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

Pull perf updates from Ingo Molnar:
 "Bigger kernel side changes:

   - Add backwards writing capability to the perf ring-buffer code,
     which is preparation for future advanced features like robust
     'overwrite support' and snapshot mode.  (Wang Nan)

   - Add pause and resume ioctls for the perf ringbuffer (Wang Nan)

   - x86 Intel cstate code cleanups and reorgnization (Thomas Gleixner)

   - x86 Intel uncore and CPU PMU driver updates (Kan Liang, Peter
     Zijlstra)

   - x86 AUX (Intel PT) related enhancements and updates (Alexander
     Shishkin)

   - x86 MSR PMU driver enhancements and updates (Huang Rui)

   - ... and lots of other changes spread out over 40+ commits.

  Biggest tooling side changes:

   - 'perf trace' features and enhancements.  (Arnaldo Carvalho de Melo)

   - BPF tooling updates (Wang Nan)

   - 'perf sched' updates (Jiri Olsa)

   - 'perf probe' updates (Masami Hiramatsu)

   - ... plus 200+ other enhancements, fixes and cleanups to tools/

  The merge commits, the shortlog and the changelogs contain a lot more
  details"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (249 commits)
  perf/core: Disable the event on a truncated AUX record
  perf/x86/intel/pt: Generate PMI in the STOP region as well
  perf buildid-cache: Use lsdir() for looking up buildid caches
  perf symbols: Use lsdir() for the search in kcore cache directory
  perf tools: Use SBUILD_ID_SIZE where applicable
  perf tools: Fix lsdir to set errno correctly
  perf trace: Move seccomp args beautifiers to tools/perf/trace/beauty/
  perf trace: Move flock op beautifier to tools/perf/trace/beauty/
  perf build: Add build-test for debug-frame on arm/arm64
  perf build: Add build-test for libunwind cross-platforms support
  perf script: Fix export of callchains with recursion in db-export
  perf script: Fix callchain addresses in db-export
  perf script: Fix symbol insertion behavior in db-export
  perf symbols: Add dso__insert_symbol function
  perf scripting python: Use Py_FatalError instead of die()
  perf tools: Remove xrealloc and ALLOC_GROW
  perf help: Do not use ALLOC_GROW in add_cmd_list
  perf pmu: Make pmu_formats_string to check return value of strbuf
  perf header: Make topology checkers to check return value of strbuf
  perf tools: Make alias handler to check return value of strbuf
  ...

81 files changed, 2679 insertions, 1073 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index da48fd843438..8c6c8a0ca642 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -8,6 +8,7 @@ libperf-y += env.o
 libperf-y += event.o
 libperf-y += evlist.o
 libperf-y += evsel.o
+libperf-y += evsel_fprintf.o
 libperf-y += find_bit.o
 libperf-y += kallsyms.o
 libperf-y += levenshtein.o
@@ -26,9 +27,9 @@ libperf-y += strlist.o
 libperf-y += strfilter.o
 libperf-y += top.o
 libperf-y += usage.o
-libperf-y += wrapper.o
 libperf-y += dso.o
 libperf-y += symbol.o
+libperf-y += symbol_fprintf.o
 libperf-y += color.o
 libperf-y += header.o
 libperf-y += callchain.o
@@ -38,6 +39,7 @@ libperf-y += machine.o
 libperf-y += map.o
 libperf-y += pstack.o
 libperf-y += session.o
+libperf-$(CONFIG_AUDIT) += syscalltbl.o
 libperf-y += ordered-events.o
 libperf-y += comm.o
 libperf-y += thread.o
@@ -69,9 +71,9 @@ libperf-y += stat-shadow.o
 libperf-y += record.o
 libperf-y += srcline.o
 libperf-y += data.o
-libperf-$(CONFIG_X86) += tsc.o
-libperf-$(CONFIG_AUXTRACE) += tsc.o
+libperf-y += tsc.o
 libperf-y += cloexec.o
+libperf-y += call-path.o
 libperf-y += thread-stack.o
 libperf-$(CONFIG_AUXTRACE) += auxtrace.o
 libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index b795b6994144..4db73d5a0dbc 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1138,7 +1138,7 @@ fallback:
 
 	if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
 	    !dso__is_kcore(dso)) {
-		char bf[BUILD_ID_SIZE * 2 + 16] = " with build id ";
+		char bf[SBUILD_ID_SIZE + 15] = " with build id ";
 		char *build_id_msg = NULL;
 
 		if (dso->annotate_warned)
@@ -1665,5 +1665,5 @@ int hist_entry__annotate(struct hist_entry *he, size_t privsize)
 
 bool ui__has_annotation(void)
 {
-	return use_browser == 1 && sort__has_sym;
+	return use_browser == 1 && perf_hpp_list.sym;
 }
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index ec164fe70718..c9169011e55e 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -940,6 +940,7 @@ void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts)
 	synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
 	synth_opts->callchain_sz = PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
 	synth_opts->last_branch_sz = PERF_ITRACE_DEFAULT_LAST_BRANCH_SZ;
+	synth_opts->initial_skip = 0;
 }
 
 /*
@@ -1064,6 +1065,12 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
 				synth_opts->last_branch_sz = val;
 			}
 			break;
+		case 's':
+			synth_opts->initial_skip = strtoul(p, &endptr, 10);
+			if (p == endptr)
+				goto out_err;
+			p = endptr;
+			break;
 		case ' ':
 		case ',':
 			break;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 57ff31ecb8e4..767989e0e312 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -68,6 +68,7 @@ enum itrace_period_type {
  * @last_branch_sz: branch context size
  * @period: 'instructions' events period
  * @period_type: 'instructions' events period type
+ * @initial_skip: skip N events at the beginning.
  */
 struct itrace_synth_opts {
 	bool			set;
@@ -86,6 +87,7 @@ struct itrace_synth_opts {
 	unsigned int		last_branch_sz;
 	unsigned long long	period;
 	enum itrace_period_type	period_type;
+	unsigned long		initial_skip;
 };
 
 /**
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 0967ce601931..493307d1414c 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -842,6 +842,58 @@ bpf_map_op__new(struct parse_events_term *term)
 	return op;
 }
 
+static struct bpf_map_op *
+bpf_map_op__clone(struct bpf_map_op *op)
+{
+	struct bpf_map_op *newop;
+
+	newop = memdup(op, sizeof(*op));
+	if (!newop) {
+		pr_debug("Failed to alloc bpf_map_op\n");
+		return NULL;
+	}
+
+	INIT_LIST_HEAD(&newop->list);
+	if (op->key_type == BPF_MAP_KEY_RANGES) {
+		size_t memsz = op->k.array.nr_ranges *
+			       sizeof(op->k.array.ranges[0]);
+
+		newop->k.array.ranges = memdup(op->k.array.ranges, memsz);
+		if (!newop->k.array.ranges) {
+			pr_debug("Failed to alloc indices for map\n");
+			free(newop);
+			return NULL;
+		}
+	}
+
+	return newop;
+}
+
+static struct bpf_map_priv *
+bpf_map_priv__clone(struct bpf_map_priv *priv)
+{
+	struct bpf_map_priv *newpriv;
+	struct bpf_map_op *pos, *newop;
+
+	newpriv = zalloc(sizeof(*newpriv));
+	if (!newpriv) {
+		pr_debug("No enough memory to alloc map private\n");
+		return NULL;
+	}
+	INIT_LIST_HEAD(&newpriv->ops_list);
+
+	list_for_each_entry(pos, &priv->ops_list, list) {
+		newop = bpf_map_op__clone(pos);
+		if (!newop) {
+			bpf_map_priv__purge(newpriv);
+			return NULL;
+		}
+		list_add_tail(&newop->list, &newpriv->ops_list);
+	}
+
+	return newpriv;
+}
+
 static int
 bpf_map__add_op(struct bpf_map *map, struct bpf_map_op *op)
 {
@@ -1417,6 +1469,89 @@ int bpf__apply_obj_config(void)
 	return 0;
 }
 
+#define bpf__for_each_map(pos, obj, objtmp)	\
+	bpf_object__for_each_safe(obj, objtmp)	\
+		bpf_map__for_each(pos, obj)
+
+#define bpf__for_each_stdout_map(pos, obj, objtmp)	\
+	bpf__for_each_map(pos, obj, objtmp) 		\
+		if (bpf_map__get_name(pos) && 		\
+			(strcmp("__bpf_stdout__", 	\
+				bpf_map__get_name(pos)) == 0))
+
+int bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused)
+{
+	struct bpf_map_priv *tmpl_priv = NULL;
+	struct bpf_object *obj, *tmp;
+	struct perf_evsel *evsel = NULL;
+	struct bpf_map *map;
+	int err;
+	bool need_init = false;
+
+	bpf__for_each_stdout_map(map, obj, tmp) {
+		struct bpf_map_priv *priv;
+
+		err = bpf_map__get_private(map, (void **)&priv);
+		if (err)
+			return -BPF_LOADER_ERRNO__INTERNAL;
+
+		/*
+		 * No need to check map type: type should have been
+		 * verified by kernel.
+		 */
+		if (!need_init && !priv)
+			need_init = !priv;
+		if (!tmpl_priv && priv)
+			tmpl_priv = priv;
+	}
+
+	if (!need_init)
+		return 0;
+
+	if (!tmpl_priv) {
+		err = parse_events(evlist, "bpf-output/no-inherit=1,name=__bpf_stdout__/",
+				   NULL);
+		if (err) {
+			pr_debug("ERROR: failed to create bpf-output event\n");
+			return -err;
+		}
+
+		evsel = perf_evlist__last(evlist);
+	}
+
+	bpf__for_each_stdout_map(map, obj, tmp) {
+		struct bpf_map_priv *priv;
+
+		err = bpf_map__get_private(map, (void **)&priv);
+		if (err)
+			return -BPF_LOADER_ERRNO__INTERNAL;
+		if (priv)
+			continue;
+
+		if (tmpl_priv) {
+			priv = bpf_map_priv__clone(tmpl_priv);
+			if (!priv)
+				return -ENOMEM;
+
+			err = bpf_map__set_private(map, priv, bpf_map_priv__clear);
+			if (err) {
+				bpf_map_priv__clear(map, priv);
+				return err;
+			}
+		} else if (evsel) {
+			struct bpf_map_op *op;
+
+			op = bpf_map__add_newop(map, NULL);
+			if (IS_ERR(op))
+				return PTR_ERR(op);
+			op->op_type = BPF_MAP_OP_SET_EVSEL;
+			op->v.evsel = evsel;
+		}
+	}
+
+	return 0;
+}
+
 #define ERRNO_OFFSET(e)		((e) - __BPF_LOADER_ERRNO__START)
 #define ERRCODE_OFFSET(c)	ERRNO_OFFSET(BPF_LOADER_ERRNO__##c)
 #define NR_ERRNO	(__BPF_LOADER_ERRNO__END - __BPF_LOADER_ERRNO__START)
@@ -1590,3 +1725,11 @@ int bpf__strerror_apply_obj_config(int err, char *buf, size_t size)
 	bpf__strerror_end(buf, size);
 	return 0;
 }
+
+int bpf__strerror_setup_stdout(struct perf_evlist *evlist __maybe_unused,
+			       int err, char *buf, size_t size)
+{
+	bpf__strerror_head(err, buf, size);
+	bpf__strerror_end(buf, size);
+	return 0;
+}
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index be4311944e3d..941e17275aa7 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -79,6 +79,11 @@ int bpf__strerror_config_obj(struct bpf_object *obj,
 			     size_t size);
 int bpf__apply_obj_config(void);
 int bpf__strerror_apply_obj_config(int err, char *buf, size_t size);
+
+int bpf__setup_stdout(struct perf_evlist *evlist);
+int bpf__strerror_setup_stdout(struct perf_evlist *evlist, int err,
+			       char *buf, size_t size);
+
 #else
 static inline struct bpf_object *
 bpf__prepare_load(const char *filename __maybe_unused,
@@ -125,6 +130,12 @@ bpf__apply_obj_config(void)
 }
 
 static inline int
+bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused)
+{
+	return 0;
+}
+
+static inline int
 __bpf_strerror(char *buf, size_t size)
 {
 	if (!size)
@@ -177,5 +188,13 @@ bpf__strerror_apply_obj_config(int err __maybe_unused,
 {
 	return __bpf_strerror(buf, size);
 }
+
+static inline int
+bpf__strerror_setup_stdout(struct perf_evlist *evlist __maybe_unused,
+			   int err __maybe_unused, char *buf,
+			   size_t size)
+{
+	return __bpf_strerror(buf, size);
+}
 #endif
 #endif
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 0573c2ec861d..bff425e1232c 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -261,14 +261,14 @@ static int machine__write_buildid_table(struct machine *machine, int fd)
 
 		if (dso__is_vdso(pos)) {
 			name = pos->short_name;
-			name_len = pos->short_name_len + 1;
+			name_len = pos->short_name_len;
 		} else if (dso__is_kcore(pos)) {
 			machine__mmap_name(machine, nm, sizeof(nm));
 			name = nm;
-			name_len = strlen(nm) + 1;
+			name_len = strlen(nm);
 		} else {
 			name = pos->long_name;
-			name_len = pos->long_name_len + 1;
+			name_len = pos->long_name_len;
 		}
 
 		in_kernel = pos->kernel ||
@@ -365,39 +365,17 @@ static char *build_id_cache__dirname_from_path(const char *name,
 int build_id_cache__list_build_ids(const char *pathname,
 				   struct strlist **result)
 {
-	struct strlist *list;
 	char *dir_name;
-	DIR *dir;
-	struct dirent *d;
 	int ret = 0;
 
-	list = strlist__new(NULL, NULL);
 	dir_name = build_id_cache__dirname_from_path(pathname, false, false);
-	if (!list || !dir_name) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	if (!dir_name)
+		return -ENOMEM;
 
-	/* List up all dirents */
-	dir = opendir(dir_name);
-	if (!dir) {
+	*result = lsdir(dir_name, lsdir_no_dot_filter);
+	if (!*result)
 		ret = -errno;
-		goto out;
-	}
-
-	while ((d = readdir(dir)) != NULL) {
-		if (!strcmp(d->d_name, ".") || !strcmp(d->d_name, ".."))
-			continue;
-		strlist__add(list, d->d_name);
-	}
-	closedir(dir);
-
-out:
 	free(dir_name);
-	if (ret)
-		strlist__delete(list);
-	else
-		*result = list;
 
 	return ret;
 }
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 1f5a93c2c9a2..0d814bb74661 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -40,25 +40,6 @@ int split_cmdline(char *cmdline, const char ***argv);
 
 #define alloc_nr(x) (((x)+16)*3/2)
 
-/*
- * Realloc the buffer pointed at by variable 'x' so that it can hold
- * at least 'nr' entries; the number of entries currently allocated
- * is 'alloc', using the standard growing factor alloc_nr() macro.
- *
- * DO NOT USE any expression with side-effect for 'x' or 'alloc'.
- */
-#define ALLOC_GROW(x, nr, alloc) \
-	do { \
-		if ((nr) > alloc) { \
-			if (alloc_nr(alloc) < (nr)) \
-				alloc = (nr); \
-			else \
-				alloc = alloc_nr(alloc); \
-			x = xrealloc((x), alloc * sizeof(*(x))); \
-		} \
-	} while(0)
-
-
 static inline int is_absolute_path(const char *path)
 {
 	return path[0] == '/';
diff --git a/tools/perf/util/call-path.c b/tools/perf/util/call-path.c
new file mode 100644
index 000000000000..904a17052e38
--- /dev/null
+++ b/tools/perf/util/call-path.c
@@ -0,0 +1,122 @@
+/*
+ * call-path.h: Manipulate a tree data structure containing function call paths
+ * Copyright (c) 2014, 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 <linux/rbtree.h>
+#include <linux/list.h>
+
+#include "util.h"
+#include "call-path.h"
+
+static void call_path__init(struct call_path *cp, struct call_path *parent,
+			    struct symbol *sym, u64 ip, bool in_kernel)
+{
+	cp->parent = parent;
+	cp->sym = sym;
+	cp->ip = sym ? 0 : ip;
+	cp->db_id = 0;
+	cp->in_kernel = in_kernel;
+	RB_CLEAR_NODE(&cp->rb_node);
+	cp->children = RB_ROOT;
+}
+
+struct call_path_root *call_path_root__new(void)
+{
+	struct call_path_root *cpr;
+
+	cpr = zalloc(sizeof(struct call_path_root));
+	if (!cpr)
+		return NULL;
+	call_path__init(&cpr->call_path, NULL, NULL, 0, false);
+	INIT_LIST_HEAD(&cpr->blocks);
+	return cpr;
+}
+
+void call_path_root__free(struct call_path_root *cpr)
+{
+	struct call_path_block *pos, *n;
+
+	list_for_each_entry_safe(pos, n, &cpr->blocks, node) {
+		list_del(&pos->node);
+		free(pos);
+	}
+	free(cpr);
+}
+
+static struct call_path *call_path__new(struct call_path_root *cpr,
+					struct call_path *parent,
+					struct symbol *sym, u64 ip,
+					bool in_kernel)
+{
+	struct call_path_block *cpb;
+	struct call_path *cp;
+	size_t n;
+
+	if (cpr->next < cpr->sz) {
+		cpb = list_last_entry(&cpr->blocks, struct call_path_block,
+				      node);
+	} else {
+		cpb = zalloc(sizeof(struct call_path_block));
+		if (!cpb)
+			return NULL;
+		list_add_tail(&cpb->node, &cpr->blocks);
+		cpr->sz += CALL_PATH_BLOCK_SIZE;
+	}
+
+	n = cpr->next++ & CALL_PATH_BLOCK_MASK;
+	cp = &cpb->cp[n];
+
+	call_path__init(cp, parent, sym, ip, in_kernel);
+
+	return cp;
+}
+
+struct call_path *call_path__findnew(struct call_path_root *cpr,
+				     struct call_path *parent,
+				     struct symbol *sym, u64 ip, u64 ks)
+{
+	struct rb_node **p;
+	struct rb_node *node_parent = NULL;
+	struct call_path *cp;
+	bool in_kernel = ip >= ks;
+
+	if (sym)
+		ip = 0;
+
+	if (!parent)
+		return call_path__new(cpr, parent, sym, ip, in_kernel);
+
+	p = &parent->children.rb_node;
+	while (*p != NULL) {
+		node_parent = *p;
+		cp = rb_entry(node_parent, struct call_path, rb_node);
+
+		if (cp->sym == sym && cp->ip == ip)
+			return cp;
+
+		if (sym < cp->sym || (sym == cp->sym && ip < cp->ip))
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	cp = call_path__new(cpr, parent, sym, ip, in_kernel);
+	if (!cp)
+		return NULL;
+
+	rb_link_node(&cp->rb_node, node_parent, p);
+	rb_insert_color(&cp->rb_node, &parent->children);
+
+	return cp;
+}
diff --git a/tools/perf/util/call-path.h b/tools/perf/util/call-path.h
new file mode 100644
index 000000000000..477f6d03b659
--- /dev/null
+++ b/tools/perf/util/call-path.h
@@ -0,0 +1,77 @@
+/*
+ * call-path.h: Manipulate a tree data structure containing function call paths
+ * Copyright (c) 2014, 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_CALL_PATH_H
+#define __PERF_CALL_PATH_H
+
+#include <sys/types.h>
+
+#include <linux/types.h>
+#include <linux/rbtree.h>
+
+/**
+ * struct call_path - node in list of calls leading to a function call.
+ * @parent: call path to the parent function call
+ * @sym: symbol of function called
+ * @ip: only if sym is null, the ip of the function
+ * @db_id: id used for db-export
+ * @in_kernel: whether function is a in the kernel
+ * @rb_node: node in parent's tree of called functions
+ * @children: tree of call paths of functions called
+ *
+ * In combination with the call_return structure, the call_path structure
+ * defines a context-sensitve call-graph.
+ */
+struct call_path {
+	struct call_path *parent;
+	struct symbol *sym;
+	u64 ip;
+	u64 db_id;
+	bool in_kernel;
+	struct rb_node rb_node;
+	struct rb_root children;
+};
+
+#define CALL_PATH_BLOCK_SHIFT 8
+#define CALL_PATH_BLOCK_SIZE (1 << CALL_PATH_BLOCK_SHIFT)
+#define CALL_PATH_BLOCK_MASK (CALL_PATH_BLOCK_SIZE - 1)
+
+struct call_path_block {
+	struct call_path cp[CALL_PATH_BLOCK_SIZE];
+	struct list_head node;
+};
+
+/**
+ * struct call_path_root - root of all call paths.
+ * @call_path: root call path
+ * @blocks: list of blocks to store call paths
+ * @next: next free space
+ * @sz: number of spaces
+ */
+struct call_path_root {
+	struct call_path call_path;
+	struct list_head blocks;
+	size_t next;
+	size_t sz;
+};
+
+struct call_path_root *call_path_root__new(void);
+void call_path_root__free(struct call_path_root *cpr);
+
+struct call_path *call_path__findnew(struct call_path_root *cpr,
+				     struct call_path *parent,
+				     struct symbol *sym, u64 ip, u64 ks);
+
+#endif
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 24b4bd0d7754..07fd30bc2f81 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -109,6 +109,7 @@ __parse_callchain_report_opt(const char *arg, bool allow_record_opt)
 	bool record_opt_set = false;
 	bool try_stack_size = false;
 
+	callchain_param.enabled = true;
 	symbol_conf.use_callchain = true;
 
 	if (!arg)
@@ -117,6 +118,7 @@ __parse_callchain_report_opt(const char *arg, bool allow_record_opt)
 	while ((tok = strtok((char *)arg, ",")) != NULL) {
 		if (!strncmp(tok, "none", strlen(tok))) {
 			callchain_param.mode = CHAIN_NONE;
+			callchain_param.enabled = false;
 			symbol_conf.use_callchain = false;
 			return 0;
 		}
@@ -788,7 +790,8 @@ int callchain_cursor_append(struct callchain_cursor *cursor,
 	return 0;
 }
 
-int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent,
+int sample__resolve_callchain(struct perf_sample *sample,
+			      struct callchain_cursor *cursor, struct symbol **parent,
 			      struct perf_evsel *evsel, struct addr_location *al,
 			      int max_stack)
 {
@@ -796,8 +799,8 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent
 		return 0;
 
 	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain ||
-	    sort__has_parent) {
-		return thread__resolve_callchain(al->thread, evsel, sample,
+	    perf_hpp_list.parent) {
+		return thread__resolve_callchain(al->thread, cursor, evsel, sample,
 						 parent, al, max_stack);
 	}
 	return 0;
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index d2a9e694810c..65e2a4f7cb4e 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -212,7 +212,14 @@ struct hist_entry;
 int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset);
 int record_callchain_opt(const struct option *opt, const char *arg, int unset);
 
-int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent,
+struct record_opts;
+
+int record_opts__parse_callchain(struct record_opts *record,
+				 struct callchain_param *callchain,
+				 const char *arg, bool unset);
+
+int sample__resolve_callchain(struct perf_sample *sample,
+			      struct callchain_cursor *cursor, struct symbol **parent,
 			      struct perf_evsel *evsel, struct addr_location *al,
 			      int max_stack);
 int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample);
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 4e727635476e..dad7d8272168 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -13,6 +13,7 @@
 #include <subcmd/exec-cmd.h>
 #include "util/hist.h"  /* perf_hist_config */
 #include "util/llvm-utils.h"   /* perf_llvm_config */
+#include "config.h"
 
 #define MAXNAME (256)
 
@@ -377,6 +378,21 @@ const char *perf_config_dirname(const char *name, const char *value)
 	return value;
 }
 
+static int perf_buildid_config(const char *var, const char *value)
+{
+	/* same dir for all commands */
+	if (!strcmp(var, "buildid.dir")) {
+		const char *dir = perf_config_dirname(var, value);
+
+		if (!dir)
+			return -1;
+		strncpy(buildid_dir, dir, MAXPATHLEN-1);
+		buildid_dir[MAXPATHLEN-1] = '\0';
+	}
+
+	return 0;
+}
+
 static int perf_default_core_config(const char *var __maybe_unused,
 				    const char *value __maybe_unused)
 {
@@ -412,6 +428,9 @@ int perf_default_config(const char *var, const char *value,
 	if (!prefixcmp(var, "llvm."))
 		return perf_llvm_config(var, value);
 
+	if (!prefixcmp(var, "buildid."))
+		return perf_buildid_config(var, value);
+
 	/* Add other config variables here. */
 	return 0;
 }
@@ -506,41 +525,185 @@ out:
 	return ret;
 }
 
-/*
- * Call this to report error for your variable that should not
- * get a boolean value (i.e. "[my] var" means "true").
- */
-int config_error_nonbool(const char *var)
+static struct perf_config_section *find_section(struct list_head *sections,
+						const char *section_name)
 {
-	return error("Missing value for '%s'", var);
+	struct perf_config_section *section;
+
+	list_for_each_entry(section, sections, node)
+		if (!strcmp(section->name, section_name))
+			return section;
+
+	return NULL;
+}
+
+static struct perf_config_item *find_config_item(const char *name,
+						 struct perf_config_section *section)
+{
+	struct perf_config_item *item;
+
+	list_for_each_entry(item, &section->items, node)
+		if (!strcmp(item->name, name))
+			return item;
+
+	return NULL;
 }
 
-struct buildid_dir_config {
-	char *dir;
-};
+static struct perf_config_section *add_section(struct list_head *sections,
+					       const char *section_name)
+{
+	struct perf_config_section *section = zalloc(sizeof(*section));
+
+	if (!section)
+		return NULL;
+
+	INIT_LIST_HEAD(&section->items);
+	section->name = strdup(section_name);
+	if (!section->name) {
+		pr_debug("%s: strdup failed\n", __func__);
+		free(section);
+		return NULL;
+	}
+
+	list_add_tail(&section->node, sections);
+	return section;
+}
 
-static int buildid_dir_command_config(const char *var, const char *value,
-				      void *data)
+static struct perf_config_item *add_config_item(struct perf_config_section *section,
+						const char *name)
 {
-	struct buildid_dir_config *c = data;
-	const char *v;
+	struct perf_config_item *item = zalloc(sizeof(*item));
 
-	/* same dir for all commands */
-	if (!strcmp(var, "buildid.dir")) {
-		v = perf_config_dirname(var, value);
-		if (!v)
-			return -1;
-		strncpy(c->dir, v, MAXPATHLEN-1);
-		c->dir[MAXPATHLEN-1] = '\0';
+	if (!item)
+		return NULL;
+
+	item->name = strdup(name);
+	if (!item->name) {
+		pr_debug("%s: strdup failed\n", __func__);
+		free(item);
+		return NULL;
 	}
+
+	list_add_tail(&item->node, &section->items);
+	return item;
+}
+
+static int set_value(struct perf_config_item *item, const char *value)
+{
+	char *val = strdup(value);
+
+	if (!val)
+		return -1;
+
+	zfree(&item->value);
+	item->value = val;
 	return 0;
 }
 
-static void check_buildid_dir_config(void)
+static int collect_config(const char *var, const char *value,
+			  void *perf_config_set)
 {
-	struct buildid_dir_config c;
-	c.dir = buildid_dir;
-	perf_config(buildid_dir_command_config, &c);
+	int ret = -1;
+	char *ptr, *key;
+	char *section_name, *name;
+	struct perf_config_section *section = NULL;
+	struct perf_config_item *item = NULL;
+	struct perf_config_set *set = perf_config_set;
+	struct list_head *sections = &set->sections;
+
+	key = ptr = strdup(var);
+	if (!key) {
+		pr_debug("%s: strdup failed\n", __func__);
+		return -1;
+	}
+
+	section_name = strsep(&ptr, ".");
+	name = ptr;
+	if (name == NULL || value == NULL)
+		goto out_free;
+
+	section = find_section(sections, section_name);
+	if (!section) {
+		section = add_section(sections, section_name);
+		if (!section)
+			goto out_free;
+	}
+
+	item = find_config_item(name, section);
+	if (!item) {
+		item = add_config_item(section, name);
+		if (!item)
+			goto out_free;
+	}
+
+	ret = set_value(item, value);
+	return ret;
+
+out_free:
+	free(key);
+	perf_config_set__delete(set);
+	return -1;
+}
+
+struct perf_config_set *perf_config_set__new(void)
+{
+	struct perf_config_set *set = zalloc(sizeof(*set));
+
+	if (set) {
+		INIT_LIST_HEAD(&set->sections);
+		perf_config(collect_config, set);
+	}
+
+	return set;
+}
+
+static void perf_config_item__delete(struct perf_config_item *item)
+{
+	zfree(&item->name);
+	zfree(&item->value);
+	free(item);
+}
+
+static void perf_config_section__purge(struct perf_config_section *section)
+{
+	struct perf_config_item *item, *tmp;
+
+	list_for_each_entry_safe(item, tmp, &section->items, node) {
+		list_del_init(&item->node);
+		perf_config_item__delete(item);
+	}
+}
+
+static void perf_config_section__delete(struct perf_config_section *section)
+{
+	perf_config_section__purge(section);
+	zfree(&section->name);
+	free(section);
+}
+
+static void perf_config_set__purge(struct perf_config_set *set)
+{
+	struct perf_config_section *section, *tmp;
+
+	list_for_each_entry_safe(section, tmp, &set->sections, node) {
+		list_del_init(&section->node);
+		perf_config_section__delete(section);
+	}
+}
+
+void perf_config_set__delete(struct perf_config_set *set)
+{
+	perf_config_set__purge(set);
+	free(set);
+}
+
+/*
+ * Call this to report error for your variable that should not
+ * get a boolean value (i.e. "[my] var" means "true").
+ */
+int config_error_nonbool(const char *var)
+{
+	return error("Missing value for '%s'", var);
 }
 
 void set_buildid_dir(const char *dir)
@@ -548,16 +711,13 @@ void set_buildid_dir(const char *dir)
 	if (dir)
 		scnprintf(buildid_dir, MAXPATHLEN-1, "%s", dir);
 
-	/* try config file */
-	if (buildid_dir[0] == '\0')
-		check_buildid_dir_config();
-
 	/* default to $HOME/.debug */
 	if (buildid_dir[0] == '\0') {
-		char *v = getenv("HOME");
-		if (v) {
+		char *home = getenv("HOME");
+
+		if (home) {
 			snprintf(buildid_dir, MAXPATHLEN-1, "%s/%s",
-				 v, DEBUG_CACHE_DIR);
+				 home, DEBUG_CACHE_DIR);
 		} else {
 			strncpy(buildid_dir, DEBUG_CACHE_DIR, MAXPATHLEN-1);
 		}
diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h
new file mode 100644
index 000000000000..22ec626ac718
--- /dev/null
+++ b/tools/perf/util/config.h
@@ -0,0 +1,26 @@
+#ifndef __PERF_CONFIG_H
+#define __PERF_CONFIG_H
+
+#include <stdbool.h>
+#include <linux/list.h>
+
+struct perf_config_item {
+	char *name;
+	char *value;
+	struct list_head node;
+};
+
+struct perf_config_section {
+	char *name;
+	struct list_head items;
+	struct list_head node;
+};
+
+struct perf_config_set {
+	struct list_head sections;
+};
+
+struct perf_config_set *perf_config_set__new(void);
+void perf_config_set__delete(struct perf_config_set *set);
+
+#endif /* __PERF_CONFIG_H */
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 9bcf2bed3a6d..02d801670f30 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -587,3 +587,15 @@ int cpu__setup_cpunode_map(void)
 	closedir(dir1);
 	return 0;
 }
+
+bool cpu_map__has(struct cpu_map *cpus, int cpu)
+{
+	int i;
+
+	for (i = 0; i < cpus->nr; ++i) {
+		if (cpus->map[i] == cpu)
+			return true;
+	}
+
+	return false;
+}
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 81a2562aaa2b..1a0a35073ce1 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -66,4 +66,6 @@ int cpu__get_node(int cpu);
 int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
 		       int (*f)(struct cpu_map *map, int cpu, void *data),
 		       void *data);
+
+bool cpu_map__has(struct cpu_map *cpus, int cpu);
 #endif /* __PERF_CPUMAP_H */
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index 1921942fc2e0..be83516155ee 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -136,3 +136,44 @@ ssize_t perf_data_file__write(struct perf_data_file *file,
 {
 	return writen(file->fd, buf, size);
 }
+
+int perf_data_file__switch(struct perf_data_file *file,
+			   const char *postfix,
+			   size_t pos, bool at_exit)
+{
+	char *new_filepath;
+	int ret;
+
+	if (check_pipe(file))
+		return -EINVAL;
+	if (perf_data_file__is_read(file))
+		return -EINVAL;
+
+	if (asprintf(&new_filepath, "%s.%s", file->path, postfix) < 0)
+		return -ENOMEM;
+
+	/*
+	 * Only fire a warning, don't return error, continue fill
+	 * original file.
+	 */
+	if (rename(file->path, new_filepath))
+		pr_warning("Failed to rename %s to %s\n", file->path, new_filepath);
+
+	if (!at_exit) {
+		close(file->fd);
+		ret = perf_data_file__open(file);
+		if (ret < 0)
+			goto out;
+
+		if (lseek(file->fd, pos, SEEK_SET) == (off_t)-1) {
+			ret = -errno;
+			pr_debug("Failed to lseek to %zu: %s",
+				 pos, strerror(errno));
+			goto out;
+		}
+	}
+	ret = file->fd;
+out:
+	free(new_filepath);
+	return ret;
+}
diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h
index 2b15d0c95c7f..ae510ce16cb1 100644
--- a/tools/perf/util/data.h
+++ b/tools/perf/util/data.h
@@ -46,5 +46,14 @@ int perf_data_file__open(struct perf_data_file *file);
 void perf_data_file__close(struct perf_data_file *file);
 ssize_t perf_data_file__write(struct perf_data_file *file,
 			      void *buf, size_t size);
-
+/*
+ * If at_exit is set, only rename current perf.data to
+ * perf.data.<postfix>, continue write on original file.
+ * Set at_exit when flushing the last output.
+ *
+ * Return value is fd of new output.
+ */
+int perf_data_file__switch(struct perf_data_file *file,
+			   const char *postfix,
+			   size_t pos, bool at_exit);
 #endif /* __PERF_DATA_H */
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index 049438d51b9a..8d96c80cc67e 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -23,6 +23,8 @@
 #include "event.h"
 #include "util.h"
 #include "thread-stack.h"
+#include "callchain.h"
+#include "call-path.h"
 #include "db-export.h"
 
 struct deferred_export {
@@ -258,8 +260,7 @@ static int db_ids_from_al(struct db_export *dbe, struct addr_location *al,
 		if (!al->sym) {
 			al->sym = symbol__new(al->addr, 0, 0, "unknown");
 			if (al->sym)
-				symbols__insert(&dso->symbols[al->map->type],
-						al->sym);
+				dso__insert_symbol(dso, al->map->type, al->sym);
 		}
 
 		if (al->sym) {
@@ -276,6 +277,80 @@ static int db_ids_from_al(struct db_export *dbe, struct addr_location *al,
 	return 0;
 }
 
+static struct call_path *call_path_from_sample(struct db_export *dbe,
+					       struct machine *machine,
+					       struct thread *thread,
+					       struct perf_sample *sample,
+					       struct perf_evsel *evsel)
+{
+	u64 kernel_start = machine__kernel_start(machine);
+	struct call_path *current = &dbe->cpr->call_path;
+	enum chain_order saved_order = callchain_param.order;
+	int err;
+
+	if (!symbol_conf.use_callchain || !sample->callchain)
+		return NULL;
+
+	/*
+	 * Since the call path tree must be built starting with the root, we
+	 * must use ORDER_CALL for call chain resolution, in order to process
+	 * the callchain starting with the root node and ending with the leaf.
+	 */
+	callchain_param.order = ORDER_CALLER;
+	err = thread__resolve_callchain(thread, &callchain_cursor, evsel,
+					sample, NULL, NULL,
+					sysctl_perf_event_max_stack);
+	if (err) {
+		callchain_param.order = saved_order;
+		return NULL;
+	}
+	callchain_cursor_commit(&callchain_cursor);
+
+	while (1) {
+		struct callchain_cursor_node *node;
+		struct addr_location al;
+		u64 dso_db_id = 0, sym_db_id = 0, offset = 0;
+
+		memset(&al, 0, sizeof(al));
+
+		node = callchain_cursor_current(&callchain_cursor);
+		if (!node)
+			break;
+		/*
+		 * Handle export of symbol and dso for this node by
+		 * constructing an addr_location struct and then passing it to
+		 * db_ids_from_al() to perform the export.
+		 */
+		al.sym = node->sym;
+		al.map = node->map;
+		al.machine = machine;
+		al.addr = node->ip;
+
+		if (al.map && !al.sym)
+			al.sym = dso__find_symbol(al.map->dso, MAP__FUNCTION,
+						  al.addr);
+
+		db_ids_from_al(dbe, &al, &dso_db_id, &sym_db_id, &offset);
+
+		/* add node to the call path tree if it doesn't exist */
+		current = call_path__findnew(dbe->cpr, current,
+					     al.sym, node->ip,
+					     kernel_start);
+
+		callchain_cursor_advance(&callchain_cursor);
+	}
+
+	/* Reset the callchain order to its prior value. */
+	callchain_param.order = saved_order;
+
+	if (current == &dbe->cpr->call_path) {
+		/* Bail because the callchain was empty. */
+		return NULL;
+	}
+
+	return current;
+}
+
 int db_export__branch_type(struct db_export *dbe, u32 branch_type,
 			   const char *name)
 {
@@ -329,6 +404,16 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
 	if (err)
 		goto out_put;
 
+	if (dbe->cpr) {
+		struct call_path *cp = call_path_from_sample(dbe, al->machine,
+							     thread, sample,
+							     evsel);
+		if (cp) {
+			db_export__call_path(dbe, cp);
+			es.call_path_id = cp->db_id;
+		}
+	}
+
 	if ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
 	    sample_addr_correlates_sym(&evsel->attr)) {
 		struct addr_location addr_al;
diff --git a/tools/perf/util/db-export.h b/tools/perf/util/db-export.h
index 25e22fd76aca..67bc6b8ad2d6 100644
--- a/tools/perf/util/db-export.h
+++ b/tools/perf/util/db-export.h
@@ -27,6 +27,7 @@ struct dso;
 struct perf_sample;
 struct addr_location;
 struct call_return_processor;
+struct call_path_root;
 struct call_path;
 struct call_return;
 
@@ -43,6 +44,7 @@ struct export_sample {
 	u64			addr_dso_db_id;
 	u64			addr_sym_db_id;
 	u64			addr_offset; /* addr offset from symbol start */
+	u64			call_path_id;
 };
 
 struct db_export {
@@ -64,6 +66,7 @@ struct db_export {
 	int (*export_call_return)(struct db_export *dbe,
 				  struct call_return *cr);
 	struct call_return_processor *crp;
+	struct call_path_root *cpr;
 	u64 evsel_last_db_id;
 	u64 machine_last_db_id;
 	u64 thread_last_db_id;
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 8e6395439ca0..3357479082ca 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -38,7 +38,7 @@ int dso__read_binary_type_filename(const struct dso *dso,
 				   enum dso_binary_type type,
 				   char *root_dir, char *filename, size_t size)
 {
-	char build_id_hex[BUILD_ID_SIZE * 2 + 1];
+	char build_id_hex[SBUILD_ID_SIZE];
 	int ret = 0;
 	size_t len;
 
@@ -1301,7 +1301,7 @@ size_t __dsos__fprintf(struct list_head *head, FILE *fp)
 
 size_t dso__fprintf_buildid(struct dso *dso, FILE *fp)
 {
-	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+	char sbuild_id[SBUILD_ID_SIZE];
 
 	build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
 	return fprintf(fp, "%s", sbuild_id);
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index aea189b41cc8..a347b19c961a 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -915,8 +915,7 @@ int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf)
 		tmp = "*";
 	else if (tag == DW_TAG_subroutine_type) {
 		/* Function pointer */
-		strbuf_add(buf, "(function_type)", 15);
-		return 0;
+		return strbuf_add(buf, "(function_type)", 15);
 	} else {
 		if (!dwarf_diename(&type))
 			return -ENOENT;
@@ -927,14 +926,10 @@ int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf)
 		else if (tag == DW_TAG_enumeration_type)
 			tmp = "enum ";
 		/* Write a base name */
-		strbuf_addf(buf, "%s%s", tmp, dwarf_diename(&type));
-		return 0;
+		return strbuf_addf(buf, "%s%s", tmp, dwarf_diename(&type));
 	}
 	ret = die_get_typename(&type, buf);
-	if (ret == 0)
-		strbuf_addstr(buf, tmp);
-
-	return ret;
+	return ret ? ret : strbuf_addstr(buf, tmp);
 }
 
 /**
@@ -951,12 +946,10 @@ int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf)
 	ret = die_get_typename(vr_die, buf);
 	if (ret < 0) {
 		pr_debug("Failed to get type, make it unknown.\n");
-		strbuf_add(buf, " (unknown_type)", 14);
+		ret = strbuf_add(buf, " (unknown_type)", 14);
 	}
 
-	strbuf_addf(buf, "\t%s", dwarf_diename(vr_die));
-
-	return 0;
+	return ret < 0 ? ret : strbuf_addf(buf, "\t%s", dwarf_diename(vr_die));
 }
 
 #ifdef HAVE_DWARF_GETLOCATIONS
@@ -999,22 +992,24 @@ static int die_get_var_innermost_scope(Dwarf_Die *sp_die, Dwarf_Die *vr_die,
 	}
 
 	while ((offset = dwarf_ranges(&scopes[1], offset, &base,
-				&start, &end)) > 0) {
+					&start, &end)) > 0) {
 		start -= entry;
 		end -= entry;
 
 		if (first) {
-			strbuf_addf(buf, "@<%s+[%" PRIu64 "-%" PRIu64,
-				name, start, end);
+			ret = strbuf_addf(buf, "@<%s+[%" PRIu64 "-%" PRIu64,
+					  name, start, end);
 			first = false;
 		} else {
-			strbuf_addf(buf, ",%" PRIu64 "-%" PRIu64,
-				start, end);
+			ret = strbuf_addf(buf, ",%" PRIu64 "-%" PRIu64,
+					  start, end);
 		}
+		if (ret < 0)
+			goto out;
 	}
 
 	if (!first)
-		strbuf_add(buf, "]>", 2);
+		ret = strbuf_add(buf, "]>", 2);
 
 out:
 	free(scopes);
@@ -1054,31 +1049,32 @@ int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf)
 	if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL)
 		return -EINVAL;
 
-	while ((offset = dwarf_getlocations(
-				&attr, offset, &base,
-				&start, &end, &op, &nops)) > 0) {
+	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;
+			goto out;
 		}
 
 		/* Location Lists */
 		start -= entry;
 		end -= entry;
 		if (first) {
-			strbuf_addf(buf, "@<%s+[%" PRIu64 "-%" PRIu64,
-				name, start, end);
+			ret = strbuf_addf(buf, "@<%s+[%" PRIu64 "-%" PRIu64,
+					  name, start, end);
 			first = false;
 		} else {
-			strbuf_addf(buf, ",%" PRIu64 "-%" PRIu64,
-				start, end);
+			ret = strbuf_addf(buf, ",%" PRIu64 "-%" PRIu64,
+					  start, end);
 		}
+		if (ret < 0)
+			goto out;
 	}
 
 	if (!first)
-		strbuf_add(buf, "]>", 2);
-
+		ret = strbuf_add(buf, "]>", 2);
+out:
 	return ret;
 }
 #else
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index edcf4ed4e99c..f6fcc6832949 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -45,6 +45,7 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_STAT]			= "STAT",
 	[PERF_RECORD_STAT_ROUND]		= "STAT_ROUND",
 	[PERF_RECORD_EVENT_UPDATE]		= "EVENT_UPDATE",
+	[PERF_RECORD_TIME_CONV]			= "TIME_CONV",
 };
 
 const char *perf_event__name(unsigned int id)
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 6bb1c928350d..8d363d5e65a2 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -233,6 +233,7 @@ enum perf_user_event_type { /* above any possible kernel type */
 	PERF_RECORD_STAT			= 76,
 	PERF_RECORD_STAT_ROUND			= 77,
 	PERF_RECORD_EVENT_UPDATE		= 78,
+	PERF_RECORD_TIME_CONV			= 79,
 	PERF_RECORD_HEADER_MAX
 };
 
@@ -469,6 +470,13 @@ struct stat_round_event {
 	u64				time;
 };
 
+struct time_conv_event {
+	struct perf_event_header header;
+	u64 time_shift;
+	u64 time_mult;
+	u64 time_zero;
+};
+
 union perf_event {
 	struct perf_event_header	header;
 	struct mmap_event		mmap;
@@ -497,6 +505,7 @@ union perf_event {
 	struct stat_config_event	stat_config;
 	struct stat_event		stat;
 	struct stat_round_event		stat_round;
+	struct time_conv_event		time_conv;
 };
 
 void perf_event__print_totals(void);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 86a03836a83f..c4bfe11479a0 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -679,53 +679,52 @@ static struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
 	return NULL;
 }
 
-union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
+/* When check_messup is true, 'end' must points to a good entry */
+static union perf_event *
+perf_mmap__read(struct perf_mmap *md, bool check_messup, u64 start,
+		u64 end, u64 *prev)
 {
-	struct perf_mmap *md = &evlist->mmap[idx];
-	u64 head;
-	u64 old = md->prev;
 	unsigned char *data = md->base + page_size;
 	union perf_event *event = NULL;
+	int diff = end - start;
 
-	/*
-	 * 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 (check_messup) {
 		/*
 		 * If we're further behind than half the buffer, there's a chance
 		 * the writer will bite our tail and mess up the samples under us.
 		 *
-		 * If we somehow ended up ahead of the head, we got messed up.
+		 * If we somehow ended up ahead of the 'end', we got messed up.
 		 *
-		 * In either case, truncate and restart at head.
+		 * In either case, truncate and restart at 'end'.
 		 */
-		int diff = head - old;
 		if (diff > md->mask / 2 || diff < 0) {
 			fprintf(stderr, "WARNING: failed to keep up with mmap data.\n");
 
 			/*
-			 * head points to a known good entry, start there.
+			 * 'end' points to a known good entry, start there.
 			 */
-			old = head;
+			start = end;
+			diff = 0;
 		}
 	}
 
-	if (old != head) {
+	if (diff >= (int)sizeof(event->header)) {
 		size_t size;
 
-		event = (union perf_event *)&data[old & md->mask];
+		event = (union perf_event *)&data[start & md->mask];
 		size = event->header.size;
 
+		if (size < sizeof(event->header) || diff < (int)size) {
+			event = NULL;
+			goto broken_event;
+		}
+
 		/*
 		 * Event straddles the mmap boundary -- header should always
 		 * be inside due to u64 alignment of output.
 		 */
-		if ((old & md->mask) + size != ((old + size) & md->mask)) {
-			unsigned int offset = old;
+		if ((start & md->mask) + size != ((start + size) & md->mask)) {
+			unsigned int offset = start;
 			unsigned int len = min(sizeof(*event), size), cpy;
 			void *dst = md->event_copy;
 
@@ -740,14 +739,83 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 			event = (union perf_event *) md->event_copy;
 		}
 
-		old += size;
+		start += size;
 	}
 
-	md->prev = old;
+broken_event:
+	if (prev)
+		*prev = start;
 
 	return event;
 }
 
+union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
+{
+	struct perf_mmap *md = &evlist->mmap[idx];
+	u64 head;
+	u64 old = md->prev;
+
+	/*
+	 * Check if event was unmapped due to a POLLHUP/POLLERR.
+	 */
+	if (!atomic_read(&md->refcnt))
+		return NULL;
+
+	head = perf_mmap__read_head(md);
+
+	return perf_mmap__read(md, evlist->overwrite, old, head, &md->prev);
+}
+
+union perf_event *
+perf_evlist__mmap_read_backward(struct perf_evlist *evlist, int idx)
+{
+	struct perf_mmap *md = &evlist->mmap[idx];
+	u64 head, end;
+	u64 start = md->prev;
+
+	/*
+	 * Check if event was unmapped due to a POLLHUP/POLLERR.
+	 */
+	if (!atomic_read(&md->refcnt))
+		return NULL;
+
+	head = perf_mmap__read_head(md);
+	if (!head)
+		return NULL;
+
+	/*
+	 * 'head' pointer starts from 0. Kernel minus sizeof(record) form
+	 * it each time when kernel writes to it, so in fact 'head' is
+	 * negative. 'end' pointer is made manually by adding the size of
+	 * the ring buffer to 'head' pointer, means the validate data can
+	 * read is the whole ring buffer. If 'end' is positive, the ring
+	 * buffer has not fully filled, so we must adjust 'end' to 0.
+	 *
+	 * However, since both 'head' and 'end' is unsigned, we can't
+	 * simply compare 'end' against 0. Here we compare '-head' and
+	 * the size of the ring buffer, where -head is the number of bytes
+	 * kernel write to the ring buffer.
+	 */
+	if (-head < (u64)(md->mask + 1))
+		end = 0;
+	else
+		end = head + md->mask + 1;
+
+	return perf_mmap__read(md, false, start, end, &md->prev);
+}
+
+void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx)
+{
+	struct perf_mmap *md = &evlist->mmap[idx];
+	u64 head;
+
+	if (!atomic_read(&md->refcnt))
+		return;
+
+	head = perf_mmap__read_head(md);
+	md->prev = head;
+}
+
 static bool perf_mmap__empty(struct perf_mmap *md)
 {
 	return perf_mmap__read_head(md) == md->prev && !md->auxtrace_mmap.base;
@@ -986,26 +1054,34 @@ out_unmap:
 	return -1;
 }
 
-static size_t perf_evlist__mmap_size(unsigned long pages)
+unsigned long perf_event_mlock_kb_in_pages(void)
 {
-	if (pages == UINT_MAX) {
-		int max;
+	unsigned long pages;
+	int max;
 
-		if (sysctl__read_int("kernel/perf_event_mlock_kb", &max) < 0) {
-			/*
-			 * Pick a once upon a time good value, i.e. things look
-			 * strange since we can't read a sysctl value, but lets not
-			 * die yet...
-			 */
-			max = 512;
-		} else {
-			max -= (page_size / 1024);
-		}
+	if (sysctl__read_int("kernel/perf_event_mlock_kb", &max) < 0) {
+		/*
+		 * Pick a once upon a time good value, i.e. things look
+		 * strange since we can't read a sysctl value, but lets not
+		 * die yet...
+		 */
+		max = 512;
+	} else {
+		max -= (page_size / 1024);
+	}
 
-		pages = (max * 1024) / page_size;
-		if (!is_power_of_2(pages))
-			pages = rounddown_pow_of_two(pages);
-	} else if (!is_power_of_2(pages))
+	pages = (max * 1024) / page_size;
+	if (!is_power_of_2(pages))
+		pages = rounddown_pow_of_two(pages);
+
+	return pages;
+}
+
+static size_t perf_evlist__mmap_size(unsigned long pages)
+{
+	if (pages == UINT_MAX)
+		pages = perf_event_mlock_kb_in_pages();
+	else if (!is_power_of_2(pages))
 		return 0;
 
 	return (pages + 1) * page_size;
@@ -1192,6 +1268,24 @@ void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus,
 	perf_evlist__propagate_maps(evlist);
 }
 
+void __perf_evlist__set_sample_bit(struct perf_evlist *evlist,
+				   enum perf_event_sample_format bit)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel)
+		__perf_evsel__set_sample_bit(evsel, bit);
+}
+
+void __perf_evlist__reset_sample_bit(struct perf_evlist *evlist,
+				     enum perf_event_sample_format bit)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel)
+		__perf_evsel__reset_sample_bit(evsel, bit);
+}
+
 int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel)
 {
 	struct perf_evsel *evsel;
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index a0d15221db6e..85d1b59802e8 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -87,6 +87,17 @@ int perf_evlist__add_dummy(struct perf_evlist *evlist);
 int perf_evlist__add_newtp(struct perf_evlist *evlist,
 			   const char *sys, const char *name, void *handler);
 
+void __perf_evlist__set_sample_bit(struct perf_evlist *evlist,
+				   enum perf_event_sample_format bit);
+void __perf_evlist__reset_sample_bit(struct perf_evlist *evlist,
+				     enum perf_event_sample_format bit);
+
+#define perf_evlist__set_sample_bit(evlist, bit) \
+	__perf_evlist__set_sample_bit(evlist, PERF_SAMPLE_##bit)
+
+#define perf_evlist__reset_sample_bit(evlist, bit) \
+	__perf_evlist__reset_sample_bit(evlist, PERF_SAMPLE_##bit)
+
 int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter);
 int perf_evlist__set_filter_pid(struct perf_evlist *evlist, pid_t pid);
 int perf_evlist__set_filter_pids(struct perf_evlist *evlist, size_t npids, pid_t *pids);
@@ -118,16 +129,23 @@ struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id);
 
 union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx);
 
+union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist,
+						  int idx);
+void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx);
+
 void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx);
 
 int perf_evlist__open(struct perf_evlist *evlist);
 void perf_evlist__close(struct perf_evlist *evlist);
 
+struct callchain_param;
+
 void perf_evlist__set_id_pos(struct perf_evlist *evlist);
 bool perf_can_sample_identifier(void);
 bool perf_can_record_switch_events(void);
 bool perf_can_record_cpu_wide(void);
-void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts);
+void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts,
+			 struct callchain_param *callchain);
 int record_opts__config(struct record_opts *opts);
 
 int perf_evlist__prepare_workload(struct perf_evlist *evlist,
@@ -144,6 +162,8 @@ int perf_evlist__parse_mmap_pages(const struct option *opt,
 				  const char *str,
 				  int unset);
 
+unsigned long perf_event_mlock_kb_in_pages(void);
+
 int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 			 bool overwrite, unsigned int auxtrace_pages,
 			 bool auxtrace_overwrite);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 645dc1828836..964c7c3602c0 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -226,7 +226,8 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 		perf_evsel__init(evsel, attr, idx);
 
 	if (perf_evsel__is_bpf_output(evsel)) {
-		evsel->attr.sample_type |= PERF_SAMPLE_RAW;
+		evsel->attr.sample_type |= (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME |
+					    PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD),
 		evsel->attr.sample_period = 1;
 	}
 
@@ -561,10 +562,9 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size)
 	return ret;
 }
 
-static void
-perf_evsel__config_callgraph(struct perf_evsel *evsel,
-			     struct record_opts *opts,
-			     struct callchain_param *param)
+void perf_evsel__config_callchain(struct perf_evsel *evsel,
+				  struct record_opts *opts,
+				  struct callchain_param *param)
 {
 	bool function = perf_evsel__is_function_event(evsel);
 	struct perf_event_attr *attr = &evsel->attr;
@@ -704,7 +704,7 @@ static void apply_config_terms(struct perf_evsel *evsel,
 
 		/* set perf-event callgraph */
 		if (param.enabled)
-			perf_evsel__config_callgraph(evsel, opts, &param);
+			perf_evsel__config_callchain(evsel, opts, &param);
 	}
 }
 
@@ -736,7 +736,8 @@ static void apply_config_terms(struct perf_evsel *evsel,
  *     enable/disable events specifically, as there's no
  *     initial traced exec call.
  */
-void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
+void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
+			struct callchain_param *callchain)
 {
 	struct perf_evsel *leader = evsel->leader;
 	struct perf_event_attr *attr = &evsel->attr;
@@ -811,8 +812,8 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	if (perf_evsel__is_function_event(evsel))
 		evsel->attr.exclude_callchain_user = 1;
 
-	if (callchain_param.enabled && !evsel->no_aux_samples)
-		perf_evsel__config_callgraph(evsel, opts, &callchain_param);
+	if (callchain && callchain->enabled && !evsel->no_aux_samples)
+		perf_evsel__config_callchain(evsel, opts, callchain);
 
 	if (opts->sample_intr_regs) {
 		attr->sample_regs_intr = opts->sample_intr_regs;
@@ -1230,6 +1231,21 @@ static void __p_sample_type(char *buf, size_t size, u64 value)
 	__p_bits(buf, size, value, bits);
 }
 
+static void __p_branch_sample_type(char *buf, size_t size, u64 value)
+{
+#define bit_name(n) { PERF_SAMPLE_BRANCH_##n, #n }
+	struct bit_names bits[] = {
+		bit_name(USER), bit_name(KERNEL), bit_name(HV), bit_name(ANY),
+		bit_name(ANY_CALL), bit_name(ANY_RETURN), bit_name(IND_CALL),
+		bit_name(ABORT_TX), bit_name(IN_TX), bit_name(NO_TX),
+		bit_name(COND), bit_name(CALL_STACK), bit_name(IND_JUMP),
+		bit_name(CALL), bit_name(NO_FLAGS), bit_name(NO_CYCLES),
+		{ .name = NULL, }
+	};
+#undef bit_name
+	__p_bits(buf, size, value, bits);
+}
+
 static void __p_read_format(char *buf, size_t size, u64 value)
 {
 #define bit_name(n) { PERF_FORMAT_##n, #n }
@@ -1248,6 +1264,7 @@ static void __p_read_format(char *buf, size_t size, u64 value)
 #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)
+#define p_branch_sample_type(val) __p_branch_sample_type(buf, BUF_SIZE, val)
 #define p_read_format(val)	__p_read_format(buf, BUF_SIZE, val)
 
 #define PRINT_ATTRn(_n, _f, _p)				\
@@ -1299,12 +1316,13 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 	PRINT_ATTRf(comm_exec, p_unsigned);
 	PRINT_ATTRf(use_clockid, p_unsigned);
 	PRINT_ATTRf(context_switch, p_unsigned);
+	PRINT_ATTRf(write_backward, p_unsigned);
 
 	PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned);
 	PRINT_ATTRf(bp_type, p_unsigned);
 	PRINT_ATTRn("{ bp_addr, config1 }", bp_addr, p_hex);
 	PRINT_ATTRn("{ bp_len, config2 }", bp_len, p_hex);
-	PRINT_ATTRf(branch_sample_type, p_unsigned);
+	PRINT_ATTRf(branch_sample_type, p_branch_sample_type);
 	PRINT_ATTRf(sample_regs_user, p_hex);
 	PRINT_ATTRf(sample_stack_user, p_unsigned);
 	PRINT_ATTRf(clockid, p_signed);
@@ -2253,95 +2271,6 @@ u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
 	return 0;
 }
 
-static int comma_fprintf(FILE *fp, bool *first, const char *fmt, ...)
-{
-	va_list args;
-	int ret = 0;
-
-	if (!*first) {
-		ret += fprintf(fp, ",");
-	} else {
-		ret += fprintf(fp, ":");
-		*first = false;
-	}
-
-	va_start(args, fmt);
-	ret += vfprintf(fp, fmt, args);
-	va_end(args);
-	return ret;
-}
-
-static int __print_attr__fprintf(FILE *fp, const char *name, const char *val, void *priv)
-{
-	return comma_fprintf(fp, (bool *)priv, " %s: %s", name, val);
-}
-
-int perf_evsel__fprintf(struct perf_evsel *evsel,
-			struct perf_attr_details *details, FILE *fp)
-{
-	bool first = true;
-	int printed = 0;
-
-	if (details->event_group) {
-		struct perf_evsel *pos;
-
-		if (!perf_evsel__is_group_leader(evsel))
-			return 0;
-
-		if (evsel->nr_members > 1)
-			printed += fprintf(fp, "%s{", evsel->group_name ?: "");
-
-		printed += fprintf(fp, "%s", perf_evsel__name(evsel));
-		for_each_group_member(pos, evsel)
-			printed += fprintf(fp, ",%s", perf_evsel__name(pos));
-
-		if (evsel->nr_members > 1)
-			printed += fprintf(fp, "}");
-		goto out;
-	}
-
-	printed += fprintf(fp, "%s", perf_evsel__name(evsel));
-
-	if (details->verbose) {
-		printed += perf_event_attr__fprintf(fp, &evsel->attr,
-						    __print_attr__fprintf, &first);
-	} else if (details->freq) {
-		const char *term = "sample_freq";
-
-		if (!evsel->attr.freq)
-			term = "sample_period";
-
-		printed += comma_fprintf(fp, &first, " %s=%" PRIu64,
-					 term, (u64)evsel->attr.sample_freq);
-	}
-
-	if (details->trace_fields) {
-		struct format_field *field;
-
-		if (evsel->attr.type != PERF_TYPE_TRACEPOINT) {
-			printed += comma_fprintf(fp, &first, " (not a tracepoint)");
-			goto out;
-		}
-
-		field = evsel->tp_format->format.fields;
-		if (field == NULL) {
-			printed += comma_fprintf(fp, &first, " (no trace field)");
-			goto out;
-		}
-
-		printed += comma_fprintf(fp, &first, " trace_fields: %s", field->name);
-
-		field = field->next;
-		while (field) {
-			printed += comma_fprintf(fp, &first, "%s", field->name);
-			field = field->next;
-		}
-	}
-out:
-	fputc('\n', fp);
-	return ++printed;
-}
-
 bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
 			  char *msg, size_t msgsize)
 {
@@ -2416,10 +2345,18 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 			 "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 ENOMEM:
+		if ((evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) != 0 &&
+		    access("/proc/sys/kernel/perf_event_max_stack", F_OK) == 0)
+			return scnprintf(msg, size,
+					 "Not enough memory to setup event with callchain.\n"
+					 "Hint: Try tweaking /proc/sys/kernel/perf_event_max_stack\n"
+					 "Hint: Current value: %d", sysctl_perf_event_max_stack);
+		break;
 	case ENODEV:
 		if (target->cpu_list)
 			return scnprintf(msg, size, "%s",
-	 "No such device - did you specify an out-of-range profile CPU?\n");
+	 "No such device - did you specify an out-of-range profile CPU?");
 		break;
 	case EOPNOTSUPP:
 		if (evsel->attr.precise_ip)
@@ -2451,7 +2388,7 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 	return scnprintf(msg, size,
 	"The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n"
 	"/bin/dmesg may provide additional information.\n"
-	"No CONFIG_PERF_EVENTS=y kernel support configured?\n",
+	"No CONFIG_PERF_EVENTS=y kernel support configured?",
 			 err, strerror_r(err, sbuf, sizeof(sbuf)),
 			 perf_evsel__name(evsel));
 }
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 501ea6e565f1..8a644fef452c 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -178,8 +178,14 @@ void perf_evsel__init(struct perf_evsel *evsel,
 void perf_evsel__exit(struct perf_evsel *evsel);
 void perf_evsel__delete(struct perf_evsel *evsel);
 
+struct callchain_param;
+
 void perf_evsel__config(struct perf_evsel *evsel,
-			struct record_opts *opts);
+			struct record_opts *opts,
+			struct callchain_param *callchain);
+void perf_evsel__config_callchain(struct perf_evsel *evsel,
+				  struct record_opts *opts,
+				  struct callchain_param *callchain);
 
 int __perf_evsel__sample_size(u64 sample_type);
 void perf_evsel__calc_id_pos(struct perf_evsel *evsel);
@@ -381,6 +387,24 @@ struct perf_attr_details {
 int perf_evsel__fprintf(struct perf_evsel *evsel,
 			struct perf_attr_details *details, FILE *fp);
 
+#define EVSEL__PRINT_IP			(1<<0)
+#define EVSEL__PRINT_SYM		(1<<1)
+#define EVSEL__PRINT_DSO		(1<<2)
+#define EVSEL__PRINT_SYMOFFSET		(1<<3)
+#define EVSEL__PRINT_ONELINE		(1<<4)
+#define EVSEL__PRINT_SRCLINE		(1<<5)
+#define EVSEL__PRINT_UNKNOWN_AS_ADDR	(1<<6)
+
+struct callchain_cursor;
+
+int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment,
+			      unsigned int print_opts,
+			      struct callchain_cursor *cursor, FILE *fp);
+
+int sample__fprintf_sym(struct perf_sample *sample, struct addr_location *al,
+			int left_alignment, unsigned int print_opts,
+			struct callchain_cursor *cursor, FILE *fp);
+
 bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
 			  char *msg, size_t msgsize);
 int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
@@ -396,7 +420,7 @@ for ((_evsel) = list_entry((_leader)->node.next, struct perf_evsel, node); 	\
      (_evsel) && (_evsel)->leader == (_leader);					\
      (_evsel) = list_entry((_evsel)->node.next, struct perf_evsel, node))
 
-static inline bool has_branch_callstack(struct perf_evsel *evsel)
+static inline bool perf_evsel__has_branch_callstack(const struct perf_evsel *evsel)
 {
 	return evsel->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK;
 }
diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c
new file mode 100644
index 000000000000..3674e77ad640
--- /dev/null
+++ b/tools/perf/util/evsel_fprintf.c
@@ -0,0 +1,212 @@
+#include <stdio.h>
+#include <stdbool.h>
+#include <traceevent/event-parse.h>
+#include "evsel.h"
+#include "callchain.h"
+#include "map.h"
+#include "symbol.h"
+
+static int comma_fprintf(FILE *fp, bool *first, const char *fmt, ...)
+{
+	va_list args;
+	int ret = 0;
+
+	if (!*first) {
+		ret += fprintf(fp, ",");
+	} else {
+		ret += fprintf(fp, ":");
+		*first = false;
+	}
+
+	va_start(args, fmt);
+	ret += vfprintf(fp, fmt, args);
+	va_end(args);
+	return ret;
+}
+
+static int __print_attr__fprintf(FILE *fp, const char *name, const char *val, void *priv)
+{
+	return comma_fprintf(fp, (bool *)priv, " %s: %s", name, val);
+}
+
+int perf_evsel__fprintf(struct perf_evsel *evsel,
+			struct perf_attr_details *details, FILE *fp)
+{
+	bool first = true;
+	int printed = 0;
+
+	if (details->event_group) {
+		struct perf_evsel *pos;
+
+		if (!perf_evsel__is_group_leader(evsel))
+			return 0;
+
+		if (evsel->nr_members > 1)
+			printed += fprintf(fp, "%s{", evsel->group_name ?: "");
+
+		printed += fprintf(fp, "%s", perf_evsel__name(evsel));
+		for_each_group_member(pos, evsel)
+			printed += fprintf(fp, ",%s", perf_evsel__name(pos));
+
+		if (evsel->nr_members > 1)
+			printed += fprintf(fp, "}");
+		goto out;
+	}
+
+	printed += fprintf(fp, "%s", perf_evsel__name(evsel));
+
+	if (details->verbose) {
+		printed += perf_event_attr__fprintf(fp, &evsel->attr,
+						    __print_attr__fprintf, &first);
+	} else if (details->freq) {
+		const char *term = "sample_freq";
+
+		if (!evsel->attr.freq)
+			term = "sample_period";
+
+		printed += comma_fprintf(fp, &first, " %s=%" PRIu64,
+					 term, (u64)evsel->attr.sample_freq);
+	}
+
+	if (details->trace_fields) {
+		struct format_field *field;
+
+		if (evsel->attr.type != PERF_TYPE_TRACEPOINT) {
+			printed += comma_fprintf(fp, &first, " (not a tracepoint)");
+			goto out;
+		}
+
+		field = evsel->tp_format->format.fields;
+		if (field == NULL) {
+			printed += comma_fprintf(fp, &first, " (no trace field)");
+			goto out;
+		}
+
+		printed += comma_fprintf(fp, &first, " trace_fields: %s", field->name);
+
+		field = field->next;
+		while (field) {
+			printed += comma_fprintf(fp, &first, "%s", field->name);
+			field = field->next;
+		}
+	}
+out:
+	fputc('\n', fp);
+	return ++printed;
+}
+
+int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment,
+			      unsigned int print_opts, struct callchain_cursor *cursor,
+			      FILE *fp)
+{
+	int printed = 0;
+	struct callchain_cursor_node *node;
+	int print_ip = print_opts & EVSEL__PRINT_IP;
+	int print_sym = print_opts & EVSEL__PRINT_SYM;
+	int print_dso = print_opts & EVSEL__PRINT_DSO;
+	int print_symoffset = print_opts & EVSEL__PRINT_SYMOFFSET;
+	int print_oneline = print_opts & EVSEL__PRINT_ONELINE;
+	int print_srcline = print_opts & EVSEL__PRINT_SRCLINE;
+	int print_unknown_as_addr = print_opts & EVSEL__PRINT_UNKNOWN_AS_ADDR;
+	char s = print_oneline ? ' ' : '\t';
+
+	if (sample->callchain) {
+		struct addr_location node_al;
+
+		callchain_cursor_commit(cursor);
+
+		while (1) {
+			u64 addr = 0;
+
+			node = callchain_cursor_current(cursor);
+			if (!node)
+				break;
+
+			if (node->sym && node->sym->ignore)
+				goto next;
+
+			printed += fprintf(fp, "%-*.*s", left_alignment, left_alignment, " ");
+
+			if (print_ip)
+				printed += fprintf(fp, "%c%16" PRIx64, s, node->ip);
+
+			if (node->map)
+				addr = node->map->map_ip(node->map, node->ip);
+
+			if (print_sym) {
+				printed += fprintf(fp, " ");
+				node_al.addr = addr;
+				node_al.map  = node->map;
+
+				if (print_symoffset) {
+					printed += __symbol__fprintf_symname_offs(node->sym, &node_al,
+										  print_unknown_as_addr, fp);
+				} else {
+					printed += __symbol__fprintf_symname(node->sym, &node_al,
+									     print_unknown_as_addr, fp);
+				}
+			}
+
+			if (print_dso) {
+				printed += fprintf(fp, " (");
+				printed += map__fprintf_dsoname(node->map, fp);
+				printed += fprintf(fp, ")");
+			}
+
+			if (print_srcline)
+				printed += map__fprintf_srcline(node->map, addr, "\n  ", fp);
+
+			if (!print_oneline)
+				printed += fprintf(fp, "\n");
+next:
+			callchain_cursor_advance(cursor);
+		}
+	}
+
+	return printed;
+}
+
+int sample__fprintf_sym(struct perf_sample *sample, struct addr_location *al,
+			int left_alignment, unsigned int print_opts,
+			struct callchain_cursor *cursor, FILE *fp)
+{
+	int printed = 0;
+	int print_ip = print_opts & EVSEL__PRINT_IP;
+	int print_sym = print_opts & EVSEL__PRINT_SYM;
+	int print_dso = print_opts & EVSEL__PRINT_DSO;
+	int print_symoffset = print_opts & EVSEL__PRINT_SYMOFFSET;
+	int print_srcline = print_opts & EVSEL__PRINT_SRCLINE;
+	int print_unknown_as_addr = print_opts & EVSEL__PRINT_UNKNOWN_AS_ADDR;
+
+	if (cursor != NULL) {
+		printed += sample__fprintf_callchain(sample, left_alignment,
+						     print_opts, cursor, fp);
+	} else if (!(al->sym && al->sym->ignore)) {
+		printed += fprintf(fp, "%-*.*s", left_alignment, left_alignment, " ");
+
+		if (print_ip)
+			printed += fprintf(fp, "%16" PRIx64, sample->ip);
+
+		if (print_sym) {
+			printed += fprintf(fp, " ");
+			if (print_symoffset) {
+				printed += __symbol__fprintf_symname_offs(al->sym, al,
+									  print_unknown_as_addr, fp);
+			} else {
+				printed += __symbol__fprintf_symname(al->sym, al,
+								     print_unknown_as_addr, fp);
+			}
+		}
+
+		if (print_dso) {
+			printed += fprintf(fp, " (");
+			printed += map__fprintf_dsoname(al->map, fp);
+			printed += fprintf(fp, ")");
+		}
+
+		if (print_srcline)
+			printed += map__fprintf_srcline(al->map, al->addr, "\n  ", fp);
+	}
+
+	return printed;
+}
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 90680ec9f8b8..08852dde1378 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1474,7 +1474,7 @@ static int __event_process_build_id(struct build_id_event *bev,
 
 	dso = machine__findnew_dso(machine, filename);
 	if (dso != NULL) {
-		char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+		char sbuild_id[SBUILD_ID_SIZE];
 
 		dso__set_build_id(dso, &bev->build_id);
 
@@ -1819,7 +1819,8 @@ static int process_cpu_topology(struct perf_file_section *section,
 
 	ph->env.nr_sibling_cores = nr;
 	size += sizeof(u32);
-	strbuf_init(&sb, 128);
+	if (strbuf_init(&sb, 128) < 0)
+		goto free_cpu;
 
 	for (i = 0; i < nr; i++) {
 		str = do_read_string(fd, ph);
@@ -1827,7 +1828,8 @@ static int process_cpu_topology(struct perf_file_section *section,
 			goto error;
 
 		/* include a NULL character at the end */
-		strbuf_add(&sb, str, strlen(str) + 1);
+		if (strbuf_add(&sb, str, strlen(str) + 1) < 0)
+			goto error;
 		size += string_size(str);
 		free(str);
 	}
@@ -1849,7 +1851,8 @@ static int process_cpu_topology(struct perf_file_section *section,
 			goto error;
 
 		/* include a NULL character at the end */
-		strbuf_add(&sb, str, strlen(str) + 1);
+		if (strbuf_add(&sb, str, strlen(str) + 1) < 0)
+			goto error;
 		size += string_size(str);
 		free(str);
 	}
@@ -1912,13 +1915,14 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse
 	/* nr nodes */
 	ret = readn(fd, &nr, sizeof(nr));
 	if (ret != sizeof(nr))
-		goto error;
+		return -1;
 
 	if (ph->needs_swap)
 		nr = bswap_32(nr);
 
 	ph->env.nr_numa_nodes = nr;
-	strbuf_init(&sb, 256);
+	if (strbuf_init(&sb, 256) < 0)
+		return -1;
 
 	for (i = 0; i < nr; i++) {
 		/* node number */
@@ -1940,15 +1944,17 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse
 			mem_free = bswap_64(mem_free);
 		}
 
-		strbuf_addf(&sb, "%u:%"PRIu64":%"PRIu64":",
-			    node, mem_total, mem_free);
+		if (strbuf_addf(&sb, "%u:%"PRIu64":%"PRIu64":",
+				node, mem_total, mem_free) < 0)
+			goto error;
 
 		str = do_read_string(fd, ph);
 		if (!str)
 			goto error;
 
 		/* include a NULL character at the end */
-		strbuf_add(&sb, str, strlen(str) + 1);
+		if (strbuf_add(&sb, str, strlen(str) + 1) < 0)
+			goto error;
 		free(str);
 	}
 	ph->env.numa_nodes = strbuf_detach(&sb, NULL);
@@ -1982,7 +1988,8 @@ static int process_pmu_mappings(struct perf_file_section *section __maybe_unused
 	}
 
 	ph->env.nr_pmu_mappings = pmu_num;
-	strbuf_init(&sb, 128);
+	if (strbuf_init(&sb, 128) < 0)
+		return -1;
 
 	while (pmu_num) {
 		if (readn(fd, &type, sizeof(type)) != sizeof(type))
@@ -1994,9 +2001,11 @@ static int process_pmu_mappings(struct perf_file_section *section __maybe_unused
 		if (!name)
 			goto error;
 
-		strbuf_addf(&sb, "%u:%s", type, name);
+		if (strbuf_addf(&sb, "%u:%s", type, name) < 0)
+			goto error;
 		/* include a NULL character at the end */
-		strbuf_add(&sb, "", 1);
+		if (strbuf_add(&sb, "", 1) < 0)
+			goto error;
 
 		if (!strcmp(name, "msr"))
 			ph->env.msr_pmu_type = type;
diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c
index 43a98a4dc1e1..d62ccaeeadd6 100644
--- a/tools/perf/util/help-unknown-cmd.c
+++ b/tools/perf/util/help-unknown-cmd.c
@@ -27,16 +27,27 @@ static int levenshtein_compare(const void *p1, const void *p2)
 	return l1 != l2 ? l1 - l2 : strcmp(s1, s2);
 }
 
-static void add_cmd_list(struct cmdnames *cmds, struct cmdnames *old)
+static int add_cmd_list(struct cmdnames *cmds, struct cmdnames *old)
 {
-	unsigned int i;
-
-	ALLOC_GROW(cmds->names, cmds->cnt + old->cnt, cmds->alloc);
-
+	unsigned int i, nr = cmds->cnt + old->cnt;
+	void *tmp;
+
+	if (nr > cmds->alloc) {
+		/* Choose bigger one to alloc */
+		if (alloc_nr(cmds->alloc) < nr)
+			cmds->alloc = nr;
+		else
+			cmds->alloc = alloc_nr(cmds->alloc);
+		tmp = realloc(cmds->names, cmds->alloc * sizeof(*cmds->names));
+		if (!tmp)
+			return -1;
+		cmds->names = tmp;
+	}
 	for (i = 0; i < old->cnt; i++)
 		cmds->names[cmds->cnt++] = old->names[i];
 	zfree(&old->names);
 	old->cnt = 0;
+	return 0;
 }
 
 const char *help_unknown_cmd(const char *cmd)
@@ -52,8 +63,11 @@ const char *help_unknown_cmd(const char *cmd)
 
 	load_command_list("perf-", &main_cmds, &other_cmds);
 
-	add_cmd_list(&main_cmds, &aliases);
-	add_cmd_list(&main_cmds, &other_cmds);
+	if (add_cmd_list(&main_cmds, &aliases) < 0 ||
+	    add_cmd_list(&main_cmds, &other_cmds) < 0) {
+		fprintf(stderr, "ERROR: Failed to allocate command list for unknown command.\n");
+		goto end;
+	}
 	qsort(main_cmds.names, main_cmds.cnt,
 	      sizeof(main_cmds.names), cmdname_compare);
 	uniq(&main_cmds);
@@ -99,6 +113,6 @@ const char *help_unknown_cmd(const char *cmd)
 		for (i = 0; i < n; i++)
 			fprintf(stderr, "\t%s\n", main_cmds.names[i]->name);
 	}
-
+end:
 	exit(1);
 }
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 31c4641fe5ff..cfab531437c7 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -295,7 +295,7 @@ static void hists__delete_entry(struct hists *hists, struct hist_entry *he)
 		root_in  = &he->parent_he->hroot_in;
 		root_out = &he->parent_he->hroot_out;
 	} else {
-		if (sort__need_collapse)
+		if (hists__has(hists, need_collapse))
 			root_in = &hists->entries_collapsed;
 		else
 			root_in = hists->entries_in;
@@ -953,7 +953,7 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
 {
 	int err, err2;
 
-	err = sample__resolve_callchain(iter->sample, &iter->parent,
+	err = sample__resolve_callchain(iter->sample, &callchain_cursor, &iter->parent,
 					iter->evsel, al, max_stack_depth);
 	if (err)
 		return err;
@@ -1295,8 +1295,9 @@ static int hists__hierarchy_insert_entry(struct hists *hists,
 	return ret;
 }
 
-int hists__collapse_insert_entry(struct hists *hists, struct rb_root *root,
-				 struct hist_entry *he)
+static int hists__collapse_insert_entry(struct hists *hists,
+					struct rb_root *root,
+					struct hist_entry *he)
 {
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
@@ -1372,7 +1373,7 @@ int hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
 	struct hist_entry *n;
 	int ret;
 
-	if (!sort__need_collapse)
+	if (!hists__has(hists, need_collapse))
 		return 0;
 
 	hists->nr_entries = 0;
@@ -1631,7 +1632,7 @@ static void output_resort(struct hists *hists, struct ui_progress *prog,
 		return;
 	}
 
-	if (sort__need_collapse)
+	if (hists__has(hists, need_collapse))
 		root = &hists->entries_collapsed;
 	else
 		root = hists->entries_in;
@@ -2035,7 +2036,7 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
 	struct hist_entry *he;
 	int64_t cmp;
 
-	if (sort__need_collapse)
+	if (hists__has(hists, need_collapse))
 		root = &hists->entries_collapsed;
 	else
 		root = hists->entries_in;
@@ -2061,6 +2062,8 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
 	if (he) {
 		memset(&he->stat, 0, sizeof(he->stat));
 		he->hists = hists;
+		if (symbol_conf.cumulate_callchain)
+			memset(he->stat_acc, 0, sizeof(he->stat));
 		rb_link_node(&he->rb_node_in, parent, p);
 		rb_insert_color(&he->rb_node_in, root);
 		hists__inc_stats(hists, he);
@@ -2075,7 +2078,7 @@ static struct hist_entry *hists__find_entry(struct hists *hists,
 {
 	struct rb_node *n;
 
-	if (sort__need_collapse)
+	if (hists__has(hists, need_collapse))
 		n = hists->entries_collapsed.rb_node;
 	else
 		n = hists->entries_in->rb_node;
@@ -2104,7 +2107,7 @@ void hists__match(struct hists *leader, struct hists *other)
 	struct rb_node *nd;
 	struct hist_entry *pos, *pair;
 
-	if (sort__need_collapse)
+	if (hists__has(leader, need_collapse))
 		root = &leader->entries_collapsed;
 	else
 		root = leader->entries_in;
@@ -2129,7 +2132,7 @@ int hists__link(struct hists *leader, struct hists *other)
 	struct rb_node *nd;
 	struct hist_entry *pos, *pair;
 
-	if (sort__need_collapse)
+	if (hists__has(other, need_collapse))
 		root = &other->entries_collapsed;
 	else
 		root = other->entries_in;
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index bec0cd660fbd..0f84bfb42bb1 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -82,6 +82,8 @@ struct hists {
 	int			nr_hpp_node;
 };
 
+#define hists__has(__h, __f) (__h)->hpp_list->__f
+
 struct hist_entry_iter;
 
 struct hist_iter_ops {
@@ -199,8 +201,6 @@ int hists__init(void);
 int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list);
 
 struct rb_root *hists__get_rotate_entries_in(struct hists *hists);
-int hists__collapse_insert_entry(struct hists *hists,
-				  struct rb_root *root, struct hist_entry *he);
 
 struct perf_hpp {
 	char *buf;
@@ -240,6 +240,14 @@ struct perf_hpp_fmt {
 struct perf_hpp_list {
 	struct list_head fields;
 	struct list_head sorts;
+
+	int need_collapse;
+	int parent;
+	int sym;
+	int dso;
+	int socket;
+	int thread;
+	int comm;
 };
 
 extern struct perf_hpp_list perf_hpp_list;
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index abf1366e2a24..9df996085563 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -66,6 +66,7 @@ struct intel_bts {
 	u64				branches_id;
 	size_t				branches_event_size;
 	bool				synth_needs_swap;
+	unsigned long			num_events;
 };
 
 struct intel_bts_queue {
@@ -275,6 +276,10 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
 	union perf_event event;
 	struct perf_sample sample = { .ip = 0, };
 
+	if (bts->synth_opts.initial_skip &&
+	    bts->num_events++ <= bts->synth_opts.initial_skip)
+		return 0;
+
 	event.sample.header.type = PERF_RECORD_SAMPLE;
 	event.sample.header.misc = PERF_RECORD_MISC_USER;
 	event.sample.header.size = sizeof(struct perf_event_header);
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 9409d014b46c..9c8f15da86ce 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -356,7 +356,7 @@ static const char *intel_pt_err_msgs[] = {
 
 int intel_pt__strerror(int code, char *buf, size_t buflen)
 {
-	if (code < 1 || code > INTEL_PT_ERR_MAX)
+	if (code < 1 || code >= INTEL_PT_ERR_MAX)
 		code = INTEL_PT_ERR_UNK;
 	strlcpy(buf, intel_pt_err_msgs[code], buflen);
 	return 0;
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 617578440989..137196990012 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -100,6 +100,8 @@ struct intel_pt {
 	u64 cyc_bit;
 	u64 noretcomp_bit;
 	unsigned max_non_turbo_ratio;
+
+	unsigned long num_events;
 };
 
 enum switch_state {
@@ -972,6 +974,10 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
 	if (pt->branches_filter && !(pt->branches_filter & ptq->flags))
 		return 0;
 
+	if (pt->synth_opts.initial_skip &&
+	    pt->num_events++ < pt->synth_opts.initial_skip)
+		return 0;
+
 	event->sample.header.type = PERF_RECORD_SAMPLE;
 	event->sample.header.misc = PERF_RECORD_MISC_USER;
 	event->sample.header.size = sizeof(struct perf_event_header);
@@ -1029,6 +1035,10 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
 	union perf_event *event = ptq->event_buf;
 	struct perf_sample sample = { .ip = 0, };
 
+	if (pt->synth_opts.initial_skip &&
+	    pt->num_events++ < pt->synth_opts.initial_skip)
+		return 0;
+
 	event->sample.header.type = PERF_RECORD_SAMPLE;
 	event->sample.header.misc = PERF_RECORD_MISC_USER;
 	event->sample.header.size = sizeof(struct perf_event_header);
@@ -1087,6 +1097,10 @@ static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq)
 	union perf_event *event = ptq->event_buf;
 	struct perf_sample sample = { .ip = 0, };
 
+	if (pt->synth_opts.initial_skip &&
+	    pt->num_events++ < pt->synth_opts.initial_skip)
+		return 0;
+
 	event->sample.header.type = PERF_RECORD_SAMPLE;
 	event->sample.header.misc = PERF_RECORD_MISC_USER;
 	event->sample.header.size = sizeof(struct perf_event_header);
@@ -1199,14 +1213,18 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 	ptq->have_sample = false;
 
 	if (pt->sample_instructions &&
-	    (state->type & INTEL_PT_INSTRUCTION)) {
+	    (state->type & INTEL_PT_INSTRUCTION) &&
+	    (!pt->synth_opts.initial_skip ||
+	     pt->num_events++ >= pt->synth_opts.initial_skip)) {
 		err = intel_pt_synth_instruction_sample(ptq);
 		if (err)
 			return err;
 	}
 
 	if (pt->sample_transactions &&
-	    (state->type & INTEL_PT_TRANSACTION)) {
+	    (state->type & INTEL_PT_TRANSACTION) &&
+	    (!pt->synth_opts.initial_skip ||
+	     pt->num_events++ >= pt->synth_opts.initial_skip)) {
 		err = intel_pt_synth_transaction_sample(ptq);
 		if (err)
 			return err;
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index ad0c0bb1fbc7..86afe9618bb0 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -17,6 +17,7 @@
 #include "strlist.h"
 #include <elf.h>
 
+#include "tsc.h"
 #include "session.h"
 #include "jit.h"
 #include "jitdump.h"
@@ -33,6 +34,7 @@ struct jit_buf_desc {
 	size_t           bufsize;
 	FILE             *in;
 	bool		 needs_bswap; /* handles cross-endianess */
+	bool		 use_arch_timestamp;
 	void		 *debug_data;
 	size_t		 nr_debug_entries;
 	uint32_t         code_load_count;
@@ -158,13 +160,16 @@ jit_open(struct jit_buf_desc *jd, const char *name)
 		header.flags      = bswap_64(header.flags);
 	}
 
+	jd->use_arch_timestamp = header.flags & JITDUMP_FLAGS_ARCH_TIMESTAMP;
+
 	if (verbose > 2)
-		pr_debug("version=%u\nhdr.size=%u\nts=0x%llx\npid=%d\nelf_mach=%d\n",
+		pr_debug("version=%u\nhdr.size=%u\nts=0x%llx\npid=%d\nelf_mach=%d\nuse_arch_timestamp=%d\n",
 			header.version,
 			header.total_size,
 			(unsigned long long)header.timestamp,
 			header.pid,
-			header.elf_mach);
+			header.elf_mach,
+			jd->use_arch_timestamp);
 
 	if (header.flags & JITDUMP_FLAGS_RESERVED) {
 		pr_err("jitdump file contains invalid or unsupported flags 0x%llx\n",
@@ -172,10 +177,15 @@ jit_open(struct jit_buf_desc *jd, const char *name)
 		goto error;
 	}
 
+	if (jd->use_arch_timestamp && !jd->session->time_conv.time_mult) {
+		pr_err("jitdump file uses arch timestamps but there is no timestamp conversion\n");
+		goto error;
+	}
+
 	/*
 	 * validate event is using the correct clockid
 	 */
-	if (jit_validate_events(jd->session)) {
+	if (!jd->use_arch_timestamp && jit_validate_events(jd->session)) {
 		pr_err("error, jitted code must be sampled with perf record -k 1\n");
 		goto error;
 	}
@@ -329,6 +339,23 @@ jit_inject_event(struct jit_buf_desc *jd, union perf_event *event)
 	return 0;
 }
 
+static uint64_t convert_timestamp(struct jit_buf_desc *jd, uint64_t timestamp)
+{
+	struct perf_tsc_conversion tc;
+
+	if (!jd->use_arch_timestamp)
+		return timestamp;
+
+	tc.time_shift = jd->session->time_conv.time_shift;
+	tc.time_mult  = jd->session->time_conv.time_mult;
+	tc.time_zero  = jd->session->time_conv.time_zero;
+
+	if (!tc.time_mult)
+		return 0;
+
+	return tsc_to_perf_time(timestamp, &tc);
+}
+
 static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr)
 {
 	struct perf_sample sample;
@@ -385,7 +412,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr)
 		return -1;
 	}
 	if (stat(filename, &st))
-		memset(&st, 0, sizeof(stat));
+		memset(&st, 0, sizeof(st));
 
 	event->mmap2.header.type = PERF_RECORD_MMAP2;
 	event->mmap2.header.misc = PERF_RECORD_MISC_USER;
@@ -410,7 +437,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr)
 		id->tid  = tid;
 	}
 	if (jd->sample_type & PERF_SAMPLE_TIME)
-		id->time = jr->load.p.timestamp;
+		id->time = convert_timestamp(jd, jr->load.p.timestamp);
 
 	/*
 	 * create pseudo sample to induce dso hit increment
@@ -473,7 +500,7 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr)
 	size++; /* for \0 */
 
 	if (stat(filename, &st))
-		memset(&st, 0, sizeof(stat));
+		memset(&st, 0, sizeof(st));
 
 	size = PERF_ALIGN(size, sizeof(u64));
 
@@ -499,7 +526,7 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr)
 		id->tid  = tid;
 	}
 	if (jd->sample_type & PERF_SAMPLE_TIME)
-		id->time = jr->load.p.timestamp;
+		id->time = convert_timestamp(jd, jr->load.p.timestamp);
 
 	/*
 	 * create pseudo sample to induce dso hit increment
diff --git a/tools/perf/util/jitdump.h b/tools/perf/util/jitdump.h
index b66c1f503d9e..bcacd20d0c1c 100644
--- a/tools/perf/util/jitdump.h
+++ b/tools/perf/util/jitdump.h
@@ -23,9 +23,12 @@
 #define JITHEADER_VERSION 1
 
 enum jitdump_flags_bits {
+	JITDUMP_FLAGS_ARCH_TIMESTAMP_BIT,
 	JITDUMP_FLAGS_MAX_BIT,
 };
 
+#define JITDUMP_FLAGS_ARCH_TIMESTAMP	(1ULL << JITDUMP_FLAGS_ARCH_TIMESTAMP_BIT)
+
 #define JITDUMP_FLAGS_RESERVED (JITDUMP_FLAGS_MAX_BIT < 64 ? \
 				(~((1ULL << JITDUMP_FLAGS_MAX_BIT) - 1)) : 0)
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 80b9b6a87990..639a2903065e 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -32,6 +32,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 
 	machine->threads = RB_ROOT;
 	pthread_rwlock_init(&machine->threads_lock, NULL);
+	machine->nr_threads = 0;
 	INIT_LIST_HEAD(&machine->dead_threads);
 	machine->last_match = NULL;
 
@@ -430,6 +431,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 		 */
 		thread__get(th);
 		machine->last_match = th;
+		++machine->nr_threads;
 	}
 
 	return th;
@@ -681,11 +683,13 @@ size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp)
 
 size_t machine__fprintf(struct machine *machine, FILE *fp)
 {
-	size_t ret = 0;
+	size_t ret;
 	struct rb_node *nd;
 
 	pthread_rwlock_rdlock(&machine->threads_lock);
 
+	ret = fprintf(fp, "Threads: %u\n", machine->nr_threads);
+
 	for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) {
 		struct thread *pos = rb_entry(nd, struct thread, rb_node);
 
@@ -908,11 +912,11 @@ int machines__create_kernel_maps(struct machines *machines, pid_t pid)
 	return machine__create_kernel_maps(machine);
 }
 
-int machine__load_kallsyms(struct machine *machine, const char *filename,
-			   enum map_type type, symbol_filter_t filter)
+int __machine__load_kallsyms(struct machine *machine, const char *filename,
+			     enum map_type type, bool no_kcore, symbol_filter_t filter)
 {
 	struct map *map = machine__kernel_map(machine);
-	int ret = dso__load_kallsyms(map->dso, filename, map, filter);
+	int ret = __dso__load_kallsyms(map->dso, filename, map, no_kcore, filter);
 
 	if (ret > 0) {
 		dso__set_loaded(map->dso, type);
@@ -927,6 +931,12 @@ int machine__load_kallsyms(struct machine *machine, const char *filename,
 	return ret;
 }
 
+int machine__load_kallsyms(struct machine *machine, const char *filename,
+			   enum map_type type, symbol_filter_t filter)
+{
+	return __machine__load_kallsyms(machine, filename, type, false, filter);
+}
+
 int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
 			       symbol_filter_t filter)
 {
@@ -1413,6 +1423,7 @@ static void __machine__remove_thread(struct machine *machine, struct thread *th,
 		pthread_rwlock_wrlock(&machine->threads_lock);
 	rb_erase_init(&th->rb_node, &machine->threads);
 	RB_CLEAR_NODE(&th->rb_node);
+	--machine->nr_threads;
 	/*
 	 * Move it first to the dead_threads list, then drop the reference,
 	 * if this is the last reference, then the thread__delete destructor
@@ -1599,6 +1610,7 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample,
 }
 
 static int add_callchain_ip(struct thread *thread,
+			    struct callchain_cursor *cursor,
 			    struct symbol **parent,
 			    struct addr_location *root_al,
 			    u8 *cpumode,
@@ -1630,7 +1642,7 @@ static int add_callchain_ip(struct thread *thread,
 				 * It seems the callchain is corrupted.
 				 * Discard all.
 				 */
-				callchain_cursor_reset(&callchain_cursor);
+				callchain_cursor_reset(cursor);
 				return 1;
 			}
 			return 0;
@@ -1640,7 +1652,7 @@ static int add_callchain_ip(struct thread *thread,
 	}
 
 	if (al.sym != NULL) {
-		if (sort__has_parent && !*parent &&
+		if (perf_hpp_list.parent && !*parent &&
 		    symbol__match_regex(al.sym, &parent_regex))
 			*parent = al.sym;
 		else if (have_ignore_callees && root_al &&
@@ -1648,13 +1660,13 @@ static int add_callchain_ip(struct thread *thread,
 			/* Treat this symbol as the root,
 			   forgetting its callees. */
 			*root_al = al;
-			callchain_cursor_reset(&callchain_cursor);
+			callchain_cursor_reset(cursor);
 		}
 	}
 
 	if (symbol_conf.hide_unresolved && al.sym == NULL)
 		return 0;
-	return callchain_cursor_append(&callchain_cursor, al.addr, al.map, al.sym);
+	return callchain_cursor_append(cursor, al.addr, al.map, al.sym);
 }
 
 struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
@@ -1724,6 +1736,7 @@ static int remove_loops(struct branch_entry *l, int nr)
  * negative error code on other errors.
  */
 static int resolve_lbr_callchain_sample(struct thread *thread,
+					struct callchain_cursor *cursor,
 					struct perf_sample *sample,
 					struct symbol **parent,
 					struct addr_location *root_al,
@@ -1756,7 +1769,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 		 */
 		int mix_chain_nr = i + 1 + lbr_nr + 1;
 
-		if (mix_chain_nr > PERF_MAX_STACK_DEPTH + PERF_MAX_BRANCH_DEPTH) {
+		if (mix_chain_nr > (int)sysctl_perf_event_max_stack + PERF_MAX_BRANCH_DEPTH) {
 			pr_warning("corrupted callchain. skipping...\n");
 			return 0;
 		}
@@ -1778,7 +1791,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 					ip = lbr_stack->entries[0].to;
 			}
 
-			err = add_callchain_ip(thread, parent, root_al, &cpumode, ip);
+			err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip);
 			if (err)
 				return (err < 0) ? err : 0;
 		}
@@ -1789,6 +1802,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 }
 
 static int thread__resolve_callchain_sample(struct thread *thread,
+					    struct callchain_cursor *cursor,
 					    struct perf_evsel *evsel,
 					    struct perf_sample *sample,
 					    struct symbol **parent,
@@ -1803,10 +1817,8 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	int skip_idx = -1;
 	int first_call = 0;
 
-	callchain_cursor_reset(&callchain_cursor);
-
-	if (has_branch_callstack(evsel)) {
-		err = resolve_lbr_callchain_sample(thread, sample, parent,
+	if (perf_evsel__has_branch_callstack(evsel)) {
+		err = resolve_lbr_callchain_sample(thread, cursor, sample, parent,
 						   root_al, max_stack);
 		if (err)
 			return (err < 0) ? err : 0;
@@ -1816,7 +1828,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	 * Based on DWARF debug information, some architectures skip
 	 * a callchain entry saved by the kernel.
 	 */
-	if (chain->nr < PERF_MAX_STACK_DEPTH)
+	if (chain->nr < sysctl_perf_event_max_stack)
 		skip_idx = arch_skip_callchain_idx(thread, chain);
 
 	/*
@@ -1863,10 +1875,10 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 		nr = remove_loops(be, nr);
 
 		for (i = 0; i < nr; i++) {
-			err = add_callchain_ip(thread, parent, root_al,
+			err = add_callchain_ip(thread, cursor, parent, root_al,
 					       NULL, be[i].to);
 			if (!err)
-				err = add_callchain_ip(thread, parent, root_al,
+				err = add_callchain_ip(thread, cursor, parent, root_al,
 						       NULL, be[i].from);
 			if (err == -EINVAL)
 				break;
@@ -1877,7 +1889,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	}
 
 check_calls:
-	if (chain->nr > PERF_MAX_STACK_DEPTH && (int)chain->nr > max_stack) {
+	if (chain->nr > sysctl_perf_event_max_stack && (int)chain->nr > max_stack) {
 		pr_warning("corrupted callchain. skipping...\n");
 		return 0;
 	}
@@ -1896,7 +1908,7 @@ check_calls:
 #endif
 		ip = chain->ips[j];
 
-		err = add_callchain_ip(thread, parent, root_al, &cpumode, ip);
+		err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip);
 
 		if (err)
 			return (err < 0) ? err : 0;
@@ -1915,19 +1927,12 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 				       entry->map, entry->sym);
 }
 
-int thread__resolve_callchain(struct thread *thread,
-			      struct perf_evsel *evsel,
-			      struct perf_sample *sample,
-			      struct symbol **parent,
-			      struct addr_location *root_al,
-			      int max_stack)
+static int thread__resolve_callchain_unwind(struct thread *thread,
+					    struct callchain_cursor *cursor,
+					    struct perf_evsel *evsel,
+					    struct perf_sample *sample,
+					    int max_stack)
 {
-	int ret = thread__resolve_callchain_sample(thread, evsel,
-						   sample, parent,
-						   root_al, max_stack);
-	if (ret)
-		return ret;
-
 	/* Can we do dwarf post unwind? */
 	if (!((evsel->attr.sample_type & PERF_SAMPLE_REGS_USER) &&
 	      (evsel->attr.sample_type & PERF_SAMPLE_STACK_USER)))
@@ -1938,9 +1943,45 @@ int thread__resolve_callchain(struct thread *thread,
 	    (!sample->user_stack.size))
 		return 0;
 
-	return unwind__get_entries(unwind_entry, &callchain_cursor,
+	return unwind__get_entries(unwind_entry, cursor,
 				   thread, sample, max_stack);
+}
+
+int thread__resolve_callchain(struct thread *thread,
+			      struct callchain_cursor *cursor,
+			      struct perf_evsel *evsel,
+			      struct perf_sample *sample,
+			      struct symbol **parent,
+			      struct addr_location *root_al,
+			      int max_stack)
+{
+	int ret = 0;
+
+	callchain_cursor_reset(&callchain_cursor);
 
+	if (callchain_param.order == ORDER_CALLEE) {
+		ret = thread__resolve_callchain_sample(thread, cursor,
+						       evsel, sample,
+						       parent, root_al,
+						       max_stack);
+		if (ret)
+			return ret;
+		ret = thread__resolve_callchain_unwind(thread, cursor,
+						       evsel, sample,
+						       max_stack);
+	} else {
+		ret = thread__resolve_callchain_unwind(thread, cursor,
+						       evsel, sample,
+						       max_stack);
+		if (ret)
+			return ret;
+		ret = thread__resolve_callchain_sample(thread, cursor,
+						       evsel, sample,
+						       parent, root_al,
+						       max_stack);
+	}
+
+	return ret;
 }
 
 int machine__for_each_thread(struct machine *machine,
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 8499db281158..83f46790c52f 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -31,6 +31,7 @@ struct machine {
 	char		  *root_dir;
 	struct rb_root	  threads;
 	pthread_rwlock_t  threads_lock;
+	unsigned int	  nr_threads;
 	struct list_head  dead_threads;
 	struct thread	  *last_match;
 	struct vdso_info  *vdso_info;
@@ -141,7 +142,11 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
 					   struct addr_location *al);
 struct mem_info *sample__resolve_mem(struct perf_sample *sample,
 				     struct addr_location *al);
+
+struct callchain_cursor;
+
 int thread__resolve_callchain(struct thread *thread,
+			      struct callchain_cursor *cursor,
 			      struct perf_evsel *evsel,
 			      struct perf_sample *sample,
 			      struct symbol **parent,
@@ -211,6 +216,8 @@ struct symbol *machine__find_kernel_function_by_name(struct machine *machine,
 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, bool no_kcore, symbol_filter_t filter);
 int machine__load_kallsyms(struct machine *machine, const char *filename,
 			   enum map_type type, symbol_filter_t filter);
 int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 171b6d10a04b..b19bcd3b7128 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -289,7 +289,7 @@ int map__load(struct map *map, symbol_filter_t filter)
 	nr = dso__load(map->dso, map, filter);
 	if (nr < 0) {
 		if (map->dso->has_build_id) {
-			char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+			char sbuild_id[SBUILD_ID_SIZE];
 
 			build_id__sprintf(map->dso->build_id,
 					  sizeof(map->dso->build_id),
@@ -431,6 +431,13 @@ u64 map__rip_2objdump(struct map *map, u64 rip)
 	if (map->dso->rel)
 		return rip - map->pgoff;
 
+	/*
+	 * kernel modules also have DSO_TYPE_USER in dso->kernel,
+	 * but all kernel modules are ET_REL, so won't get here.
+	 */
+	if (map->dso->kernel == DSO_TYPE_USER)
+		return rip + map->dso->text_offset;
+
 	return map->unmap_ip(map, rip) - map->reloc;
 }
 
@@ -454,6 +461,13 @@ u64 map__objdump_2mem(struct map *map, u64 ip)
 	if (map->dso->rel)
 		return map->unmap_ip(map, ip + map->pgoff);
 
+	/*
+	 * kernel modules also have DSO_TYPE_USER in dso->kernel,
+	 * but all kernel modules are ET_REL, so won't get here.
+	 */
+	if (map->dso->kernel == DSO_TYPE_USER)
+		return map->unmap_ip(map, ip - map->dso->text_offset);
+
 	return ip + map->reloc;
 }
 
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
index b1b9e2385f4b..fe84df1875aa 100644
--- a/tools/perf/util/ordered-events.c
+++ b/tools/perf/util/ordered-events.c
@@ -308,3 +308,12 @@ void ordered_events__free(struct ordered_events *oe)
 		free(event);
 	}
 }
+
+void ordered_events__reinit(struct ordered_events *oe)
+{
+	ordered_events__deliver_t old_deliver = oe->deliver;
+
+	ordered_events__free(oe);
+	memset(oe, '\0', sizeof(*oe));
+	ordered_events__init(oe, old_deliver);
+}
diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h
index f403991e3bfd..e11468a9a6e4 100644
--- a/tools/perf/util/ordered-events.h
+++ b/tools/perf/util/ordered-events.h
@@ -49,6 +49,7 @@ void ordered_events__delete(struct ordered_events *oe, struct ordered_event *eve
 int ordered_events__flush(struct ordered_events *oe, enum oe_flush how);
 void ordered_events__init(struct ordered_events *oe, ordered_events__deliver_t deliver);
 void ordered_events__free(struct ordered_events *oe);
+void ordered_events__reinit(struct ordered_events *oe);
 
 static inline
 void ordered_events__set_alloc_size(struct ordered_events *oe, u64 size)
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index adef23b1352e..ddb0261b2577 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -602,14 +602,13 @@ static void pmu_format_value(unsigned long *format, __u64 value, __u64 *v,
 
 static __u64 pmu_format_max_value(const unsigned long *format)
 {
-	int w;
+	__u64 w = 0;
+	int fbit;
 
-	w = bitmap_weight(format, PERF_PMU_FORMAT_BITS);
-	if (!w)
-		return 0;
-	if (w < 64)
-		return (1ULL << w) - 1;
-	return -1;
+	for_each_set_bit(fbit, format, PERF_PMU_FORMAT_BITS)
+		w |= (1ULL << fbit);
+
+	return w;
 }
 
 /*
@@ -644,20 +643,20 @@ static int pmu_resolve_param_term(struct parse_events_term *term,
 static char *pmu_formats_string(struct list_head *formats)
 {
 	struct perf_pmu_format *format;
-	char *str;
-	struct strbuf buf;
+	char *str = NULL;
+	struct strbuf buf = STRBUF_INIT;
 	unsigned i = 0;
 
 	if (!formats)
 		return NULL;
 
-	strbuf_init(&buf, 0);
 	/* sysfs exported terms */
 	list_for_each_entry(format, formats, list)
-		strbuf_addf(&buf, i++ ? ",%s" : "%s",
-			    format->name);
+		if (strbuf_addf(&buf, i++ ? ",%s" : "%s", format->name) < 0)
+			goto error;
 
 	str = strbuf_detach(&buf, NULL);
+error:
 	strbuf_release(&buf);
 
 	return str;
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 8319fbb08636..74401a20106d 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -265,6 +265,65 @@ static bool kprobe_warn_out_range(const char *symbol, unsigned long address)
 	return true;
 }
 
+/*
+ * NOTE:
+ * '.gnu.linkonce.this_module' section of kernel module elf directly
+ * maps to 'struct module' from linux/module.h. This section contains
+ * actual module name which will be used by kernel after loading it.
+ * But, we cannot use 'struct module' here since linux/module.h is not
+ * exposed to user-space. Offset of 'name' has remained same from long
+ * time, so hardcoding it here.
+ */
+#ifdef __LP64__
+#define MOD_NAME_OFFSET 24
+#else
+#define MOD_NAME_OFFSET 12
+#endif
+
+/*
+ * @module can be module name of module file path. In case of path,
+ * inspect elf and find out what is actual module name.
+ * Caller has to free mod_name after using it.
+ */
+static char *find_module_name(const char *module)
+{
+	int fd;
+	Elf *elf;
+	GElf_Ehdr ehdr;
+	GElf_Shdr shdr;
+	Elf_Data *data;
+	Elf_Scn *sec;
+	char *mod_name = NULL;
+
+	fd = open(module, O_RDONLY);
+	if (fd < 0)
+		return NULL;
+
+	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+	if (elf == NULL)
+		goto elf_err;
+
+	if (gelf_getehdr(elf, &ehdr) == NULL)
+		goto ret_err;
+
+	sec = elf_section_by_name(elf, &ehdr, &shdr,
+			".gnu.linkonce.this_module", NULL);
+	if (!sec)
+		goto ret_err;
+
+	data = elf_getdata(sec, NULL);
+	if (!data || !data->d_buf)
+		goto ret_err;
+
+	mod_name = strdup((char *)data->d_buf + MOD_NAME_OFFSET);
+
+ret_err:
+	elf_end(elf);
+elf_err:
+	close(fd);
+	return mod_name;
+}
+
 #ifdef HAVE_DWARF_SUPPORT
 
 static int kernel_get_module_dso(const char *module, struct dso **pdso)
@@ -486,8 +545,10 @@ static int get_text_start_address(const char *exec, unsigned long *address)
 		return -errno;
 
 	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
-	if (elf == NULL)
-		return -EINVAL;
+	if (elf == NULL) {
+		ret = -EINVAL;
+		goto out_close;
+	}
 
 	if (gelf_getehdr(elf, &ehdr) == NULL)
 		goto out;
@@ -499,6 +560,9 @@ static int get_text_start_address(const char *exec, unsigned long *address)
 	ret = 0;
 out:
 	elf_end(elf);
+out_close:
+	close(fd);
+
 	return ret;
 }
 
@@ -583,32 +647,23 @@ static int add_module_to_probe_trace_events(struct probe_trace_event *tevs,
 					    int ntevs, const char *module)
 {
 	int i, ret = 0;
-	char *tmp;
+	char *mod_name = NULL;
 
 	if (!module)
 		return 0;
 
-	tmp = strrchr(module, '/');
-	if (tmp) {
-		/* This is a module path -- get the module name */
-		module = strdup(tmp + 1);
-		if (!module)
-			return -ENOMEM;
-		tmp = strchr(module, '.');
-		if (tmp)
-			*tmp = '\0';
-		tmp = (char *)module;	/* For free() */
-	}
+	mod_name = find_module_name(module);
 
 	for (i = 0; i < ntevs; i++) {
-		tevs[i].point.module = strdup(module);
+		tevs[i].point.module =
+			strdup(mod_name ? mod_name : module);
 		if (!tevs[i].point.module) {
 			ret = -ENOMEM;
 			break;
 		}
 	}
 
-	free(tmp);
+	free(mod_name);
 	return ret;
 }
 
@@ -1618,69 +1673,65 @@ out:
 }
 
 /* Compose only probe arg */
-int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len)
+char *synthesize_perf_probe_arg(struct perf_probe_arg *pa)
 {
 	struct perf_probe_arg_field *field = pa->field;
-	int ret;
-	char *tmp = buf;
+	struct strbuf buf;
+	char *ret = NULL;
+	int err;
+
+	if (strbuf_init(&buf, 64) < 0)
+		return NULL;
 
 	if (pa->name && pa->var)
-		ret = e_snprintf(tmp, len, "%s=%s", pa->name, pa->var);
+		err = strbuf_addf(&buf, "%s=%s", pa->name, pa->var);
 	else
-		ret = e_snprintf(tmp, len, "%s", pa->name ? pa->name : pa->var);
-	if (ret <= 0)
-		goto error;
-	tmp += ret;
-	len -= ret;
+		err = strbuf_addstr(&buf, pa->name ?: pa->var);
+	if (err)
+		goto out;
 
 	while (field) {
 		if (field->name[0] == '[')
-			ret = e_snprintf(tmp, len, "%s", field->name);
+			err = strbuf_addstr(&buf, field->name);
 		else
-			ret = e_snprintf(tmp, len, "%s%s",
-					 field->ref ? "->" : ".", field->name);
-		if (ret <= 0)
-			goto error;
-		tmp += ret;
-		len -= ret;
+			err = strbuf_addf(&buf, "%s%s", field->ref ? "->" : ".",
+					  field->name);
 		field = field->next;
+		if (err)
+			goto out;
 	}
 
-	if (pa->type) {
-		ret = e_snprintf(tmp, len, ":%s", pa->type);
-		if (ret <= 0)
-			goto error;
-		tmp += ret;
-		len -= ret;
-	}
+	if (pa->type)
+		if (strbuf_addf(&buf, ":%s", pa->type) < 0)
+			goto out;
 
-	return tmp - buf;
-error:
-	pr_debug("Failed to synthesize perf probe argument: %d\n", ret);
+	ret = strbuf_detach(&buf, NULL);
+out:
+	strbuf_release(&buf);
 	return ret;
 }
 
 /* Compose only probe point (not argument) */
 static char *synthesize_perf_probe_point(struct perf_probe_point *pp)
 {
-	char *buf, *tmp;
-	char offs[32] = "", line[32] = "", file[32] = "";
-	int ret, len;
+	struct strbuf buf;
+	char *tmp, *ret = NULL;
+	int len, err = 0;
 
-	buf = zalloc(MAX_CMDLEN);
-	if (buf == NULL) {
-		ret = -ENOMEM;
-		goto error;
-	}
-	if (pp->offset) {
-		ret = e_snprintf(offs, 32, "+%lu", pp->offset);
-		if (ret <= 0)
-			goto error;
-	}
-	if (pp->line) {
-		ret = e_snprintf(line, 32, ":%d", pp->line);
-		if (ret <= 0)
-			goto error;
+	if (strbuf_init(&buf, 64) < 0)
+		return NULL;
+
+	if (pp->function) {
+		if (strbuf_addstr(&buf, pp->function) < 0)
+			goto out;
+		if (pp->offset)
+			err = strbuf_addf(&buf, "+%lu", pp->offset);
+		else if (pp->line)
+			err = strbuf_addf(&buf, ":%d", pp->line);
+		else if (pp->retprobe)
+			err = strbuf_addstr(&buf, "%return");
+		if (err)
+			goto out;
 	}
 	if (pp->file) {
 		tmp = pp->file;
@@ -1689,25 +1740,15 @@ static char *synthesize_perf_probe_point(struct perf_probe_point *pp)
 			tmp = strchr(pp->file + len - 30, '/');
 			tmp = tmp ? tmp + 1 : pp->file + len - 30;
 		}
-		ret = e_snprintf(file, 32, "@%s", tmp);
-		if (ret <= 0)
-			goto error;
+		err = strbuf_addf(&buf, "@%s", tmp);
+		if (!err && !pp->function && pp->line)
+			err = strbuf_addf(&buf, ":%d", pp->line);
 	}
-
-	if (pp->function)
-		ret = e_snprintf(buf, MAX_CMDLEN, "%s%s%s%s%s", pp->function,
-				 offs, pp->retprobe ? "%return" : "", line,
-				 file);
-	else
-		ret = e_snprintf(buf, MAX_CMDLEN, "%s%s", file, line);
-	if (ret <= 0)
-		goto error;
-
-	return buf;
-error:
-	pr_debug("Failed to synthesize perf probe point: %d\n", ret);
-	free(buf);
-	return NULL;
+	if (!err)
+		ret = strbuf_detach(&buf, NULL);
+out:
+	strbuf_release(&buf);
+	return ret;
 }
 
 #if 0
@@ -1736,45 +1777,32 @@ char *synthesize_perf_probe_command(struct perf_probe_event *pev)
 #endif
 
 static int __synthesize_probe_trace_arg_ref(struct probe_trace_arg_ref *ref,
-					     char **buf, size_t *buflen,
-					     int depth)
+					    struct strbuf *buf, int depth)
 {
-	int ret;
+	int err;
 	if (ref->next) {
 		depth = __synthesize_probe_trace_arg_ref(ref->next, buf,
-							 buflen, depth + 1);
+							 depth + 1);
 		if (depth < 0)
-			goto out;
-	}
-
-	ret = e_snprintf(*buf, *buflen, "%+ld(", ref->offset);
-	if (ret < 0)
-		depth = ret;
-	else {
-		*buf += ret;
-		*buflen -= ret;
+			return depth;
 	}
-out:
-	return depth;
-
+	err = strbuf_addf(buf, "%+ld(", ref->offset);
+	return (err < 0) ? err : depth;
 }
 
 static int synthesize_probe_trace_arg(struct probe_trace_arg *arg,
-				       char *buf, size_t buflen)
+				      struct strbuf *buf)
 {
 	struct probe_trace_arg_ref *ref = arg->ref;
-	int ret, depth = 0;
-	char *tmp = buf;
+	int depth = 0, err;
 
 	/* Argument name or separator */
 	if (arg->name)
-		ret = e_snprintf(buf, buflen, " %s=", arg->name);
+		err = strbuf_addf(buf, " %s=", arg->name);
 	else
-		ret = e_snprintf(buf, buflen, " ");
-	if (ret < 0)
-		return ret;
-	buf += ret;
-	buflen -= ret;
+		err = strbuf_addch(buf, ' ');
+	if (err)
+		return err;
 
 	/* Special case: @XXX */
 	if (arg->value[0] == '@' && arg->ref)
@@ -1782,59 +1810,44 @@ static int synthesize_probe_trace_arg(struct probe_trace_arg *arg,
 
 	/* Dereferencing arguments */
 	if (ref) {
-		depth = __synthesize_probe_trace_arg_ref(ref, &buf,
-							  &buflen, 1);
+		depth = __synthesize_probe_trace_arg_ref(ref, buf, 1);
 		if (depth < 0)
 			return depth;
 	}
 
 	/* Print argument value */
 	if (arg->value[0] == '@' && arg->ref)
-		ret = e_snprintf(buf, buflen, "%s%+ld", arg->value,
-				 arg->ref->offset);
+		err = strbuf_addf(buf, "%s%+ld", arg->value, arg->ref->offset);
 	else
-		ret = e_snprintf(buf, buflen, "%s", arg->value);
-	if (ret < 0)
-		return ret;
-	buf += ret;
-	buflen -= ret;
+		err = strbuf_addstr(buf, arg->value);
 
 	/* Closing */
-	while (depth--) {
-		ret = e_snprintf(buf, buflen, ")");
-		if (ret < 0)
-			return ret;
-		buf += ret;
-		buflen -= ret;
-	}
+	while (!err && depth--)
+		err = strbuf_addch(buf, ')');
+
 	/* Print argument type */
-	if (arg->type) {
-		ret = e_snprintf(buf, buflen, ":%s", arg->type);
-		if (ret <= 0)
-			return ret;
-		buf += ret;
-	}
+	if (!err && arg->type)
+		err = strbuf_addf(buf, ":%s", arg->type);
 
-	return buf - tmp;
+	return err;
 }
 
 char *synthesize_probe_trace_command(struct probe_trace_event *tev)
 {
 	struct probe_trace_point *tp = &tev->point;
-	char *buf;
-	int i, len, ret;
+	struct strbuf buf;
+	char *ret = NULL;
+	int i, err;
 
-	buf = zalloc(MAX_CMDLEN);
-	if (buf == NULL)
+	/* Uprobes must have tp->module */
+	if (tev->uprobes && !tp->module)
 		return NULL;
 
-	len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s ", tp->retprobe ? 'r' : 'p',
-			 tev->group, tev->event);
-	if (len <= 0)
-		goto error;
+	if (strbuf_init(&buf, 32) < 0)
+		return NULL;
 
-	/* Uprobes must have tp->module */
-	if (tev->uprobes && !tp->module)
+	if (strbuf_addf(&buf, "%c:%s/%s ", tp->retprobe ? 'r' : 'p',
+			tev->group, tev->event) < 0)
 		goto error;
 	/*
 	 * If tp->address == 0, then this point must be a
@@ -1849,34 +1862,25 @@ char *synthesize_probe_trace_command(struct probe_trace_event *tev)
 
 	/* Use the tp->address for uprobes */
 	if (tev->uprobes)
-		ret = e_snprintf(buf + len, MAX_CMDLEN - len, "%s:0x%lx",
-				 tp->module, tp->address);
+		err = strbuf_addf(&buf, "%s:0x%lx", tp->module, tp->address);
 	else if (!strncmp(tp->symbol, "0x", 2))
 		/* Absolute address. See try_to_find_absolute_address() */
-		ret = e_snprintf(buf + len, MAX_CMDLEN - len, "%s%s0x%lx",
-				 tp->module ?: "", tp->module ? ":" : "",
-				 tp->address);
+		err = strbuf_addf(&buf, "%s%s0x%lx", tp->module ?: "",
+				  tp->module ? ":" : "", tp->address);
 	else
-		ret = e_snprintf(buf + len, MAX_CMDLEN - len, "%s%s%s+%lu",
-				 tp->module ?: "", tp->module ? ":" : "",
-				 tp->symbol, tp->offset);
-
-	if (ret <= 0)
+		err = strbuf_addf(&buf, "%s%s%s+%lu", tp->module ?: "",
+				tp->module ? ":" : "", tp->symbol, tp->offset);
+	if (err)
 		goto error;
-	len += ret;
 
-	for (i = 0; i < tev->nargs; i++) {
-		ret = synthesize_probe_trace_arg(&tev->args[i], buf + len,
-						  MAX_CMDLEN - len);
-		if (ret <= 0)
+	for (i = 0; i < tev->nargs; i++)
+		if (synthesize_probe_trace_arg(&tev->args[i], &buf) < 0)
 			goto error;
-		len += ret;
-	}
 
-	return buf;
+	ret = strbuf_detach(&buf, NULL);
 error:
-	free(buf);
-	return NULL;
+	strbuf_release(&buf);
+	return ret;
 }
 
 static int find_perf_probe_point_from_map(struct probe_trace_point *tp,
@@ -1958,7 +1962,7 @@ static int convert_to_perf_probe_point(struct probe_trace_point *tp,
 static int convert_to_perf_probe_event(struct probe_trace_event *tev,
 			       struct perf_probe_event *pev, bool is_kprobe)
 {
-	char buf[64] = "";
+	struct strbuf buf = STRBUF_INIT;
 	int i, ret;
 
 	/* Convert event/group name */
@@ -1981,14 +1985,15 @@ static int convert_to_perf_probe_event(struct probe_trace_event *tev,
 		if (tev->args[i].name)
 			pev->args[i].name = strdup(tev->args[i].name);
 		else {
-			ret = synthesize_probe_trace_arg(&tev->args[i],
-							  buf, 64);
-			pev->args[i].name = strdup(buf);
+			if ((ret = strbuf_init(&buf, 32)) < 0)
+				goto error;
+			ret = synthesize_probe_trace_arg(&tev->args[i], &buf);
+			pev->args[i].name = strbuf_detach(&buf, NULL);
 		}
 		if (pev->args[i].name == NULL && ret >= 0)
 			ret = -ENOMEM;
 	}
-
+error:
 	if (ret < 0)
 		clear_perf_probe_event(pev);
 
@@ -2162,35 +2167,38 @@ static int perf_probe_event__sprintf(const char *group, const char *event,
 				     struct strbuf *result)
 {
 	int i, ret;
-	char buf[128];
-	char *place;
+	char *buf;
 
-	/* Synthesize only event probe point */
-	place = synthesize_perf_probe_point(&pev->point);
-	if (!place)
-		return -EINVAL;
+	if (asprintf(&buf, "%s:%s", group, event) < 0)
+		return -errno;
+	ret = strbuf_addf(result, "  %-20s (on ", buf);
+	free(buf);
+	if (ret)
+		return ret;
 
-	ret = e_snprintf(buf, 128, "%s:%s", group, event);
-	if (ret < 0)
-		goto out;
+	/* Synthesize only event probe point */
+	buf = synthesize_perf_probe_point(&pev->point);
+	if (!buf)
+		return -ENOMEM;
+	ret = strbuf_addstr(result, buf);
+	free(buf);
 
-	strbuf_addf(result, "  %-20s (on %s", buf, place);
-	if (module)
-		strbuf_addf(result, " in %s", module);
+	if (!ret && module)
+		ret = strbuf_addf(result, " in %s", module);
 
-	if (pev->nargs > 0) {
-		strbuf_add(result, " with", 5);
-		for (i = 0; i < pev->nargs; i++) {
-			ret = synthesize_perf_probe_arg(&pev->args[i],
-							buf, 128);
-			if (ret < 0)
-				goto out;
-			strbuf_addf(result, " %s", buf);
+	if (!ret && pev->nargs > 0) {
+		ret = strbuf_add(result, " with", 5);
+		for (i = 0; !ret && i < pev->nargs; i++) {
+			buf = synthesize_perf_probe_arg(&pev->args[i]);
+			if (!buf)
+				return -ENOMEM;
+			ret = strbuf_addf(result, " %s", buf);
+			free(buf);
 		}
 	}
-	strbuf_addch(result, ')');
-out:
-	free(place);
+	if (!ret)
+		ret = strbuf_addch(result, ')');
+
 	return ret;
 }
 
@@ -2498,7 +2506,8 @@ static int find_probe_functions(struct map *map, char *name,
 
 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) { }
+				struct map *map __maybe_unused,
+				struct symbol *sym __maybe_unused) { }
 
 /*
  * Find probe function addresses from map.
@@ -2516,6 +2525,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 	struct probe_trace_point *tp;
 	int num_matched_functions;
 	int ret, i, j, skipped = 0;
+	char *mod_name;
 
 	map = get_target_map(pev->target, pev->uprobes);
 	if (!map) {
@@ -2600,9 +2610,19 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 		tp->realname = strdup_or_goto(sym->name, nomem_out);
 
 		tp->retprobe = pp->retprobe;
-		if (pev->target)
-			tev->point.module = strdup_or_goto(pev->target,
-							   nomem_out);
+		if (pev->target) {
+			if (pev->uprobes) {
+				tev->point.module = strdup_or_goto(pev->target,
+								   nomem_out);
+			} else {
+				mod_name = find_module_name(pev->target);
+				tev->point.module =
+					strdup(mod_name ? mod_name : pev->target);
+				free(mod_name);
+				if (!tev->point.module)
+					goto nomem_out;
+			}
+		}
 		tev->uprobes = pev->uprobes;
 		tev->nargs = pev->nargs;
 		if (tev->nargs) {
@@ -2624,7 +2644,7 @@ 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);
+		arch__fix_tev_from_maps(pev, tev, map, sym);
 	}
 	if (ret == skipped) {
 		ret = -ENOENT;
@@ -2743,9 +2763,13 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev,
 {
 	int ret;
 
-	if (pev->uprobes && !pev->group) {
-		/* Replace group name if not given */
-		ret = convert_exec_to_group(pev->target, &pev->group);
+	if (!pev->group) {
+		/* Set group name if not given */
+		if (!pev->uprobes) {
+			pev->group = strdup(PERFPROBE_GROUP);
+			ret = pev->group ? 0 : -ENOMEM;
+		} else
+			ret = convert_exec_to_group(pev->target, &pev->group);
 		if (ret != 0) {
 			pr_warning("Failed to make a group name.\n");
 			return ret;
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index e54e7b011577..5a27eb4fad05 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -120,7 +120,7 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev);
 /* Events to command string */
 char *synthesize_perf_probe_command(struct perf_probe_event *pev);
 char *synthesize_probe_trace_command(struct probe_trace_event *tev);
-int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len);
+char *synthesize_perf_probe_arg(struct perf_probe_arg *pa);
 
 /* Check the perf_probe_event needs debuginfo */
 bool perf_probe_event_need_dwarf(struct perf_probe_event *pev);
@@ -154,7 +154,8 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
 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);
+			     struct probe_trace_event *tev, struct map *map,
+			     struct symbol *sym);
 
 /* If there is no space to write, returns -E2BIG. */
 int e_snprintf(char *str, size_t size, const char *format, ...)
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index e3b3b92e4458..3fe6214970e6 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -220,8 +220,7 @@ int probe_file__add_event(int fd, struct probe_trace_event *tev)
 
 	pr_debug("Writing event: %s\n", buf);
 	if (!probe_event_dry_run) {
-		ret = write(fd, buf, strlen(buf));
-		if (ret <= 0) {
+		if (write(fd, buf, strlen(buf)) < (int)strlen(buf)) {
 			ret = -errno;
 			pr_warning("Failed to write event: %s\n",
 				   strerror_r(errno, sbuf, sizeof(sbuf)));
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index b3bd0fba0237..1259839dbf6d 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -553,7 +553,7 @@ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
 static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf)
 {
 	Dwarf_Die vr_die;
-	char buf[32], *ptr;
+	char *buf, *ptr;
 	int ret = 0;
 
 	/* Copy raw parameters */
@@ -563,13 +563,13 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf)
 	if (pf->pvar->name)
 		pf->tvar->name = strdup(pf->pvar->name);
 	else {
-		ret = synthesize_perf_probe_arg(pf->pvar, buf, 32);
-		if (ret < 0)
-			return ret;
+		buf = synthesize_perf_probe_arg(pf->pvar);
+		if (!buf)
+			return -ENOMEM;
 		ptr = strchr(buf, ':');	/* Change type separator to _ */
 		if (ptr)
 			*ptr = '_';
-		pf->tvar->name = strdup(buf);
+		pf->tvar->name = buf;
 	}
 	if (pf->tvar->name == NULL)
 		return -ENOMEM;
@@ -1294,6 +1294,7 @@ static int collect_variables_cb(Dwarf_Die *die_mem, void *data)
 {
 	struct available_var_finder *af = data;
 	struct variable_list *vl;
+	struct strbuf buf = STRBUF_INIT;
 	int tag, ret;
 
 	vl = &af->vls[af->nvls - 1];
@@ -1307,25 +1308,26 @@ static int collect_variables_cb(Dwarf_Die *die_mem, void *data)
 		if (ret == 0 || ret == -ERANGE) {
 			int ret2;
 			bool externs = !af->child;
-			struct strbuf buf;
 
-			strbuf_init(&buf, 64);
+			if (strbuf_init(&buf, 64) < 0)
+				goto error;
 
 			if (probe_conf.show_location_range) {
-				if (!externs) {
-					if (ret)
-						strbuf_add(&buf, "[INV]\t", 6);
-					else
-						strbuf_add(&buf, "[VAL]\t", 6);
-				} else
-					strbuf_add(&buf, "[EXT]\t", 6);
+				if (!externs)
+					ret2 = strbuf_add(&buf,
+						ret ? "[INV]\t" : "[VAL]\t", 6);
+				else
+					ret2 = strbuf_add(&buf, "[EXT]\t", 6);
+				if (ret2)
+					goto error;
 			}
 
 			ret2 = die_get_varname(die_mem, &buf);
 
 			if (!ret2 && probe_conf.show_location_range &&
 				!externs) {
-				strbuf_addch(&buf, '\t');
+				if (strbuf_addch(&buf, '\t') < 0)
+					goto error;
 				ret2 = die_get_var_range(&af->pf.sp_die,
 							die_mem, &buf);
 			}
@@ -1343,6 +1345,10 @@ static int collect_variables_cb(Dwarf_Die *die_mem, void *data)
 		return DIE_FIND_CB_CONTINUE;
 	else
 		return DIE_FIND_CB_SIBLING;
+error:
+	strbuf_release(&buf);
+	pr_debug("Error in strbuf\n");
+	return DIE_FIND_CB_END;
 }
 
 /* Add a found vars into available variables list */
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 8162ba0e2e57..36c6862119e3 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -23,3 +23,4 @@ util/strlist.c
 util/trace-event.c
 ../lib/rbtree.c
 util/string.c
+util/symbol_fprintf.c
diff --git a/tools/perf/util/quote.c b/tools/perf/util/quote.c
index 01f03242b86a..c6d4ee2de752 100644
--- a/tools/perf/util/quote.c
+++ b/tools/perf/util/quote.c
@@ -17,38 +17,42 @@ static inline int need_bs_quote(char c)
 	return (c == '\'' || c == '!');
 }
 
-static void sq_quote_buf(struct strbuf *dst, const char *src)
+static int sq_quote_buf(struct strbuf *dst, const char *src)
 {
 	char *to_free = NULL;
+	int ret;
 
 	if (dst->buf == src)
 		to_free = strbuf_detach(dst, NULL);
 
-	strbuf_addch(dst, '\'');
-	while (*src) {
+	ret = strbuf_addch(dst, '\'');
+	while (!ret && *src) {
 		size_t len = strcspn(src, "'!");
-		strbuf_add(dst, src, len);
+		ret = strbuf_add(dst, src, len);
 		src += len;
-		while (need_bs_quote(*src)) {
-			strbuf_addstr(dst, "'\\");
-			strbuf_addch(dst, *src++);
-			strbuf_addch(dst, '\'');
-		}
+		while (!ret && need_bs_quote(*src))
+			ret = strbuf_addf(dst, "'\\%c\'", *src++);
 	}
-	strbuf_addch(dst, '\'');
+	if (!ret)
+		ret = strbuf_addch(dst, '\'');
 	free(to_free);
+
+	return ret;
 }
 
-void sq_quote_argv(struct strbuf *dst, const char** argv, size_t maxlen)
+int sq_quote_argv(struct strbuf *dst, const char** argv, size_t maxlen)
 {
-	int i;
+	int i, ret;
 
 	/* Copy into destination buffer. */
-	strbuf_grow(dst, 255);
-	for (i = 0; argv[i]; ++i) {
-		strbuf_addch(dst, ' ');
-		sq_quote_buf(dst, argv[i]);
+	ret = strbuf_grow(dst, 255);
+	for (i = 0; !ret && argv[i]; ++i) {
+		ret = strbuf_addch(dst, ' ');
+		if (ret)
+			break;
+		ret = sq_quote_buf(dst, argv[i]);
 		if (maxlen && dst->len > maxlen)
 			die("Too many or long arguments");
 	}
+	return ret;
 }
diff --git a/tools/perf/util/quote.h b/tools/perf/util/quote.h
index 3340c9c4a6ca..e1ec19146fb0 100644
--- a/tools/perf/util/quote.h
+++ b/tools/perf/util/quote.h
@@ -24,6 +24,6 @@
  * sq_quote() in a real application.
  */
 
-void sq_quote_argv(struct strbuf *, const char **argv, size_t maxlen);
+int sq_quote_argv(struct strbuf *, const char **argv, size_t maxlen);
 
 #endif /* __PERF_QUOTE_H */
diff --git a/tools/perf/util/rb_resort.h b/tools/perf/util/rb_resort.h
new file mode 100644
index 000000000000..abc76e3d3098
--- /dev/null
+++ b/tools/perf/util/rb_resort.h
@@ -0,0 +1,149 @@
+#ifndef _PERF_RESORT_RB_H_
+#define _PERF_RESORT_RB_H_
+/*
+ * Template for creating a class to resort an existing rb_tree according to
+ * a new sort criteria, that must be present in the entries of the source
+ * rb_tree.
+ *
+ * (c) 2016 Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Quick example, resorting threads by its shortname:
+ *
+ * First define the prefix (threads) to be used for the functions and data
+ * structures created, and provide an expression for the sorting, then the
+ * fields to be present in each of the entries in the new, sorted, rb_tree.
+ *
+ * The body of the init function should collect the fields, maybe
+ * pre-calculating them from multiple entries in the original 'entry' from
+ * the rb_tree used as a source for the entries to be sorted:
+
+DEFINE_RB_RESORT_RB(threads, strcmp(a->thread->shortname,
+				    b->thread->shortname) < 0,
+	struct thread *thread;
+)
+{
+	entry->thread = rb_entry(nd, struct thread, rb_node);
+}
+
+ * After this it is just a matter of instantiating it and iterating it,
+ * for a few data structures with existing rb_trees, such as 'struct machine',
+ * helpers are available to get the rb_root and the nr_entries:
+
+	DECLARE_RESORT_RB_MACHINE_THREADS(threads, machine_ptr);
+
+ * This will instantiate the new rb_tree and a cursor for it, that can be used as:
+
+	struct rb_node *nd;
+
+	resort_rb__for_each(nd, threads) {
+		struct thread *t = threads_entry;
+		printf("%s: %d\n", t->shortname, t->tid);
+	}
+
+ * Then delete it:
+
+	resort_rb__delete(threads);
+
+ * The name of the data structures and functions will have a _sorted suffix
+ * right before the method names, i.e. will look like:
+ *
+ * 	struct threads_sorted_entry {}
+ * 	threads_sorted__insert()
+ */
+
+#define DEFINE_RESORT_RB(__name, __comp, ...)					\
+struct __name##_sorted_entry {							\
+	struct rb_node	rb_node;						\
+	__VA_ARGS__								\
+};										\
+static void __name##_sorted__init_entry(struct rb_node *nd,			\
+					struct __name##_sorted_entry *entry);	\
+										\
+static int __name##_sorted__cmp(struct rb_node *nda, struct rb_node *ndb)	\
+{										\
+	struct __name##_sorted_entry *a, *b;					\
+	a = rb_entry(nda, struct __name##_sorted_entry, rb_node);		\
+	b = rb_entry(ndb, struct __name##_sorted_entry, rb_node);		\
+	return __comp;								\
+}										\
+										\
+struct __name##_sorted {							\
+       struct rb_root		    entries;					\
+       struct __name##_sorted_entry nd[0];					\
+};										\
+										\
+static void __name##_sorted__insert(struct __name##_sorted *sorted,		\
+				      struct rb_node *sorted_nd)		\
+{										\
+	struct rb_node **p = &sorted->entries.rb_node, *parent = NULL;		\
+	while (*p != NULL) {							\
+		parent = *p;							\
+		if (__name##_sorted__cmp(sorted_nd, parent))			\
+			p = &(*p)->rb_left;					\
+		else								\
+			p = &(*p)->rb_right;					\
+	}									\
+	rb_link_node(sorted_nd, parent, p);					\
+	rb_insert_color(sorted_nd, &sorted->entries);				\
+}										\
+										\
+static void __name##_sorted__sort(struct __name##_sorted *sorted,		\
+				    struct rb_root *entries)			\
+{										\
+	struct rb_node *nd;							\
+	unsigned int i = 0;							\
+	for (nd = rb_first(entries); nd; nd = rb_next(nd)) {			\
+		struct __name##_sorted_entry *snd = &sorted->nd[i++];		\
+		__name##_sorted__init_entry(nd, snd);				\
+		__name##_sorted__insert(sorted, &snd->rb_node);			\
+	}									\
+}										\
+										\
+static struct __name##_sorted *__name##_sorted__new(struct rb_root *entries,	\
+						    int nr_entries)		\
+{										\
+	struct __name##_sorted *sorted;						\
+	sorted = malloc(sizeof(*sorted) + sizeof(sorted->nd[0]) * nr_entries);	\
+	if (sorted) {								\
+		sorted->entries = RB_ROOT;					\
+		__name##_sorted__sort(sorted, entries);				\
+	}									\
+	return sorted;								\
+}										\
+										\
+static void __name##_sorted__delete(struct __name##_sorted *sorted)		\
+{										\
+	free(sorted);								\
+}										\
+										\
+static void __name##_sorted__init_entry(struct rb_node *nd,			\
+					struct __name##_sorted_entry *entry)
+
+#define DECLARE_RESORT_RB(__name)						\
+struct __name##_sorted_entry *__name##_entry;					\
+struct __name##_sorted *__name = __name##_sorted__new
+
+#define resort_rb__for_each(__nd, __name)					\
+	for (__nd = rb_first(&__name->entries);					\
+	     __name##_entry = rb_entry(__nd, struct __name##_sorted_entry,	\
+				       rb_node), __nd;				\
+	     __nd = rb_next(__nd))
+
+#define resort_rb__delete(__name)						\
+	__name##_sorted__delete(__name), __name = NULL
+
+/*
+ * Helpers for other classes that contains both an rbtree and the
+ * number of entries in it:
+ */
+
+/* For 'struct intlist' */
+#define DECLARE_RESORT_RB_INTLIST(__name, __ilist)				\
+	DECLARE_RESORT_RB(__name)(&__ilist->rblist.entries,			\
+				  __ilist->rblist.nr_entries)
+
+/* For 'struct machine->threads' */
+#define DECLARE_RESORT_RB_MACHINE_THREADS(__name, __machine)			\
+	DECLARE_RESORT_RB(__name)(&__machine->threads, __machine->nr_threads)
+
+#endif /* _PERF_RESORT_RB_H_ */
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 0467367dc315..481792c7484b 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -129,7 +129,8 @@ bool perf_can_record_cpu_wide(void)
 	return true;
 }
 
-void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
+void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts,
+			 struct callchain_param *callchain)
 {
 	struct perf_evsel *evsel;
 	bool use_sample_identifier = false;
@@ -148,7 +149,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
 	use_comm_exec = perf_can_comm_exec();
 
 	evlist__for_each(evlist, evsel) {
-		perf_evsel__config(evsel, opts);
+		perf_evsel__config(evsel, opts, callchain);
 		if (evsel->tracking && use_comm_exec)
 			evsel->attr.comm_exec = 1;
 	}
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index b3aabc0d4eb0..62c7f6988e0e 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -31,6 +31,8 @@
 #include <perl.h>
 
 #include "../../perf.h"
+#include "../callchain.h"
+#include "../machine.h"
 #include "../thread.h"
 #include "../event.h"
 #include "../trace-event.h"
@@ -248,10 +250,90 @@ static void define_event_symbols(struct event_format *event,
 		define_event_symbols(event, ev_name, args->next);
 }
 
+static SV *perl_process_callchain(struct perf_sample *sample,
+				  struct perf_evsel *evsel,
+				  struct addr_location *al)
+{
+	AV *list;
+
+	list = newAV();
+	if (!list)
+		goto exit;
+
+	if (!symbol_conf.use_callchain || !sample->callchain)
+		goto exit;
+
+	if (thread__resolve_callchain(al->thread, &callchain_cursor, evsel,
+				      sample, NULL, NULL,
+				      sysctl_perf_event_max_stack) != 0) {
+		pr_err("Failed to resolve callchain. Skipping\n");
+		goto exit;
+	}
+	callchain_cursor_commit(&callchain_cursor);
+
+
+	while (1) {
+		HV *elem;
+		struct callchain_cursor_node *node;
+		node = callchain_cursor_current(&callchain_cursor);
+		if (!node)
+			break;
+
+		elem = newHV();
+		if (!elem)
+			goto exit;
+
+		if (!hv_stores(elem, "ip", newSVuv(node->ip))) {
+			hv_undef(elem);
+			goto exit;
+		}
+
+		if (node->sym) {
+			HV *sym = newHV();
+			if (!sym) {
+				hv_undef(elem);
+				goto exit;
+			}
+			if (!hv_stores(sym, "start",   newSVuv(node->sym->start)) ||
+			    !hv_stores(sym, "end",     newSVuv(node->sym->end)) ||
+			    !hv_stores(sym, "binding", newSVuv(node->sym->binding)) ||
+			    !hv_stores(sym, "name",    newSVpvn(node->sym->name,
+								node->sym->namelen)) ||
+			    !hv_stores(elem, "sym",    newRV_noinc((SV*)sym))) {
+				hv_undef(sym);
+				hv_undef(elem);
+				goto exit;
+			}
+		}
+
+		if (node->map) {
+			struct map *map = node->map;
+			const char *dsoname = "[unknown]";
+			if (map && map->dso && (map->dso->name || map->dso->long_name)) {
+				if (symbol_conf.show_kernel_path && map->dso->long_name)
+					dsoname = map->dso->long_name;
+				else if (map->dso->name)
+					dsoname = map->dso->name;
+			}
+			if (!hv_stores(elem, "dso", newSVpv(dsoname,0))) {
+				hv_undef(elem);
+				goto exit;
+			}
+		}
+
+		callchain_cursor_advance(&callchain_cursor);
+		av_push(list, newRV_noinc((SV*)elem));
+	}
+
+exit:
+	return newRV_noinc((SV*)list);
+}
+
 static void perl_process_tracepoint(struct perf_sample *sample,
 				    struct perf_evsel *evsel,
-				    struct thread *thread)
+				    struct addr_location *al)
 {
+	struct thread *thread = al->thread;
 	struct event_format *event = evsel->tp_format;
 	struct format_field *field;
 	static char handler[256];
@@ -295,6 +377,7 @@ static void perl_process_tracepoint(struct perf_sample *sample,
 	XPUSHs(sv_2mortal(newSVuv(ns)));
 	XPUSHs(sv_2mortal(newSViv(pid)));
 	XPUSHs(sv_2mortal(newSVpv(comm, 0)));
+	XPUSHs(sv_2mortal(perl_process_callchain(sample, evsel, al)));
 
 	/* common fields other than pid can be accessed via xsub fns */
 
@@ -329,6 +412,7 @@ static void perl_process_tracepoint(struct perf_sample *sample,
 		XPUSHs(sv_2mortal(newSVuv(nsecs)));
 		XPUSHs(sv_2mortal(newSViv(pid)));
 		XPUSHs(sv_2mortal(newSVpv(comm, 0)));
+		XPUSHs(sv_2mortal(perl_process_callchain(sample, evsel, al)));
 		call_pv("main::trace_unhandled", G_SCALAR);
 	}
 	SPAGAIN;
@@ -366,7 +450,7 @@ static void perl_process_event(union perf_event *event,
 			       struct perf_evsel *evsel,
 			       struct addr_location *al)
 {
-	perl_process_tracepoint(sample, evsel, al->thread);
+	perl_process_tracepoint(sample, evsel, al);
 	perl_process_event_generic(event, sample, evsel);
 }
 
@@ -490,7 +574,27 @@ static int perl_generate_script(struct pevent *pevent, const char *outfile)
 	fprintf(ofp, "use Perf::Trace::Util;\n\n");
 
 	fprintf(ofp, "sub trace_begin\n{\n\t# optional\n}\n\n");
-	fprintf(ofp, "sub trace_end\n{\n\t# optional\n}\n\n");
+	fprintf(ofp, "sub trace_end\n{\n\t# optional\n}\n");
+
+
+	fprintf(ofp, "\n\
+sub print_backtrace\n\
+{\n\
+	my $callchain = shift;\n\
+	for my $node (@$callchain)\n\
+	{\n\
+		if(exists $node->{sym})\n\
+		{\n\
+			printf( \"\\t[\\%%x] \\%%s\\n\", $node->{ip}, $node->{sym}{name});\n\
+		}\n\
+		else\n\
+		{\n\
+			printf( \"\\t[\\%%x]\\n\", $node{ip});\n\
+		}\n\
+	}\n\
+}\n\n\
+");
+
 
 	while ((event = trace_find_next_event(pevent, event))) {
 		fprintf(ofp, "sub %s::%s\n{\n", event->system, event->name);
@@ -502,7 +606,8 @@ static int perl_generate_script(struct pevent *pevent, const char *outfile)
 		fprintf(ofp, "$common_secs, ");
 		fprintf(ofp, "$common_nsecs,\n");
 		fprintf(ofp, "\t    $common_pid, ");
-		fprintf(ofp, "$common_comm,\n\t    ");
+		fprintf(ofp, "$common_comm, ");
+		fprintf(ofp, "$common_callchain,\n\t    ");
 
 		not_first = 0;
 		count = 0;
@@ -519,7 +624,7 @@ static int perl_generate_script(struct pevent *pevent, const char *outfile)
 
 		fprintf(ofp, "\tprint_header($event_name, $common_cpu, "
 			"$common_secs, $common_nsecs,\n\t             "
-			"$common_pid, $common_comm);\n\n");
+			"$common_pid, $common_comm, $common_callchain);\n\n");
 
 		fprintf(ofp, "\tprintf(\"");
 
@@ -581,17 +686,22 @@ static int perl_generate_script(struct pevent *pevent, const char *outfile)
 				fprintf(ofp, "$%s", f->name);
 		}
 
-		fprintf(ofp, ");\n");
+		fprintf(ofp, ");\n\n");
+
+		fprintf(ofp, "\tprint_backtrace($common_callchain);\n");
+
 		fprintf(ofp, "}\n\n");
 	}
 
 	fprintf(ofp, "sub trace_unhandled\n{\n\tmy ($event_name, $context, "
 		"$common_cpu, $common_secs, $common_nsecs,\n\t    "
-		"$common_pid, $common_comm) = @_;\n\n");
+		"$common_pid, $common_comm, $common_callchain) = @_;\n\n");
 
 	fprintf(ofp, "\tprint_header($event_name, $common_cpu, "
 		"$common_secs, $common_nsecs,\n\t             $common_pid, "
-		"$common_comm);\n}\n\n");
+		"$common_comm, $common_callchain);\n");
+	fprintf(ofp, "\tprint_backtrace($common_callchain);\n");
+	fprintf(ofp, "}\n\n");
 
 	fprintf(ofp, "sub print_header\n{\n"
 		"\tmy ($event_name, $cpu, $secs, $nsecs, $pid, $comm) = @_;\n\n"
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index fbd05242b4e5..ff134700bf30 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -41,6 +41,7 @@
 #include "../thread-stack.h"
 #include "../trace-event.h"
 #include "../machine.h"
+#include "../call-path.h"
 #include "thread_map.h"
 #include "cpumap.h"
 #include "stat.h"
@@ -323,7 +324,7 @@ static PyObject *python_process_callchain(struct perf_sample *sample,
 	if (!symbol_conf.use_callchain || !sample->callchain)
 		goto exit;
 
-	if (thread__resolve_callchain(al->thread, evsel,
+	if (thread__resolve_callchain(al->thread, &callchain_cursor, evsel,
 				      sample, NULL, NULL,
 				      scripting_max_stack) != 0) {
 		pr_err("Failed to resolve callchain. Skipping\n");
@@ -407,8 +408,11 @@ static void python_process_tracepoint(struct perf_sample *sample,
 	if (!t)
 		Py_FatalError("couldn't create Python tuple");
 
-	if (!event)
-		die("ug! no event found for type %d", (int)evsel->attr.config);
+	if (!event) {
+		snprintf(handler_name, sizeof(handler_name),
+			 "ug! no event found for type %" PRIu64, (u64)evsel->attr.config);
+		Py_FatalError(handler_name);
+	}
 
 	pid = raw_field_value(event, "common_pid", data);
 
@@ -614,7 +618,7 @@ static int python_export_dso(struct db_export *dbe, struct dso *dso,
 			     struct machine *machine)
 {
 	struct tables *tables = container_of(dbe, struct tables, dbe);
-	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+	char sbuild_id[SBUILD_ID_SIZE];
 	PyObject *t;
 
 	build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
@@ -681,7 +685,7 @@ static int python_export_sample(struct db_export *dbe,
 	struct tables *tables = container_of(dbe, struct tables, dbe);
 	PyObject *t;
 
-	t = tuple_new(21);
+	t = tuple_new(22);
 
 	tuple_set_u64(t, 0, es->db_id);
 	tuple_set_u64(t, 1, es->evsel->db_id);
@@ -704,6 +708,7 @@ static int python_export_sample(struct db_export *dbe,
 	tuple_set_u64(t, 18, es->sample->data_src);
 	tuple_set_s32(t, 19, es->sample->flags & PERF_BRANCH_MASK);
 	tuple_set_s32(t, 20, !!(es->sample->flags & PERF_IP_FLAG_IN_TX));
+	tuple_set_u64(t, 21, es->call_path_id);
 
 	call_object(tables->sample_handler, t, "sample_table");
 
@@ -998,8 +1003,10 @@ static void set_table_handlers(struct tables *tables)
 {
 	const char *perf_db_export_mode = "perf_db_export_mode";
 	const char *perf_db_export_calls = "perf_db_export_calls";
-	PyObject *db_export_mode, *db_export_calls;
+	const char *perf_db_export_callchains = "perf_db_export_callchains";
+	PyObject *db_export_mode, *db_export_calls, *db_export_callchains;
 	bool export_calls = false;
+	bool export_callchains = false;
 	int ret;
 
 	memset(tables, 0, sizeof(struct tables));
@@ -1016,6 +1023,7 @@ static void set_table_handlers(struct tables *tables)
 	if (!ret)
 		return;
 
+	/* handle export calls */
 	tables->dbe.crp = NULL;
 	db_export_calls = PyDict_GetItemString(main_dict, perf_db_export_calls);
 	if (db_export_calls) {
@@ -1033,6 +1041,33 @@ static void set_table_handlers(struct tables *tables)
 			Py_FatalError("failed to create calls processor");
 	}
 
+	/* handle export callchains */
+	tables->dbe.cpr = NULL;
+	db_export_callchains = PyDict_GetItemString(main_dict,
+						    perf_db_export_callchains);
+	if (db_export_callchains) {
+		ret = PyObject_IsTrue(db_export_callchains);
+		if (ret == -1)
+			handler_call_die(perf_db_export_callchains);
+		export_callchains = !!ret;
+	}
+
+	if (export_callchains) {
+		/*
+		 * Attempt to use the call path root from the call return
+		 * processor, if the call return processor is in use. Otherwise,
+		 * we allocate a new call path root. This prevents exporting
+		 * duplicate call path ids when both are in use simultaniously.
+		 */
+		if (tables->dbe.crp)
+			tables->dbe.cpr = tables->dbe.crp->cpr;
+		else
+			tables->dbe.cpr = call_path_root__new();
+
+		if (!tables->dbe.cpr)
+			Py_FatalError("failed to create call path root");
+	}
+
 	tables->db_export_mode = true;
 	/*
 	 * Reserve per symbol space for symbol->db_id via symbol__priv()
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 4abd85c6346d..2335b2824d8a 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -409,6 +409,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		tool->stat = process_stat_stub;
 	if (tool->stat_round == NULL)
 		tool->stat_round = process_stat_round_stub;
+	if (tool->time_conv == NULL)
+		tool->time_conv = process_event_op2_stub;
 }
 
 static void swap_sample_id_all(union perf_event *event, void *data)
@@ -794,6 +796,7 @@ static perf_event__swap_op perf_event__swap_ops[] = {
 	[PERF_RECORD_STAT]		  = perf_event__stat_swap,
 	[PERF_RECORD_STAT_ROUND]	  = perf_event__stat_round_swap,
 	[PERF_RECORD_EVENT_UPDATE]	  = perf_event__event_update_swap,
+	[PERF_RECORD_TIME_CONV]		  = perf_event__all64_swap,
 	[PERF_RECORD_HEADER_MAX]	  = NULL,
 };
 
@@ -904,7 +907,7 @@ static void callchain__printf(struct perf_evsel *evsel,
 	unsigned int i;
 	struct ip_callchain *callchain = sample->callchain;
 
-	if (has_branch_callstack(evsel))
+	if (perf_evsel__has_branch_callstack(evsel))
 		callchain__lbr_callstack_printf(sample);
 
 	printf("... FP chain: nr:%" PRIu64 "\n", callchain->nr);
@@ -1078,7 +1081,7 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
 	if (sample_type & PERF_SAMPLE_CALLCHAIN)
 		callchain__printf(evsel, sample);
 
-	if ((sample_type & PERF_SAMPLE_BRANCH_STACK) && !has_branch_callstack(evsel))
+	if ((sample_type & PERF_SAMPLE_BRANCH_STACK) && !perf_evsel__has_branch_callstack(evsel))
 		branch_stack__printf(sample);
 
 	if (sample_type & PERF_SAMPLE_REGS_USER)
@@ -1341,6 +1344,9 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 		return tool->stat(tool, event, session);
 	case PERF_RECORD_STAT_ROUND:
 		return tool->stat_round(tool, event, session);
+	case PERF_RECORD_TIME_CONV:
+		session->time_conv = event->time_conv;
+		return tool->time_conv(tool, event, session);
 	default:
 		return -EINVAL;
 	}
@@ -1830,7 +1836,11 @@ out:
 out_err:
 	ui_progress__finish();
 	perf_session__warn_about_errors(session);
-	ordered_events__free(&session->ordered_events);
+	/*
+	 * We may switching perf.data output, make ordered_events
+	 * reusable.
+	 */
+	ordered_events__reinit(&session->ordered_events);
 	auxtrace__free_events(session);
 	session->one_mmap = false;
 	return err;
@@ -1947,105 +1957,6 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 	return NULL;
 }
 
-void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample,
-			  struct addr_location *al,
-			  unsigned int print_opts, unsigned int stack_depth)
-{
-	struct callchain_cursor_node *node;
-	int print_ip = print_opts & PRINT_IP_OPT_IP;
-	int print_sym = print_opts & PRINT_IP_OPT_SYM;
-	int print_dso = print_opts & PRINT_IP_OPT_DSO;
-	int print_symoffset = print_opts & PRINT_IP_OPT_SYMOFFSET;
-	int print_oneline = print_opts & PRINT_IP_OPT_ONELINE;
-	int print_srcline = print_opts & PRINT_IP_OPT_SRCLINE;
-	char s = print_oneline ? ' ' : '\t';
-
-	if (symbol_conf.use_callchain && sample->callchain) {
-		struct addr_location node_al;
-
-		if (thread__resolve_callchain(al->thread, evsel,
-					      sample, NULL, NULL,
-					      stack_depth) != 0) {
-			if (verbose)
-				error("Failed to resolve callchain. Skipping\n");
-			return;
-		}
-		callchain_cursor_commit(&callchain_cursor);
-
-		if (print_symoffset)
-			node_al = *al;
-
-		while (stack_depth) {
-			u64 addr = 0;
-
-			node = callchain_cursor_current(&callchain_cursor);
-			if (!node)
-				break;
-
-			if (node->sym && node->sym->ignore)
-				goto next;
-
-			if (print_ip)
-				printf("%c%16" PRIx64, s, node->ip);
-
-			if (node->map)
-				addr = node->map->map_ip(node->map, node->ip);
-
-			if (print_sym) {
-				printf(" ");
-				if (print_symoffset) {
-					node_al.addr = addr;
-					node_al.map  = node->map;
-					symbol__fprintf_symname_offs(node->sym, &node_al, stdout);
-				} else
-					symbol__fprintf_symname(node->sym, stdout);
-			}
-
-			if (print_dso) {
-				printf(" (");
-				map__fprintf_dsoname(node->map, stdout);
-				printf(")");
-			}
-
-			if (print_srcline)
-				map__fprintf_srcline(node->map, addr, "\n  ",
-						     stdout);
-
-			if (!print_oneline)
-				printf("\n");
-
-			stack_depth--;
-next:
-			callchain_cursor_advance(&callchain_cursor);
-		}
-
-	} else {
-		if (al->sym && al->sym->ignore)
-			return;
-
-		if (print_ip)
-			printf("%16" PRIx64, sample->ip);
-
-		if (print_sym) {
-			printf(" ");
-			if (print_symoffset)
-				symbol__fprintf_symname_offs(al->sym, al,
-							     stdout);
-			else
-				symbol__fprintf_symname(al->sym, stdout);
-		}
-
-		if (print_dso) {
-			printf(" (");
-			map__fprintf_dsoname(al->map, stdout);
-			printf(")");
-		}
-
-		if (print_srcline)
-			map__fprintf_srcline(al->map, al->addr, "\n  ", stdout);
-	}
-}
-
 int perf_session__cpu_bitmap(struct perf_session *session,
 			     const char *cpu_list, unsigned long *cpu_bitmap)
 {
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 5f792e35d4c1..4bd758553450 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -26,6 +26,7 @@ struct perf_session {
 	struct itrace_synth_opts *itrace_synth_opts;
 	struct list_head	auxtrace_index;
 	struct trace_event	tevent;
+	struct time_conv_event	time_conv;
 	bool			repipe;
 	bool			one_mmap;
 	void			*one_mmap_addr;
@@ -35,13 +36,6 @@ struct perf_session {
 	struct perf_tool	*tool;
 };
 
-#define PRINT_IP_OPT_IP		(1<<0)
-#define PRINT_IP_OPT_SYM		(1<<1)
-#define PRINT_IP_OPT_DSO		(1<<2)
-#define PRINT_IP_OPT_SYMOFFSET	(1<<3)
-#define PRINT_IP_OPT_ONELINE	(1<<4)
-#define PRINT_IP_OPT_SRCLINE	(1<<5)
-
 struct perf_tool;
 
 struct perf_session *perf_session__new(struct perf_data_file *file,
@@ -103,10 +97,6 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp);
 struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 					    unsigned int type);
 
-void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample,
-			  struct addr_location *al,
-			  unsigned int print_opts, unsigned int stack_depth);
-
 int perf_session__cpu_bitmap(struct perf_session *session,
 			     const char *cpu_list, unsigned long *cpu_bitmap);
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index f5ba111cd9fb..20e69edd5006 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -21,13 +21,6 @@ const char	*sort_order;
 const char	*field_order;
 regex_t		ignore_callees_regex;
 int		have_ignore_callees = 0;
-int		sort__need_collapse = 0;
-int		sort__has_parent = 0;
-int		sort__has_sym = 0;
-int		sort__has_dso = 0;
-int		sort__has_socket = 0;
-int		sort__has_thread = 0;
-int		sort__has_comm = 0;
 enum sort_mode	sort__mode = SORT_MODE__NORMAL;
 
 /*
@@ -244,7 +237,7 @@ sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
 	 * comparing symbol address alone is not enough since it's a
 	 * relative address within a dso.
 	 */
-	if (!sort__has_dso) {
+	if (!hists__has(left->hists, dso) || hists__has(right->hists, dso)) {
 		ret = sort__dso_cmp(left, right);
 		if (ret != 0)
 			return ret;
@@ -2163,7 +2156,7 @@ static int __sort_dimension__add(struct sort_dimension *sd,
 		return -1;
 
 	if (sd->entry->se_collapse)
-		sort__need_collapse = 1;
+		list->need_collapse = 1;
 
 	sd->taken = 1;
 
@@ -2245,9 +2238,9 @@ static int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
 				pr_err("Invalid regex: %s\n%s", parent_pattern, err);
 				return -EINVAL;
 			}
-			sort__has_parent = 1;
+			list->parent = 1;
 		} else if (sd->entry == &sort_sym) {
-			sort__has_sym = 1;
+			list->sym = 1;
 			/*
 			 * perf diff displays the performance difference amongst
 			 * two or more perf.data files. Those files could come
@@ -2258,13 +2251,13 @@ static int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
 				sd->entry->se_collapse = sort__sym_sort;
 
 		} else if (sd->entry == &sort_dso) {
-			sort__has_dso = 1;
+			list->dso = 1;
 		} else if (sd->entry == &sort_socket) {
-			sort__has_socket = 1;
+			list->socket = 1;
 		} else if (sd->entry == &sort_thread) {
-			sort__has_thread = 1;
+			list->thread = 1;
 		} else if (sd->entry == &sort_comm) {
-			sort__has_comm = 1;
+			list->comm = 1;
 		}
 
 		return __sort_dimension__add(sd, list, level);
@@ -2289,7 +2282,7 @@ static int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
 			return -EINVAL;
 
 		if (sd->entry == &sort_sym_from || sd->entry == &sort_sym_to)
-			sort__has_sym = 1;
+			list->sym = 1;
 
 		__sort_dimension__add(sd, list, level);
 		return 0;
@@ -2305,7 +2298,7 @@ static int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
 			return -EINVAL;
 
 		if (sd->entry == &sort_mem_daddr_sym)
-			sort__has_sym = 1;
+			list->sym = 1;
 
 		__sort_dimension__add(sd, list, level);
 		return 0;
@@ -2749,10 +2742,10 @@ int setup_sorting(struct perf_evlist *evlist)
 
 void reset_output_field(void)
 {
-	sort__need_collapse = 0;
-	sort__has_parent = 0;
-	sort__has_sym = 0;
-	sort__has_dso = 0;
+	perf_hpp_list.need_collapse = 0;
+	perf_hpp_list.parent = 0;
+	perf_hpp_list.sym = 0;
+	perf_hpp_list.dso = 0;
 
 	field_order = NULL;
 	sort_order = NULL;
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 3f4e35998119..42927f448bcb 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -31,13 +31,6 @@ extern const char *parent_pattern;
 extern const char default_sort_order[];
 extern regex_t ignore_callees_regex;
 extern int have_ignore_callees;
-extern int sort__need_collapse;
-extern int sort__has_dso;
-extern int sort__has_parent;
-extern int sort__has_sym;
-extern int sort__has_socket;
-extern int sort__has_thread;
-extern int sort__has_comm;
 extern enum sort_mode sort__mode;
 extern struct sort_entry sort_comm;
 extern struct sort_entry sort_dso;
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 4d9b481cf3b6..ffa1d0653861 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -307,6 +307,7 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 	struct perf_counts_values *aggr = &counter->counts->aggr;
 	struct perf_stat_evsel *ps = counter->priv;
 	u64 *count = counter->counts->aggr.values;
+	u64 val;
 	int i, ret;
 
 	aggr->val = aggr->ena = aggr->run = 0;
@@ -346,7 +347,8 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 	/*
 	 * Save the full runtime - to allow normalization during printout:
 	 */
-	perf_stat__update_shadow_stats(counter, count, 0);
+	val = counter->scale * *count;
+	perf_stat__update_shadow_stats(counter, &val, 0);
 
 	return 0;
 }
diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
index 8fb73295ec34..f95f682aa2b2 100644
--- a/tools/perf/util/strbuf.c
+++ b/tools/perf/util/strbuf.c
@@ -1,3 +1,4 @@
+#include "debug.h"
 #include "cache.h"
 #include <linux/kernel.h>
 
@@ -17,12 +18,13 @@ int prefixcmp(const char *str, const char *prefix)
  */
 char strbuf_slopbuf[1];
 
-void strbuf_init(struct strbuf *sb, ssize_t hint)
+int strbuf_init(struct strbuf *sb, ssize_t hint)
 {
 	sb->alloc = sb->len = 0;
 	sb->buf = strbuf_slopbuf;
 	if (hint)
-		strbuf_grow(sb, hint);
+		return strbuf_grow(sb, hint);
+	return 0;
 }
 
 void strbuf_release(struct strbuf *sb)
@@ -42,67 +44,104 @@ char *strbuf_detach(struct strbuf *sb, size_t *sz)
 	return res;
 }
 
-void strbuf_grow(struct strbuf *sb, size_t extra)
+int strbuf_grow(struct strbuf *sb, size_t extra)
 {
-	if (sb->len + extra + 1 <= sb->len)
-		die("you want to use way too much memory");
-	if (!sb->alloc)
-		sb->buf = NULL;
-	ALLOC_GROW(sb->buf, sb->len + extra + 1, sb->alloc);
+	char *buf;
+	size_t nr = sb->len + extra + 1;
+
+	if (nr < sb->alloc)
+		return 0;
+
+	if (nr <= sb->len)
+		return -E2BIG;
+
+	if (alloc_nr(sb->alloc) > nr)
+		nr = alloc_nr(sb->alloc);
+
+	/*
+	 * Note that sb->buf == strbuf_slopbuf if sb->alloc == 0, and it is
+	 * a static variable. Thus we have to avoid passing it to realloc.
+	 */
+	buf = realloc(sb->alloc ? sb->buf : NULL, nr * sizeof(*buf));
+	if (!buf)
+		return -ENOMEM;
+
+	sb->buf = buf;
+	sb->alloc = nr;
+	return 0;
 }
 
-void strbuf_addch(struct strbuf *sb, int c)
+int strbuf_addch(struct strbuf *sb, int c)
 {
-	strbuf_grow(sb, 1);
+	int ret = strbuf_grow(sb, 1);
+	if (ret)
+		return ret;
+
 	sb->buf[sb->len++] = c;
 	sb->buf[sb->len] = '\0';
+	return 0;
 }
 
-void strbuf_add(struct strbuf *sb, const void *data, size_t len)
+int strbuf_add(struct strbuf *sb, const void *data, size_t len)
 {
-	strbuf_grow(sb, len);
+	int ret = strbuf_grow(sb, len);
+	if (ret)
+		return ret;
+
 	memcpy(sb->buf + sb->len, data, len);
-	strbuf_setlen(sb, sb->len + len);
+	return strbuf_setlen(sb, sb->len + len);
 }
 
-static void strbuf_addv(struct strbuf *sb, const char *fmt, va_list ap)
+static int strbuf_addv(struct strbuf *sb, const char *fmt, va_list ap)
 {
-	int len;
+	int len, ret;
 	va_list ap_saved;
 
-	if (!strbuf_avail(sb))
-		strbuf_grow(sb, 64);
+	if (!strbuf_avail(sb)) {
+		ret = strbuf_grow(sb, 64);
+		if (ret)
+			return ret;
+	}
 
 	va_copy(ap_saved, ap);
 	len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap);
 	if (len < 0)
-		die("your vsnprintf is broken");
+		return len;
 	if (len > strbuf_avail(sb)) {
-		strbuf_grow(sb, len);
+		ret = strbuf_grow(sb, len);
+		if (ret)
+			return ret;
 		len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap_saved);
 		va_end(ap_saved);
 		if (len > strbuf_avail(sb)) {
-			die("this should not happen, your vsnprintf is broken");
+			pr_debug("this should not happen, your vsnprintf is broken");
+			return -EINVAL;
 		}
 	}
-	strbuf_setlen(sb, sb->len + len);
+	return strbuf_setlen(sb, sb->len + len);
 }
 
-void strbuf_addf(struct strbuf *sb, const char *fmt, ...)
+int strbuf_addf(struct strbuf *sb, const char *fmt, ...)
 {
 	va_list ap;
+	int ret;
 
 	va_start(ap, fmt);
-	strbuf_addv(sb, fmt, ap);
+	ret = strbuf_addv(sb, fmt, ap);
 	va_end(ap);
+	return ret;
 }
 
 ssize_t strbuf_read(struct strbuf *sb, int fd, ssize_t hint)
 {
 	size_t oldlen = sb->len;
 	size_t oldalloc = sb->alloc;
+	int ret;
+
+	ret = strbuf_grow(sb, hint ? hint : 8192);
+	if (ret)
+		return ret;
 
-	strbuf_grow(sb, hint ? hint : 8192);
 	for (;;) {
 		ssize_t cnt;
 
@@ -112,12 +151,14 @@ ssize_t strbuf_read(struct strbuf *sb, int fd, ssize_t hint)
 				strbuf_release(sb);
 			else
 				strbuf_setlen(sb, oldlen);
-			return -1;
+			return cnt;
 		}
 		if (!cnt)
 			break;
 		sb->len += cnt;
-		strbuf_grow(sb, 8192);
+		ret = strbuf_grow(sb, 8192);
+		if (ret)
+			return ret;
 	}
 
 	sb->buf[sb->len] = '\0';
diff --git a/tools/perf/util/strbuf.h b/tools/perf/util/strbuf.h
index ab9be0fbbd40..54b409297d4a 100644
--- a/tools/perf/util/strbuf.h
+++ b/tools/perf/util/strbuf.h
@@ -51,7 +51,7 @@ struct strbuf {
 #define STRBUF_INIT  { 0, 0, strbuf_slopbuf }
 
 /*----- strbuf life cycle -----*/
-void strbuf_init(struct strbuf *buf, ssize_t hint);
+int strbuf_init(struct strbuf *buf, ssize_t hint);
 void strbuf_release(struct strbuf *buf);
 char *strbuf_detach(struct strbuf *buf, size_t *);
 
@@ -60,26 +60,31 @@ static inline ssize_t strbuf_avail(const struct strbuf *sb) {
 	return sb->alloc ? sb->alloc - sb->len - 1 : 0;
 }
 
-void strbuf_grow(struct strbuf *buf, size_t);
+int strbuf_grow(struct strbuf *buf, size_t);
 
-static inline void strbuf_setlen(struct strbuf *sb, size_t len) {
-	if (!sb->alloc)
-		strbuf_grow(sb, 0);
+static inline int strbuf_setlen(struct strbuf *sb, size_t len) {
+	int ret;
+	if (!sb->alloc) {
+		ret = strbuf_grow(sb, 0);
+		if (ret)
+			return ret;
+	}
 	assert(len < sb->alloc);
 	sb->len = len;
 	sb->buf[len] = '\0';
+	return 0;
 }
 
 /*----- add data in your buffer -----*/
-void strbuf_addch(struct strbuf *sb, int c);
+int strbuf_addch(struct strbuf *sb, int c);
 
-void strbuf_add(struct strbuf *buf, const void *, size_t);
-static inline void strbuf_addstr(struct strbuf *sb, const char *s) {
-	strbuf_add(sb, s, strlen(s));
+int strbuf_add(struct strbuf *buf, const void *, size_t);
+static inline int strbuf_addstr(struct strbuf *sb, const char *s) {
+	return strbuf_add(sb, s, strlen(s));
 }
 
 __attribute__((format(printf,2,3)))
-void strbuf_addf(struct strbuf *sb, const char *fmt, ...);
+int strbuf_addf(struct strbuf *sb, const char *fmt, ...);
 
 /* XXX: if read fails, any partial read is undone */
 ssize_t strbuf_read(struct strbuf *, int fd, ssize_t hint);
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index bc229a74c6a9..87a297dd8901 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -709,17 +709,10 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 	if (ss->opdshdr.sh_type != SHT_PROGBITS)
 		ss->opdsec = NULL;
 
-	if (dso->kernel == DSO_TYPE_USER) {
-		GElf_Shdr shdr;
-		ss->adjust_symbols = (ehdr.e_type == ET_EXEC ||
-				ehdr.e_type == ET_REL ||
-				dso__is_vdso(dso) ||
-				elf_section_by_name(elf, &ehdr, &shdr,
-						     ".gnu.prelink_undo",
-						     NULL) != NULL);
-	} else {
+	if (dso->kernel == DSO_TYPE_USER)
+		ss->adjust_symbols = true;
+	else
 		ss->adjust_symbols = elf__needs_adjust_symbols(ehdr);
-	}
 
 	ss->name   = strdup(name);
 	if (!ss->name) {
@@ -777,7 +770,8 @@ 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) { }
+void __weak arch__sym_update(struct symbol *s __maybe_unused,
+		GElf_Sym *sym __maybe_unused) { }
 
 int dso__load_sym(struct dso *dso, struct map *map,
 		  struct symsrc *syms_ss, struct symsrc *runtime_ss,
@@ -954,8 +948,6 @@ 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];
 
@@ -1089,6 +1081,8 @@ new_symbol:
 		if (!f)
 			goto out_elf_end;
 
+		arch__sym_update(f, &sym);
+
 		if (filter && filter(curr_map, f))
 			symbol__delete(f);
 		else {
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index e7588dc91518..7fb33304fb4e 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -255,40 +255,6 @@ void symbol__delete(struct symbol *sym)
 	free(((void *)sym) - symbol_conf.priv_size);
 }
 
-size_t symbol__fprintf(struct symbol *sym, FILE *fp)
-{
-	return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %c %s\n",
-		       sym->start, sym->end,
-		       sym->binding == STB_GLOBAL ? 'g' :
-		       sym->binding == STB_LOCAL  ? 'l' : 'w',
-		       sym->name);
-}
-
-size_t symbol__fprintf_symname_offs(const struct symbol *sym,
-				    const struct addr_location *al, FILE *fp)
-{
-	unsigned long offset;
-	size_t length;
-
-	if (sym && sym->name) {
-		length = fprintf(fp, "%s", sym->name);
-		if (al) {
-			if (al->addr < sym->end)
-				offset = al->addr - sym->start;
-			else
-				offset = al->addr - al->map->start - sym->start;
-			length += fprintf(fp, "+0x%lx", offset);
-		}
-		return length;
-	} else
-		return fprintf(fp, "[unknown]");
-}
-
-size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp)
-{
-	return symbol__fprintf_symname_offs(sym, NULL, fp);
-}
-
 void symbols__delete(struct rb_root *symbols)
 {
 	struct symbol *pos;
@@ -335,7 +301,7 @@ static struct symbol *symbols__find(struct rb_root *symbols, u64 ip)
 
 		if (ip < s->start)
 			n = n->rb_left;
-		else if (ip >= s->end)
+		else if (ip > s->end || (ip == s->end && ip != s->start))
 			n = n->rb_right;
 		else
 			return s;
@@ -364,11 +330,6 @@ static struct symbol *symbols__next(struct symbol *sym)
 	return NULL;
 }
 
-struct symbol_name_rb_node {
-	struct rb_node	rb_node;
-	struct symbol	sym;
-};
-
 static void symbols__insert_by_name(struct rb_root *symbols, struct symbol *sym)
 {
 	struct rb_node **p = &symbols->rb_node;
@@ -452,6 +413,18 @@ void dso__reset_find_symbol_cache(struct dso *dso)
 	}
 }
 
+void dso__insert_symbol(struct dso *dso, enum map_type type, struct symbol *sym)
+{
+	symbols__insert(&dso->symbols[type], sym);
+
+	/* update the symbol cache if necessary */
+	if (dso->last_find_result[type].addr >= sym->start &&
+	    (dso->last_find_result[type].addr < sym->end ||
+	    sym->start == sym->end)) {
+		dso->last_find_result[type].symbol = sym;
+	}
+}
+
 struct symbol *dso__find_symbol(struct dso *dso,
 				enum map_type type, u64 addr)
 {
@@ -497,21 +470,6 @@ void dso__sort_by_name(struct dso *dso, enum map_type type)
 				     &dso->symbols[type]);
 }
 
-size_t dso__fprintf_symbols_by_name(struct dso *dso,
-				    enum map_type type, FILE *fp)
-{
-	size_t ret = 0;
-	struct rb_node *nd;
-	struct symbol_name_rb_node *pos;
-
-	for (nd = rb_first(&dso->symbol_names[type]); nd; nd = rb_next(nd)) {
-		pos = rb_entry(nd, struct symbol_name_rb_node, rb_node);
-		fprintf(fp, "%s\n", pos->sym.name);
-	}
-
-	return ret;
-}
-
 int modules__parse(const char *filename, void *arg,
 		   int (*process_module)(void *arg, const char *name,
 					 u64 start))
@@ -1262,8 +1220,8 @@ static int kallsyms__delta(struct map *map, const char *filename, u64 *delta)
 	return 0;
 }
 
-int dso__load_kallsyms(struct dso *dso, const char *filename,
-		       struct map *map, symbol_filter_t filter)
+int __dso__load_kallsyms(struct dso *dso, const char *filename,
+			 struct map *map, bool no_kcore, symbol_filter_t filter)
 {
 	u64 delta = 0;
 
@@ -1284,12 +1242,18 @@ int dso__load_kallsyms(struct dso *dso, const char *filename,
 	else
 		dso->symtab_type = DSO_BINARY_TYPE__KALLSYMS;
 
-	if (!dso__load_kcore(dso, map, filename))
+	if (!no_kcore && !dso__load_kcore(dso, map, filename))
 		return dso__split_kallsyms_for_kcore(dso, map, filter);
 	else
 		return dso__split_kallsyms(dso, map, delta, filter);
 }
 
+int dso__load_kallsyms(struct dso *dso, const char *filename,
+		       struct map *map, symbol_filter_t filter)
+{
+	return __dso__load_kallsyms(dso, filename, map, false, filter);
+}
+
 static int dso__load_perf_map(struct dso *dso, struct map *map,
 			      symbol_filter_t filter)
 {
@@ -1644,25 +1608,27 @@ out:
 	return err;
 }
 
+static bool visible_dir_filter(const char *name, struct dirent *d)
+{
+	if (d->d_type != DT_DIR)
+		return false;
+	return lsdir_no_dot_filter(name, d);
+}
+
 static int find_matching_kcore(struct map *map, char *dir, size_t dir_sz)
 {
 	char kallsyms_filename[PATH_MAX];
-	struct dirent *dent;
 	int ret = -1;
-	DIR *d;
+	struct strlist *dirs;
+	struct str_node *nd;
 
-	d = opendir(dir);
-	if (!d)
+	dirs = lsdir(dir, visible_dir_filter);
+	if (!dirs)
 		return -1;
 
-	while (1) {
-		dent = readdir(d);
-		if (!dent)
-			break;
-		if (dent->d_type != DT_DIR)
-			continue;
+	strlist__for_each(nd, dirs) {
 		scnprintf(kallsyms_filename, sizeof(kallsyms_filename),
-			  "%s/%s/kallsyms", dir, dent->d_name);
+			  "%s/%s/kallsyms", dir, nd->s);
 		if (!validate_kcore_addresses(kallsyms_filename, map)) {
 			strlcpy(dir, kallsyms_filename, dir_sz);
 			ret = 0;
@@ -1670,7 +1636,7 @@ static int find_matching_kcore(struct map *map, char *dir, size_t dir_sz)
 		}
 	}
 
-	closedir(d);
+	strlist__delete(dirs);
 
 	return ret;
 }
@@ -1678,7 +1644,7 @@ static int find_matching_kcore(struct map *map, char *dir, size_t dir_sz)
 static char *dso__find_kallsyms(struct dso *dso, struct map *map)
 {
 	u8 host_build_id[BUILD_ID_SIZE];
-	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+	char sbuild_id[SBUILD_ID_SIZE];
 	bool is_host = false;
 	char path[PATH_MAX];
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index c8b7544d9267..2b5e4ed76fcb 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -55,6 +55,7 @@ struct symbol {
 	u16		namelen;
 	u8		binding;
 	bool		ignore;
+	u8		arch_sym;
 	char		name[0];
 };
 
@@ -140,6 +141,11 @@ struct symbol_conf {
 
 extern struct symbol_conf symbol_conf;
 
+struct symbol_name_rb_node {
+	struct rb_node	rb_node;
+	struct symbol	sym;
+};
+
 static inline int __symbol__join_symfs(char *bf, size_t size, const char *path)
 {
 	return path__join(bf, size, symbol_conf.symfs, path);
@@ -235,9 +241,14 @@ int dso__load_vmlinux(struct dso *dso, struct map *map,
 		      symbol_filter_t filter);
 int dso__load_vmlinux_path(struct dso *dso, struct map *map,
 			   symbol_filter_t filter);
+int __dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map,
+			 bool no_kcore, symbol_filter_t filter);
 int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map,
 		       symbol_filter_t filter);
 
+void dso__insert_symbol(struct dso *dso, enum map_type type,
+			struct symbol *sym);
+
 struct symbol *dso__find_symbol(struct dso *dso, enum map_type type,
 				u64 addr);
 struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
@@ -262,8 +273,14 @@ int symbol__init(struct perf_env *env);
 void symbol__exit(void);
 void symbol__elf_init(void);
 struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name);
+size_t __symbol__fprintf_symname_offs(const struct symbol *sym,
+				      const struct addr_location *al,
+				      bool unknown_as_addr, FILE *fp);
 size_t symbol__fprintf_symname_offs(const struct symbol *sym,
 				    const struct addr_location *al, FILE *fp);
+size_t __symbol__fprintf_symname(const struct symbol *sym,
+				 const struct addr_location *al,
+				 bool unknown_as_addr, FILE *fp);
 size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp);
 size_t symbol__fprintf(struct symbol *sym, FILE *fp);
 bool symbol_type__is_a(char symbol_type, enum map_type map_type);
@@ -310,7 +327,7 @@ int setup_intlist(struct intlist **list, const char *list_str,
 
 #ifdef HAVE_LIBELF_SUPPORT
 bool elf__needs_adjust_symbols(GElf_Ehdr ehdr);
-void arch__elf_sym_adjust(GElf_Sym *sym);
+void arch__sym_update(struct symbol *s, GElf_Sym *sym);
 #endif
 
 #define SYMBOL_A 0
diff --git a/tools/perf/util/symbol_fprintf.c b/tools/perf/util/symbol_fprintf.c
new file mode 100644
index 000000000000..a680bdaa65dc
--- /dev/null
+++ b/tools/perf/util/symbol_fprintf.c
@@ -0,0 +1,71 @@
+#include <elf.h>
+#include <inttypes.h>
+#include <stdio.h>
+
+#include "symbol.h"
+
+size_t symbol__fprintf(struct symbol *sym, FILE *fp)
+{
+	return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %c %s\n",
+		       sym->start, sym->end,
+		       sym->binding == STB_GLOBAL ? 'g' :
+		       sym->binding == STB_LOCAL  ? 'l' : 'w',
+		       sym->name);
+}
+
+size_t __symbol__fprintf_symname_offs(const struct symbol *sym,
+				      const struct addr_location *al,
+				      bool unknown_as_addr, FILE *fp)
+{
+	unsigned long offset;
+	size_t length;
+
+	if (sym && sym->name) {
+		length = fprintf(fp, "%s", sym->name);
+		if (al) {
+			if (al->addr < sym->end)
+				offset = al->addr - sym->start;
+			else
+				offset = al->addr - al->map->start - sym->start;
+			length += fprintf(fp, "+0x%lx", offset);
+		}
+		return length;
+	} else if (al && unknown_as_addr)
+		return fprintf(fp, "[%#" PRIx64 "]", al->addr);
+	else
+		return fprintf(fp, "[unknown]");
+}
+
+size_t symbol__fprintf_symname_offs(const struct symbol *sym,
+				    const struct addr_location *al,
+				    FILE *fp)
+{
+	return __symbol__fprintf_symname_offs(sym, al, false, fp);
+}
+
+size_t __symbol__fprintf_symname(const struct symbol *sym,
+				 const struct addr_location *al,
+				 bool unknown_as_addr, FILE *fp)
+{
+	return __symbol__fprintf_symname_offs(sym, al, unknown_as_addr, fp);
+}
+
+size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp)
+{
+	return __symbol__fprintf_symname_offs(sym, NULL, false, fp);
+}
+
+size_t dso__fprintf_symbols_by_name(struct dso *dso,
+				    enum map_type type, FILE *fp)
+{
+	size_t ret = 0;
+	struct rb_node *nd;
+	struct symbol_name_rb_node *pos;
+
+	for (nd = rb_first(&dso->symbol_names[type]); nd; nd = rb_next(nd)) {
+		pos = rb_entry(nd, struct symbol_name_rb_node, rb_node);
+		fprintf(fp, "%s\n", pos->sym.name);
+	}
+
+	return ret;
+}
diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c
new file mode 100644
index 000000000000..bbb4c1957578
--- /dev/null
+++ b/tools/perf/util/syscalltbl.c
@@ -0,0 +1,134 @@
+/*
+ * System call table mapper
+ *
+ * (C) 2016 Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * 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 "syscalltbl.h"
+#include <stdlib.h>
+
+#ifdef HAVE_SYSCALL_TABLE
+#include <linux/compiler.h>
+#include <string.h>
+#include "util.h"
+
+#if defined(__x86_64__)
+#include <asm/syscalls_64.c>
+const int syscalltbl_native_max_id = SYSCALLTBL_x86_64_MAX_ID;
+static const char **syscalltbl_native = syscalltbl_x86_64;
+#endif
+
+struct syscall {
+	int id;
+	const char *name;
+};
+
+static int syscallcmpname(const void *vkey, const void *ventry)
+{
+	const char *key = vkey;
+	const struct syscall *entry = ventry;
+
+	return strcmp(key, entry->name);
+}
+
+static int syscallcmp(const void *va, const void *vb)
+{
+	const struct syscall *a = va, *b = vb;
+
+	return strcmp(a->name, b->name);
+}
+
+static int syscalltbl__init_native(struct syscalltbl *tbl)
+{
+	int nr_entries = 0, i, j;
+	struct syscall *entries;
+
+	for (i = 0; i <= syscalltbl_native_max_id; ++i)
+		if (syscalltbl_native[i])
+			++nr_entries;
+
+	entries = tbl->syscalls.entries = malloc(sizeof(struct syscall) * nr_entries);
+	if (tbl->syscalls.entries == NULL)
+		return -1;
+
+	for (i = 0, j = 0; i <= syscalltbl_native_max_id; ++i) {
+		if (syscalltbl_native[i]) {
+			entries[j].name = syscalltbl_native[i];
+			entries[j].id = i;
+			++j;
+		}
+	}
+
+	qsort(tbl->syscalls.entries, nr_entries, sizeof(struct syscall), syscallcmp);
+	tbl->syscalls.nr_entries = nr_entries;
+	return 0;
+}
+
+struct syscalltbl *syscalltbl__new(void)
+{
+	struct syscalltbl *tbl = malloc(sizeof(*tbl));
+	if (tbl) {
+		if (syscalltbl__init_native(tbl)) {
+			free(tbl);
+			return NULL;
+		}
+	}
+	return tbl;
+}
+
+void syscalltbl__delete(struct syscalltbl *tbl)
+{
+	zfree(&tbl->syscalls.entries);
+	free(tbl);
+}
+
+const char *syscalltbl__name(const struct syscalltbl *tbl __maybe_unused, int id)
+{
+	return id <= syscalltbl_native_max_id ? syscalltbl_native[id]: NULL;
+}
+
+int syscalltbl__id(struct syscalltbl *tbl, const char *name)
+{
+	struct syscall *sc = bsearch(name, tbl->syscalls.entries,
+				     tbl->syscalls.nr_entries, sizeof(*sc),
+				     syscallcmpname);
+
+	return sc ? sc->id : -1;
+}
+
+#else /* HAVE_SYSCALL_TABLE */
+
+#include <libaudit.h>
+
+struct syscalltbl *syscalltbl__new(void)
+{
+	struct syscalltbl *tbl = malloc(sizeof(*tbl));
+	if (tbl)
+		tbl->audit_machine = audit_detect_machine();
+	return tbl;
+}
+
+void syscalltbl__delete(struct syscalltbl *tbl)
+{
+	free(tbl);
+}
+
+const char *syscalltbl__name(const struct syscalltbl *tbl, int id)
+{
+	return audit_syscall_to_name(id, tbl->audit_machine);
+}
+
+int syscalltbl__id(struct syscalltbl *tbl, const char *name)
+{
+	return audit_name_to_syscall(name, tbl->audit_machine);
+}
+#endif /* HAVE_SYSCALL_TABLE */
diff --git a/tools/perf/util/syscalltbl.h b/tools/perf/util/syscalltbl.h
new file mode 100644
index 000000000000..e2951510484f
--- /dev/null
+++ b/tools/perf/util/syscalltbl.h
@@ -0,0 +1,20 @@
+#ifndef __PERF_SYSCALLTBL_H
+#define __PERF_SYSCALLTBL_H
+
+struct syscalltbl {
+	union {
+		int audit_machine;
+		struct {
+			int nr_entries;
+			void *entries;
+		} syscalls;
+	};
+};
+
+struct syscalltbl *syscalltbl__new(void);
+void syscalltbl__delete(struct syscalltbl *tbl);
+
+const char *syscalltbl__name(const struct syscalltbl *tbl, int id);
+int syscalltbl__id(struct syscalltbl *tbl, const char *name);
+
+#endif /* __PERF_SYSCALLTBL_H */
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index 679688e70ae7..825086aa9a08 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -22,44 +22,9 @@
 #include "debug.h"
 #include "symbol.h"
 #include "comm.h"
+#include "call-path.h"
 #include "thread-stack.h"
 
-#define CALL_PATH_BLOCK_SHIFT 8
-#define CALL_PATH_BLOCK_SIZE (1 << CALL_PATH_BLOCK_SHIFT)
-#define CALL_PATH_BLOCK_MASK (CALL_PATH_BLOCK_SIZE - 1)
-
-struct call_path_block {
-	struct call_path cp[CALL_PATH_BLOCK_SIZE];
-	struct list_head node;
-};
-
-/**
- * struct call_path_root - root of all call paths.
- * @call_path: root call path
- * @blocks: list of blocks to store call paths
- * @next: next free space
- * @sz: number of spaces
- */
-struct call_path_root {
-	struct call_path call_path;
-	struct list_head blocks;
-	size_t next;
-	size_t sz;
-};
-
-/**
- * struct call_return_processor - provides a call-back to consume call-return
- *                                information.
- * @cpr: call path root
- * @process: call-back that accepts call/return information
- * @data: anonymous data for call-back
- */
-struct call_return_processor {
-	struct call_path_root *cpr;
-	int (*process)(struct call_return *cr, void *data);
-	void *data;
-};
-
 #define STACK_GROWTH 2048
 
 /**
@@ -335,108 +300,6 @@ void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
 		chain->ips[i] = thread->ts->stack[thread->ts->cnt - i].ret_addr;
 }
 
-static void call_path__init(struct call_path *cp, struct call_path *parent,
-			    struct symbol *sym, u64 ip, bool in_kernel)
-{
-	cp->parent = parent;
-	cp->sym = sym;
-	cp->ip = sym ? 0 : ip;
-	cp->db_id = 0;
-	cp->in_kernel = in_kernel;
-	RB_CLEAR_NODE(&cp->rb_node);
-	cp->children = RB_ROOT;
-}
-
-static struct call_path_root *call_path_root__new(void)
-{
-	struct call_path_root *cpr;
-
-	cpr = zalloc(sizeof(struct call_path_root));
-	if (!cpr)
-		return NULL;
-	call_path__init(&cpr->call_path, NULL, NULL, 0, false);
-	INIT_LIST_HEAD(&cpr->blocks);
-	return cpr;
-}
-
-static void call_path_root__free(struct call_path_root *cpr)
-{
-	struct call_path_block *pos, *n;
-
-	list_for_each_entry_safe(pos, n, &cpr->blocks, node) {
-		list_del(&pos->node);
-		free(pos);
-	}
-	free(cpr);
-}
-
-static struct call_path *call_path__new(struct call_path_root *cpr,
-					struct call_path *parent,
-					struct symbol *sym, u64 ip,
-					bool in_kernel)
-{
-	struct call_path_block *cpb;
-	struct call_path *cp;
-	size_t n;
-
-	if (cpr->next < cpr->sz) {
-		cpb = list_last_entry(&cpr->blocks, struct call_path_block,
-				      node);
-	} else {
-		cpb = zalloc(sizeof(struct call_path_block));
-		if (!cpb)
-			return NULL;
-		list_add_tail(&cpb->node, &cpr->blocks);
-		cpr->sz += CALL_PATH_BLOCK_SIZE;
-	}
-
-	n = cpr->next++ & CALL_PATH_BLOCK_MASK;
-	cp = &cpb->cp[n];
-
-	call_path__init(cp, parent, sym, ip, in_kernel);
-
-	return cp;
-}
-
-static struct call_path *call_path__findnew(struct call_path_root *cpr,
-					    struct call_path *parent,
-					    struct symbol *sym, u64 ip, u64 ks)
-{
-	struct rb_node **p;
-	struct rb_node *node_parent = NULL;
-	struct call_path *cp;
-	bool in_kernel = ip >= ks;
-
-	if (sym)
-		ip = 0;
-
-	if (!parent)
-		return call_path__new(cpr, parent, sym, ip, in_kernel);
-
-	p = &parent->children.rb_node;
-	while (*p != NULL) {
-		node_parent = *p;
-		cp = rb_entry(node_parent, struct call_path, rb_node);
-
-		if (cp->sym == sym && cp->ip == ip)
-			return cp;
-
-		if (sym < cp->sym || (sym == cp->sym && ip < cp->ip))
-			p = &(*p)->rb_left;
-		else
-			p = &(*p)->rb_right;
-	}
-
-	cp = call_path__new(cpr, parent, sym, ip, in_kernel);
-	if (!cp)
-		return NULL;
-
-	rb_link_node(&cp->rb_node, node_parent, p);
-	rb_insert_color(&cp->rb_node, &parent->children);
-
-	return cp;
-}
-
 struct call_return_processor *
 call_return_processor__new(int (*process)(struct call_return *cr, void *data),
 			   void *data)
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
index e1528f1374c3..ad44c7944b8e 100644
--- a/tools/perf/util/thread-stack.h
+++ b/tools/perf/util/thread-stack.h
@@ -19,17 +19,16 @@
 #include <sys/types.h>
 
 #include <linux/types.h>
-#include <linux/rbtree.h>
 
 struct thread;
 struct comm;
 struct ip_callchain;
 struct symbol;
 struct dso;
-struct call_return_processor;
 struct comm;
 struct perf_sample;
 struct addr_location;
+struct call_path;
 
 /*
  * Call/Return flags.
@@ -69,26 +68,16 @@ struct call_return {
 };
 
 /**
- * struct call_path - node in list of calls leading to a function call.
- * @parent: call path to the parent function call
- * @sym: symbol of function called
- * @ip: only if sym is null, the ip of the function
- * @db_id: id used for db-export
- * @in_kernel: whether function is a in the kernel
- * @rb_node: node in parent's tree of called functions
- * @children: tree of call paths of functions called
- *
- * In combination with the call_return structure, the call_path structure
- * defines a context-sensitve call-graph.
+ * struct call_return_processor - provides a call-back to consume call-return
+ *                                information.
+ * @cpr: call path root
+ * @process: call-back that accepts call/return information
+ * @data: anonymous data for call-back
  */
-struct call_path {
-	struct call_path *parent;
-	struct symbol *sym;
-	u64 ip;
-	u64 db_id;
-	bool in_kernel;
-	struct rb_node rb_node;
-	struct rb_root children;
+struct call_return_processor {
+	struct call_path_root *cpr;
+	int (*process)(struct call_return *cr, void *data);
+	void *data;
 };
 
 int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index dfd00c6dad6e..45fcb715a36b 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -10,6 +10,8 @@
 #include "comm.h"
 #include "unwind.h"
 
+#include <api/fs/fs.h>
+
 int thread__init_map_groups(struct thread *thread, struct machine *machine)
 {
 	struct thread *leader;
@@ -153,6 +155,23 @@ int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp,
 	return 0;
 }
 
+int thread__set_comm_from_proc(struct thread *thread)
+{
+	char path[64];
+	char *comm = NULL;
+	size_t sz;
+	int err = -1;
+
+	if (!(snprintf(path, sizeof(path), "%d/task/%d/comm",
+		       thread->pid_, thread->tid) >= (int)sizeof(path)) &&
+	    procfs__read_str(path, &comm, &sz) == 0) {
+		comm[sz - 1] = '\0';
+		err = thread__set_comm(thread, comm, 0);
+	}
+
+	return err;
+}
+
 const char *thread__comm_str(const struct thread *thread)
 {
 	const struct comm *comm = thread__comm(thread);
@@ -233,7 +252,7 @@ void thread__find_cpumode_addr_location(struct thread *thread,
 					struct addr_location *al)
 {
 	size_t i;
-	const u8 const cpumodes[] = {
+	const u8 cpumodes[] = {
 		PERF_RECORD_MISC_USER,
 		PERF_RECORD_MISC_KERNEL,
 		PERF_RECORD_MISC_GUEST_USER,
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index a0ac0317affb..45fba13c800b 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -9,6 +9,9 @@
 #include "symbol.h"
 #include <strlist.h>
 #include <intlist.h>
+#ifdef HAVE_LIBUNWIND_SUPPORT
+#include <libunwind.h>
+#endif
 
 struct thread_stack;
 
@@ -32,6 +35,9 @@ struct thread {
 
 	void			*priv;
 	struct thread_stack	*ts;
+#ifdef HAVE_LIBUNWIND_SUPPORT
+	unw_addr_space_t	addr_space;
+#endif
 };
 
 struct machine;
@@ -65,6 +71,8 @@ static inline int thread__set_comm(struct thread *thread, const char *comm,
 	return __thread__set_comm(thread, comm, timestamp, false);
 }
 
+int thread__set_comm_from_proc(struct thread *thread);
+
 int thread__comm_len(struct thread *thread);
 struct comm *thread__comm(const struct thread *thread);
 struct comm *thread__exec_comm(const struct thread *thread);
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 267112b4e3db..5654fe15e036 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -260,7 +260,7 @@ struct thread_map *thread_map__new_dummy(void)
 	return threads;
 }
 
-static struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
+struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
 {
 	struct thread_map *threads = NULL, *nt;
 	int ntasks = 0;
@@ -436,3 +436,15 @@ struct thread_map *thread_map__new_event(struct thread_map_event *event)
 
 	return threads;
 }
+
+bool thread_map__has(struct thread_map *threads, pid_t pid)
+{
+	int i;
+
+	for (i = 0; i < threads->nr; ++i) {
+		if (threads->map[i].pid == pid)
+			return true;
+	}
+
+	return false;
+}
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index 85e4c7c4fbde..bd3b971588da 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -31,6 +31,8 @@ void thread_map__put(struct thread_map *map);
 struct thread_map *thread_map__new_str(const char *pid,
 		const char *tid, uid_t uid);
 
+struct thread_map *thread_map__new_by_tid_str(const char *tid_str);
+
 size_t thread_map__fprintf(struct thread_map *threads, FILE *fp);
 
 static inline int thread_map__nr(struct thread_map *threads)
@@ -55,4 +57,5 @@ static inline char *thread_map__comm(struct thread_map *map, int thread)
 }
 
 void thread_map__read_comms(struct thread_map *threads);
+bool thread_map__has(struct thread_map *threads, pid_t pid);
 #endif	/* __PERF_THREAD_MAP_H */
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 55de4cffcd4e..ac2590a3de2d 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -57,6 +57,7 @@ struct perf_tool {
 			id_index,
 			auxtrace_info,
 			auxtrace_error,
+			time_conv,
 			thread_map,
 			cpu_map,
 			stat_config,
diff --git a/tools/perf/util/trigger.h b/tools/perf/util/trigger.h
new file mode 100644
index 000000000000..e97d7016d771
--- /dev/null
+++ b/tools/perf/util/trigger.h
@@ -0,0 +1,94 @@
+#ifndef __TRIGGER_H_
+#define __TRIGGER_H_ 1
+
+#include "util/debug.h"
+#include "asm/bug.h"
+
+/*
+ * Use trigger to model operations which need to be executed when
+ * an event (a signal, for example) is observed.
+ *
+ * States and transits:
+ *
+ *
+ *  OFF--(on)--> READY --(hit)--> HIT
+ *                 ^               |
+ *                 |            (ready)
+ *                 |               |
+ *                  \_____________/
+ *
+ * is_hit and is_ready are two key functions to query the state of
+ * a trigger. is_hit means the event already happen; is_ready means the
+ * trigger is waiting for the event.
+ */
+
+struct trigger {
+	volatile enum {
+		TRIGGER_ERROR		= -2,
+		TRIGGER_OFF		= -1,
+		TRIGGER_READY		= 0,
+		TRIGGER_HIT		= 1,
+	} state;
+	const char *name;
+};
+
+#define TRIGGER_WARN_ONCE(t, exp) \
+	WARN_ONCE(t->state != exp, "trigger '%s' state transist error: %d in %s()\n", \
+		  t->name, t->state, __func__)
+
+static inline bool trigger_is_available(struct trigger *t)
+{
+	return t->state >= 0;
+}
+
+static inline bool trigger_is_error(struct trigger *t)
+{
+	return t->state <= TRIGGER_ERROR;
+}
+
+static inline void trigger_on(struct trigger *t)
+{
+	TRIGGER_WARN_ONCE(t, TRIGGER_OFF);
+	t->state = TRIGGER_READY;
+}
+
+static inline void trigger_ready(struct trigger *t)
+{
+	if (!trigger_is_available(t))
+		return;
+	t->state = TRIGGER_READY;
+}
+
+static inline void trigger_hit(struct trigger *t)
+{
+	if (!trigger_is_available(t))
+		return;
+	TRIGGER_WARN_ONCE(t, TRIGGER_READY);
+	t->state = TRIGGER_HIT;
+}
+
+static inline void trigger_off(struct trigger *t)
+{
+	if (!trigger_is_available(t))
+		return;
+	t->state = TRIGGER_OFF;
+}
+
+static inline void trigger_error(struct trigger *t)
+{
+	t->state = TRIGGER_ERROR;
+}
+
+static inline bool trigger_is_ready(struct trigger *t)
+{
+	return t->state == TRIGGER_READY;
+}
+
+static inline bool trigger_is_hit(struct trigger *t)
+{
+	return t->state == TRIGGER_HIT;
+}
+
+#define DEFINE_TRIGGER(n) \
+struct trigger n = {.state = TRIGGER_OFF, .name = #n}
+#endif
diff --git a/tools/perf/util/tsc.h b/tools/perf/util/tsc.h
index a8b78f1b3243..d5b11e2b85e0 100644
--- a/tools/perf/util/tsc.h
+++ b/tools/perf/util/tsc.h
@@ -3,10 +3,29 @@
 
 #include <linux/types.h>
 
-#include "../arch/x86/util/tsc.h"
+#include "event.h"
+
+struct perf_tsc_conversion {
+	u16 time_shift;
+	u32 time_mult;
+	u64 time_zero;
+};
+struct perf_event_mmap_page;
+
+int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
+			     struct perf_tsc_conversion *tc);
 
 u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc);
 u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc);
 u64 rdtsc(void);
 
+struct perf_event_mmap_page;
+struct perf_tool;
+struct machine;
+
+int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc,
+				struct perf_tool *tool,
+				perf_event__handler_t process,
+				struct machine *machine);
+
 #endif
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index ee7e372297e5..63687d3a344e 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -32,6 +32,7 @@
 #include "symbol.h"
 #include "util.h"
 #include "debug.h"
+#include "asm/bug.h"
 
 extern int
 UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
@@ -580,43 +581,33 @@ static unw_accessors_t accessors = {
 
 int unwind__prepare_access(struct thread *thread)
 {
-	unw_addr_space_t addr_space;
-
 	if (callchain_param.record_mode != CALLCHAIN_DWARF)
 		return 0;
 
-	addr_space = unw_create_addr_space(&accessors, 0);
-	if (!addr_space) {
+	thread->addr_space = unw_create_addr_space(&accessors, 0);
+	if (!thread->addr_space) {
 		pr_err("unwind: Can't create unwind address space.\n");
 		return -ENOMEM;
 	}
 
-	unw_set_caching_policy(addr_space, UNW_CACHE_GLOBAL);
-	thread__set_priv(thread, addr_space);
-
+	unw_set_caching_policy(thread->addr_space, UNW_CACHE_GLOBAL);
 	return 0;
 }
 
 void unwind__flush_access(struct thread *thread)
 {
-	unw_addr_space_t addr_space;
-
 	if (callchain_param.record_mode != CALLCHAIN_DWARF)
 		return;
 
-	addr_space = thread__priv(thread);
-	unw_flush_cache(addr_space, 0, 0);
+	unw_flush_cache(thread->addr_space, 0, 0);
 }
 
 void unwind__finish_access(struct thread *thread)
 {
-	unw_addr_space_t addr_space;
-
 	if (callchain_param.record_mode != CALLCHAIN_DWARF)
 		return;
 
-	addr_space = thread__priv(thread);
-	unw_destroy_addr_space(addr_space);
+	unw_destroy_addr_space(thread->addr_space);
 }
 
 static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
@@ -639,7 +630,9 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 	 * unwind itself.
 	 */
 	if (max_stack - 1 > 0) {
-		addr_space = thread__priv(ui->thread);
+		WARN_ONCE(!ui->thread, "WARNING: ui->thread is NULL");
+		addr_space = ui->thread->addr_space;
+
 		if (addr_space == NULL)
 			return -1;
 
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index b7766c577b01..eab077ad6ca9 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -33,6 +33,8 @@ struct callchain_param	callchain_param = {
 unsigned int page_size;
 int cacheline_size;
 
+unsigned int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH;
+
 bool test_attr__enabled;
 
 bool perf_host  = true;
@@ -117,6 +119,40 @@ int rm_rf(char *path)
 	return rmdir(path);
 }
 
+/* A filter which removes dot files */
+bool lsdir_no_dot_filter(const char *name __maybe_unused, struct dirent *d)
+{
+	return d->d_name[0] != '.';
+}
+
+/* lsdir reads a directory and store it in strlist */
+struct strlist *lsdir(const char *name,
+		      bool (*filter)(const char *, struct dirent *))
+{
+	struct strlist *list = NULL;
+	DIR *dir;
+	struct dirent *d;
+
+	dir = opendir(name);
+	if (!dir)
+		return NULL;
+
+	list = strlist__new(NULL, NULL);
+	if (!list) {
+		errno = ENOMEM;
+		goto out;
+	}
+
+	while ((d = readdir(dir)) != NULL) {
+		if (!filter || filter(name, d))
+			strlist__add(list, d->d_name);
+	}
+
+out:
+	closedir(dir);
+	return list;
+}
+
 static int slow_copyfile(const char *from, const char *to)
 {
 	int err = -1;
@@ -471,7 +507,6 @@ int parse_callchain_record(const char *arg, struct callchain_param *param)
 				       "needed for --call-graph fp\n");
 			break;
 
-#ifdef HAVE_DWARF_UNWIND_SUPPORT
 		/* Dwarf style */
 		} else if (!strncmp(name, "dwarf", sizeof("dwarf"))) {
 			const unsigned long default_stack_dump_size = 8192;
@@ -487,7 +522,6 @@ int parse_callchain_record(const char *arg, struct callchain_param *param)
 				ret = get_stack_size(tok, &size);
 				param->dump_size = size;
 			}
-#endif /* HAVE_DWARF_UNWIND_SUPPORT */
 		} else if (!strncmp(name, "lbr", sizeof("lbr"))) {
 			if (!strtok_r(NULL, ",", &saveptr)) {
 				param->record_mode = CALLCHAIN_LBR;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 8298d607c738..7651633a8dc7 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -79,6 +79,7 @@
 #include <termios.h>
 #include <linux/bitops.h>
 #include <termios.h>
+#include "strlist.h"
 
 extern const char *graph_line;
 extern const char *graph_dotted_line;
@@ -159,12 +160,6 @@ static inline char *gitstrchrnul(const char *s, int c)
 }
 #endif
 
-/*
- * Wrappers:
- */
-void *xrealloc(void *ptr, size_t size) __attribute__((weak));
-
-
 static inline void *zalloc(size_t size)
 {
 	return calloc(1, size);
@@ -222,6 +217,8 @@ static inline int sane_case(int x, int high)
 
 int mkdir_p(char *path, mode_t mode);
 int rm_rf(char *path);
+struct strlist *lsdir(const char *name, bool (*filter)(const char *, struct dirent *));
+bool lsdir_no_dot_filter(const char *name, struct dirent *d);
 int copyfile(const char *from, const char *to);
 int copyfile_mode(const char *from, const char *to, mode_t mode);
 int copyfile_offset(int fromfd, loff_t from_ofs, int tofd, loff_t to_ofs, u64 size);
@@ -254,11 +251,17 @@ int hex2u64(const char *ptr, u64 *val);
 char *ltrim(char *s);
 char *rtrim(char *s);
 
+static inline char *trim(char *s)
+{
+	return ltrim(rtrim(s));
+}
+
 void dump_stack(void);
 void sighandler_dump_stack(int sig);
 
 extern unsigned int page_size;
 extern int cacheline_size;
+extern unsigned int sysctl_perf_event_max_stack;
 
 struct parse_tag {
 	char tag;
diff --git a/tools/perf/util/wrapper.c b/tools/perf/util/wrapper.c
deleted file mode 100644
index 5f1a07c4b87b..000000000000
--- a/tools/perf/util/wrapper.c
+++ /dev/null
@@ -1,29 +0,0 @@
-/*
- * Various trivial helper wrappers around standard functions
- */
-#include "cache.h"
-
-/*
- * There's no pack memory to release - but stay close to the Git
- * version so wrap this away:
- */
-static inline void release_pack_memory(size_t size __maybe_unused,
-				       int flag __maybe_unused)
-{
-}
-
-void *xrealloc(void *ptr, size_t size)
-{
-	void *ret = realloc(ptr, size);
-	if (!ret && !size)
-		ret = realloc(ptr, 1);
-	if (!ret) {
-		release_pack_memory(size, -1);
-		ret = realloc(ptr, size);
-		if (!ret && !size)
-			ret = realloc(ptr, 1);
-		if (!ret)
-			die("Out of memory, realloc failed");
-	}
-	return ret;
-}