @@ static int add_all_matching_fields(struct perf_evlist *evlist,
 {
 	int ret = -ESRCH;
 	struct perf_evsel *evsel;
-	struct format_field *field;
+	struct tep_format_field *field;
 
 	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
@@ -2327,7 +2327,7 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok,
 {
 	char *str, *event_name, *field_name, *opt_name;
 	struct perf_evsel *evsel;
-	struct format_field *field;
+	struct tep_format_field *field;
 	bool raw_trace = symbol_conf.raw_trace;
 	int ret = 0;
 
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
new file mode 100644
index 000000000000..e7b4c44ebb62
--- /dev/null
+++ b/tools/perf/util/stat-display.c
@@ -0,0 +1,1166 @@
+#include <stdio.h>
+#include <inttypes.h>
+#include <linux/time64.h>
+#include <math.h>
+#include "evlist.h"
+#include "evsel.h"
+#include "stat.h"
+#include "top.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "string2.h"
+#include "sane_ctype.h"
+#include "cgroup.h"
+#include <math.h>
+#include <api/fs/fs.h>
+
+#define CNTR_NOT_SUPPORTED	"<not supported>"
+#define CNTR_NOT_COUNTED	"<not counted>"
+
+static bool is_duration_time(struct perf_evsel *evsel)
+{
+	return !strcmp(evsel->name, "duration_time");
+}
+
+static void print_running(struct perf_stat_config *config,
+			  u64 run, u64 ena)
+{
+	if (config->csv_output) {
+		fprintf(config->output, "%s%" PRIu64 "%s%.2f",
+					config->csv_sep,
+					run,
+					config->csv_sep,
+					ena ? 100.0 * run / ena : 100.0);
+	} else if (run != ena) {
+		fprintf(config->output, "  (%.2f%%)", 100.0 * run / ena);
+	}
+}
+
+static void print_noise_pct(struct perf_stat_config *config,
+			    double total, double avg)
+{
+	double pct = rel_stddev_stats(total, avg);
+
+	if (config->csv_output)
+		fprintf(config->output, "%s%.2f%%", config->csv_sep, pct);
+	else if (pct)
+		fprintf(config->output, "  ( +-%6.2f%% )", pct);
+}
+
+static void print_noise(struct perf_stat_config *config,
+			struct perf_evsel *evsel, double avg)
+{
+	struct perf_stat_evsel *ps;
+
+	if (config->run_count == 1)
+		return;
+
+	ps = evsel->stats;
+	print_noise_pct(config, stddev_stats(&ps->res_stats[0]), avg);
+}
+
+static void aggr_printout(struct perf_stat_config *config,
+			  struct perf_evsel *evsel, int id, int nr)
+{
+	switch (config->aggr_mode) {
+	case AGGR_CORE:
+		fprintf(config->output, "S%d-C%*d%s%*d%s",
+			cpu_map__id_to_socket(id),
+			config->csv_output ? 0 : -8,
+			cpu_map__id_to_cpu(id),
+			config->csv_sep,
+			config->csv_output ? 0 : 4,
+			nr,
+			config->csv_sep);
+		break;
+	case AGGR_SOCKET:
+		fprintf(config->output, "S%*d%s%*d%s",
+			config->csv_output ? 0 : -5,
+			id,
+			config->csv_sep,
+			config->csv_output ? 0 : 4,
+			nr,
+			config->csv_sep);
+			break;
+	case AGGR_NONE:
+		fprintf(config->output, "CPU%*d%s",
+			config->csv_output ? 0 : -4,
+			perf_evsel__cpus(evsel)->map[id], config->csv_sep);
+		break;
+	case AGGR_THREAD:
+		fprintf(config->output, "%*s-%*d%s",
+			config->csv_output ? 0 : 16,
+			thread_map__comm(evsel->threads, id),
+			config->csv_output ? 0 : -8,
+			thread_map__pid(evsel->threads, id),
+			config->csv_sep);
+		break;
+	case AGGR_GLOBAL:
+	case AGGR_UNSET:
+	default:
+		break;
+	}
+}
+
+struct outstate {
+	FILE *fh;
+	bool newline;
+	const char *prefix;
+	int  nfields;
+	int  id, nr;
+	struct perf_evsel *evsel;
+};
+
+#define METRIC_LEN  35
+
+static void new_line_std(struct perf_stat_config *config __maybe_unused,
+			 void *ctx)
+{
+	struct outstate *os = ctx;
+
+	os->newline = true;
+}
+
+static void do_new_line_std(struct perf_stat_config *config,
+			    struct outstate *os)
+{
+	fputc('\n', os->fh);
+	fputs(os->prefix, os->fh);
+	aggr_printout(config, os->evsel, os->id, os->nr);
+	if (config->aggr_mode == AGGR_NONE)
+		fprintf(os->fh, "        ");
+	fprintf(os->fh, "                                                 ");
+}
+
+static void print_metric_std(struct perf_stat_config *config,
+			     void *ctx, const char *color, const char *fmt,
+			     const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	int n;
+	bool newline = os->newline;
+
+	os->newline = false;
+
+	if (unit == NULL || fmt == NULL) {
+		fprintf(out, "%-*s", METRIC_LEN, "");
+		return;
+	}
+
+	if (newline)
+		do_new_line_std(config, os);
+
+	n = fprintf(out, " # ");
+	if (color)
+		n += color_fprintf(out, color, fmt, val);
+	else
+		n += fprintf(out, fmt, val);
+	fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
+}
+
+static void new_line_csv(struct perf_stat_config *config, void *ctx)
+{
+	struct outstate *os = ctx;
+	int i;
+
+	fputc('\n', os->fh);
+	if (os->prefix)
+		fprintf(os->fh, "%s%s", os->prefix, config->csv_sep);
+	aggr_printout(config, os->evsel, os->id, os->nr);
+	for (i = 0; i < os->nfields; i++)
+		fputs(config->csv_sep, os->fh);
+}
+
+static void print_metric_csv(struct perf_stat_config *config __maybe_unused,
+			     void *ctx,
+			     const char *color __maybe_unused,
+			     const char *fmt, const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	char buf[64], *vals, *ends;
+
+	if (unit == NULL || fmt == NULL) {
+		fprintf(out, "%s%s", config->csv_sep, config->csv_sep);
+		return;
+	}
+	snprintf(buf, sizeof(buf), fmt, val);
+	ends = vals = ltrim(buf);
+	while (isdigit(*ends) || *ends == '.')
+		ends++;
+	*ends = 0;
+	while (isspace(*unit))
+		unit++;
+	fprintf(out, "%s%s%s%s", config->csv_sep, vals, config->csv_sep, unit);
+}
+
+/* Filter out some columns that don't work well in metrics only mode */
+
+static bool valid_only_metric(const char *unit)
+{
+	if (!unit)
+		return false;
+	if (strstr(unit, "/sec") ||
+	    strstr(unit, "hz") ||
+	    strstr(unit, "Hz") ||
+	    strstr(unit, "CPUs utilized"))
+		return false;
+	return true;
+}
+
+static const char *fixunit(char *buf, struct perf_evsel *evsel,
+			   const char *unit)
+{
+	if (!strncmp(unit, "of all", 6)) {
+		snprintf(buf, 1024, "%s %s", perf_evsel__name(evsel),
+			 unit);
+		return buf;
+	}
+	return unit;
+}
+
+static void print_metric_only(struct perf_stat_config *config,
+			      void *ctx, const char *color, const char *fmt,
+			      const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	char buf[1024], str[1024];
+	unsigned mlen = config->metric_only_len;
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(buf, os->evsel, unit);
+	if (mlen < strlen(unit))
+		mlen = strlen(unit) + 1;
+
+	if (color)
+		mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1;
+
+	color_snprintf(str, sizeof(str), color ?: "", fmt, val);
+	fprintf(out, "%*s ", mlen, str);
+}
+
+static void print_metric_only_csv(struct perf_stat_config *config __maybe_unused,
+				  void *ctx, const char *color __maybe_unused,
+				  const char *fmt,
+				  const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	char buf[64], *vals, *ends;
+	char tbuf[1024];
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(tbuf, os->evsel, unit);
+	snprintf(buf, sizeof buf, fmt, val);
+	ends = vals = ltrim(buf);
+	while (isdigit(*ends) || *ends == '.')
+		ends++;
+	*ends = 0;
+	fprintf(out, "%s%s", vals, config->csv_sep);
+}
+
+static void new_line_metric(struct perf_stat_config *config __maybe_unused,
+			    void *ctx __maybe_unused)
+{
+}
+
+static void print_metric_header(struct perf_stat_config *config,
+				void *ctx, const char *color __maybe_unused,
+				const char *fmt __maybe_unused,
+				const char *unit, double val __maybe_unused)
+{
+	struct outstate *os = ctx;
+	char tbuf[1024];
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(tbuf, os->evsel, unit);
+	if (config->csv_output)
+		fprintf(os->fh, "%s%s", unit, config->csv_sep);
+	else
+		fprintf(os->fh, "%*s ", config->metric_only_len, unit);
+}
+
+static int first_shadow_cpu(struct perf_stat_config *config,
+			    struct perf_evsel *evsel, int id)
+{
+	struct perf_evlist *evlist = evsel->evlist;
+	int i;
+
+	if (!config->aggr_get_id)
+		return 0;
+
+	if (config->aggr_mode == AGGR_NONE)
+		return id;
+
+	if (config->aggr_mode == AGGR_GLOBAL)
+		return 0;
+
+	for (i = 0; i < perf_evsel__nr_cpus(evsel); i++) {
+		int cpu2 = perf_evsel__cpus(evsel)->map[i];
+
+		if (config->aggr_get_id(config, evlist->cpus, cpu2) == id)
+			return cpu2;
+	}
+	return 0;
+}
+
+static void abs_printout(struct perf_stat_config *config,
+			 int id, int nr, struct perf_evsel *evsel, double avg)
+{
+	FILE *output = config->output;
+	double sc =  evsel->scale;
+	const char *fmt;
+
+	if (config->csv_output) {
+		fmt = floor(sc) != sc ?  "%.2f%s" : "%.0f%s";
+	} else {
+		if (config->big_num)
+			fmt = floor(sc) != sc ? "%'18.2f%s" : "%'18.0f%s";
+		else
+			fmt = floor(sc) != sc ? "%18.2f%s" : "%18.0f%s";
+	}
+
+	aggr_printout(config, evsel, id, nr);
+
+	fprintf(output, fmt, avg, config->csv_sep);
+
+	if (evsel->unit)
+		fprintf(output, "%-*s%s",
+			config->csv_output ? 0 : config->unit_width,
+			evsel->unit, config->csv_sep);
+
+	fprintf(output, "%-*s", config->csv_output ? 0 : 25, perf_evsel__name(evsel));
+
+	if (evsel->cgrp)
+		fprintf(output, "%s%s", config->csv_sep, evsel->cgrp->name);
+}
+
+static bool is_mixed_hw_group(struct perf_evsel *counter)
+{
+	struct perf_evlist *evlist = counter->evlist;
+	u32 pmu_type = counter->attr.type;
+	struct perf_evsel *pos;
+
+	if (counter->nr_members < 2)
+		return false;
+
+	evlist__for_each_entry(evlist, pos) {
+		/* software events can be part of any hardware group */
+		if (pos->attr.type == PERF_TYPE_SOFTWARE)
+			continue;
+		if (pmu_type == PERF_TYPE_SOFTWARE) {
+			pmu_type = pos->attr.type;
+			continue;
+		}
+		if (pmu_type != pos->attr.type)
+			return true;
+	}
+
+	return false;
+}
+
+static void printout(struct perf_stat_config *config, int id, int nr,
+		     struct perf_evsel *counter, double uval,
+		     char *prefix, u64 run, u64 ena, double noise,
+		     struct runtime_stat *st)
+{
+	struct perf_stat_output_ctx out;
+	struct outstate os = {
+		.fh = config->output,
+		.prefix = prefix ? prefix : "",
+		.id = id,
+		.nr = nr,
+		.evsel = counter,
+	};
+	print_metric_t pm = print_metric_std;
+	new_line_t nl;
+
+	if (config->metric_only) {
+		nl = new_line_metric;
+		if (config->csv_output)
+			pm = print_metric_only_csv;
+		else
+			pm = print_metric_only;
+	} else
+		nl = new_line_std;
+
+	if (config->csv_output && !config->metric_only) {
+		static int aggr_fields[] = {
+			[AGGR_GLOBAL] = 0,
+			[AGGR_THREAD] = 1,
+			[AGGR_NONE] = 1,
+			[AGGR_SOCKET] = 2,
+			[AGGR_CORE] = 2,
+		};
+
+		pm = print_metric_csv;
+		nl = new_line_csv;
+		os.nfields = 3;
+		os.nfields += aggr_fields[config->aggr_mode];
+		if (counter->cgrp)
+			os.nfields++;
+	}
+	if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
+		if (config->metric_only) {
+			pm(config, &os, NULL, "", "", 0);
+			return;
+		}
+		aggr_printout(config, counter, id, nr);
+
+		fprintf(config->output, "%*s%s",
+			config->csv_output ? 0 : 18,
+			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
+			config->csv_sep);
+
+		if (counter->supported) {
+			config->print_free_counters_hint = 1;
+			if (is_mixed_hw_group(counter))
+				config->print_mixed_hw_group_error = 1;
+		}
+
+		fprintf(config->output, "%-*s%s",
+			config->csv_output ? 0 : config->unit_width,
+			counter->unit, config->csv_sep);
+
+		fprintf(config->output, "%*s",
+			config->csv_output ? 0 : -25,
+			perf_evsel__name(counter));
+
+		if (counter->cgrp)
+			fprintf(config->output, "%s%s",
+				config->csv_sep, counter->cgrp->name);
+
+		if (!config->csv_output)
+			pm(config, &os, NULL, NULL, "", 0);
+		print_noise(config, counter, noise);
+		print_running(config, run, ena);
+		if (config->csv_output)
+			pm(config, &os, NULL, NULL, "", 0);
+		return;
+	}
+
+	if (!config->metric_only)
+		abs_printout(config, id, nr, counter, uval);
+
+	out.print_metric = pm;
+	out.new_line = nl;
+	out.ctx = &os;
+	out.force_header = false;
+
+	if (config->csv_output && !config->metric_only) {
+		print_noise(config, counter, noise);
+		print_running(config, run, ena);
+	}
+
+	perf_stat__print_shadow_stats(config, counter, uval,
+				first_shadow_cpu(config, counter, id),
+				&out, &config->metric_events, st);
+	if (!config->csv_output && !config->metric_only) {
+		print_noise(config, counter, noise);
+		print_running(config, run, ena);
+	}
+}
+
+static void aggr_update_shadow(struct perf_stat_config *config,
+			       struct perf_evlist *evlist)
+{
+	int cpu, s2, id, s;
+	u64 val;
+	struct perf_evsel *counter;
+
+	for (s = 0; s < config->aggr_map->nr; s++) {
+		id = config->aggr_map->map[s];
+		evlist__for_each_entry(evlist, counter) {
+			val = 0;
+			for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+				s2 = config->aggr_get_id(config, evlist->cpus, cpu);
+				if (s2 != id)
+					continue;
+				val += perf_counts(counter->counts, cpu, 0)->val;
+			}
+			perf_stat__update_shadow_stats(counter, val,
+					first_shadow_cpu(config, counter, id),
+					&rt_stat);
+		}
+	}
+}
+
+static void uniquify_event_name(struct perf_evsel *counter)
+{
+	char *new_name;
+	char *config;
+
+	if (counter->uniquified_name ||
+	    !counter->pmu_name || !strncmp(counter->name, counter->pmu_name,
+					   strlen(counter->pmu_name)))
+		return;
+
+	config = strchr(counter->name, '/');
+	if (config) {
+		if (asprintf(&new_name,
+			     "%s%s", counter->pmu_name, config) > 0) {
+			free(counter->name);
+			counter->name = new_name;
+		}
+	} else {
+		if (asprintf(&new_name,
+			     "%s [%s]", counter->name, counter->pmu_name) > 0) {
+			free(counter->name);
+			counter->name = new_name;
+		}
+	}
+
+	counter->uniquified_name = true;
+}
+
+static void collect_all_aliases(struct perf_stat_config *config, struct perf_evsel *counter,
+			    void (*cb)(struct perf_stat_config *config, struct perf_evsel *counter, void *data,
+				       bool first),
+			    void *data)
+{
+	struct perf_evlist *evlist = counter->evlist;
+	struct perf_evsel *alias;
+
+	alias = list_prepare_entry(counter, &(evlist->entries), node);
+	list_for_each_entry_continue (alias, &evlist->entries, node) {
+		if (strcmp(perf_evsel__name(alias), perf_evsel__name(counter)) ||
+		    alias->scale != counter->scale ||
+		    alias->cgrp != counter->cgrp ||
+		    strcmp(alias->unit, counter->unit) ||
+		    perf_evsel__is_clock(alias) != perf_evsel__is_clock(counter))
+			break;
+		alias->merged_stat = true;
+		cb(config, alias, data, false);
+	}
+}
+
+static bool collect_data(struct perf_stat_config *config, struct perf_evsel *counter,
+			    void (*cb)(struct perf_stat_config *config, struct perf_evsel *counter, void *data,
+				       bool first),
+			    void *data)
+{
+	if (counter->merged_stat)
+		return false;
+	cb(config, counter, data, true);
+	if (config->no_merge)
+		uniquify_event_name(counter);
+	else if (counter->auto_merge_stats)
+		collect_all_aliases(config, counter, cb, data);
+	return true;
+}
+
+struct aggr_data {
+	u64 ena, run, val;
+	int id;
+	int nr;
+	int cpu;
+};
+
+static void aggr_cb(struct perf_stat_config *config,
+		    struct perf_evsel *counter, void *data, bool first)
+{
+	struct aggr_data *ad = data;
+	int cpu, s2;
+
+	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+		struct perf_counts_values *counts;
+
+		s2 = config->aggr_get_id(config, perf_evsel__cpus(counter), cpu);
+		if (s2 != ad->id)
+			continue;
+		if (first)
+			ad->nr++;
+		counts = perf_counts(counter->counts, cpu, 0);
+		/*
+		 * When any result is bad, make them all to give
+		 * consistent output in interval mode.
+		 */
+		if (counts->ena == 0 || counts->run == 0 ||
+		    counter->counts->scaled == -1) {
+			ad->ena = 0;
+			ad->run = 0;
+			break;
+		}
+		ad->val += counts->val;
+		ad->ena += counts->ena;
+		ad->run += counts->run;
+	}
+}
+
+static void print_aggr(struct perf_stat_config *config,
+		       struct perf_evlist *evlist,
+		       char *prefix)
+{
+	bool metric_only = config->metric_only;
+	FILE *output = config->output;
+	struct perf_evsel *counter;
+	int s, id, nr;
+	double uval;
+	u64 ena, run, val;
+	bool first;
+
+	if (!(config->aggr_map || config->aggr_get_id))
+		return;
+
+	aggr_update_shadow(config, evlist);
+
+	/*
+	 * With metric_only everything is on a single line.
+	 * Without each counter has its own line.
+	 */
+	for (s = 0; s < config->aggr_map->nr; s++) {
+		struct aggr_data ad;
+		if (prefix && metric_only)
+			fprintf(output, "%s", prefix);
+
+		ad.id = id = config->aggr_map->map[s];
+		first = true;
+		evlist__for_each_entry(evlist, counter) {
+			if (is_duration_time(counter))
+				continue;
+
+			ad.val = ad.ena = ad.run = 0;
+			ad.nr = 0;
+			if (!collect_data(config, counter, aggr_cb, &ad))
+				continue;
+			nr = ad.nr;
+			ena = ad.ena;
+			run = ad.run;
+			val = ad.val;
+			if (first && metric_only) {
+				first = false;
+				aggr_printout(config, counter, id, nr);
+			}
+			if (prefix && !metric_only)
+				fprintf(output, "%s", prefix);
+
+			uval = val * counter->scale;
+			printout(config, id, nr, counter, uval, prefix,
+				 run, ena, 1.0, &rt_stat);
+			if (!metric_only)
+				fputc('\n', output);
+		}
+		if (metric_only)
+			fputc('\n', output);
+	}
+}
+
+static int cmp_val(const void *a, const void *b)
+{
+	return ((struct perf_aggr_thread_value *)b)->val -
+		((struct perf_aggr_thread_value *)a)->val;
+}
+
+static struct perf_aggr_thread_value *sort_aggr_thread(
+					struct perf_evsel *counter,
+					int nthreads, int ncpus,
+					int *ret,
+					struct target *_target)
+{
+	int cpu, thread, i = 0;
+	double uval;
+	struct perf_aggr_thread_value *buf;
+
+	buf = calloc(nthreads, sizeof(struct perf_aggr_thread_value));
+	if (!buf)
+		return NULL;
+
+	for (thread = 0; thread < nthreads; thread++) {
+		u64 ena = 0, run = 0, val = 0;
+
+		for (cpu = 0; cpu < ncpus; cpu++) {
+			val += perf_counts(counter->counts, cpu, thread)->val;
+			ena += perf_counts(counter->counts, cpu, thread)->ena;
+			run += perf_counts(counter->counts, cpu, thread)->run;
+		}
+
+		uval = val * counter->scale;
+
+		/*
+		 * Skip value 0 when enabling --per-thread globally,
+		 * otherwise too many 0 output.
+		 */
+		if (uval == 0.0 && target__has_per_thread(_target))
+			continue;
+
+		buf[i].counter = counter;
+		buf[i].id = thread;
+		buf[i].uval = uval;
+		buf[i].val = val;
+		buf[i].run = run;
+		buf[i].ena = ena;
+		i++;
+	}
+
+	qsort(buf, i, sizeof(struct perf_aggr_thread_value), cmp_val);
+
+	if (ret)
+		*ret = i;
+
+	return buf;
+}
+
+static void print_aggr_thread(struct perf_stat_config *config,
+			      struct target *_target,
+			      struct perf_evsel *counter, char *prefix)
+{
+	FILE *output = config->output;
+	int nthreads = thread_map__nr(counter->threads);
+	int ncpus = cpu_map__nr(counter->cpus);
+	int thread, sorted_threads, id;
+	struct perf_aggr_thread_value *buf;
+
+	buf = sort_aggr_thread(counter, nthreads, ncpus, &sorted_threads, _target);
+	if (!buf) {
+		perror("cannot sort aggr thread");
+		return;
+	}
+
+	for (thread = 0; thread < sorted_threads; thread++) {
+		if (prefix)
+			fprintf(output, "%s", prefix);
+
+		id = buf[thread].id;
+		if (config->stats)
+			printout(config, id, 0, buf[thread].counter, buf[thread].uval,
+				 prefix, buf[thread].run, buf[thread].ena, 1.0,
+				 &config->stats[id]);
+		else
+			printout(config, id, 0, buf[thread].counter, buf[thread].uval,
+				 prefix, buf[thread].run, buf[thread].ena, 1.0,
+				 &rt_stat);
+		fputc('\n', output);
+	}
+
+	free(buf);
+}
+
+struct caggr_data {
+	double avg, avg_enabled, avg_running;
+};
+
+static void counter_aggr_cb(struct perf_stat_config *config __maybe_unused,
+			    struct perf_evsel *counter, void *data,
+			    bool first __maybe_unused)
+{
+	struct caggr_data *cd = data;
+	struct perf_stat_evsel *ps = counter->stats;
+
+	cd->avg += avg_stats(&ps->res_stats[0]);
+	cd->avg_enabled += avg_stats(&ps->res_stats[1]);
+	cd->avg_running += avg_stats(&ps->res_stats[2]);
+}
+
+/*
+ * Print out the results of a single counter:
+ * aggregated counts in system-wide mode
+ */
+static void print_counter_aggr(struct perf_stat_config *config,
+			       struct perf_evsel *counter, char *prefix)
+{
+	bool metric_only = config->metric_only;
+	FILE *output = config->output;
+	double uval;
+	struct caggr_data cd = { .avg = 0.0 };
+
+	if (!collect_data(config, counter, counter_aggr_cb, &cd))
+		return;
+
+	if (prefix && !metric_only)
+		fprintf(output, "%s", prefix);
+
+	uval = cd.avg * counter->scale;
+	printout(config, -1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled,
+		 cd.avg, &rt_stat);
+	if (!metric_only)
+		fprintf(output, "\n");
+}
+
+static void counter_cb(struct perf_stat_config *config __maybe_unused,
+		       struct perf_evsel *counter, void *data,
+		       bool first __maybe_unused)
+{
+	struct aggr_data *ad = data;
+
+	ad->val += perf_counts(counter->counts, ad->cpu, 0)->val;
+	ad->ena += perf_counts(counter->counts, ad->cpu, 0)->ena;
+	ad->run += perf_counts(counter->counts, ad->cpu, 0)->run;
+}
+
+/*
+ * Print out the results of a single counter:
+ * does not use aggregated count in system-wide
+ */
+static void print_counter(struct perf_stat_config *config,
+			  struct perf_evsel *counter, char *prefix)
+{
+	FILE *output = config->output;
+	u64 ena, run, val;
+	double uval;
+	int cpu;
+
+	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+		struct aggr_data ad = { .cpu = cpu };
+
+		if (!collect_data(config, counter, counter_cb, &ad))
+			return;
+		val = ad.val;
+		ena = ad.ena;
+		run = ad.run;
+
+		if (prefix)
+			fprintf(output, "%s", prefix);
+
+		uval = val * counter->scale;
+		printout(config, cpu, 0, counter, uval, prefix, run, ena, 1.0,
+			 &rt_stat);
+
+		fputc('\n', output);
+	}
+}
+
+static void print_no_aggr_metric(struct perf_stat_config *config,
+				 struct perf_evlist *evlist,
+				 char *prefix)
+{
+	int cpu;
+	int nrcpus = 0;
+	struct perf_evsel *counter;
+	u64 ena, run, val;
+	double uval;
+
+	nrcpus = evlist->cpus->nr;
+	for (cpu = 0; cpu < nrcpus; cpu++) {
+		bool first = true;
+
+		if (prefix)
+			fputs(prefix, config->output);
+		evlist__for_each_entry(evlist, counter) {
+			if (is_duration_time(counter))
+				continue;
+			if (first) {
+				aggr_printout(config, counter, cpu, 0);
+				first = false;
+			}
+			val = perf_counts(counter->counts, cpu, 0)->val;
+			ena = perf_counts(counter->counts, cpu, 0)->ena;
+			run = perf_counts(counter->counts, cpu, 0)->run;
+
+			uval = val * counter->scale;
+			printout(config, cpu, 0, counter, uval, prefix, run, ena, 1.0,
+				 &rt_stat);
+		}
+		fputc('\n', config->output);
+	}
+}
+
+static int aggr_header_lens[] = {
+	[AGGR_CORE] = 18,
+	[AGGR_SOCKET] = 12,
+	[AGGR_NONE] = 6,
+	[AGGR_THREAD] = 24,
+	[AGGR_GLOBAL] = 0,
+};
+
+static const char *aggr_header_csv[] = {
+	[AGGR_CORE] 	= 	"core,cpus,",
+	[AGGR_SOCKET] 	= 	"socket,cpus",
+	[AGGR_NONE] 	= 	"cpu,",
+	[AGGR_THREAD] 	= 	"comm-pid,",
+	[AGGR_GLOBAL] 	=	""
+};
+
+static void print_metric_headers(struct perf_stat_config *config,
+				 struct perf_evlist *evlist,
+				 const char *prefix, bool no_indent)
+{
+	struct perf_stat_output_ctx out;
+	struct perf_evsel *counter;
+	struct outstate os = {
+		.fh = config->output
+	};
+
+	if (prefix)
+		fprintf(config->output, "%s", prefix);
+
+	if (!config->csv_output && !no_indent)
+		fprintf(config->output, "%*s",
+			aggr_header_lens[config->aggr_mode], "");
+	if (config->csv_output) {
+		if (config->interval)
+			fputs("time,", config->output);
+		fputs(aggr_header_csv[config->aggr_mode], config->output);
+	}
+
+	/* Print metrics headers only */
+	evlist__for_each_entry(evlist, counter) {
+		if (is_duration_time(counter))
+			continue;
+		os.evsel = counter;
+		out.ctx = &os;
+		out.print_metric = print_metric_header;
+		out.new_line = new_line_metric;
+		out.force_header = true;
+		os.evsel = counter;
+		perf_stat__print_shadow_stats(config, counter, 0,
+					      0,
+					      &out,
+					      &config->metric_events,
+					      &rt_stat);
+	}
+	fputc('\n', config->output);
+}
+
+static void print_interval(struct perf_stat_config *config,
+			   struct perf_evlist *evlist,
+			   char *prefix, struct timespec *ts)
+{
+	bool metric_only = config->metric_only;
+	unsigned int unit_width = config->unit_width;
+	FILE *output = config->output;
+	static int num_print_interval;
+
+	if (config->interval_clear)
+		puts(CONSOLE_CLEAR);
+
+	sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, config->csv_sep);
+
+	if ((num_print_interval == 0 && !config->csv_output) || config->interval_clear) {
+		switch (config->aggr_mode) {
+		case AGGR_SOCKET:
+			fprintf(output, "#           time socket cpus");
+			if (!metric_only)
+				fprintf(output, "             counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_CORE:
+			fprintf(output, "#           time core         cpus");
+			if (!metric_only)
+				fprintf(output, "             counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_NONE:
+			fprintf(output, "#           time CPU    ");
+			if (!metric_only)
+				fprintf(output, "                counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_THREAD:
+			fprintf(output, "#           time             comm-pid");
+			if (!metric_only)
+				fprintf(output, "                  counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_GLOBAL:
+		default:
+			fprintf(output, "#           time");
+			if (!metric_only)
+				fprintf(output, "             counts %*s events\n", unit_width, "unit");
+		case AGGR_UNSET:
+			break;
+		}
+	}
+
+	if ((num_print_interval == 0 || config->interval_clear) && metric_only)
+		print_metric_headers(config, evlist, " ", true);
+	if (++num_print_interval == 25)
+		num_print_interval = 0;
+}
+
+static void print_header(struct perf_stat_config *config,
+			 struct target *_target,
+			 int argc, const char **argv)
+{
+	FILE *output = config->output;
+	int i;
+
+	fflush(stdout);
+
+	if (!config->csv_output) {
+		fprintf(output, "\n");
+		fprintf(output, " Performance counter stats for ");
+		if (_target->system_wide)
+			fprintf(output, "\'system wide");
+		else if (_target->cpu_list)
+			fprintf(output, "\'CPU(s) %s", _target->cpu_list);
+		else if (!target__has_task(_target)) {
+			fprintf(output, "\'%s", argv ? argv[0] : "pipe");
+			for (i = 1; argv && (i < argc); i++)
+				fprintf(output, " %s", argv[i]);
+		} else if (_target->pid)
+			fprintf(output, "process id \'%s", _target->pid);
+		else
+			fprintf(output, "thread id \'%s", _target->tid);
+
+		fprintf(output, "\'");
+		if (config->run_count > 1)
+			fprintf(output, " (%d runs)", config->run_count);
+		fprintf(output, ":\n\n");
+	}
+}
+
+static int get_precision(double num)
+{
+	if (num > 1)
+		return 0;
+
+	return lround(ceil(-log10(num)));
+}
+
+static void print_table(struct perf_stat_config *config,
+			FILE *output, int precision, double avg)
+{
+	char tmp[64];
+	int idx, indent = 0;
+
+	scnprintf(tmp, 64, " %17.*f", precision, avg);
+	while (tmp[indent] == ' ')
+		indent++;
+
+	fprintf(output, "%*s# Table of individual measurements:\n", indent, "");
+
+	for (idx = 0; idx < config->run_count; idx++) {
+		double run = (double) config->walltime_run[idx] / NSEC_PER_SEC;
+		int h, n = 1 + abs((int) (100.0 * (run - avg)/run) / 5);
+
+		fprintf(output, " %17.*f (%+.*f) ",
+			precision, run, precision, run - avg);
+
+		for (h = 0; h < n; h++)
+			fprintf(output, "#");
+
+		fprintf(output, "\n");
+	}
+
+	fprintf(output, "\n%*s# Final result:\n", indent, "");
+}
+
+static double timeval2double(struct timeval *t)
+{
+	return t->tv_sec + (double) t->tv_usec/USEC_PER_SEC;
+}
+
+static void print_footer(struct perf_stat_config *config)
+{
+	double avg = avg_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC;
+	FILE *output = config->output;
+	int n;
+
+	if (!config->null_run)
+		fprintf(output, "\n");
+
+	if (config->run_count == 1) {
+		fprintf(output, " %17.9f seconds time elapsed", avg);
+
+		if (config->ru_display) {
+			double ru_utime = timeval2double(&config->ru_data.ru_utime);
+			double ru_stime = timeval2double(&config->ru_data.ru_stime);
+
+			fprintf(output, "\n\n");
+			fprintf(output, " %17.9f seconds user\n", ru_utime);
+			fprintf(output, " %17.9f seconds sys\n", ru_stime);
+		}
+	} else {
+		double sd = stddev_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC;
+		/*
+		 * Display at most 2 more significant
+		 * digits than the stddev inaccuracy.
+		 */
+		int precision = get_precision(sd) + 2;
+
+		if (config->walltime_run_table)
+			print_table(config, output, precision, avg);
+
+		fprintf(output, " %17.*f +- %.*f seconds time elapsed",
+			precision, avg, precision, sd);
+
+		print_noise_pct(config, sd, avg);
+	}
+	fprintf(output, "\n\n");
+
+	if (config->print_free_counters_hint &&
+	    sysctl__read_int("kernel/nmi_watchdog", &n) >= 0 &&
+	    n > 0)
+		fprintf(output,
+"Some events weren't counted. Try disabling the NMI watchdog:\n"
+"	echo 0 > /proc/sys/kernel/nmi_watchdog\n"
+"	perf stat ...\n"
+"	echo 1 > /proc/sys/kernel/nmi_watchdog\n");
+
+	if (config->print_mixed_hw_group_error)
+		fprintf(output,
+			"The events in group usually have to be from "
+			"the same PMU. Try reorganizing the group.\n");
+}
+
+void
+perf_evlist__print_counters(struct perf_evlist *evlist,
+			    struct perf_stat_config *config,
+			    struct target *_target,
+			    struct timespec *ts,
+			    int argc, const char **argv)
+{
+	bool metric_only = config->metric_only;
+	int interval = config->interval;
+	struct perf_evsel *counter;
+	char buf[64], *prefix = NULL;
+
+	if (interval)
+		print_interval(config, evlist, prefix = buf, ts);
+	else
+		print_header(config, _target, argc, argv);
+
+	if (metric_only) {
+		static int num_print_iv;
+
+		if (num_print_iv == 0 && !interval)
+			print_metric_headers(config, evlist, prefix, false);
+		if (num_print_iv++ == 25)
+			num_print_iv = 0;
+		if (config->aggr_mode == AGGR_GLOBAL && prefix)
+			fprintf(config->output, "%s", prefix);
+	}
+
+	switch (config->aggr_mode) {
+	case AGGR_CORE:
+	case AGGR_SOCKET:
+		print_aggr(config, evlist, prefix);
+		break;
+	case AGGR_THREAD:
+		evlist__for_each_entry(evlist, counter) {
+			if (is_duration_time(counter))
+				continue;
+			print_aggr_thread(config, _target, counter, prefix);
+		}
+		break;
+	case AGGR_GLOBAL:
+		evlist__for_each_entry(evlist, counter) {
+			if (is_duration_time(counter))
+				continue;
+			print_counter_aggr(config, counter, prefix);
+		}
+		if (metric_only)
+			fputc('\n', config->output);
+		break;
+	case AGGR_NONE:
+		if (metric_only)
+			print_no_aggr_metric(config, evlist, prefix);
+		else {
+			evlist__for_each_entry(evlist, counter) {
+				if (is_duration_time(counter))
+					continue;
+				print_counter(config, counter, prefix);
+			}
+		}
+		break;
+	case AGGR_UNSET:
+	default:
+		break;
+	}
+
+	if (!interval && !config->csv_output)
+		print_footer(config);
+
+	fflush(config->output);
+}
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 99990f5f2512..8ad32763cfff 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -410,7 +410,8 @@ static double runtime_stat_n(struct runtime_stat *st,
 	return v->stats.n;
 }
 
-static void print_stalled_cycles_frontend(int cpu,
+static void print_stalled_cycles_frontend(struct perf_stat_config *config,
+					  int cpu,
 					  struct perf_evsel *evsel, double avg,
 					  struct perf_stat_output_ctx *out,
 					  struct runtime_stat *st)
@@ -427,13 +428,14 @@ static void print_stalled_cycles_frontend(int cpu,
 	color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
 
 	if (ratio)
-		out->print_metric(out->ctx, color, "%7.2f%%", "frontend cycles idle",
+		out->print_metric(config, out->ctx, color, "%7.2f%%", "frontend cycles idle",
 				  ratio);
 	else
-		out->print_metric(out->ctx, NULL, NULL, "frontend cycles idle", 0);
+		out->print_metric(config, out->ctx, NULL, NULL, "frontend cycles idle", 0);
 }
 
-static void print_stalled_cycles_backend(int cpu,
+static void print_stalled_cycles_backend(struct perf_stat_config *config,
+					 int cpu,
 					 struct perf_evsel *evsel, double avg,
 					 struct perf_stat_output_ctx *out,
 					 struct runtime_stat *st)
@@ -449,10 +451,11 @@ static void print_stalled_cycles_backend(int cpu,
 
 	color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
 
-	out->print_metric(out->ctx, color, "%7.2f%%", "backend cycles idle", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "backend cycles idle", ratio);
 }
 
-static void print_branch_misses(int cpu,
+static void print_branch_misses(struct perf_stat_config *config,
+				int cpu,
 				struct perf_evsel *evsel,
 				double avg,
 				struct perf_stat_output_ctx *out,
@@ -469,10 +472,11 @@ static void print_branch_misses(int cpu,
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all branches", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all branches", ratio);
 }
 
-static void print_l1_dcache_misses(int cpu,
+static void print_l1_dcache_misses(struct perf_stat_config *config,
+				   int cpu,
 				   struct perf_evsel *evsel,
 				   double avg,
 				   struct perf_stat_output_ctx *out,
@@ -490,10 +494,11 @@ static void print_l1_dcache_misses(int cpu,
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio);
 }
 
-static void print_l1_icache_misses(int cpu,
+static void print_l1_icache_misses(struct perf_stat_config *config,
+				   int cpu,
 				   struct perf_evsel *evsel,
 				   double avg,
 				   struct perf_stat_output_ctx *out,
@@ -510,10 +515,11 @@ static void print_l1_icache_misses(int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio);
 }
 
-static void print_dtlb_cache_misses(int cpu,
+static void print_dtlb_cache_misses(struct perf_stat_config *config,
+				    int cpu,
 				    struct perf_evsel *evsel,
 				    double avg,
 				    struct perf_stat_output_ctx *out,
@@ -529,10 +535,11 @@ static void print_dtlb_cache_misses(int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio);
 }
 
-static void print_itlb_cache_misses(int cpu,
+static void print_itlb_cache_misses(struct perf_stat_config *config,
+				    int cpu,
 				    struct perf_evsel *evsel,
 				    double avg,
 				    struct perf_stat_output_ctx *out,
@@ -548,10 +555,11 @@ static void print_itlb_cache_misses(int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio);
 }
 
-static void print_ll_cache_misses(int cpu,
+static void print_ll_cache_misses(struct perf_stat_config *config,
+				  int cpu,
 				  struct perf_evsel *evsel,
 				  double avg,
 				  struct perf_stat_output_ctx *out,
@@ -567,7 +575,7 @@ static void print_ll_cache_misses(int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
 }
 
 /*
@@ -674,7 +682,8 @@ static double td_be_bound(int ctx, int cpu, struct runtime_stat *st)
 	return sanitize_val(1.0 - sum);
 }
 
-static void print_smi_cost(int cpu, struct perf_evsel *evsel,
+static void print_smi_cost(struct perf_stat_config *config,
+			   int cpu, struct perf_evsel *evsel,
 			   struct perf_stat_output_ctx *out,
 			   struct runtime_stat *st)
 {
@@ -694,11 +703,12 @@ static void print_smi_cost(int cpu, struct perf_evsel *evsel,
 
 	if (cost > 10)
 		color = PERF_COLOR_RED;
-	out->print_metric(out->ctx, color, "%8.1f%%", "SMI cycles%", cost);
-	out->print_metric(out->ctx, NULL, "%4.0f", "SMI#", smi_num);
+	out->print_metric(config, out->ctx, color, "%8.1f%%", "SMI cycles%", cost);
+	out->print_metric(config, out->ctx, NULL, "%4.0f", "SMI#", smi_num);
 }
 
-static void generic_metric(const char *metric_expr,
+static void generic_metric(struct perf_stat_config *config,
+			   const char *metric_expr,
 			   struct perf_evsel **metric_events,
 			   char *name,
 			   const char *metric_name,
@@ -737,20 +747,21 @@ static void generic_metric(const char *metric_expr,
 		const char *p = metric_expr;
 
 		if (expr__parse(&ratio, &pctx, &p) == 0)
-			print_metric(ctxp, NULL, "%8.1f",
+			print_metric(config, ctxp, NULL, "%8.1f",
 				metric_name ?
 				metric_name :
 				out->force_header ?  name : "",
 				ratio);
 		else
-			print_metric(ctxp, NULL, NULL,
+			print_metric(config, ctxp, NULL, NULL,
 				     out->force_header ?
 				     (metric_name ? metric_name : name) : "", 0);
 	} else
-		print_metric(ctxp, NULL, NULL, "", 0);
+		print_metric(config, ctxp, NULL, NULL, "", 0);
 }
 
-void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+void perf_stat__print_shadow_stats(struct perf_stat_config *config,
+				   struct perf_evsel *evsel,
 				   double avg, int cpu,
 				   struct perf_stat_output_ctx *out,
 				   struct rblist *metric_events,
@@ -769,10 +780,10 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 
 		if (total) {
 			ratio = avg / total;
-			print_metric(ctxp, NULL, "%7.2f ",
+			print_metric(config, ctxp, NULL, "%7.2f ",
 					"insn per cycle", ratio);
 		} else {
-			print_metric(ctxp, NULL, NULL, "insn per cycle", 0);
+			print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0);
 		}
 
 		total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT,
@@ -783,20 +794,20 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 						    ctx, cpu));
 
 		if (total && avg) {
-			out->new_line(ctxp);
+			out->new_line(config, ctxp);
 			ratio = total / avg;
-			print_metric(ctxp, NULL, "%7.2f ",
+			print_metric(config, ctxp, NULL, "%7.2f ",
 					"stalled cycles per insn",
 					ratio);
 		} else if (have_frontend_stalled) {
-			print_metric(ctxp, NULL, NULL,
+			print_metric(config, ctxp, NULL, NULL,
 				     "stalled cycles per insn", 0);
 		}
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
 		if (runtime_stat_n(st, STAT_BRANCHES, ctx, cpu) != 0)
-			print_branch_misses(cpu, evsel, avg, out, st);
+			print_branch_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all branches", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all branches", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |
@@ -804,9 +815,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
 		if (runtime_stat_n(st, STAT_L1_DCACHE, ctx, cpu) != 0)
-			print_l1_dcache_misses(cpu, evsel, avg, out, st);
+			print_l1_dcache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all L1-dcache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all L1-dcache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
@@ -814,9 +825,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
 		if (runtime_stat_n(st, STAT_L1_ICACHE, ctx, cpu) != 0)
-			print_l1_icache_misses(cpu, evsel, avg, out, st);
+			print_l1_icache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all L1-icache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all L1-icache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
@@ -824,9 +835,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
 		if (runtime_stat_n(st, STAT_DTLB_CACHE, ctx, cpu) != 0)
-			print_dtlb_cache_misses(cpu, evsel, avg, out, st);
+			print_dtlb_cache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all dTLB cache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all dTLB cache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
@@ -834,9 +845,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
 		if (runtime_stat_n(st, STAT_ITLB_CACHE, ctx, cpu) != 0)
-			print_itlb_cache_misses(cpu, evsel, avg, out, st);
+			print_itlb_cache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all iTLB cache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all iTLB cache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
@@ -844,9 +855,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
 		if (runtime_stat_n(st, STAT_LL_CACHE, ctx, cpu) != 0)
-			print_ll_cache_misses(cpu, evsel, avg, out, st);
+			print_ll_cache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all LL-cache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all LL-cache hits", 0);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
 		total = runtime_stat_avg(st, STAT_CACHEREFS, ctx, cpu);
 
@@ -854,32 +865,32 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 			ratio = avg * 100 / total;
 
 		if (runtime_stat_n(st, STAT_CACHEREFS, ctx, cpu) != 0)
-			print_metric(ctxp, NULL, "%8.3f %%",
+			print_metric(config, ctxp, NULL, "%8.3f %%",
 				     "of all cache refs", ratio);
 		else
-			print_metric(ctxp, NULL, NULL, "of all cache refs", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
-		print_stalled_cycles_frontend(cpu, evsel, avg, out, st);
+		print_stalled_cycles_frontend(config, cpu, evsel, avg, out, st);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
-		print_stalled_cycles_backend(cpu, evsel, avg, out, st);
+		print_stalled_cycles_backend(config, cpu, evsel, avg, out, st);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
 		total = runtime_stat_avg(st, STAT_NSECS, 0, cpu);
 
 		if (total) {
 			ratio = avg / total;
-			print_metric(ctxp, NULL, "%8.3f", "GHz", ratio);
+			print_metric(config, ctxp, NULL, "%8.3f", "GHz", ratio);
 		} else {
-			print_metric(ctxp, NULL, NULL, "Ghz", 0);
+			print_metric(config, ctxp, NULL, NULL, "Ghz", 0);
 		}
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
 		total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
 
 		if (total)
-			print_metric(ctxp, NULL,
+			print_metric(config, ctxp, NULL,
 					"%7.2f%%", "transactional cycles",
 					100.0 * (avg / total));
 		else
-			print_metric(ctxp, NULL, NULL, "transactional cycles",
+			print_metric(config, ctxp, NULL, NULL, "transactional cycles",
 				     0);
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
 		total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
@@ -888,10 +899,10 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 		if (total2 < avg)
 			total2 = avg;
 		if (total)
-			print_metric(ctxp, NULL, "%7.2f%%", "aborted cycles",
+			print_metric(config, ctxp, NULL, "%7.2f%%", "aborted cycles",
 				100.0 * ((total2-avg) / total));
 		else
-			print_metric(ctxp, NULL, NULL, "aborted cycles", 0);
+			print_metric(config, ctxp, NULL, NULL, "aborted cycles", 0);
 	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) {
 		total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
 					 ctx, cpu);
@@ -900,10 +911,10 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 			ratio = total / avg;
 
 		if (runtime_stat_n(st, STAT_CYCLES_IN_TX, ctx, cpu) != 0)
-			print_metric(ctxp, NULL, "%8.0f",
+			print_metric(config, ctxp, NULL, "%8.0f",
 				     "cycles / transaction", ratio);
 		else
-			print_metric(ctxp, NULL, NULL, "cycles / transaction",
+			print_metric(config, ctxp, NULL, NULL, "cycles / transaction",
 				      0);
 	} else if (perf_stat_evsel__is(evsel, ELISION_START)) {
 		total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
@@ -912,33 +923,33 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 		if (avg)
 			ratio = total / avg;
 
-		print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
+		print_metric(config, ctxp, NULL, "%8.0f", "cycles / elision", ratio);
 	} else if (perf_evsel__is_clock(evsel)) {
 		if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
-			print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
+			print_metric(config, ctxp, NULL, "%8.3f", "CPUs utilized",
 				     avg / (ratio * evsel->scale));
 		else
-			print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
+			print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
 		double fe_bound = td_fe_bound(ctx, cpu, st);
 
 		if (fe_bound > 0.2)
 			color = PERF_COLOR_RED;
-		print_metric(ctxp, color, "%8.1f%%", "frontend bound",
+		print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
 				fe_bound * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) {
 		double retiring = td_retiring(ctx, cpu, st);
 
 		if (retiring > 0.7)
 			color = PERF_COLOR_GREEN;
-		print_metric(ctxp, color, "%8.1f%%", "retiring",
+		print_metric(config, ctxp, color, "%8.1f%%", "retiring",
 				retiring * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) {
 		double bad_spec = td_bad_spec(ctx, cpu, st);
 
 		if (bad_spec > 0.1)
 			color = PERF_COLOR_RED;
-		print_metric(ctxp, color, "%8.1f%%", "bad speculation",
+		print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
 				bad_spec * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) {
 		double be_bound = td_be_bound(ctx, cpu, st);
@@ -955,12 +966,12 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 		if (be_bound > 0.2)
 			color = PERF_COLOR_RED;
 		if (td_total_slots(ctx, cpu, st) > 0)
-			print_metric(ctxp, color, "%8.1f%%", name,
+			print_metric(config, ctxp, color, "%8.1f%%", name,
 					be_bound * 100.);
 		else
-			print_metric(ctxp, NULL, NULL, name, 0);
+			print_metric(config, ctxp, NULL, NULL, name, 0);
 	} else if (evsel->metric_expr) {
-		generic_metric(evsel->metric_expr, evsel->metric_events, evsel->name,
+		generic_metric(config, evsel->metric_expr, evsel->metric_events, evsel->name,
 				evsel->metric_name, avg, cpu, out, st);
 	} else if (runtime_stat_n(st, STAT_NSECS, 0, cpu) != 0) {
 		char unit = 'M';
@@ -975,9 +986,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 			unit = 'K';
 		}
 		snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
-		print_metric(ctxp, NULL, "%8.3f", unit_buf, ratio);
+		print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio);
 	} else if (perf_stat_evsel__is(evsel, SMI_NUM)) {
-		print_smi_cost(cpu, evsel, out, st);
+		print_smi_cost(config, cpu, evsel, out, st);
 	} else {
 		num = 0;
 	}
@@ -987,12 +998,12 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 
 		list_for_each_entry (mexp, &me->head, nd) {
 			if (num++ > 0)
-				out->new_line(ctxp);
-			generic_metric(mexp->metric_expr, mexp->metric_events,
+				out->new_line(config, ctxp);
+			generic_metric(config, mexp->metric_expr, mexp->metric_events,
 					evsel->name, mexp->metric_name,
 					avg, cpu, out, st);
 		}
 	}
 	if (num == 0)
-		print_metric(ctxp, NULL, NULL, NULL, 0);
+		print_metric(config, ctxp, NULL, NULL, NULL, 0);
 }
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index a0061e0b0fad..4d40515307b8 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -374,9 +374,8 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 	return 0;
 }
 
-int perf_event__process_stat_event(struct perf_tool *tool __maybe_unused,
-				   union perf_event *event,
-				   struct perf_session *session)
+int perf_event__process_stat_event(struct perf_session *session,
+				   union perf_event *event)
 {
 	struct perf_counts_values count;
 	struct stat_event *st = &event->stat;
@@ -435,3 +434,98 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp)
 
 	return ret;
 }
+
+int create_perf_stat_counter(struct perf_evsel *evsel,
+			     struct perf_stat_config *config,
+			     struct target *target)
+{
+	struct perf_event_attr *attr = &evsel->attr;
+	struct perf_evsel *leader = evsel->leader;
+
+	if (config->scale) {
+		attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
+				    PERF_FORMAT_TOTAL_TIME_RUNNING;
+	}
+
+	/*
+	 * The event is part of non trivial group, let's enable
+	 * the group read (for leader) and ID retrieval for all
+	 * members.
+	 */
+	if (leader->nr_members > 1)
+		attr->read_format |= PERF_FORMAT_ID|PERF_FORMAT_GROUP;
+
+	attr->inherit = !config->no_inherit;
+
+	/*
+	 * Some events get initialized with sample_(period/type) set,
+	 * like tracepoints. Clear it up for counting.
+	 */
+	attr->sample_period = 0;
+
+	if (config->identifier)
+		attr->sample_type = PERF_SAMPLE_IDENTIFIER;
+
+	/*
+	 * Disabling all counters initially, they will be enabled
+	 * either manually by us or by kernel via enable_on_exec
+	 * set later.
+	 */
+	if (perf_evsel__is_group_leader(evsel)) {
+		attr->disabled = 1;
+
+		/*
+		 * In case of initial_delay we enable tracee
+		 * events manually.
+		 */
+		if (target__none(target) && !config->initial_delay)
+			attr->enable_on_exec = 1;
+	}
+
+	if (target__has_cpu(target) && !target__has_per_thread(target))
+		return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
+
+	return perf_evsel__open_per_thread(evsel, evsel->threads);
+}
+
+int perf_stat_synthesize_config(struct perf_stat_config *config,
+				struct perf_tool *tool,
+				struct perf_evlist *evlist,
+				perf_event__handler_t process,
+				bool attrs)
+{
+	int err;
+
+	if (attrs) {
+		err = perf_event__synthesize_attrs(tool, evlist, process);
+		if (err < 0) {
+			pr_err("Couldn't synthesize attrs.\n");
+			return err;
+		}
+	}
+
+	err = perf_event__synthesize_extra_attr(tool, evlist, process,
+						attrs);
+
+	err = perf_event__synthesize_thread_map2(tool, evlist->threads,
+						 process, NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize thread map.\n");
+		return err;
+	}
+
+	err = perf_event__synthesize_cpu_map(tool, evlist->cpus,
+					     process, NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize thread map.\n");
+		return err;
+	}
+
+	err = perf_event__synthesize_stat_config(tool, config, process, NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize config.\n");
+		return err;
+	}
+
+	return 0;
+}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 36efb986f7fc..2f9c9159a364 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -4,8 +4,14 @@
 
 #include <linux/types.h>
 #include <stdio.h>
+#include <sys/types.h>
+#include <sys/time.h>
+#include <sys/resource.h>
+#include <sys/wait.h>
 #include "xyarray.h"
 #include "rblist.h"
+#include "perf.h"
+#include "event.h"
 
 struct stats {
 	double n, mean, M2;
@@ -84,15 +90,42 @@ struct runtime_stat {
 	struct rblist value_list;
 };
 
+typedef int (*aggr_get_id_t)(struct perf_stat_config *config,
+			     struct cpu_map *m, int cpu);
+
 struct perf_stat_config {
-	enum aggr_mode	aggr_mode;
-	bool		scale;
-	FILE		*output;
-	unsigned int	interval;
-	unsigned int	timeout;
-	int		times;
-	struct runtime_stat *stats;
-	int		stats_num;
+	enum aggr_mode		 aggr_mode;
+	bool			 scale;
+	bool			 no_inherit;
+	bool			 identifier;
+	bool			 csv_output;
+	bool			 interval_clear;
+	bool			 metric_only;
+	bool			 null_run;
+	bool			 ru_display;
+	bool			 big_num;
+	bool			 no_merge;
+	bool			 walltime_run_table;
+	FILE			*output;
+	unsigned int		 interval;
+	unsigned int		 timeout;
+	unsigned int		 initial_delay;
+	unsigned int		 unit_width;
+	unsigned int		 metric_only_len;
+	int			 times;
+	int			 run_count;
+	int			 print_free_counters_hint;
+	int			 print_mixed_hw_group_error;
+	struct runtime_stat	*stats;
+	int			 stats_num;
+	const char		*csv_sep;
+	struct stats		*walltime_nsecs_stats;
+	struct rusage		 ru_data;
+	struct cpu_map		*aggr_map;
+	aggr_get_id_t		 aggr_get_id;
+	struct cpu_map		*cpus_aggr_map;
+	u64			*walltime_run;
+	struct rblist		 metric_events;
 };
 
 void update_stats(struct stats *stats, u64 val);
@@ -130,9 +163,10 @@ bool __perf_evsel_stat__is(struct perf_evsel *evsel,
 extern struct runtime_stat rt_stat;
 extern struct stats walltime_nsecs_stats;
 
-typedef void (*print_metric_t)(void *ctx, const char *color, const char *unit,
+typedef void (*print_metric_t)(struct perf_stat_config *config,
+			       void *ctx, const char *color, const char *unit,
 			       const char *fmt, double val);
-typedef void (*new_line_t )(void *ctx);
+typedef void (*new_line_t)(struct perf_stat_config *config, void *ctx);
 
 void runtime_stat__init(struct runtime_stat *st);
 void runtime_stat__exit(struct runtime_stat *st);
@@ -148,7 +182,8 @@ struct perf_stat_output_ctx {
 	bool force_header;
 };
 
-void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+void perf_stat__print_shadow_stats(struct perf_stat_config *config,
+				   struct perf_evsel *evsel,
 				   double avg, int cpu,
 				   struct perf_stat_output_ctx *out,
 				   struct rblist *metric_events,
@@ -164,11 +199,25 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 struct perf_tool;
 union perf_event;
 struct perf_session;
-int perf_event__process_stat_event(struct perf_tool *tool,
-				   union perf_event *event,
-				   struct perf_session *session);
+int perf_event__process_stat_event(struct perf_session *session,
+				   union perf_event *event);
 
 size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp);
+
+int create_perf_stat_counter(struct perf_evsel *evsel,
+			     struct perf_stat_config *config,
+			     struct target *target);
+int perf_stat_synthesize_config(struct perf_stat_config *config,
+				struct perf_tool *tool,
+				struct perf_evlist *evlist,
+				perf_event__handler_t process,
+				bool attrs);
+void
+perf_evlist__print_counters(struct perf_evlist *evlist,
+			    struct perf_stat_config *config,
+			    struct target *_target,
+			    struct timespec *ts,
+			    int argc, const char **argv);
 #endif
diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
index 3d1cf5bf7f18..9005fbe0780e 100644
--- a/tools/perf/util/strbuf.c
+++ b/tools/perf/util/strbuf.c
@@ -98,19 +98,25 @@ static int strbuf_addv(struct strbuf *sb, const char *fmt, va_list ap)
 
 	va_copy(ap_saved, ap);
 	len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap);
-	if (len < 0)
+	if (len < 0) {
+		va_end(ap_saved);
 		return len;
+	}
 	if (len > strbuf_avail(sb)) {
 		ret = strbuf_grow(sb, len);
-		if (ret)
+		if (ret) {
+			va_end(ap_saved);
 			return ret;
+		}
 		len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap_saved);
 		va_end(ap_saved);
 		if (len > strbuf_avail(sb)) {
 			pr_debug("this should not happen, your vsnprintf is broken");
+			va_end(ap_saved);
 			return -EINVAL;
 		}
 	}
+	va_end(ap_saved);
 	return strbuf_setlen(sb, sb->len + len);
 }
 
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index dd17d6a38d3a..c091635bf7dc 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -36,6 +36,7 @@
  * @branch_count: the branch count when the entry was created
  * @cp: call path
  * @no_call: a 'call' was not seen
+ * @trace_end: a 'call' but trace ended
  */
 struct thread_stack_entry {
 	u64 ret_addr;
@@ -44,6 +45,7 @@ struct thread_stack_entry {
 	u64 branch_count;
 	struct call_path *cp;
 	bool no_call;
+	bool trace_end;
 };
 
 /**
@@ -112,7 +114,8 @@ static struct thread_stack *thread_stack__new(struct thread *thread,
 	return ts;
 }
 
-static int thread_stack__push(struct thread_stack *ts, u64 ret_addr)
+static int thread_stack__push(struct thread_stack *ts, u64 ret_addr,
+			      bool trace_end)
 {
 	int err = 0;
 
@@ -124,6 +127,7 @@ static int thread_stack__push(struct thread_stack *ts, u64 ret_addr)
 		}
 	}
 
+	ts->stack[ts->cnt].trace_end = trace_end;
 	ts->stack[ts->cnt++].ret_addr = ret_addr;
 
 	return err;
@@ -150,6 +154,18 @@ static void thread_stack__pop(struct thread_stack *ts, u64 ret_addr)
 	}
 }
 
+static void thread_stack__pop_trace_end(struct thread_stack *ts)
+{
+	size_t i;
+
+	for (i = ts->cnt; i; ) {
+		if (ts->stack[--i].trace_end)
+			ts->cnt = i;
+		else
+			return;
+	}
+}
+
 static bool thread_stack__in_kernel(struct thread_stack *ts)
 {
 	if (!ts->cnt)
@@ -254,10 +270,19 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 		ret_addr = from_ip + insn_len;
 		if (ret_addr == to_ip)
 			return 0; /* Zero-length calls are excluded */
-		return thread_stack__push(thread->ts, ret_addr);
-	} else if (flags & PERF_IP_FLAG_RETURN) {
-		if (!from_ip)
-			return 0;
+		return thread_stack__push(thread->ts, ret_addr,
+					  flags & PERF_IP_FLAG_TRACE_END);
+	} else if (flags & PERF_IP_FLAG_TRACE_BEGIN) {
+		/*
+		 * If the caller did not change the trace number (which would
+		 * have flushed the stack) then try to make sense of the stack.
+		 * Possibly, tracing began after returning to the current
+		 * address, so try to pop that. Also, do not expect a call made
+		 * when the trace ended, to return, so pop that.
+		 */
+		thread_stack__pop(thread->ts, to_ip);
+		thread_stack__pop_trace_end(thread->ts);
+	} else if ((flags & PERF_IP_FLAG_RETURN) && from_ip) {
 		thread_stack__pop(thread->ts, to_ip);
 	}
 
@@ -332,7 +357,7 @@ void call_return_processor__free(struct call_return_processor *crp)
 
 static int thread_stack__push_cp(struct thread_stack *ts, u64 ret_addr,
 				 u64 timestamp, u64 ref, struct call_path *cp,
-				 bool no_call)
+				 bool no_call, bool trace_end)
 {
 	struct thread_stack_entry *tse;
 	int err;
@@ -350,6 +375,7 @@ static int thread_stack__push_cp(struct thread_stack *ts, u64 ret_addr,
 	tse->branch_count = ts->branch_count;
 	tse->cp = cp;
 	tse->no_call = no_call;
+	tse->trace_end = trace_end;
 
 	return 0;
 }
@@ -423,7 +449,7 @@ static int thread_stack__bottom(struct thread *thread, struct thread_stack *ts,
 		return -ENOMEM;
 
 	return thread_stack__push_cp(thread->ts, ip, sample->time, ref, cp,
-				     true);
+				     true, false);
 }
 
 static int thread_stack__no_call_return(struct thread *thread,
@@ -455,7 +481,7 @@ static int thread_stack__no_call_return(struct thread *thread,
 			if (!cp)
 				return -ENOMEM;
 			return thread_stack__push_cp(ts, 0, sample->time, ref,
-						     cp, true);
+						     cp, true, false);
 		}
 	} else if (thread_stack__in_kernel(ts) && sample->ip < ks) {
 		/* Return to userspace, so pop all kernel addresses */
@@ -480,7 +506,7 @@ static int thread_stack__no_call_return(struct thread *thread,
 		return -ENOMEM;
 
 	err = thread_stack__push_cp(ts, sample->addr, sample->time, ref, cp,
-				    true);
+				    true, false);
 	if (err)
 		return err;
 
@@ -500,7 +526,7 @@ static int thread_stack__trace_begin(struct thread *thread,
 
 	/* Pop trace end */
 	tse = &ts->stack[ts->cnt - 1];
-	if (tse->cp->sym == NULL && tse->cp->ip == 0) {
+	if (tse->trace_end) {
 		err = thread_stack__call_return(thread, ts, --ts->cnt,
 						timestamp, ref, false);
 		if (err)
@@ -529,7 +555,7 @@ static int thread_stack__trace_end(struct thread_stack *ts,
 	ret_addr = sample->ip + sample->insn_len;
 
 	return thread_stack__push_cp(ts, ret_addr, sample->time, ref, cp,
-				     false);
+				     false, true);
 }
 
 int thread_stack__process(struct thread *thread, struct comm *comm,
@@ -579,6 +605,7 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 	ts->last_time = sample->time;
 
 	if (sample->flags & PERF_IP_FLAG_CALL) {
+		bool trace_end = sample->flags & PERF_IP_FLAG_TRACE_END;
 		struct call_path_root *cpr = ts->crp->cpr;
 		struct call_path *cp;
 		u64 ret_addr;
@@ -596,7 +623,7 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 		if (!cp)
 			return -ENOMEM;
 		err = thread_stack__push_cp(ts, ret_addr, sample->time, ref,
-					    cp, false);
+					    cp, false, trace_end);
 	} else if (sample->flags & PERF_IP_FLAG_RETURN) {
 		if (!sample->ip || !sample->addr)
 			return 0;
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 183c91453522..56e4ca54020a 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -26,15 +26,12 @@ typedef int (*event_attr_op)(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_evlist **pevlist);
 
-typedef int (*event_op2)(struct perf_tool *tool, union perf_event *event,
-			 struct perf_session *session);
+typedef int (*event_op2)(struct perf_session *session, union perf_event *event);
+typedef s64 (*event_op3)(struct perf_session *session, union perf_event *event);
 
 typedef int (*event_oe)(struct perf_tool *tool, union perf_event *event,
 			struct ordered_events *oe);
 
-typedef s64 (*event_op3)(struct perf_tool *tool, union perf_event *event,
-			 struct perf_session *session);
-
 enum show_feature_header {
 	SHOW_FEAT_NO_HEADER = 0,
 	SHOW_FEAT_HEADER,
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index 7b0ca7cbb7de..8ad8e755127b 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -531,12 +531,14 @@ struct tracing_data *tracing_data_get(struct list_head *pattrs,
 			 "/tmp/perf-XXXXXX");
 		if (!mkstemp(tdata->temp_file)) {
 			pr_debug("Can't make temp file");
+			free(tdata);
 			return NULL;
 		}
 
 		temp_fd = open(tdata->temp_file, O_RDWR);
 		if (temp_fd < 0) {
 			pr_debug("Can't read '%s'", tdata->temp_file);
+			free(tdata);
 			return NULL;
 		}
 
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index e76214f8d596..32e558a65af3 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -33,14 +33,15 @@ static int get_common_field(struct scripting_context *context,
 			    int *offset, int *size, const char *type)
 {
 	struct tep_handle *pevent = context->pevent;
-	struct event_format *event;
-	struct format_field *field;
+	struct tep_event_format *event;
+	struct tep_format_field *field;
 
 	if (!*size) {
-		if (!pevent->events)
+
+		event = tep_get_first_event(pevent);
+		if (!event)
 			return 0;
 
-		event = pevent->events[0];
 		field = tep_find_common_field(event, type);
 		if (!field)
 			return 0;
@@ -94,9 +95,9 @@ int common_pc(struct scripting_context *context)
 }
 
 unsigned long long
-raw_field_value(struct event_format *event, const char *name, void *data)
+raw_field_value(struct tep_event_format *event, const char *name, void *data)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 	unsigned long long val;
 
 	field = tep_find_any_field(event, name);
@@ -108,12 +109,12 @@ raw_field_value(struct event_format *event, const char *name, void *data)
 	return val;
 }
 
-unsigned long long read_size(struct event_format *event, void *ptr, int size)
+unsigned long long read_size(struct tep_event_format *event, void *ptr, int size)
 {
 	return tep_read_number(event->pevent, ptr, size);
 }
 
-void event_format__fprintf(struct event_format *event,
+void event_format__fprintf(struct tep_event_format *event,
 			   int cpu, void *data, int size, FILE *fp)
 {
 	struct tep_record record;
@@ -130,7 +131,7 @@ void event_format__fprintf(struct event_format *event,
 	trace_seq_destroy(&s);
 }
 
-void event_format__print(struct event_format *event,
+void event_format__print(struct tep_event_format *event,
 			 int cpu, void *data, int size)
 {
 	return event_format__fprintf(event, cpu, data, size, stdout);
@@ -158,6 +159,7 @@ void parse_ftrace_printk(struct tep_handle *pevent,
 		printk = strdup(fmt+1);
 		line = strtok_r(NULL, "\n", &next);
 		tep_register_print_string(pevent, printk, addr);
+		free(printk);
 	}
 }
 
@@ -188,29 +190,33 @@ int parse_event_file(struct tep_handle *pevent,
 	return tep_parse_event(pevent, buf, size, sys);
 }
 
-struct event_format *trace_find_next_event(struct tep_handle *pevent,
-					   struct event_format *event)
+struct tep_event_format *trace_find_next_event(struct tep_handle *pevent,
+					       struct tep_event_format *event)
 {
 	static int idx;
+	int events_count;
+	struct tep_event_format *all_events;
 
-	if (!pevent || !pevent->events)
+	all_events = tep_get_first_event(pevent);
+	events_count = tep_get_events_count(pevent);
+	if (!pevent || !all_events || events_count < 1)
 		return NULL;
 
 	if (!event) {
 		idx = 0;
-		return pevent->events[0];
+		return all_events;
 	}
 
-	if (idx < pevent->nr_events && event == pevent->events[idx]) {
+	if (idx < events_count && event == (all_events + idx)) {
 		idx++;
-		if (idx == pevent->nr_events)
+		if (idx == events_count)
 			return NULL;
-		return pevent->events[idx];
+		return (all_events + idx);
 	}
 
-	for (idx = 1; idx < pevent->nr_events; idx++) {
-		if (event == pevent->events[idx - 1])
-			return pevent->events[idx];
+	for (idx = 1; idx < events_count; idx++) {
+		if (event == (all_events + (idx - 1)))
+			return (all_events + idx);
 	}
 	return NULL;
 }
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index 3dfc1db6b25b..76f12c705ef9 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -102,7 +102,7 @@ static unsigned int read4(struct tep_handle *pevent)
 
 	if (do_read(&data, 4) < 0)
 		return 0;
-	return __data2host4(pevent, data);
+	return __tep_data2host4(pevent, data);
 }
 
 static unsigned long long read8(struct tep_handle *pevent)
@@ -111,7 +111,7 @@ static unsigned long long read8(struct tep_handle *pevent)
 
 	if (do_read(&data, 8) < 0)
 		return 0;
-	return __data2host8(pevent, data);
+	return __tep_data2host8(pevent, data);
 }
 
 static char *read_string(void)
@@ -241,7 +241,7 @@ static int read_header_files(struct tep_handle *pevent)
 		 * The commit field in the page is of type long,
 		 * use that instead, since it represents the kernel.
 		 */
-		tep_set_long_size(pevent, pevent->header_page_size_size);
+		tep_set_long_size(pevent, tep_get_header_page_size(pevent));
 	}
 	free(header_page);
 
@@ -297,10 +297,8 @@ static int read_event_file(struct tep_handle *pevent, char *sys,
 	}
 
 	ret = do_read(buf, size);
-	if (ret < 0) {
-		free(buf);
+	if (ret < 0)
 		goto out;
-	}
 
 	ret = parse_event_file(pevent, buf, size, sys);
 	if (ret < 0)
@@ -349,9 +347,12 @@ static int read_event_files(struct tep_handle *pevent)
 		for (x=0; x < count; x++) {
 			size = read8(pevent);
 			ret = read_event_file(pevent, sys, size);
-			if (ret)
+			if (ret) {
+				free(sys);
 				return ret;
+			}
 		}
+		free(sys);
 	}
 	return 0;
 }
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index 58bb72f266f3..95664b2f771e 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -72,12 +72,12 @@ void trace_event__cleanup(struct trace_event *t)
 /*
  * Returns pointer with encoded error via <linux/err.h> interface.
  */
-static struct event_format*
+static struct tep_event_format*
 tp_format(const char *sys, const char *name)
 {
 	char *tp_dir = get_events_file(sys);
 	struct tep_handle *pevent = tevent.pevent;
-	struct event_format *event = NULL;
+	struct tep_event_format *event = NULL;
 	char path[PATH_MAX];
 	size_t size;
 	char *data;
@@ -102,7 +102,7 @@ tp_format(const char *sys, const char *name)
 /*
  * Returns pointer with encoded error via <linux/err.h> interface.
  */
-struct event_format*
+struct tep_event_format*
 trace_event__tp_format(const char *sys, const char *name)
 {
 	if (!tevent_initialized && trace_event__init2())
@@ -111,7 +111,7 @@ trace_event__tp_format(const char *sys, const char *name)
 	return tp_format(sys, name);
 }
 
-struct event_format *trace_event__tp_format_id(int id)
+struct tep_event_format *trace_event__tp_format_id(int id)
 {
 	if (!tevent_initialized && trace_event__init2())
 		return ERR_PTR(-ENOMEM);
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 40204ec3a7a2..f024d73bfc40 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -3,6 +3,7 @@
 #define _PERF_UTIL_TRACE_EVENT_H
 
 #include <traceevent/event-parse.h>
+#include <traceevent/trace-seq.h>
 #include "parse-events.h"
 
 struct machine;
@@ -10,28 +11,28 @@ struct perf_sample;
 union perf_event;
 struct perf_tool;
 struct thread;
-struct plugin_list;
+struct tep_plugin_list;
 
 struct trace_event {
 	struct tep_handle	*pevent;
-	struct plugin_list	*plugin_list;
+	struct tep_plugin_list	*plugin_list;
 };
 
 int trace_event__init(struct trace_event *t);
 void trace_event__cleanup(struct trace_event *t);
 int trace_event__register_resolver(struct machine *machine,
 				   tep_func_resolver_t *func);
-struct event_format*
+struct tep_event_format*
 trace_event__tp_format(const char *sys, const char *name);
 
-struct event_format *trace_event__tp_format_id(int id);
+struct tep_event_format *trace_event__tp_format_id(int id);
 
 int bigendian(void);
 
-void event_format__fprintf(struct event_format *event,
+void event_format__fprintf(struct tep_event_format *event,
 			   int cpu, void *data, int size, FILE *fp);
 
-void event_format__print(struct event_format *event,
+void event_format__print(struct tep_event_format *event,
 			 int cpu, void *data, int size);
 
 int parse_ftrace_file(struct tep_handle *pevent, char *buf, unsigned long size);
@@ -39,7 +40,7 @@ int parse_event_file(struct tep_handle *pevent,
 		     char *buf, unsigned long size, char *sys);
 
 unsigned long long
-raw_field_value(struct event_format *event, const char *name, void *data);
+raw_field_value(struct tep_event_format *event, const char *name, void *data);
 
 void parse_proc_kallsyms(struct tep_handle *pevent, char *file, unsigned int size);
 void parse_ftrace_printk(struct tep_handle *pevent, char *file, unsigned int size);
@@ -47,9 +48,9 @@ void parse_saved_cmdline(struct tep_handle *pevent, char *file, unsigned int siz
 
 ssize_t trace_report(int fd, struct trace_event *tevent, bool repipe);
 
-struct event_format *trace_find_next_event(struct tep_handle *pevent,
-					   struct event_format *event);
-unsigned long long read_size(struct event_format *event, void *ptr, int size);
+struct tep_event_format *trace_find_next_event(struct tep_handle *pevent,
+					       struct tep_event_format *event);
+unsigned long long read_size(struct tep_event_format *event, void *ptr, int size);
 unsigned long long eval_flag(const char *flag);
 
 int read_tracing_data(int fd, struct list_head *pattrs);
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index eac5b858a371..093352e93d50 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -221,7 +221,7 @@ out:
 	return err;
 }
 
-static int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
+int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
 {
 	void *ptr;
 	loff_t pgoff;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index dc58254a2b69..14508ee7707a 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -6,6 +6,7 @@
 /* glibc 2.20 deprecates _BSD_SOURCE in favour of _DEFAULT_SOURCE */
 #define _DEFAULT_SOURCE 1
 
+#include <fcntl.h>
 #include <stdbool.h>
 #include <stddef.h>
 #include <stdlib.h>
@@ -35,6 +36,7 @@ bool lsdir_no_dot_filter(const char *name, struct dirent *d);
 int copyfile(const char *from, const char *to);
 int copyfile_mode(const char *from, const char *to, mode_t mode);
 int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi);
+int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size);
 
 ssize_t readn(int fd, void *buf, size_t n);
 ssize_t writen(int fd, const void *buf, size_t n);