Linux-libre 4.2-gnu

88 files changed, 6556 insertions, 1407 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 797490a40..d2d318c59 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -68,12 +68,15 @@ libperf-y += rblist.o
 libperf-y += intlist.o
 libperf-y += vdso.o
 libperf-y += stat.o
+libperf-y += stat-shadow.o
 libperf-y += record.o
 libperf-y += srcline.o
 libperf-y += data.o
 libperf-$(CONFIG_X86) += tsc.o
 libperf-y += cloexec.o
 libperf-y += thread-stack.o
+libperf-$(CONFIG_AUXTRACE) += auxtrace.o
+libperf-y += parse-branch-options.o
 
 libperf-$(CONFIG_LIBELF) += symbol-elf.o
 libperf-$(CONFIG_LIBELF) += probe-event.o
@@ -101,23 +104,23 @@ CFLAGS_exec_cmd.o += -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))" -DPREFIX="B
 
 $(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c
 	$(call rule_mkdir)
-	@$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) util/parse-events.l
+	$(Q)$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) util/parse-events.l
 
 $(OUTPUT)util/parse-events-bison.c: util/parse-events.y
 	$(call rule_mkdir)
-	@$(call echo-cmd,bison)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $@ -p parse_events_
+	$(Q)$(call echo-cmd,bison)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $@ -p parse_events_
 
 $(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c
 	$(call rule_mkdir)
-	@$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/pmu-flex.h util/pmu.l
+	$(Q)$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/pmu-flex.h util/pmu.l
 
 $(OUTPUT)util/pmu-bison.c: util/pmu.y
 	$(call rule_mkdir)
-	@$(call echo-cmd,bison)$(BISON) -v util/pmu.y -d -o $@ -p perf_pmu_
+	$(Q)$(call echo-cmd,bison)$(BISON) -v util/pmu.y -d -o $@ -p perf_pmu_
 
 CFLAGS_parse-events-flex.o  += -w
 CFLAGS_pmu-flex.o           += -w
-CFLAGS_parse-events-bison.o += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w
+CFLAGS_parse-events-bison.o += -DYYENABLE_NLS=0 -w
 CFLAGS_pmu-bison.o          += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w
 
 $(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c
@@ -136,10 +139,10 @@ $(OUTPUT)util/find_next_bit.o: ../lib/util/find_next_bit.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
-$(OUTPUT)util/rbtree.o: ../../lib/rbtree.c FORCE
+$(OUTPUT)util/rbtree.o: ../lib/rbtree.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
-$(OUTPUT)util/hweight.o: ../../lib/hweight.c FORCE
+$(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 7f5bdfc9b..03b7bc70e 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -506,6 +506,17 @@ static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 	return 0;
 }
 
+static struct annotation *symbol__get_annotation(struct symbol *sym)
+{
+	struct annotation *notes = symbol__annotation(sym);
+
+	if (notes->src == NULL) {
+		if (symbol__alloc_hist(sym) < 0)
+			return NULL;
+	}
+	return notes;
+}
+
 static int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 				    int evidx, u64 addr)
 {
@@ -513,13 +524,9 @@ static int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 
 	if (sym == NULL)
 		return 0;
-
-	notes = symbol__annotation(sym);
-	if (notes->src == NULL) {
-		if (symbol__alloc_hist(sym) < 0)
-			return -ENOMEM;
-	}
-
+	notes = symbol__get_annotation(sym);
+	if (notes == NULL)
+		return -ENOMEM;
 	return __symbol__inc_addr_samples(sym, map, notes, evidx, addr);
 }
 
@@ -647,14 +654,15 @@ struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disa
 }
 
 double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
-			    s64 end, const char **path)
+			    s64 end, const char **path, u64 *nr_samples)
 {
 	struct source_line *src_line = notes->src->lines;
 	double percent = 0.0;
+	*nr_samples = 0;
 
 	if (src_line) {
 		size_t sizeof_src_line = sizeof(*src_line) +
-				sizeof(src_line->p) * (src_line->nr_pcnt - 1);
+				sizeof(src_line->samples) * (src_line->nr_pcnt - 1);
 
 		while (offset < end) {
 			src_line = (void *)notes->src->lines +
@@ -663,7 +671,8 @@ double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
 			if (*path == NULL)
 				*path = src_line->path;
 
-			percent += src_line->p[evidx].percent;
+			percent += src_line->samples[evidx].percent;
+			*nr_samples += src_line->samples[evidx].nr;
 			offset++;
 		}
 	} else {
@@ -673,8 +682,10 @@ double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
 		while (offset < end)
 			hits += h->addr[offset++];
 
-		if (h->sum)
+		if (h->sum) {
+			*nr_samples = hits;
 			percent = 100.0 * hits / h->sum;
+		}
 	}
 
 	return percent;
@@ -689,8 +700,10 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 
 	if (dl->offset != -1) {
 		const char *path = NULL;
+		u64 nr_samples;
 		double percent, max_percent = 0.0;
 		double *ppercents = &percent;
+		u64 *psamples = &nr_samples;
 		int i, nr_percent = 1;
 		const char *color;
 		struct annotation *notes = symbol__annotation(sym);
@@ -703,8 +716,10 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 		if (perf_evsel__is_group_event(evsel)) {
 			nr_percent = evsel->nr_members;
 			ppercents = calloc(nr_percent, sizeof(double));
-			if (ppercents == NULL)
+			psamples = calloc(nr_percent, sizeof(u64));
+			if (ppercents == NULL || psamples == NULL) {
 				return -1;
+			}
 		}
 
 		for (i = 0; i < nr_percent; i++) {
@@ -712,9 +727,10 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 					notes->src->lines ? i : evsel->idx + i,
 					offset,
 					next ? next->offset : (s64) len,
-					&path);
+					&path, &nr_samples);
 
 			ppercents[i] = percent;
+			psamples[i] = nr_samples;
 			if (percent > max_percent)
 				max_percent = percent;
 		}
@@ -752,8 +768,14 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 
 		for (i = 0; i < nr_percent; i++) {
 			percent = ppercents[i];
+			nr_samples = psamples[i];
 			color = get_percent_color(percent);
-			color_fprintf(stdout, color, " %7.2f", percent);
+
+			if (symbol_conf.show_total_period)
+				color_fprintf(stdout, color, " %7" PRIu64,
+					      nr_samples);
+			else
+				color_fprintf(stdout, color, " %7.2f", percent);
 		}
 
 		printf(" :	");
@@ -763,6 +785,9 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 		if (ppercents != &percent)
 			free(ppercents);
 
+		if (psamples != &nr_samples)
+			free(psamples);
+
 	} else if (max_lines && printed >= max_lines)
 		return 1;
 	else {
@@ -1096,7 +1121,7 @@ static void insert_source_line(struct rb_root *root, struct source_line *src_lin
 		ret = strcmp(iter->path, src_line->path);
 		if (ret == 0) {
 			for (i = 0; i < src_line->nr_pcnt; i++)
-				iter->p[i].percent_sum += src_line->p[i].percent;
+				iter->samples[i].percent_sum += src_line->samples[i].percent;
 			return;
 		}
 
@@ -1107,7 +1132,7 @@ static void insert_source_line(struct rb_root *root, struct source_line *src_lin
 	}
 
 	for (i = 0; i < src_line->nr_pcnt; i++)
-		src_line->p[i].percent_sum = src_line->p[i].percent;
+		src_line->samples[i].percent_sum = src_line->samples[i].percent;
 
 	rb_link_node(&src_line->node, parent, p);
 	rb_insert_color(&src_line->node, root);
@@ -1118,9 +1143,9 @@ static int cmp_source_line(struct source_line *a, struct source_line *b)
 	int i;
 
 	for (i = 0; i < a->nr_pcnt; i++) {
-		if (a->p[i].percent_sum == b->p[i].percent_sum)
+		if (a->samples[i].percent_sum == b->samples[i].percent_sum)
 			continue;
-		return a->p[i].percent_sum > b->p[i].percent_sum;
+		return a->samples[i].percent_sum > b->samples[i].percent_sum;
 	}
 
 	return 0;
@@ -1172,7 +1197,7 @@ static void symbol__free_source_line(struct symbol *sym, int len)
 	int i;
 
 	sizeof_src_line = sizeof(*src_line) +
-			  (sizeof(src_line->p) * (src_line->nr_pcnt - 1));
+			  (sizeof(src_line->samples) * (src_line->nr_pcnt - 1));
 
 	for (i = 0; i < len; i++) {
 		free_srcline(src_line->path);
@@ -1204,7 +1229,7 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
 			h_sum += h->sum;
 		}
 		nr_pcnt = evsel->nr_members;
-		sizeof_src_line += (nr_pcnt - 1) * sizeof(src_line->p);
+		sizeof_src_line += (nr_pcnt - 1) * sizeof(src_line->samples);
 	}
 
 	if (!h_sum)
@@ -1224,10 +1249,10 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
 
 		for (k = 0; k < nr_pcnt; k++) {
 			h = annotation__histogram(notes, evidx + k);
-			src_line->p[k].percent = 100.0 * h->addr[i] / h->sum;
+			src_line->samples[k].percent = 100.0 * h->addr[i] / h->sum;
 
-			if (src_line->p[k].percent > percent_max)
-				percent_max = src_line->p[k].percent;
+			if (src_line->samples[k].percent > percent_max)
+				percent_max = src_line->samples[k].percent;
 		}
 
 		if (percent_max <= 0.5)
@@ -1267,7 +1292,7 @@ static void print_summary(struct rb_root *root, const char *filename)
 
 		src_line = rb_entry(node, struct source_line, node);
 		for (i = 0; i < src_line->nr_pcnt; i++) {
-			percent = src_line->p[i].percent_sum;
+			percent = src_line->samples[i].percent_sum;
 			color = get_percent_color(percent);
 			color_fprintf(stdout, color, " %7.2f", percent);
 
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index cadbdc90a..7e78e6c27 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -72,23 +72,24 @@ struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disa
 int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw);
 size_t disasm__fprintf(struct list_head *head, FILE *fp);
 double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
-			    s64 end, const char **path);
+			    s64 end, const char **path, u64 *nr_samples);
 
 struct sym_hist {
 	u64		sum;
 	u64		addr[0];
 };
 
-struct source_line_percent {
+struct source_line_samples {
 	double		percent;
 	double		percent_sum;
+	double          nr;
 };
 
 struct source_line {
 	struct rb_node	node;
 	char		*path;
 	int		nr_pcnt;
-	struct source_line_percent p[1];
+	struct source_line_samples samples[1];
 };
 
 /** struct annotated_source - symbols with hits have this attached as in sannotation
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
new file mode 100644
index 000000000..83d9dd96f
--- /dev/null
+++ b/tools/perf/util/auxtrace.c
@@ -0,0 +1,1359 @@
+/*
+ * auxtrace.c: AUX area trace support
+ * Copyright (c) 2013-2015, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include <sys/types.h>
+#include <sys/mman.h>
+#include <stdbool.h>
+
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/log2.h>
+#include <linux/string.h>
+
+#include <sys/param.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <limits.h>
+#include <errno.h>
+#include <linux/list.h>
+
+#include "../perf.h"
+#include "util.h"
+#include "evlist.h"
+#include "cpumap.h"
+#include "thread_map.h"
+#include "asm/bug.h"
+#include "auxtrace.h"
+
+#include <linux/hash.h>
+
+#include "event.h"
+#include "session.h"
+#include "debug.h"
+#include "parse-options.h"
+
+int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
+			struct auxtrace_mmap_params *mp,
+			void *userpg, int fd)
+{
+	struct perf_event_mmap_page *pc = userpg;
+
+	WARN_ONCE(mm->base, "Uninitialized auxtrace_mmap\n");
+
+	mm->userpg = userpg;
+	mm->mask = mp->mask;
+	mm->len = mp->len;
+	mm->prev = 0;
+	mm->idx = mp->idx;
+	mm->tid = mp->tid;
+	mm->cpu = mp->cpu;
+
+	if (!mp->len) {
+		mm->base = NULL;
+		return 0;
+	}
+
+#if BITS_PER_LONG != 64 && !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+	pr_err("Cannot use AUX area tracing mmaps\n");
+	return -1;
+#endif
+
+	pc->aux_offset = mp->offset;
+	pc->aux_size = mp->len;
+
+	mm->base = mmap(NULL, mp->len, mp->prot, MAP_SHARED, fd, mp->offset);
+	if (mm->base == MAP_FAILED) {
+		pr_debug2("failed to mmap AUX area\n");
+		mm->base = NULL;
+		return -1;
+	}
+
+	return 0;
+}
+
+void auxtrace_mmap__munmap(struct auxtrace_mmap *mm)
+{
+	if (mm->base) {
+		munmap(mm->base, mm->len);
+		mm->base = NULL;
+	}
+}
+
+void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,
+				off_t auxtrace_offset,
+				unsigned int auxtrace_pages,
+				bool auxtrace_overwrite)
+{
+	if (auxtrace_pages) {
+		mp->offset = auxtrace_offset;
+		mp->len = auxtrace_pages * (size_t)page_size;
+		mp->mask = is_power_of_2(mp->len) ? mp->len - 1 : 0;
+		mp->prot = PROT_READ | (auxtrace_overwrite ? 0 : PROT_WRITE);
+		pr_debug2("AUX area mmap length %zu\n", mp->len);
+	} else {
+		mp->len = 0;
+	}
+}
+
+void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
+				   struct perf_evlist *evlist, int idx,
+				   bool per_cpu)
+{
+	mp->idx = idx;
+
+	if (per_cpu) {
+		mp->cpu = evlist->cpus->map[idx];
+		if (evlist->threads)
+			mp->tid = thread_map__pid(evlist->threads, 0);
+		else
+			mp->tid = -1;
+	} else {
+		mp->cpu = -1;
+		mp->tid = thread_map__pid(evlist->threads, idx);
+	}
+}
+
+#define AUXTRACE_INIT_NR_QUEUES	32
+
+static struct auxtrace_queue *auxtrace_alloc_queue_array(unsigned int nr_queues)
+{
+	struct auxtrace_queue *queue_array;
+	unsigned int max_nr_queues, i;
+
+	max_nr_queues = UINT_MAX / sizeof(struct auxtrace_queue);
+	if (nr_queues > max_nr_queues)
+		return NULL;
+
+	queue_array = calloc(nr_queues, sizeof(struct auxtrace_queue));
+	if (!queue_array)
+		return NULL;
+
+	for (i = 0; i < nr_queues; i++) {
+		INIT_LIST_HEAD(&queue_array[i].head);
+		queue_array[i].priv = NULL;
+	}
+
+	return queue_array;
+}
+
+int auxtrace_queues__init(struct auxtrace_queues *queues)
+{
+	queues->nr_queues = AUXTRACE_INIT_NR_QUEUES;
+	queues->queue_array = auxtrace_alloc_queue_array(queues->nr_queues);
+	if (!queues->queue_array)
+		return -ENOMEM;
+	return 0;
+}
+
+static int auxtrace_queues__grow(struct auxtrace_queues *queues,
+				 unsigned int new_nr_queues)
+{
+	unsigned int nr_queues = queues->nr_queues;
+	struct auxtrace_queue *queue_array;
+	unsigned int i;
+
+	if (!nr_queues)
+		nr_queues = AUXTRACE_INIT_NR_QUEUES;
+
+	while (nr_queues && nr_queues < new_nr_queues)
+		nr_queues <<= 1;
+
+	if (nr_queues < queues->nr_queues || nr_queues < new_nr_queues)
+		return -EINVAL;
+
+	queue_array = auxtrace_alloc_queue_array(nr_queues);
+	if (!queue_array)
+		return -ENOMEM;
+
+	for (i = 0; i < queues->nr_queues; i++) {
+		list_splice_tail(&queues->queue_array[i].head,
+				 &queue_array[i].head);
+		queue_array[i].priv = queues->queue_array[i].priv;
+	}
+
+	queues->nr_queues = nr_queues;
+	queues->queue_array = queue_array;
+
+	return 0;
+}
+
+static void *auxtrace_copy_data(u64 size, struct perf_session *session)
+{
+	int fd = perf_data_file__fd(session->file);
+	void *p;
+	ssize_t ret;
+
+	if (size > SSIZE_MAX)
+		return NULL;
+
+	p = malloc(size);
+	if (!p)
+		return NULL;
+
+	ret = readn(fd, p, size);
+	if (ret != (ssize_t)size) {
+		free(p);
+		return NULL;
+	}
+
+	return p;
+}
+
+static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues,
+				       unsigned int idx,
+				       struct auxtrace_buffer *buffer)
+{
+	struct auxtrace_queue *queue;
+	int err;
+
+	if (idx >= queues->nr_queues) {
+		err = auxtrace_queues__grow(queues, idx + 1);
+		if (err)
+			return err;
+	}
+
+	queue = &queues->queue_array[idx];
+
+	if (!queue->set) {
+		queue->set = true;
+		queue->tid = buffer->tid;
+		queue->cpu = buffer->cpu;
+	} else if (buffer->cpu != queue->cpu || buffer->tid != queue->tid) {
+		pr_err("auxtrace queue conflict: cpu %d, tid %d vs cpu %d, tid %d\n",
+		       queue->cpu, queue->tid, buffer->cpu, buffer->tid);
+		return -EINVAL;
+	}
+
+	buffer->buffer_nr = queues->next_buffer_nr++;
+
+	list_add_tail(&buffer->list, &queue->head);
+
+	queues->new_data = true;
+	queues->populated = true;
+
+	return 0;
+}
+
+/* Limit buffers to 32MiB on 32-bit */
+#define BUFFER_LIMIT_FOR_32_BIT (32 * 1024 * 1024)
+
+static int auxtrace_queues__split_buffer(struct auxtrace_queues *queues,
+					 unsigned int idx,
+					 struct auxtrace_buffer *buffer)
+{
+	u64 sz = buffer->size;
+	bool consecutive = false;
+	struct auxtrace_buffer *b;
+	int err;
+
+	while (sz > BUFFER_LIMIT_FOR_32_BIT) {
+		b = memdup(buffer, sizeof(struct auxtrace_buffer));
+		if (!b)
+			return -ENOMEM;
+		b->size = BUFFER_LIMIT_FOR_32_BIT;
+		b->consecutive = consecutive;
+		err = auxtrace_queues__add_buffer(queues, idx, b);
+		if (err) {
+			auxtrace_buffer__free(b);
+			return err;
+		}
+		buffer->data_offset += BUFFER_LIMIT_FOR_32_BIT;
+		sz -= BUFFER_LIMIT_FOR_32_BIT;
+		consecutive = true;
+	}
+
+	buffer->size = sz;
+	buffer->consecutive = consecutive;
+
+	return 0;
+}
+
+static int auxtrace_queues__add_event_buffer(struct auxtrace_queues *queues,
+					     struct perf_session *session,
+					     unsigned int idx,
+					     struct auxtrace_buffer *buffer)
+{
+	if (session->one_mmap) {
+		buffer->data = buffer->data_offset - session->one_mmap_offset +
+			       session->one_mmap_addr;
+	} else if (perf_data_file__is_pipe(session->file)) {
+		buffer->data = auxtrace_copy_data(buffer->size, session);
+		if (!buffer->data)
+			return -ENOMEM;
+		buffer->data_needs_freeing = true;
+	} else if (BITS_PER_LONG == 32 &&
+		   buffer->size > BUFFER_LIMIT_FOR_32_BIT) {
+		int err;
+
+		err = auxtrace_queues__split_buffer(queues, idx, buffer);
+		if (err)
+			return err;
+	}
+
+	return auxtrace_queues__add_buffer(queues, idx, buffer);
+}
+
+int auxtrace_queues__add_event(struct auxtrace_queues *queues,
+			       struct perf_session *session,
+			       union perf_event *event, off_t data_offset,
+			       struct auxtrace_buffer **buffer_ptr)
+{
+	struct auxtrace_buffer *buffer;
+	unsigned int idx;
+	int err;
+
+	buffer = zalloc(sizeof(struct auxtrace_buffer));
+	if (!buffer)
+		return -ENOMEM;
+
+	buffer->pid = -1;
+	buffer->tid = event->auxtrace.tid;
+	buffer->cpu = event->auxtrace.cpu;
+	buffer->data_offset = data_offset;
+	buffer->offset = event->auxtrace.offset;
+	buffer->reference = event->auxtrace.reference;
+	buffer->size = event->auxtrace.size;
+	idx = event->auxtrace.idx;
+
+	err = auxtrace_queues__add_event_buffer(queues, session, idx, buffer);
+	if (err)
+		goto out_err;
+
+	if (buffer_ptr)
+		*buffer_ptr = buffer;
+
+	return 0;
+
+out_err:
+	auxtrace_buffer__free(buffer);
+	return err;
+}
+
+static int auxtrace_queues__add_indexed_event(struct auxtrace_queues *queues,
+					      struct perf_session *session,
+					      off_t file_offset, size_t sz)
+{
+	union perf_event *event;
+	int err;
+	char buf[PERF_SAMPLE_MAX_SIZE];
+
+	err = perf_session__peek_event(session, file_offset, buf,
+				       PERF_SAMPLE_MAX_SIZE, &event, NULL);
+	if (err)
+		return err;
+
+	if (event->header.type == PERF_RECORD_AUXTRACE) {
+		if (event->header.size < sizeof(struct auxtrace_event) ||
+		    event->header.size != sz) {
+			err = -EINVAL;
+			goto out;
+		}
+		file_offset += event->header.size;
+		err = auxtrace_queues__add_event(queues, session, event,
+						 file_offset, NULL);
+	}
+out:
+	return err;
+}
+
+void auxtrace_queues__free(struct auxtrace_queues *queues)
+{
+	unsigned int i;
+
+	for (i = 0; i < queues->nr_queues; i++) {
+		while (!list_empty(&queues->queue_array[i].head)) {
+			struct auxtrace_buffer *buffer;
+
+			buffer = list_entry(queues->queue_array[i].head.next,
+					    struct auxtrace_buffer, list);
+			list_del(&buffer->list);
+			auxtrace_buffer__free(buffer);
+		}
+	}
+
+	zfree(&queues->queue_array);
+	queues->nr_queues = 0;
+}
+
+static void auxtrace_heapify(struct auxtrace_heap_item *heap_array,
+			     unsigned int pos, unsigned int queue_nr,
+			     u64 ordinal)
+{
+	unsigned int parent;
+
+	while (pos) {
+		parent = (pos - 1) >> 1;
+		if (heap_array[parent].ordinal <= ordinal)
+			break;
+		heap_array[pos] = heap_array[parent];
+		pos = parent;
+	}
+	heap_array[pos].queue_nr = queue_nr;
+	heap_array[pos].ordinal = ordinal;
+}
+
+int auxtrace_heap__add(struct auxtrace_heap *heap, unsigned int queue_nr,
+		       u64 ordinal)
+{
+	struct auxtrace_heap_item *heap_array;
+
+	if (queue_nr >= heap->heap_sz) {
+		unsigned int heap_sz = AUXTRACE_INIT_NR_QUEUES;
+
+		while (heap_sz <= queue_nr)
+			heap_sz <<= 1;
+		heap_array = realloc(heap->heap_array,
+				     heap_sz * sizeof(struct auxtrace_heap_item));
+		if (!heap_array)
+			return -ENOMEM;
+		heap->heap_array = heap_array;
+		heap->heap_sz = heap_sz;
+	}
+
+	auxtrace_heapify(heap->heap_array, heap->heap_cnt++, queue_nr, ordinal);
+
+	return 0;
+}
+
+void auxtrace_heap__free(struct auxtrace_heap *heap)
+{
+	zfree(&heap->heap_array);
+	heap->heap_cnt = 0;
+	heap->heap_sz = 0;
+}
+
+void auxtrace_heap__pop(struct auxtrace_heap *heap)
+{
+	unsigned int pos, last, heap_cnt = heap->heap_cnt;
+	struct auxtrace_heap_item *heap_array;
+
+	if (!heap_cnt)
+		return;
+
+	heap->heap_cnt -= 1;
+
+	heap_array = heap->heap_array;
+
+	pos = 0;
+	while (1) {
+		unsigned int left, right;
+
+		left = (pos << 1) + 1;
+		if (left >= heap_cnt)
+			break;
+		right = left + 1;
+		if (right >= heap_cnt) {
+			heap_array[pos] = heap_array[left];
+			return;
+		}
+		if (heap_array[left].ordinal < heap_array[right].ordinal) {
+			heap_array[pos] = heap_array[left];
+			pos = left;
+		} else {
+			heap_array[pos] = heap_array[right];
+			pos = right;
+		}
+	}
+
+	last = heap_cnt - 1;
+	auxtrace_heapify(heap_array, pos, heap_array[last].queue_nr,
+			 heap_array[last].ordinal);
+}
+
+size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr)
+{
+	if (itr)
+		return itr->info_priv_size(itr);
+	return 0;
+}
+
+static int auxtrace_not_supported(void)
+{
+	pr_err("AUX area tracing is not supported on this architecture\n");
+	return -EINVAL;
+}
+
+int auxtrace_record__info_fill(struct auxtrace_record *itr,
+			       struct perf_session *session,
+			       struct auxtrace_info_event *auxtrace_info,
+			       size_t priv_size)
+{
+	if (itr)
+		return itr->info_fill(itr, session, auxtrace_info, priv_size);
+	return auxtrace_not_supported();
+}
+
+void auxtrace_record__free(struct auxtrace_record *itr)
+{
+	if (itr)
+		itr->free(itr);
+}
+
+int auxtrace_record__snapshot_start(struct auxtrace_record *itr)
+{
+	if (itr && itr->snapshot_start)
+		return itr->snapshot_start(itr);
+	return 0;
+}
+
+int auxtrace_record__snapshot_finish(struct auxtrace_record *itr)
+{
+	if (itr && itr->snapshot_finish)
+		return itr->snapshot_finish(itr);
+	return 0;
+}
+
+int auxtrace_record__find_snapshot(struct auxtrace_record *itr, int idx,
+				   struct auxtrace_mmap *mm,
+				   unsigned char *data, u64 *head, u64 *old)
+{
+	if (itr && itr->find_snapshot)
+		return itr->find_snapshot(itr, idx, mm, data, head, old);
+	return 0;
+}
+
+int auxtrace_record__options(struct auxtrace_record *itr,
+			     struct perf_evlist *evlist,
+			     struct record_opts *opts)
+{
+	if (itr)
+		return itr->recording_options(itr, evlist, opts);
+	return 0;
+}
+
+u64 auxtrace_record__reference(struct auxtrace_record *itr)
+{
+	if (itr)
+		return itr->reference(itr);
+	return 0;
+}
+
+int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
+				    struct record_opts *opts, const char *str)
+{
+	if (!str)
+		return 0;
+
+	if (itr)
+		return itr->parse_snapshot_options(itr, opts, str);
+
+	pr_err("No AUX area tracing to snapshot\n");
+	return -EINVAL;
+}
+
+struct auxtrace_record *__weak
+auxtrace_record__init(struct perf_evlist *evlist __maybe_unused, int *err)
+{
+	*err = 0;
+	return NULL;
+}
+
+static int auxtrace_index__alloc(struct list_head *head)
+{
+	struct auxtrace_index *auxtrace_index;
+
+	auxtrace_index = malloc(sizeof(struct auxtrace_index));
+	if (!auxtrace_index)
+		return -ENOMEM;
+
+	auxtrace_index->nr = 0;
+	INIT_LIST_HEAD(&auxtrace_index->list);
+
+	list_add_tail(&auxtrace_index->list, head);
+
+	return 0;
+}
+
+void auxtrace_index__free(struct list_head *head)
+{
+	struct auxtrace_index *auxtrace_index, *n;
+
+	list_for_each_entry_safe(auxtrace_index, n, head, list) {
+		list_del(&auxtrace_index->list);
+		free(auxtrace_index);
+	}
+}
+
+static struct auxtrace_index *auxtrace_index__last(struct list_head *head)
+{
+	struct auxtrace_index *auxtrace_index;
+	int err;
+
+	if (list_empty(head)) {
+		err = auxtrace_index__alloc(head);
+		if (err)
+			return NULL;
+	}
+
+	auxtrace_index = list_entry(head->prev, struct auxtrace_index, list);
+
+	if (auxtrace_index->nr >= PERF_AUXTRACE_INDEX_ENTRY_COUNT) {
+		err = auxtrace_index__alloc(head);
+		if (err)
+			return NULL;
+		auxtrace_index = list_entry(head->prev, struct auxtrace_index,
+					    list);
+	}
+
+	return auxtrace_index;
+}
+
+int auxtrace_index__auxtrace_event(struct list_head *head,
+				   union perf_event *event, off_t file_offset)
+{
+	struct auxtrace_index *auxtrace_index;
+	size_t nr;
+
+	auxtrace_index = auxtrace_index__last(head);
+	if (!auxtrace_index)
+		return -ENOMEM;
+
+	nr = auxtrace_index->nr;
+	auxtrace_index->entries[nr].file_offset = file_offset;
+	auxtrace_index->entries[nr].sz = event->header.size;
+	auxtrace_index->nr += 1;
+
+	return 0;
+}
+
+static int auxtrace_index__do_write(int fd,
+				    struct auxtrace_index *auxtrace_index)
+{
+	struct auxtrace_index_entry ent;
+	size_t i;
+
+	for (i = 0; i < auxtrace_index->nr; i++) {
+		ent.file_offset = auxtrace_index->entries[i].file_offset;
+		ent.sz = auxtrace_index->entries[i].sz;
+		if (writen(fd, &ent, sizeof(ent)) != sizeof(ent))
+			return -errno;
+	}
+	return 0;
+}
+
+int auxtrace_index__write(int fd, struct list_head *head)
+{
+	struct auxtrace_index *auxtrace_index;
+	u64 total = 0;
+	int err;
+
+	list_for_each_entry(auxtrace_index, head, list)
+		total += auxtrace_index->nr;
+
+	if (writen(fd, &total, sizeof(total)) != sizeof(total))
+		return -errno;
+
+	list_for_each_entry(auxtrace_index, head, list) {
+		err = auxtrace_index__do_write(fd, auxtrace_index);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int auxtrace_index__process_entry(int fd, struct list_head *head,
+					 bool needs_swap)
+{
+	struct auxtrace_index *auxtrace_index;
+	struct auxtrace_index_entry ent;
+	size_t nr;
+
+	if (readn(fd, &ent, sizeof(ent)) != sizeof(ent))
+		return -1;
+
+	auxtrace_index = auxtrace_index__last(head);
+	if (!auxtrace_index)
+		return -1;
+
+	nr = auxtrace_index->nr;
+	if (needs_swap) {
+		auxtrace_index->entries[nr].file_offset =
+						bswap_64(ent.file_offset);
+		auxtrace_index->entries[nr].sz = bswap_64(ent.sz);
+	} else {
+		auxtrace_index->entries[nr].file_offset = ent.file_offset;
+		auxtrace_index->entries[nr].sz = ent.sz;
+	}
+
+	auxtrace_index->nr = nr + 1;
+
+	return 0;
+}
+
+int auxtrace_index__process(int fd, u64 size, struct perf_session *session,
+			    bool needs_swap)
+{
+	struct list_head *head = &session->auxtrace_index;
+	u64 nr;
+
+	if (readn(fd, &nr, sizeof(u64)) != sizeof(u64))
+		return -1;
+
+	if (needs_swap)
+		nr = bswap_64(nr);
+
+	if (sizeof(u64) + nr * sizeof(struct auxtrace_index_entry) > size)
+		return -1;
+
+	while (nr--) {
+		int err;
+
+		err = auxtrace_index__process_entry(fd, head, needs_swap);
+		if (err)
+			return -1;
+	}
+
+	return 0;
+}
+
+static int auxtrace_queues__process_index_entry(struct auxtrace_queues *queues,
+						struct perf_session *session,
+						struct auxtrace_index_entry *ent)
+{
+	return auxtrace_queues__add_indexed_event(queues, session,
+						  ent->file_offset, ent->sz);
+}
+
+int auxtrace_queues__process_index(struct auxtrace_queues *queues,
+				   struct perf_session *session)
+{
+	struct auxtrace_index *auxtrace_index;
+	struct auxtrace_index_entry *ent;
+	size_t i;
+	int err;
+
+	list_for_each_entry(auxtrace_index, &session->auxtrace_index, list) {
+		for (i = 0; i < auxtrace_index->nr; i++) {
+			ent = &auxtrace_index->entries[i];
+			err = auxtrace_queues__process_index_entry(queues,
+								   session,
+								   ent);
+			if (err)
+				return err;
+		}
+	}
+	return 0;
+}
+
+struct auxtrace_buffer *auxtrace_buffer__next(struct auxtrace_queue *queue,
+					      struct auxtrace_buffer *buffer)
+{
+	if (buffer) {
+		if (list_is_last(&buffer->list, &queue->head))
+			return NULL;
+		return list_entry(buffer->list.next, struct auxtrace_buffer,
+				  list);
+	} else {
+		if (list_empty(&queue->head))
+			return NULL;
+		return list_entry(queue->head.next, struct auxtrace_buffer,
+				  list);
+	}
+}
+
+void *auxtrace_buffer__get_data(struct auxtrace_buffer *buffer, int fd)
+{
+	size_t adj = buffer->data_offset & (page_size - 1);
+	size_t size = buffer->size + adj;
+	off_t file_offset = buffer->data_offset - adj;
+	void *addr;
+
+	if (buffer->data)
+		return buffer->data;
+
+	addr = mmap(NULL, size, PROT_READ, MAP_SHARED, fd, file_offset);
+	if (addr == MAP_FAILED)
+		return NULL;
+
+	buffer->mmap_addr = addr;
+	buffer->mmap_size = size;
+
+	buffer->data = addr + adj;
+
+	return buffer->data;
+}
+
+void auxtrace_buffer__put_data(struct auxtrace_buffer *buffer)
+{
+	if (!buffer->data || !buffer->mmap_addr)
+		return;
+	munmap(buffer->mmap_addr, buffer->mmap_size);
+	buffer->mmap_addr = NULL;
+	buffer->mmap_size = 0;
+	buffer->data = NULL;
+	buffer->use_data = NULL;
+}
+
+void auxtrace_buffer__drop_data(struct auxtrace_buffer *buffer)
+{
+	auxtrace_buffer__put_data(buffer);
+	if (buffer->data_needs_freeing) {
+		buffer->data_needs_freeing = false;
+		zfree(&buffer->data);
+		buffer->use_data = NULL;
+		buffer->size = 0;
+	}
+}
+
+void auxtrace_buffer__free(struct auxtrace_buffer *buffer)
+{
+	auxtrace_buffer__drop_data(buffer);
+	free(buffer);
+}
+
+void auxtrace_synth_error(struct auxtrace_error_event *auxtrace_error, int type,
+			  int code, int cpu, pid_t pid, pid_t tid, u64 ip,
+			  const char *msg)
+{
+	size_t size;
+
+	memset(auxtrace_error, 0, sizeof(struct auxtrace_error_event));
+
+	auxtrace_error->header.type = PERF_RECORD_AUXTRACE_ERROR;
+	auxtrace_error->type = type;
+	auxtrace_error->code = code;
+	auxtrace_error->cpu = cpu;
+	auxtrace_error->pid = pid;
+	auxtrace_error->tid = tid;
+	auxtrace_error->ip = ip;
+	strlcpy(auxtrace_error->msg, msg, MAX_AUXTRACE_ERROR_MSG);
+
+	size = (void *)auxtrace_error->msg - (void *)auxtrace_error +
+	       strlen(auxtrace_error->msg) + 1;
+	auxtrace_error->header.size = PERF_ALIGN(size, sizeof(u64));
+}
+
+int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
+					 struct perf_tool *tool,
+					 struct perf_session *session,
+					 perf_event__handler_t process)
+{
+	union perf_event *ev;
+	size_t priv_size;
+	int err;
+
+	pr_debug2("Synthesizing auxtrace information\n");
+	priv_size = auxtrace_record__info_priv_size(itr);
+	ev = zalloc(sizeof(struct auxtrace_info_event) + priv_size);
+	if (!ev)
+		return -ENOMEM;
+
+	ev->auxtrace_info.header.type = PERF_RECORD_AUXTRACE_INFO;
+	ev->auxtrace_info.header.size = sizeof(struct auxtrace_info_event) +
+					priv_size;
+	err = auxtrace_record__info_fill(itr, session, &ev->auxtrace_info,
+					 priv_size);
+	if (err)
+		goto out_free;
+
+	err = process(tool, ev, NULL, NULL);
+out_free:
+	free(ev);
+	return err;
+}
+
+static bool auxtrace__dont_decode(struct perf_session *session)
+{
+	return !session->itrace_synth_opts ||
+	       session->itrace_synth_opts->dont_decode;
+}
+
+int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
+				      union perf_event *event,
+				      struct perf_session *session __maybe_unused)
+{
+	enum auxtrace_type type = event->auxtrace_info.type;
+
+	if (dump_trace)
+		fprintf(stdout, " type: %u\n", type);
+
+	switch (type) {
+	case PERF_AUXTRACE_UNKNOWN:
+	default:
+		return -EINVAL;
+	}
+}
+
+s64 perf_event__process_auxtrace(struct perf_tool *tool,
+				 union perf_event *event,
+				 struct perf_session *session)
+{
+	s64 err;
+
+	if (dump_trace)
+		fprintf(stdout, " size: %#"PRIx64"  offset: %#"PRIx64"  ref: %#"PRIx64"  idx: %u  tid: %d  cpu: %d\n",
+			event->auxtrace.size, event->auxtrace.offset,
+			event->auxtrace.reference, event->auxtrace.idx,
+			event->auxtrace.tid, event->auxtrace.cpu);
+
+	if (auxtrace__dont_decode(session))
+		return event->auxtrace.size;
+
+	if (!session->auxtrace || event->header.type != PERF_RECORD_AUXTRACE)
+		return -EINVAL;
+
+	err = session->auxtrace->process_auxtrace_event(session, event, tool);
+	if (err < 0)
+		return err;
+
+	return event->auxtrace.size;
+}
+
+#define PERF_ITRACE_DEFAULT_PERIOD_TYPE		PERF_ITRACE_PERIOD_NANOSECS
+#define PERF_ITRACE_DEFAULT_PERIOD		100000
+#define PERF_ITRACE_DEFAULT_CALLCHAIN_SZ	16
+#define PERF_ITRACE_MAX_CALLCHAIN_SZ		1024
+
+void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts)
+{
+	synth_opts->instructions = true;
+	synth_opts->branches = true;
+	synth_opts->transactions = true;
+	synth_opts->errors = true;
+	synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE;
+	synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
+	synth_opts->callchain_sz = PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
+}
+
+/*
+ * Please check tools/perf/Documentation/perf-script.txt for information
+ * about the options parsed here, which is introduced after this cset,
+ * when support in 'perf script' for these options is introduced.
+ */
+int itrace_parse_synth_opts(const struct option *opt, const char *str,
+			    int unset)
+{
+	struct itrace_synth_opts *synth_opts = opt->value;
+	const char *p;
+	char *endptr;
+
+	synth_opts->set = true;
+
+	if (unset) {
+		synth_opts->dont_decode = true;
+		return 0;
+	}
+
+	if (!str) {
+		itrace_synth_opts__set_default(synth_opts);
+		return 0;
+	}
+
+	for (p = str; *p;) {
+		switch (*p++) {
+		case 'i':
+			synth_opts->instructions = true;
+			while (*p == ' ' || *p == ',')
+				p += 1;
+			if (isdigit(*p)) {
+				synth_opts->period = strtoull(p, &endptr, 10);
+				p = endptr;
+				while (*p == ' ' || *p == ',')
+					p += 1;
+				switch (*p++) {
+				case 'i':
+					synth_opts->period_type =
+						PERF_ITRACE_PERIOD_INSTRUCTIONS;
+					break;
+				case 't':
+					synth_opts->period_type =
+						PERF_ITRACE_PERIOD_TICKS;
+					break;
+				case 'm':
+					synth_opts->period *= 1000;
+					/* Fall through */
+				case 'u':
+					synth_opts->period *= 1000;
+					/* Fall through */
+				case 'n':
+					if (*p++ != 's')
+						goto out_err;
+					synth_opts->period_type =
+						PERF_ITRACE_PERIOD_NANOSECS;
+					break;
+				case '\0':
+					goto out;
+				default:
+					goto out_err;
+				}
+			}
+			break;
+		case 'b':
+			synth_opts->branches = true;
+			break;
+		case 'x':
+			synth_opts->transactions = true;
+			break;
+		case 'e':
+			synth_opts->errors = true;
+			break;
+		case 'd':
+			synth_opts->log = true;
+			break;
+		case 'c':
+			synth_opts->branches = true;
+			synth_opts->calls = true;
+			break;
+		case 'r':
+			synth_opts->branches = true;
+			synth_opts->returns = true;
+			break;
+		case 'g':
+			synth_opts->callchain = true;
+			synth_opts->callchain_sz =
+					PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
+			while (*p == ' ' || *p == ',')
+				p += 1;
+			if (isdigit(*p)) {
+				unsigned int val;
+
+				val = strtoul(p, &endptr, 10);
+				p = endptr;
+				if (!val || val > PERF_ITRACE_MAX_CALLCHAIN_SZ)
+					goto out_err;
+				synth_opts->callchain_sz = val;
+			}
+			break;
+		case ' ':
+		case ',':
+			break;
+		default:
+			goto out_err;
+		}
+	}
+out:
+	if (synth_opts->instructions) {
+		if (!synth_opts->period_type)
+			synth_opts->period_type =
+					PERF_ITRACE_DEFAULT_PERIOD_TYPE;
+		if (!synth_opts->period)
+			synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
+	}
+
+	return 0;
+
+out_err:
+	pr_err("Bad Instruction Tracing options '%s'\n", str);
+	return -EINVAL;
+}
+
+static const char * const auxtrace_error_type_name[] = {
+	[PERF_AUXTRACE_ERROR_ITRACE] = "instruction trace",
+};
+
+static const char *auxtrace_error_name(int type)
+{
+	const char *error_type_name = NULL;
+
+	if (type < PERF_AUXTRACE_ERROR_MAX)
+		error_type_name = auxtrace_error_type_name[type];
+	if (!error_type_name)
+		error_type_name = "unknown AUX";
+	return error_type_name;
+}
+
+size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp)
+{
+	struct auxtrace_error_event *e = &event->auxtrace_error;
+	int ret;
+
+	ret = fprintf(fp, " %s error type %u",
+		      auxtrace_error_name(e->type), e->type);
+	ret += fprintf(fp, " cpu %d pid %d tid %d ip %#"PRIx64" code %u: %s\n",
+		       e->cpu, e->pid, e->tid, e->ip, e->code, e->msg);
+	return ret;
+}
+
+void perf_session__auxtrace_error_inc(struct perf_session *session,
+				      union perf_event *event)
+{
+	struct auxtrace_error_event *e = &event->auxtrace_error;
+
+	if (e->type < PERF_AUXTRACE_ERROR_MAX)
+		session->evlist->stats.nr_auxtrace_errors[e->type] += 1;
+}
+
+void events_stats__auxtrace_error_warn(const struct events_stats *stats)
+{
+	int i;
+
+	for (i = 0; i < PERF_AUXTRACE_ERROR_MAX; i++) {
+		if (!stats->nr_auxtrace_errors[i])
+			continue;
+		ui__warning("%u %s errors\n",
+			    stats->nr_auxtrace_errors[i],
+			    auxtrace_error_name(i));
+	}
+}
+
+int perf_event__process_auxtrace_error(struct perf_tool *tool __maybe_unused,
+				       union perf_event *event,
+				       struct perf_session *session)
+{
+	if (auxtrace__dont_decode(session))
+		return 0;
+
+	perf_event__fprintf_auxtrace_error(event, stdout);
+	return 0;
+}
+
+static int __auxtrace_mmap__read(struct auxtrace_mmap *mm,
+				 struct auxtrace_record *itr,
+				 struct perf_tool *tool, process_auxtrace_t fn,
+				 bool snapshot, size_t snapshot_size)
+{
+	u64 head, old = mm->prev, offset, ref;
+	unsigned char *data = mm->base;
+	size_t size, head_off, old_off, len1, len2, padding;
+	union perf_event ev;
+	void *data1, *data2;
+
+	if (snapshot) {
+		head = auxtrace_mmap__read_snapshot_head(mm);
+		if (auxtrace_record__find_snapshot(itr, mm->idx, mm, data,
+						   &head, &old))
+			return -1;
+	} else {
+		head = auxtrace_mmap__read_head(mm);
+	}
+
+	if (old == head)
+		return 0;
+
+	pr_debug3("auxtrace idx %d old %#"PRIx64" head %#"PRIx64" diff %#"PRIx64"\n",
+		  mm->idx, old, head, head - old);
+
+	if (mm->mask) {
+		head_off = head & mm->mask;
+		old_off = old & mm->mask;
+	} else {
+		head_off = head % mm->len;
+		old_off = old % mm->len;
+	}
+
+	if (head_off > old_off)
+		size = head_off - old_off;
+	else
+		size = mm->len - (old_off - head_off);
+
+	if (snapshot && size > snapshot_size)
+		size = snapshot_size;
+
+	ref = auxtrace_record__reference(itr);
+
+	if (head > old || size <= head || mm->mask) {
+		offset = head - size;
+	} else {
+		/*
+		 * When the buffer size is not a power of 2, 'head' wraps at the
+		 * highest multiple of the buffer size, so we have to subtract
+		 * the remainder here.
+		 */
+		u64 rem = (0ULL - mm->len) % mm->len;
+
+		offset = head - size - rem;
+	}
+
+	if (size > head_off) {
+		len1 = size - head_off;
+		data1 = &data[mm->len - len1];
+		len2 = head_off;
+		data2 = &data[0];
+	} else {
+		len1 = size;
+		data1 = &data[head_off - len1];
+		len2 = 0;
+		data2 = NULL;
+	}
+
+	if (itr->alignment) {
+		unsigned int unwanted = len1 % itr->alignment;
+
+		len1 -= unwanted;
+		size -= unwanted;
+	}
+
+	/* padding must be written by fn() e.g. record__process_auxtrace() */
+	padding = size & 7;
+	if (padding)
+		padding = 8 - padding;
+
+	memset(&ev, 0, sizeof(ev));
+	ev.auxtrace.header.type = PERF_RECORD_AUXTRACE;
+	ev.auxtrace.header.size = sizeof(ev.auxtrace);
+	ev.auxtrace.size = size + padding;
+	ev.auxtrace.offset = offset;
+	ev.auxtrace.reference = ref;
+	ev.auxtrace.idx = mm->idx;
+	ev.auxtrace.tid = mm->tid;
+	ev.auxtrace.cpu = mm->cpu;
+
+	if (fn(tool, &ev, data1, len1, data2, len2))
+		return -1;
+
+	mm->prev = head;
+
+	if (!snapshot) {
+		auxtrace_mmap__write_tail(mm, head);
+		if (itr->read_finish) {
+			int err;
+
+			err = itr->read_finish(itr, mm->idx);
+			if (err < 0)
+				return err;
+		}
+	}
+
+	return 1;
+}
+
+int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
+			struct perf_tool *tool, process_auxtrace_t fn)
+{
+	return __auxtrace_mmap__read(mm, itr, tool, fn, false, 0);
+}
+
+int auxtrace_mmap__read_snapshot(struct auxtrace_mmap *mm,
+				 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);
+}
+
+/**
+ * struct auxtrace_cache - hash table to implement a cache
+ * @hashtable: the hashtable
+ * @sz: hashtable size (number of hlists)
+ * @entry_size: size of an entry
+ * @limit: limit the number of entries to this maximum, when reached the cache
+ *         is dropped and caching begins again with an empty cache
+ * @cnt: current number of entries
+ * @bits: hashtable size (@sz = 2^@bits)
+ */
+struct auxtrace_cache {
+	struct hlist_head *hashtable;
+	size_t sz;
+	size_t entry_size;
+	size_t limit;
+	size_t cnt;
+	unsigned int bits;
+};
+
+struct auxtrace_cache *auxtrace_cache__new(unsigned int bits, size_t entry_size,
+					   unsigned int limit_percent)
+{
+	struct auxtrace_cache *c;
+	struct hlist_head *ht;
+	size_t sz, i;
+
+	c = zalloc(sizeof(struct auxtrace_cache));
+	if (!c)
+		return NULL;
+
+	sz = 1UL << bits;
+
+	ht = calloc(sz, sizeof(struct hlist_head));
+	if (!ht)
+		goto out_free;
+
+	for (i = 0; i < sz; i++)
+		INIT_HLIST_HEAD(&ht[i]);
+
+	c->hashtable = ht;
+	c->sz = sz;
+	c->entry_size = entry_size;
+	c->limit = (c->sz * limit_percent) / 100;
+	c->bits = bits;
+
+	return c;
+
+out_free:
+	free(c);
+	return NULL;
+}
+
+static void auxtrace_cache__drop(struct auxtrace_cache *c)
+{
+	struct auxtrace_cache_entry *entry;
+	struct hlist_node *tmp;
+	size_t i;
+
+	if (!c)
+		return;
+
+	for (i = 0; i < c->sz; i++) {
+		hlist_for_each_entry_safe(entry, tmp, &c->hashtable[i], hash) {
+			hlist_del(&entry->hash);
+			auxtrace_cache__free_entry(c, entry);
+		}
+	}
+
+	c->cnt = 0;
+}
+
+void auxtrace_cache__free(struct auxtrace_cache *c)
+{
+	if (!c)
+		return;
+
+	auxtrace_cache__drop(c);
+	free(c->hashtable);
+	free(c);
+}
+
+void *auxtrace_cache__alloc_entry(struct auxtrace_cache *c)
+{
+	return malloc(c->entry_size);
+}
+
+void auxtrace_cache__free_entry(struct auxtrace_cache *c __maybe_unused,
+				void *entry)
+{
+	free(entry);
+}
+
+int auxtrace_cache__add(struct auxtrace_cache *c, u32 key,
+			struct auxtrace_cache_entry *entry)
+{
+	if (c->limit && ++c->cnt > c->limit)
+		auxtrace_cache__drop(c);
+
+	entry->key = key;
+	hlist_add_head(&entry->hash, &c->hashtable[hash_32(key, c->bits)]);
+
+	return 0;
+}
+
+void *auxtrace_cache__lookup(struct auxtrace_cache *c, u32 key)
+{
+	struct auxtrace_cache_entry *entry;
+	struct hlist_head *hlist;
+
+	if (!c)
+		return NULL;
+
+	hlist = &c->hashtable[hash_32(key, c->bits)];
+	hlist_for_each_entry(entry, hlist, hash) {
+		if (entry->key == key)
+			return entry;
+	}
+
+	return NULL;
+}
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
new file mode 100644
index 000000000..471aecbc4
--- /dev/null
+++ b/tools/perf/util/auxtrace.h
@@ -0,0 +1,644 @@
+/*
+ * auxtrace.h: AUX area trace support
+ * Copyright (c) 2013-2015, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#ifndef __PERF_AUXTRACE_H
+#define __PERF_AUXTRACE_H
+
+#include <sys/types.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <linux/list.h>
+#include <linux/perf_event.h>
+#include <linux/types.h>
+
+#include "../perf.h"
+#include "event.h"
+#include "session.h"
+#include "debug.h"
+
+union perf_event;
+struct perf_session;
+struct perf_evlist;
+struct perf_tool;
+struct option;
+struct record_opts;
+struct auxtrace_info_event;
+struct events_stats;
+
+enum auxtrace_type {
+	PERF_AUXTRACE_UNKNOWN,
+};
+
+enum itrace_period_type {
+	PERF_ITRACE_PERIOD_INSTRUCTIONS,
+	PERF_ITRACE_PERIOD_TICKS,
+	PERF_ITRACE_PERIOD_NANOSECS,
+};
+
+/**
+ * struct itrace_synth_opts - AUX area tracing synthesis options.
+ * @set: indicates whether or not options have been set
+ * @inject: indicates the event (not just the sample) must be fully synthesized
+ *          because 'perf inject' will write it out
+ * @instructions: whether to synthesize 'instructions' events
+ * @branches: whether to synthesize 'branches' events
+ * @transactions: whether to synthesize events for transactions
+ * @errors: whether to synthesize decoder error events
+ * @dont_decode: whether to skip decoding entirely
+ * @log: write a decoding log
+ * @calls: limit branch samples to calls (can be combined with @returns)
+ * @returns: limit branch samples to returns (can be combined with @calls)
+ * @callchain: add callchain to 'instructions' events
+ * @callchain_sz: maximum callchain size
+ * @period: 'instructions' events period
+ * @period_type: 'instructions' events period type
+ */
+struct itrace_synth_opts {
+	bool			set;
+	bool			inject;
+	bool			instructions;
+	bool			branches;
+	bool			transactions;
+	bool			errors;
+	bool			dont_decode;
+	bool			log;
+	bool			calls;
+	bool			returns;
+	bool			callchain;
+	unsigned int		callchain_sz;
+	unsigned long long	period;
+	enum itrace_period_type	period_type;
+};
+
+/**
+ * struct auxtrace_index_entry - indexes a AUX area tracing event within a
+ *                               perf.data file.
+ * @file_offset: offset within the perf.data file
+ * @sz: size of the event
+ */
+struct auxtrace_index_entry {
+	u64			file_offset;
+	u64			sz;
+};
+
+#define PERF_AUXTRACE_INDEX_ENTRY_COUNT 256
+
+/**
+ * struct auxtrace_index - index of AUX area tracing events within a perf.data
+ *                         file.
+ * @list: linking a number of arrays of entries
+ * @nr: number of entries
+ * @entries: array of entries
+ */
+struct auxtrace_index {
+	struct list_head	list;
+	size_t			nr;
+	struct auxtrace_index_entry entries[PERF_AUXTRACE_INDEX_ENTRY_COUNT];
+};
+
+/**
+ * struct auxtrace - session callbacks to allow AUX area data decoding.
+ * @process_event: lets the decoder see all session events
+ * @flush_events: process any remaining data
+ * @free_events: free resources associated with event processing
+ * @free: free resources associated with the session
+ */
+struct auxtrace {
+	int (*process_event)(struct perf_session *session,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct perf_tool *tool);
+	int (*process_auxtrace_event)(struct perf_session *session,
+				      union perf_event *event,
+				      struct perf_tool *tool);
+	int (*flush_events)(struct perf_session *session,
+			    struct perf_tool *tool);
+	void (*free_events)(struct perf_session *session);
+	void (*free)(struct perf_session *session);
+};
+
+/**
+ * struct auxtrace_buffer - a buffer containing AUX area tracing data.
+ * @list: buffers are queued in a list held by struct auxtrace_queue
+ * @size: size of the buffer in bytes
+ * @pid: in per-thread mode, the pid this buffer is associated with
+ * @tid: in per-thread mode, the tid this buffer is associated with
+ * @cpu: in per-cpu mode, the cpu this buffer is associated with
+ * @data: actual buffer data (can be null if the data has not been loaded)
+ * @data_offset: file offset at which the buffer can be read
+ * @mmap_addr: mmap address at which the buffer can be read
+ * @mmap_size: size of the mmap at @mmap_addr
+ * @data_needs_freeing: @data was malloc'd so free it when it is no longer
+ *                      needed
+ * @consecutive: the original data was split up and this buffer is consecutive
+ *               to the previous buffer
+ * @offset: offset as determined by aux_head / aux_tail members of struct
+ *          perf_event_mmap_page
+ * @reference: an implementation-specific reference determined when the data is
+ *             recorded
+ * @buffer_nr: used to number each buffer
+ * @use_size: implementation actually only uses this number of bytes
+ * @use_data: implementation actually only uses data starting at this address
+ */
+struct auxtrace_buffer {
+	struct list_head	list;
+	size_t			size;
+	pid_t			pid;
+	pid_t			tid;
+	int			cpu;
+	void			*data;
+	off_t			data_offset;
+	void			*mmap_addr;
+	size_t			mmap_size;
+	bool			data_needs_freeing;
+	bool			consecutive;
+	u64			offset;
+	u64			reference;
+	u64			buffer_nr;
+	size_t			use_size;
+	void			*use_data;
+};
+
+/**
+ * struct auxtrace_queue - a queue of AUX area tracing data buffers.
+ * @head: head of buffer list
+ * @tid: in per-thread mode, the tid this queue is associated with
+ * @cpu: in per-cpu mode, the cpu this queue is associated with
+ * @set: %true once this queue has been dedicated to a specific thread or cpu
+ * @priv: implementation-specific data
+ */
+struct auxtrace_queue {
+	struct list_head	head;
+	pid_t			tid;
+	int			cpu;
+	bool			set;
+	void			*priv;
+};
+
+/**
+ * struct auxtrace_queues - an array of AUX area tracing queues.
+ * @queue_array: array of queues
+ * @nr_queues: number of queues
+ * @new_data: set whenever new data is queued
+ * @populated: queues have been fully populated using the auxtrace_index
+ * @next_buffer_nr: used to number each buffer
+ */
+struct auxtrace_queues {
+	struct auxtrace_queue	*queue_array;
+	unsigned int		nr_queues;
+	bool			new_data;
+	bool			populated;
+	u64			next_buffer_nr;
+};
+
+/**
+ * struct auxtrace_heap_item - element of struct auxtrace_heap.
+ * @queue_nr: queue number
+ * @ordinal: value used for sorting (lowest ordinal is top of the heap) expected
+ *           to be a timestamp
+ */
+struct auxtrace_heap_item {
+	unsigned int		queue_nr;
+	u64			ordinal;
+};
+
+/**
+ * struct auxtrace_heap - a heap suitable for sorting AUX area tracing queues.
+ * @heap_array: the heap
+ * @heap_cnt: the number of elements in the heap
+ * @heap_sz: maximum number of elements (grows as needed)
+ */
+struct auxtrace_heap {
+	struct auxtrace_heap_item	*heap_array;
+	unsigned int		heap_cnt;
+	unsigned int		heap_sz;
+};
+
+/**
+ * struct auxtrace_mmap - records an mmap of the auxtrace buffer.
+ * @base: address of mapped area
+ * @userpg: pointer to buffer's perf_event_mmap_page
+ * @mask: %0 if @len is not a power of two, otherwise (@len - %1)
+ * @len: size of mapped area
+ * @prev: previous aux_head
+ * @idx: index of this mmap
+ * @tid: tid for a per-thread mmap (also set if there is only 1 tid on a per-cpu
+ *       mmap) otherwise %0
+ * @cpu: cpu number for a per-cpu mmap otherwise %-1
+ */
+struct auxtrace_mmap {
+	void		*base;
+	void		*userpg;
+	size_t		mask;
+	size_t		len;
+	u64		prev;
+	int		idx;
+	pid_t		tid;
+	int		cpu;
+};
+
+/**
+ * struct auxtrace_mmap_params - parameters to set up struct auxtrace_mmap.
+ * @mask: %0 if @len is not a power of two, otherwise (@len - %1)
+ * @offset: file offset of mapped area
+ * @len: size of mapped area
+ * @prot: mmap memory protection
+ * @idx: index of this mmap
+ * @tid: tid for a per-thread mmap (also set if there is only 1 tid on a per-cpu
+ *       mmap) otherwise %0
+ * @cpu: cpu number for a per-cpu mmap otherwise %-1
+ */
+struct auxtrace_mmap_params {
+	size_t		mask;
+	off_t		offset;
+	size_t		len;
+	int		prot;
+	int		idx;
+	pid_t		tid;
+	int		cpu;
+};
+
+/**
+ * struct auxtrace_record - callbacks for recording AUX area data.
+ * @recording_options: validate and process recording options
+ * @info_priv_size: return the size of the private data in auxtrace_info_event
+ * @info_fill: fill-in the private data in auxtrace_info_event
+ * @free: free this auxtrace record structure
+ * @snapshot_start: starting a snapshot
+ * @snapshot_finish: finishing a snapshot
+ * @find_snapshot: find data to snapshot within auxtrace mmap
+ * @parse_snapshot_options: parse snapshot options
+ * @reference: provide a 64-bit reference number for auxtrace_event
+ * @read_finish: called after reading from an auxtrace mmap
+ */
+struct auxtrace_record {
+	int (*recording_options)(struct auxtrace_record *itr,
+				 struct perf_evlist *evlist,
+				 struct record_opts *opts);
+	size_t (*info_priv_size)(struct auxtrace_record *itr);
+	int (*info_fill)(struct auxtrace_record *itr,
+			 struct perf_session *session,
+			 struct auxtrace_info_event *auxtrace_info,
+			 size_t priv_size);
+	void (*free)(struct auxtrace_record *itr);
+	int (*snapshot_start)(struct auxtrace_record *itr);
+	int (*snapshot_finish)(struct auxtrace_record *itr);
+	int (*find_snapshot)(struct auxtrace_record *itr, int idx,
+			     struct auxtrace_mmap *mm, unsigned char *data,
+			     u64 *head, u64 *old);
+	int (*parse_snapshot_options)(struct auxtrace_record *itr,
+				      struct record_opts *opts,
+				      const char *str);
+	u64 (*reference)(struct auxtrace_record *itr);
+	int (*read_finish)(struct auxtrace_record *itr, int idx);
+	unsigned int alignment;
+};
+
+#ifdef HAVE_AUXTRACE_SUPPORT
+
+/*
+ * In snapshot mode the mmapped page is read-only which makes using
+ * __sync_val_compare_and_swap() problematic.  However, snapshot mode expects
+ * the buffer is not updated while the snapshot is made (e.g. Intel PT disables
+ * the event) so there is not a race anyway.
+ */
+static inline u64 auxtrace_mmap__read_snapshot_head(struct auxtrace_mmap *mm)
+{
+	struct perf_event_mmap_page *pc = mm->userpg;
+	u64 head = ACCESS_ONCE(pc->aux_head);
+
+	/* Ensure all reads are done after we read the head */
+	rmb();
+	return head;
+}
+
+static inline u64 auxtrace_mmap__read_head(struct auxtrace_mmap *mm)
+{
+	struct perf_event_mmap_page *pc = mm->userpg;
+#if BITS_PER_LONG == 64 || !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+	u64 head = ACCESS_ONCE(pc->aux_head);
+#else
+	u64 head = __sync_val_compare_and_swap(&pc->aux_head, 0, 0);
+#endif
+
+	/* Ensure all reads are done after we read the head */
+	rmb();
+	return head;
+}
+
+static inline void auxtrace_mmap__write_tail(struct auxtrace_mmap *mm, u64 tail)
+{
+	struct perf_event_mmap_page *pc = mm->userpg;
+#if BITS_PER_LONG != 64 && defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+	u64 old_tail;
+#endif
+
+	/* Ensure all reads are done before we write the tail out */
+	mb();
+#if BITS_PER_LONG == 64 || !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+	pc->aux_tail = tail;
+#else
+	do {
+		old_tail = __sync_val_compare_and_swap(&pc->aux_tail, 0, 0);
+	} while (!__sync_bool_compare_and_swap(&pc->aux_tail, old_tail, tail));
+#endif
+}
+
+int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
+			struct auxtrace_mmap_params *mp,
+			void *userpg, int fd);
+void auxtrace_mmap__munmap(struct auxtrace_mmap *mm);
+void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,
+				off_t auxtrace_offset,
+				unsigned int auxtrace_pages,
+				bool auxtrace_overwrite);
+void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
+				   struct perf_evlist *evlist, int idx,
+				   bool per_cpu);
+
+typedef int (*process_auxtrace_t)(struct perf_tool *tool,
+				  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,
+			struct perf_tool *tool, process_auxtrace_t fn);
+
+int auxtrace_mmap__read_snapshot(struct auxtrace_mmap *mm,
+				 struct auxtrace_record *itr,
+				 struct perf_tool *tool, process_auxtrace_t fn,
+				 size_t snapshot_size);
+
+int auxtrace_queues__init(struct auxtrace_queues *queues);
+int auxtrace_queues__add_event(struct auxtrace_queues *queues,
+			       struct perf_session *session,
+			       union perf_event *event, off_t data_offset,
+			       struct auxtrace_buffer **buffer_ptr);
+void auxtrace_queues__free(struct auxtrace_queues *queues);
+int auxtrace_queues__process_index(struct auxtrace_queues *queues,
+				   struct perf_session *session);
+struct auxtrace_buffer *auxtrace_buffer__next(struct auxtrace_queue *queue,
+					      struct auxtrace_buffer *buffer);
+void *auxtrace_buffer__get_data(struct auxtrace_buffer *buffer, int fd);
+void auxtrace_buffer__put_data(struct auxtrace_buffer *buffer);
+void auxtrace_buffer__drop_data(struct auxtrace_buffer *buffer);
+void auxtrace_buffer__free(struct auxtrace_buffer *buffer);
+
+int auxtrace_heap__add(struct auxtrace_heap *heap, unsigned int queue_nr,
+		       u64 ordinal);
+void auxtrace_heap__pop(struct auxtrace_heap *heap);
+void auxtrace_heap__free(struct auxtrace_heap *heap);
+
+struct auxtrace_cache_entry {
+	struct hlist_node hash;
+	u32 key;
+};
+
+struct auxtrace_cache *auxtrace_cache__new(unsigned int bits, size_t entry_size,
+					   unsigned int limit_percent);
+void auxtrace_cache__free(struct auxtrace_cache *auxtrace_cache);
+void *auxtrace_cache__alloc_entry(struct auxtrace_cache *c);
+void auxtrace_cache__free_entry(struct auxtrace_cache *c, void *entry);
+int auxtrace_cache__add(struct auxtrace_cache *c, u32 key,
+			struct auxtrace_cache_entry *entry);
+void *auxtrace_cache__lookup(struct auxtrace_cache *c, u32 key);
+
+struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist,
+					      int *err);
+
+int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
+				    struct record_opts *opts,
+				    const char *str);
+int auxtrace_record__options(struct auxtrace_record *itr,
+			     struct perf_evlist *evlist,
+			     struct record_opts *opts);
+size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr);
+int auxtrace_record__info_fill(struct auxtrace_record *itr,
+			       struct perf_session *session,
+			       struct auxtrace_info_event *auxtrace_info,
+			       size_t priv_size);
+void auxtrace_record__free(struct auxtrace_record *itr);
+int auxtrace_record__snapshot_start(struct auxtrace_record *itr);
+int auxtrace_record__snapshot_finish(struct auxtrace_record *itr);
+int auxtrace_record__find_snapshot(struct auxtrace_record *itr, int idx,
+				   struct auxtrace_mmap *mm,
+				   unsigned char *data, u64 *head, u64 *old);
+u64 auxtrace_record__reference(struct auxtrace_record *itr);
+
+int auxtrace_index__auxtrace_event(struct list_head *head, union perf_event *event,
+				   off_t file_offset);
+int auxtrace_index__write(int fd, struct list_head *head);
+int auxtrace_index__process(int fd, u64 size, struct perf_session *session,
+			    bool needs_swap);
+void auxtrace_index__free(struct list_head *head);
+
+void auxtrace_synth_error(struct auxtrace_error_event *auxtrace_error, int type,
+			  int code, int cpu, pid_t pid, pid_t tid, u64 ip,
+			  const char *msg);
+
+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 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);
+
+size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp);
+void perf_session__auxtrace_error_inc(struct perf_session *session,
+				      union perf_event *event);
+void events_stats__auxtrace_error_warn(const struct events_stats *stats);
+
+static inline int auxtrace__process_event(struct perf_session *session,
+					  union perf_event *event,
+					  struct perf_sample *sample,
+					  struct perf_tool *tool)
+{
+	if (!session->auxtrace)
+		return 0;
+
+	return session->auxtrace->process_event(session, event, sample, tool);
+}
+
+static inline int auxtrace__flush_events(struct perf_session *session,
+					 struct perf_tool *tool)
+{
+	if (!session->auxtrace)
+		return 0;
+
+	return session->auxtrace->flush_events(session, tool);
+}
+
+static inline void auxtrace__free_events(struct perf_session *session)
+{
+	if (!session->auxtrace)
+		return;
+
+	return session->auxtrace->free_events(session);
+}
+
+static inline void auxtrace__free(struct perf_session *session)
+{
+	if (!session->auxtrace)
+		return;
+
+	return session->auxtrace->free(session);
+}
+
+#else
+
+static inline struct auxtrace_record *
+auxtrace_record__init(struct perf_evlist *evlist __maybe_unused,
+		      int *err __maybe_unused)
+{
+	*err = 0;
+	return NULL;
+}
+
+static inline
+void auxtrace_record__free(struct auxtrace_record *itr __maybe_unused)
+{
+}
+
+static inline int
+perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr __maybe_unused,
+				     struct perf_tool *tool __maybe_unused,
+				     struct perf_session *session __maybe_unused,
+				     perf_event__handler_t process __maybe_unused)
+{
+	return -EINVAL;
+}
+
+static inline
+int auxtrace_record__options(struct auxtrace_record *itr __maybe_unused,
+			     struct perf_evlist *evlist __maybe_unused,
+			     struct record_opts *opts __maybe_unused)
+{
+	return 0;
+}
+
+#define perf_event__process_auxtrace_info		0
+#define perf_event__process_auxtrace			0
+#define perf_event__process_auxtrace_error		0
+
+static inline
+void perf_session__auxtrace_error_inc(struct perf_session *session
+				      __maybe_unused,
+				      union perf_event *event
+				      __maybe_unused)
+{
+}
+
+static inline
+void events_stats__auxtrace_error_warn(const struct events_stats *stats
+				       __maybe_unused)
+{
+}
+
+static inline
+int itrace_parse_synth_opts(const struct option *opt __maybe_unused,
+			    const char *str __maybe_unused,
+			    int unset __maybe_unused)
+{
+	pr_err("AUX area tracing not supported\n");
+	return -EINVAL;
+}
+
+static inline
+int auxtrace_parse_snapshot_options(struct auxtrace_record *itr __maybe_unused,
+				    struct record_opts *opts __maybe_unused,
+				    const char *str)
+{
+	if (!str)
+		return 0;
+	pr_err("AUX area tracing not supported\n");
+	return -EINVAL;
+}
+
+static inline
+int auxtrace__process_event(struct perf_session *session __maybe_unused,
+			    union perf_event *event __maybe_unused,
+			    struct perf_sample *sample __maybe_unused,
+			    struct perf_tool *tool __maybe_unused)
+{
+	return 0;
+}
+
+static inline
+int auxtrace__flush_events(struct perf_session *session __maybe_unused,
+			   struct perf_tool *tool __maybe_unused)
+{
+	return 0;
+}
+
+static inline
+void auxtrace__free_events(struct perf_session *session __maybe_unused)
+{
+}
+
+static inline
+void auxtrace_cache__free(struct auxtrace_cache *auxtrace_cache __maybe_unused)
+{
+}
+
+static inline
+void auxtrace__free(struct perf_session *session __maybe_unused)
+{
+}
+
+static inline
+int auxtrace_index__write(int fd __maybe_unused,
+			  struct list_head *head __maybe_unused)
+{
+	return -EINVAL;
+}
+
+static inline
+int auxtrace_index__process(int fd __maybe_unused,
+			    u64 size __maybe_unused,
+			    struct perf_session *session __maybe_unused,
+			    bool needs_swap __maybe_unused)
+{
+	return -EINVAL;
+}
+
+static inline
+void auxtrace_index__free(struct list_head *head __maybe_unused)
+{
+}
+
+int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
+			struct auxtrace_mmap_params *mp,
+			void *userpg, int fd);
+void auxtrace_mmap__munmap(struct auxtrace_mmap *mm);
+void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,
+				off_t auxtrace_offset,
+				unsigned int auxtrace_pages,
+				bool auxtrace_overwrite);
+void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
+				   struct perf_evlist *evlist, int idx,
+				   bool per_cpu);
+
+#endif
+
+#endif
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 61867dff5..1f6fc2323 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -43,6 +43,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
 	if (al.map != NULL)
 		al.map->dso->hit = 1;
 
+	thread__put(thread);
 	return 0;
 }
 
@@ -59,8 +60,10 @@ static int perf_event__exit_del_thread(struct perf_tool *tool __maybe_unused,
 	dump_printf("(%d:%d):(%d:%d)\n", event->fork.pid, event->fork.tid,
 		    event->fork.ppid, event->fork.ptid);
 
-	if (thread)
+	if (thread) {
 		machine__remove_thread(machine, thread);
+		thread__put(thread);
+	}
 
 	return 0;
 }
@@ -159,15 +162,20 @@ static int write_buildid(const char *name, size_t name_len, u8 *build_id,
 	return write_padded(fd, name, name_len + 1, len);
 }
 
-static int __dsos__write_buildid_table(struct list_head *head,
-				       struct machine *machine,
-				       pid_t pid, u16 misc, int fd)
+static int machine__write_buildid_table(struct machine *machine, int fd)
 {
+	int err = 0;
 	char nm[PATH_MAX];
 	struct dso *pos;
+	u16 kmisc = PERF_RECORD_MISC_KERNEL,
+	    umisc = PERF_RECORD_MISC_USER;
 
-	dsos__for_each_with_build_id(pos, head) {
-		int err;
+	if (!machine__is_host(machine)) {
+		kmisc = PERF_RECORD_MISC_GUEST_KERNEL;
+		umisc = PERF_RECORD_MISC_GUEST_USER;
+	}
+
+	dsos__for_each_with_build_id(pos, &machine->dsos.head) {
 		const char *name;
 		size_t name_len;
 
@@ -186,32 +194,12 @@ static int __dsos__write_buildid_table(struct list_head *head,
 			name_len = pos->long_name_len + 1;
 		}
 
-		err = write_buildid(name, name_len, pos->build_id,
-				    pid, misc, fd);
+		err = write_buildid(name, name_len, pos->build_id, machine->pid,
+				    pos->kernel ? kmisc : umisc, fd);
 		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
-static int machine__write_buildid_table(struct machine *machine, int fd)
-{
-	int err;
-	u16 kmisc = PERF_RECORD_MISC_KERNEL,
-	    umisc = PERF_RECORD_MISC_USER;
-
-	if (!machine__is_host(machine)) {
-		kmisc = PERF_RECORD_MISC_GUEST_KERNEL;
-		umisc = PERF_RECORD_MISC_GUEST_USER;
+			break;
 	}
 
-	err = __dsos__write_buildid_table(&machine->kernel_dsos.head, machine,
-					  machine->pid, kmisc, fd);
-	if (err == 0)
-		err = __dsos__write_buildid_table(&machine->user_dsos.head,
-						  machine, machine->pid, umisc,
-						  fd);
 	return err;
 }
 
@@ -244,13 +232,7 @@ static int __dsos__hit_all(struct list_head *head)
 
 static int machine__hit_all_dsos(struct machine *machine)
 {
-	int err;
-
-	err = __dsos__hit_all(&machine->kernel_dsos.head);
-	if (err)
-		return err;
-
-	return __dsos__hit_all(&machine->user_dsos.head);
+	return __dsos__hit_all(&machine->dsos.head);
 }
 
 int dsos__hit_all(struct perf_session *session)
@@ -490,9 +472,7 @@ static int __dsos__cache_build_ids(struct list_head *head,
 
 static int machine__cache_build_ids(struct machine *machine)
 {
-	int ret = __dsos__cache_build_ids(&machine->kernel_dsos.head, machine);
-	ret |= __dsos__cache_build_ids(&machine->user_dsos.head, machine);
-	return ret;
+	return __dsos__cache_build_ids(&machine->dsos.head, machine);
 }
 
 int perf_session__cache_build_ids(struct perf_session *session)
@@ -517,11 +497,7 @@ int perf_session__cache_build_ids(struct perf_session *session)
 
 static bool machine__read_build_ids(struct machine *machine, bool with_hits)
 {
-	bool ret;
-
-	ret  = __dsos__read_build_ids(&machine->kernel_dsos.head, with_hits);
-	ret |= __dsos__read_build_ids(&machine->user_dsos.head, with_hits);
-	return ret;
+	return __dsos__read_build_ids(&machine->dsos.head, with_hits);
 }
 
 bool perf_session__read_build_ids(struct perf_session *session, bool with_hits)
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index fbcca21d6..c861373aa 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -30,7 +30,6 @@ extern const char *perf_config_dirname(const char *, const char *);
 
 /* pager.c */
 extern void setup_pager(void);
-extern const char *pager_program;
 extern int pager_in_use(void);
 extern int pager_use_color;
 
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 6033a0a21..679c2c6d8 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -72,6 +72,10 @@ extern struct callchain_param callchain_param;
 struct callchain_list {
 	u64			ip;
 	struct map_symbol	ms;
+	struct /* for TUI */ {
+		bool		unfolded;
+		bool		has_children;
+	};
 	char		       *srcline;
 	struct list_head	list;
 };
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 88f7be399..32e12ecfe 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -115,23 +115,19 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
 			goto found;
 		n++;
 	}
-	if (cgrp->refcnt == 0)
+	if (atomic_read(&cgrp->refcnt) == 0)
 		free(cgrp);
 
 	return -1;
 found:
-	cgrp->refcnt++;
+	atomic_inc(&cgrp->refcnt);
 	counter->cgrp = cgrp;
 	return 0;
 }
 
 void close_cgroup(struct cgroup_sel *cgrp)
 {
-	if (!cgrp)
-		return;
-
-	/* XXX: not reentrant */
-	if (--cgrp->refcnt == 0) {
+	if (cgrp && atomic_dec_and_test(&cgrp->refcnt)) {
 		close(cgrp->fd);
 		zfree(&cgrp->name);
 		free(cgrp);
diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h
index 89acd6deb..b4b8cb42f 100644
--- a/tools/perf/util/cgroup.h
+++ b/tools/perf/util/cgroup.h
@@ -1,12 +1,14 @@
 #ifndef __CGROUP_H__
 #define __CGROUP_H__
 
+#include <linux/atomic.h>
+
 struct option;
 
 struct cgroup_sel {
 	char *name;
 	int fd;
-	int refcnt;
+	atomic_t refcnt;
 };
 
 
diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index b2bb59df6..21b7ff382 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -2,24 +2,27 @@
 #include "util.h"
 #include <stdlib.h>
 #include <stdio.h>
+#include <linux/atomic.h>
 
 struct comm_str {
 	char *str;
 	struct rb_node rb_node;
-	int ref;
+	atomic_t refcnt;
 };
 
 /* Should perhaps be moved to struct machine */
 static struct rb_root comm_str_root;
 
-static void comm_str__get(struct comm_str *cs)
+static struct comm_str *comm_str__get(struct comm_str *cs)
 {
-	cs->ref++;
+	if (cs)
+		atomic_inc(&cs->refcnt);
+	return cs;
 }
 
 static void comm_str__put(struct comm_str *cs)
 {
-	if (!--cs->ref) {
+	if (cs && atomic_dec_and_test(&cs->refcnt)) {
 		rb_erase(&cs->rb_node, &comm_str_root);
 		zfree(&cs->str);
 		free(cs);
@@ -40,6 +43,8 @@ static struct comm_str *comm_str__alloc(const char *str)
 		return NULL;
 	}
 
+	atomic_set(&cs->refcnt, 0);
+
 	return cs;
 }
 
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index c4e55b710..3667e2123 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -5,6 +5,7 @@
 #include <assert.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include "asm/bug.h"
 
 static struct cpu_map *cpu_map__default_new(void)
 {
@@ -22,6 +23,7 @@ static struct cpu_map *cpu_map__default_new(void)
 			cpus->map[i] = i;
 
 		cpus->nr = nr_cpus;
+		atomic_set(&cpus->refcnt, 1);
 	}
 
 	return cpus;
@@ -35,6 +37,7 @@ static struct cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus)
 	if (cpus != NULL) {
 		cpus->nr = nr_cpus;
 		memcpy(cpus->map, tmp_cpus, payload_size);
+		atomic_set(&cpus->refcnt, 1);
 	}
 
 	return cpus;
@@ -194,14 +197,32 @@ struct cpu_map *cpu_map__dummy_new(void)
 	if (cpus != NULL) {
 		cpus->nr = 1;
 		cpus->map[0] = -1;
+		atomic_set(&cpus->refcnt, 1);
 	}
 
 	return cpus;
 }
 
-void cpu_map__delete(struct cpu_map *map)
+static void cpu_map__delete(struct cpu_map *map)
 {
-	free(map);
+	if (map) {
+		WARN_ONCE(atomic_read(&map->refcnt) != 0,
+			  "cpu_map refcnt unbalanced\n");
+		free(map);
+	}
+}
+
+struct cpu_map *cpu_map__get(struct cpu_map *map)
+{
+	if (map)
+		atomic_inc(&map->refcnt);
+	return map;
+}
+
+void cpu_map__put(struct cpu_map *map)
+{
+	if (map && atomic_dec_and_test(&map->refcnt))
+		cpu_map__delete(map);
 }
 
 int cpu_map__get_socket(struct cpu_map *map, int idx)
@@ -263,6 +284,7 @@ static int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
 	/* ensure we process id in increasing order */
 	qsort(c->map, c->nr, sizeof(int), cmp_ids);
 
+	atomic_set(&cpus->refcnt, 1);
 	*res = c;
 	return 0;
 }
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 61a654849..0af9cecb4 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -3,18 +3,19 @@
 
 #include <stdio.h>
 #include <stdbool.h>
+#include <linux/atomic.h>
 
 #include "perf.h"
 #include "util/debug.h"
 
 struct cpu_map {
+	atomic_t refcnt;
 	int nr;
 	int map[];
 };
 
 struct cpu_map *cpu_map__new(const char *cpu_list);
 struct cpu_map *cpu_map__dummy_new(void);
-void cpu_map__delete(struct cpu_map *map);
 struct cpu_map *cpu_map__read(FILE *file);
 size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp);
 int cpu_map__get_socket(struct cpu_map *map, int idx);
@@ -22,6 +23,9 @@ int cpu_map__get_core(struct cpu_map *map, int idx);
 int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp);
 int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep);
 
+struct cpu_map *cpu_map__get(struct cpu_map *map);
+void cpu_map__put(struct cpu_map *map);
+
 static inline int cpu_map__socket(struct cpu_map *sock, int s)
 {
 	if (!sock || s > sock->nr || s < 0)
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index dd17c9a32..5bfc1198a 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -14,6 +14,7 @@
 #include <babeltrace/ctf-writer/event.h>
 #include <babeltrace/ctf-writer/event-types.h>
 #include <babeltrace/ctf-writer/event-fields.h>
+#include <babeltrace/ctf-ir/utils.h>
 #include <babeltrace/ctf/events.h>
 #include <traceevent/event-parse.h>
 #include "asm/bug.h"
@@ -38,12 +39,21 @@ struct evsel_priv {
 	struct bt_ctf_event_class *event_class;
 };
 
+#define MAX_CPUS	4096
+
+struct ctf_stream {
+	struct bt_ctf_stream *stream;
+	int cpu;
+	u32 count;
+};
+
 struct ctf_writer {
 	/* writer primitives */
-	struct bt_ctf_writer		*writer;
-	struct bt_ctf_stream		*stream;
-	struct bt_ctf_stream_class	*stream_class;
-	struct bt_ctf_clock		*clock;
+	struct bt_ctf_writer		 *writer;
+	struct ctf_stream		**stream;
+	int				  stream_cnt;
+	struct bt_ctf_stream_class	 *stream_class;
+	struct bt_ctf_clock		 *clock;
 
 	/* data types */
 	union {
@@ -65,6 +75,9 @@ struct convert {
 
 	u64			events_size;
 	u64			events_count;
+
+	/* Ordered events configured queue size. */
+	u64			queue_size;
 };
 
 static int value_set(struct bt_ctf_field_type *type,
@@ -153,6 +166,43 @@ get_tracepoint_field_type(struct ctf_writer *cw, struct format_field *field)
 		return cw->data.u32;
 }
 
+static unsigned long long adjust_signedness(unsigned long long value_int, int size)
+{
+	unsigned long long value_mask;
+
+	/*
+	 * value_mask = (1 << (size * 8 - 1)) - 1.
+	 * Directly set value_mask for code readers.
+	 */
+	switch (size) {
+	case 1:
+		value_mask = 0x7fULL;
+		break;
+	case 2:
+		value_mask = 0x7fffULL;
+		break;
+	case 4:
+		value_mask = 0x7fffffffULL;
+		break;
+	case 8:
+		/*
+		 * For 64 bit value, return it self. There is no need
+		 * to fill high bit.
+		 */
+		/* Fall through */
+	default:
+		/* BUG! */
+		return value_int;
+	}
+
+	/* If it is a positive value, don't adjust. */
+	if ((value_int & (~0ULL - value_mask)) == 0)
+		return value_int;
+
+	/* Fill upper part of value_int with 1 to make it a negative long long. */
+	return (value_int & value_mask) | ~value_mask;
+}
+
 static int add_tracepoint_field_value(struct ctf_writer *cw,
 				      struct bt_ctf_event_class *event_class,
 				      struct bt_ctf_event *event,
@@ -164,7 +214,6 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 	struct bt_ctf_field *field;
 	const char *name = fmtf->name;
 	void *data = sample->raw_data;
-	unsigned long long value_int;
 	unsigned long flags = fmtf->flags;
 	unsigned int n_items;
 	unsigned int i;
@@ -172,6 +221,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 	unsigned int len;
 	int ret;
 
+	name = fmtf->alias;
 	offset = fmtf->offset;
 	len = fmtf->size;
 	if (flags & FIELD_IS_STRING)
@@ -208,11 +258,6 @@ 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_STRING))
-			value_int = pevent_read_number(
-					fmtf->event->pevent,
-					data + offset + i * len, len);
-
 		if (flags & FIELD_IS_ARRAY)
 			field = bt_ctf_field_array_get_field(array_field, i);
 		else
@@ -226,12 +271,21 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 		if (flags & FIELD_IS_STRING)
 			ret = bt_ctf_field_string_set_value(field,
 					data + offset + i * len);
-		else if (!(flags & FIELD_IS_SIGNED))
-			ret = bt_ctf_field_unsigned_integer_set_value(
-					field, value_int);
-		else
-			ret = bt_ctf_field_signed_integer_set_value(
-					field, value_int);
+		else {
+			unsigned long long value_int;
+
+			value_int = pevent_read_number(
+					fmtf->event->pevent,
+					data + offset + i * len, len);
+
+			if (!(flags & FIELD_IS_SIGNED))
+				ret = bt_ctf_field_unsigned_integer_set_value(
+						field, value_int);
+			else
+				ret = bt_ctf_field_signed_integer_set_value(
+						field, adjust_signedness(value_int, len));
+		}
+
 		if (ret) {
 			pr_err("failed to set file value %s\n", name);
 			goto err_put_field;
@@ -346,12 +400,6 @@ static int add_generic_values(struct ctf_writer *cw,
 			return -1;
 	}
 
-	if (type & PERF_SAMPLE_CPU) {
-		ret = value_set_u32(cw, event, "perf_cpu", sample->cpu);
-		if (ret)
-			return -1;
-	}
-
 	if (type & PERF_SAMPLE_PERIOD) {
 		ret = value_set_u64(cw, event, "perf_period", sample->period);
 		if (ret)
@@ -381,6 +429,129 @@ static int add_generic_values(struct ctf_writer *cw,
 	return 0;
 }
 
+static int ctf_stream__flush(struct ctf_stream *cs)
+{
+	int err = 0;
+
+	if (cs) {
+		err = bt_ctf_stream_flush(cs->stream);
+		if (err)
+			pr_err("CTF stream %d flush failed\n", cs->cpu);
+
+		pr("Flush stream for cpu %d (%u samples)\n",
+		   cs->cpu, cs->count);
+
+		cs->count = 0;
+	}
+
+	return err;
+}
+
+static struct ctf_stream *ctf_stream__create(struct ctf_writer *cw, int cpu)
+{
+	struct ctf_stream *cs;
+	struct bt_ctf_field *pkt_ctx   = NULL;
+	struct bt_ctf_field *cpu_field = NULL;
+	struct bt_ctf_stream *stream   = NULL;
+	int ret;
+
+	cs = zalloc(sizeof(*cs));
+	if (!cs) {
+		pr_err("Failed to allocate ctf stream\n");
+		return NULL;
+	}
+
+	stream = bt_ctf_writer_create_stream(cw->writer, cw->stream_class);
+	if (!stream) {
+		pr_err("Failed to create CTF stream\n");
+		goto out;
+	}
+
+	pkt_ctx = bt_ctf_stream_get_packet_context(stream);
+	if (!pkt_ctx) {
+		pr_err("Failed to obtain packet context\n");
+		goto out;
+	}
+
+	cpu_field = bt_ctf_field_structure_get_field(pkt_ctx, "cpu_id");
+	bt_ctf_field_put(pkt_ctx);
+	if (!cpu_field) {
+		pr_err("Failed to obtain cpu field\n");
+		goto out;
+	}
+
+	ret = bt_ctf_field_unsigned_integer_set_value(cpu_field, (u32) cpu);
+	if (ret) {
+		pr_err("Failed to update CPU number\n");
+		goto out;
+	}
+
+	bt_ctf_field_put(cpu_field);
+
+	cs->cpu    = cpu;
+	cs->stream = stream;
+	return cs;
+
+out:
+	if (cpu_field)
+		bt_ctf_field_put(cpu_field);
+	if (stream)
+		bt_ctf_stream_put(stream);
+
+	free(cs);
+	return NULL;
+}
+
+static void ctf_stream__delete(struct ctf_stream *cs)
+{
+	if (cs) {
+		bt_ctf_stream_put(cs->stream);
+		free(cs);
+	}
+}
+
+static struct ctf_stream *ctf_stream(struct ctf_writer *cw, int cpu)
+{
+	struct ctf_stream *cs = cw->stream[cpu];
+
+	if (!cs) {
+		cs = ctf_stream__create(cw, cpu);
+		cw->stream[cpu] = cs;
+	}
+
+	return cs;
+}
+
+static int get_sample_cpu(struct ctf_writer *cw, struct perf_sample *sample,
+			  struct perf_evsel *evsel)
+{
+	int cpu = 0;
+
+	if (evsel->attr.sample_type & PERF_SAMPLE_CPU)
+		cpu = sample->cpu;
+
+	if (cpu > cw->stream_cnt) {
+		pr_err("Event was recorded for CPU %d, limit is at %d.\n",
+			cpu, cw->stream_cnt);
+		cpu = 0;
+	}
+
+	return cpu;
+}
+
+#define STREAM_FLUSH_COUNT 100000
+
+/*
+ * Currently we have no other way to determine the
+ * time for the stream flush other than keep track
+ * of the number of events and check it against
+ * threshold.
+ */
+static bool is_flush_needed(struct ctf_stream *cs)
+{
+	return cs->count >= STREAM_FLUSH_COUNT;
+}
+
 static int process_sample_event(struct perf_tool *tool,
 				union perf_event *_event __maybe_unused,
 				struct perf_sample *sample,
@@ -390,6 +561,7 @@ static int process_sample_event(struct perf_tool *tool,
 	struct convert *c = container_of(tool, struct convert, tool);
 	struct evsel_priv *priv = evsel->priv;
 	struct ctf_writer *cw = &c->writer;
+	struct ctf_stream *cs;
 	struct bt_ctf_event_class *event_class;
 	struct bt_ctf_event *event;
 	int ret;
@@ -424,9 +596,93 @@ static int process_sample_event(struct perf_tool *tool,
 			return -1;
 	}
 
-	bt_ctf_stream_append_event(cw->stream, event);
+	cs = ctf_stream(cw, get_sample_cpu(cw, sample, evsel));
+	if (cs) {
+		if (is_flush_needed(cs))
+			ctf_stream__flush(cs);
+
+		cs->count++;
+		bt_ctf_stream_append_event(cs->stream, event);
+	}
+
 	bt_ctf_event_put(event);
-	return 0;
+	return cs ? 0 : -1;
+}
+
+/* If dup < 0, add a prefix. Else, add _dupl_X suffix. */
+static char *change_name(char *name, char *orig_name, int dup)
+{
+	char *new_name = NULL;
+	size_t len;
+
+	if (!name)
+		name = orig_name;
+
+	if (dup >= 10)
+		goto out;
+	/*
+	 * Add '_' prefix to potential keywork.  According to
+	 * Mathieu Desnoyers (https://lkml.org/lkml/2015/1/23/652),
+	 * futher CTF spec updating may require us to use '$'.
+	 */
+	if (dup < 0)
+		len = strlen(name) + sizeof("_");
+	else
+		len = strlen(orig_name) + sizeof("_dupl_X");
+
+	new_name = malloc(len);
+	if (!new_name)
+		goto out;
+
+	if (dup < 0)
+		snprintf(new_name, len, "_%s", name);
+	else
+		snprintf(new_name, len, "%s_dupl_%d", orig_name, dup);
+
+out:
+	if (name != orig_name)
+		free(name);
+	return new_name;
+}
+
+static int event_class_add_field(struct bt_ctf_event_class *event_class,
+		struct bt_ctf_field_type *type,
+		struct format_field *field)
+{
+	struct bt_ctf_field_type *t = NULL;
+	char *name;
+	int dup = 1;
+	int ret;
+
+	/* alias was already assigned */
+	if (field->alias != field->name)
+		return bt_ctf_event_class_add_field(event_class, type,
+				(char *)field->alias);
+
+	name = field->name;
+
+	/* If 'name' is a keywork, add prefix. */
+	if (bt_ctf_validate_identifier(name))
+		name = change_name(name, field->name, -1);
+
+	if (!name) {
+		pr_err("Failed to fix invalid identifier.");
+		return -1;
+	}
+	while ((t = bt_ctf_event_class_get_field_by_name(event_class, name))) {
+		bt_ctf_field_type_put(t);
+		name = change_name(name, field->name, dup++);
+		if (!name) {
+			pr_err("Failed to create dup name for '%s'\n", field->name);
+			return -1;
+		}
+	}
+
+	ret = bt_ctf_event_class_add_field(event_class, type, name);
+	if (!ret)
+		field->alias = name;
+
+	return ret;
 }
 
 static int add_tracepoint_fields_types(struct ctf_writer *cw,
@@ -457,14 +713,14 @@ static int add_tracepoint_fields_types(struct ctf_writer *cw,
 		if (flags & FIELD_IS_ARRAY)
 			type = bt_ctf_field_type_array_create(type, field->arraylen);
 
-		ret = bt_ctf_event_class_add_field(event_class, type,
-				field->name);
+		ret = event_class_add_field(event_class, type, field);
 
 		if (flags & FIELD_IS_ARRAY)
 			bt_ctf_field_type_put(type);
 
 		if (ret) {
-			pr_err("Failed to add field '%s\n", field->name);
+			pr_err("Failed to add field '%s': %d\n",
+					field->name, ret);
 			return -1;
 		}
 	}
@@ -508,7 +764,7 @@ static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel,
 	do {								\
 		pr2("  field '%s'\n", n);				\
 		if (bt_ctf_event_class_add_field(cl, t, n)) {		\
-			pr_err("Failed to add field '%s;\n", n);	\
+			pr_err("Failed to add field '%s';\n", n);	\
 			return -1;					\
 		}							\
 	} while (0)
@@ -528,9 +784,6 @@ static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel,
 	if (type & PERF_SAMPLE_STREAM_ID)
 		ADD_FIELD(event_class, cw->data.u64, "perf_stream_id");
 
-	if (type & PERF_SAMPLE_CPU)
-		ADD_FIELD(event_class, cw->data.u32, "perf_cpu");
-
 	if (type & PERF_SAMPLE_PERIOD)
 		ADD_FIELD(event_class, cw->data.u64, "perf_period");
 
@@ -604,6 +857,39 @@ static int setup_events(struct ctf_writer *cw, struct perf_session *session)
 	return 0;
 }
 
+static int setup_streams(struct ctf_writer *cw, struct perf_session *session)
+{
+	struct ctf_stream **stream;
+	struct perf_header *ph = &session->header;
+	int ncpus;
+
+	/*
+	 * Try to get the number of cpus used in the data file,
+	 * if not present fallback to the MAX_CPUS.
+	 */
+	ncpus = ph->env.nr_cpus_avail ?: MAX_CPUS;
+
+	stream = zalloc(sizeof(*stream) * ncpus);
+	if (!stream) {
+		pr_err("Failed to allocate streams.\n");
+		return -ENOMEM;
+	}
+
+	cw->stream     = stream;
+	cw->stream_cnt = ncpus;
+	return 0;
+}
+
+static void free_streams(struct ctf_writer *cw)
+{
+	int cpu;
+
+	for (cpu = 0; cpu < cw->stream_cnt; cpu++)
+		ctf_stream__delete(cw->stream[cpu]);
+
+	free(cw->stream);
+}
+
 static int ctf_writer__setup_env(struct ctf_writer *cw,
 				 struct perf_session *session)
 {
@@ -713,7 +999,7 @@ static void ctf_writer__cleanup(struct ctf_writer *cw)
 	ctf_writer__cleanup_data(cw);
 
 	bt_ctf_clock_put(cw->clock);
-	bt_ctf_stream_put(cw->stream);
+	free_streams(cw);
 	bt_ctf_stream_class_put(cw->stream_class);
 	bt_ctf_writer_put(cw->writer);
 
@@ -725,8 +1011,9 @@ static int ctf_writer__init(struct ctf_writer *cw, const char *path)
 {
 	struct bt_ctf_writer		*writer;
 	struct bt_ctf_stream_class	*stream_class;
-	struct bt_ctf_stream		*stream;
 	struct bt_ctf_clock		*clock;
+	struct bt_ctf_field_type	*pkt_ctx_type;
+	int				ret;
 
 	/* CTF writer */
 	writer = bt_ctf_writer_create(path);
@@ -767,14 +1054,15 @@ static int ctf_writer__init(struct ctf_writer *cw, const char *path)
 	if (ctf_writer__init_data(cw))
 		goto err_cleanup;
 
-	/* CTF stream instance */
-	stream = bt_ctf_writer_create_stream(writer, stream_class);
-	if (!stream) {
-		pr("Failed to create CTF stream.\n");
+	/* Add cpu_id for packet context */
+	pkt_ctx_type = bt_ctf_stream_class_get_packet_context_type(stream_class);
+	if (!pkt_ctx_type)
 		goto err_cleanup;
-	}
 
-	cw->stream = stream;
+	ret = bt_ctf_field_type_structure_add_field(pkt_ctx_type, cw->data.u32, "cpu_id");
+	bt_ctf_field_type_put(pkt_ctx_type);
+	if (ret)
+		goto err_cleanup;
 
 	/* CTF clock writer setup */
 	if (bt_ctf_writer_add_clock(writer, clock)) {
@@ -791,6 +1079,28 @@ err:
 	return -1;
 }
 
+static int ctf_writer__flush_streams(struct ctf_writer *cw)
+{
+	int cpu, ret = 0;
+
+	for (cpu = 0; cpu < cw->stream_cnt && !ret; cpu++)
+		ret = ctf_stream__flush(cw->stream[cpu]);
+
+	return ret;
+}
+
+static int convert__config(const char *var, const char *value, void *cb)
+{
+	struct convert *c = cb;
+
+	if (!strcmp(var, "convert.queue-size")) {
+		c->queue_size = perf_config_u64(var, value);
+		return 0;
+	}
+
+	return perf_default_config(var, value, cb);
+}
+
 int bt_convert__perf2ctf(const char *input, const char *path, bool force)
 {
 	struct perf_session *session;
@@ -817,6 +1127,8 @@ int bt_convert__perf2ctf(const char *input, const char *path, bool force)
 	struct ctf_writer *cw = &c.writer;
 	int err = -1;
 
+	perf_config(convert__config, &c);
+
 	/* CTF writer */
 	if (ctf_writer__init(cw, path))
 		return -1;
@@ -826,6 +1138,11 @@ int bt_convert__perf2ctf(const char *input, const char *path, bool force)
 	if (!session)
 		goto free_writer;
 
+	if (c.queue_size) {
+		ordered_events__set_alloc_size(&session->ordered_events,
+					       c.queue_size);
+	}
+
 	/* CTF writer env/clock setup  */
 	if (ctf_writer__setup_env(cw, session))
 		goto free_session;
@@ -834,9 +1151,14 @@ int bt_convert__perf2ctf(const char *input, const char *path, bool force)
 	if (setup_events(cw, session))
 		goto free_session;
 
+	if (setup_streams(cw, session))
+		goto free_session;
+
 	err = perf_session__process_events(session);
 	if (!err)
-		err = bt_ctf_stream_flush(cw->stream);
+		err = ctf_writer__flush_streams(cw);
+	else
+		pr_err("Error during conversion.\n");
 
 	fprintf(stderr,
 		"[ perf data convert: Converted '%s' into CTF data '%s' ]\n",
@@ -847,11 +1169,15 @@ int bt_convert__perf2ctf(const char *input, const char *path, bool force)
 		(double) c.events_size / 1024.0 / 1024.0,
 		c.events_count);
 
-	/* its all good */
-free_session:
 	perf_session__delete(session);
+	ctf_writer__cleanup(cw);
+
+	return err;
 
+free_session:
+	perf_session__delete(session);
 free_writer:
 	ctf_writer__cleanup(cw);
+	pr_err("Error during conversion setup.\n");
 	return err;
 }
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index bb39a3ffc..1c9689e4c 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -122,6 +122,7 @@ int db_export__machine(struct db_export *dbe, struct machine *machine)
 int db_export__thread(struct db_export *dbe, struct thread *thread,
 		      struct machine *machine, struct comm *comm)
 {
+	struct thread *main_thread;
 	u64 main_thread_db_id = 0;
 	int err;
 
@@ -131,8 +132,6 @@ int db_export__thread(struct db_export *dbe, struct thread *thread,
 	thread->db_id = ++dbe->thread_last_db_id;
 
 	if (thread->pid_ != -1) {
-		struct thread *main_thread;
-
 		if (thread->pid_ == thread->tid) {
 			main_thread = thread;
 		} else {
@@ -144,14 +143,16 @@ int db_export__thread(struct db_export *dbe, struct thread *thread,
 			err = db_export__thread(dbe, main_thread, machine,
 						comm);
 			if (err)
-				return err;
+				goto out_put;
 			if (comm) {
 				err = db_export__comm_thread(dbe, comm, thread);
 				if (err)
-					return err;
+					goto out_put;
 			}
 		}
 		main_thread_db_id = main_thread->db_id;
+		if (main_thread != thread)
+			thread__put(main_thread);
 	}
 
 	if (dbe->export_thread)
@@ -159,6 +160,10 @@ int db_export__thread(struct db_export *dbe, struct thread *thread,
 					  machine);
 
 	return 0;
+
+out_put:
+	thread__put(main_thread);
+	return err;
 }
 
 int db_export__comm(struct db_export *dbe, struct comm *comm,
@@ -229,7 +234,7 @@ int db_export__symbol(struct db_export *dbe, struct symbol *sym,
 static struct thread *get_main_thread(struct machine *machine, struct thread *thread)
 {
 	if (thread->pid_ == thread->tid)
-		return thread;
+		return thread__get(thread);
 
 	if (thread->pid_ == -1)
 		return NULL;
@@ -309,12 +314,12 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
 
 	err = db_export__thread(dbe, thread, al->machine, comm);
 	if (err)
-		return err;
+		goto out_put;
 
 	if (comm) {
 		err = db_export__comm(dbe, comm, main_thread);
 		if (err)
-			return err;
+			goto out_put;
 		es.comm_db_id = comm->db_id;
 	}
 
@@ -322,7 +327,7 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
 
 	err = db_ids_from_al(dbe, al, &es.dso_db_id, &es.sym_db_id, &es.offset);
 	if (err)
-		return err;
+		goto out_put;
 
 	if ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
 	    sample_addr_correlates_sym(&evsel->attr)) {
@@ -332,20 +337,22 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
 		err = db_ids_from_al(dbe, &addr_al, &es.addr_dso_db_id,
 				     &es.addr_sym_db_id, &es.addr_offset);
 		if (err)
-			return err;
+			goto out_put;
 		if (dbe->crp) {
 			err = thread_stack__process(thread, comm, sample, al,
 						    &addr_al, es.db_id,
 						    dbe->crp);
 			if (err)
-				return err;
+				goto out_put;
 		}
 	}
 
 	if (dbe->export_sample)
-		return dbe->export_sample(dbe, &es);
+		err = dbe->export_sample(dbe, &es);
 
-	return 0;
+out_put:
+	thread__put(main_thread);
+	return err;
 }
 
 static struct {
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index fc0ddd579..7c0c08386 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -4,6 +4,7 @@
 #include "symbol.h"
 #include "dso.h"
 #include "machine.h"
+#include "auxtrace.h"
 #include "util.h"
 #include "debug.h"
 
@@ -165,12 +166,28 @@ bool is_supported_compression(const char *ext)
 	return false;
 }
 
-bool is_kernel_module(const char *pathname)
+bool is_kernel_module(const char *pathname, int cpumode)
 {
 	struct kmod_path m;
-
-	if (kmod_path__parse(&m, pathname))
-		return NULL;
+	int mode = cpumode & PERF_RECORD_MISC_CPUMODE_MASK;
+
+	WARN_ONCE(mode != cpumode,
+		  "Internal error: passing unmasked cpumode (%x) to is_kernel_module",
+		  cpumode);
+
+	switch (mode) {
+	case PERF_RECORD_MISC_USER:
+	case PERF_RECORD_MISC_HYPERVISOR:
+	case PERF_RECORD_MISC_GUEST_USER:
+		return false;
+	/* Treat PERF_RECORD_MISC_CPUMODE_UNKNOWN as kernel */
+	default:
+		if (kmod_path__parse(&m, pathname)) {
+			pr_err("Failed to check whether %s is a kernel module or not. Assume it is.",
+					pathname);
+			return true;
+		}
+	}
 
 	return m.kmod;
 }
@@ -214,12 +231,33 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
 {
 	const char *name = strrchr(path, '/');
 	const char *ext  = strrchr(path, '.');
+	bool is_simple_name = false;
 
 	memset(m, 0x0, sizeof(*m));
 	name = name ? name + 1 : path;
 
+	/*
+	 * '.' is also a valid character for module name. For example:
+	 * [aaa.bbb] is a valid module name. '[' should have higher
+	 * priority than '.ko' suffix.
+	 *
+	 * The kernel names are from machine__mmap_name. Such
+	 * name should belong to kernel itself, not kernel module.
+	 */
+	if (name[0] == '[') {
+		is_simple_name = true;
+		if ((strncmp(name, "[kernel.kallsyms]", 17) == 0) ||
+		    (strncmp(name, "[guest.kernel.kallsyms", 22) == 0) ||
+		    (strncmp(name, "[vdso]", 6) == 0) ||
+		    (strncmp(name, "[vsyscall]", 10) == 0)) {
+			m->kmod = false;
+
+		} else
+			m->kmod = true;
+	}
+
 	/* No extension, just return name. */
-	if (ext == NULL) {
+	if ((ext == NULL) || is_simple_name) {
 		if (alloc_name) {
 			m->name = strdup(name);
 			return m->name ? 0 : -ENOMEM;
@@ -264,6 +302,7 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
  */
 static LIST_HEAD(dso__data_open);
 static long dso__data_open_cnt;
+static pthread_mutex_t dso__data_open_lock = PTHREAD_MUTEX_INITIALIZER;
 
 static void dso__list_add(struct dso *dso)
 {
@@ -433,18 +472,12 @@ static void check_data_close(void)
  */
 void dso__data_close(struct dso *dso)
 {
+	pthread_mutex_lock(&dso__data_open_lock);
 	close_dso(dso);
+	pthread_mutex_unlock(&dso__data_open_lock);
 }
 
-/**
- * dso__data_fd - Get dso's data file descriptor
- * @dso: dso object
- * @machine: machine object
- *
- * External interface to find dso's file, open it and
- * returns file descriptor.
- */
-int dso__data_fd(struct dso *dso, struct machine *machine)
+static void try_to_open_dso(struct dso *dso, struct machine *machine)
 {
 	enum dso_binary_type binary_type_data[] = {
 		DSO_BINARY_TYPE__BUILD_ID_CACHE,
@@ -453,11 +486,8 @@ int dso__data_fd(struct dso *dso, struct machine *machine)
 	};
 	int i = 0;
 
-	if (dso->data.status == DSO_DATA_STATUS_ERROR)
-		return -1;
-
 	if (dso->data.fd >= 0)
-		goto out;
+		return;
 
 	if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND) {
 		dso->data.fd = open_dso(dso, machine);
@@ -477,10 +507,38 @@ out:
 		dso->data.status = DSO_DATA_STATUS_OK;
 	else
 		dso->data.status = DSO_DATA_STATUS_ERROR;
+}
+
+/**
+ * dso__data_get_fd - Get dso's data file descriptor
+ * @dso: dso object
+ * @machine: machine object
+ *
+ * External interface to find dso's file, open it and
+ * returns file descriptor.  It should be paired with
+ * dso__data_put_fd() if it returns non-negative value.
+ */
+int dso__data_get_fd(struct dso *dso, struct machine *machine)
+{
+	if (dso->data.status == DSO_DATA_STATUS_ERROR)
+		return -1;
+
+	if (pthread_mutex_lock(&dso__data_open_lock) < 0)
+		return -1;
+
+	try_to_open_dso(dso, machine);
+
+	if (dso->data.fd < 0)
+		pthread_mutex_unlock(&dso__data_open_lock);
 
 	return dso->data.fd;
 }
 
+void dso__data_put_fd(struct dso *dso __maybe_unused)
+{
+	pthread_mutex_unlock(&dso__data_open_lock);
+}
+
 bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by)
 {
 	u32 flag = 1 << by;
@@ -494,10 +552,12 @@ bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by)
 }
 
 static void
-dso_cache__free(struct rb_root *root)
+dso_cache__free(struct dso *dso)
 {
+	struct rb_root *root = &dso->data.cache;
 	struct rb_node *next = rb_first(root);
 
+	pthread_mutex_lock(&dso->lock);
 	while (next) {
 		struct dso_cache *cache;
 
@@ -506,10 +566,12 @@ dso_cache__free(struct rb_root *root)
 		rb_erase(&cache->rb_node, root);
 		free(cache);
 	}
+	pthread_mutex_unlock(&dso->lock);
 }
 
-static struct dso_cache *dso_cache__find(const struct rb_root *root, u64 offset)
+static struct dso_cache *dso_cache__find(struct dso *dso, u64 offset)
 {
+	const struct rb_root *root = &dso->data.cache;
 	struct rb_node * const *p = &root->rb_node;
 	const struct rb_node *parent = NULL;
 	struct dso_cache *cache;
@@ -528,17 +590,20 @@ static struct dso_cache *dso_cache__find(const struct rb_root *root, u64 offset)
 		else
 			return cache;
 	}
+
 	return NULL;
 }
 
-static void
-dso_cache__insert(struct rb_root *root, struct dso_cache *new)
+static struct dso_cache *
+dso_cache__insert(struct dso *dso, struct dso_cache *new)
 {
+	struct rb_root *root = &dso->data.cache;
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
 	struct dso_cache *cache;
 	u64 offset = new->offset;
 
+	pthread_mutex_lock(&dso->lock);
 	while (*p != NULL) {
 		u64 end;
 
@@ -550,10 +615,17 @@ dso_cache__insert(struct rb_root *root, struct dso_cache *new)
 			p = &(*p)->rb_left;
 		else if (offset >= end)
 			p = &(*p)->rb_right;
+		else
+			goto out;
 	}
 
 	rb_link_node(&new->rb_node, parent, p);
 	rb_insert_color(&new->rb_node, root);
+
+	cache = NULL;
+out:
+	pthread_mutex_unlock(&dso->lock);
+	return cache;
 }
 
 static ssize_t
@@ -568,19 +640,33 @@ dso_cache__memcpy(struct dso_cache *cache, u64 offset,
 }
 
 static ssize_t
-dso_cache__read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
+dso_cache__read(struct dso *dso, struct machine *machine,
+		u64 offset, u8 *data, ssize_t size)
 {
 	struct dso_cache *cache;
+	struct dso_cache *old;
 	ssize_t ret;
 
 	do {
 		u64 cache_offset;
 
-		ret = -ENOMEM;
-
 		cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE);
 		if (!cache)
+			return -ENOMEM;
+
+		pthread_mutex_lock(&dso__data_open_lock);
+
+		/*
+		 * dso->data.fd might be closed if other thread opened another
+		 * file (dso) due to open file limit (RLIMIT_NOFILE).
+		 */
+		try_to_open_dso(dso, machine);
+
+		if (dso->data.fd < 0) {
+			ret = -errno;
+			dso->data.status = DSO_DATA_STATUS_ERROR;
 			break;
+		}
 
 		cache_offset = offset & DSO__DATA_CACHE_MASK;
 
@@ -590,11 +676,20 @@ dso_cache__read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 
 		cache->offset = cache_offset;
 		cache->size   = ret;
-		dso_cache__insert(&dso->data.cache, cache);
+	} while (0);
 
-		ret = dso_cache__memcpy(cache, offset, data, size);
+	pthread_mutex_unlock(&dso__data_open_lock);
 
-	} while (0);
+	if (ret > 0) {
+		old = dso_cache__insert(dso, cache);
+		if (old) {
+			/* we lose the race */
+			free(cache);
+			cache = old;
+		}
+
+		ret = dso_cache__memcpy(cache, offset, data, size);
+	}
 
 	if (ret <= 0)
 		free(cache);
@@ -602,16 +697,16 @@ dso_cache__read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 	return ret;
 }
 
-static ssize_t dso_cache_read(struct dso *dso, u64 offset,
-			      u8 *data, ssize_t size)
+static ssize_t dso_cache_read(struct dso *dso, struct machine *machine,
+			      u64 offset, u8 *data, ssize_t size)
 {
 	struct dso_cache *cache;
 
-	cache = dso_cache__find(&dso->data.cache, offset);
+	cache = dso_cache__find(dso, offset);
 	if (cache)
 		return dso_cache__memcpy(cache, offset, data, size);
 	else
-		return dso_cache__read(dso, offset, data, size);
+		return dso_cache__read(dso, machine, offset, data, size);
 }
 
 /*
@@ -619,7 +714,8 @@ static ssize_t dso_cache_read(struct dso *dso, u64 offset,
  * in the rb_tree. Any read to already cached data is served
  * by cached data.
  */
-static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
+static ssize_t cached_read(struct dso *dso, struct machine *machine,
+			   u64 offset, u8 *data, ssize_t size)
 {
 	ssize_t r = 0;
 	u8 *p = data;
@@ -627,7 +723,7 @@ static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 	do {
 		ssize_t ret;
 
-		ret = dso_cache_read(dso, offset, p, size);
+		ret = dso_cache_read(dso, machine, offset, p, size);
 		if (ret < 0)
 			return ret;
 
@@ -647,21 +743,44 @@ static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 	return r;
 }
 
-static int data_file_size(struct dso *dso)
+static int data_file_size(struct dso *dso, struct machine *machine)
 {
+	int ret = 0;
 	struct stat st;
 	char sbuf[STRERR_BUFSIZE];
 
-	if (!dso->data.file_size) {
-		if (fstat(dso->data.fd, &st)) {
-			pr_err("dso mmap failed, fstat: %s\n",
-				strerror_r(errno, sbuf, sizeof(sbuf)));
-			return -1;
-		}
-		dso->data.file_size = st.st_size;
+	if (dso->data.file_size)
+		return 0;
+
+	if (dso->data.status == DSO_DATA_STATUS_ERROR)
+		return -1;
+
+	pthread_mutex_lock(&dso__data_open_lock);
+
+	/*
+	 * dso->data.fd might be closed if other thread opened another
+	 * file (dso) due to open file limit (RLIMIT_NOFILE).
+	 */
+	try_to_open_dso(dso, machine);
+
+	if (dso->data.fd < 0) {
+		ret = -errno;
+		dso->data.status = DSO_DATA_STATUS_ERROR;
+		goto out;
 	}
 
-	return 0;
+	if (fstat(dso->data.fd, &st) < 0) {
+		ret = -errno;
+		pr_err("dso cache fstat failed: %s\n",
+		       strerror_r(errno, sbuf, sizeof(sbuf)));
+		dso->data.status = DSO_DATA_STATUS_ERROR;
+		goto out;
+	}
+	dso->data.file_size = st.st_size;
+
+out:
+	pthread_mutex_unlock(&dso__data_open_lock);
+	return ret;
 }
 
 /**
@@ -673,23 +792,17 @@ static int data_file_size(struct dso *dso)
  */
 off_t dso__data_size(struct dso *dso, struct machine *machine)
 {
-	int fd;
-
-	fd = dso__data_fd(dso, machine);
-	if (fd < 0)
-		return fd;
-
-	if (data_file_size(dso))
+	if (data_file_size(dso, machine))
 		return -1;
 
 	/* For now just estimate dso data size is close to file size */
 	return dso->data.file_size;
 }
 
-static ssize_t data_read_offset(struct dso *dso, u64 offset,
-				u8 *data, ssize_t size)
+static ssize_t data_read_offset(struct dso *dso, struct machine *machine,
+				u64 offset, u8 *data, ssize_t size)
 {
-	if (data_file_size(dso))
+	if (data_file_size(dso, machine))
 		return -1;
 
 	/* Check the offset sanity. */
@@ -699,7 +812,7 @@ static ssize_t data_read_offset(struct dso *dso, u64 offset,
 	if (offset + size < offset)
 		return -1;
 
-	return cached_read(dso, offset, data, size);
+	return cached_read(dso, machine, offset, data, size);
 }
 
 /**
@@ -716,10 +829,10 @@ static ssize_t data_read_offset(struct dso *dso, u64 offset,
 ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
 			      u64 offset, u8 *data, ssize_t size)
 {
-	if (dso__data_fd(dso, machine) < 0)
+	if (dso->data.status == DSO_DATA_STATUS_ERROR)
 		return -1;
 
-	return data_read_offset(dso, offset, data, size);
+	return data_read_offset(dso, machine, offset, data, size);
 }
 
 /**
@@ -751,13 +864,13 @@ struct map *dso__new_map(const char *name)
 	return map;
 }
 
-struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
-		    const char *short_name, int dso_type)
+struct dso *machine__findnew_kernel(struct machine *machine, const char *name,
+				    const char *short_name, int dso_type)
 {
 	/*
 	 * The kernel dso could be created by build_id processing.
 	 */
-	struct dso *dso = __dsos__findnew(&machine->kernel_dsos, name);
+	struct dso *dso = machine__findnew_dso(machine, name);
 
 	/*
 	 * We need to run this in all cases, since during the build_id
@@ -776,8 +889,8 @@ struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
  * Either one of the dso or name parameter must be non-NULL or the
  * function will not work.
  */
-static struct dso *dso__findlink_by_longname(struct rb_root *root,
-					     struct dso *dso, const char *name)
+static struct dso *__dso__findlink_by_longname(struct rb_root *root,
+					       struct dso *dso, const char *name)
 {
 	struct rb_node **p = &root->rb_node;
 	struct rb_node  *parent = NULL;
@@ -824,10 +937,10 @@ static struct dso *dso__findlink_by_longname(struct rb_root *root,
 	return NULL;
 }
 
-static inline struct dso *
-dso__find_by_longname(const struct rb_root *root, const char *name)
+static inline struct dso *__dso__find_by_longname(struct rb_root *root,
+						  const char *name)
 {
-	return dso__findlink_by_longname((struct rb_root *)root, NULL, name);
+	return __dso__findlink_by_longname(root, NULL, name);
 }
 
 void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated)
@@ -935,6 +1048,8 @@ struct dso *dso__new(const char *name)
 		RB_CLEAR_NODE(&dso->rb_node);
 		INIT_LIST_HEAD(&dso->node);
 		INIT_LIST_HEAD(&dso->data.open_entry);
+		pthread_mutex_init(&dso->lock, NULL);
+		atomic_set(&dso->refcnt, 1);
 	}
 
 	return dso;
@@ -961,12 +1076,27 @@ void dso__delete(struct dso *dso)
 	}
 
 	dso__data_close(dso);
-	dso_cache__free(&dso->data.cache);
+	auxtrace_cache__free(dso->auxtrace_cache);
+	dso_cache__free(dso);
 	dso__free_a2l(dso);
 	zfree(&dso->symsrc_filename);
+	pthread_mutex_destroy(&dso->lock);
 	free(dso);
 }
 
+struct dso *dso__get(struct dso *dso)
+{
+	if (dso)
+		atomic_inc(&dso->refcnt);
+	return dso;
+}
+
+void dso__put(struct dso *dso)
+{
+	if (dso && atomic_dec_and_test(&dso->refcnt))
+		dso__delete(dso);
+}
+
 void dso__set_build_id(struct dso *dso, void *build_id)
 {
 	memcpy(dso->build_id, build_id, sizeof(dso->build_id));
@@ -1033,14 +1163,41 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
 	return have_build_id;
 }
 
-void dsos__add(struct dsos *dsos, struct dso *dso)
+void __dsos__add(struct dsos *dsos, struct dso *dso)
 {
 	list_add_tail(&dso->node, &dsos->head);
-	dso__findlink_by_longname(&dsos->root, dso, NULL);
+	__dso__findlink_by_longname(&dsos->root, dso, NULL);
+	/*
+	 * It is now in the linked list, grab a reference, then garbage collect
+	 * this when needing memory, by looking at LRU dso instances in the
+	 * list with atomic_read(&dso->refcnt) == 1, i.e. no references
+	 * anywhere besides the one for the list, do, under a lock for the
+	 * list: remove it from the list, then a dso__put(), that probably will
+	 * be the last and will then call dso__delete(), end of life.
+	 *
+	 * That, or at the end of the 'struct machine' lifetime, when all
+	 * 'struct dso' instances will be removed from the list, in
+	 * dsos__exit(), if they have no other reference from some other data
+	 * structure.
+	 *
+	 * E.g.: after processing a 'perf.data' file and storing references
+	 * to objects instantiated while processing events, we will have
+	 * references to the 'thread', 'map', 'dso' structs all from 'struct
+	 * hist_entry' instances, but we may not need anything not referenced,
+	 * so we might as well call machines__exit()/machines__delete() and
+	 * garbage collect it.
+	 */
+	dso__get(dso);
+}
+
+void dsos__add(struct dsos *dsos, struct dso *dso)
+{
+	pthread_rwlock_wrlock(&dsos->lock);
+	__dsos__add(dsos, dso);
+	pthread_rwlock_unlock(&dsos->lock);
 }
 
-struct dso *dsos__find(const struct dsos *dsos, const char *name,
-		       bool cmp_short)
+struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
 {
 	struct dso *pos;
 
@@ -1050,15 +1207,24 @@ struct dso *dsos__find(const struct dsos *dsos, const char *name,
 				return pos;
 		return NULL;
 	}
-	return dso__find_by_longname(&dsos->root, name);
+	return __dso__find_by_longname(&dsos->root, name);
+}
+
+struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
+{
+	struct dso *dso;
+	pthread_rwlock_rdlock(&dsos->lock);
+	dso = __dsos__find(dsos, name, cmp_short);
+	pthread_rwlock_unlock(&dsos->lock);
+	return dso;
 }
 
-struct dso *dsos__addnew(struct dsos *dsos, const char *name)
+struct dso *__dsos__addnew(struct dsos *dsos, const char *name)
 {
 	struct dso *dso = dso__new(name);
 
 	if (dso != NULL) {
-		dsos__add(dsos, dso);
+		__dsos__add(dsos, dso);
 		dso__set_basename(dso);
 	}
 	return dso;
@@ -1066,9 +1232,18 @@ struct dso *dsos__addnew(struct dsos *dsos, const char *name)
 
 struct dso *__dsos__findnew(struct dsos *dsos, const char *name)
 {
-	struct dso *dso = dsos__find(dsos, name, false);
+	struct dso *dso = __dsos__find(dsos, name, false);
 
-	return dso ? dso : dsos__addnew(dsos, name);
+	return dso ? dso : __dsos__addnew(dsos, name);
+}
+
+struct dso *dsos__findnew(struct dsos *dsos, const char *name)
+{
+	struct dso *dso;
+	pthread_rwlock_wrlock(&dsos->lock);
+	dso = dso__get(__dsos__findnew(dsos, name));
+	pthread_rwlock_unlock(&dsos->lock);
+	return dso;
 }
 
 size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
@@ -1130,12 +1305,15 @@ size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp)
 enum dso_type dso__type(struct dso *dso, struct machine *machine)
 {
 	int fd;
+	enum dso_type type = DSO__TYPE_UNKNOWN;
 
-	fd = dso__data_fd(dso, machine);
-	if (fd < 0)
-		return DSO__TYPE_UNKNOWN;
+	fd = dso__data_get_fd(dso, machine);
+	if (fd >= 0) {
+		type = dso__type_fd(fd);
+		dso__data_put_fd(dso);
+	}
 
-	return dso__type_fd(fd);
+	return type;
 }
 
 int dso__strerror_load(struct dso *dso, char *buf, size_t buflen)
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index e0901b4ed..2fe98bb0e 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -1,9 +1,11 @@
 #ifndef __PERF_DSO
 #define __PERF_DSO
 
+#include <linux/atomic.h>
 #include <linux/types.h>
 #include <linux/rbtree.h>
 #include <stdbool.h>
+#include <pthread.h>
 #include <linux/types.h>
 #include <linux/bitops.h>
 #include "map.h"
@@ -124,9 +126,13 @@ struct dso_cache {
 struct dsos {
 	struct list_head head;
 	struct rb_root	 root;	/* rbtree root sorted by long name */
+	pthread_rwlock_t lock;
 };
 
+struct auxtrace_cache;
+
 struct dso {
+	pthread_mutex_t	 lock;
 	struct list_head node;
 	struct rb_node	 rb_node;	/* rbtree node sorted by long name */
 	struct rb_root	 symbols[MAP__NR_TYPES];
@@ -156,6 +162,7 @@ struct dso {
 	u16		 long_name_len;
 	u16		 short_name_len;
 	void		*dwfl;			/* DWARF debug info */
+	struct auxtrace_cache *auxtrace_cache;
 
 	/* dso data file */
 	struct {
@@ -173,7 +180,7 @@ struct dso {
 		void	 *priv;
 		u64	 db_id;
 	};
-
+	atomic_t	 refcnt;
 	char		 name[0];
 };
 
@@ -200,6 +207,17 @@ void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated);
 
 int dso__name_len(const struct dso *dso);
 
+struct dso *dso__get(struct dso *dso);
+void dso__put(struct dso *dso);
+
+static inline void __dso__zput(struct dso **dso)
+{
+	dso__put(*dso);
+	*dso = NULL;
+}
+
+#define dso__zput(dso) __dso__zput(&dso)
+
 bool dso__loaded(const struct dso *dso, enum map_type type);
 
 bool dso__sorted_by_name(const struct dso *dso, enum map_type type);
@@ -216,7 +234,7 @@ char dso__symtab_origin(const struct dso *dso);
 int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type,
 				   char *root_dir, char *filename, size_t size);
 bool is_supported_compression(const char *ext);
-bool is_kernel_module(const char *pathname);
+bool is_kernel_module(const char *pathname, int cpumode);
 bool decompress_to_file(const char *ext, const char *filename, int output_fd);
 bool dso__needs_decompress(struct dso *dso);
 
@@ -236,7 +254,8 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
 
 /*
  * The dso__data_* external interface provides following functions:
- *   dso__data_fd
+ *   dso__data_get_fd
+ *   dso__data_put_fd
  *   dso__data_close
  *   dso__data_size
  *   dso__data_read_offset
@@ -253,8 +272,11 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
  * The current usage of the dso__data_* interface is as follows:
  *
  * Get DSO's fd:
- *   int fd = dso__data_fd(dso, machine);
- *   USE 'fd' SOMEHOW
+ *   int fd = dso__data_get_fd(dso, machine);
+ *   if (fd >= 0) {
+ *       USE 'fd' SOMEHOW
+ *       dso__data_put_fd(dso);
+ *   }
  *
  * Read DSO's data:
  *   n = dso__data_read_offset(dso_0, &machine, 0, buf, BUFSIZE);
@@ -273,7 +295,8 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
  *
  * TODO
 */
-int dso__data_fd(struct dso *dso, struct machine *machine);
+int dso__data_get_fd(struct dso *dso, struct machine *machine);
+void dso__data_put_fd(struct dso *dso __maybe_unused);
 void dso__data_close(struct dso *dso);
 
 off_t dso__data_size(struct dso *dso, struct machine *machine);
@@ -285,14 +308,16 @@ ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
 bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by);
 
 struct map *dso__new_map(const char *name);
-struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
-				const char *short_name, int dso_type);
+struct dso *machine__findnew_kernel(struct machine *machine, const char *name,
+				    const char *short_name, int dso_type);
 
+void __dsos__add(struct dsos *dsos, struct dso *dso);
 void dsos__add(struct dsos *dsos, struct dso *dso);
-struct dso *dsos__addnew(struct dsos *dsos, const char *name);
-struct dso *dsos__find(const struct dsos *dsos, const char *name,
-		       bool cmp_short);
+struct dso *__dsos__addnew(struct dsos *dsos, const char *name);
+struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short);
+struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short);
 struct dso *__dsos__findnew(struct dsos *dsos, const char *name);
+struct dso *dsos__findnew(struct dsos *dsos, const char *name);
 bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
 
 size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index c34e02402..57f3ef41c 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -139,11 +139,27 @@ int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr,
 bool die_compare_name(Dwarf_Die *dw_die, const char *tname)
 {
 	const char *name;
+
 	name = dwarf_diename(dw_die);
 	return name ? (strcmp(tname, name) == 0) : false;
 }
 
 /**
+ * die_match_name - Match diename and glob
+ * @dw_die: a DIE
+ * @glob: a string of target glob pattern
+ *
+ * Glob matching the name of @dw_die and @glob. Return false if matching fail.
+ */
+bool die_match_name(Dwarf_Die *dw_die, const char *glob)
+{
+	const char *name;
+
+	name = dwarf_diename(dw_die);
+	return name ? strglobmatch(name, glob) : false;
+}
+
+/**
  * die_get_call_lineno - Get callsite line number of inline-function instance
  * @in_die: a DIE of an inlined function instance
  *
@@ -417,6 +433,43 @@ struct __addr_die_search_param {
 	Dwarf_Die	*die_mem;
 };
 
+static int __die_search_func_tail_cb(Dwarf_Die *fn_die, void *data)
+{
+	struct __addr_die_search_param *ad = data;
+	Dwarf_Addr addr = 0;
+
+	if (dwarf_tag(fn_die) == DW_TAG_subprogram &&
+	    !dwarf_highpc(fn_die, &addr) &&
+	    addr == ad->addr) {
+		memcpy(ad->die_mem, fn_die, sizeof(Dwarf_Die));
+		return DWARF_CB_ABORT;
+	}
+	return DWARF_CB_OK;
+}
+
+/**
+ * die_find_tailfunc - Search for a non-inlined function with tail call at
+ * given address
+ * @cu_die: a CU DIE which including @addr
+ * @addr: target address
+ * @die_mem: a buffer for result DIE
+ *
+ * Search for a non-inlined function DIE with tail call at @addr. Stores the
+ * DIE to @die_mem and returns it if found. Returns NULL if failed.
+ */
+Dwarf_Die *die_find_tailfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
+				    Dwarf_Die *die_mem)
+{
+	struct __addr_die_search_param ad;
+	ad.addr = addr;
+	ad.die_mem = die_mem;
+	/* dwarf_getscopes can't find subprogram. */
+	if (!dwarf_getfuncs(cu_die, __die_search_func_tail_cb, &ad, 0))
+		return NULL;
+	else
+		return die_mem;
+}
+
 /* die_find callback for non-inlined function search */
 static int __die_search_func_cb(Dwarf_Die *fn_die, void *data)
 {
@@ -832,19 +885,17 @@ Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name,
 /**
  * die_get_typename - Get the name of given variable DIE
  * @vr_die: a variable DIE
- * @buf: a buffer for result type name
- * @len: a max-length of @buf
+ * @buf: a strbuf for result type name
  *
- * Get the name of @vr_die and stores it to @buf. Return the actual length
- * of type name if succeeded. Return -E2BIG if @len is not enough long, and
- * Return -ENOENT if failed to find type name.
+ * Get the name of @vr_die and stores it to @buf. Return 0 if succeeded.
+ * and Return -ENOENT if failed to find type name.
  * Note that the result will stores typedef name if possible, and stores
  * "*(function_type)" if the type is a function pointer.
  */
-int die_get_typename(Dwarf_Die *vr_die, char *buf, int len)
+int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf)
 {
 	Dwarf_Die type;
-	int tag, ret, ret2;
+	int tag, ret;
 	const char *tmp = "";
 
 	if (__die_get_real_type(vr_die, &type) == NULL)
@@ -855,8 +906,8 @@ int die_get_typename(Dwarf_Die *vr_die, char *buf, int len)
 		tmp = "*";
 	else if (tag == DW_TAG_subroutine_type) {
 		/* Function pointer */
-		ret = snprintf(buf, len, "(function_type)");
-		return (ret >= len) ? -E2BIG : ret;
+		strbuf_addf(buf, "(function_type)");
+		return 0;
 	} else {
 		if (!dwarf_diename(&type))
 			return -ENOENT;
@@ -867,39 +918,156 @@ int die_get_typename(Dwarf_Die *vr_die, char *buf, int len)
 		else if (tag == DW_TAG_enumeration_type)
 			tmp = "enum ";
 		/* Write a base name */
-		ret = snprintf(buf, len, "%s%s", tmp, dwarf_diename(&type));
-		return (ret >= len) ? -E2BIG : ret;
-	}
-	ret = die_get_typename(&type, buf, len);
-	if (ret > 0) {
-		ret2 = snprintf(buf + ret, len - ret, "%s", tmp);
-		ret = (ret2 >= len - ret) ? -E2BIG : ret2 + ret;
+		strbuf_addf(buf, "%s%s", tmp, dwarf_diename(&type));
+		return 0;
 	}
+	ret = die_get_typename(&type, buf);
+	if (ret == 0)
+		strbuf_addf(buf, "%s", tmp);
+
 	return ret;
 }
 
 /**
  * die_get_varname - Get the name and type of given variable DIE
  * @vr_die: a variable DIE
- * @buf: a buffer for type and variable name
- * @len: the max-length of @buf
+ * @buf: a strbuf for type and variable name
  *
  * Get the name and type of @vr_die and stores it in @buf as "type\tname".
  */
-int die_get_varname(Dwarf_Die *vr_die, char *buf, int len)
+int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf)
 {
-	int ret, ret2;
+	int ret;
 
-	ret = die_get_typename(vr_die, buf, len);
+	ret = die_get_typename(vr_die, buf);
 	if (ret < 0) {
 		pr_debug("Failed to get type, make it unknown.\n");
-		ret = snprintf(buf, len, "(unknown_type)");
+		strbuf_addf(buf, "(unknown_type)");
 	}
-	if (ret > 0) {
-		ret2 = snprintf(buf + ret, len - ret, "\t%s",
-				dwarf_diename(vr_die));
-		ret = (ret2 >= len - ret) ? -E2BIG : ret2 + ret;
+
+	strbuf_addf(buf, "\t%s", dwarf_diename(vr_die));
+
+	return 0;
+}
+
+/**
+ * die_get_var_innermost_scope - Get innermost scope range of given variable DIE
+ * @sp_die: a subprogram DIE
+ * @vr_die: a variable DIE
+ * @buf: a strbuf for variable byte offset range
+ *
+ * Get the innermost scope range of @vr_die and stores it in @buf as
+ * "@<function_name+[NN-NN,NN-NN]>".
+ */
+static int die_get_var_innermost_scope(Dwarf_Die *sp_die, Dwarf_Die *vr_die,
+				struct strbuf *buf)
+{
+	Dwarf_Die *scopes;
+	int count;
+	size_t offset = 0;
+	Dwarf_Addr base;
+	Dwarf_Addr start, end;
+	Dwarf_Addr entry;
+	int ret;
+	bool first = true;
+	const char *name;
+
+	ret = dwarf_entrypc(sp_die, &entry);
+	if (ret)
+		return ret;
+
+	name = dwarf_diename(sp_die);
+	if (!name)
+		return -ENOENT;
+
+	count = dwarf_getscopes_die(vr_die, &scopes);
+
+	/* (*SCOPES)[1] is the DIE for the scope containing that scope */
+	if (count <= 1) {
+		ret = -EINVAL;
+		goto out;
 	}
+
+	while ((offset = dwarf_ranges(&scopes[1], offset, &base,
+				&start, &end)) > 0) {
+		start -= entry;
+		end -= entry;
+
+		if (first) {
+			strbuf_addf(buf, "@<%s+[%" PRIu64 "-%" PRIu64,
+				name, start, end);
+			first = false;
+		} else {
+			strbuf_addf(buf, ",%" PRIu64 "-%" PRIu64,
+				start, end);
+		}
+	}
+
+	if (!first)
+		strbuf_addf(buf, "]>");
+
+out:
+	free(scopes);
 	return ret;
 }
 
+/**
+ * die_get_var_range - Get byte offset range of given variable DIE
+ * @sp_die: a subprogram DIE
+ * @vr_die: a variable DIE
+ * @buf: a strbuf for type and variable name and byte offset range
+ *
+ * Get the byte offset range of @vr_die and stores it in @buf as
+ * "@<function_name+[NN-NN,NN-NN]>".
+ */
+int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf)
+{
+	int ret = 0;
+	Dwarf_Addr base;
+	Dwarf_Addr start, end;
+	Dwarf_Addr entry;
+	Dwarf_Op *op;
+	size_t nops;
+	size_t offset = 0;
+	Dwarf_Attribute attr;
+	bool first = true;
+	const char *name;
+
+	ret = dwarf_entrypc(sp_die, &entry);
+	if (ret)
+		return ret;
+
+	name = dwarf_diename(sp_die);
+	if (!name)
+		return -ENOENT;
+
+	if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL)
+		return -EINVAL;
+
+	while ((offset = dwarf_getlocations(
+				&attr, offset, &base,
+				&start, &end, &op, &nops)) > 0) {
+		if (start == 0) {
+			/* Single Location Descriptions */
+			ret = die_get_var_innermost_scope(sp_die, vr_die, buf);
+			return ret;
+		}
+
+		/* Location Lists */
+		start -= entry;
+		end -= entry;
+		if (first) {
+			strbuf_addf(buf, "@<%s+[%" PRIu64 "-%" PRIu64,
+				name, start, end);
+			first = false;
+		} else {
+			strbuf_addf(buf, ",%" PRIu64 "-%" PRIu64,
+				start, end);
+		}
+	}
+
+	if (!first)
+		strbuf_addf(buf, "]>");
+
+	return ret;
+}
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index af7dbcd5f..c42ec366f 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -47,6 +47,9 @@ extern bool die_is_func_instance(Dwarf_Die *dw_die);
 /* Compare diename and tname */
 extern bool die_compare_name(Dwarf_Die *dw_die, const char *tname);
 
+/* Matching diename with glob pattern */
+extern bool die_match_name(Dwarf_Die *dw_die, const char *glob);
+
 /* Get callsite line number of inline-function instance */
 extern int die_get_call_lineno(Dwarf_Die *in_die);
 
@@ -82,6 +85,10 @@ extern Dwarf_Die *die_find_child(Dwarf_Die *rt_die,
 extern Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
 				    Dwarf_Die *die_mem);
 
+/* Search a non-inlined function with tail call at given address */
+Dwarf_Die *die_find_tailfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
+				    Dwarf_Die *die_mem);
+
 /* Search the top inlined function including given address */
 extern Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
 					  Dwarf_Die *die_mem);
@@ -114,8 +121,10 @@ extern Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name,
 				  Dwarf_Die *die_mem);
 
 /* Get the name of given variable DIE */
-extern int die_get_typename(Dwarf_Die *vr_die, char *buf, int len);
+extern int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf);
 
 /* Get the name and type of given variable DIE, stored as "type\tname" */
-extern int die_get_varname(Dwarf_Die *vr_die, char *buf, int len);
+extern int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf);
+extern int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die,
+			struct strbuf *buf);
 #endif
diff --git a/tools/perf/util/environment.c b/tools/perf/util/environment.c
index 275b0ee34..740512369 100644
--- a/tools/perf/util/environment.c
+++ b/tools/perf/util/environment.c
@@ -5,5 +5,4 @@
  */
 #include "cache.h"
 
-const char *pager_program;
 int pager_use_color = 1;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index ff866c4d2..67a977e5d 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -23,12 +23,18 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_FORK]			= "FORK",
 	[PERF_RECORD_READ]			= "READ",
 	[PERF_RECORD_SAMPLE]			= "SAMPLE",
+	[PERF_RECORD_AUX]			= "AUX",
+	[PERF_RECORD_ITRACE_START]		= "ITRACE_START",
+	[PERF_RECORD_LOST_SAMPLES]		= "LOST_SAMPLES",
 	[PERF_RECORD_HEADER_ATTR]		= "ATTR",
 	[PERF_RECORD_HEADER_EVENT_TYPE]		= "EVENT_TYPE",
 	[PERF_RECORD_HEADER_TRACING_DATA]	= "TRACING_DATA",
 	[PERF_RECORD_HEADER_BUILD_ID]		= "BUILD_ID",
 	[PERF_RECORD_FINISHED_ROUND]		= "FINISHED_ROUND",
 	[PERF_RECORD_ID_INDEX]			= "ID_INDEX",
+	[PERF_RECORD_AUXTRACE_INFO]		= "AUXTRACE_INFO",
+	[PERF_RECORD_AUXTRACE]			= "AUXTRACE",
+	[PERF_RECORD_AUXTRACE_ERROR]		= "AUXTRACE_ERROR",
 };
 
 const char *perf_event__name(unsigned int id)
@@ -212,10 +218,14 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 				       pid_t pid, pid_t tgid,
 				       perf_event__handler_t process,
 				       struct machine *machine,
-				       bool mmap_data)
+				       bool mmap_data,
+				       unsigned int proc_map_timeout)
 {
 	char filename[PATH_MAX];
 	FILE *fp;
+	unsigned long long t;
+	bool truncation = false;
+	unsigned long long timeout = proc_map_timeout * 1000000ULL;
 	int rc = 0;
 
 	if (machine__is_default_guest(machine))
@@ -234,6 +244,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 	}
 
 	event->header.type = PERF_RECORD_MMAP2;
+	t = rdclock();
 
 	while (1) {
 		char bf[BUFSIZ];
@@ -247,6 +258,15 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		if (fgets(bf, sizeof(bf), fp) == NULL)
 			break;
 
+		if ((rdclock() - t) > timeout) {
+			pr_warning("Reading %s time out. "
+				   "You may want to increase "
+				   "the time limit by --proc-map-timeout\n",
+				   filename);
+			truncation = true;
+			goto out;
+		}
+
 		/* ensure null termination since stack will be reused. */
 		strcpy(execname, "");
 
@@ -295,6 +315,10 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 			event->header.misc |= PERF_RECORD_MISC_MMAP_DATA;
 		}
 
+out:
+		if (truncation)
+			event->header.misc |= PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT;
+
 		if (!strcmp(execname, ""))
 			strcpy(execname, anonstr);
 
@@ -313,6 +337,9 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 			rc = -1;
 			break;
 		}
+
+		if (truncation)
+			break;
 	}
 
 	fclose(fp);
@@ -324,8 +351,9 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
 				   struct machine *machine)
 {
 	int rc = 0;
-	struct rb_node *nd;
+	struct map *pos;
 	struct map_groups *kmaps = &machine->kmaps;
+	struct maps *maps = &kmaps->maps[MAP__FUNCTION];
 	union perf_event *event = zalloc((sizeof(event->mmap) +
 					  machine->id_hdr_size));
 	if (event == NULL) {
@@ -345,10 +373,8 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
 	else
 		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
 
-	for (nd = rb_first(&kmaps->maps[MAP__FUNCTION]);
-	     nd; nd = rb_next(nd)) {
+	for (pos = maps__first(maps); pos; pos = map__next(pos)) {
 		size_t size;
-		struct map *pos = rb_entry(nd, struct map, rb_node);
 
 		if (pos->dso->kernel)
 			continue;
@@ -381,7 +407,9 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 				      pid_t pid, int full,
 					  perf_event__handler_t process,
 				      struct perf_tool *tool,
-				      struct machine *machine, bool mmap_data)
+				      struct machine *machine,
+				      bool mmap_data,
+				      unsigned int proc_map_timeout)
 {
 	char filename[PATH_MAX];
 	DIR *tasks;
@@ -398,7 +426,8 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 			return -1;
 
 		return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
-							  process, machine, mmap_data);
+							  process, machine, mmap_data,
+							  proc_map_timeout);
 	}
 
 	if (machine__is_default_guest(machine))
@@ -439,7 +468,7 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 		if (_pid == pid) {
 			/* process the parent's maps too */
 			rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
-						process, machine, mmap_data);
+						process, machine, mmap_data, proc_map_timeout);
 			if (rc)
 				break;
 		}
@@ -453,7 +482,8 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 				      struct thread_map *threads,
 				      perf_event__handler_t process,
 				      struct machine *machine,
-				      bool mmap_data)
+				      bool mmap_data,
+				      unsigned int proc_map_timeout)
 {
 	union perf_event *comm_event, *mmap_event, *fork_event;
 	int err = -1, thread, j;
@@ -474,9 +504,9 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 	for (thread = 0; thread < threads->nr; ++thread) {
 		if (__event__synthesize_thread(comm_event, mmap_event,
 					       fork_event,
-					       threads->map[thread], 0,
+					       thread_map__pid(threads, thread), 0,
 					       process, tool, machine,
-					       mmap_data)) {
+					       mmap_data, proc_map_timeout)) {
 			err = -1;
 			break;
 		}
@@ -485,12 +515,12 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 		 * comm.pid is set to thread group id by
 		 * perf_event__synthesize_comm
 		 */
-		if ((int) comm_event->comm.pid != threads->map[thread]) {
+		if ((int) comm_event->comm.pid != thread_map__pid(threads, thread)) {
 			bool need_leader = true;
 
 			/* is thread group leader in thread_map? */
 			for (j = 0; j < threads->nr; ++j) {
-				if ((int) comm_event->comm.pid == threads->map[j]) {
+				if ((int) comm_event->comm.pid == thread_map__pid(threads, j)) {
 					need_leader = false;
 					break;
 				}
@@ -502,7 +532,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 						       fork_event,
 						       comm_event->comm.pid, 0,
 						       process, tool, machine,
-						       mmap_data)) {
+						       mmap_data, proc_map_timeout)) {
 				err = -1;
 				break;
 			}
@@ -519,7 +549,9 @@ out:
 
 int perf_event__synthesize_threads(struct perf_tool *tool,
 				   perf_event__handler_t process,
-				   struct machine *machine, bool mmap_data)
+				   struct machine *machine,
+				   bool mmap_data,
+				   unsigned int proc_map_timeout)
 {
 	DIR *proc;
 	char proc_path[PATH_MAX];
@@ -559,7 +591,8 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
  		 * one thread couldn't be synthesized.
  		 */
 		__event__synthesize_thread(comm_event, mmap_event, fork_event, pid,
-					   1, process, tool, machine, mmap_data);
+					   1, process, tool, machine, mmap_data,
+					   proc_map_timeout);
 	}
 
 	err = 0;
@@ -692,6 +725,30 @@ int perf_event__process_lost(struct perf_tool *tool __maybe_unused,
 	return machine__process_lost_event(machine, event, sample);
 }
 
+int perf_event__process_aux(struct perf_tool *tool __maybe_unused,
+			    union perf_event *event,
+			    struct perf_sample *sample __maybe_unused,
+			    struct machine *machine)
+{
+	return machine__process_aux_event(machine, event);
+}
+
+int perf_event__process_itrace_start(struct perf_tool *tool __maybe_unused,
+				     union perf_event *event,
+				     struct perf_sample *sample __maybe_unused,
+				     struct machine *machine)
+{
+	return machine__process_itrace_start_event(machine, event);
+}
+
+int perf_event__process_lost_samples(struct perf_tool *tool __maybe_unused,
+				     union perf_event *event,
+				     struct perf_sample *sample,
+				     struct machine *machine)
+{
+	return machine__process_lost_samples_event(machine, event, sample);
+}
+
 size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
 {
 	return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %c %s\n",
@@ -755,6 +812,21 @@ int perf_event__process_exit(struct perf_tool *tool __maybe_unused,
 	return machine__process_exit_event(machine, event, sample);
 }
 
+size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp)
+{
+	return fprintf(fp, " offset: %#"PRIx64" size: %#"PRIx64" flags: %#"PRIx64" [%s%s]\n",
+		       event->aux.aux_offset, event->aux.aux_size,
+		       event->aux.flags,
+		       event->aux.flags & PERF_AUX_FLAG_TRUNCATED ? "T" : "",
+		       event->aux.flags & PERF_AUX_FLAG_OVERWRITE ? "O" : "");
+}
+
+size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp)
+{
+	return fprintf(fp, " pid: %u tid: %u\n",
+		       event->itrace_start.pid, event->itrace_start.tid);
+}
+
 size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 {
 	size_t ret = fprintf(fp, "PERF_RECORD_%s",
@@ -774,6 +846,12 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 	case PERF_RECORD_MMAP2:
 		ret += perf_event__fprintf_mmap2(event, fp);
 		break;
+	case PERF_RECORD_AUX:
+		ret += perf_event__fprintf_aux(event, fp);
+		break;
+	case PERF_RECORD_ITRACE_START:
+		ret += perf_event__fprintf_itrace_start(event, fp);
+		break;
 	default:
 		ret += fprintf(fp, "\n");
 	}
@@ -877,6 +955,10 @@ void thread__find_addr_location(struct thread *thread,
 		al->sym = NULL;
 }
 
+/*
+ * Callers need to drop the reference to al->thread, obtained in
+ * machine__findnew_thread()
+ */
 int perf_event__preprocess_sample(const union perf_event *event,
 				  struct machine *machine,
 				  struct addr_location *al,
@@ -937,6 +1019,17 @@ int perf_event__preprocess_sample(const union perf_event *event,
 	return 0;
 }
 
+/*
+ * The preprocess_sample method will return with reference counts for the
+ * in it, when done using (and perhaps getting ref counts if needing to
+ * keep a pointer to one of those entries) it must be paired with
+ * addr_location__put(), so that the refcounts can be decremented.
+ */
+void addr_location__put(struct addr_location *al)
+{
+	thread__zput(al->thread);
+}
+
 bool is_bts_event(struct perf_event_attr *attr)
 {
 	return attr->type == PERF_TYPE_HARDWARE &&
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 09b9e8d3f..c53f36384 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -52,6 +52,11 @@ struct lost_event {
 	u64 lost;
 };
 
+struct lost_samples_event {
+	struct perf_event_header header;
+	u64 lost;
+};
+
 /*
  * PERF_FORMAT_ENABLED | PERF_FORMAT_RUNNING | PERF_FORMAT_ID
  */
@@ -157,6 +162,8 @@ enum {
 	PERF_IP_FLAG_IN_TX		= 1ULL << 10,
 };
 
+#define PERF_IP_FLAG_CHARS "bcrosyiABEx"
+
 #define PERF_BRANCH_MASK		(\
 	PERF_IP_FLAG_BRANCH		|\
 	PERF_IP_FLAG_CALL		|\
@@ -215,9 +222,17 @@ enum perf_user_event_type { /* above any possible kernel type */
 	PERF_RECORD_HEADER_BUILD_ID		= 67,
 	PERF_RECORD_FINISHED_ROUND		= 68,
 	PERF_RECORD_ID_INDEX			= 69,
+	PERF_RECORD_AUXTRACE_INFO		= 70,
+	PERF_RECORD_AUXTRACE			= 71,
+	PERF_RECORD_AUXTRACE_ERROR		= 72,
 	PERF_RECORD_HEADER_MAX
 };
 
+enum auxtrace_error_type {
+	PERF_AUXTRACE_ERROR_ITRACE  = 1,
+	PERF_AUXTRACE_ERROR_MAX
+};
+
 /*
  * The kernel collects the number of events it couldn't send in a stretch and
  * when possible sends this number in a PERF_RECORD_LOST event. The number of
@@ -225,6 +240,12 @@ enum perf_user_event_type { /* above any possible kernel type */
  * total_lost tells exactly how many events the kernel in fact lost, i.e. it is
  * the sum of all struct lost_event.lost fields reported.
  *
+ * The kernel discards mixed up samples and sends the number in a
+ * PERF_RECORD_LOST_SAMPLES event. The number of lost-samples events is stored
+ * in .nr_events[PERF_RECORD_LOST_SAMPLES] while total_lost_samples tells
+ * exactly how many samples the kernel in fact dropped, i.e. it is the sum of
+ * all struct lost_samples_event.lost fields reported.
+ *
  * The total_period is needed because by default auto-freq is used, so
  * multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get
  * the total number of low level events, it is necessary to to sum all struct
@@ -234,6 +255,7 @@ struct events_stats {
 	u64 total_period;
 	u64 total_non_filtered_period;
 	u64 total_lost;
+	u64 total_lost_samples;
 	u64 total_invalid_chains;
 	u32 nr_events[PERF_RECORD_HEADER_MAX];
 	u32 nr_non_filtered_samples;
@@ -242,6 +264,8 @@ struct events_stats {
 	u32 nr_invalid_chains;
 	u32 nr_unknown_id;
 	u32 nr_unprocessable_samples;
+	u32 nr_auxtrace_errors[PERF_AUXTRACE_ERROR_MAX];
+	u32 nr_proc_map_timeout;
 };
 
 struct attr_event {
@@ -280,6 +304,50 @@ struct id_index_event {
 	struct id_index_entry entries[0];
 };
 
+struct auxtrace_info_event {
+	struct perf_event_header header;
+	u32 type;
+	u32 reserved__; /* For alignment */
+	u64 priv[];
+};
+
+struct auxtrace_event {
+	struct perf_event_header header;
+	u64 size;
+	u64 offset;
+	u64 reference;
+	u32 idx;
+	u32 tid;
+	u32 cpu;
+	u32 reserved__; /* For alignment */
+};
+
+#define MAX_AUXTRACE_ERROR_MSG 64
+
+struct auxtrace_error_event {
+	struct perf_event_header header;
+	u32 type;
+	u32 code;
+	u32 cpu;
+	u32 pid;
+	u32 tid;
+	u32 reserved__; /* For alignment */
+	u64 ip;
+	char msg[MAX_AUXTRACE_ERROR_MSG];
+};
+
+struct aux_event {
+	struct perf_event_header header;
+	u64	aux_offset;
+	u64	aux_size;
+	u64	flags;
+};
+
+struct itrace_start_event {
+	struct perf_event_header header;
+	u32 pid, tid;
+};
+
 union perf_event {
 	struct perf_event_header	header;
 	struct mmap_event		mmap;
@@ -287,6 +355,7 @@ union perf_event {
 	struct comm_event		comm;
 	struct fork_event		fork;
 	struct lost_event		lost;
+	struct lost_samples_event	lost_samples;
 	struct read_event		read;
 	struct throttle_event		throttle;
 	struct sample_event		sample;
@@ -295,6 +364,11 @@ union perf_event {
 	struct tracing_data_event	tracing_data;
 	struct build_id_event		build_id;
 	struct id_index_event		id_index;
+	struct auxtrace_info_event	auxtrace_info;
+	struct auxtrace_event		auxtrace;
+	struct auxtrace_error_event	auxtrace_error;
+	struct aux_event		aux;
+	struct itrace_start_event	itrace_start;
 };
 
 void perf_event__print_totals(void);
@@ -310,10 +384,12 @@ typedef int (*perf_event__handler_t)(struct perf_tool *tool,
 int perf_event__synthesize_thread_map(struct perf_tool *tool,
 				      struct thread_map *threads,
 				      perf_event__handler_t process,
-				      struct machine *machine, bool mmap_data);
+				      struct machine *machine, bool mmap_data,
+				      unsigned int proc_map_timeout);
 int perf_event__synthesize_threads(struct perf_tool *tool,
 				   perf_event__handler_t process,
-				   struct machine *machine, bool mmap_data);
+				   struct machine *machine, bool mmap_data,
+				   unsigned int proc_map_timeout);
 int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 				       perf_event__handler_t process,
 				       struct machine *machine);
@@ -330,6 +406,18 @@ int perf_event__process_lost(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_sample *sample,
 			     struct machine *machine);
+int perf_event__process_lost_samples(struct perf_tool *tool,
+				     union perf_event *event,
+				     struct perf_sample *sample,
+				     struct machine *machine);
+int perf_event__process_aux(struct perf_tool *tool,
+			    union perf_event *event,
+			    struct perf_sample *sample,
+			    struct machine *machine);
+int perf_event__process_itrace_start(struct perf_tool *tool,
+				     union perf_event *event,
+				     struct perf_sample *sample,
+				     struct machine *machine);
 int perf_event__process_mmap(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_sample *sample,
@@ -358,6 +446,8 @@ int perf_event__preprocess_sample(const union perf_event *event,
 				  struct addr_location *al,
 				  struct perf_sample *sample);
 
+void addr_location__put(struct addr_location *al);
+
 struct thread;
 
 bool is_bts_event(struct perf_event_attr *attr);
@@ -381,12 +471,15 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 				       pid_t pid, pid_t tgid,
 				       perf_event__handler_t process,
 				       struct machine *machine,
-				       bool mmap_data);
+				       bool mmap_data,
+				       unsigned int proc_map_timeout);
 
 size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_task(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf(union perf_event *event, FILE *fp);
 
 u64 kallsyms__get_function_start(const char *kallsyms_filename,
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 080be93ee..6cfdee68e 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -114,8 +114,8 @@ void perf_evlist__delete(struct perf_evlist *evlist)
 {
 	perf_evlist__munmap(evlist);
 	perf_evlist__close(evlist);
-	cpu_map__delete(evlist->cpus);
-	thread_map__delete(evlist->threads);
+	cpu_map__put(evlist->cpus);
+	thread_map__put(evlist->threads);
 	evlist->cpus = NULL;
 	evlist->threads = NULL;
 	perf_evlist__purge(evlist);
@@ -297,6 +297,8 @@ void perf_evlist__disable(struct perf_evlist *evlist)
 				      PERF_EVENT_IOC_DISABLE, 0);
 		}
 	}
+
+	evlist->enabled = false;
 }
 
 void perf_evlist__enable(struct perf_evlist *evlist)
@@ -316,6 +318,13 @@ void perf_evlist__enable(struct perf_evlist *evlist)
 				      PERF_EVENT_IOC_ENABLE, 0);
 		}
 	}
+
+	evlist->enabled = true;
+}
+
+void perf_evlist__toggle_enable(struct perf_evlist *evlist)
+{
+	(evlist->enabled ? perf_evlist__disable : perf_evlist__enable)(evlist);
 }
 
 int perf_evlist__disable_event(struct perf_evlist *evlist,
@@ -539,7 +548,7 @@ static void perf_evlist__set_sid_idx(struct perf_evlist *evlist,
 	else
 		sid->cpu = -1;
 	if (!evsel->system_wide && evlist->threads && thread >= 0)
-		sid->tid = evlist->threads->map[thread];
+		sid->tid = thread_map__pid(evlist->threads, thread);
 	else
 		sid->tid = -1;
 }
@@ -634,11 +643,18 @@ static struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
 union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 {
 	struct perf_mmap *md = &evlist->mmap[idx];
-	u64 head = perf_mmap__read_head(md);
+	u64 head;
 	u64 old = md->prev;
 	unsigned char *data = md->base + page_size;
 	union perf_event *event = NULL;
 
+	/*
+	 * Check if event was unmapped due to a POLLHUP/POLLERR.
+	 */
+	if (!atomic_read(&md->refcnt))
+		return NULL;
+
+	head = perf_mmap__read_head(md);
 	if (evlist->overwrite) {
 		/*
 		 * If we're further behind than half the buffer, there's a chance
@@ -695,19 +711,19 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 
 static bool perf_mmap__empty(struct perf_mmap *md)
 {
-	return perf_mmap__read_head(md) == md->prev;
+	return perf_mmap__read_head(md) == md->prev && !md->auxtrace_mmap.base;
 }
 
 static void perf_evlist__mmap_get(struct perf_evlist *evlist, int idx)
 {
-	++evlist->mmap[idx].refcnt;
+	atomic_inc(&evlist->mmap[idx].refcnt);
 }
 
 static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx)
 {
-	BUG_ON(evlist->mmap[idx].refcnt == 0);
+	BUG_ON(atomic_read(&evlist->mmap[idx].refcnt) == 0);
 
-	if (--evlist->mmap[idx].refcnt == 0)
+	if (atomic_dec_and_test(&evlist->mmap[idx].refcnt))
 		__perf_evlist__munmap(evlist, idx);
 }
 
@@ -721,17 +737,46 @@ void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
 		perf_mmap__write_tail(md, old);
 	}
 
-	if (md->refcnt == 1 && perf_mmap__empty(md))
+	if (atomic_read(&md->refcnt) == 1 && perf_mmap__empty(md))
 		perf_evlist__mmap_put(evlist, idx);
 }
 
+int __weak auxtrace_mmap__mmap(struct auxtrace_mmap *mm __maybe_unused,
+			       struct auxtrace_mmap_params *mp __maybe_unused,
+			       void *userpg __maybe_unused,
+			       int fd __maybe_unused)
+{
+	return 0;
+}
+
+void __weak auxtrace_mmap__munmap(struct auxtrace_mmap *mm __maybe_unused)
+{
+}
+
+void __weak auxtrace_mmap_params__init(
+			struct auxtrace_mmap_params *mp __maybe_unused,
+			off_t auxtrace_offset __maybe_unused,
+			unsigned int auxtrace_pages __maybe_unused,
+			bool auxtrace_overwrite __maybe_unused)
+{
+}
+
+void __weak auxtrace_mmap_params__set_idx(
+			struct auxtrace_mmap_params *mp __maybe_unused,
+			struct perf_evlist *evlist __maybe_unused,
+			int idx __maybe_unused,
+			bool per_cpu __maybe_unused)
+{
+}
+
 static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
 {
 	if (evlist->mmap[idx].base != NULL) {
 		munmap(evlist->mmap[idx].base, evlist->mmap_len);
 		evlist->mmap[idx].base = NULL;
-		evlist->mmap[idx].refcnt = 0;
+		atomic_set(&evlist->mmap[idx].refcnt, 0);
 	}
+	auxtrace_mmap__munmap(&evlist->mmap[idx].auxtrace_mmap);
 }
 
 void perf_evlist__munmap(struct perf_evlist *evlist)
@@ -759,6 +804,7 @@ static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 struct mmap_params {
 	int prot;
 	int mask;
+	struct auxtrace_mmap_params auxtrace_mp;
 };
 
 static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
@@ -777,7 +823,7 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
 	 * evlist layer can't just drop it when filtering events in
 	 * perf_evlist__filter_pollfd().
 	 */
-	evlist->mmap[idx].refcnt = 2;
+	atomic_set(&evlist->mmap[idx].refcnt, 2);
 	evlist->mmap[idx].prev = 0;
 	evlist->mmap[idx].mask = mp->mask;
 	evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, mp->prot,
@@ -789,6 +835,10 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
 		return -1;
 	}
 
+	if (auxtrace_mmap__mmap(&evlist->mmap[idx].auxtrace_mmap,
+				&mp->auxtrace_mp, evlist->mmap[idx].base, fd))
+		return -1;
+
 	return 0;
 }
 
@@ -853,6 +903,9 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist,
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		int output = -1;
 
+		auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, cpu,
+					      true);
+
 		for (thread = 0; thread < nr_threads; thread++) {
 			if (perf_evlist__mmap_per_evsel(evlist, cpu, mp, cpu,
 							thread, &output))
@@ -878,6 +931,9 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist,
 	for (thread = 0; thread < nr_threads; thread++) {
 		int output = -1;
 
+		auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, thread,
+					      false);
+
 		if (perf_evlist__mmap_per_evsel(evlist, thread, mp, 0, thread,
 						&output))
 			goto out_unmap;
@@ -960,10 +1016,8 @@ static long parse_pages_arg(const char *str, unsigned long min,
 	return pages;
 }
 
-int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
-				  int unset __maybe_unused)
+int __perf_evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str)
 {
-	unsigned int *mmap_pages = opt->value;
 	unsigned long max = UINT_MAX;
 	long pages;
 
@@ -980,20 +1034,32 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
 	return 0;
 }
 
+int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
+				  int unset __maybe_unused)
+{
+	return __perf_evlist__parse_mmap_pages(opt->value, str);
+}
+
 /**
- * perf_evlist__mmap - Create mmaps to receive events.
+ * perf_evlist__mmap_ex - Create mmaps to receive events.
  * @evlist: list of events
  * @pages: map length in pages
  * @overwrite: overwrite older events?
+ * @auxtrace_pages - auxtrace map length in pages
+ * @auxtrace_overwrite - overwrite older auxtrace data?
  *
  * If @overwrite is %false the user needs to signal event consumption using
  * perf_mmap__write_tail().  Using perf_evlist__mmap_read() does this
  * automatically.
  *
+ * Similarly, if @auxtrace_overwrite is %false the user needs to signal data
+ * consumption using auxtrace_mmap__write_tail().
+ *
  * Return: %0 on success, negative error code otherwise.
  */
-int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
-		      bool overwrite)
+int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
+			 bool overwrite, unsigned int auxtrace_pages,
+			 bool auxtrace_overwrite)
 {
 	struct perf_evsel *evsel;
 	const struct cpu_map *cpus = evlist->cpus;
@@ -1013,6 +1079,9 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 	pr_debug("mmap size %zuB\n", evlist->mmap_len);
 	mp.mask = evlist->mmap_len - page_size - 1;
 
+	auxtrace_mmap_params__init(&mp.auxtrace_mp, evlist->mmap_len,
+				   auxtrace_pages, auxtrace_overwrite);
+
 	evlist__for_each(evlist, evsel) {
 		if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
 		    evsel->sample_id == NULL &&
@@ -1026,6 +1095,37 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 	return perf_evlist__mmap_per_cpu(evlist, &mp);
 }
 
+int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
+		      bool overwrite)
+{
+	return perf_evlist__mmap_ex(evlist, pages, overwrite, 0, false);
+}
+
+static int perf_evlist__propagate_maps(struct perf_evlist *evlist,
+				       struct target *target)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		/*
+		 * We already have cpus for evsel (via PMU sysfs) so
+		 * keep it, if there's no target cpu list defined.
+		 */
+		if (evsel->cpus && target->cpu_list)
+			cpu_map__put(evsel->cpus);
+
+		if (!evsel->cpus || target->cpu_list)
+			evsel->cpus = cpu_map__get(evlist->cpus);
+
+		evsel->threads = thread_map__get(evlist->threads);
+
+		if (!evsel->cpus || !evsel->threads)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 {
 	evlist->threads = thread_map__new_str(target->pid, target->tid,
@@ -1042,10 +1142,10 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 	if (evlist->cpus == NULL)
 		goto out_delete_threads;
 
-	return 0;
+	return perf_evlist__propagate_maps(evlist, target);
 
 out_delete_threads:
-	thread_map__delete(evlist->threads);
+	thread_map__put(evlist->threads);
 	evlist->threads = NULL;
 	return -1;
 }
@@ -1278,7 +1378,7 @@ static int perf_evlist__create_syswide_maps(struct perf_evlist *evlist)
 out:
 	return err;
 out_free_cpus:
-	cpu_map__delete(evlist->cpus);
+	cpu_map__put(evlist->cpus);
 	evlist->cpus = NULL;
 	goto out;
 }
@@ -1400,7 +1500,7 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar
 				__func__, __LINE__);
 			goto out_close_pipes;
 		}
-		evlist->threads->map[0] = evlist->workload.pid;
+		thread_map__set_pid(evlist->threads, 0, evlist->workload.pid);
 	}
 
 	close(child_ready_pipe[1]);
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index b5cce95d6..037633c1d 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -1,6 +1,7 @@
 #ifndef __PERF_EVLIST_H
 #define __PERF_EVLIST_H 1
 
+#include <linux/atomic.h>
 #include <linux/list.h>
 #include <api/fd/array.h>
 #include <stdio.h>
@@ -8,6 +9,7 @@
 #include "event.h"
 #include "evsel.h"
 #include "util.h"
+#include "auxtrace.h"
 #include <unistd.h>
 
 struct pollfd;
@@ -26,8 +28,9 @@ struct record_opts;
 struct perf_mmap {
 	void		 *base;
 	int		 mask;
-	int		 refcnt;
+	atomic_t	 refcnt;
 	u64		 prev;
+	struct auxtrace_mmap auxtrace_mmap;
 	char		 event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8)));
 };
 
@@ -37,6 +40,8 @@ struct perf_evlist {
 	int		 nr_entries;
 	int		 nr_groups;
 	int		 nr_mmaps;
+	bool		 overwrite;
+	bool		 enabled;
 	size_t		 mmap_len;
 	int		 id_pos;
 	int		 is_pos;
@@ -45,7 +50,6 @@ struct perf_evlist {
 		int	cork_fd;
 		pid_t	pid;
 	} workload;
-	bool		 overwrite;
 	struct fdarray	 pollfd;
 	struct perf_mmap *mmap;
 	struct thread_map *threads;
@@ -122,16 +126,21 @@ int perf_evlist__start_workload(struct perf_evlist *evlist);
 
 struct option;
 
+int __perf_evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str);
 int perf_evlist__parse_mmap_pages(const struct option *opt,
 				  const char *str,
 				  int unset);
 
+int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
+			 bool overwrite, unsigned int auxtrace_pages,
+			 bool auxtrace_overwrite);
 int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 		      bool overwrite);
 void perf_evlist__munmap(struct perf_evlist *evlist);
 
 void perf_evlist__disable(struct perf_evlist *evlist);
 void perf_evlist__enable(struct perf_evlist *evlist);
+void perf_evlist__toggle_enable(struct perf_evlist *evlist);
 
 int perf_evlist__disable_event(struct perf_evlist *evlist,
 			       struct perf_evsel *evsel);
@@ -280,5 +289,4 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
 
 void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
 				     struct perf_evsel *tracking_evsel);
-
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 33e3fd8c2..2936b3080 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -26,6 +26,7 @@
 #include "perf_regs.h"
 #include "debug.h"
 #include "trace-event.h"
+#include "stat.h"
 
 static struct {
 	bool sample_id_all;
@@ -851,19 +852,6 @@ int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
 	return 0;
 }
 
-void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus)
-{
-	memset(evsel->counts, 0, (sizeof(*evsel->counts) +
-				 (ncpus * sizeof(struct perf_counts_values))));
-}
-
-int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus)
-{
-	evsel->counts = zalloc((sizeof(*evsel->counts) +
-				(ncpus * sizeof(struct perf_counts_values))));
-	return evsel->counts != NULL ? 0 : -ENOMEM;
-}
-
 static void perf_evsel__free_fd(struct perf_evsel *evsel)
 {
 	xyarray__delete(evsel->fd);
@@ -891,17 +879,14 @@ void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 		}
 }
 
-void perf_evsel__free_counts(struct perf_evsel *evsel)
-{
-	zfree(&evsel->counts);
-}
-
 void perf_evsel__exit(struct perf_evsel *evsel)
 {
 	assert(list_empty(&evsel->node));
 	perf_evsel__free_fd(evsel);
 	perf_evsel__free_id(evsel);
 	close_cgroup(evsel->cgrp);
+	cpu_map__put(evsel->cpus);
+	thread_map__put(evsel->threads);
 	zfree(&evsel->group_name);
 	zfree(&evsel->name);
 	perf_evsel__object.fini(evsel);
@@ -913,7 +898,7 @@ void perf_evsel__delete(struct perf_evsel *evsel)
 	free(evsel);
 }
 
-void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu,
+void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, int thread,
 				struct perf_counts_values *count)
 {
 	struct perf_counts_values tmp;
@@ -925,8 +910,8 @@ void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu,
 		tmp = evsel->prev_raw_counts->aggr;
 		evsel->prev_raw_counts->aggr = *count;
 	} else {
-		tmp = evsel->prev_raw_counts->cpu[cpu];
-		evsel->prev_raw_counts->cpu[cpu] = *count;
+		tmp = *perf_counts(evsel->prev_raw_counts, cpu, thread);
+		*perf_counts(evsel->prev_raw_counts, cpu, thread) = *count;
 	}
 
 	count->val = count->val - tmp.val;
@@ -954,20 +939,18 @@ void perf_counts_values__scale(struct perf_counts_values *count,
 		*pscaled = scaled;
 }
 
-int perf_evsel__read_cb(struct perf_evsel *evsel, int cpu, int thread,
-			perf_evsel__read_cb_t cb)
+int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
+		     struct perf_counts_values *count)
 {
-	struct perf_counts_values count;
-
-	memset(&count, 0, sizeof(count));
+	memset(count, 0, sizeof(*count));
 
 	if (FD(evsel, cpu, thread) < 0)
 		return -EINVAL;
 
-	if (readn(FD(evsel, cpu, thread), &count, sizeof(count)) < 0)
+	if (readn(FD(evsel, cpu, thread), count, sizeof(*count)) < 0)
 		return -errno;
 
-	return cb(evsel, cpu, thread, &count);
+	return 0;
 }
 
 int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
@@ -979,15 +962,15 @@ int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 	if (FD(evsel, cpu, thread) < 0)
 		return -EINVAL;
 
-	if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1) < 0)
+	if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1, thread + 1) < 0)
 		return -ENOMEM;
 
 	if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0)
 		return -errno;
 
-	perf_evsel__compute_deltas(evsel, cpu, &count);
+	perf_evsel__compute_deltas(evsel, cpu, thread, &count);
 	perf_counts_values__scale(&count, scale, NULL);
-	evsel->counts->cpu[cpu] = count;
+	*perf_counts(evsel->counts, cpu, thread) = count;
 	return 0;
 }
 
@@ -1058,7 +1041,7 @@ static void __p_read_format(char *buf, size_t size, u64 value)
 
 #define BUF_SIZE		1024
 
-#define p_hex(val)		snprintf(buf, BUF_SIZE, "%"PRIx64, (uint64_t)(val))
+#define p_hex(val)		snprintf(buf, BUF_SIZE, "%#"PRIx64, (uint64_t)(val))
 #define p_unsigned(val)		snprintf(buf, BUF_SIZE, "%"PRIu64, (uint64_t)(val))
 #define p_signed(val)		snprintf(buf, BUF_SIZE, "%"PRId64, (int64_t)(val))
 #define p_sample_type(val)	__p_sample_type(buf, BUF_SIZE, val)
@@ -1121,6 +1104,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 	PRINT_ATTRf(sample_stack_user, p_unsigned);
 	PRINT_ATTRf(clockid, p_signed);
 	PRINT_ATTRf(sample_regs_intr, p_hex);
+	PRINT_ATTRf(aux_watermark, p_unsigned);
 
 	return ret;
 }
@@ -1183,7 +1167,7 @@ retry_sample_id:
 			int group_fd;
 
 			if (!evsel->cgrp && !evsel->system_wide)
-				pid = threads->map[thread];
+				pid = thread_map__pid(threads, thread);
 
 			group_fd = get_group_fd(evsel, cpu, thread);
 retry_open:
@@ -2148,7 +2132,9 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 	case EMFILE:
 		return scnprintf(msg, size, "%s",
 			 "Too many events are opened.\n"
-			 "Try again after reducing the number of events.");
+			 "Probably the maximum number of open file descriptors has been reached.\n"
+			 "Hint: Try again after reducing the number of events.\n"
+			 "Hint: Try increasing the limit with 'ulimit -n <limit>'");
 	case ENODEV:
 		if (target->cpu_list)
 			return scnprintf(msg, size, "%s",
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index e486151b0..4a7ed5656 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -8,23 +8,8 @@
 #include <linux/types.h>
 #include "xyarray.h"
 #include "symbol.h"
-
-struct perf_counts_values {
-	union {
-		struct {
-			u64 val;
-			u64 ena;
-			u64 run;
-		};
-		u64 values[3];
-	};
-};
-
-struct perf_counts {
-	s8		   	  scaled;
-	struct perf_counts_values aggr;
-	struct perf_counts_values cpu[];
-};
+#include "cpumap.h"
+#include "stat.h"
 
 struct perf_evsel;
 
@@ -73,7 +58,6 @@ struct perf_evsel {
 	char			*name;
 	double			scale;
 	const char		*unit;
-	bool			snapshot;
 	struct event_format	*tp_format;
 	union {
 		void		*priv;
@@ -83,9 +67,11 @@ struct perf_evsel {
 	struct cgroup_sel	*cgrp;
 	void			*handler;
 	struct cpu_map		*cpus;
+	struct thread_map	*threads;
 	unsigned int		sample_size;
 	int			id_pos;
 	int			is_pos;
+	bool			snapshot;
 	bool 			supported;
 	bool 			needs_swap;
 	bool			no_aux_samples;
@@ -93,11 +79,11 @@ struct perf_evsel {
 	bool			system_wide;
 	bool			tracking;
 	bool			per_pkg;
-	unsigned long		*per_pkg_mask;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;
 	int			sample_read;
+	unsigned long		*per_pkg_mask;
 	struct perf_evsel	*leader;
 	char			*group_name;
 };
@@ -113,10 +99,20 @@ struct thread_map;
 struct perf_evlist;
 struct record_opts;
 
+static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel)
+{
+	return evsel->cpus;
+}
+
+static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel)
+{
+	return perf_evsel__cpus(evsel)->nr;
+}
+
 void perf_counts_values__scale(struct perf_counts_values *count,
 			       bool scale, s8 *pscaled);
 
-void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu,
+void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, int thread,
 				struct perf_counts_values *count);
 
 int perf_evsel__object_config(size_t object_size,
@@ -170,9 +166,6 @@ const char *perf_evsel__group_name(struct perf_evsel *evsel);
 int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size);
 
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
-int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
-void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus);
-void perf_evsel__free_counts(struct perf_evsel *evsel);
 void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 
 void __perf_evsel__set_sample_bit(struct perf_evsel *evsel,
@@ -236,12 +229,8 @@ static inline bool perf_evsel__match2(struct perf_evsel *e1,
 	 (a)->attr.type == (b)->attr.type &&	\
 	 (a)->attr.config == (b)->attr.config)
 
-typedef int (perf_evsel__read_cb_t)(struct perf_evsel *evsel,
-				    int cpu, int thread,
-				    struct perf_counts_values *count);
-
-int perf_evsel__read_cb(struct perf_evsel *evsel, int cpu, int thread,
-			perf_evsel__read_cb_t cb);
+int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
+		     struct perf_counts_values *count);
 
 int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 			      int cpu, int thread, bool scale);
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 918fd8ae2..03ace57a8 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -869,6 +869,20 @@ static int write_branch_stack(int fd __maybe_unused,
 	return 0;
 }
 
+static int write_auxtrace(int fd, struct perf_header *h,
+			  struct perf_evlist *evlist __maybe_unused)
+{
+	struct perf_session *session;
+	int err;
+
+	session = container_of(h, struct perf_session, header);
+
+	err = auxtrace_index__write(fd, &session->auxtrace_index);
+	if (err < 0)
+		pr_err("Failed to write auxtrace index\n");
+	return err;
+}
+
 static void print_hostname(struct perf_header *ph, int fd __maybe_unused,
 			   FILE *fp)
 {
@@ -1049,8 +1063,7 @@ out:
 	free(buf);
 	return events;
 error:
-	if (events)
-		free_event_desc(events);
+	free_event_desc(events);
 	events = NULL;
 	goto out;
 }
@@ -1151,6 +1164,12 @@ static void print_branch_stack(struct perf_header *ph __maybe_unused,
 	fprintf(fp, "# contains samples with branch stack\n");
 }
 
+static void print_auxtrace(struct perf_header *ph __maybe_unused,
+			   int fd __maybe_unused, FILE *fp)
+{
+	fprintf(fp, "# contains AUX area data (e.g. instruction trace)\n");
+}
+
 static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused,
 			       FILE *fp)
 {
@@ -1218,9 +1237,8 @@ static int __event_process_build_id(struct build_id_event *bev,
 				    struct perf_session *session)
 {
 	int err = -1;
-	struct dsos *dsos;
 	struct machine *machine;
-	u16 misc;
+	u16 cpumode;
 	struct dso *dso;
 	enum dso_kernel_type dso_type;
 
@@ -1228,39 +1246,37 @@ static int __event_process_build_id(struct build_id_event *bev,
 	if (!machine)
 		goto out;
 
-	misc = bev->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+	cpumode = bev->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
-	switch (misc) {
+	switch (cpumode) {
 	case PERF_RECORD_MISC_KERNEL:
 		dso_type = DSO_TYPE_KERNEL;
-		dsos = &machine->kernel_dsos;
 		break;
 	case PERF_RECORD_MISC_GUEST_KERNEL:
 		dso_type = DSO_TYPE_GUEST_KERNEL;
-		dsos = &machine->kernel_dsos;
 		break;
 	case PERF_RECORD_MISC_USER:
 	case PERF_RECORD_MISC_GUEST_USER:
 		dso_type = DSO_TYPE_USER;
-		dsos = &machine->user_dsos;
 		break;
 	default:
 		goto out;
 	}
 
-	dso = __dsos__findnew(dsos, filename);
+	dso = machine__findnew_dso(machine, filename);
 	if (dso != NULL) {
 		char sbuild_id[BUILD_ID_SIZE * 2 + 1];
 
 		dso__set_build_id(dso, &bev->build_id);
 
-		if (!is_kernel_module(filename))
+		if (!is_kernel_module(filename, cpumode))
 			dso->kernel = dso_type;
 
 		build_id__sprintf(dso->build_id, sizeof(dso->build_id),
 				  sbuild_id);
 		pr_debug("build id event received for %s: %s\n",
 			 dso->long_name, sbuild_id);
+		dso__put(dso);
 	}
 
 	err = 0;
@@ -1821,6 +1837,22 @@ out_free:
 	return ret;
 }
 
+static int process_auxtrace(struct perf_file_section *section,
+			    struct perf_header *ph, int fd,
+			    void *data __maybe_unused)
+{
+	struct perf_session *session;
+	int err;
+
+	session = container_of(ph, struct perf_session, header);
+
+	err = auxtrace_index__process(fd, section->size, session,
+				      ph->needs_swap);
+	if (err < 0)
+		pr_err("Failed to process auxtrace index\n");
+	return err;
+}
+
 struct feature_ops {
 	int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist);
 	void (*print)(struct perf_header *h, int fd, FILE *fp);
@@ -1861,6 +1893,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPA(HEADER_BRANCH_STACK,	branch_stack),
 	FEAT_OPP(HEADER_PMU_MAPPINGS,	pmu_mappings),
 	FEAT_OPP(HEADER_GROUP_DESC,	group_desc),
+	FEAT_OPP(HEADER_AUXTRACE,	auxtrace),
 };
 
 struct header_print_data {
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 3bb90ac17..d4d57962c 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -30,6 +30,7 @@ enum {
 	HEADER_BRANCH_STACK,
 	HEADER_PMU_MAPPINGS,
 	HEADER_GROUP_DESC,
+	HEADER_AUXTRACE,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index cc22b9158..6f28d53d4 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -313,8 +313,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template,
 				memset(&he->stat, 0, sizeof(he->stat));
 		}
 
-		if (he->ms.map)
-			he->ms.map->referenced = true;
+		map__get(he->ms.map);
 
 		if (he->branch_info) {
 			/*
@@ -324,6 +323,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template,
 			 */
 			he->branch_info = malloc(sizeof(*he->branch_info));
 			if (he->branch_info == NULL) {
+				map__zput(he->ms.map);
 				free(he->stat_acc);
 				free(he);
 				return NULL;
@@ -332,17 +332,13 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template,
 			memcpy(he->branch_info, template->branch_info,
 			       sizeof(*he->branch_info));
 
-			if (he->branch_info->from.map)
-				he->branch_info->from.map->referenced = true;
-			if (he->branch_info->to.map)
-				he->branch_info->to.map->referenced = true;
+			map__get(he->branch_info->from.map);
+			map__get(he->branch_info->to.map);
 		}
 
 		if (he->mem_info) {
-			if (he->mem_info->iaddr.map)
-				he->mem_info->iaddr.map->referenced = true;
-			if (he->mem_info->daddr.map)
-				he->mem_info->daddr.map->referenced = true;
+			map__get(he->mem_info->iaddr.map);
+			map__get(he->mem_info->daddr.map);
 		}
 
 		if (symbol_conf.use_callchain)
@@ -362,10 +358,10 @@ static u8 symbol__parent_filter(const struct symbol *parent)
 	return 0;
 }
 
-static struct hist_entry *add_hist_entry(struct hists *hists,
-					 struct hist_entry *entry,
-					 struct addr_location *al,
-					 bool sample_self)
+static struct hist_entry *hists__findnew_entry(struct hists *hists,
+					       struct hist_entry *entry,
+					       struct addr_location *al,
+					       bool sample_self)
 {
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
@@ -407,9 +403,8 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
 			 * the history counter to increment.
 			 */
 			if (he->ms.map != entry->ms.map) {
-				he->ms.map = entry->ms.map;
-				if (he->ms.map)
-					he->ms.map->referenced = true;
+				map__put(he->ms.map);
+				he->ms.map = map__get(entry->ms.map);
 			}
 			goto out;
 		}
@@ -468,7 +463,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 		.transaction = transaction,
 	};
 
-	return add_hist_entry(hists, &entry, al, sample_self);
+	return hists__findnew_entry(hists, &entry, al, sample_self);
 }
 
 static int
@@ -548,9 +543,9 @@ iter_finish_mem_entry(struct hist_entry_iter *iter,
 
 out:
 	/*
-	 * We don't need to free iter->priv (mem_info) here since
-	 * the mem info was either already freed in add_hist_entry() or
-	 * passed to a new hist entry by hist_entry__new().
+	 * We don't need to free iter->priv (mem_info) here since the mem info
+	 * was either already freed in hists__findnew_entry() or passed to a
+	 * new hist entry by hist_entry__new().
 	 */
 	iter->priv = NULL;
 
@@ -851,19 +846,15 @@ const struct hist_iter_ops hist_iter_cumulative = {
 };
 
 int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
-			 struct perf_evsel *evsel, struct perf_sample *sample,
 			 int max_stack_depth, void *arg)
 {
 	int err, err2;
 
-	err = sample__resolve_callchain(sample, &iter->parent, evsel, al,
-					max_stack_depth);
+	err = sample__resolve_callchain(iter->sample, &iter->parent,
+					iter->evsel, al, max_stack_depth);
 	if (err)
 		return err;
 
-	iter->evsel = evsel;
-	iter->sample = sample;
-
 	err = iter->ops->prepare_entry(iter, al);
 	if (err)
 		goto out;
@@ -937,8 +928,20 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
 void hist_entry__delete(struct hist_entry *he)
 {
 	thread__zput(he->thread);
-	zfree(&he->branch_info);
-	zfree(&he->mem_info);
+	map__zput(he->ms.map);
+
+	if (he->branch_info) {
+		map__zput(he->branch_info->from.map);
+		map__zput(he->branch_info->to.map);
+		zfree(&he->branch_info);
+	}
+
+	if (he->mem_info) {
+		map__zput(he->mem_info->iaddr.map);
+		map__zput(he->mem_info->daddr.map);
+		zfree(&he->mem_info);
+	}
+
 	zfree(&he->stat_acc);
 	free_srcline(he->srcline);
 	free_callchain(he->callchain);
@@ -1163,7 +1166,7 @@ static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h
 		return;
 
 	/* force fold unfiltered entry for simplicity */
-	h->ms.unfolded = false;
+	h->unfolded = false;
 	h->row_offset = 0;
 	h->nr_rows = 0;
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 9f31b89a5..5ed8d9c22 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -111,7 +111,6 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 				      u64 weight, u64 transaction,
 				      bool sample_self);
 int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
-			 struct perf_evsel *evsel, struct perf_sample *sample,
 			 int max_stack_depth, void *arg);
 
 int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right);
diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h
deleted file mode 100644
index 09e8e7aea..000000000
--- a/tools/perf/util/include/linux/kernel.h
+++ /dev/null
@@ -1,107 +0,0 @@
-#ifndef PERF_LINUX_KERNEL_H_
-#define PERF_LINUX_KERNEL_H_
-
-#include <stdarg.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <assert.h>
-
-#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
-
-#define PERF_ALIGN(x, a)	__PERF_ALIGN_MASK(x, (typeof(x))(a)-1)
-#define __PERF_ALIGN_MASK(x, mask)	(((x)+(mask))&~(mask))
-
-#ifndef offsetof
-#define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER)
-#endif
-
-#ifndef container_of
-/**
- * container_of - cast a member of a structure out to the containing structure
- * @ptr:	the pointer to the member.
- * @type:	the type of the container struct this is embedded in.
- * @member:	the name of the member within the struct.
- *
- */
-#define container_of(ptr, type, member) ({			\
-	const typeof(((type *)0)->member) * __mptr = (ptr);	\
-	(type *)((char *)__mptr - offsetof(type, member)); })
-#endif
-
-#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); }))
-
-#ifndef max
-#define max(x, y) ({				\
-	typeof(x) _max1 = (x);			\
-	typeof(y) _max2 = (y);			\
-	(void) (&_max1 == &_max2);		\
-	_max1 > _max2 ? _max1 : _max2; })
-#endif
-
-#ifndef min
-#define min(x, y) ({				\
-	typeof(x) _min1 = (x);			\
-	typeof(y) _min2 = (y);			\
-	(void) (&_min1 == &_min2);		\
-	_min1 < _min2 ? _min1 : _min2; })
-#endif
-
-#ifndef roundup
-#define roundup(x, y) (                                \
-{                                                      \
-	const typeof(y) __y = y;		       \
-	(((x) + (__y - 1)) / __y) * __y;	       \
-}                                                      \
-)
-#endif
-
-#ifndef BUG_ON
-#ifdef NDEBUG
-#define BUG_ON(cond) do { if (cond) {} } while (0)
-#else
-#define BUG_ON(cond) assert(!(cond))
-#endif
-#endif
-
-/*
- * Both need more care to handle endianness
- * (Don't use bitmap_copy_le() for now)
- */
-#define cpu_to_le64(x)	(x)
-#define cpu_to_le32(x)	(x)
-
-static inline int
-vscnprintf(char *buf, size_t size, const char *fmt, va_list args)
-{
-	int i;
-	ssize_t ssize = size;
-
-	i = vsnprintf(buf, size, fmt, args);
-
-	return (i >= ssize) ? (ssize - 1) : i;
-}
-
-static inline int scnprintf(char * buf, size_t size, const char * fmt, ...)
-{
-	va_list args;
-	ssize_t ssize = size;
-	int i;
-
-	va_start(args, fmt);
-	i = vsnprintf(buf, size, fmt, args);
-	va_end(args);
-
-	return (i >= ssize) ? (ssize - 1) : i;
-}
-
-/*
- * This looks more complex than it should be. But we need to
- * get the type for the ~ right in round_down (it needs to be
- * as wide as the result!), and we want to evaluate the macro
- * arguments just once each.
- */
-#define __round_mask(x, y) ((__typeof__(x))((y)-1))
-#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1)
-#define round_down(x, y) ((x) & ~__round_mask(x, y))
-
-#endif
diff --git a/tools/perf/util/include/linux/list.h b/tools/perf/util/include/linux/list.h
deleted file mode 100644
index 76ddbc726..000000000
--- a/tools/perf/util/include/linux/list.h
+++ /dev/null
@@ -1,29 +0,0 @@
-#include <linux/kernel.h>
-#include <linux/types.h>
-
-#include "../../../../include/linux/list.h"
-
-#ifndef PERF_LIST_H
-#define PERF_LIST_H
-/**
- * list_del_range - deletes range of entries from list.
- * @begin: first element in the range to delete from the list.
- * @end: last element in the range to delete from the list.
- * Note: list_empty on the range of entries does not return true after this,
- * the entries is in an undefined state.
- */
-static inline void list_del_range(struct list_head *begin,
-				  struct list_head *end)
-{
-	begin->prev->next = end->next;
-	end->next->prev = begin->prev;
-}
-
-/**
- * list_for_each_from	-	iterate over a list from one of its nodes
- * @pos:  the &struct list_head to use as a loop cursor, from where to start
- * @head: the head for your list.
- */
-#define list_for_each_from(pos, head) \
-	for (; pos != (head); pos = pos->next)
-#endif
diff --git a/tools/perf/util/include/linux/poison.h b/tools/perf/util/include/linux/poison.h
deleted file mode 100644
index fef6dbc9c..000000000
--- a/tools/perf/util/include/linux/poison.h
+++ /dev/null
@@ -1 +0,0 @@
-#include "../../../../include/linux/poison.h"
diff --git a/tools/perf/util/include/linux/rbtree.h b/tools/perf/util/include/linux/rbtree.h
deleted file mode 100644
index 2a030c5af..000000000
--- a/tools/perf/util/include/linux/rbtree.h
+++ /dev/null
@@ -1,2 +0,0 @@
-#include <stdbool.h>
-#include "../../../../include/linux/rbtree.h"
diff --git a/tools/perf/util/include/linux/rbtree_augmented.h b/tools/perf/util/include/linux/rbtree_augmented.h
deleted file mode 100644
index 9d6fcdf17..000000000
--- a/tools/perf/util/include/linux/rbtree_augmented.h
+++ /dev/null
@@ -1,2 +0,0 @@
-#include <stdbool.h>
-#include "../../../../include/linux/rbtree_augmented.h"
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 527e032e2..f1a4c8331 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -14,20 +14,23 @@
 #include "unwind.h"
 #include "linux/hash.h"
 
+static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock);
+
 static void dsos__init(struct dsos *dsos)
 {
 	INIT_LIST_HEAD(&dsos->head);
 	dsos->root = RB_ROOT;
+	pthread_rwlock_init(&dsos->lock, NULL);
 }
 
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 {
 	map_groups__init(&machine->kmaps, machine);
 	RB_CLEAR_NODE(&machine->rb_node);
-	dsos__init(&machine->user_dsos);
-	dsos__init(&machine->kernel_dsos);
+	dsos__init(&machine->dsos);
 
 	machine->threads = RB_ROOT;
+	pthread_rwlock_init(&machine->threads_lock, NULL);
 	INIT_LIST_HEAD(&machine->dead_threads);
 	machine->last_match = NULL;
 
@@ -54,6 +57,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 
 		snprintf(comm, sizeof(comm), "[guest/%d]", pid);
 		thread__set_comm(thread, comm, 0);
+		thread__put(thread);
 	}
 
 	machine->current_tid = NULL;
@@ -78,37 +82,50 @@ out_delete:
 	return NULL;
 }
 
-static void dsos__delete(struct dsos *dsos)
+static void dsos__purge(struct dsos *dsos)
 {
 	struct dso *pos, *n;
 
+	pthread_rwlock_wrlock(&dsos->lock);
+
 	list_for_each_entry_safe(pos, n, &dsos->head, node) {
 		RB_CLEAR_NODE(&pos->rb_node);
-		list_del(&pos->node);
-		dso__delete(pos);
+		list_del_init(&pos->node);
+		dso__put(pos);
 	}
+
+	pthread_rwlock_unlock(&dsos->lock);
+}
+
+static void dsos__exit(struct dsos *dsos)
+{
+	dsos__purge(dsos);
+	pthread_rwlock_destroy(&dsos->lock);
 }
 
 void machine__delete_threads(struct machine *machine)
 {
-	struct rb_node *nd = rb_first(&machine->threads);
+	struct rb_node *nd;
 
+	pthread_rwlock_wrlock(&machine->threads_lock);
+	nd = rb_first(&machine->threads);
 	while (nd) {
 		struct thread *t = rb_entry(nd, struct thread, rb_node);
 
 		nd = rb_next(nd);
-		machine__remove_thread(machine, t);
+		__machine__remove_thread(machine, t, false);
 	}
+	pthread_rwlock_unlock(&machine->threads_lock);
 }
 
 void machine__exit(struct machine *machine)
 {
 	map_groups__exit(&machine->kmaps);
-	dsos__delete(&machine->user_dsos);
-	dsos__delete(&machine->kernel_dsos);
-	vdso__exit(machine);
+	dsos__exit(&machine->dsos);
+	machine__exit_vdso(machine);
 	zfree(&machine->root_dir);
 	zfree(&machine->current_tid);
+	pthread_rwlock_destroy(&machine->threads_lock);
 }
 
 void machine__delete(struct machine *machine)
@@ -303,7 +320,7 @@ static void machine__update_thread_pid(struct machine *machine,
 	if (th->pid_ == th->tid)
 		return;
 
-	leader = machine__findnew_thread(machine, th->pid_, th->pid_);
+	leader = __machine__findnew_thread(machine, th->pid_, th->pid_);
 	if (!leader)
 		goto out_err;
 
@@ -325,7 +342,7 @@ static void machine__update_thread_pid(struct machine *machine,
 		if (!map_groups__empty(th->mg))
 			pr_err("Discarding thread maps for %d:%d\n",
 			       th->pid_, th->tid);
-		map_groups__delete(th->mg);
+		map_groups__put(th->mg);
 	}
 
 	th->mg = map_groups__get(leader->mg);
@@ -336,9 +353,9 @@ out_err:
 	pr_err("Failed to join map groups for %d:%d\n", th->pid_, th->tid);
 }
 
-static struct thread *__machine__findnew_thread(struct machine *machine,
-						pid_t pid, pid_t tid,
-						bool create)
+static struct thread *____machine__findnew_thread(struct machine *machine,
+						  pid_t pid, pid_t tid,
+						  bool create)
 {
 	struct rb_node **p = &machine->threads.rb_node;
 	struct rb_node *parent = NULL;
@@ -356,7 +373,7 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
 			return th;
 		}
 
-		thread__zput(machine->last_match);
+		machine->last_match = NULL;
 	}
 
 	while (*p != NULL) {
@@ -364,7 +381,7 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
 		th = rb_entry(parent, struct thread, rb_node);
 
 		if (th->tid == tid) {
-			machine->last_match = thread__get(th);
+			machine->last_match = th;
 			machine__update_thread_pid(machine, th, pid);
 			return th;
 		}
@@ -392,7 +409,8 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
 		 * leader and that would screwed the rb tree.
 		 */
 		if (thread__init_map_groups(th, machine)) {
-			rb_erase(&th->rb_node, &machine->threads);
+			rb_erase_init(&th->rb_node, &machine->threads);
+			RB_CLEAR_NODE(&th->rb_node);
 			thread__delete(th);
 			return NULL;
 		}
@@ -400,22 +418,36 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
 		 * It is now in the rbtree, get a ref
 		 */
 		thread__get(th);
-		machine->last_match = thread__get(th);
+		machine->last_match = th;
 	}
 
 	return th;
 }
 
+struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid)
+{
+	return ____machine__findnew_thread(machine, pid, tid, true);
+}
+
 struct thread *machine__findnew_thread(struct machine *machine, pid_t pid,
 				       pid_t tid)
 {
-	return __machine__findnew_thread(machine, pid, tid, true);
+	struct thread *th;
+
+	pthread_rwlock_wrlock(&machine->threads_lock);
+	th = thread__get(__machine__findnew_thread(machine, pid, tid));
+	pthread_rwlock_unlock(&machine->threads_lock);
+	return th;
 }
 
 struct thread *machine__find_thread(struct machine *machine, pid_t pid,
 				    pid_t tid)
 {
-	return __machine__findnew_thread(machine, pid, tid, false);
+	struct thread *th;
+	pthread_rwlock_rdlock(&machine->threads_lock);
+	th =  thread__get(____machine__findnew_thread(machine, pid, tid, false));
+	pthread_rwlock_unlock(&machine->threads_lock);
+	return th;
 }
 
 struct comm *machine__thread_exec_comm(struct machine *machine,
@@ -434,6 +466,7 @@ int machine__process_comm_event(struct machine *machine, union perf_event *event
 							event->comm.pid,
 							event->comm.tid);
 	bool exec = event->header.misc & PERF_RECORD_MISC_COMM_EXEC;
+	int err = 0;
 
 	if (exec)
 		machine->comm_exec = true;
@@ -444,10 +477,12 @@ int machine__process_comm_event(struct machine *machine, union perf_event *event
 	if (thread == NULL ||
 	    __thread__set_comm(thread, event->comm.comm, sample->time, exec)) {
 		dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n");
-		return -1;
+		err = -1;
 	}
 
-	return 0;
+	thread__put(thread);
+
+	return err;
 }
 
 int machine__process_lost_event(struct machine *machine __maybe_unused,
@@ -458,17 +493,27 @@ int machine__process_lost_event(struct machine *machine __maybe_unused,
 	return 0;
 }
 
-static struct dso*
-machine__module_dso(struct machine *machine, struct kmod_path *m,
-		    const char *filename)
+int machine__process_lost_samples_event(struct machine *machine __maybe_unused,
+					union perf_event *event, struct perf_sample *sample)
+{
+	dump_printf(": id:%" PRIu64 ": lost samples :%" PRIu64 "\n",
+		    sample->id, event->lost_samples.lost);
+	return 0;
+}
+
+static struct dso *machine__findnew_module_dso(struct machine *machine,
+					       struct kmod_path *m,
+					       const char *filename)
 {
 	struct dso *dso;
 
-	dso = dsos__find(&machine->kernel_dsos, m->name, true);
+	pthread_rwlock_wrlock(&machine->dsos.lock);
+
+	dso = __dsos__find(&machine->dsos, m->name, true);
 	if (!dso) {
-		dso = dsos__addnew(&machine->kernel_dsos, m->name);
+		dso = __dsos__addnew(&machine->dsos, m->name);
 		if (dso == NULL)
-			return NULL;
+			goto out_unlock;
 
 		if (machine__is_host(machine))
 			dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
@@ -483,11 +528,30 @@ machine__module_dso(struct machine *machine, struct kmod_path *m,
 		dso__set_long_name(dso, strdup(filename), true);
 	}
 
+	dso__get(dso);
+out_unlock:
+	pthread_rwlock_unlock(&machine->dsos.lock);
 	return dso;
 }
 
-struct map *machine__new_module(struct machine *machine, u64 start,
-				const char *filename)
+int machine__process_aux_event(struct machine *machine __maybe_unused,
+			       union perf_event *event)
+{
+	if (dump_trace)
+		perf_event__fprintf_aux(event, stdout);
+	return 0;
+}
+
+int machine__process_itrace_start_event(struct machine *machine __maybe_unused,
+					union perf_event *event)
+{
+	if (dump_trace)
+		perf_event__fprintf_itrace_start(event, stdout);
+	return 0;
+}
+
+struct map *machine__findnew_module_map(struct machine *machine, u64 start,
+					const char *filename)
 {
 	struct map *map = NULL;
 	struct dso *dso;
@@ -501,7 +565,7 @@ struct map *machine__new_module(struct machine *machine, u64 start,
 	if (map)
 		goto out;
 
-	dso = machine__module_dso(machine, &m, filename);
+	dso = machine__findnew_module_dso(machine, &m, filename);
 	if (dso == NULL)
 		goto out;
 
@@ -519,13 +583,11 @@ out:
 size_t machines__fprintf_dsos(struct machines *machines, FILE *fp)
 {
 	struct rb_node *nd;
-	size_t ret = __dsos__fprintf(&machines->host.kernel_dsos.head, fp) +
-		     __dsos__fprintf(&machines->host.user_dsos.head, fp);
+	size_t ret = __dsos__fprintf(&machines->host.dsos.head, fp);
 
 	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
-		ret += __dsos__fprintf(&pos->kernel_dsos.head, fp);
-		ret += __dsos__fprintf(&pos->user_dsos.head, fp);
+		ret += __dsos__fprintf(&pos->dsos.head, fp);
 	}
 
 	return ret;
@@ -534,8 +596,7 @@ size_t machines__fprintf_dsos(struct machines *machines, FILE *fp)
 size_t machine__fprintf_dsos_buildid(struct machine *m, FILE *fp,
 				     bool (skip)(struct dso *dso, int parm), int parm)
 {
-	return __dsos__fprintf_buildid(&m->kernel_dsos.head, fp, skip, parm) +
-	       __dsos__fprintf_buildid(&m->user_dsos.head, fp, skip, parm);
+	return __dsos__fprintf_buildid(&m->dsos.head, fp, skip, parm);
 }
 
 size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp,
@@ -575,12 +636,16 @@ size_t machine__fprintf(struct machine *machine, FILE *fp)
 	size_t ret = 0;
 	struct rb_node *nd;
 
+	pthread_rwlock_rdlock(&machine->threads_lock);
+
 	for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) {
 		struct thread *pos = rb_entry(nd, struct thread, rb_node);
 
 		ret += thread__fprintf(pos, fp);
 	}
 
+	pthread_rwlock_unlock(&machine->threads_lock);
+
 	return ret;
 }
 
@@ -594,9 +659,8 @@ static struct dso *machine__get_kernel(struct machine *machine)
 		if (!vmlinux_name)
 			vmlinux_name = "[kernel.kallsyms]";
 
-		kernel = dso__kernel_findnew(machine, vmlinux_name,
-					     "[kernel]",
-					     DSO_TYPE_KERNEL);
+		kernel = machine__findnew_kernel(machine, vmlinux_name,
+						 "[kernel]", DSO_TYPE_KERNEL);
 	} else {
 		char bf[PATH_MAX];
 
@@ -606,9 +670,9 @@ static struct dso *machine__get_kernel(struct machine *machine)
 			vmlinux_name = machine__mmap_name(machine, bf,
 							  sizeof(bf));
 
-		kernel = dso__kernel_findnew(machine, vmlinux_name,
-					     "[guest.kernel]",
-					     DSO_TYPE_GUEST_KERNEL);
+		kernel = machine__findnew_kernel(machine, vmlinux_name,
+						 "[guest.kernel]",
+						 DSO_TYPE_GUEST_KERNEL);
 	}
 
 	if (kernel != NULL && (!kernel->has_build_id))
@@ -713,7 +777,6 @@ void machine__destroy_kernel_maps(struct machine *machine)
 				kmap->ref_reloc_sym = NULL;
 		}
 
-		map__delete(machine->vmlinux_maps[type]);
 		machine->vmlinux_maps[type] = NULL;
 	}
 }
@@ -970,7 +1033,7 @@ static int machine__create_module(void *arg, const char *name, u64 start)
 	struct machine *machine = arg;
 	struct map *map;
 
-	map = machine__new_module(machine, start, name);
+	map = machine__findnew_module_map(machine, start, name);
 	if (map == NULL)
 		return -1;
 
@@ -1062,7 +1125,7 @@ static bool machine__uses_kcore(struct machine *machine)
 {
 	struct dso *dso;
 
-	list_for_each_entry(dso, &machine->kernel_dsos.head, node) {
+	list_for_each_entry(dso, &machine->dsos.head, node) {
 		if (dso__is_kcore(dso))
 			return true;
 	}
@@ -1093,8 +1156,8 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 				strlen(kmmap_prefix) - 1) == 0;
 	if (event->mmap.filename[0] == '/' ||
 	    (!is_kernel_mmap && event->mmap.filename[0] == '[')) {
-		map = machine__new_module(machine, event->mmap.start,
-					  event->mmap.filename);
+		map = machine__findnew_module_map(machine, event->mmap.start,
+						  event->mmap.filename);
 		if (map == NULL)
 			goto out_problem;
 
@@ -1109,23 +1172,48 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		struct dso *kernel = NULL;
 		struct dso *dso;
 
-		list_for_each_entry(dso, &machine->kernel_dsos.head, node) {
-			if (is_kernel_module(dso->long_name))
+		pthread_rwlock_rdlock(&machine->dsos.lock);
+
+		list_for_each_entry(dso, &machine->dsos.head, node) {
+
+			/*
+			 * The cpumode passed to is_kernel_module is not the
+			 * cpumode of *this* event. If we insist on passing
+			 * correct cpumode to is_kernel_module, we should
+			 * record the cpumode when we adding this dso to the
+			 * linked list.
+			 *
+			 * However we don't really need passing correct
+			 * cpumode.  We know the correct cpumode must be kernel
+			 * mode (if not, we should not link it onto kernel_dsos
+			 * list).
+			 *
+			 * Therefore, we pass PERF_RECORD_MISC_CPUMODE_UNKNOWN.
+			 * is_kernel_module() treats it as a kernel cpumode.
+			 */
+
+			if (!dso->kernel ||
+			    is_kernel_module(dso->long_name,
+					     PERF_RECORD_MISC_CPUMODE_UNKNOWN))
 				continue;
 
+
 			kernel = dso;
 			break;
 		}
 
+		pthread_rwlock_unlock(&machine->dsos.lock);
+
 		if (kernel == NULL)
-			kernel = __dsos__findnew(&machine->kernel_dsos,
-						 kmmap_prefix);
+			kernel = machine__findnew_dso(machine, kmmap_prefix);
 		if (kernel == NULL)
 			goto out_problem;
 
 		kernel->kernel = kernel_type;
-		if (__machine__create_kernel_maps(machine, kernel) < 0)
+		if (__machine__create_kernel_maps(machine, kernel) < 0) {
+			dso__put(kernel);
 			goto out_problem;
+		}
 
 		if (strstr(kernel->long_name, "vmlinux"))
 			dso__set_short_name(kernel, "[kernel.vmlinux]", false);
@@ -1197,11 +1285,15 @@ int machine__process_mmap2_event(struct machine *machine,
 			event->mmap2.filename, type, thread);
 
 	if (map == NULL)
-		goto out_problem;
+		goto out_problem_map;
 
 	thread__insert_map(thread, map);
+	thread__put(thread);
+	map__put(map);
 	return 0;
 
+out_problem_map:
+	thread__put(thread);
 out_problem:
 	dump_printf("problem processing PERF_RECORD_MMAP2, skipping event.\n");
 	return 0;
@@ -1244,31 +1336,46 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 			type, thread);
 
 	if (map == NULL)
-		goto out_problem;
+		goto out_problem_map;
 
 	thread__insert_map(thread, map);
+	thread__put(thread);
+	map__put(map);
 	return 0;
 
+out_problem_map:
+	thread__put(thread);
 out_problem:
 	dump_printf("problem processing PERF_RECORD_MMAP, skipping event.\n");
 	return 0;
 }
 
-void machine__remove_thread(struct machine *machine, struct thread *th)
+static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock)
 {
 	if (machine->last_match == th)
-		thread__zput(machine->last_match);
+		machine->last_match = NULL;
 
-	rb_erase(&th->rb_node, &machine->threads);
+	BUG_ON(atomic_read(&th->refcnt) == 0);
+	if (lock)
+		pthread_rwlock_wrlock(&machine->threads_lock);
+	rb_erase_init(&th->rb_node, &machine->threads);
+	RB_CLEAR_NODE(&th->rb_node);
 	/*
 	 * Move it first to the dead_threads list, then drop the reference,
 	 * if this is the last reference, then the thread__delete destructor
 	 * will be called and we will remove it from the dead_threads list.
 	 */
 	list_add_tail(&th->node, &machine->dead_threads);
+	if (lock)
+		pthread_rwlock_unlock(&machine->threads_lock);
 	thread__put(th);
 }
 
+void machine__remove_thread(struct machine *machine, struct thread *th)
+{
+	return __machine__remove_thread(machine, th, true);
+}
+
 int machine__process_fork_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample)
 {
@@ -1278,23 +1385,44 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 	struct thread *parent = machine__findnew_thread(machine,
 							event->fork.ppid,
 							event->fork.ptid);
+	int err = 0;
+
+	if (dump_trace)
+		perf_event__fprintf_task(event, stdout);
+
+	/*
+	 * There may be an existing thread that is not actually the parent,
+	 * either because we are processing events out of order, or because the
+	 * (fork) event that would have removed the thread was lost. Assume the
+	 * latter case and continue on as best we can.
+	 */
+	if (parent->pid_ != (pid_t)event->fork.ppid) {
+		dump_printf("removing erroneous parent thread %d/%d\n",
+			    parent->pid_, parent->tid);
+		machine__remove_thread(machine, parent);
+		thread__put(parent);
+		parent = machine__findnew_thread(machine, event->fork.ppid,
+						 event->fork.ptid);
+	}
 
 	/* if a thread currently exists for the thread id remove it */
-	if (thread != NULL)
+	if (thread != NULL) {
 		machine__remove_thread(machine, thread);
+		thread__put(thread);
+	}
 
 	thread = machine__findnew_thread(machine, event->fork.pid,
 					 event->fork.tid);
-	if (dump_trace)
-		perf_event__fprintf_task(event, stdout);
 
 	if (thread == NULL || parent == NULL ||
 	    thread__fork(thread, parent, sample->time) < 0) {
 		dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n");
-		return -1;
+		err = -1;
 	}
+	thread__put(thread);
+	thread__put(parent);
 
-	return 0;
+	return err;
 }
 
 int machine__process_exit_event(struct machine *machine, union perf_event *event,
@@ -1307,8 +1435,10 @@ int machine__process_exit_event(struct machine *machine, union perf_event *event
 	if (dump_trace)
 		perf_event__fprintf_task(event, stdout);
 
-	if (thread != NULL)
+	if (thread != NULL) {
 		thread__exited(thread);
+		thread__put(thread);
+	}
 
 	return 0;
 }
@@ -1331,6 +1461,12 @@ int machine__process_event(struct machine *machine, union perf_event *event,
 		ret = machine__process_exit_event(machine, event, sample); break;
 	case PERF_RECORD_LOST:
 		ret = machine__process_lost_event(machine, event, sample); break;
+	case PERF_RECORD_AUX:
+		ret = machine__process_aux_event(machine, event); break;
+	case PERF_RECORD_ITRACE_START:
+		ret = machine__process_itrace_start_event(machine, event); break;
+	case PERF_RECORD_LOST_SAMPLES:
+		ret = machine__process_lost_samples_event(machine, event, sample); break;
 	default:
 		ret = -1;
 		break;
@@ -1769,14 +1905,36 @@ int machine__for_each_thread(struct machine *machine,
 	return rc;
 }
 
+int machines__for_each_thread(struct machines *machines,
+			      int (*fn)(struct thread *thread, void *p),
+			      void *priv)
+{
+	struct rb_node *nd;
+	int rc = 0;
+
+	rc = machine__for_each_thread(&machines->host, fn, priv);
+	if (rc != 0)
+		return rc;
+
+	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+		struct machine *machine = rb_entry(nd, struct machine, rb_node);
+
+		rc = machine__for_each_thread(machine, fn, priv);
+		if (rc != 0)
+			return rc;
+	}
+	return rc;
+}
+
 int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
 				  struct target *target, struct thread_map *threads,
-				  perf_event__handler_t process, bool data_mmap)
+				  perf_event__handler_t process, bool data_mmap,
+				  unsigned int proc_map_timeout)
 {
 	if (target__has_task(target))
-		return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap);
+		return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap, proc_map_timeout);
 	else if (target__has_cpu(target))
-		return perf_event__synthesize_threads(tool, process, machine, data_mmap);
+		return perf_event__synthesize_threads(tool, process, machine, data_mmap, proc_map_timeout);
 	/* command specified */
 	return 0;
 }
@@ -1820,6 +1978,7 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
 		return -ENOMEM;
 
 	thread->cpu = cpu;
+	thread__put(thread);
 
 	return 0;
 }
@@ -1845,3 +2004,8 @@ int machine__get_kernel_start(struct machine *machine)
 	}
 	return err;
 }
+
+struct dso *machine__findnew_dso(struct machine *machine, const char *filename)
+{
+	return dsos__findnew(&machine->dsos, filename);
+}
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 6d64cedb9..887798e51 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -30,11 +30,11 @@ struct machine {
 	bool		  comm_exec;
 	char		  *root_dir;
 	struct rb_root	  threads;
+	pthread_rwlock_t  threads_lock;
 	struct list_head  dead_threads;
 	struct thread	  *last_match;
 	struct vdso_info  *vdso_info;
-	struct dsos	  user_dsos;
-	struct dsos	  kernel_dsos;
+	struct dsos	  dsos;
 	struct map_groups kmaps;
 	struct map	  *vmlinux_maps[MAP__NR_TYPES];
 	u64		  kernel_start;
@@ -81,6 +81,12 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 				struct perf_sample *sample);
 int machine__process_lost_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample);
+int machine__process_lost_samples_event(struct machine *machine, union perf_event *event,
+					struct perf_sample *sample);
+int machine__process_aux_event(struct machine *machine,
+			       union perf_event *event);
+int machine__process_itrace_start_event(struct machine *machine,
+					union perf_event *event);
 int machine__process_mmap_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample);
 int machine__process_mmap2_event(struct machine *machine, union perf_event *event,
@@ -147,8 +153,10 @@ static inline bool machine__is_host(struct machine *machine)
 	return machine ? machine->pid == HOST_KERNEL_ID : false;
 }
 
-struct thread *machine__findnew_thread(struct machine *machine, pid_t pid,
-				       pid_t tid);
+struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
+struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
+
+struct dso *machine__findnew_dso(struct machine *machine, const char *filename);
 
 size_t machine__fprintf(struct machine *machine, FILE *fp);
 
@@ -181,8 +189,8 @@ struct symbol *machine__find_kernel_function_by_name(struct machine *machine,
 						 filter);
 }
 
-struct map *machine__new_module(struct machine *machine, u64 start,
-				const char *filename);
+struct map *machine__findnew_module_map(struct machine *machine, u64 start,
+					const char *filename);
 
 int machine__load_kallsyms(struct machine *machine, const char *filename,
 			   enum map_type type, symbol_filter_t filter);
@@ -208,16 +216,22 @@ size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp);
 int machine__for_each_thread(struct machine *machine,
 			     int (*fn)(struct thread *thread, void *p),
 			     void *priv);
+int machines__for_each_thread(struct machines *machines,
+			      int (*fn)(struct thread *thread, void *p),
+			      void *priv);
 
 int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
 				  struct target *target, struct thread_map *threads,
-				  perf_event__handler_t process, bool data_mmap);
+				  perf_event__handler_t process, bool data_mmap,
+				  unsigned int proc_map_timeout);
 static inline
 int machine__synthesize_threads(struct machine *machine, struct target *target,
-				struct thread_map *threads, bool data_mmap)
+				struct thread_map *threads, bool data_mmap,
+				unsigned int proc_map_timeout)
 {
 	return __machine__synthesize_threads(machine, NULL, target, threads,
-					     perf_event__process, data_mmap);
+					     perf_event__process, data_mmap,
+					     proc_map_timeout);
 }
 
 pid_t machine__get_current_tid(struct machine *machine, int cpu);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index a14f08f41..b5a5e9c02 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -16,6 +16,8 @@
 #include "machine.h"
 #include <linux/string.h>
 
+static void __maps__insert(struct maps *maps, struct map *map);
+
 const char *map_type__name[MAP__NR_TYPES] = {
 	[MAP__FUNCTION] = "Functions",
 	[MAP__VARIABLE] = "Variables",
@@ -130,13 +132,13 @@ void map__init(struct map *map, enum map_type type,
 	map->end      = end;
 	map->pgoff    = pgoff;
 	map->reloc    = 0;
-	map->dso      = dso;
+	map->dso      = dso__get(dso);
 	map->map_ip   = map__map_ip;
 	map->unmap_ip = map__unmap_ip;
 	RB_CLEAR_NODE(&map->rb_node);
 	map->groups   = NULL;
-	map->referenced = false;
 	map->erange_warned = false;
+	atomic_set(&map->refcnt, 1);
 }
 
 struct map *map__new(struct machine *machine, u64 start, u64 len,
@@ -175,9 +177,9 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 
 		if (vdso) {
 			pgoff = 0;
-			dso = vdso__dso_findnew(machine, thread);
+			dso = machine__findnew_vdso(machine, thread);
 		} else
-			dso = __dsos__findnew(&machine->user_dsos, filename);
+			dso = machine__findnew_dso(machine, filename);
 
 		if (dso == NULL)
 			goto out_delete;
@@ -195,6 +197,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 			if (type != MAP__FUNCTION)
 				dso__set_loaded(dso, map->type);
 		}
+		dso__put(dso);
 	}
 	return map;
 out_delete:
@@ -221,11 +224,24 @@ struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
 	return map;
 }
 
+static void map__exit(struct map *map)
+{
+	BUG_ON(!RB_EMPTY_NODE(&map->rb_node));
+	dso__zput(map->dso);
+}
+
 void map__delete(struct map *map)
 {
+	map__exit(map);
 	free(map);
 }
 
+void map__put(struct map *map)
+{
+	if (map && atomic_dec_and_test(&map->refcnt))
+		map__delete(map);
+}
+
 void map__fixup_start(struct map *map)
 {
 	struct rb_root *symbols = &map->dso->symbols[map->type];
@@ -292,6 +308,11 @@ int map__load(struct map *map, symbol_filter_t filter)
 	return 0;
 }
 
+int __weak arch__compare_symbol_names(const char *namea, const char *nameb)
+{
+	return strcmp(namea, nameb);
+}
+
 struct symbol *map__find_symbol(struct map *map, u64 addr,
 				symbol_filter_t filter)
 {
@@ -413,48 +434,49 @@ u64 map__objdump_2mem(struct map *map, u64 ip)
 	return ip + map->reloc;
 }
 
+static void maps__init(struct maps *maps)
+{
+	maps->entries = RB_ROOT;
+	pthread_rwlock_init(&maps->lock, NULL);
+}
+
 void map_groups__init(struct map_groups *mg, struct machine *machine)
 {
 	int i;
 	for (i = 0; i < MAP__NR_TYPES; ++i) {
-		mg->maps[i] = RB_ROOT;
-		INIT_LIST_HEAD(&mg->removed_maps[i]);
+		maps__init(&mg->maps[i]);
 	}
 	mg->machine = machine;
-	mg->refcnt = 1;
+	atomic_set(&mg->refcnt, 1);
 }
 
-static void maps__delete(struct rb_root *maps)
+static void __maps__purge(struct maps *maps)
 {
-	struct rb_node *next = rb_first(maps);
+	struct rb_root *root = &maps->entries;
+	struct rb_node *next = rb_first(root);
 
 	while (next) {
 		struct map *pos = rb_entry(next, struct map, rb_node);
 
 		next = rb_next(&pos->rb_node);
-		rb_erase(&pos->rb_node, maps);
-		map__delete(pos);
+		rb_erase_init(&pos->rb_node, root);
+		map__put(pos);
 	}
 }
 
-static void maps__delete_removed(struct list_head *maps)
+static void maps__exit(struct maps *maps)
 {
-	struct map *pos, *n;
-
-	list_for_each_entry_safe(pos, n, maps, node) {
-		list_del(&pos->node);
-		map__delete(pos);
-	}
+	pthread_rwlock_wrlock(&maps->lock);
+	__maps__purge(maps);
+	pthread_rwlock_unlock(&maps->lock);
 }
 
 void map_groups__exit(struct map_groups *mg)
 {
 	int i;
 
-	for (i = 0; i < MAP__NR_TYPES; ++i) {
-		maps__delete(&mg->maps[i]);
-		maps__delete_removed(&mg->removed_maps[i]);
-	}
+	for (i = 0; i < MAP__NR_TYPES; ++i)
+		maps__exit(&mg->maps[i]);
 }
 
 bool map_groups__empty(struct map_groups *mg)
@@ -464,8 +486,6 @@ bool map_groups__empty(struct map_groups *mg)
 	for (i = 0; i < MAP__NR_TYPES; ++i) {
 		if (maps__first(&mg->maps[i]))
 			return false;
-		if (!list_empty(&mg->removed_maps[i]))
-			return false;
 	}
 
 	return true;
@@ -489,32 +509,10 @@ void map_groups__delete(struct map_groups *mg)
 
 void map_groups__put(struct map_groups *mg)
 {
-	if (--mg->refcnt == 0)
+	if (mg && atomic_dec_and_test(&mg->refcnt))
 		map_groups__delete(mg);
 }
 
-void map_groups__flush(struct map_groups *mg)
-{
-	int type;
-
-	for (type = 0; type < MAP__NR_TYPES; type++) {
-		struct rb_root *root = &mg->maps[type];
-		struct rb_node *next = rb_first(root);
-
-		while (next) {
-			struct map *pos = rb_entry(next, struct map, rb_node);
-			next = rb_next(&pos->rb_node);
-			rb_erase(&pos->rb_node, root);
-			/*
-			 * We may have references to this map, for
-			 * instance in some hist_entry instances, so
-			 * just move them to a separate list.
-			 */
-			list_add_tail(&pos->node, &mg->removed_maps[pos->type]);
-		}
-	}
-}
-
 struct symbol *map_groups__find_symbol(struct map_groups *mg,
 				       enum map_type type, u64 addr,
 				       struct map **mapp,
@@ -538,20 +536,28 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
 					       struct map **mapp,
 					       symbol_filter_t filter)
 {
+	struct maps *maps = &mg->maps[type];
+	struct symbol *sym;
 	struct rb_node *nd;
 
-	for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) {
+	pthread_rwlock_rdlock(&maps->lock);
+
+	for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) {
 		struct map *pos = rb_entry(nd, struct map, rb_node);
-		struct symbol *sym = map__find_symbol_by_name(pos, name, filter);
+
+		sym = map__find_symbol_by_name(pos, name, filter);
 
 		if (sym == NULL)
 			continue;
 		if (mapp != NULL)
 			*mapp = pos;
-		return sym;
+		goto out;
 	}
 
-	return NULL;
+	sym = NULL;
+out:
+	pthread_rwlock_unlock(&maps->lock);
+	return sym;
 }
 
 int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter)
@@ -571,73 +577,54 @@ int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter)
 	return ams->sym ? 0 : -1;
 }
 
-size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type,
-				  FILE *fp)
+static size_t maps__fprintf(struct maps *maps, FILE *fp)
 {
-	size_t printed = fprintf(fp, "%s:\n", map_type__name[type]);
+	size_t printed = 0;
 	struct rb_node *nd;
 
-	for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) {
+	pthread_rwlock_rdlock(&maps->lock);
+
+	for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) {
 		struct map *pos = rb_entry(nd, struct map, rb_node);
 		printed += fprintf(fp, "Map:");
 		printed += map__fprintf(pos, fp);
 		if (verbose > 2) {
-			printed += dso__fprintf(pos->dso, type, fp);
+			printed += dso__fprintf(pos->dso, pos->type, fp);
 			printed += fprintf(fp, "--\n");
 		}
 	}
 
-	return printed;
-}
+	pthread_rwlock_unlock(&maps->lock);
 
-static size_t map_groups__fprintf_maps(struct map_groups *mg, FILE *fp)
-{
-	size_t printed = 0, i;
-	for (i = 0; i < MAP__NR_TYPES; ++i)
-		printed += __map_groups__fprintf_maps(mg, i, fp);
 	return printed;
 }
 
-static size_t __map_groups__fprintf_removed_maps(struct map_groups *mg,
-						 enum map_type type, FILE *fp)
+size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type,
+				  FILE *fp)
 {
-	struct map *pos;
-	size_t printed = 0;
-
-	list_for_each_entry(pos, &mg->removed_maps[type], node) {
-		printed += fprintf(fp, "Map:");
-		printed += map__fprintf(pos, fp);
-		if (verbose > 1) {
-			printed += dso__fprintf(pos->dso, type, fp);
-			printed += fprintf(fp, "--\n");
-		}
-	}
-	return printed;
+	size_t printed = fprintf(fp, "%s:\n", map_type__name[type]);
+	return printed += maps__fprintf(&mg->maps[type], fp);
 }
 
-static size_t map_groups__fprintf_removed_maps(struct map_groups *mg,
-					       FILE *fp)
+size_t map_groups__fprintf(struct map_groups *mg, FILE *fp)
 {
 	size_t printed = 0, i;
 	for (i = 0; i < MAP__NR_TYPES; ++i)
-		printed += __map_groups__fprintf_removed_maps(mg, i, fp);
+		printed += __map_groups__fprintf_maps(mg, i, fp);
 	return printed;
 }
 
-size_t map_groups__fprintf(struct map_groups *mg, FILE *fp)
+static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
 {
-	size_t printed = map_groups__fprintf_maps(mg, fp);
-	printed += fprintf(fp, "Removed maps:\n");
-	return printed + map_groups__fprintf_removed_maps(mg, fp);
-}
-
-int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
-				   FILE *fp)
-{
-	struct rb_root *root = &mg->maps[map->type];
-	struct rb_node *next = rb_first(root);
+	struct rb_root *root;
+	struct rb_node *next;
 	int err = 0;
 
+	pthread_rwlock_wrlock(&maps->lock);
+
+	root = &maps->entries;
+	next = rb_first(root);
+
 	while (next) {
 		struct map *pos = rb_entry(next, struct map, rb_node);
 		next = rb_next(&pos->rb_node);
@@ -651,7 +638,7 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 			map__fprintf(pos, fp);
 		}
 
-		rb_erase(&pos->rb_node, root);
+		rb_erase_init(&pos->rb_node, root);
 		/*
 		 * Now check if we need to create new maps for areas not
 		 * overlapped by the new map:
@@ -661,11 +648,11 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 
 			if (before == NULL) {
 				err = -ENOMEM;
-				goto move_map;
+				goto put_map;
 			}
 
 			before->end = map->start;
-			map_groups__insert(mg, before);
+			__maps__insert(maps, before);
 			if (verbose >= 2)
 				map__fprintf(before, fp);
 		}
@@ -675,28 +662,31 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 
 			if (after == NULL) {
 				err = -ENOMEM;
-				goto move_map;
+				goto put_map;
 			}
 
 			after->start = map->end;
-			map_groups__insert(mg, after);
+			__maps__insert(maps, after);
 			if (verbose >= 2)
 				map__fprintf(after, fp);
 		}
-move_map:
-		/*
-		 * If we have references, just move them to a separate list.
-		 */
-		if (pos->referenced)
-			list_add_tail(&pos->node, &mg->removed_maps[map->type]);
-		else
-			map__delete(pos);
+put_map:
+		map__put(pos);
 
 		if (err)
-			return err;
+			goto out;
 	}
 
-	return 0;
+	err = 0;
+out:
+	pthread_rwlock_unlock(&maps->lock);
+	return err;
+}
+
+int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
+				   FILE *fp)
+{
+	return maps__fixup_overlappings(&mg->maps[map->type], map, fp);
 }
 
 /*
@@ -705,20 +695,28 @@ move_map:
 int map_groups__clone(struct map_groups *mg,
 		      struct map_groups *parent, enum map_type type)
 {
-	struct rb_node *nd;
-	for (nd = rb_first(&parent->maps[type]); nd; nd = rb_next(nd)) {
-		struct map *map = rb_entry(nd, struct map, rb_node);
+	int err = -ENOMEM;
+	struct map *map;
+	struct maps *maps = &parent->maps[type];
+
+	pthread_rwlock_rdlock(&maps->lock);
+
+	for (map = maps__first(maps); map; map = map__next(map)) {
 		struct map *new = map__clone(map);
 		if (new == NULL)
-			return -ENOMEM;
+			goto out_unlock;
 		map_groups__insert(mg, new);
 	}
-	return 0;
+
+	err = 0;
+out_unlock:
+	pthread_rwlock_unlock(&maps->lock);
+	return err;
 }
 
-void maps__insert(struct rb_root *maps, struct map *map)
+static void __maps__insert(struct maps *maps, struct map *map)
 {
-	struct rb_node **p = &maps->rb_node;
+	struct rb_node **p = &maps->entries.rb_node;
 	struct rb_node *parent = NULL;
 	const u64 ip = map->start;
 	struct map *m;
@@ -733,20 +731,38 @@ void maps__insert(struct rb_root *maps, struct map *map)
 	}
 
 	rb_link_node(&map->rb_node, parent, p);
-	rb_insert_color(&map->rb_node, maps);
+	rb_insert_color(&map->rb_node, &maps->entries);
+	map__get(map);
 }
 
-void maps__remove(struct rb_root *maps, struct map *map)
+void maps__insert(struct maps *maps, struct map *map)
 {
-	rb_erase(&map->rb_node, maps);
+	pthread_rwlock_wrlock(&maps->lock);
+	__maps__insert(maps, map);
+	pthread_rwlock_unlock(&maps->lock);
 }
 
-struct map *maps__find(struct rb_root *maps, u64 ip)
+static void __maps__remove(struct maps *maps, struct map *map)
 {
-	struct rb_node **p = &maps->rb_node;
-	struct rb_node *parent = NULL;
+	rb_erase_init(&map->rb_node, &maps->entries);
+	map__put(map);
+}
+
+void maps__remove(struct maps *maps, struct map *map)
+{
+	pthread_rwlock_wrlock(&maps->lock);
+	__maps__remove(maps, map);
+	pthread_rwlock_unlock(&maps->lock);
+}
+
+struct map *maps__find(struct maps *maps, u64 ip)
+{
+	struct rb_node **p, *parent = NULL;
 	struct map *m;
 
+	pthread_rwlock_rdlock(&maps->lock);
+
+	p = &maps->entries.rb_node;
 	while (*p != NULL) {
 		parent = *p;
 		m = rb_entry(parent, struct map, rb_node);
@@ -755,22 +771,25 @@ struct map *maps__find(struct rb_root *maps, u64 ip)
 		else if (ip >= m->end)
 			p = &(*p)->rb_right;
 		else
-			return m;
+			goto out;
 	}
 
-	return NULL;
+	m = NULL;
+out:
+	pthread_rwlock_unlock(&maps->lock);
+	return m;
 }
 
-struct map *maps__first(struct rb_root *maps)
+struct map *maps__first(struct maps *maps)
 {
-	struct rb_node *first = rb_first(maps);
+	struct rb_node *first = rb_first(&maps->entries);
 
 	if (first)
 		return rb_entry(first, struct map, rb_node);
 	return NULL;
 }
 
-struct map *maps__next(struct map *map)
+struct map *map__next(struct map *map)
 {
 	struct rb_node *next = rb_next(&map->rb_node);
 
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index ec19c59ca..d73e687b2 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -1,9 +1,11 @@
 #ifndef __PERF_MAP_H
 #define __PERF_MAP_H
 
+#include <linux/atomic.h>
 #include <linux/compiler.h>
 #include <linux/list.h>
 #include <linux/rbtree.h>
+#include <pthread.h>
 #include <stdio.h>
 #include <stdbool.h>
 #include <linux/types.h>
@@ -32,7 +34,6 @@ struct map {
 	u64			start;
 	u64			end;
 	u8 /* enum map_type */	type;
-	bool			referenced;
 	bool			erange_warned;
 	u32			priv;
 	u32			prot;
@@ -50,6 +51,7 @@ struct map {
 
 	struct dso		*dso;
 	struct map_groups	*groups;
+	atomic_t		refcnt;
 };
 
 struct kmap {
@@ -57,11 +59,15 @@ struct kmap {
 	struct map_groups	*kmaps;
 };
 
+struct maps {
+	struct rb_root	 entries;
+	pthread_rwlock_t lock;
+};
+
 struct map_groups {
-	struct rb_root	 maps[MAP__NR_TYPES];
-	struct list_head removed_maps[MAP__NR_TYPES];
+	struct maps	 maps[MAP__NR_TYPES];
 	struct machine	 *machine;
-	int		 refcnt;
+	atomic_t	 refcnt;
 };
 
 struct map_groups *map_groups__new(struct machine *machine);
@@ -70,7 +76,8 @@ bool map_groups__empty(struct map_groups *mg);
 
 static inline struct map_groups *map_groups__get(struct map_groups *mg)
 {
-	++mg->refcnt;
+	if (mg)
+		atomic_inc(&mg->refcnt);
 	return mg;
 }
 
@@ -124,7 +131,7 @@ struct thread;
  */
 #define __map__for_each_symbol_by_name(map, sym_name, pos, filter)	\
 	for (pos = map__find_symbol_by_name(map, sym_name, filter);	\
-	     pos && strcmp(pos->name, sym_name) == 0;		\
+	     pos && arch__compare_symbol_names(pos->name, sym_name) == 0;	\
 	     pos = symbol__next_by_name(pos))
 
 #define map__for_each_symbol_by_name(map, sym_name, pos)		\
@@ -132,6 +139,7 @@ struct thread;
 
 typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
 
+int arch__compare_symbol_names(const char *namea, const char *nameb);
 void map__init(struct map *map, enum map_type type,
 	       u64 start, u64 end, u64 pgoff, struct dso *dso);
 struct map *map__new(struct machine *machine, u64 start, u64 len,
@@ -141,6 +149,24 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
 void map__delete(struct map *map);
 struct map *map__clone(struct map *map);
+
+static inline struct map *map__get(struct map *map)
+{
+	if (map)
+		atomic_inc(&map->refcnt);
+	return map;
+}
+
+void map__put(struct map *map);
+
+static inline void __map__zput(struct map **map)
+{
+	map__put(*map);
+	*map = NULL;
+}
+
+#define map__zput(map) __map__zput(&map)
+
 int map__overlap(struct map *l, struct map *r);
 size_t map__fprintf(struct map *map, FILE *fp);
 size_t map__fprintf_dsoname(struct map *map, FILE *fp);
@@ -159,11 +185,11 @@ void map__reloc_vmlinux(struct map *map);
 
 size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type,
 				  FILE *fp);
-void maps__insert(struct rb_root *maps, struct map *map);
-void maps__remove(struct rb_root *maps, struct map *map);
-struct map *maps__find(struct rb_root *maps, u64 addr);
-struct map *maps__first(struct rb_root *maps);
-struct map *maps__next(struct map *map);
+void maps__insert(struct maps *maps, struct map *map);
+void maps__remove(struct maps *maps, struct map *map);
+struct map *maps__find(struct maps *maps, u64 addr);
+struct map *maps__first(struct maps *maps);
+struct map *map__next(struct map *map);
 void map_groups__init(struct map_groups *mg, struct machine *machine);
 void map_groups__exit(struct map_groups *mg);
 int map_groups__clone(struct map_groups *mg,
@@ -198,7 +224,7 @@ static inline struct map *map_groups__first(struct map_groups *mg,
 
 static inline struct map *map_groups__next(struct map *map)
 {
-	return maps__next(map);
+	return map__next(map);
 }
 
 struct symbol *map_groups__find_symbol(struct map_groups *mg,
@@ -230,6 +256,4 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 struct map *map_groups__find_by_name(struct map_groups *mg,
 				     enum map_type type, const char *name);
 
-void map_groups__flush(struct map_groups *mg);
-
 #endif /* __PERF_MAP_H */
diff --git a/tools/perf/util/pager.c b/tools/perf/util/pager.c
index 31ee02d4e..53ef006a9 100644
--- a/tools/perf/util/pager.c
+++ b/tools/perf/util/pager.c
@@ -50,11 +50,6 @@ void setup_pager(void)
 
 	if (!isatty(1))
 		return;
-	if (!pager) {
-		if (!pager_program)
-			perf_config(perf_default_config, NULL);
-		pager = pager_program;
-	}
 	if (!pager)
 		pager = getenv("PAGER");
 	if (!(pager || access("/usr/bin/pager", X_OK)))
diff --git a/tools/perf/util/parse-branch-options.c b/tools/perf/util/parse-branch-options.c
new file mode 100644
index 000000000..a3b1e13a0
--- /dev/null
+++ b/tools/perf/util/parse-branch-options.c
@@ -0,0 +1,94 @@
+#include "perf.h"
+#include "util/util.h"
+#include "util/debug.h"
+#include "util/parse-options.h"
+#include "util/parse-branch-options.h"
+
+#define BRANCH_OPT(n, m) \
+	{ .name = n, .mode = (m) }
+
+#define BRANCH_END { .name = NULL }
+
+struct branch_mode {
+	const char *name;
+	int mode;
+};
+
+static const struct branch_mode branch_modes[] = {
+	BRANCH_OPT("u", PERF_SAMPLE_BRANCH_USER),
+	BRANCH_OPT("k", PERF_SAMPLE_BRANCH_KERNEL),
+	BRANCH_OPT("hv", PERF_SAMPLE_BRANCH_HV),
+	BRANCH_OPT("any", PERF_SAMPLE_BRANCH_ANY),
+	BRANCH_OPT("any_call", PERF_SAMPLE_BRANCH_ANY_CALL),
+	BRANCH_OPT("any_ret", PERF_SAMPLE_BRANCH_ANY_RETURN),
+	BRANCH_OPT("ind_call", PERF_SAMPLE_BRANCH_IND_CALL),
+	BRANCH_OPT("abort_tx", PERF_SAMPLE_BRANCH_ABORT_TX),
+	BRANCH_OPT("in_tx", PERF_SAMPLE_BRANCH_IN_TX),
+	BRANCH_OPT("no_tx", PERF_SAMPLE_BRANCH_NO_TX),
+	BRANCH_OPT("cond", PERF_SAMPLE_BRANCH_COND),
+	BRANCH_OPT("ind_jmp", PERF_SAMPLE_BRANCH_IND_JUMP),
+	BRANCH_END
+};
+
+int
+parse_branch_stack(const struct option *opt, const char *str, int unset)
+{
+#define ONLY_PLM \
+	(PERF_SAMPLE_BRANCH_USER	|\
+	 PERF_SAMPLE_BRANCH_KERNEL	|\
+	 PERF_SAMPLE_BRANCH_HV)
+
+	uint64_t *mode = (uint64_t *)opt->value;
+	const struct branch_mode *br;
+	char *s, *os = NULL, *p;
+	int ret = -1;
+
+	if (unset)
+		return 0;
+
+	/*
+	 * cannot set it twice, -b + --branch-filter for instance
+	 */
+	if (*mode)
+		return -1;
+
+	/* str may be NULL in case no arg is passed to -b */
+	if (str) {
+		/* because str is read-only */
+		s = os = strdup(str);
+		if (!s)
+			return -1;
+
+		for (;;) {
+			p = strchr(s, ',');
+			if (p)
+				*p = '\0';
+
+			for (br = branch_modes; br->name; br++) {
+				if (!strcasecmp(s, br->name))
+					break;
+			}
+			if (!br->name) {
+				ui__warning("unknown branch filter %s,"
+					    " check man page\n", s);
+				goto error;
+			}
+
+			*mode |= br->mode;
+
+			if (!p)
+				break;
+
+			s = p + 1;
+		}
+	}
+	ret = 0;
+
+	/* default to any branch */
+	if ((*mode & ~ONLY_PLM) == 0) {
+		*mode = PERF_SAMPLE_BRANCH_ANY;
+	}
+error:
+	free(os);
+	return ret;
+}
diff --git a/tools/perf/util/parse-branch-options.h b/tools/perf/util/parse-branch-options.h
new file mode 100644
index 000000000..b9d9470c2
--- /dev/null
+++ b/tools/perf/util/parse-branch-options.h
@@ -0,0 +1,5 @@
+#ifndef _PERF_PARSE_BRANCH_OPTIONS_H
+#define _PERF_PARSE_BRANCH_OPTIONS_H 1
+struct option;
+int parse_branch_stack(const struct option *opt, const char *str, int unset);
+#endif /* _PERF_PARSE_BRANCH_OPTIONS_H */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index be0655388..09f8d2357 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -17,6 +17,8 @@
 #include "parse-events-flex.h"
 #include "pmu.h"
 #include "thread_map.h"
+#include "cpumap.h"
+#include "asm/bug.h"
 
 #define MAX_NAME_LEN 100
 
@@ -284,7 +286,9 @@ __add_event(struct list_head *list, int *idx,
 	if (!evsel)
 		return NULL;
 
-	evsel->cpus = cpus;
+	if (cpus)
+		evsel->cpus = cpu_map__get(cpus);
+
 	if (name)
 		evsel->name = strdup(name);
 	list_add_tail(&evsel->node, list);
@@ -538,16 +542,40 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx,
 	return add_event(list, idx, &attr, NULL);
 }
 
+static int check_type_val(struct parse_events_term *term,
+			  struct parse_events_error *err,
+			  int type)
+{
+	if (type == term->type_val)
+		return 0;
+
+	if (err) {
+		err->idx = term->err_val;
+		if (type == PARSE_EVENTS__TERM_TYPE_NUM)
+			err->str = strdup("expected numeric value");
+		else
+			err->str = strdup("expected string value");
+	}
+	return -EINVAL;
+}
+
 static int config_term(struct perf_event_attr *attr,
-		       struct parse_events_term *term)
+		       struct parse_events_term *term,
+		       struct parse_events_error *err)
 {
-#define CHECK_TYPE_VAL(type)					\
-do {								\
-	if (PARSE_EVENTS__TERM_TYPE_ ## type != term->type_val)	\
-		return -EINVAL;					\
+#define CHECK_TYPE_VAL(type)						   \
+do {									   \
+	if (check_type_val(term, err, PARSE_EVENTS__TERM_TYPE_ ## type)) \
+		return -EINVAL;						   \
 } while (0)
 
 	switch (term->type_term) {
+	case PARSE_EVENTS__TERM_TYPE_USER:
+		/*
+		 * Always succeed for sysfs terms, as we dont know
+		 * at this point what type they need to have.
+		 */
+		return 0;
 	case PARSE_EVENTS__TERM_TYPE_CONFIG:
 		CHECK_TYPE_VAL(NUM);
 		attr->config = term->val.num;
@@ -582,18 +610,20 @@ do {								\
 }
 
 static int config_attr(struct perf_event_attr *attr,
-		       struct list_head *head, int fail)
+		       struct list_head *head,
+		       struct parse_events_error *err)
 {
 	struct parse_events_term *term;
 
 	list_for_each_entry(term, head, list)
-		if (config_term(attr, term) && fail)
+		if (config_term(attr, term, err))
 			return -EINVAL;
 
 	return 0;
 }
 
-int parse_events_add_numeric(struct list_head *list, int *idx,
+int parse_events_add_numeric(struct parse_events_evlist *data,
+			     struct list_head *list,
 			     u32 type, u64 config,
 			     struct list_head *head_config)
 {
@@ -604,10 +634,10 @@ int parse_events_add_numeric(struct list_head *list, int *idx,
 	attr.config = config;
 
 	if (head_config &&
-	    config_attr(&attr, head_config, 1))
+	    config_attr(&attr, head_config, data->error))
 		return -EINVAL;
 
-	return add_event(list, idx, &attr, NULL);
+	return add_event(list, &data->idx, &attr, NULL);
 }
 
 static int parse_events__is_name_term(struct parse_events_term *term)
@@ -626,8 +656,9 @@ static char *pmu_event_name(struct list_head *head_terms)
 	return NULL;
 }
 
-int parse_events_add_pmu(struct list_head *list, int *idx,
-			 char *name, struct list_head *head_config)
+int parse_events_add_pmu(struct parse_events_evlist *data,
+			 struct list_head *list, char *name,
+			 struct list_head *head_config)
 {
 	struct perf_event_attr attr;
 	struct perf_pmu_info info;
@@ -647,7 +678,7 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
 
 	if (!head_config) {
 		attr.type = pmu->type;
-		evsel = __add_event(list, idx, &attr, NULL, pmu->cpus);
+		evsel = __add_event(list, &data->idx, &attr, NULL, pmu->cpus);
 		return evsel ? 0 : -ENOMEM;
 	}
 
@@ -658,13 +689,14 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
 	 * Configure hardcoded terms first, no need to check
 	 * return value when called with fail == 0 ;)
 	 */
-	config_attr(&attr, head_config, 0);
+	if (config_attr(&attr, head_config, data->error))
+		return -EINVAL;
 
-	if (perf_pmu__config(pmu, &attr, head_config))
+	if (perf_pmu__config(pmu, &attr, head_config, data->error))
 		return -EINVAL;
 
-	evsel = __add_event(list, idx, &attr, pmu_event_name(head_config),
-			    pmu->cpus);
+	evsel = __add_event(list, &data->idx, &attr,
+			    pmu_event_name(head_config), pmu->cpus);
 	if (evsel) {
 		evsel->unit = info.unit;
 		evsel->scale = info.scale;
@@ -1019,11 +1051,13 @@ int parse_events_terms(struct list_head *terms, const char *str)
 	return ret;
 }
 
-int parse_events(struct perf_evlist *evlist, const char *str)
+int parse_events(struct perf_evlist *evlist, const char *str,
+		 struct parse_events_error *err)
 {
 	struct parse_events_evlist data = {
-		.list = LIST_HEAD_INIT(data.list),
-		.idx  = evlist->nr_entries,
+		.list  = LIST_HEAD_INIT(data.list),
+		.idx   = evlist->nr_entries,
+		.error = err,
 	};
 	int ret;
 
@@ -1044,16 +1078,87 @@ int parse_events(struct perf_evlist *evlist, const char *str)
 	return ret;
 }
 
+#define MAX_WIDTH 1000
+static int get_term_width(void)
+{
+	struct winsize ws;
+
+	get_term_dimensions(&ws);
+	return ws.ws_col > MAX_WIDTH ? MAX_WIDTH : ws.ws_col;
+}
+
+static void parse_events_print_error(struct parse_events_error *err,
+				     const char *event)
+{
+	const char *str = "invalid or unsupported event: ";
+	char _buf[MAX_WIDTH];
+	char *buf = (char *) event;
+	int idx = 0;
+
+	if (err->str) {
+		/* -2 for extra '' in the final fprintf */
+		int width       = get_term_width() - 2;
+		int len_event   = strlen(event);
+		int len_str, max_len, cut = 0;
+
+		/*
+		 * Maximum error index indent, we will cut
+		 * the event string if it's bigger.
+		 */
+		int max_err_idx = 10;
+
+		/*
+		 * Let's be specific with the message when
+		 * we have the precise error.
+		 */
+		str     = "event syntax error: ";
+		len_str = strlen(str);
+		max_len = width - len_str;
+
+		buf = _buf;
+
+		/* We're cutting from the beggining. */
+		if (err->idx > max_err_idx)
+			cut = err->idx - max_err_idx;
+
+		strncpy(buf, event + cut, max_len);
+
+		/* Mark cut parts with '..' on both sides. */
+		if (cut)
+			buf[0] = buf[1] = '.';
+
+		if ((len_event - cut) > max_len) {
+			buf[max_len - 1] = buf[max_len - 2] = '.';
+			buf[max_len] = 0;
+		}
+
+		idx = len_str + err->idx - cut;
+	}
+
+	fprintf(stderr, "%s'%s'\n", str, buf);
+	if (idx) {
+		fprintf(stderr, "%*s\\___ %s\n", idx + 1, "", err->str);
+		if (err->help)
+			fprintf(stderr, "\n%s\n", err->help);
+		free(err->str);
+		free(err->help);
+	}
+
+	fprintf(stderr, "Run 'perf list' for a list of valid events\n");
+}
+
+#undef MAX_WIDTH
+
 int parse_events_option(const struct option *opt, const char *str,
 			int unset __maybe_unused)
 {
 	struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
-	int ret = parse_events(evlist, str);
+	struct parse_events_error err = { .idx = 0, };
+	int ret = parse_events(evlist, str, &err);
+
+	if (ret)
+		parse_events_print_error(&err, str);
 
-	if (ret) {
-		fprintf(stderr, "invalid or unsupported event: '%s'\n", str);
-		fprintf(stderr, "Run 'perf list' for a list of valid events\n");
-	}
 	return ret;
 }
 
@@ -1460,7 +1565,7 @@ int parse_events__is_hardcoded_term(struct parse_events_term *term)
 
 static int new_term(struct parse_events_term **_term, int type_val,
 		    int type_term, char *config,
-		    char *str, u64 num)
+		    char *str, u64 num, int err_term, int err_val)
 {
 	struct parse_events_term *term;
 
@@ -1472,6 +1577,8 @@ static int new_term(struct parse_events_term **_term, int type_val,
 	term->type_val  = type_val;
 	term->type_term = type_term;
 	term->config = config;
+	term->err_term = err_term;
+	term->err_val  = err_val;
 
 	switch (type_val) {
 	case PARSE_EVENTS__TERM_TYPE_NUM:
@@ -1490,17 +1597,29 @@ static int new_term(struct parse_events_term **_term, int type_val,
 }
 
 int parse_events_term__num(struct parse_events_term **term,
-			   int type_term, char *config, u64 num)
+			   int type_term, char *config, u64 num,
+			   void *loc_term_, void *loc_val_)
 {
+	YYLTYPE *loc_term = loc_term_;
+	YYLTYPE *loc_val = loc_val_;
+
 	return new_term(term, PARSE_EVENTS__TERM_TYPE_NUM, type_term,
-			config, NULL, num);
+			config, NULL, num,
+			loc_term ? loc_term->first_column : 0,
+			loc_val ? loc_val->first_column : 0);
 }
 
 int parse_events_term__str(struct parse_events_term **term,
-			   int type_term, char *config, char *str)
+			   int type_term, char *config, char *str,
+			   void *loc_term_, void *loc_val_)
 {
+	YYLTYPE *loc_term = loc_term_;
+	YYLTYPE *loc_val = loc_val_;
+
 	return new_term(term, PARSE_EVENTS__TERM_TYPE_STR, type_term,
-			config, str, 0);
+			config, str, 0,
+			loc_term ? loc_term->first_column : 0,
+			loc_val ? loc_val->first_column : 0);
 }
 
 int parse_events_term__sym_hw(struct parse_events_term **term,
@@ -1514,18 +1633,20 @@ int parse_events_term__sym_hw(struct parse_events_term **term,
 	if (config)
 		return new_term(term, PARSE_EVENTS__TERM_TYPE_STR,
 				PARSE_EVENTS__TERM_TYPE_USER, config,
-				(char *) sym->symbol, 0);
+				(char *) sym->symbol, 0, 0, 0);
 	else
 		return new_term(term, PARSE_EVENTS__TERM_TYPE_STR,
 				PARSE_EVENTS__TERM_TYPE_USER,
-				(char *) "event", (char *) sym->symbol, 0);
+				(char *) "event", (char *) sym->symbol,
+				0, 0, 0);
 }
 
 int parse_events_term__clone(struct parse_events_term **new,
 			     struct parse_events_term *term)
 {
 	return new_term(new, term->type_val, term->type_term, term->config,
-			term->val.str, term->val.num);
+			term->val.str, term->val.num,
+			term->err_term, term->err_val);
 }
 
 void parse_events__free_terms(struct list_head *terms)
@@ -1535,3 +1656,15 @@ void parse_events__free_terms(struct list_head *terms)
 	list_for_each_entry_safe(term, h, terms, list)
 		free(term);
 }
+
+void parse_events_evlist_error(struct parse_events_evlist *data,
+			       int idx, const char *str)
+{
+	struct parse_events_error *err = data->error;
+
+	if (!err)
+		return;
+	err->idx = idx;
+	err->str = strdup(str);
+	WARN_ONCE(!err->str, "WARNING: failed to allocate error string");
+}
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 52a2dda4f..131f29b2f 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -12,6 +12,7 @@
 struct list_head;
 struct perf_evsel;
 struct perf_evlist;
+struct parse_events_error;
 
 struct option;
 
@@ -29,7 +30,8 @@ const char *event_type(int type);
 
 extern int parse_events_option(const struct option *opt, const char *str,
 			       int unset);
-extern int parse_events(struct perf_evlist *evlist, const char *str);
+extern int parse_events(struct perf_evlist *evlist, const char *str,
+			struct parse_events_error *error);
 extern int parse_events_terms(struct list_head *terms, const char *str);
 extern int parse_filter(const struct option *opt, const char *str, int unset);
 
@@ -72,12 +74,23 @@ struct parse_events_term {
 	int type_term;
 	struct list_head list;
 	bool used;
+
+	/* error string indexes for within parsed string */
+	int err_term;
+	int err_val;
+};
+
+struct parse_events_error {
+	int   idx;	/* index in the parsed string */
+	char *str;      /* string to display at the index */
+	char *help;	/* optional help string */
 };
 
 struct parse_events_evlist {
-	struct list_head list;
-	int idx;
-	int nr_groups;
+	struct list_head	   list;
+	int			   idx;
+	int			   nr_groups;
+	struct parse_events_error *error;
 };
 
 struct parse_events_terms {
@@ -85,10 +98,12 @@ struct parse_events_terms {
 };
 
 int parse_events__is_hardcoded_term(struct parse_events_term *term);
-int parse_events_term__num(struct parse_events_term **_term,
-			   int type_term, char *config, u64 num);
-int parse_events_term__str(struct parse_events_term **_term,
-			   int type_term, char *config, char *str);
+int parse_events_term__num(struct parse_events_term **term,
+			   int type_term, char *config, u64 num,
+			   void *loc_term, void *loc_val);
+int parse_events_term__str(struct parse_events_term **term,
+			   int type_term, char *config, char *str,
+			   void *loc_term, void *loc_val);
 int parse_events_term__sym_hw(struct parse_events_term **term,
 			      char *config, unsigned idx);
 int parse_events_term__clone(struct parse_events_term **new,
@@ -99,21 +114,24 @@ int parse_events__modifier_group(struct list_head *list, char *event_mod);
 int parse_events_name(struct list_head *list, char *name);
 int parse_events_add_tracepoint(struct list_head *list, int *idx,
 				char *sys, char *event);
-int parse_events_add_numeric(struct list_head *list, int *idx,
+int parse_events_add_numeric(struct parse_events_evlist *data,
+			     struct list_head *list,
 			     u32 type, u64 config,
 			     struct list_head *head_config);
 int parse_events_add_cache(struct list_head *list, int *idx,
 			   char *type, char *op_result1, char *op_result2);
 int parse_events_add_breakpoint(struct list_head *list, int *idx,
 				void *ptr, char *type, u64 len);
-int parse_events_add_pmu(struct list_head *list, int *idx,
-			 char *pmu , struct list_head *head_config);
+int parse_events_add_pmu(struct parse_events_evlist *data,
+			 struct list_head *list, char *name,
+			 struct list_head *head_config);
 enum perf_pmu_event_symbol_type
 perf_pmu__parse_check(const char *name);
 void parse_events__set_leader(char *name, struct list_head *list);
 void parse_events_update_lists(struct list_head *list_event,
 			       struct list_head *list_all);
-void parse_events_error(void *data, void *scanner, char const *msg);
+void parse_events_evlist_error(struct parse_events_evlist *data,
+			       int idx, const char *str);
 
 void print_events(const char *event_glob, bool name_only);
 
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 8895cf313..13cef3c65 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -3,6 +3,8 @@
 %option bison-bridge
 %option prefix="parse_events_"
 %option stack
+%option bison-locations
+%option yylineno
 
 %{
 #include <errno.h>
@@ -51,6 +53,18 @@ static int str(yyscan_t scanner, int token)
 	return token;
 }
 
+#define REWIND(__alloc)				\
+do {								\
+	YYSTYPE *__yylval = parse_events_get_lval(yyscanner);	\
+	char *text = parse_events_get_text(yyscanner);		\
+								\
+	if (__alloc)						\
+		__yylval->str = strdup(text);			\
+								\
+	yycolumn -= strlen(text);				\
+	yyless(0);						\
+} while (0)
+
 static int pmu_str_check(yyscan_t scanner)
 {
 	YYSTYPE *yylval = parse_events_get_lval(scanner);
@@ -85,6 +99,13 @@ static int term(yyscan_t scanner, int type)
 	return PE_TERM;
 }
 
+#define YY_USER_ACTION					\
+do {							\
+	yylloc->last_column  = yylloc->first_column;	\
+	yylloc->first_column = yycolumn;		\
+	yycolumn += yyleng;				\
+} while (0);
+
 %}
 
 %x mem
@@ -98,8 +119,8 @@ event		[^,{}/]+
 num_dec		[0-9]+
 num_hex		0x[a-fA-F0-9]+
 num_raw_hex	[a-fA-F0-9]+
-name		[a-zA-Z_*?][a-zA-Z0-9_*?]*
-name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?]*
+name		[a-zA-Z_*?][a-zA-Z0-9_*?.]*
+name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?.]*
 /* If you add a modifier you need to update check_modifier() */
 modifier_event	[ukhpGHSDI]+
 modifier_bp	[rwx]{1,3}
@@ -119,6 +140,12 @@ modifier_bp	[rwx]{1,3}
 
 		if (start_token) {
 			parse_events_set_extra(NULL, yyscanner);
+			/*
+			 * The flex parser does not init locations variable
+			 * via the scan_string interface, so we need do the
+			 * init in here.
+			 */
+			yycolumn = 0;
 			return start_token;
 		}
          }
@@ -127,24 +154,29 @@ modifier_bp	[rwx]{1,3}
 <event>{
 
 {group}		{
-			BEGIN(INITIAL); yyless(0);
+			BEGIN(INITIAL);
+			REWIND(0);
 		}
 
 {event_pmu}	|
 {event}		{
-			str(yyscanner, PE_EVENT_NAME);
-			BEGIN(INITIAL); yyless(0);
+			BEGIN(INITIAL);
+			REWIND(1);
 			return PE_EVENT_NAME;
 		}
 
-.		|
 <<EOF>>		{
-			BEGIN(INITIAL); yyless(0);
+			BEGIN(INITIAL);
+			REWIND(0);
 		}
 
 }
 
 <config>{
+	/*
+	 * Please update formats_error_string any time
+	 * new static term is added.
+	 */
 config			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); }
 config1			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); }
 config2			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG2); }
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 72def077d..591905a02 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -2,6 +2,7 @@
 %parse-param {void *_data}
 %parse-param {void *scanner}
 %lex-param {void* scanner}
+%locations
 
 %{
 
@@ -14,8 +15,6 @@
 #include "parse-events.h"
 #include "parse-events-bison.h"
 
-extern int parse_events_lex (YYSTYPE* lvalp, void* scanner);
-
 #define ABORT_ON(val) \
 do { \
 	if (val) \
@@ -208,7 +207,7 @@ PE_NAME '/' event_config '/'
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_pmu(list, &data->idx, $1, $3));
+	ABORT_ON(parse_events_add_pmu(data, list, $1, $3));
 	parse_events__free_terms($3);
 	$$ = list;
 }
@@ -219,7 +218,7 @@ PE_NAME '/' '/'
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_pmu(list, &data->idx, $1, NULL));
+	ABORT_ON(parse_events_add_pmu(data, list, $1, NULL));
 	$$ = list;
 }
 |
@@ -232,11 +231,11 @@ PE_KERNEL_PMU_EVENT sep_dc
 
 	ALLOC_LIST(head);
 	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, 1));
+					$1, 1, &@1, NULL));
 	list_add_tail(&term->list, head);
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_pmu(list, &data->idx, "cpu", head));
+	ABORT_ON(parse_events_add_pmu(data, list, "cpu", head));
 	parse_events__free_terms(head);
 	$$ = list;
 }
@@ -252,7 +251,7 @@ PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc
 
 	ALLOC_LIST(head);
 	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					&pmu_name, 1));
+					&pmu_name, 1, &@1, NULL));
 	list_add_tail(&term->list, head);
 
 	ALLOC_LIST(list);
@@ -275,8 +274,7 @@ value_sym '/' event_config '/'
 	int config = $1 & 255;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_numeric(list, &data->idx,
-					  type, config, $3));
+	ABORT_ON(parse_events_add_numeric(data, list, type, config, $3));
 	parse_events__free_terms($3);
 	$$ = list;
 }
@@ -289,8 +287,7 @@ value_sym sep_slash_dc
 	int config = $1 & 255;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_numeric(list, &data->idx,
-					  type, config, NULL));
+	ABORT_ON(parse_events_add_numeric(data, list, type, config, NULL));
 	$$ = list;
 }
 
@@ -389,7 +386,15 @@ PE_NAME ':' PE_NAME
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_tracepoint(list, &data->idx, $1, $3));
+	if (parse_events_add_tracepoint(list, &data->idx, $1, $3)) {
+		struct parse_events_error *error = data->error;
+
+		if (error) {
+			error->idx = @1.first_column;
+			error->str = strdup("unknown tracepoint");
+		}
+		return -1;
+	}
 	$$ = list;
 }
 
@@ -400,7 +405,7 @@ PE_VALUE ':' PE_VALUE
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_numeric(list, &data->idx, (u32)$1, $3, NULL));
+	ABORT_ON(parse_events_add_numeric(data, list, (u32)$1, $3, NULL));
 	$$ = list;
 }
 
@@ -411,8 +416,7 @@ PE_RAW
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_numeric(list, &data->idx,
-					  PERF_TYPE_RAW, $1, NULL));
+	ABORT_ON(parse_events_add_numeric(data, list, PERF_TYPE_RAW, $1, NULL));
 	$$ = list;
 }
 
@@ -450,7 +454,7 @@ PE_NAME '=' PE_NAME
 	struct parse_events_term *term;
 
 	ABORT_ON(parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, $3));
+					$1, $3, &@1, &@3));
 	$$ = term;
 }
 |
@@ -459,7 +463,7 @@ PE_NAME '=' PE_VALUE
 	struct parse_events_term *term;
 
 	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, $3));
+					$1, $3, &@1, &@3));
 	$$ = term;
 }
 |
@@ -477,7 +481,7 @@ PE_NAME
 	struct parse_events_term *term;
 
 	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, 1));
+					$1, 1, &@1, NULL));
 	$$ = term;
 }
 |
@@ -494,7 +498,7 @@ PE_TERM '=' PE_NAME
 {
 	struct parse_events_term *term;
 
-	ABORT_ON(parse_events_term__str(&term, (int)$1, NULL, $3));
+	ABORT_ON(parse_events_term__str(&term, (int)$1, NULL, $3, &@1, &@3));
 	$$ = term;
 }
 |
@@ -502,7 +506,7 @@ PE_TERM '=' PE_VALUE
 {
 	struct parse_events_term *term;
 
-	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3));
+	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3, &@1, &@3));
 	$$ = term;
 }
 |
@@ -510,7 +514,7 @@ PE_TERM
 {
 	struct parse_events_term *term;
 
-	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1));
+	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1, &@1, NULL));
 	$$ = term;
 }
 
@@ -520,7 +524,9 @@ sep_slash_dc: '/' | ':' |
 
 %%
 
-void parse_events_error(void *data __maybe_unused, void *scanner __maybe_unused,
+void parse_events_error(YYLTYPE *loc, void *data,
+			void *scanner __maybe_unused,
 			char const *msg __maybe_unused)
 {
+	parse_events_evlist_error(data, loc->last_column, "parser error");
 }
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
index 59561fd86..367d8b816 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/perf/util/parse-options.h
@@ -123,6 +123,10 @@ struct option {
 #define OPT_LONG(s, l, v, h)        { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, long *), .help = (h) }
 #define OPT_U64(s, l, v, h)         { .type = OPTION_U64, .short_name = (s), .long_name = (l), .value = check_vtype(v, u64 *), .help = (h) }
 #define OPT_STRING(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h) }
+#define OPT_STRING_OPTARG(s, l, v, a, h, d) \
+	{ .type = OPTION_STRING,  .short_name = (s), .long_name = (l), \
+	  .value = check_vtype(v, const char **), (a), .help = (h), \
+	  .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d) }
 #define OPT_STRING_NOEMPTY(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h), .flags = PARSE_OPT_NOEMPTY}
 #define OPT_DATE(s, l, v, h) \
 	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb }
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 48411674d..7bcb8c315 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1,4 +1,5 @@
 #include <linux/list.h>
+#include <linux/compiler.h>
 #include <sys/types.h>
 #include <unistd.h>
 #include <stdio.h>
@@ -112,7 +113,11 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
 	if (sret < 0)
 		goto error;
 
-	scale[sret] = '\0';
+	if (scale[sret - 1] == '\n')
+		scale[sret - 1] = '\0';
+	else
+		scale[sret] = '\0';
+
 	/*
 	 * save current locale
 	 */
@@ -154,7 +159,10 @@ static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, char *dir, char *n
 
 	close(fd);
 
-	alias->unit[sret] = '\0';
+	if (alias->unit[sret - 1] == '\n')
+		alias->unit[sret - 1] = '\0';
+	else
+		alias->unit[sret] = '\0';
 
 	return 0;
 error:
@@ -198,17 +206,12 @@ static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias,
 	return 0;
 }
 
-static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FILE *file)
+static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
+				 char *desc __maybe_unused, char *val)
 {
 	struct perf_pmu_alias *alias;
-	char buf[256];
 	int ret;
 
-	ret = fread(buf, 1, sizeof(buf), file);
-	if (ret == 0)
-		return -EINVAL;
-	buf[ret] = 0;
-
 	alias = malloc(sizeof(*alias));
 	if (!alias)
 		return -ENOMEM;
@@ -218,26 +221,43 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
 	alias->unit[0] = '\0';
 	alias->per_pkg = false;
 
-	ret = parse_events_terms(&alias->terms, buf);
+	ret = parse_events_terms(&alias->terms, val);
 	if (ret) {
+		pr_err("Cannot parse alias %s: %d\n", val, ret);
 		free(alias);
 		return ret;
 	}
 
 	alias->name = strdup(name);
-	/*
-	 * load unit name and scale if available
-	 */
-	perf_pmu__parse_unit(alias, dir, name);
-	perf_pmu__parse_scale(alias, dir, name);
-	perf_pmu__parse_per_pkg(alias, dir, name);
-	perf_pmu__parse_snapshot(alias, dir, name);
+	if (dir) {
+		/*
+		 * load unit name and scale if available
+		 */
+		perf_pmu__parse_unit(alias, dir, name);
+		perf_pmu__parse_scale(alias, dir, name);
+		perf_pmu__parse_per_pkg(alias, dir, name);
+		perf_pmu__parse_snapshot(alias, dir, name);
+	}
 
 	list_add_tail(&alias->list, list);
 
 	return 0;
 }
 
+static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FILE *file)
+{
+	char buf[256];
+	int ret;
+
+	ret = fread(buf, 1, sizeof(buf), file);
+	if (ret == 0)
+		return -EINVAL;
+
+	buf[ret] = 0;
+
+	return __perf_pmu__new_alias(list, dir, name, NULL, buf);
+}
+
 static inline bool pmu_alias_info_file(char *name)
 {
 	size_t len;
@@ -429,7 +449,7 @@ static struct cpu_map *pmu_cpumask(const char *name)
 	return cpus;
 }
 
-struct perf_event_attr *__attribute__((weak))
+struct perf_event_attr * __weak
 perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
 {
 	return NULL;
@@ -442,6 +462,10 @@ static struct perf_pmu *pmu_lookup(const char *name)
 	LIST_HEAD(aliases);
 	__u32 type;
 
+	/* No support for intel_bts or intel_pt so disallow them */
+	if (!strcmp(name, "intel_bts") || !strcmp(name, "intel_pt"))
+		return NULL;
+
 	/*
 	 * The pmu data we store & need consists of the pmu
 	 * type value and format definitions. Load both right
@@ -579,6 +603,38 @@ static int pmu_resolve_param_term(struct parse_events_term *term,
 	return -1;
 }
 
+static char *formats_error_string(struct list_head *formats)
+{
+	struct perf_pmu_format *format;
+	char *err, *str;
+	static const char *static_terms = "config,config1,config2,name,period,branch_type\n";
+	unsigned i = 0;
+
+	if (!asprintf(&str, "valid terms:"))
+		return NULL;
+
+	/* sysfs exported terms */
+	list_for_each_entry(format, formats, list) {
+		char c = i++ ? ',' : ' ';
+
+		err = str;
+		if (!asprintf(&str, "%s%c%s", err, c, format->name))
+			goto fail;
+		free(err);
+	}
+
+	/* static terms */
+	err = str;
+	if (!asprintf(&str, "%s,%s", err, static_terms))
+		goto fail;
+
+	free(err);
+	return str;
+fail:
+	free(err);
+	return NULL;
+}
+
 /*
  * Setup one of config[12] attr members based on the
  * user input data - term parameter.
@@ -587,7 +643,7 @@ static int pmu_config_term(struct list_head *formats,
 			   struct perf_event_attr *attr,
 			   struct parse_events_term *term,
 			   struct list_head *head_terms,
-			   bool zero)
+			   bool zero, struct parse_events_error *err)
 {
 	struct perf_pmu_format *format;
 	__u64 *vp;
@@ -611,6 +667,11 @@ static int pmu_config_term(struct list_head *formats,
 	if (!format) {
 		if (verbose)
 			printf("Invalid event/parameter '%s'\n", term->config);
+		if (err) {
+			err->idx  = term->err_term;
+			err->str  = strdup("unknown term");
+			err->help = formats_error_string(formats);
+		}
 		return -EINVAL;
 	}
 
@@ -636,9 +697,14 @@ static int pmu_config_term(struct list_head *formats,
 		val = term->val.num;
 	else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) {
 		if (strcmp(term->val.str, "?")) {
-			if (verbose)
+			if (verbose) {
 				pr_info("Invalid sysfs entry %s=%s\n",
 						term->config, term->val.str);
+			}
+			if (err) {
+				err->idx = term->err_val;
+				err->str = strdup("expected numeric value");
+			}
 			return -EINVAL;
 		}
 
@@ -654,12 +720,13 @@ static int pmu_config_term(struct list_head *formats,
 int perf_pmu__config_terms(struct list_head *formats,
 			   struct perf_event_attr *attr,
 			   struct list_head *head_terms,
-			   bool zero)
+			   bool zero, struct parse_events_error *err)
 {
 	struct parse_events_term *term;
 
 	list_for_each_entry(term, head_terms, list) {
-		if (pmu_config_term(formats, attr, term, head_terms, zero))
+		if (pmu_config_term(formats, attr, term, head_terms,
+				    zero, err))
 			return -EINVAL;
 	}
 
@@ -672,12 +739,14 @@ int perf_pmu__config_terms(struct list_head *formats,
  * 2) pmu format definitions - specified by pmu parameter
  */
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
-		     struct list_head *head_terms)
+		     struct list_head *head_terms,
+		     struct parse_events_error *err)
 {
 	bool zero = !!pmu->default_config;
 
 	attr->type = pmu->type;
-	return perf_pmu__config_terms(&pmu->format, attr, head_terms, zero);
+	return perf_pmu__config_terms(&pmu->format, attr, head_terms,
+				      zero, err);
 }
 
 static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 6b1249fbd..7b9c8cf8a 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -4,6 +4,7 @@
 #include <linux/bitmap.h>
 #include <linux/perf_event.h>
 #include <stdbool.h>
+#include "parse-events.h"
 
 enum {
 	PERF_PMU_FORMAT_VALUE_CONFIG,
@@ -47,11 +48,12 @@ struct perf_pmu_alias {
 
 struct perf_pmu *perf_pmu__find(const char *name);
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
-		     struct list_head *head_terms);
+		     struct list_head *head_terms,
+		     struct parse_events_error *error);
 int perf_pmu__config_terms(struct list_head *formats,
 			   struct perf_event_attr *attr,
 			   struct list_head *head_terms,
-			   bool zero);
+			   bool zero, struct parse_events_error *error);
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 			  struct perf_pmu_info *info);
 struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index d05b77cf3..381f23a44 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -51,6 +51,7 @@
 #define PERFPROBE_GROUP "probe"
 
 bool probe_event_dry_run;	/* Dry run flag */
+struct probe_conf probe_conf;
 
 #define semantic_error(msg ...) pr_err("Semantic error :" msg)
 
@@ -161,18 +162,18 @@ static u64 kernel_get_symbol_address_by_name(const char *name, bool reloc)
 
 static struct map *kernel_get_module_map(const char *module)
 {
-	struct rb_node *nd;
 	struct map_groups *grp = &host_machine->kmaps;
+	struct maps *maps = &grp->maps[MAP__FUNCTION];
+	struct map *pos;
 
 	/* A file path -- this is an offline module */
 	if (module && strchr(module, '/'))
-		return machine__new_module(host_machine, 0, module);
+		return machine__findnew_module_map(host_machine, 0, module);
 
 	if (!module)
 		module = "kernel";
 
-	for (nd = rb_first(&grp->maps[MAP__FUNCTION]); nd; nd = rb_next(nd)) {
-		struct map *pos = rb_entry(nd, struct map, rb_node);
+	for (pos = maps__first(maps); pos; pos = map__next(pos)) {
 		if (strncmp(pos->dso->short_name + 1, module,
 			    pos->dso->short_name_len - 2) == 0) {
 			return pos;
@@ -194,52 +195,11 @@ static void put_target_map(struct map *map, bool user)
 {
 	if (map && user) {
 		/* Only the user map needs to be released */
-		dso__delete(map->dso);
-		map__delete(map);
+		map__put(map);
 	}
 }
 
 
-static struct dso *kernel_get_module_dso(const char *module)
-{
-	struct dso *dso;
-	struct map *map;
-	const char *vmlinux_name;
-
-	if (module) {
-		list_for_each_entry(dso, &host_machine->kernel_dsos.head,
-				    node) {
-			if (strncmp(dso->short_name + 1, module,
-				    dso->short_name_len - 2) == 0)
-				goto found;
-		}
-		pr_debug("Failed to find module %s.\n", module);
-		return NULL;
-	}
-
-	map = host_machine->vmlinux_maps[MAP__FUNCTION];
-	dso = map->dso;
-
-	vmlinux_name = symbol_conf.vmlinux_name;
-	if (vmlinux_name) {
-		if (dso__load_vmlinux(dso, map, vmlinux_name, false, NULL) <= 0)
-			return NULL;
-	} else {
-		if (dso__load_vmlinux_path(dso, map, NULL) <= 0) {
-			pr_debug("Failed to load kernel map.\n");
-			return NULL;
-		}
-	}
-found:
-	return dso;
-}
-
-const char *kernel_get_module_path(const char *module)
-{
-	struct dso *dso = kernel_get_module_dso(module);
-	return (dso) ? dso->long_name : NULL;
-}
-
 static int convert_exec_to_group(const char *exec, char **result)
 {
 	char *ptr1, *ptr2, *exec_copy;
@@ -286,7 +246,59 @@ static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
 		clear_probe_trace_event(tevs + i);
 }
 
+static bool kprobe_blacklist__listed(unsigned long address);
+static bool kprobe_warn_out_range(const char *symbol, unsigned long address)
+{
+	u64 etext_addr;
+
+	/* Get the address of _etext for checking non-probable text symbol */
+	etext_addr = kernel_get_symbol_address_by_name("_etext", false);
+
+	if (etext_addr != 0 && etext_addr < address)
+		pr_warning("%s is out of .text, skip it.\n", symbol);
+	else if (kprobe_blacklist__listed(address))
+		pr_warning("%s is blacklisted function, skip it.\n", symbol);
+	else
+		return false;
+
+	return true;
+}
+
 #ifdef HAVE_DWARF_SUPPORT
+
+static int kernel_get_module_dso(const char *module, struct dso **pdso)
+{
+	struct dso *dso;
+	struct map *map;
+	const char *vmlinux_name;
+	int ret = 0;
+
+	if (module) {
+		list_for_each_entry(dso, &host_machine->dsos.head, node) {
+			if (!dso->kernel)
+				continue;
+			if (strncmp(dso->short_name + 1, module,
+				    dso->short_name_len - 2) == 0)
+				goto found;
+		}
+		pr_debug("Failed to find module %s.\n", module);
+		return -ENOENT;
+	}
+
+	map = host_machine->vmlinux_maps[MAP__FUNCTION];
+	dso = map->dso;
+
+	vmlinux_name = symbol_conf.vmlinux_name;
+	dso->load_errno = 0;
+	if (vmlinux_name)
+		ret = dso__load_vmlinux(dso, map, vmlinux_name, false, NULL);
+	else
+		ret = dso__load_vmlinux_path(dso, map, NULL);
+found:
+	*pdso = dso;
+	return ret;
+}
+
 /*
  * Some binaries like glibc have special symbols which are on the symbol
  * table, but not in the debuginfo. If we can find the address of the
@@ -344,15 +356,14 @@ out:
 
 static int get_alternative_probe_event(struct debuginfo *dinfo,
 				       struct perf_probe_event *pev,
-				       struct perf_probe_point *tmp,
-				       const char *target)
+				       struct perf_probe_point *tmp)
 {
 	int ret;
 
 	memcpy(tmp, &pev->point, sizeof(*tmp));
 	memset(&pev->point, 0, sizeof(pev->point));
 	ret = find_alternative_probe_point(dinfo, tmp, &pev->point,
-					   target, pev->uprobes);
+					   pev->target, pev->uprobes);
 	if (ret < 0)
 		memcpy(&pev->point, tmp, sizeof(*tmp));
 
@@ -390,16 +401,25 @@ static int get_alternative_line_range(struct debuginfo *dinfo,
 static struct debuginfo *open_debuginfo(const char *module, bool silent)
 {
 	const char *path = module;
-	struct debuginfo *ret;
+	char reason[STRERR_BUFSIZE];
+	struct debuginfo *ret = NULL;
+	struct dso *dso = NULL;
+	int err;
 
 	if (!module || !strchr(module, '/')) {
-		path = kernel_get_module_path(module);
-		if (!path) {
+		err = kernel_get_module_dso(module, &dso);
+		if (err < 0) {
+			if (!dso || dso->load_errno == 0) {
+				if (!strerror_r(-err, reason, STRERR_BUFSIZE))
+					strcpy(reason, "(unknown)");
+			} else
+				dso__strerror_load(dso, reason, STRERR_BUFSIZE);
 			if (!silent)
-				pr_err("Failed to find path of %s module.\n",
-				       module ?: "kernel");
+				pr_err("Failed to find the path for %s: %s\n",
+					module ?: "kernel", reason);
 			return NULL;
 		}
+		path = dso->long_name;
 	}
 	ret = debuginfo__new(path);
 	if (!ret && !silent) {
@@ -413,6 +433,41 @@ static struct debuginfo *open_debuginfo(const char *module, bool silent)
 	return ret;
 }
 
+/* For caching the last debuginfo */
+static struct debuginfo *debuginfo_cache;
+static char *debuginfo_cache_path;
+
+static struct debuginfo *debuginfo_cache__open(const char *module, bool silent)
+{
+	if ((debuginfo_cache_path && !strcmp(debuginfo_cache_path, module)) ||
+	    (!debuginfo_cache_path && !module && debuginfo_cache))
+		goto out;
+
+	/* Copy module path */
+	free(debuginfo_cache_path);
+	if (module) {
+		debuginfo_cache_path = strdup(module);
+		if (!debuginfo_cache_path) {
+			debuginfo__delete(debuginfo_cache);
+			debuginfo_cache = NULL;
+			goto out;
+		}
+	}
+
+	debuginfo_cache = open_debuginfo(module, silent);
+	if (!debuginfo_cache)
+		zfree(&debuginfo_cache_path);
+out:
+	return debuginfo_cache;
+}
+
+static void debuginfo_cache__exit(void)
+{
+	debuginfo__delete(debuginfo_cache);
+	debuginfo_cache = NULL;
+	zfree(&debuginfo_cache_path);
+}
+
 
 static int get_text_start_address(const char *exec, unsigned long *address)
 {
@@ -474,12 +529,11 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp,
 	pr_debug("try to find information at %" PRIx64 " in %s\n", addr,
 		 tp->module ? : "kernel");
 
-	dinfo = open_debuginfo(tp->module, verbose == 0);
-	if (dinfo) {
+	dinfo = debuginfo_cache__open(tp->module, verbose == 0);
+	if (dinfo)
 		ret = debuginfo__find_probe_point(dinfo,
 						 (unsigned long)addr, pp);
-		debuginfo__delete(dinfo);
-	} else
+	else
 		ret = -ENOENT;
 
 	if (ret > 0) {
@@ -558,7 +612,7 @@ static int post_process_probe_trace_events(struct probe_trace_event *tevs,
 {
 	struct ref_reloc_sym *reloc_sym;
 	char *tmp;
-	int i;
+	int i, skipped = 0;
 
 	if (uprobe)
 		return add_exec_to_probe_trace_events(tevs, ntevs, module);
@@ -574,31 +628,40 @@ static int post_process_probe_trace_events(struct probe_trace_event *tevs,
 	}
 
 	for (i = 0; i < ntevs; i++) {
-		if (tevs[i].point.address && !tevs[i].point.retprobe) {
+		if (!tevs[i].point.address || tevs[i].point.retprobe)
+			continue;
+		/* If we found a wrong one, mark it by NULL symbol */
+		if (kprobe_warn_out_range(tevs[i].point.symbol,
+					  tevs[i].point.address)) {
+			tmp = NULL;
+			skipped++;
+		} else {
 			tmp = strdup(reloc_sym->name);
 			if (!tmp)
 				return -ENOMEM;
-			free(tevs[i].point.symbol);
-			tevs[i].point.symbol = tmp;
-			tevs[i].point.offset = tevs[i].point.address -
-					       reloc_sym->unrelocated_addr;
 		}
+		/* If we have no realname, use symbol for it */
+		if (!tevs[i].point.realname)
+			tevs[i].point.realname = tevs[i].point.symbol;
+		else
+			free(tevs[i].point.symbol);
+		tevs[i].point.symbol = tmp;
+		tevs[i].point.offset = tevs[i].point.address -
+				       reloc_sym->unrelocated_addr;
 	}
-	return 0;
+	return skipped;
 }
 
 /* Try to find perf_probe_event with debuginfo */
 static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
-					  struct probe_trace_event **tevs,
-					  int max_tevs, const char *target)
+					  struct probe_trace_event **tevs)
 {
 	bool need_dwarf = perf_probe_event_need_dwarf(pev);
 	struct perf_probe_point tmp;
 	struct debuginfo *dinfo;
 	int ntevs, ret = 0;
 
-	dinfo = open_debuginfo(target, !need_dwarf);
-
+	dinfo = open_debuginfo(pev->target, !need_dwarf);
 	if (!dinfo) {
 		if (need_dwarf)
 			return -ENOENT;
@@ -608,13 +671,12 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 
 	pr_debug("Try to find probe point from debuginfo.\n");
 	/* Searching trace events corresponding to a probe event */
-	ntevs = debuginfo__find_trace_events(dinfo, pev, tevs, max_tevs);
+	ntevs = debuginfo__find_trace_events(dinfo, pev, tevs);
 
 	if (ntevs == 0)	{  /* Not found, retry with an alternative */
-		ret = get_alternative_probe_event(dinfo, pev, &tmp, target);
+		ret = get_alternative_probe_event(dinfo, pev, &tmp);
 		if (!ret) {
-			ntevs = debuginfo__find_trace_events(dinfo, pev,
-							     tevs, max_tevs);
+			ntevs = debuginfo__find_trace_events(dinfo, pev, tevs);
 			/*
 			 * Write back to the original probe_event for
 			 * setting appropriate (user given) event name
@@ -629,12 +691,15 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 	if (ntevs > 0) {	/* Succeeded to find trace events */
 		pr_debug("Found %d probe_trace_events.\n", ntevs);
 		ret = post_process_probe_trace_events(*tevs, ntevs,
-							target, pev->uprobes);
-		if (ret < 0) {
+						pev->target, pev->uprobes);
+		if (ret < 0 || ret == ntevs) {
 			clear_probe_trace_events(*tevs, ntevs);
 			zfree(tevs);
 		}
-		return ret < 0 ? ret : ntevs;
+		if (ret != ntevs)
+			return ret < 0 ? ret : ntevs;
+		ntevs = 0;
+		/* Fall through */
 	}
 
 	if (ntevs == 0)	{	/* No error but failed to find probe point. */
@@ -809,8 +874,7 @@ int show_line_range(struct line_range *lr, const char *module, bool user)
 
 static int show_available_vars_at(struct debuginfo *dinfo,
 				  struct perf_probe_event *pev,
-				  int max_vls, struct strfilter *_filter,
-				  bool externs, const char *target)
+				  struct strfilter *_filter)
 {
 	char *buf;
 	int ret, i, nvars;
@@ -824,13 +888,12 @@ static int show_available_vars_at(struct debuginfo *dinfo,
 		return -EINVAL;
 	pr_debug("Searching variables at %s\n", buf);
 
-	ret = debuginfo__find_available_vars_at(dinfo, pev, &vls,
-						max_vls, externs);
+	ret = debuginfo__find_available_vars_at(dinfo, pev, &vls);
 	if (!ret) {  /* Not found, retry with an alternative */
-		ret = get_alternative_probe_event(dinfo, pev, &tmp, target);
+		ret = get_alternative_probe_event(dinfo, pev, &tmp);
 		if (!ret) {
 			ret = debuginfo__find_available_vars_at(dinfo, pev,
-						&vls, max_vls, externs);
+								&vls);
 			/* Release the old probe_point */
 			clear_perf_probe_point(&tmp);
 		}
@@ -877,8 +940,7 @@ end:
 
 /* Show available variables on given probe point */
 int show_available_vars(struct perf_probe_event *pevs, int npevs,
-			int max_vls, const char *module,
-			struct strfilter *_filter, bool externs)
+			struct strfilter *_filter)
 {
 	int i, ret = 0;
 	struct debuginfo *dinfo;
@@ -887,7 +949,7 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
 	if (ret < 0)
 		return ret;
 
-	dinfo = open_debuginfo(module, false);
+	dinfo = open_debuginfo(pevs->target, false);
 	if (!dinfo) {
 		ret = -ENOENT;
 		goto out;
@@ -896,8 +958,7 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
 	setup_pager();
 
 	for (i = 0; i < npevs && ret >= 0; i++)
-		ret = show_available_vars_at(dinfo, &pevs[i], max_vls, _filter,
-					     externs, module);
+		ret = show_available_vars_at(dinfo, &pevs[i], _filter);
 
 	debuginfo__delete(dinfo);
 out:
@@ -907,6 +968,10 @@ out:
 
 #else	/* !HAVE_DWARF_SUPPORT */
 
+static void debuginfo_cache__exit(void)
+{
+}
+
 static int
 find_perf_probe_point_from_dwarf(struct probe_trace_point *tp __maybe_unused,
 				 struct perf_probe_point *pp __maybe_unused,
@@ -916,9 +981,7 @@ find_perf_probe_point_from_dwarf(struct probe_trace_point *tp __maybe_unused,
 }
 
 static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
-				struct probe_trace_event **tevs __maybe_unused,
-				int max_tevs __maybe_unused,
-				const char *target __maybe_unused)
+				struct probe_trace_event **tevs __maybe_unused)
 {
 	if (perf_probe_event_need_dwarf(pev)) {
 		pr_warning("Debuginfo-analysis is not supported.\n");
@@ -937,10 +1000,8 @@ int show_line_range(struct line_range *lr __maybe_unused,
 }
 
 int show_available_vars(struct perf_probe_event *pevs __maybe_unused,
-			int npevs __maybe_unused, int max_vls __maybe_unused,
-			const char *module __maybe_unused,
-			struct strfilter *filter __maybe_unused,
-			bool externs __maybe_unused)
+			int npevs __maybe_unused,
+			struct strfilter *filter __maybe_unused)
 {
 	pr_warning("Debuginfo-analysis is not supported.\n");
 	return -ENOSYS;
@@ -980,6 +1041,18 @@ static int parse_line_num(char **ptr, int *val, const char *what)
 	return 0;
 }
 
+/* Check the name is good for event, group or function */
+static bool is_c_func_name(const char *name)
+{
+	if (!isalpha(*name) && *name != '_')
+		return false;
+	while (*++name != '\0') {
+		if (!isalpha(*name) && !isdigit(*name) && *name != '_')
+			return false;
+	}
+	return true;
+}
+
 /*
  * Stuff 'lr' according to the line range described by 'arg'.
  * The line range syntax is described by:
@@ -1048,10 +1121,15 @@ int parse_line_range_desc(const char *arg, struct line_range *lr)
 			goto err;
 		}
 		lr->function = name;
-	} else if (strchr(name, '.'))
+	} else if (strchr(name, '/') || strchr(name, '.'))
 		lr->file = name;
-	else
+	else if (is_c_func_name(name))/* We reuse it for checking funcname */
 		lr->function = name;
+	else {	/* Invalid name */
+		semantic_error("'%s' is not a valid function name.\n", name);
+		err = -EINVAL;
+		goto err;
+	}
 
 	return 0;
 err:
@@ -1059,24 +1137,13 @@ err:
 	return err;
 }
 
-/* Check the name is good for event/group */
-static bool check_event_name(const char *name)
-{
-	if (!isalpha(*name) && *name != '_')
-		return false;
-	while (*++name != '\0') {
-		if (!isalpha(*name) && !isdigit(*name) && *name != '_')
-			return false;
-	}
-	return true;
-}
-
 /* Parse probepoint definition. */
 static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 {
 	struct perf_probe_point *pp = &pev->point;
 	char *ptr, *tmp;
 	char c, nc = 0;
+	bool file_spec = false;
 	/*
 	 * <Syntax>
 	 * perf probe [EVENT=]SRC[:LN|;PTN]
@@ -1095,7 +1162,7 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 			semantic_error("Group name is not supported yet.\n");
 			return -ENOTSUP;
 		}
-		if (!check_event_name(arg)) {
+		if (!is_c_func_name(arg)) {
 			semantic_error("%s is bad for event name -it must "
 				       "follow C symbol-naming rule.\n", arg);
 			return -EINVAL;
@@ -1107,6 +1174,23 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 		arg = tmp;
 	}
 
+	/*
+	 * Check arg is function or file name and copy it.
+	 *
+	 * We consider arg to be a file spec if and only if it satisfies
+	 * all of the below criteria::
+	 * - it does not include any of "+@%",
+	 * - it includes one of ":;", and
+	 * - it has a period '.' in the name.
+	 *
+	 * Otherwise, we consider arg to be a function specification.
+	 */
+	if (!strpbrk(arg, "+@%") && (ptr = strpbrk(arg, ";:")) != NULL) {
+		/* This is a file spec if it includes a '.' before ; or : */
+		if (memchr(arg, '.', ptr - arg))
+			file_spec = true;
+	}
+
 	ptr = strpbrk(arg, ";:+@%");
 	if (ptr) {
 		nc = *ptr;
@@ -1117,10 +1201,9 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 	if (tmp == NULL)
 		return -ENOMEM;
 
-	/* Check arg is function or file and copy it */
-	if (strchr(tmp, '.'))	/* File */
+	if (file_spec)
 		pp->file = tmp;
-	else			/* Function */
+	else
 		pp->function = tmp;
 
 	/* Parse other options */
@@ -1762,8 +1845,7 @@ static int find_perf_probe_point_from_map(struct probe_trace_point *tp,
 
 out:
 	if (map && !is_kprobe) {
-		dso__delete(map->dso);
-		map__delete(map);
+		map__put(map);
 	}
 
 	return ret;
@@ -1877,6 +1959,7 @@ static void clear_probe_trace_event(struct probe_trace_event *tev)
 	free(tev->event);
 	free(tev->group);
 	free(tev->point.symbol);
+	free(tev->point.realname);
 	free(tev->point.module);
 	for (i = 0; i < tev->nargs; i++) {
 		free(tev->args[i].name);
@@ -1954,7 +2037,7 @@ static int open_probe_events(const char *trace_file, bool readwrite)
 	if (ret >= 0) {
 		pr_debug("Opening %s write=%d\n", buf, readwrite);
 		if (readwrite && !probe_event_dry_run)
-			ret = open(buf, O_RDWR, O_APPEND);
+			ret = open(buf, O_RDWR | O_APPEND, 0);
 		else
 			ret = open(buf, O_RDONLY, 0);
 
@@ -2095,9 +2178,31 @@ kprobe_blacklist__find_by_address(struct list_head *blacklist,
 	return NULL;
 }
 
-/* Show an event */
-static int show_perf_probe_event(struct perf_probe_event *pev,
-				 const char *module)
+static LIST_HEAD(kprobe_blacklist);
+
+static void kprobe_blacklist__init(void)
+{
+	if (!list_empty(&kprobe_blacklist))
+		return;
+
+	if (kprobe_blacklist__load(&kprobe_blacklist) < 0)
+		pr_debug("No kprobe blacklist support, ignored\n");
+}
+
+static void kprobe_blacklist__release(void)
+{
+	kprobe_blacklist__delete(&kprobe_blacklist);
+}
+
+static bool kprobe_blacklist__listed(unsigned long address)
+{
+	return !!kprobe_blacklist__find_by_address(&kprobe_blacklist, address);
+}
+
+static int perf_probe_event__sprintf(const char *group, const char *event,
+				     struct perf_probe_event *pev,
+				     const char *module,
+				     struct strbuf *result)
 {
 	int i, ret;
 	char buf[128];
@@ -2108,30 +2213,67 @@ static int show_perf_probe_event(struct perf_probe_event *pev,
 	if (!place)
 		return -EINVAL;
 
-	ret = e_snprintf(buf, 128, "%s:%s", pev->group, pev->event);
+	ret = e_snprintf(buf, 128, "%s:%s", group, event);
 	if (ret < 0)
-		return ret;
+		goto out;
 
-	pr_info("  %-20s (on %s", buf, place);
+	strbuf_addf(result, "  %-20s (on %s", buf, place);
 	if (module)
-		pr_info(" in %s", module);
+		strbuf_addf(result, " in %s", module);
 
 	if (pev->nargs > 0) {
-		pr_info(" with");
+		strbuf_addstr(result, " with");
 		for (i = 0; i < pev->nargs; i++) {
 			ret = synthesize_perf_probe_arg(&pev->args[i],
 							buf, 128);
 			if (ret < 0)
-				break;
-			pr_info(" %s", buf);
+				goto out;
+			strbuf_addf(result, " %s", buf);
 		}
 	}
-	pr_info(")\n");
+	strbuf_addch(result, ')');
+out:
 	free(place);
 	return ret;
 }
 
-static int __show_perf_probe_events(int fd, bool is_kprobe)
+/* Show an event */
+static int show_perf_probe_event(const char *group, const char *event,
+				 struct perf_probe_event *pev,
+				 const char *module, bool use_stdout)
+{
+	struct strbuf buf = STRBUF_INIT;
+	int ret;
+
+	ret = perf_probe_event__sprintf(group, event, pev, module, &buf);
+	if (ret >= 0) {
+		if (use_stdout)
+			printf("%s\n", buf.buf);
+		else
+			pr_info("%s\n", buf.buf);
+	}
+	strbuf_release(&buf);
+
+	return ret;
+}
+
+static bool filter_probe_trace_event(struct probe_trace_event *tev,
+				     struct strfilter *filter)
+{
+	char tmp[128];
+
+	/* At first, check the event name itself */
+	if (strfilter__compare(filter, tev->event))
+		return true;
+
+	/* Next, check the combination of name and group */
+	if (e_snprintf(tmp, 128, "%s:%s", tev->group, tev->event) < 0)
+		return false;
+	return strfilter__compare(filter, tmp);
+}
+
+static int __show_perf_probe_events(int fd, bool is_kprobe,
+				    struct strfilter *filter)
 {
 	int ret = 0;
 	struct probe_trace_event tev;
@@ -2149,24 +2291,31 @@ static int __show_perf_probe_events(int fd, bool is_kprobe)
 	strlist__for_each(ent, rawlist) {
 		ret = parse_probe_trace_command(ent->s, &tev);
 		if (ret >= 0) {
+			if (!filter_probe_trace_event(&tev, filter))
+				goto next;
 			ret = convert_to_perf_probe_event(&tev, &pev,
 								is_kprobe);
-			if (ret >= 0)
-				ret = show_perf_probe_event(&pev,
-							    tev.point.module);
+			if (ret < 0)
+				goto next;
+			ret = show_perf_probe_event(pev.group, pev.event,
+						    &pev, tev.point.module,
+						    true);
 		}
+next:
 		clear_perf_probe_event(&pev);
 		clear_probe_trace_event(&tev);
 		if (ret < 0)
 			break;
 	}
 	strlist__delete(rawlist);
+	/* Cleanup cached debuginfo if needed */
+	debuginfo_cache__exit();
 
 	return ret;
 }
 
 /* List up current perf-probe events */
-int show_perf_probe_events(void)
+int show_perf_probe_events(struct strfilter *filter)
 {
 	int kp_fd, up_fd, ret;
 
@@ -2178,7 +2327,7 @@ int show_perf_probe_events(void)
 
 	kp_fd = open_kprobe_events(false);
 	if (kp_fd >= 0) {
-		ret = __show_perf_probe_events(kp_fd, true);
+		ret = __show_perf_probe_events(kp_fd, true, filter);
 		close(kp_fd);
 		if (ret < 0)
 			goto out;
@@ -2192,7 +2341,7 @@ int show_perf_probe_events(void)
 	}
 
 	if (up_fd >= 0) {
-		ret = __show_perf_probe_events(up_fd, false);
+		ret = __show_perf_probe_events(up_fd, false, filter);
 		close(up_fd);
 	}
 out:
@@ -2266,6 +2415,10 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
 			      struct strlist *namelist, bool allow_suffix)
 {
 	int i, ret;
+	char *p;
+
+	if (*base == '.')
+		base++;
 
 	/* Try no suffix */
 	ret = e_snprintf(buf, len, "%s", base);
@@ -2273,6 +2426,10 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
 		pr_debug("snprintf() failed: %d\n", ret);
 		return ret;
 	}
+	/* Cut off the postfixes (e.g. .const, .isra)*/
+	p = strchr(buf, '.');
+	if (p && p != buf)
+		*p = '\0';
 	if (!strlist__has_entry(namelist, buf))
 		return 0;
 
@@ -2328,10 +2485,9 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 	int i, fd, ret;
 	struct probe_trace_event *tev = NULL;
 	char buf[64];
-	const char *event, *group;
+	const char *event = NULL, *group = NULL;
 	struct strlist *namelist;
-	LIST_HEAD(blacklist);
-	struct kprobe_blacklist_node *node;
+	bool safename;
 
 	if (pev->uprobes)
 		fd = open_uprobe_events(true);
@@ -2347,34 +2503,26 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 	namelist = get_probe_trace_event_names(fd, false);
 	if (!namelist) {
 		pr_debug("Failed to get current event list.\n");
-		return -EIO;
-	}
-	/* Get kprobe blacklist if exists */
-	if (!pev->uprobes) {
-		ret = kprobe_blacklist__load(&blacklist);
-		if (ret < 0)
-			pr_debug("No kprobe blacklist support, ignored\n");
+		ret = -ENOMEM;
+		goto close_out;
 	}
 
+	safename = (pev->point.function && !strisglob(pev->point.function));
 	ret = 0;
 	pr_info("Added new event%s\n", (ntevs > 1) ? "s:" : ":");
 	for (i = 0; i < ntevs; i++) {
 		tev = &tevs[i];
-		/* Ensure that the address is NOT blacklisted */
-		node = kprobe_blacklist__find_by_address(&blacklist,
-							 tev->point.address);
-		if (node) {
-			pr_warning("Warning: Skipped probing on blacklisted function: %s\n", node->symbol);
+		/* Skip if the symbol is out of .text or blacklisted */
+		if (!tev->point.symbol)
 			continue;
-		}
 
 		if (pev->event)
 			event = pev->event;
 		else
-			if (pev->point.function)
+			if (safename)
 				event = pev->point.function;
 			else
-				event = tev->point.symbol;
+				event = tev->point.realname;
 		if (pev->group)
 			group = pev->group;
 		else
@@ -2399,15 +2547,12 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 		/* Add added event name to namelist */
 		strlist__add(namelist, event);
 
-		/* Trick here - save current event/group */
-		event = pev->event;
-		group = pev->group;
-		pev->event = tev->event;
-		pev->group = tev->group;
-		show_perf_probe_event(pev, tev->point.module);
-		/* Trick here - restore current event/group */
-		pev->event = (char *)event;
-		pev->group = (char *)group;
+		/* We use tev's name for showing new events */
+		show_perf_probe_event(tev->group, tev->event, pev,
+				      tev->point.module, false);
+		/* Save the last valid name */
+		event = tev->event;
+		group = tev->group;
 
 		/*
 		 * Probes after the first probe which comes from same
@@ -2421,26 +2566,34 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 		warn_uprobe_event_compat(tev);
 
 	/* Note that it is possible to skip all events because of blacklist */
-	if (ret >= 0 && tev->event) {
+	if (ret >= 0 && event) {
 		/* Show how to use the event. */
 		pr_info("\nYou can now use it in all perf tools, such as:\n\n");
-		pr_info("\tperf record -e %s:%s -aR sleep 1\n\n", tev->group,
-			 tev->event);
+		pr_info("\tperf record -e %s:%s -aR sleep 1\n\n", group, event);
 	}
 
-	kprobe_blacklist__delete(&blacklist);
 	strlist__delete(namelist);
+close_out:
 	close(fd);
 	return ret;
 }
 
-static int find_probe_functions(struct map *map, char *name)
+static int find_probe_functions(struct map *map, char *name,
+				struct symbol **syms)
 {
 	int found = 0;
 	struct symbol *sym;
+	struct rb_node *tmp;
+
+	if (map__load(map, NULL) < 0)
+		return 0;
 
-	map__for_each_symbol_by_name(map, name, sym) {
-		found++;
+	map__for_each_symbol(map, sym, tmp) {
+		if (strglobmatch(sym->name, name)) {
+			found++;
+			if (syms && found < probe_conf.max_probes)
+				syms[found - 1] = sym;
+		}
 	}
 
 	return found;
@@ -2449,42 +2602,52 @@ static int find_probe_functions(struct map *map, char *name)
 #define strdup_or_goto(str, label)	\
 	({ char *__p = strdup(str); if (!__p) goto label; __p; })
 
+void __weak arch__fix_tev_from_maps(struct perf_probe_event *pev __maybe_unused,
+				struct probe_trace_event *tev __maybe_unused,
+				struct map *map __maybe_unused) { }
+
 /*
  * Find probe function addresses from map.
  * Return an error or the number of found probe_trace_event
  */
 static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
-					    struct probe_trace_event **tevs,
-					    int max_tevs, const char *target)
+					    struct probe_trace_event **tevs)
 {
 	struct map *map = NULL;
 	struct ref_reloc_sym *reloc_sym = NULL;
 	struct symbol *sym;
+	struct symbol **syms = NULL;
 	struct probe_trace_event *tev;
 	struct perf_probe_point *pp = &pev->point;
 	struct probe_trace_point *tp;
 	int num_matched_functions;
-	int ret, i;
+	int ret, i, j, skipped = 0;
 
-	map = get_target_map(target, pev->uprobes);
+	map = get_target_map(pev->target, pev->uprobes);
 	if (!map) {
 		ret = -EINVAL;
 		goto out;
 	}
 
+	syms = malloc(sizeof(struct symbol *) * probe_conf.max_probes);
+	if (!syms) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
 	/*
 	 * Load matched symbols: Since the different local symbols may have
 	 * same name but different addresses, this lists all the symbols.
 	 */
-	num_matched_functions = find_probe_functions(map, pp->function);
+	num_matched_functions = find_probe_functions(map, pp->function, syms);
 	if (num_matched_functions == 0) {
 		pr_err("Failed to find symbol %s in %s\n", pp->function,
-			target ? : "kernel");
+			pev->target ? : "kernel");
 		ret = -ENOENT;
 		goto out;
-	} else if (num_matched_functions > max_tevs) {
+	} else if (num_matched_functions > probe_conf.max_probes) {
 		pr_err("Too many functions matched in %s\n",
-			target ? : "kernel");
+			pev->target ? : "kernel");
 		ret = -E2BIG;
 		goto out;
 	}
@@ -2507,7 +2670,9 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 
 	ret = 0;
 
-	map__for_each_symbol_by_name(map, pp->function, sym) {
+	for (j = 0; j < num_matched_functions; j++) {
+		sym = syms[j];
+
 		tev = (*tevs) + ret;
 		tp = &tev->point;
 		if (ret == num_matched_functions) {
@@ -2524,16 +2689,24 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 		}
 		/* Add one probe point */
 		tp->address = map->unmap_ip(map, sym->start) + pp->offset;
-		if (reloc_sym) {
+		/* If we found a wrong one, mark it by NULL symbol */
+		if (!pev->uprobes &&
+		    kprobe_warn_out_range(sym->name, tp->address)) {
+			tp->symbol = NULL;	/* Skip it */
+			skipped++;
+		} else if (reloc_sym) {
 			tp->symbol = strdup_or_goto(reloc_sym->name, nomem_out);
 			tp->offset = tp->address - reloc_sym->addr;
 		} else {
 			tp->symbol = strdup_or_goto(sym->name, nomem_out);
 			tp->offset = pp->offset;
 		}
+		tp->realname = strdup_or_goto(sym->name, nomem_out);
+
 		tp->retprobe = pp->retprobe;
-		if (target)
-			tev->point.module = strdup_or_goto(target, nomem_out);
+		if (pev->target)
+			tev->point.module = strdup_or_goto(pev->target,
+							   nomem_out);
 		tev->uprobes = pev->uprobes;
 		tev->nargs = pev->nargs;
 		if (tev->nargs) {
@@ -2555,10 +2728,16 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 					strdup_or_goto(pev->args[i].type,
 							nomem_out);
 		}
+		arch__fix_tev_from_maps(pev, tev, map);
+	}
+	if (ret == skipped) {
+		ret = -ENOENT;
+		goto err_out;
 	}
 
 out:
 	put_target_map(map, pev->uprobes);
+	free(syms);
 	return ret;
 
 nomem_out:
@@ -2569,27 +2748,34 @@ err_out:
 	goto out;
 }
 
+bool __weak arch__prefers_symtab(void) { return false; }
+
 static int convert_to_probe_trace_events(struct perf_probe_event *pev,
-					  struct probe_trace_event **tevs,
-					  int max_tevs, const char *target)
+					 struct probe_trace_event **tevs)
 {
 	int ret;
 
 	if (pev->uprobes && !pev->group) {
 		/* Replace group name if not given */
-		ret = convert_exec_to_group(target, &pev->group);
+		ret = convert_exec_to_group(pev->target, &pev->group);
 		if (ret != 0) {
 			pr_warning("Failed to make a group name.\n");
 			return ret;
 		}
 	}
 
+	if (arch__prefers_symtab() && !perf_probe_event_need_dwarf(pev)) {
+		ret = find_probe_trace_events_from_map(pev, tevs);
+		if (ret > 0)
+			return ret; /* Found in symbol table */
+	}
+
 	/* Convert perf_probe_event with debuginfo */
-	ret = try_to_find_probe_trace_events(pev, tevs, max_tevs, target);
+	ret = try_to_find_probe_trace_events(pev, tevs);
 	if (ret != 0)
 		return ret;	/* Found in debuginfo or got an error */
 
-	return find_probe_trace_events_from_map(pev, tevs, max_tevs, target);
+	return find_probe_trace_events_from_map(pev, tevs);
 }
 
 struct __event_package {
@@ -2598,8 +2784,7 @@ struct __event_package {
 	int				ntevs;
 };
 
-int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
-			  int max_tevs, bool force_add)
+int add_perf_probe_events(struct perf_probe_event *pevs, int npevs)
 {
 	int i, j, ret;
 	struct __event_package *pkgs;
@@ -2619,20 +2804,24 @@ int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
 	/* Loop 1: convert all events */
 	for (i = 0; i < npevs; i++) {
 		pkgs[i].pev = &pevs[i];
+		/* Init kprobe blacklist if needed */
+		if (!pkgs[i].pev->uprobes)
+			kprobe_blacklist__init();
 		/* Convert with or without debuginfo */
 		ret  = convert_to_probe_trace_events(pkgs[i].pev,
-						     &pkgs[i].tevs,
-						     max_tevs,
-						     pkgs[i].pev->target);
+						     &pkgs[i].tevs);
 		if (ret < 0)
 			goto end;
 		pkgs[i].ntevs = ret;
 	}
+	/* This just release blacklist only if allocated */
+	kprobe_blacklist__release();
 
 	/* Loop 2: add all events */
 	for (i = 0; i < npevs; i++) {
 		ret = __add_probe_trace_events(pkgs[i].pev, pkgs[i].tevs,
-						pkgs[i].ntevs, force_add);
+					       pkgs[i].ntevs,
+					       probe_conf.force_add);
 		if (ret < 0)
 			break;
 	}
@@ -2684,40 +2873,39 @@ error:
 	return ret;
 }
 
-static int del_trace_probe_event(int fd, const char *buf,
-						  struct strlist *namelist)
+static int del_trace_probe_events(int fd, struct strfilter *filter,
+				  struct strlist *namelist)
 {
-	struct str_node *ent, *n;
-	int ret = -1;
+	struct str_node *ent;
+	const char *p;
+	int ret = -ENOENT;
 
-	if (strpbrk(buf, "*?")) { /* Glob-exp */
-		strlist__for_each_safe(ent, n, namelist)
-			if (strglobmatch(ent->s, buf)) {
-				ret = __del_trace_probe_event(fd, ent);
-				if (ret < 0)
-					break;
-				strlist__remove(namelist, ent);
-			}
-	} else {
-		ent = strlist__find(namelist, buf);
-		if (ent) {
+	if (!namelist)
+		return -ENOENT;
+
+	strlist__for_each(ent, namelist) {
+		p = strchr(ent->s, ':');
+		if ((p && strfilter__compare(filter, p + 1)) ||
+		    strfilter__compare(filter, ent->s)) {
 			ret = __del_trace_probe_event(fd, ent);
-			if (ret >= 0)
-				strlist__remove(namelist, ent);
+			if (ret < 0)
+				break;
 		}
 	}
 
 	return ret;
 }
 
-int del_perf_probe_events(struct strlist *dellist)
+int del_perf_probe_events(struct strfilter *filter)
 {
-	int ret = -1, ufd = -1, kfd = -1;
-	char buf[128];
-	const char *group, *event;
-	char *p, *str;
-	struct str_node *ent;
+	int ret, ret2, ufd = -1, kfd = -1;
 	struct strlist *namelist = NULL, *unamelist = NULL;
+	char *str = strfilter__string(filter);
+
+	if (!str)
+		return -EINVAL;
+
+	pr_debug("Delete filter: \'%s\'\n", str);
 
 	/* Get current event names */
 	kfd = open_kprobe_events(true);
@@ -2730,49 +2918,23 @@ int del_perf_probe_events(struct strlist *dellist)
 
 	if (kfd < 0 && ufd < 0) {
 		print_both_open_warning(kfd, ufd);
+		ret = kfd;
 		goto error;
 	}
 
-	if (namelist == NULL && unamelist == NULL)
+	ret = del_trace_probe_events(kfd, filter, namelist);
+	if (ret < 0 && ret != -ENOENT)
 		goto error;
 
-	strlist__for_each(ent, dellist) {
-		str = strdup(ent->s);
-		if (str == NULL) {
-			ret = -ENOMEM;
-			goto error;
-		}
-		pr_debug("Parsing: %s\n", str);
-		p = strchr(str, ':');
-		if (p) {
-			group = str;
-			*p = '\0';
-			event = p + 1;
-		} else {
-			group = "*";
-			event = str;
-		}
-
-		ret = e_snprintf(buf, 128, "%s:%s", group, event);
-		if (ret < 0) {
-			pr_err("Failed to copy event.");
-			free(str);
-			goto error;
-		}
-
-		pr_debug("Group: %s, Event: %s\n", group, event);
-
-		if (namelist)
-			ret = del_trace_probe_event(kfd, buf, namelist);
-
-		if (unamelist && ret != 0)
-			ret = del_trace_probe_event(ufd, buf, unamelist);
-
-		if (ret != 0)
-			pr_info("Info: Event \"%s\" does not exist.\n", buf);
-
-		free(str);
+	ret2 = del_trace_probe_events(ufd, filter, unamelist);
+	if (ret2 < 0 && ret2 != -ENOENT) {
+		ret = ret2;
+		goto error;
 	}
+	if (ret == -ENOENT && ret2 == -ENOENT)
+		pr_debug("\"%s\" does not hit any event.\n", str);
+		/* Note that this is silently ignored */
+	ret = 0;
 
 error:
 	if (kfd >= 0) {
@@ -2784,6 +2946,7 @@ error:
 		strlist__delete(unamelist);
 		close(ufd);
 	}
+	free(str);
 
 	return ret;
 }
@@ -2837,8 +3000,7 @@ int show_available_funcs(const char *target, struct strfilter *_filter,
 	dso__fprintf_symbols_by_name(map->dso, map->type, stdout);
 end:
 	if (user) {
-		dso__delete(map->dso);
-		map__delete(map);
+		map__put(map);
 	}
 	exit_symbol_maps();
 
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index d6b783447..31db6ee7d 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -6,10 +6,20 @@
 #include "strlist.h"
 #include "strfilter.h"
 
+/* Probe related configurations */
+struct probe_conf {
+	bool	show_ext_vars;
+	bool	show_location_range;
+	bool	force_add;
+	bool	no_inlines;
+	int	max_probes;
+};
+extern struct probe_conf probe_conf;
 extern bool probe_event_dry_run;
 
 /* kprobe-tracer and uprobe-tracer tracing point */
 struct probe_trace_point {
+	char		*realname;	/* function real name (if needed) */
 	char		*symbol;	/* Base symbol */
 	char		*module;	/* Module name */
 	unsigned long	offset;		/* Offset from symbol */
@@ -121,20 +131,18 @@ extern void line_range__clear(struct line_range *lr);
 /* Initialize line range */
 extern int line_range__init(struct line_range *lr);
 
-/* Internal use: Return kernel/module path */
-extern const char *kernel_get_module_path(const char *module);
-
-extern int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
-				 int max_probe_points, bool force_add);
-extern int del_perf_probe_events(struct strlist *dellist);
-extern int show_perf_probe_events(void);
+extern int add_perf_probe_events(struct perf_probe_event *pevs, int npevs);
+extern int del_perf_probe_events(struct strfilter *filter);
+extern int show_perf_probe_events(struct strfilter *filter);
 extern int show_line_range(struct line_range *lr, const char *module,
 			   bool user);
 extern int show_available_vars(struct perf_probe_event *pevs, int npevs,
-			       int max_probe_points, const char *module,
-			       struct strfilter *filter, bool externs);
+			       struct strfilter *filter);
 extern int show_available_funcs(const char *module, struct strfilter *filter,
 				bool user);
+bool arch__prefers_symtab(void);
+void arch__fix_tev_from_maps(struct perf_probe_event *pev,
+			     struct probe_trace_event *tev, struct map *map);
 
 /* Maximum index number of event-name postfix */
 #define MAX_EVENT_INDEX	1024
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 2a76e14db..2da65a710 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -130,7 +130,7 @@ struct debuginfo *debuginfo__new(const char *path)
 			continue;
 		dinfo = __debuginfo__new(buf);
 	}
-	dso__delete(dso);
+	dso__put(dso);
 
 out:
 	/* if failed to open all distro debuginfo, open given binary */
@@ -177,7 +177,7 @@ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr,
 	Dwarf_Word offs = 0;
 	bool ref = false;
 	const char *regs;
-	int ret;
+	int ret, ret2 = 0;
 
 	if (dwarf_attr(vr_die, DW_AT_external, &attr) != NULL)
 		goto static_var;
@@ -187,9 +187,19 @@ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr,
 		return -EINVAL;	/* Broken DIE ? */
 	if (dwarf_getlocation_addr(&attr, addr, &op, &nops, 1) <= 0) {
 		ret = dwarf_entrypc(sp_die, &tmp);
-		if (ret || addr != tmp ||
-		    dwarf_tag(vr_die) != DW_TAG_formal_parameter ||
-		    dwarf_highpc(sp_die, &tmp))
+		if (ret)
+			return -ENOENT;
+
+		if (probe_conf.show_location_range &&
+			(dwarf_tag(vr_die) == DW_TAG_variable)) {
+			ret2 = -ERANGE;
+		} else if (addr != tmp ||
+			dwarf_tag(vr_die) != DW_TAG_formal_parameter) {
+			return -ENOENT;
+		}
+
+		ret = dwarf_highpc(sp_die, &tmp);
+		if (ret)
 			return -ENOENT;
 		/*
 		 * This is fuzzed by fentry mcount. We try to find the
@@ -210,7 +220,7 @@ found:
 	if (op->atom == DW_OP_addr) {
 static_var:
 		if (!tvar)
-			return 0;
+			return ret2;
 		/* Static variables on memory (not stack), make @varname */
 		ret = strlen(dwarf_diename(vr_die));
 		tvar->value = zalloc(ret + 2);
@@ -220,7 +230,7 @@ static_var:
 		tvar->ref = alloc_trace_arg_ref((long)offs);
 		if (tvar->ref == NULL)
 			return -ENOMEM;
-		return 0;
+		return ret2;
 	}
 
 	/* If this is based on frame buffer, set the offset */
@@ -250,14 +260,14 @@ static_var:
 	}
 
 	if (!tvar)
-		return 0;
+		return ret2;
 
 	regs = get_arch_regstr(regn);
 	if (!regs) {
 		/* This should be a bug in DWARF or this tool */
 		pr_warning("Mapping for the register number %u "
 			   "missing on this architecture.\n", regn);
-		return -ERANGE;
+		return -ENOTSUP;
 	}
 
 	tvar->value = strdup(regs);
@@ -269,7 +279,7 @@ static_var:
 		if (tvar->ref == NULL)
 			return -ENOMEM;
 	}
-	return 0;
+	return ret2;
 }
 
 #define BYTES_TO_BITS(nb)	((nb) * BITS_PER_LONG / sizeof(long))
@@ -517,10 +527,12 @@ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
 
 	ret = convert_variable_location(vr_die, pf->addr, pf->fb_ops,
 					&pf->sp_die, pf->tvar);
-	if (ret == -ENOENT || ret == -EINVAL)
-		pr_err("Failed to find the location of %s at this address.\n"
-		       " Perhaps, it has been optimized out.\n", pf->pvar->var);
-	else if (ret == -ENOTSUP)
+	if (ret == -ENOENT || ret == -EINVAL) {
+		pr_err("Failed to find the location of the '%s' variable at this address.\n"
+		       " Perhaps it has been optimized out.\n"
+		       " Use -V with the --range option to show '%s' location range.\n",
+		       pf->pvar->var, pf->pvar->var);
+	} else if (ret == -ENOTSUP)
 		pr_err("Sorry, we don't support this variable location yet.\n");
 	else if (ret == 0 && pf->pvar->field) {
 		ret = convert_variable_fields(vr_die, pf->pvar->var,
@@ -662,9 +674,15 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
 	/* If not a real subprogram, find a real one */
 	if (!die_is_func_def(sc_die)) {
 		if (!die_find_realfunc(&pf->cu_die, pf->addr, &pf->sp_die)) {
-			pr_warning("Failed to find probe point in any "
-				   "functions.\n");
-			return -ENOENT;
+			if (die_find_tailfunc(&pf->cu_die, pf->addr, &pf->sp_die)) {
+				pr_warning("Ignoring tail call from %s\n",
+						dwarf_diename(&pf->sp_die));
+				return 0;
+			} else {
+				pr_warning("Failed to find probe point in any "
+					   "functions.\n");
+				return -ENOENT;
+			}
 		}
 	} else
 		memcpy(&pf->sp_die, sc_die, sizeof(Dwarf_Die));
@@ -719,7 +737,7 @@ static int find_best_scope_cb(Dwarf_Die *fn_die, void *data)
 	}
 	/* If the function name is given, that's what user expects */
 	if (fsp->function) {
-		if (die_compare_name(fn_die, fsp->function)) {
+		if (die_match_name(fn_die, fsp->function)) {
 			memcpy(fsp->die_mem, fn_die, sizeof(Dwarf_Die));
 			fsp->found = true;
 			return 1;
@@ -922,13 +940,14 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 
 	/* Check tag and diename */
 	if (!die_is_func_def(sp_die) ||
-	    !die_compare_name(sp_die, pp->function))
+	    !die_match_name(sp_die, pp->function))
 		return DWARF_CB_OK;
 
 	/* Check declared file */
 	if (pp->file && strtailcmp(pp->file, dwarf_decl_file(sp_die)))
 		return DWARF_CB_OK;
 
+	pr_debug("Matched function: %s\n", dwarf_diename(sp_die));
 	pf->fname = dwarf_decl_file(sp_die);
 	if (pp->line) { /* Function relative line */
 		dwarf_decl_line(sp_die, &pf->lno);
@@ -945,10 +964,20 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 			/* TODO: Check the address in this function */
 			param->retval = call_probe_finder(sp_die, pf);
 		}
-	} else
+	} else if (!probe_conf.no_inlines) {
 		/* Inlined function: search instances */
 		param->retval = die_walk_instances(sp_die,
 					probe_point_inline_cb, (void *)pf);
+		/* This could be a non-existed inline definition */
+		if (param->retval == -ENOENT && strisglob(pp->function))
+			param->retval = 0;
+	}
+
+	/* We need to find other candidates */
+	if (strisglob(pp->function) && param->retval >= 0) {
+		param->retval = 0;	/* We have to clear the result */
+		return DWARF_CB_OK;
+	}
 
 	return DWARF_CB_ABORT; /* Exit; no same symbol in this CU. */
 }
@@ -977,7 +1006,7 @@ static int pubname_search_cb(Dwarf *dbg, Dwarf_Global *gl, void *data)
 		if (dwarf_tag(param->sp_die) != DW_TAG_subprogram)
 			return DWARF_CB_OK;
 
-		if (die_compare_name(param->sp_die, param->function)) {
+		if (die_match_name(param->sp_die, param->function)) {
 			if (!dwarf_offdie(dbg, gl->cu_offset, param->cu_die))
 				return DWARF_CB_OK;
 
@@ -1030,7 +1059,7 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
 		return -ENOMEM;
 
 	/* Fastpath: lookup by function name from .debug_pubnames section */
-	if (pp->function) {
+	if (pp->function && !strisglob(pp->function)) {
 		struct pubname_callback_param pubname_param = {
 			.function = pp->function,
 			.file	  = pp->file,
@@ -1089,6 +1118,7 @@ found:
 struct local_vars_finder {
 	struct probe_finder *pf;
 	struct perf_probe_arg *args;
+	bool vars;
 	int max_args;
 	int nargs;
 	int ret;
@@ -1103,7 +1133,7 @@ static int copy_variables_cb(Dwarf_Die *die_mem, void *data)
 
 	tag = dwarf_tag(die_mem);
 	if (tag == DW_TAG_formal_parameter ||
-	    tag == DW_TAG_variable) {
+	    (tag == DW_TAG_variable && vf->vars)) {
 		if (convert_variable_location(die_mem, vf->pf->addr,
 					      vf->pf->fb_ops, &pf->sp_die,
 					      NULL) == 0) {
@@ -1129,26 +1159,28 @@ static int expand_probe_args(Dwarf_Die *sc_die, struct probe_finder *pf,
 	Dwarf_Die die_mem;
 	int i;
 	int n = 0;
-	struct local_vars_finder vf = {.pf = pf, .args = args,
+	struct local_vars_finder vf = {.pf = pf, .args = args, .vars = false,
 				.max_args = MAX_PROBE_ARGS, .ret = 0};
 
 	for (i = 0; i < pf->pev->nargs; i++) {
 		/* var never be NULL */
-		if (strcmp(pf->pev->args[i].var, "$vars") == 0) {
-			pr_debug("Expanding $vars into:");
-			vf.nargs = n;
-			/* Special local variables */
-			die_find_child(sc_die, copy_variables_cb, (void *)&vf,
-				       &die_mem);
-			pr_debug(" (%d)\n", vf.nargs - n);
-			if (vf.ret < 0)
-				return vf.ret;
-			n = vf.nargs;
-		} else {
+		if (strcmp(pf->pev->args[i].var, PROBE_ARG_VARS) == 0)
+			vf.vars = true;
+		else if (strcmp(pf->pev->args[i].var, PROBE_ARG_PARAMS) != 0) {
 			/* Copy normal argument */
 			args[n] = pf->pev->args[i];
 			n++;
+			continue;
 		}
+		pr_debug("Expanding %s into:", pf->pev->args[i].var);
+		vf.nargs = n;
+		/* Special local variables */
+		die_find_child(sc_die, copy_variables_cb, (void *)&vf,
+			       &die_mem);
+		pr_debug(" (%d)\n", vf.nargs - n);
+		if (vf.ret < 0)
+			return vf.ret;
+		n = vf.nargs;
 	}
 	return n;
 }
@@ -1176,6 +1208,10 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf)
 	if (ret < 0)
 		return ret;
 
+	tev->point.realname = strdup(dwarf_diename(sc_die));
+	if (!tev->point.realname)
+		return -ENOMEM;
+
 	pr_debug("Probe point found: %s+%lu\n", tev->point.symbol,
 		 tev->point.offset);
 
@@ -1213,15 +1249,15 @@ end:
 /* Find probe_trace_events specified by perf_probe_event from debuginfo */
 int debuginfo__find_trace_events(struct debuginfo *dbg,
 				 struct perf_probe_event *pev,
-				 struct probe_trace_event **tevs, int max_tevs)
+				 struct probe_trace_event **tevs)
 {
 	struct trace_event_finder tf = {
 			.pf = {.pev = pev, .callback = add_probe_trace_event},
-			.mod = dbg->mod, .max_tevs = max_tevs};
+			.max_tevs = probe_conf.max_probes, .mod = dbg->mod};
 	int ret;
 
 	/* Allocate result tevs array */
-	*tevs = zalloc(sizeof(struct probe_trace_event) * max_tevs);
+	*tevs = zalloc(sizeof(struct probe_trace_event) * tf.max_tevs);
 	if (*tevs == NULL)
 		return -ENOMEM;
 
@@ -1237,14 +1273,11 @@ int debuginfo__find_trace_events(struct debuginfo *dbg,
 	return (ret < 0) ? ret : tf.ntevs;
 }
 
-#define MAX_VAR_LEN 64
-
 /* Collect available variables in this scope */
 static int collect_variables_cb(Dwarf_Die *die_mem, void *data)
 {
 	struct available_var_finder *af = data;
 	struct variable_list *vl;
-	char buf[MAX_VAR_LEN];
 	int tag, ret;
 
 	vl = &af->vls[af->nvls - 1];
@@ -1255,11 +1288,38 @@ static int collect_variables_cb(Dwarf_Die *die_mem, void *data)
 		ret = convert_variable_location(die_mem, af->pf.addr,
 						af->pf.fb_ops, &af->pf.sp_die,
 						NULL);
-		if (ret == 0) {
-			ret = die_get_varname(die_mem, buf, MAX_VAR_LEN);
-			pr_debug2("Add new var: %s\n", buf);
-			if (ret > 0)
-				strlist__add(vl->vars, buf);
+		if (ret == 0 || ret == -ERANGE) {
+			int ret2;
+			bool externs = !af->child;
+			struct strbuf buf;
+
+			strbuf_init(&buf, 64);
+
+			if (probe_conf.show_location_range) {
+				if (!externs) {
+					if (ret)
+						strbuf_addf(&buf, "[INV]\t");
+					else
+						strbuf_addf(&buf, "[VAL]\t");
+				} else
+					strbuf_addf(&buf, "[EXT]\t");
+			}
+
+			ret2 = die_get_varname(die_mem, &buf);
+
+			if (!ret2 && probe_conf.show_location_range &&
+				!externs) {
+				strbuf_addf(&buf, "\t");
+				ret2 = die_get_var_range(&af->pf.sp_die,
+							die_mem, &buf);
+			}
+
+			pr_debug("Add new var: %s\n", buf.buf);
+			if (ret2 == 0) {
+				strlist__add(vl->vars,
+					strbuf_detach(&buf, NULL));
+			}
+			strbuf_release(&buf);
 		}
 	}
 
@@ -1302,9 +1362,9 @@ static int add_available_vars(Dwarf_Die *sc_die, struct probe_finder *pf)
 	die_find_child(sc_die, collect_variables_cb, (void *)af, &die_mem);
 
 	/* Find external variables */
-	if (!af->externs)
+	if (!probe_conf.show_ext_vars)
 		goto out;
-	/* Don't need to search child DIE for externs. */
+	/* Don't need to search child DIE for external vars. */
 	af->child = false;
 	die_find_child(&pf->cu_die, collect_variables_cb, (void *)af, &die_mem);
 
@@ -1324,17 +1384,16 @@ out:
  */
 int debuginfo__find_available_vars_at(struct debuginfo *dbg,
 				      struct perf_probe_event *pev,
-				      struct variable_list **vls,
-				      int max_vls, bool externs)
+				      struct variable_list **vls)
 {
 	struct available_var_finder af = {
 			.pf = {.pev = pev, .callback = add_available_vars},
 			.mod = dbg->mod,
-			.max_vls = max_vls, .externs = externs};
+			.max_vls = probe_conf.max_probes};
 	int ret;
 
 	/* Allocate result vls array */
-	*vls = zalloc(sizeof(struct variable_list) * max_vls);
+	*vls = zalloc(sizeof(struct variable_list) * af.max_vls);
 	if (*vls == NULL)
 		return -ENOMEM;
 
@@ -1535,7 +1594,7 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data)
 		return DWARF_CB_OK;
 
 	if (die_is_func_def(sp_die) &&
-	    die_compare_name(sp_die, lr->function)) {
+	    die_match_name(sp_die, lr->function)) {
 		lf->fname = dwarf_decl_file(sp_die);
 		dwarf_decl_line(sp_die, &lr->offset);
 		pr_debug("fname: %s, lineno:%d\n", lf->fname, lr->offset);
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index ebf8c8c81..bed82716e 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -10,6 +10,9 @@
 #define MAX_PROBES		 128
 #define MAX_PROBE_ARGS		 128
 
+#define PROBE_ARG_VARS		"$vars"
+#define PROBE_ARG_PARAMS	"$params"
+
 static inline int is_c_varname(const char *name)
 {
 	/* TODO */
@@ -37,8 +40,7 @@ extern void debuginfo__delete(struct debuginfo *dbg);
 /* Find probe_trace_events specified by perf_probe_event from debuginfo */
 extern int debuginfo__find_trace_events(struct debuginfo *dbg,
 					struct perf_probe_event *pev,
-					struct probe_trace_event **tevs,
-					int max_tevs);
+					struct probe_trace_event **tevs);
 
 /* Find a perf_probe_point from debuginfo */
 extern int debuginfo__find_probe_point(struct debuginfo *dbg,
@@ -52,8 +54,7 @@ extern int debuginfo__find_line_range(struct debuginfo *dbg,
 /* Find available variables */
 extern int debuginfo__find_available_vars_at(struct debuginfo *dbg,
 					     struct perf_probe_event *pev,
-					     struct variable_list **vls,
-					     int max_points, bool externs);
+					     struct variable_list **vls);
 
 /* Find a src file from a DWARF tag path */
 int get_real_path(const char *raw_path, const char *comp_dir,
@@ -96,7 +97,6 @@ struct available_var_finder {
 	struct variable_list	*vls;		/* Found variable lists */
 	int			nvls;		/* Number of variable lists */
 	int			max_vls;	/* Max no. of variable lists */
-	bool			externs;	/* Find external vars too */
 	bool			child;		/* Search child scopes */
 };
 
diff --git a/tools/perf/util/pstack.c b/tools/perf/util/pstack.c
index a126e6cc6..b234a6e3d 100644
--- a/tools/perf/util/pstack.c
+++ b/tools/perf/util/pstack.c
@@ -74,3 +74,10 @@ void *pstack__pop(struct pstack *pstack)
 	pstack->entries[pstack->top] = NULL;
 	return ret;
 }
+
+void *pstack__peek(struct pstack *pstack)
+{
+	if (pstack->top == 0)
+		return NULL;
+	return pstack->entries[pstack->top - 1];
+}
diff --git a/tools/perf/util/pstack.h b/tools/perf/util/pstack.h
index c3cb6584d..ded7f2e36 100644
--- a/tools/perf/util/pstack.h
+++ b/tools/perf/util/pstack.h
@@ -10,5 +10,6 @@ bool pstack__empty(const struct pstack *pstack);
 void pstack__remove(struct pstack *pstack, void *key);
 void pstack__push(struct pstack *pstack, void *key);
 void *pstack__pop(struct pstack *pstack);
+void *pstack__peek(struct pstack *pstack);
 
 #endif /* _PERF_PSTACK_ */
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 4d28624a1..0766d98c5 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -10,12 +10,14 @@ util/ctype.c
 util/evlist.c
 util/evsel.c
 util/cpumap.c
-../../lib/hweight.c
+../lib/hweight.c
 util/thread_map.c
 util/util.c
 util/xyarray.c
 util/cgroup.c
 util/rblist.c
+util/stat.c
 util/strlist.c
 util/trace-event.c
-../../lib/rbtree.c
+../lib/rbtree.c
+util/string.c
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index d906d0ad5..626422eda 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -384,7 +384,7 @@ static int pyrf_cpu_map__init(struct pyrf_cpu_map *pcpus,
 
 static void pyrf_cpu_map__delete(struct pyrf_cpu_map *pcpus)
 {
-	cpu_map__delete(pcpus->cpus);
+	cpu_map__put(pcpus->cpus);
 	pcpus->ob_type->tp_free((PyObject*)pcpus);
 }
 
@@ -453,7 +453,7 @@ static int pyrf_thread_map__init(struct pyrf_thread_map *pthreads,
 
 static void pyrf_thread_map__delete(struct pyrf_thread_map *pthreads)
 {
-	thread_map__delete(pthreads->threads);
+	thread_map__put(pthreads->threads);
 	pthreads->ob_type->tp_free((PyObject*)pthreads);
 }
 
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 8acd0df88..1f7becbe5 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -20,7 +20,7 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
 	if (!evlist)
 		return -ENOMEM;
 
-	if (parse_events(evlist, str))
+	if (parse_events(evlist, str, NULL))
 		goto out_delete;
 
 	evsel = perf_evlist__first(evlist);
@@ -64,7 +64,7 @@ static bool perf_probe_api(setup_probe_fn_t fn)
 	if (!cpus)
 		return false;
 	cpu = cpus->map[0];
-	cpu_map__delete(cpus);
+	cpu_map__put(cpus);
 
 	do {
 		ret = perf_do_probe_api(fn, cpu, try[i++]);
@@ -119,7 +119,16 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
 			evsel->attr.comm_exec = 1;
 	}
 
-	if (evlist->nr_entries > 1) {
+	if (opts->full_auxtrace) {
+		/*
+		 * Need to be able to synthesize and parse selected events with
+		 * arbitrary sample types, which requires always being able to
+		 * match the id.
+		 */
+		use_sample_identifier = perf_can_sample_identifier();
+		evlist__for_each(evlist, evsel)
+			perf_evsel__set_sample_id(evsel, use_sample_identifier);
+	} else if (evlist->nr_entries > 1) {
 		struct perf_evsel *first = perf_evlist__first(evlist);
 
 		evlist__for_each(evlist, evsel) {
@@ -207,7 +216,7 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str)
 	if (!temp_evlist)
 		return false;
 
-	err = parse_events(temp_evlist, str);
+	err = parse_events(temp_evlist, str, NULL);
 	if (err)
 		goto out_delete;
 
@@ -217,7 +226,7 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str)
 		struct cpu_map *cpus = cpu_map__new(NULL);
 
 		cpu =  cpus ? cpus->map[0] : 0;
-		cpu_map__delete(cpus);
+		cpu_map__put(cpus);
 	} else {
 		cpu = evlist->cpus->map[0];
 	}
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 430b5d278..1bd593bbf 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -55,10 +55,10 @@ void xs_init(pTHX)
 
 INTERP my_perl;
 
-#define FTRACE_MAX_EVENT				\
+#define TRACE_EVENT_TYPE_MAX				\
 	((1 << (sizeof(unsigned short) * 8)) - 1)
 
-static DECLARE_BITMAP(events_defined, FTRACE_MAX_EVENT);
+static DECLARE_BITMAP(events_defined, TRACE_EVENT_TYPE_MAX);
 
 extern struct scripting_context *scripting_context;
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 5544b8cdd..ace248498 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -44,10 +44,10 @@
 
 PyMODINIT_FUNC initperf_trace_context(void);
 
-#define FTRACE_MAX_EVENT				\
+#define TRACE_EVENT_TYPE_MAX				\
 	((1 << (sizeof(unsigned short) * 8)) - 1)
 
-static DECLARE_BITMAP(events_defined, FTRACE_MAX_EVENT);
+static DECLARE_BITMAP(events_defined, TRACE_EVENT_TYPE_MAX);
 
 #define MAX_FIELDS	64
 #define N_COMMON_FIELDS	7
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 0c7401257..ed9dc2555 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -15,12 +15,14 @@
 #include "cpumap.h"
 #include "perf_regs.h"
 #include "asm/bug.h"
+#include "auxtrace.h"
+#include "thread-stack.h"
 
-static int machines__deliver_event(struct machines *machines,
-				   struct perf_evlist *evlist,
-				   union perf_event *event,
-				   struct perf_sample *sample,
-				   struct perf_tool *tool, u64 file_offset);
+static int perf_session__deliver_event(struct perf_session *session,
+				       union perf_event *event,
+				       struct perf_sample *sample,
+				       struct perf_tool *tool,
+				       u64 file_offset);
 
 static int perf_session__open(struct perf_session *session)
 {
@@ -105,8 +107,8 @@ static int ordered_events__deliver_event(struct ordered_events *oe,
 		return ret;
 	}
 
-	return machines__deliver_event(&session->machines, session->evlist, event->event,
-				       &sample, session->tool, event->file_offset);
+	return perf_session__deliver_event(session, event->event, &sample,
+					   session->tool, event->file_offset);
 }
 
 struct perf_session *perf_session__new(struct perf_data_file *file,
@@ -119,6 +121,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
 
 	session->repipe = repipe;
 	session->tool   = tool;
+	INIT_LIST_HEAD(&session->auxtrace_index);
 	machines__init(&session->machines);
 	ordered_events__init(&session->ordered_events, ordered_events__deliver_event);
 
@@ -185,6 +188,8 @@ static void perf_session_env__delete(struct perf_session_env *env)
 
 void perf_session__delete(struct perf_session *session)
 {
+	auxtrace__free(session);
+	auxtrace_index__free(&session->auxtrace_index);
 	perf_session__destroy_kernel_maps(session);
 	perf_session__delete_threads(session);
 	perf_session_env__delete(&session->header.env);
@@ -262,6 +267,49 @@ static int process_id_index_stub(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
+static int process_event_auxtrace_info_stub(struct perf_tool *tool __maybe_unused,
+				union perf_event *event __maybe_unused,
+				struct perf_session *session __maybe_unused)
+{
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
+static int skipn(int fd, off_t n)
+{
+	char buf[4096];
+	ssize_t ret;
+
+	while (n > 0) {
+		ret = read(fd, buf, min(n, (off_t)sizeof(buf)));
+		if (ret <= 0)
+			return ret;
+		n -= ret;
+	}
+
+	return 0;
+}
+
+static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
+				       union perf_event *event,
+				       struct perf_session *session
+				       __maybe_unused)
+{
+	dump_printf(": unhandled!\n");
+	if (perf_data_file__is_pipe(session->file))
+		skipn(perf_data_file__fd(session->file), event->auxtrace.size);
+	return event->auxtrace.size;
+}
+
+static
+int process_event_auxtrace_error_stub(struct perf_tool *tool __maybe_unused,
+				      union perf_event *event __maybe_unused,
+				      struct perf_session *session __maybe_unused)
+{
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
 void perf_tool__fill_defaults(struct perf_tool *tool)
 {
 	if (tool->sample == NULL)
@@ -278,6 +326,12 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		tool->exit = process_event_stub;
 	if (tool->lost == NULL)
 		tool->lost = perf_event__process_lost;
+	if (tool->lost_samples == NULL)
+		tool->lost_samples = perf_event__process_lost_samples;
+	if (tool->aux == NULL)
+		tool->aux = perf_event__process_aux;
+	if (tool->itrace_start == NULL)
+		tool->itrace_start = perf_event__process_itrace_start;
 	if (tool->read == NULL)
 		tool->read = process_event_sample_stub;
 	if (tool->throttle == NULL)
@@ -298,6 +352,12 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 	}
 	if (tool->id_index == NULL)
 		tool->id_index = process_id_index_stub;
+	if (tool->auxtrace_info == NULL)
+		tool->auxtrace_info = process_event_auxtrace_info_stub;
+	if (tool->auxtrace == NULL)
+		tool->auxtrace = process_event_auxtrace_stub;
+	if (tool->auxtrace_error == NULL)
+		tool->auxtrace_error = process_event_auxtrace_error_stub;
 }
 
 static void swap_sample_id_all(union perf_event *event, void *data)
@@ -390,6 +450,26 @@ static void perf_event__read_swap(union perf_event *event, bool sample_id_all)
 		swap_sample_id_all(event, &event->read + 1);
 }
 
+static void perf_event__aux_swap(union perf_event *event, bool sample_id_all)
+{
+	event->aux.aux_offset = bswap_64(event->aux.aux_offset);
+	event->aux.aux_size   = bswap_64(event->aux.aux_size);
+	event->aux.flags      = bswap_64(event->aux.flags);
+
+	if (sample_id_all)
+		swap_sample_id_all(event, &event->aux + 1);
+}
+
+static void perf_event__itrace_start_swap(union perf_event *event,
+					  bool sample_id_all)
+{
+	event->itrace_start.pid	 = bswap_32(event->itrace_start.pid);
+	event->itrace_start.tid	 = bswap_32(event->itrace_start.tid);
+
+	if (sample_id_all)
+		swap_sample_id_all(event, &event->itrace_start + 1);
+}
+
 static void perf_event__throttle_swap(union perf_event *event,
 				      bool sample_id_all)
 {
@@ -438,19 +518,42 @@ void perf_event__attr_swap(struct perf_event_attr *attr)
 {
 	attr->type		= bswap_32(attr->type);
 	attr->size		= bswap_32(attr->size);
-	attr->config		= bswap_64(attr->config);
-	attr->sample_period	= bswap_64(attr->sample_period);
-	attr->sample_type	= bswap_64(attr->sample_type);
-	attr->read_format	= bswap_64(attr->read_format);
-	attr->wakeup_events	= bswap_32(attr->wakeup_events);
-	attr->bp_type		= bswap_32(attr->bp_type);
-	attr->bp_addr		= bswap_64(attr->bp_addr);
-	attr->bp_len		= bswap_64(attr->bp_len);
-	attr->branch_sample_type = bswap_64(attr->branch_sample_type);
-	attr->sample_regs_user	 = bswap_64(attr->sample_regs_user);
-	attr->sample_stack_user  = bswap_32(attr->sample_stack_user);
 
-	swap_bitfield((u8 *) (&attr->read_format + 1), sizeof(u64));
+#define bswap_safe(f, n) 					\
+	(attr->size > (offsetof(struct perf_event_attr, f) + 	\
+		       sizeof(attr->f) * (n)))
+#define bswap_field(f, sz) 			\
+do { 						\
+	if (bswap_safe(f, 0))			\
+		attr->f = bswap_##sz(attr->f);	\
+} while(0)
+#define bswap_field_32(f) bswap_field(f, 32)
+#define bswap_field_64(f) bswap_field(f, 64)
+
+	bswap_field_64(config);
+	bswap_field_64(sample_period);
+	bswap_field_64(sample_type);
+	bswap_field_64(read_format);
+	bswap_field_32(wakeup_events);
+	bswap_field_32(bp_type);
+	bswap_field_64(bp_addr);
+	bswap_field_64(bp_len);
+	bswap_field_64(branch_sample_type);
+	bswap_field_64(sample_regs_user);
+	bswap_field_32(sample_stack_user);
+	bswap_field_32(aux_watermark);
+
+	/*
+	 * After read_format are bitfields. Check read_format because
+	 * we are unable to use offsetof on bitfield.
+	 */
+	if (bswap_safe(read_format, 1))
+		swap_bitfield((u8 *) (&attr->read_format + 1),
+			      sizeof(u64));
+#undef bswap_field_64
+#undef bswap_field_32
+#undef bswap_field
+#undef bswap_safe
 }
 
 static void perf_event__hdr_attr_swap(union perf_event *event,
@@ -478,6 +581,40 @@ static void perf_event__tracing_data_swap(union perf_event *event,
 	event->tracing_data.size = bswap_32(event->tracing_data.size);
 }
 
+static void perf_event__auxtrace_info_swap(union perf_event *event,
+					   bool sample_id_all __maybe_unused)
+{
+	size_t size;
+
+	event->auxtrace_info.type = bswap_32(event->auxtrace_info.type);
+
+	size = event->header.size;
+	size -= (void *)&event->auxtrace_info.priv - (void *)event;
+	mem_bswap_64(event->auxtrace_info.priv, size);
+}
+
+static void perf_event__auxtrace_swap(union perf_event *event,
+				      bool sample_id_all __maybe_unused)
+{
+	event->auxtrace.size      = bswap_64(event->auxtrace.size);
+	event->auxtrace.offset    = bswap_64(event->auxtrace.offset);
+	event->auxtrace.reference = bswap_64(event->auxtrace.reference);
+	event->auxtrace.idx       = bswap_32(event->auxtrace.idx);
+	event->auxtrace.tid       = bswap_32(event->auxtrace.tid);
+	event->auxtrace.cpu       = bswap_32(event->auxtrace.cpu);
+}
+
+static void perf_event__auxtrace_error_swap(union perf_event *event,
+					    bool sample_id_all __maybe_unused)
+{
+	event->auxtrace_error.type = bswap_32(event->auxtrace_error.type);
+	event->auxtrace_error.code = bswap_32(event->auxtrace_error.code);
+	event->auxtrace_error.cpu  = bswap_32(event->auxtrace_error.cpu);
+	event->auxtrace_error.pid  = bswap_32(event->auxtrace_error.pid);
+	event->auxtrace_error.tid  = bswap_32(event->auxtrace_error.tid);
+	event->auxtrace_error.ip   = bswap_64(event->auxtrace_error.ip);
+}
+
 typedef void (*perf_event__swap_op)(union perf_event *event,
 				    bool sample_id_all);
 
@@ -492,11 +629,17 @@ static perf_event__swap_op perf_event__swap_ops[] = {
 	[PERF_RECORD_THROTTLE]		  = perf_event__throttle_swap,
 	[PERF_RECORD_UNTHROTTLE]	  = perf_event__throttle_swap,
 	[PERF_RECORD_SAMPLE]		  = perf_event__all64_swap,
+	[PERF_RECORD_AUX]		  = perf_event__aux_swap,
+	[PERF_RECORD_ITRACE_START]	  = perf_event__itrace_start_swap,
+	[PERF_RECORD_LOST_SAMPLES]	  = perf_event__all64_swap,
 	[PERF_RECORD_HEADER_ATTR]	  = perf_event__hdr_attr_swap,
 	[PERF_RECORD_HEADER_EVENT_TYPE]	  = perf_event__event_type_swap,
 	[PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,
 	[PERF_RECORD_HEADER_BUILD_ID]	  = NULL,
 	[PERF_RECORD_ID_INDEX]		  = perf_event__all64_swap,
+	[PERF_RECORD_AUXTRACE_INFO]	  = perf_event__auxtrace_info_swap,
+	[PERF_RECORD_AUXTRACE]		  = perf_event__auxtrace_swap,
+	[PERF_RECORD_AUXTRACE_ERROR]	  = perf_event__auxtrace_error_swap,
 	[PERF_RECORD_HEADER_MAX]	  = NULL,
 };
 
@@ -543,6 +686,8 @@ static int process_finished_round(struct perf_tool *tool __maybe_unused,
 				  union perf_event *event __maybe_unused,
 				  struct ordered_events *oe)
 {
+	if (dump_trace)
+		fprintf(stdout, "\n");
 	return ordered_events__flush(oe, OE_FLUSH__ROUND);
 }
 
@@ -921,6 +1066,8 @@ static int machines__deliver_event(struct machines *machines,
 	case PERF_RECORD_MMAP:
 		return tool->mmap(tool, event, sample, machine);
 	case PERF_RECORD_MMAP2:
+		if (event->header.misc & PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT)
+			++evlist->stats.nr_proc_map_timeout;
 		return tool->mmap2(tool, event, sample, machine);
 	case PERF_RECORD_COMM:
 		return tool->comm(tool, event, sample, machine);
@@ -932,18 +1079,44 @@ static int machines__deliver_event(struct machines *machines,
 		if (tool->lost == perf_event__process_lost)
 			evlist->stats.total_lost += event->lost.lost;
 		return tool->lost(tool, event, sample, machine);
+	case PERF_RECORD_LOST_SAMPLES:
+		if (tool->lost_samples == perf_event__process_lost_samples)
+			evlist->stats.total_lost_samples += event->lost_samples.lost;
+		return tool->lost_samples(tool, event, sample, machine);
 	case PERF_RECORD_READ:
 		return tool->read(tool, event, sample, evsel, machine);
 	case PERF_RECORD_THROTTLE:
 		return tool->throttle(tool, event, sample, machine);
 	case PERF_RECORD_UNTHROTTLE:
 		return tool->unthrottle(tool, event, sample, machine);
+	case PERF_RECORD_AUX:
+		return tool->aux(tool, event, sample, machine);
+	case PERF_RECORD_ITRACE_START:
+		return tool->itrace_start(tool, event, sample, machine);
 	default:
 		++evlist->stats.nr_unknown_events;
 		return -1;
 	}
 }
 
+static int perf_session__deliver_event(struct perf_session *session,
+				       union perf_event *event,
+				       struct perf_sample *sample,
+				       struct perf_tool *tool,
+				       u64 file_offset)
+{
+	int ret;
+
+	ret = auxtrace__process_event(session, event, sample, tool);
+	if (ret < 0)
+		return ret;
+	if (ret > 0)
+		return 0;
+
+	return machines__deliver_event(&session->machines, session->evlist,
+				       event, sample, tool, file_offset);
+}
+
 static s64 perf_session__process_user_event(struct perf_session *session,
 					    union perf_event *event,
 					    u64 file_offset)
@@ -980,6 +1153,15 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 		return tool->finished_round(tool, event, oe);
 	case PERF_RECORD_ID_INDEX:
 		return tool->id_index(tool, event, session);
+	case PERF_RECORD_AUXTRACE_INFO:
+		return tool->auxtrace_info(tool, event, session);
+	case PERF_RECORD_AUXTRACE:
+		/* setup for reading amidst mmap */
+		lseek(fd, file_offset + event->header.size, SEEK_SET);
+		return tool->auxtrace(tool, event, session);
+	case PERF_RECORD_AUXTRACE_ERROR:
+		perf_session__auxtrace_error_inc(session, event);
+		return tool->auxtrace_error(tool, event, session);
 	default:
 		return -EINVAL;
 	}
@@ -1034,7 +1216,7 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset,
 		return -1;
 
 	if (lseek(fd, file_offset, SEEK_SET) == (off_t)-1 ||
-	    readn(fd, &buf, hdr_sz) != (ssize_t)hdr_sz)
+	    readn(fd, buf, hdr_sz) != (ssize_t)hdr_sz)
 		return -1;
 
 	event = (union perf_event *)buf;
@@ -1042,12 +1224,12 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset,
 	if (session->header.needs_swap)
 		perf_event_header__bswap(&event->header);
 
-	if (event->header.size < hdr_sz)
+	if (event->header.size < hdr_sz || event->header.size > buf_sz)
 		return -1;
 
 	rest = event->header.size - hdr_sz;
 
-	if (readn(fd, &buf, rest) != (ssize_t)rest)
+	if (readn(fd, buf, rest) != (ssize_t)rest)
 		return -1;
 
 	if (session->header.needs_swap)
@@ -1096,8 +1278,8 @@ static s64 perf_session__process_event(struct perf_session *session,
 			return ret;
 	}
 
-	return machines__deliver_event(&session->machines, evlist, event,
-				       &sample, tool, file_offset);
+	return perf_session__deliver_event(session, event, &sample, tool,
+					   file_offset);
 }
 
 void perf_event_header__bswap(struct perf_event_header *hdr)
@@ -1138,6 +1320,18 @@ static void perf_session__warn_about_errors(const struct perf_session *session)
 			    stats->nr_events[PERF_RECORD_LOST]);
 	}
 
+	if (session->tool->lost_samples == perf_event__process_lost_samples) {
+		double drop_rate;
+
+		drop_rate = (double)stats->total_lost_samples /
+			    (double) (stats->nr_events[PERF_RECORD_SAMPLE] + stats->total_lost_samples);
+		if (drop_rate > 0.05) {
+			ui__warning("Processed %" PRIu64 " samples and lost %3.2f%% samples!\n\n",
+				    stats->nr_events[PERF_RECORD_SAMPLE] + stats->total_lost_samples,
+				    drop_rate * 100.0);
+		}
+	}
+
 	if (stats->nr_unknown_events != 0) {
 		ui__warning("Found %u unknown events!\n\n"
 			    "Is this an older tool processing a perf.data "
@@ -1168,6 +1362,32 @@ static void perf_session__warn_about_errors(const struct perf_session *session)
 
 	if (oe->nr_unordered_events != 0)
 		ui__warning("%u out of order events recorded.\n", oe->nr_unordered_events);
+
+	events_stats__auxtrace_error_warn(stats);
+
+	if (stats->nr_proc_map_timeout != 0) {
+		ui__warning("%d map information files for pre-existing threads were\n"
+			    "not processed, if there are samples for addresses they\n"
+			    "will not be resolved, you may find out which are these\n"
+			    "threads by running with -v and redirecting the output\n"
+			    "to a file.\n"
+			    "The time limit to process proc map is too short?\n"
+			    "Increase it by --proc-map-timeout\n",
+			    stats->nr_proc_map_timeout);
+	}
+}
+
+static int perf_session__flush_thread_stack(struct thread *thread,
+					    void *p __maybe_unused)
+{
+	return thread_stack__flush(thread);
+}
+
+static int perf_session__flush_thread_stacks(struct perf_session *session)
+{
+	return machines__for_each_thread(&session->machines,
+					 perf_session__flush_thread_stack,
+					 NULL);
 }
 
 volatile int session_done;
@@ -1256,10 +1476,17 @@ more:
 done:
 	/* do the final flush for ordered samples */
 	err = ordered_events__flush(oe, OE_FLUSH__FINAL);
+	if (err)
+		goto out_err;
+	err = auxtrace__flush_events(session, tool);
+	if (err)
+		goto out_err;
+	err = perf_session__flush_thread_stacks(session);
 out_err:
 	free(buf);
 	perf_session__warn_about_errors(session);
 	ordered_events__free(&session->ordered_events);
+	auxtrace__free_events(session);
 	return err;
 }
 
@@ -1402,10 +1629,17 @@ more:
 out:
 	/* do the final flush for ordered samples */
 	err = ordered_events__flush(oe, OE_FLUSH__FINAL);
+	if (err)
+		goto out_err;
+	err = auxtrace__flush_events(session, tool);
+	if (err)
+		goto out_err;
+	err = perf_session__flush_thread_stacks(session);
 out_err:
 	ui_progress__finish();
 	perf_session__warn_about_errors(session);
 	ordered_events__free(&session->ordered_events);
+	auxtrace__free_events(session);
 	session->one_mmap = false;
 	return err;
 }
@@ -1488,7 +1722,13 @@ size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp
 
 size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
 {
-	size_t ret = fprintf(fp, "Aggregated stats:\n");
+	size_t ret;
+	const char *msg = "";
+
+	if (perf_header__has_feat(&session->header, HEADER_AUXTRACE))
+		msg = " (excludes AUX area (e.g. instruction trace) decoded / synthesized events)";
+
+	ret = fprintf(fp, "\nAggregated stats:%s\n", msg);
 
 	ret += events_stats__fprintf(&session->evlist->stats, fp);
 	return ret;
@@ -1655,7 +1895,7 @@ int perf_session__cpu_bitmap(struct perf_session *session,
 	err = 0;
 
 out_delete_map:
-	cpu_map__delete(map);
+	cpu_map__put(map);
 	return err;
 }
 
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index d5fa7b791..b44afc75d 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -15,10 +15,16 @@
 struct ip_callchain;
 struct thread;
 
+struct auxtrace;
+struct itrace_synth_opts;
+
 struct perf_session {
 	struct perf_header	header;
 	struct machines		machines;
 	struct perf_evlist	*evlist;
+	struct auxtrace		*auxtrace;
+	struct itrace_synth_opts *itrace_synth_opts;
+	struct list_head	auxtrace_index;
 	struct trace_event	tevent;
 	bool			repipe;
 	bool			one_mmap;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 4593f36ec..4c65a143a 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -89,14 +89,14 @@ static int64_t
 sort__comm_cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	/* Compare the addr that should be unique among comm */
-	return comm__str(right->comm) - comm__str(left->comm);
+	return strcmp(comm__str(right->comm), comm__str(left->comm));
 }
 
 static int64_t
 sort__comm_collapse(struct hist_entry *left, struct hist_entry *right)
 {
 	/* Compare the addr that should be unique among comm */
-	return comm__str(right->comm) - comm__str(left->comm);
+	return strcmp(comm__str(right->comm), comm__str(left->comm));
 }
 
 static int64_t
@@ -182,18 +182,16 @@ static int64_t _sort__addr_cmp(u64 left_ip, u64 right_ip)
 
 static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r)
 {
-	u64 ip_l, ip_r;
-
 	if (!sym_l || !sym_r)
 		return cmp_null(sym_l, sym_r);
 
 	if (sym_l == sym_r)
 		return 0;
 
-	ip_l = sym_l->start;
-	ip_r = sym_r->start;
+	if (sym_l->start != sym_r->start)
+		return (int64_t)(sym_r->start - sym_l->start);
 
-	return (int64_t)(ip_r - ip_l);
+	return (int64_t)(sym_r->end - sym_l->end);
 }
 
 static int64_t
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 846036a92..e97cd476d 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -58,15 +58,16 @@ struct he_stat {
 
 struct hist_entry_diff {
 	bool	computed;
+	union {
+		/* PERF_HPP__DELTA */
+		double	period_ratio_delta;
 
-	/* PERF_HPP__DELTA */
-	double	period_ratio_delta;
-
-	/* PERF_HPP__RATIO */
-	double	period_ratio;
+		/* PERF_HPP__RATIO */
+		double	period_ratio;
 
-	/* HISTC_WEIGHTED_DIFF */
-	s64	wdiff;
+		/* HISTC_WEIGHTED_DIFF */
+		s64	wdiff;
+	};
 };
 
 /**
@@ -92,21 +93,28 @@ struct hist_entry {
 	s32			cpu;
 	u8			cpumode;
 
-	struct hist_entry_diff	diff;
-
 	/* We are added by hists__add_dummy_entry. */
 	bool			dummy;
 
-	/* XXX These two should move to some tree widget lib */
-	u16			row_offset;
-	u16			nr_rows;
-
-	bool			init_have_children;
 	char			level;
 	u8			filtered;
+	union {
+		/*
+		 * Since perf diff only supports the stdio output, TUI
+		 * fields are only accessed from perf report (or perf
+		 * top).  So make it an union to reduce memory usage.
+		 */
+		struct hist_entry_diff	diff;
+		struct /* for TUI */ {
+			u16	row_offset;
+			u16	nr_rows;
+			bool	init_have_children;
+			bool	unfolded;
+			bool	has_children;
+		};
+	};
 	char			*srcline;
 	struct symbol		*parent;
-	unsigned long		position;
 	struct rb_root		sorted_chain;
 	struct branch_info	*branch_info;
 	struct hists		*hists;
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
new file mode 100644
index 000000000..2a5d8d769
--- /dev/null
+++ b/tools/perf/util/stat-shadow.c
@@ -0,0 +1,432 @@
+#include <stdio.h>
+#include "evsel.h"
+#include "stat.h"
+#include "color.h"
+
+enum {
+	CTX_BIT_USER	= 1 << 0,
+	CTX_BIT_KERNEL	= 1 << 1,
+	CTX_BIT_HV	= 1 << 2,
+	CTX_BIT_HOST	= 1 << 3,
+	CTX_BIT_IDLE	= 1 << 4,
+	CTX_BIT_MAX	= 1 << 5,
+};
+
+#define NUM_CTX CTX_BIT_MAX
+
+static struct stats runtime_nsecs_stats[MAX_NR_CPUS];
+static struct stats runtime_cycles_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_stalled_cycles_front_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_stalled_cycles_back_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_branches_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_cacherefs_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_l1_dcache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_l1_icache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_ll_cache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_itlb_cache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_dtlb_cache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_cycles_in_tx_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_transaction_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_elision_stats[NUM_CTX][MAX_NR_CPUS];
+
+struct stats walltime_nsecs_stats;
+
+static int evsel_context(struct perf_evsel *evsel)
+{
+	int ctx = 0;
+
+	if (evsel->attr.exclude_kernel)
+		ctx |= CTX_BIT_KERNEL;
+	if (evsel->attr.exclude_user)
+		ctx |= CTX_BIT_USER;
+	if (evsel->attr.exclude_hv)
+		ctx |= CTX_BIT_HV;
+	if (evsel->attr.exclude_host)
+		ctx |= CTX_BIT_HOST;
+	if (evsel->attr.exclude_idle)
+		ctx |= CTX_BIT_IDLE;
+
+	return ctx;
+}
+
+void perf_stat__reset_shadow_stats(void)
+{
+	memset(runtime_nsecs_stats, 0, sizeof(runtime_nsecs_stats));
+	memset(runtime_cycles_stats, 0, sizeof(runtime_cycles_stats));
+	memset(runtime_stalled_cycles_front_stats, 0, sizeof(runtime_stalled_cycles_front_stats));
+	memset(runtime_stalled_cycles_back_stats, 0, sizeof(runtime_stalled_cycles_back_stats));
+	memset(runtime_branches_stats, 0, sizeof(runtime_branches_stats));
+	memset(runtime_cacherefs_stats, 0, sizeof(runtime_cacherefs_stats));
+	memset(runtime_l1_dcache_stats, 0, sizeof(runtime_l1_dcache_stats));
+	memset(runtime_l1_icache_stats, 0, sizeof(runtime_l1_icache_stats));
+	memset(runtime_ll_cache_stats, 0, sizeof(runtime_ll_cache_stats));
+	memset(runtime_itlb_cache_stats, 0, sizeof(runtime_itlb_cache_stats));
+	memset(runtime_dtlb_cache_stats, 0, sizeof(runtime_dtlb_cache_stats));
+	memset(runtime_cycles_in_tx_stats, 0,
+			sizeof(runtime_cycles_in_tx_stats));
+	memset(runtime_transaction_stats, 0,
+		sizeof(runtime_transaction_stats));
+	memset(runtime_elision_stats, 0, sizeof(runtime_elision_stats));
+	memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats));
+}
+
+/*
+ * Update various tracking values we maintain to print
+ * more semantic information such as miss/hit ratios,
+ * instruction rates, etc:
+ */
+void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
+				    int cpu)
+{
+	int ctx = evsel_context(counter);
+
+	if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
+		update_stats(&runtime_nsecs_stats[cpu], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
+		update_stats(&runtime_cycles_stats[ctx][cpu], count[0]);
+	else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
+		update_stats(&runtime_cycles_in_tx_stats[ctx][cpu], count[0]);
+	else if (perf_stat_evsel__is(counter, TRANSACTION_START))
+		update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
+	else if (perf_stat_evsel__is(counter, ELISION_START))
+		update_stats(&runtime_elision_stats[ctx][cpu], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
+		update_stats(&runtime_stalled_cycles_front_stats[ctx][cpu], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
+		update_stats(&runtime_stalled_cycles_back_stats[ctx][cpu], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
+		update_stats(&runtime_branches_stats[ctx][cpu], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
+		update_stats(&runtime_cacherefs_stats[ctx][cpu], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
+		update_stats(&runtime_l1_dcache_stats[ctx][cpu], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
+		update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))
+		update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
+		update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
+		update_stats(&runtime_itlb_cache_stats[ctx][cpu], count[0]);
+}
+
+/* used for get_ratio_color() */
+enum grc_type {
+	GRC_STALLED_CYCLES_FE,
+	GRC_STALLED_CYCLES_BE,
+	GRC_CACHE_MISSES,
+	GRC_MAX_NR
+};
+
+static const char *get_ratio_color(enum grc_type type, double ratio)
+{
+	static const double grc_table[GRC_MAX_NR][3] = {
+		[GRC_STALLED_CYCLES_FE] = { 50.0, 30.0, 10.0 },
+		[GRC_STALLED_CYCLES_BE] = { 75.0, 50.0, 20.0 },
+		[GRC_CACHE_MISSES] 	= { 20.0, 10.0, 5.0 },
+	};
+	const char *color = PERF_COLOR_NORMAL;
+
+	if (ratio > grc_table[type][0])
+		color = PERF_COLOR_RED;
+	else if (ratio > grc_table[type][1])
+		color = PERF_COLOR_MAGENTA;
+	else if (ratio > grc_table[type][2])
+		color = PERF_COLOR_YELLOW;
+
+	return color;
+}
+
+static void print_stalled_cycles_frontend(FILE *out, int cpu,
+					  struct perf_evsel *evsel
+					  __maybe_unused, double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+	int ctx = evsel_context(evsel);
+
+	total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
+
+	fprintf(out, " #  ");
+	color_fprintf(out, color, "%6.2f%%", ratio);
+	fprintf(out, " frontend cycles idle   ");
+}
+
+static void print_stalled_cycles_backend(FILE *out, int cpu,
+					 struct perf_evsel *evsel
+					 __maybe_unused, double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+	int ctx = evsel_context(evsel);
+
+	total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
+
+	fprintf(out, " #  ");
+	color_fprintf(out, color, "%6.2f%%", ratio);
+	fprintf(out, " backend  cycles idle   ");
+}
+
+static void print_branch_misses(FILE *out, int cpu,
+				struct perf_evsel *evsel __maybe_unused,
+				double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+	int ctx = evsel_context(evsel);
+
+	total = avg_stats(&runtime_branches_stats[ctx][cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+	fprintf(out, " #  ");
+	color_fprintf(out, color, "%6.2f%%", ratio);
+	fprintf(out, " of all branches        ");
+}
+
+static void print_l1_dcache_misses(FILE *out, int cpu,
+				   struct perf_evsel *evsel __maybe_unused,
+				   double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+	int ctx = evsel_context(evsel);
+
+	total = avg_stats(&runtime_l1_dcache_stats[ctx][cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+	fprintf(out, " #  ");
+	color_fprintf(out, color, "%6.2f%%", ratio);
+	fprintf(out, " of all L1-dcache hits  ");
+}
+
+static void print_l1_icache_misses(FILE *out, int cpu,
+				   struct perf_evsel *evsel __maybe_unused,
+				   double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+	int ctx = evsel_context(evsel);
+
+	total = avg_stats(&runtime_l1_icache_stats[ctx][cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+	fprintf(out, " #  ");
+	color_fprintf(out, color, "%6.2f%%", ratio);
+	fprintf(out, " of all L1-icache hits  ");
+}
+
+static void print_dtlb_cache_misses(FILE *out, int cpu,
+				    struct perf_evsel *evsel __maybe_unused,
+				    double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+	int ctx = evsel_context(evsel);
+
+	total = avg_stats(&runtime_dtlb_cache_stats[ctx][cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+	fprintf(out, " #  ");
+	color_fprintf(out, color, "%6.2f%%", ratio);
+	fprintf(out, " of all dTLB cache hits ");
+}
+
+static void print_itlb_cache_misses(FILE *out, int cpu,
+				    struct perf_evsel *evsel __maybe_unused,
+				    double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+	int ctx = evsel_context(evsel);
+
+	total = avg_stats(&runtime_itlb_cache_stats[ctx][cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+	fprintf(out, " #  ");
+	color_fprintf(out, color, "%6.2f%%", ratio);
+	fprintf(out, " of all iTLB cache hits ");
+}
+
+static void print_ll_cache_misses(FILE *out, int cpu,
+				  struct perf_evsel *evsel __maybe_unused,
+				  double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+	int ctx = evsel_context(evsel);
+
+	total = avg_stats(&runtime_ll_cache_stats[ctx][cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+	fprintf(out, " #  ");
+	color_fprintf(out, color, "%6.2f%%", ratio);
+	fprintf(out, " of all LL-cache hits   ");
+}
+
+void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
+				   double avg, int cpu, enum aggr_mode aggr)
+{
+	double total, ratio = 0.0, total2;
+	int ctx = evsel_context(evsel);
+
+	if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
+		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+		if (total) {
+			ratio = avg / total;
+			fprintf(out, " #   %5.2f  insns per cycle        ", ratio);
+		} else {
+			fprintf(out, "                                   ");
+		}
+		total = avg_stats(&runtime_stalled_cycles_front_stats[ctx][cpu]);
+		total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[ctx][cpu]));
+
+		if (total && avg) {
+			ratio = total / avg;
+			fprintf(out, "\n");
+			if (aggr == AGGR_NONE)
+				fprintf(out, "        ");
+			fprintf(out, "                                                  #   %5.2f  stalled cycles per insn", ratio);
+		}
+
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
+			runtime_branches_stats[ctx][cpu].n != 0) {
+		print_branch_misses(out, cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_l1_dcache_stats[ctx][cpu].n != 0) {
+		print_l1_dcache_misses(out, cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_l1_icache_stats[ctx][cpu].n != 0) {
+		print_l1_icache_misses(out, cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_dtlb_cache_stats[ctx][cpu].n != 0) {
+		print_dtlb_cache_misses(out, cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_itlb_cache_stats[ctx][cpu].n != 0) {
+		print_itlb_cache_misses(out, cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_ll_cache_stats[ctx][cpu].n != 0) {
+		print_ll_cache_misses(out, cpu, evsel, avg);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
+			runtime_cacherefs_stats[ctx][cpu].n != 0) {
+		total = avg_stats(&runtime_cacherefs_stats[ctx][cpu]);
+
+		if (total)
+			ratio = avg * 100 / total;
+
+		fprintf(out, " # %8.3f %% of all cache refs    ", ratio);
+
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
+		print_stalled_cycles_frontend(out, cpu, evsel, avg);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
+		print_stalled_cycles_backend(out, cpu, evsel, avg);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
+		total = avg_stats(&runtime_nsecs_stats[cpu]);
+
+		if (total) {
+			ratio = avg / total;
+			fprintf(out, " # %8.3f GHz                    ", ratio);
+		} else {
+			fprintf(out, "                                   ");
+		}
+	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
+		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+		if (total)
+			fprintf(out,
+				" #   %5.2f%% transactional cycles   ",
+				100.0 * (avg / total));
+	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
+		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+		total2 = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
+		if (total2 < avg)
+			total2 = avg;
+		if (total)
+			fprintf(out,
+				" #   %5.2f%% aborted cycles         ",
+				100.0 * ((total2-avg) / total));
+	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START) &&
+		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
+
+		if (avg)
+			ratio = total / avg;
+
+		fprintf(out, " # %8.0f cycles / transaction   ", ratio);
+	} else if (perf_stat_evsel__is(evsel, ELISION_START) &&
+		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
+
+		if (avg)
+			ratio = total / avg;
+
+		fprintf(out, " # %8.0f cycles / elision       ", ratio);
+	} else if (runtime_nsecs_stats[cpu].n != 0) {
+		char unit = 'M';
+
+		total = avg_stats(&runtime_nsecs_stats[cpu]);
+
+		if (total)
+			ratio = 1000.0 * avg / total;
+		if (ratio < 0.001) {
+			ratio *= 1000;
+			unit = 'K';
+		}
+
+		fprintf(out, " # %8.3f %c/sec                  ", ratio, unit);
+	} else {
+		fprintf(out, "                                   ");
+	}
+}
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 6506b3dfb..f2a0d1521 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -1,6 +1,8 @@
 #include <math.h>
-
 #include "stat.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "thread_map.h"
 
 void update_stats(struct stats *stats, u64 val)
 {
@@ -61,3 +63,178 @@ double rel_stddev_stats(double stddev, double avg)
 
 	return pct;
 }
+
+bool __perf_evsel_stat__is(struct perf_evsel *evsel,
+			   enum perf_stat_evsel_id id)
+{
+	struct perf_stat *ps = evsel->priv;
+
+	return ps->id == id;
+}
+
+#define ID(id, name) [PERF_STAT_EVSEL_ID__##id] = #name
+static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = {
+	ID(NONE,		x),
+	ID(CYCLES_IN_TX,	cpu/cycles-t/),
+	ID(TRANSACTION_START,	cpu/tx-start/),
+	ID(ELISION_START,	cpu/el-start/),
+	ID(CYCLES_IN_TX_CP,	cpu/cycles-ct/),
+};
+#undef ID
+
+void perf_stat_evsel_id_init(struct perf_evsel *evsel)
+{
+	struct perf_stat *ps = evsel->priv;
+	int i;
+
+	/* ps->id is 0 hence PERF_STAT_EVSEL_ID__NONE by default */
+
+	for (i = 0; i < PERF_STAT_EVSEL_ID__MAX; i++) {
+		if (!strcmp(perf_evsel__name(evsel), id_str[i])) {
+			ps->id = i;
+			break;
+		}
+	}
+}
+
+struct perf_counts *perf_counts__new(int ncpus, int nthreads)
+{
+	struct perf_counts *counts = zalloc(sizeof(*counts));
+
+	if (counts) {
+		struct xyarray *values;
+
+		values = xyarray__new(ncpus, nthreads, sizeof(struct perf_counts_values));
+		if (!values) {
+			free(counts);
+			return NULL;
+		}
+
+		counts->values = values;
+	}
+
+	return counts;
+}
+
+void perf_counts__delete(struct perf_counts *counts)
+{
+	if (counts) {
+		xyarray__delete(counts->values);
+		free(counts);
+	}
+}
+
+static void perf_counts__reset(struct perf_counts *counts)
+{
+	xyarray__reset(counts->values);
+}
+
+void perf_evsel__reset_counts(struct perf_evsel *evsel)
+{
+	perf_counts__reset(evsel->counts);
+}
+
+int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads)
+{
+	evsel->counts = perf_counts__new(ncpus, nthreads);
+	return evsel->counts != NULL ? 0 : -ENOMEM;
+}
+
+void perf_evsel__free_counts(struct perf_evsel *evsel)
+{
+	perf_counts__delete(evsel->counts);
+	evsel->counts = NULL;
+}
+
+void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
+{
+	int i;
+	struct perf_stat *ps = evsel->priv;
+
+	for (i = 0; i < 3; i++)
+		init_stats(&ps->res_stats[i]);
+
+	perf_stat_evsel_id_init(evsel);
+}
+
+int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
+{
+	evsel->priv = zalloc(sizeof(struct perf_stat));
+	if (evsel->priv == NULL)
+		return -ENOMEM;
+	perf_evsel__reset_stat_priv(evsel);
+	return 0;
+}
+
+void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
+{
+	zfree(&evsel->priv);
+}
+
+int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
+				      int ncpus, int nthreads)
+{
+	struct perf_counts *counts;
+
+	counts = perf_counts__new(ncpus, nthreads);
+	if (counts)
+		evsel->prev_raw_counts = counts;
+
+	return counts ? 0 : -ENOMEM;
+}
+
+void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
+{
+	perf_counts__delete(evsel->prev_raw_counts);
+	evsel->prev_raw_counts = NULL;
+}
+
+int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw)
+{
+	int ncpus = perf_evsel__nr_cpus(evsel);
+	int nthreads = thread_map__nr(evsel->threads);
+
+	if (perf_evsel__alloc_stat_priv(evsel) < 0 ||
+	    perf_evsel__alloc_counts(evsel, ncpus, nthreads) < 0 ||
+	    (alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel, ncpus, nthreads) < 0))
+		return -ENOMEM;
+
+	return 0;
+}
+
+int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		if (perf_evsel__alloc_stats(evsel, alloc_raw))
+			goto out_free;
+	}
+
+	return 0;
+
+out_free:
+	perf_evlist__free_stats(evlist);
+	return -1;
+}
+
+void perf_evlist__free_stats(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		perf_evsel__free_stat_priv(evsel);
+		perf_evsel__free_counts(evsel);
+		perf_evsel__free_prev_raw_counts(evsel);
+	}
+}
+
+void perf_evlist__reset_stats(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		perf_evsel__reset_stat_priv(evsel);
+		perf_evsel__reset_counts(evsel);
+	}
+}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 5667fc3e3..1cfbe0a98 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -2,6 +2,8 @@
 #define __PERF_STATS_H
 
 #include <linux/types.h>
+#include <stdio.h>
+#include "xyarray.h"
 
 struct stats
 {
@@ -9,6 +11,51 @@ struct stats
 	u64 max, min;
 };
 
+enum perf_stat_evsel_id {
+	PERF_STAT_EVSEL_ID__NONE = 0,
+	PERF_STAT_EVSEL_ID__CYCLES_IN_TX,
+	PERF_STAT_EVSEL_ID__TRANSACTION_START,
+	PERF_STAT_EVSEL_ID__ELISION_START,
+	PERF_STAT_EVSEL_ID__CYCLES_IN_TX_CP,
+	PERF_STAT_EVSEL_ID__MAX,
+};
+
+struct perf_stat {
+	struct stats		res_stats[3];
+	enum perf_stat_evsel_id	id;
+};
+
+enum aggr_mode {
+	AGGR_NONE,
+	AGGR_GLOBAL,
+	AGGR_SOCKET,
+	AGGR_CORE,
+	AGGR_THREAD,
+};
+
+struct perf_counts_values {
+	union {
+		struct {
+			u64 val;
+			u64 ena;
+			u64 run;
+		};
+		u64 values[3];
+	};
+};
+
+struct perf_counts {
+	s8			  scaled;
+	struct perf_counts_values aggr;
+	struct xyarray		  *values;
+};
+
+static inline struct perf_counts_values*
+perf_counts(struct perf_counts *counts, int cpu, int thread)
+{
+	return xyarray__entry(counts->values, cpu, thread);
+}
+
 void update_stats(struct stats *stats, u64 val);
 double avg_stats(struct stats *stats);
 double stddev_stats(struct stats *stats);
@@ -22,4 +69,44 @@ static inline void init_stats(struct stats *stats)
 	stats->min  = (u64) -1;
 	stats->max  = 0;
 }
+
+struct perf_evsel;
+struct perf_evlist;
+
+bool __perf_evsel_stat__is(struct perf_evsel *evsel,
+			   enum perf_stat_evsel_id id);
+
+#define perf_stat_evsel__is(evsel, id) \
+	__perf_evsel_stat__is(evsel, PERF_STAT_EVSEL_ID__ ## id)
+
+void perf_stat_evsel_id_init(struct perf_evsel *evsel);
+
+extern struct stats walltime_nsecs_stats;
+
+void perf_stat__reset_shadow_stats(void);
+void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
+				    int cpu);
+void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
+				   double avg, int cpu, enum aggr_mode aggr);
+
+struct perf_counts *perf_counts__new(int ncpus, int nthreads);
+void perf_counts__delete(struct perf_counts *counts);
+
+void perf_evsel__reset_counts(struct perf_evsel *evsel);
+int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads);
+void perf_evsel__free_counts(struct perf_evsel *evsel);
+
+void perf_evsel__reset_stat_priv(struct perf_evsel *evsel);
+int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel);
+void perf_evsel__free_stat_priv(struct perf_evsel *evsel);
+
+int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
+				      int ncpus, int nthreads);
+void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel);
+
+int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw);
+
+int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
+void perf_evlist__free_stats(struct perf_evlist *evlist);
+void perf_evlist__reset_stats(struct perf_evlist *evlist);
 #endif
diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c
index 79a757a2a..bcae659b6 100644
--- a/tools/perf/util/strfilter.c
+++ b/tools/perf/util/strfilter.c
@@ -170,6 +170,46 @@ struct strfilter *strfilter__new(const char *rules, const char **err)
 	return filter;
 }
 
+static int strfilter__append(struct strfilter *filter, bool _or,
+			     const char *rules, const char **err)
+{
+	struct strfilter_node *right, *root;
+	const char *ep = NULL;
+
+	if (!filter || !rules)
+		return -EINVAL;
+
+	right = strfilter_node__new(rules, &ep);
+	if (!right || *ep != '\0') {
+		if (err)
+			*err = ep;
+		goto error;
+	}
+	root = strfilter_node__alloc(_or ? OP_or : OP_and, filter->root, right);
+	if (!root) {
+		ep = NULL;
+		goto error;
+	}
+
+	filter->root = root;
+	return 0;
+
+error:
+	strfilter_node__delete(right);
+	return ep ? -EINVAL : -ENOMEM;
+}
+
+int strfilter__or(struct strfilter *filter, const char *rules, const char **err)
+{
+	return strfilter__append(filter, true, rules, err);
+}
+
+int strfilter__and(struct strfilter *filter, const char *rules,
+		   const char **err)
+{
+	return strfilter__append(filter, false, rules, err);
+}
+
 static bool strfilter_node__compare(struct strfilter_node *node,
 				    const char *str)
 {
@@ -197,3 +237,70 @@ bool strfilter__compare(struct strfilter *filter, const char *str)
 		return false;
 	return strfilter_node__compare(filter->root, str);
 }
+
+static int strfilter_node__sprint(struct strfilter_node *node, char *buf);
+
+/* sprint node in parenthesis if needed */
+static int strfilter_node__sprint_pt(struct strfilter_node *node, char *buf)
+{
+	int len;
+	int pt = node->r ? 2 : 0;	/* don't need to check node->l */
+
+	if (buf && pt)
+		*buf++ = '(';
+	len = strfilter_node__sprint(node, buf);
+	if (len < 0)
+		return len;
+	if (buf && pt)
+		*(buf + len) = ')';
+	return len + pt;
+}
+
+static int strfilter_node__sprint(struct strfilter_node *node, char *buf)
+{
+	int len = 0, rlen;
+
+	if (!node || !node->p)
+		return -EINVAL;
+
+	switch (*node->p) {
+	case '|':
+	case '&':
+		len = strfilter_node__sprint_pt(node->l, buf);
+		if (len < 0)
+			return len;
+	case '!':
+		if (buf) {
+			*(buf + len++) = *node->p;
+			buf += len;
+		} else
+			len++;
+		rlen = strfilter_node__sprint_pt(node->r, buf);
+		if (rlen < 0)
+			return rlen;
+		len += rlen;
+		break;
+	default:
+		len = strlen(node->p);
+		if (buf)
+			strcpy(buf, node->p);
+	}
+
+	return len;
+}
+
+char *strfilter__string(struct strfilter *filter)
+{
+	int len;
+	char *ret = NULL;
+
+	len = strfilter_node__sprint(filter->root, NULL);
+	if (len < 0)
+		return NULL;
+
+	ret = malloc(len + 1);
+	if (ret)
+		strfilter_node__sprint(filter->root, ret);
+
+	return ret;
+}
diff --git a/tools/perf/util/strfilter.h b/tools/perf/util/strfilter.h
index fe611f3c9..cff5eda88 100644
--- a/tools/perf/util/strfilter.h
+++ b/tools/perf/util/strfilter.h
@@ -29,6 +29,32 @@ struct strfilter {
 struct strfilter *strfilter__new(const char *rules, const char **err);
 
 /**
+ * strfilter__or - Append an additional rule by logical-or
+ * @filter: Original string filter
+ * @rules: Filter rule to be appended at left of the root of
+ *         @filter by using logical-or.
+ * @err: Pointer which points an error detected on @rules
+ *
+ * Parse @rules and join it to the @filter by using logical-or.
+ * Return 0 if success, or return the error code.
+ */
+int strfilter__or(struct strfilter *filter,
+		  const char *rules, const char **err);
+
+/**
+ * strfilter__add - Append an additional rule by logical-and
+ * @filter: Original string filter
+ * @rules: Filter rule to be appended at left of the root of
+ *         @filter by using logical-and.
+ * @err: Pointer which points an error detected on @rules
+ *
+ * Parse @rules and join it to the @filter by using logical-and.
+ * Return 0 if success, or return the error code.
+ */
+int strfilter__and(struct strfilter *filter,
+		   const char *rules, const char **err);
+
+/**
  * strfilter__compare - compare given string and a string filter
  * @filter: String filter
  * @str: target string
@@ -45,4 +71,13 @@ bool strfilter__compare(struct strfilter *filter, const char *str);
  */
 void strfilter__delete(struct strfilter *filter);
 
+/**
+ * strfilter__string - Reconstruct a rule string from filter
+ * @filter: String filter to reconstruct
+ *
+ * Reconstruct a rule string from @filter. This will be good for
+ * debug messages. Note that returning string must be freed afterward.
+ */
+char *strfilter__string(struct strfilter *filter);
+
 #endif
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 283d3e73e..eec6c1149 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -748,7 +748,7 @@ static int str_to_bitmap(char *s, cpumask_t *b)
 		set_bit(c, cpumask_bits(b));
 	}
 
-	cpu_map__delete(m);
+	cpu_map__put(m);
 
 	return ret;
 }
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index a7ab6063e..65f7e389a 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -630,6 +630,11 @@ void symsrc__destroy(struct symsrc *ss)
 	close(ss->fd);
 }
 
+bool __weak elf__needs_adjust_symbols(GElf_Ehdr ehdr)
+{
+	return ehdr.e_type == ET_EXEC || ehdr.e_type == ET_REL;
+}
+
 int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 		 enum dso_binary_type type)
 {
@@ -678,6 +683,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 		}
 
 		if (!dso__build_id_equal(dso, build_id)) {
+			pr_debug("%s: build id mismatch for %s.\n", __func__, name);
 			dso->load_errno = DSO_LOAD_ERRNO__MISMATCHING_BUILDID;
 			goto out_elf_end;
 		}
@@ -711,8 +717,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 						     ".gnu.prelink_undo",
 						     NULL) != NULL);
 	} else {
-		ss->adjust_symbols = ehdr.e_type == ET_EXEC ||
-				     ehdr.e_type == ET_REL;
+		ss->adjust_symbols = elf__needs_adjust_symbols(ehdr);
 	}
 
 	ss->name   = strdup(name);
@@ -771,6 +776,8 @@ static bool want_demangle(bool is_kernel_sym)
 	return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle;
 }
 
+void __weak arch__elf_sym_adjust(GElf_Sym *sym __maybe_unused) { }
+
 int dso__load_sym(struct dso *dso, struct map *map,
 		  struct symsrc *syms_ss, struct symsrc *runtime_ss,
 		  symbol_filter_t filter, int kmodule)
@@ -935,6 +942,8 @@ int dso__load_sym(struct dso *dso, struct map *map,
 		    (sym.st_value & 1))
 			--sym.st_value;
 
+		arch__elf_sym_adjust(&sym);
+
 		if (dso->kernel || kmodule) {
 			char dso_name[PATH_MAX];
 
@@ -963,8 +972,10 @@ int dso__load_sym(struct dso *dso, struct map *map,
 					map->unmap_ip = map__unmap_ip;
 					/* Ensure maps are correctly ordered */
 					if (kmaps) {
+						map__get(map);
 						map_groups__remove(kmaps, map);
 						map_groups__insert(kmaps, map);
+						map__put(map);
 					}
 				}
 
@@ -1005,7 +1016,7 @@ int dso__load_sym(struct dso *dso, struct map *map,
 				curr_map = map__new2(start, curr_dso,
 						     map->type);
 				if (curr_map == NULL) {
-					dso__delete(curr_dso);
+					dso__put(curr_dso);
 					goto out_elf_end;
 				}
 				if (adjust_kernel_syms) {
@@ -1020,11 +1031,7 @@ int dso__load_sym(struct dso *dso, struct map *map,
 				}
 				curr_dso->symtab_type = dso->symtab_type;
 				map_groups__insert(kmaps, curr_map);
-				/*
-				 * The new DSO should go to the kernel DSOS
-				 */
-				dsos__add(&map->groups->machine->kernel_dsos,
-					  curr_dso);
+				dsos__add(&map->groups->machine->dsos, curr_dso);
 				dso__set_loaded(curr_dso, map->type);
 			} else
 				curr_dso = curr_map->dso;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 99378a5c5..60f11414b 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -85,8 +85,17 @@ static int prefix_underscores_count(const char *str)
 	return tail - str;
 }
 
-#define SYMBOL_A 0
-#define SYMBOL_B 1
+int __weak arch__choose_best_symbol(struct symbol *syma,
+				    struct symbol *symb __maybe_unused)
+{
+	/* Avoid "SyS" kernel syscall aliases */
+	if (strlen(syma->name) >= 3 && !strncmp(syma->name, "SyS", 3))
+		return SYMBOL_B;
+	if (strlen(syma->name) >= 10 && !strncmp(syma->name, "compat_SyS", 10))
+		return SYMBOL_B;
+
+	return SYMBOL_A;
+}
 
 static int choose_best_symbol(struct symbol *syma, struct symbol *symb)
 {
@@ -134,13 +143,7 @@ static int choose_best_symbol(struct symbol *syma, struct symbol *symb)
 	else if (na < nb)
 		return SYMBOL_B;
 
-	/* Avoid "SyS" kernel syscall aliases */
-	if (na >= 3 && !strncmp(syma->name, "SyS", 3))
-		return SYMBOL_B;
-	if (na >= 10 && !strncmp(syma->name, "compat_SyS", 10))
-		return SYMBOL_B;
-
-	return SYMBOL_A;
+	return arch__choose_best_symbol(syma, symb);
 }
 
 void symbols__fixup_duplicate(struct rb_root *symbols)
@@ -199,18 +202,18 @@ void symbols__fixup_end(struct rb_root *symbols)
 
 void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
 {
-	struct map *prev, *curr;
-	struct rb_node *nd, *prevnd = rb_first(&mg->maps[type]);
+	struct maps *maps = &mg->maps[type];
+	struct map *next, *curr;
 
-	if (prevnd == NULL)
-		return;
+	pthread_rwlock_wrlock(&maps->lock);
 
-	curr = rb_entry(prevnd, struct map, rb_node);
+	curr = maps__first(maps);
+	if (curr == NULL)
+		goto out_unlock;
 
-	for (nd = rb_next(prevnd); nd; nd = rb_next(nd)) {
-		prev = curr;
-		curr = rb_entry(nd, struct map, rb_node);
-		prev->end = curr->start;
+	for (next = map__next(curr); next; next = map__next(curr)) {
+		curr->end = next->start;
+		curr = next;
 	}
 
 	/*
@@ -218,6 +221,9 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
 	 * last map final address.
 	 */
 	curr->end = ~0ULL;
+
+out_unlock:
+	pthread_rwlock_unlock(&maps->lock);
 }
 
 struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name)
@@ -397,7 +403,7 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
 					    const char *name)
 {
 	struct rb_node *n;
-	struct symbol_name_rb_node *s;
+	struct symbol_name_rb_node *s = NULL;
 
 	if (symbols == NULL)
 		return NULL;
@@ -408,7 +414,7 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
 		int cmp;
 
 		s = rb_entry(n, struct symbol_name_rb_node, rb_node);
-		cmp = strcmp(name, s->sym.name);
+		cmp = arch__compare_symbol_names(name, s->sym.name);
 
 		if (cmp < 0)
 			n = n->rb_left;
@@ -426,7 +432,7 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
 		struct symbol_name_rb_node *tmp;
 
 		tmp = rb_entry(n, struct symbol_name_rb_node, rb_node);
-		if (strcmp(tmp->sym.name, s->sym.name))
+		if (arch__compare_symbol_names(tmp->sym.name, s->sym.name))
 			break;
 
 		s = tmp;
@@ -653,14 +659,14 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map,
 		curr_map = map_groups__find(kmaps, map->type, pos->start);
 
 		if (!curr_map || (filter && filter(curr_map, pos))) {
-			rb_erase(&pos->rb_node, root);
+			rb_erase_init(&pos->rb_node, root);
 			symbol__delete(pos);
 		} else {
 			pos->start -= curr_map->start - curr_map->pgoff;
 			if (pos->end)
 				pos->end -= curr_map->start - curr_map->pgoff;
 			if (curr_map != map) {
-				rb_erase(&pos->rb_node, root);
+				rb_erase_init(&pos->rb_node, root);
 				symbols__insert(
 					&curr_map->dso->symbols[curr_map->type],
 					pos);
@@ -780,7 +786,7 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta,
 
 			curr_map = map__new2(pos->start, ndso, map->type);
 			if (curr_map == NULL) {
-				dso__delete(ndso);
+				dso__put(ndso);
 				return -1;
 			}
 
@@ -1126,8 +1132,11 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 	INIT_LIST_HEAD(&md.maps);
 
 	fd = open(kcore_filename, O_RDONLY);
-	if (fd < 0)
+	if (fd < 0) {
+		pr_err("%s requires CAP_SYS_RAWIO capability to access.\n",
+			kcore_filename);
 		return -EINVAL;
+	}
 
 	/* Read new maps into temporary lists */
 	err = file__read_maps(fd, md.type == MAP__FUNCTION, kcore_mapfn, &md,
@@ -1167,20 +1176,23 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 	/* Add new maps */
 	while (!list_empty(&md.maps)) {
 		new_map = list_entry(md.maps.next, struct map, node);
-		list_del(&new_map->node);
+		list_del_init(&new_map->node);
 		if (new_map == replacement_map) {
 			map->start	= new_map->start;
 			map->end	= new_map->end;
 			map->pgoff	= new_map->pgoff;
 			map->map_ip	= new_map->map_ip;
 			map->unmap_ip	= new_map->unmap_ip;
-			map__delete(new_map);
 			/* Ensure maps are correctly ordered */
+			map__get(map);
 			map_groups__remove(kmaps, map);
 			map_groups__insert(kmaps, map);
+			map__put(map);
 		} else {
 			map_groups__insert(kmaps, new_map);
 		}
+
+		map__put(new_map);
 	}
 
 	/*
@@ -1205,8 +1217,8 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 out_err:
 	while (!list_empty(&md.maps)) {
 		map = list_entry(md.maps.next, struct map, node);
-		list_del(&map->node);
-		map__delete(map);
+		list_del_init(&map->node);
+		map__put(map);
 	}
 	close(fd);
 	return -EINVAL;
@@ -1355,7 +1367,7 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod,
 	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP:
 		/*
 		 * kernel modules know their symtab type - it's set when
-		 * creating a module dso in machine__new_module().
+		 * creating a module dso in machine__findnew_module_map().
 		 */
 		return kmod && dso->symtab_type == type;
 
@@ -1380,12 +1392,22 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 	struct symsrc *syms_ss = NULL, *runtime_ss = NULL;
 	bool kmod;
 
-	dso__set_loaded(dso, map->type);
+	pthread_mutex_lock(&dso->lock);
 
-	if (dso->kernel == DSO_TYPE_KERNEL)
-		return dso__load_kernel_sym(dso, map, filter);
-	else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
-		return dso__load_guest_kernel_sym(dso, map, filter);
+	/* check again under the dso->lock */
+	if (dso__loaded(dso, map->type)) {
+		ret = 1;
+		goto out;
+	}
+
+	if (dso->kernel) {
+		if (dso->kernel == DSO_TYPE_KERNEL)
+			ret = dso__load_kernel_sym(dso, map, filter);
+		else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+			ret = dso__load_guest_kernel_sym(dso, map, filter);
+
+		goto out;
+	}
 
 	if (map->groups && map->groups->machine)
 		machine = map->groups->machine;
@@ -1398,18 +1420,18 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 		struct stat st;
 
 		if (lstat(dso->name, &st) < 0)
-			return -1;
+			goto out;
 
 		if (st.st_uid && (st.st_uid != geteuid())) {
 			pr_warning("File %s not owned by current user or root, "
 				"ignoring it.\n", dso->name);
-			return -1;
+			goto out;
 		}
 
 		ret = dso__load_perf_map(dso, map, filter);
 		dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT :
 					     DSO_BINARY_TYPE__NOT_FOUND;
-		return ret;
+		goto out;
 	}
 
 	if (machine)
@@ -1417,7 +1439,7 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 
 	name = malloc(PATH_MAX);
 	if (!name)
-		return -1;
+		goto out;
 
 	kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE ||
 		dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP ||
@@ -1498,23 +1520,32 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 out_free:
 	free(name);
 	if (ret < 0 && strstr(dso->name, " (deleted)") != NULL)
-		return 0;
+		ret = 0;
+out:
+	dso__set_loaded(dso, map->type);
+	pthread_mutex_unlock(&dso->lock);
+
 	return ret;
 }
 
 struct map *map_groups__find_by_name(struct map_groups *mg,
 				     enum map_type type, const char *name)
 {
-	struct rb_node *nd;
+	struct maps *maps = &mg->maps[type];
+	struct map *map;
 
-	for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) {
-		struct map *map = rb_entry(nd, struct map, rb_node);
+	pthread_rwlock_rdlock(&maps->lock);
 
+	for (map = maps__first(maps); map; map = map__next(map)) {
 		if (map->dso && strcmp(map->dso->short_name, name) == 0)
-			return map;
+			goto out_unlock;
 	}
 
-	return NULL;
+	map = NULL;
+
+out_unlock:
+	pthread_rwlock_unlock(&maps->lock);
+	return map;
 }
 
 int dso__load_vmlinux(struct dso *dso, struct map *map,
@@ -1802,6 +1833,7 @@ static void vmlinux_path__exit(void)
 {
 	while (--vmlinux_path__nr_entries >= 0)
 		zfree(&vmlinux_path[vmlinux_path__nr_entries]);
+	vmlinux_path__nr_entries = 0;
 
 	zfree(&vmlinux_path);
 }
@@ -1879,6 +1911,8 @@ int setup_list(struct strlist **list, const char *list_str,
 		pr_err("problems parsing %s list\n", list_name);
 		return -1;
 	}
+
+	symbol_conf.has_filter = true;
 	return 0;
 }
 
@@ -1893,8 +1927,6 @@ int setup_intlist(struct intlist **list, const char *list_str,
 		pr_err("problems parsing %s list\n", list_name);
 		return -1;
 	}
-
-	symbol_conf.has_filter = true;
 	return 0;
 }
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index be0217989..b98ce51af 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -159,8 +159,6 @@ struct ref_reloc_sym {
 struct map_symbol {
 	struct map    *map;
 	struct symbol *sym;
-	bool	      unfolded;
-	bool	      has_children;
 };
 
 struct addr_map_symbol {
@@ -304,4 +302,14 @@ int setup_list(struct strlist **list, const char *list_str,
 int setup_intlist(struct intlist **list, const char *list_str,
 		  const char *list_name);
 
+#ifdef HAVE_LIBELF_SUPPORT
+bool elf__needs_adjust_symbols(GElf_Ehdr ehdr);
+void arch__elf_sym_adjust(GElf_Sym *sym);
+#endif
+
+#define SYMBOL_A 0
+#define SYMBOL_B 1
+
+int arch__choose_best_symbol(struct symbol *syma, struct symbol *symb);
+
 #endif /* __PERF_SYMBOL */
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index 9ed59a452..679688e70 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -219,7 +219,7 @@ static int thread_stack__call_return(struct thread *thread,
 	return crp->process(&cr, crp->data);
 }
 
-static int thread_stack__flush(struct thread *thread, struct thread_stack *ts)
+static int __thread_stack__flush(struct thread *thread, struct thread_stack *ts)
 {
 	struct call_return_processor *crp = ts->crp;
 	int err;
@@ -242,6 +242,14 @@ static int thread_stack__flush(struct thread *thread, struct thread_stack *ts)
 	return 0;
 }
 
+int thread_stack__flush(struct thread *thread)
+{
+	if (thread->ts)
+		return __thread_stack__flush(thread, thread->ts);
+
+	return 0;
+}
+
 int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 			u64 to_ip, u16 insn_len, u64 trace_nr)
 {
@@ -264,7 +272,7 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 	 */
 	if (trace_nr != thread->ts->trace_nr) {
 		if (thread->ts->trace_nr)
-			thread_stack__flush(thread, thread->ts);
+			__thread_stack__flush(thread, thread->ts);
 		thread->ts->trace_nr = trace_nr;
 	}
 
@@ -297,7 +305,7 @@ void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr)
 
 	if (trace_nr != thread->ts->trace_nr) {
 		if (thread->ts->trace_nr)
-			thread_stack__flush(thread, thread->ts);
+			__thread_stack__flush(thread, thread->ts);
 		thread->ts->trace_nr = trace_nr;
 	}
 }
@@ -305,7 +313,7 @@ void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr)
 void thread_stack__free(struct thread *thread)
 {
 	if (thread->ts) {
-		thread_stack__flush(thread, thread->ts);
+		__thread_stack__flush(thread, thread->ts);
 		zfree(&thread->ts->stack);
 		zfree(&thread->ts);
 	}
@@ -689,7 +697,7 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 
 	/* Flush stack on exec */
 	if (ts->comm != comm && thread->pid_ == thread->tid) {
-		err = thread_stack__flush(thread, ts);
+		err = __thread_stack__flush(thread, ts);
 		if (err)
 			return err;
 		ts->comm = comm;
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
index b843bbef8..e1528f137 100644
--- a/tools/perf/util/thread-stack.h
+++ b/tools/perf/util/thread-stack.h
@@ -96,6 +96,7 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr);
 void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
 			  size_t sz, u64 ip);
+int thread_stack__flush(struct thread *thread);
 void thread_stack__free(struct thread *thread);
 
 struct call_return_processor *
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 1c8fbc958..0a9ae8014 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -18,7 +18,7 @@ int thread__init_map_groups(struct thread *thread, struct machine *machine)
 	if (pid == thread->tid || pid == -1) {
 		thread->mg = map_groups__new(machine);
 	} else {
-		leader = machine__findnew_thread(machine, pid, pid);
+		leader = __machine__findnew_thread(machine, pid, pid);
 		if (leader)
 			thread->mg = map_groups__get(leader->mg);
 	}
@@ -53,7 +53,8 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 			goto err_thread;
 
 		list_add(&comm->list, &thread->comm_list);
-
+		atomic_set(&thread->refcnt, 0);
+		RB_CLEAR_NODE(&thread->rb_node);
 	}
 
 	return thread;
@@ -67,6 +68,8 @@ void thread__delete(struct thread *thread)
 {
 	struct comm *comm, *tmp;
 
+	BUG_ON(!RB_EMPTY_NODE(&thread->rb_node));
+
 	thread_stack__free(thread);
 
 	if (thread->mg) {
@@ -84,13 +87,14 @@ void thread__delete(struct thread *thread)
 
 struct thread *thread__get(struct thread *thread)
 {
-	++thread->refcnt;
+	if (thread)
+		atomic_inc(&thread->refcnt);
 	return thread;
 }
 
 void thread__put(struct thread *thread)
 {
-	if (thread && --thread->refcnt == 0) {
+	if (thread && atomic_dec_and_test(&thread->refcnt)) {
 		list_del_init(&thread->node);
 		thread__delete(thread);
 	}
@@ -187,6 +191,12 @@ static int thread__clone_map_groups(struct thread *thread,
 	if (thread->pid_ == parent->pid_)
 		return 0;
 
+	if (thread->mg == parent->mg) {
+		pr_debug("broken map groups on thread %d/%d parent %d/%d\n",
+			 thread->pid_, thread->tid, parent->pid_, parent->tid);
+		return 0;
+	}
+
 	/* But this one is new process, copy maps. */
 	for (i = 0; i < MAP__NR_TYPES; ++i)
 		if (map_groups__clone(thread->mg, parent->mg, i) < 0)
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 9b8a54dc3..a0ac0317a 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -1,6 +1,7 @@
 #ifndef __PERF_THREAD_H
 #define __PERF_THREAD_H
 
+#include <linux/atomic.h>
 #include <linux/rbtree.h>
 #include <linux/list.h>
 #include <unistd.h>
@@ -21,12 +22,12 @@ struct thread {
 	pid_t			tid;
 	pid_t			ppid;
 	int			cpu;
-	int			refcnt;
+	atomic_t		refcnt;
 	char			shortname[3];
 	bool			comm_set;
+	int			comm_len;
 	bool			dead; /* if set thread has exited */
 	struct list_head	comm_list;
-	int			comm_len;
 	u64			db_id;
 
 	void			*priv;
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index f93b97347..292ae2c90 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -8,8 +8,11 @@
 #include <unistd.h>
 #include "strlist.h"
 #include <string.h>
+#include <api/fs/fs.h>
+#include "asm/bug.h"
 #include "thread_map.h"
 #include "util.h"
+#include "debug.h"
 
 /* Skip "." and ".." directories */
 static int filter(const struct dirent *dir)
@@ -20,6 +23,30 @@ static int filter(const struct dirent *dir)
 		return 1;
 }
 
+static void thread_map__reset(struct thread_map *map, int start, int nr)
+{
+	size_t size = (nr - start) * sizeof(map->map[0]);
+
+	memset(&map->map[start], 0, size);
+}
+
+static struct thread_map *thread_map__realloc(struct thread_map *map, int nr)
+{
+	size_t size = sizeof(*map) + sizeof(map->map[0]) * nr;
+	int start = map ? map->nr : 0;
+
+	map = realloc(map, size);
+	/*
+	 * We only realloc to add more items, let's reset new items.
+	 */
+	if (map)
+		thread_map__reset(map, start, nr);
+
+	return map;
+}
+
+#define thread_map__alloc(__nr) thread_map__realloc(NULL, __nr)
+
 struct thread_map *thread_map__new_by_pid(pid_t pid)
 {
 	struct thread_map *threads;
@@ -33,11 +60,12 @@ struct thread_map *thread_map__new_by_pid(pid_t pid)
 	if (items <= 0)
 		return NULL;
 
-	threads = malloc(sizeof(*threads) + sizeof(pid_t) * items);
+	threads = thread_map__alloc(items);
 	if (threads != NULL) {
 		for (i = 0; i < items; i++)
-			threads->map[i] = atoi(namelist[i]->d_name);
+			thread_map__set_pid(threads, i, atoi(namelist[i]->d_name));
 		threads->nr = items;
+		atomic_set(&threads->refcnt, 1);
 	}
 
 	for (i=0; i<items; i++)
@@ -49,11 +77,12 @@ struct thread_map *thread_map__new_by_pid(pid_t pid)
 
 struct thread_map *thread_map__new_by_tid(pid_t tid)
 {
-	struct thread_map *threads = malloc(sizeof(*threads) + sizeof(pid_t));
+	struct thread_map *threads = thread_map__alloc(1);
 
 	if (threads != NULL) {
-		threads->map[0] = tid;
-		threads->nr	= 1;
+		thread_map__set_pid(threads, 0, tid);
+		threads->nr = 1;
+		atomic_set(&threads->refcnt, 1);
 	}
 
 	return threads;
@@ -65,8 +94,8 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 	int max_threads = 32, items, i;
 	char path[256];
 	struct dirent dirent, *next, **namelist = NULL;
-	struct thread_map *threads = malloc(sizeof(*threads) +
-					    max_threads * sizeof(pid_t));
+	struct thread_map *threads = thread_map__alloc(max_threads);
+
 	if (threads == NULL)
 		goto out;
 
@@ -75,6 +104,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 		goto out_free_threads;
 
 	threads->nr = 0;
+	atomic_set(&threads->refcnt, 1);
 
 	while (!readdir_r(proc, &dirent, &next) && next) {
 		char *end;
@@ -106,16 +136,17 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 		if (grow) {
 			struct thread_map *tmp;
 
-			tmp = realloc(threads, (sizeof(*threads) +
-						max_threads * sizeof(pid_t)));
+			tmp = thread_map__realloc(threads, max_threads);
 			if (tmp == NULL)
 				goto out_free_namelist;
 
 			threads = tmp;
 		}
 
-		for (i = 0; i < items; i++)
-			threads->map[threads->nr + i] = atoi(namelist[i]->d_name);
+		for (i = 0; i < items; i++) {
+			thread_map__set_pid(threads, threads->nr + i,
+					    atoi(namelist[i]->d_name));
+		}
 
 		for (i = 0; i < items; i++)
 			zfree(&namelist[i]);
@@ -185,15 +216,14 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str)
 			goto out_free_threads;
 
 		total_tasks += items;
-		nt = realloc(threads, (sizeof(*threads) +
-				       sizeof(pid_t) * total_tasks));
+		nt = thread_map__realloc(threads, total_tasks);
 		if (nt == NULL)
 			goto out_free_namelist;
 
 		threads = nt;
 
 		for (i = 0; i < items; i++) {
-			threads->map[j++] = atoi(namelist[i]->d_name);
+			thread_map__set_pid(threads, j++, atoi(namelist[i]->d_name));
 			zfree(&namelist[i]);
 		}
 		threads->nr = total_tasks;
@@ -202,6 +232,8 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str)
 
 out:
 	strlist__delete(slist);
+	if (threads)
+		atomic_set(&threads->refcnt, 1);
 	return threads;
 
 out_free_namelist:
@@ -216,11 +248,12 @@ out_free_threads:
 
 struct thread_map *thread_map__new_dummy(void)
 {
-	struct thread_map *threads = malloc(sizeof(*threads) + sizeof(pid_t));
+	struct thread_map *threads = thread_map__alloc(1);
 
 	if (threads != NULL) {
-		threads->map[0]	= -1;
-		threads->nr	= 1;
+		thread_map__set_pid(threads, 0, -1);
+		threads->nr = 1;
+		atomic_set(&threads->refcnt, 1);
 	}
 	return threads;
 }
@@ -253,16 +286,18 @@ static struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
 			continue;
 
 		ntasks++;
-		nt = realloc(threads, sizeof(*threads) + sizeof(pid_t) * ntasks);
+		nt = thread_map__realloc(threads, ntasks);
 
 		if (nt == NULL)
 			goto out_free_threads;
 
 		threads = nt;
-		threads->map[ntasks - 1] = tid;
-		threads->nr		 = ntasks;
+		thread_map__set_pid(threads, ntasks - 1, tid);
+		threads->nr = ntasks;
 	}
 out:
+	if (threads)
+		atomic_set(&threads->refcnt, 1);
 	return threads;
 
 out_free_threads:
@@ -282,9 +317,30 @@ struct thread_map *thread_map__new_str(const char *pid, const char *tid,
 	return thread_map__new_by_tid_str(tid);
 }
 
-void thread_map__delete(struct thread_map *threads)
+static void thread_map__delete(struct thread_map *threads)
 {
-	free(threads);
+	if (threads) {
+		int i;
+
+		WARN_ONCE(atomic_read(&threads->refcnt) != 0,
+			  "thread map refcnt unbalanced\n");
+		for (i = 0; i < threads->nr; i++)
+			free(thread_map__comm(threads, i));
+		free(threads);
+	}
+}
+
+struct thread_map *thread_map__get(struct thread_map *map)
+{
+	if (map)
+		atomic_inc(&map->refcnt);
+	return map;
+}
+
+void thread_map__put(struct thread_map *map)
+{
+	if (map && atomic_dec_and_test(&map->refcnt))
+		thread_map__delete(map);
 }
 
 size_t thread_map__fprintf(struct thread_map *threads, FILE *fp)
@@ -293,7 +349,60 @@ size_t thread_map__fprintf(struct thread_map *threads, FILE *fp)
 	size_t printed = fprintf(fp, "%d thread%s: ",
 				 threads->nr, threads->nr > 1 ? "s" : "");
 	for (i = 0; i < threads->nr; ++i)
-		printed += fprintf(fp, "%s%d", i ? ", " : "", threads->map[i]);
+		printed += fprintf(fp, "%s%d", i ? ", " : "", thread_map__pid(threads, i));
 
 	return printed + fprintf(fp, "\n");
 }
+
+static int get_comm(char **comm, pid_t pid)
+{
+	char *path;
+	size_t size;
+	int err;
+
+	if (asprintf(&path, "%s/%d/comm", procfs__mountpoint(), pid) == -1)
+		return -ENOMEM;
+
+	err = filename__read_str(path, comm, &size);
+	if (!err) {
+		/*
+		 * We're reading 16 bytes, while filename__read_str
+		 * allocates data per BUFSIZ bytes, so we can safely
+		 * mark the end of the string.
+		 */
+		(*comm)[size] = 0;
+		rtrim(*comm);
+	}
+
+	free(path);
+	return err;
+}
+
+static void comm_init(struct thread_map *map, int i)
+{
+	pid_t pid = thread_map__pid(map, i);
+	char *comm = NULL;
+
+	/* dummy pid comm initialization */
+	if (pid == -1) {
+		map->map[i].comm = strdup("dummy");
+		return;
+	}
+
+	/*
+	 * The comm name is like extra bonus ;-),
+	 * so just warn if we fail for any reason.
+	 */
+	if (get_comm(&comm, pid))
+		pr_warning("Couldn't resolve comm name for pid %d\n", pid);
+
+	map->map[i].comm = comm;
+}
+
+void thread_map__read_comms(struct thread_map *threads)
+{
+	int i;
+
+	for (i = 0; i < threads->nr; ++i)
+		comm_init(threads, i);
+}
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index 95313f43c..af679d8a5 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -3,10 +3,17 @@
 
 #include <sys/types.h>
 #include <stdio.h>
+#include <linux/atomic.h>
+
+struct thread_map_data {
+	pid_t    pid;
+	char	*comm;
+};
 
 struct thread_map {
+	atomic_t refcnt;
 	int nr;
-	pid_t map[];
+	struct thread_map_data map[];
 };
 
 struct thread_map *thread_map__new_dummy(void);
@@ -15,11 +22,12 @@ struct thread_map *thread_map__new_by_tid(pid_t tid);
 struct thread_map *thread_map__new_by_uid(uid_t uid);
 struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid);
 
+struct thread_map *thread_map__get(struct thread_map *map);
+void thread_map__put(struct thread_map *map);
+
 struct thread_map *thread_map__new_str(const char *pid,
 		const char *tid, uid_t uid);
 
-void thread_map__delete(struct thread_map *threads);
-
 size_t thread_map__fprintf(struct thread_map *threads, FILE *fp);
 
 static inline int thread_map__nr(struct thread_map *threads)
@@ -27,4 +35,21 @@ static inline int thread_map__nr(struct thread_map *threads)
 	return threads ? threads->nr : 1;
 }
 
+static inline pid_t thread_map__pid(struct thread_map *map, int thread)
+{
+	return map->map[thread].pid;
+}
+
+static inline void
+thread_map__set_pid(struct thread_map *map, int thread, pid_t pid)
+{
+	map->map[thread].pid = pid;
+}
+
+static inline char *thread_map__comm(struct thread_map *map, int thread)
+{
+	return map->map[thread].comm;
+}
+
+void thread_map__read_comms(struct thread_map *threads);
 #endif	/* __PERF_THREAD_MAP_H */
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 51d9e56c0..c307dd438 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -3,6 +3,8 @@
 
 #include <stdbool.h>
 
+#include <linux/types.h>
+
 struct perf_session;
 union perf_event;
 struct perf_evlist;
@@ -29,6 +31,9 @@ typedef int (*event_op2)(struct perf_tool *tool, 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);
+
 struct perf_tool {
 	event_sample	sample,
 			read;
@@ -38,13 +43,19 @@ struct perf_tool {
 			fork,
 			exit,
 			lost,
+			lost_samples,
+			aux,
+			itrace_start,
 			throttle,
 			unthrottle;
 	event_attr_op	attr;
 	event_op2	tracing_data;
 	event_oe	finished_round;
 	event_op2	build_id,
-			id_index;
+			id_index,
+			auxtrace_info,
+			auxtrace_error;
+	event_op3	auxtrace;
 	bool		ordered_events;
 	bool		ordering_requires_timestamps;
 };
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 25d6c737b..d49574186 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -173,7 +173,7 @@ void parse_ftrace_printk(struct pevent *pevent,
 	char *line;
 	char *next = NULL;
 	char *addr_str;
-	char *fmt;
+	char *fmt = NULL;
 
 	line = strtok_r(file, "\n", &next);
 	while (line) {
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 7b09a443a..4c00507ee 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -269,13 +269,14 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine,
 	u64 offset = dso->data.eh_frame_hdr_offset;
 
 	if (offset == 0) {
-		fd = dso__data_fd(dso, machine);
+		fd = dso__data_get_fd(dso, machine);
 		if (fd < 0)
 			return -EINVAL;
 
 		/* Check the .eh_frame section for unwinding info */
 		offset = elf_section_offset(fd, ".eh_frame_hdr");
 		dso->data.eh_frame_hdr_offset = offset;
+		dso__data_put_fd(dso);
 	}
 
 	if (offset)
@@ -294,13 +295,14 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
 	u64 ofs = dso->data.debug_frame_offset;
 
 	if (ofs == 0) {
-		fd = dso__data_fd(dso, machine);
+		fd = dso__data_get_fd(dso, machine);
 		if (fd < 0)
 			return -EINVAL;
 
 		/* Check the .debug_frame section for unwinding info */
 		ofs = elf_section_offset(fd, ".debug_frame");
 		dso->data.debug_frame_offset = ofs;
+		dso__data_put_fd(dso);
 	}
 
 	*offset = ofs;
@@ -353,10 +355,13 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
 #ifndef NO_LIBUNWIND_DEBUG_FRAME
 	/* Check the .debug_frame section for unwinding info */
 	if (!read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) {
-		int fd = dso__data_fd(map->dso, ui->machine);
+		int fd = dso__data_get_fd(map->dso, ui->machine);
 		int is_exec = elf_is_exec(fd, map->dso->name);
 		unw_word_t base = is_exec ? 0 : map->start;
 
+		if (fd >= 0)
+			dso__data_put_fd(map->dso);
+
 		memset(&di, 0, sizeof(di));
 		if (dwarf_find_debug_frame(0, &di, ip, base, map->dso->name,
 					   map->start, map->end))
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 4ee6d0d4c..edc2d633b 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -72,20 +72,60 @@ int mkdir_p(char *path, mode_t mode)
 	return (stat(path, &st) && mkdir(path, mode)) ? -1 : 0;
 }
 
-static int slow_copyfile(const char *from, const char *to, mode_t mode)
+int rm_rf(char *path)
+{
+	DIR *dir;
+	int ret = 0;
+	struct dirent *d;
+	char namebuf[PATH_MAX];
+
+	dir = opendir(path);
+	if (dir == NULL)
+		return 0;
+
+	while ((d = readdir(dir)) != NULL && !ret) {
+		struct stat statbuf;
+
+		if (!strcmp(d->d_name, ".") || !strcmp(d->d_name, ".."))
+			continue;
+
+		scnprintf(namebuf, sizeof(namebuf), "%s/%s",
+			  path, d->d_name);
+
+		ret = stat(namebuf, &statbuf);
+		if (ret < 0) {
+			pr_debug("stat failed: %s\n", namebuf);
+			break;
+		}
+
+		if (S_ISREG(statbuf.st_mode))
+			ret = unlink(namebuf);
+		else if (S_ISDIR(statbuf.st_mode))
+			ret = rm_rf(namebuf);
+		else {
+			pr_debug("unknown file: %s\n", namebuf);
+			ret = -1;
+		}
+	}
+	closedir(dir);
+
+	if (ret < 0)
+		return ret;
+
+	return rmdir(path);
+}
+
+static int slow_copyfile(const char *from, const char *to)
 {
 	int err = -1;
 	char *line = NULL;
 	size_t n;
 	FILE *from_fp = fopen(from, "r"), *to_fp;
-	mode_t old_umask;
 
 	if (from_fp == NULL)
 		goto out;
 
-	old_umask = umask(mode ^ 0777);
 	to_fp = fopen(to, "w");
-	umask(old_umask);
 	if (to_fp == NULL)
 		goto out_fclose_from;
 
@@ -102,42 +142,81 @@ out:
 	return err;
 }
 
+int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
+{
+	void *ptr;
+	loff_t pgoff;
+
+	pgoff = off_in & ~(page_size - 1);
+	off_in -= pgoff;
+
+	ptr = mmap(NULL, off_in + size, PROT_READ, MAP_PRIVATE, ifd, pgoff);
+	if (ptr == MAP_FAILED)
+		return -1;
+
+	while (size) {
+		ssize_t ret = pwrite(ofd, ptr + off_in, size, off_out);
+		if (ret < 0 && errno == EINTR)
+			continue;
+		if (ret <= 0)
+			break;
+
+		size -= ret;
+		off_in += ret;
+		off_out -= ret;
+	}
+	munmap(ptr, off_in + size);
+
+	return size ? -1 : 0;
+}
+
 int copyfile_mode(const char *from, const char *to, mode_t mode)
 {
 	int fromfd, tofd;
 	struct stat st;
-	void *addr;
 	int err = -1;
+	char *tmp = NULL, *ptr = NULL;
 
 	if (stat(from, &st))
 		goto out;
 
-	if (st.st_size == 0) /* /proc? do it slowly... */
-		return slow_copyfile(from, to, mode);
-
-	fromfd = open(from, O_RDONLY);
-	if (fromfd < 0)
+	/* extra 'x' at the end is to reserve space for '.' */
+	if (asprintf(&tmp, "%s.XXXXXXx", to) < 0) {
+		tmp = NULL;
 		goto out;
+	}
+	ptr = strrchr(tmp, '/');
+	if (!ptr)
+		goto out;
+	ptr = memmove(ptr + 1, ptr, strlen(ptr) - 1);
+	*ptr = '.';
 
-	tofd = creat(to, mode);
+	tofd = mkstemp(tmp);
 	if (tofd < 0)
-		goto out_close_from;
+		goto out;
+
+	if (fchmod(tofd, mode))
+		goto out_close_to;
+
+	if (st.st_size == 0) { /* /proc? do it slowly... */
+		err = slow_copyfile(from, tmp);
+		goto out_close_to;
+	}
 
-	addr = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fromfd, 0);
-	if (addr == MAP_FAILED)
+	fromfd = open(from, O_RDONLY);
+	if (fromfd < 0)
 		goto out_close_to;
 
-	if (write(tofd, addr, st.st_size) == st.st_size)
-		err = 0;
+	err = copyfile_offset(fromfd, 0, tofd, 0, st.st_size);
 
-	munmap(addr, st.st_size);
+	close(fromfd);
 out_close_to:
 	close(tofd);
-	if (err)
-		unlink(to);
-out_close_from:
-	close(fromfd);
+	if (!err)
+		err = link(tmp, to);
+	unlink(tmp);
 out:
+	free(tmp);
 	return err;
 }
 
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 1ff23e04a..8bce58b47 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -249,14 +249,20 @@ static inline int sane_case(int x, int high)
 }
 
 int mkdir_p(char *path, mode_t mode);
+int rm_rf(char *path);
 int copyfile(const char *from, const char *to);
 int copyfile_mode(const char *from, const char *to, mode_t mode);
+int copyfile_offset(int fromfd, loff_t from_ofs, int tofd, loff_t to_ofs, u64 size);
 
 s64 perf_atoll(const char *str);
 char **argv_split(const char *str, int *argcp);
 void argv_free(char **argv);
 bool strglobmatch(const char *str, const char *pat);
 bool strlazymatch(const char *str, const char *pat);
+static inline bool strisglob(const char *str)
+{
+	return strpbrk(str, "*?[") != NULL;
+}
 int strtailcmp(const char *s1, const char *s2);
 char *strxfrchar(char *s, char from, char to);
 unsigned long convert_unit(unsigned long value, char *unit);
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 5c7dd7969..44d440da1 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -101,7 +101,7 @@ static char *get_file(struct vdso_file *vdso_file)
 	return vdso;
 }
 
-void vdso__exit(struct machine *machine)
+void machine__exit_vdso(struct machine *machine)
 {
 	struct vdso_info *vdso_info = machine->vdso_info;
 
@@ -120,14 +120,14 @@ void vdso__exit(struct machine *machine)
 	zfree(&machine->vdso_info);
 }
 
-static struct dso *vdso__new(struct machine *machine, const char *short_name,
-			     const char *long_name)
+static struct dso *__machine__addnew_vdso(struct machine *machine, const char *short_name,
+					  const char *long_name)
 {
 	struct dso *dso;
 
 	dso = dso__new(short_name);
 	if (dso != NULL) {
-		dsos__add(&machine->user_dsos, dso);
+		__dsos__add(&machine->dsos, dso);
 		dso__set_long_name(dso, long_name, false);
 	}
 
@@ -230,27 +230,29 @@ static const char *vdso__get_compat_file(struct vdso_file *vdso_file)
 	return vdso_file->temp_file_name;
 }
 
-static struct dso *vdso__findnew_compat(struct machine *machine,
-					struct vdso_file *vdso_file)
+static struct dso *__machine__findnew_compat(struct machine *machine,
+					     struct vdso_file *vdso_file)
 {
 	const char *file_name;
 	struct dso *dso;
 
-	dso = dsos__find(&machine->user_dsos, vdso_file->dso_name, true);
+	dso = __dsos__find(&machine->dsos, vdso_file->dso_name, true);
 	if (dso)
-		return dso;
+		goto out;
 
 	file_name = vdso__get_compat_file(vdso_file);
 	if (!file_name)
-		return NULL;
+		goto out;
 
-	return vdso__new(machine, vdso_file->dso_name, file_name);
+	dso = __machine__addnew_vdso(machine, vdso_file->dso_name, file_name);
+out:
+	return dso;
 }
 
-static int vdso__dso_findnew_compat(struct machine *machine,
-				    struct thread *thread,
-				    struct vdso_info *vdso_info,
-				    struct dso **dso)
+static int __machine__findnew_vdso_compat(struct machine *machine,
+					  struct thread *thread,
+					  struct vdso_info *vdso_info,
+					  struct dso **dso)
 {
 	enum dso_type dso_type;
 
@@ -267,10 +269,10 @@ static int vdso__dso_findnew_compat(struct machine *machine,
 
 	switch (dso_type) {
 	case DSO__TYPE_32BIT:
-		*dso = vdso__findnew_compat(machine, &vdso_info->vdso32);
+		*dso = __machine__findnew_compat(machine, &vdso_info->vdso32);
 		return 1;
 	case DSO__TYPE_X32BIT:
-		*dso = vdso__findnew_compat(machine, &vdso_info->vdsox32);
+		*dso = __machine__findnew_compat(machine, &vdso_info->vdsox32);
 		return 1;
 	case DSO__TYPE_UNKNOWN:
 	case DSO__TYPE_64BIT:
@@ -281,35 +283,37 @@ static int vdso__dso_findnew_compat(struct machine *machine,
 
 #endif
 
-struct dso *vdso__dso_findnew(struct machine *machine,
-			      struct thread *thread __maybe_unused)
+struct dso *machine__findnew_vdso(struct machine *machine,
+				  struct thread *thread __maybe_unused)
 {
 	struct vdso_info *vdso_info;
-	struct dso *dso;
+	struct dso *dso = NULL;
 
+	pthread_rwlock_wrlock(&machine->dsos.lock);
 	if (!machine->vdso_info)
 		machine->vdso_info = vdso_info__new();
 
 	vdso_info = machine->vdso_info;
 	if (!vdso_info)
-		return NULL;
+		goto out_unlock;
 
 #if BITS_PER_LONG == 64
-	if (vdso__dso_findnew_compat(machine, thread, vdso_info, &dso))
-		return dso;
+	if (__machine__findnew_vdso_compat(machine, thread, vdso_info, &dso))
+		goto out_unlock;
 #endif
 
-	dso = dsos__find(&machine->user_dsos, DSO__NAME_VDSO, true);
+	dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO, true);
 	if (!dso) {
 		char *file;
 
 		file = get_file(&vdso_info->vdso);
-		if (!file)
-			return NULL;
-
-		dso = vdso__new(machine, DSO__NAME_VDSO, file);
+		if (file)
+			dso = __machine__addnew_vdso(machine, DSO__NAME_VDSO, file);
 	}
 
+out_unlock:
+	dso__get(dso);
+	pthread_rwlock_unlock(&machine->dsos.lock);
 	return dso;
 }
 
diff --git a/tools/perf/util/vdso.h b/tools/perf/util/vdso.h
index d97da1616..cdc4fabfc 100644
--- a/tools/perf/util/vdso.h
+++ b/tools/perf/util/vdso.h
@@ -23,7 +23,7 @@ bool dso__is_vdso(struct dso *dso);
 struct machine;
 struct thread;
 
-struct dso *vdso__dso_findnew(struct machine *machine, struct thread *thread);
-void vdso__exit(struct machine *machine);
+struct dso *machine__findnew_vdso(struct machine *machine, struct thread *thread);
+void machine__exit_vdso(struct machine *machine);
 
 #endif /* __PERF_VDSO__ */
diff --git a/tools/perf/util/xyarray.c b/tools/perf/util/xyarray.c
index 22afbf6c5..c10ba41ef 100644
--- a/tools/perf/util/xyarray.c
+++ b/tools/perf/util/xyarray.c
@@ -9,11 +9,19 @@ struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size)
 	if (xy != NULL) {
 		xy->entry_size = entry_size;
 		xy->row_size   = row_size;
+		xy->entries    = xlen * ylen;
 	}
 
 	return xy;
 }
 
+void xyarray__reset(struct xyarray *xy)
+{
+	size_t n = xy->entries * xy->entry_size;
+
+	memset(xy->contents, 0, n);
+}
+
 void xyarray__delete(struct xyarray *xy)
 {
 	free(xy);
diff --git a/tools/perf/util/xyarray.h b/tools/perf/util/xyarray.h
index c488a0727..7f30af371 100644
--- a/tools/perf/util/xyarray.h
+++ b/tools/perf/util/xyarray.h
@@ -6,11 +6,13 @@
 struct xyarray {
 	size_t row_size;
 	size_t entry_size;
+	size_t entries;
 	char contents[];
 };
 
 struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size);
 void xyarray__delete(struct xyarray *xy);
+void xyarray__reset(struct xyarray *xy);
 
 static inline void *xyarray__entry(struct xyarray *xy, int x, int y)
 {